From f62fa0ced46afc541ca617d4ea9524095a4839d7 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 8 Jul 2019 14:39:32 +0200 Subject: [PATCH 001/823] habanalabs: use %pad for printing a dma_addr_t dma_addr_t might be different sizes depending on the configuration, so we cannot print it as %llx: drivers/misc/habanalabs/goya/goya.c: In function 'goya_sw_init': drivers/misc/habanalabs/goya/goya.c:698:21: error: format '%llx' expects argument of type 'long long unsigned int', but argument 4 has type 'dma_addr_t' {aka 'unsigned int'} [-Werror=format=] Use the special %pad format string. This requires passing the argument by reference. Fixes: 2a51558c8c7f ("habanalabs: remove DMA mask hack for Goya") Signed-off-by: Arnd Bergmann Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 75294ec65257..60e509f64051 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -695,8 +695,8 @@ static int goya_sw_init(struct hl_device *hdev) goto free_dma_pool; } - dev_dbg(hdev->dev, "cpu accessible memory at bus address 0x%llx\n", - hdev->cpu_accessible_dma_address); + dev_dbg(hdev->dev, "cpu accessible memory at bus address %pad\n", + &hdev->cpu_accessible_dma_address); hdev->cpu_accessible_dma_pool = gen_pool_create(ilog2(32), -1); if (!hdev->cpu_accessible_dma_pool) { From 717261e1769d443515517f101b133b28370ffb7e Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Thu, 27 Jun 2019 11:10:15 +0300 Subject: [PATCH 002/823] habanalabs: don't reset device when getting VRHOT VRHOT event from the F/W indicates the device has reached a temperature of 100 Celsius degrees. In this case, the driver should only print this information to the kernel log. The device will shutdown itself automatically when reaching 125 degrees. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 60e509f64051..1a2c062a57d4 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -4449,7 +4449,6 @@ void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry) case GOYA_ASYNC_EVENT_ID_AXI_ECC: case GOYA_ASYNC_EVENT_ID_L2_RAM_ECC: case GOYA_ASYNC_EVENT_ID_PSOC_GPIO_05_SW_RESET: - case GOYA_ASYNC_EVENT_ID_PSOC_GPIO_10_VRHOT_ICRIT: goya_print_irq_info(hdev, event_type, false); hl_device_reset(hdev, true, false); break; @@ -4485,6 +4484,7 @@ void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry) goya_unmask_irq(hdev, event_type); break; + case GOYA_ASYNC_EVENT_ID_PSOC_GPIO_10_VRHOT_ICRIT: case GOYA_ASYNC_EVENT_ID_TPC0_BMON_SPMU: case GOYA_ASYNC_EVENT_ID_TPC1_BMON_SPMU: case GOYA_ASYNC_EVENT_ID_TPC2_BMON_SPMU: From 18ec54fdd6d18d92025af097cd042a75cf0ea24c Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 8 Jul 2019 11:52:25 -0500 Subject: [PATCH 003/823] x86/speculation: Prepare entry code for Spectre v1 swapgs mitigations Spectre v1 isn't only about array bounds checks. It can affect any conditional checks. The kernel entry code interrupt, exception, and NMI handlers all have conditional swapgs checks. Those may be problematic in the context of Spectre v1, as kernel code can speculatively run with a user GS. For example: if (coming from user space) swapgs mov %gs:, %reg mov (%reg), %reg1 When coming from user space, the CPU can speculatively skip the swapgs, and then do a speculative percpu load using the user GS value. So the user can speculatively force a read of any kernel value. If a gadget exists which uses the percpu value as an address in another load/store, then the contents of the kernel value may become visible via an L1 side channel attack. A similar attack exists when coming from kernel space. The CPU can speculatively do the swapgs, causing the user GS to get used for the rest of the speculative window. The mitigation is similar to a traditional Spectre v1 mitigation, except: a) index masking isn't possible; because the index (percpu offset) isn't user-controlled; and b) an lfence is needed in both the "from user" swapgs path and the "from kernel" non-swapgs path (because of the two attacks described above). The user entry swapgs paths already have SWITCH_TO_KERNEL_CR3, which has a CR3 write when PTI is enabled. Since CR3 writes are serializing, the lfences can be skipped in those cases. On the other hand, the kernel entry swapgs paths don't depend on PTI. To avoid unnecessary lfences for the user entry case, create two separate features for alternative patching: X86_FEATURE_FENCE_SWAPGS_USER X86_FEATURE_FENCE_SWAPGS_KERNEL Use these features in entry code to patch in lfences where needed. The features aren't enabled yet, so there's no functional change. Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Reviewed-by: Dave Hansen --- arch/x86/entry/calling.h | 17 +++++++++++++++++ arch/x86/entry/entry_64.S | 21 ++++++++++++++++++--- arch/x86/include/asm/cpufeatures.h | 2 ++ 3 files changed, 37 insertions(+), 3 deletions(-) diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 9f1f9e3b8230..7ce7ac9d9d3f 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -314,6 +314,23 @@ For 32-bit we have the following conventions - kernel is built with #endif +/* + * Mitigate Spectre v1 for conditional swapgs code paths. + * + * FENCE_SWAPGS_USER_ENTRY is used in the user entry swapgs code path, to + * prevent a speculative swapgs when coming from kernel space. + * + * FENCE_SWAPGS_KERNEL_ENTRY is used in the kernel entry non-swapgs code path, + * to prevent the swapgs from getting speculatively skipped when coming from + * user space. + */ +.macro FENCE_SWAPGS_USER_ENTRY + ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_USER +.endm +.macro FENCE_SWAPGS_KERNEL_ENTRY + ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_KERNEL +.endm + .macro STACKLEAK_ERASE_NOCLOBBER #ifdef CONFIG_GCC_PLUGIN_STACKLEAK PUSH_AND_CLEAR_REGS diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index a829dd3117d0..57a0d96d6beb 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -519,7 +519,7 @@ ENTRY(interrupt_entry) testb $3, CS-ORIG_RAX+8(%rsp) jz 1f SWAPGS - + FENCE_SWAPGS_USER_ENTRY /* * Switch to the thread stack. The IRET frame and orig_ax are * on the stack, as well as the return address. RDI..R12 are @@ -549,8 +549,10 @@ ENTRY(interrupt_entry) UNWIND_HINT_FUNC movq (%rdi), %rdi + jmpq 2f 1: - + FENCE_SWAPGS_KERNEL_ENTRY +2: PUSH_AND_CLEAR_REGS save_ret=1 ENCODE_FRAME_POINTER 8 @@ -1221,6 +1223,13 @@ ENTRY(paranoid_entry) */ SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14 + /* + * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an + * unconditional CR3 write, even in the PTI case. So do an lfence + * to prevent GS speculation, regardless of whether PTI is enabled. + */ + FENCE_SWAPGS_KERNEL_ENTRY + ret END(paranoid_entry) @@ -1271,6 +1280,7 @@ ENTRY(error_entry) * from user mode due to an IRET fault. */ SWAPGS + FENCE_SWAPGS_USER_ENTRY /* We have user CR3. Change to kernel CR3. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax @@ -1292,6 +1302,8 @@ ENTRY(error_entry) CALL_enter_from_user_mode ret +.Lerror_entry_done_lfence: + FENCE_SWAPGS_KERNEL_ENTRY .Lerror_entry_done: TRACE_IRQS_OFF ret @@ -1310,7 +1322,7 @@ ENTRY(error_entry) cmpq %rax, RIP+8(%rsp) je .Lbstep_iret cmpq $.Lgs_change, RIP+8(%rsp) - jne .Lerror_entry_done + jne .Lerror_entry_done_lfence /* * hack: .Lgs_change can fail with user gsbase. If this happens, fix up @@ -1318,6 +1330,7 @@ ENTRY(error_entry) * .Lgs_change's error handler with kernel gsbase. */ SWAPGS + FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax jmp .Lerror_entry_done @@ -1332,6 +1345,7 @@ ENTRY(error_entry) * gsbase and CR3. Switch to kernel gsbase and CR3: */ SWAPGS + FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax /* @@ -1423,6 +1437,7 @@ ENTRY(nmi) swapgs cld + FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx movq %rsp, %rdx movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 998c2cc08363..4393278666d9 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -281,6 +281,8 @@ #define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring */ #define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring */ #define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */ +#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ +#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ From a2059825986a1c8143fd6698774fa9d83733bb11 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 8 Jul 2019 11:52:26 -0500 Subject: [PATCH 004/823] x86/speculation: Enable Spectre v1 swapgs mitigations The previous commit added macro calls in the entry code which mitigate the Spectre v1 swapgs issue if the X86_FEATURE_FENCE_SWAPGS_* features are enabled. Enable those features where applicable. The mitigations may be disabled with "nospectre_v1" or "mitigations=off". There are different features which can affect the risk of attack: - When FSGSBASE is enabled, unprivileged users are able to place any value in GS, using the wrgsbase instruction. This means they can write a GS value which points to any value in kernel space, which can be useful with the following gadget in an interrupt/exception/NMI handler: if (coming from user space) swapgs mov %gs:, %reg1 // dependent load or store based on the value of %reg // for example: mov %(reg1), %reg2 If an interrupt is coming from user space, and the entry code speculatively skips the swapgs (due to user branch mistraining), it may speculatively execute the GS-based load and a subsequent dependent load or store, exposing the kernel data to an L1 side channel leak. Note that, on Intel, a similar attack exists in the above gadget when coming from kernel space, if the swapgs gets speculatively executed to switch back to the user GS. On AMD, this variant isn't possible because swapgs is serializing with respect to future GS-based accesses. NOTE: The FSGSBASE patch set hasn't been merged yet, so the above case doesn't exist quite yet. - When FSGSBASE is disabled, the issue is mitigated somewhat because unprivileged users must use prctl(ARCH_SET_GS) to set GS, which restricts GS values to user space addresses only. That means the gadget would need an additional step, since the target kernel address needs to be read from user space first. Something like: if (coming from user space) swapgs mov %gs:, %reg1 mov (%reg1), %reg2 // dependent load or store based on the value of %reg2 // for example: mov %(reg2), %reg3 It's difficult to audit for this gadget in all the handlers, so while there are no known instances of it, it's entirely possible that it exists somewhere (or could be introduced in the future). Without tooling to analyze all such code paths, consider it vulnerable. Effects of SMAP on the !FSGSBASE case: - If SMAP is enabled, and the CPU reports RDCL_NO (i.e., not susceptible to Meltdown), the kernel is prevented from speculatively reading user space memory, even L1 cached values. This effectively disables the !FSGSBASE attack vector. - If SMAP is enabled, but the CPU *is* susceptible to Meltdown, SMAP still prevents the kernel from speculatively reading user space memory. But it does *not* prevent the kernel from reading the user value from L1, if it has already been cached. This is probably only a small hurdle for an attacker to overcome. Thanks to Dave Hansen for contributing the speculative_smap() function. Thanks to Andrew Cooper for providing the inside scoop on whether swapgs is serializing on AMD. [ tglx: Fixed the USER fence decision and polished the comment as suggested by Dave Hansen ] Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Reviewed-by: Dave Hansen --- .../admin-guide/kernel-parameters.txt | 8 +- arch/x86/kernel/cpu/bugs.c | 115 ++++++++++++++++-- 2 files changed, 110 insertions(+), 13 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index e6e806285703..01d7ad250e98 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2587,7 +2587,7 @@ expose users to several CPU vulnerabilities. Equivalent to: nopti [X86,PPC] kpti=0 [ARM64] - nospectre_v1 [PPC] + nospectre_v1 [X86,PPC] nobp=0 [S390] nospectre_v2 [X86,PPC,S390,ARM64] spectre_v2_user=off [X86] @@ -2936,9 +2936,9 @@ nosmt=force: Force disable SMT, cannot be undone via the sysfs control file. - nospectre_v1 [PPC] Disable mitigations for Spectre Variant 1 (bounds - check bypass). With this option data leaks are possible - in the system. + nospectre_v1 [X86,PPC] Disable mitigations for Spectre Variant 1 + (bounds check bypass). With this option data leaks are + possible in the system. nospectre_v2 [X86,PPC_FSL_BOOK3E,ARM64] Disable all mitigations for the Spectre variant 2 (indirect branch prediction) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 66ca906aa790..992f832c447b 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -34,6 +34,7 @@ #include "cpu.h" +static void __init spectre_v1_select_mitigation(void); static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); @@ -98,17 +99,11 @@ void __init check_bugs(void) if (boot_cpu_has(X86_FEATURE_STIBP)) x86_spec_ctrl_mask |= SPEC_CTRL_STIBP; - /* Select the proper spectre mitigation before patching alternatives */ + /* Select the proper CPU mitigations before patching alternatives: */ + spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); - - /* - * Select proper mitigation for any exposure to the Speculative Store - * Bypass vulnerability. - */ ssb_select_mitigation(); - l1tf_select_mitigation(); - mds_select_mitigation(); arch_smt_update(); @@ -273,6 +268,108 @@ static int __init mds_cmdline(char *str) } early_param("mds", mds_cmdline); +#undef pr_fmt +#define pr_fmt(fmt) "Spectre V1 : " fmt + +enum spectre_v1_mitigation { + SPECTRE_V1_MITIGATION_NONE, + SPECTRE_V1_MITIGATION_AUTO, +}; + +static enum spectre_v1_mitigation spectre_v1_mitigation __ro_after_init = + SPECTRE_V1_MITIGATION_AUTO; + +static const char * const spectre_v1_strings[] = { + [SPECTRE_V1_MITIGATION_NONE] = "Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers", + [SPECTRE_V1_MITIGATION_AUTO] = "Mitigation: usercopy/swapgs barriers and __user pointer sanitization", +}; + +static bool is_swapgs_serializing(void) +{ + /* + * Technically, swapgs isn't serializing on AMD (despite it previously + * being documented as such in the APM). But according to AMD, %gs is + * updated non-speculatively, and the issuing of %gs-relative memory + * operands will be blocked until the %gs update completes, which is + * good enough for our purposes. + */ + return boot_cpu_data.x86_vendor == X86_VENDOR_AMD; +} + +/* + * Does SMAP provide full mitigation against speculative kernel access to + * userspace? + */ +static bool smap_works_speculatively(void) +{ + if (!boot_cpu_has(X86_FEATURE_SMAP)) + return false; + + /* + * On CPUs which are vulnerable to Meltdown, SMAP does not + * prevent speculative access to user data in the L1 cache. + * Consider SMAP to be non-functional as a mitigation on these + * CPUs. + */ + if (boot_cpu_has(X86_BUG_CPU_MELTDOWN)) + return false; + + return true; +} + +static void __init spectre_v1_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1) || cpu_mitigations_off()) { + spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE; + return; + } + + if (spectre_v1_mitigation == SPECTRE_V1_MITIGATION_AUTO) { + /* + * With Spectre v1, a user can speculatively control either + * path of a conditional swapgs with a user-controlled GS + * value. The mitigation is to add lfences to both code paths. + * + * If FSGSBASE is enabled, the user can put a kernel address in + * GS, in which case SMAP provides no protection. + * + * [ NOTE: Don't check for X86_FEATURE_FSGSBASE until the + * FSGSBASE enablement patches have been merged. ] + * + * If FSGSBASE is disabled, the user can only put a user space + * address in GS. That makes an attack harder, but still + * possible if there's no SMAP protection. + */ + if (!smap_works_speculatively()) { + /* + * Mitigation can be provided from SWAPGS itself or + * PTI as the CR3 write in the Meltdown mitigation + * is serializing. + * + * If neither is there, mitigate with an LFENCE. + */ + if (!is_swapgs_serializing() && !boot_cpu_has(X86_FEATURE_PTI)) + setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_USER); + + /* + * Enable lfences in the kernel entry (non-swapgs) + * paths, to prevent user entry from speculatively + * skipping swapgs. + */ + setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_KERNEL); + } + } + + pr_info("%s\n", spectre_v1_strings[spectre_v1_mitigation]); +} + +static int __init nospectre_v1_cmdline(char *str) +{ + spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE; + return 0; +} +early_param("nospectre_v1", nospectre_v1_cmdline); + #undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt @@ -1290,7 +1387,7 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr break; case X86_BUG_SPECTRE_V1: - return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); case X86_BUG_SPECTRE_V2: return sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], From 43167bb1f6bb7efa73adc40d2dd700bb6546cc2c Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 9 Jul 2019 13:26:31 -0600 Subject: [PATCH 005/823] spi: dt-bindings: spi-controller: remove unnecessary 'maxItems: 1' from reg Mixing array constraints like 'maxItems' and string or integer value constraints like 'minimum' don't make sense. Also, with only value constraints, it is implied we have a single value. So lets remove 'maxItems: 1'. Cc: Mark Brown Cc: linux-spi@vger.kernel.org Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20190709192631.16394-1-robh@kernel.org Signed-off-by: Mark Brown --- Documentation/devicetree/bindings/spi/spi-controller.yaml | 1 - 1 file changed, 1 deletion(-) diff --git a/Documentation/devicetree/bindings/spi/spi-controller.yaml b/Documentation/devicetree/bindings/spi/spi-controller.yaml index 876c0623f322..a02e2fe2bfb2 100644 --- a/Documentation/devicetree/bindings/spi/spi-controller.yaml +++ b/Documentation/devicetree/bindings/spi/spi-controller.yaml @@ -73,7 +73,6 @@ patternProperties: Compatible of the SPI device. reg: - maxItems: 1 minimum: 0 maximum: 256 description: From d6b197a14863818a7ed7890e91f043fab49e8c60 Mon Sep 17 00:00:00 2001 From: Han Xu Date: Wed, 10 Jul 2019 10:31:27 +0800 Subject: [PATCH 006/823] spi: spi-fsl-qspi: change i.MX7D RX FIFO size The RX FIFO should be 128 byte rather than 512 byte. It's a typo on reference manual. Signed-off-by: Han Xu Link: https://lore.kernel.org/r/20190710023128.13115-3-han.xu@nxp.com Signed-off-by: Mark Brown --- drivers/spi/spi-fsl-qspi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/spi/spi-fsl-qspi.c b/drivers/spi/spi-fsl-qspi.c index 41a49b93ca60..448c00e4065b 100644 --- a/drivers/spi/spi-fsl-qspi.c +++ b/drivers/spi/spi-fsl-qspi.c @@ -206,7 +206,7 @@ static const struct fsl_qspi_devtype_data imx6sx_data = { }; static const struct fsl_qspi_devtype_data imx7d_data = { - .rxfifo = SZ_512, + .rxfifo = SZ_128, .txfifo = SZ_512, .ahb_buf_size = SZ_1K, .quirks = QUADSPI_QUIRK_TKT253890 | QUADSPI_QUIRK_4X_INT_CLK, From 224d5fd43d250f850d64fb6d668114aff29d7022 Mon Sep 17 00:00:00 2001 From: Marcus Folkesson Date: Tue, 9 Jul 2019 09:54:36 +0200 Subject: [PATCH 007/823] docs: driver-api: generic-counter: fix file path to ABI doc Fixes: 09e7d4ed8991 ("docs: Add Generic Counter interface documentation") Signed-off-by: Marcus Folkesson Acked-by: William Breathitt Gray Signed-off-by: Jonathan Corbet --- Documentation/driver-api/generic-counter.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/driver-api/generic-counter.rst b/Documentation/driver-api/generic-counter.rst index 0c161b1a3be6..8382f01a53e3 100644 --- a/Documentation/driver-api/generic-counter.rst +++ b/Documentation/driver-api/generic-counter.rst @@ -233,7 +233,7 @@ Userspace Interface Several sysfs attributes are generated by the Generic Counter interface, and reside under the /sys/bus/counter/devices/counterX directory, where counterX refers to the respective counter device. Please see -Documentation/ABI/testing/sys-bus-counter-generic-sysfs for detailed +Documentation/ABI/testing/sysfs-bus-counter for detailed information on each Generic Counter interface sysfs attribute. Through these sysfs attributes, programs and scripts may interact with @@ -325,7 +325,7 @@ sysfs attributes, where Y is the unique ID of the respective Count: For a more detailed breakdown of the available Generic Counter interface sysfs attributes, please refer to the -Documentation/ABI/testing/sys-bus-counter file. +Documentation/ABI/testing/sysfs-bus-counter file. The Signals and Counts associated with the Counter device are registered to the system as well by the counter_register function. The From a1f32eeca60e74f6f103ce74f586570deddaef7a Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 1 Jul 2019 13:26:28 -0700 Subject: [PATCH 008/823] f2fs: use generic checking and prep function for FS_IOC_SETFLAGS Make the f2fs implementation of FS_IOC_SETFLAGS use the new VFS helper function vfs_ioc_setflags_prepare(). This is based on a patch from Darrick Wong, but reworked to apply after commit 360985573b55 ("f2fs: separate f2fs i_flags from fs_flags and ext4 i_flags"). Originally-from: Darrick J. Wong Signed-off-by: Eric Biggers Reviewed-by: Chao Yu Reviewed-by: Darrick J. Wong Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index f8d46df8fa9e..b7aa0144d874 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1770,7 +1770,8 @@ static int f2fs_ioc_getflags(struct file *filp, unsigned long arg) static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); - u32 fsflags; + struct f2fs_inode_info *fi = F2FS_I(inode); + u32 fsflags, old_fsflags; u32 iflags; int ret; @@ -1794,8 +1795,14 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) inode_lock(inode); + old_fsflags = f2fs_iflags_to_fsflags(fi->i_flags); + ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags); + if (ret) + goto out; + ret = f2fs_setflags_common(inode, iflags, f2fs_fsflags_to_iflags(F2FS_SETTABLE_FS_FL)); +out: inode_unlock(inode); mnt_drop_write_file(filp); return ret; From 6fc93c4e0ad12e34475755315749143013c702ab Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 1 Jul 2019 13:26:29 -0700 Subject: [PATCH 009/823] f2fs: use generic checking function for FS_IOC_FSSETXATTR Make the f2fs implementation of FS_IOC_FSSETXATTR use the new VFS helper function vfs_ioc_fssetxattr_check(), and remove the project quota check since it's now done by the helper function. This is based on a patch from Darrick Wong, but reworked to apply after commit 360985573b55 ("f2fs: separate f2fs i_flags from fs_flags and ext4 i_flags"). Originally-from: Darrick J. Wong Signed-off-by: Eric Biggers Reviewed-by: Chao Yu Reviewed-by: Darrick J. Wong Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 49 ++++++++++++++++--------------------------------- 1 file changed, 16 insertions(+), 33 deletions(-) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index b7aa0144d874..717bad8d31b0 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2862,52 +2862,32 @@ static inline u32 f2fs_xflags_to_iflags(u32 xflags) return iflags; } +static void f2fs_fill_fsxattr(struct inode *inode, struct fsxattr *fa) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + + simple_fill_fsxattr(fa, f2fs_iflags_to_xflags(fi->i_flags)); + + if (f2fs_sb_has_project_quota(F2FS_I_SB(inode))) + fa->fsx_projid = from_kprojid(&init_user_ns, fi->i_projid); +} + static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); - struct f2fs_inode_info *fi = F2FS_I(inode); struct fsxattr fa; - memset(&fa, 0, sizeof(struct fsxattr)); - fa.fsx_xflags = f2fs_iflags_to_xflags(fi->i_flags); - - if (f2fs_sb_has_project_quota(F2FS_I_SB(inode))) - fa.fsx_projid = (__u32)from_kprojid(&init_user_ns, - fi->i_projid); + f2fs_fill_fsxattr(inode, &fa); if (copy_to_user((struct fsxattr __user *)arg, &fa, sizeof(fa))) return -EFAULT; return 0; } -static int f2fs_ioctl_check_project(struct inode *inode, struct fsxattr *fa) -{ - /* - * Project Quota ID state is only allowed to change from within the init - * namespace. Enforce that restriction only if we are trying to change - * the quota ID state. Everything else is allowed in user namespaces. - */ - if (current_user_ns() == &init_user_ns) - return 0; - - if (__kprojid_val(F2FS_I(inode)->i_projid) != fa->fsx_projid) - return -EINVAL; - - if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL) { - if (!(fa->fsx_xflags & FS_XFLAG_PROJINHERIT)) - return -EINVAL; - } else { - if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT) - return -EINVAL; - } - - return 0; -} - static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); - struct fsxattr fa; + struct fsxattr fa, old_fa; u32 iflags; int err; @@ -2930,9 +2910,12 @@ static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg) return err; inode_lock(inode); - err = f2fs_ioctl_check_project(inode, &fa); + + f2fs_fill_fsxattr(inode, &old_fa); + err = vfs_ioc_fssetxattr_check(inode, &old_fa, &fa); if (err) goto out; + err = f2fs_setflags_common(inode, iflags, f2fs_xflags_to_iflags(F2FS_SUPPORTED_XFLAGS)); if (err) From d5e5efa250cd644896f541551610fe7f0de35e0a Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 1 Jul 2019 13:26:30 -0700 Subject: [PATCH 010/823] f2fs: remove redundant check from f2fs_setflags_common() Now that f2fs_ioc_setflags() and f2fs_ioc_fssetxattr() call the VFS helper functions which check for permission to change the immutable and append-only flags, it's no longer needed to do this check in f2fs_setflags_common() too. So remove it. This is based on a patch from Darrick Wong, but reworked to apply after commit 360985573b55 ("f2fs: separate f2fs i_flags from fs_flags and ext4 i_flags"). Originally-from: Darrick J. Wong Signed-off-by: Eric Biggers Reviewed-by: Chao Yu Reviewed-by: Darrick J. Wong Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 717bad8d31b0..3e58a6f697dd 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1653,19 +1653,12 @@ static int f2fs_file_flush(struct file *file, fl_owner_t id) static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) { struct f2fs_inode_info *fi = F2FS_I(inode); - u32 oldflags; /* Is it quota file? Do not allow user to mess with it */ if (IS_NOQUOTA(inode)) return -EPERM; - oldflags = fi->i_flags; - - if ((iflags ^ oldflags) & (F2FS_APPEND_FL | F2FS_IMMUTABLE_FL)) - if (!capable(CAP_LINUX_IMMUTABLE)) - return -EPERM; - - fi->i_flags = iflags | (oldflags & ~mask); + fi->i_flags = iflags | (fi->i_flags & ~mask); if (fi->i_flags & F2FS_PROJINHERIT_FL) set_inode_flag(inode, FI_PROJ_INHERIT); From da0ef93310e67ae6902efded60b6724dab27a5d1 Mon Sep 17 00:00:00 2001 From: Suraj Jitindar Singh Date: Wed, 10 Jul 2019 15:20:18 +1000 Subject: [PATCH 011/823] powerpc/mm: Limit rma_size to 1TB when running without HV mode The virtual real mode addressing (VRMA) mechanism is used when a partition is using HPT (Hash Page Table) translation and performs real mode accesses (MSR[IR|DR] = 0) in non-hypervisor mode. In this mode effective address bits 0:23 are treated as zero (i.e. the access is aliased to 0) and the access is performed using an implicit 1TB SLB entry. The size of the RMA (Real Memory Area) is communicated to the guest as the size of the first memory region in the device tree. And because of the mechanism described above can be expected to not exceed 1TB. In the event that the host erroneously represents the RMA as being larger than 1TB, guest accesses in real mode to memory addresses above 1TB will be aliased down to below 1TB. This means that a memory access performed in real mode may differ to one performed in virtual mode for the same memory address, which would likely have unintended consequences. To avoid this outcome have the guest explicitly limit the size of the RMA to the current maximum, which is 1TB. This means that even if the first memory block is larger than 1TB, only the first 1TB should be accessed in real mode. Fixes: c610d65c0ad0 ("powerpc/pseries: lift RTAS limit for hash") Cc: stable@vger.kernel.org # v4.16+ Signed-off-by: Suraj Jitindar Singh Tested-by: Satheesh Rajendran Reviewed-by: David Gibson Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190710052018.14628-1-sjitindarsingh@gmail.com --- arch/powerpc/mm/book3s64/hash_utils.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 9a5963e07a82..b8ad14bb1170 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1899,11 +1899,20 @@ void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base, * * For guests on platforms before POWER9, we clamp the it limit to 1G * to avoid some funky things such as RTAS bugs etc... + * + * On POWER9 we limit to 1TB in case the host erroneously told us that + * the RMA was >1TB. Effective address bits 0:23 are treated as zero + * (meaning the access is aliased to zero i.e. addr = addr % 1TB) + * for virtual real mode addressing and so it doesn't make sense to + * have an area larger than 1TB as it can't be addressed. */ if (!early_cpu_has_feature(CPU_FTR_HVMODE)) { ppc64_rma_size = first_memblock_size; if (!early_cpu_has_feature(CPU_FTR_ARCH_300)) ppc64_rma_size = min_t(u64, ppc64_rma_size, 0x40000000); + else + ppc64_rma_size = min_t(u64, ppc64_rma_size, + 1UL << SID_SHIFT_1T); /* Finally limit subsequent allocations */ memblock_set_current_limit(ppc64_rma_size); From 63279eeb7f93abb1692573c26f1e038e1a87358b Mon Sep 17 00:00:00 2001 From: Suraj Jitindar Singh Date: Wed, 3 Jul 2019 11:20:20 +1000 Subject: [PATCH 012/823] KVM: PPC: Book3S HV: Always save guest pmu for guest capable of nesting The performance monitoring unit (PMU) registers are saved on guest exit when the guest has set the pmcregs_in_use flag in its lppaca, if it exists, or unconditionally if it doesn't. If a nested guest is being run then the hypervisor doesn't, and in most cases can't, know if the PMU registers are in use since it doesn't know the location of the lppaca for the nested guest, although it may have one for its immediate guest. This results in the values of these registers being lost across nested guest entry and exit in the case where the nested guest was making use of the performance monitoring facility while it's nested guest hypervisor wasn't. Further more the hypervisor could interrupt a guest hypervisor between when it has loaded up the PMU registers and it calling H_ENTER_NESTED or between returning from the nested guest to the guest hypervisor and the guest hypervisor reading the PMU registers, in kvmhv_p9_guest_entry(). This means that it isn't sufficient to just save the PMU registers when entering or exiting a nested guest, but that it is necessary to always save the PMU registers whenever a guest is capable of running nested guests to ensure the register values aren't lost in the context switch. Ensure the PMU register values are preserved by always saving their value into the vcpu struct when a guest is capable of running nested guests. This should have minimal performance impact however any impact can be avoided by booting a guest with "-machine pseries,cap-nested-hv=false" on the qemu commandline. Fixes: 95a6432ce903 ("KVM: PPC: Book3S HV: Streamlined guest entry/exit path on P9 for radix guests") Cc: stable@vger.kernel.org # v4.20+ Signed-off-by: Suraj Jitindar Singh Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190703012022.15644-1-sjitindarsingh@gmail.com --- arch/powerpc/kvm/book3s_hv.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index ec1804f822af..b682a429f3ef 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3654,6 +3654,8 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, vcpu->arch.vpa.dirty = 1; save_pmu = lp->pmcregs_in_use; } + /* Must save pmu if this guest is capable of running nested guests */ + save_pmu |= nesting_enabled(vcpu->kvm); kvmhv_save_guest_pmu(vcpu, save_pmu); From 28d2a6e6684d9851905f379816d8a4d03587ed94 Mon Sep 17 00:00:00 2001 From: Suraj Jitindar Singh Date: Wed, 3 Jul 2019 11:20:21 +1000 Subject: [PATCH 013/823] powerpc/pmu: Set pmcregs_in_use in paca when running as LPAR The ability to run nested guests under KVM means that a guest can also act as a hypervisor for it's own nested guest. Currently ppc_set_pmu_inuse() assumes that either FW_FEATURE_LPAR is set, indicating a guest environment, and so sets the pmcregs_in_use flag in the lppaca, or that it isn't set, indicating a hypervisor environment, and so sets the pmcregs_in_use flag in the paca. The pmcregs_in_use flag in the lppaca is used to communicate this information to a hypervisor and so must be set in a guest environment. The pmcregs_in_use flag in the paca is used by KVM code to determine whether the host state of the performance monitoring unit (PMU) must be saved and restored when running a guest. Thus when a guest also acts as a hypervisor it must set this bit in both places since it needs to ensure both that the real hypervisor saves it's PMU registers when it runs (requires pmcregs_in_use flag in lppaca), and that it saves it's own PMU registers when running a nested guest (requires pmcregs_in_use flag in paca). Modify ppc_set_pmu_inuse() so that the pmcregs_in_use bit is set in both the lppaca and the paca when a guest (LPAR) is running with the capability of running it's own guests (CONFIG_KVM_BOOK3S_HV_POSSIBLE). Fixes: 95a6432ce903 ("KVM: PPC: Book3S HV: Streamlined guest entry/exit path on P9 for radix guests") Cc: stable@vger.kernel.org # v4.20+ Signed-off-by: Suraj Jitindar Singh Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190703012022.15644-2-sjitindarsingh@gmail.com --- arch/powerpc/include/asm/pmc.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/include/asm/pmc.h b/arch/powerpc/include/asm/pmc.h index dc9a1ca70edf..c6bbe9778d3c 100644 --- a/arch/powerpc/include/asm/pmc.h +++ b/arch/powerpc/include/asm/pmc.h @@ -26,12 +26,11 @@ static inline void ppc_set_pmu_inuse(int inuse) if (firmware_has_feature(FW_FEATURE_LPAR)) { #ifdef CONFIG_PPC_PSERIES get_lppaca()->pmcregs_in_use = inuse; -#endif - } else { -#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE - get_paca()->pmcregs_in_use = inuse; #endif } +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + get_paca()->pmcregs_in_use = inuse; +#endif #endif } From c8b4083db915dfe5a3b4a755ad2317e0509b43f1 Mon Sep 17 00:00:00 2001 From: Suraj Jitindar Singh Date: Wed, 3 Jul 2019 11:20:22 +1000 Subject: [PATCH 014/823] KVM: PPC: Book3S HV: Save and restore guest visible PSSCR bits on pseries The Performance Stop Status and Control Register (PSSCR) is used to control the power saving facilities of the processor. This register has various fields, some of which can be modified only in hypervisor state, and others which can be modified in both hypervisor and privileged non-hypervisor state. The bits which can be modified in privileged non-hypervisor state are referred to as guest visible. Currently the L0 hypervisor saves and restores both it's own host value as well as the guest value of the PSSCR when context switching between the hypervisor and guest. However a nested hypervisor running it's own nested guests (as indicated by kvmhv_on_pseries()) doesn't context switch the PSSCR register. That means if a nested (L2) guest modifies the PSSCR then the L1 guest hypervisor will run with that modified value, and if the L1 guest hypervisor modifies the PSSCR and then goes to run the nested (L2) guest again then the L2 PSSCR value will be lost. Fix this by having the (L1) nested hypervisor save and restore both its host and the guest PSSCR value when entering and exiting a nested (L2) guest. Note that only the guest visible parts of the PSSCR are context switched since this is all the L1 nested hypervisor can access, this is fine however as these are the only fields the L0 hypervisor provides guest control of anyway and so all other fields are ignored. This could also have been implemented by adding the PSSCR register to the hv_regs passed to the L0 hypervisor as input to the H_ENTER_NESTED hcall, however this would have meant updating the structure layout and thus required modifications to both the L0 and L1 kernels. Whereas the approach used doesn't require L0 kernel modifications while achieving the same result. Fixes: 95a6432ce903 ("KVM: PPC: Book3S HV: Streamlined guest entry/exit path on P9 for radix guests") Cc: stable@vger.kernel.org # v4.20+ Signed-off-by: Suraj Jitindar Singh Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190703012022.15644-3-sjitindarsingh@gmail.com --- arch/powerpc/kvm/book3s_hv.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index b682a429f3ef..cde3f5a4b3e4 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3569,9 +3569,18 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb()); if (kvmhv_on_pseries()) { + /* + * We need to save and restore the guest visible part of the + * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor + * doesn't do this for us. Note only required if pseries since + * this is done in kvmhv_load_hv_regs_and_go() below otherwise. + */ + unsigned long host_psscr; /* call our hypervisor to load up HV regs and go */ struct hv_guest_state hvregs; + host_psscr = mfspr(SPRN_PSSCR_PR); + mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); kvmhv_save_hv_regs(vcpu, &hvregs); hvregs.lpcr = lpcr; vcpu->arch.regs.msr = vcpu->arch.shregs.msr; @@ -3590,6 +3599,8 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, vcpu->arch.shregs.msr = vcpu->arch.regs.msr; vcpu->arch.shregs.dar = mfspr(SPRN_DAR); vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR); + vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); + mtspr(SPRN_PSSCR_PR, host_psscr); /* H_CEDE has to be handled now, not later */ if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && From 03800e0526ee25ed7c843ca1e57b69ac2a5af642 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Tue, 25 Jun 2019 10:17:27 -0400 Subject: [PATCH 015/823] powerpc: fix off by one in max_zone_pfn initialization for ZONE_DMA 25078dc1f74be16b858e914f52cc8f4d03c2271a first introduced an off by one error in the ZONE_DMA initialization of PPC_BOOK3E_64=y and since 9739ab7eda459f0669ec9807e0d9be5020bab88c the off by one applies to PPC32=y too. This simply corrects the off by one and should resolve crashes like below: [ 65.179101] page 0x7fff outside node 0 zone DMA [ 0x0 - 0x7fff ] Unfortunately in various MM places "max" means a non inclusive end of range. free_area_init_nodes max_zone_pfn parameter is one case and MAX_ORDER is another one (unrelated) that comes by memory. Reported-by: Zorro Lang Fixes: 25078dc1f74b ("powerpc: use mm zones more sensibly") Fixes: 9739ab7eda45 ("powerpc: enable a 30-bit ZONE_DMA for 32-bit pmac") Signed-off-by: Andrea Arcangeli Reviewed-by: Christoph Hellwig Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190625141727.2883-1-aarcange@redhat.com --- arch/powerpc/mm/mem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 6d5f0fc76666..b6beb86e5300 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -249,7 +249,7 @@ void __init paging_init(void) #ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = min(max_low_pfn, - ((1UL << ARCH_ZONE_DMA_BITS) - 1) >> PAGE_SHIFT); + 1UL << (ARCH_ZONE_DMA_BITS - PAGE_SHIFT)); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM From c9f597a4d6d7a01590571291f659a2f146111e34 Mon Sep 17 00:00:00 2001 From: Farhan Ali Date: Thu, 11 Jul 2019 10:28:51 -0400 Subject: [PATCH 016/823] vfio-ccw: Fix misleading comment when setting orb.cmd.c64 The comment is misleading because it tells us that we should set orb.cmd.c64 before calling ccwchain_calc_length, otherwise the function ccwchain_calc_length would return an error. This is not completely accurate. We want to allow an orb without cmd.c64, and this is fine as long as the channel program does not use IDALs. But we do want to reject any channel program that uses IDALs and does not set the flag, which is what we do in ccwchain_calc_length. After we have done the ccw processing, we need to set cmd.c64, as we use IDALs for all translated channel programs. Also for better code readability let's move the setting of cmd.c64 within the non error path. Fixes: fb9e7880af35 ("vfio: ccw: push down unsupported IDA check") Signed-off-by: Farhan Ali Reviewed-by: Cornelia Huck Message-Id: Reviewed-by: Eric Farman Signed-off-by: Cornelia Huck --- drivers/s390/cio/vfio_ccw_cp.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index 1d4c893ead23..46967c664c0f 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -645,14 +645,15 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb) if (ret) cp_free(cp); - /* It is safe to force: if not set but idals used - * ccwchain_calc_length returns an error. - */ - cp->orb.cmd.c64 = 1; - - if (!ret) + if (!ret) { cp->initialized = true; + /* It is safe to force: if it was not set but idals used + * ccwchain_calc_length would have returned an error. + */ + cp->orb.cmd.c64 = 1; + } + return ret; } From 8b515be512a2435bb8aedc6390cbe140167f9eb9 Mon Sep 17 00:00:00 2001 From: Farhan Ali Date: Thu, 11 Jul 2019 10:28:52 -0400 Subject: [PATCH 017/823] vfio-ccw: Fix memory leak and don't call cp_free in cp_init We don't set cp->initialized to true so calling cp_free will just return and not do anything. Also fix a memory leak where we fail to free a ccwchain on an error. Fixes: 812271b910 ("s390/cio: Squash cp_free() and cp_unpin_free()") Signed-off-by: Farhan Ali Message-Id: <3173c4216f4555d9765eb6e4922534982bc820e4.1562854091.git.alifm@linux.ibm.com> Reviewed-by: Cornelia Huck Reviewed-by: Eric Farman Signed-off-by: Cornelia Huck --- drivers/s390/cio/vfio_ccw_cp.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index 46967c664c0f..e4e8724eddaa 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -421,7 +421,7 @@ static int ccwchain_loop_tic(struct ccwchain *chain, static int ccwchain_handle_ccw(u32 cda, struct channel_program *cp) { struct ccwchain *chain; - int len; + int len, ret; /* Copy 2K (the most we support today) of possible CCWs */ len = copy_from_iova(cp->mdev, cp->guest_cp, cda, @@ -448,7 +448,12 @@ static int ccwchain_handle_ccw(u32 cda, struct channel_program *cp) memcpy(chain->ch_ccw, cp->guest_cp, len * sizeof(struct ccw1)); /* Loop for tics on this new chain. */ - return ccwchain_loop_tic(chain, cp); + ret = ccwchain_loop_tic(chain, cp); + + if (ret) + ccwchain_free(chain); + + return ret; } /* Loop for TICs. */ @@ -642,8 +647,6 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb) /* Build a ccwchain for the first CCW segment */ ret = ccwchain_handle_ccw(orb->cmd.cpa, cp); - if (ret) - cp_free(cp); if (!ret) { cp->initialized = true; From c1ab69268d124ebdbb3864580808188ccd3ea355 Mon Sep 17 00:00:00 2001 From: Farhan Ali Date: Thu, 11 Jul 2019 10:28:53 -0400 Subject: [PATCH 018/823] vfio-ccw: Set pa_nr to 0 if memory allocation fails for pa_iova_pfn So we don't call try to call vfio_unpin_pages() incorrectly. Fixes: 0a19e61e6d4c ("vfio: ccw: introduce channel program interfaces") Signed-off-by: Farhan Ali Reviewed-by: Eric Farman Reviewed-by: Cornelia Huck Message-Id: <33a89467ad6369196ae6edf820cbcb1e2d8d050c.1562854091.git.alifm@linux.ibm.com> Signed-off-by: Cornelia Huck --- drivers/s390/cio/vfio_ccw_cp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index e4e8724eddaa..3645d1720c4b 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -72,8 +72,10 @@ static int pfn_array_alloc(struct pfn_array *pa, u64 iova, unsigned int len) sizeof(*pa->pa_iova_pfn) + sizeof(*pa->pa_pfn), GFP_KERNEL); - if (unlikely(!pa->pa_iova_pfn)) + if (unlikely(!pa->pa_iova_pfn)) { + pa->pa_nr = 0; return -ENOMEM; + } pa->pa_pfn = pa->pa_iova_pfn + pa->pa_nr; pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT; From f4c9939433bd396d0b08e803b2b880a9d02682b9 Mon Sep 17 00:00:00 2001 From: Farhan Ali Date: Thu, 11 Jul 2019 10:28:54 -0400 Subject: [PATCH 019/823] vfio-ccw: Don't call cp_free if we are processing a channel program There is a small window where it's possible that we could be working on an interrupt (queued in the workqueue) and setting up a channel program (i.e allocating memory, pinning pages, translating address). This can lead to allocating and freeing the channel program at the same time and can cause memory corruption. Let's not call cp_free if we are currently processing a channel program. The only way we know for sure that we don't have a thread setting up a channel program is when the state is set to VFIO_CCW_STATE_CP_PENDING. Fixes: d5afd5d135c8 ("vfio-ccw: add handling for async channel instructions") Signed-off-by: Farhan Ali Reviewed-by: Cornelia Huck Message-Id: <62e87bf67b38dc8d5760586e7c96d400db854ebe.1562854091.git.alifm@linux.ibm.com> Reviewed-by: Eric Farman Signed-off-by: Cornelia Huck --- drivers/s390/cio/vfio_ccw_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index 2b90a5ecaeb9..9208c0e56c33 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -88,7 +88,7 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work) (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT)); if (scsw_is_solicited(&irb->scsw)) { cp_update_scsw(&private->cp, &irb->scsw); - if (is_final) + if (is_final && private->state == VFIO_CCW_STATE_CP_PENDING) cp_free(&private->cp); } mutex_lock(&private->io_mutex); From 127e62174041496b383f82d696e1592ce6838604 Mon Sep 17 00:00:00 2001 From: Farhan Ali Date: Thu, 11 Jul 2019 10:28:55 -0400 Subject: [PATCH 020/823] vfio-ccw: Update documentation for csch/hsch We now support CLEAR SUBCHANNEL and HALT SUBCHANNEL via ccw_cmd_region. Fixes: d5afd5d135c8 ("vfio-ccw: add handling for async channel instructions") Signed-off-by: Farhan Ali Message-Id: <7d977612c3f3152ffb950d77ae11b4b25c1e20c4.1562854091.git.alifm@linux.ibm.com> [CH: properly mark region as literal block] Reviewed-by: Cornelia Huck Reviewed-by: Eric Farman Signed-off-by: Cornelia Huck --- Documentation/s390/vfio-ccw.rst | 31 ++++++++++++++++++++++++++++--- 1 file changed, 28 insertions(+), 3 deletions(-) diff --git a/Documentation/s390/vfio-ccw.rst b/Documentation/s390/vfio-ccw.rst index 1f6d0b56d53e..be2af10e12b4 100644 --- a/Documentation/s390/vfio-ccw.rst +++ b/Documentation/s390/vfio-ccw.rst @@ -180,6 +180,13 @@ The process of how these work together. add it to an iommu_group and a vfio_group. Then we could pass through the mdev to a guest. + +VFIO-CCW Regions +---------------- + +The vfio-ccw driver exposes MMIO regions to accept requests from and return +results to userspace. + vfio-ccw I/O region ------------------- @@ -205,6 +212,25 @@ irb_area stores the I/O result. ret_code stores a return code for each access of the region. +This region is always available. + +vfio-ccw cmd region +------------------- + +The vfio-ccw cmd region is used to accept asynchronous instructions +from userspace. + +#define VFIO_CCW_ASYNC_CMD_HSCH (1 << 0) +#define VFIO_CCW_ASYNC_CMD_CSCH (1 << 1) +struct ccw_cmd_region { + __u32 command; + __u32 ret_code; +} __packed; + +This region is exposed via region type VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD. + +Currently, CLEAR SUBCHANNEL and HALT SUBCHANNEL use this region. + vfio-ccw operation details -------------------------- @@ -306,9 +332,8 @@ Together with the corresponding work in QEMU, we can bring the passed through DASD/ECKD device online in a guest now and use it as a block device. -While the current code allows the guest to start channel programs via -START SUBCHANNEL, support for HALT SUBCHANNEL or CLEAR SUBCHANNEL is -not yet implemented. +The current code allows the guest to start channel programs via +START SUBCHANNEL, and to issue HALT SUBCHANNEL and CLEAR SUBCHANNEL. vfio-ccw supports classic (command mode) channel I/O only. Transport mode (HPF) is not supported. From 7aaddd96d5febcf5b24357a326b3038d49a20532 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Thu, 11 Jul 2019 05:13:13 +0300 Subject: [PATCH 021/823] drm/modes: Don't apply cmdline's rotation if it wasn't specified The rotation mode from cmdline shouldn't be taken into account if it wasn't specified in the cmdline. This fixes ignored default display orientation when display mode is given using cmdline without the rotation being specified. Fixes: 1bf4e09227c3 ("drm/modes: Allow to specify rotation and reflection on the commandline") Signed-off-by: Dmitry Osipenko Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20190711021313.29445-1-digetx@gmail.com --- drivers/gpu/drm/drm_client_modeset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index 56d36779d213..c8922b7cac09 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -859,7 +859,7 @@ bool drm_client_rotation(struct drm_mode_set *modeset, unsigned int *rotation) * simple XOR between the two handle the addition nicely. */ cmdline = &connector->cmdline_mode; - if (cmdline->specified) { + if (cmdline->specified && cmdline->rotation_reflection) { unsigned int cmdline_rest, panel_rest; unsigned int cmdline_rot, panel_rot; unsigned int sum_rot, sum_rest; From dbd0f6d6c2a11eb9c31ca9cd454f95bb5713e92e Mon Sep 17 00:00:00 2001 From: Zhengyuan Liu Date: Sat, 13 Jul 2019 11:58:26 +0800 Subject: [PATCH 022/823] io_uring: fix the sequence comparison in io_sequence_defer sq->cached_sq_head and cq->cached_cq_tail are both unsigned int. If cached_sq_head overflows before cached_cq_tail, then we may miss a barrier req. As cached_cq_tail always follows cached_sq_head, the NQ should be enough. Cc: stable@vger.kernel.org Fixes: de0617e46717 ("io_uring: add support for marking commands as draining") Signed-off-by: Zhengyuan Liu Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index d682049c07b2..708d133492a1 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -429,7 +429,7 @@ static inline bool io_sequence_defer(struct io_ring_ctx *ctx, if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN) return false; - return req->sequence > ctx->cached_cq_tail + ctx->sq_ring->dropped; + return req->sequence != ctx->cached_cq_tail + ctx->sq_ring->dropped; } static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx) From c56cbfae62b7d572c7994c927202d337633cc7d9 Mon Sep 17 00:00:00 2001 From: Ding Xiang Date: Tue, 16 Jul 2019 17:54:08 +0800 Subject: [PATCH 023/823] ata: libahci_platform: remove redundant dev_err message devm_ioremap_resource already contains error message, so remove the redundant dev_err message Signed-off-by: Ding Xiang Signed-off-by: Jens Axboe --- drivers/ata/libahci_platform.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 72312ad2e142..3a36e76eca83 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -408,7 +408,6 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev, hpriv->mmio = devm_ioremap_resource(dev, platform_get_resource(pdev, IORESOURCE_MEM, 0)); if (IS_ERR(hpriv->mmio)) { - dev_err(dev, "no mmio space\n"); rc = PTR_ERR(hpriv->mmio); goto err_out; } From f7b76ac9d17e16e44feebb6d2749fec92bfd6dd4 Mon Sep 17 00:00:00 2001 From: Zhengyuan Liu Date: Tue, 16 Jul 2019 23:26:14 +0800 Subject: [PATCH 024/823] io_uring: fix counter inc/dec mismatch in async_list We could queue a work for each req in defer and link list without increasing async_list->cnt, so we shouldn't decrease it while exiting from workqueue as well if we didn't process the req in async list. Thanks to Jens Axboe for his guidance. Fixes: 31b515106428 ("io_uring: allow workqueue item to handle multiple buffered requests") Signed-off-by: Zhengyuan Liu Signed-off-by: Jens Axboe --- fs/io_uring.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 708d133492a1..5ec06e5ba0be 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -333,7 +333,8 @@ struct io_kiocb { #define REQ_F_IO_DRAIN 16 /* drain existing IO first */ #define REQ_F_IO_DRAINED 32 /* drain done */ #define REQ_F_LINK 64 /* linked sqes */ -#define REQ_F_FAIL_LINK 128 /* fail rest of links */ +#define REQ_F_LINK_DONE 128 /* linked sqes done */ +#define REQ_F_FAIL_LINK 256 /* fail rest of links */ u64 user_data; u32 result; u32 sequence; @@ -632,6 +633,7 @@ static void io_req_link_next(struct io_kiocb *req) nxt->flags |= REQ_F_LINK; } + nxt->flags |= REQ_F_LINK_DONE; INIT_WORK(&nxt->work, io_sq_wq_submit_work); queue_work(req->ctx->sqo_wq, &nxt->work); } @@ -1844,6 +1846,10 @@ restart: /* async context always use a copy of the sqe */ kfree(sqe); + /* req from defer and link list needn't decrease async cnt */ + if (req->flags & (REQ_F_IO_DRAINED | REQ_F_LINK_DONE)) + goto out; + if (!async_list) break; if (!list_empty(&req_list)) { @@ -1891,6 +1897,7 @@ restart: } } +out: if (cur_mm) { set_fs(old_fs); unuse_mm(cur_mm); From 07b0fdecb2477396bcb69609019aade2b22124a1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 16 Jul 2019 07:58:31 -0700 Subject: [PATCH 025/823] blkcg: allow blkcg_policy->pd_stat() to print non-debug info too Currently, ->pd_stat() is called only when moduleparam blkcg_debug_stats is set which prevents it from printing non-debug policy-specific statistics. Let's move debug testing down so that ->pd_stat() can print non-debug stat too. This patch doesn't cause any visible behavior change. Signed-off-by: Tejun Heo Cc: Josef Bacik Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 9 +++------ block/blk-iolatency.c | 3 +++ include/linux/blk-cgroup.h | 1 + 3 files changed, 7 insertions(+), 6 deletions(-) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 24ed26957367..55a7dc227dfb 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -54,7 +54,7 @@ static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */ -static bool blkcg_debug_stats = false; +bool blkcg_debug_stats = false; static struct workqueue_struct *blkcg_punt_bio_wq; static bool blkcg_policy_enabled(struct request_queue *q, @@ -944,10 +944,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) dbytes, dios); } - if (!blkcg_debug_stats) - goto next; - - if (atomic_read(&blkg->use_delay)) { + if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { has_stats = true; off += scnprintf(buf+off, size-off, " use_delay=%d delay_nsec=%llu", @@ -967,7 +964,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) has_stats = true; off += written; } -next: + if (has_stats) { if (off < size - 1) { off += scnprintf(buf+off, size-off, "\n"); diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index d973c38ee4fd..0fff7b56df0e 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -917,6 +917,9 @@ static size_t iolatency_pd_stat(struct blkg_policy_data *pd, char *buf, unsigned long long avg_lat; unsigned long long cur_win; + if (!blkcg_debug_stats) + return 0; + if (iolat->ssd) return iolatency_ssd_stat(iolat, buf, size); diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 689a58231288..12811091fd50 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -181,6 +181,7 @@ struct blkcg_policy { extern struct blkcg blkcg_root; extern struct cgroup_subsys_state * const blkcg_root_css; +extern bool blkcg_debug_stats; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); From 1624b0b200399bd6cd2b46ab3494738d1aef6b75 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Tue, 16 Jul 2019 21:59:35 +0900 Subject: [PATCH 026/823] block: fix sysfs module parameters directory path in comment The runtime configurable module parameter files are located under /sys/module/MODULENAME/parameters, not /sys/module/MODULENAME. Cc: Jens Axboe Signed-off-by: Akinobu Mita Signed-off-by: Jens Axboe --- block/genhd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/genhd.c b/block/genhd.c index 97887e59f3b2..54f1f0d381f4 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1969,7 +1969,7 @@ static const struct attribute *disk_events_attrs[] = { * The default polling interval can be specified by the kernel * parameter block.events_dfl_poll_msecs which defaults to 0 * (disable). This can also be modified runtime by writing to - * /sys/module/block/events_dfl_poll_msecs. + * /sys/module/block/parameters/events_dfl_poll_msecs. */ static int disk_events_set_dfl_poll_msecs(const char *val, const struct kernel_param *kp) From 1ef55fed9219963359a7b3bc7edca8517c6e45ac Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Sat, 13 Jul 2019 11:07:16 +0200 Subject: [PATCH 027/823] regulator: axp20x: fix DCDCA and DCDCD for AXP806 Refactoring of the driver introduced bugs in AXP806's DCDCA and DCDCD regulator definitions. In DCDCA case, AXP806_DCDCA_1120mV_STEPS was obtained by subtracting 0x47 and 0x33. This should be 0x14 (hex) and not 14 (dec). In DCDCD case, axp806_dcdcd_ranges[] contains two ranges with same start and end macros, which is clearly wrong. Second range starts at 1.6V so it should use AXP806_DCDCD_1600mV_[START|END] macros. They are already defined but unused. Fixes: db4a555f7c4c ("regulator: axp20x: use defines for masks") Signed-off-by: Jernej Skrabec Link: https://lore.kernel.org/r/20190713090717.347-2-jernej.skrabec@siol.net Signed-off-by: Mark Brown --- drivers/regulator/axp20x-regulator.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index 152053361862..c951568994a1 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -240,7 +240,7 @@ #define AXP806_DCDCA_600mV_END \ (AXP806_DCDCA_600mV_START + AXP806_DCDCA_600mV_STEPS) #define AXP806_DCDCA_1120mV_START 0x33 -#define AXP806_DCDCA_1120mV_STEPS 14 +#define AXP806_DCDCA_1120mV_STEPS 20 #define AXP806_DCDCA_1120mV_END \ (AXP806_DCDCA_1120mV_START + AXP806_DCDCA_1120mV_STEPS) #define AXP806_DCDCA_NUM_VOLTAGES 72 @@ -774,8 +774,8 @@ static const struct regulator_linear_range axp806_dcdcd_ranges[] = { AXP806_DCDCD_600mV_END, 20000), REGULATOR_LINEAR_RANGE(1600000, - AXP806_DCDCD_600mV_START, - AXP806_DCDCD_600mV_END, + AXP806_DCDCD_1600mV_START, + AXP806_DCDCD_1600mV_END, 100000), }; From 8f46e22b5ac692b48d04bb722547ca17b66dda02 Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Sat, 13 Jul 2019 11:07:17 +0200 Subject: [PATCH 028/823] regulator: axp20x: fix DCDC5 and DCDC6 for AXP803 Refactoring of axp20x driver introduced a bug in AXP803's DCDC6 regulator definition. AXP803_DCDC6_1120mV_STEPS was obtained by subtracting 0x47 and 0x33. This should be 0x14 (hex) and not 14 (dec). Refactoring also carried over a bug in DCDC5 regulator definition. Number of possible voltages must be for 1 bigger than maximum valid voltage index, because 0 is also valid and it means lowest voltage. Fixes: 1dbe0ccb0631 ("regulator: axp20x-regulator: add support for AXP803") Fixes: db4a555f7c4c ("regulator: axp20x: use defines for masks") Signed-off-by: Jernej Skrabec Link: https://lore.kernel.org/r/20190713090717.347-3-jernej.skrabec@siol.net Signed-off-by: Mark Brown --- drivers/regulator/axp20x-regulator.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index c951568994a1..989506bd90b1 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -174,14 +174,14 @@ #define AXP803_DCDC5_1140mV_STEPS 35 #define AXP803_DCDC5_1140mV_END \ (AXP803_DCDC5_1140mV_START + AXP803_DCDC5_1140mV_STEPS) -#define AXP803_DCDC5_NUM_VOLTAGES 68 +#define AXP803_DCDC5_NUM_VOLTAGES 69 #define AXP803_DCDC6_600mV_START 0x00 #define AXP803_DCDC6_600mV_STEPS 50 #define AXP803_DCDC6_600mV_END \ (AXP803_DCDC6_600mV_START + AXP803_DCDC6_600mV_STEPS) #define AXP803_DCDC6_1120mV_START 0x33 -#define AXP803_DCDC6_1120mV_STEPS 14 +#define AXP803_DCDC6_1120mV_STEPS 20 #define AXP803_DCDC6_1120mV_END \ (AXP803_DCDC6_1120mV_START + AXP803_DCDC6_1120mV_STEPS) #define AXP803_DCDC6_NUM_VOLTAGES 72 From 4c4cbbaa693a5cc435664f2f220c8b0be873abd1 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Wed, 17 Jul 2019 11:35:35 +0200 Subject: [PATCH 029/823] Documentation: fix vfio-ccw doc *Really* mark the literal block as such. Fixes: 127e62174041 ("vfio-ccw: Update documentation for csch/hsch") Signed-off-by: Cornelia Huck --- Documentation/s390/vfio-ccw.rst | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/Documentation/s390/vfio-ccw.rst b/Documentation/s390/vfio-ccw.rst index be2af10e12b4..3fe918f0c80d 100644 --- a/Documentation/s390/vfio-ccw.rst +++ b/Documentation/s390/vfio-ccw.rst @@ -218,14 +218,14 @@ vfio-ccw cmd region ------------------- The vfio-ccw cmd region is used to accept asynchronous instructions -from userspace. +from userspace:: -#define VFIO_CCW_ASYNC_CMD_HSCH (1 << 0) -#define VFIO_CCW_ASYNC_CMD_CSCH (1 << 1) -struct ccw_cmd_region { - __u32 command; - __u32 ret_code; -} __packed; + #define VFIO_CCW_ASYNC_CMD_HSCH (1 << 0) + #define VFIO_CCW_ASYNC_CMD_CSCH (1 << 1) + struct ccw_cmd_region { + __u32 command; + __u32 ret_code; + } __packed; This region is exposed via region type VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD. From 4d2e26a38fbcde2ba14882cbdb845caa1c17e19b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 10 Apr 2019 08:32:42 -0300 Subject: [PATCH 030/823] docs: powerpc: convert docs to ReST and rename to *.rst Convert docs to ReST and add them to the arch-specific book. The conversion here was trivial, as almost every file there was already using an elegant format close to ReST standard. The changes were mostly to mark literal blocks and add a few missing section title identifiers. One note with regards to "--": on Sphinx, this can't be used to identify a list, as it will format it badly. This can be used, however, to identify a long hyphen - and "---" is an even longer one. At its new index.rst, let's add a :orphan: while this is not linked to the main index.rst file, in order to avoid build warnings. Signed-off-by: Mauro Carvalho Chehab Acked-by: Andrew Donnellan # cxl --- Documentation/PCI/pci-error-recovery.rst | 5 +- Documentation/index.rst | 1 + .../{bootwrapper.txt => bootwrapper.rst} | 28 +++- .../{cpu_families.txt => cpu_families.rst} | 23 +-- .../{cpu_features.txt => cpu_features.rst} | 6 +- Documentation/powerpc/{cxl.txt => cxl.rst} | 46 ++++-- .../powerpc/{cxlflash.txt => cxlflash.rst} | 10 +- .../{DAWR-POWER9.txt => dawr-power9.rst} | 15 +- Documentation/powerpc/{dscr.txt => dscr.rst} | 18 +- ...ecovery.txt => eeh-pci-error-recovery.rst} | 110 ++++++------ ...ed-dump.txt => firmware-assisted-dump.rst} | 117 +++++++------ Documentation/powerpc/{hvcs.txt => hvcs.rst} | 108 ++++++------ Documentation/powerpc/index.rst | 34 ++++ Documentation/powerpc/isa-versions.rst | 15 +- .../powerpc/{mpc52xx.txt => mpc52xx.rst} | 12 +- ...nv.txt => pci_iov_resource_on_powernv.rst} | 15 +- .../powerpc/{pmu-ebb.txt => pmu-ebb.rst} | 1 + Documentation/powerpc/ptrace.rst | 156 ++++++++++++++++++ Documentation/powerpc/ptrace.txt | 151 ----------------- .../{qe_firmware.txt => qe_firmware.rst} | 37 +++-- .../{syscall64-abi.txt => syscall64-abi.rst} | 29 ++-- ...al_memory.txt => transactional_memory.rst} | 45 ++--- MAINTAINERS | 6 +- arch/powerpc/kernel/exceptions-64s.S | 2 +- drivers/soc/fsl/qe/qe.c | 2 +- drivers/tty/hvc/hvcs.c | 2 +- include/soc/fsl/qe/qe.h | 2 +- 27 files changed, 568 insertions(+), 428 deletions(-) rename Documentation/powerpc/{bootwrapper.txt => bootwrapper.rst} (93%) rename Documentation/powerpc/{cpu_families.txt => cpu_families.rst} (95%) rename Documentation/powerpc/{cpu_features.txt => cpu_features.rst} (97%) rename Documentation/powerpc/{cxl.txt => cxl.rst} (95%) rename Documentation/powerpc/{cxlflash.txt => cxlflash.rst} (98%) rename Documentation/powerpc/{DAWR-POWER9.txt => dawr-power9.rst} (95%) rename Documentation/powerpc/{dscr.txt => dscr.rst} (91%) rename Documentation/powerpc/{eeh-pci-error-recovery.txt => eeh-pci-error-recovery.rst} (82%) rename Documentation/powerpc/{firmware-assisted-dump.txt => firmware-assisted-dump.rst} (80%) rename Documentation/powerpc/{hvcs.txt => hvcs.rst} (91%) create mode 100644 Documentation/powerpc/index.rst rename Documentation/powerpc/{mpc52xx.txt => mpc52xx.rst} (91%) rename Documentation/powerpc/{pci_iov_resource_on_powernv.txt => pci_iov_resource_on_powernv.rst} (97%) rename Documentation/powerpc/{pmu-ebb.txt => pmu-ebb.rst} (99%) create mode 100644 Documentation/powerpc/ptrace.rst delete mode 100644 Documentation/powerpc/ptrace.txt rename Documentation/powerpc/{qe_firmware.txt => qe_firmware.rst} (95%) rename Documentation/powerpc/{syscall64-abi.txt => syscall64-abi.rst} (82%) rename Documentation/powerpc/{transactional_memory.txt => transactional_memory.rst} (93%) diff --git a/Documentation/PCI/pci-error-recovery.rst b/Documentation/PCI/pci-error-recovery.rst index 83db42092935..e5d450df06b4 100644 --- a/Documentation/PCI/pci-error-recovery.rst +++ b/Documentation/PCI/pci-error-recovery.rst @@ -403,7 +403,7 @@ That is, the recovery API only requires that: .. note:: Implementation details for the powerpc platform are discussed in - the file Documentation/powerpc/eeh-pci-error-recovery.txt + the file Documentation/powerpc/eeh-pci-error-recovery.rst As of this writing, there is a growing list of device drivers with patches implementing error recovery. Not all of these patches are in @@ -422,3 +422,6 @@ That is, the recovery API only requires that: - drivers/net/cxgb3 - drivers/net/s2io.c - drivers/net/qlge + +The End +------- diff --git a/Documentation/index.rst b/Documentation/index.rst index 70ae148ec980..3fe6170aa41d 100644 --- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -143,6 +143,7 @@ implementation. arm64/index ia64/index m68k/index + powerpc/index riscv/index s390/index sh/index diff --git a/Documentation/powerpc/bootwrapper.txt b/Documentation/powerpc/bootwrapper.rst similarity index 93% rename from Documentation/powerpc/bootwrapper.txt rename to Documentation/powerpc/bootwrapper.rst index d60fced5e1cc..a6292afba573 100644 --- a/Documentation/powerpc/bootwrapper.txt +++ b/Documentation/powerpc/bootwrapper.rst @@ -1,5 +1,7 @@ +======================== The PowerPC boot wrapper ------------------------- +======================== + Copyright (C) Secret Lab Technologies Ltd. PowerPC image targets compresses and wraps the kernel image (vmlinux) with @@ -21,6 +23,7 @@ it uses the wrapper script (arch/powerpc/boot/wrapper) to generate target image. The details of the build system is discussed in the next section. Currently, the following image format targets exist: + ==================== ======================================================== cuImage.%: Backwards compatible uImage for older version of U-Boot (for versions that don't understand the device tree). This image embeds a device tree blob inside @@ -29,31 +32,36 @@ Currently, the following image format targets exist: with boot wrapper code that extracts data from the old bd_info structure and loads the data into the device tree before jumping into the kernel. - Because of the series of #ifdefs found in the + + Because of the series of #ifdefs found in the bd_info structure used in the old U-Boot interfaces, cuImages are platform specific. Each specific U-Boot platform has a different platform init file which populates the embedded device tree with data from the platform specific bd_info file. The platform specific cuImage platform init code can be found in - arch/powerpc/boot/cuboot.*.c. Selection of the correct + `arch/powerpc/boot/cuboot.*.c`. Selection of the correct cuImage init code for a specific board can be found in the wrapper structure. + dtbImage.%: Similar to zImage, except device tree blob is embedded inside the image instead of provided by firmware. The output image file can be either an elf file or a flat binary depending on the platform. - dtbImages are used on systems which do not have an + + dtbImages are used on systems which do not have an interface for passing a device tree directly. dtbImages are similar to simpleImages except that dtbImages have platform specific code for extracting data from the board firmware, but simpleImages do not talk to the firmware at all. - PlayStation 3 support uses dtbImage. So do Embedded + + PlayStation 3 support uses dtbImage. So do Embedded Planet boards using the PlanetCore firmware. Board specific initialization code is typically found in a file named arch/powerpc/boot/.c; but this can be overridden by the wrapper script. + simpleImage.%: Firmware independent compressed image that does not depend on any particular firmware interface and embeds a device tree blob. This image is a flat binary that @@ -61,14 +69,16 @@ Currently, the following image format targets exist: Firmware cannot pass any configuration data to the kernel with this image type and it depends entirely on the embedded device tree for all information. - The simpleImage is useful for booting systems with + + The simpleImage is useful for booting systems with an unknown firmware interface or for booting from a debugger when no firmware is present (such as on the Xilinx Virtex platform). The only assumption that simpleImage makes is that RAM is correctly initialized and that the MMU is either off or has RAM mapped to base address 0. - simpleImage also supports inserting special platform + + simpleImage also supports inserting special platform specific initialization code to the start of the bootup sequence. The virtex405 platform uses this feature to ensure that the cache is invalidated before caching @@ -81,9 +91,11 @@ Currently, the following image format targets exist: named (virtex405-.dts). Search the wrapper script for 'virtex405' and see the file arch/powerpc/boot/virtex405-head.S for details. + treeImage.%; Image format for used with OpenBIOS firmware found on some ppc4xx hardware. This image embeds a device tree blob inside the image. + uImage: Native image format used by U-Boot. The uImage target does not add any boot code. It just wraps a compressed vmlinux in the uImage data structure. This image @@ -91,12 +103,14 @@ Currently, the following image format targets exist: a device tree to the kernel at boot. If using an older version of U-Boot, then you need to use a cuImage instead. + zImage.%: Image format which does not embed a device tree. Used by OpenFirmware and other firmware interfaces which are able to supply a device tree. This image expects firmware to provide the device tree at boot. Typically, if you have general purpose PowerPC hardware then you want this image format. + ==================== ======================================================== Image types which embed a device tree blob (simpleImage, dtbImage, treeImage, and cuImage) all generate the device tree blob from a file in the diff --git a/Documentation/powerpc/cpu_families.txt b/Documentation/powerpc/cpu_families.rst similarity index 95% rename from Documentation/powerpc/cpu_families.txt rename to Documentation/powerpc/cpu_families.rst index fc08e22feb1a..1e063c5440c3 100644 --- a/Documentation/powerpc/cpu_families.txt +++ b/Documentation/powerpc/cpu_families.rst @@ -1,3 +1,4 @@ +============ CPU Families ============ @@ -8,8 +9,8 @@ and are supported by arch/powerpc. Book3S (aka sPAPR) ------------------ - - Hash MMU - - Mix of 32 & 64 bit +- Hash MMU +- Mix of 32 & 64 bit:: +--------------+ +----------------+ | Old POWER | --------------> | RS64 (threads) | @@ -108,8 +109,8 @@ Book3S (aka sPAPR) IBM BookE --------- - - Software loaded TLB. - - All 32 bit +- Software loaded TLB. +- All 32 bit:: +--------------+ | 401 | @@ -155,8 +156,8 @@ IBM BookE Motorola/Freescale 8xx ---------------------- - - Software loaded with hardware assist. - - All 32 bit +- Software loaded with hardware assist. +- All 32 bit:: +-------------+ | MPC8xx Core | @@ -166,9 +167,9 @@ Motorola/Freescale 8xx Freescale BookE --------------- - - Software loaded TLB. - - e6500 adds HW loaded indirect TLB entries. - - Mix of 32 & 64 bit +- Software loaded TLB. +- e6500 adds HW loaded indirect TLB entries. +- Mix of 32 & 64 bit:: +--------------+ | e200 | @@ -207,8 +208,8 @@ Freescale BookE IBM A2 core ----------- - - Book3E, software loaded TLB + HW loaded indirect TLB entries. - - 64 bit +- Book3E, software loaded TLB + HW loaded indirect TLB entries. +- 64 bit:: +--------------+ +----------------+ | A2 core | --> | WSP | diff --git a/Documentation/powerpc/cpu_features.txt b/Documentation/powerpc/cpu_features.rst similarity index 97% rename from Documentation/powerpc/cpu_features.txt rename to Documentation/powerpc/cpu_features.rst index ae09df8722c8..b7bcdd2f41bb 100644 --- a/Documentation/powerpc/cpu_features.txt +++ b/Documentation/powerpc/cpu_features.rst @@ -1,3 +1,7 @@ +============ +CPU Features +============ + Hollis Blanchard 5 Jun 2002 @@ -32,7 +36,7 @@ anyways). After detecting the processor type, the kernel patches out sections of code that shouldn't be used by writing nop's over it. Using cpufeatures requires just 2 macros (found in arch/powerpc/include/asm/cputable.h), as seen in head.S -transfer_to_handler: +transfer_to_handler:: #ifdef CONFIG_ALTIVEC BEGIN_FTR_SECTION diff --git a/Documentation/powerpc/cxl.txt b/Documentation/powerpc/cxl.rst similarity index 95% rename from Documentation/powerpc/cxl.txt rename to Documentation/powerpc/cxl.rst index c5e8d5098ed3..920546d81326 100644 --- a/Documentation/powerpc/cxl.txt +++ b/Documentation/powerpc/cxl.rst @@ -1,3 +1,4 @@ +==================================== Coherent Accelerator Interface (CXL) ==================================== @@ -21,6 +22,8 @@ Introduction Hardware overview ================= + :: + POWER8/9 FPGA +----------+ +---------+ | | | | @@ -59,14 +62,16 @@ Hardware overview the fault. The context to which this fault is serviced is based on who owns that acceleration function. - POWER8 <-----> PSL Version 8 is compliant to the CAIA Version 1.0. - POWER9 <-----> PSL Version 9 is compliant to the CAIA Version 2.0. + - POWER8 and PSL Version 8 are compliant to the CAIA Version 1.0. + - POWER9 and PSL Version 9 are compliant to the CAIA Version 2.0. + This PSL Version 9 provides new features such as: + * Interaction with the nest MMU on the P9 chip. * Native DMA support. * Supports sending ASB_Notify messages for host thread wakeup. * Supports Atomic operations. - * .... + * etc. Cards with a PSL9 won't work on a POWER8 system and cards with a PSL8 won't work on a POWER9 system. @@ -147,7 +152,9 @@ User API master devices. A userspace library libcxl is available here: + https://github.com/ibm-capi/libcxl + This provides a C interface to this kernel API. open @@ -165,7 +172,8 @@ open When all available contexts are allocated the open call will fail and return -ENOSPC. - Note: IRQs need to be allocated for each context, which may limit + Note: + IRQs need to be allocated for each context, which may limit the number of contexts that can be created, and therefore how many times the device can be opened. The POWER8 CAPP supports 2040 IRQs and 3 are used by the kernel, so 2037 are @@ -186,7 +194,9 @@ ioctl updated as userspace allocates and frees memory. This ioctl returns once the AFU context is started. - Takes a pointer to a struct cxl_ioctl_start_work: + Takes a pointer to a struct cxl_ioctl_start_work + + :: struct cxl_ioctl_start_work { __u64 flags; @@ -269,7 +279,7 @@ read The buffer passed to read() must be at least 4K bytes. The result of the read will be a buffer of one or more events, - each event is of type struct cxl_event, of varying size. + each event is of type struct cxl_event, of varying size:: struct cxl_event { struct cxl_event_header header; @@ -280,7 +290,9 @@ read }; }; - The struct cxl_event_header is defined as: + The struct cxl_event_header is defined as + + :: struct cxl_event_header { __u16 type; @@ -307,7 +319,9 @@ read For future extensions and padding. If the event type is CXL_EVENT_AFU_INTERRUPT then the event - structure is defined as: + structure is defined as + + :: struct cxl_event_afu_interrupt { __u16 flags; @@ -326,7 +340,9 @@ read For future extensions and padding. If the event type is CXL_EVENT_DATA_STORAGE then the event - structure is defined as: + structure is defined as + + :: struct cxl_event_data_storage { __u16 flags; @@ -356,7 +372,9 @@ read For future extensions If the event type is CXL_EVENT_AFU_ERROR then the event structure - is defined as: + is defined as + + :: struct cxl_event_afu_error { __u16 flags; @@ -393,15 +411,15 @@ open ioctl ----- -CXL_IOCTL_DOWNLOAD_IMAGE: -CXL_IOCTL_VALIDATE_IMAGE: +CXL_IOCTL_DOWNLOAD_IMAGE / CXL_IOCTL_VALIDATE_IMAGE: Starts and controls flashing a new FPGA image. Partial reconfiguration is not supported (yet), so the image must contain a copy of the PSL and AFU(s). Since an image can be quite large, the caller may have to iterate, splitting the image in smaller chunks. - Takes a pointer to a struct cxl_adapter_image: + Takes a pointer to a struct cxl_adapter_image:: + struct cxl_adapter_image { __u64 flags; __u64 data; @@ -442,7 +460,7 @@ Udev rules The following udev rules could be used to create a symlink to the most logical chardev to use in any programming mode (afuX.Yd for dedicated, afuX.Ys for afu directed), since the API is virtually - identical for each: + identical for each:: SUBSYSTEM=="cxl", ATTRS{mode}=="dedicated_process", SYMLINK="cxl/%b" SUBSYSTEM=="cxl", ATTRS{mode}=="afu_directed", \ diff --git a/Documentation/powerpc/cxlflash.txt b/Documentation/powerpc/cxlflash.rst similarity index 98% rename from Documentation/powerpc/cxlflash.txt rename to Documentation/powerpc/cxlflash.rst index a64bdaa0a1cf..cea67931b3b9 100644 --- a/Documentation/powerpc/cxlflash.txt +++ b/Documentation/powerpc/cxlflash.rst @@ -1,3 +1,7 @@ +================================ +Coherent Accelerator (CXL) Flash +================================ + Introduction ============ @@ -28,7 +32,7 @@ Introduction responsible for the initialization of the adapter, setting up the special path for user space access, and performing error recovery. It communicates directly the Flash Accelerator Functional Unit (AFU) - as described in Documentation/powerpc/cxl.txt. + as described in Documentation/powerpc/cxl.rst. The cxlflash driver supports two, mutually exclusive, modes of operation at the device (LUN) level: @@ -58,7 +62,7 @@ Overview The CXL Flash Adapter Driver establishes a master context with the AFU. It uses memory mapped I/O (MMIO) for this control and setup. The - Adapter Problem Space Memory Map looks like this: + Adapter Problem Space Memory Map looks like this:: +-------------------------------+ | 512 * 64 KB User MMIO | @@ -375,7 +379,7 @@ CXL Flash Driver Host IOCTLs Each host adapter instance that is supported by the cxlflash driver has a special character device associated with it to enable a set of host management function. These character devices are hosted in a - class dedicated for cxlflash and can be accessed via /dev/cxlflash/*. + class dedicated for cxlflash and can be accessed via `/dev/cxlflash/*`. Applications can be written to perform various functions using the host ioctl APIs below. diff --git a/Documentation/powerpc/DAWR-POWER9.txt b/Documentation/powerpc/dawr-power9.rst similarity index 95% rename from Documentation/powerpc/DAWR-POWER9.txt rename to Documentation/powerpc/dawr-power9.rst index ecdbb076438c..c96ab6befd9c 100644 --- a/Documentation/powerpc/DAWR-POWER9.txt +++ b/Documentation/powerpc/dawr-power9.rst @@ -1,10 +1,11 @@ +===================== DAWR issues on POWER9 -============================ +===================== On POWER9 the Data Address Watchpoint Register (DAWR) can cause a checkstop if it points to cache inhibited (CI) memory. Currently Linux has no way to disinguish CI memory when configuring the DAWR, so (for now) the DAWR is -disabled by this commit: +disabled by this commit:: commit 9654153158d3e0684a1bdb76dbababdb7111d5a0 Author: Michael Neuling @@ -12,7 +13,7 @@ disabled by this commit: powerpc: Disable DAWR in the base POWER9 CPU features Technical Details: -============================ +================== DAWR has 6 different ways of being set. 1) ptrace @@ -37,7 +38,7 @@ DAWR on the migration. For xmon, the 'bd' command will return an error on P9. Consequences for users -============================ +====================== For GDB watchpoints (ie 'watch' command) on POWER9 bare metal , GDB will accept the command. Unfortunately since there is no hardware @@ -57,8 +58,8 @@ trapped in GDB. The watchpoint is remembered, so if the guest is migrated back to the POWER8 host, it will start working again. Force enabling the DAWR -============================= -Kernels (since ~v5.2) have an option to force enable the DAWR via: +======================= +Kernels (since ~v5.2) have an option to force enable the DAWR via:: echo Y > /sys/kernel/debug/powerpc/dawr_enable_dangerous @@ -86,5 +87,7 @@ dawr_enable_dangerous file will fail if the hypervisor doesn't support writing the DAWR. To double check the DAWR is working, run this kernel selftest: + tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c + Any errors/failures/skips mean something is wrong. diff --git a/Documentation/powerpc/dscr.txt b/Documentation/powerpc/dscr.rst similarity index 91% rename from Documentation/powerpc/dscr.txt rename to Documentation/powerpc/dscr.rst index ece300c64f76..2ab99006014c 100644 --- a/Documentation/powerpc/dscr.txt +++ b/Documentation/powerpc/dscr.rst @@ -1,5 +1,6 @@ - DSCR (Data Stream Control Register) - ================================================ +=================================== +DSCR (Data Stream Control Register) +=================================== DSCR register in powerpc allows user to have some control of prefetch of data stream in the processor. Please refer to the ISA documents or related manual @@ -10,14 +11,17 @@ user interface. (A) Data Structures: - (1) thread_struct: + (1) thread_struct:: + dscr /* Thread DSCR value */ dscr_inherit /* Thread has changed default DSCR */ - (2) PACA: + (2) PACA:: + dscr_default /* per-CPU DSCR default value */ - (3) sysfs.c: + (3) sysfs.c:: + dscr_default /* System DSCR default value */ (B) Scheduler Changes: @@ -35,8 +39,8 @@ user interface. (C) SYSFS Interface: - Global DSCR default: /sys/devices/system/cpu/dscr_default - CPU specific DSCR default: /sys/devices/system/cpu/cpuN/dscr + - Global DSCR default: /sys/devices/system/cpu/dscr_default + - CPU specific DSCR default: /sys/devices/system/cpu/cpuN/dscr Changing the global DSCR default in the sysfs will change all the CPU specific DSCR defaults immediately in their PACA structures. Again if diff --git a/Documentation/powerpc/eeh-pci-error-recovery.txt b/Documentation/powerpc/eeh-pci-error-recovery.rst similarity index 82% rename from Documentation/powerpc/eeh-pci-error-recovery.txt rename to Documentation/powerpc/eeh-pci-error-recovery.rst index 678189280bb4..438a87ebc095 100644 --- a/Documentation/powerpc/eeh-pci-error-recovery.txt +++ b/Documentation/powerpc/eeh-pci-error-recovery.rst @@ -1,10 +1,10 @@ +========================== +PCI Bus EEH Error Recovery +========================== +Linas Vepstas - PCI Bus EEH Error Recovery - -------------------------- - Linas Vepstas - - 12 January 2005 +12 January 2005 Overview: @@ -143,17 +143,17 @@ seen in /proc/ppc64/eeh (subject to change). Normally, almost all of these occur during boot, when the PCI bus is scanned, where a large number of 0xff reads are part of the bus scan procedure. -If a frozen slot is detected, code in -arch/powerpc/platforms/pseries/eeh.c will print a stack trace to -syslog (/var/log/messages). This stack trace has proven to be very -useful to device-driver authors for finding out at what point the EEH -error was detected, as the error itself usually occurs slightly +If a frozen slot is detected, code in +arch/powerpc/platforms/pseries/eeh.c will print a stack trace to +syslog (/var/log/messages). This stack trace has proven to be very +useful to device-driver authors for finding out at what point the EEH +error was detected, as the error itself usually occurs slightly beforehand. Next, it uses the Linux kernel notifier chain/work queue mechanism to allow any interested parties to find out about the failure. Device drivers, or other parts of the kernel, can use -eeh_register_notifier(struct notifier_block *) to find out about EEH +`eeh_register_notifier(struct notifier_block *)` to find out about EEH events. The event will include a pointer to the pci device, the device node and some state info. Receivers of the event can "do as they wish"; the default handler will be described further in this @@ -162,10 +162,13 @@ section. To assist in the recovery of the device, eeh.c exports the following functions: -rtas_set_slot_reset() -- assert the PCI #RST line for 1/8th of a second -rtas_configure_bridge() -- ask firmware to configure any PCI bridges +rtas_set_slot_reset() + assert the PCI #RST line for 1/8th of a second +rtas_configure_bridge() + ask firmware to configure any PCI bridges located topologically under the pci slot. -eeh_save_bars() and eeh_restore_bars(): save and restore the PCI +eeh_save_bars() and eeh_restore_bars(): + save and restore the PCI config-space info for a device and any devices under it. @@ -191,7 +194,7 @@ events get delivered to user-space scripts. Following is an example sequence of events that cause a device driver close function to be called during the first phase of an EEH reset. -The following sequence is an example of the pcnet32 device driver. +The following sequence is an example of the pcnet32 device driver:: rpa_php_unconfig_pci_adapter (struct slot *) // in rpaphp_pci.c { @@ -241,53 +244,54 @@ The following sequence is an example of the pcnet32 device driver. }}}}}} - in drivers/pci/pci_driver.c, - struct device_driver->remove() is just pci_device_remove() - which calls struct pci_driver->remove() which is pcnet32_remove_one() - which calls unregister_netdev() (in net/core/dev.c) - which calls dev_close() (in net/core/dev.c) - which calls dev->stop() which is pcnet32_close() - which then does the appropriate shutdown. +in drivers/pci/pci_driver.c, +struct device_driver->remove() is just pci_device_remove() +which calls struct pci_driver->remove() which is pcnet32_remove_one() +which calls unregister_netdev() (in net/core/dev.c) +which calls dev_close() (in net/core/dev.c) +which calls dev->stop() which is pcnet32_close() +which then does the appropriate shutdown. --- -Following is the analogous stack trace for events sent to user-space -when the pci device is unconfigured. -rpa_php_unconfig_pci_adapter() { // in rpaphp_pci.c - calls - pci_remove_bus_device (struct pci_dev *) { // in /drivers/pci/remove.c +Following is the analogous stack trace for events sent to user-space +when the pci device is unconfigured:: + + rpa_php_unconfig_pci_adapter() { // in rpaphp_pci.c calls - pci_destroy_dev (struct pci_dev *) { + pci_remove_bus_device (struct pci_dev *) { // in /drivers/pci/remove.c calls - device_unregister (&dev->dev) { // in /drivers/base/core.c + pci_destroy_dev (struct pci_dev *) { calls - device_del(struct device * dev) { // in /drivers/base/core.c + device_unregister (&dev->dev) { // in /drivers/base/core.c calls - kobject_del() { //in /libs/kobject.c + device_del(struct device * dev) { // in /drivers/base/core.c calls - kobject_uevent() { // in /libs/kobject.c + kobject_del() { //in /libs/kobject.c calls - kset_uevent() { // in /lib/kobject.c + kobject_uevent() { // in /libs/kobject.c calls - kset->uevent_ops->uevent() // which is really just - a call to - dev_uevent() { // in /drivers/base/core.c + kset_uevent() { // in /lib/kobject.c calls - dev->bus->uevent() which is really just a call to - pci_uevent () { // in drivers/pci/hotplug.c - which prints device name, etc.... + kset->uevent_ops->uevent() // which is really just + a call to + dev_uevent() { // in /drivers/base/core.c + calls + dev->bus->uevent() which is really just a call to + pci_uevent () { // in drivers/pci/hotplug.c + which prints device name, etc.... + } } - } - then kobject_uevent() sends a netlink uevent to userspace - --> userspace uevent - (during early boot, nobody listens to netlink events and - kobject_uevent() executes uevent_helper[], which runs the - event process /sbin/hotplug) + then kobject_uevent() sends a netlink uevent to userspace + --> userspace uevent + (during early boot, nobody listens to netlink events and + kobject_uevent() executes uevent_helper[], which runs the + event process /sbin/hotplug) + } } - } - kobject_del() then calls sysfs_remove_dir(), which would - trigger any user-space daemon that was watching /sysfs, - and notice the delete event. + kobject_del() then calls sysfs_remove_dir(), which would + trigger any user-space daemon that was watching /sysfs, + and notice the delete event. Pro's and Con's of the Current Design @@ -299,12 +303,12 @@ individual device drivers, so that the current design throws a wide net. The biggest negative of the design is that it potentially disturbs network daemons and file systems that didn't need to be disturbed. --- A minor complaint is that resetting the network card causes +- A minor complaint is that resetting the network card causes user-space back-to-back ifdown/ifup burps that potentially disturb network daemons, that didn't need to even know that the pci card was being rebooted. --- A more serious concern is that the same reset, for SCSI devices, +- A more serious concern is that the same reset, for SCSI devices, causes havoc to mounted file systems. Scripts cannot post-facto unmount a file system without flushing pending buffers, but this is impossible, because I/O has already been stopped. Thus, @@ -322,7 +326,7 @@ network daemons and file systems that didn't need to be disturbed. from the block layer. It would be very natural to add an EEH reset into this chain of events. --- If a SCSI error occurs for the root device, all is lost unless +- If a SCSI error occurs for the root device, all is lost unless the sysadmin had the foresight to run /bin, /sbin, /etc, /var and so on, out of ramdisk/tmpfs. @@ -330,5 +334,3 @@ network daemons and file systems that didn't need to be disturbed. Conclusions ----------- There's forward progress ... - - diff --git a/Documentation/powerpc/firmware-assisted-dump.txt b/Documentation/powerpc/firmware-assisted-dump.rst similarity index 80% rename from Documentation/powerpc/firmware-assisted-dump.txt rename to Documentation/powerpc/firmware-assisted-dump.rst index 10e7f4d16c14..9ca12830a48e 100644 --- a/Documentation/powerpc/firmware-assisted-dump.txt +++ b/Documentation/powerpc/firmware-assisted-dump.rst @@ -1,7 +1,8 @@ +====================== +Firmware-Assisted Dump +====================== - Firmware-Assisted Dump - ------------------------ - July 2011 +July 2011 The goal of firmware-assisted dump is to enable the dump of a crashed system, and to do so from a fully-reset system, and @@ -27,11 +28,11 @@ in production use. Comparing with kdump or other strategies, firmware-assisted dump offers several strong, practical advantages: --- Unlike kdump, the system has been reset, and loaded +- Unlike kdump, the system has been reset, and loaded with a fresh copy of the kernel. In particular, PCI and I/O devices have been reinitialized and are in a clean, consistent state. --- Once the dump is copied out, the memory that held the dump +- Once the dump is copied out, the memory that held the dump is immediately available to the running kernel. And therefore, unlike kdump, fadump doesn't need a 2nd reboot to get back the system to the production configuration. @@ -40,17 +41,18 @@ The above can only be accomplished by coordination with, and assistance from the Power firmware. The procedure is as follows: --- The first kernel registers the sections of memory with the +- The first kernel registers the sections of memory with the Power firmware for dump preservation during OS initialization. These registered sections of memory are reserved by the first kernel during early boot. --- When a system crashes, the Power firmware will save +- When a system crashes, the Power firmware will save the low memory (boot memory of size larger of 5% of system RAM or 256MB) of RAM to the previous registered region. It will also save system registers, and hardware PTE's. - NOTE: The term 'boot memory' means size of the low memory chunk + NOTE: + The term 'boot memory' means size of the low memory chunk that is required for a kernel to boot successfully when booted with restricted memory. By default, the boot memory size will be the larger of 5% of system RAM or 256MB. @@ -64,12 +66,12 @@ as follows: as fadump uses a predefined offset to reserve memory for boot memory dump preservation in case of a crash. --- After the low memory (boot memory) area has been saved, the +- After the low memory (boot memory) area has been saved, the firmware will reset PCI and other hardware state. It will *not* clear the RAM. It will then launch the bootloader, as normal. --- The freshly booted kernel will notice that there is a new +- The freshly booted kernel will notice that there is a new node (ibm,dump-kernel) in the device tree, indicating that there is crash data available from a previous boot. During the early boot OS will reserve rest of the memory above @@ -77,17 +79,18 @@ as follows: size. This will make sure that the second kernel will not touch any of the dump memory area. --- User-space tools will read /proc/vmcore to obtain the contents +- User-space tools will read /proc/vmcore to obtain the contents of memory, which holds the previous crashed kernel dump in ELF format. The userspace tools may copy this info to disk, or network, nas, san, iscsi, etc. as desired. --- Once the userspace tool is done saving dump, it will echo +- Once the userspace tool is done saving dump, it will echo '1' to /sys/kernel/fadump_release_mem to release the reserved memory back to general use, except the memory required for next firmware-assisted dump registration. - e.g. + e.g.:: + # echo 1 > /sys/kernel/fadump_release_mem Please note that the firmware-assisted dump feature @@ -95,7 +98,7 @@ is only available on Power6 and above systems with recent firmware versions. Implementation details: ----------------------- +----------------------- During boot, a check is made to see if firmware supports this feature on that particular machine. If it does, then @@ -121,7 +124,7 @@ Allocator (CMA) for memory reservation if CMA is configured for kernel. With CMA reservation this memory will be available for applications to use it, while kernel is prevented from using it. With this fadump will still be able to capture all of the kernel memory and most of the user -space memory except the user pages that were present in CMA region. +space memory except the user pages that were present in CMA region:: o Memory Reservation during first kernel @@ -166,7 +169,7 @@ The tools to examine the dump will be same as the ones used for kdump. How to enable firmware-assisted dump (fadump): -------------------------------------- +---------------------------------------------- 1. Set config option CONFIG_FA_DUMP=y and build kernel. 2. Boot into linux kernel with 'fadump=on' kernel cmdline option. @@ -177,19 +180,20 @@ How to enable firmware-assisted dump (fadump): to specify size of the memory to reserve for boot memory dump preservation. -NOTE: 1. 'fadump_reserve_mem=' parameter has been deprecated. Instead - use 'crashkernel=' to specify size of the memory to reserve - for boot memory dump preservation. - 2. If firmware-assisted dump fails to reserve memory then it - will fallback to existing kdump mechanism if 'crashkernel=' - option is set at kernel cmdline. - 3. if user wants to capture all of user space memory and ok with - reserved memory not available to production system, then - 'fadump=nocma' kernel parameter can be used to fallback to - old behaviour. +NOTE: + 1. 'fadump_reserve_mem=' parameter has been deprecated. Instead + use 'crashkernel=' to specify size of the memory to reserve + for boot memory dump preservation. + 2. If firmware-assisted dump fails to reserve memory then it + will fallback to existing kdump mechanism if 'crashkernel=' + option is set at kernel cmdline. + 3. if user wants to capture all of user space memory and ok with + reserved memory not available to production system, then + 'fadump=nocma' kernel parameter can be used to fallback to + old behaviour. Sysfs/debugfs files: ------------- +-------------------- Firmware-assisted dump feature uses sysfs file system to hold the control files and debugfs file to display memory reserved region. @@ -197,20 +201,20 @@ the control files and debugfs file to display memory reserved region. Here is the list of files under kernel sysfs: /sys/kernel/fadump_enabled - This is used to display the fadump status. - 0 = fadump is disabled - 1 = fadump is enabled + + - 0 = fadump is disabled + - 1 = fadump is enabled This interface can be used by kdump init scripts to identify if fadump is enabled in the kernel and act accordingly. /sys/kernel/fadump_registered - This is used to display the fadump registration status as well as to control (start/stop) the fadump registration. - 0 = fadump is not registered. - 1 = fadump is registered and ready to handle system crash. + + - 0 = fadump is not registered. + - 1 = fadump is registered and ready to handle system crash. To register fadump echo 1 > /sys/kernel/fadump_registered and echo 0 > /sys/kernel/fadump_registered for un-register and stop the @@ -219,13 +223,12 @@ Here is the list of files under kernel sysfs: easily integrated with kdump service start/stop. /sys/kernel/fadump_release_mem - This file is available only when fadump is active during second kernel. This is used to release the reserved memory region that are held for saving crash dump. To release the - reserved memory echo 1 to it: + reserved memory echo 1 to it:: - echo 1 > /sys/kernel/fadump_release_mem + echo 1 > /sys/kernel/fadump_release_mem After echo 1, the content of the /sys/kernel/debug/powerpc/fadump_region file will change to reflect the new memory reservations. @@ -238,38 +241,39 @@ Here is the list of files under powerpc debugfs: (Assuming debugfs is mounted on /sys/kernel/debug directory.) /sys/kernel/debug/powerpc/fadump_region - This file shows the reserved memory regions if fadump is enabled otherwise this file is empty. The output format - is: - : [-] bytes, Dumped: + is:: + + : [-] bytes, Dumped: e.g. - Contents when fadump is registered during first kernel + Contents when fadump is registered during first kernel:: - # cat /sys/kernel/debug/powerpc/fadump_region - CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x0 - HPTE: [0x0000006fff0020-0x0000006fff101f] 0x1000 bytes, Dumped: 0x0 - DUMP: [0x0000006fff1020-0x0000007fff101f] 0x10000000 bytes, Dumped: 0x0 + # cat /sys/kernel/debug/powerpc/fadump_region + CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x0 + HPTE: [0x0000006fff0020-0x0000006fff101f] 0x1000 bytes, Dumped: 0x0 + DUMP: [0x0000006fff1020-0x0000007fff101f] 0x10000000 bytes, Dumped: 0x0 - Contents when fadump is active during second kernel + Contents when fadump is active during second kernel:: - # cat /sys/kernel/debug/powerpc/fadump_region - CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x40020 - HPTE: [0x0000006fff0020-0x0000006fff101f] 0x1000 bytes, Dumped: 0x1000 - DUMP: [0x0000006fff1020-0x0000007fff101f] 0x10000000 bytes, Dumped: 0x10000000 - : [0x00000010000000-0x0000006ffaffff] 0x5ffb0000 bytes, Dumped: 0x5ffb0000 + # cat /sys/kernel/debug/powerpc/fadump_region + CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x40020 + HPTE: [0x0000006fff0020-0x0000006fff101f] 0x1000 bytes, Dumped: 0x1000 + DUMP: [0x0000006fff1020-0x0000007fff101f] 0x10000000 bytes, Dumped: 0x10000000 + : [0x00000010000000-0x0000006ffaffff] 0x5ffb0000 bytes, Dumped: 0x5ffb0000 -NOTE: Please refer to Documentation/filesystems/debugfs.txt on +NOTE: + Please refer to Documentation/filesystems/debugfs.txt on how to mount the debugfs filesystem. TODO: ----- - o Need to come up with the better approach to find out more + - Need to come up with the better approach to find out more accurate boot memory size that is required for a kernel to boot successfully when booted with restricted memory. - o The fadump implementation introduces a fadump crash info structure + - The fadump implementation introduces a fadump crash info structure in the scratch area before the ELF core header. The idea of introducing this structure is to pass some important crash info data to the second kernel which will help second kernel to populate ELF core header with @@ -277,7 +281,9 @@ TODO: design implementation does not address a possibility of introducing additional fields (in future) to this structure without affecting compatibility. Need to come up with the better approach to address this. + The possible approaches are: + 1. Introduce version field for version tracking, bump up the version whenever a new field is added to the structure in future. The version field can be used to find out what fields are valid for the current @@ -285,8 +291,11 @@ TODO: 2. Reserve the area of predefined size (say PAGE_SIZE) for this structure and have unused area as reserved (initialized to zero) for future field additions. + The advantage of approach 1 over 2 is we don't need to reserve extra space. ---- + Author: Mahesh Salgaonkar + This document is based on the original documentation written for phyp + assisted dump by Linas Vepstas and Manish Ahuja. diff --git a/Documentation/powerpc/hvcs.txt b/Documentation/powerpc/hvcs.rst similarity index 91% rename from Documentation/powerpc/hvcs.txt rename to Documentation/powerpc/hvcs.rst index a730ca5a07f8..6808acde672f 100644 --- a/Documentation/powerpc/hvcs.txt +++ b/Documentation/powerpc/hvcs.rst @@ -1,19 +1,22 @@ -=========================================================================== - HVCS - IBM "Hypervisor Virtual Console Server" Installation Guide - for Linux Kernel 2.6.4+ - Copyright (C) 2004 IBM Corporation +=============================================================== +HVCS IBM "Hypervisor Virtual Console Server" Installation Guide +=============================================================== -=========================================================================== -NOTE:Eight space tabs are the optimum editor setting for reading this file. -=========================================================================== +for Linux Kernel 2.6.4+ - Author(s) : Ryan S. Arnold - Date Created: March, 02, 2004 - Last Changed: August, 24, 2004 +Copyright (C) 2004 IBM Corporation ---------------------------------------------------------------------------- -Table of contents: +.. =========================================================================== +.. NOTE:Eight space tabs are the optimum editor setting for reading this file. +.. =========================================================================== + + +Author(s): Ryan S. Arnold + +Date Created: March, 02, 2004 +Last Changed: August, 24, 2004 + +.. Table of contents: 1. Driver Introduction: 2. System Requirements @@ -27,8 +30,8 @@ Table of contents: 8. Questions & Answers: 9. Reporting Bugs: ---------------------------------------------------------------------------- 1. Driver Introduction: +======================= This is the device driver for the IBM Hypervisor Virtual Console Server, "hvcs". The IBM hvcs provides a tty driver interface to allow Linux user @@ -38,8 +41,8 @@ ppc64 system. Physical hardware consoles per partition are not practical on this hardware so system consoles are accessed by this driver using firmware interfaces to virtual terminal devices. ---------------------------------------------------------------------------- 2. System Requirements: +======================= This device driver was written using 2.6.4 Linux kernel APIs and will only build and run on kernels of this version or later. @@ -52,8 +55,8 @@ Sysfs must be mounted on the system so that the user can determine which major and minor numbers are associated with each vty-server. Directions for sysfs mounting are outside the scope of this document. ---------------------------------------------------------------------------- 3. Build Options: +================= The hvcs driver registers itself as a tty driver. The tty layer dynamically allocates a block of major and minor numbers in a quantity @@ -65,11 +68,11 @@ If the default number of device entries is adequate then this driver can be built into the kernel. If not, the default can be over-ridden by inserting the driver as a module with insmod parameters. ---------------------------------------------------------------------------- 3.1 Built-in: +------------- The following menuconfig example demonstrates selecting to build this -driver into the kernel. +driver into the kernel:: Device Drivers ---> Character devices ---> @@ -77,11 +80,11 @@ driver into the kernel. Begin the kernel make process. ---------------------------------------------------------------------------- 3.2 Module: +----------- The following menuconfig example demonstrates selecting to build this -driver as a kernel module. +driver as a kernel module:: Device Drivers ---> Character devices ---> @@ -89,11 +92,11 @@ driver as a kernel module. The make process will build the following kernel modules: - hvcs.ko - hvcserver.ko + - hvcs.ko + - hvcserver.ko To insert the module with the default allocation execute the following -commands in the order they appear: +commands in the order they appear:: insmod hvcserver.ko insmod hvcs.ko @@ -103,7 +106,7 @@ be inserted first, otherwise the hvcs module will not find some of the symbols it expects. To override the default use an insmod parameter as follows (requesting 4 -tty devices as an example): +tty devices as an example):: insmod hvcs.ko hvcs_parm_num_devs=4 @@ -115,31 +118,31 @@ source file before building. NOTE: The length of time it takes to insmod the driver seems to be related to the number of tty interfaces the registering driver requests. -In order to remove the driver module execute the following command: +In order to remove the driver module execute the following command:: rmmod hvcs.ko The recommended method for installing hvcs as a module is to use depmod to build a current modules.dep file in /lib/modules/`uname -r` and then -execute: +execute:: -modprobe hvcs hvcs_parm_num_devs=4 + modprobe hvcs hvcs_parm_num_devs=4 The modules.dep file indicates that hvcserver.ko needs to be inserted before hvcs.ko and modprobe uses this file to smartly insert the modules in the proper order. The following modprobe command is used to remove hvcs and hvcserver in the -proper order: +proper order:: -modprobe -r hvcs + modprobe -r hvcs ---------------------------------------------------------------------------- 4. Installation: +================ The tty layer creates sysfs entries which contain the major and minor numbers allocated for the hvcs driver. The following snippet of "tree" -output of the sysfs directory shows where these numbers are presented: +output of the sysfs directory shows where these numbers are presented:: sys/ |-- *other sysfs base dirs* @@ -164,7 +167,7 @@ output of the sysfs directory shows where these numbers are presented: |-- *other sysfs base dirs* For the above examples the following output is a result of cat'ing the -"dev" entry in the hvcs directory: +"dev" entry in the hvcs directory:: Pow5:/sys/class/tty/hvcs0/ # cat dev 254:0 @@ -184,7 +187,7 @@ systems running hvcs will already have the device entries created or udev will do it automatically. Given the example output above, to manually create a /dev/hvcs* node entry -mknod can be used as follows: +mknod can be used as follows:: mknod /dev/hvcs0 c 254 0 mknod /dev/hvcs1 c 254 1 @@ -195,15 +198,15 @@ Using mknod to manually create the device entries makes these device nodes persistent. Once created they will exist prior to the driver insmod. Attempting to connect an application to /dev/hvcs* prior to insertion of -the hvcs module will result in an error message similar to the following: +the hvcs module will result in an error message similar to the following:: "/dev/hvcs*: No such device". NOTE: Just because there is a device node present doesn't mean that there is a vty-server device configured for that node. ---------------------------------------------------------------------------- 5. Connection +============= Since this driver controls devices that provide a tty interface a user can interact with the device node entries using any standard tty-interactive @@ -249,7 +252,7 @@ vty-server adapter is associated with which /dev/hvcs* node a special sysfs attribute has been added to each vty-server sysfs entry. This entry is called "index" and showing it reveals an integer that refers to the /dev/hvcs* entry to use to connect to that device. For instance cating the -index attribute of vty-server adapter 30000004 shows the following. +index attribute of vty-server adapter 30000004 shows the following:: Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat index 2 @@ -262,8 +265,8 @@ system the /dev/hvcs* entry that interacts with a particular vty-server adapter is not guaranteed to remain the same across system reboots. Look in the Q & A section for more on this issue. ---------------------------------------------------------------------------- 6. Disconnection +================ As a security feature to prevent the delivery of stale data to an unintended target the Power5 system firmware disables the fetching of data @@ -305,7 +308,7 @@ connection between the vty-server and target vty ONLY if the vterm_state previously read '1'. The write directive is ignored if the vterm_state read '0' or if any value other than '0' was written to the vterm_state attribute. The following example will show the method used for verifying -the vty-server connection status and disconnecting a vty-server connection. +the vty-server connection status and disconnecting a vty-server connection:: Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat vterm_state 1 @@ -318,12 +321,12 @@ the vty-server connection status and disconnecting a vty-server connection. All vty-server connections are automatically terminated when the device is hotplug removed and when the module is removed. ---------------------------------------------------------------------------- 7. Configuration +================ Each vty-server has a sysfs entry in the /sys/devices/vio directory, which is symlinked in several other sysfs tree directories, notably under the -hvcs driver entry, which looks like the following example: +hvcs driver entry, which looks like the following example:: Pow5:/sys/bus/vio/drivers/hvcs # ls . .. 30000003 30000004 rescan @@ -344,7 +347,7 @@ completed or was never executed. Vty-server entries in this directory are a 32 bit partition unique unit address that is created by firmware. An example vty-server sysfs entry -looks like the following: +looks like the following:: Pow5:/sys/bus/vio/drivers/hvcs/30000004 # ls . current_vty devspec name partner_vtys @@ -352,21 +355,21 @@ looks like the following: Each entry is provided, by default with a "name" attribute. Reading the "name" attribute will reveal the device type as shown in the following -example: +example:: Pow5:/sys/bus/vio/drivers/hvcs/30000003 # cat name vty-server Each entry is also provided, by default, with a "devspec" attribute which reveals the full device specification when read, as shown in the following -example: +example:: Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat devspec /vdevice/vty-server@30000004 Each vty-server sysfs dir is provided with two read-only attributes that provide lists of easily parsed partner vty data: "partner_vtys" and -"partner_clcs". +"partner_clcs":: Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat partner_vtys 30000000 @@ -396,7 +399,7 @@ A vty-server can only be connected to a single vty at a time. The entry, read. The current_vty can be changed by writing a valid partner clc to the entry -as in the following example: +as in the following example:: Pow5:/sys/bus/vio/drivers/hvcs/30000004 # echo U5112.428.10304 8A-V4-C0 > current_vty @@ -408,9 +411,9 @@ currently open connection is freed. Information on the "vterm_state" attribute was covered earlier on the chapter entitled "disconnection". ---------------------------------------------------------------------------- 8. Questions & Answers: -=========================================================================== +======================= + Q: What are the security concerns involving hvcs? A: There are three main security concerns: @@ -429,6 +432,7 @@ A: There are three main security concerns: partition) will experience the previously logged in session. --------------------------------------------------------------------------- + Q: How do I multiplex a console that I grab through hvcs so that other people can see it: @@ -440,6 +444,7 @@ term type "screen" to others. This means that curses based programs may not display properly in screen sessions. --------------------------------------------------------------------------- + Q: Why are the colors all messed up? Q: Why are the control characters acting strange or not working? Q: Why is the console output all strange and unintelligible? @@ -455,6 +460,7 @@ disconnect from the console. This will ensure that the next user gets their own TERM type set when they login. --------------------------------------------------------------------------- + Q: When I try to CONNECT kermit to an hvcs device I get: "Sorry, can't open connection: /dev/hvcs*"What is happening? @@ -490,6 +496,7 @@ A: There is not a corresponding vty-server device that maps to an existing /dev/hvcs* entry. --------------------------------------------------------------------------- + Q: When I try to CONNECT kermit to an hvcs device I get: "Sorry, write access to UUCP lockfile directory denied." @@ -497,6 +504,7 @@ A: The /dev/hvcs* entry you have specified doesn't exist where you said it does? Maybe you haven't inserted the module (on systems with udev). --------------------------------------------------------------------------- + Q: If I already have one Linux partition installed can I use hvcs on said partition to provide the console for the install of a second Linux partition? @@ -505,6 +513,7 @@ A: Yes granted that your are connected to the /dev/hvcs* device using kermit or cu or some other program that doesn't provide terminal emulation. --------------------------------------------------------------------------- + Q: Can I connect to more than one partition's console at a time using this driver? @@ -512,6 +521,7 @@ A: Yes. Of course this means that there must be more than one vty-server configured for this partition and each must point to a disconnected vty. --------------------------------------------------------------------------- + Q: Does the hvcs driver support dynamic (hotplug) addition of devices? A: Yes, if you have dlpar and hotplug enabled for your system and it has @@ -519,6 +529,7 @@ been built into the kernel the hvcs drivers is configured to dynamically handle additions of new devices and removals of unused devices. --------------------------------------------------------------------------- + Q: For some reason /dev/hvcs* doesn't map to the same vty-server adapter after a reboot. What happened? @@ -533,6 +544,7 @@ on how to determine which vty-server goes with which /dev/hvcs* node. Hint; look at the sysfs "index" attribute for the vty-server. --------------------------------------------------------------------------- + Q: Can I use /dev/hvcs* as a conduit to another partition and use a tty device on that partition as the other end of the pipe? @@ -554,7 +566,9 @@ read or write to /dev/hvcs*. Now you have a tty conduit between two partitions. --------------------------------------------------------------------------- + 9. Reporting Bugs: +================== The proper channel for reporting bugs is either through the Linux OS distribution company that provided your OS or by posting issues to the diff --git a/Documentation/powerpc/index.rst b/Documentation/powerpc/index.rst new file mode 100644 index 000000000000..549b1cdd77ae --- /dev/null +++ b/Documentation/powerpc/index.rst @@ -0,0 +1,34 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======= +powerpc +======= + +.. toctree:: + :maxdepth: 1 + + bootwrapper + cpu_families + cpu_features + cxl + cxlflash + dawr-power9 + dscr + eeh-pci-error-recovery + firmware-assisted-dump + hvcs + isa-versions + mpc52xx + pci_iov_resource_on_powernv + pmu-ebb + ptrace + qe_firmware + syscall64-abi + transactional_memory + +.. only:: subproject and html + + Indices + ======= + + * :ref:`genindex` diff --git a/Documentation/powerpc/isa-versions.rst b/Documentation/powerpc/isa-versions.rst index 66c24140ebf1..a363d8c1603c 100644 --- a/Documentation/powerpc/isa-versions.rst +++ b/Documentation/powerpc/isa-versions.rst @@ -1,13 +1,12 @@ -:orphan: - +========================== CPU to ISA Version Mapping ========================== Mapping of some CPU versions to relevant ISA versions. -========= ==================== +========= ==================================================================== CPU Architecture version -========= ==================== +========= ==================================================================== Power9 Power ISA v3.0B Power8 Power ISA v2.07 Power7 Power ISA v2.06 @@ -24,7 +23,7 @@ PPC970 - PowerPC User Instruction Set Architecture Book I v2.01 - PowerPC Virtual Environment Architecture Book II v2.01 - PowerPC Operating Environment Architecture Book III v2.01 - Plus Altivec/VMX ~= 2.03 -========= ==================== +========= ==================================================================== Key Features @@ -60,9 +59,9 @@ Power5 No PPC970 No ========== ==== -========== ==================== +========== ==================================== CPU Transactional Memory -========== ==================== +========== ==================================== Power9 Yes (* see transactional_memory.txt) Power8 Yes Power7 No @@ -73,4 +72,4 @@ Power5++ No Power5+ No Power5 No PPC970 No -========== ==================== +========== ==================================== diff --git a/Documentation/powerpc/mpc52xx.txt b/Documentation/powerpc/mpc52xx.rst similarity index 91% rename from Documentation/powerpc/mpc52xx.txt rename to Documentation/powerpc/mpc52xx.rst index 0d540a31ea1a..8676ac63e077 100644 --- a/Documentation/powerpc/mpc52xx.txt +++ b/Documentation/powerpc/mpc52xx.rst @@ -1,11 +1,13 @@ +============================= Linux 2.6.x on MPC52xx family ------------------------------ +============================= For the latest info, go to http://www.246tNt.com/mpc52xx/ To compile/use : - - U-Boot: + - U-Boot:: + # tftpboot 400000 pRamdisk => bootm 200000 400000 - - DBug: + - DBug:: + # dn -i zImage.initrd.lite5200 -Some remarks : +Some remarks: + - The port is named mpc52xxx, and config options are PPC_MPC52xx. The MGT5100 is not supported, and I'm not sure anyone is interesting in working on it so. I didn't took 5xxx because there's apparently a lot of 5xxx that have diff --git a/Documentation/powerpc/pci_iov_resource_on_powernv.txt b/Documentation/powerpc/pci_iov_resource_on_powernv.rst similarity index 97% rename from Documentation/powerpc/pci_iov_resource_on_powernv.txt rename to Documentation/powerpc/pci_iov_resource_on_powernv.rst index b55c5cd83f8d..f5a5793e1613 100644 --- a/Documentation/powerpc/pci_iov_resource_on_powernv.txt +++ b/Documentation/powerpc/pci_iov_resource_on_powernv.rst @@ -1,6 +1,13 @@ +=================================================== +PCI Express I/O Virtualization Resource on Powerenv +=================================================== + Wei Yang + Benjamin Herrenschmidt + Bjorn Helgaas + 26 Aug 2014 This document describes the requirement from hardware for PCI MMIO resource @@ -10,6 +17,7 @@ Endpoints and the implementation on P8 (IODA2). The next two sections talks about considerations on enabling SRIOV on IODA2. 1. Introduction to Partitionable Endpoints +========================================== A Partitionable Endpoint (PE) is a way to group the various resources associated with a device or a set of devices to provide isolation between @@ -35,6 +43,7 @@ is a completely separate HW entity that replicates the entire logic, so has its own set of PEs, etc. 2. Implementation of Partitionable Endpoints on P8 (IODA2) +========================================================== P8 supports up to 256 Partitionable Endpoints per PHB. @@ -149,6 +158,7 @@ P8 supports up to 256 Partitionable Endpoints per PHB. sense, but we haven't done it yet. 3. Considerations for SR-IOV on PowerKVM +======================================== * SR-IOV Background @@ -224,7 +234,7 @@ P8 supports up to 256 Partitionable Endpoints per PHB. IODA supports 256 PEs, so segmented windows contain 256 segments, so if total_VFs is less than 256, we have the situation in Figure 1.0, where segments [total_VFs, 255] of the M64 window may map to some MMIO range on - other devices: + other devices:: 0 1 total_VFs - 1 +------+------+- -+------+------+ @@ -243,7 +253,7 @@ P8 supports up to 256 Partitionable Endpoints per PHB. Figure 1.0 Direct map VF(n) BAR space Our current solution is to allocate 256 segments even if the VF(n) BAR - space doesn't need that much, as shown in Figure 1.1: + space doesn't need that much, as shown in Figure 1.1:: 0 1 total_VFs - 1 255 +------+------+- -+------+------+- -+------+------+ @@ -269,6 +279,7 @@ P8 supports up to 256 Partitionable Endpoints per PHB. responds to segments [total_VFs, 255]. 4. Implications for the Generic PCI Code +======================================== The PCIe SR-IOV spec requires that the base of the VF(n) BAR space be aligned to the size of an individual VF BAR. diff --git a/Documentation/powerpc/pmu-ebb.txt b/Documentation/powerpc/pmu-ebb.rst similarity index 99% rename from Documentation/powerpc/pmu-ebb.txt rename to Documentation/powerpc/pmu-ebb.rst index 73cd163dbfb8..4f474758eb55 100644 --- a/Documentation/powerpc/pmu-ebb.txt +++ b/Documentation/powerpc/pmu-ebb.rst @@ -1,3 +1,4 @@ +======================== PMU Event Based Branches ======================== diff --git a/Documentation/powerpc/ptrace.rst b/Documentation/powerpc/ptrace.rst new file mode 100644 index 000000000000..864d4b6dddd1 --- /dev/null +++ b/Documentation/powerpc/ptrace.rst @@ -0,0 +1,156 @@ +====== +Ptrace +====== + +GDB intends to support the following hardware debug features of BookE +processors: + +4 hardware breakpoints (IAC) +2 hardware watchpoints (read, write and read-write) (DAC) +2 value conditions for the hardware watchpoints (DVC) + +For that, we need to extend ptrace so that GDB can query and set these +resources. Since we're extending, we're trying to create an interface +that's extendable and that covers both BookE and server processors, so +that GDB doesn't need to special-case each of them. We added the +following 3 new ptrace requests. + +1. PTRACE_PPC_GETHWDEBUGINFO +============================ + +Query for GDB to discover the hardware debug features. The main info to +be returned here is the minimum alignment for the hardware watchpoints. +BookE processors don't have restrictions here, but server processors have +an 8-byte alignment restriction for hardware watchpoints. We'd like to avoid +adding special cases to GDB based on what it sees in AUXV. + +Since we're at it, we added other useful info that the kernel can return to +GDB: this query will return the number of hardware breakpoints, hardware +watchpoints and whether it supports a range of addresses and a condition. +The query will fill the following structure provided by the requesting process:: + + struct ppc_debug_info { + unit32_t version; + unit32_t num_instruction_bps; + unit32_t num_data_bps; + unit32_t num_condition_regs; + unit32_t data_bp_alignment; + unit32_t sizeof_condition; /* size of the DVC register */ + uint64_t features; /* bitmask of the individual flags */ + }; + +features will have bits indicating whether there is support for:: + + #define PPC_DEBUG_FEATURE_INSN_BP_RANGE 0x1 + #define PPC_DEBUG_FEATURE_INSN_BP_MASK 0x2 + #define PPC_DEBUG_FEATURE_DATA_BP_RANGE 0x4 + #define PPC_DEBUG_FEATURE_DATA_BP_MASK 0x8 + #define PPC_DEBUG_FEATURE_DATA_BP_DAWR 0x10 + +2. PTRACE_SETHWDEBUG + +Sets a hardware breakpoint or watchpoint, according to the provided structure:: + + struct ppc_hw_breakpoint { + uint32_t version; + #define PPC_BREAKPOINT_TRIGGER_EXECUTE 0x1 + #define PPC_BREAKPOINT_TRIGGER_READ 0x2 + #define PPC_BREAKPOINT_TRIGGER_WRITE 0x4 + uint32_t trigger_type; /* only some combinations allowed */ + #define PPC_BREAKPOINT_MODE_EXACT 0x0 + #define PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE 0x1 + #define PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE 0x2 + #define PPC_BREAKPOINT_MODE_MASK 0x3 + uint32_t addr_mode; /* address match mode */ + + #define PPC_BREAKPOINT_CONDITION_MODE 0x3 + #define PPC_BREAKPOINT_CONDITION_NONE 0x0 + #define PPC_BREAKPOINT_CONDITION_AND 0x1 + #define PPC_BREAKPOINT_CONDITION_EXACT 0x1 /* different name for the same thing as above */ + #define PPC_BREAKPOINT_CONDITION_OR 0x2 + #define PPC_BREAKPOINT_CONDITION_AND_OR 0x3 + #define PPC_BREAKPOINT_CONDITION_BE_ALL 0x00ff0000 /* byte enable bits */ + #define PPC_BREAKPOINT_CONDITION_BE(n) (1<<((n)+16)) + uint32_t condition_mode; /* break/watchpoint condition flags */ + + uint64_t addr; + uint64_t addr2; + uint64_t condition_value; + }; + +A request specifies one event, not necessarily just one register to be set. +For instance, if the request is for a watchpoint with a condition, both the +DAC and DVC registers will be set in the same request. + +With this GDB can ask for all kinds of hardware breakpoints and watchpoints +that the BookE supports. COMEFROM breakpoints available in server processors +are not contemplated, but that is out of the scope of this work. + +ptrace will return an integer (handle) uniquely identifying the breakpoint or +watchpoint just created. This integer will be used in the PTRACE_DELHWDEBUG +request to ask for its removal. Return -ENOSPC if the requested breakpoint +can't be allocated on the registers. + +Some examples of using the structure to: + +- set a breakpoint in the first breakpoint register:: + + p.version = PPC_DEBUG_CURRENT_VERSION; + p.trigger_type = PPC_BREAKPOINT_TRIGGER_EXECUTE; + p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; + p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; + p.addr = (uint64_t) address; + p.addr2 = 0; + p.condition_value = 0; + +- set a watchpoint which triggers on reads in the second watchpoint register:: + + p.version = PPC_DEBUG_CURRENT_VERSION; + p.trigger_type = PPC_BREAKPOINT_TRIGGER_READ; + p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; + p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; + p.addr = (uint64_t) address; + p.addr2 = 0; + p.condition_value = 0; + +- set a watchpoint which triggers only with a specific value:: + + p.version = PPC_DEBUG_CURRENT_VERSION; + p.trigger_type = PPC_BREAKPOINT_TRIGGER_READ; + p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; + p.condition_mode = PPC_BREAKPOINT_CONDITION_AND | PPC_BREAKPOINT_CONDITION_BE_ALL; + p.addr = (uint64_t) address; + p.addr2 = 0; + p.condition_value = (uint64_t) condition; + +- set a ranged hardware breakpoint:: + + p.version = PPC_DEBUG_CURRENT_VERSION; + p.trigger_type = PPC_BREAKPOINT_TRIGGER_EXECUTE; + p.addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE; + p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; + p.addr = (uint64_t) begin_range; + p.addr2 = (uint64_t) end_range; + p.condition_value = 0; + +- set a watchpoint in server processors (BookS):: + + p.version = 1; + p.trigger_type = PPC_BREAKPOINT_TRIGGER_RW; + p.addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE; + or + p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; + + p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; + p.addr = (uint64_t) begin_range; + /* For PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE addr2 needs to be specified, where + * addr2 - addr <= 8 Bytes. + */ + p.addr2 = (uint64_t) end_range; + p.condition_value = 0; + +3. PTRACE_DELHWDEBUG + +Takes an integer which identifies an existing breakpoint or watchpoint +(i.e., the value returned from PTRACE_SETHWDEBUG), and deletes the +corresponding breakpoint or watchpoint.. diff --git a/Documentation/powerpc/ptrace.txt b/Documentation/powerpc/ptrace.txt deleted file mode 100644 index 99c5ce88d0fe..000000000000 --- a/Documentation/powerpc/ptrace.txt +++ /dev/null @@ -1,151 +0,0 @@ -GDB intends to support the following hardware debug features of BookE -processors: - -4 hardware breakpoints (IAC) -2 hardware watchpoints (read, write and read-write) (DAC) -2 value conditions for the hardware watchpoints (DVC) - -For that, we need to extend ptrace so that GDB can query and set these -resources. Since we're extending, we're trying to create an interface -that's extendable and that covers both BookE and server processors, so -that GDB doesn't need to special-case each of them. We added the -following 3 new ptrace requests. - -1. PTRACE_PPC_GETHWDEBUGINFO - -Query for GDB to discover the hardware debug features. The main info to -be returned here is the minimum alignment for the hardware watchpoints. -BookE processors don't have restrictions here, but server processors have -an 8-byte alignment restriction for hardware watchpoints. We'd like to avoid -adding special cases to GDB based on what it sees in AUXV. - -Since we're at it, we added other useful info that the kernel can return to -GDB: this query will return the number of hardware breakpoints, hardware -watchpoints and whether it supports a range of addresses and a condition. -The query will fill the following structure provided by the requesting process: - -struct ppc_debug_info { - unit32_t version; - unit32_t num_instruction_bps; - unit32_t num_data_bps; - unit32_t num_condition_regs; - unit32_t data_bp_alignment; - unit32_t sizeof_condition; /* size of the DVC register */ - uint64_t features; /* bitmask of the individual flags */ -}; - -features will have bits indicating whether there is support for: - -#define PPC_DEBUG_FEATURE_INSN_BP_RANGE 0x1 -#define PPC_DEBUG_FEATURE_INSN_BP_MASK 0x2 -#define PPC_DEBUG_FEATURE_DATA_BP_RANGE 0x4 -#define PPC_DEBUG_FEATURE_DATA_BP_MASK 0x8 -#define PPC_DEBUG_FEATURE_DATA_BP_DAWR 0x10 - -2. PTRACE_SETHWDEBUG - -Sets a hardware breakpoint or watchpoint, according to the provided structure: - -struct ppc_hw_breakpoint { - uint32_t version; -#define PPC_BREAKPOINT_TRIGGER_EXECUTE 0x1 -#define PPC_BREAKPOINT_TRIGGER_READ 0x2 -#define PPC_BREAKPOINT_TRIGGER_WRITE 0x4 - uint32_t trigger_type; /* only some combinations allowed */ -#define PPC_BREAKPOINT_MODE_EXACT 0x0 -#define PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE 0x1 -#define PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE 0x2 -#define PPC_BREAKPOINT_MODE_MASK 0x3 - uint32_t addr_mode; /* address match mode */ - -#define PPC_BREAKPOINT_CONDITION_MODE 0x3 -#define PPC_BREAKPOINT_CONDITION_NONE 0x0 -#define PPC_BREAKPOINT_CONDITION_AND 0x1 -#define PPC_BREAKPOINT_CONDITION_EXACT 0x1 /* different name for the same thing as above */ -#define PPC_BREAKPOINT_CONDITION_OR 0x2 -#define PPC_BREAKPOINT_CONDITION_AND_OR 0x3 -#define PPC_BREAKPOINT_CONDITION_BE_ALL 0x00ff0000 /* byte enable bits */ -#define PPC_BREAKPOINT_CONDITION_BE(n) (1<<((n)+16)) - uint32_t condition_mode; /* break/watchpoint condition flags */ - - uint64_t addr; - uint64_t addr2; - uint64_t condition_value; -}; - -A request specifies one event, not necessarily just one register to be set. -For instance, if the request is for a watchpoint with a condition, both the -DAC and DVC registers will be set in the same request. - -With this GDB can ask for all kinds of hardware breakpoints and watchpoints -that the BookE supports. COMEFROM breakpoints available in server processors -are not contemplated, but that is out of the scope of this work. - -ptrace will return an integer (handle) uniquely identifying the breakpoint or -watchpoint just created. This integer will be used in the PTRACE_DELHWDEBUG -request to ask for its removal. Return -ENOSPC if the requested breakpoint -can't be allocated on the registers. - -Some examples of using the structure to: - -- set a breakpoint in the first breakpoint register - - p.version = PPC_DEBUG_CURRENT_VERSION; - p.trigger_type = PPC_BREAKPOINT_TRIGGER_EXECUTE; - p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; - p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; - p.addr = (uint64_t) address; - p.addr2 = 0; - p.condition_value = 0; - -- set a watchpoint which triggers on reads in the second watchpoint register - - p.version = PPC_DEBUG_CURRENT_VERSION; - p.trigger_type = PPC_BREAKPOINT_TRIGGER_READ; - p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; - p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; - p.addr = (uint64_t) address; - p.addr2 = 0; - p.condition_value = 0; - -- set a watchpoint which triggers only with a specific value - - p.version = PPC_DEBUG_CURRENT_VERSION; - p.trigger_type = PPC_BREAKPOINT_TRIGGER_READ; - p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; - p.condition_mode = PPC_BREAKPOINT_CONDITION_AND | PPC_BREAKPOINT_CONDITION_BE_ALL; - p.addr = (uint64_t) address; - p.addr2 = 0; - p.condition_value = (uint64_t) condition; - -- set a ranged hardware breakpoint - - p.version = PPC_DEBUG_CURRENT_VERSION; - p.trigger_type = PPC_BREAKPOINT_TRIGGER_EXECUTE; - p.addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE; - p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; - p.addr = (uint64_t) begin_range; - p.addr2 = (uint64_t) end_range; - p.condition_value = 0; - -- set a watchpoint in server processors (BookS) - - p.version = 1; - p.trigger_type = PPC_BREAKPOINT_TRIGGER_RW; - p.addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE; - or - p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; - - p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; - p.addr = (uint64_t) begin_range; - /* For PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE addr2 needs to be specified, where - * addr2 - addr <= 8 Bytes. - */ - p.addr2 = (uint64_t) end_range; - p.condition_value = 0; - -3. PTRACE_DELHWDEBUG - -Takes an integer which identifies an existing breakpoint or watchpoint -(i.e., the value returned from PTRACE_SETHWDEBUG), and deletes the -corresponding breakpoint or watchpoint.. diff --git a/Documentation/powerpc/qe_firmware.txt b/Documentation/powerpc/qe_firmware.rst similarity index 95% rename from Documentation/powerpc/qe_firmware.txt rename to Documentation/powerpc/qe_firmware.rst index e7ac24aec4ff..42f5103140c9 100644 --- a/Documentation/powerpc/qe_firmware.txt +++ b/Documentation/powerpc/qe_firmware.rst @@ -1,23 +1,23 @@ - Freescale QUICC Engine Firmware Uploading - ----------------------------------------- +========================================= +Freescale QUICC Engine Firmware Uploading +========================================= (c) 2007 Timur Tabi , Freescale Semiconductor -Table of Contents -================= +.. Table of Contents - I - Software License for Firmware + I - Software License for Firmware - II - Microcode Availability + II - Microcode Availability - III - Description and Terminology + III - Description and Terminology - IV - Microcode Programming Details + IV - Microcode Programming Details - V - Firmware Structure Layout + V - Firmware Structure Layout - VI - Sample Code for Creating Firmware Files + VI - Sample Code for Creating Firmware Files Revision Information ==================== @@ -39,7 +39,7 @@ http://opensource.freescale.com. For other firmware files, please contact your Freescale representative or your operating system vendor. III - Description and Terminology -================================ +================================= In this document, the term 'microcode' refers to the sequence of 32-bit integers that compose the actual QE microcode. @@ -89,7 +89,7 @@ being fixed in the RAM package utilizing they should be activated. This data structure signals the microcode which of these virtual traps is active. This structure contains 6 words that the application should copy to some -specific been defined. This table describes the structure. +specific been defined. This table describes the structure:: --------------------------------------------------------------- | Offset in | | Destination Offset | Size of | @@ -119,7 +119,7 @@ Extended Modes This is a double word bit array (64 bits) that defines special functionality which has an impact on the software drivers. Each bit has its own impact and has special instructions for the s/w associated with it. This structure is -described in this table: +described in this table:: ----------------------------------------------------------------------- | Bit # | Name | Description | @@ -220,7 +220,8 @@ The 'model' field is a 16-bit number that matches the actual SOC. The 'major' and 'minor' fields are the major and minor revision numbers, respectively, of the SOC. -For example, to match the 8323, revision 1.0: +For example, to match the 8323, revision 1.0:: + soc.model = 8323 soc.major = 1 soc.minor = 0 @@ -273,10 +274,10 @@ library and available to any driver that calles qe_get_firmware_info(). 'reserved'. After the last microcode is a 32-bit CRC. It can be calculated using -this algorithm: +this algorithm:: -u32 crc32(const u8 *p, unsigned int len) -{ + u32 crc32(const u8 *p, unsigned int len) + { unsigned int i; u32 crc = 0; @@ -286,7 +287,7 @@ u32 crc32(const u8 *p, unsigned int len) crc = (crc >> 1) ^ ((crc & 1) ? 0xedb88320 : 0); } return crc; -} + } VI - Sample Code for Creating Firmware Files ============================================ diff --git a/Documentation/powerpc/syscall64-abi.txt b/Documentation/powerpc/syscall64-abi.rst similarity index 82% rename from Documentation/powerpc/syscall64-abi.txt rename to Documentation/powerpc/syscall64-abi.rst index fa716a0d88bd..e49f69f941b9 100644 --- a/Documentation/powerpc/syscall64-abi.txt +++ b/Documentation/powerpc/syscall64-abi.rst @@ -5,12 +5,12 @@ Power Architecture 64-bit Linux system call ABI syscall ======= -syscall calling sequence[*] matches the Power Architecture 64-bit ELF ABI +syscall calling sequence\ [1]_ matches the Power Architecture 64-bit ELF ABI specification C function calling sequence, including register preservation rules, with the following differences. -[*] Some syscalls (typically low-level management functions) may have - different calling sequences (e.g., rt_sigreturn). +.. [1] Some syscalls (typically low-level management functions) may have + different calling sequences (e.g., rt_sigreturn). Parameters and return value --------------------------- @@ -33,12 +33,14 @@ Register preservation rules Register preservation rules match the ELF ABI calling sequence with the following differences: -r0: Volatile. (System call number.) -r3: Volatile. (Parameter 1, and return value.) -r4-r8: Volatile. (Parameters 2-6.) -cr0: Volatile (cr0.SO is the return error condition) -cr1, cr5-7: Nonvolatile. -lr: Nonvolatile. +=========== ============= ======================================== +r0 Volatile (System call number.) +r3 Volatile (Parameter 1, and return value.) +r4-r8 Volatile (Parameters 2-6.) +cr0 Volatile (cr0.SO is the return error condition) +cr1, cr5-7 Nonvolatile +lr Nonvolatile +=========== ============= ======================================== All floating point and vector data registers as well as control and status registers are nonvolatile. @@ -90,9 +92,12 @@ The vsyscall may or may not use the caller's stack frame save areas. Register preservation rules --------------------------- -r0: Volatile. -cr1, cr5-7: Volatile. -lr: Volatile. + +=========== ======== +r0 Volatile +cr1, cr5-7 Volatile +lr Volatile +=========== ======== Invocation ---------- diff --git a/Documentation/powerpc/transactional_memory.txt b/Documentation/powerpc/transactional_memory.rst similarity index 93% rename from Documentation/powerpc/transactional_memory.txt rename to Documentation/powerpc/transactional_memory.rst index 52c023e14f26..09955103acb4 100644 --- a/Documentation/powerpc/transactional_memory.txt +++ b/Documentation/powerpc/transactional_memory.rst @@ -1,3 +1,4 @@ +============================ Transactional Memory support ============================ @@ -17,29 +18,29 @@ instructions are presented to delimit transactions; transactions are guaranteed to either complete atomically or roll back and undo any partial changes. -A simple transaction looks like this: +A simple transaction looks like this:: -begin_move_money: - tbegin - beq abort_handler + begin_move_money: + tbegin + beq abort_handler - ld r4, SAVINGS_ACCT(r3) - ld r5, CURRENT_ACCT(r3) - subi r5, r5, 1 - addi r4, r4, 1 - std r4, SAVINGS_ACCT(r3) - std r5, CURRENT_ACCT(r3) + ld r4, SAVINGS_ACCT(r3) + ld r5, CURRENT_ACCT(r3) + subi r5, r5, 1 + addi r4, r4, 1 + std r4, SAVINGS_ACCT(r3) + std r5, CURRENT_ACCT(r3) - tend + tend - b continue + b continue -abort_handler: - ... test for odd failures ... + abort_handler: + ... test for odd failures ... - /* Retry the transaction if it failed because it conflicted with - * someone else: */ - b begin_move_money + /* Retry the transaction if it failed because it conflicted with + * someone else: */ + b begin_move_money The 'tbegin' instruction denotes the start point, and 'tend' the end point. @@ -123,7 +124,7 @@ Transaction-aware signal handlers can read the transactional register state from the second ucontext. This will be necessary for crash handlers to determine, for example, the address of the instruction causing the SIGSEGV. -Example signal handler: +Example signal handler:: void crash_handler(int sig, siginfo_t *si, void *uc) { @@ -133,9 +134,9 @@ Example signal handler: if (ucp_link) { u64 msr = ucp->uc_mcontext.regs->msr; /* May have transactional ucontext! */ -#ifndef __powerpc64__ + #ifndef __powerpc64__ msr |= ((u64)transactional_ucp->uc_mcontext.regs->msr) << 32; -#endif + #endif if (MSR_TM_ACTIVE(msr)) { /* Yes, we crashed during a transaction. Oops. */ fprintf(stderr, "Transaction to be restarted at 0x%llx, but " @@ -176,6 +177,7 @@ Failure cause codes used by kernel These are defined in , and distinguish different reasons why the kernel aborted a transaction: + ====================== ================================ TM_CAUSE_RESCHED Thread was rescheduled. TM_CAUSE_TLBI Software TLB invalid. TM_CAUSE_FAC_UNAV FP/VEC/VSX unavailable trap. @@ -184,6 +186,7 @@ kernel aborted a transaction: TM_CAUSE_MISC Currently unused. TM_CAUSE_ALIGNMENT Alignment fault. TM_CAUSE_EMULATE Emulation that touched memory. + ====================== ================================ These can be checked by the user program's abort handler as TEXASR[0:7]. If bit 7 is set, it indicates that the error is consider persistent. For example @@ -203,7 +206,7 @@ POWER9 ====== TM on POWER9 has issues with storing the complete register state. This -is described in this commit: +is described in this commit:: commit 4bb3c7a0208fc13ca70598efd109901a7cd45ae7 Author: Paul Mackerras diff --git a/MAINTAINERS b/MAINTAINERS index c144bd6a432e..8671909ee75c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4468,7 +4468,7 @@ F: arch/powerpc/platforms/powernv/pci-cxl.c F: drivers/misc/cxl/ F: include/misc/cxl* F: include/uapi/misc/cxl.h -F: Documentation/powerpc/cxl.txt +F: Documentation/powerpc/cxl.rst F: Documentation/ABI/testing/sysfs-class-cxl CXLFLASH (IBM Coherent Accelerator Processor Interface CAPI Flash) SCSI DRIVER @@ -4479,7 +4479,7 @@ L: linux-scsi@vger.kernel.org S: Supported F: drivers/scsi/cxlflash/ F: include/uapi/scsi/cxlflash_ioctl.h -F: Documentation/powerpc/cxlflash.txt +F: Documentation/powerpc/cxlflash.rst CYBERPRO FB DRIVER M: Russell King @@ -12353,7 +12353,7 @@ F: Documentation/PCI/pci-error-recovery.rst F: drivers/pci/pcie/aer.c F: drivers/pci/pcie/dpc.c F: drivers/pci/pcie/err.c -F: Documentation/powerpc/eeh-pci-error-recovery.txt +F: Documentation/powerpc/eeh-pci-error-recovery.rst F: arch/powerpc/kernel/eeh*.c F: arch/powerpc/platforms/*/eeh*.c F: arch/powerpc/include/*/eeh*.h diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index eee5bef736c8..6ba3cc2ef8ab 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1531,7 +1531,7 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) * * Call convention: * - * syscall register convention is in Documentation/powerpc/syscall64-abi.txt + * syscall register convention is in Documentation/powerpc/syscall64-abi.rst * * For hypercalls, the register convention is as follows: * r0 volatile diff --git a/drivers/soc/fsl/qe/qe.c b/drivers/soc/fsl/qe/qe.c index 62c6ba17991a..c9519e62308c 100644 --- a/drivers/soc/fsl/qe/qe.c +++ b/drivers/soc/fsl/qe/qe.c @@ -419,7 +419,7 @@ static void qe_upload_microcode(const void *base, /* * Upload a microcode to the I-RAM at a specific address. * - * See Documentation/powerpc/qe_firmware.txt for information on QE microcode + * See Documentation/powerpc/qe_firmware.rst for information on QE microcode * uploading. * * Currently, only version 1 is supported, so the 'version' field must be diff --git a/drivers/tty/hvc/hvcs.c b/drivers/tty/hvc/hvcs.c index cb4db1b3ca3c..5fb214e67d73 100644 --- a/drivers/tty/hvc/hvcs.c +++ b/drivers/tty/hvc/hvcs.c @@ -47,7 +47,7 @@ * using the 2.6 Linux kernel kref construct. * * For direction on installation and usage of this driver please reference - * Documentation/powerpc/hvcs.txt. + * Documentation/powerpc/hvcs.rst. */ #include diff --git a/include/soc/fsl/qe/qe.h b/include/soc/fsl/qe/qe.h index 3f9d6b6a5691..c1036d16ed03 100644 --- a/include/soc/fsl/qe/qe.h +++ b/include/soc/fsl/qe/qe.h @@ -259,7 +259,7 @@ static inline int qe_alive_during_sleep(void) /* Structure that defines QE firmware binary files. * - * See Documentation/powerpc/qe_firmware.txt for a description of these + * See Documentation/powerpc/qe_firmware.rst for a description of these * fields. */ struct qe_firmware { From 08a69058c02f9588775360c8703e69fc0ec4626c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 15 Jul 2019 09:39:57 -0300 Subject: [PATCH 031/823] docs: power: add it to to the main documentation index The power docs are orphaned at the documentation body. While it could likely be moved to be inside some guide, I'm opting to just adding it to the main index.rst, removing the :orphan: and adding the SPDX header. The reason is similar to what it was done for other driver-specific subsystems: the docs there contain a mix of Kernelspace, uAPI and admin-guide. So, better to keep them on its own directory, while the docs there are not properly classified. Signed-off-by: Mauro Carvalho Chehab --- Documentation/index.rst | 1 + Documentation/power/index.rst | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/Documentation/index.rst b/Documentation/index.rst index 3fe6170aa41d..68ae2a4d689d 100644 --- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -111,6 +111,7 @@ needed). netlabel/index networking/index pcmcia/index + power/index target/index timers/index watchdog/index diff --git a/Documentation/power/index.rst b/Documentation/power/index.rst index 20415f21e48a..002e42745263 100644 --- a/Documentation/power/index.rst +++ b/Documentation/power/index.rst @@ -1,4 +1,4 @@ -:orphan: +.. SPDX-License-Identifier: GPL-2.0 ================ Power Management From bff9e34c678552eb172916d9288913e8bd8cc9d1 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 15 Jul 2019 05:31:06 -0300 Subject: [PATCH 032/823] docs: fix broken doc references due to renames Some files got renamed but probably due to some merge conflicts, a few references still point to the old locations. Signed-off-by: Mauro Carvalho Chehab --- Documentation/RCU/rculist_nulls.txt | 2 +- Documentation/devicetree/bindings/arm/idle-states.txt | 2 +- Documentation/locking/spinlocks.rst | 4 ++-- Documentation/memory-barriers.txt | 2 +- Documentation/translations/ko_KR/memory-barriers.txt | 2 +- Documentation/watchdog/hpwdt.rst | 2 +- MAINTAINERS | 8 ++++---- drivers/gpu/drm/drm_modes.c | 2 +- drivers/i2c/busses/i2c-nvidia-gpu.c | 2 +- drivers/scsi/hpsa.c | 4 ++-- 10 files changed, 15 insertions(+), 15 deletions(-) diff --git a/Documentation/RCU/rculist_nulls.txt b/Documentation/RCU/rculist_nulls.txt index 8151f0195f76..23f115dc87cf 100644 --- a/Documentation/RCU/rculist_nulls.txt +++ b/Documentation/RCU/rculist_nulls.txt @@ -1,7 +1,7 @@ Using hlist_nulls to protect read-mostly linked lists and objects using SLAB_TYPESAFE_BY_RCU allocations. -Please read the basics in Documentation/RCU/listRCU.txt +Please read the basics in Documentation/RCU/listRCU.rst Using special makers (called 'nulls') is a convenient way to solve following problem : diff --git a/Documentation/devicetree/bindings/arm/idle-states.txt b/Documentation/devicetree/bindings/arm/idle-states.txt index 326f29b270ad..2d325bed37e5 100644 --- a/Documentation/devicetree/bindings/arm/idle-states.txt +++ b/Documentation/devicetree/bindings/arm/idle-states.txt @@ -703,4 +703,4 @@ cpus { https://www.devicetree.org/specifications/ [6] ARM Linux Kernel documentation - Booting AArch64 Linux - Documentation/arm64/booting.txt + Documentation/arm64/booting.rst diff --git a/Documentation/locking/spinlocks.rst b/Documentation/locking/spinlocks.rst index 098107fb7d86..e93ec6645238 100644 --- a/Documentation/locking/spinlocks.rst +++ b/Documentation/locking/spinlocks.rst @@ -82,7 +82,7 @@ itself. The read lock allows many concurrent readers. Anything that **changes** the list will have to get the write lock. NOTE! RCU is better for list traversal, but requires careful - attention to design detail (see Documentation/RCU/listRCU.txt). + attention to design detail (see Documentation/RCU/listRCU.rst). Also, you cannot "upgrade" a read-lock to a write-lock, so if you at _any_ time need to do any changes (even if you don't do it every time), you have @@ -90,7 +90,7 @@ to get the write-lock at the very beginning. NOTE! We are working hard to remove reader-writer spinlocks in most cases, so please don't add a new one without consensus. (Instead, see - Documentation/RCU/rcu.txt for complete information.) + Documentation/RCU/rcu.rst for complete information.) ---- diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 045bb8148fe9..1adbb8a371c7 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -548,7 +548,7 @@ There are certain things that the Linux kernel memory barriers do not guarantee: [*] For information on bus mastering DMA and coherency please read: - Documentation/PCI/pci.rst + Documentation/driver-api/pci/pci.rst Documentation/DMA-API-HOWTO.txt Documentation/DMA-API.txt diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt index a33c2a536542..2774624ee843 100644 --- a/Documentation/translations/ko_KR/memory-barriers.txt +++ b/Documentation/translations/ko_KR/memory-barriers.txt @@ -569,7 +569,7 @@ ACQUIRE 는 해당 오퍼레이션의 로드 부분에만 적용되고 RELEASE [*] 버스 마스터링 DMA 와 일관성에 대해서는 다음을 참고하시기 바랍니다: - Documentation/PCI/pci.rst + Documentation/driver-api/pci/pci.rst Documentation/DMA-API-HOWTO.txt Documentation/DMA-API.txt diff --git a/Documentation/watchdog/hpwdt.rst b/Documentation/watchdog/hpwdt.rst index 94a96371113e..49c647dba8aa 100644 --- a/Documentation/watchdog/hpwdt.rst +++ b/Documentation/watchdog/hpwdt.rst @@ -59,7 +59,7 @@ Last reviewed: 08/20/2018 and loop forever. This is generally not what a watchdog user wants. For those wishing to learn more please see: - Documentation/kdump/kdump.rst + Documentation/admin-guide/kdump/kdump.rst Documentation/admin-guide/kernel-parameters.txt (panic=) Your Linux Distribution specific documentation. diff --git a/MAINTAINERS b/MAINTAINERS index 8671909ee75c..5fe6fd597138 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -899,7 +899,7 @@ L: linux-iio@vger.kernel.org W: http://ez.analog.com/community/linux-device-drivers S: Supported F: drivers/iio/adc/ad7124.c -F: Documentation/devicetree/bindings/iio/adc/adi,ad7124.txt +F: Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml ANALOG DEVICES INC AD7606 DRIVER M: Stefan Popa @@ -4189,7 +4189,7 @@ M: Jens Axboe L: cgroups@vger.kernel.org L: linux-block@vger.kernel.org T: git git://git.kernel.dk/linux-block -F: Documentation/cgroup-v1/blkio-controller.rst +F: Documentation/admin-guide/cgroup-v1/blkio-controller.rst F: block/blk-cgroup.c F: include/linux/blk-cgroup.h F: block/blk-throttle.c @@ -6848,7 +6848,7 @@ R: Sagi Shahar R: Jon Olson L: netdev@vger.kernel.org S: Supported -F: Documentation/networking/device_drivers/google/gve.txt +F: Documentation/networking/device_drivers/google/gve.rst F: drivers/net/ethernet/google GPD POCKET FAN DRIVER @@ -12096,7 +12096,7 @@ M: Juergen Gross M: Alok Kataria L: virtualization@lists.linux-foundation.org S: Supported -F: Documentation/virtual/paravirt_ops.txt +F: Documentation/virtual/paravirt_ops.rst F: arch/*/kernel/paravirt* F: arch/*/include/asm/paravirt*.h F: include/linux/hypervisor.h diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 57e6408288c8..4645af681ef8 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1680,7 +1680,7 @@ static int drm_mode_parse_cmdline_options(char *str, size_t len, * * Additionals options can be provided following the mode, using a comma to * separate each option. Valid options can be found in - * Documentation/fb/modedb.txt. + * Documentation/fb/modedb.rst. * * The intermediate drm_cmdline_mode structure is required to store additional * options from the command line modline like the force-enable/disable flag. diff --git a/drivers/i2c/busses/i2c-nvidia-gpu.c b/drivers/i2c/busses/i2c-nvidia-gpu.c index cfc76b5de726..5a1235fd86bb 100644 --- a/drivers/i2c/busses/i2c-nvidia-gpu.c +++ b/drivers/i2c/busses/i2c-nvidia-gpu.c @@ -364,7 +364,7 @@ static void gpu_i2c_remove(struct pci_dev *pdev) /* * We need gpu_i2c_suspend() even if it is stub, for runtime pm to work * correctly. Without it, lspci shows runtime pm status as "D0" for the card. - * Documentation/power/pci.txt also insists for driver to provide this. + * Documentation/power/pci.rst also insists for driver to provide this. */ static __maybe_unused int gpu_i2c_suspend(struct device *dev) { diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 43a6b5350775..eaf6177ac9ee 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -7798,7 +7798,7 @@ static void hpsa_free_pci_init(struct ctlr_info *h) hpsa_disable_interrupt_mode(h); /* pci_init 2 */ /* * call pci_disable_device before pci_release_regions per - * Documentation/PCI/pci.rst + * Documentation/driver-api/pci/pci.rst */ pci_disable_device(h->pdev); /* pci_init 1 */ pci_release_regions(h->pdev); /* pci_init 2 */ @@ -7881,7 +7881,7 @@ clean2: /* intmode+region, pci */ clean1: /* * call pci_disable_device before pci_release_regions per - * Documentation/PCI/pci.rst + * Documentation/driver-api/pci/pci.rst */ pci_disable_device(h->pdev); pci_release_regions(h->pdev); From 9d42afbe6bd4ce6d424159715e4abf3ea3ddb789 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 9 Jul 2019 06:52:36 -0300 Subject: [PATCH 033/823] docs: pdf: add all Documentation/*/index.rst to PDF output Currently, all index files should be manually added to the latex_documents array at conf.py. While this allows fine-tuning some LaTeX specific things, like the name of the output file and the name of the document, it is not uncommon to forget adding new documents there. So, add a logic that will seek for all Documentation/*/index.rst. If the index is not yet at latex_documents, it includes using a reasonable default. Signed-off-by: Mauro Carvalho Chehab --- Documentation/conf.py | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/Documentation/conf.py b/Documentation/conf.py index 3b2397bcb565..13b5f711bddf 100644 --- a/Documentation/conf.py +++ b/Documentation/conf.py @@ -410,6 +410,21 @@ latex_documents = [ 'The kernel development community', 'manual'), ] +# Add all other index files from Documentation/ subdirectories +for fn in os.listdir('.'): + doc = os.path.join(fn, "index") + if os.path.exists(doc + ".rst"): + has = False + for l in latex_documents: + if l[0] == doc: + has = True + break + if not has: + latex_documents.append((doc, fn + '.tex', + 'Linux %s Documentation' % fn.capitalize(), + 'The kernel development community', + 'manual')) + # The name of an image file (relative to this directory) to place at the top of # the title page. #latex_logo = None From 24889dad3d9e7c9e22f5be46d9ae7b8ca92cc1cc Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 9 Jul 2019 15:14:17 -0300 Subject: [PATCH 034/823] docs: conf.py: add CJK package needed by translations In order to be able to output Asian symbols with XeLaTeX, we need the xeCJK package, and a default font for CJK symbols. Signed-off-by: Mauro Carvalho Chehab --- Documentation/conf.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/conf.py b/Documentation/conf.py index 13b5f711bddf..fa0a42b47e62 100644 --- a/Documentation/conf.py +++ b/Documentation/conf.py @@ -277,6 +277,10 @@ latex_elements = { \\setromanfont{DejaVu Serif} \\setmonofont{DejaVu Sans Mono} + % This is needed for translations + \\usepackage{xeCJK} + \\setCJKmainfont{Noto Sans CJK SC} + ''' } From e0de2b59e243c88296fc983e32dd6484365e87a7 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sun, 14 Jul 2019 07:16:18 -0300 Subject: [PATCH 035/823] docs: conf.py: only use CJK if the font is available If we try to build a book with asian characters with XeLaTeX and the font is not available, it will produce an error. So, instead, add a logic at conf.py to detect if the proper font is installed. This will avoid an error while building the document, although the result may not be readable. Signed-off-by: Mauro Carvalho Chehab --- Documentation/conf.py | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/Documentation/conf.py b/Documentation/conf.py index fa0a42b47e62..a8fe845832bc 100644 --- a/Documentation/conf.py +++ b/Documentation/conf.py @@ -16,6 +16,8 @@ import sys import os import sphinx +from subprocess import check_output + # Get Sphinx version major, minor, patch = sphinx.version_info[:3] @@ -276,13 +278,20 @@ latex_elements = { \\setsansfont{DejaVu Sans} \\setromanfont{DejaVu Serif} \\setmonofont{DejaVu Sans Mono} + ''' +} +# At least one book (translations) may have Asian characters +# with are only displayed if xeCJK is used + +cjk_cmd = check_output(['fc-list', '--format="%{family[0]}\n"']).decode('utf-8', 'ignore') +if cjk_cmd.find("Noto Sans CJK SC") >= 0: + print ("enabling CJK for LaTeX builder") + latex_elements['preamble'] += ''' % This is needed for translations \\usepackage{xeCJK} \\setCJKmainfont{Noto Sans CJK SC} - ''' -} # Fix reference escape troubles with Sphinx 1.4.x if major == 1 and minor > 3: From b308467c916aa7acc5069802ab76a9f657434701 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 13 Jul 2019 08:50:24 -0300 Subject: [PATCH 036/823] scripts/sphinx-pre-install: fix script for RHEL/CentOS There's a missing parenthesis at the script, with causes it to fail to detect non-Fedora releases (e. g. RHEL/CentOS). Tested with Centos 7.6.1810. Signed-off-by: Mauro Carvalho Chehab --- scripts/sphinx-pre-install | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/sphinx-pre-install b/scripts/sphinx-pre-install index f230e65329a2..101ddd00bf02 100755 --- a/scripts/sphinx-pre-install +++ b/scripts/sphinx-pre-install @@ -371,7 +371,7 @@ sub give_redhat_hints() # # Checks valid for RHEL/CentOS version 7.x. # - if (! $system_release =~ /Fedora/) { + if (!($system_release =~ /Fedora/)) { $map{"virtualenv"} = "python-virtualenv"; } From 56e5a633923793b31515795ad30156a307572c1e Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 13 Jul 2019 09:37:16 -0300 Subject: [PATCH 037/823] scripts/sphinx-pre-install: don't use LaTeX with CentOS 7 There aren't enough texlive packages for LaTeX-based builds to work on CentOS/RHEL <= 7. Signed-off-by: Mauro Carvalho Chehab --- scripts/sphinx-pre-install | 70 +++++++++++++++++++++++++++----------- 1 file changed, 51 insertions(+), 19 deletions(-) diff --git a/scripts/sphinx-pre-install b/scripts/sphinx-pre-install index 101ddd00bf02..33efadd6c0b6 100755 --- a/scripts/sphinx-pre-install +++ b/scripts/sphinx-pre-install @@ -83,6 +83,17 @@ sub check_missing(%) foreach my $prog (sort keys %missing) { my $is_optional = $missing{$prog}; + # At least on some LTS distros like CentOS 7, texlive doesn't + # provide all packages we need. When such distros are + # detected, we have to disable PDF output. + # + # So, we need to ignore the packages that distros would + # need for LaTeX to work + if ($is_optional == 2 && !$pdf) { + $optional--; + next; + } + if ($is_optional) { print "Warning: better to also install \"$prog\".\n"; } else { @@ -333,10 +344,10 @@ sub give_debian_hints() if ($pdf) { check_missing_file("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf", - "fonts-dejavu", 1); + "fonts-dejavu", 2); } - check_program("dvipng", 1) if ($pdf); + check_program("dvipng", 2) if ($pdf); check_missing(\%map); return if (!$need && !$optional); @@ -371,22 +382,40 @@ sub give_redhat_hints() # # Checks valid for RHEL/CentOS version 7.x. # + my $old = 0; + my $rel; + $rel = $1 if ($system_release =~ /release\s+(\d+)/); + if (!($system_release =~ /Fedora/)) { $map{"virtualenv"} = "python-virtualenv"; + + if ($rel && $rel < 8) { + $old = 1; + $pdf = 0; + + printf("Note: texlive packages on RHEL/CENTOS <= 7 are incomplete. Can't support PDF output\n"); + printf("If you want to build PDF, please read:\n"); + printf("\thttps://www.systutorials.com/241660/how-to-install-tex-live-on-centos-7-linux/\n"); + } + } else { + if ($rel && $rel < 26) { + $old = 1; + } + } + if (!$rel) { + printf("Couldn't identify release number\n"); + $old = 1; + $pdf = 0; } - my $release; - - $release = $1 if ($system_release =~ /Fedora\s+release\s+(\d+)/); - - check_rpm_missing(\@fedora26_opt_pkgs, 1) if ($pdf && $release >= 26); - check_rpm_missing(\@fedora_tex_pkgs, 1) if ($pdf); - check_missing_tex(1) if ($pdf); + check_rpm_missing(\@fedora26_opt_pkgs, 2) if ($pdf && !$old); + check_rpm_missing(\@fedora_tex_pkgs, 2) if ($pdf); + check_missing_tex(2) if ($pdf); check_missing(\%map); return if (!$need && !$optional); - if ($release >= 18) { + if (!$old) { # dnf, for Fedora 18+ printf("You should run:\n\n\tsudo dnf install -y $install\n"); } else { @@ -425,8 +454,8 @@ sub give_opensuse_hints() "texlive-zapfding", ); - check_rpm_missing(\@suse_tex_pkgs, 1) if ($pdf); - check_missing_tex(1) if ($pdf); + check_rpm_missing(\@suse_tex_pkgs, 2) if ($pdf); + check_missing_tex(2) if ($pdf); check_missing(\%map); return if (!$need && !$optional); @@ -450,7 +479,7 @@ sub give_mageia_hints() "texlive-fontsextra", ); - check_rpm_missing(\@tex_pkgs, 1) if ($pdf); + check_rpm_missing(\@tex_pkgs, 2) if ($pdf); check_missing(\%map); return if (!$need && !$optional); @@ -473,7 +502,8 @@ sub give_arch_linux_hints() "texlive-latexextra", "ttf-dejavu", ); - check_pacman_missing(\@archlinux_tex_pkgs, 1) if ($pdf); + check_pacman_missing(\@archlinux_tex_pkgs, 2) if ($pdf); + check_missing(\%map); return if (!$need && !$optional); @@ -492,7 +522,7 @@ sub give_gentoo_hints() ); check_missing_file("/usr/share/fonts/dejavu/DejaVuSans.ttf", - "media-fonts/dejavu", 1) if ($pdf); + "media-fonts/dejavu", 2) if ($pdf); check_missing(\%map); @@ -560,7 +590,7 @@ sub check_distros() my %map = ( "sphinx-build" => "sphinx" ); - check_missing_tex(1) if ($pdf); + check_missing_tex(2) if ($pdf); check_missing(\%map); print "I don't know distro $system_release.\n"; print "So, I can't provide you a hint with the install procedure.\n"; @@ -589,11 +619,13 @@ sub check_needs() check_program("make", 0); check_program("gcc", 0); check_python_module("sphinx_rtd_theme", 1) if (!$virtualenv); - check_program("xelatex", 1) if ($pdf); check_program("dot", 1); check_program("convert", 1); - check_program("rsvg-convert", 1) if ($pdf); - check_program("latexmk", 1) if ($pdf); + + # Extra PDF files - should use 2 for is_optional + check_program("xelatex", 2) if ($pdf); + check_program("rsvg-convert", 2) if ($pdf); + check_program("latexmk", 2) if ($pdf); check_distros(); From 353290a9eb5362a80bc8e52fcd7eb77a30f48afc Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 13 Jul 2019 08:19:44 -0300 Subject: [PATCH 038/823] scripts/sphinx-pre-install: fix latexmk dependencies The name of the package with carries latexmk is different on two distros: - On OpenSUSE, latexmk is packaged as "texlive-latexmk-bin" - On Mageia, latexmk is packaged at "texlive-collection-basic" Signed-off-by: Mauro Carvalho Chehab --- scripts/sphinx-pre-install | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/scripts/sphinx-pre-install b/scripts/sphinx-pre-install index 33efadd6c0b6..8dc13fe95ffe 100755 --- a/scripts/sphinx-pre-install +++ b/scripts/sphinx-pre-install @@ -454,6 +454,8 @@ sub give_opensuse_hints() "texlive-zapfding", ); + $map{"latexmk"} = "texlive-latexmk-bin"; + check_rpm_missing(\@suse_tex_pkgs, 2) if ($pdf); check_missing_tex(2) if ($pdf); check_missing(\%map); @@ -479,6 +481,8 @@ sub give_mageia_hints() "texlive-fontsextra", ); + $map{"latexmk"} = "texlive-collection-basic"; + check_rpm_missing(\@tex_pkgs, 2) if ($pdf); check_missing(\%map); From 4ea96d57bbfda93ae6cfdc8e565a3c419a78f328 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 13 Jul 2019 08:19:44 -0300 Subject: [PATCH 039/823] scripts/sphinx-pre-install: cleanup Gentoo checks On Gentoo, the portage changes for ImageMagick to work are always suggested, even if already applied. While the two extra commands should be harmless, add a check to avoid reporting it without need. Signed-off-by: Mauro Carvalho Chehab --- scripts/sphinx-pre-install | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/scripts/sphinx-pre-install b/scripts/sphinx-pre-install index 8dc13fe95ffe..0a5c83aa5f44 100755 --- a/scripts/sphinx-pre-install +++ b/scripts/sphinx-pre-install @@ -533,8 +533,19 @@ sub give_gentoo_hints() return if (!$need && !$optional); printf("You should run:\n\n"); - printf("\tsudo su -c 'echo \"media-gfx/imagemagick svg png\" > /etc/portage/package.use/imagemagick'\n"); - printf("\tsudo su -c 'echo \"media-gfx/graphviz cairo pdf\" > /etc/portage/package.use/graphviz'\n"); + + my $imagemagick = "media-gfx/imagemagick svg png"; + my $cairo = "media-gfx/graphviz cairo pdf"; + my $portage_imagemagick = "/etc/portage/package.use/imagemagick"; + my $portage_cairo = "/etc/portage/package.use/graphviz"; + + if (qx(cat $portage_imagemagick) ne "$imagemagick\n") { + printf("\tsudo su -c 'echo \"$imagemagick\" > $portage_imagemagick'\n") + } + if (qx(cat $portage_cairo) ne "$cairo\n") { + printf("\tsudo su -c 'echo \"$cairo\" > $portage_cairo'\n"); + } + printf("\tsudo emerge --ask $install\n"); } From 27eed923f715f6269b98e089ad2164f9b016eace Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 13 Jul 2019 08:19:44 -0300 Subject: [PATCH 040/823] scripts/sphinx-pre-install: seek for Noto CJK fonts for pdf output The translations guide need Noto CJK fonts. So, add a logic that would suggest its install for distros. It also fix a few other issues while testing the script with several distributions. Signed-off-by: Mauro Carvalho Chehab --- scripts/sphinx-pre-install | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/scripts/sphinx-pre-install b/scripts/sphinx-pre-install index 0a5c83aa5f44..3b638c0e1a4f 100755 --- a/scripts/sphinx-pre-install +++ b/scripts/sphinx-pre-install @@ -345,6 +345,9 @@ sub give_debian_hints() if ($pdf) { check_missing_file("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf", "fonts-dejavu", 2); + + check_missing_file("/usr/share/fonts/noto-cjk/NotoSansCJK-Regular.ttc", + "fonts-noto-cjk", 2); } check_program("dvipng", 2) if ($pdf); @@ -374,6 +377,7 @@ sub give_redhat_hints() my @fedora_tex_pkgs = ( "texlive-collection-fontsrecommended", "texlive-collection-latex", + "texlive-xecjk", "dejavu-sans-fonts", "dejavu-serif-fonts", "dejavu-sans-mono-fonts", @@ -408,6 +412,11 @@ sub give_redhat_hints() $pdf = 0; } + if ($pdf) { + check_missing_file("/usr/share/fonts/google-noto-cjk/NotoSansCJK-Regular.ttc", + "google-noto-sans-cjk-ttc-fonts", 2); + } + check_rpm_missing(\@fedora26_opt_pkgs, 2) if ($pdf && !$old); check_rpm_missing(\@fedora_tex_pkgs, 2) if ($pdf); check_missing_tex(2) if ($pdf); @@ -456,6 +465,11 @@ sub give_opensuse_hints() $map{"latexmk"} = "texlive-latexmk-bin"; + # FIXME: add support for installing CJK fonts + # + # I tried hard, but was unable to find a way to install + # "Noto Sans CJK SC" on openSUSE + check_rpm_missing(\@suse_tex_pkgs, 2) if ($pdf); check_missing_tex(2) if ($pdf); check_missing(\%map); @@ -483,6 +497,11 @@ sub give_mageia_hints() $map{"latexmk"} = "texlive-collection-basic"; + if ($pdf) { + check_missing_file("/usr/share/fonts/google-noto-cjk/NotoSansCJK-Regular.ttc", + "google-noto-sans-cjk-ttc-fonts", 2); + } + check_rpm_missing(\@tex_pkgs, 2) if ($pdf); check_missing(\%map); @@ -508,6 +527,11 @@ sub give_arch_linux_hints() ); check_pacman_missing(\@archlinux_tex_pkgs, 2) if ($pdf); + if ($pdf) { + check_missing_file("/usr/share/fonts/noto-cjk/NotoSansCJK-Regular.ttc", + "noto-fonts-cjk", 2); + } + check_missing(\%map); return if (!$need && !$optional); @@ -528,6 +552,11 @@ sub give_gentoo_hints() check_missing_file("/usr/share/fonts/dejavu/DejaVuSans.ttf", "media-fonts/dejavu", 2) if ($pdf); + if ($pdf) { + check_missing_file("/usr/share/fonts/noto-cjk/NotoSansCJKsc-Regular.otf", + "media-fonts/noto-cjk", 2); + } + check_missing(\%map); return if (!$need && !$optional); From a84d9e899683cd79cb134c6d962e57d0de9446cc Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sun, 14 Jul 2019 11:18:13 -0300 Subject: [PATCH 041/823] docs: load_config.py: avoid needing a conf.py just due to LaTeX docs Right now, for every directory that we need to have LaTeX output, a conf.py file is required. That causes an extra overhead and it is actually a hack, as the latex_documents line there are usually a copy of the ones that are there already at the main conf.py. So, instead, re-use the global latex_documents var, just adjusting the path to be relative ones. Signed-off-by: Mauro Carvalho Chehab --- Documentation/sphinx/load_config.py | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) diff --git a/Documentation/sphinx/load_config.py b/Documentation/sphinx/load_config.py index 301a21aa4f63..101e6f0b0fcf 100644 --- a/Documentation/sphinx/load_config.py +++ b/Documentation/sphinx/load_config.py @@ -21,6 +21,29 @@ def loadConfig(namespace): and os.path.normpath(namespace["__file__"]) != os.path.normpath(config_file) ): config_file = os.path.abspath(config_file) + # Let's avoid one conf.py file just due to latex_documents + start = config_file.find('Documentation/') + if start >= 0: + start = config_file.find('/', start + 1) + + end = config_file.rfind('/') + if start >= 0 and end > 0: + dir = config_file[start + 1:end] + + print("source directory: %s" % dir) + new_latex_docs = [] + latex_documents = namespace['latex_documents'] + + for l in latex_documents: + if l[0].find(dir) == 0: + has = True + fn = l[0][len(dir) + 1:] + new_latex_docs.append((fn, l[1], l[2], l[3], l[4])) + break + + namespace['latex_documents'] = new_latex_docs + + # If there is an extra conf.py file, load it if os.path.isfile(config_file): sys.stdout.write("load additional sphinx-config: %s\n" % config_file) config = namespace.copy() @@ -29,4 +52,6 @@ def loadConfig(namespace): del config['__file__'] namespace.update(config) else: - sys.stderr.write("WARNING: additional sphinx-config not found: %s\n" % config_file) + config = namespace.copy() + config['tags'].add("subproject") + namespace.update(config) From 9fc3a18a942f74d245429211577a733930d365fa Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sun, 14 Jul 2019 11:44:23 -0300 Subject: [PATCH 042/823] docs: remove extra conf.py files Now that the latex_documents are handled automatically, we can remove those extra conf.py files. Signed-off-by: Mauro Carvalho Chehab --- Documentation/admin-guide/conf.py | 10 ---------- Documentation/core-api/conf.py | 10 ---------- Documentation/crypto/conf.py | 10 ---------- Documentation/dev-tools/conf.py | 10 ---------- Documentation/doc-guide/conf.py | 10 ---------- Documentation/driver-api/80211/conf.py | 10 ---------- Documentation/driver-api/conf.py | 10 ---------- Documentation/driver-api/pm/conf.py | 10 ---------- Documentation/filesystems/conf.py | 10 ---------- Documentation/gpu/conf.py | 10 ---------- Documentation/input/conf.py | 10 ---------- Documentation/kernel-hacking/conf.py | 10 ---------- Documentation/maintainer/conf.py | 10 ---------- Documentation/media/conf.py | 12 ------------ Documentation/networking/conf.py | 10 ---------- Documentation/process/conf.py | 10 ---------- Documentation/sh/conf.py | 10 ---------- Documentation/sound/conf.py | 10 ---------- Documentation/userspace-api/conf.py | 10 ---------- Documentation/vm/conf.py | 10 ---------- Documentation/x86/conf.py | 10 ---------- 21 files changed, 212 deletions(-) delete mode 100644 Documentation/admin-guide/conf.py delete mode 100644 Documentation/core-api/conf.py delete mode 100644 Documentation/crypto/conf.py delete mode 100644 Documentation/dev-tools/conf.py delete mode 100644 Documentation/doc-guide/conf.py delete mode 100644 Documentation/driver-api/80211/conf.py delete mode 100644 Documentation/driver-api/conf.py delete mode 100644 Documentation/driver-api/pm/conf.py delete mode 100644 Documentation/filesystems/conf.py delete mode 100644 Documentation/gpu/conf.py delete mode 100644 Documentation/input/conf.py delete mode 100644 Documentation/kernel-hacking/conf.py delete mode 100644 Documentation/maintainer/conf.py delete mode 100644 Documentation/media/conf.py delete mode 100644 Documentation/networking/conf.py delete mode 100644 Documentation/process/conf.py delete mode 100644 Documentation/sh/conf.py delete mode 100644 Documentation/sound/conf.py delete mode 100644 Documentation/userspace-api/conf.py delete mode 100644 Documentation/vm/conf.py delete mode 100644 Documentation/x86/conf.py diff --git a/Documentation/admin-guide/conf.py b/Documentation/admin-guide/conf.py deleted file mode 100644 index 86f738953799..000000000000 --- a/Documentation/admin-guide/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = 'Linux Kernel User Documentation' - -tags.add("subproject") - -latex_documents = [ - ('index', 'linux-user.tex', 'Linux Kernel User Documentation', - 'The kernel development community', 'manual'), -] diff --git a/Documentation/core-api/conf.py b/Documentation/core-api/conf.py deleted file mode 100644 index db1f7659f3da..000000000000 --- a/Documentation/core-api/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Core-API Documentation" - -tags.add("subproject") - -latex_documents = [ - ('index', 'core-api.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/crypto/conf.py b/Documentation/crypto/conf.py deleted file mode 100644 index 4335d251ddf3..000000000000 --- a/Documentation/crypto/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = 'Linux Kernel Crypto API' - -tags.add("subproject") - -latex_documents = [ - ('index', 'crypto-api.tex', 'Linux Kernel Crypto API manual', - 'The kernel development community', 'manual'), -] diff --git a/Documentation/dev-tools/conf.py b/Documentation/dev-tools/conf.py deleted file mode 100644 index 7faafa3f7888..000000000000 --- a/Documentation/dev-tools/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Development tools for the kernel" - -tags.add("subproject") - -latex_documents = [ - ('index', 'dev-tools.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/doc-guide/conf.py b/Documentation/doc-guide/conf.py deleted file mode 100644 index fd3731182d5a..000000000000 --- a/Documentation/doc-guide/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = 'Linux Kernel Documentation Guide' - -tags.add("subproject") - -latex_documents = [ - ('index', 'kernel-doc-guide.tex', 'Linux Kernel Documentation Guide', - 'The kernel development community', 'manual'), -] diff --git a/Documentation/driver-api/80211/conf.py b/Documentation/driver-api/80211/conf.py deleted file mode 100644 index 4424b4b0b9c3..000000000000 --- a/Documentation/driver-api/80211/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Linux 802.11 Driver Developer's Guide" - -tags.add("subproject") - -latex_documents = [ - ('index', '80211.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/driver-api/conf.py b/Documentation/driver-api/conf.py deleted file mode 100644 index 202726d20088..000000000000 --- a/Documentation/driver-api/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "The Linux driver implementer's API guide" - -tags.add("subproject") - -latex_documents = [ - ('index', 'driver-api.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/driver-api/pm/conf.py b/Documentation/driver-api/pm/conf.py deleted file mode 100644 index a89fac11272f..000000000000 --- a/Documentation/driver-api/pm/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Device Power Management" - -tags.add("subproject") - -latex_documents = [ - ('index', 'pm.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/filesystems/conf.py b/Documentation/filesystems/conf.py deleted file mode 100644 index ea44172af5c4..000000000000 --- a/Documentation/filesystems/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Linux Filesystems API" - -tags.add("subproject") - -latex_documents = [ - ('index', 'filesystems.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/gpu/conf.py b/Documentation/gpu/conf.py deleted file mode 100644 index 1757b040fb32..000000000000 --- a/Documentation/gpu/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Linux GPU Driver Developer's Guide" - -tags.add("subproject") - -latex_documents = [ - ('index', 'gpu.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/input/conf.py b/Documentation/input/conf.py deleted file mode 100644 index d2352fdc92ed..000000000000 --- a/Documentation/input/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "The Linux input driver subsystem" - -tags.add("subproject") - -latex_documents = [ - ('index', 'linux-input.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/kernel-hacking/conf.py b/Documentation/kernel-hacking/conf.py deleted file mode 100644 index 3d8acf0f33ad..000000000000 --- a/Documentation/kernel-hacking/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Kernel Hacking Guides" - -tags.add("subproject") - -latex_documents = [ - ('index', 'kernel-hacking.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/maintainer/conf.py b/Documentation/maintainer/conf.py deleted file mode 100644 index 81e9eb7a7884..000000000000 --- a/Documentation/maintainer/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = 'Linux Kernel Development Documentation' - -tags.add("subproject") - -latex_documents = [ - ('index', 'maintainer.tex', 'Linux Kernel Development Documentation', - 'The kernel development community', 'manual'), -] diff --git a/Documentation/media/conf.py b/Documentation/media/conf.py deleted file mode 100644 index 1f194fcd2cae..000000000000 --- a/Documentation/media/conf.py +++ /dev/null @@ -1,12 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -# SPDX-License-Identifier: GPL-2.0 - -project = 'Linux Media Subsystem Documentation' - -tags.add("subproject") - -latex_documents = [ - ('index', 'media.tex', 'Linux Media Subsystem Documentation', - 'The kernel development community', 'manual'), -] diff --git a/Documentation/networking/conf.py b/Documentation/networking/conf.py deleted file mode 100644 index 40f69e67a883..000000000000 --- a/Documentation/networking/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Linux Networking Documentation" - -tags.add("subproject") - -latex_documents = [ - ('index', 'networking.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/process/conf.py b/Documentation/process/conf.py deleted file mode 100644 index 1b01a80ad9ce..000000000000 --- a/Documentation/process/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = 'Linux Kernel Development Documentation' - -tags.add("subproject") - -latex_documents = [ - ('index', 'process.tex', 'Linux Kernel Development Documentation', - 'The kernel development community', 'manual'), -] diff --git a/Documentation/sh/conf.py b/Documentation/sh/conf.py deleted file mode 100644 index 1eb684a13ac8..000000000000 --- a/Documentation/sh/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "SuperH architecture implementation manual" - -tags.add("subproject") - -latex_documents = [ - ('index', 'sh.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/sound/conf.py b/Documentation/sound/conf.py deleted file mode 100644 index 3f1fc5e74e7b..000000000000 --- a/Documentation/sound/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Linux Sound Subsystem Documentation" - -tags.add("subproject") - -latex_documents = [ - ('index', 'sound.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/userspace-api/conf.py b/Documentation/userspace-api/conf.py deleted file mode 100644 index 2eaf59f844e5..000000000000 --- a/Documentation/userspace-api/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "The Linux kernel user-space API guide" - -tags.add("subproject") - -latex_documents = [ - ('index', 'userspace-api.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/vm/conf.py b/Documentation/vm/conf.py deleted file mode 100644 index 3b0b601af558..000000000000 --- a/Documentation/vm/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Linux Memory Management Documentation" - -tags.add("subproject") - -latex_documents = [ - ('index', 'memory-management.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/x86/conf.py b/Documentation/x86/conf.py deleted file mode 100644 index 33c5c3142e20..000000000000 --- a/Documentation/x86/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "X86 architecture specific documentation" - -tags.add("subproject") - -latex_documents = [ - ('index', 'x86.tex', project, - 'The kernel development community', 'manual'), -] From 518b7d55f80eb548595c7940b6975ba350e5255d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 18 Jun 2019 15:13:40 -0300 Subject: [PATCH 043/823] docs: virtual: add it to the documentation body As files are getting converted to ReST, add them to the documentation body. Signed-off-by: Mauro Carvalho Chehab --- Documentation/index.rst | 1 + Documentation/virtual/kvm/index.rst | 1 + 2 files changed, 2 insertions(+) diff --git a/Documentation/index.rst b/Documentation/index.rst index 68ae2a4d689d..2df5a3da563c 100644 --- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -115,6 +115,7 @@ needed). target/index timers/index watchdog/index + virtual/index input/index hwmon/index gpu/index diff --git a/Documentation/virtual/kvm/index.rst b/Documentation/virtual/kvm/index.rst index 0b206a06f5be..ada224a511fe 100644 --- a/Documentation/virtual/kvm/index.rst +++ b/Documentation/virtual/kvm/index.rst @@ -9,3 +9,4 @@ KVM amd-memory-encryption cpuid + vcpu-requests From 600ea54dbaecdf3f68ec52b8d027bacbebf27d92 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Filipe=20La=C3=ADns?= Date: Tue, 16 Jul 2019 08:36:21 +0100 Subject: [PATCH 044/823] HID: logitech-dj: rename "gaming" receiver to "lightspeed" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This should help people identify the receiver. there are several receivers used in gaming mice. the "lightspeed" technology is pretty well advertise so this won't just be an obscure name. Signed-off-by: Filipe Laíns Signed-off-by: Jiri Kosina --- drivers/hid/hid-ids.h | 2 +- drivers/hid/hid-logitech-dj.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 0d695f8e1b2c..ab9d382b067d 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -768,7 +768,7 @@ #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER 0xc52f #define USB_DEVICE_ID_LOGITECH_UNIFYING_RECEIVER_2 0xc532 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_2 0xc534 -#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_GAMING 0xc539 +#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED 0xc539 #define USB_DEVICE_ID_SPACETRAVELLER 0xc623 #define USB_DEVICE_ID_SPACENAVIGATOR 0xc626 #define USB_DEVICE_ID_DINOVO_DESKTOP 0xc704 diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 6196217a7d93..4334acb49129 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -1832,9 +1832,9 @@ static const struct hid_device_id logi_dj_receivers[] = { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_2), .driver_data = recvr_type_hidpp}, - { /* Logitech gaming receiver (0xc539) */ + { /* Logitech lightspeed receiver (0xc539) */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, - USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_GAMING), + USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED), .driver_data = recvr_type_gaming_hidpp}, { /* Logitech 27 MHz HID++ 1.0 receiver (0xc513) */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER), From 27fc32fd9417968a459d43d9a7c50fd423d53eb9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Filipe=20La=C3=ADns?= Date: Tue, 16 Jul 2019 08:37:26 +0100 Subject: [PATCH 045/823] HID: logitech-hidpp: add USB PID for a few more supported mice MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add more device IDs to logitech-hidpp driver. Signed-off-by: Filipe Laíns Signed-off-by: Jiri Kosina --- drivers/hid/hid-logitech-hidpp.c | 32 +++++++++++++++++++++++++++++++- 1 file changed, 31 insertions(+), 1 deletion(-) diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index e3b6245bf4b2..21268c9fa71a 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -3749,15 +3749,45 @@ static const struct hid_device_id hidpp_devices[] = { { L27MHZ_DEVICE(HID_ANY_ID) }, - { /* Logitech G403 Gaming Mouse over USB */ + { /* Logitech G203/Prodigy Gaming Mouse */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC084) }, + { /* Logitech G302 Gaming Mouse */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC07F) }, + { /* Logitech G303 Gaming Mouse */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC080) }, + { /* Logitech G400 Gaming Mouse */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC07E) }, + { /* Logitech G403 Wireless Gaming Mouse over USB */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC082) }, + { /* Logitech G403 Gaming Mouse */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC083) }, + { /* Logitech G403 Hero Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC08F) }, + { /* Logitech G502 Proteus Core Gaming Mouse */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC07D) }, + { /* Logitech G502 Proteus Spectrum Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC332) }, + { /* Logitech G502 Hero Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC08B) }, { /* Logitech G700 Gaming Mouse over USB */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC06B) }, + { /* Logitech G700s Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC07C) }, + { /* Logitech G703 Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC087) }, + { /* Logitech G703 Hero Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC090) }, { /* Logitech G900 Gaming Mouse over USB */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC081) }, + { /* Logitech G903 Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC086) }, + { /* Logitech G903 Hero Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC091) }, { /* Logitech G920 Wheel over USB */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G920_WHEEL), .driver_data = HIDPP_QUIRK_CLASS_G920 | HIDPP_QUIRK_FORCE_OUTPUT_REPORTS}, + { /* Logitech G Pro Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC088) }, { /* MX5000 keyboard over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb305), From d79f7badd118e678cf85462df637329aff26e9d5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Filipe=20La=C3=ADns?= Date: Tue, 16 Jul 2019 08:37:47 +0100 Subject: [PATCH 046/823] HID: logitech-dj: add the Powerplay receiver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add device ID for Powerplay receiver. Signed-off-by: Filipe Laíns Signed-off-by: Jiri Kosina --- drivers/hid/hid-ids.h | 1 + drivers/hid/hid-logitech-dj.c | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index ab9d382b067d..884356feb016 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -769,6 +769,7 @@ #define USB_DEVICE_ID_LOGITECH_UNIFYING_RECEIVER_2 0xc532 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_2 0xc534 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED 0xc539 +#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_POWERPLAY 0xc53a #define USB_DEVICE_ID_SPACETRAVELLER 0xc623 #define USB_DEVICE_ID_SPACENAVIGATOR 0xc626 #define USB_DEVICE_ID_DINOVO_DESKTOP 0xc704 diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 4334acb49129..d5b47ec1510c 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -1839,6 +1839,10 @@ static const struct hid_device_id logi_dj_receivers[] = { { /* Logitech 27 MHz HID++ 1.0 receiver (0xc513) */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER), .driver_data = recvr_type_27mhz}, + { /* Logitech powerplay receiver (0xc53a) */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, + USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_POWERPLAY), + .driver_data = recvr_type_gaming_hidpp}, { /* Logitech 27 MHz HID++ 1.0 receiver (0xc517) */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_S510_RECEIVER_2), From 65f11c72780fa9d598df88def045ccb6a885cf80 Mon Sep 17 00:00:00 2001 From: Ilya Trukhanov Date: Tue, 2 Jul 2019 13:37:16 +0300 Subject: [PATCH 047/823] HID: Add 044f:b320 ThrustMaster, Inc. 2 in 1 DT Enable force feedback for the Thrustmaster Dual Trigger 2 in 1 Rumble Force gamepad. Compared to other Thrustmaster devices, left and right rumble motors here are swapped. Signed-off-by: Ilya Trukhanov Signed-off-by: Jiri Kosina --- drivers/hid/hid-tmff.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/hid/hid-tmff.c b/drivers/hid/hid-tmff.c index e12f2588ddeb..bdfc5ff3b2c5 100644 --- a/drivers/hid/hid-tmff.c +++ b/drivers/hid/hid-tmff.c @@ -22,6 +22,8 @@ #include "hid-ids.h" +#define THRUSTMASTER_DEVICE_ID_2_IN_1_DT 0xb320 + static const signed short ff_rumble[] = { FF_RUMBLE, -1 @@ -76,6 +78,7 @@ static int tmff_play(struct input_dev *dev, void *data, struct hid_field *ff_field = tmff->ff_field; int x, y; int left, right; /* Rumbling */ + int motor_swap; switch (effect->type) { case FF_CONSTANT: @@ -100,6 +103,13 @@ static int tmff_play(struct input_dev *dev, void *data, ff_field->logical_minimum, ff_field->logical_maximum); + /* 2-in-1 strong motor is left */ + if (hid->product == THRUSTMASTER_DEVICE_ID_2_IN_1_DT) { + motor_swap = left; + left = right; + right = motor_swap; + } + dbg_hid("(left,right)=(%08x, %08x)\n", left, right); ff_field->value[0] = left; ff_field->value[1] = right; @@ -226,6 +236,8 @@ static const struct hid_device_id tm_devices[] = { .driver_data = (unsigned long)ff_rumble }, { HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb304), /* FireStorm Dual Power 2 (and 3) */ .driver_data = (unsigned long)ff_rumble }, + { HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, THRUSTMASTER_DEVICE_ID_2_IN_1_DT), /* Dual Trigger 2-in-1 */ + .driver_data = (unsigned long)ff_rumble }, { HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb323), /* Dual Trigger 3-in-1 (PC Mode) */ .driver_data = (unsigned long)ff_rumble }, { HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb324), /* Dual Trigger 3-in-1 (PS3 Mode) */ From 64dbc122b20f75183d8822618c24f85144a5a94d Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 15 Jul 2019 11:51:39 -0500 Subject: [PATCH 048/823] x86/entry/64: Use JMP instead of JMPQ Somehow the swapgs mitigation entry code patch ended up with a JMPQ instruction instead of JMP, where only the short jump is needed. Some assembler versions apparently fail to optimize JMPQ into a two-byte JMP when possible, instead always using a 7-byte JMP with relocation. For some reason that makes the entry code explode with a #GP during boot. Change it back to "JMP" as originally intended. Fixes: 18ec54fdd6d1 ("x86/speculation: Prepare entry code for Spectre v1 swapgs mitigations") Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner --- arch/x86/entry/entry_64.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 57a0d96d6beb..b043c754d978 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -549,7 +549,7 @@ ENTRY(interrupt_entry) UNWIND_HINT_FUNC movq (%rdi), %rdi - jmpq 2f + jmp 2f 1: FENCE_SWAPGS_KERNEL_ENTRY 2: From 2922d1cc1696200a3e1fd6d82a7798fcd2cadf12 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 16 Jul 2019 22:46:51 +0200 Subject: [PATCH 049/823] spi: gpio: Add SPI_MASTER_GPIO_SS flag The GPIO SPI master has some code in its local CS callback to set the initial sck GPIO value. This was lost in the commit converting it to use SPI core GPIO handling as this callback isn't called if the internal GPIO handling is active. Add the special SPI_MASTER_GPIO_SS to ascertain it gets called anyway so we get the initial SCK setting right. There is some platform provided GPIO handling there as well but this will be skipped as the cs_gpios will be NULL. My test targets seem not to care about the initial SCK value so I am uncertain if this is a regression, but to preserve the previous semantic we better do this. Cc: Andrey Smirnov Fixes: 249e2632dcd0 ("spi: gpio: Don't request CS GPIO in DT use-case") Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20190716204651.7743-1-linus.walleij@linaro.org Signed-off-by: Mark Brown --- drivers/spi/spi-gpio.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c index eca9d52ecf65..9eb82150666e 100644 --- a/drivers/spi/spi-gpio.c +++ b/drivers/spi/spi-gpio.c @@ -410,6 +410,12 @@ static int spi_gpio_probe(struct platform_device *pdev) bb = &spi_gpio->bitbang; bb->master = master; + /* + * There is some additional business, apart from driving the CS GPIO + * line, that we need to do on selection. This makes the local + * callback for chipselect always get called. + */ + master->flags |= SPI_MASTER_GPIO_SS; bb->chipselect = spi_gpio_chipselect; bb->set_line_direction = spi_gpio_set_direction; From 59d81c1e3cade953a0cb3f66ce9a3f2398fdfac3 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 16 Jul 2019 11:52:00 +0200 Subject: [PATCH 050/823] ALSA: hda - Optimize resume for codecs without jack detection The codecs without jack detection also don't have to be resumed forcibly because, obviously, they have no jack. Skip the forced resume in such a case as optimization as well. Reviewed-by: Kai Vehmanen Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_codec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index e30e86ca6b72..51f10ed9bc43 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -2942,7 +2942,7 @@ static int hda_codec_runtime_resume(struct device *dev) static int hda_codec_force_resume(struct device *dev) { struct hda_codec *codec = dev_to_hda_codec(dev); - bool forced_resume = !codec->relaxed_resume; + bool forced_resume = !codec->relaxed_resume && codec->jacktbl.used; int ret; /* The get/put pair below enforces the runtime resume even if the From 70256b42caaf3e13c2932c2be7903a73fbe8bb8b Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Thu, 18 Jul 2019 17:53:13 +0800 Subject: [PATCH 051/823] ALSA: line6: Fix wrong altsetting for LINE6_PODHD500_1 Commit 7b9584fa1c0b ("staging: line6: Move altsetting to properties") set a wrong altsetting for LINE6_PODHD500_1 during refactoring. Set the correct altsetting number to fix the issue. BugLink: https://bugs.launchpad.net/bugs/1790595 Fixes: 7b9584fa1c0b ("staging: line6: Move altsetting to properties") Signed-off-by: Kai-Heng Feng Cc: Signed-off-by: Takashi Iwai --- sound/usb/line6/podhd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/usb/line6/podhd.c b/sound/usb/line6/podhd.c index f0662bd4e50f..27bf61c177c0 100644 --- a/sound/usb/line6/podhd.c +++ b/sound/usb/line6/podhd.c @@ -368,7 +368,7 @@ static const struct line6_properties podhd_properties_table[] = { .name = "POD HD500", .capabilities = LINE6_CAP_PCM | LINE6_CAP_HWMON, - .altsetting = 1, + .altsetting = 0, .ep_ctrl_r = 0x81, .ep_ctrl_w = 0x01, .ep_audio_r = 0x86, From b5e02b484d6f12112d49326bff2aecfccd2f518d Mon Sep 17 00:00:00 2001 From: Paolo Valente Date: Thu, 18 Jul 2019 09:08:52 +0200 Subject: [PATCH 052/823] block, bfq: check also in-flight I/O in dispatch plugging Consider a sync bfq_queue Q that remains empty while in service, and suppose that, when this happens, there is a fair amount of already in-flight I/O not belonging to Q. In such a situation, I/O dispatching may need to be plugged (until new I/O arrives for Q), for the following reason. The drive may decide to serve in-flight non-Q's I/O requests before Q's ones, thereby delaying the arrival of new I/O requests for Q (recall that Q is sync). If I/O-dispatching is not plugged, then, while Q remains empty, a basically uncontrolled amount of I/O from other queues may be dispatched too, possibly causing the service of Q's I/O to be delayed even longer in the drive. This problem gets more and more serious as the speed and the queue depth of the drive grow, because, as these two quantities grow, the probability to find no queue busy but many requests in flight grows too. If Q has the same weight and priority as the other queues, then the above delay is unlikely to cause any issue, because all queues tend to undergo the same treatment. So, since not plugging I/O dispatching is convenient for throughput, it is better not to plug. Things change in case Q has a higher weight or priority than some other queue, because Q's service guarantees may simply be violated. For this reason, commit 1de0c4cd9ea6 ("block, bfq: reduce idling only in symmetric scenarios") does plug I/O in such an asymmetric scenario. Plugging minimizes the delay induced by already in-flight I/O, and enables Q to recover the bandwidth it may lose because of this delay. Yet the above commit does not cover the case of weight-raised queues, for efficiency concerns. For weight-raised queues, I/O-dispatch plugging is activated simply if not all bfq_queues are weight-raised. But this check does not handle the case of in-flight requests, because a bfq_queue may become non busy *before* all its in-flight requests are completed. This commit performs I/O-dispatch plugging for weight-raised queues if there are some in-flight requests. As a practical example of the resulting recover of control, under write load on a Samsung SSD 970 PRO, gnome-terminal starts in 1.5 seconds after this fix, against 15 seconds before the fix (as a reference, gnome-terminal takes about 35 seconds to start with any of the other I/O schedulers). Fixes: 1de0c4cd9ea6 ("block, bfq: reduce idling only in symmetric scenarios") Signed-off-by: Paolo Valente Signed-off-by: Jens Axboe --- block/bfq-iosched.c | 67 +++++++++++++++++++++++++++++---------------- 1 file changed, 43 insertions(+), 24 deletions(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 50c9d2598500..b627e3fc6d53 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -3354,38 +3354,57 @@ static void bfq_dispatch_remove(struct request_queue *q, struct request *rq) * there is no active group, then the primary expectation for * this device is probably a high throughput. * - * We are now left only with explaining the additional - * compound condition that is checked below for deciding - * whether the scenario is asymmetric. To explain this - * compound condition, we need to add that the function + * We are now left only with explaining the two sub-conditions in the + * additional compound condition that is checked below for deciding + * whether the scenario is asymmetric. To explain the first + * sub-condition, we need to add that the function * bfq_asymmetric_scenario checks the weights of only - * non-weight-raised queues, for efficiency reasons (see - * comments on bfq_weights_tree_add()). Then the fact that - * bfqq is weight-raised is checked explicitly here. More - * precisely, the compound condition below takes into account - * also the fact that, even if bfqq is being weight-raised, - * the scenario is still symmetric if all queues with requests - * waiting for completion happen to be - * weight-raised. Actually, we should be even more precise - * here, and differentiate between interactive weight raising - * and soft real-time weight raising. + * non-weight-raised queues, for efficiency reasons (see comments on + * bfq_weights_tree_add()). Then the fact that bfqq is weight-raised + * is checked explicitly here. More precisely, the compound condition + * below takes into account also the fact that, even if bfqq is being + * weight-raised, the scenario is still symmetric if all queues with + * requests waiting for completion happen to be + * weight-raised. Actually, we should be even more precise here, and + * differentiate between interactive weight raising and soft real-time + * weight raising. + * + * The second sub-condition checked in the compound condition is + * whether there is a fair amount of already in-flight I/O not + * belonging to bfqq. If so, I/O dispatching is to be plugged, for the + * following reason. The drive may decide to serve in-flight + * non-bfqq's I/O requests before bfqq's ones, thereby delaying the + * arrival of new I/O requests for bfqq (recall that bfqq is sync). If + * I/O-dispatching is not plugged, then, while bfqq remains empty, a + * basically uncontrolled amount of I/O from other queues may be + * dispatched too, possibly causing the service of bfqq's I/O to be + * delayed even longer in the drive. This problem gets more and more + * serious as the speed and the queue depth of the drive grow, + * because, as these two quantities grow, the probability to find no + * queue busy but many requests in flight grows too. By contrast, + * plugging I/O dispatching minimizes the delay induced by already + * in-flight I/O, and enables bfqq to recover the bandwidth it may + * lose because of this delay. * * As a side note, it is worth considering that the above - * device-idling countermeasures may however fail in the - * following unlucky scenario: if idling is (correctly) - * disabled in a time period during which all symmetry - * sub-conditions hold, and hence the device is allowed to - * enqueue many requests, but at some later point in time some - * sub-condition stops to hold, then it may become impossible - * to let requests be served in the desired order until all - * the requests already queued in the device have been served. + * device-idling countermeasures may however fail in the following + * unlucky scenario: if I/O-dispatch plugging is (correctly) disabled + * in a time period during which all symmetry sub-conditions hold, and + * therefore the device is allowed to enqueue many requests, but at + * some later point in time some sub-condition stops to hold, then it + * may become impossible to make requests be served in the desired + * order until all the requests already queued in the device have been + * served. The last sub-condition commented above somewhat mitigates + * this problem for weight-raised queues. */ static bool idling_needed_for_service_guarantees(struct bfq_data *bfqd, struct bfq_queue *bfqq) { return (bfqq->wr_coeff > 1 && - bfqd->wr_busy_queues < - bfq_tot_busy_queues(bfqd)) || + (bfqd->wr_busy_queues < + bfq_tot_busy_queues(bfqd) || + bfqd->rq_in_driver >= + bfqq->dispatched + 4)) || bfq_asymmetric_scenario(bfqd, bfqq); } From 4d202c8c8ed3822327285747db1765967110b274 Mon Sep 17 00:00:00 2001 From: "Gautham R. Shenoy" Date: Wed, 17 Jul 2019 16:05:24 +0530 Subject: [PATCH 053/823] powerpc/xive: Fix loop exit-condition in xive_find_target_in_mask() xive_find_target_in_mask() has the following for(;;) loop which has a bug when @first == cpumask_first(@mask) and condition 1 fails to hold for every CPU in @mask. In this case we loop forever in the for-loop. first = cpu; for (;;) { if (cpu_online(cpu) && xive_try_pick_target(cpu)) // condition 1 return cpu; cpu = cpumask_next(cpu, mask); if (cpu == first) // condition 2 break; if (cpu >= nr_cpu_ids) // condition 3 cpu = cpumask_first(mask); } This is because, when @first == cpumask_first(@mask), we never hit the condition 2 (cpu == first) since prior to this check, we would have executed "cpu = cpumask_next(cpu, mask)" which will set the value of @cpu to a value greater than @first or to nr_cpus_ids. When this is coupled with the fact that condition 1 is not met, we will never exit this loop. This was discovered by the hard-lockup detector while running LTP test concurrently with SMT switch tests. watchdog: CPU 12 detected hard LOCKUP on other CPUs 68 watchdog: CPU 12 TB:85587019220796, last SMP heartbeat TB:85578827223399 (15999ms ago) watchdog: CPU 68 Hard LOCKUP watchdog: CPU 68 TB:85587019361273, last heartbeat TB:85576815065016 (19930ms ago) CPU: 68 PID: 45050 Comm: hxediag Kdump: loaded Not tainted 4.18.0-100.el8.ppc64le #1 NIP: c0000000006f5578 LR: c000000000cba9ec CTR: 0000000000000000 REGS: c000201fff3c7d80 TRAP: 0100 Not tainted (4.18.0-100.el8.ppc64le) MSR: 9000000002883033 CR: 24028424 XER: 00000000 CFAR: c0000000006f558c IRQMASK: 1 GPR00: c0000000000afc58 c000201c01c43400 c0000000015ce500 c000201cae26ec18 GPR04: 0000000000000800 0000000000000540 0000000000000800 00000000000000f8 GPR08: 0000000000000020 00000000000000a8 0000000080000000 c00800001a1beed8 GPR12: c0000000000b1410 c000201fff7f4c00 0000000000000000 0000000000000000 GPR16: 0000000000000000 0000000000000000 0000000000000540 0000000000000001 GPR20: 0000000000000048 0000000010110000 c00800001a1e3780 c000201cae26ed18 GPR24: 0000000000000000 c000201cae26ed8c 0000000000000001 c000000001116bc0 GPR28: c000000001601ee8 c000000001602494 c000201cae26ec18 000000000000001f NIP [c0000000006f5578] find_next_bit+0x38/0x90 LR [c000000000cba9ec] cpumask_next+0x2c/0x50 Call Trace: [c000201c01c43400] [c000201cae26ec18] 0xc000201cae26ec18 (unreliable) [c000201c01c43420] [c0000000000afc58] xive_find_target_in_mask+0x1b8/0x240 [c000201c01c43470] [c0000000000b0228] xive_pick_irq_target.isra.3+0x168/0x1f0 [c000201c01c435c0] [c0000000000b1470] xive_irq_startup+0x60/0x260 [c000201c01c43640] [c0000000001d8328] __irq_startup+0x58/0xf0 [c000201c01c43670] [c0000000001d844c] irq_startup+0x8c/0x1a0 [c000201c01c436b0] [c0000000001d57b0] __setup_irq+0x9f0/0xa90 [c000201c01c43760] [c0000000001d5aa0] request_threaded_irq+0x140/0x220 [c000201c01c437d0] [c00800001a17b3d4] bnx2x_nic_load+0x188c/0x3040 [bnx2x] [c000201c01c43950] [c00800001a187c44] bnx2x_self_test+0x1fc/0x1f70 [bnx2x] [c000201c01c43a90] [c000000000adc748] dev_ethtool+0x11d8/0x2cb0 [c000201c01c43b60] [c000000000b0b61c] dev_ioctl+0x5ac/0xa50 [c000201c01c43bf0] [c000000000a8d4ec] sock_do_ioctl+0xbc/0x1b0 [c000201c01c43c60] [c000000000a8dfb8] sock_ioctl+0x258/0x4f0 [c000201c01c43d20] [c0000000004c9704] do_vfs_ioctl+0xd4/0xa70 [c000201c01c43de0] [c0000000004ca274] sys_ioctl+0xc4/0x160 [c000201c01c43e30] [c00000000000b388] system_call+0x5c/0x70 Instruction dump: 78aad182 54a806be 3920ffff 78a50664 794a1f24 7d294036 7d43502a 7d295039 4182001c 48000034 78a9d182 79291f24 <7d23482a> 2fa90000 409e0020 38a50040 To fix this, move the check for condition 2 after the check for condition 3, so that we are able to break out of the loop soon after iterating through all the CPUs in the @mask in the problem case. Use do..while() to achieve this. Fixes: 243e25112d06 ("powerpc/xive: Native exploitation of the XIVE interrupt controller") Cc: stable@vger.kernel.org # v4.12+ Reported-by: Indira P. Joga Signed-off-by: Gautham R. Shenoy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1563359724-13931-1-git-send-email-ego@linux.vnet.ibm.com --- arch/powerpc/sysdev/xive/common.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index 082c7e1c20f0..1cdb39575eae 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -479,7 +479,7 @@ static int xive_find_target_in_mask(const struct cpumask *mask, * Now go through the entire mask until we find a valid * target. */ - for (;;) { + do { /* * We re-check online as the fallback case passes us * an untested affinity mask @@ -487,12 +487,11 @@ static int xive_find_target_in_mask(const struct cpumask *mask, if (cpu_online(cpu) && xive_try_pick_target(cpu)) return cpu; cpu = cpumask_next(cpu, mask); - if (cpu == first) - break; /* Wrap around */ if (cpu >= nr_cpu_ids) cpu = cpumask_first(mask); - } + } while (cpu != first); + return -1; } From a6d81d30d3cd87f85bfd922358eb18b8146c4925 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 16 Jul 2019 16:19:25 -0400 Subject: [PATCH 054/823] wait: add wq_has_single_sleeper helper rq-qos sits in the io path so we want to take locks as sparingly as possible. To accomplish this we try not to take the waitqueue head lock unless we are sure we need to go to sleep, and we have an optimization to make sure that we don't starve out existing waiters. Since we check if there are existing waiters locklessly we need to be able to update our view of the waitqueue list after we've added ourselves to the waitqueue. Accomplish this by adding this helper to see if there is more than just ourselves on the list. Reviewed-by: Oleg Nesterov Signed-off-by: Josef Bacik Signed-off-by: Jens Axboe --- include/linux/wait.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/include/linux/wait.h b/include/linux/wait.h index b6f77cf60dd7..30c515520fb2 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -126,6 +126,19 @@ static inline int waitqueue_active(struct wait_queue_head *wq_head) return !list_empty(&wq_head->head); } +/** + * wq_has_single_sleeper - check if there is only one sleeper + * @wq_head: wait queue head + * + * Returns true of wq_head has only one sleeper on the list. + * + * Please refer to the comment for waitqueue_active. + */ +static inline bool wq_has_single_sleeper(struct wait_queue_head *wq_head) +{ + return list_is_singular(&wq_head->head); +} + /** * wq_has_sleeper - check if there are any waiting processes * @wq_head: wait queue head From 545fbd0775bafcefc8f7bc844291bd13c44b7fdc Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 16 Jul 2019 16:19:26 -0400 Subject: [PATCH 055/823] rq-qos: fix missed wake-ups in rq_qos_throttle We saw a hang in production with WBT where there was only one waiter in the throttle path and no outstanding IO. This is because of the has_sleepers optimization that is used to make sure we don't steal an inflight counter for new submitters when there are people already on the list. We can race with our check to see if the waitqueue has any waiters (this is done locklessly) and the time we actually add ourselves to the waitqueue. If this happens we'll go to sleep and never be woken up because nobody is doing IO to wake us up. Fix this by checking if the waitqueue has a single sleeper on the list after we add ourselves, that way we have an uptodate view of the list. Reviewed-by: Oleg Nesterov Signed-off-by: Josef Bacik Signed-off-by: Jens Axboe --- block/blk-rq-qos.c | 1 + 1 file changed, 1 insertion(+) diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index 659ccb8b693f..67a0a4c07060 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -244,6 +244,7 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, return; prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE); + has_sleeper = !wq_has_single_sleeper(&rqw->wait); do { if (data.got_token) break; From 64e7ea875ef63b2801be7954cf7257d1bfccc266 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 16 Jul 2019 16:19:27 -0400 Subject: [PATCH 056/823] rq-qos: don't reset has_sleepers on spurious wakeups If we raced with somebody else getting an inflight counter we could fail to get an inflight counter with no sleepers on the list, and thus need to go to sleep. In this case has_sleepers should be true because we are now relying on the waker to get our inflight counter for us. And in the case of spurious wakeups we'd still want this to be the case. So set has_sleepers to true if we went to sleep to make sure we're woken up the proper way. Reviewed-by: Oleg Nesterov Signed-off-by: Josef Bacik Signed-off-by: Jens Axboe --- block/blk-rq-qos.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index 67a0a4c07060..69a0f0b77795 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -261,7 +261,7 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, break; } io_schedule(); - has_sleeper = false; + has_sleeper = true; } while (1); finish_wait(&rqw->wait, &data.wq); } From d14a9b389a86a5154b704bc88ce8dd37c701456a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 16 Jul 2019 16:19:28 -0400 Subject: [PATCH 057/823] rq-qos: set ourself TASK_UNINTERRUPTIBLE after we schedule In case we get a spurious wakeup we need to make sure to re-set ourselves to TASK_UNINTERRUPTIBLE so we don't busy wait. Reviewed-by: Oleg Nesterov Signed-off-by: Josef Bacik Signed-off-by: Jens Axboe --- block/blk-rq-qos.c | 1 + 1 file changed, 1 insertion(+) diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index 69a0f0b77795..c450b8952eae 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -262,6 +262,7 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, } io_schedule(); has_sleeper = true; + set_current_state(TASK_UNINTERRUPTIBLE); } while (1); finish_wait(&rqw->wait, &data.wq); } From ac38297f7038cd5b80d66f8809c7bbf5b70031f3 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 16 Jul 2019 16:19:29 -0400 Subject: [PATCH 058/823] rq-qos: use a mb for got_token Oleg noticed that our checking of data.got_token is unsafe in the cleanup case, and should really use a memory barrier. Use a wmb on the write side, and a rmb() on the read side. We don't need one in the main loop since we're saved by set_current_state(). Reviewed-by: Oleg Nesterov Signed-off-by: Josef Bacik Signed-off-by: Jens Axboe --- block/blk-rq-qos.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index c450b8952eae..3954c0dc1443 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -202,6 +202,7 @@ static int rq_qos_wake_function(struct wait_queue_entry *curr, return -1; data->got_token = true; + smp_wmb(); list_del_init(&curr->entry); wake_up_process(data->task); return 1; @@ -246,6 +247,7 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE); has_sleeper = !wq_has_single_sleeper(&rqw->wait); do { + /* The memory barrier in set_task_state saves us here. */ if (data.got_token) break; if (!has_sleeper && acquire_inflight_cb(rqw, private_data)) { @@ -256,6 +258,7 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, * which means we now have two. Put our local token * and wake anyone else potentially waiting for one. */ + smp_rmb(); if (data.got_token) cleanup_cb(rqw, private_data); break; From c0e48f9dea9129aa11bec3ed13803bcc26e96e49 Mon Sep 17 00:00:00 2001 From: Zhengyuan Liu Date: Thu, 18 Jul 2019 20:44:00 +0800 Subject: [PATCH 059/823] io_uring: add a memory barrier before atomic_read There is a hang issue while using fio to do some basic test. The issue can be easily reproduced using the below script: while true do fio --ioengine=io_uring -rw=write -bs=4k -numjobs=1 \ -size=1G -iodepth=64 -name=uring --filename=/dev/zero done After several minutes (or more), fio would block at io_uring_enter->io_cqring_wait in order to waiting for previously committed sqes to be completed and can't return to user anymore until we send a SIGTERM to fio. After receiving SIGTERM, fio hangs at io_ring_ctx_wait_and_kill with a backtrace like this: [54133.243816] Call Trace: [54133.243842] __schedule+0x3a0/0x790 [54133.243868] schedule+0x38/0xa0 [54133.243880] schedule_timeout+0x218/0x3b0 [54133.243891] ? sched_clock+0x9/0x10 [54133.243903] ? wait_for_completion+0xa3/0x130 [54133.243916] ? _raw_spin_unlock_irq+0x2c/0x40 [54133.243930] ? trace_hardirqs_on+0x3f/0xe0 [54133.243951] wait_for_completion+0xab/0x130 [54133.243962] ? wake_up_q+0x70/0x70 [54133.243984] io_ring_ctx_wait_and_kill+0xa0/0x1d0 [54133.243998] io_uring_release+0x20/0x30 [54133.244008] __fput+0xcf/0x270 [54133.244029] ____fput+0xe/0x10 [54133.244040] task_work_run+0x7f/0xa0 [54133.244056] do_exit+0x305/0xc40 [54133.244067] ? get_signal+0x13b/0xbd0 [54133.244088] do_group_exit+0x50/0xd0 [54133.244103] get_signal+0x18d/0xbd0 [54133.244112] ? _raw_spin_unlock_irqrestore+0x36/0x60 [54133.244142] do_signal+0x34/0x720 [54133.244171] ? exit_to_usermode_loop+0x7e/0x130 [54133.244190] exit_to_usermode_loop+0xc0/0x130 [54133.244209] do_syscall_64+0x16b/0x1d0 [54133.244221] entry_SYSCALL_64_after_hwframe+0x49/0xbe The reason is that we had added a req to ctx->pending_async at the very end, but it didn't get a chance to be processed. How could this happen? fio#cpu0 wq#cpu1 io_add_to_prev_work io_sq_wq_submit_work atomic_read() <<< 1 atomic_dec_return() << 1->0 list_empty(); <<< true; list_add_tail() atomic_read() << 0 or 1? As atomic_ops.rst states, atomic_read does not guarantee that the runtime modification by any other thread is visible yet, so we must take care of that with a proper implicit or explicit memory barrier. This issue was detected with the help of Jackie's Fixes: 31b515106428 ("io_uring: allow workqueue item to handle multiple buffered requests") Signed-off-by: Zhengyuan Liu Signed-off-by: Jens Axboe --- fs/io_uring.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/io_uring.c b/fs/io_uring.c index 5ec06e5ba0be..324530c4d2ce 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1924,6 +1924,10 @@ static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req) ret = true; spin_lock(&list->lock); list_add_tail(&req->list, &list->list); + /* + * Ensure we see a simultaneous modification from io_sq_wq_submit_work() + */ + smp_mb(); if (!atomic_read(&list->cnt)) { list_del_init(&req->list); ret = false; From ad28e02420beae459bf48be14de5de1d76e79704 Mon Sep 17 00:00:00 2001 From: Joseph Greathouse Date: Wed, 17 Jul 2019 11:55:22 -0500 Subject: [PATCH 060/823] drm/amdgpu: Default disable GDS for compute VMIDs The GDS and GWS blocks default to allowing all VMIDs to access all entries. Graphics VMIDs can handle setting these limits when the driver launches work. However, compute workloads under HWS control don't go through the kernel driver. Instead, HWS firmware should set these limits when a process is put into a VMID slot. Disable access to these devices by default by turning off all mask bits (for OA) and setting BASE=SIZE=0 (for GDS and GWS) for all compute VMIDs. If a process wants to use these resources, they can request this from the HWS firmware (when such capabilities are enabled). HWS will then handle setting the base and limit for the process when it is assigned to a VMID. This will also prevent user kernels from getting 'stuck' in GWS by accident if they write GWS-using code but HWS firmware is not set up to handle GWS reset. Until HWS is enabled to handle GWS properly, all GWS accesses will MEM_VIOL fault the kernel. v2: Move initialization outside of SRBM mutex Signed-off-by: Joseph Greathouse Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 9 +++++++++ drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 9 +++++++++ drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 9 +++++++++ drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 9 +++++++++ 4 files changed, 36 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 1675d5837c3c..3df50c9c2fb0 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -1441,6 +1441,15 @@ static void gfx_v10_0_init_compute_vmid(struct amdgpu_device *adev) } nv_grbm_select(adev, 0, 0, 0, 0); mutex_unlock(&adev->srbm_mutex); + + /* Initialize all compute VMIDs to have no GDS, GWS, or OA + acccess. These should be enabled by FW for target VMIDs. */ + for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) { + WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_BASE, 2 * i, 0); + WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_SIZE, 2 * i, 0); + WREG32_SOC15_OFFSET(GC, 0, mmGDS_GWS_VMID0, i, 0); + WREG32_SOC15_OFFSET(GC, 0, mmGDS_OA_VMID0, i, 0); + } } static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 0db9f488da7e..21187275dfd3 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -1879,6 +1879,15 @@ static void gfx_v7_0_init_compute_vmid(struct amdgpu_device *adev) } cik_srbm_select(adev, 0, 0, 0, 0); mutex_unlock(&adev->srbm_mutex); + + /* Initialize all compute VMIDs to have no GDS, GWS, or OA + acccess. These should be enabled by FW for target VMIDs. */ + for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) { + WREG32(amdgpu_gds_reg_offset[i].mem_base, 0); + WREG32(amdgpu_gds_reg_offset[i].mem_size, 0); + WREG32(amdgpu_gds_reg_offset[i].gws, 0); + WREG32(amdgpu_gds_reg_offset[i].oa, 0); + } } static void gfx_v7_0_config_init(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 5f401b41ef7c..751567f78567 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -3706,6 +3706,15 @@ static void gfx_v8_0_init_compute_vmid(struct amdgpu_device *adev) } vi_srbm_select(adev, 0, 0, 0, 0); mutex_unlock(&adev->srbm_mutex); + + /* Initialize all compute VMIDs to have no GDS, GWS, or OA + acccess. These should be enabled by FW for target VMIDs. */ + for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) { + WREG32(amdgpu_gds_reg_offset[i].mem_base, 0); + WREG32(amdgpu_gds_reg_offset[i].mem_size, 0); + WREG32(amdgpu_gds_reg_offset[i].gws, 0); + WREG32(amdgpu_gds_reg_offset[i].oa, 0); + } } static void gfx_v8_0_config_init(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index f4c4eea62526..1cf639a51178 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1918,6 +1918,15 @@ static void gfx_v9_0_init_compute_vmid(struct amdgpu_device *adev) } soc15_grbm_select(adev, 0, 0, 0, 0); mutex_unlock(&adev->srbm_mutex); + + /* Initialize all compute VMIDs to have no GDS, GWS, or OA + acccess. These should be enabled by FW for target VMIDs. */ + for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) { + WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_BASE, 2 * i, 0); + WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_SIZE, 2 * i, 0); + WREG32_SOC15_OFFSET(GC, 0, mmGDS_GWS_VMID0, i, 0); + WREG32_SOC15_OFFSET(GC, 0, mmGDS_OA_VMID0, i, 0); + } } static void gfx_v9_0_constants_init(struct amdgpu_device *adev) From 23d66e75d7c75f108754297f6eae77348a7cd544 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Wed, 17 Jul 2019 16:32:27 +0800 Subject: [PATCH 061/823] drm/amd/powerplay: report bootup clock as max supported on dpm disabled With gfxclk or uclk dpm disabled, it's reasonable to report bootup clock as the max supported. Signed-off-by: Evan Quan Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/amdgpu_smu.c | 27 +++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index f1565c448de5..768aae2e20da 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -137,12 +137,37 @@ int smu_get_dpm_freq_range(struct smu_context *smu, enum smu_clk_type clk_type, { int ret = 0, clk_id = 0; uint32_t param = 0; + uint32_t clock_limit; if (!min && !max) return -EINVAL; - if (!smu_clk_dpm_is_enabled(smu, clk_type)) + if (!smu_clk_dpm_is_enabled(smu, clk_type)) { + switch (clk_type) { + case SMU_MCLK: + case SMU_UCLK: + clock_limit = smu->smu_table.boot_values.uclk; + break; + case SMU_GFXCLK: + case SMU_SCLK: + clock_limit = smu->smu_table.boot_values.gfxclk; + break; + case SMU_SOCCLK: + clock_limit = smu->smu_table.boot_values.socclk; + break; + default: + clock_limit = 0; + break; + } + + /* clock in Mhz unit */ + if (min) + *min = clock_limit / 100; + if (max) + *max = clock_limit / 100; + return 0; + } mutex_lock(&smu->mutex); clk_id = smu_clk_get_index(smu, clk_type); From 5f872b723a451a26ad0f1d29541df9de5d23529d Mon Sep 17 00:00:00 2001 From: Hawking Zhang Date: Thu, 18 Jul 2019 12:49:15 +0800 Subject: [PATCH 062/823] drm/amdgpu: do not create ras debugfs/sysfs node for ASICs that don't have ras ability driver shouldn't init any ras debugfs/sysfs node for ASICs that don't have ras hardware ability Signed-off-by: Hawking Zhang Reviewed-by: Feifei Xu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 1a4412e47810..3a9ece450b31 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1557,6 +1557,12 @@ int amdgpu_ras_init(struct amdgpu_device *adev) amdgpu_ras_check_supported(adev, &con->hw_supported, &con->supported); + if (!con->hw_supported) { + amdgpu_ras_set_context(adev, NULL); + kfree(con); + return 0; + } + con->features = 0; INIT_LIST_HEAD(&con->head); /* Might need get this flag from vbios. */ From 59d9c0ab7169346d53b12db6a5e986a26a28c479 Mon Sep 17 00:00:00 2001 From: Hawking Zhang Date: Thu, 18 Jul 2019 12:52:56 +0800 Subject: [PATCH 063/823] drm/amdgpu: disable GFX RAS by default GFX RAS has not been stablized yet. disable GFX ras until it is fully funcitonal. Signed-off-by: Hawking Zhang Reviewed-by: Feifei Xu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index f2e8b4238efd..5376328d3fd0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -148,7 +148,7 @@ struct amdgpu_mgpu_info mgpu_info = { .mutex = __MUTEX_INITIALIZER(mgpu_info.mutex), }; int amdgpu_ras_enable = -1; -uint amdgpu_ras_mask = 0xffffffff; +uint amdgpu_ras_mask = 0xfffffffb; /** * DOC: vramlimit (int) From 29bd650809225f51ba475c556f43e53e392c44e3 Mon Sep 17 00:00:00 2001 From: Hawking Zhang Date: Thu, 18 Jul 2019 13:59:38 +0800 Subject: [PATCH 064/823] drm/amdgpu: only allow error injection to UMC IP block error injection to other IP blocks (except UMC) will be enabled until RAS feature stablize on those IP blocks Signed-off-by: Hawking Zhang Reviewed-by: Feifei Xu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 3a9ece450b31..fc346eb1aacd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -689,6 +689,12 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev, if (!obj) return -EINVAL; + if (block_info.block_id != TA_RAS_BLOCK__UMC) { + DRM_INFO("%s error injection is not supported yet\n", + ras_block_str(info->head.block)); + return -EINVAL; + } + ret = psp_ras_trigger_error(&adev->psp, &block_info); if (ret) DRM_ERROR("RAS ERROR: inject %s error failed ret %d\n", From 578a4daa1cd61f9783b5d0f566d6ec0a2cb9f6a3 Mon Sep 17 00:00:00 2001 From: Hawking Zhang Date: Thu, 18 Jul 2019 16:03:46 +0800 Subject: [PATCH 065/823] drm/amdgpu: drop ras self test this function is not needed any more. error injection is the only way to validate ras but it can't be executed in amdgpu_ras_init, where gpu is even not initialized Signed-off-by: Hawking Zhang Reviewed-by: Feifei Xu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index fc346eb1aacd..fac7aa2c244f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -136,11 +136,6 @@ static int amdgpu_ras_reserve_vram(struct amdgpu_device *adev, static int amdgpu_ras_release_vram(struct amdgpu_device *adev, struct amdgpu_bo **bo_ptr); -static void amdgpu_ras_self_test(struct amdgpu_device *adev) -{ - /* TODO */ -} - static ssize_t amdgpu_ras_debugfs_read(struct file *f, char __user *buf, size_t size, loff_t *pos) { @@ -1582,8 +1577,6 @@ int amdgpu_ras_init(struct amdgpu_device *adev) if (amdgpu_ras_fs_init(adev)) goto fs_out; - amdgpu_ras_self_test(adev); - DRM_INFO("RAS INFO: ras initialized successfully, " "hardware ability[%x] ras_mask[%x]\n", con->hw_supported, con->supported); From 1a195ed5f197fcfd1d99ceedd469857fcd7d8c4f Mon Sep 17 00:00:00 2001 From: Kevin Wang Date: Thu, 18 Jul 2019 15:46:55 +0800 Subject: [PATCH 066/823] drm/amd/powerplay: change sysfs pp_dpm_xxx format for navi10 v2: set average clock value on level 1 when current clock equal min or max clock (fine grained dpm support). the navi10 gfxclk (sclk) support fine grained DPM, so use level 1 to show current dpm freq in sysfs pp_dpm_xxx Signed-off-by: Kevin Wang Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/navi10_ppt.c | 47 +++++++++++++++++++--- 1 file changed, 41 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 2dae0ae0829e..8293b5216aad 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -626,11 +626,26 @@ static int navi10_get_current_clk_freq_by_table(struct smu_context *smu, return ret; } +static bool navi10_is_support_fine_grained_dpm(struct smu_context *smu, enum smu_clk_type clk_type) +{ + PPTable_t *pptable = smu->smu_table.driver_pptable; + DpmDescriptor_t *dpm_desc = NULL; + uint32_t clk_index = 0; + + clk_index = smu_clk_get_index(smu, clk_type); + dpm_desc = &pptable->DpmDescriptor[clk_index]; + + /* 0 - Fine grained DPM, 1 - Discrete DPM */ + return dpm_desc->SnapToDiscrete == 0 ? true : false; +} + static int navi10_print_clk_levels(struct smu_context *smu, enum smu_clk_type clk_type, char *buf) { int i, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0; + uint32_t freq_values[3] = {0}; + uint32_t mark_index = 0; switch (clk_type) { case SMU_GFXCLK: @@ -643,22 +658,42 @@ static int navi10_print_clk_levels(struct smu_context *smu, ret = smu_get_current_clk_freq(smu, clk_type, &cur_value); if (ret) return size; + /* 10KHz -> MHz */ cur_value = cur_value / 100; - size += sprintf(buf, "current clk: %uMhz\n", cur_value); - ret = smu_get_dpm_level_count(smu, clk_type, &count); if (ret) return size; - for (i = 0; i < count; i++) { - ret = smu_get_dpm_freq_by_index(smu, clk_type, i, &value); + if (!navi10_is_support_fine_grained_dpm(smu, clk_type)) { + for (i = 0; i < count; i++) { + ret = smu_get_dpm_freq_by_index(smu, clk_type, i, &value); + if (ret) + return size; + + size += sprintf(buf + size, "%d: %uMhz %s\n", i, value, + cur_value == value ? "*" : ""); + } + } else { + ret = smu_get_dpm_freq_by_index(smu, clk_type, 0, &freq_values[0]); + if (ret) + return size; + ret = smu_get_dpm_freq_by_index(smu, clk_type, count - 1, &freq_values[2]); if (ret) return size; - size += sprintf(buf + size, "%d: %uMhz %s\n", i, value, - cur_value == value ? "*" : ""); + freq_values[1] = cur_value; + mark_index = cur_value == freq_values[0] ? 0 : + cur_value == freq_values[2] ? 2 : 1; + if (mark_index != 1) + freq_values[1] = (freq_values[0] + freq_values[2]) / 2; + + for (i = 0; i < 3; i++) { + size += sprintf(buf + size, "%d: %uMhz %s\n", i, freq_values[i], + i == mark_index ? "*" : ""); + } + } break; default: From 3457b3055e43fbe457d9779c1362d56f19a888e7 Mon Sep 17 00:00:00 2001 From: Fuqian Huang Date: Thu, 11 Jul 2019 11:10:21 +0800 Subject: [PATCH 067/823] drm/ttm: use the same attributes when freeing d_page->vaddr MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In function __ttm_dma_alloc_page(), d_page->addr is allocated by dma_alloc_attrs() but freed with use dma_free_coherent() in __ttm_dma_free_page(). Use the correct dma_free_attrs() to free d_page->vaddr. Signed-off-by: Fuqian Huang Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/ttm/ttm_page_alloc_dma.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c index d594f7520b7b..7d78e6deac89 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c @@ -285,9 +285,13 @@ static int ttm_set_pages_caching(struct dma_pool *pool, static void __ttm_dma_free_page(struct dma_pool *pool, struct dma_page *d_page) { + unsigned long attrs = 0; dma_addr_t dma = d_page->dma; d_page->vaddr &= ~VADDR_FLAG_HUGE_POOL; - dma_free_coherent(pool->dev, pool->size, (void *)d_page->vaddr, dma); + if (pool->type & IS_HUGE) + attrs = DMA_ATTR_NO_WARN; + + dma_free_attrs(pool->dev, pool->size, (void *)d_page->vaddr, dma, attrs); kfree(d_page); d_page = NULL; From c6d5245d41de3a9786707b34189c41d6412fd0ba Mon Sep 17 00:00:00 2001 From: Leo Liu Date: Thu, 18 Jul 2019 11:38:46 -0400 Subject: [PATCH 068/823] drm/amdgpu: use VCN firmware offset for cache window Since we are using the signed FW now, and also using PSP firmware loading, but it's still potential to break driver when loading FW directly instead of PSP, so we should add offset. Signed-off-by: Leo Liu Acked-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index 988c0adaca91..1cfc2620b2dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -372,11 +372,8 @@ static void vcn_v2_0_mc_resume(struct amdgpu_device *adev) WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH, upper_32_bits(adev->vcn.gpu_addr)); offset = size; - /* No signed header for now from firmware WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0, AMDGPU_UVD_FIRMWARE_OFFSET >> 3); - */ - WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0, 0); } WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE0, size); From 61f33f6aa88388e36ff8ef27a40b4a173c1511d1 Mon Sep 17 00:00:00 2001 From: Jun Lei Date: Fri, 31 May 2019 15:14:13 -0400 Subject: [PATCH 069/823] drm/amd/display: initialize p_state to proper value [why] On some modes SMU will be in infinite loop state at boot, this is because driver assumes p_state_support is false, but this is the opposite of the assumed boot state by SMU. we optimize away notifying SMU about no pstate, and so they will get stuck [how] when we init clk manager, init pstate to true, so it matches driver load assumption Signed-off-by: Jun Lei Reviewed-by: Tony Cheng Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c index 08a774fc7b67..740f5db22bb5 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c @@ -301,6 +301,8 @@ void dcn2_update_clocks_fpga(struct clk_mgr *clk_mgr, void dcn2_init_clocks(struct clk_mgr *clk_mgr) { memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks)); + // Assumption is that boot state always supports pstate + clk_mgr->clks.p_state_change_support = true; } void dcn2_enable_pme_wa(struct clk_mgr *clk_mgr_base) From 0bd8ac7ed5f9a1a26c722c6cdbc4cb178d36cc03 Mon Sep 17 00:00:00 2001 From: Jun Lei Date: Mon, 3 Jun 2019 08:13:12 -0400 Subject: [PATCH 070/823] drm/amd/display: fix up HUBBUB hw programming for VM [why] Some values were not being converted or bit-shifted properly for HW registers, causing black screen [how] Fix up the values before programming HW Signed-off-by: Jun Lei Reviewed-by: Anthony Koo Acked-by: Leo Li Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c | 17 ++++++++--------- .../gpu/drm/amd/display/dc/inc/hw/dchubbub.h | 4 ++-- 2 files changed, 10 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c index ece6e136437b..c72a9ff57f15 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c @@ -366,25 +366,24 @@ int hubbub2_init_dchub_sys_ctx(struct hubbub *hubbub, struct dcn_vmid_page_table_config phys_config; REG_SET(DCN_VM_FB_LOCATION_BASE, 0, - FB_BASE, pa_config->system_aperture.fb_base); + FB_BASE, pa_config->system_aperture.fb_base >> 24); REG_SET(DCN_VM_FB_LOCATION_TOP, 0, - FB_TOP, pa_config->system_aperture.fb_top); + FB_TOP, pa_config->system_aperture.fb_top >> 24); REG_SET(DCN_VM_FB_OFFSET, 0, - FB_OFFSET, pa_config->system_aperture.fb_offset); + FB_OFFSET, pa_config->system_aperture.fb_offset >> 24); REG_SET(DCN_VM_AGP_BOT, 0, - AGP_BOT, pa_config->system_aperture.agp_bot); + AGP_BOT, pa_config->system_aperture.agp_bot >> 24); REG_SET(DCN_VM_AGP_TOP, 0, - AGP_TOP, pa_config->system_aperture.agp_top); + AGP_TOP, pa_config->system_aperture.agp_top >> 24); REG_SET(DCN_VM_AGP_BASE, 0, - AGP_BASE, pa_config->system_aperture.agp_base); + AGP_BASE, pa_config->system_aperture.agp_base >> 24); if (pa_config->gart_config.page_table_start_addr != pa_config->gart_config.page_table_end_addr) { - phys_config.depth = 1; - phys_config.block_size = 4096; phys_config.page_table_start_addr = pa_config->gart_config.page_table_start_addr >> 12; phys_config.page_table_end_addr = pa_config->gart_config.page_table_end_addr >> 12; phys_config.page_table_base_addr = pa_config->gart_config.page_table_base_addr; - + phys_config.depth = 0; + phys_config.block_size = 0; // Init VMID 0 based on PA config dcn20_vmid_setup(&hubbub1->vmid[0], &phys_config); } diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h index 959f5b654611..1ea505f7a05a 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h @@ -61,8 +61,8 @@ enum dcn_hubbub_page_table_depth { }; enum dcn_hubbub_page_table_block_size { - DCN_PAGE_TABLE_BLOCK_SIZE_4KB, - DCN_PAGE_TABLE_BLOCK_SIZE_64KB + DCN_PAGE_TABLE_BLOCK_SIZE_4KB = 0, + DCN_PAGE_TABLE_BLOCK_SIZE_64KB = 4 }; struct dcn_hubbub_phys_addr_config { From 5d109be38b23c8859ec78a2ed7c254ccd569719d Mon Sep 17 00:00:00 2001 From: Dmytro Laktyushkin Date: Thu, 30 May 2019 15:47:51 -0400 Subject: [PATCH 071/823] drm/amd/display: fix dsc disable A regression caused dsc to never get disabled in certain situations. Signed-off-by: Dmytro Laktyushkin Reviewed-by: Nikola Cornij Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 0b84a322b8a2..94f2f9fc6956 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1740,8 +1740,11 @@ static void dcn20_reset_back_end_for_pipe( else if (pipe_ctx->stream_res.audio) { dc->hwss.disable_audio_stream(pipe_ctx, FREE_ACQUIRED_RESOURCE); } - } +#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT + else if (pipe_ctx->stream_res.dsc) + dp_set_dsc_enable(pipe_ctx, false); +#endif /* by upper caller loop, parent pipe: pipe0, will be reset last. * back end share by all pipes and will be disable only when disable From db31af12a5169f4ac26acec759c1d872eef26554 Mon Sep 17 00:00:00 2001 From: Jun Lei Date: Mon, 3 Jun 2019 11:37:44 -0400 Subject: [PATCH 072/823] drm/amd/display: cap DCFCLK hardmin to 507 for NV10 [why] Due to limitation in SMU/PPLIB, it is not possible to know Fmax @ Vmin for DCFCLK. This causes issues at high display configurations where extra headroom of DCFCLK can enable P-state switching [how] Use existing override logic. If override not defined, then force min = 507 Signed-off-by: Jun Lei Reviewed-by: Eric Yang Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index d200bc3cec71..b949e202d6cb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -2643,6 +2643,10 @@ static void update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_ if (dc->bb_overrides.min_dcfclk_mhz > 0) min_dcfclk = dc->bb_overrides.min_dcfclk_mhz; + else + // Accounting for SOC/DCF relationship, we can go as high as + // 506Mhz in Vmin. We need to code 507 since SMU will round down to 506. + min_dcfclk = 507; for (i = 0; i < num_states; i++) { int min_fclk_required_by_uclk; From 5b25e5f1a97284020abee7348427f89abdb674e8 Mon Sep 17 00:00:00 2001 From: Harmanprit Tatla Date: Tue, 4 Jun 2019 14:12:21 -0400 Subject: [PATCH 073/823] drm/amd/display: No audio endpoint for Dell MST display [Why] There are certain MST displays (i.e. Dell P2715Q) that although have the MST feature set to off may still report it is a branch device and a non-zero value for downstream port present. This can lead to us incorrectly classifying a dp dongle connection as being active and disabling the audio endpoint for the display. [How] Modified the placement and condition used to assign the is_branch_dev bit. Signed-off-by: Harmanprit Tatla Reviewed-by: Aric Cyr Acked-by: Anthony Koo Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 056be4c34a98..3e00c88bd2b6 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -2230,11 +2230,18 @@ static void get_active_converter_info( link->dpcd_caps.dongle_type = DISPLAY_DONGLE_NONE; ddc_service_set_dongle_type(link->ddc, link->dpcd_caps.dongle_type); + link->dpcd_caps.is_branch_dev = false; return; } /* DPCD 0x5 bit 0 = 1, it indicate it's branch device */ - link->dpcd_caps.is_branch_dev = ds_port.fields.PORT_PRESENT; + if (ds_port.fields.PORT_TYPE == DOWNSTREAM_DP) { + link->dpcd_caps.is_branch_dev = false; + } + + else { + link->dpcd_caps.is_branch_dev = ds_port.fields.PORT_PRESENT; + } switch (ds_port.fields.PORT_TYPE) { case DOWNSTREAM_VGA: From 90bbf6374b88bdc1411fd83b24d87513ba23d519 Mon Sep 17 00:00:00 2001 From: Dmytro Laktyushkin Date: Tue, 4 Jun 2019 14:48:33 -0400 Subject: [PATCH 074/823] drm/amd/display: Set default block_size, even in unexpected cases We're not expected to enter the default case, but not returning a default value here is incorrect. Signed-off-by: Dmytro Laktyushkin Reviewed-by: Eric Bernstein Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c | 1 + drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c index c72a9ff57f15..6e2dbd03f9bf 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c @@ -337,6 +337,7 @@ static enum dcn_hubbub_page_table_block_size page_table_block_size_to_hw(unsigne break; default: ASSERT(false); + block_size = page_table_block_size; break; } diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h index 1ea505f7a05a..9502478c4a1b 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h @@ -62,7 +62,7 @@ enum dcn_hubbub_page_table_depth { enum dcn_hubbub_page_table_block_size { DCN_PAGE_TABLE_BLOCK_SIZE_4KB = 0, - DCN_PAGE_TABLE_BLOCK_SIZE_64KB = 4 + DCN_PAGE_TABLE_BLOCK_SIZE_64KB = 4, }; struct dcn_hubbub_phys_addr_config { From 61011e63f87fe5dd0ebff787cd78df4d7d66aec5 Mon Sep 17 00:00:00 2001 From: Nikola Cornij Date: Wed, 5 Jun 2019 14:29:47 -0400 Subject: [PATCH 075/823] drm/amd/display: Set one 4:2:0-related PPS field as recommended by DSC spec [why] 'second_line_offset_adj' was mistakenly left at zero, even though DSC spec v1.2a recommends setting this field to 512 for 4:2:0. [how] Set 'second_line_offset_adj' to 512 for 4:2:0 and leave at zero otherwise Signed-off-by: Nikola Cornij Reviewed-by: Eric Bernstein Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dsc/drm_dsc_dc.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dsc/drm_dsc_dc.c b/drivers/gpu/drm/amd/display/dc/dsc/drm_dsc_dc.c index 67089765780b..340ef4d41ebd 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/drm_dsc_dc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/drm_dsc_dc.c @@ -377,6 +377,12 @@ int drm_dsc_compute_rc_parameters(struct drm_dsc_config *vdsc_cfg) vdsc_cfg->rc_bits = (hrd_delay * vdsc_cfg->bits_per_pixel) / 16; vdsc_cfg->initial_dec_delay = hrd_delay - vdsc_cfg->initial_xmit_delay; + /* As per DSC spec v1.2a recommendation: */ + if (vdsc_cfg->native_420) + vdsc_cfg->second_line_offset_adj = 512; + else + vdsc_cfg->second_line_offset_adj = 0; + return 0; } EXPORT_SYMBOL(drm_dsc_compute_rc_parameters); From 4a876eecf6a5bfbe05ca6358e1b6a484e27ce32f Mon Sep 17 00:00:00 2001 From: Jun Lei Date: Wed, 5 Jun 2019 10:53:40 -0400 Subject: [PATCH 076/823] drm/amd/display: swap system aperture high/low [why] Currently logical values are swapped in HW, causing system aperture to be undefined, so VA and PA cannot co-exist [how] program values correctly Signed-off-by: Jun Lei Reviewed-by: Yongqiang Sun Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 94f2f9fc6956..710727e5d0f8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1153,8 +1153,8 @@ void dcn20_enable_plane( apt.sys_default.quad_part = 0; - apt.sys_high.quad_part = dc->vm_pa_config.system_aperture.start_addr; - apt.sys_low.quad_part = dc->vm_pa_config.system_aperture.end_addr; + apt.sys_low.quad_part = dc->vm_pa_config.system_aperture.start_addr; + apt.sys_high.quad_part = dc->vm_pa_config.system_aperture.end_addr; // Program system aperture settings pipe_ctx->plane_res.hubp->funcs->hubp_set_vm_system_aperture_settings(pipe_ctx->plane_res.hubp, &apt); From 4fc1609bcd5475a9cef1caeb10a04106f4f85fac Mon Sep 17 00:00:00 2001 From: Samson Tam Date: Tue, 4 Jun 2019 15:52:59 -0400 Subject: [PATCH 077/823] drm/amd/display: skip retrain in dc_link_set_preferred_link_settings() if using passive dongle [Why] Fixes issue when we have a display connected using a passive dongle and then emulate over it using a DP connection at 1 x 1.62 Ghz. System hangs because register bus returns back 0xFFFFFFFF for all register reads after setting register DIG_BE_CNTL in dcn10_link_encoder_connect_dig_be_to_fe(). Hang occurs later when trying to do a register read. [How] At the start of the emulation, dc_link_set_preferred_link_settings() and dp_retrain_link_dp_test() is called, even though it is connected using a passive dongle. Add an extra condition in dp_retrain_link_dp_test() to check for link->dongle_max_pix_clk > 0. This is the only way we know if the connection is using passive dongle so we don't retrain DP. Signed-off-by: Samson Tam Reviewed-by: Jun Lei Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 8dbf759eba45..435d50356bad 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -2984,8 +2984,10 @@ void dc_link_set_preferred_link_settings(struct dc *dc, /* Retrain with preferred link settings only relevant for * DP signal type + * Check for non-DP signal or if passive dongle present */ - if (!dc_is_dp_signal(link->connector_signal)) + if (!dc_is_dp_signal(link->connector_signal) || + link->dongle_max_pix_clk > 0) return; for (i = 0; i < MAX_PIPES; i++) { From 492d9ec244923420af96db6b69ad7d575859aa92 Mon Sep 17 00:00:00 2001 From: Murton Liu Date: Mon, 10 Jun 2019 17:55:28 -0400 Subject: [PATCH 078/823] drm/amd/display: Clock does not lower in Updateplanes [why] We reset the optimized_required in atomic_plane_disable flag immediately after it is set in atomic_plane_disconnect, causing us to never have flag set during next flip in UpdatePlanes. [how] Optimize directly after each time plane is removed. Signed-off-by: Murton Liu Reviewed-by: Tony Cheng Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index e50a696fcb5d..0c4340404e24 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -2516,6 +2516,12 @@ static void dcn10_apply_ctx_for_surface( if (removed_pipe[i]) dcn10_disable_plane(dc, &dc->current_state->res_ctx.pipe_ctx[i]); + for (i = 0; i < dc->res_pool->pipe_count; i++) + if (removed_pipe[i]) { + dc->hwss.optimize_bandwidth(dc, context); + break; + } + if (dc->hwseq->wa.DEGVIDCN10_254) hubbub1_wm_change_req_wa(dc->res_pool->hubbub); } From 7f6964c5a05e6593bda3a4bcb5581d0b72fc71cb Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Wed, 5 Jun 2019 15:02:04 -0400 Subject: [PATCH 079/823] drm/amd/display: Copy max_clks_by_state after dce_clk_mgr_construct [Why] For DCE110, DCE112 and DCE120 the max_clks_by_state for the clk_mgr are copied from their respective table before the call to dce_clk_mgr_construct, but then dce_clk_mgr_construct overwrites these with the dce80_max_clks_by_state. [How] Copy these after we call dce_clk_mgr_construct so we're using the right tables. Signed-off-by: Nicholas Kazlauskas Reviewed-by: David Francis Acked-by: Leo Li Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c | 4 ++-- .../gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c | 4 ++-- .../gpu/drm/amd/display/dc/clk_mgr/dce120/dce120_clk_mgr.c | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c index c1a92c16535c..5cc3acccda2a 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c @@ -262,12 +262,12 @@ void dce110_clk_mgr_construct( struct dc_context *ctx, struct clk_mgr_internal *clk_mgr) { + dce_clk_mgr_construct(ctx, clk_mgr); + memcpy(clk_mgr->max_clks_by_state, dce110_max_clks_by_state, sizeof(dce110_max_clks_by_state)); - dce_clk_mgr_construct(ctx, clk_mgr); - clk_mgr->regs = &disp_clk_regs; clk_mgr->clk_mgr_shift = &disp_clk_shift; clk_mgr->clk_mgr_mask = &disp_clk_mask; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c index 778392c73187..7c746ef1e32e 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c @@ -226,12 +226,12 @@ void dce112_clk_mgr_construct( struct dc_context *ctx, struct clk_mgr_internal *clk_mgr) { + dce_clk_mgr_construct(ctx, clk_mgr); + memcpy(clk_mgr->max_clks_by_state, dce112_max_clks_by_state, sizeof(dce112_max_clks_by_state)); - dce_clk_mgr_construct(ctx, clk_mgr); - clk_mgr->regs = &disp_clk_regs; clk_mgr->clk_mgr_shift = &disp_clk_shift; clk_mgr->clk_mgr_mask = &disp_clk_mask; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce120/dce120_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce120/dce120_clk_mgr.c index 906310c3e2eb..5399b8cf6b75 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce120/dce120_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce120/dce120_clk_mgr.c @@ -127,12 +127,12 @@ static struct clk_mgr_funcs dce120_funcs = { void dce120_clk_mgr_construct(struct dc_context *ctx, struct clk_mgr_internal *clk_mgr) { + dce_clk_mgr_construct(ctx, clk_mgr); + memcpy(clk_mgr->max_clks_by_state, dce120_max_clks_by_state, sizeof(dce120_max_clks_by_state)); - dce_clk_mgr_construct(ctx, clk_mgr); - clk_mgr->base.dprefclk_khz = 600000; clk_mgr->base.funcs = &dce120_funcs; } From dd5d9348da02dd83dbb235e55aa0acb3f48ccc95 Mon Sep 17 00:00:00 2001 From: Wenjing Liu Date: Tue, 11 Jun 2019 18:18:36 -0400 Subject: [PATCH 080/823] drm/amd/display: wait for the whole frame after global unlock [why] The current code will not wait for the entire frame after global unlock. This causes dsc dynamic target bpp update corruption when there is a surface update immediately happens after this. [how] Wait for the entire whole frame after unlock before continuing the rest of stream and surface update. Signed-off-by: Wenjing Liu Reviewed-by: Jun Lei Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 710727e5d0f8..e5e78aa930a6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1242,6 +1242,8 @@ void dcn20_pipe_control_lock_global( CRTC_STATE_VACTIVE); pipe->stream_res.tg->funcs->wait_for_state(pipe->stream_res.tg, CRTC_STATE_VBLANK); + pipe->stream_res.tg->funcs->wait_for_state(pipe->stream_res.tg, + CRTC_STATE_VACTIVE); pipe->stream_res.tg->funcs->lock_doublebuffer_disable( pipe->stream_res.tg); } From ca6f188cdf80de09b92174cf5fb2716021264222 Mon Sep 17 00:00:00 2001 From: Julian Parkin Date: Thu, 13 Jun 2019 12:49:37 -0400 Subject: [PATCH 081/823] drm/amd/display: Poll for GPUVM context ready (v2) [Why] Hardware docs state that we must wait until the GPUVM context is ready after programming it. [How] Poll until the valid bit of PAGE_TABLE_BASE_ADDR_LO32 is set to 1 after programming it. v2: fix include for udelay (Alex) Signed-off-by: Julian Parkin Reviewed-by: Charlene Liu Acked-by: Leo Li Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/dcn20/dcn20_vmid.c | 37 +++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_vmid.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_vmid.c index 27679ef6ebe8..96c263223315 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_vmid.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_vmid.c @@ -23,6 +23,8 @@ * */ +#include + #include "dcn20_vmid.h" #include "reg_helper.h" @@ -36,6 +38,38 @@ #define FN(reg_name, field_name) \ vmid->shifts->field_name, vmid->masks->field_name +static void dcn20_wait_for_vmid_ready(struct dcn20_vmid *vmid) +{ + /* According the hardware spec, we need to poll for the lowest + * bit of PAGE_TABLE_BASE_ADDR_LO32 = 1 any time a GPUVM + * context is updated. We can't use REG_WAIT here since we + * don't have a seperate field to wait on. + * + * TODO: Confirm timeout / poll interval with hardware team + */ + + int max_times = 10000; + int delay_us = 5; + int i; + + for (i = 0; i < max_times; ++i) { + uint32_t entry_lo32; + + REG_GET(PAGE_TABLE_BASE_ADDR_LO32, + VM_CONTEXT0_PAGE_DIRECTORY_ENTRY_LO32, + &entry_lo32); + + if (entry_lo32 & 0x1) + return; + + udelay(delay_us); + } + + /* VM setup timed out */ + DC_LOG_WARNING("Timeout while waiting for GPUVM context update\n"); + ASSERT(0); +} + void dcn20_vmid_setup(struct dcn20_vmid *vmid, const struct dcn_vmid_page_table_config *config) { REG_SET(PAGE_TABLE_START_ADDR_HI32, 0, @@ -54,6 +88,9 @@ void dcn20_vmid_setup(struct dcn20_vmid *vmid, const struct dcn_vmid_page_table_ REG_SET(PAGE_TABLE_BASE_ADDR_HI32, 0, VM_CONTEXT0_PAGE_DIRECTORY_ENTRY_HI32, (config->page_table_base_addr >> 32) & 0xFFFFFFFF); + /* Note: per hardware spec PAGE_TABLE_BASE_ADDR_LO32 must be programmed last in sequence */ REG_SET(PAGE_TABLE_BASE_ADDR_LO32, 0, VM_CONTEXT0_PAGE_DIRECTORY_ENTRY_LO32, config->page_table_base_addr & 0xFFFFFFFF); + + dcn20_wait_for_vmid_ready(vmid); } From c7990daebe71d11a9e360b5c3b0ecd1846a3a4bb Mon Sep 17 00:00:00 2001 From: SivapiriyanKumarasamy Date: Fri, 14 Jun 2019 15:04:00 -0400 Subject: [PATCH 082/823] drm/amd/display: Wait for backlight programming completion in set backlight level [WHY] Currently we don't wait for blacklight programming completion in DMCU when setting backlight level. Some sequences such as PSR static screen event trigger reprogramming requires it to be complete. [How] Add generic wait for dmcu command completion in set backlight level. Signed-off-by: SivapiriyanKumarasamy Reviewed-by: Anthony Koo Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dce/dce_abm.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c index f8903bcabe49..58bd131d5b48 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c @@ -239,6 +239,10 @@ static void dmcu_set_backlight_level( s2 |= (backlight_8_bit << ATOM_S2_CURRENT_BL_LEVEL_SHIFT); REG_WRITE(BIOS_SCRATCH_2, s2); + + /* waitDMCUReadyForCmd */ + REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, + 0, 1, 80000); } static void dce_abm_init(struct abm *abm) From 288af96df16b629552c5bcc9ec0f0191c6198a72 Mon Sep 17 00:00:00 2001 From: Ilya Bakoulin Date: Wed, 29 May 2019 18:52:17 -0400 Subject: [PATCH 083/823] drm/amd/display: Check for valid stream_encode Before accessing it's vtable, check that stream_encoder is non-null. Signed-off-by: Ilya Bakoulin Reviewed-by: Eric Bernstein Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_stream.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index af7f8be230f7..352862370390 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -612,7 +612,8 @@ bool dc_stream_set_dynamic_metadata(struct dc *dc, pipe_ctx->stream->dmdata_address = attr->address; - if (pipe_ctx->stream_res.stream_enc->funcs->set_dynamic_metadata != NULL) { + if (pipe_ctx->stream_res.stream_enc && + pipe_ctx->stream_res.stream_enc->funcs->set_dynamic_metadata != NULL) { if (pipe_ctx->stream->dmdata_address.quad_part != 0) { /* if using dynamic meta, don't set up generic infopackets */ pipe_ctx->stream_res.encoder_info_frame.hdrsmd.valid = false; From 12d0e503dd9e0576487b2f20577717b2a36fe0c5 Mon Sep 17 00:00:00 2001 From: Derek Lai Date: Tue, 18 Jun 2019 14:55:57 +0800 Subject: [PATCH 084/823] drm/amd/display: Read max down spread [Why] When launch D10.2, driver will write DPCD 0x107 with 0x00 [How] Read MAX_DOWNSPREAD (0x0003h) then keep in current link settings Signed-off-by: Derek Lai Reviewed-by: Tony Cheng Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 435d50356bad..652960c5548a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -532,6 +532,7 @@ static void read_edp_current_link_settings_on_detect(struct dc_link *link) uint32_t read_dpcd_retry_cnt = 10; enum dc_status status = DC_ERROR_UNEXPECTED; int i; + union max_down_spread max_down_spread = { {0} }; // Read DPCD 00101h to find out the number of lanes currently set for (i = 0; i < read_dpcd_retry_cnt; i++) { @@ -576,6 +577,12 @@ static void read_edp_current_link_settings_on_detect(struct dc_link *link) link->cur_link_settings.link_rate = link_bw_set; link->cur_link_settings.use_link_rate_set = false; } + // Read DPCD 00003h to find the max down spread. + core_link_read_dpcd(link, DP_MAX_DOWNSPREAD, + &max_down_spread.raw, sizeof(max_down_spread)); + link->cur_link_settings.link_spread = + max_down_spread.bits.MAX_DOWN_SPREAD ? + LINK_SPREAD_05_DOWNSPREAD_30KHZ : LINK_SPREAD_DISABLED; } static bool detect_dp( From 19f876967a98db63fbfca7e0d9f55099f52189e0 Mon Sep 17 00:00:00 2001 From: Alvin Lee Date: Thu, 20 Jun 2019 13:03:25 -0400 Subject: [PATCH 085/823] drm/amd/display: Disable Audio on reinitialize hardware [Why] When we recover from hang, we do not want to skip the audio enable call. [How] Disable audio in dc_reinitialize_hardware Signed-off-by: Alvin Lee Reviewed-by: Jun Lei Acked-by: Leo Li Signed-off-by: Alex Deucher --- .../display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c | 1 + .../display/dc/dce110/dce110_hw_sequencer.c | 20 +++++++++++++++---- 2 files changed, 17 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c index 740f5db22bb5..50bfb5921de0 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c @@ -333,6 +333,7 @@ void dcn20_clk_mgr_construct( struct dccg *dccg) { clk_mgr->base.ctx = ctx; + clk_mgr->pp_smu = pp_smu; clk_mgr->base.funcs = &dcn2_funcs; clk_mgr->regs = &clk_mgr_regs; clk_mgr->clk_mgr_shift = &clk_mgr_shift; diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 858a58856ebd..8005989c1263 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -965,11 +965,17 @@ void hwss_edp_backlight_control( void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx) { /* notify audio driver for audio modes of monitor */ - struct dc *core_dc = pipe_ctx->stream->ctx->dc; + struct dc *core_dc; struct pp_smu_funcs *pp_smu = NULL; - struct clk_mgr *clk_mgr = core_dc->clk_mgr; + struct clk_mgr *clk_mgr; unsigned int i, num_audio = 1; + if (!pipe_ctx->stream) + return; + + core_dc = pipe_ctx->stream->ctx->dc; + clk_mgr = core_dc->clk_mgr; + if (pipe_ctx->stream_res.audio && pipe_ctx->stream_res.audio->enabled == true) return; @@ -999,9 +1005,15 @@ void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx) void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx, int option) { - struct dc *dc = pipe_ctx->stream->ctx->dc; + struct dc *dc; struct pp_smu_funcs *pp_smu = NULL; - struct clk_mgr *clk_mgr = dc->clk_mgr; + struct clk_mgr *clk_mgr; + + if (!pipe_ctx || !pipe_ctx->stream) + return; + + dc = pipe_ctx->stream->ctx->dc; + clk_mgr = dc->clk_mgr; if (pipe_ctx->stream_res.audio && pipe_ctx->stream_res.audio->enabled == false) return; From 1ca068ed34d6b39d336c1b0d618ed73ba8f04548 Mon Sep 17 00:00:00 2001 From: Zi Yu Liao Date: Thu, 20 Jun 2019 10:55:26 -0400 Subject: [PATCH 086/823] drm/amd/display: fix DMCU hang when going into Modern Standby [why] When the system is going into suspend, set_backlight gets called after the eDP got blanked. Since smooth brightness is enabled, the driver will make a call into the DMCU to ramp the brightness. The DMCU would try to enable ABM to do so. But since the display is blanked, this ends up causing ABM1_ACE_DBUF_REG_UPDATE_PENDING to get stuck at 1, which results in a dead lock in the DMCU firmware. [how] Disable brightness ramping when the eDP display is blanked. Signed-off-by: Zi Yu Liao Reviewed-by: Eric Yang Acked-by: Anthony Koo Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 652960c5548a..f9bed7c65b43 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -2336,7 +2336,7 @@ bool dc_link_set_backlight_level(const struct dc_link *link, if (core_dc->current_state->res_ctx.pipe_ctx[i].stream) { if (core_dc->current_state->res_ctx. pipe_ctx[i].stream->link - == link) + == link) { /* DMCU -1 for all controller id values, * therefore +1 here */ @@ -2344,6 +2344,13 @@ bool dc_link_set_backlight_level(const struct dc_link *link, core_dc->current_state-> res_ctx.pipe_ctx[i].stream_res.tg->inst + 1; + + /* Disable brightness ramping when the display is blanked + * as it can hang the DMCU + */ + if (core_dc->current_state->res_ctx.pipe_ctx[i].plane_state == NULL) + frame_ramp = 0; + } } } abm->funcs->set_backlight_level_pwm( From 74eda776d7a4e69ec7aa1ce30a87636f14220fbb Mon Sep 17 00:00:00 2001 From: Tai Man Date: Fri, 7 Jun 2019 17:32:27 -0400 Subject: [PATCH 087/823] drm/amd/display: use encoder's engine id to find matched free audio device [Why] On some platforms, the encoder id 3 is not populated. So the encoders are not stored in right order as index (id: 0, 1, 2, 4, 5) at pool. This would cause encoders id 4 & id 5 to fail when finding corresponding audio device, defaulting to the first available audio device. As result, we cannot stream audio into two DP ports with encoders id 4 & id 5. [How] It need to create enough audio device objects (0 - 5) to perform matching. Then use encoder engine id to find matched audio device. Signed-off-by: Tai Man Reviewed-by: Charlene Liu Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 51a78283a86d..a0e29c37ab69 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -258,7 +258,7 @@ bool resource_construct( * PORT_CONNECTIVITY == 1 (as instructed by HW team). */ update_num_audio(&straps, &num_audio, &pool->audio_support); - for (i = 0; i < pool->pipe_count && i < num_audio; i++) { + for (i = 0; i < caps->num_audio; i++) { struct audio *aud = create_funcs->create_audio(ctx, i); if (aud == NULL) { @@ -1669,6 +1669,12 @@ static struct audio *find_first_free_audio( return pool->audios[i]; } } + + /* use engine id to find free audio */ + if ((id < pool->audio_count) && (res_ctx->is_audio_acquired[id] == false)) { + return pool->audios[id]; + } + /*not found the matching one, first come first serve*/ for (i = 0; i < pool->audio_count; i++) { if (res_ctx->is_audio_acquired[i] == false) { From 09fc26c1718fe7a552866d4eda84e2cc5f9c9c78 Mon Sep 17 00:00:00 2001 From: Fatemeh Darbehani Date: Fri, 21 Jun 2019 17:44:50 -0400 Subject: [PATCH 088/823] drm/amd/display: Change min_h_sync_width from 8 to 4 [Why] Some display's hsync width is lower than the minimum dcn20 is set to support right now. This will cause optc1_validate_timing to fail which eventually will result in wrong set mode. This was set to 8 as per HW team's request for no valid reason. [How] Changing min_h_sync_width to 4 will let us validate timing for preffered mode and light up the headset. This change was made to Vega 10 before for a similar issue. Signed-off-by: Fatemeh Darbehani Reviewed-by: Joshua Aberback Acked-by: Aric Cyr Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c index 26a66ccf6e72..1ae973962d53 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c @@ -535,7 +535,7 @@ void dcn20_timing_generator_init(struct optc *optc1) optc1->min_h_blank = 32; optc1->min_v_blank = 3; optc1->min_v_blank_interlace = 5; - optc1->min_h_sync_width = 8; + optc1->min_h_sync_width = 4;// Minimum HSYNC = 8 pixels asked By HW in the first place for no actual reason. Oculus Rift S will not light up with 8 as it's hsyncWidth is 6. Changing it to 4 to fix that issue. optc1->min_v_sync_width = 1; optc1->comb_opp_id = 0xf; } From 39fee5f60ce069cfba55fc3a8ba55faacae330b9 Mon Sep 17 00:00:00 2001 From: Alvin Lee Date: Mon, 24 Jun 2019 09:49:44 -0400 Subject: [PATCH 089/823] drm/amd/display: Wait for flip to complete [why] In pipe split issue occurs when we program immediate flip while vsync flip is pending [how] Don't program immediate flip until flip is no longer pending Signed-off-by: Alvin Lee Reviewed-by: Jaehyun Chung Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index e5e78aa930a6..d810c8940129 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1265,6 +1265,17 @@ void dcn20_pipe_control_lock( if (pipe->plane_state != NULL) flip_immediate = pipe->plane_state->flip_immediate; + if (flip_immediate && lock) { + while (pipe->plane_res.hubp->funcs->hubp_is_flip_pending(pipe->plane_res.hubp)) { + udelay(1); + } + + if (pipe->bottom_pipe != NULL) + while (pipe->bottom_pipe->plane_res.hubp->funcs->hubp_is_flip_pending(pipe->bottom_pipe->plane_res.hubp)) { + udelay(1); + } + } + /* In flip immediate and pipe splitting case, we need to use GSL * for synchronization. Only do setup on locking and on flip type change. */ From feb7eb522e0a7a22c1e60d386bd3c3bfa1d5e4f7 Mon Sep 17 00:00:00 2001 From: Eric Yang Date: Mon, 24 Jun 2019 18:18:58 -0400 Subject: [PATCH 090/823] drm/amd/display: put back front end initialization sequence [Why] Seamless boot optimization removed proper front end power off sequence. In driver disable enable case, this causes driver to power gate hubp and dpp while there is still memory fetching going on, this can cause invalid memory requests to be generated which will hang data fabric. [How] Put back proper front end power off sequence Signed-off-by: Eric Yang Reviewed-by: Anthony Koo Acked-by: Leo Li Acked-by: Tony Cheng Signed-off-by: Alex Deucher --- .