diff --git a/.mailmap b/.mailmap index e2af78f67f7c..e42486317d18 100644 --- a/.mailmap +++ b/.mailmap @@ -265,7 +265,9 @@ Krzysztof Kozlowski Krzysztof Kozlowski Kuninori Morimoto Kuogee Hsieh +Leonard Crestez Leonard Crestez Leonardo Bras +Leonard Göhrs Leonid I Ananiev Leon Romanovsky Leon Romanovsky diff --git a/Documentation/devicetree/bindings/interrupt-controller/loongarch,cpu-interrupt-controller.yaml b/Documentation/devicetree/bindings/interrupt-controller/loongson,cpu-interrupt-controller.yaml similarity index 72% rename from Documentation/devicetree/bindings/interrupt-controller/loongarch,cpu-interrupt-controller.yaml rename to Documentation/devicetree/bindings/interrupt-controller/loongson,cpu-interrupt-controller.yaml index 2a1cf885c99d..adf989976dcc 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/loongarch,cpu-interrupt-controller.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/loongson,cpu-interrupt-controller.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause %YAML 1.2 --- -$id: http://devicetree.org/schemas/interrupt-controller/loongarch,cpu-interrupt-controller.yaml# +$id: http://devicetree.org/schemas/interrupt-controller/loongson,cpu-interrupt-controller.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: LoongArch CPU Interrupt Controller @@ -11,7 +11,7 @@ maintainers: properties: compatible: - const: loongarch,cpu-interrupt-controller + const: loongson,cpu-interrupt-controller '#interrupt-cells': const: 1 @@ -28,7 +28,7 @@ required: examples: - | interrupt-controller { - compatible = "loongarch,cpu-interrupt-controller"; + compatible = "loongson,cpu-interrupt-controller"; #interrupt-cells = <1>; interrupt-controller; }; diff --git a/Documentation/devicetree/bindings/serial/renesas,scif.yaml b/Documentation/devicetree/bindings/serial/renesas,scif.yaml index 1989bd67d04e..54e4f41be9b4 100644 --- a/Documentation/devicetree/bindings/serial/renesas,scif.yaml +++ b/Documentation/devicetree/bindings/serial/renesas,scif.yaml @@ -92,7 +92,7 @@ properties: - description: Error interrupt - description: Receive buffer full interrupt - description: Transmit buffer empty interrupt - - description: Transmit End interrupt + - description: Break interrupt - items: - description: Error interrupt - description: Receive buffer full interrupt @@ -107,7 +107,7 @@ properties: - const: eri - const: rxi - const: txi - - const: tei + - const: bri - items: - const: eri - const: rxi diff --git a/Documentation/mm/zsmalloc.rst b/Documentation/mm/zsmalloc.rst index 64d127bfc221..a3c26d587752 100644 --- a/Documentation/mm/zsmalloc.rst +++ b/Documentation/mm/zsmalloc.rst @@ -39,13 +39,12 @@ With CONFIG_ZSMALLOC_STAT, we could see zsmalloc internal information via # cat /sys/kernel/debug/zsmalloc/zram0/classes - class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage + class size 10% 20% 30% 40% 50% 60% 70% 80% 90% 99% 100% obj_allocated obj_used pages_used pages_per_zspage freeable ... ... - 9 176 0 1 186 129 8 4 - 10 192 1 0 2880 2872 135 3 - 11 208 0 1 819 795 42 2 - 12 224 0 1 219 159 12 4 + 30 512 0 12 4 1 0 1 0 0 1 0 414 3464 3346 433 1 14 + 31 528 2 7 2 2 1 0 1 0 0 2 117 4154 3793 536 4 44 + 32 544 6 3 4 1 2 1 0 0 0 1 260 4170 3965 556 2 26 ... ... @@ -54,10 +53,28 @@ class index size object size zspage stores -almost_empty - the number of ZS_ALMOST_EMPTY zspages(see below) -almost_full - the number of ZS_ALMOST_FULL zspages(see below) +10% + the number of zspages with usage ratio less than 10% (see below) +20% + the number of zspages with usage ratio between 10% and 20% +30% + the number of zspages with usage ratio between 20% and 30% +40% + the number of zspages with usage ratio between 30% and 40% +50% + the number of zspages with usage ratio between 40% and 50% +60% + the number of zspages with usage ratio between 50% and 60% +70% + the number of zspages with usage ratio between 60% and 70% +80% + the number of zspages with usage ratio between 70% and 80% +90% + the number of zspages with usage ratio between 80% and 90% +99% + the number of zspages with usage ratio between 90% and 99% +100% + the number of zspages with usage ratio 100% obj_allocated the number of objects allocated obj_used @@ -66,19 +83,14 @@ pages_used the number of pages allocated for the class pages_per_zspage the number of 0-order pages to make a zspage +freeable + the approximate number