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 0c4340404e24..2118ea21d7e9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1195,16 +1195,7 @@ static void dcn10_init_hw(struct dc *dc) * everything down. */ if (dcb->funcs->is_accelerated_mode(dcb) || dc->config.power_down_display_on_boot) { - for (i = 0; i < dc->res_pool->pipe_count; i++) { - struct hubp *hubp = dc->res_pool->hubps[i]; - struct dpp *dpp = dc->res_pool->dpps[i]; - - hubp->funcs->hubp_init(hubp); - dc->res_pool->opps[i]->mpc_tree_params.opp_id = dc->res_pool->opps[i]->inst; - plane_atomic_power_down(dc, dpp, hubp); - } - - apply_DEGVIDCN10_253_wa(dc); + dc->hwss.init_pipes(dc, dc->current_state); } for (i = 0; i < dc->res_pool->audio_count; i++) { @@ -1375,10 +1366,6 @@ static bool dcn10_set_input_transfer_func(struct pipe_ctx *pipe_ctx, return result; } - - - - static bool dcn10_set_output_transfer_func(struct pipe_ctx *pipe_ctx, const struct dc_stream_state *stream) From 67fd6c0d2de8e51e84ff3fa6e68bbd524f823e49 Mon Sep 17 00:00:00 2001 From: Derek Lai Date: Tue, 2 Jul 2019 17:50:41 +0800 Subject: [PATCH 091/823] drm/amd/display: allocate 4 ddc engines for RV2 [Why] Driver will create 0, 1, and 2 ddc engines for RV2, but some platforms used 0, 1, and 3. [How] Still allocate 4 ddc engines for RV2. Signed-off-by: Derek Lai Reviewed-by: Aric Cyr Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 1a20461c2937..a12530a3ab9c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -508,7 +508,7 @@ static const struct resource_caps rv2_res_cap = { .num_audio = 3, .num_stream_encoder = 3, .num_pll = 3, - .num_ddc = 3, + .num_ddc = 4, }; static const struct dc_plane_cap plane_cap = { From 0905f32977268149f06e3ce6ea4bd6d374dd891f Mon Sep 17 00:00:00 2001 From: Julian Parkin Date: Tue, 25 Jun 2019 14:55:53 -0400 Subject: [PATCH 092/823] drm/amd/display: Fix dc_create failure handling and 666 color depths [Why] It is possible (but very unlikely) that constructing dc fails before current_state is created. We support 666 color depth in some scenarios, but this isn't handled in get_norm_pix_clk. It uses exactly the same pixel clock as the 888 case. [How] Check for non null current_state before destructing. Add case for 666 color depth to get_norm_pix_clk to avoid assertion. Signed-off-by: Julian Parkin Reviewed-by: Charlene Liu Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc.c | 6 ++++-- drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 1 + 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 4ef4dc63e221..fa20201eef3a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -502,8 +502,10 @@ void dc_stream_set_static_screen_events(struct dc *dc, static void destruct(struct dc *dc) { - dc_release_state(dc->current_state); - dc->current_state = NULL; + if (dc->current_state) { + dc_release_state(dc->current_state); + dc->current_state = NULL; + } destroy_links(dc); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index a0e29c37ab69..87f97b3a4106 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1839,6 +1839,7 @@ static int get_norm_pix_clk(const struct dc_crtc_timing *timing) pix_clk /= 2; if (timing->pixel_encoding != PIXEL_ENCODING_YCBCR422) { switch (timing->display_color_depth) { + case COLOR_DEPTH_666: case COLOR_DEPTH_888: normalized_pix_clk = pix_clk; break; From 6ac25e6d5b2fbf251e9fa2f4131d42c815b43867 Mon Sep 17 00:00:00 2001 From: Alvin Lee Date: Thu, 4 Jul 2019 15:17:42 -0400 Subject: [PATCH 093/823] drm/amd/display: Only enable audio if speaker allocation exists [Why] In dm_helpers_parse_edid_caps, there is a corner case where no speakers can be allocated even though the audio mode count is greater than 0. Enabling audio when no speaker allocations exists can cause issues in the video stream. [How] Add a check to not enable audio unless one or more speaker allocations exist (since doing this can cause issues in the video stream). Signed-off-by: Alvin Lee Reviewed-by: Jun Lei Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 87f97b3a4106..2ceaab4fb5de 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1986,7 +1986,7 @@ enum dc_status resource_map_pool_resources( /* TODO: Add check if ASIC support and EDID audio */ if (!stream->converter_disable_audio && dc_is_audio_capable_signal(pipe_ctx->stream->signal) && - stream->audio_info.mode_count) { + stream->audio_info.mode_count && stream->audio_info.flags.all) { pipe_ctx->stream_res.audio = find_first_free_audio( &context->res_ctx, pool, pipe_ctx->stream_res.stream_enc->id); From 58caae27df41d2ef3b1ae3bd06284da5b85ac288 Mon Sep 17 00:00:00 2001 From: Zhan Liu Date: Tue, 2 Jul 2019 15:17:07 -0400 Subject: [PATCH 094/823] drm/amd/display: drop ASSERT() if eDP panel is not connected [Why] For boards that support eDP but do not have a physical eDP display connected an ASSERT will be thrown. This is not a critical failure and shouldn't be treated as such. [How] Drop the assertion. Signed-off-by: Zhan Liu Reviewed-by: Nicholas Kazlauskas Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index f9bed7c65b43..909b8f03346e 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -554,8 +554,6 @@ static void read_edp_current_link_settings_on_detect(struct dc_link *link) msleep(8); } - ASSERT(status == DC_OK); - // Read DPCD 00100h to find if standard link rates are set core_link_read_dpcd(link, DP_LINK_BW_SET, &link_bw_set, sizeof(link_bw_set)); From 7352193a33dfc9b69ba3bf6a8caea925b96243b1 Mon Sep 17 00:00:00 2001 From: Tai Man Date: Fri, 28 Jun 2019 11:40:38 -0400 Subject: [PATCH 095/823] drm/amd/display: Increase size of audios array [Why] The audios array defined in "struct resource_pool" is only 6 (MAX_PIPES) but the max number of audio devices (num_audio) is 7. In some projects, it will run out of audios array. [How] Incraese the audios array size to 7. Signed-off-by: Tai Man Reviewed-by: Joshua Aberback Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/inc/core_types.h | 2 +- drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index c89393c19232..a148ffde8b12 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -212,7 +212,7 @@ struct resource_pool { struct clock_source *clock_sources[MAX_CLOCK_SOURCES]; unsigned int clk_src_count; - struct audio *audios[MAX_PIPES]; + struct audio *audios[MAX_AUDIOS]; unsigned int audio_count; struct audio_support audio_support; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h index 8759ec03aede..f82365e2d03c 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h @@ -34,6 +34,7 @@ * Data types shared between different Virtual HW blocks ******************************************************************************/ +#define MAX_AUDIOS 7 #define MAX_PIPES 6 #if defined(CONFIG_DRM_AMD_DC_DCN2_0) #define MAX_DWB_PIPES 1 From b791f9dc2de4f9e66aae28451d1284d054542614 Mon Sep 17 00:00:00 2001 From: Eric Yang Date: Sat, 29 Jun 2019 14:38:04 -0400 Subject: [PATCH 096/823] drm/amd/display: do not read link setting if edp not connected [Why] Previously assume eDP sink present if connector present. Do not need to enforce this restriction. Fix issue where driver attempt to read link setting even though no edp connected. {How] Only read link setting after reading connection status. Signed-off-by: Eric Yang Reviewed-by: Yongqiang Sun Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 909b8f03346e..355b4ba12796 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -722,13 +722,6 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason) return false; } - if (link->connector_signal == SIGNAL_TYPE_EDP) { - /* On detect, we want to make sure current link settings are - * up to date, especially if link was powered on by GOP. - */ - read_edp_current_link_settings_on_detect(link); - } - prev_sink = link->local_sink; if (prev_sink != NULL) { dc_sink_retain(prev_sink); @@ -770,6 +763,7 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason) } case SIGNAL_TYPE_EDP: { + read_edp_current_link_settings_on_detect(link); detect_edp_sink_caps(link); sink_caps.transaction_type = DDC_TRANSACTION_TYPE_I2C_OVER_AUX; From b70666934b41c081489d5ff3c5bf017796545d35 Mon Sep 17 00:00:00 2001 From: Dale Zhao Date: Wed, 10 Jul 2019 17:36:53 +0800 Subject: [PATCH 097/823] drm/amd/display: handle active dongle port type is DP++ or DP case [Why]: Some active dongles have DP++ port and DP port at the same time. Current code doesn't cover DP++ case and processes as default DVI case, in which audio is disabled. Because of dual mode, DP case is also treat as DVI case for the other port. [How]: According DP 1.4 spec, add DP++ procedure similar with HDMI case. Also add None dongle type for DP case. Signed-off-by: Dale Zhao Reviewed-by: Wenjing Liu Acked-by: Leo Li Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/core/dc_link_dp.c | 30 ++++++++++++------- .../gpu/drm/amd/display/include/dpcd_defs.h | 2 +- 2 files changed, 21 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 3e00c88bd2b6..2c7aaed907b9 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -2247,8 +2247,8 @@ static void get_active_converter_info( case DOWNSTREAM_VGA: link->dpcd_caps.dongle_type = DISPLAY_DONGLE_DP_VGA_CONVERTER; break; - case DOWNSTREAM_DVI_HDMI: - /* At this point we don't know is it DVI or HDMI, + case DOWNSTREAM_DVI_HDMI_DP_PLUS_PLUS: + /* At this point we don't know is it DVI or HDMI or DP++, * assume DVI.*/ link->dpcd_caps.dongle_type = DISPLAY_DONGLE_DP_DVI_CONVERTER; break; @@ -2265,6 +2265,10 @@ static void get_active_converter_info( det_caps, sizeof(det_caps)); switch (port_caps->bits.DWN_STRM_PORTX_TYPE) { + /*Handle DP case as DONGLE_NONE*/ + case DOWN_STREAM_DETAILED_DP: + link->dpcd_caps.dongle_type = DISPLAY_DONGLE_NONE; + break; case DOWN_STREAM_DETAILED_VGA: link->dpcd_caps.dongle_type = DISPLAY_DONGLE_DP_VGA_CONVERTER; @@ -2274,6 +2278,8 @@ static void get_active_converter_info( DISPLAY_DONGLE_DP_DVI_CONVERTER; break; case DOWN_STREAM_DETAILED_HDMI: + case DOWN_STREAM_DETAILED_DP_PLUS_PLUS: + /*Handle DP++ active converter case, process DP++ case as HDMI case according DP1.4 spec*/ link->dpcd_caps.dongle_type = DISPLAY_DONGLE_DP_HDMI_CONVERTER; @@ -2289,14 +2295,18 @@ static void get_active_converter_info( link->dpcd_caps.dongle_caps.is_dp_hdmi_s3d_converter = hdmi_caps.bits.FRAME_SEQ_TO_FRAME_PACK; - link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr422_pass_through = - hdmi_caps.bits.YCrCr422_PASS_THROUGH; - link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr420_pass_through = - hdmi_caps.bits.YCrCr420_PASS_THROUGH; - link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr422_converter = - hdmi_caps.bits.YCrCr422_CONVERSION; - link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr420_converter = - hdmi_caps.bits.YCrCr420_CONVERSION; + /*YCBCR capability only for HDMI case*/ + if (port_caps->bits.DWN_STRM_PORTX_TYPE + == DOWN_STREAM_DETAILED_HDMI) { + link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr422_pass_through = + hdmi_caps.bits.YCrCr422_PASS_THROUGH; + link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr420_pass_through = + hdmi_caps.bits.YCrCr420_PASS_THROUGH; + link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr422_converter = + hdmi_caps.bits.YCrCr422_CONVERSION; + link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr420_converter = + hdmi_caps.bits.YCrCr420_CONVERSION; + } link->dpcd_caps.dongle_caps.dp_hdmi_max_bpc = translate_dpcd_max_bpc( diff --git a/drivers/gpu/drm/amd/display/include/dpcd_defs.h b/drivers/gpu/drm/amd/display/include/dpcd_defs.h index 1c66166d0a94..2c90d1b46c8b 100644 --- a/drivers/gpu/drm/amd/display/include/dpcd_defs.h +++ b/drivers/gpu/drm/amd/display/include/dpcd_defs.h @@ -43,7 +43,7 @@ enum dpcd_revision { enum dpcd_downstream_port_type { DOWNSTREAM_DP = 0, DOWNSTREAM_VGA, - DOWNSTREAM_DVI_HDMI, + DOWNSTREAM_DVI_HDMI_DP_PLUS_PLUS,/* DVI, HDMI, DP++ */ DOWNSTREAM_NONDDC /* has no EDID (TV,CV) */ }; From a07e3324538a989b7cdbf2c679be6a7f9df2544f Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 13 May 2019 13:47:25 +0200 Subject: [PATCH 098/823] MIPS: kernel: only use i8253 clocksource with periodic clockevent i8253 clocksource needs a free running timer. This could only be used, if i8253 clockevent is set up as periodic. Signed-off-by: Thomas Bogendoerfer Signed-off-by: Paul Burton Cc: Ralf Baechle Cc: James Hogan Cc: linux-mips@vger.kernel.org Cc: linux-kernel@vger.kernel.org --- arch/mips/kernel/i8253.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c index 5f209f111e59..df7ddd246eaa 100644 --- a/arch/mips/kernel/i8253.c +++ b/arch/mips/kernel/i8253.c @@ -32,7 +32,8 @@ void __init setup_pit_timer(void) static int __init init_pit_clocksource(void) { - if (num_possible_cpus() > 1) /* PIT does not scale! */ + if (num_possible_cpus() > 1 || /* PIT does not scale! */ + !clockevent_state_periodic(&i8253_clockevent)) return 0; return clocksource_i8253_init(); From b8bea8a5e5d942e62203416ab41edecaed4fda02 Mon Sep 17 00:00:00 2001 From: Vladimir Kondratiev Date: Tue, 16 Jul 2019 10:36:56 +0300 Subject: [PATCH 099/823] mips: fix cacheinfo Because CONFIG_OF defined for MIPS, cacheinfo attempts to fill information from DT, ignoring data filled by architecture routine. This leads to error reported cacheinfo: Unable to detect cache hierarchy for CPU 0 Way to fix this provided in commit fac51482577d ("drivers: base: cacheinfo: fix x86 with CONFIG_OF enabled") Utilize same mechanism to report that cacheinfo set by architecture specific function Signed-off-by: Vladimir Kondratiev Signed-off-by: Paul Burton Cc: Ralf Baechle Cc: James Hogan Cc: linux-mips@vger.kernel.org Cc: linux-kernel@vger.kernel.org --- arch/mips/kernel/cacheinfo.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/mips/kernel/cacheinfo.c b/arch/mips/kernel/cacheinfo.c index 97d5239ca47b..428ef2189203 100644 --- a/arch/mips/kernel/cacheinfo.c +++ b/arch/mips/kernel/cacheinfo.c @@ -80,6 +80,8 @@ static int __populate_cache_leaves(unsigned int cpu) if (c->tcache.waysize) populate_cache(tcache, this_leaf, 3, CACHE_TYPE_UNIFIED); + this_cpu_ci->cpu_map_populated = true; + return 0; } From 5bbe54346b539b5938b65d542b6ff5e956c3c08d Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Wed, 17 Jul 2019 19:49:10 +0000 Subject: [PATCH 100/823] MIPS: Annotate fall-through in kvm/emulate.c kvm_compute_return_epc contains a switch statement with an intentional fall-through from a case handling jal (jump and link) instructions to one handling j (jump) instructions. With -Wimplicit-fallthrough this triggers a compile error (due to -Werror being enabled for arch/mips). This can be reproduced using malta_kvm_defconfig. Fix this by annotating the intentional fall-through. Signed-off-by: Paul Burton Cc: linux-mips@vger.kernel.org --- arch/mips/kvm/emulate.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index e5de6bac8197..754094b40a75 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -140,6 +140,7 @@ static int kvm_compute_return_epc(struct kvm_vcpu *vcpu, unsigned long instpc, /* These are unconditional and in j_format. */ case jal_op: arch->gprs[31] = instpc + 8; + /* fall through */ case j_op: epc += 4; epc >>= 28; From 2a15d6481741a418837a22df3a440d5bd8b9c412 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Wed, 17 Jul 2019 20:12:23 +0000 Subject: [PATCH 101/823] MIPS: Annotate fall-through in Cavium Octeon code There's an intentional switch case fall-through in Cavium Octeon USB code, which triggers compile errors with -Wimplicit-fallthrough due to -Werror being enabled for arch/mips. This can be encountered when building cavium_octeon_defconfig. Fix the build issue by annotating the intentional fall-through. Signed-off-by: Paul Burton Cc: linux-mips@vger.kernel.org --- arch/mips/cavium-octeon/octeon-usb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/cavium-octeon/octeon-usb.c b/arch/mips/cavium-octeon/octeon-usb.c index 1f730ded5224..cc88a08bc1f7 100644 --- a/arch/mips/cavium-octeon/octeon-usb.c +++ b/arch/mips/cavium-octeon/octeon-usb.c @@ -398,6 +398,7 @@ static int dwc3_octeon_clocks_start(struct device *dev, u64 base) default: dev_err(dev, "Invalid ref_clk %u, using 100000000 instead\n", clock_rate); + /* fall through */ case 100000000: mpll_mul = 0x19; if (ref_clk_sel < 2) From 00289cd87676e14913d2d8492d1ce05c4baafdae Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 17 Jul 2019 18:07:53 -0700 Subject: [PATCH 102/823] drivers/base: Introduce kill_device() The libnvdimm subsystem arranges for devices to be destroyed as a result of a sysfs operation. Since device_unregister() cannot be called from an actively running sysfs attribute of the same device libnvdimm arranges for device_unregister() to be performed in an out-of-line async context. The driver core maintains a 'dead' state for coordinating its own racing async registration / de-registration requests. Rather than add local 'dead' state tracking infrastructure to libnvdimm device objects, export the existing state tracking via a new kill_device() helper. The kill_device() helper simply marks the device as dead, i.e. that it is on its way to device_del(), or returns that the device was already dead. This can be used in advance of calling device_unregister() for subsystems like libnvdimm that might need to handle multiple user threads racing to delete a device. This refactoring does not change any behavior, but it is a pre-requisite for follow-on fixes and therefore marked for -stable. Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Fixes: 4d88a97aa9e8 ("libnvdimm, nvdimm: dimm driver and base libnvdimm device-driver...") Cc: Tested-by: Jane Chu Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/156341207332.292348.14959761496009347574.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/base/core.c | 27 +++++++++++++++++++-------- include/linux/device.h | 1 + 2 files changed, 20 insertions(+), 8 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index fd7511e04e62..eaf3aa0cb803 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2211,6 +2211,24 @@ void put_device(struct device *dev) } EXPORT_SYMBOL_GPL(put_device); +bool kill_device(struct device *dev) +{ + /* + * Require the device lock and set the "dead" flag to guarantee that + * the update behavior is consistent with the other bitfields near + * it and that we cannot have an asynchronous probe routine trying + * to run while we are tearing out the bus/class/sysfs from + * underneath the device. + */ + lockdep_assert_held(&dev->mutex); + + if (dev->p->dead) + return false; + dev->p->dead = true; + return true; +} +EXPORT_SYMBOL_GPL(kill_device); + /** * device_del - delete device from system. * @dev: device. @@ -2230,15 +2248,8 @@ void device_del(struct device *dev) struct kobject *glue_dir = NULL; struct class_interface *class_intf; - /* - * Hold the device lock and set the "dead" flag to guarantee that - * the update behavior is consistent with the other bitfields near - * it and that we cannot have an asynchronous probe routine trying - * to run while we are tearing out the bus/class/sysfs from - * underneath the device. - */ device_lock(dev); - dev->p->dead = true; + kill_device(dev); device_unlock(dev); /* Notify clients of device removal. This call must come diff --git a/include/linux/device.h b/include/linux/device.h index e85264fb6616..0da5c67f6be1 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1373,6 +1373,7 @@ extern int (*platform_notify_remove)(struct device *dev); */ extern struct device *get_device(struct device *dev); extern void put_device(struct device *dev); +extern bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS extern int devtmpfs_create_node(struct device *dev); From 8aac0e2338916e273ccbd438a2b7a1e8c61749f5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 17 Jul 2019 18:07:58 -0700 Subject: [PATCH 103/823] libnvdimm/bus: Prevent duplicate device_unregister() calls A multithreaded namespace creation/destruction stress test currently fails with signatures like the following: sysfs group 'power' not found for kobject 'dax1.1' RIP: 0010:sysfs_remove_group+0x76/0x80 Call Trace: device_del+0x73/0x370 device_unregister+0x16/0x50 nd_async_device_unregister+0x1e/0x30 [libnvdimm] async_run_entry_fn+0x39/0x160 process_one_work+0x23c/0x5e0 worker_thread+0x3c/0x390 BUG: kernel NULL pointer dereference, address: 0000000000000020 RIP: 0010:klist_put+0x1b/0x6c Call Trace: klist_del+0xe/0x10 device_del+0x8a/0x2c9 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 device_unregister+0x44/0x4f nd_async_device_unregister+0x22/0x2d [libnvdimm] async_run_entry_fn+0x47/0x15a process_one_work+0x1a2/0x2eb worker_thread+0x1b8/0x26e Use the kill_device() helper to atomically resolve the race of multiple threads issuing kill, device_unregister(), requests. Reported-by: Jane Chu Reported-by: Erwin Tsaur Fixes: 4d88a97aa9e8 ("libnvdimm, nvdimm: dimm driver and base libnvdimm device-driver...") Cc: Link: https://github.com/pmem/ndctl/issues/96 Tested-by: Tested-by: Jane Chu Link: https://lore.kernel.org/r/156341207846.292348.10435719262819764054.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/bus.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 2dca3034fee0..42713b210f51 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -547,13 +547,38 @@ EXPORT_SYMBOL(nd_device_register); void nd_device_unregister(struct device *dev, enum nd_async_mode mode) { + bool killed; + switch (mode) { case ND_ASYNC: + /* + * In the async case this is being triggered with the + * device lock held and the unregistration work needs to + * be moved out of line iff this is thread has won the + * race to schedule the deletion. + */ + if (!kill_device(dev)) + return; + get_device(dev); async_schedule_domain(nd_async_device_unregister, dev, &nd_async_domain); break; case ND_SYNC: + /* + * In the sync case the device is being unregistered due + * to a state change of the parent. Claim the kill state + * to synchronize against other unregistration requests, + * or otherwise let the async path handle it if the + * unregistration was already queued. + */ + device_lock(dev); + killed = kill_device(dev); + device_unlock(dev); + + if (!killed) + return; + nd_synchronize(); device_unregister(dev); break; From 700cd033a82d466ad8f9615f9985525e45f8960a Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 17 Jul 2019 18:08:03 -0700 Subject: [PATCH 104/823] libnvdimm/region: Register badblocks before namespaces Namespace activation expects to be able to reference region badblocks. The following warning sometimes triggers when asynchronous namespace activation races in front of the completion of namespace probing. Move all possible namespace probing after region badblocks initialization. Otherwise, lockdep sometimes catches the uninitialized state of the badblocks seqlock with stack trace signatures like: INFO: trying to register non-static key. pmem2: detected capacity change from 0 to 136365211648 the code is fine but needs lockdep annotation. turning off the locking correctness validator. CPU: 9 PID: 358 Comm: kworker/u80:5 Tainted: G OE 5.2.0-rc4+ #3382 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.0.0 02/06/2015 Workqueue: events_unbound async_run_entry_fn Call Trace: dump_stack+0x85/0xc0 pmem1.12: detected capacity change from 0 to 8589934592 register_lock_class+0x56a/0x570 ? check_object+0x140/0x270 __lock_acquire+0x80/0x1710 ? __mutex_lock+0x39d/0x910 lock_acquire+0x9e/0x180 ? nd_pfn_validate+0x28f/0x440 [libnvdimm] badblocks_check+0x93/0x1f0 ? nd_pfn_validate+0x28f/0x440 [libnvdimm] nd_pfn_validate+0x28f/0x440 [libnvdimm] ? lockdep_hardirqs_on+0xf0/0x180 nd_dax_probe+0x9a/0x120 [libnvdimm] nd_pmem_probe+0x6d/0x180 [nd_pmem] nvdimm_bus_probe+0x90/0x2c0 [libnvdimm] Fixes: 48af2f7e52f4 ("libnvdimm, pfn: during init, clear errors...") Cc: Cc: Vishal Verma Reviewed-by: Vishal Verma Link: https://lore.kernel.org/r/156341208365.292348.1547528796026249120.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/region.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c index ef46cc3a71ae..488c47ac4c4a 100644 --- a/drivers/nvdimm/region.c +++ b/drivers/nvdimm/region.c @@ -34,17 +34,6 @@ static int nd_region_probe(struct device *dev) if (rc) return rc; - rc = nd_region_register_namespaces(nd_region, &err); - if (rc < 0) - return rc; - - ndrd = dev_get_drvdata(dev); - ndrd->ns_active = rc; - ndrd->ns_count = rc + err; - - if (rc && err && rc == err) - return -ENODEV; - if (is_nd_pmem(&nd_region->dev)) { struct resource ndr_res; @@ -60,6 +49,17 @@ static int nd_region_probe(struct device *dev) nvdimm_badblocks_populate(nd_region, &nd_region->bb, &ndr_res); } + rc = nd_region_register_namespaces(nd_region, &err); + if (rc < 0) + return rc; + + ndrd = dev_get_drvdata(dev); + ndrd->ns_active = rc; + ndrd->ns_count = rc + err; + + if (rc && err && rc == err) + return -ENODEV; + nd_region->btt_seed = nd_btt_create(nd_region); nd_region->pfn_seed = nd_pfn_create(nd_region); nd_region->dax_seed = nd_dax_create(nd_region); From 6de5d06e657acdbcf9637dac37916a4a5309e0f4 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 17 Jul 2019 18:08:09 -0700 Subject: [PATCH 105/823] libnvdimm/bus: Prepare the nd_ioctl() path to be re-entrant In preparation for not holding a lock over the execution of nd_ioctl(), update the implementation to allow multiple threads to be attempting ioctls at the same time. The bus lock still prevents multiple in-flight ->ndctl() invocations from corrupting each other's state, but static global staging buffers are moved to the heap. Reported-by: Vishal Verma Reviewed-by: Vishal Verma Tested-by: Vishal Verma Link: https://lore.kernel.org/r/156341208947.292348.10560140326807607481.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/bus.c | 59 +++++++++++++++++++++++++++----------------- 1 file changed, 37 insertions(+), 22 deletions(-) diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 42713b210f51..a3180c28fb2b 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -970,20 +970,19 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, int read_only, unsigned int ioctl_cmd, unsigned long arg) { struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc; - static char out_env[ND_CMD_MAX_ENVELOPE]; - static char in_env[ND_CMD_MAX_ENVELOPE]; const struct nd_cmd_desc *desc = NULL; unsigned int cmd = _IOC_NR(ioctl_cmd); struct device *dev = &nvdimm_bus->dev; void __user *p = (void __user *) arg; + char *out_env = NULL, *in_env = NULL; const char *cmd_name, *dimm_name; u32 in_len = 0, out_len = 0; unsigned int func = cmd; unsigned long cmd_mask; struct nd_cmd_pkg pkg; int rc, i, cmd_rc; + void *buf = NULL; u64 buf_len = 0; - void *buf; if (nvdimm) { desc = nd_cmd_dimm_desc(cmd); @@ -1023,6 +1022,9 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, } /* process an input envelope */ + in_env = kzalloc(ND_CMD_MAX_ENVELOPE, GFP_KERNEL); + if (!in_env) + return -ENOMEM; for (i = 0; i < desc->in_num; i++) { u32 in_size, copy; @@ -1030,14 +1032,17 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, if (in_size == UINT_MAX) { dev_err(dev, "%s:%s unknown input size cmd: %s field: %d\n", __func__, dimm_name, cmd_name, i); - return -ENXIO; + rc = -ENXIO; + goto out; } - if (in_len < sizeof(in_env)) - copy = min_t(u32, sizeof(in_env) - in_len, in_size); + if (in_len < ND_CMD_MAX_ENVELOPE) + copy = min_t(u32, ND_CMD_MAX_ENVELOPE - in_len, in_size); else copy = 0; - if (copy && copy_from_user(&in_env[in_len], p + in_len, copy)) - return -EFAULT; + if (copy && copy_from_user(&in_env[in_len], p + in_len, copy)) { + rc = -EFAULT; + goto out; + } in_len += in_size; } @@ -1049,6 +1054,12 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, } /* process an output envelope */ + out_env = kzalloc(ND_CMD_MAX_ENVELOPE, GFP_KERNEL); + if (!out_env) { + rc = -ENOMEM; + goto out; + } + for (i = 0; i < desc->out_num; i++) { u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, (u32 *) in_env, (u32 *) out_env, 0); @@ -1057,15 +1068,18 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, if (out_size == UINT_MAX) { dev_dbg(dev, "%s unknown output size cmd: %s field: %d\n", dimm_name, cmd_name, i); - return -EFAULT; + rc = -EFAULT; + goto out; } - if (out_len < sizeof(out_env)) - copy = min_t(u32, sizeof(out_env) - out_len, out_size); + if (out_len < ND_CMD_MAX_ENVELOPE) + copy = min_t(u32, ND_CMD_MAX_ENVELOPE - out_len, out_size); else copy = 0; if (copy && copy_from_user(&out_env[out_len], - p + in_len + out_len, copy)) - return -EFAULT; + p + in_len + out_len, copy)) { + rc = -EFAULT; + goto out; + } out_len += out_size; } @@ -1073,12 +1087,15 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, if (buf_len > ND_IOCTL_MAX_BUFLEN) { dev_dbg(dev, "%s cmd: %s buf_len: %llu > %d\n", dimm_name, cmd_name, buf_len, ND_IOCTL_MAX_BUFLEN); - return -EINVAL; + rc = -EINVAL; + goto out; } buf = vmalloc(buf_len); - if (!buf) - return -ENOMEM; + if (!buf) { + rc = -ENOMEM; + goto out; + } if (copy_from_user(buf, p, buf_len)) { rc = -EFAULT; @@ -1100,17 +1117,15 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, nvdimm_account_cleared_poison(nvdimm_bus, clear_err->address, clear_err->cleared); } - nvdimm_bus_unlock(&nvdimm_bus->dev); if (copy_to_user(p, buf, buf_len)) rc = -EFAULT; - vfree(buf); - return rc; - - out_unlock: +out_unlock: nvdimm_bus_unlock(&nvdimm_bus->dev); - out: +out: + kfree(in_env); + kfree(out_env); vfree(buf); return rc; } From b70d31d054ee3a6fc1034b9d7fc0ae1e481aa018 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 17 Jul 2019 18:08:15 -0700 Subject: [PATCH 106/823] libnvdimm/bus: Stop holding nvdimm_bus_list_mutex over __nd_ioctl() In preparation for fixing a deadlock between wait_for_bus_probe_idle() and the nvdimm_bus_list_mutex arrange for __nd_ioctl() without nvdimm_bus_list_mutex held. This also unifies the 'dimm' and 'bus' level ioctls into a common nd_ioctl() preamble implementation. Marked for -stable as it is a pre-requisite for a follow-on fix. Cc: Fixes: bf9bccc14c05 ("libnvdimm: pmem label sets and namespace instantiation") Cc: Vishal Verma Tested-by: Jane Chu Link: https://lore.kernel.org/r/156341209518.292348.7183897251740665198.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/bus.c | 94 ++++++++++++++++++++++++---------------- drivers/nvdimm/nd-core.h | 3 +- 2 files changed, 59 insertions(+), 38 deletions(-) diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index a3180c28fb2b..a38572bf486b 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -73,7 +73,7 @@ static void nvdimm_bus_probe_end(struct nvdimm_bus *nvdimm_bus) { nvdimm_bus_lock(&nvdimm_bus->dev); if (--nvdimm_bus->probe_active == 0) - wake_up(&nvdimm_bus->probe_wait); + wake_up(&nvdimm_bus->wait); nvdimm_bus_unlock(&nvdimm_bus->dev); } @@ -341,7 +341,7 @@ struct nvdimm_bus *nvdimm_bus_register(struct device *parent, return NULL; INIT_LIST_HEAD(&nvdimm_bus->list); INIT_LIST_HEAD(&nvdimm_bus->mapping_list); - init_waitqueue_head(&nvdimm_bus->probe_wait); + init_waitqueue_head(&nvdimm_bus->wait); nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL); if (nvdimm_bus->id < 0) { kfree(nvdimm_bus); @@ -426,6 +426,9 @@ static int nd_bus_remove(struct device *dev) list_del_init(&nvdimm_bus->list); mutex_unlock(&nvdimm_bus_list_mutex); + wait_event(nvdimm_bus->wait, + atomic_read(&nvdimm_bus->ioctl_active) == 0); + nd_synchronize(); device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister); @@ -885,7 +888,7 @@ void wait_nvdimm_bus_probe_idle(struct device *dev) if (nvdimm_bus->probe_active == 0) break; nvdimm_bus_unlock(&nvdimm_bus->dev); - wait_event(nvdimm_bus->probe_wait, + wait_event(nvdimm_bus->wait, nvdimm_bus->probe_active == 0); nvdimm_bus_lock(&nvdimm_bus->dev); } while (true); @@ -1130,24 +1133,10 @@ out: return rc; } -static long nd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) -{ - long id = (long) file->private_data; - int rc = -ENXIO, ro; - struct nvdimm_bus *nvdimm_bus; - - ro = ((file->f_flags & O_ACCMODE) == O_RDONLY); - mutex_lock(&nvdimm_bus_list_mutex); - list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) { - if (nvdimm_bus->id == id) { - rc = __nd_ioctl(nvdimm_bus, NULL, ro, cmd, arg); - break; - } - } - mutex_unlock(&nvdimm_bus_list_mutex); - - return rc; -} +enum nd_ioctl_mode { + BUS_IOCTL, + DIMM_IOCTL, +}; static int match_dimm(struct device *dev, void *data) { @@ -1162,31 +1151,62 @@ static int match_dimm(struct device *dev, void *data) return 0; } -static long nvdimm_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +static long nd_ioctl(struct file *file, unsigned int cmd, unsigned long arg, + enum nd_ioctl_mode mode) + { - int rc = -ENXIO, ro; - struct nvdimm_bus *nvdimm_bus; + struct nvdimm_bus *nvdimm_bus, *found = NULL; + long id = (long) file->private_data; + struct nvdimm *nvdimm = NULL; + int rc, ro; ro = ((file->f_flags & O_ACCMODE) == O_RDONLY); mutex_lock(&nvdimm_bus_list_mutex); list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) { - struct device *dev = device_find_child(&nvdimm_bus->dev, - file->private_data, match_dimm); - struct nvdimm *nvdimm; + if (mode == DIMM_IOCTL) { + struct device *dev; - if (!dev) - continue; + dev = device_find_child(&nvdimm_bus->dev, + file->private_data, match_dimm); + if (!dev) + continue; + nvdimm = to_nvdimm(dev); + found = nvdimm_bus; + } else if (nvdimm_bus->id == id) { + found = nvdimm_bus; + } - nvdimm = to_nvdimm(dev); - rc = __nd_ioctl(nvdimm_bus, nvdimm, ro, cmd, arg); - put_device(dev); - break; + if (found) { + atomic_inc(&nvdimm_bus->ioctl_active); + break; + } } mutex_unlock(&nvdimm_bus_list_mutex); + if (!found) + return -ENXIO; + + nvdimm_bus = found; + rc = __nd_ioctl(nvdimm_bus, nvdimm, ro, cmd, arg); + + if (nvdimm) + put_device(&nvdimm->dev); + if (atomic_dec_and_test(&nvdimm_bus->ioctl_active)) + wake_up(&nvdimm_bus->wait); + return rc; } +static long bus_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + return nd_ioctl(file, cmd, arg, BUS_IOCTL); +} + +static long dimm_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + return nd_ioctl(file, cmd, arg, DIMM_IOCTL); +} + static int nd_open(struct inode *inode, struct file *file) { long minor = iminor(inode); @@ -1198,16 +1218,16 @@ static int nd_open(struct inode *inode, struct file *file) static const struct file_operations nvdimm_bus_fops = { .owner = THIS_MODULE, .open = nd_open, - .unlocked_ioctl = nd_ioctl, - .compat_ioctl = nd_ioctl, + .unlocked_ioctl = bus_ioctl, + .compat_ioctl = bus_ioctl, .llseek = noop_llseek, }; static const struct file_operations nvdimm_fops = { .owner = THIS_MODULE, .open = nd_open, - .unlocked_ioctl = nvdimm_ioctl, - .compat_ioctl = nvdimm_ioctl, + .unlocked_ioctl = dimm_ioctl, + .compat_ioctl = dimm_ioctl, .llseek = noop_llseek, }; diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index 391e88de3a29..6cd470547106 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -17,10 +17,11 @@ extern struct workqueue_struct *nvdimm_wq; struct nvdimm_bus { struct nvdimm_bus_descriptor *nd_desc; - wait_queue_head_t probe_wait; + wait_queue_head_t wait; struct list_head list; struct device dev; int id, probe_active; + atomic_t ioctl_active; struct list_head mapping_list; struct mutex reconfig_mutex; struct badrange badrange; From ca6bf264f6d856f959c4239cda1047b587745c67 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 17 Jul 2019 18:08:21 -0700 Subject: [PATCH 107/823] libnvdimm/bus: Fix wait_nvdimm_bus_probe_idle() ABBA deadlock A multithreaded namespace creation/destruction stress test currently deadlocks with the following lockup signature: INFO: task ndctl:2924 blocked for more than 122 seconds. Tainted: G OE 5.2.0-rc4+ #3382 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. ndctl D 0 2924 1176 0x00000000 Call Trace: ? __schedule+0x27e/0x780 schedule+0x30/0xb0 wait_nvdimm_bus_probe_idle+0x8a/0xd0 [libnvdimm] ? finish_wait+0x80/0x80 uuid_store+0xe6/0x2e0 [libnvdimm] kernfs_fop_write+0xf0/0x1a0 vfs_write+0xb7/0x1b0 ksys_write+0x5c/0xd0 do_syscall_64+0x60/0x240 INFO: task ndctl:2923 blocked for more than 122 seconds. Tainted: G OE 5.2.0-rc4+ #3382 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. ndctl D 0 2923 1175 0x00000000 Call Trace: ? __schedule+0x27e/0x780 ? __mutex_lock+0x489/0x910 schedule+0x30/0xb0 schedule_preempt_disabled+0x11/0x20 __mutex_lock+0x48e/0x910 ? nvdimm_namespace_common_probe+0x95/0x4d0 [libnvdimm] ? __lock_acquire+0x23f/0x1710 ? nvdimm_namespace_common_probe+0x95/0x4d0 [libnvdimm] nvdimm_namespace_common_probe+0x95/0x4d0 [libnvdimm] __dax_pmem_probe+0x5e/0x210 [dax_pmem_core] ? nvdimm_bus_probe+0x1d0/0x2c0 [libnvdimm] dax_pmem_probe+0xc/0x20 [dax_pmem] nvdimm_bus_probe+0x90/0x2c0 [libnvdimm] really_probe+0xef/0x390 driver_probe_device+0xb4/0x100 In this sequence an 'nd_dax' device is being probed and trying to take the lock on its backing namespace to validate that the 'nd_dax' device indeed has exclusive access to the backing namespace. Meanwhile, another thread is trying to update the uuid property of that same backing namespace. So one thread is in the probe path trying to acquire the lock, and the other thread has acquired the lock and tries to flush the probe path. Fix this deadlock by not holding the namespace device_lock over the wait_nvdimm_bus_probe_idle() synchronization step. In turn this requires the device_lock to be held on entry to wait_nvdimm_bus_probe_idle() and subsequently dropped internally to wait_nvdimm_bus_probe_idle(). Cc: Fixes: bf9bccc14c05 ("libnvdimm: pmem label sets and namespace instantiation") Cc: Vishal Verma Tested-by: Jane Chu Link: https://lore.kernel.org/r/156341210094.292348.2384694131126767789.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/bus.c | 14 +++++++++----- drivers/nvdimm/region_devs.c | 4 ++++ 2 files changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index a38572bf486b..df41f3571dc9 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -887,10 +887,12 @@ void wait_nvdimm_bus_probe_idle(struct device *dev) do { if (nvdimm_bus->probe_active == 0) break; - nvdimm_bus_unlock(&nvdimm_bus->dev); + nvdimm_bus_unlock(dev); + device_unlock(dev); wait_event(nvdimm_bus->wait, nvdimm_bus->probe_active == 0); - nvdimm_bus_lock(&nvdimm_bus->dev); + device_lock(dev); + nvdimm_bus_lock(dev); } while (true); } @@ -1016,7 +1018,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, case ND_CMD_ARS_START: case ND_CMD_CLEAR_ERROR: case ND_CMD_CALL: - dev_dbg(&nvdimm_bus->dev, "'%s' command while read-only.\n", + dev_dbg(dev, "'%s' command while read-only.\n", nvdimm ? nvdimm_cmd_name(cmd) : nvdimm_bus_cmd_name(cmd)); return -EPERM; @@ -1105,7 +1107,8 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, goto out; } - nvdimm_bus_lock(&nvdimm_bus->dev); + device_lock(dev); + nvdimm_bus_lock(dev); rc = nd_cmd_clear_to_send(nvdimm_bus, nvdimm, func, buf); if (rc) goto out_unlock; @@ -1125,7 +1128,8 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, rc = -EFAULT; out_unlock: - nvdimm_bus_unlock(&nvdimm_bus->dev); + nvdimm_bus_unlock(dev); + device_unlock(dev); out: kfree(in_env); kfree(out_env); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 4fed9ce9c2fe..a15276cdec7d 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -422,10 +422,12 @@ static ssize_t available_size_show(struct device *dev, * memory nvdimm_bus_lock() is dropped, but that's userspace's * problem to not race itself. */ + device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); available = nd_region_available_dpa(nd_region); nvdimm_bus_unlock(dev); + device_unlock(dev); return sprintf(buf, "%llu\n", available); } @@ -437,10 +439,12 @@ static ssize_t max_available_extent_show(struct device *dev, struct nd_region *nd_region = to_nd_region(dev); unsigned long long available = 0; + device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); available = nd_region_allocatable_dpa(nd_region); nvdimm_bus_unlock(dev); + device_unlock(dev); return sprintf(buf, "%llu\n", available); } From 87a30e1f05d73a34e6d1895065541369131aaf1c Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 17 Jul 2019 18:08:26 -0700 Subject: [PATCH 108/823] driver-core, libnvdimm: Let device subsystems add local lockdep coverage For good reason, the standard device_lock() is marked lockdep_set_novalidate_class() because there is simply no sane way to describe the myriad ways the device_lock() ordered with other locks. However, that leaves subsystems that know their own local device_lock() ordering rules to find lock ordering mistakes manually. Instead, introduce an optional / additional lockdep-enabled lock that a subsystem can acquire in all the same paths that the device_lock() is acquired. A conversion of the NFIT driver and NVDIMM subsystem to a lockdep-validate device_lock() scheme is included. The debug_nvdimm_lock() implementation implements the correct lock-class and stacking order for the libnvdimm device topology hierarchy. Yes, this is a hack, but hopefully it is a useful hack for other subsystems device_lock() debug sessions. Quoting Greg: "Yeah, it feels a bit hacky but it's really up to a subsystem to mess up using it as much as anything else, so user beware :) I don't object to it if it makes things easier for you to debug." Cc: Ingo Molnar Cc: Ira Weiny Cc: Will Deacon Cc: Dave Jiang Cc: Keith Busch Cc: Peter Zijlstra Cc: Vishal Verma Cc: "Rafael J. Wysocki" Cc: Greg Kroah-Hartman Signed-off-by: Dan Williams Acked-by: Greg Kroah-Hartman Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/156341210661.292348.7014034644265455704.stgit@dwillia2-desk3.amr.corp.intel.com --- drivers/acpi/nfit/core.c | 28 +++++++------- drivers/acpi/nfit/nfit.h | 24 ++++++++++++ drivers/base/core.c | 3 ++ drivers/nvdimm/btt_devs.c | 16 ++++---- drivers/nvdimm/bus.c | 28 ++++++++------ drivers/nvdimm/core.c | 10 ++--- drivers/nvdimm/dimm_devs.c | 4 +- drivers/nvdimm/namespace_devs.c | 36 ++++++++--------- drivers/nvdimm/nd-core.h | 68 +++++++++++++++++++++++++++++++++ drivers/nvdimm/pfn_devs.c | 24 ++++++------ drivers/nvdimm/pmem.c | 4 +- drivers/nvdimm/region.c | 2 +- drivers/nvdimm/region_devs.c | 16 ++++---- include/linux/device.h | 5 +++ 14 files changed, 187 insertions(+), 81 deletions(-) diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 23022cf20d26..f22139458ce1 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1282,7 +1282,7 @@ static ssize_t hw_error_scrub_store(struct device *dev, if (rc) return rc; - device_lock(dev); + nfit_device_lock(dev); nd_desc = dev_get_drvdata(dev); if (nd_desc) { struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); @@ -1299,7 +1299,7 @@ static ssize_t hw_error_scrub_store(struct device *dev, break; } } - device_unlock(dev); + nfit_device_unlock(dev); if (rc) return rc; return size; @@ -1319,7 +1319,7 @@ static ssize_t scrub_show(struct device *dev, ssize_t rc = -ENXIO; bool busy; - device_lock(dev); + nfit_device_lock(dev); nd_desc = dev_get_drvdata(dev); if (!nd_desc) { device_unlock(dev); @@ -1339,7 +1339,7 @@ static ssize_t scrub_show(struct device *dev, } mutex_unlock(&acpi_desc->init_mutex); - device_unlock(dev); + nfit_device_unlock(dev); return rc; } @@ -1356,14 +1356,14 @@ static ssize_t scrub_store(struct device *dev, if (val != 1) return -EINVAL; - device_lock(dev); + nfit_device_lock(dev); nd_desc = dev_get_drvdata(dev); if (nd_desc) { struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); rc = acpi_nfit_ars_rescan(acpi_desc, ARS_REQ_LONG); } - device_unlock(dev); + nfit_device_unlock(dev); if (rc) return rc; return size; @@ -1749,9 +1749,9 @@ static void acpi_nvdimm_notify(acpi_handle handle, u32 event, void *data) struct acpi_device *adev = data; struct device *dev = &adev->dev; - device_lock(dev->parent); + nfit_device_lock(dev->parent); __acpi_nvdimm_notify(dev, event); - device_unlock(dev->parent); + nfit_device_unlock(dev->parent); } static bool acpi_nvdimm_has_method(struct acpi_device *adev, char *method) @@ -3457,8 +3457,8 @@ static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc) struct device *dev = acpi_desc->dev; /* Bounce the device lock to flush acpi_nfit_add / acpi_nfit_notify */ - device_lock(dev); - device_unlock(dev); + nfit_device_lock(dev); + nfit_device_unlock(dev); /* Bounce the init_mutex to complete initial registration */ mutex_lock(&acpi_desc->init_mutex); @@ -3602,8 +3602,8 @@ void acpi_nfit_shutdown(void *data) * acpi_nfit_ars_rescan() submissions have had a chance to * either submit or see ->cancel set. */ - device_lock(bus_dev); - device_unlock(bus_dev); + nfit_device_lock(bus_dev); + nfit_device_unlock(bus_dev); flush_workqueue(nfit_wq); } @@ -3746,9 +3746,9 @@ EXPORT_SYMBOL_GPL(__acpi_nfit_notify); static void acpi_nfit_notify(struct acpi_device *adev, u32 event) { - device_lock(&adev->dev); + nfit_device_lock(&adev->dev); __acpi_nfit_notify(&adev->dev, adev->handle, event); - device_unlock(&adev->dev); + nfit_device_unlock(&adev->dev); } static const struct acpi_device_id acpi_nfit_ids[] = { diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index 6ee2b02af73e..24241941181c 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -312,6 +312,30 @@ static inline struct acpi_nfit_desc *to_acpi_desc( return container_of(nd_desc, struct acpi_nfit_desc, nd_desc); } +#ifdef CONFIG_PROVE_LOCKING +static inline void nfit_device_lock(struct device *dev) +{ + device_lock(dev); + mutex_lock(&dev->lockdep_mutex); +} + +static inline void nfit_device_unlock(struct device *dev) +{ + mutex_unlock(&dev->lockdep_mutex); + device_unlock(dev); +} +#else +static inline void nfit_device_lock(struct device *dev) +{ + device_lock(dev); +} + +static inline void nfit_device_unlock(struct device *dev) +{ + device_unlock(dev); +} +#endif + const guid_t *to_nfit_uuid(enum nfit_uuids id); int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *nfit, acpi_size sz); void acpi_nfit_shutdown(void *data); diff --git a/drivers/base/core.c b/drivers/base/core.c index eaf3aa0cb803..4825949d6547 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1663,6 +1663,9 @@ void device_initialize(struct device *dev) kobject_init(&dev->kobj, &device_ktype); INIT_LIST_HEAD(&dev->dma_pools); mutex_init(&dev->mutex); +#ifdef CONFIG_PROVE_LOCKING + mutex_init(&dev->lockdep_mutex); +#endif lockdep_set_novalidate_class(&dev->mutex); spin_lock_init(&dev->devres_lock); INIT_LIST_HEAD(&dev->devres_head); diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c index 62d00fffa4af..3508a79110c7 100644 --- a/drivers/nvdimm/btt_devs.c +++ b/drivers/nvdimm/btt_devs.c @@ -62,14 +62,14 @@ static ssize_t sector_size_store(struct device *dev, struct nd_btt *nd_btt = to_nd_btt(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); rc = nd_size_select_store(dev, buf, &nd_btt->lbasize, btt_lbasize_supported); dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc ? rc : len; } @@ -91,11 +91,11 @@ static ssize_t uuid_store(struct device *dev, struct nd_btt *nd_btt = to_nd_btt(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); rc = nd_uuid_store(dev, &nd_btt->uuid, buf, len); dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); - device_unlock(dev); + nd_device_unlock(dev); return rc ? rc : len; } @@ -120,13 +120,13 @@ static ssize_t namespace_store(struct device *dev, struct nd_btt *nd_btt = to_nd_btt(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); rc = nd_namespace_store(dev, &nd_btt->ndns, buf, len); dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc; } @@ -138,14 +138,14 @@ static ssize_t size_show(struct device *dev, struct nd_btt *nd_btt = to_nd_btt(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); if (dev->driver) rc = sprintf(buf, "%llu\n", nd_btt->size); else { /* no size to convey if the btt instance is disabled */ rc = -ENXIO; } - device_unlock(dev); + nd_device_unlock(dev); return rc; } diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index df41f3571dc9..798c5c4aea9c 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -26,7 +26,7 @@ int nvdimm_major; static int nvdimm_bus_major; -static struct class *nd_class; +struct class *nd_class; static DEFINE_IDA(nd_ida); static int to_nd_device_type(struct device *dev) @@ -91,7 +91,10 @@ static int nvdimm_bus_probe(struct device *dev) dev->driver->name, dev_name(dev)); nvdimm_bus_probe_start(nvdimm_bus); + debug_nvdimm_lock(dev); rc = nd_drv->probe(dev); + debug_nvdimm_unlock(dev); + if (rc == 0) nd_region_probe_success(nvdimm_bus, dev); else @@ -113,8 +116,11 @@ static int nvdimm_bus_remove(struct device *dev) struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); int rc = 0; - if (nd_drv->remove) + if (nd_drv->remove) { + debug_nvdimm_lock(dev); rc = nd_drv->remove(dev); + debug_nvdimm_unlock(dev); + } nd_region_disable(nvdimm_bus, dev); dev_dbg(&nvdimm_bus->dev, "%s.remove(%s) = %d\n", dev->driver->name, @@ -140,7 +146,7 @@ static void nvdimm_bus_shutdown(struct device *dev) void nd_device_notify(struct device *dev, enum nvdimm_event event) { - device_lock(dev); + nd_device_lock(dev); if (dev->driver) { struct nd_device_driver *nd_drv; @@ -148,7 +154,7 @@ void nd_device_notify(struct device *dev, enum nvdimm_event event) if (nd_drv->notify) nd_drv->notify(dev, event); } - device_unlock(dev); + nd_device_unlock(dev); } EXPORT_SYMBOL(nd_device_notify); @@ -296,7 +302,7 @@ static void nvdimm_bus_release(struct device *dev) kfree(nvdimm_bus); } -static bool is_nvdimm_bus(struct device *dev) +bool is_nvdimm_bus(struct device *dev) { return dev->release == nvdimm_bus_release; } @@ -575,9 +581,9 @@ void nd_device_unregister(struct device *dev, enum nd_async_mode mode) * or otherwise let the async path handle it if the * unregistration was already queued. */ - device_lock(dev); + nd_device_lock(dev); killed = kill_device(dev); - device_unlock(dev); + nd_device_unlock(dev); if (!killed) return; @@ -888,10 +894,10 @@ void wait_nvdimm_bus_probe_idle(struct device *dev) if (nvdimm_bus->probe_active == 0) break; nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); wait_event(nvdimm_bus->wait, nvdimm_bus->probe_active == 0); - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); } while (true); } @@ -1107,7 +1113,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, goto out; } - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); rc = nd_cmd_clear_to_send(nvdimm_bus, nvdimm, func, buf); if (rc) @@ -1129,7 +1135,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, out_unlock: nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); out: kfree(in_env); kfree(out_env); diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c index 5e1f060547bf..9204f1e9fd14 100644 --- a/drivers/nvdimm/core.c +++ b/drivers/nvdimm/core.c @@ -246,7 +246,7 @@ static int nd_uuid_parse(struct device *dev, u8 *uuid_out, const char *buf, * * Enforce that uuids can only be changed while the device is disabled * (driver detached) - * LOCKING: expects device_lock() is held on entry + * LOCKING: expects nd_device_lock() is held on entry */ int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf, size_t len) @@ -347,15 +347,15 @@ static DEVICE_ATTR_RO(provider); static int flush_namespaces(struct device *dev, void *data) { - device_lock(dev); - device_unlock(dev); + nd_device_lock(dev); + nd_device_unlock(dev); return 0; } static int flush_regions_dimms(struct device *dev, void *data) { - device_lock(dev); - device_unlock(dev); + nd_device_lock(dev); + nd_device_unlock(dev); device_for_each_child(dev, NULL, flush_namespaces); return 0; } diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index dfecd6e17043..29a065e769ea 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -484,12 +484,12 @@ static ssize_t security_store(struct device *dev, * done while probing is idle and the DIMM is not in active use * in any region. */ - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); rc = __security_store(dev, buf, len); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc; } diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index a434a5964cb9..92cd809d7e43 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -410,7 +410,7 @@ static ssize_t alt_name_store(struct device *dev, struct nd_region *nd_region = to_nd_region(dev->parent); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); rc = __alt_name_store(dev, buf, len); @@ -418,7 +418,7 @@ static ssize_t alt_name_store(struct device *dev, rc = nd_namespace_label_update(nd_region, dev); dev_dbg(dev, "%s(%zd)\n", rc < 0 ? "fail " : "", rc); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc < 0 ? rc : len; } @@ -1077,7 +1077,7 @@ static ssize_t size_store(struct device *dev, if (rc) return rc; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); rc = __size_store(dev, val); @@ -1103,7 +1103,7 @@ static ssize_t size_store(struct device *dev, dev_dbg(dev, "%llx %s (%d)\n", val, rc < 0 ? "fail" : "success", rc); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc < 0 ? rc : len; } @@ -1286,7 +1286,7 @@ static ssize_t uuid_store(struct device *dev, } else return -ENXIO; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); if (to_ndns(dev)->claim) @@ -1302,7 +1302,7 @@ static ssize_t uuid_store(struct device *dev, dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc < 0 ? rc : len; } @@ -1376,7 +1376,7 @@ static ssize_t sector_size_store(struct device *dev, } else return -ENXIO; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); if (to_ndns(dev)->claim) rc = -EBUSY; @@ -1387,7 +1387,7 @@ static ssize_t sector_size_store(struct device *dev, dev_dbg(dev, "result: %zd %s: %s%s", rc, rc < 0 ? "tried" : "wrote", buf, buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc ? rc : len; } @@ -1502,9 +1502,9 @@ static ssize_t holder_show(struct device *dev, struct nd_namespace_common *ndns = to_ndns(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); rc = sprintf(buf, "%s\n", ndns->claim ? dev_name(ndns->claim) : ""); - device_unlock(dev); + nd_device_unlock(dev); return rc; } @@ -1541,7 +1541,7 @@ static ssize_t holder_class_store(struct device *dev, struct nd_region *nd_region = to_nd_region(dev->parent); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); rc = __holder_class_store(dev, buf); @@ -1549,7 +1549,7 @@ static ssize_t holder_class_store(struct device *dev, rc = nd_namespace_label_update(nd_region, dev); dev_dbg(dev, "%s(%zd)\n", rc < 0 ? "fail " : "", rc); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc < 0 ? rc : len; } @@ -1560,7 +1560,7 @@ static ssize_t holder_class_show(struct device *dev, struct nd_namespace_common *ndns = to_ndns(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); if (ndns->claim_class == NVDIMM_CCLASS_NONE) rc = sprintf(buf, "\n"); else if ((ndns->claim_class == NVDIMM_CCLASS_BTT) || @@ -1572,7 +1572,7 @@ static ssize_t holder_class_show(struct device *dev, rc = sprintf(buf, "dax\n"); else rc = sprintf(buf, "\n"); - device_unlock(dev); + nd_device_unlock(dev); return rc; } @@ -1586,7 +1586,7 @@ static ssize_t mode_show(struct device *dev, char *mode; ssize_t rc; - device_lock(dev); + nd_device_lock(dev); claim = ndns->claim; if (claim && is_nd_btt(claim)) mode = "safe"; @@ -1599,7 +1599,7 @@ static ssize_t mode_show(struct device *dev, else mode = "raw"; rc = sprintf(buf, "%s\n", mode); - device_unlock(dev); + nd_device_unlock(dev); return rc; } @@ -1703,8 +1703,8 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev) * Flush any in-progess probes / removals in the driver * for the raw personality of this namespace. */ - device_lock(&ndns->dev); - device_unlock(&ndns->dev); + nd_device_lock(&ndns->dev); + nd_device_unlock(&ndns->dev); if (ndns->dev.driver) { dev_dbg(&ndns->dev, "is active, can't bind %s\n", dev_name(dev)); diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index 6cd470547106..0ac52b6eb00e 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -9,6 +9,7 @@ #include #include #include +#include "nd.h" extern struct list_head nvdimm_bus_list; extern struct mutex nvdimm_bus_list_mutex; @@ -182,4 +183,71 @@ ssize_t nd_namespace_store(struct device *dev, struct nd_namespace_common **_ndns, const char *buf, size_t len); struct nd_pfn *to_nd_pfn_safe(struct device *dev); +bool is_nvdimm_bus(struct device *dev); + +#ifdef CONFIG_PROVE_LOCKING +extern struct class *nd_class; + +enum { + LOCK_BUS, + LOCK_NDCTL, + LOCK_REGION, + LOCK_DIMM = LOCK_REGION, + LOCK_NAMESPACE, + LOCK_CLAIM, +}; + +static inline void debug_nvdimm_lock(struct device *dev) +{ + if (is_nd_region(dev)) + mutex_lock_nested(&dev->lockdep_mutex, LOCK_REGION); + else if (is_nvdimm(dev)) + mutex_lock_nested(&dev->lockdep_mutex, LOCK_DIMM); + else if (is_nd_btt(dev) || is_nd_pfn(dev) || is_nd_dax(dev)) + mutex_lock_nested(&dev->lockdep_mutex, LOCK_CLAIM); + else if (dev->parent && (is_nd_region(dev->parent))) + mutex_lock_nested(&dev->lockdep_mutex, LOCK_NAMESPACE); + else if (is_nvdimm_bus(dev)) + mutex_lock_nested(&dev->lockdep_mutex, LOCK_BUS); + else if (dev->class && dev->class == nd_class) + mutex_lock_nested(&dev->lockdep_mutex, LOCK_NDCTL); + else + dev_WARN(dev, "unknown lock level\n"); +} + +static inline void debug_nvdimm_unlock(struct device *dev) +{ + mutex_unlock(&dev->lockdep_mutex); +} + +static inline void nd_device_lock(struct device *dev) +{ + device_lock(dev); + debug_nvdimm_lock(dev); +} + +static inline void nd_device_unlock(struct device *dev) +{ + debug_nvdimm_unlock(dev); + device_unlock(dev); +} +#else +static inline void nd_device_lock(struct device *dev) +{ + device_lock(dev); +} + +static inline void nd_device_unlock(struct device *dev) +{ + device_unlock(dev); +} + +static inline void debug_nvdimm_lock(struct device *dev) +{ +} + +static inline void debug_nvdimm_unlock(struct device *dev) +{ +} +#endif #endif /* __ND_CORE_H__ */ diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index 0f81fc56bbfd..9b09fe18e666 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -67,7 +67,7 @@ static ssize_t mode_store(struct device *dev, struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc = 0; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); if (dev->driver) rc = -EBUSY; @@ -89,7 +89,7 @@ static ssize_t mode_store(struct device *dev, dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc ? rc : len; } @@ -132,14 +132,14 @@ static ssize_t align_store(struct device *dev, struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); rc = nd_size_select_store(dev, buf, &nd_pfn->align, nd_pfn_supported_alignments()); dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc ? rc : len; } @@ -161,11 +161,11 @@ static ssize_t uuid_store(struct device *dev, struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); rc = nd_uuid_store(dev, &nd_pfn->uuid, buf, len); dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); - device_unlock(dev); + nd_device_unlock(dev); return rc ? rc : len; } @@ -190,13 +190,13 @@ static ssize_t namespace_store(struct device *dev, struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); rc = nd_namespace_store(dev, &nd_pfn->ndns, buf, len); dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc; } @@ -208,7 +208,7 @@ static ssize_t resource_show(struct device *dev, struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); if (dev->driver) { struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb; u64 offset = __le64_to_cpu(pfn_sb->dataoff); @@ -222,7 +222,7 @@ static ssize_t resource_show(struct device *dev, /* no address to convey if the pfn instance is disabled */ rc = -ENXIO; } - device_unlock(dev); + nd_device_unlock(dev); return rc; } @@ -234,7 +234,7 @@ static ssize_t size_show(struct device *dev, struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); if (dev->driver) { struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb; u64 offset = __le64_to_cpu(pfn_sb->dataoff); @@ -250,7 +250,7 @@ static ssize_t size_show(struct device *dev, /* no size to convey if the pfn instance is disabled */ rc = -ENXIO; } - device_unlock(dev); + nd_device_unlock(dev); return rc; } diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 28cb44c61d4a..53797e7be18a 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -520,8 +520,8 @@ static int nd_pmem_remove(struct device *dev) nvdimm_namespace_detach_btt(to_nd_btt(dev)); else { /* - * Note, this assumes device_lock() context to not race - * nd_pmem_notify() + * Note, this assumes nd_device_lock() context to not + * race nd_pmem_notify() */ sysfs_put(pmem->bb_state); pmem->bb_state = NULL; diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c index 488c47ac4c4a..37bf8719a2a4 100644 --- a/drivers/nvdimm/region.c +++ b/drivers/nvdimm/region.c @@ -102,7 +102,7 @@ static int nd_region_remove(struct device *dev) nvdimm_bus_unlock(dev); /* - * Note, this assumes device_lock() context to not race + * Note, this assumes nd_device_lock() context to not race * nd_region_notify() */ sysfs_put(nd_region->bb_state); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index a15276cdec7d..91b5a7ade0d5 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -329,7 +329,7 @@ static ssize_t set_cookie_show(struct device *dev, * the v1.1 namespace label cookie definition. To read all this * data we need to wait for probing to settle. */ - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); if (nd_region->ndr_mappings) { @@ -346,7 +346,7 @@ static ssize_t set_cookie_show(struct device *dev, } } nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); if (rc) return rc; @@ -422,12 +422,12 @@ static ssize_t available_size_show(struct device *dev, * memory nvdimm_bus_lock() is dropped, but that's userspace's * problem to not race itself. */ - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); available = nd_region_available_dpa(nd_region); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return sprintf(buf, "%llu\n", available); } @@ -439,12 +439,12 @@ static ssize_t max_available_extent_show(struct device *dev, struct nd_region *nd_region = to_nd_region(dev); unsigned long long available = 0; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); available = nd_region_allocatable_dpa(nd_region); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return sprintf(buf, "%llu\n", available); } @@ -563,12 +563,12 @@ static ssize_t region_badblocks_show(struct device *dev, struct nd_region *nd_region = to_nd_region(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); if (dev->driver) rc = badblocks_show(&nd_region->bb, buf, 0); else rc = -ENXIO; - device_unlock(dev); + nd_device_unlock(dev); return rc; } diff --git a/include/linux/device.h b/include/linux/device.h index 0da5c67f6be1..9237b857b598 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -909,6 +909,8 @@ struct dev_links_info { * This identifies the device type and carries type-specific * information. * @mutex: Mutex to synchronize calls to its driver. + * @lockdep_mutex: An optional debug lock that a subsystem can use as a + * peer lock to gain localized lockdep coverage of the device_lock. * @bus: Type of bus device is on. * @driver: Which driver has allocated this * @platform_data: Platform data specific to the device. @@ -991,6 +993,9 @@ struct device { core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set_drvdata/dev_get_drvdata */ +#ifdef CONFIG_PROVE_LOCKING + struct mutex lockdep_mutex; +#endif struct mutex mutex; /* mutex to synchronize calls to * its driver. */ From 9798f4ea71eaf8eaad7e688c5b298528089c7bf8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Date: Thu, 18 Jul 2019 23:51:54 +0200 Subject: [PATCH 109/823] KVM: PPC: Book3S HV: XIVE: fix rollback when kvmppc_xive_create fails MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The XIVE device structure is now allocated in kvmppc_xive_get_device() and kfree'd in kvmppc_core_destroy_vm(). In case of an OPAL error when allocating the XIVE VPs, the kfree() call in kvmppc_xive_*create() will result in a double free and corrupt the host memory. Fixes: 5422e95103cf ("KVM: PPC: Book3S HV: XIVE: Replace the 'destroy' method by a 'release' method") Cc: stable@vger.kernel.org # v5.2+ Signed-off-by: Cédric Le Goater Tested-by: Michael Ellerman Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/6ea6998b-a890-2511-01d1-747d7621eb19@kaod.org --- arch/powerpc/kvm/book3s_xive.c | 4 +--- arch/powerpc/kvm/book3s_xive_native.c | 4 ++-- 2 files changed, 3 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 6ca0d7376a9f..e3ba67095895 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1986,10 +1986,8 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) xive->single_escalation = xive_native_has_single_escalation(); - if (ret) { - kfree(xive); + if (ret) return ret; - } return 0; } diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 5596c8ec221a..a998823f68a3 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -1090,9 +1090,9 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type) xive->ops = &kvmppc_xive_native_ops; if (ret) - kfree(xive); + return ret; - return ret; + return 0; } /* From 56ac5e2139331898f29e6990f67ae8d2f080686b Mon Sep 17 00:00:00 2001 From: Paul Walmsley Date: Thu, 18 Jul 2019 17:15:06 -0700 Subject: [PATCH 110/823] riscv: enable sys_clone3 syscall for rv64 Enable the sys_clone3 syscall for RV64. We simply include the generic version. Tested by running the program from https://lore.kernel.org/lkml/20190716130631.tohj4ub54md25dys@brauner.io/ and verifying that it completes successfully. Signed-off-by: Paul Walmsley Acked-by: Christian Brauner Cc: Christian Brauner --- arch/riscv/include/uapi/asm/unistd.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h index 0e2eeeb1fd27..13ce76cc5aff 100644 --- a/arch/riscv/include/uapi/asm/unistd.h +++ b/arch/riscv/include/uapi/asm/unistd.h @@ -18,6 +18,7 @@ #ifdef __LP64__ #define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SET_GET_RLIMIT +#define __ARCH_WANT_SYS_CLONE3 #endif /* __LP64__ */ #include From b4fc36e60f25cf22bf8b7b015a701015740c3743 Mon Sep 17 00:00:00 2001 From: Shawn Anastasio Date: Wed, 17 Jul 2019 18:54:37 -0500 Subject: [PATCH 111/823] powerpc/dma: Fix invalid DMA mmap behavior The refactor of powerpc DMA functions in commit 6666cc17d780 ("powerpc/dma: remove dma_nommu_mmap_coherent") incorrectly changes the way DMA mappings are handled on powerpc. Since this change, all mapped pages are marked as cache-inhibited through the default implementation of arch_dma_mmap_pgprot. This differs from the previous behavior of only marking pages in noncoherent mappings as cache-inhibited and has resulted in sporadic system crashes in certain hardware configurations and workloads (see Bugzilla). This commit restores the previous correct behavior by providing an implementation of arch_dma_mmap_pgprot that only marks pages in noncoherent mappings as cache-inhibited. As this behavior should be universal for all powerpc platforms a new file, dma-generic.c, was created to store it. Fixes: 6666cc17d780 ("powerpc/dma: remove dma_nommu_mmap_coherent") # NOTE: fixes commit 6666cc17d780 released in v5.1. # Consider a stable tag: # Cc: stable@vger.kernel.org # v5.1+ # NOTE: fixes commit 6666cc17d780 released in v5.1. # Consider a stable tag: # Cc: stable@vger.kernel.org # v5.1+ Cc: stable@vger.kernel.org # v5.1+ Signed-off-by: Shawn Anastasio Reviewed-by: Alexey Kardashevskiy Reviewed-by: Christoph Hellwig Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190717235437.12908-1-shawn@anastas.io --- arch/powerpc/Kconfig | 1 + arch/powerpc/kernel/Makefile | 3 ++- arch/powerpc/kernel/dma-common.c | 17 +++++++++++++++++ 3 files changed, 20 insertions(+), 1 deletion(-) create mode 100644 arch/powerpc/kernel/dma-common.c diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index f516796dd819..5c96d3c948cd 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -121,6 +121,7 @@ config PPC select ARCH_32BIT_OFF_T if PPC32 select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEVMEM_IS_ALLOWED + select ARCH_HAS_DMA_MMAP_PGPROT select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 56dfa7a2a6f2..ea0c69236789 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -49,7 +49,8 @@ obj-y := cputable.o ptrace.o syscalls.o \ signal.o sysfs.o cacheinfo.o time.o \ prom.o traps.o setup-common.o \ udbg.o misc.o io.o misc_$(BITS).o \ - of_platform.o prom_parse.o + of_platform.o prom_parse.o \ + dma-common.o obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ signal_64.o ptrace32.o \ paca.o nvram_64.o firmware.o diff --git a/arch/powerpc/kernel/dma-common.c b/arch/powerpc/kernel/dma-common.c new file mode 100644 index 000000000000..dc7ef6b17b69 --- /dev/null +++ b/arch/powerpc/kernel/dma-common.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Contains common dma routines for all powerpc platforms. + * + * Copyright (C) 2019 Shawn Anastasio. + */ + +#include +#include + +pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, + unsigned long attrs) +{ + if (!dev_is_dma_coherent(dev)) + return pgprot_noncached(prot); + return prot; +} From d6f0f2f19a9e41bd0bcd5757f68500ed29352509 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 18 Jul 2019 16:13:48 -0300 Subject: [PATCH 112/823] docs: load_config.py: ensure subdirs end with "/" The logic with seeks for a subdir passed via SPHINXDIRS is incomplete: if one uses something like: make SPHINXDIRS=arm pdfdocs It will find both "arm" and "arm64" directories. Worse than that, it will convert "arm64/index" to "4/index". Signed-off-by: Mauro Carvalho Chehab --- Documentation/sphinx/load_config.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/sphinx/load_config.py b/Documentation/sphinx/load_config.py index 101e6f0b0fcf..eeb394b39e2c 100644 --- a/Documentation/sphinx/load_config.py +++ b/Documentation/sphinx/load_config.py @@ -35,7 +35,7 @@ def loadConfig(namespace): latex_documents = namespace['latex_documents'] for l in latex_documents: - if l[0].find(dir) == 0: + if l[0].find(dir + '/') == 0: has = True fn = l[0][len(dir) + 1:] new_latex_docs.append((fn, l[1], l[2], l[3], l[4])) From 0e279dcea0ec897af1c979ebee4ec92b461793f5 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 19 Jul 2019 10:55:05 +0200 Subject: [PATCH 113/823] ALSA: pcm: Fix refcount_inc() on zero usage The recent rewrite of PCM link lock management introduced the refcount in snd_pcm_group object, managed by the kernel refcount_t API. This caused unexpected kernel warnings when the kernel is built with CONFIG_REFCOUNT_FULL=y. As the warning line indicates, the problem is obviously that we start with refcount=0 and do refcount_inc() for adding each PCM link, while refcount_t API doesn't like refcount_inc() performed on zero. For adapting the proper refcount_t usage, this patch changes the logic slightly: - The initial refcount is 1, assuming the single list entry - The refcount is incremented / decremented at each PCM link addition and deletion - ... which allows us concentrating only on the refcount as a release condition Fixes: f57f3df03a8e ("ALSA: pcm: More fine-grained PCM link locking") BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=204221 Reported-and-tested-by: Duncan Overbruck Cc: Signed-off-by: Takashi Iwai --- sound/core/pcm_native.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 860543a4c840..12dd9b318db1 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -77,7 +77,7 @@ void snd_pcm_group_init(struct snd_pcm_group *group) spin_lock_init(&group->lock); mutex_init(&group->mutex); INIT_LIST_HEAD(&group->substreams); - refcount_set(&group->refs, 0); + refcount_set(&group->refs, 1); } /* define group lock helpers */ @@ -1096,8 +1096,7 @@ static void snd_pcm_group_unref(struct snd_pcm_group *group, if (!group) return; - do_free = refcount_dec_and_test(&group->refs) && - list_empty(&group->substreams); + do_free = refcount_dec_and_test(&group->refs); snd_pcm_group_unlock(group, substream->pcm->nonatomic); if (do_free) kfree(group); @@ -2020,6 +2019,7 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) snd_pcm_group_lock_irq(target_group, nonatomic); snd_pcm_stream_lock(substream1); snd_pcm_group_assign(substream1, target_group); + refcount_inc(&target_group->refs); snd_pcm_stream_unlock(substream1); snd_pcm_group_unlock_irq(target_group, nonatomic); _end: @@ -2056,13 +2056,14 @@ static int snd_pcm_unlink(struct snd_pcm_substream *substream) snd_pcm_group_lock_irq(group, nonatomic); relink_to_local(substream); + refcount_dec(&group->refs); /* detach the last stream, too */ if (list_is_singular(&group->substreams)) { relink_to_local(list_first_entry(&group->substreams, struct snd_pcm_substream, link_list)); - do_free = !refcount_read(&group->refs); + do_free = refcount_dec_and_test(&group->refs); } snd_pcm_group_unlock_irq(group, nonatomic); From 04efe5911fb30664a56ec63d272a0f39a71545db Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 19 Jul 2019 12:32:42 -0700 Subject: [PATCH 114/823] libbpf: fix SIGSEGV when BTF loading fails, but .BTF.ext exists In case when BTF loading fails despite sanitization, but BPF object has .BTF.ext loaded as well, we free and null obj->btf, but not obj->btf_ext. This leads to an attempt to relocate .BTF.ext later on during bpf_object__load(), which assumes obj->btf is present. This leads to SIGSEGV on null pointer access. Fix bug by freeing and nulling obj->btf_ext as well. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/libbpf.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 794dd5064ae8..87168f21ef43 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1500,6 +1500,12 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) BTF_ELF_SEC, err); btf__free(obj->btf); obj->btf = NULL; + /* btf_ext can't exist without btf, so free it as well */ + if (obj->btf_ext) { + btf_ext__free(obj->btf_ext); + obj->btf_ext = NULL; + } + if (bpf_object__is_btf_mandatory(obj)) return err; } From 1d4126c4e1190d2f7d3f388552f9bd17ae0c64fc Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 19 Jul 2019 12:46:03 -0700 Subject: [PATCH 115/823] libbpf: sanitize VAR to conservative 1-byte INT If VAR in non-sanitized BTF was size less than 4, converting such VAR into an INT with size=4 will cause BTF validation failure due to violationg of STRUCT (into which DATASEC was converted) member size. Fix by conservatively using size=1. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/libbpf.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 87168f21ef43..d8833ff6c4a1 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1377,8 +1377,13 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) if (!has_datasec && kind == BTF_KIND_VAR) { /* replace VAR with INT */ t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); - t->size = sizeof(int); - *(int *)(t+1) = BTF_INT_ENC(0, 0, 32); + /* + * using size = 1 is the safest choice, 4 will be too + * big and cause kernel BTF validation failure if + * original variable took less than 4 bytes + */ + t->size = 1; + *(int *)(t+1) = BTF_INT_ENC(0, 0, 8); } else if (!has_datasec && kind == BTF_KIND_DATASEC) { /* replace DATASEC with STRUCT */ struct btf_var_secinfo *v = (void *)(t + 1); From 94bccc34071094c165c79b515d21b63c78f7e968 Mon Sep 17 00:00:00 2001 From: Thomas Tai Date: Thu, 18 Jul 2019 18:37:34 +0000 Subject: [PATCH 116/823] iscsi_ibft: make ISCSI_IBFT dependson ACPI instead of ISCSI_IBFT_FIND iscsi_ibft can use ACPI to find the iBFT entry during bootup, currently, ISCSI_IBFT depends on ISCSI_IBFT_FIND which is a X86 legacy way to find the iBFT by searching through the low memory. This patch changes the dependency so that other arch like ARM64 can use ISCSI_IBFT as long as the arch supports ACPI. ibft_init() needs to use the global variable ibft_addr declared in iscsi_ibft_find.c. A #ifndef CONFIG_ISCSI_IBFT_FIND is needed to declare the variable if CONFIG_ISCSI_IBFT_FIND is not selected. Moving ibft_addr into the iscsi_ibft.c does not work because if ISCSI_IBFT is selected as a module, the arch/x86/kernel/setup.c won't be able to find the variable at compile time. Signed-off-by: Thomas Tai Signed-off-by: Konrad Rzeszutek Wilk --- drivers/firmware/Kconfig | 5 +++-- drivers/firmware/iscsi_ibft.c | 4 ++++ 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index f754578414f0..f028218815c6 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -170,7 +170,7 @@ config DMI_SCAN_MACHINE_NON_EFI_FALLBACK config ISCSI_IBFT_FIND bool "iSCSI Boot Firmware Table Attributes" - depends on X86 && ACPI + depends on X86 && ISCSI_IBFT default n help This option enables the kernel to find the region of memory @@ -181,7 +181,8 @@ config ISCSI_IBFT_FIND config ISCSI_IBFT tristate "iSCSI Boot Firmware Table Attributes module" select ISCSI_BOOT_SYSFS - depends on ISCSI_IBFT_FIND && SCSI && SCSI_LOWLEVEL + select ISCSI_IBFT_FIND if X86 + depends on ACPI && SCSI && SCSI_LOWLEVEL default n help This option enables support for detection and exposing of iSCSI diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c index c51462f5aa1e..966aef334c42 100644 --- a/drivers/firmware/iscsi_ibft.c +++ b/drivers/firmware/iscsi_ibft.c @@ -93,6 +93,10 @@ MODULE_DESCRIPTION("sysfs interface to BIOS iBFT information"); MODULE_LICENSE("GPL"); MODULE_VERSION(IBFT_ISCSI_VERSION); +#ifndef CONFIG_ISCSI_IBFT_FIND +struct acpi_table_ibft *ibft_addr; +#endif + struct ibft_hdr { u8 id; u8 version; From f5e03d3a04978d2866f82cb11cc7a6b808c8ce07 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Sun, 21 Jul 2019 11:00:39 +0200 Subject: [PATCH 117/823] parisc: add kprobe_fault_handler() Add kprobe_fault_handler() to fix compilation for PA-RISC. On PA-RISC we actually don't need that function as the recovery counter is restored after interrupt. See the PA-RISC 2.0 Architecture Manual, pg. 4-8, Figure 4-4: "Interruption Processing". Fixes: b98cca444d28 ("mm, kprobes: generalize and rename notify_page_fault() as kprobe_page_fault()") Signed-off-by: Sven Schnelle Signed-off-by: Helge Deller --- arch/parisc/include/asm/kprobes.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/parisc/include/asm/kprobes.h b/arch/parisc/include/asm/kprobes.h index e09cf2deeafe..904034da4974 100644 --- a/arch/parisc/include/asm/kprobes.h +++ b/arch/parisc/include/asm/kprobes.h @@ -50,6 +50,10 @@ struct kprobe_ctlblk { int __kprobes parisc_kprobe_break_handler(struct pt_regs *regs); int __kprobes parisc_kprobe_ss_handler(struct pt_regs *regs); +static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) +{ + return 0; +} #endif /* CONFIG_KPROBES */ #endif /* _PARISC_KPROBES_H */ From 69245c97560b40f88c609b078f4b51c5be81d88b Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 21 Jul 2019 00:55:48 +0200 Subject: [PATCH 118/823] parisc: Flush ITLB in flush_tlb_all_local() only on split TLB machines flush_tlb_all_local() flushes the ITLB and DTLB of the CPU. In case the machine does not have separate ITLBs and DTLBs, use the alternative functionality to replace the code which flushes the ITLB with nops while keeping the code which flushes the DTLB. Signed-off-by: Helge Deller --- arch/parisc/kernel/pacache.S | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S index ba67893a1d72..df46b0e5a915 100644 --- a/arch/parisc/kernel/pacache.S +++ b/arch/parisc/kernel/pacache.S @@ -63,7 +63,7 @@ ENTRY_CFI(flush_tlb_all_local) /* Flush Instruction Tlb */ - LDREG ITLB_SID_BASE(%r1), %r20 +88: LDREG ITLB_SID_BASE(%r1), %r20 LDREG ITLB_SID_STRIDE(%r1), %r21 LDREG ITLB_SID_COUNT(%r1), %r22 LDREG ITLB_OFF_BASE(%r1), %arg0 @@ -103,6 +103,7 @@ fitonemiddle: /* Loop if LOOP = 1 */ add %r21, %r20, %r20 /* increment space */ fitdone: + ALTERNATIVE(88b, fitdone, ALT_COND_NO_SPLIT_TLB, INSN_NOP) /* Flush Data Tlb */ From 15a78ba1844a8e052c1226f930133de4cef4e7ad Mon Sep 17 00:00:00 2001 From: Wenwen Wang Date: Sat, 20 Jul 2019 07:22:45 -0500 Subject: [PATCH 119/823] netfilter: ebtables: fix a memory leak bug in compat In compat_do_replace(), a temporary buffer is allocated through vmalloc() to hold entries copied from the user space. The buffer address is firstly saved to 'newinfo->entries', and later on assigned to 'entries_tmp'. Then the entries in this temporary buffer is copied to the internal kernel structure through compat_copy_entries(). If this copy process fails, compat_do_replace() should be terminated. However, the allocated temporary buffer is not freed on this path, leading to a memory leak. To fix the bug, free the buffer before returning from compat_do_replace(). Signed-off-by: Wenwen Wang Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/ebtables.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 963dfdc14827..fd84b48e48b5 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2261,8 +2261,10 @@ static int compat_do_replace(struct net *net, void __user *user, state.buf_kern_len = size64; ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); - if (WARN_ON(ret < 0)) + if (WARN_ON(ret < 0)) { + vfree(entries_tmp); goto out_unlock; + } vfree(entries_tmp); tmp.entries_size = size64; From 6e998ef24d603839c29a8f75a31d176142786e03 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Tue, 25 Jun 2019 12:40:00 -0300 Subject: [PATCH 120/823] ARM: dts: imx7ulp: Fix usb-phy unit address format The following warning is seen when building with W=1: arch/arm/boot/dts/imx7ulp.dtsi:189.31-195.5: Warning (simple_bus_reg): /bus@40000000/usb-phy@0x40350000: simple-bus unit address format error, expected "40350000" Fix it as suggested by removing the extra "0x" notation. Fixes: 5b7bd456318a ("ARM: dts: imx7ulp: add imx7ulp USBOTG1 support") Signed-off-by: Fabio Estevam Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx7ulp.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx7ulp.dtsi b/arch/arm/boot/dts/imx7ulp.dtsi index 992747a57442..56907bb4b329 100644 --- a/arch/arm/boot/dts/imx7ulp.dtsi +++ b/arch/arm/boot/dts/imx7ulp.dtsi @@ -186,7 +186,7 @@ reg = <0x40330200 0x200>; }; - usbphy1: usb-phy@0x40350000 { + usbphy1: usb-phy@40350000 { compatible = "fsl,imx7ulp-usbphy", "fsl,imx6ul-usbphy"; reg = <0x40350000 0x1000>; interrupts = ; From 211186cae14de09573b062e478eb9fe215aed8d9 Mon Sep 17 00:00:00 2001 From: Lei YU Date: Thu, 11 Jul 2019 10:44:48 +0800 Subject: [PATCH 121/823] hwmon: (occ) Fix division by zero issue The code in occ_get_powr_avg() invokes div64_u64() without checking the divisor. In case the divisor is zero, kernel gets an "Division by zero in kernel" error. Check the divisor and make it return 0 if the divisor is 0. Fixes: c10e753d43eb ("hwmon (occ): Add sensor types and versions") Signed-off-by: Lei YU Reviewed-by: Eddie James Link: https://lore.kernel.org/r/1562813088-23708-1-git-send-email-mine260309@gmail.com Signed-off-by: Guenter Roeck --- drivers/hwmon/occ/common.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c index a7d2b16dd702..30e18eb60da7 100644 --- a/drivers/hwmon/occ/common.c +++ b/drivers/hwmon/occ/common.c @@ -408,8 +408,10 @@ static ssize_t occ_show_power_1(struct device *dev, static u64 occ_get_powr_avg(u64 *accum, u32 *samples) { - return div64_u64(get_unaligned_be64(accum) * 1000000ULL, - get_unaligned_be32(samples)); + u64 divisor = get_unaligned_be32(samples); + + return (divisor == 0) ? 0 : + div64_u64(get_unaligned_be64(accum) * 1000000ULL, divisor); } static ssize_t occ_show_power_2(struct device *dev, From f3d43e2e45fd9d44ba52d20debd12cd4ee9c89bf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20Gerhart?= Date: Mon, 15 Jul 2019 18:33:55 +0200 Subject: [PATCH 122/823] hwmon: (nct6775) Fix register address and added missed tolerance for nct6106 Fixed address of third NCT6106_REG_WEIGHT_DUTY_STEP, and added missed NCT6106_REG_TOLERANCE_H. Fixes: 6c009501ff200 ("hwmon: (nct6775) Add support for NCT6102D/6106D") Signed-off-by: Bjoern Gerhart Signed-off-by: Guenter Roeck --- drivers/hwmon/nct6775.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index e7dff5febe16..d42bc0883a32 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -852,7 +852,7 @@ static const u16 NCT6106_REG_TARGET[] = { 0x111, 0x121, 0x131 }; static const u16 NCT6106_REG_WEIGHT_TEMP_SEL[] = { 0x168, 0x178, 0x188 }; static const u16 NCT6106_REG_WEIGHT_TEMP_STEP[] = { 0x169, 0x179, 0x189 }; static const u16 NCT6106_REG_WEIGHT_TEMP_STEP_TOL[] = { 0x16a, 0x17a, 0x18a }; -static const u16 NCT6106_REG_WEIGHT_DUTY_STEP[] = { 0x16b, 0x17b, 0x17c }; +static const u16 NCT6106_REG_WEIGHT_DUTY_STEP[] = { 0x16b, 0x17b, 0x18b }; static const u16 NCT6106_REG_WEIGHT_TEMP_BASE[] = { 0x16c, 0x17c, 0x18c }; static const u16 NCT6106_REG_WEIGHT_DUTY_BASE[] = { 0x16d, 0x17d, 0x18d }; @@ -3764,6 +3764,7 @@ static int nct6775_probe(struct platform_device *pdev) data->REG_FAN_TIME[0] = NCT6106_REG_FAN_STOP_TIME; data->REG_FAN_TIME[1] = NCT6106_REG_FAN_STEP_UP_TIME; data->REG_FAN_TIME[2] = NCT6106_REG_FAN_STEP_DOWN_TIME; + data->REG_TOLERANCE_H = NCT6106_REG_TOLERANCE_H; data->REG_PWM[0] = NCT6106_REG_PWM; data->REG_PWM[1] = NCT6106_REG_FAN_START_OUTPUT; data->REG_PWM[2] = NCT6106_REG_FAN_STOP_OUTPUT; From 223b2b5030f370f219c23c2c4678b419a72434d9 Mon Sep 17 00:00:00 2001 From: Robert Karszniewicz Date: Sat, 20 Jul 2019 15:16:52 +0200 Subject: [PATCH 123/823] hwmon: (k8temp) documentation: update URL of datasheet The old URL is dead. Signed-off-by: Robert Karszniewicz Link: https://lore.kernel.org/r/7139bc7707c24bd4dd7eb323e2da90105a3de9c1.1563522498.git.avoidr@firemail.cc Signed-off-by: Guenter Roeck --- Documentation/hwmon/k8temp.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/hwmon/k8temp.rst b/Documentation/hwmon/k8temp.rst index 72da12aa17e5..fe9109521056 100644 --- a/Documentation/hwmon/k8temp.rst +++ b/Documentation/hwmon/k8temp.rst @@ -9,7 +9,7 @@ Supported chips: Addresses scanned: PCI space - Datasheet: http://support.amd.com/us/Processor_TechDocs/32559.pdf + Datasheet: http://www.amd.com/system/files/TechDocs/32559.pdf Author: Rudolf Marek From ae00fcc51e714ce0fc72382332147ffffcf9a883 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 22 Jul 2019 00:41:57 +0200 Subject: [PATCH 124/823] ARM: Delete netx a second time Commit ceb02dcf676f ARM: delete netx machine deleted the mach-netx machine. Then eight days later it was resurrected by SPDX tag fixes. I think. Taking the liberty to fix some additional debug uart cruft. Link: https://lore.kernel.org/r/20190721224157.6597-1-linus.walleij@linaro.org Fixes: ceb02dcf676f ("ARM: delete netx machine") Acked-By: Robert Schwebel Acked-by: Sascha Hauer Signed-off-by: Linus Walleij Signed-off-by: Olof Johansson --- arch/arm/Kconfig.debug | 5 - arch/arm/mach-netx/Kconfig | 22 - arch/arm/mach-netx/Makefile | 13 - arch/arm/mach-netx/Makefile.boot | 3 - arch/arm/mach-netx/fb.c | 65 --- arch/arm/mach-netx/fb.h | 12 - arch/arm/mach-netx/generic.c | 182 -------- arch/arm/mach-netx/generic.h | 14 - arch/arm/mach-netx/include/mach/hardware.h | 27 -- arch/arm/mach-netx/include/mach/irqs.h | 58 --- arch/arm/mach-netx/include/mach/netx-regs.h | 420 ------------------- arch/arm/mach-netx/include/mach/pfifo.h | 42 -- arch/arm/mach-netx/include/mach/uncompress.h | 63 --- arch/arm/mach-netx/include/mach/xc.h | 30 -- arch/arm/mach-netx/nxdb500.c | 197 --------- arch/arm/mach-netx/nxdkn.c | 90 ---- arch/arm/mach-netx/nxeb500hmi.c | 174 -------- arch/arm/mach-netx/pfifo.c | 56 --- arch/arm/mach-netx/time.c | 141 ------- arch/arm/mach-netx/xc.c | 246 ----------- 20 files changed, 1860 deletions(-) delete mode 100644 arch/arm/mach-netx/Kconfig delete mode 100644 arch/arm/mach-netx/Makefile delete mode 100644 arch/arm/mach-netx/Makefile.boot delete mode 100644 arch/arm/mach-netx/fb.c delete mode 100644 arch/arm/mach-netx/fb.h delete mode 100644 arch/arm/mach-netx/generic.c delete mode 100644 arch/arm/mach-netx/generic.h delete mode 100644 arch/arm/mach-netx/include/mach/hardware.h delete mode 100644 arch/arm/mach-netx/include/mach/irqs.h delete mode 100644 arch/arm/mach-netx/include/mach/netx-regs.h delete mode 100644 arch/arm/mach-netx/include/mach/pfifo.h delete mode 100644 arch/arm/mach-netx/include/mach/uncompress.h delete mode 100644 arch/arm/mach-netx/include/mach/xc.h delete mode 100644 arch/arm/mach-netx/nxdb500.c delete mode 100644 arch/arm/mach-netx/nxdkn.c delete mode 100644 arch/arm/mach-netx/nxeb500hmi.c delete mode 100644 arch/arm/mach-netx/pfifo.c delete mode 100644 arch/arm/mach-netx/time.c delete mode 100644 arch/arm/mach-netx/xc.c diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index c929bea9a9ff..85710e078afb 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -1535,7 +1535,6 @@ config DEBUG_LL_INCLUDE DEBUG_IMX7D_UART default "debug/ks8695.S" if DEBUG_KS8695_UART default "debug/msm.S" if DEBUG_QCOM_UARTDM - default "debug/netx.S" if DEBUG_NETX_UART default "debug/omap2plus.S" if DEBUG_OMAP2PLUS_UART default "debug/renesas-scif.S" if DEBUG_R7S72100_SCIF2 default "debug/renesas-scif.S" if DEBUG_RCAR_GEN1_SCIF0 @@ -1575,7 +1574,6 @@ config DEBUG_UART_8250 config DEBUG_UART_PHYS hex "Physical base address of debug UART" - default 0x00100a00 if DEBUG_NETX_UART default 0x01c20000 if DEBUG_DAVINCI_DMx_UART0 default 0x01c28000 if DEBUG_SUNXI_UART0 default 0x01c28400 if DEBUG_SUNXI_UART1 @@ -1700,7 +1698,6 @@ config DEBUG_UART_PHYS DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \ DEBUG_LL_UART_EFM32 || \ DEBUG_UART_8250 || DEBUG_UART_PL01X || DEBUG_MESON_UARTAO || \ - DEBUG_NETX_UART || \ DEBUG_QCOM_UARTDM || DEBUG_R7S72100_SCIF2 || \ DEBUG_RCAR_GEN1_SCIF0 || DEBUG_RCAR_GEN1_SCIF2 || \ DEBUG_RCAR_GEN2_SCIF0 || DEBUG_RCAR_GEN2_SCIF1 || \ @@ -1717,7 +1714,6 @@ config DEBUG_UART_VIRT default 0xc881f000 if DEBUG_RV1108_UART2 default 0xc8821000 if DEBUG_RV1108_UART1 default 0xc8912000 if DEBUG_RV1108_UART0 - default 0xe0000a00 if DEBUG_NETX_UART default 0xe0010fe0 if ARCH_RPC default 0xf0000be0 if ARCH_EBSA110 default 0xf0010000 if DEBUG_ASM9260_UART @@ -1822,7 +1818,6 @@ config DEBUG_UART_VIRT default DEBUG_UART_PHYS if !MMU depends on DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \ DEBUG_UART_8250 || DEBUG_UART_PL01X || DEBUG_MESON_UARTAO || \ - DEBUG_NETX_UART || \ DEBUG_QCOM_UARTDM || DEBUG_S3C24XX_UART || \ DEBUG_S3C64XX_UART || \ DEBUG_BCM63XX_UART || DEBUG_ASM9260_UART || \ diff --git a/arch/arm/mach-netx/Kconfig b/arch/arm/mach-netx/Kconfig deleted file mode 100644 index 1e5d9c870784..000000000000 --- a/arch/arm/mach-netx/Kconfig +++ /dev/null @@ -1,22 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -menu "NetX Implementations" - depends on ARCH_NETX - -config MACH_NXDKN - bool "Enable Hilscher nxdkn Eval Board support" - help - Board support for the Hilscher NetX Eval Board - -config MACH_NXDB500 - bool "Enable Hilscher nxdb500 Eval Board support" - select ARM_AMBA - help - Board support for the Hilscher nxdb500 Eval Board - -config MACH_NXEB500HMI - bool "Enable Hilscher nxeb500hmi Eval Board support" - select ARM_AMBA - help - Board support for the Hilscher nxeb500hmi Eval Board - -endmenu diff --git a/arch/arm/mach-netx/Makefile b/arch/arm/mach-netx/Makefile deleted file mode 100644 index 44ea83f7d9c2..000000000000 --- a/arch/arm/mach-netx/Makefile +++ /dev/null @@ -1,13 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -# Makefile for the linux kernel. -# - -# Object file lists. - -obj-y += time.o generic.o pfifo.o xc.o - -# Specific board support -obj-$(CONFIG_MACH_NXDKN) += nxdkn.o -obj-$(CONFIG_MACH_NXDB500) += nxdb500.o fb.o -obj-$(CONFIG_MACH_NXEB500HMI) += nxeb500hmi.o fb.o diff --git a/arch/arm/mach-netx/Makefile.boot b/arch/arm/mach-netx/Makefile.boot deleted file mode 100644 index 2eb23c0cb6b0..000000000000 --- a/arch/arm/mach-netx/Makefile.boot +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only - zreladdr-y += 0x80008000 - diff --git a/arch/arm/mach-netx/fb.c b/arch/arm/mach-netx/fb.c deleted file mode 100644 index 2dc80db07390..000000000000 --- a/arch/arm/mach-netx/fb.c +++ /dev/null @@ -1,65 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/fb.c - * - * Copyright (c) 2005 Sascha Hauer , Pengutronix - */ - -#include -#include -#include -#include -#include -#include -#include - -#include - -#include -#include - -static struct clcd_panel *netx_panel; - -void netx_clcd_enable(struct clcd_fb *fb) -{ -} - -int netx_clcd_setup(struct clcd_fb *fb) -{ - dma_addr_t dma; - - fb->panel = netx_panel; - - fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, 1024 * 1024, &dma, - GFP_KERNEL); - if (!fb->fb.screen_base) { - printk(KERN_ERR "CLCD: unable to map framebuffer\n"); - return -ENOMEM; - } - - fb->fb.fix.smem_start = dma; - fb->fb.fix.smem_len = 1024*1024; - - return 0; -} - -int netx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma) -{ - return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base, - fb->fb.fix.smem_start, fb->fb.fix.smem_len); -} - -void netx_clcd_remove(struct clcd_fb *fb) -{ - dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base, - fb->fb.fix.smem_start); -} - -static AMBA_AHB_DEVICE(fb, "fb", 0, 0x00104000, { NETX_IRQ_LCD }, NULL); - -int netx_fb_init(struct clcd_board *board, struct clcd_panel *panel) -{ - netx_panel = panel; - fb_device.dev.platform_data = board; - return amba_device_register(&fb_device, &iomem_resource); -} diff --git a/arch/arm/mach-netx/fb.h b/arch/arm/mach-netx/fb.h deleted file mode 100644 index 5cdc01fc3c86..000000000000 --- a/arch/arm/mach-netx/fb.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm/mach-netx/fb.h - * - * Copyright (c) 2005 Sascha Hauer , Pengutronix - */ - -void netx_clcd_enable(struct clcd_fb *fb); -int netx_clcd_setup(struct clcd_fb *fb); -int netx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma); -void netx_clcd_remove(struct clcd_fb *fb); -int netx_fb_init(struct clcd_board *board, struct clcd_panel *panel); diff --git a/arch/arm/mach-netx/generic.c b/arch/arm/mach-netx/generic.c deleted file mode 100644 index 88881fd45e9f..000000000000 --- a/arch/arm/mach-netx/generic.c +++ /dev/null @@ -1,182 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/generic.c - * - * Copyright (C) 2005 Sascha Hauer , Pengutronix - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static struct map_desc netx_io_desc[] __initdata = { - { - .virtual = NETX_IO_VIRT, - .pfn = __phys_to_pfn(NETX_IO_PHYS), - .length = NETX_IO_SIZE, - .type = MT_DEVICE - } -}; - -void __init netx_map_io(void) -{ - iotable_init(netx_io_desc, ARRAY_SIZE(netx_io_desc)); -} - -static struct resource netx_rtc_resources[] = { - [0] = { - .start = 0x00101200, - .end = 0x00101220, - .flags = IORESOURCE_MEM, - }, -}; - -static struct platform_device netx_rtc_device = { - .name = "netx-rtc", - .id = 0, - .num_resources = ARRAY_SIZE(netx_rtc_resources), - .resource = netx_rtc_resources, -}; - -static struct platform_device *devices[] __initdata = { - &netx_rtc_device, -}; - -#if 0 -#define DEBUG_IRQ(fmt...) printk(fmt) -#else -#define DEBUG_IRQ(fmt...) while (0) {} -#endif - -static void netx_hif_demux_handler(struct irq_desc *desc) -{ - unsigned int irq = NETX_IRQ_HIF_CHAINED(0); - unsigned int stat; - - stat = ((readl(NETX_DPMAS_INT_EN) & - readl(NETX_DPMAS_INT_STAT)) >> 24) & 0x1f; - - while (stat) { - if (stat & 1) { - DEBUG_IRQ("handling irq %d\n", irq); - generic_handle_irq(irq); - } - irq++; - stat >>= 1; - } -} - -static int -netx_hif_irq_type(struct irq_data *d, unsigned int type) -{ - unsigned int val, irq; - - val = readl(NETX_DPMAS_IF_CONF1); - - irq = d->irq - NETX_IRQ_HIF_CHAINED(0); - - if (type & IRQ_TYPE_EDGE_RISING) { - DEBUG_IRQ("rising edges\n"); - val |= (1 << 26) << irq; - } - if (type & IRQ_TYPE_EDGE_FALLING) { - DEBUG_IRQ("falling edges\n"); - val &= ~((1 << 26) << irq); - } - if (type & IRQ_TYPE_LEVEL_LOW) { - DEBUG_IRQ("low level\n"); - val &= ~((1 << 26) << irq); - } - if (type & IRQ_TYPE_LEVEL_HIGH) { - DEBUG_IRQ("high level\n"); - val |= (1 << 26) << irq; - } - - writel(val, NETX_DPMAS_IF_CONF1); - - return 0; -} - -static void -netx_hif_ack_irq(struct irq_data *d) -{ - unsigned int val, irq; - - irq = d->irq - NETX_IRQ_HIF_CHAINED(0); - writel((1 << 24) << irq, NETX_DPMAS_INT_STAT); - - val = readl(NETX_DPMAS_INT_EN); - val &= ~((1 << 24) << irq); - writel(val, NETX_DPMAS_INT_EN); - - DEBUG_IRQ("%s: irq %d\n", __func__, d->irq); -} - -static void -netx_hif_mask_irq(struct irq_data *d) -{ - unsigned int val, irq; - - irq = d->irq - NETX_IRQ_HIF_CHAINED(0); - val = readl(NETX_DPMAS_INT_EN); - val &= ~((1 << 24) << irq); - writel(val, NETX_DPMAS_INT_EN); - DEBUG_IRQ("%s: irq %d\n", __func__, d->irq); -} - -static void -netx_hif_unmask_irq(struct irq_data *d) -{ - unsigned int val, irq; - - irq = d->irq - NETX_IRQ_HIF_CHAINED(0); - val = readl(NETX_DPMAS_INT_EN); - val |= (1 << 24) << irq; - writel(val, NETX_DPMAS_INT_EN); - DEBUG_IRQ("%s: irq %d\n", __func__, d->irq); -} - -static struct irq_chip netx_hif_chip = { - .irq_ack = netx_hif_ack_irq, - .irq_mask = netx_hif_mask_irq, - .irq_unmask = netx_hif_unmask_irq, - .irq_set_type = netx_hif_irq_type, -}; - -void __init netx_init_irq(void) -{ - int irq; - - vic_init(io_p2v(NETX_PA_VIC), NETX_IRQ_VIC_START, ~0, 0); - - for (irq = NETX_IRQ_HIF_CHAINED(0); irq <= NETX_IRQ_HIF_LAST; irq++) { - irq_set_chip_and_handler(irq, &netx_hif_chip, - handle_level_irq); - irq_clear_status_flags(irq, IRQ_NOREQUEST); - } - - writel(NETX_DPMAS_INT_EN_GLB_EN, NETX_DPMAS_INT_EN); - irq_set_chained_handler(NETX_IRQ_HIF, netx_hif_demux_handler); -} - -static int __init netx_init(void) -{ - return platform_add_devices(devices, ARRAY_SIZE(devices)); -} - -subsys_initcall(netx_init); - -void netx_restart(enum reboot_mode mode, const char *cmd) -{ - writel(NETX_SYSTEM_RES_CR_FIRMW_RES_EN | NETX_SYSTEM_RES_CR_FIRMW_RES, - NETX_SYSTEM_RES_CR); -} diff --git a/arch/arm/mach-netx/generic.h b/arch/arm/mach-netx/generic.h deleted file mode 100644 index 223e304574a5..000000000000 --- a/arch/arm/mach-netx/generic.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm/mach-netx/generic.h - * - * Copyright (c) 2005 Sascha Hauer , Pengutronix - */ - -#include - -extern void __init netx_map_io(void); -extern void __init netx_init_irq(void); -extern void netx_restart(enum reboot_mode, const char *); - -extern void netx_timer_init(void); diff --git a/arch/arm/mach-netx/include/mach/hardware.h b/arch/arm/mach-netx/include/mach/hardware.h deleted file mode 100644 index 84253993d1e0..000000000000 --- a/arch/arm/mach-netx/include/mach/hardware.h +++ /dev/null @@ -1,27 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm/mach-netx/include/mach/hardware.h - * - * Copyright (C) 2005 Sascha Hauer , Pengutronix - */ -#ifndef __ASM_ARCH_HARDWARE_H -#define __ASM_ARCH_HARDWARE_H - -#define NETX_IO_PHYS 0x00100000 -#define NETX_IO_VIRT 0xe0000000 -#define NETX_IO_SIZE 0x00100000 - -#define SRAM_INTERNAL_PHYS_0 0x00000 -#define SRAM_INTERNAL_PHYS_1 0x08000 -#define SRAM_INTERNAL_PHYS_2 0x10000 -#define SRAM_INTERNAL_PHYS_3 0x18000 -#define SRAM_INTERNAL_PHYS(no) ((no) * 0x8000) - -#define XPEC_MEM_SIZE 0x4000 -#define XMAC_MEM_SIZE 0x1000 -#define SRAM_MEM_SIZE 0x8000 - -#define io_p2v(x) IOMEM((x) - NETX_IO_PHYS + NETX_IO_VIRT) -#define io_v2p(x) ((x) - NETX_IO_VIRT + NETX_IO_PHYS) - -#endif diff --git a/arch/arm/mach-netx/include/mach/irqs.h b/arch/arm/mach-netx/include/mach/irqs.h deleted file mode 100644 index 540c92104fe8..000000000000 --- a/arch/arm/mach-netx/include/mach/irqs.h +++ /dev/null @@ -1,58 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm/mach-netx/include/mach/irqs.h - * - * Copyright (C) 2005 Sascha Hauer , Pengutronix - */ - -#define NETX_IRQ_VIC_START 64 -#define NETX_IRQ_SOFTINT (NETX_IRQ_VIC_START + 0) -#define NETX_IRQ_TIMER0 (NETX_IRQ_VIC_START + 1) -#define NETX_IRQ_TIMER1 (NETX_IRQ_VIC_START + 2) -#define NETX_IRQ_TIMER2 (NETX_IRQ_VIC_START + 3) -#define NETX_IRQ_SYSTIME_NS (NETX_IRQ_VIC_START + 4) -#define NETX_IRQ_SYSTIME_S (NETX_IRQ_VIC_START + 5) -#define NETX_IRQ_GPIO_15 (NETX_IRQ_VIC_START + 6) -#define NETX_IRQ_WATCHDOG (NETX_IRQ_VIC_START + 7) -#define NETX_IRQ_UART0 (NETX_IRQ_VIC_START + 8) -#define NETX_IRQ_UART1 (NETX_IRQ_VIC_START + 9) -#define NETX_IRQ_UART2 (NETX_IRQ_VIC_START + 10) -#define NETX_IRQ_USB (NETX_IRQ_VIC_START + 11) -#define NETX_IRQ_SPI (NETX_IRQ_VIC_START + 12) -#define NETX_IRQ_I2C (NETX_IRQ_VIC_START + 13) -#define NETX_IRQ_LCD (NETX_IRQ_VIC_START + 14) -#define NETX_IRQ_HIF (NETX_IRQ_VIC_START + 15) -#define NETX_IRQ_GPIO_0_14 (NETX_IRQ_VIC_START + 16) -#define NETX_IRQ_XPEC0 (NETX_IRQ_VIC_START + 17) -#define NETX_IRQ_XPEC1 (NETX_IRQ_VIC_START + 18) -#define NETX_IRQ_XPEC2 (NETX_IRQ_VIC_START + 19) -#define NETX_IRQ_XPEC3 (NETX_IRQ_VIC_START + 20) -#define NETX_IRQ_XPEC(no) (NETX_IRQ_VIC_START + 17 + (no)) -#define NETX_IRQ_MSYNC0 (NETX_IRQ_VIC_START + 21) -#define NETX_IRQ_MSYNC1 (NETX_IRQ_VIC_START + 22) -#define NETX_IRQ_MSYNC2 (NETX_IRQ_VIC_START + 23) -#define NETX_IRQ_MSYNC3 (NETX_IRQ_VIC_START + 24) -#define NETX_IRQ_IRQ_PHY (NETX_IRQ_VIC_START + 25) -#define NETX_IRQ_ISO_AREA (NETX_IRQ_VIC_START + 26) -/* int 27 is reserved */ -/* int 28 is reserved */ -#define NETX_IRQ_TIMER3 (NETX_IRQ_VIC_START + 29) -#define NETX_IRQ_TIMER4 (NETX_IRQ_VIC_START + 30) -/* int 31 is reserved */ - -#define NETX_IRQS (NETX_IRQ_VIC_START + 32) - -/* for multiplexed irqs on gpio 0..14 */ -#define NETX_IRQ_GPIO(x) (NETX_IRQS + (x)) -#define NETX_IRQ_GPIO_LAST NETX_IRQ_GPIO(14) - -/* Host interface interrupts */ -#define NETX_IRQ_HIF_CHAINED(x) (NETX_IRQ_GPIO_LAST + 1 + (x)) -#define NETX_IRQ_HIF_PIO35 NETX_IRQ_HIF_CHAINED(0) -#define NETX_IRQ_HIF_PIO36 NETX_IRQ_HIF_CHAINED(1) -#define NETX_IRQ_HIF_PIO40 NETX_IRQ_HIF_CHAINED(2) -#define NETX_IRQ_HIF_PIO47 NETX_IRQ_HIF_CHAINED(3) -#define NETX_IRQ_HIF_PIO72 NETX_IRQ_HIF_CHAINED(4) -#define NETX_IRQ_HIF_LAST NETX_IRQ_HIF_CHAINED(4) - -#define NR_IRQS (NETX_IRQ_HIF_LAST + 1) diff --git a/arch/arm/mach-netx/include/mach/netx-regs.h b/arch/arm/mach-netx/include/mach/netx-regs.h deleted file mode 100644 index 7c356a6ab80b..000000000000 --- a/arch/arm/mach-netx/include/mach/netx-regs.h +++ /dev/null @@ -1,420 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm/mach-netx/include/mach/netx-regs.h - * - * Copyright (c) 2005 Sascha Hauer , Pengutronix - */ - -#ifndef __ASM_ARCH_NETX_REGS_H -#define __ASM_ARCH_NETX_REGS_H - -/* offsets relative to the beginning of the io space */ -#define NETX_OFS_SYSTEM 0x00000 -#define NETX_OFS_MEMCR 0x00100 -#define NETX_OFS_DPMAS 0x03000 -#define NETX_OFS_GPIO 0x00800 -#define NETX_OFS_PIO 0x00900 -#define NETX_OFS_UART0 0x00a00 -#define NETX_OFS_UART1 0x00a40 -#define NETX_OFS_UART2 0x00a80 -#define NETX_OF_MIIMU 0x00b00 -#define NETX_OFS_SPI 0x00c00 -#define NETX_OFS_I2C 0x00d00 -#define NETX_OFS_SYSTIME 0x01100 -#define NETX_OFS_RTC 0x01200 -#define NETX_OFS_EXTBUS 0x03600 -#define NETX_OFS_LCD 0x04000 -#define NETX_OFS_USB 0x20000 -#define NETX_OFS_XMAC0 0x60000 -#define NETX_OFS_XMAC1 0x61000 -#define NETX_OFS_XMAC2 0x62000 -#define NETX_OFS_XMAC3 0x63000 -#define NETX_OFS_XMAC(no) (0x60000 + (no) * 0x1000) -#define NETX_OFS_PFIFO 0x64000 -#define NETX_OFS_XPEC0 0x70000 -#define NETX_OFS_XPEC1 0x74000 -#define NETX_OFS_XPEC2 0x78000 -#define NETX_OFS_XPEC3 0x7c000 -#define NETX_OFS_XPEC(no) (0x70000 + (no) * 0x4000) -#define NETX_OFS_VIC 0xff000 - -/* physical addresses */ -#define NETX_PA_SYSTEM (NETX_IO_PHYS + NETX_OFS_SYSTEM) -#define NETX_PA_MEMCR (NETX_IO_PHYS + NETX_OFS_MEMCR) -#define NETX_PA_DPMAS (NETX_IO_PHYS + NETX_OFS_DPMAS) -#define NETX_PA_GPIO (NETX_IO_PHYS + NETX_OFS_GPIO) -#define NETX_PA_PIO (NETX_IO_PHYS + NETX_OFS_PIO) -#define NETX_PA_UART0 (NETX_IO_PHYS + NETX_OFS_UART0) -#define NETX_PA_UART1 (NETX_IO_PHYS + NETX_OFS_UART1) -#define NETX_PA_UART2 (NETX_IO_PHYS + NETX_OFS_UART2) -#define NETX_PA_MIIMU (NETX_IO_PHYS + NETX_OF_MIIMU) -#define NETX_PA_SPI (NETX_IO_PHYS + NETX_OFS_SPI) -#define NETX_PA_I2C (NETX_IO_PHYS + NETX_OFS_I2C) -#define NETX_PA_SYSTIME (NETX_IO_PHYS + NETX_OFS_SYSTIME) -#define NETX_PA_RTC (NETX_IO_PHYS + NETX_OFS_RTC) -#define NETX_PA_EXTBUS (NETX_IO_PHYS + NETX_OFS_EXTBUS) -#define NETX_PA_LCD (NETX_IO_PHYS + NETX_OFS_LCD) -#define NETX_PA_USB (NETX_IO_PHYS + NETX_OFS_USB) -#define NETX_PA_XMAC0 (NETX_IO_PHYS + NETX_OFS_XMAC0) -#define NETX_PA_XMAC1 (NETX_IO_PHYS + NETX_OFS_XMAC1) -#define NETX_PA_XMAC2 (NETX_IO_PHYS + NETX_OFS_XMAC2) -#define NETX_PA_XMAC3 (NETX_IO_PHYS + NETX_OFS_XMAC3) -#define NETX_PA_XMAC(no) (NETX_IO_PHYS + NETX_OFS_XMAC(no)) -#define NETX_PA_PFIFO (NETX_IO_PHYS + NETX_OFS_PFIFO) -#define NETX_PA_XPEC0 (NETX_IO_PHYS + NETX_OFS_XPEC0) -#define NETX_PA_XPEC1 (NETX_IO_PHYS + NETX_OFS_XPEC1) -#define NETX_PA_XPEC2 (NETX_IO_PHYS + NETX_OFS_XPEC2) -#define NETX_PA_XPEC3 (NETX_IO_PHYS + NETX_OFS_XPEC3) -#define NETX_PA_XPEC(no) (NETX_IO_PHYS + NETX_OFS_XPEC(no)) -#define NETX_PA_VIC (NETX_IO_PHYS + NETX_OFS_VIC) - -/* virtual addresses */ -#define NETX_VA_SYSTEM (NETX_IO_VIRT + NETX_OFS_SYSTEM) -#define NETX_VA_MEMCR (NETX_IO_VIRT + NETX_OFS_MEMCR) -#define NETX_VA_DPMAS (NETX_IO_VIRT + NETX_OFS_DPMAS) -#define NETX_VA_GPIO (NETX_IO_VIRT + NETX_OFS_GPIO) -#define NETX_VA_PIO (NETX_IO_VIRT + NETX_OFS_PIO) -#define NETX_VA_UART0 (NETX_IO_VIRT + NETX_OFS_UART0) -#define NETX_VA_UART1 (NETX_IO_VIRT + NETX_OFS_UART1) -#define NETX_VA_UART2 (NETX_IO_VIRT + NETX_OFS_UART2) -#define NETX_VA_MIIMU (NETX_IO_VIRT + NETX_OF_MIIMU) -#define NETX_VA_SPI (NETX_IO_VIRT + NETX_OFS_SPI) -#define NETX_VA_I2C (NETX_IO_VIRT + NETX_OFS_I2C) -#define NETX_VA_SYSTIME (NETX_IO_VIRT + NETX_OFS_SYSTIME) -#define NETX_VA_RTC (NETX_IO_VIRT + NETX_OFS_RTC) -#define NETX_VA_EXTBUS (NETX_IO_VIRT + NETX_OFS_EXTBUS) -#define NETX_VA_LCD (NETX_IO_VIRT + NETX_OFS_LCD) -#define NETX_VA_USB (NETX_IO_VIRT + NETX_OFS_USB) -#define NETX_VA_XMAC0 (NETX_IO_VIRT + NETX_OFS_XMAC0) -#define NETX_VA_XMAC1 (NETX_IO_VIRT + NETX_OFS_XMAC1) -#define NETX_VA_XMAC2 (NETX_IO_VIRT + NETX_OFS_XMAC2) -#define NETX_VA_XMAC3 (NETX_IO_VIRT + NETX_OFS_XMAC3) -#define NETX_VA_XMAC(no) (NETX_IO_VIRT + NETX_OFS_XMAC(no)) -#define NETX_VA_PFIFO (NETX_IO_VIRT + NETX_OFS_PFIFO) -#define NETX_VA_XPEC0 (NETX_IO_VIRT + NETX_OFS_XPEC0) -#define NETX_VA_XPEC1 (NETX_IO_VIRT + NETX_OFS_XPEC1) -#define NETX_VA_XPEC2 (NETX_IO_VIRT + NETX_OFS_XPEC2) -#define NETX_VA_XPEC3 (NETX_IO_VIRT + NETX_OFS_XPEC3) -#define NETX_VA_XPEC(no) (NETX_IO_VIRT + NETX_OFS_XPEC(no)) -#define NETX_VA_VIC (NETX_IO_VIRT + NETX_OFS_VIC) - -/********************************* - * System functions * - *********************************/ - -/* Registers */ -#define NETX_SYSTEM_REG(ofs) IOMEM(NETX_VA_SYSTEM + (ofs)) -#define NETX_SYSTEM_BOO_SR NETX_SYSTEM_REG(0x00) -#define NETX_SYSTEM_IOC_CR NETX_SYSTEM_REG(0x04) -#define NETX_SYSTEM_IOC_MR NETX_SYSTEM_REG(0x08) - -/* FIXME: Docs are not consistent */ -/* #define NETX_SYSTEM_RES_CR NETX_SYSTEM_REG(0x08) */ -#define NETX_SYSTEM_RES_CR NETX_SYSTEM_REG(0x0c) - -#define NETX_SYSTEM_PHY_CONTROL NETX_SYSTEM_REG(0x10) -#define NETX_SYSTEM_REV NETX_SYSTEM_REG(0x34) -#define NETX_SYSTEM_IOC_ACCESS_KEY NETX_SYSTEM_REG(0x70) -#define NETX_SYSTEM_WDG_TR NETX_SYSTEM_REG(0x200) -#define NETX_SYSTEM_WDG_CTR NETX_SYSTEM_REG(0x204) -#define NETX_SYSTEM_WDG_IRQ_TIMEOUT NETX_SYSTEM_REG(0x208) -#define NETX_SYSTEM_WDG_RES_TIMEOUT NETX_SYSTEM_REG(0x20c) - -/* Bits */ -#define NETX_SYSTEM_RES_CR_RSTIN (1<<0) -#define NETX_SYSTEM_RES_CR_WDG_RES (1<<1) -#define NETX_SYSTEM_RES_CR_HOST_RES (1<<2) -#define NETX_SYSTEM_RES_CR_FIRMW_RES (1<<3) -#define NETX_SYSTEM_RES_CR_XPEC0_RES (1<<4) -#define NETX_SYSTEM_RES_CR_XPEC1_RES (1<<5) -#define NETX_SYSTEM_RES_CR_XPEC2_RES (1<<6) -#define NETX_SYSTEM_RES_CR_XPEC3_RES (1<<7) -#define NETX_SYSTEM_RES_CR_DIS_XPEC0_RES (1<<16) -#define NETX_SYSTEM_RES_CR_DIS_XPEC1_RES (1<<17) -#define NETX_SYSTEM_RES_CR_DIS_XPEC2_RES (1<<18) -#define NETX_SYSTEM_RES_CR_DIS_XPEC3_RES (1<<19) -#define NETX_SYSTEM_RES_CR_FIRMW_FLG0 (1<<20) -#define NETX_SYSTEM_RES_CR_FIRMW_FLG1 (1<<21) -#define NETX_SYSTEM_RES_CR_FIRMW_FLG2 (1<<22) -#define NETX_SYSTEM_RES_CR_FIRMW_FLG3 (1<<23) -#define NETX_SYSTEM_RES_CR_FIRMW_RES_EN (1<<24) -#define NETX_SYSTEM_RES_CR_RSTOUT (1<<25) -#define NETX_SYSTEM_RES_CR_EN_RSTOUT (1<<26) - -#define PHY_CONTROL_RESET (1<<31) -#define PHY_CONTROL_SIM_BYP (1<<30) -#define PHY_CONTROL_CLK_XLATIN (1<<29) -#define PHY_CONTROL_PHY1_EN (1<<21) -#define PHY_CONTROL_PHY1_NP_MSG_CODE -#define PHY_CONTROL_PHY1_AUTOMDIX (1<<17) -#define PHY_CONTROL_PHY1_FIXMODE (1<<16) -#define PHY_CONTROL_PHY1_MODE(mode) (((mode) & 0x7) << 13) -#define PHY_CONTROL_PHY0_EN (1<<12) -#define PHY_CONTROL_PHY0_NP_MSG_CODE -#define PHY_CONTROL_PHY0_AUTOMDIX (1<<8) -#define PHY_CONTROL_PHY0_FIXMODE (1<<7) -#define PHY_CONTROL_PHY0_MODE(mode) (((mode) & 0x7) << 4) -#define PHY_CONTROL_PHY_ADDRESS(adr) ((adr) & 0xf) - -#define PHY_MODE_10BASE_T_HALF 0 -#define PHY_MODE_10BASE_T_FULL 1 -#define PHY_MODE_100BASE_TX_FX_FULL 2 -#define PHY_MODE_100BASE_TX_FX_HALF 3 -#define PHY_MODE_100BASE_TX_HALF 4 -#define PHY_MODE_REPEATER 5 -#define PHY_MODE_POWER_DOWN 6 -#define PHY_MODE_ALL 7 - -/* Bits */ -#define VECT_CNTL_ENABLE (1 << 5) - -/******************************* - * GPIO and timer module * - *******************************/ - -/* Registers */ -#define NETX_GPIO_REG(ofs) IOMEM(NETX_VA_GPIO + (ofs)) -#define NETX_GPIO_CFG(gpio) NETX_GPIO_REG(0x0 + ((gpio)<<2)) -#define NETX_GPIO_THRESHOLD_CAPTURE(gpio) NETX_GPIO_REG(0x40 + ((gpio)<<2)) -#define NETX_GPIO_COUNTER_CTRL(counter) NETX_GPIO_REG(0x80 + ((counter)<<2)) -#define NETX_GPIO_COUNTER_MAX(counter) NETX_GPIO_REG(0x94 + ((counter)<<2)) -#define NETX_GPIO_COUNTER_CURRENT(counter) NETX_GPIO_REG(0xa8 + ((counter)<<2)) -#define NETX_GPIO_IRQ_ENABLE NETX_GPIO_REG(0xbc) -#define NETX_GPIO_IRQ_DISABLE NETX_GPIO_REG(0xc0) -#define NETX_GPIO_SYSTIME_NS_CMP NETX_GPIO_REG(0xc4) -#define NETX_GPIO_LINE NETX_GPIO_REG(0xc8) -#define NETX_GPIO_IRQ NETX_GPIO_REG(0xd0) - -/* Bits */ -#define NETX_GPIO_CFG_IOCFG_GP_INPUT (0x0) -#define NETX_GPIO_CFG_IOCFG_GP_OUTPUT (0x1) -#define NETX_GPIO_CFG_IOCFG_GP_UART (0x2) -#define NETX_GPIO_CFG_INV (1<<2) -#define NETX_GPIO_CFG_MODE_INPUT_READ (0<<3) -#define NETX_GPIO_CFG_MODE_INPUT_CAPTURE_CONT_RISING (1<<3) -#define NETX_GPIO_CFG_MODE_INPUT_CAPTURE_ONCE_RISING (2<<3) -#define NETX_GPIO_CFG_MODE_INPUT_CAPTURE_HIGH_LEVEL (3<<3) -#define NETX_GPIO_CFG_COUNT_REF_COUNTER0 (0<<5) -#define NETX_GPIO_CFG_COUNT_REF_COUNTER1 (1<<5) -#define NETX_GPIO_CFG_COUNT_REF_COUNTER2 (2<<5) -#define NETX_GPIO_CFG_COUNT_REF_COUNTER3 (3<<5) -#define NETX_GPIO_CFG_COUNT_REF_COUNTER4 (4<<5) -#define NETX_GPIO_CFG_COUNT_REF_SYSTIME (7<<5) - -#define NETX_GPIO_COUNTER_CTRL_RUN (1<<0) -#define NETX_GPIO_COUNTER_CTRL_SYM (1<<1) -#define NETX_GPIO_COUNTER_CTRL_ONCE (1<<2) -#define NETX_GPIO_COUNTER_CTRL_IRQ_EN (1<<3) -#define NETX_GPIO_COUNTER_CTRL_CNT_EVENT (1<<4) -#define NETX_GPIO_COUNTER_CTRL_RST_EN (1<<5) -#define NETX_GPIO_COUNTER_CTRL_SEL_EVENT (1<<6) -#define NETX_GPIO_COUNTER_CTRL_GPIO_REF /* FIXME */ - -#define GPIO_BIT(gpio) (1<<(gpio)) -#define COUNTER_BIT(counter) ((1<<16)<<(counter)) - -/******************************* - * PIO * - *******************************/ - -/* Registers */ -#define NETX_PIO_REG(ofs) IOMEM(NETX_VA_PIO + (ofs)) -#define NETX_PIO_INPIO NETX_PIO_REG(0x0) -#define NETX_PIO_OUTPIO NETX_PIO_REG(0x4) -#define NETX_PIO_OEPIO NETX_PIO_REG(0x8) - -/******************************* - * MII Unit * - *******************************/ - -/* Registers */ -#define NETX_MIIMU IOMEM(NETX_VA_MIIMU) - -/* Bits */ -#define MIIMU_SNRDY (1<<0) -#define MIIMU_PREAMBLE (1<<1) -#define MIIMU_OPMODE_WRITE (1<<2) -#define MIIMU_MDC_PERIOD (1<<3) -#define MIIMU_PHY_NRES (1<<4) -#define MIIMU_RTA (1<<5) -#define MIIMU_REGADDR(adr) (((adr) & 0x1f) << 6) -#define MIIMU_PHYADDR(adr) (((adr) & 0x1f) << 11) -#define MIIMU_DATA(data) (((data) & 0xffff) << 16) - -/******************************* - * xmac / xpec * - *******************************/ - -/* XPEC register offsets relative to NETX_VA_XPEC(no) */ -#define NETX_XPEC_R0_OFS 0x00 -#define NETX_XPEC_R1_OFS 0x04 -#define NETX_XPEC_R2_OFS 0x08 -#define NETX_XPEC_R3_OFS 0x0c -#define NETX_XPEC_R4_OFS 0x10 -#define NETX_XPEC_R5_OFS 0x14 -#define NETX_XPEC_R6_OFS 0x18 -#define NETX_XPEC_R7_OFS 0x1c -#define NETX_XPEC_RANGE01_OFS 0x20 -#define NETX_XPEC_RANGE23_OFS 0x24 -#define NETX_XPEC_RANGE45_OFS 0x28 -#define NETX_XPEC_RANGE67_OFS 0x2c -#define NETX_XPEC_PC_OFS 0x48 -#define NETX_XPEC_TIMER_OFS(timer) (0x30 + ((timer)<<2)) -#define NETX_XPEC_IRQ_OFS 0x8c -#define NETX_XPEC_SYSTIME_NS_OFS 0x90 -#define NETX_XPEC_FIFO_DATA_OFS 0x94 -#define NETX_XPEC_SYSTIME_S_OFS 0x98 -#define NETX_XPEC_ADC_OFS 0x9c -#define NETX_XPEC_URX_COUNT_OFS 0x40 -#define NETX_XPEC_UTX_COUNT_OFS 0x44 -#define NETX_XPEC_PC_OFS 0x48 -#define NETX_XPEC_ZERO_OFS 0x4c -#define NETX_XPEC_STATCFG_OFS 0x50 -#define NETX_XPEC_EC_MASKA_OFS 0x54 -#define NETX_XPEC_EC_MASKB_OFS 0x58 -#define NETX_XPEC_EC_MASK0_OFS 0x5c -#define NETX_XPEC_EC_MASK8_OFS 0x7c -#define NETX_XPEC_EC_MASK9_OFS 0x80 -#define NETX_XPEC_XPU_HOLD_PC_OFS 0x100 -#define NETX_XPEC_RAM_START_OFS 0x2000 - -/* Bits */ -#define XPU_HOLD_PC (1<<0) - -/* XMAC register offsets relative to NETX_VA_XMAC(no) */ -#define NETX_XMAC_RPU_PROGRAM_START_OFS 0x000 -#define NETX_XMAC_RPU_PROGRAM_END_OFS 0x3ff -#define NETX_XMAC_TPU_PROGRAM_START_OFS 0x400 -#define NETX_XMAC_TPU_PROGRAM_END_OFS 0x7ff -#define NETX_XMAC_RPU_HOLD_PC_OFS 0xa00 -#define NETX_XMAC_TPU_HOLD_PC_OFS 0xa04 -#define NETX_XMAC_STATUS_SHARED0_OFS 0x840 -#define NETX_XMAC_CONFIG_SHARED0_OFS 0x844 -#define NETX_XMAC_STATUS_SHARED1_OFS 0x848 -#define NETX_XMAC_CONFIG_SHARED1_OFS 0x84c -#define NETX_XMAC_STATUS_SHARED2_OFS 0x850 -#define NETX_XMAC_CONFIG_SHARED2_OFS 0x854 -#define NETX_XMAC_STATUS_SHARED3_OFS 0x858 -#define NETX_XMAC_CONFIG_SHARED3_OFS 0x85c - -#define RPU_HOLD_PC (1<<15) -#define TPU_HOLD_PC (1<<15) - -/******************************* - * Pointer FIFO * - *******************************/ - -/* Registers */ -#define NETX_PFIFO_REG(ofs) IOMEM(NETX_VA_PFIFO + (ofs)) -#define NETX_PFIFO_BASE(pfifo) NETX_PFIFO_REG(0x00 + ((pfifo)<<2)) -#define NETX_PFIFO_BORDER_BASE(pfifo) NETX_PFIFO_REG(0x80 + ((pfifo)<<2)) -#define NETX_PFIFO_RESET NETX_PFIFO_REG(0x100) -#define NETX_PFIFO_FULL NETX_PFIFO_REG(0x104) -#define NETX_PFIFO_EMPTY NETX_PFIFO_REG(0x108) -#define NETX_PFIFO_OVEFLOW NETX_PFIFO_REG(0x10c) -#define NETX_PFIFO_UNDERRUN NETX_PFIFO_REG(0x110) -#define NETX_PFIFO_FILL_LEVEL(pfifo) NETX_PFIFO_REG(0x180 + ((pfifo)<<2)) -#define NETX_PFIFO_XPEC_ISR(xpec) NETX_PFIFO_REG(0x400 + ((xpec) << 2)) - - -/******************************* - * Memory Controller * - *******************************/ - -/* Registers */ -#define NETX_MEMCR_REG(ofs) IOMEM(NETX_VA_MEMCR + (ofs)) -#define NETX_MEMCR_SRAM_CTRL(cs) NETX_MEMCR_REG(0x0 + 4 * (cs)) /* SRAM for CS 0..2 */ -#define NETX_MEMCR_SDRAM_CFG_CTRL NETX_MEMCR_REG(0x40) -#define NETX_MEMCR_SDRAM_TIMING_CTRL NETX_MEMCR_REG(0x44) -#define NETX_MEMCR_SDRAM_MODE NETX_MEMCR_REG(0x48) -#define NETX_MEMCR_SDRAM_EXT_MODE NETX_MEMCR_REG(0x4c) -#define NETX_MEMCR_PRIO_TIMESLOT_CTRL NETX_MEMCR_REG(0x80) -#define NETX_MEMCR_PRIO_ACCESS_CTRL NETX_MEMCR_REG(0x84) - -/* Bits */ -#define NETX_MEMCR_SRAM_CTRL_WIDTHEXTMEM(x) (((x) & 0x3) << 24) -#define NETX_MEMCR_SRAM_CTRL_WSPOSTPAUSEEXTMEM(x) (((x) & 0x3) << 16) -#define NETX_MEMCR_SRAM_CTRL_WSPREPASEEXTMEM(x) (((x) & 0x3) << 8) -#define NETX_MEMCR_SRAM_CTRL_WSEXTMEM(x) (((x) & 0x1f) << 0) - - -/******************************* - * Dual Port Memory * - *******************************/ - -/* Registers */ -#define NETX_DPMAS_REG(ofs) IOMEM(NETX_VA_DPMAS + (ofs)) -#define NETX_DPMAS_SYS_STAT NETX_DPMAS_REG(0x4d8) -#define NETX_DPMAS_INT_STAT NETX_DPMAS_REG(0x4e0) -#define NETX_DPMAS_INT_EN NETX_DPMAS_REG(0x4f0) -#define NETX_DPMAS_IF_CONF0 NETX_DPMAS_REG(0x608) -#define NETX_DPMAS_IF_CONF1 NETX_DPMAS_REG(0x60c) -#define NETX_DPMAS_EXT_CONFIG(cs) NETX_DPMAS_REG(0x610 + 4 * (cs)) -#define NETX_DPMAS_IO_MODE0 NETX_DPMAS_REG(0x620) /* I/O 32..63 */ -#define NETX_DPMAS_DRV_EN0 NETX_DPMAS_REG(0x624) -#define NETX_DPMAS_DATA0 NETX_DPMAS_REG(0x628) -#define NETX_DPMAS_IO_MODE1 NETX_DPMAS_REG(0x630) /* I/O 64..84 */ -#define NETX_DPMAS_DRV_EN1 NETX_DPMAS_REG(0x634) -#define NETX_DPMAS_DATA1 NETX_DPMAS_REG(0x638) - -/* Bits */ -#define NETX_DPMAS_INT_EN_GLB_EN (1<<31) -#define NETX_DPMAS_INT_EN_MEM_LCK (1<<30) -#define NETX_DPMAS_INT_EN_WDG (1<<29) -#define NETX_DPMAS_INT_EN_PIO72 (1<<28) -#define NETX_DPMAS_INT_EN_PIO47 (1<<27) -#define NETX_DPMAS_INT_EN_PIO40 (1<<26) -#define NETX_DPMAS_INT_EN_PIO36 (1<<25) -#define NETX_DPMAS_INT_EN_PIO35 (1<<24) - -#define NETX_DPMAS_IF_CONF0_HIF_DISABLED (0<<28) -#define NETX_DPMAS_IF_CONF0_HIF_EXT_BUS (1<<28) -#define NETX_DPMAS_IF_CONF0_HIF_UP_8BIT (2<<28) -#define NETX_DPMAS_IF_CONF0_HIF_UP_16BIT (3<<28) -#define NETX_DPMAS_IF_CONF0_HIF_IO (4<<28) -#define NETX_DPMAS_IF_CONF0_WAIT_DRV_PP (1<<14) -#define NETX_DPMAS_IF_CONF0_WAIT_DRV_OD (2<<14) -#define NETX_DPMAS_IF_CONF0_WAIT_DRV_TRI (3<<14) - -#define NETX_DPMAS_IF_CONF1_IRQ_POL_PIO35 (1<<26) -#define NETX_DPMAS_IF_CONF1_IRQ_POL_PIO36 (1<<27) -#define NETX_DPMAS_IF_CONF1_IRQ_POL_PIO40 (1<<28) -#define NETX_DPMAS_IF_CONF1_IRQ_POL_PIO47 (1<<29) -#define NETX_DPMAS_IF_CONF1_IRQ_POL_PIO72 (1<<30) - -#define NETX_EXT_CONFIG_TALEWIDTH(x) (((x) & 0x7) << 29) -#define NETX_EXT_CONFIG_TADRHOLD(x) (((x) & 0x7) << 26) -#define NETX_EXT_CONFIG_TCSON(x) (((x) & 0x7) << 23) -#define NETX_EXT_CONFIG_TRDON(x) (((x) & 0x7) << 20) -#define NETX_EXT_CONFIG_TWRON(x) (((x) & 0x7) << 17) -#define NETX_EXT_CONFIG_TWROFF(x) (((x) & 0x1f) << 12) -#define NETX_EXT_CONFIG_TRDWRCYC(x) (((x) & 0x1f) << 7) -#define NETX_EXT_CONFIG_WAIT_POL (1<<6) -#define NETX_EXT_CONFIG_WAIT_EN (1<<5) -#define NETX_EXT_CONFIG_NRD_MODE (1<<4) -#define NETX_EXT_CONFIG_DS_MODE (1<<3) -#define NETX_EXT_CONFIG_NWR_MODE (1<<2) -#define NETX_EXT_CONFIG_16BIT (1<<1) -#define NETX_EXT_CONFIG_CS_ENABLE (1<<0) - -#define NETX_DPMAS_IO_MODE0_WRL (1<<13) -#define NETX_DPMAS_IO_MODE0_WAIT (1<<14) -#define NETX_DPMAS_IO_MODE0_READY (1<<15) -#define NETX_DPMAS_IO_MODE0_CS0 (1<<19) -#define NETX_DPMAS_IO_MODE0_EXTRD (1<<20) - -#define NETX_DPMAS_IO_MODE1_CS2 (1<<15) -#define NETX_DPMAS_IO_MODE1_CS1 (1<<16) -#define NETX_DPMAS_IO_MODE1_SAMPLE_NPOR (0<<30) -#define NETX_DPMAS_IO_MODE1_SAMPLE_100MHZ (1<<30) -#define NETX_DPMAS_IO_MODE1_SAMPLE_NPIO36 (2<<30) -#define NETX_DPMAS_IO_MODE1_SAMPLE_PIO36 (3<<30) - -/******************************* - * I2C * - *******************************/ -#define NETX_I2C_REG(ofs) IOMEM(NETX_VA_I2C, (ofs)) -#define NETX_I2C_CTRL NETX_I2C_REG(0x0) -#define NETX_I2C_DATA NETX_I2C_REG(0x4) - -#endif /* __ASM_ARCH_NETX_REGS_H */ diff --git a/arch/arm/mach-netx/include/mach/pfifo.h b/arch/arm/mach-netx/include/mach/pfifo.h deleted file mode 100644 index de23180bc937..000000000000 --- a/arch/arm/mach-netx/include/mach/pfifo.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm/mach-netx/include/mach/pfifo.h - * - * Copyright (c) 2005 Sascha Hauer , Pengutronix - */ - - -#ifndef ASM_ARCH_PFIFO_H -#define ASM_ARCH_PFIFO_H - -static inline int pfifo_push(int no, unsigned int pointer) -{ - writel(pointer, NETX_PFIFO_BASE(no)); - return 0; -} - -static inline unsigned int pfifo_pop(int no) -{ - return readl(NETX_PFIFO_BASE(no)); -} - -static inline int pfifo_fill_level(int no) -{ - - return readl(NETX_PFIFO_FILL_LEVEL(no)); -} - -static inline int pfifo_full(int no) -{ - return readl(NETX_PFIFO_FULL) & (1<, Pengutronix - */ - -/* - * The following code assumes the serial port has already been - * initialized by the bootloader. We search for the first enabled - * port in the most probable order. If you didn't setup a port in - * your bootloader then nothing will appear (which might be desired). - * - * This does not append a newline - */ - -#define REG(x) (*(volatile unsigned long *)(x)) - -#define UART1_BASE 0x100a00 -#define UART2_BASE 0x100a80 - -#define UART_DR 0x0 - -#define UART_CR 0x14 -#define CR_UART_EN (1<<0) - -#define UART_FR 0x18 -#define FR_BUSY (1<<3) -#define FR_TXFF (1<<5) - -static inline void putc(char c) -{ - unsigned long base; - - if (REG(UART1_BASE + UART_CR) & CR_UART_EN) - base = UART1_BASE; - else if (REG(UART2_BASE + UART_CR) & CR_UART_EN) - base = UART2_BASE; - else - return; - - while (REG(base + UART_FR) & FR_TXFF); - REG(base + UART_DR) = c; -} - -static inline void flush(void) -{ - unsigned long base; - - if (REG(UART1_BASE + UART_CR) & CR_UART_EN) - base = UART1_BASE; - else if (REG(UART2_BASE + UART_CR) & CR_UART_EN) - base = UART2_BASE; - else - return; - - while (REG(base + UART_FR) & FR_BUSY); -} - -/* - * nothing to do - */ -#define arch_decomp_setup() diff --git a/arch/arm/mach-netx/include/mach/xc.h b/arch/arm/mach-netx/include/mach/xc.h deleted file mode 100644 index 465d5e250ab8..000000000000 --- a/arch/arm/mach-netx/include/mach/xc.h +++ /dev/null @@ -1,30 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm/mach-netx/include/mach/xc.h - * - * Copyright (C) 2005 Sascha Hauer , Pengutronix - */ - -#ifndef __ASM_ARCH_XC_H -#define __ASM_ARCH_XC_H - -struct xc { - int no; - unsigned int type; - unsigned int version; - void __iomem *xpec_base; - void __iomem *xmac_base; - void __iomem *sram_base; - int irq; - struct device *dev; -}; - -int xc_reset(struct xc *x); -int xc_stop(struct xc* x); -int xc_start(struct xc *x); -int xc_running(struct xc *x); -int xc_request_firmware(struct xc* x); -struct xc* request_xc(int xcno, struct device *dev); -void free_xc(struct xc *x); - -#endif /* __ASM_ARCH_XC_H */ diff --git a/arch/arm/mach-netx/nxdb500.c b/arch/arm/mach-netx/nxdb500.c deleted file mode 100644 index ad5e6747b834..000000000000 --- a/arch/arm/mach-netx/nxdb500.c +++ /dev/null @@ -1,197 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/nxdb500.c - * - * Copyright (c) 2005 Sascha Hauer , Pengutronix - */ - -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include - -#include "generic.h" -#include "fb.h" - -static struct clcd_panel qvga = { - .mode = { - .name = "QVGA", - .refresh = 60, - .xres = 240, - .yres = 320, - .pixclock = 187617, - .left_margin = 6, - .right_margin = 26, - .upper_margin = 0, - .lower_margin = 6, - .hsync_len = 6, - .vsync_len = 1, - .sync = 0, - .vmode = FB_VMODE_NONINTERLACED, - }, - .width = -1, - .height = -1, - .tim2 = 16, - .cntl = CNTL_LCDTFT | CNTL_BGR, - .bpp = 16, - .grayscale = 0, -}; - -static inline int nxdb500_check(struct clcd_fb *fb, struct fb_var_screeninfo *var) -{ - var->green.length = 5; - var->green.msb_right = 0; - - return clcdfb_check(fb, var); -} - -static int nxdb500_clcd_setup(struct clcd_fb *fb) -{ - unsigned int val; - - fb->fb.var.green.length = 5; - fb->fb.var.green.msb_right = 0; - - /* enable asic control */ - val = readl(NETX_SYSTEM_IOC_ACCESS_KEY); - writel(val, NETX_SYSTEM_IOC_ACCESS_KEY); - - writel(3, NETX_SYSTEM_IOC_CR); - - val = readl(NETX_PIO_OUTPIO); - writel(val | 1, NETX_PIO_OUTPIO); - - val = readl(NETX_PIO_OEPIO); - writel(val | 1, NETX_PIO_OEPIO); - return netx_clcd_setup(fb); -} - -static struct clcd_board clcd_data = { - .name = "netX", - .check = nxdb500_check, - .decode = clcdfb_decode, - .enable = netx_clcd_enable, - .setup = nxdb500_clcd_setup, - .mmap = netx_clcd_mmap, - .remove = netx_clcd_remove, -}; - -static struct netxeth_platform_data eth0_platform_data = { - .xcno = 0, -}; - -static struct platform_device netx_eth0_device = { - .name = "netx-eth", - .id = 0, - .num_resources = 0, - .resource = NULL, - .dev = { - .platform_data = ð0_platform_data, - } -}; - -static struct netxeth_platform_data eth1_platform_data = { - .xcno = 1, -}; - -static struct platform_device netx_eth1_device = { - .name = "netx-eth", - .id = 1, - .num_resources = 0, - .resource = NULL, - .dev = { - .platform_data = ð1_platform_data, - } -}; - -static struct resource netx_uart0_resources[] = { - [0] = { - .start = 0x00100A00, - .end = 0x00100A3F, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = (NETX_IRQ_UART0), - .end = (NETX_IRQ_UART0), - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device netx_uart0_device = { - .name = "netx-uart", - .id = 0, - .num_resources = ARRAY_SIZE(netx_uart0_resources), - .resource = netx_uart0_resources, -}; - -static struct resource netx_uart1_resources[] = { - [0] = { - .start = 0x00100A40, - .end = 0x00100A7F, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = (NETX_IRQ_UART1), - .end = (NETX_IRQ_UART1), - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device netx_uart1_device = { - .name = "netx-uart", - .id = 1, - .num_resources = ARRAY_SIZE(netx_uart1_resources), - .resource = netx_uart1_resources, -}; - -static struct resource netx_uart2_resources[] = { - [0] = { - .start = 0x00100A80, - .end = 0x00100ABF, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = (NETX_IRQ_UART2), - .end = (NETX_IRQ_UART2), - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device netx_uart2_device = { - .name = "netx-uart", - .id = 2, - .num_resources = ARRAY_SIZE(netx_uart2_resources), - .resource = netx_uart2_resources, -}; - -static struct platform_device *devices[] __initdata = { - &netx_eth0_device, - &netx_eth1_device, - &netx_uart0_device, - &netx_uart1_device, - &netx_uart2_device, -}; - -static void __init nxdb500_init(void) -{ - netx_fb_init(&clcd_data, &qvga); - platform_add_devices(devices, ARRAY_SIZE(devices)); -} - -MACHINE_START(NXDB500, "Hilscher nxdb500") - .atag_offset = 0x100, - .map_io = netx_map_io, - .init_irq = netx_init_irq, - .init_time = netx_timer_init, - .init_machine = nxdb500_init, - .restart = netx_restart, -MACHINE_END diff --git a/arch/arm/mach-netx/nxdkn.c b/arch/arm/mach-netx/nxdkn.c deleted file mode 100644 index 917381559628..000000000000 --- a/arch/arm/mach-netx/nxdkn.c +++ /dev/null @@ -1,90 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/nxdkn.c - * - * Copyright (c) 2005 Sascha Hauer , Pengutronix - */ - -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include - -#include "generic.h" - -static struct netxeth_platform_data eth0_platform_data = { - .xcno = 0, -}; - -static struct platform_device nxdkn_eth0_device = { - .name = "netx-eth", - .id = 0, - .num_resources = 0, - .resource = NULL, - .dev = { - .platform_data = ð0_platform_data, - } -}; - -static struct netxeth_platform_data eth1_platform_data = { - .xcno = 1, -}; - -static struct platform_device nxdkn_eth1_device = { - .name = "netx-eth", - .id = 1, - .num_resources = 0, - .resource = NULL, - .dev = { - .platform_data = ð1_platform_data, - } -}; - -static struct resource netx_uart0_resources[] = { - [0] = { - .start = 0x00100A00, - .end = 0x00100A3F, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = (NETX_IRQ_UART0), - .end = (NETX_IRQ_UART0), - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device netx_uart0_device = { - .name = "netx-uart", - .id = 0, - .num_resources = ARRAY_SIZE(netx_uart0_resources), - .resource = netx_uart0_resources, -}; - -static struct platform_device *devices[] __initdata = { - &nxdkn_eth0_device, - &nxdkn_eth1_device, - &netx_uart0_device, -}; - -static void __init nxdkn_init(void) -{ - platform_add_devices(devices, ARRAY_SIZE(devices)); -} - -MACHINE_START(NXDKN, "Hilscher nxdkn") - .atag_offset = 0x100, - .map_io = netx_map_io, - .init_irq = netx_init_irq, - .init_time = netx_timer_init, - .init_machine = nxdkn_init, - .restart = netx_restart, -MACHINE_END diff --git a/arch/arm/mach-netx/nxeb500hmi.c b/arch/arm/mach-netx/nxeb500hmi.c deleted file mode 100644 index aa0d5b2ca712..000000000000 --- a/arch/arm/mach-netx/nxeb500hmi.c +++ /dev/null @@ -1,174 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/nxeb500hmi.c - * - * Copyright (c) 2005 Sascha Hauer , Pengutronix - */ - -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include - -#include "generic.h" -#include "fb.h" - -static struct clcd_panel qvga = { - .mode = { - .name = "QVGA", - .refresh = 60, - .xres = 240, - .yres = 320, - .pixclock = 187617, - .left_margin = 6, - .right_margin = 26, - .upper_margin = 0, - .lower_margin = 6, - .hsync_len = 6, - .vsync_len = 1, - .sync = 0, - .vmode = FB_VMODE_NONINTERLACED, - }, - .width = -1, - .height = -1, - .tim2 = 16, - .cntl = CNTL_LCDTFT | CNTL_BGR, - .bpp = 16, - .grayscale = 0, -}; - -static inline int nxeb500hmi_check(struct clcd_fb *fb, struct fb_var_screeninfo *var) -{ - var->green.length = 5; - var->green.msb_right = 0; - - return clcdfb_check(fb, var); -} - -static int nxeb500hmi_clcd_setup(struct clcd_fb *fb) -{ - unsigned int val; - - fb->fb.var.green.length = 5; - fb->fb.var.green.msb_right = 0; - - /* enable asic control */ - val = readl(NETX_SYSTEM_IOC_ACCESS_KEY); - writel(val, NETX_SYSTEM_IOC_ACCESS_KEY); - - writel(3, NETX_SYSTEM_IOC_CR); - - /* GPIO 14 is used for display enable on newer boards */ - writel(9, NETX_GPIO_CFG(14)); - - val = readl(NETX_PIO_OUTPIO); - writel(val | 1, NETX_PIO_OUTPIO); - - val = readl(NETX_PIO_OEPIO); - writel(val | 1, NETX_PIO_OEPIO); - return netx_clcd_setup(fb); -} - -static struct clcd_board clcd_data = { - .name = "netX", - .check = nxeb500hmi_check, - .decode = clcdfb_decode, - .enable = netx_clcd_enable, - .setup = nxeb500hmi_clcd_setup, - .mmap = netx_clcd_mmap, - .remove = netx_clcd_remove, -}; - -static struct netxeth_platform_data eth0_platform_data = { - .xcno = 0, -}; - -static struct platform_device netx_eth0_device = { - .name = "netx-eth", - .id = 0, - .num_resources = 0, - .resource = NULL, - .dev = { - .platform_data = ð0_platform_data, - } -}; - -static struct netxeth_platform_data eth1_platform_data = { - .xcno = 1, -}; - -static struct platform_device netx_eth1_device = { - .name = "netx-eth", - .id = 1, - .num_resources = 0, - .resource = NULL, - .dev = { - .platform_data = ð1_platform_data, - } -}; - -static struct resource netx_cf_resources[] = { - [0] = { - .start = 0x20000000, - .end = 0x25ffffff, - .flags = IORESOURCE_MEM | IORESOURCE_MEM_8AND16BIT, - }, -}; - -static struct platform_device netx_cf_device = { - .name = "netx-cf", - .id = 0, - .resource = netx_cf_resources, - .num_resources = ARRAY_SIZE(netx_cf_resources), -}; - -static struct resource netx_uart0_resources[] = { - [0] = { - .start = 0x00100A00, - .end = 0x00100A3F, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = (NETX_IRQ_UART0), - .end = (NETX_IRQ_UART0), - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device netx_uart0_device = { - .name = "netx-uart", - .id = 0, - .num_resources = ARRAY_SIZE(netx_uart0_resources), - .resource = netx_uart0_resources, -}; - -static struct platform_device *devices[] __initdata = { - &netx_eth0_device, - &netx_eth1_device, - &netx_cf_device, - &netx_uart0_device, -}; - -static void __init nxeb500hmi_init(void) -{ - netx_fb_init(&clcd_data, &qvga); - platform_add_devices(devices, ARRAY_SIZE(devices)); -} - -MACHINE_START(NXEB500HMI, "Hilscher nxeb500hmi") - .atag_offset = 0x100, - .map_io = netx_map_io, - .init_irq = netx_init_irq, - .init_time = netx_timer_init, - .init_machine = nxeb500hmi_init, - .restart = netx_restart, -MACHINE_END diff --git a/arch/arm/mach-netx/pfifo.c b/arch/arm/mach-netx/pfifo.c deleted file mode 100644 index 2e5cc777329f..000000000000 --- a/arch/arm/mach-netx/pfifo.c +++ /dev/null @@ -1,56 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/pfifo.c - * - * Copyright (c) 2005 Sascha Hauer , Pengutronix - */ - -#include -#include -#include -#include - -#include -#include -#include - -static DEFINE_MUTEX(pfifo_lock); - -static unsigned int pfifo_used = 0; - -int pfifo_request(unsigned int pfifo_mask) -{ - int err = 0; - unsigned int val; - - mutex_lock(&pfifo_lock); - - if (pfifo_mask & pfifo_used) { - err = -EBUSY; - goto out; - } - - pfifo_used |= pfifo_mask; - - val = readl(NETX_PFIFO_RESET); - writel(val | pfifo_mask, NETX_PFIFO_RESET); - writel(val, NETX_PFIFO_RESET); - -out: - mutex_unlock(&pfifo_lock); - return err; -} - -void pfifo_free(unsigned int pfifo_mask) -{ - mutex_lock(&pfifo_lock); - pfifo_used &= ~pfifo_mask; - mutex_unlock(&pfifo_lock); -} - -EXPORT_SYMBOL(pfifo_push); -EXPORT_SYMBOL(pfifo_pop); -EXPORT_SYMBOL(pfifo_fill_level); -EXPORT_SYMBOL(pfifo_empty); -EXPORT_SYMBOL(pfifo_request); -EXPORT_SYMBOL(pfifo_free); diff --git a/arch/arm/mach-netx/time.c b/arch/arm/mach-netx/time.c deleted file mode 100644 index d9defa1ab605..000000000000 --- a/arch/arm/mach-netx/time.c +++ /dev/null @@ -1,141 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/time.c - * - * Copyright (c) 2005 Sascha Hauer , Pengutronix - */ - -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -#define NETX_CLOCK_FREQ 100000000 -#define NETX_LATCH DIV_ROUND_CLOSEST(NETX_CLOCK_FREQ, HZ) - -#define TIMER_CLOCKEVENT 0 -#define TIMER_CLOCKSOURCE 1 - -static inline void timer_shutdown(struct clock_event_device *evt) -{ - /* disable timer */ - writel(0, NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKEVENT)); -} - -static int netx_shutdown(struct clock_event_device *evt) -{ - timer_shutdown(evt); - - return 0; -} - -static int netx_set_oneshot(struct clock_event_device *evt) -{ - u32 tmode = NETX_GPIO_COUNTER_CTRL_IRQ_EN | NETX_GPIO_COUNTER_CTRL_RUN; - - timer_shutdown(evt); - writel(0, NETX_GPIO_COUNTER_MAX(TIMER_CLOCKEVENT)); - writel(tmode, NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKEVENT)); - - return 0; -} - -static int netx_set_periodic(struct clock_event_device *evt) -{ - u32 tmode = NETX_GPIO_COUNTER_CTRL_RST_EN | - NETX_GPIO_COUNTER_CTRL_IRQ_EN | NETX_GPIO_COUNTER_CTRL_RUN; - - timer_shutdown(evt); - writel(NETX_LATCH, NETX_GPIO_COUNTER_MAX(TIMER_CLOCKEVENT)); - writel(tmode, NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKEVENT)); - - return 0; -} - -static int netx_set_next_event(unsigned long evt, - struct clock_event_device *clk) -{ - writel(0 - evt, NETX_GPIO_COUNTER_CURRENT(TIMER_CLOCKEVENT)); - return 0; -} - -static struct clock_event_device netx_clockevent = { - .name = "netx-timer" __stringify(TIMER_CLOCKEVENT), - .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, - .set_next_event = netx_set_next_event, - .set_state_shutdown = netx_shutdown, - .set_state_periodic = netx_set_periodic, - .set_state_oneshot = netx_set_oneshot, - .tick_resume = netx_shutdown, -}; - -/* - * IRQ handler for the timer - */ -static irqreturn_t -netx_timer_interrupt(int irq, void *dev_id) -{ - struct clock_event_device *evt = &netx_clockevent; - - /* acknowledge interrupt */ - writel(COUNTER_BIT(0), NETX_GPIO_IRQ); - - evt->event_handler(evt); - - return IRQ_HANDLED; -} - -static struct irqaction netx_timer_irq = { - .name = "NetX Timer Tick", - .flags = IRQF_TIMER | IRQF_IRQPOLL, - .handler = netx_timer_interrupt, -}; - -/* - * Set up timer interrupt - */ -void __init netx_timer_init(void) -{ - /* disable timer initially */ - writel(0, NETX_GPIO_COUNTER_CTRL(0)); - - /* Reset the timer value to zero */ - writel(0, NETX_GPIO_COUNTER_CURRENT(0)); - - writel(NETX_LATCH, NETX_GPIO_COUNTER_MAX(0)); - - /* acknowledge interrupt */ - writel(COUNTER_BIT(0), NETX_GPIO_IRQ); - - /* Enable the interrupt in the specific timer - * register and start timer - */ - writel(COUNTER_BIT(0), NETX_GPIO_IRQ_ENABLE); - writel(NETX_GPIO_COUNTER_CTRL_IRQ_EN | NETX_GPIO_COUNTER_CTRL_RUN, - NETX_GPIO_COUNTER_CTRL(0)); - - setup_irq(NETX_IRQ_TIMER0, &netx_timer_irq); - - /* Setup timer one for clocksource */ - writel(0, NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKSOURCE)); - writel(0, NETX_GPIO_COUNTER_CURRENT(TIMER_CLOCKSOURCE)); - writel(0xffffffff, NETX_GPIO_COUNTER_MAX(TIMER_CLOCKSOURCE)); - - writel(NETX_GPIO_COUNTER_CTRL_RUN, - NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKSOURCE)); - - clocksource_mmio_init(NETX_GPIO_COUNTER_CURRENT(TIMER_CLOCKSOURCE), - "netx_timer", NETX_CLOCK_FREQ, 200, 32, clocksource_mmio_readl_up); - - /* with max_delta_ns >= delta2ns(0x800) the system currently runs fine. - * Adding some safety ... */ - netx_clockevent.cpumask = cpumask_of(0); - clockevents_config_and_register(&netx_clockevent, NETX_CLOCK_FREQ, - 0xa00, 0xfffffffe); -} diff --git a/arch/arm/mach-netx/xc.c b/arch/arm/mach-netx/xc.c deleted file mode 100644 index 885a618b2651..000000000000 --- a/arch/arm/mach-netx/xc.c +++ /dev/null @@ -1,246 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/xc.c - * - * Copyright (c) 2005 Sascha Hauer , Pengutronix - */ - -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -#include - -static DEFINE_MUTEX(xc_lock); - -static int xc_in_use = 0; - -struct fw_desc { - unsigned int ofs; - unsigned int size; - unsigned int patch_ofs; - unsigned int patch_entries; -}; - -struct fw_header { - unsigned int magic; - unsigned int type; - unsigned int version; - unsigned int reserved[5]; - struct fw_desc fw_desc[3]; -} __attribute__ ((packed)); - -int xc_stop(struct xc *x) -{ - writel(RPU_HOLD_PC, x->xmac_base + NETX_XMAC_RPU_HOLD_PC_OFS); - writel(TPU_HOLD_PC, x->xmac_base + NETX_XMAC_TPU_HOLD_PC_OFS); - writel(XPU_HOLD_PC, x->xpec_base + NETX_XPEC_XPU_HOLD_PC_OFS); - return 0; -} - -int xc_start(struct xc *x) -{ - writel(0, x->xmac_base + NETX_XMAC_RPU_HOLD_PC_OFS); - writel(0, x->xmac_base + NETX_XMAC_TPU_HOLD_PC_OFS); - writel(0, x->xpec_base + NETX_XPEC_XPU_HOLD_PC_OFS); - return 0; -} - -int xc_running(struct xc *x) -{ - return (readl(x->xmac_base + NETX_XMAC_RPU_HOLD_PC_OFS) & RPU_HOLD_PC) - || (readl(x->xmac_base + NETX_XMAC_TPU_HOLD_PC_OFS) & TPU_HOLD_PC) - || (readl(x->xpec_base + NETX_XPEC_XPU_HOLD_PC_OFS) & XPU_HOLD_PC) ? - 0 : 1; -} - -int xc_reset(struct xc *x) -{ - writel(0, x->xpec_base + NETX_XPEC_PC_OFS); - return 0; -} - -static int xc_check_ptr(struct xc *x, unsigned long adr, unsigned int size) -{ - if (adr >= NETX_PA_XMAC(x->no) && - adr + size < NETX_PA_XMAC(x->no) + XMAC_MEM_SIZE) - return 0; - - if (adr >= NETX_PA_XPEC(x->no) && - adr + size < NETX_PA_XPEC(x->no) + XPEC_MEM_SIZE) - return 0; - - dev_err(x->dev, "Illegal pointer in firmware found. aborting\n"); - - return -1; -} - -static int xc_patch(struct xc *x, const void *patch, int count) -{ - unsigned int val, adr; - const unsigned int *data = patch; - - int i; - for (i = 0; i < count; i++) { - adr = *data++; - val = *data++; - if (xc_check_ptr(x, adr, 4) < 0) - return -EINVAL; - - writel(val, (void __iomem *)io_p2v(adr)); - } - return 0; -} - -int xc_request_firmware(struct xc *x) -{ - int ret; - char name[16]; - const struct firmware *fw; - struct fw_header *head; - unsigned int size; - int i; - const void *src; - unsigned long dst; - - sprintf(name, "xc%d.bin", x->no); - - ret = request_firmware(&fw, name, x->dev); - - if (ret < 0) { - dev_err(x->dev, "request_firmware failed\n"); - return ret; - } - - head = (struct fw_header *)fw->data; - if (head->magic != 0x4e657458) { - if (head->magic == 0x5874654e) { - dev_err(x->dev, - "firmware magic is 'XteN'. Endianness problems?\n"); - ret = -ENODEV; - goto exit_release_firmware; - } - dev_err(x->dev, "unrecognized firmware magic 0x%08x\n", - head->magic); - ret = -ENODEV; - goto exit_release_firmware; - } - - x->type = head->type; - x->version = head->version; - - ret = -EINVAL; - - for (i = 0; i < 3; i++) { - src = fw->data + head->fw_desc[i].ofs; - dst = *(unsigned int *)src; - src += sizeof (unsigned int); - size = head->fw_desc[i].size - sizeof (unsigned int); - - if (xc_check_ptr(x, dst, size)) - goto exit_release_firmware; - - memcpy((void *)io_p2v(dst), src, size); - - src = fw->data + head->fw_desc[i].patch_ofs; - size = head->fw_desc[i].patch_entries; - ret = xc_patch(x, src, size); - if (ret < 0) - goto exit_release_firmware; - } - - ret = 0; - - exit_release_firmware: - release_firmware(fw); - - return ret; -} - -struct xc *request_xc(int xcno, struct device *dev) -{ - struct xc *x = NULL; - - mutex_lock(&xc_lock); - - if (xcno > 3) - goto exit; - if (xc_in_use & (1 << xcno)) - goto exit; - - x = kmalloc(sizeof (struct xc), GFP_KERNEL); - if (!x) - goto exit; - - if (!request_mem_region - (NETX_PA_XPEC(xcno), XPEC_MEM_SIZE, kobject_name(&dev->kobj))) - goto exit_free; - - if (!request_mem_region - (NETX_PA_XMAC(xcno), XMAC_MEM_SIZE, kobject_name(&dev->kobj))) - goto exit_release_1; - - if (!request_mem_region - (SRAM_INTERNAL_PHYS(xcno), SRAM_MEM_SIZE, kobject_name(&dev->kobj))) - goto exit_release_2; - - x->xpec_base = (void * __iomem)io_p2v(NETX_PA_XPEC(xcno)); - x->xmac_base = (void * __iomem)io_p2v(NETX_PA_XMAC(xcno)); - x->sram_base = ioremap(SRAM_INTERNAL_PHYS(xcno), SRAM_MEM_SIZE); - if (!x->sram_base) - goto exit_release_3; - - x->irq = NETX_IRQ_XPEC(xcno); - - x->no = xcno; - x->dev = dev; - - xc_in_use |= (1 << xcno); - - goto exit; - - exit_release_3: - release_mem_region(SRAM_INTERNAL_PHYS(xcno), SRAM_MEM_SIZE); - exit_release_2: - release_mem_region(NETX_PA_XMAC(xcno), XMAC_MEM_SIZE); - exit_release_1: - release_mem_region(NETX_PA_XPEC(xcno), XPEC_MEM_SIZE); - exit_free: - kfree(x); - x = NULL; - exit: - mutex_unlock(&xc_lock); - return x; -} - -void free_xc(struct xc *x) -{ - int xcno = x->no; - - mutex_lock(&xc_lock); - - iounmap(x->sram_base); - release_mem_region(SRAM_INTERNAL_PHYS(xcno), SRAM_MEM_SIZE); - release_mem_region(NETX_PA_XMAC(xcno), XMAC_MEM_SIZE); - release_mem_region(NETX_PA_XPEC(xcno), XPEC_MEM_SIZE); - xc_in_use &= ~(1 << x->no); - kfree(x); - - mutex_unlock(&xc_lock); -} - -EXPORT_SYMBOL(free_xc); -EXPORT_SYMBOL(request_xc); -EXPORT_SYMBOL(xc_request_firmware); -EXPORT_SYMBOL(xc_reset); -EXPORT_SYMBOL(xc_running); -EXPORT_SYMBOL(xc_start); -EXPORT_SYMBOL(xc_stop); From f16d80b75a096c52354c6e0a574993f3b0dfbdfe Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Fri, 19 Jul 2019 15:05:02 +1000 Subject: [PATCH 125/823] powerpc/tm: Fix oops on sigreturn on systems without TM On systems like P9 powernv where we have no TM (or P8 booted with ppc_tm=off), userspace can construct a signal context which still has the MSR TS bits set. The kernel tries to restore this context which results in the following crash: Unexpected TM Bad Thing exception at c0000000000022fc (msr 0x8000000102a03031) tm_scratch=800000020280f033 Oops: Unrecoverable exception, sig: 6 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: CPU: 0 PID: 1636 Comm: sigfuz Not tainted 5.2.0-11043-g0a8ad0ffa4 #69 NIP: c0000000000022fc LR: 00007fffb2d67e48 CTR: 0000000000000000 REGS: c00000003fffbd70 TRAP: 0700 Not tainted (5.2.0-11045-g7142b497d8) MSR: 8000000102a03031 CR: 42004242 XER: 00000000 CFAR: c0000000000022e0 IRQMASK: 0 GPR00: 0000000000000072 00007fffb2b6e560 00007fffb2d87f00 0000000000000669 GPR04: 00007fffb2b6e728 0000000000000000 0000000000000000 00007fffb2b6f2a8 GPR08: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR12: 0000000000000000 00007fffb2b76900 0000000000000000 0000000000000000 GPR16: 00007fffb2370000 00007fffb2d84390 00007fffea3a15ac 000001000a250420 GPR20: 00007fffb2b6f260 0000000010001770 0000000000000000 0000000000000000 GPR24: 00007fffb2d843a0 00007fffea3a14a0 0000000000010000 0000000000800000 GPR28: 00007fffea3a14d8 00000000003d0f00 0000000000000000 00007fffb2b6e728 NIP [c0000000000022fc] rfi_flush_fallback+0x7c/0x80 LR [00007fffb2d67e48] 0x7fffb2d67e48 Call Trace: Instruction dump: e96a0220 e96a02a8 e96a0330 e96a03b8 394a0400 4200ffdc 7d2903a6 e92d0c00 e94d0c08 e96d0c10 e82d0c18 7db242a6 <4c000024> 7db243a6 7db142a6 f82d0c18 The problem is the signal code assumes TM is enabled when CONFIG_PPC_TRANSACTIONAL_MEM is enabled. This may not be the case as with P9 powernv or if `ppc_tm=off` is used on P8. This means any local user can crash the system. Fix the problem by returning a bad stack frame to the user if they try to set the MSR TS bits with sigreturn() on systems where TM is not supported. Found with sigfuz kernel selftest on P9. This fixes CVE-2019-13648. Fixes: 2b0a576d15e0 ("powerpc: Add new transactional memory state to the signal context") Cc: stable@vger.kernel.org # v3.9 Reported-by: Praveen Pandey Signed-off-by: Michael Neuling Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190719050502.405-1-mikey@neuling.org --- arch/powerpc/kernel/signal_32.c | 3 +++ arch/powerpc/kernel/signal_64.c | 5 +++++ 2 files changed, 8 insertions(+) diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index f50b708d6d77..98600b276f76 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1198,6 +1198,9 @@ SYSCALL_DEFINE0(rt_sigreturn) goto bad; if (MSR_TM_ACTIVE(msr_hi<<32)) { + /* Trying to start TM on non TM system */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto bad; /* We only recheckpoint on return if we're * transaction. */ diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 2f80e270c7b0..117515564ec7 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -771,6 +771,11 @@ SYSCALL_DEFINE0(rt_sigreturn) if (MSR_TM_ACTIVE(msr)) { /* We recheckpoint on return. */ struct ucontext __user *uc_transact; + + /* Trying to start TM on non TM system */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto badframe; + if (__get_user(uc_transact, &uc->uc_link)) goto badframe; if (restore_tm_sigcontexts(current, &uc->uc_mcontext, From 893a1c97205a3ece0cbb3f571a3b972080f3b4c7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 16 Jul 2019 13:55:23 -0600 Subject: [PATCH 126/823] blk-mq: allow REQ_NOWAIT to return an error inline By default, if a caller sets REQ_NOWAIT and we need to block, we'll return -EAGAIN through the bio->bi_end_io() callback. For some use cases, this makes it hard to use. Allow a caller to ask for inline return of errors related to blocking by also setting REQ_NOWAIT_INLINE. Signed-off-by: Jens Axboe --- block/blk-mq.c | 8 ++++++-- include/linux/blk_types.h | 5 ++++- 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index b038ec680e84..2bc2c0705660 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1960,9 +1960,13 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) rq = blk_mq_get_request(q, bio, &data); if (unlikely(!rq)) { rq_qos_cleanup(q, bio); - if (bio->bi_opf & REQ_NOWAIT) + + cookie = BLK_QC_T_NONE; + if (bio->bi_opf & REQ_NOWAIT_INLINE) + cookie = BLK_QC_T_EAGAIN; + else if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); - return BLK_QC_T_NONE; + return cookie; } trace_block_getrq(q, bio, bio->bi_opf); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index feff3fe4467e..1b1fa1557e68 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -311,6 +311,7 @@ enum req_flag_bits { __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ __REQ_NOWAIT, /* Don't wait if request will block */ + __REQ_NOWAIT_INLINE, /* Return would-block error inline */ /* * When a shared kthread needs to issue a bio for a cgroup, doing * so synchronously can lead to priority inversions as the kthread @@ -345,6 +346,7 @@ enum req_flag_bits { #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) #define REQ_NOWAIT (1ULL << __REQ_NOWAIT) +#define REQ_NOWAIT_INLINE (1ULL << __REQ_NOWAIT_INLINE) #define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT) #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) @@ -418,12 +420,13 @@ static inline int op_stat_group(unsigned int op) typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U +#define BLK_QC_T_EAGAIN -2U #define BLK_QC_T_SHIFT 16 #define BLK_QC_T_INTERNAL (1U << 31) static inline bool blk_qc_t_valid(blk_qc_t cookie) { - return cookie != BLK_QC_T_NONE; + return cookie != BLK_QC_T_NONE && cookie != BLK_QC_T_EAGAIN; } static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie) From 6a43074e2f461c2c49a607f9f6f5218d53f97d1e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 16 Jul 2019 13:56:42 -0600 Subject: [PATCH 127/823] block: properly handle IOCB_NOWAIT for async O_DIRECT IO A caller is supposed to pass in REQ_NOWAIT if we can't block for any given operation, but O_DIRECT for block devices just ignore this. Hence we'll block for various resource shortages on the block layer side, like having to wait for requests. Use the new REQ_NOWAIT_INLINE to ask for this error to be returned inline, so we can handle it appropriately and return -EAGAIN to the caller. Signed-off-by: Jens Axboe --- fs/block_dev.c | 58 +++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 50 insertions(+), 8 deletions(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index f00b569a9f89..5dc613eec4d2 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -344,15 +344,24 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) struct bio *bio; bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0; bool is_read = (iov_iter_rw(iter) == READ), is_sync; + bool nowait = (iocb->ki_flags & IOCB_NOWAIT) != 0; loff_t pos = iocb->ki_pos; blk_qc_t qc = BLK_QC_T_NONE; - int ret = 0; + gfp_t gfp; + ssize_t ret; if ((pos | iov_iter_alignment(iter)) & (bdev_logical_block_size(bdev) - 1)) return -EINVAL; - bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool); + if (nowait) + gfp = GFP_NOWAIT; + else + gfp = GFP_KERNEL; + + bio = bio_alloc_bioset(gfp, nr_pages, &blkdev_dio_pool); + if (!bio) + return -EAGAIN; dio = container_of(bio, struct blkdev_dio, bio); dio->is_sync = is_sync = is_sync_kiocb(iocb); @@ -374,7 +383,10 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) if (!is_poll) blk_start_plug(&plug); + ret = 0; for (;;) { + int err; + bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = pos >> 9; bio->bi_write_hint = iocb->ki_hint; @@ -382,8 +394,10 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) bio->bi_end_io = blkdev_bio_end_io; bio->bi_ioprio = iocb->ki_ioprio; - ret = bio_iov_iter_get_pages(bio, iter); - if (unlikely(ret)) { + err = bio_iov_iter_get_pages(bio, iter); + if (unlikely(err)) { + if (!ret) + ret = err; bio->bi_status = BLK_STS_IOERR; bio_endio(bio); break; @@ -398,6 +412,14 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) task_io_account_write(bio->bi_iter.bi_size); } + /* + * Tell underlying layer to not block for resource shortage. + * And if we would have blocked, return error inline instead + * of through the bio->bi_end_io() callback. + */ + if (nowait) + bio->bi_opf |= (REQ_NOWAIT | REQ_NOWAIT_INLINE); + dio->size += bio->bi_iter.bi_size; pos += bio->bi_iter.bi_size; @@ -411,6 +433,11 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) } qc = submit_bio(bio); + if (qc == BLK_QC_T_EAGAIN) { + if (!ret) + ret = -EAGAIN; + goto error; + } if (polled) WRITE_ONCE(iocb->ki_cookie, qc); @@ -431,8 +458,20 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) atomic_inc(&dio->ref); } - submit_bio(bio); - bio = bio_alloc(GFP_KERNEL, nr_pages); + qc = submit_bio(bio); + if (qc == BLK_QC_T_EAGAIN) { + if (!ret) + ret = -EAGAIN; + goto error; + } + ret += bio->bi_iter.bi_size; + + bio = bio_alloc(gfp, nr_pages); + if (!bio) { + if (!ret) + ret = -EAGAIN; + goto error; + } } if (!is_poll) @@ -452,13 +491,16 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) } __set_current_state(TASK_RUNNING); +out: if (!ret) ret = blk_status_to_errno(dio->bio.bi_status); - if (likely(!ret)) - ret = dio->size; bio_put(&dio->bio); return ret; +error: + if (!is_poll) + blk_finish_plug(&plug); + goto out; } static ssize_t From bd11b3a391e3df6fa958facbe4b3f9f4cca9bd49 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 20 Jul 2019 08:37:31 -0600 Subject: [PATCH 128/823] io_uring: don't use iov_iter_advance() for fixed buffers Hrvoje reports that when a large fixed buffer is registered and IO is being done to the latter pages of said buffer, the IO submission time is much worse: reading to the start of the buffer: 11238 ns reading to the end of the buffer: 1039879 ns In fact, it's worse by two orders of magnitude. The reason for that is how io_uring figures out how to setup the iov_iter. We point the iter at the first bvec, and then use iov_iter_advance() to fast-forward to the offset within that buffer we need. However, that is abysmally slow, as it entails iterating the bvecs that we setup as part of buffer registration. There's really no need to use this generic helper, as we know it's a BVEC type iterator, and we also know that each bvec is PAGE_SIZE in size, apart from possibly the first and last. Hence we can just use a shift on the offset to find the right index, and then adjust the iov_iter appropriately. After this fix, the timings are: reading to the start of the buffer: 10135 ns reading to the end of the buffer: 1377 ns Or about an 755x improvement for the tail page. Reported-by: Hrvoje Zeba Tested-by: Hrvoje Zeba Signed-off-by: Jens Axboe --- fs/io_uring.c | 40 ++++++++++++++++++++++++++++++++++++++-- 1 file changed, 38 insertions(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 324530c4d2ce..0e6bd60cb113 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1066,8 +1066,44 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw, */ offset = buf_addr - imu->ubuf; iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len); - if (offset) - iov_iter_advance(iter, offset); + + if (offset) { + /* + * Don't use iov_iter_advance() here, as it's really slow for + * using the latter parts of a big fixed buffer - it iterates + * over each segment manually. We can cheat a bit here, because + * we know that: + * + * 1) it's a BVEC iter, we set it up + * 2) all bvecs are PAGE_SIZE in size, except potentially the + * first and last bvec + * + * So just find our index, and adjust the iterator afterwards. + * If the offset is within the first bvec (or the whole first + * bvec, just use iov_iter_advance(). This makes it easier + * since we can just skip the first segment, which may not + * be PAGE_SIZE aligned. + */ + const struct bio_vec *bvec = imu->bvec; + + if (offset <= bvec->bv_len) { + iov_iter_advance(iter, offset); + } else { + unsigned long seg_skip; + + /* skip first vec */ + offset -= bvec->bv_len; + seg_skip = 1 + (offset >> PAGE_SHIFT); + + iter->bvec = bvec + seg_skip; + iter->nr_segs -= seg_skip; + iter->count -= (seg_skip << PAGE_SHIFT); + iter->iov_offset = offset & ~PAGE_MASK; + if (iter->iov_offset) + iter->count -= iter->iov_offset; + } + } + return 0; } From 9310a7ba6de8cce6209e3e8a3cdf733f824cdd9b Mon Sep 17 00:00:00 2001 From: Zhengyuan Liu Date: Mon, 22 Jul 2019 10:23:27 +0800 Subject: [PATCH 129/823] io_uring: track io length in async_list based on bytes We are using PAGE_SIZE as the unit to determine if the total len in async_list has exceeded max_pages, it's not fair for smaller io sizes. For example, if we are doing 1k-size io streams, we will never exceed max_pages since len >>= PAGE_SHIFT always gets zero. So use original bytes to make it more accurate. Signed-off-by: Zhengyuan Liu Signed-off-by: Jens Axboe --- fs/io_uring.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 0e6bd60cb113..2039f888197e 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -202,7 +202,7 @@ struct async_list { struct file *file; off_t io_end; - size_t io_pages; + size_t io_len; }; struct io_ring_ctx { @@ -1158,28 +1158,26 @@ static void io_async_list_note(int rw, struct io_kiocb *req, size_t len) off_t io_end = kiocb->ki_pos + len; if (filp == async_list->file && kiocb->ki_pos == async_list->io_end) { - unsigned long max_pages; + unsigned long max_bytes; /* Use 8x RA size as a decent limiter for both reads/writes */ - max_pages = filp->f_ra.ra_pages; - if (!max_pages) - max_pages = VM_READAHEAD_PAGES; - max_pages *= 8; + max_bytes = filp->f_ra.ra_pages << (PAGE_SHIFT + 3); + if (!max_bytes) + max_bytes = VM_READAHEAD_PAGES << (PAGE_SHIFT + 3); - /* If max pages are exceeded, reset the state */ - len >>= PAGE_SHIFT; - if (async_list->io_pages + len <= max_pages) { + /* If max len are exceeded, reset the state */ + if (async_list->io_len + len <= max_bytes) { req->flags |= REQ_F_SEQ_PREV; - async_list->io_pages += len; + async_list->io_len += len; } else { io_end = 0; - async_list->io_pages = 0; + async_list->io_len = 0; } } /* New file? Reset state. */ if (async_list->file != filp) { - async_list->io_pages = 0; + async_list->io_len = 0; async_list->file = filp; } async_list->io_end = io_end; From c8917b8ff09e8a4d6ef77e32ce0052f7158baa1f Mon Sep 17 00:00:00 2001 From: Mauro Rossi Date: Mon, 22 Jul 2019 07:55:36 +0200 Subject: [PATCH 130/823] firmware: fix build errors in paged buffer handling code fw_{grow,map}_paged_buf() need to be defined as static inline when CONFIG_FW_LOADER_PAGED_BUF is not enabled, infact fw_free_paged_buf() is also defined as static inline when CONFIG_FW_LOADER_PAGED_BUF is not enabled. Fixes the following mutiple definition building errors for Android kernel: drivers/base/firmware_loader/fallback_efi.o: In function `fw_grow_paged_buf': fallback_efi.c:(.text+0x0): multiple definition of `fw_grow_paged_buf' drivers/base/firmware_loader/main.o:(.text+0x73b): first defined here drivers/base/firmware_loader/fallback_efi.o: In function `fw_map_paged_buf': fallback_efi.c:(.text+0xf): multiple definition of `fw_map_paged_buf' drivers/base/firmware_loader/main.o:(.text+0x74a): first defined here [ slightly corrected the patch description -- tiwai ] Fixes: 5342e7093ff2 ("firmware: Factor out the paged buffer handling code") Fixes: 82fd7a8142a1 ("firmware: Add support for loading compressed files") Signed-off-by: Mauro Rossi Signed-off-by: Takashi Iwai Link: https://lore.kernel.org/r/20190722055536.15342-1-tiwai@suse.de Signed-off-by: Greg Kroah-Hartman --- drivers/base/firmware_loader/firmware.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/base/firmware_loader/firmware.h b/drivers/base/firmware_loader/firmware.h index 7048a41973ed..842e63f19f22 100644 --- a/drivers/base/firmware_loader/firmware.h +++ b/drivers/base/firmware_loader/firmware.h @@ -141,8 +141,8 @@ int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed); int fw_map_paged_buf(struct fw_priv *fw_priv); #else static inline void fw_free_paged_buf(struct fw_priv *fw_priv) {} -int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed) { return -ENXIO; } -int fw_map_paged_buf(struct fw_priv *fw_priv) { return -ENXIO; } +static int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed) { return -ENXIO; } +static int fw_map_paged_buf(struct fw_priv *fw_priv) { return -ENXIO; } #endif #endif /* __FIRMWARE_LOADER_H */ From e4091bdd2fd957793a10449a8682c767578b0430 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 21 Jul 2019 12:25:58 +0200 Subject: [PATCH 131/823] ALSA: line6: Fix a typo s/Vairax/Variax/ Signed-off-by: Christophe JAILLET Signed-off-by: Takashi Iwai --- sound/usb/line6/variax.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/usb/line6/variax.c b/sound/usb/line6/variax.c index 0d24c72c155f..ed158f04de80 100644 --- a/sound/usb/line6/variax.c +++ b/sound/usb/line6/variax.c @@ -244,5 +244,5 @@ static struct usb_driver variax_driver = { module_usb_driver(variax_driver); -MODULE_DESCRIPTION("Vairax Workbench USB driver"); +MODULE_DESCRIPTION("Variax Workbench USB driver"); MODULE_LICENSE("GPL"); From 2ca99396333999b9b5c5b91b36cbccacfe571aaf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?S=C3=A9bastien=20Szymanski?= Date: Thu, 4 Jul 2019 13:00:53 +0200 Subject: [PATCH 132/823] ARM: dts: imx6ul: fix clock frequency property name of I2C buses MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A few boards set clock frequency of their I2C buses with "clock_frequency" property. The right property is "clock-frequency". Signed-off-by: Sébastien Szymanski Reviewed-by: Fabio Estevam Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6ul-14x14-evk.dtsi | 2 +- arch/arm/boot/dts/imx6ul-geam.dts | 2 +- arch/arm/boot/dts/imx6ul-isiot.dtsi | 2 +- arch/arm/boot/dts/imx6ul-pico-hobbit.dts | 2 +- arch/arm/boot/dts/imx6ul-pico-pi.dts | 4 ++-- 5 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi index cbe61b61a212..c2a9dd57e56a 100644 --- a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi +++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi @@ -112,7 +112,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; diff --git a/arch/arm/boot/dts/imx6ul-geam.dts b/arch/arm/boot/dts/imx6ul-geam.dts index 21ddd359d3ed..9f63706383a7 100644 --- a/arch/arm/boot/dts/imx6ul-geam.dts +++ b/arch/arm/boot/dts/imx6ul-geam.dts @@ -156,7 +156,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; diff --git a/arch/arm/boot/dts/imx6ul-isiot.dtsi b/arch/arm/boot/dts/imx6ul-isiot.dtsi index b26d4f57c655..cc9adce638f5 100644 --- a/arch/arm/boot/dts/imx6ul-isiot.dtsi +++ b/arch/arm/boot/dts/imx6ul-isiot.dtsi @@ -148,7 +148,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; diff --git a/arch/arm/boot/dts/imx6ul-pico-hobbit.dts b/arch/arm/boot/dts/imx6ul-pico-hobbit.dts index 39eeeddac39e..09f7ffa9ad8c 100644 --- a/arch/arm/boot/dts/imx6ul-pico-hobbit.dts +++ b/arch/arm/boot/dts/imx6ul-pico-hobbit.dts @@ -43,7 +43,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; diff --git a/arch/arm/boot/dts/imx6ul-pico-pi.dts b/arch/arm/boot/dts/imx6ul-pico-pi.dts index de07357b27fc..6cd7d5877d20 100644 --- a/arch/arm/boot/dts/imx6ul-pico-pi.dts +++ b/arch/arm/boot/dts/imx6ul-pico-pi.dts @@ -43,7 +43,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; @@ -58,7 +58,7 @@ }; &i2c3 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c3>; status = "okay"; From 51b75b5b563a2637f9d8dc5bd02a31b2ff9e5ea0 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 19 Jul 2019 20:46:50 +0200 Subject: [PATCH 133/823] x86/mm: Check for pfn instead of page in vmalloc_sync_one() Do not require a struct page for the mapped memory location because it might not exist. This can happen when an ioremapped region is mapped with 2MB pages. Fixes: 5d72b4fba40ef ('x86, mm: support huge I/O mapping capability I/F') Signed-off-by: Joerg Roedel Signed-off-by: Thomas Gleixner Reviewed-by: Dave Hansen Link: https://lkml.kernel.org/r/20190719184652.11391-2-joro@8bytes.org --- arch/x86/mm/fault.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 6c46095cd0d9..e64173db4970 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -183,7 +183,7 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) if (!pmd_present(*pmd)) set_pmd(pmd, *pmd_k); else - BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k)); + BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k)); return pmd_k; } From 8e998fc24de47c55b47a887f6c95ab91acd4a720 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 19 Jul 2019 20:46:51 +0200 Subject: [PATCH 134/823] x86/mm: Sync also unmappings in vmalloc_sync_all() With huge-page ioremap areas the unmappings also need to be synced between all page-tables. Otherwise it can cause data corruption when a region is unmapped and later re-used. Make the vmalloc_sync_one() function ready to sync unmappings and make sure vmalloc_sync_all() iterates over all page-tables even when an unmapped PMD is found. Fixes: 5d72b4fba40ef ('x86, mm: support huge I/O mapping capability I/F') Signed-off-by: Joerg Roedel Signed-off-by: Thomas Gleixner Reviewed-by: Dave Hansen Link: https://lkml.kernel.org/r/20190719184652.11391-3-joro@8bytes.org --- arch/x86/mm/fault.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e64173db4970..9ceacd1156db 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -177,11 +177,12 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) pmd = pmd_offset(pud, address); pmd_k = pmd_offset(pud_k, address); + + if (pmd_present(*pmd) != pmd_present(*pmd_k)) + set_pmd(pmd, *pmd_k); + if (!pmd_present(*pmd_k)) return NULL; - - if (!pmd_present(*pmd)) - set_pmd(pmd, *pmd_k); else BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k)); @@ -203,17 +204,13 @@ void vmalloc_sync_all(void) spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { spinlock_t *pgt_lock; - pmd_t *ret; /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); - ret = vmalloc_sync_one(page_address(page), address); + vmalloc_sync_one(page_address(page), address); spin_unlock(pgt_lock); - - if (!ret) - break; } spin_unlock(&pgd_lock); } From 3f8fd02b1bf1d7ba964485a56f2f4b53ae88c167 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 19 Jul 2019 20:46:52 +0200 Subject: [PATCH 135/823] mm/vmalloc: Sync unmappings in __purge_vmap_area_lazy() On x86-32 with PTI enabled, parts of the kernel page-tables are not shared between processes. This can cause mappings in the vmalloc/ioremap area to persist in some page-tables after the region is unmapped and released. When the region is re-used the processes with the old mappings do not fault in the new mappings but still access the old ones. This causes undefined behavior, in reality often data corruption, kernel oopses and panics and even spontaneous reboots. Fix this problem by activly syncing unmaps in the vmalloc/ioremap area to all page-tables in the system before the regions can be re-used. References: https://bugzilla.suse.com/show_bug.cgi?id=1118689 Fixes: 5d72b4fba40ef ('x86, mm: support huge I/O mapping capability I/F') Signed-off-by: Joerg Roedel Signed-off-by: Thomas Gleixner Reviewed-by: Dave Hansen Link: https://lkml.kernel.org/r/20190719184652.11391-4-joro@8bytes.org --- mm/vmalloc.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 4fa8d84599b0..e0fc963acc41 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1258,6 +1258,12 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) if (unlikely(valist == NULL)) return false; + /* + * First make sure the mappings are removed from all page-tables + * before they are freed. + */ + vmalloc_sync_all(); + /* * TODO: to calculate a flush range without looping. * The list can be up to lazy_max_pages() elements. @@ -3038,6 +3044,9 @@ EXPORT_SYMBOL(remap_vmalloc_range); /* * Implement a stub for vmalloc_sync_all() if the architecture chose not to * have one. + * + * The purpose of this function is to make sure the vmalloc area + * mappings are identical in all page-tables in the system. */ void __weak vmalloc_sync_all(void) { From 2af7c85714d8cafadf925d55441458eae312cd6b Mon Sep 17 00:00:00 2001 From: Eiichi Tsukata Date: Mon, 22 Jul 2019 17:32:16 +0900 Subject: [PATCH 136/823] x86/stacktrace: Prevent access_ok() warnings in arch_stack_walk_user() When arch_stack_walk_user() is called from atomic contexts, access_ok() can trigger the following warning if compiled with CONFIG_DEBUG_ATOMIC_SLEEP=y. Reproducer: // CONFIG_DEBUG_ATOMIC_SLEEP=y # cd /sys/kernel/debug/tracing # echo 1 > options/userstacktrace # echo 1 > events/irq/irq_handler_entry/enable WARNING: CPU: 0 PID: 2649 at arch/x86/kernel/stacktrace.c:103 arch_stack_walk_user+0x6e/0xf6 CPU: 0 PID: 2649 Comm: bash Not tainted 5.3.0-rc1+ #99 RIP: 0010:arch_stack_walk_user+0x6e/0xf6 Call Trace: stack_trace_save_user+0x10a/0x16d trace_buffer_unlock_commit_regs+0x185/0x240 trace_event_buffer_commit+0xec/0x330 trace_event_raw_event_irq_handler_entry+0x159/0x1e0 __handle_irq_event_percpu+0x22d/0x440 handle_irq_event_percpu+0x70/0x100 handle_irq_event+0x5a/0x8b handle_edge_irq+0x12f/0x3f0 handle_irq+0x34/0x40 do_IRQ+0xa6/0x1f0 common_interrupt+0xf/0xf Fix it by calling __range_not_ok() directly instead of access_ok() as copy_from_user_nmi() does. This is fine here because the actual copy is inside a pagefault disabled region. Reported-by: Juri Lelli Signed-off-by: Eiichi Tsukata Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20190722083216.16192-2-devel@etsukata.com --- arch/x86/kernel/stacktrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 4f36d3241faf..2d6898c2cb64 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -100,7 +100,7 @@ copy_stack_frame(const void __user *fp, struct stack_frame_user *frame) { int ret; - if (!access_ok(fp, sizeof(*frame))) + if (__range_not_ok(fp, sizeof(*frame), TASK_SIZE)) return 0; ret = 1; From d02f1aa39189e0619c3525d5cd03254e61bf606a Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 21 Jul 2019 17:24:18 +0200 Subject: [PATCH 137/823] x86/sysfb_efi: Add quirks for some devices with swapped width and height Some Lenovo 2-in-1s with a detachable keyboard have a portrait screen but advertise a landscape resolution and pitch, resulting in a messed up display if the kernel tries to show anything on the efifb (because of the wrong pitch). Fix this by adding a new DMI match table for devices which need to have their width and height swapped. At first it was tried to use the existing table for overriding some of the efifb parameters, but some of the affected devices have variants with different LCD resolutions which will not work with hardcoded override values. Reference: https://bugzilla.redhat.com/show_bug.cgi?id=1730783 Signed-off-by: Hans de Goede Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190721152418.11644-1-hdegoede@redhat.com --- arch/x86/kernel/sysfb_efi.c | 46 +++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c index 8eb67a670b10..653b7f617b61 100644 --- a/arch/x86/kernel/sysfb_efi.c +++ b/arch/x86/kernel/sysfb_efi.c @@ -230,9 +230,55 @@ static const struct dmi_system_id efifb_dmi_system_table[] __initconst = { {}, }; +/* + * Some devices have a portrait LCD but advertise a landscape resolution (and + * pitch). We simply swap width and height for these devices so that we can + * correctly deal with some of them coming with multiple resolutions. + */ +static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = { + { + /* + * Lenovo MIIX310-10ICR, only some batches have the troublesome + * 800x1280 portrait screen. Luckily the portrait version has + * its own BIOS version, so we match on that. + */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "MIIX 310-10ICR"), + DMI_EXACT_MATCH(DMI_BIOS_VERSION, "1HCN44WW"), + }, + }, + { + /* Lenovo MIIX 320-10ICR with 800x1280 portrait screen */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, + "Lenovo MIIX 320-10ICR"), + }, + }, + { + /* Lenovo D330 with 800x1280 or 1200x1920 portrait screen */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, + "Lenovo ideapad D330-10IGM"), + }, + }, + {}, +}; + __init void sysfb_apply_efi_quirks(void) { if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS)) dmi_check_system(efifb_dmi_system_table); + + if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI && + dmi_check_system(efifb_dmi_swap_width_height)) { + u16 temp = screen_info.lfb_width; + + screen_info.lfb_width = screen_info.lfb_height; + screen_info.lfb_height = temp; + screen_info.lfb_linelength = 4 * screen_info.lfb_width; + } } From 385065734cd417b9d7739b2ebb62c960aeb3ccb5 Mon Sep 17 00:00:00 2001 From: Cao jin Date: Fri, 19 Jul 2019 16:16:35 +0800 Subject: [PATCH 138/823] x86/irq/64: Update stale comment Commit e6401c130931 ("x86/irq/64: Split the IRQ stack into its own pages") missed to update one piece of comment as it did to its peer in Xen, which will confuse people who still need to read comment. Signed-off-by: Cao jin Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20190719081635.26528-1-caoj.fnst@cn.fujitsu.com --- arch/x86/kernel/head_64.S | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index a6342c899be5..f3d3e9646a99 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -193,10 +193,10 @@ ENTRY(secondary_startup_64) /* Set up %gs. * - * The base of %gs always points to the bottom of the irqstack - * union. If the stack protector canary is enabled, it is - * located at %gs:40. Note that, on SMP, the boot cpu uses - * init data section till per cpu areas are set up. + * The base of %gs always points to fixed_percpu_data. If the + * stack protector canary is enabled, it is located at %gs:40. + * Note that, on SMP, the boot cpu uses init data section until + * the per cpu areas are set up. */ movl $MSR_GS_BASE,%ecx movl initial_gs(%rip),%eax From f9adc23ee91e6f561bb70c6147d8d45bd164d62f Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 16 Jul 2019 09:22:03 +0300 Subject: [PATCH 139/823] futex: Cleanup generic SMP variant of arch_futex_atomic_op_inuser() The generic SMP variant of arch_futex_atomic_op_inuser() returns always -ENOSYS so the switch case and surrounding code are pointless. Remove it and just return -ENOSYS. Signed-off-by: Vasily Averin Signed-off-by: Thomas Gleixner Acked-by: Arnd Bergmann Link: https://lkml.kernel.org/r/12bdaca8-99eb-e576-f842-5970ab1d6a92@virtuozzo.com --- include/asm-generic/futex.h | 21 +-------------------- 1 file changed, 1 insertion(+), 20 deletions(-) diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h index 8666fe7f35d7..02970b11f71f 100644 --- a/include/asm-generic/futex.h +++ b/include/asm-generic/futex.h @@ -118,26 +118,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, static inline int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr) { - int oldval = 0, ret; - - pagefault_disable(); - - switch (op) { - case FUTEX_OP_SET: - case FUTEX_OP_ADD: - case FUTEX_OP_OR: - case FUTEX_OP_ANDN: - case FUTEX_OP_XOR: - default: - ret = -ENOSYS; - } - - pagefault_enable(); - - if (!ret) - *oval = oldval; - - return ret; + return -ENOSYS; } static inline int From f76cb066edd1eef84edc85e5dd93c8aee71992da Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Fri, 19 Jul 2019 23:25:14 +0800 Subject: [PATCH 140/823] powercap: Invoke powercap_init() and rapl_init() earlier The MMIO RAPL interface driver depends on both powercap subsystem and the intel_rapl_common code. But when all of them are built-in, the MMIO RAPL interface driver can be loaded before the other two and this breaks the system during boot. Fix this by adjusting the init order of the powercap subsystem and the intel_rapl_common code, so that it can be initialized first. Fixes: 555c45fe0d04 ("int340X/processor_thermal_device: add support for MMIO RAPL") Reported-by: Kenneth R. Crudup Tested-by: Kenneth R. Crudup Signed-off-by: Zhang Rui [ rjw: Subject & changelog ] Signed-off-by: Rafael J. Wysocki --- drivers/powercap/intel_rapl_common.c | 2 +- drivers/powercap/powercap_sys.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index 9fd6dd342169..6df481896b5f 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -1454,7 +1454,7 @@ static void __exit rapl_exit(void) unregister_pm_notifier(&rapl_pm_notifier); } -module_init(rapl_init); +fs_initcall(rapl_init); module_exit(rapl_exit); MODULE_DESCRIPTION("Intel Runtime Average Power Limit (RAPL) common code"); diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c index 540e8aafc990..f808c5fa9838 100644 --- a/drivers/powercap/powercap_sys.c +++ b/drivers/powercap/powercap_sys.c @@ -671,7 +671,7 @@ static int __init powercap_init(void) return class_register(&powercap_class); } -device_initcall(powercap_init); +fs_initcall(powercap_init); MODULE_DESCRIPTION("PowerCap sysfs Driver"); MODULE_AUTHOR("Srinivas Pandruvada "); From 85751e9e5b1480fc675106aeaf94fadb8028469b Mon Sep 17 00:00:00 2001 From: Vincenzo Frascino Date: Wed, 10 Jul 2019 15:01:19 +0100 Subject: [PATCH 141/823] arm64: vdso: Fix population of AT_SYSINFO_EHDR for compat vdso Prior to the introduction of Unified vDSO support and compat layer for vDSO on arm64, AT_SYSINFO_EHDR was not defined for compat tasks. In the current implementation, AT_SYSINFO_EHDR is defined even if the compat vdso layer is not built, which has been shown to break Android applications using bionic: | 01-01 01:22:14.097 755 755 F libc : Fatal signal 11 (SIGSEGV), | code 1 (SEGV_MAPERR), fault addr 0x3cf2c96c in tid 755 (cameraserver), | pid 755 (cameraserver) | 01-01 01:22:14.112 759 759 F libc : Fatal signal 11 (SIGSEGV), | code 1 (SEGV_MAPERR), fault addr 0x3cf2c96c in tid 759 | (android.hardwar), pid 759 (android.hardwar) | 01-01 01:22:14.120 756 756 F libc : Fatal signal 11 (SIGSEGV) | code 1 (SEGV_MAPERR), fault addr 0x3cf2c96c in tid 756 (drmserver), | pid 756 (drmserver) Restore the old behaviour by making sure that AT_SYSINFO_EHDR for compat tasks is defined only when CONFIG_COMPAT_VDSO is enabled. Reported-by: John Stultz Tested-by: John Stultz Signed-off-by: Vincenzo Frascino Signed-off-by: Will Deacon --- arch/arm64/include/asm/elf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index 3c7037c6ba9b..b618017205a3 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -202,7 +202,7 @@ typedef compat_elf_greg_t compat_elf_gregset_t[COMPAT_ELF_NGREG]; ({ \ set_thread_flag(TIF_32BIT); \ }) -#ifdef CONFIG_GENERIC_COMPAT_VDSO +#ifdef CONFIG_COMPAT_VDSO #define COMPAT_ARCH_DLINFO \ do { \ /* \ From 2e2f3c9b864d9f21fb82aa8da5ac9adc1e020f60 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Fri, 12 Jul 2019 19:15:56 +0900 Subject: [PATCH 142/823] arm64: vdso: fix flip/flop vdso build bug Running "make" on an already compiled kernel tree will rebuild the kernel even without any modifications: $ make ARCH=arm64 CROSS_COMPILE=/usr/bin/aarch64-unknown-linux-gnu- arch/arm64/Makefile:58: CROSS_COMPILE_COMPAT not defined or empty, the compat vDSO will not be built CALL scripts/checksyscalls.sh CALL scripts/atomic/check-atomics.sh VDSOCHK arch/arm64/kernel/vdso/vdso.so.dbg VDSOSYM include/generated/vdso-offsets.h CHK include/generated/compile.h CC arch/arm64/kernel/signal.o CC arch/arm64/kernel/vdso.o CC arch/arm64/kernel/signal32.o LD arch/arm64/kernel/vdso/vdso.so.dbg OBJCOPY arch/arm64/kernel/vdso/vdso.so AS arch/arm64/kernel/vdso/vdso.o AR arch/arm64/kernel/vdso/built-in.a AR arch/arm64/kernel/built-in.a GEN .version CHK include/generated/compile.h UPD include/generated/compile.h CC init/version.o AR init/built-in.a LD vmlinux.o This is the same bug fixed in commit 92a4728608a8 ("x86/boot: Fix if_changed build flip/flop bug"). We cannot use two "if_changed" in one target. Fix this build bug by merging two commands into one function. Fixes: a7f71a2c8903 ("arm64: compat: Add vDSO") Fixes: 28b1a824a4f4 ("arm64: vdso: Substitute gettimeofday() with C implementation") Reviewed-by: Masahiro Yamada Reviewed-by: Vincenzo Frascino Tested-by: Vincenzo Frascino Co-developed-by: Vincenzo Frascino Signed-off-by: Vincenzo Frascino Signed-off-by: Naohiro Aota [will: merged in compat fix from Vincenzo and made rule names consistent] Signed-off-by: Will Deacon --- arch/arm64/kernel/vdso/Makefile | 6 ++++-- arch/arm64/kernel/vdso32/Makefile | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 4ab863045188..75d25679d879 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -57,8 +57,7 @@ $(obj)/vdso.o : $(obj)/vdso.so # Link rule for the .so file, .lds has to be first $(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE - $(call if_changed,ld) - $(call if_changed,vdso_check) + $(call if_changed,vdsold_and_vdso_check) # Strip rule for the .so file $(obj)/%.so: OBJCOPYFLAGS := -S @@ -77,6 +76,9 @@ include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE quiet_cmd_vdsocc = VDSOCC $@ cmd_vdsocc = $(CC) $(a_flags) $(c_flags) -c -o $@ $< +quiet_cmd_vdsold_and_vdso_check = LD $@ + cmd_vdsold_and_vdso_check = $(cmd_ld); $(cmd_vdso_check) + # Install commands for the unstripped file quiet_cmd_vdso_install = INSTALL $@ cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 60a4c6239712..8dfa45bc3c9f 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -144,8 +144,7 @@ $(obj)/vdso.so.dbg: $(obj)/vdso.so.raw $(obj)/$(munge) FORCE # Link rule for the .so file, .lds has to be first $(obj)/vdso.so.raw: $(src)/vdso.lds $(obj-vdso) FORCE - $(call if_changed,vdsold) - $(call if_changed,vdso_check) + $(call if_changed,vdsold_and_vdso_check) # Compilation rules for the vDSO sources $(c-obj-vdso): %.o: %.c FORCE @@ -156,6 +155,9 @@ $(asm-obj-vdso): %.o: %.S FORCE $(call if_changed_dep,vdsoas) # Actual build commands +quiet_cmd_vdsold_and_vdso_check = LD $@ + cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check) + quiet_cmd_vdsold = VDSOL $@ cmd_vdsold = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \ -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@ From a88754b23114cfb61efed56ed448c05e4cb7e20d Mon Sep 17 00:00:00 2001 From: Vincenzo Frascino Date: Fri, 19 Jul 2019 11:10:18 +0100 Subject: [PATCH 143/823] arm64: vdso: Cleanup Makefiles The recent changes to the vdso library for arm64 and the introduction of the compat vdso library have generated some misalignment in the Makefiles. Cleanup the Makefiles for vdso and vdso32 libraries: * Removing unused rules. * Unifying the displayed compilation messages. * Simplifying the generic library inclusion path for arm64 vdso. Cc: Catalin Marinas Cc: Will Deacon Signed-off-by: Vincenzo Frascino Signed-off-by: Will Deacon --- arch/arm64/kernel/vdso/Makefile | 9 +++------ arch/arm64/kernel/vdso32/Makefile | 10 +++++----- 2 files changed, 8 insertions(+), 11 deletions(-) diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 75d25679d879..dd2514bb1511 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -32,10 +32,10 @@ UBSAN_SANITIZE := n OBJECT_FILES_NON_STANDARD := y KCOV_INSTRUMENT := n -ifeq ($(c-gettimeofday-y),) CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny -else -CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny -include $(c-gettimeofday-y) + +ifneq ($(c-gettimeofday-y),) + CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y) endif # Clang versions less than 8 do not support -mcmodel=tiny @@ -73,9 +73,6 @@ include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE $(call if_changed,vdsosym) # Actual build commands -quiet_cmd_vdsocc = VDSOCC $@ - cmd_vdsocc = $(CC) $(a_flags) $(c_flags) -c -o $@ $< - quiet_cmd_vdsold_and_vdso_check = LD $@ cmd_vdsold_and_vdso_check = $(cmd_ld); $(cmd_vdso_check) diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 8dfa45bc3c9f..1fba0776ed40 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -155,17 +155,17 @@ $(asm-obj-vdso): %.o: %.S FORCE $(call if_changed_dep,vdsoas) # Actual build commands -quiet_cmd_vdsold_and_vdso_check = LD $@ +quiet_cmd_vdsold_and_vdso_check = LD32 $@ cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check) -quiet_cmd_vdsold = VDSOL $@ +quiet_cmd_vdsold = LD32 $@ cmd_vdsold = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \ -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@ -quiet_cmd_vdsocc = VDSOC $@ +quiet_cmd_vdsocc = CC32 $@ cmd_vdsocc = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $< -quiet_cmd_vdsocc_gettimeofday = VDSOC_GTD $@ +quiet_cmd_vdsocc_gettimeofday = CC32 $@ cmd_vdsocc_gettimeofday = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) $(VDSO_CFLAGS_gettimeofday_o) -c -o $@ $< -quiet_cmd_vdsoas = VDSOA $@ +quiet_cmd_vdsoas = AS32 $@ cmd_vdsoas = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_AFLAGS) -c -o $@ $< quiet_cmd_vdsomunge = MUNGE $@ From 8caa6e2be72313c170f2b30e8475323526dd7ed1 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Tue, 2 Jul 2019 14:07:27 +0100 Subject: [PATCH 144/823] arm64: stacktrace: Constify stacktrace.h functions on_accessible_stack() and on_task_stack() shouldn't (and don't) modify their task argument, so it can be const. This patch adds the appropriate modifiers. Whitespace violations in the parameter lists are fixed at the same time. No functional change. Acked-by: Catalin Marinas Signed-off-by: Dave Martin [Mark: fixup const location, whitespace] Signed-off-by: Mark Rutland Signed-off-by: Will Deacon --- arch/arm64/include/asm/stacktrace.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index df45af931459..1e0c5a7cdce5 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -64,8 +64,9 @@ static inline bool on_irq_stack(unsigned long sp, return true; } -static inline bool on_task_stack(struct task_struct *tsk, unsigned long sp, - struct stack_info *info) +static inline bool on_task_stack(const struct task_struct *tsk, + unsigned long sp, + struct stack_info *info) { unsigned long low = (unsigned long)task_stack_page(tsk); unsigned long high = low + THREAD_SIZE; @@ -112,9 +113,9 @@ static inline bool on_overflow_stack(unsigned long sp, * We can only safely access per-cpu stacks from current in a non-preemptible * context. */ -static inline bool on_accessible_stack(struct task_struct *tsk, - unsigned long sp, - struct stack_info *info) +static inline bool on_accessible_stack(const struct task_struct *tsk, + unsigned long sp, + struct stack_info *info) { if (on_task_stack(tsk, sp, info)) return true; From f3dcbe67ed424f1cf92065f9ad0cc647f2b44eac Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Tue, 2 Jul 2019 14:07:28 +0100 Subject: [PATCH 145/823] arm64: stacktrace: Factor out backtrace initialisation Some common code is required by each stacktrace user to initialise struct stackframe before the first call to unwind_frame(). In preparation for adding to the common code, this patch factors it out into a separate function start_backtrace(), and modifies the stacktrace callers appropriately. No functional change. Signed-off-by: Dave Martin [Mark: drop tsk argument, update more callsites] Signed-off-by: Mark Rutland Reviewed-by: James Morse Acked-by: Catalin Marinas Signed-off-by: Will Deacon --- arch/arm64/include/asm/stacktrace.h | 10 ++++++++++ arch/arm64/kernel/perf_callchain.c | 7 +------ arch/arm64/kernel/process.c | 7 ++----- arch/arm64/kernel/return_address.c | 9 +++------ arch/arm64/kernel/stacktrace.c | 19 ++++++------------- arch/arm64/kernel/time.c | 7 ++----- arch/arm64/kernel/traps.c | 13 ++++++------- 7 files changed, 30 insertions(+), 42 deletions(-) diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 1e0c5a7cdce5..7fa0dfedb8e9 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -131,4 +131,14 @@ static inline bool on_accessible_stack(const struct task_struct *tsk, return false; } +static inline void start_backtrace(struct stackframe *frame, + unsigned long fp, unsigned long pc) +{ + frame->fp = fp; + frame->pc = pc; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame->graph = 0; +#endif +} + #endif /* __ASM_STACKTRACE_H */ diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index 9d63514b9836..b0e03e052dd1 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -154,12 +154,7 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, return; } - frame.fp = regs->regs[29]; - frame.pc = regs->pc; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif - + start_backtrace(&frame, regs->regs[29], regs->pc); walk_stackframe(current, &frame, callchain_trace, entry); } diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 6a869d9f304f..8d836d0abc96 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -498,11 +498,8 @@ unsigned long get_wchan(struct task_struct *p) if (!stack_page) return 0; - frame.fp = thread_saved_fp(p); - frame.pc = thread_saved_pc(p); -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif + start_backtrace(&frame, thread_saved_fp(p), thread_saved_pc(p)); + do { if (unwind_frame(p, &frame)) goto out; diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c index b21cba90f82d..c4ae647d2306 100644 --- a/arch/arm64/kernel/return_address.c +++ b/arch/arm64/kernel/return_address.c @@ -38,12 +38,9 @@ void *return_address(unsigned int level) data.level = level + 2; data.addr = NULL; - frame.fp = (unsigned long)__builtin_frame_address(0); - frame.pc = (unsigned long)return_address; /* dummy */ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif - + start_backtrace(&frame, + (unsigned long)__builtin_frame_address(0), + (unsigned long)return_address); walk_stackframe(current, &frame, save_return_addr, &data); if (!data.level) diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 62d395151abe..017972c2de90 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -122,12 +122,7 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) data.skip = trace->skip; data.no_sched_functions = 0; - frame.fp = regs->regs[29]; - frame.pc = regs->pc; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif - + start_backtrace(&frame, regs->regs[29], regs->pc); walk_stackframe(current, &frame, save_trace, &data); } EXPORT_SYMBOL_GPL(save_stack_trace_regs); @@ -146,17 +141,15 @@ static noinline void __save_stack_trace(struct task_struct *tsk, data.no_sched_functions = nosched; if (tsk != current) { - frame.fp = thread_saved_fp(tsk); - frame.pc = thread_saved_pc(tsk); + start_backtrace(&frame, thread_saved_fp(tsk), + thread_saved_pc(tsk)); } else { /* We don't want this function nor the caller */ data.skip += 2; - frame.fp = (unsigned long)__builtin_frame_address(0); - frame.pc = (unsigned long)__save_stack_trace; + start_backtrace(&frame, + (unsigned long)__builtin_frame_address(0), + (unsigned long)__save_stack_trace); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif walk_stackframe(tsk, &frame, save_trace, &data); diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index 9f25aedeac9d..0b2946414dc9 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -38,11 +38,8 @@ unsigned long profile_pc(struct pt_regs *regs) if (!in_lock_functions(regs->pc)) return regs->pc; - frame.fp = regs->regs[29]; - frame.pc = regs->pc; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif + start_backtrace(&frame, regs->regs[29], regs->pc); + do { int ret = unwind_frame(NULL, &frame); if (ret < 0) diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 8c03456dade6..d3313797cca9 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -100,18 +100,17 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) return; if (tsk == current) { - frame.fp = (unsigned long)__builtin_frame_address(0); - frame.pc = (unsigned long)dump_backtrace; + start_backtrace(&frame, + (unsigned long)__builtin_frame_address(0), + (unsigned long)dump_backtrace); } else { /* * task blocked in __switch_to */ - frame.fp = thread_saved_fp(tsk); - frame.pc = thread_saved_pc(tsk); + start_backtrace(&frame, + thread_saved_fp(tsk), + thread_saved_pc(tsk)); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif printk("Call trace:\n"); do { From 592700f094be229b5c9cc1192d5cea46eb4c7afc Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 2 Jul 2019 14:07:29 +0100 Subject: [PATCH 146/823] arm64: stacktrace: Better handle corrupted stacks The arm64 stacktrace code is careful to only dereference frame records in valid stack ranges, ensuring that a corrupted frame record won't result in a faulting access. However, it's still possible for corrupt frame records to result in infinite loops in the stacktrace code, which is also undesirable. This patch ensures that we complete a stacktrace in finite time, by keeping track of which stacks we have already completed unwinding, and verifying that if the next frame record is on the same stack, it is at a higher address. As this has turned out to be particularly subtle, comments are added to explain the procedure. Signed-off-by: Mark Rutland Reviewed-by: James Morse Tested-by: James Morse Acked-by: Dave Martin Acked-by: Catalin Marinas Cc: Tengfei Fan Signed-off-by: Will Deacon --- arch/arm64/include/asm/stacktrace.h | 57 +++++++++++++++++++++++++---- arch/arm64/kernel/stacktrace.c | 40 +++++++++++++++++++- 2 files changed, 88 insertions(+), 9 deletions(-) diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 7fa0dfedb8e9..4d9b1f48dc39 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -8,19 +8,12 @@ #include #include #include +#include #include #include #include -struct stackframe { - unsigned long fp; - unsigned long pc; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - int graph; -#endif -}; - enum stack_type { STACK_TYPE_UNKNOWN, STACK_TYPE_TASK, @@ -28,6 +21,7 @@ enum stack_type { STACK_TYPE_OVERFLOW, STACK_TYPE_SDEI_NORMAL, STACK_TYPE_SDEI_CRITICAL, + __NR_STACK_TYPES }; struct stack_info { @@ -36,6 +30,37 @@ struct stack_info { enum stack_type type; }; +/* + * A snapshot of a frame record or fp/lr register values, along with some + * accounting information necessary for robust unwinding. + * + * @fp: The fp value in the frame record (or the real fp) + * @pc: The fp value in the frame record (or the real lr) + * + * @stacks_done: Stacks which have been entirely unwound, for which it is no + * longer valid to unwind to. + * + * @prev_fp: The fp that pointed to this frame record, or a synthetic value + * of 0. This is used to ensure that within a stack, each + * subsequent frame record is at an increasing address. + * @prev_type: The type of stack this frame record was on, or a synthetic + * value of STACK_TYPE_UNKNOWN. This is used to detect a + * transition from one stack to another. + * + * @graph: When FUNCTION_GRAPH_TRACER is selected, holds the index of a + * replacement lr value in the ftrace graph stack. + */ +struct stackframe { + unsigned long fp; + unsigned long pc; + DECLARE_BITMAP(stacks_done, __NR_STACK_TYPES); + unsigned long prev_fp; + enum stack_type prev_type; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + int graph; +#endif +}; + extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame); extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame, int (*fn)(struct stackframe *, void *), void *data); @@ -117,6 +142,9 @@ static inline bool on_accessible_stack(const struct task_struct *tsk, unsigned long sp, struct stack_info *info) { + if (info) + info->type = STACK_TYPE_UNKNOWN; + if (on_task_stack(tsk, sp, info)) return true; if (tsk != current || preemptible()) @@ -139,6 +167,19 @@ static inline void start_backtrace(struct stackframe *frame, #ifdef CONFIG_FUNCTION_GRAPH_TRACER frame->graph = 0; #endif + + /* + * Prime the first unwind. + * + * In unwind_frame() we'll check that the FP points to a valid stack, + * which can't be STACK_TYPE_UNKNOWN, and the first unwind will be + * treated as a transition to whichever stack that happens to be. The + * prev_fp value won't be used, but we set it to 0 such that it is + * definitely not an accessible stack address. + */ + bitmap_zero(frame->stacks_done, __NR_STACK_TYPES); + frame->prev_fp = 0; + frame->prev_type = STACK_TYPE_UNKNOWN; } #endif /* __ASM_STACKTRACE_H */ diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 017972c2de90..2b160ae594eb 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -29,9 +29,18 @@ * ldp x29, x30, [sp] * add sp, sp, #0x10 */ + +/* + * Unwind from one frame record (A) to the next frame record (B). + * + * We terminate early if the location of B indicates a malformed chain of frame + * records (e.g. a cycle), determined based on the location and fp value of A + * and the location (but not the fp value) of B. + */ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) { unsigned long fp = frame->fp; + struct stack_info info; if (fp & 0xf) return -EINVAL; @@ -39,11 +48,40 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) if (!tsk) tsk = current; - if (!on_accessible_stack(tsk, fp, NULL)) + if (!on_accessible_stack(tsk, fp, &info)) return -EINVAL; + if (test_bit(info.type, frame->stacks_done)) + return -EINVAL; + + /* + * As stacks grow downward, any valid record on the same stack must be + * at a strictly higher address than the prior record. + * + * Stacks can nest in several valid orders, e.g. + * + * TASK -> IRQ -> OVERFLOW -> SDEI_NORMAL + * TASK -> SDEI_NORMAL -> SDEI_CRITICAL -> OVERFLOW + * + * ... but the nesting itself is strict. Once we transition from one + * stack to another, it's never valid to unwind back to that first + * stack. + */ + if (info.type == frame->prev_type) { + if (fp <= frame->prev_fp) + return -EINVAL; + } else { + set_bit(frame->prev_type, frame->stacks_done); + } + + /* + * Record this frame record's values and location. The prev_fp and + * prev_type are only meaningful to the next unwind_frame() invocation. + */ frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp)); frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8)); + frame->prev_fp = fp; + frame->prev_type = info.type; #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (tsk->ret_stack && From d16af870a70e0e399126c6419f92e7badf5e465b Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Wed, 12 Jun 2019 17:00:33 +0100 Subject: [PATCH 147/823] arm64/sve: Factor out FPSIMD to SVE state conversion Currently we convert from FPSIMD to SVE register state in memory in two places. To ease future maintenance, let's consolidate this in one place. Reviewed-by: Julien Grall Acked-by: Catalin Marinas Signed-off-by: Dave Martin Signed-off-by: Will Deacon --- arch/arm64/kernel/fpsimd.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index eec4776ae5f0..386d848e6b42 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -406,6 +406,18 @@ static __uint128_t arm64_cpu_to_le128(__uint128_t x) #define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x) +static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst, + unsigned int vq) +{ + unsigned int i; + __uint128_t *p; + + for (i = 0; i < 32; ++i) { + p = (__uint128_t *)ZREG(sst, vq, i); + *p = arm64_cpu_to_le128(fst->vregs[i]); + } +} + /* * Transfer the FPSIMD state in task->thread.uw.fpsimd_state to * task->thread.sve_state. @@ -423,17 +435,12 @@ static void fpsimd_to_sve(struct task_struct *task) unsigned int vq; void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; - unsigned int i; - __uint128_t *p; if (!system_supports_sve()) return; vq = sve_vq_from_vl(task->thread.sve_vl); - for (i = 0; i < 32; ++i) { - p = (__uint128_t *)ZREG(sst, vq, i); - *p = arm64_cpu_to_le128(fst->vregs[i]); - } + __fpsimd_to_sve(sst, fst, vq); } /* @@ -550,8 +557,6 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) unsigned int vq; void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; - unsigned int i; - __uint128_t *p; if (!test_tsk_thread_flag(task, TIF_SVE)) return; @@ -559,11 +564,7 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) vq = sve_vq_from_vl(task->thread.sve_vl); memset(sst, 0, SVE_SIG_REGS_SIZE(vq)); - - for (i = 0; i < 32; ++i) { - p = (__uint128_t *)ZREG(sst, vq, i); - *p = arm64_cpu_to_le128(fst->vregs[i]); - } + __fpsimd_to_sve(sst, fst, vq); } int sve_set_vector_length(struct task_struct *task, From ed2f3e9ff637c7c9f65b98468a084393683ff93b Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Wed, 12 Jun 2019 17:00:34 +0100 Subject: [PATCH 148/823] arm64/sve: Fix a couple of magic numbers for the Z-reg count There are some hand-written instances of "32" to express the number of SVE Z-registers. Since this code was written a #define was added for this, so convert trivial instances of this magic number as appropriate. No functional change. Reviewed-by: Julien Grall Acked-by: Catalin Marinas Signed-off-by: Dave Martin Signed-off-by: Will Deacon --- arch/arm64/kernel/fpsimd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 386d848e6b42..37d3912cfe06 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -412,7 +412,7 @@ static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst, unsigned int i; __uint128_t *p; - for (i = 0; i < 32; ++i) { + for (i = 0; i < SVE_NUM_ZREGS; ++i) { p = (__uint128_t *)ZREG(sst, vq, i); *p = arm64_cpu_to_le128(fst->vregs[i]); } @@ -466,7 +466,7 @@ static void sve_to_fpsimd(struct task_struct *task) return; vq = sve_vq_from_vl(task->thread.sve_vl); - for (i = 0; i < 32; ++i) { + for (i = 0; i < SVE_NUM_ZREGS; ++i) { p = (__uint128_t const *)ZREG(sst, vq, i); fst->vregs[i] = arm64_le128_to_cpu(*p); } From 5a9060e9437be47f92f85a2b5c7cd73314d080e8 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Tue, 2 Jul 2019 11:02:55 +0530 Subject: [PATCH 149/823] arm64: mm: Drop pte_huge() This helper is required from generic huge_pte_alloc() which is available when arch subscribes ARCH_WANT_GENERAL_HUGETLB. arm64 implements it's own huge_pte_alloc() and does not depend on the generic definition. Drop this helper which is redundant on arm64. Cc: Mark Rutland Cc: Steve Capper Acked-by: Catalin Marinas Signed-off-by: Anshuman Khandual Signed-off-by: Will Deacon --- arch/arm64/include/asm/pgtable.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 87a4b2ddc1a1..3f5461f7b560 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -301,7 +301,6 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b) /* * Huge pte definitions. */ -#define pte_huge(pte) (!(pte_val(pte) & PTE_TABLE_BIT)) #define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT)) /* From cf64527bb33f6cec2ed50f89182fc4688d0056b6 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Sun, 21 Jul 2019 13:52:18 +0200 Subject: [PATCH 150/823] KVM: nVMX: Clear pending KVM_REQ_GET_VMCS12_PAGES when leaving nested Letting this pend may cause nested_get_vmcs12_pages to run against an invalid state, corrupting the effective vmcs of L1. This was triggerable in QEMU after a guest corruption in L2, followed by a L1 reset. Signed-off-by: Jan Kiszka Reviewed-by: Liran Alon Cc: stable@vger.kernel.org Fixes: 7f7f1ba33cf2 ("KVM: x86: do not load vmcs12 pages while still in SMM") Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/nested.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 0f1378789bd0..4cdab4b4eff1 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -220,6 +220,8 @@ static void free_nested(struct kvm_vcpu *vcpu) if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon) return; + kvm_clear_request(KVM_REQ_GET_VMCS12_PAGES, vcpu); + vmx->nested.vmxon = false; vmx->nested.smm.vmxon = false; free_vpid(vmx->nested.vpid02); From ec269475cba7bcdd1eb8fdf8e87f4c6c81a376fe Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 22 Jul 2019 13:31:27 +0200 Subject: [PATCH 151/823] Revert "kvm: x86: Use task structs fpu field for user" This reverts commit 240c35a3783ab9b3a0afaba0dde7291295680a6b ("kvm: x86: Use task structs fpu field for user", 2018-11-06). The commit is broken and causes QEMU's FPU state to be destroyed when KVM_RUN is preempted. Fixes: 240c35a3783a ("kvm: x86: Use task structs fpu field for user") Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 7 ++++--- arch/x86/kvm/x86.c | 4 ++-- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 0cc5b611a113..b2f1ffb937af 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -607,15 +607,16 @@ struct kvm_vcpu_arch { /* * QEMU userspace and the guest each have their own FPU state. - * In vcpu_run, we switch between the user, maintained in the - * task_struct struct, and guest FPU contexts. While running a VCPU, - * the VCPU thread will have the guest FPU context. + * In vcpu_run, we switch between the user and guest FPU contexts. + * While running a VCPU, the VCPU thread will have the guest FPU + * context. * * Note that while the PKRU state lives inside the fpu registers, * it is switched out separately at VMENTER and VMEXIT time. The * "guest_fpu" state here contains the guest FPU context, with the * host PRKU bits. */ + struct fpu user_fpu; struct fpu *guest_fpu; u64 xcr0; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 58305cf81182..cf2afdf8facf 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8270,7 +8270,7 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { fpregs_lock(); - copy_fpregs_to_fpstate(¤t->thread.fpu); + copy_fpregs_to_fpstate(&vcpu->arch.user_fpu); /* PKRU is separately restored in kvm_x86_ops->run. */ __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state, ~XFEATURE_MASK_PKRU); @@ -8287,7 +8287,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) fpregs_lock(); copy_fpregs_to_fpstate(vcpu->arch.guest_fpu); - copy_kernel_to_fpregs(¤t->thread.fpu.state); + copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state); fpregs_mark_activate(); fpregs_unlock(); From e751732486eb3f159089a64d1901992b1357e7cc Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Mon, 22 Jul 2019 12:26:20 +0800 Subject: [PATCH 152/823] KVM: X86: Fix fpu state crash in kvm guest MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The idea before commit 240c35a37 (which has just been reverted) was that we have the following FPU states: userspace (QEMU) guest --------------------------------------------------------------------------- processor vcpu->arch.guest_fpu >>> KVM_RUN: kvm_load_guest_fpu vcpu->arch.user_fpu processor >>> preempt out vcpu->arch.user_fpu current->thread.fpu >>> preempt in vcpu->arch.user_fpu processor >>> back to userspace >>> kvm_put_guest_fpu processor vcpu->arch.guest_fpu --------------------------------------------------------------------------- With the new lazy model we want to get the state back to the processor when schedule in from current->thread.fpu. Reported-by: Thomas Lambertz Reported-by: anthony Tested-by: anthony Cc: Paolo Bonzini Cc: Radim Krčmář Cc: Thomas Lambertz Cc: anthony Cc: stable@vger.kernel.org Fixes: 5f409e20b (x86/fpu: Defer FPU state load until return to userspace) Signed-off-by: Wanpeng Li [Add a comment in front of the warning. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cf2afdf8facf..7eb56f8e2ea8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3306,6 +3306,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_x86_ops->vcpu_load(vcpu, cpu); + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); + /* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) { adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment); @@ -7990,9 +7994,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) trace_kvm_entry(vcpu->vcpu_id); guest_enter_irqoff(); - fpregs_assert_state_consistent(); - if (test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_return(); + /* The preempt notifier should have taken care of the FPU already. */ + WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD)); if (unlikely(vcpu->arch.switch_db_regs)) { set_debugreg(0, 7); From d9a710e5fc4941944d565b013414e9fdc66242b5 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Mon, 22 Jul 2019 12:26:21 +0800 Subject: [PATCH 153/823] KVM: X86: Dynamically allocate user_fpu MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After reverting commit 240c35a3783a (kvm: x86: Use task structs fpu field for user), struct kvm_vcpu is 19456 bytes on my server, PAGE_ALLOC_COSTLY_ORDER(3) is the order at which allocations are deemed costly to service. In serveless scenario, one host can service hundreds/thoudands firecracker/kata-container instances, howerver, new instance will fail to launch after memory is too fragmented to allocate kvm_vcpu struct on host, this was observed in some cloud provider product environments. This patch dynamically allocates user_fpu, kvm_vcpu is 15168 bytes now on my Skylake server. Cc: Paolo Bonzini Cc: Radim Krčmář Signed-off-by: Wanpeng Li Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/svm.c | 13 ++++++++++++- arch/x86/kvm/vmx/vmx.c | 13 ++++++++++++- arch/x86/kvm/x86.c | 4 ++-- 4 files changed, 27 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b2f1ffb937af..e74f0711eaaf 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -616,7 +616,7 @@ struct kvm_vcpu_arch { * "guest_fpu" state here contains the guest FPU context, with the * host PRKU bits. */ - struct fpu user_fpu; + struct fpu *user_fpu; struct fpu *guest_fpu; u64 xcr0; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 19f69df96758..7eafc6907861 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2143,12 +2143,20 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) goto out; } + svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!svm->vcpu.arch.user_fpu) { + printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); + err = -ENOMEM; + goto free_partial_svm; + } + svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL_ACCOUNT); if (!svm->vcpu.arch.guest_fpu) { printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); err = -ENOMEM; - goto free_partial_svm; + goto free_user_fpu; } err = kvm_vcpu_init(&svm->vcpu, kvm, id); @@ -2211,6 +2219,8 @@ uninit: kvm_vcpu_uninit(&svm->vcpu); free_svm: kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); +free_user_fpu: + kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); free_partial_svm: kmem_cache_free(kvm_vcpu_cache, svm); out: @@ -2241,6 +2251,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_page(virt_to_page(svm->nested.hsave)); __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); + kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); kmem_cache_free(kvm_vcpu_cache, svm); } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index a279447eb75b..074385c86c09 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6598,6 +6598,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) free_loaded_vmcs(vmx->loaded_vmcs); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); + kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); kmem_cache_free(kvm_vcpu_cache, vmx); } @@ -6613,12 +6614,20 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx) return ERR_PTR(-ENOMEM); + vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!vmx->vcpu.arch.user_fpu) { + printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); + err = -ENOMEM; + goto free_partial_vcpu; + } + vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL_ACCOUNT); if (!vmx->vcpu.arch.guest_fpu) { printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); err = -ENOMEM; - goto free_partial_vcpu; + goto free_user_fpu; } vmx->vpid = allocate_vpid(); @@ -6721,6 +6730,8 @@ uninit_vcpu: free_vcpu: free_vpid(vmx->vpid); kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); +free_user_fpu: + kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); free_partial_vcpu: kmem_cache_free(kvm_vcpu_cache, vmx); return ERR_PTR(err); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7eb56f8e2ea8..01e18caac825 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8273,7 +8273,7 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { fpregs_lock(); - copy_fpregs_to_fpstate(&vcpu->arch.user_fpu); + copy_fpregs_to_fpstate(vcpu->arch.user_fpu); /* PKRU is separately restored in kvm_x86_ops->run. */ __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state, ~XFEATURE_MASK_PKRU); @@ -8290,7 +8290,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) fpregs_lock(); copy_fpregs_to_fpstate(vcpu->arch.guest_fpu); - copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state); + copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state); fpregs_mark_activate(); fpregs_unlock(); From c6bf2ae931adbd3e10967e12142856439a211813 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Sun, 21 Jul 2019 16:01:36 +0200 Subject: [PATCH 154/823] KVM: nVMX: Set cached_vmcs12 and cached_shadow_vmcs12 NULL after free Shall help finding use-after-free bugs earlier. Suggested-by: Liran Alon Signed-off-by: Jan Kiszka Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/nested.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 4cdab4b4eff1..ced9fba32598 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -234,7 +234,9 @@ static void free_nested(struct kvm_vcpu *vcpu) vmx->vmcs01.shadow_vmcs = NULL; } kfree(vmx->nested.cached_vmcs12); + vmx->nested.cached_vmcs12 = NULL; kfree(vmx->nested.cached_shadow_vmcs12); + vmx->nested.cached_shadow_vmcs12 = NULL; /* Unpin physical memory we referred to in the vmcs02 */ if (vmx->nested.apic_access_page) { kvm_release_page_dirty(vmx->nested.apic_access_page); From 1274204542f683e1d8491ebe9cc86284d5a8ebcc Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Fri, 19 Jul 2019 14:27:13 +0200 Subject: [PATCH 155/823] spi: pxa2xx: Balance runtime PM enable/disable on error Don't undo the PM initialization if we error out before we managed to initialize it. The call to pm_runtime_disable() without being preceded by pm_runtime_enable() would disturb the balance of the Force. In practice, this happens if we fail to allocate any of the GPIOS ("cs", "ready") due to -EPROBE_DEFER because we're getting probled before the GPIO driver. Signed-off-by: Lubomir Rintel Link: https://lore.kernel.org/r/20190719122713.3444318-1-lkundrak@v3.sk Signed-off-by: Mark Brown --- drivers/spi/spi-pxa2xx.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index fc7ab4b26880..22513caf2000 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -1831,14 +1831,16 @@ static int pxa2xx_spi_probe(struct platform_device *pdev) status = devm_spi_register_controller(&pdev->dev, controller); if (status != 0) { dev_err(&pdev->dev, "problem registering spi controller\n"); - goto out_error_clock_enabled; + goto out_error_pm_runtime_enabled; } return status; -out_error_clock_enabled: +out_error_pm_runtime_enabled: pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); + +out_error_clock_enabled: clk_disable_unprepare(ssp->clk); out_error_dma_irq_alloc: From fc62113b32c95906b3ea8ba42e91014c7d0c6fa6 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 15 Jul 2019 18:00:14 +0800 Subject: [PATCH 156/823] mmc: host: sdhci-sprd: Fix the missing pm_runtime_put_noidle() When the SD host controller tries to probe again due to the derferred probe mechanism, it will always keep the SD host device as runtime resume state due to missing the runtime put operation in error path last time. Thus add the pm_runtime_put_noidle() in error path to make the PM runtime counter balance, which can make the SD host device's PM runtime work well. Signed-off-by: Baolin Wang Acked-by: Adrian Hunter Fixes: fb8bd90f83c4 ("mmc: sdhci-sprd: Add Spreadtrum's initial host controller") Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-sprd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c index 6ee340a3fb3a..603a5d9f045a 100644 --- a/drivers/mmc/host/sdhci-sprd.c +++ b/drivers/mmc/host/sdhci-sprd.c @@ -624,6 +624,7 @@ err_cleanup_host: sdhci_cleanup_host(host); pm_runtime_disable: + pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); From ba2d139b02ba684c6c101de42fed782d6cd2b997 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Mon, 8 Jul 2019 12:56:13 -0700 Subject: [PATCH 157/823] mmc: dw_mmc: Fix occasional hang after tuning on eMMC In commit 46d179525a1f ("mmc: dw_mmc: Wait for data transfer after response errors.") we fixed a tuning-induced hang that I saw when stress testing tuning on certain SD cards. I won't re-hash that whole commit, but the summary is that as a normal part of tuning you need to deal with transfer errors and there were cases where these transfer errors was putting my system into a bad state causing all future transfers to fail. That commit fixed handling of the transfer errors for me. In downstream Chrome OS my fix landed and had the same behavior for all SD/MMC commands. However, it looks like when the commit landed upstream we limited it to only SD tuning commands. Presumably this was to try to get around problems that Alim Akhtar reported on exynos [1]. Unfortunately while stress testing reboots (and suspend/resume) on some rk3288-based Chromebooks I found the same problem on the eMMC on some of my Chromebooks (the ones with Hynix eMMC). Since the eMMC tuning command is different (MMC_SEND_TUNING_BLOCK_HS200 vs. MMC_SEND_TUNING_BLOCK) we were basically getting back into the same situation. I'm hoping that whatever problems exynos was having in the past are somehow magically fixed now and we can make the behavior the same for all commands. [1] https://lkml.kernel.org/r/CAGOxZ53WfNbaMe0_AM0qBqU47kAfgmPBVZC8K8Y-_J3mDMqW4A@mail.gmail.com Fixes: 46d179525a1f ("mmc: dw_mmc: Wait for data transfer after response errors.") Signed-off-by: Douglas Anderson Cc: Marek Szyprowski Cc: Alim Akhtar Cc: Enric Balletbo i Serra Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/host/dw_mmc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index faaaf52a46d2..eea52e2c5a0c 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -2012,8 +2012,7 @@ static void dw_mci_tasklet_func(unsigned long priv) * delayed. Allowing the transfer to take place * avoids races and keeps things simple. */ - if ((err != -ETIMEDOUT) && - (cmd->opcode == MMC_SEND_TUNING_BLOCK)) { + if (err != -ETIMEDOUT) { state = STATE_SENDING_DATA; continue; } From 665e985c2f41bebc3e6cee7e04c36a44afbc58f7 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 9 Jul 2019 22:04:19 -0700 Subject: [PATCH 158/823] mmc: meson-mx-sdio: Fix misuse of GENMASK macro Arguments are supposed to be ordered high then low. Signed-off-by: Joe Perches Reviewed-by: Neil Armstrong Fixes: ed80a13bb4c4 ("mmc: meson-mx-sdio: Add a driver for the Amlogic Meson8 and Meson8b SoCs") Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/host/meson-mx-sdio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/meson-mx-sdio.c b/drivers/mmc/host/meson-mx-sdio.c index 2d736e416775..ba9a63db73da 100644 --- a/drivers/mmc/host/meson-mx-sdio.c +++ b/drivers/mmc/host/meson-mx-sdio.c @@ -73,7 +73,7 @@ #define MESON_MX_SDIO_IRQC_IF_CONFIG_MASK GENMASK(7, 6) #define MESON_MX_SDIO_IRQC_FORCE_DATA_CLK BIT(8) #define MESON_MX_SDIO_IRQC_FORCE_DATA_CMD BIT(9) - #define MESON_MX_SDIO_IRQC_FORCE_DATA_DAT_MASK GENMASK(10, 13) + #define MESON_MX_SDIO_IRQC_FORCE_DATA_DAT_MASK GENMASK(13, 10) #define MESON_MX_SDIO_IRQC_SOFT_RESET BIT(15) #define MESON_MX_SDIO_IRQC_FORCE_HALT BIT(30) #define MESON_MX_SDIO_IRQC_HALT_HOLE BIT(31) From 0aafd138b322d0b1bec3f14cdef4be3374d9fc39 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 16 Jul 2019 18:43:08 +0100 Subject: [PATCH 159/823] MAINTAINERS: Update my email address to @kernel.org I will soon lose access to my @arm.com email address, so let's update the MAINTAINERS file to point to my @kernel.org address, as well as .mailmap for good measure. Note that my @arm.com address will still work, but someone else will be reading whatever is sent there. Don't say you didn't know! Signed-off-by: Marc Zyngier Signed-off-by: Will Deacon --- .mailmap | 1 + MAINTAINERS | 8 ++++---- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/.mailmap b/.mailmap index 0fef932de3db..23cfed2e015c 100644 --- a/.mailmap +++ b/.mailmap @@ -132,6 +132,7 @@ Linus Lüssing Li Yang Li Yang Maciej W. Rozycki +Marc Zyngier Marcin Nowakowski Mark Brown Mark Yao diff --git a/MAINTAINERS b/MAINTAINERS index 783569e3c4b4..b3d1eaddc5cf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1194,7 +1194,7 @@ F: include/uapi/linux/if_arcnet.h ARM ARCHITECTED TIMER DRIVER M: Mark Rutland -M: Marc Zyngier +M: Marc Zyngier L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/include/asm/arch_timer.h @@ -8490,7 +8490,7 @@ S: Obsolete F: include/uapi/linux/ipx.h IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY) -M: Marc Zyngier +M: Marc Zyngier S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core F: Documentation/IRQ-domain.txt @@ -8508,7 +8508,7 @@ F: kernel/irq/ IRQCHIP DRIVERS M: Thomas Gleixner M: Jason Cooper -M: Marc Zyngier +M: Marc Zyngier L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core @@ -8828,7 +8828,7 @@ F: arch/x86/include/asm/svm.h F: arch/x86/kvm/svm.c KERNEL VIRTUAL MACHINE FOR ARM/ARM64 (KVM/arm, KVM/arm64) -M: Marc Zyngier +M: Marc Zyngier R: James Morse R: Julien Thierry R: Suzuki K Pouloze From 01233d47836d96264f3d66eda4514739b0ce7d9d Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Wed, 17 Jul 2019 13:33:30 +0100 Subject: [PATCH 160/823] MAINTAINERS: Fix spelling mistake in my name Fix a typo in my name for the KVM-ARM reviewers entry. Acked-by: Marc Zyngier Signed-off-by: Suzuki K Poulose Signed-off-by: Will Deacon --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index b3d1eaddc5cf..ef195bda7c70 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8831,7 +8831,7 @@ KERNEL VIRTUAL MACHINE FOR ARM/ARM64 (KVM/arm, KVM/arm64) M: Marc Zyngier R: James Morse R: Julien Thierry -R: Suzuki K Pouloze +R: Suzuki K Poulose L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: kvmarm@lists.cs.columbia.edu T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm.git From 8d419adb0511c8f0a2324fefb27752051eacc995 Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Wed, 17 Jul 2019 11:32:15 +0100 Subject: [PATCH 161/823] MAINTAINERS: Update my email address My @arm.com address will stop working in a couple of weeks. Update MAINTAINERS and .mailmap files with an address I'll have access to. Signed-off-by: Julien Thierry Signed-off-by: Will Deacon --- .mailmap | 1 + MAINTAINERS | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/.mailmap b/.mailmap index 23cfed2e015c..1043793cd557 100644 --- a/.mailmap +++ b/.mailmap @@ -116,6 +116,7 @@ John Stultz Juha Yrjola Juha Yrjola Juha Yrjola +Julien Thierry Kay Sievers Kenneth W Chen Konstantin Khlebnikov diff --git a/MAINTAINERS b/MAINTAINERS index ef195bda7c70..50cf99beb7af 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8830,7 +8830,7 @@ F: arch/x86/kvm/svm.c KERNEL VIRTUAL MACHINE FOR ARM/ARM64 (KVM/arm, KVM/arm64) M: Marc Zyngier R: James Morse -R: Julien Thierry +R: Julien Thierry R: Suzuki K Poulose L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: kvmarm@lists.cs.columbia.edu From 6d140e7569db89a1b596c1c2d1c2293d5c594432 Mon Sep 17 00:00:00 2001 From: Vaibhav Jain Date: Sat, 29 Jun 2019 21:36:08 +0530 Subject: [PATCH 162/823] powerpc/pseries: Update SCM hcall op-codes in hvcall.h Update the hvcalls.h to include op-codes for new hcalls introduce to manage SCM memory. Also update existing hcall definitions to reflect current papr specification for SCM. The removed hcall op-codes H_SCM_MEM_QUERY, H_SCM_BLOCK_CLEAR were transient proposals and there support was never implemented by Power-VM nor they were used anywhere in Linux kernel. Hence we don't expect anyone to be impacted by this change. Signed-off-by: Vaibhav Jain Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190629160610.23402-2-vaibhav@linux.ibm.com --- arch/powerpc/include/asm/hvcall.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 463c63a9fcf1..11112023e327 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -302,9 +302,14 @@ #define H_SCM_UNBIND_MEM 0x3F0 #define H_SCM_QUERY_BLOCK_MEM_BINDING 0x3F4 #define H_SCM_QUERY_LOGICAL_MEM_BINDING 0x3F8 -#define H_SCM_MEM_QUERY 0x3FC -#define H_SCM_BLOCK_CLEAR 0x400 -#define MAX_HCALL_OPCODE H_SCM_BLOCK_CLEAR +#define H_SCM_UNBIND_ALL 0x3FC +#define H_SCM_HEALTH 0x400 +#define H_SCM_PERFORMANCE_STATS 0x418 +#define MAX_HCALL_OPCODE H_SCM_PERFORMANCE_STATS + +/* Scope args for H_SCM_UNBIND_ALL */ +#define H_UNBIND_SCOPE_ALL (0x1) +#define H_UNBIND_SCOPE_DRC (0x2) /* H_VIOCTL functions */ #define H_GET_VIOA_DUMP_SIZE 0x01 From 0d7fc080ba139a2a639d3732616403ccddfa2d36 Mon Sep 17 00:00:00 2001 From: Vaibhav Jain Date: Sat, 29 Jun 2019 21:36:09 +0530 Subject: [PATCH 163/823] powerpc/papr_scm: Update drc_pmem_unbind() to use H_SCM_UNBIND_ALL The new hcall named H_SCM_UNBIND_ALL has been introduce that can unbind all or specific scm memory assigned to an lpar. This is more efficient than using H_SCM_UNBIND_MEM as currently we don't support partial unbind of scm memory. Hence this patch proposes following changes to drc_pmem_unbind(): * Update drc_pmem_unbind() to replace hcall H_SCM_UNBIND_MEM to H_SCM_UNBIND_ALL. * Update drc_pmem_unbind() to handles cases when PHYP asks the guest kernel to wait for specific amount of time before retrying the hcall via the 'LONG_BUSY' return value. * Ensure appropriate error code is returned back from the function in case of an error. Reviewed-by: Oliver O'Halloran Signed-off-by: Vaibhav Jain Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190629160610.23402-3-vaibhav@linux.ibm.com --- arch/powerpc/platforms/pseries/papr_scm.c | 29 +++++++++++++++++------ 1 file changed, 22 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index c8ec670ee924..82568a7e0a7c 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -11,6 +11,7 @@ #include #include #include +#include #include @@ -78,22 +79,36 @@ static int drc_pmem_bind(struct papr_scm_priv *p) static int drc_pmem_unbind(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; - uint64_t rc, token; + uint64_t token = 0; + int64_t rc; - token = 0; + dev_dbg(&p->pdev->dev, "unbind drc %x\n", p->drc_index); - /* NB: unbind has the same retry requirements mentioned above */ + /* NB: unbind has the same retry requirements as drc_pmem_bind() */ do { - rc = plpar_hcall(H_SCM_UNBIND_MEM, ret, p->drc_index, - p->bound_addr, p->blocks, token); + + /* Unbind of all SCM resources associated with drcIndex */ + rc = plpar_hcall(H_SCM_UNBIND_ALL, ret, H_UNBIND_SCOPE_DRC, + p->drc_index, token); token = ret[0]; - cond_resched(); + + /* Check if we are stalled for some time */ + if (H_IS_LONG_BUSY(rc)) { + msleep(get_longbusy_msecs(rc)); + rc = H_BUSY; + } else if (rc == H_BUSY) { + cond_resched(); + } + } while (rc == H_BUSY); if (rc) dev_err(&p->pdev->dev, "unbind error: %lld\n", rc); + else + dev_dbg(&p->pdev->dev, "unbind drc %x complete\n", + p->drc_index); - return !!rc; + return rc == H_SUCCESS ? 0 : -ENXIO; } static int papr_scm_meta_get(struct papr_scm_priv *p, From 3a855b7ac7d5021674aa3e1cc9d3bfd6b604e9c0 Mon Sep 17 00:00:00 2001 From: Vaibhav Jain Date: Sat, 29 Jun 2019 21:36:10 +0530 Subject: [PATCH 164/823] powerpc/papr_scm: Force a scm-unbind if initial scm-bind fails In some cases initial bind of scm memory for an lpar can fail if previously it wasn't released using a scm-unbind hcall. This situation can arise due to panic of the previous kernel or forced lpar fadump. In such cases the H_SCM_BIND_MEM return a H_OVERLAP error. To mitigate such cases the patch updates papr_scm_probe() to force a call to drc_pmem_unbind() in case the initial bind of scm memory fails with EBUSY error. In case scm-bind operation again fails after the forced scm-unbind then we follow the existing error path. We also update drc_pmem_bind() to handle the H_OVERLAP error returned by phyp and indicate it as a EBUSY error back to the caller. Suggested-by: "Oliver O'Halloran" Signed-off-by: Vaibhav Jain Reviewed-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190629160610.23402-4-vaibhav@linux.ibm.com --- arch/powerpc/platforms/pseries/papr_scm.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 82568a7e0a7c..2c07908359b2 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -44,8 +44,9 @@ struct papr_scm_priv { static int drc_pmem_bind(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; - uint64_t rc, token; uint64_t saved = 0; + uint64_t token; + int64_t rc; /* * When the hypervisor cannot map all the requested memory in a single @@ -65,6 +66,10 @@ static int drc_pmem_bind(struct papr_scm_priv *p) } while (rc == H_BUSY); if (rc) { + /* H_OVERLAP needs a separate error path */ + if (rc == H_OVERLAP) + return -EBUSY; + dev_err(&p->pdev->dev, "bind err: %lld\n", rc); return -ENXIO; } @@ -404,6 +409,14 @@ static int papr_scm_probe(struct platform_device *pdev) /* request the hypervisor to bind this region to somewhere in memory */ rc = drc_pmem_bind(p); + + /* If phyp says drc memory still bound then force unbound and retry */ + if (rc == -EBUSY) { + dev_warn(&pdev->dev, "Retrying bind after unbinding\n"); + drc_pmem_unbind(p); + rc = drc_pmem_bind(p); + } + if (rc) goto err; From 3a6ffb3c8c3274a39dc8f2514526e645c5d21753 Mon Sep 17 00:00:00 2001 From: Andreas Koop Date: Mon, 22 Jul 2019 12:03:06 +0800 Subject: [PATCH 165/823] mmc: mmc_spi: Enable stable writes While using the mmc_spi driver occasionally errors like this popped up: mmcblk0: error -84 transferring data end_request: I/O error, dev mmcblk0, sector 581756 I looked on the Internet for occurrences of the same problem and came across a helpful post [1]. It includes source code to reproduce the bug. There is also an analysis about the cause. During transmission data in the supplied buffer is being modified. Thus the previously calculated checksum is not correct anymore. After some digging I found out that device drivers are supposed to report they need stable writes. To fix this I set the appropriate flag at queue initialization if CRC checksumming is enabled for that SPI host. [1] https://groups.google.com/forum/#!msg/sim1/gLlzWeXGFr8/KevXinUXfc8J Signed-off-by: Andreas Koop [shihpo: Rebase on top of v5.3-rc1] Signed-off-by: ShihPo Hung Cc: Paul Walmsley CC: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/core/queue.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index e327f80ebe70..7102e2ebc614 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -427,6 +428,10 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card) goto free_tag_set; } + if (mmc_host_is_spi(host) && host->use_spi_crc) + mq->queue->backing_dev_info->capabilities |= + BDI_CAP_STABLE_WRITES; + mq->queue->queuedata = mq; blk_queue_rq_timeout(mq->queue, 60 * HZ); From 223ecaf140b1dd1c1d2a1a1d96281efc5c906984 Mon Sep 17 00:00:00 2001 From: Michael Wu Date: Mon, 8 Jul 2019 13:23:08 +0800 Subject: [PATCH 166/823] gpiolib: fix incorrect IRQ requesting of an active-low lineevent When a pin is active-low, logical trigger edge should be inverted to match the same interrupt opportunity. For example, a button pushed triggers falling edge in ACTIVE_HIGH case; in ACTIVE_LOW case, the button pushed triggers rising edge. For user space the IRQ requesting doesn't need to do any modification except to configuring GPIOHANDLE_REQUEST_ACTIVE_LOW. For example, we want to catch the event when the button is pushed. The button on the original board drives level to be low when it is pushed, and drives level to be high when it is released. In user space we can do: req.handleflags = GPIOHANDLE_REQUEST_INPUT; req.eventflags = GPIOEVENT_REQUEST_FALLING_EDGE; while (1) { read(fd, &dat, sizeof(dat)); if (dat.id == GPIOEVENT_EVENT_FALLING_EDGE) printf("button pushed\n"); } Run the same logic on another board which the polarity of the button is inverted; it drives level to be high when pushed, and level to be low when released. For this inversion we add flag GPIOHANDLE_REQUEST_ACTIVE_LOW: req.handleflags = GPIOHANDLE_REQUEST_INPUT | GPIOHANDLE_REQUEST_ACTIVE_LOW; req.eventflags = GPIOEVENT_REQUEST_FALLING_EDGE; At the result, there are no any events caught when the button is pushed. By the way, button releasing will emit a "falling" event. The timing of "falling" catching is not expected. Cc: stable@vger.kernel.org Signed-off-by: Michael Wu Tested-by: Bartosz Golaszewski Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpiolib.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 3ee99d070608..bf05c29b53be 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -956,9 +956,11 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) } if (eflags & GPIOEVENT_REQUEST_RISING_EDGE) - irqflags |= IRQF_TRIGGER_RISING; + irqflags |= test_bit(FLAG_ACTIVE_LOW, &desc->flags) ? + IRQF_TRIGGER_FALLING : IRQF_TRIGGER_RISING; if (eflags & GPIOEVENT_REQUEST_FALLING_EDGE) - irqflags |= IRQF_TRIGGER_FALLING; + irqflags |= test_bit(FLAG_ACTIVE_LOW, &desc->flags) ? + IRQF_TRIGGER_RISING : IRQF_TRIGGER_FALLING; irqflags |= IRQF_ONESHOT; INIT_KFIFO(le->events); From 4574b0b9abc83a3522b2e91c43b9f0c479855d3a Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Mon, 22 Jul 2019 14:44:40 +0100 Subject: [PATCH 167/823] MAINTAINERS: Update my email address Update MAINTAINERS and .mailmap with my @linaro.org address, since I don't have access to my @arm.com address anymore. Signed-off-by: Jean-Philippe Brucker Signed-off-by: Will Deacon --- .mailmap | 1 + MAINTAINERS | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/.mailmap b/.mailmap index 1043793cd557..acba1a6163f1 100644 --- a/.mailmap +++ b/.mailmap @@ -98,6 +98,7 @@ Jason Gunthorpe Javi Merino Jean Tourrilhes + Jeff Garzik Jeff Layton Jeff Layton diff --git a/MAINTAINERS b/MAINTAINERS index 50cf99beb7af..3d5577d5ca3d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17123,7 +17123,7 @@ F: drivers/virtio/virtio_input.c F: include/uapi/linux/virtio_input.h VIRTIO IOMMU DRIVER -M: Jean-Philippe Brucker +M: Jean-Philippe Brucker L: virtualization@lists.linux-foundation.org S: Maintained F: drivers/iommu/virtio-iommu.c From 318892ac068397f40ff81d9155898da01493b1d2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 19 Jul 2019 10:29:14 -0700 Subject: [PATCH 168/823] net/tls: don't arm strparser immediately in tls_set_sw_offload() In tls_set_device_offload_rx() we prepare the software context for RX fallback and proceed to add the connection to the device. Unfortunately, software context prep includes arming strparser so in case of a later error we have to release the socket lock to call strp_done(). In preparation for not releasing the socket lock half way through callbacks move arming strparser into a separate function. Following patches will make use of that. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: Daniel Borkmann --- include/net/tls.h | 1 + net/tls/tls_device.c | 1 + net/tls/tls_main.c | 8 +++++--- net/tls/tls_sw.c | 19 ++++++++++++------- 4 files changed, 19 insertions(+), 10 deletions(-) diff --git a/include/net/tls.h b/include/net/tls.h index 584609174fe0..43f551cd508b 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -355,6 +355,7 @@ int tls_sk_attach(struct sock *sk, int optname, char __user *optval, unsigned int optlen); int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx); +void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 7c0b2b778703..4d67d72f007c 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1045,6 +1045,7 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) rc = tls_set_sw_offload(sk, ctx, 0); if (rc) goto release_ctx; + tls_sw_strparser_arm(sk, ctx); rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_RX, &ctx->crypto_recv.info, diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 4674e57e66b0..85a9d7d57b32 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -526,6 +526,8 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, { #endif rc = tls_set_sw_offload(sk, ctx, 1); + if (rc) + goto err_crypto_info; conf = TLS_SW; } } else { @@ -537,13 +539,13 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, { #endif rc = tls_set_sw_offload(sk, ctx, 0); + if (rc) + goto err_crypto_info; + tls_sw_strparser_arm(sk, ctx); conf = TLS_SW; } } - if (rc) - goto err_crypto_info; - if (tx) ctx->tx_conf = conf; else diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 53b4ad94e74a..f58a8ffc2a9c 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2160,6 +2160,18 @@ void tls_sw_write_space(struct sock *sk, struct tls_context *ctx) } } +void tls_sw_strparser_arm(struct sock *sk, struct tls_context *tls_ctx) +{ + struct tls_sw_context_rx *rx_ctx = tls_sw_ctx_rx(tls_ctx); + + write_lock_bh(&sk->sk_callback_lock); + rx_ctx->saved_data_ready = sk->sk_data_ready; + sk->sk_data_ready = tls_data_ready; + write_unlock_bh(&sk->sk_callback_lock); + + strp_check_rcv(&rx_ctx->strp); +} + int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { struct tls_context *tls_ctx = tls_get_ctx(sk); @@ -2357,13 +2369,6 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) cb.parse_msg = tls_read_size; strp_init(&sw_ctx_rx->strp, sk, &cb); - - write_lock_bh(&sk->sk_callback_lock); - sw_ctx_rx->saved_data_ready = sk->sk_data_ready; - sk->sk_data_ready = tls_data_ready; - write_unlock_bh(&sk->sk_callback_lock); - - strp_check_rcv(&sw_ctx_rx->strp); } goto out; From ac78fc148d8249dbf382c2127456dd08ec5b161c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 19 Jul 2019 10:29:15 -0700 Subject: [PATCH 169/823] net/tls: don't call tls_sk_proto_close for hw record offload The deprecated TOE offload doesn't actually do anything in tls_sk_proto_close() - all TLS code is skipped and context not freed. Remove the callback to make it easier to refactor tls_sk_proto_close(). Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: Daniel Borkmann --- net/tls/tls_main.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 85a9d7d57b32..7ab682ed99fa 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -271,9 +271,6 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) lock_sock(sk); sk_proto_close = ctx->sk_proto_close; - if (ctx->tx_conf == TLS_HW_RECORD && ctx->rx_conf == TLS_HW_RECORD) - goto skip_tx_cleanup; - if (ctx->tx_conf == TLS_BASE && ctx->rx_conf == TLS_BASE) { free_ctx = true; goto skip_tx_cleanup; @@ -766,7 +763,6 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_HW_RECORD][TLS_HW_RECORD] = *base; prot[TLS_HW_RECORD][TLS_HW_RECORD].hash = tls_hw_hash; prot[TLS_HW_RECORD][TLS_HW_RECORD].unhash = tls_hw_unhash; - prot[TLS_HW_RECORD][TLS_HW_RECORD].close = tls_sk_proto_close; } static int tls_init(struct sock *sk) From f87e62d45e51b12d48d2cb46b5cde8f83b866bc4 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 19 Jul 2019 10:29:16 -0700 Subject: [PATCH 170/823] net/tls: remove close callback sock unlock/lock around TX work flush The tls close() callback currently drops the sock lock, makes a cancel_delayed_work_sync() call, and then relocks the sock. By restructuring the code we can avoid droping lock and then reclaiming it. To simplify this we do the following, tls_sk_proto_close set_bit(CLOSING) set_bit(SCHEDULE) cancel_delay_work_sync() <- cancel workqueue lock_sock(sk) ... release_sock(sk) strp_done() Setting the CLOSING bit prevents the SCHEDULE bit from being cleared by any workqueue items e.g. if one happens to be scheduled and run between when we set SCHEDULE bit and cancel work. Then because SCHEDULE bit is set now no new work will be scheduled. Tested with net selftests and bpf selftests. Signed-off-by: John Fastabend Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: Daniel Borkmann --- include/net/tls.h | 2 ++ net/tls/tls_main.c | 3 +++ net/tls/tls_sw.c | 24 +++++++++++++++++------- 3 files changed, 22 insertions(+), 7 deletions(-) diff --git a/include/net/tls.h b/include/net/tls.h index 43f551cd508b..d4276cb6de53 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -162,6 +162,7 @@ struct tls_sw_context_tx { int async_capable; #define BIT_TX_SCHEDULED 0 +#define BIT_TX_CLOSING 1 unsigned long tx_bitmask; }; @@ -360,6 +361,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); void tls_sw_close(struct sock *sk, long timeout); +void tls_sw_cancel_work_tx(struct tls_context *tls_ctx); void tls_sw_free_resources_tx(struct sock *sk); void tls_sw_free_resources_rx(struct sock *sk); void tls_sw_release_resources_rx(struct sock *sk); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 7ab682ed99fa..5c29b410cf7d 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -268,6 +268,9 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) void (*sk_proto_close)(struct sock *sk, long timeout); bool free_ctx = false; + if (ctx->tx_conf == TLS_SW) + tls_sw_cancel_work_tx(ctx); + lock_sock(sk); sk_proto_close = ctx->sk_proto_close; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index f58a8ffc2a9c..38c0e53c727d 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2054,6 +2054,15 @@ static void tls_data_ready(struct sock *sk) } } +void tls_sw_cancel_work_tx(struct tls_context *tls_ctx) +{ + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + + set_bit(BIT_TX_CLOSING, &ctx->tx_bitmask); + set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask); + cancel_delayed_work_sync(&ctx->tx_work.work); +} + void tls_sw_free_resources_tx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); @@ -2065,11 +2074,6 @@ void tls_sw_free_resources_tx(struct sock *sk) if (atomic_read(&ctx->encrypt_pending)) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); - release_sock(sk); - cancel_delayed_work_sync(&ctx->tx_work.work); - lock_sock(sk); - - /* Tx whatever records we can transmit and abandon the rest */ tls_tx_records(sk, -1); /* Free up un-sent records in tx_list. First, free @@ -2137,11 +2141,17 @@ static void tx_work_handler(struct work_struct *work) struct tx_work, work); struct sock *sk = tx_work->sk; struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_sw_context_tx *ctx; + + if (unlikely(!tls_ctx)) + return; + + ctx = tls_sw_ctx_tx(tls_ctx); + if (test_bit(BIT_TX_CLOSING, &ctx->tx_bitmask)) + return; if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) return; - lock_sock(sk); tls_tx_records(sk, -1); release_sock(sk); From 313ab004805cf52a42673b15852b3842474ccd87 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 19 Jul 2019 10:29:17 -0700 Subject: [PATCH 171/823] net/tls: remove sock unlock/lock around strp_done() The tls close() callback currently drops the sock lock to call strp_done(). Split up the RX cleanup into stopping the strparser and releasing most resources, syncing strparser and finally freeing the context. To avoid the need for a strp_done() call on the cleanup path of device offload make sure we don't arm the strparser until we are sure init will be successful. Signed-off-by: John Fastabend Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: Daniel Borkmann --- include/net/tls.h | 7 ++--- net/tls/tls_device.c | 1 - net/tls/tls_main.c | 61 ++++++++++++++++++++++---------------------- net/tls/tls_sw.c | 40 +++++++++++++++++++++-------- 4 files changed, 64 insertions(+), 45 deletions(-) diff --git a/include/net/tls.h b/include/net/tls.h index d4276cb6de53..235508e35fd4 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -107,9 +107,7 @@ struct tls_device { enum { TLS_BASE, TLS_SW, -#ifdef CONFIG_TLS_DEVICE TLS_HW, -#endif TLS_HW_RECORD, TLS_NUM_CONFIG, }; @@ -357,14 +355,17 @@ int tls_sk_attach(struct sock *sk, int optname, char __user *optval, int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx); void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); +void tls_sw_strparser_done(struct tls_context *tls_ctx); int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); void tls_sw_close(struct sock *sk, long timeout); void tls_sw_cancel_work_tx(struct tls_context *tls_ctx); -void tls_sw_free_resources_tx(struct sock *sk); +void tls_sw_release_resources_tx(struct sock *sk); +void tls_sw_free_ctx_tx(struct tls_context *tls_ctx); void tls_sw_free_resources_rx(struct sock *sk); void tls_sw_release_resources_rx(struct sock *sk); +void tls_sw_free_ctx_rx(struct tls_context *tls_ctx); int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); bool tls_sw_stream_read(const struct sock *sk); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 4d67d72f007c..7c0b2b778703 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1045,7 +1045,6 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) rc = tls_set_sw_offload(sk, ctx, 0); if (rc) goto release_ctx; - tls_sw_strparser_arm(sk, ctx); rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_RX, &ctx->crypto_recv.info, diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 5c29b410cf7d..d152a00a7a27 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -261,24 +261,9 @@ void tls_ctx_free(struct tls_context *ctx) kfree(ctx); } -static void tls_sk_proto_close(struct sock *sk, long timeout) +static void tls_sk_proto_cleanup(struct sock *sk, + struct tls_context *ctx, long timeo) { - struct tls_context *ctx = tls_get_ctx(sk); - long timeo = sock_sndtimeo(sk, 0); - void (*sk_proto_close)(struct sock *sk, long timeout); - bool free_ctx = false; - - if (ctx->tx_conf == TLS_SW) - tls_sw_cancel_work_tx(ctx); - - lock_sock(sk); - sk_proto_close = ctx->sk_proto_close; - - if (ctx->tx_conf == TLS_BASE && ctx->rx_conf == TLS_BASE) { - free_ctx = true; - goto skip_tx_cleanup; - } - if (unlikely(sk->sk_write_pending) && !wait_on_pending_writer(sk, &timeo)) tls_handle_open_record(sk, 0); @@ -287,7 +272,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) if (ctx->tx_conf == TLS_SW) { kfree(ctx->tx.rec_seq); kfree(ctx->tx.iv); - tls_sw_free_resources_tx(sk); + tls_sw_release_resources_tx(sk); #ifdef CONFIG_TLS_DEVICE } else if (ctx->tx_conf == TLS_HW) { tls_device_free_resources_tx(sk); @@ -295,26 +280,40 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) } if (ctx->rx_conf == TLS_SW) - tls_sw_free_resources_rx(sk); + tls_sw_release_resources_rx(sk); #ifdef CONFIG_TLS_DEVICE if (ctx->rx_conf == TLS_HW) tls_device_offload_cleanup_rx(sk); - - if (ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW) { -#else - { #endif - tls_ctx_free(ctx); - ctx = NULL; - } +} + +static void tls_sk_proto_close(struct sock *sk, long timeout) +{ + void (*sk_proto_close)(struct sock *sk, long timeout); + struct tls_context *ctx = tls_get_ctx(sk); + long timeo = sock_sndtimeo(sk, 0); + bool free_ctx; + + if (ctx->tx_conf == TLS_SW) + tls_sw_cancel_work_tx(ctx); + + lock_sock(sk); + free_ctx = ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW; + sk_proto_close = ctx->sk_proto_close; + + if (ctx->tx_conf != TLS_BASE || ctx->rx_conf != TLS_BASE) + tls_sk_proto_cleanup(sk, ctx, timeo); -skip_tx_cleanup: release_sock(sk); + if (ctx->tx_conf == TLS_SW) + tls_sw_free_ctx_tx(ctx); + if (ctx->rx_conf == TLS_SW || ctx->rx_conf == TLS_HW) + tls_sw_strparser_done(ctx); + if (ctx->rx_conf == TLS_SW) + tls_sw_free_ctx_rx(ctx); sk_proto_close(sk, timeout); - /* free ctx for TLS_HW_RECORD, used by tcp_set_state - * for sk->sk_prot->unhash [tls_hw_unhash] - */ + if (free_ctx) tls_ctx_free(ctx); } @@ -541,9 +540,9 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, rc = tls_set_sw_offload(sk, ctx, 0); if (rc) goto err_crypto_info; - tls_sw_strparser_arm(sk, ctx); conf = TLS_SW; } + tls_sw_strparser_arm(sk, ctx); } if (tx) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 38c0e53c727d..91d21b048a9b 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2063,7 +2063,7 @@ void tls_sw_cancel_work_tx(struct tls_context *tls_ctx) cancel_delayed_work_sync(&ctx->tx_work.work); } -void tls_sw_free_resources_tx(struct sock *sk) +void tls_sw_release_resources_tx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); @@ -2096,6 +2096,11 @@ void tls_sw_free_resources_tx(struct sock *sk) crypto_free_aead(ctx->aead_send); tls_free_open_rec(sk); +} + +void tls_sw_free_ctx_tx(struct tls_context *tls_ctx) +{ + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); kfree(ctx); } @@ -2114,23 +2119,38 @@ void tls_sw_release_resources_rx(struct sock *sk) skb_queue_purge(&ctx->rx_list); crypto_free_aead(ctx->aead_recv); strp_stop(&ctx->strp); - write_lock_bh(&sk->sk_callback_lock); - sk->sk_data_ready = ctx->saved_data_ready; - write_unlock_bh(&sk->sk_callback_lock); - release_sock(sk); - strp_done(&ctx->strp); - lock_sock(sk); + /* If tls_sw_strparser_arm() was not called (cleanup paths) + * we still want to strp_stop(), but sk->sk_data_ready was + * never swapped. + */ + if (ctx->saved_data_ready) { + write_lock_bh(&sk->sk_callback_lock); + sk->sk_data_ready = ctx->saved_data_ready; + write_unlock_bh(&sk->sk_callback_lock); + } } } +void tls_sw_strparser_done(struct tls_context *tls_ctx) +{ + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + + strp_done(&ctx->strp); +} + +void tls_sw_free_ctx_rx(struct tls_context *tls_ctx) +{ + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + + kfree(ctx); +} + void tls_sw_free_resources_rx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); tls_sw_release_resources_rx(sk); - - kfree(ctx); + tls_sw_free_ctx_rx(tls_ctx); } /* The work handler to transmitt the encrypted records in tx_list */ From 32857cf57f920cdc03b5095f08febec94cf9c36b Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 19 Jul 2019 10:29:18 -0700 Subject: [PATCH 172/823] net/tls: fix transition through disconnect with close It is possible (via shutdown()) for TCP socks to go through TCP_CLOSE state via tcp_disconnect() without actually calling tcp_close which would then call the tls close callback. Because of this a user could disconnect a socket then put it in a LISTEN state which would break our assumptions about sockets always being ESTABLISHED state. More directly because close() can call unhash() and unhash is implemented by sockmap if a sockmap socket has TLS enabled we can incorrectly destroy the psock from unhash() and then call its close handler again. But because the psock (sockmap socket representation) is already destroyed we call close handler in sk->prot. However, in some cases (TLS BASE/BASE case) this will still point at the sockmap close handler resulting in a circular call and crash reported by syzbot. To fix both above issues implement the unhash() routine for TLS. v4: - add note about tls offload still needing the fix; - move sk_proto to the cold cache line; - split TX context free into "release" and "free", otherwise the GC work itself is in already freed memory; - more TX before RX for consistency; - reuse tls_ctx_free(); - schedule the GC work after we're done with context to avoid UAF; - don't set the unhash in all modes, all modes "inherit" TLS_BASE's callbacks anyway; - disable the unhash hook for TLS_HW. Fixes: 3c4d7559159bf ("tls: kernel TLS support") Reported-by: Eric Dumazet Signed-off-by: John Fastabend Signed-off-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- Documentation/networking/tls-offload.rst | 6 +++ include/net/tls.h | 5 ++- net/tls/tls_main.c | 55 ++++++++++++++++++++++++ 3 files changed, 65 insertions(+), 1 deletion(-) diff --git a/Documentation/networking/tls-offload.rst b/Documentation/networking/tls-offload.rst index 048e5ca44824..8a1eeb393316 100644 --- a/Documentation/networking/tls-offload.rst +++ b/Documentation/networking/tls-offload.rst @@ -513,3 +513,9 @@ Redirects leak clear text In the RX direction, if segment has already been decrypted by the device and it gets redirected or mirrored - clear text will be transmitted out. + +shutdown() doesn't clear TLS state +---------------------------------- + +shutdown() system call allows for a TLS socket to be reused as a different +connection. Offload doesn't currently handle that. diff --git a/include/net/tls.h b/include/net/tls.h index 235508e35fd4..9e425ac2de45 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -271,6 +271,8 @@ struct tls_context { unsigned long flags; /* cache cold stuff */ + struct proto *sk_proto; + void (*sk_destruct)(struct sock *sk); void (*sk_proto_close)(struct sock *sk, long timeout); @@ -288,6 +290,8 @@ struct tls_context { struct list_head list; refcount_t refcount; + + struct work_struct gc; }; enum tls_offload_ctx_dir { @@ -359,7 +363,6 @@ void tls_sw_strparser_done(struct tls_context *tls_ctx); int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); -void tls_sw_close(struct sock *sk, long timeout); void tls_sw_cancel_work_tx(struct tls_context *tls_ctx); void tls_sw_release_resources_tx(struct sock *sk); void tls_sw_free_ctx_tx(struct tls_context *tls_ctx); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index d152a00a7a27..48f1c26459d0 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -261,6 +261,33 @@ void tls_ctx_free(struct tls_context *ctx) kfree(ctx); } +static void tls_ctx_free_deferred(struct work_struct *gc) +{ + struct tls_context *ctx = container_of(gc, struct tls_context, gc); + + /* Ensure any remaining work items are completed. The sk will + * already have lost its tls_ctx reference by the time we get + * here so no xmit operation will actually be performed. + */ + if (ctx->tx_conf == TLS_SW) { + tls_sw_cancel_work_tx(ctx); + tls_sw_free_ctx_tx(ctx); + } + + if (ctx->rx_conf == TLS_SW) { + tls_sw_strparser_done(ctx); + tls_sw_free_ctx_rx(ctx); + } + + tls_ctx_free(ctx); +} + +static void tls_ctx_free_wq(struct tls_context *ctx) +{ + INIT_WORK(&ctx->gc, tls_ctx_free_deferred); + schedule_work(&ctx->gc); +} + static void tls_sk_proto_cleanup(struct sock *sk, struct tls_context *ctx, long timeo) { @@ -288,6 +315,26 @@ static void tls_sk_proto_cleanup(struct sock *sk, #endif } +static void tls_sk_proto_unhash(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + long timeo = sock_sndtimeo(sk, 0); + struct tls_context *ctx; + + if (unlikely(!icsk->icsk_ulp_data)) { + if (sk->sk_prot->unhash) + sk->sk_prot->unhash(sk); + } + + ctx = tls_get_ctx(sk); + tls_sk_proto_cleanup(sk, ctx, timeo); + icsk->icsk_ulp_data = NULL; + + if (ctx->sk_proto->unhash) + ctx->sk_proto->unhash(sk); + tls_ctx_free_wq(ctx); +} + static void tls_sk_proto_close(struct sock *sk, long timeout) { void (*sk_proto_close)(struct sock *sk, long timeout); @@ -305,6 +352,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) if (ctx->tx_conf != TLS_BASE || ctx->rx_conf != TLS_BASE) tls_sk_proto_cleanup(sk, ctx, timeo); + sk->sk_prot = ctx->sk_proto; release_sock(sk); if (ctx->tx_conf == TLS_SW) tls_sw_free_ctx_tx(ctx); @@ -608,6 +656,7 @@ static struct tls_context *create_ctx(struct sock *sk) ctx->setsockopt = sk->sk_prot->setsockopt; ctx->getsockopt = sk->sk_prot->getsockopt; ctx->sk_proto_close = sk->sk_prot->close; + ctx->unhash = sk->sk_prot->unhash; return ctx; } @@ -731,6 +780,7 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_BASE][TLS_BASE].setsockopt = tls_setsockopt; prot[TLS_BASE][TLS_BASE].getsockopt = tls_getsockopt; prot[TLS_BASE][TLS_BASE].close = tls_sk_proto_close; + prot[TLS_BASE][TLS_BASE].unhash = tls_sk_proto_unhash; prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; prot[TLS_SW][TLS_BASE].sendmsg = tls_sw_sendmsg; @@ -748,16 +798,20 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], #ifdef CONFIG_TLS_DEVICE prot[TLS_HW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; + prot[TLS_HW][TLS_BASE].unhash = base->unhash; prot[TLS_HW][TLS_BASE].sendmsg = tls_device_sendmsg; prot[TLS_HW][TLS_BASE].sendpage = tls_device_sendpage; prot[TLS_HW][TLS_SW] = prot[TLS_BASE][TLS_SW]; + prot[TLS_HW][TLS_SW].unhash = base->unhash; prot[TLS_HW][TLS_SW].sendmsg = tls_device_sendmsg; prot[TLS_HW][TLS_SW].sendpage = tls_device_sendpage; prot[TLS_BASE][TLS_HW] = prot[TLS_BASE][TLS_SW]; + prot[TLS_BASE][TLS_HW].unhash = base->unhash; prot[TLS_SW][TLS_HW] = prot[TLS_SW][TLS_SW]; + prot[TLS_SW][TLS_HW].unhash = base->unhash; prot[TLS_HW][TLS_HW] = prot[TLS_HW][TLS_SW]; #endif @@ -794,6 +848,7 @@ static int tls_init(struct sock *sk) tls_build_proto(sk); ctx->tx_conf = TLS_BASE; ctx->rx_conf = TLS_BASE; + ctx->sk_proto = sk->sk_prot; update_sk_prot(sk, ctx); out: return rc; From 45a4521dcbd92e71c9e53031b40e34211d3b4feb Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 19 Jul 2019 10:29:19 -0700 Subject: [PATCH 173/823] bpf: sockmap, sock_map_delete needs to use xchg __sock_map_delete() may be called from a tcp event such as unhash or close from the following trace, tcp_bpf_close() tcp_bpf_remove() sk_psock_unlink() sock_map_delete_from_link() __sock_map_delete() In this case the sock lock is held but this only protects against duplicate removals on the TCP side. If the map is free'd then we have this trace, sock_map_free xchg() <- replaces map entry sock_map_unref() sk_psock_put() sock_map_del_link() The __sock_map_delete() call however uses a read, test, null over the map entry which can result in both paths trying to free the map entry. To fix use xchg in TCP paths as well so we avoid having two references to the same map entry. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann --- net/core/sock_map.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 52d4faeee18b..28702f2e9a4a 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -276,16 +276,20 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock **psk) { struct sock *sk; + int err = 0; raw_spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) - *psk = NULL; + sk = xchg(psk, NULL); + + if (likely(sk)) + sock_map_unref(sk, psk); + else + err = -EINVAL; + raw_spin_unlock_bh(&stab->lock); - if (unlikely(!sk)) - return -EINVAL; - sock_map_unref(sk, psk); - return 0; + return err; } static void sock_map_delete_from_link(struct bpf_map *map, struct sock *sk, From 2bb90e5cc90e1d09f631aeab041a9cf913a5bbe5 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 19 Jul 2019 10:29:20 -0700 Subject: [PATCH 174/823] bpf: sockmap, synchronize_rcu before free'ing map We need to have a synchronize_rcu before free'ing the sockmap because any outstanding psock references will have a pointer to the map and when they use this could trigger a use after free. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann --- net/core/sock_map.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 28702f2e9a4a..56bcabe7c2f2 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -247,6 +247,8 @@ static void sock_map_free(struct bpf_map *map) raw_spin_unlock_bh(&stab->lock); rcu_read_unlock(); + synchronize_rcu(); + bpf_map_area_free(stab->sks); kfree(stab); } From 0e858739c2d2eedeeac1d35bfa0ec3cc2a7190d8 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 19 Jul 2019 10:29:21 -0700 Subject: [PATCH 175/823] bpf: sockmap, only create entry if ulp is not already enabled Sockmap does not currently support adding sockets after TLS has been enabled. There never was a real use case for this so it was never added. But, we lost the test for ULP at some point so add it here and fail the socket insert if TLS is enabled. Future work could make sockmap support this use case but fixup the bug here. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann --- net/core/sock_map.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 56bcabe7c2f2..1330a7442e5b 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -334,6 +334,7 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx, struct sock *sk, u64 flags) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct inet_connection_sock *icsk = inet_csk(sk); struct sk_psock_link *link; struct sk_psock *psock; struct sock *osk; @@ -344,6 +345,8 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx, return -EINVAL; if (unlikely(idx >= map->max_entries)) return -E2BIG; + if (unlikely(icsk->icsk_ulp_data)) + return -EINVAL; link = sk_psock_init_link(); if (!link) From 95fa145479fbc0a0c1fd3274ceb42ec03c042a4a Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 19 Jul 2019 10:29:22 -0700 Subject: [PATCH 176/823] bpf: sockmap/tls, close can race with map free When a map free is called and in parallel a socket is closed we have two paths that can potentially reset the socket prot ops, the bpf close() path and the map free path. This creates a problem with which prot ops should be used from the socket closed side. If the map_free side completes first then we want to call the original lowest level ops. However, if the tls path runs first we want to call the sockmap ops. Additionally there was no locking around prot updates in TLS code paths so the prot ops could be changed multiple times once from TLS path and again from sockmap side potentially leaving ops pointed at either TLS or sockmap when psock and/or tls context have already been destroyed. To fix this race first only update ops inside callback lock so that TLS, sockmap and lowest level all agree on prot state. Second and a ULP callback update() so that lower layers can inform the upper layer when they are being removed allowing the upper layer to reset prot ops. This gets us close to allowing sockmap and tls to be stacked in arbitrary order but will save that patch for *next trees. v4: - make sure we don't free things for device; - remove the checks which swap the callbacks back only if TLS is at the top. Reported-by: syzbot+06537213db7ba2745c4a@syzkaller.appspotmail.com Fixes: 02c558b2d5d6 ("bpf: sockmap, support for msg_peek in sk_msg with redirect ingress") Signed-off-by: John Fastabend Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: Daniel Borkmann --- include/linux/skmsg.h | 8 +++++++- include/net/tcp.h | 3 +++ net/core/skmsg.c | 4 ++-- net/ipv4/tcp_ulp.c | 13 +++++++++++++ net/tls/tls_main.c | 33 ++++++++++++++++++++++++++++----- 5 files changed, 53 insertions(+), 8 deletions(-) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 50ced8aba9db..e4b3fb4bb77c 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -354,7 +354,13 @@ static inline void sk_psock_restore_proto(struct sock *sk, sk->sk_write_space = psock->saved_write_space; if (psock->sk_proto) { - sk->sk_prot = psock->sk_proto; + struct inet_connection_sock *icsk = inet_csk(sk); + bool has_ulp = !!icsk->icsk_ulp_data; + + if (has_ulp) + tcp_update_ulp(sk, psock->sk_proto); + else + sk->sk_prot = psock->sk_proto; psock->sk_proto = NULL; } } diff --git a/include/net/tcp.h b/include/net/tcp.h index f42d300f0cfa..c82a23470081 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2103,6 +2103,8 @@ struct tcp_ulp_ops { /* initialize ulp */ int (*init)(struct sock *sk); + /* update ulp */ + void (*update)(struct sock *sk, struct proto *p); /* cleanup ulp */ void (*release)(struct sock *sk); @@ -2114,6 +2116,7 @@ void tcp_unregister_ulp(struct tcp_ulp_ops *type); int tcp_set_ulp(struct sock *sk, const char *name); void tcp_get_available_ulp(char *buf, size_t len); void tcp_cleanup_ulp(struct sock *sk); +void tcp_update_ulp(struct sock *sk, struct proto *p); #define MODULE_ALIAS_TCP_ULP(name) \ __MODULE_INFO(alias, alias_userspace, name); \ diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 93bffaad2135..6832eeb4b785 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -585,12 +585,12 @@ EXPORT_SYMBOL_GPL(sk_psock_destroy); void sk_psock_drop(struct sock *sk, struct sk_psock *psock) { - rcu_assign_sk_user_data(sk, NULL); sk_psock_cork_free(psock); sk_psock_zap_ingress(psock); - sk_psock_restore_proto(sk, psock); write_lock_bh(&sk->sk_callback_lock); + sk_psock_restore_proto(sk, psock); + rcu_assign_sk_user_data(sk, NULL); if (psock->progs.skb_parser) sk_psock_stop_strp(sk, psock); write_unlock_bh(&sk->sk_callback_lock); diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 3d8a1d835471..4849edb62d52 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -96,6 +96,19 @@ void tcp_get_available_ulp(char *buf, size_t maxlen) rcu_read_unlock(); } +void tcp_update_ulp(struct sock *sk, struct proto *proto) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (!icsk->icsk_ulp_ops) { + sk->sk_prot = proto; + return; + } + + if (icsk->icsk_ulp_ops->update) + icsk->icsk_ulp_ops->update(sk, proto); +} + void tcp_cleanup_ulp(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 48f1c26459d0..f208f8455ef2 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -328,7 +328,10 @@ static void tls_sk_proto_unhash(struct sock *sk) ctx = tls_get_ctx(sk); tls_sk_proto_cleanup(sk, ctx, timeo); + write_lock_bh(&sk->sk_callback_lock); icsk->icsk_ulp_data = NULL; + sk->sk_prot = ctx->sk_proto; + write_unlock_bh(&sk->sk_callback_lock); if (ctx->sk_proto->unhash) ctx->sk_proto->unhash(sk); @@ -337,7 +340,7 @@ static void tls_sk_proto_unhash(struct sock *sk) static void tls_sk_proto_close(struct sock *sk, long timeout) { - void (*sk_proto_close)(struct sock *sk, long timeout); + struct inet_connection_sock *icsk = inet_csk(sk); struct tls_context *ctx = tls_get_ctx(sk); long timeo = sock_sndtimeo(sk, 0); bool free_ctx; @@ -347,12 +350,15 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) lock_sock(sk); free_ctx = ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW; - sk_proto_close = ctx->sk_proto_close; if (ctx->tx_conf != TLS_BASE || ctx->rx_conf != TLS_BASE) tls_sk_proto_cleanup(sk, ctx, timeo); + write_lock_bh(&sk->sk_callback_lock); + if (free_ctx) + icsk->icsk_ulp_data = NULL; sk->sk_prot = ctx->sk_proto; + write_unlock_bh(&sk->sk_callback_lock); release_sock(sk); if (ctx->tx_conf == TLS_SW) tls_sw_free_ctx_tx(ctx); @@ -360,7 +366,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) tls_sw_strparser_done(ctx); if (ctx->rx_conf == TLS_SW) tls_sw_free_ctx_rx(ctx); - sk_proto_close(sk, timeout); + ctx->sk_proto_close(sk, timeout); if (free_ctx) tls_ctx_free(ctx); @@ -827,7 +833,7 @@ static int tls_init(struct sock *sk) int rc = 0; if (tls_hw_prot(sk)) - goto out; + return 0; /* The TLS ulp is currently supported only for TCP sockets * in ESTABLISHED state. @@ -838,22 +844,38 @@ static int tls_init(struct sock *sk) if (sk->sk_state != TCP_ESTABLISHED) return -ENOTSUPP; + tls_build_proto(sk); + /* allocate tls context */ + write_lock_bh(&sk->sk_callback_lock); ctx = create_ctx(sk); if (!ctx) { rc = -ENOMEM; goto out; } - tls_build_proto(sk); ctx->tx_conf = TLS_BASE; ctx->rx_conf = TLS_BASE; ctx->sk_proto = sk->sk_prot; update_sk_prot(sk, ctx); out: + write_unlock_bh(&sk->sk_callback_lock); return rc; } +static void tls_update(struct sock *sk, struct proto *p) +{ + struct tls_context *ctx; + + ctx = tls_get_ctx(sk); + if (likely(ctx)) { + ctx->sk_proto_close = p->close; + ctx->sk_proto = p; + } else { + sk->sk_prot = p; + } +} + void tls_register_device(struct tls_device *device) { spin_lock_bh(&device_spinlock); @@ -874,6 +896,7 @@ static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = { .name = "tls", .owner = THIS_MODULE, .init = tls_init, + .update = tls_update, }; static int __init tls_register(void) From cf32526c8842781e32d6652a1e01e83b20490948 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 19 Jul 2019 10:29:23 -0700 Subject: [PATCH 177/823] selftests/tls: add a test for ULP but no keys Make sure we test the TLS_BASE/TLS_BASE case both with data and the tear down/clean up path. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: Daniel Borkmann --- tools/testing/selftests/net/tls.c | 74 +++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 090fff9dbc48..194826fee4f7 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -25,6 +25,80 @@ #define TLS_PAYLOAD_MAX_LEN 16384 #define SOL_TLS 282 +#ifndef ENOTSUPP +#define ENOTSUPP 524 +#endif + +FIXTURE(tls_basic) +{ + int fd, cfd; + bool notls; +}; + +FIXTURE_SETUP(tls_basic) +{ + struct sockaddr_in addr; + socklen_t len; + int sfd, ret; + + self->notls = false; + len = sizeof(addr); + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + self->fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ret = bind(sfd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + ret = listen(sfd, 10); + ASSERT_EQ(ret, 0); + + ret = getsockname(sfd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = connect(self->fd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + + self->cfd = accept(sfd, &addr, &len); + ASSERT_GE(self->cfd, 0); + + close(sfd); + + ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (ret != 0) { + ASSERT_EQ(errno, ENOTSUPP); + self->notls = true; + printf("Failure setting TCP_ULP, testing without tls\n"); + return; + } + + ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ASSERT_EQ(ret, 0); +} + +FIXTURE_TEARDOWN(tls_basic) +{ + close(self->fd); + close(self->cfd); +} + +/* Send some data through with ULP but no keys */ +TEST_F(tls_basic, base_base) +{ + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + + ASSERT_EQ(strlen(test_str) + 1, send_len); + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); +}; + FIXTURE(tls) { int fd, cfd; From 78b5dc3d68dcb1d18d805e8f4e565f19ed6d976a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 19 Jul 2019 10:29:24 -0700 Subject: [PATCH 178/823] selftests/tls: test error codes around TLS ULP installation Test the error codes returned when TCP connection is not in ESTABLISHED state. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: Daniel Borkmann --- tools/testing/selftests/net/tls.c | 52 +++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 194826fee4f7..10df77326d34 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -911,6 +911,58 @@ TEST_F(tls, control_msg) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } +TEST(non_established) { + struct tls12_crypto_info_aes_gcm_256 tls12; + struct sockaddr_in addr; + int sfd, ret, fd; + socklen_t len; + + len = sizeof(addr); + + memset(&tls12, 0, sizeof(tls12)); + tls12.info.version = TLS_1_2_VERSION; + tls12.info.cipher_type = TLS_CIPHER_AES_GCM_256; + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ret = bind(sfd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + ret = listen(sfd, 10); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + EXPECT_EQ(ret, -1); + /* TLS ULP not supported */ + if (errno == ENOENT) + return; + EXPECT_EQ(errno, ENOTSUPP); + + ret = setsockopt(sfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, ENOTSUPP); + + ret = getsockname(sfd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = connect(fd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, EEXIST); + + close(fd); + close(sfd); +} + TEST(keysizes) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; From 65d41fb317c62b7c8663a134e88eaee439f270d6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 19 Jul 2019 10:29:25 -0700 Subject: [PATCH 179/823] selftests/tls: add a bidirectional test Add a simple test which installs the TLS state for both directions, sends and receives data on both sockets. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: Daniel Borkmann --- tools/testing/selftests/net/tls.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 10df77326d34..6d78bd050813 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -684,6 +684,37 @@ TEST_F(tls, recv_lowat) EXPECT_EQ(memcmp(send_mem, recv_mem + 10, 5), 0); } +TEST_F(tls, bidir) +{ + struct tls12_crypto_info_aes_gcm_128 tls12; + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + int ret; + + memset(&tls12, 0, sizeof(tls12)); + tls12.info.version = TLS_1_3_VERSION; + tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128; + + ret = setsockopt(self->fd, SOL_TLS, TLS_RX, &tls12, sizeof(tls12)); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_TX, &tls12, sizeof(tls12)); + ASSERT_EQ(ret, 0); + + ASSERT_EQ(strlen(test_str) + 1, send_len); + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); + + memset(buf, 0, sizeof(buf)); + + EXPECT_EQ(send(self->cfd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(self->fd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); +}; + TEST_F(tls, pollin) { char const *test_str = "test_poll"; From 8051bb7f2cbf68ec1289753616703791dd004b5c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 19 Jul 2019 10:29:26 -0700 Subject: [PATCH 180/823] selftests/tls: close the socket with open record Add test which sends some data with MSG_MORE and then closes the socket (never calling send without MSG_MORE). This should make sure we clean up open records correctly. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: Daniel Borkmann --- tools/testing/selftests/net/tls.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 6d78bd050813..94a86ca882de 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -239,6 +239,16 @@ TEST_F(tls, msg_more) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } +TEST_F(tls, msg_more_unsent) +{ + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + + EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1); +} + TEST_F(tls, sendmsg_single) { struct msghdr msg; From d4d34185e710750ad748a0f0a73e8cdac7480bfc Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 19 Jul 2019 10:29:27 -0700 Subject: [PATCH 181/823] selftests/tls: add shutdown tests Add test for killing the connection via shutdown. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: Daniel Borkmann --- tools/testing/selftests/net/tls.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 94a86ca882de..630c5b884d43 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -952,6 +952,33 @@ TEST_F(tls, control_msg) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } +TEST_F(tls, shutdown) +{ + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + + ASSERT_EQ(strlen(test_str) + 1, send_len); + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); + + shutdown(self->fd, SHUT_RDWR); + shutdown(self->cfd, SHUT_RDWR); +} + +TEST_F(tls, shutdown_unsent) +{ + char const *test_str = "test_read"; + int send_len = 10; + + EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len); + + shutdown(self->fd, SHUT_RDWR); + shutdown(self->cfd, SHUT_RDWR); +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; From cdb2f9207109c9c858277fde8b7dc1445b9f952e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 19 Jul 2019 11:34:06 -0300 Subject: [PATCH 182/823] libbpf: Fix endianness macro usage for some compilers Using endian.h and its endianness macros makes this code build in a wider range of compilers, as some don't have those macros (__BYTE_ORDER__, __ORDER_LITTLE_ENDIAN__, __ORDER_BIG_ENDIAN__), so use instead endian.h's macros (__BYTE_ORDER, __LITTLE_ENDIAN, __BIG_ENDIAN) which makes this code even shorter :-) Acked-by: Andrii Nakryiko Cc: Adrian Hunter Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Jiri Olsa Cc: Namhyung Kim Fixes: 12ef5634a855 ("libbpf: simplify endianness check") Fixes: e6c64855fd7a ("libbpf: add btf__parse_elf API to load .BTF and .BTF.ext") Link: https://lkml.kernel.org/n/tip-eep5n8vgwcdphw3uc058k03u@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Daniel Borkmann --- tools/lib/bpf/btf.c | 5 +++-- tools/lib/bpf/libbpf.c | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 467224feb43b..d821107f55f9 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* Copyright (c) 2018 Facebook */ +#include #include #include #include @@ -419,9 +420,9 @@ done: static bool btf_check_endianness(const GElf_Ehdr *ehdr) { -#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#if __BYTE_ORDER == __LITTLE_ENDIAN return ehdr->e_ident[EI_DATA] == ELFDATA2LSB; -#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +#elif __BYTE_ORDER == __BIG_ENDIAN return ehdr->e_ident[EI_DATA] == ELFDATA2MSB; #else # error "Unrecognized __BYTE_ORDER__" diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index d8833ff6c4a1..c4ea239abff3 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -612,10 +613,10 @@ errout: static int bpf_object__check_endianness(struct bpf_object *obj) { -#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#if __BYTE_ORDER == __LITTLE_ENDIAN if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB) return 0; -#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +#elif __BYTE_ORDER == __BIG_ENDIAN if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB) return 0; #else From 4be6e05c4d4c2ff87750d3242f69999245d119f8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 19 Jul 2019 11:34:07 -0300 Subject: [PATCH 183/823] libbpf: Avoid designated initializers for unnamed union members As it fails to build in some systems with: libbpf.c: In function 'perf_buffer__new': libbpf.c:4515: error: unknown field 'sample_period' specified in initializer libbpf.c:4516: error: unknown field 'wakeup_events' specified in initializer Doing as: attr.sample_period = 1; I.e. not as a designated initializer makes it build everywhere. Cc: Andrii Nakryiko Cc: Adrian Hunter Cc: Daniel Borkmann Cc: Jiri Olsa Cc: Namhyung Kim Fixes: fb84b8224655 ("libbpf: add perf buffer API") Link: https://lkml.kernel.org/n/tip-hnlmch8qit1ieksfppmr32si@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo Acked-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann --- tools/lib/bpf/libbpf.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index c4ea239abff3..2586b6cb8f34 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -4519,13 +4519,13 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, const struct perf_buffer_opts *opts) { struct perf_buffer_params p = {}; - struct perf_event_attr attr = { - .config = PERF_COUNT_SW_BPF_OUTPUT, - .type = PERF_TYPE_SOFTWARE, - .sample_type = PERF_SAMPLE_RAW, - .sample_period = 1, - .wakeup_events = 1, - }; + struct perf_event_attr attr = { 0, }; + + attr.config = PERF_COUNT_SW_BPF_OUTPUT, + attr.type = PERF_TYPE_SOFTWARE; + attr.sample_type = PERF_SAMPLE_RAW; + attr.sample_period = 1; + attr.wakeup_events = 1; p.attr = &attr; p.sample_cb = opts ? opts->sample_cb : NULL; From 5d9e06d60eee95e021ffccf0d2c7ed800ae9dc14 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Mon, 22 Jul 2019 22:12:36 +0800 Subject: [PATCH 184/823] bcache: fix possible memory leak in bch_cached_dev_run() memory malloced in bch_cached_dev_run() and should be freed before leaving from the error handling cases, otherwise it will cause memory leak. Fixes: 0b13efecf5f2 ("bcache: add return value check to bch_cached_dev_run()") Signed-off-by: Wei Yongjun Signed-off-by: Coly Li Signed-off-by: Jens Axboe --- drivers/md/bcache/super.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 26e374fbf57c..20ed838e9413 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -931,6 +931,9 @@ int bch_cached_dev_run(struct cached_dev *dc) if (dc->io_disable) { pr_err("I/O disabled on cached dev %s", dc->backing_dev_name); + kfree(env[1]); + kfree(env[2]); + kfree(buf); return -EIO; } From c8eee4135a456bc031d67cadc454e76880d1afd8 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Fri, 19 Jul 2019 11:06:11 +0200 Subject: [PATCH 185/823] selftests/bpf: fix sendmsg6_prog on s390 "sendmsg6: rewrite IP & port (C)" fails on s390, because the code in sendmsg_v6_prog() assumes that (ctx->user_ip6[0] & 0xFFFF) refers to leading IPv6 address digits, which is not the case on big-endian machines. Since checking bitwise operations doesn't seem to be the point of the test, replace two short comparisons with a single int comparison. Signed-off-by: Ilya Leoshkevich Acked-by: Andrey Ignatov Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/progs/sendmsg6_prog.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c index 5aeaa284fc47..a68062820410 100644 --- a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c +++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c @@ -41,8 +41,7 @@ int sendmsg_v6_prog(struct bpf_sock_addr *ctx) } /* Rewrite destination. */ - if ((ctx->user_ip6[0] & 0xFFFF) == bpf_htons(0xFACE) && - ctx->user_ip6[0] >> 16 == bpf_htons(0xB00C)) { + if (ctx->user_ip6[0] == bpf_htonl(0xFACEB00C)) { ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0); ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_1); ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2); From 301e7ee1dec513e5aca12d01c819a1f762918d0a Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 22 Jul 2019 16:21:05 +0200 Subject: [PATCH 186/823] Revert "iommu/vt-d: Consolidate domain_init() to avoid duplication" This reverts commit 123b2ffc376e1b3e9e015c75175b61e88a8b8518. This commit reportedly caused boot failures on some systems and needs to be reverted for now. Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 123 +++++++++++++++++++++++++----------- 1 file changed, 87 insertions(+), 36 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index ac4172c02244..441781d12553 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1833,6 +1833,63 @@ static inline int guestwidth_to_adjustwidth(int gaw) return agaw; } +static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu, + int guest_width) +{ + int adjust_width, agaw; + unsigned long sagaw; + int err; + + init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN); + + err = init_iova_flush_queue(&domain->iovad, + iommu_flush_iova, iova_entry_free); + if (err) + return err; + + domain_reserve_special_ranges(domain); + + /* calculate AGAW */ + if (guest_width > cap_mgaw(iommu->cap)) + guest_width = cap_mgaw(iommu->cap); + domain->gaw = guest_width; + adjust_width = guestwidth_to_adjustwidth(guest_width); + agaw = width_to_agaw(adjust_width); + sagaw = cap_sagaw(iommu->cap); + if (!test_bit(agaw, &sagaw)) { + /* hardware doesn't support it, choose a bigger one */ + pr_debug("Hardware doesn't support agaw %d\n", agaw); + agaw = find_next_bit(&sagaw, 5, agaw); + if (agaw >= 5) + return -ENODEV; + } + domain->agaw = agaw; + + if (ecap_coherent(iommu->ecap)) + domain->iommu_coherency = 1; + else + domain->iommu_coherency = 0; + + if (ecap_sc_support(iommu->ecap)) + domain->iommu_snooping = 1; + else + domain->iommu_snooping = 0; + + if (intel_iommu_superpage) + domain->iommu_superpage = fls(cap_super_page_val(iommu->cap)); + else + domain->iommu_superpage = 0; + + domain->nid = iommu->node; + + /* always allocate the top pgd */ + domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid); + if (!domain->pgd) + return -ENOMEM; + __iommu_flush_cache(iommu, domain->pgd, PAGE_SIZE); + return 0; +} + static void domain_exit(struct dmar_domain *domain) { struct page *freelist; @@ -2513,31 +2570,6 @@ static int get_last_alias(struct pci_dev *pdev, u16 alias, void *opaque) return 0; } -static int domain_init(struct dmar_domain *domain, int guest_width) -{ - int adjust_width; - - init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN); - domain_reserve_special_ranges(domain); - - /* calculate AGAW */ - domain->gaw = guest_width; - adjust_width = guestwidth_to_adjustwidth(guest_width); - domain->agaw = width_to_agaw(adjust_width); - - domain->iommu_coherency = 0; - domain->iommu_snooping = 0; - domain->iommu_superpage = 0; - domain->max_addr = 0; - - /* always allocate the top pgd */ - domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid); - if (!domain->pgd) - return -ENOMEM; - domain_flush_cache(domain, domain->pgd, PAGE_SIZE); - return 0; -} - static struct dmar_domain *find_or_alloc_domain(struct device *dev, int gaw) { struct device_domain_info *info; @@ -2575,19 +2607,11 @@ static struct dmar_domain *find_or_alloc_domain(struct device *dev, int gaw) domain = alloc_domain(0); if (!domain) return NULL; - - if (domain_init(domain, gaw)) { + if (domain_init(domain, iommu, gaw)) { domain_exit(domain); return NULL; } - if (init_iova_flush_queue(&domain->iovad, - iommu_flush_iova, - iova_entry_free)) { - pr_warn("iova flush queue initialization failed\n"); - intel_iommu_strict = 1; - } - out: return domain; } @@ -2692,6 +2716,8 @@ static int domain_prepare_identity_map(struct device *dev, return iommu_domain_identity_map(domain, start, end); } +static int md_domain_init(struct dmar_domain *domain, int guest_width); + static int __init si_domain_init(int hw) { struct dmar_rmrr_unit *rmrr; @@ -2702,7 +2728,7 @@ static int __init si_domain_init(int hw) if (!si_domain) return -EFAULT; - if (domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { + if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { domain_exit(si_domain); return -EFAULT; } @@ -4829,6 +4855,31 @@ static void dmar_remove_one_dev_info(struct device *dev) spin_unlock_irqrestore(&device_domain_lock, flags); } +static int md_domain_init(struct dmar_domain *domain, int guest_width) +{ + int adjust_width; + + init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN); + domain_reserve_special_ranges(domain); + + /* calculate AGAW */ + domain->gaw = guest_width; + adjust_width = guestwidth_to_adjustwidth(guest_width); + domain->agaw = width_to_agaw(adjust_width); + + domain->iommu_coherency = 0; + domain->iommu_snooping = 0; + domain->iommu_superpage = 0; + domain->max_addr = 0; + + /* always allocate the top pgd */ + domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid); + if (!domain->pgd) + return -ENOMEM; + domain_flush_cache(domain, domain->pgd, PAGE_SIZE); + return 0; +} + static struct iommu_domain *intel_iommu_domain_alloc(unsigned type) { struct dmar_domain *dmar_domain; @@ -4843,7 +4894,7 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type) pr_err("Can't allocate dmar_domain\n"); return NULL; } - if (domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { + if (md_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { pr_err("Domain initialization failed\n"); domain_exit(dmar_domain); return NULL; From cbdf8a189a66001c36007bf0f5c975d0376c5c3a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 22 Jul 2019 14:53:09 +0100 Subject: [PATCH 187/823] arm64: Force SSBS on context switch On a CPU that doesn't support SSBS, PSTATE[12] is RES0. In a system where only some of the CPUs implement SSBS, we end-up losing track of the SSBS bit across task migration. To address this issue, let's force the SSBS bit on context switch. Fixes: 8f04e8e6e29c ("arm64: ssbd: Add support for PSTATE.SSBS rather than trapping to EL3") Signed-off-by: Marc Zyngier [will: inverted logic and added comments] Signed-off-by: Will Deacon --- arch/arm64/include/asm/processor.h | 14 ++++++++++++-- arch/arm64/kernel/process.c | 29 ++++++++++++++++++++++++++++- 2 files changed, 40 insertions(+), 3 deletions(-) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index fd5b1a4efc70..844e2964b0f5 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -193,6 +193,16 @@ static inline void start_thread_common(struct pt_regs *regs, unsigned long pc) regs->pmr_save = GIC_PRIO_IRQON; } +static inline void set_ssbs_bit(struct pt_regs *regs) +{ + regs->pstate |= PSR_SSBS_BIT; +} + +static inline void set_compat_ssbs_bit(struct pt_regs *regs) +{ + regs->pstate |= PSR_AA32_SSBS_BIT; +} + static inline void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { @@ -200,7 +210,7 @@ static inline void start_thread(struct pt_regs *regs, unsigned long pc, regs->pstate = PSR_MODE_EL0t; if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE) - regs->pstate |= PSR_SSBS_BIT; + set_ssbs_bit(regs); regs->sp = sp; } @@ -219,7 +229,7 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, #endif if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE) - regs->pstate |= PSR_AA32_SSBS_BIT; + set_compat_ssbs_bit(regs); regs->compat_sp = sp; } diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 8d836d0abc96..f674f28df663 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -398,7 +398,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, childregs->pstate |= PSR_UAO_BIT; if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) - childregs->pstate |= PSR_SSBS_BIT; + set_ssbs_bit(childregs); if (system_uses_irq_prio_masking()) childregs->pmr_save = GIC_PRIO_IRQON; @@ -442,6 +442,32 @@ void uao_thread_switch(struct task_struct *next) } } +/* + * Force SSBS state on context-switch, since it may be lost after migrating + * from a CPU which treats the bit as RES0 in a heterogeneous system. + */ +static void ssbs_thread_switch(struct task_struct *next) +{ + struct pt_regs *regs = task_pt_regs(next); + + /* + * Nothing to do for kernel threads, but 'regs' may be junk + * (e.g. idle task) so check the flags and bail early. + */ + if (unlikely(next->flags & PF_KTHREAD)) + return; + + /* If the mitigation is enabled, then we leave SSBS clear. */ + if ((arm64_get_ssbd_state() == ARM64_SSBD_FORCE_ENABLE) || + test_tsk_thread_flag(next, TIF_SSBD)) + return; + + if (compat_user_mode(regs)) + set_compat_ssbs_bit(regs); + else if (user_mode(regs)) + set_ssbs_bit(regs); +} + /* * We store our current task in sp_el0, which is clobbered by userspace. Keep a * shadow copy so that we can restore this upon entry from userspace. @@ -471,6 +497,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, entry_task_switch(next); uao_thread_switch(next); ptrauth_thread_switch(next); + ssbs_thread_switch(next); /* * Complete any pending TLB or cache maintenance on this CPU in case From 557529494d79f3f1fadd486dd18d2de0b19be4da Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 9 Jul 2019 13:22:45 +0800 Subject: [PATCH 188/823] iommu/vt-d: Avoid duplicated pci dma alias consideration As we have abandoned the home-made lazy domain allocation and delegated the DMA domain life cycle up to the default domain mechanism defined in the generic iommu layer, we needn't consider pci alias anymore when mapping/unmapping the context entries. Without this fix, we see kernel NULL pointer dereference during pci device hot-plug test. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Fixes: fa954e6831789 ("iommu/vt-d: Delegate the dma domain to upper layer") Signed-off-by: Lu Baolu Reported-and-tested-by: Xu Pengfei Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 55 ++----------------------------------- 1 file changed, 2 insertions(+), 53 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 441781d12553..9b1d62d03370 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -339,8 +339,6 @@ static void domain_exit(struct dmar_domain *domain); static void domain_remove_dev_info(struct dmar_domain *domain); static void dmar_remove_one_dev_info(struct device *dev); static void __dmar_remove_one_dev_info(struct device_domain_info *info); -static void domain_context_clear(struct intel_iommu *iommu, - struct device *dev); static int domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu); static bool device_is_rmrr_locked(struct device *dev); @@ -2105,26 +2103,9 @@ out_unlock: return ret; } -struct domain_context_mapping_data { - struct dmar_domain *domain; - struct intel_iommu *iommu; - struct pasid_table *table; -}; - -static int domain_context_mapping_cb(struct pci_dev *pdev, - u16 alias, void *opaque) -{ - struct domain_context_mapping_data *data = opaque; - - return domain_context_mapping_one(data->domain, data->iommu, - data->table, PCI_BUS_NUM(alias), - alias & 0xff); -} - static int domain_context_mapping(struct dmar_domain *domain, struct device *dev) { - struct domain_context_mapping_data data; struct pasid_table *table; struct intel_iommu *iommu; u8 bus, devfn; @@ -2134,17 +2115,7 @@ domain_context_mapping(struct dmar_domain *domain, struct device *dev) return -ENODEV; table = intel_pasid_get_table(dev); - - if (!dev_is_pci(dev)) - return domain_context_mapping_one(domain, iommu, table, - bus, devfn); - - data.domain = domain; - data.iommu = iommu; - data.table = table; - - return pci_for_each_dma_alias(to_pci_dev(dev), - &domain_context_mapping_cb, &data); + return domain_context_mapping_one(domain, iommu, table, bus, devfn); } static int domain_context_mapped_cb(struct pci_dev *pdev, @@ -4784,28 +4755,6 @@ out_free_dmar: return ret; } -static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *opaque) -{ - struct intel_iommu *iommu = opaque; - - domain_context_clear_one(iommu, PCI_BUS_NUM(alias), alias & 0xff); - return 0; -} - -/* - * NB - intel-iommu lacks any sort of reference counting for the users of - * dependent devices. If multiple endpoints have intersecting dependent - * devices, unbinding the driver from any one of them will possibly leave - * the others unable to operate. - */ -static void domain_context_clear(struct intel_iommu *iommu, struct device *dev) -{ - if (!iommu || !dev || !dev_is_pci(dev)) - return; - - pci_for_each_dma_alias(to_pci_dev(dev), &domain_context_clear_one_cb, iommu); -} - static void __dmar_remove_one_dev_info(struct device_domain_info *info) { struct dmar_domain *domain; @@ -4826,7 +4775,7 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info) PASID_RID2PASID); iommu_disable_dev_iotlb(info); - domain_context_clear(iommu, info->dev); + domain_context_clear_one(iommu, info->bus, info->devfn); intel_pasid_free_table(info->dev); } From dd422906799f240bfd400a5d376aa43f7b89c38a Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Thu, 18 Jul 2019 17:27:20 +0800 Subject: [PATCH 189/823] mm/balloon_compaction: avoid duplicate page removal A #GP is reported in the guest when requesting balloon inflation via virtio-balloon. The reason is that the virtio-balloon driver has removed the page from its internal page list (via balloon_page_pop), but balloon_page_enqueue_one also calls "list_del" to do the removal. This is necessary when it's used from balloon_page_enqueue_list, but not from balloon_page_enqueue. Move list_del to balloon_page_enqueue, and update comments accordingly. Fixes: 418a3ab1e778 (mm/balloon_compaction: List interfaces) Signed-off-by: Wei Wang Signed-off-by: Michael S. Tsirkin --- mm/balloon_compaction.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c index 83a7b614061f..d25664e1857b 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -21,7 +21,6 @@ static void balloon_page_enqueue_one(struct balloon_dev_info *b_dev_info, * memory corruption is possible and we should stop execution. */ BUG_ON(!trylock_page(page)); - list_del(&page->lru); balloon_page_insert(b_dev_info, page); unlock_page(page); __count_vm_event(BALLOON_INFLATE); @@ -47,6 +46,7 @@ size_t balloon_page_list_enqueue(struct balloon_dev_info *b_dev_info, spin_lock_irqsave(&b_dev_info->pages_lock, flags); list_for_each_entry_safe(page, tmp, pages, lru) { + list_del(&page->lru); balloon_page_enqueue_one(b_dev_info, page); n_pages++; } @@ -128,13 +128,19 @@ struct page *balloon_page_alloc(void) EXPORT_SYMBOL_GPL(balloon_page_alloc); /* - * balloon_page_enqueue - allocates a new page and inserts it into the balloon - * page list. + * balloon_page_enqueue - inserts a new page into the balloon page list. + * * @b_dev_info: balloon device descriptor where we will insert a new page to * @page: new page to enqueue - allocated using balloon_page_alloc. * * Driver must call it to properly enqueue a new allocated balloon page * before definitively removing it from the guest system. + * + * Drivers must not call balloon_page_enqueue on pages that have been + * pushed to a list with balloon_page_push before removing them with + * balloon_page_pop. To all pages on a list, use balloon_page_list_enqueue + * instead. + * * This function returns the page address for the recently enqueued page or * NULL in the case we fail to allocate a new page this turn. */ From cfe61801b0f11eb561f1adf452d995efaafbc68b Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 18 Jul 2019 08:19:24 -0400 Subject: [PATCH 190/823] balloon: fix up comments Lots of comments bitrotted. Fix them up. Fixes: 418a3ab1e778 (mm/balloon_compaction: List interfaces) Reviewed-by: Wei Wang Signed-off-by: Michael S. Tsirkin Reviewed-by: Ralph Campbell Acked-by: Nadav Amit --- mm/balloon_compaction.c | 67 +++++++++++++++++++++++------------------ 1 file changed, 37 insertions(+), 30 deletions(-) diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c index d25664e1857b..798275a51887 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -32,8 +32,8 @@ static void balloon_page_enqueue_one(struct balloon_dev_info *b_dev_info, * @b_dev_info: balloon device descriptor where we will insert a new page to * @pages: pages to enqueue - allocated using balloon_page_alloc. * - * Driver must call it to properly enqueue a balloon pages before definitively - * removing it from the guest system. + * Driver must call this function to properly enqueue balloon pages before + * definitively removing them from the guest system. * * Return: number of pages that were enqueued. */ @@ -63,12 +63,13 @@ EXPORT_SYMBOL_GPL(balloon_page_list_enqueue); * @n_req_pages: number of requested pages. * * Driver must call this function to properly de-allocate a previous enlisted - * balloon pages before definetively releasing it back to the guest system. + * balloon pages before definitively releasing it back to the guest system. * This function tries to remove @n_req_pages from the ballooned pages and * return them to the caller in the @pages list. * - * Note that this function may fail to dequeue some pages temporarily empty due - * to compaction isolated pages. + * Note that this function may fail to dequeue some pages even if the balloon + * isn't empty - since the page list can be temporarily empty due to compaction + * of isolated pages. * * Return: number of pages that were added to the @pages list. */ @@ -112,12 +113,13 @@ EXPORT_SYMBOL_GPL(balloon_page_list_dequeue); /* * balloon_page_alloc - allocates a new page for insertion into the balloon - * page list. + * page list. * - * Driver must call it to properly allocate a new enlisted balloon page. - * Driver must call balloon_page_enqueue before definitively removing it from - * the guest system. This function returns the page address for the recently - * allocated page or NULL in the case we fail to allocate a new page this turn. + * Driver must call this function to properly allocate a new balloon page. + * Driver must call balloon_page_enqueue before definitively removing the page + * from the guest system. + * + * Return: struct page for the allocated page or NULL on allocation failure. */ struct page *balloon_page_alloc(void) { @@ -130,19 +132,15 @@ EXPORT_SYMBOL_GPL(balloon_page_alloc); /* * balloon_page_enqueue - inserts a new page into the balloon page list. * - * @b_dev_info: balloon device descriptor where we will insert a new page to + * @b_dev_info: balloon device descriptor where we will insert a new page * @page: new page to enqueue - allocated using balloon_page_alloc. * - * Driver must call it to properly enqueue a new allocated balloon page - * before definitively removing it from the guest system. + * Drivers must call this function to properly enqueue a new allocated balloon + * page before definitively removing the page from the guest system. * - * Drivers must not call balloon_page_enqueue on pages that have been - * pushed to a list with balloon_page_push before removing them with - * balloon_page_pop. To all pages on a list, use balloon_page_list_enqueue - * instead. - * - * This function returns the page address for the recently enqueued page or - * NULL in the case we fail to allocate a new page this turn. + * Drivers must not call balloon_page_enqueue on pages that have been pushed to + * a list with balloon_page_push before removing them with balloon_page_pop. To + * enqueue a list of pages, use balloon_page_list_enqueue instead. */ void balloon_page_enqueue(struct balloon_dev_info *b_dev_info, struct page *page) @@ -157,14 +155,23 @@ EXPORT_SYMBOL_GPL(balloon_page_enqueue); /* * balloon_page_dequeue - removes a page from balloon's page list and returns - * the its address to allow the driver release the page. + * its address to allow the driver to release the page. * @b_dev_info: balloon device decriptor where we will grab a page from. * - * Driver must call it to properly de-allocate a previous enlisted balloon page - * before definetively releasing it back to the guest system. - * This function returns the page address for the recently dequeued page or - * NULL in the case we find balloon's page list temporarily empty due to - * compaction isolated pages. + * Driver must call this function to properly dequeue a previously enqueued page + * before definitively releasing it back to the guest system. + * + * Caller must perform its own accounting to ensure that this + * function is called only if some pages are actually enqueued. + * + * Note that this function may fail to dequeue some pages even if there are + * some enqueued pages - since the page list can be temporarily empty due to + * the compaction of isolated pages. + * + * TODO: remove the caller accounting requirements, and allow caller to wait + * until all pages can be dequeued. + * + * Return: struct page for the dequeued page, or NULL if no page was dequeued. */ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info) { @@ -177,9 +184,9 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info) if (n_pages != 1) { /* * If we are unable to dequeue a balloon page because the page - * list is empty and there is no isolated pages, then something + * list is empty and there are no isolated pages, then something * went out of track and some balloon pages are lost. - * BUG() here, otherwise the balloon driver may get stuck into + * BUG() here, otherwise the balloon driver may get stuck in * an infinite loop while attempting to release all its pages. */ spin_lock_irqsave(&b_dev_info->pages_lock, flags); @@ -230,8 +237,8 @@ int balloon_page_migrate(struct address_space *mapping, /* * We can not easily support the no copy case here so ignore it as it - * is unlikely to be use with ballon pages. See include/linux/hmm.h for - * user of the MIGRATE_SYNC_NO_COPY mode. + * is unlikely to be used with balloon pages. See include/linux/hmm.h + * for a user of the MIGRATE_SYNC_NO_COPY mode. */ if (mode == MIGRATE_SYNC_NO_COPY) return -EINVAL; From 40ca0ce56d4bb889dc43b455c55398468115569a Mon Sep 17 00:00:00 2001 From: James Morse Date: Mon, 22 Jul 2019 16:11:48 +0100 Subject: [PATCH 191/823] arm64: entry: SP Alignment Fault doesn't write to FAR_EL1 Comparing the arm-arm's pseudocode for AArch64.PCAlignmentFault() with AArch64.SPAlignmentFault() shows that SP faults don't copy the faulty-SP to FAR_EL1, but this is where we read from, and the address we provide to user-space with the BUS_ADRALN signal. For user-space this value will be UNKNOWN due to the previous ERET to user-space. If the last value is preserved, on systems with KASLR or KPTI this will be the user-space link-register left in FAR_EL1 by tramp_exit(). Fix this to retrieve the original sp_el0 value, and pass this to do_sp_pc_fault(). SP alignment faults from EL1 will cause us to take the fault again when trying to store the pt_regs. This eventually takes us to the overflow stack. Remove the ESR_ELx_EC_SP_ALIGN check as we will never make it this far. Fixes: 60ffc30d5652 ("arm64: Exception handling") Signed-off-by: James Morse [will: change label name and fleshed out comment] Signed-off-by: Will Deacon --- arch/arm64/kernel/entry.S | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 9cdc4592da3e..320a30dbe35e 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -586,10 +586,8 @@ el1_sync: b.eq el1_ia cmp x24, #ESR_ELx_EC_SYS64 // configurable trap b.eq el1_undef - cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception - b.eq el1_sp_pc cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el1_sp_pc + b.eq el1_pc cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL1 b.eq el1_undef cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1 @@ -611,9 +609,11 @@ el1_da: bl do_mem_abort kernel_exit 1 -el1_sp_pc: +el1_pc: /* - * Stack or PC alignment exception handling + * PC alignment exception handling. We don't handle SP alignment faults, + * since we will have hit a recursive exception when trying to push the + * initial pt_regs. */ mrs x0, far_el1 inherit_daif pstate=x23, tmp=x2 @@ -732,9 +732,9 @@ el0_sync: ccmp x24, #ESR_ELx_EC_WFx, #4, ne b.eq el0_sys cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception - b.eq el0_sp_pc + b.eq el0_sp cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el0_sp_pc + b.eq el0_pc cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0 b.eq el0_undef cmp x24, #ESR_ELx_EC_BREAKPT_LOW // debug exception in EL0 @@ -758,7 +758,7 @@ el0_sync_compat: cmp x24, #ESR_ELx_EC_FP_EXC32 // FP/ASIMD exception b.eq el0_fpsimd_exc cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el0_sp_pc + b.eq el0_pc cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0 b.eq el0_undef cmp x24, #ESR_ELx_EC_CP15_32 // CP15 MRC/MCR trap @@ -858,11 +858,15 @@ el0_fpsimd_exc: mov x1, sp bl do_fpsimd_exc b ret_to_user +el0_sp: + ldr x26, [sp, #S_SP] + b el0_sp_pc +el0_pc: + mrs x26, far_el1 el0_sp_pc: /* * Stack or PC alignment exception handling */ - mrs x26, far_el1 gic_prio_kentry_setup tmp=x0 enable_da_f #ifdef CONFIG_TRACE_IRQFLAGS From effa467870c7612012885df4e246bdb8ffd8e44c Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Tue, 16 Jul 2019 22:38:05 +0100 Subject: [PATCH 192/823] iommu/vt-d: Don't queue_iova() if there is no flush queue Intel VT-d driver was reworked to use common deferred flushing implementation. Previously there was one global per-cpu flush queue, afterwards - one per domain. Before deferring a flush, the queue should be allocated and initialized. Currently only domains with IOMMU_DOMAIN_DMA type initialize their flush queue. It's probably worth to init it for static or unmanaged domains too, but it may be arguable - I'm leaving it to iommu folks. Prevent queuing an iova flush if the domain doesn't have a queue. The defensive check seems to be worth to keep even if queue would be initialized for all kinds of domains. And is easy backportable. On 4.19.43 stable kernel it has a user-visible effect: previously for devices in si domain there were crashes, on sata devices: BUG: spinlock bad magic on CPU#6, swapper/0/1 lock: 0xffff88844f582008, .magic: 00000000, .owner: /-1, .owner_cpu: 0 CPU: 6 PID: 1 Comm: swapper/0 Not tainted 4.19.43 #1 Call Trace: dump_stack+0x61/0x7e spin_bug+0x9d/0xa3 do_raw_spin_lock+0x22/0x8e _raw_spin_lock_irqsave+0x32/0x3a queue_iova+0x45/0x115 intel_unmap+0x107/0x113 intel_unmap_sg+0x6b/0x76 __ata_qc_complete+0x7f/0x103 ata_qc_complete+0x9b/0x26a ata_qc_complete_multiple+0xd0/0xe3 ahci_handle_port_interrupt+0x3ee/0x48a ahci_handle_port_intr+0x73/0xa9 ahci_single_level_irq_intr+0x40/0x60 __handle_irq_event_percpu+0x7f/0x19a handle_irq_event_percpu+0x32/0x72 handle_irq_event+0x38/0x56 handle_edge_irq+0x102/0x121 handle_irq+0x147/0x15c do_IRQ+0x66/0xf2 common_interrupt+0xf/0xf RIP: 0010:__do_softirq+0x8c/0x2df The same for usb devices that use ehci-pci: BUG: spinlock bad magic on CPU#0, swapper/0/1 lock: 0xffff88844f402008, .magic: 00000000, .owner: /-1, .owner_cpu: 0 CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.19.43 #4 Call Trace: dump_stack+0x61/0x7e spin_bug+0x9d/0xa3 do_raw_spin_lock+0x22/0x8e _raw_spin_lock_irqsave+0x32/0x3a queue_iova+0x77/0x145 intel_unmap+0x107/0x113 intel_unmap_page+0xe/0x10 usb_hcd_unmap_urb_setup_for_dma+0x53/0x9d usb_hcd_unmap_urb_for_dma+0x17/0x100 unmap_urb_for_dma+0x22/0x24 __usb_hcd_giveback_urb+0x51/0xc3 usb_giveback_urb_bh+0x97/0xde tasklet_action_common.isra.4+0x5f/0xa1 tasklet_action+0x2d/0x30 __do_softirq+0x138/0x2df irq_exit+0x7d/0x8b smp_apic_timer_interrupt+0x10f/0x151 apic_timer_interrupt+0xf/0x20 RIP: 0010:_raw_spin_unlock_irqrestore+0x17/0x39 Cc: David Woodhouse Cc: Joerg Roedel Cc: Lu Baolu Cc: iommu@lists.linux-foundation.org Cc: # 4.14+ Fixes: 13cf01744608 ("iommu/vt-d: Make use of iova deferred flushing") Signed-off-by: Dmitry Safonov Reviewed-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 3 ++- drivers/iommu/iova.c | 18 ++++++++++++++---- include/linux/iova.h | 6 ++++++ 3 files changed, 22 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 9b1d62d03370..72c6d647bec9 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -3561,7 +3561,8 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size) freelist = domain_unmap(domain, start_pfn, last_pfn); - if (intel_iommu_strict || (pdev && pdev->untrusted)) { + if (intel_iommu_strict || (pdev && pdev->untrusted) || + !has_iova_flush_queue(&domain->iovad)) { iommu_flush_iotlb_psi(iommu, domain, start_pfn, nrpages, !freelist, 0); /* free iova */ diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index d499b2621239..8413ae54904a 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -54,9 +54,14 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule, } EXPORT_SYMBOL_GPL(init_iova_domain); +bool has_iova_flush_queue(struct iova_domain *iovad) +{ + return !!iovad->fq; +} + static void free_iova_flush_queue(struct iova_domain *iovad) { - if (!iovad->fq) + if (!has_iova_flush_queue(iovad)) return; if (timer_pending(&iovad->fq_timer)) @@ -74,13 +79,14 @@ static void free_iova_flush_queue(struct iova_domain *iovad) int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb, iova_entry_dtor entry_dtor) { + struct iova_fq __percpu *queue; int cpu; atomic64_set(&iovad->fq_flush_start_cnt, 0); atomic64_set(&iovad->fq_flush_finish_cnt, 0); - iovad->fq = alloc_percpu(struct iova_fq); - if (!iovad->fq) + queue = alloc_percpu(struct iova_fq); + if (!queue) return -ENOMEM; iovad->flush_cb = flush_cb; @@ -89,13 +95,17 @@ int init_iova_flush_queue(struct iova_domain *iovad, for_each_possible_cpu(cpu) { struct iova_fq *fq; - fq = per_cpu_ptr(iovad->fq, cpu); + fq = per_cpu_ptr(queue, cpu); fq->head = 0; fq->tail = 0; spin_lock_init(&fq->lock); } + smp_wmb(); + + iovad->fq = queue; + timer_setup(&iovad->fq_timer, fq_flush_timeout, 0); atomic_set(&iovad->fq_timer_on, 0); diff --git a/include/linux/iova.h b/include/linux/iova.h index 781b96ac706f..cd0f1de901a8 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -155,6 +155,7 @@ struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn); +bool has_iova_flush_queue(struct iova_domain *iovad); int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb, iova_entry_dtor entry_dtor); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); @@ -235,6 +236,11 @@ static inline void init_iova_domain(struct iova_domain *iovad, { } +bool has_iova_flush_queue(struct iova_domain *iovad) +{ + return false; +} + static inline int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb, iova_entry_dtor entry_dtor) From 3ee9eca760e7d0b68c55813243de66bbb499dc3b Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Tue, 16 Jul 2019 22:38:06 +0100 Subject: [PATCH 193/823] iommu/vt-d: Check if domain->pgd was allocated There is a couple of places where on domain_init() failure domain_exit() is called. While currently domain_init() can fail only if alloc_pgtable_page() has failed. Make domain_exit() check if domain->pgd present, before calling domain_unmap(), as it theoretically should crash on clearing pte entries in dma_pte_clear_level(). Cc: David Woodhouse Cc: Joerg Roedel Cc: Lu Baolu Cc: iommu@lists.linux-foundation.org Signed-off-by: Dmitry Safonov Reviewed-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 72c6d647bec9..bdaed2da8a55 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1890,7 +1890,6 @@ static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu, static void domain_exit(struct dmar_domain *domain) { - struct page *freelist; /* Remove associated devices and clear attached or cached domains */ domain_remove_dev_info(domain); @@ -1898,9 +1897,12 @@ static void domain_exit(struct dmar_domain *domain) /* destroy iovas */ put_iova_domain(&domain->iovad); - freelist = domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw)); + if (domain->pgd) { + struct page *freelist; - dma_free_pagelist(freelist); + freelist = domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw)); + dma_free_pagelist(freelist); + } free_domain_mem(domain); } From 9eed17d37c77171cf5ffb95c4257f87df3cd4c8f Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Sat, 20 Jul 2019 19:08:48 +0100 Subject: [PATCH 194/823] iommu/iova: Remove stale cached32_node Since the cached32_node is allowed to be advanced above dma_32bit_pfn (to provide a shortcut into the limited range), we need to be careful to remove the to be freed node if it is the cached32_node. [ 48.477773] BUG: KASAN: use-after-free in __cached_rbnode_delete_update+0x68/0x110 [ 48.477812] Read of size 8 at addr ffff88870fc19020 by task kworker/u8:1/37 [ 48.477843] [ 48.477879] CPU: 1 PID: 37 Comm: kworker/u8:1 Tainted: G U 5.2.0+ #735 [ 48.477915] Hardware name: Intel Corporation NUC7i5BNK/NUC7i5BNB, BIOS BNKBL357.86A.0052.2017.0918.1346 09/18/2017 [ 48.478047] Workqueue: i915 __i915_gem_free_work [i915] [ 48.478075] Call Trace: [ 48.478111] dump_stack+0x5b/0x90 [ 48.478137] print_address_description+0x67/0x237 [ 48.478178] ? __cached_rbnode_delete_update+0x68/0x110 [ 48.478212] __kasan_report.cold.3+0x1c/0x38 [ 48.478240] ? __cached_rbnode_delete_update+0x68/0x110 [ 48.478280] ? __cached_rbnode_delete_update+0x68/0x110 [ 48.478308] __cached_rbnode_delete_update+0x68/0x110 [ 48.478344] private_free_iova+0x2b/0x60 [ 48.478378] iova_magazine_free_pfns+0x46/0xa0 [ 48.478403] free_iova_fast+0x277/0x340 [ 48.478443] fq_ring_free+0x15a/0x1a0 [ 48.478473] queue_iova+0x19c/0x1f0 [ 48.478597] cleanup_page_dma.isra.64+0x62/0xb0 [i915] [ 48.478712] __gen8_ppgtt_cleanup+0x63/0x80 [i915] [ 48.478826] __gen8_ppgtt_cleanup+0x42/0x80 [i915] [ 48.478940] __gen8_ppgtt_clear+0x433/0x4b0 [i915] [ 48.479053] __gen8_ppgtt_clear+0x462/0x4b0 [i915] [ 48.479081] ? __sg_free_table+0x9e/0xf0 [ 48.479116] ? kfree+0x7f/0x150 [ 48.479234] i915_vma_unbind+0x1e2/0x240 [i915] [ 48.479352] i915_vma_destroy+0x3a/0x280 [i915] [ 48.479465] __i915_gem_free_objects+0xf0/0x2d0 [i915] [ 48.479579] __i915_gem_free_work+0x41/0xa0 [i915] [ 48.479607] process_one_work+0x495/0x710 [ 48.479642] worker_thread+0x4c7/0x6f0 [ 48.479687] ? process_one_work+0x710/0x710 [ 48.479724] kthread+0x1b2/0x1d0 [ 48.479774] ? kthread_create_worker_on_cpu+0xa0/0xa0 [ 48.479820] ret_from_fork+0x1f/0x30 [ 48.479864] [ 48.479907] Allocated by task 631: [ 48.479944] save_stack+0x19/0x80 [ 48.479994] __kasan_kmalloc.constprop.6+0xc1/0xd0 [ 48.480038] kmem_cache_alloc+0x91/0xf0 [ 48.480082] alloc_iova+0x2b/0x1e0 [ 48.480125] alloc_iova_fast+0x58/0x376 [ 48.480166] intel_alloc_iova+0x90/0xc0 [ 48.480214] intel_map_sg+0xde/0x1f0 [ 48.480343] i915_gem_gtt_prepare_pages+0xb8/0x170 [i915] [ 48.480465] huge_get_pages+0x232/0x2b0 [i915] [ 48.480590] ____i915_gem_object_get_pages+0x40/0xb0 [i915] [ 48.480712] __i915_gem_object_get_pages+0x90/0xa0 [i915] [ 48.480834] i915_gem_object_prepare_write+0x2d6/0x330 [i915] [ 48.480955] create_test_object.isra.54+0x1a9/0x3e0 [i915] [ 48.481075] igt_shared_ctx_exec+0x365/0x3c0 [i915] [ 48.481210] __i915_subtests.cold.4+0x30/0x92 [i915] [ 48.481341] __run_selftests.cold.3+0xa9/0x119 [i915] [ 48.481466] i915_live_selftests+0x3c/0x70 [i915] [ 48.481583] i915_pci_probe+0xe7/0x220 [i915] [ 48.481620] pci_device_probe+0xe0/0x180 [ 48.481665] really_probe+0x163/0x4e0 [ 48.481710] device_driver_attach+0x85/0x90 [ 48.481750] __driver_attach+0xa5/0x180 [ 48.481796] bus_for_each_dev+0xda/0x130 [ 48.481831] bus_add_driver+0x205/0x2e0 [ 48.481882] driver_register+0xca/0x140 [ 48.481927] do_one_initcall+0x6c/0x1af [ 48.481970] do_init_module+0x106/0x350 [ 48.482010] load_module+0x3d2c/0x3ea0 [ 48.482058] __do_sys_finit_module+0x110/0x180 [ 48.482102] do_syscall_64+0x62/0x1f0 [ 48.482147] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 48.482190] [ 48.482224] Freed by task 37: [ 48.482273] save_stack+0x19/0x80 [ 48.482318] __kasan_slab_free+0x12e/0x180 [ 48.482363] kmem_cache_free+0x70/0x140 [ 48.482406] __free_iova+0x1d/0x30 [ 48.482445] fq_ring_free+0x15a/0x1a0 [ 48.482490] queue_iova+0x19c/0x1f0 [ 48.482624] cleanup_page_dma.isra.64+0x62/0xb0 [i915] [ 48.482749] __gen8_ppgtt_cleanup+0x63/0x80 [i915] [ 48.482873] __gen8_ppgtt_cleanup+0x42/0x80 [i915] [ 48.482999] __gen8_ppgtt_clear+0x433/0x4b0 [i915] [ 48.483123] __gen8_ppgtt_clear+0x462/0x4b0 [i915] [ 48.483250] i915_vma_unbind+0x1e2/0x240 [i915] [ 48.483378] i915_vma_destroy+0x3a/0x280 [i915] [ 48.483500] __i915_gem_free_objects+0xf0/0x2d0 [i915] [ 48.483622] __i915_gem_free_work+0x41/0xa0 [i915] [ 48.483659] process_one_work+0x495/0x710 [ 48.483704] worker_thread+0x4c7/0x6f0 [ 48.483748] kthread+0x1b2/0x1d0 [ 48.483787] ret_from_fork+0x1f/0x30 [ 48.483831] [ 48.483868] The buggy address belongs to the object at ffff88870fc19000 [ 48.483868] which belongs to the cache iommu_iova of size 40 [ 48.483920] The buggy address is located 32 bytes inside of [ 48.483920] 40-byte region [ffff88870fc19000, ffff88870fc19028) [ 48.483964] The buggy address belongs to the page: [ 48.484006] page:ffffea001c3f0600 refcount:1 mapcount:0 mapping:ffff8888181a91c0 index:0x0 compound_mapcount: 0 [ 48.484045] flags: 0x8000000000010200(slab|head) [ 48.484096] raw: 8000000000010200 ffffea001c421a08 ffffea001c447e88 ffff8888181a91c0 [ 48.484141] raw: 0000000000000000 0000000000120012 00000001ffffffff 0000000000000000 [ 48.484188] page dumped because: kasan: bad access detected [ 48.484230] [ 48.484265] Memory state around the buggy address: [ 48.484314] ffff88870fc18f00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 48.484361] ffff88870fc18f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 48.484406] >ffff88870fc19000: fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc [ 48.484451] ^ [ 48.484494] ffff88870fc19080: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 48.484530] ffff88870fc19100: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108602 Fixes: e60aa7b53845 ("iommu/iova: Extend rbtree node caching") Signed-off-by: Chris Wilson Cc: Robin Murphy Cc: Joerg Roedel Cc: Joerg Roedel Cc: # v4.15+ Reviewed-by: Robin Murphy Signed-off-by: Joerg Roedel --- drivers/iommu/iova.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index 8413ae54904a..3e1a8a675572 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -137,8 +137,9 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free) struct iova *cached_iova; cached_iova = rb_entry(iovad->cached32_node, struct iova, node); - if (free->pfn_hi < iovad->dma_32bit_pfn && - free->pfn_lo >= cached_iova->pfn_lo) { + if (free == cached_iova || + (free->pfn_hi < iovad->dma_32bit_pfn && + free->pfn_lo >= cached_iova->pfn_lo)) { iovad->cached32_node = rb_next(&free->node); iovad->max32_alloc_size = iovad->dma_32bit_pfn; } From ae24fb49d01103c80d6ff3b78714259c1c62c958 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Mon, 22 Jul 2019 15:40:07 +0100 Subject: [PATCH 195/823] iommu/virtio: Update to most recent specification Following specification review a few things were changed in v8 of the virtio-iommu series [1], but have been omitted when merging the base driver. Add them now: * Remove the EXEC flag. * Add feature bit for the MMIO flag. * Change domain_bits to domain_range. * Add NOMEM status flag. [1] https://lore.kernel.org/linux-iommu/20190530170929.19366-1-jean-philippe.brucker@arm.com/ Fixes: edcd69ab9a32 ("iommu: Add virtio-iommu driver") Reported-by: Eric Auger Signed-off-by: Jean-Philippe Brucker Signed-off-by: Michael S. Tsirkin Reviewed-by: Eric Auger Tested-by: Eric Auger Acked-by: Joerg Roedel --- drivers/iommu/virtio-iommu.c | 40 ++++++++++++++++++++++--------- include/uapi/linux/virtio_iommu.h | 32 ++++++++++++++----------- 2 files changed, 47 insertions(+), 25 deletions(-) diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 433f4d2ee956..80a740df0737 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -2,7 +2,7 @@ /* * Virtio driver for the paravirtualized IOMMU * - * Copyright (C) 2018 Arm Limited + * Copyright (C) 2019 Arm Limited */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -47,7 +47,10 @@ struct viommu_dev { /* Device configuration */ struct iommu_domain_geometry geometry; u64 pgsize_bitmap; - u8 domain_bits; + u32 first_domain; + u32 last_domain; + /* Supported MAP flags */ + u32 map_flags; u32 probe_size; }; @@ -62,6 +65,7 @@ struct viommu_domain { struct viommu_dev *viommu; struct mutex mutex; /* protects viommu pointer */ unsigned int id; + u32 map_flags; spinlock_t mappings_lock; struct rb_root_cached mappings; @@ -113,6 +117,8 @@ static int viommu_get_req_errno(void *buf, size_t len) return -ENOENT; case VIRTIO_IOMMU_S_FAULT: return -EFAULT; + case VIRTIO_IOMMU_S_NOMEM: + return -ENOMEM; case VIRTIO_IOMMU_S_IOERR: case VIRTIO_IOMMU_S_DEVERR: default: @@ -607,15 +613,15 @@ static int viommu_domain_finalise(struct viommu_dev *viommu, { int ret; struct viommu_domain *vdomain = to_viommu_domain(domain); - unsigned int max_domain = viommu->domain_bits > 31 ? ~0 : - (1U << viommu->domain_bits) - 1; vdomain->viommu = viommu; + vdomain->map_flags = viommu->map_flags; domain->pgsize_bitmap = viommu->pgsize_bitmap; domain->geometry = viommu->geometry; - ret = ida_alloc_max(&viommu->domain_ids, max_domain, GFP_KERNEL); + ret = ida_alloc_range(&viommu->domain_ids, viommu->first_domain, + viommu->last_domain, GFP_KERNEL); if (ret >= 0) vdomain->id = (unsigned int)ret; @@ -710,7 +716,7 @@ static int viommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot) { int ret; - int flags; + u32 flags; struct virtio_iommu_req_map map; struct viommu_domain *vdomain = to_viommu_domain(domain); @@ -718,6 +724,9 @@ static int viommu_map(struct iommu_domain *domain, unsigned long iova, (prot & IOMMU_WRITE ? VIRTIO_IOMMU_MAP_F_WRITE : 0) | (prot & IOMMU_MMIO ? VIRTIO_IOMMU_MAP_F_MMIO : 0); + if (flags & ~vdomain->map_flags) + return -EINVAL; + ret = viommu_add_mapping(vdomain, iova, paddr, size, flags); if (ret) return ret; @@ -1027,7 +1036,8 @@ static int viommu_probe(struct virtio_device *vdev) goto err_free_vqs; } - viommu->domain_bits = 32; + viommu->map_flags = VIRTIO_IOMMU_MAP_F_READ | VIRTIO_IOMMU_MAP_F_WRITE; + viommu->last_domain = ~0U; /* Optional features */ virtio_cread_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE, @@ -1038,9 +1048,13 @@ static int viommu_probe(struct virtio_device *vdev) struct virtio_iommu_config, input_range.end, &input_end); - virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_BITS, - struct virtio_iommu_config, domain_bits, - &viommu->domain_bits); + virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE, + struct virtio_iommu_config, domain_range.start, + &viommu->first_domain); + + virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE, + struct virtio_iommu_config, domain_range.end, + &viommu->last_domain); virtio_cread_feature(vdev, VIRTIO_IOMMU_F_PROBE, struct virtio_iommu_config, probe_size, @@ -1052,6 +1066,9 @@ static int viommu_probe(struct virtio_device *vdev) .force_aperture = true, }; + if (virtio_has_feature(vdev, VIRTIO_IOMMU_F_MMIO)) + viommu->map_flags |= VIRTIO_IOMMU_MAP_F_MMIO; + viommu_ops.pgsize_bitmap = viommu->pgsize_bitmap; virtio_device_ready(vdev); @@ -1130,9 +1147,10 @@ static void viommu_config_changed(struct virtio_device *vdev) static unsigned int features[] = { VIRTIO_IOMMU_F_MAP_UNMAP, - VIRTIO_IOMMU_F_DOMAIN_BITS, VIRTIO_IOMMU_F_INPUT_RANGE, + VIRTIO_IOMMU_F_DOMAIN_RANGE, VIRTIO_IOMMU_F_PROBE, + VIRTIO_IOMMU_F_MMIO, }; static struct virtio_device_id id_table[] = { diff --git a/include/uapi/linux/virtio_iommu.h b/include/uapi/linux/virtio_iommu.h index ba1b460c9944..237e36a280cb 100644 --- a/include/uapi/linux/virtio_iommu.h +++ b/include/uapi/linux/virtio_iommu.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: BSD-3-Clause */ /* - * Virtio-iommu definition v0.9 + * Virtio-iommu definition v0.12 * - * Copyright (C) 2018 Arm Ltd. + * Copyright (C) 2019 Arm Ltd. */ #ifndef _UAPI_LINUX_VIRTIO_IOMMU_H #define _UAPI_LINUX_VIRTIO_IOMMU_H @@ -11,26 +11,31 @@ /* Feature bits */ #define VIRTIO_IOMMU_F_INPUT_RANGE 0 -#define VIRTIO_IOMMU_F_DOMAIN_BITS 1 +#define VIRTIO_IOMMU_F_DOMAIN_RANGE 1 #define VIRTIO_IOMMU_F_MAP_UNMAP 2 #define VIRTIO_IOMMU_F_BYPASS 3 #define VIRTIO_IOMMU_F_PROBE 4 +#define VIRTIO_IOMMU_F_MMIO 5 -struct virtio_iommu_range { - __u64 start; - __u64 end; +struct virtio_iommu_range_64 { + __le64 start; + __le64 end; +}; + +struct virtio_iommu_range_32 { + __le32 start; + __le32 end; }; struct virtio_iommu_config { /* Supported page sizes */ - __u64 page_size_mask; + __le64 page_size_mask; /* Supported IOVA range */ - struct virtio_iommu_range input_range; + struct virtio_iommu_range_64 input_range; /* Max domain ID size */ - __u8 domain_bits; - __u8 padding[3]; + struct virtio_iommu_range_32 domain_range; /* Probe buffer size */ - __u32 probe_size; + __le32 probe_size; }; /* Request types */ @@ -49,6 +54,7 @@ struct virtio_iommu_config { #define VIRTIO_IOMMU_S_RANGE 0x05 #define VIRTIO_IOMMU_S_NOENT 0x06 #define VIRTIO_IOMMU_S_FAULT 0x07 +#define VIRTIO_IOMMU_S_NOMEM 0x08 struct virtio_iommu_req_head { __u8 type; @@ -78,12 +84,10 @@ struct virtio_iommu_req_detach { #define VIRTIO_IOMMU_MAP_F_READ (1 << 0) #define VIRTIO_IOMMU_MAP_F_WRITE (1 << 1) -#define VIRTIO_IOMMU_MAP_F_EXEC (1 << 2) -#define VIRTIO_IOMMU_MAP_F_MMIO (1 << 3) +#define VIRTIO_IOMMU_MAP_F_MMIO (1 << 2) #define VIRTIO_IOMMU_MAP_F_MASK (VIRTIO_IOMMU_MAP_F_READ | \ VIRTIO_IOMMU_MAP_F_WRITE | \ - VIRTIO_IOMMU_MAP_F_EXEC | \ VIRTIO_IOMMU_MAP_F_MMIO) struct virtio_iommu_req_map { From 7f6cade5b6bf47daa315118a05aab613c73462ff Mon Sep 17 00:00:00 2001 From: Sai Praneeth Prakhya Date: Sun, 21 Jul 2019 17:22:07 -0700 Subject: [PATCH 196/823] iommu/vt-d: Print pasid table entries MSB to LSB in debugfs Commit dd5142ca5d24 ("iommu/vt-d: Add debugfs support to show scalable mode DMAR table internals") prints content of pasid table entries from LSB to MSB where as other entries are printed MSB to LSB. So, to maintain uniformity among all entries and to not confuse the user, print MSB first. Cc: Joerg Roedel Cc: Lu Baolu Cc: Sohil Mehta Cc: Jacob Pan Signed-off-by: Sai Praneeth Prakhya Fixes: dd5142ca5d24 ("iommu/vt-d: Add debugfs support to show scalable mode DMAR table internals") Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu-debugfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c index 73a552914455..2b25d9c59336 100644 --- a/drivers/iommu/intel-iommu-debugfs.c +++ b/drivers/iommu/intel-iommu-debugfs.c @@ -162,9 +162,9 @@ static inline void print_tbl_walk(struct seq_file *m) (u64)0, (u64)0, (u64)0); else seq_printf(m, "%-6d\t0x%016llx:0x%016llx:0x%016llx\n", - tbl_wlk->pasid, tbl_wlk->pasid_tbl_entry->val[0], + tbl_wlk->pasid, tbl_wlk->pasid_tbl_entry->val[2], tbl_wlk->pasid_tbl_entry->val[1], - tbl_wlk->pasid_tbl_entry->val[2]); + tbl_wlk->pasid_tbl_entry->val[0]); } static void pasid_tbl_walk(struct seq_file *m, struct pasid_entry *tbl_entry, From d5121ffebc38a16b2419b664e466a2f3e5c7b457 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Thu, 18 Jul 2019 09:27:10 +0000 Subject: [PATCH 197/823] RDMA/siw: Fix error return code in siw_init_module() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: bdcf26bf9b3a ("rdma/siw: network and RDMA core interface") Link: https://lore.kernel.org/r/20190718092710.85709-1-weiyongjun1@huawei.com Signed-off-by: Wei Yongjun Reviewed-by: Bernard Metzler Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/siw/siw_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index f55c4e80aea4..d0f140daf659 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -612,6 +612,7 @@ static __init int siw_init_module(void) if (!siw_create_tx_threads()) { pr_info("siw: Could not start any TX thread\n"); + rv = -ENOMEM; goto out_error; } /* From 7af5cdb158f3398a3220bd2fe81cec8d2be9317c Mon Sep 17 00:00:00 2001 From: Brian Masney Date: Wed, 26 Jun 2019 22:05:15 -0400 Subject: [PATCH 198/823] drm/msm: correct NULL pointer dereference in context_init Correct attempted NULL pointer dereference in context_init() when running without an IOMMU. Reviewed-by: Rob Clark Signed-off-by: Brian Masney Fixes: 295b22ae596c ("drm/msm: Pass the MMU domain index in struct msm_file_private") Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20190627020515.5660-1-masneyb@onstation.org --- drivers/gpu/drm/msm/msm_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index ab64ab470de7..c226156f2dea 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -619,7 +619,7 @@ static int context_init(struct drm_device *dev, struct drm_file *file) msm_submitqueue_init(dev, ctx); - ctx->aspace = priv->gpu->aspace; + ctx->aspace = priv->gpu ? priv->gpu->aspace : NULL; file->driver_priv = ctx; return 0; From 60c3becfd1a138fdcfe48f2a5ef41ef0078d481e Mon Sep 17 00:00:00 2001 From: Xi Wang Date: Thu, 11 Jul 2019 09:32:17 +0800 Subject: [PATCH 199/823] RDMA/hns: Fix sg offset non-zero issue When run perftest in many times, the system will report a BUG as follows: BUG: Bad rss-counter state mm:(____ptrval____) idx:0 val:-1 BUG: Bad rss-counter state mm:(____ptrval____) idx:1 val:1 We tested with different kernel version and found it started from the the following commit: commit d10bcf947a3e ("RDMA/umem: Combine contiguous PAGE_SIZE regions in SGEs") In this commit, the sg->offset is always 0 when sg_set_page() is called in ib_umem_get() and the drivers are not allowed to change the sgl, otherwise it will get bad page descriptor when unfolding SGEs in __ib_umem_release() as sg_page_count() will get wrong result while sgl->offset is not 0. However, there is a weird sgl usage in the current hns driver, the driver modified sg->offset after calling ib_umem_get(), which caused we iterate past the wrong number of pages in for_each_sg_page iterator. This patch fixes it by correcting the non-standard sgl usage found in the hns_roce_db_map_user() function. Fixes: d10bcf947a3e ("RDMA/umem: Combine contiguous PAGE_SIZE regions in SGEs") Fixes: 0425e3e6e0c7 ("RDMA/hns: Support flush cqe for hip08 in kernel space") Link: https://lore.kernel.org/r/1562808737-45723-1-git-send-email-oulijun@huawei.com Signed-off-by: Xi Wang Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hns/hns_roce_db.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_db.c b/drivers/infiniband/hw/hns/hns_roce_db.c index 627aa46ef683..c00714c2f16a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_db.c +++ b/drivers/infiniband/hw/hns/hns_roce_db.c @@ -12,13 +12,15 @@ int hns_roce_db_map_user(struct hns_roce_ucontext *context, struct ib_udata *udata, unsigned long virt, struct hns_roce_db *db) { + unsigned long page_addr = virt & PAGE_MASK; struct hns_roce_user_db_page *page; + unsigned int offset; int ret = 0; mutex_lock(&context->page_mutex); list_for_each_entry(page, &context->page_list, list) - if (page->user_virt == (virt & PAGE_MASK)) + if (page->user_virt == page_addr) goto found; page = kmalloc(sizeof(*page), GFP_KERNEL); @@ -28,8 +30,8 @@ int hns_roce_db_map_user(struct hns_roce_ucontext *context, } refcount_set(&page->refcount, 1); - page->user_virt = (virt & PAGE_MASK); - page->umem = ib_umem_get(udata, virt & PAGE_MASK, PAGE_SIZE, 0, 0); + page->user_virt = page_addr; + page->umem = ib_umem_get(udata, page_addr, PAGE_SIZE, 0, 0); if (IS_ERR(page->umem)) { ret = PTR_ERR(page->umem); kfree(page); @@ -39,10 +41,9 @@ int hns_roce_db_map_user(struct hns_roce_ucontext *context, list_add(&page->list, &context->page_list); found: - db->dma = sg_dma_address(page->umem->sg_head.sgl) + - (virt & ~PAGE_MASK); - page->umem->sg_head.sgl->offset = virt & ~PAGE_MASK; - db->virt_addr = sg_virt(page->umem->sg_head.sgl); + offset = virt - page_addr; + db->dma = sg_dma_address(page->umem->sg_head.sgl) + offset; + db->virt_addr = sg_virt(page->umem->sg_head.sgl) + offset; db->u.user_page = page; refcount_inc(&page->refcount); From 2e7b801eadbf327bf61041c943e5c44a5de4b0e5 Mon Sep 17 00:00:00 2001 From: Shubhashree Dhar Date: Mon, 24 Jun 2019 11:57:12 +0530 Subject: [PATCH 200/823] drm/msm/dpu: Correct dpu encoder spinlock initialization dpu encoder spinlock should be initialized during dpu encoder init instead of dpu encoder setup which is part of modeset init. Signed-off-by: Shubhashree Dhar [seanpaul resolved conflict in old init removal and revised the commit message] Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/1561357632-15361-1-git-send-email-dhar@codeaurora.org --- drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 0e2f74163a16..0aa8a12c9952 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -2221,8 +2221,6 @@ int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc, if (ret) goto fail; - spin_lock_init(&dpu_enc->enc_spinlock); - atomic_set(&dpu_enc->frame_done_timeout_ms, 0); timer_setup(&dpu_enc->frame_done_timer, dpu_encoder_frame_done_timeout, 0); @@ -2276,6 +2274,7 @@ struct drm_encoder *dpu_encoder_init(struct drm_device *dev, drm_encoder_helper_add(&dpu_enc->base, &dpu_encoder_helper_funcs); + spin_lock_init(&dpu_enc->enc_spinlock); dpu_enc->enabled = false; return &dpu_enc->base; From cd48a82087231fdba0e77521102386c6ed0168d6 Mon Sep 17 00:00:00 2001 From: John Fleck Date: Mon, 15 Jul 2019 12:45:21 -0400 Subject: [PATCH 201/823] IB/hfi1: Check for error on call to alloc_rsm_map_table The call to alloc_rsm_map_table does not check if the kmalloc fails. Check for a NULL on alloc, and bail if it fails. Fixes: 372cc85a13c9 ("IB/hfi1: Extract RSM map table init from QOS") Link: https://lore.kernel.org/r/20190715164521.74174.27047.stgit@awfm-01.aw.intel.com Cc: Reviewed-by: Mike Marciniszyn Signed-off-by: John Fleck Signed-off-by: Mike Marciniszyn Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hfi1/chip.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index d5b643a1d9fd..67052dc3100c 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -14452,7 +14452,7 @@ void hfi1_deinit_vnic_rsm(struct hfi1_devdata *dd) clear_rcvctrl(dd, RCV_CTRL_RCV_RSM_ENABLE_SMASK); } -static void init_rxe(struct hfi1_devdata *dd) +static int init_rxe(struct hfi1_devdata *dd) { struct rsm_map_table *rmt; u64 val; @@ -14461,6 +14461,9 @@ static void init_rxe(struct hfi1_devdata *dd) write_csr(dd, RCV_ERR_MASK, ~0ull); rmt = alloc_rsm_map_table(dd); + if (!rmt) + return -ENOMEM; + /* set up QOS, including the QPN map table */ init_qos(dd, rmt); init_fecn_handling(dd, rmt); @@ -14487,6 +14490,7 @@ static void init_rxe(struct hfi1_devdata *dd) val |= ((4ull & RCV_BYPASS_HDR_SIZE_MASK) << RCV_BYPASS_HDR_SIZE_SHIFT); write_csr(dd, RCV_BYPASS, val); + return 0; } static void init_other(struct hfi1_devdata *dd) @@ -15024,7 +15028,10 @@ int hfi1_init_dd(struct hfi1_devdata *dd) goto bail_cleanup; /* set initial RXE CSRs */ - init_rxe(dd); + ret = init_rxe(dd); + if (ret) + goto bail_cleanup; + /* set initial TXE CSRs */ init_txe(dd); /* set initial non-RXE, non-TXE CSRs */ From 2b74c878b0eae4c32629c2d5ba69a29f69048313 Mon Sep 17 00:00:00 2001 From: Kaike Wan Date: Mon, 15 Jul 2019 12:45:28 -0400 Subject: [PATCH 202/823] IB/hfi1: Unreserve a flushed OPFN request When an OPFN request is flushed, the request is completed without unreserving itself from the send queue. Subsequently, when a new request is post sent, the following warning will be triggered: WARNING: CPU: 4 PID: 8130 at rdmavt/qp.c:1761 rvt_post_send+0x72a/0x880 [rdmavt] Call Trace: [] dump_stack+0x19/0x1b [] __warn+0xd8/0x100 [] warn_slowpath_null+0x1d/0x20 [] rvt_post_send+0x72a/0x880 [rdmavt] [] ? account_entity_dequeue+0xae/0xd0 [] ? __kmalloc+0x55/0x230 [] ib_uverbs_post_send+0x37c/0x5d0 [ib_uverbs] [] ? rdma_lookup_put_uobject+0x26/0x60 [ib_uverbs] [] ib_uverbs_write+0x286/0x460 [ib_uverbs] [] ? security_file_permission+0x27/0xa0 [] vfs_write+0xc0/0x1f0 [] SyS_write+0x7f/0xf0 [] system_call_fastpath+0x22/0x27 This patch fixes the problem by moving rvt_qp_wqe_unreserve() into rvt_qp_complete_swqe() to simplify the code and make it less error-prone. Fixes: ca95f802ef51 ("IB/hfi1: Unreserve a reserved request when it is completed") Link: https://lore.kernel.org/r/20190715164528.74174.31364.stgit@awfm-01.aw.intel.com Cc: Reviewed-by: Mike Marciniszyn Reviewed-by: Dennis Dalessandro Signed-off-by: Kaike Wan Signed-off-by: Mike Marciniszyn Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hfi1/rc.c | 2 -- include/rdma/rdmavt_qp.h | 9 ++++----- 2 files changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c index 0477c14633ab..024a7c2b6124 100644 --- a/drivers/infiniband/hw/hfi1/rc.c +++ b/drivers/infiniband/hw/hfi1/rc.c @@ -1835,7 +1835,6 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct hfi1_opa_header *opah) cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) <= 0) break; trdma_clean_swqe(qp, wqe); - rvt_qp_wqe_unreserve(qp, wqe); trace_hfi1_qp_send_completion(qp, wqe, qp->s_last); rvt_qp_complete_swqe(qp, wqe, @@ -1882,7 +1881,6 @@ struct rvt_swqe *do_rc_completion(struct rvt_qp *qp, if (cmp_psn(wqe->lpsn, qp->s_sending_psn) < 0 || cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) > 0) { trdma_clean_swqe(qp, wqe); - rvt_qp_wqe_unreserve(qp, wqe); trace_hfi1_qp_send_completion(qp, wqe, qp->s_last); rvt_qp_complete_swqe(qp, wqe, diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index 0eeea520a853..e06c77d76463 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -608,7 +608,7 @@ static inline void rvt_qp_wqe_reserve( /** * rvt_qp_wqe_unreserve - clean reserved operation * @qp - the rvt qp - * @wqe - the send wqe + * @flags - send wqe flags * * This decrements the reserve use count. * @@ -620,11 +620,9 @@ static inline void rvt_qp_wqe_reserve( * the compiler does not juggle the order of the s_last * ring index and the decrementing of s_reserved_used. */ -static inline void rvt_qp_wqe_unreserve( - struct rvt_qp *qp, - struct rvt_swqe *wqe) +static inline void rvt_qp_wqe_unreserve(struct rvt_qp *qp, int flags) { - if (unlikely(wqe->wr.send_flags & RVT_SEND_RESERVE_USED)) { + if (unlikely(flags & RVT_SEND_RESERVE_USED)) { atomic_dec(&qp->s_reserved_used); /* insure no compiler re-order up to s_last change */ smp_mb__after_atomic(); @@ -853,6 +851,7 @@ rvt_qp_complete_swqe(struct rvt_qp *qp, u32 byte_len, last; int flags = wqe->wr.send_flags; + rvt_qp_wqe_unreserve(qp, flags); rvt_put_qp_swqe(qp, wqe); need_completion = From dc25b239ebeaa3c58e5ceaa732140427d386aa16 Mon Sep 17 00:00:00 2001 From: Kaike Wan Date: Mon, 15 Jul 2019 12:45:34 -0400 Subject: [PATCH 203/823] IB/hfi1: Field not zero-ed when allocating TID flow memory The field flow->resync_npkts is added for TID RDMA WRITE request and zero-ed when a TID RDMA WRITE RESP packet is received by the requester. This field is used to rewind a request during retry in the function hfi1_tid_rdma_restart_req() shared by both TID RDMA WRITE and TID RDMA READ requests. Therefore, when a TID RDMA READ request is retried, this field may not be initialized at all, which causes the retry to start at an incorrect psn, leading to the drop of the retry request by the responder. This patch fixes the problem by zeroing out the field when the flow memory is allocated. Fixes: 838b6fd2d9ca ("IB/hfi1: TID RDMA RcvArray programming and TID allocation") Cc: Link: https://lore.kernel.org/r/20190715164534.74174.6177.stgit@awfm-01.aw.intel.com Reviewed-by: Mike Marciniszyn Signed-off-by: Kaike Wan Signed-off-by: Mike Marciniszyn Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hfi1/tid_rdma.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index 92acccaaaa86..7fcbeee84293 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -1620,6 +1620,7 @@ static int hfi1_kern_exp_rcv_alloc_flows(struct tid_rdma_request *req, flows[i].req = req; flows[i].npagesets = 0; flows[i].pagesets[0].mapped = 0; + flows[i].resync_npkts = 0; } req->flows = flows; return 0; From f4d46119f214f9a7620b0d18b153d7e0e8c90b4f Mon Sep 17 00:00:00 2001 From: Kaike Wan Date: Mon, 15 Jul 2019 12:45:40 -0400 Subject: [PATCH 204/823] IB/hfi1: Drop all TID RDMA READ RESP packets after r_next_psn When a TID sequence error occurs while receiving TID RDMA READ RESP packets, all packets after flow->flow_state.r_next_psn should be dropped, including those response packets for subsequent segments. The current implementation will drop the subsequent response packets for the segment to complete next, but may accept packets for subsequent segments and therefore mistakenly advance the r_next_psn fields for the corresponding software flows. This may result in failures to complete subsequent segments after the current segment is completed. The fix is to only use the flow pointed by req->clear_tail for checking KDETH PSN instead of finding a flow from the request's flow array. Fixes: b885d5be9ca1 ("IB/hfi1: Unify the software PSN check for TID RDMA READ/WRITE") Cc: Link: https://lore.kernel.org/r/20190715164540.74174.54702.stgit@awfm-01.aw.intel.com Reviewed-by: Mike Marciniszyn Signed-off-by: Kaike Wan Signed-off-by: Mike Marciniszyn Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hfi1/tid_rdma.c | 42 +-------------------------- 1 file changed, 1 insertion(+), 41 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index 7fcbeee84293..996fc298207e 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -1674,34 +1674,6 @@ static struct tid_rdma_flow *find_flow_ib(struct tid_rdma_request *req, return NULL; } -static struct tid_rdma_flow * -__find_flow_ranged(struct tid_rdma_request *req, u16 head, u16 tail, - u32 psn, u16 *fidx) -{ - for ( ; CIRC_CNT(head, tail, MAX_FLOWS); - tail = CIRC_NEXT(tail, MAX_FLOWS)) { - struct tid_rdma_flow *flow = &req->flows[tail]; - u32 spsn, lpsn; - - spsn = full_flow_psn(flow, flow->flow_state.spsn); - lpsn = full_flow_psn(flow, flow->flow_state.lpsn); - - if (cmp_psn(psn, spsn) >= 0 && cmp_psn(psn, lpsn) <= 0) { - if (fidx) - *fidx = tail; - return flow; - } - } - return NULL; -} - -static struct tid_rdma_flow *find_flow(struct tid_rdma_request *req, - u32 psn, u16 *fidx) -{ - return __find_flow_ranged(req, req->setup_head, req->clear_tail, psn, - fidx); -} - /* TID RDMA READ functions */ u32 hfi1_build_tid_rdma_read_packet(struct rvt_swqe *wqe, struct ib_other_headers *ohdr, u32 *bth1, @@ -2789,19 +2761,7 @@ static bool handle_read_kdeth_eflags(struct hfi1_ctxtdata *rcd, * to prevent continuous Flow Sequence errors for any * packets that could be still in the fabric. */ - flow = find_flow(req, psn, NULL); - if (!flow) { - /* - * We can't find the IB PSN matching the - * received KDETH PSN. The only thing we can - * do at this point is report the error to - * the QP. - */ - hfi1_kern_read_tid_flow_free(qp); - spin_unlock(&qp->s_lock); - rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR); - return ret; - } + flow = &req->flows[req->clear_tail]; if (priv->s_flags & HFI1_R_TID_SW_PSN) { diff = cmp_psn(psn, flow->flow_state.r_next_psn); From c56b593d2af4cbd189c6af5fd6790728fade80cc Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Mon, 15 Jul 2019 05:19:13 -0400 Subject: [PATCH 205/823] RDMA/bnxt_re: Honor vlan_id in GID entry comparison A GID entry consists of GID, vlan, netdev and smac. Extend GID duplicate check comparisons to consider vlan_id as well to support IPv6 VLAN based link local addresses. Introduce a new structure (bnxt_qplib_gid_info) to hold gid and vlan_id information. The issue is discussed in the following thread https://lore.kernel.org/r/AM0PR05MB4866CFEDCDF3CDA1D7D18AA5D1F20@AM0PR05MB4866.eurprd05.prod.outlook.com Fixes: 823b23da7113 ("IB/core: Allow vlan link local address based RoCE GIDs") Cc: # v5.2+ Link: https://lore.kernel.org/r/20190715091913.15726-1-selvin.xavier@broadcom.com Reported-by: Yi Zhang Co-developed-by: Parav Pandit Signed-off-by: Parav Pandit Signed-off-by: Selvin Xavier Tested-by: Yi Zhang Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/bnxt_re/ib_verbs.c | 7 +++++-- drivers/infiniband/hw/bnxt_re/qplib_res.c | 13 +++++++++---- drivers/infiniband/hw/bnxt_re/qplib_res.h | 2 +- drivers/infiniband/hw/bnxt_re/qplib_sp.c | 14 +++++++++----- drivers/infiniband/hw/bnxt_re/qplib_sp.h | 7 ++++++- 5 files changed, 30 insertions(+), 13 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index a91653aabf38..098ab883733e 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -308,6 +308,7 @@ int bnxt_re_del_gid(const struct ib_gid_attr *attr, void **context) struct bnxt_re_dev *rdev = to_bnxt_re_dev(attr->device, ibdev); struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl; struct bnxt_qplib_gid *gid_to_del; + u16 vlan_id = 0xFFFF; /* Delete the entry from the hardware */ ctx = *context; @@ -317,7 +318,8 @@ int bnxt_re_del_gid(const struct ib_gid_attr *attr, void **context) if (sgid_tbl && sgid_tbl->active) { if (ctx->idx >= sgid_tbl->max) return -EINVAL; - gid_to_del = &sgid_tbl->tbl[ctx->idx]; + gid_to_del = &sgid_tbl->tbl[ctx->idx].gid; + vlan_id = sgid_tbl->tbl[ctx->idx].vlan_id; /* DEL_GID is called in WQ context(netdevice_event_work_handler) * or via the ib_unregister_device path. In the former case QP1 * may not be destroyed yet, in which case just return as FW @@ -335,7 +337,8 @@ int bnxt_re_del_gid(const struct ib_gid_attr *attr, void **context) } ctx->refcnt--; if (!ctx->refcnt) { - rc = bnxt_qplib_del_sgid(sgid_tbl, gid_to_del, true); + rc = bnxt_qplib_del_sgid(sgid_tbl, gid_to_del, + vlan_id, true); if (rc) { dev_err(rdev_to_dev(rdev), "Failed to remove GID: %#x", rc); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index 37928b1111df..bdbde8e22420 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -488,7 +488,7 @@ static int bnxt_qplib_alloc_sgid_tbl(struct bnxt_qplib_res *res, struct bnxt_qplib_sgid_tbl *sgid_tbl, u16 max) { - sgid_tbl->tbl = kcalloc(max, sizeof(struct bnxt_qplib_gid), GFP_KERNEL); + sgid_tbl->tbl = kcalloc(max, sizeof(*sgid_tbl->tbl), GFP_KERNEL); if (!sgid_tbl->tbl) return -ENOMEM; @@ -526,9 +526,10 @@ static void bnxt_qplib_cleanup_sgid_tbl(struct bnxt_qplib_res *res, for (i = 0; i < sgid_tbl->max; i++) { if (memcmp(&sgid_tbl->tbl[i], &bnxt_qplib_gid_zero, sizeof(bnxt_qplib_gid_zero))) - bnxt_qplib_del_sgid(sgid_tbl, &sgid_tbl->tbl[i], true); + bnxt_qplib_del_sgid(sgid_tbl, &sgid_tbl->tbl[i].gid, + sgid_tbl->tbl[i].vlan_id, true); } - memset(sgid_tbl->tbl, 0, sizeof(struct bnxt_qplib_gid) * sgid_tbl->max); + memset(sgid_tbl->tbl, 0, sizeof(*sgid_tbl->tbl) * sgid_tbl->max); memset(sgid_tbl->hw_id, -1, sizeof(u16) * sgid_tbl->max); memset(sgid_tbl->vlan, 0, sizeof(u8) * sgid_tbl->max); sgid_tbl->active = 0; @@ -537,7 +538,11 @@ static void bnxt_qplib_cleanup_sgid_tbl(struct bnxt_qplib_res *res, static void bnxt_qplib_init_sgid_tbl(struct bnxt_qplib_sgid_tbl *sgid_tbl, struct net_device *netdev) { - memset(sgid_tbl->tbl, 0, sizeof(struct bnxt_qplib_gid) * sgid_tbl->max); + u32 i; + + for (i = 0; i < sgid_tbl->max; i++) + sgid_tbl->tbl[i].vlan_id = 0xffff; + memset(sgid_tbl->hw_id, -1, sizeof(u16) * sgid_tbl->max); } diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h index 30c42c92fac7..fbda11a7ab1a 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h @@ -111,7 +111,7 @@ struct bnxt_qplib_pd_tbl { }; struct bnxt_qplib_sgid_tbl { - struct bnxt_qplib_gid *tbl; + struct bnxt_qplib_gid_info *tbl; u16 *hw_id; u16 max; u16 active; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 48793d3512ac..40296b97d21e 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -213,12 +213,12 @@ int bnxt_qplib_get_sgid(struct bnxt_qplib_res *res, index, sgid_tbl->max); return -EINVAL; } - memcpy(gid, &sgid_tbl->tbl[index], sizeof(*gid)); + memcpy(gid, &sgid_tbl->tbl[index].gid, sizeof(*gid)); return 0; } int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, - struct bnxt_qplib_gid *gid, bool update) + struct bnxt_qplib_gid *gid, u16 vlan_id, bool update) { struct bnxt_qplib_res *res = to_bnxt_qplib(sgid_tbl, struct bnxt_qplib_res, @@ -236,7 +236,8 @@ int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, return -ENOMEM; } for (index = 0; index < sgid_tbl->max; index++) { - if (!memcmp(&sgid_tbl->tbl[index], gid, sizeof(*gid))) + if (!memcmp(&sgid_tbl->tbl[index].gid, gid, sizeof(*gid)) && + vlan_id == sgid_tbl->tbl[index].vlan_id) break; } if (index == sgid_tbl->max) { @@ -262,8 +263,9 @@ int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, if (rc) return rc; } - memcpy(&sgid_tbl->tbl[index], &bnxt_qplib_gid_zero, + memcpy(&sgid_tbl->tbl[index].gid, &bnxt_qplib_gid_zero, sizeof(bnxt_qplib_gid_zero)); + sgid_tbl->tbl[index].vlan_id = 0xFFFF; sgid_tbl->vlan[index] = 0; sgid_tbl->active--; dev_dbg(&res->pdev->dev, @@ -296,7 +298,8 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, } free_idx = sgid_tbl->max; for (i = 0; i < sgid_tbl->max; i++) { - if (!memcmp(&sgid_tbl->tbl[i], gid, sizeof(*gid))) { + if (!memcmp(&sgid_tbl->tbl[i], gid, sizeof(*gid)) && + sgid_tbl->tbl[i].vlan_id == vlan_id) { dev_dbg(&res->pdev->dev, "SGID entry already exist in entry %d!\n", i); *index = i; @@ -351,6 +354,7 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, } /* Add GID to the sgid_tbl */ memcpy(&sgid_tbl->tbl[free_idx], gid, sizeof(*gid)); + sgid_tbl->tbl[free_idx].vlan_id = vlan_id; sgid_tbl->active++; if (vlan_id != 0xFFFF) sgid_tbl->vlan[free_idx] = 1; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h index 0ec3b12b0bcd..13d9432d5ce2 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h @@ -84,6 +84,11 @@ struct bnxt_qplib_gid { u8 data[16]; }; +struct bnxt_qplib_gid_info { + struct bnxt_qplib_gid gid; + u16 vlan_id; +}; + struct bnxt_qplib_ah { struct bnxt_qplib_gid dgid; struct bnxt_qplib_pd *pd; @@ -221,7 +226,7 @@ int bnxt_qplib_get_sgid(struct bnxt_qplib_res *res, struct bnxt_qplib_sgid_tbl *sgid_tbl, int index, struct bnxt_qplib_gid *gid); int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, - struct bnxt_qplib_gid *gid, bool update); + struct bnxt_qplib_gid *gid, u16 vlan_id, bool update); int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, struct bnxt_qplib_gid *gid, u8 *mac, u16 vlan_id, bool update, u32 *index); From b7f406bb883ba7ac3222298f6b44cebc4cfe2dde Mon Sep 17 00:00:00 2001 From: Chuhong Yuan Date: Wed, 17 Jul 2019 16:21:01 +0800 Subject: [PATCH 206/823] IB/mlx5: Replace kfree with kvfree Memory allocated by kvzalloc should not be freed by kfree(), use kvfree() instead. Fixes: 813e90b1aeaa ("IB/mlx5: Add advise_mr() support") Link: https://lore.kernel.org/r/20190717082101.14196-1-hslester96@gmail.com Signed-off-by: Chuhong Yuan Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/odp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 5b642d81e617..36ba901cc9a5 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -1771,7 +1771,7 @@ static void mlx5_ib_prefetch_mr_work(struct work_struct *work) num_pending_prefetch_dec(to_mdev(w->pd->device), w->sg_list, w->num_sge, 0); - kfree(w); + kvfree(w); } int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd, @@ -1813,7 +1813,7 @@ int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd, if (valid_req) queue_work(system_unbound_wq, &work->work); else - kfree(work); + kvfree(work); srcu_read_unlock(&dev->mr_srcu, srcu_key); From af0653d56657340a80622aeb96707f7fc8506225 Mon Sep 17 00:00:00 2001 From: Mao Wenan Date: Fri, 19 Jul 2019 09:29:38 +0800 Subject: [PATCH 207/823] RDMA/siw: Remove set but not used variables 'rv' Fixes gcc '-Wunused-but-set-variable' warning: drivers/infiniband/sw/siw/siw_cm.c: In function siw_cep_set_inuse: drivers/infiniband/sw/siw/siw_cm.c:223:6: warning: variable rv set but not used [-Wunused-but-set-variable] Fixes: 6c52fdc244b5 ("rdma/siw: connection management") Link: https://lore.kernel.org/r/20190719012938.100628-1-maowenan@huawei.com Signed-off-by: Mao Wenan Reviewed-by: Bernard Metzler Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/siw/siw_cm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c index a7cde98e73e8..9ce8a1b925d2 100644 --- a/drivers/infiniband/sw/siw/siw_cm.c +++ b/drivers/infiniband/sw/siw/siw_cm.c @@ -220,13 +220,12 @@ static void siw_put_work(struct siw_cm_work *work) static void siw_cep_set_inuse(struct siw_cep *cep) { unsigned long flags; - int rv; retry: spin_lock_irqsave(&cep->lock, flags); if (cep->in_use) { spin_unlock_irqrestore(&cep->lock, flags); - rv = wait_event_interruptible(cep->waitq, !cep->in_use); + wait_event_interruptible(cep->waitq, !cep->in_use); if (signal_pending(current)) flush_signals(current); goto retry; From 0036bc73ccbe7e600a3468bf8e8879b122252274 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Sun, 30 Jun 2019 05:47:22 -0700 Subject: [PATCH 208/823] drm/msm: stop abusing dma_map/unmap for cache Recently splats like this started showing up: WARNING: CPU: 4 PID: 251 at drivers/iommu/dma-iommu.c:451 __iommu_dma_unmap+0xb8/0xc0 Modules linked in: ath10k_snoc ath10k_core fuse msm ath mac80211 uvcvideo cfg80211 videobuf2_vmalloc videobuf2_memops vide CPU: 4 PID: 251 Comm: kworker/u16:4 Tainted: G W 5.2.0-rc5-next-20190619+ #2317 Hardware name: LENOVO 81JL/LNVNB161216, BIOS 9UCN23WW(V1.06) 10/25/2018 Workqueue: msm msm_gem_free_work [msm] pstate: 80c00005 (Nzcv daif +PAN +UAO) pc : __iommu_dma_unmap+0xb8/0xc0 lr : __iommu_dma_unmap+0x54/0xc0 sp : ffff0000119abce0 x29: ffff0000119abce0 x28: 0000000000000000 x27: ffff8001f9946648 x26: ffff8001ec271068 x25: 0000000000000000 x24: ffff8001ea3580a8 x23: ffff8001f95ba010 x22: ffff80018e83ba88 x21: ffff8001e548f000 x20: fffffffffffff000 x19: 0000000000001000 x18: 00000000c00001fe x17: 0000000000000000 x16: 0000000000000000 x15: ffff000015b70068 x14: 0000000000000005 x13: 0003142cc1be1768 x12: 0000000000000001 x11: ffff8001f6de9100 x10: 0000000000000009 x9 : ffff000015b78000 x8 : 0000000000000000 x7 : 0000000000000001 x6 : fffffffffffff000 x5 : 0000000000000fff x4 : ffff00001065dbc8 x3 : 000000000000000d x2 : 0000000000001000 x1 : fffffffffffff000 x0 : 0000000000000000 Call trace: __iommu_dma_unmap+0xb8/0xc0 iommu_dma_unmap_sg+0x98/0xb8 put_pages+0x5c/0xf0 [msm] msm_gem_free_work+0x10c/0x150 [msm] process_one_work+0x1e0/0x330 worker_thread+0x40/0x438 kthread+0x12c/0x130 ret_from_fork+0x10/0x18 ---[ end trace afc0dc5ab81a06bf ]--- Not quite sure what triggered that, but we really shouldn't be abusing dma_{map,unmap}_sg() for cache maint. Cc: Stephen Boyd Tested-by: Stephen Boyd Reviewed-by: Jordan Crouse Signed-off-by: Rob Clark Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20190630124735.27786-1-robdclark@gmail.com --- drivers/gpu/drm/msm/msm_gem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 8b78554cfde3..c2114c748c2f 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -97,7 +97,7 @@ static struct page **get_pages(struct drm_gem_object *obj) * because display controller, GPU, etc. are not coherent: */ if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED)) - dma_map_sg(dev->dev, msm_obj->sgt->sgl, + dma_sync_sg_for_device(dev->dev, msm_obj->sgt->sgl, msm_obj->sgt->nents, DMA_BIDIRECTIONAL); } @@ -127,7 +127,7 @@ static void put_pages(struct drm_gem_object *obj) * GPU, etc. are not coherent: */ if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED)) - dma_unmap_sg(obj->dev->dev, msm_obj->sgt->sgl, + dma_sync_sg_for_cpu(obj->dev->dev, msm_obj->sgt->sgl, msm_obj->sgt->nents, DMA_BIDIRECTIONAL); From 12185dfe44360f814ac4ead9d22ad2af7511b2e9 Mon Sep 17 00:00:00 2001 From: Thomas Falcon Date: Tue, 16 Jul 2019 17:25:10 -0500 Subject: [PATCH 209/823] bonding: Force slave speed check after link state recovery for 802.3ad The following scenario was encountered during testing of logical partition mobility on pseries partitions with bonded ibmvnic adapters in LACP mode. 1. Driver receives a signal that the device has been swapped, and it needs to reset to initialize the new device. 2. Driver reports loss of carrier and begins initialization. 3. Bonding driver receives NETDEV_CHANGE notifier and checks the slave's current speed and duplex settings. Because these are unknown at the time, the bond sets its link state to BOND_LINK_FAIL and handles the speed update, clearing AD_PORT_LACP_ENABLE. 4. Driver finishes recovery and reports that the carrier is on. 5. Bond receives a new notification and checks the speed again. The speeds are valid but miimon has not altered the link state yet. AD_PORT_LACP_ENABLE remains off. Because the slave's link state is still BOND_LINK_FAIL, no further port checks are made when it recovers. Though the slave devices are operational and have valid speed and duplex settings, the bond will not send LACPDU's. The simplest fix I can see is to force another speed check in bond_miimon_commit. This way the bond will update AD_PORT_LACP_ENABLE if needed when transitioning from BOND_LINK_FAIL to BOND_LINK_UP. CC: Jarod Wilson CC: Jay Vosburgh CC: Veaceslav Falico CC: Andy Gospodarek Signed-off-by: Thomas Falcon Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 9b7016abca2f..02fd7822c14a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2196,6 +2196,15 @@ static void bond_miimon_commit(struct bonding *bond) bond_for_each_slave(bond, slave, iter) { switch (slave->new_link) { case BOND_LINK_NOCHANGE: + /* For 802.3ad mode, check current slave speed and + * duplex again in case its port was disabled after + * invalid speed/duplex reporting but recovered before + * link monitoring could make a decision on the actual + * link status + */ + if (BOND_MODE(bond) == BOND_MODE_8023AD && + slave->link == BOND_LINK_UP) + bond_3ad_adapter_speed_duplex_changed(slave); continue; case BOND_LINK_UP: From 5adcce34f8a3880a7b3b1cfd90b094d8a931bbae Mon Sep 17 00:00:00 2001 From: Federico Vaga Date: Thu, 18 Jul 2019 09:47:24 +0200 Subject: [PATCH 210/823] doc:it_IT: align translation to mainline The patch translates the following patches in Italian: d9d7c0c497b8 docs: Note that :c:func: should no longer be used 83e8b971f81c sphinx.rst: Add note about code snippets embedded in the text cca5e0b8a430 Documentation: PGP: update for newer HW devices Signed-off-by: Federico Vaga Signed-off-by: Jonathan Corbet --- .../translations/it_IT/doc-guide/sphinx.rst | 15 ++++++----- .../it_IT/process/maintainer-pgp-guide.rst | 25 ++++++++++++------- 2 files changed, 25 insertions(+), 15 deletions(-) diff --git a/Documentation/translations/it_IT/doc-guide/sphinx.rst b/Documentation/translations/it_IT/doc-guide/sphinx.rst index 1739cba8863e..d9ee4b1f098f 100644 --- a/Documentation/translations/it_IT/doc-guide/sphinx.rst +++ b/Documentation/translations/it_IT/doc-guide/sphinx.rst @@ -243,7 +243,8 @@ del kernel: esempio, casi d'uso, eccetera): utilizzate ``::`` quando non è necessario evidenziare la sintassi, specialmente per piccoli frammenti; invece, utilizzate ``.. code-block:: `` per blocchi di più lunghi che - potranno beneficiare dell'avere la sintassi evidenziata. + potranno beneficiare dell'avere la sintassi evidenziata. Per un breve pezzo + di codice da inserire nel testo, usate \`\`. Il dominio C @@ -267,12 +268,14 @@ molto comune come ``open`` o ``ioctl``: Il nome della funzione (per esempio ioctl) rimane nel testo ma il nome del suo riferimento cambia da ``ioctl`` a ``VIDIOC_LOG_STATUS``. Anche la voce -nell'indice cambia in ``VIDIOC_LOG_STATUS`` e si potrà quindi fare riferimento -a questa funzione scrivendo: +nell'indice cambia in ``VIDIOC_LOG_STATUS``. -.. code-block:: rst - - :c:func:`VIDIOC_LOG_STATUS` +Notate che per una funzione non c'è bisogno di usare ``c:func:`` per generarne +i riferimenti nella documentazione. Grazie a qualche magica estensione a +Sphinx, il sistema di generazione della documentazione trasformerà +automaticamente un riferimento ad una ``funzione()`` in un riferimento +incrociato quando questa ha una voce nell'indice. Se trovate degli usi di +``c:func:`` nella documentazione del kernel, sentitevi liberi di rimuoverli. Tabelle a liste diff --git a/Documentation/translations/it_IT/process/maintainer-pgp-guide.rst b/Documentation/translations/it_IT/process/maintainer-pgp-guide.rst index 276db0e37f43..118fb4153e8f 100644 --- a/Documentation/translations/it_IT/process/maintainer-pgp-guide.rst +++ b/Documentation/translations/it_IT/process/maintainer-pgp-guide.rst @@ -248,7 +248,10 @@ possano ricevere la vostra nuova sottochiave:: kernel. Se per qualche ragione preferite rimanere con sottochiavi RSA, nel comando - precedente, sostituite "ed25519" con "rsa2048". + precedente, sostituite "ed25519" con "rsa2048". In aggiunta, se avete + intenzione di usare un dispositivo hardware che non supporta le chiavi + ED25519 ECC, come la Nitrokey Pro o la Yubikey, allora dovreste usare + "nistp256" al posto di "ed25519". Copia di riserva della chiave primaria per gestire il recupero da disastro -------------------------------------------------------------------------- @@ -449,23 +452,27 @@ implementi le funzionalità delle smartcard. Sul mercato ci sono diverse soluzioni disponibili: - `Nitrokey Start`_: è Open hardware e Free Software, è basata sul progetto - `GnuK`_ della FSIJ. Ha il supporto per chiavi ECC, ma meno funzionalità di - sicurezza (come la resistenza alla manomissione o alcuni attacchi ad un - canale laterale). + `GnuK`_ della FSIJ. Questo è uno dei pochi dispositivi a supportare le chiavi + ECC ED25519, ma offre meno funzionalità di sicurezza (come la resistenza + alla manomissione o alcuni attacchi ad un canale laterale). - `Nitrokey Pro`_: è simile alla Nitrokey Start, ma è più resistente alla - manomissione e offre più funzionalità di sicurezza, ma l'ECC. -- `Yubikey 4`_: l'hardware e il software sono proprietari, ma è più economica + manomissione e offre più funzionalità di sicurezza. La Pro 2 supporta la + crittografia ECC (NISTP). +- `Yubikey 5`_: l'hardware e il software sono proprietari, ma è più economica della Nitrokey Pro ed è venduta anche con porta USB-C il che è utile con i computer portatili più recenti. In aggiunta, offre altre funzionalità di - sicurezza come FIDO, U2F, ma non l'ECC + sicurezza come FIDO, U2F, e ora supporta anche le chiavi ECC (NISTP) `Su LWN c'è una buona recensione`_ dei modelli elencati qui sopra e altri. +La scelta dipenderà dal costo, dalla disponibilità nella vostra area +geografica e vostre considerazioni sull'hardware aperto/proprietario. + Se volete usare chiavi ECC, la vostra migliore scelta sul mercato è la Nitrokey Start. .. _`Nitrokey Start`: https://shop.nitrokey.com/shop/product/nitrokey-start-6 -.. _`Nitrokey Pro`: https://shop.nitrokey.com/shop/product/nitrokey-pro-3 -.. _`Yubikey 4`: https://www.yubico.com/product/yubikey-4-series/ +.. _`Nitrokey Pro 2`: https://shop.nitrokey.com/shop/product/nitrokey-pro-2-3 +.. _`Yubikey 5`: https://www.yubico.com/product/yubikey-5-overview/ .. _Gnuk: http://www.fsij.org/doc-gnuk/ .. _`Su LWN c'è una buona recensione`: https://lwn.net/Articles/736231/ From 143134ba498327e3d389e10f55f56e9c37257c7c Mon Sep 17 00:00:00 2001 From: Federico Vaga Date: Thu, 18 Jul 2019 09:47:54 +0200 Subject: [PATCH 211/823] doc:it_IT: rephrase statement The statement sounds more like a literal translation Signed-off-by: Federico Vaga Signed-off-by: Jonathan Corbet --- Documentation/translations/it_IT/doc-guide/sphinx.rst | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/translations/it_IT/doc-guide/sphinx.rst b/Documentation/translations/it_IT/doc-guide/sphinx.rst index d9ee4b1f098f..f1ad4504b734 100644 --- a/Documentation/translations/it_IT/doc-guide/sphinx.rst +++ b/Documentation/translations/it_IT/doc-guide/sphinx.rst @@ -242,9 +242,9 @@ del kernel: * Per inserire blocchi di testo con caratteri a dimensione fissa (codici di esempio, casi d'uso, eccetera): utilizzate ``::`` quando non è necessario evidenziare la sintassi, specialmente per piccoli frammenti; invece, - utilizzate ``.. code-block:: `` per blocchi di più lunghi che - potranno beneficiare dell'avere la sintassi evidenziata. Per un breve pezzo - di codice da inserire nel testo, usate \`\`. + utilizzate ``.. code-block:: `` per blocchi più lunghi che + beneficeranno della sintassi evidenziata. Per un breve pezzo di codice da + inserire nel testo, usate \`\`. Il dominio C From f4da5d074c8e51fcafd44889bf1caaa6a71ed6d9 Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Thu, 27 Jun 2019 17:27:53 -0700 Subject: [PATCH 212/823] MAINTAINERS: Add Paul as a RISC-V maintainer The RISC-V port has grown significantly over the past year. Paul's been helping out for a while ago. We agreed in person that he'd take over collecting the patches and submitting the PRs, but it looks like I forgot to make it official. Signed-off-by: Palmer Dabbelt Signed-off-by: Paul Walmsley --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 500cdb68ccbc..b6479a5f6a9a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13717,6 +13717,7 @@ F: drivers/mtd/nand/raw/r852.c F: drivers/mtd/nand/raw/r852.h RISC-V ARCHITECTURE +M: Paul Walmsley M: Palmer Dabbelt M: Albert Ou L: linux-riscv@lists.infradead.org From bbb6fc43f131f77fcb7ae8081f6d7c51396a2120 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Mon, 22 Jul 2019 15:14:46 -0400 Subject: [PATCH 213/823] drm: silence variable 'conn' set but not used The "struct drm_connector" iteration cursor from "for_each_new_connector_in_state" is never used in atomic_remove_fb() which generates a compilation warning, drivers/gpu/drm/drm_framebuffer.c: In function 'atomic_remove_fb': drivers/gpu/drm/drm_framebuffer.c:838:24: warning: variable 'conn' set but not used [-Wunused-but-set-variable] Silence it by marking "conn" __maybe_unused. Signed-off-by: Qian Cai Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/1563822886-13570-1-git-send-email-cai@lca.pw --- drivers/gpu/drm/drm_framebuffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c index 0b72468e8131..57564318ceea 100644 --- a/drivers/gpu/drm/drm_framebuffer.c +++ b/drivers/gpu/drm/drm_framebuffer.c @@ -835,7 +835,7 @@ static int atomic_remove_fb(struct drm_framebuffer *fb) struct drm_device *dev = fb->dev; struct drm_atomic_state *state; struct drm_plane *plane; - struct drm_connector *conn; + struct drm_connector *conn __maybe_unused; struct drm_connector_state *conn_state; int i, ret; unsigned plane_mask; From 251a44888183003b0380df184835a2c00bfa39d7 Mon Sep 17 00:00:00 2001 From: Wesley Terpstra Date: Mon, 20 May 2019 10:29:26 -0700 Subject: [PATCH 214/823] riscv: include generic support for MSI irqdomains Some RISC-V systems include PCIe host controllers that support PCIe message-signaled interrupts. For this to work on Linux, we need to enable PCI_MSI_IRQ_DOMAIN and define struct msi_alloc_info. Support for the latter is enabled by including the architecture-generic msi.h include. Signed-off-by: Wesley Terpstra [paul.walmsley@sifive.com: split initial patch into one arch/riscv patch and one drivers/pci patch] Signed-off-by: Paul Walmsley --- arch/riscv/include/asm/Kbuild | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index 1efaeddf1e4b..16970f246860 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -22,6 +22,7 @@ generic-y += kvm_para.h generic-y += local.h generic-y += local64.h generic-y += mm-arch-hooks.h +generic-y += msi.h generic-y += percpu.h generic-y += preempt.h generic-y += sections.h From b840e4d5fec6fe2019de36b10412b69df9c4d39a Mon Sep 17 00:00:00 2001 From: Kevin Wang Date: Fri, 19 Jul 2019 11:39:21 +0800 Subject: [PATCH 215/823] drm/amd/powerplay: custom peak clock freq for navi10 v2: add function smu_default_set_performance_level as default dpm level handler. change function name smu_set_performance_level to smu_asic_set_performance_level v1: 1.NAVI10_PEAK_SCLK_XTX 1830 Mhz 2.NAVI10_PEAK_SCLK_XT 1755 Mhz 3.NAVI10_PEAK_SCLK_XL 1625 Mhz Signed-off-by: Kevin Wang Reviewed-by: Huang Rui Reviewed-by: Kenneth Feng Reviewed-by: Evan Quan Reviewed-by: Jack Gui Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/amdgpu_smu.c | 73 ++++++++++--------- .../gpu/drm/amd/powerplay/inc/amdgpu_smu.h | 4 + drivers/gpu/drm/amd/powerplay/navi10_ppt.c | 55 ++++++++++++++ drivers/gpu/drm/amd/powerplay/navi10_ppt.h | 4 + 4 files changed, 103 insertions(+), 33 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index 768aae2e20da..c097113c3976 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -1374,13 +1374,49 @@ static int smu_enable_umd_pstate(void *handle, return 0; } +static int smu_default_set_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level) +{ + int ret = 0; + uint32_t sclk_mask, mclk_mask, soc_mask; + + switch (level) { + case AMD_DPM_FORCED_LEVEL_HIGH: + ret = smu_force_dpm_limit_value(smu, true); + break; + case AMD_DPM_FORCED_LEVEL_LOW: + ret = smu_force_dpm_limit_value(smu, false); + break; + case AMD_DPM_FORCED_LEVEL_AUTO: + case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD: + ret = smu_unforce_dpm_levels(smu); + break; + case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK: + case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK: + case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK: + ret = smu_get_profiling_clk_mask(smu, level, + &sclk_mask, + &mclk_mask, + &soc_mask); + if (ret) + return ret; + smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask); + smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask); + smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask); + break; + case AMD_DPM_FORCED_LEVEL_MANUAL: + case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT: + default: + break; + } + return ret; +} + int smu_adjust_power_state_dynamic(struct smu_context *smu, enum amd_dpm_forced_level level, bool skip_display_settings) { int ret = 0; int index = 0; - uint32_t sclk_mask, mclk_mask, soc_mask; long workload; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); @@ -1411,39 +1447,10 @@ int smu_adjust_power_state_dynamic(struct smu_context *smu, } if (smu_dpm_ctx->dpm_level != level) { - switch (level) { - case AMD_DPM_FORCED_LEVEL_HIGH: - ret = smu_force_dpm_limit_value(smu, true); - break; - case AMD_DPM_FORCED_LEVEL_LOW: - ret = smu_force_dpm_limit_value(smu, false); - break; - - case AMD_DPM_FORCED_LEVEL_AUTO: - case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD: - ret = smu_unforce_dpm_levels(smu); - break; - - case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK: - case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK: - case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK: - ret = smu_get_profiling_clk_mask(smu, level, - &sclk_mask, - &mclk_mask, - &soc_mask); - if (ret) - return ret; - smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask); - smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask); - smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask); - break; - - case AMD_DPM_FORCED_LEVEL_MANUAL: - case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT: - default: - break; + ret = smu_asic_set_performance_level(smu, level); + if (ret) { + ret = smu_default_set_performance_level(smu, level); } - if (!ret) smu_dpm_ctx->dpm_level = level; } diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h index 1af992fb0bde..564446ff0d1b 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h @@ -621,6 +621,7 @@ struct pptable_funcs { int (*get_thermal_temperature_range)(struct smu_context *smu, struct smu_temperature_range *range); int (*get_uclk_dpm_states)(struct smu_context *smu, uint32_t *clocks_in_khz, uint32_t *num_states); int (*set_default_od_settings)(struct smu_context *smu, bool initialize); + int (*set_performance_level)(struct smu_context *smu, enum amd_dpm_forced_level level); }; struct smu_funcs @@ -918,6 +919,9 @@ struct smu_funcs ((smu)->funcs->baco_get_state? (smu)->funcs->baco_get_state((smu), (state)) : 0) #define smu_baco_reset(smu) \ ((smu)->funcs->baco_reset? (smu)->funcs->baco_reset((smu)) : 0) +#define smu_asic_set_performance_level(smu, level) \ + ((smu)->ppt_funcs->set_performance_level? (smu)->ppt_funcs->set_performance_level((smu), (level)) : -EINVAL); + extern int smu_get_atom_data_table(struct smu_context *smu, uint32_t table, uint16_t *size, uint8_t *frev, uint8_t *crev, diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 8293b5216aad..7b1753f9a5bf 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -1565,6 +1565,60 @@ static int navi10_set_ppfeature_status(struct smu_context *smu, return 0; } +static int navi10_set_peak_clock_by_device(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + int ret = 0; + uint32_t sclk_freq = 0, uclk_freq = 0; + uint32_t uclk_level = 0; + + switch (adev->rev_id) { + case 0xf0: /* XTX */ + case 0xc0: + sclk_freq = NAVI10_PEAK_SCLK_XTX; + break; + case 0xf1: /* XT */ + case 0xc1: + sclk_freq = NAVI10_PEAK_SCLK_XT; + break; + default: /* XL */ + sclk_freq = NAVI10_PEAK_SCLK_XL; + break; + } + + ret = smu_get_dpm_level_count(smu, SMU_UCLK, &uclk_level); + if (ret) + return ret; + ret = smu_get_dpm_freq_by_index(smu, SMU_UCLK, uclk_level - 1, &uclk_freq); + if (ret) + return ret; + + ret = smu_set_soft_freq_range(smu, SMU_SCLK, sclk_freq, sclk_freq); + if (ret) + return ret; + ret = smu_set_soft_freq_range(smu, SMU_UCLK, uclk_freq, uclk_freq); + if (ret) + return ret; + + return ret; +} + +static int navi10_set_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level) +{ + int ret = 0; + + switch (level) { + case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK: + ret = navi10_set_peak_clock_by_device(smu); + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + static const struct pptable_funcs navi10_ppt_funcs = { .tables_init = navi10_tables_init, .alloc_dpm_context = navi10_allocate_dpm_context, @@ -1600,6 +1654,7 @@ static const struct pptable_funcs navi10_ppt_funcs = { .get_uclk_dpm_states = navi10_get_uclk_dpm_states, .get_ppfeature_status = navi10_get_ppfeature_status, .set_ppfeature_status = navi10_set_ppfeature_status, + .set_performance_level = navi10_set_performance_level, }; void navi10_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.h b/drivers/gpu/drm/amd/powerplay/navi10_ppt.h index 957288e22f47..620ff17c2fef 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.h +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.h @@ -23,6 +23,10 @@ #ifndef __NAVI10_PPT_H__ #define __NAVI10_PPT_H__ +#define NAVI10_PEAK_SCLK_XTX (1830) +#define NAVI10_PEAK_SCLK_XT (1755) +#define NAVI10_PEAK_SCLK_XL (1625) + extern void navi10_set_ppt_funcs(struct smu_context *smu); #endif From 1bcff32679f60fe2387f63f22b8b35375052bcb0 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 18 Jul 2019 15:25:04 -0500 Subject: [PATCH 216/823] drm/amdgpu/smu: move fan rpm query into the asic specific code On vega20, there is an SMU message to query it. On navi, it's fetched from the metrics table. Reviewed-by: Evan Quan Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 4 ++-- .../gpu/drm/amd/powerplay/inc/amdgpu_smu.h | 6 +++--- drivers/gpu/drm/amd/powerplay/navi10_ppt.c | 12 ++++++----- drivers/gpu/drm/amd/powerplay/smu_v11_0.c | 18 ----------------- drivers/gpu/drm/amd/powerplay/vega20_ppt.c | 20 ++++++++++++++++++- 5 files changed, 31 insertions(+), 29 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 8b7efd0a7028..03ca8c69114f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -1734,7 +1734,7 @@ static ssize_t amdgpu_hwmon_get_fan1_input(struct device *dev, return -EINVAL; if (is_support_sw_smu(adev)) { - err = smu_get_current_rpm(&adev->smu, &speed); + err = smu_get_fan_speed_rpm(&adev->smu, &speed); if (err) return err; } else if (adev->powerplay.pp_funcs->get_fan_speed_rpm) { @@ -1794,7 +1794,7 @@ static ssize_t amdgpu_hwmon_get_fan1_target(struct device *dev, return -EINVAL; if (is_support_sw_smu(adev)) { - err = smu_get_current_rpm(&adev->smu, &rpm); + err = smu_get_fan_speed_rpm(&adev->smu, &rpm); if (err) return err; } else if (adev->powerplay.pp_funcs->get_fan_speed_rpm) { diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h index 564446ff0d1b..22e46a289a16 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h @@ -613,6 +613,7 @@ struct pptable_funcs { int (*tables_init)(struct smu_context *smu, struct smu_table *tables); int (*set_thermal_fan_table)(struct smu_context *smu); int (*get_fan_speed_percent)(struct smu_context *smu, uint32_t *speed); + int (*get_fan_speed_rpm)(struct smu_context *smu, uint32_t *speed); int (*set_watermarks_table)(struct smu_context *smu, void *watermarks, struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges); int (*get_current_clk_freq_by_table)(struct smu_context *smu, @@ -686,7 +687,6 @@ struct smu_funcs int (*set_watermarks_for_clock_ranges)(struct smu_context *smu, struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges); int (*conv_power_profile_to_pplib_workload)(int power_profile); - int (*get_current_rpm)(struct smu_context *smu, uint32_t *speed); uint32_t (*get_fan_control_mode)(struct smu_context *smu); int (*set_fan_control_mode)(struct smu_context *smu, uint32_t mode); int (*set_fan_speed_percent)(struct smu_context *smu, uint32_t speed); @@ -752,8 +752,6 @@ struct smu_funcs ((smu)->funcs->init_max_sustainable_clocks ? (smu)->funcs->init_max_sustainable_clocks((smu)) : 0) #define smu_set_default_od_settings(smu, initialize) \ ((smu)->ppt_funcs->set_default_od_settings ? (smu)->ppt_funcs->set_default_od_settings((smu), (initialize)) : 0) -#define smu_get_current_rpm(smu, speed) \ - ((smu)->funcs->get_current_rpm ? (smu)->funcs->get_current_rpm((smu), (speed)) : 0) #define smu_set_fan_speed_rpm(smu, speed) \ ((smu)->funcs->set_fan_speed_rpm ? (smu)->funcs->set_fan_speed_rpm((smu), (speed)) : 0) #define smu_send_smc_msg(smu, msg) \ @@ -842,6 +840,8 @@ struct smu_funcs ((smu)->ppt_funcs->get_fan_speed_percent ? (smu)->ppt_funcs->get_fan_speed_percent((smu), (speed)) : 0) #define smu_set_fan_speed_percent(smu, speed) \ ((smu)->funcs->set_fan_speed_percent ? (smu)->funcs->set_fan_speed_percent((smu), (speed)) : 0) +#define smu_get_fan_speed_rpm(smu, speed) \ + ((smu)->ppt_funcs->get_fan_speed_rpm ? (smu)->ppt_funcs->get_fan_speed_rpm((smu), (speed)) : 0) #define smu_msg_get_index(smu, msg) \ ((smu)->ppt_funcs? ((smu)->ppt_funcs->get_smu_msg_index? (smu)->ppt_funcs->get_smu_msg_index((smu), (msg)) : -EINVAL) : -EINVAL) diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 7b1753f9a5bf..4aaad255a288 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -954,12 +954,13 @@ static bool navi10_is_dpm_running(struct smu_context *smu) return !!(feature_enabled & SMC_DPM_FEATURE); } -static int navi10_get_fan_speed(struct smu_context *smu, uint16_t *value) +static int navi10_get_fan_speed_rpm(struct smu_context *smu, + uint32_t *speed) { SmuMetrics_t metrics; int ret = 0; - if (!value) + if (!speed) return -EINVAL; memset(&metrics, 0, sizeof(metrics)); @@ -969,7 +970,7 @@ static int navi10_get_fan_speed(struct smu_context *smu, uint16_t *value) if (ret) return ret; - *value = metrics.CurrFanSpeed; + *speed = metrics.CurrFanSpeed; return ret; } @@ -979,10 +980,10 @@ static int navi10_get_fan_speed_percent(struct smu_context *smu, { int ret = 0; uint32_t percent = 0; - uint16_t current_rpm; + uint32_t current_rpm; PPTable_t *pptable = smu->smu_table.driver_pptable; - ret = navi10_get_fan_speed(smu, ¤t_rpm); + ret = navi10_get_fan_speed_rpm(smu, ¤t_rpm); if (ret) return ret; @@ -1646,6 +1647,7 @@ static const struct pptable_funcs navi10_ppt_funcs = { .unforce_dpm_levels = navi10_unforce_dpm_levels, .is_dpm_running = navi10_is_dpm_running, .get_fan_speed_percent = navi10_get_fan_speed_percent, + .get_fan_speed_rpm = navi10_get_fan_speed_rpm, .get_power_profile_mode = navi10_get_power_profile_mode, .set_power_profile_mode = navi10_set_power_profile_mode, .get_profiling_clk_mask = navi10_get_profiling_clk_mask, diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c index 95c7c4dae523..caca9091bfcc 100644 --- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c +++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c @@ -1371,23 +1371,6 @@ static int smu_v11_0_gfx_off_control(struct smu_context *smu, bool enable) return ret; } -static int smu_v11_0_get_current_rpm(struct smu_context *smu, - uint32_t *current_rpm) -{ - int ret; - - ret = smu_send_smc_msg(smu, SMU_MSG_GetCurrentRpm); - - if (ret) { - pr_err("Attempt to get current RPM from SMC Failed!\n"); - return ret; - } - - smu_read_smc_arg(smu, current_rpm); - - return 0; -} - static uint32_t smu_v11_0_get_fan_control_mode(struct smu_context *smu) { @@ -1773,7 +1756,6 @@ static const struct smu_funcs smu_v11_0_funcs = { .set_deep_sleep_dcefclk = smu_v11_0_set_deep_sleep_dcefclk, .display_clock_voltage_request = smu_v11_0_display_clock_voltage_request, .set_watermarks_for_clock_ranges = smu_v11_0_set_watermarks_for_clock_ranges, - .get_current_rpm = smu_v11_0_get_current_rpm, .get_fan_control_mode = smu_v11_0_get_fan_control_mode, .set_fan_control_mode = smu_v11_0_set_fan_control_mode, .set_fan_speed_percent = smu_v11_0_set_fan_speed_percent, diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c index bb9bb09cfc7a..dc139a6feeb1 100644 --- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c @@ -3015,6 +3015,23 @@ static int vega20_set_thermal_fan_table(struct smu_context *smu) return ret; } +static int vega20_get_fan_speed_rpm(struct smu_context *smu, + uint32_t *speed) +{ + int ret; + + ret = smu_send_smc_msg(smu, SMU_MSG_GetCurrentRpm); + + if (ret) { + pr_err("Attempt to get current RPM from SMC Failed!\n"); + return ret; + } + + smu_read_smc_arg(smu, speed); + + return 0; +} + static int vega20_get_fan_speed_percent(struct smu_context *smu, uint32_t *speed) { @@ -3022,7 +3039,7 @@ static int vega20_get_fan_speed_percent(struct smu_context *smu, uint32_t current_rpm = 0, percent = 0; PPTable_t *pptable = smu->smu_table.driver_pptable; - ret = smu_get_current_rpm(smu, ¤t_rpm); + ret = vega20_get_fan_speed_rpm(smu, ¤t_rpm); if (ret) return ret; @@ -3293,6 +3310,7 @@ static const struct pptable_funcs vega20_ppt_funcs = { .is_dpm_running = vega20_is_dpm_running, .set_thermal_fan_table = vega20_set_thermal_fan_table, .get_fan_speed_percent = vega20_get_fan_speed_percent, + .get_fan_speed_rpm = vega20_get_fan_speed_rpm, .set_watermarks_table = vega20_set_watermarks_table, .get_thermal_temperature_range = vega20_get_thermal_temperature_range }; From 74af0d0be1d76d407ebda3b357108111bd62ff3e Mon Sep 17 00:00:00 2001 From: Jeremy Cline Date: Tue, 16 Jul 2019 10:49:08 -0400 Subject: [PATCH 217/823] docs/vm: transhuge: fix typo in madvise reference Fix an off-by-one typo in the transparent huge pages admin documentation. Signed-off-by: Jeremy Cline Acked-by: Mike Rapoport Signed-off-by: Jonathan Corbet --- Documentation/admin-guide/mm/transhuge.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index 7ab93a8404b9..bd5714547cee 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -53,7 +53,7 @@ disabled, there is ``khugepaged`` daemon that scans memory and collapses sequences of basic pages into huge pages. The THP behaviour is controlled via :ref:`sysfs ` -interface and using madivse(2) and prctl(2) system calls. +interface and using madvise(2) and prctl(2) system calls. Transparent Hugepage Support maximizes the usefulness of free memory if compared to the reservation approach of hugetlbfs by allowing all From 2b607f7088f915e561225311ff6f9f3dc23411c5 Mon Sep 17 00:00:00 2001 From: Federico Vaga Date: Fri, 12 Jul 2019 11:48:22 +0200 Subject: [PATCH 218/823] doc:it_IT: translations in process/ This patch add translations for: - programming-languages - kernel-docs (It is better to not translate this since English is a requirement to get something useful out of it) Signed-off-by: Federico Vaga Signed-off-by: Jonathan Corbet --- .../translations/it_IT/process/index.rst | 1 + .../it_IT/process/kernel-docs.rst | 11 ++-- .../it_IT/process/programming-language.rst | 51 +++++++++++++++++++ 3 files changed, 60 insertions(+), 3 deletions(-) create mode 100644 Documentation/translations/it_IT/process/programming-language.rst diff --git a/Documentation/translations/it_IT/process/index.rst b/Documentation/translations/it_IT/process/index.rst index 2eda85d5cd1e..012de0f3154a 100644 --- a/Documentation/translations/it_IT/process/index.rst +++ b/Documentation/translations/it_IT/process/index.rst @@ -27,6 +27,7 @@ Di seguito le guide che ogni sviluppatore dovrebbe leggere. code-of-conduct development-process submitting-patches + programming-language coding-style maintainer-pgp-guide email-clients diff --git a/Documentation/translations/it_IT/process/kernel-docs.rst b/Documentation/translations/it_IT/process/kernel-docs.rst index 7bd70d661737..38e0a955121a 100644 --- a/Documentation/translations/it_IT/process/kernel-docs.rst +++ b/Documentation/translations/it_IT/process/kernel-docs.rst @@ -1,6 +1,7 @@ .. include:: ../disclaimer-ita.rst :Original: :ref:`Documentation/process/kernel-docs.rst ` +:Translator: Federico Vaga .. _it_kernel_docs: @@ -8,6 +9,10 @@ Indice di documenti per le persone interessate a capire e/o scrivere per il kernel Linux ======================================================================================== -.. warning:: - - TODO ancora da tradurre +.. note:: + Questo documento contiene riferimenti a documenti in lingua inglese; inoltre + utilizza dai campi *ReStructuredText* di supporto alla ricerca e che per + questo motivo è meglio non tradurre al fine di garantirne un corretto + utilizzo. + Per questi motivi il documento non verrà tradotto. Per favore fate + riferimento al documento originale in lingua inglese. diff --git a/Documentation/translations/it_IT/process/programming-language.rst b/Documentation/translations/it_IT/process/programming-language.rst new file mode 100644 index 000000000000..f4b006395849 --- /dev/null +++ b/Documentation/translations/it_IT/process/programming-language.rst @@ -0,0 +1,51 @@ +.. include:: ../disclaimer-ita.rst + +:Original: :ref:`Documentation/process/programming-language.rst ` +:Translator: Federico Vaga + +.. _it_programming_language: + +Linguaggio di programmazione +============================ + +Il kernel è scritto nel linguaggio di programmazione C [c-language]_. +Più precisamente, il kernel viene compilato con ``gcc`` [gcc]_ usando +l'opzione ``-std=gnu89`` [gcc-c-dialect-options]_: il dialetto GNU +dello standard ISO C90 (con l'aggiunta di alcune funzionalità da C99) + +Questo dialetto contiene diverse estensioni al linguaggio [gnu-extensions]_, +e molte di queste vengono usate sistematicamente dal kernel. + +Il kernel offre un certo livello di supporto per la compilazione con ``clang`` +[clang]_ e ``icc`` [icc]_ su diverse architetture, tuttavia in questo momento +il supporto non è completo e richiede delle patch aggiuntive. + +Attributi +--------- + +Una delle estensioni più comuni e usate nel kernel sono gli attributi +[gcc-attribute-syntax]_. Gli attributi permettono di aggiungere una semantica, +definita dell'implementazione, alle entità del linguaggio (come le variabili, +le funzioni o i tipi) senza dover fare importanti modifiche sintattiche al +linguaggio stesso (come l'aggiunta di nuove parole chiave) [n2049]_. + +In alcuni casi, gli attributi sono opzionali (ovvero un compilatore che non +dovesse supportarli dovrebbe produrre comunque codice corretto, anche se +più lento o che non esegue controlli aggiuntivi durante la compilazione). + +Il kernel definisce alcune pseudo parole chiave (per esempio ``__pure``) +in alternativa alla sintassi GNU per gli attributi (per esempio +``__attribute__((__pure__))``) allo scopo di mostrare quali funzionalità si +possono usare e/o per accorciare il codice. + +Per maggiori informazioni consultate il file d'intestazione +``include/linux/compiler_attributes.h``. + +.. [c-language] http://www.open-std.org/jtc1/sc22/wg14/www/standards +.. [gcc] https://gcc.gnu.org +.. [clang] https://clang.llvm.org +.. [icc] https://software.intel.com/en-us/c-compilers +.. [gcc-c-dialect-options] https://gcc.gnu.org/onlinedocs/gcc/C-Dialect-Options.html +.. [gnu-extensions] https://gcc.gnu.org/onlinedocs/gcc/C-Extensions.html +.. [gcc-attribute-syntax] https://gcc.gnu.org/onlinedocs/gcc/Attribute-Syntax.html +.. [n2049] http://www.open-std.org/jtc1/sc22/wg14/www/docs/n2049.pdf From 985eaf99eb180a9a194ef2787cc03682c7ad615b Mon Sep 17 00:00:00 2001 From: Varun Prakash Date: Mon, 17 Jun 2019 18:47:45 +0530 Subject: [PATCH 219/823] scsi: target: cxgbit: add support for IEEE_8021QAZ_APP_SEL_STREAM selector IEEE_8021QAZ_APP_SEL_STREAM is a valid selector for iSCSI connections, so add code to use IEEE_8021QAZ_APP_SEL_STREAM selector to get priority mask. Signed-off-by: Varun Prakash Signed-off-by: Martin K. Petersen --- drivers/target/iscsi/cxgbit/cxgbit_cm.c | 8 +++++--- drivers/target/iscsi/cxgbit/cxgbit_main.c | 3 ++- 2 files changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c index 22dd4c457d6a..c70caf4ea490 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c @@ -875,10 +875,12 @@ static u8 cxgbit_get_iscsi_dcb_priority(struct net_device *ndev, u16 local_port) return 0; if (caps & DCB_CAP_DCBX_VER_IEEE) { - iscsi_dcb_app.selector = IEEE_8021QAZ_APP_SEL_ANY; - + iscsi_dcb_app.selector = IEEE_8021QAZ_APP_SEL_STREAM; ret = dcb_ieee_getapp_mask(ndev, &iscsi_dcb_app); - + if (!ret) { + iscsi_dcb_app.selector = IEEE_8021QAZ_APP_SEL_ANY; + ret = dcb_ieee_getapp_mask(ndev, &iscsi_dcb_app); + } } else if (caps & DCB_CAP_DCBX_VER_CEE) { iscsi_dcb_app.selector = DCB_APP_IDTYPE_PORTNUM; diff --git a/drivers/target/iscsi/cxgbit/cxgbit_main.c b/drivers/target/iscsi/cxgbit/cxgbit_main.c index 343b129c2cfa..e877b917c15f 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_main.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_main.c @@ -589,7 +589,8 @@ static void cxgbit_dcb_workfn(struct work_struct *work) iscsi_app = &dcb_work->dcb_app; if (iscsi_app->dcbx & DCB_CAP_DCBX_VER_IEEE) { - if (iscsi_app->app.selector != IEEE_8021QAZ_APP_SEL_ANY) + if ((iscsi_app->app.selector != IEEE_8021QAZ_APP_SEL_STREAM) && + (iscsi_app->app.selector != IEEE_8021QAZ_APP_SEL_ANY)) goto out; priority = iscsi_app->app.priority; From 1573eebeaa8055777eb753f9b4d1cbe653380c38 Mon Sep 17 00:00:00 2001 From: Codrin Ciubotariu Date: Tue, 25 Jun 2019 12:10:02 +0300 Subject: [PATCH 220/823] clk: at91: generated: Truncate divisor to GENERATED_MAX_DIV + 1 In clk_generated_determine_rate(), if the divisor is greater than GENERATED_MAX_DIV + 1, then the wrong best_rate will be returned. If clk_generated_set_rate() will be called later with this wrong rate, it will return -EINVAL, so the generated clock won't change its value. Do no let the divisor be greater than GENERATED_MAX_DIV + 1. Fixes: 8c7aa6328947 ("clk: at91: clk-generated: remove useless divisor loop") Signed-off-by: Codrin Ciubotariu Acked-by: Nicolas Ferre Acked-by: Ludovic Desroches Signed-off-by: Stephen Boyd --- drivers/clk/at91/clk-generated.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/clk/at91/clk-generated.c b/drivers/clk/at91/clk-generated.c index 44db83a6d01c..44a46dcc0518 100644 --- a/drivers/clk/at91/clk-generated.c +++ b/drivers/clk/at91/clk-generated.c @@ -141,6 +141,8 @@ static int clk_generated_determine_rate(struct clk_hw *hw, continue; div = DIV_ROUND_CLOSEST(parent_rate, req->rate); + if (div > GENERATED_MAX_DIV + 1) + div = GENERATED_MAX_DIV + 1; clk_generated_best_diff(req, parent, parent_rate, div, &best_diff, &best_rate); From 6ee82ef04e38b0d8b09b04bc1b068673deed6582 Mon Sep 17 00:00:00 2001 From: Sylwester Nawrocki Date: Mon, 1 Jul 2019 13:46:51 +0200 Subject: [PATCH 221/823] clk: Add missing documentation of devm_clk_bulk_get_optional() argument Fix an incomplete devm_clk_bulk_get_optional() function documentation by adding description of the num_clks argument as in other *clk_bulk* functions. Fixes: 9bd5ef0bd874 ("clk: Add devm_clk_bulk_get_optional() function") Reported-by: kbuild test robot Signed-off-by: Sylwester Nawrocki Signed-off-by: Stephen Boyd --- include/linux/clk.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/clk.h b/include/linux/clk.h index 3c096c7a51dc..853a8f181394 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -359,6 +359,7 @@ int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, /** * devm_clk_bulk_get_optional - managed get multiple optional consumer clocks * @dev: device for clock "consumer" + * @num_clks: the number of clk_bulk_data * @clks: pointer to the clk_bulk_data table of consumer * * Behaves the same as devm_clk_bulk_get() except where there is no clock From c93d059a80450af99dd6c0e8c36790579343675a Mon Sep 17 00:00:00 2001 From: Weiyi Lu Date: Fri, 28 Jun 2019 15:22:34 +0800 Subject: [PATCH 222/823] clk: mediatek: mt8183: Register 13MHz clock earlier for clocksource The 13MHz clock should be registered before clocksource driver is initialized. Use CLK_OF_DECLARE_DRIVER() to guarantee. Fixes: acddfc2c261b ("clk: mediatek: Add MT8183 clock support") Cc: Signed-off-by: Weiyi Lu Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8183.c | 46 +++++++++++++++++++++++-------- 1 file changed, 34 insertions(+), 12 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8183.c b/drivers/clk/mediatek/clk-mt8183.c index 1aa5f4059251..73b7e238eee7 100644 --- a/drivers/clk/mediatek/clk-mt8183.c +++ b/drivers/clk/mediatek/clk-mt8183.c @@ -25,9 +25,11 @@ static const struct mtk_fixed_clk top_fixed_clks[] = { FIXED_CLK(CLK_TOP_UNIVP_192M, "univpll_192m", "univpll", 192000000), }; +static const struct mtk_fixed_factor top_early_divs[] = { + FACTOR(CLK_TOP_CLK13M, "clk13m", "clk26m", 1, 2), +}; + static const struct mtk_fixed_factor top_divs[] = { - FACTOR(CLK_TOP_CLK13M, "clk13m", "clk26m", 1, - 2), FACTOR(CLK_TOP_F26M_CK_D2, "csw_f26m_ck_d2", "clk26m", 1, 2), FACTOR(CLK_TOP_SYSPLL_CK, "syspll_ck", "mainpll", 1, @@ -1148,37 +1150,57 @@ static int clk_mt8183_apmixed_probe(struct platform_device *pdev) return of_clk_add_provider(node, of_clk_src_onecell_get, clk_data); } +static struct clk_onecell_data *top_clk_data; + +static void clk_mt8183_top_init_early(struct device_node *node) +{ + int i; + + top_clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); + + for (i = 0; i < CLK_TOP_NR_CLK; i++) + top_clk_data->clks[i] = ERR_PTR(-EPROBE_DEFER); + + mtk_clk_register_factors(top_early_divs, ARRAY_SIZE(top_early_divs), + top_clk_data); + + of_clk_add_provider(node, of_clk_src_onecell_get, top_clk_data); +} + +CLK_OF_DECLARE_DRIVER(mt8183_topckgen, "mediatek,mt8183-topckgen", + clk_mt8183_top_init_early); + static int clk_mt8183_top_probe(struct platform_device *pdev) { struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); void __iomem *base; - struct clk_onecell_data *clk_data; struct device_node *node = pdev->dev.of_node; base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(base)) return PTR_ERR(base); - clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); - mtk_clk_register_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks), - clk_data); + top_clk_data); - mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); + mtk_clk_register_factors(top_early_divs, ARRAY_SIZE(top_early_divs), + top_clk_data); + + mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), top_clk_data); mtk_clk_register_muxes(top_muxes, ARRAY_SIZE(top_muxes), - node, &mt8183_clk_lock, clk_data); + node, &mt8183_clk_lock, top_clk_data); mtk_clk_register_composites(top_aud_muxes, ARRAY_SIZE(top_aud_muxes), - base, &mt8183_clk_lock, clk_data); + base, &mt8183_clk_lock, top_clk_data); mtk_clk_register_composites(top_aud_divs, ARRAY_SIZE(top_aud_divs), - base, &mt8183_clk_lock, clk_data); + base, &mt8183_clk_lock, top_clk_data); mtk_clk_register_gates(node, top_clks, ARRAY_SIZE(top_clks), - clk_data); + top_clk_data); - return of_clk_add_provider(node, of_clk_src_onecell_get, clk_data); + return of_clk_add_provider(node, of_clk_src_onecell_get, top_clk_data); } static int clk_mt8183_infra_probe(struct platform_device *pdev) From 26091eef3c179f940d2967e9bef6e22c9e1c445f Mon Sep 17 00:00:00 2001 From: Yash Shah Date: Fri, 19 Jul 2019 16:40:31 +0530 Subject: [PATCH 223/823] riscv: dts: Add DT node for SiFive FU540 Ethernet controller driver DT node for SiFive FU540-C000 GEMGXL Ethernet controller driver added Signed-off-by: Yash Shah Reviewed-by: Sagar Kadam Cc: Andrew Lunn [paul.walmsley@sifive.com: changed "phy1" to "phy0" at Andrew Lunn's suggestion] Signed-off-by: Paul Walmsley --- arch/riscv/boot/dts/sifive/fu540-c000.dtsi | 15 +++++++++++++++ .../boot/dts/sifive/hifive-unleashed-a00.dts | 9 +++++++++ 2 files changed, 24 insertions(+) diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi index 40983491b95f..9bf63f0ab253 100644 --- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi @@ -217,5 +217,20 @@ #size-cells = <0>; status = "disabled"; }; + eth0: ethernet@10090000 { + compatible = "sifive,fu540-c000-gem"; + interrupt-parent = <&plic0>; + interrupts = <53>; + reg = <0x0 0x10090000 0x0 0x2000 + 0x0 0x100a0000 0x0 0x1000>; + local-mac-address = [00 00 00 00 00 00]; + clock-names = "pclk", "hclk"; + clocks = <&prci PRCI_CLK_GEMGXLPLL>, + <&prci PRCI_CLK_GEMGXLPLL>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + }; }; diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 0b55c53c08c7..93d68cbd64fe 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -76,3 +76,12 @@ disable-wp; }; }; + +ð0 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy0>; + phy0: ethernet-phy@0 { + reg = <0>; + }; +}; From c9a67cbb5189e966c70451562b2ca4c3876ab546 Mon Sep 17 00:00:00 2001 From: Chunyan Zhang Date: Thu, 18 Jul 2019 13:36:16 +0800 Subject: [PATCH 224/823] clk: sprd: Select REGMAP_MMIO to avoid compile errors Make REGMAP_MMIO selected to avoid undefined reference to regmap symbols. Fixes: d41f59fd92f2 ("clk: sprd: Add common infrastructure") Signed-off-by: Chunyan Zhang Signed-off-by: Stephen Boyd --- drivers/clk/sprd/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/sprd/Kconfig b/drivers/clk/sprd/Kconfig index 91d3d721c801..3c219af25100 100644 --- a/drivers/clk/sprd/Kconfig +++ b/drivers/clk/sprd/Kconfig @@ -3,6 +3,7 @@ config SPRD_COMMON_CLK tristate "Clock support for Spreadtrum SoCs" depends on ARCH_SPRD || COMPILE_TEST default ARCH_SPRD + select REGMAP_MMIO if SPRD_COMMON_CLK From e1f1ae8002e4b06addc52443fcd975bbf554ae92 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 11 Jul 2019 15:03:59 +0200 Subject: [PATCH 225/823] clk: renesas: cpg-mssr: Fix reset control race condition The module reset code in the Renesas CPG/MSSR driver uses read-modify-write (RMW) operations to write to a Software Reset Register (SRCRn), and simple writes to write to a Software Reset Clearing Register (SRSTCLRn), as was mandated by the R-Car Gen2 and Gen3 Hardware User's Manuals. However, this may cause a race condition when two devices are reset in parallel: if the reset for device A completes in the middle of the RMW operation for device B, device A may be reset again, causing subtle failures (e.g. i2c timeouts): thread A thread B -------- -------- val = SRCRn val |= bit A SRCRn = val delay val = SRCRn (bit A is set) SRSTCLRn = bit A (bit A in SRCRn is cleared) val |= bit B SRCRn = val (bit A and B are set) This can be reproduced on e.g. Salvator-XS using: $ while true; do i2cdump -f -y 4 0x6A b > /dev/null; done & $ while true; do i2cdump -f -y 2 0x10 b > /dev/null; done & i2c-rcar e6510000.i2c: error -110 : 40000002 i2c-rcar e66d8000.i2c: error -110 : 40000002 According to the R-Car Gen3 Hardware Manual Errata for Rev. 0.80 of Feb 28, 2018, reflected in Rev. 1.00 of the R-Car Gen3 Hardware User's Manual, writes to SRCRn do not require read-modify-write cycles. Note that the R-Car Gen2 Hardware User's Manual has not been updated yet, and still says a read-modify-write sequence is required. According to the hardware team, the reset hardware block is the same on both R-Car Gen2 and Gen3, though. Hence fix the issue by replacing the read-modify-write operations on SRCRn by simple writes. Reported-by: Yao Lihua Fixes: 6197aa65c4905532 ("clk: renesas: cpg-mssr: Add support for reset control") Signed-off-by: Geert Uytterhoeven Tested-by: Linh Phung Signed-off-by: Stephen Boyd --- drivers/clk/renesas/renesas-cpg-mssr.c | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) diff --git a/drivers/clk/renesas/renesas-cpg-mssr.c b/drivers/clk/renesas/renesas-cpg-mssr.c index 52bbb9ce3807..d4075b130674 100644 --- a/drivers/clk/renesas/renesas-cpg-mssr.c +++ b/drivers/clk/renesas/renesas-cpg-mssr.c @@ -572,17 +572,11 @@ static int cpg_mssr_reset(struct reset_controller_dev *rcdev, unsigned int reg = id / 32; unsigned int bit = id % 32; u32 bitmask = BIT(bit); - unsigned long flags; - u32 value; dev_dbg(priv->dev, "reset %u%02u\n", reg, bit); /* Reset module */ - spin_lock_irqsave(&priv->rmw_lock, flags); - value = readl(priv->base + SRCR(reg)); - value |= bitmask; - writel(value, priv->base + SRCR(reg)); - spin_unlock_irqrestore(&priv->rmw_lock, flags); + writel(bitmask, priv->base + SRCR(reg)); /* Wait for at least one cycle of the RCLK clock (@ ca. 32 kHz) */ udelay(35); @@ -599,16 +593,10 @@ static int cpg_mssr_assert(struct reset_controller_dev *rcdev, unsigned long id) unsigned int reg = id / 32; unsigned int bit = id % 32; u32 bitmask = BIT(bit); - unsigned long flags; - u32 value; dev_dbg(priv->dev, "assert %u%02u\n", reg, bit); - spin_lock_irqsave(&priv->rmw_lock, flags); - value = readl(priv->base + SRCR(reg)); - value |= bitmask; - writel(value, priv->base + SRCR(reg)); - spin_unlock_irqrestore(&priv->rmw_lock, flags); + writel(bitmask, priv->base + SRCR(reg)); return 0; } From bba18318e7d1d5c8b0bbafd65010a0cee3c65608 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Fri, 19 Jul 2019 16:38:48 +0200 Subject: [PATCH 226/823] net: mvpp2: Don't check for 3 consecutive Idle frames for 10G links PPv2's XLGMAC can wait for 3 idle frames before triggering a link up event. This can cause the link to be stuck low when there's traffic on the interface, so disable this feature. Fixes: 4bb043262878 ("net: mvpp2: phylink support") Signed-off-by: Maxime Chevallier Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index c51f1d5b550b..b6591ea0c6d6 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4739,9 +4739,9 @@ static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode, else ctrl0 &= ~MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN; - ctrl4 &= ~MVPP22_XLG_CTRL4_MACMODSELECT_GMAC; - ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC | - MVPP22_XLG_CTRL4_EN_IDLE_CHECK; + ctrl4 &= ~(MVPP22_XLG_CTRL4_MACMODSELECT_GMAC | + MVPP22_XLG_CTRL4_EN_IDLE_CHECK); + ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC; if (old_ctrl0 != ctrl0) writel(ctrl0, port->base + MVPP22_XLG_CTRL0_REG); From f4e5f775db5a4631300dccd0de5eafb50a77c131 Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Mon, 22 Jul 2019 13:59:12 +0800 Subject: [PATCH 227/823] net: hns: fix LED configuration for marvell phy Since commit(net: phy: marvell: change default m88e1510 LED configuration), the active LED of Hip07 devices is always off, because Hip07 just use 2 LEDs. This patch adds a phy_register_fixup_for_uid() for m88e1510 to correct the LED configuration. Fixes: 077772468ec1 ("net: phy: marvell: change default m88e1510 LED configuration") Signed-off-by: Yonglong Liu Reviewed-by: linyunsheng Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 23 ++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 2235dd55fab2..5b213eb4f825 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -1149,6 +1150,13 @@ static void hns_nic_adjust_link(struct net_device *ndev) } } +static int hns_phy_marvell_fixup(struct phy_device *phydev) +{ + phydev->dev_flags |= MARVELL_PHY_LED0_LINK_LED1_ACTIVE; + + return 0; +} + /** *hns_nic_init_phy - init phy *@ndev: net device @@ -1174,6 +1182,16 @@ int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h) if (h->phy_if != PHY_INTERFACE_MODE_XGMII) { phy_dev->dev_flags = 0; + /* register the PHY fixup (for Marvell 88E1510) */ + ret = phy_register_fixup_for_uid(MARVELL_PHY_ID_88E1510, + MARVELL_PHY_ID_MASK, + hns_phy_marvell_fixup); + /* we can live without it, so just issue a warning */ + if (ret) + netdev_warn(ndev, + "Cannot register PHY fixup, ret=%d\n", + ret); + ret = phy_connect_direct(ndev, phy_dev, hns_nic_adjust_link, h->phy_if); } else { @@ -2430,8 +2448,11 @@ static int hns_nic_dev_remove(struct platform_device *pdev) hns_nic_uninit_ring_data(priv); priv->ring_data = NULL; - if (ndev->phydev) + if (ndev->phydev) { + phy_unregister_fixup_for_uid(MARVELL_PHY_ID_88E1510, + MARVELL_PHY_ID_MASK); phy_disconnect(ndev->phydev); + } if (!IS_ERR_OR_NULL(priv->ae_handle)) hnae_put_handle(priv->ae_handle); From cbcf0999ae33e7a8e1dba7ca935556634f679ccf Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Mon, 22 Jul 2019 10:39:30 +0200 Subject: [PATCH 228/823] net: stmmac: RX Descriptors need to be clean before setting buffers RX Descriptors are being cleaned after setting the buffers which may lead to buffer addresses being wiped out. Fix this by clearing earlier the RX Descriptors. Fixes: 2af6106ae949 ("net: stmmac: Introducing support for Page Pool") Signed-off-by: Jose Abreu Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index c7c9e5f162e6..5f1294ce0216 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1295,6 +1295,8 @@ static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags) "(%s) dma_rx_phy=0x%08x\n", __func__, (u32)rx_q->dma_rx_phy); + stmmac_clear_rx_descriptors(priv, queue); + for (i = 0; i < DMA_RX_SIZE; i++) { struct dma_desc *p; @@ -1312,8 +1314,6 @@ static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags) rx_q->cur_rx = 0; rx_q->dirty_rx = (unsigned int)(i - DMA_RX_SIZE); - stmmac_clear_rx_descriptors(priv, queue); - /* Setup the chained descriptor addresses */ if (priv->mode == STMMAC_CHAIN_MODE) { if (priv->extend_desc) From ec5e5ce1e18b44d0c4779619de3552e0afa5a11d Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Mon, 22 Jul 2019 10:39:31 +0200 Subject: [PATCH 229/823] net: stmmac: Use kcalloc() instead of kmalloc_array() We need the memory to be zeroed upon allocation so use kcalloc() instead. Signed-off-by: Jose Abreu Signed-off-by: David S. Miller --- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 5f1294ce0216..0ac79f3e2cee 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1555,9 +1555,8 @@ static int alloc_dma_rx_desc_resources(struct stmmac_priv *priv) goto err_dma; } - rx_q->buf_pool = kmalloc_array(DMA_RX_SIZE, - sizeof(*rx_q->buf_pool), - GFP_KERNEL); + rx_q->buf_pool = kcalloc(DMA_RX_SIZE, sizeof(*rx_q->buf_pool), + GFP_KERNEL); if (!rx_q->buf_pool) goto err_dma; @@ -1608,15 +1607,15 @@ static int alloc_dma_tx_desc_resources(struct stmmac_priv *priv) tx_q->queue_index = queue; tx_q->priv_data = priv; - tx_q->tx_skbuff_dma = kmalloc_array(DMA_TX_SIZE, - sizeof(*tx_q->tx_skbuff_dma), - GFP_KERNEL); + tx_q->tx_skbuff_dma = kcalloc(DMA_TX_SIZE, + sizeof(*tx_q->tx_skbuff_dma), + GFP_KERNEL); if (!tx_q->tx_skbuff_dma) goto err_dma; - tx_q->tx_skbuff = kmalloc_array(DMA_TX_SIZE, - sizeof(struct sk_buff *), - GFP_KERNEL); + tx_q->tx_skbuff = kcalloc(DMA_TX_SIZE, + sizeof(struct sk_buff *), + GFP_KERNEL); if (!tx_q->tx_skbuff) goto err_dma; From df7699c70c1bc1d9333d610fdc91fbbad84b59f2 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Mon, 22 Jul 2019 16:07:21 +0200 Subject: [PATCH 230/823] net: stmmac: Do not cut down 1G modes Some glue logic drivers support 1G without having GMAC/GMAC4/XGMAC. Let's allow this speed by default. Reported-by: Ondrej Jirman Tested-by: Ondrej Jirman Fixes: 5b0d7d7da64b ("net: stmmac: Add the missing speeds that XGMAC supports") Signed-off-by: Jose Abreu Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 0ac79f3e2cee..98b1a5c6d537 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -814,20 +814,15 @@ static void stmmac_validate(struct phylink_config *config, phylink_set(mac_supported, 10baseT_Full); phylink_set(mac_supported, 100baseT_Half); phylink_set(mac_supported, 100baseT_Full); + phylink_set(mac_supported, 1000baseT_Half); + phylink_set(mac_supported, 1000baseT_Full); + phylink_set(mac_supported, 1000baseKX_Full); phylink_set(mac_supported, Autoneg); phylink_set(mac_supported, Pause); phylink_set(mac_supported, Asym_Pause); phylink_set_port_modes(mac_supported); - if (priv->plat->has_gmac || - priv->plat->has_gmac4 || - priv->plat->has_xgmac) { - phylink_set(mac_supported, 1000baseT_Half); - phylink_set(mac_supported, 1000baseT_Full); - phylink_set(mac_supported, 1000baseKX_Full); - } - /* Cut down 1G if asked to */ if ((max_speed > 0) && (max_speed < 1000)) { phylink_set(mask, 1000baseT_Full); From e70bdd81bfe230a1044eaa49f7d9c9450178d635 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Jul 2019 14:19:08 +0200 Subject: [PATCH 231/823] scsi: fdomain: fix building pcmcia front-end We get a warning when CONFIG_SCSI_LOWLEVEL is disabled here: WARNING: unmet direct dependencies detected for SCSI_FDOMAIN Depends on [n]: SCSI_LOWLEVEL [=n] && SCSI [=y] Selected by [m]: - PCMCIA_FDOMAIN [=m] && SCSI_LOWLEVEL_PCMCIA [=y] && SCSI [=y] && PCMCIA [=y] && m && MODULES [=y] Move all of SCSI_LOWLEVEL_PCMCIA inside of the existing SCSI_LOWLEVEL section. Very few people use the PCMCIA support these days, and they likely don't mind having to turn on SCSI_LOWLEVEL as well. This way we avoid the link error and get a more sensible structure. Fixes: 7d47fa065e62 ("scsi: fdomain: Add PCMCIA support") Signed-off-by: Arnd Bergmann Signed-off-by: Martin K. Petersen --- drivers/scsi/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 75f66f8ad3ea..1b92f3c19ff3 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -1523,10 +1523,10 @@ config SCSI_VIRTIO source "drivers/scsi/csiostor/Kconfig" -endif # SCSI_LOWLEVEL - source "drivers/scsi/pcmcia/Kconfig" +endif # SCSI_LOWLEVEL + source "drivers/scsi/device_handler/Kconfig" endmenu From 1b5d9a6e98350e0713b4faa1b04e8f239f63b581 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 22 Jul 2019 11:20:38 +0200 Subject: [PATCH 232/823] scsi: core: fix the dma_max_mapping_size call We should only call dma_max_mapping_size for devices that have a DMA mask set, otherwise we can run into a NULL pointer dereference that will crash the system. Also we need to do right shift to get the sectors from the size in bytes, not a left shift. Fixes: bdd17bdef7d8 ("scsi: core: take the DMA max mapping size into account") Reported-by: Bart Van Assche Reported-by: Ming Lei Tested-by: Guilherme G. Piccoli Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 9381171c2fc0..11e64b50497f 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1784,8 +1784,10 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q) blk_queue_max_integrity_segments(q, shost->sg_prot_tablesize); } - shost->max_sectors = min_t(unsigned int, shost->max_sectors, - dma_max_mapping_size(dev) << SECTOR_SHIFT); + if (dev->dma_mask) { + shost->max_sectors = min_t(unsigned int, shost->max_sectors, + dma_max_mapping_size(dev) >> SECTOR_SHIFT); + } blk_queue_max_hw_sectors(q, shost->max_sectors); if (shost->unchecked_isa_dma) blk_queue_bounce_limit(q, BLK_BOUNCE_ISA); From b3e487c0cf425369a48049251af75593a5652dc1 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 22 Jul 2019 20:44:48 -0700 Subject: [PATCH 233/823] Revert "net: hns: fix LED configuration for marvell phy" This reverts commit f4e5f775db5a4631300dccd0de5eafb50a77c131. Andrew Lunn says this should be handled another way. Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 23 +------------------ 1 file changed, 1 insertion(+), 22 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 5b213eb4f825..2235dd55fab2 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include @@ -1150,13 +1149,6 @@ static void hns_nic_adjust_link(struct net_device *ndev) } } -static int hns_phy_marvell_fixup(struct phy_device *phydev) -{ - phydev->dev_flags |= MARVELL_PHY_LED0_LINK_LED1_ACTIVE; - - return 0; -} - /** *hns_nic_init_phy - init phy *@ndev: net device @@ -1182,16 +1174,6 @@ int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h) if (h->phy_if != PHY_INTERFACE_MODE_XGMII) { phy_dev->dev_flags = 0; - /* register the PHY fixup (for Marvell 88E1510) */ - ret = phy_register_fixup_for_uid(MARVELL_PHY_ID_88E1510, - MARVELL_PHY_ID_MASK, - hns_phy_marvell_fixup); - /* we can live without it, so just issue a warning */ - if (ret) - netdev_warn(ndev, - "Cannot register PHY fixup, ret=%d\n", - ret); - ret = phy_connect_direct(ndev, phy_dev, hns_nic_adjust_link, h->phy_if); } else { @@ -2448,11 +2430,8 @@ static int hns_nic_dev_remove(struct platform_device *pdev) hns_nic_uninit_ring_data(priv); priv->ring_data = NULL; - if (ndev->phydev) { - phy_unregister_fixup_for_uid(MARVELL_PHY_ID_88E1510, - MARVELL_PHY_ID_MASK); + if (ndev->phydev) phy_disconnect(ndev->phydev); - } if (!IS_ERR_OR_NULL(priv->ae_handle)) hnae_put_handle(priv->ae_handle); From 52d09014bb104a9157c0f5530700291052d2955c Mon Sep 17 00:00:00 2001 From: Anson Huang Date: Tue, 16 Jul 2019 11:09:33 +0800 Subject: [PATCH 234/823] arm64: dts: imx8mm: Correct SAI3 RXC/TXFS pin's mux option #1 According to i.MX8MM reference manual Rev.1, 03/2019: SAI3_RXC pin's mux option #1 should be GPT1_CLK, NOT GPT1_CAPTURE2; SAI3_TXFS pin's mux option #1 should be GPT1_CAPTURE2, NOT GPT1_CLK. Fixes: c1c9d41319c3 ("dt-bindings: imx: Add pinctrl binding doc for imx8mm") Signed-off-by: Anson Huang Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h index e25f7fcd7997..cffa8991880d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h +++ b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h @@ -462,7 +462,7 @@ #define MX8MM_IOMUXC_SAI3_RXFS_GPIO4_IO28 0x1CC 0x434 0x000 0x5 0x0 #define MX8MM_IOMUXC_SAI3_RXFS_TPSMP_HTRANS0 0x1CC 0x434 0x000 0x7 0x0 #define MX8MM_IOMUXC_SAI3_RXC_SAI3_RX_BCLK 0x1D0 0x438 0x000 0x0 0x0 -#define MX8MM_IOMUXC_SAI3_RXC_GPT1_CAPTURE2 0x1D0 0x438 0x000 0x1 0x0 +#define MX8MM_IOMUXC_SAI3_RXC_GPT1_CLK 0x1D0 0x438 0x000 0x1 0x0 #define MX8MM_IOMUXC_SAI3_RXC_SAI5_RX_BCLK 0x1D0 0x438 0x4D0 0x2 0x2 #define MX8MM_IOMUXC_SAI3_RXC_GPIO4_IO29 0x1D0 0x438 0x000 0x5 0x0 #define MX8MM_IOMUXC_SAI3_RXC_TPSMP_HTRANS1 0x1D0 0x438 0x000 0x7 0x0 @@ -472,7 +472,7 @@ #define MX8MM_IOMUXC_SAI3_RXD_GPIO4_IO30 0x1D4 0x43C 0x000 0x5 0x0 #define MX8MM_IOMUXC_SAI3_RXD_TPSMP_HDATA0 0x1D4 0x43C 0x000 0x7 0x0 #define MX8MM_IOMUXC_SAI3_TXFS_SAI3_TX_SYNC 0x1D8 0x440 0x000 0x0 0x0 -#define MX8MM_IOMUXC_SAI3_TXFS_GPT1_CLK 0x1D8 0x440 0x000 0x1 0x0 +#define MX8MM_IOMUXC_SAI3_TXFS_GPT1_CAPTURE2 0x1D8 0x440 0x000 0x1 0x0 #define MX8MM_IOMUXC_SAI3_TXFS_SAI5_RX_DATA1 0x1D8 0x440 0x4D8 0x2 0x2 #define MX8MM_IOMUXC_SAI3_TXFS_GPIO4_IO31 0x1D8 0x440 0x000 0x5 0x0 #define MX8MM_IOMUXC_SAI3_TXFS_TPSMP_HDATA1 0x1D8 0x440 0x000 0x7 0x0 From c528adefd645f5cd16fff658c863e2142d775c61 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 22 Jul 2019 12:22:57 +0200 Subject: [PATCH 235/823] int340X/processor_thermal_device: Fix proc_thermal_rapl_remove() Passing 0 to cpuhp_remove_state() triggers the BUG_ON() in __cpuhp_remove_state_cpuslocked() and the argument passed to powercap_unregister_control_type() is expected to be a valid pointer, so avoid calling these functions with incorrect arguments from proc_thermal_rapl_remove(). Fixes: 555c45fe0d04 ("int340X/processor_thermal_device: add support for MMIO RAPL") Signed-off-by: Rafael J. Wysocki Acked-by: Zhang Rui --- .../thermal/intel/int340x_thermal/processor_thermal_device.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c index 213ab3cc6b80..d3446acf9bbd 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c @@ -487,6 +487,7 @@ static int proc_thermal_rapl_add(struct pci_dev *pdev, rapl_mmio_cpu_online, rapl_mmio_cpu_down_prep); if (ret < 0) { powercap_unregister_control_type(rapl_mmio_priv.control_type); + rapl_mmio_priv.control_type = NULL; return ret; } rapl_mmio_priv.pcap_rapl_online = ret; @@ -496,6 +497,9 @@ static int proc_thermal_rapl_add(struct pci_dev *pdev, static void proc_thermal_rapl_remove(void) { + if (IS_ERR_OR_NULL(rapl_mmio_priv.control_type)) + return; + cpuhp_remove_state(rapl_mmio_priv.pcap_rapl_online); powercap_unregister_control_type(rapl_mmio_priv.control_type); } From 8d0148473dece51675d11dd59b8db5fe4b5d2e7e Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Wed, 17 Jul 2019 11:54:36 +0200 Subject: [PATCH 236/823] arm64: dts: imx8mq: fix SAI compatible The i.MX8M SAI block is not compatible with the i.MX6SX one, as the register layout has changed due to two version registers being added at the beginning of the address map. Remove the bogus compatible. Fixes: 8c61538dc945 ("arm64: dts: imx8mq: Add SAI2 node") Signed-off-by: Lucas Stach Reviewed-by: Daniel Baluta Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8mq.dtsi | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index d09b808eff87..52aae341d0da 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -715,8 +715,7 @@ sai2: sai@308b0000 { #sound-dai-cells = <0>; - compatible = "fsl,imx8mq-sai", - "fsl,imx6sx-sai"; + compatible = "fsl,imx8mq-sai"; reg = <0x308b0000 0x10000>; interrupts = ; clocks = <&clk IMX8MQ_CLK_SAI2_IPG>, From e0a12445d1cb186d875410d093a00d215bec6a89 Mon Sep 17 00:00:00 2001 From: Wen Yang Date: Wed, 17 Jul 2019 11:55:04 +0800 Subject: [PATCH 237/823] cpufreq/pasemi: fix use-after-free in pas_cpufreq_cpu_init() The cpu variable is still being used in the of_get_property() call after the of_node_put() call, which may result in use-after-free. Fixes: a9acc26b75f6 ("cpufreq/pasemi: fix possible object reference leak") Signed-off-by: Wen Yang Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/pasemi-cpufreq.c | 25 ++++++++++--------------- 1 file changed, 10 insertions(+), 15 deletions(-) diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c index 93f39a1d4c3d..c66f566a854c 100644 --- a/drivers/cpufreq/pasemi-cpufreq.c +++ b/drivers/cpufreq/pasemi-cpufreq.c @@ -131,11 +131,19 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy) int err = -ENODEV; cpu = of_get_cpu_node(policy->cpu, NULL); - - of_node_put(cpu); if (!cpu) goto out; + max_freqp = of_get_property(cpu, "clock-frequency", NULL); + of_node_put(cpu); + if (!max_freqp) { + err = -EINVAL; + goto out; + } + + /* we need the freq in kHz */ + max_freq = *max_freqp / 1000; + dn = of_find_compatible_node(NULL, NULL, "1682m-sdc"); if (!dn) dn = of_find_compatible_node(NULL, NULL, @@ -171,16 +179,6 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy) } pr_debug("init cpufreq on CPU %d\n", policy->cpu); - - max_freqp = of_get_property(cpu, "clock-frequency", NULL); - if (!max_freqp) { - err = -EINVAL; - goto out_unmap_sdcpwr; - } - - /* we need the freq in kHz */ - max_freq = *max_freqp / 1000; - pr_debug("max clock-frequency is at %u kHz\n", max_freq); pr_debug("initializing frequency table\n"); @@ -199,9 +197,6 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy) cpufreq_generic_init(policy, pas_freqs, get_gizmo_latency()); return 0; -out_unmap_sdcpwr: - iounmap(sdcpwr_mapbase); - out_unmap_sdcasr: iounmap(sdcasr_mapbase); out: From 201c1db90cd643282185a00770f12f95da330eca Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 23 Jul 2019 09:51:00 +0200 Subject: [PATCH 238/823] iommu/iova: Fix compilation error with !CONFIG_IOMMU_IOVA The stub function for !CONFIG_IOMMU_IOVA needs to be 'static inline'. Fixes: effa467870c76 ('iommu/vt-d: Don't queue_iova() if there is no flush queue') Signed-off-by: Joerg Roedel --- include/linux/iova.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/iova.h b/include/linux/iova.h index cd0f1de901a8..a0637abffee8 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -236,7 +236,7 @@ static inline void init_iova_domain(struct iova_domain *iovad, { } -bool has_iova_flush_queue(struct iova_domain *iovad) +static inline bool has_iova_flush_queue(struct iova_domain *iovad) { return false; } From 333a2101f47c4360ee78bb827277615d405b1cf7 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 Jul 2019 10:11:59 +0200 Subject: [PATCH 239/823] firmware: Fix missing inline I mistakenly dropped the inline while resolving the patch conflicts in the previous fix patch. Without inline, we get compiler warnings wrt unused functions. Note that Mauro's original patch contained the correct changes; it's all my fault to submit a patch before a morning coffee. Fixes: c8917b8ff09e ("firmware: fix build errors in paged buffer handling code") Signed-off-by: Takashi Iwai Link: https://lore.kernel.org/r/20190723081159.22624-1-tiwai@suse.de Signed-off-by: Greg Kroah-Hartman --- drivers/base/firmware_loader/firmware.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/base/firmware_loader/firmware.h b/drivers/base/firmware_loader/firmware.h index 842e63f19f22..7ecd590e67fe 100644 --- a/drivers/base/firmware_loader/firmware.h +++ b/drivers/base/firmware_loader/firmware.h @@ -141,8 +141,8 @@ int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed); int fw_map_paged_buf(struct fw_priv *fw_priv); #else static inline void fw_free_paged_buf(struct fw_priv *fw_priv) {} -static int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed) { return -ENXIO; } -static int fw_map_paged_buf(struct fw_priv *fw_priv) { return -ENXIO; } +static inline int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed) { return -ENXIO; } +static inline int fw_map_paged_buf(struct fw_priv *fw_priv) { return -ENXIO; } #endif #endif /* __FIRMWARE_LOADER_H */ From 6abe28197024f732f1e298b1a593505282505857 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Mon, 15 Jul 2019 15:30:33 +0200 Subject: [PATCH 240/823] s390: enable detection of kernel version from bzImage Extend "parmarea" to include an offset of the version string, which is stored as 8-byte big endian value. To retrieve version string from bzImage reliably, one should check the presence of "S390EP" ascii string at 0x10008 (available since v3.2), then read the version string offset from 0x10428 (which has been 0 since v3.2 up to now). The string is null terminated. Could be retrieved with the following "file" command magic (requires file v5.34): 8 string \x02\x00\x00\x18\x60\x00\x00\x50\x02\x00\x00\x68\x60\x00\x00\x50\x40\x40\x40\x40\x40\x40\x40\x40 Linux S390 >0x10008 string S390EP >>0x10428 bequad >0 >>>(0x10428.Q) string >\0 \b, version %s Reported-by: Petr Tesarik Suggested-by: Petr Tesarik Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/boot/Makefile | 2 +- arch/s390/boot/boot.h | 1 + arch/s390/boot/head.S | 1 + arch/s390/boot/version.c | 7 +++++++ arch/s390/include/asm/setup.h | 4 +++- 5 files changed, 13 insertions(+), 2 deletions(-) create mode 100644 arch/s390/boot/version.c diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index 7cba96e7587b..4cf0bddb7d92 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -36,7 +36,7 @@ CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char obj-y := head.o als.o startup.o mem_detect.o ipl_parm.o ipl_report.o obj-y += string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o -obj-y += ctype.o text_dma.o +obj-y += version.o ctype.o text_dma.o obj-$(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) += uv.o obj-$(CONFIG_RELOCATABLE) += machine_kexec_reloc.o obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h index ad57c2205a71..082905d97309 100644 --- a/arch/s390/boot/boot.h +++ b/arch/s390/boot/boot.h @@ -12,6 +12,7 @@ void print_missing_facilities(void); unsigned long get_random_base(unsigned long safe_addr); extern int kaslr_enabled; +extern const char kernel_version[]; unsigned long read_ipl_report(unsigned long safe_offset); diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S index 028aab03a9e7..2087bed6e60f 100644 --- a/arch/s390/boot/head.S +++ b/arch/s390/boot/head.S @@ -361,6 +361,7 @@ ENTRY(startup_kdump) .quad 0 # INITRD_SIZE .quad 0 # OLDMEM_BASE .quad 0 # OLDMEM_SIZE + .quad kernel_version # points to kernel version string .org COMMAND_LINE .byte "root=/dev/ram0 ro" diff --git a/arch/s390/boot/version.c b/arch/s390/boot/version.c new file mode 100644 index 000000000000..d32e58bdda6a --- /dev/null +++ b/arch/s390/boot/version.c @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include "boot.h" + +const char kernel_version[] = UTS_RELEASE + " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ") " UTS_VERSION; diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 82deb8fc8319..c5cfff7b1f91 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -54,6 +54,7 @@ #define INITRD_SIZE_OFFSET 0x10410 #define OLDMEM_BASE_OFFSET 0x10418 #define OLDMEM_SIZE_OFFSET 0x10420 +#define KERNEL_VERSION_OFFSET 0x10428 #define COMMAND_LINE_OFFSET 0x10480 #ifndef __ASSEMBLY__ @@ -74,7 +75,8 @@ struct parmarea { unsigned long initrd_size; /* 0x10410 */ unsigned long oldmem_base; /* 0x10418 */ unsigned long oldmem_size; /* 0x10420 */ - char pad1[0x10480 - 0x10428]; /* 0x10428 - 0x10480 */ + unsigned long kernel_version; /* 0x10428 */ + char pad1[0x10480 - 0x10430]; /* 0x10430 - 0x10480 */ char command_line[ARCH_COMMAND_LINE_SIZE]; /* 0x10480 */ }; From a6ec414a4dd529eeac5c3ea51c661daba3397108 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Thu, 11 Jul 2019 18:17:36 +0200 Subject: [PATCH 241/823] s390/qdio: add sanity checks to the fast-requeue path If the device driver were to send out a full queue's worth of SBALs, current code would end up discovering the last of those SBALs as PRIMED and erroneously skip the SIGA-w. This immediately stalls the queue. Add a check to not attempt fast-requeue in this case. While at it also make sure that the state of the previous SBAL was successfully extracted before inspecting it. Signed-off-by: Julian Wiedmann Reviewed-by: Jens Remus Signed-off-by: Heiko Carstens --- drivers/s390/cio/qdio_main.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 730c4e68094b..7f5adf02f095 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -1558,13 +1558,13 @@ static int handle_outbound(struct qdio_q *q, unsigned int callflags, rc = qdio_kick_outbound_q(q, phys_aob); } else if (need_siga_sync(q)) { rc = qdio_siga_sync_q(q); + } else if (count < QDIO_MAX_BUFFERS_PER_Q && + get_buf_state(q, prev_buf(bufnr), &state, 0) > 0 && + state == SLSB_CU_OUTPUT_PRIMED) { + /* The previous buffer is not processed yet, tack on. */ + qperf_inc(q, fast_requeue); } else { - /* try to fast requeue buffers */ - get_buf_state(q, prev_buf(bufnr), &state, 0); - if (state != SLSB_CU_OUTPUT_PRIMED) - rc = qdio_kick_outbound_q(q, 0); - else - qperf_inc(q, fast_requeue); + rc = qdio_kick_outbound_q(q, 0); } /* in case of SIGA errors we must process the error immediately */ From 69e96207ebf90ff8d5bac457134b0d4569f6634e Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Mon, 1 Jul 2019 14:19:29 +0200 Subject: [PATCH 242/823] s390/qdio: restrict QAOB usage to IQD unicast queues The IQD mcast queue doesn't support QAOB mode, so skip the qdio_enable_async_operation() setup call for this queue. This avoids the allocation of an unneeded QAOB pointer array, and sets up q->use_cq properly so that drivers are prohibited from using QAOBs for mcast traffic. Take this opportunity to streamline the q->use_cq and aob != 0 checks. The path to qdio_siga_output() is straight-forward, we don't need to worry about being called with bad operands. Signed-off-by: Julian Wiedmann Signed-off-by: Heiko Carstens --- drivers/s390/cio/qdio_main.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 7f5adf02f095..4142c85e77d8 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -319,9 +319,7 @@ static int qdio_siga_output(struct qdio_q *q, unsigned int *busy_bit, int retries = 0, cc; unsigned long laob = 0; - WARN_ON_ONCE(aob && ((queue_type(q) != QDIO_IQDIO_QFMT) || - !q->u.out.use_cq)); - if (q->u.out.use_cq && aob != 0) { + if (aob) { fc = QDIO_SIGA_WRITEQ; laob = aob; } @@ -621,9 +619,6 @@ static inline unsigned long qdio_aob_for_buffer(struct qdio_output_q *q, { unsigned long phys_aob = 0; - if (!q->use_cq) - return 0; - if (!q->aobs[bufnr]) { struct qaob *aob = qdio_allocate_aob(); q->aobs[bufnr] = aob; @@ -1308,6 +1303,8 @@ static void qdio_detect_hsicq(struct qdio_irq *irq_ptr) for_each_output_queue(irq_ptr, q, i) { if (use_cq) { + if (multicast_outbound(q)) + continue; if (qdio_enable_async_operation(&q->u.out) < 0) { use_cq = 0; continue; @@ -1553,7 +1550,8 @@ static int handle_outbound(struct qdio_q *q, unsigned int callflags, /* One SIGA-W per buffer required for unicast HSI */ WARN_ON_ONCE(count > 1 && !multicast_outbound(q)); - phys_aob = qdio_aob_for_buffer(&q->u.out, bufnr); + if (q->u.out.use_cq) + phys_aob = qdio_aob_for_buffer(&q->u.out, bufnr); rc = qdio_kick_outbound_q(q, phys_aob); } else if (need_siga_sync(q)) { From 3f4b04e3cfd40fb779f2404453f53157ec171da5 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 21 Jul 2019 14:33:21 +0200 Subject: [PATCH 243/823] s390/hypfs: fix a typo in the name of a function Everything is about hypfs_..., except 'hpyfs_vm_create_guest()' s/hpy/hyp/ Signed-off-by: Christophe JAILLET Signed-off-by: Christian Borntraeger Signed-off-by: Heiko Carstens --- arch/s390/hypfs/hypfs_vm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c index 42f2375c203e..e1fcc03159ef 100644 --- a/arch/s390/hypfs/hypfs_vm.c +++ b/arch/s390/hypfs/hypfs_vm.c @@ -118,7 +118,7 @@ do { \ return PTR_ERR(rc); \ } while(0) -static int hpyfs_vm_create_guest(struct dentry *systems_dir, +static int hypfs_vm_create_guest(struct dentry *systems_dir, struct diag2fc_data *data) { char guest_name[NAME_LEN + 1] = {}; @@ -219,7 +219,7 @@ int hypfs_vm_create_files(struct dentry *root) } for (i = 0; i < count; i++) { - rc = hpyfs_vm_create_guest(dir, &(data[i])); + rc = hypfs_vm_create_guest(dir, &(data[i])); if (rc) goto failed; } From 061c996239490a402aa31cd116f71a8bf9db1d8c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 21 Jul 2019 23:20:08 +0900 Subject: [PATCH 244/823] s390: use __u{16,32,64} instead of uint{16,32,64}_t in uapi header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When CONFIG_UAPI_HEADER_TEST=y, exported headers are compile-tested to make sure they can be included from user-space. Currently, zcrypt.h is excluded from the test coverage. To make it join the compile-test, we need to fix the build errors attached below. For a case like this, we decided to use __u{8,16,32,64} variable types in this discussion: https://lkml.org/lkml/2019/6/5/18 Build log: CC usr/include/asm/zcrypt.h.s In file included from :32:0: ./usr/include/asm/zcrypt.h:163:2: error: unknown type name ‘uint16_t’ uint16_t cprb_len; ^~~~~~~~ ./usr/include/asm/zcrypt.h:168:2: error: unknown type name ‘uint32_t’ uint32_t source_id; ^~~~~~~~ ./usr/include/asm/zcrypt.h:169:2: error: unknown type name ‘uint32_t’ uint32_t target_id; ^~~~~~~~ ./usr/include/asm/zcrypt.h:170:2: error: unknown type name ‘uint32_t’ uint32_t ret_code; ^~~~~~~~ ./usr/include/asm/zcrypt.h:171:2: error: unknown type name ‘uint32_t’ uint32_t reserved1; ^~~~~~~~ ./usr/include/asm/zcrypt.h:172:2: error: unknown type name ‘uint32_t’ uint32_t reserved2; ^~~~~~~~ ./usr/include/asm/zcrypt.h:173:2: error: unknown type name ‘uint32_t’ uint32_t payload_len; ^~~~~~~~ ./usr/include/asm/zcrypt.h:182:2: error: unknown type name ‘uint16_t’ uint16_t ap_id; ^~~~~~~~ ./usr/include/asm/zcrypt.h:183:2: error: unknown type name ‘uint16_t’ uint16_t dom_id; ^~~~~~~~ ./usr/include/asm/zcrypt.h:198:2: error: unknown type name ‘uint16_t’ uint16_t targets_num; ^~~~~~~~ ./usr/include/asm/zcrypt.h:199:2: error: unknown type name ‘uint64_t’ uint64_t targets; ^~~~~~~~ ./usr/include/asm/zcrypt.h:200:2: error: unknown type name ‘uint64_t’ uint64_t weight; ^~~~~~~~ ./usr/include/asm/zcrypt.h:201:2: error: unknown type name ‘uint64_t’ uint64_t req_no; ^~~~~~~~ ./usr/include/asm/zcrypt.h:202:2: error: unknown type name ‘uint64_t’ uint64_t req_len; ^~~~~~~~ ./usr/include/asm/zcrypt.h:203:2: error: unknown type name ‘uint64_t’ uint64_t req; ^~~~~~~~ ./usr/include/asm/zcrypt.h:204:2: error: unknown type name ‘uint64_t’ uint64_t resp_len; ^~~~~~~~ ./usr/include/asm/zcrypt.h:205:2: error: unknown type name ‘uint64_t’ uint64_t resp; ^~~~~~~~ Signed-off-by: Masahiro Yamada Signed-off-by: Heiko Carstens --- arch/s390/include/uapi/asm/zcrypt.h | 35 +++++++++++++++-------------- 1 file changed, 18 insertions(+), 17 deletions(-) diff --git a/arch/s390/include/uapi/asm/zcrypt.h b/arch/s390/include/uapi/asm/zcrypt.h index 494c34c50716..8c5755f41dde 100644 --- a/arch/s390/include/uapi/asm/zcrypt.h +++ b/arch/s390/include/uapi/asm/zcrypt.h @@ -20,6 +20,7 @@ #include #include +#include /* Name of the zcrypt device driver. */ #define ZCRYPT_NAME "zcrypt" @@ -160,17 +161,17 @@ struct ica_xcRB { * @payload_len: Payload length */ struct ep11_cprb { - uint16_t cprb_len; + __u16 cprb_len; unsigned char cprb_ver_id; unsigned char pad_000[2]; unsigned char flags; unsigned char func_id[2]; - uint32_t source_id; - uint32_t target_id; - uint32_t ret_code; - uint32_t reserved1; - uint32_t reserved2; - uint32_t payload_len; + __u32 source_id; + __u32 target_id; + __u32 ret_code; + __u32 reserved1; + __u32 reserved2; + __u32 payload_len; } __attribute__((packed)); /** @@ -179,8 +180,8 @@ struct ep11_cprb { * @dom_id: Usage domain id */ struct ep11_target_dev { - uint16_t ap_id; - uint16_t dom_id; + __u16 ap_id; + __u16 dom_id; }; /** @@ -195,14 +196,14 @@ struct ep11_target_dev { * @resp: Addr to response block */ struct ep11_urb { - uint16_t targets_num; - uint64_t targets; - uint64_t weight; - uint64_t req_no; - uint64_t req_len; - uint64_t req; - uint64_t resp_len; - uint64_t resp; + __u16 targets_num; + __u64 targets; + __u64 weight; + __u64 req_no; + __u64 req_len; + __u64 req; + __u64 resp_len; + __u64 resp; } __attribute__((packed)); /** From a963609e27786e2b0a80e649ca78798bf769c5d3 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 22 Jul 2019 14:16:46 +0200 Subject: [PATCH 245/823] kbuild: enable arch/s390/include/uapi/asm/zcrypt.h for uapi header test Masahiro Yamada changed the zcrypt.h header file to use __u{16,32,64} instead of uint{16,32,64}_t with ("s390: use __u{16,32,64} instead of uint{16,32,64}_t in uapi header"). This makes all s390 header files pass - remove zcrypt.h from the blacklist. Cc: Masahiro Yamada Signed-off-by: Heiko Carstens --- usr/include/Makefile | 4 ---- 1 file changed, 4 deletions(-) diff --git a/usr/include/Makefile b/usr/include/Makefile index aa316d99e035..1fb6abe29b2f 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -101,10 +101,6 @@ ifeq ($(SRCARCH),riscv) header-test- += linux/bpf_perf_event.h endif -ifeq ($(SRCARCH),s390) -header-test- += asm/zcrypt.h -endif - ifeq ($(SRCARCH),sparc) header-test- += asm/stat.h header-test- += asm/uctx.h From 5518aed82d2abd97f8d3ec91d8ba455d939e8cd1 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Sun, 14 Jul 2019 20:49:23 +0200 Subject: [PATCH 246/823] s390: wire up clone3 system call Tested (64-bit and compat mode) using program from http://lkml.kernel.org/r/20190604212930.jaaztvkent32b7d3@brauner.io with the following: return syscall(__NR_clone, flags, 0, pidfd, 0, 0); changed to: return syscall(__NR_clone, 0, flags, pidfd, 0, 0); due to CLONE_BACKWARDS2. Signed-off-by: Vasily Gorbik Acked-by: Christian Borntraeger Signed-off-by: Heiko Carstens --- arch/s390/include/asm/unistd.h | 1 + arch/s390/kernel/syscalls/syscall.tbl | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h index b6755685c7b8..9e9f75ef046a 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -34,5 +34,6 @@ #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_SYS_VFORK #define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_CLONE3 #endif /* _ASM_S390_UNISTD_H_ */ diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index a90d3e945445..3054e9c035a3 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -437,4 +437,4 @@ 432 common fsmount sys_fsmount sys_fsmount 433 common fspick sys_fspick sys_fspick 434 common pidfd_open sys_pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 common clone3 sys_clone3 sys_clone3 From 0a5c3c2f47667a14cd1a3127160af709e64e67b2 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Sun, 14 Jul 2019 20:49:26 +0200 Subject: [PATCH 247/823] s390/bitops: make test functions return bool Make s390/bitops test functions return bool values. That enforces return value range to 0 and 1 and matches with asm-generic/bitops-instrumented.h declarations as well as some other architectures implementations. Signed-off-by: Vasily Gorbik Reviewed-by: Christian Borntraeger Signed-off-by: Heiko Carstens --- arch/s390/include/asm/bitops.h | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 9900d655014c..74fafd8baaef 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -35,6 +35,7 @@ #include #include +#include #include #include @@ -118,7 +119,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *ptr) __atomic64_xor(mask, (long *)addr); } -static inline int +static inline bool test_and_set_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); @@ -129,7 +130,7 @@ test_and_set_bit(unsigned long nr, volatile unsigned long *ptr) return (old & mask) != 0; } -static inline int +static inline bool test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); @@ -140,7 +141,7 @@ test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr) return (old & ~mask) != 0; } -static inline int +static inline bool test_and_change_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); @@ -173,7 +174,7 @@ static inline void __change_bit(unsigned long nr, volatile unsigned long *ptr) *addr ^= 1 << (nr & 7); } -static inline int +static inline bool __test_and_set_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned char *addr = __bitops_byte(nr, ptr); @@ -184,7 +185,7 @@ __test_and_set_bit(unsigned long nr, volatile unsigned long *ptr) return (ch >> (nr & 7)) & 1; } -static inline int +static inline bool __test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned char *addr = __bitops_byte(nr, ptr); @@ -195,7 +196,7 @@ __test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr) return (ch >> (nr & 7)) & 1; } -static inline int +static inline bool __test_and_change_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned char *addr = __bitops_byte(nr, ptr); @@ -206,7 +207,7 @@ __test_and_change_bit(unsigned long nr, volatile unsigned long *ptr) return (ch >> (nr & 7)) & 1; } -static inline int test_bit(unsigned long nr, const volatile unsigned long *ptr) +static inline bool test_bit(unsigned long nr, const volatile unsigned long *ptr) { const volatile unsigned char *addr; @@ -215,8 +216,8 @@ static inline int test_bit(unsigned long nr, const volatile unsigned long *ptr) return (*addr >> (nr & 7)) & 1; } -static inline int test_and_set_bit_lock(unsigned long nr, - volatile unsigned long *ptr) +static inline bool test_and_set_bit_lock(unsigned long nr, + volatile unsigned long *ptr) { if (test_bit(nr, ptr)) return 1; @@ -261,7 +262,8 @@ static inline void clear_bit_inv(unsigned long nr, volatile unsigned long *ptr) return clear_bit(nr ^ (BITS_PER_LONG - 1), ptr); } -static inline int test_and_clear_bit_inv(unsigned long nr, volatile unsigned long *ptr) +static inline bool test_and_clear_bit_inv(unsigned long nr, + volatile unsigned long *ptr) { return test_and_clear_bit(nr ^ (BITS_PER_LONG - 1), ptr); } @@ -276,8 +278,8 @@ static inline void __clear_bit_inv(unsigned long nr, volatile unsigned long *ptr return __clear_bit(nr ^ (BITS_PER_LONG - 1), ptr); } -static inline int test_bit_inv(unsigned long nr, - const volatile unsigned long *ptr) +static inline bool test_bit_inv(unsigned long nr, + const volatile unsigned long *ptr) { return test_bit(nr ^ (BITS_PER_LONG - 1), ptr); } From 9779048d71b18ea85c067a85b648cebb2d29858e Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Sun, 14 Jul 2019 20:49:29 +0200 Subject: [PATCH 248/823] s390/kasan: add bitops instrumentation Add KASAN instrumentation of architecture-specific asm implementation of bitops. It also covers s390 specific *_inv functions. Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/include/asm/bitops.h | 71 ++++++++++++++++++---------------- 1 file changed, 38 insertions(+), 33 deletions(-) diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 74fafd8baaef..b8833ac983fa 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -56,7 +56,7 @@ __bitops_byte(unsigned long nr, volatile unsigned long *ptr) return ((unsigned char *)ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3); } -static inline void set_bit(unsigned long nr, volatile unsigned long *ptr) +static inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; @@ -77,7 +77,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *ptr) __atomic64_or(mask, (long *)addr); } -static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr) +static inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; @@ -98,7 +98,8 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr) __atomic64_and(mask, (long *)addr); } -static inline void change_bit(unsigned long nr, volatile unsigned long *ptr) +static inline void arch_change_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; @@ -119,8 +120,8 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *ptr) __atomic64_xor(mask, (long *)addr); } -static inline bool -test_and_set_bit(unsigned long nr, volatile unsigned long *ptr) +static inline bool arch_test_and_set_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long old, mask; @@ -130,8 +131,8 @@ test_and_set_bit(unsigned long nr, volatile unsigned long *ptr) return (old & mask) != 0; } -static inline bool -test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr) +static inline bool arch_test_and_clear_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long old, mask; @@ -141,8 +142,8 @@ test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr) return (old & ~mask) != 0; } -static inline bool -test_and_change_bit(unsigned long nr, volatile unsigned long *ptr) +static inline bool arch_test_and_change_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long old, mask; @@ -152,30 +153,31 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *ptr) return (old & mask) != 0; } -static inline void __set_bit(unsigned long nr, volatile unsigned long *ptr) +static inline void arch___set_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned char *addr = __bitops_byte(nr, ptr); *addr |= 1 << (nr & 7); } -static inline void -__clear_bit(unsigned long nr, volatile unsigned long *ptr) +static inline void arch___clear_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned char *addr = __bitops_byte(nr, ptr); *addr &= ~(1 << (nr & 7)); } -static inline void __change_bit(unsigned long nr, volatile unsigned long *ptr) +static inline void arch___change_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned char *addr = __bitops_byte(nr, ptr); *addr ^= 1 << (nr & 7); } -static inline bool -__test_and_set_bit(unsigned long nr, volatile unsigned long *ptr) +static inline bool arch___test_and_set_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned char *addr = __bitops_byte(nr, ptr); unsigned char ch; @@ -185,8 +187,8 @@ __test_and_set_bit(unsigned long nr, volatile unsigned long *ptr) return (ch >> (nr & 7)) & 1; } -static inline bool -__test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr) +static inline bool arch___test_and_clear_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned char *addr = __bitops_byte(nr, ptr); unsigned char ch; @@ -196,8 +198,8 @@ __test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr) return (ch >> (nr & 7)) & 1; } -static inline bool -__test_and_change_bit(unsigned long nr, volatile unsigned long *ptr) +static inline bool arch___test_and_change_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned char *addr = __bitops_byte(nr, ptr); unsigned char ch; @@ -207,7 +209,8 @@ __test_and_change_bit(unsigned long nr, volatile unsigned long *ptr) return (ch >> (nr & 7)) & 1; } -static inline bool test_bit(unsigned long nr, const volatile unsigned long *ptr) +static inline bool arch_test_bit(unsigned long nr, + const volatile unsigned long *ptr) { const volatile unsigned char *addr; @@ -216,28 +219,30 @@ static inline bool test_bit(unsigned long nr, const volatile unsigned long *ptr) return (*addr >> (nr & 7)) & 1; } -static inline bool test_and_set_bit_lock(unsigned long nr, +static inline bool arch_test_and_set_bit_lock(unsigned long nr, + volatile unsigned long *ptr) +{ + if (arch_test_bit(nr, ptr)) + return 1; + return arch_test_and_set_bit(nr, ptr); +} + +static inline void arch_clear_bit_unlock(unsigned long nr, volatile unsigned long *ptr) -{ - if (test_bit(nr, ptr)) - return 1; - return test_and_set_bit(nr, ptr); -} - -static inline void clear_bit_unlock(unsigned long nr, - volatile unsigned long *ptr) { smp_mb__before_atomic(); - clear_bit(nr, ptr); + arch_clear_bit(nr, ptr); } -static inline void __clear_bit_unlock(unsigned long nr, - volatile unsigned long *ptr) +static inline void arch___clear_bit_unlock(unsigned long nr, + volatile unsigned long *ptr) { smp_mb(); - __clear_bit(nr, ptr); + arch___clear_bit(nr, ptr); } +#include + /* * Functions which use MSB0 bit numbering. * The bits are numbered: From 4475f8c4ab7b248991a60d9c02808dbb813d6be8 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Mon, 22 Jul 2019 10:24:33 +0100 Subject: [PATCH 249/823] ALSA: compress: Fix regression on compressed capture streams A previous fix to the stop handling on compressed capture streams causes some knock on issues. The previous fix updated snd_compr_drain_notify to set the state back to PREPARED for capture streams. This causes some issues however as the handling for snd_compr_poll differs between the two states and some user-space applications were relying on the poll failing after the stream had been stopped. To correct this regression whilst still fixing the original problem the patch was addressing, update the capture handling to skip the PREPARED state rather than skipping the SETUP state as it has done until now. Fixes: 4f2ab5e1d13d ("ALSA: compress: Fix stop handling on compressed capture streams") Signed-off-by: Charles Keepax Acked-by: Vinod Koul Signed-off-by: Takashi Iwai --- include/sound/compress_driver.h | 5 +---- sound/core/compress_offload.c | 16 +++++++++++----- 2 files changed, 12 insertions(+), 9 deletions(-) diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h index c5188ff724d1..bc88d6f964da 100644 --- a/include/sound/compress_driver.h +++ b/include/sound/compress_driver.h @@ -173,10 +173,7 @@ static inline void snd_compr_drain_notify(struct snd_compr_stream *stream) if (snd_BUG_ON(!stream)) return; - if (stream->direction == SND_COMPRESS_PLAYBACK) - stream->runtime->state = SNDRV_PCM_STATE_SETUP; - else - stream->runtime->state = SNDRV_PCM_STATE_PREPARED; + stream->runtime->state = SNDRV_PCM_STATE_SETUP; wake_up(&stream->runtime->sleep); } diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 99b882158705..d79aee6b9edd 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -574,10 +574,7 @@ snd_compr_set_params(struct snd_compr_stream *stream, unsigned long arg) stream->metadata_set = false; stream->next_track = false; - if (stream->direction == SND_COMPRESS_PLAYBACK) - stream->runtime->state = SNDRV_PCM_STATE_SETUP; - else - stream->runtime->state = SNDRV_PCM_STATE_PREPARED; + stream->runtime->state = SNDRV_PCM_STATE_SETUP; } else { return -EPERM; } @@ -693,8 +690,17 @@ static int snd_compr_start(struct snd_compr_stream *stream) { int retval; - if (stream->runtime->state != SNDRV_PCM_STATE_PREPARED) + switch (stream->runtime->state) { + case SNDRV_PCM_STATE_SETUP: + if (stream->direction != SND_COMPRESS_CAPTURE) + return -EPERM; + break; + case SNDRV_PCM_STATE_PREPARED: + break; + default: return -EPERM; + } + retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_START); if (!retval) stream->runtime->state = SNDRV_PCM_STATE_RUNNING; From 26c3f1542f5064310ad26794c09321780d00c57d Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Mon, 22 Jul 2019 10:24:34 +0100 Subject: [PATCH 250/823] ALSA: compress: Prevent bypasses of set_params Currently, whilst in SNDRV_PCM_STATE_OPEN it is possible to call snd_compr_stop, snd_compr_drain and snd_compr_partial_drain, which allow a transition to SNDRV_PCM_STATE_SETUP. The stream should only be able to move to the setup state once it has received a SNDRV_COMPRESS_SET_PARAMS ioctl. Fix this issue by not allowing those ioctls whilst in the open state. Signed-off-by: Charles Keepax Acked-by: Vinod Koul Signed-off-by: Takashi Iwai --- sound/core/compress_offload.c | 30 ++++++++++++++++++++++++------ 1 file changed, 24 insertions(+), 6 deletions(-) diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index d79aee6b9edd..40dae723c59d 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -711,9 +711,15 @@ static int snd_compr_stop(struct snd_compr_stream *stream) { int retval; - if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED || - stream->runtime->state == SNDRV_PCM_STATE_SETUP) + switch (stream->runtime->state) { + case SNDRV_PCM_STATE_OPEN: + case SNDRV_PCM_STATE_SETUP: + case SNDRV_PCM_STATE_PREPARED: return -EPERM; + default: + break; + } + retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_STOP); if (!retval) { snd_compr_drain_notify(stream); @@ -801,9 +807,14 @@ static int snd_compr_drain(struct snd_compr_stream *stream) { int retval; - if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED || - stream->runtime->state == SNDRV_PCM_STATE_SETUP) + switch (stream->runtime->state) { + case SNDRV_PCM_STATE_OPEN: + case SNDRV_PCM_STATE_SETUP: + case SNDRV_PCM_STATE_PREPARED: return -EPERM; + default: + break; + } retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_DRAIN); if (retval) { @@ -840,9 +851,16 @@ static int snd_compr_next_track(struct snd_compr_stream *stream) static int snd_compr_partial_drain(struct snd_compr_stream *stream) { int retval; - if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED || - stream->runtime->state == SNDRV_PCM_STATE_SETUP) + + switch (stream->runtime->state) { + case SNDRV_PCM_STATE_OPEN: + case SNDRV_PCM_STATE_SETUP: + case SNDRV_PCM_STATE_PREPARED: return -EPERM; + default: + break; + } + /* stream can be drained only when next track has been signalled */ if (stream->next_track == false) return -EPERM; From a70ab8a8645083f3700814e757f2940a88b7ef88 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Mon, 22 Jul 2019 10:24:35 +0100 Subject: [PATCH 251/823] ALSA: compress: Don't allow paritial drain operations on capture streams Partial drain and next track are intended for gapless playback and don't really have an obvious interpretation for a capture stream, so makes sense to not allow those operations on capture streams. Signed-off-by: Charles Keepax Acked-by: Vinod Koul Signed-off-by: Takashi Iwai --- sound/core/compress_offload.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 40dae723c59d..6cf5b8440cf3 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -834,6 +834,10 @@ static int snd_compr_next_track(struct snd_compr_stream *stream) if (stream->runtime->state != SNDRV_PCM_STATE_RUNNING) return -EPERM; + /* next track doesn't have any meaning for capture streams */ + if (stream->direction == SND_COMPRESS_CAPTURE) + return -EPERM; + /* you can signal next track if this is intended to be a gapless stream * and current track metadata is set */ @@ -861,6 +865,10 @@ static int snd_compr_partial_drain(struct snd_compr_stream *stream) break; } + /* partial drain doesn't have any meaning for capture streams */ + if (stream->direction == SND_COMPRESS_CAPTURE) + return -EPERM; + /* stream can be drained only when next track has been signalled */ if (stream->next_track == false) return -EPERM; From 3b8179944cb0dd53e5223996966746cdc8a60657 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Mon, 22 Jul 2019 10:24:36 +0100 Subject: [PATCH 252/823] ALSA: compress: Be more restrictive about when a drain is allowed Draining makes little sense in the situation of hardware overrun, as the hardware will have consumed all its available samples. Additionally, draining whilst the stream is paused would presumably get stuck as no data is being consumed on the DSP side. Signed-off-by: Charles Keepax Acked-by: Vinod Koul Signed-off-by: Takashi Iwai --- sound/core/compress_offload.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 6cf5b8440cf3..41905afada63 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -811,7 +811,10 @@ static int snd_compr_drain(struct snd_compr_stream *stream) case SNDRV_PCM_STATE_OPEN: case SNDRV_PCM_STATE_SETUP: case SNDRV_PCM_STATE_PREPARED: + case SNDRV_PCM_STATE_PAUSED: return -EPERM; + case SNDRV_PCM_STATE_XRUN: + return -EPIPE; default: break; } @@ -860,7 +863,10 @@ static int snd_compr_partial_drain(struct snd_compr_stream *stream) case SNDRV_PCM_STATE_OPEN: case SNDRV_PCM_STATE_SETUP: case SNDRV_PCM_STATE_PREPARED: + case SNDRV_PCM_STATE_PAUSED: return -EPERM; + case SNDRV_PCM_STATE_XRUN: + return -EPIPE; default: break; } From 5f8eec3225ff7b86763b060164e9ce47b1a71406 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 11 Jul 2019 11:19:20 -0700 Subject: [PATCH 253/823] perf script: Fix --max-blocks man page description The --max-blocks description was using the old name brstackasm. Use brstackinsn instead. Signed-off-by: Andi Kleen Cc: Jiri Olsa Link: http://lkml.kernel.org/r/20190711181922.18765-1-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-script.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index d4e2e18a5881..042b9e5dcc32 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -384,7 +384,7 @@ include::itrace.txt[] perf script --time 0%-10%,30%-40% --max-blocks:: - Set the maximum number of program blocks to print with brstackasm for + Set the maximum number of program blocks to print with brstackinsn for each sample. --reltime:: From 7db7218a7ea577f04c2df92453d47ab5ebfc8863 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 11 Jul 2019 11:19:22 -0700 Subject: [PATCH 254/823] perf script: Improve man page description of metrics Clarify that a metric is based on events, not referring to itself. Also some improvements with the sentences. Signed-off-by: Andi Kleen Cc: Jiri Olsa Link: http://lkml.kernel.org/r/20190711181922.18765-3-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-script.txt | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 042b9e5dcc32..caaab28f8400 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -228,11 +228,11 @@ OPTIONS With the metric option perf script can compute metrics for sampling periods, similar to perf stat. This requires - specifying a group with multiple metrics with the :S option + specifying a group with multiple events defining metrics with the :S option for perf record. perf will sample on the first event, and - compute metrics for all the events in the group. Please note + print computed metrics for all the events in the group. Please note that the metric computed is averaged over the whole sampling - period, not just for the sample point. + period (since the last sample), not just for the sample point. For sample events it's possible to display misc field with -F +misc option, following letters are displayed for each bit: From dde4e732a5b02fa5599c2c0e6c48a0c11789afc4 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 11 Jul 2019 11:19:21 -0700 Subject: [PATCH 255/823] perf script: Fix off by one in brstackinsn IPC computation When we hit the end of a program block, need to count the last instruction too for the IPC computation. This caused large errors for small blocks. % perf script -b ls / > /dev/null Before: % perf script -F +brstackinsn --xed ... 00007f94c9ac70d8 jz 0x7f94c9ac70e3 # PRED 3 cycles [36] 4.33 IPC 00007f94c9ac70e3 testb $0x20, 0x31d(%rbx) 00007f94c9ac70ea jnz 0x7f94c9ac70b0 00007f94c9ac70ec testb $0x8, 0x205ad(%rip) 00007f94c9ac70f3 jz 0x7f94c9ac6ff0 # PRED 1 cycles [37] 3.00 IPC After: % perf script -F +brstackinsn --xed ... 00007f94c9ac70d8 jz 0x7f94c9ac70e3 # PRED 3 cycles [15] 4.67 IPC 00007f94c9ac70e3 testb $0x20, 0x31d(%rbx) 00007f94c9ac70ea jnz 0x7f94c9ac70b0 00007f94c9ac70ec testb $0x8, 0x205ad(%rip) 00007f94c9ac70f3 jz 0x7f94c9ac6ff0 # PRED 1 cycles [16] 4.00 IPC Suggested-by: Denis Bakhvalov Signed-off-by: Andi Kleen Cc: Jiri Olsa Link: http://lkml.kernel.org/r/20190711181922.18765-2-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 8f24865596af..0140ddb8dd0b 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1059,7 +1059,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp); if (ip == end) { - printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp, + printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, ++insn, fp, &total_cycles); if (PRINT_FIELD(SRCCODE)) printed += print_srccode(thread, x.cpumode, ip); From 79b2fe5e756163897175a8f57d66b26cd9befd59 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 15 Jul 2019 16:04:26 +0200 Subject: [PATCH 256/823] perf tools: Fix proper buffer size for feature processing After Song Liu's segfault fix for pipe mode, Arnaldo reported following error: # perf record -o - | perf script 0x514 [0x1ac]: failed to process type: 80 It's caused by wrong buffer size setup in feature processing, which makes cpu topology feature fail, because it's using buffer size to recognize its header version. Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: David Carrillo-Cisneros Cc: Kan Liang Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Fixes: e9def1b2e74e ("perf tools: Add feature header record to pipe-mode") Link: http://lkml.kernel.org/r/20190715140426.32509-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/header.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index c24db7f4909c..20111f8da5cb 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -3747,7 +3747,7 @@ int perf_event__process_feature(struct perf_session *session, return 0; ff.buf = (void *)fe->data; - ff.size = event->header.size - sizeof(event->header); + ff.size = event->header.size - sizeof(*fe); ff.ph = &session->header; if (feat_ops[feat].process(&ff, NULL)) From 08ef3af1579d0446db1c1bd08e2c42565addf10f Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 15 Jul 2019 16:21:21 +0200 Subject: [PATCH 257/823] perf stat: Fix segfault for event group in repeat mode Numfor Mbiziwo-Tiapo reported segfault on stat of event group in repeat mode: # perf stat -e '{cycles,instructions}' -r 10 ls It's caused by memory corruption due to not cleaned evsel's id array and index, which needs to be rebuilt in every stat iteration. Currently the ids index grows, while the array (which is also not freed) has the same size. Fixing this by releasing id array and zeroing ids index in perf_evsel__close function. We also need to keep the evsel_list alive for stat record (which is disabled in repeat mode). Reported-by: Numfor Mbiziwo-Tiapo Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Ian Rogers Cc: Mark Drayton Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20190715142121.GC6032@krava Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 9 ++++++++- tools/perf/util/evsel.c | 2 ++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index b55a534b4de0..352cf39d7c2f 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -607,7 +607,13 @@ try_again: * group leaders. */ read_counters(&(struct timespec) { .tv_nsec = t1-t0 }); - perf_evlist__close(evsel_list); + + /* + * We need to keep evsel_list alive, because it's processed + * later the evsel_list will be closed after. + */ + if (!STAT_RECORD) + perf_evlist__close(evsel_list); return WEXITSTATUS(status); } @@ -1997,6 +2003,7 @@ int cmd_stat(int argc, const char **argv) perf_session__write_header(perf_stat.session, evsel_list, fd, true); } + perf_evlist__close(evsel_list); perf_session__delete(perf_stat.session); } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index ebb46da4dfe5..52459dd5ad0c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1291,6 +1291,7 @@ static void perf_evsel__free_id(struct perf_evsel *evsel) xyarray__delete(evsel->sample_id); evsel->sample_id = NULL; zfree(&evsel->id); + evsel->ids = 0; } static void perf_evsel__free_config_terms(struct perf_evsel *evsel) @@ -2077,6 +2078,7 @@ void perf_evsel__close(struct perf_evsel *evsel) perf_evsel__close_fd(evsel); perf_evsel__free_fd(evsel); + perf_evsel__free_id(evsel); } int perf_evsel__open_per_cpu(struct perf_evsel *evsel, From 146540fb545b8464ba1be298e3392daca0d183a2 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 17 May 2019 15:10:39 -0700 Subject: [PATCH 258/823] perf stat: Always separate stalled cycles per insn The "stalled cycles per insn" is appended to "instructions" when the CPU has this hardware counter directly. We should always make it a separate line, which also aligns to the output when we hit the "if (total && avg)" branch. Before: $ sudo perf stat --all-cpus --field-separator , --log-fd 1 -einstructions,cycles -- sleep 1 4565048704,,instructions,64114578096,100.00,1.34,insn per cycle,, 3396325133,,cycles,64146628546,100.00,, After: $ sudo ./tools/perf/perf stat --all-cpus --field-separator , --log-fd 1 -einstructions,cycles -- sleep 1 6721924,,instructions,24026790339,100.00,0.22,insn per cycle ,,,,,0.00,stalled cycles per insn 30939953,,cycles,24025512526,100.00,, Signed-off-by: Cong Wang Acked-by: Jiri Olsa Cc: Andi Kleen Link: http://lkml.kernel.org/r/20190517221039.8975-1-xiyou.wangcong@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-shadow.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 656065af4971..accb1bf1cfd8 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -819,7 +819,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, "stalled cycles per insn", ratio); } else if (have_frontend_stalled) { - print_metric(config, ctxp, NULL, NULL, + out->new_line(config, ctxp); + print_metric(config, ctxp, NULL, "%7.2f ", "stalled cycles per insn", 0); } } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { From 872c8ee8f0f47222f7b10da96eea84d0486540a3 Mon Sep 17 00:00:00 2001 From: Alexey Budankov Date: Tue, 9 Jul 2019 17:48:14 +0300 Subject: [PATCH 259/823] perf session: Fix loading of compressed data split across adjacent records Fix decompression failure found during the loading of compressed trace collected on larger scale systems (>48 cores). The error happened due to lack of decompression space for a mmaped buffer data chunk split across adjacent PERF_RECORD_COMPRESSED records. $ perf report -i bt.16384.data --stats failed to decompress (B): 63869 -> 0 : Destination buffer is too small user stack dump failure Can't parse sample, err = -14 0x2637e436 [0x4080]: failed to process type: 9 Error: failed to process sample $ perf test 71 71: Zstd perf.data compression/decompression : Ok Signed-off-by: Alexey Budankov Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/4d839e1b-9c48-89c4-9702-a12217420611@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 22 ++++++++++++++-------- tools/perf/util/session.h | 1 + tools/perf/util/zstd.c | 4 ++-- 3 files changed, 17 insertions(+), 10 deletions(-) diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index d0fd6c614e68..37efa1f43d8b 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -36,10 +36,16 @@ static int perf_session__process_compressed_event(struct perf_session *session, void *src; size_t decomp_size, src_size; u64 decomp_last_rem = 0; - size_t decomp_len = session->header.env.comp_mmap_len; + size_t mmap_len, decomp_len = session->header.env.comp_mmap_len; struct decomp *decomp, *decomp_last = session->decomp_last; - decomp = mmap(NULL, sizeof(struct decomp) + decomp_len, PROT_READ|PROT_WRITE, + if (decomp_last) { + decomp_last_rem = decomp_last->size - decomp_last->head; + decomp_len += decomp_last_rem; + } + + mmap_len = sizeof(struct decomp) + decomp_len; + decomp = mmap(NULL, mmap_len, PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); if (decomp == MAP_FAILED) { pr_err("Couldn't allocate memory for decompression\n"); @@ -47,10 +53,10 @@ static int perf_session__process_compressed_event(struct perf_session *session, } decomp->file_pos = file_offset; + decomp->mmap_len = mmap_len; decomp->head = 0; - if (decomp_last) { - decomp_last_rem = decomp_last->size - decomp_last->head; + if (decomp_last_rem) { memcpy(decomp->data, &(decomp_last->data[decomp_last->head]), decomp_last_rem); decomp->size = decomp_last_rem; } @@ -61,7 +67,7 @@ static int perf_session__process_compressed_event(struct perf_session *session, decomp_size = zstd_decompress_stream(&(session->zstd_data), src, src_size, &(decomp->data[decomp_last_rem]), decomp_len - decomp_last_rem); if (!decomp_size) { - munmap(decomp, sizeof(struct decomp) + decomp_len); + munmap(decomp, mmap_len); pr_err("Couldn't decompress data\n"); return -1; } @@ -255,15 +261,15 @@ static void perf_session__delete_threads(struct perf_session *session) static void perf_session__release_decomp_events(struct perf_session *session) { struct decomp *next, *decomp; - size_t decomp_len; + size_t mmap_len; next = session->decomp; - decomp_len = session->header.env.comp_mmap_len; do { decomp = next; if (decomp == NULL) break; next = decomp->next; - munmap(decomp, decomp_len + sizeof(struct decomp)); + mmap_len = decomp->mmap_len; + munmap(decomp, mmap_len); } while (1); } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index dd8920b745bc..863dbad87849 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -46,6 +46,7 @@ struct perf_session { struct decomp { struct decomp *next; u64 file_pos; + size_t mmap_len; u64 head; size_t size; char data[]; diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c index 23bdb9884576..d2202392ffdb 100644 --- a/tools/perf/util/zstd.c +++ b/tools/perf/util/zstd.c @@ -99,8 +99,8 @@ size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size while (input.pos < input.size) { ret = ZSTD_decompressStream(data->dstream, &output, &input); if (ZSTD_isError(ret)) { - pr_err("failed to decompress (B): %ld -> %ld : %s\n", - src_size, output.size, ZSTD_getErrorName(ret)); + pr_err("failed to decompress (B): %ld -> %ld, dst_size %ld : %s\n", + src_size, output.size, dst_size, ZSTD_getErrorName(ret)); break; } output.dst = dst + output.pos; From df8350ed56a26f502a9636f37faf699a12ee906e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 18 Jul 2019 11:22:58 -0300 Subject: [PATCH 260/823] perf probe: Set pev->nargs to zero after freeing pev->args entries So that, when perf_add_probe_events() fails, like in: # perf probe icmp_rcv:64 "type=icmph->type" Failed to find 'icmph' in this function. Error: Failed to add events. Segmentation fault (core dumped) # We don't segfault. clear_perf_probe_event() was zeroing the whole pev, and since the switch to zfree() for the members in the pev, that memset() was removed, which left nargs with its original value, in the above case 1. With the memset the same pev could be passed to clear_perf_probe_event() multiple times, since all it would have would be zeroes, and free() accepts zero, the loop would not happen and we would just memset it again to zeroes. Without it we got that segfault, so zero nargs to keep it like it was, next cset will avoid calling clear_perf_probe_event() for the same pevs in case of failure. Cc: Adrian Hunter Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Namhyung Kim Fixes: d8f9da240495 ("perf tools: Use zfree() where applicable") Link: https://lkml.kernel.org/n/tip-802f2jypnwqsvyavvivs8464@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 0c3b55d0617d..4acd3457d39d 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -2219,6 +2219,7 @@ void clear_perf_probe_event(struct perf_probe_event *pev) field = next; } } + pev->nargs = 0; zfree(&pev->args); } From d95daf5accf4a72005daa13fbb1d1bd8709f2861 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 18 Jul 2019 11:28:37 -0300 Subject: [PATCH 261/823] perf probe: Avoid calling freeing routine multiple times for same pointer When perf_add_probe_events() we call cleanup_perf_probe_events() for the pev pointer it receives, then, as part of handling this failure the main 'perf probe' goes on and calls cleanup_params() and that will again call cleanup_perf_probe_events()for the same pointer, so just set nevents to zero when handling the failure of perf_add_probe_events() to avoid the double free. Cc: Adrian Hunter Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-x8qgma4g813z96dvtw9w219q@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-probe.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 6418782951a4..3d0ffd41fb55 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -698,6 +698,16 @@ __cmd_probe(int argc, const char **argv) ret = perf_add_probe_events(params.events, params.nevents); if (ret < 0) { + + /* + * When perf_add_probe_events() fails it calls + * cleanup_perf_probe_events(pevs, npevs), i.e. + * cleanup_perf_probe_events(params.events, params.nevents), which + * will call clear_perf_probe_event(), so set nevents to zero + * to avoid cleanup_params() to call clear_perf_probe_event() again + * on the same pevs. + */ + params.nevents = 0; pr_err_with_code(" Error: Failed to add events.", ret); return ret; } From 39e7317e37f7f0be366d1201c283f968c17268da Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 19 Jul 2019 15:34:30 -0300 Subject: [PATCH 262/823] perf build: Do not use -Wshadow on gcc < 4.8 As it is too strict, see https://lkml.org/lkml/2006/11/28/253 and https://gcc.gnu.org/gcc-4.8/changes.html, that takes into account Linus's comments (search for Wshadow) for the reasoning about -Wshadow not being interesting before gcc 4.8. Acked-by: Andrii Nakryiko Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/r/20190719183417.GQ3624@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/scripts/Makefile.include | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index 495066bafbe3..ded7a950dc40 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -32,7 +32,6 @@ EXTRA_WARNINGS += -Wno-system-headers EXTRA_WARNINGS += -Wold-style-definition EXTRA_WARNINGS += -Wpacked EXTRA_WARNINGS += -Wredundant-decls -EXTRA_WARNINGS += -Wshadow EXTRA_WARNINGS += -Wstrict-prototypes EXTRA_WARNINGS += -Wswitch-default EXTRA_WARNINGS += -Wswitch-enum @@ -69,8 +68,16 @@ endif # will do for now and keep the above -Wstrict-aliasing=3 in place # in newer systems. # Needed for the __raw_cmpxchg in tools/arch/x86/include/asm/cmpxchg.h +# +# See https://lkml.org/lkml/2006/11/28/253 and https://gcc.gnu.org/gcc-4.8/changes.html, +# that takes into account Linus's comments (search for Wshadow) for the reasoning about +# -Wshadow not being interesting before gcc 4.8. + ifneq ($(filter 3.%,$(MAKE_VERSION)),) # make-3 EXTRA_WARNINGS += -fno-strict-aliasing +EXTRA_WARNINGS += -Wno-shadow +else +EXTRA_WARNINGS += -Wshadow endif ifneq ($(findstring $(MAKEFLAGS), w),w) From 607975b30db41aad6edc846ed567191aa6b7d893 Mon Sep 17 00:00:00 2001 From: Ding Xiang Date: Tue, 23 Jul 2019 15:44:41 +0800 Subject: [PATCH 263/823] ALSA: ac97: Fix double free of ac97_codec_device put_device will call ac97_codec_release to free ac97_codec_device and other resources, so remove the kfree and other redundant code. Fixes: 74426fbff66e ("ALSA: ac97: add an ac97 bus") Signed-off-by: Ding Xiang Cc: Signed-off-by: Takashi Iwai --- sound/ac97/bus.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/sound/ac97/bus.c b/sound/ac97/bus.c index 7b977b753a03..7985dd8198b6 100644 --- a/sound/ac97/bus.c +++ b/sound/ac97/bus.c @@ -122,17 +122,12 @@ static int ac97_codec_add(struct ac97_controller *ac97_ctrl, int idx, vendor_id); ret = device_add(&codec->dev); - if (ret) - goto err_free_codec; + if (ret) { + put_device(&codec->dev); + return ret; + } return 0; -err_free_codec: - of_node_put(codec->dev.of_node); - put_device(&codec->dev); - kfree(codec); - ac97_ctrl->codecs[idx] = NULL; - - return ret; } unsigned int snd_ac97_bus_scan_one(struct ac97_controller *adrv, From 327fe1d42b83f8a06b33ba30159582b49af5fc8e Mon Sep 17 00:00:00 2001 From: Marcos Paulo de Souza Date: Tue, 23 Jul 2019 00:27:41 -0300 Subject: [PATCH 264/823] block: blk-mq: Remove blk_mq_sched_started_request and started_request blk_mq_sched_completed_request is a function that checks if the elevator related to the request has started_request implemented, but currently, none of the available IO schedulers implement started_request, so remove both. Signed-off-by: Marcos Paulo de Souza Signed-off-by: Jens Axboe --- block/blk-mq-sched.h | 9 --------- block/blk-mq.c | 2 -- include/linux/elevator.h | 1 - 3 files changed, 12 deletions(-) diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index cf22ab00fefb..126021fc3a11 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -61,15 +61,6 @@ static inline void blk_mq_sched_completed_request(struct request *rq, u64 now) e->type->ops.completed_request(rq, now); } -static inline void blk_mq_sched_started_request(struct request *rq) -{ - struct request_queue *q = rq->q; - struct elevator_queue *e = q->elevator; - - if (e && e->type->ops.started_request) - e->type->ops.started_request(rq); -} - static inline void blk_mq_sched_requeue_request(struct request *rq) { struct request_queue *q = rq->q; diff --git a/block/blk-mq.c b/block/blk-mq.c index 2bc2c0705660..f78d3287dd82 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -669,8 +669,6 @@ void blk_mq_start_request(struct request *rq) { struct request_queue *q = rq->q; - blk_mq_sched_started_request(rq); - trace_block_rq_issue(q, rq); if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) { diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 17cd0078377c..1dd014c9c87b 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -45,7 +45,6 @@ struct elevator_mq_ops { struct request *(*dispatch_request)(struct blk_mq_hw_ctx *); bool (*has_work)(struct blk_mq_hw_ctx *); void (*completed_request)(struct request *, u64); - void (*started_request)(struct request *); void (*requeue_request)(struct request *); struct request *(*former_request)(struct request_queue *, struct request *); struct request *(*next_request)(struct request_queue *, struct request *); From 77ce56e2bfaa64127ae5e23ef136c0168b818777 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Jul 2019 14:26:34 +0200 Subject: [PATCH 265/823] drbd: dynamically allocate shash descriptor Building with clang and KASAN, we get a warning about an overly large stack frame on 32-bit architectures: drivers/block/drbd/drbd_receiver.c:921:31: error: stack frame size of 1280 bytes in function 'conn_connect' [-Werror,-Wframe-larger-than=] We already allocate other data dynamically in this function, so just do the same for the shash descriptor, which makes up most of this memory. Link: https://lore.kernel.org/lkml/20190617132440.2721536-1-arnd@arndb.de/ Reviewed-by: Kees Cook Reviewed-by: Roland Kammerer Signed-off-by: Arnd Bergmann Signed-off-by: Jens Axboe --- drivers/block/drbd/drbd_receiver.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 90ebfcae0ce6..2b3103c30857 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -5417,7 +5417,7 @@ static int drbd_do_auth(struct drbd_connection *connection) unsigned int key_len; char secret[SHARED_SECRET_MAX]; /* 64 byte */ unsigned int resp_size; - SHASH_DESC_ON_STACK(desc, connection->cram_hmac_tfm); + struct shash_desc *desc; struct packet_info pi; struct net_conf *nc; int err, rv; @@ -5430,6 +5430,13 @@ static int drbd_do_auth(struct drbd_connection *connection) memcpy(secret, nc->shared_secret, key_len); rcu_read_unlock(); + desc = kmalloc(sizeof(struct shash_desc) + + crypto_shash_descsize(connection->cram_hmac_tfm), + GFP_KERNEL); + if (!desc) { + rv = -1; + goto fail; + } desc->tfm = connection->cram_hmac_tfm; rv = crypto_shash_setkey(connection->cram_hmac_tfm, (u8 *)secret, key_len); @@ -5571,7 +5578,10 @@ static int drbd_do_auth(struct drbd_connection *connection) kfree(peers_ch); kfree(response); kfree(right_response); - shash_desc_zero(desc); + if (desc) { + shash_desc_zero(desc); + kfree(desc); + } return rv; } From 5a46d3f71d5e5a9f82eabc682f996f1281705ac7 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Mon, 22 Jul 2019 17:25:48 +0100 Subject: [PATCH 266/823] ACPI/IORT: Fix off-by-one check in iort_dev_find_its_id() Static analysis identified that index comparison against ITS entries in iort_dev_find_its_id() is off by one. Update the comparison condition and clarify the resulting error message. Fixes: 4bf2efd26d76 ("ACPI: Add new IORT functions to support MSI domain handling") Link: https://lore.kernel.org/linux-arm-kernel/20190613065410.GB16334@mwanda/ Reviewed-by: Hanjun Guo Reported-by: Dan Carpenter Signed-off-by: Lorenzo Pieralisi Cc: Dan Carpenter Cc: Will Deacon Cc: Hanjun Guo Cc: Sudeep Holla Cc: Catalin Marinas Cc: Robin Murphy Signed-off-by: Will Deacon --- drivers/acpi/arm64/iort.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index d4551e33fa71..8569b79e8b58 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -611,8 +611,8 @@ static int iort_dev_find_its_id(struct device *dev, u32 req_id, /* Move to ITS specific data */ its = (struct acpi_iort_its_group *)node->node_data; - if (idx > its->its_count) { - dev_err(dev, "requested ITS ID index [%d] is greater than available [%d]\n", + if (idx >= its->its_count) { + dev_err(dev, "requested ITS ID index [%d] overruns ITS entries [%d]\n", idx, its->its_count); return -ENXIO; } From 66929812955bbec808c94d7a3916f41638a98a0a Mon Sep 17 00:00:00 2001 From: "Suthikulpanit, Suravee" Date: Tue, 16 Jul 2019 04:29:16 +0000 Subject: [PATCH 267/823] iommu/amd: Add support for X2APIC IOMMU interrupts AMD IOMMU requires IntCapXT registers to be setup in order to generate its own interrupts (for Event Log, PPR Log, and GA Log) with 32-bit APIC destination ID. Without this support, AMD IOMMU MSI interrupts will not be routed correctly when booting the system in X2APIC mode. Cc: Joerg Roedel Fixes: 90fcffd9cf5e ('iommu/amd: Add support for IOMMU XT mode') Signed-off-by: Suravee Suthikulpanit Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu_init.c | 90 +++++++++++++++++++++++++++++++++ drivers/iommu/amd_iommu_types.h | 9 ++++ 2 files changed, 99 insertions(+) diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index eb104c719629..4413aa67000e 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -23,6 +23,8 @@ #include #include #include +#include +#include #include #include #include @@ -1920,6 +1922,90 @@ static int iommu_setup_msi(struct amd_iommu *iommu) return 0; } +#define XT_INT_DEST_MODE(x) (((x) & 0x1ULL) << 2) +#define XT_INT_DEST_LO(x) (((x) & 0xFFFFFFULL) << 8) +#define XT_INT_VEC(x) (((x) & 0xFFULL) << 32) +#define XT_INT_DEST_HI(x) ((((x) >> 24) & 0xFFULL) << 56) + +/** + * Setup the IntCapXT registers with interrupt routing information + * based on the PCI MSI capability block registers, accessed via + * MMIO MSI address low/hi and MSI data registers. + */ +static void iommu_update_intcapxt(struct amd_iommu *iommu) +{ + u64 val; + u32 addr_lo = readl(iommu->mmio_base + MMIO_MSI_ADDR_LO_OFFSET); + u32 addr_hi = readl(iommu->mmio_base + MMIO_MSI_ADDR_HI_OFFSET); + u32 data = readl(iommu->mmio_base + MMIO_MSI_DATA_OFFSET); + bool dm = (addr_lo >> MSI_ADDR_DEST_MODE_SHIFT) & 0x1; + u32 dest = ((addr_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xFF); + + if (x2apic_enabled()) + dest |= MSI_ADDR_EXT_DEST_ID(addr_hi); + + val = XT_INT_VEC(data & 0xFF) | + XT_INT_DEST_MODE(dm) | + XT_INT_DEST_LO(dest) | + XT_INT_DEST_HI(dest); + + /** + * Current IOMMU implemtation uses the same IRQ for all + * 3 IOMMU interrupts. + */ + writeq(val, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET); + writeq(val, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET); + writeq(val, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET); +} + +static void _irq_notifier_notify(struct irq_affinity_notify *notify, + const cpumask_t *mask) +{ + struct amd_iommu *iommu; + + for_each_iommu(iommu) { + if (iommu->dev->irq == notify->irq) { + iommu_update_intcapxt(iommu); + break; + } + } +} + +static void _irq_notifier_release(struct kref *ref) +{ +} + +static int iommu_init_intcapxt(struct amd_iommu *iommu) +{ + int ret; + struct irq_affinity_notify *notify = &iommu->intcapxt_notify; + + /** + * IntCapXT requires XTSup=1, which can be inferred + * amd_iommu_xt_mode. + */ + if (amd_iommu_xt_mode != IRQ_REMAP_X2APIC_MODE) + return 0; + + /** + * Also, we need to setup notifier to update the IntCapXT registers + * whenever the irq affinity is changed from user-space. + */ + notify->irq = iommu->dev->irq; + notify->notify = _irq_notifier_notify, + notify->release = _irq_notifier_release, + ret = irq_set_affinity_notifier(iommu->dev->irq, notify); + if (ret) { + pr_err("Failed to register irq affinity notifier (devid=%#x, irq %d)\n", + iommu->devid, iommu->dev->irq); + return ret; + } + + iommu_update_intcapxt(iommu); + iommu_feature_enable(iommu, CONTROL_INTCAPXT_EN); + return ret; +} + static int iommu_init_msi(struct amd_iommu *iommu) { int ret; @@ -1936,6 +2022,10 @@ static int iommu_init_msi(struct amd_iommu *iommu) return ret; enable_faults: + ret = iommu_init_intcapxt(iommu); + if (ret) + return ret; + iommu_feature_enable(iommu, CONTROL_EVT_INT_EN); if (iommu->ppr_log != NULL) diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index 52c35d557fad..64edd5a9694c 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -60,6 +60,12 @@ #define MMIO_PPR_LOG_OFFSET 0x0038 #define MMIO_GA_LOG_BASE_OFFSET 0x00e0 #define MMIO_GA_LOG_TAIL_OFFSET 0x00e8 +#define MMIO_MSI_ADDR_LO_OFFSET 0x015C +#define MMIO_MSI_ADDR_HI_OFFSET 0x0160 +#define MMIO_MSI_DATA_OFFSET 0x0164 +#define MMIO_INTCAPXT_EVT_OFFSET 0x0170 +#define MMIO_INTCAPXT_PPR_OFFSET 0x0178 +#define MMIO_INTCAPXT_GALOG_OFFSET 0x0180 #define MMIO_CMD_HEAD_OFFSET 0x2000 #define MMIO_CMD_TAIL_OFFSET 0x2008 #define MMIO_EVT_HEAD_OFFSET 0x2010 @@ -150,6 +156,7 @@ #define CONTROL_GALOG_EN 0x1CULL #define CONTROL_GAINT_EN 0x1DULL #define CONTROL_XT_EN 0x32ULL +#define CONTROL_INTCAPXT_EN 0x33ULL #define CTRL_INV_TO_MASK (7 << CONTROL_INV_TIMEOUT) #define CTRL_INV_TO_NONE 0 @@ -592,6 +599,8 @@ struct amd_iommu { /* DebugFS Info */ struct dentry *debugfs; #endif + /* IRQ notifier for IntCapXT interrupt */ + struct irq_affinity_notify intcapxt_notify; }; static inline struct amd_iommu *dev_to_amd_iommu(struct device *dev) From 06532750010e06dd4b6d69983773677df7fc5291 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Mon, 22 Jul 2019 18:51:49 +0200 Subject: [PATCH 268/823] dma-mapping: use dma_get_mask in dma_addressing_limited We currently have cases where the dma_addressing_limited() gets called with dma_mask unset. This causes a NULL pointer dereference. Use dma_get_mask() accessor to prevent the crash. Fixes: b866455423e0 ("dma-mapping: add a dma_addressing_limited helper") Signed-off-by: Eric Auger Acked-by: Michael S. Tsirkin Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index e11b115dd0e4..f7d1eea32c78 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -689,8 +689,8 @@ static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask) */ static inline bool dma_addressing_limited(struct device *dev) { - return min_not_zero(*dev->dma_mask, dev->bus_dma_mask) < - dma_get_required_mask(dev); + return min_not_zero(dma_get_mask(dev), dev->bus_dma_mask) < + dma_get_required_mask(dev); } #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS From 08b903b5fd0c49e5f224a9bf085b6329ec3c55c0 Mon Sep 17 00:00:00 2001 From: Misha Nasledov Date: Mon, 15 Jul 2019 00:11:49 -0700 Subject: [PATCH 269/823] nvme: ignore subnqn for ADATA SX6000LNP The ADATA SX6000LNP NVMe SSDs have the same subnqn and, due to this, a system with more than one of these SSDs will only have one usable. [ 0.942706] nvme nvme1: ignoring ctrl due to duplicate subnqn (nqn.2018-05.com.example:nvme:nvm-subsystem-OUI00E04C). [ 0.943017] nvme nvme1: Removing after probe failure status: -22 02:00.0 Non-Volatile memory controller [0108]: Realtek Semiconductor Co., Ltd. Device [10ec:5762] (rev 01) 71:00.0 Non-Volatile memory controller [0108]: Realtek Semiconductor Co., Ltd. Device [10ec:5762] (rev 01) There are no firmware updates available from the vendor, unfortunately. Applying the NVME_QUIRK_IGNORE_DEV_SUBNQN quirk for these SSDs resolves the issue, and they all work after this patch: /dev/nvme0n1 2J1120050420 ADATA SX6000LNP [...] /dev/nvme1n1 2J1120050540 ADATA SX6000LNP [...] Signed-off-by: Misha Nasledov Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index bb970ca82517..dd10cf78f2d3 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3029,6 +3029,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_LIGHTNVM, }, { PCI_DEVICE(0x1d1d, 0x2601), /* CNEX Granby */ .driver_data = NVME_QUIRK_LIGHTNVM, }, + { PCI_DEVICE(0x10ec, 0x5762), /* ADATA SX6000LNP */ + .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) }, From e654dfd38c1ecf58d8d019f3c053189413484a5b Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 18 Jul 2019 17:53:50 -0600 Subject: [PATCH 270/823] nvme: fix memory leak caused by incorrect subsystem free When freeing the subsystem after finding another match with __nvme_find_get_subsystem(), use put_device() instead of __nvme_release_subsystem() which calls kfree() directly. Per the documentation, put_device() should always be used after device_initialization() is called. Otherwise, leaks like the one below which was detected by kmemleak may occur. Once the call of __nvme_release_subsystem() is removed it no longer makes sense to keep the helper, so fold it back into nvme_release_subsystem(). unreferenced object 0xffff8883d12bfbc0 (size 16): comm "nvme", pid 2635, jiffies 4294933602 (age 739.952s) hex dump (first 16 bytes): 6e 76 6d 65 2d 73 75 62 73 79 73 32 00 88 ff ff nvme-subsys2.... backtrace: [<000000007d8fc208>] __kmalloc_track_caller+0x16d/0x2a0 [<0000000081169e5f>] kvasprintf+0xad/0x130 [<0000000025626f25>] kvasprintf_const+0x47/0x120 [<00000000fa66ad36>] kobject_set_name_vargs+0x44/0x120 [<000000004881f8b3>] dev_set_name+0x98/0xc0 [<000000007124dae3>] nvme_init_identify+0x1995/0x38e0 [<000000009315020a>] nvme_loop_configure_admin_queue+0x4fa/0x5e0 [<000000001a63e766>] nvme_loop_create_ctrl+0x489/0xf80 [<00000000a46ecc23>] nvmf_dev_write+0x1a12/0x2220 [<000000002259b3d5>] __vfs_write+0x66/0x120 [<000000002f6df81e>] vfs_write+0x154/0x490 [<000000007e8cfc19>] ksys_write+0x10a/0x240 [<00000000ff5c7b85>] __x64_sys_write+0x73/0xb0 [<00000000fee6d692>] do_syscall_64+0xaa/0x470 [<00000000997e1ede>] entry_SYSCALL_64_after_hwframe+0x49/0xbe Fixes: ab9e00cc72fa ("nvme: track subsystems") Signed-off-by: Logan Gunthorpe Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index cc09b81fc7f4..8f3fbe5ca937 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2311,15 +2311,13 @@ static void nvme_init_subnqn(struct nvme_subsystem *subsys, struct nvme_ctrl *ct memset(subsys->subnqn + off, 0, sizeof(subsys->subnqn) - off); } -static void __nvme_release_subsystem(struct nvme_subsystem *subsys) -{ - ida_simple_remove(&nvme_subsystems_ida, subsys->instance); - kfree(subsys); -} - static void nvme_release_subsystem(struct device *dev) { - __nvme_release_subsystem(container_of(dev, struct nvme_subsystem, dev)); + struct nvme_subsystem *subsys = + container_of(dev, struct nvme_subsystem, dev); + + ida_simple_remove(&nvme_subsystems_ida, subsys->instance); + kfree(subsys); } static void nvme_destroy_subsystem(struct kref *ref) @@ -2477,7 +2475,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) mutex_lock(&nvme_subsystems_lock); found = __nvme_find_get_subsystem(subsys->subnqn); if (found) { - __nvme_release_subsystem(subsys); + put_device(&subsys->dev); subsys = found; if (!nvme_validate_cntlid(subsys, ctrl, id)) { From 66b20ac0a1a10769d059d6903202f53494e3d902 Mon Sep 17 00:00:00 2001 From: Marta Rybczynska Date: Tue, 23 Jul 2019 07:41:20 +0200 Subject: [PATCH 271/823] nvme: fix multipath crash when ANA is deactivated Fix a crash with multipath activated. It happends when ANA log page is larger than MDTS and because of that ANA is disabled. The driver then tries to access unallocated buffer when connecting to a nvme target. The signature is as follows: [ 300.433586] nvme nvme0: ANA log page size (8208) larger than MDTS (8192). [ 300.435387] nvme nvme0: disabling ANA support. [ 300.437835] nvme nvme0: creating 4 I/O queues. [ 300.459132] nvme nvme0: new ctrl: NQN "nqn.0.0.0", addr 10.91.0.1:8009 [ 300.464609] BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 [ 300.466342] #PF error: [normal kernel read fault] [ 300.467385] PGD 0 P4D 0 [ 300.467987] Oops: 0000 [#1] SMP PTI [ 300.468787] CPU: 3 PID: 50 Comm: kworker/u8:1 Not tainted 5.0.20kalray+ #4 [ 300.470264] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 [ 300.471532] Workqueue: nvme-wq nvme_scan_work [nvme_core] [ 300.472724] RIP: 0010:nvme_parse_ana_log+0x21/0x140 [nvme_core] [ 300.474038] Code: 45 01 d2 d8 48 98 c3 66 90 0f 1f 44 00 00 41 57 41 56 41 55 41 54 55 53 48 89 fb 48 83 ec 08 48 8b af 20 0a 00 00 48 89 34 24 <66> 83 7d 08 00 0f 84 c6 00 00 00 44 8b 7d 14 49 89 d5 8b 55 10 48 [ 300.477374] RSP: 0018:ffffa50e80fd7cb8 EFLAGS: 00010296 [ 300.478334] RAX: 0000000000000001 RBX: ffff9130f1872258 RCX: 0000000000000000 [ 300.479784] RDX: ffffffffc06c4c30 RSI: ffff9130edad4280 RDI: ffff9130f1872258 [ 300.481488] RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000044 [ 300.483203] R10: 0000000000000220 R11: 0000000000000040 R12: ffff9130f18722c0 [ 300.484928] R13: ffff9130f18722d0 R14: ffff9130edad4280 R15: ffff9130f18722c0 [ 300.486626] FS: 0000000000000000(0000) GS:ffff9130f7b80000(0000) knlGS:0000000000000000 [ 300.488538] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 300.489907] CR2: 0000000000000008 CR3: 00000002365e6000 CR4: 00000000000006e0 [ 300.491612] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 300.493303] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 300.494991] Call Trace: [ 300.495645] nvme_mpath_add_disk+0x5c/0xb0 [nvme_core] [ 300.496880] nvme_validate_ns+0x2ef/0x550 [nvme_core] [ 300.498105] ? nvme_identify_ctrl.isra.45+0x6a/0xb0 [nvme_core] [ 300.499539] nvme_scan_work+0x2b4/0x370 [nvme_core] [ 300.500717] ? __switch_to_asm+0x35/0x70 [ 300.501663] process_one_work+0x171/0x380 [ 300.502340] worker_thread+0x49/0x3f0 [ 300.503079] kthread+0xf8/0x130 [ 300.503795] ? max_active_store+0x80/0x80 [ 300.504690] ? kthread_bind+0x10/0x10 [ 300.505502] ret_from_fork+0x35/0x40 [ 300.506280] Modules linked in: nvme_tcp nvme_rdma rdma_cm iw_cm ib_cm ib_core nvme_fabrics nvme_core xt_physdev ip6table_raw ip6table_mangle ip6table_filter ip6_tables xt_comment iptable_nat nf_nat_ipv4 nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 xt_CHECKSUM iptable_mangle iptable_filter veth ebtable_filter ebtable_nat ebtables iptable_raw vxlan ip6_udp_tunnel udp_tunnel sunrpc joydev pcspkr virtio_balloon br_netfilter bridge stp llc ip_tables xfs libcrc32c ata_generic pata_acpi virtio_net virtio_console net_failover virtio_blk failover ata_piix serio_raw libata virtio_pci virtio_ring virtio [ 300.514984] CR2: 0000000000000008 [ 300.515569] ---[ end trace faa2eefad7e7f218 ]--- [ 300.516354] RIP: 0010:nvme_parse_ana_log+0x21/0x140 [nvme_core] [ 300.517330] Code: 45 01 d2 d8 48 98 c3 66 90 0f 1f 44 00 00 41 57 41 56 41 55 41 54 55 53 48 89 fb 48 83 ec 08 48 8b af 20 0a 00 00 48 89 34 24 <66> 83 7d 08 00 0f 84 c6 00 00 00 44 8b 7d 14 49 89 d5 8b 55 10 48 [ 300.520353] RSP: 0018:ffffa50e80fd7cb8 EFLAGS: 00010296 [ 300.521229] RAX: 0000000000000001 RBX: ffff9130f1872258 RCX: 0000000000000000 [ 300.522399] RDX: ffffffffc06c4c30 RSI: ffff9130edad4280 RDI: ffff9130f1872258 [ 300.523560] RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000044 [ 300.524734] R10: 0000000000000220 R11: 0000000000000040 R12: ffff9130f18722c0 [ 300.525915] R13: ffff9130f18722d0 R14: ffff9130edad4280 R15: ffff9130f18722c0 [ 300.527084] FS: 0000000000000000(0000) GS:ffff9130f7b80000(0000) knlGS:0000000000000000 [ 300.528396] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 300.529440] CR2: 0000000000000008 CR3: 00000002365e6000 CR4: 00000000000006e0 [ 300.530739] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 300.531989] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 300.533264] Kernel panic - not syncing: Fatal exception [ 300.534338] Kernel Offset: 0x17c00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 300.536227] ---[ end Kernel panic - not syncing: Fatal exception ]--- Condition check refactoring from Christoph Hellwig. Signed-off-by: Marta Rybczynska Tested-by: Jean-Baptiste Riaux Signed-off-by: Christoph Hellwig --- drivers/nvme/host/multipath.c | 8 ++------ drivers/nvme/host/nvme.h | 6 +++++- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index a9a927677970..4f0d0d12744e 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -12,11 +12,6 @@ module_param(multipath, bool, 0444); MODULE_PARM_DESC(multipath, "turn on native support for multiple controllers per subsystem"); -inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) -{ - return multipath && ctrl->subsys && (ctrl->subsys->cmic & (1 << 3)); -} - /* * If multipathing is enabled we need to always use the subsystem instance * number for numbering our devices to avoid conflicts between subsystems that @@ -622,7 +617,8 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) { int error; - if (!nvme_ctrl_use_ana(ctrl)) + /* check if multipath is enabled and we have the capability */ + if (!multipath || !ctrl->subsys || !(ctrl->subsys->cmic & (1 << 3))) return 0; ctrl->anacap = id->anacap; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 716a876119c8..26b563f9985b 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -485,7 +485,11 @@ extern const struct attribute_group *nvme_ns_id_attr_groups[]; extern const struct block_device_operations nvme_ns_head_ops; #ifdef CONFIG_NVME_MULTIPATH -bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl); +static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) +{ + return ctrl->ana_log_buf != NULL; +} + void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns, struct nvme_ctrl *ctrl, int *flags); void nvme_failover_req(struct request *req); From 8fe34be14ecb5eb0ef8d8d44aa7ab62d9e2911ca Mon Sep 17 00:00:00 2001 From: yangerkun Date: Tue, 23 Jul 2019 11:23:13 +0800 Subject: [PATCH 272/823] Revert "nvme-pci: don't create a read hctx mapping without read queues" This reverts commit 0298d5435276e7795b0b939d74827f6e775e7009. With this patch, set 'poll_queues > hard queues' will lead to 'nr_read_queues = 0' in nvme_calc_irq_sets. Then poll_queues setting can fail since dev->tagset.nr_maps equals to 2 and nvme_pci_map_queues will not do map for poll queues. Signed-off-by: yangerkun Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index dd10cf78f2d3..db160cee42ad 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2254,9 +2254,7 @@ static int nvme_dev_add(struct nvme_dev *dev) if (!dev->ctrl.tagset) { dev->tagset.ops = &nvme_mq_ops; dev->tagset.nr_hw_queues = dev->online_queues - 1; - dev->tagset.nr_maps = 1; /* default */ - if (dev->io_queues[HCTX_TYPE_READ]) - dev->tagset.nr_maps++; + dev->tagset.nr_maps = 2; /* default + read */ if (dev->io_queues[HCTX_TYPE_POLL]) dev->tagset.nr_maps++; dev->tagset.timeout = NVME_IO_TIMEOUT; From 36876b30d2143121322cd199cc23f27143912deb Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Tue, 23 Jul 2019 19:22:52 +0900 Subject: [PATCH 273/823] selftests: kmod: Fix typo in kmod.sh This patch fixes some spelling typos in kmod.sh Signed-off-by: Masanari Iida Acked-by: Randy Dunlap Signed-off-by: Shuah Khan --- tools/testing/selftests/kmod/kmod.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh index 0a76314b4414..8b944cf042f6 100755 --- a/tools/testing/selftests/kmod/kmod.sh +++ b/tools/testing/selftests/kmod/kmod.sh @@ -28,7 +28,7 @@ # override by exporting to your environment prior running this script. # For instance this script assumes you do not have xfs loaded upon boot. # If this is false, export DEFAULT_KMOD_FS="ext4" prior to running this -# script if the filesyste module you don't have loaded upon bootup +# script if the filesystem module you don't have loaded upon bootup # is ext4 instead. Refer to allow_user_defaults() for a list of user # override variables possible. # @@ -263,7 +263,7 @@ config_get_test_result() config_reset() { if ! echo -n "1" >"$DIR"/reset; then - echo "$0: reset shuld have worked" >&2 + echo "$0: reset should have worked" >&2 exit 1 fi } @@ -488,7 +488,7 @@ usage() echo Example uses: echo echo "${TEST_NAME}.sh -- executes all tests" - echo "${TEST_NAME}.sh -t 0008 -- Executes test ID 0008 number of times is recomended" + echo "${TEST_NAME}.sh -t 0008 -- Executes test ID 0008 number of times is recommended" echo "${TEST_NAME}.sh -w 0008 -- Watch test ID 0008 run until an error occurs" echo "${TEST_NAME}.sh -s 0008 -- Run test ID 0008 once" echo "${TEST_NAME}.sh -c 0008 3 -- Run test ID 0008 three times" From 399ea57a4c8bc5fdb71a024a6870b5767b2ef6d8 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 1 Jul 2019 14:04:31 +0100 Subject: [PATCH 274/823] selftests/x86: fix spelling mistake "FAILT" -> "FAIL" There is an spelling mistake in an a test error message. Fix it. Acked-by: Andy Lutomirski Signed-off-by: Colin Ian King Signed-off-by: Shuah Khan --- tools/testing/selftests/x86/test_vsyscall.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c index 4602326b8f5b..a4f4d4cf22c3 100644 --- a/tools/testing/selftests/x86/test_vsyscall.c +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -451,7 +451,7 @@ static int test_vsys_x(void) printf("[OK]\tExecuting the vsyscall page failed: #PF(0x%lx)\n", segv_err); } else { - printf("[FAILT]\tExecution failed with the wrong error: #PF(0x%lx)\n", + printf("[FAIL]\tExecution failed with the wrong error: #PF(0x%lx)\n", segv_err); return 1; } From d64b212ea960db4276a1d8372bd98cb861dfcbb0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Jul 2019 16:51:50 +0200 Subject: [PATCH 275/823] ARM: davinci: fix sleep.S build error on ARMv4 When building a multiplatform kernel that includes armv4 support, the default target CPU does not support the blx instruction, which leads to a build failure: arch/arm/mach-davinci/sleep.S: Assembler messages: arch/arm/mach-davinci/sleep.S:56: Error: selected processor does not support `blx ip' in ARM mode Add a .arch statement in the sources to make this file build. Link: https://lore.kernel.org/r/20190722145211.1154785-1-arnd@arndb.de Acked-by: Sekhar Nori Signed-off-by: Arnd Bergmann Signed-off-by: Olof Johansson --- arch/arm/mach-davinci/sleep.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/mach-davinci/sleep.S b/arch/arm/mach-davinci/sleep.S index 05d03f09ff54..71262dcdbca3 100644 --- a/arch/arm/mach-davinci/sleep.S +++ b/arch/arm/mach-davinci/sleep.S @@ -24,6 +24,7 @@ #define DEEPSLEEP_SLEEPENABLE_BIT BIT(31) .text + .arch armv5te /* * Move DaVinci into deep sleep state * From 3a9d2569e45cb02769cda26fee4a02126867c934 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Jul 2019 16:55:52 +0200 Subject: [PATCH 276/823] ARM: dts: bcm: bcm47094: add missing #cells for mdio-bus-mux The mdio-bus-mux has no #address-cells/#size-cells property, which causes a few dtc warnings: arch/arm/boot/dts/bcm47094-linksys-panamera.dts:129.4-18: Warning (reg_format): /mdio-bus-mux/mdio@200:reg: property has invalid length (4 bytes) (#address-cells == 2, #size-cells == 1) arch/arm/boot/dts/bcm47094-linksys-panamera.dtb: Warning (pci_device_bus_num): Failed prerequisite 'reg_format' arch/arm/boot/dts/bcm47094-linksys-panamera.dtb: Warning (i2c_bus_reg): Failed prerequisite 'reg_format' arch/arm/boot/dts/bcm47094-linksys-panamera.dtb: Warning (spi_bus_reg): Failed prerequisite 'reg_format' arch/arm/boot/dts/bcm47094-linksys-panamera.dts:128.22-132.5: Warning (avoid_default_addr_size): /mdio-bus-mux/mdio@200: Relying on default #address-cells value arch/arm/boot/dts/bcm47094-linksys-panamera.dts:128.22-132.5: Warning (avoid_default_addr_size): /mdio-bus-mux/mdio@200: Relying on default #size-cells value Add the normal cell numbers. Link: https://lore.kernel.org/r/20190722145618.1155492-1-arnd@arndb.de Fixes: 2bebdfcdcd0f ("ARM: dts: BCM5301X: Add support for Linksys EA9500") Signed-off-by: Arnd Bergmann Signed-off-by: Olof Johansson --- arch/arm/boot/dts/bcm47094-linksys-panamera.dts | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm/boot/dts/bcm47094-linksys-panamera.dts b/arch/arm/boot/dts/bcm47094-linksys-panamera.dts index 18d0ae46e76c..0faae8950375 100644 --- a/arch/arm/boot/dts/bcm47094-linksys-panamera.dts +++ b/arch/arm/boot/dts/bcm47094-linksys-panamera.dts @@ -124,6 +124,9 @@ }; mdio-bus-mux { + #address-cells = <1>; + #size-cells = <0>; + /* BIT(9) = 1 => external mdio */ mdio_ext: mdio@200 { reg = <0x200>; From 14d017bee4accf6ba80ed01b190e4f61b47d9327 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 23 Jul 2019 10:15:22 +0200 Subject: [PATCH 277/823] ARM: defconfig: u8500: Refresh defconfig This refreshes the outdated U8500 defconfig: some options moved around, PS/2 mouse is no longer default on, crypto options moved around etc. Link: https://lore.kernel.org/r/20190723081523.13079-1-linus.walleij@linaro.org Signed-off-by: Linus Walleij Signed-off-by: Olof Johansson --- arch/arm/configs/u8500_defconfig | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig index e6b98b6eb88d..215bd3cd6e34 100644 --- a/arch/arm/configs/u8500_defconfig +++ b/arch/arm/configs/u8500_defconfig @@ -4,17 +4,9 @@ CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BLK_DEV_INITRD=y CONFIG_KALLSYMS_ALL=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_PARTITION_ADVANCED=y CONFIG_ARCH_U8500=y -CONFIG_MACH_HREFV60=y -CONFIG_MACH_SNOWBALL=y CONFIG_SMP=y CONFIG_NR_CPUS=2 -CONFIG_PREEMPT=y -CONFIG_AEABI=y CONFIG_HIGHMEM=y CONFIG_ARM_APPENDED_DTB=y CONFIG_ARM_ATAG_DTB_COMPAT=y @@ -25,6 +17,10 @@ CONFIG_CPU_IDLE=y CONFIG_ARM_U8500_CPUIDLE=y CONFIG_VFP=y CONFIG_NEON=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_BLK_DEV_BSG is not set +CONFIG_PARTITION_ADVANCED=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -47,7 +43,6 @@ CONFIG_SMSC911X=y CONFIG_SMSC_PHY=y CONFIG_CW1200=y CONFIG_CW1200_WLAN_SDIO=y -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_EVDEV=y # CONFIG_KEYBOARD_ATKBD is not set CONFIG_KEYBOARD_GPIO=y @@ -126,20 +121,19 @@ CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y +CONFIG_CRYPTO_DEV_UX500=y +CONFIG_CRYPTO_DEV_UX500_CRYP=y +CONFIG_CRYPTO_DEV_UX500_HASH=y +CONFIG_CRYPTO_DEV_UX500_DEBUG=y CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y # CONFIG_SCHED_DEBUG is not set -# CONFIG_DEBUG_PREEMPT is not set # CONFIG_FTRACE is not set CONFIG_DEBUG_USER=y CONFIG_CORESIGHT=y CONFIG_CORESIGHT_SINK_TPIU=y CONFIG_CORESIGHT_SINK_ETBV10=y CONFIG_CORESIGHT_SOURCE_ETM3X=y -CONFIG_CRYPTO_DEV_UX500=y -CONFIG_CRYPTO_DEV_UX500_CRYP=y -CONFIG_CRYPTO_DEV_UX500_HASH=y -CONFIG_CRYPTO_DEV_UX500_DEBUG=y From 02a0242549aaec4490e9280cebbb1474b36281ca Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 23 Jul 2019 10:15:23 +0200 Subject: [PATCH 278/823] ARM: defconfig: u8500: Add new drivers This enables the new or updates driver options for U8500 that got merged into v5.3-rc1: - CMA, MCDE driver, LIMA driver and the Samsung S6D16D0 driver enabled by default bringing up the new graphics support. Include the LOGO so we can see when the graphics are live. - We use the IIO hwmon bridge for reflecting temperature in the system. - Set MUSB to PIO mode as this is the one working most stable for the time being. - HWSPINLOCK needs to be set to get the hardware semaphore driver to compile and link properly. Link: https://lore.kernel.org/r/20190723081523.13079-2-linus.walleij@linaro.org Signed-off-by: Linus Walleij Signed-off-by: Olof Johansson --- arch/arm/configs/u8500_defconfig | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig index 215bd3cd6e34..822cddfbf1af 100644 --- a/arch/arm/configs/u8500_defconfig +++ b/arch/arm/configs/u8500_defconfig @@ -21,6 +21,7 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y +CONFIG_CMA=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -58,7 +59,6 @@ CONFIG_RMI4_CORE=y CONFIG_RMI4_I2C=y CONFIG_RMI4_F11=y # CONFIG_SERIO is not set -CONFIG_VT_HW_CONSOLE_BINDING=y # CONFIG_LEGACY_PTYS is not set CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y @@ -67,6 +67,7 @@ CONFIG_SPI=y CONFIG_SPI_PL022=y CONFIG_GPIO_STMPE=y CONFIG_GPIO_TC3589X=y +CONFIG_SENSORS_IIO_HWMON=y CONFIG_THERMAL=y CONFIG_CPU_THERMAL=y CONFIG_WATCHDOG=y @@ -74,6 +75,13 @@ CONFIG_MFD_STMPE=y CONFIG_MFD_TC3589X=y CONFIG_REGULATOR_AB8500=y CONFIG_REGULATOR_GPIO=y +CONFIG_DRM=y +CONFIG_DRM_PANEL_SAMSUNG_S6D16D0=y +CONFIG_DRM_LIMA=y +CONFIG_DRM_MCDE=y +CONFIG_BACKLIGHT_CLASS_DEVICE=y +CONFIG_BACKLIGHT_GENERIC=m +CONFIG_LOGO=y CONFIG_SOUND=y CONFIG_SND=y CONFIG_SND_SOC=y @@ -82,6 +90,7 @@ CONFIG_SND_SOC_UX500_MACH_MOP500=y CONFIG_USB=y CONFIG_USB_MUSB_HDRC=y CONFIG_USB_MUSB_UX500=y +CONFIG_MUSB_PIO_ONLY=y CONFIG_AB8500_USB=y CONFIG_USB_GADGET=y CONFIG_USB_ETH=m @@ -98,6 +107,7 @@ CONFIG_RTC_DRV_AB8500=y CONFIG_RTC_DRV_PL031=y CONFIG_DMADEVICES=y CONFIG_STE_DMA40=y +CONFIG_HWSPINLOCK=y CONFIG_HSEM_U8500=y CONFIG_IIO=y CONFIG_IIO_SW_TRIGGER=y From efa7b79f675da0efafe3f32ba0d6efe916cf4867 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 23 Jul 2019 11:19:25 +0300 Subject: [PATCH 279/823] selftests: forwarding: gre_multipath: Enable IPv4 forwarding The test did not enable IPv4 forwarding during its setup phase, which causes the test to fail on machines where IPv4 forwarding is disabled. Fixes: 54818c4c4b93 ("selftests: forwarding: Test multipath tunneling") Signed-off-by: Ido Schimmel Reported-by: Stephen Suryaputra Tested-by: Stephen Suryaputra Signed-off-by: David S. Miller --- tools/testing/selftests/net/forwarding/gre_multipath.sh | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/net/forwarding/gre_multipath.sh b/tools/testing/selftests/net/forwarding/gre_multipath.sh index cca2baa03fb8..37d7297e1cf8 100755 --- a/tools/testing/selftests/net/forwarding/gre_multipath.sh +++ b/tools/testing/selftests/net/forwarding/gre_multipath.sh @@ -187,12 +187,16 @@ setup_prepare() sw1_create sw2_create h2_create + + forwarding_enable } cleanup() { pre_cleanup + forwarding_restore + h2_destroy sw2_destroy sw1_destroy From 1be79d89b7ae96e004911bd228ce8c2b5cc6415f Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 23 Jul 2019 11:19:26 +0300 Subject: [PATCH 280/823] selftests: forwarding: gre_multipath: Fix flower filters The TC filters used in the test do not work with veth devices because the outer Ethertype is 802.1Q and not IPv4. The test passes with mlxsw netdevs since the hardware always looks at "The first Ethertype that does not point to either: VLAN, CNTAG or configurable Ethertype". Fix this by matching on the VLAN ID instead, but on the ingress side. The reason why this is not performed at egress is explained in the commit cited below. Fixes: 541ad323db3a ("selftests: forwarding: gre_multipath: Update next-hop statistics match criteria") Signed-off-by: Ido Schimmel Reported-by: Stephen Suryaputra Tested-by: Stephen Suryaputra Signed-off-by: David S. Miller --- .../selftests/net/forwarding/gre_multipath.sh | 24 +++++++++---------- 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/gre_multipath.sh b/tools/testing/selftests/net/forwarding/gre_multipath.sh index 37d7297e1cf8..a8d8e8b3dc81 100755 --- a/tools/testing/selftests/net/forwarding/gre_multipath.sh +++ b/tools/testing/selftests/net/forwarding/gre_multipath.sh @@ -93,18 +93,10 @@ sw1_create() ip route add vrf v$ol1 192.0.2.16/28 \ nexthop dev g1a \ nexthop dev g1b - - tc qdisc add dev $ul1 clsact - tc filter add dev $ul1 egress pref 111 prot ipv4 \ - flower dst_ip 192.0.2.66 action pass - tc filter add dev $ul1 egress pref 222 prot ipv4 \ - flower dst_ip 192.0.2.82 action pass } sw1_destroy() { - tc qdisc del dev $ul1 clsact - ip route del vrf v$ol1 192.0.2.16/28 ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146 @@ -139,10 +131,18 @@ sw2_create() ip route add vrf v$ol2 192.0.2.0/28 \ nexthop dev g2a \ nexthop dev g2b + + tc qdisc add dev $ul2 clsact + tc filter add dev $ul2 ingress pref 111 prot 802.1Q \ + flower vlan_id 111 action pass + tc filter add dev $ul2 ingress pref 222 prot 802.1Q \ + flower vlan_id 222 action pass } sw2_destroy() { + tc qdisc del dev $ul2 clsact + ip route del vrf v$ol2 192.0.2.0/28 ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145 @@ -215,15 +215,15 @@ multipath4_test() nexthop dev g1a weight $weight1 \ nexthop dev g1b weight $weight2 - local t0_111=$(tc_rule_stats_get $ul1 111 egress) - local t0_222=$(tc_rule_stats_get $ul1 222 egress) + local t0_111=$(tc_rule_stats_get $ul2 111 ingress) + local t0_222=$(tc_rule_stats_get $ul2 222 ingress) ip vrf exec v$h1 \ $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \ -d 1msec -t udp "sp=1024,dp=0-32768" - local t1_111=$(tc_rule_stats_get $ul1 111 egress) - local t1_222=$(tc_rule_stats_get $ul1 222 egress) + local t1_111=$(tc_rule_stats_get $ul2 111 ingress) + local t1_222=$(tc_rule_stats_get $ul2 222 ingress) local d111=$((t1_111 - t0_111)) local d222=$((t1_222 - t0_222)) From 92e6475ae0a0383b012eb21c1aaf0e5456b1a3d9 Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Wed, 3 Jul 2019 10:02:39 -0400 Subject: [PATCH 281/823] drm/amd/display: Set enabled to false at start of audio disable [Why] In an effort to stop redundant calls to dce110_disable_audio_stream the audio->enabled flag was added to the audio resource struct. While this state probably shouldn't have been tracked on the audio struct itself it still works fine for some sequences. However, it does not work for cases where we're freeing the audio resource (such as hotplugs) or when dynamic audio is enabled. In these cases the pipe_ctx->stream_res.audio = NULL before we can set audio->enabled = false. The next time we acquire the audio resource such as on hotplug the audio will not be enabled for the stream since DC thinks it's still enabled. Audio state tracking should cover this sequence. [How] Set audio->enabled = false at the start as long as we have pipe_ctx->stream_res.audio. Signed-off-by: Nicholas Kazlauskas Reviewed-by: Zhan Liu Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 8005989c1263..fafb4b470140 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1021,6 +1021,8 @@ void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx, int option) pipe_ctx->stream_res.stream_enc->funcs->audio_mute_control( pipe_ctx->stream_res.stream_enc, true); if (pipe_ctx->stream_res.audio) { + pipe_ctx->stream_res.audio->enabled = false; + if (dc->res_pool->pp_smu) pp_smu = dc->res_pool->pp_smu; @@ -1051,8 +1053,6 @@ void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx, int option) /* dal_audio_disable_azalia_audio_jack_presence(stream->audio, * stream->stream_engine_id); */ - if (pipe_ctx->stream_res.audio) - pipe_ctx->stream_res.audio->enabled = false; } } From 78e420408d12eddd0e72613fc717f7994736ea9a Mon Sep 17 00:00:00 2001 From: Nishka Dasgupta Date: Tue, 23 Jul 2019 16:13:07 +0530 Subject: [PATCH 282/823] net: dsa: mv88e6xxx: chip: Add of_node_put() before return Each iteration of for_each_available_child_of_node puts the previous node, but in the case of a return from the middle of the loop, there is no put, thus causing a memory leak. Hence add an of_node_put before the return. Issue found with Coccinelle. Signed-off-by: Nishka Dasgupta Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 6b17cd961d06..c97dea4599a8 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2721,6 +2721,7 @@ static int mv88e6xxx_mdios_register(struct mv88e6xxx_chip *chip, err = mv88e6xxx_mdio_register(chip, child, true); if (err) { mv88e6xxx_mdios_unregister(chip); + of_node_put(child); return err; } } From 7ba771e3e246fa8787abf2cce9064ec8c9b38133 Mon Sep 17 00:00:00 2001 From: Nishka Dasgupta Date: Tue, 23 Jul 2019 16:14:48 +0530 Subject: [PATCH 283/823] net: dsa: sja1105: sja1105_main: Add of_node_put() Each iteration of for_each_child_of_node puts the previous node, but in the case of a return from the middle of the loop, there is no put, thus causing a memory leak. Hence add an of_node_put before the return. Issue found with Coccinelle. Signed-off-by: Nishka Dasgupta Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 32bf3a7cc3b6..6ed5f1e35789 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -625,6 +625,7 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, if (of_property_read_u32(child, "reg", &index) < 0) { dev_err(dev, "Port number not defined in device tree " "(property \"reg\")\n"); + of_node_put(child); return -ENODEV; } @@ -634,6 +635,7 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, dev_err(dev, "Failed to read phy-mode or " "phy-interface-type property for port %d\n", index); + of_node_put(child); return -ENODEV; } ports[index].phy_mode = phy_mode; @@ -643,6 +645,7 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, if (!of_phy_is_fixed_link(child)) { dev_err(dev, "phy-handle or fixed-link " "properties missing!\n"); + of_node_put(child); return -ENODEV; } /* phy-handle is missing, but fixed-link isn't. From a261e3797506bd561700be643fe1a85bf81e9661 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 Jul 2019 17:15:25 +0200 Subject: [PATCH 284/823] sky2: Disable MSI on ASUS P6T The onboard sky2 NIC on ASUS P6T WS PRO doesn't work after PM resume due to the infamous IRQ problem. Disabling MSI works around it, so let's add it to the blacklist. Unfortunately the BIOS on the machine doesn't fill the standard DMI_SYS_* entry, so we pick up DMI_BOARD_* entries instead. BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1142496 Reported-and-tested-by: Marcus Seyfarth Signed-off-by: Takashi Iwai Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/sky2.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index f518312ffe69..a01c75ede871 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4924,6 +4924,13 @@ static const struct dmi_system_id msi_blacklist[] = { DMI_MATCH(DMI_PRODUCT_NAME, "P5W DH Deluxe"), }, }, + { + .ident = "ASUS P6T", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), + DMI_MATCH(DMI_BOARD_NAME, "P6T"), + }, + }, {} }; From d9b8aadaffa65809d146cf0f8632a22a946367d7 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Fri, 19 Jul 2019 11:18:15 +0200 Subject: [PATCH 285/823] bpf: fix narrower loads on s390 The very first check in test_pkt_md_access is failing on s390, which happens because loading a part of a struct __sk_buff field produces an incorrect result. The preprocessed code of the check is: { __u8 tmp = *((volatile __u8 *)&skb->len + ((sizeof(skb->len) - sizeof(__u8)) / sizeof(__u8))); if (tmp != ((*(volatile __u32 *)&skb->len) & 0xFF)) return 2; }; clang generates the following code for it: 0: 71 21 00 03 00 00 00 00 r2 = *(u8 *)(r1 + 3) 1: 61 31 00 00 00 00 00 00 r3 = *(u32 *)(r1 + 0) 2: 57 30 00 00 00 00 00 ff r3 &= 255 3: 5d 23 00 1d 00 00 00 00 if r2 != r3 goto +29 Finally, verifier transforms it to: 0: (61) r2 = *(u32 *)(r1 +104) 1: (bc) w2 = w2 2: (74) w2 >>= 24 3: (bc) w2 = w2 4: (54) w2 &= 255 5: (bc) w2 = w2 The problem is that when verifier emits the code to replace a partial load of a struct __sk_buff field (*(u8 *)(r1 + 3)) with a full load of struct sk_buff field (*(u32 *)(r1 + 104)), an optional shift and a bitwise AND, it assumes that the machine is little endian and incorrectly decides to use a shift. Adjust shift count calculation to account for endianness. Fixes: 31fd85816dbe ("bpf: permits narrower load from bpf program context fields") Signed-off-by: Ilya Leoshkevich Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 13 +++++++++++++ kernel/bpf/verifier.c | 4 ++-- 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/include/linux/filter.h b/include/linux/filter.h index ff65d22cf336..92c6e31fb008 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -24,6 +24,7 @@ #include +#include #include #include @@ -747,6 +748,18 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) return size <= size_default && (size & (size - 1)) == 0; } +static inline u8 +bpf_ctx_narrow_load_shift(u32 off, u32 size, u32 size_default) +{ + u8 load_off = off & (size_default - 1); + +#ifdef __LITTLE_ENDIAN + return load_off * 8; +#else + return (size_default - (load_off + size)) * 8; +#endif +} + #define bpf_ctx_wide_access_ok(off, size, type, field) \ (size == sizeof(__u64) && \ off >= offsetof(type, field) && \ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5900cbb966b1..c84d83f86141 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8616,8 +8616,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } if (is_narrower_load && size < target_size) { - u8 shift = (off & (size_default - 1)) * 8; - + u8 shift = bpf_ctx_narrow_load_shift(off, size, + size_default); if (ctx_field_size <= 4) { if (shift) insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH, From d86afb89305de205b0d2f20c2160adf039e9508d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 23 Jul 2019 23:03:43 +0300 Subject: [PATCH 286/823] net: thunderx: Use fwnode_get_mac_address() Replace the custom implementation with fwnode_get_mac_address, which works on both DT and ACPI platforms. While here, replace memcpy() by ether_addr_copy(). Signed-off-by: Andy Shevchenko Signed-off-by: David S. Miller --- .../net/ethernet/cavium/thunder/thunder_bgx.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index ad22554857bf..acb016834f04 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1381,24 +1381,18 @@ static int acpi_get_mac_address(struct device *dev, struct acpi_device *adev, u8 *dst) { u8 mac[ETH_ALEN]; - int ret; + u8 *addr; - ret = fwnode_property_read_u8_array(acpi_fwnode_handle(adev), - "mac-address", mac, ETH_ALEN); - if (ret) - goto out; - - if (!is_valid_ether_addr(mac)) { + addr = fwnode_get_mac_address(acpi_fwnode_handle(adev), mac, ETH_ALEN); + if (!addr) { dev_err(dev, "MAC address invalid: %pM\n", mac); - ret = -EINVAL; - goto out; + return -EINVAL; } dev_info(dev, "MAC address set to: %pM\n", mac); - memcpy(dst, mac, ETH_ALEN); -out: - return ret; + ether_addr_copy(dst, mac); + return 0; } /* Currently only sets the MAC address. */ From 06a22d897d82f12776d44dbf0850f5895469cb2a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 23 Jul 2019 03:15:37 -0700 Subject: [PATCH 287/823] bpf: fix access to skb_shared_info->gso_segs It is possible we reach bpf_convert_ctx_access() with si->dst_reg == si->src_reg Therefore, we need to load BPF_REG_AX before eventually mangling si->src_reg. syzbot generated this x86 code : 3: 55 push %rbp 4: 48 89 e5 mov %rsp,%rbp 7: 48 81 ec 00 00 00 00 sub $0x0,%rsp // Might be avoided ? e: 53 push %rbx f: 41 55 push %r13 11: 41 56 push %r14 13: 41 57 push %r15 15: 6a 00 pushq $0x0 17: 31 c0 xor %eax,%eax 19: 48 8b bf c0 00 00 00 mov 0xc0(%rdi),%rdi 20: 44 8b 97 bc 00 00 00 mov 0xbc(%rdi),%r10d 27: 4c 01 d7 add %r10,%rdi 2a: 48 0f b7 7f 06 movzwq 0x6(%rdi),%rdi // Crash 2f: 5b pop %rbx 30: 41 5f pop %r15 32: 41 5e pop %r14 34: 41 5d pop %r13 36: 5b pop %rbx 37: c9 leaveq 38: c3 retq Fixes: d9ff286a0f59 ("bpf: allow BPF programs access skb_shared_info->gso_segs field") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: Alexei Starovoitov --- net/core/filter.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index 4e2a79b2fd77..7878f918b8c0 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7455,12 +7455,12 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, gso_segs): /* si->dst_reg = skb_shinfo(SKB); */ #ifdef NET_SKBUFF_DATA_USES_OFFSET - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), - si->dst_reg, si->src_reg, - offsetof(struct sk_buff, head)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, end)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, head)); *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); #else *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), From be69483bf4f3abaaca5d5ba460dbb50239463552 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 23 Jul 2019 03:15:38 -0700 Subject: [PATCH 288/823] selftests/bpf: add another gso_segs access Use BPF_REG_1 for source and destination of gso_segs read, to exercise "bpf: fix access to skb_shared_info->gso_segs" fix. Signed-off-by: Eric Dumazet Suggested-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/verifier/ctx_skb.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c index b0fda2877119..d438193804b2 100644 --- a/tools/testing/selftests/bpf/verifier/ctx_skb.c +++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c @@ -974,6 +974,17 @@ .result = ACCEPT, .prog_type = BPF_PROG_TYPE_CGROUP_SKB, }, +{ + "read gso_segs from CGROUP_SKB", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, + offsetof(struct __sk_buff, gso_segs)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, { "write gso_segs from CGROUP_SKB", .insns = { From decb705e01a5d325c9876b9674043cde4b54f0db Mon Sep 17 00:00:00 2001 From: Ilya Maximets Date: Tue, 23 Jul 2019 15:08:10 +0300 Subject: [PATCH 289/823] libbpf: fix using uninitialized ioctl results 'channels.max_combined' initialized only on ioctl success and errno is only valid on ioctl failure. The code doesn't produce any runtime issues, but makes memory sanitizers angry: Conditional jump or move depends on uninitialised value(s) at 0x55C056F: xsk_get_max_queues (xsk.c:336) by 0x55C05B2: xsk_create_bpf_maps (xsk.c:354) by 0x55C089F: xsk_setup_xdp_prog (xsk.c:447) by 0x55C0E57: xsk_socket__create (xsk.c:601) Uninitialised value was created by a stack allocation at 0x55C04CD: xsk_get_max_queues (xsk.c:318) Additionally fixed warning on uninitialized bytes in ioctl arguments: Syscall param ioctl(SIOCETHTOOL) points to uninitialised byte(s) at 0x648D45B: ioctl (in /usr/lib64/libc-2.28.so) by 0x55C0546: xsk_get_max_queues (xsk.c:330) by 0x55C05B2: xsk_create_bpf_maps (xsk.c:354) by 0x55C089F: xsk_setup_xdp_prog (xsk.c:447) by 0x55C0E57: xsk_socket__create (xsk.c:601) Address 0x1ffefff378 is on thread 1's stack in frame #1, created by xsk_get_max_queues (xsk.c:318) Uninitialised value was created by a stack allocation at 0x55C04CD: xsk_get_max_queues (xsk.c:318) CC: Magnus Karlsson Fixes: 1cad07884239 ("libbpf: add support for using AF_XDP sockets") Signed-off-by: Ilya Maximets Acked-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/xsk.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 5007b5d4fd2c..e02025bbe36d 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -317,15 +317,14 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) static int xsk_get_max_queues(struct xsk_socket *xsk) { - struct ethtool_channels channels; - struct ifreq ifr; + struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS }; + struct ifreq ifr = {}; int fd, err, ret; fd = socket(AF_INET, SOCK_DGRAM, 0); if (fd < 0) return -errno; - channels.cmd = ETHTOOL_GCHANNELS; ifr.ifr_data = (void *)&channels; strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1); ifr.ifr_name[IFNAMSIZ - 1] = '\0'; @@ -335,7 +334,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk) goto out; } - if (channels.max_combined == 0 || errno == EOPNOTSUPP) + if (err || channels.max_combined == 0) /* If the device says it has no channels, then all traffic * is sent to a single stream, so max queues = 1. */ From 359603a3847e58843881db87e5f464bb85539e95 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Sat, 20 Jul 2019 22:58:40 +0100 Subject: [PATCH 290/823] scsi: megaraid_sas: fix spelling mistake "megarid_sas" -> "megaraid_sas" Fix spelling mistake in kernel warning message and replace printk with with pr_warn. Signed-off-by: Colin Ian King Acked-by: Sumit Saxena Signed-off-by: Martin K. Petersen --- drivers/scsi/megaraid/megaraid_sas_base.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index b2339d04a700..2590746c81e3 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -8763,7 +8763,7 @@ static int __init megasas_init(void) if ((event_log_level < MFI_EVT_CLASS_DEBUG) || (event_log_level > MFI_EVT_CLASS_DEAD)) { - printk(KERN_WARNING "megarid_sas: provided event log level is out of range, setting it to default 2(CLASS_CRITICAL), permissible range is: -2 to 4\n"); + pr_warn("megaraid_sas: provided event log level is out of range, setting it to default 2(CLASS_CRITICAL), permissible range is: -2 to 4\n"); event_log_level = MFI_EVT_CLASS_CRITICAL; } From 3b5f307ef3cb5022bfe3c8ca5b8f2114d5bf6c29 Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Mon, 22 Jul 2019 09:15:24 -0700 Subject: [PATCH 291/823] scsi: megaraid_sas: fix panic on loading firmware crashdump While loading fw crashdump in function fw_crash_buffer_show(), left bytes in one dma chunk was not checked, if copying size over it, overflow access will cause kernel panic. Signed-off-by: Junxiao Bi Acked-by: Sumit Saxena Signed-off-by: Martin K. Petersen --- drivers/scsi/megaraid/megaraid_sas_base.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 2590746c81e3..f9f07935556e 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -3163,6 +3163,7 @@ fw_crash_buffer_show(struct device *cdev, (struct megasas_instance *) shost->hostdata; u32 size; unsigned long dmachunk = CRASH_DMA_BUF_SIZE; + unsigned long chunk_left_bytes; unsigned long src_addr; unsigned long flags; u32 buff_offset; @@ -3186,6 +3187,8 @@ fw_crash_buffer_show(struct device *cdev, } size = (instance->fw_crash_buffer_size * dmachunk) - buff_offset; + chunk_left_bytes = dmachunk - (buff_offset % dmachunk); + size = (size > chunk_left_bytes) ? chunk_left_bytes : size; size = (size >= PAGE_SIZE) ? (PAGE_SIZE - 1) : size; src_addr = (unsigned long)instance->crash_buf[buff_offset / dmachunk] + From e45ab43b1d404c5a9bacf565652421e8541c9f26 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Tue, 23 Jul 2019 22:34:50 +0800 Subject: [PATCH 292/823] scsi: megaraid_sas: Make some functions static Fix sparse warnings: drivers/scsi/megaraid/megaraid_sas_fusion.c:541:1: warning: symbol 'megasas_alloc_cmdlist_fusion' was not declared. Should it be static? drivers/scsi/megaraid/megaraid_sas_fusion.c:580:1: warning: symbol 'megasas_alloc_request_fusion' was not declared. Should it be static? drivers/scsi/megaraid/megaraid_sas_fusion.c:661:1: warning: symbol 'megasas_alloc_reply_fusion' was not declared. Should it be static? drivers/scsi/megaraid/megaraid_sas_fusion.c:738:1: warning: symbol 'megasas_alloc_rdpq_fusion' was not declared. Should it be static? drivers/scsi/megaraid/megaraid_sas_fusion.c:920:1: warning: symbol 'megasas_alloc_cmds_fusion' was not declared. Should it be static? drivers/scsi/megaraid/megaraid_sas_fusion.c:1740:1: warning: symbol 'megasas_init_adapter_fusion' was not declared. Should it be static? drivers/scsi/megaraid/megaraid_sas_fusion.c:1966:1: warning: symbol 'map_cmd_status' was not declared. Should it be static? drivers/scsi/megaraid/megaraid_sas_fusion.c:2379:1: warning: symbol 'megasas_set_pd_lba' was not declared. Should it be static? drivers/scsi/megaraid/megaraid_sas_fusion.c:2718:1: warning: symbol 'megasas_build_ldio_fusion' was not declared. Should it be static? drivers/scsi/megaraid/megaraid_sas_fusion.c:3215:1: warning: symbol 'megasas_build_io_fusion' was not declared. Should it be static? drivers/scsi/megaraid/megaraid_sas_fusion.c:3328:6: warning: symbol 'megasas_prepare_secondRaid1_IO' was not declared. Should it be static? Reported-by: Hulk Robot Signed-off-by: YueHaibing Acked-by: Sumit Saxena Signed-off-by: Martin K. Petersen --- drivers/scsi/megaraid/megaraid_sas_fusion.c | 27 +++++++++++---------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index a32b3f0fcd15..120e3c4de8c2 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -537,7 +537,7 @@ static int megasas_create_sg_sense_fusion(struct megasas_instance *instance) return 0; } -int +static int megasas_alloc_cmdlist_fusion(struct megasas_instance *instance) { u32 max_mpt_cmd, i, j; @@ -576,7 +576,8 @@ megasas_alloc_cmdlist_fusion(struct megasas_instance *instance) return 0; } -int + +static int megasas_alloc_request_fusion(struct megasas_instance *instance) { struct fusion_context *fusion; @@ -657,7 +658,7 @@ retry_alloc: return 0; } -int +static int megasas_alloc_reply_fusion(struct megasas_instance *instance) { int i, count; @@ -734,7 +735,7 @@ megasas_alloc_reply_fusion(struct megasas_instance *instance) return 0; } -int +static int megasas_alloc_rdpq_fusion(struct megasas_instance *instance) { int i, j, k, msix_count; @@ -916,7 +917,7 @@ megasas_free_reply_fusion(struct megasas_instance *instance) { * and is used as SMID of the cmd. * SMID value range is from 1 to max_fw_cmds. */ -int +static int megasas_alloc_cmds_fusion(struct megasas_instance *instance) { int i; @@ -1736,7 +1737,7 @@ static inline void megasas_free_ioc_init_cmd(struct megasas_instance *instance) * * This is the main function for initializing firmware. */ -u32 +static u32 megasas_init_adapter_fusion(struct megasas_instance *instance) { struct fusion_context *fusion; @@ -1962,7 +1963,7 @@ megasas_fusion_stop_watchdog(struct megasas_instance *instance) * @ext_status : ext status of cmd returned by FW */ -void +static void map_cmd_status(struct fusion_context *fusion, struct scsi_cmnd *scmd, u8 status, u8 ext_status, u32 data_length, u8 *sense) @@ -2375,7 +2376,7 @@ int megasas_make_sgl(struct megasas_instance *instance, struct scsi_cmnd *scp, * * Used to set the PD LBA in CDB for FP IOs */ -void +static void megasas_set_pd_lba(struct MPI2_RAID_SCSI_IO_REQUEST *io_request, u8 cdb_len, struct IO_REQUEST_INFO *io_info, struct scsi_cmnd *scp, struct MR_DRV_RAID_MAP_ALL *local_map_ptr, u32 ref_tag) @@ -2714,7 +2715,7 @@ megasas_set_raidflag_cpu_affinity(struct fusion_context *fusion, * Prepares the io_request and chain elements (sg_frame) for IO * The IO can be for PD (Fast Path) or LD */ -void +static void megasas_build_ldio_fusion(struct megasas_instance *instance, struct scsi_cmnd *scp, struct megasas_cmd_fusion *cmd) @@ -3211,7 +3212,7 @@ megasas_build_syspd_fusion(struct megasas_instance *instance, * Invokes helper functions to prepare request frames * and sets flags appropriate for IO/Non-IO cmd */ -int +static int megasas_build_io_fusion(struct megasas_instance *instance, struct scsi_cmnd *scp, struct megasas_cmd_fusion *cmd) @@ -3325,9 +3326,9 @@ megasas_get_request_descriptor(struct megasas_instance *instance, u16 index) /* megasas_prepate_secondRaid1_IO * It prepares the raid 1 second IO */ -void megasas_prepare_secondRaid1_IO(struct megasas_instance *instance, - struct megasas_cmd_fusion *cmd, - struct megasas_cmd_fusion *r1_cmd) +static void megasas_prepare_secondRaid1_IO(struct megasas_instance *instance, + struct megasas_cmd_fusion *cmd, + struct megasas_cmd_fusion *r1_cmd) { union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc, *req_desc2 = NULL; struct fusion_context *fusion; From 5523ca8f624dc9268bda109d37cbdc3efb5e79be Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 21 Jul 2019 14:50:39 +0200 Subject: [PATCH 293/823] scsi: fcoe: fix a typo #define relative to FCOE CTLR start with FCOE_CTLR, except FCOE_CTRL_SOL_TOV. This is likely a typo and CTRL should be CTLR here as well. Signed-off-by: Christophe JAILLET Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/scsi/fcoe/fcoe_ctlr.c | 2 +- include/scsi/libfcoe.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index 590ec8009f52..1a85fe9e4b7b 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -1019,7 +1019,7 @@ static void fcoe_ctlr_recv_adv(struct fcoe_ctlr *fip, struct sk_buff *skb) { struct fcoe_fcf *fcf; struct fcoe_fcf new; - unsigned long sol_tov = msecs_to_jiffies(FCOE_CTRL_SOL_TOV); + unsigned long sol_tov = msecs_to_jiffies(FCOE_CTLR_SOL_TOV); int first = 0; int mtu_valid; int found = 0; diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h index c50fb297e265..dc14b52577f7 100644 --- a/include/scsi/libfcoe.h +++ b/include/scsi/libfcoe.h @@ -31,7 +31,7 @@ * FIP tunable parameters. */ #define FCOE_CTLR_START_DELAY 2000 /* mS after first adv. to choose FCF */ -#define FCOE_CTRL_SOL_TOV 2000 /* min. solicitation interval (mS) */ +#define FCOE_CTLR_SOL_TOV 2000 /* min. solicitation interval (mS) */ #define FCOE_CTLR_FCF_LIMIT 20 /* max. number of FCF entries */ #define FCOE_CTLR_VN2VN_LOGIN_LIMIT 3 /* max. VN2VN rport login retries */ From 5578257ca0e21056821e6481bd534ba267b84e58 Mon Sep 17 00:00:00 2001 From: Tyrel Datwyler Date: Wed, 17 Jul 2019 14:48:27 -0500 Subject: [PATCH 294/823] scsi: ibmvfc: fix WARN_ON during event pool release While removing an ibmvfc client adapter a WARN_ON like the following WARN_ON is seen in the kernel log: WARNING: CPU: 6 PID: 5421 at ./include/linux/dma-mapping.h:541 ibmvfc_free_event_pool+0x12c/0x1f0 [ibmvfc] CPU: 6 PID: 5421 Comm: rmmod Tainted: G E 4.17.0-rc1-next-20180419-autotest #1 NIP: d00000000290328c LR: d00000000290325c CTR: c00000000036ee20 REGS: c000000288d1b7e0 TRAP: 0700 Tainted: G E (4.17.0-rc1-next-20180419-autotest) MSR: 800000010282b033 CR: 44008828 XER: 20000000 CFAR: c00000000036e408 SOFTE: 1 GPR00: d00000000290325c c000000288d1ba60 d000000002917900 c000000289d75448 GPR04: 0000000000000071 c0000000ff870000 0000000018040000 0000000000000001 GPR08: 0000000000000000 c00000000156e838 0000000000000001 d00000000290c640 GPR12: c00000000036ee20 c00000001ec4dc00 0000000000000000 0000000000000000 GPR16: 0000000000000000 0000000000000000 00000100276901e0 0000000010020598 GPR20: 0000000010020550 0000000010020538 0000000010020578 00000000100205b0 GPR24: 0000000000000000 0000000000000000 0000000010020590 5deadbeef0000100 GPR28: 5deadbeef0000200 d000000002910b00 0000000000000071 c0000002822f87d8 NIP [d00000000290328c] ibmvfc_free_event_pool+0x12c/0x1f0 [ibmvfc] LR [d00000000290325c] ibmvfc_free_event_pool+0xfc/0x1f0 [ibmvfc] Call Trace: [c000000288d1ba60] [d00000000290325c] ibmvfc_free_event_pool+0xfc/0x1f0 [ibmvfc] (unreliable) [c000000288d1baf0] [d000000002909390] ibmvfc_abort_task_set+0x7b0/0x8b0 [ibmvfc] [c000000288d1bb70] [c0000000000d8c68] vio_bus_remove+0x68/0x100 [c000000288d1bbb0] [c0000000007da7c4] device_release_driver_internal+0x1f4/0x2d0 [c000000288d1bc00] [c0000000007da95c] driver_detach+0x7c/0x100 [c000000288d1bc40] [c0000000007d8af4] bus_remove_driver+0x84/0x140 [c000000288d1bcb0] [c0000000007db6ac] driver_unregister+0x4c/0xa0 [c000000288d1bd20] [c0000000000d6e7c] vio_unregister_driver+0x2c/0x50 [c000000288d1bd50] [d00000000290ba0c] cleanup_module+0x24/0x15e0 [ibmvfc] [c000000288d1bd70] [c0000000001dadb0] sys_delete_module+0x220/0x2d0 [c000000288d1be30] [c00000000000b284] system_call+0x58/0x6c Instruction dump: e8410018 e87f0068 809f0078 e8bf0080 e8df0088 2fa30000 419e008c e9230200 2fa90000 419e0080 894d098a 794a07e0 <0b0a0000> e9290008 2fa90000 419e0028 This is tripped as a result of irqs being disabled during the call to dma_free_coherent() by ibmvfc_free_event_pool(). At this point in the code path we have quiesced the adapter and its overly paranoid anyways to be holding the host lock. Reported-by: Abdul Haleem Signed-off-by: Tyrel Datwyler Signed-off-by: Martin K. Petersen --- drivers/scsi/ibmvscsi/ibmvfc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index acd16e0d52cf..8cdbac076a1b 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -4864,8 +4864,8 @@ static int ibmvfc_remove(struct vio_dev *vdev) spin_lock_irqsave(vhost->host->host_lock, flags); ibmvfc_purge_requests(vhost, DID_ERROR); - ibmvfc_free_event_pool(vhost); spin_unlock_irqrestore(vhost->host->host_lock, flags); + ibmvfc_free_event_pool(vhost); ibmvfc_free_mem(vhost); spin_lock(&ibmvfc_driver_lock); From 20122994e38aef0ae50555884d287adde6641c94 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Fri, 12 Jul 2019 08:53:47 +0200 Subject: [PATCH 295/823] scsi: scsi_dh_alua: always use a 2 second delay before retrying RTPG Retrying immediately after we've received a 'transitioning' sense code is pretty much pointless, we should always use a delay before retrying. So ensure the default delay is applied before retrying. Signed-off-by: Hannes Reinecke Tested-by: Zhangguanghui Signed-off-by: Martin K. Petersen --- drivers/scsi/device_handler/scsi_dh_alua.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index f0066f8a1786..4971104b1817 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -40,6 +40,7 @@ #define ALUA_FAILOVER_TIMEOUT 60 #define ALUA_FAILOVER_RETRIES 5 #define ALUA_RTPG_DELAY_MSECS 5 +#define ALUA_RTPG_RETRY_DELAY 2 /* device handler flags */ #define ALUA_OPTIMIZE_STPG 0x01 @@ -682,7 +683,7 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) case SCSI_ACCESS_STATE_TRANSITIONING: if (time_before(jiffies, pg->expiry)) { /* State transition, retry */ - pg->interval = 2; + pg->interval = ALUA_RTPG_RETRY_DELAY; err = SCSI_DH_RETRY; } else { struct alua_dh_data *h; @@ -807,6 +808,8 @@ static void alua_rtpg_work(struct work_struct *work) spin_lock_irqsave(&pg->lock, flags); pg->flags &= ~ALUA_PG_RUNNING; pg->flags |= ALUA_PG_RUN_RTPG; + if (!pg->interval) + pg->interval = ALUA_RTPG_RETRY_DELAY; spin_unlock_irqrestore(&pg->lock, flags); queue_delayed_work(kaluad_wq, &pg->rtpg_work, pg->interval * HZ); @@ -818,6 +821,8 @@ static void alua_rtpg_work(struct work_struct *work) spin_lock_irqsave(&pg->lock, flags); if (err == SCSI_DH_RETRY || pg->flags & ALUA_PG_RUN_RTPG) { pg->flags &= ~ALUA_PG_RUNNING; + if (!pg->interval && !