of pages class compaction can free -We assign a zspage to ZS_ALMOST_EMPTY fullness group when n <= N / f, where - -* n = number of allocated objects -* N = total number of objects zspage can store -* f = fullness_threshold_frac(ie, 4 at the moment) - -Similarly, we assign zspage to: - -* ZS_ALMOST_FULL when n > N / f -* ZS_EMPTY when n == 0 -* ZS_FULL when n == N - +Each zspage maintains inuse counter which keeps track of the number of +objects stored in the zspage. The inuse counter determines the zspage's +"fullness group" which is calculated as the ratio of the "inuse" objects to +the total number of objects the zspage can hold (objs_per_zspage). The +closer the inuse counter is to objs_per_zspage, the better. Internals ========= @@ -94,10 +106,10 @@ of objects that each zspage can store. For instance, consider the following size classes::: - class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage freeable + class size 10% .... 100% obj_allocated obj_used pages_used pages_per_zspage freeable ... - 94 1536 0 0 0 0 0 3 0 - 100 1632 0 0 0 0 0 2 0 + 94 1536 0 .... 0 0 0 0 3 0 + 100 1632 0 .... 0 0 0 0 2 0 ... @@ -134,10 +146,11 @@ reduces memory wastage. Let's take a closer look at the bottom of `/sys/kernel/debug/zsmalloc/zramX/classes`::: - class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage freeable + class size 10% .... 100% obj_allocated obj_used pages_used pages_per_zspage freeable + ... - 202 3264 0 0 0 0 0 4 0 - 254 4096 0 0 0 0 0 1 0 + 202 3264 0 .. 0 0 0 0 4 0 + 254 4096 0 .. 0 0 0 0 1 0 ... Size class #202 stores objects of size 3264 bytes and has a maximum of 4 pages @@ -151,40 +164,42 @@ efficient storage of large objects. For zspage chain size of 8, huge class watermark becomes 3632 bytes::: - class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage freeable + class size 10% .... 100% obj_allocated obj_used pages_used pages_per_zspage freeable + ... - 202 3264 0 0 0 0 0 4 0 - 211 3408 0 0 0 0 0 5 0 - 217 3504 0 0 0 0 0 6 0 - 222 3584 0 0 0 0 0 7 0 - 225 3632 0 0 0 0 0 8 0 - 254 4096 0 0 0 0 0 1 0 + 202 3264 0 .. 0 0 0 0 4 0 + 211 3408 0 .. 0 0 0 0 5 0 + 217 3504 0 .. 0 0 0 0 6 0 + 222 3584 0 .. 0 0 0 0 7 0 + 225 3632 0 .. 0 0 0 0 8 0 + 254 4096 0 .. 0 0 0 0 1 0 ... For zspage chain size of 16, huge class watermark becomes 3840 bytes::: - class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage freeable + class size 10% .... 100% obj_allocated obj_used pages_used pages_per_zspage freeable + ... - 202 3264 0 0 0 0 0 4 0 - 206 3328 0 0 0 0 0 13 0 - 207 3344 0 0 0 0 0 9 0 - 208 3360 0 0 0 0 0 14 0 - 211 3408 0 0 0 0 0 5 0 - 212 3424 0 0 0 0 0 16 0 - 214 3456 0 0 0 0 0 11 0 - 217 3504 0 0 0 0 0 6 0 - 219 3536 0 0 0 0 0 13 0 - 222 3584 0 0 0 0 0 7 0 - 223 3600 0 0 0 0 0 15 0 - 225 3632 0 0 0 0 0 8 0 - 228 3680 0 0 0 0 0 9 0 - 230 3712 0 0 0 0 0 10 0 - 232 3744 0 0 0 0 0 11 0 - 234 3776 0 0 0 0 0 12 0 - 235 3792 0 0 0 0 0 13 0 - 236 3808 0 0 0 0 0 14 0 - 238 3840 0 0 0 0 0 15 0 - 254 4096 0 0 0 0 0 1 0 + 202 3264 0 .. 0 0 0 0 4 0 + 206 3328 0 .. 0 0 0 0 13 0 + 207 3344 0 .. 0 0 0 0 9 0 + 208 3360 0 .. 0 0 0 0 14 0 + 211 3408 0 .. 0 0 0 0 5 0 + 212 3424 0 .. 0 0 0 0 16 0 + 214 3456 0 .. 0 0 0 0 11 0 + 217 3504 0 .. 0 0 0 0 6 0 + 219 3536 0 .. 0 0 0 0 13 0 + 222 3584 0 .. 0 0 0 0 7 0 + 223 3600 0 .. 0 0 0 0 15 0 + 225 3632 0 .. 0 0 0 0 8 0 + 228 3680 0 .. 0 0 0 0 9 0 + 230 3712 0 .. 0 0 0 0 10 0 + 232 3744 0 .. 0 0 0 0 11 0 + 234 3776 0 .. 0 0 0 0 12 0 + 235 3792 0 .. 0 0 0 0 13 0 + 236 3808 0 .. 0 0 0 0 14 0 + 238 3840 0 .. 0 0 0 0 15 0 + 254 4096 0 .. 0 0 0 0 1 0 ... Overall the combined zspage chain size effect on zsmalloc pool configuration::: @@ -214,9 +229,10 @@ zram as a build artifacts storage (Linux kernel compilation). zsmalloc classes stats::: - class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage freeable + class size 10% .... 100% obj_allocated obj_used pages_used pages_per_zspage freeable + ... - Total 13 51 413836 412973 159955 3 + Total 13 .. 51 413836 412973 159955 3 zram mm_stat::: @@ -227,9 +243,10 @@ zram as a build artifacts storage (Linux kernel compilation). zsmalloc classes stats::: - class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage freeable + class size 10% .... 100% obj_allocated obj_used pages_used pages_per_zspage freeable + ... - Total 18 87 414852 412978 156666 0 + Total 18 .. 87 414852 412978 156666 0 zram mm_stat::: diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 87dd1c5283e6..58a78a316697 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -340,6 +340,8 @@ tcp_app_win - INTEGER Reserve max(window/2^tcp_app_win, mss) of window for application buffer. Value 0 is special, it means that nothing is reserved. + Possible values are [0, 31], inclusive. + Default: 31 tcp_autocorking - BOOLEAN diff --git a/MAINTAINERS b/MAINTAINERS index fdcef63fa9a0..b8b275e27cdb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -224,13 +224,13 @@ S: Orphan / Obsolete F: drivers/net/ethernet/8390/ 9P FILE SYSTEM -M: Eric Van Hensbergen +M: Eric Van Hensbergen M: Latchesar Ionkov M: Dominique Martinet R: Christian Schoenebeck -L: v9fs-developer@lists.sourceforge.net +L: v9fs@lists.linux.dev S: Maintained -W: http://swik.net/v9fs +W: http://github.com/v9fs Q: http://patchwork.kernel.org/project/v9fs-devel/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/ericvh/v9fs.git T: git git://github.com/martinetd/linux.git @@ -4468,14 +4468,14 @@ F: Documentation/devicetree/bindings/net/ieee802154/ca8210.txt F: drivers/net/ieee802154/ca8210.c CANAAN/KENDRYTE K210 SOC FPIOA DRIVER -M: Damien Le Moal +M: Damien Le Moal L: linux-riscv@lists.infradead.org L: linux-gpio@vger.kernel.org (pinctrl driver) F: Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml F: drivers/pinctrl/pinctrl-k210.c CANAAN/KENDRYTE K210 SOC RESET CONTROLLER DRIVER -M: Damien Le Moal +M: Damien Le Moal L: linux-kernel@vger.kernel.org L: linux-riscv@lists.infradead.org S: Maintained @@ -4483,7 +4483,7 @@ F: Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml F: drivers/reset/reset-k210.c CANAAN/KENDRYTE K210 SOC SYSTEM CONTROLLER DRIVER -M: Damien Le Moal +M: Damien Le Moal L: linux-riscv@lists.infradead.org S: Maintained F: Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml @@ -11765,7 +11765,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git F: drivers/ata/sata_promise.* LIBATA SUBSYSTEM (Serial and Parallel ATA drivers) -M: Damien Le Moal +M: Damien Le Moal L: linux-ide@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/libata.git @@ -23139,7 +23139,7 @@ S: Maintained F: arch/x86/kernel/cpu/zhaoxin.c ZONEFS FILESYSTEM -M: Damien Le Moal +M: Damien Le Moal M: Naohiro Aota R: Johannes Thumshirn L: linux-fsdevel@vger.kernel.org diff --git a/Makefile b/Makefile index ef4e96b9cd5b..5aeea3d98fc0 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 3 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm64/kernel/compat_alignment.c b/arch/arm64/kernel/compat_alignment.c index 5edec2f49ec9..deff21bfa680 100644 --- a/arch/arm64/kernel/compat_alignment.c +++ b/arch/arm64/kernel/compat_alignment.c @@ -314,36 +314,32 @@ int do_compat_alignment_fixup(unsigned long addr, struct pt_regs *regs) int (*handler)(unsigned long addr, u32 instr, struct pt_regs *regs); unsigned int type; u32 instr = 0; - u16 tinstr = 0; int isize = 4; int thumb2_32b = 0; - int fault; instrptr = instruction_pointer(regs); if (compat_thumb_mode(regs)) { __le16 __user *ptr = (__le16 __user *)(instrptr & ~1); + u16 tinstr, tinst2; - fault = alignment_get_thumb(regs, ptr, &tinstr); - if (!fault) { - if (IS_T32(tinstr)) { - /* Thumb-2 32-bit */ - u16 tinst2; - fault = alignment_get_thumb(regs, ptr + 1, &tinst2); - instr = ((u32)tinstr << 16) | tinst2; - thumb2_32b = 1; - } else { - isize = 2; - instr = thumb2arm(tinstr); - } + if (alignment_get_thumb(regs, ptr, &tinstr)) + return 1; + + if (IS_T32(tinstr)) { /* Thumb-2 32-bit */ + if (alignment_get_thumb(regs, ptr + 1, &tinst2)) + return 1; + instr = ((u32)tinstr << 16) | tinst2; + thumb2_32b = 1; + } else { + isize = 2; + instr = thumb2arm(tinstr); } } else { - fault = alignment_get_arm(regs, (__le32 __user *)instrptr, &instr); + if (alignment_get_arm(regs, (__le32 __user *)instrptr, &instr)) + return 1; } - if (fault) - return 1; - switch (CODING_BITS(instr)) { case 0x00000000: /* 3.13.4 load/store instruction extensions */ if (LDSTHD_I_BIT(instr)) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 3f6a5efdbcf0..4b2e16e696a8 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1890,9 +1890,33 @@ static int __init do_pkvm_init(u32 hyp_va_bits) return ret; } +static u64 get_hyp_id_aa64pfr0_el1(void) +{ + /* + * Track whether the system isn't affected by spectre/meltdown in the + * hypervisor's view