(pg->flags & ALUA_PG_RUN_RTPG)) + pg->interval = ALUA_RTPG_RETRY_DELAY; pg->flags |= ALUA_PG_RUN_RTPG; spin_unlock_irqrestore(&pg->lock, flags); queue_delayed_work(kaluad_wq, &pg->rtpg_work, From 2f5947dfcaecb99f2dd559156eecbeb7b95e4c02 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 24 Jul 2019 09:24:49 +0200 Subject: [PATCH 296/823] Documentation: move Documentation/virtual to Documentation/virt Renaming docs seems to be en vogue at the moment, so fix on of the grossly misnamed directories. We usually never use "virtual" as a shortcut for virtualization in the kernel, but always virt, as seen in the virt/ top-level directory. Fix up the documentation to match that. Fixes: ed16648eb5b8 ("Move kvm, uml, and lguest subdirectories under a common "virtual" directory, I.E:") Signed-off-by: Christoph Hellwig Signed-off-by: Paolo Bonzini --- Documentation/admin-guide/kernel-parameters.txt | 2 +- Documentation/{virtual => virt}/index.rst | 0 .../{virtual => virt}/kvm/amd-memory-encryption.rst | 0 Documentation/{virtual => virt}/kvm/api.txt | 2 +- Documentation/{virtual => virt}/kvm/arm/hyp-abi.txt | 0 Documentation/{virtual => virt}/kvm/arm/psci.txt | 0 Documentation/{virtual => virt}/kvm/cpuid.rst | 0 Documentation/{virtual => virt}/kvm/devices/README | 0 .../{virtual => virt}/kvm/devices/arm-vgic-its.txt | 0 Documentation/{virtual => virt}/kvm/devices/arm-vgic-v3.txt | 0 Documentation/{virtual => virt}/kvm/devices/arm-vgic.txt | 0 Documentation/{virtual => virt}/kvm/devices/mpic.txt | 0 Documentation/{virtual => virt}/kvm/devices/s390_flic.txt | 0 Documentation/{virtual => virt}/kvm/devices/vcpu.txt | 0 Documentation/{virtual => virt}/kvm/devices/vfio.txt | 0 Documentation/{virtual => virt}/kvm/devices/vm.txt | 0 Documentation/{virtual => virt}/kvm/devices/xics.txt | 0 Documentation/{virtual => virt}/kvm/devices/xive.txt | 0 Documentation/{virtual => virt}/kvm/halt-polling.txt | 0 Documentation/{virtual => virt}/kvm/hypercalls.txt | 4 ++-- Documentation/{virtual => virt}/kvm/index.rst | 0 Documentation/{virtual => virt}/kvm/locking.txt | 0 Documentation/{virtual => virt}/kvm/mmu.txt | 2 +- Documentation/{virtual => virt}/kvm/msr.txt | 0 Documentation/{virtual => virt}/kvm/nested-vmx.txt | 0 Documentation/{virtual => virt}/kvm/ppc-pv.txt | 0 Documentation/{virtual => virt}/kvm/review-checklist.txt | 2 +- Documentation/{virtual => virt}/kvm/s390-diag.txt | 0 Documentation/{virtual => virt}/kvm/timekeeping.txt | 0 Documentation/{virtual => virt}/kvm/vcpu-requests.rst | 0 Documentation/{virtual => virt}/paravirt_ops.rst | 0 Documentation/{virtual => virt}/uml/UserModeLinux-HOWTO.txt | 0 MAINTAINERS | 6 +++--- arch/powerpc/include/uapi/asm/kvm_para.h | 2 +- arch/x86/kvm/mmu.c | 2 +- include/uapi/linux/kvm.h | 4 ++-- tools/include/uapi/linux/kvm.h | 4 ++-- virt/kvm/arm/arm.c | 2 +- virt/kvm/arm/vgic/vgic-mmio-v3.c | 2 +- virt/kvm/arm/vgic/vgic.h | 4 ++-- 40 files changed, 19 insertions(+), 19 deletions(-) rename Documentation/{virtual => virt}/index.rst (100%) rename Documentation/{virtual => virt}/kvm/amd-memory-encryption.rst (100%) rename Documentation/{virtual => virt}/kvm/api.txt (99%) rename Documentation/{virtual => virt}/kvm/arm/hyp-abi.txt (100%) rename Documentation/{virtual => virt}/kvm/arm/psci.txt (100%) rename Documentation/{virtual => virt}/kvm/cpuid.rst (100%) rename Documentation/{virtual => virt}/kvm/devices/README (100%) rename Documentation/{virtual => virt}/kvm/devices/arm-vgic-its.txt (100%) rename Documentation/{virtual => virt}/kvm/devices/arm-vgic-v3.txt (100%) rename Documentation/{virtual => virt}/kvm/devices/arm-vgic.txt (100%) rename Documentation/{virtual => virt}/kvm/devices/mpic.txt (100%) rename Documentation/{virtual => virt}/kvm/devices/s390_flic.txt (100%) rename Documentation/{virtual => virt}/kvm/devices/vcpu.txt (100%) rename Documentation/{virtual => virt}/kvm/devices/vfio.txt (100%) rename Documentation/{virtual => virt}/kvm/devices/vm.txt (100%) rename Documentation/{virtual => virt}/kvm/devices/xics.txt (100%) rename Documentation/{virtual => virt}/kvm/devices/xive.txt (100%) rename Documentation/{virtual => virt}/kvm/halt-polling.txt (100%) rename Documentation/{virtual => virt}/kvm/hypercalls.txt (97%) rename Documentation/{virtual => virt}/kvm/index.rst (100%) rename Documentation/{virtual => virt}/kvm/locking.txt (100%) rename Documentation/{virtual => virt}/kvm/mmu.txt (99%) rename Documentation/{virtual => virt}/kvm/msr.txt (100%) rename Documentation/{virtual => virt}/kvm/nested-vmx.txt (100%) rename Documentation/{virtual => virt}/kvm/ppc-pv.txt (100%) rename Documentation/{virtual => virt}/kvm/review-checklist.txt (95%) rename Documentation/{virtual => virt}/kvm/s390-diag.txt (100%) rename Documentation/{virtual => virt}/kvm/timekeeping.txt (100%) rename Documentation/{virtual => virt}/kvm/vcpu-requests.rst (100%) rename Documentation/{virtual => virt}/paravirt_ops.rst (100%) rename Documentation/{virtual => virt}/uml/UserModeLinux-HOWTO.txt (100%) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 099c5a4be95b..8a8880cec34b 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2532,7 +2532,7 @@ mem_encrypt=on: Activate SME mem_encrypt=off: Do not activate SME - Refer to Documentation/virtual/kvm/amd-memory-encryption.rst + Refer to Documentation/virt/kvm/amd-memory-encryption.rst for details on when memory encryption can be activated. mem_sleep_default= [SUSPEND] Default system suspend mode: diff --git a/Documentation/virtual/index.rst b/Documentation/virt/index.rst similarity index 100% rename from Documentation/virtual/index.rst rename to Documentation/virt/index.rst diff --git a/Documentation/virtual/kvm/amd-memory-encryption.rst b/Documentation/virt/kvm/amd-memory-encryption.rst similarity index 100% rename from Documentation/virtual/kvm/amd-memory-encryption.rst rename to Documentation/virt/kvm/amd-memory-encryption.rst diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virt/kvm/api.txt similarity index 99% rename from Documentation/virtual/kvm/api.txt rename to Documentation/virt/kvm/api.txt index e54a3f51ddc5..2d067767b617 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virt/kvm/api.txt @@ -3781,7 +3781,7 @@ encrypted VMs. Currently, this ioctl is used for issuing Secure Encrypted Virtualization (SEV) commands on AMD Processors. The SEV commands are defined in -Documentation/virtual/kvm/amd-memory-encryption.rst. +Documentation/virt/kvm/amd-memory-encryption.rst. 4.111 KVM_MEMORY_ENCRYPT_REG_REGION diff --git a/Documentation/virtual/kvm/arm/hyp-abi.txt b/Documentation/virt/kvm/arm/hyp-abi.txt similarity index 100% rename from Documentation/virtual/kvm/arm/hyp-abi.txt rename to Documentation/virt/kvm/arm/hyp-abi.txt diff --git a/Documentation/virtual/kvm/arm/psci.txt b/Documentation/virt/kvm/arm/psci.txt similarity index 100% rename from Documentation/virtual/kvm/arm/psci.txt rename to Documentation/virt/kvm/arm/psci.txt diff --git a/Documentation/virtual/kvm/cpuid.rst b/Documentation/virt/kvm/cpuid.rst similarity index 100% rename from Documentation/virtual/kvm/cpuid.rst rename to Documentation/virt/kvm/cpuid.rst diff --git a/Documentation/virtual/kvm/devices/README b/Documentation/virt/kvm/devices/README similarity index 100% rename from Documentation/virtual/kvm/devices/README rename to Documentation/virt/kvm/devices/README diff --git a/Documentation/virtual/kvm/devices/arm-vgic-its.txt b/Documentation/virt/kvm/devices/arm-vgic-its.txt similarity index 100% rename from Documentation/virtual/kvm/devices/arm-vgic-its.txt rename to Documentation/virt/kvm/devices/arm-vgic-its.txt diff --git a/Documentation/virtual/kvm/devices/arm-vgic-v3.txt b/Documentation/virt/kvm/devices/arm-vgic-v3.txt similarity index 100% rename from Documentation/virtual/kvm/devices/arm-vgic-v3.txt rename to Documentation/virt/kvm/devices/arm-vgic-v3.txt diff --git a/Documentation/virtual/kvm/devices/arm-vgic.txt b/Documentation/virt/kvm/devices/arm-vgic.txt similarity index 100% rename from Documentation/virtual/kvm/devices/arm-vgic.txt rename to Documentation/virt/kvm/devices/arm-vgic.txt diff --git a/Documentation/virtual/kvm/devices/mpic.txt b/Documentation/virt/kvm/devices/mpic.txt similarity index 100% rename from Documentation/virtual/kvm/devices/mpic.txt rename to Documentation/virt/kvm/devices/mpic.txt diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virt/kvm/devices/s390_flic.txt similarity index 100% rename from Documentation/virtual/kvm/devices/s390_flic.txt rename to Documentation/virt/kvm/devices/s390_flic.txt diff --git a/Documentation/virtual/kvm/devices/vcpu.txt b/Documentation/virt/kvm/devices/vcpu.txt similarity index 100% rename from Documentation/virtual/kvm/devices/vcpu.txt rename to Documentation/virt/kvm/devices/vcpu.txt diff --git a/Documentation/virtual/kvm/devices/vfio.txt b/Documentation/virt/kvm/devices/vfio.txt similarity index 100% rename from Documentation/virtual/kvm/devices/vfio.txt rename to Documentation/virt/kvm/devices/vfio.txt diff --git a/Documentation/virtual/kvm/devices/vm.txt b/Documentation/virt/kvm/devices/vm.txt similarity index 100% rename from Documentation/virtual/kvm/devices/vm.txt rename to Documentation/virt/kvm/devices/vm.txt diff --git a/Documentation/virtual/kvm/devices/xics.txt b/Documentation/virt/kvm/devices/xics.txt similarity index 100% rename from Documentation/virtual/kvm/devices/xics.txt rename to Documentation/virt/kvm/devices/xics.txt diff --git a/Documentation/virtual/kvm/devices/xive.txt b/Documentation/virt/kvm/devices/xive.txt similarity index 100% rename from Documentation/virtual/kvm/devices/xive.txt rename to Documentation/virt/kvm/devices/xive.txt diff --git a/Documentation/virtual/kvm/halt-polling.txt b/Documentation/virt/kvm/halt-polling.txt similarity index 100% rename from Documentation/virtual/kvm/halt-polling.txt rename to Documentation/virt/kvm/halt-polling.txt diff --git a/Documentation/virtual/kvm/hypercalls.txt b/Documentation/virt/kvm/hypercalls.txt similarity index 97% rename from Documentation/virtual/kvm/hypercalls.txt rename to Documentation/virt/kvm/hypercalls.txt index da210651f714..5f6d291bd004 100644 --- a/Documentation/virtual/kvm/hypercalls.txt +++ b/Documentation/virt/kvm/hypercalls.txt @@ -18,7 +18,7 @@ S390: number in R1. For further information on the S390 diagnose call as supported by KVM, - refer to Documentation/virtual/kvm/s390-diag.txt. + refer to Documentation/virt/kvm/s390-diag.txt. PowerPC: It uses R3-R10 and hypercall number in R11. R4-R11 are used as output registers. @@ -26,7 +26,7 @@ S390: KVM hypercalls uses 4 byte opcode, that are patched with 'hypercall-instructions' property inside the device tree's /hypervisor node. - For more information refer to Documentation/virtual/kvm/ppc-pv.txt + For more information refer to Documentation/virt/kvm/ppc-pv.txt MIPS: KVM hypercalls use the HYPCALL instruction with code 0 and the hypercall diff --git a/Documentation/virtual/kvm/index.rst b/Documentation/virt/kvm/index.rst similarity index 100% rename from Documentation/virtual/kvm/index.rst rename to Documentation/virt/kvm/index.rst diff --git a/Documentation/virtual/kvm/locking.txt b/Documentation/virt/kvm/locking.txt similarity index 100% rename from Documentation/virtual/kvm/locking.txt rename to Documentation/virt/kvm/locking.txt diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virt/kvm/mmu.txt similarity index 99% rename from Documentation/virtual/kvm/mmu.txt rename to Documentation/virt/kvm/mmu.txt index 2efe0efc516e..1b9880dfba0a 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virt/kvm/mmu.txt @@ -298,7 +298,7 @@ Handling a page fault is performed as follows: vcpu->arch.mmio_gfn, and call the emulator - If both P bit and R/W bit of error code are set, this could possibly be handled as a "fast page fault" (fixed without taking the MMU lock). See - the description in Documentation/virtual/kvm/locking.txt. + the description in Documentation/virt/kvm/locking.txt. - if needed, walk the guest page tables to determine the guest translation (gva->gpa or ngpa->gpa) - if permissions are insufficient, reflect the fault back to the guest diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virt/kvm/msr.txt similarity index 100% rename from Documentation/virtual/kvm/msr.txt rename to Documentation/virt/kvm/msr.txt diff --git a/Documentation/virtual/kvm/nested-vmx.txt b/Documentation/virt/kvm/nested-vmx.txt similarity index 100% rename from Documentation/virtual/kvm/nested-vmx.txt rename to Documentation/virt/kvm/nested-vmx.txt diff --git a/Documentation/virtual/kvm/ppc-pv.txt b/Documentation/virt/kvm/ppc-pv.txt similarity index 100% rename from Documentation/virtual/kvm/ppc-pv.txt rename to Documentation/virt/kvm/ppc-pv.txt diff --git a/Documentation/virtual/kvm/review-checklist.txt b/Documentation/virt/kvm/review-checklist.txt similarity index 95% rename from Documentation/virtual/kvm/review-checklist.txt rename to Documentation/virt/kvm/review-checklist.txt index a83b27635fdd..499af499e296 100644 --- a/Documentation/virtual/kvm/review-checklist.txt +++ b/Documentation/virt/kvm/review-checklist.txt @@ -7,7 +7,7 @@ Review checklist for kvm patches 2. Patches should be against kvm.git master branch. 3. If the patch introduces or modifies a new userspace API: - - the API must be documented in Documentation/virtual/kvm/api.txt + - the API must be documented in Documentation/virt/kvm/api.txt - the API must be discoverable using KVM_CHECK_EXTENSION 4. New state must include support for save/restore. diff --git a/Documentation/virtual/kvm/s390-diag.txt b/Documentation/virt/kvm/s390-diag.txt similarity index 100% rename from Documentation/virtual/kvm/s390-diag.txt rename to Documentation/virt/kvm/s390-diag.txt diff --git a/Documentation/virtual/kvm/timekeeping.txt b/Documentation/virt/kvm/timekeeping.txt similarity index 100% rename from Documentation/virtual/kvm/timekeeping.txt rename to Documentation/virt/kvm/timekeeping.txt diff --git a/Documentation/virtual/kvm/vcpu-requests.rst b/Documentation/virt/kvm/vcpu-requests.rst similarity index 100% rename from Documentation/virtual/kvm/vcpu-requests.rst rename to Documentation/virt/kvm/vcpu-requests.rst diff --git a/Documentation/virtual/paravirt_ops.rst b/Documentation/virt/paravirt_ops.rst similarity index 100% rename from Documentation/virtual/paravirt_ops.rst rename to Documentation/virt/paravirt_ops.rst diff --git a/Documentation/virtual/uml/UserModeLinux-HOWTO.txt b/Documentation/virt/uml/UserModeLinux-HOWTO.txt similarity index 100% rename from Documentation/virtual/uml/UserModeLinux-HOWTO.txt rename to Documentation/virt/uml/UserModeLinux-HOWTO.txt diff --git a/MAINTAINERS b/MAINTAINERS index debbb7b97c98..1aec93695040 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8727,7 +8727,7 @@ L: kvm@vger.kernel.org W: http://www.linux-kvm.org T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git S: Supported -F: Documentation/virtual/kvm/ +F: Documentation/virt/kvm/ F: include/trace/events/kvm.h F: include/uapi/asm-generic/kvm* F: include/uapi/linux/kvm* @@ -12054,7 +12054,7 @@ M: Juergen Gross M: Alok Kataria L: virtualization@lists.linux-foundation.org S: Supported -F: Documentation/virtual/paravirt_ops.txt +F: Documentation/virt/paravirt_ops.txt F: arch/*/kernel/paravirt* F: arch/*/include/asm/paravirt*.h F: include/linux/hypervisor.h @@ -16745,7 +16745,7 @@ W: http://user-mode-linux.sourceforge.net Q: https://patchwork.ozlabs.org/project/linux-um/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml.git S: Maintained -F: Documentation/virtual/uml/ +F: Documentation/virt/uml/ F: arch/um/ F: arch/x86/um/ F: fs/hostfs/ diff --git a/arch/powerpc/include/uapi/asm/kvm_para.h b/arch/powerpc/include/uapi/asm/kvm_para.h index 01555c6ae0f5..be48c2215fa2 100644 --- a/arch/powerpc/include/uapi/asm/kvm_para.h +++ b/arch/powerpc/include/uapi/asm/kvm_para.h @@ -31,7 +31,7 @@ * Struct fields are always 32 or 64 bit aligned, depending on them being 32 * or 64 bit wide respectively. * - * See Documentation/virtual/kvm/ppc-pv.txt + * See Documentation/virt/kvm/ppc-pv.txt */ struct kvm_vcpu_arch_shared { __u64 scratch1; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8f72526e2f68..24843cf49579 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3466,7 +3466,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, /* * Currently, fast page fault only works for direct mapping * since the gfn is not stable for indirect shadow page. See - * Documentation/virtual/kvm/locking.txt to get more detail. + * Documentation/virt/kvm/locking.txt to get more detail. */ fault_handled = fast_pf_fix_direct_spte(vcpu, sp, iterator.sptep, spte, diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index a7c19540ce21..5e3f12d5359e 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -116,7 +116,7 @@ struct kvm_irq_level { * ACPI gsi notion of irq. * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47.. * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23.. - * For ARM: See Documentation/virtual/kvm/api.txt + * For ARM: See Documentation/virt/kvm/api.txt */ union { __u32 irq; @@ -1086,7 +1086,7 @@ struct kvm_xen_hvm_config { * * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies * the irqfd to operate in resampling mode for level triggered interrupt - * emulation. See Documentation/virtual/kvm/api.txt. + * emulation. See Documentation/virt/kvm/api.txt. */ #define KVM_IRQFD_FLAG_RESAMPLE (1 << 1) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index c2152f3dd02d..e7c67be7c15f 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -116,7 +116,7 @@ struct kvm_irq_level { * ACPI gsi notion of irq. * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47.. * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23.. - * For ARM: See Documentation/virtual/kvm/api.txt + * For ARM: See Documentation/virt/kvm/api.txt */ union { __u32 irq; @@ -1085,7 +1085,7 @@ struct kvm_xen_hvm_config { * * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies * the irqfd to operate in resampling mode for level triggered interrupt - * emulation. See Documentation/virtual/kvm/api.txt. + * emulation. See Documentation/virt/kvm/api.txt. */ #define KVM_IRQFD_FLAG_RESAMPLE (1 << 1) diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index f645c0fbf7ec..acc43242a310 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -727,7 +727,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) * Ensure we set mode to IN_GUEST_MODE after we disable * interrupts and before the final VCPU requests check. * See the comment in kvm_vcpu_exiting_guest_mode() and - * Documentation/virtual/kvm/vcpu-requests.rst + * Documentation/virt/kvm/vcpu-requests.rst */ smp_store_mb(vcpu->mode, IN_GUEST_MODE); diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index 936962abc38d..c45e2d7e942f 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -250,7 +250,7 @@ static unsigned long vgic_v3_uaccess_read_pending(struct kvm_vcpu *vcpu, * pending state of interrupt is latched in pending_latch variable. * Userspace will save and restore pending state and line_level * separately. - * Refer to Documentation/virtual/kvm/devices/arm-vgic-v3.txt + * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.txt * for handling of ISPENDR and ICPENDR. */ for (i = 0; i < len * 8; i++) { diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 57205beaa981..3b7525deec80 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -42,7 +42,7 @@ VGIC_AFFINITY_LEVEL(val, 3)) /* - * As per Documentation/virtual/kvm/devices/arm-vgic-v3.txt, + * As per Documentation/virt/kvm/devices/arm-vgic-v3.txt, * below macros are defined for CPUREG encoding. */ #define KVM_REG_ARM_VGIC_SYSREG_OP0_MASK 0x000000000000c000 @@ -63,7 +63,7 @@ KVM_REG_ARM_VGIC_SYSREG_OP2_MASK) /* - * As per Documentation/virtual/kvm/devices/arm-vgic-its.txt, + * As per Documentation/virt/kvm/devices/arm-vgic-its.txt, * below macros are defined for ITS table entry encoding. */ #define KVM_ITS_CTE_VALID_SHIFT 63 From a56587065094fd96eb4c2b5ad65571daad32156d Mon Sep 17 00:00:00 2001 From: Martijn Coenen Date: Tue, 9 Jul 2019 13:09:23 +0200 Subject: [PATCH 297/823] binder: Set end of SG buffer area properly. In case the target node requests a security context, the extra_buffers_size is increased with the size of the security context. But, that size is not available for use by regular scatter-gather buffers; make sure the ending of that buffer is marked correctly. Acked-by: Todd Kjos Fixes: ec74136ded79 ("binder: create node flag to request sender's security context") Signed-off-by: Martijn Coenen Cc: stable@vger.kernel.org # 5.1+ Link: https://lore.kernel.org/r/20190709110923.220736-1-maco@android.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 38a59a630cd4..5bde08603fbc 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -3239,7 +3239,8 @@ static void binder_transaction(struct binder_proc *proc, buffer_offset = off_start_offset; off_end_offset = off_start_offset + tr->offsets_size; sg_buf_offset = ALIGN(off_end_offset, sizeof(void *)); - sg_buf_end_offset = sg_buf_offset + extra_buffers_size; + sg_buf_end_offset = sg_buf_offset + extra_buffers_size - + ALIGN(secctx_sz, sizeof(u64)); off_min = 0; for (buffer_offset = off_start_offset; buffer_offset < off_end_offset; buffer_offset += sizeof(binder_size_t)) { From 49ed96943a8e0c62cc5a9b0a6cfc88be87d1fcec Mon Sep 17 00:00:00 2001 From: Hridya Valsaraju Date: Mon, 15 Jul 2019 12:18:04 -0700 Subject: [PATCH 298/823] binder: prevent transactions to context manager from its own process. Currently, a transaction to context manager from its own process is prevented by checking if its binder_proc struct is the same as that of the sender. However, this would not catch cases where the process opens the binder device again and uses the new fd to send a transaction to the context manager. Reported-by: syzbot+8b3c354d33c4ac78bfad@syzkaller.appspotmail.com Signed-off-by: Hridya Valsaraju Acked-by: Todd Kjos Cc: stable Link: https://lore.kernel.org/r/20190715191804.112933-1-hridya@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 5bde08603fbc..dc1c83eafc22 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2988,7 +2988,7 @@ static void binder_transaction(struct binder_proc *proc, else return_error = BR_DEAD_REPLY; mutex_unlock(&context->context_mgr_node_lock); - if (target_node && target_proc == proc) { + if (target_node && target_proc->pid == proc->pid) { binder_user_error("%d:%d got transaction to context manager from process owning it\n", proc->pid, thread->pid); return_error = BR_FAILED_REPLY; From c63845609c4700488e5eacd6ab4d06d5d420e5ef Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 24 Jun 2019 08:34:13 +0000 Subject: [PATCH 299/823] can: dev: call netif_carrier_off() in register_candev() CONFIG_CAN_LEDS is deprecated. When trying to use the generic netdev trigger as suggested, there's a small inconsistency with the link property: The LED is on initially, stays on when the device is brought up, and then turns off (as expected) when the device is brought down. Make sure the LED always reflects the state of the CAN device. Signed-off-by: Rasmus Villemoes Acked-by: Willem de Bruijn Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index b6b93a2d93a5..483d270664cc 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -1249,6 +1249,8 @@ int register_candev(struct net_device *dev) return -EINVAL; dev->rtnl_link_ops = &can_link_ops; + netif_carrier_off(dev); + return register_netdev(dev); } EXPORT_SYMBOL_GPL(register_candev); From d4b890aec4bea7334ca2ca56fd3b12fb48a00cd1 Mon Sep 17 00:00:00 2001 From: Nikita Yushchenko Date: Wed, 26 Jun 2019 16:08:48 +0300 Subject: [PATCH 300/823] can: rcar_canfd: fix possible IRQ storm on high load We have observed rcar_canfd driver entering IRQ storm under high load, with following scenario: - rcar_canfd_global_interrupt() in entered due to Rx available, - napi_schedule_prep() is called, and sets NAPIF_STATE_SCHED in state - Rx fifo interrupts are masked, - rcar_canfd_global_interrupt() is entered again, this time due to error interrupt (e.g. due to overflow), - since scheduled napi poller has not yet executed, condition for calling napi_schedule_prep() from rcar_canfd_global_interrupt() remains true, thus napi_schedule_prep() gets called and sets NAPIF_STATE_MISSED flag in state, - later, napi poller function rcar_canfd_rx_poll() gets executed, and calls napi_complete_done(), - due to NAPIF_STATE_MISSED flag in state, this call does not clear NAPIF_STATE_SCHED flag from state, - on return from napi_complete_done(), rcar_canfd_rx_poll() unmasks Rx interrutps, - Rx interrupt happens, rcar_canfd_global_interrupt() gets called and calls napi_schedule_prep(), - since NAPIF_STATE_SCHED is set in state at this time, this call returns false, - due to that false return, rcar_canfd_global_interrupt() returns without masking Rx interrupt - and this results into IRQ storm: unmasked Rx interrupt happens again and again is misprocessed in the same way. This patch fixes that scenario by unmasking Rx interrupts only when napi_complete_done() returns true, which means it has cleared NAPIF_STATE_SCHED in state. Fixes: dd3bd23eb438 ("can: rcar_canfd: Add Renesas R-Car CAN FD driver") Signed-off-by: Nikita Yushchenko Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/rcar/rcar_canfd.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index 05410008aa6b..de34a4b82d4a 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -1508,10 +1508,11 @@ static int rcar_canfd_rx_poll(struct napi_struct *napi, int quota) /* All packets processed */ if (num_pkts < quota) { - napi_complete_done(napi, num_pkts); - /* Enable Rx FIFO interrupts */ - rcar_canfd_set_bit(priv->base, RCANFD_RFCC(ridx), - RCANFD_RFCC_RFIE); + if (napi_complete_done(napi, num_pkts)) { + /* Enable Rx FIFO interrupts */ + rcar_canfd_set_bit(priv->base, RCANFD_RFCC(ridx), + RCANFD_RFCC_RFIE); + } } return num_pkts; } From 375f755899b8fc21196197e02aab26257df26e85 Mon Sep 17 00:00:00 2001 From: Weitao Hou Date: Tue, 25 Jun 2019 20:50:48 +0800 Subject: [PATCH 301/823] can: mcp251x: add error check when wq alloc failed add error check when workqueue alloc failed, and remove redundant code to make it clear. Fixes: e0000163e30e ("can: Driver for the Microchip MCP251x SPI CAN controllers") Signed-off-by: Weitao Hou Acked-by: Willem de Bruijn Tested-by: Sean Nyekjaer Signed-off-by: Marc Kleine-Budde --- drivers/net/can/spi/mcp251x.c | 49 ++++++++++++++++------------------- 1 file changed, 22 insertions(+), 27 deletions(-) diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index 44e99e3d7134..2aec934fab0c 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -664,17 +664,6 @@ static int mcp251x_power_enable(struct regulator *reg, int enable) return regulator_disable(reg); } -static void mcp251x_open_clean(struct net_device *net) -{ - struct mcp251x_priv *priv = netdev_priv(net); - struct spi_device *spi = priv->spi; - - free_irq(spi->irq, priv); - mcp251x_hw_sleep(spi); - mcp251x_power_enable(priv->transceiver, 0); - close_candev(net); -} - static int mcp251x_stop(struct net_device *net) { struct mcp251x_priv *priv = netdev_priv(net); @@ -940,37 +929,43 @@ static int mcp251x_open(struct net_device *net) flags | IRQF_ONESHOT, DEVICE_NAME, priv); if (ret) { dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq); - mcp251x_power_enable(priv->transceiver, 0); - close_candev(net); - goto open_unlock; + goto out_close; } priv->wq = alloc_workqueue("mcp251x_wq", WQ_FREEZABLE | WQ_MEM_RECLAIM, 0); + if (!priv->wq) { + ret = -ENOMEM; + goto out_clean; + } INIT_WORK(&priv->tx_work, mcp251x_tx_work_handler); INIT_WORK(&priv->restart_work, mcp251x_restart_work_handler); ret = mcp251x_hw_reset(spi); - if (ret) { - mcp251x_open_clean(net); - goto open_unlock; - } + if (ret) + goto out_free_wq; ret = mcp251x_setup(net, spi); - if (ret) { - mcp251x_open_clean(net); - goto open_unlock; - } + if (ret) + goto out_free_wq; ret = mcp251x_set_normal_mode(spi); - if (ret) { - mcp251x_open_clean(net); - goto open_unlock; - } + if (ret) + goto out_free_wq; can_led_event(net, CAN_LED_EVENT_OPEN); netif_wake_queue(net); + mutex_unlock(&priv->mcp_lock); -open_unlock: + return 0; + +out_free_wq: + destroy_workqueue(priv->wq); +out_clean: + free_irq(spi->irq, priv); + mcp251x_hw_sleep(spi); +out_close: + mcp251x_power_enable(priv->transceiver, 0); + close_candev(net); mutex_unlock(&priv->mcp_lock); return ret; } From e9f2a856e102fa27715b94bcc2240f686536d29b Mon Sep 17 00:00:00 2001 From: Wen Yang Date: Sat, 6 Jul 2019 11:37:20 +0800 Subject: [PATCH 302/823] can: flexcan: fix an use-after-free in flexcan_setup_stop_mode() The gpr_np variable is still being used in dev_dbg() after the of_node_put() call, which may result in use-after-free. Fixes: de3578c198c6 ("can: flexcan: add self wakeup support") Signed-off-by: Wen Yang Cc: linux-stable # >= v5.0 Signed-off-by: Marc Kleine-Budde --- drivers/net/can/flexcan.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index f2fe344593d5..33ce45d51e15 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -1437,10 +1437,10 @@ static int flexcan_setup_stop_mode(struct platform_device *pdev) priv = netdev_priv(dev); priv->stm.gpr = syscon_node_to_regmap(gpr_np); - of_node_put(gpr_np); if (IS_ERR(priv->stm.gpr)) { dev_dbg(&pdev->dev, "could not find gpr regmap\n"); - return PTR_ERR(priv->stm.gpr); + ret = PTR_ERR(priv->stm.gpr); + goto out_put_node; } priv->stm.req_gpr = out_val[1]; @@ -1455,7 +1455,9 @@ static int flexcan_setup_stop_mode(struct platform_device *pdev) device_set_wakeup_capable(&pdev->dev, true); - return 0; +out_put_node: + of_node_put(gpr_np); + return ret; } static const struct of_device_id flexcan_of_match[] = { From 5f186c257fa4808bb7f14e643b9fba3e11f08a30 Mon Sep 17 00:00:00 2001 From: Joakim Zhang Date: Tue, 2 Jul 2019 01:45:41 +0000 Subject: [PATCH 303/823] can: flexcan: fix stop mode acknowledgment To enter stop mode, the CPU should manually assert a global Stop Mode request and check the acknowledgment asserted by FlexCAN. The CPU must only consider the FlexCAN in stop mode when both request and acknowledgment conditions are satisfied. Fixes: de3578c198c6 ("can: flexcan: add self wakeup support") Reported-by: Marc Kleine-Budde Signed-off-by: Joakim Zhang Cc: linux-stable # >= v5.0 Signed-off-by: Marc Kleine-Budde --- drivers/net/can/flexcan.c | 31 +++++++++++++++++++++++++++---- 1 file changed, 27 insertions(+), 4 deletions(-) diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 33ce45d51e15..fcec8bcb53d6 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -400,9 +400,10 @@ static void flexcan_enable_wakeup_irq(struct flexcan_priv *priv, bool enable) priv->write(reg_mcr, ®s->mcr); } -static inline void flexcan_enter_stop_mode(struct flexcan_priv *priv) +static inline int flexcan_enter_stop_mode(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; + unsigned int ackval; u32 reg_mcr; reg_mcr = priv->read(®s->mcr); @@ -412,20 +413,37 @@ static inline void flexcan_enter_stop_mode(struct flexcan_priv *priv) /* enable stop request */ regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr, 1 << priv->stm.req_bit, 1 << priv->stm.req_bit); + + /* get stop acknowledgment */ + if (regmap_read_poll_timeout(priv->stm.gpr, priv->stm.ack_gpr, + ackval, ackval & (1 << priv->stm.ack_bit), + 0, FLEXCAN_TIMEOUT_US)) + return -ETIMEDOUT; + + return 0; } -static inline void flexcan_exit_stop_mode(struct flexcan_priv *priv) +static inline int flexcan_exit_stop_mode(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; + unsigned int ackval; u32 reg_mcr; /* remove stop request */ regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr, 1 << priv->stm.req_bit, 0); + /* get stop acknowledgment */ + if (regmap_read_poll_timeout(priv->stm.gpr, priv->stm.ack_gpr, + ackval, !(ackval & (1 << priv->stm.ack_bit)), + 0, FLEXCAN_TIMEOUT_US)) + return -ETIMEDOUT; + reg_mcr = priv->read(®s->mcr); reg_mcr &= ~FLEXCAN_MCR_SLF_WAK; priv->write(reg_mcr, ®s->mcr); + + return 0; } static inline void flexcan_error_irq_enable(const struct flexcan_priv *priv) @@ -1614,7 +1632,9 @@ static int __maybe_unused flexcan_suspend(struct device *device) */ if (device_may_wakeup(device)) { enable_irq_wake(dev->irq); - flexcan_enter_stop_mode(priv); + err = flexcan_enter_stop_mode(priv); + if (err) + return err; } else { err = flexcan_chip_disable(priv); if (err) @@ -1664,10 +1684,13 @@ static int __maybe_unused flexcan_noirq_resume(struct device *device) { struct net_device *dev = dev_get_drvdata(device); struct flexcan_priv *priv = netdev_priv(dev); + int err; if (netif_running(dev) && device_may_wakeup(device)) { flexcan_enable_wakeup_irq(priv, false); - flexcan_exit_stop_mode(priv); + err = flexcan_exit_stop_mode(priv); + if (err) + return err; } return 0; From fee6a8923ae0d318a7f7950c6c6c28a96cea099b Mon Sep 17 00:00:00 2001 From: Stephane Grosjean Date: Fri, 5 Jul 2019 15:32:16 +0200 Subject: [PATCH 304/823] can: peak_usb: fix potential double kfree_skb() When closing the CAN device while tx skbs are inflight, echo skb could be released twice. By calling close_candev() before unlinking all pending tx urbs, then the internal echo_skb[] array is fully and correctly cleared before the USB write callback and, therefore, can_get_echo_skb() are called, for each aborted URB. Fixes: bb4785551f64 ("can: usb: PEAK-System Technik USB adapters driver core") Signed-off-by: Stephane Grosjean Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/peak_usb/pcan_usb_core.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 458154c9b482..22b9c8e6d040 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -568,16 +568,16 @@ static int peak_usb_ndo_stop(struct net_device *netdev) dev->state &= ~PCAN_USB_STATE_STARTED; netif_stop_queue(netdev); + close_candev(netdev); + + dev->can.state = CAN_STATE_STOPPED; + /* unlink all pending urbs and free used memory */ peak_usb_unlink_all_urbs(dev); if (dev->adapter->dev_stop) dev->adapter->dev_stop(dev); - close_candev(netdev); - - dev->can.state = CAN_STATE_STOPPED; - /* can set bus off now */ if (dev->adapter->dev_set_bus) { int err = dev->adapter->dev_set_bus(dev, 0); From b7a14297f102b6e2ce6f16feffebbb9bde1e9b55 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Sat, 18 May 2019 17:35:43 +0800 Subject: [PATCH 305/823] can: gw: Fix error path of cgw_module_init This patch add error path for cgw_module_init to avoid possible crash if some error occurs. Fixes: c1aabdf379bc ("can-gw: add netlink based CAN routing") Signed-off-by: YueHaibing Acked-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- net/can/gw.c | 46 ++++++++++++++++++++++++++++++++-------------- 1 file changed, 32 insertions(+), 14 deletions(-) diff --git a/net/can/gw.c b/net/can/gw.c index 5275ddf580bc..72711053ebe6 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -1046,32 +1046,50 @@ static __init int cgw_module_init(void) pr_info("can: netlink gateway (rev " CAN_GW_VERSION ") max_hops=%d\n", max_hops); - register_pernet_subsys(&cangw_pernet_ops); + ret = register_pernet_subsys(&cangw_pernet_ops); + if (ret) + return ret; + + ret = -ENOMEM; cgw_cache = kmem_cache_create("can_gw", sizeof(struct cgw_job), 0, 0, NULL); - if (!cgw_cache) - return -ENOMEM; + goto out_cache_create; /* set notifier */ notifier.notifier_call = cgw_notifier; - register_netdevice_notifier(¬ifier); + ret = register_netdevice_notifier(¬ifier); + if (ret) + goto out_register_notifier; ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_GETROUTE, NULL, cgw_dump_jobs, 0); - if (ret) { - unregister_netdevice_notifier(¬ifier); - kmem_cache_destroy(cgw_cache); - return -ENOBUFS; - } + if (ret) + goto out_rtnl_register1; - /* Only the first call to rtnl_register_module can fail */ - rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE, - cgw_create_job, NULL, 0); - rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE, - cgw_remove_job, NULL, 0); + ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE, + cgw_create_job, NULL, 0); + if (ret) + goto out_rtnl_register2; + ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE, + cgw_remove_job, NULL, 0); + if (ret) + goto out_rtnl_register3; return 0; + +out_rtnl_register3: + rtnl_unregister(PF_CAN, RTM_NEWROUTE); +out_rtnl_register2: + rtnl_unregister(PF_CAN, RTM_GETROUTE); +out_rtnl_register1: + unregister_netdevice_notifier(¬ifier); +out_register_notifier: + kmem_cache_destroy(cgw_cache); +out_cache_create: + unregister_pernet_subsys(&cangw_pernet_ops); + + return ret; } static __exit void cgw_module_exit(void) From 1be8624a0cbef720e8da39a15971e01abffc865b Mon Sep 17 00:00:00 2001 From: Alexander Usyskin Date: Fri, 12 Jul 2019 12:58:14 +0300 Subject: [PATCH 306/823] mei: me: add mule creek canyon (EHL) device ids Add Mule Creek Canyon (PCH) MEI device ids for Elkhart Lake (EHL) Platform. Signed-off-by: Alexander Usyskin Signed-off-by: Tomas Winkler Cc: stable Link: https://lore.kernel.org/r/20190712095814.20746-1-tomas.winkler@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/hw-me-regs.h | 3 +++ drivers/misc/mei/pci-me.c | 3 +++ 2 files changed, 6 insertions(+) diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index d74b182e19f3..6c0173772162 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -81,6 +81,9 @@ #define MEI_DEV_ID_ICP_LP 0x34E0 /* Ice Lake Point LP */ +#define MEI_DEV_ID_MCC 0x4B70 /* Mule Creek Canyon (EHL) */ +#define MEI_DEV_ID_MCC_4 0x4B75 /* Mule Creek Canyon 4 (EHL) */ + /* * MEI HW Section */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 7a2b3545a7f9..57cb68f5cc64 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -98,6 +98,9 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_ICP_LP, MEI_ME_PCH12_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_MCC, MEI_ME_PCH12_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_MCC_4, MEI_ME_PCH8_CFG)}, + /* required last entry */ {0, } }; From 3d139703d397f6281368047ba7ad1c8bf95aa8ab Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Mon, 8 Jul 2019 15:13:56 +0800 Subject: [PATCH 307/823] fpga-manager: altera-ps-spi: Fix build error If BITREVERSE is m and FPGA_MGR_ALTERA_PS_SPI is y, build fails: drivers/fpga/altera-ps-spi.o: In function `altera_ps_write': altera-ps-spi.c:(.text+0x4ec): undefined reference to `byte_rev_table' Select BITREVERSE to fix this. Reported-by: Hulk Robot Fixes: fcfe18f885f6 ("fpga-manager: altera-ps-spi: use bitrev8x4") Signed-off-by: YueHaibing Cc: stable Acked-by: Moritz Fischer Link: https://lore.kernel.org/r/20190708071356.50928-1-yuehaibing@huawei.com Signed-off-by: Greg Kroah-Hartman --- drivers/fpga/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/fpga/Kconfig b/drivers/fpga/Kconfig index 474f304ec109..cdd4f73b4869 100644 --- a/drivers/fpga/Kconfig +++ b/drivers/fpga/Kconfig @@ -40,6 +40,7 @@ config ALTERA_PR_IP_CORE_PLAT config FPGA_MGR_ALTERA_PS_SPI tristate "Altera FPGA Passive Serial over SPI" depends on SPI + select BITREVERSE help FPGA manager driver support for Altera Arria/Cyclone/Stratix using the passive serial interface over SPI. From b8f70953c1251d8b16276995816a95639f598e70 Mon Sep 17 00:00:00 2001 From: Matt Mullins Date: Tue, 23 Jul 2019 21:20:58 -0700 Subject: [PATCH 308/823] x86/entry/32: Pass cr2 to do_async_page_fault() Commit a0d14b8909de ("x86/mm, tracing: Fix CR2 corruption") added the address parameter to do_async_page_fault(), but does not pass it from the 32-bit entry point. To plumb it through, factor-out common_exception_read_cr2 in the same fashion as common_exception, and uses it from both page_fault and async_page_fault. For a 32-bit KVM guest, this fixes: Run /sbin/init as init process Starting init: /sbin/init exists but couldn't execute it (error -14) Fixes: a0d14b8909de ("x86/mm, tracing: Fix CR2 corruption") Signed-off-by: Matt Mullins Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20190724042058.24506-1-mmullins@fb.com --- arch/x86/entry/entry_32.S | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 2bb986f305ac..4f86928246e7 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -1443,8 +1443,12 @@ BUILD_INTERRUPT3(hv_stimer0_callback_vector, HYPERV_STIMER0_VECTOR, ENTRY(page_fault) ASM_CLAC - pushl $0; /* %gs's slot on the stack */ + pushl $do_page_fault + jmp common_exception_read_cr2 +END(page_fault) +common_exception_read_cr2: + /* the function address is in %gs's slot on the stack */ SAVE_ALL switch_stacks=1 skip_gs=1 ENCODE_FRAME_POINTER @@ -1452,6 +1456,7 @@ ENTRY(page_fault) /* fixup %gs */ GS_TO_REG %ecx + movl PT_GS(%esp), %edi REG_TO_PTGS %ecx SET_KERNEL_GS %ecx @@ -1463,9 +1468,9 @@ ENTRY(page_fault) TRACE_IRQS_OFF movl %esp, %eax # pt_regs pointer - call do_page_fault + CALL_NOSPEC %edi jmp ret_from_exception -END(page_fault) +END(common_exception_read_cr2) common_exception: /* the function address is in %gs's slot on the stack */ @@ -1595,7 +1600,7 @@ END(general_protection) ENTRY(async_page_fault) ASM_CLAC pushl $do_async_page_fault - jmp common_exception + jmp common_exception_read_cr2 END(async_page_fault) #endif From 266e85a5ec9100dcd9ae03601453bbc96fefee5d Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Wed, 24 Jul 2019 17:43:13 +0800 Subject: [PATCH 309/823] KVM: X86: Boost queue head vCPU to mitigate lock waiter preemption MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 11752adb (locking/pvqspinlock: Implement hybrid PV queued/unfair locks) introduces hybrid PV queued/unfair locks - queued mode (no starvation) - unfair mode (good performance on not heavily contended lock) The lock waiter goes into the unfair mode especially in VMs with over-commit vCPUs since increaing over-commitment increase the likehood that the queue head vCPU may have been preempted and not actively spinning. However, reschedule queue head vCPU timely to acquire the lock still can get better performance than just depending on lock stealing in over-subscribe scenario. Testing on 80 HT 2 socket Xeon Skylake server, with 80 vCPUs VM 80GB RAM: ebizzy -M vanilla boosting improved 1VM 23520 25040 6% 2VM 8000 13600 70% 3VM 3100 5400 74% The lock holder vCPU yields to the queue head vCPU when unlock, to boost queue head vCPU which is involuntary preemption or the one which is voluntary halt due to fail to acquire the lock after a short spin in the guest. Cc: Waiman Long Cc: Peter Zijlstra Cc: Paolo Bonzini Cc: Radim Krčmář Signed-off-by: Wanpeng Li Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 01e18caac825..c6d951cbd76c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7206,7 +7206,7 @@ static void kvm_sched_yield(struct kvm *kvm, unsigned long dest_id) rcu_read_unlock(); - if (target) + if (target && READ_ONCE(target->ready)) kvm_vcpu_yield_to(target); } @@ -7246,6 +7246,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) break; case KVM_HC_KICK_CPU: kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1); + kvm_sched_yield(vcpu->kvm, a1); ret = 0; break; #ifdef CONFIG_X86_64 From c7842d1080a31ab02950be74d3c6960139ff0f7f Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 23 Jul 2019 17:03:44 -0600 Subject: [PATCH 310/823] dt-bindings: clk: allwinner,sun4i-a10-ccu: Correct path in $id The path in the schema '$id' value is wrong. Fix it. Cc: Michael Turquette Cc: Stephen Boyd Cc: Chen-Yu Tsai Cc: linux-clk@vger.kernel.org Acked-by: Maxime Ripard Signed-off-by: Rob Herring --- .../devicetree/bindings/clock/allwinner,sun4i-a10-ccu.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-ccu.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-ccu.yaml index c935405458fe..fa4d143a73de 100644 --- a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-ccu.yaml +++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-ccu.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/phy/allwinner,sun4i-a10-ccu.yaml# +$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-ccu.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Allwinner Clock Control Unit Device Tree Bindings From acbc372e6109c803cbee4733769d02008381740f Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Tue, 23 Jul 2019 08:50:59 +0200 Subject: [PATCH 311/823] selinux: check sidtab limit before adding a new entry We need to error out when trying to add an entry above SIDTAB_MAX in sidtab_reverse_lookup() to avoid overflow on the odd chance that this happens. Cc: stable@vger.kernel.org Fixes: ee1a84fdfeed ("selinux: overhaul sidtab to fix bug and improve performance") Signed-off-by: Ondrej Mosnacek Reviewed-by: Kees Cook Signed-off-by: Paul Moore --- security/selinux/ss/sidtab.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/security/selinux/ss/sidtab.c b/security/selinux/ss/sidtab.c index e63a90ff2728..1f0a6eaa2d6a 100644 --- a/security/selinux/ss/sidtab.c +++ b/security/selinux/ss/sidtab.c @@ -286,6 +286,11 @@ static int sidtab_reverse_lookup(struct sidtab *s, struct context *context, ++count; } + /* bail out if we already reached max entries */ + rc = -EOVERFLOW; + if (count >= SIDTAB_MAX) + goto out_unlock; + /* insert context into new entry */ rc = -ENOMEM; dst = sidtab_do_lookup(s, count, 1); From 66d7780f18eae0232827fcffeaded39a6a168236 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jul 2019 11:51:56 -0700 Subject: [PATCH 312/823] dma-mapping: check pfn validity in dma_common_{mmap,get_sgtable} Check that the pfn returned from arch_dma_coherent_to_pfn refers to a valid page and reject the mmap / get_sgtable requests otherwise. Based on the arm implementation of the mmap and get_sgtable methods. Signed-off-by: Christoph Hellwig Tested-by: Vignesh Raghavendra --- kernel/dma/mapping.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 1f628e7ac709..b945239621d8 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -116,11 +116,16 @@ int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, int ret; if (!dev_is_dma_coherent(dev)) { + unsigned long pfn; + if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN)) return -ENXIO; - page = pfn_to_page(arch_dma_coherent_to_pfn(dev, cpu_addr, - dma_addr)); + /* If the PFN is not valid, we do not have a struct page */ + pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr); + if (!pfn_valid(pfn)) + return -ENXIO; + page = pfn_to_page(pfn); } else { page = virt_to_page(cpu_addr); } @@ -170,7 +175,11 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, if (!dev_is_dma_coherent(dev)) { if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN)) return -ENXIO; + + /* If the PFN is not valid, we do not have a struct page */ pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr); + if (!pfn_valid(pfn)) + return -ENXIO; } else { pfn = page_to_pfn(virt_to_page(cpu_addr)); } From ad3c7b18c5b362be5dbd0f2c0bcf1fd5fd659315 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 23 Jul 2019 11:33:12 +0200 Subject: [PATCH 313/823] arm: use swiotlb for bounce buffering on LPAE configs The DMA API requires that 32-bit DMA masks are always supported, but on arm LPAE configs they do not currently work when memory is present above 4GB. Wire up the swiotlb code like for all other architectures to provide the bounce buffering in that case. Fixes: 21e07dba9fb11 ("scsi: reduce use of block bounce buffers"). Reported-by: Roger Quadros Signed-off-by: Christoph Hellwig Tested-by: Vignesh Raghavendra --- arch/arm/include/asm/dma-mapping.h | 4 +- arch/arm/mm/Kconfig | 5 +++ arch/arm/mm/dma-mapping.c | 61 ++++++++++++++++++++++++++++++ arch/arm/mm/init.c | 5 +++ 4 files changed, 74 insertions(+), 1 deletion(-) diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 7e0486ad1318..dba9355e2484 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -18,7 +18,9 @@ extern const struct dma_map_ops arm_coherent_dma_ops; static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { - return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : NULL; + if (IS_ENABLED(CONFIG_MMU) && !IS_ENABLED(CONFIG_ARM_LPAE)) + return &arm_dma_ops; + return NULL; } #ifdef __arch_page_to_dma diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 820b60a50125..c54cd7ed90ba 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -663,6 +663,11 @@ config ARM_LPAE depends on MMU && CPU_32v7 && !CPU_32v6 && !CPU_32v5 && \ !CPU_32v4 && !CPU_32v3 select PHYS_ADDR_T_64BIT + select SWIOTLB + select ARCH_HAS_DMA_COHERENT_TO_PFN + select ARCH_HAS_DMA_MMAP_PGPROT + select ARCH_HAS_SYNC_DMA_FOR_DEVICE + select ARCH_HAS_SYNC_DMA_FOR_CPU help Say Y if you have an ARMv7 processor supporting the LPAE page table format and you would like to access memory beyond the diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 4789c60a86e3..6774b03aa405 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -1125,6 +1126,19 @@ int arm_dma_supported(struct device *dev, u64 mask) static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent) { + /* + * When CONFIG_ARM_LPAE is set, physical address can extend above + * 32-bits, which then can't be addressed by devices that only support + * 32-bit DMA. + * Use the generic dma-direct / swiotlb ops code in that case, as that + * handles bounce buffering for us. + * + * Note: this checks CONFIG_ARM_LPAE instead of CONFIG_SWIOTLB as the + * latter is also selected by the Xen code, but that code for now relies + * on non-NULL dev_dma_ops. To be cleaned up later. + */ + if (IS_ENABLED(CONFIG_ARM_LPAE)) + return NULL; return coherent ? &arm_coherent_dma_ops : &arm_dma_ops; } @@ -2329,6 +2343,9 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, const struct dma_map_ops *dma_ops; dev->archdata.dma_coherent = coherent; +#ifdef CONFIG_SWIOTLB + dev->dma_coherent = coherent; +#endif /* * Don't override the dma_ops if they have already been set. Ideally @@ -2363,3 +2380,47 @@ void arch_teardown_dma_ops(struct device *dev) /* Let arch_setup_dma_ops() start again from scratch upon re-probe */ set_dma_ops(dev, NULL); } + +#ifdef CONFIG_SWIOTLB +void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir) +{ + __dma_page_cpu_to_dev(phys_to_page(paddr), paddr & (PAGE_SIZE - 1), + size, dir); +} + +void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir) +{ + __dma_page_dev_to_cpu(phys_to_page(paddr), paddr & (PAGE_SIZE - 1), + size, dir); +} + +long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, + dma_addr_t dma_addr) +{ + return dma_to_pfn(dev, dma_addr); +} + +pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, + unsigned long attrs) +{ + if (!dev_is_dma_coherent(dev)) + return __get_dma_pgprot(attrs, prot); + return prot; +} + +void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs) +{ + return __dma_alloc(dev, size, dma_handle, gfp, + __get_dma_pgprot(attrs, PAGE_KERNEL), false, + attrs, __builtin_return_address(0)); +} + +void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_handle, unsigned long attrs) +{ + __arm_dma_free(dev, size, cpu_addr, dma_handle, attrs, false); +} +#endif /* CONFIG_SWIOTLB */ diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 4920a206dce9..16d373d587c4 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -463,6 +464,10 @@ static void __init free_highpages(void) */ void __init mem_init(void) { +#ifdef CONFIG_ARM_LPAE + swiotlb_init(1); +#endif + set_max_mapnr(pfn_to_page(max_pfn) - mem_map); /* this will put all unused low memory onto the freelists */ From a853c0a0b013af3fee0f028cff3c44e275ce9abd Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Thu, 11 Jul 2019 19:35:17 +0800 Subject: [PATCH 314/823] regulator: lp87565: Fix probe failure for "ti,lp87565" The "ti,lp87565" compatible string is still in of_lp87565_match_table, but current code will return -EINVAL because lp87565->dev_type is unknown. This was working in earlier kernel versions, so fix it. Fixes: 7ee63bd74750 ("regulator: lp87565: Add 4-phase lp87561 regulator support") Signed-off-by: Axel Lin Link: https://lore.kernel.org/r/20190711113517.26077-1-axel.lin@ingics.com Signed-off-by: Mark Brown --- drivers/regulator/lp87565-regulator.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/regulator/lp87565-regulator.c b/drivers/regulator/lp87565-regulator.c index 5d067f7c2116..0c440c5e2832 100644 --- a/drivers/regulator/lp87565-regulator.c +++ b/drivers/regulator/lp87565-regulator.c @@ -163,7 +163,7 @@ static int lp87565_regulator_probe(struct platform_device *pdev) struct lp87565 *lp87565 = dev_get_drvdata(pdev->dev.parent); struct regulator_config config = { }; struct regulator_dev *rdev; - int i, min_idx = LP87565_BUCK_0, max_idx = LP87565_BUCK_3; + int i, min_idx, max_idx; platform_set_drvdata(pdev, lp87565); @@ -182,9 +182,9 @@ static int lp87565_regulator_probe(struct platform_device *pdev) max_idx = LP87565_BUCK_3210; break; default: - dev_err(lp87565->dev, "Invalid lp config %d\n", - lp87565->dev_type); - return -EINVAL; + min_idx = LP87565_BUCK_0; + max_idx = LP87565_BUCK_3; + break; } for (i = min_idx; i <= max_idx; i++) { From d7852fbd0f0423937fa287a598bfde188bb68c22 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 11 Jul 2019 09:54:40 -0700 Subject: [PATCH 315/823] access: avoid the RCU grace period for the temporary subjective credentials It turns out that 'access()' (and 'faccessat()') can cause a lot of RCU work because it installs a temporary credential that gets allocated and freed for each system call. The allocation and freeing overhead is mostly benign, but because credentials can be accessed under the RCU read lock, the freeing involves a RCU grace period. Which is not a huge deal normally, but if you have a lot of access() calls, this causes a fair amount of seconday damage: instead of having a nice alloc/free patterns that hits in hot per-CPU slab caches, you have all those delayed free's, and on big machines with hundreds of cores, the RCU overhead can end up being enormous. But it turns out that all of this is entirely unnecessary. Exactly because access() only installs the credential as the thread-local subjective credential, the temporary cred pointer doesn't actually need to be RCU free'd at all. Once we're done using it, we can just free it synchronously and avoid all the RCU overhead. So add a 'non_rcu' flag to 'struct cred', which can be set by users that know they only use it in non-RCU context (there are other potential users for this). We can make it a union with the rcu freeing list head that we need for the RCU case, so this doesn't need any extra storage. Note that this also makes 'get_current_cred()' clear the new non_rcu flag, in case we have filesystems that take a long-term reference to the cred and then expect the RCU delayed freeing afterwards. It's not entirely clear that this is required, but it makes for clear semantics: the subjective cred remains non-RCU as long as you only access it synchronously using the thread-local accessors, but you _can_ use it as a generic cred if you want to. It is possible that we should just remove the whole RCU markings for ->cred entirely. Only ->real_cred is really supposed to be accessed through RCU, and the long-term cred copies that nfs uses might want to explicitly re-enable RCU freeing if required, rather than have get_current_cred() do it implicitly. But this is a "minimal semantic changes" change for the immediate problem. Acked-by: Peter Zijlstra (Intel) Acked-by: Eric Dumazet Acked-by: Paul E. McKenney Cc: Oleg Nesterov Cc: Jan Glauber Cc: Jiri Kosina Cc: Jayachandran Chandrasekharan Nair Cc: Greg KH Cc: Kees Cook Cc: David Howells Cc: Miklos Szeredi Cc: Al Viro Signed-off-by: Linus Torvalds --- fs/open.c | 19 +++++++++++++++++++ include/linux/cred.h | 8 +++++++- kernel/cred.c | 21 +++++++++++++++++++-- 3 files changed, 45 insertions(+), 3 deletions(-) diff --git a/fs/open.c b/fs/open.c index b5b80469b93d..a59abe3c669a 100644 --- a/fs/open.c +++ b/fs/open.c @@ -374,6 +374,25 @@ long do_faccessat(int dfd, const char __user *filename, int mode) override_cred->cap_permitted; } + /* + * The new set of credentials can *only* be used in + * task-synchronous circumstances, and does not need + * RCU freeing, unless somebody then takes a separate + * reference to it. + * + * NOTE! This is _only_ true because this credential + * is used purely for override_creds() that installs + * it as the subjective cred. Other threads will be + * accessing ->real_cred, not the subjective cred. + * + * If somebody _does_ make a copy of this (using the + * 'get_current_cred()' function), that will clear the + * non_rcu field, because now that other user may be + * expecting RCU freeing. But normal thread-synchronous + * cred accesses will keep things non-RCY. + */ + override_cred->non_rcu = 1; + old_cred = override_creds(override_cred); retry: res = user_path_at(dfd, filename, lookup_flags, &path); diff --git a/include/linux/cred.h b/include/linux/cred.h index 7eb43a038330..f7a30e0099be 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -145,7 +145,11 @@ struct cred { struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ - struct rcu_head rcu; /* RCU deletion hook */ + /* RCU deletion */ + union { + int non_rcu; /* Can we skip RCU deletion? */ + struct rcu_head rcu; /* RCU deletion hook */ + }; } __randomize_layout; extern void __put_cred(struct cred *); @@ -246,6 +250,7 @@ static inline const struct cred *get_cred(const struct cred *cred) if (!cred) return cred; validate_creds(cred); + nonconst_cred->non_rcu = 0; return get_new_cred(nonconst_cred); } @@ -257,6 +262,7 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred) if (!atomic_inc_not_zero(&nonconst_cred->usage)) return NULL; validate_creds(cred); + nonconst_cred->non_rcu = 0; return cred; } diff --git a/kernel/cred.c b/kernel/cred.c index c73a87a4df13..153ae369e024 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -144,7 +144,10 @@ void __put_cred(struct cred *cred) BUG_ON(cred == current->cred); BUG_ON(cred == current->real_cred); - call_rcu(&cred->rcu, put_cred_rcu); + if (cred->non_rcu) + put_cred_rcu(&cred->rcu); + else + call_rcu(&cred->rcu, put_cred_rcu); } EXPORT_SYMBOL(__put_cred); @@ -256,6 +259,7 @@ struct cred *prepare_creds(void) old = task->cred; memcpy(new, old, sizeof(struct cred)); + new->non_rcu = 0; atomic_set(&new->usage, 1); set_cred_subscribers(new, 0); get_group_info(new->group_info); @@ -535,7 +539,19 @@ const struct cred *override_creds(const struct cred *new) validate_creds(old); validate_creds(new); - get_cred(new); + + /* + * NOTE! This uses 'get_new_cred()' rather than 'get_cred()'. + * + * That means that we do not clear the 'non_rcu' flag, since + * we are only installing the cred into the thread-synchronous + * '->cred' pointer, not the '->real_cred' pointer that is + * visible to other threads under RCU. + * + * Also note that we did validate_creds() manually, not depending + * on the validation in 'get_cred()'. + */ + get_new_cred((struct cred *)new); alter_cred_subscribers(new, 1); rcu_assign_pointer(current->cred, new); alter_cred_subscribers(old, -1); @@ -672,6 +688,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) validate_creds(old); *new = *old; + new->non_rcu = 0; atomic_set(&new->usage, 1); set_cred_subscribers(new, 0); get_uid(new->user); From 2e05ec4834f9bb7fe3575e4c48acebebfa1e24d9 Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Wed, 24 Jul 2019 23:15:54 +0900 Subject: [PATCH 316/823] selftests: mlxsw: Fix typo in qos_mc_aware.sh This patch fixes some spelling typo in qos_mc_aware.sh Signed-off-by: Masanari Iida Acked-by: Randy Dunlap Reviewed-by: Ido Schimmel Signed-off-by: Shuah Khan --- tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh index 71231ad2dbfb..47315fe48d5a 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh @@ -262,7 +262,7 @@ test_mc_aware() stop_traffic - log_test "UC performace under MC overload" + log_test "UC performance under MC overload" echo "UC-only throughput $(humanize $ucth1)" echo "UC+MC throughput $(humanize $ucth2)" @@ -316,7 +316,7 @@ test_uc_aware() stop_traffic - log_test "MC performace under UC overload" + log_test "MC performance under UC overload" echo " ingress UC throughput $(humanize ${uc_ir})" echo " egress UC throughput $(humanize ${uc_er})" echo " sent $attempts BC ARPs, got $passes responses" From 8d8bef50365847134b51c1ec46786bc2873e4e47 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Wed, 3 Jul 2019 12:29:31 +0200 Subject: [PATCH 317/823] spi: bcm2835: Fix 3-wire mode if DMA is enabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 6935224da248 ("spi: bcm2835: enable support of 3-wire mode") added 3-wire support to the BCM2835 SPI driver by setting the REN bit (Read Enable) in the CS register when receiving data. The REN bit puts the transmitter in high-impedance state. The driver recognizes that data is to be received by checking whether the rx_buf of a transfer is non-NULL. Commit 3ecd37edaa2a ("spi: bcm2835: enable dma modes for transfers meeting certain conditions") subsequently broke 3-wire support because it set the SPI_MASTER_MUST_RX flag which causes spi_map_msg() to replace rx_buf with a dummy buffer if it is NULL. As a result, rx_buf is *always* non-NULL if DMA is enabled. Reinstate 3-wire support by not only checking whether rx_buf is non-NULL, but also checking that it is not the dummy buffer. Fixes: 3ecd37edaa2a ("spi: bcm2835: enable dma modes for transfers meeting certain conditions") Reported-by: Nuno Sá Signed-off-by: Lukas Wunner Cc: stable@vger.kernel.org # v4.2+ Cc: Martin Sperl Acked-by: Stefan Wahren Link: https://lore.kernel.org/r/328318841455e505370ef8ecad97b646c033dc8a.1562148527.git.lukas@wunner.de Signed-off-by: Mark Brown --- drivers/spi/spi-bcm2835.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c index 6f243a90c844..840b1b8ff3dc 100644 --- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -834,7 +834,8 @@ static int bcm2835_spi_transfer_one(struct spi_controller *ctlr, bcm2835_wr(bs, BCM2835_SPI_CLK, cdiv); /* handle all the 3-wire mode */ - if ((spi->mode & SPI_3WIRE) && (tfr->rx_buf)) + if (spi->mode & SPI_3WIRE && tfr->rx_buf && + tfr->rx_buf != ctlr->dummy_rx) cs |= BCM2835_SPI_CS_REN; else cs &= ~BCM2835_SPI_CS_REN; From aecea57f84b0586b62c010bea946468d77f6bf0f Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Tue, 23 Jul 2019 12:24:45 +0900 Subject: [PATCH 318/823] ktest: Fix some typos in config-bisect.pl This patch fixes some spelling typos in config-bisect.pl Link: http://lkml.kernel.org/r/20190723032445.14220-1-standby24x7@gmail.com Acked-by: Randy Dunlap Signed-off-by: Masanari Iida Signed-off-by: Steven Rostedt (VMware) --- tools/testing/ktest/config-bisect.pl | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/ktest/config-bisect.pl b/tools/testing/ktest/config-bisect.pl index 72525426654b..6fd864935319 100755 --- a/tools/testing/ktest/config-bisect.pl +++ b/tools/testing/ktest/config-bisect.pl @@ -663,7 +663,7 @@ while ($#ARGV >= 0) { } else { - die "Unknow option $opt\n"; + die "Unknown option $opt\n"; } } @@ -732,7 +732,7 @@ if ($start) { } } run_command "cp $good_start $good" or die "failed to copy to $good\n"; - run_command "cp $bad_start $bad" or die "faield to copy to $bad\n"; + run_command "cp $bad_start $bad" or die "failed to copy to $bad\n"; } else { if ( ! -f $good ) { die "Can not find file $good\n"; From 6a053953739d23694474a5f9c81d1a30093da81a Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 23 Jul 2019 09:57:25 +0300 Subject: [PATCH 319/823] IB/mlx5: Fix unreg_umr to ignore the mkey state Fix unreg_umr to ignore the mkey state and do not fail if was freed. This prevents a case that a user space application already changed the mkey state to free and then the UMR operation will fail leaving the mkey in an inappropriate state. Link: https://lore.kernel.org/r/20190723065733.4899-3-leon@kernel.org Cc: # 3.19 Fixes: 968e78dd9644 ("IB/mlx5: Enhance UMR support to allow partial page table update") Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/mlx5_ib.h | 1 + drivers/infiniband/hw/mlx5/mr.c | 4 ++-- drivers/infiniband/hw/mlx5/qp.c | 12 ++++++++---- 3 files changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index c482f19958b3..f6a53455bf8b 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -481,6 +481,7 @@ struct mlx5_umr_wr { u64 length; int access_flags; u32 mkey; + u8 ignore_free_state:1; }; static inline const struct mlx5_umr_wr *umr_wr(const struct ib_send_wr *wr) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 20ece6e0b2fc..266edaf8029d 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1372,10 +1372,10 @@ static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) return 0; - umrwr.wr.send_flags = MLX5_IB_SEND_UMR_DISABLE_MR | - MLX5_IB_SEND_UMR_FAIL_IF_FREE; + umrwr.wr.send_flags = MLX5_IB_SEND_UMR_DISABLE_MR; umrwr.wr.opcode = MLX5_IB_WR_UMR; umrwr.mkey = mr->mmkey.key; + umrwr.ignore_free_state = 1; return mlx5_ib_post_send_wait(dev, &umrwr); } diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 2a97619ed603..615cc6771516 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -4295,10 +4295,14 @@ static int set_reg_umr_segment(struct mlx5_ib_dev *dev, memset(umr, 0, sizeof(*umr)); - if (wr->send_flags & MLX5_IB_SEND_UMR_FAIL_IF_FREE) - umr->flags = MLX5_UMR_CHECK_FREE; /* fail if free */ - else - umr->flags = MLX5_UMR_CHECK_NOT_FREE; /* fail if not free */ + if (!umrwr->ignore_free_state) { + if (wr->send_flags & MLX5_IB_SEND_UMR_FAIL_IF_FREE) + /* fail if free */ + umr->flags = MLX5_UMR_CHECK_FREE; + else + /* fail if not free */ + umr->flags = MLX5_UMR_CHECK_NOT_FREE; + } umr->xlt_octowords = cpu_to_be16(get_xlt_octo(umrwr->xlt_size)); if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_XLT) { From afd1417404fba6dbfa6c0a8e5763bd348da682e4 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 23 Jul 2019 09:57:26 +0300 Subject: [PATCH 320/823] IB/mlx5: Use direct mkey destroy command upon UMR unreg failure Use a direct firmware command to destroy the mkey in case the unreg UMR operation has failed. This prevents a case that a mkey will leak out from the cache post a failure to be destroyed by a UMR WR. In case the MR cache limit didn't reach a call to add another entry to the cache instead of the destroyed one is issued. In addition, replaced a warn message to WARN_ON() as this flow is fatal and can't happen unless some bug around. Link: https://lore.kernel.org/r/20190723065733.4899-4-leon@kernel.org Cc: # 4.10 Fixes: 49780d42dfc9 ("IB/mlx5: Expose MR cache for mlx5_ib") Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/mr.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 266edaf8029d..b83361aebf28 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -545,14 +545,17 @@ void mlx5_mr_cache_free(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) return; c = order2idx(dev, mr->order); - if (c < 0 || c >= MAX_MR_CACHE_ENTRIES) { - mlx5_ib_warn(dev, "order %d, cache index %d\n", mr->order, c); + WARN_ON(c < 0 || c >= MAX_MR_CACHE_ENTRIES); + + if (unreg_umr(dev, mr)) { + mr->allocated_from_cache = false; + destroy_mkey(dev, mr); + ent = &cache->ent[c]; + if (ent->cur < ent->limit) + queue_work(cache->wq, &ent->work); return; } - if (unreg_umr(dev, mr)) - return; - ent = &cache->ent[c]; spin_lock_irq(&ent->lock); list_add_tail(&mr->list, &ent->head); From 9ec4483a3f0f71a228a5933bc040441322bfb090 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 23 Jul 2019 09:57:27 +0300 Subject: [PATCH 321/823] IB/mlx5: Move MRs to a kernel PD when freeing them to the MR cache Fix unreg_umr to move the MR to a kernel owned PD (i.e. the UMR PD) which can't be accessed by userspace. This ensures that nothing can continue to access the MR once it has been placed in the kernels cache for reuse. MRs in the cache continue to have their HW state, including DMA tables, present. Even though the MR has been invalidated, changing the PD provides an additional layer of protection against use of the MR. Link: https://lore.kernel.org/r/20190723065733.4899-5-leon@kernel.org Cc: # 3.10 Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/mr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index b83361aebf28..7274a9b9df58 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1375,8 +1375,10 @@ static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) return 0; - umrwr.wr.send_flags = MLX5_IB_SEND_UMR_DISABLE_MR; + umrwr.wr.send_flags = MLX5_IB_SEND_UMR_DISABLE_MR | + MLX5_IB_SEND_UMR_UPDATE_PD_ACCESS; umrwr.wr.opcode = MLX5_IB_WR_UMR; + umrwr.pd = dev->umrc.pd; umrwr.mkey = mr->mmkey.key; umrwr.ignore_free_state = 1; From b9332dad987018745a0c0bb718d12dacfa760489 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 23 Jul 2019 09:57:28 +0300 Subject: [PATCH 322/823] IB/mlx5: Fix clean_mr() to work in the expected order Any dma map underlying the MR should only be freed once the MR is fenced at the hardware. As of the above we first destroy the MKEY and just after that can safely call to dma_unmap_single(). Link: https://lore.kernel.org/r/20190723065733.4899-6-leon@kernel.org Cc: # 4.3 Fixes: 8a187ee52b04 ("IB/mlx5: Support the new memory registration API") Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/mr.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 7274a9b9df58..2c77456f359f 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1582,10 +1582,10 @@ static void clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) mr->sig = NULL; } - mlx5_free_priv_descs(mr); - - if (!allocated_from_cache) + if (!allocated_from_cache) { destroy_mkey(dev, mr); + mlx5_free_priv_descs(mr); + } } static void dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) From 527d37e9e575bc0e9024de9b499385e7bb31f1ad Mon Sep 17 00:00:00 2001 From: Joe Lawrence Date: Wed, 24 Jul 2019 16:05:58 -0400 Subject: [PATCH 323/823] selftests/livepatch: add test skip handling Add a skip() message function that stops the test, logs an explanation, and sets the "skip" return code (4). Before loading a livepatch self-test kernel module, first verify that we've built and installed it by running a 'modprobe --dry-run'. This should catch a few environment issues, including !CONFIG_LIVEPATCH and !CONFIG_TEST_LIVEPATCH. In these cases, exit gracefully with the new skip() function. Reported-by: Jiri Benc Suggested-by: Shuah Khan Reviewed-by: Petr Mladek Signed-off-by: Joe Lawrence Signed-off-by: Shuah Khan --- .../testing/selftests/livepatch/functions.sh | 20 +++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index 30195449c63c..edcfeace4655 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -13,6 +13,14 @@ function log() { echo "$1" > /dev/kmsg } +# skip(msg) - testing can't proceed +# msg - explanation +function skip() { + log "SKIP: $1" + echo "SKIP: $1" >&2 + exit 4 +} + # die(msg) - game over, man # msg - dying words function die() { @@ -43,6 +51,12 @@ function loop_until() { done } +function assert_mod() { + local mod="$1" + + modprobe --dry-run "$mod" &>/dev/null +} + function is_livepatch_mod() { local mod="$1" @@ -75,6 +89,9 @@ function __load_mod() { function load_mod() { local mod="$1"; shift + assert_mod "$mod" || + skip "unable to load module ${mod}, verify CONFIG_TEST_LIVEPATCH=m and run self-tests as root" + is_livepatch_mod "$mod" && die "use load_lp() to load the livepatch module $mod" @@ -88,6 +105,9 @@ function load_mod() { function load_lp_nowait() { local mod="$1"; shift + assert_mod "$mod" || + skip "unable to load module ${mod}, verify CONFIG_TEST_LIVEPATCH=m and run self-tests as root" + is_livepatch_mod "$mod" || die "module $mod is not a livepatch" From 50ce73cfbb4aa47ed14d223e3dd6a66ea5c792a1 Mon Sep 17 00:00:00 2001 From: Talel Shenhar Date: Thu, 11 Jul 2019 09:38:59 +0300 Subject: [PATCH 324/823] dt-bindings: interrupt-controller: al-fic: remove redundant binding Remove dt binding description for standard binding. Signed-off-by: Talel Shenhar Signed-off-by: Rob Herring --- .../interrupt-controller/amazon,al-fic.txt | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/Documentation/devicetree/bindings/interrupt-controller/amazon,al-fic.txt b/Documentation/devicetree/bindings/interrupt-controller/amazon,al-fic.txt index 4e82fd575cec..c676b03c752e 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/amazon,al-fic.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/amazon,al-fic.txt @@ -5,21 +5,19 @@ Required properties: - compatible: should be "amazon,al-fic" - reg: physical base address and size of the registers - interrupt-controller: identifies the node as an interrupt controller -- #interrupt-cells: must be 2. - First cell defines the index of the interrupt within the controller. - Second cell is used to specify the trigger type and must be one of the - following: - - bits[3:0] trigger type and level flags - 1 = low-to-high edge triggered - 4 = active high level-sensitive -- interrupt-parent: specifies the parent interrupt controller. +- #interrupt-cells : must be 2. Specifies the number of cells needed to encode + an interrupt source. Supported trigger types are low-to-high edge + triggered and active high level-sensitive. - interrupts: describes which input line in the interrupt parent, this fic's output is connected to. This field property depends on the parent's binding +Please refer to interrupts.txt in this directory for details of the common +Interrupt Controllers bindings used by client devices. + Example: -amazon_fic: interrupt-controller@0xfd8a8500 { +amazon_fic: interrupt-controller@fd8a8500 { compatible = "amazon,al-fic"; interrupt-controller; #interrupt-cells = <2>; From 71be7b0e7d4069822c89146daed800686db8f147 Mon Sep 17 00:00:00 2001 From: Asmaa Mnebhi Date: Wed, 24 Jul 2019 15:32:57 -0400 Subject: [PATCH 325/823] Fix uninitialized variable in ipmb_dev_int.c ret at line 112 of ipmb_dev_int.c is uninitialized which results in a warning during build regressions. This warning was found by build regression/improvement testing for v5.3-rc1. Reported-by: build regression/improvement testing for v5.3-rc1. Fixes: 51bd6f291583 ("Add support for IPMB driver") Signed-off-by: Asmaa Mnebhi Message-Id: <571dbb67cf58411d567953d9fb3739eb4789238b.1563996586.git.Asmaa@mellanox.com> Signed-off-by: Corey Minyard --- drivers/char/ipmi/ipmb_dev_int.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/char/ipmi/ipmb_dev_int.c b/drivers/char/ipmi/ipmb_dev_int.c index 57204335c5f5..285e0b8f9a97 100644 --- a/drivers/char/ipmi/ipmb_dev_int.c +++ b/drivers/char/ipmi/ipmb_dev_int.c @@ -76,7 +76,7 @@ static ssize_t ipmb_read(struct file *file, char __user *buf, size_t count, struct ipmb_dev *ipmb_dev = to_ipmb_dev(file); struct ipmb_request_elem *queue_elem; struct ipmb_msg msg; - ssize_t ret; + ssize_t ret = 0; memset(&msg, 0, sizeof(msg)); From c7148c03db80e44da7197ec5f558f630333c5cad Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Wed, 24 Jul 2019 13:56:37 -0700 Subject: [PATCH 326/823] net/ipv4: cleanup error condition testing Cleanup testing for error condition. Signed-off-by: Pavel Machek Signed-off-by: David S. Miller --- net/ipv4/inet_fragment.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index d666756be5f1..a999451345f9 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -331,7 +331,7 @@ struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key) prev = rhashtable_lookup(&fqdir->rhashtable, key, fqdir->f->rhash_params); if (!prev) fq = inet_frag_create(fqdir, key, &prev); - if (prev && !IS_ERR(prev)) { + if (!IS_ERR_OR_NULL(prev)) { fq = prev; if (!refcount_inc_not_zero(&fq->refcnt)) fq = NULL; From 3bc817d665ac6d9de89f59df522ad86f5b5dfc03 Mon Sep 17 00:00:00 2001 From: Haishuang Yan Date: Wed, 24 Jul 2019 20:00:42 +0800 Subject: [PATCH 327/823] ip6_gre: reload ipv6h in prepare_ip6gre_xmit_ipv6 Since ip6_tnl_parse_tlv_enc_lim() can call pskb_may_pull() which may change skb->data, so we need to re-load ipv6h at the right place. Fixes: 898b29798e36 ("ip6_gre: Refactor ip6gre xmit codes") Cc: William Tu Signed-off-by: Haishuang Yan Acked-by: William Tu Signed-off-by: David S. Miller --- net/ipv6/ip6_gre.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c2049c72f3e5..dd2d0b963260 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -660,12 +660,13 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb, struct flowi6 *fl6, __u8 *dsfield, int *encap_limit) { - struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct ipv6hdr *ipv6h; struct ip6_tnl *t = netdev_priv(dev); __u16 offset; offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */ + ipv6h = ipv6_hdr(skb); if (offset > 0) { struct ipv6_tlv_tnl_enc_lim *tel; From c7fa7f567cab6532be285a5df104617d80bce245 Mon Sep 17 00:00:00 2001 From: Arseny Solokha Date: Wed, 24 Jul 2019 20:31:39 +0700 Subject: [PATCH 328/823] net: phylink: don't start and stop SGMII PHYs in SFP modules twice SFP modules connected using the SGMII interface have their own PHYs which are handled by the struct phylink's phydev field. On the other hand, for the modules connected using 1000Base-X interface that field is not set. Since commit ce0aa27ff3f6 ("sfp: add sfp-bus to bridge between network devices and sfp cages") phylink_start() ends up setting the phydev field using the sfp-bus infrastructure, which eventually calls phy_start() on it, and then calling phy_start() again on the same phydev from phylink_start() itself. Similar call sequence holds for phylink_stop(), only in the reverse order. This results in WARNs during network interface bringup and shutdown when a copper SFP module is connected, as phy_start() and phy_stop() are called twice in a row for the same phy_device: % ip link set up dev eth0 ------------[ cut here ]------------ called from state UP WARNING: CPU: 1 PID: 155 at drivers/net/phy/phy.c:895 phy_start+0x74/0xc0 Modules linked in: CPU: 1 PID: 155 Comm: backend Not tainted 5.2.0+ #1 NIP: c0227bf0 LR: c0227bf0 CTR: c004d224 REGS: df547720 TRAP: 0700 Not tainted (5.2.0+) MSR: 00029000 CR: 24002822 XER: 00000000 GPR00: c0227bf0 df5477d8 df5d7080 00000014 df9d2370 df9d5ac4 1f4eb000 00000001 GPR08: c061fe58 00000000 00000000 df5477d8 0000003c 100c8768 00000000 00000000 GPR16: df486a00 c046f1c8 c046eea0 00000000 c046e904 c0239604 db68449c 00000000 GPR24: e9083204 00000000 00000001 db684460 e9083404 00000000 db6dce00 db6dcc00 NIP [c0227bf0] phy_start+0x74/0xc0 LR [c0227bf0] phy_start+0x74/0xc0 Call Trace: [df5477d8] [c0227bf0] phy_start+0x74/0xc0 (unreliable) [df5477e8] [c023cad0] startup_gfar+0x398/0x3f4 [df547828] [c023cf08] gfar_enet_open+0x364/0x374 [df547898] [c029d870] __dev_open+0xe4/0x140 [df5478c8] [c029db70] __dev_change_flags+0xf0/0x188 [df5478f8] [c029dc28] dev_change_flags+0x20/0x54 [df547918] [c02ae304] do_setlink+0x310/0x818 [df547a08] [c02b1eb8] __rtnl_newlink+0x384/0x6b0 [df547c28] [c02b222c] rtnl_newlink+0x48/0x68 [df547c48] [c02ad7c8] rtnetlink_rcv_msg+0x240/0x27c [df547c98] [c02cc068] netlink_rcv_skb+0x8c/0xf0 [df547cd8] [c02cba3c] netlink_unicast+0x114/0x19c [df547d08] [c02cbd74] netlink_sendmsg+0x2b0/0x2c0 [df547d58] [c027b668] sock_sendmsg_nosec+0x20/0x40 [df547d68] [c027d080] ___sys_sendmsg+0x17c/0x1dc [df547e98] [c027df7c] __sys_sendmsg+0x68/0x84 [df547ef8] [c027e430] sys_socketcall+0x1a0/0x204 [df547f38] [c000d1d8] ret_from_syscall+0x0/0x38 --- interrupt: c01 at 0xfd4e030 LR = 0xfd4e010 Instruction dump: 813f0188 38800000 2b890005 419d0014 3d40c046 5529103a 394aa208 7c8a482e 3c60c046 3863a1b8 4cc63182 4be009a1 <0fe00000> 48000030 3c60c046 3863a1d0 ---[ end trace d4c095aeaf6ea998 ]--- and % ip link set down dev eth0 ------------[ cut here ]------------ called from state HALTED WARNING: CPU: 1 PID: 184 at drivers/net/phy/phy.c:858 phy_stop+0x3c/0x88 <...> Call Trace: [df581788] [c0228450] phy_stop+0x3c/0x88 (unreliable) [df581798] [c022d548] sfp_sm_phy_detach+0x1c/0x44 [df5817a8] [c022e8cc] sfp_sm_event+0x4b0/0x87c [df581848] [c022f04c] sfp_upstream_stop+0x34/0x44 [df581858] [c0225608] phylink_stop+0x7c/0xe4 [df581868] [c023c57c] stop_gfar+0x7c/0x94 [df581888] [c023c5b8] gfar_close+0x24/0x94 [df5818a8] [c0298688] __dev_close_many+0xdc/0xf8 [df5818c8] [c029db58] __dev_change_flags+0xd8/0x188 [df5818f8] [c029dc28] dev_change_flags+0x20/0x54 [df581918] [c02ae304] do_setlink+0x310/0x818 [df581a08] [c02b1eb8] __rtnl_newlink+0x384/0x6b0 [df581c28] [c02b222c] rtnl_newlink+0x48/0x68 [df581c48] [c02ad7c8] rtnetlink_rcv_msg+0x240/0x27c [df581c98] [c02cc068] netlink_rcv_skb+0x8c/0xf0 [df581cd8] [c02cba3c] netlink_unicast+0x114/0x19c [df581d08] [c02cbd74] netlink_sendmsg+0x2b0/0x2c0 [df581d58] [c027b668] sock_sendmsg_nosec+0x20/0x40 [df581d68] [c027d080] ___sys_sendmsg+0x17c/0x1dc [df581e98] [c027df7c] __sys_sendmsg+0x68/0x84 [df581ef8] [c027e430] sys_socketcall+0x1a0/0x204 [df581f38] [c000d1d8] ret_from_syscall+0x0/0x38 <...> ---[ end trace d4c095aeaf6ea999 ]--- SFP modules with the 1000Base-X interface are not affected. Place explicit calls to phy_start() and phy_stop() before enabling or after disabling an attached SFP module, where phydev is not yet set (or is already unset), so they will be made only from the inside of sfp-bus, if needed. Fixes: 217962615662 ("net: phy: warn if phy_start is called from invalid state") Signed-off-by: Arseny Solokha Acked-by: Russell King Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 5d0af041b8f9..b45862465c4d 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -990,10 +990,10 @@ void phylink_start(struct phylink *pl) } if (pl->link_an_mode == MLO_AN_FIXED && pl->get_fixed_state) mod_timer(&pl->link_poll, jiffies + HZ); - if (pl->sfp_bus) - sfp_upstream_start(pl->sfp_bus); if (pl->phydev) phy_start(pl->phydev); + if (pl->sfp_bus) + sfp_upstream_start(pl->sfp_bus); } EXPORT_SYMBOL_GPL(phylink_start); @@ -1010,10 +1010,10 @@ void phylink_stop(struct phylink *pl) { ASSERT_RTNL(); - if (pl->phydev) - phy_stop(pl->phydev); if (pl->sfp_bus) sfp_upstream_stop(pl->sfp_bus); + if (pl->phydev) + phy_stop(pl->phydev); del_timer_sync(&pl->link_poll); if (pl->link_irq) { free_irq(pl->link_irq, pl); From 2756d9143aa517b97961e85412882b8ce31371a6 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 19 Jul 2019 10:27:54 +0200 Subject: [PATCH 329/823] ALSA: hda - Fix intermittent CORB/RIRB stall on Intel chips It turned out that the recent Intel HD-audio controller chips show a significant stall during the system PM resume intermittently. It doesn't happen so often and usually it may read back successfully after one or more seconds, but in some rare worst cases the driver went into fallback mode. After trial-and-error, we found out that the communication stall seems covered by issuing the sync after each verb write, as already done for AMD and other chipsets. So this patch enables the write-sync flag for the recent Intel chips, Skylake and onward, as a workaround. Also, since Broxton and co have the very same driver flags as Skylake, refer to the Skylake driver flags instead of defining the same contents again for simplification. BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=201901 Reported-and-tested-by: Todd Brandt Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_intel.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index cb8b0945547c..1e14d7270adf 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -313,11 +313,10 @@ enum { #define AZX_DCAPS_INTEL_SKYLAKE \ (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\ + AZX_DCAPS_SYNC_WRITE |\ AZX_DCAPS_SEPARATE_STREAM_TAG | AZX_DCAPS_I915_COMPONENT) -#define AZX_DCAPS_INTEL_BROXTON \ - (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\ - AZX_DCAPS_SEPARATE_STREAM_TAG | AZX_DCAPS_I915_COMPONENT) +#define AZX_DCAPS_INTEL_BROXTON AZX_DCAPS_INTEL_SKYLAKE /* quirks for ATI SB / AMD Hudson */ #define AZX_DCAPS_PRESET_ATI_SB \ From f972037e71246c5e0916eef835174d58ffc517e4 Mon Sep 17 00:00:00 2001 From: Andreas Schwab Date: Wed, 24 Jul 2019 17:32:57 +0200 Subject: [PATCH 330/823] net: phy: mscc: initialize stats array The memory allocated for the stats array may contain arbitrary data. Fixes: e4f9ba642f0b ("net: phy: mscc: add support for VSC8514 PHY.") Fixes: 00d70d8e0e78 ("net: phy: mscc: add support for VSC8574 PHY") Fixes: a5afc1678044 ("net: phy: mscc: add support for VSC8584 PHY") Fixes: f76178dc5218 ("net: phy: mscc: add ethtool statistics counters") Signed-off-by: Andreas Schwab Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/mscc.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c index 28676af97b42..645d354ffb48 100644 --- a/drivers/net/phy/mscc.c +++ b/drivers/net/phy/mscc.c @@ -2226,8 +2226,8 @@ static int vsc8514_probe(struct phy_device *phydev) vsc8531->supp_led_modes = VSC85XX_SUPP_LED_MODES; vsc8531->hw_stats = vsc85xx_hw_stats; vsc8531->nstats = ARRAY_SIZE(vsc85xx_hw_stats); - vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats, - sizeof(u64), GFP_KERNEL); + vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, + sizeof(u64), GFP_KERNEL); if (!vsc8531->stats) return -ENOMEM; @@ -2251,8 +2251,8 @@ static int vsc8574_probe(struct phy_device *phydev) vsc8531->supp_led_modes = VSC8584_SUPP_LED_MODES; vsc8531->hw_stats = vsc8584_hw_stats; vsc8531->nstats = ARRAY_SIZE(vsc8584_hw_stats); - vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats, - sizeof(u64), GFP_KERNEL); + vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, + sizeof(u64), GFP_KERNEL); if (!vsc8531->stats) return -ENOMEM; @@ -2281,8 +2281,8 @@ static int vsc8584_probe(struct phy_device *phydev) vsc8531->supp_led_modes = VSC8584_SUPP_LED_MODES; vsc8531->hw_stats = vsc8584_hw_stats; vsc8531->nstats = ARRAY_SIZE(vsc8584_hw_stats); - vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats, - sizeof(u64), GFP_KERNEL); + vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, + sizeof(u64), GFP_KERNEL); if (!vsc8531->stats) return -ENOMEM; @@ -2311,8 +2311,8 @@ static int vsc85xx_probe(struct phy_device *phydev) vsc8531->supp_led_modes = VSC85XX_SUPP_LED_MODES; vsc8531->hw_stats = vsc85xx_hw_stats; vsc8531->nstats = ARRAY_SIZE(vsc85xx_hw_stats); - vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats, - sizeof(u64), GFP_KERNEL); + vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, + sizeof(u64), GFP_KERNEL); if (!vsc8531->stats) return -ENOMEM; From 47b79bbb19e1cfc615823ccaac258cdd2c810c47 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Jul 2019 11:02:48 -0700 Subject: [PATCH 331/823] net/tls: add myself as a co-maintainer I've been spending quite a bit of time fixing and preventing bit rot in the core TLS code. TLS seems to only be growing in importance, I'd like to help ensuring the quality of our implementation. Signed-off-by: Jakub Kicinski Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Simon Horman Signed-off-by: David S. Miller --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 783569e3c4b4..3ff2e6ab3cf4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11282,6 +11282,7 @@ M: Aviad Yehezkel M: Dave Watson M: John Fastabend M: Daniel Borkmann +M: Jakub Kicinski L: netdev@vger.kernel.org S: Maintained F: net/tls/* From 260637903f47f20c5918bb5c1eea52b2a28ea863 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Jul 2019 17:00:01 +0200 Subject: [PATCH 332/823] ovs: datapath: hide clang frame-overflow warnings Some functions in the datapath code are factored out so that each one has a stack frame smaller than 1024 bytes with gcc. However, when compiling with clang, the functions are inlined more aggressively and combined again so we get net/openvswitch/datapath.c:1124:12: error: stack frame size of 1528 bytes in function 'ovs_flow_cmd_set' [-Werror,-Wframe-larger-than=] Marking both get_flow_actions() and ovs_nla_init_match_and_action() as 'noinline_for_stack' gives us the same behavior that we see with gcc, and no warning. Note that this does not mean we actually use less stack, as the functions call each other, and we still get three copies of the large 'struct sw_flow_key' type on the stack. The comment tells us that this was previously considered safe, presumably since the netlink parsing functions are called with a known backchain that does not also use a lot of stack space. Fixes: 9cc9a5cb176c ("datapath: Avoid using stack larger than 1024.") Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- net/openvswitch/datapath.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 892287d06c17..d01410e52097 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1047,7 +1047,7 @@ error: } /* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */ -static struct sw_flow_actions *get_flow_actions(struct net *net, +static noinline_for_stack struct sw_flow_actions *get_flow_actions(struct net *net, const struct nlattr *a, const struct sw_flow_key *key, const struct sw_flow_mask *mask, @@ -1081,12 +1081,13 @@ static struct sw_flow_actions *get_flow_actions(struct net *net, * we should not to return match object with dangling reference * to mask. * */ -static int ovs_nla_init_match_and_action(struct net *net, - struct sw_flow_match *match, - struct sw_flow_key *key, - struct nlattr **a, - struct sw_flow_actions **acts, - bool log) +static noinline_for_stack int +ovs_nla_init_match_and_action(struct net *net, + struct sw_flow_match *match, + struct sw_flow_key *key, + struct nlattr **a, + struct sw_flow_actions **acts, + bool log) { struct sw_flow_mask mask; int error = 0; From 4638faac032756f7eab5524be7be56bee77e426b Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 22 Jul 2019 20:41:22 -0700 Subject: [PATCH 333/823] netrom: hold sock when setting skb->destructor sock_efree() releases the sock refcnt, if we don't hold this refcnt when setting skb->destructor to it, the refcnt would not be balanced. This leads to several bug reports from syzbot. I have checked other users of sock_efree(), all of them hold the sock refcnt. Fixes: c8c8218ec5af ("netrom: fix a memory leak in nr_rx_frame()") Reported-and-tested-by: Reported-and-tested-by: Reported-and-tested-by: Reported-and-tested-by: Cc: Ralf Baechle Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/netrom/af_netrom.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 96740d389377..c4f54ad2b98a 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -967,6 +967,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) window = skb->data[20]; + sock_hold(make); skb->sk = make; skb->destructor = sock_efree; make->sk_state = TCP_ESTABLISHED; From e3cacb73e626d885b8cf24103fed0ae26518e3c4 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Wed, 24 Jul 2019 17:39:47 -0700 Subject: [PATCH 334/823] xtensa: fix build for cores with coprocessors Assembly entry/return abstraction change didn't add asmmacro.h include statement to coprocessor.S, resulting in references to undefined macros abi_entry and abi_ret on cores that define XTENSA_HAVE_COPROCESSORS. Fix that by including asm/asmmacro.h from the coprocessor.S. Signed-off-by: Max Filippov --- arch/xtensa/kernel/coprocessor.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S index 60c220020054..80828b95a51f 100644 --- a/arch/xtensa/kernel/coprocessor.S +++ b/arch/xtensa/kernel/coprocessor.S @@ -14,6 +14,7 @@ #include #include +#include #include #include #include From 882a0db9d143e5e8dac54b96e83135bccd1f68d1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Jul 2019 17:47:26 -0500 Subject: [PATCH 335/823] objtool: Improve UACCESS coverage A clang build reported an (obvious) double CLAC while a GCC build did not; it turns out that objtool only re-visits instructions if the first visit was with AC=0. If OTOH the first visit was with AC=1, it completely ignores any subsequent visit, even when it has AC=0. Fix this by using a visited mask instead of a boolean, and (explicitly) mark the AC state. $ ./objtool check -b --no-fp --retpoline --uaccess drivers/gpu/drm/i915/gem/i915_gem_execbuffer.o drivers/gpu/drm/i915/gem/i915_gem_execbuffer.o: warning: objtool: .altinstr_replacement+0x22: redundant UACCESS disable drivers/gpu/drm/i915/gem/i915_gem_execbuffer.o: warning: objtool: eb_copy_relocations.isra.34()+0xea: (alt) drivers/gpu/drm/i915/gem/i915_gem_execbuffer.o: warning: objtool: .altinstr_replacement+0xffffffffffffffff: (branch) drivers/gpu/drm/i915/gem/i915_gem_execbuffer.o: warning: objtool: eb_copy_relocations.isra.34()+0xd9: (alt) drivers/gpu/drm/i915/gem/i915_gem_execbuffer.o: warning: objtool: eb_copy_relocations.isra.34()+0xb2: (branch) drivers/gpu/drm/i915/gem/i915_gem_execbuffer.o: warning: objtool: eb_copy_relocations.isra.34()+0x39: (branch) drivers/gpu/drm/i915/gem/i915_gem_execbuffer.o: warning: objtool: eb_copy_relocations.isra.34()+0x0: <=== (func) Reported-by: Josh Poimboeuf Reported-by: Thomas Gleixner Reported-by: Sedat Dilek Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Tested-by: Nathan Chancellor Tested-by: Nick Desaulniers Tested-by: Sedat Dilek Link: https://github.com/ClangBuiltLinux/linux/issues/617 Link: https://lkml.kernel.org/r/5359166aad2d53f3145cd442d83d0e5115e0cd17.1564007838.git.jpoimboe@redhat.com --- tools/objtool/check.c | 7 ++++--- tools/objtool/check.h | 3 ++- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 5f26620f13f5..176f2f084060 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1946,6 +1946,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, struct alternative *alt; struct instruction *insn, *next_insn; struct section *sec; + u8 visited; int ret; insn = first; @@ -1972,12 +1973,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, return 1; } + visited = 1 << state.uaccess; if (insn->visited) { if (!insn->hint && !insn_state_match(insn, &state)) return 1; - /* If we were here with AC=0, but now have AC=1, go again */ - if (insn->state.uaccess || !state.uaccess) + if (insn->visited & visited) return 0; } @@ -2024,7 +2025,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, } else insn->state = state; - insn->visited = true; + insn->visited |= visited; if (!insn->ignore_alts) { bool skip_orig = false; diff --git a/tools/objtool/check.h b/tools/objtool/check.h index b881fafcf55d..6d875ca6fce0 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -33,8 +33,9 @@ struct instruction { unsigned int len; enum insn_type type; unsigned long immediate; - bool alt_group, visited, dead_end, ignore, hint, save, restore, ignore_alts; + bool alt_group, dead_end, ignore, hint, save, restore, ignore_alts; bool retpoline_safe; + u8 visited; struct symbol *call_dest; struct instruction *jump_dest; struct instruction *first_jump_src; From cb81572e8cb50c5fb98b0b962cdfe48fff71fd37 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Tue, 23 Jul 2019 15:27:52 +0200 Subject: [PATCH 336/823] netfilter: nf_tables: Make nft_meta expression more robust nft_meta_get_eval()'s tendency to bail out setting NFT_BREAK verdict in situations where required data is missing leads to unexpected behaviour with inverted checks like so: | meta iifname != eth0 accept This rule will never match if there is no input interface (or it is not known) which is not intuitive and, what's worse, breaks consistency of iptables-nft with iptables-legacy. Fix this by falling back to placing a value in dreg which never matches (avoiding accidental matches), i.e. zero for interface index and an empty string for interface name. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/nft_meta_bridge.c | 6 +----- net/netfilter/nft_meta.c | 16 ++++------------ 2 files changed, 5 insertions(+), 17 deletions(-) diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index bed66f536b34..a98dec2cf0cf 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -30,13 +30,9 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr, switch (priv->key) { case NFT_META_BRI_IIFNAME: br_dev = nft_meta_get_bridge(in); - if (!br_dev) - goto err; break; case NFT_META_BRI_OIFNAME: br_dev = nft_meta_get_bridge(out); - if (!br_dev) - goto err; break; case NFT_META_BRI_IIFPVID: { u16 p_pvid; @@ -64,7 +60,7 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr, goto out; } - strncpy((char *)dest, br_dev->name, IFNAMSIZ); + strncpy((char *)dest, br_dev ? br_dev->name : "", IFNAMSIZ); return; out: return nft_meta_get_eval(expr, regs, pkt); diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index f1b1d948c07b..f69afb9ff3cb 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -60,24 +60,16 @@ void nft_meta_get_eval(const struct nft_expr *expr, *dest = skb->mark; break; case NFT_META_IIF: - if (in == NULL) - goto err; - *dest = in->ifindex; + *dest = in ? in->ifindex : 0; break; case NFT_META_OIF: - if (out == NULL) - goto err; - *dest = out->ifindex; + *dest = out ? out->ifindex : 0; break; case NFT_META_IIFNAME: - if (in == NULL) - goto err; - strncpy((char *)dest, in->name, IFNAMSIZ); + strncpy((char *)dest, in ? in->name : "", IFNAMSIZ); break; case NFT_META_OIFNAME: - if (out == NULL) - goto err; - strncpy((char *)dest, out->name, IFNAMSIZ); + strncpy((char *)dest, out ? out->name : "", IFNAMSIZ); break; case NFT_META_IIFTYPE: if (in == NULL) From 67d86835840a533ce868c42a7f05507e66ba95f0 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Tue, 23 Jul 2019 15:27:53 +0200 Subject: [PATCH 337/823] netfilter: nft_meta_bridge: Eliminate 'out' label The label is used just once and the code it points at is not reused, no point in keeping it. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/nft_meta_bridge.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index a98dec2cf0cf..1804e867f715 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -57,13 +57,11 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr, return; } default: - goto out; + return nft_meta_get_eval(expr, regs, pkt); } strncpy((char *)dest, br_dev ? br_dev->name : "", IFNAMSIZ); return; -out: - return nft_meta_get_eval(expr, regs, pkt); err: regs->verdict.code = NFT_BREAK; } From 3f8809499bf02ef7874254c5e23fc764a47a21a0 Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Thu, 25 Jul 2019 14:57:37 +0800 Subject: [PATCH 338/823] ALSA: hda - Add a conexant codec entry to let mute led work This conexant codec isn't in the supported codec list yet, the hda generic driver can drive this codec well, but on a Lenovo machine with mute/mic-mute leds, we need to apply CXT_FIXUP_THINKPAD_ACPI to make the leds work. After adding this codec to the list, the driver patch_conexant.c will apply THINKPAD_ACPI to this machine. Cc: stable@vger.kernel.org Signed-off-by: Hui Wang Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_conexant.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 4f8d0845ee1e..f299f137eaea 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -1083,6 +1083,7 @@ static int patch_conexant_auto(struct hda_codec *codec) */ static const struct hda_device_id snd_hda_id_conexant[] = { + HDA_CODEC_ENTRY(0x14f11f86, "CX8070", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f12008, "CX8200", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15045, "CX20549 (Venice)", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15047, "CX20551 (Waikiki)", patch_conexant_auto), From f3dccdaade4118070a3a47bef6b18321431f9ac6 Mon Sep 17 00:00:00 2001 From: Ryan Kennedy Date: Thu, 4 Jul 2019 11:35:28 -0400 Subject: [PATCH 339/823] usb: pci-quirks: Correct AMD PLL quirk detection The AMD PLL USB quirk is incorrectly enabled on newer Ryzen chipsets. The logic in usb_amd_find_chipset_info currently checks for unaffected chipsets rather than affected ones. This broke once a new chipset was added in e788787ef. It makes more sense to reverse the logic so it won't need to be updated as new chipsets are added. Note that the core of the workaround in usb_amd_quirk_pll does correctly check the chipset. Signed-off-by: Ryan Kennedy Fixes: e788787ef4f9 ("usb:xhci:Add quirk for Certain failing HP keyboard on reset after resume") Cc: stable Acked-by: Alan Stern Link: https://lore.kernel.org/r/20190704153529.9429-2-ryan5544@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/pci-quirks.c | 31 +++++++++++++++++++------------ 1 file changed, 19 insertions(+), 12 deletions(-) diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 3ce71cbfbb58..ad05c27b3a7b 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -205,7 +205,7 @@ int usb_amd_find_chipset_info(void) { unsigned long flags; struct amd_chipset_info info; - int ret; + int need_pll_quirk = 0; spin_lock_irqsave(&amd_lock, flags); @@ -219,21 +219,28 @@ int usb_amd_find_chipset_info(void) spin_unlock_irqrestore(&amd_lock, flags); if (!amd_chipset_sb_type_init(&info)) { - ret = 0; goto commit; } - /* Below chipset generations needn't enable AMD PLL quirk */ - if (info.sb_type.gen == AMD_CHIPSET_UNKNOWN || - info.sb_type.gen == AMD_CHIPSET_SB600 || - info.sb_type.gen == AMD_CHIPSET_YANGTZE || - (info.sb_type.gen == AMD_CHIPSET_SB700 && - info.sb_type.rev > 0x3b)) { + switch (info.sb_type.gen) { + case AMD_CHIPSET_SB700: + need_pll_quirk = info.sb_type.rev <= 0x3B; + break; + case AMD_CHIPSET_SB800: + case AMD_CHIPSET_HUDSON2: + case AMD_CHIPSET_BOLTON: + need_pll_quirk = 1; + break; + default: + need_pll_quirk = 0; + break; + } + + if (!need_pll_quirk) { if (info.smbus_dev) { pci_dev_put(info.smbus_dev); info.smbus_dev = NULL; } - ret = 0; goto commit; } @@ -252,7 +259,7 @@ int usb_amd_find_chipset_info(void) } } - ret = info.probe_result = 1; + need_pll_quirk = info.probe_result = 1; printk(KERN_DEBUG "QUIRK: Enable AMD PLL fix\n"); commit: @@ -263,7 +270,7 @@ commit: /* Mark that we where here */ amd_chipset.probe_count++; - ret = amd_chipset.probe_result; + need_pll_quirk = amd_chipset.probe_result; spin_unlock_irqrestore(&amd_lock, flags); @@ -277,7 +284,7 @@ commit: spin_unlock_irqrestore(&amd_lock, flags); } - return ret; + return need_pll_quirk; } EXPORT_SYMBOL_GPL(usb_amd_find_chipset_info); From 4fbb8aa75836c3361987f431d9451aecc1830bdd Mon Sep 17 00:00:00 2001 From: Ryan Kennedy Date: Thu, 4 Jul 2019 11:35:29 -0400 Subject: [PATCH 340/823] usb: pci-quirks: Minor cleanup for AMD PLL quirk usb_amd_find_chipset_info() is used for chipset detection for several quirks. It is strange that its return value indicates the need for the PLL quirk, which means it is often ignored. This patch adds a function specifically for checking the PLL quirk like the other ones. Additionally, rename probe_result to something more appropriate. Signed-off-by: Ryan Kennedy Acked-by: Alan Stern Link: https://lore.kernel.org/r/20190704153529.9429-3-ryan5544@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/ehci-pci.c | 4 ++-- drivers/usb/host/ohci-pci.c | 2 +- drivers/usb/host/pci-quirks.c | 30 ++++++++++++++++-------------- drivers/usb/host/pci-quirks.h | 2 +- drivers/usb/host/xhci-pci.c | 2 +- 5 files changed, 21 insertions(+), 19 deletions(-) diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c index fe9422d3bcdc..b0882c13a1d1 100644 --- a/drivers/usb/host/ehci-pci.c +++ b/drivers/usb/host/ehci-pci.c @@ -149,7 +149,7 @@ static int ehci_pci_setup(struct usb_hcd *hcd) break; case PCI_VENDOR_ID_AMD: /* AMD PLL quirk */ - if (usb_amd_find_chipset_info()) + if (usb_amd_quirk_pll_check()) ehci->amd_pll_fix = 1; /* AMD8111 EHCI doesn't work, according to AMD errata */ if (pdev->device == 0x7463) { @@ -186,7 +186,7 @@ static int ehci_pci_setup(struct usb_hcd *hcd) break; case PCI_VENDOR_ID_ATI: /* AMD PLL quirk */ - if (usb_amd_find_chipset_info()) + if (usb_amd_quirk_pll_check()) ehci->amd_pll_fix = 1; /* diff --git a/drivers/usb/host/ohci-pci.c b/drivers/usb/host/ohci-pci.c index a033f7d855e0..f4e13a3fddee 100644 --- a/drivers/usb/host/ohci-pci.c +++ b/drivers/usb/host/ohci-pci.c @@ -152,7 +152,7 @@ static int ohci_quirk_amd700(struct usb_hcd *hcd) { struct ohci_hcd *ohci = hcd_to_ohci(hcd); - if (usb_amd_find_chipset_info()) + if (usb_amd_quirk_pll_check()) ohci->flags |= OHCI_QUIRK_AMD_PLL; /* SB800 needs pre-fetch fix */ diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index ad05c27b3a7b..f6d04491df60 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -132,7 +132,7 @@ static struct amd_chipset_info { struct amd_chipset_type sb_type; int isoc_reqs; int probe_count; - int probe_result; + bool need_pll_quirk; } amd_chipset; static DEFINE_SPINLOCK(amd_lock); @@ -201,11 +201,11 @@ void sb800_prefetch(struct device *dev, int on) } EXPORT_SYMBOL_GPL(sb800_prefetch); -int usb_amd_find_chipset_info(void) +static void usb_amd_find_chipset_info(void) { unsigned long flags; struct amd_chipset_info info; - int need_pll_quirk = 0; + info.need_pll_quirk = 0; spin_lock_irqsave(&amd_lock, flags); @@ -213,7 +213,7 @@ int usb_amd_find_chipset_info(void) if (amd_chipset.probe_count > 0) { amd_chipset.probe_count++; spin_unlock_irqrestore(&amd_lock, flags); - return amd_chipset.probe_result; + return; } memset(&info, 0, sizeof(info)); spin_unlock_irqrestore(&amd_lock, flags); @@ -224,19 +224,19 @@ int usb_amd_find_chipset_info(void) switch (info.sb_type.gen) { case AMD_CHIPSET_SB700: - need_pll_quirk = info.sb_type.rev <= 0x3B; + info.need_pll_quirk = info.sb_type.rev <= 0x3B; break; case AMD_CHIPSET_SB800: case AMD_CHIPSET_HUDSON2: case AMD_CHIPSET_BOLTON: - need_pll_quirk = 1; + info.need_pll_quirk = 1; break; default: - need_pll_quirk = 0; + info.need_pll_quirk = 0; break; } - if (!need_pll_quirk) { + if (!info.need_pll_quirk) { if (info.smbus_dev) { pci_dev_put(info.smbus_dev); info.smbus_dev = NULL; @@ -259,7 +259,6 @@ int usb_amd_find_chipset_info(void) } } - need_pll_quirk = info.probe_result = 1; printk(KERN_DEBUG "QUIRK: Enable AMD PLL fix\n"); commit: @@ -270,7 +269,6 @@ commit: /* Mark that we where here */ amd_chipset.probe_count++; - need_pll_quirk = amd_chipset.probe_result; spin_unlock_irqrestore(&amd_lock, flags); @@ -283,10 +281,7 @@ commit: amd_chipset = info; spin_unlock_irqrestore(&amd_lock, flags); } - - return need_pll_quirk; } -EXPORT_SYMBOL_GPL(usb_amd_find_chipset_info); int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *pdev) { @@ -322,6 +317,13 @@ bool usb_amd_prefetch_quirk(void) } EXPORT_SYMBOL_GPL(usb_amd_prefetch_quirk); +bool usb_amd_quirk_pll_check(void) +{ + usb_amd_find_chipset_info(); + return amd_chipset.need_pll_quirk; +} +EXPORT_SYMBOL_GPL(usb_amd_quirk_pll_check); + /* * The hardware normally enables the A-link power management feature, which * lets the system lower the power consumption in idle states. @@ -527,7 +529,7 @@ void usb_amd_dev_put(void) amd_chipset.nb_type = 0; memset(&amd_chipset.sb_type, 0, sizeof(amd_chipset.sb_type)); amd_chipset.isoc_reqs = 0; - amd_chipset.probe_result = 0; + amd_chipset.need_pll_quirk = 0; spin_unlock_irqrestore(&amd_lock, flags); diff --git a/drivers/usb/host/pci-quirks.h b/drivers/usb/host/pci-quirks.h index 63c633077d9e..e729de21fad7 100644 --- a/drivers/usb/host/pci-quirks.h +++ b/drivers/usb/host/pci-quirks.h @@ -5,11 +5,11 @@ #ifdef CONFIG_USB_PCI void uhci_reset_hc(struct pci_dev *pdev, unsigned long base); int uhci_check_and_reset_hc(struct pci_dev *pdev, unsigned long base); -int usb_amd_find_chipset_info(void); int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *pdev); bool usb_amd_hang_symptom_quirk(void); bool usb_amd_prefetch_quirk(void); void usb_amd_dev_put(void); +bool usb_amd_quirk_pll_check(void); void usb_amd_quirk_pll_disable(void); void usb_amd_quirk_pll_enable(void); void usb_asmedia_modifyflowcontrol(struct pci_dev *pdev); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index c2fe218e051f..1e0236e90687 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -130,7 +130,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_AMD_0x96_HOST; /* AMD PLL quirk */ - if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info()) + if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_quirk_pll_check()) xhci->quirks |= XHCI_AMD_PLL_FIX; if (pdev->vendor == PCI_VENDOR_ID_AMD && From d74ffae8b8dd17eaa8b82fc163e6aa2076dc8fb1 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Mon, 22 Jul 2019 19:58:25 +0900 Subject: [PATCH 341/823] usb-storage: Add a limitation for blk_queue_max_hw_sectors() This patch fixes an issue that the following error happens on swiotlb environment: xhci-hcd ee000000.usb: swiotlb buffer is full (sz: 524288 bytes), total 32768 (slots), used 1338 (slots) On the kernel v5.1, block settings of a usb-storage with SuperSpeed were the following so that the block layer will allocate buffers up to 64 KiB, and then the issue didn't happen. max_segment_size = 65536 max_hw_sectors_kb = 1024 After the commit 09324d32d2a0 ("block: force an unlimited segment size on queues with a virt boundary") is applied, the block settings are the following. So, the block layer will allocate buffers up to 1024 KiB, and then the issue happens: max_segment_size = 4294967295 max_hw_sectors_kb = 1024 To fix the issue, the usb-storage driver checks the maximum size of a mapping for the device and then adjusts the max_hw_sectors_kb if required. After this patch is applied, the block settings will be the following, and then the issue doesn't happen. max_segment_size = 4294967295 max_hw_sectors_kb = 256 Fixes: 09324d32d2a0 ("block: force an unlimited segment size on queues with a virt boundary") Cc: stable Signed-off-by: Yoshihiro Shimoda Acked-by: Alan Stern Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/1563793105-20597-1-git-send-email-yoshihiro.shimoda.uh@renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/scsiglue.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 30790240aec6..05b80211290d 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -28,6 +28,8 @@ * status of a command. */ +#include +#include #include #include @@ -99,6 +101,7 @@ static int slave_alloc (struct scsi_device *sdev) static int slave_configure(struct scsi_device *sdev) { struct us_data *us = host_to_us(sdev->host); + struct device *dev = us->pusb_dev->bus->sysdev; /* * Many devices have trouble transferring more than 32KB at a time, @@ -128,6 +131,14 @@ static int slave_configure(struct scsi_device *sdev) blk_queue_max_hw_sectors(sdev->request_queue, 2048); } + /* + * The max_hw_sectors should be up to maximum size of a mapping for + * the device. Otherwise, a DMA API might fail on swiotlb environment. + */ + blk_queue_max_hw_sectors(sdev->request_queue, + min_t(size_t, queue_max_hw_sectors(sdev->request_queue), + dma_max_mapping_size(dev) >> SECTOR_SHIFT)); + /* * Some USB host controllers can't do DMA; they have to use PIO. * They indicate this by setting their dma_mask to NULL. For From 94b9a70d32db0d1e8eeaeb27d74a5ae712644da9 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 7 Jun 2019 16:57:09 +0300 Subject: [PATCH 342/823] usb/hcd: Fix a NULL vs IS_ERR() bug in usb_hcd_setup_local_mem() The devm_memremap() function doesn't return NULL, it returns error pointers. Fixes: b0310c2f09bb ("USB: use genalloc for USB HCs with local memory") Signed-off-by: Dan Carpenter Acked-by: Sebastian Andrzej Siewior Link: https://lore.kernel.org/r/20190607135709.GC16718@mwanda Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hcd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 88533938ce19..9320787ac2e6 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -3052,8 +3052,8 @@ int usb_hcd_setup_local_mem(struct usb_hcd *hcd, phys_addr_t phys_addr, local_mem = devm_memremap(hcd->self.sysdev, phys_addr, size, MEMREMAP_WC); - if (!local_mem) - return -ENOMEM; + if (IS_ERR(local_mem)) + return PTR_ERR(local_mem); /* * Here we pass a dma_addr_t but the arg type is a phys_addr_t. From f90bf1ece48a736097ea224430578fe586a9544c Mon Sep 17 00:00:00 2001 From: Phong Tran Date: Wed, 24 Jul 2019 09:06:01 +0700 Subject: [PATCH 343/823] usb: wusbcore: fix unbalanced get/put cluster_id syzboot reported that https://syzkaller.appspot.com/bug?extid=fd2bd7df88c606eea4ef There is not consitency parameter in cluste_id_get/put calling. In case of getting the id with result is failure, the wusbhc->cluster_id will not be updated and this can not be used for wusb_cluster_id_put(). Tested report https://groups.google.com/d/msg/syzkaller-bugs/0znZopp3-9k/oxOrhLkLEgAJ Reproduce and gdb got the details: 139 addr = wusb_cluster_id_get(); (gdb) n 140 if (addr == 0) (gdb) print addr $1 = 254 '\376' (gdb) n 142 result = __hwahc_set_cluster_id(hwahc, addr); (gdb) print result $2 = -71 (gdb) break wusb_cluster_id_put Breakpoint 3 at 0xffffffff836e3f20: file drivers/usb/wusbcore/wusbhc.c, line 384. (gdb) s Thread 2 hit Breakpoint 3, wusb_cluster_id_put (id=0 '\000') at drivers/usb/wusbcore/wusbhc.c:384 384 id = 0xff - id; (gdb) n 385 BUG_ON(id >= CLUSTER_IDS); (gdb) print id $3 = 255 '\377' Reported-by: syzbot+fd2bd7df88c606eea4ef@syzkaller.appspotmail.com Signed-off-by: Phong Tran Cc: stable Link: https://lore.kernel.org/r/20190724020601.15257-1-tranmanphong@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/hwa-hc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/hwa-hc.c b/drivers/usb/host/hwa-hc.c index 09a8ebd95588..6968b9f2b76b 100644 --- a/drivers/usb/host/hwa-hc.c +++ b/drivers/usb/host/hwa-hc.c @@ -159,7 +159,7 @@ out: return result; error_set_cluster_id: - wusb_cluster_id_put(wusbhc->cluster_id); + wusb_cluster_id_put(addr); error_cluster_id_get: goto out; From d9c5252295218df4cfe64353aa860d7b5c8700ef Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 25 Jul 2019 16:58:31 +0900 Subject: [PATCH 344/823] treewide: add "WITH Linux-syscall-note" to SPDX tag of uapi headers UAPI headers licensed under GPL are supposed to have exception "WITH Linux-syscall-note" so that they can be included into non-GPL user space application code. The exception note is missing in some UAPI headers. Some of them slipped in by the treewide conversion commit b24413180f56 ("License cleanup: add SPDX GPL-2.0 license identifier to files with no license"). Just run: $ git show --oneline b24413180f56 -- arch/x86/include/uapi/asm/ I believe they are not intentional, and should be fixed too. This patch was generated by the following script: git grep -l --not -e Linux-syscall-note --and -e SPDX-License-Identifier \ -- :arch/*/include/uapi/asm/*.h :include/uapi/ :^*/Kbuild | while read file do sed -i -e '/[[:space:]]OR[[:space:]]/s/\(GPL-[^[:space:]]*\)/(\1 WITH Linux-syscall-note)/g' \ -e '/[[:space:]]or[[:space:]]/s/\(GPL-[^[:space:]]*\)/(\1 WITH Linux-syscall-note)/g' \ -e '/[[:space:]]OR[[:space:]]/!{/[[:space:]]or[[:space:]]/!s/\(GPL-[^[:space:]]*\)/\1 WITH Linux-syscall-note/g}' $file done After this patch is applied, there are 5 UAPI headers that do not contain "WITH Linux-syscall-note". They are kept untouched since this exception applies only to GPL variants. $ git grep --not -e Linux-syscall-note --and -e SPDX-License-Identifier \ -- :arch/*/include/uapi/asm/*.h :include/uapi/ :^*/Kbuild include/uapi/drm/panfrost_drm.h:/* SPDX-License-Identifier: MIT */ include/uapi/linux/batman_adv.h:/* SPDX-License-Identifier: MIT */ include/uapi/linux/qemu_fw_cfg.h:/* SPDX-License-Identifier: BSD-3-Clause */ include/uapi/linux/vbox_err.h:/* SPDX-License-Identifier: MIT */ include/uapi/linux/virtio_iommu.h:/* SPDX-License-Identifier: BSD-3-Clause */ Signed-off-by: Masahiro Yamada Reviewed-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/uapi/asm/bpf_perf_event.h | 2 +- arch/csky/include/uapi/asm/byteorder.h | 2 +- arch/csky/include/uapi/asm/cachectl.h | 2 +- arch/csky/include/uapi/asm/perf_regs.h | 2 +- arch/csky/include/uapi/asm/ptrace.h | 2 +- arch/csky/include/uapi/asm/sigcontext.h | 2 +- arch/csky/include/uapi/asm/unistd.h | 2 +- arch/nds32/include/uapi/asm/auxvec.h | 2 +- arch/nds32/include/uapi/asm/byteorder.h | 2 +- arch/nds32/include/uapi/asm/cachectl.h | 2 +- arch/nds32/include/uapi/asm/fp_udfiex_crtl.h | 2 +- arch/nds32/include/uapi/asm/param.h | 2 +- arch/nds32/include/uapi/asm/ptrace.h | 2 +- arch/nds32/include/uapi/asm/sigcontext.h | 2 +- arch/nds32/include/uapi/asm/unistd.h | 2 +- arch/powerpc/include/uapi/asm/bpf_perf_event.h | 2 +- arch/riscv/include/uapi/asm/auxvec.h | 2 +- arch/riscv/include/uapi/asm/bitsperlong.h | 2 +- arch/riscv/include/uapi/asm/byteorder.h | 2 +- arch/riscv/include/uapi/asm/hwcap.h | 2 +- arch/riscv/include/uapi/asm/ptrace.h | 2 +- arch/riscv/include/uapi/asm/sigcontext.h | 2 +- arch/riscv/include/uapi/asm/ucontext.h | 2 +- arch/s390/include/uapi/asm/bpf_perf_event.h | 2 +- arch/s390/include/uapi/asm/ipl.h | 2 +- arch/sh/include/uapi/asm/setup.h | 2 +- arch/sh/include/uapi/asm/types.h | 2 +- arch/sparc/include/uapi/asm/oradax.h | 2 +- arch/x86/include/uapi/asm/byteorder.h | 2 +- arch/x86/include/uapi/asm/hwcap2.h | 2 +- arch/x86/include/uapi/asm/sigcontext32.h | 2 +- arch/x86/include/uapi/asm/types.h | 2 +- include/uapi/linux/bpfilter.h | 2 +- include/uapi/linux/ipmi_bmc.h | 2 +- include/uapi/linux/isst_if.h | 2 +- include/uapi/linux/netfilter/nf_synproxy.h | 2 +- include/uapi/linux/psp-sev.h | 2 +- include/uapi/linux/rxrpc.h | 2 +- include/uapi/linux/usb/g_uvc.h | 2 +- include/uapi/linux/vbox_vmmdev_types.h | 2 +- include/uapi/linux/vboxguest.h | 2 +- include/uapi/linux/virtio_pmem.h | 2 +- include/uapi/linux/vmcore.h | 2 +- include/uapi/linux/wmi.h | 2 +- include/uapi/misc/fastrpc.h | 2 +- include/uapi/rdma/rvt-abi.h | 2 +- include/uapi/rdma/siw-abi.h | 2 +- include/uapi/scsi/scsi_bsg_ufs.h | 2 +- include/uapi/sound/skl-tplg-interface.h | 2 +- 49 files changed, 49 insertions(+), 49 deletions(-) diff --git a/arch/arm64/include/uapi/asm/bpf_perf_event.h b/arch/arm64/include/uapi/asm/bpf_perf_event.h index b551b741653d..5e1e648aeec4 100644 --- a/arch/arm64/include/uapi/asm/bpf_perf_event.h +++ b/arch/arm64/include/uapi/asm/bpf_perf_event.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ #define _UAPI__ASM_BPF_PERF_EVENT_H__ diff --git a/arch/csky/include/uapi/asm/byteorder.h b/arch/csky/include/uapi/asm/byteorder.h index b079ec715cdf..d150cd664873 100644 --- a/arch/csky/include/uapi/asm/byteorder.h +++ b/arch/csky/include/uapi/asm/byteorder.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. #ifndef __ASM_CSKY_BYTEORDER_H diff --git a/arch/csky/include/uapi/asm/cachectl.h b/arch/csky/include/uapi/asm/cachectl.h index ddf2f39aa925..ed7fad1ea20d 100644 --- a/arch/csky/include/uapi/asm/cachectl.h +++ b/arch/csky/include/uapi/asm/cachectl.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_CSKY_CACHECTL_H #define __ASM_CSKY_CACHECTL_H diff --git a/arch/csky/include/uapi/asm/perf_regs.h b/arch/csky/include/uapi/asm/perf_regs.h index ee323d818592..49d4e147a559 100644 --- a/arch/csky/include/uapi/asm/perf_regs.h +++ b/arch/csky/include/uapi/asm/perf_regs.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. #ifndef _ASM_CSKY_PERF_REGS_H diff --git a/arch/csky/include/uapi/asm/ptrace.h b/arch/csky/include/uapi/asm/ptrace.h index 4e248d5b86ef..66b2268e324e 100644 --- a/arch/csky/include/uapi/asm/ptrace.h +++ b/arch/csky/include/uapi/asm/ptrace.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. #ifndef _CSKY_PTRACE_H diff --git a/arch/csky/include/uapi/asm/sigcontext.h b/arch/csky/include/uapi/asm/sigcontext.h index e81e7ff11e36..670c020f2cb8 100644 --- a/arch/csky/include/uapi/asm/sigcontext.h +++ b/arch/csky/include/uapi/asm/sigcontext.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. #ifndef __ASM_CSKY_SIGCONTEXT_H diff --git a/arch/csky/include/uapi/asm/unistd.h b/arch/csky/include/uapi/asm/unistd.h index ec60e49cea66..211c983c7282 100644 --- a/arch/csky/include/uapi/asm/unistd.h +++ b/arch/csky/include/uapi/asm/unistd.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. #define __ARCH_WANT_SYS_CLONE diff --git a/arch/nds32/include/uapi/asm/auxvec.h b/arch/nds32/include/uapi/asm/auxvec.h index b5d58ea8decb..bc0b92ab8c15 100644 --- a/arch/nds32/include/uapi/asm/auxvec.h +++ b/arch/nds32/include/uapi/asm/auxvec.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2005-2017 Andes Technology Corporation #ifndef __ASM_AUXVEC_H diff --git a/arch/nds32/include/uapi/asm/byteorder.h b/arch/nds32/include/uapi/asm/byteorder.h index 511e653c709d..c264ef12c49c 100644 --- a/arch/nds32/include/uapi/asm/byteorder.h +++ b/arch/nds32/include/uapi/asm/byteorder.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2005-2017 Andes Technology Corporation #ifndef __NDS32_BYTEORDER_H__ diff --git a/arch/nds32/include/uapi/asm/cachectl.h b/arch/nds32/include/uapi/asm/cachectl.h index 73793662815c..31b9b439d819 100644 --- a/arch/nds32/include/uapi/asm/cachectl.h +++ b/arch/nds32/include/uapi/asm/cachectl.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 1994, 1995, 1996 by Ralf Baechle // Copyright (C) 2005-2017 Andes Technology Corporation #ifndef _ASM_CACHECTL diff --git a/arch/nds32/include/uapi/asm/fp_udfiex_crtl.h b/arch/nds32/include/uapi/asm/fp_udfiex_crtl.h index d54a5d6c6538..f17396db16ec 100644 --- a/arch/nds32/include/uapi/asm/fp_udfiex_crtl.h +++ b/arch/nds32/include/uapi/asm/fp_udfiex_crtl.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* Copyright (C) 2005-2019 Andes Technology Corporation */ #ifndef _FP_UDF_IEX_CRTL_H #define _FP_UDF_IEX_CRTL_H diff --git a/arch/nds32/include/uapi/asm/param.h b/arch/nds32/include/uapi/asm/param.h index 2977534a6bd3..48d00328d328 100644 --- a/arch/nds32/include/uapi/asm/param.h +++ b/arch/nds32/include/uapi/asm/param.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2005-2017 Andes Technology Corporation #ifndef __ASM_NDS32_PARAM_H diff --git a/arch/nds32/include/uapi/asm/ptrace.h b/arch/nds32/include/uapi/asm/ptrace.h index 1a6e01c00e6f..d76217c7c010 100644 --- a/arch/nds32/include/uapi/asm/ptrace.h +++ b/arch/nds32/include/uapi/asm/ptrace.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2005-2017 Andes Technology Corporation #ifndef __UAPI_ASM_NDS32_PTRACE_H diff --git a/arch/nds32/include/uapi/asm/sigcontext.h b/arch/nds32/include/uapi/asm/sigcontext.h index dc89af7ddcc3..6c1e6648878f 100644 --- a/arch/nds32/include/uapi/asm/sigcontext.h +++ b/arch/nds32/include/uapi/asm/sigcontext.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2005-2017 Andes Technology Corporation #ifndef _ASMNDS32_SIGCONTEXT_H diff --git a/arch/nds32/include/uapi/asm/unistd.h b/arch/nds32/include/uapi/asm/unistd.h index a0b2f7b9c0f2..410795e280fe 100644 --- a/arch/nds32/include/uapi/asm/unistd.h +++ b/arch/nds32/include/uapi/asm/unistd.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2005-2017 Andes Technology Corporation #define __ARCH_WANT_STAT64 diff --git a/arch/powerpc/include/uapi/asm/bpf_perf_event.h b/arch/powerpc/include/uapi/asm/bpf_perf_event.h index b551b741653d..5e1e648aeec4 100644 --- a/arch/powerpc/include/uapi/asm/bpf_perf_event.h +++ b/arch/powerpc/include/uapi/asm/bpf_perf_event.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ #define _UAPI__ASM_BPF_PERF_EVENT_H__ diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h index 62716653554b..d86cb17bbabe 100644 --- a/arch/riscv/include/uapi/asm/auxvec.h +++ b/arch/riscv/include/uapi/asm/auxvec.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * Copyright (C) 2015 Regents of the University of California diff --git a/arch/riscv/include/uapi/asm/bitsperlong.h b/arch/riscv/include/uapi/asm/bitsperlong.h index 0b9b58b57ff6..7d0b32e3b701 100644 --- a/arch/riscv/include/uapi/asm/bitsperlong.h +++ b/arch/riscv/include/uapi/asm/bitsperlong.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * Copyright (C) 2015 Regents of the University of California diff --git a/arch/riscv/include/uapi/asm/byteorder.h b/arch/riscv/include/uapi/asm/byteorder.h index 1920debc09c0..f671e16bf6af 100644 --- a/arch/riscv/include/uapi/asm/byteorder.h +++ b/arch/riscv/include/uapi/asm/byteorder.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * Copyright (C) 2015 Regents of the University of California diff --git a/arch/riscv/include/uapi/asm/hwcap.h b/arch/riscv/include/uapi/asm/hwcap.h index 7d786145183b..4e7646077056 100644 --- a/arch/riscv/include/uapi/asm/hwcap.h +++ b/arch/riscv/include/uapi/asm/hwcap.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Copied from arch/arm64/include/asm/hwcap.h * diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h index 92d8f7cd8f84..882547f6bd5c 100644 --- a/arch/riscv/include/uapi/asm/ptrace.h +++ b/arch/riscv/include/uapi/asm/ptrace.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Copyright (C) 2012 Regents of the University of California */ diff --git a/arch/riscv/include/uapi/asm/sigcontext.h b/arch/riscv/include/uapi/asm/sigcontext.h index 053f809e52ce..84f2dfcfdbce 100644 --- a/arch/riscv/include/uapi/asm/sigcontext.h +++ b/arch/riscv/include/uapi/asm/sigcontext.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Copyright (C) 2012 Regents of the University of California */ diff --git a/arch/riscv/include/uapi/asm/ucontext.h b/arch/riscv/include/uapi/asm/ucontext.h index b58e00cee2ec..411dd7b52ed6 100644 --- a/arch/riscv/include/uapi/asm/ucontext.h +++ b/arch/riscv/include/uapi/asm/ucontext.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * Copyright (C) 2017 SiFive, Inc. diff --git a/arch/s390/include/uapi/asm/bpf_perf_event.h b/arch/s390/include/uapi/asm/bpf_perf_event.h index cefe7c7cd4f6..3ed42ff6da94 100644 --- a/arch/s390/include/uapi/asm/bpf_perf_event.h +++ b/arch/s390/include/uapi/asm/bpf_perf_event.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ #define _UAPI__ASM_BPF_PERF_EVENT_H__ diff --git a/arch/s390/include/uapi/asm/ipl.h b/arch/s390/include/uapi/asm/ipl.h index fd32b1cd80d2..451ba7d08905 100644 --- a/arch/s390/include/uapi/asm/ipl.h +++ b/arch/s390/include/uapi/asm/ipl.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_S390_UAPI_IPL_H #define _ASM_S390_UAPI_IPL_H diff --git a/arch/sh/include/uapi/asm/setup.h b/arch/sh/include/uapi/asm/setup.h index 1170dd2fb998..4bd19f80f9b0 100644 --- a/arch/sh/include/uapi/asm/setup.h +++ b/arch/sh/include/uapi/asm/setup.h @@ -1,2 +1,2 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/sh/include/uapi/asm/types.h b/arch/sh/include/uapi/asm/types.h index f83795fdc0da..68100e108ea6 100644 --- a/arch/sh/include/uapi/asm/types.h +++ b/arch/sh/include/uapi/asm/types.h @@ -1,2 +1,2 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/sparc/include/uapi/asm/oradax.h b/arch/sparc/include/uapi/asm/oradax.h index 64c67f2ea33f..0dace69058ab 100644 --- a/arch/sparc/include/uapi/asm/oradax.h +++ b/arch/sparc/include/uapi/asm/oradax.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* SPDX-License-Identifier: GPL-2.0-or-later WITH Linux-syscall-note */ /* * Copyright (c) 2017, Oracle and/or its affiliates. All rights reserved. */ diff --git a/arch/x86/include/uapi/asm/byteorder.h b/arch/x86/include/uapi/asm/byteorder.h index 484e3cfd7ef2..149143cab9ff 100644 --- a/arch/x86/include/uapi/asm/byteorder.h +++ b/arch/x86/include/uapi/asm/byteorder.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_BYTEORDER_H #define _ASM_X86_BYTEORDER_H diff --git a/arch/x86/include/uapi/asm/hwcap2.h b/arch/x86/include/uapi/asm/hwcap2.h index 6ebaae90e207..8b2effe6efb8 100644 --- a/arch/x86/include/uapi/asm/hwcap2.h +++ b/arch/x86/include/uapi/asm/hwcap2.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_HWCAP2_H #define _ASM_X86_HWCAP2_H diff --git a/arch/x86/include/uapi/asm/sigcontext32.h b/arch/x86/include/uapi/asm/sigcontext32.h index 6b18e88de8a6..7114801d0499 100644 --- a/arch/x86/include/uapi/asm/sigcontext32.h +++ b/arch/x86/include/uapi/asm/sigcontext32.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_SIGCONTEXT32_H #define _ASM_X86_SIGCONTEXT32_H diff --git a/arch/x86/include/uapi/asm/types.h b/arch/x86/include/uapi/asm/types.h index df55e1ddb0c9..9d5c11a24279 100644 --- a/arch/x86/include/uapi/asm/types.h +++ b/arch/x86/include/uapi/asm/types.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_TYPES_H #define _ASM_X86_TYPES_H diff --git a/include/uapi/linux/bpfilter.h b/include/uapi/linux/bpfilter.h index 2ec3cc99ea4c..cbc1f5813f50 100644 --- a/include/uapi/linux/bpfilter.h +++ b/include/uapi/linux/bpfilter.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_BPFILTER_H #define _UAPI_LINUX_BPFILTER_H diff --git a/include/uapi/linux/ipmi_bmc.h b/include/uapi/linux/ipmi_bmc.h index 1670f0944227..782a03eb1086 100644 --- a/include/uapi/linux/ipmi_bmc.h +++ b/include/uapi/linux/ipmi_bmc.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2015-2018, Intel Corporation. */ diff --git a/include/uapi/linux/isst_if.h b/include/uapi/linux/isst_if.h index d10b832c58c5..0a52b7b093d3 100644 --- a/include/uapi/linux/isst_if.h +++ b/include/uapi/linux/isst_if.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Intel Speed Select Interface: OS to hardware Interface * Copyright (c) 2019, Intel Corporation. diff --git a/include/uapi/linux/netfilter/nf_synproxy.h b/include/uapi/linux/netfilter/nf_synproxy.h index 6f3791c8946f..00d787f0260e 100644 --- a/include/uapi/linux/netfilter/nf_synproxy.h +++ b/include/uapi/linux/netfilter/nf_synproxy.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _NF_SYNPROXY_H #define _NF_SYNPROXY_H diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index 8654b2442f6a..592a0c1b77c9 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Userspace interface for AMD Secure Encrypted Virtualization (SEV) * platform management commands. diff --git a/include/uapi/linux/rxrpc.h b/include/uapi/linux/rxrpc.h index 782069dcf607..4accfa7e266d 100644 --- a/include/uapi/linux/rxrpc.h +++ b/include/uapi/linux/rxrpc.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* SPDX-License-Identifier: GPL-2.0-or-later WITH Linux-syscall-note */ /* Types and definitions for AF_RXRPC. * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. diff --git a/include/uapi/linux/usb/g_uvc.h b/include/uapi/linux/usb/g_uvc.h index 3c9ee3020cbb..652f169a019e 100644 --- a/include/uapi/linux/usb/g_uvc.h +++ b/include/uapi/linux/usb/g_uvc.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * g_uvc.h -- USB Video Class Gadget driver API * diff --git a/include/uapi/linux/vbox_vmmdev_types.h b/include/uapi/linux/vbox_vmmdev_types.h index 26f39816af14..c27289fd619a 100644 --- a/include/uapi/linux/vbox_vmmdev_types.h +++ b/include/uapi/linux/vbox_vmmdev_types.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: (GPL-2.0 OR CDDL-1.0) */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR CDDL-1.0) */ /* * Virtual Device for Guest <-> VMM/Host communication, type definitions * which are also used for the vboxguest ioctl interface / by vboxsf diff --git a/include/uapi/linux/vboxguest.h b/include/uapi/linux/vboxguest.h index 612f0c7d3558..9cec58a6a5ea 100644 --- a/include/uapi/linux/vboxguest.h +++ b/include/uapi/linux/vboxguest.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: (GPL-2.0 OR CDDL-1.0) */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR CDDL-1.0) */ /* * VBoxGuest - VirtualBox Guest Additions Driver Interface. * diff --git a/include/uapi/linux/virtio_pmem.h b/include/uapi/linux/virtio_pmem.h index 9a63ed6d062f..b022787ffb94 100644 --- a/include/uapi/linux/virtio_pmem.h +++ b/include/uapi/linux/virtio_pmem.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause */ /* * Definitions for virtio-pmem devices. * diff --git a/include/uapi/linux/vmcore.h b/include/uapi/linux/vmcore.h index 022619668e0e..3e9da91866ff 100644 --- a/include/uapi/linux/vmcore.h +++ b/include/uapi/linux/vmcore.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_VMCORE_H #define _UAPI_VMCORE_H diff --git a/include/uapi/linux/wmi.h b/include/uapi/linux/wmi.h index c36f2d7675a4..7085c5dca9fa 100644 --- a/include/uapi/linux/wmi.h +++ b/include/uapi/linux/wmi.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * User API methods for ACPI-WMI mapping driver * diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h index 6d701af9fc42..fb792e882cef 100644 --- a/include/uapi/misc/fastrpc.h +++ b/include/uapi/misc/fastrpc.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __QCOM_FASTRPC_H__ #define __QCOM_FASTRPC_H__ diff --git a/include/uapi/rdma/rvt-abi.h b/include/uapi/rdma/rvt-abi.h index 7328293c715c..7c05a02d2be5 100644 --- a/include/uapi/rdma/rvt-abi.h +++ b/include/uapi/rdma/rvt-abi.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * This file contains defines, structures, etc. that are used diff --git a/include/uapi/rdma/siw-abi.h b/include/uapi/rdma/siw-abi.h index 3dd8071ace7b..7de68f1dc707 100644 --- a/include/uapi/rdma/siw-abi.h +++ b/include/uapi/rdma/siw-abi.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause */ +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) or BSD-3-Clause */ /* Authors: Bernard Metzler */ /* Copyright (c) 2008-2019, IBM Corporation */ diff --git a/include/uapi/scsi/scsi_bsg_ufs.h b/include/uapi/scsi/scsi_bsg_ufs.h index 17c7abd0803a..9988db6ad244 100644 --- a/include/uapi/scsi/scsi_bsg_ufs.h +++ b/include/uapi/scsi/scsi_bsg_ufs.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * UFS Transport SGIO v4 BSG Message Support * diff --git a/include/uapi/sound/skl-tplg-interface.h b/include/uapi/sound/skl-tplg-interface.h index f39352cef382..9eee32f5e407 100644 --- a/include/uapi/sound/skl-tplg-interface.h +++ b/include/uapi/sound/skl-tplg-interface.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * skl-tplg-interface.h - Intel DSP FW private data interface * From dc3bf49ea330414724e429e4e9b291899c134e3b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 25 Jul 2019 16:58:32 +0900 Subject: [PATCH 345/823] treewide: remove SPDX "WITH Linux-syscall-note" from kernel-space headers again The "WITH Linux-syscall-note" exception exists for headers exported to user space. It is strange to add it to non-exported headers. Commit 687a3e4d8e61 ("treewide: remove SPDX "WITH Linux-syscall-note" from kernel-space headers") did cleanups some months ago, but it looks like we need to do this periodically. This patch was generated by the following script: git grep -l -e Linux-syscall-note \ -- :*.h :^arch/*/include/uapi/asm/*.h :^include/uapi/ :^tools | while read file do sed -i -e 's/(\(GPL-[^[:space:]]*\) WITH Linux-syscall-note)/\1/g' \ -e 's/ WITH Linux-syscall-note//g' $file done I did not commit drivers/staging/android/uapi/ion.h . This header is not currently exported, but somebody may plan to move it to include/uapi/ when the time comes. I am not sure. Anyway, it will be better to check the license inconsistency in drivers/staging/android/uapi/. Signed-off-by: Masahiro Yamada Reviewed-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- include/sound/sof/control.h | 2 +- include/sound/sof/dai-intel.h | 2 +- include/sound/sof/dai.h | 2 +- include/sound/sof/header.h | 2 +- include/sound/sof/info.h | 2 +- include/sound/sof/pm.h | 2 +- include/sound/sof/stream.h | 2 +- include/sound/sof/topology.h | 2 +- include/sound/sof/trace.h | 2 +- include/sound/sof/xtensa.h | 2 +- samples/vfio-mdev/mdpy-defs.h | 2 +- 11 files changed, 11 insertions(+), 11 deletions(-) diff --git a/include/sound/sof/control.h b/include/sound/sof/control.h index bded69e696d4..6080ea0facd7 100644 --- a/include/sound/sof/control.h +++ b/include/sound/sof/control.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/dai-intel.h b/include/sound/sof/dai-intel.h index 4bb8ee138ba7..65e4c20e567c 100644 --- a/include/sound/sof/dai-intel.h +++ b/include/sound/sof/dai-intel.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/dai.h b/include/sound/sof/dai.h index 3d174e20aa53..5b8de1b1983c 100644 --- a/include/sound/sof/dai.h +++ b/include/sound/sof/dai.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/header.h b/include/sound/sof/header.h index 12867bbd4372..10f00c08dbb7 100644 --- a/include/sound/sof/header.h +++ b/include/sound/sof/header.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/info.h b/include/sound/sof/info.h index 16528d2b4a50..a9156b4a062c 100644 --- a/include/sound/sof/info.h +++ b/include/sound/sof/info.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/pm.h b/include/sound/sof/pm.h index 8ae3ad45bdf7..003879401d63 100644 --- a/include/sound/sof/pm.h +++ b/include/sound/sof/pm.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/stream.h b/include/sound/sof/stream.h index 643f175cb479..0b71b381b952 100644 --- a/include/sound/sof/stream.h +++ b/include/sound/sof/stream.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/topology.h b/include/sound/sof/topology.h index 41dcabf89899..c47b36240920 100644 --- a/include/sound/sof/topology.h +++ b/include/sound/sof/topology.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/trace.h b/include/sound/sof/trace.h index 9257d5473d97..fda6e8f6ead4 100644 --- a/include/sound/sof/trace.h +++ b/include/sound/sof/trace.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/xtensa.h b/include/sound/sof/xtensa.h index d25c764b10e8..dd53d36b34e1 100644 --- a/include/sound/sof/xtensa.h +++ b/include/sound/sof/xtensa.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/samples/vfio-mdev/mdpy-defs.h b/samples/vfio-mdev/mdpy-defs.h index 96b3b1b49d34..eb26421b6429 100644 --- a/samples/vfio-mdev/mdpy-defs.h +++ b/samples/vfio-mdev/mdpy-defs.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Simple pci display device. * From 0ce38c5f929c83dff8ea805f6c6ef2eb97b66431 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 25 Jul 2019 16:58:33 +0900 Subject: [PATCH 346/823] iomap: fix Invalid License ID Detected by: $ ./scripts/spdxcheck.py fs/iomap/Makefile: 1:27 Invalid License ID: GPL-2.0-or-newer Fixes: 1c230208f53d ("iomap: start moving code to fs/iomap/") Signed-off-by: Masahiro Yamada Reviewed-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- fs/iomap/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/iomap/Makefile b/fs/iomap/Makefile index 2d165388d952..93cd11938bf5 100644 --- a/fs/iomap/Makefile +++ b/fs/iomap/Makefile @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0-or-newer +# SPDX-License-Identifier: GPL-2.0-or-later # # Copyright (c) 2019 Oracle. # All Rights Reserved. From bafe64e5f0edaa689e72e2f8dc236641da37fed4 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 19 Jul 2019 10:44:05 +0200 Subject: [PATCH 347/823] Revert "usb: usb251xb: Add US lanes inversion dts-bindings" This reverts commit 3342ce35a1, as there is no need for this separate property and it breaks compatibility with existing devicetree files (arch/arm64/boot/dts/freescale/imx8mq.dtsi). CC: stable@vger.kernel.org #5.2 Fixes: 3342ce35a183 ("usb: usb251xb: Add US lanes inversion dts-bindings") Signed-off-by: Lucas Stach Link: https://lore.kernel.org/r/20190719084407.28041-1-l.stach@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/usb251xb.txt | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/usb/usb251xb.txt b/Documentation/devicetree/bindings/usb/usb251xb.txt index bc7945e9dbfe..17915f64b8ee 100644 --- a/Documentation/devicetree/bindings/usb/usb251xb.txt +++ b/Documentation/devicetree/bindings/usb/usb251xb.txt @@ -64,10 +64,8 @@ Optional properties : - power-on-time-ms : Specifies the time it takes from the time the host initiates the power-on sequence to a port until the port has adequate power. The value is given in ms in a 0 - 510 range (default is 100ms). - - swap-dx-lanes : Specifies the downstream ports which will swap the - differential-pair (D+/D-), default is not-swapped. - - swap-us-lanes : Selects the upstream port differential-pair (D+/D-) - swapping (boolean, default is not-swapped) + - swap-dx-lanes : Specifies the ports which will swap the differential-pair + (D+/D-), default is not-swapped. Examples: usb2512b@2c { From 79f6fafad4e2a874015cb67d735f9f87f1834367 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 19 Jul 2019 10:44:06 +0200 Subject: [PATCH 348/823] Revert "usb: usb251xb: Add US port lanes inversion property" This property isn't needed and not yet used anywhere. The swap-dx-lanes property is perfectly fine for doing the swap on the upstream port lanes. CC: stable@vger.kernel.org #5.2 Signed-off-by: Lucas Stach Link: https://lore.kernel.org/r/20190719084407.28041-2-l.stach@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/misc/usb251xb.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/usb/misc/usb251xb.c b/drivers/usb/misc/usb251xb.c index 4d6ae3795a88..119aeb658c81 100644 --- a/drivers/usb/misc/usb251xb.c +++ b/drivers/usb/misc/usb251xb.c @@ -574,8 +574,6 @@ static int usb251xb_get_ofdata(struct usb251xb *hub, hub->port_swap = USB251XB_DEF_PORT_SWAP; usb251xb_get_ports_field(hub, "swap-dx-lanes", data->port_cnt, &hub->port_swap); - if (of_get_property(np, "swap-us-lanes", NULL)) - hub->port_swap |= BIT(0); /* The following parameters are currently not exposed to devicetree, but * may be as soon as needed. From 4849ee6129702dcb05d36f9c7c61b4661fcd751f Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 19 Jul 2019 10:44:07 +0200 Subject: [PATCH 349/823] usb: usb251xb: Reallow swap-dx-lanes to apply to the upstream port This is a partial revert of 73d31def1aab "usb: usb251xb: Create a ports field collector method", which broke a existing devicetree (arch/arm64/boot/dts/freescale/imx8mq.dtsi). There is no reason why the swap-dx-lanes property should not apply to the upstream port. The reason given in the breaking commit was that it's inconsitent with respect to other port properties, but in fact it is not. All other properties which only apply to the downstream ports explicitly reject port 0, so there is pretty strong precedence that the driver referred to the upstream port as port 0. So there is no inconsistency in this property at all, other than the swapping being also applicable to the upstream port. CC: stable@vger.kernel.org #5.2 Signed-off-by: Lucas Stach Link: https://lore.kernel.org/r/20190719084407.28041-3-l.stach@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/misc/usb251xb.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/usb/misc/usb251xb.c b/drivers/usb/misc/usb251xb.c index 119aeb658c81..6ca9111d150a 100644 --- a/drivers/usb/misc/usb251xb.c +++ b/drivers/usb/misc/usb251xb.c @@ -375,7 +375,8 @@ out_err: #ifdef CONFIG_OF static void usb251xb_get_ports_field(struct usb251xb *hub, - const char *prop_name, u8 port_cnt, u8 *fld) + const char *prop_name, u8 port_cnt, + bool ds_only, u8 *fld) { struct device *dev = hub->dev; struct property *prop; @@ -383,7 +384,7 @@ static void usb251xb_get_ports_field(struct usb251xb *hub, u32 port; of_property_for_each_u32(dev->of_node, prop_name, prop, p, port) { - if ((port >= 1) && (port <= port_cnt)) + if ((port >= ds_only ? 1 : 0) && (port <= port_cnt)) *fld |= BIT(port); else dev_warn(dev, "port %u doesn't exist\n", port); @@ -501,15 +502,15 @@ static int usb251xb_get_ofdata(struct usb251xb *hub, hub->non_rem_dev = USB251XB_DEF_NON_REMOVABLE_DEVICES; usb251xb_get_ports_field(hub, "non-removable-ports", data->port_cnt, - &hub->non_rem_dev); + true, &hub->non_rem_dev); hub->port_disable_sp = USB251XB_DEF_PORT_DISABLE_SELF; usb251xb_get_ports_field(hub, "sp-disabled-ports", data->port_cnt, - &hub->port_disable_sp); + true, &hub->port_disable_sp); hub->port_disable_bp = USB251XB_DEF_PORT_DISABLE_BUS; usb251xb_get_ports_field(hub, "bp-disabled-ports", data->port_cnt, - &hub->port_disable_bp); + true, &hub->port_disable_bp); hub->max_power_sp = USB251XB_DEF_MAX_POWER_SELF; if (!of_property_read_u32(np, "sp-max-total-current-microamp", @@ -573,7 +574,7 @@ static int usb251xb_get_ofdata(struct usb251xb *hub, */ hub->port_swap = USB251XB_DEF_PORT_SWAP; usb251xb_get_ports_field(hub, "swap-dx-lanes", data->port_cnt, - &hub->port_swap); + false, &hub->port_swap); /* The following parameters are currently not exposed to devicetree, but * may be as soon as needed. From d39b5bad8658d6d94cb2d98a44a7e159db4f5030 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Thu, 25 Jul 2019 11:54:21 +0300 Subject: [PATCH 350/823] xhci: Fix crash if scatter gather is used with Immediate Data Transfer (IDT). A second regression was found in the immediate data transfer (IDT) support which was added to 5.2 kernel IDT is used to transfer small amounts of data (up to 8 bytes) in the field normally used for data dma address, thus avoiding dma mapping. If the data was not already dma mapped, then IDT support assumed data was in urb->transfer_buffer, and did not take into accound that even small amounts of data (8 bytes) can be in a scatterlist instead. This caused a NULL pointer dereference when sg_dma_len() was used with non-dma mapped data. Solve this by not using IDT if scatter gather buffer list is used. Fixes: 33e39350ebd2 ("usb: xhci: add Immediate Data Transfer support") Cc: # v5.2 Reported-by: Maik Stohn Tested-by: Maik Stohn CC: Nicolas Saenz Julienne Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/1564044861-1445-1-git-send-email-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 7a264962a1a9..f5c41448d067 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -2175,7 +2175,8 @@ static inline bool xhci_urb_suitable_for_idt(struct urb *urb) if (!usb_endpoint_xfer_isoc(&urb->ep->desc) && usb_urb_dir_out(urb) && usb_endpoint_maxp(&urb->ep->desc) >= TRB_IDT_MAX_SIZE && urb->transfer_buffer_length <= TRB_IDT_MAX_SIZE && - !(urb->transfer_flags & URB_NO_TRANSFER_DMA_MAP)) + !(urb->transfer_flags & URB_NO_TRANSFER_DMA_MAP) && + !urb->num_sgs) return true; return false; From 4a2b8560e3dff8637ccb09524650864f60ebab7f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 22 Jul 2019 08:51:46 +0200 Subject: [PATCH 351/823] tty: serial: netx: Delete driver The Netx ARM machine was deleted from the kernel. This driver had no users and has to go. Cc: Robert Schwebel Cc: Sascha Hauer Signed-off-by: Linus Walleij Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20190722065146.4844-1-linus.walleij@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/Kconfig | 19 - drivers/tty/serial/Makefile | 1 - drivers/tty/serial/netx-serial.c | 733 ------------------------------- include/uapi/linux/serial_core.h | 3 - 4 files changed, 756 deletions(-) delete mode 100644 drivers/tty/serial/netx-serial.c diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index fd385c8c53a5..3083dbae35f7 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -1035,25 +1035,6 @@ config SERIAL_VT8500_CONSOLE depends on SERIAL_VT8500=y select SERIAL_CORE_CONSOLE -config SERIAL_NETX - tristate "NetX serial port support" - depends on ARCH_NETX - select SERIAL_CORE - help - If you have a machine based on a Hilscher NetX SoC you - can enable its onboard serial port by enabling this option. - - To compile this driver as a module, choose M here: the - module will be called netx-serial. - -config SERIAL_NETX_CONSOLE - bool "Console on NetX serial port" - depends on SERIAL_NETX=y - select SERIAL_CORE_CONSOLE - help - If you have enabled the serial port on the Hilscher NetX SoC - you can make it the console by answering Y to this option. - config SERIAL_OMAP tristate "OMAP serial port support" depends on ARCH_OMAP2PLUS diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile index 7cd7cabfa6c4..15a0fccadf7e 100644 --- a/drivers/tty/serial/Makefile +++ b/drivers/tty/serial/Makefile @@ -59,7 +59,6 @@ obj-$(CONFIG_SERIAL_ATMEL) += atmel_serial.o obj-$(CONFIG_SERIAL_UARTLITE) += uartlite.o obj-$(CONFIG_SERIAL_MSM) += msm_serial.o obj-$(CONFIG_SERIAL_QCOM_GENI) += qcom_geni_serial.o -obj-$(CONFIG_SERIAL_NETX) += netx-serial.o obj-$(CONFIG_SERIAL_KS8695) += serial_ks8695.o obj-$(CONFIG_SERIAL_OMAP) += omap-serial.o obj-$(CONFIG_SERIAL_ALTERA_UART) += altera_uart.o diff --git a/drivers/tty/serial/netx-serial.c b/drivers/tty/serial/netx-serial.c deleted file mode 100644 index b3556863491f..000000000000 --- a/drivers/tty/serial/netx-serial.c +++ /dev/null @@ -1,733 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2005 Sascha Hauer , Pengutronix - */ - -#if defined(CONFIG_SERIAL_NETX_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ) -#define SUPPORT_SYSRQ -#endif - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -/* We've been assigned a range on the "Low-density serial ports" major */ -#define SERIAL_NX_MAJOR 204 -#define MINOR_START 170 - -enum uart_regs { - UART_DR = 0x00, - UART_SR = 0x04, - UART_LINE_CR = 0x08, - UART_BAUDDIV_MSB = 0x0c, - UART_BAUDDIV_LSB = 0x10, - UART_CR = 0x14, - UART_FR = 0x18, - UART_IIR = 0x1c, - UART_ILPR = 0x20, - UART_RTS_CR = 0x24, - UART_RTS_LEAD = 0x28, - UART_RTS_TRAIL = 0x2c, - UART_DRV_ENABLE = 0x30, - UART_BRM_CR = 0x34, - UART_RXFIFO_IRQLEVEL = 0x38, - UART_TXFIFO_IRQLEVEL = 0x3c, -}; - -#define SR_FE (1<<0) -#define SR_PE (1<<1) -#define SR_BE (1<<2) -#define SR_OE (1<<3) - -#define LINE_CR_BRK (1<<0) -#define LINE_CR_PEN (1<<1) -#define LINE_CR_EPS (1<<2) -#define LINE_CR_STP2 (1<<3) -#define LINE_CR_FEN (1<<4) -#define LINE_CR_5BIT (0<<5) -#define LINE_CR_6BIT (1<<5) -#define LINE_CR_7BIT (2<<5) -#define LINE_CR_8BIT (3<<5) -#define LINE_CR_BITS_MASK (3<<5) - -#define CR_UART_EN (1<<0) -#define CR_SIREN (1<<1) -#define CR_SIRLP (1<<2) -#define CR_MSIE (1<<3) -#define CR_RIE (1<<4) -#define CR_TIE (1<<5) -#define CR_RTIE (1<<6) -#define CR_LBE (1<<7) - -#define FR_CTS (1<<0) -#define FR_DSR (1<<1) -#define FR_DCD (1<<2) -#define FR_BUSY (1<<3) -#define FR_RXFE (1<<4) -#define FR_TXFF (1<<5) -#define FR_RXFF (1<<6) -#define FR_TXFE (1<<7) - -#define IIR_MIS (1<<0) -#define IIR_RIS (1<<1) -#define IIR_TIS (1<<2) -#define IIR_RTIS (1<<3) -#define IIR_MASK 0xf - -#define RTS_CR_AUTO (1<<0) -#define RTS_CR_RTS (1<<1) -#define RTS_CR_COUNT (1<<2) -#define RTS_CR_MOD2 (1<<3) -#define RTS_CR_RTS_POL (1<<4) -#define RTS_CR_CTS_CTR (1<<5) -#define RTS_CR_CTS_POL (1<<6) -#define RTS_CR_STICK (1<<7) - -#define UART_PORT_SIZE 0x40 -#define DRIVER_NAME "netx-uart" - -struct netx_port { - struct uart_port port; -}; - -static void netx_stop_tx(struct uart_port *port) -{ - unsigned int val; - val = readl(port->membase + UART_CR); - writel(val & ~CR_TIE, port->membase + UART_CR); -} - -static void netx_stop_rx(struct uart_port *port) -{ - unsigned int val; - val = readl(port->membase + UART_CR); - writel(val & ~CR_RIE, port->membase + UART_CR); -} - -static void netx_enable_ms(struct uart_port *port) -{ - unsigned int val; - val = readl(port->membase + UART_CR); - writel(val | CR_MSIE, port->membase + UART_CR); -} - -static inline void netx_transmit_buffer(struct uart_port *port) -{ - struct circ_buf *xmit = &port->state->xmit; - - if (port->x_char) { - writel(port->x_char, port->membase + UART_DR); - port->icount.tx++; - port->x_char = 0; - return; - } - - if (uart_tx_stopped(port) || uart_circ_empty(xmit)) { - netx_stop_tx(port); - return; - } - - do { - /* send xmit->buf[xmit->tail] - * out the port here */ - writel(xmit->buf[xmit->tail], port->membase + UART_DR); - xmit->tail = (xmit->tail + 1) & - (UART_XMIT_SIZE - 1); - port->icount.tx++; - if (uart_circ_empty(xmit)) - break; - } while (!(readl(port->membase + UART_FR) & FR_TXFF)); - - if (uart_circ_empty(xmit)) - netx_stop_tx(port); -} - -static void netx_start_tx(struct uart_port *port) -{ - writel( - readl(port->membase + UART_CR) | CR_TIE, port->membase + UART_CR); - - if (!(readl(port->membase + UART_FR) & FR_TXFF)) - netx_transmit_buffer(port); -} - -static unsigned int netx_tx_empty(struct uart_port *port) -{ - return readl(port->membase + UART_FR) & FR_BUSY ? 0 : TIOCSER_TEMT; -} - -static void netx_txint(struct uart_port *port) -{ - struct circ_buf *xmit = &port->state->xmit; - - if (uart_circ_empty(xmit) || uart_tx_stopped(port)) { - netx_stop_tx(port); - return; - } - - netx_transmit_buffer(port); - - if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) - uart_write_wakeup(port); -} - -static void netx_rxint(struct uart_port *port, unsigned long *flags) -{ - unsigned char rx, flg, status; - - while (!(readl(port->membase + UART_FR) & FR_RXFE)) { - rx = readl(port->membase + UART_DR); - flg = TTY_NORMAL; - port->icount.rx++; - status = readl(port->membase + UART_SR); - if (status & SR_BE) { - writel(0, port->membase + UART_SR); - if (uart_handle_break(port)) - continue; - } - - if (unlikely(status & (SR_FE | SR_PE | SR_OE))) { - - if (status & SR_PE) - port->icount.parity++; - else if (status & SR_FE) - port->icount.frame++; - if (status & SR_OE) - port->icount.overrun++; - - status &= port->read_status_mask; - - if (status & SR_BE) - flg = TTY_BREAK; - else if (status & SR_PE) - flg = TTY_PARITY; - else if (status & SR_FE) - flg = TTY_FRAME; - } - - if (uart_handle_sysrq_char(port, rx)) - continue; - - uart_insert_char(port, status, SR_OE, rx, flg); - } - - spin_unlock_irqrestore(&port->lock, *flags); - tty_flip_buffer_push(&port->state->port); - spin_lock_irqsave(&port->lock, *flags); -} - -static irqreturn_t netx_int(int irq, void *dev_id) -{ - struct uart_port *port = dev_id; - unsigned long flags; - unsigned char status; - - spin_lock_irqsave(&port->lock,flags); - - status = readl(port->membase + UART_IIR) & IIR_MASK; - while (status) { - if (status & IIR_RIS) - netx_rxint(port, &flags); - if (status & IIR_TIS) - netx_txint(port); - if (status & IIR_MIS) { - if (readl(port->membase + UART_FR) & FR_CTS) - uart_handle_cts_change(port, 1); - else - uart_handle_cts_change(port, 0); - } - writel(0, port->membase + UART_IIR); - status = readl(port->membase + UART_IIR) & IIR_MASK; - } - - spin_unlock_irqrestore(&port->lock,flags); - return IRQ_HANDLED; -} - -static unsigned int netx_get_mctrl(struct uart_port *port) -{ - unsigned int ret = TIOCM_DSR | TIOCM_CAR; - - if (readl(port->membase + UART_FR) & FR_CTS) - ret |= TIOCM_CTS; - - return ret; -} - -static void netx_set_mctrl(struct uart_port *port, unsigned int mctrl) -{ - unsigned int val; - - /* FIXME: Locking needed ? */ - if (mctrl & TIOCM_RTS) { - val = readl(port->membase + UART_RTS_CR); - writel(val | RTS_CR_RTS, port->membase + UART_RTS_CR); - } -} - -static void netx_break_ctl(struct uart_port *port, int break_state) -{ - unsigned int line_cr; - spin_lock_irq(&port->lock); - - line_cr = readl(port->membase + UART_LINE_CR); - if (break_state != 0) - line_cr |= LINE_CR_BRK; - else - line_cr &= ~LINE_CR_BRK; - writel(line_cr, port->membase + UART_LINE_CR); - - spin_unlock_irq(&port->lock); -} - -static int netx_startup(struct uart_port *port) -{ - int ret; - - ret = request_irq(port->irq, netx_int, 0, - DRIVER_NAME, port); - if (ret) { - dev_err(port->dev, "unable to grab irq%d\n",port->irq); - goto exit; - } - - writel(readl(port->membase + UART_LINE_CR) | LINE_CR_FEN, - port->membase + UART_LINE_CR); - - writel(CR_MSIE | CR_RIE | CR_TIE | CR_RTIE | CR_UART_EN, - port->membase + UART_CR); - -exit: - return ret; -} - -static void netx_shutdown(struct uart_port *port) -{ - writel(0, port->membase + UART_CR) ; - - free_irq(port->irq, port); -} - -static void -netx_set_termios(struct uart_port *port, struct ktermios *termios, - struct ktermios *old) -{ - unsigned int baud, quot; - unsigned char old_cr; - unsigned char line_cr = LINE_CR_FEN; - unsigned char rts_cr = 0; - - switch (termios->c_cflag & CSIZE) { - case CS5: - line_cr |= LINE_CR_5BIT; - break; - case CS6: - line_cr |= LINE_CR_6BIT; - break; - case CS7: - line_cr |= LINE_CR_7BIT; - break; - case CS8: - line_cr |= LINE_CR_8BIT; - break; - } - - if (termios->c_cflag & CSTOPB) - line_cr |= LINE_CR_STP2; - - if (termios->c_cflag & PARENB) { - line_cr |= LINE_CR_PEN; - if (!(termios->c_cflag & PARODD)) - line_cr |= LINE_CR_EPS; - } - - if (termios->c_cflag & CRTSCTS) - rts_cr = RTS_CR_AUTO | RTS_CR_CTS_CTR | RTS_CR_RTS_POL; - - baud = uart_get_baud_rate(port, termios, old, 0, port->uartclk/16); - quot = baud * 4096; - quot /= 1000; - quot *= 256; - quot /= 100000; - - spin_lock_irq(&port->lock); - - uart_update_timeout(port, termios->c_cflag, baud); - - old_cr = readl(port->membase + UART_CR); - - /* disable interrupts */ - writel(old_cr & ~(CR_MSIE | CR_RIE | CR_TIE | CR_RTIE), - port->membase + UART_CR); - - /* drain transmitter */ - while (readl(port->membase + UART_FR) & FR_BUSY); - - /* disable UART */ - writel(old_cr & ~CR_UART_EN, port->membase + UART_CR); - - /* modem status interrupts */ - old_cr &= ~CR_MSIE; - if (UART_ENABLE_MS(port, termios->c_cflag)) - old_cr |= CR_MSIE; - - writel((quot>>8) & 0xff, port->membase + UART_BAUDDIV_MSB); - writel(quot & 0xff, port->membase + UART_BAUDDIV_LSB); - writel(line_cr, port->membase + UART_LINE_CR); - - writel(rts_cr, port->membase + UART_RTS_CR); - - /* - * Characters to ignore - */ - port->ignore_status_mask = 0; - if (termios->c_iflag & IGNPAR) - port->ignore_status_mask |= SR_PE; - if (termios->c_iflag & IGNBRK) { - port->ignore_status_mask |= SR_BE; - /* - * If we're ignoring parity and break indicators, - * ignore overruns too (for real raw support). - */ - if (termios->c_iflag & IGNPAR) - port->ignore_status_mask |= SR_PE; - } - - port->read_status_mask = 0; - if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) - port->read_status_mask |= SR_BE; - if (termios->c_iflag & INPCK) - port->read_status_mask |= SR_PE | SR_FE; - - writel(old_cr, port->membase + UART_CR); - - spin_unlock_irq(&port->lock); -} - -static const char *netx_type(struct uart_port *port) -{ - return port->type == PORT_NETX ? "NETX" : NULL; -} - -static void netx_release_port(struct uart_port *port) -{ - release_mem_region(port->mapbase, UART_PORT_SIZE); -} - -static int netx_request_port(struct uart_port *port) -{ - return request_mem_region(port->mapbase, UART_PORT_SIZE, - DRIVER_NAME) != NULL ? 0 : -EBUSY; -} - -static void netx_config_port(struct uart_port *port, int flags) -{ - if (flags & UART_CONFIG_TYPE && netx_request_port(port) == 0) - port->type = PORT_NETX; -} - -static int -netx_verify_port(struct uart_port *port, struct serial_struct *ser) -{ - int ret = 0; - - if (ser->type != PORT_UNKNOWN && ser->type != PORT_NETX) - ret = -EINVAL; - - return ret; -} - -static struct uart_ops netx_pops = { - .tx_empty = netx_tx_empty, - .set_mctrl = netx_set_mctrl, - .get_mctrl = netx_get_mctrl, - .stop_tx = netx_stop_tx, - .start_tx = netx_start_tx, - .stop_rx = netx_stop_rx, - .enable_ms = netx_enable_ms, - .break_ctl = netx_break_ctl, - .startup = netx_startup, - .shutdown = netx_shutdown, - .set_termios = netx_set_termios, - .type = netx_type, - .release_port = netx_release_port, - .request_port = netx_request_port, - .config_port = netx_config_port, - .verify_port = netx_verify_port, -}; - -static struct netx_port netx_ports[] = { - { - .port = { - .type = PORT_NETX, - .iotype = UPIO_MEM, - .membase = (char __iomem *)io_p2v(NETX_PA_UART0), - .mapbase = NETX_PA_UART0, - .irq = NETX_IRQ_UART0, - .uartclk = 100000000, - .fifosize = 16, - .flags = UPF_BOOT_AUTOCONF, - .ops = &netx_pops, - .line = 0, - }, - }, { - .port = { - .type = PORT_NETX, - .iotype = UPIO_MEM, - .membase = (char __iomem *)io_p2v(NETX_PA_UART1), - .mapbase = NETX_PA_UART1, - .irq = NETX_IRQ_UART1, - .uartclk = 100000000, - .fifosize = 16, - .flags = UPF_BOOT_AUTOCONF, - .ops = &netx_pops, - .line = 1, - }, - }, { - .port = { - .type = PORT_NETX, - .iotype = UPIO_MEM, - .membase = (char __iomem *)io_p2v(NETX_PA_UART2), - .mapbase = NETX_PA_UART2, - .irq = NETX_IRQ_UART2, - .uartclk = 100000000, - .fifosize = 16, - .flags = UPF_BOOT_AUTOCONF, - .ops = &netx_pops, - .line = 2, - }, - } -}; - -#ifdef CONFIG_SERIAL_NETX_CONSOLE - -static void netx_console_putchar(struct uart_port *port, int ch) -{ - while (readl(port->membase + UART_FR) & FR_BUSY); - writel(ch, port->membase + UART_DR); -} - -static void -netx_console_write(struct console *co, const char *s, unsigned int count) -{ - struct uart_port *port = &netx_ports[co->index].port; - unsigned char cr_save; - - cr_save = readl(port->membase + UART_CR); - writel(cr_save | CR_UART_EN, port->membase + UART_CR); - - uart_console_write(port, s, count, netx_console_putchar); - - while (readl(port->membase + UART_FR) & FR_BUSY); - writel(cr_save, port->membase + UART_CR); -} - -static void __init -netx_console_get_options(struct uart_port *port, int *baud, - int *parity, int *bits, int *flow) -{ - unsigned char line_cr; - - *baud = (readl(port->membase + UART_BAUDDIV_MSB) << 8) | - readl(port->membase + UART_BAUDDIV_LSB); - *baud *= 1000; - *baud /= 4096; - *baud *= 1000; - *baud /= 256; - *baud *= 100; - - line_cr = readl(port->membase + UART_LINE_CR); - *parity = 'n'; - if (line_cr & LINE_CR_PEN) { - if (line_cr & LINE_CR_EPS) - *parity = 'e'; - else - *parity = 'o'; - } - - switch (line_cr & LINE_CR_BITS_MASK) { - case LINE_CR_8BIT: - *bits = 8; - break; - case LINE_CR_7BIT: - *bits = 7; - break; - case LINE_CR_6BIT: - *bits = 6; - break; - case LINE_CR_5BIT: - *bits = 5; - break; - } - - if (readl(port->membase + UART_RTS_CR) & RTS_CR_AUTO) - *flow = 'r'; -} - -static int __init -netx_console_setup(struct console *co, char *options) -{ - struct netx_port *sport; - int baud = 9600; - int bits = 8; - int parity = 'n'; - int flow = 'n'; - - /* - * Check whether an invalid uart number has been specified, and - * if so, search for the first available port that does have - * console support. - */ - if (co->index == -1 || co->index >= ARRAY_SIZE(netx_ports)) - co->index = 0; - sport = &netx_ports[co->index]; - - if (options) { - uart_parse_options(options, &baud, &parity, &bits, &flow); - } else { - /* if the UART is enabled, assume it has been correctly setup - * by the bootloader and get the options - */ - if (readl(sport->port.membase + UART_CR) & CR_UART_EN) { - netx_console_get_options(&sport->port, &baud, - &parity, &bits, &flow); - } - - } - - return uart_set_options(&sport->port, co, baud, parity, bits, flow); -} - -static struct uart_driver netx_reg; -static struct console netx_console = { - .name = "ttyNX", - .write = netx_console_write, - .device = uart_console_device, - .setup = netx_console_setup, - .flags = CON_PRINTBUFFER, - .index = -1, - .data = &netx_reg, -}; - -static int __init netx_console_init(void) -{ - register_console(&netx_console); - return 0; -} -console_initcall(netx_console_init); - -#define NETX_CONSOLE &netx_console -#else -#define NETX_CONSOLE NULL -#endif - -static struct uart_driver netx_reg = { - .owner = THIS_MODULE, - .driver_name = DRIVER_NAME, - .dev_name = "ttyNX", - .major = SERIAL_NX_MAJOR, - .minor = MINOR_START, - .nr = ARRAY_SIZE(netx_ports), - .cons = NETX_CONSOLE, -}; - -static int serial_netx_suspend(struct platform_device *pdev, pm_message_t state) -{ - struct netx_port *sport = platform_get_drvdata(pdev); - - if (sport) - uart_suspend_port(&netx_reg, &sport->port); - - return 0; -} - -static int serial_netx_resume(struct platform_device *pdev) -{ - struct netx_port *sport = platform_get_drvdata(pdev); - - if (sport) - uart_resume_port(&netx_reg, &sport->port); - - return 0; -} - -static int serial_netx_probe(struct platform_device *pdev) -{ - struct uart_port *port = &netx_ports[pdev->id].port; - - dev_info(&pdev->dev, "initialising\n"); - - port->dev = &pdev->dev; - - writel(1, port->membase + UART_RXFIFO_IRQLEVEL); - uart_add_one_port(&netx_reg, &netx_ports[pdev->id].port); - platform_set_drvdata(pdev, &netx_ports[pdev->id]); - - return 0; -} - -static int serial_netx_remove(struct platform_device *pdev) -{ - struct netx_port *sport = platform_get_drvdata(pdev); - - if (sport) - uart_remove_one_port(&netx_reg, &sport->port); - - return 0; -} - -static struct platform_driver serial_netx_driver = { - .probe = serial_netx_probe, - .remove = serial_netx_remove, - - .suspend = serial_netx_suspend, - .resume = serial_netx_resume, - - .driver = { - .name = DRIVER_NAME, - }, -}; - -static int __init netx_serial_init(void) -{ - int ret; - - printk(KERN_INFO "Serial: NetX driver\n"); - - ret = uart_register_driver(&netx_reg); - if (ret) - return ret; - - ret = platform_driver_register(&serial_netx_driver); - if (ret != 0) - uart_unregister_driver(&netx_reg); - - return 0; -} - -static void __exit netx_serial_exit(void) -{ - platform_driver_unregister(&serial_netx_driver); - uart_unregister_driver(&netx_reg); -} - -module_init(netx_serial_init); -module_exit(netx_serial_exit); - -MODULE_AUTHOR("Sascha Hauer"); -MODULE_DESCRIPTION("NetX serial port driver"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:" DRIVER_NAME); diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 5642c05e0da0..3cc3af1c2ee1 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -150,9 +150,6 @@ #define PORT_PNX8XXX 70 -/* Hilscher netx */ -#define PORT_NETX 71 - /* SUN4V Hypervisor Console */ #define PORT_SUNHV 72 From 643d83f0a3518d6fbcf88f970de0340a5aa6b5a2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 25 Jul 2019 08:28:45 +0200 Subject: [PATCH 352/823] x86/hpet: Undo the early counter is counting check Rui reported that on a Pentium D machine which has HPET forced enabled because it is not advertised by ACPI, the early counter is counting check leads to a silent boot hang. The reason is that the ordering of checking the counter first and then reconfiguring the HPET fails to work on that machine. As the HPET is not advertised and presumably not initialized by the BIOS the early enable and the following reconfiguration seems to bring it into a broken state. Adding clocksource=jiffies to the command line results in the following clocksource watchdog warning: clocksource: timekeeping watchdog on CPU1: Marking clocksource 'tsc-early' as unstable because the skew is too large: clocksource: 'hpet' wd_now: 33 wd_last: 33 mask: ffffffff That clearly shows that the HPET is not counting after it got reconfigured and reenabled. If the counter is not working then the HPET timer is not expiring either, which explains the boot hang. Move the counter is counting check after the full configuration again to unbreak these systems. Reported-by: Rui Salvaterra Fixes: 3222daf970f3 ("x86/hpet: Separate counter check out of clocksource register code") Signed-off-by: Thomas Gleixner Tested-by: Rui Salvaterra Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1907250810530.1791@nanos.tec.linutronix.de --- arch/x86/kernel/hpet.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index c43e96a938d0..c6f791bc481e 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -827,10 +827,6 @@ int __init hpet_enable(void) if (!hpet_cfg_working()) goto out_nohpet; - /* Validate that the counter is counting */ - if (!hpet_counting()) - goto out_nohpet; - /* * Read the period and check for a sane value: */ @@ -896,6 +892,14 @@ int __init hpet_enable(void) } hpet_print_config(); + /* + * Validate that the counter is counting. This needs to be done + * after sanitizing the config registers to properly deal with + * force enabled HPETs. + */ + if (!hpet_counting()) + goto out_nohpet; + clocksource_register_hz(&clocksource_hpet, (u32)hpet_freq); if (id & HPET_ID_LEGSUP) { From 517c3ba00916383af6411aec99442c307c23f684 Mon Sep 17 00:00:00 2001 From: Zhenzhong Duan Date: Thu, 25 Jul 2019 10:39:09 +0800 Subject: [PATCH 353/823] x86/speculation/mds: Apply more accurate check on hypervisor platform X86_HYPER_NATIVE isn't accurate for checking if running on native platform, e.g. CONFIG_HYPERVISOR_GUEST isn't set or "nopv" is enabled. Checking the CPU feature bit X86_FEATURE_HYPERVISOR to determine if it's running on native platform is more accurate. This still doesn't cover the platforms on which X86_FEATURE_HYPERVISOR is unsupported, e.g. VMware, but there is nothing which can be done about this scenario. Fixes: 8a4b06d391b0 ("x86/speculation/mds: Add sysfs reporting for MDS") Signed-off-by: Zhenzhong Duan Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1564022349-17338-1-git-send-email-zhenzhong.duan@oracle.com --- arch/x86/kernel/cpu/bugs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 66ca906aa790..801ecd1c3fd5 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1226,7 +1226,7 @@ static ssize_t l1tf_show_state(char *buf) static ssize_t mds_show_state(char *buf) { - if (!hypervisor_is_type(X86_HYPER_NATIVE)) { + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { return sprintf(buf, "%s; SMT Host state unknown\n", mds_strings[mds_mitigation]); } From 10b0f1c227ed8236555318cb26933881b7e907f9 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Tue, 2 Jul 2019 03:05:19 -0700 Subject: [PATCH 354/823] vmw_balloon: Remove Julien from the maintainers list Julien will not be a maintainer anymore. Signed-off-by: Nadav Amit Link: https://lore.kernel.org/r/20190702100519.7464-1-namit@vmware.com Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 783569e3c4b4..506902c3d5b6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17172,7 +17172,6 @@ F: drivers/vme/ F: include/linux/vme* VMWARE BALLOON DRIVER -M: Julien Freche M: Nadav Amit M: "VMware, Inc." L: linux-kernel@vger.kernel.org From 61d51456f35760a09e8aa1e6ddd247f1547015d3 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 18 Jul 2019 10:09:03 +0200 Subject: [PATCH 355/823] vt: Grab console_lock around con_is_bound in show_bind Not really harmful not to, but also not harm in grabbing the lock. And this shuts up a new WARNING I introduced in commit ddde3c18b700 ("vt: More locking checks"). Reported-by: Jens Remus Cc: linux-kernel@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: Nicolas Pitre Cc: Martin Hostettler Cc: Adam Borowski Cc: Mikulas Patocka Cc: Daniel Vetter Cc: Sam Ravnborg Fixes: ddde3c18b700 ("vt: More locking checks") Signed-off-by: Daniel Vetter Tested-by: Jens Remus Acked-by: Sam Ravnborg Link: https://lore.kernel.org/r/20190718080903.22622-1-daniel.vetter@ffwll.ch Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index ec92f36ab5c4..34aa39d1aed9 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -3771,7 +3771,11 @@ static ssize_t show_bind(struct device *dev, struct device_attribute *attr, char *buf) { struct con_driver *con = dev_get_drvdata(dev); - int bind = con_is_bound(con->con); + int bind; + + console_lock(); + bind = con_is_bound(con->con); + console_unlock(); return snprintf(buf, PAGE_SIZE, "%i\n", bind); } From 1b5621832f9bd9899370ea6928462cd02ebe7dc0 Mon Sep 17 00:00:00 2001 From: Arseny Solokha Date: Tue, 16 Jul 2019 18:12:36 +0700 Subject: [PATCH 356/823] eeprom: make older eeprom drivers select NVMEM_SYSFS misc/eeprom/{at24,at25,eeprom_93xx46} drivers all register their corresponding devices in the nvmem framework in compat mode which requires nvmem sysfs interface to be present. The latter, however, has been split out from nvmem under a separate Kconfig in commit ae0c2d725512 ("nvmem: core: add NVMEM_SYSFS Kconfig"). As a result, probing certain I2C-attached EEPROMs now fails with at24: probe of 0-0050 failed with error -38 because of a stub implementation of nvmem_sysfs_setup_compat() in drivers/nvmem/nvmem.h. Update the nvmem dependency for these drivers so they could load again: at24 0-0050: 32768 byte 24c256 EEPROM, writable, 64 bytes/write Cc: Adrian Bunk Cc: Bartosz Golaszewski Cc: Srinivas Kandagatla Cc: stable@vger.kernel.org # v5.2+ Signed-off-by: Arseny Solokha Link: https://lore.kernel.org/r/20190716111236.27803-1-asolokha@kb.kras.ru Signed-off-by: Greg Kroah-Hartman --- drivers/misc/eeprom/Kconfig | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/misc/eeprom/Kconfig b/drivers/misc/eeprom/Kconfig index f88094719552..f2abe27010ef 100644 --- a/drivers/misc/eeprom/Kconfig +++ b/drivers/misc/eeprom/Kconfig @@ -5,6 +5,7 @@ config EEPROM_AT24 tristate "I2C EEPROMs / RAMs / ROMs from most vendors" depends on I2C && SYSFS select NVMEM + select NVMEM_SYSFS select REGMAP_I2C help Enable this driver to get read/write support to most I2C EEPROMs @@ -34,6 +35,7 @@ config EEPROM_AT25 tristate "SPI EEPROMs from most vendors" depends on SPI && SYSFS select NVMEM + select NVMEM_SYSFS help Enable this driver to get read/write support to most SPI EEPROMs, after you configure the board init code to know about each eeprom @@ -80,6 +82,7 @@ config EEPROM_93XX46 depends on SPI && SYSFS select REGMAP select NVMEM + select NVMEM_SYSFS help Driver for the microwire EEPROM chipsets 93xx46x. The driver supports both read and write commands and also the command to From 0c7d37f4d9b8446956e97b7c5e61173cdb7c8522 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 11 Jul 2019 21:27:57 +0800 Subject: [PATCH 357/823] hpet: Fix division by zero in hpet_time_div() The base value in do_div() called by hpet_time_div() is truncated from unsigned long to uint32_t, resulting in a divide-by-zero exception. UBSAN: Undefined behaviour in ../drivers/char/hpet.c:572:2 division by zero CPU: 1 PID: 23682 Comm: syz-executor.3 Not tainted 4.4.184.x86_64+ #4 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 0000000000000000 b573382df1853d00 ffff8800a3287b98 ffffffff81ad7561 ffff8800a3287c00 ffffffff838b35b0 ffffffff838b3860 ffff8800a3287c20 0000000000000000 ffff8800a3287bb0 ffffffff81b8f25e ffffffff838b35a0 Call Trace: [] __dump_stack lib/dump_stack.c:15 [inline] [] dump_stack+0xc1/0x120 lib/dump_stack.c:51 [] ubsan_epilogue+0x12/0x8d lib/ubsan.c:166 [] __ubsan_handle_divrem_overflow+0x282/0x2c8 lib/ubsan.c:262 [] hpet_time_div drivers/char/hpet.c:572 [inline] [] hpet_ioctl_common drivers/char/hpet.c:663 [inline] [] hpet_ioctl_common.cold+0xa8/0xad drivers/char/hpet.c:577 [] hpet_ioctl+0xc6/0x180 drivers/char/hpet.c:676 [] vfs_ioctl fs/ioctl.c:43 [inline] [] file_ioctl fs/ioctl.c:470 [inline] [] do_vfs_ioctl+0x6e0/0xf70 fs/ioctl.c:605 [] SYSC_ioctl fs/ioctl.c:622 [inline] [] SyS_ioctl+0x94/0xc0 fs/ioctl.c:613 [] tracesys_phase2+0x90/0x95 The main C reproducer autogenerated by syzkaller, syscall(__NR_mmap, 0x20000000, 0x1000000, 3, 0x32, -1, 0); memcpy((void*)0x20000100, "/dev/hpet\000", 10); syscall(__NR_openat, 0xffffffffffffff9c, 0x20000100, 0, 0); syscall(__NR_ioctl, r[0], 0x40086806, 0x40000000000000); Fix it by using div64_ul(). Signed-off-by: Kefeng Wang Signed-off-by: Zhang HongJun Cc: stable Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/r/20190711132757.130092-1-wangkefeng.wang@huawei.com Signed-off-by: Greg Kroah-Hartman --- drivers/char/hpet.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 5c39f20378b8..9ac6671bb514 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -567,8 +567,7 @@ static inline unsigned long hpet_time_div(struct hpets *hpets, unsigned long long m; m = hpets->hp_tick_freq + (dis >> 1); - do_div(m, dis); - return (unsigned long)m; + return div64_ul(m, dis); } static int From d4fddac5a51c378c5d3e68658816c37132611e1f Mon Sep 17 00:00:00 2001 From: Wenwen Wang Date: Sun, 14 Jul 2019 01:11:35 -0500 Subject: [PATCH 358/823] test_firmware: fix a memory leak bug In test_firmware_init(), the buffer pointed to by the global pointer 'test_fw_config' is allocated through kzalloc(). Then, the buffer is initialized in __test_firmware_config_init(). In the case that the initialization fails, the following execution in test_firmware_init() needs to be terminated with an error code returned to indicate this failure. However, the allocated buffer is not freed on this execution path, leading to a memory leak bug. To fix the above issue, free the allocated buffer before returning from test_firmware_init(). Signed-off-by: Wenwen Wang Link: https://lore.kernel.org/r/1563084696-6865-1-git-send-email-wang6495@umn.edu Signed-off-by: Greg Kroah-Hartman --- lib/test_firmware.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/lib/test_firmware.c b/lib/test_firmware.c index 83ea6c4e623c..6ca97a63b3d6 100644 --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -886,8 +886,11 @@ static int __init test_firmware_init(void) return -ENOMEM; rc = __test_firmware_config_init(); - if (rc) + if (rc) { + kfree(test_fw_config); + pr_err("could not init firmware test config: %d\n", rc); return rc; + } rc = misc_register(&test_fw_misc_device); if (rc) { From 16d51a590a8ce3befb1308e0e7ab77f3b661af33 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 16 Jul 2019 17:20:45 +0200 Subject: [PATCH 359/823] sched/fair: Don't free p->numa_faults with concurrent readers When going through execve(), zero out the NUMA fault statistics instead of freeing them. During execve, the task is reachable through procfs and the scheduler. A concurrent /proc/*/sched reader can read data from a freed ->numa_faults allocation (confirmed by KASAN) and write it back to userspace. I believe that it would also be possible for a use-after-free read to occur through a race between a NUMA fault and execve(): task_numa_fault() can lead to task_numa_compare(), which invokes task_weight() on the currently running task of a different CPU. Another way to fix this would be to make ->numa_faults RCU-managed or add extra locking, but it seems easier to wipe the NUMA fault statistics on execve. Signed-off-by: Jann Horn Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Petr Mladek Cc: Sergey Senozhatsky Cc: Thomas Gleixner Cc: Will Deacon Fixes: 82727018b0d3 ("sched/numa: Call task_numa_free() from do_execve()") Link: https://lkml.kernel.org/r/20190716152047.14424-1-jannh@google.com Signed-off-by: Ingo Molnar --- fs/exec.c | 2 +- include/linux/sched/numa_balancing.h | 4 ++-- kernel/fork.c | 2 +- kernel/sched/fair.c | 24 ++++++++++++++++++++---- 4 files changed, 24 insertions(+), 8 deletions(-) diff --git a/fs/exec.c b/fs/exec.c index c71cbfe6826a..f7f6a140856a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1828,7 +1828,7 @@ static int __do_execve_file(int fd, struct filename *filename, membarrier_execve(current); rseq_execve(current); acct_update_integrals(current); - task_numa_free(current); + task_numa_free(current, false); free_bprm(bprm); kfree(pathbuf); if (filename) diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h index e7dd04a84ba8..3988762efe15 100644 --- a/include/linux/sched/numa_balancing.h +++ b/include/linux/sched/numa_balancing.h @@ -19,7 +19,7 @@ extern void task_numa_fault(int last_node, int node, int pages, int flags); extern pid_t task_numa_group_id(struct task_struct *p); extern void set_numabalancing_state(bool enabled); -extern void task_numa_free(struct task_struct *p); +extern void task_numa_free(struct task_struct *p, bool final); extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page, int src_nid, int dst_cpu); #else @@ -34,7 +34,7 @@ static inline pid_t task_numa_group_id(struct task_struct *p) static inline void set_numabalancing_state(bool enabled) { } -static inline void task_numa_free(struct task_struct *p) +static inline void task_numa_free(struct task_struct *p, bool final) { } static inline bool should_numa_migrate_memory(struct task_struct *p, diff --git a/kernel/fork.c b/kernel/fork.c index d8ae0f1b4148..2852d0e76ea3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -726,7 +726,7 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(tsk == current); cgroup_free(tsk); - task_numa_free(tsk); + task_numa_free(tsk, true); security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 036be95a87e9..6adb0e0f5feb 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2353,13 +2353,23 @@ no_join: return; } -void task_numa_free(struct task_struct *p) +/* + * Get rid of NUMA staticstics associated with a task (either current or dead). + * If @final is set, the task is dead and has reached refcount zero, so we can + * safely free all relevant data structures. Otherwise, there might be + * concurrent reads from places like load balancing and procfs, and we should + * reset the data back to default state without freeing ->numa_faults. + */ +void task_numa_free(struct task_struct *p, bool final) { struct numa_group *grp = p->numa_group; - void *numa_faults = p->numa_faults; + unsigned long *numa_faults = p->numa_faults; unsigned long flags; int i; + if (!numa_faults) + return; + if (grp) { spin_lock_irqsave(&grp->lock, flags); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) @@ -2372,8 +2382,14 @@ void task_numa_free(struct task_struct *p) put_numa_group(grp); } - p->numa_faults = NULL; - kfree(numa_faults); + if (final) { + p->numa_faults = NULL; + kfree(numa_faults); + } else { + p->total_numa_faults = 0; + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + numa_faults[i] = 0; + } } /* From cb361d8cdef69990f6b4504dc1fd9a594d983c97 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 16 Jul 2019 17:20:47 +0200 Subject: [PATCH 360/823] sched/fair: Use RCU accessors consistently for ->numa_group The old code used RCU annotations and accessors inconsistently for ->numa_group, which can lead to use-after-frees and NULL dereferences. Let all accesses to ->numa_group use proper RCU helpers to prevent such issues. Signed-off-by: Jann Horn Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Petr Mladek Cc: Sergey Senozhatsky Cc: Thomas Gleixner Cc: Will Deacon Fixes: 8c8a743c5087 ("sched/numa: Use {cpu, pid} to create task groups for shared faults") Link: https://lkml.kernel.org/r/20190716152047.14424-3-jannh@google.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 10 +++- kernel/sched/fair.c | 122 ++++++++++++++++++++++++++++-------------- 2 files changed, 91 insertions(+), 41 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 8dc1811487f5..9f51932bd543 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1092,7 +1092,15 @@ struct task_struct { u64 last_sum_exec_runtime; struct callback_head numa_work; - struct numa_group *numa_group; + /* + * This pointer is only modified for current in syscall and + * pagefault context (and for tasks being destroyed), so it can be read + * from any of the following contexts: + * - RCU read-side critical section + * - current->numa_group from everywhere + * - task's runqueue locked, task not running + */ + struct numa_group __rcu *numa_group; /* * numa_faults is an array split into four regions: diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6adb0e0f5feb..bc9cfeaac8bd 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1086,6 +1086,21 @@ struct numa_group { unsigned long faults[0]; }; +/* + * For functions that can be called in multiple contexts that permit reading + * ->numa_group (see struct task_struct for locking rules). + */ +static struct numa_group *deref_task_numa_group(struct task_struct *p) +{ + return rcu_dereference_check(p->numa_group, p == current || + (lockdep_is_held(&task_rq(p)->lock) && !READ_ONCE(p->on_cpu))); +} + +static struct numa_group *deref_curr_numa_group(struct task_struct *p) +{ + return rcu_dereference_protected(p->numa_group, p == current); +} + static inline unsigned long group_faults_priv(struct numa_group *ng); static inline unsigned long group_faults_shared(struct numa_group *ng); @@ -1129,10 +1144,12 @@ static unsigned int task_scan_start(struct task_struct *p) { unsigned long smin = task_scan_min(p); unsigned long period = smin; + struct numa_group *ng; /* Scale the maximum scan period with the amount of shared memory. */ - if (p->numa_group) { - struct numa_group *ng = p->numa_group; + rcu_read_lock(); + ng = rcu_dereference(p->numa_group); + if (ng) { unsigned long shared = group_faults_shared(ng); unsigned long private = group_faults_priv(ng); @@ -1140,6 +1157,7 @@ static unsigned int task_scan_start(struct task_struct *p) period *= shared + 1; period /= private + shared + 1; } + rcu_read_unlock(); return max(smin, period); } @@ -1148,13 +1166,14 @@ static unsigned int task_scan_max(struct task_struct *p) { unsigned long smin = task_scan_min(p); unsigned long smax; + struct numa_group *ng; /* Watch for min being lower than max due to floor calculations */ smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p); /* Scale the maximum scan period with the amount of shared memory. */ - if (p->numa_group) { - struct numa_group *ng = p->numa_group; + ng = deref_curr_numa_group(p); + if (ng) { unsigned long shared = group_faults_shared(ng); unsigned long private = group_faults_priv(ng); unsigned long period = smax; @@ -1186,7 +1205,7 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) p->numa_scan_period = sysctl_numa_balancing_scan_delay; p->numa_work.next = &p->numa_work; p->numa_faults = NULL; - p->numa_group = NULL; + RCU_INIT_POINTER(p->numa_group, NULL); p->last_task_numa_placement = 0; p->last_sum_exec_runtime = 0; @@ -1233,7 +1252,16 @@ static void account_numa_dequeue(struct rq *rq, struct task_struct *p) pid_t task_numa_group_id(struct task_struct *p) { - return p->numa_group ? p->numa_group->gid : 0; + struct numa_group *ng; + pid_t gid = 0; + + rcu_read_lock(); + ng = rcu_dereference(p->numa_group); + if (ng) + gid = ng->gid; + rcu_read_unlock(); + + return gid; } /* @@ -1258,11 +1286,13 @@ static inline unsigned long task_faults(struct task_struct *p, int nid) static inline unsigned long group_faults(struct task_struct *p, int nid) { - if (!p->numa_group) + struct numa_group *ng = deref_task_numa_group(p); + + if (!ng) return 0; - return p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 0)] + - p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)]; + return ng->faults[task_faults_idx(NUMA_MEM, nid, 0)] + + ng->faults[task_faults_idx(NUMA_MEM, nid, 1)]; } static inline unsigned long group_faults_cpu(struct numa_group *group, int nid) @@ -1400,12 +1430,13 @@ static inline unsigned long task_weight(struct task_struct *p, int nid, static inline unsigned long group_weight(struct task_struct *p, int nid, int dist) { + struct numa_group *ng = deref_task_numa_group(p); unsigned long faults, total_faults; - if (!p->numa_group) + if (!ng) return 0; - total_faults = p->numa_group->total_faults; + total_faults = ng->total_faults; if (!total_faults) return 0; @@ -1419,7 +1450,7 @@ static inline unsigned long group_weight(struct task_struct *p, int nid, bool should_numa_migrate_memory(struct task_struct *p, struct page * page, int src_nid, int dst_cpu) { - struct numa_group *ng = p->numa_group; + struct numa_group *ng = deref_curr_numa_group(p); int dst_nid = cpu_to_node(dst_cpu); int last_cpupid, this_cpupid; @@ -1600,13 +1631,14 @@ static bool load_too_imbalanced(long src_load, long dst_load, static void task_numa_compare(struct task_numa_env *env, long taskimp, long groupimp, bool maymove) { + struct numa_group *cur_ng, *p_ng = deref_curr_numa_group(env->p); struct rq *dst_rq = cpu_rq(env->dst_cpu); + long imp = p_ng ? groupimp : taskimp; struct task_struct *cur; long src_load, dst_load; - long load; - long imp = env->p->numa_group ? groupimp : taskimp; - long moveimp = imp; int dist = env->dist; + long moveimp = imp; + long load; if (READ_ONCE(dst_rq->numa_migrate_on)) return; @@ -1645,21 +1677,22 @@ static void task_numa_compare(struct task_numa_env *env, * If dst and source tasks are in the same NUMA group, or not * in any group then look only at task weights. */ - if (cur->numa_group == env->p->numa_group) { + cur_ng = rcu_dereference(cur->numa_group); + if (cur_ng == p_ng) { imp = taskimp + task_weight(cur, env->src_nid, dist) - task_weight(cur, env->dst_nid, dist); /* * Add some hysteresis to prevent swapping the * tasks within a group over tiny differences. */ - if (cur->numa_group) + if (cur_ng) imp -= imp / 16; } else { /* * Compare the group weights. If a task is all by itself * (not part of a group), use the task weight instead. */ - if (cur->numa_group && env->p->numa_group) + if (cur_ng && p_ng) imp += group_weight(cur, env->src_nid, dist) - group_weight(cur, env->dst_nid, dist); else @@ -1757,11 +1790,12 @@ static int task_numa_migrate(struct task_struct *p) .best_imp = 0, .best_cpu = -1, }; - struct sched_domain *sd; - struct rq *best_rq; unsigned long taskweight, groupweight; - int nid, ret, dist; + struct sched_domain *sd; long taskimp, groupimp; + struct numa_group *ng; + struct rq *best_rq; + int nid, ret, dist; /* * Pick the lowest SD_NUMA domain, as that would have the smallest @@ -1807,7 +1841,8 @@ static int task_numa_migrate(struct task_struct *p) * multiple NUMA nodes; in order to better consolidate the group, * we need to check other locations. */ - if (env.best_cpu == -1 || (p->numa_group && p->numa_group->active_nodes > 1)) { + ng = deref_curr_numa_group(p); + if (env.best_cpu == -1 || (ng && ng->active_nodes > 1)) { for_each_online_node(nid) { if (nid == env.src_nid || nid == p->numa_preferred_nid) continue; @@ -1840,7 +1875,7 @@ static int task_numa_migrate(struct task_struct *p) * A task that migrated to a second choice node will be better off * trying for a better one later. Do not set the preferred node here. */ - if (p->numa_group) { + if (ng) { if (env.best_cpu == -1) nid = env.src_nid; else @@ -2135,6 +2170,7 @@ static void task_numa_placement(struct task_struct *p) unsigned long total_faults; u64 runtime, period; spinlock_t *group_lock = NULL; + struct numa_group *ng; /* * The p->mm->numa_scan_seq field gets updated without @@ -2152,8 +2188,9 @@ static void task_numa_placement(struct task_struct *p) runtime = numa_get_avg_runtime(p, &period); /* If the task is part of a group prevent parallel updates to group stats */ - if (p->numa_group) { - group_lock = &p->numa_group->lock; + ng = deref_curr_numa_group(p); + if (ng) { + group_lock = &ng->lock; spin_lock_irq(group_lock); } @@ -2194,7 +2231,7 @@ static void task_numa_placement(struct task_struct *p) p->numa_faults[cpu_idx] += f_diff; faults += p->numa_faults[mem_idx]; p->total_numa_faults += diff; - if (p->numa_group) { + if (ng) { /* * safe because we can only change our own group * @@ -2202,14 +2239,14 @@ static void task_numa_placement(struct task_struct *p) * nid and priv in a specific region because it * is at the beginning of the numa_faults array. */ - p->numa_group->faults[mem_idx] += diff; - p->numa_group->faults_cpu[mem_idx] += f_diff; - p->numa_group->total_faults += diff; - group_faults += p->numa_group->faults[mem_idx]; + ng->faults[mem_idx] += diff; + ng->faults_cpu[mem_idx] += f_diff; + ng->total_faults += diff; + group_faults += ng->faults[mem_idx]; } } - if (!p->numa_group) { + if (!ng) { if (faults > max_faults) { max_faults = faults; max_nid = nid; @@ -2220,8 +2257,8 @@ static void task_numa_placement(struct task_struct *p) } } - if (p->numa_group) { - numa_group_count_active_nodes(p->numa_group); + if (ng) { + numa_group_count_active_nodes(ng); spin_unlock_irq(group_lock); max_nid = preferred_group_nid(p, max_nid); } @@ -2255,7 +2292,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, int cpu = cpupid_to_cpu(cpupid); int i; - if (unlikely(!p->numa_group)) { + if (unlikely(!deref_curr_numa_group(p))) { unsigned int size = sizeof(struct numa_group) + 4*nr_node_ids*sizeof(unsigned long); @@ -2291,7 +2328,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, if (!grp) goto no_join; - my_grp = p->numa_group; + my_grp = deref_curr_numa_group(p); if (grp == my_grp) goto no_join; @@ -2362,7 +2399,8 @@ no_join: */ void task_numa_free(struct task_struct *p, bool final) { - struct numa_group *grp = p->numa_group; + /* safe: p either is current or is being freed by current */ + struct numa_group *grp = rcu_dereference_raw(p->numa_group); unsigned long *numa_faults = p->numa_faults; unsigned long flags; int i; @@ -2442,7 +2480,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) * actively using should be counted as local. This allows the * scan rate to slow down when a workload has settled down. */ - ng = p->numa_group; + ng = deref_curr_numa_group(p); if (!priv && !local && ng && ng->active_nodes > 1 && numa_is_active_node(cpu_node, ng) && numa_is_active_node(mem_node, ng)) @@ -10460,18 +10498,22 @@ void show_numa_stats(struct task_struct *p, struct seq_file *m) { int node; unsigned long tsf = 0, tpf = 0, gsf = 0, gpf = 0; + struct numa_group *ng; + rcu_read_lock(); + ng = rcu_dereference(p->numa_group); for_each_online_node(node) { if (p->numa_faults) { tsf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 0)]; tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)]; } - if (p->numa_group) { - gsf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 0)], - gpf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 1)]; + if (ng) { + gsf = ng->faults[task_faults_idx(NUMA_MEM, node, 0)], + gpf = ng->faults[task_faults_idx(NUMA_MEM, node, 1)]; } print_numa_stats(m, node, tsf, tpf, gsf, gpf); } + rcu_read_unlock(); } #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_SCHED_DEBUG */ From 78134300579a45f527ca173ec8fdb4701b69f16e Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Sat, 20 Jul 2019 11:04:10 -0400 Subject: [PATCH 361/823] locking/rwsem: Don't call owner_on_cpu() on read-owner For writer, the owner value is cleared on unlock. For reader, it is left intact on unlock for providing better debugging aid on crash dump and the unlock of one reader may not mean the lock is free. As a result, the owner_on_cpu() shouldn't be used on read-owner as the task pointer value may not be valid and it might have been freed. That is the case in rwsem_spin_on_owner(), but not in rwsem_can_spin_on_owner(). This can lead to use-after-free error from KASAN. For example, BUG: KASAN: use-after-free in rwsem_down_write_slowpath (/home/miguel/kernel/linux/kernel/locking/rwsem.c:669 /home/miguel/kernel/linux/kernel/locking/rwsem.c:1125) Fix this by checking for RWSEM_READER_OWNED flag before calling owner_on_cpu(). Reported-by: Luis Henriques Tested-by: Luis Henriques Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Cc: Borislav Petkov Cc: Davidlohr Bueso Cc: H. Peter Anvin Cc: Jeff Layton Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tim Chen Cc: Will Deacon Cc: huang ying Fixes: 94a9717b3c40e ("locking/rwsem: Make rwsem->owner an atomic_long_t") Link: https://lkml.kernel.org/r/81e82d5b-5074-77e8-7204-28479bbe0df0@redhat.com Signed-off-by: Ingo Molnar --- kernel/locking/rwsem.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 37524a47f002..bc91aacaab58 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -666,7 +666,11 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem, preempt_disable(); rcu_read_lock(); owner = rwsem_owner_flags(sem, &flags); - if ((flags & nonspinnable) || (owner && !owner_on_cpu(owner))) + /* + * Don't check the read-owner as the entry may be stale. + */ + if ((flags & nonspinnable) || + (owner && !(flags & RWSEM_READER_OWNED) && !owner_on_cpu(owner))) ret = false; rcu_read_unlock(); preempt_enable(); From e1b98fa316648420d0434d9ff5b92ad6609ba6c3 Mon Sep 17 00:00:00 2001 From: Jan Stancek Date: Thu, 18 Jul 2019 10:51:25 +0200 Subject: [PATCH 362/823] locking/rwsem: Add missing ACQUIRE to read_slowpath exit when queue is empty LTP mtest06 has been observed to occasionally hit "still mapped when deleted" and following BUG_ON on arm64. The extra mapcount originated from pagefault handler, which handled pagefault for vma that has already been detached. vma is detached under mmap_sem write lock by detach_vmas_to_be_unmapped(), which also invalidates vmacache. When the pagefault handler (under mmap_sem read lock) calls find_vma(), vmacache_valid() wrongly reports vmacache as valid. After rwsem down_read() returns via 'queue empty' path (as of v5.2), it does so without an ACQUIRE on sem->count: down_read() __down_read() rwsem_down_read_failed() __rwsem_down_read_failed_common() raw_spin_lock_irq(&sem->wait_lock); if (list_empty(&sem->wait_list)) { if (atomic_long_read(&sem->count) >= 0) { raw_spin_unlock_irq(&sem->wait_lock); return sem; The problem can be reproduced by running LTP mtest06 in a loop and building the kernel (-j $NCPUS) in parallel. It does reproduces since v4.20 on arm64 HPE Apollo 70 (224 CPUs, 256GB RAM, 2 nodes). It triggers reliably in about an hour. The patched kernel ran fine for 10+ hours. Signed-off-by: Jan Stancek Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Will Deacon Acked-by: Waiman Long Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dbueso@suse.de Fixes: 4b486b535c33 ("locking/rwsem: Exit read lock slowpath if queue empty & no writer") Link: https://lkml.kernel.org/r/50b8914e20d1d62bb2dee42d342836c2c16ebee7.1563438048.git.jstancek@redhat.com Signed-off-by: Ingo Molnar --- kernel/locking/rwsem.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index bc91aacaab58..d3ce7c6c42a6 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1036,6 +1036,8 @@ queue: */ if (adjustment && !(atomic_long_read(&sem->count) & (RWSEM_WRITER_MASK | RWSEM_FLAG_HANDOFF))) { + /* Provide lock ACQUIRE */ + smp_acquire__after_ctrl_dep(); raw_spin_unlock_irq(&sem->wait_lock); rwsem_set_reader_owned(sem); lockevent_inc(rwsem_rlock_fast); From 99143f82a255e7f054bead8443462fae76dd829e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 18 Jul 2019 14:56:17 +0200 Subject: [PATCH 363/823] lcoking/rwsem: Add missing ACQUIRE to read_slowpath sleep loop While reviewing another read_slowpath patch, both Will and I noticed another missing ACQUIRE, namely: X = 0; CPU0 CPU1 rwsem_down_read() for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); X = 1; rwsem_up_write(); rwsem_mark_wake() atomic_long_add(adjustment, &sem->count); smp_store_release(&waiter->task, NULL); if (!waiter.task) break; ... } r = X; Allows 'r == 0'. Reported-by: Peter Zijlstra (Intel) Reported-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Ingo Molnar --- kernel/locking/rwsem.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index d3ce7c6c42a6..571938887cc8 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1073,8 +1073,10 @@ queue: /* wait to be given the lock */ while (true) { set_current_state(state); - if (!waiter.task) + if (!smp_load_acquire(&waiter.task)) { + /* Orders against rwsem_mark_wake()'s smp_store_release() */ break; + } if (signal_pending_state(state, current)) { raw_spin_lock_irq(&sem->wait_lock); if (waiter.task) From 952041a8639a7a3a73a2b6573cb8aa8518bc39f8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 18 Jul 2019 15:03:15 +0200 Subject: [PATCH 364/823] tty/ldsem, locking/rwsem: Add missing ACQUIRE to read_failed sleep loop While reviewing rwsem down_slowpath, Will noticed ldsem had a copy of a bug we just found for rwsem. X = 0; CPU0 CPU1 rwsem_down_read() for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); X = 1; rwsem_up_write(); rwsem_mark_wake() atomic_long_add(adjustment, &sem->count); smp_store_release(&waiter->task, NULL); if (!waiter.task) break; ... } r = X; Allows 'r == 0'. Reported-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Linus Torvalds Cc: Peter Hurley Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 4898e640caf0 ("tty: Add timed, writer-prioritized rw semaphore") Signed-off-by: Ingo Molnar --- drivers/tty/tty_ldsem.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c index 717292c1c0df..60ff236a3d63 100644 --- a/drivers/tty/tty_ldsem.c +++ b/drivers/tty/tty_ldsem.c @@ -93,8 +93,7 @@ static void __ldsem_wake_readers(struct ld_semaphore *sem) list_for_each_entry_safe(waiter, next, &sem->read_wait, list) { tsk = waiter->task; - smp_mb(); - waiter->task = NULL; + smp_store_release(&waiter->task, NULL); wake_up_process(tsk); put_task_struct(tsk); } @@ -194,7 +193,7 @@ down_read_failed(struct ld_semaphore *sem, long count, long timeout) for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); - if (!waiter.task) + if (!smp_load_acquire(&waiter.task)) break; if (!timeout) break; From 6ffddfb9e1de21c3d0c0cfa4fe4a20dd3291a812 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 18 Jul 2019 15:08:53 +0200 Subject: [PATCH 365/823] locking/rwsem: Add ACQUIRE comments Since we just reviewed read_slowpath for ACQUIRE correctness, add a few coments to retain our findings. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- kernel/locking/rwsem.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 571938887cc8..bd0f0d05724c 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1004,6 +1004,7 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, int state) atomic_long_add(-RWSEM_READER_BIAS, &sem->count); adjustment = 0; if (rwsem_optimistic_spin(sem, false)) { + /* rwsem_optimistic_spin() implies ACQUIRE on success */ /* * Wake up other readers in the wait list if the front * waiter is a reader. @@ -1018,6 +1019,7 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, int state) } return sem; } else if (rwsem_reader_phase_trylock(sem, waiter.last_rowner)) { + /* rwsem_reader_phase_trylock() implies ACQUIRE on success */ return sem; } @@ -1071,10 +1073,10 @@ queue: wake_up_q(&wake_q); /* wait to be given the lock */ - while (true) { + for (;;) { set_current_state(state); if (!smp_load_acquire(&waiter.task)) { - /* Orders against rwsem_mark_wake()'s smp_store_release() */ + /* Matches rwsem_mark_wake()'s smp_store_release(). */ break; } if (signal_pending_state(state, current)) { @@ -1082,6 +1084,7 @@ queue: if (waiter.task) goto out_nolock; raw_spin_unlock_irq(&sem->wait_lock); + /* Ordered by sem->wait_lock against rwsem_mark_wake(). */ break; } schedule(); @@ -1091,6 +1094,7 @@ queue: __set_current_state(TASK_RUNNING); lockevent_inc(rwsem_rlock); return sem; + out_nolock: list_del(&waiter.list); if (list_empty(&sem->wait_list)) { @@ -1131,8 +1135,10 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) /* do optimistic spinning and steal lock if possible */ if (rwsem_can_spin_on_owner(sem, RWSEM_WR_NONSPINNABLE) && - rwsem_optimistic_spin(sem, true)) + rwsem_optimistic_spin(sem, true)) { + /* rwsem_optimistic_spin() implies ACQUIRE on success */ return sem; + } /* * Disable reader optimistic spinning for this rwsem after @@ -1192,9 +1198,11 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) wait: /* wait until we successfully acquire the lock */ set_current_state(state); - while (true) { - if (rwsem_try_write_lock(sem, wstate)) + for (;;) { + if (rwsem_try_write_lock(sem, wstate)) { + /* rwsem_try_write_lock() implies ACQUIRE on success */ break; + } raw_spin_unlock_irq(&sem->wait_lock); From 68037aa78208f34bda4e5cd76c357f718b838cbb Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 15 Jul 2019 11:27:49 +0200 Subject: [PATCH 366/823] locking/lockdep: Hide unused 'class' variable The usage is now hidden in an #ifdef, so we need to move the variable itself in there as well to avoid this warning: kernel/locking/lockdep_proc.c:203:21: error: unused variable 'class' [-Werror,-Wunused-variable] Signed-off-by: Arnd Bergmann Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Bart Van Assche Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Qian Cai Cc: Thomas Gleixner Cc: Waiman Long Cc: Will Deacon Cc: Will Deacon Cc: Yuyang Du Cc: frederic@kernel.org Fixes: 68d41d8c94a3 ("locking/lockdep: Fix lock used or unused stats error") Link: https://lkml.kernel.org/r/20190715092809.736834-1-arnd@arndb.de Signed-off-by: Ingo Molnar --- kernel/locking/lockdep_proc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index 65b6a1600c8f..bda006f8a88b 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -200,7 +200,6 @@ static void lockdep_stats_debug_show(struct seq_file *m) static int lockdep_stats_show(struct seq_file *m, void *v) { - struct lock_class *class; unsigned long nr_unused = 0, nr_uncategorized = 0, nr_irq_safe = 0, nr_irq_unsafe = 0, nr_softirq_safe = 0, nr_softirq_unsafe = 0, @@ -211,6 +210,8 @@ static int lockdep_stats_show(struct seq_file *m, void *v) sum_forward_deps = 0; #ifdef CONFIG_PROVE_LOCKING + struct lock_class *class; + list_for_each_entry(class, &all_lock_classes, lock_entry) { if (class->usage_mask == 0) From 30a35f79faadfeb1b89a7fdb3875f14063519041 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 28 Jun 2019 12:29:03 +0200 Subject: [PATCH 367/823] locking/lockdep: Clean up #ifdef checks As Will Deacon points out, CONFIG_PROVE_LOCKING implies TRACE_IRQFLAGS, so the conditions I added in the previous patch, and some others in the same file can be simplified by only checking for the former. No functional change. Signed-off-by: Arnd Bergmann Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Andrew Morton Cc: Bart Van Assche Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman Long Cc: Yuyang Du Fixes: 886532aee3cd ("locking/lockdep: Move mark_lock() inside CONFIG_TRACE_IRQFLAGS && CONFIG_PROVE_LOCKING") Link: https://lkml.kernel.org/r/20190628102919.2345242-1-arnd@arndb.de Signed-off-by: Ingo Molnar --- kernel/locking/lockdep.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 341f52117f88..4861cf8e274b 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -448,7 +448,7 @@ static void print_lockdep_off(const char *bug_msg) unsigned long nr_stack_trace_entries; -#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) +#ifdef CONFIG_PROVE_LOCKING /* * Stack-trace: tightly packed array of stack backtrace * addresses. Protected by the graph_lock. @@ -491,7 +491,7 @@ unsigned int max_lockdep_depth; DEFINE_PER_CPU(struct lockdep_stats, lockdep_stats); #endif -#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) +#ifdef CONFIG_PROVE_LOCKING /* * Locking printouts: */ @@ -2969,7 +2969,7 @@ static void check_chain_key(struct task_struct *curr) #endif } -#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) +#ifdef CONFIG_PROVE_LOCKING static int mark_lock(struct task_struct *curr, struct held_lock *this, enum lock_usage_bit new_bit); @@ -3608,7 +3608,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, return ret; } -#else /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */ +#else /* CONFIG_PROVE_LOCKING */ static inline int mark_usage(struct task_struct *curr, struct held_lock *hlock, int check) @@ -3627,7 +3627,7 @@ static inline int separate_irq_context(struct task_struct *curr, return 0; } -#endif /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */ +#endif /* CONFIG_PROVE_LOCKING */ /* * Initialize a lock instance's lock-class mapping info: @@ -4321,8 +4321,7 @@ static void __lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie */ static void check_flags(unsigned long flags) { -#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP) && \ - defined(CONFIG_TRACE_IRQFLAGS) +#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP) if (!debug_locks) return; From 6c11c6e3d5e9e5caf8686cd6a5e4552cfc3ea326 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 3 Jul 2019 11:21:26 +0200 Subject: [PATCH 368/823] locking/mutex: Test for initialized mutex An uninitialized/ zeroed mutex will go unnoticed because there is no check for it. There is a magic check in the unlock's slowpath path which might go unnoticed if the unlock happens in the fastpath. Add a ->magic check early in the mutex_lock() and mutex_trylock() path. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20190703092125.lsdf4gpsh2plhavb@linutronix.de Signed-off-by: Ingo Molnar --- kernel/locking/mutex.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index edd1c082dbf5..5e069734363c 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -908,6 +908,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, might_sleep(); +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(lock->magic != lock); +#endif + ww = container_of(lock, struct ww_mutex, base); if (use_ww_ctx && ww_ctx) { if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) @@ -1379,8 +1383,13 @@ __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock, */ int __sched mutex_trylock(struct mutex *lock) { - bool locked = __mutex_trylock(lock); + bool locked; +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(lock->magic != lock); +#endif + + locked = __mutex_trylock(lock); if (locked) mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); From 3d0c3953601d250175c7684ec0d9df612061dae5 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 23 Jul 2019 13:04:29 -0700 Subject: [PATCH 369/823] perf/x86/intel: Fix SLOTS PEBS event constraint Sampling SLOTS event and ref-cycles event in a group on Icelake gives EINVAL. SLOTS event is the event stands for the fixed counter 3, not fixed counter 2. Wrong mask was set to SLOTS event in intel_icl_pebs_event_constraints[]. Reported-by: Andi Kleen Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 6017608936c1 ("perf/x86/intel: Add Icelake support") Link: https://lkml.kernel.org/r/20190723200429.8180-1-kan.liang@linux.intel.com Signed-off-by: Ingo Molnar --- arch/x86/events/intel/ds.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 2c8db2c19328..f1269e804e9b 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -851,7 +851,7 @@ struct event_constraint intel_skl_pebs_event_constraints[] = { struct event_constraint intel_icl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ - INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x400000000ULL), /* SLOTS */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */ From 3b238a64c3009fed36eaea1af629d9377759d87d Mon Sep 17 00:00:00 2001 From: Yunying Sun Date: Wed, 24 Jul 2019 16:29:32 +0800 Subject: [PATCH 370/823] perf/x86/intel: Fix invalid Bit 13 for Icelake MSR_OFFCORE_RSP_x register The Intel SDM states that bit 13 of Icelake's MSR_OFFCORE_RSP_x register is valid, and used for counting hardware generated prefetches of L3 cache. Update the bitmask to allow bit 13. Before: $ perf stat -e cpu/event=0xb7,umask=0x1,config1=0x1bfff/u sleep 3 Performance counter stats for 'sleep 3': cpu/event=0xb7,umask=0x1,config1=0x1bfff/u After: $ perf stat -e cpu/event=0xb7,umask=0x1,config1=0x1bfff/u sleep 3 Performance counter stats for 'sleep 3': 9,293 cpu/event=0xb7,umask=0x1,config1=0x1bfff/u Signed-off-by: Yunying Sun Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Kan Liang Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: acme@kernel.org Cc: alexander.shishkin@linux.intel.com Cc: bp@alien8.de Cc: hpa@zytor.com Cc: jolsa@redhat.com Cc: namhyung@kernel.org Link: https://lkml.kernel.org/r/20190724082932.12833-1-yunying.sun@intel.com Signed-off-by: Ingo Molnar --- arch/x86/events/intel/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 9e911a96972b..b35519cbc8b4 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -263,8 +263,8 @@ static struct event_constraint intel_icl_event_constraints[] = { }; static struct extra_reg intel_icl_extra_regs[] __read_mostly = { - INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff9fffull, RSP_0), - INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff9fffull, RSP_1), + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffffbfffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffffbfffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), EVENT_EXTRA_END From 5ea3f6fb37b79da33ac9211df336fd2b9f47c39f Mon Sep 17 00:00:00 2001 From: Zhenzhong Duan Date: Thu, 25 Jul 2019 10:39:26 +0800 Subject: [PATCH 371/823] perf/x86: Apply more accurate check on hypervisor platform check_msr is used to fix a bug report in guest where KVM doesn't support LBR MSR and cause #GP. The msr check is bypassed on real HW to workaround a false failure, see commit d0e1a507bdc7 ("perf/x86/intel: Disable check_msr for real HW") When running a guest with CONFIG_HYPERVISOR_GUEST not set or "nopv" enabled, current check isn't enough and #GP could trigger. Signed-off-by: Zhenzhong Duan Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Jiri Olsa Cc: Juergen Gross Cc: Linus Torvalds Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/1564022366-18293-1-git-send-email-zhenzhong.duan@oracle.com Signed-off-by: Ingo Molnar --- arch/x86/events/intel/core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index b35519cbc8b4..c9075fc75cb6 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -20,7 +20,6 @@ #include #include #include -#include #include "../perf_event.h" @@ -4053,7 +4052,7 @@ static bool check_msr(unsigned long msr, u64 mask) * Disable the check for real HW, so we don't * mess with potentionaly enabled registers: */ - if (hypervisor_is_type(X86_HYPER_NATIVE)) + if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) return true; /* From 4ce54af8b33d3e21ca935fc1b89b58cbba956051 Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Wed, 24 Jul 2019 15:53:24 +0300 Subject: [PATCH 372/823] perf/core: Fix creating kernel counters for PMUs that override event->cpu Some hardware PMU drivers will override perf_event.cpu inside their event_init callback. This causes a lockdep splat when initialized through the kernel API: WARNING: CPU: 0 PID: 250 at kernel/events/core.c:2917 ctx_sched_out+0x78/0x208 pc : ctx_sched_out+0x78/0x208 Call trace: ctx_sched_out+0x78/0x208 __perf_install_in_context+0x160/0x248 remote_function+0x58/0x68 generic_exec_single+0x100/0x180 smp_call_function_single+0x174/0x1b8 perf_install_in_context+0x178/0x188 perf_event_create_kernel_counter+0x118/0x160 Fix this by calling perf_install_in_context with event->cpu, just like perf_event_open Signed-off-by: Leonard Crestez Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Mark Rutland Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Frank Li Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Link: https://lkml.kernel.org/r/c4ebe0503623066896d7046def4d6b1e06e0eb2e.1563972056.git.leonard.crestez@nxp.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 026a14541a38..0463c1151bae 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -11274,7 +11274,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, goto err_unlock; } - perf_install_in_context(ctx, event, cpu); + perf_install_in_context(ctx, event, event->cpu); perf_unpin_context(ctx); mutex_unlock(&ctx->mutex); From 289a2d22b5b611d85030795802a710e9f520df29 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 24 Jun 2019 11:19:13 -0500 Subject: [PATCH 373/823] perf/x86/intel: Mark expected switch fall-throughs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. This patch fixes the following warnings: arch/x86/events/intel/core.c: In function ‘intel_pmu_init’: arch/x86/events/intel/core.c:4959:8: warning: this statement may fall through [-Wimplicit-fallthrough=] arch/x86/events/intel/core.c:5008:8: warning: this statement may fall through [-Wimplicit-fallthrough=] Warning level 3 was used: -Wimplicit-fallthrough=3 This patch is part of the ongoing efforts to enable -Wimplicit-fallthrough. Signed-off-by: Gustavo A. R. Silva Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Jiri Olsa Cc: Kan Liang Cc: Kees Cook Cc: Linus Torvalds Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20190624161913.GA32270@embeddedor Signed-off-by: Ingo Molnar --- arch/x86/events/intel/core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index c9075fc75cb6..648260b5f367 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4954,6 +4954,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_SKYLAKE_X: pmem = true; + /* fall through */ case INTEL_FAM6_SKYLAKE_MOBILE: case INTEL_FAM6_SKYLAKE_DESKTOP: case INTEL_FAM6_KABYLAKE_MOBILE: @@ -5003,6 +5004,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ICELAKE_X: case INTEL_FAM6_ICELAKE_XEON_D: pmem = true; + /* fall through */ case INTEL_FAM6_ICELAKE_MOBILE: case INTEL_FAM6_ICELAKE_DESKTOP: x86_pmu.late_ack = true; From 296e3a2aad09d328f22e54655c3d736033fe1ae8 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Tue, 23 Jul 2019 09:57:30 +0300 Subject: [PATCH 374/823] IB/mlx5: Prevent concurrent MR updates during invalidation The device requires that memory registration work requests that update the address translation table of a MR will be fenced if posted together. This scenario can happen when address ranges are invalidated by the mmu in separate concurrent calls to the invalidation callback. We prefer to block concurrent address updates for a single MR over fencing since making the decision if a WQE needs fencing will be more expensive and fencing all WQEs is a too radical choice. Further, it isn't clear that this code can even run safely concurrently, so a lock is a safer choice. Fixes: b4cfe447d47b ("IB/mlx5: Implement on demand paging by adding support for MMU notifiers") Link: https://lore.kernel.org/r/20190723065733.4899-8-leon@kernel.org Signed-off-by: Moni Shoua Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/odp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 36ba901cc9a5..81da82050d05 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -246,7 +246,7 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start, * overwrite the same MTTs. Concurent invalidations might race us, * but they will write 0s as well, so no difference in the end result. */ - + mutex_lock(&umem_odp->umem_mutex); for (addr = start; addr < end; addr += BIT(umem_odp->page_shift)) { idx = (addr - ib_umem_start(umem_odp)) >> umem_odp->page_shift; /* @@ -278,6 +278,7 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start, idx - blk_start_idx + 1, 0, MLX5_IB_UPD_XLT_ZAP | MLX5_IB_UPD_XLT_ATOMIC); + mutex_unlock(&umem_odp->umem_mutex); /* * We are now sure that the device will not access the * memory. We can safely unmap it, and mark it as dirty if From a379d1ce32f1c97b19d68cffbd195e025dbb9d43 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 23 Jul 2019 09:57:32 +0300 Subject: [PATCH 375/823] IB/core: Fix querying total rdma stats rdma_counter_init() may fail for a device. In such case while calculating total sum, ignore NULL hstats. This fixes below observed call trace. BUG: kernel NULL pointer dereference, address: 00000000000000a0 PGD 8000001009b30067 P4D 8000001009b30067 PUD 10549c9067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 55 PID: 20887 Comm: cat Kdump: loaded Not tainted 5.2.0-rc6-jdc+ #13 RIP: 0010:rdma_counter_get_hwstat_value+0xf2/0x150 [ib_core] Call Trace: show_hw_stats+0x5e/0x130 [ib_core] dev_attr_show+0x15/0x50 sysfs_kf_seq_show+0xc6/0x1a0 seq_read+0x132/0x370 vfs_read+0x89/0x140 ksys_read+0x5c/0xd0 do_syscall_64+0x5a/0x240 entry_SYSCALL_64_after_hwframe+0x49/0xbe Fixes: f34a55e497e8 ("RDMA/core: Get sum value of all counters when perform a sysfs stat read") Link: https://lore.kernel.org/r/20190723065733.4899-10-leon@kernel.org Signed-off-by: Parav Pandit Reviewed-by: Mark Zhang Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/counters.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c index 01faef7bc061..c7d445635476 100644 --- a/drivers/infiniband/core/counters.c +++ b/drivers/infiniband/core/counters.c @@ -393,6 +393,9 @@ u64 rdma_counter_get_hwstat_value(struct ib_device *dev, u8 port, u32 index) u64 sum; port_counter = &dev->port_data[port].port_counter; + if (!port_counter->hstats) + return 0; + sum = get_running_counters_hwstat_sum(dev, port, index); sum += port_counter->hstats->value[index]; From d191152f43a5869d7dbb50dd2a7a4b3b8b71f1f0 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 23 Jul 2019 09:57:33 +0300 Subject: [PATCH 376/823] IB/counters: Always initialize the port counter object Port counter objects should be initialized even if alloc_stats is unsupported, otherwise QP bind operations in user space can trigger a NULL pointer deference if they try to bind QP on RDMA device which doesn't support counters. Fixes: f34a55e497e8 ("RDMA/core: Get sum value of all counters when perform a sysfs stat read") Link: https://lore.kernel.org/r/20190723065733.4899-11-leon@kernel.org Signed-off-by: Parav Pandit Reviewed-by: Mark Zhang Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/counters.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c index c7d445635476..45d5164e9574 100644 --- a/drivers/infiniband/core/counters.c +++ b/drivers/infiniband/core/counters.c @@ -597,7 +597,7 @@ void rdma_counter_init(struct ib_device *dev) struct rdma_port_counter *port_counter; u32 port; - if (!dev->ops.alloc_hw_stats || !dev->port_data) + if (!dev->port_data) return; rdma_for_each_port(dev, port) { @@ -605,6 +605,9 @@ void rdma_counter_init(struct ib_device *dev) port_counter->mode.mode = RDMA_COUNTER_MODE_NONE; mutex_init(&port_counter->lock); + if (!dev->ops.alloc_hw_stats) + continue; + port_counter->hstats = dev->ops.alloc_hw_stats(dev, port); if (!port_counter->hstats) goto fail; @@ -627,9 +630,6 @@ void rdma_counter_release(struct ib_device *dev) struct rdma_port_counter *port_counter; u32 port; - if (!dev->ops.alloc_hw_stats) - return; - rdma_for_each_port(dev, port) { port_counter = &dev->port_data[port].port_counter; kfree(port_counter->hstats); From b7165bd0d6cbb93732559be6ea8774653b204480 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 23 Jul 2019 09:57:29 +0300 Subject: [PATCH 377/823] IB/mlx5: Fix RSS Toeplitz setup to be aligned with the HW specification The specification for the Toeplitz function doesn't require to set the key explicitly to be symmetric. In case a symmetric functionality is required a symmetric key can be simply used. Wrongly forcing the algorithm to symmetric causes the wrong packet distribution and a performance degradation. Link: https://lore.kernel.org/r/20190723065733.4899-7-leon@kernel.org Cc: # 4.7 Fixes: 28d6137008b2 ("IB/mlx5: Add RSS QP support") Signed-off-by: Yishai Hadas Reviewed-by: Alex Vainman Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/qp.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 615cc6771516..379328b2598f 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1713,7 +1713,6 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, } MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_TOEPLITZ); - MLX5_SET(tirc, tirc, rx_hash_symmetric, 1); memcpy(rss_key, ucmd.rx_hash_key, len); break; } From 6e7ca09b583de4be6c27d9d4b06e8c5dd46a58fa Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Thu, 25 Jul 2019 11:27:29 +0300 Subject: [PATCH 378/823] btrfs: Fix deadlock caused by missing memory barrier Commit 06297d8cefca ("btrfs: switch extent_buffer blocking_writers from atomic to int") changed the type of blocking_writers but forgot to adjust relevant code in btrfs_tree_unlock by converting the smp_mb__after_atomic to smp_mb. This opened up the possibility of a deadlock due to re-ordering of setting blocking_writers and checking/waking up the waiter. This particular lockup is explained in a comment above waitqueue_active() function. Fix it by converting the memory barrier to a full smp_mb, accounting for the fact that blocking_writers is a simple integer. Fixes: 06297d8cefca ("btrfs: switch extent_buffer blocking_writers from atomic to int") Tested-by: Johannes Thumshirn Signed-off-by: Nikolay Borisov Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/locking.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 98fccce4208c..393eceda57c8 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -346,9 +346,12 @@ void btrfs_tree_unlock(struct extent_buffer *eb) if (blockers) { btrfs_assert_no_spinning_writers(eb); eb->blocking_writers--; - /* Use the lighter barrier after atomic */ - smp_mb__after_atomic(); - cond_wake_up_nomb(&eb->write_lock_wq); + /* + * We need to order modifying blocking_writers above with + * actually waking up the sleepers to ensure they see the + * updated value of blocking_writers + */ + cond_wake_up(&eb->write_lock_wq); } else { btrfs_assert_spinning_writers_put(eb); write_unlock(&eb->lock); From 36703247d5f52a679df9da51192b6950fe81689f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 25 Jul 2019 10:20:18 -0600 Subject: [PATCH 379/823] io_uring: ensure ->list is initialized for poll commands Daniel reports that when testing an http server that uses io_uring to poll for incoming connections, sometimes it hard crashes. This is due to an uninitialized list member for the io_uring request. Normally this doesn't trigger and none of the test cases caught it. Reported-by: Daniel Kozak Tested-by: Daniel Kozak Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/io_uring.c b/fs/io_uring.c index 2039f888197e..15d9b16ed29d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1666,6 +1666,8 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) INIT_LIST_HEAD(&poll->wait.entry); init_waitqueue_func_entry(&poll->wait, io_poll_wake); + INIT_LIST_HEAD(&req->list); + mask = vfs_poll(poll->file, &ipt.pt) & poll->events; spin_lock_irq(&ctx->completion_lock); From edbfe83def34153a05439ecb3352ae0bb65024de Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sat, 29 Jun 2019 11:41:36 +0200 Subject: [PATCH 380/823] platform/x86: pcengines-apuv2: Fix softdep statement Only first MODULE_SOFTDEP statement is handled per module. Multiple dependencies must be expressed in a single statement. Signed-off-by: Jean Delvare Cc: "Enrico Weigelt, metux IT consult" Cc: Darren Hart Cc: Andy Shevchenko [andy: massaged commit message] Signed-off-by: Andy Shevchenko --- drivers/platform/x86/pcengines-apuv2.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/platform/x86/pcengines-apuv2.c b/drivers/platform/x86/pcengines-apuv2.c index b0d3110ae378..96b499c6929a 100644 --- a/drivers/platform/x86/pcengines-apuv2.c +++ b/drivers/platform/x86/pcengines-apuv2.c @@ -255,6 +255,4 @@ MODULE_DESCRIPTION("PC Engines APUv2/APUv3 board GPIO/LED/keys driver"); MODULE_LICENSE("GPL"); MODULE_DEVICE_TABLE(dmi, apu_gpio_dmi_table); MODULE_ALIAS("platform:pcengines-apuv2"); -MODULE_SOFTDEP("pre: platform:" AMD_FCH_GPIO_DRIVER_NAME); -MODULE_SOFTDEP("pre: platform:leds-gpio"); -MODULE_SOFTDEP("pre: platform:gpio_keys_polled"); +MODULE_SOFTDEP("pre: platform:" AMD_FCH_GPIO_DRIVER_NAME " platform:leds-gpio platform:gpio_keys_polled"); From 8732d85a69a0411f16a4b78df8fdc7b09c50a849 Mon Sep 17 00:00:00 2001 From: Mattias Jacobsson <2pi@mok.nu> Date: Fri, 19 Jul 2019 19:51:45 +0200 Subject: [PATCH 381/823] platform/x86: wmi: add missing struct parameter description Add a description for the context parameter in the struct wmi_device_id. Reported-by: kbuild test robot Fixes: a48e23385fcf ("platform/x86: wmi: add context pointer field to struct wmi_device_id") Signed-off-by: Mattias Jacobsson <2pi@mok.nu> Signed-off-by: Andy Shevchenko --- include/linux/mod_devicetable.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index b2c1648f7e5d..5714fd35a83c 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -814,6 +814,7 @@ struct tee_client_device_id { /** * struct wmi_device_id - WMI device identifier * @guid_string: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba + * @context: pointer to driver specific data */ struct wmi_device_id { const char guid_string[UUID_STRING_LEN+1]; From cb8ffde5694ae5fffb456eae932aac442aa3a207 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 24 Jul 2019 14:47:53 -0700 Subject: [PATCH 382/823] libbpf: silence GCC8 warning about string truncation Despite a proper NULL-termination after strncpy(..., ..., IFNAMSIZ - 1), GCC8 still complains about *expected* string truncation: xsk.c:330:2: error: 'strncpy' output may be truncated copying 15 bytes from a string of length 15 [-Werror=stringop-truncation] strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1); This patch gets rid of the issue altogether by using memcpy instead. There is no performance regression, as strncpy will still copy and fill all of the bytes anyway. v1->v2: - rebase against bpf tree. Cc: Magnus Karlsson Signed-off-by: Andrii Nakryiko Acked-by: Magnus Karlsson Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/xsk.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index e02025bbe36d..680e63066cf3 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -326,7 +326,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk) return -errno; ifr.ifr_data = (void *)&channels; - strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1); + memcpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1); ifr.ifr_name[IFNAMSIZ - 1] = '\0'; err = ioctl(fd, SIOCETHTOOL, &ifr); if (err && errno != EOPNOTSUPP) { @@ -516,7 +516,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, err = -errno; goto out_socket; } - strncpy(xsk->ifname, ifname, IFNAMSIZ - 1); + memcpy(xsk->ifname, ifname, IFNAMSIZ - 1); xsk->ifname[IFNAMSIZ - 1] = '\0'; err = xsk_set_xdp_socket_config(&xsk->config, usr_config); From 6acf5d76ab685e921771abbbae5353929f3ebbe6 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Tue, 23 Jul 2019 11:20:22 +0200 Subject: [PATCH 383/823] Platform: OLPC: add SPI MODULE_DEVICE_TABLE The SPI bus creates a device with the modalias of "xo1.75-ec". This fixes XO-1.75 EC driver autoloading Fixes: 0c3d931b3ab9 ("Platform: OLPC: Add XO-1.75 EC driver") Signed-off-by: Lubomir Rintel Signed-off-by: Andy Shevchenko --- drivers/platform/olpc/olpc-xo175-ec.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/platform/olpc/olpc-xo175-ec.c b/drivers/platform/olpc/olpc-xo175-ec.c index 48d6f0d87583..83ed1fbf73cf 100644 --- a/drivers/platform/olpc/olpc-xo175-ec.c +++ b/drivers/platform/olpc/olpc-xo175-ec.c @@ -736,6 +736,12 @@ static const struct of_device_id olpc_xo175_ec_of_match[] = { }; MODULE_DEVICE_TABLE(of, olpc_xo175_ec_of_match); +static const struct spi_device_id olpc_xo175_ec_id_table[] = { + { "xo1.75-ec", 0 }, + {} +}; +MODULE_DEVICE_TABLE(spi, olpc_xo175_ec_id_table); + static struct spi_driver olpc_xo175_ec_spi_driver = { .driver = { .name = "olpc-xo175-ec", From 66013e8ec6850f9c62df6aea555fe7668e84dc3c Mon Sep 17 00:00:00 2001 From: Rajneesh Bhardwaj Date: Fri, 14 Jun 2019 13:39:40 +0530 Subject: [PATCH 384/823] platform/x86: intel_pmc_core: Add ICL-NNPI support to PMC Core Ice Lake Neural Network Processor for deep learning inference a.k.a. ICL-NNPI can re-use Ice Lake Mobile regmap to enable Intel PMC Core driver on it. Cc: Darren Hart Cc: Andy Shevchenko Cc: platform-driver-x86@vger.kernel.org Link: https://lkml.org/lkml/2019/6/5/1034 Signed-off-by: Rajneesh Bhardwaj Signed-off-by: Andy Shevchenko --- drivers/platform/x86/intel_pmc_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c index 235c0b89f824..c510d0d72475 100644 --- a/drivers/platform/x86/intel_pmc_core.c +++ b/drivers/platform/x86/intel_pmc_core.c @@ -812,6 +812,7 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = { INTEL_CPU_FAM6(KABYLAKE_DESKTOP, spt_reg_map), INTEL_CPU_FAM6(CANNONLAKE_MOBILE, cnp_reg_map), INTEL_CPU_FAM6(ICELAKE_MOBILE, icl_reg_map), + INTEL_CPU_FAM6(ICELAKE_NNPI, icl_reg_map), {} }; From c8ec4632c6ac9cda0e8c3d51aa41eeab66585bd5 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 22 Jul 2019 21:43:00 -0700 Subject: [PATCH 385/823] ife: error out when nla attributes are empty act_ife at least requires TCA_IFE_PARMS, so we have to bail out when there is no attribute passed in. Reported-by: syzbot+fbb5b288c9cb6a2eeac4@syzkaller.appspotmail.com Fixes: ef6980b6becb ("introduce IFE action") Cc: Jamal Hadi Salim Cc: Jiri Pirko Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/act_ife.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 41d5398dd2f2..3578196d1600 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -481,6 +481,11 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, int ret = 0; int err; + if (!nla) { + NL_SET_ERR_MSG_MOD(extack, "IFE requires attributes to be passed"); + return -EINVAL; + } + err = nla_parse_nested_deprecated(tb, TCA_IFE_MAX, nla, ife_policy, NULL); if (err < 0) From f06d0ca45827a5790d7508de4759aed976933d4d Mon Sep 17 00:00:00 2001 From: Yamin Friedman Date: Tue, 23 Jul 2019 10:22:47 +0300 Subject: [PATCH 386/823] linux/dim: Fix overflow in dim calculation While using net_dim, a dim_sample was used without ever initializing the comps value. Added use of DIV_ROUND_DOWN_ULL() to prevent potential overflow, it should not be a problem to save the final result in an int because after the division by epms the value should not be larger than a few thousand. [ 1040.127124] UBSAN: Undefined behaviour in lib/dim/dim.c:78:23 [ 1040.130118] signed integer overflow: [ 1040.131643] 134718714 * 100 cannot be represented in type 'int' Fixes: 398c2b05bbee ("linux/dim: Add completions count to dim_sample") Signed-off-by: Yamin Friedman Signed-off-by: Leon Romanovsky Acked-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcmsysport.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c | 4 ++-- lib/dim/dim.c | 4 ++-- 5 files changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index b9c5cea8db16..9483553ce444 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -992,7 +992,7 @@ static int bcm_sysport_poll(struct napi_struct *napi, int budget) { struct bcm_sysport_priv *priv = container_of(napi, struct bcm_sysport_priv, napi); - struct dim_sample dim_sample; + struct dim_sample dim_sample = {}; unsigned int work_done = 0; work_done = bcm_sysport_desc_rx(priv, budget); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 7134d2c3eb1c..7070349915bc 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2136,7 +2136,7 @@ static int bnxt_poll(struct napi_struct *napi, int budget) } } if (bp->flags & BNXT_FLAG_DIM) { - struct dim_sample dim_sample; + struct dim_sample dim_sample = {}; dim_update_sample(cpr->event_ctr, cpr->rx_packets, diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index a2b57807453b..d3a0b614dbfa 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1895,7 +1895,7 @@ static int bcmgenet_rx_poll(struct napi_struct *napi, int budget) { struct bcmgenet_rx_ring *ring = container_of(napi, struct bcmgenet_rx_ring, napi); - struct dim_sample dim_sample; + struct dim_sample dim_sample = {}; unsigned int work_done; work_done = bcmgenet_desc_rx(ring, budget); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index c50b6f0769c8..49b06b256c92 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -49,7 +49,7 @@ static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c) static void mlx5e_handle_tx_dim(struct mlx5e_txqsq *sq) { struct mlx5e_sq_stats *stats = sq->stats; - struct dim_sample dim_sample; + struct dim_sample dim_sample = {}; if (unlikely(!test_bit(MLX5E_SQ_STATE_AM, &sq->state))) return; @@ -61,7 +61,7 @@ static void mlx5e_handle_tx_dim(struct mlx5e_txqsq *sq) static void mlx5e_handle_rx_dim(struct mlx5e_rq *rq) { struct mlx5e_rq_stats *stats = rq->stats; - struct dim_sample dim_sample; + struct dim_sample dim_sample = {}; if (unlikely(!test_bit(MLX5E_RQ_STATE_AM, &rq->state))) return; diff --git a/lib/dim/dim.c b/lib/dim/dim.c index 439d641ec796..38045d6d0538 100644 --- a/lib/dim/dim.c +++ b/lib/dim/dim.c @@ -74,8 +74,8 @@ void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, delta_us); curr_stats->cpms = DIV_ROUND_UP(ncomps * USEC_PER_MSEC, delta_us); if (curr_stats->epms != 0) - curr_stats->cpe_ratio = - (curr_stats->cpms * 100) / curr_stats->epms; + curr_stats->cpe_ratio = DIV_ROUND_DOWN_ULL( + curr_stats->cpms * 100, curr_stats->epms); else curr_stats->cpe_ratio = 0; From f8be17b81d44aed1f9ea68c3fc70f501c9616e2d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 23 Jul 2019 10:22:48 +0300 Subject: [PATCH 387/823] lib/dim: Fix -Wunused-const-variable warnings DIM causes to the following warnings during kernel compilation which indicates that tx_profile and rx_profile are supposed to be declared in *.c and not in *.h files. In file included from ./include/rdma/ib_verbs.h:64, from ./include/linux/mlx5/device.h:37, from ./include/linux/mlx5/driver.h:51, from ./include/linux/mlx5/vport.h:36, from drivers/infiniband/hw/mlx5/ib_virt.c:34: ./include/linux/dim.h:326:1: warning: _tx_profile_ defined but not used [-Wunused-const-variable=] 326 | tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { | ^~~~~~~~~~ ./include/linux/dim.h:320:1: warning: _rx_profile_ defined but not used [-Wunused-const-variable=] 320 | rx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { | ^~~~~~~~~~ Fixes: 4f75da3666c0 ("linux/dim: Move implementation to .c files") Signed-off-by: Leon Romanovsky Reviewed-by: Bart Van Assche Acked-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/dim.h | 56 --------------------------------------------- lib/dim/net_dim.c | 56 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+), 56 deletions(-) diff --git a/include/linux/dim.h b/include/linux/dim.h index d3a0fbfff2bb..9fa4b3f88c39 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -272,62 +272,6 @@ dim_update_sample_with_comps(u16 event_ctr, u64 packets, u64 bytes, u64 comps, /* Net DIM */ -/* - * Net DIM profiles: - * There are different set of profiles for each CQ period mode. - * There are different set of profiles for RX/TX CQs. - * Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES - */ -#define NET_DIM_PARAMS_NUM_PROFILES 5 -#define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256 -#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128 -#define NET_DIM_DEF_PROFILE_CQE 1 -#define NET_DIM_DEF_PROFILE_EQE 1 - -#define NET_DIM_RX_EQE_PROFILES { \ - {1, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {8, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {64, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {128, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ -} - -#define NET_DIM_RX_CQE_PROFILES { \ - {2, 256}, \ - {8, 128}, \ - {16, 64}, \ - {32, 64}, \ - {64, 64} \ -} - -#define NET_DIM_TX_EQE_PROFILES { \ - {1, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {8, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {32, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {64, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE} \ -} - -#define NET_DIM_TX_CQE_PROFILES { \ - {5, 128}, \ - {8, 64}, \ - {16, 32}, \ - {32, 32}, \ - {64, 32} \ -} - -static const struct dim_cq_moder -rx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { - NET_DIM_RX_EQE_PROFILES, - NET_DIM_RX_CQE_PROFILES, -}; - -static const struct dim_cq_moder -tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { - NET_DIM_TX_EQE_PROFILES, - NET_DIM_TX_CQE_PROFILES, -}; - /** * net_dim_get_rx_moderation - provide a CQ moderation object for the given RX profile * @cq_period_mode: CQ period mode diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index 5bcc902c5388..a4db51c21266 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -5,6 +5,62 @@ #include +/* + * Net DIM profiles: + * There are different set of profiles for each CQ period mode. + * There are different set of profiles for RX/TX CQs. + * Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES + */ +#define NET_DIM_PARAMS_NUM_PROFILES 5 +#define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256 +#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128 +#define NET_DIM_DEF_PROFILE_CQE 1 +#define NET_DIM_DEF_PROFILE_EQE 1 + +#define NET_DIM_RX_EQE_PROFILES { \ + {1, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {8, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {64, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {128, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ +} + +#define NET_DIM_RX_CQE_PROFILES { \ + {2, 256}, \ + {8, 128}, \ + {16, 64}, \ + {32, 64}, \ + {64, 64} \ +} + +#define NET_DIM_TX_EQE_PROFILES { \ + {1, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {8, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {32, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {64, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE} \ +} + +#define NET_DIM_TX_CQE_PROFILES { \ + {5, 128}, \ + {8, 64}, \ + {16, 32}, \ + {32, 32}, \ + {64, 32} \ +} + +static const struct dim_cq_moder +rx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { + NET_DIM_RX_EQE_PROFILES, + NET_DIM_RX_CQE_PROFILES, +}; + +static const struct dim_cq_moder +tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { + NET_DIM_TX_EQE_PROFILES, + NET_DIM_TX_CQE_PROFILES, +}; + struct dim_cq_moder net_dim_get_rx_moderation(u8 cq_period_mode, int ix) { From 4b663366246be1d1d4b1b8b01245b2e88ad9e706 Mon Sep 17 00:00:00 2001 From: Alexis Bauvin Date: Tue, 23 Jul 2019 16:23:01 +0200 Subject: [PATCH 388/823] tun: mark small packets as owned by the tap sock - v1 -> v2: Move skb_set_owner_w to __tun_build_skb to reduce patch size Small packets going out of a tap device go through an optimized code path that uses build_skb() rather than sock_alloc_send_pskb(). The latter calls skb_set_owner_w(), but the small packet code path does not. The net effect is that small packets are not owned by the userland application's socket (e.g. QEMU), while large packets are. This can be seen with a TCP session, where packets are not owned when the window size is small enough (around PAGE_SIZE), while they are once the window grows (note that this requires the host to support virtio tso for the guest to offload segmentation). All this leads to inconsistent behaviour in the kernel, especially on netfilter modules that uses sk->socket (e.g. xt_owner). Fixes: 66ccbc9c87c2 ("tap: use build_skb() for small packet") Signed-off-by: Alexis Bauvin Acked-by: Jason Wang Signed-off-by: David S. Miller --- drivers/net/tun.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 3d443597bd04..db16d7a13e00 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1599,7 +1599,8 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile, return true; } -static struct sk_buff *__tun_build_skb(struct page_frag *alloc_frag, char *buf, +static struct sk_buff *__tun_build_skb(struct tun_file *tfile, + struct page_frag *alloc_frag, char *buf, int buflen, int len, int pad) { struct sk_buff *skb = build_skb(buf, buflen); @@ -1609,6 +1610,7 @@ static struct sk_buff *__tun_build_skb(struct page_frag *alloc_frag, char *buf, skb_reserve(skb, pad); skb_put(skb, len); + skb_set_owner_w(skb, tfile->socket.sk); get_page(alloc_frag->page); alloc_frag->offset += buflen; @@ -1686,7 +1688,8 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, */ if (hdr->gso_type || !xdp_prog) { *skb_xdp = 1; - return __tun_build_skb(alloc_frag, buf, buflen, len, pad); + return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, + pad); } *skb_xdp = 0; @@ -1723,7 +1726,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, rcu_read_unlock(); local_bh_enable(); - return __tun_build_skb(alloc_frag, buf, buflen, len, pad); + return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad); err_xdp: put_page(alloc_frag->page); From 9891d06836e67324c9e9c4675ed90fc8b8110034 Mon Sep 17 00:00:00 2001 From: Navid Emamdoost Date: Tue, 23 Jul 2019 17:04:30 -0500 Subject: [PATCH 389/823] st21nfca_connectivity_event_received: null check the allocation devm_kzalloc may fail and return null. So the null check is needed. Signed-off-by: Navid Emamdoost Signed-off-by: David S. Miller --- drivers/nfc/st21nfca/se.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/nfc/st21nfca/se.c b/drivers/nfc/st21nfca/se.c index 06fc542fd198..6586378cacb0 100644 --- a/drivers/nfc/st21nfca/se.c +++ b/drivers/nfc/st21nfca/se.c @@ -317,6 +317,8 @@ int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host, transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev, skb->len - 2, GFP_KERNEL); + if (!transaction) + return -ENOMEM; transaction->aid_len = skb->data[1]; memcpy(transaction->aid, &skb->data[2], From 3008e06fdf0973770370f97d5f1fba3701d8281d Mon Sep 17 00:00:00 2001 From: Navid Emamdoost Date: Tue, 23 Jul 2019 17:11:51 -0500 Subject: [PATCH 390/823] st_nci_hci_connectivity_event_received: null check the allocation devm_kzalloc may fail and return NULL. So the null check is needed. Signed-off-by: Navid Emamdoost Signed-off-by: David S. Miller --- drivers/nfc/st-nci/se.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index c3e10b6ab3a4..f25f1ec5f9e9 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -333,6 +333,8 @@ static int st_nci_hci_connectivity_event_received(struct nci_dev *ndev, transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev, skb->len - 2, GFP_KERNEL); + if (!transaction) + return -ENOMEM; transaction->aid_len = skb->data[1]; memcpy(transaction->aid, &skb->data[2], transaction->aid_len); From 83fbae60fd3885c6e8da5863582d0317731c5528 Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Wed, 24 Jul 2019 11:35:01 +1200 Subject: [PATCH 391/823] fsl/fman: Remove comment referring to non-existent function fm_set_max_frm() existed in the Freescale SDK as a callback for an early_param. When this code was ported to the upstream kernel the early_param was converted to a module_param making the reference to the function incorrect. The rest of the comment already does a good job of explaining the parameter so removing the reference to the non-existent function seems like the best thing to do. Signed-off-by: Chris Packham Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fman/fman.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index e80fedb27cee..210749bf1eac 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -2439,9 +2439,6 @@ MODULE_PARM_DESC(fsl_fm_rx_extra_headroom, "Extra headroom for Rx buffers"); * buffers when not using jumbo frames. * Must be large enough to accommodate the network MTU, but small enough * to avoid wasting skb memory. - * - * Could be overridden once, at boot-time, via the - * fm_set_max_frm() callback. */ static int fsl_fm_max_frm = FSL_FM_MAX_FRAME_SIZE; module_param(fsl_fm_max_frm, int, 0); From 2bcbeaefde2f0384d6ad351c151b1a9fe7791a0a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 24 Jul 2019 08:52:52 +0200 Subject: [PATCH 392/823] mm/hmm: always return EBUSY for invalid ranges in hmm_range_{fault,snapshot} We should not have two different error codes for the same condition. EAGAIN must be reserved for the FAULT_FLAG_ALLOW_RETRY retry case and signals to the caller that the mmap_sem has been unlocked. Use EBUSY for the !valid case so that callers can get the locking right. Link: https://lore.kernel.org/r/20190724065258.16603-2-hch@lst.de Tested-by: Ralph Campbell Signed-off-by: Christoph Hellwig Reviewed-by: Ralph Campbell Reviewed-by: Jason Gunthorpe Reviewed-by: Felix Kuehling [jgg: elaborated commit message] Signed-off-by: Jason Gunthorpe --- Documentation/vm/hmm.rst | 2 +- mm/hmm.c | 10 ++++------ 2 files changed, 5 insertions(+), 7 deletions(-) diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst index 7d90964abbb0..710ce1c701bf 100644 --- a/Documentation/vm/hmm.rst +++ b/Documentation/vm/hmm.rst @@ -237,7 +237,7 @@ The usage pattern is:: ret = hmm_range_snapshot(&range); if (ret) { up_read(&mm->mmap_sem); - if (ret == -EAGAIN) { + if (ret == -EBUSY) { /* * No need to check hmm_range_wait_until_valid() return value * on retry we will get proper error with hmm_range_snapshot() diff --git a/mm/hmm.c b/mm/hmm.c index e1eedef129cf..16b6731a34db 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -946,7 +946,7 @@ EXPORT_SYMBOL(hmm_range_unregister); * @range: range * Return: -EINVAL if invalid argument, -ENOMEM out of memory, -EPERM invalid * permission (for instance asking for write and range is read only), - * -EAGAIN if you need to retry, -EFAULT invalid (ie either no valid + * -EBUSY if you need to retry, -EFAULT invalid (ie either no valid * vma or it is illegal to access that range), number of valid pages * in range->pfns[] (from range start address). * @@ -967,7 +967,7 @@ long hmm_range_snapshot(struct hmm_range *range) do { /* If range is no longer valid force retry. */ if (!range->valid) - return -EAGAIN; + return -EBUSY; vma = find_vma(hmm->mm, start); if (vma == NULL || (vma->vm_flags & device_vma)) @@ -1062,10 +1062,8 @@ long hmm_range_fault(struct hmm_range *range, bool block) do { /* If range is no longer valid force retry. */ - if (!range->valid) { - up_read(&hmm->mm->mmap_sem); - return -EAGAIN; - } + if (!range->valid) + return -EBUSY; vma = find_vma(hmm->mm, start); if (vma == NULL || (vma->vm_flags & device_vma)) From 02712bc3250849c1cf99d626aea98f610e695f34 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 24 Jul 2019 08:52:53 +0200 Subject: [PATCH 393/823] mm/hmm: move hmm_vma_range_done and hmm_vma_fault to nouveau These two functions are marked as a legacy APIs to get rid of, but seem to suit the current nouveau flow. Move it to the only user in preparation for fixing a locking bug involving caller and callee. All comments referring to the old API have been removed as this now is a driver private helper. Link: https://lore.kernel.org/r/20190724065258.16603-3-hch@lst.de Tested-by: Ralph Campbell Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/gpu/drm/nouveau/nouveau_svm.c | 46 ++++++++++++++++++++++- include/linux/hmm.h | 54 --------------------------- 2 files changed, 44 insertions(+), 56 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 8c92374afcf2..6c1b04de0db8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -475,6 +475,48 @@ nouveau_svm_fault_cache(struct nouveau_svm *svm, fault->inst, fault->addr, fault->access); } +static inline bool +nouveau_range_done(struct hmm_range *range) +{ + bool ret = hmm_range_valid(range); + + hmm_range_unregister(range); + return ret; +} + +static int +nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range, + bool block) +{ + long ret; + + range->default_flags = 0; + range->pfn_flags_mask = -1UL; + + ret = hmm_range_register(range, mirror, + range->start, range->end, + PAGE_SHIFT); + if (ret) + return (int)ret; + + if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) { + up_read(&range->vma->vm_mm->mmap_sem); + return -EAGAIN; + } + + ret = hmm_range_fault(range, block); + if (ret <= 0) { + if (ret == -EBUSY || !ret) { + up_read(&range->vma->vm_mm->mmap_sem); + ret = -EBUSY; + } else if (ret == -EAGAIN) + ret = -EBUSY; + hmm_range_unregister(range); + return ret; + } + return 0; +} + static int nouveau_svm_fault(struct nvif_notify *notify) { @@ -649,10 +691,10 @@ nouveau_svm_fault(struct nvif_notify *notify) range.values = nouveau_svm_pfn_values; range.pfn_shift = NVIF_VMM_PFNMAP_V0_ADDR_SHIFT; again: - ret = hmm_vma_fault(&svmm->mirror, &range, true); + ret = nouveau_range_fault(&svmm->mirror, &range, true); if (ret == 0) { mutex_lock(&svmm->mutex); - if (!hmm_vma_range_done(&range)) { + if (!nouveau_range_done(&range)) { mutex_unlock(&svmm->mutex); goto again; } diff --git a/include/linux/hmm.h b/include/linux/hmm.h index b8a08b2a10ca..7ef56dc18050 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -484,60 +484,6 @@ long hmm_range_dma_unmap(struct hmm_range *range, */ #define HMM_RANGE_DEFAULT_TIMEOUT 1000 -/* This is a temporary helper to avoid merge conflict between trees. */ -static inline bool hmm_vma_range_done(struct hmm_range *range) -{ - bool ret = hmm_range_valid(range); - - hmm_range_unregister(range); - return ret; -} - -/* This is a temporary helper to avoid merge conflict between trees. */ -static inline int hmm_vma_fault(struct hmm_mirror *mirror, - struct hmm_range *range, bool block) -{ - long ret; - - /* - * With the old API the driver must set each individual entries with - * the requested flags (valid, write, ...). So here we set the mask to - * keep intact the entries provided by the driver and zero out the - * default_flags. - */ - range->default_flags = 0; - range->pfn_flags_mask = -1UL; - - ret = hmm_range_register(range, mirror, - range->start, range->end, - PAGE_SHIFT); - if (ret) - return (int)ret; - - if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) { - /* - * The mmap_sem was taken by driver we release it here and - * returns -EAGAIN which correspond to mmap_sem have been - * drop in the old API. - */ - up_read(&range->vma->vm_mm->mmap_sem); - return -EAGAIN; - } - - ret = hmm_range_fault(range, block); - if (ret <= 0) { - if (ret == -EBUSY || !ret) { - /* Same as above, drop mmap_sem to match old API. */ - up_read(&range->vma->vm_mm->mmap_sem); - ret = -EBUSY; - } else if (ret == -EAGAIN) - ret = -EBUSY; - hmm_range_unregister(range); - return ret; - } - return 0; -} - /* Below are for HMM internal use only! Not to be used by device driver! */ static inline void hmm_mm_init(struct mm_struct *mm) { From 5fbcf5015db8e9f04a9da6d40322622fa229da54 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 24 Jul 2019 08:52:54 +0200 Subject: [PATCH 394/823] nouveau: remove the block parameter to nouveau_range_fault The parameter is always false, so remove it as well as the -EAGAIN handling that can only happen for the non-blocking case. Link: https://lore.kernel.org/r/20190724065258.16603-4-hch@lst.de Tested-by: Ralph Campbell Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/gpu/drm/nouveau/nouveau_svm.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 6c1b04de0db8..e3097492b4ad 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -485,8 +485,7 @@ nouveau_range_done(struct hmm_range *range) } static int -nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range, - bool block) +nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range) { long ret; @@ -504,13 +503,12 @@ nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range, return -EAGAIN; } - ret = hmm_range_fault(range, block); + ret = hmm_range_fault(range, true); if (ret <= 0) { if (ret == -EBUSY || !ret) { up_read(&range->vma->vm_mm->mmap_sem); ret = -EBUSY; - } else if (ret == -EAGAIN) - ret = -EBUSY; + } hmm_range_unregister(range); return ret; } @@ -691,7 +689,7 @@ nouveau_svm_fault(struct nvif_notify *notify) range.values = nouveau_svm_pfn_values; range.pfn_shift = NVIF_VMM_PFNMAP_V0_ADDR_SHIFT; again: - ret = nouveau_range_fault(&svmm->mirror, &range, true); + ret = nouveau_range_fault(&svmm->mirror, &range); if (ret == 0) { mutex_lock(&svmm->mutex); if (!nouveau_range_done(&range)) { From de4ee728465f7c0c29241550e083139b2ce9159c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 24 Jul 2019 08:52:55 +0200 Subject: [PATCH 395/823] nouveau: unlock mmap_sem on all errors from nouveau_range_fault Currently nouveau_svm_fault expects nouveau_range_fault to never unlock mmap_sem, but the latter unlocks it for a random selection of error codes. Fix this up by always unlocking mmap_sem for non-zero return values in nouveau_range_fault, and only unlocking it in the caller for successful returns. Link: https://lore.kernel.org/r/20190724065258.16603-5-hch@lst.de Tested-by: Ralph Campbell Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/gpu/drm/nouveau/nouveau_svm.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index e3097492b4ad..a835cebb6d90 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -495,8 +495,10 @@ nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range) ret = hmm_range_register(range, mirror, range->start, range->end, PAGE_SHIFT); - if (ret) + if (ret) { + up_read(&range->vma->vm_mm->mmap_sem); return (int)ret; + } if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) { up_read(&range->vma->vm_mm->mmap_sem); @@ -505,10 +507,9 @@ nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range) ret = hmm_range_fault(range, true); if (ret <= 0) { - if (ret == -EBUSY || !ret) { - up_read(&range->vma->vm_mm->mmap_sem); + if (ret == 0) ret = -EBUSY; - } + up_read(&range->vma->vm_mm->mmap_sem); hmm_range_unregister(range); return ret; } @@ -706,8 +707,8 @@ again: NULL); svmm->vmm->vmm.object.client->super = false; mutex_unlock(&svmm->mutex); + up_read(&svmm->mm->mmap_sem); } - up_read(&svmm->mm->mmap_sem); /* Cancel any faults in the window whose pages didn't manage * to keep their valid bit, or stay writeable when required. From 08aa5e7da6bce1a1963f63cf32c2e7ad434ad578 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Tue, 9 Jul 2019 05:37:12 +0300 Subject: [PATCH 396/823] net/mlx5: Use reversed order when unregister devices When lag is active, which is controlled by the bonded mlx5e netdev, mlx5 interface unregestering must happen in the reverse order where rdma is unregistered (unloaded) first, to guarantee all references to the lag context in hardware is removed, then remove mlx5e netdev interface which will cleanup the lag context from hardware. Without this fix during destroy of LAG interface, we observed following errors: * mlx5_cmd_check:752:(pid 12556): DESTROY_LAG(0x843) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0xe4ac33) * mlx5_cmd_check:752:(pid 12556): DESTROY_LAG(0x843) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0xa5aee8). Fixes: a31208b1e11d ("net/mlx5_core: New init and exit flow for mlx5_core") Reviewed-by: Parav Pandit Reviewed-by: Leon Romanovsky Signed-off-by: Mark Zhang Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 5bb6a26ea267..50862275544e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -213,7 +213,7 @@ void mlx5_unregister_device(struct mlx5_core_dev *dev) struct mlx5_interface *intf; mutex_lock(&mlx5_intf_mutex); - list_for_each_entry(intf, &intf_list, list) + list_for_each_entry_reverse(intf, &intf_list, list) mlx5_remove_device(intf, priv); list_del(&priv->dev_list); mutex_unlock(&mlx5_intf_mutex); From 987f6c69dd923069d443f6a37225f5b1630a30f2 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Sun, 14 Jul 2019 11:33:07 +0300 Subject: [PATCH 397/823] net/mlx5: Add missing RDMA_RX capabilities New flow table type RDMA_RX was added but the MLX5_CAP_FLOW_TABLE_TYPE didn't handle this new flow table type. This means that MLX5_CAP_FLOW_TABLE_TYPE returns an empty capability to this flow table type. Update both the macro and the maximum supported flow table type to RDMA_RX. Fixes: d83eb50e29de ("net/mlx5: Add support in RDMA RX steering") Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index c48c382f926f..c1252d6be0ef 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -68,7 +68,7 @@ enum fs_flow_table_type { FS_FT_SNIFFER_RX = 0X5, FS_FT_SNIFFER_TX = 0X6, FS_FT_RDMA_RX = 0X7, - FS_FT_MAX_TYPE = FS_FT_SNIFFER_TX, + FS_FT_MAX_TYPE = FS_FT_RDMA_RX, }; enum fs_flow_table_op_mod { @@ -275,7 +275,8 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev); (type == FS_FT_FDB) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) : \ (type == FS_FT_SNIFFER_RX) ? MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) : \ (type == FS_FT_SNIFFER_TX) ? MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) : \ - (BUILD_BUG_ON_ZERO(FS_FT_SNIFFER_TX != FS_FT_MAX_TYPE))\ + (type == FS_FT_RDMA_RX) ? MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) : \ + (BUILD_BUG_ON_ZERO(FS_FT_RDMA_RX != FS_FT_MAX_TYPE))\ ) #endif From 7a32f2962c56d9d8a836b4469855caeee8766bd4 Mon Sep 17 00:00:00 2001 From: Edward Srouji Date: Tue, 23 Jul 2019 10:12:55 +0300 Subject: [PATCH 398/823] net/mlx5: Fix modify_cq_in alignment Fix modify_cq_in alignment to match the device specification. After this fix the 'cq_umem_valid' field will be in the right offset. Cc: # 4.19 Fixes: bd37197554eb ("net/mlx5: Update mlx5_ifc with DEVX UID bits") Signed-off-by: Edward Srouji Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b3d5752657d9..ec571fd7fcf8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5975,10 +5975,12 @@ struct mlx5_ifc_modify_cq_in_bits { struct mlx5_ifc_cqc_bits cq_context; - u8 reserved_at_280[0x40]; + u8 reserved_at_280[0x60]; u8 cq_umem_valid[0x1]; - u8 reserved_at_2c1[0x5bf]; + u8 reserved_at_2e1[0x1f]; + + u8 reserved_at_300[0x580]; u8 pas[0][0x40]; }; From 694826e366349d5b27599f591d3bd3a53512306e Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Sun, 14 Jul 2019 11:43:43 +0300 Subject: [PATCH 399/823] net/mlx5e: Fix wrong max num channels indication No XSK support in the enhanced IPoIB driver and representors. Add a profile property to specify this, and enhance the logic that calculates the max number of channels to take it into account. Fixes: db05815b36cb ("net/mlx5e: Add XSK zero-copy support") Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 12 ++----- .../ethernet/mellanox/mlx5/core/en/params.h | 5 +-- .../ethernet/mellanox/mlx5/core/en_ethtool.c | 2 +- .../mellanox/mlx5/core/en_fs_ethtool.c | 3 +- .../net/ethernet/mellanox/mlx5/core/en_main.c | 36 +++++++++---------- .../net/ethernet/mellanox/mlx5/core/en_rep.c | 2 ++ .../ethernet/mellanox/mlx5/core/en_stats.c | 8 ++--- .../ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 7 ++-- .../mellanox/mlx5/core/ipoib/ipoib_vlan.c | 1 + 9 files changed, 35 insertions(+), 41 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 79d93d6c7d7a..ce1be2a84231 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -159,7 +159,7 @@ do { \ enum mlx5e_rq_group { MLX5E_RQ_GROUP_REGULAR, MLX5E_RQ_GROUP_XSK, - MLX5E_NUM_RQ_GROUPS /* Keep last. */ +#define MLX5E_NUM_RQ_GROUPS(g) (1 + MLX5E_RQ_GROUP_##g) }; static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size) @@ -182,14 +182,6 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) min_t(int, mlx5_comp_vectors_count(mdev), MLX5E_MAX_NUM_CHANNELS); } -/* Use this function to get max num channels after netdev was created */ -static inline int mlx5e_get_netdev_max_channels(struct net_device *netdev) -{ - return min_t(unsigned int, - netdev->num_rx_queues / MLX5E_NUM_RQ_GROUPS, - netdev->num_tx_queues); -} - struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_eth_seg eth; @@ -830,6 +822,7 @@ struct mlx5e_priv { struct net_device *netdev; struct mlx5e_stats stats; struct mlx5e_channel_stats channel_stats[MLX5E_MAX_NUM_CHANNELS]; + u16 max_nch; u8 max_opened_tc; struct hwtstamp_config tstamp; u16 q_counter; @@ -871,6 +864,7 @@ struct mlx5e_profile { mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe; } rx_handlers; int max_tc; + u8 rq_groups; }; void mlx5e_build_ptys2ethtool_map(void); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index bd882b5ee9a7..3a615d663d84 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -66,9 +66,10 @@ static inline void mlx5e_qid_get_ch_and_group(struct mlx5e_params *params, *group = qid / nch; } -static inline bool mlx5e_qid_validate(struct mlx5e_params *params, u64 qid) +static inline bool mlx5e_qid_validate(const struct mlx5e_profile *profile, + struct mlx5e_params *params, u64 qid) { - return qid < params->num_channels * MLX5E_NUM_RQ_GROUPS; + return qid < params->num_channels * profile->rq_groups; } /* Parameter calculations */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 126ec4181286..ed25757ac5bd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -391,7 +391,7 @@ void mlx5e_ethtool_get_channels(struct mlx5e_priv *priv, { mutex_lock(&priv->state_lock); - ch->max_combined = mlx5e_get_netdev_max_channels(priv->netdev); + ch->max_combined = priv->max_nch; ch->combined_count = priv->channels.params.num_channels; if (priv->xsk.refcnt) { /* The upper half are XSK queues. */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index ea3a490b569a..94304abc49e9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -611,7 +611,8 @@ static int validate_flow(struct mlx5e_priv *priv, return -ENOSPC; if (fs->ring_cookie != RX_CLS_FLOW_DISC) - if (!mlx5e_qid_validate(&priv->channels.params, fs->ring_cookie)) + if (!mlx5e_qid_validate(priv->profile, &priv->channels.params, + fs->ring_cookie)) return -EINVAL; switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 47eea6b3a1c3..570c42b7eeea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1677,10 +1677,10 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c, struct mlx5e_channel_param *cparam) { struct mlx5e_priv *priv = c->priv; - int err, tc, max_nch = mlx5e_get_netdev_max_channels(priv->netdev); + int err, tc; for (tc = 0; tc < params->num_tc; tc++) { - int txq_ix = c->ix + tc * max_nch; + int txq_ix = c->ix + tc * priv->max_nch; err = mlx5e_open_txqsq(c, c->priv->tisn[tc], txq_ix, params, &cparam->sq, &c->sq[tc], tc); @@ -2438,11 +2438,10 @@ int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv) int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs) { - const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); int err; int ix; - for (ix = 0; ix < max_nch; ix++) { + for (ix = 0; ix < priv->max_nch; ix++) { err = mlx5e_create_rqt(priv, 1 /*size */, &tirs[ix].rqt); if (unlikely(err)) goto err_destroy_rqts; @@ -2460,10 +2459,9 @@ err_destroy_rqts: void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs) { - const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); int i; - for (i = 0; i < max_nch; i++) + for (i = 0; i < priv->max_nch; i++) mlx5e_destroy_rqt(priv, &tirs[i].rqt); } @@ -2557,7 +2555,7 @@ static void mlx5e_redirect_rqts(struct mlx5e_priv *priv, mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp); } - for (ix = 0; ix < mlx5e_get_netdev_max_channels(priv->netdev); ix++) { + for (ix = 0; ix < priv->max_nch; ix++) { struct mlx5e_redirect_rqt_param direct_rrp = { .is_rss = false, { @@ -2758,7 +2756,7 @@ static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv) goto free_in; } - for (ix = 0; ix < mlx5e_get_netdev_max_channels(priv->netdev); ix++) { + for (ix = 0; ix < priv->max_nch; ix++) { err = mlx5_core_modify_tir(mdev, priv->direct_tir[ix].tirn, in, inlen); if (err) @@ -2858,12 +2856,11 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev) static void mlx5e_build_tc2txq_maps(struct mlx5e_priv *priv) { - int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); int i, tc; - for (i = 0; i < max_nch; i++) + for (i = 0; i < priv->max_nch; i++) for (tc = 0; tc < priv->profile->max_tc; tc++) - priv->channel_tc2txq[i][tc] = i + tc * max_nch; + priv->channel_tc2txq[i][tc] = i + tc * priv->max_nch; } static void mlx5e_build_tx2sq_maps(struct mlx5e_priv *priv) @@ -2884,7 +2881,7 @@ static void mlx5e_build_tx2sq_maps(struct mlx5e_priv *priv) void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) { int num_txqs = priv->channels.num * priv->channels.params.num_tc; - int num_rxqs = priv->channels.num * MLX5E_NUM_RQ_GROUPS; + int num_rxqs = priv->channels.num * priv->profile->rq_groups; struct net_device *netdev = priv->netdev; mlx5e_netdev_set_tcs(netdev); @@ -3306,7 +3303,6 @@ err_destroy_inner_tirs: int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs) { - const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); struct mlx5e_tir *tir; void *tirc; int inlen; @@ -3319,7 +3315,7 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs) if (!in) return -ENOMEM; - for (ix = 0; ix < max_nch; ix++) { + for (ix = 0; ix < priv->max_nch; ix++) { memset(in, 0, inlen); tir = &tirs[ix]; tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); @@ -3358,10 +3354,9 @@ void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc) void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs) { - const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); int i; - for (i = 0; i < max_nch; i++) + for (i = 0; i < priv->max_nch; i++) mlx5e_destroy_tir(priv->mdev, &tirs[i]); } @@ -3487,7 +3482,7 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s) { int i; - for (i = 0; i < mlx5e_get_netdev_max_channels(priv->netdev); i++) { + for (i = 0; i < priv->max_nch; i++) { struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i]; struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq; struct mlx5e_rq_stats *rq_stats = &channel_stats->rq; @@ -4960,8 +4955,7 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, return err; mlx5e_build_nic_params(mdev, &priv->xsk, rss, &priv->channels.params, - mlx5e_get_netdev_max_channels(netdev), - netdev->mtu); + priv->max_nch, netdev->mtu); mlx5e_timestamp_init(priv); @@ -5164,6 +5158,7 @@ static const struct mlx5e_profile mlx5e_nic_profile = { .rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe, .rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq, .max_tc = MLX5E_MAX_NUM_TC, + .rq_groups = MLX5E_NUM_RQ_GROUPS(XSK), }; /* mlx5e generic netdev management API (move to en_common.c) */ @@ -5181,6 +5176,7 @@ int mlx5e_netdev_init(struct net_device *netdev, priv->profile = profile; priv->ppriv = ppriv; priv->msglevel = MLX5E_MSG_LEVEL; + priv->max_nch = netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1); priv->max_opened_tc = 1; mutex_init(&priv->state_lock); @@ -5218,7 +5214,7 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev, netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv), nch * profile->max_tc, - nch * MLX5E_NUM_RQ_GROUPS); + nch * profile->rq_groups); if (!netdev) { mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n"); return NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 7245d287633d..731819a26a0c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1702,6 +1702,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = { .rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe_rep, .rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq, .max_tc = 1, + .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR), }; static const struct mlx5e_profile mlx5e_uplink_rep_profile = { @@ -1719,6 +1720,7 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = { .rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe_rep, .rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq, .max_tc = MLX5E_MAX_NUM_TC, + .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR), }; static bool diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 539b4d3656da..57f9f346d213 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -172,7 +172,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) memset(s, 0, sizeof(*s)); - for (i = 0; i < mlx5e_get_netdev_max_channels(priv->netdev); i++) { + for (i = 0; i < priv->max_nch; i++) { struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i]; struct mlx5e_xdpsq_stats *xdpsq_red_stats = &channel_stats->xdpsq; @@ -1395,7 +1395,7 @@ static const struct counter_desc ch_stats_desc[] = { static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv) { - int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); + int max_nch = priv->max_nch; return (NUM_RQ_STATS * max_nch) + (NUM_CH_STATS * max_nch) + @@ -1409,8 +1409,8 @@ static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv) static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data, int idx) { - int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); bool is_xsk = priv->xsk.ever_used; + int max_nch = priv->max_nch; int i, j, tc; for (i = 0; i < max_nch; i++) @@ -1452,8 +1452,8 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data, static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx) { - int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); bool is_xsk = priv->xsk.ever_used; + int max_nch = priv->max_nch; int i, j, tc; for (i = 0; i < max_nch; i++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 6bfaaab362dc..1a2560e3bf7c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -88,8 +88,7 @@ int mlx5i_init(struct mlx5_core_dev *mdev, netdev->mtu = netdev->max_mtu; mlx5e_build_nic_params(mdev, NULL, &priv->rss_params, &priv->channels.params, - mlx5e_get_netdev_max_channels(netdev), - netdev->mtu); + priv->max_nch, netdev->mtu); mlx5i_build_nic_params(mdev, &priv->channels.params); mlx5e_timestamp_init(priv); @@ -118,11 +117,10 @@ void mlx5i_cleanup(struct mlx5e_priv *priv) static void mlx5i_grp_sw_update_stats(struct mlx5e_priv *priv) { - int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); struct mlx5e_sw_stats s = { 0 }; int i, j; - for (i = 0; i < max_nch; i++) { + for (i = 0; i < priv->max_nch; i++) { struct mlx5e_channel_stats *channel_stats; struct mlx5e_rq_stats *rq_stats; @@ -436,6 +434,7 @@ static const struct mlx5e_profile mlx5i_nic_profile = { .rx_handlers.handle_rx_cqe = mlx5i_handle_rx_cqe, .rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */ .max_tc = MLX5I_MAX_NUM_TC, + .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR), }; /* mlx5i netdev NDos */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index 6e56fa769d2e..c5a491e22e55 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -355,6 +355,7 @@ static const struct mlx5e_profile mlx5i_pkey_nic_profile = { .rx_handlers.handle_rx_cqe = mlx5i_handle_rx_cqe, .rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */ .max_tc = MLX5I_MAX_NUM_TC, + .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR), }; const struct mlx5e_profile *mlx5i_pkey_get_profile(void) From 4b95840a6ced0634082f6d962ba9aa0ce797f12f Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Sun, 16 Jun 2019 13:20:29 +0300 Subject: [PATCH 400/823] net/mlx5e: Fix matching of speed to PRM link modes Speed translation is performed based on legacy or extended PTYS register. Translate speed with respect to: 1) Capability bit of extended PTYS table. 2) User request: a) When auto-negotiation is turned on, inspect advertisement whether it contains extended link modes. b) When auto-negotiation is turned off, speed > 100Gbps (maximal speed supported in legacy mode). With both conditions fulfilled translation is done with extended PTYS table otherwise use legacy PTYS table. Without this patch 25/50/100 Gbps speed cannot be set, since try to configure in extended mode but read from legacy mode. Fixes: dd1b9e09c12b ("net/mlx5: ethtool, Allow legacy link-modes configuration via non-extended ptys") Signed-off-by: Aya Levin Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en/port.c | 27 ++++--- .../net/ethernet/mellanox/mlx5/core/en/port.h | 6 +- .../ethernet/mellanox/mlx5/core/en_ethtool.c | 71 +++++++++++++------ 3 files changed, 70 insertions(+), 34 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index d5e5afbdca6d..f777994f3005 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -78,9 +78,10 @@ static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = { }; static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev, - const u32 **arr, u32 *size) + const u32 **arr, u32 *size, + bool force_legacy) { - bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + bool ext = force_legacy ? false : MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); *size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) : ARRAY_SIZE(mlx5e_link_speed); @@ -152,7 +153,8 @@ int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable, sizeof(out), MLX5_REG_PTYS, 0, 1); } -u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper) +u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper, + bool force_legacy) { unsigned long temp = eth_proto_oper; const u32 *table; @@ -160,7 +162,7 @@ u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper) u32 max_size; int i; - mlx5e_port_get_speed_arr(mdev, &table, &max_size); + mlx5e_port_get_speed_arr(mdev, &table, &max_size, force_legacy); i = find_first_bit(&temp, max_size); if (i < max_size) speed = table[i]; @@ -170,6 +172,7 @@ u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper) int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) { struct mlx5e_port_eth_proto eproto; + bool force_legacy = false; bool ext; int err; @@ -177,8 +180,13 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto); if (err) goto out; - - *speed = mlx5e_port_ptys2speed(mdev, eproto.oper); + if (ext && !eproto.admin) { + force_legacy = true; + err = mlx5_port_query_eth_proto(mdev, 1, false, &eproto); + if (err) + goto out; + } + *speed = mlx5e_port_ptys2speed(mdev, eproto.oper, force_legacy); if (!(*speed)) err = -EINVAL; @@ -201,7 +209,7 @@ int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) if (err) return err; - mlx5e_port_get_speed_arr(mdev, &table, &max_size); + mlx5e_port_get_speed_arr(mdev, &table, &max_size, false); for (i = 0; i < max_size; ++i) if (eproto.cap & MLX5E_PROT_MASK(i)) max_speed = max(max_speed, table[i]); @@ -210,14 +218,15 @@ int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) return 0; } -u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed) +u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed, + bool force_legacy) { u32 link_modes = 0; const u32 *table; u32 max_size; int i; - mlx5e_port_get_speed_arr(mdev, &table, &max_size); + mlx5e_port_get_speed_arr(mdev, &table, &max_size, force_legacy); for (i = 0; i < max_size; ++i) { if (table[i] == speed) link_modes |= MLX5E_PROT_MASK(i); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h index 70f536ec51c4..4a7f4497692b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h @@ -48,10 +48,12 @@ void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status, u8 *an_disable_cap, u8 *an_disable_admin); int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable, u32 proto_admin, bool ext); -u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper); +u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper, + bool force_legacy); int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); -u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed); +u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed, + bool force_legacy); int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out); int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index ed25757ac5bd..03bed714bac3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -785,7 +785,7 @@ static void ptys2ethtool_supported_advertised_port(struct ethtool_link_ksettings } static void get_speed_duplex(struct net_device *netdev, - u32 eth_proto_oper, + u32 eth_proto_oper, bool force_legacy, struct ethtool_link_ksettings *link_ksettings) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -795,7 +795,7 @@ static void get_speed_duplex(struct net_device *netdev, if (!netif_carrier_ok(netdev)) goto out; - speed = mlx5e_port_ptys2speed(priv->mdev, eth_proto_oper); + speed = mlx5e_port_ptys2speed(priv->mdev, eth_proto_oper, force_legacy); if (!speed) { speed = SPEED_UNKNOWN; goto out; @@ -914,8 +914,8 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, /* Fields: eth_proto_admin and ext_eth_proto_admin are * mutually exclusive. Hence try reading legacy advertising * when extended advertising is zero. - * admin_ext indicates how eth_proto_admin should be - * interpreted + * admin_ext indicates which proto_admin (ext vs. legacy) + * should be read and interpreted */ admin_ext = ext; if (ext && !eth_proto_admin) { @@ -924,7 +924,7 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, admin_ext = false; } - eth_proto_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, + eth_proto_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, admin_ext, eth_proto_oper); eth_proto_lp = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise); an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin); @@ -939,7 +939,8 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, get_supported(mdev, eth_proto_cap, link_ksettings); get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings, admin_ext); - get_speed_duplex(priv->netdev, eth_proto_oper, link_ksettings); + get_speed_duplex(priv->netdev, eth_proto_oper, !admin_ext, + link_ksettings); eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; @@ -1016,45 +1017,69 @@ static u32 mlx5e_ethtool2ptys_ext_adver_link(const unsigned long *link_modes) return ptys_modes; } +static bool ext_link_mode_requested(const unsigned long *adver) +{ +#define MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT ETHTOOL_LINK_MODE_50000baseKR_Full_BIT + int size = __ETHTOOL_LINK_MODE_MASK_NBITS - MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT; + __ETHTOOL_DECLARE_LINK_MODE_MASK(modes); + + bitmap_set(modes, MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT, size); + return bitmap_intersects(modes, adver, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static bool ext_speed_requested(u32 speed) +{ +#define MLX5E_MAX_PTYS_LEGACY_SPEED 100000 + return !!(speed > MLX5E_MAX_PTYS_LEGACY_SPEED); +} + +static bool ext_requested(u8 autoneg, const unsigned long *adver, u32 speed) +{ + bool ext_link_mode = ext_link_mode_requested(adver); + bool ext_speed = ext_speed_requested(speed); + + return autoneg == AUTONEG_ENABLE ? ext_link_mode : ext_speed; +} + int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, const struct ethtool_link_ksettings *link_ksettings) { struct mlx5_core_dev *mdev = priv->mdev; struct mlx5e_port_eth_proto eproto; + const unsigned long *adver; bool an_changes = false; u8 an_disable_admin; bool ext_supported; - bool ext_requested; u8 an_disable_cap; bool an_disable; u32 link_modes; u8 an_status; + u8 autoneg; u32 speed; + bool ext; int err; u32 (*ethtool2ptys_adver_func)(const unsigned long *adver); -#define MLX5E_PTYS_EXT ((1ULL << ETHTOOL_LINK_MODE_50000baseKR_Full_BIT) - 1) - - ext_requested = !!(link_ksettings->link_modes.advertising[0] > - MLX5E_PTYS_EXT || - link_ksettings->link_modes.advertising[1]); - ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); - ext_requested &= ext_supported; - + adver = link_ksettings->link_modes.advertising; + autoneg = link_ksettings->base.autoneg; speed = link_ksettings->base.speed; - ethtool2ptys_adver_func = ext_requested ? - mlx5e_ethtool2ptys_ext_adver_link : + + ext = ext_requested(autoneg, adver, speed), + ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + if (!ext_supported && ext) + return -EOPNOTSUPP; + + ethtool2ptys_adver_func = ext ? mlx5e_ethtool2ptys_ext_adver_link : mlx5e_ethtool2ptys_adver_link; - err = mlx5_port_query_eth_proto(mdev, 1, ext_requested, &eproto); + err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto); if (err) { netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n", __func__, err); goto out; } - link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ? - ethtool2ptys_adver_func(link_ksettings->link_modes.advertising) : - mlx5e_port_speed2linkmodes(mdev, speed); + link_modes = autoneg == AUTONEG_ENABLE ? ethtool2ptys_adver_func(adver) : + mlx5e_port_speed2linkmodes(mdev, speed, !ext); link_modes = link_modes & eproto.cap; if (!link_modes) { @@ -1067,14 +1092,14 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, mlx5_port_query_eth_autoneg(mdev, &an_status, &an_disable_cap, &an_disable_admin); - an_disable = link_ksettings->base.autoneg == AUTONEG_DISABLE; + an_disable = autoneg == AUTONEG_DISABLE; an_changes = ((!an_disable && an_disable_admin) || (an_disable && !an_disable_admin)); if (!an_changes && link_modes == eproto.admin) goto out; - mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext_requested); + mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext); mlx5_toggle_port_link(mdev); out: From 90bb769291161cf25a818d69cf608c181654473e Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Sat, 6 Jul 2019 18:06:15 +0300 Subject: [PATCH 401/823] net/mlx5e: Prevent encap flow counter update async to user query This patch prevents a race between user invoked cached counters query and a neighbor last usage updater. The cached flow counter stats can be queried by calling "mlx5_fc_query_cached" which provides the number of bytes and packets that passed via this flow since the last time this counter was queried. It does so by reducting the last saved stats from the current, cached stats and then updating the last saved stats with the cached stats. It also provide the lastuse value for that flow. Since "mlx5e_tc_update_neigh_used_value" needs to retrieve the last usage time of encapsulation flows, it calls the flow counter query method periodically and async to user queries of the flow counter using cls_flower. This call is causing the driver to update the last reported bytes and packets from the cache and therefore, future user queries of the flow stats will return lower than expected number for bytes and packets since the last saved stats in the driver was updated async to the last saved stats in cls_flower. This causes wrong stats presentation of encapsulation flows to user. Since the neighbor usage updater only needs the lastuse stats from the cached counter, the fix is to use a dedicated lastuse query call that returns the lastuse value without synching between the cached stats and the last saved stats. Fixes: f6dfb4c3f216 ("net/mlx5e: Update neighbour 'used' state using HW flow rules counters") Signed-off-by: Ariel Levkovich Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c | 5 +++++ include/linux/mlx5/fs.h | 1 + 3 files changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index cc096f6011d9..7ecfc53cf5f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1230,13 +1230,13 @@ static struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow) void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) { struct mlx5e_neigh *m_neigh = &nhe->m_neigh; - u64 bytes, packets, lastuse = 0; struct mlx5e_tc_flow *flow; struct mlx5e_encap_entry *e; struct mlx5_fc *counter; struct neigh_table *tbl; bool neigh_used = false; struct neighbour *n; + u64 lastuse; if (m_neigh->family == AF_INET) tbl = &arp_tbl; @@ -1256,7 +1256,7 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) encaps[efi->index]); if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) { counter = mlx5e_tc_get_counter(flow); - mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse); + lastuse = mlx5_fc_query_lastuse(counter); if (time_after((unsigned long)lastuse, nhe->reported_lastuse)) { neigh_used = true; break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index b3762123a69c..1834d9f3aa1c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -369,6 +369,11 @@ int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, } EXPORT_SYMBOL(mlx5_fc_query); +u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter) +{ + return counter->cache.lastuse; +} + void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse) { diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 04a569568eac..f049af3f3cd8 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -220,6 +220,7 @@ int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler, struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); +u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse); int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, From 304ecc9a34b81a8b03b685f4460d0f9c1d6d4df9 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Thu, 18 Jul 2019 16:32:31 +0300 Subject: [PATCH 402/823] net/mlx5e: kTLS, Call WARN_ONCE on netdev mismatch A netdev mismatch in the processed TLS SKB should not occur, and indicates a kernel bug. Add WARN_ONCE to spot such cases. Fixes: d2ead1f360e8 ("net/mlx5e: Add kTLS TX HW offload support") Suggested-by: Jakub Kicinski Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index ea032f54197e..3766545ce259 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -412,7 +412,7 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev, goto out; tls_ctx = tls_get_ctx(skb->sk); - if (unlikely(tls_ctx->netdev != netdev)) + if (unlikely(WARN_ON_ONCE(tls_ctx->netdev != netdev))) goto err_out; priv_tx = mlx5e_get_ktls_tx_priv_ctx(tls_ctx); From 4ea52e25089724abf7ee2d6c0c52064e49252b64 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Thu, 18 Jul 2019 16:34:05 +0300 Subject: [PATCH 403/823] nfp: tls: rename tls packet counters Align to the naming convention in TLS documentation. Fixes: 51a5e563298d ("nfp: tls: add basic statistics") Suggested-by: Jakub Kicinski Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index d9cbe84ac6ad..1b840ee47339 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -444,12 +444,12 @@ static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data) data = nfp_pr_et(data, "hw_rx_csum_complete"); data = nfp_pr_et(data, "hw_rx_csum_err"); data = nfp_pr_et(data, "rx_replace_buf_alloc_fail"); - data = nfp_pr_et(data, "rx_tls_decrypted"); + data = nfp_pr_et(data, "rx_tls_decrypted_packets"); data = nfp_pr_et(data, "hw_tx_csum"); data = nfp_pr_et(data, "hw_tx_inner_csum"); data = nfp_pr_et(data, "tx_gather"); data = nfp_pr_et(data, "tx_lso"); - data = nfp_pr_et(data, "tx_tls_encrypted"); + data = nfp_pr_et(data, "tx_tls_encrypted_packets"); data = nfp_pr_et(data, "tx_tls_ooo"); data = nfp_pr_et(data, "tx_tls_drop_no_sync_data"); From 280c089916228a005af7f95c1716ea1fea1027b5 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 22 Jul 2019 13:43:03 +0300 Subject: [PATCH 404/823] Documentation: TLS: fix stat counters description Add missing description of counters. Split tx_tls_encrypted counter into two, to give packets and bytes indications. Fixes: f42c104f2ec9 ("Documentation: add TLS offload documentation") Suggested-by: Jakub Kicinski Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- Documentation/networking/tls-offload.rst | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/Documentation/networking/tls-offload.rst b/Documentation/networking/tls-offload.rst index 048e5ca44824..b70b70dc4524 100644 --- a/Documentation/networking/tls-offload.rst +++ b/Documentation/networking/tls-offload.rst @@ -424,13 +424,24 @@ Statistics Following minimum set of TLS-related statistics should be reported by the driver: - * ``rx_tls_decrypted`` - number of successfully decrypted TLS segments - * ``tx_tls_encrypted`` - number of in-order TLS segments passed to device - for encryption + * ``rx_tls_decrypted_packets`` - number of successfully decrypted RX packets + which were part of a TLS stream. + * ``rx_tls_decrypted_bytes`` - number of TLS payload bytes in RX packets + which were successfully decrypted. + * ``tx_tls_encrypted_packets`` - number of TX packets passed to the device + for encryption of their TLS payload. + * ``tx_tls_encrypted_bytes`` - number of TLS payload bytes in TX packets + passed to the device for encryption. + * ``tx_tls_ctx`` - number of TLS TX HW offload contexts added to device for + encryption. * ``tx_tls_ooo`` - number of TX packets which were part of a TLS stream - but did not arrive in the expected order - * ``tx_tls_drop_no_sync_data`` - number of TX packets dropped because - they arrived out of order and associated record could not be found + but did not arrive in the expected order. + * ``tx_tls_drop_no_sync_data`` - number of TX packets which were part of + a TLS stream dropped, because they arrived out of order and associated + record could not be found. + * ``tx_tls_drop_bypass_req`` - number of TX packets which were part of a TLS + stream dropped, because they contain both data that has been encrypted by + software and data that expects hardware crypto offload. Notable corner cases, exceptions and additional requirements ============================================================ From 173e6ee21e2b3f477f07548a79c43b8d9cfbb37d Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Jul 2019 13:41:20 +0200 Subject: [PATCH 405/823] structleak: disable STRUCTLEAK_BYREF in combination with KASAN_STACK The combination of KASAN_STACK and GCC_PLUGIN_STRUCTLEAK_BYREF leads to much larger kernel stack usage, as seen from the warnings about functions that now exceed the 2048 byte limit: drivers/media/i2c/tvp5150.c:253:1: error: the frame size of 3936 bytes is larger than 2048 bytes drivers/media/tuners/r820t.c:1327:1: error: the frame size of 2816 bytes is larger than 2048 bytes drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c:16552:1: error: the frame size of 3144 bytes is larger than 2048 bytes [-Werror=frame-larger-than=] fs/ocfs2/aops.c:1892:1: error: the frame size of 2088 bytes is larger than 2048 bytes fs/ocfs2/dlm/dlmrecovery.c:737:1: error: the frame size of 2088 bytes is larger than 2048 bytes fs/ocfs2/namei.c:1677:1: error: the frame size of 2584 bytes is larger than 2048 bytes fs/ocfs2/super.c:1186:1: error: the frame size of 2640 bytes is larger than 2048 bytes fs/ocfs2/xattr.c:3678:1: error: the frame size of 2176 bytes is larger than 2048 bytes net/bluetooth/l2cap_core.c:7056:1: error: the frame size of 2144 bytes is larger than 2048 bytes [-Werror=frame-larger-than=] net/bluetooth/l2cap_core.c: In function 'l2cap_recv_frame': net/bridge/br_netlink.c:1505:1: error: the frame size of 2448 bytes is larger than 2048 bytes net/ieee802154/nl802154.c:548:1: error: the frame size of 2232 bytes is larger than 2048 bytes net/wireless/nl80211.c:1726:1: error: the frame size of 2224 bytes is larger than 2048 bytes net/wireless/nl80211.c:2357:1: error: the frame size of 4584 bytes is larger than 2048 bytes net/wireless/nl80211.c:5108:1: error: the frame size of 2760 bytes is larger than 2048 bytes net/wireless/nl80211.c:6472:1: error: the frame size of 2112 bytes is larger than 2048 bytes The structleak plugin was previously disabled for CONFIG_COMPILE_TEST, but meant we missed some bugs, so this time we should address them. The frame size warnings are distracting, and risking a kernel stack overflow is generally not beneficial to performance, so it may be best to disallow that particular combination. This can be done by turning off either one. I picked the dependency in GCC_PLUGIN_STRUCTLEAK_BYREF and GCC_PLUGIN_STRUCTLEAK_BYREF_ALL, as this option is designed to make uninitialized stack usage less harmful when enabled on its own, but it also prevents KASAN from detecting those cases in which it was in fact needed. KASAN_STACK is currently implied by KASAN on gcc, but could be made a user selectable option if we want to allow combining (non-stack) KASAN with GCC_PLUGIN_STRUCTLEAK_BYREF. Note that it would be possible to specifically address the files that print the warning, but presumably the overall stack usage is still significantly higher than in other configurations, so this would not address the full problem. I could not test this with CONFIG_INIT_STACK_ALL, which may or may not suffer from a similar problem. Fixes: 81a56f6dcd20 ("gcc-plugins: structleak: Generalize to all variable types") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20190722114134.3123901-1-arnd@arndb.de Signed-off-by: Kees Cook --- security/Kconfig.hardening | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index c6cb2d9b2905..107176069af3 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -61,6 +61,7 @@ choice config GCC_PLUGIN_STRUCTLEAK_BYREF bool "zero-init structs passed by reference (strong)" depends on GCC_PLUGINS + depends on !(KASAN && KASAN_STACK=1) select GCC_PLUGIN_STRUCTLEAK help Zero-initialize any structures on the stack that may @@ -70,9 +71,15 @@ choice exposures, like CVE-2017-1000410: https://git.kernel.org/linus/06e7e776ca4d3654 + As a side-effect, this keeps a lot of variables on the + stack that can otherwise be optimized out, so combining + this with CONFIG_KASAN_STACK can lead to a stack overflow + and is disallowed. + config GCC_PLUGIN_STRUCTLEAK_BYREF_ALL bool "zero-init anything passed by reference (very strong)" depends on GCC_PLUGINS + depends on !(KASAN && KASAN_STACK=1) select GCC_PLUGIN_STRUCTLEAK help Zero-initialize any stack variables that may be passed From d1f0b5dce8fda09a7f5f04c1878f181d548e42f5 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Tue, 23 Jul 2019 19:32:41 -0700 Subject: [PATCH 406/823] bnx2x: Disable multi-cos feature. Commit 3968d38917eb ("bnx2x: Fix Multi-Cos.") which enabled multi-cos feature after prolonged time in driver added some regression causing numerous issues (sudden reboots, tx timeout etc.) reported by customers. We plan to backout this commit and submit proper fix once we have root cause of issues reported with this feature enabled. Fixes: 3968d38917eb ("bnx2x: Fix Multi-Cos.") Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Manish Chopra Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index e2be5a685130..e47ea92e2ae3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -1934,8 +1934,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, } /* select a non-FCoE queue */ - return netdev_pick_tx(dev, skb, NULL) % - (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos); + return netdev_pick_tx(dev, skb, NULL) % (BNX2X_NUM_ETH_QUEUES(bp)); } void bnx2x_set_num_queues(struct bnx2x *bp) From 53db1cced401e4c65d49edf198e00daa9fc837e6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Jul 2019 17:07:14 -0700 Subject: [PATCH 407/823] selftests/net: add missing gitignores (ipv6_flowlabel) ipv6_flowlabel and ipv6_flowlabel_mgr are missing from gitignore. Quentin points out that the original commit 3fb321fde22d ("selftests/net: ipv6 flowlabel") did add ignore entries, they are just missing the "ipv6_" prefix. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- tools/testing/selftests/net/.gitignore | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 4ce0bc1612f5..c7cced739c34 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -17,7 +17,7 @@ tcp_inq tls txring_overwrite ip_defrag +ipv6_flowlabel +ipv6_flowlabel_mgr so_txtime -flowlabel -flowlabel_mgr tcp_fastopen_backup_key From 47d858d0bdcd47cc1c6c9eeca91b091dd9e55637 Mon Sep 17 00:00:00 2001 From: Haishuang Yan Date: Thu, 25 Jul 2019 11:07:56 +0800 Subject: [PATCH 408/823] ipip: validate header length in ipip_tunnel_xmit We need the same checks introduced by commit cb9f1b783850 ("ip: validate header length on virtual device xmit") for ipip tunnel. Fixes: cb9f1b783850b ("ip: validate header length on virtual device xmit") Signed-off-by: Haishuang Yan Signed-off-by: David S. Miller --- net/ipv4/ipip.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 43adfc1641ba..2f01cf6fa0de 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -275,6 +275,9 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, const struct iphdr *tiph = &tunnel->parms.iph; u8 ipproto; + if (!pskb_inet_may_pull(skb)) + goto tx_error; + switch (skb->protocol) { case htons(ETH_P_IP): ipproto = IPPROTO_IPIP; From eba6120de93b8d5f2987fac1f533c35b53eaa771 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 11 Feb 2019 11:48:21 -0600 Subject: [PATCH 409/823] firewire: mark expected switch fall-throughs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. This patch fixes the following warnings: drivers/firewire/core-device.c: In function ‘set_broadcast_channel’: drivers/firewire/core-device.c:969:7: warning: this statement may fall through [-Wimplicit-fallthrough=] if (data & cpu_to_be32(1 << 31)) { ^ drivers/firewire/core-device.c:974:3: note: here case RCODE_ADDRESS_ERROR: ^~~~ drivers/firewire/core-iso.c: In function ‘manage_channel’: drivers/firewire/core-iso.c:308:7: warning: this statement may fall through [-Wimplicit-fallthrough=] if ((data[0] & bit) == (data[1] & bit)) ^ drivers/firewire/core-iso.c:312:3: note: here default: ^~~~~~~ drivers/firewire/core-topology.c: In function ‘count_ports’: drivers/firewire/core-topology.c:69:23: warning: this statement may fall through [-Wimplicit-fallthrough=] (*child_port_count)++; ~~~~~~~~~~~~~~~~~~~^~ drivers/firewire/core-topology.c:70:3: note: here case SELFID_PORT_PARENT: ^~~~ Warning level 3 was used: -Wimplicit-fallthrough=3 Notice that in some cases, the code comment is modified in accordance with what GCC is expecting to find. This patch is part of the ongoing efforts to enable -Wimplicit-fallthrough. Cc: Kees Cook Cc: Mathieu Malaterre Signed-off-by: Stefan Richter (reworded a comment) Signed-off-by: Gustavo A. R. Silva --- drivers/firewire/core-device.c | 2 +- drivers/firewire/core-iso.c | 2 +- drivers/firewire/core-topology.c | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index 3dc1cbf849db..b785e936244f 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -957,7 +957,7 @@ static void set_broadcast_channel(struct fw_device *device, int generation) device->bc_implemented = BC_IMPLEMENTED; break; } - /* else fall through to case address error */ + /* else, fall through - to case address error */ case RCODE_ADDRESS_ERROR: device->bc_implemented = BC_UNIMPLEMENTED; } diff --git a/drivers/firewire/core-iso.c b/drivers/firewire/core-iso.c index 42566b7be8f5..df8a56a979b9 100644 --- a/drivers/firewire/core-iso.c +++ b/drivers/firewire/core-iso.c @@ -284,7 +284,7 @@ static int manage_channel(struct fw_card *card, int irm_id, int generation, if ((data[0] & bit) == (data[1] & bit)) continue; - /* 1394-1995 IRM, fall through to retry. */ + /* fall through - It's a 1394-1995 IRM, retry. */ default: if (retry) { retry--; diff --git a/drivers/firewire/core-topology.c b/drivers/firewire/core-topology.c index 46bd22dde535..94a13fca8267 100644 --- a/drivers/firewire/core-topology.c +++ b/drivers/firewire/core-topology.c @@ -54,6 +54,7 @@ static u32 *count_ports(u32 *sid, int *total_port_count, int *child_port_count) switch (port_type) { case SELFID_PORT_CHILD: (*child_port_count)++; + /* fall through */ case SELFID_PORT_PARENT: case SELFID_PORT_NCONN: (*total_port_count)++; From 5a8dadbcfa6b04ea3be6f0ffa04eba173c865378 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 29 Jan 2019 11:59:28 -0600 Subject: [PATCH 410/823] can: mark expected switch fall-throughs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. This patch fixes the following warnings: drivers/net/can/peak_canfd/peak_pciefd_main.c:668:3: warning: this statement may fall through [-Wimplicit-fallthrough=] drivers/net/can/spi/mcp251x.c:875:7: warning: this statement may fall through [-Wimplicit-fallthrough=] drivers/net/can/usb/peak_usb/pcan_usb.c:422:6: warning: this statement may fall through [-Wimplicit-fallthrough=] drivers/net/can/at91_can.c:895:6: warning: this statement may fall through [-Wimplicit-fallthrough=] drivers/net/can/at91_can.c:953:15: warning: this statement may fall through [-Wimplicit-fallthrough=] drivers/net/can/usb/peak_usb/pcan_usb.c: In function ‘pcan_usb_decode_error’: drivers/net/can/usb/peak_usb/pcan_usb.c:422:6: warning: this statement may fall through [-Wimplicit-fallthrough=] if (n & PCAN_USB_ERROR_BUS_LIGHT) { ^ drivers/net/can/usb/peak_usb/pcan_usb.c:428:2: note: here case CAN_STATE_ERROR_WARNING: ^~~~ Warning level 3 was used: -Wimplicit-fallthrough=3 This patch is part of the ongoing efforts to enabling -Wimplicit-fallthrough. Notice that in some cases spelling mistakes were fixed. In other cases, the /* fall through */ comment is placed at the bottom of the case statement, which is what GCC is expecting to find. Signed-off-by: Gustavo A. R. Silva --- drivers/net/can/at91_can.c | 6 ++++-- drivers/net/can/peak_canfd/peak_pciefd_main.c | 2 +- drivers/net/can/spi/mcp251x.c | 3 ++- drivers/net/can/usb/peak_usb/pcan_usb.c | 2 +- 4 files changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index 1d4075903971..c8e1a04ba384 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -898,7 +898,8 @@ static void at91_irq_err_state(struct net_device *dev, CAN_ERR_CRTL_TX_WARNING : CAN_ERR_CRTL_RX_WARNING; } - case CAN_STATE_ERROR_WARNING: /* fallthrough */ + /* fall through */ + case CAN_STATE_ERROR_WARNING: /* * from: ERROR_ACTIVE, ERROR_WARNING * to : ERROR_PASSIVE, BUS_OFF @@ -947,7 +948,8 @@ static void at91_irq_err_state(struct net_device *dev, netdev_dbg(dev, "Error Active\n"); cf->can_id |= CAN_ERR_PROT; cf->data[2] = CAN_ERR_PROT_ACTIVE; - case CAN_STATE_ERROR_WARNING: /* fallthrough */ + /* fall through */ + case CAN_STATE_ERROR_WARNING: reg_idr = AT91_IRQ_ERRA | AT91_IRQ_WARN | AT91_IRQ_BOFF; reg_ier = AT91_IRQ_ERRP; break; diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c index 7f6a3b971da9..13b10cbf236a 100644 --- a/drivers/net/can/peak_canfd/peak_pciefd_main.c +++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c @@ -660,7 +660,7 @@ static int pciefd_can_probe(struct pciefd_board *pciefd) pciefd_can_writereg(priv, CANFD_CLK_SEL_80MHZ, PCIEFD_REG_CAN_CLK_SEL); - /* fallthough */ + /* fall through */ case CANFD_CLK_SEL_80MHZ: priv->ucan.can.clock.freq = 80 * 1000 * 1000; break; diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index 44e99e3d7134..234cf1042df6 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -860,7 +860,8 @@ static irqreturn_t mcp251x_can_ist(int irq, void *dev_id) if (new_state >= CAN_STATE_ERROR_WARNING && new_state <= CAN_STATE_BUS_OFF) priv->can.can_stats.error_warning++; - case CAN_STATE_ERROR_WARNING: /* fallthrough */ + /* fall through */ + case CAN_STATE_ERROR_WARNING: if (new_state >= CAN_STATE_ERROR_PASSIVE && new_state <= CAN_STATE_BUS_OFF) priv->can.can_stats.error_passive++; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index 15ce5ad1d632..617da295b6c1 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -415,7 +415,7 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n, new_state = CAN_STATE_ERROR_WARNING; break; } - /* else: fall through */ + /* fall through */ case CAN_STATE_ERROR_WARNING: if (n & PCAN_USB_ERROR_BUS_HEAVY) { From 35a3a90cc56cee54fb4d45afbbc6dfea0835de0c Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Sun, 19 May 2019 18:56:50 -0500 Subject: [PATCH 411/823] afs: yfsclient: Mark expected switch fall-throughs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. This patch fixes the following warnings: fs/afs/yfsclient.c: In function ‘yfs_deliver_fs_fetch_opaque_acl’: fs/afs/yfsclient.c:1984:19: warning: this statement may fall through [-Wimplicit-fallthrough=] call->unmarshall++; ~~~~~~~~~~~~~~~~^~ fs/afs/yfsclient.c:1987:2: note: here case 1: ^~~~ fs/afs/yfsclient.c:2005:19: warning: this statement may fall through [-Wimplicit-fallthrough=] call->unmarshall++; ~~~~~~~~~~~~~~~~^~ fs/afs/yfsclient.c:2008:2: note: here case 2: ^~~~ fs/afs/yfsclient.c:2014:19: warning: this statement may fall through [-Wimplicit-fallthrough=] call->unmarshall++; ~~~~~~~~~~~~~~~~^~ fs/afs/yfsclient.c:2017:2: note: here case 3: ^~~~ fs/afs/yfsclient.c:2035:19: warning: this statement may fall through [-Wimplicit-fallthrough=] call->unmarshall++; ~~~~~~~~~~~~~~~~^~ fs/afs/yfsclient.c:2038:2: note: here case 4: ^~~~ fs/afs/yfsclient.c:2047:19: warning: this statement may fall through [-Wimplicit-fallthrough=] call->unmarshall++; ~~~~~~~~~~~~~~~~^~ fs/afs/yfsclient.c:2050:2: note: here case 5: ^~~~ Warning level 3 was used: -Wimplicit-fallthrough=3 Also, fix some commenting style issues. This patch is part of the ongoing efforts to enable -Wimplicit-fallthrough. Signed-off-by: Gustavo A. R. Silva --- fs/afs/yfsclient.c | 54 ++++++++++++++++++++++++++++++---------------- 1 file changed, 35 insertions(+), 19 deletions(-) diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 18722aaeda33..2575503170fc 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -450,8 +450,9 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) req->offset = req->pos & (PAGE_SIZE - 1); afs_extract_to_tmp64(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the returned data length */ + /* extract the returned data length */ case 1: _debug("extract data length"); ret = afs_extract_data(call, true); @@ -477,8 +478,9 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) call->bvec[0].bv_page = req->pages[req->index]; iov_iter_bvec(&call->iter, READ, call->bvec, 1, size); ASSERTCMP(size, <=, PAGE_SIZE); + /* Fall through */ - /* Fall through - and extract the returned data */ + /* extract the returned data */ case 2: _debug("extract data %zu/%llu", iov_iter_count(&call->iter), req->remain); @@ -505,8 +507,8 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) /* Discard any excess data the server gave us */ iov_iter_discard(&call->iter, READ, req->actual_len - req->len); call->unmarshall = 3; - /* Fall through */ + case 3: _debug("extract discard %zu/%llu", iov_iter_count(&call->iter), req->actual_len - req->len); @@ -521,8 +523,9 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSCallBack) + sizeof(struct yfs_xdr_YFSVolSync)); + /* Fall through */ - /* Fall through - and extract the metadata */ + /* extract the metadata */ case 4: ret = afs_extract_data(call, false); if (ret < 0) @@ -539,8 +542,8 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) req->file_size = call->out_scb->status.size; call->unmarshall++; - /* Fall through */ + case 5: break; } @@ -1429,8 +1432,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) case 0: call->unmarshall++; afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchVolumeStatus)); + /* Fall through */ - /* Fall through - and extract the returned status record */ + /* extract the returned status record */ case 1: _debug("extract status"); ret = afs_extract_data(call, true); @@ -1441,8 +1445,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) xdr_decode_YFSFetchVolumeStatus(&bp, call->out_volstatus); call->unmarshall++; afs_extract_to_tmp(call); + /* Fall through */ - /* Fall through - and extract the volume name length */ + /* extract the volume name length */ case 2: ret = afs_extract_data(call, true); if (ret < 0) @@ -1456,8 +1461,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the volume name */ + /* extract the volume name */ case 3: _debug("extract volname"); ret = afs_extract_data(call, true); @@ -1469,8 +1475,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) _debug("volname '%s'", p); afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the offline message length */ + /* extract the offline message length */ case 4: ret = afs_extract_data(call, true); if (ret < 0) @@ -1484,8 +1491,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the offline message */ + /* extract the offline message */ case 5: _debug("extract offline"); ret = afs_extract_data(call, true); @@ -1498,8 +1506,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the message of the day length */ + /* extract the message of the day length */ case 6: ret = afs_extract_data(call, true); if (ret < 0) @@ -1513,8 +1522,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the message of the day */ + /* extract the message of the day */ case 7: _debug("extract motd"); ret = afs_extract_data(call, false); @@ -1526,8 +1536,8 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) _debug("motd '%s'", p); call->unmarshall++; - /* Fall through */ + case 8: break; } @@ -1805,9 +1815,9 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ /* Extract the file status count and array in two steps */ - /* Fall through */ case 1: _debug("extract status count"); ret = afs_extract_data(call, true); @@ -1824,8 +1834,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_counts: afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchStatus)); - /* Fall through */ + case 2: _debug("extract status array %u", call->count); ret = afs_extract_data(call, true); @@ -1845,9 +1855,9 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) call->count = 0; call->unmarshall++; afs_extract_to_tmp(call); + /* Fall through */ /* Extract the callback count and array in two steps */ - /* Fall through */ case 3: _debug("extract CB count"); ret = afs_extract_data(call, true); @@ -1863,8 +1873,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_cbs: afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSCallBack)); - /* Fall through */ + case 4: _debug("extract CB array"); ret = afs_extract_data(call, true); @@ -1881,8 +1891,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSVolSync)); call->unmarshall++; - /* Fall through */ + case 5: ret = afs_extract_data(call, false); if (ret < 0) @@ -1892,8 +1902,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) xdr_decode_YFSVolSync(&bp, call->out_volsync); call->unmarshall++; - /* Fall through */ + case 6: break; } @@ -1978,6 +1988,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ /* Extract the file ACL length */ case 1: @@ -1999,6 +2010,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) iov_iter_discard(&call->iter, READ, size); } call->unmarshall++; + /* Fall through */ /* Extract the file ACL */ case 2: @@ -2008,6 +2020,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ /* Extract the volume ACL length */ case 3: @@ -2029,6 +2042,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) iov_iter_discard(&call->iter, READ, size); } call->unmarshall++; + /* Fall through */ /* Extract the volume ACL */ case 4: @@ -2041,6 +2055,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); call->unmarshall++; + /* Fall through */ /* extract the metadata */ case 5: @@ -2057,6 +2072,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) xdr_decode_YFSVolSync(&bp, call->out_volsync); call->unmarshall++; + /* Fall through */ case 6: break; From 2988160827b780eec3f958ade2100cc223d4d2d6 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Sun, 19 May 2019 18:43:53 -0500 Subject: [PATCH 412/823] afs: fsclient: Mark expected switch fall-throughs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. This patch fixes the following warnings: Warning level 3 was used: -Wimplicit-fallthrough=3 fs/afs/fsclient.c: In function ‘afs_deliver_fs_fetch_acl’: fs/afs/fsclient.c:2199:19: warning: this statement may fall through [-Wimplicit-fallthrough=] call->unmarshall++; ~~~~~~~~~~~~~~~~^~ fs/afs/fsclient.c:2202:2: note: here case 1: ^~~~ fs/afs/fsclient.c:2216:19: warning: this statement may fall through [-Wimplicit-fallthrough=] call->unmarshall++; ~~~~~~~~~~~~~~~~^~ fs/afs/fsclient.c:2219:2: note: here case 2: ^~~~ fs/afs/fsclient.c:2225:19: warning: this statement may fall through [-Wimplicit-fallthrough=] call->unmarshall++; ~~~~~~~~~~~~~~~~^~ fs/afs/fsclient.c:2228:2: note: here case 3: ^~~~ This patch is part of the ongoing efforts to enable -Wimplicit-fallthrough. Signed-off-by: Gustavo A. R. Silva --- fs/afs/fsclient.c | 51 ++++++++++++++++++++++++++++++----------------- 1 file changed, 33 insertions(+), 18 deletions(-) diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 1ce73e014139..114f281f3687 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -339,8 +339,9 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) call->tmp_u = htonl(0); afs_extract_to_tmp(call); } + /* Fall through */ - /* Fall through - and extract the returned data length */ + /* extract the returned data length */ case 1: _debug("extract data length"); ret = afs_extract_data(call, true); @@ -366,8 +367,9 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) call->bvec[0].bv_page = req->pages[req->index]; iov_iter_bvec(&call->iter, READ, call->bvec, 1, size); ASSERTCMP(size, <=, PAGE_SIZE); + /* Fall through */ - /* Fall through - and extract the returned data */ + /* extract the returned data */ case 2: _debug("extract data %zu/%llu", iov_iter_count(&call->iter), req->remain); @@ -394,8 +396,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) /* Discard any excess data the server gave us */ iov_iter_discard(&call->iter, READ, req->actual_len - req->len); call->unmarshall = 3; - /* Fall through */ + case 3: _debug("extract discard %zu/%llu", iov_iter_count(&call->iter), req->actual_len - req->len); @@ -407,8 +409,9 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) no_more_data: call->unmarshall = 4; afs_extract_to_buf(call, (21 + 3 + 6) * 4); + /* Fall through */ - /* Fall through - and extract the metadata */ + /* extract the metadata */ case 4: ret = afs_extract_data(call, false); if (ret < 0) @@ -1471,8 +1474,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) case 0: call->unmarshall++; afs_extract_to_buf(call, 12 * 4); + /* Fall through */ - /* Fall through - and extract the returned status record */ + /* extract the returned status record */ case 1: _debug("extract status"); ret = afs_extract_data(call, true); @@ -1483,8 +1487,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) xdr_decode_AFSFetchVolumeStatus(&bp, call->out_volstatus); call->unmarshall++; afs_extract_to_tmp(call); + /* Fall through */ - /* Fall through - and extract the volume name length */ + /* extract the volume name length */ case 2: ret = afs_extract_data(call, true); if (ret < 0) @@ -1498,8 +1503,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the volume name */ + /* extract the volume name */ case 3: _debug("extract volname"); ret = afs_extract_data(call, true); @@ -1511,8 +1517,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) _debug("volname '%s'", p); afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the offline message length */ + /* extract the offline message length */ case 4: ret = afs_extract_data(call, true); if (ret < 0) @@ -1526,8 +1533,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the offline message */ + /* extract the offline message */ case 5: _debug("extract offline"); ret = afs_extract_data(call, true); @@ -1540,8 +1548,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the message of the day length */ + /* extract the message of the day length */ case 6: ret = afs_extract_data(call, true); if (ret < 0) @@ -1555,8 +1564,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the message of the day */ + /* extract the message of the day */ case 7: _debug("extract motd"); ret = afs_extract_data(call, false); @@ -1850,8 +1860,9 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the capabilities word count */ + /* Extract the capabilities word count */ case 1: ret = afs_extract_data(call, true); if (ret < 0) @@ -1863,8 +1874,9 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call) call->count2 = count; iov_iter_discard(&call->iter, READ, count * sizeof(__be32)); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract capabilities words */ + /* Extract capabilities words */ case 2: ret = afs_extract_data(call, false); if (ret < 0) @@ -2020,9 +2032,9 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ /* Extract the file status count and array in two steps */ - /* Fall through */ case 1: _debug("extract status count"); ret = afs_extract_data(call, true); @@ -2039,8 +2051,8 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_counts: afs_extract_to_buf(call, 21 * sizeof(__be32)); - /* Fall through */ + case 2: _debug("extract status array %u", call->count); ret = afs_extract_data(call, true); @@ -2060,9 +2072,9 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) call->count = 0; call->unmarshall++; afs_extract_to_tmp(call); + /* Fall through */ /* Extract the callback count and array in two steps */ - /* Fall through */ case 3: _debug("extract CB count"); ret = afs_extract_data(call, true); @@ -2078,8 +2090,8 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_cbs: afs_extract_to_buf(call, 3 * sizeof(__be32)); - /* Fall through */ + case 4: _debug("extract CB array"); ret = afs_extract_data(call, true); @@ -2096,8 +2108,8 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) afs_extract_to_buf(call, 6 * sizeof(__be32)); call->unmarshall++; - /* Fall through */ + case 5: ret = afs_extract_data(call, false); if (ret < 0) @@ -2193,6 +2205,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ /* extract the returned data length */ case 1: @@ -2210,6 +2223,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) acl->size = call->count2; afs_extract_begin(call, acl->data, size); call->unmarshall++; + /* Fall through */ /* extract the returned data */ case 2: @@ -2219,6 +2233,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) afs_extract_to_buf(call, (21 + 6) * 4); call->unmarshall++; + /* Fall through */ /* extract the metadata */ case 3: From cc4070449a5bd700c02de4a9d37adb40e116773d Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 4 Jun 2019 08:58:02 -0500 Subject: [PATCH 413/823] mtd: onenand_base: Mark expected switch fall-through MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. This patch fixes the following warning: drivers/mtd/nand/onenand/onenand_base.c: In function ‘onenand_check_features’: drivers/mtd/nand/onenand/onenand_base.c:3264:17: warning: this statement may fall through [-Wimplicit-fallthrough=] this->options |= ONENAND_HAS_NOP_1; drivers/mtd/nand/onenand/onenand_base.c:3265:2: note: here case ONENAND_DEVICE_DENSITY_4Gb: ^~~~ Warning level 3 was used: -Wimplicit-fallthrough=3 This patch is part of the ongoing efforts to enable -Wimplicit-fallthrough. Cc: Jonathan Bakker Signed-off-by: Gustavo A. R. Silva --- drivers/mtd/nand/onenand/onenand_base.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mtd/nand/onenand/onenand_base.c b/drivers/mtd/nand/onenand/onenand_base.c index a1f8fe1abb10..e082d632fb74 100644 --- a/drivers/mtd/nand/onenand/onenand_base.c +++ b/drivers/mtd/nand/onenand/onenand_base.c @@ -3259,6 +3259,7 @@ static void onenand_check_features(struct mtd_info *mtd) switch (density) { case ONENAND_DEVICE_DENSITY_8Gb: this->options |= ONENAND_HAS_NOP_1; + /* fall through */ case ONENAND_DEVICE_DENSITY_4Gb: if (ONENAND_IS_DDP(this)) this->options |= ONENAND_HAS_2PLANE; From 7b26b91d3b2320a64af63b6ec989ee3bed59f0d3 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 24 Jun 2019 11:11:07 -0500 Subject: [PATCH 414/823] perf/x86/intel: Mark expected switch fall-throughs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. This patch fixes the following warnings: arch/x86/events/intel/core.c: In function ‘intel_pmu_init’: arch/x86/events/intel/core.c:4959:8: warning: this statement may fall through [-Wimplicit-fallthrough=] pmem = true; ~~~~~^~~~~~ arch/x86/events/intel/core.c:4960:2: note: here case INTEL_FAM6_SKYLAKE_MOBILE: ^~~~ arch/x86/events/intel/core.c:5008:8: warning: this statement may fall through [-Wimplicit-fallthrough=] pmem = true; ~~~~~^~~~~~ arch/x86/events/intel/core.c:5009:2: note: here case INTEL_FAM6_ICELAKE_MOBILE: ^~~~ Warning level 3 was used: -Wimplicit-fallthrough=3 This patch is part of the ongoing efforts to enable -Wimplicit-fallthrough. Signed-off-by: Gustavo A. R. Silva --- arch/x86/events/intel/core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 9e911a96972b..62feab0233fa 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4955,6 +4955,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_SKYLAKE_X: pmem = true; + /* fall through */ case INTEL_FAM6_SKYLAKE_MOBILE: case INTEL_FAM6_SKYLAKE_DESKTOP: case INTEL_FAM6_KABYLAKE_MOBILE: @@ -5004,6 +5005,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ICELAKE_X: case INTEL_FAM6_ICELAKE_XEON_D: pmem = true; + /* fall through */ case INTEL_FAM6_ICELAKE_MOBILE: case INTEL_FAM6_ICELAKE_DESKTOP: x86_pmu.late_ack = true; From 737298d18836fd14b8820de6504536c998986bcd Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Sun, 21 Jul 2019 16:41:37 -0500 Subject: [PATCH 415/823] drm/amdkfd: Fix missing break in switch statement Add missing break statement in order to prevent the code from falling through to case CHIP_NAVI10. This bug was found thanks to the ongoing efforts to enable -Wimplicit-fallthrough. Fixes: 14328aa58ce5 ("drm/amdkfd: Add navi10 support to amdkfd. (v3)") Cc: stable@vger.kernel.org Reviewed-by: Alex Deucher Signed-off-by: Gustavo A. R. Silva --- drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 792371442195..4e3fc284f6ac 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -668,6 +668,7 @@ static int kfd_fill_gpu_cache_info(struct kfd_dev *kdev, case CHIP_RAVEN: pcache_info = raven_cache_info; num_of_cache_types = ARRAY_SIZE(raven_cache_info); + break; case CHIP_NAVI10: pcache_info = navi10_cache_info; num_of_cache_types = ARRAY_SIZE(navi10_cache_info); From d64062b57eeb58d4928aed945515bf53f7944913 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Sun, 21 Jul 2019 17:37:33 -0500 Subject: [PATCH 416/823] drm/amdgpu/gfx10: Fix missing break in switch statement Add missing break statement in order to prevent the code from falling through to case AMDGPU_IRQ_STATE_ENABLE. This bug was found thanks to the ongoing efforts to enable -Wimplicit-fallthrough. Fixes: a644d85a5cd4 ("drm/amdgpu: add gfx v10 implementation (v10)") Cc: stable@vger.kernel.org Reviewed-by: Alex Deucher Signed-off-by: Gustavo A. R. Silva --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 1675d5837c3c..35e8e29139b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -4611,6 +4611,7 @@ gfx_v10_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev, cp_int_cntl = REG_SET_FIELD(cp_int_cntl, CP_INT_CNTL_RING0, TIME_STAMP_INT_ENABLE, 0); WREG32(cp_int_cntl_reg, cp_int_cntl); + break; case AMDGPU_IRQ_STATE_ENABLE: cp_int_cntl = RREG32(cp_int_cntl_reg); cp_int_cntl = REG_SET_FIELD(cp_int_cntl, CP_INT_CNTL_RING0, From 12fce1ab4ad97773a19b7de4f5f4953cb74e9881 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 22 Jul 2019 11:26:31 -0500 Subject: [PATCH 417/823] drm/amdkfd/kfd_mqd_manager_v10: Avoid fall-through warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to enabling -Wimplicit-fallthrough, this patch silences the following warning: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_mqd_manager_v10.c: In function ‘mqd_manager_init_v10’: ./include/linux/dynamic_debug.h:122:52: warning: this statement may fall through [-Wimplicit-fallthrough=] #define __dynamic_func_call(id, fmt, func, ...) do { \ ^ ./include/linux/dynamic_debug.h:143:2: note: in expansion of macro ‘__dynamic_func_call’ __dynamic_func_call(__UNIQUE_ID(ddebug), fmt, func, ##__VA_ARGS__) ^~~~~~~~~~~~~~~~~~~ ./include/linux/dynamic_debug.h:153:2: note: in expansion of macro ‘_dynamic_func_call’ _dynamic_func_call(fmt, __dynamic_pr_debug, \ ^~~~~~~~~~~~~~~~~~ ./include/linux/printk.h:336:2: note: in expansion of macro ‘dynamic_pr_debug’ dynamic_pr_debug(fmt, ##__VA_ARGS__) ^~~~~~~~~~~~~~~~ drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_mqd_manager_v10.c:432:3: note: in expansion of macro ‘pr_debug’ pr_debug("%s@%i\n", __func__, __LINE__); ^~~~~~~~ drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_mqd_manager_v10.c:433:2: note: here case KFD_MQD_TYPE_COMPUTE: ^~~~ by removing the call to pr_debug() in KFD_MQD_TYPE_CP: "The mqd init for CP and COMPUTE will have the same routine." [1] This bug was found thanks to the ongoing efforts to enable -Wimplicit-fallthrough. [1] https://lore.kernel.org/lkml/c735a1cc-a545-50fb-44e7-c0ad93ee8ee7@amd.com/ Reviewed-by: Alex Deucher Signed-off-by: Gustavo A. R. Silva --- drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c index 4f8a6ffc5775..9cd3eb2d90bd 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c @@ -429,7 +429,6 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type, switch (type) { case KFD_MQD_TYPE_CP: - pr_debug("%s@%i\n", __func__, __LINE__); case KFD_MQD_TYPE_COMPUTE: pr_debug("%s@%i\n", __func__, __LINE__); mqd->allocate_mqd = allocate_mqd; From 9e87891799dc4b203ad680ff431bfcce679c89be Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 25 Jul 2019 19:13:51 -0500 Subject: [PATCH 418/823] drm/amd/display: Mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Warning level 3 was used: -Wimplicit-fallthrough=3 This patch is part of the ongoing efforts to enable -Wimplicit-fallthrough. Signed-off-by: Gustavo A. R. Silva --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c index 51a3dfe97f0e..31aa6ee5cd5b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c @@ -102,14 +102,19 @@ void dccg2_init(struct dccg *dccg) switch (dccg_dcn->base.ctx->dc->res_pool->pipe_count) { case 6: REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[5], 1); + /* Fall through */ case 5: REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[4], 1); + /* Fall through */ case 4: REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[3], 1); + /* Fall through */ case 3: REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[2], 1); + /* Fall through */ case 2: REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[1], 1); + /* Fall through */ case 1: REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[0], 1); break; From 2defb94edb44784b0b5064633e05c97fdb1b0e0f Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 22 Jul 2019 13:03:46 -0500 Subject: [PATCH 419/823] drm/i915: Mark expected switch fall-throughs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. This patch fixes the following warnings: drivers/gpu/drm/i915/gem/i915_gem_mman.c: In function ‘i915_gem_fault’: drivers/gpu/drm/i915/gem/i915_gem_mman.c:342:6: warning: this statement may fall through [-Wimplicit-fallthrough=] if (!i915_terminally_wedged(i915)) ^ drivers/gpu/drm/i915/gem/i915_gem_mman.c:345:2: note: here case -EAGAIN: ^~~~ drivers/gpu/drm/i915/gem/i915_gem_pages.c: In function ‘i915_gem_object_map’: ./include/linux/compiler.h:78:22: warning: this statement may fall through [-Wimplicit-fallthrough=] # define unlikely(x) __builtin_expect(!!(x), 0) ^~~~~~~~~~~~~~~~~~~~~~~~~~ ./include/asm-generic/bug.h:136:2: note: in expansion of macro ‘unlikely’ unlikely(__ret_warn_on); \ ^~~~~~~~ drivers/gpu/drm/i915/i915_utils.h:49:25: note: in expansion of macro ‘WARN’ #define MISSING_CASE(x) WARN(1, "Missing case (%s == %ld)\n", \ ^~~~ drivers/gpu/drm/i915/gem/i915_gem_pages.c:270:3: note: in expansion of macro ‘MISSING_CASE’ MISSING_CASE(type); ^~~~~~~~~~~~ drivers/gpu/drm/i915/gem/i915_gem_pages.c:272:2: note: here case I915_MAP_WB: ^~~~ drivers/gpu/drm/i915/i915_gpu_error.c: In function ‘error_record_engine_registers’: ./include/linux/compiler.h:78:22: warning: this statement may fall through [-Wimplicit-fallthrough=] # define unlikely(x) __builtin_expect(!!(x), 0) ^~~~~~~~~~~~~~~~~~~~~~~~~~ ./include/asm-generic/bug.h:136:2: note: in expansion of macro ‘unlikely’ unlikely(__ret_warn_on); \ ^~~~~~~~ drivers/gpu/drm/i915/i915_utils.h:49:25: note: in expansion of macro ‘WARN’ #define MISSING_CASE(x) WARN(1, "Missing case (%s == %ld)\n", \ ^~~~ drivers/gpu/drm/i915/i915_gpu_error.c:1196:5: note: in expansion of macro ‘MISSING_CASE’ MISSING_CASE(engine->id); ^~~~~~~~~~~~ drivers/gpu/drm/i915/i915_gpu_error.c:1197:4: note: here case RCS0: ^~~~ drivers/gpu/drm/i915/display/intel_dp.c: In function ‘intel_dp_get_fia_supported_lane_count’: ./include/linux/compiler.h:78:22: warning: this statement may fall through [-Wimplicit-fallthrough=] # define unlikely(x) __builtin_expect(!!(x), 0) ^~~~~~~~~~~~~~~~~~~~~~~~~~ ./include/asm-generic/bug.h:136:2: note: in expansion of macro ‘unlikely’ unlikely(__ret_warn_on); \ ^~~~~~~~ drivers/gpu/drm/i915/i915_utils.h:49:25: note: in expansion of macro ‘WARN’ #define MISSING_CASE(x) WARN(1, "Missing case (%s == %ld)\n", \ ^~~~ drivers/gpu/drm/i915/display/intel_dp.c:233:3: note: in expansion of macro ‘MISSING_CASE’ MISSING_CASE(lane_info); ^~~~~~~~~~~~ drivers/gpu/drm/i915/display/intel_dp.c:234:2: note: here case 1: ^~~~ drivers/gpu/drm/i915/display/intel_display.c: In function ‘check_digital_port_conflicts’: CC [M] drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgv100.o drivers/gpu/drm/i915/display/intel_display.c:12043:7: warning: this statement may fall through [-Wimplicit-fallthrough=] if (WARN_ON(!HAS_DDI(to_i915(dev)))) ^ drivers/gpu/drm/i915/display/intel_display.c:12046:3: note: here case INTEL_OUTPUT_DP: ^~~~ Also, notice that the Makefile is modified to stop ignoring fall-through warnings. The -Wimplicit-fallthrough option will be enabled globally in v5.3. Warning level 3 was used: -Wimplicit-fallthrough=3 This patch is part of the ongoing efforts to enable -Wimplicit-fallthrough. Reviewed-by: Kees Cook Signed-off-by: Gustavo A. R. Silva --- drivers/gpu/drm/i915/Makefile | 1 - drivers/gpu/drm/i915/display/intel_display.c | 2 +- drivers/gpu/drm/i915/display/intel_dp.c | 1 + drivers/gpu/drm/i915/gem/i915_gem_mman.c | 2 +- drivers/gpu/drm/i915/gem/i915_gem_pages.c | 2 +- drivers/gpu/drm/i915/i915_gpu_error.c | 1 + 6 files changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 91355c2ea8a5..8cace65f50ce 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -16,7 +16,6 @@ subdir-ccflags-y := -Wall -Wextra subdir-ccflags-y += $(call cc-disable-warning, unused-parameter) subdir-ccflags-y += $(call cc-disable-warning, type-limits) subdir-ccflags-y += $(call cc-disable-warning, missing-field-initializers) -subdir-ccflags-y += $(call cc-disable-warning, implicit-fallthrough) subdir-ccflags-y += $(call cc-disable-warning, unused-but-set-variable) # clang warnings subdir-ccflags-y += $(call cc-disable-warning, sign-compare) diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 8592a7d422de..30b97ded6fdd 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -12042,7 +12042,7 @@ static bool check_digital_port_conflicts(struct intel_atomic_state *state) case INTEL_OUTPUT_DDI: if (WARN_ON(!HAS_DDI(to_i915(dev)))) break; - /* else: fall through */ + /* else, fall through */ case INTEL_OUTPUT_DP: case INTEL_OUTPUT_HDMI: case INTEL_OUTPUT_EDP: diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 4336df46fe78..d0fc34826771 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -231,6 +231,7 @@ static int intel_dp_get_fia_supported_lane_count(struct intel_dp *intel_dp) switch (lane_info) { default: MISSING_CASE(lane_info); + /* fall through */ case 1: case 2: case 4: diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 391621ee3cbb..39a661927d8e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -341,7 +341,7 @@ err: */ if (!i915_terminally_wedged(i915)) return VM_FAULT_SIGBUS; - /* else: fall through */ + /* else, fall through */ case -EAGAIN: /* * EAGAIN means the gpu is hung and we'll wait for the error diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index b36ad269f4ea..65eb430cedba 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -268,7 +268,7 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj, switch (type) { default: MISSING_CASE(type); - /* fallthrough to use PAGE_KERNEL anyway */ + /* fallthrough - to use PAGE_KERNEL anyway */ case I915_MAP_WB: pgprot = PAGE_KERNEL; break; diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index b7e9fddef270..41a511d5267f 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1194,6 +1194,7 @@ static void error_record_engine_registers(struct i915_gpu_state *error, switch (engine->id) { default: MISSING_CASE(engine->id); + /* fall through */ case RCS0: mmio = RENDER_HWS_PGA_GEN7; break; From a035d552a93bb9ef6048733bb9f2a0dc857ff869 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 6 Jun 2019 19:46:17 -0500 Subject: [PATCH 420/823] Makefile: Globally enable fall-through warning Now that all the fall-through warnings have been addressed in the kernel, enable the fall-through warning globally. Also, update the deprecated.rst file to include implicit fall-through as 'deprecated' so people can be pointed to a single location for justification. Cc: Masahiro Yamada Cc: Andrew Morton Cc: Michal Marek Cc: Kees Cook Cc: linux-kbuild@vger.kernel.org Signed-off-by: Gustavo A. R. Silva --- Documentation/process/deprecated.rst | 14 ++++++++++++++ Makefile | 3 +++ 2 files changed, 17 insertions(+) diff --git a/Documentation/process/deprecated.rst b/Documentation/process/deprecated.rst index 49e0f64a3427..053b24a6dd38 100644 --- a/Documentation/process/deprecated.rst +++ b/Documentation/process/deprecated.rst @@ -119,3 +119,17 @@ array may exceed the remaining memory in the stack segment. This could lead to a crash, possible overwriting sensitive contents at the end of the stack (when built without `CONFIG_THREAD_INFO_IN_TASK=y`), or overwriting memory adjacent to the stack (when built without `CONFIG_VMAP_STACK=y`) + +Implicit switch case fall-through +--------------------------------- +The C language allows switch cases to "fall through" when +a "break" statement is missing at the end of a case. This, +however, introduces ambiguity in the code, as it's not always +clear if the missing break is intentional or a bug. As there +have been a long list of flaws `due to missing "break" statements +`_, we no longer allow +"implicit fall-through". In order to identify an intentional fall-through +case, we have adopted the marking used by static analyzers: a comment +saying `/* Fall through */`. Once the C++17 `__attribute__((fallthrough))` +is more widely handled by C compilers, static analyzers, and IDEs, we can +switch to using that instead. diff --git a/Makefile b/Makefile index 9be5834073f8..bdf8eac51b07 100644 --- a/Makefile +++ b/Makefile @@ -843,6 +843,9 @@ NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include) # warn about C99 declaration after statement KBUILD_CFLAGS += -Wdeclaration-after-statement +# Warn about unmarked fall-throughs in switch statement. +KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough=3,) + # Variable Length Arrays (VLAs) should not be used anywhere in the kernel KBUILD_CFLAGS += -Wvla From 09e088a4903bd0dd911b4f1732b250130cdaffed Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 24 Jul 2019 22:08:50 +0800 Subject: [PATCH 421/823] xen/pciback: remove set but not used variable 'old_state' Fixes gcc '-Wunused-but-set-variable' warning: drivers/xen/xen-pciback/conf_space_capability.c: In function pm_ctrl_write: drivers/xen/xen-pciback/conf_space_capability.c:119:25: warning: variable old_state set but not used [-Wunused-but-set-variable] It is never used so can be removed. Reported-by: Hulk Robot Signed-off-by: YueHaibing Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- drivers/xen/xen-pciback/conf_space_capability.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/xen/xen-pciback/conf_space_capability.c b/drivers/xen/xen-pciback/conf_space_capability.c index 73427d8e0116..e5694133ebe5 100644 --- a/drivers/xen/xen-pciback/conf_space_capability.c +++ b/drivers/xen/xen-pciback/conf_space_capability.c @@ -116,13 +116,12 @@ static int pm_ctrl_write(struct pci_dev *dev, int offset, u16 new_value, { int err; u16 old_value; - pci_power_t new_state, old_state; + pci_power_t new_state; err = pci_read_config_word(dev, offset, &old_value); if (err) goto out; - old_state = (pci_power_t)(old_value & PCI_PM_CTRL_STATE_MASK); new_state = (pci_power_t)(new_value & PCI_PM_CTRL_STATE_MASK); new_value &= PM_OK_BITS; From a3b46b86ca76d7f9d487e6a0b594fd1984e0796e Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Fri, 26 Jul 2019 16:47:05 +0900 Subject: [PATCH 422/823] btrfs: fix extent_state leak in btrfs_lock_and_flush_ordered_range btrfs_lock_and_flush_ordered_range() loads given "*cached_state" into cachedp, which, in general, is NULL. Then, lock_extent_bits() updates "cachedp", but it never goes backs to the caller. Thus the caller still see its "cached_state" to be NULL and never free the state allocated under btrfs_lock_and_flush_ordered_range(). As a result, we will see massive state leak with e.g. fstests btrfs/005. Fix this bug by properly handling the pointers. Fixes: bd80d94efb83 ("btrfs: Always use a cached extent_state in btrfs_lock_and_flush_ordered_range") Reviewed-by: Nikolay Borisov Signed-off-by: Naohiro Aota Signed-off-by: David Sterba --- fs/btrfs/ordered-data.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 1744ba8b2754..ae7f64a8facb 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -985,13 +985,14 @@ void btrfs_lock_and_flush_ordered_range(struct extent_io_tree *tree, struct extent_state **cached_state) { struct btrfs_ordered_extent *ordered; - struct extent_state *cachedp = NULL; + struct extent_state *cache = NULL; + struct extent_state **cachedp = &cache; if (cached_state) - cachedp = *cached_state; + cachedp = cached_state; while (1) { - lock_extent_bits(tree, start, end, &cachedp); + lock_extent_bits(tree, start, end, cachedp); ordered = btrfs_lookup_ordered_range(inode, start, end - start + 1); if (!ordered) { @@ -1001,10 +1002,10 @@ void btrfs_lock_and_flush_ordered_range(struct extent_io_tree *tree, * aren't exposing it outside of this function */ if (!cached_state) - refcount_dec(&cachedp->refs); + refcount_dec(&cache->refs); break; } - unlock_extent_cached(tree, start, end, &cachedp); + unlock_extent_cached(tree, start, end, cachedp); btrfs_start_ordered_extent(&inode->vfs_inode, ordered, 1); btrfs_put_ordered_extent(ordered); } From 1a2dcff881059dedc14fafc8a442664c8dbd60f1 Mon Sep 17 00:00:00 2001 From: Halil Pasic Date: Wed, 24 Jul 2019 00:51:55 +0200 Subject: [PATCH 423/823] s390/dma: provide proper ARCH_ZONE_DMA_BITS value On s390 ZONE_DMA is up to 2G, i.e. ARCH_ZONE_DMA_BITS should be 31 bits. The current value is 24 and makes __dma_direct_alloc_pages() take a wrong turn first (but __dma_direct_alloc_pages() recovers then). Let's correct ARCH_ZONE_DMA_BITS value and avoid wrong turns. Signed-off-by: Halil Pasic Reported-by: Petr Tesarik Fixes: c61e9637340e ("dma-direct: add support for allocation from ZONE_DMA and ZONE_DMA32") Signed-off-by: Heiko Carstens --- arch/s390/include/asm/page.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index a4d38092530a..823578c6b9e2 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -177,6 +177,8 @@ static inline int devmem_is_allowed(unsigned long pfn) #define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define ARCH_ZONE_DMA_BITS 31 + #include #include From 4f419eb14272e0698e8c55bb5f3f266cc2a21c81 Mon Sep 17 00:00:00 2001 From: Halil Pasic Date: Tue, 23 Jul 2019 17:11:01 +0200 Subject: [PATCH 424/823] virtio/s390: fix race on airq_areas[] The access to airq_areas was racy ever since the adapter interrupts got introduced to virtio-ccw, but since commit 39c7dcb15892 ("virtio/s390: make airq summary indicators DMA") this became an issue in practice as well. Namely before that commit the airq_info that got overwritten was still functional. After that commit however the two infos share a summary_indicator, which aggravates the situation. Which means auto-online mechanism occasionally hangs the boot with virtio_blk. Signed-off-by: Halil Pasic Reported-by: Marc Hartmayer Reviewed-by: Cornelia Huck Cc: stable@vger.kernel.org Fixes: 96b14536d935 ("virtio-ccw: virtio-ccw adapter interrupt support.") Signed-off-by: Heiko Carstens --- drivers/s390/virtio/virtio_ccw.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index 1a55e5942d36..957889a42d2e 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -145,6 +145,8 @@ struct airq_info { struct airq_iv *aiv; }; static struct airq_info *airq_areas[MAX_AIRQ_AREAS]; +static DEFINE_MUTEX(airq_areas_lock); + static u8 *summary_indicators; static inline u8 *get_summary_indicator(struct airq_info *info) @@ -265,9 +267,11 @@ static unsigned long get_airq_indicator(struct virtqueue *vqs[], int nvqs, unsigned long bit, flags; for (i = 0; i < MAX_AIRQ_AREAS && !indicator_addr; i++) { + mutex_lock(&airq_areas_lock); if (!airq_areas[i]) airq_areas[i] = new_airq_info(i); info = airq_areas[i]; + mutex_unlock(&airq_areas_lock); if (!info) return 0; write_lock_irqsave(&info->lock, flags); From ac7a0fcea39d29125b83b73583463e5ab70fdb37 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 26 Jun 2019 00:00:42 +0200 Subject: [PATCH 425/823] s390/mm: use shared variables for sysctl range check Since commit eec4844fae7c ("proc/sysctl: add shared variables for range check") special shared variables are available for sysctl range check. Reuse them for /proc/sys/vm/allocate_pgste proc handler. Acked-by: Christian Borntraeger Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/mm/pgalloc.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 99e06213a22b..54fcdf66ae96 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -17,8 +17,6 @@ #ifdef CONFIG_PGSTE -static int page_table_allocate_pgste_min = 0; -static int page_table_allocate_pgste_max = 1; int page_table_allocate_pgste = 0; EXPORT_SYMBOL(page_table_allocate_pgste); @@ -29,8 +27,8 @@ static struct ctl_table page_table_sysctl[] = { .maxlen = sizeof(int), .mode = S_IRUGO | S_IWUSR, .proc_handler = proc_dointvec_minmax, - .extra1 = &page_table_allocate_pgste_min, - .extra2 = &page_table_allocate_pgste_max, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { } }; From 98abe0227827f45cddb21875b2ffa9aeca3848b3 Mon Sep 17 00:00:00 2001 From: Farhan Ali Date: Wed, 24 Jul 2019 17:32:03 -0400 Subject: [PATCH 426/823] MAINTAINERS: vfio-ccw: Remove myself as the maintainer I will not be able to continue with my maintainership responsibilities going forward, so remove myself as the maintainer. Signed-off-by: Farhan Ali Acked-by: Cornelia Huck Signed-off-by: Christian Borntraeger Signed-off-by: Heiko Carstens --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 783569e3c4b4..82d9e1b5d17d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13947,7 +13947,6 @@ F: drivers/pci/hotplug/s390_pci_hpc.c S390 VFIO-CCW DRIVER M: Cornelia Huck -M: Farhan Ali M: Eric Farman R: Halil Pasic L: linux-s390@vger.kernel.org From 73f628ec9e6bcc45b77c53fe6d0c0ec55eaf82af Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 26 Jul 2019 07:49:29 -0400 Subject: [PATCH 427/823] vhost: disable metadata prefetch optimization This seems to cause guest and host memory corruption. Disable for now until we get a better handle on that. Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vhost.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 819296332913..42a8c2a13ab1 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -96,7 +96,7 @@ struct vhost_uaddr { }; #if defined(CONFIG_MMU_NOTIFIER) && ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0 -#define VHOST_ARCH_CAN_ACCEL_UACCESS 1 +#define VHOST_ARCH_CAN_ACCEL_UACCESS 0 #else #define VHOST_ARCH_CAN_ACCEL_UACCESS 0 #endif From e6f4051123fd33901e9655a675b22aefcdc5d277 Mon Sep 17 00:00:00 2001 From: Manikanta Pubbisetty Date: Mon, 22 Jul 2019 12:44:50 +0530 Subject: [PATCH 428/823] {nl,mac}80211: fix interface combinations on crypto controlled devices Commit 33d915d9e8ce ("{nl,mac}80211: allow 4addr AP operation on crypto controlled devices") has introduced a change which allows 4addr operation on crypto controlled devices (ex: ath10k). This change has inadvertently impacted the interface combinations logic on such devices. General rule is that software interfaces like AP/VLAN should not be listed under supported interface combinations and should not be considered during validation of these combinations; because of the aforementioned change, AP/VLAN interfaces(if present) will be checked against interfaces supported by the device and blocks valid interface combinations. Consider a case where an AP and AP/VLAN are up and running; when a second AP device is brought up on the same physical device, this AP will be checked against the AP/VLAN interface (which will not be part of supported interface combinations of the device) and blocks second AP to come up. Add a new API cfg80211_iftype_allowed() to fix the problem, this API works for all devices with/without SW crypto control. Signed-off-by: Manikanta Pubbisetty Fixes: 33d915d9e8ce ("{nl,mac}80211: allow 4addr AP operation on crypto controlled devices") Link: https://lore.kernel.org/r/1563779690-9716-1-git-send-email-mpubbise@codeaurora.org Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 15 +++++++++++++++ net/mac80211/util.c | 7 +++---- net/wireless/core.c | 6 ++---- net/wireless/nl80211.c | 4 +--- net/wireless/util.c | 27 +++++++++++++++++++++++++-- 5 files changed, 46 insertions(+), 13 deletions(-) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 45850a8391d9..26e2ad2c7027 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -7320,6 +7320,21 @@ void cfg80211_pmsr_complete(struct wireless_dev *wdev, struct cfg80211_pmsr_request *req, gfp_t gfp); +/** + * cfg80211_iftype_allowed - check whether the interface can be allowed + * @wiphy: the wiphy + * @iftype: interface type + * @is_4addr: use_4addr flag, must be '0' when check_swif is '1' + * @check_swif: check iftype against software interfaces + * + * Check whether the interface is allowed to operate; additionally, this API + * can be used to check iftype against the software interfaces when + * check_swif is '1'. + */ +bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, + bool is_4addr, u8 check_swif); + + /* Logging, debugging and troubleshooting/diagnostic helpers. */ /* wiphy_printk helpers, similar to dev_printk */ diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 1b224fa27367..ad1e58184c4e 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3796,9 +3796,7 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, } /* Always allow software iftypes */ - if (local->hw.wiphy->software_iftypes & BIT(iftype) || - (iftype == NL80211_IFTYPE_AP_VLAN && - local->hw.wiphy->flags & WIPHY_FLAG_4ADDR_AP)) { + if (cfg80211_iftype_allowed(local->hw.wiphy, iftype, 0, 1)) { if (radar_detect) return -EINVAL; return 0; @@ -3833,7 +3831,8 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, if (sdata_iter == sdata || !ieee80211_sdata_running(sdata_iter) || - local->hw.wiphy->software_iftypes & BIT(wdev_iter->iftype)) + cfg80211_iftype_allowed(local->hw.wiphy, + wdev_iter->iftype, 0, 1)) continue; params.iftype_num[wdev_iter->iftype]++; diff --git a/net/wireless/core.c b/net/wireless/core.c index 45d9afcff6d5..32b3c719fdfc 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1410,10 +1410,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, } break; case NETDEV_PRE_UP: - if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype)) && - !(wdev->iftype == NL80211_IFTYPE_AP_VLAN && - rdev->wiphy.flags & WIPHY_FLAG_4ADDR_AP && - wdev->use_4addr)) + if (!cfg80211_iftype_allowed(wdev->wiphy, wdev->iftype, + wdev->use_4addr, 0)) return notifier_from_errno(-EOPNOTSUPP); if (rfkill_blocked(rdev->rfkill)) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index fc83dd179c1a..fd05ae1437a9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3484,9 +3484,7 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) return err; } - if (!(rdev->wiphy.interface_modes & (1 << type)) && - !(type == NL80211_IFTYPE_AP_VLAN && params.use_4addr && - rdev->wiphy.flags & WIPHY_FLAG_4ADDR_AP)) + if (!cfg80211_iftype_allowed(&rdev->wiphy, type, params.use_4addr, 0)) return -EOPNOTSUPP; err = nl80211_parse_mon_options(rdev, type, info, ¶ms); diff --git a/net/wireless/util.c b/net/wireless/util.c index 1c39d6a2e850..d0e35b7b9e35 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1697,7 +1697,7 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { num_interfaces += params->iftype_num[iftype]; if (params->iftype_num[iftype] > 0 && - !(wiphy->software_iftypes & BIT(iftype))) + !cfg80211_iftype_allowed(wiphy, iftype, 0, 1)) used_iftypes |= BIT(iftype); } @@ -1719,7 +1719,7 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, return -ENOMEM; for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { - if (wiphy->software_iftypes & BIT(iftype)) + if (cfg80211_iftype_allowed(wiphy, iftype, 0, 1)) continue; for (j = 0; j < c->n_limits; j++) { all_iftypes |= limits[j].types; @@ -2072,3 +2072,26 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, return max_vht_nss; } EXPORT_SYMBOL(ieee80211_get_vht_max_nss); + +bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, + bool is_4addr, u8 check_swif) + +{ + bool is_vlan = iftype == NL80211_IFTYPE_AP_VLAN; + + switch (check_swif) { + case 0: + if (is_vlan && is_4addr) + return wiphy->flags & WIPHY_FLAG_4ADDR_AP; + return wiphy->interface_modes & BIT(iftype); + case 1: + if (!(wiphy->software_iftypes & BIT(iftype)) && is_vlan) + return wiphy->flags & WIPHY_FLAG_4ADDR_AP; + return wiphy->software_iftypes & BIT(iftype); + default: + break; + } + + return false; +} +EXPORT_SYMBOL(cfg80211_iftype_allowed); From 19a1c4092e7ca1ad1a72ac5535f902c483372cd5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 24 Jul 2019 12:45:46 -0400 Subject: [PATCH 429/823] fix the struct mount leak in umount_tree() We need to drop everything we remove from the tree, whether mnt_has_parent() is true or not. Usually the bug manifests as a slow memory leak (leaked struct mount for initramfs); it becomes much more visible in mount_subtree() users, such as btrfs. There we leak a struct mount for btrfs superblock being mounted, which prevents fs shutdown on subsequent umount. Fixes: 56cbb429d911 ("switch the remnants of releasing the mountpoint away from fs_pin") Reported-by: Nikolay Borisov Tested-by: Nikolay Borisov Signed-off-by: Al Viro --- fs/namespace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/namespace.c b/fs/namespace.c index 6464ea4acba9..d28d30b13043 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1463,7 +1463,6 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; disconnect = disconnect_mount(p, how); - if (mnt_has_parent(p)) { mnt_add_count(p->mnt_parent, -1); if (!disconnect) { @@ -1471,10 +1470,11 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts); } else { umount_mnt(p); - hlist_add_head(&p->mnt_umount, &unmounted); } } change_mnt_propagation(p, MS_PRIVATE); + if (disconnect) + hlist_add_head(&p->mnt_umount, &unmounted); } } From 52f8c8b32ea2f2044efcb4214c1857e29f421c5d Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Fri, 26 Jul 2019 13:28:26 +0200 Subject: [PATCH 430/823] irqchip/gic-v3: Mark expected switch fall-through MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When fall-through warnings was enabled by default the following warning was starting to show up: In file included from ../arch/arm64/include/asm/cputype.h:132, from ../arch/arm64/include/asm/cache.h:8, from ../include/linux/cache.h:6, from ../include/linux/printk.h:9, from ../include/linux/kernel.h:15, from ../include/linux/list.h:9, from ../include/linux/kobject.h:19, from ../include/linux/of.h:17, from ../include/linux/irqdomain.h:35, from ../include/linux/acpi.h:13, from ../drivers/irqchip/irq-gic-v3.c:9: ../drivers/irqchip/irq-gic-v3.c: In function ‘gic_cpu_sys_reg_init’: ../arch/arm64/include/asm/sysreg.h:853:2: warning: this statement may fall through [-Wimplicit-fallthrough=] asm volatile(__msr_s(r, "%x0") : : "rZ" (__val)); \ ^~~ ../arch/arm64/include/asm/arch_gicv3.h:20:29: note: in expansion of macro ‘write_sysreg_s’ #define write_gicreg(v, r) write_sysreg_s(v, SYS_ ## r) ^~~~~~~~~~~~~~ ../drivers/irqchip/irq-gic-v3.c:773:4: note: in expansion of macro ‘write_gicreg’ write_gicreg(0, ICC_AP0R2_EL1); ^~~~~~~~~~~~ ../drivers/irqchip/irq-gic-v3.c:774:3: note: here case 6: ^~~~ Rework so that the compiler doesn't warn about fall-through. Fixes: d93512ef0f0e ("Makefile: Globally enable fall-through warning") Signed-off-by: Anders Roxell Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 1282f81696b2..acd784c37090 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -775,8 +775,10 @@ static void gic_cpu_sys_reg_init(void) case 7: write_gicreg(0, ICC_AP0R3_EL1); write_gicreg(0, ICC_AP0R2_EL1); + /* Fall through */ case 6: write_gicreg(0, ICC_AP0R1_EL1); + /* Fall through */ case 5: case 4: write_gicreg(0, ICC_AP0R0_EL1); @@ -790,8 +792,10 @@ static void gic_cpu_sys_reg_init(void) case 7: write_gicreg(0, ICC_AP1R3_EL1); write_gicreg(0, ICC_AP1R2_EL1); + /* Fall through */ case 6: write_gicreg(0, ICC_AP1R1_EL1); + /* Fall through */ case 5: case 4: write_gicreg(0, ICC_AP1R0_EL1); From 34f8eb92ca053cbba2887bb7e4dbf2b2cd6eb733 Mon Sep 17 00:00:00 2001 From: Nianyao Tang Date: Fri, 26 Jul 2019 17:32:57 +0800 Subject: [PATCH 431/823] irqchip/gic-v3-its: Free unused vpt_page when alloc vpe table fail In its_vpe_init, when its_alloc_vpe_table fails, we should free vpt_page allocated just before, instead of vpe->vpt_page. Let's fix it. Cc: Thomas Gleixner Cc: Jason Cooper Cc: Marc Zyngier Signed-off-by: Nianyao Tang Signed-off-by: Shaokun Zhang Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index cfb9b4e5f914..4439ed881f98 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3008,7 +3008,7 @@ static int its_vpe_init(struct its_vpe *vpe) if (!its_alloc_vpe_table(vpe_id)) { its_vpe_id_free(vpe_id); - its_free_pending_table(vpe->vpt_page); + its_free_pending_table(vpt_page); return -ENOMEM; } From 321275f0d8f5939f2a98749fe03ee97ac97e73d0 Mon Sep 17 00:00:00 2001 From: Nishka Dasgupta Date: Tue, 23 Jul 2019 16:09:10 +0530 Subject: [PATCH 432/823] irqchip/irq-mbigen: Add of_node_put() before return Each iteration of for_each_child_of_node puts the previous node, but in the case of a return from the middle of the loop, there is no put, thus causing a memory leak. Add an of_node_put before the return in three places. Issue found with Coccinelle. Signed-off-by: Nishka Dasgupta Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-mbigen.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c index c0f65ea0ae0f..64f3574cc009 100644 --- a/drivers/irqchip/irq-mbigen.c +++ b/drivers/irqchip/irq-mbigen.c @@ -252,12 +252,15 @@ static int mbigen_of_create_domain(struct platform_device *pdev, parent = platform_bus_type.dev_root; child = of_platform_device_create(np, NULL, parent); - if (!child) + if (!child) { + of_node_put(np); return -ENOMEM; + } if (of_property_read_u32(child->dev.of_node, "num-pins", &num_pins) < 0) { dev_err(&pdev->dev, "No num-pins property\n"); + of_node_put(np); return -EINVAL; } @@ -265,8 +268,10 @@ static int mbigen_of_create_domain(struct platform_device *pdev, mbigen_write_msg, &mbigen_domain_ops, mgn_chip); - if (!domain) + if (!domain) { + of_node_put(np); return -ENOMEM; + } } return 0; From 9a446ef08f3bfc0c3deb9c6be840af2528ef8cf8 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 12 Jul 2019 15:29:05 +0200 Subject: [PATCH 433/823] irqchip/irq-imx-gpcv2: Forward irq type to parent The GPCv2 is a stacked IRQ controller below the ARM GIC. It doesn't care about the IRQ type itself, but needs to forward the type to the parent IRQ controller, so this one can be configured correctly. Signed-off-by: Lucas Stach Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-imx-gpcv2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/irqchip/irq-imx-gpcv2.c b/drivers/irqchip/irq-imx-gpcv2.c index 66501ea4fd75..f869386eb4cf 100644 --- a/drivers/irqchip/irq-imx-gpcv2.c +++ b/drivers/irqchip/irq-imx-gpcv2.c @@ -134,6 +134,7 @@ static struct irq_chip gpcv2_irqchip_data_chip = { .irq_unmask = imx_gpcv2_irq_unmask, .irq_set_wake = imx_gpcv2_irq_set_wake, .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_set_type = irq_chip_set_type_parent, #ifdef CONFIG_SMP .irq_set_affinity = irq_chip_set_affinity_parent, #endif From b5fa9fc9e809f84bb20439730162eccfed906a76 Mon Sep 17 00:00:00 2001 From: Wen Yang Date: Mon, 8 Jul 2019 14:19:04 +0800 Subject: [PATCH 434/823] irqchip/renesas-rza1: Fix an use-after-free in rza1_irqc_probe() The gic_node is still being used in the rza1_irqc_parse_map() call after the of_node_put() call, which may result in use-after-free. Fixes: a644ccb819bc ("irqchip: Add Renesas RZ/A1 Interrupt Controller driver") Signed-off-by: Wen Yang Reviewed-by: Geert Uytterhoeven Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-renesas-rza1.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/irqchip/irq-renesas-rza1.c b/drivers/irqchip/irq-renesas-rza1.c index b1f19b210190..b0d46ac42b89 100644 --- a/drivers/irqchip/irq-renesas-rza1.c +++ b/drivers/irqchip/irq-renesas-rza1.c @@ -208,20 +208,19 @@ static int rza1_irqc_probe(struct platform_device *pdev) return PTR_ERR(priv->base); gic_node = of_irq_find_parent(np); - if (gic_node) { + if (gic_node) parent = irq_find_host(gic_node); - of_node_put(gic_node); - } if (!parent) { dev_err(dev, "cannot find parent domain\n"); - return -ENODEV; + ret = -ENODEV; + goto out_put_node; } ret = rza1_irqc_parse_map(priv, gic_node); if (ret) { dev_err(dev, "cannot parse %s: %d\n", "interrupt-map", ret); - return ret; + goto out_put_node; } priv->chip.name = "rza1-irqc", @@ -237,10 +236,12 @@ static int rza1_irqc_probe(struct platform_device *pdev) priv); if (!priv->irq_domain) { dev_err(dev, "cannot initialize irq domain\n"); - return -ENOMEM; + ret = -ENOMEM; } - return 0; +out_put_node: + of_node_put(gic_node); + return ret; } static int rza1_irqc_remove(struct platform_device *pdev) From d2eba640a4b96bc1bdc0f4a500b8b8d5e16725c8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Guido=20G=C3=BCnther?= Date: Fri, 26 Jul 2019 11:55:34 +0200 Subject: [PATCH 435/823] docs: phy: Drop duplicate 'be made' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix duplicate words. Signed-off-by: Guido Günther Signed-off-by: Jonathan Corbet --- Documentation/driver-api/phy/phy.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/driver-api/phy/phy.rst b/Documentation/driver-api/phy/phy.rst index 457c3e0f86d6..8fc1ce0bb905 100644 --- a/Documentation/driver-api/phy/phy.rst +++ b/Documentation/driver-api/phy/phy.rst @@ -179,8 +179,8 @@ PHY Mappings In order to get reference to a PHY without help from DeviceTree, the framework offers lookups which can be compared to clkdev that allow clk structures to be -bound to devices. A lookup can be made be made during runtime when a handle to -the struct phy already exists. +bound to devices. A lookup can be made during runtime when a handle to the +struct phy already exists. The framework offers the following API for registering and unregistering the lookups:: From 820571af721990e354649368e641313f85a29976 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 26 Jul 2019 12:31:28 -0300 Subject: [PATCH 436/823] tools include UAPI: Sync x86's syscalls_64.tbl and generic unistd.h to pick up clone3 and pidfd_open MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 05a70a8ec287 ("unistd: protect clone3 via __ARCH_WANT_SYS_CLONE3") 8f3220a80654 ("arch: wire-up clone3() syscall") 7615d9e1780e ("arch: wire-up pidfd_open()") Silencing the following tools/perf build warnings Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/unistd.h' differs from latest version at 'include/uapi/asm-generic/unistd.h' diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl' diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl Now 'perf trace -e pidfd*,clone*' will trace those syscalls as well as the others with those prefixes. $ diff -u /tmp/build/perf/arch/x86/include/generated/asm/syscalls_64.c.before /tmp/build/perf/arch/x86/include/generated/asm/syscalls_64.c --- /tmp/build/perf/arch/x86/include/generated/asm/syscalls_64.c.before 2019-07-26 12:24:55.020944201 -0300 +++ /tmp/build/perf/arch/x86/include/generated/asm/syscalls_64.c 2019-07-26 12:25:03.919047217 -0300 @@ -344,5 +344,7 @@ [431] = "fsconfig", [432] = "fsmount", [433] = "fspick", + [434] = "pidfd_open", + [435] = "clone3", }; -#define SYSCALLTBL_x86_64_MAX_ID 433 +#define SYSCALLTBL_x86_64_MAX_ID 435 $ Cc: Adrian Hunter Cc: Brendan Gregg Cc: Christian Brauner Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-0isnnqxtr1ihz6p8wzjiy47d@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/asm-generic/unistd.h | 8 +++++++- tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 2 ++ 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index a87904daf103..1be0e798e362 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -844,9 +844,15 @@ __SYSCALL(__NR_fsconfig, sys_fsconfig) __SYSCALL(__NR_fsmount, sys_fsmount) #define __NR_fspick 433 __SYSCALL(__NR_fspick, sys_fspick) +#define __NR_pidfd_open 434 +__SYSCALL(__NR_pidfd_open, sys_pidfd_open) +#ifdef __ARCH_WANT_SYS_CLONE3 +#define __NR_clone3 435 +__SYSCALL(__NR_clone3, sys_clone3) +#endif #undef __NR_syscalls -#define __NR_syscalls 434 +#define __NR_syscalls 436 /* * 32 bit systems traditionally used different diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index b4e6f9e6204a..c29976eca4a8 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -355,6 +355,8 @@ 431 common fsconfig __x64_sys_fsconfig 432 common fsmount __x64_sys_fsmount 433 common fspick __x64_sys_fspick +434 common pidfd_open __x64_sys_pidfd_open +435 common clone3 __x64_sys_clone3/ptregs # # x32-specific system call numbers start at 512 to avoid cache impact From e0d99c4d24fd8861da724b88ebd18a9fae8a2260 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 26 Jul 2019 12:43:23 -0300 Subject: [PATCH 437/823] tools headers UAPI: Update tools's copy of kvm.h headers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Picking the changes from: 66bb8a065f5a ("KVM: x86: PMU Event Filter") f087a02941fe ("KVM: nVMX: Stash L1's CR3 in vmcs01.GUEST_CR3 on nested entry w/o EPT") 99adb567632b ("KVM: arm/arm64: Add save/restore support for firmware workaround state") Silencing this perf build warning: Warning: Kernel ABI header at 'tools/arch/arm/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm/include/uapi/asm/kvm.h' diff -u tools/arch/arm/include/uapi/asm/kvm.h arch/arm/include/uapi/asm/kvm.h Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h' diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/vmx.h' differs from latest version at 'arch/x86/include/uapi/asm/vmx.h' diff -u tools/arch/x86/include/uapi/asm/vmx.h arch/x86/include/uapi/asm/vmx.h Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/kvm.h' differs from latest version at 'arch/x86/include/uapi/asm/kvm.h' diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h' diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h Now 'perf trace' and other code that might use the tools/perf/trace/beauty autogenerated tables will be able to translate this new ioctl code into a string: $ tools/perf/trace/beauty/kvm_ioctl.sh > before $ $ cp include/uapi/linux/kvm.h tools/include/uapi/linux/kvm.h $ tools/perf/trace/beauty/kvm_ioctl.sh > after $ diff -u before after --- before 2019-07-26 12:32:47.959220236 -0300 +++ after 2019-07-26 12:33:05.766464871 -0300 @@ -79,6 +79,7 @@ [0xac] = "SET_ONE_REG", [0xad] = "KVMCLOCK_CTRL", [0xb0] = "GET_REG_LIST", + [0xb2] = "SET_PMU_EVENT_FILTER", [0xb7] = "SMI", [0xba] = "MEMORY_ENCRYPT_OP", [0xbb] = "MEMORY_ENCRYPT_REG_REGION", $ Cc: Adrian Hunter Cc: Andre Przywara Cc: Brendan Gregg Cc: Eric Hankland Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Marc Zyngier Cc: Namhyung Kim Cc: Paolo Bonzini Cc: Sean Christopherson Link: https://lkml.kernel.org/n/tip-py1gcmt6rboehlwg6zvagfg2@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/arm/include/uapi/asm/kvm.h | 12 ++++++++++++ tools/arch/arm64/include/uapi/asm/kvm.h | 10 ++++++++++ tools/arch/x86/include/uapi/asm/kvm.h | 22 ++++++++++++++++++---- tools/arch/x86/include/uapi/asm/vmx.h | 1 - tools/include/uapi/linux/kvm.h | 3 +++ 5 files changed, 43 insertions(+), 5 deletions(-) diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index 4602464ebdfb..a4217c1a5d01 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -214,6 +214,18 @@ struct kvm_vcpu_events { #define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \ KVM_REG_ARM_FW | ((r) & 0xffff)) #define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1) + /* Higher values mean better protection. */ +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2) + /* Higher values mean better protection. */ +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index d819a3e8b552..9a507716ae2f 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -229,6 +229,16 @@ struct kvm_vcpu_events { #define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ KVM_REG_ARM_FW | ((r) & 0xffff)) #define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) /* SVE registers */ #define KVM_REG_ARM64_SVE (0x15 << KVM_REG_ARM_COPROC_SHIFT) diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index d6ab5b4d15e5..503d3f42da16 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -378,10 +378,11 @@ struct kvm_sync_regs { struct kvm_vcpu_events events; }; -#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) -#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) -#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) -#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) +#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) +#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) +#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) +#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 /* unused */ @@ -432,4 +433,17 @@ struct kvm_nested_state { } data; }; +/* for KVM_CAP_PMU_EVENT_FILTER */ +struct kvm_pmu_event_filter { + __u32 action; + __u32 nevents; + __u32 fixed_counter_bitmap; + __u32 flags; + __u32 pad[4]; + __u64 events[0]; +}; + +#define KVM_PMU_EVENT_ALLOW 0 +#define KVM_PMU_EVENT_DENY 1 + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index d213ec5c3766..f0b0c90dd398 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -146,7 +146,6 @@ #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2 -#define VMX_ABORT_VMCS_CORRUPTED 3 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 #endif /* _UAPIVMX_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index c2152f3dd02d..a7c19540ce21 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -995,6 +995,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_SVE 170 #define KVM_CAP_ARM_PTRAUTH_ADDRESS 171 #define KVM_CAP_ARM_PTRAUTH_GENERIC 172 +#define KVM_CAP_PMU_EVENT_FILTER 173 #ifdef KVM_CAP_IRQ_ROUTING @@ -1329,6 +1330,8 @@ struct kvm_s390_ucas_mapping { #define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info) /* Available with KVM_CAP_PPC_GET_CPU_CHAR */ #define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char) +/* Available with KVM_CAP_PMU_EVENT_FILTER */ +#define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) From c6c84f78e2f77be37b9a150ed33be992198741f0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 24 Jul 2019 18:26:56 +0200 Subject: [PATCH 438/823] block: fix max segment size handling in blk_queue_virt_boundary We should only set the max segment size to unlimited if we actually have a virt boundary. Otherwise we accidentally clear that limit when called from the SCSI midlayer, which always calls blk_queue_virt_boundary, even if that mask is 0. Fixes: 7ad388d8e4c7 ("scsi: core: add a host / host template field for the virt boundary") Reported-by: Guenter Roeck Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-settings.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block/blk-settings.c b/block/blk-settings.c index 2ae348c101a0..2c1831207a8f 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -752,7 +752,8 @@ void blk_queue_virt_boundary(struct request_queue *q, unsigned long mask) * page (which might not be idential to the Linux PAGE_SIZE). Because * of that they are not limited by our notion of "segment size". */ - q->limits.max_segment_size = UINT_MAX; + if (mask) + q->limits.max_segment_size = UINT_MAX; } EXPORT_SYMBOL(blk_queue_virt_boundary); From 9a07406b00cdc6ec689dc142540739575c717f3c Mon Sep 17 00:00:00 2001 From: Bob Ham Date: Wed, 24 Jul 2019 07:52:27 -0700 Subject: [PATCH 439/823] net: usb: qmi_wwan: Add the BroadMobi BM818 card The BroadMobi BM818 M.2 card uses the QMI protocol Signed-off-by: Bob Ham Signed-off-by: Angus Ainslie (Purism) Signed-off-by: David S. Miller --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 69e0a2acfcb0..b6dc5d714b5e 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1295,6 +1295,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2001, 0x7e3d, 4)}, /* D-Link DWM-222 A2 */ {QMI_FIXED_INTF(0x2020, 0x2031, 4)}, /* Olicard 600 */ {QMI_FIXED_INTF(0x2020, 0x2033, 4)}, /* BroadMobi BM806U */ + {QMI_FIXED_INTF(0x2020, 0x2060, 4)}, /* BroadMobi BM818 */ {QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */ {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */ {QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */ From 81af04b432fdfabcdbd2c06be2ee647e3ca41a22 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Thu, 25 Jul 2019 13:59:55 +0300 Subject: [PATCH 440/823] qed: RDMA - Fix the hw_ver returned in device attributes The hw_ver field was initialized to zero. Return the chip revision. This is relevant for rdma driver. Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_rdma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index 17c64e43d6c3..158ac0738911 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -442,7 +442,7 @@ static void qed_rdma_init_devinfo(struct qed_hwfn *p_hwfn, /* Vendor specific information */ dev->vendor_id = cdev->vendor_id; dev->vendor_part_id = cdev->device_id; - dev->hw_ver = 0; + dev->hw_ver = cdev->chip_rev; dev->fw_ver = (FW_MAJOR_VERSION << 24) | (FW_MINOR_VERSION << 16) | (FW_REVISION_VERSION << 8) | (FW_ENGINEERING_VERSION); From c5d139697d5d9ecf9c7cd92d7d7838a173508900 Mon Sep 17 00:00:00 2001 From: Claudiu Manoil Date: Thu, 25 Jul 2019 16:33:18 +0300 Subject: [PATCH 441/823] ocelot: Cancel delayed work before wq destruction Make sure the delayed work for stats update is not pending before wq destruction. This fixes the module unload path. The issue is there since day 1. Fixes: a556c76adc05 ("net: mscc: Add initial Ocelot switch support") Signed-off-by: Claudiu Manoil Reviewed-by: Alexandre Belloni Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index b71e4ecbe469..6932e615d4b0 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1818,6 +1818,7 @@ EXPORT_SYMBOL(ocelot_init); void ocelot_deinit(struct ocelot *ocelot) { + cancel_delayed_work(&ocelot->stats_work); destroy_workqueue(ocelot->stats_queue); mutex_destroy(&ocelot->stats_lock); ocelot_ace_deinit(); From 01f5bffad555f8e22a61f4b1261fe09cf1b96994 Mon Sep 17 00:00:00 2001 From: Haishuang Yan Date: Fri, 26 Jul 2019 00:40:17 +0800 Subject: [PATCH 442/823] ip6_tunnel: fix possible use-after-free on xmit ip4ip6/ip6ip6 tunnels run iptunnel_handle_offloads on xmit which can cause a possible use-after-free accessing iph/ipv6h pointer since the packet will be 'uncloned' running pskb_expand_head if it is a cloned gso skb. Fixes: 0e9a709560db ("ip6_tunnel, ip6_gre: fix setting of DSCP on encapsulated packets") Signed-off-by: Haishuang Yan Signed-off-by: David S. Miller --- net/ipv6/ip6_tunnel.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 3134fbb65d7f..754a484d35df 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1278,12 +1278,11 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) } fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL); + dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph)); if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; - dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph)); - skb_set_inner_ipproto(skb, IPPROTO_IPIP); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, @@ -1367,12 +1366,11 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) } fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL); + dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h)); if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; - dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h)); - skb_set_inner_ipproto(skb, IPPROTO_IPV6); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, From a7cf3d24ee6081930feb4c830a7f6f16ebe31c49 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Thu, 25 Jul 2019 12:07:12 -0600 Subject: [PATCH 443/823] net: qualcomm: rmnet: Fix incorrect UL checksum offload logic The udp_ip4_ind bit is set only for IPv4 UDP non-fragmented packets so that the hardware can flip the checksum to 0xFFFF if the computed checksum is 0 per RFC768. However, this bit had to be set for IPv6 UDP non fragmented packets as well per hardware requirements. Otherwise, IPv6 UDP packets with computed checksum as 0 were transmitted by hardware and were dropped in the network. In addition to setting this bit for IPv6 UDP, the field is also appropriately renamed to udp_ind as part of this change. Fixes: 5eb5f8608ef1 ("net: qualcomm: rmnet: Add support for TX checksum offload") Cc: Sean Tranchetti Signed-off-by: Subash Abhinov Kasiviswanathan Signed-off-by: David S. Miller --- .../net/ethernet/qualcomm/rmnet/rmnet_map_data.c | 13 +++++++++---- include/linux/if_rmnet.h | 4 ++-- 2 files changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c index 60189923737a..21d38167f961 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c @@ -206,9 +206,9 @@ rmnet_map_ipv4_ul_csum_header(void *iphdr, ul_header->csum_insert_offset = skb->csum_offset; ul_header->csum_enabled = 1; if (ip4h->protocol == IPPROTO_UDP) - ul_header->udp_ip4_ind = 1; + ul_header->udp_ind = 1; else - ul_header->udp_ip4_ind = 0; + ul_header->udp_ind = 0; /* Changing remaining fields to network order */ hdr++; @@ -239,6 +239,7 @@ rmnet_map_ipv6_ul_csum_header(void *ip6hdr, struct rmnet_map_ul_csum_header *ul_header, struct sk_buff *skb) { + struct ipv6hdr *ip6h = (struct ipv6hdr *)ip6hdr; __be16 *hdr = (__be16 *)ul_header, offset; offset = htons((__force u16)(skb_transport_header(skb) - @@ -246,7 +247,11 @@ rmnet_map_ipv6_ul_csum_header(void *ip6hdr, ul_header->csum_start_offset = offset; ul_header->csum_insert_offset = skb->csum_offset; ul_header->csum_enabled = 1; - ul_header->udp_ip4_ind = 0; + + if (ip6h->nexthdr == IPPROTO_UDP) + ul_header->udp_ind = 1; + else + ul_header->udp_ind = 0; /* Changing remaining fields to network order */ hdr++; @@ -419,7 +424,7 @@ sw_csum: ul_header->csum_start_offset = 0; ul_header->csum_insert_offset = 0; ul_header->csum_enabled = 0; - ul_header->udp_ip4_ind = 0; + ul_header->udp_ind = 0; priv->stats.csum_sw++; } diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h index b4f5403383fc..9661416a9bb4 100644 --- a/include/linux/if_rmnet.h +++ b/include/linux/if_rmnet.h @@ -41,11 +41,11 @@ struct rmnet_map_ul_csum_header { __be16 csum_start_offset; #if defined(__LITTLE_ENDIAN_BITFIELD) u16 csum_insert_offset:14; - u16 udp_ip4_ind:1; + u16 udp_ind:1; u16 csum_enabled:1; #elif defined (__BIG_ENDIAN_BITFIELD) u16 csum_enabled:1; - u16 udp_ip4_ind:1; + u16 udp_ind:1; u16 csum_insert_offset:14; #else #error "Please fix " From f1765a1819ff3489db9500c6d464e682e6844a14 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 26 Jul 2019 12:17:44 +0200 Subject: [PATCH 444/823] of: Fix typo in kerneldoc "Findfrom" is not a word. Replace the function synopsis by something that makes sense. Signed-off-by: Thierry Reding Signed-off-by: Rob Herring --- include/linux/of.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/of.h b/include/linux/of.h index 0cf857012f11..844f89e1b039 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1164,7 +1164,7 @@ static inline int of_property_read_string_index(const struct device_node *np, } /** - * of_property_read_bool - Findfrom a property + * of_property_read_bool - Find a property * @np: device node from which the property value is to be read. * @propname: name of the property to be searched. * From c61f0256964b173e4dc71d0e24465ebfd68ef6e1 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 27 Jun 2019 16:10:37 +0100 Subject: [PATCH 445/823] dt-bindings: nvmem: Add YAML schemas for the generic NVMEM bindings The nvmem providers and consumers have a bunch of generic properties that are needed in a device tree. Add a YAML schemas for those. Reviewed-by: Rob Herring Signed-off-by: Maxime Ripard [Srini: Changed licence to (GPL-2.0 OR BSD-2-Clause)] Signed-off-by: Srinivas Kandagatla Signed-off-by: Rob Herring --- .../bindings/nvmem/nvmem-consumer.yaml | 45 +++++++++ .../devicetree/bindings/nvmem/nvmem.txt | 81 +--------------- .../devicetree/bindings/nvmem/nvmem.yaml | 93 +++++++++++++++++++ 3 files changed, 139 insertions(+), 80 deletions(-) create mode 100644 Documentation/devicetree/bindings/nvmem/nvmem-consumer.yaml create mode 100644 Documentation/devicetree/bindings/nvmem/nvmem.yaml diff --git a/Documentation/devicetree/bindings/nvmem/nvmem-consumer.yaml b/Documentation/devicetree/bindings/nvmem/nvmem-consumer.yaml new file mode 100644 index 000000000000..b7c00ed31085 --- /dev/null +++ b/Documentation/devicetree/bindings/nvmem/nvmem-consumer.yaml @@ -0,0 +1,45 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/nvmem/nvmem-consumer.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NVMEM (Non Volatile Memory) Consumer Device Tree Bindings + +maintainers: + - Srinivas Kandagatla + +select: true + +properties: + nvmem: + $ref: /schemas/types.yaml#/definitions/phandle-array + description: + List of phandle to the nvmem providers. + + nvmem-cells: + $ref: /schemas/types.yaml#/definitions/phandle-array + description: + List of phandle to the nvmem data cells. + + nvmem-names: + $ref: /schemas/types.yaml#/definitions/string-array + description: + Names for the each nvmem provider. + + nvmem-cell-names: + $ref: /schemas/types.yaml#/definitions/string-array + description: + Names for each nvmem-cells specified. + +dependencies: + nvmem-names: [ nvmem ] + nvmem-cell-names: [ nvmem-cells ] + +examples: + - | + tsens { + /* ... */ + nvmem-cells = <&tsens_calibration>; + nvmem-cell-names = "calibration"; + }; diff --git a/Documentation/devicetree/bindings/nvmem/nvmem.txt b/Documentation/devicetree/bindings/nvmem/nvmem.txt index fd06c09b822b..46a7ef485e24 100644 --- a/Documentation/devicetree/bindings/nvmem/nvmem.txt +++ b/Documentation/devicetree/bindings/nvmem/nvmem.txt @@ -1,80 +1 @@ -= NVMEM(Non Volatile Memory) Data Device Tree Bindings = - -This binding is intended to represent the location of hardware -configuration data stored in NVMEMs like eeprom, efuses and so on. - -On a significant proportion of boards, the manufacturer has stored -some data on NVMEM, for the OS to be able to retrieve these information -and act upon it. Obviously, the OS has to know about where to retrieve -these data from, and where they are stored on the storage device. - -This document is here to document this. - -= Data providers = -Contains bindings specific to provider drivers and data cells as children -of this node. - -Optional properties: - read-only: Mark the provider as read only. - -= Data cells = -These are the child nodes of the provider which contain data cell -information like offset and size in nvmem provider. - -Required properties: -reg: specifies the offset in byte within the storage device. - -Optional properties: - -bits: Is pair of bit location and number of bits, which specifies offset - in bit and number of bits within the address range specified by reg property. - Offset takes values from 0-7. - -For example: - - /* Provider */ - qfprom: qfprom@700000 { - ... - - /* Data cells */ - tsens_calibration: calib@404 { - reg = <0x404 0x10>; - }; - - tsens_calibration_bckp: calib_bckp@504 { - reg = <0x504 0x11>; - bits = <6 128> - }; - - pvs_version: pvs-version@6 { - reg = <0x6 0x2> - bits = <7 2> - }; - - speed_bin: speed-bin@c{ - reg = <0xc 0x1>; - bits = <2 3>; - - }; - ... - }; - -= Data consumers = -Are device nodes which consume nvmem data cells/providers. - -Required-properties: -nvmem-cells: list of phandle to the nvmem data cells. -nvmem-cell-names: names for the each nvmem-cells specified. Required if - nvmem-cells is used. - -Optional-properties: -nvmem : list of phandles to nvmem providers. -nvmem-names: names for the each nvmem provider. required if nvmem is used. - -For example: - - tsens { - ... - nvmem-cells = <&tsens_calibration>; - nvmem-cell-names = "calibration"; - }; +This file has been moved to nvmem.yaml and nvmem-consumer.yaml. diff --git a/Documentation/devicetree/bindings/nvmem/nvmem.yaml b/Documentation/devicetree/bindings/nvmem/nvmem.yaml new file mode 100644 index 000000000000..1c75a059206c --- /dev/null +++ b/Documentation/devicetree/bindings/nvmem/nvmem.yaml @@ -0,0 +1,93 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/nvmem/nvmem.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NVMEM (Non Volatile Memory) Device Tree Bindings + +maintainers: + - Srinivas Kandagatla + +description: | + This binding is intended to represent the location of hardware + configuration data stored in NVMEMs like eeprom, efuses and so on. + + On a significant proportion of boards, the manufacturer has stored + some data on NVMEM, for the OS to be able to retrieve these + information and act upon it. Obviously, the OS has to know about + where to retrieve these data from, and where they are stored on the + storage device. + +properties: + $nodename: + pattern: "^(eeprom|efuse|nvram)(@.*|-[0-9a-f])*$" + + "#address-cells": + const: 1 + + "#size-cells": + const: 1 + + read-only: + $ref: /schemas/types.yaml#/definitions/flag + description: + Mark the provider as read only. + +patternProperties: + "^.*@[0-9a-f]+$": + type: object + + properties: + reg: + maxItems: 1 + description: + Offset and size in bytes within the storage device. + + bits: + maxItems: 1 + items: + items: + - minimum: 0 + maximum: 7 + description: + Offset in bit within the address range specified by reg. + - minimum: 1 + description: + Size in bit within the address range specified by reg. + + required: + - reg + + additionalProperties: false + +examples: + - | + qfprom: eeprom@700000 { + #address-cells = <1>; + #size-cells = <1>; + + /* ... */ + + /* Data cells */ + tsens_calibration: calib@404 { + reg = <0x404 0x10>; + }; + + tsens_calibration_bckp: calib_bckp@504 { + reg = <0x504 0x11>; + bits = <6 128>; + }; + + pvs_version: pvs-version@6 { + reg = <0x6 0x2>; + bits = <7 2>; + }; + + speed_bin: speed-bin@c{ + reg = <0xc 0x1>; + bits = <2 3>; + }; + }; + +... From ce842e73bccfc61e851c68e155d6365456a4cc16 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Wed, 3 Jul 2019 11:54:21 +0200 Subject: [PATCH 446/823] dt-bindings: nvmem: SID: Fix the examples node names Now that the examples are validated, the examples in the SID binding generates an error since the node names aren't one of the valid ones. Let's switch for one that is ok. Signed-off-by: Maxime Ripard Signed-off-by: Rob Herring --- .../devicetree/bindings/nvmem/allwinner,sun4i-a10-sid.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/nvmem/allwinner,sun4i-a10-sid.yaml b/Documentation/devicetree/bindings/nvmem/allwinner,sun4i-a10-sid.yaml index c9efd6e2c134..1084e9d2917d 100644 --- a/Documentation/devicetree/bindings/nvmem/allwinner,sun4i-a10-sid.yaml +++ b/Documentation/devicetree/bindings/nvmem/allwinner,sun4i-a10-sid.yaml @@ -37,13 +37,13 @@ required: examples: - | - sid@1c23800 { + efuse@1c23800 { compatible = "allwinner,sun4i-a10-sid"; reg = <0x01c23800 0x10>; }; - | - sid@1c23800 { + efuse@1c23800 { compatible = "allwinner,sun7i-a20-sid"; reg = <0x01c23800 0x200>; }; From e1ff7390f58e609aa113a2452a953f669abce6cc Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 26 Jul 2019 17:36:52 -0600 Subject: [PATCH 447/823] dt-bindings: Fix more $id value mismatches filenames The path in the schema '$id' values are wrong. Fix them. Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/arm/renesas.yaml | 2 +- Documentation/devicetree/bindings/arm/socionext/milbeaut.yaml | 2 +- Documentation/devicetree/bindings/arm/ti/ti,davinci.yaml | 2 +- .../firmware/intel,ixp4xx-network-processing-engine.yaml | 2 +- Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml | 2 +- Documentation/devicetree/bindings/iio/accel/adi,adxl372.yaml | 2 +- .../bindings/interrupt-controller/intel,ixp4xx-interrupt.yaml | 2 +- ...x-queue-manager.yaml => intel,ixp4xx-ahb-queue-manager.yaml} | 2 +- .../devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml | 2 +- .../devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml | 2 +- Documentation/devicetree/bindings/timer/intel,ixp4xx-timer.yaml | 2 +- 11 files changed, 11 insertions(+), 11 deletions(-) rename Documentation/devicetree/bindings/misc/{intel,ixp4xx-queue-manager.yaml => intel,ixp4xx-ahb-queue-manager.yaml} (95%) diff --git a/Documentation/devicetree/bindings/arm/renesas.yaml b/Documentation/devicetree/bindings/arm/renesas.yaml index 08c923f8c257..28eb458f761a 100644 --- a/Documentation/devicetree/bindings/arm/renesas.yaml +++ b/Documentation/devicetree/bindings/arm/renesas.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/arm/shmobile.yaml# +$id: http://devicetree.org/schemas/arm/renesas.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Renesas SH-Mobile, R-Mobile, and R-Car Platform Device Tree Bindings diff --git a/Documentation/devicetree/bindings/arm/socionext/milbeaut.yaml b/Documentation/devicetree/bindings/arm/socionext/milbeaut.yaml index aae53fc3cb1e..2bd519d2e855 100644 --- a/Documentation/devicetree/bindings/arm/socionext/milbeaut.yaml +++ b/Documentation/devicetree/bindings/arm/socionext/milbeaut.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/arm/milbeaut.yaml# +$id: http://devicetree.org/schemas/arm/socionext/milbeaut.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Milbeaut platforms device tree bindings diff --git a/Documentation/devicetree/bindings/arm/ti/ti,davinci.yaml b/Documentation/devicetree/bindings/arm/ti/ti,davinci.yaml index 4326d2cfa15d..a8765ba29476 100644 --- a/Documentation/devicetree/bindings/arm/ti/ti,davinci.yaml +++ b/Documentation/devicetree/bindings/arm/ti/ti,davinci.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/arm/ti/davinci.yaml# +$id: http://devicetree.org/schemas/arm/ti/ti,davinci.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Texas Instruments DaVinci Platforms Device Tree Bindings diff --git a/Documentation/devicetree/bindings/firmware/intel,ixp4xx-network-processing-engine.yaml b/Documentation/devicetree/bindings/firmware/intel,ixp4xx-network-processing-engine.yaml index 8cb136c376fb..4f0db8ee226a 100644 --- a/Documentation/devicetree/bindings/firmware/intel,ixp4xx-network-processing-engine.yaml +++ b/Documentation/devicetree/bindings/firmware/intel,ixp4xx-network-processing-engine.yaml @@ -2,7 +2,7 @@ # Copyright 2019 Linaro Ltd. %YAML 1.2 --- -$id: "http://devicetree.org/schemas/firmware/intel-ixp4xx-network-processing-engine.yaml#" +$id: "http://devicetree.org/schemas/firmware/intel,ixp4xx-network-processing-engine.yaml#" $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Intel IXP4xx Network Processing Engine diff --git a/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml b/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml index 7ba167e2e1ea..c602b6fe1c0c 100644 --- a/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml +++ b/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/iio/accelerometers/adi,adxl345.yaml# +$id: http://devicetree.org/schemas/iio/accel/adi,adxl345.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Analog Devices ADXL345/ADXL375 3-Axis Digital Accelerometers diff --git a/Documentation/devicetree/bindings/iio/accel/adi,adxl372.yaml b/Documentation/devicetree/bindings/iio/accel/adi,adxl372.yaml index a7fafb9bf5c6..e7daffec88d3 100644 --- a/Documentation/devicetree/bindings/iio/accel/adi,adxl372.yaml +++ b/Documentation/devicetree/bindings/iio/accel/adi,adxl372.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/iio/accelerometers/adi,adxl372.yaml# +$id: http://devicetree.org/schemas/iio/accel/adi,adxl372.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Analog Devices ADXL372 3-Axis, +/-(200g) Digital Accelerometer diff --git a/Documentation/devicetree/bindings/interrupt-controller/intel,ixp4xx-interrupt.yaml b/Documentation/devicetree/bindings/interrupt-controller/intel,ixp4xx-interrupt.yaml index bae10e261fa9..507c141ea760 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/intel,ixp4xx-interrupt.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/intel,ixp4xx-interrupt.yaml @@ -2,7 +2,7 @@ # Copyright 2018 Linaro Ltd. %YAML 1.2 --- -$id: "http://devicetree.org/schemas/interrupt/intel-ixp4xx-interrupt.yaml#" +$id: "http://devicetree.org/schemas/interrupt-controller/intel,ixp4xx-interrupt.yaml#" $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Intel IXP4xx XScale Networking Processors Interrupt Controller diff --git a/Documentation/devicetree/bindings/misc/intel,ixp4xx-queue-manager.yaml b/Documentation/devicetree/bindings/misc/intel,ixp4xx-ahb-queue-manager.yaml similarity index 95% rename from Documentation/devicetree/bindings/misc/intel,ixp4xx-queue-manager.yaml rename to Documentation/devicetree/bindings/misc/intel,ixp4xx-ahb-queue-manager.yaml index d2313b1d9405..0ea21a6f70b4 100644 --- a/Documentation/devicetree/bindings/misc/intel,ixp4xx-queue-manager.yaml +++ b/Documentation/devicetree/bindings/misc/intel,ixp4xx-ahb-queue-manager.yaml @@ -2,7 +2,7 @@ # Copyright 2019 Linaro Ltd. %YAML 1.2 --- -$id: "http://devicetree.org/schemas/misc/intel-ixp4xx-ahb-queue-manager.yaml#" +$id: "http://devicetree.org/schemas/misc/intel,ixp4xx-ahb-queue-manager.yaml#" $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Intel IXP4xx AHB Queue Manager diff --git a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml index d4084c149768..3fb0714e761e 100644 --- a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml +++ b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/net/allwinner,sun8i-a83t-gmac.yaml# +$id: http://devicetree.org/schemas/net/allwinner,sun8i-a83t-emac.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Allwinner A83t EMAC Device Tree Bindings diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml index 250f9d5aabdf..fa46670de299 100644 --- a/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml +++ b/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/display/allwinner,sun6i-a31-mipi-dphy.yaml# +$id: http://devicetree.org/schemas/phy/allwinner,sun6i-a31-mipi-dphy.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Allwinner A31 MIPI D-PHY Controller Device Tree Bindings diff --git a/Documentation/devicetree/bindings/timer/intel,ixp4xx-timer.yaml b/Documentation/devicetree/bindings/timer/intel,ixp4xx-timer.yaml index a36a0746c056..2807225db902 100644 --- a/Documentation/devicetree/bindings/timer/intel,ixp4xx-timer.yaml +++ b/Documentation/devicetree/bindings/timer/intel,ixp4xx-timer.yaml @@ -2,7 +2,7 @@ # Copyright 2018 Linaro Ltd. %YAML 1.2 --- -$id: "http://devicetree.org/schemas/timer/intel-ixp4xx-timer.yaml#" +$id: "http://devicetree.org/schemas/timer/intel,ixp4xx-timer.yaml#" $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Intel IXP4xx XScale Networking Processors Timers From 543b8c468f55f27f3c0178a22a91a51aabbbc428 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Wed, 17 Jul 2019 18:31:53 -0700 Subject: [PATCH 448/823] f2fs: fix to read source block before invalidating it f2fs_allocate_data_block() invalidates old block address and enable new block address. Then, if we try to read old block by f2fs_submit_page_bio(), it will give WARN due to reading invalid blocks. Let's make the order sanely back. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/gc.c | 70 +++++++++++++++++++++++++--------------------------- 1 file changed, 34 insertions(+), 36 deletions(-) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 6691f526fa40..8974672db78f 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -796,6 +796,29 @@ static int move_data_block(struct inode *inode, block_t bidx, if (lfs_mode) down_write(&fio.sbi->io_order_lock); + mpage = f2fs_grab_cache_page(META_MAPPING(fio.sbi), + fio.old_blkaddr, false); + if (!mpage) + goto up_out; + + fio.encrypted_page = mpage; + + /* read source block in mpage */ + if (!PageUptodate(mpage)) { + err = f2fs_submit_page_bio(&fio); + if (err) { + f2fs_put_page(mpage, 1); + goto up_out; + } + lock_page(mpage); + if (unlikely(mpage->mapping != META_MAPPING(fio.sbi) || + !PageUptodate(mpage))) { + err = -EIO; + f2fs_put_page(mpage, 1); + goto up_out; + } + } + f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr, &sum, CURSEG_COLD_DATA, NULL, false); @@ -803,44 +826,18 @@ static int move_data_block(struct inode *inode, block_t bidx, newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS); if (!fio.encrypted_page) { err = -ENOMEM; + f2fs_put_page(mpage, 1); goto recover_block; } - mpage = f2fs_pagecache_get_page(META_MAPPING(fio.sbi), - fio.old_blkaddr, FGP_LOCK, GFP_NOFS); - if (mpage) { - bool updated = false; - - if (PageUptodate(mpage)) { - memcpy(page_address(fio.encrypted_page), - page_address(mpage), PAGE_SIZE); - updated = true; - } - f2fs_put_page(mpage, 1); - invalidate_mapping_pages(META_MAPPING(fio.sbi), - fio.old_blkaddr, fio.old_blkaddr); - if (updated) - goto write_page; - } - - err = f2fs_submit_page_bio(&fio); - if (err) - goto put_page_out; - - /* write page */ - lock_page(fio.encrypted_page); - - if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) { - err = -EIO; - goto put_page_out; - } - if (unlikely(!PageUptodate(fio.encrypted_page))) { - err = -EIO; - goto put_page_out; - } - -write_page: + /* write target block */ f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true, true); + memcpy(page_address(fio.encrypted_page), + page_address(mpage), PAGE_SIZE); + f2fs_put_page(mpage, 1); + invalidate_mapping_pages(META_MAPPING(fio.sbi), + fio.old_blkaddr, fio.old_blkaddr); + set_page_dirty(fio.encrypted_page); if (clear_page_dirty_for_io(fio.encrypted_page)) dec_page_count(fio.sbi, F2FS_DIRTY_META); @@ -871,11 +868,12 @@ write_page: put_page_out: f2fs_put_page(fio.encrypted_page, 1); recover_block: - if (lfs_mode) - up_write(&fio.sbi->io_order_lock); if (err) f2fs_do_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr, true, true); +up_out: + if (lfs_mode) + up_write(&fio.sbi->io_order_lock); put_out: f2fs_put_dnode(&dn); out: From b2eff0921805935132bc308d3c769ef2efb321ad Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 23 Jul 2019 13:11:26 +0900 Subject: [PATCH 449/823] kbuild: remove unused objectify macro Commit 415008af3219 ("docs-rst: convert lsm from DocBook to ReST") removed the last users of this macro. Signed-off-by: Masahiro Yamada --- scripts/Kbuild.include | 3 --- 1 file changed, 3 deletions(-) diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include index 77c742fa4fb1..4b0432e095ae 100644 --- a/scripts/Kbuild.include +++ b/scripts/Kbuild.include @@ -190,9 +190,6 @@ echo-cmd = $(if $($(quiet)cmd_$(1)),\ # printing commands cmd = @set -e; $(echo-cmd) $(cmd_$(1)) -# Add $(obj)/ for paths that are not absolute -objectify = $(foreach o,$(1),$(if $(filter /%,$(o)),$(o),$(obj)/$(o))) - ### # if_changed - execute command if any prerequisite is newer than # target, or command line has changed From 26c4c71bcd9a9f2baf8334995b31f718854f7f42 Mon Sep 17 00:00:00 2001 From: Toru Komatsu Date: Wed, 24 Jul 2019 09:22:33 +0900 Subject: [PATCH 450/823] .gitignore: Add compilation database file This file is used by clangd to use language server protocol. It can be generated at each compile using scripts/gen_compile_commands.py. Therefore it is different depending on the environment and should be ignored. Signed-off-by: Toru Komatsu Reviewed-by: Nick Desaulniers Signed-off-by: Masahiro Yamada --- .gitignore | 3 +++ 1 file changed, 3 insertions(+) diff --git a/.gitignore b/.gitignore index 8f5422cba6e2..2030c7a4d2f8 100644 --- a/.gitignore +++ b/.gitignore @@ -142,3 +142,6 @@ x509.genkey # Kdevelop4 *.kdev4 + +# Clang's compilation database file +/compile_commands.json From cb36955a5569f1ff17a42ae93264ef391c013a97 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 27 Jul 2019 12:01:10 +0900 Subject: [PATCH 451/823] gen_compile_commands: lower the entry count threshold Running gen_compile_commands.py after building the kernel with allnoconfig gave this: $ ./scripts/gen_compile_commands.py WARNING: Found 449 entries. Have you compiled the kernel? Signed-off-by: Masahiro Yamada --- scripts/gen_compile_commands.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scripts/gen_compile_commands.py b/scripts/gen_compile_commands.py index 7915823b92a5..c458696ef3a7 100755 --- a/scripts/gen_compile_commands.py +++ b/scripts/gen_compile_commands.py @@ -21,9 +21,9 @@ _LINE_PATTERN = r'^cmd_[^ ]*\.o := (.* )([^ ]*\.c)$' _VALID_LOG_LEVELS = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'] # A kernel build generally has over 2000 entries in its compile_commands.json -# database. If this code finds 500 or fewer, then warn the user that they might +# database. If this code finds 300 or fewer, then warn the user that they might # not have all the .cmd files, and they might need to compile the kernel. -_LOW_COUNT_THRESHOLD = 500 +_LOW_COUNT_THRESHOLD = 300 def parse_arguments(): From b25e8a23d4ea7e8ade2c349c22efe88da88c0988 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 26 Jul 2019 11:17:38 +0900 Subject: [PATCH 452/823] kbuild: remove unused single-used-m This is unused since commit 9f69a496f100 ("kbuild: split out *.mod out of {single,multi}-used-m rules"). Signed-off-by: Masahiro Yamada --- scripts/Makefile.lib | 2 -- 1 file changed, 2 deletions(-) diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 5241d0751eb0..41c50f9461e5 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -45,7 +45,6 @@ subdir-ym := $(sort $(subdir-y) $(subdir-m)) multi-used-y := $(sort $(foreach m,$(obj-y), $(if $(strip $($(m:.o=-objs)) $($(m:.o=-y))), $(m)))) multi-used-m := $(sort $(foreach m,$(obj-m), $(if $(strip $($(m:.o=-objs)) $($(m:.o=-y)) $($(m:.o=-m))), $(m)))) multi-used := $(multi-used-y) $(multi-used-m) -single-used-m := $(sort $(filter-out $(multi-used-m),$(obj-m))) # $(subdir-obj-y) is the list of objects in $(obj-y) which uses dir/ to # tell kbuild to descend @@ -91,7 +90,6 @@ lib-y := $(addprefix $(obj)/,$(lib-y)) subdir-obj-y := $(addprefix $(obj)/,$(subdir-obj-y)) real-obj-y := $(addprefix $(obj)/,$(real-obj-y)) real-obj-m := $(addprefix $(obj)/,$(real-obj-m)) -single-used-m := $(addprefix $(obj)/,$(single-used-m)) multi-used-m := $(addprefix $(obj)/,$(multi-used-m)) subdir-ym := $(addprefix $(obj)/,$(subdir-ym)) From 74bf71ed792ab0f64631cc65ccdb54c356c36d45 Mon Sep 17 00:00:00 2001 From: Samuel Thibault Date: Fri, 26 Jul 2019 23:47:02 +0200 Subject: [PATCH 453/823] ALSA: hda: Fix 1-minute detection delay when i915 module is not available Distribution installation images such as Debian include different sets of modules which can be downloaded dynamically. Such images may notably include the hda sound modules but not the i915 DRM module, even if the latter was enabled at build time, as reported on https://bugs.debian.org/931507 In such a case hdac_i915 would be linked in and try to load the i915 module, fail since it is not there, but still wait for a whole minute before giving up binding with it. This fixes such as case by only waiting for the binding if the module was properly loaded (or module support is disabled, in which case i915 is already compiled-in anyway). Fixes: f9b54e1961c7 ("ALSA: hda/i915: Allow delayed i915 audio component binding") Signed-off-by: Samuel Thibault Cc: Signed-off-by: Takashi Iwai --- sound/hda/hdac_i915.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c index 1192c7561d62..3c2db3816029 100644 --- a/sound/hda/hdac_i915.c +++ b/sound/hda/hdac_i915.c @@ -136,10 +136,12 @@ int snd_hdac_i915_init(struct hdac_bus *bus) if (!acomp) return -ENODEV; if (!acomp->ops) { - request_module("i915"); - /* 60s timeout */ - wait_for_completion_timeout(&bind_complete, - msecs_to_jiffies(60 * 1000)); + if (!IS_ENABLED(CONFIG_MODULES) || + !request_module("i915")) { + /* 60s timeout */ + wait_for_completion_timeout(&bind_complete, + msecs_to_jiffies(60 * 1000)); + } } if (!acomp->ops) { dev_info(bus->dev, "couldn't bind with audio component\n"); From a0d57a552b836206ad7705a1060e6e1ce5a38203 Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Fri, 26 Jul 2019 16:27:36 +0800 Subject: [PATCH 454/823] isdn: mISDN: hfcsusb: Fix possible null-pointer dereferences in start_isoc_chain() In start_isoc_chain(), usb_alloc_urb() on line 1392 may fail and return NULL. At this time, fifo->iso[i].urb is assigned to NULL. Then, fifo->iso[i].urb is used at some places, such as: LINE 1405: fill_isoc_urb(fifo->iso[i].urb, ...) urb->number_of_packets = num_packets; urb->transfer_flags = URB_ISO_ASAP; urb->actual_length = 0; urb->interval = interval; LINE 1416: fifo->iso[i].urb->... LINE 1419: fifo->iso[i].urb->... Thus, possible null-pointer dereferences may occur. To fix these bugs, "continue" is added to avoid using fifo->iso[i].urb when it is NULL. These bugs are found by a static analysis tool STCheck written by us. Signed-off-by: Jia-Ju Bai Signed-off-by: David S. Miller --- drivers/isdn/hardware/mISDN/hfcsusb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c index 0e224232f746..8fb7c5dea07f 100644 --- a/drivers/isdn/hardware/mISDN/hfcsusb.c +++ b/drivers/isdn/hardware/mISDN/hfcsusb.c @@ -1394,6 +1394,7 @@ start_isoc_chain(struct usb_fifo *fifo, int num_packets_per_urb, printk(KERN_DEBUG "%s: %s: alloc urb for fifo %i failed", hw->name, __func__, fifo->fifonum); + continue; } fifo->iso[i].owner_fifo = (struct usb_fifo *) fifo; fifo->iso[i].indx = i; From c7ba50fe2399f0621fae39eb6f5e6abfbb83c38d Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Fri, 26 Jul 2019 22:17:05 +0800 Subject: [PATCH 455/823] net: rds: Fix possible null-pointer dereferences in rds_rdma_cm_event_handler_cmn() In rds_rdma_cm_event_handler_cmn(), there are some if statements to check whether conn is NULL, such as on lines 65, 96 and 112. But conn is not checked before being used on line 108: trans->cm_connect_complete(conn, event); and on lines 140-143: rdsdebug("DISCONNECT event - dropping connection " "%pI6c->%pI6c\n", &conn->c_laddr, &conn->c_faddr); rds_conn_drop(conn); Thus, possible null-pointer dereferences may occur. To fix these bugs, conn is checked before being used. These bugs are found by a static analysis tool STCheck written by us. Signed-off-by: Jia-Ju Bai Acked-by: Santosh Shilimkar Signed-off-by: David S. Miller --- net/rds/rdma_transport.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index ff74c4bbb9fc..9986d6065c4d 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -105,7 +105,8 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_ESTABLISHED: - trans->cm_connect_complete(conn, event); + if (conn) + trans->cm_connect_complete(conn, event); break; case RDMA_CM_EVENT_REJECTED: @@ -137,6 +138,8 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_DISCONNECTED: + if (!conn) + break; rdsdebug("DISCONNECT event - dropping connection " "%pI6c->%pI6c\n", &conn->c_laddr, &conn->c_faddr); From 3db1fa8bb489370b6df634a3d548728294139d66 Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Sat, 27 Jul 2019 00:05:41 +0200 Subject: [PATCH 456/823] gigaset: stop maintaining seperately The Dutch consumer grade ISDN network will be shut down on September 1, 2019. This means I'll be converted to some sort of VOIP shortly. At that point it would be unwise to try to maintain the gigaset driver, even for odd fixes as I do. So I'll stop maintaining it as a seperate driver and bump support to CAPI in staging. De facto this means the driver will be unmaintained, since no-one seems to be working on CAPI. I've lighty tested the hardware specific modules of this driver (bas-gigaset, ser-gigaset, and usb-gigaset) for v5.3-rc1. The basic functionality appears to be working. It's unclear whether anyone still cares. I'm aware of only one person sort of using the driver a few years ago. Thanks to Karsten Keil for the ISDN subsystems gigaset was using (I4L and CAPI). And many thanks to Hansjoerg Lipp and Tilman Schmidt for writing and upstreaming this driver. Signed-off-by: Paul Bolle Signed-off-by: David S. Miller --- MAINTAINERS | 7 ------- 1 file changed, 7 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 3ff2e6ab3cf4..bbc2efb2b236 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6822,13 +6822,6 @@ F: Documentation/filesystems/gfs2*.txt F: fs/gfs2/ F: include/uapi/linux/gfs2_ondisk.h -GIGASET ISDN DRIVERS -M: Paul Bolle -L: gigaset307x-common@lists.sourceforge.net -W: http://gigaset307x.sourceforge.net/ -S: Odd Fixes -F: drivers/staging/isdn/gigaset/ - GNSS SUBSYSTEM M: Johan Hovold T: git git://git.kernel.org/pub/scm/linux/kernel/git/johan/gnss.git From 8aace4f3eba2a3ceb431e18683ea0e1ecbade5cd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ren=C3=A9=20van=20Dorst?= Date: Sat, 27 Jul 2019 11:40:11 +0200 Subject: [PATCH 457/823] net: phylink: Fix flow control for fixed-link MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In phylink_parse_fixedlink() the pl->link_config.advertising bits are AND with pl->supported, pl->supported is zeroed and only the speed/duplex modes and MII bits are set. So pl->link_config.advertising always loses the flow control/pause bits. By setting Pause and Asym_Pause bits in pl->supported, the flow control work again when devicetree "pause" is set in fixes-link node and the MAC advertise that is supports pause. Results with this patch. Legend: - DT = 'Pause' is set in the fixed-link in devicetree. - validate() = ‘Yes’ means phylink_set(mask, Pause) is set in the validate(). - flow = results reported my link is Up line. +-----+------------+-------+ | DT | validate() | flow | +-----+------------+-------+ | Yes | Yes | rx/tx | | No | Yes | off | | Yes | No | off | +-----+------------+-------+ Fixes: 9525ae83959b ("phylink: add phylink infrastructure") Signed-off-by: René van Dorst Acked-by: Russell King Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index b45862465c4d..a45c5de96ab1 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -216,6 +216,8 @@ static int phylink_parse_fixedlink(struct phylink *pl, pl->supported, true); linkmode_zero(pl->supported); phylink_set(pl->supported, MII); + phylink_set(pl->supported, Pause); + phylink_set(pl->supported, Asym_Pause); if (s) { __set_bit(s->bit, pl->supported); } else { From 66058b1ca5651c7671bf2ba27fcf6907fb20bd0b Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 27 Jul 2019 12:32:28 +0200 Subject: [PATCH 458/823] Revert ("r8169: remove 1000/Half from supported modes") This reverts commit a6851c613fd7fccc5d1f28d5d8a0cbe9b0f4e8cc. It was reported that RTL8111b successfully finishes 1000/Full autoneg but no data flows. Reverting the original patch fixes the issue. It seems to be a HW issue with the integrated RTL8211B PHY. This PHY version used also e.g. on RTL8168d, so better revert the original patch. Reported-by: Bernhard Held Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169_main.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 6272115b2848..a71dd669a728 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -6136,10 +6136,7 @@ static int r8169_phy_connect(struct rtl8169_private *tp) if (ret) return ret; - if (tp->supports_gmii) - phy_remove_link_mode(phydev, - ETHTOOL_LINK_MODE_1000baseT_Half_BIT); - else + if (!tp->supports_gmii) phy_set_max_speed(phydev, SPEED_100); phy_support_asym_pause(phydev); From 003bd5b4a7b4a94b501e3a1e2e7c9df6b2a94ed4 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 27 Jul 2019 12:43:31 +0200 Subject: [PATCH 459/823] r8169: don't use MSI before RTL8168d MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It was reported that after resuming from suspend network fails with error "do_IRQ: 3.38 No irq handler for vector", see [0]. Enabling WoL can work around the issue, but the only actual fix is to disable MSI. So let's mimic the behavior of the vendor driver and disable MSI on all chip versions before RTL8168d. [0] https://bugzilla.kernel.org/show_bug.cgi?id=204079 Fixes: 6c6aa15fdea5 ("r8169: improve interrupt handling") Reported-by: Dušan Dragić Tested-by: Dušan Dragić Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169_main.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index a71dd669a728..e1dd6ea60d67 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -6586,13 +6586,18 @@ static int rtl_alloc_irq(struct rtl8169_private *tp) { unsigned int flags; - if (tp->mac_version <= RTL_GIGA_MAC_VER_06) { + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06: rtl_unlock_config_regs(tp); RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable); rtl_lock_config_regs(tp); + /* fall through */ + case RTL_GIGA_MAC_VER_07 ... RTL_GIGA_MAC_VER_24: flags = PCI_IRQ_LEGACY; - } else { + break; + default: flags = PCI_IRQ_ALL_TYPES; + break; } return pci_alloc_irq_vectors(tp->pci_dev, 1, 1, flags); From ffe0bbabb0cffceceae07484fde1ec2a63b1537c Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 8 Jul 2019 10:23:43 +0200 Subject: [PATCH 460/823] gpio: don't WARN() on NULL descs if gpiolib is disabled If gpiolib is disabled, we use the inline stubs from gpio/consumer.h instead of regular definitions of GPIO API. The stubs for 'optional' variants of gpiod_get routines return NULL in this case as if the relevant GPIO wasn't found. This is correct so far. Calling other (non-gpio_get) stubs from this header triggers a warning because the GPIO descriptor couldn't have been requested. The warning however is unconditional (WARN_ON(1)) and is emitted even if the passed descriptor pointer is NULL. We don't want to force the users of 'optional' gpio_get to check the returned pointer before calling e.g. gpiod_set_value() so let's only WARN on non-NULL descriptors. Cc: stable@vger.kernel.org Reported-by: Claus H. Stovgaard Signed-off-by: Bartosz Golaszewski --- include/linux/gpio/consumer.h | 64 +++++++++++++++++------------------ 1 file changed, 32 insertions(+), 32 deletions(-) diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 9ddcf50a3c59..a7f08fb0f865 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -247,7 +247,7 @@ static inline void gpiod_put(struct gpio_desc *desc) might_sleep(); /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); } static inline void devm_gpiod_unhinge(struct device *dev, @@ -256,7 +256,7 @@ static inline void devm_gpiod_unhinge(struct device *dev, might_sleep(); /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); } static inline void gpiod_put_array(struct gpio_descs *descs) @@ -264,7 +264,7 @@ static inline void gpiod_put_array(struct gpio_descs *descs) might_sleep(); /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(descs); } static inline struct gpio_desc *__must_check @@ -317,7 +317,7 @@ static inline void devm_gpiod_put(struct device *dev, struct gpio_desc *desc) might_sleep(); /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); } static inline void devm_gpiod_put_array(struct device *dev, @@ -326,32 +326,32 @@ static inline void devm_gpiod_put_array(struct device *dev, might_sleep(); /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(descs); } static inline int gpiod_get_direction(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -ENOSYS; } static inline int gpiod_direction_input(struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -ENOSYS; } static inline int gpiod_direction_output(struct gpio_desc *desc, int value) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -ENOSYS; } static inline int gpiod_direction_output_raw(struct gpio_desc *desc, int value) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -ENOSYS; } @@ -359,7 +359,7 @@ static inline int gpiod_direction_output_raw(struct gpio_desc *desc, int value) static inline int gpiod_get_value(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return 0; } static inline int gpiod_get_array_value(unsigned int array_size, @@ -368,13 +368,13 @@ static inline int gpiod_get_array_value(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline void gpiod_set_value(struct gpio_desc *desc, int value) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); } static inline int gpiod_set_array_value(unsigned int array_size, struct gpio_desc **desc_array, @@ -382,13 +382,13 @@ static inline int gpiod_set_array_value(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline int gpiod_get_raw_value(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return 0; } static inline int gpiod_get_raw_array_value(unsigned int array_size, @@ -397,13 +397,13 @@ static inline int gpiod_get_raw_array_value(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); } static inline int gpiod_set_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, @@ -411,14 +411,14 @@ static inline int gpiod_set_raw_array_value(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline int gpiod_get_value_cansleep(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return 0; } static inline int gpiod_get_array_value_cansleep(unsigned int array_size, @@ -427,13 +427,13 @@ static inline int gpiod_get_array_value_cansleep(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); } static inline int gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, @@ -441,13 +441,13 @@ static inline int gpiod_set_array_value_cansleep(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return 0; } static inline int gpiod_get_raw_array_value_cansleep(unsigned int array_size, @@ -456,14 +456,14 @@ static inline int gpiod_get_raw_array_value_cansleep(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); } static inline int gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, @@ -471,41 +471,41 @@ static inline int gpiod_set_raw_array_value_cansleep(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -ENOSYS; } static inline int gpiod_set_transitory(struct gpio_desc *desc, bool transitory) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -ENOSYS; } static inline int gpiod_is_active_low(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return 0; } static inline int gpiod_cansleep(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return 0; } static inline int gpiod_to_irq(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -EINVAL; } @@ -513,7 +513,7 @@ static inline int gpiod_set_consumer_name(struct gpio_desc *desc, const char *name) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -EINVAL; } @@ -525,7 +525,7 @@ static inline struct gpio_desc *gpio_to_desc(unsigned gpio) static inline int desc_to_gpio(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -EINVAL; } From 25e5ef302c24a6fead369c0cfe88c073d7b97ca8 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 28 Jul 2019 18:41:38 +0200 Subject: [PATCH 461/823] eeprom: at24: make spd world-readable again The integration of the at24 driver into the nvmem framework broke the world-readability of spd EEPROMs. Fix it. Signed-off-by: Jean Delvare Cc: stable@vger.kernel.org Fixes: 57d155506dd5 ("eeprom: at24: extend driver to plug into the NVMEM framework") Cc: Andrew Lunn Cc: Srinivas Kandagatla Cc: Greg Kroah-Hartman Cc: Bartosz Golaszewski Cc: Arnd Bergmann Signed-off-by: Bartosz Golaszewski --- drivers/misc/eeprom/at24.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 35bf2477693d..518945b2f737 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -685,7 +685,7 @@ static int at24_probe(struct i2c_client *client) nvmem_config.name = dev_name(dev); nvmem_config.dev = dev; nvmem_config.read_only = !writable; - nvmem_config.root_only = true; + nvmem_config.root_only = !(flags & AT24_FLAG_IRUGO); nvmem_config.owner = THIS_MODULE; nvmem_config.compat = true; nvmem_config.base_dev = dev; From f36cf386e3fec258a341d446915862eded3e13d8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 17 Jul 2019 21:18:59 +0200 Subject: [PATCH 462/823] x86/speculation/swapgs: Exclude ATOMs from speculation through SWAPGS Intel provided the following information: On all current Atom processors, instructions that use a segment register value (e.g. a load or store) will not speculatively execute before the last writer of that segment retires. Thus they will not use a speculatively written segment value. That means on ATOMs there is no speculation through SWAPGS, so the SWAPGS entry paths can be excluded from the extra LFENCE if PTI is disabled. Create a separate bug flag for the through SWAPGS speculation and mark all out-of-order ATOMs and AMD/HYGON CPUs as not affected. The in-order ATOMs are excluded from the whole mitigation mess anyway. Reported-by: Andrew Cooper Signed-off-by: Thomas Gleixner Reviewed-by: Tyler Hicks Reviewed-by: Josh Poimboeuf --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/kernel/cpu/bugs.c | 18 +++--------- arch/x86/kernel/cpu/common.c | 44 +++++++++++++++++++----------- 3 files changed, 33 insertions(+), 30 deletions(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 4393278666d9..e880f2408e29 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -396,5 +396,6 @@ #define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */ #define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ #define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ +#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 992f832c447b..6383f0db098c 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -284,18 +284,6 @@ static const char * const spectre_v1_strings[] = { [SPECTRE_V1_MITIGATION_AUTO] = "Mitigation: usercopy/swapgs barriers and __user pointer sanitization", }; -static bool is_swapgs_serializing(void) -{ - /* - * Technically, swapgs isn't serializing on AMD (despite it previously - * being documented as such in the APM). But according to AMD, %gs is - * updated non-speculatively, and the issuing of %gs-relative memory - * operands will be blocked until the %gs update completes, which is - * good enough for our purposes. - */ - return boot_cpu_data.x86_vendor == X86_VENDOR_AMD; -} - /* * Does SMAP provide full mitigation against speculative kernel access to * userspace? @@ -346,9 +334,11 @@ static void __init spectre_v1_select_mitigation(void) * PTI as the CR3 write in the Meltdown mitigation * is serializing. * - * If neither is there, mitigate with an LFENCE. + * If neither is there, mitigate with an LFENCE to + * stop speculation through swapgs. */ - if (!is_swapgs_serializing() && !boot_cpu_has(X86_FEATURE_PTI)) + if (boot_cpu_has_bug(X86_BUG_SWAPGS) && + !boot_cpu_has(X86_FEATURE_PTI)) setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_USER); /* diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 309b6b9b49d4..300dcf00d287 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -970,6 +970,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_L1TF BIT(3) #define NO_MDS BIT(4) #define MSBDS_ONLY BIT(5) +#define NO_SWAPGS BIT(6) #define VULNWL(_vendor, _family, _model, _whitelist) \ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } @@ -996,30 +997,38 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION), VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION), - VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), VULNWL_INTEL(CORE_YONAH, NO_SSB), - VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF), - VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF), - VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF), + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS), + VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF | NO_SWAPGS), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS), + + /* + * Technically, swapgs isn't serializing on AMD (despite it previously + * being documented as such in the APM). But according to AMD, %gs is + * updated non-speculatively, and the issuing of %gs-relative memory + * operands will be blocked until the %gs update completes, which is + * good enough for our purposes. + */ /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS), {} }; @@ -1056,6 +1065,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); } + if (!cpu_matches(NO_SWAPGS)) + setup_force_cpu_bug(X86_BUG_SWAPGS); + if (cpu_matches(NO_MELTDOWN)) return; From 609488bc979f99f805f34e9a32c1e3b71179d10b Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 28 Jul 2019 12:47:02 -0700 Subject: [PATCH 463/823] Linux 5.3-rc2 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index bdf8eac51b07..fa0fbe7851ea 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 3 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Bobtail Squid # *DOCUMENTATION* From d95da993383c78f7efd25957ba3af23af4b1c613 Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Mon, 8 Jul 2019 08:35:58 +1200 Subject: [PATCH 464/823] gpiolib: Preserve desc->flags when setting state desc->flags may already have values set by of_gpiochip_add() so make sure that this isn't undone when setting the initial direction. Cc: stable@vger.kernel.org Fixes: 3edfb7bd76bd1cba ("gpiolib: Show correct direction from the beginning") Signed-off-by: Chris Packham Link: https://lore.kernel.org/r/20190707203558.10993-1-chris.packham@alliedtelesis.co.nz Signed-off-by: Linus Walleij --- drivers/gpio/gpiolib.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index bf05c29b53be..f497003f119c 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1394,12 +1394,17 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data, for (i = 0; i < chip->ngpio; i++) { struct gpio_desc *desc = &gdev->descs[i]; - if (chip->get_direction && gpiochip_line_is_valid(chip, i)) - desc->flags = !chip->get_direction(chip, i) ? - (1 << FLAG_IS_OUT) : 0; - else - desc->flags = !chip->direction_input ? - (1 << FLAG_IS_OUT) : 0; + if (chip->get_direction && gpiochip_line_is_valid(chip, i)) { + if (!chip->get_direction(chip, i)) + set_bit(FLAG_IS_OUT, &desc->flags); + else + clear_bit(FLAG_IS_OUT, &desc->flags); + } else { + if (!chip->direction_input) + set_bit(FLAG_IS_OUT, &desc->flags); + else + clear_bit(FLAG_IS_OUT, &desc->flags); + } } acpi_gpiochip_add(chip); From cee3536d24a1d5db66b9f68c3ece0af128187ab4 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 22 Jul 2019 22:26:56 +1000 Subject: [PATCH 465/823] powerpc: Wire up clone3 syscall Wire up the new clone3 syscall added in commit 7f192e3cd316 ("fork: add clone3"). This requires a ppc_clone3 wrapper, in order to save the non-volatile GPRs before calling into the generic syscall code. Otherwise we hit the BUG_ON in CHECK_FULL_REGS in copy_thread(). Lightly tested using Christian's test code on a Power8 LE VM. Signed-off-by: Michael Ellerman Acked-by: Christian Brauner Link: https://lore.kernel.org/r/20190724140259.23554-1-mpe@ellerman.id.au --- arch/powerpc/include/asm/unistd.h | 1 + arch/powerpc/kernel/entry_32.S | 8 ++++++++ arch/powerpc/kernel/entry_64.S | 5 +++++ arch/powerpc/kernel/syscalls/syscall.tbl | 2 +- 4 files changed, 15 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 68473c3c471c..b0720c7c3fcf 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -49,6 +49,7 @@ #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_SYS_VFORK #define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_CLONE3 #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 85fdb6d879f1..54fab22c9a43 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -597,6 +597,14 @@ ppc_clone: stw r0,_TRAP(r1) /* register set saved */ b sys_clone + .globl ppc_clone3 +ppc_clone3: + SAVE_NVGPRS(r1) + lwz r0,_TRAP(r1) + rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */ + stw r0,_TRAP(r1) /* register set saved */ + b sys_clone3 + .globl ppc_swapcontext ppc_swapcontext: SAVE_NVGPRS(r1) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index d9105fcf4021..0a0b5310f54a 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -487,6 +487,11 @@ _GLOBAL(ppc_clone) bl sys_clone b .Lsyscall_exit +_GLOBAL(ppc_clone3) + bl save_nvgprs + bl sys_clone3 + b .Lsyscall_exit + _GLOBAL(ppc32_swapcontext) bl save_nvgprs bl compat_sys_swapcontext diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 3331749aab20..43f736ed47f2 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -516,4 +516,4 @@ 432 common fsmount sys_fsmount 433 common fspick sys_fspick 434 common pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 nospu clone3 ppc_clone3 From 622445541b751ce70a952b8486ce4512a792c0a2 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 25 Jul 2019 17:05:13 +0900 Subject: [PATCH 466/823] kbuild: detect missing "WITH Linux-syscall-note" for uapi headers UAPI headers licensed under GPL are supposed to have exception "WITH Linux-syscall-note" so that they can be included into non-GPL user space application code. Unfortunately, people often miss to add it. Break 'make headers' when any of exported headers lacks the exception note so that the 0-day bot can easily catch it. Signed-off-by: Masahiro Yamada --- scripts/headers_install.sh | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/scripts/headers_install.sh b/scripts/headers_install.sh index 47f6f3ea0771..bbaf29386995 100755 --- a/scripts/headers_install.sh +++ b/scripts/headers_install.sh @@ -23,6 +23,12 @@ TMPFILE=$OUTFILE.tmp trap 'rm -f $OUTFILE $TMPFILE' EXIT +# SPDX-License-Identifier with GPL variants must have "WITH Linux-syscall-note" +if [ -n "$(sed -n -e "/SPDX-License-Identifier:.*GPL-/{/WITH Linux-syscall-note/!p}" $INFILE)" ]; then + echo "error: $INFILE: missing \"WITH Linux-syscall-note\" for SPDX-License-Identifier" >&2 + exit 1 +fi + sed -E -e ' s/([[:space:](])(__user|__force|__iomem)[[:space:]]/\1/g s/__attribute_const__([[:space:]]|$)/\1/g From 2e616d9f9ce8d469db4cd0a019cdc2ff3feab577 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sun, 28 Jul 2019 21:12:32 -0700 Subject: [PATCH 467/823] xfs: fix stack contents leakage in the v1 inumber ioctls Explicitly initialize the onstack structures to zero so we don't leak kernel memory into userspace when converting the in-core inumbers structure to the v1 inogrp ioctl structure. Add a comment about why we have to use memset to ensure that the padding holes in the structures are set to zero. Fixes: 5f19c7fc6873351 ("xfs: introduce v5 inode group structure") Reported-by: Dan Carpenter Signed-off-by: Darrick J. Wong Reviewed-by: Eric Sandeen --- fs/xfs/xfs_itable.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index a8a06bb78ea8..f5c955d35be4 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -272,6 +272,7 @@ xfs_bulkstat_to_bstat( struct xfs_bstat *bs1, const struct xfs_bulkstat *bstat) { + /* memset is needed here because of padding holes in the structure. */ memset(bs1, 0, sizeof(struct xfs_bstat)); bs1->bs_ino = bstat->bs_ino; bs1->bs_mode = bstat->bs_mode; @@ -388,6 +389,8 @@ xfs_inumbers_to_inogrp( struct xfs_inogrp *ig1, const struct xfs_inumbers *ig) { + /* memset is needed here because of padding holes in the structure. */ + memset(ig1, 0, sizeof(struct xfs_inogrp)); ig1->xi_startino = ig->xi_startino; ig1->xi_alloccount = ig->xi_alloccount; ig1->xi_allocmask = ig->xi_allocmask; From 38fb6d0ea34299d97b031ed64fe994158b6f8eb3 Mon Sep 17 00:00:00 2001 From: Icenowy Zheng Date: Thu, 25 Jul 2019 11:08:52 +0800 Subject: [PATCH 468/823] f2fs: use EINVAL for superblock with invalid magic The kernel mount_block_root() function expects -EACESS or -EINVAL for a unmountable filesystem when trying to mount the root with different filesystem types. However, in 5.3-rc1 the behavior when F2FS code cannot find valid block changed to return -EFSCORRUPTED(-EUCLEAN), and this error code makes mount_block_root() fail when trying to probe F2FS. When the magic number of the superblock mismatches, it has a high probability that it's just not a F2FS. In this case return -EINVAL seems to be a better result, and this return value can make mount_block_root() probing work again. Return -EINVAL when the superblock has magic mismatch, -EFSCORRUPTED in other cases (the magic matches but the superblock cannot be recognized). Fixes: 10f966bbf521 ("f2fs: use generic EFSBADCRC/EFSCORRUPTED") Signed-off-by: Icenowy Zheng Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/super.c | 48 ++++++++++++++++++++++++------------------------ 1 file changed, 24 insertions(+), 24 deletions(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index d95a681ef7c9..1838dd852a50 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2422,6 +2422,12 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, size_t crc_offset = 0; __u32 crc = 0; + if (le32_to_cpu(raw_super->magic) != F2FS_SUPER_MAGIC) { + f2fs_info(sbi, "Magic Mismatch, valid(0x%x) - read(0x%x)", + F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic)); + return -EINVAL; + } + /* Check checksum_offset and crc in superblock */ if (__F2FS_HAS_FEATURE(raw_super, F2FS_FEATURE_SB_CHKSUM)) { crc_offset = le32_to_cpu(raw_super->checksum_offset); @@ -2429,26 +2435,20 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, offsetof(struct f2fs_super_block, crc)) { f2fs_info(sbi, "Invalid SB checksum offset: %zu", crc_offset); - return 1; + return -EFSCORRUPTED; } crc = le32_to_cpu(raw_super->crc); if (!f2fs_crc_valid(sbi, crc, raw_super, crc_offset)) { f2fs_info(sbi, "Invalid SB checksum value: %u", crc); - return 1; + return -EFSCORRUPTED; } } - if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) { - f2fs_info(sbi, "Magic Mismatch, valid(0x%x) - read(0x%x)", - F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic)); - return 1; - } - /* Currently, support only 4KB page cache size */ if (F2FS_BLKSIZE != PAGE_SIZE) { f2fs_info(sbi, "Invalid page_cache_size (%lu), supports only 4KB", PAGE_SIZE); - return 1; + return -EFSCORRUPTED; } /* Currently, support only 4KB block size */ @@ -2456,14 +2456,14 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, if (blocksize != F2FS_BLKSIZE) { f2fs_info(sbi, "Invalid blocksize (%u), supports only 4KB", blocksize); - return 1; + return -EFSCORRUPTED; } /* check log blocks per segment */ if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) { f2fs_info(sbi, "Invalid log blocks per segment (%u)", le32_to_cpu(raw_super->log_blocks_per_seg)); - return 1; + return -EFSCORRUPTED; } /* Currently, support 512/1024/2048/4096 bytes sector size */ @@ -2473,7 +2473,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, F2FS_MIN_LOG_SECTOR_SIZE) { f2fs_info(sbi, "Invalid log sectorsize (%u)", le32_to_cpu(raw_super->log_sectorsize)); - return 1; + return -EFSCORRUPTED; } if (le32_to_cpu(raw_super->log_sectors_per_block) + le32_to_cpu(raw_super->log_sectorsize) != @@ -2481,7 +2481,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, f2fs_info(sbi, "Invalid log sectors per block(%u) log sectorsize(%u)", le32_to_cpu(raw_super->log_sectors_per_block), le32_to_cpu(raw_super->log_sectorsize)); - return 1; + return -EFSCORRUPTED; } segment_count = le32_to_cpu(raw_super->segment_count); @@ -2495,7 +2495,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, if (segment_count > F2FS_MAX_SEGMENT || segment_count < F2FS_MIN_SEGMENTS) { f2fs_info(sbi, "Invalid segment count (%u)", segment_count); - return 1; + return -EFSCORRUPTED; } if (total_sections > segment_count || @@ -2503,25 +2503,25 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, segs_per_sec > segment_count || !segs_per_sec) { f2fs_info(sbi, "Invalid segment/section count (%u, %u x %u)", segment_count, total_sections, segs_per_sec); - return 1; + return -EFSCORRUPTED; } if ((segment_count / segs_per_sec) < total_sections) { f2fs_info(sbi, "Small segment_count (%u < %u * %u)", segment_count, segs_per_sec, total_sections); - return 1; + return -EFSCORRUPTED; } if (segment_count > (le64_to_cpu(raw_super->block_count) >> 9)) { f2fs_info(sbi, "Wrong segment_count / block_count (%u > %llu)", segment_count, le64_to_cpu(raw_super->block_count)); - return 1; + return -EFSCORRUPTED; } if (secs_per_zone > total_sections || !secs_per_zone) { f2fs_info(sbi, "Wrong secs_per_zone / total_sections (%u, %u)", secs_per_zone, total_sections); - return 1; + return -EFSCORRUPTED; } if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION || raw_super->hot_ext_count > F2FS_MAX_EXTENSION || @@ -2531,7 +2531,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, le32_to_cpu(raw_super->extension_count), raw_super->hot_ext_count, F2FS_MAX_EXTENSION); - return 1; + return -EFSCORRUPTED; } if (le32_to_cpu(raw_super->cp_payload) > @@ -2539,7 +2539,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, f2fs_info(sbi, "Insane cp_payload (%u > %u)", le32_to_cpu(raw_super->cp_payload), blocks_per_seg - F2FS_CP_PACKS); - return 1; + return -EFSCORRUPTED; } /* check reserved ino info */ @@ -2550,12 +2550,12 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, le32_to_cpu(raw_super->node_ino), le32_to_cpu(raw_super->meta_ino), le32_to_cpu(raw_super->root_ino)); - return 1; + return -EFSCORRUPTED; } /* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */ if (sanity_check_area_boundary(sbi, bh)) - return 1; + return -EFSCORRUPTED; return 0; } @@ -2872,10 +2872,10 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi, } /* sanity checking of raw super */ - if (sanity_check_raw_super(sbi, bh)) { + err = sanity_check_raw_super(sbi, bh); + if (err) { f2fs_err(sbi, "Can't find valid F2FS filesystem in %dth superblock", block + 1); - err = -EFSCORRUPTED; brelse(bh); continue; } From c6622a425acd1d2f3a443cd39b490a8777b622d7 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Fri, 26 Jul 2019 12:34:32 -0700 Subject: [PATCH 469/823] dma-contiguous: do not overwrite align in dma_alloc_contiguous() The dma_alloc_contiguous() limits align at CONFIG_CMA_ALIGNMENT for cma_alloc() however it does not restore it for the fallback routine. This will result in a size mismatch between the allocation and free when running into the fallback routines after cma_alloc() fails, if the align is larger than CONFIG_CMA_ALIGNMENT. This patch adds a cma_align to take care of cma_alloc() and prevent the align from being overwritten. Fixes: fdaeec198ada ("dma-contiguous: add dma_{alloc,free}_contiguous() helpers") Reported-by: Dafna Hirschfeld Signed-off-by: Nicolin Chen Signed-off-by: Christoph Hellwig --- kernel/dma/contiguous.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index bfc0c17f2a3d..ea8259f53eda 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -243,8 +243,9 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp) /* CMA can be used only in the context which permits sleeping */ if (cma && gfpflags_allow_blocking(gfp)) { - align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT); - page = cma_alloc(cma, count, align, gfp & __GFP_NOWARN); + size_t cma_align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT); + + page = cma_alloc(cma, count, cma_align, gfp & __GFP_NOWARN); } /* Fallback allocation of normal pages */ From f46cc0152501e46d1b3aa5e7eade61145070eab0 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Fri, 26 Jul 2019 12:34:33 -0700 Subject: [PATCH 470/823] dma-contiguous: page-align the size in dma_free_contiguous() According to the original dma_direct_alloc_pages() code: { unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; if (!dma_release_from_contiguous(dev, page, count)) __free_pages(page, get_order(size)); } The count parameter for dma_release_from_contiguous() was page aligned before the right-shifting operation, while the new API dma_free_contiguous() forgets to have PAGE_ALIGN() at the size. So this patch simply adds it to prevent any corner case. Fixes: fdaeec198ada ("dma-contiguous: add dma_{alloc,free}_contiguous() helpers") Signed-off-by: Nicolin Chen Reviewed-by: Christoph Hellwig Signed-off-by: Christoph Hellwig --- kernel/dma/contiguous.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index ea8259f53eda..2bd410f934b3 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -267,7 +267,8 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp) */ void dma_free_contiguous(struct device *dev, struct page *page, size_t size) { - if (!cma_release(dev_get_cma_area(dev), page, size >> PAGE_SHIFT)) + if (!cma_release(dev_get_cma_area(dev), page, + PAGE_ALIGN(size) >> PAGE_SHIFT)) __free_pages(page, get_order(size)); } From 849adec41203ac5837c40c2d7e08490ffdef3c2c Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 29 Jul 2019 11:06:17 +0100 Subject: [PATCH 471/823] arm64: compat: Allow single-byte watchpoints on all addresses Commit d968d2b801d8 ("ARM: 7497/1: hw_breakpoint: allow single-byte watchpoints on all addresses") changed the validation requirements for hardware watchpoints on arch/arm/. Update our compat layer to implement the same relaxation. Cc: Signed-off-by: Will Deacon --- arch/arm64/kernel/hw_breakpoint.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index dceb84520948..67b3bae50b92 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -536,13 +536,14 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, /* Aligned */ break; case 1: - /* Allow single byte watchpoint. */ - if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) - break; case 2: /* Allow halfword watchpoints and breakpoints. */ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2) break; + case 3: + /* Allow single byte watchpoint. */ + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) + break; default: return -EINVAL; } From 0d7fd70f26039bd4b33444ca47f0e69ce3ae0354 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 29 Jul 2019 11:43:48 +0100 Subject: [PATCH 472/823] drivers/perf: arm_pmu: Fix failure path in PM notifier Handling of the CPU_PM_ENTER_FAILED transition in the Arm PMU PM notifier code incorrectly skips restoration of the counters. Fix the logic so that CPU_PM_ENTER_FAILED follows the same path as CPU_PM_EXIT. Cc: Fixes: da4e4f18afe0f372 ("drivers/perf: arm_pmu: implement CPU_PM notifier") Reported-by: Anders Roxell Acked-by: Lorenzo Pieralisi Signed-off-by: Will Deacon --- drivers/perf/arm_pmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 2d06b8095a19..df352b334ea7 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -723,8 +723,8 @@ static int cpu_pm_pmu_notify(struct notifier_block *b, unsigned long cmd, cpu_pm_pmu_setup(armpmu, cmd); break; case CPU_PM_EXIT: - cpu_pm_pmu_setup(armpmu, cmd); case CPU_PM_ENTER_FAILED: + cpu_pm_pmu_setup(armpmu, cmd); armpmu->start(armpmu); break; default: From 75a382f1c9e5092db10ad1e2111633d61b65e578 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 29 Jul 2019 11:39:45 +0100 Subject: [PATCH 473/823] arm64: hw_breakpoint: Fix warnings about implicit fallthrough Now that -Wimplicit-fallthrough is passed to GCC by default, the kernel build has suddenly got noisy. Annotate the two fall-through cases in our hw_breakpoint implementation, since they are both intentional. Reported-by: Anders Roxell Signed-off-by: Will Deacon --- arch/arm64/kernel/hw_breakpoint.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 67b3bae50b92..38ee1514cd9c 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -540,10 +540,14 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, /* Allow halfword watchpoints and breakpoints. */ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2) break; + + /* Fallthrough */ case 3: /* Allow single byte watchpoint. */ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) break; + + /* Fallthrough */ default: return -EINVAL; } From 6655473920129eb2dd1dded147722316294a699a Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Fri, 26 Jul 2019 13:27:25 +0200 Subject: [PATCH 474/823] arm64: smp: Mark expected switch fall-through MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When fall-through warnings was enabled by default the following warning was starting to show up: In file included from ../include/linux/kernel.h:15, from ../include/linux/list.h:9, from ../include/linux/kobject.h:19, from ../include/linux/of.h:17, from ../include/linux/irqdomain.h:35, from ../include/linux/acpi.h:13, from ../arch/arm64/kernel/smp.c:9: ../arch/arm64/kernel/smp.c: In function ‘__cpu_up’: ../include/linux/printk.h:302:2: warning: this statement may fall through [-Wimplicit-fallthrough=] printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ../arch/arm64/kernel/smp.c:156:4: note: in expansion of macro ‘pr_crit’ pr_crit("CPU%u: may not have shut down cleanly\n", cpu); ^~~~~~~ ../arch/arm64/kernel/smp.c:157:3: note: here case CPU_STUCK_IN_KERNEL: ^~~~ Rework so that the compiler doesn't warn about fall-through. Fixes: d93512ef0f0e ("Makefile: Globally enable fall-through warning") Signed-off-by: Anders Roxell Signed-off-by: Will Deacon --- arch/arm64/kernel/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index ea90d3bd9253..018a33e01b0e 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -152,8 +152,8 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) pr_crit("CPU%u: died during early boot\n", cpu); break; } - /* Fall through */ pr_crit("CPU%u: may not have shut down cleanly\n", cpu); + /* Fall through */ case CPU_STUCK_IN_KERNEL: pr_crit("CPU%u: is stuck in kernel\n", cpu); if (status & CPU_STUCK_REASON_52_BIT_VA) From eca92a53a6ab9f27f1b61dcb3e16ebef75f0d5bb Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Fri, 26 Jul 2019 13:27:21 +0200 Subject: [PATCH 475/823] arm64: module: Mark expected switch fall-through MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When fall-through warnings was enabled by default the following warnings was starting to show up: ../arch/arm64/kernel/module.c: In function ‘apply_relocate_add’: ../arch/arm64/kernel/module.c:316:19: warning: this statement may fall through [-Wimplicit-fallthrough=] overflow_check = false; ~~~~~~~~~~~~~~~^~~~~~~ ../arch/arm64/kernel/module.c:317:3: note: here case R_AARCH64_MOVW_UABS_G0: ^~~~ ../arch/arm64/kernel/module.c:322:19: warning: this statement may fall through [-Wimplicit-fallthrough=] overflow_check = false; ~~~~~~~~~~~~~~~^~~~~~~ ../arch/arm64/kernel/module.c:323:3: note: here case R_AARCH64_MOVW_UABS_G1: ^~~~ Rework so that the compiler doesn't warn about fall-through. Fixes: d93512ef0f0e ("Makefile: Globally enable fall-through warning") Signed-off-by: Anders Roxell Signed-off-by: Will Deacon --- arch/arm64/kernel/module.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 46e643e30708..03ff15bffbb6 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -314,18 +314,21 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, /* MOVW instruction relocations. */ case R_AARCH64_MOVW_UABS_G0_NC: overflow_check = false; + /* Fall through */ case R_AARCH64_MOVW_UABS_G0: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0, AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G1_NC: overflow_check = false; + /* Fall through */ case R_AARCH64_MOVW_UABS_G1: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16, AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G2_NC: overflow_check = false; + /* Fall through */ case R_AARCH64_MOVW_UABS_G2: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32, AARCH64_INSN_IMM_MOVKZ); @@ -393,6 +396,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, break; case R_AARCH64_ADR_PREL_PG_HI21_NC: overflow_check = false; + /* Fall through */ case R_AARCH64_ADR_PREL_PG_HI21: ovf = reloc_insn_adrp(me, sechdrs, loc, val); if (ovf && ovf != -ERANGE) From ac65bdfef14a902b40ff69a35f5c604dba096547 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 19 Jun 2019 18:01:35 +0100 Subject: [PATCH 476/823] drm/i915: Keep rings pinned while the context is active Remember to keep the rings pinned as well as the context image until the GPU is no longer active. v2: Introduce a ring->pin_count primarily to hide the mock_ring that doesn't fit into the normal GGTT vma picture. v3: Order is important in teardown, ringbuffer submission needs to drop the pin count on the engine->kernel_context before it can gleefully free its ring. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=110946 Fixes: ce476c80b8bf ("drm/i915: Keep contexts pinned until after the next kernel context switch") Signed-off-by: Chris Wilson Cc: Mika Kuoppala Cc: Tvrtko Ursulin Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20190619170135.15281-1-chris@chris-wilson.co.uk (cherry picked from commit 09c5ab384f6fb30f834a5777888b4486dd7f015d) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gt/intel_context.c | 27 +++++++++++------ drivers/gpu/drm/i915/gt/intel_engine_types.h | 12 ++++++++ drivers/gpu/drm/i915/gt/intel_lrc.c | 10 ++----- drivers/gpu/drm/i915/gt/intel_ringbuffer.c | 31 +++++++++++++------- drivers/gpu/drm/i915/gt/mock_engine.c | 1 + 5 files changed, 53 insertions(+), 28 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 2c454f227c2e..23120901c55f 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -126,6 +126,7 @@ static void intel_context_retire(struct i915_active *active) if (ce->state) __context_unpin_state(ce->state); + intel_ring_unpin(ce->ring); intel_context_put(ce); } @@ -160,27 +161,35 @@ int intel_context_active_acquire(struct intel_context *ce, unsigned long flags) intel_context_get(ce); + err = intel_ring_pin(ce->ring); + if (err) + goto err_put; + if (!ce->state) return 0; err = __context_pin_state(ce->state, flags); - if (err) { - i915_active_cancel(&ce->active); - intel_context_put(ce); - return err; - } + if (err) + goto err_ring; /* Preallocate tracking nodes */ if (!i915_gem_context_is_kernel(ce->gem_context)) { err = i915_active_acquire_preallocate_barrier(&ce->active, ce->engine); - if (err) { - i915_active_release(&ce->active); - return err; - } + if (err) + goto err_state; } return 0; + +err_state: + __context_unpin_state(ce->state); +err_ring: + intel_ring_unpin(ce->ring); +err_put: + intel_context_put(ce); + i915_active_cancel(&ce->active); + return err; } void intel_context_active_release(struct intel_context *ce) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 868b220214f8..43e975a26016 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -70,6 +70,18 @@ struct intel_ring { struct list_head request_list; struct list_head active_link; + /* + * As we have two types of rings, one global to the engine used + * by ringbuffer submission and those that are exclusive to a + * context used by execlists, we have to play safe and allow + * atomic updates to the pin_count. However, the actual pinning + * of the context is either done during initialisation for + * ringbuffer submission or serialised as part of the context + * pinning for execlists, and so we do not need a mutex ourselves + * to serialise intel_ring_pin/intel_ring_unpin. + */ + atomic_t pin_count; + u32 head; u32 tail; u32 emit; diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index b42b5f158295..82b7ace62d97 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1414,6 +1414,7 @@ static void execlists_context_destroy(struct kref *kref) { struct intel_context *ce = container_of(kref, typeof(*ce), ref); + GEM_BUG_ON(!i915_active_is_idle(&ce->active)); GEM_BUG_ON(intel_context_is_pinned(ce)); if (ce->state) @@ -1426,7 +1427,6 @@ static void execlists_context_unpin(struct intel_context *ce) { i915_gem_context_unpin_hw_id(ce->gem_context); i915_gem_object_unpin_map(ce->state->obj); - intel_ring_unpin(ce->ring); } static void @@ -1478,13 +1478,9 @@ __execlists_context_pin(struct intel_context *ce, goto unpin_active; } - ret = intel_ring_pin(ce->ring); - if (ret) - goto unpin_map; - ret = i915_gem_context_pin_hw_id(ce->gem_context); if (ret) - goto unpin_ring; + goto unpin_map; ce->lrc_desc = lrc_descriptor(ce, engine); ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE; @@ -1492,8 +1488,6 @@ __execlists_context_pin(struct intel_context *ce, return 0; -unpin_ring: - intel_ring_unpin(ce->ring); unpin_map: i915_gem_object_unpin_map(ce->state->obj); unpin_active: diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c index c6023bc9452d..12010e798868 100644 --- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c @@ -1149,16 +1149,16 @@ i915_emit_bb_start(struct i915_request *rq, int intel_ring_pin(struct intel_ring *ring) { struct i915_vma *vma = ring->vma; - enum i915_map_type map = i915_coherent_map_type(vma->vm->i915); unsigned int flags; void *addr; int ret; - GEM_BUG_ON(ring->vaddr); + if (atomic_fetch_inc(&ring->pin_count)) + return 0; ret = i915_timeline_pin(ring->timeline); if (ret) - return ret; + goto err_unpin; flags = PIN_GLOBAL; @@ -1172,26 +1172,31 @@ int intel_ring_pin(struct intel_ring *ring) ret = i915_vma_pin(vma, 0, 0, flags); if (unlikely(ret)) - goto unpin_timeline; + goto err_timeline; if (i915_vma_is_map_and_fenceable(vma)) addr = (void __force *)i915_vma_pin_iomap(vma); else - addr = i915_gem_object_pin_map(vma->obj, map); + addr = i915_gem_object_pin_map(vma->obj, + i915_coherent_map_type(vma->vm->i915)); if (IS_ERR(addr)) { ret = PTR_ERR(addr); - goto unpin_ring; + goto err_ring; } vma->obj->pin_global++; + GEM_BUG_ON(ring->vaddr); ring->vaddr = addr; + return 0; -unpin_ring: +err_ring: i915_vma_unpin(vma); -unpin_timeline: +err_timeline: i915_timeline_unpin(ring->timeline); +err_unpin: + atomic_dec(&ring->pin_count); return ret; } @@ -1207,16 +1212,19 @@ void intel_ring_reset(struct intel_ring *ring, u32 tail) void intel_ring_unpin(struct intel_ring *ring) { - GEM_BUG_ON(!ring->vma); - GEM_BUG_ON(!ring->vaddr); + if (!atomic_dec_and_test(&ring->pin_count)) + return; /* Discard any unused bytes beyond that submitted to hw. */ intel_ring_reset(ring, ring->tail); + GEM_BUG_ON(!ring->vma); if (i915_vma_is_map_and_fenceable(ring->vma)) i915_vma_unpin_iomap(ring->vma); else i915_gem_object_unpin_map(ring->vma->obj); + + GEM_BUG_ON(!ring->vaddr); ring->vaddr = NULL; ring->vma->obj->pin_global--; @@ -2081,10 +2089,11 @@ static void ring_destroy(struct intel_engine_cs *engine) WARN_ON(INTEL_GEN(dev_priv) > 2 && (ENGINE_READ(engine, RING_MI_MODE) & MODE_IDLE) == 0); + intel_engine_cleanup_common(engine); + intel_ring_unpin(engine->buffer); intel_ring_put(engine->buffer); - intel_engine_cleanup_common(engine); kfree(engine); } diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c index 086801b51441..486c6953dcb1 100644 --- a/drivers/gpu/drm/i915/gt/mock_engine.c +++ b/drivers/gpu/drm/i915/gt/mock_engine.c @@ -66,6 +66,7 @@ static struct intel_ring *mock_ring(struct intel_engine_cs *engine) ring->base.effective_size = sz; ring->base.vaddr = (void *)(ring + 1); ring->base.timeline = &ring->timeline; + atomic_set(&ring->base.pin_count, 1); INIT_LIST_HEAD(&ring->base.request_list); intel_ring_update_space(&ring->base); From 248f883db61283b4f5a1c92a5e27277377b09f16 Mon Sep 17 00:00:00 2001 From: Kenneth Graunke Date: Tue, 25 Jun 2019 10:06:55 +0100 Subject: [PATCH 477/823] drm/i915: Disable SAMPLER_STATE prefetching on all Gen11 steppings. The Demand Prefetch workaround (binding table prefetching) only applies to Icelake A0/B0. But the Sampler Prefetch workaround needs to be applied to all Gen11 steppings, according to a programming note in the SARCHKMD documentation. Using the Intel Gallium driver, I have seen intermittent failures in the dEQP-GLES31.functional.copy_image.non_compressed.* tests. After applying this workaround, the tests reliably pass. v2: Remove the overlap with a pre-production w/a BSpec: 9663 Signed-off-by: Kenneth Graunke Signed-off-by: Chris Wilson Cc: stable@vger.kernel.org Reviewed-by: Mika Kuoppala Link: https://patchwork.freedesktop.org/patch/msgid/20190625090655.19220-1-chris@chris-wilson.co.uk (cherry picked from commit f9a393875d3af13cc3267477746608dadb7f17c1) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gt/intel_workarounds.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 15e90fd2cfdc..50c0060509a6 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -1258,8 +1258,12 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_B0)) wa_write_or(wal, GEN7_SARCHKMD, - GEN7_DISABLE_DEMAND_PREFETCH | - GEN7_DISABLE_SAMPLER_PREFETCH); + GEN7_DISABLE_DEMAND_PREFETCH); + + /* Wa_1606682166:icl */ + wa_write_or(wal, + GEN7_SARCHKMD, + GEN7_DISABLE_SAMPLER_PREFETCH); } if (IS_GEN_RANGE(i915, 9, 11)) { From 95eef14cdad150fed43147bcd4f29eea3d0a3f03 Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Mon, 10 Jun 2019 11:19:14 +0300 Subject: [PATCH 478/823] drm/i915/perf: fix ICL perf register offsets We got the wrong offsets (could they have changed?). New values were computed off an error state by looking up the register offset in the context image as written by the HW. Signed-off-by: Lionel Landwerlin Fixes: 1de401c08fa805 ("drm/i915/perf: enable perf support on ICL") Cc: # v4.18+ Acked-by: Kenneth Graunke Link: https://patchwork.freedesktop.org/patch/msgid/20190610081914.25428-1-lionel.g.landwerlin@intel.com (cherry picked from commit 8dcfdfb4501012a8d36d2157dc73925715f2befb) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_perf.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index a700c5c3d167..1ae06a1b6749 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -3477,9 +3477,13 @@ void i915_perf_init(struct drm_i915_private *dev_priv) dev_priv->perf.oa.ops.enable_metric_set = gen8_enable_metric_set; dev_priv->perf.oa.ops.disable_metric_set = gen10_disable_metric_set; - dev_priv->perf.oa.ctx_oactxctrl_offset = 0x128; - dev_priv->perf.oa.ctx_flexeu0_offset = 0x3de; - + if (IS_GEN(dev_priv, 10)) { + dev_priv->perf.oa.ctx_oactxctrl_offset = 0x128; + dev_priv->perf.oa.ctx_flexeu0_offset = 0x3de; + } else { + dev_priv->perf.oa.ctx_oactxctrl_offset = 0x124; + dev_priv->perf.oa.ctx_flexeu0_offset = 0x78e; + } dev_priv->perf.oa.gen8_valid_ctx_bit = (1<<16); } } From 7d3cd66261665da491d0ee582beabe23df60f983 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Wed, 19 Jun 2019 20:08:39 +0300 Subject: [PATCH 479/823] drm/i915: Fix various tracepoints for gen2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Gen2 doesn't have a frame counter and apparently we no longer provide a fake .get_vblank_counter() hook for it. That means all tracepoints calling that hook will oops. Update the tracepoints to use intel_crtc_get_vblank_counter() which will gracefully fall back to using the software counter. This is actually a better approach since we now get (hopefully accurate) frame numbers in the traces. This also gets rid of the raw driver->get_vblank_counter() calls, which we need to do in order to switch to the per-crtc vblank vfuncs. v2: Deal with new tracepoints v3: Use a distinct variable name for the internal crtc iterator (Chris) Cc: Shawn Guo Cc: Daniel Vetter Fixes: 967dd4841787 ("drm: remove drm_vblank_no_hw_counter assignment from driver code") Signed-off-by: Ville Syrjälä Reviewed-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20190619170842.20579-2-ville.syrjala@linux.intel.com (cherry picked from commit 4c888e7bd26f58deb27c2e6ddc90000b89ee9393) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_display.c | 4 +- drivers/gpu/drm/i915/i915_trace.h | 76 +++++++++----------- 2 files changed, 35 insertions(+), 45 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 30b97ded6fdd..592b92782fab 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -1839,7 +1839,7 @@ static void intel_enable_pipe(const struct intel_crtc_state *new_crtc_state) /* FIXME: assert CPU port conditions for SNB+ */ } - trace_intel_pipe_enable(dev_priv, pipe); + trace_intel_pipe_enable(crtc); reg = PIPECONF(cpu_transcoder); val = I915_READ(reg); @@ -1880,7 +1880,7 @@ static void intel_disable_pipe(const struct intel_crtc_state *old_crtc_state) */ assert_planes_disabled(crtc); - trace_intel_pipe_disable(dev_priv, pipe); + trace_intel_pipe_disable(crtc); reg = PIPECONF(cpu_transcoder); val = I915_READ(reg); diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index f4ce643b3bc3..cce426b23a24 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -21,24 +21,22 @@ /* watermark/fifo updates */ TRACE_EVENT(intel_pipe_enable, - TP_PROTO(struct drm_i915_private *dev_priv, enum pipe pipe), - TP_ARGS(dev_priv, pipe), + TP_PROTO(struct intel_crtc *crtc), + TP_ARGS(crtc), TP_STRUCT__entry( __array(u32, frame, 3) __array(u32, scanline, 3) __field(enum pipe, pipe) ), - TP_fast_assign( - enum pipe _pipe; - for_each_pipe(dev_priv, _pipe) { - __entry->frame[_pipe] = - dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, _pipe); - __entry->scanline[_pipe] = - intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, _pipe)); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_crtc *it__; + for_each_intel_crtc(&dev_priv->drm, it__) { + __entry->frame[it__->pipe] = intel_crtc_get_vblank_counter(it__); + __entry->scanline[it__->pipe] = intel_get_crtc_scanline(it__); } - __entry->pipe = pipe; + __entry->pipe = crtc->pipe; ), TP_printk("pipe %c enable, pipe A: frame=%u, scanline=%u, pipe B: frame=%u, scanline=%u, pipe C: frame=%u, scanline=%u", @@ -49,8 +47,8 @@ TRACE_EVENT(intel_pipe_enable, ); TRACE_EVENT(intel_pipe_disable, - TP_PROTO(struct drm_i915_private *dev_priv, enum pipe pipe), - TP_ARGS(dev_priv, pipe), + TP_PROTO(struct intel_crtc *crtc), + TP_ARGS(crtc), TP_STRUCT__entry( __array(u32, frame, 3) @@ -59,14 +57,13 @@ TRACE_EVENT(intel_pipe_disable, ), TP_fast_assign( - enum pipe _pipe; - for_each_pipe(dev_priv, _pipe) { - __entry->frame[_pipe] = - dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, _pipe); - __entry->scanline[_pipe] = - intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, _pipe)); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_crtc *it__; + for_each_intel_crtc(&dev_priv->drm, it__) { + __entry->frame[it__->pipe] = intel_crtc_get_vblank_counter(it__); + __entry->scanline[it__->pipe] = intel_get_crtc_scanline(it__); } - __entry->pipe = pipe; + __entry->pipe = crtc->pipe; ), TP_printk("pipe %c disable, pipe A: frame=%u, scanline=%u, pipe B: frame=%u, scanline=%u, pipe C: frame=%u, scanline=%u", @@ -89,8 +86,7 @@ TRACE_EVENT(intel_pipe_crc, TP_fast_assign( __entry->pipe = crtc->pipe; - __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, - crtc->pipe); + __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); memcpy(__entry->crcs, crcs, sizeof(__entry->crcs)); ), @@ -112,9 +108,10 @@ TRACE_EVENT(intel_cpu_fifo_underrun, ), TP_fast_assign( + struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); __entry->pipe = pipe; - __entry->frame = dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, pipe); - __entry->scanline = intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, pipe)); + __entry->frame = intel_crtc_get_vblank_counter(crtc); + __entry->scanline = intel_get_crtc_scanline(crtc); ), TP_printk("pipe %c, frame=%u, scanline=%u", @@ -134,9 +131,10 @@ TRACE_EVENT(intel_pch_fifo_underrun, TP_fast_assign( enum pipe pipe = pch_transcoder; + struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); __entry->pipe = pipe; - __entry->frame = dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, pipe); - __entry->scanline = intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, pipe)); + __entry->frame = intel_crtc_get_vblank_counter(crtc); + __entry->scanline = intel_get_crtc_scanline(crtc); ), TP_printk("pch transcoder %c, frame=%u, scanline=%u", @@ -156,12 +154,10 @@ TRACE_EVENT(intel_memory_cxsr, ), TP_fast_assign( - enum pipe pipe; - for_each_pipe(dev_priv, pipe) { - __entry->frame[pipe] = - dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, pipe); - __entry->scanline[pipe] = - intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, pipe)); + struct intel_crtc *crtc; + for_each_intel_crtc(&dev_priv->drm, crtc) { + __entry->frame[crtc->pipe] = intel_crtc_get_vblank_counter(crtc); + __entry->scanline[crtc->pipe] = intel_get_crtc_scanline(crtc); } __entry->old = old; __entry->new = new; @@ -198,8 +194,7 @@ TRACE_EVENT(g4x_wm, TP_fast_assign( __entry->pipe = crtc->pipe; - __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, - crtc->pipe); + __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); __entry->primary = wm->pipe[crtc->pipe].plane[PLANE_PRIMARY]; __entry->sprite = wm->pipe[crtc->pipe].plane[PLANE_SPRITE0]; @@ -243,8 +238,7 @@ TRACE_EVENT(vlv_wm, TP_fast_assign( __entry->pipe = crtc->pipe; - __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, - crtc->pipe); + __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); __entry->level = wm->level; __entry->cxsr = wm->cxsr; @@ -278,8 +272,7 @@ TRACE_EVENT(vlv_fifo_size, TP_fast_assign( __entry->pipe = crtc->pipe; - __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, - crtc->pipe); + __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); __entry->sprite0_start = sprite0_start; __entry->sprite1_start = sprite1_start; @@ -310,8 +303,7 @@ TRACE_EVENT(intel_update_plane, TP_fast_assign( __entry->pipe = crtc->pipe; __entry->name = plane->name; - __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, - crtc->pipe); + __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); memcpy(__entry->src, &plane->state->src, sizeof(__entry->src)); memcpy(__entry->dst, &plane->state->dst, sizeof(__entry->dst)); @@ -338,8 +330,7 @@ TRACE_EVENT(intel_disable_plane, TP_fast_assign( __entry->pipe = crtc->pipe; __entry->name = plane->name; - __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, - crtc->pipe); + __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); ), @@ -364,8 +355,7 @@ TRACE_EVENT(i915_pipe_update_start, TP_fast_assign( __entry->pipe = crtc->pipe; - __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, - crtc->pipe); + __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); __entry->min = crtc->debug.min_vbl; __entry->max = crtc->debug.max_vbl; From b830f94f7303a49d509d5b1bb34ecb2e648b23c4 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 26 Jul 2019 12:49:00 -0300 Subject: [PATCH 480/823] tools headers UAPI: Update tools's copy of mman.h headers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To pick up the changes from: 8aa3c927ec10 ("mm/mmap: move common defines to mman-common.h") 22fcea6f85f2 ("mm: move MAP_SYNC to asm-generic/mman-common.h") 0bf5f9492389 ("mm: fix the MAP_UNINITIALIZED flag") To address the following perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/mman-common.h' differs from latest version at 'include/uapi/asm-generic/mman-common.h' diff -u tools/include/uapi/asm-generic/mman-common.h include/uapi/asm-generic/mman-common.h Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/mman.h' differs from latest version at 'include/uapi/asm-generic/mman.h' diff -u tools/include/uapi/asm-generic/mman.h include/uapi/asm-generic/mman.h That ends up just moving a bit the auto-generated code->string tables: $ tools/perf/trace/beauty/mmap_flags.sh > before $ cp include/uapi/asm-generic/mman.h tools/include/uapi/asm-generic/mman.h $ cp include/uapi/asm-generic/mman-common.h tools/include/uapi/asm-generic/mman-common.h $ tools/perf/trace/beauty/mmap_flags.sh > after $ diff -u before after --- before 2019-07-26 12:45:02.948335904 -0300 +++ after 2019-07-26 12:48:05.342893539 -0300 @@ -4,15 +4,15 @@ [ilog2(0x02) + 1] = "PRIVATE", [ilog2(0x10) + 1] = "FIXED", [ilog2(0x20) + 1] = "ANONYMOUS", + [ilog2(0x008000) + 1] = "POPULATE", + [ilog2(0x010000) + 1] = "NONBLOCK", + [ilog2(0x020000) + 1] = "STACK", + [ilog2(0x040000) + 1] = "HUGETLB", + [ilog2(0x080000) + 1] = "SYNC", [ilog2(0x100000) + 1] = "FIXED_NOREPLACE", [ilog2(0x0100) + 1] = "GROWSDOWN", [ilog2(0x0800) + 1] = "DENYWRITE", [ilog2(0x1000) + 1] = "EXECUTABLE", [ilog2(0x2000) + 1] = "LOCKED", [ilog2(0x4000) + 1] = "NORESERVE", - [ilog2(0x8000) + 1] = "POPULATE", - [ilog2(0x10000) + 1] = "NONBLOCK", - [ilog2(0x20000) + 1] = "STACK", - [ilog2(0x40000) + 1] = "HUGETLB", - [ilog2(0x80000) + 1] = "SYNC", }; $ Cc: Adrian Hunter Cc: Aneesh Kumar K.V Cc: Christoph Hellwig Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-fzqvzni9megaurmsp0k4vy27@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/powerpc/include/uapi/asm/mman.h | 4 ---- tools/arch/sparc/include/uapi/asm/mman.h | 4 ---- tools/include/uapi/asm-generic/mman-common.h | 15 +++++++++------ tools/include/uapi/asm-generic/mman.h | 10 ++++------ 4 files changed, 13 insertions(+), 20 deletions(-) diff --git a/tools/arch/powerpc/include/uapi/asm/mman.h b/tools/arch/powerpc/include/uapi/asm/mman.h index f33105bc5ca6..8601d824a9c6 100644 --- a/tools/arch/powerpc/include/uapi/asm/mman.h +++ b/tools/arch/powerpc/include/uapi/asm/mman.h @@ -4,12 +4,8 @@ #define MAP_DENYWRITE 0x0800 #define MAP_EXECUTABLE 0x1000 #define MAP_GROWSDOWN 0x0100 -#define MAP_HUGETLB 0x40000 #define MAP_LOCKED 0x80 -#define MAP_NONBLOCK 0x10000 #define MAP_NORESERVE 0x40 -#define MAP_POPULATE 0x8000 -#define MAP_STACK 0x20000 #include /* MAP_32BIT is undefined on powerpc, fix it for perf */ #define MAP_32BIT 0 diff --git a/tools/arch/sparc/include/uapi/asm/mman.h b/tools/arch/sparc/include/uapi/asm/mman.h index 38920eed8cbf..7b94dccc843d 100644 --- a/tools/arch/sparc/include/uapi/asm/mman.h +++ b/tools/arch/sparc/include/uapi/asm/mman.h @@ -4,12 +4,8 @@ #define MAP_DENYWRITE 0x0800 #define MAP_EXECUTABLE 0x1000 #define MAP_GROWSDOWN 0x0200 -#define MAP_HUGETLB 0x40000 #define MAP_LOCKED 0x100 -#define MAP_NONBLOCK 0x10000 #define MAP_NORESERVE 0x40 -#define MAP_POPULATE 0x8000 -#define MAP_STACK 0x20000 #include /* MAP_32BIT is undefined on sparc, fix it for perf */ #define MAP_32BIT 0 diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index abd238d0f7a4..63b1f506ea67 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -19,15 +19,18 @@ #define MAP_TYPE 0x0f /* Mask for type of mapping */ #define MAP_FIXED 0x10 /* Interpret addr exactly */ #define MAP_ANONYMOUS 0x20 /* don't use a file */ -#ifdef CONFIG_MMAP_ALLOW_UNINITIALIZED -# define MAP_UNINITIALIZED 0x4000000 /* For anonymous mmap, memory could be uninitialized */ -#else -# define MAP_UNINITIALIZED 0x0 /* Don't support this flag */ -#endif -/* 0x0100 - 0x80000 flags are defined in asm-generic/mman.h */ +/* 0x0100 - 0x4000 flags are defined in asm-generic/mman.h */ +#define MAP_POPULATE 0x008000 /* populate (prefault) pagetables */ +#define MAP_NONBLOCK 0x010000 /* do not block on IO */ +#define MAP_STACK 0x020000 /* give out an address that is best suited for process/thread stacks */ +#define MAP_HUGETLB 0x040000 /* create a huge page mapping */ +#define MAP_SYNC 0x080000 /* perform synchronous page faults for the mapping */ #define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */ +#define MAP_UNINITIALIZED 0x4000000 /* For anonymous mmap, memory could be + * uninitialized */ + /* * Flags for mlock */ diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h index 36c197fc44a0..406f7718f9ad 100644 --- a/tools/include/uapi/asm-generic/mman.h +++ b/tools/include/uapi/asm-generic/mman.h @@ -9,13 +9,11 @@ #define MAP_EXECUTABLE 0x1000 /* mark it as an executable */ #define MAP_LOCKED 0x2000 /* pages are locked */ #define MAP_NORESERVE 0x4000 /* don't check for reservations */ -#define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */ -#define MAP_NONBLOCK 0x10000 /* do not block on IO */ -#define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */ -#define MAP_HUGETLB 0x40000 /* create a huge page mapping */ -#define MAP_SYNC 0x80000 /* perform synchronous page faults for the mapping */ -/* Bits [26:31] are reserved, see mman-common.h for MAP_HUGETLB usage */ +/* + * Bits [26:31] are reserved, see asm-generic/hugetlb_encode.h + * for MAP_HUGETLB usage + */ #define MCL_CURRENT 1 /* lock all current mappings */ #define MCL_FUTURE 2 /* lock all future mappings */ From 95dc663aa6382fec92674e748682cefeeb2bfc22 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 26 Jul 2019 15:00:24 -0300 Subject: [PATCH 481/823] tools headers UAPI: Update tools's copy of drm.h headers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Picking the changes from: c5d3e39caa45 ("drm/i915: Engine discovery query") a88b6e4cbafd ("drm/i915: Allow specification of parallel execbuf") ee1136908e9b ("drm/i915/execlists: Virtual engine bonding") 6d06779e8672 ("drm/i915: Load balancing across a virtual engine") b81dde719439 ("drm/i915: Allow userspace to clone contexts on creation") 8319f44c0525 ("drm/i915: Re-expose SINGLE_TIMELINE flags for context creation") e620f7b3a263 ("drm/i915: Extend I915_CONTEXT_PARAM_SSEU to support local ctx->engine[]") 976b55f0e1db ("drm/i915: Allow a context to define its set of engines") 7f3f317a66ca ("drm/i915: Restore control over ppgtt for context creation ABI") 75b3f1cb50bd ("drm: Fix drm.h uapi header for GNU/kFreeBSD") Silencing these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/drm/drm.h' differs from latest version at 'include/uapi/drm/drm.h' diff -u tools/include/uapi/drm/drm.h include/uapi/drm/drm.h Warning: Kernel ABI header at 'tools/include/uapi/drm/i915_drm.h' differs from latest version at 'include/uapi/drm/i915_drm.h' diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h Now 'perf trace' and other code that might use the tools/perf/trace/beauty autogenerated tables will be able to translate this new ioctl code into a string: $ tools/perf/trace/beauty/drm_ioctl.sh > before $ cp include/uapi/drm/i915_drm.h tools/include/uapi/drm/i915_drm.h $ tools/perf/trace/beauty/drm_ioctl.sh > after $ diff -u before after --- before 2019-07-26 13:02:22.052723640 -0300 +++ after 2019-07-26 13:02:35.354906036 -0300 @@ -163,4 +163,6 @@ [DRM_COMMAND_BASE + 0x37] = "I915_PERF_ADD_CONFIG", [DRM_COMMAND_BASE + 0x38] = "I915_PERF_REMOVE_CONFIG", [DRM_COMMAND_BASE + 0x39] = "I915_QUERY", + [DRM_COMMAND_BASE + 0x3a] = "I915_GEM_VM_CREATE", + [DRM_COMMAND_BASE + 0x3b] = "I915_GEM_VM_DESTROY", }; $ Cc: Adrian Hunter Cc: Chris Wilson Cc: Eric Anholt Cc: James Clarke Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Cc: Tvrtko Ursulin Link: https://lkml.kernel.org/n/tip-a9173whgu3h1vo24jgdg5do8@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/drm/drm.h | 1 + tools/include/uapi/drm/i915_drm.h | 209 +++++++++++++++++++++++++++++- 2 files changed, 207 insertions(+), 3 deletions(-) diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 661d73f9a919..8a5b2f8f8eb9 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -50,6 +50,7 @@ typedef unsigned int drm_handle_t; #else /* One of the BSDs */ +#include #include #include typedef int8_t __s8; diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 3a73f5316766..328d05e77d9f 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -136,6 +136,8 @@ enum drm_i915_gem_engine_class { struct i915_engine_class_instance { __u16 engine_class; /* see enum drm_i915_gem_engine_class */ __u16 engine_instance; +#define I915_ENGINE_CLASS_INVALID_NONE -1 +#define I915_ENGINE_CLASS_INVALID_VIRTUAL -2 }; /** @@ -355,6 +357,8 @@ typedef struct _drm_i915_sarea { #define DRM_I915_PERF_ADD_CONFIG 0x37 #define DRM_I915_PERF_REMOVE_CONFIG 0x38 #define DRM_I915_QUERY 0x39 +#define DRM_I915_GEM_VM_CREATE 0x3a +#define DRM_I915_GEM_VM_DESTROY 0x3b /* Must be kept compact -- no holes */ #define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) @@ -415,6 +419,8 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_PERF_ADD_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config) #define DRM_IOCTL_I915_PERF_REMOVE_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64) #define DRM_IOCTL_I915_QUERY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query) +#define DRM_IOCTL_I915_GEM_VM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_VM_CREATE, struct drm_i915_gem_vm_control) +#define DRM_IOCTL_I915_GEM_VM_DESTROY DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_VM_DESTROY, struct drm_i915_gem_vm_control) /* Allow drivers to submit batchbuffers directly to hardware, relying * on the security mechanisms provided by hardware. @@ -598,6 +604,12 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_MMAP_GTT_COHERENT 52 +/* + * Query whether DRM_I915_GEM_EXECBUFFER2 supports coordination of parallel + * execution through use of explicit fence support. + * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT. + */ +#define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53 /* Must be kept compact -- no holes and well documented */ typedef struct drm_i915_getparam { @@ -1120,7 +1132,16 @@ struct drm_i915_gem_execbuffer2 { */ #define I915_EXEC_FENCE_ARRAY (1<<19) -#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1)) +/* + * Setting I915_EXEC_FENCE_SUBMIT implies that lower_32_bits(rsvd2) represent + * a sync_file fd to wait upon (in a nonblocking manner) prior to executing + * the batch. + * + * Returns -EINVAL if the sync_file fd cannot be found. + */ +#define I915_EXEC_FENCE_SUBMIT (1 << 20) + +#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1)) #define I915_EXEC_CONTEXT_ID_MASK (0xffffffff) #define i915_execbuffer2_set_context_id(eb2, context) \ @@ -1464,8 +1485,9 @@ struct drm_i915_gem_context_create_ext { __u32 ctx_id; /* output: id of new context*/ __u32 flags; #define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS (1u << 0) +#define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE (1u << 1) #define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \ - (-(I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS << 1)) + (-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1)) __u64 extensions; }; @@ -1507,6 +1529,41 @@ struct drm_i915_gem_context_param { * On creation, all new contexts are marked as recoverable. */ #define I915_CONTEXT_PARAM_RECOVERABLE 0x8 + + /* + * The id of the associated virtual memory address space (ppGTT) of + * this context. Can be retrieved and passed to another context + * (on the same fd) for both to use the same ppGTT and so share + * address layouts, and avoid reloading the page tables on context + * switches between themselves. + * + * See DRM_I915_GEM_VM_CREATE and DRM_I915_GEM_VM_DESTROY. + */ +#define I915_CONTEXT_PARAM_VM 0x9 + +/* + * I915_CONTEXT_PARAM_ENGINES: + * + * Bind this context to operate on this subset of available engines. Henceforth, + * the I915_EXEC_RING selector for DRM_IOCTL_I915_GEM_EXECBUFFER2 operates as + * an index into this array of engines; I915_EXEC_DEFAULT selecting engine[0] + * and upwards. Slots 0...N are filled in using the specified (class, instance). + * Use + * engine_class: I915_ENGINE_CLASS_INVALID, + * engine_instance: I915_ENGINE_CLASS_INVALID_NONE + * to specify a gap in the array that can be filled in later, e.g. by a + * virtual engine used for load balancing. + * + * Setting the number of engines bound to the context to 0, by passing a zero + * sized argument, will revert back to default settings. + * + * See struct i915_context_param_engines. + * + * Extensions: + * i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE) + * i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND) + */ +#define I915_CONTEXT_PARAM_ENGINES 0xa /* Must be kept compact -- no holes and well documented */ __u64 value; @@ -1540,9 +1597,10 @@ struct drm_i915_gem_context_param_sseu { struct i915_engine_class_instance engine; /* - * Unused for now. Must be cleared to zero. + * Unknown flags must be cleared to zero. */ __u32 flags; +#define I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX (1u << 0) /* * Mask of slices to enable for the context. Valid values are a subset @@ -1570,12 +1628,115 @@ struct drm_i915_gem_context_param_sseu { __u32 rsvd; }; +/* + * i915_context_engines_load_balance: + * + * Enable load balancing across this set of engines. + * + * Into the I915_EXEC_DEFAULT slot [0], a virtual engine is created that when + * used will proxy the execbuffer request onto one of the set of engines + * in such a way as to distribute the load evenly across the set. + * + * The set of engines must be compatible (e.g. the same HW class) as they + * will share the same logical GPU context and ring. + * + * To intermix rendering with the virtual engine and direct rendering onto + * the backing engines (bypassing the load balancing proxy), the context must + * be defined to use a single timeline for all engines. + */ +struct i915_context_engines_load_balance { + struct i915_user_extension base; + + __u16 engine_index; + __u16 num_siblings; + __u32 flags; /* all undefined flags must be zero */ + + __u64 mbz64; /* reserved for future use; must be zero */ + + struct i915_engine_class_instance engines[0]; +} __attribute__((packed)); + +#define I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(name__, N__) struct { \ + struct i915_user_extension base; \ + __u16 engine_index; \ + __u16 num_siblings; \ + __u32 flags; \ + __u64 mbz64; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + +/* + * i915_context_engines_bond: + * + * Constructed bonded pairs for execution within a virtual engine. + * + * All engines are equal, but some are more equal than others. Given + * the distribution of resources in the HW, it may be preferable to run + * a request on a given subset of engines in parallel to a request on a + * specific engine. We enable this selection of engines within a virtual + * engine by specifying bonding pairs, for any given master engine we will + * only execute on one of the corresponding siblings within the virtual engine. + * + * To execute a request in parallel on the master engine and a sibling requires + * coordination with a I915_EXEC_FENCE_SUBMIT. + */ +struct i915_context_engines_bond { + struct i915_user_extension base; + + struct i915_engine_class_instance master; + + __u16 virtual_index; /* index of virtual engine in ctx->engines[] */ + __u16 num_bonds; + + __u64 flags; /* all undefined flags must be zero */ + __u64 mbz64[4]; /* reserved for future use; must be zero */ + + struct i915_engine_class_instance engines[0]; +} __attribute__((packed)); + +#define I915_DEFINE_CONTEXT_ENGINES_BOND(name__, N__) struct { \ + struct i915_user_extension base; \ + struct i915_engine_class_instance master; \ + __u16 virtual_index; \ + __u16 num_bonds; \ + __u64 flags; \ + __u64 mbz64[4]; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + +struct i915_context_param_engines { + __u64 extensions; /* linked chain of extension blocks, 0 terminates */ +#define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ +#define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */ + struct i915_engine_class_instance engines[0]; +} __attribute__((packed)); + +#define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \ + __u64 extensions; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + struct drm_i915_gem_context_create_ext_setparam { #define I915_CONTEXT_CREATE_EXT_SETPARAM 0 struct i915_user_extension base; struct drm_i915_gem_context_param param; }; +struct drm_i915_gem_context_create_ext_clone { +#define I915_CONTEXT_CREATE_EXT_CLONE 1 + struct i915_user_extension base; + __u32 clone_id; + __u32 flags; +#define I915_CONTEXT_CLONE_ENGINES (1u << 0) +#define I915_CONTEXT_CLONE_FLAGS (1u << 1) +#define I915_CONTEXT_CLONE_SCHEDATTR (1u << 2) +#define I915_CONTEXT_CLONE_SSEU (1u << 3) +#define I915_CONTEXT_CLONE_TIMELINE (1u << 4) +#define I915_CONTEXT_CLONE_VM (1u << 5) +#define I915_CONTEXT_CLONE_UNKNOWN -(I915_CONTEXT_CLONE_VM << 1) + __u64 rsvd; +}; + struct drm_i915_gem_context_destroy { __u32 ctx_id; __u32 pad; @@ -1821,6 +1982,7 @@ struct drm_i915_perf_oa_config { struct drm_i915_query_item { __u64 query_id; #define DRM_I915_QUERY_TOPOLOGY_INFO 1 +#define DRM_I915_QUERY_ENGINE_INFO 2 /* Must be kept compact -- no holes and well documented */ /* @@ -1919,6 +2081,47 @@ struct drm_i915_query_topology_info { __u8 data[]; }; +/** + * struct drm_i915_engine_info + * + * Describes one engine and it's capabilities as known to the driver. + */ +struct drm_i915_engine_info { + /** Engine class and instance. */ + struct i915_engine_class_instance engine; + + /** Reserved field. */ + __u32 rsvd0; + + /** Engine flags. */ + __u64 flags; + + /** Capabilities of this engine. */ + __u64 capabilities; +#define I915_VIDEO_CLASS_CAPABILITY_HEVC (1 << 0) +#define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC (1 << 1) + + /** Reserved fields. */ + __u64 rsvd1[4]; +}; + +/** + * struct drm_i915_query_engine_info + * + * Engine info query enumerates all engines known to the driver by filling in + * an array of struct drm_i915_engine_info structures. + */ +struct drm_i915_query_engine_info { + /** Number of struct drm_i915_engine_info structs following. */ + __u32 num_engines; + + /** MBZ */ + __u32 rsvd[3]; + + /** Marker for drm_i915_engine_info structures. */ + struct drm_i915_engine_info engines[]; +}; + #if defined(__cplusplus) } #endif From 7ee526152db7a75d7b8713346dac76ffc3662b29 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 26 Jul 2019 15:29:56 -0300 Subject: [PATCH 482/823] tools perf beauty: Fix usbdevfs_ioctl table generator to handle _IOC() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In addition to _IOW() and _IOR(), to handle this case: #define USBDEVFS_CONNINFO_EX(len) _IOC(_IOC_READ, 'U', 32, len) That will happen in the next sync of this header file. Cc: Adrian Hunter Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-3br5e4t64e4lp0goo84che3s@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/usbdevfs_ioctl.sh | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/tools/perf/trace/beauty/usbdevfs_ioctl.sh b/tools/perf/trace/beauty/usbdevfs_ioctl.sh index 930b80f422e8..aa597ae53747 100755 --- a/tools/perf/trace/beauty/usbdevfs_ioctl.sh +++ b/tools/perf/trace/beauty/usbdevfs_ioctl.sh @@ -3,10 +3,13 @@ [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ +# also as: +# #define USBDEVFS_CONNINFO_EX(len) _IOC(_IOC_READ, 'U', 32, len) + printf "static const char *usbdevfs_ioctl_cmds[] = {\n" -regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)[[:space:]]+_IO[WR]{0,2}\([[:space:]]*'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*" -egrep $regex ${header_dir}/usbdevice_fs.h | egrep -v 'USBDEVFS_\w+32[[:space:]]' | \ - sed -r "s/$regex/\2 \1/g" | \ +regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)(\(\w+\))?[[:space:]]+_IO[CWR]{0,2}\([[:space:]]*(_IOC_\w+,[[:space:]]*)?'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*" +egrep "$regex" ${header_dir}/usbdevice_fs.h | egrep -v 'USBDEVFS_\w+32[[:space:]]' | \ + sed -r "s/$regex/\4 \1/g" | \ sort | xargs printf "\t[%s] = \"%s\",\n" printf "};\n\n" printf "#if 0\n" From 0f58163c9d5702efbc242d144fd038e54b4c6ad0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 26 Jul 2019 15:31:25 -0300 Subject: [PATCH 483/823] tools headers UAPI: Sync usbdevice_fs.h with the kernels to get new ioctl MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To get the changes in: 6d101f24f1dd ("USB: add usbfs ioctl to retrieve the connection parameters") And address this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/usbdevice_fs.h' differs from latest version at 'include/uapi/linux/usbdevice_fs.h' diff -u tools/include/uapi/linux/usbdevice_fs.h include/uapi/linux/usbdevice_fs.h Which ends up autogenerating a ioctl_cmd->string table used by 'perf trace': $ tools/perf/trace/beauty/usbdevfs_ioctl.sh > before $ cp include/uapi/linux/usbdevice_fs.h tools/include/uapi/linux/usbdevice_fs.h $ tools/perf/trace/beauty/usbdevfs_ioctl.sh > after $ diff -u before after --- before 2019-07-26 15:26:55.513636844 -0300 +++ after 2019-07-26 15:29:11.650518677 -0300 @@ -23,6 +23,7 @@ [2] = "BULK", [30] = "DROP_PRIVILEGES", [31] = "GET_SPEED", + [32] = "CONNINFO_EX", [3] = "RESETEP", [4] = "SETINTERFACE", [5] = "SETCONFIGURATION", $ Now 'perf trace' ioctl beautifier will translate this new ioctl to a string and at some point will allow filtering the 'ioctl' syscall with something like this in a system wide strace-like sessin: # perf trace -e ioctl/cmd=USBDEVFS_CONNINFO_EX/ Cc: Adrian Hunter Cc: Dmitry Torokhov Cc: Greg Kroah-Hartman Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-tkdfbgzqypwco96b309c0ovd@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/usbdevice_fs.h | 26 +++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/tools/include/uapi/linux/usbdevice_fs.h b/tools/include/uapi/linux/usbdevice_fs.h index 964e87217be4..78efe870c2b7 100644 --- a/tools/include/uapi/linux/usbdevice_fs.h +++ b/tools/include/uapi/linux/usbdevice_fs.h @@ -76,6 +76,26 @@ struct usbdevfs_connectinfo { unsigned char slow; }; +struct usbdevfs_conninfo_ex { + __u32 size; /* Size of the structure from the kernel's */ + /* point of view. Can be used by userspace */ + /* to determine how much data can be */ + /* used/trusted. */ + __u32 busnum; /* USB bus number, as enumerated by the */ + /* kernel, the device is connected to. */ + __u32 devnum; /* Device address on the bus. */ + __u32 speed; /* USB_SPEED_* constants from ch9.h */ + __u8 num_ports; /* Number of ports the device is connected */ + /* to on the way to the root hub. It may */ + /* be bigger than size of 'ports' array so */ + /* userspace can detect overflows. */ + __u8 ports[7]; /* List of ports on the way from the root */ + /* hub to the device. Current limit in */ + /* USB specification is 7 tiers (root hub, */ + /* 5 intermediate hubs, device), which */ + /* gives at most 6 port entries. */ +}; + #define USBDEVFS_URB_SHORT_NOT_OK 0x01 #define USBDEVFS_URB_ISO_ASAP 0x02 #define USBDEVFS_URB_BULK_CONTINUATION 0x04 @@ -137,6 +157,7 @@ struct usbdevfs_hub_portinfo { #define USBDEVFS_CAP_REAP_AFTER_DISCONNECT 0x10 #define USBDEVFS_CAP_MMAP 0x20 #define USBDEVFS_CAP_DROP_PRIVILEGES 0x40 +#define USBDEVFS_CAP_CONNINFO_EX 0x80 /* USBDEVFS_DISCONNECT_CLAIM flags & struct */ @@ -197,5 +218,10 @@ struct usbdevfs_streams { #define USBDEVFS_FREE_STREAMS _IOR('U', 29, struct usbdevfs_streams) #define USBDEVFS_DROP_PRIVILEGES _IOW('U', 30, __u32) #define USBDEVFS_GET_SPEED _IO('U', 31) +/* + * Returns struct usbdevfs_conninfo_ex; length is variable to allow + * extending size of the data returned. + */ +#define USBDEVFS_CONNINFO_EX(len) _IOC(_IOC_READ, 'U', 32, len) #endif /* _UAPI_LINUX_USBDEVICE_FS_H */ From c093de6bd3c50d3dd597ff9fa5cf7a30acbb3eb7 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 26 Jul 2019 15:41:09 -0300 Subject: [PATCH 484/823] tools headers UAPI: Sync sched.h with the kernel MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To get the changes in: a509a7cd7974 ("sched/uclamp: Extend sched_setattr() to support utilization clamping") 1d6362fa0cfc ("sched/core: Allow sched_setattr() to use the current policy") 7f192e3cd316 ("fork: add clone3") And silence this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/sched.h' differs from latest version at 'include/uapi/linux/sched.h' diff -u tools/include/uapi/linux/sched.h include/uapi/linux/sched.h No changes in tools/ due to the above. Cc: Adrian Hunter Cc: Christian Brauner Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Cc: Patrick Bellasi Link: https://lkml.kernel.org/n/tip-mtrpsjrux5hgyr5uf8l1aa46@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/sched.h | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-) diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h index ed4ee170bee2..b3105ac1381a 100644 --- a/tools/include/uapi/linux/sched.h +++ b/tools/include/uapi/linux/sched.h @@ -2,6 +2,8 @@ #ifndef _UAPI_LINUX_SCHED_H #define _UAPI_LINUX_SCHED_H +#include + /* * cloning flags: */ @@ -31,6 +33,20 @@ #define CLONE_NEWNET 0x40000000 /* New network namespace */ #define CLONE_IO 0x80000000 /* Clone io context */ +/* + * Arguments for the clone3 syscall + */ +struct clone_args { + __aligned_u64 flags; + __aligned_u64 pidfd; + __aligned_u64 child_tid; + __aligned_u64 parent_tid; + __aligned_u64 exit_signal; + __aligned_u64 stack; + __aligned_u64 stack_size; + __aligned_u64 tls; +}; + /* * Scheduling policies */ @@ -51,9 +67,21 @@ #define SCHED_FLAG_RESET_ON_FORK 0x01 #define SCHED_FLAG_RECLAIM 0x02 #define SCHED_FLAG_DL_OVERRUN 0x04 +#define SCHED_FLAG_KEEP_POLICY 0x08 +#define SCHED_FLAG_KEEP_PARAMS 0x10 +#define SCHED_FLAG_UTIL_CLAMP_MIN 0x20 +#define SCHED_FLAG_UTIL_CLAMP_MAX 0x40 + +#define SCHED_FLAG_KEEP_ALL (SCHED_FLAG_KEEP_POLICY | \ + SCHED_FLAG_KEEP_PARAMS) + +#define SCHED_FLAG_UTIL_CLAMP (SCHED_FLAG_UTIL_CLAMP_MIN | \ + SCHED_FLAG_UTIL_CLAMP_MAX) #define SCHED_FLAG_ALL (SCHED_FLAG_RESET_ON_FORK | \ SCHED_FLAG_RECLAIM | \ - SCHED_FLAG_DL_OVERRUN) + SCHED_FLAG_DL_OVERRUN | \ + SCHED_FLAG_KEEP_ALL | \ + SCHED_FLAG_UTIL_CLAMP) #endif /* _UAPI_LINUX_SCHED_H */ From e54599c93dbf487ef80ba2833c5760c22bd20c32 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 26 Jul 2019 15:44:41 -0300 Subject: [PATCH 485/823] tools headers UAPI: Sync if_link.h with the kernel MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To pick the changes in: 07a4ddec3ce9 ("bonding: add an option to specify a delay between peer notifications") And silence this build warning: Kernel ABI header at 'tools/include/uapi/linux/if_link.h' differs from latest version at 'include/uapi/linux/if_link.h' Cc: Adrian Hunter Cc: David S. Miller Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Cc: Vincent Bernat Link: https://lkml.kernel.org/n/tip-3liw4exxh8goc0rq9xryl2kv@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/if_link.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 7d113a9602f0..4a8c02cafa9a 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -695,6 +695,7 @@ enum { IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */ IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */ IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */ + IFLA_VF_BROADCAST, /* VF broadcast */ __IFLA_VF_MAX, }; @@ -705,6 +706,10 @@ struct ifla_vf_mac { __u8 mac[32]; /* MAX_ADDR_LEN */ }; +struct ifla_vf_broadcast { + __u8 broadcast[32]; +}; + struct ifla_vf_vlan { __u32 vf; __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ From 7622236ceb167aa3857395f9bdaf871442aa467e Mon Sep 17 00:00:00 2001 From: Vince Weaver Date: Tue, 23 Jul 2019 11:06:01 -0400 Subject: [PATCH 486/823] perf header: Fix divide by zero error if f_header.attr_size==0 So I have been having lots of trouble with hand-crafted perf.data files causing segfaults and the like, so I have started fuzzing the perf tool. First issue found: If f_header.attr_size is 0 in the perf.data file, then perf will crash with a divide-by-zero error. Committer note: Added a pr_err() to tell the user why the command failed. Signed-off-by: Vince Weaver Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/alpine.DEB.2.21.1907231100440.14532@macbook-air Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/header.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 20111f8da5cb..47877f0f6667 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -3559,6 +3559,13 @@ int perf_session__read_header(struct perf_session *session) data->file.path); } + if (f_header.attr_size == 0) { + pr_err("ERROR: The %s file's attr size field is 0 which is unexpected.\n" + "Was the 'perf record' command properly terminated?\n", + data->file.path); + return -EINVAL; + } + nr_attrs = f_header.attrs.size / f_header.attr_size; lseek(fd, f_header.attrs.offset, SEEK_SET); From 20f9781f491360e7459c589705a2e4b1f136bee9 Mon Sep 17 00:00:00 2001 From: Numfor Mbiziwo-Tiapo Date: Wed, 24 Jul 2019 16:44:58 -0700 Subject: [PATCH 487/823] perf header: Fix use of unitialized value warning When building our local version of perf with MSAN (Memory Sanitizer) and running the perf record command, MSAN throws a use of uninitialized value warning in "tools/perf/util/util.c:333:6". This warning stems from the "buf" variable being passed into "write". It originated as the variable "ev" with the type union perf_event* defined in the "perf_event__synthesize_attr" function in "tools/perf/util/header.c". In the "perf_event__synthesize_attr" function they allocate space with a malloc call using ev, then go on to only assign some of the member variables before passing "ev" on as a parameter to the "process" function therefore "ev" contains uninitialized memory. Changing the malloc call to zalloc to initialize all the members of "ev" which gets rid of the warning. To reproduce this warning, build perf by running: make -C tools/perf CLANG=1 CC=clang EXTRA_CFLAGS="-fsanitize=memory\ -fsanitize-memory-track-origins" (Additionally, llvm might have to be installed and clang might have to be specified as the compiler - export CC=/usr/bin/clang) then running: tools/perf/perf record -o - ls / | tools/perf/perf --no-pager annotate\ -i - --stdio Please see the cover letter for why false positive warnings may be generated. Signed-off-by: Numfor Mbiziwo-Tiapo Cc: Alexander Shishkin Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Drayton Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20190724234500.253358-2-nums@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/header.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 47877f0f6667..1903d7ec9797 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -3646,7 +3646,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool, size += sizeof(struct perf_event_header); size += ids * sizeof(u64); - ev = malloc(size); + ev = zalloc(size); if (ev == NULL) return -ENOMEM; From 2e9a06dda10aea81a17c623f08534dac6735434a Mon Sep 17 00:00:00 2001 From: Vince Weaver Date: Thu, 25 Jul 2019 11:57:43 -0400 Subject: [PATCH 488/823] perf tools: Fix perf.data documentation units for memory size The perf.data-file-format documentation incorrectly says the HEADER_TOTAL_MEM results are in bytes. The results are in kilobytes (perf reads the value from /proc/meminfo) Signed-off-by: Vince Weaver Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/alpine.DEB.2.21.1907251155500.22624@macbook-air Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf.data-file-format.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index 5f54feb19977..d030c87ed9f5 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -126,7 +126,7 @@ vendor,family,model,stepping. For example: GenuineIntel,6,69,1 HEADER_TOTAL_MEM = 10, -An uint64_t with the total memory in bytes. +An uint64_t with the total memory in kilobytes. HEADER_CMDLINE = 11, From 705d0abbcc7adf04743d04ea8754acbcdf21c326 Mon Sep 17 00:00:00 2001 From: Santosh Sivaraj Date: Mon, 29 Jul 2019 11:25:36 +0530 Subject: [PATCH 489/823] powerpc/kvm: Fall through switch case explicitly Implicit fallthrough warning was enabled globally which broke the build. Make it explicit with a `fall through` comment. Signed-off-by: Santosh Sivaraj Reviewed-by: Stephen Rothwell Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190729055536.25591-1-santosh@fossix.org --- arch/powerpc/kvm/book3s_32_mmu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index 653936177857..18f244aad7aa 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -239,6 +239,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr, case 2: case 6: pte->may_write = true; + /* fall through */ case 3: case 5: case 7: From c270cac40828eca4fb8d7c27cab1d0ac7765ff3d Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Sat, 29 Jun 2019 14:13:50 +0100 Subject: [PATCH 490/823] drm/i915: fix whitelist selftests with readonly registers When a register is readonly there is not much we can tell about its value (apart from its default value?). This can be covered by tests exercising the value of the register from userspace. For PS_INVOCATION_COUNT we've got the following piglit tests : KHR-GL45.pipeline_statistics_query_tests_ARB.functional_fragment_shader_invocations Vulkan CTS tests : dEQP-VK.query_pool.statistics_query.fragment_shader_invocations.* v2: Use a local to shrink under 80cols. Signed-off-by: Lionel Landwerlin Fixes: 86554f48e511 ("drm/i915/selftests: Verify whitelist of context registers") Tested-by: Anuj Phogat Signed-off-by: Chris Wilson Reviewed-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20190629131350.31185-1-chris@chris-wilson.co.uk (cherry picked from commit 361b69051326ed0e07553315227678d00d651a9e) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gt/selftest_workarounds.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c index 9eaf030affd0..44becd9538be 100644 --- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c +++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c @@ -925,7 +925,12 @@ check_whitelisted_registers(struct intel_engine_cs *engine, err = 0; for (i = 0; i < engine->whitelist.count; i++) { - if (!fn(engine, a[i], b[i], engine->whitelist.list[i].reg)) + const struct i915_wa *wa = &engine->whitelist.list[i]; + + if (i915_mmio_reg_offset(wa->reg) & RING_FORCE_TO_NONPRIV_RD) + continue; + + if (!fn(engine, a[i], b[i], wa->reg)) err = -EINVAL; } From 6ce5bfe936ac31d5c52c4b1328d0bfda5f97e7ca Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Fri, 28 Jun 2019 15:07:19 +0300 Subject: [PATCH 491/823] drm/i915: whitelist PS_(DEPTH|INVOCATION)_COUNT CFL:C0+ changed the status of those registers which are now blacklisted by default. This is breaking a number of CTS tests on GL & Vulkan : KHR-GL45.pipeline_statistics_query_tests_ARB.functional_fragment_shader_invocations (GL) dEQP-VK.query_pool.statistics_query.fragment_shader_invocations.* (Vulkan) v2: Only use one whitelist entry (Lionel) Bspec: 14091 Signed-off-by: Lionel Landwerlin Cc: stable@vger.kernel.org # 6883eab27481: drm/i915: Support flags in whitlist WAs Cc: stable@vger.kernel.org Acked-by: Chris Wilson Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20190628120720.21682-3-lionel.g.landwerlin@intel.com (cherry picked from commit 2c903da50f5a9522b134e488bd0f92646c46f3c0) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gt/intel_workarounds.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 50c0060509a6..b26c3549429e 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -1098,10 +1098,25 @@ static void glk_whitelist_build(struct intel_engine_cs *engine) static void cfl_whitelist_build(struct intel_engine_cs *engine) { + struct i915_wa_list *w = &engine->whitelist; + if (engine->class != RENDER_CLASS) return; - gen9_whitelist_build(&engine->whitelist); + gen9_whitelist_build(w); + + /* + * WaAllowPMDepthAndInvocationCountAccessFromUMD:cfl,whl,cml,aml + * + * This covers 4 register which are next to one another : + * - PS_INVOCATION_COUNT + * - PS_INVOCATION_COUNT_UDW + * - PS_DEPTH_COUNT + * - PS_DEPTH_COUNT_UDW + */ + whitelist_reg_ext(w, PS_INVOCATION_COUNT, + RING_FORCE_TO_NONPRIV_RD | + RING_FORCE_TO_NONPRIV_RANGE_4); } static void cnl_whitelist_build(struct intel_engine_cs *engine) From cf8f9aa1eda7d916bd23f6b8c226404deb11690c Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Fri, 28 Jun 2019 15:07:20 +0300 Subject: [PATCH 492/823] drm/i915/icl: whitelist PS_(DEPTH|INVOCATION)_COUNT The same tests failing on CFL+ platforms are also failing on ICL. Documentation doesn't list the WaAllowPMDepthAndInvocationCountAccessFromUMD workaround for ICL but applying it fixes the same tests as CFL. v2: Use only one whitelist entry (Lionel) Signed-off-by: Lionel Landwerlin Tested-by: Anuj Phogat Cc: stable@vger.kernel.org # 6883eab27481: drm/i915: Support flags in whitlist WAs Cc: stable@vger.kernel.org Acked-by: Chris Wilson Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20190628120720.21682-4-lionel.g.landwerlin@intel.com (cherry picked from commit 3fe0107e45ab396342497e06b8924cdd485cde3b) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gt/intel_workarounds.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index b26c3549429e..98dfb086320f 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -1144,6 +1144,19 @@ static void icl_whitelist_build(struct intel_engine_cs *engine) /* WaEnableStateCacheRedirectToCS:icl */ whitelist_reg(w, GEN9_SLICE_COMMON_ECO_CHICKEN1); + + /* + * WaAllowPMDepthAndInvocationCountAccessFromUMD:icl + * + * This covers 4 register which are next to one another : + * - PS_INVOCATION_COUNT + * - PS_INVOCATION_COUNT_UDW + * - PS_DEPTH_COUNT + * - PS_DEPTH_COUNT_UDW + */ + whitelist_reg_ext(w, PS_INVOCATION_COUNT, + RING_FORCE_TO_NONPRIV_RD | + RING_FORCE_TO_NONPRIV_RANGE_4); break; case VIDEO_DECODE_CLASS: From fdcc789a4a0bb2ef01857095752be12b03cbb341 Mon Sep 17 00:00:00 2001 From: Mika Kuoppala Date: Mon, 1 Jul 2019 13:44:42 +0300 Subject: [PATCH 493/823] drm/i915: Fix memleak in runtime wakeref tracking If we untrack wakerefs, the actual count may reach zero. However the krealloced owners array is still there and needs to be taken care of. Free the owners unconditionally to fix the leak. Fixes: bd780f37a361 ("drm/i915: Track all held rpm wakerefs") Reported-by: Juha-Pekka Heikkila Cc: Juha-Pekka Heikkila Cc: Chris Wilson Signed-off-by: Mika Kuoppala Reviewed-by: Chris Wilson Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20190701104442.9319-1-mika.kuoppala@linux.intel.com (cherry picked from commit c5f846eed2a1856b78e988eeef08215c70598ecd) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_runtime_pm.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 502c54428570..8d1aebc3e857 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -221,13 +221,11 @@ __untrack_all_wakerefs(struct intel_runtime_pm_debug *debug, static void dump_and_free_wakeref_tracking(struct intel_runtime_pm_debug *debug) { - struct drm_printer p; + if (debug->count) { + struct drm_printer p = drm_debug_printer("i915"); - if (!debug->count) - return; - - p = drm_debug_printer("i915"); - __print_intel_runtime_pm_wakeref(&p, debug); + __print_intel_runtime_pm_wakeref(&p, debug); + } kfree(debug->owners); } From d1b739f326b960631827f0ea350002c5bc8df443 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Thu, 6 Jun 2019 15:42:10 +0300 Subject: [PATCH 494/823] drm/i915: Deal with machines that expose less than three QGV points MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When SAGV is forced to disabled/min/med/max in the BIOS pcode will only hand us a single QGV point instead of the normal three. Fix the code to deal with that instead declaring the bandwidth limit to be 0 MB/s (and thus preventing any planes from being enabled). Also shrink the max_bw sturct a bit while at it, and change the deratedbw type to unsigned since the code returns the bw as an unsigned int. Since we now keep track of how many qgv points we got from pcode we can drop the earlier check added for the "pcode doesn't support the memory subsystem query" case. Cc: felix.j.degrood@intel.com Cc: Mark Janes Cc: Matt Roper Cc: Clint Taylor Fixes: c457d9cf256e ("drm/i915: Make sure we have enough memory bandwidth on ICL") Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=110838 Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20190606124210.3482-1-ville.syrjala@linux.intel.com Reviewed-by: Matt Roper (cherry picked from commit 56e9371bc3f3e7d6c1a197a45d550b2ce6af25f6) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_bw.c | 15 ++++++++++----- drivers/gpu/drm/i915/i915_drv.h | 5 +++-- 2 files changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index 753ac3165061..7b908e10d32e 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -178,6 +178,8 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv) clpchgroup = (sa->deburst * deinterleave / num_channels) << i; bi->num_planes = (ipqdepth - clpchgroup) / clpchgroup + 1; + bi->num_qgv_points = qi.num_points; + for (j = 0; j < qi.num_points; j++) { const struct intel_qgv_point *sp = &qi.points[j]; int ct, bw; @@ -195,7 +197,7 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv) bi->deratedbw[j] = min(maxdebw, bw * 9 / 10); /* 90% */ - DRM_DEBUG_KMS("BW%d / QGV %d: num_planes=%d deratedbw=%d\n", + DRM_DEBUG_KMS("BW%d / QGV %d: num_planes=%d deratedbw=%u\n", i, j, bi->num_planes, bi->deratedbw[j]); } @@ -211,14 +213,17 @@ static unsigned int icl_max_bw(struct drm_i915_private *dev_priv, { int i; - /* Did we initialize the bw limits successfully? */ - if (dev_priv->max_bw[0].num_planes == 0) - return UINT_MAX; - for (i = 0; i < ARRAY_SIZE(dev_priv->max_bw); i++) { const struct intel_bw_info *bi = &dev_priv->max_bw[i]; + /* + * Pcode will not expose all QGV points when + * SAGV is forced to off/min/med/max. + */ + if (qgv_point >= bi->num_qgv_points) + return UINT_MAX; + if (num_planes >= bi->num_planes) return bi->deratedbw[qgv_point]; } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index bc909ec5d9c3..fe7a6ec2c199 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1674,8 +1674,9 @@ struct drm_i915_private { } dram_info; struct intel_bw_info { - int num_planes; - int deratedbw[3]; + unsigned int deratedbw[3]; /* for each QGV point */ + u8 num_qgv_points; + u8 num_planes; } max_bw[6]; struct drm_private_obj bw_obj; From f691eaa4801484fffc8a2bcb24caa27fb2edcce3 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 3 Jul 2019 18:19:12 +0100 Subject: [PATCH 495/823] drm/i915/gtt: Defer the free for alloc error paths If we hit an error while allocating the page tables, we have to unwind the incomplete updates, and wish to free the unused pd. However, we are not allowed to be hoding the spinlock at that point, and so must use the later free to defer it until after we drop the lock. <3> [414.363795] BUG: sleeping function called from invalid context at drivers/gpu/drm/i915/i915_gem_gtt.c:472 <3> [414.364167] in_atomic(): 1, irqs_disabled(): 0, pid: 3905, name: i915_selftest <4> [414.364406] 3 locks held by i915_selftest/3905: <4> [414.364408] #0: 0000000034fe8aa8 (&dev->mutex){....}, at: device_driver_attach+0x18/0x50 <4> [414.364415] #1: 000000006bd8a560 (&dev->struct_mutex){+.+.}, at: igt_ctx_exec+0xb7/0x410 [i915] <4> [414.364476] #2: 000000003dfdc766 (&(&pd->lock)->rlock){+.+.}, at: gen8_ppgtt_alloc_pdp+0x448/0x540 [i915] <3> [414.364529] Preemption disabled at: <4> [414.364530] [<0000000000000000>] 0x0 <4> [414.364696] CPU: 0 PID: 3905 Comm: i915_selftest Tainted: G U 5.2.0-rc7-CI-CI_DRM_6403+ #1 <4> [414.364698] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.1-0-g8891697-prebuilt.qemu-project.org 04/01/2014 <4> [414.364699] Call Trace: <4> [414.364704] dump_stack+0x67/0x9b <4> [414.364708] ___might_sleep+0x167/0x250 <4> [414.364777] vm_free_page+0x24/0xc0 [i915] <4> [414.364852] free_pd+0xf/0x20 [i915] <4> [414.364897] gen8_ppgtt_alloc_pdp+0x489/0x540 [i915] <4> [414.364946] gen8_ppgtt_alloc_4lvl+0x8e/0x2e0 [i915] <4> [414.364992] ppgtt_bind_vma+0x2e/0x60 [i915] <4> [414.365039] i915_vma_bind+0xe8/0x2c0 [i915] <4> [414.365088] __i915_vma_do_pin+0xa1/0xd20 [i915] Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111050 Fixes: 1d1b5490b91c ("drm/i915/gtt: Replace struct_mutex serialisation for allocation") Signed-off-by: Chris Wilson Cc: Matthew Auld Cc: Mika Kuoppala Reviewed-by: Mika Kuoppala Link: https://patchwork.freedesktop.org/patch/msgid/20190703171913.16585-3-chris@chris-wilson.co.uk (cherry picked from commit 068610895ebd4bd86f496f01eb7b97e56d7269b2) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_gem_gtt.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 8ab820145ea6..50fe72d40d8b 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -1446,7 +1446,8 @@ unwind_pd: gen8_ppgtt_set_pdpe(pdp, vm->scratch_pd, pdpe); GEM_BUG_ON(!atomic_read(&pdp->used)); atomic_dec(&pdp->used); - free_pd(vm, pd); + GEM_BUG_ON(alloc); + alloc = pd; /* defer the free to after the lock */ } spin_unlock(&pdp->lock); unwind: @@ -1515,7 +1516,8 @@ unwind_pdp: spin_lock(&pml4->lock); if (atomic_dec_and_test(&pdp->used)) { gen8_ppgtt_set_pml4e(pml4, vm->scratch_pdp, pml4e); - free_pd(vm, pdp); + GEM_BUG_ON(alloc); + alloc = pdp; /* defer the free until after the lock */ } spin_unlock(&pml4->lock); unwind: From 5f4c82c89ff0e11b31561aa7e547acb10bf650c2 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 4 Jul 2019 21:16:56 +0100 Subject: [PATCH 496/823] drm/i915/gtt: Mark the freed page table entries with scratch On unwinding the allocation error path and having freed the page table entry, it is imperative that we mark it as scratch. <4> [416.075569] general protection fault: 0000 [#1] PREEMPT SMP PTI <4> [416.075801] CPU: 0 PID: 2385 Comm: kworker/u2:11 Tainted: G U 5.2.0-rc7-CI-Patchwork_13534+ #1 <4> [416.076162] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.1-0-g8891697-prebuilt.qemu-project.org 04/01/2014 <4> [416.076522] Workqueue: i915 __i915_vm_release [i915] <4> [416.076754] RIP: 0010:gen8_ppgtt_cleanup_3lvl+0x58/0xb0 [i915] <4> [416.077023] Code: 81 e2 04 fe ff ff 81 c2 ff 01 00 00 4c 8d 74 d6 58 4d 8b 65 00 4d 3b a7 28 02 00 00 74 40 49 8d 5c 24 50 49 81 c4 50 10 00 00 <48> 8b 2b 49 3b af 20 02 00 00 74 13 4c 89 ff 48 89 ee e8 01 fb ff <4> [416.077445] RSP: 0018:ffffc9000046bd98 EFLAGS: 00010206 <4> [416.077625] RAX: 0001000000000000 RBX: 6b6b6b6b6b6b6bbb RCX: 8b4b56d500000000 <4> [416.077838] RDX: 00000000000001ff RSI: ffff88805a578008 RDI: ffff88805bd0efc8 <4> [416.078167] RBP: ffff88805bd0efc8 R08: 0000000004e42b93 R09: 0000000000000001 <4> [416.078381] R10: 0000000000000000 R11: ffff888077a1b0b8 R12: 6b6b6b6b6b6b7bbb <4> [416.078594] R13: ffff88805a578058 R14: ffff88805a579058 R15: ffff88805bd0efc8 <4> [416.078815] FS: 0000000000000000(0000) GS:ffff88807da00000(0000) knlGS:0000000000000000 <4> [416.079395] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4> [416.079851] CR2: 000056160fec2b14 CR3: 0000000071bbc003 CR4: 00000000003606f0 <4> [416.080388] Call Trace: <4> [416.080828] gen8_ppgtt_cleanup+0x64/0x100 [i915] <4> [416.081399] __i915_vm_release+0xfc/0x1d0 [i915] Fixes: 1d1b5490b91c ("drm/i915/gtt: Replace struct_mutex serialisation for allocation") Signed-off-by: Chris Wilson Cc: Matthew Auld Cc: Mika Kuoppala Reviewed-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20190704201656.15775-1-chris@chris-wilson.co.uk (cherry picked from commit e7539b79f703a6b533385088fc15cb5c9ab3f56f) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_gem_gtt.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 50fe72d40d8b..7015a97b1097 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -1444,6 +1444,7 @@ unwind_pd: spin_lock(&pdp->lock); if (atomic_dec_and_test(&pd->used)) { gen8_ppgtt_set_pdpe(pdp, vm->scratch_pd, pdpe); + pdp->entry[pdpe] = vm->scratch_pd; GEM_BUG_ON(!atomic_read(&pdp->used)); atomic_dec(&pdp->used); GEM_BUG_ON(alloc); @@ -1516,6 +1517,7 @@ unwind_pdp: spin_lock(&pml4->lock); if (atomic_dec_and_test(&pdp->used)) { gen8_ppgtt_set_pml4e(pml4, vm->scratch_pdp, pml4e); + pml4->entry[pml4e] = vm->scratch_pdp; GEM_BUG_ON(alloc); alloc = pdp; /* defer the free until after the lock */ } From aa56a292ce623734ddd30f52d73f527d1f3529b5 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 8 Jul 2019 15:03:27 +0100 Subject: [PATCH 497/823] drm/i915/userptr: Acquire the page lock around set_page_dirty() set_page_dirty says: For pages with a mapping this should be done under the page lock for the benefit of asynchronous memory errors who prefer a consistent dirty state. This rule can be broken in some special cases, but should be better not to. Under those rules, it is only safe for us to use the plain set_page_dirty calls for shmemfs/anonymous memory. Userptr may be used with real mappings and so needs to use the locked version (set_page_dirty_lock). Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203317 Fixes: 5cc9ed4b9a7a ("drm/i915: Introduce mapping of user pages into video memory (userptr) ioctl") References: 6dcc693bc57f ("ext4: warn when page is dirtied without buffers") Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Cc: stable@vger.kernel.org Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20190708140327.26825-1-chris@chris-wilson.co.uk (cherry picked from commit cb6d7c7dc7ff8cace666ddec66334117a6068ce2) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gem/i915_gem_userptr.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 528b61678334..2caa594322bc 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -664,7 +664,15 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj, for_each_sgt_page(page, sgt_iter, pages) { if (obj->mm.dirty) - set_page_dirty(page); + /* + * As this may not be anonymous memory (e.g. shmem) + * but exist on a real mapping, we have to lock + * the page in order to dirty it -- holding + * the page reference is not sufficient to + * prevent the inode from being truncated. + * Play safe and take the lock. + */ + set_page_dirty_lock(page); mark_page_accessed(page); put_page(page); From 06c12ae3b401238477e65e8c4e04e065699a6115 Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Tue, 9 Jul 2019 15:33:39 +0300 Subject: [PATCH 498/823] drm/i915/perf: ensure we keep a reference on the driver The i915 perf stream has its own file descriptor and is tied to reference of the driver. We haven't taken care of keep the driver alive. Signed-off-by: Lionel Landwerlin Suggested-by: Chris Wilson Fixes: eec688e1420da5 ("drm/i915: Add i915 perf infrastructure") Reviewed-by: Chris Wilson Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20190709123351.5645-2-lionel.g.landwerlin@intel.com (cherry picked from commit a5af1df716c123a09341351008fc497bea137b77) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_perf.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 1ae06a1b6749..629511ea9a18 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -2515,6 +2515,9 @@ static int i915_perf_release(struct inode *inode, struct file *file) i915_perf_destroy_locked(stream); mutex_unlock(&dev_priv->perf.lock); + /* Release the reference the perf stream kept on the driver. */ + drm_dev_put(&dev_priv->drm); + return 0; } @@ -2650,6 +2653,11 @@ i915_perf_open_ioctl_locked(struct drm_i915_private *dev_priv, if (!(param->flags & I915_PERF_FLAG_DISABLED)) i915_perf_enable_locked(stream); + /* Take a reference on the driver that will be kept with stream_fd + * until its release. + */ + drm_dev_get(&dev_priv->drm); + return stream_fd; err_open: From 8f48de49795ca52f70c96558ccc6a0c174504779 Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Wed, 10 Jul 2019 11:55:24 +0100 Subject: [PATCH 499/823] drm/i915/perf: add missing delay for OA muxes configuration This was dropped from the original patch series, we weren't sure whether it was needed at the time. More recent tests show it's definitely needed to have acurate performance data. Signed-off-by: Lionel Landwerlin Fixes: 19f81df2859eb1 ("drm/i915/perf: Add OA unit support for Gen 8+") Acked-by: Chris Wilson [ickle: combine duplicate code and comments] Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20190710105524.23017-1-chris@chris-wilson.co.uk (cherry picked from commit 14bfcd3e0daeb0f757a02aac85fd03e0933ab37e) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_perf.c | 49 ++++++++++++++++++-------------- 1 file changed, 28 insertions(+), 21 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 629511ea9a18..5140017f9a39 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1567,28 +1567,10 @@ static void config_oa_regs(struct drm_i915_private *dev_priv, } } -static int hsw_enable_metric_set(struct i915_perf_stream *stream) +static void delay_after_mux(void) { - struct drm_i915_private *dev_priv = stream->dev_priv; - const struct i915_oa_config *oa_config = stream->oa_config; - - /* PRM: - * - * OA unit is using “crclk” for its functionality. When trunk - * level clock gating takes place, OA clock would be gated, - * unable to count the events from non-render clock domain. - * Render clock gating must be disabled when OA is enabled to - * count the events from non-render domain. Unit level clock - * gating for RCS should also be disabled. - */ - I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) & - ~GEN7_DOP_CLOCK_GATE_ENABLE)); - I915_WRITE(GEN6_UCGCTL1, (I915_READ(GEN6_UCGCTL1) | - GEN6_CSUNIT_CLOCK_GATE_DISABLE)); - - config_oa_regs(dev_priv, oa_config->mux_regs, oa_config->mux_regs_len); - - /* It apparently takes a fairly long time for a new MUX + /* + * It apparently takes a fairly long time for a new MUX * configuration to be be applied after these register writes. * This delay duration was derived empirically based on the * render_basic config but hopefully it covers the maximum @@ -1610,6 +1592,30 @@ static int hsw_enable_metric_set(struct i915_perf_stream *stream) * a delay at this location would mitigate any invalid reports. */ usleep_range(15000, 20000); +} + +static int hsw_enable_metric_set(struct i915_perf_stream *stream) +{ + struct drm_i915_private *dev_priv = stream->dev_priv; + const struct i915_oa_config *oa_config = stream->oa_config; + + /* + * PRM: + * + * OA unit is using “crclk” for its functionality. When trunk + * level clock gating takes place, OA clock would be gated, + * unable to count the events from non-render clock domain. + * Render clock gating must be disabled when OA is enabled to + * count the events from non-render domain. Unit level clock + * gating for RCS should also be disabled. + */ + I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) & + ~GEN7_DOP_CLOCK_GATE_ENABLE)); + I915_WRITE(GEN6_UCGCTL1, (I915_READ(GEN6_UCGCTL1) | + GEN6_CSUNIT_CLOCK_GATE_DISABLE)); + + config_oa_regs(dev_priv, oa_config->mux_regs, oa_config->mux_regs_len); + delay_after_mux(); config_oa_regs(dev_priv, oa_config->b_counter_regs, oa_config->b_counter_regs_len); @@ -1835,6 +1841,7 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream) return ret; config_oa_regs(dev_priv, oa_config->mux_regs, oa_config->mux_regs_len); + delay_after_mux(); config_oa_regs(dev_priv, oa_config->b_counter_regs, oa_config->b_counter_regs_len); From 982b1d002f16c2695871e005c4132060c836db56 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 15 Jul 2019 09:09:28 +0100 Subject: [PATCH 500/823] drm/i915: Lock the engine while dumping the active request We cannot let the request be retired and freed while we are trying to dump it during error capture. It is not sufficient just to grab a reference to the request, as during retirement we may free the ring which we are also dumping. So take the engine lock to prevent retiring and freeing of the request. Reported-by: Alex Shumsky Fixes: 83c317832eb1 ("drm/i915: Dump the ringbuffer of the active request for debugging") Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Cc: Joonas Lahtinen Cc: Alex Shumsky Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20190715080946.15593-6-chris@chris-wilson.co.uk (cherry picked from commit cfe7288c276e359eebf057699fe86c2f8af14224) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gt/intel_engine_cs.c | 11 ++++------- drivers/gpu/drm/i915/i915_gpu_error.c | 6 ++++-- 2 files changed, 8 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 7fd33e81c2d9..aa5a1f11a91b 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -1471,6 +1471,7 @@ void intel_engine_dump(struct intel_engine_cs *engine, struct i915_gpu_error * const error = &engine->i915->gpu_error; struct i915_request *rq; intel_wakeref_t wakeref; + unsigned long flags; if (header) { va_list ap; @@ -1490,10 +1491,9 @@ void intel_engine_dump(struct intel_engine_cs *engine, i915_reset_engine_count(error, engine), i915_reset_count(error)); - rcu_read_lock(); - drm_printf(m, "\tRequests:\n"); + spin_lock_irqsave(&engine->active.lock, flags); rq = intel_engine_find_active_request(engine); if (rq) { print_request(m, rq, "\t\tactive "); @@ -1513,8 +1513,7 @@ void intel_engine_dump(struct intel_engine_cs *engine, print_request_ring(m, rq); } - - rcu_read_unlock(); + spin_unlock_irqrestore(&engine->active.lock, flags); wakeref = intel_runtime_pm_get_if_in_use(&engine->i915->runtime_pm); if (wakeref) { @@ -1672,7 +1671,6 @@ struct i915_request * intel_engine_find_active_request(struct intel_engine_cs *engine) { struct i915_request *request, *active = NULL; - unsigned long flags; /* * We are called by the error capture, reset and to dump engine @@ -1685,7 +1683,7 @@ intel_engine_find_active_request(struct intel_engine_cs *engine) * At all other times, we must assume the GPU is still running, but * we only care about the snapshot of this moment. */ - spin_lock_irqsave(&engine->active.lock, flags); + lockdep_assert_held(&engine->active.lock); list_for_each_entry(request, &engine->active.requests, sched.link) { if (i915_request_completed(request)) continue; @@ -1700,7 +1698,6 @@ intel_engine_find_active_request(struct intel_engine_cs *engine) active = request; break; } - spin_unlock_irqrestore(&engine->active.lock, flags); return active; } diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 41a511d5267f..8bc76fcff70d 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1418,6 +1418,7 @@ static void gem_record_rings(struct i915_gpu_state *error) struct intel_engine_cs *engine = i915->engine[i]; struct drm_i915_error_engine *ee = &error->engine[i]; struct i915_request *request; + unsigned long flags; ee->engine_id = -1; @@ -1429,10 +1430,11 @@ static void gem_record_rings(struct i915_gpu_state *error) error_record_engine_registers(error, engine, ee); error_record_engine_execlists(engine, ee); + spin_lock_irqsave(&engine->active.lock, flags); request = intel_engine_find_active_request(engine); if (request) { struct i915_gem_context *ctx = request->gem_context; - struct intel_ring *ring; + struct intel_ring *ring = request->ring; ee->vm = ctx->vm ?: &ggtt->vm; @@ -1462,7 +1464,6 @@ static void gem_record_rings(struct i915_gpu_state *error) ee->rq_post = request->postfix; ee->rq_tail = request->tail; - ring = request->ring; ee->cpu_ring_head = ring->head; ee->cpu_ring_tail = ring->tail; ee->ringbuffer = @@ -1470,6 +1471,7 @@ static void gem_record_rings(struct i915_gpu_state *error) engine_record_requests(engine, request, ee); } + spin_unlock_irqrestore(&engine->active.lock, flags); ee->hws_page = i915_error_object_create(i915, From a8f196a0fa6391a436f63f360a1fb57031fdf26c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Wed, 17 Jul 2019 14:45:36 +0300 Subject: [PATCH 501/823] drm/i915: Make sure cdclk is high enough for DP audio on VLV/CHV MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On VLV/CHV there is some kind of linkage between the cdclk frequency and the DP link frequency. The spec says: "For DP audio configuration, cdclk frequency shall be set to meet the following requirements: DP Link Frequency(MHz) | Cdclk frequency(MHz) 270 | 320 or higher 162 | 200 or higher" I suspect that would more accurately be expressed as "cdclk >= DP link clock", and in any case we can express it like that in the code because of the limited set of cdclk (200, 266, 320, 400 MHz) and link frequencies (162 and 270 MHz) we support. Without this we can end up in a situation where the cdclk is too low and enabling DP audio will kill the pipe. Happens eg. with 2560x1440 modes where the 266MHz cdclk is sufficient to pump the pixels (241.5 MHz dotclock) but is too low for the DP audio due to the link frequency being 270 MHz. v2: Spell out the cdclk and link frequencies we actually support Cc: stable@vger.kernel.org Tested-by: Stefan Gottwald Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111149 Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20190717114536.22937-1-ville.syrjala@linux.intel.com Acked-by: Chris Wilson (cherry picked from commit bffb31f73b29a60ef693842d8744950c2819851d) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_cdclk.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index 8993ab283562..0d19bbd08122 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -2239,6 +2239,17 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state) if (crtc_state->has_audio && INTEL_GEN(dev_priv) >= 9) min_cdclk = max(2 * 96000, min_cdclk); + /* + * "For DP audio configuration, cdclk frequency shall be set to + * meet the following requirements: + * DP Link Frequency(MHz) | Cdclk frequency(MHz) + * 270 | 320 or higher + * 162 | 200 or higher" + */ + if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) && + intel_crtc_has_dp_encoder(crtc_state) && crtc_state->has_audio) + min_cdclk = max(crtc_state->port_clock, min_cdclk); + /* * On Valleyview some DSI panels lose (v|h)sync when the clock is lower * than 320000KHz. From 6d61f716a01ec0e134de38ae97e71d6fec5a6ff6 Mon Sep 17 00:00:00 2001 From: Dhinakaran Pandiyan Date: Wed, 17 Jul 2019 15:34:51 -0700 Subject: [PATCH 502/823] drm/i915/vbt: Fix VBT parsing for the PSR section MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A single 32-bit PSR2 training pattern field follows the sixteen element array of PSR table entries in the VBT spec. But, we incorrectly define this PSR2 field for each of the PSR table entries. As a result, the PSR1 training pattern duration for any panel_type != 0 will be parsed incorrectly. Secondly, PSR2 training pattern durations for VBTs with bdb version >= 226 will also be wrong. Cc: Rodrigo Vivi Cc: José Roberto de Souza Cc: stable@vger.kernel.org Cc: stable@vger.kernel.org #v5.2 Fixes: 88a0d9606aff ("drm/i915/vbt: Parse and use the new field with PSR2 TP2/3 wakeup time") Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111088 Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=204183 Signed-off-by: Dhinakaran Pandiyan Reviewed-by: Ville Syrjälä Reviewed-by: José Roberto de Souza Acked-by: Rodrigo Vivi Tested-by: François Guerraz Signed-off-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20190717223451.2595-1-dhinakaran.pandiyan@intel.com (cherry picked from commit b5ea9c9337007d6e700280c8a60b4e10d070fb53) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_bios.c | 2 +- drivers/gpu/drm/i915/display/intel_vbt_defs.h | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index c4710889cb32..3ef4e9f573cf 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -765,7 +765,7 @@ parse_psr(struct drm_i915_private *dev_priv, const struct bdb_header *bdb) } if (bdb->version >= 226) { - u32 wakeup_time = psr_table->psr2_tp2_tp3_wakeup_time; + u32 wakeup_time = psr->psr2_tp2_tp3_wakeup_time; wakeup_time = (wakeup_time >> (2 * panel_type)) & 0x3; switch (wakeup_time) { diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h index 2f4894e9a03d..5ddbe71ab423 100644 --- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h +++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h @@ -478,13 +478,13 @@ struct psr_table { /* TP wake up time in multiple of 100 */ u16 tp1_wakeup_time; u16 tp2_tp3_wakeup_time; - - /* PSR2 TP2/TP3 wakeup time for 16 panels */ - u32 psr2_tp2_tp3_wakeup_time; } __packed; struct bdb_psr { struct psr_table psr_table[16]; + + /* PSR2 TP2/TP3 wakeup time for 16 panels */ + u32 psr2_tp2_tp3_wakeup_time; } __packed; /* From 0bbfdce345c8cf01a3a985fa99fefd2146dcc748 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Wed, 17 Jul 2019 19:06:19 +0100 Subject: [PATCH 503/823] drm/i915: Fix GEN8_MCR_SELECTOR programming fls returns bit positions starting from one for the lsb and the MCR register expects zero based (sub)slice addressing. Incorrent MCR programming can have the effect of directing MMIO reads of registers in the 0xb100-0xb3ff range to invalid subslice returning zeroes instead of actual content. Signed-off-by: Tvrtko Ursulin Fixes: 1e40d4aea57b ("drm/i915/cnl: Implement WaProgramMgsrForCorrectSliceSpecificMmioReads") Reviewed-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20190717180624.20354-2-tvrtko.ursulin@linux.intel.com (cherry picked from commit 15160879d47213c32f357bc67b6014d9aaf14ed7) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gt/intel_engine_cs.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index aa5a1f11a91b..f25632c9b292 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -969,9 +969,14 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type) u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv) { const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu; + unsigned int slice = fls(sseu->slice_mask) - 1; + unsigned int subslice; u32 mcr_s_ss_select; - u32 slice = fls(sseu->slice_mask); - u32 subslice = fls(sseu->subslice_mask[slice]); + + GEM_BUG_ON(slice >= ARRAY_SIZE(sseu->subslice_mask)); + subslice = fls(sseu->subslice_mask[slice]); + GEM_BUG_ON(!subslice); + subslice--; if (IS_GEN(dev_priv, 10)) mcr_s_ss_select = GEN8_MCR_SLICE(slice) | From 89f5752307cf53010d97503ac501b2ca1b089922 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 28 Jun 2019 17:36:18 +0300 Subject: [PATCH 504/823] drm/i915: Fix the TBT AUX power well enabling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the mapping from a TBT AUX power well index to the DP_AUX_CH_CTL register. Fixes: c7375d9542f1 ("drm/i915: Configure AUX_CH_CTL when enabling the AUX power domain") Cc: José Roberto de Souza Cc: Rodrigo Vivi Signed-off-by: Imre Deak Reviewed-by: José Roberto de Souza Link: https://patchwork.freedesktop.org/patch/msgid/20190628143635.22066-7-imre.deak@intel.com (cherry picked from commit 29ae36abf08f943b76a2959f5000c44efa335be7) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_display_power.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index c93ad512014c..2d1939db108f 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -438,16 +438,23 @@ icl_combo_phy_aux_power_well_disable(struct drm_i915_private *dev_priv, #define ICL_AUX_PW_TO_CH(pw_idx) \ ((pw_idx) - ICL_PW_CTL_IDX_AUX_A + AUX_CH_A) +#define ICL_TBT_AUX_PW_TO_CH(pw_idx) \ + ((pw_idx) - ICL_PW_CTL_IDX_AUX_TBT1 + AUX_CH_C) + static void icl_tc_phy_aux_power_well_enable(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { - enum aux_ch aux_ch = ICL_AUX_PW_TO_CH(power_well->desc->hsw.idx); + int pw_idx = power_well->desc->hsw.idx; + bool is_tbt = power_well->desc->hsw.is_tc_tbt; + enum aux_ch aux_ch; u32 val; + aux_ch = is_tbt ? ICL_TBT_AUX_PW_TO_CH(pw_idx) : + ICL_AUX_PW_TO_CH(pw_idx); val = I915_READ(DP_AUX_CH_CTL(aux_ch)); val &= ~DP_AUX_CH_CTL_TBT_IO; - if (power_well->desc->hsw.is_tc_tbt) + if (is_tbt) val |= DP_AUX_CH_CTL_TBT_IO; I915_WRITE(DP_AUX_CH_CTL(aux_ch), val); From 91826ba13855f73e252fef68369b3b0e1ed25253 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 29 Jul 2019 00:51:38 +0900 Subject: [PATCH 505/823] netfilter: add include guard to xt_connlabel.h Add a header include guard just in case. Signed-off-by: Masahiro Yamada Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/xt_connlabel.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/include/uapi/linux/netfilter/xt_connlabel.h b/include/uapi/linux/netfilter/xt_connlabel.h index 2312f0ec07b2..323f0dfc2a4e 100644 --- a/include/uapi/linux/netfilter/xt_connlabel.h +++ b/include/uapi/linux/netfilter/xt_connlabel.h @@ -1,4 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _UAPI_XT_CONNLABEL_H +#define _UAPI_XT_CONNLABEL_H + #include #define XT_CONNLABEL_MAXBIT 127 @@ -11,3 +15,5 @@ struct xt_connlabel_mtinfo { __u16 bit; __u16 options; }; + +#endif /* _UAPI_XT_CONNLABEL_H */ From 8aa259b10a6a759c50137bbbf225df0c17ca5d27 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 18 Jul 2019 10:30:21 -0700 Subject: [PATCH 506/823] libbpf: fix missing __WORDSIZE definition hashmap.h depends on __WORDSIZE being defined. It is defined by glibc/musl in different headers. It's an explicit goal for musl to be "non-detectable" at compilation time, so instead include glibc header if glibc is explicitly detected and fall back to musl header otherwise. Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Andrii Nakryiko Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Andrii Nakryiko Cc: Daniel Borkmann Fixes: e3b924224028 ("libbpf: add resizable non-thread safe internal hashmap") Link: https://lkml.kernel.org/r/20190718173021.2418606-1-andriin@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/bpf/hashmap.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h index 03748a742146..bae8879cdf58 100644 --- a/tools/lib/bpf/hashmap.h +++ b/tools/lib/bpf/hashmap.h @@ -10,6 +10,11 @@ #include #include +#ifdef __GLIBC__ +#include +#else +#include +#endif #include "libbpf_internal.h" static inline size_t hash_bits(size_t h, int bits) From 05aaa5c97dce4c10a9e7eae2f1569a684e0c5ced Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 26 Jul 2019 15:47:58 -0700 Subject: [PATCH 507/823] mac80211: don't WARN on short WMM parameters from AP In a very similar spirit to commit c470bdc1aaf3 ("mac80211: don't WARN on bad WMM parameters from buggy APs"), an AP may not transmit a fully-formed WMM IE. For example, it may miss or repeat an Access Category. The above loop won't catch that and will instead leave one of the four ACs zeroed out. This triggers the following warning in drv_conf_tx() wlan0: invalid CW_min/CW_max: 0/0 and it may leave one of the hardware queues unconfigured. If we detect such a case, let's just print a warning and fall back to the defaults. Tested with a hacked version of hostapd, intentionally corrupting the IEs in hostapd_eid_wmm(). Cc: stable@vger.kernel.org Signed-off-by: Brian Norris Link: https://lore.kernel.org/r/20190726224758.210953-1-briannorris@chromium.org Signed-off-by: Johannes Berg --- net/mac80211/mlme.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index a99ad0325309..4c888dc9bd81 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2042,6 +2042,16 @@ ieee80211_sta_wmm_params(struct ieee80211_local *local, ieee80211_regulatory_limit_wmm_params(sdata, ¶ms[ac], ac); } + /* WMM specification requires all 4 ACIs. */ + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + if (params[ac].cw_min == 0) { + sdata_info(sdata, + "AP has invalid WMM params (missing AC %d), using defaults\n", + ac); + return false; + } + } + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { mlme_dbg(sdata, "WMM AC=%d acm=%d aifs=%d cWmin=%d cWmax=%d txop=%d uapsd=%d, downgraded=%d\n", From b55f3b841099e641bdb2701d361a4c304e2dbd6f Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Mon, 29 Jul 2019 16:23:32 +0800 Subject: [PATCH 508/823] mac80211_hwsim: Fix possible null-pointer dereferences in hwsim_dump_radio_nl() In hwsim_dump_radio_nl(), when genlmsg_put() on line 3617 fails, hdr is assigned to NULL. Then hdr is used on lines 3622 and 3623: genl_dump_check_consistent(cb, hdr); genlmsg_end(skb, hdr); Thus, possible null-pointer dereferences may occur. To fix these bugs, hdr is used here when it is not NULL. This bug is found by a static analysis tool STCheck written by us. Signed-off-by: Jia-Ju Bai Link: https://lore.kernel.org/r/20190729082332.28895-1-baijiaju1990@gmail.com [put braces on all branches] Signed-off-by: Johannes Berg --- drivers/net/wireless/mac80211_hwsim.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 519b4ee88c5c..772e54f0696f 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3617,10 +3617,12 @@ static int hwsim_dump_radio_nl(struct sk_buff *skb, hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &hwsim_genl_family, NLM_F_MULTI, HWSIM_CMD_GET_RADIO); - if (!hdr) + if (hdr) { + genl_dump_check_consistent(cb, hdr); + genlmsg_end(skb, hdr); + } else { res = -EMSGSIZE; - genl_dump_check_consistent(cb, hdr); - genlmsg_end(skb, hdr); + } } done: From 3884ae44f41247e0ae41952d4fad46db86d2e0a8 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 23 Jul 2019 10:08:28 +0200 Subject: [PATCH 509/823] pidfd: remove obsolete comments from test Since the introduction of CLONE_PIDFD pidfd_send_signal() is independent of CONFIG_PROC_FS. Signed-off-by: Christian Brauner --- tools/testing/selftests/pidfd/pidfd_test.