of id_aa64pfr0_el1, used for protected VMs. + * Although this is per-CPU, we make it global for simplicity, e.g., not + * to have to worry about vcpu migration. + * + * Unlike for non-protected VMs, userspace cannot override this for + * protected VMs. + */ + u64 val = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); + + val &= ~(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2) | + ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3)); + + val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2), + arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED); + val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3), + arm64_get_meltdown_state() == SPECTRE_UNAFFECTED); + + return val; +} + static void kvm_hyp_init_symbols(void) { - kvm_nvhe_sym(id_aa64pfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); + kvm_nvhe_sym(id_aa64pfr0_el1_sys_val) = get_hyp_id_aa64pfr0_el1(); kvm_nvhe_sym(id_aa64pfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1); kvm_nvhe_sym(id_aa64isar0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR0_EL1); kvm_nvhe_sym(id_aa64isar1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR1_EL1); diff --git a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h index 07edfc7524c9..37440e1dda93 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h +++ b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h @@ -33,11 +33,14 @@ * Allow for protected VMs: * - Floating-point and Advanced SIMD * - Data Independent Timing + * - Spectre/Meltdown Mitigation */ #define PVM_ID_AA64PFR0_ALLOW (\ ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_FP) | \ ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_AdvSIMD) | \ - ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_DIT) \ + ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_DIT) | \ + ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2) | \ + ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3) \ ) /* diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 08d2b004f4b7..edd969a1f36b 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -85,19 +85,12 @@ static u64 get_restricted_features_unsigned(u64 sys_reg_val, static u64 get_pvm_id_aa64pfr0(const struct kvm_vcpu *vcpu) { - const struct kvm *kvm = (const struct kvm *)kern_hyp_va(vcpu->kvm); u64 set_mask = 0; u64 allow_mask = PVM_ID_AA64PFR0_ALLOW; set_mask |= get_restricted_features_unsigned(id_aa64pfr0_el1_sys_val, PVM_ID_AA64PFR0_RESTRICT_UNSIGNED); - /* Spectre and Meltdown mitigation in KVM */ - set_mask |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2), - (u64)kvm->arch.pfr0_csv2); - set_mask |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3), - (u64)kvm->arch.pfr0_csv3); - return (id_aa64pfr0_el1_sys_val & allow_mask) | set_mask; } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index c243b10f3e15..5eca0cdd961d 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -558,6 +558,7 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) for_each_set_bit(i, &mask, 32) kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true); } + kvm_vcpu_pmu_restore_guest(vcpu); } static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 1b2c161120be..34688918c811 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -794,7 +794,6 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, if (!kvm_supports_32bit_el0()) val |= ARMV8_PMU_PMCR_LC; kvm_pmu_handle_pmcr(vcpu, val); - kvm_vcpu_pmu_restore_guest(vcpu); } else { /* PMCR.P & PMCR.C are RAZ */ val = __vcpu_sys_reg(vcpu, PMCR_EL0) diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index a6acb94ea3d6..c2edadb8ec6a 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -281,4 +281,8 @@ /* DMB */ #define A64_DMB_ISH aarch64_insn_gen_dmb(AARCH64_INSN_MB_ISH) +/* ADR */ +#define A64_ADR(Rd, offset) \ + aarch64_insn_gen_adr(0, offset, Rd, AARCH64_INSN_ADR_TYPE_ADR) + #endif /* _BPF_JIT_H */ diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 62f805f427b7..b26da8efa616 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1900,7 +1900,8 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, restore_args(ctx, args_off, nargs); /* call original func */ emit(A64_LDR64I(A64_R(10), A64_SP, retaddr_off), ctx); - emit(A64_BLR(A64_R(10)), ctx); + emit(A64_ADR(A64_LR, AARCH64_INSN_SIZE * 2), ctx); + emit(A64_RET(A64_R(10)), ctx); /* store return value */ emit(A64_STR64I(A64_R(0), A64_SP, retval_off), ctx); /* reserve a nop for bpf_tramp_image_put */ diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index e70c846efaa1..db9342b2d0e6 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -1022,6 +1022,10 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext emit_atomic(insn, ctx); break; + /* Speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; + default: pr_err("bpf_jit: unknown opcode %02x\n", code); return -EINVAL; diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um index b70559b821df..2106a2bd152b 100644 --- a/arch/x86/Makefile.um +++ b/arch/x86/Makefile.um @@ -3,9 +3,14 @@ core-y += arch/x86/crypto/ # # Disable SSE and other FP/SIMD instructions to match normal x86 +# This is required to work around issues in older LLVM versions, but breaks +# GCC versions < 11. See: +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=99652 # +ifeq ($(CONFIG_CC_IS_CLANG),y) KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2 +endif ifeq ($(CONFIG_X86_32),y) START := 0x8048000 diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index cbaf174d8efd..b3af2d45bbbb 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -125,6 +125,8 @@ #define INTEL_FAM6_LUNARLAKE_M 0xBD +#define INTEL_FAM6_ARROWLAKE 0xC6 + /* "Small Core" Processors (Atom/E-Core) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 1c38174b5f01..0dac4ab5b55b 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -146,7 +146,11 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) pr_debug("Local APIC address 0x%08x\n", madt->address); } - if (madt->header.revision >= 5) + + /* ACPI 6.3 and newer support the online capable bit. */ + if (acpi_gbl_FADT.header.revision > 6 || + (acpi_gbl_FADT.header.revision == 6 && + acpi_gbl_FADT.minor_revision >= 3)) acpi_support_online_capable = true; default_acpi_madt_oem_check(madt->header.oem_id, @@ -193,7 +197,8 @@ static bool __init acpi_is_processor_usable(u32 lapic_flags) if (lapic_flags & ACPI_MADT_ENABLED) return true; - if (acpi_support_online_capable && (lapic_flags & ACPI_MADT_ONLINE_CAPABLE)) + if (!acpi_support_online_capable || + (lapic_flags & ACPI_MADT_ONLINE_CAPABLE)) return true; return false; diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 615a76d70019..bf5161dcf89e 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include @@ -824,3 +825,23 @@ static void rs690_fix_64bit_dma(struct pci_dev *pdev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7910, rs690_fix_64bit_dma); #endif + +#ifdef CONFIG_AMD_NB + +#define AMD_15B8_RCC_DEV2_EPF0_STRAP2 0x10136008 +#define AMD_15B8_RCC_DEV2_EPF0_STRAP2_NO_SOFT_RESET_DEV2_F0_MASK 0x00000080L + +static void quirk_clear_strap_no_soft_reset_dev2_f0(struct pci_dev *dev) +{ + u32 data; + + if (!amd_smn_read(0, AMD_15B8_RCC_DEV2_EPF0_STRAP2, &data)) { + data &= ~AMD_15B8_RCC_DEV2_EPF0_STRAP2_NO_SOFT_RESET_DEV2_F0_MASK; + if (amd_smn_write(0, AMD_15B8_RCC_DEV2_EPF0_STRAP2, data)) + pci_err(dev, "Failed to write data 0x%x\n", data); + } else { + pci_err(dev, "Failed to read data\n"); + } +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15b8, quirk_clear_strap_no_soft_reset_dev2_f0); +#endif diff --git a/block/blk-mq.c b/block/blk-mq.c index cf1a39adf9a5..f0ea9dcfb966 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1359,8 +1359,6 @@ bool blk_rq_is_poll(struct request *rq) return false; if (rq->mq_hctx->type != HCTX_TYPE_POLL) return false; - if (WARN_ON_ONCE(!rq->bio)) - return false; return true; } EXPORT_SYMBOL_GPL(blk_rq_is_poll); @@ -1368,7 +1366,7 @@ EXPORT_SYMBOL_GPL(blk_rq_is_poll); static void blk_rq_poll_completion(struct request *rq, struct completion *wait) { do { - bio_poll(rq->bio, NULL, 0); + blk_mq_poll(rq->q, blk_rq_to_qc(rq), NULL, 0); cond_resched(); } while (!completion_done(wait)); } diff --git a/block/genhd.c b/block/genhd.c index 02d9cfb9e077..7f874737af68 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -368,7 +368,6 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode) if (disk->open_partitions) return -EBUSY; - set_bit(GD_NEED_PART_SCAN, &disk->state); /* * If the device is opened exclusively by current thread already, it's * safe to scan partitons, otherwise, use bd_prepare_to_claim() to @@ -381,12 +380,19 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode) return ret; } + set_bit(GD_NEED_PART_SCAN, &disk->state); bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~FMODE_EXCL, NULL); if (IS_ERR(bdev)) ret = PTR_ERR(bdev); else blkdev_put(bdev, mode & ~FMODE_EXCL); + /* + * If blkdev_get_by_dev() failed early, GD_NEED_PART_SCAN is still set, + * and this will cause that re-assemble partitioned raid device will + * creat partition for underlying disk. + */ + clear_bit(GD_NEED_PART_SCAN, &disk->state); if (!