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 7eaa8a3de262..b632965e60eb 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -339,13 +339,9 @@ static int test_pidfd_send_signal_syscall_support(void) ret = sys_pidfd_send_signal(pidfd, 0, NULL, 0); if (ret < 0) { - /* - * pidfd_send_signal() will currently return ENOSYS when - * CONFIG_PROC_FS is not set. - */ if (errno == ENOSYS) ksft_exit_skip( - "%s test: pidfd_send_signal() syscall not supported (Ensure that CONFIG_PROC_FS=y is set)\n", + "%s test: pidfd_send_signal() syscall not supported\n", test_name); ksft_exit_fail_msg("%s test: Failed to send signal\n", From 1caf7d50f46bd0388e38e653b146aa81700e8eb8 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Wed, 24 Jul 2019 12:48:16 -0400 Subject: [PATCH 510/823] pidfd: Add warning if exit_state is 0 during notification Previously a condition got missed where the pidfd waiters are awakened before the exit_state gets set. This can result in a missed notification [1] and the polling thread waiting forever. It is fixed now, however it would be nice to avoid this kind of issue going unnoticed in the future. So just add a warning to catch it in the future. /* References */ [1]: https://lore.kernel.org/lkml/20190717172100.261204-1-joel@joelfernandes.org/ Signed-off-by: Joel Fernandes (Google) Link: https://lore.kernel.org/r/20190724164816.201099-1-joel@joelfernandes.org Signed-off-by: Christian Brauner --- kernel/signal.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/signal.c b/kernel/signal.c index 91b789dd6e72..349f5a67f100 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1885,6 +1885,7 @@ static void do_notify_pidfd(struct task_struct *task) { struct pid *pid; + WARN_ON(task->exit_state == 0); pid = task_pid(task); wake_up_all(&pid->wait_pidfd); } From f14312a93b34b9350dc33ff0b4215c24f4c82617 Mon Sep 17 00:00:00 2001 From: Enrico Weigelt Date: Thu, 25 Jul 2019 21:06:03 +0200 Subject: [PATCH 511/823] platform/x86: pcengines-apuv2: use KEY_RESTART for front button The keycode KEY_RESTART is more appropriate for the front button, as most people use it for things like restart or factory reset. Signed-off-by: Enrico Weigelt Fixes: f8eb0235f659 ("x86: pcengines apuv2 gpio/leds/keys platform driver") Signed-off-by: Andy Shevchenko --- drivers/platform/x86/pcengines-apuv2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/pcengines-apuv2.c b/drivers/platform/x86/pcengines-apuv2.c index 96b499c6929a..e4c68efac0c2 100644 --- a/drivers/platform/x86/pcengines-apuv2.c +++ b/drivers/platform/x86/pcengines-apuv2.c @@ -93,7 +93,7 @@ static struct gpiod_lookup_table gpios_led_table = { static struct gpio_keys_button apu2_keys_buttons[] = { { - .code = KEY_SETUP, + .code = KEY_RESTART, .active_low = 1, .desc = "front button", .type = EV_KEY, From d655e5b4e1c8ce207f0a1868aa334c4ecdcbddfb Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Tue, 23 Jul 2019 10:24:51 +0200 Subject: [PATCH 512/823] s390: clean up qdio.h Fix two typos, document missing fields in the driver initialization data and remove the copy&pasted 'pfmt' field from the qdr struct. Signed-off-by: Julian Wiedmann Reviewed-by: Jens Remus Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/qdio.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index db5ef22c46e4..f647d565bd6d 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -28,7 +28,7 @@ * @sliba: storage list information block address * @sla: storage list address * @slsba: storage list state block address - * @akey: access key for DLIB + * @akey: access key for SLIB * @bkey: access key for SL * @ckey: access key for SBALs * @dkey: access key for SLSB @@ -50,11 +50,10 @@ struct qdesfmt0 { /** * struct qdr - queue description record (QDR) * @qfmt: queue format - * @pfmt: implementation dependent parameter format * @ac: adapter characteristics * @iqdcnt: input queue descriptor count * @oqdcnt: output queue descriptor count - * @iqdsz: inpout queue descriptor size + * @iqdsz: input queue descriptor size * @oqdsz: output queue descriptor size * @qiba: queue information block address * @qkey: queue information block key @@ -62,8 +61,7 @@ struct qdesfmt0 { */ struct qdr { u32 qfmt : 8; - u32 pfmt : 8; - u32 : 8; + u32 : 16; u32 ac : 8; u32 : 8; u32 iqdcnt : 8; @@ -327,6 +325,7 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int, * struct qdio_initialize - qdio initialization data * @cdev: associated ccw device * @q_format: queue format + * @qdr_ac: feature flags to set * @adapter_name: name for the adapter * @qib_param_field_format: format for qib_parm_field * @qib_param_field: pointer to 128 bytes or NULL, if no param field @@ -338,6 +337,7 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int, * @input_handler: handler to be called for input queues * @output_handler: handler to be called for output queues * @queue_start_poll_array: polling handlers (one per input queue or NULL) + * @scan_threshold: # of in-use buffers that triggers scan on output queue * @int_parm: interruption parameter * @input_sbal_addr_array: address of no_input_qs * 128 pointers * @output_sbal_addr_array: address of no_output_qs * 128 pointers From 3361f3193c747e8b32b9edf60f2567187ed4faef Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 25 Jul 2019 13:52:08 +0200 Subject: [PATCH 513/823] s390: update configs Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/configs/debug_defconfig | 330 ++++++++++++++++----------- arch/s390/configs/defconfig | 321 +++++++++++++++----------- arch/s390/configs/zfcpdump_defconfig | 31 +-- 3 files changed, 410 insertions(+), 272 deletions(-) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index e26d4413d34c..74e78ec5beb6 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -3,6 +3,7 @@ CONFIG_POSIX_MQUEUE=y CONFIG_AUDIT=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_PREEMPT=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_TASKSTATS=y @@ -18,55 +19,71 @@ CONFIG_BLK_CGROUP=y CONFIG_CFS_BANDWIDTH=y CONFIG_RT_GROUP_SCHED=y CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_RDMA=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_HUGETLB=y CONFIG_CPUSETS=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y +CONFIG_CGROUP_BPF=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y +CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set -CONFIG_CHECKPOINT_RESTORE=y CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y +CONFIG_LIVEPATCH=y +CONFIG_TUNE_ZEC12=y +CONFIG_NR_CPUS=512 +CONFIG_NUMA=y +CONFIG_HZ_100=y +CONFIG_KEXEC_FILE=y +CONFIG_EXPOLINE=y +CONFIG_EXPOLINE_AUTO=y +CONFIG_CHSC_SCH=y +CONFIG_VFIO_CCW=m +CONFIG_VFIO_AP=m +CONFIG_CRASH_DUMP=y +CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y +CONFIG_CMM=m +CONFIG_APPLDATA_BASE=y +CONFIG_KVM=m +CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m CONFIG_OPROFILE=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y CONFIG_STATIC_KEYS_SELFTEST=y +CONFIG_REFCOUNT_FULL=y +CONFIG_LOCK_EVENT_COUNTS=y CONFIG_MODULES=y CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_MODULE_SIG=y +CONFIG_MODULE_SIG_SHA256=y CONFIG_BLK_DEV_INTEGRITY=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y -CONFIG_BLK_WBT_SQ=y +CONFIG_BLK_CGROUP_IOLATENCY=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y CONFIG_MINIX_SUBPARTITION=y CONFIG_SOLARIS_X86_PARTITION=y CONFIG_UNIXWARE_DISKLABEL=y -CONFIG_CFQ_GROUP_IOSCHED=y -CONFIG_DEFAULT_DEADLINE=y -CONFIG_LIVEPATCH=y -CONFIG_TUNE_ZEC12=y -CONFIG_NR_CPUS=512 -CONFIG_NUMA=y -CONFIG_PREEMPT=y -CONFIG_HZ_100=y -CONFIG_KEXEC_FILE=y -CONFIG_KEXEC_VERIFY_SIG=y -CONFIG_EXPOLINE=y -CONFIG_EXPOLINE_AUTO=y +CONFIG_IOSCHED_BFQ=y +CONFIG_BFQ_GROUP_IOSCHED=y +CONFIG_BINFMT_MISC=m CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -82,17 +99,8 @@ CONFIG_ZSMALLOC=m CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y -CONFIG_PCI=y -CONFIG_PCI_DEBUG=y -CONFIG_HOTPLUG_PCI=y -CONFIG_HOTPLUG_PCI_S390=y -CONFIG_CHSC_SCH=y -CONFIG_VFIO_AP=m -CONFIG_VFIO_CCW=m -CONFIG_CRASH_DUMP=y -CONFIG_BINFMT_MISC=m -CONFIG_HIBERNATION=y -CONFIG_PM_DEBUG=y +CONFIG_PERCPU_STATS=y +CONFIG_GUP_BENCHMARK=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -121,9 +129,6 @@ CONFIG_NET_IPVTI=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -CONFIG_INET_XFRM_MODE_TRANSPORT=m -CONFIG_INET_XFRM_MODE_TUNNEL=m -CONFIG_INET_XFRM_MODE_BEET=m CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m CONFIG_TCP_CONG_ADVANCED=y @@ -139,10 +144,6 @@ CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m CONFIG_IPV6_MIP6=m -CONFIG_INET6_XFRM_MODE_TRANSPORT=m -CONFIG_INET6_XFRM_MODE_TUNNEL=m -CONFIG_INET6_XFRM_MODE_BEET=m -CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m CONFIG_IPV6_VTI=m CONFIG_IPV6_SIT=m CONFIG_IPV6_GRE=m @@ -264,11 +265,8 @@ CONFIG_IP_VS_SED=m CONFIG_IP_VS_NQ=m CONFIG_IP_VS_FTP=m CONFIG_IP_VS_PE_SIP=m -CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NF_TABLES_IPV4=y -CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NF_TABLES_ARP=y -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -287,10 +285,7 @@ CONFIG_IP_NF_SECURITY=m CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NF_TABLES_IPV6=y -CONFIG_NFT_CHAIN_ROUTE_IPV6=m -CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -309,7 +304,7 @@ CONFIG_IP6_NF_RAW=m CONFIG_IP6_NF_SECURITY=m CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m -CONFIG_NF_TABLES_BRIDGE=y +CONFIG_NF_TABLES_BRIDGE=m CONFIG_RDS=m CONFIG_RDS_RDMA=m CONFIG_RDS_TCP=m @@ -375,9 +370,11 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m +CONFIG_PCI=y +CONFIG_PCI_DEBUG=y +CONFIG_HOTPLUG_PCI=y +CONFIG_HOTPLUG_PCI_S390=y CONFIG_DEVTMPFS=y -CONFIG_DMA_CMA=y -CONFIG_CMA_SIZE_MBYTES=0 CONFIG_CONNECTOR=y CONFIG_ZRAM=m CONFIG_BLK_DEV_LOOP=m @@ -395,7 +392,6 @@ CONFIG_RAID_ATTRS=m CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m -CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=m CONFIG_CHR_DEV_SG=y CONFIG_CHR_DEV_SCH=m @@ -415,17 +411,19 @@ CONFIG_SCSI_DH_RDAC=m CONFIG_SCSI_DH_HP_SW=m CONFIG_SCSI_DH_EMC=m CONFIG_SCSI_DH_ALUA=m -CONFIG_SCSI_OSD_INITIATOR=m -CONFIG_SCSI_OSD_ULD=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y CONFIG_MD_LINEAR=m CONFIG_MD_MULTIPATH=m CONFIG_MD_FAULTY=m +CONFIG_MD_CLUSTER=m +CONFIG_BCACHE=m CONFIG_BLK_DEV_DM=m +CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_MIRROR=m CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_RAID=m @@ -445,23 +443,78 @@ CONFIG_EQUALIZER=m CONFIG_IFB=m CONFIG_MACVLAN=m CONFIG_MACVTAP=m -CONFIG_VXLAN=m CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m CONFIG_NLMON=m +# CONFIG_NET_VENDOR_3COM is not set +# CONFIG_NET_VENDOR_ADAPTEC is not set +# CONFIG_NET_VENDOR_AGERE is not set +# CONFIG_NET_VENDOR_ALACRITECH is not set +# CONFIG_NET_VENDOR_ALTEON is not set +# CONFIG_NET_VENDOR_AMAZON is not set +# CONFIG_NET_VENDOR_AMD is not set +# CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_ATHEROS is not set +# CONFIG_NET_VENDOR_AURORA is not set +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_BROCADE is not set +# CONFIG_NET_VENDOR_CADENCE is not set +# CONFIG_NET_VENDOR_CAVIUM is not set # CONFIG_NET_VENDOR_CHELSIO is not set +# CONFIG_NET_VENDOR_CISCO is not set +# CONFIG_NET_VENDOR_CORTINA is not set +# CONFIG_NET_VENDOR_DEC is not set +# CONFIG_NET_VENDOR_DLINK is not set +# CONFIG_NET_VENDOR_EMULEX is not set +# CONFIG_NET_VENDOR_EZCHIP is not set +# CONFIG_NET_VENDOR_GOOGLE is not set +# CONFIG_NET_VENDOR_HP is not set +# CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y +# CONFIG_MLXFW is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROCHIP is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set +# CONFIG_NET_VENDOR_MYRI is not set # CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_NETERION is not set +# CONFIG_NET_VENDOR_NETRONOME is not set +# CONFIG_NET_VENDOR_NI is not set +# CONFIG_NET_VENDOR_NVIDIA is not set +# CONFIG_NET_VENDOR_OKI is not set +# CONFIG_NET_VENDOR_PACKET_ENGINES is not set +# CONFIG_NET_VENDOR_QLOGIC is not set +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_RDC is not set +# CONFIG_NET_VENDOR_REALTEK is not set +# CONFIG_NET_VENDOR_RENESAS is not set +# CONFIG_NET_VENDOR_ROCKER is not set +# CONFIG_NET_VENDOR_SAMSUNG is not set +# CONFIG_NET_VENDOR_SEEQ is not set +# CONFIG_NET_VENDOR_SOLARFLARE is not set +# CONFIG_NET_VENDOR_SILAN is not set +# CONFIG_NET_VENDOR_SIS is not set +# CONFIG_NET_VENDOR_SMSC is not set +# CONFIG_NET_VENDOR_SOCIONEXT is not set +# CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SUN is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set +# CONFIG_NET_VENDOR_TEHUTI is not set +# CONFIG_NET_VENDOR_TI is not set +# CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m +CONFIG_PPP_FILTER=y CONFIG_PPP_MPPE=m +CONFIG_PPP_MULTILINK=y CONFIG_PPPOE=m CONFIG_PPTP=m CONFIG_PPPOL2TP=m @@ -473,10 +526,13 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=0 +CONFIG_NULL_TTY=m CONFIG_HW_RANDOM_VIRTIO=m CONFIG_RAW_DRIVER=m CONFIG_HANGCHECK_TIMER=m CONFIG_TN3270_FS=y +CONFIG_PPS=m +# CONFIG_PTP_1588_CLOCK is not set # CONFIG_HWMON is not set CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y @@ -498,8 +554,8 @@ CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y -CONFIG_S390_AP_IOMMU=y CONFIG_S390_CCW_IOMMU=y +CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -519,6 +575,7 @@ CONFIG_OCFS2_FS=m CONFIG_BTRFS_FS=y CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_BTRFS_DEBUG=y +CONFIG_BTRFS_ASSERT=y CONFIG_NILFS2_FS=m CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y @@ -552,8 +609,10 @@ CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m CONFIG_SQUASHFS_XATTR=y +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_SQUASHFS_XZ=y +CONFIG_SQUASHFS_ZSTD=y CONFIG_ROMFS_FS=m CONFIG_NFS_FS=m CONFIG_NFS_V3_ACL=y @@ -564,7 +623,6 @@ CONFIG_NFSD_V3_ACL=y CONFIG_NFSD_V4=y CONFIG_NFSD_V4_SECURITY_LABEL=y CONFIG_CIFS=m -CONFIG_CIFS_STATS=y CONFIG_CIFS_STATS2=y CONFIG_CIFS_WEAK_PW_HASH=y CONFIG_CIFS_UPCALL=y @@ -580,19 +638,112 @@ CONFIG_NLS_ISO8859_1=m CONFIG_NLS_ISO8859_15=m CONFIG_NLS_UTF8=m CONFIG_DLM=m +CONFIG_UNICODE=y +CONFIG_PERSISTENT_KEYRINGS=y +CONFIG_BIG_KEYS=y +CONFIG_ENCRYPTED_KEYS=m +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_FORTIFY_SOURCE=y +CONFIG_SECURITY_SELINUX=y +CONFIG_SECURITY_SELINUX_BOOTPARAM=y +CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_INTEGRITY_SIGNATURE=y +CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y +CONFIG_IMA=y +CONFIG_IMA_DEFAULT_HASH_SHA256=y +CONFIG_IMA_WRITE_POLICY=y +CONFIG_IMA_APPRAISE=y +CONFIG_CRYPTO_USER=m +# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set +CONFIG_CRYPTO_PCRYPT=m +CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_TEST=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m +CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m +CONFIG_CRYPTO_CFB=m +CONFIG_CRYPTO_LRW=m +CONFIG_CRYPTO_PCBC=m +CONFIG_CRYPTO_KEYWRAP=m +CONFIG_CRYPTO_ADIANTUM=m +CONFIG_CRYPTO_XCBC=m +CONFIG_CRYPTO_VMAC=m +CONFIG_CRYPTO_CRC32=m +CONFIG_CRYPTO_XXHASH=m +CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_RMD128=m +CONFIG_CRYPTO_RMD160=m +CONFIG_CRYPTO_RMD256=m +CONFIG_CRYPTO_RMD320=m +CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m +CONFIG_CRYPTO_TGR192=m +CONFIG_CRYPTO_WP512=m +CONFIG_CRYPTO_AES_TI=m +CONFIG_CRYPTO_ANUBIS=m +CONFIG_CRYPTO_ARC4=m +CONFIG_CRYPTO_BLOWFISH=m +CONFIG_CRYPTO_CAMELLIA=m +CONFIG_CRYPTO_CAST5=m +CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_FCRYPT=m +CONFIG_CRYPTO_KHAZAD=m +CONFIG_CRYPTO_SALSA20=m +CONFIG_CRYPTO_SEED=m +CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_SM4=m +CONFIG_CRYPTO_TEA=m +CONFIG_CRYPTO_TWOFISH=m +CONFIG_CRYPTO_842=m +CONFIG_CRYPTO_LZ4=m +CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m +CONFIG_CRYPTO_ANSI_CPRNG=m +CONFIG_CRYPTO_USER_API_HASH=m +CONFIG_CRYPTO_USER_API_SKCIPHER=m +CONFIG_CRYPTO_USER_API_RNG=m +CONFIG_CRYPTO_USER_API_AEAD=m +CONFIG_CRYPTO_STATS=y +CONFIG_ZCRYPT=m +CONFIG_PKEY=m +CONFIG_CRYPTO_PAES_S390=m +CONFIG_CRYPTO_SHA1_S390=m +CONFIG_CRYPTO_SHA256_S390=m +CONFIG_CRYPTO_SHA512_S390=m +CONFIG_CRYPTO_DES_S390=m +CONFIG_CRYPTO_AES_S390=m +CONFIG_CRYPTO_GHASH_S390=m +CONFIG_CRYPTO_CRC32_S390=y +CONFIG_CORDIC=m +CONFIG_CRC32_SELFTEST=y +CONFIG_CRC4=m +CONFIG_CRC7=m +CONFIG_CRC8=m +CONFIG_RANDOM32_SELFTEST=y +CONFIG_DMA_CMA=y +CONFIG_CMA_SIZE_MBYTES=0 +CONFIG_DMA_API_DEBUG=y +CONFIG_STRING_SELFTEST=y CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 -CONFIG_READABLE_ASM=y CONFIG_UNUSED_SYMBOLS=y CONFIG_HEADERS_INSTALL=y CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_PAGEALLOC=y +CONFIG_PAGE_OWNER=y CONFIG_DEBUG_RODATA_TEST=y CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_SELFTEST=y @@ -645,7 +796,6 @@ CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_FUNCTION_PROFILER=y CONFIG_HIST_TRIGGERS=y -CONFIG_DMA_API_DEBUG=y CONFIG_LKDTM=m CONFIG_TEST_LIST_SORT=y CONFIG_TEST_SORT=y @@ -657,85 +807,3 @@ CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_S390_PTDUMP=y -CONFIG_PERSISTENT_KEYRINGS=y -CONFIG_BIG_KEYS=y -CONFIG_ENCRYPTED_KEYS=m -CONFIG_SECURITY=y -CONFIG_SECURITY_NETWORK=y -CONFIG_FORTIFY_SOURCE=y -CONFIG_SECURITY_SELINUX=y -CONFIG_SECURITY_SELINUX_BOOTPARAM=y -CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0 -CONFIG_SECURITY_SELINUX_DISABLE=y -CONFIG_INTEGRITY_SIGNATURE=y -CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y -CONFIG_IMA=y -CONFIG_IMA_DEFAULT_HASH_SHA256=y -CONFIG_IMA_WRITE_POLICY=y -CONFIG_IMA_APPRAISE=y -CONFIG_CRYPTO_DH=m -CONFIG_CRYPTO_ECDH=m -CONFIG_CRYPTO_USER=m -# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set -CONFIG_CRYPTO_PCRYPT=m -CONFIG_CRYPTO_CRYPTD=m -CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_CHACHA20POLY1305=m -CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_KEYWRAP=m -CONFIG_CRYPTO_XCBC=m -CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_CRC32=m -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_RMD128=m -CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_RMD256=m -CONFIG_CRYPTO_RMD320=m -CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_SHA3=m -CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_WP512=m -CONFIG_CRYPTO_AES_TI=m -CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAMELLIA=m -CONFIG_CRYPTO_CAST5=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_FCRYPT=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SALSA20=m -CONFIG_CRYPTO_SEED=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_842=m -CONFIG_CRYPTO_LZ4=m -CONFIG_CRYPTO_LZ4HC=m -CONFIG_CRYPTO_ANSI_CPRNG=m -CONFIG_CRYPTO_USER_API_HASH=m -CONFIG_CRYPTO_USER_API_SKCIPHER=m -CONFIG_CRYPTO_USER_API_RNG=m -CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_ZCRYPT=m -CONFIG_PKEY=m -CONFIG_CRYPTO_PAES_S390=m -CONFIG_CRYPTO_SHA1_S390=m -CONFIG_CRYPTO_SHA256_S390=m -CONFIG_CRYPTO_SHA512_S390=m -CONFIG_CRYPTO_DES_S390=m -CONFIG_CRYPTO_AES_S390=m -CONFIG_CRYPTO_GHASH_S390=m -CONFIG_CRYPTO_CRC32_S390=y -CONFIG_PKCS7_MESSAGE_PARSER=y -CONFIG_SYSTEM_TRUSTED_KEYRING=y -CONFIG_CRC7=m -CONFIG_CRC8=m -CONFIG_RANDOM32_SELFTEST=y -CONFIG_CORDIC=m -CONFIG_CMM=m -CONFIG_APPLDATA_BASE=y -CONFIG_KVM=m -CONFIG_KVM_S390_UCONTROL=y -CONFIG_VHOST_NET=m -CONFIG_VHOST_VSOCK=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index e4bc40073003..68d3ca83302b 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -12,30 +12,51 @@ CONFIG_TASK_IO_ACCOUNTING=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_NUMA_BALANCING=y -# CONFIG_NUMA_BALANCING_DEFAULT_ENABLED is not set CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y CONFIG_BLK_CGROUP=y CONFIG_CFS_BANDWIDTH=y CONFIG_RT_GROUP_SCHED=y CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_RDMA=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_HUGETLB=y CONFIG_CPUSETS=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y +CONFIG_CGROUP_BPF=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y +CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set -CONFIG_CHECKPOINT_RESTORE=y CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y +CONFIG_LIVEPATCH=y +CONFIG_TUNE_ZEC12=y +CONFIG_NR_CPUS=512 +CONFIG_NUMA=y +# CONFIG_NUMA_EMU is not set +CONFIG_HZ_100=y +CONFIG_KEXEC_FILE=y +CONFIG_EXPOLINE=y +CONFIG_EXPOLINE_AUTO=y +CONFIG_CHSC_SCH=y +CONFIG_VFIO_CCW=m +CONFIG_VFIO_AP=m +CONFIG_CRASH_DUMP=y +CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y +CONFIG_CMM=m +CONFIG_APPLDATA_BASE=y +CONFIG_KVM=m +CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m CONFIG_OPROFILE=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y @@ -47,27 +68,18 @@ CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y CONFIG_MODULE_SIG=y CONFIG_MODULE_SIG_SHA256=y -CONFIG_BLK_DEV_INTEGRITY=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y -CONFIG_BLK_WBT_SQ=y +CONFIG_BLK_CGROUP_IOLATENCY=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y CONFIG_MINIX_SUBPARTITION=y CONFIG_SOLARIS_X86_PARTITION=y CONFIG_UNIXWARE_DISKLABEL=y -CONFIG_CFQ_GROUP_IOSCHED=y -CONFIG_DEFAULT_DEADLINE=y -CONFIG_LIVEPATCH=y -CONFIG_TUNE_ZEC12=y -CONFIG_NR_CPUS=512 -CONFIG_NUMA=y -CONFIG_HZ_100=y -CONFIG_KEXEC_FILE=y -CONFIG_KEXEC_VERIFY_SIG=y -CONFIG_EXPOLINE=y -CONFIG_EXPOLINE_AUTO=y +CONFIG_IOSCHED_BFQ=y +CONFIG_BFQ_GROUP_IOSCHED=y +CONFIG_BINFMT_MISC=m CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -81,16 +93,8 @@ CONFIG_ZSMALLOC=m CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y -CONFIG_PCI=y -CONFIG_HOTPLUG_PCI=y -CONFIG_HOTPLUG_PCI_S390=y -CONFIG_CHSC_SCH=y -CONFIG_VFIO_AP=m -CONFIG_VFIO_CCW=m -CONFIG_CRASH_DUMP=y -CONFIG_BINFMT_MISC=m -CONFIG_HIBERNATION=y -CONFIG_PM_DEBUG=y +CONFIG_PERCPU_STATS=y +CONFIG_GUP_BENCHMARK=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -119,9 +123,6 @@ CONFIG_NET_IPVTI=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -CONFIG_INET_XFRM_MODE_TRANSPORT=m -CONFIG_INET_XFRM_MODE_TUNNEL=m -CONFIG_INET_XFRM_MODE_BEET=m CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m CONFIG_TCP_CONG_ADVANCED=y @@ -137,10 +138,6 @@ CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m CONFIG_IPV6_MIP6=m -CONFIG_INET6_XFRM_MODE_TRANSPORT=m -CONFIG_INET6_XFRM_MODE_TUNNEL=m -CONFIG_INET6_XFRM_MODE_BEET=m -CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m CONFIG_IPV6_VTI=m CONFIG_IPV6_SIT=m CONFIG_IPV6_GRE=m @@ -262,11 +259,8 @@ CONFIG_IP_VS_SED=m CONFIG_IP_VS_NQ=m CONFIG_IP_VS_FTP=m CONFIG_IP_VS_PE_SIP=m -CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NF_TABLES_IPV4=y -CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NF_TABLES_ARP=y -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -285,10 +279,7 @@ CONFIG_IP_NF_SECURITY=m CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NF_TABLES_IPV6=y -CONFIG_NFT_CHAIN_ROUTE_IPV6=m -CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -307,7 +298,7 @@ CONFIG_IP6_NF_RAW=m CONFIG_IP6_NF_SECURITY=m CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m -CONFIG_NF_TABLES_BRIDGE=y +CONFIG_NF_TABLES_BRIDGE=m CONFIG_RDS=m CONFIG_RDS_RDMA=m CONFIG_RDS_TCP=m @@ -372,9 +363,11 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m +CONFIG_PCI=y +CONFIG_HOTPLUG_PCI=y +CONFIG_HOTPLUG_PCI_S390=y +CONFIG_UEVENT_HELPER=y CONFIG_DEVTMPFS=y -CONFIG_DMA_CMA=y -CONFIG_CMA_SIZE_MBYTES=0 CONFIG_CONNECTOR=y CONFIG_ZRAM=m CONFIG_BLK_DEV_LOOP=m @@ -383,6 +376,7 @@ CONFIG_BLK_DEV_DRBD=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 +# CONFIG_BLK_DEV_XPRAM is not set CONFIG_VIRTIO_BLK=y CONFIG_BLK_DEV_RBD=m CONFIG_BLK_DEV_NVME=m @@ -392,7 +386,6 @@ CONFIG_RAID_ATTRS=m CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m -CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=m CONFIG_CHR_DEV_SG=y CONFIG_CHR_DEV_SCH=m @@ -412,17 +405,19 @@ CONFIG_SCSI_DH_RDAC=m CONFIG_SCSI_DH_HP_SW=m CONFIG_SCSI_DH_EMC=m CONFIG_SCSI_DH_ALUA=m -CONFIG_SCSI_OSD_INITIATOR=m -CONFIG_SCSI_OSD_ULD=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y CONFIG_MD_LINEAR=m CONFIG_MD_MULTIPATH=m CONFIG_MD_FAULTY=m +CONFIG_MD_CLUSTER=m +CONFIG_BCACHE=m CONFIG_BLK_DEV_DM=m +CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_MIRROR=m CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_RAID=m @@ -435,6 +430,7 @@ CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m CONFIG_DM_VERITY=m CONFIG_DM_SWITCH=m +CONFIG_DM_INTEGRITY=m CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=m @@ -442,23 +438,78 @@ CONFIG_EQUALIZER=m CONFIG_IFB=m CONFIG_MACVLAN=m CONFIG_MACVTAP=m -CONFIG_VXLAN=m CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m CONFIG_NLMON=m +# CONFIG_NET_VENDOR_3COM is not set +# CONFIG_NET_VENDOR_ADAPTEC is not set +# CONFIG_NET_VENDOR_AGERE is not set +# CONFIG_NET_VENDOR_ALACRITECH is not set +# CONFIG_NET_VENDOR_ALTEON is not set +# CONFIG_NET_VENDOR_AMAZON is not set +# CONFIG_NET_VENDOR_AMD is not set +# CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_ATHEROS is not set +# CONFIG_NET_VENDOR_AURORA is not set +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_BROCADE is not set +# CONFIG_NET_VENDOR_CADENCE is not set +# CONFIG_NET_VENDOR_CAVIUM is not set # CONFIG_NET_VENDOR_CHELSIO is not set +# CONFIG_NET_VENDOR_CISCO is not set +# CONFIG_NET_VENDOR_CORTINA is not set +# CONFIG_NET_VENDOR_DEC is not set +# CONFIG_NET_VENDOR_DLINK is not set +# CONFIG_NET_VENDOR_EMULEX is not set +# CONFIG_NET_VENDOR_EZCHIP is not set +# CONFIG_NET_VENDOR_GOOGLE is not set +# CONFIG_NET_VENDOR_HP is not set +# CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y +# CONFIG_MLXFW is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROCHIP is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set +# CONFIG_NET_VENDOR_MYRI is not set # CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_NETERION is not set +# CONFIG_NET_VENDOR_NETRONOME is not set +# CONFIG_NET_VENDOR_NI is not set +# CONFIG_NET_VENDOR_NVIDIA is not set +# CONFIG_NET_VENDOR_OKI is not set +# CONFIG_NET_VENDOR_PACKET_ENGINES is not set +# CONFIG_NET_VENDOR_QLOGIC is not set +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_RDC is not set +# CONFIG_NET_VENDOR_REALTEK is not set +# CONFIG_NET_VENDOR_RENESAS is not set +# CONFIG_NET_VENDOR_ROCKER is not set +# CONFIG_NET_VENDOR_SAMSUNG is not set +# CONFIG_NET_VENDOR_SEEQ is not set +# CONFIG_NET_VENDOR_SOLARFLARE is not set +# CONFIG_NET_VENDOR_SILAN is not set +# CONFIG_NET_VENDOR_SIS is not set +# CONFIG_NET_VENDOR_SMSC is not set +# CONFIG_NET_VENDOR_SOCIONEXT is not set +# CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SUN is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set +# CONFIG_NET_VENDOR_TEHUTI is not set +# CONFIG_NET_VENDOR_TI is not set +# CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m +CONFIG_PPP_FILTER=y CONFIG_PPP_MPPE=m +CONFIG_PPP_MULTILINK=y CONFIG_PPPOE=m CONFIG_PPTP=m CONFIG_PPPOL2TP=m @@ -470,17 +521,21 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=0 +CONFIG_NULL_TTY=m CONFIG_HW_RANDOM_VIRTIO=m CONFIG_RAW_DRIVER=m CONFIG_HANGCHECK_TIMER=m CONFIG_TN3270_FS=y +# CONFIG_PTP_1588_CLOCK is not set # CONFIG_HWMON is not set CONFIG_WATCHDOG=y +CONFIG_WATCHDOG_CORE=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m CONFIG_DRM=y CONFIG_DRM_VIRTIO_GPU=y +# CONFIG_BACKLIGHT_CLASS_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set @@ -495,8 +550,8 @@ CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y -CONFIG_S390_AP_IOMMU=y CONFIG_S390_CCW_IOMMU=y +CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -546,8 +601,10 @@ CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m CONFIG_SQUASHFS_XATTR=y +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_SQUASHFS_XZ=y +CONFIG_SQUASHFS_ZSTD=y CONFIG_ROMFS_FS=m CONFIG_NFS_FS=m CONFIG_NFS_V3_ACL=y @@ -558,7 +615,6 @@ CONFIG_NFSD_V3_ACL=y CONFIG_NFSD_V4=y CONFIG_NFSD_V4_SECURITY_LABEL=y CONFIG_CIFS=m -CONFIG_CIFS_STATS=y CONFIG_CIFS_STATS2=y CONFIG_CIFS_WEAK_PW_HASH=y CONFIG_CIFS_UPCALL=y @@ -574,13 +630,103 @@ CONFIG_NLS_ISO8859_1=m CONFIG_NLS_ISO8859_15=m CONFIG_NLS_UTF8=m CONFIG_DLM=m +CONFIG_UNICODE=y +CONFIG_PERSISTENT_KEYRINGS=y +CONFIG_BIG_KEYS=y +CONFIG_ENCRYPTED_KEYS=m +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_SELINUX=y +CONFIG_SECURITY_SELINUX_BOOTPARAM=y +CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_INTEGRITY_SIGNATURE=y +CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y +CONFIG_IMA=y +CONFIG_IMA_DEFAULT_HASH_SHA256=y +CONFIG_IMA_WRITE_POLICY=y +CONFIG_IMA_APPRAISE=y +CONFIG_CRYPTO_FIPS=y +CONFIG_CRYPTO_USER=m +# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set +CONFIG_CRYPTO_PCRYPT=m +CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_TEST=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m +CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m +CONFIG_CRYPTO_CFB=m +CONFIG_CRYPTO_LRW=m +CONFIG_CRYPTO_OFB=m +CONFIG_CRYPTO_PCBC=m +CONFIG_CRYPTO_KEYWRAP=m +CONFIG_CRYPTO_ADIANTUM=m +CONFIG_CRYPTO_XCBC=m +CONFIG_CRYPTO_VMAC=m +CONFIG_CRYPTO_CRC32=m +CONFIG_CRYPTO_XXHASH=m +CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_RMD128=m +CONFIG_CRYPTO_RMD160=m +CONFIG_CRYPTO_RMD256=m +CONFIG_CRYPTO_RMD320=m +CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m +CONFIG_CRYPTO_TGR192=m +CONFIG_CRYPTO_WP512=m +CONFIG_CRYPTO_AES_TI=m +CONFIG_CRYPTO_ANUBIS=m +CONFIG_CRYPTO_ARC4=m +CONFIG_CRYPTO_BLOWFISH=m +CONFIG_CRYPTO_CAMELLIA=m +CONFIG_CRYPTO_CAST5=m +CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_FCRYPT=m +CONFIG_CRYPTO_KHAZAD=m +CONFIG_CRYPTO_SALSA20=m +CONFIG_CRYPTO_SEED=m +CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_SM4=m +CONFIG_CRYPTO_TEA=m +CONFIG_CRYPTO_TWOFISH=m +CONFIG_CRYPTO_842=m +CONFIG_CRYPTO_LZ4=m +CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m +CONFIG_CRYPTO_ANSI_CPRNG=m +CONFIG_CRYPTO_USER_API_HASH=m +CONFIG_CRYPTO_USER_API_SKCIPHER=m +CONFIG_CRYPTO_USER_API_RNG=m +CONFIG_CRYPTO_USER_API_AEAD=m +CONFIG_CRYPTO_STATS=y +CONFIG_ZCRYPT=m +CONFIG_PKEY=m +CONFIG_CRYPTO_PAES_S390=m +CONFIG_CRYPTO_SHA1_S390=m +CONFIG_CRYPTO_SHA256_S390=m +CONFIG_CRYPTO_SHA512_S390=m +CONFIG_CRYPTO_DES_S390=m +CONFIG_CRYPTO_AES_S390=m +CONFIG_CRYPTO_GHASH_S390=m +CONFIG_CRYPTO_CRC32_S390=y +CONFIG_CORDIC=m +CONFIG_CRC4=m +CONFIG_CRC7=m +CONFIG_CRC8=m +CONFIG_DMA_CMA=y +CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y -# CONFIG_ENABLE_MUST_CHECK is not set CONFIG_FRAME_WARN=1024 CONFIG_UNUSED_SYMBOLS=y +CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_PANIC_ON_OOPS=y @@ -599,82 +745,3 @@ CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_S390_PTDUMP=y -CONFIG_PERSISTENT_KEYRINGS=y -CONFIG_BIG_KEYS=y -CONFIG_ENCRYPTED_KEYS=m -CONFIG_SECURITY=y -CONFIG_SECURITY_NETWORK=y -CONFIG_SECURITY_SELINUX=y -CONFIG_SECURITY_SELINUX_BOOTPARAM=y -CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0 -CONFIG_SECURITY_SELINUX_DISABLE=y -CONFIG_INTEGRITY_SIGNATURE=y -CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y -CONFIG_IMA=y -CONFIG_IMA_DEFAULT_HASH_SHA256=y -CONFIG_IMA_WRITE_POLICY=y -CONFIG_IMA_APPRAISE=y -CONFIG_CRYPTO_FIPS=y -CONFIG_CRYPTO_DH=m -CONFIG_CRYPTO_ECDH=m -CONFIG_CRYPTO_USER=m -# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set -CONFIG_CRYPTO_PCRYPT=m -CONFIG_CRYPTO_CRYPTD=m -CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_CHACHA20POLY1305=m -CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_KEYWRAP=m -CONFIG_CRYPTO_XCBC=m -CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_CRC32=m -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_RMD128=m -CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_RMD256=m -CONFIG_CRYPTO_RMD320=m -CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_SHA3=m -CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_WP512=m -CONFIG_CRYPTO_AES_TI=m -CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAMELLIA=m -CONFIG_CRYPTO_CAST5=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_FCRYPT=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SALSA20=m -CONFIG_CRYPTO_SEED=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_842=m -CONFIG_CRYPTO_LZ4=m -CONFIG_CRYPTO_LZ4HC=m -CONFIG_CRYPTO_ANSI_CPRNG=m -CONFIG_CRYPTO_USER_API_HASH=m -CONFIG_CRYPTO_USER_API_SKCIPHER=m -CONFIG_CRYPTO_USER_API_RNG=m -CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_ZCRYPT=m -CONFIG_PKEY=m -CONFIG_CRYPTO_PAES_S390=m -CONFIG_CRYPTO_SHA1_S390=m -CONFIG_CRYPTO_SHA256_S390=m -CONFIG_CRYPTO_SHA512_S390=m -CONFIG_CRYPTO_DES_S390=m -CONFIG_CRYPTO_AES_S390=m -CONFIG_CRYPTO_GHASH_S390=m -CONFIG_CRYPTO_CRC32_S390=y -CONFIG_CRC7=m -CONFIG_CRC8=m -CONFIG_CORDIC=m -CONFIG_CMM=m -CONFIG_APPLDATA_BASE=y -CONFIG_KVM=m -CONFIG_KVM_S390_UCONTROL=y -CONFIG_VHOST_NET=m -CONFIG_VHOST_VSOCK=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index d92bab844b73..be09a208b608 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -1,27 +1,33 @@ # CONFIG_SWAP is not set CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +# CONFIG_CPU_ISOLATION is not set +# CONFIG_UTS_NS is not set +# CONFIG_PID_NS is not set +# CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_COMPAT_BRK is not set -CONFIG_PARTITION_ADVANCED=y -CONFIG_IBM_PARTITION=y -CONFIG_DEFAULT_DEADLINE=y CONFIG_TUNE_ZEC12=y # CONFIG_COMPAT is not set CONFIG_NR_CPUS=2 -# CONFIG_HOTPLUG_CPU is not set CONFIG_HZ_100=y # CONFIG_ARCH_RANDOM is not set -# CONFIG_COMPACTION is not set -# CONFIG_MIGRATION is not set -# CONFIG_BOUNCE is not set -# CONFIG_CHECK_STACK is not set +# CONFIG_RELOCATABLE is not set # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set CONFIG_CRASH_DUMP=y -# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set # CONFIG_SECCOMP is not set +# CONFIG_PFAULT is not set +# CONFIG_S390_HYPFS_FS is not set +# CONFIG_VIRTUALIZATION is not set +# CONFIG_S390_GUEST is not set +CONFIG_PARTITION_ADVANCED=y +CONFIG_IBM_PARTITION=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +# CONFIG_COMPACTION is not set +# CONFIG_MIGRATION is not set +# CONFIG_BOUNCE is not set CONFIG_NET=y # CONFIG_IUCV is not set CONFIG_DEVTMPFS=y @@ -43,7 +49,6 @@ CONFIG_ZFCP=y # CONFIG_HVC_IUCV is not set # CONFIG_HW_RANDOM_S390 is not set CONFIG_RAW_DRIVER=y -# CONFIG_SCLP_ASYNC is not set # CONFIG_HMC_DRV is not set # CONFIG_S390_TAPE is not set # CONFIG_VMCP is not set @@ -56,6 +61,7 @@ CONFIG_RAW_DRIVER=y CONFIG_CONFIGFS_FS=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set +# CONFIG_DIMLIB is not set CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_FS=y @@ -64,7 +70,4 @@ CONFIG_PANIC_ON_OOPS=y # CONFIG_SCHED_DEBUG is not set CONFIG_RCU_CPU_STALL_TIMEOUT=60 # CONFIG_FTRACE is not set -# CONFIG_PFAULT is not set -# CONFIG_S390_HYPFS_FS is not set -# CONFIG_VIRTUALIZATION is not set -# CONFIG_S390_GUEST is not set +# CONFIG_RUNTIME_TESTING_MENU is not set From 868202ce15a7b52534257426a94f40b6d9f6150f Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 17 Jul 2019 19:38:42 +0200 Subject: [PATCH 514/823] s390/boot: add missing declarations and includes Add __swsusp_reset_dma declaration to avoid the following sparse warnings: arch/s390/kernel/setup.c:107:15: warning: symbol '__swsusp_reset_dma' was not declared. Should it be static? arch/s390/boot/startup.c:52:15: warning: symbol '__swsusp_reset_dma' was not declared. Should it be static? Add verify_facilities declaration to avoid the following sparse warning: arch/s390/boot/als.c:105:6: warning: symbol 'verify_facilities' was not declared. Should it be static? Include "boot.h" into arch/s390/boot/kaslr.c to expose get_random_base function declaration and avoid the following sparse warning: arch/s390/boot/kaslr.c:90:15: warning: symbol 'get_random_base' was not declared. Should it be static? Signed-off-by: Vasily Gorbik --- arch/s390/boot/boot.h | 1 + arch/s390/boot/kaslr.c | 1 + arch/s390/include/asm/setup.h | 1 + 3 files changed, 3 insertions(+) diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h index 082905d97309..1c3b2b257637 100644 --- a/arch/s390/boot/boot.h +++ b/arch/s390/boot/boot.h @@ -8,6 +8,7 @@ void store_ipl_parmblock(void); void setup_boot_command_line(void); void parse_boot_command_line(void); void setup_memory_end(void); +void verify_facilities(void); void print_missing_facilities(void); unsigned long get_random_base(unsigned long safe_addr); diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c index 3bdd8132e56b..c34a6387ce38 100644 --- a/arch/s390/boot/kaslr.c +++ b/arch/s390/boot/kaslr.c @@ -7,6 +7,7 @@ #include #include #include "compressed/decompressor.h" +#include "boot.h" #define PRNG_MODE_TDES 1 #define PRNG_MODE_SHA512 2 diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index c5cfff7b1f91..70bd65724ec4 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -84,6 +84,7 @@ extern int noexec_disabled; extern int memory_end_set; extern unsigned long memory_end; extern unsigned long max_physmem_end; +extern unsigned long __swsusp_reset_dma; #define MACHINE_IS_VM (S390_lowcore.machine_flags & MACHINE_FLAG_VM) #define MACHINE_IS_KVM (S390_lowcore.machine_flags & MACHINE_FLAG_KVM) From d25220d2f2ece9e516588ed5df2ed373069b3a02 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 17 Jul 2019 20:07:42 +0200 Subject: [PATCH 515/823] s390/lib: add missing include Include into arch/s390/lib/xor.c to expose xor_block_xc declaration and avoid the following sparse warning: arch/s390/lib/xor.c:128:27: warning: symbol 'xor_block_xc' was not declared. Should it be static? Signed-off-by: Vasily Gorbik --- arch/s390/lib/xor.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c index 96580590ccaf..29d9470dbceb 100644 --- a/arch/s390/lib/xor.c +++ b/arch/s390/lib/xor.c @@ -9,6 +9,7 @@ #include #include #include +#include static void xor_xc_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) { From 06f9895fda39422fb9250a78454e69aadace13c7 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 17 Jul 2019 20:05:11 +0200 Subject: [PATCH 516/823] s390/perf: make cf_diag_csd static Since there is really no reason for cf_diag_csd per cpu variable to be globally visible make it static to avoid the following sparse warning: arch/s390/kernel/perf_cpum_cf_diag.c:37:1: warning: symbol 'cf_diag_csd' was not declared. Should it be static? Signed-off-by: Vasily Gorbik --- arch/s390/kernel/perf_cpum_cf_diag.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c index d4e031f7b9c8..5f1fd1581330 100644 --- a/arch/s390/kernel/perf_cpum_cf_diag.c +++ b/arch/s390/kernel/perf_cpum_cf_diag.c @@ -34,7 +34,7 @@ struct cf_diag_csd { /* Counter set data per CPU */ unsigned char start[PAGE_SIZE]; /* Counter set at event start */ unsigned char data[PAGE_SIZE]; /* Counter set at event delete */ }; -DEFINE_PER_CPU(struct cf_diag_csd, cf_diag_csd); +static DEFINE_PER_CPU(struct cf_diag_csd, cf_diag_csd); /* Counter sets are stored as data stream in a page sized memory buffer and * exported to user space via raw data attached to the event sample data. From 1877011a3568fcadf2ee28f4d02fe5c31b1bb060 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 17 Jul 2019 19:42:22 +0200 Subject: [PATCH 517/823] s390/kexec: add missing include to machine_kexec_reloc.c Include into machine_kexec_reloc.c to expose arch_kexec_do_relocs declaration and avoid the following sparse warnings: arch/s390/kernel/machine_kexec_reloc.c:4:5: warning: symbol 'arch_kexec_do_relocs' was not declared. Should it be static? arch/s390/boot/../kernel/machine_kexec_reloc.c:4:5: warning: symbol 'arch_kexec_do_relocs' was not declared. Should it be static? Signed-off-by: Vasily Gorbik --- arch/s390/kernel/machine_kexec_reloc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c index 1dded39239f8..3b664cb3ec4d 100644 --- a/arch/s390/kernel/machine_kexec_reloc.c +++ b/arch/s390/kernel/machine_kexec_reloc.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val, unsigned long addr) From ffbd268506ca70c2cd18238762a29b9a47d8d9fa Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 17 Jul 2019 19:41:09 +0200 Subject: [PATCH 518/823] s390/mm: make gmap_test_and_clear_dirty_pmd static Since gmap_test_and_clear_dirty_pmd is not exported and has no reason to be globally visible make it static to avoid the following sparse warning: arch/s390/mm/gmap.c:2427:6: warning: symbol 'gmap_test_and_clear_dirty_pmd' was not declared. Should it be static? Signed-off-by: Vasily Gorbik --- arch/s390/mm/gmap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 1e668b95e0c6..39c3a6e3d262 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2424,8 +2424,8 @@ EXPORT_SYMBOL_GPL(gmap_pmdp_idte_global); * This function is assumed to be called with the guest_table_lock * held. */ -bool gmap_test_and_clear_dirty_pmd(struct gmap *gmap, pmd_t *pmdp, - unsigned long gaddr) +static bool gmap_test_and_clear_dirty_pmd(struct gmap *gmap, pmd_t *pmdp, + unsigned long gaddr) { if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID) return false; From 7f5aa1154b1a30653a12e0f7f473494de77ad670 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 29 Jul 2019 07:39:44 +0200 Subject: [PATCH 519/823] s390/mm: add fallthrough annotations Commit a035d552a93b ("Makefile: Globally enable fall-through warning") enables fall-through warnings globally. Add missing annotations. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/mm/fault.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 63507662828f..7b0bb475c166 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -327,6 +327,7 @@ static noinline void do_fault_error(struct pt_regs *regs, int access, case VM_FAULT_BADACCESS: if (access == VM_EXEC && signal_return(regs) == 0) break; + /* fallthrough */ case VM_FAULT_BADMAP: /* Bad memory access. Check if it is kernel or user space. */ if (user_mode(regs)) { @@ -336,7 +337,9 @@ static noinline void do_fault_error(struct pt_regs *regs, int access, do_sigsegv(regs, si_code); break; } + /* fallthrough */ case VM_FAULT_BADCONTEXT: + /* fallthrough */ case VM_FAULT_PFAULT: do_no_context(regs); break; From 90a93ff4051ede8320c5576d99f34e0f75e99c1a Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 29 Jul 2019 07:47:02 +0200 Subject: [PATCH 520/823] s390/tape: add fallthrough annotations Commit a035d552a93b ("Makefile: Globally enable fall-through warning") enables fall-through warnings globally. Add missing annotations. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- drivers/s390/char/tape_core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/s390/char/tape_core.c b/drivers/s390/char/tape_core.c index 8d3370da2dfc..3e0b2f63a9d2 100644 --- a/drivers/s390/char/tape_core.c +++ b/drivers/s390/char/tape_core.c @@ -677,6 +677,7 @@ tape_generic_remove(struct ccw_device *cdev) switch (device->tape_state) { case TS_INIT: tape_state_set(device, TS_NOT_OPER); + /* fallthrough */ case TS_NOT_OPER: /* * Nothing to do. @@ -949,6 +950,7 @@ __tape_start_request(struct tape_device *device, struct tape_request *request) break; if (device->tape_state == TS_UNUSED) break; + /* fallthrough */ default: if (device->tape_state == TS_BLKUSE) break; @@ -1116,6 +1118,7 @@ __tape_do_irq (struct ccw_device *cdev, unsigned long intparm, struct irb *irb) case -ETIMEDOUT: DBF_LH(1, "(%08x): Request timed out\n", device->cdev_id); + /* fallthrough */ case -EIO: __tape_end_request(device, request, -EIO); break; From 943dd5fa70ada0266c3a572c641be537b69ae2a8 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Mon, 29 Jul 2019 01:01:21 +0200 Subject: [PATCH 521/823] s390/3215: add switch fall through comment for -Wimplicit-fallthrough Silence the following warning when built with -Wimplicit-fallthrough=3 enabled by default since 5.3-rc2: drivers/s390/char/con3215.c: In function 'raw3215_irq': drivers/s390/char/con3215.c:399:6: warning: this statement may fall through [-Wimplicit-fallthrough=] 399 | if (dstat == 0x08) | ^ drivers/s390/char/con3215.c:401:2: note: here 401 | case 0x04: | ^~~~ Signed-off-by: Vasily Gorbik --- drivers/s390/char/con3215.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c index 8c9d412b6d33..e7cf0a1d4f71 100644 --- a/drivers/s390/char/con3215.c +++ b/drivers/s390/char/con3215.c @@ -398,6 +398,7 @@ static void raw3215_irq(struct ccw_device *cdev, unsigned long intparm, } if (dstat == 0x08) break; + /* else, fall through */ case 0x04: /* Device end interrupt. */ if ((raw = req->info) == NULL) From 8480657280ee769ad23101297e1e6be0f8d205ec Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 17 Jul 2019 20:09:28 +0200 Subject: [PATCH 522/823] vfio-ccw: make vfio_ccw_async_region_ops static Since vfio_ccw_async_region_ops is not exported and has no reason to be globally visible make it static to avoid the following sparse warning: drivers/s390/cio/vfio_ccw_async.c:73:30: warning: symbol 'vfio_ccw_async_region_ops' was not declared. Should it be static? Fixes: d5afd5d135c8 ("vfio-ccw: add handling for async channel instructions") Reviewed-by: Cornelia Huck Signed-off-by: Vasily Gorbik --- drivers/s390/cio/vfio_ccw_async.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/s390/cio/vfio_ccw_async.c b/drivers/s390/cio/vfio_ccw_async.c index 8c1d2357ef5b..7a838e3d7c0f 100644 --- a/drivers/s390/cio/vfio_ccw_async.c +++ b/drivers/s390/cio/vfio_ccw_async.c @@ -70,7 +70,7 @@ static void vfio_ccw_async_region_release(struct vfio_ccw_private *private, } -const struct vfio_ccw_regops vfio_ccw_async_region_ops = { +static const struct vfio_ccw_regops vfio_ccw_async_region_ops = { .read = vfio_ccw_async_region_read, .write = vfio_ccw_async_region_write, .release = vfio_ccw_async_region_release, From a07fc0bb483eb24444cebd59a8112ce6e6964c48 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 24 Jul 2019 14:54:43 +0800 Subject: [PATCH 523/823] RDMA/hns: Fix build error If INFINIBAND_HNS_HIP08 is selected and HNS3 is m, but INFINIBAND_HNS is y, building fails: drivers/infiniband/hw/hns/hns_roce_hw_v2.o: In function `hns_roce_hw_v2_exit': hns_roce_hw_v2.c:(.exit.text+0xd): undefined reference to `hnae3_unregister_client' drivers/infiniband/hw/hns/hns_roce_hw_v2.o: In function `hns_roce_hw_v2_init': hns_roce_hw_v2.c:(.init.text+0xd): undefined reference to `hnae3_register_client' Also if INFINIBAND_HNS_HIP06 is selected and HNS_DSAF is m, but INFINIBAND_HNS is y, building fails: drivers/infiniband/hw/hns/hns_roce_hw_v1.o: In function `hns_roce_v1_reset': hns_roce_hw_v1.c:(.text+0x39fa): undefined reference to `hns_dsaf_roce_reset' hns_roce_hw_v1.c:(.text+0x3a25): undefined reference to `hns_dsaf_roce_reset' Reported-by: Hulk Robot Fixes: dd74282df573 ("RDMA/hns: Initialize the PCI device for hip08 RoCE") Fixes: 08805fdbeb2d ("RDMA/hns: Split hw v1 driver from hns roce driver") Signed-off-by: YueHaibing Link: https://lore.kernel.org/r/20190724065443.53068-1-yuehaibing@huawei.com Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hns/Kconfig | 6 +++--- drivers/infiniband/hw/hns/Makefile | 8 ++------ 2 files changed, 5 insertions(+), 9 deletions(-) diff --git a/drivers/infiniband/hw/hns/Kconfig b/drivers/infiniband/hw/hns/Kconfig index 8bf847bcd8d3..54782197c717 100644 --- a/drivers/infiniband/hw/hns/Kconfig +++ b/drivers/infiniband/hw/hns/Kconfig @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only config INFINIBAND_HNS - tristate "HNS RoCE Driver" + bool "HNS RoCE Driver" depends on NET_VENDOR_HISILICON depends on ARM64 || (COMPILE_TEST && 64BIT) ---help--- @@ -11,7 +11,7 @@ config INFINIBAND_HNS To compile HIP06 or HIP08 driver as module, choose M here. config INFINIBAND_HNS_HIP06 - bool "Hisilicon Hip06 Family RoCE support" + tristate "Hisilicon Hip06 Family RoCE support" depends on INFINIBAND_HNS && HNS && HNS_DSAF && HNS_ENET ---help--- RoCE driver support for Hisilicon RoCE engine in Hisilicon Hip06 and @@ -21,7 +21,7 @@ config INFINIBAND_HNS_HIP06 module will be called hns-roce-hw-v1 config INFINIBAND_HNS_HIP08 - bool "Hisilicon Hip08 Family RoCE support" + tristate "Hisilicon Hip08 Family RoCE support" depends on INFINIBAND_HNS && PCI && HNS3 ---help--- RoCE driver support for Hisilicon RoCE engine in Hisilicon Hip08 SoC. diff --git a/drivers/infiniband/hw/hns/Makefile b/drivers/infiniband/hw/hns/Makefile index e105945b94a1..449a2d81319d 100644 --- a/drivers/infiniband/hw/hns/Makefile +++ b/drivers/infiniband/hw/hns/Makefile @@ -9,12 +9,8 @@ hns-roce-objs := hns_roce_main.o hns_roce_cmd.o hns_roce_pd.o \ hns_roce_ah.o hns_roce_hem.o hns_roce_mr.o hns_roce_qp.o \ hns_roce_cq.o hns_roce_alloc.o hns_roce_db.o hns_roce_srq.o hns_roce_restrack.o -ifdef CONFIG_INFINIBAND_HNS_HIP06 hns-roce-hw-v1-objs := hns_roce_hw_v1.o $(hns-roce-objs) -obj-$(CONFIG_INFINIBAND_HNS) += hns-roce-hw-v1.o -endif +obj-$(CONFIG_INFINIBAND_HNS_HIP06) += hns-roce-hw-v1.o -ifdef CONFIG_INFINIBAND_HNS_HIP08 hns-roce-hw-v2-objs := hns_roce_hw_v2.o hns_roce_hw_v2_dfx.o $(hns-roce-objs) -obj-$(CONFIG_INFINIBAND_HNS) += hns-roce-hw-v2.o -endif +obj-$(CONFIG_INFINIBAND_HNS_HIP08) += hns-roce-hw-v2.o From 61c30c98ef17e5a330d7bb8494b78b3d6dffe9b8 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 29 Jul 2019 13:57:49 +0200 Subject: [PATCH 524/823] dax: Fix missed wakeup in put_unlocked_entry() The condition checking whether put_unlocked_entry() needs to wake up following waiter got broken by commit 23c84eb78375 ("dax: Fix missed wakeup with PMD faults"). We need to wake the waiter whenever the passed entry is valid (i.e., non-NULL and not special conflict entry). This could lead to processes never being woken up when waiting for entry lock. Fix the condition. Cc: Link: http://lore.kernel.org/r/20190729120228.GC17833@quack2.suse.cz Fixes: 23c84eb78375 ("dax: Fix missed wakeup with PMD faults") Signed-off-by: Jan Kara Signed-off-by: Dan Williams --- fs/dax.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/dax.c b/fs/dax.c index a237141d8787..b64964ef44f6 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -266,7 +266,7 @@ static void wait_entry_unlocked(struct xa_state *xas, void *entry) static void put_unlocked_entry(struct xa_state *xas, void *entry) { /* If we were the only waiter woken, wake the next one */ - if (entry && dax_is_conflict(entry)) + if (entry && !dax_is_conflict(entry)) dax_wake_entry(xas, entry, false); } From f3eb2c334a6d3f5e704ecd0b150d5cfe6e3aca40 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 29 Jul 2019 06:09:53 -0500 Subject: [PATCH 525/823] arcnet: com90xx: Mark expected switch fall-throughs Mark switch cases where we are expecting to fall through. This patch fixes the following warnings (Building: powerpc allyesconfig): drivers/net/arcnet/com90xx.c: In function 'com90xx_setup': include/linux/printk.h:304:2: warning: this statement may fall through [-Wimplicit-fallthrough=] printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/net/arcnet/com90xx.c:695:3: note: in expansion of macro 'pr_err' pr_err("Too many arguments\n"); ^~~~~~ drivers/net/arcnet/com90xx.c:696:2: note: here case 3: /* Mem address */ ^~~~ drivers/net/arcnet/com90xx.c:697:9: warning: this statement may fall through [-Wimplicit-fallthrough=] shmem = ints[3]; ~~~~~~^~~~~~~~~ drivers/net/arcnet/com90xx.c:698:2: note: here case 2: /* IRQ */ ^~~~ drivers/net/arcnet/com90xx.c:699:7: warning: this statement may fall through [-Wimplicit-fallthrough=] irq = ints[2]; ~~~~^~~~~~~~~ drivers/net/arcnet/com90xx.c:700:2: note: here case 1: /* IO address */ ^~~~ Reported-by: Stephen Rothwell Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/arcnet/com90xx.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c index ca4a57c30bf8..bd75d06ad7df 100644 --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -693,10 +693,13 @@ static int __init com90xx_setup(char *s) switch (ints[0]) { default: /* ERROR */ pr_err("Too many arguments\n"); + /* Fall through */ case 3: /* Mem address */ shmem = ints[3]; + /* Fall through */ case 2: /* IRQ */ irq = ints[2]; + /* Fall through */ case 1: /* IO address */ io = ints[1]; } From 56f37a3fa2190732957882e10ec20adf83c6cb93 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 29 Jul 2019 06:13:20 -0500 Subject: [PATCH 526/823] arcnet: com90io: Mark expected switch fall-throughs Mark switch cases where we are expecting to fall through. This patch fixes the following warnings (Building: powerpc allyesconfig): drivers/net/arcnet/com90io.c: In function 'com90io_setup': include/linux/printk.h:304:2: warning: this statement may fall through [-Wimplicit-fallthrough=] printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/net/arcnet/com90io.c:365:3: note: in expansion of macro 'pr_err' pr_err("Too many arguments\n"); ^~~~~~ drivers/net/arcnet/com90io.c:366:2: note: here case 2: /* IRQ */ ^~~~ drivers/net/arcnet/com90io.c:367:7: warning: this statement may fall through [-Wimplicit-fallthrough=] irq = ints[2]; ~~~~^~~~~~~~~ drivers/net/arcnet/com90io.c:368:2: note: here case 1: /* IO address */ ^~~~ Reported-by: Stephen Rothwell Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/arcnet/com90io.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index 2c546013a980..186bbf87bc84 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -363,8 +363,10 @@ static int __init com90io_setup(char *s) switch (ints[0]) { default: /* ERROR */ pr_err("Too many arguments\n"); + /* Fall through */ case 2: /* IRQ */ irq = ints[2]; + /* Fall through */ case 1: /* IO address */ io = ints[1]; } From 26027f4243c1a23399b85a3cff9b0b89e405be59 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 29 Jul 2019 06:15:50 -0500 Subject: [PATCH 527/823] arcnet: arc-rimi: Mark expected switch fall-throughs Mark switch cases where we are expecting to fall through. This patch fixes the following warnings (Building: powerpc allyesconfig): drivers/net/arcnet/arc-rimi.c: In function 'arcrimi_setup': include/linux/printk.h:304:2: warning: this statement may fall through [-Wimplicit-fallthrough=] printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/net/arcnet/arc-rimi.c:365:3: note: in expansion of macro 'pr_err' pr_err("Too many arguments\n"); ^~~~~~ drivers/net/arcnet/arc-rimi.c:366:2: note: here case 3: /* Node ID */ ^~~~ drivers/net/arcnet/arc-rimi.c:367:8: warning: this statement may fall through [-Wimplicit-fallthrough=] node = ints[3]; ~~~~~^~~~~~~~~ drivers/net/arcnet/arc-rimi.c:368:2: note: here case 2: /* IRQ */ ^~~~ drivers/net/arcnet/arc-rimi.c:369:7: warning: this statement may fall through [-Wimplicit-fallthrough=] irq = ints[2]; ~~~~^~~~~~~~~ drivers/net/arcnet/arc-rimi.c:370:2: note: here case 1: /* IO address */ ^~~~ Reported-by: Stephen Rothwell Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/arcnet/arc-rimi.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index 11c5bad95226..14a5fb378145 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -363,10 +363,13 @@ static int __init arcrimi_setup(char *s) switch (ints[0]) { default: /* ERROR */ pr_err("Too many arguments\n"); + /* Fall through */ case 3: /* Node ID */ node = ints[3]; + /* Fall through */ case 2: /* IRQ */ irq = ints[2]; + /* Fall through */ case 1: /* IO address */ io = ints[1]; } From a7f9cbf0ed2f67380b547971145e823b9225d39d Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 29 Jul 2019 14:16:37 +0200 Subject: [PATCH 528/823] MAINTAINERS: Remove mailing-list entry for XDP (eXpress Data Path) This removes the mailing list xdp-newbies@vger.kernel.org from the XDP kernel maintainers entry. Being in the kernel MAINTAINERS file successfully caused the list to receive kbuild bot warnings, syzbot reports and sometimes developer patches. The level of details in these messages, doesn't match the target audience of the XDP-newbies list. This is based on a survey on the mailing list, where 73% voted for removal from MAINTAINERS file. Signed-off-by: Jesper Dangaard Brouer Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index bbc2efb2b236..9f5b8bd4faf9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17549,7 +17549,6 @@ M: Jakub Kicinski M: Jesper Dangaard Brouer M: John Fastabend L: netdev@vger.kernel.org -L: xdp-newbies@vger.kernel.org L: bpf@vger.kernel.org S: Supported F: net/core/xdp.c From 051c7b39be4a91f6b7d8c4548444e4b850f1f56c Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Mon, 29 Jul 2019 16:24:33 +0800 Subject: [PATCH 529/823] net: sched: Fix a possible null-pointer dereference in dequeue_func() In dequeue_func(), there is an if statement on line 74 to check whether skb is NULL: if (skb) When skb is NULL, it is used on line 77: prefetch(&skb->end); Thus, a possible null-pointer dereference may occur. To fix this bug, skb->end is used when skb is not NULL. This bug is found by a static analysis tool STCheck written by us. Fixes: 76e3cc126bb2 ("codel: Controlled Delay AQM") Signed-off-by: Jia-Ju Bai Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- net/sched/sch_codel.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index 25ef172c23df..30169b3adbbb 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -71,10 +71,10 @@ static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx) struct Qdisc *sch = ctx; struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); - if (skb) + if (skb) { sch->qstats.backlog -= qdisc_pkt_len(skb); - - prefetch(&skb->end); /* we'll need skb_shinfo() */ + prefetch(&skb->end); /* we'll need skb_shinfo() */ + } return skb; } From d7bae09fa008c6c9a489580db0a5a12063b97f97 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Mon, 29 Jul 2019 12:28:41 +0300 Subject: [PATCH 530/823] net: bridge: delete local fdb on device init failure On initialization failure we have to delete the local fdb which was inserted due to the default pvid creation. This problem has been present since the inception of default_pvid. Note that currently there are 2 cases: 1) in br_dev_init() when br_multicast_init() fails 2) if register_netdevice() fails after calling ndo_init() This patch takes care of both since br_vlan_flush() is called on both occasions. Also the new fdb delete would be a no-op on normal bridge device destruction since the local fdb would've been already flushed by br_dev_delete(). This is not an issue for ports since nbp_vlan_init() is called last when adding a port thus nothing can fail after it. Reported-by: syzbot+88533dc8b582309bf3ee@syzkaller.appspotmail.com Fixes: 5be5a2df40f0 ("bridge: Add filtering support for default_pvid") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_vlan.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 021cc9f66804..a544e161c7fa 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -715,6 +715,11 @@ void br_vlan_flush(struct net_bridge *br) ASSERT_RTNL(); + /* delete auto-added default pvid local fdb before flushing vlans + * otherwise it will be leaked on bridge device init failure + */ + br_fdb_delete_by_port(br, NULL, 0, 1); + vg = br_vlan_group(br); __vlan_flush(vg); RCU_INIT_POINTER(br->vlgrp, NULL); From 15fe6a8dcc3b48358c28e17b485fc837f9605ec4 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Sun, 28 Jul 2019 14:13:38 +0300 Subject: [PATCH 531/823] RDMA/qedr: Fix the hca_type and hca_rev returned in device attributes There was a place holder for hca_type and vendor was returned in hca_rev. Fix the hca_rev to return the hw revision and fix the hca_type to return an informative string representing the hca. Signed-off-by: Michal Kalderon Link: https://lore.kernel.org/r/20190728111338.21930-1-michal.kalderon@marvell.com Signed-off-by: Doug Ledford --- drivers/infiniband/hw/qedr/main.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index 533157a2a3be..f97b3d65b30c 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -125,14 +125,20 @@ static ssize_t hw_rev_show(struct device *device, struct device_attribute *attr, struct qedr_dev *dev = rdma_device_to_drv_device(device, struct qedr_dev, ibdev); - return scnprintf(buf, PAGE_SIZE, "0x%x\n", dev->pdev->vendor); + return scnprintf(buf, PAGE_SIZE, "0x%x\n", dev->attr.hw_ver); } static DEVICE_ATTR_RO(hw_rev); static ssize_t hca_type_show(struct device *device, struct device_attribute *attr, char *buf) { - return scnprintf(buf, PAGE_SIZE, "%s\n", "HCA_TYPE_TO_SET"); + struct qedr_dev *dev = + rdma_device_to_drv_device(device, struct qedr_dev, ibdev); + + return scnprintf(buf, PAGE_SIZE, "FastLinQ QL%x %s\n", + dev->pdev->device, + rdma_protocol_iwarp(&dev->ibdev, 1) ? + "iWARP" : "RoCE"); } static DEVICE_ATTR_RO(hca_type); From 37151a41df800493cfcbbef4f7208ffe04feb959 Mon Sep 17 00:00:00 2001 From: Yuki Tsunashima Date: Mon, 29 Jul 2019 17:10:36 +0200 Subject: [PATCH 532/823] ALSA: pcm: fix lost wakeup event scenarios in snd_pcm_drain lost wakeup can occur after enabling irq, therefore put task into interruptible before enabling interrupts, without this change, task can be put to sleep and snd_pcm_drain will delay Fixes: f2b3614cefb6 ("ALSA: PCM - Don't check DMA time-out too shortly") Signed-off-by: Yuki Tsunashima Signed-off-by: Suresh Udipi [ported from 4.9] Signed-off-by: Adam Miartus Signed-off-by: Takashi Iwai --- sound/core/pcm_native.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 12dd9b318db1..703857aab00f 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -1873,6 +1873,7 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream, if (!to_check) break; /* all drained */ init_waitqueue_entry(&wait, current); + set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&to_check->sleep, &wait); snd_pcm_stream_unlock_irq(substream); if (runtime->no_period_wakeup) @@ -1885,7 +1886,7 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream, } tout = msecs_to_jiffies(tout * 1000); } - tout = schedule_timeout_interruptible(tout); + tout = schedule_timeout(tout); snd_pcm_stream_lock_irq(substream); group = snd_pcm_stream_group_ref(substream); From e1ab2431ebee2634b9868013d3fefd03c800e510 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 29 Jul 2019 09:25:03 -0500 Subject: [PATCH 533/823] arcnet: com20020-isa: Mark expected switch fall-throughs Mark switch cases where we are expecting to fall through. This patch fixes the following warnings: drivers/net/arcnet/com20020-isa.c: warning: this statement may fall through [-Wimplicit-fallthrough=]: => 205:13, 203:10, 209:7, 201:11, 207:8 Reported-by: Geert Uytterhoeven Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/arcnet/com20020-isa.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index 28510e33924f..cd27fdc1059b 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -197,16 +197,22 @@ static int __init com20020isa_setup(char *s) switch (ints[0]) { default: /* ERROR */ pr_info("Too many arguments\n"); + /* Fall through */ case 6: /* Timeout */ timeout = ints[6]; + /* Fall through */ case 5: /* CKP value */ clockp = ints[5]; + /* Fall through */ case 4: /* Backplane flag */ backplane = ints[4]; + /* Fall through */ case 3: /* Node ID */ node = ints[3]; + /* Fall through */ case 2: /* IRQ */ irq = ints[2]; + /* Fall through */ case 1: /* IO address */ io = ints[1]; } From 05bba1edaf9c11023901800bc4d2ce5b96e0836a Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 29 Jul 2019 09:59:47 -0500 Subject: [PATCH 534/823] net/af_iucv: mark expected switch fall-throughs Mark switch cases where we are expecting to fall through. This patch fixes the following warnings: net/iucv/af_iucv.c: warning: this statement may fall through [-Wimplicit-fallthrough=]: => 537:3, 519:6, 2246:6, 510:6 Notice that, in this particular case, the code comment is modified in accordance with what GCC is expecting to find. Reported-by: Geert Uytterhoeven Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: David S. Miller --- net/iucv/af_iucv.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 09e1694b6d34..ebb62a4ebe30 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -512,7 +512,9 @@ static void iucv_sock_close(struct sock *sk) sk->sk_state = IUCV_DISCONN; sk->sk_state_change(sk); } - case IUCV_DISCONN: /* fall through */ + /* fall through */ + + case IUCV_DISCONN: sk->sk_state = IUCV_CLOSING; sk->sk_state_change(sk); @@ -525,8 +527,9 @@ static void iucv_sock_close(struct sock *sk) iucv_sock_in_state(sk, IUCV_CLOSED, 0), timeo); } + /* fall through */ - case IUCV_CLOSING: /* fall through */ + case IUCV_CLOSING: sk->sk_state = IUCV_CLOSED; sk->sk_state_change(sk); @@ -535,8 +538,9 @@ static void iucv_sock_close(struct sock *sk) skb_queue_purge(&iucv->send_skb_q); skb_queue_purge(&iucv->backlog_skb_q); + /* fall through */ - default: /* fall through */ + default: iucv_sever_path(sk, 1); } @@ -2247,10 +2251,10 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, kfree_skb(skb); break; } - /* fall through and receive non-zero length data */ + /* fall through - and receive non-zero length data */ case (AF_IUCV_FLAG_SHT): /* shutdown request */ - /* fall through and receive zero length data */ + /* fall through - and receive zero length data */ case 0: /* plain data frame */ IUCV_SKB_CB(skb)->class = trans_hdr->iucv_hdr.class; From 708637e65abd487ebb75fb55401c36a466c3135b Mon Sep 17 00:00:00 2001 From: Bernard Metzler Date: Sat, 27 Jul 2019 12:38:32 +0200 Subject: [PATCH 535/823] Do not dereference 'siw_crypto_shash' before checking Reported-by: "Dan Carpenter" Fixes: f29dd55b0236 ("rdma/siw: queue pair methods") Link: https://lore.kernel.org/r/OF61E386ED.49A73798-ON00258444.003BD6A6-00258444.003CC8D9@notes.na.collabserv.com Signed-off-by: Bernard Metzler Signed-off-by: Doug Ledford --- drivers/infiniband/sw/siw/siw_qp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/sw/siw/siw_qp.c b/drivers/infiniband/sw/siw/siw_qp.c index 11383d9f95ef..e27bd5b35b96 100644 --- a/drivers/infiniband/sw/siw/siw_qp.c +++ b/drivers/infiniband/sw/siw/siw_qp.c @@ -220,12 +220,14 @@ static int siw_qp_enable_crc(struct siw_qp *qp) { struct siw_rx_stream *c_rx = &qp->rx_stream; struct siw_iwarp_tx *c_tx = &qp->tx_ctx; - int size = crypto_shash_descsize(siw_crypto_shash) + - sizeof(struct shash_desc); + int size; if (siw_crypto_shash == NULL) return -ENOENT; + size = crypto_shash_descsize(siw_crypto_shash) + + sizeof(struct shash_desc); + c_tx->mpa_crc_hd = kzalloc(size, GFP_KERNEL); c_rx->mpa_crc_hd = kzalloc(size, GFP_KERNEL); if (!c_tx->mpa_crc_hd || !c_rx->mpa_crc_hd) { From 195b2919ccd7ffcaf6b6bbcb39444a53ab8308c7 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Sat, 27 Jul 2019 21:21:37 +0200 Subject: [PATCH 536/823] net: stmmac: manage errors returned by of_get_mac_address() Commit d01f449c008a ("of_net: add NVMEM support to of_get_mac_address") added support for reading the MAC address from an nvmem-cell. This required changing the logic to return an error pointer upon failure. If stmmac is loaded before the nvmem provider driver then of_get_mac_address() return an error pointer with -EPROBE_DEFER. Propagate this error so the stmmac driver will be probed again after the nvmem provider driver is loaded. Default to a random generated MAC address in case of any other error, instead of using the error pointer as MAC address. Fixes: d01f449c008a ("of_net: add NVMEM support to of_get_mac_address") Signed-off-by: Martin Blumenstingl Reviewed-by: Neil Armstrong Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 73fc2524372e..154daf4d1072 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -370,6 +370,13 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) return ERR_PTR(-ENOMEM); *mac = of_get_mac_address(np); + if (IS_ERR(*mac)) { + if (PTR_ERR(*mac) == -EPROBE_DEFER) + return ERR_CAST(*mac); + + *mac = NULL; + } + plat->interface = of_get_phy_mode(np); /* Some wrapper drivers still rely on phy_node. Let's save it while From 011f175428d46461f94a65dacb9a416529d08dda Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Sun, 28 Jul 2019 00:37:26 +0100 Subject: [PATCH 537/823] rocker: fix memory leaks of fib_work on two error return paths Currently there are two error return paths that leak memory allocated to fib_work. Fix this by kfree'ing fib_work before returning. Addresses-Coverity: ("Resource leak") Fixes: 19a9d136f198 ("ipv4: Flag fib_info with a fib_nh using IPv6 gateway") Fixes: dbcc4fa718ee ("rocker: Fail attempts to use routes with nexthop objects") Signed-off-by: Colin Ian King Reviewed-by: David Ahern Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 079f459c73a5..2c5d3f5b84dd 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2208,10 +2208,12 @@ static int rocker_router_fib_event(struct notifier_block *nb, if (fen_info->fi->fib_nh_is_v6) { NL_SET_ERR_MSG_MOD(info->extack, "IPv6 gateway with IPv4 route is not supported"); + kfree(fib_work); return notifier_from_errno(-EINVAL); } if (fen_info->fi->nh) { NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported"); + kfree(fib_work); return notifier_from_errno(-EINVAL); } } From 230bd958c2c846ee292aa38bc6b006296c24ca01 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Sun, 28 Jul 2019 02:46:45 +0200 Subject: [PATCH 538/823] mvpp2: refactor MTU change code The MTU change code can call napi_disable() with the device already down, leading to a deadlock. Also, lot of code is duplicated unnecessarily. Rework mvpp2_change_mtu() to avoid the deadlock and remove duplicated code. Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit") Signed-off-by: Matteo Croce Signed-off-by: David S. Miller --- .../net/ethernet/marvell/mvpp2/mvpp2_main.c | 41 ++++++------------- 1 file changed, 13 insertions(+), 28 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index b6591ea0c6d6..68fa2d563f0d 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -3700,6 +3700,7 @@ static int mvpp2_set_mac_address(struct net_device *dev, void *p) static int mvpp2_change_mtu(struct net_device *dev, int mtu) { struct mvpp2_port *port = netdev_priv(dev); + bool running = netif_running(dev); int err; if (!IS_ALIGNED(MVPP2_RX_PKT_SIZE(mtu), 8)) { @@ -3708,40 +3709,24 @@ static int mvpp2_change_mtu(struct net_device *dev, int mtu) mtu = ALIGN(MVPP2_RX_PKT_SIZE(mtu), 8); } - if (!netif_running(dev)) { - err = mvpp2_bm_update_mtu(dev, mtu); - if (!err) { - port->pkt_size = MVPP2_RX_PKT_SIZE(mtu); - return 0; - } - - /* Reconfigure BM to the original MTU */ - err = mvpp2_bm_update_mtu(dev, dev->mtu); - if (err) - goto log_error; - } - - mvpp2_stop_dev(port); + if (running) + mvpp2_stop_dev(port); err = mvpp2_bm_update_mtu(dev, mtu); - if (!err) { + if (err) { + netdev_err(dev, "failed to change MTU\n"); + /* Reconfigure BM to the original MTU */ + mvpp2_bm_update_mtu(dev, dev->mtu); + } else { port->pkt_size = MVPP2_RX_PKT_SIZE(mtu); - goto out_start; } - /* Reconfigure BM to the original MTU */ - err = mvpp2_bm_update_mtu(dev, dev->mtu); - if (err) - goto log_error; + if (running) { + mvpp2_start_dev(port); + mvpp2_egress_enable(port); + mvpp2_ingress_enable(port); + } -out_start: - mvpp2_start_dev(port); - mvpp2_egress_enable(port); - mvpp2_ingress_enable(port); - - return 0; -log_error: - netdev_err(dev, "failed to change MTU\n"); return err; } From 55b40dbf0e76b4bfb9d8b3a16a0208640a9a45df Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sun, 28 Jul 2019 14:56:36 +0200 Subject: [PATCH 539/823] net: fix ifindex collision during namespace removal Commit aca51397d014 ("netns: Fix arbitrary net_device-s corruptions on net_ns stop.") introduced a possibility to hit a BUG in case device is returning back to init_net and two following conditions are met: 1) dev->ifindex value is used in a name of another "dev%d" device in init_net. 2) dev->name is used by another device in init_net. Under real life circumstances this is hard to get. Therefore this has been present happily for over 10 years. To reproduce: $ ip a 1: lo: mtu 65536 qdisc noqueue state UNKNOWN group default qlen 1000 link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00 inet 127.0.0.1/8 scope host lo valid_lft forever preferred_lft forever inet6 ::1/128 scope host valid_lft forever preferred_lft forever 2: dummy0: mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 86:89:3f:86:61:29 brd ff:ff:ff:ff:ff:ff 3: enp0s2: mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 52:54:00:12:34:56 brd ff:ff:ff:ff:ff:ff $ ip netns add ns1 $ ip -n ns1 link add dummy1ns1 type dummy $ ip -n ns1 link add dummy2ns1 type dummy $ ip link set enp0s2 netns ns1 $ ip -n ns1 link set enp0s2 name dummy0 [ 100.858894] virtio_net virtio0 dummy0: renamed from enp0s2 $ ip link add dev4 type dummy $ ip -n ns1 a 1: lo: mtu 65536 qdisc noop state DOWN group default qlen 1000 link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00 2: dummy1ns1: mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 16:63:4c:38:3e:ff brd ff:ff:ff:ff:ff:ff 3: dummy2ns1: mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether aa:9e:86:dd:6b:5d brd ff:ff:ff:ff:ff:ff 4: dummy0: mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 52:54:00:12:34:56 brd ff:ff:ff:ff:ff:ff $ ip a 1: lo: mtu 65536 qdisc noqueue state UNKNOWN group default qlen 1000 link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00 inet 127.0.0.1/8 scope host lo valid_lft forever preferred_lft forever inet6 ::1/128 scope host valid_lft forever preferred_lft forever 2: dummy0: mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 86:89:3f:86:61:29 brd ff:ff:ff:ff:ff:ff 4: dev4: mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 5a:e1:4a:b6:ec:f8 brd ff:ff:ff:ff:ff:ff $ ip netns del ns1 [ 158.717795] default_device_exit: failed to move dummy0 to init_net: -17 [ 158.719316] ------------[ cut here ]------------ [ 158.720591] kernel BUG at net/core/dev.c:9824! [ 158.722260] invalid opcode: 0000 [#1] SMP KASAN PTI [ 158.723728] CPU: 0 PID: 56 Comm: kworker/u2:1 Not tainted 5.3.0-rc1+ #18 [ 158.725422] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 [ 158.727508] Workqueue: netns cleanup_net [ 158.728915] RIP: 0010:default_device_exit.cold+0x1d/0x1f [ 158.730683] Code: 84 e8 18 c9 3e fe 0f 0b e9 70 90 ff ff e8 36 e4 52 fe 89 d9 4c 89 e2 48 c7 c6 80 d6 25 84 48 c7 c7 20 c0 25 84 e8 f4 c8 3e [ 158.736854] RSP: 0018:ffff8880347e7b90 EFLAGS: 00010282 [ 158.738752] RAX: 000000000000003b RBX: 00000000ffffffef RCX: 0000000000000000 [ 158.741369] RDX: 0000000000000000 RSI: ffffffff8128013d RDI: ffffed10068fcf64 [ 158.743418] RBP: ffff888033550170 R08: 000000000000003b R09: fffffbfff0b94b9c [ 158.745626] R10: fffffbfff0b94b9b R11: ffffffff85ca5cdf R12: ffff888032f28000 [ 158.748405] R13: dffffc0000000000 R14: ffff8880335501b8 R15: 1ffff110068fcf72 [ 158.750638] FS: 0000000000000000(0000) GS:ffff888036000000(0000) knlGS:0000000000000000 [ 158.752944] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 158.755245] CR2: 00007fe8b45d21d0 CR3: 00000000340b4005 CR4: 0000000000360ef0 [ 158.757654] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 158.760012] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 158.762758] Call Trace: [ 158.763882] ? dev_change_net_namespace+0xbb0/0xbb0 [ 158.766148] ? devlink_nl_cmd_set_doit+0x520/0x520 [ 158.768034] ? dev_change_net_namespace+0xbb0/0xbb0 [ 158.769870] ops_exit_list.isra.0+0xa8/0x150 [ 158.771544] cleanup_net+0x446/0x8f0 [ 158.772945] ? unregister_pernet_operations+0x4a0/0x4a0 [ 158.775294] process_one_work+0xa1a/0x1740 [ 158.776896] ? pwq_dec_nr_in_flight+0x310/0x310 [ 158.779143] ? do_raw_spin_lock+0x11b/0x280 [ 158.780848] worker_thread+0x9e/0x1060 [ 158.782500] ? process_one_work+0x1740/0x1740 [ 158.784454] kthread+0x31b/0x420 [ 158.786082] ? __kthread_create_on_node+0x3f0/0x3f0 [ 158.788286] ret_from_fork+0x3a/0x50 [ 158.789871] ---[ end trace defd6c657c71f936 ]--- [ 158.792273] RIP: 0010:default_device_exit.cold+0x1d/0x1f [ 158.795478] Code: 84 e8 18 c9 3e fe 0f 0b e9 70 90 ff ff e8 36 e4 52 fe 89 d9 4c 89 e2 48 c7 c6 80 d6 25 84 48 c7 c7 20 c0 25 84 e8 f4 c8 3e [ 158.804854] RSP: 0018:ffff8880347e7b90 EFLAGS: 00010282 [ 158.807865] RAX: 000000000000003b RBX: 00000000ffffffef RCX: 0000000000000000 [ 158.811794] RDX: 0000000000000000 RSI: ffffffff8128013d RDI: ffffed10068fcf64 [ 158.816652] RBP: ffff888033550170 R08: 000000000000003b R09: fffffbfff0b94b9c [ 158.820930] R10: fffffbfff0b94b9b R11: ffffffff85ca5cdf R12: ffff888032f28000 [ 158.825113] R13: dffffc0000000000 R14: ffff8880335501b8 R15: 1ffff110068fcf72 [ 158.829899] FS: 0000000000000000(0000) GS:ffff888036000000(0000) knlGS:0000000000000000 [ 158.834923] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 158.838164] CR2: 00007fe8b45d21d0 CR3: 00000000340b4005 CR4: 0000000000360ef0 [ 158.841917] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 158.845149] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Fix this by checking if a device with the same name exists in init_net and fallback to original code - dev%d to allocate name - in case it does. This was found using syzkaller. Fixes: aca51397d014 ("netns: Fix arbitrary net_device-s corruptions on net_ns stop.") Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/dev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/dev.c b/net/core/dev.c index fc676b2610e3..2f341b850845 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9701,6 +9701,8 @@ static void __net_exit default_device_exit(struct net *net) /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); + if (__dev_get_by_name(&init_net, fb_name)) + snprintf(fb_name, IFNAMSIZ, "dev%%d"); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", From d66503c43c0036d8db526d6c47c149bb971ac0b9 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Sun, 28 Jul 2019 19:35:49 +0200 Subject: [PATCH 540/823] mvpp2: refactor the HW checksum setup The hardware can only offload checksum calculation on first port due to the Tx FIFO size limitation, and has a maximum L3 offset of 128 bytes. Document this in a comment and move duplicated code in a function. Fixes: 576193f2d579 ("net: mvpp2: jumbo frames support") Signed-off-by: Matteo Croce Signed-off-by: David S. Miller --- .../net/ethernet/marvell/mvpp2/mvpp2_main.c | 35 ++++++++++++------- 1 file changed, 22 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 68fa2d563f0d..e2e61a4a9000 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -811,6 +811,26 @@ static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) return 0; } +static void mvpp2_set_hw_csum(struct mvpp2_port *port, + enum mvpp2_bm_pool_log_num new_long_pool) +{ + const netdev_features_t csums = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + + /* Update L4 checksum when jumbo enable/disable on port. + * Only port 0 supports hardware checksum offload due to + * the Tx FIFO size limitation. + * Also, don't set NETIF_F_HW_CSUM because L3_offset in TX descriptor + * has 7 bits, so the maximum L3 offset is 128. + */ + if (new_long_pool == MVPP2_BM_JUMBO && port->id != 0) { + port->dev->features &= ~csums; + port->dev->hw_features &= ~csums; + } else { + port->dev->features |= csums; + port->dev->hw_features |= csums; + } +} + static int mvpp2_bm_update_mtu(struct net_device *dev, int mtu) { struct mvpp2_port *port = netdev_priv(dev); @@ -843,15 +863,7 @@ static int mvpp2_bm_update_mtu(struct net_device *dev, int mtu) /* Add port to new short & long pool */ mvpp2_swf_bm_pool_init(port); - /* Update L4 checksum when jumbo enable/disable on port */ - if (new_long_pool == MVPP2_BM_JUMBO && port->id != 0) { - dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - dev->hw_features &= ~(NETIF_F_IP_CSUM | - NETIF_F_IPV6_CSUM); - } else { - dev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; - dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; - } + mvpp2_set_hw_csum(port, new_long_pool); } dev->mtu = mtu; @@ -5193,10 +5205,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, dev->features |= NETIF_F_NTUPLE; } - if (port->pool_long->id == MVPP2_BM_JUMBO && port->id != 0) { - dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - dev->hw_features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - } + mvpp2_set_hw_csum(port, port->pool_long->id); dev->vlan_features |= features; dev->gso_max_segs = MVPP2_MAX_TSO_SEGS; From 6f315c42d4120303d4cd6520f67889ff7f42736e Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Sun, 28 Jul 2019 19:30:09 -0500 Subject: [PATCH 541/823] net: ehea: Mark expected switch fall-through Mark switch cases where we are expecting to fall through. This patch fixes the following warning: drivers/net/ethernet/ibm/ehea/ehea_main.c: In function 'ehea_mem_notifier': include/linux/printk.h:311:2: warning: this statement may fall through [-Wimplicit-fallthrough=] printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/net/ethernet/ibm/ehea/ehea_main.c:3253:3: note: in expansion of macro 'pr_info' pr_info("memory offlining canceled"); ^~~~~~~ drivers/net/ethernet/ibm/ehea/ehea_main.c:3256:2: note: here case MEM_ONLINE: ^~~~ Notice that, in this particular case, the code comment is modified in accordance with what GCC is expecting to find. Reported-by: Stephen Rothwell Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ehea/ehea_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index 4138a8480347..cca71ba7a74a 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -3251,7 +3251,7 @@ static int ehea_mem_notifier(struct notifier_block *nb, switch (action) { case MEM_CANCEL_OFFLINE: pr_info("memory offlining canceled"); - /* Fall through: re-add canceled memory block */ + /* Fall through - re-add canceled memory block */ case MEM_ONLINE: pr_info("memory is going online"); From 52023a53993061b524f6ba1de68858c472f52aad Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Sun, 28 Jul 2019 19:32:51 -0500 Subject: [PATCH 542/823] net: spider_net: Mark expected switch fall-through Mark switch cases where we are expecting to fall through. This patch fixes the following warning: drivers/net/ethernet/toshiba/spider_net.c: In function 'spider_net_release_tx_chain': drivers/net/ethernet/toshiba/spider_net.c:783:7: warning: this statement may fall through [-Wimplicit-fallthrough=] if (!brutal) { ^ drivers/net/ethernet/toshiba/spider_net.c:792:3: note: here case SPIDER_NET_DESCR_RESPONSE_ERROR: ^~~~ Notice that, in this particular case, the code comment is modified in accordance with what GCC is expecting to find. Reported-by: Stephen Rothwell Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/toshiba/spider_net.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c index 5b196ebfed49..0f346761a2b2 100644 --- a/drivers/net/ethernet/toshiba/spider_net.c +++ b/drivers/net/ethernet/toshiba/spider_net.c @@ -788,6 +788,7 @@ spider_net_release_tx_chain(struct spider_net_card *card, int brutal) /* fallthrough, if we release the descriptors * brutally (then we don't care about * SPIDER_NET_DESCR_CARDOWNED) */ + /* Fall through */ case SPIDER_NET_DESCR_RESPONSE_ERROR: case SPIDER_NET_DESCR_PROTECTION_ERROR: From b89d15480d0cacacae1a0fe0b3da01b529f2914f Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Mon, 24 Jun 2019 15:20:11 +0200 Subject: [PATCH 543/823] netfilter: ipset: Actually allow destination MAC address for hash:ip,mac sets too In commit 8cc4ccf58379 ("ipset: Allow matching on destination MAC address for mac and ipmac sets"), ipset.git commit 1543514c46a7, I removed the KADT check that prevents matching on destination MAC addresses for hash:mac sets, but forgot to remove the same check for hash:ip,mac set. Drop this check: functionality is now commented in man pages and there's no reason to restrict to source MAC address matching anymore. Reported-by: Chen Yi Fixes: 8cc4ccf58379 ("ipset: Allow matching on destination MAC address for mac and ipmac sets") Signed-off-by: Stefano Brivio Signed-off-by: Jozsef Kadlecsik --- net/netfilter/ipset/ip_set_hash_ipmac.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c index faf59b6a998f..eb1443408320 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmac.c +++ b/net/netfilter/ipset/ip_set_hash_ipmac.c @@ -89,10 +89,6 @@ hash_ipmac4_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_ipmac4_elem e = { .ip = 0, { .foo[0] = 0, .foo[1] = 0 } }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - /* MAC can be src only */ - if (!(opt->flags & IPSET_DIM_TWO_SRC)) - return 0; - if (skb_mac_header(skb) < skb->head || (skb_mac_header(skb) + ETH_HLEN) > skb->data) return -EINVAL; From 1b4a75108d5bc153daf965d334e77e8e94534f96 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Mon, 24 Jun 2019 15:20:12 +0200 Subject: [PATCH 544/823] netfilter: ipset: Copy the right MAC address in bitmap:ip,mac and hash:ip,mac sets In commit 8cc4ccf58379 ("ipset: Allow matching on destination MAC address for mac and ipmac sets"), ipset.git commit 1543514c46a7, I added to the KADT functions for sets matching on MAC addreses the copy of source or destination MAC address depending on the configured match. This was done correctly for hash:mac, but for hash:ip,mac and bitmap:ip,mac, copying and pasting the same code block presents an obvious problem: in these two set types, the MAC address is the second dimension, not the first one, and we are actually selecting the MAC address depending on whether the first dimension (IP address) specifies source or destination. Fix this by checking for the IPSET_DIM_TWO_SRC flag in option flags. This way, mixing source and destination matches for the two dimensions of ip,mac set types works as expected. With this setup: ip netns add A ip link add veth1 type veth peer name veth2 netns A ip addr add 192.0.2.1/24 dev veth1 ip -net A addr add 192.0.2.2/24 dev veth2 ip link set veth1 up ip -net A link set veth2 up dst=$(ip netns exec A cat /sys/class/net/veth2/address) ip netns exec A ipset create test_bitmap bitmap:ip,mac range 192.0.0.0/16 ip netns exec A ipset add test_bitmap 192.0.2.1,${dst} ip netns exec A iptables -A INPUT -m set ! --match-set test_bitmap src,dst -j DROP ip netns exec A ipset create test_hash hash:ip,mac ip netns exec A ipset add test_hash 192.0.2.1,${dst} ip netns exec A iptables -A INPUT -m set ! --match-set test_hash src,dst -j DROP ipset correctly matches a test packet: # ping -c1 192.0.2.2 >/dev/null # echo $? 0 Reported-by: Chen Yi Fixes: 8cc4ccf58379 ("ipset: Allow matching on destination MAC address for mac and ipmac sets") Signed-off-by: Stefano Brivio Signed-off-by: Jozsef Kadlecsik --- net/netfilter/ipset/ip_set_bitmap_ipmac.c | 2 +- net/netfilter/ipset/ip_set_hash_ipmac.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index ca7ac4a25ada..1d4e63326e68 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -226,7 +226,7 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, e.id = ip_to_id(map, ip); - if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c index eb1443408320..24d8f4df4230 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmac.c +++ b/net/netfilter/ipset/ip_set_hash_ipmac.c @@ -93,7 +93,7 @@ hash_ipmac4_kadt(struct ip_set *set, const struct sk_buff *skb, (skb_mac_header(skb) + ETH_HLEN) > skb->data) return -EINVAL; - if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); From 6c1f7e2c1b96ab9b09ac97c4df2bd9dc327206f6 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Tue, 23 Jul 2019 10:25:55 +0200 Subject: [PATCH 545/823] netfilter: ipset: Fix rename concurrency with listing Shijie Luo reported that when stress-testing ipset with multiple concurrent create, rename, flush, list, destroy commands, it can result ipset : Broken LIST kernel message: missing DATA part! error messages and broken list results. The problem was the rename operation was not properly handled with respect of listing. The patch fixes the issue. Reported-by: Shijie Luo Signed-off-by: Jozsef Kadlecsik --- net/netfilter/ipset/ip_set_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 2e151856ad99..e64d5f9a89dd 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1161,7 +1161,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, return -ENOENT; write_lock_bh(&ip_set_ref_lock); - if (set->ref != 0) { + if (set->ref != 0 || set->ref_netlink != 0) { ret = -IPSET_ERR_REFERENCED; goto out; } From c6b36bdd04b5c22b2705f7ae561d4f3b4d8a0ac3 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Mon, 29 Jul 2019 18:26:14 +0000 Subject: [PATCH 546/823] mlxsw: spectrum_ptp: Increase parsing depth when PTP is enabled Spectrum systems have a configurable limit on how far into the packet they parse. By default, the limit is 96 bytes. An IPv6 PTP packet is layered as Ethernet/IPv6/UDP (14+40+8 bytes), and sequence ID of a PTP event is only available 32 bytes into payload, for a total of 94 bytes. When an additional 802.1q header is present as well (such as when ptp4l is running on a VLAN port), the parsing limit is exceeded. Such packets are not recognized as PTP, and are not timestamped. Therefore generalize the current VXLAN-specific parsing depth setting to allow reference-counted requests from other modules as well. Keep it in the VXLAN module, because the MPRS register also configures UDP destination port number used for VXLAN, and is thus closely tied to the VXLAN code anyway. Then invoke the new interfaces from both VXLAN (in obvious places), as well as from PTP code, when the (global) timestamping configuration changes from disabled to enabled or vice versa. Fixes: 8748642751ed ("mlxsw: spectrum: PTP: Support SIOCGHWTSTAMP, SIOCSHWTSTAMP ioctls") Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.h | 4 + .../ethernet/mellanox/mlxsw/spectrum_nve.c | 1 + .../ethernet/mellanox/mlxsw/spectrum_nve.h | 1 + .../mellanox/mlxsw/spectrum_nve_vxlan.c | 76 ++++++++++++++----- .../ethernet/mellanox/mlxsw/spectrum_ptp.c | 17 +++++ 5 files changed, 82 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 131f62ce9297..6664119fb0c8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -951,4 +951,8 @@ void mlxsw_sp_port_nve_fini(struct mlxsw_sp_port *mlxsw_sp_port); int mlxsw_sp_nve_init(struct mlxsw_sp *mlxsw_sp); void mlxsw_sp_nve_fini(struct mlxsw_sp *mlxsw_sp); +/* spectrum_nve_vxlan.c */ +int mlxsw_sp_nve_inc_parsing_depth_get(struct mlxsw_sp *mlxsw_sp); +void mlxsw_sp_nve_inc_parsing_depth_put(struct mlxsw_sp *mlxsw_sp); + #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c index 1df164a4b06d..17f334b46c40 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c @@ -775,6 +775,7 @@ static void mlxsw_sp_nve_tunnel_fini(struct mlxsw_sp *mlxsw_sp) ops->fini(nve); mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, nve->tunnel_index); + memset(&nve->config, 0, sizeof(nve->config)); } nve->num_nve_tunnels--; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h index 0035640156a1..12f664f42f21 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h @@ -29,6 +29,7 @@ struct mlxsw_sp_nve { unsigned int num_max_mc_entries[MLXSW_SP_L3_PROTO_MAX]; u32 tunnel_index; u16 ul_rif_index; /* Reserved for Spectrum */ + unsigned int inc_parsing_depth_refs; }; struct mlxsw_sp_nve_ops { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c index 93ccd9fc2266..05517c7feaa5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c @@ -103,9 +103,9 @@ static void mlxsw_sp_nve_vxlan_config(const struct mlxsw_sp_nve *nve, config->udp_dport = cfg->dst_port; } -static int mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp, - unsigned int parsing_depth, - __be16 udp_dport) +static int __mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp, + unsigned int parsing_depth, + __be16 udp_dport) { char mprs_pl[MLXSW_REG_MPRS_LEN]; @@ -113,6 +113,56 @@ static int mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mprs), mprs_pl); } +static int mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp, + __be16 udp_dport) +{ + int parsing_depth = mlxsw_sp->nve->inc_parsing_depth_refs ? + MLXSW_SP_NVE_VXLAN_PARSING_DEPTH : + MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH; + + return __mlxsw_sp_nve_parsing_set(mlxsw_sp, parsing_depth, udp_dport); +} + +static int +__mlxsw_sp_nve_inc_parsing_depth_get(struct mlxsw_sp *mlxsw_sp, + __be16 udp_dport) +{ + int err; + + mlxsw_sp->nve->inc_parsing_depth_refs++; + + err = mlxsw_sp_nve_parsing_set(mlxsw_sp, udp_dport); + if (err) + goto err_nve_parsing_set; + return 0; + +err_nve_parsing_set: + mlxsw_sp->nve->inc_parsing_depth_refs--; + return err; +} + +static void +__mlxsw_sp_nve_inc_parsing_depth_put(struct mlxsw_sp *mlxsw_sp, + __be16 udp_dport) +{ + mlxsw_sp->nve->inc_parsing_depth_refs--; + mlxsw_sp_nve_parsing_set(mlxsw_sp, udp_dport); +} + +int mlxsw_sp_nve_inc_parsing_depth_get(struct mlxsw_sp *mlxsw_sp) +{ + __be16 udp_dport = mlxsw_sp->nve->config.udp_dport; + + return __mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp, udp_dport); +} + +void mlxsw_sp_nve_inc_parsing_depth_put(struct mlxsw_sp *mlxsw_sp) +{ + __be16 udp_dport = mlxsw_sp->nve->config.udp_dport; + + __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, udp_dport); +} + static void mlxsw_sp_nve_vxlan_config_prepare(char *tngcr_pl, const struct mlxsw_sp_nve_config *config) @@ -176,9 +226,7 @@ static int mlxsw_sp1_nve_vxlan_init(struct mlxsw_sp_nve *nve, struct mlxsw_sp *mlxsw_sp = nve->mlxsw_sp; int err; - err = mlxsw_sp_nve_parsing_set(mlxsw_sp, - MLXSW_SP_NVE_VXLAN_PARSING_DEPTH, - config->udp_dport); + err = __mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp, config->udp_dport); if (err) return err; @@ -203,8 +251,7 @@ err_promote_decap: err_rtdp_set: mlxsw_sp1_nve_vxlan_config_clear(mlxsw_sp); err_config_set: - mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH, - config->udp_dport); + __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0); return err; } @@ -216,8 +263,7 @@ static void mlxsw_sp1_nve_vxlan_fini(struct mlxsw_sp_nve *nve) mlxsw_sp_router_nve_demote_decap(mlxsw_sp, config->ul_tb_id, config->ul_proto, &config->ul_sip); mlxsw_sp1_nve_vxlan_config_clear(mlxsw_sp); - mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH, - config->udp_dport); + __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0); } static int @@ -320,9 +366,7 @@ static int mlxsw_sp2_nve_vxlan_init(struct mlxsw_sp_nve *nve, struct mlxsw_sp *mlxsw_sp = nve->mlxsw_sp; int err; - err = mlxsw_sp_nve_parsing_set(mlxsw_sp, - MLXSW_SP_NVE_VXLAN_PARSING_DEPTH, - config->udp_dport); + err = __mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp, config->udp_dport); if (err) return err; @@ -348,8 +392,7 @@ err_promote_decap: err_rtdp_set: mlxsw_sp2_nve_vxlan_config_clear(mlxsw_sp); err_config_set: - mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH, - config->udp_dport); + __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0); return err; } @@ -361,8 +404,7 @@ static void mlxsw_sp2_nve_vxlan_fini(struct mlxsw_sp_nve *nve) mlxsw_sp_router_nve_demote_decap(mlxsw_sp, config->ul_tb_id, config->ul_proto, &config->ul_sip); mlxsw_sp2_nve_vxlan_config_clear(mlxsw_sp); - mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH, - config->udp_dport); + __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0); } const struct mlxsw_sp_nve_ops mlxsw_sp2_nve_vxlan_ops = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index bd9c2bc2d5d6..98c5ba3200bc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -979,6 +979,9 @@ static int mlxsw_sp1_ptp_mtpppc_update(struct mlxsw_sp_port *mlxsw_sp_port, { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_port *tmp; + u16 orig_ing_types = 0; + u16 orig_egr_types = 0; + int err; int i; /* MTPPPC configures timestamping globally, not per port. Find the @@ -986,12 +989,26 @@ static int mlxsw_sp1_ptp_mtpppc_update(struct mlxsw_sp_port *mlxsw_sp_port, */ for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++) { tmp = mlxsw_sp->ports[i]; + if (tmp) { + orig_ing_types |= tmp->ptp.ing_types; + orig_egr_types |= tmp->ptp.egr_types; + } if (tmp && tmp != mlxsw_sp_port) { ing_types |= tmp->ptp.ing_types; egr_types |= tmp->ptp.egr_types; } } + if ((ing_types || egr_types) && !(orig_egr_types || orig_egr_types)) { + err = mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp); + if (err) { + netdev_err(mlxsw_sp_port->dev, "Failed to increase parsing depth"); + return err; + } + } + if (!(ing_types || egr_types) && (orig_egr_types || orig_egr_types)) + mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp); + return mlxsw_sp1_ptp_mtpppc_set(mlxsw_sp_port->mlxsw_sp, ing_types, egr_types); } From d4e575ba9fcc04d10c0a2e555a5b32fa3a8a19d3 Mon Sep 17 00:00:00 2001 From: Enrico Weigelt Date: Mon, 29 Jul 2019 20:55:21 +0200 Subject: [PATCH 547/823] net: sctp: drop unneeded likely() call around IS_ERR() IS_ERR() already calls unlikely(), so this extra unlikely() call around IS_ERR() is not needed. Signed-off-by: Enrico Weigelt Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/socket.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index aa80cda36581..9d1f83b10c0a 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -985,7 +985,7 @@ static int sctp_setsockopt_bindx(struct sock *sk, return -EINVAL; kaddrs = memdup_user(addrs, addrs_size); - if (unlikely(IS_ERR(kaddrs))) + if (IS_ERR(kaddrs)) return PTR_ERR(kaddrs); /* Walk through the addrs buffer and count the number of addresses. */ @@ -1315,7 +1315,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk, return -EINVAL; kaddrs = memdup_user(addrs, addrs_size); - if (unlikely(IS_ERR(kaddrs))) + if (IS_ERR(kaddrs)) return PTR_ERR(kaddrs); /* Allow security module to validate connectx addresses. */ From 0bc10ad3a42a1c8ef2cef6e158cc40b87c46352d Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 29 Jul 2019 15:01:39 -0500 Subject: [PATCH 548/823] net: wan: sdla: Mark expected switch fall-through MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Mark switch cases where we are expecting to fall through. This patch fixes the following warning (Building: i386): drivers/net/wan/sdla.c: In function ‘sdla_errors’: drivers/net/wan/sdla.c:414:7: warning: this statement may fall through [-Wimplicit-fallthrough=] if (cmd == SDLA_INFORMATION_WRITE) ^ drivers/net/wan/sdla.c:417:3: note: here default: ^~~~~~~ Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- drivers/net/wan/sdla.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wan/sdla.c b/drivers/net/wan/sdla.c index a9ac3f37b904..e2e679a01b65 100644 --- a/drivers/net/wan/sdla.c +++ b/drivers/net/wan/sdla.c @@ -413,6 +413,7 @@ static void sdla_errors(struct net_device *dev, int cmd, int dlci, int ret, int case SDLA_RET_NO_BUFS: if (cmd == SDLA_INFORMATION_WRITE) break; + /* Else, fall through */ default: netdev_dbg(dev, "Cmd 0x%02X generated return code 0x%02X\n", From 7bd6ba4ef4b29db7464da496963081f5fdc88300 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 29 Jul 2019 15:12:31 -0500 Subject: [PATCH 549/823] net: hamradio: baycom_epp: Mark expected switch fall-through MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Mark switch cases where we are expecting to fall through. This patch fixes the following warning (Building: i386): drivers/net/hamradio/baycom_epp.c: In function ‘transmit’: drivers/net/hamradio/baycom_epp.c:491:7: warning: this statement may fall through [-Wimplicit-fallthrough=] if (i) { ^ drivers/net/hamradio/baycom_epp.c:504:3: note: here default: /* fall through */ ^~~~~~~ Notice that, in this particular case, the code comment is modified in accordance with what GCC is expecting to find. Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- drivers/net/hamradio/baycom_epp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index daab2c07d891..9303aeb2595f 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -500,8 +500,9 @@ static int transmit(struct baycom_state *bc, int cnt, unsigned char stat) } break; } + /* fall through */ - default: /* fall through */ + default: if (bc->hdlctx.calibrate <= 0) return 0; i = min_t(int, cnt, bc->hdlctx.calibrate); From 7be21763f703d0f7e878283ec31e52b225097449 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 29 Jul 2019 16:10:53 -0500 Subject: [PATCH 550/823] ataflop: Mark expected switch fall-through MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Mark switch cases where we are expecting to fall through. This patch fixes the following warning (Building: m68k): drivers/block/ataflop.c: In function ‘fd_locked_ioctl’: drivers/block/ataflop.c:1728:3: warning: this statement may fall through [-Wimplicit-fallthrough=] set_capacity(floppy->disk, MAX_DISK_SIZE * 2); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/block/ataflop.c:1729:2: note: here case FDFMTEND: ^~~~ Signed-off-by: Gustavo A. R. Silva Signed-off-by: Jens Axboe --- drivers/block/ataflop.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index 85f20e371f2f..bd7d3bb8b890 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -1726,6 +1726,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, /* MSch: invalidate default_params */ default_params[drive].blocks = 0; set_capacity(floppy->disk, MAX_DISK_SIZE * 2); + /* Fall through */ case FDFMTEND: case FDFLUSH: /* invalidate the buffer track to force a reread */ From 71d6c505b4d9e6f76586350450e785e3d452b346 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 29 Jul 2019 14:47:22 -0700 Subject: [PATCH 551/823] libata: zpodd: Fix small read overflow in zpodd_get_mech_type() Jeffrin reported a KASAN issue: BUG: KASAN: global-out-of-bounds in ata_exec_internal_sg+0x50f/0xc70 Read of size 16 at addr ffffffff91f41f80 by task scsi_eh_1/149 ... The buggy address belongs to the variable: cdb.48319+0x0/0x40 Much like commit 18c9a99bce2a ("libata: zpodd: small read overflow in eject_tray()"), this fixes a cdb[] buffer length, this time in zpodd_get_mech_type(): We read from the cdb[] buffer in ata_exec_internal_sg(). It has to be ATAPI_CDB_LEN (16) bytes long, but this buffer is only 12 bytes. Reported-by: Jeffrin Jose T Fixes: afe759511808c ("libata: identify and init ZPODD devices") Link: https://lore.kernel.org/lkml/201907181423.E808958@keescook/ Tested-by: Jeffrin Jose T Reviewed-by: Nick Desaulniers Signed-off-by: Kees Cook Signed-off-by: Jens Axboe --- drivers/ata/libata-zpodd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/libata-zpodd.c b/drivers/ata/libata-zpodd.c index 173e6f2dd9af..eefda51f97d3 100644 --- a/drivers/ata/libata-zpodd.c +++ b/drivers/ata/libata-zpodd.c @@ -56,7 +56,7 @@ static enum odd_mech_type zpodd_get_mech_type(struct ata_device *dev) unsigned int ret; struct rm_feature_desc *desc; struct ata_taskfile tf; - static const char cdb[] = { GPCMD_GET_CONFIGURATION, + static const char cdb[ATAPI_CDB_LEN] = { GPCMD_GET_CONFIGURATION, 2, /* only 1 feature descriptor requested */ 0, 3, /* 3, removable medium feature */ 0, 0, 0,/* reserved */ From a20961cc9493be46b5c4f565b925284a90c7864c Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 29 Jul 2019 17:10:16 -0500 Subject: [PATCH 552/823] net: smc911x: Mark expected switch fall-through MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Mark switch cases where we are expecting to fall through. This patch fixes the following warning (Building: arm): drivers/net/ethernet/smsc/smc911x.c: In function ‘smc911x_phy_detect’: drivers/net/ethernet/smsc/smc911x.c:677:7: warning: this statement may fall through [-Wimplicit-fallthrough=] if (cfg & HW_CFG_EXT_PHY_DET_) { ^ drivers/net/ethernet/smsc/smc911x.c:715:3: note: here default: ^~~~~~~ Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- drivers/net/ethernet/smsc/smc911x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c index bd14803545de..8d88e4083456 100644 --- a/drivers/net/ethernet/smsc/smc911x.c +++ b/drivers/net/ethernet/smsc/smc911x.c @@ -712,6 +712,7 @@ static void smc911x_phy_detect(struct net_device *dev) /* Found an external PHY */ break; } + /* Else, fall through */ default: /* Internal media only */ SMC_GET_PHY_ID1(lp, 1, id1); From f3e4ff28b8685d856f381ee6bcf88b6149a6db5b Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 24 Jul 2019 11:00:54 +0200 Subject: [PATCH 553/823] scsi: libfc: Whitespace cleanup in libfc.h No functional change. [mkp: typo] Signed-off-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- include/scsi/libfc.h | 52 ++++++++++++++++++++++---------------------- 1 file changed, 26 insertions(+), 26 deletions(-) diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h index 2d64b53f947c..9b87e1a1c646 100644 --- a/include/scsi/libfc.h +++ b/include/scsi/libfc.h @@ -115,7 +115,7 @@ struct fc_disc_port { struct fc_lport *lp; struct list_head peers; struct work_struct rport_work; - u32 port_id; + u32 port_id; }; /** @@ -155,14 +155,14 @@ struct fc_rport_operations { */ struct fc_rport_libfc_priv { struct fc_lport *local_port; - enum fc_rport_state rp_state; + enum fc_rport_state rp_state; u16 flags; #define FC_RP_FLAGS_REC_SUPPORTED (1 << 0) #define FC_RP_FLAGS_RETRY (1 << 1) #define FC_RP_STARTED (1 << 2) #define FC_RP_FLAGS_CONF_REQ (1 << 3) - unsigned int e_d_tov; - unsigned int r_a_tov; + unsigned int e_d_tov; + unsigned int r_a_tov; }; /** @@ -191,24 +191,24 @@ struct fc_rport_priv { struct fc_lport *local_port; struct fc_rport *rport; struct kref kref; - enum fc_rport_state rp_state; + enum fc_rport_state rp_state; struct fc_rport_identifiers ids; u16 flags; - u16 max_seq; + u16 max_seq; u16 disc_id; u16 maxframe_size; - unsigned int retries; - unsigned int major_retries; - unsigned int e_d_tov; - unsigned int r_a_tov; - struct mutex rp_mutex; + unsigned int retries; + unsigned int major_retries; + unsigned int e_d_tov; + unsigned int r_a_tov; + struct mutex rp_mutex; struct delayed_work retry_work; - enum fc_rport_event event; + enum fc_rport_event event; struct fc_rport_operations *ops; - struct list_head peers; - struct work_struct event_work; + struct list_head peers; + struct work_struct event_work; u32 supported_classes; - u16 prli_count; + u16 prli_count; struct rcu_head rcu; u16 sp_features; u8 spp_type; @@ -618,12 +618,12 @@ struct libfc_function_template { * @disc_callback: Callback routine called when discovery completes */ struct fc_disc { - unsigned char retry_count; - unsigned char pending; - unsigned char requested; - unsigned short seq_count; - unsigned char buf_len; - u16 disc_id; + unsigned char retry_count; + unsigned char pending; + unsigned char requested; + unsigned short seq_count; + unsigned char buf_len; + u16 disc_id; struct list_head rports; void *priv; @@ -697,7 +697,7 @@ struct fc_lport { struct fc_rport_priv *ms_rdata; struct fc_rport_priv *ptp_rdata; void *scsi_priv; - struct fc_disc disc; + struct fc_disc disc; /* Virtual port information */ struct list_head vports; @@ -715,7 +715,7 @@ struct fc_lport { u8 retry_count; /* Fabric information */ - u32 port_id; + u32 port_id; u64 wwpn; u64 wwnn; unsigned int service_params; @@ -743,11 +743,11 @@ struct fc_lport { struct fc_ns_fts fcts; /* Miscellaneous */ - struct mutex lp_mutex; - struct list_head list; + struct mutex lp_mutex; + struct list_head list; struct delayed_work retry_work; void *prov[FC_FC4_PROV_SIZE]; - struct list_head lport_list; + struct list_head lport_list; }; /** From 023358b136d490ca91735ac6490db3741af5a8bd Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 24 Jul 2019 11:00:55 +0200 Subject: [PATCH 554/823] scsi: fcoe: Embed fc_rport_priv in fcoe_rport structure Gcc-9 complains for a memset across pointer boundaries, which happens as the code tries to allocate a flexible array on the stack. Turns out we cannot do this without relying on gcc-isms, so with this patch we'll embed the fc_rport_priv structure into fcoe_rport, can use the normal 'container_of' outcast, and will only have to do a memset over one structure. Signed-off-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/scsi/fcoe/fcoe_ctlr.c | 51 ++++++++++++++--------------------- drivers/scsi/libfc/fc_rport.c | 5 +++- include/scsi/libfcoe.h | 1 + 3 files changed, 25 insertions(+), 32 deletions(-) diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index 1a85fe9e4b7b..fc32b5d76821 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -2005,7 +2005,7 @@ EXPORT_SYMBOL_GPL(fcoe_wwn_from_mac); */ static inline struct fcoe_rport *fcoe_ctlr_rport(struct fc_rport_priv *rdata) { - return (struct fcoe_rport *)(rdata + 1); + return container_of(rdata, struct fcoe_rport, rdata); } /** @@ -2269,7 +2269,7 @@ static void fcoe_ctlr_vn_start(struct fcoe_ctlr *fip) */ static int fcoe_ctlr_vn_parse(struct fcoe_ctlr *fip, struct sk_buff *skb, - struct fc_rport_priv *rdata) + struct fcoe_rport *frport) { struct fip_header *fiph; struct fip_desc *desc = NULL; @@ -2277,16 +2277,12 @@ static int fcoe_ctlr_vn_parse(struct fcoe_ctlr *fip, struct fip_wwn_desc *wwn = NULL; struct fip_vn_desc *vn = NULL; struct fip_size_desc *size = NULL; - struct fcoe_rport *frport; size_t rlen; size_t dlen; u32 desc_mask = 0; u32 dtype; u8 sub; - memset(rdata, 0, sizeof(*rdata) + sizeof(*frport)); - frport = fcoe_ctlr_rport(rdata); - fiph = (struct fip_header *)skb->data; frport->flags = ntohs(fiph->fip_flags); @@ -2349,15 +2345,17 @@ static int fcoe_ctlr_vn_parse(struct fcoe_ctlr *fip, if (dlen != sizeof(struct fip_wwn_desc)) goto len_err; wwn = (struct fip_wwn_desc *)desc; - rdata->ids.node_name = get_unaligned_be64(&wwn->fd_wwn); + frport->rdata.ids.node_name = + get_unaligned_be64(&wwn->fd_wwn); break; case FIP_DT_VN_ID: if (dlen != sizeof(struct fip_vn_desc)) goto len_err; vn = (struct fip_vn_desc *)desc; memcpy(frport->vn_mac, vn->fd_mac, ETH_ALEN); - rdata->ids.port_id = ntoh24(vn->fd_fc_id); - rdata->ids.port_name = get_unaligned_be64(&vn->fd_wwpn); + frport->rdata.ids.port_id = ntoh24(vn->fd_fc_id); + frport->rdata.ids.port_name = + get_unaligned_be64(&vn->fd_wwpn); break; case FIP_DT_FC4F: if (dlen != sizeof(struct fip_fc4_feat)) @@ -2738,10 +2736,7 @@ static int fcoe_ctlr_vn_recv(struct fcoe_ctlr *fip, struct sk_buff *skb) { struct fip_header *fiph; enum fip_vn2vn_subcode sub; - struct { - struct fc_rport_priv rdata; - struct fcoe_rport frport; - } buf; + struct fcoe_rport frport = { }; int rc, vlan_id = 0; fiph = (struct fip_header *)skb->data; @@ -2757,7 +2752,7 @@ static int fcoe_ctlr_vn_recv(struct fcoe_ctlr *fip, struct sk_buff *skb) goto drop; } - rc = fcoe_ctlr_vn_parse(fip, skb, &buf.rdata); + rc = fcoe_ctlr_vn_parse(fip, skb, &frport); if (rc) { LIBFCOE_FIP_DBG(fip, "vn_recv vn_parse error %d\n", rc); goto drop; @@ -2766,19 +2761,19 @@ static int fcoe_ctlr_vn_recv(struct fcoe_ctlr *fip, struct sk_buff *skb) mutex_lock(&fip->ctlr_mutex); switch (sub) { case FIP_SC_VN_PROBE_REQ: - fcoe_ctlr_vn_probe_req(fip, &buf.rdata); + fcoe_ctlr_vn_probe_req(fip, &frport.rdata); break; case FIP_SC_VN_PROBE_REP: - fcoe_ctlr_vn_probe_reply(fip, &buf.rdata); + fcoe_ctlr_vn_probe_reply(fip, &frport.rdata); break; case FIP_SC_VN_CLAIM_NOTIFY: - fcoe_ctlr_vn_claim_notify(fip, &buf.rdata); + fcoe_ctlr_vn_claim_notify(fip, &frport.rdata); break; case FIP_SC_VN_CLAIM_REP: - fcoe_ctlr_vn_claim_resp(fip, &buf.rdata); + fcoe_ctlr_vn_claim_resp(fip, &frport.rdata); break; case FIP_SC_VN_BEACON: - fcoe_ctlr_vn_beacon(fip, &buf.rdata); + fcoe_ctlr_vn_beacon(fip, &frport.rdata); break; default: LIBFCOE_FIP_DBG(fip, "vn_recv unknown subcode %d\n", sub); @@ -2802,22 +2797,18 @@ drop: */ static int fcoe_ctlr_vlan_parse(struct fcoe_ctlr *fip, struct sk_buff *skb, - struct fc_rport_priv *rdata) + struct fcoe_rport *frport) { struct fip_header *fiph; struct fip_desc *desc = NULL; struct fip_mac_desc *macd = NULL; struct fip_wwn_desc *wwn = NULL; - struct fcoe_rport *frport; size_t rlen; size_t dlen; u32 desc_mask = 0; u32 dtype; u8 sub; - memset(rdata, 0, sizeof(*rdata) + sizeof(*frport)); - frport = fcoe_ctlr_rport(rdata); - fiph = (struct fip_header *)skb->data; frport->flags = ntohs(fiph->fip_flags); @@ -2871,7 +2862,8 @@ static int fcoe_ctlr_vlan_parse(struct fcoe_ctlr *fip, if (dlen != sizeof(struct fip_wwn_desc)) goto len_err; wwn = (struct fip_wwn_desc *)desc; - rdata->ids.node_name = get_unaligned_be64(&wwn->fd_wwn); + frport->rdata.ids.node_name = + get_unaligned_be64(&wwn->fd_wwn); break; default: LIBFCOE_FIP_DBG(fip, "unexpected descriptor type %x " @@ -2982,22 +2974,19 @@ static int fcoe_ctlr_vlan_recv(struct fcoe_ctlr *fip, struct sk_buff *skb) { struct fip_header *fiph; enum fip_vlan_subcode sub; - struct { - struct fc_rport_priv rdata; - struct fcoe_rport frport; - } buf; + struct fcoe_rport frport = { }; int rc; fiph = (struct fip_header *)skb->data; sub = fiph->fip_subcode; - rc = fcoe_ctlr_vlan_parse(fip, skb, &buf.rdata); + rc = fcoe_ctlr_vlan_parse(fip, skb, &frport); if (rc) { LIBFCOE_FIP_DBG(fip, "vlan_recv vlan_parse error %d\n", rc); goto drop; } mutex_lock(&fip->ctlr_mutex); if (sub == FIP_SC_VL_REQ) - fcoe_ctlr_vlan_disc_reply(fip, &buf.rdata); + fcoe_ctlr_vlan_disc_reply(fip, &frport.rdata); mutex_unlock(&fip->ctlr_mutex); drop: diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index e0f3852fdad1..da6e97d8dc3b 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -128,6 +128,7 @@ EXPORT_SYMBOL(fc_rport_lookup); struct fc_rport_priv *fc_rport_create(struct fc_lport *lport, u32 port_id) { struct fc_rport_priv *rdata; + size_t rport_priv_size = sizeof(*rdata); lockdep_assert_held(&lport->disc.disc_mutex); @@ -135,7 +136,9 @@ struct fc_rport_priv *fc_rport_create(struct fc_lport *lport, u32 port_id) if (rdata) return rdata; - rdata = kzalloc(sizeof(*rdata) + lport->rport_priv_size, GFP_KERNEL); + if (lport->rport_priv_size > 0) + rport_priv_size = lport->rport_priv_size; + rdata = kzalloc(rport_priv_size, GFP_KERNEL); if (!rdata) return NULL; diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h index dc14b52577f7..2568cb0627ec 100644 --- a/include/scsi/libfcoe.h +++ b/include/scsi/libfcoe.h @@ -229,6 +229,7 @@ struct fcoe_fcf { * @vn_mac: VN_Node assigned MAC address for data */ struct fcoe_rport { + struct fc_rport_priv rdata; unsigned long time; u16 fcoe_len; u16 flags; From d478418703d6bcdd163d5d8127683c6c471539f0 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 24 Jul 2019 11:00:56 +0200 Subject: [PATCH 555/823] scsi: fcoe: pass in fcoe_rport structure instead of fc_rport_priv Instead of using the generic 'fc_rport_priv' structure as argument and then having to painstakingly outcast this to fcoe_rport we should be passing the fcoe_rport structure itself and reduce complexity. Signed-off-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/scsi/fcoe/fcoe_ctlr.c | 99 ++++++++++++++++++----------------- 1 file changed, 51 insertions(+), 48 deletions(-) diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index fc32b5d76821..1791a393795d 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -2401,16 +2401,14 @@ static void fcoe_ctlr_vn_send_claim(struct fcoe_ctlr *fip) /** * fcoe_ctlr_vn_probe_req() - handle incoming VN2VN probe request. * @fip: The FCoE controller - * @rdata: parsed remote port with frport from the probe request + * @frport: parsed FCoE rport from the probe request * * Called with ctlr_mutex held. */ static void fcoe_ctlr_vn_probe_req(struct fcoe_ctlr *fip, - struct fc_rport_priv *rdata) + struct fcoe_rport *frport) { - struct fcoe_rport *frport = fcoe_ctlr_rport(rdata); - - if (rdata->ids.port_id != fip->port_id) + if (frport->rdata.ids.port_id != fip->port_id) return; switch (fip->state) { @@ -2430,7 +2428,7 @@ static void fcoe_ctlr_vn_probe_req(struct fcoe_ctlr *fip, * Probe's REC bit is not set. * If we don't reply, we will change our address. */ - if (fip->lp->wwpn > rdata->ids.port_name && + if (fip->lp->wwpn > frport->rdata.ids.port_name && !(frport->flags & FIP_FL_REC_OR_P2P)) { LIBFCOE_FIP_DBG(fip, "vn_probe_req: " "port_id collision\n"); @@ -2454,14 +2452,14 @@ static void fcoe_ctlr_vn_probe_req(struct fcoe_ctlr *fip, /** * fcoe_ctlr_vn_probe_reply() - handle incoming VN2VN probe reply. * @fip: The FCoE controller - * @rdata: parsed remote port with frport from the probe request + * @frport: parsed FCoE rport from the probe request * * Called with ctlr_mutex held. */ static void fcoe_ctlr_vn_probe_reply(struct fcoe_ctlr *fip, - struct fc_rport_priv *rdata) + struct fcoe_rport *frport) { - if (rdata->ids.port_id != fip->port_id) + if (frport->rdata.ids.port_id != fip->port_id) return; switch (fip->state) { case FIP_ST_VNMP_START: @@ -2484,11 +2482,11 @@ static void fcoe_ctlr_vn_probe_reply(struct fcoe_ctlr *fip, /** * fcoe_ctlr_vn_add() - Add a VN2VN entry to the list, based on a claim reply. * @fip: The FCoE controller - * @new: newly-parsed remote port with frport as a template for new rdata + * @new: newly-parsed FCoE rport as a template for new rdata * * Called with ctlr_mutex held. */ -static void fcoe_ctlr_vn_add(struct fcoe_ctlr *fip, struct fc_rport_priv *new) +static void fcoe_ctlr_vn_add(struct fcoe_ctlr *fip, struct fcoe_rport *new) { struct fc_lport *lport = fip->lp; struct fc_rport_priv *rdata; @@ -2496,7 +2494,7 @@ static void fcoe_ctlr_vn_add(struct fcoe_ctlr *fip, struct fc_rport_priv *new) struct fcoe_rport *frport; u32 port_id; - port_id = new->ids.port_id; + port_id = new->rdata.ids.port_id; if (port_id == fip->port_id) return; @@ -2513,22 +2511,28 @@ static void fcoe_ctlr_vn_add(struct fcoe_ctlr *fip, struct fc_rport_priv *new) rdata->disc_id = lport->disc.disc_id; ids = &rdata->ids; - if ((ids->port_name != -1 && ids->port_name != new->ids.port_name) || - (ids->node_name != -1 && ids->node_name != new->ids.node_name)) { + if ((ids->port_name != -1 && + ids->port_name != new->rdata.ids.port_name) || + (ids->node_name != -1 && + ids->node_name != new->rdata.ids.node_name)) { mutex_unlock(&rdata->rp_mutex); LIBFCOE_FIP_DBG(fip, "vn_add rport logoff %6.6x\n", port_id); fc_rport_logoff(rdata); mutex_lock(&rdata->rp_mutex); } - ids->port_name = new->ids.port_name; - ids->node_name = new->ids.node_name; + ids->port_name = new->rdata.ids.port_name; + ids->node_name = new->rdata.ids.node_name; mutex_unlock(&rdata->rp_mutex); frport = fcoe_ctlr_rport(rdata); LIBFCOE_FIP_DBG(fip, "vn_add rport %6.6x %s state %d\n", port_id, frport->fcoe_len ? "old" : "new", rdata->rp_state); - *frport = *fcoe_ctlr_rport(new); + frport->fcoe_len = new->fcoe_len; + frport->flags = new->flags; + frport->login_count = new->login_count; + memcpy(frport->enode_mac, new->enode_mac, ETH_ALEN); + memcpy(frport->vn_mac, new->vn_mac, ETH_ALEN); frport->time = 0; } @@ -2560,16 +2564,14 @@ static int fcoe_ctlr_vn_lookup(struct fcoe_ctlr *fip, u32 port_id, u8 *mac) /** * fcoe_ctlr_vn_claim_notify() - handle received FIP VN2VN Claim Notification * @fip: The FCoE controller - * @new: newly-parsed remote port with frport as a template for new rdata + * @new: newly-parsed FCoE rport as a template for new rdata * * Called with ctlr_mutex held. */ static void fcoe_ctlr_vn_claim_notify(struct fcoe_ctlr *fip, - struct fc_rport_priv *new) + struct fcoe_rport *new) { - struct fcoe_rport *frport = fcoe_ctlr_rport(new); - - if (frport->flags & FIP_FL_REC_OR_P2P) { + if (new->flags & FIP_FL_REC_OR_P2P) { LIBFCOE_FIP_DBG(fip, "send probe req for P2P/REC\n"); fcoe_ctlr_vn_send(fip, FIP_SC_VN_PROBE_REQ, fcoe_all_vn2vn, 0); return; @@ -2578,7 +2580,7 @@ static void fcoe_ctlr_vn_claim_notify(struct fcoe_ctlr *fip, case FIP_ST_VNMP_START: case FIP_ST_VNMP_PROBE1: case FIP_ST_VNMP_PROBE2: - if (new->ids.port_id == fip->port_id) { + if (new->rdata.ids.port_id == fip->port_id) { LIBFCOE_FIP_DBG(fip, "vn_claim_notify: " "restart, state %d\n", fip->state); @@ -2587,8 +2589,8 @@ static void fcoe_ctlr_vn_claim_notify(struct fcoe_ctlr *fip, break; case FIP_ST_VNMP_CLAIM: case FIP_ST_VNMP_UP: - if (new->ids.port_id == fip->port_id) { - if (new->ids.port_name > fip->lp->wwpn) { + if (new->rdata.ids.port_id == fip->port_id) { + if (new->rdata.ids.port_name > fip->lp->wwpn) { LIBFCOE_FIP_DBG(fip, "vn_claim_notify: " "restart, port_id collision\n"); fcoe_ctlr_vn_restart(fip); @@ -2600,15 +2602,16 @@ static void fcoe_ctlr_vn_claim_notify(struct fcoe_ctlr *fip, break; } LIBFCOE_FIP_DBG(fip, "vn_claim_notify: send reply to %x\n", - new->ids.port_id); - fcoe_ctlr_vn_send(fip, FIP_SC_VN_CLAIM_REP, frport->enode_mac, - min((u32)frport->fcoe_len, + new->rdata.ids.port_id); + fcoe_ctlr_vn_send(fip, FIP_SC_VN_CLAIM_REP, new->enode_mac, + min((u32)new->fcoe_len, fcoe_ctlr_fcoe_size(fip))); fcoe_ctlr_vn_add(fip, new); break; default: LIBFCOE_FIP_DBG(fip, "vn_claim_notify: " - "ignoring claim from %x\n", new->ids.port_id); + "ignoring claim from %x\n", + new->rdata.ids.port_id); break; } } @@ -2616,15 +2619,15 @@ static void fcoe_ctlr_vn_claim_notify(struct fcoe_ctlr *fip, /** * fcoe_ctlr_vn_claim_resp() - handle received Claim Response * @fip: The FCoE controller that received the frame - * @new: newly-parsed remote port with frport from the Claim Response + * @new: newly-parsed FCoE rport from the Claim Response * * Called with ctlr_mutex held. */ static void fcoe_ctlr_vn_claim_resp(struct fcoe_ctlr *fip, - struct fc_rport_priv *new) + struct fcoe_rport *new) { LIBFCOE_FIP_DBG(fip, "claim resp from from rport %x - state %s\n", - new->ids.port_id, fcoe_ctlr_state(fip->state)); + new->rdata.ids.port_id, fcoe_ctlr_state(fip->state)); if (fip->state == FIP_ST_VNMP_UP || fip->state == FIP_ST_VNMP_CLAIM) fcoe_ctlr_vn_add(fip, new); } @@ -2632,28 +2635,28 @@ static void fcoe_ctlr_vn_claim_resp(struct fcoe_ctlr *fip, /** * fcoe_ctlr_vn_beacon() - handle received beacon. * @fip: The FCoE controller that received the frame - * @new: newly-parsed remote port with frport from the Beacon + * @new: newly-parsed FCoE rport from the Beacon * * Called with ctlr_mutex held. */ static void fcoe_ctlr_vn_beacon(struct fcoe_ctlr *fip, - struct fc_rport_priv *new) + struct fcoe_rport *new) { struct fc_lport *lport = fip->lp; struct fc_rport_priv *rdata; struct fcoe_rport *frport; - frport = fcoe_ctlr_rport(new); - if (frport->flags & FIP_FL_REC_OR_P2P) { + if (new->flags & FIP_FL_REC_OR_P2P) { LIBFCOE_FIP_DBG(fip, "p2p beacon while in vn2vn mode\n"); fcoe_ctlr_vn_send(fip, FIP_SC_VN_PROBE_REQ, fcoe_all_vn2vn, 0); return; } - rdata = fc_rport_lookup(lport, new->ids.port_id); + rdata = fc_rport_lookup(lport, new->rdata.ids.port_id); if (rdata) { - if (rdata->ids.node_name == new->ids.node_name && - rdata->ids.port_name == new->ids.port_name) { + if (rdata->ids.node_name == new->rdata.ids.node_name && + rdata->ids.port_name == new->rdata.ids.port_name) { frport = fcoe_ctlr_rport(rdata); + LIBFCOE_FIP_DBG(fip, "beacon from rport %x\n", rdata->ids.port_id); if (!frport->time && fip->state == FIP_ST_VNMP_UP) { @@ -2676,7 +2679,7 @@ static void fcoe_ctlr_vn_beacon(struct fcoe_ctlr *fip, * Don't add the neighbor yet. */ LIBFCOE_FIP_DBG(fip, "beacon from new rport %x. sending claim notify\n", - new->ids.port_id); + new->rdata.ids.port_id); if (time_after(jiffies, fip->sol_time + msecs_to_jiffies(FIP_VN_ANN_WAIT))) fcoe_ctlr_vn_send_claim(fip); @@ -2761,19 +2764,19 @@ static int fcoe_ctlr_vn_recv(struct fcoe_ctlr *fip, struct sk_buff *skb) mutex_lock(&fip->ctlr_mutex); switch (sub) { case FIP_SC_VN_PROBE_REQ: - fcoe_ctlr_vn_probe_req(fip, &frport.rdata); + fcoe_ctlr_vn_probe_req(fip, &frport); break; case FIP_SC_VN_PROBE_REP: - fcoe_ctlr_vn_probe_reply(fip, &frport.rdata); + fcoe_ctlr_vn_probe_reply(fip, &frport); break; case FIP_SC_VN_CLAIM_NOTIFY: - fcoe_ctlr_vn_claim_notify(fip, &frport.rdata); + fcoe_ctlr_vn_claim_notify(fip, &frport); break; case FIP_SC_VN_CLAIM_REP: - fcoe_ctlr_vn_claim_resp(fip, &frport.rdata); + fcoe_ctlr_vn_claim_resp(fip, &frport); break; case FIP_SC_VN_BEACON: - fcoe_ctlr_vn_beacon(fip, &frport.rdata); + fcoe_ctlr_vn_beacon(fip, &frport); break; default: LIBFCOE_FIP_DBG(fip, "vn_recv unknown subcode %d\n", sub); @@ -2949,13 +2952,13 @@ static void fcoe_ctlr_vlan_send(struct fcoe_ctlr *fip, /** * fcoe_ctlr_vlan_disk_reply() - send FIP VLAN Discovery Notification. * @fip: The FCoE controller + * @frport: The newly-parsed FCoE rport from the Discovery Request * * Called with ctlr_mutex held. */ static void fcoe_ctlr_vlan_disc_reply(struct fcoe_ctlr *fip, - struct fc_rport_priv *rdata) + struct fcoe_rport *frport) { - struct fcoe_rport *frport = fcoe_ctlr_rport(rdata); enum fip_vlan_subcode sub = FIP_SC_VL_NOTE; if (fip->mode == FIP_MODE_VN2VN) @@ -2986,7 +2989,7 @@ static int fcoe_ctlr_vlan_recv(struct fcoe_ctlr *fip, struct sk_buff *skb) } mutex_lock(&fip->ctlr_mutex); if (sub == FIP_SC_VL_REQ) - fcoe_ctlr_vlan_disc_reply(fip, &frport.rdata); + fcoe_ctlr_vlan_disc_reply(fip, &frport); mutex_unlock(&fip->ctlr_mutex); drop: From c00f9c6b79f7e1c5caf774c38e9fd5dad2d2ef1c Mon Sep 17 00:00:00 2001 From: Zhenyu Wang Date: Wed, 12 Jun 2019 11:17:46 +0800 Subject: [PATCH 556/823] drm/i915/gvt: remove duplicate include of trace.h This removes duplicate include of trace.h. Found by Hariprasad Kelam with includecheck. Reported-by: Hariprasad Kelam Reviewed-by: Yan Zhao Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/trace_points.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/trace_points.c b/drivers/gpu/drm/i915/gvt/trace_points.c index a3deed692b9c..fe552e877e09 100644 --- a/drivers/gpu/drm/i915/gvt/trace_points.c +++ b/drivers/gpu/drm/i915/gvt/trace_points.c @@ -28,8 +28,6 @@ * */ -#include "trace.h" - #ifndef __CHECKER__ #define CREATE_TRACE_POINTS #include "trace.h" From d18fd0576e05a4b03b588e131093b0437fccb75f Mon Sep 17 00:00:00 2001 From: Xiong Zhang Date: Mon, 27 May 2019 13:45:51 +0800 Subject: [PATCH 557/823] drm/i915/gvt: Warning for invalid ggtt access Instead of silently return virtual ggtt entries that guest is allowed to access, this patch add extra range check. If guest read out of range, it will print a warning and return 0. If guest write out of range, the write will be dropped without any message. Reviewed-by: Zhenyu Wang Signed-off-by: Xiong Zhang Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/gtt.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 53115bdae12b..4b04af569c05 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -2141,11 +2141,20 @@ static int emulate_ggtt_mmio_read(struct intel_vgpu *vgpu, struct intel_vgpu_mm *ggtt_mm = vgpu->gtt.ggtt_mm; const struct intel_gvt_device_info *info = &vgpu->gvt->device_info; unsigned long index = off >> info->gtt_entry_size_shift; + unsigned long gma; struct intel_gvt_gtt_entry e; if (bytes != 4 && bytes != 8) return -EINVAL; + gma = index << I915_GTT_PAGE_SHIFT; + if (!intel_gvt_ggtt_validate_range(vgpu, + gma, 1 << I915_GTT_PAGE_SHIFT)) { + gvt_dbg_mm("read invalid ggtt at 0x%lx\n", gma); + memset(p_data, 0, bytes); + return 0; + } + ggtt_get_guest_entry(ggtt_mm, &e, index); memcpy(p_data, (void *)&e.val64 + (off & (info->gtt_entry_size - 1)), bytes); From c25144098bee19b089c8a37c54517bf467f06403 Mon Sep 17 00:00:00 2001 From: Xiong Zhang Date: Mon, 27 May 2019 13:45:52 +0800 Subject: [PATCH 558/823] drm/i915/gvt: Don't use ggtt_validdate_range() with size=0 Use vgpu_gmadr_is_valid() directly instead. Reviewed-by: Zhenyu Wang Signed-off-by: Xiong Zhang Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/fb_decoder.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c index 65e847392aea..8bb292b01271 100644 --- a/drivers/gpu/drm/i915/gvt/fb_decoder.c +++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c @@ -245,7 +245,7 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu, plane->hw_format = fmt; plane->base = vgpu_vreg_t(vgpu, DSPSURF(pipe)) & I915_GTT_PAGE_MASK; - if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) + if (!vgpu_gmadr_is_valid(vgpu, plane->base)) return -EINVAL; plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base); @@ -368,7 +368,7 @@ int intel_vgpu_decode_cursor_plane(struct intel_vgpu *vgpu, alpha_plane, alpha_force); plane->base = vgpu_vreg_t(vgpu, CURBASE(pipe)) & I915_GTT_PAGE_MASK; - if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) + if (!vgpu_gmadr_is_valid(vgpu, plane->base)) return -EINVAL; plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base); @@ -472,7 +472,7 @@ int intel_vgpu_decode_sprite_plane(struct intel_vgpu *vgpu, plane->drm_format = drm_format; plane->base = vgpu_vreg_t(vgpu, SPRSURF(pipe)) & I915_GTT_PAGE_MASK; - if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) + if (!vgpu_gmadr_is_valid(vgpu, plane->base)) return -EINVAL; plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base); From 2089a76ade9005a06c5e08e8454f45f3625fdc1c Mon Sep 17 00:00:00 2001 From: Xiong Zhang Date: Mon, 27 May 2019 13:45:53 +0800 Subject: [PATCH 559/823] drm/i915/gvt: Checking workload's gma earlier Workload contains RB and WA_CTX which are in ggtt space, if they aren't in valid ggtt space, the workload shouldn't be shadowed and scanned. So checking them earlier to avoid shadow them. Reviewed-by: Zhenyu Wang Signed-off-by: Xiong Zhang Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/cmd_parser.c | 10 ---------- drivers/gpu/drm/i915/gvt/scheduler.c | 28 +++++++++++++++++++++++++++ 2 files changed, 28 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index 6ea88270c818..b09dc315e2da 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -2674,11 +2674,6 @@ static int scan_workload(struct intel_vgpu_workload *workload) gma_head == gma_tail) return 0; - if (!intel_gvt_ggtt_validate_range(s.vgpu, s.ring_start, s.ring_size)) { - ret = -EINVAL; - goto out; - } - ret = ip_gma_set(&s, gma_head); if (ret) goto out; @@ -2724,11 +2719,6 @@ static int scan_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx) s.workload = workload; s.is_ctx_wa = true; - if (!intel_gvt_ggtt_validate_range(s.vgpu, s.ring_start, s.ring_size)) { - ret = -EINVAL; - goto out; - } - ret = ip_gma_set(&s, gma_head); if (ret) goto out; diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 2144fb46d0e1..6469366c1753 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -1492,6 +1492,12 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id, intel_gvt_hypervisor_read_gpa(vgpu, ring_context_gpa + RING_CTX_OFF(ctx_ctrl.val), &ctx_ctl, 4); + if (!intel_gvt_ggtt_validate_range(vgpu, start, + _RING_CTL_BUF_SIZE(ctl))) { + gvt_vgpu_err("context contain invalid rb at: 0x%x\n", start); + return ERR_PTR(-EINVAL); + } + workload = alloc_workload(vgpu); if (IS_ERR(workload)) return workload; @@ -1516,9 +1522,31 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id, workload->wa_ctx.indirect_ctx.size = (indirect_ctx & INDIRECT_CTX_SIZE_MASK) * CACHELINE_BYTES; + + if (workload->wa_ctx.indirect_ctx.size != 0) { + if (!intel_gvt_ggtt_validate_range(vgpu, + workload->wa_ctx.indirect_ctx.guest_gma, + workload->wa_ctx.indirect_ctx.size)) { + kmem_cache_free(s->workloads, workload); + gvt_vgpu_err("invalid wa_ctx at: 0x%lx\n", + workload->wa_ctx.indirect_ctx.guest_gma); + return ERR_PTR(-EINVAL); + } + } + workload->wa_ctx.per_ctx.guest_gma = per_ctx & PER_CTX_ADDR_MASK; workload->wa_ctx.per_ctx.valid = per_ctx & 1; + if (workload->wa_ctx.per_ctx.valid) { + if (!intel_gvt_ggtt_validate_range(vgpu, + workload->wa_ctx.per_ctx.guest_gma, + CACHELINE_BYTES)) { + kmem_cache_free(s->workloads, workload); + gvt_vgpu_err("invalid per_ctx at: 0x%lx\n", + workload->wa_ctx.per_ctx.guest_gma); + return ERR_PTR(-EINVAL); + } + } } gvt_dbg_el("workload %p ring id %d head %x tail %x start %x ctl %x\n", From 7366aeb77cd840f3edea02c65065d40affaa7f45 Mon Sep 17 00:00:00 2001 From: Xiaolin Zhang Date: Thu, 18 Jul 2019 01:10:24 +0800 Subject: [PATCH 560/823] drm/i915/gvt: fix incorrect cache entry for guest page mapping GPU hang observed during the guest OCL conformance test which is caused by THP GTT feature used durning the test. It was observed the same GFN with different size (4K and 2M) requested from the guest in GVT. So during the guest page dma map stage, it is required to unmap first with orginal size and then remap again with requested size. Fixes: b901b252b6cf ("drm/i915/gvt: Add 2M huge gtt support") Cc: stable@vger.kernel.org Reviewed-by: Zhenyu Wang Signed-off-by: Xiaolin Zhang Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/kvmgt.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 144301b778df..23aa3e50cbf8 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -1904,6 +1904,18 @@ static int kvmgt_dma_map_guest_page(unsigned long handle, unsigned long gfn, entry = __gvt_cache_find_gfn(info->vgpu, gfn); if (!entry) { + ret = gvt_dma_map_page(vgpu, gfn, dma_addr, size); + if (ret) + goto err_unlock; + + ret = __gvt_cache_add(info->vgpu, gfn, *dma_addr, size); + if (ret) + goto err_unmap; + } else if (entry->size != size) { + /* the same gfn with different size: unmap and re-map */ + gvt_dma_unmap_page(vgpu, gfn, entry->dma_addr, entry->size); + __gvt_cache_remove_entry(vgpu, entry); + ret = gvt_dma_map_page(vgpu, gfn, dma_addr, size); if (ret) goto err_unlock; From ef5b0b444e6297d03ac0bdc0c82f65396ef4dccd Mon Sep 17 00:00:00 2001 From: Xiaolin Zhang Date: Thu, 20 Jun 2019 10:29:24 -0400 Subject: [PATCH 561/823] drm/i915/gvt: grab runtime pm first for forcewake use in workload_thread, it should grab runtime pm wakelock and later uncore forcewake get will check rpm wakelock held successfully. otherwise, sometimes, rpm wakelock not hold and print call trace below: Call Trace: intel_uncore_forcewake_get+0x15/0x20 [i915] workload_thread+0x5f9/0x16f0 [i915] ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 ? __switch_to_asm+0x34/0x70 ? __switch_to+0x85/0x3f0 ? __switch_to_asm+0x40/0x70 ? do_wait_intr_irq+0x90/0x90 kthread+0x121/0x140 ? intel_vgpu_clean_workloads+0x100/0x100 [i915] ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 --[ end trace 86525f742a02e12c ]-- v2: adapted to use rpm structure. Fixes: 251d46b0875c ("drm/i915/gvt: Pin the per-engine GVT shadow contexts") Reviewed-by: Zhenyu Wang Signed-off-by: Xiaolin Zhang Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/scheduler.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 6469366c1753..196b4155a309 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -990,6 +990,7 @@ static int workload_thread(void *priv) int ret; bool need_force_wake = (INTEL_GEN(gvt->dev_priv) >= 9); DEFINE_WAIT_FUNC(wait, woken_wake_function); + struct intel_runtime_pm *rpm = &gvt->dev_priv->runtime_pm; kfree(p); @@ -1013,6 +1014,8 @@ static int workload_thread(void *priv) workload->ring_id, workload, workload->vgpu->id); + intel_runtime_pm_get(rpm); + gvt_dbg_sched("ring id %d will dispatch workload %p\n", workload->ring_id, workload); @@ -1042,6 +1045,7 @@ complete: intel_uncore_forcewake_put(&gvt->dev_priv->uncore, FORCEWAKE_ALL); + intel_runtime_pm_put_unchecked(rpm); if (ret && (vgpu_is_vm_unhealthy(ret))) enter_failsafe_mode(vgpu, GVT_FAILSAFE_GUEST_ERR); } From 4187414808095f645ca0661f8dde77617e2e7cb3 Mon Sep 17 00:00:00 2001 From: Colin Xu Date: Thu, 4 Jul 2019 16:45:06 +0800 Subject: [PATCH 562/823] drm/i915/gvt: Adding ppgtt to GVT GEM context after shadow pdps settled. Windows guest can't run after force-TDR with host log: ... gvt: vgpu 1: workload shadow ppgtt isn't ready gvt: vgpu 1: fail to dispatch workload, skip ... The error is raised by set_context_ppgtt_from_shadow(), when it checks and found the shadow_mm isn't marked as shadowed. In work thread before each submission, a shadow_mm is set to shadowed in: shadow_ppgtt_mm() <-intel_vgpu_pin_mm() <-prepare_workload() <-dispatch_workload() <-workload_thread() However checking whether or not shadow_mm is shadowed is prior to it: set_context_ppgtt_from_shadow() <-dispatch_workload() <-workload_thread() In normal case, create workload will check the existence of shadow_mm, if not it will create a new one and marked as shadowed. If already exist it will reuse the old one. Since shadow_mm is reused, checking of shadowed in set_context_ppgtt_from_shadow() actually always see the state set in creation, but not the state set in intel_vgpu_pin_mm(). When force-TDR, all engines are reset, since it's not dmlr level, all ppgtt_mm are invalidated but not destroyed. Invalidation will mark all reused shadow_mm as not shadowed but still keeps in ppgtt_mm_list_head. If workload submission phase those shadow_mm are reused with shadowed not set, then set_context_ppgtt_from_shadow() will report error. Pin for context after shadow_mm pinned and shadow pdps settled. v2: Move set_context_ppgtt_from_shadow() after prepare_workload(). (zhenyu) v3: Move set_context_ppgtt_from_shadow() after shadow pdps updated.(zhenyu) Fixes: 4f15665ccbba ("drm/i915: Add ppgtt to GVT GEM context") Cc: stable@vger.kernel.org Signed-off-by: Colin Xu Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/scheduler.c | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 196b4155a309..9f3fd7d96a69 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -364,16 +364,13 @@ static void release_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx) wa_ctx->indirect_ctx.shadow_va = NULL; } -static int set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload, - struct i915_gem_context *ctx) +static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload, + struct i915_gem_context *ctx) { struct intel_vgpu_mm *mm = workload->shadow_mm; struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(ctx->vm); int i = 0; - if (mm->type != INTEL_GVT_MM_PPGTT || !mm->ppgtt_mm.shadowed) - return -EINVAL; - if (mm->ppgtt_mm.root_entry_type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY) { px_dma(ppgtt->pd) = mm->ppgtt_mm.shadow_pdps[0]; } else { @@ -384,8 +381,6 @@ static int set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload, px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i]; } } - - return 0; } static int @@ -614,6 +609,8 @@ static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload) static int prepare_workload(struct intel_vgpu_workload *workload) { struct intel_vgpu *vgpu = workload->vgpu; + struct intel_vgpu_submission *s = &vgpu->submission; + int ring = workload->ring_id; int ret = 0; ret = intel_vgpu_pin_mm(workload->shadow_mm); @@ -622,8 +619,16 @@ static int prepare_workload(struct intel_vgpu_workload *workload) return ret; } + if (workload->shadow_mm->type != INTEL_GVT_MM_PPGTT || + !workload->shadow_mm->ppgtt_mm.shadowed) { + gvt_vgpu_err("workload shadow ppgtt isn't ready\n"); + return -EINVAL; + } + update_shadow_pdps(workload); + set_context_ppgtt_from_shadow(workload, s->shadow[ring]->gem_context); + ret = intel_vgpu_sync_oos_pages(workload->vgpu); if (ret) { gvt_vgpu_err("fail to vgpu sync oos pages\n"); @@ -674,7 +679,6 @@ static int dispatch_workload(struct intel_vgpu_workload *workload) { struct intel_vgpu *vgpu = workload->vgpu; struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; - struct intel_vgpu_submission *s = &vgpu->submission; struct i915_request *rq; int ring_id = workload->ring_id; int ret; @@ -685,13 +689,6 @@ static int dispatch_workload(struct intel_vgpu_workload *workload) mutex_lock(&vgpu->vgpu_lock); mutex_lock(&dev_priv->drm.struct_mutex); - ret = set_context_ppgtt_from_shadow(workload, - s->shadow[ring_id]->gem_context); - if (ret < 0) { - gvt_vgpu_err("workload shadow ppgtt isn't ready\n"); - goto err_req; - } - ret = intel_gvt_workload_req_alloc(workload); if (ret) goto err_req; From 5d78e1c2b7f4be00bbe62141603a631dc7812f35 Mon Sep 17 00:00:00 2001 From: Hillf Danton Date: Tue, 30 Jul 2019 17:24:36 +0800 Subject: [PATCH 563/823] ALSA: usb-audio: Fix gpf in snd_usb_pipe_sanity_check syzbot found the following crash on: general protection fault: 0000 [#1] SMP KASAN RIP: 0010:snd_usb_pipe_sanity_check+0x80/0x130 sound/usb/helper.c:75 Call Trace: snd_usb_motu_microbookii_communicate.constprop.0+0xa0/0x2fb sound/usb/quirks.c:1007 snd_usb_motu_microbookii_boot_quirk sound/usb/quirks.c:1051 [inline] snd_usb_apply_boot_quirk.cold+0x163/0x370 sound/usb/quirks.c:1280 usb_audio_probe+0x2ec/0x2010 sound/usb/card.c:576 usb_probe_interface+0x305/0x7a0 drivers/usb/core/driver.c:361 really_probe+0x281/0x650 drivers/base/dd.c:548 .... It was introduced in commit 801ebf1043ae for checking pipe and endpoint types. It is fixed by adding a check of the ep pointer in question. BugLink: https://syzkaller.appspot.com/bug?extid=d59c4387bfb6eced94e2 Reported-by: syzbot Fixes: 801ebf1043ae ("ALSA: usb-audio: Sanity checks for each pipe and EP types") Cc: Andrey Konovalov Signed-off-by: Hillf Danton Signed-off-by: Takashi Iwai --- sound/usb/helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/usb/helper.c b/sound/usb/helper.c index 71d5f540334a..4c12cc5b53fd 100644 --- a/sound/usb/helper.c +++ b/sound/usb/helper.c @@ -72,7 +72,7 @@ int snd_usb_pipe_sanity_check(struct usb_device *dev, unsigned int pipe) struct usb_host_endpoint *ep; ep = usb_pipe_endpoint(dev, pipe); - if (usb_pipetype(pipe) != pipetypes[usb_endpoint_type(&ep->desc)]) + if (!ep || usb_pipetype(pipe) != pipetypes[usb_endpoint_type(&ep->desc)]) return -EINVAL; return 0; } From da1115fdbd6e86c62185cdd2b4bf7add39f2f82b Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 29 Jul 2019 15:21:28 +0530 Subject: [PATCH 564/823] powerpc/nvdimm: Pick nearby online node if the device node is not online MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, nvdimm subsystem expects the device numa node for SCM device to be an online node. It also doesn't try to bring the device numa node online. Hence if we use a non-online numa node as device node we hit crashes like below. This is because we try to access uninitialized NODE_DATA in different code paths. cpu 0x0: Vector: 300 (Data Access) at [c0000000fac53170] pc: c0000000004bbc50: ___slab_alloc+0x120/0xca0 lr: c0000000004bc834: __slab_alloc+0x64/0xc0 sp: c0000000fac53400 msr: 8000000002009033 dar: 73e8 dsisr: 80000 current = 0xc0000000fabb6d80 paca = 0xc000000003870000 irqmask: 0x03 irq_happened: 0x01 pid = 7, comm = kworker/u16:0 Linux version 5.2.0-06234-g76bd729b2644 (kvaneesh@ltc-boston123) (gcc version 7.4.0 (Ubuntu 7.4.0-1ubuntu1~18.04.1)) #135 SMP Thu Jul 11 05:36:30 CDT 2019 enter ? for help [link register ] c0000000004bc834 __slab_alloc+0x64/0xc0 [c0000000fac53400] c0000000fac53480 (unreliable) [c0000000fac53500] c0000000004bc818 __slab_alloc+0x48/0xc0 [c0000000fac53560] c0000000004c30a0 __kmalloc_node_track_caller+0x3c0/0x6b0 [c0000000fac535d0] c000000000cfafe4 devm_kmalloc+0x74/0xc0 [c0000000fac53600] c000000000d69434 nd_region_activate+0x144/0x560 [c0000000fac536d0] c000000000d6b19c nd_region_probe+0x17c/0x370 [c0000000fac537b0] c000000000d6349c nvdimm_bus_probe+0x10c/0x230 [c0000000fac53840] c000000000cf3cc4 really_probe+0x254/0x4e0 [c0000000fac538d0] c000000000cf429c driver_probe_device+0x16c/0x1e0 [c0000000fac53950] c000000000cf0b44 bus_for_each_drv+0x94/0x130 [c0000000fac539b0] c000000000cf392c __device_attach+0xdc/0x200 [c0000000fac53a50] c000000000cf231c bus_probe_device+0x4c/0xf0 [c0000000fac53a90] c000000000ced268 device_add+0x528/0x810 [c0000000fac53b60] c000000000d62a58 nd_async_device_register+0x28/0xa0 [c0000000fac53bd0] c0000000001ccb8c async_run_entry_fn+0xcc/0x1f0 [c0000000fac53c50] c0000000001bcd9c process_one_work+0x46c/0x860 [c0000000fac53d20] c0000000001bd4f4 worker_thread+0x364/0x5f0 [c0000000fac53db0] c0000000001c7260 kthread+0x1b0/0x1c0 [c0000000fac53e20] c00000000000b954 ret_from_kernel_thread+0x5c/0x68 The patch tries to fix this by picking the nearest online node as the SCM node. This does have a problem of us losing the information that SCM node is equidistant from two other online nodes. If applications need to understand these fine-grained details we should express then like x86 does via /sys/devices/system/node/nodeX/accessY/initiators/ With the patch we get # numactl -H available: 2 nodes (0-1) node 0 cpus: node 0 size: 0 MB node 0 free: 0 MB node 1 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 node 1 size: 130865 MB node 1 free: 129130 MB node distances: node 0 1 0: 10 20 1: 20 10 # cat /sys/bus/nd/devices/region0/numa_node 0 # dmesg | grep papr_scm [ 91.332305] papr_scm ibm,persistent-memory:ibm,pmemory@44104001: Region registered with target node 2 and online node 0 Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190729095128.23707-1-aneesh.kumar@linux.ibm.com --- arch/powerpc/platforms/pseries/papr_scm.c | 29 +++++++++++++++++++++-- 1 file changed, 27 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 2c07908359b2..a5ac371a3f06 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -275,12 +275,32 @@ static const struct attribute_group *papr_scm_dimm_groups[] = { NULL, }; +static inline int papr_scm_node(int node) +{ + int min_dist = INT_MAX, dist; + int nid, min_node; + + if ((node == NUMA_NO_NODE) || node_online(node)) + return node; + + min_node = first_online_node; + for_each_online_node(nid) { + dist = node_distance(node, nid); + if (dist < min_dist) { + min_dist = dist; + min_node = nid; + } + } + return min_node; +} + static int papr_scm_nvdimm_init(struct papr_scm_priv *p) { struct device *dev = &p->pdev->dev; struct nd_mapping_desc mapping; struct nd_region_desc ndr_desc; unsigned long dimm_flags; + int target_nid, online_nid; p->bus_desc.ndctl = papr_scm_ndctl; p->bus_desc.module = THIS_MODULE; @@ -319,8 +339,10 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) memset(&ndr_desc, 0, sizeof(ndr_desc)); ndr_desc.attr_groups = region_attr_groups; - ndr_desc.numa_node = dev_to_node(&p->pdev->dev); - ndr_desc.target_node = ndr_desc.numa_node; + target_nid = dev_to_node(&p->pdev->dev); + online_nid = papr_scm_node(target_nid); + ndr_desc.numa_node = online_nid; + ndr_desc.target_node = target_nid; ndr_desc.res = &p->res; ndr_desc.of_node = p->dn; ndr_desc.provider_data = p; @@ -338,6 +360,9 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) ndr_desc.res, p->dn); goto err; } + if (target_nid != online_nid) + dev_info(dev, "Region registered with target node %d and online node %d", + target_nid, online_nid); return 0; From 3b48300d5cc7c7bed63fddb006c4046549ed4aec Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 29 Jul 2019 17:58:10 +0200 Subject: [PATCH 565/823] netfilter: ebtables: also count base chain policies ebtables doesn't include the base chain policies in the rule count, so we need to add them manually when we call into the x_tables core to allocate space for the comapt offset table. This lead syzbot to trigger: WARNING: CPU: 1 PID: 9012 at net/netfilter/x_tables.c:649 xt_compat_add_offset.cold+0x11/0x36 net/netfilter/x_tables.c:649 Reported-by: syzbot+276ddebab3382bbf72db@syzkaller.appspotmail.com Fixes: 2035f3ff8eaa ("netfilter: ebtables: compat: un-break 32bit setsockopt when no rules are present") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/ebtables.c | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index fd84b48e48b5..c8177a89f52c 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1770,20 +1770,28 @@ static int compat_calc_entry(const struct ebt_entry *e, return 0; } +static int ebt_compat_init_offsets(unsigned int number) +{ + if (number > INT_MAX) + return -EINVAL; + + /* also count the base chain policies */ + number += NF_BR_NUMHOOKS; + + return xt_compat_init_offsets(NFPROTO_BRIDGE, number); +} static int compat_table_info(const struct ebt_table_info *info, struct compat_ebt_replace *newinfo) { unsigned int size = info->entries_size; const void *entries = info->entries; + int ret; newinfo->entries_size = size; - if (info->nentries) { - int ret = xt_compat_init_offsets(NFPROTO_BRIDGE, - info->nentries); - if (ret) - return ret; - } + ret = ebt_compat_init_offsets(info->nentries); + if (ret) + return ret; return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info, entries, newinfo); @@ -2234,11 +2242,9 @@ static int compat_do_replace(struct net *net, void __user *user, xt_compat_lock(NFPROTO_BRIDGE); - if (tmp.nentries) { - ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); - if (ret < 0) - goto out_unlock; - } + ret = ebt_compat_init_offsets(tmp.nentries); + if (ret < 0) + goto out_unlock; ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); if (ret < 0) From f4cc743a98136df3c3763050a0e8223b52d9a960 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Mon, 29 Jul 2019 15:12:16 +0800 Subject: [PATCH 566/823] drm/bridge: lvds-encoder: Fix build error while CONFIG_DRM_KMS_HELPER=m If DRM_LVDS_ENCODER=y but CONFIG_DRM_KMS_HELPER=m, build fails: drivers/gpu/drm/bridge/lvds-encoder.o: In function `lvds_encoder_probe': lvds-encoder.c:(.text+0x155): undefined reference to `devm_drm_panel_bridge_add' Reported-by: Hulk Robot Fixes: dbb58bfd9ae6 ("drm/bridge: Fix lvds-encoder since the panel_bridge rework.") Signed-off-by: YueHaibing Reviewed-by: Neil Armstrong Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20190729071216.27488-1-yuehaibing@huawei.com --- drivers/gpu/drm/bridge/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index ee777469293a..cc62603b87c5 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -48,6 +48,7 @@ config DRM_DUMB_VGA_DAC config DRM_LVDS_ENCODER tristate "Transparent parallel to LVDS encoder support" depends on OF + select DRM_KMS_HELPER select DRM_PANEL_BRIDGE help Support for transparent parallel to LVDS encoders that don't require From eef347f846ee8f7296a6f84e3866c057ca6bcce0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 30 Jul 2019 14:52:07 +0200 Subject: [PATCH 567/823] Revert "mac80211: set NETIF_F_LLTX when using intermediate tx queues" Revert this for now, it has been reported multiple times that it completely breaks connectivity on various devices. Cc: stable@vger.kernel.org Fixes: 8dbb000ee73b ("mac80211: set NETIF_F_LLTX when using intermediate tx queues") Reported-by: Jean Delvare Reported-by: Peter Lebbing Signed-off-by: Johannes Berg --- net/mac80211/iface.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 06aac0aaae64..8dc6580e1787 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1222,7 +1222,6 @@ static void ieee80211_if_setup(struct net_device *dev) static void ieee80211_if_setup_no_queue(struct net_device *dev) { ieee80211_if_setup(dev); - dev->features |= NETIF_F_LLTX; dev->priv_flags |= IFF_NO_QUEUE; } From e1ae72a21e5f0d1846e26e3f5963930664702071 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Mon, 29 Jul 2019 17:05:20 +0800 Subject: [PATCH 568/823] drm/bridge: tc358764: Fix build error If CONFIG_DRM_TOSHIBA_TC358764=y but CONFIG_DRM_KMS_HELPER=m, building fails: drivers/gpu/drm/bridge/tc358764.o:(.rodata+0x228): undefined reference to `drm_atomic_helper_connector_reset' drivers/gpu/drm/bridge/tc358764.o:(.rodata+0x240): undefined reference to `drm_helper_probe_single_connector_modes' drivers/gpu/drm/bridge/tc358764.o:(.rodata+0x268): undefined reference to `drm_atomic_helper_connector_duplicate_state' drivers/gpu/drm/bridge/tc358764.o:(.rodata+0x270): undefined reference to `drm_atomic_helper_connector_destroy_state' Like TC358767, select DRM_KMS_HELPER to fix this, and change to select DRM_PANEL to avoid recursive dependency. Reported-by: Hulk Robot Fixes: f38b7cca6d0e ("drm/bridge: tc358764: Add DSI to LVDS bridge driver") Signed-off-by: YueHaibing Reviewed-by: Laurent Pinchart Reviewed-by: Neil Armstrong Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20190729090520.25968-1-yuehaibing@huawei.com --- drivers/gpu/drm/bridge/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index cc62603b87c5..e4e22bbae2a7 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -117,9 +117,10 @@ config DRM_THINE_THC63LVD1024 config DRM_TOSHIBA_TC358764 tristate "TC358764 DSI/LVDS bridge" - depends on DRM && DRM_PANEL depends on OF select DRM_MIPI_DSI + select DRM_KMS_HELPER + select DRM_PANEL help Toshiba TC358764 DSI/LVDS bridge driver. From 60034d3d146b11922ab1db613bce062dddc0327a Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 30 Jul 2019 14:42:50 +0100 Subject: [PATCH 569/823] rxrpc: Fix potential deadlock There is a potential deadlock in rxrpc_peer_keepalive_dispatch() whereby rxrpc_put_peer() is called with the peer_hash_lock held, but if it reduces the peer's refcount to 0, rxrpc_put_peer() calls __rxrpc_put_peer() - which the tries to take the already held lock. Fix this by providing a version of rxrpc_put_peer() that can be called in situations where the lock is already held. The bug may produce the following lockdep report: ============================================ WARNING: possible recursive locking detected 5.2.0-next-20190718 #41 Not tainted -------------------------------------------- kworker/0:3/21678 is trying to acquire lock: 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: spin_lock_bh /./include/linux/spinlock.h:343 [inline] 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: __rxrpc_put_peer /net/rxrpc/peer_object.c:415 [inline] 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: rxrpc_put_peer+0x2d3/0x6a0 /net/rxrpc/peer_object.c:435 but task is already holding lock: 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: spin_lock_bh /./include/linux/spinlock.h:343 [inline] 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: rxrpc_peer_keepalive_dispatch /net/rxrpc/peer_event.c:378 [inline] 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: rxrpc_peer_keepalive_worker+0x6b3/0xd02 /net/rxrpc/peer_event.c:430 Fixes: 330bdcfadcee ("rxrpc: Fix the keepalive generator [ver #2]") Reported-by: syzbot+72af434e4b3417318f84@syzkaller.appspotmail.com Signed-off-by: David Howells Reviewed-by: Marc Dionne Reviewed-by: Jeffrey Altman --- net/rxrpc/ar-internal.h | 1 + net/rxrpc/peer_event.c | 2 +- net/rxrpc/peer_object.c | 18 ++++++++++++++++++ 3 files changed, 20 insertions(+), 1 deletion(-) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 80335b4ee4fd..822f45386e31 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1061,6 +1061,7 @@ void rxrpc_destroy_all_peers(struct rxrpc_net *); struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *); struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *); void rxrpc_put_peer(struct rxrpc_peer *); +void rxrpc_put_peer_locked(struct rxrpc_peer *); /* * proc.c diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 9f2f45c09e58..7666ec72d37e 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -378,7 +378,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, spin_lock_bh(&rxnet->peer_hash_lock); list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive[slot & mask]); - rxrpc_put_peer(peer); + rxrpc_put_peer_locked(peer); } spin_unlock_bh(&rxnet->peer_hash_lock); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 9d3ce81cf8ae..9c3ac96f71cb 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -436,6 +436,24 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) } } +/* + * Drop a ref on a peer record where the caller already holds the + * peer_hash_lock. + */ +void rxrpc_put_peer_locked(struct rxrpc_peer *peer) +{ + const void *here = __builtin_return_address(0); + int n; + + n = atomic_dec_return(&peer->usage); + trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + if (n == 0) { + hash_del_rcu(&peer->hash_link); + list_del_init(&peer->keepalive_link); + kfree_rcu(peer, rcu); + } +} + /* * Make sure all peer records have been discarded. */ From 7db57e77586744af46c8bbf8f831bb2b941b7afc Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 31 Jul 2019 00:00:15 +1000 Subject: [PATCH 570/823] powerpc/spe: Mark expected switch fall-throughs Mark switch cases where we are expecting to fall through. Fixes errors such as below, seen with mpc85xx_defconfig: arch/powerpc/kernel/align.c: In function 'emulate_spe': arch/powerpc/kernel/align.c:178:8: error: this statement may fall through ret |= __get_user_inatomic(temp.v[3], p++); ^~ Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190730141917.21817-1-mpe@ellerman.id.au --- arch/powerpc/kernel/align.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 7107ad86de65..92045ed64976 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -176,9 +176,11 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg, ret |= __get_user_inatomic(temp.v[1], p++); ret |= __get_user_inatomic(temp.v[2], p++); ret |= __get_user_inatomic(temp.v[3], p++); + /* fall through */ case 4: ret |= __get_user_inatomic(temp.v[4], p++); ret |= __get_user_inatomic(temp.v[5], p++); + /* fall through */ case 2: ret |= __get_user_inatomic(temp.v[6], p++); ret |= __get_user_inatomic(temp.v[7], p++); @@ -259,9 +261,11 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg, ret |= __put_user_inatomic(data.v[1], p++); ret |= __put_user_inatomic(data.v[2], p++); ret |= __put_user_inatomic(data.v[3], p++); + /* fall through */ case 4: ret |= __put_user_inatomic(data.v[4], p++); ret |= __put_user_inatomic(data.v[5], p++); + /* fall through */ case 2: ret |= __put_user_inatomic(data.v[6], p++); ret |= __put_user_inatomic(data.v[7], p++); From c69565ee6681e151e2bb80502930a16e04b553d1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 30 Jul 2019 14:42:50 +0100 Subject: [PATCH 571/823] rxrpc: Fix the lack of notification when sendmsg() fails on a DATA packet Fix the fact that a notification isn't sent to the recvmsg side to indicate a call failed when sendmsg() fails to transmit a DATA packet with the error ENETUNREACH, EHOSTUNREACH or ECONNREFUSED. Without this notification, the afs client just sits there waiting for the call to complete in some manner (which it's not now going to do), which also pins the rxrpc call in place. This can be seen if the client has a scope-level IPv6 address, but not a global-level IPv6 address, and we try and transmit an operation to a server's IPv6 address. Looking in /proc/net/rxrpc/calls shows completed calls just sat there with an abort code of RX_USER_ABORT and an error code of -ENETUNREACH. Fixes: c54e43d752c7 ("rxrpc: Fix missing start of call timeout") Signed-off-by: David Howells Reviewed-by: Marc Dionne Reviewed-by: Jeffrey Altman --- net/rxrpc/sendmsg.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 5d3f33ce6d41..bae14438f869 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -226,6 +226,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); + rxrpc_notify_socket(call); goto out; } _debug("need instant resend %d", ret); From df612421fe2566654047769c6852ffae1a31df16 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Wed, 24 Jul 2019 12:46:34 -0700 Subject: [PATCH 572/823] mwifiex: fix 802.11n/WPA detection Commit 63d7ef36103d ("mwifiex: Don't abort on small, spec-compliant vendor IEs") adjusted the ieee_types_vendor_header struct, which inadvertently messed up the offsets used in mwifiex_is_wpa_oui_present(). Add that offset back in, mirroring mwifiex_is_rsn_oui_present(). As it stands, commit 63d7ef36103d breaks compatibility with WPA (not WPA2) 802.11n networks, since we hit the "info: Disable 11n if AES is not supported by AP" case in mwifiex_is_network_compatible(). Fixes: 63d7ef36103d ("mwifiex: Don't abort on small, spec-compliant vendor IEs") Cc: Signed-off-by: Brian Norris Signed-off-by: Kalle Valo --- drivers/net/wireless/marvell/mwifiex/main.h | 1 + drivers/net/wireless/marvell/mwifiex/scan.c | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h index 3e442c7f7882..095837fba300 100644 --- a/drivers/net/wireless/marvell/mwifiex/main.h +++ b/drivers/net/wireless/marvell/mwifiex/main.h @@ -124,6 +124,7 @@ enum { #define MWIFIEX_MAX_TOTAL_SCAN_TIME (MWIFIEX_TIMER_10S - MWIFIEX_TIMER_1S) +#define WPA_GTK_OUI_OFFSET 2 #define RSN_GTK_OUI_OFFSET 2 #define MWIFIEX_OUI_NOT_PRESENT 0 diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c index 0d6d41727037..21dda385f6c6 100644 --- a/drivers/net/wireless/marvell/mwifiex/scan.c +++ b/drivers/net/wireless/marvell/mwifiex/scan.c @@ -181,7 +181,8 @@ mwifiex_is_wpa_oui_present(struct mwifiex_bssdescriptor *bss_desc, u32 cipher) u8 ret = MWIFIEX_OUI_NOT_PRESENT; if (has_vendor_hdr(bss_desc->bcn_wpa_ie, WLAN_EID_VENDOR_SPECIFIC)) { - iebody = (struct ie_body *) bss_desc->bcn_wpa_ie->data; + iebody = (struct ie_body *)((u8 *)bss_desc->bcn_wpa_ie->data + + WPA_GTK_OUI_OFFSET); oui = &mwifiex_wpa_oui[cipher][0]; ret = mwifiex_search_oui_in_ie(iebody, oui); if (ret) From 5241ab4cf42d3a93b933b55d3d53f43049081fa1 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 29 Jul 2019 18:15:17 +0900 Subject: [PATCH 573/823] kbuild: initialize CLANG_FLAGS correctly in the top Makefile CLANG_FLAGS is initialized by the following line: CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%)) ..., which is run only when CROSS_COMPILE is set. Some build targets (bindeb-pkg etc.) recurse to the top Makefile. When you build the kernel with Clang but without CROSS_COMPILE, the same compiler flags such as -no-integrated-as are accumulated into CLANG_FLAGS. If you run 'make CC=clang' and then 'make CC=clang bindeb-pkg', Kbuild will recompile everything needlessly due to the build command change. Fix this by correctly initializing CLANG_FLAGS. Fixes: 238bcbc4e07f ("kbuild: consolidate Clang compiler flags") Cc: # v5.0+ Signed-off-by: Masahiro Yamada Reviewed-by: Nathan Chancellor Acked-by: Nick Desaulniers --- Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/Makefile b/Makefile index fa0fbe7851ea..5ee6f6889869 100644 --- a/Makefile +++ b/Makefile @@ -472,6 +472,7 @@ KBUILD_CFLAGS_MODULE := -DMODULE KBUILD_LDFLAGS_MODULE := -T $(srctree)/scripts/module-common.lds KBUILD_LDFLAGS := GCC_PLUGINS_CFLAGS := +CLANG_FLAGS := export ARCH SRCARCH CONFIG_SHELL HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE AS LD CC export CPP AR NM STRIP OBJCOPY OBJDUMP PAHOLE KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS @@ -519,7 +520,7 @@ endif ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) ifneq ($(CROSS_COMPILE),) -CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%)) +CLANG_FLAGS += --target=$(notdir $(CROSS_COMPILE:%-=%)) GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit)) CLANG_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR) GCC_TOOLCHAIN := $(realpath $(GCC_TOOLCHAIN_DIR)/..) From b4f9a1a87a48c255bb90d8a6c3d555a1abb88130 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 17 Jul 2019 13:23:39 +0100 Subject: [PATCH 574/823] Btrfs: fix incremental send failure after deduplication When doing an incremental send operation we can fail if we previously did deduplication operations against a file that exists in both snapshots. In that case we will fail the send operation with -EIO and print a message to dmesg/syslog like the following: BTRFS error (device sdc): Send: inconsistent snapshot, found updated \ extent for inode 257 without updated inode item, send root is 258, \ parent root is 257 This requires that we deduplicate to the same file in both snapshots for the same amount of times on each snapshot. The issue happens because a deduplication only updates the iversion of an inode and does not update any other field of the inode, therefore if we deduplicate the file on each snapshot for the same amount of time, the inode will have the same iversion value (stored as the "sequence" field on the inode item) on both snapshots, therefore it will be seen as unchanged between in the send snapshot while there are new/updated/deleted extent items when comparing to the parent snapshot. This makes the send operation return -EIO and print an error message. Example reproducer: $ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt # Create our first file. The first half of the file has several 64Kb # extents while the second half as a single 512Kb extent. $ xfs_io -f -s -c "pwrite -S 0xb8 -b 64K 0 512K" /mnt/foo $ xfs_io -c "pwrite -S 0xb8 512K 512K" /mnt/foo # Create the base snapshot and the parent send stream from it. $ btrfs subvolume snapshot -r /mnt /mnt/mysnap1 $ btrfs send -f /tmp/1.snap /mnt/mysnap1 # Create our second file, that has exactly the same data as the first # file. $ xfs_io -f -c "pwrite -S 0xb8 0 1M" /mnt/bar # Create the second snapshot, used for the incremental send, before # doing the file deduplication. $ btrfs subvolume snapshot -r /mnt /mnt/mysnap2 # Now before creating the incremental send stream: # # 1) Deduplicate into a subrange of file foo in snapshot mysnap1. This # will drop several extent items and add a new one, also updating # the inode's iversion (sequence field in inode item) by 1, but not # any other field of the inode; # # 2) Deduplicate into a different subrange of file foo in snapshot # mysnap2. This will replace an extent item with a new one, also # updating the inode's iversion by 1 but not any other field of the # inode. # # After these two deduplication operations, the inode items, for file # foo, are identical in both snapshots, but we have different extent # items for this inode in both snapshots. We want to check this doesn't # cause send to fail with an error or produce an incorrect stream. $ xfs_io -r -c "dedupe /mnt/bar 0 0 512K" /mnt/mysnap1/foo $ xfs_io -r -c "dedupe /mnt/bar 512K 512K 512K" /mnt/mysnap2/foo # Create the incremental send stream. $ btrfs send -p /mnt/mysnap1 -f /tmp/2.snap /mnt/mysnap2 ERROR: send ioctl failed with -5: Input/output error This issue started happening back in 2015 when deduplication was updated to not update the inode's ctime and mtime and update only the iversion. Back then we would hit a BUG_ON() in send, but later in 2016 send was updated to return -EIO and print the error message instead of doing the BUG_ON(). A test case for fstests follows soon. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203933 Fixes: 1c919a5e13702c ("btrfs: don't update mtime/ctime on deduped inodes") CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/send.c | 77 ++++++++++--------------------------------------- 1 file changed, 15 insertions(+), 62 deletions(-) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 69b59bf75882..c3c0c064c25d 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6322,68 +6322,21 @@ static int changed_extent(struct send_ctx *sctx, { int ret = 0; - if (sctx->cur_ino != sctx->cmp_key->objectid) { - - if (result == BTRFS_COMPARE_TREE_CHANGED) { - struct extent_buffer *leaf_l; - struct extent_buffer *leaf_r; - struct btrfs_file_extent_item *ei_l; - struct btrfs_file_extent_item *ei_r; - - leaf_l = sctx->left_path->nodes[0]; - leaf_r = sctx->right_path->nodes[0]; - ei_l = btrfs_item_ptr(leaf_l, - sctx->left_path->slots[0], - struct btrfs_file_extent_item); - ei_r = btrfs_item_ptr(leaf_r, - sctx->right_path->slots[0], - struct btrfs_file_extent_item); - - /* - * We may have found an extent item that has changed - * only its disk_bytenr field and the corresponding - * inode item was not updated. This case happens due to - * very specific timings during relocation when a leaf - * that contains file extent items is COWed while - * relocation is ongoing and its in the stage where it - * updates data pointers. So when this happens we can - * safely ignore it since we know it's the same extent, - * but just at different logical and physical locations - * (when an extent is fully replaced with a new one, we - * know the generation number must have changed too, - * since snapshot creation implies committing the current - * transaction, and the inode item must have been updated - * as well). - * This replacement of the disk_bytenr happens at - * relocation.c:replace_file_extents() through - * relocation.c:btrfs_reloc_cow_block(). - */ - if (btrfs_file_extent_generation(leaf_l, ei_l) == - btrfs_file_extent_generation(leaf_r, ei_r) && - btrfs_file_extent_ram_bytes(leaf_l, ei_l) == - btrfs_file_extent_ram_bytes(leaf_r, ei_r) && - btrfs_file_extent_compression(leaf_l, ei_l) == - btrfs_file_extent_compression(leaf_r, ei_r) && - btrfs_file_extent_encryption(leaf_l, ei_l) == - btrfs_file_extent_encryption(leaf_r, ei_r) && - btrfs_file_extent_other_encoding(leaf_l, ei_l) == - btrfs_file_extent_other_encoding(leaf_r, ei_r) && - btrfs_file_extent_type(leaf_l, ei_l) == - btrfs_file_extent_type(leaf_r, ei_r) && - btrfs_file_extent_disk_bytenr(leaf_l, ei_l) != - btrfs_file_extent_disk_bytenr(leaf_r, ei_r) && - btrfs_file_extent_disk_num_bytes(leaf_l, ei_l) == - btrfs_file_extent_disk_num_bytes(leaf_r, ei_r) && - btrfs_file_extent_offset(leaf_l, ei_l) == - btrfs_file_extent_offset(leaf_r, ei_r) && - btrfs_file_extent_num_bytes(leaf_l, ei_l) == - btrfs_file_extent_num_bytes(leaf_r, ei_r)) - return 0; - } - - inconsistent_snapshot_error(sctx, result, "extent"); - return -EIO; - } + /* + * We have found an extent item that changed without the inode item + * having changed. This can happen either after relocation (where the + * disk_bytenr of an extent item is replaced at + * relocation.c:replace_file_extents()) or after deduplication into a + * file in both the parent and send snapshots (where an extent item can + * get modified or replaced with a new one). Note that deduplication + * updates the inode item, but it only changes the iversion (sequence + * field in the inode item) of the inode, so if a file is deduplicated + * the same amount of times in both the parent and send snapshots, its + * iversion becames the same in both snapshots, whence the inode item is + * the same on both snapshots. + */ + if (sctx->cur_ino != sctx->cmp_key->objectid) + return 0; if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) { if (result != BTRFS_COMPARE_TREE_DELETED) From cb2d3daddbfb6318d170e79aac1f7d5e4d49f0d7 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 25 Jul 2019 11:27:04 +0100 Subject: [PATCH 575/823] Btrfs: fix race leading to fs corruption after transaction abort When one transaction is finishing its commit, it is possible for another transaction to start and enter its initial commit phase as well. If the first ends up getting aborted, we have a small time window where the second transaction commit does not notice that the previous transaction aborted and ends up committing, writing a superblock that points to btrees that reference extent buffers (nodes and leafs) that were not persisted to disk. The consequence is that after mounting the filesystem again, we will be unable to load some btree nodes/leafs, either because the content on disk is either garbage (or just zeroes) or corresponds to the old content of a previouly COWed or deleted node/leaf, resulting in the well known error messages "parent transid verify failed on ...". The following sequence diagram illustrates how this can happen. CPU 1 CPU 2 btrfs_commit_transaction() (...) --> sets transaction state to TRANS_STATE_UNBLOCKED --> sets fs_info->running_transaction to NULL (...) btrfs_start_transaction() start_transaction() wait_current_trans() --> returns immediately because fs_info->running_transaction is NULL join_transaction() --> creates transaction N + 1 --> sets fs_info->running_transaction to transaction N + 1 --> adds transaction N + 1 to the fs_info->trans_list list --> returns transaction handle pointing to the new transaction N + 1 (...) btrfs_sync_file() btrfs_start_transaction() --> returns handle to transaction N + 1 (...) btrfs_write_and_wait_transaction() --> writeback of some extent buffer fails, returns an error btrfs_handle_fs_error() --> sets BTRFS_FS_STATE_ERROR in fs_info->fs_state --> jumps to label "scrub_continue" cleanup_transaction() btrfs_abort_transaction(N) --> sets BTRFS_FS_STATE_TRANS_ABORTED flag in fs_info->fs_state --> sets aborted field in the transaction and transaction handle structures, for transaction N only --> removes transaction from the list fs_info->trans_list btrfs_commit_transaction(N + 1) --> transaction N + 1 was not aborted, so it proceeds (...) --> sets the transaction's state to TRANS_STATE_COMMIT_START --> does not find the previous transaction (N) in the fs_info->trans_list, so it doesn't know that transaction was aborted, and the commit of transaction N + 1 proceeds (...) --> sets transaction N + 1 state to TRANS_STATE_UNBLOCKED btrfs_write_and_wait_transaction() --> succeeds writing all extent buffers created in the transaction N + 1 write_all_supers() --> succeeds --> we now have a superblock on disk that points to trees that refer to at least one extent buffer that was never persisted So fix this by updating the transaction commit path to check if the flag BTRFS_FS_STATE_TRANS_ABORTED is set on fs_info->fs_state if after setting the transaction to the TRANS_STATE_COMMIT_START we do not find any previous transaction in the fs_info->trans_list. If the flag is set, just fail the transaction commit with -EROFS, as we do in other places. The exact error code for the previous transaction abort was already logged and reported. Fixes: 49b25e0540904b ("btrfs: enhance transaction abort infrastructure") CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/transaction.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 3b8ae1a8f02d..39b7bcde3c6f 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2037,6 +2037,16 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) } } else { spin_unlock(&fs_info->trans_lock); + /* + * The previous transaction was aborted and was already removed + * from the list of transactions at fs_info->trans_list. So we + * abort to prevent writing a new superblock that reflects a + * corrupt state (pointing to trees with unwritten nodes/leafs). + */ + if (test_bit(BTRFS_FS_STATE_TRANS_ABORTED, &fs_info->fs_state)) { + ret = -EROFS; + goto cleanup_transaction; + } } extwriter_counter_dec(cur_trans, trans->type); From a6d155d2e363f26290ffd50591169cb96c2a609e Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 29 Jul 2019 09:37:10 +0100 Subject: [PATCH 576/823] Btrfs: fix deadlock between fiemap and transaction commits The fiemap handler locks a file range that can have unflushed delalloc, and after locking the range, it tries to attach to a running transaction. If the running transaction started its commit, that is, it is in state TRANS_STATE_COMMIT_START, and either the filesystem was mounted with the flushoncommit option or the transaction is creating a snapshot for the subvolume that contains the file that fiemap is operating on, we end up deadlocking. This happens because fiemap is blocked on the transaction, waiting for it to complete, and the transaction is waiting for the flushed dealloc to complete, which requires locking the file range that the fiemap task already locked. The following stack traces serve as an example of when this deadlock happens: (...) [404571.515510] Workqueue: btrfs-endio-write btrfs_endio_write_helper [btrfs] [404571.515956] Call Trace: [404571.516360] ? __schedule+0x3ae/0x7b0 [404571.516730] schedule+0x3a/0xb0 [404571.517104] lock_extent_bits+0x1ec/0x2a0 [btrfs] [404571.517465] ? remove_wait_queue+0x60/0x60 [404571.517832] btrfs_finish_ordered_io+0x292/0x800 [btrfs] [404571.518202] normal_work_helper+0xea/0x530 [btrfs] [404571.518566] process_one_work+0x21e/0x5c0 [404571.518990] worker_thread+0x4f/0x3b0 [404571.519413] ? process_one_work+0x5c0/0x5c0 [404571.519829] kthread+0x103/0x140 [404571.520191] ? kthread_create_worker_on_cpu+0x70/0x70 [404571.520565] ret_from_fork+0x3a/0x50 [404571.520915] kworker/u8:6 D 0 31651 2 0x80004000 [404571.521290] Workqueue: btrfs-flush_delalloc btrfs_flush_delalloc_helper [btrfs] (...) [404571.537000] fsstress D 0 13117 13115 0x00004000 [404571.537263] Call Trace: [404571.537524] ? __schedule+0x3ae/0x7b0 [404571.537788] schedule+0x3a/0xb0 [404571.538066] wait_current_trans+0xc8/0x100 [btrfs] [404571.538349] ? remove_wait_queue+0x60/0x60 [404571.538680] start_transaction+0x33c/0x500 [btrfs] [404571.539076] btrfs_check_shared+0xa3/0x1f0 [btrfs] [404571.539513] ? extent_fiemap+0x2ce/0x650 [btrfs] [404571.539866] extent_fiemap+0x2ce/0x650 [btrfs] [404571.540170] do_vfs_ioctl+0x526/0x6f0 [404571.540436] ksys_ioctl+0x70/0x80 [404571.540734] __x64_sys_ioctl+0x16/0x20 [404571.540997] do_syscall_64+0x60/0x1d0 [404571.541279] entry_SYSCALL_64_after_hwframe+0x49/0xbe (...) [404571.543729] btrfs D 0 14210 14208 0x00004000 [404571.544023] Call Trace: [404571.544275] ? __schedule+0x3ae/0x7b0 [404571.544526] ? wait_for_completion+0x112/0x1a0 [404571.544795] schedule+0x3a/0xb0 [404571.545064] schedule_timeout+0x1ff/0x390 [404571.545351] ? lock_acquire+0xa6/0x190 [404571.545638] ? wait_for_completion+0x49/0x1a0 [404571.545890] ? wait_for_completion+0x112/0x1a0 [404571.546228] wait_for_completion+0x131/0x1a0 [404571.546503] ? wake_up_q+0x70/0x70 [404571.546775] btrfs_wait_ordered_extents+0x27c/0x400 [btrfs] [404571.547159] btrfs_commit_transaction+0x3b0/0xae0 [btrfs] [404571.547449] ? btrfs_mksubvol+0x4a4/0x640 [btrfs] [404571.547703] ? remove_wait_queue+0x60/0x60 [404571.547969] btrfs_mksubvol+0x605/0x640 [btrfs] [404571.548226] ? __sb_start_write+0xd4/0x1c0 [404571.548512] ? mnt_want_write_file+0x24/0x50 [404571.548789] btrfs_ioctl_snap_create_transid+0x169/0x1a0 [btrfs] [404571.549048] btrfs_ioctl_snap_create_v2+0x11d/0x170 [btrfs] [404571.549307] btrfs_ioctl+0x133f/0x3150 [btrfs] [404571.549549] ? mem_cgroup_charge_statistics+0x4c/0xd0 [404571.549792] ? mem_cgroup_commit_charge+0x84/0x4b0 [404571.550064] ? __handle_mm_fault+0xe3e/0x11f0 [404571.550306] ? do_raw_spin_unlock+0x49/0xc0 [404571.550608] ? _raw_spin_unlock+0x24/0x30 [404571.550976] ? __handle_mm_fault+0xedf/0x11f0 [404571.551319] ? do_vfs_ioctl+0xa2/0x6f0 [404571.551659] ? btrfs_ioctl_get_supported_features+0x30/0x30 [btrfs] [404571.552087] do_vfs_ioctl+0xa2/0x6f0 [404571.552355] ksys_ioctl+0x70/0x80 [404571.552621] __x64_sys_ioctl+0x16/0x20 [404571.552864] do_syscall_64+0x60/0x1d0 [404571.553104] entry_SYSCALL_64_after_hwframe+0x49/0xbe (...) If we were joining the transaction instead of attaching to it, we would not risk a deadlock because a join only blocks if the transaction is in a state greater then or equals to TRANS_STATE_COMMIT_DOING, and the delalloc flush performed by a transaction is done before it reaches that state, when it is in the state TRANS_STATE_COMMIT_START. However a transaction join is intended for use cases where we do modify the filesystem, and fiemap only needs to peek at delayed references from the current transaction in order to determine if extents are shared, and, besides that, when there is no current transaction or when it blocks to wait for a current committing transaction to complete, it creates a new transaction without reserving any space. Such unnecessary transactions, besides doing unnecessary IO, can cause transaction aborts (-ENOSPC) and unnecessary rotation of the precious backup roots. So fix this by adding a new transaction join variant, named join_nostart, which behaves like the regular join, but it does not create a transaction when none currently exists or after waiting for a committing transaction to complete. Fixes: 03628cdbc64db6 ("Btrfs: do not start a transaction during fiemap") Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/backref.c | 2 +- fs/btrfs/transaction.c | 22 ++++++++++++++++++---- fs/btrfs/transaction.h | 3 +++ 3 files changed, 22 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 89116afda7a2..e5d85311d5d5 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1483,7 +1483,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr, ulist_init(roots); ulist_init(tmp); - trans = btrfs_attach_transaction(root); + trans = btrfs_join_transaction_nostart(root); if (IS_ERR(trans)) { if (PTR_ERR(trans) != -ENOENT && PTR_ERR(trans) != -EROFS) { ret = PTR_ERR(trans); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 39b7bcde3c6f..e3adb714c04b 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -28,15 +28,18 @@ static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = { [TRANS_STATE_COMMIT_START] = (__TRANS_START | __TRANS_ATTACH), [TRANS_STATE_COMMIT_DOING] = (__TRANS_START | __TRANS_ATTACH | - __TRANS_JOIN), + __TRANS_JOIN | + __TRANS_JOIN_NOSTART), [TRANS_STATE_UNBLOCKED] = (__TRANS_START | __TRANS_ATTACH | __TRANS_JOIN | - __TRANS_JOIN_NOLOCK), + __TRANS_JOIN_NOLOCK | + __TRANS_JOIN_NOSTART), [TRANS_STATE_COMPLETED] = (__TRANS_START | __TRANS_ATTACH | __TRANS_JOIN | - __TRANS_JOIN_NOLOCK), + __TRANS_JOIN_NOLOCK | + __TRANS_JOIN_NOSTART), }; void btrfs_put_transaction(struct btrfs_transaction *transaction) @@ -543,7 +546,8 @@ again: ret = join_transaction(fs_info, type); if (ret == -EBUSY) { wait_current_trans(fs_info); - if (unlikely(type == TRANS_ATTACH)) + if (unlikely(type == TRANS_ATTACH || + type == TRANS_JOIN_NOSTART)) ret = -ENOENT; } } while (ret == -EBUSY); @@ -659,6 +663,16 @@ struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root BTRFS_RESERVE_NO_FLUSH, true); } +/* + * Similar to regular join but it never starts a transaction when none is + * running or after waiting for the current one to finish. + */ +struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root) +{ + return start_transaction(root, 0, TRANS_JOIN_NOSTART, + BTRFS_RESERVE_NO_FLUSH, true); +} + /* * btrfs_attach_transaction() - catch the running transaction * diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 527ea94b57d9..2c5a6f6e5bb0 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -94,11 +94,13 @@ struct btrfs_transaction { #define __TRANS_JOIN (1U << 11) #define __TRANS_JOIN_NOLOCK (1U << 12) #define __TRANS_DUMMY (1U << 13) +#define __TRANS_JOIN_NOSTART (1U << 14) #define TRANS_START (__TRANS_START | __TRANS_FREEZABLE) #define TRANS_ATTACH (__TRANS_ATTACH) #define TRANS_JOIN (__TRANS_JOIN | __TRANS_FREEZABLE) #define TRANS_JOIN_NOLOCK (__TRANS_JOIN_NOLOCK) +#define TRANS_JOIN_NOSTART (__TRANS_JOIN_NOSTART) #define TRANS_EXTWRITERS (__TRANS_START | __TRANS_ATTACH) @@ -183,6 +185,7 @@ struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv( int min_factor); struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root); struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root); +struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root); struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root); struct btrfs_trans_handle *btrfs_attach_transaction_barrier( struct btrfs_root *root); From cfb21b11b891b08b79be07be57c40a85bb926668 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 12 Jun 2019 11:09:58 +0200 Subject: [PATCH 577/823] iwlwifi: mvm: disable TX-AMSDU on older NICs On older NICs, we occasionally see issues with A-MSDU support, where the commands in the FIFO get confused and then we see an assert EDC because the next command in the FIFO isn't TX. We've tried to isolate this issue and understand where it comes from, but haven't found any errors in building the A-MSDU in software. At least for now, disable A-MSDU support on older hardware so that users can use it again without fearing the assert. This fixes https://bugzilla.kernel.org/show_bug.cgi?id=203315. Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 55cd49ccbf0b..99fa440bc639 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -474,7 +474,19 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm) ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW); ieee80211_hw_set(hw, BUFF_MMPDU_TXQ); ieee80211_hw_set(hw, STA_MMPDU_TXQ); - ieee80211_hw_set(hw, TX_AMSDU); + /* + * On older devices, enabling TX A-MSDU occasionally leads to + * something getting messed up, the command read from the FIFO + * gets out of sync and isn't a TX command, so that we have an + * assert EDC. + * + * It's not clear where the bug is, but since we didn't used to + * support A-MSDU until moving the mac80211 iTXQs, just leave it + * for older devices. We also don't see this issue on any newer + * devices. + */ + if (mvm->cfg->device_family >= IWL_DEVICE_FAMILY_9000) + ieee80211_hw_set(hw, TX_AMSDU); ieee80211_hw_set(hw, TX_FRAG_LIST); if (iwl_mvm_has_tlc_offload(mvm)) { From 0f8084cdc1f9d4a6693ef4168167febb0918c6f6 Mon Sep 17 00:00:00 2001 From: Mordechay Goodstein Date: Thu, 13 Jun 2019 16:34:07 +0300 Subject: [PATCH 578/823] iwlwifi: mvm: avoid races in rate init and rate perform Rate perform uses the lq_sta table to calculate the next rate to scale while rate init resets the same table, Rate perform is done in soft irq context in parallel to rate init that can be called in case we are doing changes like AP changes BW or moving state for auth to assoc. Signed-off-by: Mordechay Goodstein Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/rs.c | 42 ++++++++++++++++++-- drivers/net/wireless/intel/iwlwifi/mvm/rs.h | 7 +++- drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 6 +++ drivers/net/wireless/intel/iwlwifi/mvm/sta.h | 1 + 4 files changed, 51 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index 8c9069f28a58..02b4ef92543f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -1197,6 +1197,27 @@ static u8 rs_get_tid(struct ieee80211_hdr *hdr) return tid; } +void iwl_mvm_rs_init_wk(struct work_struct *wk) +{ + struct iwl_mvm_sta *mvmsta = container_of(wk, struct iwl_mvm_sta, + rs_init_wk); + struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(mvmsta->vif); + struct ieee80211_sta *sta; + + rcu_read_lock(); + + sta = rcu_dereference(mvmvif->mvm->fw_id_to_mac_id[mvmsta->sta_id]); + if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) { + rcu_read_unlock(); + return; + } + + iwl_mvm_rs_rate_init(mvmvif->mvm, sta, mvmvif->phy_ctxt->channel->band, + true); + + rcu_read_unlock(); +} + void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, int tid, struct ieee80211_tx_info *info, bool ndp) { @@ -1269,7 +1290,7 @@ void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, (unsigned long)(lq_sta->last_tx + (IWL_MVM_RS_IDLE_TIMEOUT * HZ)))) { IWL_DEBUG_RATE(mvm, "Tx idle for too long. reinit rs\n"); - iwl_mvm_rs_rate_init(mvm, sta, info->band, true); + schedule_work(&mvmsta->rs_init_wk); return; } lq_sta->last_tx = jiffies; @@ -1442,16 +1463,24 @@ static void rs_drv_mac80211_tx_status(void *mvm_r, struct iwl_op_mode *op_mode = mvm_r; struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode); struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); - if (!iwl_mvm_sta_from_mac80211(sta)->vif) + if (!mvmsta->vif) return; if (!ieee80211_is_data(hdr->frame_control) || info->flags & IEEE80211_TX_CTL_NO_ACK) return; + /* If it's locked we are in middle of init flow + * just wait for next tx status to update the lq_sta data + */ + if (!mutex_trylock(&mvmsta->lq_sta.rs_drv.mutex)) + return; + iwl_mvm_rs_tx_status(mvm, sta, rs_get_tid(hdr), info, ieee80211_is_qos_nullfunc(hdr->frame_control)); + mutex_unlock(&mvmsta->lq_sta.rs_drv.mutex); } /* @@ -4132,10 +4161,15 @@ static const struct rate_control_ops rs_mvm_ops_drv = { void iwl_mvm_rs_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta, enum nl80211_band band, bool update) { - if (iwl_mvm_has_tlc_offload(mvm)) + if (iwl_mvm_has_tlc_offload(mvm)) { rs_fw_rate_init(mvm, sta, band, update); - else + } else { + struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); + + mutex_lock(&mvmsta->lq_sta.rs_drv.mutex); rs_drv_rate_init(mvm, sta, band, update); + mutex_unlock(&mvmsta->lq_sta.rs_drv.mutex); + } } int iwl_mvm_rate_control_register(void) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h index f7eb60dbaf20..086f47e2a4f0 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h @@ -4,7 +4,7 @@ * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2015 Intel Mobile Communications GmbH * Copyright(c) 2017 Intel Deutschland GmbH - * Copyright(c) 2018 Intel Corporation + * Copyright(c) 2018 - 2019 Intel Corporation * * Contact Information: * Intel Linux Wireless @@ -376,6 +376,9 @@ struct iwl_lq_sta { /* tx power reduce for this sta */ int tpc_reduce; + /* avoid races of reinit and update table from rx_tx */ + struct mutex mutex; + /* persistent fields - initialized only once - keep last! */ struct lq_sta_pers { #ifdef CONFIG_MAC80211_DEBUGFS @@ -440,6 +443,8 @@ struct iwl_mvm_sta; int iwl_mvm_tx_protection(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta, bool enable); +void iwl_mvm_rs_init_wk(struct work_struct *wk); + #ifdef CONFIG_IWLWIFI_DEBUGFS void iwl_mvm_reset_frame_stats(struct iwl_mvm *mvm); #endif diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index f545a737a92d..ac9bc65c4d15 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -1684,6 +1684,10 @@ int iwl_mvm_add_sta(struct iwl_mvm *mvm, */ if (iwl_mvm_has_tlc_offload(mvm)) iwl_mvm_rs_add_sta(mvm, mvm_sta); + else + mutex_init(&mvm_sta->lq_sta.rs_drv.mutex); + + INIT_WORK(&mvm_sta->rs_init_wk, iwl_mvm_rs_init_wk); iwl_mvm_toggle_tx_ant(mvm, &mvm_sta->tx_ant); @@ -1846,6 +1850,8 @@ int iwl_mvm_rm_sta(struct iwl_mvm *mvm, if (ret) return ret; + cancel_work_sync(&mvm_sta->rs_init_wk); + /* flush its queues here since we are freeing mvm_sta */ ret = iwl_mvm_flush_sta(mvm, mvm_sta, false, 0); if (ret) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h index 4487cc3e07c1..84139fc38c34 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h @@ -424,6 +424,7 @@ struct iwl_mvm_sta { struct iwl_lq_sta_rs_fw rs_fw; struct iwl_lq_sta rs_drv; } lq_sta; + struct work_struct rs_init_wk; struct ieee80211_vif *vif; struct iwl_mvm_key_pn __rcu *ptk_pn[4]; struct iwl_mvm_rxq_dup_data *dup_data; From 39bd984c203e86f3109b49c2a2e20677c4d3ab65 Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Mon, 24 Jun 2019 22:29:33 +0300 Subject: [PATCH 579/823] iwlwifi: mvm: don't send GEO_TX_POWER_LIMIT on version < 41 Firmware versions before 41 don't support the GEO_TX_POWER_LIMIT command, and sending it to the firmware will cause a firmware crash. We allow this via debugfs, so we need to return an error value in case it's not supported. This had already been fixed during init, when we send the command if the ACPI WGDS table is present. Fix it also for the other, userspace-triggered case. Cc: stable@vger.kernel.org Fixes: 7fe90e0e3d60 ("iwlwifi: mvm: refactor geo init") Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 22 ++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 1d608e9e9101..a837cf40afde 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -880,6 +880,17 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b) return iwl_mvm_send_cmd_pdu(mvm, REDUCE_TX_POWER_CMD, 0, len, &cmd); } +static bool iwl_mvm_sar_geo_support(struct iwl_mvm *mvm) +{ + /* + * The GEO_TX_POWER_LIMIT command is not supported on earlier + * firmware versions. Unfortunately, we don't have a TLV API + * flag to rely on, so rely on the major version which is in + * the first byte of ucode_ver. + */ + return IWL_UCODE_SERIAL(mvm->fw->ucode_ver) >= 41; +} + int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm) { struct iwl_geo_tx_power_profiles_resp *resp; @@ -909,6 +920,9 @@ int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm) .data = { data }, }; + if (!iwl_mvm_sar_geo_support(mvm)) + return -EOPNOTSUPP; + ret = iwl_mvm_send_cmd(mvm, &cmd); if (ret) { IWL_ERR(mvm, "Failed to get geographic profile info %d\n", ret); @@ -934,13 +948,7 @@ static int iwl_mvm_sar_geo_init(struct iwl_mvm *mvm) int ret, i, j; u16 cmd_wide_id = WIDE_ID(PHY_OPS_GROUP, GEO_TX_POWER_LIMIT); - /* - * This command is not supported on earlier firmware versions. - * Unfortunately, we don't have a TLV API flag to rely on, so - * rely on the major version which is in the first byte of - * ucode_ver. - */ - if (IWL_UCODE_SERIAL(mvm->fw->ucode_ver) < 41) + if (!iwl_mvm_sar_geo_support(mvm)) return 0; ret = iwl_mvm_sar_get_wgds_table(mvm); From 6b2dbce549bb513316823af34e92f0bb2e0dbd55 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Mon, 24 Jun 2019 13:41:13 +0300 Subject: [PATCH 580/823] iwlwifi: mvm: prepare the ground for more RSS notifications We will need a new type of synchronization message going through all the RSS queues. Prepare the ground for this. Signed-off-by: Emmanuel Grumbach Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 2 +- drivers/net/wireless/intel/iwlwifi/mvm/sta.h | 6 ++++-- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index ac9bc65c4d15..23fd3108adb9 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -2427,7 +2427,7 @@ int iwl_mvm_rm_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) static void iwl_mvm_sync_rxq_del_ba(struct iwl_mvm *mvm, u8 baid) { - struct iwl_mvm_delba_notif notif = { + struct iwl_mvm_rss_sync_notif notif = { .metadata.type = IWL_MVM_RXQ_NOTIF_DEL_BA, .metadata.sync = 1, .delba.baid = baid, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h index 84139fc38c34..79d655b3fce0 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h @@ -343,9 +343,11 @@ struct iwl_mvm_delba_data { u32 baid; } __packed; -struct iwl_mvm_delba_notif { +struct iwl_mvm_rss_sync_notif { struct iwl_mvm_internal_rxq_notif metadata; - struct iwl_mvm_delba_data delba; + union { + struct iwl_mvm_delba_data delba; + }; } __packed; /** From c61b655a88a54d8690c1e134c47bc3f6d40d2dc3 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Mon, 24 Jun 2019 13:57:34 +0300 Subject: [PATCH 581/823] iwlwifi: mvm: add a new RSS sync notification for NSSN sync We will soon be using a new notification that will be initiated by the driver, sent to the firmware and sent back to all the RSS queues by the firmware. This new notification will be useful to synchronize the NSSN across all the queues. For now, don't send the notification, just add the code to handle it. Later patch will add the code to actually send it. While at it, validate the baid coming from the firmware to avoid accessing an array with a bad index in the driver. Signed-off-by: Emmanuel Grumbach Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- .../net/wireless/intel/iwlwifi/fw/api/rx.h | 2 + drivers/net/wireless/intel/iwlwifi/mvm/mvm.h | 4 +- drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 4 +- drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 84 ++++++++++++------- drivers/net/wireless/intel/iwlwifi/mvm/sta.h | 6 ++ 5 files changed, 64 insertions(+), 36 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h index d55312ef58c9..ed69eec4fcd9 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h @@ -812,10 +812,12 @@ struct iwl_rxq_sync_notification { * * @IWL_MVM_RXQ_EMPTY: empty sync notification * @IWL_MVM_RXQ_NOTIF_DEL_BA: notify RSS queues of delBA + * @IWL_MVM_RXQ_NSSN_SYNC: notify all the RSS queues with the new NSSN */ enum iwl_mvm_rxq_notif_type { IWL_MVM_RXQ_EMPTY, IWL_MVM_RXQ_NOTIF_DEL_BA, + IWL_MVM_RXQ_NSSN_SYNC, }; /** diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 48c77af54e99..c1e8b4766b0c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -1665,8 +1665,8 @@ void iwl_mvm_rx_frame_release(struct iwl_mvm *mvm, struct napi_struct *napi, struct iwl_rx_cmd_buffer *rxb, int queue); int iwl_mvm_notify_rx_queue(struct iwl_mvm *mvm, u32 rxq_mask, const u8 *data, u32 count); -void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb, - int queue); +void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct napi_struct *napi, + struct iwl_rx_cmd_buffer *rxb, int queue); void iwl_mvm_rx_tx_cmd(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb); void iwl_mvm_mfu_assert_dump_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index d7d6f3398f86..4888054dc3d8 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -1088,7 +1088,7 @@ static void iwl_mvm_rx_mq(struct iwl_op_mode *op_mode, iwl_mvm_rx_mpdu_mq(mvm, napi, rxb, 0); else if (unlikely(cmd == WIDE_ID(DATA_PATH_GROUP, RX_QUEUES_NOTIFICATION))) - iwl_mvm_rx_queue_notif(mvm, rxb, 0); + iwl_mvm_rx_queue_notif(mvm, napi, rxb, 0); else if (cmd == WIDE_ID(LEGACY_GROUP, FRAME_RELEASE)) iwl_mvm_rx_frame_release(mvm, napi, rxb, 0); else if (cmd == WIDE_ID(DATA_PATH_GROUP, RX_NO_DATA_NOTIF)) @@ -1812,7 +1812,7 @@ static void iwl_mvm_rx_mq_rss(struct iwl_op_mode *op_mode, iwl_mvm_rx_frame_release(mvm, napi, rxb, queue); else if (unlikely(cmd == WIDE_ID(DATA_PATH_GROUP, RX_QUEUES_NOTIFICATION))) - iwl_mvm_rx_queue_notif(mvm, rxb, queue); + iwl_mvm_rx_queue_notif(mvm, napi, rxb, queue); else if (likely(cmd == WIDE_ID(LEGACY_GROUP, REPLY_RX_MPDU_CMD))) iwl_mvm_rx_mpdu_mq(mvm, napi, rxb, queue); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 64f950501287..bf097329efa2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -665,8 +665,51 @@ out: rcu_read_unlock(); } -void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb, - int queue) +static void iwl_mvm_release_frames_from_notif(struct iwl_mvm *mvm, + struct napi_struct *napi, + u8 baid, u16 nssn, int queue) +{ + struct ieee80211_sta *sta; + struct iwl_mvm_reorder_buffer *reorder_buf; + struct iwl_mvm_baid_data *ba_data; + + IWL_DEBUG_HT(mvm, "Frame release notification for BAID %u, NSSN %d\n", + baid, nssn); + + if (WARN_ON_ONCE(baid == IWL_RX_REORDER_DATA_INVALID_BAID || + baid >= ARRAY_SIZE(mvm->baid_map))) + return; + + rcu_read_lock(); + + ba_data = rcu_dereference(mvm->baid_map[baid]); + if (WARN_ON_ONCE(!ba_data)) + goto out; + + sta = rcu_dereference(mvm->fw_id_to_mac_id[ba_data->sta_id]); + if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) + goto out; + + reorder_buf = &ba_data->reorder_buf[queue]; + + spin_lock_bh(&reorder_buf->lock); + iwl_mvm_release_frames(mvm, sta, napi, ba_data, reorder_buf, nssn); + spin_unlock_bh(&reorder_buf->lock); + +out: + rcu_read_unlock(); +} + +static void iwl_mvm_nssn_sync(struct iwl_mvm *mvm, + struct napi_struct *napi, int queue, + const struct iwl_mvm_nssn_sync_data *data) +{ + iwl_mvm_release_frames_from_notif(mvm, napi, data->baid, + data->nssn, queue); +} + +void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct napi_struct *napi, + struct iwl_rx_cmd_buffer *rxb, int queue) { struct iwl_rx_packet *pkt = rxb_addr(rxb); struct iwl_rxq_sync_notification *notif; @@ -687,6 +730,10 @@ void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb, case IWL_MVM_RXQ_NOTIF_DEL_BA: iwl_mvm_del_ba(mvm, queue, (void *)internal_notif->data); break; + case IWL_MVM_RXQ_NSSN_SYNC: + iwl_mvm_nssn_sync(mvm, napi, queue, + (void *)internal_notif->data); + break; default: WARN_ONCE(1, "Invalid identifier %d", internal_notif->type); } @@ -1840,40 +1887,13 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi, out: rcu_read_unlock(); } + void iwl_mvm_rx_frame_release(struct iwl_mvm *mvm, struct napi_struct *napi, struct iwl_rx_cmd_buffer *rxb, int queue) { struct iwl_rx_packet *pkt = rxb_addr(rxb); struct iwl_frame_release *release = (void *)pkt->data; - struct ieee80211_sta *sta; - struct iwl_mvm_reorder_buffer *reorder_buf; - struct iwl_mvm_baid_data *ba_data; - int baid = release->baid; - - IWL_DEBUG_HT(mvm, "Frame release notification for BAID %u, NSSN %d\n", - release->baid, le16_to_cpu(release->nssn)); - - if (WARN_ON_ONCE(baid == IWL_RX_REORDER_DATA_INVALID_BAID)) - return; - - rcu_read_lock(); - - ba_data = rcu_dereference(mvm->baid_map[baid]); - if (WARN_ON_ONCE(!ba_data)) - goto out; - - sta = rcu_dereference(mvm->fw_id_to_mac_id[ba_data->sta_id]); - if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) - goto out; - - reorder_buf = &ba_data->reorder_buf[queue]; - - spin_lock_bh(&reorder_buf->lock); - iwl_mvm_release_frames(mvm, sta, napi, ba_data, reorder_buf, - le16_to_cpu(release->nssn)); - spin_unlock_bh(&reorder_buf->lock); - -out: - rcu_read_unlock(); + iwl_mvm_release_frames_from_notif(mvm, napi, release->baid, + le16_to_cpu(release->nssn), queue); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h index 79d655b3fce0..4823c06e6909 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h @@ -343,10 +343,16 @@ struct iwl_mvm_delba_data { u32 baid; } __packed; +struct iwl_mvm_nssn_sync_data { + u32 baid; + u32 nssn; +} __packed; + struct iwl_mvm_rss_sync_notif { struct iwl_mvm_internal_rxq_notif metadata; union { struct iwl_mvm_delba_data delba; + struct iwl_mvm_nssn_sync_data nssn_sync; }; } __packed; From 521dc6c7c74e88fbd02947e4e50a5cb0d49b4395 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Tue, 25 Jun 2019 09:14:14 +0300 Subject: [PATCH 582/823] iwlwiif: mvm: refactor iwl_mvm_notify_rx_queue Instead of allocating memory for which we have an upper limit, use a small buffer on stack. Signed-off-by: Emmanuel Grumbach Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/fw/api/rx.h | 1 - drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 17 +++++++++-------- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h index ed69eec4fcd9..9b0bb89599fc 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h @@ -776,7 +776,6 @@ struct iwl_rss_config_cmd { u8 indirection_table[IWL_RSS_INDIRECTION_TABLE_SIZE]; } __packed; /* RSS_CONFIG_CMD_API_S_VER_1 */ -#define IWL_MULTI_QUEUE_SYNC_MSG_MAX_SIZE 128 #define IWL_MULTI_QUEUE_SYNC_SENDER_POS 0 #define IWL_MULTI_QUEUE_SYNC_SENDER_MSK 0xf diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index bf097329efa2..16078aa7c95f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -465,18 +465,20 @@ static bool iwl_mvm_is_dup(struct ieee80211_sta *sta, int queue, int iwl_mvm_notify_rx_queue(struct iwl_mvm *mvm, u32 rxq_mask, const u8 *data, u32 count) { - struct iwl_rxq_sync_cmd *cmd; + u8 buf[sizeof(struct iwl_rxq_sync_cmd) + + sizeof(struct iwl_mvm_rss_sync_notif)]; + struct iwl_rxq_sync_cmd *cmd = (void *)buf; u32 data_size = sizeof(*cmd) + count; int ret; - /* should be DWORD aligned */ - if (WARN_ON(count & 3 || count > IWL_MULTI_QUEUE_SYNC_MSG_MAX_SIZE)) + /* + * size must be a multiple of DWORD + * Ensure we don't overflow buf + */ + if (WARN_ON(count & 3 || + count > sizeof(struct iwl_mvm_rss_sync_notif))) return -EINVAL; - cmd = kzalloc(data_size, GFP_KERNEL); - if (!cmd) - return -ENOMEM; - cmd->rxq_mask = cpu_to_le32(rxq_mask); cmd->count = cpu_to_le32(count); cmd->flags = 0; @@ -487,7 +489,6 @@ int iwl_mvm_notify_rx_queue(struct iwl_mvm *mvm, u32 rxq_mask, TRIGGER_RX_QUEUES_NOTIF_CMD), 0, data_size, cmd); - kfree(cmd); return ret; } From 3c514bf831ac12356b695ff054bef641b9e99593 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Mon, 24 Jun 2019 16:26:24 +0300 Subject: [PATCH 583/823] iwlwifi: mvm: add a loose synchronization of the NSSN across Rx queues In order to support MSI-X efficiently, we want to avoid communication across Rx queues. Each Rx queue should have all the data it needs to process a packet. The reordering buffer is a challenge in the MSI-X world since we can have a single BA session whose packets are directed to different queues. This is why each queue has its own reordering buffer. The hardware is able to hint the driver whether we have a hole or not, which allows the driver to know whether it can release a packet or not. This indication is called NSSN. Roughly, if the packet's SN is lower than the NSSN, we can release the packet to the stack. The NSSN is the SN of the newest packet received without any holes + 1. This is working as long as we don't have packets that we release because of a timeout. When that happens, we could have taken the decision to release a packet after we have been waiting for its predecessor for too long. If this predecessor comes later, we have to drop it because we can't release packets out of order. In that case, the hardware will give us an indication that we can we release the packet (SN < NSSN), but the packet still needs to be dropped. This is why we sometimes need to ignore the NSSN and we track the head_sn in software. Here is a specific example of this: 1) Rx queue 1 got packets: 480, 482, 483 2) We release 480 to to the stack and wait for 481 3) NSSN is now 481 4) The timeout expires 5) We release 482 and 483, NSSN is still 480 6) 481 arrives its NSSN is 484. We need to drop 481 even if 481 < 484. This is why we'll update the head_sn to 484 at step 2. The flow now is: 1) Rx queue 1 got packets: 480, 482, 483 2) We release 480 to to the stack and wait for 481 3) NSSN is now 481 / head_sn is 481 4) The timeout expires 5) We release 482 and 483, NSSN is still 480 but head_sn is 484. 6) 481 arrives its NSSN is 484, but head_sn is 484 and we drop it. This code introduces another problem in case all the traffic goes well (no hole, no timeout): Rx queue 1: 0 -> 483 (head_sn = 484) Rx queue 2: 501 -> 4095 (head_sn = 0) Rx queue 2: 0 -> 480 (head_sn = 481) Rx queue 1: 481 but head_sn = 484 and we drop it. At this point, the SN of queue 1 is far behind: more than 4040 packets behind. Queue 1 will consider 481 "old" because 481 is in [501-64:501] whereas it is a very new packet. In order to fix that, send an Rx notification from time to time (twice across the full set of 4096 packets) to make sure no Rx queue is lagging too far behind. What will happen then is: Rx queue 1: 0 -> 483 (head_sn = 484) Rx queue 2: 501 -> 2047 (head_sn = 2048) Rx queue 1: Sync nofication (head_sn = 2048) Rx queue 2: 2048 -> 4095 (head_sn = 0) Rx queue 1: Sync notification (head_sn = 0) Rx queue 2: 1 -> 481 (head_sn = 482) Rx queue 1: 481 and head_sn = 0. In queue 1's data, head_sn is now 0, the packet coming in is 481, it'll understand that the new packet is new and it won't be dropped. Signed-off-by: Emmanuel Grumbach Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- .../net/wireless/intel/iwlwifi/mvm/mac80211.c | 5 +- drivers/net/wireless/intel/iwlwifi/mvm/mvm.h | 2 +- drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 64 +++++++++++++++---- 3 files changed, 56 insertions(+), 15 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 99fa440bc639..982682ec74fd 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -5053,7 +5053,6 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm, u32 qmask = BIT(mvm->trans->num_rx_queues) - 1; int ret; - lockdep_assert_held(&mvm->mutex); if (!iwl_mvm_has_new_rx_api(mvm)) return; @@ -5064,13 +5063,15 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm, atomic_set(&mvm->queue_sync_counter, mvm->trans->num_rx_queues); - ret = iwl_mvm_notify_rx_queue(mvm, qmask, (u8 *)notif, size); + ret = iwl_mvm_notify_rx_queue(mvm, qmask, (u8 *)notif, + size, !notif->sync); if (ret) { IWL_ERR(mvm, "Failed to trigger RX queues sync (%d)\n", ret); goto out; } if (notif->sync) { + lockdep_assert_held(&mvm->mutex); ret = wait_event_timeout(mvm->rx_sync_waitq, atomic_read(&mvm->queue_sync_counter) == 0 || iwl_mvm_is_radio_killed(mvm), diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index c1e8b4766b0c..fd1764df592f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -1664,7 +1664,7 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi, void iwl_mvm_rx_frame_release(struct iwl_mvm *mvm, struct napi_struct *napi, struct iwl_rx_cmd_buffer *rxb, int queue); int iwl_mvm_notify_rx_queue(struct iwl_mvm *mvm, u32 rxq_mask, - const u8 *data, u32 count); + const u8 *data, u32 count, bool async); void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct napi_struct *napi, struct iwl_rx_cmd_buffer *rxb, int queue); void iwl_mvm_rx_tx_cmd(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 16078aa7c95f..4f4fdaf49eef 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -463,7 +463,7 @@ static bool iwl_mvm_is_dup(struct ieee80211_sta *sta, int queue, } int iwl_mvm_notify_rx_queue(struct iwl_mvm *mvm, u32 rxq_mask, - const u8 *data, u32 count) + const u8 *data, u32 count, bool async) { u8 buf[sizeof(struct iwl_rxq_sync_cmd) + sizeof(struct iwl_mvm_rss_sync_notif)]; @@ -487,7 +487,7 @@ int iwl_mvm_notify_rx_queue(struct iwl_mvm *mvm, u32 rxq_mask, ret = iwl_mvm_send_cmd_pdu(mvm, WIDE_ID(DATA_PATH_GROUP, TRIGGER_RX_QUEUES_NOTIF_CMD), - 0, data_size, cmd); + async ? CMD_ASYNC : 0, data_size, cmd); return ret; } @@ -504,6 +504,18 @@ static bool iwl_mvm_is_sn_less(u16 sn1, u16 sn2, u16 buffer_size) !ieee80211_sn_less(sn1, sn2 - buffer_size); } +static void iwl_mvm_sync_nssn(struct iwl_mvm *mvm, u8 baid, u16 nssn) +{ + struct iwl_mvm_rss_sync_notif notif = { + .metadata.type = IWL_MVM_RXQ_NSSN_SYNC, + .metadata.sync = 0, + .nssn_sync.baid = baid, + .nssn_sync.nssn = nssn, + }; + + iwl_mvm_sync_rx_queues_internal(mvm, (void *)¬if, sizeof(notif)); +} + #define RX_REORDER_BUF_TIMEOUT_MQ (HZ / 10) static void iwl_mvm_release_frames(struct iwl_mvm *mvm, @@ -511,7 +523,7 @@ static void iwl_mvm_release_frames(struct iwl_mvm *mvm, struct napi_struct *napi, struct iwl_mvm_baid_data *baid_data, struct iwl_mvm_reorder_buffer *reorder_buf, - u16 nssn) + u16 nssn, bool sync_rss) { struct iwl_mvm_reorder_buf_entry *entries = &baid_data->entries[reorder_buf->queue * @@ -530,6 +542,8 @@ static void iwl_mvm_release_frames(struct iwl_mvm *mvm, struct sk_buff *skb; ssn = ieee80211_sn_inc(ssn); + if (sync_rss && (ssn == 2048 || ssn == 0)) + iwl_mvm_sync_nssn(mvm, baid_data->baid, ssn); /* * Empty the list. Will have more than one frame for A-MSDU. @@ -616,7 +630,8 @@ void iwl_mvm_reorder_timer_expired(struct timer_list *t) sta_id, sn); iwl_mvm_event_frame_timeout_callback(buf->mvm, mvmsta->vif, sta, baid_data->tid); - iwl_mvm_release_frames(buf->mvm, sta, NULL, baid_data, buf, sn); + iwl_mvm_release_frames(buf->mvm, sta, NULL, baid_data, + buf, sn, true); rcu_read_unlock(); } else { /* @@ -658,7 +673,8 @@ static void iwl_mvm_del_ba(struct iwl_mvm *mvm, int queue, spin_lock_bh(&reorder_buf->lock); iwl_mvm_release_frames(mvm, sta, NULL, ba_data, reorder_buf, ieee80211_sn_add(reorder_buf->head_sn, - reorder_buf->buf_size)); + reorder_buf->buf_size), + false); spin_unlock_bh(&reorder_buf->lock); del_timer_sync(&reorder_buf->reorder_timer); @@ -694,7 +710,8 @@ static void iwl_mvm_release_frames_from_notif(struct iwl_mvm *mvm, reorder_buf = &ba_data->reorder_buf[queue]; spin_lock_bh(&reorder_buf->lock); - iwl_mvm_release_frames(mvm, sta, napi, ba_data, reorder_buf, nssn); + iwl_mvm_release_frames(mvm, sta, napi, ba_data, + reorder_buf, nssn, false); spin_unlock_bh(&reorder_buf->lock); out: @@ -833,7 +850,8 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, } if (ieee80211_is_back_req(hdr->frame_control)) { - iwl_mvm_release_frames(mvm, sta, napi, baid_data, buffer, nssn); + iwl_mvm_release_frames(mvm, sta, napi, baid_data, + buffer, nssn, false); goto drop; } @@ -842,7 +860,10 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, * If the SN is smaller than the NSSN it might need to first go into * the reorder buffer, in which case we just release up to it and the * rest of the function will take care of storing it and releasing up to - * the nssn + * the nssn. + * This should not happen. This queue has been lagging and it should + * have been updated by a IWL_MVM_RXQ_NSSN_SYNC notification. Be nice + * and update the other queues. */ if (!iwl_mvm_is_sn_less(nssn, buffer->head_sn + buffer->buf_size, buffer->buf_size) || @@ -850,7 +871,7 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, u16 min_sn = ieee80211_sn_less(sn, nssn) ? sn : nssn; iwl_mvm_release_frames(mvm, sta, napi, baid_data, buffer, - min_sn); + min_sn, true); } /* drop any oudated packets */ @@ -861,8 +882,23 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, if (!buffer->num_stored && ieee80211_sn_less(sn, nssn)) { if (iwl_mvm_is_sn_less(buffer->head_sn, nssn, buffer->buf_size) && - (!amsdu || last_subframe)) + (!amsdu || last_subframe)) { + /* + * If we crossed the 2048 or 0 SN, notify all the + * queues. This is done in order to avoid having a + * head_sn that lags behind for too long. When that + * happens, we can get to a situation where the head_sn + * is within the interval [nssn - buf_size : nssn] + * which will make us think that the nssn is a packet + * that we already freed because of the reordering + * buffer and we will ignore it. So maintain the + * head_sn somewhat updated across all the queues: + * when it crosses 0 and 2048. + */ + if (sn == 2048 || sn == 0) + iwl_mvm_sync_nssn(mvm, baid, sn); buffer->head_sn = nssn; + } /* No need to update AMSDU last SN - we are moving the head */ spin_unlock_bh(&buffer->lock); return false; @@ -877,8 +913,11 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, * while technically there is no hole and we can move forward. */ if (!buffer->num_stored && sn == buffer->head_sn) { - if (!amsdu || last_subframe) + if (!amsdu || last_subframe) { + if (sn == 2048 || sn == 0) + iwl_mvm_sync_nssn(mvm, baid, sn); buffer->head_sn = ieee80211_sn_inc(buffer->head_sn); + } /* No need to update AMSDU last SN - we are moving the head */ spin_unlock_bh(&buffer->lock); return false; @@ -923,7 +962,8 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, * release notification with up to date NSSN. */ if (!amsdu || last_subframe) - iwl_mvm_release_frames(mvm, sta, napi, baid_data, buffer, nssn); + iwl_mvm_release_frames(mvm, sta, napi, baid_data, + buffer, nssn, true); spin_unlock_bh(&buffer->lock); return true; From 23babdf06779482a65c5072a145d826a62979534 Mon Sep 17 00:00:00 2001 From: Gregory Greenman Date: Tue, 25 Jun 2019 11:42:49 +0300 Subject: [PATCH 584/823] iwlwifi: mvm: add a wrapper around rs_tx_status to handle locks iwl_mvm_rs_tx_status can be called from two places in the code, but the mutex is taken only on one of the calls. Split it into a wrapper taking locks and an internal __iwl_mvm_rs_tx_status function. Signed-off-by: Gregory Greenman Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/rs.c | 28 ++++++++++++++------- 1 file changed, 19 insertions(+), 9 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index 02b4ef92543f..b50a47e86ef0 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -1218,8 +1218,10 @@ void iwl_mvm_rs_init_wk(struct work_struct *wk) rcu_read_unlock(); } -void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, - int tid, struct ieee80211_tx_info *info, bool ndp) +static void __iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, + struct ieee80211_sta *sta, + int tid, struct ieee80211_tx_info *info, + bool ndp) { int legacy_success; int retries; @@ -1451,6 +1453,21 @@ done: rs_rate_scale_perform(mvm, sta, lq_sta, tid, ndp); } +void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, + int tid, struct ieee80211_tx_info *info, bool ndp) +{ + struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); + + /* If it's locked we are in middle of init flow + * just wait for next tx status to update the lq_sta data + */ + if (!mutex_trylock(&mvmsta->lq_sta.rs_drv.mutex)) + return; + + __iwl_mvm_rs_tx_status(mvm, sta, tid, info, ndp); + mutex_unlock(&mvmsta->lq_sta.rs_drv.mutex); +} + /* * mac80211 sends us Tx status */ @@ -1472,15 +1489,8 @@ static void rs_drv_mac80211_tx_status(void *mvm_r, info->flags & IEEE80211_TX_CTL_NO_ACK) return; - /* If it's locked we are in middle of init flow - * just wait for next tx status to update the lq_sta data - */ - if (!mutex_trylock(&mvmsta->lq_sta.rs_drv.mutex)) - return; - iwl_mvm_rs_tx_status(mvm, sta, rs_get_tid(hdr), info, ieee80211_is_qos_nullfunc(hdr->frame_control)); - mutex_unlock(&mvmsta->lq_sta.rs_drv.mutex); } /* From 072b30642f90b01d139131ec7bf763778a3a3f41 Mon Sep 17 00:00:00 2001 From: Shahar S Matityahu Date: Thu, 13 Jun 2019 15:08:24 +0300 Subject: [PATCH 585/823] iwlwifi: dbg_ini: move iwl_dbg_tlv_load_bin out of debug override ifdef ini debug mode should work even if debug override is not defined. Signed-off-by: Shahar S Matityahu Fixes: 68f6f492c4fa ("iwlwifi: trans: support loading ini TLVs from external file") Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index 57d09049e615..d91686b9a540 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -1640,6 +1640,8 @@ struct iwl_drv *iwl_drv_start(struct iwl_trans *trans) init_completion(&drv->request_firmware_complete); INIT_LIST_HEAD(&drv->list); + iwl_load_fw_dbg_tlv(drv->trans->dev, drv->trans); + #ifdef CONFIG_IWLWIFI_DEBUGFS /* Create the device debugfs entries. */ drv->dbgfs_drv = debugfs_create_dir(dev_name(trans->dev), From abcbef5977df1fb61026ba429964cd6b9a085699 Mon Sep 17 00:00:00 2001 From: Shahar S Matityahu Date: Thu, 13 Jun 2019 15:11:24 +0300 Subject: [PATCH 586/823] iwlwifi: dbg_ini: move iwl_dbg_tlv_free outside of debugfs ifdef The driver should call iwl_dbg_tlv_free even if debugfs is not defined since ini mode does not depend on debugfs ifdef. Signed-off-by: Shahar S Matityahu Fixes: 68f6f492c4fa ("iwlwifi: trans: support loading ini TLVs from external file") Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index d91686b9a540..38672dd5aae9 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -1662,8 +1662,8 @@ struct iwl_drv *iwl_drv_start(struct iwl_trans *trans) err_fw: #ifdef CONFIG_IWLWIFI_DEBUGFS debugfs_remove_recursive(drv->dbgfs_drv); - iwl_fw_dbg_free(drv->trans); #endif + iwl_fw_dbg_free(drv->trans); kfree(drv); err: return ERR_PTR(ret); From 6569e7d36773956298ec1d5f4e6a2487913d2752 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 27 Jun 2019 09:44:50 +0200 Subject: [PATCH 587/823] iwlwifi: fix locking in delayed GTK setting This code clearly never could have worked, since it locks while already locked. Add an unlocked __iwl_mvm_mac_set_key() variant that doesn't do locking to fix that. Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- .../net/wireless/intel/iwlwifi/mvm/mac80211.c | 39 ++++++++++++------- 1 file changed, 26 insertions(+), 13 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 982682ec74fd..1c904b5226aa 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -207,11 +207,11 @@ static const struct cfg80211_pmsr_capabilities iwl_mvm_pmsr_capa = { }, }; -static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw, - enum set_key_cmd cmd, - struct ieee80211_vif *vif, - struct ieee80211_sta *sta, - struct ieee80211_key_conf *key); +static int __iwl_mvm_mac_set_key(struct ieee80211_hw *hw, + enum set_key_cmd cmd, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct ieee80211_key_conf *key); void iwl_mvm_ref(struct iwl_mvm *mvm, enum iwl_mvm_ref_type ref_type) { @@ -2738,7 +2738,7 @@ static int iwl_mvm_start_ap_ibss(struct ieee80211_hw *hw, mvmvif->ap_early_keys[i] = NULL; - ret = iwl_mvm_mac_set_key(hw, SET_KEY, vif, NULL, key); + ret = __iwl_mvm_mac_set_key(hw, SET_KEY, vif, NULL, key); if (ret) goto out_quota_failed; } @@ -3506,11 +3506,11 @@ static int iwl_mvm_mac_sched_scan_stop(struct ieee80211_hw *hw, return ret; } -static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw, - enum set_key_cmd cmd, - struct ieee80211_vif *vif, - struct ieee80211_sta *sta, - struct ieee80211_key_conf *key) +static int __iwl_mvm_mac_set_key(struct ieee80211_hw *hw, + enum set_key_cmd cmd, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct ieee80211_key_conf *key) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); @@ -3565,8 +3565,6 @@ static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw, return -EOPNOTSUPP; } - mutex_lock(&mvm->mutex); - switch (cmd) { case SET_KEY: if ((vif->type == NL80211_IFTYPE_ADHOC || @@ -3712,7 +3710,22 @@ static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw, ret = -EINVAL; } + return ret; +} + +static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw, + enum set_key_cmd cmd, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct ieee80211_key_conf *key) +{ + struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); + int ret; + + mutex_lock(&mvm->mutex); + ret = __iwl_mvm_mac_set_key(hw, cmd, vif, sta, key); mutex_unlock(&mvm->mutex); + return ret; } From b6cf28796756246f9e317eed6f63f1e2981e9817 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 1 Jul 2019 17:26:57 +0100 Subject: [PATCH 588/823] iwlwifi: mvm: fix comparison of u32 variable with less than zero The comparison of the u32 variable wgds_tbl_idx with less than zero is always going to be false because it is unsigned. Fix this by making wgds_tbl_idx a plain signed int. Addresses-Coverity: ("Unsigned compared against 0") Fixes: 4fd445a2c855 ("iwlwifi: mvm: Add log information about SAR status") Signed-off-by: Colin Ian King Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/nvm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c index 719f793b3487..a9bb43a2f27b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c @@ -620,7 +620,7 @@ void iwl_mvm_rx_chub_update_mcc(struct iwl_mvm *mvm, enum iwl_mcc_source src; char mcc[3]; struct ieee80211_regdomain *regd; - u32 wgds_tbl_idx; + int wgds_tbl_idx; lockdep_assert_held(&mvm->mutex); From cd4d6b0bcd51580efda9ae54ab7b2d630b4147dc Mon Sep 17 00:00:00 2001 From: Gregory Greenman Date: Sun, 30 Jun 2019 09:18:15 +0300 Subject: [PATCH 589/823] iwlwifi: mvm: send LQ command always ASYNC The only place where the command was sent as SYNC is during init and this is not really critical. This change is required for replacing RS mutex with a spinlock (in the subsequent patch), since SYNC comamnd requres sleeping and thus the flow cannot be done when holding a spinlock. Signed-off-by: Gregory Greenman Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/mvm.h | 2 +- drivers/net/wireless/intel/iwlwifi/mvm/rs.c | 23 ++++++++++--------- drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 2 +- .../net/wireless/intel/iwlwifi/mvm/utils.c | 4 ++-- 4 files changed, 16 insertions(+), 15 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index fd1764df592f..a263cc629d75 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -1813,7 +1813,7 @@ iwl_mvm_vif_dbgfs_clean(struct iwl_mvm *mvm, struct ieee80211_vif *vif) #endif /* CONFIG_IWLWIFI_DEBUGFS */ /* rate scaling */ -int iwl_mvm_send_lq_cmd(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq, bool sync); +int iwl_mvm_send_lq_cmd(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq); void iwl_mvm_update_frame_stats(struct iwl_mvm *mvm, u32 rate, bool agg); int rs_pretty_print_rate(char *buf, int bufsz, const u32 rate); void rs_update_last_rssi(struct iwl_mvm *mvm, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index b50a47e86ef0..bd977ec8629b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -1328,7 +1328,7 @@ static void __iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, IWL_DEBUG_RATE(mvm, "Too many rates mismatch. Send sync LQ. rs_state %d\n", lq_sta->rs_state); - iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq, false); + iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq); } /* Regardless, ignore this status info for outdated rate */ return; @@ -1390,7 +1390,8 @@ static void __iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, if (info->status.ampdu_ack_len == 0) info->status.ampdu_len = 1; - rs_collect_tlc_data(mvm, mvmsta, tid, curr_tbl, tx_resp_rate.index, + rs_collect_tlc_data(mvm, mvmsta, tid, curr_tbl, + tx_resp_rate.index, info->status.ampdu_len, info->status.ampdu_ack_len); @@ -1833,7 +1834,7 @@ static void rs_update_rate_tbl(struct iwl_mvm *mvm, struct iwl_scale_tbl_info *tbl) { rs_fill_lq_cmd(mvm, sta, lq_sta, &tbl->rate); - iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq, false); + iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq); } static bool rs_tweak_rate_tbl(struct iwl_mvm *mvm, @@ -2935,7 +2936,7 @@ void rs_update_last_rssi(struct iwl_mvm *mvm, static void rs_initialize_lq(struct iwl_mvm *mvm, struct ieee80211_sta *sta, struct iwl_lq_sta *lq_sta, - enum nl80211_band band, bool update) + enum nl80211_band band) { struct iwl_scale_tbl_info *tbl; struct rs_rate *rate; @@ -2965,7 +2966,7 @@ static void rs_initialize_lq(struct iwl_mvm *mvm, rs_set_expected_tpt_table(lq_sta, tbl); rs_fill_lq_cmd(mvm, sta, lq_sta, rate); /* TODO restore station should remember the lq cmd */ - iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq, !update); + iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq); } static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta, @@ -3214,7 +3215,7 @@ void iwl_mvm_update_frame_stats(struct iwl_mvm *mvm, u32 rate, bool agg) * Called after adding a new station to initialize rate scaling */ static void rs_drv_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta, - enum nl80211_band band, bool update) + enum nl80211_band band) { int i, j; struct ieee80211_hw *hw = mvm->hw; @@ -3294,7 +3295,7 @@ static void rs_drv_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta, #ifdef CONFIG_IWLWIFI_DEBUGFS iwl_mvm_reset_frame_stats(mvm); #endif - rs_initialize_lq(mvm, sta, lq_sta, band, update); + rs_initialize_lq(mvm, sta, lq_sta, band); } static void rs_drv_rate_update(void *mvm_r, @@ -3608,7 +3609,7 @@ static void rs_set_lq_ss_params(struct iwl_mvm *mvm, bfersta_ss_params &= ~LQ_SS_BFER_ALLOWED; bfersta_lq_cmd->ss_params = cpu_to_le32(bfersta_ss_params); - iwl_mvm_send_lq_cmd(mvm, bfersta_lq_cmd, false); + iwl_mvm_send_lq_cmd(mvm, bfersta_lq_cmd); ss_params |= LQ_SS_BFER_ALLOWED; IWL_DEBUG_RATE(mvm, @@ -3774,7 +3775,7 @@ static void rs_program_fix_rate(struct iwl_mvm *mvm, if (lq_sta->pers.dbg_fixed_rate) { rs_fill_lq_cmd(mvm, NULL, lq_sta, NULL); - iwl_mvm_send_lq_cmd(lq_sta->pers.drv, &lq_sta->lq, false); + iwl_mvm_send_lq_cmd(lq_sta->pers.drv, &lq_sta->lq); } } @@ -4177,7 +4178,7 @@ void iwl_mvm_rs_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta, struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); mutex_lock(&mvmsta->lq_sta.rs_drv.mutex); - rs_drv_rate_init(mvm, sta, band, update); + rs_drv_rate_init(mvm, sta, band); mutex_unlock(&mvmsta->lq_sta.rs_drv.mutex); } } @@ -4209,7 +4210,7 @@ static int rs_drv_tx_protection(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta, lq->flags &= ~LQ_FLAG_USE_RTS_MSK; } - return iwl_mvm_send_lq_cmd(mvm, lq, false); + return iwl_mvm_send_lq_cmd(mvm, lq); } /** diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 23fd3108adb9..88d16b5442e7 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -2978,7 +2978,7 @@ out: IWL_DEBUG_HT(mvm, "Tx aggregation enabled on ra = %pM tid = %d\n", sta->addr, tid); - return iwl_mvm_send_lq_cmd(mvm, &mvmsta->lq_sta.rs_drv.lq, false); + return iwl_mvm_send_lq_cmd(mvm, &mvmsta->lq_sta.rs_drv.lq); } static void iwl_mvm_unreserve_agg_queue(struct iwl_mvm *mvm, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c index 9ecd5f09615a..b8e20a01c192 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c @@ -653,12 +653,12 @@ int iwl_mvm_reconfig_scd(struct iwl_mvm *mvm, int queue, int fifo, int sta_id, * this case to clear the state indicating that station creation is in * progress. */ -int iwl_mvm_send_lq_cmd(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq, bool sync) +int iwl_mvm_send_lq_cmd(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq) { struct iwl_host_cmd cmd = { .id = LQ_CMD, .len = { sizeof(struct iwl_lq_cmd), }, - .flags = sync ? 0 : CMD_ASYNC, + .flags = CMD_ASYNC, .data = { lq, }, }; From f5d88fa334e6c8e2d840512ffbb30e3cb58d065b Mon Sep 17 00:00:00 2001 From: Gregory Greenman Date: Sun, 30 Jun 2019 09:42:57 +0300 Subject: [PATCH 590/823] iwlwifi: mvm: replace RS mutex with a spin_lock The solution with the worker still had a bug, as in order to get sta, rcu_read_lock should be used and thus no mutex can be used inside iwl_mvm_rs_rate_init. Also, spin_lock is a simpler solution, no need to spawn a dedicated worker. Signed-off-by: Gregory Greenman Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/rs.c | 530 +++++++++---------- drivers/net/wireless/intel/iwlwifi/mvm/rs.h | 6 +- drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 6 +- drivers/net/wireless/intel/iwlwifi/mvm/sta.h | 1 - 4 files changed, 258 insertions(+), 285 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index bd977ec8629b..3fa50b1955bb 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -1197,278 +1197,6 @@ static u8 rs_get_tid(struct ieee80211_hdr *hdr) return tid; } -void iwl_mvm_rs_init_wk(struct work_struct *wk) -{ - struct iwl_mvm_sta *mvmsta = container_of(wk, struct iwl_mvm_sta, - rs_init_wk); - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(mvmsta->vif); - struct ieee80211_sta *sta; - - rcu_read_lock(); - - sta = rcu_dereference(mvmvif->mvm->fw_id_to_mac_id[mvmsta->sta_id]); - if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) { - rcu_read_unlock(); - return; - } - - iwl_mvm_rs_rate_init(mvmvif->mvm, sta, mvmvif->phy_ctxt->channel->band, - true); - - rcu_read_unlock(); -} - -static void __iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, - struct ieee80211_sta *sta, - int tid, struct ieee80211_tx_info *info, - bool ndp) -{ - int legacy_success; - int retries; - int i; - struct iwl_lq_cmd *table; - u32 lq_hwrate; - struct rs_rate lq_rate, tx_resp_rate; - struct iwl_scale_tbl_info *curr_tbl, *other_tbl, *tmp_tbl; - u32 tlc_info = (uintptr_t)info->status.status_driver_data[0]; - u8 reduced_txp = tlc_info & RS_DRV_DATA_TXP_MSK; - u8 lq_color = RS_DRV_DATA_LQ_COLOR_GET(tlc_info); - u32 tx_resp_hwrate = (uintptr_t)info->status.status_driver_data[1]; - struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); - struct iwl_lq_sta *lq_sta = &mvmsta->lq_sta.rs_drv; - - /* Treat uninitialized rate scaling data same as non-existing. */ - if (!lq_sta) { - IWL_DEBUG_RATE(mvm, "Station rate scaling not created yet.\n"); - return; - } else if (!lq_sta->pers.drv) { - IWL_DEBUG_RATE(mvm, "Rate scaling not initialized yet.\n"); - return; - } - - /* This packet was aggregated but doesn't carry status info */ - if ((info->flags & IEEE80211_TX_CTL_AMPDU) && - !(info->flags & IEEE80211_TX_STAT_AMPDU)) - return; - - if (rs_rate_from_ucode_rate(tx_resp_hwrate, info->band, - &tx_resp_rate)) { - WARN_ON_ONCE(1); - return; - } - -#ifdef CONFIG_MAC80211_DEBUGFS - /* Disable last tx check if we are debugging with fixed rate but - * update tx stats */ - if (lq_sta->pers.dbg_fixed_rate) { - int index = tx_resp_rate.index; - enum rs_column column; - int attempts, success; - - column = rs_get_column_from_rate(&tx_resp_rate); - if (WARN_ONCE(column == RS_COLUMN_INVALID, - "Can't map rate 0x%x to column", - tx_resp_hwrate)) - return; - - if (info->flags & IEEE80211_TX_STAT_AMPDU) { - attempts = info->status.ampdu_len; - success = info->status.ampdu_ack_len; - } else { - attempts = info->status.rates[0].count; - success = !!(info->flags & IEEE80211_TX_STAT_ACK); - } - - lq_sta->pers.tx_stats[column][index].total += attempts; - lq_sta->pers.tx_stats[column][index].success += success; - - IWL_DEBUG_RATE(mvm, "Fixed rate 0x%x success %d attempts %d\n", - tx_resp_hwrate, success, attempts); - return; - } -#endif - - if (time_after(jiffies, - (unsigned long)(lq_sta->last_tx + - (IWL_MVM_RS_IDLE_TIMEOUT * HZ)))) { - IWL_DEBUG_RATE(mvm, "Tx idle for too long. reinit rs\n"); - schedule_work(&mvmsta->rs_init_wk); - return; - } - lq_sta->last_tx = jiffies; - - /* Ignore this Tx frame response if its initial rate doesn't match - * that of latest Link Quality command. There may be stragglers - * from a previous Link Quality command, but we're no longer interested - * in those; they're either from the "active" mode while we're trying - * to check "search" mode, or a prior "search" mode after we've moved - * to a new "search" mode (which might become the new "active" mode). - */ - table = &lq_sta->lq; - lq_hwrate = le32_to_cpu(table->rs_table[0]); - if (rs_rate_from_ucode_rate(lq_hwrate, info->band, &lq_rate)) { - WARN_ON_ONCE(1); - return; - } - - /* Here we actually compare this rate to the latest LQ command */ - if (lq_color != LQ_FLAG_COLOR_GET(table->flags)) { - IWL_DEBUG_RATE(mvm, - "tx resp color 0x%x does not match 0x%x\n", - lq_color, LQ_FLAG_COLOR_GET(table->flags)); - - /* - * Since rates mis-match, the last LQ command may have failed. - * After IWL_MISSED_RATE_MAX mis-matches, resync the uCode with - * ... driver. - */ - lq_sta->missed_rate_counter++; - if (lq_sta->missed_rate_counter > IWL_MVM_RS_MISSED_RATE_MAX) { - lq_sta->missed_rate_counter = 0; - IWL_DEBUG_RATE(mvm, - "Too many rates mismatch. Send sync LQ. rs_state %d\n", - lq_sta->rs_state); - iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq); - } - /* Regardless, ignore this status info for outdated rate */ - return; - } else - /* Rate did match, so reset the missed_rate_counter */ - lq_sta->missed_rate_counter = 0; - - if (!lq_sta->search_better_tbl) { - curr_tbl = &(lq_sta->lq_info[lq_sta->active_tbl]); - other_tbl = &(lq_sta->lq_info[1 - lq_sta->active_tbl]); - } else { - curr_tbl = &(lq_sta->lq_info[1 - lq_sta->active_tbl]); - other_tbl = &(lq_sta->lq_info[lq_sta->active_tbl]); - } - - if (WARN_ON_ONCE(!rs_rate_column_match(&lq_rate, &curr_tbl->rate))) { - IWL_DEBUG_RATE(mvm, - "Neither active nor search matches tx rate\n"); - tmp_tbl = &(lq_sta->lq_info[lq_sta->active_tbl]); - rs_dump_rate(mvm, &tmp_tbl->rate, "ACTIVE"); - tmp_tbl = &(lq_sta->lq_info[1 - lq_sta->active_tbl]); - rs_dump_rate(mvm, &tmp_tbl->rate, "SEARCH"); - rs_dump_rate(mvm, &lq_rate, "ACTUAL"); - - /* - * no matching table found, let's by-pass the data collection - * and continue to perform rate scale to find the rate table - */ - rs_stay_in_table(lq_sta, true); - goto done; - } - - /* - * Updating the frame history depends on whether packets were - * aggregated. - * - * For aggregation, all packets were transmitted at the same rate, the - * first index into rate scale table. - */ - if (info->flags & IEEE80211_TX_STAT_AMPDU) { - rs_collect_tpc_data(mvm, lq_sta, curr_tbl, tx_resp_rate.index, - info->status.ampdu_len, - info->status.ampdu_ack_len, - reduced_txp); - - /* ampdu_ack_len = 0 marks no BA was received. For TLC, treat - * it as a single frame loss as we don't want the success ratio - * to dip too quickly because a BA wasn't received. - * For TPC, there's no need for this optimisation since we want - * to recover very quickly from a bad power reduction and, - * therefore we'd like the success ratio to get an immediate hit - * when failing to get a BA, so we'd switch back to a lower or - * zero power reduction. When FW transmits agg with a rate - * different from the initial rate, it will not use reduced txp - * and will send BA notification twice (one empty with reduced - * txp equal to the value from LQ and one with reduced txp 0). - * We need to update counters for each txp level accordingly. - */ - if (info->status.ampdu_ack_len == 0) - info->status.ampdu_len = 1; - - rs_collect_tlc_data(mvm, mvmsta, tid, curr_tbl, - tx_resp_rate.index, - info->status.ampdu_len, - info->status.ampdu_ack_len); - - /* Update success/fail counts if not searching for new mode */ - if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) { - lq_sta->total_success += info->status.ampdu_ack_len; - lq_sta->total_failed += (info->status.ampdu_len - - info->status.ampdu_ack_len); - } - } else { - /* For legacy, update frame history with for each Tx retry. */ - retries = info->status.rates[0].count - 1; - /* HW doesn't send more than 15 retries */ - retries = min(retries, 15); - - /* The last transmission may have been successful */ - legacy_success = !!(info->flags & IEEE80211_TX_STAT_ACK); - /* Collect data for each rate used during failed TX attempts */ - for (i = 0; i <= retries; ++i) { - lq_hwrate = le32_to_cpu(table->rs_table[i]); - if (rs_rate_from_ucode_rate(lq_hwrate, info->band, - &lq_rate)) { - WARN_ON_ONCE(1); - return; - } - - /* - * Only collect stats if retried rate is in the same RS - * table as active/search. - */ - if (rs_rate_column_match(&lq_rate, &curr_tbl->rate)) - tmp_tbl = curr_tbl; - else if (rs_rate_column_match(&lq_rate, - &other_tbl->rate)) - tmp_tbl = other_tbl; - else - continue; - - rs_collect_tpc_data(mvm, lq_sta, tmp_tbl, - tx_resp_rate.index, 1, - i < retries ? 0 : legacy_success, - reduced_txp); - rs_collect_tlc_data(mvm, mvmsta, tid, tmp_tbl, - tx_resp_rate.index, 1, - i < retries ? 0 : legacy_success); - } - - /* Update success/fail counts if not searching for new mode */ - if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) { - lq_sta->total_success += legacy_success; - lq_sta->total_failed += retries + (1 - legacy_success); - } - } - /* The last TX rate is cached in lq_sta; it's set in if/else above */ - lq_sta->last_rate_n_flags = lq_hwrate; - IWL_DEBUG_RATE(mvm, "reduced txpower: %d\n", reduced_txp); -done: - /* See if there's a better rate or modulation mode to try. */ - if (sta->supp_rates[info->band]) - rs_rate_scale_perform(mvm, sta, lq_sta, tid, ndp); -} - -void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, - int tid, struct ieee80211_tx_info *info, bool ndp) -{ - struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); - - /* If it's locked we are in middle of init flow - * just wait for next tx status to update the lq_sta data - */ - if (!mutex_trylock(&mvmsta->lq_sta.rs_drv.mutex)) - return; - - __iwl_mvm_rs_tx_status(mvm, sta, tid, info, ndp); - mutex_unlock(&mvmsta->lq_sta.rs_drv.mutex); -} - /* * mac80211 sends us Tx status */ @@ -3226,6 +2954,8 @@ static void rs_drv_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta, struct ieee80211_supported_band *sband; unsigned long supp; /* must be unsigned long for for_each_set_bit */ + lockdep_assert_held(&mvmsta->lq_sta.rs_drv.pers.lock); + /* clear all non-persistent lq data */ memset(lq_sta, 0, offsetof(typeof(*lq_sta), pers)); @@ -3318,6 +3048,258 @@ static void rs_drv_rate_update(void *mvm_r, iwl_mvm_rs_rate_init(mvm, sta, sband->band, true); } +static void __iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, + struct ieee80211_sta *sta, + int tid, struct ieee80211_tx_info *info, + bool ndp) +{ + int legacy_success; + int retries; + int i; + struct iwl_lq_cmd *table; + u32 lq_hwrate; + struct rs_rate lq_rate, tx_resp_rate; + struct iwl_scale_tbl_info *curr_tbl, *other_tbl, *tmp_tbl; + u32 tlc_info = (uintptr_t)info->status.status_driver_data[0]; + u8 reduced_txp = tlc_info & RS_DRV_DATA_TXP_MSK; + u8 lq_color = RS_DRV_DATA_LQ_COLOR_GET(tlc_info); + u32 tx_resp_hwrate = (uintptr_t)info->status.status_driver_data[1]; + struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); + struct iwl_lq_sta *lq_sta = &mvmsta->lq_sta.rs_drv; + + /* Treat uninitialized rate scaling data same as non-existing. */ + if (!lq_sta) { + IWL_DEBUG_RATE(mvm, "Station rate scaling not created yet.\n"); + return; + } else if (!lq_sta->pers.drv) { + IWL_DEBUG_RATE(mvm, "Rate scaling not initialized yet.\n"); + return; + } + + /* This packet was aggregated but doesn't carry status info */ + if ((info->flags & IEEE80211_TX_CTL_AMPDU) && + !(info->flags & IEEE80211_TX_STAT_AMPDU)) + return; + + if (rs_rate_from_ucode_rate(tx_resp_hwrate, info->band, + &tx_resp_rate)) { + WARN_ON_ONCE(1); + return; + } + +#ifdef CONFIG_MAC80211_DEBUGFS + /* Disable last tx check if we are debugging with fixed rate but + * update tx stats + */ + if (lq_sta->pers.dbg_fixed_rate) { + int index = tx_resp_rate.index; + enum rs_column column; + int attempts, success; + + column = rs_get_column_from_rate(&tx_resp_rate); + if (WARN_ONCE(column == RS_COLUMN_INVALID, + "Can't map rate 0x%x to column", + tx_resp_hwrate)) + return; + + if (info->flags & IEEE80211_TX_STAT_AMPDU) { + attempts = info->status.ampdu_len; + success = info->status.ampdu_ack_len; + } else { + attempts = info->status.rates[0].count; + success = !!(info->flags & IEEE80211_TX_STAT_ACK); + } + + lq_sta->pers.tx_stats[column][index].total += attempts; + lq_sta->pers.tx_stats[column][index].success += success; + + IWL_DEBUG_RATE(mvm, "Fixed rate 0x%x success %d attempts %d\n", + tx_resp_hwrate, success, attempts); + return; + } +#endif + + if (time_after(jiffies, + (unsigned long)(lq_sta->last_tx + + (IWL_MVM_RS_IDLE_TIMEOUT * HZ)))) { + IWL_DEBUG_RATE(mvm, "Tx idle for too long. reinit rs\n"); + /* reach here only in case of driver RS, call directly + * the unlocked version + */ + rs_drv_rate_init(mvm, sta, info->band); + return; + } + lq_sta->last_tx = jiffies; + + /* Ignore this Tx frame response if its initial rate doesn't match + * that of latest Link Quality command. There may be stragglers + * from a previous Link Quality command, but we're no longer interested + * in those; they're either from the "active" mode while we're trying + * to check "search" mode, or a prior "search" mode after we've moved + * to a new "search" mode (which might become the new "active" mode). + */ + table = &lq_sta->lq; + lq_hwrate = le32_to_cpu(table->rs_table[0]); + if (rs_rate_from_ucode_rate(lq_hwrate, info->band, &lq_rate)) { + WARN_ON_ONCE(1); + return; + } + + /* Here we actually compare this rate to the latest LQ command */ + if (lq_color != LQ_FLAG_COLOR_GET(table->flags)) { + IWL_DEBUG_RATE(mvm, + "tx resp color 0x%x does not match 0x%x\n", + lq_color, LQ_FLAG_COLOR_GET(table->flags)); + + /* Since rates mis-match, the last LQ command may have failed. + * After IWL_MISSED_RATE_MAX mis-matches, resync the uCode with + * ... driver. + */ + lq_sta->missed_rate_counter++; + if (lq_sta->missed_rate_counter > IWL_MVM_RS_MISSED_RATE_MAX) { + lq_sta->missed_rate_counter = 0; + IWL_DEBUG_RATE(mvm, + "Too many rates mismatch. Send sync LQ. rs_state %d\n", + lq_sta->rs_state); + iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq); + } + /* Regardless, ignore this status info for outdated rate */ + return; + } + + /* Rate did match, so reset the missed_rate_counter */ + lq_sta->missed_rate_counter = 0; + + if (!lq_sta->search_better_tbl) { + curr_tbl = &lq_sta->lq_info[lq_sta->active_tbl]; + other_tbl = &lq_sta->lq_info[1 - lq_sta->active_tbl]; + } else { + curr_tbl = &lq_sta->lq_info[1 - lq_sta->active_tbl]; + other_tbl = &lq_sta->lq_info[lq_sta->active_tbl]; + } + + if (WARN_ON_ONCE(!rs_rate_column_match(&lq_rate, &curr_tbl->rate))) { + IWL_DEBUG_RATE(mvm, + "Neither active nor search matches tx rate\n"); + tmp_tbl = &lq_sta->lq_info[lq_sta->active_tbl]; + rs_dump_rate(mvm, &tmp_tbl->rate, "ACTIVE"); + tmp_tbl = &lq_sta->lq_info[1 - lq_sta->active_tbl]; + rs_dump_rate(mvm, &tmp_tbl->rate, "SEARCH"); + rs_dump_rate(mvm, &lq_rate, "ACTUAL"); + + /* no matching table found, let's by-pass the data collection + * and continue to perform rate scale to find the rate table + */ + rs_stay_in_table(lq_sta, true); + goto done; + } + + /* Updating the frame history depends on whether packets were + * aggregated. + * + * For aggregation, all packets were transmitted at the same rate, the + * first index into rate scale table. + */ + if (info->flags & IEEE80211_TX_STAT_AMPDU) { + rs_collect_tpc_data(mvm, lq_sta, curr_tbl, tx_resp_rate.index, + info->status.ampdu_len, + info->status.ampdu_ack_len, + reduced_txp); + + /* ampdu_ack_len = 0 marks no BA was received. For TLC, treat + * it as a single frame loss as we don't want the success ratio + * to dip too quickly because a BA wasn't received. + * For TPC, there's no need for this optimisation since we want + * to recover very quickly from a bad power reduction and, + * therefore we'd like the success ratio to get an immediate hit + * when failing to get a BA, so we'd switch back to a lower or + * zero power reduction. When FW transmits agg with a rate + * different from the initial rate, it will not use reduced txp + * and will send BA notification twice (one empty with reduced + * txp equal to the value from LQ and one with reduced txp 0). + * We need to update counters for each txp level accordingly. + */ + if (info->status.ampdu_ack_len == 0) + info->status.ampdu_len = 1; + + rs_collect_tlc_data(mvm, mvmsta, tid, curr_tbl, + tx_resp_rate.index, + info->status.ampdu_len, + info->status.ampdu_ack_len); + + /* Update success/fail counts if not searching for new mode */ + if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) { + lq_sta->total_success += info->status.ampdu_ack_len; + lq_sta->total_failed += (info->status.ampdu_len - + info->status.ampdu_ack_len); + } + } else { + /* For legacy, update frame history with for each Tx retry. */ + retries = info->status.rates[0].count - 1; + /* HW doesn't send more than 15 retries */ + retries = min(retries, 15); + + /* The last transmission may have been successful */ + legacy_success = !!(info->flags & IEEE80211_TX_STAT_ACK); + /* Collect data for each rate used during failed TX attempts */ + for (i = 0; i <= retries; ++i) { + lq_hwrate = le32_to_cpu(table->rs_table[i]); + if (rs_rate_from_ucode_rate(lq_hwrate, info->band, + &lq_rate)) { + WARN_ON_ONCE(1); + return; + } + + /* Only collect stats if retried rate is in the same RS + * table as active/search. + */ + if (rs_rate_column_match(&lq_rate, &curr_tbl->rate)) + tmp_tbl = curr_tbl; + else if (rs_rate_column_match(&lq_rate, + &other_tbl->rate)) + tmp_tbl = other_tbl; + else + continue; + + rs_collect_tpc_data(mvm, lq_sta, tmp_tbl, + tx_resp_rate.index, 1, + i < retries ? 0 : legacy_success, + reduced_txp); + rs_collect_tlc_data(mvm, mvmsta, tid, tmp_tbl, + tx_resp_rate.index, 1, + i < retries ? 0 : legacy_success); + } + + /* Update success/fail counts if not searching for new mode */ + if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) { + lq_sta->total_success += legacy_success; + lq_sta->total_failed += retries + (1 - legacy_success); + } + } + /* The last TX rate is cached in lq_sta; it's set in if/else above */ + lq_sta->last_rate_n_flags = lq_hwrate; + IWL_DEBUG_RATE(mvm, "reduced txpower: %d\n", reduced_txp); +done: + /* See if there's a better rate or modulation mode to try. */ + if (sta->supp_rates[info->band]) + rs_rate_scale_perform(mvm, sta, lq_sta, tid, ndp); +} + +void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, + int tid, struct ieee80211_tx_info *info, bool ndp) +{ + struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); + + /* If it's locked we are in middle of init flow + * just wait for next tx status to update the lq_sta data + */ + if (!spin_trylock(&mvmsta->lq_sta.rs_drv.pers.lock)) + return; + + __iwl_mvm_rs_tx_status(mvm, sta, tid, info, ndp); + spin_unlock(&mvmsta->lq_sta.rs_drv.pers.lock); +} + #ifdef CONFIG_MAC80211_DEBUGFS static void rs_build_rates_table_from_fixed(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq_cmd, @@ -4177,9 +4159,9 @@ void iwl_mvm_rs_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta, } else { struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); - mutex_lock(&mvmsta->lq_sta.rs_drv.mutex); + spin_lock(&mvmsta->lq_sta.rs_drv.pers.lock); rs_drv_rate_init(mvm, sta, band); - mutex_unlock(&mvmsta->lq_sta.rs_drv.mutex); + spin_unlock(&mvmsta->lq_sta.rs_drv.pers.lock); } } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h index 086f47e2a4f0..428642e66658 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h @@ -376,9 +376,6 @@ struct iwl_lq_sta { /* tx power reduce for this sta */ int tpc_reduce; - /* avoid races of reinit and update table from rx_tx */ - struct mutex mutex; - /* persistent fields - initialized only once - keep last! */ struct lq_sta_pers { #ifdef CONFIG_MAC80211_DEBUGFS @@ -393,6 +390,7 @@ struct iwl_lq_sta { s8 last_rssi; struct rs_rate_stats tx_stats[RS_COLUMN_COUNT][IWL_RATE_COUNT]; struct iwl_mvm *drv; + spinlock_t lock; /* for races in reinit/update table */ } pers; }; @@ -443,8 +441,6 @@ struct iwl_mvm_sta; int iwl_mvm_tx_protection(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta, bool enable); -void iwl_mvm_rs_init_wk(struct work_struct *wk); - #ifdef CONFIG_IWLWIFI_DEBUGFS void iwl_mvm_reset_frame_stats(struct iwl_mvm *mvm); #endif diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 88d16b5442e7..10f18536dd0d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -1685,9 +1685,7 @@ int iwl_mvm_add_sta(struct iwl_mvm *mvm, if (iwl_mvm_has_tlc_offload(mvm)) iwl_mvm_rs_add_sta(mvm, mvm_sta); else - mutex_init(&mvm_sta->lq_sta.rs_drv.mutex); - - INIT_WORK(&mvm_sta->rs_init_wk, iwl_mvm_rs_init_wk); + spin_lock_init(&mvm_sta->lq_sta.rs_drv.pers.lock); iwl_mvm_toggle_tx_ant(mvm, &mvm_sta->tx_ant); @@ -1850,8 +1848,6 @@ int iwl_mvm_rm_sta(struct iwl_mvm *mvm, if (ret) return ret; - cancel_work_sync(&mvm_sta->rs_init_wk); - /* flush its queues here since we are freeing mvm_sta */ ret = iwl_mvm_flush_sta(mvm, mvm_sta, false, 0); if (ret) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h index 4823c06e6909..8d70093847cb 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h @@ -432,7 +432,6 @@ struct iwl_mvm_sta { struct iwl_lq_sta_rs_fw rs_fw; struct iwl_lq_sta rs_drv; } lq_sta; - struct work_struct rs_init_wk; struct ieee80211_vif *vif; struct iwl_mvm_key_pn __rcu *ptk_pn[4]; struct iwl_mvm_rxq_dup_data *dup_data; From ecd09ddc1d14cca4f874151aed51a7feee3f765b Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Thu, 27 Jun 2019 21:50:24 +0300 Subject: [PATCH 591/823] iwlwifi: mvm: fix frame drop from the reordering buffer An earlier patch made sure that the queues are not lagging too far behind. This means that iwl_mvm_release_frames should not be called with a head_sn too far behind NSSN. Don't take the risk to change completely the entry condition to iwl_mvm_release_frames, but don't update the head_sn is the NSSN is more than 2048 packets ahead of us. Since this just cannot be right. This means that the scenario described here happened. We are queue 0. Q:0 Q:1 head_sn: 0 -> 2047 head_sn: 2048 Lots of packets arrive: head_sn: 2047 -> 2150 send NSSN_SYNC notification Handle notification from the firmware and do NOT move the head_sn back to 2048 Signed-off-by: Emmanuel Grumbach Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 44 ++++++++++++++----- 1 file changed, 33 insertions(+), 11 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 4f4fdaf49eef..854edd7d7103 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -518,12 +518,17 @@ static void iwl_mvm_sync_nssn(struct iwl_mvm *mvm, u8 baid, u16 nssn) #define RX_REORDER_BUF_TIMEOUT_MQ (HZ / 10) +enum iwl_mvm_release_flags { + IWL_MVM_RELEASE_SEND_RSS_SYNC = BIT(0), + IWL_MVM_RELEASE_FROM_RSS_SYNC = BIT(1), +}; + static void iwl_mvm_release_frames(struct iwl_mvm *mvm, struct ieee80211_sta *sta, struct napi_struct *napi, struct iwl_mvm_baid_data *baid_data, struct iwl_mvm_reorder_buffer *reorder_buf, - u16 nssn, bool sync_rss) + u16 nssn, u32 flags) { struct iwl_mvm_reorder_buf_entry *entries = &baid_data->entries[reorder_buf->queue * @@ -532,6 +537,18 @@ static void iwl_mvm_release_frames(struct iwl_mvm *mvm, lockdep_assert_held(&reorder_buf->lock); + /* + * We keep the NSSN not too far behind, if we are sync'ing it and it + * is more than 2048 ahead of us, it must be behind us. Discard it. + * This can happen if the queue that hit the 0 / 2048 seqno was lagging + * behind and this queue already processed packets. The next if + * would have caught cases where this queue would have processed less + * than 64 packets, but it may have processed more than 64 packets. + */ + if ((flags & IWL_MVM_RELEASE_FROM_RSS_SYNC) && + ieee80211_sn_less(nssn, ssn)) + goto set_timer; + /* ignore nssn smaller than head sn - this can happen due to timeout */ if (iwl_mvm_is_sn_less(nssn, ssn, reorder_buf->buf_size)) goto set_timer; @@ -542,7 +559,8 @@ static void iwl_mvm_release_frames(struct iwl_mvm *mvm, struct sk_buff *skb; ssn = ieee80211_sn_inc(ssn); - if (sync_rss && (ssn == 2048 || ssn == 0)) + if ((flags & IWL_MVM_RELEASE_SEND_RSS_SYNC) && + (ssn == 2048 || ssn == 0)) iwl_mvm_sync_nssn(mvm, baid_data->baid, ssn); /* @@ -631,7 +649,7 @@ void iwl_mvm_reorder_timer_expired(struct timer_list *t) iwl_mvm_event_frame_timeout_callback(buf->mvm, mvmsta->vif, sta, baid_data->tid); iwl_mvm_release_frames(buf->mvm, sta, NULL, baid_data, - buf, sn, true); + buf, sn, IWL_MVM_RELEASE_SEND_RSS_SYNC); rcu_read_unlock(); } else { /* @@ -674,7 +692,7 @@ static void iwl_mvm_del_ba(struct iwl_mvm *mvm, int queue, iwl_mvm_release_frames(mvm, sta, NULL, ba_data, reorder_buf, ieee80211_sn_add(reorder_buf->head_sn, reorder_buf->buf_size), - false); + 0); spin_unlock_bh(&reorder_buf->lock); del_timer_sync(&reorder_buf->reorder_timer); @@ -684,7 +702,8 @@ out: static void iwl_mvm_release_frames_from_notif(struct iwl_mvm *mvm, struct napi_struct *napi, - u8 baid, u16 nssn, int queue) + u8 baid, u16 nssn, int queue, + u32 flags) { struct ieee80211_sta *sta; struct iwl_mvm_reorder_buffer *reorder_buf; @@ -711,7 +730,7 @@ static void iwl_mvm_release_frames_from_notif(struct iwl_mvm *mvm, spin_lock_bh(&reorder_buf->lock); iwl_mvm_release_frames(mvm, sta, napi, ba_data, - reorder_buf, nssn, false); + reorder_buf, nssn, flags); spin_unlock_bh(&reorder_buf->lock); out: @@ -723,7 +742,8 @@ static void iwl_mvm_nssn_sync(struct iwl_mvm *mvm, const struct iwl_mvm_nssn_sync_data *data) { iwl_mvm_release_frames_from_notif(mvm, napi, data->baid, - data->nssn, queue); + data->nssn, queue, + IWL_MVM_RELEASE_FROM_RSS_SYNC); } void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct napi_struct *napi, @@ -851,7 +871,7 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, if (ieee80211_is_back_req(hdr->frame_control)) { iwl_mvm_release_frames(mvm, sta, napi, baid_data, - buffer, nssn, false); + buffer, nssn, 0); goto drop; } @@ -871,7 +891,7 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, u16 min_sn = ieee80211_sn_less(sn, nssn) ? sn : nssn; iwl_mvm_release_frames(mvm, sta, napi, baid_data, buffer, - min_sn, true); + min_sn, IWL_MVM_RELEASE_SEND_RSS_SYNC); } /* drop any oudated packets */ @@ -963,7 +983,8 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, */ if (!amsdu || last_subframe) iwl_mvm_release_frames(mvm, sta, napi, baid_data, - buffer, nssn, true); + buffer, nssn, + IWL_MVM_RELEASE_SEND_RSS_SYNC); spin_unlock_bh(&buffer->lock); return true; @@ -1936,5 +1957,6 @@ void iwl_mvm_rx_frame_release(struct iwl_mvm *mvm, struct napi_struct *napi, struct iwl_frame_release *release = (void *)pkt->data; iwl_mvm_release_frames_from_notif(mvm, napi, release->baid, - le16_to_cpu(release->nssn), queue); + le16_to_cpu(release->nssn), + queue, 0); } From 514ea05b0743435bf181c41f48d83aac050cc6fa Mon Sep 17 00:00:00 2001 From: Gregory Greenman Date: Mon, 8 Jul 2019 09:07:42 +0300 Subject: [PATCH 592/823] iwlwifi: mvm: fix possible out-of-bounds read when accessing lq_info lq_info is an arary of size 2, active_tbl index is u8. When accessing lq_info[1 - active_tbl], theoretically it's possible that the access will be made to a negative index value. Signed-off-by: Gregory Greenman Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/rs.c | 28 +++++++++++++++------ 1 file changed, 20 insertions(+), 8 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index 3fa50b1955bb..d3f04acfbacb 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -1352,6 +1352,18 @@ static void rs_set_expected_tpt_table(struct iwl_lq_sta *lq_sta, tbl->expected_tpt = rs_get_expected_tpt_table(lq_sta, column, rate->bw); } +/* rs uses two tables, one is active and the second is for searching better + * configuration. This function, according to the index of the currently + * active table returns the search table, which is located at the + * index complementary to 1 according to the active table (active = 1, + * search = 0 or active = 0, search = 1). + * Since lq_info is an arary of size 2, make sure index cannot be out of bounds. + */ +static inline u8 rs_search_tbl(u8 active_tbl) +{ + return (active_tbl ^ 1) & 1; +} + static s32 rs_get_best_rate(struct iwl_mvm *mvm, struct iwl_lq_sta *lq_sta, struct iwl_scale_tbl_info *tbl, /* "search" */ @@ -1699,9 +1711,9 @@ static int rs_switch_to_column(struct iwl_mvm *mvm, struct ieee80211_sta *sta, enum rs_column col_id) { - struct iwl_scale_tbl_info *tbl = &(lq_sta->lq_info[lq_sta->active_tbl]); + struct iwl_scale_tbl_info *tbl = &lq_sta->lq_info[lq_sta->active_tbl]; struct iwl_scale_tbl_info *search_tbl = - &(lq_sta->lq_info[(1 - lq_sta->active_tbl)]); + &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)]; struct rs_rate *rate = &search_tbl->rate; const struct rs_tx_column *column = &rs_tx_columns[col_id]; const struct rs_tx_column *curr_column = &rs_tx_columns[tbl->column]; @@ -2109,7 +2121,7 @@ static void rs_rate_scale_perform(struct iwl_mvm *mvm, if (!lq_sta->search_better_tbl) active_tbl = lq_sta->active_tbl; else - active_tbl = 1 - lq_sta->active_tbl; + active_tbl = rs_search_tbl(lq_sta->active_tbl); tbl = &(lq_sta->lq_info[active_tbl]); rate = &tbl->rate; @@ -2333,7 +2345,7 @@ lq_update: /* If new "search" mode was selected, set up in uCode table */ if (lq_sta->search_better_tbl) { /* Access the "search" table, clear its history. */ - tbl = &(lq_sta->lq_info[(1 - lq_sta->active_tbl)]); + tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)]; rs_rate_scale_clear_tbl_windows(mvm, tbl); /* Use new "search" start rate */ @@ -2676,7 +2688,7 @@ static void rs_initialize_lq(struct iwl_mvm *mvm, if (!lq_sta->search_better_tbl) active_tbl = lq_sta->active_tbl; else - active_tbl = 1 - lq_sta->active_tbl; + active_tbl = rs_search_tbl(lq_sta->active_tbl); tbl = &(lq_sta->lq_info[active_tbl]); rate = &tbl->rate; @@ -3172,9 +3184,9 @@ static void __iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, if (!lq_sta->search_better_tbl) { curr_tbl = &lq_sta->lq_info[lq_sta->active_tbl]; - other_tbl = &lq_sta->lq_info[1 - lq_sta->active_tbl]; + other_tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)]; } else { - curr_tbl = &lq_sta->lq_info[1 - lq_sta->active_tbl]; + curr_tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)]; other_tbl = &lq_sta->lq_info[lq_sta->active_tbl]; } @@ -3183,7 +3195,7 @@ static void __iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, "Neither active nor search matches tx rate\n"); tmp_tbl = &lq_sta->lq_info[lq_sta->active_tbl]; rs_dump_rate(mvm, &tmp_tbl->rate, "ACTIVE"); - tmp_tbl = &lq_sta->lq_info[1 - lq_sta->active_tbl]; + tmp_tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)]; rs_dump_rate(mvm, &tmp_tbl->rate, "SEARCH"); rs_dump_rate(mvm, &lq_rate, "ACTUAL"); From 03a0995ccc0717ca0c0c7454a033c260872d45ae Mon Sep 17 00:00:00 2001 From: Ihab Zhaika Date: Mon, 15 Jul 2019 15:30:48 +0300 Subject: [PATCH 593/823] iwlwifi: add 3 new IDs for the 9000 series (iwl9260_2ac_160_cfg) Add a few PCI ID'S for 9000 series. Signed-off-by: Ihab Zhaika Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index ea2a03d4bf55..de711c1160d3 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -604,10 +604,13 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2526, 0x40A4, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x42A4, iwl9462_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x6010, iwl9260_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x6014, iwl9260_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x8014, iwl9260_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x8010, iwl9260_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0xA014, iwl9260_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0xE010, iwl9260_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0xE014, iwl9260_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0010, iwl9160_2ac_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0014, iwl9160_2ac_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0210, iwl9160_2ac_cfg)}, From f5a47fae6aa3eb06f100e701d2342ee56b857bee Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Fri, 19 Jul 2019 12:21:59 +0300 Subject: [PATCH 594/823] iwlwifi: mvm: fix version check for GEO_TX_POWER_LIMIT support We erroneously added a check for FW API version 41 before sending GEO_TX_POWER_LIMIT, but this was already implemented in version 38. Additionally, it was cherry-picked to older versions, namely 17, 26 and 29, so check for those as well. Cc: stable@vger.kernel.org Fixes: eca1e56ceedd ("iwlwifi: mvm: don't send GEO_TX_POWER_LIMIT to old firmwares") Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index a837cf40afde..00c89bcfdf6a 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -886,9 +886,14 @@ static bool iwl_mvm_sar_geo_support(struct iwl_mvm *mvm) * The GEO_TX_POWER_LIMIT command is not supported on earlier * firmware versions. Unfortunately, we don't have a TLV API * flag to rely on, so rely on the major version which is in - * the first byte of ucode_ver. + * the first byte of ucode_ver. This was implemented + * initially on version 38 and then backported to 36, 29 and + * 17. */ - return IWL_UCODE_SERIAL(mvm->fw->ucode_ver) >= 41; + return IWL_UCODE_SERIAL(mvm->fw->ucode_ver) >= 38 || + IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 36 || + IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 29 || + IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 17; } int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm) From 87e7e25aee6b59fef740856f4e86d4b60496c9e1 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sun, 21 Jul 2019 14:02:27 +0300 Subject: [PATCH 595/823] iwlwifi: don't unmap as page memory that was mapped as single In order to remember how to unmap a memory (as single or as page), we maintain a bit per Transmit Buffer (TBs) in the meta data (structure iwl_cmd_meta). We maintain a bitmap: 1 bit per TB. If the TB is set, we will free the memory as a page. This bitmap was never cleared. Fix this. Cc: stable@vger.kernel.org Fixes: 3cd1980b0cdf ("iwlwifi: pcie: introduce new tfd and tb formats") Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/pcie/tx.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index fa4245d0d4a8..2f0ba7ef53b8 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -435,6 +435,8 @@ static void iwl_pcie_tfd_unmap(struct iwl_trans *trans, DMA_TO_DEVICE); } + meta->tbs = 0; + if (trans->cfg->use_tfh) { struct iwl_tfh_tfd *tfd_fh = (void *)tfd; From ba3224db78034435e9ff0247277cce7c7bb1756c Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Mon, 22 Jul 2019 12:47:27 +0300 Subject: [PATCH 596/823] iwlwifi: mvm: fix an out-of-bound access The index for the elements of the ACPI object we dereference was static. This means that if we called the function twice we wouldn't start from 3 again, but rather from the latest index we reached in the previous call. This was dutifully reported by KASAN. Fix this. Cc: stable@vger.kernel.org Fixes: 6996490501ed ("iwlwifi: mvm: add support for EWRD (Dynamic SAR) ACPI table") Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 00c89bcfdf6a..5de54d1559dd 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -755,7 +755,7 @@ static int iwl_mvm_sar_get_ewrd_table(struct iwl_mvm *mvm) for (i = 0; i < n_profiles; i++) { /* the tables start at element 3 */ - static int pos = 3; + int pos = 3; /* The EWRD profiles officially go from 2 to 4, but we * save them in sar_profiles[1-3] (because we don't From 71b256f8f7a5c09810d2c3ed6165629c2cc0a652 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Mon, 22 Jul 2019 13:02:25 +0300 Subject: [PATCH 597/823] iwlwifi: mvm: fix a use-after-free bug in iwl_mvm_tx_tso_segment Accessing the hdr of an skb that was consumed already isn't a good idea. First ask if the skb is a QoS packet, then keep that data on stack, and then consume the skb. This was spotted by KASAN. Cc: stable@vger.kernel.org Fixes: 08f7d8b69aaf ("iwlwifi: mvm: bring back mvm GSO code") Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index a3e5d88f1c07..6ac114a393cc 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -831,6 +831,7 @@ iwl_mvm_tx_tso_segment(struct sk_buff *skb, unsigned int num_subframes, unsigned int tcp_payload_len; unsigned int mss = skb_shinfo(skb)->gso_size; bool ipv4 = (skb->protocol == htons(ETH_P_IP)); + bool qos = ieee80211_is_data_qos(hdr->frame_control); u16 ip_base_id = ipv4 ? ntohs(ip_hdr(skb)->id) : 0; skb_shinfo(skb)->gso_size = num_subframes * mss; @@ -864,7 +865,7 @@ iwl_mvm_tx_tso_segment(struct sk_buff *skb, unsigned int num_subframes, if (tcp_payload_len > mss) { skb_shinfo(tmp)->gso_size = mss; } else { - if (ieee80211_is_data_qos(hdr->frame_control)) { + if (qos) { u8 *qc; if (ipv4) From eeebce1862970653cdf5c01e98bc669edd8f529a Mon Sep 17 00:00:00 2001 From: Don Brace Date: Wed, 24 Jul 2019 17:08:06 -0500 Subject: [PATCH 598/823] scsi: hpsa: correct scsi command status issue after reset Reviewed-by: Bader Ali - Saleh Reviewed-by: Scott Teel Reviewed-by: Scott Benesh Reviewed-by: Kevin Barnett Signed-off-by: Don Brace Signed-off-by: Martin K. Petersen --- drivers/scsi/hpsa.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 43a6b5350775..89e71ebc5964 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -2334,6 +2334,8 @@ static int handle_ioaccel_mode2_error(struct ctlr_info *h, case IOACCEL2_SERV_RESPONSE_COMPLETE: switch (c2->error_data.status) { case IOACCEL2_STATUS_SR_TASK_COMP_GOOD: + if (cmd) + cmd->result = 0; break; case IOACCEL2_STATUS_SR_TASK_COMP_CHK_COND: cmd->result |= SAM_STAT_CHECK_CONDITION; @@ -2483,8 +2485,10 @@ static void process_ioaccel2_completion(struct ctlr_info *h, /* check for good status */ if (likely(c2->error_data.serv_response == 0 && - c2->error_data.status == 0)) + c2->error_data.status == 0)) { + cmd->result = 0; return hpsa_cmd_free_and_done(h, c, cmd); + } /* * Any RAID offload error results in retry which will use @@ -5653,6 +5657,12 @@ static int hpsa_scsi_queue_command(struct Scsi_Host *sh, struct scsi_cmnd *cmd) if (c == NULL) return SCSI_MLQUEUE_DEVICE_BUSY; + /* + * This is necessary because the SML doesn't zero out this field during + * error recovery. + */ + cmd->result = 0; + /* * Call alternate submit routine for I/O accelerated commands. * Retries always go down the normal I/O path. From 2d291e6cc183608e1f6eb8580268df7c68bdf7c3 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 29 Jul 2019 18:32:10 -0500 Subject: [PATCH 599/823] MIPS: OProfile: Mark expected switch fall-throughs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Mark switch cases where we are expecting to fall through. This patch fixes the following warning (Building: mips): arch/mips/oprofile/op_model_mipsxx.c: In function ‘mipsxx_cpu_stop’: arch/mips/oprofile/op_model_mipsxx.c:217:3: warning: this statement may fall through [-Wimplicit-fallthrough=] w_c0_perfctrl3(0); ^~~~~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:218:2: note: here case 3: ^~~~ arch/mips/oprofile/op_model_mipsxx.c:219:3: warning: this statement may fall through [-Wimplicit-fallthrough=] w_c0_perfctrl2(0); ^~~~~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:220:2: note: here case 2: ^~~~ arch/mips/oprofile/op_model_mipsxx.c:221:3: warning: this statement may fall through [-Wimplicit-fallthrough=] w_c0_perfctrl1(0); ^~~~~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:222:2: note: here case 1: ^~~~ arch/mips/oprofile/op_model_mipsxx.c: In function ‘mipsxx_cpu_start’: arch/mips/oprofile/op_model_mipsxx.c:197:3: warning: this statement may fall through [-Wimplicit-fallthrough=] w_c0_perfctrl3(WHAT | reg.control[3]); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:198:2: note: here case 3: ^~~~ arch/mips/oprofile/op_model_mipsxx.c:199:3: warning: this statement may fall through [-Wimplicit-fallthrough=] w_c0_perfctrl2(WHAT | reg.control[2]); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:200:2: note: here case 2: ^~~~ arch/mips/oprofile/op_model_mipsxx.c:201:3: warning: this statement may fall through [-Wimplicit-fallthrough=] w_c0_perfctrl1(WHAT | reg.control[1]); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:202:2: note: here case 1: ^~~~ arch/mips/oprofile/op_model_mipsxx.c: In function ‘reset_counters’: arch/mips/oprofile/op_model_mipsxx.c:299:3: warning: this statement may fall through [-Wimplicit-fallthrough=] w_c0_perfcntr3(0); ^~~~~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:300:2: note: here case 3: ^~~~ arch/mips/oprofile/op_model_mipsxx.c:302:3: warning: this statement may fall through [-Wimplicit-fallthrough=] w_c0_perfcntr2(0); ^~~~~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:303:2: note: here case 2: ^~~~ arch/mips/oprofile/op_model_mipsxx.c:305:3: warning: this statement may fall through [-Wimplicit-fallthrough=] w_c0_perfcntr1(0); ^~~~~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:306:2: note: here case 1: ^~~~ arch/mips/oprofile/op_model_mipsxx.c: In function ‘mipsxx_perfcount_handler’: arch/mips/oprofile/op_model_mipsxx.c:242:6: warning: this statement may fall through [-Wimplicit-fallthrough=] if ((control & MIPS_PERFCTRL_IE) && \ ^ arch/mips/oprofile/op_model_mipsxx.c:248:2: note: in expansion of macro ‘HANDLE_COUNTER’ HANDLE_COUNTER(3) ^~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:239:2: note: here case n + 1: \ ^ arch/mips/oprofile/op_model_mipsxx.c:249:2: note: in expansion of macro ‘HANDLE_COUNTER’ HANDLE_COUNTER(2) ^~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:242:6: warning: this statement may fall through [-Wimplicit-fallthrough=] if ((control & MIPS_PERFCTRL_IE) && \ ^ arch/mips/oprofile/op_model_mipsxx.c:249:2: note: in expansion of macro ‘HANDLE_COUNTER’ HANDLE_COUNTER(2) ^~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:239:2: note: here case n + 1: \ ^ arch/mips/oprofile/op_model_mipsxx.c:250:2: note: in expansion of macro ‘HANDLE_COUNTER’ HANDLE_COUNTER(1) ^~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:242:6: warning: this statement may fall through [-Wimplicit-fallthrough=] if ((control & MIPS_PERFCTRL_IE) && \ ^ arch/mips/oprofile/op_model_mipsxx.c:250:2: note: in expansion of macro ‘HANDLE_COUNTER’ HANDLE_COUNTER(1) ^~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:239:2: note: here case n + 1: \ ^ arch/mips/oprofile/op_model_mipsxx.c:251:2: note: in expansion of macro ‘HANDLE_COUNTER’ HANDLE_COUNTER(0) ^~~~~~~~~~~~~~ CC usr/include/linux/pmu.h.s arch/mips/oprofile/op_model_mipsxx.c: In function ‘mipsxx_cpu_setup’: arch/mips/oprofile/op_model_mipsxx.c:174:3: warning: this statement may fall through [-Wimplicit-fallthrough=] w_c0_perfcntr3(reg.counter[3]); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:175:2: note: here case 3: ^~~~ arch/mips/oprofile/op_model_mipsxx.c:177:3: warning: this statement may fall through [-Wimplicit-fallthrough=] w_c0_perfcntr2(reg.counter[2]); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:178:2: note: here case 2: ^~~~ arch/mips/oprofile/op_model_mipsxx.c:180:3: warning: this statement may fall through [-Wimplicit-fallthrough=] w_c0_perfcntr1(reg.counter[1]); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ arch/mips/oprofile/op_model_mipsxx.c:181:2: note: here case 1: ^~~~ Signed-off-by: Gustavo A. R. Silva Signed-off-by: Paul Burton Cc: Robert Richter Cc: Ralf Baechle Cc: James Hogan Cc: oprofile-list@lists.sf.net Cc: linux-mips@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Kees Cook --- arch/mips/oprofile/op_model_mipsxx.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/mips/oprofile/op_model_mipsxx.c b/arch/mips/oprofile/op_model_mipsxx.c index 7c04b17f4a48..96c13a0ab078 100644 --- a/arch/mips/oprofile/op_model_mipsxx.c +++ b/arch/mips/oprofile/op_model_mipsxx.c @@ -172,12 +172,15 @@ static void mipsxx_cpu_setup(void *args) case 4: w_c0_perfctrl3(0); w_c0_perfcntr3(reg.counter[3]); + /* fall through */ case 3: w_c0_perfctrl2(0); w_c0_perfcntr2(reg.counter[2]); + /* fall through */ case 2: w_c0_perfctrl1(0); w_c0_perfcntr1(reg.counter[1]); + /* fall through */ case 1: w_c0_perfctrl0(0); w_c0_perfcntr0(reg.counter[0]); @@ -195,10 +198,13 @@ static void mipsxx_cpu_start(void *args) switch (counters) { case 4: w_c0_perfctrl3(WHAT | reg.control[3]); + /* fall through */ case 3: w_c0_perfctrl2(WHAT | reg.control[2]); + /* fall through */ case 2: w_c0_perfctrl1(WHAT | reg.control[1]); + /* fall through */ case 1: w_c0_perfctrl0(WHAT | reg.control[0]); } @@ -215,10 +221,13 @@ static void mipsxx_cpu_stop(void *args) switch (counters) { case 4: w_c0_perfctrl3(0); + /* fall through */ case 3: w_c0_perfctrl2(0); + /* fall through */ case 2: w_c0_perfctrl1(0); + /* fall through */ case 1: w_c0_perfctrl0(0); } @@ -236,6 +245,7 @@ static int mipsxx_perfcount_handler(void) switch (counters) { #define HANDLE_COUNTER(n) \ + /* fall through */ \ case n + 1: \ control = r_c0_perfctrl ## n(); \ counter = r_c0_perfcntr ## n(); \ @@ -297,12 +307,15 @@ static void reset_counters(void *arg) case 4: w_c0_perfctrl3(0); w_c0_perfcntr3(0); + /* fall through */ case 3: w_c0_perfctrl2(0); w_c0_perfcntr2(0); + /* fall through */ case 2: w_c0_perfctrl1(0); w_c0_perfcntr1(0); + /* fall through */ case 1: w_c0_perfctrl0(0); w_c0_perfcntr0(0); From 18a56d699d174f3ac41f2ea86e1ca21f98b01d8f Mon Sep 17 00:00:00 2001 From: Don Brace Date: Wed, 24 Jul 2019 17:08:12 -0500 Subject: [PATCH 600/823] scsi: hpsa: remove printing internal cdb on tag collision Remove racy printing of internal commands. Completion thread can be cleaning up the command in parallel. Reviewed-by: Bader Ali - Saleh Reviewed-by: Scott Teel Reviewed-by: Scott Benesh Reviewed-by: Kevin Barnett Signed-off-by: Don Brace Signed-off-by: Martin K. Petersen --- drivers/scsi/hpsa.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 89e71ebc5964..bba099e53266 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -6091,8 +6091,6 @@ static struct CommandList *cmd_tagged_alloc(struct ctlr_info *h, if (idx != h->last_collision_tag) { /* Print once per tag */ dev_warn(&h->pdev->dev, "%s: tag collision (tag=%d)\n", __func__, idx); - if (c->scsi_cmd != NULL) - scsi_print_command(c->scsi_cmd); if (scmd) scsi_print_command(scmd); h->last_collision_tag = idx; From df9a606184bfdb5ae3ca9d226184e9489f5c24f7 Mon Sep 17 00:00:00 2001 From: Suganath Prabu Date: Tue, 30 Jul 2019 03:43:57 -0400 Subject: [PATCH 601/823] scsi: mpt3sas: Use 63-bit DMA addressing on SAS35 HBA Although SAS3 & SAS3.5 IT HBA controllers support 64-bit DMA addressing, as per hardware design, if DMA-able range contains all 64-bits set (0xFFFFFFFF-FFFFFFFF) then it results in a firmware fault. E.g. SGE's start address is 0xFFFFFFFF-FFFF000 and data length is 0x1000 bytes. when HBA tries to DMA the data at 0xFFFFFFFF-FFFFFFFF location then HBA will fault the firmware. Driver will set 63-bit DMA mask to ensure the above address will not be used. Cc: # 5.1.20+ Signed-off-by: Suganath Prabu Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_base.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 684662888792..050c0f029ef9 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2703,6 +2703,8 @@ _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev) { u64 required_mask, coherent_mask; struct sysinfo s; + /* Set 63 bit DMA mask for all SAS3 and SAS35 controllers */ + int dma_mask = (ioc->hba_mpi_version_belonged > MPI2_VERSION) ? 63 : 64; if (ioc->is_mcpu_endpoint) goto try_32bit; @@ -2712,17 +2714,17 @@ _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev) goto try_32bit; if (ioc->dma_mask) - coherent_mask = DMA_BIT_MASK(64); + coherent_mask = DMA_BIT_MASK(dma_mask); else coherent_mask = DMA_BIT_MASK(32); - if (dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) || + if (dma_set_mask(&pdev->dev, DMA_BIT_MASK(dma_mask)) || dma_set_coherent_mask(&pdev->dev, coherent_mask)) goto try_32bit; ioc->base_add_sg_single = &_base_add_sg_single_64; ioc->sge_size = sizeof(Mpi2SGESimple64_t); - ioc->dma_mask = 64; + ioc->dma_mask = dma_mask; goto out; try_32bit: @@ -2744,7 +2746,7 @@ static int _base_change_consistent_dma_mask(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev) { - if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64))) { + if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(ioc->dma_mask))) { if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32))) return -ENODEV; } @@ -4989,7 +4991,7 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc) total_sz += sz; } while (ioc->rdpq_array_enable && (++i < ioc->reply_queue_count)); - if (ioc->dma_mask == 64) { + if (ioc->dma_mask > 32) { if (_base_change_consistent_dma_mask(ioc, ioc->pdev) != 0) { ioc_warn(ioc, "no suitable consistent DMA mask for %s\n", pci_name(ioc->pdev)); From e82f04ec6ba91065fd33a6201ffd7cab840e1475 Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Mon, 29 Jul 2019 16:44:51 +0800 Subject: [PATCH 602/823] scsi: qla2xxx: Fix possible fcport null-pointer dereferences In qla2x00_alloc_fcport(), fcport is assigned to NULL in the error handling code on line 4880: fcport = NULL; Then fcport is used on lines 4883-4886: INIT_WORK(&fcport->del_work, qla24xx_delete_sess_fn); INIT_WORK(&fcport->reg_work, qla_register_fcport_fn); INIT_LIST_HEAD(&fcport->gnl_entry); INIT_LIST_HEAD(&fcport->list); Thus, possible null-pointer dereferences may occur. To fix these bugs, qla2x00_alloc_fcport() directly returns NULL in the error handling code. These bugs are found by a static analysis tool STCheck written by us. Signed-off-by: Jia-Ju Bai Acked-by: Himanshu Madhani Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 4059655639d9..da83034d4759 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -4877,7 +4877,7 @@ qla2x00_alloc_fcport(scsi_qla_host_t *vha, gfp_t flags) ql_log(ql_log_warn, vha, 0xd049, "Failed to allocate ct_sns request.\n"); kfree(fcport); - fcport = NULL; + return NULL; } INIT_WORK(&fcport->del_work, qla24xx_delete_sess_fn); From ab98c008ac761752cdc27f9eb053419feadeb2f7 Mon Sep 17 00:00:00 2001 From: Hubert Feurstein Date: Tue, 30 Jul 2019 11:46:23 +0200 Subject: [PATCH 603/823] net: phy: fixed_phy: print gpio error only if gpio node is present It is perfectly ok to not have an gpio attached to the fixed-link node. So the driver should not throw an error message when the gpio is missing. Fixes: 5468e82f7034 ("net: phy: fixed-phy: Drop GPIO from fixed_phy_add()") Signed-off-by: Hubert Feurstein Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/fixed_phy.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index 3ffe46df249e..7c5265fd2b94 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -216,8 +216,10 @@ static struct gpio_desc *fixed_phy_get_gpiod(struct device_node *np) if (IS_ERR(gpiod)) { if (PTR_ERR(gpiod) == -EPROBE_DEFER) return gpiod; - pr_err("error getting GPIO for fixed link %pOF, proceed without\n", - fixed_link_node); + + if (PTR_ERR(gpiod) != -ENOENT) + pr_err("error getting GPIO for fixed link %pOF, proceed without\n", + fixed_link_node); gpiod = NULL; } From 43c8e0ae76bdcb5c00b381c294c176b373316c8d Mon Sep 17 00:00:00 2001 From: Hubert Feurstein Date: Tue, 30 Jul 2019 12:11:42 +0200 Subject: [PATCH 604/823] net: dsa: mv88e6xxx: use link-down-define instead of plain value Using the define here makes the code more expressive. Signed-off-by: Hubert Feurstein Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index c97dea4599a8..a0f288efcc12 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -430,7 +430,7 @@ int mv88e6xxx_port_setup_mac(struct mv88e6xxx_chip *chip, int port, int link, return 0; /* Port's MAC control must not be changed unless the link is down */ - err = chip->info->ops->port_set_link(chip, port, 0); + err = chip->info->ops->port_set_link(chip, port, LINK_FORCED_DOWN); if (err) return err; From 2ad07086a557efdd80dd036f7b843bd3c51b81c2 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 30 Jul 2019 12:47:52 +0100 Subject: [PATCH 605/823] mlxsw: spectrum_ptp: fix duplicated check on orig_egr_types Currently are duplicated checks on orig_egr_types which are redundant, I believe this is a typo and should actually be orig_ing_types || orig_egr_types instead of the expression orig_egr_types || orig_egr_types. Fix these. Addresses-Coverity: ("Same on both sides") Fixes: c6b36bdd04b5 ("mlxsw: spectrum_ptp: Increase parsing depth when PTP is enabled") Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index 98c5ba3200bc..63b07edd9d81 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -999,14 +999,14 @@ static int mlxsw_sp1_ptp_mtpppc_update(struct mlxsw_sp_port *mlxsw_sp_port, } } - if ((ing_types || egr_types) && !(orig_egr_types || orig_egr_types)) { + if ((ing_types || egr_types) && !(orig_ing_types || orig_egr_types)) { err = mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp); if (err) { netdev_err(mlxsw_sp_port->dev, "Failed to increase parsing depth"); return err; } } - if (!(ing_types || egr_types) && (orig_egr_types || orig_egr_types)) + if (!(ing_types || egr_types) && (orig_ing_types || orig_egr_types)) mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp); return mlxsw_sp1_ptp_mtpppc_set(mlxsw_sp_port->mlxsw_sp, From 3caa61c208753492fe59efb20e06f7c608eb8db2 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Tue, 30 Jul 2019 15:57:16 +0200 Subject: [PATCH 606/823] net: stmmac: Sync RX Buffer upon allocation With recent changes that introduced support for Page Pool in stmmac, Jon reported that NFS boot was no longer working on an ARM64 based platform that had the IP behind an IOMMU. As Page Pool API does not guarantee DMA syncing because of the use of DMA_ATTR_SKIP_CPU_SYNC flag, we have to explicit sync the whole buffer upon re-allocation because we are always re-using same pages. In fact, ARM64 code invalidates the DMA area upon two situations [1]: - sync_single_for_cpu(): Invalidates if direction != DMA_TO_DEVICE - sync_single_for_device(): Invalidates if direction == DMA_FROM_DEVICE So, as we must invalidate both the current RX buffer and the newly allocated buffer we propose this fix. [1] arch/arm64/mm/cache.S Reported-by: Jon Hunter Tested-by: Jon Hunter Fixes: 2af6106ae949 ("net: stmmac: Introducing support for Page Pool") Signed-off-by: Jose Abreu Tested-by: Ezequiel Garcia Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 98b1a5c6d537..9a4a56ad35cd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3271,9 +3271,11 @@ static inline int stmmac_rx_threshold_count(struct stmmac_rx_queue *rx_q) static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) { struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; - int dirty = stmmac_rx_dirty(priv, queue); + int len, dirty = stmmac_rx_dirty(priv, queue); unsigned int entry = rx_q->dirty_rx; + len = DIV_ROUND_UP(priv->dma_buf_sz, PAGE_SIZE) * PAGE_SIZE; + while (dirty-- > 0) { struct stmmac_rx_buffer *buf = &rx_q->buf_pool[entry]; struct dma_desc *p; @@ -3291,6 +3293,13 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) } buf->addr = page_pool_get_dma_addr(buf->page); + + /* Sync whole allocation to device. This will invalidate old + * data. + */ + dma_sync_single_for_device(priv->device, buf->addr, len, + DMA_FROM_DEVICE); + stmmac_set_desc_addr(priv, p, buf->addr); stmmac_refill_desc3(priv, rx_q, p); @@ -3425,8 +3434,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) skb_copy_to_linear_data(skb, page_address(buf->page), frame_len); skb_put(skb, frame_len); - dma_sync_single_for_device(priv->device, buf->addr, - frame_len, DMA_FROM_DEVICE); if (netif_msg_pktdata(priv)) { netdev_dbg(priv->dev, "frame received (%dbytes)", From 5f4e4203add2b860d2345312509a160f8292063b Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Tue, 30 Jul 2019 22:29:59 +0800 Subject: [PATCH 607/823] enetc: Fix build error without PHYLIB If PHYLIB is not set, build enetc will fails: drivers/net/ethernet/freescale/enetc/enetc.o: In function `enetc_open': enetc.c: undefined reference to `phy_disconnect' enetc.c: undefined reference to `phy_start' drivers/net/ethernet/freescale/enetc/enetc.o: In function `enetc_close': enetc.c: undefined reference to `phy_stop' enetc.c: undefined reference to `phy_disconnect' drivers/net/ethernet/freescale/enetc/enetc_ethtool.o: undefined reference to `phy_ethtool_get_link_ksettings' drivers/net/ethernet/freescale/enetc/enetc_ethtool.o: undefined reference to `phy_ethtool_set_link_ksettings' drivers/net/ethernet/freescale/enetc/enetc_mdio.o: In function `enetc_mdio_probe': enetc_mdio.c: undefined reference to `mdiobus_alloc_size' enetc_mdio.c: undefined reference to `mdiobus_free' Reported-by: Hulk Robot Fixes: d4fd0404c1c9 ("enetc: Introduce basic PF and VF ENETC ethernet drivers") Signed-off-by: YueHaibing Acked-by: Claudiu Manoil Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/enetc/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig index ed0d010c7cf2..46fdf36bfece 100644 --- a/drivers/net/ethernet/freescale/enetc/Kconfig +++ b/drivers/net/ethernet/freescale/enetc/Kconfig @@ -2,6 +2,7 @@ config FSL_ENETC tristate "ENETC PF driver" depends on PCI && PCI_MSI && (ARCH_LAYERSCAPE || COMPILE_TEST) + select PHYLIB help This driver supports NXP ENETC gigabit ethernet controller PCIe physical function (PF) devices, managing ENETC Ports at a privileged From 30b692d3b390c6fe78a5064be0c4bbd44a41be59 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 29 Jul 2019 17:48:24 +0200 Subject: [PATCH 608/823] exit: make setting exit_state consistent Since commit b191d6491be6 ("pidfd: fix a poll race when setting exit_state") we unconditionally set exit_state to EXIT_ZOMBIE before calling into do_notify_parent(). This was done to eliminate a race when querying exit_state in do_notify_pidfd(). Back then we decided to do the absolute minimal thing to fix this and not touch the rest of the exit_notify() function where exit_state is set. Since this fix has not caused any issues change the setting of exit_state to EXIT_DEAD in the autoreap case to account for the fact hat exit_state is set to EXIT_ZOMBIE unconditionally. This fix was planned but also explicitly requested in [1] and makes the whole code more consistent. /* References */ [1]: https://lore.kernel.org/lkml/CAHk-=wigcxGFR2szue4wavJtH5cYTTeNES=toUBVGsmX0rzX+g@mail.gmail.com Signed-off-by: Christian Brauner Acked-by: Oleg Nesterov Cc: Linus Torvalds --- kernel/exit.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/kernel/exit.c b/kernel/exit.c index 4436158a6d30..5b4a5dcce8f8 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -734,9 +734,10 @@ static void exit_notify(struct task_struct *tsk, int group_dead) autoreap = true; } - tsk->exit_state = autoreap ? EXIT_DEAD : EXIT_ZOMBIE; - if (tsk->exit_state == EXIT_DEAD) + if (autoreap) { + tsk->exit_state = EXIT_DEAD; list_add(&tsk->ptrace_entry, &dead); + } /* mt-exec, de_thread() is waiting for group leader */ if (unlikely(tsk->signal->notify_count < 0)) From afa1d96d1430c2138c545fb76e6dcb21222098d4 Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Tue, 30 Jul 2019 11:28:20 -0700 Subject: [PATCH 609/823] xfs: Fix possible null-pointer dereferences in xchk_da_btree_block_check_sibling() In xchk_da_btree_block_check_sibling(), there is an if statement on line 274 to check whether ds->state->altpath.blk[level].bp is NULL: if (ds->state->altpath.blk[level].bp) When ds->state->altpath.blk[level].bp is NULL, it is used on line 281: xfs_trans_brelse(..., ds->state->altpath.blk[level].bp); struct xfs_buf_log_item *bip = bp->b_log_item; ASSERT(bp->b_transp == tp); Thus, possible null-pointer dereferences may occur. To fix these bugs, ds->state->altpath.blk[level].bp is checked before being used. These bugs are found by a static analysis tool STCheck written by us. Signed-off-by: Jia-Ju Bai Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/scrub/dabtree.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c index 94c4f1de1922..77ff9f97bcda 100644 --- a/fs/xfs/scrub/dabtree.c +++ b/fs/xfs/scrub/dabtree.c @@ -278,7 +278,11 @@ xchk_da_btree_block_check_sibling( /* Compare upper level pointer to sibling pointer. */ if (ds->state->altpath.blk[level].blkno != sibling) xchk_da_set_corrupt(ds, level); - xfs_trans_brelse(ds->dargs.trans, ds->state->altpath.blk[level].bp); + if (ds->state->altpath.blk[level].bp) { + xfs_trans_brelse(ds->dargs.trans, + ds->state->altpath.blk[level].bp); + ds->state->altpath.blk[level].bp = NULL; + } out: return error; } From 89e524c04fa966330e2e80ab2bc50b9944c5847a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 30 Jul 2019 13:10:14 +0200 Subject: [PATCH 610/823] loop: Fix mount(2) failure due to race with LOOP_SET_FD Commit 33ec3e53e7b1 ("loop: Don't change loop device under exclusive opener") made LOOP_SET_FD ioctl acquire exclusive block device reference while it updates loop device binding. However this can make perfectly valid mount(2) fail with EBUSY due to racing LOOP_SET_FD holding temporarily the exclusive bdev reference in cases like this: for i in {a..z}{a..z}; do dd if=/dev/zero of=$i.image bs=1k count=0 seek=1024 mkfs.ext2 $i.image mkdir mnt$i done echo "Run" for i in {a..z}{a..z}; do mount -o loop -t ext2 $i.image mnt$i & done Fix the problem by not getting full exclusive bdev reference in LOOP_SET_FD but instead just mark the bdev as being claimed while we update the binding information. This just blocks new exclusive openers instead of failing them with EBUSY thus fixing the problem. Fixes: 33ec3e53e7b1 ("loop: Don't change loop device under exclusive opener") Cc: stable@vger.kernel.org Tested-by: Kai-Heng Feng Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- drivers/block/loop.c | 16 +++++---- fs/block_dev.c | 83 +++++++++++++++++++++++++++++++------------- include/linux/fs.h | 6 ++++ 3 files changed, 73 insertions(+), 32 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 44c9985f352a..3036883fc9f8 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -924,6 +924,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, struct file *file; struct inode *inode; struct address_space *mapping; + struct block_device *claimed_bdev = NULL; int lo_flags = 0; int error; loff_t size; @@ -942,10 +943,11 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, * here to avoid changing device under exclusive owner. */ if (!(mode & FMODE_EXCL)) { - bdgrab(bdev); - error = blkdev_get(bdev, mode | FMODE_EXCL, loop_set_fd); - if (error) + claimed_bdev = bd_start_claiming(bdev, loop_set_fd); + if (IS_ERR(claimed_bdev)) { + error = PTR_ERR(claimed_bdev); goto out_putf; + } } error = mutex_lock_killable(&loop_ctl_mutex); @@ -1015,15 +1017,15 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, mutex_unlock(&loop_ctl_mutex); if (partscan) loop_reread_partitions(lo, bdev); - if (!(mode & FMODE_EXCL)) - blkdev_put(bdev, mode | FMODE_EXCL); + if (claimed_bdev) + bd_abort_claiming(bdev, claimed_bdev, loop_set_fd); return 0; out_unlock: mutex_unlock(&loop_ctl_mutex); out_bdev: - if (!(mode & FMODE_EXCL)) - blkdev_put(bdev, mode | FMODE_EXCL); + if (claimed_bdev) + bd_abort_claiming(bdev, claimed_bdev, loop_set_fd); out_putf: fput(file); out: diff --git a/fs/block_dev.c b/fs/block_dev.c index c2a85b587922..22591bad9353 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1181,8 +1181,7 @@ static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno) * Pointer to the block device containing @bdev on success, ERR_PTR() * value on failure. */ -static struct block_device *bd_start_claiming(struct block_device *bdev, - void *holder) +struct block_device *bd_start_claiming(struct block_device *bdev, void *holder) { struct gendisk *disk; struct block_device *whole; @@ -1229,6 +1228,62 @@ static struct block_device *bd_start_claiming(struct block_device *bdev, return ERR_PTR(err); } } +EXPORT_SYMBOL(bd_start_claiming); + +static void bd_clear_claiming(struct block_device *whole, void *holder) +{ + lockdep_assert_held(&bdev_lock); + /* tell others that we're done */ + BUG_ON(whole->bd_claiming != holder); + whole->bd_claiming = NULL; + wake_up_bit(&whole->bd_claiming, 0); +} + +/** + * bd_finish_claiming - finish claiming of a block device + * @bdev: block device of interest + * @whole: whole block device (returned from bd_start_claiming()) + * @holder: holder that has claimed @bdev + * + * Finish exclusive open of a block device. Mark the device as exlusively + * open by the holder and wake up all waiters for exclusive open to finish. + */ +void bd_finish_claiming(struct block_device *bdev, struct block_device *whole, + void *holder) +{ + spin_lock(&bdev_lock); + BUG_ON(!bd_may_claim(bdev, whole, holder)); + /* + * Note that for a whole device bd_holders will be incremented twice, + * and bd_holder will be set to bd_may_claim before being set to holder + */ + whole->bd_holders++; + whole->bd_holder = bd_may_claim; + bdev->bd_holders++; + bdev->bd_holder = holder; + bd_clear_claiming(whole, holder); + spin_unlock(&bdev_lock); +} +EXPORT_SYMBOL(bd_finish_claiming); + +/** + * bd_abort_claiming - abort claiming of a block device + * @bdev: block device of interest + * @whole: whole block device (returned from bd_start_claiming()) + * @holder: holder that has claimed @bdev + * + * Abort claiming of a block device when the exclusive open failed. This can be + * also used when exclusive open is not actually desired and we just needed + * to block other exclusive openers for a while. + */ +void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, + void *holder) +{ + spin_lock(&bdev_lock); + bd_clear_claiming(whole, holder); + spin_unlock(&bdev_lock); +} +EXPORT_SYMBOL(bd_abort_claiming); #ifdef CONFIG_SYSFS struct bd_holder_disk { @@ -1698,29 +1753,7 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder) /* finish claiming */ mutex_lock(&bdev->bd_mutex); - spin_lock(&bdev_lock); - - if (!res) { - BUG_ON(!bd_may_claim(bdev, whole, holder)); - /* - * Note that for a whole device bd_holders - * will be incremented twice, and bd_holder - * will be set to bd_may_claim before being - * set to holder - */ - whole->bd_holders++; - whole->bd_holder = bd_may_claim; - bdev->bd_holders++; - bdev->bd_holder = holder; - } - - /* tell others that we're done */ - BUG_ON(whole->bd_claiming != holder); - whole->bd_claiming = NULL; - wake_up_bit(&whole->bd_claiming, 0); - - spin_unlock(&bdev_lock); - + bd_finish_claiming(bdev, whole, holder); /* * Block event polling for write claims if requested. Any * write holder makes the write_holder state stick until diff --git a/include/linux/fs.h b/include/linux/fs.h index 56b8e358af5c..997a530ff4e9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2598,6 +2598,12 @@ extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder); extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); +extern struct block_device *bd_start_claiming(struct block_device *bdev, + void *holder); +extern void bd_finish_claiming(struct block_device *bdev, + struct block_device *whole, void *holder); +extern void bd_abort_claiming(struct block_device *bdev, + struct block_device *whole, void *holder); extern void blkdev_put(struct block_device *bdev, fmode_t mode); extern int __blkdev_reread_part(struct block_device *bdev); extern int blkdev_reread_part(struct block_device *bdev); From 2948a1fcd77a8bb11604387e3fc52f0ebf5729e9 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Tue, 30 Jul 2019 20:19:10 +0200 Subject: [PATCH 611/823] tipc: fix unitilized skb list crash Our test suite somtimes provokes the following crash: Description of problem: [ 1092.597234] BUG: unable to handle kernel NULL pointer dereference at 00000000000000e8 [ 1092.605072] PGD 0 P4D 0 [ 1092.607620] Oops: 0000 [#1] SMP PTI [ 1092.611118] CPU: 37 PID: 0 Comm: swapper/37 Kdump: loaded Not tainted 4.18.0-122.el8.x86_64 #1 [ 1092.619724] Hardware name: Dell Inc. PowerEdge R740/08D89F, BIOS 1.3.7 02/08/2018 [ 1092.627215] RIP: 0010:tipc_mcast_filter_msg+0x93/0x2d0 [tipc] [ 1092.632955] Code: 0f 84 aa 01 00 00 89 cf 4d 01 ca 4c 8b 26 c1 ef 19 83 e7 0f 83 ff 0c 4d 0f 45 d1 41 8b 6a 10 0f cd 4c 39 e6 0f 84 81 01 00 00 <4d> 8b 9c 24 e8 00 00 00 45 8b 13 41 0f ca 44 89 d7 c1 ef 13 83 e7 [ 1092.651703] RSP: 0018:ffff929e5fa83a18 EFLAGS: 00010282 [ 1092.656927] RAX: ffff929e3fb38100 RBX: 00000000069f29ee RCX: 00000000416c0045 [ 1092.664058] RDX: ffff929e5fa83a88 RSI: ffff929e31a28420 RDI: 0000000000000000 [ 1092.671209] RBP: 0000000029b11821 R08: 0000000000000000 R09: ffff929e39b4407a [ 1092.678343] R10: ffff929e39b4407a R11: 0000000000000007 R12: 0000000000000000 [ 1092.685475] R13: 0000000000000001 R14: ffff929e3fb38100 R15: ffff929e39b4407a [ 1092.692614] FS: 0000000000000000(0000) GS:ffff929e5fa80000(0000) knlGS:0000000000000000 [ 1092.700702] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1092.706447] CR2: 00000000000000e8 CR3: 000000031300a004 CR4: 00000000007606e0 [ 1092.713579] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1092.720712] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 1092.727843] PKRU: 55555554 [ 1092.730556] Call Trace: [ 1092.733010] [ 1092.735034] tipc_sk_filter_rcv+0x7ca/0xb80 [tipc] [ 1092.739828] ? __kmalloc_node_track_caller+0x1cb/0x290 [ 1092.744974] ? dev_hard_start_xmit+0xa5/0x210 [ 1092.749332] tipc_sk_rcv+0x389/0x640 [tipc] [ 1092.753519] tipc_sk_mcast_rcv+0x23c/0x3a0 [tipc] [ 1092.758224] tipc_rcv+0x57a/0xf20 [tipc] [ 1092.762154] ? ktime_get_real_ts64+0x40/0xe0 [ 1092.766432] ? tpacket_rcv+0x50/0x9f0 [ 1092.770098] tipc_l2_rcv_msg+0x4a/0x70 [tipc] [ 1092.774452] __netif_receive_skb_core+0xb62/0xbd0 [ 1092.779164] ? enqueue_entity+0xf6/0x630 [ 1092.783084] ? kmem_cache_alloc+0x158/0x1c0 [ 1092.787272] ? __build_skb+0x25/0xd0 [ 1092.790849] netif_receive_skb_internal+0x42/0xf0 [ 1092.795557] napi_gro_receive+0xba/0xe0 [ 1092.799417] mlx5e_handle_rx_cqe+0x83/0xd0 [mlx5_core] [ 1092.804564] mlx5e_poll_rx_cq+0xd5/0x920 [mlx5_core] [ 1092.809536] mlx5e_napi_poll+0xb2/0xce0 [mlx5_core] [ 1092.814415] ? __wake_up_common_lock+0x89/0xc0 [ 1092.818861] net_rx_action+0x149/0x3b0 [ 1092.822616] __do_softirq+0xe3/0x30a [ 1092.826193] irq_exit+0x100/0x110 [ 1092.829512] do_IRQ+0x85/0xd0 [ 1092.832483] common_interrupt+0xf/0xf [ 1092.836147] [ 1092.838255] RIP: 0010:cpuidle_enter_state+0xb7/0x2a0 [ 1092.843221] Code: e8 3e 79 a5 ff 80 7c 24 03 00 74 17 9c 58 0f 1f 44 00 00 f6 c4 02 0f 85 d7 01 00 00 31 ff e8 a0 6b ab ff fb 66 0f 1f 44 00 00 <48> b8 ff ff ff ff f3 01 00 00 4c 29 f3 ba ff ff ff 7f 48 39 c3 7f [ 1092.861967] RSP: 0018:ffffaa5ec6533e98 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffdd [ 1092.869530] RAX: ffff929e5faa3100 RBX: 000000fe63dd2092 RCX: 000000000000001f [ 1092.876665] RDX: 000000fe63dd2092 RSI: 000000003a518aaa RDI: 0000000000000000 [ 1092.883795] RBP: 0000000000000003 R08: 0000000000000004 R09: 0000000000022940 [ 1092.890929] R10: 0000040cb0666b56 R11: ffff929e5faa20a8 R12: ffff929e5faade78 [ 1092.898060] R13: ffffffffb59258f8 R14: 000000fe60f3228d R15: 0000000000000000 [ 1092.905196] ? cpuidle_enter_state+0x92/0x2a0 [ 1092.909555] do_idle+0x236/0x280 [ 1092.912785] cpu_startup_entry+0x6f/0x80 [ 1092.916715] start_secondary+0x1a7/0x200 [ 1092.920642] secondary_startup_64+0xb7/0xc0 [...] The reason is that the skb list tipc_socket::mc_method.deferredq only is initialized for connectionless sockets, while nothing stops arriving multicast messages from being filtered by connection oriented sockets, with subsequent access to the said list. We fix this by initializing the list unconditionally at socket creation. This eliminates the crash, while the message still is dropped further down in tipc_sk_filter_rcv() as it should be. Reported-by: Li Shuang Signed-off-by: Jon Maloy Reviewed-by: Xin Long Signed-off-by: David S. Miller --- net/tipc/socket.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index dd8537f988c4..83ae41d7e554 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -485,9 +485,8 @@ static int tipc_sk_create(struct net *net, struct socket *sock, tsk_set_unreturnable(tsk, true); if (sock->type == SOCK_DGRAM) tsk_set_unreliable(tsk, true); - __skb_queue_head_init(&tsk->mc_method.deferredq); } - + __skb_queue_head_init(&tsk->mc_method.deferredq); trace_tipc_sk_create(sk, NULL, TIPC_DUMP_NONE, " "); return 0; } From 055d88242a6046a1ceac3167290f054c72571cd9 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 30 Jul 2019 21:25:20 +0200 Subject: [PATCH 612/823] compat_ioctl: pppoe: fix PPPOEIOCSFWD handling Support for handling the PPPOEIOCSFWD ioctl in compat mode was added in linux-2.5.69 along with hundreds of other commands, but was always broken sincen only the structure is compatible, but the command number is not, due to the size being sizeof(size_t), or at first sizeof(sizeof((struct sockaddr_pppox)), which is different on 64-bit architectures. Guillaume Nault adds: And the implementation was broken until 2016 (see 29e73269aa4d ("pppoe: fix reference counting in PPPoE proxy")), and nobody ever noticed. I should probably have removed this ioctl entirely instead of fixing it. Clearly, it has never been used. Fix it by adding a compat_ioctl handler for all pppoe variants that translates the command number and then calls the regular ioctl function. All other ioctl commands handled by pppoe are compatible between 32-bit and 64-bit, and require compat_ptr() conversion. This should apply to all stable kernels. Acked-by: Guillaume Nault Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ppp/pppoe.c | 3 +++ drivers/net/ppp/pppox.c | 13 +++++++++++++ drivers/net/ppp/pptp.c | 3 +++ fs/compat_ioctl.c | 3 --- include/linux/if_pppox.h | 3 +++ net/l2tp/l2tp_ppp.c | 3 +++ 6 files changed, 25 insertions(+), 3 deletions(-) diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 1d902ecb4aa8..a44dd3c8af63 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -1115,6 +1115,9 @@ static const struct proto_ops pppoe_ops = { .recvmsg = pppoe_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = pppox_compat_ioctl, +#endif }; static const struct pppox_proto pppoe_proto = { diff --git a/drivers/net/ppp/pppox.c b/drivers/net/ppp/pppox.c index 5ef422a43d70..08364f10a43f 100644 --- a/drivers/net/ppp/pppox.c +++ b/drivers/net/ppp/pppox.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -98,6 +99,18 @@ int pppox_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) EXPORT_SYMBOL(pppox_ioctl); +#ifdef CONFIG_COMPAT +int pppox_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + if (cmd == PPPOEIOCSFWD32) + cmd = PPPOEIOCSFWD; + + return pppox_ioctl(sock, cmd, (unsigned long)compat_ptr(arg)); +} + +EXPORT_SYMBOL(pppox_compat_ioctl); +#endif + static int pppox_create(struct net *net, struct socket *sock, int protocol, int kern) { diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index a8e52c8e4128..734de7de03f7 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -623,6 +623,9 @@ static const struct proto_ops pptp_ops = { .recvmsg = sock_no_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = pppox_compat_ioctl, +#endif }; static const struct pppox_proto pppox_pptp_proto = { diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 6e30949d9f77..a7ec2d3dff92 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -638,9 +638,6 @@ COMPATIBLE_IOCTL(PPPIOCDISCONN) COMPATIBLE_IOCTL(PPPIOCATTCHAN) COMPATIBLE_IOCTL(PPPIOCGCHAN) COMPATIBLE_IOCTL(PPPIOCGL2TPSTATS) -/* PPPOX */ -COMPATIBLE_IOCTL(PPPOEIOCSFWD) -COMPATIBLE_IOCTL(PPPOEIOCDFWD) /* Big A */ /* sparc only */ /* Big Q for sound/OSS */ diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h index 8b728750a625..69e813bcb947 100644 --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -80,6 +80,9 @@ extern int register_pppox_proto(int proto_num, const struct pppox_proto *pp); extern void unregister_pppox_proto(int proto_num); extern void pppox_unbind_sock(struct sock *sk);/* delete ppp-channel binding */ extern int pppox_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); +extern int pppox_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); + +#define PPPOEIOCSFWD32 _IOW(0xB1 ,0, compat_size_t) /* PPPoX socket states */ enum { diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 1d0e5904dedf..c54cb59593ef 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1681,6 +1681,9 @@ static const struct proto_ops pppol2tp_ops = { .recvmsg = pppol2tp_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = pppox_compat_ioctl, +#endif }; static const struct pppox_proto pppol2tp_proto = { From fc2e634e997d84f2610a482b500865ef2c04fcde Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 20 Jul 2019 10:03:32 +1000 Subject: [PATCH 613/823] kselftest: save-and-restore errno to allow for %m formatting Previously, using "%m" in a ksft_* format string can result in strange output because the errno value wasn't saved before calling other libc functions. The solution is to simply save and restore the errno before we format the user-supplied format string. Signed-off-by: Aleksa Sarai Signed-off-by: Shuah Khan --- tools/testing/selftests/kselftest.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index ec15c4f6af55..0ac49d91a260 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -10,6 +10,7 @@ #ifndef __KSELFTEST_H #define __KSELFTEST_H +#include #include #include #include @@ -81,58 +82,68 @@ static inline void ksft_print_cnts(void) static inline void ksft_print_msg(const char *msg, ...) { + int saved_errno = errno; va_list args; va_start(args, msg); printf("# "); + errno = saved_errno; vprintf(msg, args); va_end(args); } static inline void ksft_test_result_pass(const char *msg, ...) { + int saved_errno = errno; va_list args; ksft_cnt.ksft_pass++; va_start(args, msg); printf("ok %d ", ksft_test_num()); + errno = saved_errno; vprintf(msg, args); va_end(args); } static inline void ksft_test_result_fail(const char *msg, ...) { + int saved_errno = errno; va_list args; ksft_cnt.ksft_fail++; va_start(args, msg); printf("not ok %d ", ksft_test_num()); + errno = saved_errno; vprintf(msg, args); va_end(args); } static inline void ksft_test_result_skip(const char *msg, ...) { + int saved_errno = errno; va_list args; ksft_cnt.ksft_xskip++; va_start(args, msg); printf("not ok %d # SKIP ", ksft_test_num()); + errno = saved_errno; vprintf(msg, args); va_end(args); } static inline void ksft_test_result_error(const char *msg, ...) { + int saved_errno = errno; va_list args; ksft_cnt.ksft_error++; va_start(args, msg); printf("not ok %d # error ", ksft_test_num()); + errno = saved_errno; vprintf(msg, args); va_end(args); } @@ -152,10 +163,12 @@ static inline int ksft_exit_fail(void) static inline int ksft_exit_fail_msg(const char *msg, ...) { + int saved_errno = errno; va_list args; va_start(args, msg); printf("Bail out! "); + errno = saved_errno; vprintf(msg, args); va_end(args); @@ -178,10 +191,12 @@ static inline int ksft_exit_xpass(void) static inline int ksft_exit_skip(const char *msg, ...) { if (msg) { + int saved_errno = errno; va_list args; va_start(args, msg); printf("not ok %d # SKIP ", 1 + ksft_test_num()); + errno = saved_errno; vprintf(msg, args); va_end(args); } else { From fbb01c52471c8fb4ec2422c0ab26c134bd90bbff Mon Sep 17 00:00:00 2001 From: Joe Lawrence Date: Thu, 18 Jul 2019 16:29:48 -0400 Subject: [PATCH 614/823] selftests/livepatch: push and pop dynamic debug config The livepatching self-tests tweak the dynamic debug config to verify the kernel log during the tests. Enhance set_dynamic_debug() so that the config changes are restored when the script exits. Note this functionality needs to keep in sync with: - dynamic_debug input/output formatting - functions affected by set_dynamic_debug() For example, push_dynamic_debug() transforms: kernel/livepatch/transition.c:530 [livepatch]klp_init_transition =_ "'%s': initializing %s transition\012" to the following: file kernel/livepatch/transition.c line 530 =_ Signed-off-by: Joe Lawrence Tested-by: Petr Mladek Signed-off-by: Shuah Khan --- .../testing/selftests/livepatch/functions.sh | 26 ++++++++++++++----- 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index edcfeace4655..79b0affd21fb 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -29,13 +29,27 @@ function die() { exit 1 } -# set_dynamic_debug() - setup kernel dynamic debug -# TODO - push and pop this config? +function push_dynamic_debug() { + DYNAMIC_DEBUG=$(grep '^kernel/livepatch' /sys/kernel/debug/dynamic_debug/control | \ + awk -F'[: ]' '{print "file " $1 " line " $2 " " $4}') +} + +function pop_dynamic_debug() { + if [[ -n "$DYNAMIC_DEBUG" ]]; then + echo -n "$DYNAMIC_DEBUG" > /sys/kernel/debug/dynamic_debug/control + fi +} + +# set_dynamic_debug() - save the current dynamic debug config and tweak +# it for the self-tests. Set a script exit trap +# that restores the original config. function set_dynamic_debug() { - cat << EOF > /sys/kernel/debug/dynamic_debug/control -file kernel/livepatch/* +p -func klp_try_switch_task -p -EOF + push_dynamic_debug + trap pop_dynamic_debug EXIT INT TERM HUP + cat <<-EOF > /sys/kernel/debug/dynamic_debug/control + file kernel/livepatch/* +p + func klp_try_switch_task -p + EOF } # loop_until(cmd) - loop a command until it is successful or $MAX_RETRIES, From abb48f801396ba312e95f3c11072425221ce7401 Mon Sep 17 00:00:00 2001 From: xiaofeis Date: Sun, 28 Jul 2019 08:57:50 +0800 Subject: [PATCH 615/823] net: dsa: qca8k: enable port flow control Set phy device advertising to enable MAC flow control. Signed-off-by: Xiaofei Shen Signed-off-by: David S. Miller --- drivers/net/dsa/qca8k.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 232e8cc96f6d..e429e92dedf4 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -2,7 +2,7 @@ /* * Copyright (C) 2009 Felix Fietkau * Copyright (C) 2011-2012 Gabor Juhos - * Copyright (c) 2015, The Linux Foundation. All rights reserved. + * Copyright (c) 2015, 2019, The Linux Foundation. All rights reserved. * Copyright (c) 2016 John Crispin */ @@ -935,6 +935,8 @@ qca8k_port_enable(struct dsa_switch *ds, int port, qca8k_port_set_status(priv, port, 1); priv->port_sts[port].enabled = 1; + phy_support_asym_pause(phy); + return 0; } From a9446a906f52292c52ecbd5be78eaa4d8395756c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 28 Jul 2019 15:12:52 +0200 Subject: [PATCH 616/823] lib/vdso/32: Remove inconsistent NULL pointer checks The 32bit variants of vdso_clock_gettime()/getres() have a NULL pointer check for the timespec pointer. That's inconsistent vs. 64bit. But the vdso implementation will never be consistent versus the syscall because the only case which it can handle is NULL. Any other invalid pointer will cause a segfault. So special casing NULL is not really useful. Remove it along with the superflouos syscall fallback invocation as that will return -EFAULT anyway. That also gets rid of the dubious typecast which only works because the pointer is NULL. Fixes: 00b26474c2f1 ("lib/vdso: Provide generic VDSO implementation") Signed-off-by: Thomas Gleixner Tested-by: Vincenzo Frascino Reviewed-by: Vincenzo Frascino Reviewed-by: Andy Lutomirski Link: https://lkml.kernel.org/r/20190728131648.587523358@linutronix.de --- lib/vdso/gettimeofday.c | 18 ++---------------- 1 file changed, 2 insertions(+), 16 deletions(-) diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c index 2d1c1f241fd9..e28f5a607a5f 100644 --- a/lib/vdso/gettimeofday.c +++ b/lib/vdso/gettimeofday.c @@ -115,9 +115,6 @@ __cvdso_clock_gettime32(clockid_t clock, struct old_timespec32 *res) struct __kernel_timespec ts; int ret; - if (res == NULL) - goto fallback; - ret = __cvdso_clock_gettime(clock, &ts); if (ret == 0) { @@ -126,9 +123,6 @@ __cvdso_clock_gettime32(clockid_t clock, struct old_timespec32 *res) } return ret; - -fallback: - return clock_gettime_fallback(clock, (struct __kernel_timespec *)res); } static __maybe_unused int @@ -204,10 +198,8 @@ int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res) goto fallback; } - if (res) { - res->tv_sec = 0; - res->tv_nsec = ns; - } + res->tv_sec = 0; + res->tv_nsec = ns; return 0; @@ -221,9 +213,6 @@ __cvdso_clock_getres_time32(clockid_t clock, struct old_timespec32 *res) struct __kernel_timespec ts; int ret; - if (res == NULL) - goto fallback; - ret = __cvdso_clock_getres(clock, &ts); if (ret == 0) { @@ -232,8 +221,5 @@ __cvdso_clock_getres_time32(clockid_t clock, struct old_timespec32 *res) } return ret; - -fallback: - return clock_getres_fallback(clock, (struct __kernel_timespec *)res); } #endif /* VDSO_HAS_CLOCK_GETRES */ From 502a590a170b3b3d0ad998ee0b639ac0b3db1dfa Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 28 Jul 2019 15:12:53 +0200 Subject: [PATCH 617/823] lib/vdso: Move fallback invocation to the callers To allow syscall fallbacks using the legacy 32bit syscall for 32bit VDSO builds, move the fallback invocation out into the callers. Split the common code out of __cvdso_clock_gettime/getres() and invoke the syscall fallback in the 64bit and 32bit variants. Preparatory work for using legacy syscalls in 32bit VDSO. No functional change. Fixes: 00b26474c2f1 ("lib/vdso: Provide generic VDSO implementation") Signed-off-by: Thomas Gleixner Tested-by: Vincenzo Frascino Reviewed-by: Andy Lutomirski Reviewed-by: Vincenzo Frascino Link: https://lkml.kernel.org/r/20190728131648.695579736@linutronix.de --- lib/vdso/gettimeofday.c | 53 ++++++++++++++++++++++++++++------------- 1 file changed, 36 insertions(+), 17 deletions(-) diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c index e28f5a607a5f..a9e7fd029593 100644 --- a/lib/vdso/gettimeofday.c +++ b/lib/vdso/gettimeofday.c @@ -51,7 +51,7 @@ static int do_hres(const struct vdso_data *vd, clockid_t clk, ns = vdso_ts->nsec; last = vd->cycle_last; if (unlikely((s64)cycles < 0)) - return clock_gettime_fallback(clk, ts); + return -1; ns += vdso_calc_delta(cycles, last, vd->mask, vd->mult); ns >>= vd->shift; @@ -82,14 +82,14 @@ static void do_coarse(const struct vdso_data *vd, clockid_t clk, } static __maybe_unused int -__cvdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) +__cvdso_clock_gettime_common(clockid_t clock, struct __kernel_timespec *ts) { const struct vdso_data *vd = __arch_get_vdso_data(); u32 msk; /* Check for negative values or invalid clocks */ if (unlikely((u32) clock >= MAX_CLOCKS)) - goto fallback; + return -1; /* * Convert the clockid to a bitmask and use it to check which @@ -104,9 +104,17 @@ __cvdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) } else if (msk & VDSO_RAW) { return do_hres(&vd[CS_RAW], clock, ts); } + return -1; +} -fallback: - return clock_gettime_fallback(clock, ts); +static __maybe_unused int +__cvdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) +{ + int ret = __cvdso_clock_gettime_common(clock, ts); + + if (unlikely(ret)) + return clock_gettime_fallback(clock, ts); + return 0; } static __maybe_unused int @@ -115,9 +123,12 @@ __cvdso_clock_gettime32(clockid_t clock, struct old_timespec32 *res) struct __kernel_timespec ts; int ret; - ret = __cvdso_clock_gettime(clock, &ts); + ret = __cvdso_clock_gettime_common(clock, &ts); - if (ret == 0) { + if (unlikely(ret)) + ret = clock_gettime_fallback(clock, &ts); + + if (likely(!ret)) { res->tv_sec = ts.tv_sec; res->tv_nsec = ts.tv_nsec; } @@ -163,17 +174,18 @@ static __maybe_unused time_t __cvdso_time(time_t *time) #ifdef VDSO_HAS_CLOCK_GETRES static __maybe_unused -int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res) +int __cvdso_clock_getres_common(clockid_t clock, struct __kernel_timespec *res) { const struct vdso_data *vd = __arch_get_vdso_data(); - u64 ns; + u64 hrtimer_res; u32 msk; - u64 hrtimer_res = READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res); + u64 ns; /* Check for negative values or invalid clocks */ if (unlikely((u32) clock >= MAX_CLOCKS)) - goto fallback; + return -1; + hrtimer_res = READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res); /* * Convert the clockid to a bitmask and use it to check which * clocks are handled in the VDSO directly. @@ -195,16 +207,22 @@ int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res) */ ns = hrtimer_res; } else { - goto fallback; + return -1; } res->tv_sec = 0; res->tv_nsec = ns; return 0; +} -fallback: - return clock_getres_fallback(clock, res); +int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res) +{ + int ret = __cvdso_clock_getres_common(clock, res); + + if (unlikely(ret)) + return clock_getres_fallback(clock, res); + return 0; } static __maybe_unused int @@ -213,13 +231,14 @@ __cvdso_clock_getres_time32(clockid_t clock, struct old_timespec32 *res) struct __kernel_timespec ts; int ret; - ret = __cvdso_clock_getres(clock, &ts); + ret = __cvdso_clock_getres_common(clock, &ts); + if (unlikely(ret)) + ret = clock_getres_fallback(clock, &ts); - if (ret == 0) { + if (likely(!ret)) { res->tv_sec = ts.tv_sec; res->tv_nsec = ts.tv_nsec; } - return ret; } #endif /* VDSO_HAS_CLOCK_GETRES */ From c60a32ea4f459f99b98d383cad3b1ac7cfb3f4be Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 30 Jul 2019 11:38:50 +0200 Subject: [PATCH 618/823] lib/vdso/32: Provide legacy syscall fallbacks To address the regression which causes seccomp to deny applications the access to clock_gettime64() and clock_getres64() syscalls because they are not enabled in the existing filters. That trips over the fact that 32bit VDSOs use the new clock_gettime64() and clock_getres64() syscalls in the fallback path. Add a conditional to invoke the 32bit legacy fallback syscalls instead of the new 64bit variants. The conditional can go away once all architectures are converted. Fixes: 00b26474c2f1 ("lib/vdso: Provide generic VDSO implementation") Signed-off-by: Thomas Gleixner Tested-by: Sean Christopherson Reviewed-by: Sean Christopherson Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1907301134470.1738@nanos.tec.linutronix.de --- lib/vdso/gettimeofday.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c index a9e7fd029593..e630e7ff57f1 100644 --- a/lib/vdso/gettimeofday.c +++ b/lib/vdso/gettimeofday.c @@ -125,14 +125,18 @@ __cvdso_clock_gettime32(clockid_t clock, struct old_timespec32 *res) ret = __cvdso_clock_gettime_common(clock, &ts); +#ifdef VDSO_HAS_32BIT_FALLBACK + if (unlikely(ret)) + return clock_gettime32_fallback(clock, res); +#else if (unlikely(ret)) ret = clock_gettime_fallback(clock, &ts); +#endif if (likely(!ret)) { res->tv_sec = ts.tv_sec; res->tv_nsec = ts.tv_nsec; } - return ret; } @@ -232,8 +236,14 @@ __cvdso_clock_getres_time32(clockid_t clock, struct old_timespec32 *res) int ret; ret = __cvdso_clock_getres_common(clock, &ts); + +#ifdef VDSO_HAS_32BIT_FALLBACK + if (unlikely(ret)) + return clock_getres32_fallback(clock, res); +#else if (unlikely(ret)) ret = clock_getres_fallback(clock, &ts); +#endif if (likely(!ret)) { res->tv_sec = ts.tv_sec; From d2f5d3fa26196183adb44a413c44caa9872275b4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 28 Jul 2019 15:12:55 +0200 Subject: [PATCH 619/823] x86/vdso/32: Use 32bit syscall fallback The generic VDSO implementation uses the Y2038 safe clock_gettime64() and clock_getres_time64() syscalls as fallback for 32bit VDSO. This breaks seccomp setups because these syscalls might be not (yet) allowed. Implement the 32bit variants which use the legacy syscalls and select the variant in the core library. The 64bit time variants are not removed because they are required for the time64 based vdso accessors. Fixes: 7ac870747988 ("x86/vdso: Switch to generic vDSO implementation") Reported-by: Sean Christopherson Reported-by: Paul Bolle Suggested-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Vincenzo Frascino Reviewed-by: Andy Lutomirski Link: https://lkml.kernel.org/r/20190728131648.879156507@linutronix.de --- arch/x86/include/asm/vdso/gettimeofday.h | 36 ++++++++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h index ae91429129a6..ba71a63cdac4 100644 --- a/arch/x86/include/asm/vdso/gettimeofday.h +++ b/arch/x86/include/asm/vdso/gettimeofday.h @@ -96,6 +96,8 @@ long clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) #else +#define VDSO_HAS_32BIT_FALLBACK 1 + static __always_inline long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) { @@ -113,6 +115,23 @@ long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) return ret; } +static __always_inline +long clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + long ret; + + asm ( + "mov %%ebx, %%edx \n" + "mov %[clock], %%ebx \n" + "call __kernel_vsyscall \n" + "mov %%edx, %%ebx \n" + : "=a" (ret), "=m" (*_ts) + : "0" (__NR_clock_gettime), [clock] "g" (_clkid), "c" (_ts) + : "edx"); + + return ret; +} + static __always_inline long gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz) @@ -148,6 +167,23 @@ clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) return ret; } +static __always_inline +long clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + long ret; + + asm ( + "mov %%ebx, %%edx \n" + "mov %[clock], %%ebx \n" + "call __kernel_vsyscall \n" + "mov %%edx, %%ebx \n" + : "=a" (ret), "=m" (*_ts) + : "0" (__NR_clock_getres), [clock] "g" (_clkid), "c" (_ts) + : "edx"); + + return ret; +} + #endif #ifdef CONFIG_PARAVIRT_CLOCK From 33a58980ff3cc5dbf0bb1b325746ac69223eda0b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 28 Jul 2019 15:12:56 +0200 Subject: [PATCH 620/823] arm64: compat: vdso: Use legacy syscalls as fallback The generic VDSO implementation uses the Y2038 safe clock_gettime64() and clock_getres_time64() syscalls as fallback for 32bit VDSO. This breaks seccomp setups because these syscalls might be not (yet) allowed. Implement the 32bit variants which use the legacy syscalls and select the variant in the core library. The 64bit time variants are not removed because they are required for the time64 based vdso accessors. Fixes: 00b26474c2f1 ("lib/vdso: Provide generic VDSO implementation") Reported-by: Sean Christopherson Reported-by: Paul Bolle Suggested-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Tested-by: Vincenzo Frascino Reviewed-by: Vincenzo Frascino Link: https://lkml.kernel.org/r/20190728131648.971361611@linutronix.de --- .../include/asm/vdso/compat_gettimeofday.h | 40 +++++++++++++++++++ 1 file changed, 40 insertions(+) diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h index f4812777f5c5..c50ee1b7d5cd 100644 --- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h +++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h @@ -16,6 +16,8 @@ #define VDSO_HAS_CLOCK_GETRES 1 +#define VDSO_HAS_32BIT_FALLBACK 1 + static __always_inline int gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz) @@ -51,6 +53,23 @@ long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) return ret; } +static __always_inline +long clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + register struct old_timespec32 *ts asm("r1") = _ts; + register clockid_t clkid asm("r0") = _clkid; + register long ret asm ("r0"); + register long nr asm("r7") = __NR_compat_clock_gettime; + + asm volatile( + " swi #0\n" + : "=r" (ret) + : "r" (clkid), "r" (ts), "r" (nr) + : "memory"); + + return ret; +} + static __always_inline int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) { @@ -72,6 +91,27 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) return ret; } +static __always_inline +int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + register struct old_timespec32 *ts asm("r1") = _ts; + register clockid_t clkid asm("r0") = _clkid; + register long ret asm ("r0"); + register long nr asm("r7") = __NR_compat_clock_getres; + + /* The checks below are required for ABI consistency with arm */ + if ((_clkid >= MAX_CLOCKS) && (_ts == NULL)) + return -EINVAL; + + asm volatile( + " swi #0\n" + : "=r" (ret) + : "r" (clkid), "r" (ts), "r" (nr) + : "memory"); + + return ret; +} + static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) { u64 res; From 5348deb138abb90ca8f728356772e38abc791cf9 Mon Sep 17 00:00:00 2001 From: Pankaj Gupta Date: Tue, 30 Jul 2019 17:07:08 +0530 Subject: [PATCH 621/823] dm table: fix dax_dev NULL dereference in device_synchronous() If a device doesn't support DAX its 'dax_dev' is NULL. Fix device_synchronous() to first check if dax_dev is NULL before dereferencing it. Fixes: 2e9ee0955d3c ("dm: enable synchronous dax") Reported-by: jencce.kernel@gmail.com Signed-off-by: Pankaj Gupta Acked-by: Dan Williams Signed-off-by: Mike Snitzer --- drivers/md/dm-table.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index caaee8032afe..12857beaa7f9 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -894,7 +894,7 @@ int device_supports_dax(struct dm_target *ti, struct dm_dev *dev, static int device_synchronous(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - return dax_synchronous(dev->dax_dev); + return dev->dax_dev && dax_synchronous(dev->dax_dev); } bool dm_table_supports_dax(struct dm_table *t, From 9c50a98f55f4b123227eebb25009524d20bc4c2a Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 30 Jul 2019 14:39:43 -0400 Subject: [PATCH 622/823] dm table: fix various whitespace issues with recent DAX code Also, rename device_synchronous to device_dax_synchronous. Signed-off-by: Mike Snitzer --- drivers/md/dm-table.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 12857beaa7f9..7b6c3ee9e755 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -882,23 +882,23 @@ EXPORT_SYMBOL_GPL(dm_table_set_type); /* validate the dax capability of the target device span */ int device_supports_dax(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) + sector_t start, sector_t len, void *data) { int blocksize = *(int *) data; return generic_fsdax_supported(dev->dax_dev, dev->bdev, blocksize, - start, len); + start, len); } /* Check devices support synchronous DAX */ -static int device_synchronous(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static int device_dax_synchronous(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { return dev->dax_dev && dax_synchronous(dev->dax_dev); } bool dm_table_supports_dax(struct dm_table *t, - iterate_devices_callout_fn iterate_fn, int *blocksize) + iterate_devices_callout_fn iterate_fn, int *blocksize) { struct dm_target *ti; unsigned i; @@ -911,7 +911,7 @@ bool dm_table_supports_dax(struct dm_table *t, return false; if (!ti->type->iterate_devices || - !ti->type->iterate_devices(ti, iterate_fn, blocksize)) + !ti->type->iterate_devices(ti, iterate_fn, blocksize)) return false; } @@ -1921,7 +1921,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, if (dm_table_supports_dax(t, device_supports_dax, &page_size)) { blk_queue_flag_set(QUEUE_FLAG_DAX, q); - if (dm_table_supports_dax(t, device_synchronous, NULL)) + if (dm_table_supports_dax(t, device_dax_synchronous, NULL)) set_dax_synchronous(t->md->dax_dev); } else From b1d45c23284e55a379f85554a27a548b7988d47a Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 20 Jul 2019 19:39:43 +0900 Subject: [PATCH 623/823] tracing: Fix header include guards in trace event headers These include guards are broken. Match the #if !define() and #define lines so that they work correctly. Link: http://lkml.kernel.org/r/20190720103943.16982-1-yamada.masahiro@socionext.com Fixes: f54d1867005c3 ("dma-buf: Rename struct fence to dma_fence") Fixes: 2e26ca7150a4f ("tracing: Fix tracepoint.h DECLARE_TRACE() to allow more than one header") Fixes: e543002f77f46 ("qdisc: add tracepoint qdisc:qdisc_dequeue for dequeued SKBs") Fixes: 95f295f9fe081 ("dmaengine: tegra: add tracepoints to driver") Signed-off-by: Masahiro Yamada Signed-off-by: Steven Rostedt (VMware) --- include/trace/events/dma_fence.h | 2 +- include/trace/events/napi.h | 4 ++-- include/trace/events/qdisc.h | 4 ++-- include/trace/events/tegra_apb_dma.h | 4 ++-- 4 files changed, 7 insertions(+), 7 deletions(-) diff --git a/include/trace/events/dma_fence.h b/include/trace/events/dma_fence.h index 2212adda8f77..64e92d56c6a8 100644 --- a/include/trace/events/dma_fence.h +++ b/include/trace/events/dma_fence.h @@ -2,7 +2,7 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM dma_fence -#if !defined(_TRACE_FENCE_H) || defined(TRACE_HEADER_MULTI_READ) +#if !defined(_TRACE_DMA_FENCE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_DMA_FENCE_H #include diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h index f3a12566bed0..6678cf8b235b 100644 --- a/include/trace/events/napi.h +++ b/include/trace/events/napi.h @@ -3,7 +3,7 @@ #define TRACE_SYSTEM napi #if !defined(_TRACE_NAPI_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_NAPI_H_ +#define _TRACE_NAPI_H #include #include @@ -38,7 +38,7 @@ TRACE_EVENT(napi_poll, #undef NO_DEV -#endif /* _TRACE_NAPI_H_ */ +#endif /* _TRACE_NAPI_H */ /* This part must be outside protection */ #include diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h index 60d0d8bd336d..0d1a9ebf55ba 100644 --- a/include/trace/events/qdisc.h +++ b/include/trace/events/qdisc.h @@ -2,7 +2,7 @@ #define TRACE_SYSTEM qdisc #if !defined(_TRACE_QDISC_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_QDISC_H_ +#define _TRACE_QDISC_H #include #include @@ -44,7 +44,7 @@ TRACE_EVENT(qdisc_dequeue, __entry->txq_state, __entry->packets, __entry->skbaddr ) ); -#endif /* _TRACE_QDISC_H_ */ +#endif /* _TRACE_QDISC_H */ /* This part must be outside protection */ #include diff --git a/include/trace/events/tegra_apb_dma.h b/include/trace/events/tegra_apb_dma.h index 0818f6286110..971cd02d2daf 100644 --- a/include/trace/events/tegra_apb_dma.h +++ b/include/trace/events/tegra_apb_dma.h @@ -1,5 +1,5 @@ #if !defined(_TRACE_TEGRA_APB_DMA_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_TEGRA_APM_DMA_H +#define _TRACE_TEGRA_APB_DMA_H #include #include @@ -55,7 +55,7 @@ TRACE_EVENT(tegra_dma_isr, TP_printk("%s: irq %d\n", __get_str(chan), __entry->irq) ); -#endif /* _TRACE_TEGRADMA_H */ +#endif /* _TRACE_TEGRA_APB_DMA_H */ /* This part must be outside protection */ #include From 6c77221df96177da0520847ce91e33f539fb8b2d Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Tue, 30 Jul 2019 22:08:50 +0800 Subject: [PATCH 624/823] fgraph: Remove redundant ftrace_graph_notrace_addr() test We already have tested it before. The second one should be removed. With this change, the performance should have little improvement. Link: http://lkml.kernel.org/r/20190730140850.7927-1-changbin.du@gmail.com Cc: stable@vger.kernel.org Fixes: 9cd2992f2d6c ("fgraph: Have set_graph_notrace only affect function_graph tracer") Signed-off-by: Changbin Du Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_functions_graph.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 69ebf3c2f1b5..78af97163147 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -137,6 +137,13 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) return 0; + /* + * Do not trace a function if it's filtered by set_graph_notrace. + * Make the index of ret stack negative to indicate that it should + * ignore further functions. But it needs its own ret stack entry + * to recover the original index in order to continue tracing after + * returning from the function. + */ if (ftrace_graph_notrace_addr(trace->func)) { trace_recursion_set(TRACE_GRAPH_NOTRACE_BIT); /* @@ -155,16 +162,6 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) if (ftrace_graph_ignore_irqs()) return 0; - /* - * Do not trace a function if it's filtered by set_graph_notrace. - * Make the index of ret stack negative to indicate that it should - * ignore further functions. But it needs its own ret stack entry - * to recover the original index in order to continue tracing after - * returning from the function. - */ - if (ftrace_graph_notrace_addr(trace->func)) - return 1; - /* * Stop here if tracing_threshold is set. We only write function return * events to the ring buffer. From d65848657c3da5c0d4b685f823d0230f151ab34e Mon Sep 17 00:00:00 2001 From: Kent Russell Date: Tue, 23 Jul 2019 10:18:01 -0400 Subject: [PATCH 625/823] drm/amdkfd: Fix byte align on VegaM This was missed during the addition of VegaM support Reviewed-by: Alex Deucher Signed-off-by: Kent Russell Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 1d3ee9c42f7e..6a5c96e519b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1140,7 +1140,8 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( adev->asic_type != CHIP_FIJI && adev->asic_type != CHIP_POLARIS10 && adev->asic_type != CHIP_POLARIS11 && - adev->asic_type != CHIP_POLARIS12) ? + adev->asic_type != CHIP_POLARIS12 && + adev->asic_type != CHIP_VEGAM) ? VI_BO_SIZE_ALIGN : 1; mapping_flags = AMDGPU_VM_PAGE_READABLE; From 2c0f07fe3ca57c8fb4ee179c9fb50d6eba75349e Mon Sep 17 00:00:00 2001 From: Kevin Wang Date: Mon, 3 Jun 2019 15:58:31 +0800 Subject: [PATCH 626/823] drm/amd/powerplay: add callback function of get_thermal_temperature_range 1. the thermal temperature is asic related data, move the code logic to xxx_ppt.c. 2. replace data structure PP_TemperatureRange with smu_temperature_range. 3. change temperature uint from temp*1000 to temp (temperature uint). Signed-off-by: Kevin Wang Signed-off-by: Kenneth Feng Acked-by: Huang Rui Signed-off-by: Alex Deucher --- .../gpu/drm/amd/powerplay/inc/amdgpu_smu.h | 1 - drivers/gpu/drm/amd/powerplay/navi10_ppt.c | 17 ++++++++++ drivers/gpu/drm/amd/powerplay/smu_v11_0.c | 18 ++++++---- drivers/gpu/drm/amd/powerplay/vega20_ppt.c | 34 ++++++------------- 4 files changed, 40 insertions(+), 30 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h index 22e46a289a16..208e6711d506 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h @@ -429,7 +429,6 @@ struct smu_table_context struct smu_table *tables; uint32_t table_count; struct smu_table memory_pool; - uint16_t software_shutdown_temp; uint8_t thermal_controller_type; uint16_t TDPODLimit; diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 4aaad255a288..3f68268a8733 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -1620,6 +1620,22 @@ static int navi10_set_performance_level(struct smu_context *smu, enum amd_dpm_fo return ret; } +static int navi10_get_thermal_temperature_range(struct smu_context *smu, + struct smu_temperature_range *range) +{ + struct smu_table_context *table_context = &smu->smu_table; + struct smu_11_0_powerplay_table *powerplay_table = table_context->power_play_table; + + if (!range || !powerplay_table) + return -EINVAL; + + /* The unit is temperature */ + range->min = 0; + range->max = powerplay_table->software_shutdown_temp; + + return 0; +} + static const struct pptable_funcs navi10_ppt_funcs = { .tables_init = navi10_tables_init, .alloc_dpm_context = navi10_allocate_dpm_context, @@ -1657,6 +1673,7 @@ static const struct pptable_funcs navi10_ppt_funcs = { .get_ppfeature_status = navi10_get_ppfeature_status, .set_ppfeature_status = navi10_set_ppfeature_status, .set_performance_level = navi10_set_performance_level, + .get_thermal_temperature_range = navi10_get_thermal_temperature_range, }; void navi10_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c index caca9091bfcc..1ecb409e3bed 100644 --- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c +++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c @@ -1124,10 +1124,8 @@ static int smu_v11_0_set_thermal_range(struct smu_context *smu, struct smu_temperature_range *range) { struct amdgpu_device *adev = smu->adev; - int low = SMU_THERMAL_MINIMUM_ALERT_TEMP * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; - int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + int low = SMU_THERMAL_MINIMUM_ALERT_TEMP; + int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP; uint32_t val; if (!range) @@ -1138,6 +1136,9 @@ static int smu_v11_0_set_thermal_range(struct smu_context *smu, if (high > range->max) high = range->max; + low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP, range->min); + high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP, range->max); + if (low > high) return -EINVAL; @@ -1146,8 +1147,8 @@ static int smu_v11_0_set_thermal_range(struct smu_context *smu, val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1); val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_INTH_MASK, 0); val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_INTL_MASK, 0); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES)); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES)); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high & 0xff)); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low & 0xff)); val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val); @@ -1186,7 +1187,10 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu) if (!smu->pm_enabled) return ret; + ret = smu_get_thermal_temperature_range(smu, &range); + if (ret) + return ret; if (smu->smu_table.thermal_controller_type) { ret = smu_v11_0_set_thermal_range(smu, &range); @@ -1211,6 +1215,8 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu) adev->pm.dpm.thermal.min_mem_temp = range.mem_min; adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max; adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max; + adev->pm.dpm.thermal.min_temp = range.min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.max_temp = range.max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; return ret; } diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c index dc139a6feeb1..dd6fd1c8bf24 100644 --- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c @@ -450,7 +450,6 @@ static int vega20_store_powerplay_table(struct smu_context *smu) memcpy(table_context->driver_pptable, &powerplay_table->smcPPTable, sizeof(PPTable_t)); - table_context->software_shutdown_temp = powerplay_table->usSoftwareShutdownTemp; table_context->thermal_controller_type = powerplay_table->ucThermalControllerType; table_context->TDPODLimit = le32_to_cpu(powerplay_table->OverDrive8Table.ODSettingsMax[ATOM_VEGA20_ODSETTING_POWERPERCENTAGE]); @@ -3234,35 +3233,24 @@ static int vega20_set_watermarks_table(struct smu_context *smu, return 0; } -static const struct smu_temperature_range vega20_thermal_policy[] = -{ - {-273150, 99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000}, - { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000}, -}; - static int vega20_get_thermal_temperature_range(struct smu_context *smu, struct smu_temperature_range *range) { - + struct smu_table_context *table_context = &smu->smu_table; + ATOM_Vega20_POWERPLAYTABLE *powerplay_table = table_context->power_play_table; PPTable_t *pptable = smu->smu_table.driver_pptable; - if (!range) + if (!range || !powerplay_table) return -EINVAL; - memcpy(range, &vega20_thermal_policy[0], sizeof(struct smu_temperature_range)); - - range->max = pptable->TedgeLimit * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; - range->edge_emergency_max = (pptable->TedgeLimit + CTF_OFFSET_EDGE) * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; - range->hotspot_crit_max = pptable->ThotspotLimit * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; - range->hotspot_emergency_max = (pptable->ThotspotLimit + CTF_OFFSET_HOTSPOT) * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; - range->mem_crit_max = pptable->ThbmLimit * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; - range->mem_emergency_max = (pptable->ThbmLimit + CTF_OFFSET_HBM)* - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + /* The unit is temperature */ + range->min = 0; + range->max = powerplay_table->usSoftwareShutdownTemp; + range->edge_emergency_max = (pptable->TedgeLimit + CTF_OFFSET_EDGE); + range->hotspot_crit_max = pptable->ThotspotLimit; + range->hotspot_emergency_max = (pptable->ThotspotLimit + CTF_OFFSET_HOTSPOT); + range->mem_crit_max = pptable->ThbmLimit; + range->mem_emergency_max = (pptable->ThbmLimit + CTF_OFFSET_HBM); return 0; From 45a660143bf90a35ab64df663b88d82c02a17091 Mon Sep 17 00:00:00 2001 From: Kevin Wang Date: Tue, 23 Jul 2019 19:56:52 +0800 Subject: [PATCH 627/823] drm/amd/powerplay: fix temperature granularity error in smu11 in this patch, drm/amd/powerplay: add callback function of get_thermal_temperature_range the driver missed temperature granularity change on other temperature. Signed-off-by: Kevin Wang Reviewed-by: Evan Quan Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/smu_v11_0.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c index 1ecb409e3bed..ac5b26228e75 100644 --- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c +++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c @@ -1206,15 +1206,15 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu) return ret; } - adev->pm.dpm.thermal.min_temp = range.min; - adev->pm.dpm.thermal.max_temp = range.max; - adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max; - adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min; - adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max; - adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max; - adev->pm.dpm.thermal.min_mem_temp = range.mem_min; - adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max; - adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max; + adev->pm.dpm.thermal.min_temp = range.min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.max_temp = range.max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.min_mem_temp = range.mem_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; adev->pm.dpm.thermal.min_temp = range.min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; adev->pm.dpm.thermal.max_temp = range.max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; From 090efd946d00cd23ce4ac25bce125f408b704d7d Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 25 Jul 2019 22:28:58 -0500 Subject: [PATCH 628/823] drm/amdgpu/powerplay: use proper revision id for navi The PCI revision id determines the sku. Reviewed-by: Feifei Xu Reviewed-by: Kevin Wang Reviewed-by: Evan Quan Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/navi10_ppt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 3f68268a8733..be592d22bdcc 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -23,6 +23,7 @@ #include "pp_debug.h" #include +#include #include "amdgpu.h" #include "amdgpu_smu.h" #include "atomfirmware.h" @@ -1573,7 +1574,7 @@ static int navi10_set_peak_clock_by_device(struct smu_context *smu) uint32_t sclk_freq = 0, uclk_freq = 0; uint32_t uclk_level = 0; - switch (adev->rev_id) { + switch (adev->pdev->revision) { case 0xf0: /* XTX */ case 0xc0: sclk_freq = NAVI10_PEAK_SCLK_XTX; From 479156f2e5540077377a823eaf5a4263bd329063 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Thu, 25 Jul 2019 12:10:34 +0800 Subject: [PATCH 629/823] drm/amd/powerplay: fix null pointer dereference around dpm state relates DPM state relates are not supported on the new SW SMU ASICs. But still it's not OK to trigger null pointer dereference on accessing them. Signed-off-by: Evan Quan Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 18 +++++++++++++----- drivers/gpu/drm/amd/powerplay/amdgpu_smu.c | 3 ++- 2 files changed, 15 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 03ca8c69114f..8c90baca07b2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -159,12 +159,16 @@ static ssize_t amdgpu_get_dpm_state(struct device *dev, struct amdgpu_device *adev = ddev->dev_private; enum amd_pm_state_type pm; - if (is_support_sw_smu(adev) && adev->smu.ppt_funcs->get_current_power_state) - pm = amdgpu_smu_get_current_power_state(adev); - else if (adev->powerplay.pp_funcs->get_current_power_state) + if (is_support_sw_smu(adev)) { + if (adev->smu.ppt_funcs->get_current_power_state) + pm = amdgpu_smu_get_current_power_state(adev); + else + pm = adev->pm.dpm.user_state; + } else if (adev->powerplay.pp_funcs->get_current_power_state) { pm = amdgpu_dpm_get_current_power_state(adev); - else + } else { pm = adev->pm.dpm.user_state; + } return snprintf(buf, PAGE_SIZE, "%s\n", (pm == POWER_STATE_TYPE_BATTERY) ? "battery" : @@ -191,7 +195,11 @@ static ssize_t amdgpu_set_dpm_state(struct device *dev, goto fail; } - if (adev->powerplay.pp_funcs->dispatch_tasks) { + if (is_support_sw_smu(adev)) { + mutex_lock(&adev->pm.mutex); + adev->pm.dpm.user_state = state; + mutex_unlock(&adev->pm.mutex); + } else if (adev->powerplay.pp_funcs->dispatch_tasks) { amdgpu_dpm_dispatch_task(adev, AMD_PP_TASK_ENABLE_USER_STATE, &state); } else { mutex_lock(&adev->pm.mutex); diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index c097113c3976..88ed85e3d233 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -306,7 +306,8 @@ int smu_get_power_num_states(struct smu_context *smu, /* not support power state */ memset(state_info, 0, sizeof(struct pp_states_info)); - state_info->nums = 0; + state_info->nums = 1; + state_info->states[0] = POWER_STATE_TYPE_DEFAULT; return 0; } From f0bc1ee473fefd4d9f2ace9fad1cefdc0b7f6fdd Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Thu, 25 Jul 2019 10:12:42 +0800 Subject: [PATCH 630/823] drm/amd/powerplay: enable SW SMU reset functionality Move SMU irq handler register to sw_init as that's totally software related. Otherwise, it will prevent SMU reset working. Signed-off-by: Evan Quan Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/amdgpu_smu.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index 88ed85e3d233..93cd969e5cf5 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -724,6 +724,12 @@ static int smu_sw_init(void *handle) return ret; } + ret = smu_register_irq_handler(smu); + if (ret) { + pr_err("Failed to register smc irq handler!\n"); + return ret; + } + return 0; } @@ -733,6 +739,9 @@ static int smu_sw_fini(void *handle) struct smu_context *smu = &adev->smu; int ret; + kfree(smu->irq_source); + smu->irq_source = NULL; + ret = smu_smc_table_sw_fini(smu); if (ret) { pr_err("Failed to sw fini smc table!\n"); @@ -1089,10 +1098,6 @@ static int smu_hw_init(void *handle) if (ret) goto failed; - ret = smu_register_irq_handler(smu); - if (ret) - goto failed; - if (!smu->pm_enabled) adev->pm.dpm_enabled = false; else @@ -1122,9 +1127,6 @@ static int smu_hw_fini(void *handle) kfree(table_context->overdrive_table); table_context->overdrive_table = NULL; - kfree(smu->irq_source); - smu->irq_source = NULL; - ret = smu_fini_fb_allocations(smu); if (ret) return ret; From 8d1502f629c9966743de45744f4c1ba93a57d105 Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Wed, 31 Jul 2019 00:04:56 +0530 Subject: [PATCH 631/823] xen/gntdev.c: Replace vm_map_pages() with vm_map_pages_zero() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 'commit df9bde015a72 ("xen/gntdev.c: convert to use vm_map_pages()")' breaks gntdev driver. If vma->vm_pgoff > 0, vm_map_pages() will: - use map->pages starting at vma->vm_pgoff instead of 0 - verify map->count against vma_pages()+vma->vm_pgoff instead of just vma_pages(). In practice, this breaks using a single gntdev FD for mapping multiple grants. relevant strace output: [pid 857] ioctl(7, IOCTL_GNTDEV_MAP_GRANT_REF, 0x7ffd3407b6d0) = 0 [pid 857] mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_SHARED, 7, 0) = 0x777f1211b000 [pid 857] ioctl(7, IOCTL_GNTDEV_SET_UNMAP_NOTIFY, 0x7ffd3407b710) = 0 [pid 857] ioctl(7, IOCTL_GNTDEV_MAP_GRANT_REF, 0x7ffd3407b6d0) = 0 [pid 857] mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_SHARED, 7, 0x1000) = -1 ENXIO (No such device or address) details here: https://github.com/QubesOS/qubes-issues/issues/5199 The reason is -> ( copying Marek's word from discussion) vma->vm_pgoff is used as index passed to gntdev_find_map_index. It's basically using this parameter for "which grant reference to map". map struct returned by gntdev_find_map_index() describes just the pages to be mapped. Specifically map->pages[0] should be mapped at vma->vm_start, not vma->vm_start+vma->vm_pgoff*PAGE_SIZE. When trying to map grant with index (aka vma->vm_pgoff) > 1, __vm_map_pages() will refuse to map it because it will expect map->count to be at least vma_pages(vma)+vma->vm_pgoff, while it is exactly vma_pages(vma). Converting vm_map_pages() to use vm_map_pages_zero() will fix the problem. Marek has tested and confirmed the same. Cc: stable@vger.kernel.org # v5.2+ Fixes: df9bde015a72 ("xen/gntdev.c: convert to use vm_map_pages()") Reported-by: Marek Marczykowski-Górecki Signed-off-by: Souptick Joarder Tested-by: Marek Marczykowski-Górecki Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- drivers/xen/gntdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 4c339c7e66e5..a446a7221e13 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -1143,7 +1143,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) goto out_put_map; if (!use_ptemod) { - err = vm_map_pages(vma, map->pages, map->count); + err = vm_map_pages_zero(vma, map->pages, map->count); if (err) goto out_put_map; } else { From a78d14a31666c636a9e00a589032119fb59e3b94 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Jul 2019 09:46:29 +0200 Subject: [PATCH 632/823] xen: avoid link error on ARM Building the privcmd code as a loadable module on ARM, we get a link error due to the private cache management functions: ERROR: "__sync_icache_dcache" [drivers/xen/xen-privcmd.ko] undefined! Move the code into a new that is always built in when Xen is enabled, as suggested by Juergen Gross and Boris Ostrovsky. Signed-off-by: Arnd Bergmann Reviewed-by: Stefano Stabellini Signed-off-by: Juergen Gross --- drivers/xen/privcmd.c | 35 +++++------------------------------ drivers/xen/xlate_mmu.c | 32 ++++++++++++++++++++++++++++++++ include/xen/xen-ops.h | 3 +++ 3 files changed, 40 insertions(+), 30 deletions(-) diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 2f5ce7230a43..c6070e70dd73 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -724,25 +724,6 @@ static long privcmd_ioctl_restrict(struct file *file, void __user *udata) return 0; } -struct remap_pfn { - struct mm_struct *mm; - struct page **pages; - pgprot_t prot; - unsigned long i; -}; - -static int remap_pfn_fn(pte_t *ptep, unsigned long addr, void *data) -{ - struct remap_pfn *r = data; - struct page *page = r->pages[r->i]; - pte_t pte = pte_mkspecial(pfn_pte(page_to_pfn(page), r->prot)); - - set_pte_at(r->mm, addr, ptep, pte); - r->i++; - - return 0; -} - static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata) { struct privcmd_data *data = file->private_data; @@ -774,7 +755,8 @@ static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata) goto out; } - if (xen_feature(XENFEAT_auto_translated_physmap)) { + if (IS_ENABLED(CONFIG_XEN_AUTO_XLATE) && + xen_feature(XENFEAT_auto_translated_physmap)) { unsigned int nr = DIV_ROUND_UP(kdata.num, XEN_PFN_PER_PAGE); struct page **pages; unsigned int i; @@ -808,16 +790,9 @@ static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata) if (rc) goto out; - if (xen_feature(XENFEAT_auto_translated_physmap)) { - struct remap_pfn r = { - .mm = vma->vm_mm, - .pages = vma->vm_private_data, - .prot = vma->vm_page_prot, - }; - - rc = apply_to_page_range(r.mm, kdata.addr, - kdata.num << PAGE_SHIFT, - remap_pfn_fn, &r); + if (IS_ENABLED(CONFIG_XEN_AUTO_XLATE) && + xen_feature(XENFEAT_auto_translated_physmap)) { + rc = xen_remap_vma_range(vma, kdata.addr, kdata.num << PAGE_SHIFT); } else { unsigned int domid = (xdata.flags & XENMEM_rsrc_acq_caller_owned) ? diff --git a/drivers/xen/xlate_mmu.c b/drivers/xen/xlate_mmu.c index ba883a80b3c0..7b1077f0abcb 100644 --- a/drivers/xen/xlate_mmu.c +++ b/drivers/xen/xlate_mmu.c @@ -262,3 +262,35 @@ int __init xen_xlate_map_ballooned_pages(xen_pfn_t **gfns, void **virt, return 0; } EXPORT_SYMBOL_GPL(xen_xlate_map_ballooned_pages); + +struct remap_pfn { + struct mm_struct *mm; + struct page **pages; + pgprot_t prot; + unsigned long i; +}; + +static int remap_pfn_fn(pte_t *ptep, unsigned long addr, void *data) +{ + struct remap_pfn *r = data; + struct page *page = r->pages[r->i]; + pte_t pte = pte_mkspecial(pfn_pte(page_to_pfn(page), r->prot)); + + set_pte_at(r->mm, addr, ptep, pte); + r->i++; + + return 0; +} + +/* Used by the privcmd module, but has to be built-in on ARM */ +int xen_remap_vma_range(struct vm_area_struct *vma, unsigned long addr, unsigned long len) +{ + struct remap_pfn r = { + .mm = vma->vm_mm, + .pages = vma->vm_private_data, + .prot = vma->vm_page_prot, + }; + + return apply_to_page_range(vma->vm_mm, addr, len, remap_pfn_fn, &r); +} +EXPORT_SYMBOL_GPL(xen_remap_vma_range); diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 4969817124a8..98b30c1613b2 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -109,6 +109,9 @@ static inline int xen_xlate_unmap_gfn_range(struct vm_area_struct *vma, } #endif +int xen_remap_vma_range(struct vm_area_struct *vma, unsigned long addr, + unsigned long len); + /* * xen_remap_domain_gfn_array() - map an array of foreign frames by gfn * @vma: VMA to map the pages into From 67d0859e2758ef992fd32499747ce4b1038a63c0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 30 Jul 2019 11:17:03 +0200 Subject: [PATCH 633/823] drm/amdgpu: fix error handling in amdgpu_cs_process_fence_dep MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We always need to drop the ctx reference and should check for errors first and then dereference the fence pointer. Signed-off-by: Christian König Reviewed-by: Chunming Zhou Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index e069de8b54e6..4e4094f842e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1044,29 +1044,27 @@ static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p, return r; } - fence = amdgpu_ctx_get_fence(ctx, entity, - deps[i].handle); + fence = amdgpu_ctx_get_fence(ctx, entity, deps[i].handle); + amdgpu_ctx_put(ctx); + + if (IS_ERR(fence)) + return PTR_ERR(fence); + else if (!fence) + continue; if (chunk->chunk_id == AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES) { - struct drm_sched_fence *s_fence = to_drm_sched_fence(fence); + struct drm_sched_fence *s_fence; struct dma_fence *old = fence; + s_fence = to_drm_sched_fence(fence); fence = dma_fence_get(&s_fence->scheduled); dma_fence_put(old); } - if (IS_ERR(fence)) { - r = PTR_ERR(fence); - amdgpu_ctx_put(ctx); + r = amdgpu_sync_fence(p->adev, &p->job->sync, fence, true); + dma_fence_put(fence); + if (r) return r; - } else if (fence) { - r = amdgpu_sync_fence(p->adev, &p->job->sync, fence, - true); - dma_fence_put(fence); - amdgpu_ctx_put(ctx); - if (r) - return r; - } } return 0; } From 929e571c04c285861e0bb049a396a2bdaea63282 Mon Sep 17 00:00:00 2001 From: Wang Xiayang Date: Sat, 27 Jul 2019 17:30:30 +0800 Subject: [PATCH 634/823] drm/amdgpu: fix a potential information leaking bug MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Coccinelle reports a path that the array "data" is never initialized. The path skips the checks in the conditional branches when either of callback functions, read_wave_vgprs and read_wave_sgprs, is not registered. Later, the uninitialized "data" array is read in the while-loop below and passed to put_user(). Fix the path by allocating the array with kcalloc(). The patch is simplier than adding a fall-back branch that explicitly calls memset(data, 0, ...). Also it does not need the multiplication 1024*sizeof(*data) as the size parameter for memset() though there is no risk of integer overflow. Signed-off-by: Wang Xiayang Reviewed-by: Chunming Zhou Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 6d54decef7f8..5652cc72ed3a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -707,7 +707,7 @@ static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf, thread = (*pos & GENMASK_ULL(59, 52)) >> 52; bank = (*pos & GENMASK_ULL(61, 60)) >> 60; - data = kmalloc_array(1024, sizeof(*data), GFP_KERNEL); + data = kcalloc(1024, sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; From a02709818f397e7ed7a0943d65a49d54b2752626 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Mon, 22 Jul 2019 09:51:59 +0800 Subject: [PATCH 635/823] drm/amd/powerplay: add new sensor type for VCN powergate status VCN is widely used in new ASICs and different from tranditional UVD and VCE. Signed-off-by: Evan Quan Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/include/kgd_pp_interface.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h index 9f661bf96ed0..5b1ebb7f995a 100644 --- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h @@ -123,6 +123,7 @@ enum amd_pp_sensors { AMDGPU_PP_SENSOR_ENABLED_SMC_FEATURES_MASK, AMDGPU_PP_SENSOR_MIN_FAN_RPM, AMDGPU_PP_SENSOR_MAX_FAN_RPM, + AMDGPU_PP_SENSOR_VCN_POWER_STATE, }; enum amd_pp_task { From 201cd702b7012ecee2a613e09b6a227ca0e12504 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Mon, 22 Jul 2019 09:55:36 +0800 Subject: [PATCH 636/823] drm/amd/powerplay: support VCN powergate status retrieval on Raven Enable VCN powergate status report on Raven. Signed-off-by: Evan Quan Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c index e32ae9d3373c..18e780f566fa 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c @@ -1111,6 +1111,7 @@ static int smu10_thermal_get_temperature(struct pp_hwmgr *hwmgr) static int smu10_read_sensor(struct pp_hwmgr *hwmgr, int idx, void *value, int *size) { + struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); uint32_t sclk, mclk; int ret = 0; @@ -1132,6 +1133,10 @@ static int smu10_read_sensor(struct pp_hwmgr *hwmgr, int idx, case AMDGPU_PP_SENSOR_GPU_TEMP: *((uint32_t *)value) = smu10_thermal_get_temperature(hwmgr); break; + case AMDGPU_PP_SENSOR_VCN_POWER_STATE: + *(uint32_t *)value = smu10_data->vcn_power_gated ? 0 : 1; + *size = 4; + break; default: ret = -EINVAL; break; @@ -1175,18 +1180,22 @@ static int smu10_powergate_sdma(struct pp_hwmgr *hwmgr, bool gate) static void smu10_powergate_vcn(struct pp_hwmgr *hwmgr, bool bgate) { + struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); + if (bgate) { amdgpu_device_ip_set_powergating_state(hwmgr->adev, AMD_IP_BLOCK_TYPE_VCN, AMD_PG_STATE_GATE); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_PowerDownVcn, 0); + smu10_data->vcn_power_gated = true; } else { smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_PowerUpVcn, 0); amdgpu_device_ip_set_powergating_state(hwmgr->adev, AMD_IP_BLOCK_TYPE_VCN, AMD_PG_STATE_UNGATE); + smu10_data->vcn_power_gated = false; } } From e21e3581e2a1df75abb96b545be15e526bd8c1c6 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Mon, 22 Jul 2019 09:57:27 +0800 Subject: [PATCH 637/823] drm/amd/powerplay: support VCN powergate status retrieval for SW SMU Commonly used for VCN powergate status retrieval for SW SMU. Signed-off-by: Evan Quan Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/amdgpu_smu.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index 93cd969e5cf5..0685a3388e38 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -338,6 +338,10 @@ int smu_common_read_sensor(struct smu_context *smu, enum amd_pp_sensors sensor, *(uint32_t *)data = smu_feature_is_enabled(smu, SMU_FEATURE_DPM_VCE_BIT) ? 1 : 0; *size = 4; break; + case AMDGPU_PP_SENSOR_VCN_POWER_STATE: + *(uint32_t *)data = smu_feature_is_enabled(smu, SMU_FEATURE_VCN_PG_BIT) ? 1 : 0; + *size = 4; + break; default: ret = -EINVAL; break; From a3ebbdb95f8c343a547ee2abec4d8abbf71f8a94 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Mon, 22 Jul 2019 10:27:21 +0800 Subject: [PATCH 638/823] drm/amd/powerplay: correct Navi10 VCN powergate control (v2) No VCN DPM bit check as that's different from VCN PG. Also no extra check for possible double enablement/disablement as that's already done by VCN. v2: check return value of smu_feature_set_enabled Signed-off-by: Evan Quan Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/navi10_ppt.c | 28 ++++++++-------------- 1 file changed, 10 insertions(+), 18 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index be592d22bdcc..cc0a3b2256af 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -578,28 +578,20 @@ static int navi10_set_default_dpm_table(struct smu_context *smu) static int navi10_dpm_set_uvd_enable(struct smu_context *smu, bool enable) { int ret = 0; - struct smu_power_context *smu_power = &smu->smu_power; - struct smu_power_gate *power_gate = &smu_power->power_gate; - if (enable && power_gate->uvd_gated) { - if (smu_feature_is_enabled(smu, SMU_FEATURE_DPM_UVD_BIT)) { - ret = smu_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn, 1); - if (ret) - return ret; - } - power_gate->uvd_gated = false; + if (enable) { + ret = smu_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn, 1); + if (ret) + return ret; } else { - if (!enable && !power_gate->uvd_gated) { - if (smu_feature_is_enabled(smu, SMU_FEATURE_DPM_UVD_BIT)) { - ret = smu_send_smc_msg(smu, SMU_MSG_PowerDownVcn); - if (ret) - return ret; - } - power_gate->uvd_gated = true; - } + ret = smu_send_smc_msg(smu, SMU_MSG_PowerDownVcn); + if (ret) + return ret; } - return 0; + ret = smu_feature_set_enabled(smu, SMU_FEATURE_VCN_PG_BIT, enable); + + return ret; } static int navi10_get_current_clk_freq_by_table(struct smu_context *smu, From 6dee4829cfde106a8af7d0d3ba23022f8f054761 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Mon, 22 Jul 2019 10:42:29 +0800 Subject: [PATCH 639/823] drm/amd/powerplay: correct UVD/VCE/VCN power status retrieval VCN should be used for Vega20 later ASICs while UVD and VCE are for previous ASICs. Signed-off-by: Evan Quan Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 56 +++++++++++++++++--------- 1 file changed, 36 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 8c90baca07b2..2b546567853b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -3075,28 +3075,44 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_ENABLED_SMC_FEATURES_MASK, (void *)&value64, &size)) seq_printf(m, "SMC Feature Mask: 0x%016llx\n", value64); - /* UVD clocks */ - if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_POWER, (void *)&value, &size)) { - if (!value) { - seq_printf(m, "UVD: Disabled\n"); - } else { - seq_printf(m, "UVD: Enabled\n"); - if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size)) - seq_printf(m, "\t%u MHz (DCLK)\n", value/100); - if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size)) - seq_printf(m, "\t%u MHz (VCLK)\n", value/100); + if (adev->asic_type > CHIP_VEGA20) { + /* VCN clocks */ + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCN_POWER_STATE, (void *)&value, &size)) { + if (!value) { + seq_printf(m, "VCN: Disabled\n"); + } else { + seq_printf(m, "VCN: Enabled\n"); + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size)) + seq_printf(m, "\t%u MHz (DCLK)\n", value/100); + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size)) + seq_printf(m, "\t%u MHz (VCLK)\n", value/100); + } } - } - seq_printf(m, "\n"); + seq_printf(m, "\n"); + } else { + /* UVD clocks */ + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_POWER, (void *)&value, &size)) { + if (!value) { + seq_printf(m, "UVD: Disabled\n"); + } else { + seq_printf(m, "UVD: Enabled\n"); + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size)) + seq_printf(m, "\t%u MHz (DCLK)\n", value/100); + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size)) + seq_printf(m, "\t%u MHz (VCLK)\n", value/100); + } + } + seq_printf(m, "\n"); - /* VCE clocks */ - if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_POWER, (void *)&value, &size)) { - if (!value) { - seq_printf(m, "VCE: Disabled\n"); - } else { - seq_printf(m, "VCE: Enabled\n"); - if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_ECCLK, (void *)&value, &size)) - seq_printf(m, "\t%u MHz (ECCLK)\n", value/100); + /* VCE clocks */ + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_POWER, (void *)&value, &size)) { + if (!value) { + seq_printf(m, "VCE: Disabled\n"); + } else { + seq_printf(m, "VCE: Enabled\n"); + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_ECCLK, (void *)&value, &size)) + seq_printf(m, "\t%u MHz (ECCLK)\n", value/100); + } } } From 7440ea8b2a4430eef5120d0a7faac6c39304ae6d Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Tue, 30 Jul 2019 14:37:04 +1000 Subject: [PATCH 640/823] drivers/macintosh/smu.c: Mark expected switch fall-through Mark switch cases where we are expecting to fall through. This patch fixes the following warning (Building: powerpc): drivers/macintosh/smu.c: In function 'smu_queue_i2c': drivers/macintosh/smu.c:854:21: warning: this statement may fall through [-Wimplicit-fallthrough=] cmd->info.devaddr &= 0xfe; ~~~~~~~~~~~~~~~~~~^~~~~~~ drivers/macintosh/smu.c:855:2: note: here case SMU_I2C_TRANSFER_STDSUB: ^~~~ Fixes: 0365ba7fb1fa ("[PATCH] ppc64: SMU driver update & i2c support") Signed-off-by: Stephen Rothwell Reviewed-by: Kees Cook Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190730143704.060a2606@canb.auug.org.au --- drivers/macintosh/smu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 276065c888bc..23f1f41c8602 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -852,6 +852,7 @@ int smu_queue_i2c(struct smu_i2c_cmd *cmd) break; case SMU_I2C_TRANSFER_COMBINED: cmd->info.devaddr &= 0xfe; + /* fall through */ case SMU_I2C_TRANSFER_STDSUB: if (cmd->info.sublen > 3) return -EINVAL; From d7e23b887f67178c4f840781be7a6aa6aeb52ab1 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 31 Jul 2019 06:01:42 +0000 Subject: [PATCH 641/823] powerpc/kasan: fix early boot failure on PPC32 Due to commit 4a6d8cf90017 ("powerpc/mm: don't use pte_alloc_kernel() until slab is available on PPC32"), pte_alloc_kernel() cannot be used during early KASAN init. Fix it by using memblock_alloc() instead. Fixes: 2edb16efc899 ("powerpc/32: Add KASAN support") Cc: stable@vger.kernel.org # v5.2+ Reported-by: Erhard F. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/da89670093651437f27d2975224712e0a130b055.1564552796.git.christophe.leroy@c-s.fr --- arch/powerpc/mm/kasan/kasan_init_32.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index 0d62be3cba47..74f4555a62ba 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -21,7 +21,7 @@ static void kasan_populate_pte(pte_t *ptep, pgprot_t prot) __set_pte_at(&init_mm, va, ptep, pfn_pte(PHYS_PFN(pa), prot), 0); } -static int kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end) +static int __ref kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end) { pmd_t *pmd; unsigned long k_cur, k_next; @@ -35,7 +35,10 @@ static int kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_ if ((void *)pmd_page_vaddr(*pmd) != kasan_early_shadow_pte) continue; - new = pte_alloc_one_kernel(&init_mm); + if (slab_is_available()) + new = pte_alloc_one_kernel(&init_mm); + else + new = memblock_alloc(PTE_FRAG_SIZE, PTE_FRAG_SIZE); if (!new) return -ENOMEM; From 12d1402ce35a900b4273893b885ddf35dbea0571 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 31 Jul 2019 16:16:00 +0200 Subject: [PATCH 642/823] parisc: Mark expected switch fall-throughs in fault.c Fix a fall-through warning in fault.c. Fixes: a035d552a93b ("Makefile: Globally enable fall-through warning") Signed-off-by: Helge Deller --- arch/parisc/mm/fault.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 6dd4669ce7a5..adbd5e2144a3 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -66,6 +66,7 @@ parisc_acctyp(unsigned long code, unsigned int inst) case 0x30000000: /* coproc2 */ if (bit22set(inst)) return VM_WRITE; + /* fall through */ case 0x0: /* indexed/memory management */ if (bit22set(inst)) { From 73b886724747ea5fa599ada988fe0a30edcc2e00 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 31 Jul 2019 16:16:43 +0200 Subject: [PATCH 643/823] parisc: Fix fall-through warnings in fpudispatch.c In fpudispatch.c we see a lot of fall-through warnings, but for this file we prefer to not mark the switches and instead keep it in it's original state as it's copied from HP-UX. Fixes: a035d552a93b ("Makefile: Globally enable fall-through warning") Signed-off-by: Helge Deller --- arch/parisc/math-emu/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/parisc/math-emu/Makefile b/arch/parisc/math-emu/Makefile index b6c4b254901a..55c1396580a4 100644 --- a/arch/parisc/math-emu/Makefile +++ b/arch/parisc/math-emu/Makefile @@ -18,3 +18,4 @@ obj-y := frnd.o driver.o decode_exc.o fpudispatch.o denormal.o \ # other very old or stripped-down PA-RISC CPUs -- not currently supported obj-$(CONFIG_MATH_EMULATION) += unimplemented-math-emulation.o +CFLAGS_REMOVE_fpudispatch.o = -Wimplicit-fallthrough=3 From c5df04521b521f14c30de327aa1e880f1190a355 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 23 Jul 2019 18:47:51 +0900 Subject: [PATCH 644/823] parisc: rename default_defconfig to defconfig 'default_defconfig' is an awkward name since 'defconfig' is the default. Let's simply say 'defconfig' like other architectures. You can drop the KBUILD_DEFCONFIG define by following the standard naming. Signed-off-by: Masahiro Yamada Signed-off-by: Helge Deller --- arch/parisc/Makefile | 2 -- arch/parisc/configs/{default_defconfig => defconfig} | 0 2 files changed, 2 deletions(-) rename arch/parisc/configs/{default_defconfig => defconfig} (100%) diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 8acb8fa1f8d6..b10a1179291a 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -19,8 +19,6 @@ KBUILD_IMAGE := vmlinuz -KBUILD_DEFCONFIG := default_defconfig - NM = sh $(srctree)/arch/parisc/nm CHECKFLAGS += -D__hppa__=1 LIBGCC = $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name) diff --git a/arch/parisc/configs/default_defconfig b/arch/parisc/configs/defconfig similarity index 100% rename from arch/parisc/configs/default_defconfig rename to arch/parisc/configs/defconfig From 740f05f30a8c49ec63668055d28feedd906d3c50 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Tue, 23 Jul 2019 22:37:54 +0200 Subject: [PATCH 645/823] parisc: fix race condition in patching code Assume the following ftrace code sequence that was patched in earlier by ftrace_make_call(): PAGE A: ffc: addr of ftrace_caller() PAGE B: 000: 0x6fc10080 /* stw,ma r1,40(sp) */ 004: 0x48213fd1 /* ldw -18(r1),r1 */ 008: 0xe820c002 /* bv,n r0(r1) */ 00c: 0xe83f1fdf /* b,l,n .-c,r1 */ When a Code sequences that is to be patched spans a page break, we might have already cleared the part on the PAGE A. If an interrupt is coming in during the remap of the fixed mapping to PAGE B, it might execute the patched function with only parts of the FTRACE code cleared. To prevent this, clear the jump to our mini trampoline first, and clear the remaining parts after this. This might also happen when patch_text() patches a function that it calls during remap. Signed-off-by: Sven Schnelle Cc: # 5.2+ Signed-off-by: Helge Deller --- arch/parisc/kernel/ftrace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index d784ccdd8fef..b6fb30f2e4bf 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -181,8 +181,9 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, for (i = 0; i < ARRAY_SIZE(insn); i++) insn[i] = INSN_NOP; + __patch_text((void *)rec->ip, INSN_NOP); __patch_text_multiple((void *)rec->ip + 4 - sizeof(insn), - insn, sizeof(insn)); + insn, sizeof(insn)-4); return 0; } #endif From d0ee879187df966ef638031b5f5183078d672141 Mon Sep 17 00:00:00 2001 From: Jackie Liu Date: Wed, 31 Jul 2019 14:39:33 +0800 Subject: [PATCH 646/823] io_uring: fix KASAN use after free in io_sq_wq_submit_work [root@localhost ~]# ./liburing/test/link QEMU Standard PC report that: [ 29.379892] CPU: 0 PID: 84 Comm: kworker/u2:2 Not tainted 5.3.0-rc2-00051-g4010b622f1d2-dirty #86 [ 29.379902] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 [ 29.379913] Workqueue: io_ring-wq io_sq_wq_submit_work [ 29.379929] Call Trace: [ 29.379953] dump_stack+0xa9/0x10e [ 29.379970] ? io_sq_wq_submit_work+0xbf4/0xe90 [ 29.379986] print_address_description.cold.6+0x9/0x317 [ 29.379999] ? io_sq_wq_submit_work+0xbf4/0xe90 [ 29.380010] ? io_sq_wq_submit_work+0xbf4/0xe90 [ 29.380026] __kasan_report.cold.7+0x1a/0x34 [ 29.380044] ? io_sq_wq_submit_work+0xbf4/0xe90 [ 29.380061] kasan_report+0xe/0x12 [ 29.380076] io_sq_wq_submit_work+0xbf4/0xe90 [ 29.380104] ? io_sq_thread+0xaf0/0xaf0 [ 29.380152] process_one_work+0xb59/0x19e0 [ 29.380184] ? pwq_dec_nr_in_flight+0x2c0/0x2c0 [ 29.380221] worker_thread+0x8c/0xf40 [ 29.380248] ? __kthread_parkme+0xab/0x110 [ 29.380265] ? process_one_work+0x19e0/0x19e0 [ 29.380278] kthread+0x30b/0x3d0 [ 29.380292] ? kthread_create_on_node+0xe0/0xe0 [ 29.380311] ret_from_fork+0x3a/0x50 [ 29.380635] Allocated by task 209: [ 29.381255] save_stack+0x19/0x80 [ 29.381268] __kasan_kmalloc.constprop.6+0xc1/0xd0 [ 29.381279] kmem_cache_alloc+0xc0/0x240 [ 29.381289] io_submit_sqe+0x11bc/0x1c70 [ 29.381300] io_ring_submit+0x174/0x3c0 [ 29.381311] __x64_sys_io_uring_enter+0x601/0x780 [ 29.381322] do_syscall_64+0x9f/0x4d0 [ 29.381336] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 29.381633] Freed by task 84: [ 29.382186] save_stack+0x19/0x80 [ 29.382198] __kasan_slab_free+0x11d/0x160 [ 29.382210] kmem_cache_free+0x8c/0x2f0 [ 29.382220] io_put_req+0x22/0x30 [ 29.382230] io_sq_wq_submit_work+0x28b/0xe90 [ 29.382241] process_one_work+0xb59/0x19e0 [ 29.382251] worker_thread+0x8c/0xf40 [ 29.382262] kthread+0x30b/0x3d0 [ 29.382272] ret_from_fork+0x3a/0x50 [ 29.382569] The buggy address belongs to the object at ffff888067172140 which belongs to the cache io_kiocb of size 224 [ 29.384692] The buggy address is located 120 bytes inside of 224-byte region [ffff888067172140, ffff888067172220) [ 29.386723] The buggy address belongs to the page: [ 29.387575] page:ffffea00019c5c80 refcount:1 mapcount:0 mapping:ffff88806ace5180 index:0x0 [ 29.387587] flags: 0x100000000000200(slab) [ 29.387603] raw: 0100000000000200 dead000000000100 dead000000000122 ffff88806ace5180 [ 29.387617] raw: 0000000000000000 00000000800c000c 00000001ffffffff 0000000000000000 [ 29.387624] page dumped because: kasan: bad access detected [ 29.387920] Memory state around the buggy address: [ 29.388771] ffff888067172080: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc [ 29.390062] ffff888067172100: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb [ 29.391325] >ffff888067172180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 29.392578] ^ [ 29.393480] ffff888067172200: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc [ 29.394744] ffff888067172280: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 29.396003] ================================================================== [ 29.397260] Disabling lock debugging due to kernel taint io_sq_wq_submit_work free and read req again. Cc: Zhengyuan Liu Cc: linux-block@vger.kernel.org Cc: stable@vger.kernel.org Fixes: f7b76ac9d17e ("io_uring: fix counter inc/dec mismatch in async_list") Signed-off-by: Jackie Liu Signed-off-by: Jens Axboe --- fs/io_uring.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 012bc0efb9d3..d542f1cf4428 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1838,6 +1838,7 @@ restart: do { struct sqe_submit *s = &req->submit; const struct io_uring_sqe *sqe = s->sqe; + unsigned int flags = req->flags; /* Ensure we clear previously set non-block flag */ req->rw.ki_flags &= ~IOCB_NOWAIT; @@ -1883,7 +1884,7 @@ restart: kfree(sqe); /* req from defer and link list needn't decrease async cnt */ - if (req->flags & (REQ_F_IO_DRAINED | REQ_F_LINK_DONE)) + if (flags & (REQ_F_IO_DRAINED | REQ_F_LINK_DONE)) goto out; if (!async_list) From 090bb803708198e5ab6b0046398c7ed9f4d12d6b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 31 Jul 2019 14:26:51 +0200 Subject: [PATCH 647/823] ata: libahci: do not complain in case of deferred probe Retrieving PHYs can defer the probe, do not spawn an error when -EPROBE_DEFER is returned, it is normal behavior. Fixes: b1a9edbda040 ("ata: libahci: allow to use multiple PHYs") Reviewed-by: Hans de Goede Signed-off-by: Miquel Raynal Signed-off-by: Jens Axboe --- drivers/ata/libahci_platform.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 3a36e76eca83..9e9583a6bba9 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -338,6 +338,9 @@ static int ahci_platform_get_phy(struct ahci_host_priv *hpriv, u32 port, hpriv->phys[port] = NULL; rc = 0; break; + case -EPROBE_DEFER: + /* Do not complain yet */ + break; default: dev_err(dev, From 2b5c8f0063e4b263cf2de82029798183cf85c320 Mon Sep 17 00:00:00 2001 From: Munehisa Kamata Date: Wed, 31 Jul 2019 20:13:10 +0800 Subject: [PATCH 648/823] nbd: replace kill_bdev() with __invalidate_device() again Commit abbbdf12497d ("replace kill_bdev() with __invalidate_device()") once did this, but 29eaadc03649 ("nbd: stop using the bdev everywhere") resurrected kill_bdev() and it has been there since then. So buffer_head mappings still get killed on a server disconnection, and we can still hit the BUG_ON on a filesystem on the top of the nbd device. EXT4-fs (nbd0): mounted filesystem with ordered data mode. Opts: (null) block nbd0: Receive control failed (result -32) block nbd0: shutting down sockets print_req_error: I/O error, dev nbd0, sector 66264 flags 3000 EXT4-fs warning (device nbd0): htree_dirblock_to_tree:979: inode #2: lblock 0: comm ls: error -5 reading directory block print_req_error: I/O error, dev nbd0, sector 2264 flags 3000 EXT4-fs error (device nbd0): __ext4_get_inode_loc:4690: inode #2: block 283: comm ls: unable to read itable block EXT4-fs error (device nbd0) in ext4_reserve_inode_write:5894: IO failure ------------[ cut here ]------------ kernel BUG at fs/buffer.c:3057! invalid opcode: 0000 [#1] SMP PTI CPU: 7 PID: 40045 Comm: jbd2/nbd0-8 Not tainted 5.1.0-rc3+ #4 Hardware name: Amazon EC2 m5.12xlarge/, BIOS 1.0 10/16/2017 RIP: 0010:submit_bh_wbc+0x18b/0x190 ... Call Trace: jbd2_write_superblock+0xf1/0x230 [jbd2] ? account_entity_enqueue+0xc5/0xf0 jbd2_journal_update_sb_log_tail+0x94/0xe0 [jbd2] jbd2_journal_commit_transaction+0x12f/0x1d20 [jbd2] ? __switch_to_asm+0x40/0x70 ... ? lock_timer_base+0x67/0x80 kjournald2+0x121/0x360 [jbd2] ? remove_wait_queue+0x60/0x60 kthread+0xf8/0x130 ? commit_timeout+0x10/0x10 [jbd2] ? kthread_bind+0x10/0x10 ret_from_fork+0x35/0x40 With __invalidate_device(), I no longer hit the BUG_ON with sync or unmount on the disconnected device. Fixes: 29eaadc03649 ("nbd: stop using the bdev everywhere") Cc: linux-block@vger.kernel.org Cc: Ratna Manoj Bolla Cc: nbd@other.debian.org Cc: stable@vger.kernel.org Cc: David Woodhouse Reviewed-by: Josef Bacik Signed-off-by: Munehisa Kamata Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 9bcde2325893..e21d2ded732b 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1231,7 +1231,7 @@ static void nbd_clear_sock_ioctl(struct nbd_device *nbd, struct block_device *bdev) { sock_shutdown(nbd); - kill_bdev(bdev); + __invalidate_device(bdev, true); nbd_bdev_reset(bdev); if (test_and_clear_bit(NBD_HAS_CONFIG_REF, &nbd->config->runtime_flags)) From dc25ace66c74ca148c393952bd2ce0856029c692 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Jul 2019 22:25:20 +0200 Subject: [PATCH 649/823] drm/i810: Use CONFIG_PREEMPTION CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT. Both PREEMPT and PREEMPT_RT require the same functionality which today depends on CONFIG_PREEMPT. Change the Kconfig dependency of i810 to !CONFIG_PREEMPTION so the driver is not accidentally built on a RT kernel. Signed-off-by: Thomas Gleixner Cc: dri-devel@lists.freedesktop.org Cc: Maarten Lankhorst Cc: David Airlie Cc: Daniel Vetter Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/alpine.DEB.2.21.1907262223280.1791@nanos.tec.linutronix.de --- drivers/gpu/drm/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 1d80222587ad..3c88420e3497 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -394,7 +394,7 @@ config DRM_R128 config DRM_I810 tristate "Intel I810" # !PREEMPT because of missing ioctl locking - depends on DRM && AGP && AGP_INTEL && (!PREEMPT || BROKEN) + depends on DRM && AGP && AGP_INTEL && (!PREEMPTION || BROKEN) help Choose this option if you have an Intel I810 graphics card. If M is selected, the module will be called i810. AGP support is required From 944cfe9be1fbbec73bab2f7e77fe2e8f9c72970f Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 31 Jul 2019 00:58:59 +0900 Subject: [PATCH 650/823] kbuild: modpost: include .*.cmd files only when targets exist If a build rule fails, the .DELETE_ON_ERROR special target removes the target, but does nothing for the .*.cmd file, which might be corrupted. So, .*.cmd files should be included only when the corresponding targets exist. Commit 392885ee82d3 ("kbuild: let fixdep directly write to .*.cmd files") missed to fix up this file. Fixes: 392885ee82d3 ("kbuild: let fixdep directly write to .*.cmd") Cc: # v5.0+ Signed-off-by: Masahiro Yamada --- scripts/Makefile.modpost | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index 6b19c1a4eae5..ad4b9829a456 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -145,10 +145,8 @@ FORCE: # optimization, we don't need to read them if the target does not # exist, we will rebuild anyway in that case. -cmd_files := $(wildcard $(foreach f,$(sort $(targets)),$(dir $(f)).$(notdir $(f)).cmd)) +existing-targets := $(wildcard $(sort $(targets))) -ifneq ($(cmd_files),) - include $(cmd_files) -endif +-include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd) .PHONY: $(PHONY) From cb4819934a7f9b87876f11ed05b8624c0114551b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 31 Jul 2019 00:59:00 +0900 Subject: [PATCH 651/823] kbuild: modpost: handle KBUILD_EXTRA_SYMBOLS only for external modules KBUILD_EXTRA_SYMBOLS makes sense only when building external modules. Moreover, the modpost sets 'external_module' if the -e option is given. I replaced $(patsubst %, -e %,...) with simpler $(addprefix -e,...) while I was here. Signed-off-by: Masahiro Yamada --- scripts/Makefile.modpost | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index ad4b9829a456..c856512349cd 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -78,7 +78,7 @@ modpost = scripts/mod/modpost \ $(if $(CONFIG_MODULE_SRCVERSION_ALL),-a,) \ $(if $(KBUILD_EXTMOD),-i,-o) $(kernelsymfile) \ $(if $(KBUILD_EXTMOD),-I $(modulesymfile)) \ - $(if $(KBUILD_EXTRA_SYMBOLS), $(patsubst %, -e %,$(KBUILD_EXTRA_SYMBOLS))) \ + $(if $(KBUILD_EXTMOD),$(addprefix -e ,$(KBUILD_EXTRA_SYMBOLS))) \ $(if $(KBUILD_EXTMOD),-o $(modulesymfile)) \ $(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \ $(if $(KBUILD_MODPOST_WARN),-w) From acf2a1397a686365775385ed4657941119172263 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 31 Jul 2019 00:59:01 +0900 Subject: [PATCH 652/823] kbuild: modpost: remove unnecessary dependency for __modpost __modpost is a phony target. The dependency on FORCE is pointless. All the objects have been built in the previous stage, so the dependency on the objects are not necessary either. Count the number of modules in a more straightforward way. Signed-off-by: Masahiro Yamada --- scripts/Makefile.modpost | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index c856512349cd..fdab32d6f552 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -86,11 +86,11 @@ modpost = scripts/mod/modpost \ MODPOST_OPT=$(subst -i,-n,$(filter -i,$(MAKEFLAGS))) # We can go over command line length here, so be careful. -quiet_cmd_modpost = MODPOST $(words $(filter-out vmlinux FORCE, $^)) modules +quiet_cmd_modpost = MODPOST $(words $(modules)) modules cmd_modpost = sed 's/ko$$/o/' $(modorder) | $(modpost) $(MODPOST_OPT) -s -T - PHONY += __modpost -__modpost: $(modules:.ko=.o) FORCE +__modpost: $(call cmd,modpost) $(wildcard vmlinux) quiet_cmd_kernel-mod = MODPOST $@ From a721588d9475cbbf9e8b3ae1a69b1dea88d01653 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 31 Jul 2019 00:59:02 +0900 Subject: [PATCH 653/823] kbuild: modpost: do not parse unnecessary rules for vmlinux modpost Since commit ff9b45c55b26 ("kbuild: modpost: read modules.order instead of $(MODVERDIR)/*.mod"), 'make vmlinux' emits a warning, like this: $ make defconfig vmlinux [ snip ] LD vmlinux.o cat: modules.order: No such file or directory MODPOST vmlinux.o MODINFO modules.builtin.modinfo KSYM .tmp_kallsyms1.o KSYM .tmp_kallsyms2.o LD vmlinux SORTEX vmlinux SYSMAP System.map When building only vmlinux, KBUILD_MODULES is not set. Hence, the modules.order is not generated. For the vmlinux modpost, it is not necessary at all. Separate scripts/Makefile.modpost for the vmlinux/modules stages. This works more efficiently because the vmlinux modpost does not need to include .*.cmd files. Fixes: ff9b45c55b26 ("kbuild: modpost: read modules.order instead of $(MODVERDIR)/*.mod") Signed-off-by: Masahiro Yamada --- scripts/Makefile.modpost | 74 ++++++++++++++++++++++------------------ scripts/link-vmlinux.sh | 2 +- 2 files changed, 41 insertions(+), 35 deletions(-) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index fdab32d6f552..92ed02d7cd5e 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -38,12 +38,39 @@ # symbols in the final module linking stage # KBUILD_MODPOST_NOFINAL can be set to skip the final link of modules. # This is solely useful to speed up test compiles -PHONY := _modpost -_modpost: __modpost + +PHONY := __modpost +__modpost: include include/config/auto.conf include scripts/Kbuild.include +kernelsymfile := $(objtree)/Module.symvers +modulesymfile := $(firstword $(KBUILD_EXTMOD))/Module.symvers + +MODPOST = scripts/mod/modpost \ + $(if $(CONFIG_MODVERSIONS),-m) \ + $(if $(CONFIG_MODULE_SRCVERSION_ALL),-a) \ + $(if $(KBUILD_EXTMOD),-i,-o) $(kernelsymfile) \ + $(if $(KBUILD_EXTMOD),-I $(modulesymfile)) \ + $(if $(KBUILD_EXTMOD),$(addprefix -e ,$(KBUILD_EXTRA_SYMBOLS))) \ + $(if $(KBUILD_EXTMOD),-o $(modulesymfile)) \ + $(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \ + $(if $(KBUILD_MODPOST_WARN),-w) + +ifdef MODPOST_VMLINUX + +__modpost: vmlinux.o + +quiet_cmd_modpost = MODPOST $@ + cmd_modpost = $(MODPOST) $@ + +PHONY += vmlinux.o +vmlinux.o: + $(call cmd,modpost) + +else + # When building external modules load the Kbuild file to retrieve EXTRA_SYMBOLS info ifneq ($(KBUILD_EXTMOD),) @@ -58,50 +85,27 @@ endif include scripts/Makefile.lib -kernelsymfile := $(objtree)/Module.symvers -modulesymfile := $(firstword $(KBUILD_EXTMOD))/Module.symvers - modorder := $(if $(KBUILD_EXTMOD),$(KBUILD_EXTMOD)/)modules.order -# Step 1), find all modules listed in modules.order -ifdef CONFIG_MODULES +# find all modules listed in modules.order modules := $(sort $(shell cat $(modorder))) -endif # Stop after building .o files if NOFINAL is set. Makes compile tests quicker -_modpost: $(if $(KBUILD_MODPOST_NOFINAL), $(modules:.ko:.o),$(modules)) +__modpost: $(if $(KBUILD_MODPOST_NOFINAL), $(modules:.ko:.o),$(modules)) + @: -# Step 2), invoke modpost -# Includes step 3,4 -modpost = scripts/mod/modpost \ - $(if $(CONFIG_MODVERSIONS),-m) \ - $(if $(CONFIG_MODULE_SRCVERSION_ALL),-a,) \ - $(if $(KBUILD_EXTMOD),-i,-o) $(kernelsymfile) \ - $(if $(KBUILD_EXTMOD),-I $(modulesymfile)) \ - $(if $(KBUILD_EXTMOD),$(addprefix -e ,$(KBUILD_EXTRA_SYMBOLS))) \ - $(if $(KBUILD_EXTMOD),-o $(modulesymfile)) \ - $(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \ - $(if $(KBUILD_MODPOST_WARN),-w) - -MODPOST_OPT=$(subst -i,-n,$(filter -i,$(MAKEFLAGS))) +MODPOST += $(subst -i,-n,$(filter -i,$(MAKEFLAGS))) -s -T - $(wildcard vmlinux) # We can go over command line length here, so be careful. quiet_cmd_modpost = MODPOST $(words $(modules)) modules - cmd_modpost = sed 's/ko$$/o/' $(modorder) | $(modpost) $(MODPOST_OPT) -s -T - + cmd_modpost = sed 's/ko$$/o/' $(modorder) | $(MODPOST) -PHONY += __modpost -__modpost: - $(call cmd,modpost) $(wildcard vmlinux) - -quiet_cmd_kernel-mod = MODPOST $@ - cmd_kernel-mod = $(modpost) $@ - -vmlinux.o: FORCE - $(call cmd,kernel-mod) +PHONY += modules-modpost +modules-modpost: + $(call cmd,modpost) # Declare generated files as targets for modpost -$(modules:.ko=.mod.c): __modpost ; - +$(modules:.ko=.mod.c): modules-modpost # Step 5), compile all *.mod.c files @@ -149,4 +153,6 @@ existing-targets := $(wildcard $(sort $(targets))) -include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd) +endif + .PHONY: $(PHONY) diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index a7124f895b24..915775eb2921 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -210,7 +210,7 @@ info LD vmlinux.o modpost_link vmlinux.o # modpost vmlinux.o to check for section mismatches -${MAKE} -f "${srctree}/scripts/Makefile.modpost" vmlinux.o +${MAKE} -f "${srctree}/scripts/Makefile.modpost" MODPOST_VMLINUX=1 info MODINFO modules.builtin.modinfo ${OBJCOPY} -j .modinfo -O binary vmlinux.o modules.builtin.modinfo From e2a280d28d32d2cf7eaa2b1cecefd079b24c0245 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 31 Jul 2019 01:40:42 +0900 Subject: [PATCH 654/823] lib/raid6: fix unnecessary rebuild of vpermxor*.c The following four files are every time rebuilt: UNROLL lib/raid6/vpermxor1.c UNROLL lib/raid6/vpermxor2.c UNROLL lib/raid6/vpermxor4.c UNROLL lib/raid6/vpermxor8.c Fix the suffixes in the targets. Fixes: 72ad21075df8 ("lib/raid6: refactor unroll rules with pattern rules") Signed-off-by: Masahiro Yamada --- lib/raid6/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile index 42695bc8d451..0083b5cc646c 100644 --- a/lib/raid6/Makefile +++ b/lib/raid6/Makefile @@ -66,7 +66,7 @@ CFLAGS_vpermxor1.o += $(altivec_flags) CFLAGS_vpermxor2.o += $(altivec_flags) CFLAGS_vpermxor4.o += $(altivec_flags) CFLAGS_vpermxor8.o += $(altivec_flags) -targets += vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o +targets += vpermxor1.c vpermxor2.c vpermxor4.c vpermxor8.c $(obj)/vpermxor%.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) From e8de12fb7cde2c85bc31097cd098da79a4818305 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Tue, 30 Jul 2019 09:48:03 -0700 Subject: [PATCH 655/823] kbuild: Check for unknown options with cc-option usage in Kconfig and clang If the particular version of clang a user has doesn't enable -Werror=unknown-warning-option by default, even though it is the default[1], then make sure to pass the option to the Kconfig cc-option command so that testing options from Kconfig files works properly. Otherwise, depending on the default values setup in the clang toolchain we will silently assume options such as -Wmaybe-uninitialized are supported by clang, when they really aren't. A compilation issue only started happening for me once commit 589834b3a009 ("kbuild: Add -Werror=unknown-warning-option to CLANG_FLAGS") was applied on top of commit b303c6df80c9 ("kbuild: compute false-positive -Wmaybe-uninitialized cases in Kconfig"). This leads kbuild to try and test for the existence of the -Wmaybe-uninitialized flag with the cc-option command in scripts/Kconfig.include, and it doesn't see an error returned from the option test so it sets the config value to Y. Then the Makefile tries to pass the unknown option on the command line and -Werror=unknown-warning-option catches the invalid option and breaks the build. Before commit 589834b3a009 ("kbuild: Add -Werror=unknown-warning-option to CLANG_FLAGS") the build works fine, but any cc-option test of a warning option in Kconfig files silently evaluates to true, even if the warning option flag isn't supported on clang. Note: This doesn't change cc-option usages in Makefiles because those use a different rule that includes KBUILD_CFLAGS by default (see the __cc-option command in scripts/Kbuild.incluide). The KBUILD_CFLAGS variable already has the -Werror=unknown-warning-option flag set. Thanks to Doug for pointing out the different rule. [1] https://clang.llvm.org/docs/DiagnosticsReference.html#wunknown-warning-option Cc: Peter Smith Cc: Nick Desaulniers Cc: Douglas Anderson Signed-off-by: Stephen Boyd Reviewed-by: Nathan Chancellor Signed-off-by: Masahiro Yamada --- scripts/Kconfig.include | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include index 8a5c4d645eb1..4bbf4fc163a2 100644 --- a/scripts/Kconfig.include +++ b/scripts/Kconfig.include @@ -25,7 +25,7 @@ failure = $(if-success,$(1),n,y) # $(cc-option,) # Return y if the compiler supports , n otherwise -cc-option = $(success,$(CC) -Werror $(1) -E -x c /dev/null -o /dev/null) +cc-option = $(success,$(CC) -Werror $(CLANG_FLAGS) $(1) -E -x c /dev/null -o /dev/null) # $(ld-option,) # Return y if the linker supports , n otherwise From 28fe79000e9b0a6f99959869947f1ca305f14599 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 31 Jul 2019 09:33:14 +0300 Subject: [PATCH 656/823] mlxsw: spectrum: Fix error path in mlxsw_sp_module_init() In case of sp2 pci driver registration fail, fix the error path to start with sp1 pci driver unregister. Fixes: c3ab435466d5 ("mlxsw: spectrum: Extend to support Spectrum-2 ASIC") Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 650638152bbc..eda9c23e87b2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -6330,7 +6330,7 @@ static int __init mlxsw_sp_module_init(void) return 0; err_sp2_pci_driver_register: - mlxsw_pci_driver_unregister(&mlxsw_sp2_pci_driver); + mlxsw_pci_driver_unregister(&mlxsw_sp1_pci_driver); err_sp1_pci_driver_register: mlxsw_core_driver_unregister(&mlxsw_sp2_driver); err_sp2_core_driver_register: From 744ad9a357280d03d567538cee7e1e457dedd481 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 31 Jul 2019 09:33:15 +0300 Subject: [PATCH 657/823] mlxsw: spectrum_buffers: Further reduce pool size on Spectrum-2 In commit e891ce1dd2a5 ("mlxsw: spectrum_buffers: Reduce pool size on Spectrum-2"), pool size was reduced to mitigate a problem in port buffer usage of ports split four ways. It turns out that this work around does not solve the issue, and a further reduction is required. Thus reduce the size of pool 0 by another 2.7 MiB, and round down to the whole number of cells. Fixes: e891ce1dd2a5 ("mlxsw: spectrum_buffers: Reduce pool size on Spectrum-2") Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 1537f70bc26d..888ba4300bcc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -437,8 +437,8 @@ static const struct mlxsw_sp_sb_pr mlxsw_sp1_sb_prs[] = { MLXSW_SP1_SB_PR_CPU_SIZE, true, false), }; -#define MLXSW_SP2_SB_PR_INGRESS_SIZE 38128752 -#define MLXSW_SP2_SB_PR_EGRESS_SIZE 38128752 +#define MLXSW_SP2_SB_PR_INGRESS_SIZE 35297568 +#define MLXSW_SP2_SB_PR_EGRESS_SIZE 35297568 #define MLXSW_SP2_SB_PR_CPU_SIZE (256 * 1000) /* Order according to mlxsw_sp2_sb_pool_dess */ From 5b31f3e39a6c4be55ede49da0dd352017f09e8cf Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 31 Jul 2019 09:38:19 +0300 Subject: [PATCH 658/823] drop_monitor: Add missing uAPI file to MAINTAINERS file Fixes: 6e43650cee64 ("add maintainer for network drop monitor kernel service") Signed-off-by: Ido Schimmel Acked-by: Neil Horman Signed-off-by: David S. Miller --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 9f5b8bd4faf9..b540794cbd91 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11137,6 +11137,7 @@ L: netdev@vger.kernel.org S: Maintained W: https://fedorahosted.org/dropwatch/ F: net/core/drop_monitor.c +F: include/uapi/linux/net_dropmon.h NETWORKING DRIVERS M: "David S. Miller" From 3d0b63c5dfa8a912ac2d5026a24826b99b20ecc9 Mon Sep 17 00:00:00 2001 From: Denis Efremov Date: Wed, 31 Jul 2019 08:53:42 -0600 Subject: [PATCH 659/823] MAINTAINERS: floppy: take over maintainership I would like to maintain the floppy driver. After the recent fixes, I think I know the code pretty well. Nowadays I've got 2 physical 3.5" readers to test all the changes. Signed-off-by: Denis Efremov Acked-by: Will Deacon Signed-off-by: Jens Axboe --- MAINTAINERS | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 6426db5198f0..6c49b48cfd69 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6322,7 +6322,8 @@ F: Documentation/devicetree/bindings/counter/ftm-quaddec.txt F: drivers/counter/ftm-quaddec.c FLOPPY DRIVER -S: Orphan +M: Denis Efremov +S: Odd Fixes L: linux-block@vger.kernel.org F: drivers/block/floppy.c From 47b69bf74f16b20a3bb95b1fe27e5347dd34b683 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 31 Jul 2019 09:38:42 +0200 Subject: [PATCH 660/823] net: ethernet: et131x: Use GFP_KERNEL instead of GFP_ATOMIC when allocating tx_ring->tcb_ring There is no good reason to use GFP_ATOMIC here. Other memory allocations are performed with GFP_KERNEL (see other 'dma_alloc_coherent()' below and 'kzalloc()' in 'et131x_rx_dma_memory_alloc()') Use GFP_KERNEL which should be enough. Signed-off-by: Christophe JAILLET Signed-off-by: David S. Miller --- drivers/net/ethernet/agere/et131x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index ea34bcb868b5..edbb4b3604c7 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -2362,7 +2362,7 @@ static int et131x_tx_dma_memory_alloc(struct et131x_adapter *adapter) /* Allocate memory for the TCB's (Transmit Control Block) */ tx_ring->tcb_ring = kcalloc(NUM_TCB, sizeof(struct tcb), - GFP_ATOMIC | GFP_DMA); + GFP_KERNEL | GFP_DMA); if (!tx_ring->tcb_ring) return -ENOMEM; From 246902bdf562d45ea3475fac64c93048a7a39f01 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 31 Jul 2019 10:06:48 +0200 Subject: [PATCH 661/823] net: ag71xx: Use GFP_KERNEL instead of GFP_ATOMIC in 'ag71xx_rings_init()' There is no need to use GFP_ATOMIC here, GFP_KERNEL should be enough. The 'kcalloc()' just a few lines above, already uses GFP_KERNEL. Signed-off-by: Christophe JAILLET Signed-off-by: David S. Miller --- drivers/net/ethernet/atheros/ag71xx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 8b69d0d7e726..6703960c7cf5 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1141,7 +1141,7 @@ static int ag71xx_rings_init(struct ag71xx *ag) tx->descs_cpu = dma_alloc_coherent(&ag->pdev->dev, ring_size * AG71XX_DESC_SIZE, - &tx->descs_dma, GFP_ATOMIC); + &tx->descs_dma, GFP_KERNEL); if (!tx->descs_cpu) { kfree(tx->buf); tx->buf = NULL; From c6349f8807324e270c5214920a1309481dd89ba4 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 31 Jul 2019 15:12:02 +0200 Subject: [PATCH 662/823] net: mediatek: Drop unneeded dependency on NET_VENDOR_MEDIATEK The whole block is protected by "if NET_VENDOR_MEDIATEK", so there is no need for individual driver config symbols to duplicate this dependency. Signed-off-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig index 263cd0909fe0..1f7fff81f24d 100644 --- a/drivers/net/ethernet/mediatek/Kconfig +++ b/drivers/net/ethernet/mediatek/Kconfig @@ -9,7 +9,6 @@ if NET_VENDOR_MEDIATEK config NET_MEDIATEK_SOC tristate "MediaTek SoC Gigabit Ethernet support" - depends on NET_VENDOR_MEDIATEK select PHYLIB ---help--- This driver supports the gigabit ethernet MACs in the From d8a1de3d5bb881507602bc02e004904828f88711 Mon Sep 17 00:00:00 2001 From: Juliana Rodrigueiro Date: Wed, 31 Jul 2019 15:17:23 +0200 Subject: [PATCH 663/823] isdn: hfcsusb: Fix mISDN driver crash caused by transfer buffer on the stack Since linux 4.9 it is not possible to use buffers on the stack for DMA transfers. During usb probe the driver crashes with "transfer buffer is on stack" message. This fix k-allocates a buffer to be used on "read_reg_atomic", which is a macro that calls "usb_control_msg" under the hood. Kernel 4.19 backtrace: usb_hcd_submit_urb+0x3e5/0x900 ? sched_clock+0x9/0x10 ? log_store+0x203/0x270 ? get_random_u32+0x6f/0x90 ? cache_alloc_refill+0x784/0x8a0 usb_submit_urb+0x3b4/0x550 usb_start_wait_urb+0x4e/0xd0 usb_control_msg+0xb8/0x120 hfcsusb_probe+0x6bc/0xb40 [hfcsusb] usb_probe_interface+0xc2/0x260 really_probe+0x176/0x280 driver_probe_device+0x49/0x130 __driver_attach+0xa9/0xb0 ? driver_probe_device+0x130/0x130 bus_for_each_dev+0x5a/0x90 driver_attach+0x14/0x20 ? driver_probe_device+0x130/0x130 bus_add_driver+0x157/0x1e0 driver_register+0x51/0xe0 usb_register_driver+0x5d/0x120 ? 0xf81ed000 hfcsusb_drv_init+0x17/0x1000 [hfcsusb] do_one_initcall+0x44/0x190 ? free_unref_page_commit+0x6a/0xd0 do_init_module+0x46/0x1c0 load_module+0x1dc1/0x2400 sys_init_module+0xed/0x120 do_fast_syscall_32+0x7a/0x200 entry_SYSENTER_32+0x6b/0xbe Signed-off-by: Juliana Rodrigueiro Signed-off-by: David S. Miller --- drivers/isdn/hardware/mISDN/hfcsusb.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c index 8fb7c5dea07f..008a74a1ed44 100644 --- a/drivers/isdn/hardware/mISDN/hfcsusb.c +++ b/drivers/isdn/hardware/mISDN/hfcsusb.c @@ -1693,13 +1693,23 @@ hfcsusb_stop_endpoint(struct hfcsusb *hw, int channel) static int setup_hfcsusb(struct hfcsusb *hw) { + void *dmabuf = kmalloc(sizeof(u_char), GFP_KERNEL); u_char b; + int ret; if (debug & DBG_HFC_CALL_TRACE) printk(KERN_DEBUG "%s: %s\n", hw->name, __func__); + if (!dmabuf) + return -ENOMEM; + + ret = read_reg_atomic(hw, HFCUSB_CHIP_ID, dmabuf); + + memcpy(&b, dmabuf, sizeof(u_char)); + kfree(dmabuf); + /* check the chip id */ - if (read_reg_atomic(hw, HFCUSB_CHIP_ID, &b) != 1) { + if (ret != 1) { printk(KERN_DEBUG "%s: %s: cannot read chip id\n", hw->name, __func__); return 1; From c2c44ec20a8496f7a3b3401c092afe96908eced1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 27 Jul 2019 08:29:57 -0400 Subject: [PATCH 664/823] Unbreak mount_capable() In "consolidate the capability checks in sget_{fc,userns}())" the wrong argument had been passed to mount_capable() by sget_fc(). That mistake had been further obscured later, when switching mount_capable() to fs_context has moved the calculation of bogus argument from sget_fc() to mount_capable() itself. It should've been fc->user_ns all along. Screwed-up-by: Al Viro Reported-by: Christian Brauner Tested-by: Christian Brauner Reviewed-by: David Howells Signed-off-by: Al Viro --- fs/super.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/fs/super.c b/fs/super.c index 113c58f19425..5960578a4076 100644 --- a/fs/super.c +++ b/fs/super.c @@ -478,13 +478,10 @@ EXPORT_SYMBOL(generic_shutdown_super); bool mount_capable(struct fs_context *fc) { - struct user_namespace *user_ns = fc->global ? &init_user_ns - : fc->user_ns; - if (!(fc->fs_type->fs_flags & FS_USERNS_MOUNT)) return capable(CAP_SYS_ADMIN); else - return ns_capable(user_ns, CAP_SYS_ADMIN); + return ns_capable(fc->user_ns, CAP_SYS_ADMIN); } /** From 706cb5492c8c459199fa0ab3b5fd2ba54ee53b0c Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Sat, 27 Jul 2019 17:12:54 +0200 Subject: [PATCH 665/823] gfs2: Inode dirtying fix With the recent iomap write page reclaim deadlock fix, it turns out that the GLF_DIRTY flag isn't always set when it needs to be anymore: previously, this happened as a side effect of always adding the inode buffer head to the current transaction with gfs2_trans_add_meta, but this isn't happening consistently anymore. Fix by removing an additional unnecessary gfs2_trans_add_meta call and by setting the GLF_DIRTY flag in gfs2_iomap_end. (The GLF_DIRTY flag causes inode_go_sync to flush the transaction log when syncing out the glock of that inode. When the flag isn't set, inode_go_sync will skip inodes, including ones with an i_state of I_DIRTY_PAGES, which will lead to cluster incoherency.) In addition, in gfs2_iomap_page_done, if the metadata has changed, mark the inode as I_DIRTY_DATASYNC to have the inode added to the current transaction: we don't expect metadata to change here, but let's err on the safe side. Fixes: d0a22a4b03b8 ("gfs2: Fix iomap write page reclaim deadlock"); Signed-off-by: Andreas Gruenbacher --- fs/gfs2/bmap.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 79581b9bdebb..4df26ef2b2b1 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1002,11 +1002,16 @@ static void gfs2_iomap_page_done(struct inode *inode, loff_t pos, unsigned copied, struct page *page, struct iomap *iomap) { + struct gfs2_trans *tr = current->journal_info; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); if (page && !gfs2_is_stuffed(ip)) gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied); + + if (tr->tr_num_buf_new) + __mark_inode_dirty(inode, I_DIRTY_DATASYNC); + gfs2_trans_end(sdp); } @@ -1099,8 +1104,6 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, tr = current->journal_info; if (tr->tr_num_buf_new) __mark_inode_dirty(inode, I_DIRTY_DATASYNC); - else - gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[0]); gfs2_trans_end(sdp); } @@ -1181,10 +1184,16 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length, if (ip->i_qadata && ip->i_qadata->qa_qd_num) gfs2_quota_unlock(ip); + + if (unlikely(!written)) + goto out_unlock; + if (iomap->flags & IOMAP_F_SIZE_CHANGED) mark_inode_dirty(inode); - gfs2_write_unlock(inode); + set_bit(GLF_DIRTY, &ip->i_gl->gl_flags); +out_unlock: + gfs2_write_unlock(inode); out: return 0; } From a22c5cf5d37ddcd4d2dd98ee9cf04fa5dd1e1c01 Mon Sep 17 00:00:00 2001 From: Vincenzo Frascino Date: Mon, 29 Jul 2019 13:54:21 +0100 Subject: [PATCH 666/823] arm64: vdso: Fix Makefile regression Using an old .config in combination with "make oldconfig" can cause an incorrect detection of the compat compiler: $ grep CROSS_COMPILE_COMPAT .config CONFIG_CROSS_COMPILE_COMPAT_VDSO="" $ make oldconfig && make arch/arm64/Makefile:58: gcc not found, check CROSS_COMPILE_COMPAT. Stop. Accordingly to the section 7.2 of the GNU Make manual "Syntax of Conditionals", "When the value results from complex expansions of variables and functions, expansions you would consider empty may actually contain whitespace characters and thus are not seen as empty. However, you can use the strip function to avoid interpreting whitespace as a non-empty value." Fix the issue adding strip to the CROSS_COMPILE_COMPAT string evaluation. Reported-by: Matteo Croce Tested-by: Matteo Croce Acked-by: Will Deacon Signed-off-by: Vincenzo Frascino Signed-off-by: Catalin Marinas --- arch/arm64/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index bb1f1dbb34e8..61de992bbea3 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -52,7 +52,7 @@ ifeq ($(CONFIG_GENERIC_COMPAT_VDSO), y) ifeq ($(CONFIG_CC_IS_CLANG), y) $(warning CROSS_COMPILE_COMPAT is clang, the compat vDSO will not be built) - else ifeq ($(CROSS_COMPILE_COMPAT),) + else ifeq ($(strip $(CROSS_COMPILE_COMPAT)),) $(warning CROSS_COMPILE_COMPAT not defined or empty, the compat vDSO will not be built) else ifeq ($(shell which $(CROSS_COMPILE_COMPAT)gcc 2> /dev/null),) $(error $(CROSS_COMPILE_COMPAT)gcc not found, check CROSS_COMPILE_COMPAT) From 147b9635e6347104b91f48ca9dca61eb0fbf2a54 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 30 Jul 2019 15:40:20 +0100 Subject: [PATCH 667/823] arm64: cpufeature: Fix feature comparison for CTR_EL0.{CWG,ERG} If CTR_EL0.{CWG,ERG} are 0b0000 then they must be interpreted to have their architecturally maximum values, which defeats the use of FTR_HIGHER_SAFE when sanitising CPU ID registers on heterogeneous machines. Introduce FTR_HIGHER_OR_ZERO_SAFE so that these fields effectively saturate at zero. Fixes: 3c739b571084 ("arm64: Keep track of CPU feature registers") Cc: # 4.4.x- Reviewed-by: Suzuki K Poulose Acked-by: Mark Rutland Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cpufeature.h | 7 ++++--- arch/arm64/kernel/cpufeature.c | 8 ++++++-- 2 files changed, 10 insertions(+), 5 deletions(-) diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 407e2bf23676..c96ffa4722d3 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -35,9 +35,10 @@ */ enum ftr_type { - FTR_EXACT, /* Use a predefined safe value */ - FTR_LOWER_SAFE, /* Smaller value is safe */ - FTR_HIGHER_SAFE,/* Bigger value is safe */ + FTR_EXACT, /* Use a predefined safe value */ + FTR_LOWER_SAFE, /* Smaller value is safe */ + FTR_HIGHER_SAFE, /* Bigger value is safe */ + FTR_HIGHER_OR_ZERO_SAFE, /* Bigger value is safe, but 0 is biggest */ }; #define FTR_STRICT true /* SANITY check strict matching required */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f29f36a65175..d19d14ba9ae4 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -225,8 +225,8 @@ static const struct arm64_ftr_bits ftr_ctr[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RES1 */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DIC_SHIFT, 1, 1), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_IDC_SHIFT, 1, 1), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_CWG_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_ERG_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_CWG_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_ERG_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DMINLINE_SHIFT, 4, 1), /* * Linux can handle differing I-cache policies. Userspace JITs will @@ -468,6 +468,10 @@ static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, case FTR_LOWER_SAFE: ret = new < cur ? new : cur; break; + case FTR_HIGHER_OR_ZERO_SAFE: + if (!cur || !new) + break; + /* Fallthrough */ case FTR_HIGHER_SAFE: ret = new > cur ? new : cur; break; From f1d4836201543e88ebe70237e67938168d5fab19 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Tue, 30 Jul 2019 17:23:48 -0400 Subject: [PATCH 668/823] arm64/efi: fix variable 'si' set but not used GCC throws out this warning on arm64. drivers/firmware/efi/libstub/arm-stub.c: In function 'efi_entry': drivers/firmware/efi/libstub/arm-stub.c:132:22: warning: variable 'si' set but not used [-Wunused-but-set-variable] Fix it by making free_screen_info() a static inline function. Acked-by: Will Deacon Signed-off-by: Qian Cai Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/efi.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 8e79ce9c3f5c..76a144702586 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -105,7 +105,11 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base, ((protocol##_t *)instance)->f(instance, ##__VA_ARGS__) #define alloc_screen_info(x...) &screen_info -#define free_screen_info(x...) + +static inline void free_screen_info(efi_system_table_t *sys_table_arg, + struct screen_info *si) +{ +} /* redeclare as 'hidden' so the compiler will generate relative references */ extern struct screen_info screen_info __attribute__((__visibility__("hidden"))); From 7e9e5ead55beacc11116b3fb90b0de6e7cf55a69 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Wed, 17 Jul 2019 14:15:37 -0700 Subject: [PATCH 669/823] drm/vgem: fix cache synchronization on arm/arm64 drm_cflush_pages() is no-op on arm/arm64. But instead we can use dma_sync API. Fixes failures w/ vgem_test. Acked-by: Daniel Vetter Signed-off-by: Rob Clark Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20190717211542.30482-1-robdclark@gmail.com --- drivers/gpu/drm/vgem/vgem_drv.c | 130 ++++++++++++++++++++------------ 1 file changed, 83 insertions(+), 47 deletions(-) diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c index 11a8f99ba18c..fc04803ff403 100644 --- a/drivers/gpu/drm/vgem/vgem_drv.c +++ b/drivers/gpu/drm/vgem/vgem_drv.c @@ -47,10 +47,16 @@ static struct vgem_device { struct platform_device *platform; } *vgem_device; +static void sync_and_unpin(struct drm_vgem_gem_object *bo); +static struct page **pin_and_sync(struct drm_vgem_gem_object *bo); + static void vgem_gem_free_object(struct drm_gem_object *obj) { struct drm_vgem_gem_object *vgem_obj = to_vgem_bo(obj); + if (!obj->import_attach) + sync_and_unpin(vgem_obj); + kvfree(vgem_obj->pages); mutex_destroy(&vgem_obj->pages_lock); @@ -78,40 +84,15 @@ static vm_fault_t vgem_gem_fault(struct vm_fault *vmf) return VM_FAULT_SIGBUS; mutex_lock(&obj->pages_lock); + if (!obj->pages) + pin_and_sync(obj); if (obj->pages) { get_page(obj->pages[page_offset]); vmf->page = obj->pages[page_offset]; ret = 0; } mutex_unlock(&obj->pages_lock); - if (ret) { - struct page *page; - page = shmem_read_mapping_page( - file_inode(obj->base.filp)->i_mapping, - page_offset); - if (!IS_ERR(page)) { - vmf->page = page; - ret = 0; - } else switch (PTR_ERR(page)) { - case -ENOSPC: - case -ENOMEM: - ret = VM_FAULT_OOM; - break; - case -EBUSY: - ret = VM_FAULT_RETRY; - break; - case -EFAULT: - case -EINVAL: - ret = VM_FAULT_SIGBUS; - break; - default: - WARN_ON(PTR_ERR(page)); - ret = VM_FAULT_SIGBUS; - break; - } - - } return ret; } @@ -277,32 +258,93 @@ static const struct file_operations vgem_driver_fops = { .release = drm_release, }; +/* Called under pages_lock, except in free path (where it can't race): */ +static void sync_and_unpin(struct drm_vgem_gem_object *bo) +{ + struct drm_device *dev = bo->base.dev; + + if (bo->table) { + dma_sync_sg_for_cpu(dev->dev, bo->table->sgl, + bo->table->nents, DMA_BIDIRECTIONAL); + sg_free_table(bo->table); + kfree(bo->table); + bo->table = NULL; + } + + if (bo->pages) { + drm_gem_put_pages(&bo->base, bo->pages, true, true); + bo->pages = NULL; + } +} + +static struct page **pin_and_sync(struct drm_vgem_gem_object *bo) +{ + struct drm_device *dev = bo->base.dev; + int npages = bo->base.size >> PAGE_SHIFT; + struct page **pages; + struct sg_table *sgt; + + WARN_ON(!mutex_is_locked(&bo->pages_lock)); + + pages = drm_gem_get_pages(&bo->base); + if (IS_ERR(pages)) { + bo->pages_pin_count--; + mutex_unlock(&bo->pages_lock); + return pages; + } + + sgt = drm_prime_pages_to_sg(pages, npages); + if (IS_ERR(sgt)) { + dev_err(dev->dev, + "failed to allocate sgt: %ld\n", + PTR_ERR(bo->table)); + drm_gem_put_pages(&bo->base, pages, false, false); + mutex_unlock(&bo->pages_lock); + return ERR_CAST(bo->table); + } + + /* + * Flush the object from the CPU cache so that importers + * can rely on coherent indirect access via the exported + * dma-address. + */ + dma_sync_sg_for_device(dev->dev, sgt->sgl, + sgt->nents, DMA_BIDIRECTIONAL); + + bo->pages = pages; + bo->table = sgt; + + return pages; +} + static struct page **vgem_pin_pages(struct drm_vgem_gem_object *bo) { + struct page **pages; + mutex_lock(&bo->pages_lock); - if (bo->pages_pin_count++ == 0) { - struct page **pages; - - pages = drm_gem_get_pages(&bo->base); - if (IS_ERR(pages)) { - bo->pages_pin_count--; - mutex_unlock(&bo->pages_lock); - return pages; - } - - bo->pages = pages; + if (bo->pages_pin_count++ == 0 && !bo->pages) { + pages = pin_and_sync(bo); + } else { + WARN_ON(!bo->pages); + pages = bo->pages; } mutex_unlock(&bo->pages_lock); - return bo->pages; + return pages; } static void vgem_unpin_pages(struct drm_vgem_gem_object *bo) { + /* + * We shouldn't hit this for imported bo's.. in the import + * case we don't own the scatter-table + */ + WARN_ON(bo->base.import_attach); + mutex_lock(&bo->pages_lock); if (--bo->pages_pin_count == 0) { - drm_gem_put_pages(&bo->base, bo->pages, true, true); - bo->pages = NULL; + WARN_ON(!bo->table); + sync_and_unpin(bo); } mutex_unlock(&bo->pages_lock); } @@ -310,18 +352,12 @@ static void vgem_unpin_pages(struct drm_vgem_gem_object *bo) static int vgem_prime_pin(struct drm_gem_object *obj) { struct drm_vgem_gem_object *bo = to_vgem_bo(obj); - long n_pages = obj->size >> PAGE_SHIFT; struct page **pages; pages = vgem_pin_pages(bo); if (IS_ERR(pages)) return PTR_ERR(pages); - /* Flush the object from the CPU cache so that importers can rely - * on coherent indirect access via the exported dma-address. - */ - drm_clflush_pages(pages, n_pages); - return 0; } From b399abe7c21e248dc6224cadc9a378a2beb10cfd Mon Sep 17 00:00:00 2001 From: Mao Han Date: Thu, 11 Jul 2019 10:38:40 +0800 Subject: [PATCH 670/823] riscv: Fix perf record without libelf support This patch fix following perf record error by linking vdso.so with build id. perf.data perf.data.old [ perf record: Woken up 1 times to write data ] free(): double free detected in tcache 2 Aborted perf record use filename__read_build_id(util/symbol-minimal.c) to get build id when libelf is not supported. When vdso.so is linked without build id, the section size of PT_NOTE will be zero, buf size will realloc to zero and cause memory corruption. Signed-off-by: Mao Han Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Signed-off-by: Paul Walmsley --- arch/riscv/kernel/vdso/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index f1d6ffe43e42..49a5852fd07d 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -37,7 +37,7 @@ $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE # these symbols in the kernel code rather than hand-coded addresses. SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \ - -Wl,--hash-style=both + -Wl,--build-id -Wl,--hash-style=both $(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE $(call if_changed,vdsold) From 11ae2d892139a1086f257188d457ddcb71ab5257 Mon Sep 17 00:00:00 2001 From: Paul Walmsley Date: Thu, 25 Jul 2019 13:41:31 -0700 Subject: [PATCH 671/823] riscv: dts: fu540-c000: drop "timebase-frequency" On FU540-based systems, the "timebase-frequency" (RTCCLK) is sourced from an external crystal located on the PCB. Thus the timebase-frequency DT property should be defined by the board that uses the SoC, not the SoC itself. Drop the superfluous timebase-frequency property from the SoC DT data. (It's already present in the board DT data.) Signed-off-by: Paul Walmsley Reviewed-by: Bin Meng --- arch/riscv/boot/dts/sifive/fu540-c000.dtsi | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi index 9bf63f0ab253..42b5ec223100 100644 --- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi @@ -21,7 +21,6 @@ cpus { #address-cells = <1>; #size-cells = <0>; - timebase-frequency = <1000000>; cpu0: cpu@0 { compatible = "sifive,e51", "sifive,rocket0", "riscv"; device_type = "cpu"; From b7edabfe843805b7ab8a91396b0782042a289308 Mon Sep 17 00:00:00 2001 From: Paul Walmsley Date: Thu, 25 Jul 2019 15:05:59 -0700 Subject: [PATCH 672/823] riscv: defconfig: align RV64 defconfig to the output of "make savedefconfig" Align the RV64 defconfig to the output of "make savedefconfig" to avoid unnecessary deltas for future defconfig patches. This patch should have no runtime functional impact. Signed-off-by: Paul Walmsley Reviewed-by: Bin Meng --- arch/riscv/configs/defconfig | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index b7b749b18853..93205c0bf71d 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -34,6 +34,7 @@ CONFIG_PCIEPORTBUS=y CONFIG_PCI_HOST_GENERIC=y CONFIG_PCIE_XILINX=y CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y CONFIG_BLK_DEV_LOOP=y CONFIG_VIRTIO_BLK=y CONFIG_BLK_DEV_SD=y @@ -53,6 +54,8 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_EARLYCON_RISCV_SBI=y CONFIG_HVC_RISCV_SBI=y +CONFIG_SPI=y +CONFIG_SPI_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_DRM=y CONFIG_DRM_RADEON=y @@ -66,8 +69,9 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y +CONFIG_MMC=y +CONFIG_MMC_SPI=y CONFIG_VIRTIO_MMIO=y -CONFIG_SPI_SIFIVE=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_AUTOFS4_FS=y @@ -83,8 +87,4 @@ CONFIG_ROOT_NFS=y CONFIG_CRYPTO_USER_API_HASH=y CONFIG_CRYPTO_DEV_VIRTIO=y CONFIG_PRINTK_TIME=y -CONFIG_SPI=y -CONFIG_MMC_SPI=y -CONFIG_MMC=y -CONFIG_DEVTMPFS_MOUNT=y # CONFIG_RCU_TRACE is not set From 1b7e816fc80e668f0ccc8542cec20b9259abace1 Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Wed, 31 Jul 2019 15:32:40 -0400 Subject: [PATCH 673/823] mm: slub: Fix slab walking for init_on_free To properly clear the slab on free with slab_want_init_on_free, we walk the list of free objects using get_freepointer/set_freepointer. The value we get from get_freepointer may not be valid. This isn't an issue since an actual value will get written later but this means there's a chance of triggering a bug if we use this value with set_freepointer: kernel BUG at mm/slub.c:306! invalid opcode: 0000 [#1] PREEMPT PTI CPU: 0 PID: 0 Comm: swapper Not tainted 5.2.0-05754-g6471384a #4 RIP: 0010:kfree+0x58a/0x5c0 Code: 48 83 05 78 37 51 02 01 0f 0b 48 83 05 7e 37 51 02 01 48 83 05 7e 37 51 02 01 48 83 05 7e 37 51 02 01 48 83 05 d6 37 51 02 01 <0f> 0b 48 83 05 d4 37 51 02 01 48 83 05 d4 37 51 02 01 48 83 05 d4 RSP: 0000:ffffffff82603d90 EFLAGS: 00010002 RAX: ffff8c3976c04320 RBX: ffff8c3976c04300 RCX: 0000000000000000 RDX: ffff8c3976c04300 RSI: 0000000000000000 RDI: ffff8c3976c04320 RBP: ffffffff82603db8 R08: 0000000000000000 R09: 0000000000000000 R10: ffff8c3976c04320 R11: ffffffff8289e1e0 R12: ffffd52cc8db0100 R13: ffff8c3976c01a00 R14: ffffffff810f10d4 R15: ffff8c3976c04300 FS: 0000000000000000(0000) GS:ffffffff8266b000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff8c397ffff000 CR3: 0000000125020000 CR4: 00000000000406b0 Call Trace: apply_wqattrs_prepare+0x154/0x280 apply_workqueue_attrs_locked+0x4e/0xe0 apply_workqueue_attrs+0x36/0x60 alloc_workqueue+0x25a/0x6d0 workqueue_init_early+0x246/0x348 start_kernel+0x3c7/0x7ec x86_64_start_reservations+0x40/0x49 x86_64_start_kernel+0xda/0xe4 secondary_startup_64+0xb6/0xc0 Modules linked in: ---[ end trace f67eb9af4d8d492b ]--- Fix this by ensuring the value we set with set_freepointer is either NULL or another value in the chain. Reported-by: kernel test robot Signed-off-by: Laura Abbott Fixes: 6471384af2a6 ("mm: security: introduce init_on_alloc=1 and init_on_free=1 boot options") Reviewed-by: Kees Cook Signed-off-by: Linus Torvalds --- mm/slub.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index e6c030e47364..8834563cdb4b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1432,7 +1432,9 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, void *old_tail = *tail ? *tail : *head; int rsize; - if (slab_want_init_on_free(s)) + if (slab_want_init_on_free(s)) { + void *p = NULL; + do { object = next; next = get_freepointer(s, object); @@ -1445,8 +1447,10 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, : 0; memset((char *)object + s->inuse, 0, s->size - s->inuse - rsize); - set_freepointer(s, object, next); + set_freepointer(s, object, p); + p = object; } while (object != old_tail); + } /* * Compiler cannot detect this function can be removed if slab_free_hook() From b36a1552d7319bbfd5cf7f08726c23c5c66d4f73 Mon Sep 17 00:00:00 2001 From: Vladis Dronov Date: Tue, 30 Jul 2019 11:33:45 +0200 Subject: [PATCH 674/823] Bluetooth: hci_uart: check for missing tty operations Certain ttys operations (pty_unix98_ops) lack tiocmget() and tiocmset() functions which are called by the certain HCI UART protocols (hci_ath, hci_bcm, hci_intel, hci_mrvl, hci_qca) via hci_uart_set_flow_control() or directly. This leads to an execution at NULL and can be triggered by an unprivileged user. Fix this by adding a helper function and a check for the missing tty operations in the protocols code. This fixes CVE-2019-10207. The Fixes: lines list commits where calls to tiocm[gs]et() or hci_uart_set_flow_control() were added to the HCI UART protocols. Link: https://syzkaller.appspot.com/bug?id=1b42faa2848963564a5b1b7f8c837ea7b55ffa50 Reported-by: syzbot+79337b501d6aa974d0f6@syzkaller.appspotmail.com Cc: stable@vger.kernel.org # v2.6.36+ Fixes: b3190df62861 ("Bluetooth: Support for Atheros AR300x serial chip") Fixes: 118612fb9165 ("Bluetooth: hci_bcm: Add suspend/resume PM functions") Fixes: ff2895592f0f ("Bluetooth: hci_intel: Add Intel baudrate configuration support") Fixes: 162f812f23ba ("Bluetooth: hci_uart: Add Marvell support") Fixes: fa9ad876b8e0 ("Bluetooth: hci_qca: Add support for Qualcomm Bluetooth chip wcn3990") Signed-off-by: Vladis Dronov Signed-off-by: Marcel Holtmann Reviewed-by: Yu-Chen, Cho Tested-by: Yu-Chen, Cho Signed-off-by: Linus Torvalds --- drivers/bluetooth/hci_ath.c | 3 +++ drivers/bluetooth/hci_bcm.c | 3 +++ drivers/bluetooth/hci_intel.c | 3 +++ drivers/bluetooth/hci_ldisc.c | 13 +++++++++++++ drivers/bluetooth/hci_mrvl.c | 3 +++ drivers/bluetooth/hci_qca.c | 3 +++ drivers/bluetooth/hci_uart.h | 1 + 7 files changed, 29 insertions(+) diff --git a/drivers/bluetooth/hci_ath.c b/drivers/bluetooth/hci_ath.c index a55be205b91a..dbfe34664633 100644 --- a/drivers/bluetooth/hci_ath.c +++ b/drivers/bluetooth/hci_ath.c @@ -98,6 +98,9 @@ static int ath_open(struct hci_uart *hu) BT_DBG("hu %p", hu); + if (!hci_uart_has_flow_control(hu)) + return -EOPNOTSUPP; + ath = kzalloc(sizeof(*ath), GFP_KERNEL); if (!ath) return -ENOMEM; diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c index 8905ad2edde7..ae2624fce913 100644 --- a/drivers/bluetooth/hci_bcm.c +++ b/drivers/bluetooth/hci_bcm.c @@ -406,6 +406,9 @@ static int bcm_open(struct hci_uart *hu) bt_dev_dbg(hu->hdev, "hu %p", hu); + if (!hci_uart_has_flow_control(hu)) + return -EOPNOTSUPP; + bcm = kzalloc(sizeof(*bcm), GFP_KERNEL); if (!bcm) return -ENOMEM; diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c index 207bae5e0d46..31f25153087d 100644 --- a/drivers/bluetooth/hci_intel.c +++ b/drivers/bluetooth/hci_intel.c @@ -391,6 +391,9 @@ static int intel_open(struct hci_uart *hu) BT_DBG("hu %p", hu); + if (!hci_uart_has_flow_control(hu)) + return -EOPNOTSUPP; + intel = kzalloc(sizeof(*intel), GFP_KERNEL); if (!intel) return -ENOMEM; diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 8950e07889fe..85a30fb9177b 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -292,6 +292,19 @@ static int hci_uart_send_frame(struct hci_dev *hdev, struct sk_buff *skb) return 0; } +/* Check the underlying device or tty has flow control support */ +bool hci_uart_has_flow_control(struct hci_uart *hu) +{ + /* serdev nodes check if the needed operations are present */ + if (hu->serdev) + return true; + + if (hu->tty->driver->ops->tiocmget && hu->tty->driver->ops->tiocmset) + return true; + + return false; +} + /* Flow control or un-flow control the device */ void hci_uart_set_flow_control(struct hci_uart *hu, bool enable) { diff --git a/drivers/bluetooth/hci_mrvl.c b/drivers/bluetooth/hci_mrvl.c index f98e5cc343b2..fbc3f7c3a5c7 100644 --- a/drivers/bluetooth/hci_mrvl.c +++ b/drivers/bluetooth/hci_mrvl.c @@ -59,6 +59,9 @@ static int mrvl_open(struct hci_uart *hu) BT_DBG("hu %p", hu); + if (!hci_uart_has_flow_control(hu)) + return -EOPNOTSUPP; + mrvl = kzalloc(sizeof(*mrvl), GFP_KERNEL); if (!mrvl) return -ENOMEM; diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 9a5c9c1f9484..82a0a3691a63 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -473,6 +473,9 @@ static int qca_open(struct hci_uart *hu) BT_DBG("hu %p qca_open", hu); + if (!hci_uart_has_flow_control(hu)) + return -EOPNOTSUPP; + qca = kzalloc(sizeof(struct qca_data), GFP_KERNEL); if (!qca) return -ENOMEM; diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h index f11af3912ce6..6ab631101019 100644 --- a/drivers/bluetooth/hci_uart.h +++ b/drivers/bluetooth/hci_uart.h @@ -104,6 +104,7 @@ int hci_uart_wait_until_sent(struct hci_uart *hu); int hci_uart_init_ready(struct hci_uart *hu); void hci_uart_init_work(struct work_struct *work); void hci_uart_set_baudrate(struct hci_uart *hu, unsigned int speed); +bool hci_uart_has_flow_control(struct hci_uart *hu); void hci_uart_set_flow_control(struct hci_uart *hu, bool enable); void hci_uart_set_speeds(struct hci_uart *hu, unsigned int init_speed, unsigned int oper_speed); From 3de433c5b38af49a5fc7602721e2ab5d39f1e69c Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Tue, 30 Jul 2019 14:46:28 -0700 Subject: [PATCH 675/823] drm/msm: Use the correct dma_sync calls in msm_gem [subject was: drm/msm: shake fist angrily at dma-mapping] So, using dma_sync_* for our cache needs works out w/ dma iommu ops, but it falls appart with dma direct ops. The problem is that, depending on display generation, we can have either set of dma ops (mdp4 and dpu have iommu wired to mdss node, which maps to toplevel drm device, but mdp5 has iommu wired up to the mdp sub-node within mdss). Fixes this splat on mdp5 devices: Unable to handle kernel paging request at virtual address ffffffff80000000 Mem abort info: ESR = 0x96000144 Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000144 CM = 1, WnR = 1 swapper pgtable: 4k pages, 48-bit VAs, pgdp=00000000810e4000 [ffffffff80000000] pgd=0000000000000000 Internal error: Oops: 96000144 [#1] SMP Modules linked in: btqcomsmd btqca bluetooth cfg80211 ecdh_generic ecc rfkill libarc4 panel_simple msm wcnss_ctrl qrtr_smd drm_kms_helper venus_enc venus_dec videobuf2_dma_sg videobuf2_memops drm venus_core ipv6 qrtr qcom_wcnss_pil v4l2_mem2mem qcom_sysmon videobuf2_v4l2 qmi_helpers videobuf2_common crct10dif_ce mdt_loader qcom_common videodev qcom_glink_smem remoteproc bmc150_accel_i2c bmc150_magn_i2c bmc150_accel_core bmc150_magn snd_soc_lpass_apq8016 snd_soc_msm8916_analog mms114 mc nf_defrag_ipv6 snd_soc_lpass_cpu snd_soc_apq8016_sbc industrialio_triggered_buffer kfifo_buf snd_soc_lpass_platform snd_soc_msm8916_digital drm_panel_orientation_quirks CPU: 2 PID: 33 Comm: kworker/2:1 Not tainted 5.3.0-rc2 #1 Hardware name: Samsung Galaxy A5U (EUR) (DT) Workqueue: events deferred_probe_work_func pstate: 80000005 (Nzcv daif -PAN -UAO) pc : __clean_dcache_area_poc+0x20/0x38 lr : arch_sync_dma_for_device+0x28/0x30 sp : ffff0000115736a0 x29: ffff0000115736a0 x28: 0000000000000001 x27: ffff800074830800 x26: ffff000011478000 x25: 0000000000000000 x24: 0000000000000001 x23: ffff000011478a98 x22: ffff800009fd1c10 x21: 0000000000000001 x20: ffff800075ad0a00 x19: 0000000000000000 x18: ffff0000112b2000 x17: 0000000000000000 x16: 0000000000000000 x15: 00000000fffffff0 x14: ffff000011455d70 x13: 0000000000000000 x12: 0000000000000028 x11: 0000000000000001 x10: ffff00001106c000 x9 : ffff7e0001d6b380 x8 : 0000000000001000 x7 : ffff7e0001d6b380 x6 : ffff7e0001d6b382 x5 : 0000000000000000 x4 : 0000000000001000 x3 : 000000000000003f x2 : 0000000000000040 x1 : ffffffff80001000 x0 : ffffffff80000000 Call trace: __clean_dcache_area_poc+0x20/0x38 dma_direct_sync_sg_for_device+0xb8/0xe8 get_pages+0x22c/0x250 [msm] msm_gem_get_and_pin_iova+0xdc/0x168 [msm] ... Fixes the combination of two patches: Fixes: 0036bc73ccbe (drm/msm: stop abusing dma_map/unmap for cache) Fixes: 449fa54d6815 (dma-direct: correct the physical addr in dma_direct_sync_sg_for_cpu/device) Tested-by: Stephan Gerhold Signed-off-by: Rob Clark [seanpaul changed subject to something more desriptive] Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20190730214633.17820-1-robdclark@gmail.com --- drivers/gpu/drm/msm/msm_gem.c | 47 +++++++++++++++++++++++++++++++---- 1 file changed, 42 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index c2114c748c2f..8cf6362e64bf 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -32,6 +32,46 @@ static bool use_pages(struct drm_gem_object *obj) return !msm_obj->vram_node; } +/* + * Cache sync.. this is a bit over-complicated, to fit dma-mapping + * API. Really GPU cache is out of scope here (handled on cmdstream) + * and all we need to do is invalidate newly allocated pages before + * mapping to CPU as uncached/writecombine. + * + * On top of this, we have the added headache, that depending on + * display generation, the display's iommu may be wired up to either + * the toplevel drm device (mdss), or to the mdp sub-node, meaning + * that here we either have dma-direct or iommu ops. + * + * Let this be a cautionary tail of abstraction gone wrong. + */ + +static void sync_for_device(struct msm_gem_object *msm_obj) +{ + struct device *dev = msm_obj->base.dev->dev; + + if (get_dma_ops(dev)) { + dma_sync_sg_for_device(dev, msm_obj->sgt->sgl, + msm_obj->sgt->nents, DMA_BIDIRECTIONAL); + } else { + dma_map_sg(dev, msm_obj->sgt->sgl, + msm_obj->sgt->nents, DMA_BIDIRECTIONAL); + } +} + +static void sync_for_cpu(struct msm_gem_object *msm_obj) +{ + struct device *dev = msm_obj->base.dev->dev; + + if (get_dma_ops(dev)) { + dma_sync_sg_for_cpu(dev, msm_obj->sgt->sgl, + msm_obj->sgt->nents, DMA_BIDIRECTIONAL); + } else { + dma_unmap_sg(dev, msm_obj->sgt->sgl, + msm_obj->sgt->nents, DMA_BIDIRECTIONAL); + } +} + /* allocate pages from VRAM carveout, used when no IOMMU: */ static struct page **get_pages_vram(struct drm_gem_object *obj, int npages) { @@ -97,8 +137,7 @@ static struct page **get_pages(struct drm_gem_object *obj) * because display controller, GPU, etc. are not coherent: */ if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED)) - dma_sync_sg_for_device(dev->dev, msm_obj->sgt->sgl, - msm_obj->sgt->nents, DMA_BIDIRECTIONAL); + sync_for_device(msm_obj); } return msm_obj->pages; @@ -127,9 +166,7 @@ static void put_pages(struct drm_gem_object *obj) * GPU, etc. are not coherent: */ if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED)) - dma_sync_sg_for_cpu(obj->dev->dev, msm_obj->sgt->sgl, - msm_obj->sgt->nents, - DMA_BIDIRECTIONAL); + sync_for_cpu(msm_obj); sg_free_table(msm_obj->sgt); kfree(msm_obj->sgt); From 45385237f65aeee73641f1ef737d7273905a233f Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Thu, 25 Jul 2019 12:52:43 +0200 Subject: [PATCH 676/823] selinux: fix memory leak in policydb_init() Since roles_init() adds some entries to the role hash table, we need to destroy also its keys/values on error, otherwise we get a memory leak in the error path. Cc: Reported-by: syzbot+fee3a14d4cdf92646287@syzkaller.appspotmail.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Ondrej Mosnacek Signed-off-by: Paul Moore --- security/selinux/ss/policydb.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index daecdfb15a9c..38d0083204f1 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -274,6 +274,8 @@ static int rangetr_cmp(struct hashtab *h, const void *k1, const void *k2) return v; } +static int (*destroy_f[SYM_NUM]) (void *key, void *datum, void *datap); + /* * Initialize a policy database structure. */ @@ -321,8 +323,10 @@ static int policydb_init(struct policydb *p) out: hashtab_destroy(p->filename_trans); hashtab_destroy(p->range_tr); - for (i = 0; i < SYM_NUM; i++) + for (i = 0; i < SYM_NUM; i++) { + hashtab_map(p->symtab[i].table, destroy_f[i], NULL); hashtab_destroy(p->symtab[i].table); + } return rc; } From e29903c49990376e5e928b20f658cdf7c29bf1eb Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 29 Jul 2019 16:08:03 -0700 Subject: [PATCH 677/823] selftests/tls: fix TLS tests with CONFIG_TLS=n Build bot reports some recent TLS tests are failing with CONFIG_TLS=n. Correct the expected return code and skip TLS installation if not supported. Tested with CONFIG_TLS=n and CONFIG_TLS=m. Reported-by: kernel test robot Fixes: cf32526c8842 ("selftests/tls: add a test for ULP but no keys") Fixes: 65d41fb317c6 ("selftests/tls: add a bidirectional test") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- tools/testing/selftests/net/tls.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 630c5b884d43..d995e6503b1a 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -69,7 +69,7 @@ FIXTURE_SETUP(tls_basic) ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); if (ret != 0) { - ASSERT_EQ(errno, ENOTSUPP); + ASSERT_EQ(errno, ENOENT); self->notls = true; printf("Failure setting TCP_ULP, testing without tls\n"); return; @@ -696,21 +696,26 @@ TEST_F(tls, recv_lowat) TEST_F(tls, bidir) { - struct tls12_crypto_info_aes_gcm_128 tls12; char const *test_str = "test_read"; int send_len = 10; char buf[10]; int ret; - memset(&tls12, 0, sizeof(tls12)); - tls12.info.version = TLS_1_3_VERSION; - tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128; + if (!self->notls) { + struct tls12_crypto_info_aes_gcm_128 tls12; - ret = setsockopt(self->fd, SOL_TLS, TLS_RX, &tls12, sizeof(tls12)); - ASSERT_EQ(ret, 0); + memset(&tls12, 0, sizeof(tls12)); + tls12.info.version = TLS_1_3_VERSION; + tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128; - ret = setsockopt(self->cfd, SOL_TLS, TLS_TX, &tls12, sizeof(tls12)); - ASSERT_EQ(ret, 0); + ret = setsockopt(self->fd, SOL_TLS, TLS_RX, &tls12, + sizeof(tls12)); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_TX, &tls12, + sizeof(tls12)); + ASSERT_EQ(ret, 0); + } ASSERT_EQ(strlen(test_str) + 1, send_len); From 271da132e29b5341c31eca6ba6a72ea1302ebac8 Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Tue, 30 Jul 2019 16:08:13 +0800 Subject: [PATCH 678/823] net: phy: phy_led_triggers: Fix a possible null-pointer dereference in phy_led_trigger_change_speed() In phy_led_trigger_change_speed(), there is an if statement on line 48 to check whether phy->last_triggered is NULL: if (!phy->last_triggered) When phy->last_triggered is NULL, it is used on line 52: led_trigger_event(&phy->last_triggered->trigger, LED_OFF); Thus, a possible null-pointer dereference may occur. To fix this bug, led_trigger_event(&phy->last_triggered->trigger, LED_OFF) is called when phy->last_triggered is not NULL. This bug is found by a static analysis tool STCheck written by the OSLAB group in Tsinghua University. Signed-off-by: Jia-Ju Bai Signed-off-by: David S. Miller --- drivers/net/phy/phy_led_triggers.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/phy_led_triggers.c b/drivers/net/phy/phy_led_triggers.c index b86a4b2116f8..59a94e07e7c5 100644 --- a/drivers/net/phy/phy_led_triggers.c +++ b/drivers/net/phy/phy_led_triggers.c @@ -48,8 +48,9 @@ void phy_led_trigger_change_speed(struct phy_device *phy) if (!phy->last_triggered) led_trigger_event(&phy->led_link_trigger->trigger, LED_FULL); + else + led_trigger_event(&phy->last_triggered->trigger, LED_OFF); - led_trigger_event(&phy->last_triggered->trigger, LED_OFF); led_trigger_event(&plt->trigger, LED_FULL); phy->last_triggered = plt; } From 5c725b6b65067909548ac9ca9bc777098ec9883d Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 30 Jul 2019 14:21:00 +0300 Subject: [PATCH 679/823] net: bridge: mcast: don't delete permanent entries when fast leave is enabled When permanent entries were introduced by the commit below, they were exempt from timing out and thus igmp leave wouldn't affect them unless fast leave was enabled on the port which was added before permanent entries existed. It shouldn't matter if fast leave is enabled or not if the user added a permanent entry it shouldn't be deleted on igmp leave. Before: $ echo 1 > /sys/class/net/eth4/brport/multicast_fast_leave $ bridge mdb add dev br0 port eth4 grp 229.1.1.1 permanent $ bridge mdb show dev br0 port eth4 grp 229.1.1.1 permanent < join and leave 229.1.1.1 on eth4 > $ bridge mdb show $ After: $ echo 1 > /sys/class/net/eth4/brport/multicast_fast_leave $ bridge mdb add dev br0 port eth4 grp 229.1.1.1 permanent $ bridge mdb show dev br0 port eth4 grp 229.1.1.1 permanent < join and leave 229.1.1.1 on eth4 > $ bridge mdb show dev br0 port eth4 grp 229.1.1.1 permanent Fixes: ccb1c31a7a87 ("bridge: add flags to distinguish permanent mdb entires") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_multicast.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3d8deac2353d..f8cac3702712 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1388,6 +1388,9 @@ br_multicast_leave_group(struct net_bridge *br, if (!br_port_group_equal(p, port, src)) continue; + if (p->flags & MDB_PG_FLAGS_PERMANENT) + break; + rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); From 4d97972b45f080db4c6d27cc0b54321d9cd7be17 Mon Sep 17 00:00:00 2001 From: Frode Isaksen Date: Tue, 30 Jul 2019 13:38:14 +0200 Subject: [PATCH 680/823] net: stmmac: Use netif_tx_napi_add() for TX polling function This variant of netif_napi_add() should be used from drivers using NAPI to exclusively poll a TX queue. Signed-off-by: Frode Isaksen Tested-by: Bartosz Golaszewski Signed-off-by: Bartosz Golaszewski Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 9a4a56ad35cd..fd54c7c87485 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4320,8 +4320,9 @@ int stmmac_dvr_probe(struct device *device, NAPI_POLL_WEIGHT); } if (queue < priv->plat->tx_queues_to_use) { - netif_napi_add(ndev, &ch->tx_napi, stmmac_napi_poll_tx, - NAPI_POLL_WEIGHT); + netif_tx_napi_add(ndev, &ch->tx_napi, + stmmac_napi_poll_tx, + NAPI_POLL_WEIGHT); } } From 50f6393f9654c561df4cdcf8e6cfba7260143601 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 14 Jun 2019 07:46:02 +0200 Subject: [PATCH 681/823] xen/swiotlb: fix condition for calling xen_destroy_contiguous_region() The condition in xen_swiotlb_free_coherent() for deciding whether to call xen_destroy_contiguous_region() is wrong: in case the region to be freed is not contiguous calling xen_destroy_contiguous_region() is the wrong thing to do: it would result in inconsistent mappings of multiple PFNs to the same MFN. This will lead to various strange crashes or data corruption. Instead of calling xen_destroy_contiguous_region() in that case a warning should be issued as that situation should never occur. Cc: stable@vger.kernel.org Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Reviewed-by: Jan Beulich Acked-by: Konrad Rzeszutek Wilk Signed-off-by: Juergen Gross --- drivers/xen/swiotlb-xen.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index d53f3493a6b9..50fd7de54969 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -361,8 +361,8 @@ xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr, /* Convert the size to actually allocated. */ size = 1UL << (order + XEN_PAGE_SHIFT); - if (((dev_addr + size - 1 <= dma_mask)) || - range_straddles_page_boundary(phys, size)) + if (!WARN_ON((dev_addr + size - 1 > dma_mask) || + range_straddles_page_boundary(phys, size))) xen_destroy_contiguous_region(phys, order); xen_free_coherent_pages(hwdev, size, vaddr, (dma_addr_t)phys, attrs); From bf70726668c6116aa4976e0cc87f470be6268a2f Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 14 Jun 2019 07:46:03 +0200 Subject: [PATCH 682/823] xen/swiotlb: simplify range_straddles_page_boundary() range_straddles_page_boundary() is open coding several macros from include/xen/page.h. Use those instead. Additionally there is no need to have check_pages_physically_contiguous() as a separate function as it is used only once, so merge it into range_straddles_page_boundary(). Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Acked-by: Konrad Rzeszutek Wilk Signed-off-by: Juergen Gross --- drivers/xen/swiotlb-xen.c | 34 +++++++++------------------------- 1 file changed, 9 insertions(+), 25 deletions(-) diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 50fd7de54969..37ddcfcfbb21 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -83,34 +83,18 @@ static inline dma_addr_t xen_virt_to_bus(void *address) return xen_phys_to_bus(virt_to_phys(address)); } -static int check_pages_physically_contiguous(unsigned long xen_pfn, - unsigned int offset, - size_t length) -{ - unsigned long next_bfn; - int i; - int nr_pages; - - next_bfn = pfn_to_bfn(xen_pfn); - nr_pages = (offset + length + XEN_PAGE_SIZE-1) >> XEN_PAGE_SHIFT; - - for (i = 1; i < nr_pages; i++) { - if (pfn_to_bfn(++xen_pfn) != ++next_bfn) - return 0; - } - return 1; -} - static inline int range_straddles_page_boundary(phys_addr_t p, size_t size) { - unsigned long xen_pfn = XEN_PFN_DOWN(p); - unsigned int offset = p & ~XEN_PAGE_MASK; + unsigned long next_bfn, xen_pfn = XEN_PFN_DOWN(p); + unsigned int i, nr_pages = XEN_PFN_UP(xen_offset_in_page(p) + size); - if (offset + size <= XEN_PAGE_SIZE) - return 0; - if (check_pages_physically_contiguous(xen_pfn, offset, size)) - return 0; - return 1; + next_bfn = pfn_to_bfn(xen_pfn); + + for (i = 1; i < nr_pages; i++) + if (pfn_to_bfn(++xen_pfn) != ++next_bfn) + return 1; + + return 0; } static int is_xen_swiotlb_buffer(dma_addr_t dma_addr) From b877ac9815a8fe7e5f6d7fdde3dc34652408840a Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 14 Jun 2019 07:46:04 +0200 Subject: [PATCH 683/823] xen/swiotlb: remember having called xen_create_contiguous_region() Instead of always calling xen_destroy_contiguous_region() in case the memory is DMA-able for the used device, do so only in case it has been made DMA-able via xen_create_contiguous_region() before. This will avoid a lot of xen_destroy_contiguous_region() calls for 64-bit capable devices. As the memory in question is owned by swiotlb-xen the PG_owner_priv_1 flag of the first allocated page can be used for remembering. Signed-off-by: Juergen Gross Acked-by: Konrad Rzeszutek Wilk Signed-off-by: Juergen Gross --- drivers/xen/swiotlb-xen.c | 4 +++- include/linux/page-flags.h | 4 ++++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 37ddcfcfbb21..ceb681cf64bb 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -322,6 +322,7 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size, xen_free_coherent_pages(hwdev, size, ret, (dma_addr_t)phys, attrs); return NULL; } + SetPageXenRemapped(virt_to_page(ret)); } memset(ret, 0, size); return ret; @@ -346,7 +347,8 @@ xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr, size = 1UL << (order + XEN_PAGE_SHIFT); if (!WARN_ON((dev_addr + size - 1 > dma_mask) || - range_straddles_page_boundary(phys, size))) + range_straddles_page_boundary(phys, size)) && + TestClearPageXenRemapped(virt_to_page(vaddr))) xen_destroy_contiguous_region(phys, order); xen_free_coherent_pages(hwdev, size, vaddr, (dma_addr_t)phys, attrs); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index b848517da64c..f91cb8898ff0 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -152,6 +152,8 @@ enum pageflags { PG_savepinned = PG_dirty, /* Has a grant mapping of another (foreign) domain's page. */ PG_foreign = PG_owner_priv_1, + /* Remapped by swiotlb-xen. */ + PG_xen_remapped = PG_owner_priv_1, /* SLOB */ PG_slob_free = PG_private, @@ -329,6 +331,8 @@ PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND) TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND) PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND); PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); +PAGEFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) + TESTCLEARFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) From 0de50e40fc685fed4d6896a379b123f859ffb17b Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 26 Jun 2019 16:45:49 +0100 Subject: [PATCH 684/823] drm/i915: Lift intel_engines_resume() to callers Since the reset path wants to recover the engines itself, it only wants to reinitialise the hardware using i915_gem_init_hw(). Pull the call to intel_engines_resume() to the module init/resume path so we can avoid it during reset. Fixes: 79ffac8599c4 ("drm/i915: Invert the GEM wakeref hierarchy") Signed-off-by: Chris Wilson Reviewed-by: Mika Kuoppala Cc: Tvrtko Ursulin Cc: Imre Deak Link: https://patchwork.freedesktop.org/patch/msgid/20190626154549.10066-3-chris@chris-wilson.co.uk (cherry picked from commit 092be382a2602067766f190a113514d469162456) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gem/i915_gem_pm.c | 7 ++++--- drivers/gpu/drm/i915/gt/intel_engine_pm.c | 24 ---------------------- drivers/gpu/drm/i915/gt/intel_engine_pm.h | 2 -- drivers/gpu/drm/i915/gt/intel_gt_pm.c | 21 ++++++++++++++++++- drivers/gpu/drm/i915/gt/intel_gt_pm.h | 2 +- drivers/gpu/drm/i915/gt/intel_reset.c | 21 ++++++++++++++++++- drivers/gpu/drm/i915/i915_gem.c | 25 ++++++++++------------- 7 files changed, 56 insertions(+), 46 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c index 05011d4a3b88..914b5d4112bb 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c @@ -253,14 +253,15 @@ void i915_gem_resume(struct drm_i915_private *i915) i915_gem_restore_gtt_mappings(i915); i915_gem_restore_fences(i915); + if (i915_gem_init_hw(i915)) + goto err_wedged; + /* * As we didn't flush the kernel context before suspend, we cannot * guarantee that the context image is complete. So let's just reset * it and start again. */ - intel_gt_resume(i915); - - if (i915_gem_init_hw(i915)) + if (intel_gt_resume(i915)) goto err_wedged; intel_uc_resume(i915); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index 2ce00d3dc42a..ae5b6baf6dff 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -142,27 +142,3 @@ void intel_engine_init__pm(struct intel_engine_cs *engine) { intel_wakeref_init(&engine->wakeref); } - -int intel_engines_resume(struct drm_i915_private *i915) -{ - struct intel_engine_cs *engine; - enum intel_engine_id id; - int err = 0; - - intel_gt_pm_get(i915); - for_each_engine(engine, i915, id) { - intel_engine_pm_get(engine); - engine->serial++; /* kernel context lost */ - err = engine->resume(engine); - intel_engine_pm_put(engine); - if (err) { - dev_err(i915->drm.dev, - "Failed to restart %s (%d)\n", - engine->name, err); - break; - } - } - intel_gt_pm_put(i915); - - return err; -} diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.h b/drivers/gpu/drm/i915/gt/intel_engine_pm.h index b326cd993d60..f6f213fbc98c 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.h @@ -17,6 +17,4 @@ void intel_engine_park(struct intel_engine_cs *engine); void intel_engine_init__pm(struct intel_engine_cs *engine); -int intel_engines_resume(struct drm_i915_private *i915); - #endif /* INTEL_ENGINE_PM_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index 7b5967751762..9f8f7f54191f 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -5,6 +5,7 @@ */ #include "i915_drv.h" +#include "intel_engine_pm.h" #include "intel_gt_pm.h" #include "intel_pm.h" #include "intel_wakeref.h" @@ -118,10 +119,11 @@ void intel_gt_sanitize(struct drm_i915_private *i915, bool force) intel_engine_reset(engine, false); } -void intel_gt_resume(struct drm_i915_private *i915) +int intel_gt_resume(struct drm_i915_private *i915) { struct intel_engine_cs *engine; enum intel_engine_id id; + int err = 0; /* * After resume, we may need to poke into the pinned kernel @@ -129,9 +131,12 @@ void intel_gt_resume(struct drm_i915_private *i915) * Only the kernel contexts should remain pinned over suspend, * allowing us to fixup the user contexts on their first pin. */ + intel_gt_pm_get(i915); for_each_engine(engine, i915, id) { struct intel_context *ce; + intel_engine_pm_get(engine); + ce = engine->kernel_context; if (ce) ce->ops->reset(ce); @@ -139,5 +144,19 @@ void intel_gt_resume(struct drm_i915_private *i915) ce = engine->preempt_context; if (ce) ce->ops->reset(ce); + + engine->serial++; /* kernel context lost */ + err = engine->resume(engine); + + intel_engine_pm_put(engine); + if (err) { + dev_err(i915->drm.dev, + "Failed to restart %s (%d)\n", + engine->name, err); + break; + } } + intel_gt_pm_put(i915); + + return err; } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h index 7dd1130a19a4..53f342b20181 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h @@ -22,6 +22,6 @@ void intel_gt_pm_put(struct drm_i915_private *i915); void intel_gt_pm_init(struct drm_i915_private *i915); void intel_gt_sanitize(struct drm_i915_private *i915, bool force); -void intel_gt_resume(struct drm_i915_private *i915); +int intel_gt_resume(struct drm_i915_private *i915); #endif /* INTEL_GT_PM_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index 4c478b38e420..0439ed66e969 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -951,6 +951,21 @@ static int do_reset(struct drm_i915_private *i915, return gt_reset(i915, stalled_mask); } +static int resume(struct drm_i915_private *i915) +{ + struct intel_engine_cs *engine; + enum intel_engine_id id; + int ret; + + for_each_engine(engine, i915, id) { + ret = engine->resume(engine); + if (ret) + return ret; + } + + return 0; +} + /** * i915_reset - reset chip after a hang * @i915: #drm_i915_private to reset @@ -1024,9 +1039,13 @@ void i915_reset(struct drm_i915_private *i915, if (ret) { DRM_ERROR("Failed to initialise HW following reset (%d)\n", ret); - goto error; + goto taint; } + ret = resume(i915); + if (ret) + goto taint; + i915_queue_hangcheck(i915); finish: diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 190ad54fb072..8a659d3d7435 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -46,7 +46,6 @@ #include "gem/i915_gem_ioctls.h" #include "gem/i915_gem_pm.h" #include "gem/i915_gemfs.h" -#include "gt/intel_engine_pm.h" #include "gt/intel_gt_pm.h" #include "gt/intel_mocs.h" #include "gt/intel_reset.h" @@ -1307,21 +1306,13 @@ int i915_gem_init_hw(struct drm_i915_private *dev_priv) intel_mocs_init_l3cc_table(dev_priv); - /* Only when the HW is re-initialised, can we replay the requests */ - ret = intel_engines_resume(dev_priv); - if (ret) - goto cleanup_uc; - intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL); intel_engines_set_scheduler_caps(dev_priv); return 0; -cleanup_uc: - intel_uc_fini_hw(dev_priv); out: intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL); - return ret; } @@ -1580,6 +1571,11 @@ int i915_gem_init(struct drm_i915_private *dev_priv) if (ret) goto err_uc_init; + /* Only when the HW is re-initialised, can we replay the requests */ + ret = intel_gt_resume(dev_priv); + if (ret) + goto err_init_hw; + /* * Despite its name intel_init_clock_gating applies both display * clock gating workarounds; GT mmio workarounds and the occasional @@ -1593,20 +1589,20 @@ int i915_gem_init(struct drm_i915_private *dev_priv) ret = intel_engines_verify_workarounds(dev_priv); if (ret) - goto err_init_hw; + goto err_gt; ret = __intel_engines_record_defaults(dev_priv); if (ret) - goto err_init_hw; + goto err_gt; if (i915_inject_load_failure()) { ret = -ENODEV; - goto err_init_hw; + goto err_gt; } if (i915_inject_load_failure()) { ret = -EIO; - goto err_init_hw; + goto err_gt; } intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL); @@ -1620,7 +1616,7 @@ int i915_gem_init(struct drm_i915_private *dev_priv) * HW as irrevisibly wedged, but keep enough state around that the * driver doesn't explode during runtime. */ -err_init_hw: +err_gt: mutex_unlock(&dev_priv->drm.struct_mutex); i915_gem_set_wedged(dev_priv); @@ -1630,6 +1626,7 @@ err_init_hw: i915_gem_drain_workqueue(dev_priv); mutex_lock(&dev_priv->drm.struct_mutex); +err_init_hw: intel_uc_fini_hw(dev_priv); err_uc_init: intel_uc_fini(dev_priv); From b1fa6fd94fc6a5d6be85359743b5f3626f3f881c Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 26 Jun 2019 16:45:47 +0100 Subject: [PATCH 685/823] drm/i915: Add a wakeref getter for iff the wakeref is already active For use in the next patch, we want to acquire a wakeref without having to wake the device up -- i.e. only acquire the engine wakeref if the engine is already active. Signed-off-by: Chris Wilson Reviewed-by: Mika Kuoppala Link: https://patchwork.freedesktop.org/patch/msgid/20190626154549.10066-1-chris@chris-wilson.co.uk (cherry picked from commit de5147b8ce6d51f634661d7c531385371485cec6) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gt/intel_engine_pm.h | 10 +++++++++- drivers/gpu/drm/i915/intel_wakeref.h | 15 +++++++++++++++ 2 files changed, 24 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.h b/drivers/gpu/drm/i915/gt/intel_engine_pm.h index f6f213fbc98c..a11c893f64c6 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.h @@ -7,12 +7,20 @@ #ifndef INTEL_ENGINE_PM_H #define INTEL_ENGINE_PM_H +#include "intel_engine_types.h" +#include "intel_wakeref.h" + struct drm_i915_private; -struct intel_engine_cs; void intel_engine_pm_get(struct intel_engine_cs *engine); void intel_engine_pm_put(struct intel_engine_cs *engine); +static inline bool +intel_engine_pm_get_if_awake(struct intel_engine_cs *engine) +{ + return intel_wakeref_get_if_active(&engine->wakeref); +} + void intel_engine_park(struct intel_engine_cs *engine); void intel_engine_init__pm(struct intel_engine_cs *engine); diff --git a/drivers/gpu/drm/i915/intel_wakeref.h b/drivers/gpu/drm/i915/intel_wakeref.h index 9cbb2ebf575b..38275310b196 100644 --- a/drivers/gpu/drm/i915/intel_wakeref.h +++ b/drivers/gpu/drm/i915/intel_wakeref.h @@ -65,6 +65,21 @@ intel_wakeref_get(struct intel_runtime_pm *rpm, return 0; } +/** + * intel_wakeref_get_if_in_use: Acquire the wakeref + * @wf: the wakeref + * + * Acquire a hold on the wakeref, but only if the wakeref is already + * active. + * + * Returns: true if the wakeref was acquired, false otherwise. + */ +static inline bool +intel_wakeref_get_if_active(struct intel_wakeref *wf) +{ + return atomic_inc_not_zero(&wf->count); +} + /** * intel_wakeref_put: Release the wakeref * @i915: the drm_i915_private device From 4b9bb9728c915c6079619e71e3340fe4840d9d40 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 26 Jun 2019 16:45:48 +0100 Subject: [PATCH 686/823] drm/i915: Only recover active engines If we issue a reset to a currently idle engine, leave it idle afterwards. This is useful to excise a linkage between reset and the shrinker. When waking the engine, we need to pin the default context image which we use for overwriting a guilty context -- if the engine is idle we do not need this pinned image! However, this pinning means that waking the engine acquires the FS_RECLAIM, and so may trigger the shrinker. The shrinker itself may need to wait upon the GPU to unbind and object and so may require services of reset; ergo we should avoid the engine wake up path. The danger in skipping the recovery for idle engines is that we leave the engine with no context defined, which may interfere with the operation of the power context on some older platforms. In practice, we should only be resetting an active GPU but it something to look out for on Ironlake (if memory serves). Fixes: 79ffac8599c4 ("drm/i915: Invert the GEM wakeref hierarchy") Signed-off-by: Chris Wilson Reviewed-by: Mika Kuoppala Cc: Tvrtko Ursulin Cc: Imre Deak Link: https://patchwork.freedesktop.org/patch/msgid/20190626154549.10066-2-chris@chris-wilson.co.uk (cherry picked from commit 18398904ca9e3ddd180e2ecd45886e146b1d9d5b) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gt/intel_reset.c | 37 ++++++++++++++---------- drivers/gpu/drm/i915/gt/selftest_reset.c | 5 +++- 2 files changed, 26 insertions(+), 16 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index 0439ed66e969..3f907701ef4d 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -687,7 +687,6 @@ static void reset_prepare_engine(struct intel_engine_cs *engine) * written to the powercontext is undefined and so we may lose * GPU state upon resume, i.e. fail to restart after a reset. */ - intel_engine_pm_get(engine); intel_uncore_forcewake_get(engine->uncore, FORCEWAKE_ALL); engine->reset.prepare(engine); } @@ -718,16 +717,21 @@ static void revoke_mmaps(struct drm_i915_private *i915) } } -static void reset_prepare(struct drm_i915_private *i915) +static intel_engine_mask_t reset_prepare(struct drm_i915_private *i915) { struct intel_engine_cs *engine; + intel_engine_mask_t awake = 0; enum intel_engine_id id; - intel_gt_pm_get(i915); - for_each_engine(engine, i915, id) + for_each_engine(engine, i915, id) { + if (intel_engine_pm_get_if_awake(engine)) + awake |= engine->mask; reset_prepare_engine(engine); + } intel_uc_reset_prepare(i915); + + return awake; } static void gt_revoke(struct drm_i915_private *i915) @@ -761,20 +765,22 @@ static int gt_reset(struct drm_i915_private *i915, static void reset_finish_engine(struct intel_engine_cs *engine) { engine->reset.finish(engine); - intel_engine_pm_put(engine); intel_uncore_forcewake_put(engine->uncore, FORCEWAKE_ALL); + + intel_engine_signal_breadcrumbs(engine); } -static void reset_finish(struct drm_i915_private *i915) +static void reset_finish(struct drm_i915_private *i915, + intel_engine_mask_t awake) { struct intel_engine_cs *engine; enum intel_engine_id id; for_each_engine(engine, i915, id) { reset_finish_engine(engine); - intel_engine_signal_breadcrumbs(engine); + if (awake & engine->mask) + intel_engine_pm_put(engine); } - intel_gt_pm_put(i915); } static void nop_submit_request(struct i915_request *request) @@ -798,6 +804,7 @@ static void __i915_gem_set_wedged(struct drm_i915_private *i915) { struct i915_gpu_error *error = &i915->gpu_error; struct intel_engine_cs *engine; + intel_engine_mask_t awake; enum intel_engine_id id; if (test_bit(I915_WEDGED, &error->flags)) @@ -817,7 +824,7 @@ static void __i915_gem_set_wedged(struct drm_i915_private *i915) * rolling the global seqno forward (since this would complete requests * for which we haven't set the fence error to EIO yet). */ - reset_prepare(i915); + awake = reset_prepare(i915); /* Even if the GPU reset fails, it should still stop the engines */ if (!INTEL_INFO(i915)->gpu_reset_clobbers_display) @@ -841,7 +848,7 @@ static void __i915_gem_set_wedged(struct drm_i915_private *i915) for_each_engine(engine, i915, id) engine->cancel_requests(engine); - reset_finish(i915); + reset_finish(i915, awake); GEM_TRACE("end\n"); } @@ -988,6 +995,7 @@ void i915_reset(struct drm_i915_private *i915, const char *reason) { struct i915_gpu_error *error = &i915->gpu_error; + intel_engine_mask_t awake; int ret; GEM_TRACE("flags=%lx\n", error->flags); @@ -1004,7 +1012,7 @@ void i915_reset(struct drm_i915_private *i915, dev_notice(i915->drm.dev, "Resetting chip for %s\n", reason); error->reset_count++; - reset_prepare(i915); + awake = reset_prepare(i915); if (!intel_has_gpu_reset(i915)) { if (i915_modparams.reset) @@ -1049,7 +1057,7 @@ void i915_reset(struct drm_i915_private *i915, i915_queue_hangcheck(i915); finish: - reset_finish(i915); + reset_finish(i915, awake); unlock: mutex_unlock(&error->wedge_mutex); return; @@ -1100,7 +1108,7 @@ int i915_reset_engine(struct intel_engine_cs *engine, const char *msg) GEM_TRACE("%s flags=%lx\n", engine->name, error->flags); GEM_BUG_ON(!test_bit(I915_RESET_ENGINE + engine->id, &error->flags)); - if (!intel_wakeref_active(&engine->wakeref)) + if (!intel_engine_pm_get_if_awake(engine)) return 0; reset_prepare_engine(engine); @@ -1135,12 +1143,11 @@ int i915_reset_engine(struct intel_engine_cs *engine, const char *msg) * process to program RING_MODE, HWSP and re-enable submission. */ ret = engine->resume(engine); - if (ret) - goto out; out: intel_engine_cancel_stop_cs(engine); reset_finish_engine(engine); + intel_engine_pm_put(engine); return ret; } diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c index 89da9e7cc1ba..b5c590c9ccba 100644 --- a/drivers/gpu/drm/i915/gt/selftest_reset.c +++ b/drivers/gpu/drm/i915/gt/selftest_reset.c @@ -71,13 +71,16 @@ static int igt_atomic_reset(void *arg) goto unlock; for (p = igt_atomic_phases; p->name; p++) { + intel_engine_mask_t awake; + GEM_TRACE("intel_gpu_reset under %s\n", p->name); + awake = reset_prepare(i915); p->critical_section_begin(); reset_prepare(i915); err = intel_gpu_reset(i915, ALL_ENGINES); - reset_finish(i915); p->critical_section_end(); + reset_finish(i915, awake); if (err) { pr_err("intel_gpu_reset failed under %s\n", p->name); From 3fe6c873af2f2247544debdbe51ec29f690a2ccf Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Thu, 1 Aug 2019 13:33:39 +0200 Subject: [PATCH 687/823] parisc: Fix build of compressed kernel even with debug enabled With debug info enabled (CONFIG_DEBUG_INFO=y) the resulting vmlinux may get that huge that we need to increase the start addresss for the decompression text section otherwise one will face a linker error. Reported-by: Sven Schnelle Tested-by: Sven Schnelle Cc: stable@vger.kernel.org # v4.14+ Signed-off-by: Helge Deller --- arch/parisc/boot/compressed/vmlinux.lds.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/parisc/boot/compressed/vmlinux.lds.S b/arch/parisc/boot/compressed/vmlinux.lds.S index bfd7872739a3..2ac3a643f2eb 100644 --- a/arch/parisc/boot/compressed/vmlinux.lds.S +++ b/arch/parisc/boot/compressed/vmlinux.lds.S @@ -48,8 +48,8 @@ SECTIONS *(.rodata.compressed) } - /* bootloader code and data starts behind area of extracted kernel */ - . = (SZ_end - SZparisc_kernel_start + KERNEL_BINARY_TEXT_START); + /* bootloader code and data starts at least behind area of extracted kernel */ + . = MAX(ABSOLUTE(.), (SZ_end - SZparisc_kernel_start + KERNEL_BINARY_TEXT_START)); /* align on next page boundary */ . = ALIGN(4096); From e50beea8e7738377b4fa664078547be338038ff9 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Thu, 1 Aug 2019 13:42:18 +0200 Subject: [PATCH 688/823] parisc: Strip debug info from kernel before creating compressed vmlinuz Same as on x86-64, strip the .comment, .note and debug sections from the Linux kernel before creating the compressed image for the boot loader. Reported-by: James Bottomley Reported-by: Sven Schnelle Cc: stable@vger.kernel.org # v4.20+ Signed-off-by: Helge Deller --- arch/parisc/boot/compressed/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/parisc/boot/compressed/Makefile b/arch/parisc/boot/compressed/Makefile index 2da8624e5cf6..3b28d1b92218 100644 --- a/arch/parisc/boot/compressed/Makefile +++ b/arch/parisc/boot/compressed/Makefile @@ -55,7 +55,8 @@ $(obj)/misc.o: $(obj)/sizes.h CPPFLAGS_vmlinux.lds += -I$(objtree)/$(obj) -DBOOTLOADER $(obj)/vmlinux.lds: $(obj)/sizes.h -$(obj)/vmlinux.bin: vmlinux +OBJCOPYFLAGS_vmlinux.bin := -R .comment -R .note -S +$(obj)/vmlinux.bin: vmlinux FORCE $(call if_changed,objcopy) vmlinux.bin.all-y := $(obj)/vmlinux.bin From f2c5ed0dd5004c2cff5c0e3d430a107576fcc17f Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Thu, 1 Aug 2019 13:47:03 +0200 Subject: [PATCH 689/823] parisc: Add archclean Makefile target Apparently we don't have an archclean target in our arch/parisc/Makefile, so files in there never get cleaned out by make mrproper. This, in turn means that the sizes.h file in arch/parisc/boot/compressed never gets removed and worse, when you transition to an O=build/parisc[64] build model it overrides the generated file. The upshot being my bzImage was building with a SZ_end that was too small. I fixed it by making mrproper clean everything. Signed-off-by: James Bottomley Cc: stable@vger.kernel.org # v4.20+ Signed-off-by: Helge Deller --- arch/parisc/Makefile | 3 +++ arch/parisc/boot/compressed/Makefile | 1 + 2 files changed, 4 insertions(+) diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index b10a1179291a..3b77d729057f 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -180,5 +180,8 @@ define archhelp @echo ' zinstall - Install compressed vmlinuz kernel' endef +archclean: + $(Q)$(MAKE) $(clean)=$(boot) + archheaders: $(Q)$(MAKE) $(build)=arch/parisc/kernel/syscalls all diff --git a/arch/parisc/boot/compressed/Makefile b/arch/parisc/boot/compressed/Makefile index 3b28d1b92218..1e5879c6a752 100644 --- a/arch/parisc/boot/compressed/Makefile +++ b/arch/parisc/boot/compressed/Makefile @@ -12,6 +12,7 @@ UBSAN_SANITIZE := n targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4 targets += misc.o piggy.o sizes.h head.o real2.o firmware.o +targets += real2.S firmware.c KBUILD_CFLAGS := -D__KERNEL__ -O2 -DBOOTLOADER KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING From fd01eecdf9591453177d7b06faaabef8c300114a Mon Sep 17 00:00:00 2001 From: Rayagonda Kokatanur Date: Wed, 24 Jul 2019 13:58:27 +0530 Subject: [PATCH 690/823] i2c: iproc: Fix i2c master read more than 63 bytes Use SMBUS_MASTER_DATA_READ.MASTER_RD_STATUS bit to check for RX FIFO empty condition because SMBUS_MASTER_FIFO_CONTROL.MASTER_RX_PKT_COUNT is not updated for read >= 64 bytes. This fixes the issue when trying to read from the I2C slave more than 63 bytes. Fixes: c24b8d574b7c ("i2c: iproc: Extend I2C read up to 255 bytes") Cc: stable@kernel.org Signed-off-by: Rayagonda Kokatanur Reviewed-by: Ray Jui Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-bcm-iproc.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c index 2c7f145a036e..d7fd76baec92 100644 --- a/drivers/i2c/busses/i2c-bcm-iproc.c +++ b/drivers/i2c/busses/i2c-bcm-iproc.c @@ -392,16 +392,18 @@ static bool bcm_iproc_i2c_slave_isr(struct bcm_iproc_i2c_dev *iproc_i2c, static void bcm_iproc_i2c_read_valid_bytes(struct bcm_iproc_i2c_dev *iproc_i2c) { struct i2c_msg *msg = iproc_i2c->msg; + uint32_t val; /* Read valid data from RX FIFO */ while (iproc_i2c->rx_bytes < msg->len) { - if (!((iproc_i2c_rd_reg(iproc_i2c, M_FIFO_CTRL_OFFSET) >> M_FIFO_RX_CNT_SHIFT) - & M_FIFO_RX_CNT_MASK)) + val = iproc_i2c_rd_reg(iproc_i2c, M_RX_OFFSET); + + /* rx fifo empty */ + if (!((val >> M_RX_STATUS_SHIFT) & M_RX_STATUS_MASK)) break; msg->buf[iproc_i2c->rx_bytes] = - (iproc_i2c_rd_reg(iproc_i2c, M_RX_OFFSET) >> - M_RX_DATA_SHIFT) & M_RX_DATA_MASK; + (val >> M_RX_DATA_SHIFT) & M_RX_DATA_MASK; iproc_i2c->rx_bytes++; } } From d9b42dfab513c9130ee0458f2e6febb75c89d1c8 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Wed, 3 Jul 2019 09:58:18 +0200 Subject: [PATCH 691/823] drm/client: Support unmapping of DRM client buffers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit DRM clients, such as the fbdev emulation, have their buffer objects mapped by default. Mapping a buffer implicitly prevents its relocation. Hence, the buffer may permanently consume video memory while it's allocated. This is a problem for drivers of low-memory devices, such as ast, mgag200 or older framebuffer hardware, which will then not have enough memory to display other content (e.g., X11). This patch introduces drm_client_buffer_vmap() and _vunmap(). Internal DRM clients can use these functions to unmap and remap buffer objects as needed. There's no reference counting for vmap operations. Callers are expected to either keep buffers mapped (as it is now), or call vmap and vunmap in pairs around code that accesses the mapped memory. v2: * remove several duplicated NULL-pointer checks v3: * style and typo fixes Signed-off-by: Thomas Zimmermann Reviewed-by: Noralf Trønnes Link: https://patchwork.freedesktop.org/patch/315831/ Signed-off-by: Gerd Hoffmann --- drivers/gpu/drm/drm_client.c | 68 ++++++++++++++++++++++++++++++------ include/drm/drm_client.h | 2 ++ 2 files changed, 59 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c index 410572f14257..fb107b24baae 100644 --- a/drivers/gpu/drm/drm_client.c +++ b/drivers/gpu/drm/drm_client.c @@ -281,22 +281,12 @@ drm_client_buffer_create(struct drm_client_dev *client, u32 width, u32 height, u buffer->gem = obj; - /* - * FIXME: The dependency on GEM here isn't required, we could - * convert the driver handle to a dma-buf instead and use the - * backend-agnostic dma-buf vmap support instead. This would - * require that the handle2fd prime ioctl is reworked to pull the - * fd_install step out of the driver backend hooks, to make that - * final step optional for internal users. - */ - vaddr = drm_gem_vmap(obj); + vaddr = drm_client_buffer_vmap(buffer); if (IS_ERR(vaddr)) { ret = PTR_ERR(vaddr); goto err_delete; } - buffer->vaddr = vaddr; - return buffer; err_delete: @@ -305,6 +295,62 @@ err_delete: return ERR_PTR(ret); } +/** + * drm_client_buffer_vmap - Map DRM client buffer into address space + * @buffer: DRM client buffer + * + * This function maps a client buffer into kernel address space. If the + * buffer is already mapped, it returns the mapping's address. + * + * Client buffer mappings are not ref'counted. Each call to + * drm_client_buffer_vmap() should be followed by a call to + * drm_client_buffer_vunmap(); or the client buffer should be mapped + * throughout its lifetime. The latter is the default. + * + * Returns: + * The mapped memory's address + */ +void *drm_client_buffer_vmap(struct drm_client_buffer *buffer) +{ + void *vaddr; + + if (buffer->vaddr) + return buffer->vaddr; + + /* + * FIXME: The dependency on GEM here isn't required, we could + * convert the driver handle to a dma-buf instead and use the + * backend-agnostic dma-buf vmap support instead. This would + * require that the handle2fd prime ioctl is reworked to pull the + * fd_install step out of the driver backend hooks, to make that + * final step optional for internal users. + */ + vaddr = drm_gem_vmap(buffer->gem); + if (IS_ERR(vaddr)) + return vaddr; + + buffer->vaddr = vaddr; + + return vaddr; +} +EXPORT_SYMBOL(drm_client_buffer_vmap); + +/** + * drm_client_buffer_vunmap - Unmap DRM client buffer + * @buffer: DRM client buffer + * + * This function removes a client buffer's memory mapping. This + * function is only required by clients that manage their buffers + * by themselves. By default, DRM client buffers are mapped throughout + * their entire lifetime. + */ +void drm_client_buffer_vunmap(struct drm_client_buffer *buffer) +{ + drm_gem_vunmap(buffer->gem, buffer->vaddr); + buffer->vaddr = NULL; +} +EXPORT_SYMBOL(drm_client_buffer_vunmap); + static void drm_client_buffer_rmfb(struct drm_client_buffer *buffer) { int ret; diff --git a/include/drm/drm_client.h b/include/drm/drm_client.h index 72d51d1e9dd9..5cf2c5dd8b1e 100644 --- a/include/drm/drm_client.h +++ b/include/drm/drm_client.h @@ -149,6 +149,8 @@ struct drm_client_buffer { struct drm_client_buffer * drm_client_framebuffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format); void drm_client_framebuffer_delete(struct drm_client_buffer *buffer); +void *drm_client_buffer_vmap(struct drm_client_buffer *buffer); +void drm_client_buffer_vunmap(struct drm_client_buffer *buffer); int drm_client_modeset_create(struct drm_client_dev *client); void drm_client_modeset_free(struct drm_client_dev *client); From 87e281f88f3aa4ed401554f793685bcb2463580a Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Wed, 3 Jul 2019 09:58:24 +0200 Subject: [PATCH 692/823] drm/fb-helper: Map DRM client buffer only when required MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch changes DRM clients to not map the buffer by default. The buffer, like any buffer object, should be mapped and unmapped when needed. An unmapped buffer object can be evicted to system memory and does not consume video ram until displayed. This allows to use generic fbdev emulation with drivers for low-memory devices, such as ast and mgag200. This change affects the generic framebuffer console. HW-based consoles map their console buffer once and keep it mapped. Userspace can mmap this buffer into its address space. The shadow-buffered framebuffer console only needs the buffer object to be mapped during updates. While not being updated from the shadow buffer, the buffer object can remain unmapped. Userspace will always mmap the shadow buffer. v2: * change DRM client to not map buffer by default * manually map client buffer for fbdev with HW framebuffer Signed-off-by: Thomas Zimmermann Reviewed-by: Noralf Trønnes Link: https://patchwork.freedesktop.org/patch/315830/ Signed-off-by: Gerd Hoffmann --- drivers/gpu/drm/drm_client.c | 16 ++++------------ drivers/gpu/drm/drm_fb_helper.c | 33 +++++++++++++++++++++++++-------- 2 files changed, 29 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c index fb107b24baae..e1dafb0cc5e2 100644 --- a/drivers/gpu/drm/drm_client.c +++ b/drivers/gpu/drm/drm_client.c @@ -254,7 +254,6 @@ drm_client_buffer_create(struct drm_client_dev *client, u32 width, u32 height, u struct drm_device *dev = client->dev; struct drm_client_buffer *buffer; struct drm_gem_object *obj; - void *vaddr; int ret; buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); @@ -281,12 +280,6 @@ drm_client_buffer_create(struct drm_client_dev *client, u32 width, u32 height, u buffer->gem = obj; - vaddr = drm_client_buffer_vmap(buffer); - if (IS_ERR(vaddr)) { - ret = PTR_ERR(vaddr); - goto err_delete; - } - return buffer; err_delete: @@ -305,7 +298,7 @@ err_delete: * Client buffer mappings are not ref'counted. Each call to * drm_client_buffer_vmap() should be followed by a call to * drm_client_buffer_vunmap(); or the client buffer should be mapped - * throughout its lifetime. The latter is the default. + * throughout its lifetime. * * Returns: * The mapped memory's address @@ -339,10 +332,9 @@ EXPORT_SYMBOL(drm_client_buffer_vmap); * drm_client_buffer_vunmap - Unmap DRM client buffer * @buffer: DRM client buffer * - * This function removes a client buffer's memory mapping. This - * function is only required by clients that manage their buffers - * by themselves. By default, DRM client buffers are mapped throughout - * their entire lifetime. + * This function removes a client buffer's memory mapping. Calling this + * function is only required by clients that manage their buffer mappings + * by themselves. */ void drm_client_buffer_vunmap(struct drm_client_buffer *buffer) { diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 1984e5c54d58..7ba6a0255821 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -403,6 +403,7 @@ static void drm_fb_helper_dirty_work(struct work_struct *work) struct drm_clip_rect *clip = &helper->dirty_clip; struct drm_clip_rect clip_copy; unsigned long flags; + void *vaddr; spin_lock_irqsave(&helper->dirty_lock, flags); clip_copy = *clip; @@ -412,10 +413,18 @@ static void drm_fb_helper_dirty_work(struct work_struct *work) /* call dirty callback only when it has been really touched */ if (clip_copy.x1 < clip_copy.x2 && clip_copy.y1 < clip_copy.y2) { + /* Generic fbdev uses a shadow buffer */ - if (helper->buffer) + if (helper->buffer) { + vaddr = drm_client_buffer_vmap(helper->buffer); + if (IS_ERR(vaddr)) + return; drm_fb_helper_dirty_blit_real(helper, &clip_copy); + } helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, &clip_copy, 1); + + if (helper->buffer) + drm_client_buffer_vunmap(helper->buffer); } } @@ -2178,6 +2187,7 @@ int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper, struct drm_framebuffer *fb; struct fb_info *fbi; u32 format; + void *vaddr; DRM_DEBUG_KMS("surface width(%d), height(%d) and bpp(%d)\n", sizes->surface_width, sizes->surface_height, @@ -2200,13 +2210,7 @@ int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper, fbi->fbops = &drm_fbdev_fb_ops; fbi->screen_size = fb->height * fb->pitches[0]; fbi->fix.smem_len = fbi->screen_size; - fbi->screen_buffer = buffer->vaddr; - /* Shamelessly leak the physical address to user-space */ -#if IS_ENABLED(CONFIG_DRM_FBDEV_LEAK_PHYS_SMEM) - if (drm_leak_fbdev_smem && fbi->fix.smem_start == 0) - fbi->fix.smem_start = - page_to_phys(virt_to_page(fbi->screen_buffer)); -#endif + drm_fb_helper_fill_info(fbi, fb_helper, sizes); if (fb->funcs->dirty) { @@ -2231,6 +2235,19 @@ int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper, fbi->fbdefio = &drm_fbdev_defio; fb_deferred_io_init(fbi); + } else { + /* buffer is mapped for HW framebuffer */ + vaddr = drm_client_buffer_vmap(fb_helper->buffer); + if (IS_ERR(vaddr)) + return PTR_ERR(vaddr); + + fbi->screen_buffer = vaddr; + /* Shamelessly leak the physical address to user-space */ +#if IS_ENABLED(CONFIG_DRM_FBDEV_LEAK_PHYS_SMEM) + if (drm_leak_fbdev_smem && fbi->fix.smem_start == 0) + fbi->fix.smem_start = + page_to_phys(virt_to_page(fbi->screen_buffer)); +#endif } return 0; From 01b947afaa940327e7adf57070a4bf3d0bed9810 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 5 Jul 2019 09:31:00 +0200 Subject: [PATCH 693/823] drm/fb-helper: Instanciate shadow FB if configured in device's mode_config MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Generic framebuffer emulation uses a shadow buffer for framebuffers with dirty() function. If drivers want to use the shadow FB without such a function, they can now set prefer_shadow or prefer_shadow_fbdev in their mode_config structures. The former flag is exported to userspace, the latter flag is fbdev-only. v3: * only schedule dirty worker if fbdev uses shadow fb * test shadow fb settings with boolean operators * use bool for struct drm_mode_config.prefer_shadow_fbdev * fix documentation comments Signed-off-by: Thomas Zimmermann Reviewed-by: Noralf Trønnes Tested-by: Noralf Trønnes Link: https://patchwork.freedesktop.org/patch/315834/ Signed-off-by: Gerd Hoffmann --- drivers/gpu/drm/drm_fb_helper.c | 18 +++++++++++++++--- include/drm/drm_mode_config.h | 7 +++++++ 2 files changed, 22 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 7ba6a0255821..a7ba5b4902d6 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -421,7 +421,9 @@ static void drm_fb_helper_dirty_work(struct work_struct *work) return; drm_fb_helper_dirty_blit_real(helper, &clip_copy); } - helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, &clip_copy, 1); + if (helper->fb->funcs->dirty) + helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, + &clip_copy, 1); if (helper->buffer) drm_client_buffer_vunmap(helper->buffer); @@ -613,6 +615,16 @@ void drm_fb_helper_unlink_fbi(struct drm_fb_helper *fb_helper) } EXPORT_SYMBOL(drm_fb_helper_unlink_fbi); +static bool drm_fbdev_use_shadow_fb(struct drm_fb_helper *fb_helper) +{ + struct drm_device *dev = fb_helper->dev; + struct drm_framebuffer *fb = fb_helper->fb; + + return dev->mode_config.prefer_shadow_fbdev || + dev->mode_config.prefer_shadow || + fb->funcs->dirty; +} + static void drm_fb_helper_dirty(struct fb_info *info, u32 x, u32 y, u32 width, u32 height) { @@ -620,7 +632,7 @@ static void drm_fb_helper_dirty(struct fb_info *info, u32 x, u32 y, struct drm_clip_rect *clip = &helper->dirty_clip; unsigned long flags; - if (!helper->fb->funcs->dirty) + if (!drm_fbdev_use_shadow_fb(helper)) return; spin_lock_irqsave(&helper->dirty_lock, flags); @@ -2213,7 +2225,7 @@ int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper, drm_fb_helper_fill_info(fbi, fb_helper, sizes); - if (fb->funcs->dirty) { + if (drm_fbdev_use_shadow_fb(fb_helper)) { struct fb_ops *fbops; void *shadow; diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index 759d462d028b..f57eea0481e0 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -852,6 +852,13 @@ struct drm_mode_config { /* dumb ioctl parameters */ uint32_t preferred_depth, prefer_shadow; + /** + * @prefer_shadow_fbdev: + * + * Hint to framebuffer emulation to prefer shadow-fb rendering. + */ + bool prefer_shadow_fbdev; + /** * @quirk_addfb_prefer_xbgr_30bpp: * From 58540594570778fd149cd8c9b2bff61f2cefa8c9 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Wed, 3 Jul 2019 09:58:34 +0200 Subject: [PATCH 694/823] drm/bochs: Use shadow buffer for bochs framebuffer console MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The bochs driver (and virtual hardware) requires buffer objects to reside in video ram to display them to the screen. So it can not display the framebuffer console because the respective buffer object is permanently pinned in system memory. Using a shadow buffer for the console solves this problem. The console emulation will pin the buffer object only during updates from the shadow buffer. Otherwise, the bochs driver can freely relocated the buffer between system memory and video ram. v2: * select shadow FB via struct drm_mode_config.prefer_shadow_fbdev Signed-off-by: Thomas Zimmermann Acked-by: Noralf Trønnes Link: https://patchwork.freedesktop.org/patch/315833/ Signed-off-by: Gerd Hoffmann --- drivers/gpu/drm/bochs/bochs_kms.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c index bc19dbd531ef..359030d5d818 100644 --- a/drivers/gpu/drm/bochs/bochs_kms.c +++ b/drivers/gpu/drm/bochs/bochs_kms.c @@ -191,6 +191,7 @@ int bochs_kms_init(struct bochs_device *bochs) bochs->dev->mode_config.fb_base = bochs->fb_base; bochs->dev->mode_config.preferred_depth = 24; bochs->dev->mode_config.prefer_shadow = 0; + bochs->dev->mode_config.prefer_shadow_fbdev = 1; bochs->dev->mode_config.quirk_addfb_prefer_host_byte_order = true; bochs->dev->mode_config.funcs = &bochs_mode_funcs; From 811ba489fa524ec634933cdf83aaf6c007a4c004 Mon Sep 17 00:00:00 2001 From: Nishka Dasgupta Date: Wed, 24 Jul 2019 14:02:31 +0530 Subject: [PATCH 695/823] regulator: of: Add of_node_put() before return in function The local variable search in regulator_of_get_init_node takes the value returned by either of_get_child_by_name or of_node_get, both of which get a node. If this node is not put before returning, it could cause a memory leak. Hence put search before a mid-loop return statement. Issue found with Coccinelle. Signed-off-by: Nishka Dasgupta Link: https://lore.kernel.org/r/20190724083231.10276-1-nishkadg.linux@gmail.com Signed-off-by: Mark Brown --- drivers/regulator/of_regulator.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c index 397918ebba55..9112faa6a9a0 100644 --- a/drivers/regulator/of_regulator.c +++ b/drivers/regulator/of_regulator.c @@ -416,8 +416,10 @@ device_node *regulator_of_get_init_node(struct device *dev, if (!name) name = child->name; - if (!strcmp(desc->of_match, name)) + if (!strcmp(desc->of_match, name)) { + of_node_put(search); return of_node_get(child); + } } of_node_put(search); From 677379bc9139ac24b310a281fcb21a2f04288353 Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Mon, 29 Jul 2019 15:57:46 +0100 Subject: [PATCH 696/823] arm64: Lower priority mask for GIC_PRIO_IRQON On a system with two security states, if SCR_EL3.FIQ is cleared, non-secure IRQ priorities get shifted to fit the secure view but priority masks aren't. On such system, it turns out that GIC_PRIO_IRQON masks the priority of normal interrupts, which obviously ends up in a hang. Increase GIC_PRIO_IRQON value (i.e. lower priority) to make sure interrupts are not blocked by it. Cc: Oleg Nesterov Fixes: bd82d4bd21880b7c ("arm64: Fix incorrect irqflag restore for priority masking") Acked-by: Marc Zyngier Signed-off-by: Julien Thierry Signed-off-by: Catalin Marinas [will: fixed Fixes: tag] Signed-off-by: Will Deacon --- arch/arm64/include/asm/arch_gicv3.h | 6 ++++++ arch/arm64/include/asm/ptrace.h | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 79155a8cfe7c..89e4c8b79349 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -155,6 +155,12 @@ static inline void gic_pmr_mask_irqs(void) BUILD_BUG_ON(GICD_INT_DEF_PRI < (GIC_PRIO_IRQOFF | GIC_PRIO_PSR_I_SET)); BUILD_BUG_ON(GICD_INT_DEF_PRI >= GIC_PRIO_IRQON); + /* + * Need to make sure IRQON allows IRQs when SCR_EL3.FIQ is cleared + * and non-secure PMR accesses are not subject to the shifts that + * are applied to IRQ priorities + */ + BUILD_BUG_ON((0x80 | (GICD_INT_DEF_PRI >> 1)) >= GIC_PRIO_IRQON); gic_write_pmr(GIC_PRIO_IRQOFF); } diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index b1dd039023ef..1dcf63a9ac1f 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -30,7 +30,7 @@ * in the the priority mask, it indicates that PSR.I should be set and * interrupt disabling temporarily does not rely on IRQ priorities. */ -#define GIC_PRIO_IRQON 0xc0 +#define GIC_PRIO_IRQON 0xe0 #define GIC_PRIO_IRQOFF (GIC_PRIO_IRQON & ~0x80) #define GIC_PRIO_PSR_I_SET (1 << 4) From ee07b93e7721ccd5d5b9fa6f0c10cb3fe2f1f4f9 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 25 Jul 2019 17:16:05 +0900 Subject: [PATCH 697/823] arm64: unwind: Prohibit probing on return_address() Prohibit probing on return_address() and subroutines which is called from return_address(), since the it is invoked from trace_hardirqs_off() which is also kprobe blacklisted. Reported-by: Naresh Kamboju Signed-off-by: Masami Hiramatsu Signed-off-by: Will Deacon --- arch/arm64/kernel/return_address.c | 3 +++ arch/arm64/kernel/stacktrace.c | 3 +++ 2 files changed, 6 insertions(+) diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c index c4ae647d2306..a5e8b3b9d798 100644 --- a/arch/arm64/kernel/return_address.c +++ b/arch/arm64/kernel/return_address.c @@ -8,6 +8,7 @@ #include #include +#include #include #include @@ -29,6 +30,7 @@ static int save_return_addr(struct stackframe *frame, void *d) return 0; } } +NOKPROBE_SYMBOL(save_return_addr); void *return_address(unsigned int level) { @@ -49,3 +51,4 @@ void *return_address(unsigned int level) return NULL; } EXPORT_SYMBOL_GPL(return_address); +NOKPROBE_SYMBOL(return_address); diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 2b160ae594eb..a336cb124320 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -111,6 +112,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) return 0; } +NOKPROBE_SYMBOL(unwind_frame); void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame, int (*fn)(struct stackframe *, void *), void *data) @@ -125,6 +127,7 @@ void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame, break; } } +NOKPROBE_SYMBOL(walk_stackframe); #ifdef CONFIG_STACKTRACE struct stack_trace_data { From 760d8ed069c4e32a92e2ba251a3b0d9a87a3e771 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 25 Jul 2019 17:16:25 +0900 Subject: [PATCH 698/823] arm64: Remove unneeded rcu_read_lock from debug handlers Remove rcu_read_lock()/rcu_read_unlock() from debug exception handlers since we are sure those are not preemptible and interrupts are off. Acked-by: Paul E. McKenney Signed-off-by: Masami Hiramatsu Signed-off-by: Will Deacon --- arch/arm64/kernel/debug-monitors.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index f8719bd30850..48222a4760c2 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -207,16 +207,16 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr) list = user_mode(regs) ? &user_step_hook : &kernel_step_hook; - rcu_read_lock(); - + /* + * Since single-step exception disables interrupt, this function is + * entirely not preemptible, and we can use rcu list safely here. + */ list_for_each_entry_rcu(hook, list, node) { retval = hook->fn(regs, esr); if (retval == DBG_HOOK_HANDLED) break; } - rcu_read_unlock(); - return retval; } NOKPROBE_SYMBOL(call_step_hook); @@ -305,14 +305,16 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr) list = user_mode(regs) ? &user_break_hook : &kernel_break_hook; - rcu_read_lock(); + /* + * Since brk exception disables interrupt, this function is + * entirely not preemptible, and we can use rcu list safely here. + */ list_for_each_entry_rcu(hook, list, node) { unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK; if ((comment & ~hook->mask) == hook->imm) fn = hook->fn; } - rcu_read_unlock(); return fn ? fn(regs, esr) : DBG_HOOK_ERROR; } From 7d4e2dcf311d3b98421d1f119efe5964cafa32fc Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Wed, 31 Jul 2019 16:05:45 -0400 Subject: [PATCH 699/823] arm64/mm: fix variable 'pud' set but not used GCC throws a warning, arch/arm64/mm/mmu.c: In function 'pud_free_pmd_page': arch/arm64/mm/mmu.c:1033:8: warning: variable 'pud' set but not used [-Wunused-but-set-variable] pud_t pud; ^~~ because pud_table() is a macro and compiled away. Fix it by making it a static inline function and for pud_sect() as well. Signed-off-by: Qian Cai Signed-off-by: Will Deacon --- arch/arm64/include/asm/pgtable.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 3f5461f7b560..5fdcfe237338 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -447,8 +447,8 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, PMD_TYPE_SECT) #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3 -#define pud_sect(pud) (0) -#define pud_table(pud) (1) +static inline bool pud_sect(pud_t pud) { return false; } +static inline bool pud_table(pud_t pud) { return true; } #else #define pud_sect(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \ PUD_TYPE_SECT) From 2bab52af6fe68c43b327a57e5ce5fc10eefdfadf Mon Sep 17 00:00:00 2001 From: Brian Masney Date: Fri, 31 May 2019 05:46:15 -0400 Subject: [PATCH 700/823] drm/msm: add support for per-CRTC max_vblank_count on mdp5 The mdp5 drm/kms driver currently does not work on command-mode DSI panels due to 'vblank wait timed out' errors. This causes a latency of seconds, or tens of seconds in some cases, before content is shown on the panel. This hardware does not have the something that we can use as a frame counter available when running in command mode, so we need to fall back to using timestamps by setting the max_vblank_count to zero. This can be done on a per-CRTC basis, so the convert mdp5 to use drm_crtc_set_max_vblank_count(). This change was tested on a LG Nexus 5 (hammerhead) phone. Suggested-by: Jeffrey Hugo Reviewed-by: Jeffrey Hugo Signed-off-by: Brian Masney Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20190531094619.31704-3-masneyb@onstation.org --- drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c | 16 +++++++++++++++- drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c | 2 +- 2 files changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c index ff14555372d0..78d5fa230c16 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c @@ -439,6 +439,18 @@ static void mdp5_crtc_atomic_disable(struct drm_crtc *crtc, mdp5_crtc->enabled = false; } +static void mdp5_crtc_vblank_on(struct drm_crtc *crtc) +{ + struct mdp5_crtc_state *mdp5_cstate = to_mdp5_crtc_state(crtc->state); + struct mdp5_interface *intf = mdp5_cstate->pipeline.intf; + u32 count; + + count = intf->mode == MDP5_INTF_DSI_MODE_COMMAND ? 0 : 0xffffffff; + drm_crtc_set_max_vblank_count(crtc, count); + + drm_crtc_vblank_on(crtc); +} + static void mdp5_crtc_atomic_enable(struct drm_crtc *crtc, struct drm_crtc_state *old_state) { @@ -475,7 +487,7 @@ static void mdp5_crtc_atomic_enable(struct drm_crtc *crtc, } /* Restore vblank irq handling after power is enabled */ - drm_crtc_vblank_on(crtc); + mdp5_crtc_vblank_on(crtc); mdp5_crtc_mode_set_nofb(crtc); @@ -1028,6 +1040,8 @@ static void mdp5_crtc_reset(struct drm_crtc *crtc) mdp5_crtc_destroy_state(crtc, crtc->state); __drm_atomic_helper_crtc_reset(crtc, &mdp5_cstate->base); + + drm_crtc_vblank_reset(crtc); } static const struct drm_crtc_funcs mdp5_crtc_funcs = { diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c index 4a60f5fca6b0..fec6ef1ae3b9 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c @@ -740,7 +740,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev) dev->driver->get_vblank_timestamp = drm_calc_vbltimestamp_from_scanoutpos; dev->driver->get_scanout_position = mdp5_get_scanoutpos; dev->driver->get_vblank_counter = mdp5_get_vblank_counter; - dev->max_vblank_count = 0xffffffff; + dev->max_vblank_count = 0; /* max_vblank_count is set on each CRTC */ dev->vblank_disable_immediate = true; return kms; From c14b5dce5ece48035cfd0aa951b39c69ad5056f4 Mon Sep 17 00:00:00 2001 From: Jordan Crouse Date: Thu, 25 Jul 2019 10:53:08 -0600 Subject: [PATCH 701/823] drm/msm: Annotate intentional switch statement fall throughs Explicitly mark intentional fall throughs in switch statements to keep -Wimplicit-fallthrough from complaining. Reviewed-by: Rob Clark Signed-off-by: Jordan Crouse Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/1564073588-27386-1-git-send-email-jcrouse@codeaurora.org --- drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 2 ++ drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 1 + drivers/gpu/drm/msm/adreno/adreno_gpu.c | 1 + 3 files changed, 4 insertions(+) diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 1671db47aa57..e9c55d1d6c04 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -59,6 +59,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: if (priv->lastctx == ctx) break; + /* fall-thru */ case MSM_SUBMIT_CMD_BUF: /* copy commands into RB: */ obj = submit->bos[submit->cmd[i].idx].obj; @@ -149,6 +150,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: if (priv->lastctx == ctx) break; + /* fall-thru */ case MSM_SUBMIT_CMD_BUF: OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3); OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index be39cf01e51e..dc8ec2c94301 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -115,6 +115,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: if (priv->lastctx == ctx) break; + /* fall-thru */ case MSM_SUBMIT_CMD_BUF: OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3); OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 9acbbc0f3232..048c8be426f3 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -428,6 +428,7 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, /* ignore if there has not been a ctx switch: */ if (priv->lastctx == ctx) break; + /* fall-thru */ case MSM_SUBMIT_CMD_BUF: OUT_PKT3(ring, adreno_is_a430(adreno_gpu) ? CP_INDIRECT_BUFFER_PFE : CP_INDIRECT_BUFFER_PFD, 2); From 7732d20a160c76006c7fe7bca5178aea6af1d2e8 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 1 Aug 2019 10:47:05 -0400 Subject: [PATCH 702/823] arm64/mm: fix variable 'tag' set but not used When CONFIG_KASAN_SW_TAGS=n, set_tag() is compiled away. GCC throws a warning, mm/kasan/common.c: In function '__kasan_kmalloc': mm/kasan/common.c:464:5: warning: variable 'tag' set but not used [-Wunused-but-set-variable] u8 tag = 0xff; ^~~ Fix it by making __tag_set() a static inline function the same as arch_kasan_set_tag() in mm/kasan/kasan.h for consistency because there is a macro in arch/arm64/include/asm/kasan.h, #define arch_kasan_set_tag(addr, tag) __tag_set(addr, tag) However, when CONFIG_DEBUG_VIRTUAL=n and CONFIG_SPARSEMEM_VMEMMAP=y, page_to_virt() will call __tag_set() with incorrect type of a parameter, so fix that as well. Also, still let page_to_virt() return "void *" instead of "const void *", so will not need to add a similar cast in lowmem_page_address(). Signed-off-by: Qian Cai Signed-off-by: Will Deacon --- arch/arm64/include/asm/memory.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index b7ba75809751..fb04f10a78ab 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -210,7 +210,11 @@ extern u64 vabits_user; #define __tag_reset(addr) untagged_addr(addr) #define __tag_get(addr) (__u8)((u64)(addr) >> 56) #else -#define __tag_set(addr, tag) (addr) +static inline const void *__tag_set(const void *addr, u8 tag) +{ + return addr; +} + #define __tag_reset(addr) (addr) #define __tag_get(addr) 0 #endif @@ -301,8 +305,8 @@ static inline void *phys_to_virt(phys_addr_t x) #define page_to_virt(page) ({ \ unsigned long __addr = \ ((__page_to_voff(page)) | PAGE_OFFSET); \ - unsigned long __addr_tag = \ - __tag_set(__addr, page_kasan_tag(page)); \ + const void *__addr_tag = \ + __tag_set((void *)__addr, page_kasan_tag(page)); \ ((void *)__addr_tag); \ }) From 61f259821dd3306e49b7d42a3f90fb5a4ff3351b Mon Sep 17 00:00:00 2001 From: "Luck, Tony" Date: Tue, 30 Jul 2019 21:39:57 -0700 Subject: [PATCH 703/823] IB/core: Add mitigation for Spectre V1 Some processors may mispredict an array bounds check and speculatively access memory that they should not. With a user supplied array index we like to play things safe by masking the value with the array size before it is used as an index. Signed-off-by: Tony Luck Link: https://lore.kernel.org/r/20190731043957.GA1600@agluck-desk2.amr.corp.intel.com Signed-off-by: Doug Ledford --- drivers/infiniband/core/user_mad.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index 9f8a48016b41..ffdeaf6e0b68 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -49,6 +49,7 @@ #include #include #include +#include #include @@ -884,11 +885,14 @@ static int ib_umad_unreg_agent(struct ib_umad_file *file, u32 __user *arg) if (get_user(id, arg)) return -EFAULT; + if (id >= IB_UMAD_MAX_AGENTS) + return -EINVAL; mutex_lock(&file->port->file_mutex); mutex_lock(&file->mutex); - if (id >= IB_UMAD_MAX_AGENTS || !__get_agent(file, id)) { + id = array_index_nospec(id, IB_UMAD_MAX_AGENTS); + if (!__get_agent(file, id)) { ret = -EINVAL; goto out; } From 621e55ff5b8e0ab5d1063f0eae0ef3960bef8f6e Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 31 Jul 2019 11:18:40 +0300 Subject: [PATCH 704/823] RDMA/devices: Do not deadlock during client removal lockdep reports: WARNING: possible circular locking dependency detected modprobe/302 is trying to acquire lock: 0000000007c8919c ((wq_completion)ib_cm){+.+.}, at: flush_workqueue+0xdf/0x990 but task is already holding lock: 000000002d3d2ca9 (&device->client_data_rwsem){++++}, at: remove_client_context+0x79/0xd0 [ib_core] which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&device->client_data_rwsem){++++}: down_read+0x3f/0x160 ib_get_net_dev_by_params+0xd5/0x200 [ib_core] cma_ib_req_handler+0x5f6/0x2090 [rdma_cm] cm_process_work+0x29/0x110 [ib_cm] cm_req_handler+0x10f5/0x1c00 [ib_cm] cm_work_handler+0x54c/0x311d [ib_cm] process_one_work+0x4aa/0xa30 worker_thread+0x62/0x5b0 kthread+0x1ca/0x1f0 ret_from_fork+0x24/0x30 -> #1 ((work_completion)(&(&work->work)->work)){+.+.}: process_one_work+0x45f/0xa30 worker_thread+0x62/0x5b0 kthread+0x1ca/0x1f0 ret_from_fork+0x24/0x30 -> #0 ((wq_completion)ib_cm){+.+.}: lock_acquire+0xc8/0x1d0 flush_workqueue+0x102/0x990 cm_remove_one+0x30e/0x3c0 [ib_cm] remove_client_context+0x94/0xd0 [ib_core] disable_device+0x10a/0x1f0 [ib_core] __ib_unregister_device+0x5a/0xe0 [ib_core] ib_unregister_device+0x21/0x30 [ib_core] mlx5_ib_stage_ib_reg_cleanup+0x9/0x10 [mlx5_ib] __mlx5_ib_remove+0x3d/0x70 [mlx5_ib] mlx5_ib_remove+0x12e/0x140 [mlx5_ib] mlx5_remove_device+0x144/0x150 [mlx5_core] mlx5_unregister_interface+0x3f/0xf0 [mlx5_core] mlx5_ib_cleanup+0x10/0x3a [mlx5_ib] __x64_sys_delete_module+0x227/0x350 do_syscall_64+0xc3/0x6a4 entry_SYSCALL_64_after_hwframe+0x49/0xbe Which is due to the read side of the client_data_rwsem being obtained recursively through a work queue flush during cm client removal. The lock is being held across the remove in remove_client_context() so that the function is a fence, once it returns the client is removed. This is required so that the two callers do not proceed with destruction until the client completes removal. Instead of using client_data_rwsem use the existing device unregistration refcount and add a similar client unregistration (client->uses) refcount. This will fence the two unregistration paths without holding any locks. Cc: Fixes: 921eab1143aa ("RDMA/devices: Re-organize device.c locking") Signed-off-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/20190731081841.32345-2-leon@kernel.org Signed-off-by: Doug Ledford --- drivers/infiniband/core/device.c | 56 ++++++++++++++++++++++++-------- include/rdma/ib_verbs.h | 3 ++ 2 files changed, 45 insertions(+), 14 deletions(-) diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 9773145dee09..d86fbabe48d6 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -99,6 +99,12 @@ static LIST_HEAD(client_list); static DEFINE_XARRAY_FLAGS(clients, XA_FLAGS_ALLOC); static DECLARE_RWSEM(clients_rwsem); +static void ib_client_put(struct ib_client *client) +{ + if (refcount_dec_and_test(&client->uses)) + complete(&client->uses_zero); +} + /* * If client_data is registered then the corresponding client must also still * be registered. @@ -660,6 +666,14 @@ static int add_client_context(struct ib_device *device, return 0; down_write(&device->client_data_rwsem); + /* + * So long as the client is registered hold both the client and device + * unregistration locks. + */ + if (!refcount_inc_not_zero(&client->uses)) + goto out_unlock; + refcount_inc(&device->refcount); + /* * Another caller to add_client_context got here first and has already * completely initialized context. @@ -683,6 +697,9 @@ static int add_client_context(struct ib_device *device, return 0; out: + ib_device_put(device); + ib_client_put(client); +out_unlock: up_write(&device->client_data_rwsem); return ret; } @@ -702,7 +719,7 @@ static void remove_client_context(struct ib_device *device, client_data = xa_load(&device->client_data, client_id); xa_clear_mark(&device->client_data, client_id, CLIENT_DATA_REGISTERED); client = xa_load(&clients, client_id); - downgrade_write(&device->client_data_rwsem); + up_write(&device->client_data_rwsem); /* * Notice we cannot be holding any exclusive locks when calling the @@ -712,17 +729,13 @@ static void remove_client_context(struct ib_device *device, * * For this reason clients and drivers should not call the * unregistration functions will holdling any locks. - * - * It tempting to drop the client_data_rwsem too, but this is required - * to ensure that unregister_client does not return until all clients - * are completely unregistered, which is required to avoid module - * unloading races. */ if (client->remove) client->remove(device, client_data); xa_erase(&device->client_data, client_id); - up_read(&device->client_data_rwsem); + ib_device_put(device); + ib_client_put(client); } static int alloc_port_data(struct ib_device *device) @@ -1705,6 +1718,8 @@ int ib_register_client(struct ib_client *client) unsigned long index; int ret; + refcount_set(&client->uses, 1); + init_completion(&client->uses_zero); ret = assign_client_id(client); if (ret) return ret; @@ -1740,16 +1755,29 @@ void ib_unregister_client(struct ib_client *client) unsigned long index; down_write(&clients_rwsem); + ib_client_put(client); xa_clear_mark(&clients, client->client_id, CLIENT_REGISTERED); up_write(&clients_rwsem); - /* - * Every device still known must be serialized to make sure we are - * done with the client callbacks before we return. - */ - down_read(&devices_rwsem); - xa_for_each (&devices, index, device) + + /* We do not want to have locks while calling client->remove() */ + rcu_read_lock(); + xa_for_each (&devices, index, device) { + if (!ib_device_try_get(device)) + continue; + rcu_read_unlock(); + remove_client_context(device, client->client_id); - up_read(&devices_rwsem); + + ib_device_put(device); + rcu_read_lock(); + } + rcu_read_unlock(); + + /* + * remove_client_context() is not a fence, it can return even though a + * removal is ongoing. Wait until all removals are completed. + */ + wait_for_completion(&client->uses_zero); down_write(&clients_rwsem); list_del(&client->list); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index c5f8a9f17063..7b80ec822043 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2647,6 +2647,9 @@ struct ib_client { const union ib_gid *gid, const struct sockaddr *addr, void *client_data); + + refcount_t uses; + struct completion uses_zero; struct list_head list; u32 client_id; From 9cd5881719e9555cae300ec8b389eda3c8101339 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 31 Jul 2019 11:18:41 +0300 Subject: [PATCH 705/823] RDMA/devices: Remove the lock around remove_client_context Due to the complexity of client->remove() callbacks it is desirable to not hold any locks while calling them. Remove the last one by tracking only the highest client ID and running backwards from there over the xarray. Since the only purpose of that lock was to protect the linked list, we can drop the lock. Signed-off-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/20190731081841.32345-3-leon@kernel.org Signed-off-by: Doug Ledford --- drivers/infiniband/core/device.c | 48 ++++++++++++++++++-------------- include/rdma/ib_verbs.h | 1 - 2 files changed, 27 insertions(+), 22 deletions(-) diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index d86fbabe48d6..ea8661a00651 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -94,7 +94,7 @@ static DEFINE_XARRAY_FLAGS(devices, XA_FLAGS_ALLOC); static DECLARE_RWSEM(devices_rwsem); #define DEVICE_REGISTERED XA_MARK_1 -static LIST_HEAD(client_list); +static u32 highest_client_id; #define CLIENT_REGISTERED XA_MARK_1 static DEFINE_XARRAY_FLAGS(clients, XA_FLAGS_ALLOC); static DECLARE_RWSEM(clients_rwsem); @@ -1237,7 +1237,7 @@ static int setup_device(struct ib_device *device) static void disable_device(struct ib_device *device) { - struct ib_client *client; + u32 cid; WARN_ON(!refcount_read(&device->refcount)); @@ -1245,10 +1245,19 @@ static void disable_device(struct ib_device *device) xa_clear_mark(&devices, device->index, DEVICE_REGISTERED); up_write(&devices_rwsem); + /* + * Remove clients in LIFO order, see assign_client_id. This could be + * more efficient if xarray learns to reverse iterate. Since no new + * clients can be added to this ib_device past this point we only need + * the maximum possible client_id value here. + */ down_read(&clients_rwsem); - list_for_each_entry_reverse(client, &client_list, list) - remove_client_context(device, client->client_id); + cid = highest_client_id; up_read(&clients_rwsem); + while (cid) { + cid--; + remove_client_context(device, cid); + } /* Pairs with refcount_set in enable_device */ ib_device_put(device); @@ -1675,30 +1684,31 @@ static int assign_client_id(struct ib_client *client) /* * The add/remove callbacks must be called in FIFO/LIFO order. To * achieve this we assign client_ids so they are sorted in - * registration order, and retain a linked list we can reverse iterate - * to get the LIFO order. The extra linked list can go away if xarray - * learns to reverse iterate. + * registration order. */ - if (list_empty(&client_list)) { - client->client_id = 0; - } else { - struct ib_client *last; - - last = list_last_entry(&client_list, struct ib_client, list); - client->client_id = last->client_id + 1; - } + client->client_id = highest_client_id; ret = xa_insert(&clients, client->client_id, client, GFP_KERNEL); if (ret) goto out; + highest_client_id++; xa_set_mark(&clients, client->client_id, CLIENT_REGISTERED); - list_add_tail(&client->list, &client_list); out: up_write(&clients_rwsem); return ret; } +static void remove_client_id(struct ib_client *client) +{ + down_write(&clients_rwsem); + xa_erase(&clients, client->client_id); + for (; highest_client_id; highest_client_id--) + if (xa_load(&clients, highest_client_id - 1)) + break; + up_write(&clients_rwsem); +} + /** * ib_register_client - Register an IB client * @client:Client to register @@ -1778,11 +1788,7 @@ void ib_unregister_client(struct ib_client *client) * removal is ongoing. Wait until all removals are completed. */ wait_for_completion(&client->uses_zero); - - down_write(&clients_rwsem); - list_del(&client->list); - xa_erase(&clients, client->client_id); - up_write(&clients_rwsem); + remove_client_id(client); } EXPORT_SYMBOL(ib_unregister_client); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 7b80ec822043..4f225175cb91 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2650,7 +2650,6 @@ struct ib_client { refcount_t uses; struct completion uses_zero; - struct list_head list; u32 client_id; /* kverbs are not required by the client */ From e5366d309a772fef264ec85e858f9ea46f939848 Mon Sep 17 00:00:00 2001 From: Guy Levi Date: Wed, 31 Jul 2019 11:19:29 +0300 Subject: [PATCH 706/823] IB/mlx5: Fix MR registration flow to use UMR properly Driver shouldn't allow to use UMR to register a MR when umr_modify_atomic_disabled is set. Otherwise it will always end up with a failure in the post send flow which sets the UMR WQE to modify atomic access right. Fixes: c8d75a980fab ("IB/mlx5: Respect new UMR capabilities") Signed-off-by: Guy Levi Reviewed-by: Moni Shoua Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/20190731081929.32559-1-leon@kernel.org Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/mr.c | 27 +++++++++------------------ 1 file changed, 9 insertions(+), 18 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 2c77456f359f..b74fad08412f 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -51,22 +51,12 @@ static void clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); static void dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); static int mr_cache_max_order(struct mlx5_ib_dev *dev); static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); -static bool umr_can_modify_entity_size(struct mlx5_ib_dev *dev) -{ - return !MLX5_CAP_GEN(dev->mdev, umr_modify_entity_size_disabled); -} static bool umr_can_use_indirect_mkey(struct mlx5_ib_dev *dev) { return !MLX5_CAP_GEN(dev->mdev, umr_indirect_mkey_disabled); } -static bool use_umr(struct mlx5_ib_dev *dev, int order) -{ - return order <= mr_cache_max_order(dev) && - umr_can_modify_entity_size(dev); -} - static int destroy_mkey(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { int err = mlx5_core_destroy_mkey(dev->mdev, &mr->mmkey); @@ -1271,7 +1261,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, { struct mlx5_ib_dev *dev = to_mdev(pd->device); struct mlx5_ib_mr *mr = NULL; - bool populate_mtts = false; + bool use_umr; struct ib_umem *umem; int page_shift; int npages; @@ -1303,29 +1293,30 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, if (err < 0) return ERR_PTR(err); - if (use_umr(dev, order)) { + use_umr = !MLX5_CAP_GEN(dev->mdev, umr_modify_entity_size_disabled) && + (!MLX5_CAP_GEN(dev->mdev, umr_modify_atomic_disabled) || + !MLX5_CAP_GEN(dev->mdev, atomic)); + + if (order <= mr_cache_max_order(dev) && use_umr) { mr = alloc_mr_from_cache(pd, umem, virt_addr, length, ncont, page_shift, order, access_flags); if (PTR_ERR(mr) == -EAGAIN) { mlx5_ib_dbg(dev, "cache empty for order %d\n", order); mr = NULL; } - populate_mtts = false; } else if (!MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset)) { if (access_flags & IB_ACCESS_ON_DEMAND) { err = -EINVAL; pr_err("Got MR registration for ODP MR > 512MB, not supported for Connect-IB\n"); goto error; } - populate_mtts = true; + use_umr = false; } if (!mr) { - if (!umr_can_modify_entity_size(dev)) - populate_mtts = true; mutex_lock(&dev->slow_path_mutex); mr = reg_create(NULL, pd, virt_addr, length, umem, ncont, - page_shift, access_flags, populate_mtts); + page_shift, access_flags, !use_umr); mutex_unlock(&dev->slow_path_mutex); } @@ -1341,7 +1332,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, update_odp_mr(mr); - if (!populate_mtts) { + if (use_umr) { int update_xlt_flags = MLX5_IB_UPD_XLT_ENABLE; if (access_flags & IB_ACCESS_ON_DEMAND) From 52e0a118a20308dd6aa531e20a5ab5907d2264c8 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 1 Aug 2019 13:43:54 +0300 Subject: [PATCH 707/823] RDMA/restrack: Track driver QP types in resource tracker The check for QP type different than XRC has excluded driver QP types from the resource tracker. As a result, "rdma resource show" user command would not show opened driver QPs which does not reflect the real state of the system. Check QP type explicitly instead of assuming enum values/ordering. Fixes: 40909f664d27 ("RDMA/efa: Add EFA verbs implementation") Signed-off-by: Gal Pressman Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20190801104354.11417-1-galpress@amazon.com Signed-off-by: Doug Ledford --- drivers/infiniband/core/core_priv.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h index 888d89ce81df..beee7b7e0d9a 100644 --- a/drivers/infiniband/core/core_priv.h +++ b/drivers/infiniband/core/core_priv.h @@ -302,7 +302,9 @@ static inline struct ib_qp *_ib_create_qp(struct ib_device *dev, struct ib_udata *udata, struct ib_uobject *uobj) { + enum ib_qp_type qp_type = attr->qp_type; struct ib_qp *qp; + bool is_xrc; if (!dev->ops.create_qp) return ERR_PTR(-EOPNOTSUPP); @@ -320,7 +322,8 @@ static inline struct ib_qp *_ib_create_qp(struct ib_device *dev, * and more importantly they are created internaly by driver, * see mlx5 create_dev_resources() as an example. */ - if (attr->qp_type < IB_QPT_XRC_INI) { + is_xrc = qp_type == IB_QPT_XRC_INI || qp_type == IB_QPT_XRC_TGT; + if ((qp_type < IB_QPT_MAX && !is_xrc) || qp_type == IB_QPT_DRIVER) { qp->res.type = RDMA_RESTRACK_QP; if (uobj) rdma_restrack_uadd(&qp->res); From 770b7d96cfff6a8bf6c9f261ba6f135dc9edf484 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Thu, 1 Aug 2019 15:14:49 +0300 Subject: [PATCH 708/823] IB/mad: Fix use-after-free in ib mad completion handling We encountered a use-after-free bug when unloading the driver: [ 3562.116059] BUG: KASAN: use-after-free in ib_mad_post_receive_mads+0xddc/0xed0 [ib_core] [ 3562.117233] Read of size 4 at addr ffff8882ca5aa868 by task kworker/u13:2/23862 [ 3562.118385] [ 3562.119519] CPU: 2 PID: 23862 Comm: kworker/u13:2 Tainted: G OE 5.1.0-for-upstream-dbg-2019-05-19_16-44-30-13 #1 [ 3562.121806] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu2 04/01/2014 [ 3562.123075] Workqueue: ib-comp-unb-wq ib_cq_poll_work [ib_core] [ 3562.124383] Call Trace: [ 3562.125640] dump_stack+0x9a/0xeb [ 3562.126911] print_address_description+0xe3/0x2e0 [ 3562.128223] ? ib_mad_post_receive_mads+0xddc/0xed0 [ib_core] [ 3562.129545] __kasan_report+0x15c/0x1df [ 3562.130866] ? ib_mad_post_receive_mads+0xddc/0xed0 [ib_core] [ 3562.132174] kasan_report+0xe/0x20 [ 3562.133514] ib_mad_post_receive_mads+0xddc/0xed0 [ib_core] [ 3562.134835] ? find_mad_agent+0xa00/0xa00 [ib_core] [ 3562.136158] ? qlist_free_all+0x51/0xb0 [ 3562.137498] ? mlx4_ib_sqp_comp_worker+0x1970/0x1970 [mlx4_ib] [ 3562.138833] ? quarantine_reduce+0x1fa/0x270 [ 3562.140171] ? kasan_unpoison_shadow+0x30/0x40 [ 3562.141522] ib_mad_recv_done+0xdf6/0x3000 [ib_core] [ 3562.142880] ? _raw_spin_unlock_irqrestore+0x46/0x70 [ 3562.144277] ? ib_mad_send_done+0x1810/0x1810 [ib_core] [ 3562.145649] ? mlx4_ib_destroy_cq+0x2a0/0x2a0 [mlx4_ib] [ 3562.147008] ? _raw_spin_unlock_irqrestore+0x46/0x70 [ 3562.148380] ? debug_object_deactivate+0x2b9/0x4a0 [ 3562.149814] __ib_process_cq+0xe2/0x1d0 [ib_core] [ 3562.151195] ib_cq_poll_work+0x45/0xf0 [ib_core] [ 3562.152577] process_one_work+0x90c/0x1860 [ 3562.153959] ? pwq_dec_nr_in_flight+0x320/0x320 [ 3562.155320] worker_thread+0x87/0xbb0 [ 3562.156687] ? __kthread_parkme+0xb6/0x180 [ 3562.158058] ? process_one_work+0x1860/0x1860 [ 3562.159429] kthread+0x320/0x3e0 [ 3562.161391] ? kthread_park+0x120/0x120 [ 3562.162744] ret_from_fork+0x24/0x30 ... [ 3562.187615] Freed by task 31682: [ 3562.188602] save_stack+0x19/0x80 [ 3562.189586] __kasan_slab_free+0x11d/0x160 [ 3562.190571] kfree+0xf5/0x2f0 [ 3562.191552] ib_mad_port_close+0x200/0x380 [ib_core] [ 3562.192538] ib_mad_remove_device+0xf0/0x230 [ib_core] [ 3562.193538] remove_client_context+0xa6/0xe0 [ib_core] [ 3562.194514] disable_device+0x14e/0x260 [ib_core] [ 3562.195488] __ib_unregister_device+0x79/0x150 [ib_core] [ 3562.196462] ib_unregister_device+0x21/0x30 [ib_core] [ 3562.197439] mlx4_ib_remove+0x162/0x690 [mlx4_ib] [ 3562.198408] mlx4_remove_device+0x204/0x2c0 [mlx4_core] [ 3562.199381] mlx4_unregister_interface+0x49/0x1d0 [mlx4_core] [ 3562.200356] mlx4_ib_cleanup+0xc/0x1d [mlx4_ib] [ 3562.201329] __x64_sys_delete_module+0x2d2/0x400 [ 3562.202288] do_syscall_64+0x95/0x470 [ 3562.203277] entry_SYSCALL_64_after_hwframe+0x49/0xbe The problem was that the MAD PD was deallocated before the MAD CQ. There was completion work pending for the CQ when the PD got deallocated. When the mad completion handling reached procedure ib_mad_post_receive_mads(), we got a use-after-free bug in the following line of code in that procedure: sg_list.lkey = qp_info->port_priv->pd->local_dma_lkey; (the pd pointer in the above line is no longer valid, because the pd has been deallocated). We fix this by allocating the PD before the CQ in procedure ib_mad_port_open(), and deallocating the PD after freeing the CQ in procedure ib_mad_port_close(). Since the CQ completion work queue is flushed during ib_free_cq(), no completions will be pending for that CQ when the PD is later deallocated. Note that freeing the CQ before deallocating the PD is the practice in the ULPs. Fixes: 4be90bc60df4 ("IB/mad: Remove ib_get_dma_mr calls") Signed-off-by: Jack Morgenstein Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/20190801121449.24973-1-leon@kernel.org Signed-off-by: Doug Ledford --- drivers/infiniband/core/mad.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index cc99479b2c09..9947d16edef2 100644 --- a/drivers/infiniband/core/mad.c +++ b/drivers/infiniband/core/mad.c @@ -3224,18 +3224,18 @@ static int ib_mad_port_open(struct ib_device *device, if (has_smi) cq_size *= 2; + port_priv->pd = ib_alloc_pd(device, 0); + if (IS_ERR(port_priv->pd)) { + dev_err(&device->dev, "Couldn't create ib_mad PD\n"); + ret = PTR_ERR(port_priv->pd); + goto error3; + } + port_priv->cq = ib_alloc_cq(port_priv->device, port_priv, cq_size, 0, IB_POLL_UNBOUND_WORKQUEUE); if (IS_ERR(port_priv->cq)) { dev_err(&device->dev, "Couldn't create ib_mad CQ\n"); ret = PTR_ERR(port_priv->cq); - goto error3; - } - - port_priv->pd = ib_alloc_pd(device, 0); - if (IS_ERR(port_priv->pd)) { - dev_err(&device->dev, "Couldn't create ib_mad PD\n"); - ret = PTR_ERR(port_priv->pd); goto error4; } @@ -3278,11 +3278,11 @@ error8: error7: destroy_mad_qp(&port_priv->qp_info[0]); error6: - ib_dealloc_pd(port_priv->pd); -error4: ib_free_cq(port_priv->cq); cleanup_recv_queue(&port_priv->qp_info[1]); cleanup_recv_queue(&port_priv->qp_info[0]); +error4: + ib_dealloc_pd(port_priv->pd); error3: kfree(port_priv); @@ -3312,8 +3312,8 @@ static int ib_mad_port_close(struct ib_device *device, int port_num) destroy_workqueue(port_priv->wq); destroy_mad_qp(&port_priv->qp_info[1]); destroy_mad_qp(&port_priv->qp_info[0]); - ib_dealloc_pd(port_priv->pd); ib_free_cq(port_priv->cq); + ib_dealloc_pd(port_priv->pd); cleanup_recv_queue(&port_priv->qp_info[1]); cleanup_recv_queue(&port_priv->qp_info[0]); /* XXX: Handle deallocation of MAD registration tables */ From 6497d0a9c53df6e98b25e2b79f2295d7caa47b6e Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 31 Jul 2019 12:54:28 -0500 Subject: [PATCH 709/823] IB/hfi1: Fix Spectre v1 vulnerability sl is controlled by user-space, hence leading to a potential exploitation of the Spectre variant 1 vulnerability. Fix this by sanitizing sl before using it to index ibp->sl_to_sc. Notice that given that speculation windows are large, the policy is to kill the speculation on the first load and not worry if it can be completed with a dependent load/store [1]. [1] https://lore.kernel.org/lkml/20180423164740.GY17484@dhcp22.suse.cz/ Cc: stable@vger.kernel.org Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20190731175428.GA16736@embeddedor Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/verbs.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index c4b243f50c76..646f61545ed6 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -54,6 +54,7 @@ #include #include #include +#include #include "hfi.h" #include "common.h" @@ -1536,6 +1537,7 @@ static int hfi1_check_ah(struct ib_device *ibdev, struct rdma_ah_attr *ah_attr) sl = rdma_ah_get_sl(ah_attr); if (sl >= ARRAY_SIZE(ibp->sl_to_sc)) return -EINVAL; + sl = array_index_nospec(sl, ARRAY_SIZE(ibp->sl_to_sc)); sc5 = ibp->sl_to_sc[sl]; if (sc_to_vlt(dd, sc5) > num_vls && sc_to_vlt(dd, sc5) != 0xf) From 23eaf3b5c1a755e3193480c76fb29414be648688 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 31 Jul 2019 11:38:52 +0300 Subject: [PATCH 710/823] RDMA/mlx5: Release locks during notifier unregister The below kernel panic was observed when created bond mode LACP with GRE tunnel on top. The reason to it was not released spinlock during mlx5 notify unregsiter sequence. [ 234.562007] BUG: scheduling while atomic: sh/10900/0x00000002 [ 234.563005] Preemption disabled at: [ 234.566864] ------------[ cut here ]------------ [ 234.567120] DEBUG_LOCKS_WARN_ON(val > preempt_count()) [ 234.567139] WARNING: CPU: 16 PID: 10900 at kernel/sched/core.c:3203 preempt_count_sub+0xca/0x170 [ 234.569550] CPU: 16 PID: 10900 Comm: sh Tainted: G W 5.2.0-rc1-for-linust-dbg-2019-05-25_04-57-33-60 #1 [ 234.569886] Hardware name: Dell Inc. PowerEdge R720/0X3D66, BIOS 2.6.1 02/12/2018 [ 234.570183] RIP: 0010:preempt_count_sub+0xca/0x170 [ 234.570404] Code: 03 38 d0 7c 08 84 d2 0f 85 b0 00 00 00 8b 15 dd 02 03 04 85 d2 75 ba 48 c7 c6 00 e1 88 83 48 c7 c7 40 e1 88 83 e8 76 11 f7 ff <0f> 0b 5b c3 65 8b 05 d3 1f d8 7e 84 c0 75 82 e8 62 c3 c3 00 85 c0 [ 234.570911] RSP: 0018:ffff888b94477b08 EFLAGS: 00010286 [ 234.571133] RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000 [ 234.571391] RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000246 [ 234.571648] RBP: ffff888ba5560000 R08: fffffbfff08962d5 R09: fffffbfff08962d5 [ 234.571902] R10: 0000000000000001 R11: fffffbfff08962d4 R12: ffff888bac6e9548 [ 234.572157] R13: ffff888babfaf728 R14: ffff888bac6e9568 R15: ffff888babfaf750 [ 234.572412] FS: 00007fcafa59b740(0000) GS:ffff888bed200000(0000) knlGS:0000000000000000 [ 234.572686] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 234.572914] CR2: 00007f984f16b140 CR3: 0000000b2bf0a001 CR4: 00000000001606e0 [ 234.573172] Call Trace: [ 234.573336] _raw_spin_unlock+0x2e/0x50 [ 234.573542] mlx5_ib_unbind_slave_port+0x1bc/0x690 [mlx5_ib] [ 234.573793] mlx5_ib_cleanup_multiport_master+0x1d3/0x660 [mlx5_ib] [ 234.574039] mlx5_ib_stage_init_cleanup+0x4c/0x360 [mlx5_ib] [ 234.574271] ? kfree+0xf5/0x2f0 [ 234.574465] __mlx5_ib_remove+0x61/0xd0 [mlx5_ib] [ 234.574688] ? __mlx5_ib_remove+0xd0/0xd0 [mlx5_ib] [ 234.574951] mlx5_remove_device+0x234/0x300 [mlx5_core] [ 234.575224] mlx5_unregister_device+0x4d/0x1e0 [mlx5_core] [ 234.575493] remove_one+0x4f/0x160 [mlx5_core] [ 234.575704] pci_device_remove+0xef/0x2a0 [ 234.581407] ? pcibios_free_irq+0x10/0x10 [ 234.587143] ? up_read+0xc1/0x260 [ 234.592785] device_release_driver_internal+0x1ab/0x430 [ 234.598442] unbind_store+0x152/0x200 [ 234.604064] ? sysfs_kf_write+0x3b/0x180 [ 234.609441] ? sysfs_file_ops+0x160/0x160 [ 234.615021] kernfs_fop_write+0x277/0x440 [ 234.620288] ? __sb_start_write+0x1ef/0x2c0 [ 234.625512] vfs_write+0x15e/0x460 [ 234.630786] ksys_write+0x156/0x1e0 [ 234.635988] ? __ia32_sys_read+0xb0/0xb0 [ 234.641120] ? trace_hardirqs_off_thunk+0x1a/0x1c [ 234.646163] do_syscall_64+0x95/0x470 [ 234.651106] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 234.656004] RIP: 0033:0x7fcaf9c9cfd0 [ 234.660686] Code: 73 01 c3 48 8b 0d c0 6e 2d 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d cd cf 2d 00 00 75 10 b8 01 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 ee cb 01 00 48 89 04 24 [ 234.670128] RSP: 002b:00007ffd3b01ddd8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 234.674811] RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007fcaf9c9cfd0 [ 234.679387] RDX: 000000000000000d RSI: 00007fcafa5c1000 RDI: 0000000000000001 [ 234.683848] RBP: 00007fcafa5c1000 R08: 000000000000000a R09: 00007fcafa59b740 [ 234.688167] R10: 00007ffd3b01d8e0 R11: 0000000000000246 R12: 00007fcaf9f75400 [ 234.692386] R13: 000000000000000d R14: 0000000000000001 R15: 0000000000000000 [ 234.696495] irq event stamp: 153067 [ 234.700525] hardirqs last enabled at (153067): [] _raw_spin_unlock_irqrestore+0x59/0x70 [ 234.704665] hardirqs last disabled at (153066): [] _raw_spin_lock_irqsave+0x22/0x90 [ 234.708722] softirqs last enabled at (153058): [] __do_softirq+0x6c5/0xb4e [ 234.712673] softirqs last disabled at (153051): [] irq_exit+0x17d/0x1d0 [ 234.716601] ---[ end trace 5dbf096843ee9ce6 ]--- Fixes: df097a278c75 ("IB/mlx5: Use the new mlx5 core notifier API") Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/20190731083852.584-1-leon@kernel.org Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index c2a5780cb394..e12a4404096b 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -5802,13 +5802,12 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev, return; } - if (mpi->mdev_events.notifier_call) - mlx5_notifier_unregister(mpi->mdev, &mpi->mdev_events); - mpi->mdev_events.notifier_call = NULL; - mpi->ibdev = NULL; spin_unlock(&port->mp.mpi_lock); + if (mpi->mdev_events.notifier_call) + mlx5_notifier_unregister(mpi->mdev, &mpi->mdev_events); + mpi->mdev_events.notifier_call = NULL; mlx5_remove_netdev_notifier(ibdev, port_num); spin_lock(&port->mp.mpi_lock); From 1f66072503316134873060b24b7895dbbcccf00e Mon Sep 17 00:00:00 2001 From: Mauro Rossi Date: Thu, 1 Aug 2019 09:04:34 +0200 Subject: [PATCH 711/823] iwlwifi: dbg_ini: fix compile time assert build errors This patch fixes and preserves existing code style, and readability, for IWL_ERR() and IWL_WARN() macros invocations recently added in dbg.c Fixes the following build errors with Android build system: /home/utente/pie-x86_kernel/kernel/drivers/net/wireless/intel/iwlwifi/fw/dbg.c: In function '_iwl_fw_dbg_apply_point': /home/utente/pie-x86_kernel/kernel/drivers/net/wireless/intel/iwlwifi/fw/dbg.c:2445:3: error: call to '__compiletime_assert_2446' declared with attribute error: BUILD_BUG_ON failed: err_str[sizeof(err_str) - 2] != '\n' /home/utente/pie-x86_kernel/kernel/drivers/net/wireless/intel/iwlwifi/fw/dbg.c:2451:3: error: call to '__compiletime_assert_2452' declared with attribute error: BUILD_BUG_ON failed: err_str[sizeof(err_str) - 2] != '\n' ... /home/utente/pie-x86_kernel/kernel/drivers/net/wireless/intel/iwlwifi/fw/dbg.c:2789:5: error: call to '__compiletime_assert_2790' declared with attribute error: BUILD_BUG_ON failed: invalid_ap_str[sizeof(invalid_ap_str) - 2] != '\n' /home/utente/pie-x86_kernel/kernel/drivers/net/wireless/intel/iwlwifi/fw/dbg.c:2800:5: error: call to '__compiletime_assert_2801' declared with attribute error: BUILD_BUG_ON failed: invalid_ap_str[sizeof(invalid_ap_str) - 2] != '\n' Fixes: 427ab6385cf3 ("iwlwifi: dbg_ini: enforce apply point early on buffer allocation tlv") Fixes: 57d88b116175 ("iwlwifi: dbg_ini: support debug info TLV") Signed-off-by: Mauro Rossi Signed-off-by: Johannes Berg Reviewed-by: Nathan Chancellor Tested-by: Nathan Chancellor Signed-off-by: Kalle Valo --- drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 22 +++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c index e411ac98290d..4d81776f576d 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c @@ -2438,17 +2438,19 @@ static void iwl_fw_dbg_info_apply(struct iwl_fw_runtime *fwrt, { u32 img_name_len = le32_to_cpu(dbg_info->img_name_len); u32 dbg_cfg_name_len = le32_to_cpu(dbg_info->dbg_cfg_name_len); - const char err_str[] = - "WRT: ext=%d. Invalid %s name length %d, expected %d\n"; if (img_name_len != IWL_FW_INI_MAX_IMG_NAME_LEN) { - IWL_WARN(fwrt, err_str, ext, "image", img_name_len, + IWL_WARN(fwrt, + "WRT: ext=%d. Invalid image name length %d, expected %d\n", + ext, img_name_len, IWL_FW_INI_MAX_IMG_NAME_LEN); return; } if (dbg_cfg_name_len != IWL_FW_INI_MAX_DBG_CFG_NAME_LEN) { - IWL_WARN(fwrt, err_str, ext, "debug cfg", dbg_cfg_name_len, + IWL_WARN(fwrt, + "WRT: ext=%d. Invalid debug cfg name length %d, expected %d\n", + ext, dbg_cfg_name_len, IWL_FW_INI_MAX_DBG_CFG_NAME_LEN); return; } @@ -2775,8 +2777,6 @@ static void _iwl_fw_dbg_apply_point(struct iwl_fw_runtime *fwrt, struct iwl_ucode_tlv *tlv = iter; void *ini_tlv = (void *)tlv->data; u32 type = le32_to_cpu(tlv->type); - const char invalid_ap_str[] = - "WRT: ext=%d. Invalid apply point %d for %s\n"; switch (type) { case IWL_UCODE_TLV_TYPE_DEBUG_INFO: @@ -2786,8 +2786,9 @@ static void _iwl_fw_dbg_apply_point(struct iwl_fw_runtime *fwrt, struct iwl_fw_ini_allocation_data *buf_alloc = ini_tlv; if (pnt != IWL_FW_INI_APPLY_EARLY) { - IWL_ERR(fwrt, invalid_ap_str, ext, pnt, - "buffer allocation"); + IWL_ERR(fwrt, + "WRT: ext=%d. Invalid apply point %d for buffer allocation\n", + ext, pnt); goto next; } @@ -2797,8 +2798,9 @@ static void _iwl_fw_dbg_apply_point(struct iwl_fw_runtime *fwrt, } case IWL_UCODE_TLV_TYPE_HCMD: if (pnt < IWL_FW_INI_APPLY_AFTER_ALIVE) { - IWL_ERR(fwrt, invalid_ap_str, ext, pnt, - "host command"); + IWL_ERR(fwrt, + "WRT: ext=%d. Invalid apply point %d for host command\n", + ext, pnt); goto next; } iwl_fw_dbg_send_hcmd(fwrt, tlv, ext); From 9ca7ad6c7706edeae331c1632d0c63897418ebad Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Wed, 26 Jun 2019 11:00:15 -0700 Subject: [PATCH 712/823] drm: msm: Fix add_gpu_components add_gpu_components() adds found GPU nodes from the DT to the match list, regardless of the status of the nodes. This is a problem, because if the nodes are disabled, they should not be on the match list because they will not be matched. This prevents display from initing if a GPU node is defined, but it's status is disabled. Fix this by checking the node's status before adding it to the match list. Fixes: dc3ea265b856 (drm/msm: Drop the gpu binding) Reviewed-by: Rob Clark Signed-off-by: Jeffrey Hugo Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20190626180015.45242-1-jeffrey.l.hugo@gmail.com --- drivers/gpu/drm/msm/msm_drv.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index c226156f2dea..c356f5ccf253 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -1279,7 +1279,8 @@ static int add_gpu_components(struct device *dev, if (!np) return 0; - drm_of_component_match_add(dev, matchptr, compare_of, np); + if (of_device_is_available(np)) + drm_of_component_match_add(dev, matchptr, compare_of, np); of_node_put(np); From 020fb3bebc224dfe9353a56ecbe2d5fac499dffc Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Thu, 1 Aug 2019 01:27:25 +0000 Subject: [PATCH 713/823] RDMA/hns: Fix error return code in hns_roce_v1_rsv_lp_qp() Fix to return error code -ENOMEM from the rdma_zalloc_drv_obj() error handling case instead of 0, as done elsewhere in this function. Fixes: e8ac9389f0d7 ("RDMA: Fix allocation failure on pointer pd") Fixes: 21a428a019c9 ("RDMA: Handle PD allocations by IB/core") Signed-off-by: Wei Yongjun Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20190801012725.150493-1-weiyongjun1@huawei.com Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hns/hns_roce_hw_v1.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index 81e6dedb1e02..c07e387a07a3 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -750,8 +750,10 @@ static int hns_roce_v1_rsv_lp_qp(struct hns_roce_dev *hr_dev) atomic_set(&free_mr->mr_free_cq->ib_cq.usecnt, 0); pd = rdma_zalloc_drv_obj(ibdev, ib_pd); - if (!pd) + if (!pd) { + ret = -ENOMEM; goto alloc_mem_failed; + } pd->device = ibdev; ret = hns_roce_alloc_pd(pd, NULL); From 944a83a2669ae8aa2c7664e79376ca7468eb0a2b Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Thu, 1 Aug 2019 14:13:30 +0200 Subject: [PATCH 714/823] mvpp2: fix panic on module removal mvpp2 uses a delayed workqueue to gather traffic statistics. On module removal the workqueue can be destroyed before calling cancel_delayed_work_sync() on its works. Fix it by moving the destroy_workqueue() call after mvpp2_port_remove(). Also remove an unneeded call to flush_workqueue() # rmmod mvpp2 [ 2743.311722] mvpp2 f4000000.ethernet eth1: phy link down 10gbase-kr/10Gbps/Full [ 2743.320063] mvpp2 f4000000.ethernet eth1: Link is Down [ 2743.572263] mvpp2 f4000000.ethernet eth2: phy link down sgmii/1Gbps/Full [ 2743.580076] mvpp2 f4000000.ethernet eth2: Link is Down [ 2744.102169] mvpp2 f2000000.ethernet eth0: phy link down 10gbase-kr/10Gbps/Full [ 2744.110441] mvpp2 f2000000.ethernet eth0: Link is Down [ 2744.115614] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 2744.115615] Mem abort info: [ 2744.115616] ESR = 0x96000005 [ 2744.115617] Exception class = DABT (current EL), IL = 32 bits [ 2744.115618] SET = 0, FnV = 0 [ 2744.115619] EA = 0, S1PTW = 0 [ 2744.115620] Data abort info: [ 2744.115621] ISV = 0, ISS = 0x00000005 [ 2744.115622] CM = 0, WnR = 0 [ 2744.115624] user pgtable: 4k pages, 39-bit VAs, pgdp=0000000422681000 [ 2744.115626] [0000000000000000] pgd=0000000000000000, pud=0000000000000000 [ 2744.115630] Internal error: Oops: 96000005 [#1] SMP [ 2744.115632] Modules linked in: mvpp2(-) algif_hash af_alg nls_iso8859_1 nls_cp437 vfat fat xhci_plat_hcd m25p80 spi_nor xhci_hcd mtd usbcore i2c_mv64xxx sfp usb_common marvell10g phy_generic spi_orion mdio_i2c i2c_core mvmdio phylink sbsa_gwdt ip_tables x_tables autofs4 [last unloaded: mvpp2] [ 2744.115654] CPU: 3 PID: 8357 Comm: kworker/3:2 Not tainted 5.3.0-rc2 #1 [ 2744.115655] Hardware name: Marvell 8040 MACCHIATOBin Double-shot (DT) [ 2744.115665] Workqueue: events_power_efficient phylink_resolve [phylink] [ 2744.115669] pstate: a0000085 (NzCv daIf -PAN -UAO) [ 2744.115675] pc : __queue_work+0x9c/0x4d8 [ 2744.115677] lr : __queue_work+0x170/0x4d8 [ 2744.115678] sp : ffffff801001bd50 [ 2744.115680] x29: ffffff801001bd50 x28: ffffffc422597600 [ 2744.115684] x27: ffffff80109ae6f0 x26: ffffff80108e4018 [ 2744.115688] x25: 0000000000000003 x24: 0000000000000004 [ 2744.115691] x23: ffffff80109ae6e0 x22: 0000000000000017 [ 2744.115694] x21: ffffffc42c030000 x20: ffffffc42209e8f8 [ 2744.115697] x19: 0000000000000000 x18: 0000000000000000 [ 2744.115699] x17: 0000000000000000 x16: 0000000000000000 [ 2744.115701] x15: 0000000000000010 x14: ffffffffffffffff [ 2744.115702] x13: ffffff8090e2b95f x12: ffffff8010e2b967 [ 2744.115704] x11: ffffff8010906000 x10: 0000000000000040 [ 2744.115706] x9 : ffffff80109223b8 x8 : ffffff80109223b0 [ 2744.115707] x7 : ffffffc42bc00068 x6 : 0000000000000000 [ 2744.115709] x5 : ffffffc42bc00000 x4 : 0000000000000000 [ 2744.115710] x3 : 0000000000000000 x2 : 0000000000000000 [ 2744.115712] x1 : 0000000000000008 x0 : ffffffc42c030000 [ 2744.115714] Call trace: [ 2744.115716] __queue_work+0x9c/0x4d8 [ 2744.115718] delayed_work_timer_fn+0x28/0x38 [ 2744.115722] call_timer_fn+0x3c/0x180 [ 2744.115723] expire_timers+0x60/0x168 [ 2744.115724] run_timer_softirq+0xbc/0x1e8 [ 2744.115727] __do_softirq+0x128/0x320 [ 2744.115731] irq_exit+0xa4/0xc0 [ 2744.115734] __handle_domain_irq+0x70/0xc0 [ 2744.115735] gic_handle_irq+0x58/0xa8 [ 2744.115737] el1_irq+0xb8/0x140 [ 2744.115738] console_unlock+0x3a0/0x568 [ 2744.115740] vprintk_emit+0x200/0x2a0 [ 2744.115744] dev_vprintk_emit+0x1c8/0x1e4 [ 2744.115747] dev_printk_emit+0x6c/0x7c [ 2744.115751] __netdev_printk+0x104/0x1d8 [ 2744.115752] netdev_printk+0x60/0x70 [ 2744.115756] phylink_resolve+0x38c/0x3c8 [phylink] [ 2744.115758] process_one_work+0x1f8/0x448 [ 2744.115760] worker_thread+0x54/0x500 [ 2744.115762] kthread+0x12c/0x130 [ 2744.115764] ret_from_fork+0x10/0x1c [ 2744.115768] Code: aa1403e0 97fffbbe aa0003f5 b4000700 (f9400261) Fixes: 118d6298f6f0 ("net: mvpp2: add ethtool GOP statistics") Signed-off-by: Lorenzo Bianconi Signed-off-by: Matteo Croce Acked-by: Antoine Tenart Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index e2e61a4a9000..ccdd47f3b8fb 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5753,9 +5753,6 @@ static int mvpp2_remove(struct platform_device *pdev) mvpp2_dbgfs_cleanup(priv); - flush_workqueue(priv->stats_queue); - destroy_workqueue(priv->stats_queue); - fwnode_for_each_available_child_node(fwnode, port_fwnode) { if (priv->port_list[i]) { mutex_destroy(&priv->port_list[i]->gather_stats_lock); @@ -5764,6 +5761,8 @@ static int mvpp2_remove(struct platform_device *pdev) i++; } + destroy_workqueue(priv->stats_queue); + for (i = 0; i < MVPP2_BM_POOLS_NUM; i++) { struct mvpp2_bm_pool *bm_pool = &priv->bm_pools[i]; From fc5b34a35458314df1dd00281f6e41f419581aa9 Mon Sep 17 00:00:00 2001 From: Micah Morton Date: Thu, 1 Aug 2019 10:28:27 -0700 Subject: [PATCH 715/823] Add entry in MAINTAINERS file for SafeSetID LSM This LSM was added in v5.1 and needs an entry in the MAINTAINERS file. Signed-off-by: Micah Morton Acked-by: James Morris --- MAINTAINERS | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 6426db5198f0..30b8a83c3afa 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14016,6 +14016,12 @@ F: drivers/media/common/saa7146/ F: drivers/media/pci/saa7146/ F: include/media/drv-intf/saa7146* +SAFESETID SECURITY MODULE +M: Micah Morton +S: Supported +F: security/safesetid/ +F: Documentation/admin-guide/LSM/SafeSetID.rst + SAMSUNG AUDIO (ASoC) DRIVERS M: Krzysztof Kozlowski M: Sangbeom Kim From 14f1c0f2ff156c89b14fa4c52605e7586436ffb8 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 31 Jul 2019 15:22:09 +0200 Subject: [PATCH 716/823] net: 8390: Fix manufacturer name in Kconfig help text The help text refers to Western Digital instead of National Semiconductor 8390, presumably because it was copied from the former. Fixes: 644570b830266ff3 ("8390: Move the 8390 related drivers") Signed-off-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- drivers/net/ethernet/8390/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/8390/Kconfig b/drivers/net/ethernet/8390/Kconfig index 2a3e2450968e..a9478577b495 100644 --- a/drivers/net/ethernet/8390/Kconfig +++ b/drivers/net/ethernet/8390/Kconfig @@ -12,8 +12,8 @@ config NET_VENDOR_8390 Note that the answer to this question doesn't directly affect the kernel: saying N will just cause the configurator to skip all - the questions about Western Digital cards. If you say Y, you will be - asked for your specific card in the following questions. + the questions about National Semiconductor 8390 cards. If you say Y, + you will be asked for your specific card in the following questions. if NET_VENDOR_8390 From 93ae6d2d2e0eef6973d634dd6e1a19ba1b031c30 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 31 Jul 2019 15:22:10 +0200 Subject: [PATCH 717/823] net: amd: Spelling s/case/cause/ Signed-off-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig index de4950d2022e..9f965cdfff5c 100644 --- a/drivers/net/ethernet/amd/Kconfig +++ b/drivers/net/ethernet/amd/Kconfig @@ -14,7 +14,7 @@ config NET_VENDOR_AMD say Y. Note that the answer to this question does not directly affect - the kernel: saying N will just case the configurator to skip all + the kernel: saying N will just cause the configurator to skip all the questions regarding AMD chipsets. If you say Y, you will be asked for your specific chipset/driver in the following questions. From ac0e3f20c7a9fbace30d38e7d306ab15f3e6fd31 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 31 Jul 2019 15:22:11 +0200 Subject: [PATCH 718/823] net: apple: Fix manufacturer name in Kconfig help text The help text refers to IBM instead of Apple, presumably because it was copied from the former. Fixes: 8fb6b0908176704a ("bmac/mace/macmace/mac89x0/cs89x0: Move the Macintosh (Apple) drivers") Signed-off-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- drivers/net/ethernet/apple/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/apple/Kconfig b/drivers/net/ethernet/apple/Kconfig index fde7ae33e302..f78b9c841296 100644 --- a/drivers/net/ethernet/apple/Kconfig +++ b/drivers/net/ethernet/apple/Kconfig @@ -11,8 +11,8 @@ config NET_VENDOR_APPLE If you have a network (Ethernet) card belonging to this class, say Y. Note that the answer to this question doesn't directly affect the - kernel: saying N will just cause the configurator to skip all - the questions about IBM devices. If you say Y, you will be asked for + kernel: saying N will just cause the configurator to skip all the + questions about Apple devices. If you say Y, you will be asked for your specific card in the following questions. if NET_VENDOR_APPLE From aca3432a607b6f9db2a9fe34f4b87d01cd99a68a Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 31 Jul 2019 15:22:12 +0200 Subject: [PATCH 719/823] net: broadcom: Fix manufacturer name in Kconfig help text The help text refers to AMD instead of Broadcom, presumably because it was copied from the former. Fixes: adfc5217e9db68d3 ("broadcom: Move the Broadcom drivers") Signed-off-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/Kconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index e9017caf024d..e24f5d2b6afe 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -14,9 +14,9 @@ config NET_VENDOR_BROADCOM say Y. Note that the answer to this question does not directly affect - the kernel: saying N will just case the configurator to skip all - the questions regarding AMD chipsets. If you say Y, you will be asked - for your specific chipset/driver in the following questions. + the kernel: saying N will just cause the configurator to skip all + the questions regarding Broadcom chipsets. If you say Y, you will + be asked for your specific chipset/driver in the following questions. if NET_VENDOR_BROADCOM From cec754cc7813f300d286b1d7e14480f82f7f2ffa Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 31 Jul 2019 15:22:13 +0200 Subject: [PATCH 720/823] net: ixp4xx: Spelling s/XSacle/XScale/ Signed-off-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- drivers/net/ethernet/xscale/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/xscale/Kconfig b/drivers/net/ethernet/xscale/Kconfig index 2f354ba029a6..cd0a8f46e7c6 100644 --- a/drivers/net/ethernet/xscale/Kconfig +++ b/drivers/net/ethernet/xscale/Kconfig @@ -13,7 +13,7 @@ config NET_VENDOR_XSCALE Note that the answer to this question does not directly affect the kernel: saying N will just cause the configurator to skip all - the questions about XSacle IXP devices. If you say Y, you will be + the questions about XScale IXP devices. If you say Y, you will be asked for your specific card in the following questions. if NET_VENDOR_XSCALE From 85aee0a793ba223c48fd2cfe534edf83729deef6 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 31 Jul 2019 15:22:14 +0200 Subject: [PATCH 721/823] net: nixge: Spelling s/Instrument/Instruments/ Signed-off-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- drivers/net/ethernet/ni/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ni/Kconfig b/drivers/net/ethernet/ni/Kconfig index 70b1a03c0953..01229190132d 100644 --- a/drivers/net/ethernet/ni/Kconfig +++ b/drivers/net/ethernet/ni/Kconfig @@ -11,7 +11,7 @@ config NET_VENDOR_NI Note that the answer to this question doesn't directly affect the kernel: saying N will just cause the configurator to skip all - the questions about National Instrument devices. + the questions about National Instruments devices. If you say Y, you will be asked for your specific device in the following questions. From 1583d448ea84a5b8b98c8d250200ce768b6ced38 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 31 Jul 2019 15:22:15 +0200 Subject: [PATCH 722/823] net: packetengines: Fix manufacturer spelling and capitalization Use "Packet Engines" consistently. Signed-off-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- drivers/net/ethernet/packetengines/Kconfig | 6 +++--- drivers/net/ethernet/packetengines/Makefile | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/packetengines/Kconfig b/drivers/net/ethernet/packetengines/Kconfig index 8161e308e64b..ead3750b4489 100644 --- a/drivers/net/ethernet/packetengines/Kconfig +++ b/drivers/net/ethernet/packetengines/Kconfig @@ -1,10 +1,10 @@ # SPDX-License-Identifier: GPL-2.0-only # -# Packet engine device configuration +# Packet Engines device configuration # config NET_VENDOR_PACKET_ENGINES - bool "Packet Engine devices" + bool "Packet Engines devices" default y depends on PCI ---help--- @@ -12,7 +12,7 @@ config NET_VENDOR_PACKET_ENGINES Note that the answer to this question doesn't directly affect the kernel: saying N will just cause the configurator to skip all - the questions about packet engine devices. If you say Y, you will + the questions about Packet Engines devices. If you say Y, you will be asked for your specific card in the following questions. if NET_VENDOR_PACKET_ENGINES diff --git a/drivers/net/ethernet/packetengines/Makefile b/drivers/net/ethernet/packetengines/Makefile index 1553c9cfc254..cf054b796d11 100644 --- a/drivers/net/ethernet/packetengines/Makefile +++ b/drivers/net/ethernet/packetengines/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only # -# Makefile for the Packet Engine network device drivers. +# Makefile for the Packet Engines network device drivers. # obj-$(CONFIG_HAMACHI) += hamachi.o From 509b0538bc28870164903f5683e4c3f3b1eca965 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 31 Jul 2019 15:22:16 +0200 Subject: [PATCH 723/823] net: samsung: Spelling s/case/cause/ Signed-off-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- drivers/net/ethernet/samsung/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/samsung/Kconfig b/drivers/net/ethernet/samsung/Kconfig index 027938017579..e92a178a76df 100644 --- a/drivers/net/ethernet/samsung/Kconfig +++ b/drivers/net/ethernet/samsung/Kconfig @@ -11,7 +11,7 @@ config NET_VENDOR_SAMSUNG say Y. Note that the answer to this question does not directly affect - the kernel: saying N will just case the configurator to skip all + the kernel: saying N will just cause the configurator to skip all the questions about Samsung chipsets. If you say Y, you will be asked for your specific chipset/driver in the following questions. From 0eb6ddfb865c7d7ec05cb330050671363515e67f Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 1 Aug 2019 19:21:51 +0900 Subject: [PATCH 724/823] block: Fix __blkdev_direct_IO() for bio fragments The recent fix to properly handle IOCB_NOWAIT for async O_DIRECT IO (patch 6a43074e2f46) introduced two problems with BIO fragment handling for direct IOs: 1) The dio size processed is calculated by incrementing the ret variable by the size of the bio fragment issued for the dio. However, this size is obtained directly from bio->bi_iter.bi_size AFTER the bio submission which may result in referencing the bi_size value after the bio completed, resulting in an incorrect value use. 2) The ret variable is not incremented by the size of the last bio fragment issued for the bio, leading to an invalid IO size being returned to the user. Fix both problem by using dio->size (which is incremented before the bio submission) to update the value of ret after bio submissions, including for the last bio fragment issued. Fixes: 6a43074e2f46 ("block: properly handle IOCB_NOWAIT for async O_DIRECT IO") Reported-by: Masato Suzuki Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- fs/block_dev.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index 22591bad9353..a6f7c892cb4a 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -439,6 +439,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) ret = -EAGAIN; goto error; } + ret = dio->size; if (polled) WRITE_ONCE(iocb->ki_cookie, qc); @@ -465,7 +466,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) ret = -EAGAIN; goto error; } - ret += bio->bi_iter.bi_size; + ret = dio->size; bio = bio_alloc(gfp, nr_pages); if (!bio) { From d12e3aae160fb26b534c4496b211d6e60a5179ed Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Mon, 22 Jul 2019 20:55:27 +0200 Subject: [PATCH 725/823] i2c: at91: disable TXRDY interrupt after sending data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Driver was not disabling TXRDY interrupt after last TX byte. This caused interrupt storm until transfer timeouts for slow or broken device on the bus. The patch fixes the interrupt storm on my SAMA5D2-based board. Cc: stable@vger.kernel.org # 5.2.x [v5.2 introduced file split; the patch should apply to i2c-at91.c before the split] Fixes: fac368a04048 ("i2c: at91: add new driver") Signed-off-by: Michał Mirosław Acked-by: Ludovic Desroches Tested-by: Raag Jadav Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-at91-master.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/i2c/busses/i2c-at91-master.c b/drivers/i2c/busses/i2c-at91-master.c index e87232f2e708..a3fcc35ffd3b 100644 --- a/drivers/i2c/busses/i2c-at91-master.c +++ b/drivers/i2c/busses/i2c-at91-master.c @@ -122,9 +122,11 @@ static void at91_twi_write_next_byte(struct at91_twi_dev *dev) writeb_relaxed(*dev->buf, dev->base + AT91_TWI_THR); /* send stop when last byte has been written */ - if (--dev->buf_len == 0) + if (--dev->buf_len == 0) { if (!dev->use_alt_cmd) at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP); + at91_twi_write(dev, AT91_TWI_IDR, AT91_TWI_TXRDY); + } dev_dbg(dev->dev, "wrote 0x%x, to go %zu\n", *dev->buf, dev->buf_len); @@ -542,9 +544,8 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev) } else { at91_twi_write_next_byte(dev); at91_twi_write(dev, AT91_TWI_IER, - AT91_TWI_TXCOMP | - AT91_TWI_NACK | - AT91_TWI_TXRDY); + AT91_TWI_TXCOMP | AT91_TWI_NACK | + (dev->buf_len ? AT91_TWI_TXRDY : 0)); } } From b1ac6704493fa14b5dc19eb6b69a73932361a131 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Mon, 22 Jul 2019 21:05:56 +0200 Subject: [PATCH 726/823] i2c: at91: fix clk_offset for sama5d2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In SAMA5D2 datasheet, TWIHS_CWGR register rescription mentions clock offset of 3 cycles (compared to 4 in eg. SAMA5D3). Cc: stable@vger.kernel.org # 5.2.x [needs applying to i2c-at91.c instead for earlier kernels] Fixes: 0ef6f3213dac ("i2c: at91: add support for new alternative command mode") Signed-off-by: Michał Mirosław Acked-by: Ludovic Desroches Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-at91-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-at91-core.c b/drivers/i2c/busses/i2c-at91-core.c index 8d55cdd69ff4..435c7d7377a3 100644 --- a/drivers/i2c/busses/i2c-at91-core.c +++ b/drivers/i2c/busses/i2c-at91-core.c @@ -142,7 +142,7 @@ static struct at91_twi_pdata sama5d4_config = { static struct at91_twi_pdata sama5d2_config = { .clk_max_div = 7, - .clk_offset = 4, + .clk_offset = 3, .has_unre_flag = true, .has_alt_cmd = true, .has_hold_field = true, From 8eb9a2dff019055e4ff307bb7f8c64a7a20e79c8 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Sun, 28 Jul 2019 18:51:38 -0500 Subject: [PATCH 727/823] i2c: s3c2410: Mark expected switch fall-through Mark switch cases where we are expecting to fall through. This patch fixes the following warning: drivers/i2c/busses/i2c-s3c2410.c: In function 'i2c_s3c_irq_nextbyte': drivers/i2c/busses/i2c-s3c2410.c:431:6: warning: this statement may fall through [-Wimplicit-fallthrough=] if (i2c->state == STATE_READ) ^ drivers/i2c/busses/i2c-s3c2410.c:439:2: note: here case STATE_WRITE: ^~~~ Notice that, in this particular case, the code comment is modified in accordance with what GCC is expecting to find. Reported-by: Stephen Rothwell Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-s3c2410.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index d97fb857b0ea..c98ef4c4a0c9 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -435,6 +435,7 @@ static int i2c_s3c_irq_nextbyte(struct s3c24xx_i2c *i2c, unsigned long iicstat) * fall through to the write state, as we will need to * send a byte as well */ + /* Fall through */ case STATE_WRITE: /* From 42787ed79638dc7f0f8d5c164caba1e87bfab50f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 1 Aug 2019 01:31:08 +0200 Subject: [PATCH 728/823] ACPI: PM: Fix regression in acpi_device_set_power() Commit f850a48a0799 ("ACPI: PM: Allow transitions to D0 to occur in special cases") overlooked the fact that acpi_power_transition() may change the power.state value for the target device and if that happens, it may confuse acpi_device_set_power() and cause it to omit the _PS0 evaluation which on some systems is necessary to change power states of devices from low-power to D0. Fix that by saving the current value of power.state for the target device before passing it to acpi_power_transition() and using the saved value in a subsequent check. Fixes: f850a48a0799 ("ACPI: PM: Allow transitions to D0 to occur in special cases") Reported-by: Kai-Heng Feng Reported-by: Mario Limonciello Signed-off-by: Rafael J. Wysocki Tested-by: Kai-Heng Feng Tested-by: Mario Limonciello --- drivers/acpi/device_pm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index 28cffaaf9d82..f616b16c1f0b 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -232,13 +232,15 @@ int acpi_device_set_power(struct acpi_device *device, int state) if (device->power.flags.power_resources) result = acpi_power_transition(device, target_state); } else { + int cur_state = device->power.state; + if (device->power.flags.power_resources) { result = acpi_power_transition(device, ACPI_STATE_D0); if (result) goto end; } - if (device->power.state == ACPI_STATE_D0) { + if (cur_state == ACPI_STATE_D0) { int psc; /* Nothing to do here if _PSC is not present. */ From 4da5f0018eef4c0de31675b670c80e82e13e99d1 Mon Sep 17 00:00:00 2001 From: Taras Kondratiuk Date: Mon, 29 Jul 2019 22:15:07 +0000 Subject: [PATCH 729/823] tipc: compat: allow tipc commands without arguments Commit 2753ca5d9009 ("tipc: fix uninit-value in tipc_nl_compat_doit") broke older tipc tools that use compat interface (e.g. tipc-config from tipcutils package): % tipc-config -p operation not supported The commit started to reject TIPC netlink compat messages that do not have attributes. It is too restrictive because some of such messages are valid (they don't need any arguments): % grep 'tx none' include/uapi/linux/tipc_config.h #define TIPC_CMD_NOOP 0x0000 /* tx none, rx none */ #define TIPC_CMD_GET_MEDIA_NAMES 0x0002 /* tx none, rx media_name(s) */ #define TIPC_CMD_GET_BEARER_NAMES 0x0003 /* tx none, rx bearer_name(s) */ #define TIPC_CMD_SHOW_PORTS 0x0006 /* tx none, rx ultra_string */ #define TIPC_CMD_GET_REMOTE_MNG 0x4003 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_PORTS 0x4004 /* tx none, rx unsigned */ #define TIPC_CMD_GET_NETID 0x400B /* tx none, rx unsigned */ #define TIPC_CMD_NOT_NET_ADMIN 0xC001 /* tx none, rx none */ This patch relaxes the original fix and rejects messages without arguments only if such arguments are expected by a command (reg_type is non zero). Fixes: 2753ca5d9009 ("tipc: fix uninit-value in tipc_nl_compat_doit") Cc: stable@vger.kernel.org Signed-off-by: Taras Kondratiuk Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/netlink_compat.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index d86030ef1232..e135d4e11231 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -55,6 +55,7 @@ struct tipc_nl_compat_msg { int rep_type; int rep_size; int req_type; + int req_size; struct net *net; struct sk_buff *rep; struct tlv_desc *req; @@ -257,7 +258,8 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, int err; struct sk_buff *arg; - if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type)) + if (msg->req_type && (!msg->req_size || + !TLV_CHECK_TYPE(msg->req, msg->req_type))) return -EINVAL; msg->rep = tipc_tlv_alloc(msg->rep_size); @@ -354,7 +356,8 @@ static int tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd, { int err; - if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type)) + if (msg->req_type && (!msg->req_size || + !TLV_CHECK_TYPE(msg->req, msg->req_type))) return -EINVAL; err = __tipc_nl_compat_doit(cmd, msg); @@ -1278,8 +1281,8 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info) goto send; } - len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN); - if (!len || !TLV_OK(msg.req, len)) { + msg.req_size = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN); + if (msg.req_size && !TLV_OK(msg.req, msg.req_size)) { msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED); err = -EOPNOTSUPP; goto send; From 224c04973db1125fcebefffd86115f99f50f8277 Mon Sep 17 00:00:00 2001 From: Denis Kirjanov Date: Tue, 30 Jul 2019 15:13:57 +0200 Subject: [PATCH 730/823] net: usb: pegasus: fix improper read if get_registers() fail get_registers() may fail with -ENOMEM and in this case we can read a garbage from the status variable tmp. Reported-by: syzbot+3499a83b2d062ae409d4@syzkaller.appspotmail.com Signed-off-by: Denis Kirjanov Signed-off-by: David S. Miller --- drivers/net/usb/pegasus.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 6d25dea5ad4b..f7d117d80cfb 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -282,7 +282,7 @@ static void mdio_write(struct net_device *dev, int phy_id, int loc, int val) static int read_eprom_word(pegasus_t *pegasus, __u8 index, __u16 *retdata) { int i; - __u8 tmp; + __u8 tmp = 0; __le16 retdatai; int ret; From 412e85b605315fd129a849599cf4a5a7959573a8 Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Thu, 1 Aug 2019 18:02:15 -0400 Subject: [PATCH 731/823] drm/nouveau: Only release VCPI slots on mode changes Looks like a regression got introduced into nv50_mstc_atomic_check() that somehow didn't get found until now. If userspace changes crtc_state->active to false but leaves the CRTC enabled, we end up calling drm_dp_atomic_find_vcpi_slots() using the PBN calculated in asyh->dp.pbn. However, if the display is inactive we end up calculating a PBN of 0, which inadvertently causes us to have an allocation of 0. >From there, if userspace then disables the CRTC afterwards we end up accidentally attempting to free the VCPI twice: WARNING: CPU: 0 PID: 1484 at drivers/gpu/drm/drm_dp_mst_topology.c:3336 drm_dp_atomic_release_vcpi_slots+0x87/0xb0 [drm_kms_helper] RIP: 0010:drm_dp_atomic_release_vcpi_slots+0x87/0xb0 [drm_kms_helper] Call Trace: drm_atomic_helper_check_modeset+0x3f3/0xa60 [drm_kms_helper] ? drm_atomic_check_only+0x43/0x780 [drm] drm_atomic_helper_check+0x15/0x90 [drm_kms_helper] nv50_disp_atomic_check+0x83/0x1d0 [nouveau] drm_atomic_check_only+0x54d/0x780 [drm] ? drm_atomic_set_crtc_for_connector+0xec/0x100 [drm] drm_atomic_commit+0x13/0x50 [drm] drm_atomic_helper_set_config+0x81/0x90 [drm_kms_helper] drm_mode_setcrtc+0x194/0x6a0 [drm] ? vprintk_emit+0x16a/0x230 ? drm_ioctl+0x163/0x390 [drm] ? drm_mode_getcrtc+0x180/0x180 [drm] drm_ioctl_kernel+0xaa/0xf0 [drm] drm_ioctl+0x208/0x390 [drm] ? drm_mode_getcrtc+0x180/0x180 [drm] nouveau_drm_ioctl+0x63/0xb0 [nouveau] do_vfs_ioctl+0x405/0x660 ? recalc_sigpending+0x17/0x50 ? _copy_from_user+0x37/0x60 ksys_ioctl+0x5e/0x90 ? exit_to_usermode_loop+0x92/0xe0 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x59/0x190 entry_SYSCALL_64_after_hwframe+0x44/0xa9 WARNING: CPU: 0 PID: 1484 at drivers/gpu/drm/drm_dp_mst_topology.c:3336 drm_dp_atomic_release_vcpi_slots+0x87/0xb0 [drm_kms_helper] ---[ end trace 4c395c0c51b1f88d ]--- [drm:drm_dp_atomic_release_vcpi_slots [drm_kms_helper]] *ERROR* no VCPI for [MST PORT:00000000e288eb7d] found in mst state 000000008e642070 So, fix this by doing what we probably should have done from the start: only call drm_dp_atomic_find_vcpi_slots() when crtc_state->mode_changed is set, so that VCPI allocations remain for as long as the CRTC is enabled. Signed-off-by: Lyude Paul Fixes: 232c9eec417a ("drm/nouveau: Use atomic VCPI helpers for MST") Cc: Lyude Paul Cc: Ben Skeggs Cc: Daniel Vetter Cc: David Airlie Cc: Jerry Zuo Cc: Harry Wentland Cc: Juston Li Cc: Karol Herbst Cc: Laurent Pinchart Cc: Ilia Mirkin Cc: # v5.1+ Acked-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20190801220216.15323-1-lyude@redhat.com --- drivers/gpu/drm/nouveau/dispnv50/disp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 8497768f1b41..126703816794 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -780,7 +780,7 @@ nv50_msto_atomic_check(struct drm_encoder *encoder, drm_dp_calc_pbn_mode(crtc_state->adjusted_mode.clock, connector->display_info.bpc * 3); - if (drm_atomic_crtc_needs_modeset(crtc_state)) { + if (crtc_state->mode_changed) { slots = drm_dp_atomic_find_vcpi_slots(state, &mstm->mgr, mstc->port, asyh->dp.pbn); From 41995342b40c418a47603e1321256d2c4a2ed0fb Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Thu, 1 Aug 2019 13:06:30 +0200 Subject: [PATCH 732/823] s390/dasd: fix endless loop after read unit address configuration After getting a storage server event that causes the DASD device driver to update its unit address configuration during a device shutdown there is the possibility of an endless loop in the device driver. In the system log there will be ongoing DASD error messages with RC: -19. The reason is that the loop starting the ruac request only terminates when the retry counter is decreased to 0. But in the sleep_on function there are early exit paths that do not decrease the retry counter. Prevent an endless loop by handling those cases separately. Remove the unnecessary do..while loop since the sleep_on function takes care of retries by itself. Fixes: 8e09f21574ea ("[S390] dasd: add hyper PAV support to DASD device driver, part 1") Cc: stable@vger.kernel.org # 2.6.25+ Signed-off-by: Stefan Haberland Reviewed-by: Jan Hoeppner Signed-off-by: Jens Axboe --- drivers/s390/block/dasd_alias.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index b9ce93e9df89..99f86612f775 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -383,6 +383,20 @@ suborder_not_supported(struct dasd_ccw_req *cqr) char msg_format; char msg_no; + /* + * intrc values ENODEV, ENOLINK and EPERM + * will be optained from sleep_on to indicate that no + * IO operation can be started + */ + if (cqr->intrc == -ENODEV) + return 1; + + if (cqr->intrc == -ENOLINK) + return 1; + + if (cqr->intrc == -EPERM) + return 1; + sense = dasd_get_sense(&cqr->irb); if (!sense) return 0; @@ -447,12 +461,8 @@ static int read_unit_address_configuration(struct dasd_device *device, lcu->flags &= ~NEED_UAC_UPDATE; spin_unlock_irqrestore(&lcu->lock, flags); - do { - rc = dasd_sleep_on(cqr); - if (rc && suborder_not_supported(cqr)) - return -EOPNOTSUPP; - } while (rc && (cqr->retries > 0)); - if (rc) { + rc = dasd_sleep_on(cqr); + if (rc && !suborder_not_supported(cqr)) { spin_lock_irqsave(&lcu->lock, flags); lcu->flags |= NEED_UAC_UPDATE; spin_unlock_irqrestore(&lcu->lock, flags); From 9eae7c3bcb52ec0a9f816d830e232e36a20b46d4 Mon Sep 17 00:00:00 2001 From: Fuqian Huang Date: Thu, 4 Jul 2019 10:34:36 +0800 Subject: [PATCH 733/823] drm/exynos: using dev_get_drvdata directly Several drivers cast a struct device pointer to a struct platform_device pointer only to then call platform_get_drvdata(). To improve readability, these constructs can be simplified by using dev_get_drvdata() directly. Signed-off-by: Fuqian Huang Reviewed-by: Emil Velikov Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_drm_fimc.c | 2 +- drivers/gpu/drm/exynos/exynos_drm_gsc.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c index a594ab7be2c0..164d914cbe9a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c @@ -44,7 +44,7 @@ static unsigned int fimc_mask = 0xc; module_param_named(fimc_devs, fimc_mask, uint, 0644); MODULE_PARM_DESC(fimc_devs, "Alias mask for assigning FIMC devices to Exynos DRM"); -#define get_fimc_context(dev) platform_get_drvdata(to_platform_device(dev)) +#define get_fimc_context(dev) dev_get_drvdata(dev) enum { FIMC_CLK_LCLK, diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 1e4b21c49a06..1c524db9570f 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -58,7 +58,7 @@ #define GSC_COEF_DEPTH 3 #define GSC_AUTOSUSPEND_DELAY 2000 -#define get_gsc_context(dev) platform_get_drvdata(to_platform_device(dev)) +#define get_gsc_context(dev) dev_get_drvdata(dev) #define gsc_read(offset) readl(ctx->regs + (offset)) #define gsc_write(cfg, offset) writel(cfg, ctx->regs + (offset)) From 59d431746f1b3c76fd551b71241d7fdce38a58e9 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 9 Jul 2019 21:01:14 +0900 Subject: [PATCH 734/823] drm/exynos: remove redundant assignment to pointer 'node' The pointer 'node' is being assigned with a value that is never read and is re-assigned later. The assignment is redundant and can be removed. Addresses-Coverity: ("Unused value") Signed-off-by: Colin Ian King Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_drm_g2d.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 50904eee96f7..2a3382d43bc9 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -267,7 +267,7 @@ static inline void g2d_hw_reset(struct g2d_data *g2d) static int g2d_init_cmdlist(struct g2d_data *g2d) { struct device *dev = g2d->dev; - struct g2d_cmdlist_node *node = g2d->cmdlist_node; + struct g2d_cmdlist_node *node; int nr; int ret; struct g2d_buf_info *buf_info; From d6f25bd9d4079165ea90f12d71e06d1dca83cd86 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 9 Jul 2019 21:08:48 +0900 Subject: [PATCH 735/823] drm/exynos: add CONFIG_MMU dependency Compile-testing this driver on a NOMMU configuration shows a link failure: drivers/gpu/drm/exynos/exynos_drm_gem.o: In function `exynos_drm_gem_fault': exynos_drm_gem.c:(.text+0x484): undefined reference to `vmf_insert_mixed' Add a CONFIG_MMU dependency to ensure we only enable this in configurations that build correctly. Many other drm drivers have the same dependency. It would be nice to make this work in MMU-less configurations, but evidently nobody has ever needed this so far. Fixes: 156bdac99061 ("drm/exynos: trigger build of all modules") Signed-off-by: Arnd Bergmann Reviewed-by: Vladimir Murzin Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig index 60ce4a8ad9e1..6f7d3b3b3628 100644 --- a/drivers/gpu/drm/exynos/Kconfig +++ b/drivers/gpu/drm/exynos/Kconfig @@ -2,6 +2,7 @@ config DRM_EXYNOS tristate "DRM Support for Samsung SoC EXYNOS Series" depends on OF && DRM && (ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || ARCH_MULTIPLATFORM || COMPILE_TEST) + depends on MMU select DRM_KMS_HELPER select VIDEOMODE_HELPERS select SND_SOC_HDMI_CODEC if SND_SOC From 1bbbab097a05276e312dd2462791d32b21ceb1ee Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 22 Jul 2019 23:25:35 +0100 Subject: [PATCH 736/823] drm/exynos: fix missing decrement of retry counter Currently the retry counter is not being decremented, leading to a potential infinite spin if the scalar_reads don't change state. Addresses-Coverity: ("Infinite loop") Fixes: 280e54c9f614 ("drm/exynos: scaler: Reset hardware before starting the operation") Signed-off-by: Colin Ian King Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_drm_scaler.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_scaler.c b/drivers/gpu/drm/exynos/exynos_drm_scaler.c index 9af096479e1c..b24ba948b725 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_scaler.c +++ b/drivers/gpu/drm/exynos/exynos_drm_scaler.c @@ -94,12 +94,12 @@ static inline int scaler_reset(struct scaler_context *scaler) scaler_write(SCALER_CFG_SOFT_RESET, SCALER_CFG); do { cpu_relax(); - } while (retry > 1 && + } while (--retry > 1 && scaler_read(SCALER_CFG) & SCALER_CFG_SOFT_RESET); do { cpu_relax(); scaler_write(1, SCALER_INT_EN); - } while (retry > 0 && scaler_read(SCALER_INT_EN) != 1); + } while (--retry > 0 && scaler_read(SCALER_INT_EN) != 1); return retry ? 0 : -EIO; } From b3980e48528c4d2a9e70b145a5bba328b73a0f93 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 1 Aug 2019 23:25:49 +0900 Subject: [PATCH 737/823] arm64: kprobes: Recover pstate.D in single-step exception handler kprobes manipulates the interrupted PSTATE for single step, and doesn't restore it. Thus, if we put a kprobe where the pstate.D (debug) masked, the mask will be cleared after the kprobe hits. Moreover, in the most complicated case, this can lead a kernel crash with below message when a nested kprobe hits. [ 152.118921] Unexpected kernel single-step exception at EL1 When the 1st kprobe hits, do_debug_exception() will be called. At this point, debug exception (= pstate.D) must be masked (=1). But if another kprobes hits before single-step of the first kprobe (e.g. inside user pre_handler), it unmask the debug exception (pstate.D = 0) and return. Then, when the 1st kprobe setting up single-step, it saves current DAIF, mask DAIF, enable single-step, and restore DAIF. However, since "D" flag in DAIF is cleared by the 2nd kprobe, the single-step exception happens soon after restoring DAIF. This has been introduced by commit 7419333fa15e ("arm64: kprobe: Always clear pstate.D in breakpoint exception handler") To solve this issue, this stores all DAIF bits and restore it after single stepping. Reported-by: Naresh Kamboju Fixes: 7419333fa15e ("arm64: kprobe: Always clear pstate.D in breakpoint exception handler") Reviewed-by: James Morse Tested-by: James Morse Signed-off-by: Masami Hiramatsu Signed-off-by: Will Deacon --- arch/arm64/include/asm/daifflags.h | 2 ++ arch/arm64/kernel/probes/kprobes.c | 40 +++++------------------------- 2 files changed, 8 insertions(+), 34 deletions(-) diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h index 987926ed535e..063c964af705 100644 --- a/arch/arm64/include/asm/daifflags.h +++ b/arch/arm64/include/asm/daifflags.h @@ -13,6 +13,8 @@ #define DAIF_PROCCTX 0 #define DAIF_PROCCTX_NOIRQ PSR_I_BIT #define DAIF_ERRCTX (PSR_I_BIT | PSR_A_BIT) +#define DAIF_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) + /* mask/save/unmask/restore all exceptions, including interrupts. */ static inline void local_daif_mask(void) diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index bd5dfffca272..c4452827419b 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -167,33 +168,6 @@ static void __kprobes set_current_kprobe(struct kprobe *p) __this_cpu_write(current_kprobe, p); } -/* - * When PSTATE.D is set (masked), then software step exceptions can not be - * generated. - * SPSR's D bit shows the value of PSTATE.D immediately before the - * exception was taken. PSTATE.D is set while entering into any exception - * mode, however software clears it for any normal (none-debug-exception) - * mode in the exception entry. Therefore, when we are entering into kprobe - * breakpoint handler from any normal mode then SPSR.D bit is already - * cleared, however it is set when we are entering from any debug exception - * mode. - * Since we always need to generate single step exception after a kprobe - * breakpoint exception therefore we need to clear it unconditionally, when - * we become sure that the current breakpoint exception is for kprobe. - */ -static void __kprobes -spsr_set_debug_flag(struct pt_regs *regs, int mask) -{ - unsigned long spsr = regs->pstate; - - if (mask) - spsr |= PSR_D_BIT; - else - spsr &= ~PSR_D_BIT; - - regs->pstate = spsr; -} - /* * Interrupts need to be disabled before single-step mode is set, and not * reenabled until after single-step mode ends. @@ -205,17 +179,17 @@ spsr_set_debug_flag(struct pt_regs *regs, int mask) static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb, struct pt_regs *regs) { - kcb->saved_irqflag = regs->pstate; + kcb->saved_irqflag = regs->pstate & DAIF_MASK; regs->pstate |= PSR_I_BIT; + /* Unmask PSTATE.D for enabling software step exceptions. */ + regs->pstate &= ~PSR_D_BIT; } static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb, struct pt_regs *regs) { - if (kcb->saved_irqflag & PSR_I_BIT) - regs->pstate |= PSR_I_BIT; - else - regs->pstate &= ~PSR_I_BIT; + regs->pstate &= ~DAIF_MASK; + regs->pstate |= kcb->saved_irqflag; } static void __kprobes @@ -252,8 +226,6 @@ static void __kprobes setup_singlestep(struct kprobe *p, set_ss_context(kcb, slot); /* mark pending ss */ - spsr_set_debug_flag(regs, 0); - /* IRQs and single stepping do not mix well. */ kprobes_save_local_irqflag(kcb, regs); kernel_enable_single_step(regs); From d8bb6718c4db9bcd075dde7ff55d46091ccfae15 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 1 Aug 2019 23:36:14 +0900 Subject: [PATCH 738/823] arm64: Make debug exception handlers visible from RCU Make debug exceptions visible from RCU so that synchronize_rcu() correctly track the debug exception handler. This also introduces sanity checks for user-mode exceptions as same as x86's ist_enter()/ist_exit(). The debug exception can interrupt in idle task. For example, it warns if we put a kprobe on a function called from idle task as below. The warning message showed that the rcu_read_lock() caused this problem. But actually, this means the RCU is lost the context which is already in NMI/IRQ. /sys/kernel/debug/tracing # echo p default_idle_call >> kprobe_events /sys/kernel/debug/tracing # echo 1 > events/kprobes/enable /sys/kernel/debug/tracing # [ 135.122237] [ 135.125035] ============================= [ 135.125310] WARNING: suspicious RCU usage [ 135.125581] 5.2.0-08445-g9187c508bdc7 #20 Not tainted [ 135.125904] ----------------------------- [ 135.126205] include/linux/rcupdate.h:594 rcu_read_lock() used illegally while idle! [ 135.126839] [ 135.126839] other info that might help us debug this: [ 135.126839] [ 135.127410] [ 135.127410] RCU used illegally from idle CPU! [ 135.127410] rcu_scheduler_active = 2, debug_locks = 1 [ 135.128114] RCU used illegally from extended quiescent state! [ 135.128555] 1 lock held by swapper/0/0: [ 135.128944] #0: (____ptrval____) (rcu_read_lock){....}, at: call_break_hook+0x0/0x178 [ 135.130499] [ 135.130499] stack backtrace: [ 135.131192] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.2.0-08445-g9187c508bdc7 #20 [ 135.131841] Hardware name: linux,dummy-virt (DT) [ 135.132224] Call trace: [ 135.132491] dump_backtrace+0x0/0x140 [ 135.132806] show_stack+0x24/0x30 [ 135.133133] dump_stack+0xc4/0x10c [ 135.133726] lockdep_rcu_suspicious+0xf8/0x108 [ 135.134171] call_break_hook+0x170/0x178 [ 135.134486] brk_handler+0x28/0x68 [ 135.134792] do_debug_exception+0x90/0x150 [ 135.135051] el1_dbg+0x18/0x8c [ 135.135260] default_idle_call+0x0/0x44 [ 135.135516] cpu_startup_entry+0x2c/0x30 [ 135.135815] rest_init+0x1b0/0x280 [ 135.136044] arch_call_rest_init+0x14/0x1c [ 135.136305] start_kernel+0x4d4/0x500 [ 135.136597] So make debug exception visible to RCU can fix this warning. Reported-by: Naresh Kamboju Acked-by: Paul E. McKenney Signed-off-by: Masami Hiramatsu Signed-off-by: Will Deacon --- arch/arm64/mm/fault.c | 57 +++++++++++++++++++++++++++++++++++++------ 1 file changed, 49 insertions(+), 8 deletions(-) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 9568c116ac7f..cfd65b63f36f 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -777,6 +777,53 @@ void __init hook_debug_fault_code(int nr, debug_fault_info[nr].name = name; } +/* + * In debug exception context, we explicitly disable preemption despite + * having interrupts disabled. + * This serves two purposes: it makes it much less likely that we would + * accidentally schedule in exception context and it will force a warning + * if we somehow manage to schedule by accident. + */ +static void debug_exception_enter(struct pt_regs *regs) +{ + /* + * Tell lockdep we disabled irqs in entry.S. Do nothing if they were + * already disabled to preserve the last enabled/disabled addresses. + */ + if (interrupts_enabled(regs)) + trace_hardirqs_off(); + + if (user_mode(regs)) { + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); + } else { + /* + * We might have interrupted pretty much anything. In + * fact, if we're a debug exception, we can even interrupt + * NMI processing. We don't want this code makes in_nmi() + * to return true, but we need to notify RCU. + */ + rcu_nmi_enter(); + } + + preempt_disable(); + + /* This code is a bit fragile. Test it. */ + RCU_LOCKDEP_WARN(!rcu_is_watching(), "exception_enter didn't work"); +} +NOKPROBE_SYMBOL(debug_exception_enter); + +static void debug_exception_exit(struct pt_regs *regs) +{ + preempt_enable_no_resched(); + + if (!user_mode(regs)) + rcu_nmi_exit(); + + if (interrupts_enabled(regs)) + trace_hardirqs_on(); +} +NOKPROBE_SYMBOL(debug_exception_exit); + #ifdef CONFIG_ARM64_ERRATUM_1463225 DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); @@ -817,12 +864,7 @@ asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint, if (cortex_a76_erratum_1463225_debug_handler(regs)) return; - /* - * Tell lockdep we disabled irqs in entry.S. Do nothing if they were - * already disabled to preserve the last enabled/disabled addresses. - */ - if (interrupts_enabled(regs)) - trace_hardirqs_off(); + debug_exception_enter(regs); if (user_mode(regs) && !is_ttbr0_addr(pc)) arm64_apply_bp_hardening(); @@ -832,7 +874,6 @@ asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint, inf->sig, inf->code, (void __user *)pc, esr); } - if (interrupts_enabled(regs)) - trace_hardirqs_on(); + debug_exception_exit(regs); } NOKPROBE_SYMBOL(do_debug_exception); From a4127952859a869cf3fc5a49547dbe2ffa2eac89 Mon Sep 17 00:00:00 2001 From: Jarkko Nikula Date: Thu, 1 Aug 2019 16:49:01 +0300 Subject: [PATCH 739/823] spi: pxa2xx: Add support for Intel Tiger Lake Intel Tiger Lake -LP LPSS SPI controller is otherwise similar than Cannon Lake but has more controllers and up to two chip selects per controller. Signed-off-by: Jarkko Nikula Link: https://lore.kernel.org/r/20190801134901.12635-1-jarkko.nikula@linux.intel.com Signed-off-by: Mark Brown --- drivers/spi/spi-pxa2xx.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index 22513caf2000..bb6a14d1ab0f 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -1457,6 +1457,14 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = { { PCI_VDEVICE(INTEL, 0x02aa), LPSS_CNL_SSP }, { PCI_VDEVICE(INTEL, 0x02ab), LPSS_CNL_SSP }, { PCI_VDEVICE(INTEL, 0x02fb), LPSS_CNL_SSP }, + /* TGL-LP */ + { PCI_VDEVICE(INTEL, 0xa0aa), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0xa0ab), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0xa0de), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0xa0df), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0xa0fb), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0xa0fd), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0xa0fe), LPSS_CNL_SSP }, { }, }; From cd28aa2e056cd1ea79fc5f24eed0ce868c6cab5c Mon Sep 17 00:00:00 2001 From: Wang Xiayang Date: Wed, 31 Jul 2019 15:31:14 +0800 Subject: [PATCH 740/823] can: sja1000: force the string buffer NULL-terminated strncpy() does not ensure NULL-termination when the input string size equals to the destination buffer size IFNAMSIZ. The output string 'name' is passed to dev_info which relies on NULL-termination. Use strlcpy() instead. This issue is identified by a Coccinelle script. Signed-off-by: Wang Xiayang Signed-off-by: Marc Kleine-Budde --- drivers/net/can/sja1000/peak_pcmcia.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/sja1000/peak_pcmcia.c b/drivers/net/can/sja1000/peak_pcmcia.c index 185c7f7d38a4..5e0d5e8101c8 100644 --- a/drivers/net/can/sja1000/peak_pcmcia.c +++ b/drivers/net/can/sja1000/peak_pcmcia.c @@ -479,7 +479,7 @@ static void pcan_free_channels(struct pcan_pccard *card) if (!netdev) continue; - strncpy(name, netdev->name, IFNAMSIZ); + strlcpy(name, netdev->name, IFNAMSIZ); unregister_sja1000dev(netdev); From e787f19373b8a5fa24087800ed78314fd17b984a Mon Sep 17 00:00:00 2001 From: Wang Xiayang Date: Wed, 31 Jul 2019 15:25:59 +0800 Subject: [PATCH 741/823] can: peak_usb: force the string buffer NULL-terminated strncpy() does not ensure NULL-termination when the input string size equals to the destination buffer size IFNAMSIZ. The output string is passed to dev_info() which relies on the NULL-termination. Use strlcpy() instead. This issue is identified by a Coccinelle script. Signed-off-by: Wang Xiayang Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/peak_usb/pcan_usb_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 22b9c8e6d040..65dce642b86b 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -855,7 +855,7 @@ static void peak_usb_disconnect(struct usb_interface *intf) dev_prev_siblings = dev->prev_siblings; dev->state &= ~PCAN_USB_STATE_CONNECTED; - strncpy(name, netdev->name, IFNAMSIZ); + strlcpy(name, netdev->name, IFNAMSIZ); unregister_netdev(netdev); From 30a8beeb3042f49d0537b7050fd21b490166a3d9 Mon Sep 17 00:00:00 2001 From: Tomas Bortoli Date: Wed, 31 Jul 2019 10:54:47 -0400 Subject: [PATCH 742/823] can: peak_usb: pcan_usb_fd: Fix info-leaks to USB devices Uninitialized Kernel memory can leak to USB devices. Fix by using kzalloc() instead of kmalloc() on the affected buffers. Signed-off-by: Tomas Bortoli Reported-by: syzbot+513e4d0985298538bf9b@syzkaller.appspotmail.com Fixes: 0a25e1f4f185 ("can: peak_usb: add support for PEAK new CANFD USB adapters") Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/peak_usb/pcan_usb_fd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index 34761c3a6286..47cc1ff5b88e 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -841,7 +841,7 @@ static int pcan_usb_fd_init(struct peak_usb_device *dev) goto err_out; /* allocate command buffer once for all for the interface */ - pdev->cmd_buffer_addr = kmalloc(PCAN_UFD_CMD_BUFFER_SIZE, + pdev->cmd_buffer_addr = kzalloc(PCAN_UFD_CMD_BUFFER_SIZE, GFP_KERNEL); if (!pdev->cmd_buffer_addr) goto err_out_1; From ead16e53c2f0ed946d82d4037c630e2f60f4ab69 Mon Sep 17 00:00:00 2001 From: Tomas Bortoli Date: Wed, 31 Jul 2019 10:54:47 -0400 Subject: [PATCH 743/823] can: peak_usb: pcan_usb_pro: Fix info-leaks to USB devices Uninitialized Kernel memory can leak to USB devices. Fix by using kzalloc() instead of kmalloc() on the affected buffers. Signed-off-by: Tomas Bortoli Reported-by: syzbot+d6a5a1a3657b596ef132@syzkaller.appspotmail.com Fixes: f14e22435a27 ("net: can: peak_usb: Do not do dma on the stack") Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/peak_usb/pcan_usb_pro.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c index 178bb7cff0c1..53cb2f72bdd0 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c @@ -494,7 +494,7 @@ static int pcan_usb_pro_drv_loaded(struct peak_usb_device *dev, int loaded) u8 *buffer; int err; - buffer = kmalloc(PCAN_USBPRO_FCT_DRVLD_REQ_LEN, GFP_KERNEL); + buffer = kzalloc(PCAN_USBPRO_FCT_DRVLD_REQ_LEN, GFP_KERNEL); if (!buffer) return -ENOMEM; From 3cdd98606750a5a1d1c8bcda5b481cb86ed67b3b Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Mon, 29 Jul 2019 01:23:46 +0200 Subject: [PATCH 744/823] s390/zcrypt: adjust switch fall through comments for -Wimplicit-fallthrough Silence the following warnings when built with -Wimplicit-fallthrough=3 enabled by default since 5.3-rc2: In file included from ./include/linux/preempt.h:11, from ./include/linux/spinlock.h:51, from ./include/linux/mmzone.h:8, from ./include/linux/gfp.h:6, from ./include/linux/slab.h:15, from drivers/s390/crypto/ap_queue.c:13: drivers/s390/crypto/ap_queue.c: In function 'ap_sm_recv': ./include/linux/list.h:577:2: warning: this statement may fall through [-Wimplicit-fallthrough=] 577 | for (pos = list_first_entry(head, typeof(*pos), member); \ | ^~~ drivers/s390/crypto/ap_queue.c:147:3: note: in expansion of macro 'list_for_each_entry' 147 | list_for_each_entry(ap_msg, &aq->pendingq, list) { | ^~~~~~~~~~~~~~~~~~~ drivers/s390/crypto/ap_queue.c:155:2: note: here 155 | case AP_RESPONSE_NO_PENDING_REPLY: | ^~~~ drivers/s390/crypto/zcrypt_msgtype6.c: In function 'convert_response_ep11_xcrb': drivers/s390/crypto/zcrypt_msgtype6.c:871:6: warning: this statement may fall through [-Wimplicit-fallthrough=] 871 | if (msg->cprbx.cprb_ver_id == 0x04) | ^ drivers/s390/crypto/zcrypt_msgtype6.c:874:2: note: here 874 | default: /* Unknown response type, this should NEVER EVER happen */ | ^~~~~~~ drivers/s390/crypto/zcrypt_msgtype6.c: In function 'convert_response_rng': drivers/s390/crypto/zcrypt_msgtype6.c:901:6: warning: this statement may fall through [-Wimplicit-fallthrough=] 901 | if (msg->cprbx.cprb_ver_id == 0x02) | ^ drivers/s390/crypto/zcrypt_msgtype6.c:907:2: note: here 907 | default: /* Unknown response type, this should NEVER EVER happen */ | ^~~~~~~ drivers/s390/crypto/zcrypt_msgtype6.c: In function 'convert_response_xcrb': drivers/s390/crypto/zcrypt_msgtype6.c:838:6: warning: this statement may fall through [-Wimplicit-fallthrough=] 838 | if (msg->cprbx.cprb_ver_id == 0x02) | ^ drivers/s390/crypto/zcrypt_msgtype6.c:844:2: note: here 844 | default: /* Unknown response type, this should NEVER EVER happen */ | ^~~~~~~ drivers/s390/crypto/zcrypt_msgtype6.c: In function 'convert_response_ica': drivers/s390/crypto/zcrypt_msgtype6.c:801:6: warning: this statement may fall through [-Wimplicit-fallthrough=] 801 | if (msg->cprbx.cprb_ver_id == 0x02) | ^ drivers/s390/crypto/zcrypt_msgtype6.c:808:2: note: here 808 | default: /* Unknown response type, this should NEVER EVER happen */ | ^~~~~~~ Acked-by: Patrick Steuer Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/ap_queue.c | 1 + drivers/s390/crypto/zcrypt_msgtype6.c | 17 ++++------------- 2 files changed, 5 insertions(+), 13 deletions(-) diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 5ea83dc4f1d7..dad2be333d82 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -152,6 +152,7 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq) ap_msg->receive(aq, ap_msg, aq->reply); break; } + /* fall through */ case AP_RESPONSE_NO_PENDING_REPLY: if (!status.queue_empty || aq->queue_count <= 0) break; diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 12fe9deb265e..a36251d138fb 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -801,10 +801,7 @@ static int convert_response_ica(struct zcrypt_queue *zq, if (msg->cprbx.cprb_ver_id == 0x02) return convert_type86_ica(zq, reply, outputdata, outputdatalength); - /* - * Fall through, no break, incorrect cprb version is an unknown - * response - */ + /* fall through - wrong cprb version is an unknown response */ default: /* Unknown response type, this should NEVER EVER happen */ zq->online = 0; pr_err("Cryptographic device %02x.%04x failed and was set offline\n", @@ -837,10 +834,7 @@ static int convert_response_xcrb(struct zcrypt_queue *zq, } if (msg->cprbx.cprb_ver_id == 0x02) return convert_type86_xcrb(zq, reply, xcRB); - /* - * Fall through, no break, incorrect cprb version is an unknown - * response - */ + /* fall through - wrong cprb version is an unknown response */ default: /* Unknown response type, this should NEVER EVER happen */ xcRB->status = 0x0008044DL; /* HDD_InvalidParm */ zq->online = 0; @@ -870,7 +864,7 @@ static int convert_response_ep11_xcrb(struct zcrypt_queue *zq, return convert_error(zq, reply); if (msg->cprbx.cprb_ver_id == 0x04) return convert_type86_ep11_xcrb(zq, reply, xcRB); - /* Fall through, no break, incorrect cprb version is an unknown resp.*/ + /* fall through - wrong cprb version is an unknown resp */ default: /* Unknown response type, this should NEVER EVER happen */ zq->online = 0; pr_err("Cryptographic device %02x.%04x failed and was set offline\n", @@ -900,10 +894,7 @@ static int convert_response_rng(struct zcrypt_queue *zq, return -EINVAL; if (msg->cprbx.cprb_ver_id == 0x02) return convert_type86_rng(zq, reply, data); - /* - * Fall through, no break, incorrect cprb version is an unknown - * response - */ + /* fall through - wrong cprb version is an unknown response */ default: /* Unknown response type, this should NEVER EVER happen */ zq->online = 0; pr_err("Cryptographic device %02x.%04x failed and was set offline\n", From 63dc6e63e682cf756ab8c18aa1b85b0efb358dad Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 1 Aug 2019 13:44:58 +0100 Subject: [PATCH 745/823] Revert "drm/vgem: fix cache synchronization on arm/arm64" commit 7e9e5ead55be ("drm/vgem: fix cache synchronization on arm/arm64") broke all of the !llc i915-vgem coherency tests in CI, and left the HW very, very unhappy (which is even more scary). Fixes: 7e9e5ead55be ("drm/vgem: fix cache synchronization on arm/arm64") Signed-off-by: Chris Wilson Cc: Daniel Vetter Cc: Rob Clark Cc: Sean Paul Acked-by: Sean Paul Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20190801124458.24949-1-chris@chris-wilson.co.uk --- drivers/gpu/drm/vgem/vgem_drv.c | 130 ++++++++++++-------------------- 1 file changed, 47 insertions(+), 83 deletions(-) diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c index fc04803ff403..11a8f99ba18c 100644 --- a/drivers/gpu/drm/vgem/vgem_drv.c +++ b/drivers/gpu/drm/vgem/vgem_drv.c @@ -47,16 +47,10 @@ static struct vgem_device { struct platform_device *platform; } *vgem_device; -static void sync_and_unpin(struct drm_vgem_gem_object *bo); -static struct page **pin_and_sync(struct drm_vgem_gem_object *bo); - static void vgem_gem_free_object(struct drm_gem_object *obj) { struct drm_vgem_gem_object *vgem_obj = to_vgem_bo(obj); - if (!obj->import_attach) - sync_and_unpin(vgem_obj); - kvfree(vgem_obj->pages); mutex_destroy(&vgem_obj->pages_lock); @@ -84,15 +78,40 @@ static vm_fault_t vgem_gem_fault(struct vm_fault *vmf) return VM_FAULT_SIGBUS; mutex_lock(&obj->pages_lock); - if (!obj->pages) - pin_and_sync(obj); if (obj->pages) { get_page(obj->pages[page_offset]); vmf->page = obj->pages[page_offset]; ret = 0; } mutex_unlock(&obj->pages_lock); + if (ret) { + struct page *page; + page = shmem_read_mapping_page( + file_inode(obj->base.filp)->i_mapping, + page_offset); + if (!IS_ERR(page)) { + vmf->page = page; + ret = 0; + } else switch (PTR_ERR(page)) { + case -ENOSPC: + case -ENOMEM: + ret = VM_FAULT_OOM; + break; + case -EBUSY: + ret = VM_FAULT_RETRY; + break; + case -EFAULT: + case -EINVAL: + ret = VM_FAULT_SIGBUS; + break; + default: + WARN_ON(PTR_ERR(page)); + ret = VM_FAULT_SIGBUS; + break; + } + + } return ret; } @@ -258,93 +277,32 @@ static const struct file_operations vgem_driver_fops = { .release = drm_release, }; -/* Called under pages_lock, except in free path (where it can't race): */ -static void sync_and_unpin(struct drm_vgem_gem_object *bo) -{ - struct drm_device *dev = bo->base.dev; - - if (bo->table) { - dma_sync_sg_for_cpu(dev->dev, bo->table->sgl, - bo->table->nents, DMA_BIDIRECTIONAL); - sg_free_table(bo->table); - kfree(bo->table); - bo->table = NULL; - } - - if (bo->pages) { - drm_gem_put_pages(&bo->base, bo->pages, true, true); - bo->pages = NULL; - } -} - -static struct page **pin_and_sync(struct drm_vgem_gem_object *bo) -{ - struct drm_device *dev = bo->base.dev; - int npages = bo->base.size >> PAGE_SHIFT; - struct page **pages; - struct sg_table *sgt; - - WARN_ON(!mutex_is_locked(&bo->pages_lock)); - - pages = drm_gem_get_pages(&bo->base); - if (IS_ERR(pages)) { - bo->pages_pin_count--; - mutex_unlock(&bo->pages_lock); - return pages; - } - - sgt = drm_prime_pages_to_sg(pages, npages); - if (IS_ERR(sgt)) { - dev_err(dev->dev, - "failed to allocate sgt: %ld\n", - PTR_ERR(bo->table)); - drm_gem_put_pages(&bo->base, pages, false, false); - mutex_unlock(&bo->pages_lock); - return ERR_CAST(bo->table); - } - - /* - * Flush the object from the CPU cache so that importers - * can rely on coherent indirect access via the exported - * dma-address. - */ - dma_sync_sg_for_device(dev->dev, sgt->sgl, - sgt->nents, DMA_BIDIRECTIONAL); - - bo->pages = pages; - bo->table = sgt; - - return pages; -} - static struct page **vgem_pin_pages(struct drm_vgem_gem_object *bo) { - struct page **pages; - mutex_lock(&bo->pages_lock); - if (bo->pages_pin_count++ == 0 && !bo->pages) { - pages = pin_and_sync(bo); - } else { - WARN_ON(!bo->pages); - pages = bo->pages; + if (bo->pages_pin_count++ == 0) { + struct page **pages; + + pages = drm_gem_get_pages(&bo->base); + if (IS_ERR(pages)) { + bo->pages_pin_count--; + mutex_unlock(&bo->pages_lock); + return pages; + } + + bo->pages = pages; } mutex_unlock(&bo->pages_lock); - return pages; + return bo->pages; } static void vgem_unpin_pages(struct drm_vgem_gem_object *bo) { - /* - * We shouldn't hit this for imported bo's.. in the import - * case we don't own the scatter-table - */ - WARN_ON(bo->base.import_attach); - mutex_lock(&bo->pages_lock); if (--bo->pages_pin_count == 0) { - WARN_ON(!bo->table); - sync_and_unpin(bo); + drm_gem_put_pages(&bo->base, bo->pages, true, true); + bo->pages = NULL; } mutex_unlock(&bo->pages_lock); } @@ -352,12 +310,18 @@ static void vgem_unpin_pages(struct drm_vgem_gem_object *bo) static int vgem_prime_pin(struct drm_gem_object *obj) { struct drm_vgem_gem_object *bo = to_vgem_bo(obj); + long n_pages = obj->size >> PAGE_SHIFT; struct page **pages; pages = vgem_pin_pages(bo); if (IS_ERR(pages)) return PTR_ERR(pages); + /* Flush the object from the CPU cache so that importers can rely + * on coherent indirect access via the exported dma-address. + */ + drm_clflush_pages(pages, n_pages); + return 0; } From 8493b2a06fc5b77ef5c579dc32b12761f7b7a84c Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Tue, 30 Jul 2019 15:44:07 +0200 Subject: [PATCH 746/823] mtd: rawnand: micron: handle on-die "ECC-off" devices correctly Some devices are not supposed to support on-die ECC but experience shows that internal ECC machinery can actually be enabled through the "SET FEATURE (EFh)" command, even if a read of the "READ ID Parameter Tables" returns that it is not. Currently, the driver checks the "READ ID Parameter" field directly after having enabled the feature. If the check fails it returns immediately but leaves the ECC on. When using buggy chips like MT29F2G08ABAGA and MT29F2G08ABBGA, all future read/program cycles will go through the on-die ECC, confusing the host controller which is supposed to be the one handling correction. To address this in a common way we need to turn off the on-die ECC directly after reading the "READ ID Parameter" and before checking the "ECC status". Cc: stable@vger.kernel.org Fixes: dbc44edbf833 ("mtd: rawnand: micron: Fix on-die ECC detection logic") Signed-off-by: Marco Felsch Reviewed-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_micron.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c index 1622d3145587..8ca9fad6e6ad 100644 --- a/drivers/mtd/nand/raw/nand_micron.c +++ b/drivers/mtd/nand/raw/nand_micron.c @@ -390,6 +390,14 @@ static int micron_supports_on_die_ecc(struct nand_chip *chip) (chip->id.data[4] & MICRON_ID_INTERNAL_ECC_MASK) != 0x2) return MICRON_ON_DIE_UNSUPPORTED; + /* + * It seems that there are devices which do not support ECC officially. + * At least the MT29F2G08ABAGA / MT29F2G08ABBGA devices supports + * enabling the ECC feature but don't reflect that to the READ_ID table. + * So we have to guarantee that we disable the ECC feature directly + * after we did the READ_ID table command. Later we can evaluate the + * ECC_ENABLE support. + */ ret = micron_nand_on_die_ecc_setup(chip, true); if (ret) return MICRON_ON_DIE_UNSUPPORTED; @@ -398,13 +406,13 @@ static int micron_supports_on_die_ecc(struct nand_chip *chip) if (ret) return MICRON_ON_DIE_UNSUPPORTED; - if (!(id[4] & MICRON_ID_ECC_ENABLED)) - return MICRON_ON_DIE_UNSUPPORTED; - ret = micron_nand_on_die_ecc_setup(chip, false); if (ret) return MICRON_ON_DIE_UNSUPPORTED; + if (!(id[4] & MICRON_ID_ECC_ENABLED)) + return MICRON_ON_DIE_UNSUPPORTED; + ret = nand_readid_op(chip, 0, id, sizeof(id)); if (ret) return MICRON_ON_DIE_UNSUPPORTED; From 2d75989d2d92b71f3f34f2704ac109897a87319f Mon Sep 17 00:00:00 2001 From: Vignesh Raghavendra Date: Fri, 19 Jul 2019 13:59:12 +0530 Subject: [PATCH 747/823] mtd: hyperbus: Kconfig: Fix HBMC_AM654 dependencies On x86_64, when CONFIG_OF is not disabled: WARNING: unmet direct dependencies detected for MUX_MMIO Depends on [n]: MULTIPLEXER [=y] && (OF [=n] || COMPILE_TEST [=n]) Selected by [y]: - HBMC_AM654 [=y] && MTD [=y] && MTD_HYPERBUS [=y] due to config HBMC_AM654 tristate "HyperBus controller driver for AM65x SoC" select MULTIPLEXER select MUX_MMIO Fix this by making HBMC_AM654 imply MUX_MMIO instead of select so that dependencies are taken care of. MUX_MMIO is optional for functioning of driver. Fixes: b07079f1642c ("mtd: hyperbus: Add driver for TI's HyperBus memory controller") Reported-by: Randy Dunlap Signed-off-by: Vignesh Raghavendra Acked-by: Randy Dunlap # build-tested Signed-off-by: Miquel Raynal --- drivers/mtd/hyperbus/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/hyperbus/Kconfig b/drivers/mtd/hyperbus/Kconfig index cff6bbd226f5..1c691df8eff7 100644 --- a/drivers/mtd/hyperbus/Kconfig +++ b/drivers/mtd/hyperbus/Kconfig @@ -15,7 +15,7 @@ if MTD_HYPERBUS config HBMC_AM654 tristate "HyperBus controller driver for AM65x SoC" select MULTIPLEXER - select MUX_MMIO + imply MUX_MMIO help This is the driver for HyperBus controller on TI's AM65x and other SoCs From 2b372a9685a757a1d3ab30615ef42b2db7c45298 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Wed, 31 Jul 2019 10:07:06 +0200 Subject: [PATCH 748/823] mtd: hyperbus: Add hardware dependency to AM654 driver The hbmc-am654 driver is for the TI AM654, which is an ARM64 SoC, so don't propose this driver on other architectures unless build-testing. Fixes: b07079f1642c ("mtd: hyperbus: Add driver for TI's HyperBus memory controller") Signed-off-by: Jean Delvare Cc: Vignesh Raghavendra Cc: Miquel Raynal Signed-off-by: Miquel Raynal --- drivers/mtd/hyperbus/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mtd/hyperbus/Kconfig b/drivers/mtd/hyperbus/Kconfig index 1c691df8eff7..b4e3caf7d799 100644 --- a/drivers/mtd/hyperbus/Kconfig +++ b/drivers/mtd/hyperbus/Kconfig @@ -14,6 +14,7 @@ if MTD_HYPERBUS config HBMC_AM654 tristate "HyperBus controller driver for AM65x SoC" + depends on ARM64 || COMPILE_TEST select MULTIPLEXER imply MUX_MMIO help From 685703b497bacea8765bb409d6b73455b73c540e Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 31 Jul 2019 01:25:45 +0000 Subject: [PATCH 749/823] hv_sock: Fix hang when a connection is closed There is a race condition for an established connection that is being closed by the guest: the refcnt is 4 at the end of hvs_release() (Note: here the 'remove_sock' is false): 1 for the initial value; 1 for the sk being in the bound list; 1 for the sk being in the connected list; 1 for the delayed close_work. After hvs_release() finishes, __vsock_release() -> sock_put(sk) *may* decrease the refcnt to 3. Concurrently, hvs_close_connection() runs in another thread: calls vsock_remove_sock() to decrease the refcnt by 2; call sock_put() to decrease the refcnt to 0, and free the sk; next, the "release_sock(sk)" may hang due to use-after-free. In the above, after hvs_release() finishes, if hvs_close_connection() runs faster than "__vsock_release() -> sock_put(sk)", then there is not any issue, because at the beginning of hvs_close_connection(), the refcnt is still 4. The issue can be resolved if an extra reference is taken when the connection is established. Fixes: a9eeb998c28d ("hv_sock: Add support for delayed close") Signed-off-by: Dexuan Cui Reviewed-by: Sunil Muthuswamy Signed-off-by: David S. Miller --- net/vmw_vsock/hyperv_transport.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index f2084e3f7aa4..9d864ebeb7b3 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -312,6 +312,11 @@ static void hvs_close_connection(struct vmbus_channel *chan) lock_sock(sk); hvs_do_close_lock_held(vsock_sk(sk), true); release_sock(sk); + + /* Release the refcnt for the channel that's opened in + * hvs_open_connection(). + */ + sock_put(sk); } static void hvs_open_connection(struct vmbus_channel *chan) @@ -407,6 +412,9 @@ static void hvs_open_connection(struct vmbus_channel *chan) } set_per_channel_state(chan, conn_from_host ? new : sk); + + /* This reference will be dropped by hvs_close_connection(). */ + sock_hold(conn_from_host ? new : sk); vmbus_set_chn_rescind_callback(chan, hvs_close_connection); /* Set the pending send size to max packet size to always get From ea443e5e98b5b74e317ef3d26bcaea54931ccdee Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 30 Jul 2019 22:21:41 -0500 Subject: [PATCH 750/823] atm: iphase: Fix Spectre v1 vulnerability board is controlled by user-space, hence leading to a potential exploitation of the Spectre variant 1 vulnerability. This issue was detected with the help of Smatch: drivers/atm/iphase.c:2765 ia_ioctl() warn: potential spectre issue 'ia_dev' [r] (local cap) drivers/atm/iphase.c:2774 ia_ioctl() warn: possible spectre second half. 'iadev' drivers/atm/iphase.c:2782 ia_ioctl() warn: possible spectre second half. 'iadev' drivers/atm/iphase.c:2816 ia_ioctl() warn: possible spectre second half. 'iadev' drivers/atm/iphase.c:2823 ia_ioctl() warn: possible spectre second half. 'iadev' drivers/atm/iphase.c:2830 ia_ioctl() warn: potential spectre issue '_ia_dev' [r] (local cap) drivers/atm/iphase.c:2845 ia_ioctl() warn: possible spectre second half. 'iadev' drivers/atm/iphase.c:2856 ia_ioctl() warn: possible spectre second half. 'iadev' Fix this by sanitizing board before using it to index ia_dev and _ia_dev Notice that given that speculation windows are large, the policy is to kill the speculation on the first load and not worry if it can be completed with a dependent load/store [1]. [1] https://lore.kernel.org/lkml/20180423164740.GY17484@dhcp22.suse.cz/ Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- drivers/atm/iphase.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c index 302cf0ba1600..8c7a996d1f16 100644 --- a/drivers/atm/iphase.c +++ b/drivers/atm/iphase.c @@ -63,6 +63,7 @@ #include #include #include +#include #include "iphase.h" #include "suni.h" #define swap_byte_order(x) (((x & 0xff) << 8) | ((x & 0xff00) >> 8)) @@ -2760,8 +2761,11 @@ static int ia_ioctl(struct atm_dev *dev, unsigned int cmd, void __user *arg) } if (copy_from_user(&ia_cmds, arg, sizeof ia_cmds)) return -EFAULT; board = ia_cmds.status; - if ((board < 0) || (board > iadev_count)) - board = 0; + + if ((board < 0) || (board > iadev_count)) + board = 0; + board = array_index_nospec(board, iadev_count + 1); + iadev = ia_dev[board]; switch (ia_cmds.cmd) { case MEMDUMP: From 3690c8c9a8edff0db077a38783112d8fe12a7dd2 Mon Sep 17 00:00:00 2001 From: Wang Xiayang Date: Wed, 31 Jul 2019 16:15:42 +0800 Subject: [PATCH 751/823] net/ethernet/qlogic/qed: force the string buffer NULL-terminated strncpy() does not ensure NULL-termination when the input string size equals to the destination buffer size 30. The output string is passed to qed_int_deassertion_aeu_bit() which calls DP_INFO() and relies NULL-termination. Use strlcpy instead. The other conditional branch above strncpy() needs no fix as snprintf() ensures NULL-termination. This issue is identified by a Coccinelle script. Signed-off-by: Wang Xiayang Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_int.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index 4e8118a08654..9f5113639eaf 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -1093,7 +1093,7 @@ static int qed_int_deassertion(struct qed_hwfn *p_hwfn, snprintf(bit_name, 30, p_aeu->bit_name, num); else - strncpy(bit_name, + strlcpy(bit_name, p_aeu->bit_name, 30); /* We now need to pass bitmask in its From 2802d2cf24b1ca7ea4c54dde266ded6a16020eb5 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 1 Aug 2019 09:24:19 +0800 Subject: [PATCH 752/823] enetc: Select PHYLIB while CONFIG_FSL_ENETC_VF is set Like FSL_ENETC, when CONFIG_FSL_ENETC_VF is set, we should select PHYLIB, otherwise building still fails: drivers/net/ethernet/freescale/enetc/enetc.o: In function `enetc_open': enetc.c:(.text+0x2744): undefined reference to `phy_start' enetc.c:(.text+0x282c): undefined reference to `phy_disconnect' drivers/net/ethernet/freescale/enetc/enetc.o: In function `enetc_close': enetc.c:(.text+0x28f8): undefined reference to `phy_stop' enetc.c:(.text+0x2904): undefined reference to `phy_disconnect' drivers/net/ethernet/freescale/enetc/enetc_ethtool.o:(.rodata+0x3f8): undefined reference to `phy_ethtool_get_link_ksettings' drivers/net/ethernet/freescale/enetc/enetc_ethtool.o:(.rodata+0x400): undefined reference to `phy_ethtool_set_link_ksettings' Reported-by: Hulk Robot Fixes: d4fd0404c1c9 ("enetc: Introduce basic PF and VF ENETC ethernet drivers") Signed-off-by: YueHaibing Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/enetc/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig index 46fdf36bfece..04a59db03f2b 100644 --- a/drivers/net/ethernet/freescale/enetc/Kconfig +++ b/drivers/net/ethernet/freescale/enetc/Kconfig @@ -13,6 +13,7 @@ config FSL_ENETC config FSL_ENETC_VF tristate "ENETC VF driver" depends on PCI && PCI_MSI && (ARCH_LAYERSCAPE || COMPILE_TEST) + select PHYLIB help This driver supports NXP ENETC gigabit ethernet controller PCIe virtual function (VF) devices enabled by the ENETC PF driver. From aa6b1956158f1afc52761137620d4b3f8a058d24 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 31 Jul 2019 23:05:10 +0200 Subject: [PATCH 753/823] net: phy: fix race in genphy_update_link In phy_start_aneg() autoneg is started, and immediately after that link and autoneg status are read. As reported in [0] it can happen that at time of this read the PHY has reset the "aneg complete" bit but not yet the "link up" bit, what can result in a false link-up detection. To fix this don't report link as up if we're in aneg mode and PHY doesn't signal "aneg complete". [0] https://marc.info/?t=156413509900003&r=1&w=2 Fixes: 4950c2ba49cc ("net: phy: fix autoneg mismatch case in genphy_read_status") Reported-by: liuyonglong Tested-by: liuyonglong Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 6b5cb87f3866..7ddd91df99e3 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1774,6 +1774,12 @@ done: phydev->link = status & BMSR_LSTATUS ? 1 : 0; phydev->autoneg_complete = status & BMSR_ANEGCOMPLETE ? 1 : 0; + /* Consider the case that autoneg was started and "aneg complete" + * bit has been reset, but "link up" bit not yet. + */ + if (phydev->autoneg == AUTONEG_ENABLE && !phydev->autoneg_complete) + phydev->link = 0; + return 0; } EXPORT_SYMBOL(genphy_update_link); From 59c0b47a1e11b5e81ab1dfd13579c9fbdb02f0b4 Mon Sep 17 00:00:00 2001 From: Kevin Lo Date: Thu, 1 Aug 2019 11:29:38 +0800 Subject: [PATCH 754/823] r8152: fix typo in register name It is likely that PAL_BDC_CR should be PLA_BDC_CR. Signed-off-by: Kevin Lo Acked-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 39e0768d734d..0cc03a9ff545 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -50,7 +50,7 @@ #define PLA_TEREDO_WAKE_BASE 0xc0c4 #define PLA_MAR 0xcd00 #define PLA_BACKUP 0xd000 -#define PAL_BDC_CR 0xd1a0 +#define PLA_BDC_CR 0xd1a0 #define PLA_TEREDO_TIMER 0xd2cc #define PLA_REALWOW_TIMER 0xd2e8 #define PLA_SUSPEND_FLAG 0xd38a @@ -274,7 +274,7 @@ #define TEREDO_RS_EVENT_MASK 0x00fe #define OOB_TEREDO_EN 0x0001 -/* PAL_BDC_CR */ +/* PLA_BDC_CR */ #define ALDPS_PROXY_MODE 0x0001 /* PLA_EFUSE_CMD */ @@ -3191,9 +3191,9 @@ static void r8152b_enter_oob(struct r8152 *tp) rtl_rx_vlan_en(tp, true); - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PAL_BDC_CR); + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_BDC_CR); ocp_data |= ALDPS_PROXY_MODE; - ocp_write_word(tp, MCU_TYPE_PLA, PAL_BDC_CR, ocp_data); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_BDC_CR, ocp_data); ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL); ocp_data |= NOW_IS_OOB | DIS_MCU_CLROOB; @@ -3577,9 +3577,9 @@ static void r8153_enter_oob(struct r8152 *tp) rtl_rx_vlan_en(tp, true); - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PAL_BDC_CR); + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_BDC_CR); ocp_data |= ALDPS_PROXY_MODE; - ocp_write_word(tp, MCU_TYPE_PLA, PAL_BDC_CR, ocp_data); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_BDC_CR, ocp_data); ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL); ocp_data |= NOW_IS_OOB | DIS_MCU_CLROOB; From 68d8681e97bd1c90259f341c1695af05002070ef Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 2 Aug 2019 21:48:33 -0700 Subject: [PATCH 755/823] kernel/signal.c: fix a kernel-doc markup The kernel-doc parser doesn't handle expressions with %foo*. Instead, when an asterisk should be part of a constant, it uses an alternative notation: `foo*`. Link: http://lkml.kernel.org/r/7f18c2e0b5e39e6b7eb55ddeb043b8b260b49f2d.1563361575.git.mchehab+samsung@kernel.org Signed-off-by: Mauro Carvalho Chehab Cc: Deepa Dinamani Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/signal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/signal.c b/kernel/signal.c index 349f5a67f100..e667be6907d7 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -349,7 +349,7 @@ void task_clear_jobctl_pending(struct task_struct *task, unsigned long mask) * @task has %JOBCTL_STOP_PENDING set and is participating in a group stop. * Group stop states are cleared and the group stop count is consumed if * %JOBCTL_STOP_CONSUME was set. If the consumption completes the group - * stop, the appropriate %SIGNAL_* flags are set. + * stop, the appropriate `SIGNAL_*` flags are set. * * CONTEXT: * Must be called with @task->sighand->siglock held. From df9576def004d2cd5beedc00cb6e8901427634b9 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 2 Aug 2019 21:48:37 -0700 Subject: [PATCH 756/823] Revert "kmemleak: allow to coexist with fault injection" When running ltp's oom test with kmemleak enabled, the below warning was triggerred since kernel detects __GFP_NOFAIL & ~__GFP_DIRECT_RECLAIM is passed in: WARNING: CPU: 105 PID: 2138 at mm/page_alloc.c:4608 __alloc_pages_nodemask+0x1c31/0x1d50 Modules linked in: loop dax_pmem dax_pmem_core ip_tables x_tables xfs virtio_net net_failover virtio_blk failover ata_generic virtio_pci virtio_ring virtio libata CPU: 105 PID: 2138 Comm: oom01 Not tainted 5.2.0-next-20190710+ #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.2-0-g5f4c7b1-prebuilt.qemu-project.org 04/01/2014 RIP: 0010:__alloc_pages_nodemask+0x1c31/0x1d50 ... kmemleak_alloc+0x4e/0xb0 kmem_cache_alloc+0x2a7/0x3e0 mempool_alloc_slab+0x2d/0x40 mempool_alloc+0x118/0x2b0 bio_alloc_bioset+0x19d/0x350 get_swap_bio+0x80/0x230 __swap_writepage+0x5ff/0xb20 The mempool_alloc_slab() clears __GFP_DIRECT_RECLAIM, however kmemleak has __GFP_NOFAIL set all the time due to d9570ee3bd1d4f2 ("kmemleak: allow to coexist with fault injection"). But, it doesn't make any sense to have __GFP_NOFAIL and ~__GFP_DIRECT_RECLAIM specified at the same time. According to the discussion on the mailing list, the commit should be reverted for short term solution. Catalin Marinas would follow up with a better solution for longer term. The failure rate of kmemleak metadata allocation may increase in some circumstances, but this should be expected side effect. Link: http://lkml.kernel.org/r/1563299431-111710-1-git-send-email-yang.shi@linux.alibaba.com Fixes: d9570ee3bd1d4f2 ("kmemleak: allow to coexist with fault injection") Signed-off-by: Yang Shi Suggested-by: Catalin Marinas Acked-by: Michal Hocko Cc: Dmitry Vyukov Cc: David Rientjes Cc: Matthew Wilcox Cc: Qian Cai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kmemleak.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index dbbd518fb6b3..6e9e8cca663e 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -114,7 +114,7 @@ /* GFP bitmask for kmemleak internal allocations */ #define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \ __GFP_NORETRY | __GFP_NOMEMALLOC | \ - __GFP_NOWARN | __GFP_NOFAIL) + __GFP_NOWARN) /* scanning area inside a memory block */ struct kmemleak_scan_area { From 7bc36e3ce91471b6377c8eadc0a2f220a2280083 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 2 Aug 2019 21:48:40 -0700 Subject: [PATCH 757/823] ocfs2: remove set but not used variable 'last_hash' Fixes gcc '-Wunused-but-set-variable' warning: fs/ocfs2/xattr.c: In function ocfs2_xattr_bucket_find: fs/ocfs2/xattr.c:3828:6: warning: variable last_hash set but not used [-Wunused-but-set-variable] It's never used and can be removed. Link: http://lkml.kernel.org/r/20190716132110.34836-1-yuehaibing@huawei.com Signed-off-by: YueHaibing Acked-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/xattr.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 385f3aaa2448..90c830e3758e 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -3825,7 +3825,6 @@ static int ocfs2_xattr_bucket_find(struct inode *inode, u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb); int low_bucket = 0, bucket, high_bucket; struct ocfs2_xattr_bucket *search; - u32 last_hash; u64 blkno, lower_blkno = 0; search = ocfs2_xattr_bucket_new(inode); @@ -3869,8 +3868,6 @@ static int ocfs2_xattr_bucket_find(struct inode *inode, if (xh->xh_count) xe = &xh->xh_entries[le16_to_cpu(xh->xh_count) - 1]; - last_hash = le32_to_cpu(xe->xe_name_hash); - /* record lower_blkno which may be the insert place. */ lower_blkno = blkno; From fa1e512fac717f34e7c12d7a384c46e90a647392 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 2 Aug 2019 21:48:44 -0700 Subject: [PATCH 758/823] mm: vmscan: check if mem cgroup is disabled or not before calling memcg slab shrinker Shakeel Butt reported premature oom on kernel with "cgroup_disable=memory" since mem_cgroup_is_root() returns false even though memcg is actually NULL. The drop_caches is also broken. It is because commit aeed1d325d42 ("mm/vmscan.c: generalize shrink_slab() calls in shrink_node()") removed the !memcg check before !mem_cgroup_is_root(). And, surprisingly root memcg is allocated even though memory cgroup is disabled by kernel boot parameter. Add mem_cgroup_disabled() check to make reclaimer work as expected. Link: http://lkml.kernel.org/r/1563385526-20805-1-git-send-email-yang.shi@linux.alibaba.com Fixes: aeed1d325d42 ("mm/vmscan.c: generalize shrink_slab() calls in shrink_node()") Signed-off-by: Yang Shi Reported-by: Shakeel Butt Reviewed-by: Shakeel Butt Reviewed-by: Kirill Tkhai Acked-by: Michal Hocko Cc: Jan Hadrava Cc: Vladimir Davydov Cc: Johannes Weiner Cc: Roman Gushchin Cc: Hugh Dickins Cc: Qian Cai Cc: Kirill A. Shutemov Cc: [4.19+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 44df66a98f2a..dbdc46a84f63 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -699,7 +699,14 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, unsigned long ret, freed = 0; struct shrinker *shrinker; - if (!mem_cgroup_is_root(memcg)) + /* + * The root memcg might be allocated even though memcg is disabled + * via "cgroup_disable=memory" boot parameter. This could make + * mem_cgroup_is_root() return false, then just run memcg slab + * shrink, but skip global shrink. This may result in premature + * oom. + */ + if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); if (!down_read_trylock(&shrinker_rwsem)) From ebdf4de5642fb6580b0763158b6b4b791c4d6a4d Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 2 Aug 2019 21:48:47 -0700 Subject: [PATCH 759/823] mm: migrate: fix reference check race between __find_get_block() and migration buffer_migrate_page_norefs() can race with bh users in the following way: CPU1 CPU2 buffer_migrate_page_norefs() buffer_migrate_lock_buffers() checks bh refs spin_unlock(&mapping->private_lock) __find_get_block() spin_lock(&mapping->private_lock) grab bh ref spin_unlock(&mapping->private_lock) move page do bh work This can result in various issues like lost updates to buffers (i.e. metadata corruption) or use after free issues for the old page. This patch closes the race by holding mapping->private_lock while the mapping is being moved to a new page. Ordinarily, a reference can be taken outside of the private_lock using the per-cpu BH LRU but the references are checked and the LRU invalidated if necessary. The private_lock is held once the references are known so the buffer lookup slow path will spin on the private_lock. Between the page lock and private_lock, it should be impossible for other references to be acquired and updates to happen during the migration. A user had reported data corruption issues on a distribution kernel with a similar page migration implementation as mainline. The data corruption could not be reproduced with this patch applied. A small number of migration-intensive tests were run and no performance problems were noted. [mgorman@techsingularity.net: Changelog, removed tracing] Link: http://lkml.kernel.org/r/20190718090238.GF24383@techsingularity.net Fixes: 89cb0888ca14 "mm: migrate: provide buffer_migrate_page_norefs()" Signed-off-by: Jan Kara Signed-off-by: Mel Gorman Cc: [5.0+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/mm/migrate.c b/mm/migrate.c index 8992741f10aa..515718392b24 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -767,12 +767,12 @@ recheck_buffers: } bh = bh->b_this_page; } while (bh != head); - spin_unlock(&mapping->private_lock); if (busy) { if (invalidated) { rc = -EAGAIN; goto unlock_buffers; } + spin_unlock(&mapping->private_lock); invalidate_bh_lrus(); invalidated = true; goto recheck_buffers; @@ -805,6 +805,8 @@ recheck_buffers: rc = MIGRATEPAGE_SUCCESS; unlock_buffers: + if (check_refs) + spin_unlock(&mapping->private_lock); bh = head; do { unlock_buffer(bh); From 670105a25608affe01cb0ccdc2a1f4bd2327172b Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 2 Aug 2019 21:48:51 -0700 Subject: [PATCH 760/823] mm: compaction: avoid 100% CPU usage during compaction when a task is killed "howaboutsynergy" reported via kernel buzilla number 204165 that compact_zone_order was consuming 100% CPU during a stress test for prolonged periods of time. Specifically the following command, which should exit in 10 seconds, was taking an excessive time to finish while the CPU was pegged at 100%. stress -m 220 --vm-bytes 1000000000 --timeout 10 Tracing indicated a pattern as follows stress-3923 [007] 519.106208: mm_compaction_isolate_migratepages: range=(0x70bb80 ~ 0x70bb80) nr_scanned=0 nr_taken=0 stress-3923 [007] 519.106212: mm_compaction_isolate_migratepages: range=(0x70bb80 ~ 0x70bb80) nr_scanned=0 nr_taken=0 stress-3923 [007] 519.106216: mm_compaction_isolate_migratepages: range=(0x70bb80 ~ 0x70bb80) nr_scanned=0 nr_taken=0 stress-3923 [007] 519.106219: mm_compaction_isolate_migratepages: range=(0x70bb80 ~ 0x70bb80) nr_scanned=0 nr_taken=0 stress-3923 [007] 519.106223: mm_compaction_isolate_migratepages: range=(0x70bb80 ~ 0x70bb80) nr_scanned=0 nr_taken=0 stress-3923 [007] 519.106227: mm_compaction_isolate_migratepages: range=(0x70bb80 ~ 0x70bb80) nr_scanned=0 nr_taken=0 stress-3923 [007] 519.106231: mm_compaction_isolate_migratepages: range=(0x70bb80 ~ 0x70bb80) nr_scanned=0 nr_taken=0 stress-3923 [007] 519.106235: mm_compaction_isolate_migratepages: range=(0x70bb80 ~ 0x70bb80) nr_scanned=0 nr_taken=0 stress-3923 [007] 519.106238: mm_compaction_isolate_migratepages: range=(0x70bb80 ~ 0x70bb80) nr_scanned=0 nr_taken=0 stress-3923 [007] 519.106242: mm_compaction_isolate_migratepages: range=(0x70bb80 ~ 0x70bb80) nr_scanned=0 nr_taken=0 Note that compaction is entered in rapid succession while scanning and isolating nothing. The problem is that when a task that is compacting receives a fatal signal, it retries indefinitely instead of exiting while making no progress as a fatal signal is pending. It's not easy to trigger this condition although enabling zswap helps on the basis that the timing is altered. A very small window has to be hit for the problem to occur (signal delivered while compacting and isolating a PFN for migration that is not aligned to SWAP_CLUSTER_MAX). This was reproduced locally -- 16G single socket system, 8G swap, 30% zswap configured, vm-bytes 22000000000 using Colin Kings stress-ng implementation from github running in a loop until the problem hits). Tracing recorded the problem occurring almost 200K times in a short window. With this patch, the problem hit 4 times but the task existed normally instead of consuming CPU. This problem has existed for some time but it was made worse by commit cf66f0700c8f ("mm, compaction: do not consider a need to reschedule as contention"). Before that commit, if the same condition was hit then locks would be quickly contended and compaction would exit that way. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=204165 Link: http://lkml.kernel.org/r/20190718085708.GE24383@techsingularity.net Fixes: cf66f0700c8f ("mm, compaction: do not consider a need to reschedule as contention") Signed-off-by: Mel Gorman Reviewed-by: Vlastimil Babka Cc: [5.1+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/compaction.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/mm/compaction.c b/mm/compaction.c index 9e1b9acb116b..952dc2fb24e5 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -842,13 +842,15 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, /* * Periodically drop the lock (if held) regardless of its - * contention, to give chance to IRQs. Abort async compaction - * if contended. + * contention, to give chance to IRQs. Abort completely if + * a fatal signal is pending. */ if (!(low_pfn % SWAP_CLUSTER_MAX) && compact_unlock_should_abort(&pgdat->lru_lock, - flags, &locked, cc)) - break; + flags, &locked, cc)) { + low_pfn = 0; + goto fatal_pending; + } if (!pfn_valid_within(low_pfn)) goto isolate_fail; @@ -1060,6 +1062,7 @@ isolate_abort: trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn, nr_scanned, nr_isolated); +fatal_pending: cc->total_migrate_scanned += nr_scanned; if (nr_isolated) count_compact_events(COMPACTISOLATED, nr_isolated); From ebb6d35a74ce21ce1673b8f404c1039d5a1e7e2d Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 2 Aug 2019 21:48:54 -0700 Subject: [PATCH 761/823] kasan: remove clang version check for KASAN_STACK asan-stack mode still uses dangerously large kernel stacks of tens of kilobytes in some drivers, and it does not seem that anyone is working on the clang bug. Turn it off for all clang versions to prevent users from accidentally enabling it once they update to clang-9, and to help automated build testing with clang-9. Link: https://bugs.llvm.org/show_bug.cgi?id=38809 Link: http://lkml.kernel.org/r/20190719200347.2596375-1-arnd@arndb.de Fixes: 6baec880d7a5 ("kasan: turn off asan-stack for clang-8 and earlier") Signed-off-by: Arnd Bergmann Acked-by: Nick Desaulniers Reviewed-by: Mark Brown Reviewed-by: Andrey Ryabinin Cc: Qian Cai Cc: Andrey Konovalov Cc: Vasily Gorbik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Kconfig.kasan | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index 4fafba1a923b..7fa97a8b5717 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -106,7 +106,6 @@ endchoice config KASAN_STACK_ENABLE bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST - default !(CLANG_VERSION < 90000) depends on KASAN help The LLVM stack address sanitizer has a know problem that @@ -115,11 +114,11 @@ config KASAN_STACK_ENABLE Disabling asan-stack makes it safe to run kernels build with clang-8 with KASAN enabled, though it loses some of the functionality. - This feature is always disabled when compile-testing with clang-8 - or earlier to avoid cluttering the output in stack overflow - warnings, but clang-8 users can still enable it for builds without - CONFIG_COMPILE_TEST. On gcc and later clang versions it is - assumed to always be safe to use and enabled by default. + This feature is always disabled when compile-testing with clang + to avoid cluttering the output in stack overflow warnings, + but clang users can still enable it for builds without + CONFIG_COMPILE_TEST. On gcc it is assumed to always be safe + to use and enabled by default. config KASAN_STACK int From af700eaed0564d5d3963a7a51cb0843629d7fe3d Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 2 Aug 2019 21:48:58 -0700 Subject: [PATCH 762/823] ubsan: build ubsan.c more conservatively objtool points out several conditions that it does not like, depending on the combination with other configuration options and compiler variants: stack protector: lib/ubsan.o: warning: objtool: __ubsan_handle_type_mismatch()+0xbf: call to __stack_chk_fail() with UACCESS enabled lib/ubsan.o: warning: objtool: __ubsan_handle_type_mismatch_v1()+0xbe: call to __stack_chk_fail() with UACCESS enabled stackleak plugin: lib/ubsan.o: warning: objtool: __ubsan_handle_type_mismatch()+0x4a: call to stackleak_track_stack() with UACCESS enabled lib/ubsan.o: warning: objtool: __ubsan_handle_type_mismatch_v1()+0x4a: call to stackleak_track_stack() with UACCESS enabled kasan: lib/ubsan.o: warning: objtool: __ubsan_handle_type_mismatch()+0x25: call to memcpy() with UACCESS enabled lib/ubsan.o: warning: objtool: __ubsan_handle_type_mismatch_v1()+0x25: call to memcpy() with UACCESS enabled The stackleak and kasan options just need to be disabled for this file as we do for other files already. For the stack protector, we already attempt to disable it, but this fails on clang because the check is mixed with the gcc specific -fno-conserve-stack option. According to Andrey Ryabinin, that option is not even needed, dropping it here fixes the stackprotector issue. Link: http://lkml.kernel.org/r/20190722125139.1335385-1-arnd@arndb.de Link: https://lore.kernel.org/lkml/20190617123109.667090-1-arnd@arndb.de/t/ Link: https://lore.kernel.org/lkml/20190722091050.2188664-1-arnd@arndb.de/t/ Fixes: d08965a27e84 ("x86/uaccess, ubsan: Fix UBSAN vs. SMAP") Signed-off-by: Arnd Bergmann Reviewed-by: Andrey Ryabinin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Dmitry Vyukov Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Kees Cook Cc: Matthew Wilcox Cc: Ard Biesheuvel Cc: Andy Shevchenko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/lib/Makefile b/lib/Makefile index 095601ce371d..29c02a924973 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -279,7 +279,8 @@ obj-$(CONFIG_UCS2_STRING) += ucs2_string.o obj-$(CONFIG_UBSAN) += ubsan.o UBSAN_SANITIZE_ubsan.o := n -CFLAGS_ubsan.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) +KASAN_SANITIZE_ubsan.o := n +CFLAGS_ubsan.o := $(call cc-option, -fno-stack-protector) $(DISABLE_STACKLEAK_PLUGIN) obj-$(CONFIG_SBITMAP) += sbitmap.o From ee38d94a0ad89890b770f6c876263cf9fcbfde84 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 2 Aug 2019 21:49:02 -0700 Subject: [PATCH 763/823] page flags: prioritize kasan bits over last-cpuid ARM64 randdconfig builds regularly run into a build error, especially when NUMA_BALANCING and SPARSEMEM are enabled but not SPARSEMEM_VMEMMAP: #error "KASAN: not enough bits in page flags for tag" The last-cpuid bits are already contitional on the available space, so the result of the calculation is a bit random on whether they were already left out or not. Adding the kasan tag bits before last-cpuid makes it much more likely to end up with a successful build here, and should be reliable for randconfig at least, as long as that does not randomize NR_CPUS or NODES_SHIFT but uses the defaults. In order for the modified check to not trigger in the x86 vdso32 code where all constants are wrong (building with -m32), enclose all the definitions with an #ifdef. [arnd@arndb.de: build fix] Link: http://lkml.kernel.org/r/CAK8P3a3Mno1SWTcuAOT0Wa9VS15pdU6EfnkxLbDpyS55yO04+g@mail.gmail.com Link: http://lkml.kernel.org/r/20190722115520.3743282-1-arnd@arndb.de Link: https://lore.kernel.org/lkml/20190618095347.3850490-1-arnd@arndb.de/ Fixes: 2813b9c02962 ("kasan, mm, arm64: tag non slab memory allocated via pagealloc") Signed-off-by: Arnd Bergmann Signed-off-by: Arnd Bergmann Reviewed-by: Andrey Konovalov Reviewed-by: Andrey Ryabinin Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Will Deacon Cc: Christoph Lameter Cc: Mark Rutland Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/vdso/vdso.h | 1 + include/linux/page-flags-layout.h | 18 +++++++++++------- 2 files changed, 12 insertions(+), 7 deletions(-) diff --git a/arch/mips/vdso/vdso.h b/arch/mips/vdso/vdso.h index 14b1931be69c..b65b169778e3 100644 --- a/arch/mips/vdso/vdso.h +++ b/arch/mips/vdso/vdso.h @@ -9,6 +9,7 @@ #if _MIPS_SIM != _MIPS_SIM_ABI64 && defined(CONFIG_64BIT) /* Building 32-bit VDSO for the 64-bit kernel. Fake a 32-bit Kconfig. */ +#define BUILD_VDSO32_64 #undef CONFIG_64BIT #define CONFIG_32BIT 1 #ifndef __ASSEMBLY__ diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h index 1dda31825ec4..71283739ffd2 100644 --- a/include/linux/page-flags-layout.h +++ b/include/linux/page-flags-layout.h @@ -32,6 +32,7 @@ #endif /* CONFIG_SPARSEMEM */ +#ifndef BUILD_VDSO32_64 /* * page->flags layout: * @@ -76,20 +77,22 @@ #define LAST_CPUPID_SHIFT 0 #endif -#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_CPUPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS +#ifdef CONFIG_KASAN_SW_TAGS +#define KASAN_TAG_WIDTH 8 +#else +#define KASAN_TAG_WIDTH 0 +#endif + +#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_CPUPID_SHIFT+KASAN_TAG_WIDTH \ + <= BITS_PER_LONG - NR_PAGEFLAGS #define LAST_CPUPID_WIDTH LAST_CPUPID_SHIFT #else #define LAST_CPUPID_WIDTH 0 #endif -#ifdef CONFIG_KASAN_SW_TAGS -#define KASAN_TAG_WIDTH 8 #if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH+LAST_CPUPID_WIDTH+KASAN_TAG_WIDTH \ > BITS_PER_LONG - NR_PAGEFLAGS -#error "KASAN: not enough bits in page flags for tag" -#endif -#else -#define KASAN_TAG_WIDTH 0 +#error "Not enough bits in page flags" #endif /* @@ -104,4 +107,5 @@ #define LAST_CPUPID_NOT_IN_PAGE_FLAGS #endif +#endif #endif /* _LINUX_PAGE_FLAGS_LAYOUT */ From 315c69261dd3fa12dbc830d4fa00d1fad98d3b03 Mon Sep 17 00:00:00 2001 From: Paul Wise Date: Fri, 2 Aug 2019 21:49:05 -0700 Subject: [PATCH 764/823] coredump: split pipe command whitespace before expanding template Save the offsets of the start of each argument to avoid having to update pointers to each argument after every corename krealloc and to avoid having to duplicate the memory for the dump command. Executable names containing spaces were previously being expanded from %e or %E and then split in the middle of the filename. This is incorrect behaviour since an argument list can represent arguments with spaces. The splitting could lead to extra arguments being passed to the core dump handler that it might have interpreted as options or ignored completely. Core dump handlers that are not aware of this Linux kernel issue will be using %e or %E without considering that it may be split and so they will be vulnerable to processes with spaces in their names breaking their argument list. If their internals are otherwise well written, such as if they are written in shell but quote arguments, they will work better after this change than before. If they are not well written, then there is a slight chance of breakage depending on the details of the code but they will already be fairly broken by the split filenames. Core dump handlers that are aware of this Linux kernel issue will be placing %e or %E as the last item in their core_pattern and then aggregating all of the remaining arguments into one, separated by spaces. Alternatively they will be obtaining the filename via other methods. Both of these will be compatible with the new arrangement. A side effect from this change is that unknown template types (for example %z) result in an empty argument to the dump handler instead of the argument being dropped. This is a desired change as: It is easier for dump handlers to process empty arguments than dropped ones, especially if they are written in shell or don't pass each template item with a preceding command-line option in order to differentiate between individual template types. Most core_patterns in the wild do not use options so they can confuse different template types (especially numeric ones) if an earlier one gets dropped in old kernels. If the kernel introduces a new template type and a core_pattern uses it, the core dump handler might not expect that the argument can be dropped in old kernels. For example, this can result in security issues when %d is dropped in old kernels. This happened with the corekeeper package in Debian and resulted in the interface between corekeeper and Linux having to be rewritten to use command-line options to differentiate between template types. The core_pattern for most core dump handlers is written by the handler author who would generally not insert unknown template types so this change should be compatible with all the core dump handlers that exist. Link: http://lkml.kernel.org/r/20190528051142.24939-1-pabs3@bonedaddy.net Fixes: 74aadce98605 ("core_pattern: allow passing of arguments to user mode helper when core_pattern is a pipe") Signed-off-by: Paul Wise Reported-by: Jakub Wilk [https://bugs.debian.org/924398] Reported-by: Paul Wise [https://lore.kernel.org/linux-fsdevel/c8b7ecb8508895bf4adb62a748e2ea2c71854597.camel@bonedaddy.net/] Suggested-by: Jakub Wilk Acked-by: Neil Horman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/coredump.c | 44 +++++++++++++++++++++++++++++++++++++++----- 1 file changed, 39 insertions(+), 5 deletions(-) diff --git a/fs/coredump.c b/fs/coredump.c index e42e17e55bfd..b1ea7dfbd149 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -187,11 +188,13 @@ put_exe_file: * name into corename, which must have space for at least * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator. */ -static int format_corename(struct core_name *cn, struct coredump_params *cprm) +static int format_corename(struct core_name *cn, struct coredump_params *cprm, + size_t **argv, int *argc) { const struct cred *cred = current_cred(); const char *pat_ptr = core_pattern; int ispipe = (*pat_ptr == '|'); + bool was_space = false; int pid_in_pattern = 0; int err = 0; @@ -201,12 +204,35 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm) return -ENOMEM; cn->corename[0] = '\0'; - if (ispipe) + if (ispipe) { + int argvs = sizeof(core_pattern) / 2; + (*argv) = kmalloc_array(argvs, sizeof(**argv), GFP_KERNEL); + if (!(*argv)) + return -ENOMEM; + (*argv)[(*argc)++] = 0; ++pat_ptr; + } /* Repeat as long as we have more pattern to process and more output space */ while (*pat_ptr) { + /* + * Split on spaces before doing template expansion so that + * %e and %E don't get split if they have spaces in them + */ + if (ispipe) { + if (isspace(*pat_ptr)) { + was_space = true; + pat_ptr++; + continue; + } else if (was_space) { + was_space = false; + err = cn_printf(cn, "%c", '\0'); + if (err) + return err; + (*argv)[(*argc)++] = cn->used; + } + } if (*pat_ptr != '%') { err = cn_printf(cn, "%c", *pat_ptr++); } else { @@ -546,6 +572,8 @@ void do_coredump(const kernel_siginfo_t *siginfo) struct cred *cred; int retval = 0; int ispipe; + size_t *argv = NULL; + int argc = 0; struct files_struct *displaced; /* require nonrelative corefile path and be extra careful */ bool need_suid_safe = false; @@ -592,9 +620,10 @@ void do_coredump(const kernel_siginfo_t *siginfo) old_cred = override_creds(cred); - ispipe = format_corename(&cn, &cprm); + ispipe = format_corename(&cn, &cprm, &argv, &argc); if (ispipe) { + int argi; int dump_count; char **helper_argv; struct subprocess_info *sub_info; @@ -637,12 +666,16 @@ void do_coredump(const kernel_siginfo_t *siginfo) goto fail_dropcount; } - helper_argv = argv_split(GFP_KERNEL, cn.corename, NULL); + helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv), + GFP_KERNEL); if (!helper_argv) { printk(KERN_WARNING "%s failed to allocate memory\n", __func__); goto fail_dropcount; } + for (argi = 0; argi < argc; argi++) + helper_argv[argi] = cn.corename + argv[argi]; + helper_argv[argi] = NULL; retval = -ENOMEM; sub_info = call_usermodehelper_setup(helper_argv[0], @@ -652,7 +685,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) retval = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC); - argv_free(helper_argv); + kfree(helper_argv); if (retval) { printk(KERN_INFO "Core dump to |%s pipe failed\n", cn.corename); @@ -766,6 +799,7 @@ fail_dropcount: if (ispipe) atomic_dec(&core_dump_count); fail_unlock: + kfree(argv); kfree(cn.corename); coredump_finish(mm, core_dumped); revert_creds(old_cred); From 7b358c6f12dc82364f6d317f8c8f1d794adbc3f5 Mon Sep 17 00:00:00 2001 From: Ralph Campbell Date: Fri, 2 Aug 2019 21:49:08 -0700 Subject: [PATCH 765/823] mm/migrate.c: initialize pud_entry in migrate_vma() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When CONFIG_MIGRATE_VMA_HELPER is enabled, migrate_vma() calls migrate_vma_collect() which initializes a struct mm_walk but didn't initialize mm_walk.pud_entry. (Found by code inspection) Use a C structure initialization to make sure it is set to NULL. Link: http://lkml.kernel.org/r/20190719233225.12243-1-rcampbell@nvidia.com Fixes: 8763cb45ab967 ("mm/migrate: new memory migration helper for use with device memory") Signed-off-by: Ralph Campbell Reviewed-by: John Hubbard Reviewed-by: Andrew Morton Cc: "Jérôme Glisse" Cc: Mel Gorman Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/mm/migrate.c b/mm/migrate.c index 515718392b24..a42858d8e00b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2340,16 +2340,13 @@ next: static void migrate_vma_collect(struct migrate_vma *migrate) { struct mmu_notifier_range range; - struct mm_walk mm_walk; - - mm_walk.pmd_entry = migrate_vma_collect_pmd; - mm_walk.pte_entry = NULL; - mm_walk.pte_hole = migrate_vma_collect_hole; - mm_walk.hugetlb_entry = NULL; - mm_walk.test_walk = NULL; - mm_walk.vma = migrate->vma; - mm_walk.mm = migrate->vma->vm_mm; - mm_walk.private = migrate; + struct mm_walk mm_walk = { + .pmd_entry = migrate_vma_collect_pmd, + .pte_hole = migrate_vma_collect_hole, + .vma = migrate->vma, + .mm = migrate->vma->vm_mm, + .private = migrate, + }; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm_walk.mm, migrate->start, From aa4996b3af19f8535177ba21cb7241348a34fb94 Mon Sep 17 00:00:00 2001 From: Weitao Hou Date: Fri, 2 Aug 2019 21:49:12 -0700 Subject: [PATCH 766/823] mm/memory_hotplug.c: remove unneeded return for void function return is unneeded in void function Link: http://lkml.kernel.org/r/20190723130814.21826-1-houweitaoo@gmail.com Signed-off-by: Weitao Hou Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 2a9bbddb0e55..c73f09913165 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -132,7 +132,6 @@ static void release_memory_resource(struct resource *res) return; release_resource(res); kfree(res); - return; } #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE @@ -979,7 +978,6 @@ static void rollback_node_hotadd(int nid) arch_refresh_nodedata(nid, NULL); free_percpu(pgdat->per_cpu_nodestats); arch_free_nodedata(pgdat); - return; } From b59b1baab789eacdde809135542e3d4f256f6878 Mon Sep 17 00:00:00 2001 From: Chris Down Date: Fri, 2 Aug 2019 21:49:15 -0700 Subject: [PATCH 767/823] cgroup: kselftest: relax fs_spec checks On my laptop most memcg kselftests were being skipped because it claimed cgroup v2 hierarchy wasn't mounted, but this isn't correct. Instead, it seems current systemd HEAD mounts it with the name "cgroup2" instead of "cgroup": % grep cgroup /proc/mounts cgroup2 /sys/fs/cgroup cgroup2 rw,nosuid,nodev,noexec,relatime,nsdelegate 0 0 I can't think of a reason to need to check fs_spec explicitly since it's arbitrary, so we can just rely on fs_vfstype. After these changes, `make TARGETS=cgroup kselftest` actually runs the cgroup v2 tests in more cases. Link: http://lkml.kernel.org/r/20190723210737.GA487@chrisdown.name Signed-off-by: Chris Down Cc: Johannes Weiner Cc: Tejun Heo Cc: Roman Gushchin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/cgroup/cgroup_util.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c index 4c223266299a..bdb69599c4bd 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.c +++ b/tools/testing/selftests/cgroup/cgroup_util.c @@ -191,8 +191,7 @@ int cg_find_unified_root(char *root, size_t len) strtok(NULL, delim); strtok(NULL, delim); - if (strcmp(fs, "cgroup") == 0 && - strcmp(type, "cgroup2") == 0) { + if (strcmp(type, "cgroup2") == 0) { strncpy(root, mount, len); return 0; } From cbedfe11347fe418621bd188d58a206beb676218 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 2 Aug 2019 21:49:19 -0700 Subject: [PATCH 768/823] asm-generic: fix -Wtype-limits compiler warnings Commit d66acc39c7ce ("bitops: Optimise get_order()") introduced a compilation warning because "rx_frag_size" is an "ushort" while PAGE_SHIFT here is 16. The commit changed the get_order() to be a multi-line macro where compilers insist to check all statements in the macro even when __builtin_constant_p(rx_frag_size) will return false as "rx_frag_size" is a module parameter. In file included from ./arch/powerpc/include/asm/page_64.h:107, from ./arch/powerpc/include/asm/page.h:242, from ./arch/powerpc/include/asm/mmu.h:132, from ./arch/powerpc/include/asm/lppaca.h:47, from ./arch/powerpc/include/asm/paca.h:17, from ./arch/powerpc/include/asm/current.h:13, from ./include/linux/thread_info.h:21, from ./arch/powerpc/include/asm/processor.h:39, from ./include/linux/prefetch.h:15, from drivers/net/ethernet/emulex/benet/be_main.c:14: drivers/net/ethernet/emulex/benet/be_main.c: In function 'be_rx_cqs_create': ./include/asm-generic/getorder.h:54:9: warning: comparison is always true due to limited range of data type [-Wtype-limits] (((n) < (1UL << PAGE_SHIFT)) ? 0 : \ ^ drivers/net/ethernet/emulex/benet/be_main.c:3138:33: note: in expansion of macro 'get_order' adapter->big_page_size = (1 << get_order(rx_frag_size)) * PAGE_SIZE; ^~~~~~~~~ Fix it by moving all of this multi-line macro into a proper function, and killing __get_order() off. [akpm@linux-foundation.org: remove __get_order() altogether] [cai@lca.pw: v2] Link: http://lkml.kernel.org/r/1564000166-31428-1-git-send-email-cai@lca.pw Link: http://lkml.kernel.org/r/1563914986-26502-1-git-send-email-cai@lca.pw Fixes: d66acc39c7ce ("bitops: Optimise get_order()") Signed-off-by: Qian Cai Reviewed-by: Nathan Chancellor Cc: David S. Miller Cc: Arnd Bergmann Cc: David Howells Cc: Jakub Jelinek Cc: Nick Desaulniers Cc: Bill Wendling Cc: James Y Knight Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/getorder.h | 50 ++++++++++++++-------------------- 1 file changed, 20 insertions(+), 30 deletions(-) diff --git a/include/asm-generic/getorder.h b/include/asm-generic/getorder.h index c64bea7a52be..e9f20b813a69 100644 --- a/include/asm-generic/getorder.h +++ b/include/asm-generic/getorder.h @@ -7,24 +7,6 @@ #include #include -/* - * Runtime evaluation of get_order() - */ -static inline __attribute_const__ -int __get_order(unsigned long size) -{ - int order; - - size--; - size >>= PAGE_SHIFT; -#if BITS_PER_LONG == 32 - order = fls(size); -#else - order = fls64(size); -#endif - return order; -} - /** * get_order - Determine the allocation order of a memory size * @size: The size for which to get the order @@ -43,19 +25,27 @@ int __get_order(unsigned long size) * to hold an object of the specified size. * * The result is undefined if the size is 0. - * - * This function may be used to initialise variables with compile time - * evaluations of constants. */ -#define get_order(n) \ -( \ - __builtin_constant_p(n) ? ( \ - ((n) == 0UL) ? BITS_PER_LONG - PAGE_SHIFT : \ - (((n) < (1UL << PAGE_SHIFT)) ? 0 : \ - ilog2((n) - 1) - PAGE_SHIFT + 1) \ - ) : \ - __get_order(n) \ -) +static inline __attribute_const__ int get_order(unsigned long size) +{ + if (__builtin_constant_p(size)) { + if (!size) + return BITS_PER_LONG - PAGE_SHIFT; + + if (size < (1UL << PAGE_SHIFT)) + return 0; + + return ilog2((size) - 1) - PAGE_SHIFT + 1; + } + + size--; + size >>= PAGE_SHIFT; +#if BITS_PER_LONG == 32 + return fls(size); +#else + return fls64(size); +#endif +} #endif /* __ASSEMBLY__ */ From 733d1d1a7745113e2b6a1761300e7e26b6eb6009 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 2 Aug 2019 21:49:22 -0700 Subject: [PATCH 769/823] lib/test_meminit.c: use GFP_ATOMIC in RCU critical section kmalloc() shouldn't sleep while in RCU critical section, therefore use GFP_ATOMIC instead of GFP_KERNEL. The bug was spotted by the 0day kernel testing robot. Link: http://lkml.kernel.org/r/20190725121703.210874-1-glider@google.com Fixes: 7e659650cbda ("lib: introduce test_meminit module") Signed-off-by: Alexander Potapenko Reviewed-by: Andrew Morton Reported-by: kernel test robot Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_meminit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/test_meminit.c b/lib/test_meminit.c index 62d19f270cad..9729f271d150 100644 --- a/lib/test_meminit.c +++ b/lib/test_meminit.c @@ -222,7 +222,7 @@ static int __init do_kmem_cache_size(size_t size, bool want_ctor, * Copy the buffer to check that it's not wiped on * free(). */ - buf_copy = kmalloc(size, GFP_KERNEL); + buf_copy = kmalloc(size, GFP_ATOMIC); if (buf_copy) memcpy(buf_copy, buf, size); From 14c5cebad510c2875ca525f36605b47058769670 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 2 Aug 2019 21:49:26 -0700 Subject: [PATCH 770/823] memremap: move from kernel/ to mm/ memremap.c implements MM functionality for ZONE_DEVICE, so it really should be in the mm/ directory, not the kernel/ one. Link: http://lkml.kernel.org/r/20190722094143.18387-1-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Anshuman Khandual Acked-by: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/Makefile | 1 - mm/Makefile | 1 + {kernel => mm}/memremap.c | 0 3 files changed, 1 insertion(+), 1 deletion(-) rename {kernel => mm}/memremap.c (100%) diff --git a/kernel/Makefile b/kernel/Makefile index a8d923b5481b..ef0d95a190b4 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -111,7 +111,6 @@ obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o obj-$(CONFIG_TORTURE_TEST) += torture.o obj-$(CONFIG_HAS_IOMEM) += iomem.o -obj-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_RSEQ) += rseq.o obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o diff --git a/mm/Makefile b/mm/Makefile index 338e528ad436..d0b295c3b764 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -102,5 +102,6 @@ obj-$(CONFIG_FRAME_VECTOR) += frame_vector.o obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o +obj-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_HMM_MIRROR) += hmm.o obj-$(CONFIG_MEMFD_CREATE) += memfd.o diff --git a/kernel/memremap.c b/mm/memremap.c similarity index 100% rename from kernel/memremap.c rename to mm/memremap.c From 7291edca20215dfdf0eb841881d63753448ef09c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 2 Aug 2019 21:49:29 -0700 Subject: [PATCH 771/823] drivers/acpi/scan.c: document why we don't need the device_hotplug_lock Let's document why the lock is not needed in acpi_scan_init(), right now this is not really obvious. [akpm@linux-foundation.org: fix tpyo] Link: http://lkml.kernel.org/r/20190731135306.31524-1-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Michal Hocko Acked-by: Rafael J. Wysocki Cc: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/acpi/scan.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 0e28270b0fd8..aad6be5c0af0 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2204,6 +2204,12 @@ int __init acpi_scan_init(void) acpi_gpe_apply_masked_gpes(); acpi_update_all_gpes(); + /* + * Although we call __add_memory() that is documented to require the + * device_hotplug_lock, it is not necessary here because this is an + * early code when userspace or any other code path cannot trigger + * hotplug/hotunplug operations. + */ mutex_lock(&acpi_scan_lock); /* * Enumerate devices in the ACPI namespace. From 5e5412c365a32e452daa762eac36121cb8a370bb Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Tue, 30 Jul 2019 11:30:33 -0400 Subject: [PATCH 772/823] net/socket: fix GCC8+ Wpacked-not-aligned warnings There are a lot of those warnings with GCC8+ 64-bit, In file included from ./include/linux/sctp.h:42, from net/core/skbuff.c:47: ./include/uapi/linux/sctp.h:395:1: warning: alignment 4 of 'struct sctp_paddr_change' is less than 8 [-Wpacked-not-aligned] } __attribute__((packed, aligned(4))); ^ ./include/uapi/linux/sctp.h:728:1: warning: alignment 4 of 'struct sctp_setpeerprim' is less than 8 [-Wpacked-not-aligned] } __attribute__((packed, aligned(4))); ^ ./include/uapi/linux/sctp.h:727:26: warning: 'sspp_addr' offset 4 in 'struct sctp_setpeerprim' isn't aligned to 8 [-Wpacked-not-aligned] struct sockaddr_storage sspp_addr; ^~~~~~~~~ ./include/uapi/linux/sctp.h:741:1: warning: alignment 4 of 'struct sctp_prim' is less than 8 [-Wpacked-not-aligned] } __attribute__((packed, aligned(4))); ^ ./include/uapi/linux/sctp.h:740:26: warning: 'ssp_addr' offset 4 in 'struct sctp_prim' isn't aligned to 8 [-Wpacked-not-aligned] struct sockaddr_storage ssp_addr; ^~~~~~~~ ./include/uapi/linux/sctp.h:792:1: warning: alignment 4 of 'struct sctp_paddrparams' is less than 8 [-Wpacked-not-aligned] } __attribute__((packed, aligned(4))); ^ ./include/uapi/linux/sctp.h:784:26: warning: 'spp_address' offset 4 in 'struct sctp_paddrparams' isn't aligned to 8 [-Wpacked-not-aligned] struct sockaddr_storage spp_address; ^~~~~~~~~~~ ./include/uapi/linux/sctp.h:905:1: warning: alignment 4 of 'struct sctp_paddrinfo' is less than 8 [-Wpacked-not-aligned] } __attribute__((packed, aligned(4))); ^ ./include/uapi/linux/sctp.h:899:26: warning: 'spinfo_address' offset 4 in 'struct sctp_paddrinfo' isn't aligned to 8 [-Wpacked-not-aligned] struct sockaddr_storage spinfo_address; ^~~~~~~~~~~~~~ This is because the commit 20c9c825b12f ("[SCTP] Fix SCTP socket options to work with 32-bit apps on 64-bit kernels.") added "packed, aligned(4)" GCC attributes to some structures but one of the members, i.e, "struct sockaddr_storage" in those structures has the attribute, "aligned(__alignof__ (struct sockaddr *)" which is 8-byte on 64-bit systems, so the commit overwrites the designed alignments for "sockaddr_storage". To fix this, "struct sockaddr_storage" needs to be aligned to 4-byte as it is only used in those packed sctp structure which is part of UAPI, and "struct __kernel_sockaddr_storage" is used in some other places of UAPI that need not to change alignments in order to not breaking userspace. Use an implicit alignment for "struct __kernel_sockaddr_storage" so it can keep the same alignments as a member in both packed and un-packed structures without breaking UAPI. Suggested-by: David Laight Signed-off-by: Qian Cai Signed-off-by: David S. Miller --- include/uapi/linux/socket.h | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index 8eb96021709c..c3409c8ec0dd 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -6,17 +6,24 @@ * Desired design of maximum size and alignment (see RFC2553) */ #define _K_SS_MAXSIZE 128 /* Implementation specific max size */ -#define _K_SS_ALIGNSIZE (__alignof__ (struct sockaddr *)) - /* Implementation specific desired alignment */ typedef unsigned short __kernel_sa_family_t; +/* + * The definition uses anonymous union and struct in order to control the + * default alignment. + */ struct __kernel_sockaddr_storage { - __kernel_sa_family_t ss_family; /* address family */ - /* Following field(s) are implementation specific */ - char __data[_K_SS_MAXSIZE - sizeof(unsigned short)]; + union { + struct { + __kernel_sa_family_t ss_family; /* address family */ + /* Following field(s) are implementation specific */ + char __data[_K_SS_MAXSIZE - sizeof(unsigned short)]; /* space to achieve desired size, */ /* _SS_MAXSIZE value minus size of ss_family */ -} __attribute__ ((aligned(_K_SS_ALIGNSIZE))); /* force desired alignment */ + }; + void *__align; /* implementation specific desired alignment */ + }; +}; #endif /* _UAPI_LINUX_SOCKET_H */ From 4c92057661a3412f547ede95715641d7ee16ddac Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Sat, 3 Aug 2019 21:21:54 +0200 Subject: [PATCH 773/823] Documentation: Add swapgs description to the Spectre v1 documentation Add documentation to the Spectre document about the new swapgs variant of Spectre v1. Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner --- Documentation/admin-guide/hw-vuln/spectre.rst | 88 +++++++++++++++++-- 1 file changed, 80 insertions(+), 8 deletions(-) diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index 25f3b2532198..e05e581af5cf 100644 --- a/Documentation/admin-guide/hw-vuln/spectre.rst +++ b/Documentation/admin-guide/hw-vuln/spectre.rst @@ -41,10 +41,11 @@ Related CVEs The following CVE entries describe Spectre variants: - ============= ======================= ================= + ============= ======================= ========================== CVE-2017-5753 Bounds check bypass Spectre variant 1 CVE-2017-5715 Branch target injection Spectre variant 2 - ============= ======================= ================= + CVE-2019-1125 Spectre v1 swapgs Spectre variant 1 (swapgs) + ============= ======================= ========================== Problem ------- @@ -78,6 +79,13 @@ There are some extensions of Spectre variant 1 attacks for reading data over the network, see :ref:`[12] `. However such attacks are difficult, low bandwidth, fragile, and are considered low risk. +Note that, despite "Bounds Check Bypass" name, Spectre variant 1 is not +only about user-controlled array bounds checks. It can affect any +conditional checks. The kernel entry code interrupt, exception, and NMI +handlers all have conditional swapgs checks. Those may be problematic +in the context of Spectre v1, as kernel code can speculatively run with +a user GS. + Spectre variant 2 (Branch Target Injection) ------------------------------------------- @@ -132,6 +140,9 @@ not cover all possible attack vectors. 1. A user process attacking the kernel ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +Spectre variant 1 +~~~~~~~~~~~~~~~~~ + The attacker passes a parameter to the kernel via a register or via a known address in memory during a syscall. Such parameter may be used later by the kernel as an index to an array or to derive @@ -144,7 +155,40 @@ not cover all possible attack vectors. potentially be influenced for Spectre attacks, new "nospec" accessor macros are used to prevent speculative loading of data. - Spectre variant 2 attacker can :ref:`poison ` the branch +Spectre variant 1 (swapgs) +~~~~~~~~~~~~~~~~~~~~~~~~~~ + + An attacker can train the branch predictor to speculatively skip the + swapgs path for an interrupt or exception. If they initialize + the GS register to a user-space value, if the swapgs is speculatively + skipped, subsequent GS-related percpu accesses in the speculation + window will be done with the attacker-controlled GS value. This + could cause privileged memory to be accessed and leaked. + + For example: + + :: + + if (coming from user space) + swapgs + mov %gs:, %reg + mov (%reg), %reg1 + + When coming from user space, the CPU can speculatively skip the + swapgs, and then do a speculative percpu load using the user GS + value. So the user can speculatively force a read of any kernel + value. If a gadget exists which uses the percpu value as an address + in another load/store, then the contents of the kernel value may + become visible via an L1 side channel attack. + + A similar attack exists when coming from kernel space. The CPU can + speculatively do the swapgs, causing the user GS to get used for the + rest of the speculative window. + +Spectre variant 2 +~~~~~~~~~~~~~~~~~ + + A spectre variant 2 attacker can :ref:`poison ` the branch target buffer (BTB) before issuing syscall to launch an attack. After entering the kernel, the kernel could use the poisoned branch target buffer on indirect jump and jump to gadget code in speculative @@ -280,11 +324,18 @@ The sysfs file showing Spectre variant 1 mitigation status is: The possible values in this file are: - ======================================= ================================= - 'Mitigation: __user pointer sanitation' Protection in kernel on a case by - case base with explicit pointer - sanitation. - ======================================= ================================= + .. list-table:: + + * - 'Not affected' + - The processor is not vulnerable. + * - 'Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers' + - The swapgs protections are disabled; otherwise it has + protection in the kernel on a case by case base with explicit + pointer sanitation and usercopy LFENCE barriers. + * - 'Mitigation: usercopy/swapgs barriers and __user pointer sanitization' + - Protection in the kernel on a case by case base with explicit + pointer sanitation, usercopy LFENCE barriers, and swapgs LFENCE + barriers. However, the protections are put in place on a case by case basis, and there is no guarantee that all possible attack vectors for Spectre @@ -366,12 +417,27 @@ Turning on mitigation for Spectre variant 1 and Spectre variant 2 1. Kernel mitigation ^^^^^^^^^^^^^^^^^^^^ +Spectre variant 1 +~~~~~~~~~~~~~~~~~ + For the Spectre variant 1, vulnerable kernel code (as determined by code audit or scanning tools) is annotated on a case by case basis to use nospec accessor macros for bounds clipping :ref:`[2] ` to avoid any usable disclosure gadgets. However, it may not cover all attack vectors for Spectre variant 1. + Copy-from-user code has an LFENCE barrier to prevent the access_ok() + check from being mis-speculated. The barrier is done by the + barrier_nospec() macro. + + For the swapgs variant of Spectre variant 1, LFENCE barriers are + added to interrupt, exception and NMI entry where needed. These + barriers are done by the FENCE_SWAPGS_KERNEL_ENTRY and + FENCE_SWAPGS_USER_ENTRY macros. + +Spectre variant 2 +~~~~~~~~~~~~~~~~~ + For Spectre variant 2 mitigation, the compiler turns indirect calls or jumps in the kernel into equivalent return trampolines (retpolines) :ref:`[3] ` :ref:`[9] ` to go to the target @@ -473,6 +539,12 @@ Mitigation control on the kernel command line Spectre variant 2 mitigation can be disabled or force enabled at the kernel command line. + nospectre_v1 + + [X86,PPC] Disable mitigations for Spectre Variant 1 + (bounds check bypass). With this option data leaks are + possible in the system. + nospectre_v2 [X86] Disable all mitigations for the Spectre variant 2 From 0c5b6c28ed68becb692b43eae5e44d5aa7e160ce Mon Sep 17 00:00:00 2001 From: "M. Vefa Bicakci" Date: Sat, 3 Aug 2019 06:02:12 -0400 Subject: [PATCH 774/823] kconfig: Clear "written" flag to avoid data loss Prior to this commit, starting nconfig, xconfig or gconfig, and saving the .config file more than once caused data loss, where a .config file that contained only comments would be written to disk starting from the second save operation. This bug manifests itself because the SYMBOL_WRITTEN flag is never cleared after the first call to conf_write, and subsequent calls to conf_write then skip all of the configuration symbols due to the SYMBOL_WRITTEN flag being set. This commit resolves this issue by clearing the SYMBOL_WRITTEN flag from all symbols before conf_write returns. Fixes: 8e2442a5f86e ("kconfig: fix missing choice values in auto.conf") Cc: linux-stable # 4.19+ Signed-off-by: M. Vefa Bicakci Signed-off-by: Masahiro Yamada --- scripts/kconfig/confdata.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 1134892599da..3569d2dec37c 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -848,6 +848,7 @@ int conf_write(const char *name) const char *str; char tmpname[PATH_MAX + 1], oldname[PATH_MAX + 1]; char *env; + int i; bool need_newline = false; if (!name) @@ -930,6 +931,9 @@ next: } fclose(out); + for_all_symbols(i, sym) + sym->flags &= ~SYMBOL_WRITTEN; + if (*tmpname) { if (is_same(name, tmpname)) { conf_message("No change to %s", name); From 4c0d228c3bd498b3119d68eb41a17880f7728993 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 29 Jul 2019 19:56:58 +0200 Subject: [PATCH 775/823] MAINTAINERS: Add Geert as Renesas SoC Co-Maintainer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit At the end of the v5.3 upstream kernel development cycle, Simon will be stepping down from his role as Renesas SoC maintainer. Starting with the v5.4 development cycle, Geert is taking over this role. Add Geert as a co-maintainer, and add his git repository and branch. Signed-off-by: Geert Uytterhoeven Reviewed-by: Niklas Söderlund Acked-by: Simon Horman Signed-off-by: Linus Torvalds --- MAINTAINERS | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 0f5004592ffc..a2c343ee3b2c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2155,10 +2155,12 @@ F: Documentation/devicetree/bindings/arm/realtek.txt ARM/RENESAS ARM64 ARCHITECTURE M: Simon Horman +M: Geert Uytterhoeven M: Magnus Damm L: linux-renesas-soc@vger.kernel.org Q: http://patchwork.kernel.org/project/linux-renesas-soc/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas.git next +T: git git://git.kernel.org/pub/scm/linux/kernel/git/geert/renesas-devel.git next S: Supported F: arch/arm64/boot/dts/renesas/ F: Documentation/devicetree/bindings/arm/renesas.yaml @@ -2269,10 +2271,12 @@ F: drivers/media/platform/s5p-mfc/ ARM/SHMOBILE ARM ARCHITECTURE M: Simon Horman +M: Geert Uytterhoeven M: Magnus Damm L: linux-renesas-soc@vger.kernel.org Q: http://patchwork.kernel.org/project/linux-renesas-soc/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas.git next +T: git git://git.kernel.org/pub/scm/linux/kernel/git/geert/renesas-devel.git next S: Supported F: arch/arm/boot/dts/emev2* F: arch/arm/boot/dts/gr-peach* From 1e5ac6300a07ceecfc70a893ebef3352be21e6f8 Mon Sep 17 00:00:00 2001 From: Milan Broz Date: Thu, 4 Jul 2019 09:26:15 +0200 Subject: [PATCH 776/823] tpm: Fix null pointer dereference on chip register error path If clk_enable is not defined and chip initialization is canceled code hits null dereference. Easily reproducible with vTPM init fail: swtpm chardev --tpmstate dir=nonexistent_dir --tpm2 --vtpm-proxy BUG: kernel NULL pointer dereference, address: 00000000 ... Call Trace: tpm_chip_start+0x9d/0xa0 [tpm] tpm_chip_register+0x10/0x1a0 [tpm] vtpm_proxy_work+0x11/0x30 [tpm_vtpm_proxy] process_one_work+0x214/0x5a0 worker_thread+0x134/0x3e0 ? process_one_work+0x5a0/0x5a0 kthread+0xd4/0x100 ? process_one_work+0x5a0/0x5a0 ? kthread_park+0x90/0x90 ret_from_fork+0x19/0x24 Fixes: 719b7d81f204 ("tpm: introduce tpm_chip_start() and tpm_chip_stop()") Cc: stable@vger.kernel.org # v5.1+ Signed-off-by: Milan Broz Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm-chip.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index d47ad10a35fe..bf868260f435 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -77,6 +77,18 @@ static int tpm_go_idle(struct tpm_chip *chip) return chip->ops->go_idle(chip); } +static void tpm_clk_enable(struct tpm_chip *chip) +{ + if (chip->ops->clk_enable) + chip->ops->clk_enable(chip, true); +} + +static void tpm_clk_disable(struct tpm_chip *chip) +{ + if (chip->ops->clk_enable) + chip->ops->clk_enable(chip, false); +} + /** * tpm_chip_start() - power on the TPM * @chip: a TPM chip to use @@ -89,13 +101,12 @@ int tpm_chip_start(struct tpm_chip *chip) { int ret; - if (chip->ops->clk_enable) - chip->ops->clk_enable(chip, true); + tpm_clk_enable(chip); if (chip->locality == -1) { ret = tpm_request_locality(chip); if (ret) { - chip->ops->clk_enable(chip, false); + tpm_clk_disable(chip); return ret; } } @@ -103,8 +114,7 @@ int tpm_chip_start(struct tpm_chip *chip) ret = tpm_cmd_ready(chip); if (ret) { tpm_relinquish_locality(chip); - if (chip->ops->clk_enable) - chip->ops->clk_enable(chip, false); + tpm_clk_disable(chip); return ret; } @@ -124,8 +134,7 @@ void tpm_chip_stop(struct tpm_chip *chip) { tpm_go_idle(chip); tpm_relinquish_locality(chip); - if (chip->ops->clk_enable) - chip->ops->clk_enable(chip, false); + tpm_clk_disable(chip); } EXPORT_SYMBOL_GPL(tpm_chip_stop); From fa4f99c05320eb28bf6ba52a9adf64d888da1f9e Mon Sep 17 00:00:00 2001 From: Nayna Jain Date: Thu, 11 Jul 2019 12:13:35 -0400 Subject: [PATCH 777/823] tpm: tpm_ibm_vtpm: Fix unallocated banks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The nr_allocated_banks and allocated banks are initialized as part of tpm_chip_register. Currently, this is done as part of auto startup function. However, some drivers, like the ibm vtpm driver, do not run auto startup during initialization. This results in uninitialized memory issue and causes a kernel panic during boot. This patch moves the pcr allocation outside the auto startup function into tpm_chip_register. This ensures that allocated banks are initialized in any case. Fixes: 879b589210a9 ("tpm: retrieve digest size of unknown algorithms with PCR read") Reported-by: Michal Suchanek Signed-off-by: Nayna Jain Reviewed-by: Mimi Zohar Tested-by: Sachin Sant Tested-by: Michal Suchánek Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm-chip.c | 20 ++++++++++++++++++++ drivers/char/tpm/tpm.h | 2 ++ drivers/char/tpm/tpm1-cmd.c | 36 ++++++++++++++++++++++++------------ drivers/char/tpm/tpm2-cmd.c | 6 +----- 4 files changed, 47 insertions(+), 17 deletions(-) diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index bf868260f435..4838c6a9f0f2 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -554,6 +554,20 @@ static int tpm_add_hwrng(struct tpm_chip *chip) return hwrng_register(&chip->hwrng); } +static int tpm_get_pcr_allocation(struct tpm_chip *chip) +{ + int rc; + + rc = (chip->flags & TPM_CHIP_FLAG_TPM2) ? + tpm2_get_pcr_allocation(chip) : + tpm1_get_pcr_allocation(chip); + + if (rc > 0) + return -ENODEV; + + return rc; +} + /* * tpm_chip_register() - create a character device for the TPM chip * @chip: TPM chip to use. @@ -573,6 +587,12 @@ int tpm_chip_register(struct tpm_chip *chip) if (rc) return rc; rc = tpm_auto_startup(chip); + if (rc) { + tpm_chip_stop(chip); + return rc; + } + + rc = tpm_get_pcr_allocation(chip); tpm_chip_stop(chip); if (rc) return rc; diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index e503ffc3aa39..a7fea3e0ca86 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -394,6 +394,7 @@ int tpm1_pcr_read(struct tpm_chip *chip, u32 pcr_idx, u8 *res_buf); ssize_t tpm1_getcap(struct tpm_chip *chip, u32 subcap_id, cap_t *cap, const char *desc, size_t min_cap_length); int tpm1_get_random(struct tpm_chip *chip, u8 *out, size_t max); +int tpm1_get_pcr_allocation(struct tpm_chip *chip); unsigned long tpm_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal); int tpm_pm_suspend(struct device *dev); int tpm_pm_resume(struct device *dev); @@ -449,6 +450,7 @@ int tpm2_unseal_trusted(struct tpm_chip *chip, ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id, u32 *value, const char *desc); +ssize_t tpm2_get_pcr_allocation(struct tpm_chip *chip); int tpm2_auto_startup(struct tpm_chip *chip); void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type); unsigned long tpm2_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal); diff --git a/drivers/char/tpm/tpm1-cmd.c b/drivers/char/tpm/tpm1-cmd.c index faacbe1ffa1a..149e953ca369 100644 --- a/drivers/char/tpm/tpm1-cmd.c +++ b/drivers/char/tpm/tpm1-cmd.c @@ -699,18 +699,6 @@ int tpm1_auto_startup(struct tpm_chip *chip) goto out; } - chip->allocated_banks = kcalloc(1, sizeof(*chip->allocated_banks), - GFP_KERNEL); - if (!chip->allocated_banks) { - rc = -ENOMEM; - goto out; - } - - chip->allocated_banks[0].alg_id = TPM_ALG_SHA1; - chip->allocated_banks[0].digest_size = hash_digest_size[HASH_ALGO_SHA1]; - chip->allocated_banks[0].crypto_id = HASH_ALGO_SHA1; - chip->nr_allocated_banks = 1; - return rc; out: if (rc > 0) @@ -779,3 +767,27 @@ int tpm1_pm_suspend(struct tpm_chip *chip, u32 tpm_suspend_pcr) return rc; } +/** + * tpm1_get_pcr_allocation() - initialize the allocated bank + * @chip: TPM chip to use. + * + * The function initializes the SHA1 allocated bank to extend PCR + * + * Return: + * * 0 on success, + * * < 0 on error. + */ +int tpm1_get_pcr_allocation(struct tpm_chip *chip) +{ + chip->allocated_banks = kcalloc(1, sizeof(*chip->allocated_banks), + GFP_KERNEL); + if (!chip->allocated_banks) + return -ENOMEM; + + chip->allocated_banks[0].alg_id = TPM_ALG_SHA1; + chip->allocated_banks[0].digest_size = hash_digest_size[HASH_ALGO_SHA1]; + chip->allocated_banks[0].crypto_id = HASH_ALGO_SHA1; + chip->nr_allocated_banks = 1; + + return 0; +} diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index d103545e4055..ba9acae83bff 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -840,7 +840,7 @@ struct tpm2_pcr_selection { u8 pcr_select[3]; } __packed; -static ssize_t tpm2_get_pcr_allocation(struct tpm_chip *chip) +ssize_t tpm2_get_pcr_allocation(struct tpm_chip *chip) { struct tpm2_pcr_selection pcr_selection; struct tpm_buf buf; @@ -1040,10 +1040,6 @@ int tpm2_auto_startup(struct tpm_chip *chip) goto out; } - rc = tpm2_get_pcr_allocation(chip); - if (rc) - goto out; - rc = tpm2_get_cc_attrs_tbl(chip); out: From e21a712a9685488f5ce80495b37b9fdbe96c230d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 4 Aug 2019 18:40:12 -0700 Subject: [PATCH 778/823] Linux 5.3-rc3 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 5ee6f6889869..23cdf1f41364 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 3 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Bobtail Squid # *DOCUMENTATION* From 6fb08f1a5f7e5cdde1ce00104788e602f4299b99 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 29 Jul 2019 17:50:36 +0200 Subject: [PATCH 779/823] HID: logitech-dj: Really fix return value of logi_dj_recv_query_hidpp_devices Commit dbcbabf7da92 ("HID: logitech-dj: fix return value of logi_dj_recv_query_hidpp_devices") made logi_dj_recv_query_hidpp_devices return the return value of hid_hw_raw_request instead of unconditionally returning 0. But hid_hw_raw_request returns the report-size on a successful request (and a negative error-code on failure) where as the callers of logi_dj_recv_query_hidpp_devices expect a 0 return on success. This commit fixes things so that either the negative error gets returned or 0 on success, fixing HID++ receivers such as the Logitech nano receivers no longer working. Cc: YueHaibing Cc: Rafael J. Wysocki Cc: Lionel Landwerlin Fixes: dbcbabf7da92 ("HID: logitech-dj: fix return value of logi_dj_recv_query_hidpp_devices") Reported-by: Lionel Landwerlin Reported-by: Rafael J. Wysocki Signed-off-by: Hans de Goede Tested-by: Rafael J. Wysocki Reviewed-by: Petr Vorel Tested-by: Petr Vorel Reviewed-by: YueHaibing Signed-off-by: Jiri Kosina --- drivers/hid/hid-logitech-dj.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index d5b47ec1510c..cc47f948c1d0 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -1125,7 +1125,7 @@ static int logi_dj_recv_query_hidpp_devices(struct dj_receiver_dev *djrcv_dev) HID_REQ_SET_REPORT); kfree(hidpp_report); - return retval; + return (retval < 0) ? retval : 0; } static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev) From 7bc74853fd61432ec59f812a40425bf6d8c986a4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Istv=C3=A1n=20V=C3=A1radi?= Date: Wed, 24 Jul 2019 20:09:18 +0200 Subject: [PATCH 780/823] HID: quirks: Set the INCREMENT_USAGE_ON_DUPLICATE quirk on Saitek X52 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Saitek X52 joystick has a pair of axes that are originally (by the Windows driver) used as mouse pointer controls. The corresponding usage->hid values are 0x50024 and 0x50026. Thus they are handled as unknown axes and both get mapped to ABS_MISC. The quirk makes the second axis to be mapped to ABS_MISC1 and thus made available separately. [jkosina@suse.cz: squashed two patches into one] Signed-off-by: István Váradi Signed-off-by: Jiri Kosina --- drivers/hid/hid-ids.h | 1 + drivers/hid/hid-quirks.c | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 884356feb016..31e9782f234e 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -990,6 +990,7 @@ #define USB_DEVICE_ID_SAITEK_RAT7 0x0cd7 #define USB_DEVICE_ID_SAITEK_RAT9 0x0cfa #define USB_DEVICE_ID_SAITEK_MMO7 0x0cd0 +#define USB_DEVICE_ID_SAITEK_X52 0x075c #define USB_VENDOR_ID_SAMSUNG 0x0419 #define USB_DEVICE_ID_SAMSUNG_IR_REMOTE 0x0001 diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 1549c7a2f04c..73eb7ea7e76c 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -140,6 +140,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPAD), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPORT), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RUMBLEPAD), HID_QUIRK_BADPAD }, + { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SENNHEISER, USB_DEVICE_ID_SENNHEISER_BTD500USB), HID_QUIRK_NOGET }, From 693c3dab4e50403f91bca4b52fc6d8562a3180f6 Mon Sep 17 00:00:00 2001 From: Aaron Armstrong Skomra Date: Tue, 23 Jul 2019 11:09:15 -0700 Subject: [PATCH 781/823] HID: wacom: fix bit shift for Cintiq Companion 2 The bit indicating BTN_6 on this device is overshifted by 2 bits, resulting in the incorrect button being reported. Also fix copy-paste mistake in comments. Signed-off-by: Aaron Armstrong Skomra Reviewed-by: Ping Cheng Link: https://github.com/linuxwacom/xf86-input-wacom/issues/71 Fixes: c7f0522a1ad1 ("HID: wacom: Slim down wacom_intuos_pad processing") Cc: # v4.5+ Signed-off-by: Jiri Kosina --- drivers/hid/wacom_wac.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 8fc36a28081b..7a8ddc999a8e 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -533,14 +533,14 @@ static int wacom_intuos_pad(struct wacom_wac *wacom) */ buttons = (data[4] << 1) | (data[3] & 0x01); } else if (features->type == CINTIQ_COMPANION_2) { - /* d-pad right -> data[4] & 0x10 - * d-pad up -> data[4] & 0x20 - * d-pad left -> data[4] & 0x40 - * d-pad down -> data[4] & 0x80 - * d-pad center -> data[3] & 0x01 + /* d-pad right -> data[2] & 0x10 + * d-pad up -> data[2] & 0x20 + * d-pad left -> data[2] & 0x40 + * d-pad down -> data[2] & 0x80 + * d-pad center -> data[1] & 0x01 */ buttons = ((data[2] >> 4) << 7) | - ((data[1] & 0x04) << 6) | + ((data[1] & 0x04) << 4) | ((data[2] & 0x0F) << 2) | (data[1] & 0x03); } else if (features->type >= INTUOS5S && features->type <= INTUOSPL) { From 01ec0a5f19c8c82960a07f6c7410fc9e01d7fb51 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Thu, 25 Jul 2019 15:13:33 +0200 Subject: [PATCH 782/823] HID: holtek: test for sanity of intfdata The ioctl handler uses the intfdata of a second interface, which may not be present in a broken or malicious device, hence the intfdata needs to be checked for NULL. [jkosina@suse.cz: fix newly added spurious space] Reported-by: syzbot+965152643a75a56737be@syzkaller.appspotmail.com Signed-off-by: Oliver Neukum Signed-off-by: Jiri Kosina --- drivers/hid/hid-holtek-kbd.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-holtek-kbd.c b/drivers/hid/hid-holtek-kbd.c index b3d502421b79..0a38e8e9bc78 100644 --- a/drivers/hid/hid-holtek-kbd.c +++ b/drivers/hid/hid-holtek-kbd.c @@ -123,9 +123,14 @@ static int holtek_kbd_input_event(struct input_dev *dev, unsigned int type, /* Locate the boot interface, to receive the LED change events */ struct usb_interface *boot_interface = usb_ifnum_to_if(usb_dev, 0); + struct hid_device *boot_hid; + struct hid_input *boot_hid_input; - struct hid_device *boot_hid = usb_get_intfdata(boot_interface); - struct hid_input *boot_hid_input = list_first_entry(&boot_hid->inputs, + if (unlikely(boot_interface == NULL)) + return -ENODEV; + + boot_hid = usb_get_intfdata(boot_interface); + boot_hid_input = list_first_entry(&boot_hid->inputs, struct hid_input, list); return boot_hid_input->input->event(boot_hid_input->input, type, code, From 49869d2ea9eecc105a10724c1abf035151a3c4e2 Mon Sep 17 00:00:00 2001 From: Sebastian Parschauer Date: Wed, 24 Jul 2019 20:40:03 +0200 Subject: [PATCH 783/823] HID: Add quirk for HP X1200 PIXART OEM mouse The PixArt OEM mice are known for disconnecting every minute in runlevel 1 or 3 if they are not always polled. So add quirk ALWAYS_POLL for this one as well. Jonathan Teh (@jonathan-teh) reported and tested the quirk. Reference: https://github.com/sriemer/fix-linux-mouse/issues/15 Signed-off-by: Sebastian Parschauer CC: stable@vger.kernel.org Signed-off-by: Jiri Kosina --- drivers/hid/hid-ids.h | 1 + drivers/hid/hid-quirks.c | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 31e9782f234e..0a00be19f7a0 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -568,6 +568,7 @@ #define USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A 0x0b4a #define USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE 0x134a #define USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_094A 0x094a +#define USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_0641 0x0641 #define USB_VENDOR_ID_HUION 0x256c #define USB_DEVICE_ID_HUION_TABLET 0x006e diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 73eb7ea7e76c..4fe2c3ab76f9 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -91,6 +91,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_094A), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_0641), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_IDEACOM, USB_DEVICE_ID_IDEACOM_IDC6680), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_INNOMEDIA, USB_DEVICE_ID_INNEX_GENESIS_ATARI), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X), HID_QUIRK_MULTI_INPUT }, From 1c703b53e5bfb5c2205c30f0fb157ce271fd42fb Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Tue, 11 Jun 2019 14:13:20 +0200 Subject: [PATCH 784/823] HID: input: fix a4tech horizontal wheel custom usage Some a4tech mice use the 'GenericDesktop.00b8' usage to inform whether the previous wheel report was horizontal or vertical. Before c01908a14bf73 ("HID: input: add mapping for "Toggle Display" key") this usage was being mapped to 'Relative.Misc'. After the patch it's simply ignored (usage->type == 0 & usage->code == 0). Which ultimately makes hid-a4tech ignore the WHEEL/HWHEEL selection event, as it has no usage->type. We shouldn't rely on a mapping for that usage as it's nonstandard and doesn't really map to an input event. So we bypass the mapping and make sure the custom event handling properly handles both reports. Fixes: c01908a14bf73 ("HID: input: add mapping for "Toggle Display" key") Signed-off-by: Nicolas Saenz Julienne Signed-off-by: Jiri Kosina --- drivers/hid/hid-a4tech.c | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-) diff --git a/drivers/hid/hid-a4tech.c b/drivers/hid/hid-a4tech.c index 98bf694626f7..3a8c4a5971f7 100644 --- a/drivers/hid/hid-a4tech.c +++ b/drivers/hid/hid-a4tech.c @@ -23,12 +23,36 @@ #define A4_2WHEEL_MOUSE_HACK_7 0x01 #define A4_2WHEEL_MOUSE_HACK_B8 0x02 +#define A4_WHEEL_ORIENTATION (HID_UP_GENDESK | 0x000000b8) + struct a4tech_sc { unsigned long quirks; unsigned int hw_wheel; __s32 delayed_value; }; +static int a4_input_mapping(struct hid_device *hdev, struct hid_input *hi, + struct hid_field *field, struct hid_usage *usage, + unsigned long **bit, int *max) +{ + struct a4tech_sc *a4 = hid_get_drvdata(hdev); + + if (a4->quirks & A4_2WHEEL_MOUSE_HACK_B8 && + usage->hid == A4_WHEEL_ORIENTATION) { + /* + * We do not want to have this usage mapped to anything as it's + * nonstandard and doesn't really behave like an HID report. + * It's only selecting the orientation (vertical/horizontal) of + * the previous mouse wheel report. The input_events will be + * generated once both reports are recorded in a4_event(). + */ + return -1; + } + + return 0; + +} + static int a4_input_mapped(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) @@ -52,8 +76,7 @@ static int a4_event(struct hid_device *hdev, struct hid_field *field, struct a4tech_sc *a4 = hid_get_drvdata(hdev); struct input_dev *input; - if (!(hdev->claimed & HID_CLAIMED_INPUT) || !field->hidinput || - !usage->type) + if (!(hdev->claimed & HID_CLAIMED_INPUT) || !field->hidinput) return 0; input = field->hidinput->input; @@ -64,7 +87,7 @@ static int a4_event(struct hid_device *hdev, struct hid_field *field, return 1; } - if (usage->hid == 0x000100b8) { + if (usage->hid == A4_WHEEL_ORIENTATION) { input_event(input, EV_REL, value ? REL_HWHEEL : REL_WHEEL, a4->delayed_value); input_event(input, EV_REL, value ? REL_HWHEEL_HI_RES : @@ -131,6 +154,7 @@ MODULE_DEVICE_TABLE(hid, a4_devices); static struct hid_driver a4_driver = { .name = "a4tech", .id_table = a4_devices, + .input_mapping = a4_input_mapping, .input_mapped = a4_input_mapped, .event = a4_event, .probe = a4_probe, From c3953a3c2d3175d2f9f0304c9a1ba89e7743c5e4 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 5 Aug 2019 12:00:55 +0200 Subject: [PATCH 785/823] NFC: nfcmrvl: fix gpio-handling regression Fix two reset-gpio sanity checks which were never converted to use gpio_is_valid(), and make sure to use -EINVAL to indicate a missing reset line also for the UART-driver module parameter and for the USB driver. This specifically prevents the UART and USB drivers from incidentally trying to request and use gpio 0, and also avoids triggering a WARN() in gpio_to_desc() during probe when no valid reset line has been specified. Fixes: e33a3f84f88f ("NFC: nfcmrvl: allow gpio 0 for reset signalling") Reported-by: syzbot+cf35b76f35e068a1107f@syzkaller.appspotmail.com Tested-by: syzbot+cf35b76f35e068a1107f@syzkaller.appspotmail.com Signed-off-by: Johan Hovold --- drivers/nfc/nfcmrvl/main.c | 4 ++-- drivers/nfc/nfcmrvl/uart.c | 4 ++-- drivers/nfc/nfcmrvl/usb.c | 1 + 3 files changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/nfc/nfcmrvl/main.c b/drivers/nfc/nfcmrvl/main.c index e65d027b91fa..529be35ac178 100644 --- a/drivers/nfc/nfcmrvl/main.c +++ b/drivers/nfc/nfcmrvl/main.c @@ -244,7 +244,7 @@ void nfcmrvl_chip_reset(struct nfcmrvl_private *priv) /* Reset possible fault of previous session */ clear_bit(NFCMRVL_PHY_ERROR, &priv->flags); - if (priv->config.reset_n_io) { + if (gpio_is_valid(priv->config.reset_n_io)) { nfc_info(priv->dev, "reset the chip\n"); gpio_set_value(priv->config.reset_n_io, 0); usleep_range(5000, 10000); @@ -255,7 +255,7 @@ void nfcmrvl_chip_reset(struct nfcmrvl_private *priv) void nfcmrvl_chip_halt(struct nfcmrvl_private *priv) { - if (priv->config.reset_n_io) + if (gpio_is_valid(priv->config.reset_n_io)) gpio_set_value(priv->config.reset_n_io, 0); } diff --git a/drivers/nfc/nfcmrvl/uart.c b/drivers/nfc/nfcmrvl/uart.c index 9a22056e8d9e..e5a622ce4b95 100644 --- a/drivers/nfc/nfcmrvl/uart.c +++ b/drivers/nfc/nfcmrvl/uart.c @@ -26,7 +26,7 @@ static unsigned int hci_muxed; static unsigned int flow_control; static unsigned int break_control; -static unsigned int reset_n_io; +static int reset_n_io = -EINVAL; /* ** NFCMRVL NCI OPS @@ -231,5 +231,5 @@ MODULE_PARM_DESC(break_control, "Tell if UART driver must drive break signal."); module_param(hci_muxed, uint, 0); MODULE_PARM_DESC(hci_muxed, "Tell if transport is muxed in HCI one."); -module_param(reset_n_io, uint, 0); +module_param(reset_n_io, int, 0); MODULE_PARM_DESC(reset_n_io, "GPIO that is wired to RESET_N signal."); diff --git a/drivers/nfc/nfcmrvl/usb.c b/drivers/nfc/nfcmrvl/usb.c index 945cc903d8f1..888e298f610b 100644 --- a/drivers/nfc/nfcmrvl/usb.c +++ b/drivers/nfc/nfcmrvl/usb.c @@ -305,6 +305,7 @@ static int nfcmrvl_probe(struct usb_interface *intf, /* No configuration for USB */ memset(&config, 0, sizeof(config)); + config.reset_n_io = -EINVAL; nfc_info(&udev->dev, "intf %p id %p\n", intf, id); From 7fb5a711545d7d25fe9726a9ad277474dd83bd06 Mon Sep 17 00:00:00 2001 From: Hubert Feurstein Date: Wed, 31 Jul 2019 17:42:39 +0200 Subject: [PATCH 786/823] net: dsa: mv88e6xxx: drop adjust_link to enabled phylink We have to drop the adjust_link callback in order to finally migrate to phylink. Otherwise we get the following warning during startup: "mv88e6xxx 2188000.ethernet-1:10: Using legacy PHYLIB callbacks. Please migrate to PHYLINK!" The warning is generated in the function dsa_port_link_register_of in dsa/port.c: int dsa_port_link_register_of(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; if (!ds->ops->adjust_link) return dsa_port_phylink_register(dp); dev_warn(ds->dev, "Using legacy PHYLIB callbacks. Please migrate to PHYLINK!\n"); [...] } Signed-off-by: Hubert Feurstein Reviewed-by: Andrew Lunn Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 26 -------------------------- 1 file changed, 26 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index a0f288efcc12..d0a97eb73a37 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -27,7 +27,6 @@ #include #include #include -#include #include #include @@ -482,30 +481,6 @@ static int mv88e6xxx_phy_is_internal(struct dsa_switch *ds, int port) return port < chip->info->num_internal_phys; } -/* We expect the switch to perform auto negotiation if there is a real - * phy. However, in the case of a fixed link phy, we force the port - * settings from the fixed link settings. - */ -static void mv88e6xxx_adjust_link(struct dsa_switch *ds, int port, - struct phy_device *phydev) -{ - struct mv88e6xxx_chip *chip = ds->priv; - int err; - - if (!phy_is_pseudo_fixed_link(phydev) && - mv88e6xxx_phy_is_internal(ds, port)) - return; - - mv88e6xxx_reg_lock(chip); - err = mv88e6xxx_port_setup_mac(chip, port, phydev->link, phydev->speed, - phydev->duplex, phydev->pause, - phydev->interface); - mv88e6xxx_reg_unlock(chip); - - if (err && err != -EOPNOTSUPP) - dev_err(ds->dev, "p%d: failed to configure MAC\n", port); -} - static void mv88e6065_phylink_validate(struct mv88e6xxx_chip *chip, int port, unsigned long *mask, struct phylink_link_state *state) @@ -4639,7 +4614,6 @@ static int mv88e6xxx_port_egress_floods(struct dsa_switch *ds, int port, static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .get_tag_protocol = mv88e6xxx_get_tag_protocol, .setup = mv88e6xxx_setup, - .adjust_link = mv88e6xxx_adjust_link, .phylink_validate = mv88e6xxx_validate, .phylink_mac_link_state = mv88e6xxx_link_state, .phylink_mac_config = mv88e6xxx_mac_config, From 7be8ef2cdbfe41a2e524b7c6cc3f8e6cfaa906e4 Mon Sep 17 00:00:00 2001 From: Dmytro Linkin Date: Thu, 1 Aug 2019 13:02:51 +0000 Subject: [PATCH 787/823] net: sched: use temporary variable for actions indexes Currently init call of all actions (except ipt) init their 'parm' structure as a direct pointer to nla data in skb. This leads to race condition when some of the filter actions were initialized successfully (and were assigned with idr action index that was written directly into nla data), but then were deleted and retried (due to following action module missing or classifier-initiated retry), in which case action init code tries to insert action to idr with index that was assigned on previous iteration. During retry the index can be reused by another action that was inserted concurrently, which causes unintended action sharing between filters. To fix described race condition, save action idr index to temporary stack-allocated variable instead on nla data. Fixes: 0190c1d452a9 ("net: sched: atomically check-allocate action") Signed-off-by: Dmytro Linkin Signed-off-by: Vlad Buslov Acked-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/act_bpf.c | 9 +++++---- net/sched/act_connmark.c | 9 +++++---- net/sched/act_csum.c | 9 +++++---- net/sched/act_ct.c | 9 +++++---- net/sched/act_ctinfo.c | 9 +++++---- net/sched/act_gact.c | 8 +++++--- net/sched/act_ife.c | 8 +++++--- net/sched/act_mirred.c | 13 +++++++------ net/sched/act_mpls.c | 8 +++++--- net/sched/act_nat.c | 9 +++++---- net/sched/act_pedit.c | 10 ++++++---- net/sched/act_police.c | 8 +++++--- net/sched/act_sample.c | 10 +++++----- net/sched/act_simple.c | 10 ++++++---- net/sched/act_skbedit.c | 11 ++++++----- net/sched/act_skbmod.c | 11 ++++++----- net/sched/act_tunnel_key.c | 8 +++++--- net/sched/act_vlan.c | 16 +++++++++------- 18 files changed, 100 insertions(+), 75 deletions(-) diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 8126b26f125e..fd1f7e799e23 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -285,6 +285,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct tcf_bpf *prog; bool is_bpf, is_ebpf; int ret, res = 0; + u32 index; if (!nla) return -EINVAL; @@ -298,13 +299,13 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_ACT_BPF_PARMS]); - - ret = tcf_idr_check_alloc(tn, &parm->index, act, bind); + index = parm->index; + ret = tcf_idr_check_alloc(tn, &index, act, bind); if (!ret) { - ret = tcf_idr_create(tn, parm->index, est, act, + ret = tcf_idr_create(tn, index, est, act, &act_bpf_ops, bind, true); if (ret < 0) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index ce36b0f7e1dc..32ac04d77a45 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -103,6 +103,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, struct tcf_connmark_info *ci; struct tc_connmark *parm; int ret = 0, err; + u32 index; if (!nla) return -EINVAL; @@ -116,13 +117,13 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_CONNMARK_PARMS]); - - ret = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + ret = tcf_idr_check_alloc(tn, &index, a, bind); if (!ret) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_connmark_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 621fb22ce2a9..9b9288267a54 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -52,6 +52,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, struct tc_csum *parm; struct tcf_csum *p; int ret = 0, err; + u32 index; if (nla == NULL) return -EINVAL; @@ -64,13 +65,13 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, if (tb[TCA_CSUM_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_CSUM_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_csum_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b501ce0cf116..33a1a7406e87 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -666,6 +666,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, struct tc_ct *parm; struct tcf_ct *c; int err, res = 0; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Ct requires attributes to be passed"); @@ -681,16 +682,16 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, return -EINVAL; } parm = nla_data(tb[TCA_CT_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; if (!err) { - err = tcf_idr_create(tn, parm->index, est, a, + err = tcf_idr_create(tn, index, est, a, &act_ct_ops, bind, true); if (err) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return err; } res = ACT_P_CREATED; diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 10eb2bb99861..06ef74b74911 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -157,10 +157,10 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ctinfo_net_id); + u32 dscpmask = 0, dscpstatemask, index; struct nlattr *tb[TCA_CTINFO_MAX + 1]; struct tcf_ctinfo_params *cp_new; struct tcf_chain *goto_ch = NULL; - u32 dscpmask = 0, dscpstatemask; struct tc_ctinfo *actparm; struct tcf_ctinfo *ci; u8 dscpmaskshift; @@ -206,12 +206,13 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, } /* done the validation:now to the actual action allocation */ - err = tcf_idr_check_alloc(tn, &actparm->index, a, bind); + index = actparm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, actparm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_ctinfo_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, actparm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index b2380c5284e6..8f0140c6ca58 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -61,6 +61,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, struct tc_gact *parm; struct tcf_gact *gact; int ret = 0; + u32 index; int err; #ifdef CONFIG_GACT_PROB struct tc_gact_p *p_parm = NULL; @@ -77,6 +78,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, if (tb[TCA_GACT_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_GACT_PARMS]); + index = parm->index; #ifndef CONFIG_GACT_PROB if (tb[TCA_GACT_PROB] != NULL) @@ -94,12 +96,12 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, } #endif - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_gact_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 3578196d1600..92ee853d43e6 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -479,6 +479,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, u8 *saddr = NULL; bool exists = false; int ret = 0; + u32 index; int err; if (!nla) { @@ -507,7 +508,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (!p) return -ENOMEM; - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) { kfree(p); return err; @@ -519,10 +521,10 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops, + ret = tcf_idr_create(tn, index, est, a, &act_ife_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); kfree(p); return ret; } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 055faa298c8e..be3f88dfc37e 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -104,6 +104,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct net_device *dev; bool exists = false; int ret, err; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed"); @@ -118,8 +119,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, return -EINVAL; } parm = nla_data(tb[TCA_MIRRED_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -136,21 +137,21 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option"); return -EINVAL; } if (!exists) { if (!parm->ifindex) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist"); return -EINVAL; } - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_mirred_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index ca2597ce4ac9..0f299e3b618c 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -138,6 +138,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, struct tcf_mpls *m; int ret = 0, err; u8 mpls_ttl = 0; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Missing netlink attributes"); @@ -153,6 +154,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, return -EINVAL; } parm = nla_data(tb[TCA_MPLS_PARMS]); + index = parm->index; /* Verify parameters against action type. */ switch (parm->m_action) { @@ -209,7 +211,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, return -EINVAL; } - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -217,10 +219,10 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, return 0; if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_mpls_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 45923ebb7a4f..7b858c11b1b5 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -44,6 +44,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_nat *parm; int ret = 0, err; struct tcf_nat *p; + u32 index; if (nla == NULL) return -EINVAL; @@ -56,13 +57,13 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, if (tb[TCA_NAT_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_NAT_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_nat_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 45e9d6bfddb3..17360c6faeaa 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -149,6 +149,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct tcf_pedit *p; int ret = 0, err; int ksize; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Pedit requires attributes to be passed"); @@ -179,18 +180,19 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (IS_ERR(keys_ex)) return PTR_ERR(keys_ex); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { if (!parm->nkeys) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); ret = -EINVAL; goto out_free; } - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_pedit_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); goto out_free; } ret = ACT_P_CREATED; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index a065f62fa79c..49cec3e64a4d 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -57,6 +57,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, police_net_id); struct tcf_police_params *new; bool exists = false; + u32 index; if (nla == NULL) return -EINVAL; @@ -73,7 +74,8 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_POLICE_TBF]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -81,10 +83,10 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, return 0; if (!exists) { - ret = tcf_idr_create(tn, parm->index, NULL, a, + ret = tcf_idr_create(tn, index, NULL, a, &act_police_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 274d7a0c0e25..595308d60133 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -41,8 +41,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, sample_net_id); struct nlattr *tb[TCA_SAMPLE_MAX + 1]; struct psample_group *psample_group; + u32 psample_group_num, rate, index; struct tcf_chain *goto_ch = NULL; - u32 psample_group_num, rate; struct tc_sample *parm; struct tcf_sample *s; bool exists = false; @@ -59,8 +59,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_SAMPLE_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -68,10 +68,10 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, return 0; if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_sample_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index f28ddbabff76..33aefa25b545 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -95,6 +95,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, struct tcf_defact *d; bool exists = false; int ret = 0, err; + u32 index; if (nla == NULL) return -EINVAL; @@ -108,7 +109,8 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_DEF_PARMS]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -119,15 +121,15 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_simp_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 215a06705cef..b100870f02a6 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -99,6 +99,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, u16 *queue_mapping = NULL, *ptype = NULL; bool exists = false; int ret = 0, err; + u32 index; if (nla == NULL) return -EINVAL; @@ -146,8 +147,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, } parm = nla_data(tb[TCA_SKBEDIT_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -158,15 +159,15 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_skbedit_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 4f07706eff07..7da3518e18ef 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -87,12 +87,12 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, struct tcf_skbmod_params *p, *p_old; struct tcf_chain *goto_ch = NULL; struct tc_skbmod *parm; + u32 lflags = 0, index; struct tcf_skbmod *d; bool exists = false; u8 *daddr = NULL; u8 *saddr = NULL; u16 eth_type = 0; - u32 lflags = 0; int ret = 0, err; if (!nla) @@ -122,10 +122,11 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, } parm = nla_data(tb[TCA_SKBMOD_PARMS]); + index = parm->index; if (parm->flags & SKBMOD_F_SWAPMAC) lflags = SKBMOD_F_SWAPMAC; - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -136,15 +137,15 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_skbmod_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 10dffda1d5cc..6d0debdc9b97 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -225,6 +225,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, __be16 flags = 0; u8 tos, ttl; int ret = 0; + u32 index; int err; if (!nla) { @@ -245,7 +246,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, } parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -345,7 +347,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_tunnel_key_ops, bind, true); if (ret) { NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); @@ -403,7 +405,7 @@ err_out: if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 9269d350fb8a..984b05ab0c87 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -116,6 +116,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, u8 push_prio = 0; bool exists = false; int ret = 0, err; + u32 index; if (!nla) return -EINVAL; @@ -128,7 +129,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (!tb[TCA_VLAN_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_VLAN_PARMS]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -144,7 +146,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]); @@ -152,7 +154,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -ERANGE; } @@ -166,7 +168,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EPROTONOSUPPORT; } } else { @@ -180,16 +182,16 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } action = parm->v_action; if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_vlan_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } From 60d60c8fbd8d1acf25b041ecd72ae4fa16e9405b Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 1 Aug 2019 09:52:54 -0400 Subject: [PATCH 788/823] net/mlx5e: always initialize frag->last_in_page The commit 069d11465a80 ("net/mlx5e: RX, Enhance legacy Receive Queue memory scheme") introduced an undefined behaviour below due to "frag->last_in_page" is only initialized in mlx5e_init_frags_partition() when, if (next_frag.offset + frag_info[f].frag_stride > PAGE_SIZE) or after bailed out the loop, for (i = 0; i < mlx5_wq_cyc_get_size(&rq->wqe.wq); i++) As the result, there could be some "frag" have uninitialized value of "last_in_page". Later, get_frag() obtains those "frag" and check "frag->last_in_page" in mlx5e_put_rx_frag() and triggers the error during boot. Fix it by always initializing "frag->last_in_page" to "false" in mlx5e_init_frags_partition(). UBSAN: Undefined behaviour in drivers/net/ethernet/mellanox/mlx5/core/en_rx.c:325:12 load of value 170 is not a valid value for type 'bool' (aka '_Bool') Call trace: dump_backtrace+0x0/0x264 show_stack+0x20/0x2c dump_stack+0xb0/0x104 __ubsan_handle_load_invalid_value+0x104/0x128 mlx5e_handle_rx_cqe+0x8e8/0x12cc [mlx5_core] mlx5e_poll_rx_cq+0xca8/0x1a94 [mlx5_core] mlx5e_napi_poll+0x17c/0xa30 [mlx5_core] net_rx_action+0x248/0x940 __do_softirq+0x350/0x7b8 irq_exit+0x200/0x26c __handle_domain_irq+0xc8/0x128 gic_handle_irq+0x138/0x228 el1_irq+0xb8/0x140 arch_cpu_idle+0x1a4/0x348 do_idle+0x114/0x1b0 cpu_startup_entry+0x24/0x28 rest_init+0x1ac/0x1dc arch_call_rest_init+0x10/0x18 start_kernel+0x4d4/0x57c Fixes: 069d11465a80 ("net/mlx5e: RX, Enhance legacy Receive Queue memory scheme") Signed-off-by: Qian Cai Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 570c42b7eeea..6c712c5be4d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -331,12 +331,11 @@ static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix) static void mlx5e_init_frags_partition(struct mlx5e_rq *rq) { - struct mlx5e_wqe_frag_info next_frag, *prev; + struct mlx5e_wqe_frag_info next_frag = {}; + struct mlx5e_wqe_frag_info *prev = NULL; int i; next_frag.di = &rq->wqe.di[0]; - next_frag.offset = 0; - prev = NULL; for (i = 0; i < mlx5_wq_cyc_get_size(&rq->wqe.wq); i++) { struct mlx5e_rq_frag_info *frag_info = &rq->wqe.info.arr[0]; From 4de9c89a4982431c4a02739743fd360dc5581f22 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 1 Aug 2019 20:00:16 +0200 Subject: [PATCH 789/823] bpf: fix XDP vlan selftests test_xdp_vlan.sh Change BPF selftest test_xdp_vlan.sh to (default) use generic XDP. This selftest was created together with a fix for generic XDP, in commit 297249569932 ("net: fix generic XDP to handle if eth header was mangled"). And was suppose to catch if generic XDP was broken again. The tests are using veth and assumed that veth driver didn't support native driver XDP, thus it used the (ip link set) 'xdp' attach that fell back to generic-XDP. But veth gained native-XDP support in 948d4f214fde ("veth: Add driver XDP"), which caused this test script to use native-XDP. Fixes: 948d4f214fde ("veth: Add driver XDP") Fixes: 97396ff0bc2d ("selftests/bpf: add XDP selftests for modifying and popping VLAN headers") Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- tools/testing/selftests/bpf/test_xdp_vlan.sh | 42 +++++++++++++++++--- 1 file changed, 36 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh index 51a3a31d1aac..c8aed63b0ffe 100755 --- a/tools/testing/selftests/bpf/test_xdp_vlan.sh +++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh @@ -1,7 +1,12 @@ #!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Author: Jesper Dangaard Brouer TESTNAME=xdp_vlan +# Default XDP mode +XDP_MODE=xdpgeneric + usage() { echo "Testing XDP + TC eBPF VLAN manipulations: $TESTNAME" echo "" @@ -9,9 +14,23 @@ usage() { echo " -v | --verbose : Verbose" echo " --flush : Flush before starting (e.g. after --interactive)" echo " --interactive : Keep netns setup running after test-run" + echo " --mode=XXX : Choose XDP mode (xdp | xdpgeneric | xdpdrv)" echo "" } +valid_xdp_mode() +{ + local mode=$1 + + case "$mode" in + xdpgeneric | xdpdrv | xdp) + return 0 + ;; + *) + return 1 + esac +} + cleanup() { local status=$? @@ -37,7 +56,7 @@ cleanup() # Using external program "getopt" to get --long-options OPTIONS=$(getopt -o hvfi: \ - --long verbose,flush,help,interactive,debug -- "$@") + --long verbose,flush,help,interactive,debug,mode: -- "$@") if (( $? != 0 )); then usage echo "selftests: $TESTNAME [FAILED] Error calling getopt, unknown option?" @@ -60,6 +79,11 @@ while true; do cleanup shift ;; + --mode ) + shift + XDP_MODE=$1 + shift + ;; -- ) shift break @@ -81,8 +105,14 @@ if [ "$EUID" -ne 0 ]; then exit 1 fi -ip link set dev lo xdp off 2>/dev/null > /dev/null -if [ $? -ne 0 ];then +valid_xdp_mode $XDP_MODE +if [ $? -ne 0 ]; then + echo "selftests: $TESTNAME [FAILED] unknown XDP mode ($XDP_MODE)" + exit 1 +fi + +ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null +if [ $? -ne 0 ]; then echo "selftests: $TESTNAME [SKIP] need ip xdp support" exit 0 fi @@ -166,7 +196,7 @@ export FILE=test_xdp_vlan.o # First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change" export XDP_PROG=xdp_vlan_change -ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG +ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG # In ns1: egress use TC to add back VLAN tag 4011 # (del cmd) @@ -187,8 +217,8 @@ ip netns exec ns1 ping -W 2 -c 3 $IPADDR2 # ETH_P_8021Q indication, and this cause overwriting of our changes. # export XDP_PROG=xdp_vlan_remove_outer2 -ip netns exec ns1 ip link set $DEVNS1 xdp off -ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG +ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE off +ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG # Now the namespaces should still be able reach each-other, test with ping: ip netns exec ns2 ping -W 2 -c 3 $IPADDR1 From d35661fcf95d8818c1f9acc818a1bad23dda4e1c Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 1 Aug 2019 20:00:21 +0200 Subject: [PATCH 790/823] selftests/bpf: add wrapper scripts for test_xdp_vlan.sh In-order to test both native-XDP (xdpdrv) and generic-XDP (xdpgeneric) create two wrapper test scripts, that start the test_xdp_vlan.sh script with these modes. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- tools/testing/selftests/bpf/Makefile | 3 ++- tools/testing/selftests/bpf/test_xdp_vlan.sh | 5 ++++- .../testing/selftests/bpf/test_xdp_vlan_mode_generic.sh | 9 +++++++++ tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh | 9 +++++++++ 4 files changed, 24 insertions(+), 2 deletions(-) create mode 100755 tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh create mode 100755 tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 11c9c62c3362..c085964e1d05 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -57,7 +57,8 @@ TEST_PROGS := test_kmod.sh \ test_lirc_mode2.sh \ test_skb_cgroup_id.sh \ test_flow_dissector.sh \ - test_xdp_vlan.sh \ + test_xdp_vlan_mode_generic.sh \ + test_xdp_vlan_mode_native.sh \ test_lwt_ip_encap.sh \ test_tcp_check_syncookie.sh \ test_tc_tunnel.sh \ diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh index c8aed63b0ffe..7348661be815 100755 --- a/tools/testing/selftests/bpf/test_xdp_vlan.sh +++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh @@ -2,7 +2,10 @@ # SPDX-License-Identifier: GPL-2.0 # Author: Jesper Dangaard Brouer -TESTNAME=xdp_vlan +# Allow wrapper scripts to name test +if [ -z "$TESTNAME" ]; then + TESTNAME=xdp_vlan +fi # Default XDP mode XDP_MODE=xdpgeneric diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh new file mode 100755 index 000000000000..c515326d6d59 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Exit on failure +set -e + +# Wrapper script to test generic-XDP +export TESTNAME=xdp_vlan_mode_generic +./test_xdp_vlan.sh --mode=xdpgeneric diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh new file mode 100755 index 000000000000..5cf7ce1f16c1 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Exit on failure +set -e + +# Wrapper script to test native-XDP +export TESTNAME=xdp_vlan_mode_native +./test_xdp_vlan.sh --mode=xdpdrv From 13978d1e73d2fcfb6addcf3392707ad68fa88ccb Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 1 Aug 2019 20:00:26 +0200 Subject: [PATCH 791/823] selftests/bpf: reduce time to execute test_xdp_vlan.sh Given the increasing number of BPF selftests, it makes sense to reduce the time to execute these tests. The ping parameters are adjusted to reduce the time from measures 9 sec to approx 2.8 sec. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- tools/testing/selftests/bpf/test_xdp_vlan.sh | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh index 7348661be815..bb8b0da91686 100755 --- a/tools/testing/selftests/bpf/test_xdp_vlan.sh +++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh @@ -188,7 +188,7 @@ ip netns exec ns2 ip link set lo up # At this point, the hosts cannot reach each-other, # because ns2 are using VLAN tags on the packets. -ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Okay ping fails"' +ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Success: First ping must fail"' # Now we can use the test_xdp_vlan.c program to pop/push these VLAN tags @@ -210,8 +210,8 @@ ip netns exec ns1 tc filter add dev $DEVNS1 egress \ prio 1 handle 1 bpf da obj $FILE sec tc_vlan_push # Now the namespaces can reach each-other, test with ping: -ip netns exec ns2 ping -W 2 -c 3 $IPADDR1 -ip netns exec ns1 ping -W 2 -c 3 $IPADDR2 +ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1 +ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2 # Second test: Replace xdp prog, that fully remove vlan header # @@ -224,5 +224,5 @@ ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE off ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG # Now the namespaces should still be able reach each-other, test with ping: -ip netns exec ns2 ping -W 2 -c 3 $IPADDR1 -ip netns exec ns1 ping -W 2 -c 3 $IPADDR2 +ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1 +ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2 From 065af355470519bd184019a93ac579f22b036045 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 1 Aug 2019 20:00:31 +0200 Subject: [PATCH 792/823] net: fix bpf_xdp_adjust_head regression for generic-XDP When generic-XDP was moved to a later processing step by commit 458bf2f224f0 ("net: core: support XDP generic on stacked devices.") a regression was introduced when using bpf_xdp_adjust_head. The issue is that after this commit the skb->network_header is now changed prior to calling generic XDP and not after. Thus, if the header is changed by XDP (via bpf_xdp_adjust_head), then skb->network_header also need to be updated again. Fix by calling skb_reset_network_header(). Fixes: 458bf2f224f0 ("net: core: support XDP generic on stacked devices.") Reported-by: Brandon Cazander Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- net/core/dev.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 2f341b850845..0891f499c1bb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4374,12 +4374,17 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, act = bpf_prog_run_xdp(xdp_prog, xdp); + /* check if bpf_xdp_adjust_head was used */ off = xdp->data - orig_data; - if (off > 0) - __skb_pull(skb, off); - else if (off < 0) - __skb_push(skb, -off); - skb->mac_header += off; + if (off) { + if (off > 0) + __skb_pull(skb, off); + else if (off < 0) + __skb_push(skb, -off); + + skb->mac_header += off; + skb_reset_network_header(skb); + } /* check if bpf_xdp_adjust_tail was used. it can only "shrink" * pckt. From 5d92e631b8be8965a90c144320f06e096081a551 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 1 Aug 2019 14:36:01 -0700 Subject: [PATCH 793/823] net/tls: partially revert fix transition through disconnect with close Looks like we were slightly overzealous with the shutdown() cleanup. Even though the sock->sk_state can reach CLOSED again, socket->state will not got back to SS_UNCONNECTED once connections is ESTABLISHED. Meaning we will see EISCONN if we try to reconnect, and EINVAL if we try to listen. Only listen sockets can be shutdown() and reused, but since ESTABLISHED sockets can never be re-connected() or used for listen() we don't need to try to clean up the ULP state early. Fixes: 32857cf57f92 ("net/tls: fix transition through disconnect with close") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- Documentation/networking/tls-offload.rst | 6 --- include/net/tls.h | 2 - net/tls/tls_main.c | 55 ------------------------ 3 files changed, 63 deletions(-) diff --git a/Documentation/networking/tls-offload.rst b/Documentation/networking/tls-offload.rst index 2d9f9ebf4117..b70b70dc4524 100644 --- a/Documentation/networking/tls-offload.rst +++ b/Documentation/networking/tls-offload.rst @@ -524,9 +524,3 @@ Redirects leak clear text In the RX direction, if segment has already been decrypted by the device and it gets redirected or mirrored - clear text will be transmitted out. - -shutdown() doesn't clear TLS state ----------------------------------- - -shutdown() system call allows for a TLS socket to be reused as a different -connection. Offload doesn't currently handle that. diff --git a/include/net/tls.h b/include/net/tls.h index 9e425ac2de45..41b2d41bb1b8 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -290,8 +290,6 @@ struct tls_context { struct list_head list; refcount_t refcount; - - struct work_struct gc; }; enum tls_offload_ctx_dir { diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index f208f8455ef2..9cbbae606ced 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -261,33 +261,6 @@ void tls_ctx_free(struct tls_context *ctx) kfree(ctx); } -static void tls_ctx_free_deferred(struct work_struct *gc) -{ - struct tls_context *ctx = container_of(gc, struct tls_context, gc); - - /* Ensure any remaining work items are completed. The sk will - * already have lost its tls_ctx reference by the time we get - * here so no xmit operation will actually be performed. - */ - if (ctx->tx_conf == TLS_SW) { - tls_sw_cancel_work_tx(ctx); - tls_sw_free_ctx_tx(ctx); - } - - if (ctx->rx_conf == TLS_SW) { - tls_sw_strparser_done(ctx); - tls_sw_free_ctx_rx(ctx); - } - - tls_ctx_free(ctx); -} - -static void tls_ctx_free_wq(struct tls_context *ctx) -{ - INIT_WORK(&ctx->gc, tls_ctx_free_deferred); - schedule_work(&ctx->gc); -} - static void tls_sk_proto_cleanup(struct sock *sk, struct tls_context *ctx, long timeo) { @@ -315,29 +288,6 @@ static void tls_sk_proto_cleanup(struct sock *sk, #endif } -static void tls_sk_proto_unhash(struct sock *sk) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - long timeo = sock_sndtimeo(sk, 0); - struct tls_context *ctx; - - if (unlikely(!icsk->icsk_ulp_data)) { - if (sk->sk_prot->unhash) - sk->sk_prot->unhash(sk); - } - - ctx = tls_get_ctx(sk); - tls_sk_proto_cleanup(sk, ctx, timeo); - write_lock_bh(&sk->sk_callback_lock); - icsk->icsk_ulp_data = NULL; - sk->sk_prot = ctx->sk_proto; - write_unlock_bh(&sk->sk_callback_lock); - - if (ctx->sk_proto->unhash) - ctx->sk_proto->unhash(sk); - tls_ctx_free_wq(ctx); -} - static void tls_sk_proto_close(struct sock *sk, long timeout) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -786,7 +736,6 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_BASE][TLS_BASE].setsockopt = tls_setsockopt; prot[TLS_BASE][TLS_BASE].getsockopt = tls_getsockopt; prot[TLS_BASE][TLS_BASE].close = tls_sk_proto_close; - prot[TLS_BASE][TLS_BASE].unhash = tls_sk_proto_unhash; prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; prot[TLS_SW][TLS_BASE].sendmsg = tls_sw_sendmsg; @@ -804,20 +753,16 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], #ifdef CONFIG_TLS_DEVICE prot[TLS_HW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; - prot[TLS_HW][TLS_BASE].unhash = base->unhash; prot[TLS_HW][TLS_BASE].sendmsg = tls_device_sendmsg; prot[TLS_HW][TLS_BASE].sendpage = tls_device_sendpage; prot[TLS_HW][TLS_SW] = prot[TLS_BASE][TLS_SW]; - prot[TLS_HW][TLS_SW].unhash = base->unhash; prot[TLS_HW][TLS_SW].sendmsg = tls_device_sendmsg; prot[TLS_HW][TLS_SW].sendpage = tls_device_sendpage; prot[TLS_BASE][TLS_HW] = prot[TLS_BASE][TLS_SW]; - prot[TLS_BASE][TLS_HW].unhash = base->unhash; prot[TLS_SW][TLS_HW] = prot[TLS_SW][TLS_SW]; - prot[TLS_SW][TLS_HW].unhash = base->unhash; prot[TLS_HW][TLS_HW] = prot[TLS_HW][TLS_SW]; #endif From cd114d2e81f632104b3f1e804104060b97337410 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 1 Aug 2019 14:36:02 -0700 Subject: [PATCH 794/823] selftests/tls: add a litmus test for the socket reuse through shutdown Make sure that shutdown never works, and at the same time document how I tested to came to the conclusion that currently reuse is not possible. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- tools/testing/selftests/net/tls.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index d995e6503b1a..4c285b6e1db8 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -984,6 +984,30 @@ TEST_F(tls, shutdown_unsent) shutdown(self->cfd, SHUT_RDWR); } +TEST_F(tls, shutdown_reuse) +{ + struct sockaddr_in addr; + int ret; + + shutdown(self->fd, SHUT_RDWR); + shutdown(self->cfd, SHUT_RDWR); + close(self->cfd); + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + ret = bind(self->fd, &addr, sizeof(addr)); + EXPECT_EQ(ret, 0); + ret = listen(self->fd, 10); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, EINVAL); + + ret = connect(self->fd, &addr, sizeof(addr)); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, EISCONN); +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; From cff6a327d78b05c98e0d1c4be77225ea2c0bfe8e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 1 Aug 2019 14:36:35 -0700 Subject: [PATCH 795/823] ipv6: Fix unbalanced rcu locking in rt6_update_exception_stamp_rt The nexthop path in rt6_update_exception_stamp_rt needs to call rcu_read_unlock if it fails to find a fib6_nh match rather than just returning. Fixes: e659ba31d806 ("ipv6: Handle all fib6_nh in a nexthop in exception handling") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e49fec767a10..fd059e08785a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1951,7 +1951,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) nexthop_for_each_fib6_nh(from->nh, fib6_nh_find_match, &arg); if (!arg.match) - return; + goto unlock; fib6_nh = arg.match; } else { fib6_nh = from->fib6_nh; From 438b43bdb95d3189e0098919f321c014ed71f410 Mon Sep 17 00:00:00 2001 From: Catherine Sullivan Date: Thu, 1 Aug 2019 16:07:31 -0700 Subject: [PATCH 796/823] gve: Fix case where desc_cnt and data_cnt can get out of sync desc_cnt and data_cnt should always be equal. In the case of a dropped packet desc_cnt was still getting updated (correctly), data_cnt was not. To eliminate this bug and prevent it from recurring this patch combines them into one ring level cnt. Signed-off-by: Catherine Sullivan Reviewed-by: Sagi Shahar Signed-off-by: David S. Miller --- drivers/net/ethernet/google/gve/gve.h | 8 ++--- drivers/net/ethernet/google/gve/gve_ethtool.c | 4 +-- drivers/net/ethernet/google/gve/gve_rx.c | 34 ++++++++----------- 3 files changed, 20 insertions(+), 26 deletions(-) diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 92372dc43be8..ebc37e256922 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -31,9 +31,6 @@ struct gve_rx_desc_queue { struct gve_rx_desc *desc_ring; /* the descriptor ring */ dma_addr_t bus; /* the bus for the desc_ring */ - u32 cnt; /* free-running total number of completed packets */ - u32 fill_cnt; /* free-running total number of descriptors posted */ - u32 mask; /* masks the cnt to the size of the ring */ u8 seqno; /* the next expected seqno for this desc*/ }; @@ -60,8 +57,6 @@ struct gve_rx_data_queue { dma_addr_t data_bus; /* dma mapping of the slots */ struct gve_rx_slot_page_info *page_info; /* page info of the buffers */ struct gve_queue_page_list *qpl; /* qpl assigned to this queue */ - u32 mask; /* masks the cnt to the size of the ring */ - u32 cnt; /* free-running total number of completed packets */ }; struct gve_priv; @@ -73,6 +68,9 @@ struct gve_rx_ring { struct gve_rx_data_queue data; u64 rbytes; /* free-running bytes received */ u64 rpackets; /* free-running packets received */ + u32 cnt; /* free-running total number of completed packets */ + u32 fill_cnt; /* free-running total number of descs and buffs posted */ + u32 mask; /* masks the cnt and fill_cnt to the size of the ring */ u32 q_num; /* queue index */ u32 ntfy_id; /* notification block index */ struct gve_queue_resources *q_resources; /* head and tail pointer idx */ diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 26540b856541..d8fa816f4473 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -138,8 +138,8 @@ gve_get_ethtool_stats(struct net_device *netdev, for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) { struct gve_rx_ring *rx = &priv->rx[ring]; - data[i++] = rx->desc.cnt; - data[i++] = rx->desc.fill_cnt; + data[i++] = rx->cnt; + data[i++] = rx->fill_cnt; } } else { i += priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS; diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index 1914b8350da7..59564ac99d2a 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -37,7 +37,7 @@ static void gve_rx_free_ring(struct gve_priv *priv, int idx) rx->data.qpl = NULL; kvfree(rx->data.page_info); - slots = rx->data.mask + 1; + slots = rx->mask + 1; bytes = sizeof(*rx->data.data_ring) * slots; dma_free_coherent(dev, bytes, rx->data.data_ring, rx->data.data_bus); @@ -64,7 +64,7 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx) /* Allocate one page per Rx queue slot. Each page is split into two * packet buffers, when possible we "page flip" between the two. */ - slots = rx->data.mask + 1; + slots = rx->mask + 1; rx->data.page_info = kvzalloc(slots * sizeof(*rx->data.page_info), GFP_KERNEL); @@ -111,7 +111,7 @@ static int gve_rx_alloc_ring(struct gve_priv *priv, int idx) rx->q_num = idx; slots = priv->rx_pages_per_qpl; - rx->data.mask = slots - 1; + rx->mask = slots - 1; /* alloc rx data ring */ bytes = sizeof(*rx->data.data_ring) * slots; @@ -125,7 +125,7 @@ static int gve_rx_alloc_ring(struct gve_priv *priv, int idx) err = -ENOMEM; goto abort_with_slots; } - rx->desc.fill_cnt = filled_pages; + rx->fill_cnt = filled_pages; /* Ensure data ring slots (packet buffers) are visible. */ dma_wmb(); @@ -156,8 +156,8 @@ static int gve_rx_alloc_ring(struct gve_priv *priv, int idx) err = -ENOMEM; goto abort_with_q_resources; } - rx->desc.mask = slots - 1; - rx->desc.cnt = 0; + rx->mask = slots - 1; + rx->cnt = 0; rx->desc.seqno = 1; gve_rx_add_to_block(priv, idx); @@ -213,7 +213,7 @@ void gve_rx_write_doorbell(struct gve_priv *priv, struct gve_rx_ring *rx) { u32 db_idx = be32_to_cpu(rx->q_resources->db_index); - iowrite32be(rx->desc.fill_cnt, &priv->db_bar2[db_idx]); + iowrite32be(rx->fill_cnt, &priv->db_bar2[db_idx]); } static enum pkt_hash_types gve_rss_type(__be16 pkt_flags) @@ -273,7 +273,7 @@ static void gve_rx_flip_buff(struct gve_rx_slot_page_info *page_info, } static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, - netdev_features_t feat) + netdev_features_t feat, u32 idx) { struct gve_rx_slot_page_info *page_info; struct gve_priv *priv = rx->gve; @@ -282,14 +282,12 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, struct sk_buff *skb; int pagecount; u16 len; - u32 idx; /* drop this packet */ if (unlikely(rx_desc->flags_seq & GVE_RXF_ERR)) return true; len = be16_to_cpu(rx_desc->len) - GVE_RX_PAD; - idx = rx->data.cnt & rx->data.mask; page_info = &rx->data.page_info[idx]; /* gvnic can only receive into registered segments. If the buffer @@ -340,8 +338,6 @@ have_skb: if (!skb) return true; - rx->data.cnt++; - if (likely(feat & NETIF_F_RXCSUM)) { /* NIC passes up the partial sum */ if (rx_desc->csum) @@ -370,7 +366,7 @@ static bool gve_rx_work_pending(struct gve_rx_ring *rx) __be16 flags_seq; u32 next_idx; - next_idx = rx->desc.cnt & rx->desc.mask; + next_idx = rx->cnt & rx->mask; desc = rx->desc.desc_ring + next_idx; flags_seq = desc->flags_seq; @@ -385,8 +381,8 @@ bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, { struct gve_priv *priv = rx->gve; struct gve_rx_desc *desc; - u32 cnt = rx->desc.cnt; - u32 idx = cnt & rx->desc.mask; + u32 cnt = rx->cnt; + u32 idx = cnt & rx->mask; u32 work_done = 0; u64 bytes = 0; @@ -401,10 +397,10 @@ bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, rx->q_num, GVE_SEQNO(desc->flags_seq), rx->desc.seqno); bytes += be16_to_cpu(desc->len) - GVE_RX_PAD; - if (!gve_rx(rx, desc, feat)) + if (!gve_rx(rx, desc, feat, idx)) gve_schedule_reset(priv); cnt++; - idx = cnt & rx->desc.mask; + idx = cnt & rx->mask; desc = rx->desc.desc_ring + idx; rx->desc.seqno = gve_next_seqno(rx->desc.seqno); work_done++; @@ -417,8 +413,8 @@ bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, rx->rpackets += work_done; rx->rbytes += bytes; u64_stats_update_end(&rx->statss); - rx->desc.cnt = cnt; - rx->desc.fill_cnt += work_done; + rx->cnt = cnt; + rx->fill_cnt += work_done; /* restock desc ring slots */ dma_wmb(); /* Ensure descs are visible before ringing doorbell */ From f9cedf1a9b1cdcfb0c52edb391d01771e43994a4 Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Fri, 2 Aug 2019 10:16:38 +0200 Subject: [PATCH 797/823] net/smc: do not schedule tx_work in SMC_CLOSED state The setsockopts options TCP_NODELAY and TCP_CORK may schedule the tx worker. Make sure the socket is not yet moved into SMC_CLOSED state (for instance by a shutdown SHUT_RDWR call). Reported-by: syzbot+92209502e7aab127c75f@syzkaller.appspotmail.com Reported-by: syzbot+b972214bb803a343f4fe@syzkaller.appspotmail.com Fixes: 01d2f7e2cdd31 ("net/smc: sockopts TCP_NODELAY and TCP_CORK") Signed-off-by: Ursula Braun Signed-off-by: Karsten Graul Signed-off-by: David S. Miller --- net/smc/af_smc.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 302e355f2ebc..f5ea09258ab0 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1732,14 +1732,18 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, } break; case TCP_NODELAY: - if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) { + if (sk->sk_state != SMC_INIT && + sk->sk_state != SMC_LISTEN && + sk->sk_state != SMC_CLOSED) { if (val && !smc->use_fallback) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } break; case TCP_CORK: - if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) { + if (sk->sk_state != SMC_INIT && + sk->sk_state != SMC_LISTEN && + sk->sk_state != SMC_CLOSED) { if (!val && !smc->use_fallback) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); From cd2063604ea6a8c2683b4eb9b5f4c4da74592d87 Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Fri, 2 Aug 2019 10:47:50 +0200 Subject: [PATCH 798/823] net/smc: avoid fallback in case of non-blocking connect FASTOPEN is not possible with SMC. sendmsg() with msg_flag MSG_FASTOPEN triggers a fallback to TCP if the socket is in state SMC_INIT. But if a nonblocking connect is already started, fallback to TCP is no longer possible, even though the socket may still be in state SMC_INIT. And if a nonblocking connect is already started, a listen() call does not make sense. Reported-by: syzbot+bd8cc73d665590a1fcad@syzkaller.appspotmail.com Fixes: 50717a37db032 ("net/smc: nonblocking connect rework") Signed-off-by: Ursula Braun Signed-off-by: Karsten Graul Signed-off-by: David S. Miller --- net/smc/af_smc.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index f5ea09258ab0..5b932583e407 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -263,7 +263,7 @@ static int smc_bind(struct socket *sock, struct sockaddr *uaddr, /* Check if socket is already active */ rc = -EINVAL; - if (sk->sk_state != SMC_INIT) + if (sk->sk_state != SMC_INIT || smc->connect_nonblock) goto out_rel; smc->clcsock->sk->sk_reuse = sk->sk_reuse; @@ -1390,7 +1390,8 @@ static int smc_listen(struct socket *sock, int backlog) lock_sock(sk); rc = -EINVAL; - if ((sk->sk_state != SMC_INIT) && (sk->sk_state != SMC_LISTEN)) + if ((sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) || + smc->connect_nonblock) goto out; rc = 0; @@ -1518,7 +1519,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) goto out; if (msg->msg_flags & MSG_FASTOPEN) { - if (sk->sk_state == SMC_INIT) { + if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { From d934423ac26ed373dfe089734d505dca5ff679b6 Mon Sep 17 00:00:00 2001 From: "Arnaud Patard (Rtp)" Date: Fri, 2 Aug 2019 10:32:40 +0200 Subject: [PATCH 799/823] drivers/net/ethernet/marvell/mvmdio.c: Fix non OF case Orion5.x systems are still using machine files and not device-tree. Commit 96cb4342382290c9 ("net: mvmdio: allow up to three clocks to be specified for orion-mdio") has replaced devm_clk_get() with of_clk_get(), leading to a oops at boot and not working network, as reported in https://lists.debian.org/debian-arm/2019/07/msg00088.html and possibly in https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=908712. Link: https://lists.debian.org/debian-arm/2019/07/msg00088.html Fixes: 96cb4342382290c9 ("net: mvmdio: allow up to three clocks to be specified for orion-mdio") Signed-off-by: Arnaud Patard Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvmdio.c | 31 +++++++++++++++++++-------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c index f660cc2b8258..0b9e851f3da4 100644 --- a/drivers/net/ethernet/marvell/mvmdio.c +++ b/drivers/net/ethernet/marvell/mvmdio.c @@ -319,20 +319,33 @@ static int orion_mdio_probe(struct platform_device *pdev) init_waitqueue_head(&dev->smi_busy_wait); - for (i = 0; i < ARRAY_SIZE(dev->clk); i++) { - dev->clk[i] = of_clk_get(pdev->dev.of_node, i); - if (PTR_ERR(dev->clk[i]) == -EPROBE_DEFER) { + if (pdev->dev.of_node) { + for (i = 0; i < ARRAY_SIZE(dev->clk); i++) { + dev->clk[i] = of_clk_get(pdev->dev.of_node, i); + if (PTR_ERR(dev->clk[i]) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto out_clk; + } + if (IS_ERR(dev->clk[i])) + break; + clk_prepare_enable(dev->clk[i]); + } + + if (!IS_ERR(of_clk_get(pdev->dev.of_node, + ARRAY_SIZE(dev->clk)))) + dev_warn(&pdev->dev, + "unsupported number of clocks, limiting to the first " + __stringify(ARRAY_SIZE(dev->clk)) "\n"); + } else { + dev->clk[0] = clk_get(&pdev->dev, NULL); + if (PTR_ERR(dev->clk[0]) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; goto out_clk; } - if (IS_ERR(dev->clk[i])) - break; - clk_prepare_enable(dev->clk[i]); + if (!IS_ERR(dev->clk[0])) + clk_prepare_enable(dev->clk[0]); } - if (!IS_ERR(of_clk_get(pdev->dev.of_node, ARRAY_SIZE(dev->clk)))) - dev_warn(&pdev->dev, "unsupported number of clocks, limiting to the first " - __stringify(ARRAY_SIZE(dev->clk)) "\n"); dev->err_interrupt = platform_get_irq(pdev, 0); if (dev->err_interrupt > 0 && From 091adf9ba6cdb432cbcc217b47e4ffb8aa0d8865 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 2 Aug 2019 13:57:36 +0300 Subject: [PATCH 800/823] net: bridge: move default pvid init/deinit to NETDEV_REGISTER/UNREGISTER Most of the bridge device's vlan init bugs come from the fact that its default pvid is created at the wrong time, way too early in ndo_init() before the device is even assigned an ifindex. It introduces a bug when the bridge's dev_addr is added as fdb during the initial default pvid creation the notification has ifindex/NDA_MASTER both equal to 0 (see example below) which really makes no sense for user-space[0] and is wrong. Usually user-space software would ignore such entries, but they are actually valid and will eventually have all necessary attributes. It makes much more sense to send a notification *after* the device has registered and has a proper ifindex allocated rather than before when there's a chance that the registration might still fail or to receive it with ifindex/NDA_MASTER == 0. Note that we can remove the fdb flush from br_vlan_flush() since that case can no longer happen. At NETDEV_REGISTER br->default_pvid is always == 1 as it's initialized by br_vlan_init() before that and at NETDEV_UNREGISTER it can be anything depending why it was called (if called due to NETDEV_REGISTER error it'll still be == 1, otherwise it could be any value changed during the device life time). For the demonstration below a small change to iproute2 for printing all fdb notifications is added, because it contained a workaround not to show entries with ifindex == 0. Command executed while monitoring: $ ip l add br0 type bridge Before (both ifindex and master == 0): $ bridge monitor fdb 36:7e:8a:b3:56:ba dev * vlan 1 master * permanent After (proper br0 ifindex): $ bridge monitor fdb e6:2a:ae:7a:b7:48 dev br0 vlan 1 master br0 permanent v4: move only the default pvid init/deinit to NETDEV_REGISTER/UNREGISTER v3: send the correct v2 patch with all changes (stub should return 0) v2: on error in br_vlan_init set br->vlgrp to NULL and return 0 in the br_vlan_bridge_event stub when bridge vlans are disabled [0] https://bugzilla.kernel.org/show_bug.cgi?id=204389 Reported-by: michael-dev Fixes: 5be5a2df40f0 ("bridge: Add filtering support for default_pvid") Signed-off-by: Nikolay Aleksandrov Acked-by: Roopa Prabhu Signed-off-by: David S. Miller --- net/bridge/br.c | 5 ++++- net/bridge/br_private.h | 9 +++++---- net/bridge/br_vlan.c | 34 ++++++++++++++++------------------ 3 files changed, 25 insertions(+), 23 deletions(-) diff --git a/net/bridge/br.c b/net/bridge/br.c index d164f63a4345..8a8f9e5f264f 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -37,12 +37,15 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v int err; if (dev->priv_flags & IFF_EBRIDGE) { + err = br_vlan_bridge_event(dev, event, ptr); + if (err) + return notifier_from_errno(err); + if (event == NETDEV_REGISTER) { /* register of bridge completed, add sysfs entries */ br_sysfs_addbr(dev); return NOTIFY_DONE; } - br_vlan_bridge_event(dev, event, ptr); } /* not a port of a bridge */ diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index e8cf03b43b7d..646504db0220 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -894,8 +894,8 @@ int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask); void br_vlan_get_stats(const struct net_bridge_vlan *v, struct br_vlan_stats *stats); void br_vlan_port_event(struct net_bridge_port *p, unsigned long event); -void br_vlan_bridge_event(struct net_device *dev, unsigned long event, - void *ptr); +int br_vlan_bridge_event(struct net_device *dev, unsigned long event, + void *ptr); static inline struct net_bridge_vlan_group *br_vlan_group( const struct net_bridge *br) @@ -1085,9 +1085,10 @@ static inline void br_vlan_port_event(struct net_bridge_port *p, { } -static inline void br_vlan_bridge_event(struct net_device *dev, - unsigned long event, void *ptr) +static inline int br_vlan_bridge_event(struct net_device *dev, + unsigned long event, void *ptr) { + return 0; } #endif diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index a544e161c7fa..f5b2aeebbfe9 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -715,11 +715,6 @@ void br_vlan_flush(struct net_bridge *br) ASSERT_RTNL(); - /* delete auto-added default pvid local fdb before flushing vlans - * otherwise it will be leaked on bridge device init failure - */ - br_fdb_delete_by_port(br, NULL, 0, 1); - vg = br_vlan_group(br); __vlan_flush(vg); RCU_INIT_POINTER(br->vlgrp, NULL); @@ -1058,7 +1053,6 @@ int br_vlan_init(struct net_bridge *br) { struct net_bridge_vlan_group *vg; int ret = -ENOMEM; - bool changed; vg = kzalloc(sizeof(*vg), GFP_KERNEL); if (!vg) @@ -1073,17 +1067,10 @@ int br_vlan_init(struct net_bridge *br) br->vlan_proto = htons(ETH_P_8021Q); br->default_pvid = 1; rcu_assign_pointer(br->vlgrp, vg); - ret = br_vlan_add(br, 1, - BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | - BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL); - if (ret) - goto err_vlan_add; out: return ret; -err_vlan_add: - vlan_tunnel_deinit(vg); err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: @@ -1469,13 +1456,23 @@ static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid) } /* Must be protected by RTNL. */ -void br_vlan_bridge_event(struct net_device *dev, unsigned long event, - void *ptr) +int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) { struct netdev_notifier_changeupper_info *info; - struct net_bridge *br; + struct net_bridge *br = netdev_priv(dev); + bool changed; + int ret = 0; switch (event) { + case NETDEV_REGISTER: + ret = br_vlan_add(br, br->default_pvid, + BRIDGE_VLAN_INFO_PVID | + BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL); + break; + case NETDEV_UNREGISTER: + br_vlan_delete(br, br->default_pvid); + break; case NETDEV_CHANGEUPPER: info = ptr; br_vlan_upper_change(dev, info->upper_dev, info->linking); @@ -1483,12 +1480,13 @@ void br_vlan_bridge_event(struct net_device *dev, unsigned long event, case NETDEV_CHANGE: case NETDEV_UP: - br = netdev_priv(dev); if (!br_opt_get(br, BROPT_VLAN_BRIDGE_BINDING)) - return; + break; br_vlan_link_state_change(dev, br); break; } + + return ret; } /* Must be protected by RTNL. */ From 74034a09267c1f48d5ce7ae4c4a317fac7d43418 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 5 Aug 2019 13:55:33 -0500 Subject: [PATCH 801/823] MIPS: BCM63XX: Mark expected switch fall-through MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Mark switch cases where we are expecting to fall through. This patch fixes the following warning (Building: bcm63xx_defconfig mips): arch/mips/pci/ops-bcm63xx.c: In function ‘bcm63xx_pcie_can_access’: arch/mips/pci/ops-bcm63xx.c:474:6: warning: this statement may fall through [-Wimplicit-fallthrough=] if (PCI_SLOT(devfn) == 0) ^ arch/mips/pci/ops-bcm63xx.c:477:2: note: here default: ^~~~~~~ Signed-off-by: Gustavo A. R. Silva Signed-off-by: Paul Burton Cc: Ralf Baechle Cc: James Hogan Cc: Florian Fainelli Cc: bcm-kernel-feedback-list@broadcom.com Cc: linux-mips@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org --- arch/mips/pci/ops-bcm63xx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/pci/ops-bcm63xx.c b/arch/mips/pci/ops-bcm63xx.c index d02eb9d16b55..925c72348fb6 100644 --- a/arch/mips/pci/ops-bcm63xx.c +++ b/arch/mips/pci/ops-bcm63xx.c @@ -474,6 +474,7 @@ static int bcm63xx_pcie_can_access(struct pci_bus *bus, int devfn) if (PCI_SLOT(devfn) == 0) return bcm_pcie_readl(PCIE_DLSTATUS_REG) & DLSTATUS_PHYLINKUP; + /* else, fall through */ default: return false; } From 9c09b214f30e3c11f9b0b03f89442df03643794d Mon Sep 17 00:00:00 2001 From: Hillf Danton Date: Tue, 6 Aug 2019 16:38:58 +0800 Subject: [PATCH 802/823] HID: hiddev: avoid opening a disconnected device syzbot found the following crash on: HEAD commit: e96407b4 usb-fuzzer: main usb gadget fuzzer driver git tree: https://github.com/google/kasan.git usb-fuzzer console output: https://syzkaller.appspot.com/x/log.txt?x=147ac20c600000 kernel config: https://syzkaller.appspot.com/x/.config?x=792eb47789f57810 dashboard link: https://syzkaller.appspot.com/bug?extid=62a1e04fd3ec2abf099e compiler: gcc (GCC) 9.0.0 20181231 (experimental) ================================================================== BUG: KASAN: use-after-free in __lock_acquire+0x302a/0x3b50 kernel/locking/lockdep.c:3753 Read of size 8 at addr ffff8881cf591a08 by task syz-executor.1/26260 CPU: 1 PID: 26260 Comm: syz-executor.1 Not tainted 5.3.0-rc2+ #24 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0xca/0x13e lib/dump_stack.c:113 print_address_description+0x6a/0x32c mm/kasan/report.c:351 __kasan_report.cold+0x1a/0x33 mm/kasan/report.c:482 kasan_report+0xe/0x12 mm/kasan/common.c:612 __lock_acquire+0x302a/0x3b50 kernel/locking/lockdep.c:3753 lock_acquire+0x127/0x320 kernel/locking/lockdep.c:4412 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] _raw_spin_lock_irqsave+0x32/0x50 kernel/locking/spinlock.c:159 hiddev_release+0x82/0x520 drivers/hid/usbhid/hiddev.c:221 __fput+0x2d7/0x840 fs/file_table.c:280 task_work_run+0x13f/0x1c0 kernel/task_work.c:113 exit_task_work include/linux/task_work.h:22 [inline] do_exit+0x8ef/0x2c50 kernel/exit.c:878 do_group_exit+0x125/0x340 kernel/exit.c:982 get_signal+0x466/0x23d0 kernel/signal.c:2728 do_signal+0x88/0x14e0 arch/x86/kernel/signal.c:815 exit_to_usermode_loop+0x1a2/0x200 arch/x86/entry/common.c:159 prepare_exit_to_usermode arch/x86/entry/common.c:194 [inline] syscall_return_slowpath arch/x86/entry/common.c:274 [inline] do_syscall_64+0x45f/0x580 arch/x86/entry/common.c:299 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x459829 Code: fd b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 cb b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f75b2a6ccf8 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: fffffffffffffe00 RBX: 000000000075c078 RCX: 0000000000459829 RDX: 0000000000000000 RSI: 0000000000000080 RDI: 000000000075c078 RBP: 000000000075c070 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000075c07c R13: 00007ffcdfe1023f R14: 00007f75b2a6d9c0 R15: 000000000075c07c Allocated by task 104: save_stack+0x1b/0x80 mm/kasan/common.c:69 set_track mm/kasan/common.c:77 [inline] __kasan_kmalloc mm/kasan/common.c:487 [inline] __kasan_kmalloc.constprop.0+0xbf/0xd0 mm/kasan/common.c:460 kmalloc include/linux/slab.h:552 [inline] kzalloc include/linux/slab.h:748 [inline] hiddev_connect+0x242/0x5b0 drivers/hid/usbhid/hiddev.c:900 hid_connect+0x239/0xbb0 drivers/hid/hid-core.c:1882 hid_hw_start drivers/hid/hid-core.c:1981 [inline] hid_hw_start+0xa2/0x130 drivers/hid/hid-core.c:1972 appleir_probe+0x13e/0x1a0 drivers/hid/hid-appleir.c:308 hid_device_probe+0x2be/0x3f0 drivers/hid/hid-core.c:2209 really_probe+0x281/0x650 drivers/base/dd.c:548 driver_probe_device+0x101/0x1b0 drivers/base/dd.c:709 __device_attach_driver+0x1c2/0x220 drivers/base/dd.c:816 bus_for_each_drv+0x15c/0x1e0 drivers/base/bus.c:454 __device_attach+0x217/0x360 drivers/base/dd.c:882 bus_probe_device+0x1e4/0x290 drivers/base/bus.c:514 device_add+0xae6/0x16f0 drivers/base/core.c:2114 hid_add_device+0x33c/0x990 drivers/hid/hid-core.c:2365 usbhid_probe+0xa81/0xfa0 drivers/hid/usbhid/hid-core.c:1386 usb_probe_interface+0x305/0x7a0 drivers/usb/core/driver.c:361 really_probe+0x281/0x650 drivers/base/dd.c:548 driver_probe_device+0x101/0x1b0 drivers/base/dd.c:709 __device_attach_driver+0x1c2/0x220 drivers/base/dd.c:816 bus_for_each_drv+0x15c/0x1e0 drivers/base/bus.c:454 __device_attach+0x217/0x360 drivers/base/dd.c:882 bus_probe_device+0x1e4/0x290 drivers/base/bus.c:514 device_add+0xae6/0x16f0 drivers/base/core.c:2114 usb_set_configuration+0xdf6/0x1670 drivers/usb/core/message.c:2023 generic_probe+0x9d/0xd5 drivers/usb/core/generic.c:210 usb_probe_device+0x99/0x100 drivers/usb/core/driver.c:266 really_probe+0x281/0x650 drivers/base/dd.c:548 driver_probe_device+0x101/0x1b0 drivers/base/dd.c:709 __device_attach_driver+0x1c2/0x220 drivers/base/dd.c:816 bus_for_each_drv+0x15c/0x1e0 drivers/base/bus.c:454 __device_attach+0x217/0x360 drivers/base/dd.c:882 bus_probe_device+0x1e4/0x290 drivers/base/bus.c:514 device_add+0xae6/0x16f0 drivers/base/core.c:2114 usb_new_device.cold+0x6a4/0xe79 drivers/usb/core/hub.c:2536 hub_port_connect drivers/usb/core/hub.c:5098 [inline] hub_port_connect_change drivers/usb/core/hub.c:5213 [inline] port_event drivers/usb/core/hub.c:5359 [inline] hub_event+0x1b5c/0x3640 drivers/usb/core/hub.c:5441 process_one_work+0x92b/0x1530 kernel/workqueue.c:2269 worker_thread+0x96/0xe20 kernel/workqueue.c:2415 kthread+0x318/0x420 kernel/kthread.c:255 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352 Freed by task 104: save_stack+0x1b/0x80 mm/kasan/common.c:69 set_track mm/kasan/common.c:77 [inline] __kasan_slab_free+0x130/0x180 mm/kasan/common.c:449 slab_free_hook mm/slub.c:1423 [inline] slab_free_freelist_hook mm/slub.c:1470 [inline] slab_free mm/slub.c:3012 [inline] kfree+0xe4/0x2f0 mm/slub.c:3953 hiddev_connect.cold+0x45/0x5c drivers/hid/usbhid/hiddev.c:914 hid_connect+0x239/0xbb0 drivers/hid/hid-core.c:1882 hid_hw_start drivers/hid/hid-core.c:1981 [inline] hid_hw_start+0xa2/0x130 drivers/hid/hid-core.c:1972 appleir_probe+0x13e/0x1a0 drivers/hid/hid-appleir.c:308 hid_device_probe+0x2be/0x3f0 drivers/hid/hid-core.c:2209 really_probe+0x281/0x650 drivers/base/dd.c:548 driver_probe_device+0x101/0x1b0 drivers/base/dd.c:709 __device_attach_driver+0x1c2/0x220 drivers/base/dd.c:816 bus_for_each_drv+0x15c/0x1e0 drivers/base/bus.c:454 __device_attach+0x217/0x360 drivers/base/dd.c:882 bus_probe_device+0x1e4/0x290 drivers/base/bus.c:514 device_add+0xae6/0x16f0 drivers/base/core.c:2114 hid_add_device+0x33c/0x990 drivers/hid/hid-core.c:2365 usbhid_probe+0xa81/0xfa0 drivers/hid/usbhid/hid-core.c:1386 usb_probe_interface+0x305/0x7a0 drivers/usb/core/driver.c:361 really_probe+0x281/0x650 drivers/base/dd.c:548 driver_probe_device+0x101/0x1b0 drivers/base/dd.c:709 __device_attach_driver+0x1c2/0x220 drivers/base/dd.c:816 bus_for_each_drv+0x15c/0x1e0 drivers/base/bus.c:454 __device_attach+0x217/0x360 drivers/base/dd.c:882 bus_probe_device+0x1e4/0x290 drivers/base/bus.c:514 device_add+0xae6/0x16f0 drivers/base/core.c:2114 usb_set_configuration+0xdf6/0x1670 drivers/usb/core/message.c:2023 generic_probe+0x9d/0xd5 drivers/usb/core/generic.c:210 usb_probe_device+0x99/0x100 drivers/usb/core/driver.c:266 really_probe+0x281/0x650 drivers/base/dd.c:548 driver_probe_device+0x101/0x1b0 drivers/base/dd.c:709 __device_attach_driver+0x1c2/0x220 drivers/base/dd.c:816 bus_for_each_drv+0x15c/0x1e0 drivers/base/bus.c:454 __device_attach+0x217/0x360 drivers/base/dd.c:882 bus_probe_device+0x1e4/0x290 drivers/base/bus.c:514 device_add+0xae6/0x16f0 drivers/base/core.c:2114 usb_new_device.cold+0x6a4/0xe79 drivers/usb/core/hub.c:2536 hub_port_connect drivers/usb/core/hub.c:5098 [inline] hub_port_connect_change drivers/usb/core/hub.c:5213 [inline] port_event drivers/usb/core/hub.c:5359 [inline] hub_event+0x1b5c/0x3640 drivers/usb/core/hub.c:5441 process_one_work+0x92b/0x1530 kernel/workqueue.c:2269 worker_thread+0x96/0xe20 kernel/workqueue.c:2415 kthread+0x318/0x420 kernel/kthread.c:255 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352 The buggy address belongs to the object at ffff8881cf591900 which belongs to the cache kmalloc-512 of size 512 The buggy address is located 264 bytes inside of 512-byte region [ffff8881cf591900, ffff8881cf591b00) The buggy address belongs to the page: page:ffffea00073d6400 refcount:1 mapcount:0 mapping:ffff8881da002500 index:0x0 compound_mapcount: 0 flags: 0x200000000010200(slab|head) raw: 0200000000010200 0000000000000000 0000000100000001 ffff8881da002500 raw: 0000000000000000 00000000000c000c 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8881cf591900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8881cf591980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb > ffff8881cf591a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8881cf591a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8881cf591b00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ================================================================== In order to avoid opening a disconnected device, we need to check exist again after acquiring the existance lock, and bail out if necessary. Reported-by: syzbot Cc: Andrey Konovalov Signed-off-by: Hillf Danton Signed-off-by: Jiri Kosina --- drivers/hid/usbhid/hiddev.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index 55b72573066b..c07df8292380 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -284,6 +284,14 @@ static int hiddev_open(struct inode *inode, struct file *file) spin_unlock_irq(&list->hiddev->list_lock); mutex_lock(&hiddev->existancelock); + /* + * recheck exist with existance lock held to + * avoid opening a disconnected device + */ + if (!list->hiddev->exist) { + res = -ENODEV; + goto bail_unlock; + } if (!list->hiddev->open++) if (list->hiddev->exist) { struct hid_device *hid = hiddev->hid; From 6d4472d7bec39917b54e4e80245784ea5d60ce49 Mon Sep 17 00:00:00 2001 From: Hillf Danton Date: Tue, 6 Aug 2019 16:40:15 +0800 Subject: [PATCH 803/823] HID: hiddev: do cleanup in failure of opening a device Undo what we did for opening before releasing the memory slice. Reported-by: syzbot Cc: Andrey Konovalov Signed-off-by: Hillf Danton Signed-off-by: Jiri Kosina --- drivers/hid/usbhid/hiddev.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index c07df8292380..4e11cc6fc34b 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -308,6 +308,10 @@ bail_normal_power: hid_hw_power(hid, PM_HINT_NORMAL); bail_unlock: mutex_unlock(&hiddev->existancelock); + + spin_lock_irq(&list->hiddev->list_lock); + list_del(&list->node); + spin_unlock_irq(&list->hiddev->list_lock); bail: file->private_data = NULL; vfree(list); From e0f6974a54d3f7f1b5fdf5a593bd43ce9206ec04 Mon Sep 17 00:00:00 2001 From: Roderick Colenbrander Date: Fri, 2 Aug 2019 15:50:19 -0700 Subject: [PATCH 804/823] HID: sony: Fix race condition between rumble and device remove. Valve reported a kernel crash on Ubuntu 18.04 when disconnecting a DS4 gamepad while rumble is enabled. This issue is reproducible with a frequency of 1 in 3 times in the game Borderlands 2 when using an automatic weapon, which triggers many rumble operations. We found the issue to be a race condition between sony_remove and the final device destruction by the HID / input system. The problem was that sony_remove didn't clean some of its work_item state in "struct sony_sc". After sony_remove work, the corresponding evdev node was around for sufficient time for applications to still queue rumble work after "sony_remove". On pre-4.19 kernels the race condition caused a kernel crash due to a NULL-pointer dereference as "sc->output_report_dmabuf" got freed during sony_remove. On newer kernels this crash doesn't happen due the buffer now being allocated using devm_kzalloc. However we can still queue work, while the driver is an undefined state. This patch fixes the described problem, by guarding the work_item "state_worker" with an initialized variable, which we are setting back to 0 on cleanup. Signed-off-by: Roderick Colenbrander CC: stable@vger.kernel.org Signed-off-by: Jiri Kosina --- drivers/hid/hid-sony.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c index 93942063b51b..49dd2d905c7f 100644 --- a/drivers/hid/hid-sony.c +++ b/drivers/hid/hid-sony.c @@ -585,10 +585,14 @@ static void sony_set_leds(struct sony_sc *sc); static inline void sony_schedule_work(struct sony_sc *sc, enum sony_worker which) { + unsigned long flags; + switch (which) { case SONY_WORKER_STATE: - if (!sc->defer_initialization) + spin_lock_irqsave(&sc->lock, flags); + if (!sc->defer_initialization && sc->state_worker_initialized) schedule_work(&sc->state_worker); + spin_unlock_irqrestore(&sc->lock, flags); break; case SONY_WORKER_HOTPLUG: if (sc->hotplug_worker_initialized) @@ -2558,13 +2562,18 @@ static inline void sony_init_output_report(struct sony_sc *sc, static inline void sony_cancel_work_sync(struct sony_sc *sc) { + unsigned long flags; + if (sc->hotplug_worker_initialized) cancel_work_sync(&sc->hotplug_worker); - if (sc->state_worker_initialized) + if (sc->state_worker_initialized) { + spin_lock_irqsave(&sc->lock, flags); + sc->state_worker_initialized = 0; + spin_unlock_irqrestore(&sc->lock, flags); cancel_work_sync(&sc->state_worker); + } } - static int sony_input_configured(struct hid_device *hdev, struct hid_input *hidinput) { From 5c4e2e1af345426f63410a50e2a678673574aa02 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Tue, 6 Aug 2019 15:35:39 +0800 Subject: [PATCH 805/823] net: ethernet: sun4i-emac: Support phy-handle property for finding PHYs The sun4i-emac uses the "phy" property to find the PHY it's supposed to use. This property was deprecated in favor of "phy-handle" in commit 8c5b09447625 ("dt-bindings: net: sun4i-emac: Convert the binding to a schemas"). Add support for this new property name, and fall back to the old one in case the device tree hasn't been updated. Signed-off-by: Chen-Yu Tsai Signed-off-by: David S. Miller --- drivers/net/ethernet/allwinner/sun4i-emac.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index 3434730a7699..0537df06a9b5 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -860,7 +860,9 @@ static int emac_probe(struct platform_device *pdev) goto out_clk_disable_unprepare; } - db->phy_node = of_parse_phandle(np, "phy", 0); + db->phy_node = of_parse_phandle(np, "phy-handle", 0); + if (!db->phy_node) + db->phy_node = of_parse_phandle(np, "phy", 0); if (!db->phy_node) { dev_err(&pdev->dev, "no associated PHY\n"); ret = -ENODEV; From debea2cd3193ac868289e8893c3a719c265b0612 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 6 Aug 2019 10:55:12 +0200 Subject: [PATCH 806/823] net: cxgb3_main: Fix a resource leak in a error path in 'init_one()' A call to 'kfree_skb()' is missing in the error handling path of 'init_one()'. This is already present in 'remove_one()' but is missing here. Signed-off-by: Christophe JAILLET Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 1e82b9efe447..58f89f6a040f 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -3269,7 +3269,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (!adapter->regs) { dev_err(&pdev->dev, "cannot map device registers\n"); err = -ENOMEM; - goto out_free_adapter; + goto out_free_adapter_nofail; } adapter->pdev = pdev; @@ -3397,6 +3397,9 @@ out_free_dev: if (adapter->port[i]) free_netdev(adapter->port[i]); +out_free_adapter_nofail: + kfree_skb(adapter->nofail_skb); + out_free_adapter: kfree(adapter); From d0d006a43e9a7a796f6f178839c92fcc222c564d Mon Sep 17 00:00:00 2001 From: Denis Kirjanov Date: Tue, 6 Aug 2019 12:51:11 +0200 Subject: [PATCH 807/823] be2net: disable bh with spin_lock in be_process_mcc be_process_mcc() is invoked in 3 different places and always with BHs disabled except the be_poll function but since it's invoked from softirq with BHs disabled it won't hurt. v1->v2: added explanation to the patch v2->v3: add a missing call from be_cmds.c Signed-off-by: Denis Kirjanov Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_cmds.c | 6 ++---- drivers/net/ethernet/emulex/benet/be_main.c | 2 -- 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index ef5d61d57597..323976c811e9 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -550,7 +550,7 @@ int be_process_mcc(struct be_adapter *adapter) int num = 0, status = 0; struct be_mcc_obj *mcc_obj = &adapter->mcc_obj; - spin_lock(&adapter->mcc_cq_lock); + spin_lock_bh(&adapter->mcc_cq_lock); while ((compl = be_mcc_compl_get(adapter))) { if (compl->flags & CQE_FLAGS_ASYNC_MASK) { @@ -566,7 +566,7 @@ int be_process_mcc(struct be_adapter *adapter) if (num) be_cq_notify(adapter, mcc_obj->cq.id, mcc_obj->rearm_cq, num); - spin_unlock(&adapter->mcc_cq_lock); + spin_unlock_bh(&adapter->mcc_cq_lock); return status; } @@ -581,9 +581,7 @@ static int be_mcc_wait_compl(struct be_adapter *adapter) if (be_check_error(adapter, BE_ERROR_ANY)) return -EIO; - local_bh_disable(); status = be_process_mcc(adapter); - local_bh_enable(); if (atomic_read(&mcc_obj->q.used) == 0) break; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 2edb86ec9fe9..4d8e40ac66d2 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -5630,9 +5630,7 @@ static void be_worker(struct work_struct *work) * mcc completions */ if (!netif_running(adapter->netdev)) { - local_bh_disable(); be_process_mcc(adapter); - local_bh_enable(); goto reschedule; } From 0efedbf11f07adee555e0c4ba9c6eb58760aa94f Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Tue, 6 Aug 2019 15:16:16 +0200 Subject: [PATCH 808/823] net: stmmac: xgmac: Fix XGMAC selftests Fixup the XGMAC selftests by correctly finishing the implementation of set_filter callback. Result: $ ethtool -t enp4s0 The test result is PASS The test extra info: 1. MAC Loopback 0 2. PHY Loopback -95 3. MMC Counters -95 4. EEE -95 5. Hash Filter MC 0 6. Perfect Filter UC 0 7. MC Filter 0 8. UC Filter 0 9. Flow Control 0 Signed-off-by: Jose Abreu Signed-off-by: David S. Miller --- .../net/ethernet/stmicro/stmmac/dwxgmac2.h | 7 +- .../ethernet/stmicro/stmmac/dwxgmac2_core.c | 83 +++++++++++++++++-- 2 files changed, 79 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index 7f86dffb264d..3174b701aa90 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -44,11 +44,13 @@ #define XGMAC_CORE_INIT_RX 0 #define XGMAC_PACKET_FILTER 0x00000008 #define XGMAC_FILTER_RA BIT(31) +#define XGMAC_FILTER_HPF BIT(10) #define XGMAC_FILTER_PCF BIT(7) #define XGMAC_FILTER_PM BIT(4) #define XGMAC_FILTER_HMC BIT(2) #define XGMAC_FILTER_PR BIT(0) #define XGMAC_HASH_TABLE(x) (0x00000010 + (x) * 4) +#define XGMAC_MAX_HASH_TABLE 8 #define XGMAC_RXQ_CTRL0 0x000000a0 #define XGMAC_RXQEN(x) GENMASK((x) * 2 + 1, (x) * 2) #define XGMAC_RXQEN_SHIFT(x) ((x) * 2) @@ -99,11 +101,12 @@ #define XGMAC_MDIO_ADDR 0x00000200 #define XGMAC_MDIO_DATA 0x00000204 #define XGMAC_MDIO_C22P 0x00000220 -#define XGMAC_ADDR0_HIGH 0x00000300 +#define XGMAC_ADDRx_HIGH(x) (0x00000300 + (x) * 0x8) +#define XGMAC_ADDR_MAX 32 #define XGMAC_AE BIT(31) #define XGMAC_DCS GENMASK(19, 16) #define XGMAC_DCS_SHIFT 16 -#define XGMAC_ADDR0_LOW 0x00000304 +#define XGMAC_ADDRx_LOW(x) (0x00000304 + (x) * 0x8) #define XGMAC_ARP_ADDR 0x00000c10 #define XGMAC_TIMESTAMP_STATUS 0x00000d20 #define XGMAC_TXTSC BIT(15) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 0a32c96a7854..03a6a59650ca 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -4,6 +4,8 @@ * stmmac XGMAC support. */ +#include +#include #include "stmmac.h" #include "dwxgmac2.h" @@ -278,10 +280,10 @@ static void dwxgmac2_set_umac_addr(struct mac_device_info *hw, u32 value; value = (addr[5] << 8) | addr[4]; - writel(value | XGMAC_AE, ioaddr + XGMAC_ADDR0_HIGH); + writel(value | XGMAC_AE, ioaddr + XGMAC_ADDRx_HIGH(reg_n)); value = (addr[3] << 24) | (addr[2] << 16) | (addr[1] << 8) | addr[0]; - writel(value, ioaddr + XGMAC_ADDR0_LOW); + writel(value, ioaddr + XGMAC_ADDRx_LOW(reg_n)); } static void dwxgmac2_get_umac_addr(struct mac_device_info *hw, @@ -291,8 +293,8 @@ static void dwxgmac2_get_umac_addr(struct mac_device_info *hw, u32 hi_addr, lo_addr; /* Read the MAC address from the hardware */ - hi_addr = readl(ioaddr + XGMAC_ADDR0_HIGH); - lo_addr = readl(ioaddr + XGMAC_ADDR0_LOW); + hi_addr = readl(ioaddr + XGMAC_ADDRx_HIGH(reg_n)); + lo_addr = readl(ioaddr + XGMAC_ADDRx_LOW(reg_n)); /* Extract the MAC address from the high and low words */ addr[0] = lo_addr & 0xff; @@ -303,19 +305,82 @@ static void dwxgmac2_get_umac_addr(struct mac_device_info *hw, addr[5] = (hi_addr >> 8) & 0xff; } +static void dwxgmac2_set_mchash(void __iomem *ioaddr, u32 *mcfilterbits, + int mcbitslog2) +{ + int numhashregs, regs; + + switch (mcbitslog2) { + case 6: + numhashregs = 2; + break; + case 7: + numhashregs = 4; + break; + case 8: + numhashregs = 8; + break; + default: + return; + } + + for (regs = 0; regs < numhashregs; regs++) + writel(mcfilterbits[regs], ioaddr + XGMAC_HASH_TABLE(regs)); +} + static void dwxgmac2_set_filter(struct mac_device_info *hw, struct net_device *dev) { void __iomem *ioaddr = (void __iomem *)dev->base_addr; - u32 value = XGMAC_FILTER_RA; + u32 value = readl(ioaddr + XGMAC_PACKET_FILTER); + int mcbitslog2 = hw->mcast_bits_log2; + u32 mc_filter[8]; + int i; + + value &= ~(XGMAC_FILTER_PR | XGMAC_FILTER_HMC | XGMAC_FILTER_PM); + value |= XGMAC_FILTER_HPF; + + memset(mc_filter, 0, sizeof(mc_filter)); if (dev->flags & IFF_PROMISC) { - value |= XGMAC_FILTER_PR | XGMAC_FILTER_PCF; + value |= XGMAC_FILTER_PR; + value |= XGMAC_FILTER_PCF; } else if ((dev->flags & IFF_ALLMULTI) || - (netdev_mc_count(dev) > HASH_TABLE_SIZE)) { + (netdev_mc_count(dev) > hw->multicast_filter_bins)) { value |= XGMAC_FILTER_PM; - writel(~0x0, ioaddr + XGMAC_HASH_TABLE(0)); - writel(~0x0, ioaddr + XGMAC_HASH_TABLE(1)); + + for (i = 0; i < XGMAC_MAX_HASH_TABLE; i++) + writel(~0x0, ioaddr + XGMAC_HASH_TABLE(i)); + } else if (!netdev_mc_empty(dev)) { + struct netdev_hw_addr *ha; + + value |= XGMAC_FILTER_HMC; + + netdev_for_each_mc_addr(ha, dev) { + int nr = (bitrev32(~crc32_le(~0, ha->addr, 6)) >> + (32 - mcbitslog2)); + mc_filter[nr >> 5] |= (1 << (nr & 0x1F)); + } + } + + dwxgmac2_set_mchash(ioaddr, mc_filter, mcbitslog2); + + /* Handle multiple unicast addresses */ + if (netdev_uc_count(dev) > XGMAC_ADDR_MAX) { + value |= XGMAC_FILTER_PR; + } else { + struct netdev_hw_addr *ha; + int reg = 1; + + netdev_for_each_uc_addr(ha, dev) { + dwxgmac2_set_umac_addr(hw, ha->addr, reg); + reg++; + } + + for ( ; reg < XGMAC_ADDR_MAX; reg++) { + writel(0, ioaddr + XGMAC_ADDRx_HIGH(reg)); + writel(0, ioaddr + XGMAC_ADDRx_LOW(reg)); + } } writel(value, ioaddr + XGMAC_PACKET_FILTER); From e8df7e8c233a18d2704e37ecff47583b494789d3 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Tue, 6 Aug 2019 15:16:17 +0200 Subject: [PATCH 809/823] net: stmmac: Fix issues when number of Queues >= 4 When queues >= 4 we use different registers but we were not subtracting the offset of 4. Fix this. Found out by Coverity. Signed-off-by: Jose Abreu Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 4 ++++ drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 01c2e2d83e76..fc9954e4a772 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -85,6 +85,8 @@ static void dwmac4_rx_queue_priority(struct mac_device_info *hw, u32 value; base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3; + if (queue >= 4) + queue -= 4; value = readl(ioaddr + base_register); @@ -102,6 +104,8 @@ static void dwmac4_tx_queue_priority(struct mac_device_info *hw, u32 value; base_register = (queue < 4) ? GMAC_TXQ_PRTY_MAP0 : GMAC_TXQ_PRTY_MAP1; + if (queue >= 4) + queue -= 4; value = readl(ioaddr + base_register); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 03a6a59650ca..85c68b7ee8c6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -108,6 +108,8 @@ static void dwxgmac2_rx_queue_prio(struct mac_device_info *hw, u32 prio, u32 value, reg; reg = (queue < 4) ? XGMAC_RXQ_CTRL2 : XGMAC_RXQ_CTRL3; + if (queue >= 4) + queue -= 4; value = readl(ioaddr + reg); value &= ~XGMAC_PSRQ(queue); @@ -171,6 +173,8 @@ static void dwxgmac2_map_mtl_to_dma(struct mac_device_info *hw, u32 queue, u32 value, reg; reg = (queue < 4) ? XGMAC_MTL_RXQ_DMA_MAP0 : XGMAC_MTL_RXQ_DMA_MAP1; + if (queue >= 4) + queue -= 4; value = readl(ioaddr + reg); value &= ~XGMAC_QxMDMACH(queue); From 4a6a1385a4db5f42258a40fcd497cbfd22075968 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Tue, 6 Aug 2019 15:16:18 +0200 Subject: [PATCH 810/823] net: stmmac: tc: Do not return a fragment entry Do not try to return a fragment entry from TC list. Otherwise we may not clean properly allocated entries. Signed-off-by: Jose Abreu Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 58ea18af9813..37c0bc699cd9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -37,7 +37,7 @@ static struct stmmac_tc_entry *tc_find_entry(struct stmmac_priv *priv, entry = &priv->tc_entries[i]; if (!entry->in_use && !first && free) first = entry; - if (entry->handle == loc && !free) + if ((entry->handle == loc) && !free && !entry->is_frag) dup = entry; } From b35475c5491a14c8ce7a5046ef7bcda8a860581a Mon Sep 17 00:00:00 2001 From: Roman Mashak Date: Fri, 2 Aug 2019 15:16:46 -0400 Subject: [PATCH 811/823] net sched: update vlan action for batched events operations Add get_fill_size() routine used to calculate the action size when building a batch of events. Fixes: c7e2b9689 ("sched: introduce vlan action") Signed-off-by: Roman Mashak Signed-off-by: David S. Miller --- net/sched/act_vlan.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 984b05ab0c87..a3c9eea1ee8a 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -308,6 +308,14 @@ static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index) return tcf_idr_search(tn, a, index); } +static size_t tcf_vlan_get_fill_size(const struct tc_action *act) +{ + return nla_total_size(sizeof(struct tc_vlan)) + + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_ID */ + + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_PROTOCOL */ + + nla_total_size(sizeof(u8)); /* TCA_VLAN_PUSH_VLAN_PRIORITY */ +} + static struct tc_action_ops act_vlan_ops = { .kind = "vlan", .id = TCA_ID_VLAN, @@ -317,6 +325,7 @@ static struct tc_action_ops act_vlan_ops = { .init = tcf_vlan_init, .cleanup = tcf_vlan_cleanup, .walk = tcf_vlan_walker, + .get_fill_size = tcf_vlan_get_fill_size, .lookup = tcf_vlan_search, .size = sizeof(struct tcf_vlan), }; From 8571deb013812f35260b2b7152a522eacfa9ccf9 Mon Sep 17 00:00:00 2001 From: Roman Mashak Date: Fri, 2 Aug 2019 15:16:47 -0400 Subject: [PATCH 812/823] tc-testing: updated vlan action tests with batch create/delete Update TDC tests with cases varifying ability of TC to install or delete batches of vlan actions. Signed-off-by: Roman Mashak Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/vlan.json | 94 +++++++++++++++++++ 1 file changed, 94 insertions(+) diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json index cc7c7d758008..6503b1ce091f 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json @@ -713,5 +713,99 @@ "teardown": [ "$TC actions flush action vlan" ] + }, + { + "id": "294e", + "name": "Add batch of 32 vlan push actions with cookie", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan push protocol 802.1q id 4094 priority 7 pipe index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "32", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "56f7", + "name": "Delete batch of 32 vlan push actions", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan push protocol 802.1q id 4094 priority 7 pipe index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\"" + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "759f", + "name": "Add batch of 32 vlan pop actions with cookie", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan pop continue index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "32", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "c84a", + "name": "Delete batch of 32 vlan pop actions", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan pop index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\"" + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "0", + "teardown": [] } ] From 1a2c070ae805910a853b4a14818481ed2e17c727 Mon Sep 17 00:00:00 2001 From: Jiangfeng Xiao Date: Sat, 3 Aug 2019 20:31:39 +0800 Subject: [PATCH 813/823] net: hisilicon: make hip04_tx_reclaim non-reentrant If hip04_tx_reclaim is interrupted while it is running and then __napi_schedule continues to execute hip04_rx_poll->hip04_tx_reclaim, reentrancy occurs and oops is generated. So you need to mask the interrupt during the hip04_tx_reclaim run. The kernel oops exception stack is as follows: Unable to handle kernel NULL pointer dereference at virtual address 00000050 pgd = c0003000 [00000050] *pgd=80000000a04003, *pmd=00000000 Internal error: Oops: 206 [#1] SMP ARM Modules linked in: hip04_eth mtdblock mtd_blkdevs mtd ohci_platform ehci_platform ohci_hcd ehci_hcd vfat fat sd_mod usb_storage scsi_mod usbcore usb_common CPU: 0 PID: 0 Comm: swapper/0 Tainted: G O 4.4.185 #1 Hardware name: Hisilicon A15 task: c0a250e0 task.stack: c0a00000 PC is at hip04_tx_reclaim+0xe0/0x17c [hip04_eth] LR is at hip04_tx_reclaim+0x30/0x17c [hip04_eth] pc : [] lr : [] psr: 600e0313 sp : c0a01d88 ip : 00000000 fp : c0601f9c r10: 00000000 r9 : c3482380 r8 : 00000001 r7 : 00000000 r6 : 000000e1 r5 : c3482000 r4 : 0000000c r3 : f2209800 r2 : 00000000 r1 : 00000000 r0 : 00000000 Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment kernel Control: 32c5387d Table: 03d28c80 DAC: 55555555 Process swapper/0 (pid: 0, stack limit = 0xc0a00190) Stack: (0xc0a01d88 to 0xc0a02000) [] (hip04_tx_reclaim [hip04_eth]) from [] (hip04_rx_poll+0x88/0x368 [hip04_eth]) [] (hip04_rx_poll [hip04_eth]) from [] (net_rx_action+0x114/0x34c) [] (net_rx_action) from [] (__do_softirq+0x218/0x318) [] (__do_softirq) from [] (irq_exit+0x88/0xac) [] (irq_exit) from [] (msa_irq_exit+0x11c/0x1d4) [] (msa_irq_exit) from [] (__handle_domain_irq+0x110/0x148) [] (__handle_domain_irq) from [] (gic_handle_irq+0xd4/0x118) [] (gic_handle_irq) from [] (__irq_svc+0x40/0x58) Exception stack(0xc0a01f30 to 0xc0a01f78) 1f20: c0ae8b40 00000000 00000000 00000000 1f40: 00000002 ffffe000 c0601f9c 00000000 ffffffff c0a2257c c0a22440 c0831a38 1f60: c0a01ec4 c0a01f80 c0203714 c0203718 600e0213 ffffffff [] (__irq_svc) from [] (arch_cpu_idle+0x20/0x3c) [] (arch_cpu_idle) from [] (cpu_startup_entry+0x244/0x29c) [] (cpu_startup_entry) from [] (rest_init+0xc8/0x10c) [] (rest_init) from [] (start_kernel+0x468/0x514) Code: a40599e5 016086e2 018088e2 7660efe6 (503090e5) ---[ end trace 1db21d6d09c49d74 ]--- Kernel panic - not syncing: Fatal exception in interrupt CPU3: stopping CPU: 3 PID: 0 Comm: swapper/3 Tainted: G D O 4.4.185 #1 Signed-off-by: Jiangfeng Xiao Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hip04_eth.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index d60452845539..1e1b154ed2ec 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -585,6 +585,9 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget) u16 len; u32 err; + /* clean up tx descriptors */ + tx_remaining = hip04_tx_reclaim(ndev, false); + while (cnt && !last) { buf = priv->rx_buf[priv->rx_head]; skb = build_skb(buf, priv->rx_buf_size); @@ -645,8 +648,7 @@ refill: } napi_complete_done(napi, rx); done: - /* clean up tx descriptors and start a new timer if necessary */ - tx_remaining = hip04_tx_reclaim(ndev, false); + /* start a new timer if necessary */ if (rx < budget && tx_remaining) hip04_start_tx_timer(priv); From f2243b82785942be519016067ee6c55a063bbfe2 Mon Sep 17 00:00:00 2001 From: Jiangfeng Xiao Date: Sat, 3 Aug 2019 20:31:40 +0800 Subject: [PATCH 814/823] net: hisilicon: fix hip04-xmit never return TX_BUSY TX_DESC_NUM is 256, in tx_count, the maximum value of mod(TX_DESC_NUM - 1) is 254, the variable "count" in the hip04_mac_start_xmit function is never equal to (TX_DESC_NUM - 1), so hip04_mac_start_xmit never return NETDEV_TX_BUSY. tx_count is modified to mod(TX_DESC_NUM) so that the maximum value of tx_count can reach (TX_DESC_NUM - 1), then hip04_mac_start_xmit can reurn NETDEV_TX_BUSY. Signed-off-by: Jiangfeng Xiao Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hip04_eth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 1e1b154ed2ec..d775b980f1bb 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -248,7 +248,7 @@ struct hip04_priv { static inline unsigned int tx_count(unsigned int head, unsigned int tail) { - return (head - tail) % (TX_DESC_NUM - 1); + return (head - tail) % TX_DESC_NUM; } static void hip04_config_port(struct net_device *ndev, u32 speed, u32 duplex) From 96a50c0d907ac8f5c3d6b051031a19eb8a2b53e3 Mon Sep 17 00:00:00 2001 From: Jiangfeng Xiao Date: Sat, 3 Aug 2019 20:31:41 +0800 Subject: [PATCH 815/823] net: hisilicon: Fix dma_map_single failed on arm64 On the arm64 platform, executing "ifconfig eth0 up" will fail, returning "ifconfig: SIOCSIFFLAGS: Input/output error." ndev->dev is not initialized, dma_map_single->get_dma_ops-> dummy_dma_ops->__dummy_map_page will return DMA_ERROR_CODE directly, so when we use dma_map_single, the first parameter is to use the device of platform_device. Signed-off-by: Jiangfeng Xiao Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hip04_eth.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index d775b980f1bb..c84167447abe 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -220,6 +220,7 @@ struct hip04_priv { unsigned int reg_inten; struct napi_struct napi; + struct device *dev; struct net_device *ndev; struct tx_desc *tx_desc; @@ -465,7 +466,7 @@ static int hip04_tx_reclaim(struct net_device *ndev, bool force) } if (priv->tx_phys[tx_tail]) { - dma_unmap_single(&ndev->dev, priv->tx_phys[tx_tail], + dma_unmap_single(priv->dev, priv->tx_phys[tx_tail], priv->tx_skb[tx_tail]->len, DMA_TO_DEVICE); priv->tx_phys[tx_tail] = 0; @@ -516,8 +517,8 @@ hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_BUSY; } - phys = dma_map_single(&ndev->dev, skb->data, skb->len, DMA_TO_DEVICE); - if (dma_mapping_error(&ndev->dev, phys)) { + phys = dma_map_single(priv->dev, skb->data, skb->len, DMA_TO_DEVICE); + if (dma_mapping_error(priv->dev, phys)) { dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -596,7 +597,7 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget) goto refill; } - dma_unmap_single(&ndev->dev, priv->rx_phys[priv->rx_head], + dma_unmap_single(priv->dev, priv->rx_phys[priv->rx_head], RX_BUF_SIZE, DMA_FROM_DEVICE); priv->rx_phys[priv->rx_head] = 0; @@ -625,9 +626,9 @@ refill: buf = netdev_alloc_frag(priv->rx_buf_size); if (!buf) goto done; - phys = dma_map_single(&ndev->dev, buf, + phys = dma_map_single(priv->dev, buf, RX_BUF_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(&ndev->dev, phys)) + if (dma_mapping_error(priv->dev, phys)) goto done; priv->rx_buf[priv->rx_head] = buf; priv->rx_phys[priv->rx_head] = phys; @@ -730,9 +731,9 @@ static int hip04_mac_open(struct net_device *ndev) for (i = 0; i < RX_DESC_NUM; i++) { dma_addr_t phys; - phys = dma_map_single(&ndev->dev, priv->rx_buf[i], + phys = dma_map_single(priv->dev, priv->rx_buf[i], RX_BUF_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(&ndev->dev, phys)) + if (dma_mapping_error(priv->dev, phys)) return -EIO; priv->rx_phys[i] = phys; @@ -766,7 +767,7 @@ static int hip04_mac_stop(struct net_device *ndev) for (i = 0; i < RX_DESC_NUM; i++) { if (priv->rx_phys[i]) { - dma_unmap_single(&ndev->dev, priv->rx_phys[i], + dma_unmap_single(priv->dev, priv->rx_phys[i], RX_BUF_SIZE, DMA_FROM_DEVICE); priv->rx_phys[i] = 0; } @@ -909,6 +910,7 @@ static int hip04_mac_probe(struct platform_device *pdev) return -ENOMEM; priv = netdev_priv(ndev); + priv->dev = d; priv->ndev = ndev; platform_set_drvdata(pdev, ndev); SET_NETDEV_DEV(ndev, &pdev->dev); From c4bd48699beb92d6bb99d6139d1e9737cca73480 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Sat, 3 Aug 2019 16:36:18 +0300 Subject: [PATCH 816/823] net: sched: police: allow accessing police->params with rtnl Recently implemented support for police action in flow_offload infra leads to following rcu usage warning: [ 1925.881092] ============================= [ 1925.881094] WARNING: suspicious RCU usage [ 1925.881098] 5.3.0-rc1+ #574 Not tainted [ 1925.881100] ----------------------------- [ 1925.881104] include/net/tc_act/tc_police.h:57 suspicious rcu_dereference_check() usage! [ 1925.881106] other info that might help us debug this: [ 1925.881109] rcu_scheduler_active = 2, debug_locks = 1 [ 1925.881112] 1 lock held by tc/18591: [ 1925.881115] #0: 00000000b03cb918 (rtnl_mutex){+.+.}, at: tc_new_tfilter+0x47c/0x970 [ 1925.881124] stack backtrace: [ 1925.881127] CPU: 2 PID: 18591 Comm: tc Not tainted 5.3.0-rc1+ #574 [ 1925.881130] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 1925.881132] Call Trace: [ 1925.881138] dump_stack+0x85/0xc0 [ 1925.881145] tc_setup_flow_action+0x1771/0x2040 [ 1925.881155] fl_hw_replace_filter+0x11f/0x2e0 [cls_flower] [ 1925.881175] fl_change+0xd24/0x1b30 [cls_flower] [ 1925.881200] tc_new_tfilter+0x3e0/0x970 [ 1925.881231] ? tc_del_tfilter+0x720/0x720 [ 1925.881243] rtnetlink_rcv_msg+0x389/0x4b0 [ 1925.881250] ? netlink_deliver_tap+0x95/0x400 [ 1925.881257] ? rtnl_dellink+0x2d0/0x2d0 [ 1925.881264] netlink_rcv_skb+0x49/0x110 [ 1925.881275] netlink_unicast+0x171/0x200 [ 1925.881284] netlink_sendmsg+0x224/0x3f0 [ 1925.881299] sock_sendmsg+0x5e/0x60 [ 1925.881305] ___sys_sendmsg+0x2ae/0x330 [ 1925.881309] ? task_work_add+0x43/0x50 [ 1925.881314] ? fput_many+0x45/0x80 [ 1925.881329] ? __lock_acquire+0x248/0x1930 [ 1925.881342] ? find_held_lock+0x2b/0x80 [ 1925.881347] ? task_work_run+0x7b/0xd0 [ 1925.881359] __sys_sendmsg+0x59/0xa0 [ 1925.881375] do_syscall_64+0x5c/0xb0 [ 1925.881381] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 1925.881384] RIP: 0033:0x7feb245047b8 [ 1925.881388] Code: 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 65 8f 0c 00 8b 00 85 c0 75 17 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 48 83 ec 28 89 54 [ 1925.881391] RSP: 002b:00007ffc2d2a5788 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 1925.881395] RAX: ffffffffffffffda RBX: 000000005d4497ed RCX: 00007feb245047b8 [ 1925.881398] RDX: 0000000000000000 RSI: 00007ffc2d2a57f0 RDI: 0000000000000003 [ 1925.881400] RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000006 [ 1925.881403] R10: 0000000000404ec2 R11: 0000000000000246 R12: 0000000000000001 [ 1925.881406] R13: 0000000000480640 R14: 0000000000000012 R15: 0000000000000001 Change tcf_police_rate_bytes_ps() and tcf_police_tcfp_burst() helpers to allow using them from both rtnl and rcu protected contexts. Fixes: 8c8cfc6ed274 ("net/sched: add police action to the hardware intermediate representation") Signed-off-by: Vlad Buslov Reviewed-by: Pieter Jansen van Vuuren Signed-off-by: David S. Miller --- include/net/tc_act/tc_police.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/net/tc_act/tc_police.h b/include/net/tc_act/tc_police.h index 8b9ef3664262..cfdc7cb82cad 100644 --- a/include/net/tc_act/tc_police.h +++ b/include/net/tc_act/tc_police.h @@ -54,7 +54,7 @@ static inline u64 tcf_police_rate_bytes_ps(const struct tc_action *act) struct tcf_police *police = to_police(act); struct tcf_police_params *params; - params = rcu_dereference_bh(police->params); + params = rcu_dereference_bh_rtnl(police->params); return params->rate.rate_bytes_ps; } @@ -63,7 +63,7 @@ static inline s64 tcf_police_tcfp_burst(const struct tc_action *act) struct tcf_police *police = to_police(act); struct tcf_police_params *params; - params = rcu_dereference_bh(police->params); + params = rcu_dereference_bh_rtnl(police->params); return params->tcfp_burst; } From 67cbf7dedd03a63ca2fbd9df2049eabba7a37edf Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Sat, 3 Aug 2019 16:36:19 +0300 Subject: [PATCH 817/823] net: sched: sample: allow accessing psample_group with rtnl Recently implemented support for sample action in flow_offload infra leads to following rcu usage warning: [ 1938.234856] ============================= [ 1938.234858] WARNING: suspicious RCU usage [ 1938.234863] 5.3.0-rc1+ #574 Not tainted [ 1938.234866] ----------------------------- [ 1938.234869] include/net/tc_act/tc_sample.h:47 suspicious rcu_dereference_check() usage! [ 1938.234872] other info that might help us debug this: [ 1938.234875] rcu_scheduler_active = 2, debug_locks = 1 [ 1938.234879] 1 lock held by tc/19540: [ 1938.234881] #0: 00000000b03cb918 (rtnl_mutex){+.+.}, at: tc_new_tfilter+0x47c/0x970 [ 1938.234900] stack backtrace: [ 1938.234905] CPU: 2 PID: 19540 Comm: tc Not tainted 5.3.0-rc1+ #574 [ 1938.234908] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 1938.234911] Call Trace: [ 1938.234922] dump_stack+0x85/0xc0 [ 1938.234930] tc_setup_flow_action+0xed5/0x2040 [ 1938.234944] fl_hw_replace_filter+0x11f/0x2e0 [cls_flower] [ 1938.234965] fl_change+0xd24/0x1b30 [cls_flower] [ 1938.234990] tc_new_tfilter+0x3e0/0x970 [ 1938.235021] ? tc_del_tfilter+0x720/0x720 [ 1938.235028] rtnetlink_rcv_msg+0x389/0x4b0 [ 1938.235038] ? netlink_deliver_tap+0x95/0x400 [ 1938.235044] ? rtnl_dellink+0x2d0/0x2d0 [ 1938.235053] netlink_rcv_skb+0x49/0x110 [ 1938.235063] netlink_unicast+0x171/0x200 [ 1938.235073] netlink_sendmsg+0x224/0x3f0 [ 1938.235091] sock_sendmsg+0x5e/0x60 [ 1938.235097] ___sys_sendmsg+0x2ae/0x330 [ 1938.235111] ? __handle_mm_fault+0x12cd/0x19e0 [ 1938.235125] ? __handle_mm_fault+0x12cd/0x19e0 [ 1938.235138] ? find_held_lock+0x2b/0x80 [ 1938.235147] ? do_user_addr_fault+0x22d/0x490 [ 1938.235160] __sys_sendmsg+0x59/0xa0 [ 1938.235178] do_syscall_64+0x5c/0xb0 [ 1938.235187] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 1938.235192] RIP: 0033:0x7ff9a4d597b8 [ 1938.235197] Code: 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 65 8f 0c 00 8b 00 85 c0 75 17 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 48 83 ec 28 89 54 [ 1938.235200] RSP: 002b:00007ffcfe381c48 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 1938.235205] RAX: ffffffffffffffda RBX: 000000005d4497f9 RCX: 00007ff9a4d597b8 [ 1938.235208] RDX: 0000000000000000 RSI: 00007ffcfe381cb0 RDI: 0000000000000003 [ 1938.235211] RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000006 [ 1938.235214] R10: 0000000000404ec2 R11: 0000000000000246 R12: 0000000000000001 [ 1938.235217] R13: 0000000000480640 R14: 0000000000000012 R15: 0000000000000001 Change tcf_sample_psample_group() helper to allow using it from both rtnl and rcu protected contexts. Fixes: a7a7be6087b0 ("net/sched: add sample action to the hardware intermediate representation") Signed-off-by: Vlad Buslov Reviewed-by: Pieter Jansen van Vuuren Signed-off-by: David S. Miller --- include/net/tc_act/tc_sample.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/tc_act/tc_sample.h b/include/net/tc_act/tc_sample.h index 0a559d4b6f0f..b4fce0fae645 100644 --- a/include/net/tc_act/tc_sample.h +++ b/include/net/tc_act/tc_sample.h @@ -44,7 +44,7 @@ static inline int tcf_sample_trunc_size(const struct tc_action *a) static inline struct psample_group * tcf_sample_psample_group(const struct tc_action *a) { - return rcu_dereference(to_sample(a)->psample_group); + return rcu_dereference_rtnl(to_sample(a)->psample_group); } #endif /* __NET_TC_SAMPLE_H */ From f26e0cca14c9494c863d8fa6825b10bd12dc9eaa Mon Sep 17 00:00:00 2001 From: Nishka Dasgupta Date: Sun, 4 Aug 2019 21:00:18 +0530 Subject: [PATCH 818/823] net: dsa: qca8k: Add of_node_put() in qca8k_setup_mdio_bus() Each iteration of for_each_available_child_of_node() puts the previous node, but in the case of a return from the middle of the loop, there is no put, thus causing a memory leak. Hence add an of_node_put() before the return. Additionally, the local variable ports in the function qca8k_setup_mdio_bus() takes the return value of of_get_child_by_name(), which gets a node but does not put it. If the function returns without putting ports, it may cause a memory leak. Hence put ports before the mid-loop return statement, and also outside the loop after its last usage in this function. Issues found with Coccinelle. Signed-off-by: Nishka Dasgupta Signed-off-by: David S. Miller --- drivers/net/dsa/qca8k.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index e429e92dedf4..16f15c93a102 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -583,8 +583,11 @@ qca8k_setup_mdio_bus(struct qca8k_priv *priv) for_each_available_child_of_node(ports, port) { err = of_property_read_u32(port, "reg", ®); - if (err) + if (err) { + of_node_put(port); + of_node_put(ports); return err; + } if (!dsa_is_user_port(priv->ds, reg)) continue; @@ -595,6 +598,7 @@ qca8k_setup_mdio_bus(struct qca8k_priv *priv) internal_mdio_mask |= BIT(reg); } + of_node_put(ports); if (!external_mdio_mask && !internal_mdio_mask) { dev_err(priv->dev, "no PHYs are defined.\n"); return -EINVAL; From 6d7c7d948a2e9f87b4e7726dee94c59300e1786b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 5 Aug 2019 01:38:44 +0300 Subject: [PATCH 819/823] net: dsa: sja1105: Fix broken learning with vlan_filtering disabled When put under a bridge with vlan_filtering 0, the SJA1105 ports will flood all traffic as if learning was broken. This is because learning interferes with the rx_vid's configured by dsa_8021q as unique pvid's. So learning technically still *does* work, it's just that the learnt entries never get matched due to their unique VLAN ID. The setting that saves the day is Shared VLAN Learning, which on this switch family works exactly as desired: VLAN tagging still works (untagged traffic gets the correct pvid) and FDB entries are still populated with the correct contents including VID. Also, a frame cannot violate the forwarding domain restrictions enforced by its classified VLAN. It is just that the VID is ignored when looking up the FDB for taking a forwarding decision (selecting the egress port). This patch activates SVL, and the result is that frames with a learnt DMAC are no longer flooded in the scenario described above. Now exactly *because* SVL works as desired, we have to revisit some earlier patches: - It is no longer necessary to manipulate the VID of the 'bridge fdb {add,del}' command when vlan_filtering is off. This is because now, SVL is enabled for that case, so the actual VID does not matter*. - It is still desirable to hide dsa_8021q VID's in the FDB dump callback. But right now the dump callback should no longer hide duplicates (one per each front panel port's pvid, plus one for the VLAN that the CPU port is going to tag a TX frame with), because there shouldn't be any (the switch will match a single FDB entry no matter its VID anyway). * Not really... It's no longer necessary to transform a 'bridge fdb add' into 5 fdb add operations, but the user might still add a fdb entry with any vid, and all of them would appear as duplicates in 'bridge fdb show'. So force a 'bridge fdb add' to insert the VID of 0**, so that we can prune the duplicates at insertion time. ** The VID of 0 is better than 1 because it is always guaranteed to be in the ports' hardware filter. DSA also avoids putting the VID inside the netlink response message towards the bridge driver when we return this particular VID, which makes it suitable for FDB entries learnt with vlan_filtering off. Fixes: 227d07a07ef1 ("net: dsa: sja1105: Add support for traffic through standalone ports") Signed-off-by: Vladimir Oltean Signed-off-by: Georg Waibel Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 121 +++++++++++-------------- 1 file changed, 55 insertions(+), 66 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 6ed5f1e35789..b6d8ef0ab879 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -218,7 +218,7 @@ static int sja1105_init_l2_lookup_params(struct sja1105_private *priv) /* This selects between Independent VLAN Learning (IVL) and * Shared VLAN Learning (SVL) */ - .shared_learn = false, + .shared_learn = true, /* Don't discard management traffic based on ENFPORT - * we don't perform SMAC port enforcement anyway, so * what we are setting here doesn't matter. @@ -1092,8 +1092,13 @@ int sja1105pqrs_fdb_add(struct dsa_switch *ds, int port, l2_lookup.vlanid = vid; l2_lookup.iotag = SJA1105_S_TAG; l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0); - l2_lookup.mask_vlanid = VLAN_VID_MASK; - l2_lookup.mask_iotag = BIT(0); + if (dsa_port_is_vlan_filtering(&ds->ports[port])) { + l2_lookup.mask_vlanid = VLAN_VID_MASK; + l2_lookup.mask_iotag = BIT(0); + } else { + l2_lookup.mask_vlanid = 0; + l2_lookup.mask_iotag = 0; + } l2_lookup.destports = BIT(port); rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP, @@ -1150,8 +1155,13 @@ int sja1105pqrs_fdb_del(struct dsa_switch *ds, int port, l2_lookup.vlanid = vid; l2_lookup.iotag = SJA1105_S_TAG; l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0); - l2_lookup.mask_vlanid = VLAN_VID_MASK; - l2_lookup.mask_iotag = BIT(0); + if (dsa_port_is_vlan_filtering(&ds->ports[port])) { + l2_lookup.mask_vlanid = VLAN_VID_MASK; + l2_lookup.mask_iotag = BIT(0); + } else { + l2_lookup.mask_vlanid = 0; + l2_lookup.mask_iotag = 0; + } l2_lookup.destports = BIT(port); rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP, @@ -1181,60 +1191,31 @@ static int sja1105_fdb_add(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid) { struct sja1105_private *priv = ds->priv; - u16 rx_vid, tx_vid; - int rc, i; - if (dsa_port_is_vlan_filtering(&ds->ports[port])) - return priv->info->fdb_add_cmd(ds, port, addr, vid); - - /* Since we make use of VLANs even when the bridge core doesn't tell us - * to, translate these FDB entries into the correct dsa_8021q ones. - * The basic idea (also repeats for removal below) is: - * - Each of the other front-panel ports needs to be able to forward a - * pvid-tagged (aka tagged with their rx_vid) frame that matches this - * DMAC. - * - The CPU port (aka the tx_vid of this port) needs to be able to - * send a frame matching this DMAC to the specified port. - * For a better picture see net/dsa/tag_8021q.c. + /* dsa_8021q is in effect when the bridge's vlan_filtering isn't, + * so the switch still does some VLAN processing internally. + * But Shared VLAN Learning (SVL) is also active, and it will take + * care of autonomous forwarding between the unique pvid's of each + * port. Here we just make sure that users can't add duplicate FDB + * entries when in this mode - the actual VID doesn't matter except + * for what gets printed in 'bridge fdb show'. In the case of zero, + * no VID gets printed at all. */ - for (i = 0; i < SJA1105_NUM_PORTS; i++) { - if (i == port) - continue; - if (i == dsa_upstream_port(priv->ds, port)) - continue; + if (!dsa_port_is_vlan_filtering(&ds->ports[port])) + vid = 0; - rx_vid = dsa_8021q_rx_vid(ds, i); - rc = priv->info->fdb_add_cmd(ds, port, addr, rx_vid); - if (rc < 0) - return rc; - } - tx_vid = dsa_8021q_tx_vid(ds, port); - return priv->info->fdb_add_cmd(ds, port, addr, tx_vid); + return priv->info->fdb_add_cmd(ds, port, addr, vid); } static int sja1105_fdb_del(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid) { struct sja1105_private *priv = ds->priv; - u16 rx_vid, tx_vid; - int rc, i; - if (dsa_port_is_vlan_filtering(&ds->ports[port])) - return priv->info->fdb_del_cmd(ds, port, addr, vid); + if (!dsa_port_is_vlan_filtering(&ds->ports[port])) + vid = 0; - for (i = 0; i < SJA1105_NUM_PORTS; i++) { - if (i == port) - continue; - if (i == dsa_upstream_port(priv->ds, port)) - continue; - - rx_vid = dsa_8021q_rx_vid(ds, i); - rc = priv->info->fdb_del_cmd(ds, port, addr, rx_vid); - if (rc < 0) - return rc; - } - tx_vid = dsa_8021q_tx_vid(ds, port); - return priv->info->fdb_del_cmd(ds, port, addr, tx_vid); + return priv->info->fdb_del_cmd(ds, port, addr, vid); } static int sja1105_fdb_dump(struct dsa_switch *ds, int port, @@ -1288,24 +1269,9 @@ static int sja1105_fdb_dump(struct dsa_switch *ds, int port, l2_lookup.lockeds = (match >= 0); } - /* We need to hide the dsa_8021q VLANs from the user. This - * basically means hiding the duplicates and only showing - * the pvid that is supposed to be active in standalone and - * non-vlan_filtering modes (aka 1). - * - For statically added FDB entries (bridge fdb add), we - * can convert the TX VID (coming from the CPU port) into the - * pvid and ignore the RX VIDs of the other ports. - * - For dynamically learned FDB entries, a single entry with - * no duplicates is learned - that which has the real port's - * pvid, aka RX VID. - */ - if (!dsa_port_is_vlan_filtering(&ds->ports[port])) { - if (l2_lookup.vlanid == tx_vid || - l2_lookup.vlanid == rx_vid) - l2_lookup.vlanid = 1; - else - continue; - } + /* We need to hide the dsa_8021q VLANs from the user. */ + if (!dsa_port_is_vlan_filtering(&ds->ports[port])) + l2_lookup.vlanid = 0; cb(macaddr, l2_lookup.vlanid, l2_lookup.lockeds, data); } return 0; @@ -1597,6 +1563,7 @@ static int sja1105_vlan_prepare(struct dsa_switch *ds, int port, */ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled) { + struct sja1105_l2_lookup_params_entry *l2_lookup_params; struct sja1105_general_params_entry *general_params; struct sja1105_private *priv = ds->priv; struct sja1105_table *table; @@ -1625,6 +1592,28 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled) general_params->incl_srcpt1 = enabled; general_params->incl_srcpt0 = enabled; + /* VLAN filtering => independent VLAN learning. + * No VLAN filtering => shared VLAN learning. + * + * In shared VLAN learning mode, untagged traffic still gets + * pvid-tagged, and the FDB table gets populated with entries + * containing the "real" (pvid or from VLAN tag) VLAN ID. + * However the switch performs a masked L2 lookup in the FDB, + * effectively only looking up a frame's DMAC (and not VID) for the + * forwarding decision. + * + * This is extremely convenient for us, because in modes with + * vlan_filtering=0, dsa_8021q actually installs unique pvid's into + * each front panel port. This is good for identification but breaks + * learning badly - the VID of the learnt FDB entry is unique, aka + * no frames coming from any other port are going to have it. So + * for forwarding purposes, this is as though learning was broken + * (all frames get flooded). + */ + table = &priv->static_config.tables[BLK_IDX_L2_LOOKUP_PARAMS]; + l2_lookup_params = table->entries; + l2_lookup_params->shared_learn = !enabled; + rc = sja1105_static_config_reload(priv); if (rc) dev_err(ds->dev, "Failed to change VLAN Ethertype\n"); From 4b7da3d808f91cdad3e34059cd68ba3dfe4c3695 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 5 Aug 2019 01:38:45 +0300 Subject: [PATCH 820/823] net: dsa: sja1105: Use the LOCKEDS bit for SJA1105 E/T as well It looks like the FDB dump taken from first-generation switches also contains information on whether entries are static or not. So use that instead of searching through the driver's tables. Fixes: d763778224ea ("net: dsa: sja1105: Implement is_static for FDB entries on E/T") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_dynamic_config.c | 14 +++++++++++++- drivers/net/dsa/sja1105/sja1105_main.c | 15 --------------- 2 files changed, 13 insertions(+), 16 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c index 6bfb1696a6f2..9988c9d18567 100644 --- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c +++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c @@ -277,6 +277,18 @@ sja1105et_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, SJA1105ET_SIZE_L2_LOOKUP_ENTRY, op); } +static size_t sja1105et_dyn_l2_lookup_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_l2_lookup_entry *entry = entry_ptr; + u8 *cmd = buf + SJA1105ET_SIZE_L2_LOOKUP_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(cmd, &entry->lockeds, 28, 28, size, op); + + return sja1105et_l2_lookup_entry_packing(buf, entry_ptr, op); +} + static void sja1105et_mgmt_route_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, enum packing_op op) @@ -477,7 +489,7 @@ sja1105et_general_params_entry_packing(void *buf, void *entry_ptr, /* SJA1105E/T: First generation */ struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = { [BLK_IDX_L2_LOOKUP] = { - .entry_packing = sja1105et_l2_lookup_entry_packing, + .entry_packing = sja1105et_dyn_l2_lookup_entry_packing, .cmd_packing = sja1105et_l2_lookup_cmd_packing, .access = (OP_READ | OP_WRITE | OP_DEL), .max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT, diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index b6d8ef0ab879..a573ae136ebd 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1254,21 +1254,6 @@ static int sja1105_fdb_dump(struct dsa_switch *ds, int port, continue; u64_to_ether_addr(l2_lookup.macaddr, macaddr); - /* On SJA1105 E/T, the switch doesn't implement the LOCKEDS - * bit, so it doesn't tell us whether a FDB entry is static - * or not. - * But, of course, we can find out - we're the ones who added - * it in the first place. - */ - if (priv->info->device_id == SJA1105E_DEVICE_ID || - priv->info->device_id == SJA1105T_DEVICE_ID) { - int match; - - match = sja1105_find_static_fdb_entry(priv, port, - &l2_lookup); - l2_lookup.lockeds = (match >= 0); - } - /* We need to hide the dsa_8021q VLANs from the user. */ if (!dsa_port_is_vlan_filtering(&ds->ports[port])) l2_lookup.vlanid = 0; From 6cb0abbdf90c180e1310976c47399f57477e0e53 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 5 Aug 2019 01:38:46 +0300 Subject: [PATCH 821/823] net: dsa: sja1105: Really fix panic on unregistering PTP clock The IS_ERR_OR_NULL(priv->clock) check inside sja1105_ptp_clock_unregister() is preventing cancel_delayed_work_sync from actually being run. Additionally, sja1105_ptp_clock_unregister() does not actually get run, when placed in sja1105_remove(). The DSA switch gets torn down, but the sja1105 module does not get unregistered. So sja1105_ptp_clock_unregister needs to be moved to sja1105_teardown, to be symmetrical with sja1105_ptp_clock_register which is called from the DSA sja1105_setup. It is strange to fix a "fixes" patch, but the probe failure can only be seen when the attached PHY does not respond to MDIO (issue which I can't pinpoint the reason to) and it goes away after I power-cycle the board. This time the patch was validated on a failing board, and the kernel panic from the fixed commit's message can no longer be seen. Fixes: 29dd908d355f ("net: dsa: sja1105: Cancel PTP delayed work on unregister") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 4 ++-- drivers/net/dsa/sja1105/sja1105_ptp.c | 7 +++---- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index a573ae136ebd..d073baffc20b 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1728,6 +1728,8 @@ static void sja1105_teardown(struct dsa_switch *ds) cancel_work_sync(&priv->tagger_data.rxtstamp_work); skb_queue_purge(&priv->tagger_data.skb_rxtstamp_queue); + sja1105_ptp_clock_unregister(priv); + sja1105_static_config_free(&priv->static_config); } static int sja1105_mgmt_xmit(struct dsa_switch *ds, int port, int slot, @@ -2185,9 +2187,7 @@ static int sja1105_remove(struct spi_device *spi) { struct sja1105_private *priv = spi_get_drvdata(spi); - sja1105_ptp_clock_unregister(priv); dsa_unregister_switch(priv->ds); - sja1105_static_config_free(&priv->static_config); return 0; } diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index d19cfdf681af..d8e8dd59f3d1 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -369,16 +369,15 @@ int sja1105_ptp_clock_register(struct sja1105_private *priv) .mult = SJA1105_CC_MULT, }; mutex_init(&priv->ptp_lock); - INIT_DELAYED_WORK(&priv->refresh_work, sja1105_ptp_overflow_check); - - schedule_delayed_work(&priv->refresh_work, SJA1105_REFRESH_INTERVAL); - priv->ptp_caps = sja1105_ptp_caps; priv->clock = ptp_clock_register(&priv->ptp_caps, ds->dev); if (IS_ERR_OR_NULL(priv->clock)) return PTR_ERR(priv->clock); + INIT_DELAYED_WORK(&priv->refresh_work, sja1105_ptp_overflow_check); + schedule_delayed_work(&priv->refresh_work, SJA1105_REFRESH_INTERVAL); + return sja1105_ptp_reset(priv); } From f163fed2764e66511fb5c489bf87e532ad7606fb Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 5 Aug 2019 01:38:47 +0300 Subject: [PATCH 822/823] net: dsa: sja1105: Fix memory leak on meta state machine normal path After a meta frame is received, it is associated with the cached sp->data->stampable_skb from the DSA tagger private structure. Cached means its refcount is incremented with skb_get() in order for dsa_switch_rcv() to not free it when the tagger .rcv returns NULL. The mistake is that skb_unref() is not the correct function to use. It will correctly decrement the refcount (which will go back to zero) but the skb memory will not be freed. That is the job of kfree_skb(), which also calls skb_unref(). But it turns out that freeing the cached stampable_skb is in fact not necessary. It is still a perfectly valid skb, and now it is even annotated with the partial RX timestamp. So remove the skb_copy() altogether and simply pass the stampable_skb with a refcount of 1 (incremented by us, decremented by dsa_switch_rcv) up the stack. Fixes: f3097be21bf1 ("net: dsa: sja1105: Add a state machine for RX timestamping") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- net/dsa/tag_sja1105.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 26363d72d25b..8fa8dda8a15b 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -211,17 +211,8 @@ static struct sk_buff * for further processing up the network stack. */ kfree_skb(skb); - - skb = skb_copy(stampable_skb, GFP_ATOMIC); - if (!skb) { - dev_err_ratelimited(dp->ds->dev, - "Failed to copy stampable skb\n"); - spin_unlock(&sp->data->meta_lock); - return NULL; - } + skb = stampable_skb; sja1105_transfer_meta(skb, meta); - /* The cached copy will be freed now */ - skb_unref(stampable_skb); spin_unlock(&sp->data->meta_lock); } From 93fa8587b25356382a39f1ca3a81d6c1b42ac731 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 5 Aug 2019 01:38:48 +0300 Subject: [PATCH 823/823] net: dsa: sja1105: Fix memory leak on meta state machine error path When RX timestamping is enabled and two link-local (non-meta) frames are received in a row, this constitutes an error. The tagger is always caching the last link-local frame, in an attempt to merge it with the meta follow-up frame when that arrives. To recover from the above error condition, the initial cached link-local frame is dropped and the second frame in a row is cached (in expectance of the second meta frame). However, when dropping the initial link-local frame, its backing memory was being leaked. Fixes: f3097be21bf1 ("net: dsa: sja1105: Add a state machine for RX timestamping") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- net/dsa/tag_sja1105.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 8fa8dda8a15b..47ee88163a9d 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -165,6 +165,7 @@ static struct sk_buff "Expected meta frame, is %12llx " "in the DSA master multicast filter?\n", SJA1105_META_DMAC); + kfree_skb(sp->data->stampable_skb); } /* Hold a reference to avoid dsa_switch_rcv