(mode & FMODE_EXCL)) bd_abort_claiming(disk->part0, disk_scan_partitions); return ret; diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 97b711e57bff..c7a6d0b69dab 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -1984,6 +1984,7 @@ static int instance; static int acpi_video_bus_add(struct acpi_device *device) { struct acpi_video_bus *video; + bool auto_detect; int error; acpi_status status; @@ -2045,10 +2046,20 @@ static int acpi_video_bus_add(struct acpi_device *device) mutex_unlock(&video_list_lock); /* - * The userspace visible backlight_device gets registered separately - * from acpi_video_register_backlight(). + * If backlight-type auto-detection is used then a native backlight may + * show up later and this may change the result from video to native. + * Therefor normally the userspace visible /sys/class/backlight device + * gets registered separately by the GPU driver calling + * acpi_video_register_backlight() when an internal panel is detected. + * Register the backlight now when not using auto-detection, so that + * when the kernel cmdline or DMI-quirks are used the backlight will + * get registered even if acpi_video_register_backlight() is not called. */ acpi_video_run_bcl_for_osi(video); + if (__acpi_video_get_backlight_type(false, &auto_detect) == acpi_backlight_video && + !auto_detect) + acpi_video_bus_register_backlight(video); + acpi_video_bus_add_notify_handler(video); return 0; diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index fd7cbce8076e..e85729fc481f 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -276,6 +276,43 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, }, + /* + * Models which need acpi_video backlight control where the GPU drivers + * do not call acpi_video_register_backlight() because no internal panel + * is detected. Typically these are all-in-ones (monitors with builtin + * PC) where the panel connection shows up as regular DP instead of eDP. + */ + { + .callback = video_detect_force_video, + /* Apple iMac14,1 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac14,1"), + }, + }, + { + .callback = video_detect_force_video, + /* Apple iMac14,2 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac14,2"), + }, + }, + + /* + * Older models with nvidia GPU which need acpi_video backlight + * control and where the old nvidia binary driver series does not + * call acpi_video_register_backlight(). + */ + { + .callback = video_detect_force_video, + /* ThinkPad W530 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W530"), + }, + }, + /* * These models have a working acpi_video backlight control, and using * native backlight causes a regression where backlight does not work @@ -782,7 +819,7 @@ static bool prefer_native_over_acpi_video(void) * Determine which type of backlight interface to use on this system, * First check cmdline, then dmi quirks, then do autodetect. */ -static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) +enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto_detect) { static DEFINE_MUTEX(init_mutex); static bool nvidia_wmi_ec_present; @@ -807,6 +844,9 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) native_available = true; mutex_unlock(&init_mutex); + if (auto_detect) + *auto_detect = false; + /* * The below heuristics / detection steps are in order of descending * presedence. The commandline takes presedence over anything else. @@ -818,6 +858,9 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) if (acpi_backlight_dmi != acpi_backlight_undef) return acpi_backlight_dmi; + if (auto_detect) + *auto_detect = true; + /* Special cases such as nvidia_wmi_ec and apple gmux. */ if (nvidia_wmi_ec_present) return acpi_backlight_nvidia_wmi_ec; @@ -837,15 +880,4 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) /* No ACPI video/native (old hw), use vendor specific fw methods. */ return acpi_backlight_vendor; } - -enum acpi_backlight_type acpi_video_get_backlight_type(void) -{ - return __acpi_video_get_backlight_type(false); -} -EXPORT_SYMBOL(acpi_video_get_backlight_type); - -bool acpi_video_backlight_use_native(void) -{ - return __acpi_video_get_backlight_type(true) == acpi_backlight_native; -} -EXPORT_SYMBOL(acpi_video_backlight_use_native); +EXPORT_SYMBOL(__acpi_video_get_backlight_type); diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index c73cc57ec547..604c1a13c76e 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -246,7 +246,7 @@ static int ublk_validate_params(const struct ublk_device *ub) if (ub->params.types & UBLK_PARAM_TYPE_BASIC) { const struct ublk_param_basic *p = &ub->params.basic; - if (p->logical_bs_shift > PAGE_SHIFT) + if (p->logical_bs_shift > PAGE_SHIFT || p->logical_bs_shift < 9) return -EINVAL; if (p->logical_bs_shift > p->physical_bs_shift) @@ -1261,9 +1261,10 @@ static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id, ublk_queue_cmd(ubq, req); } -static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) +static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, + unsigned int issue_flags, + struct ublksrv_io_cmd *ub_cmd) { - struct ublksrv_io_cmd *ub_cmd = (struct ublksrv_io_cmd *)cmd->cmd; struct ublk_device *ub = cmd->file->private_data; struct ublk_queue *ubq; struct ublk_io *io; @@ -1362,6 +1363,23 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) return -EIOCBQUEUED; } +static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) +{ + struct ublksrv_io_cmd *ub_src = (struct ublksrv_io_cmd *) cmd->cmd; + struct ublksrv_io_cmd ub_cmd; + + /* + * Not necessary for async retry, but let's keep it simple and always + * copy the values to avoid any potential reuse. + */ + ub_cmd.q_id = READ_ONCE(ub_src->q_id); + ub_cmd.tag = READ_ONCE(ub_src->tag); + ub_cmd.result = READ_ONCE(ub_src->result); + ub_cmd.addr = READ_ONCE(ub_src->addr); + + return __ublk_ch_uring_cmd(cmd, issue_flags, &ub_cmd); +} + static const struct file_operations ublk_ch_fops = { .owner = THIS_MODULE, .open = ublk_ch_open, @@ -1952,6 +1970,8 @@ static int ublk_ctrl_set_params(struct ublk_device *ub, /* clear all we don't support yet */ ub->params.types &= UBLK_PARAM_TYPE_ALL; ret = ublk_validate_params(ub); + if (ret) + ub->params.types = 0; } mutex_unlock(&ub->mutex); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 2723eede6f21..2b918e28acaa 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -96,16 +96,14 @@ struct virtblk_req { /* * The zone append command has an extended in header. - * The status field in zone_append_in_hdr must have - * the same offset in virtblk_req as the non-zoned - * status field above. + * The status field in zone_append_in_hdr must always + * be the last byte. */ struct { + __virtio64 sector; u8 status; - u8 reserved[7]; - __le64 append_sector; - } zone_append_in_hdr; - }; + } zone_append; + } in_hdr; size_t in_hdr_len; @@ -154,7 +152,7 @@ static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr) sgs[num_out + num_in++] = vbr->sg_table.sgl; } - sg_init_one(&in_hdr, &vbr->status, vbr->in_hdr_len); + sg_init_one(&in_hdr, &vbr->in_hdr.status, vbr->in_hdr_len); sgs[num_out + num_in++] = &in_hdr; return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC); @@ -242,11 +240,14 @@ static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev, struct request *req, struct virtblk_req *vbr) { - size_t in_hdr_len = sizeof(vbr->status); + size_t in_hdr_len = sizeof(vbr->in_hdr.status); bool unmap = false; u32 type; u64 sector = 0; + if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) && op_is_zone_mgmt(req_op(req))) + return BLK_STS_NOTSUPP; + /* Set fields for all request types */ vbr->out_hdr.ioprio = cpu_to_virtio32(vdev, req_get_ioprio(req)); @@ -287,7 +288,7 @@ static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev, case REQ_OP_ZONE_APPEND: type = VIRTIO_BLK_T_ZONE_APPEND; sector = blk_rq_pos(req); - in_hdr_len = sizeof(vbr->zone_append_in_hdr); + in_hdr_len = sizeof(vbr->in_hdr.zone_append); break; case REQ_OP_ZONE_RESET: type = VIRTIO_BLK_T_ZONE_RESET; @@ -297,7 +298,10 @@ static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev, type = VIRTIO_BLK_T_ZONE_RESET_ALL; break; case REQ_OP_DRV_IN: - /* Out header already filled in, nothing to do */ + /* + * Out header has already been prepared by the caller (virtblk_get_id() + * or virtblk_submit_zone_report()), nothing to do here. + */ return 0; default: WARN_ON_ONCE(1); @@ -318,16 +322,28 @@ static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev, return 0; } +/* + * The status byte is always the last byte of the virtblk request + * in-header. This helper fetches its value for all in-header formats + * that are currently defined. + */ +static inline u8 virtblk_vbr_status(struct virtblk_req *vbr) +{ + return *((u8 *)&vbr->in_hdr + vbr->in_hdr_len - 1); +} + static inline void virtblk_request_done(struct request *req) { struct virtblk_req *vbr = blk_mq_rq_to_pdu(req); - blk_status_t status = virtblk_result(vbr->status); + blk_status_t status = virtblk_result(virtblk_vbr_status(vbr)); + struct virtio_blk *vblk = req->mq_hctx->queue->queuedata; virtblk_unmap_data(req, vbr); virtblk_cleanup_cmd(req); if (req_op(req) == REQ_OP_ZONE_APPEND) - req->__sector = le64_to_cpu(vbr->zone_append_in_hdr.append_sector); + req->__sector = virtio64_to_cpu(vblk->vdev, + vbr->in_hdr.zone_append.sector); blk_mq_end_request(req, status); } @@ -355,7 +371,7 @@ static int virtblk_handle_req(struct virtio_blk_vq *vq, if (likely(!blk_should_fake_timeout(req->q)) && !blk_mq_complete_request_remote(req) && - !blk_mq_add_to_batch(req, iob, vbr->status, + !blk_mq_add_to_batch(req, iob, virtblk_vbr_status(vbr), virtblk_complete_batch)) virtblk_request_done(req); req_done++; @@ -550,7 +566,6 @@ static void virtio_queue_rqs(struct request **rqlist) #ifdef CONFIG_BLK_DEV_ZONED static void *virtblk_alloc_report_buffer(struct virtio_blk *vblk, unsigned int nr_zones, - unsigned int zone_sectors, size_t *buflen) { struct request_queue *q = vblk->disk->queue; @@ -558,7 +573,7 @@ static void *virtblk_alloc_report_buffer(struct virtio_blk *vblk, void *buf; nr_zones = min_t(unsigned int, nr_zones, - get_capacity(vblk->disk) >> ilog2(zone_sectors)); + get_capacity(vblk->disk) >> ilog2(vblk->zone_sectors)); bufsize = sizeof(struct virtio_blk_zone_report) + nr_zones * sizeof(struct virtio_blk_zone_descriptor); @@ -592,7 +607,7 @@ static int virtblk_submit_zone_report(struct virtio_blk *vblk, return PTR_ERR(req); vbr = blk_mq_rq_to_pdu(req); - vbr->in_hdr_len = sizeof(vbr->status); + vbr->in_hdr_len = sizeof(vbr->in_hdr.status); vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_ZONE_REPORT); vbr->out_hdr.sector = cpu_to_virtio64(vblk->vdev, sector); @@ -601,7 +616,7 @@ static int virtblk_submit_zone_report(struct virtio_blk *vblk, goto out; blk_execute_rq(req, false); - err = blk_status_to_errno(virtblk_result(vbr->status)); + err = blk_status_to_errno(virtblk_result(vbr->in_hdr.status)); out: blk_mq_free_request(req); return err; @@ -609,29 +624,72 @@ out: static int virtblk_parse_zone(struct virtio_blk *vblk, struct virtio_blk_zone_descriptor *entry, - unsigned int idx, unsigned int zone_sectors, - report_zones_cb cb, void *data) + unsigned int idx, report_zones_cb cb, void *data) { struct blk_zone zone = { }; - if (entry->z_type != VIRTIO_BLK_ZT_SWR && - entry->z_type != VIRTIO_BLK_ZT_SWP && - entry->z_type != VIRTIO_BLK_ZT_CONV) { - dev_err(&vblk->vdev->dev, "invalid zone type %#x\n", - entry->z_type); - return -EINVAL; + zone.start = virtio64_to_cpu(vblk->vdev, entry->z_start); + if (zone.start + vblk->zone_sectors <= get_capacity(vblk->disk)) + zone.len = vblk->zone_sectors; + else + zone.len = get_capacity(vblk->disk) - zone.start; + zone.capacity = virtio64_to_cpu(vblk->vdev, entry->z_cap); + zone.wp = virtio64_to_cpu(vblk->vdev, entry->z_wp); + + switch (entry->z_type) { + case VIRTIO_BLK_ZT_SWR: + zone.type = BLK_ZONE_TYPE_SEQWRITE_REQ; + break; + case VIRTIO_BLK_ZT_SWP: + zone.type = BLK_ZONE_TYPE_SEQWRITE_PREF; + break; + case VIRTIO_BLK_ZT_CONV: + zone.type = BLK_ZONE_TYPE_CONVENTIONAL; + break; + default: + dev_err(&vblk->vdev->dev, "zone %llu: invalid type %#x\n", + zone.start, entry->z_type); + return -EIO; } - zone.type = entry->z_type; - zone.cond = entry->z_state; - zone.len = zone_sectors; - zone.capacity = le64_to_cpu(entry->z_cap); - zone.start = le64_to_cpu(entry->z_start); - if (zone.cond == BLK_ZONE_COND_FULL) + switch (entry->z_state) { + case VIRTIO_BLK_ZS_EMPTY: + zone.cond = BLK_ZONE_COND_EMPTY; + break; + case VIRTIO_BLK_ZS_CLOSED: + zone.cond = BLK_ZONE_COND_CLOSED; + break; + case VIRTIO_BLK_ZS_FULL: + zone.cond = BLK_ZONE_COND_FULL; zone.wp = zone.start + zone.len; - else - zone.wp = le64_to_cpu(entry->z_wp); + break; + case VIRTIO_BLK_ZS_EOPEN: + zone.cond = BLK_ZONE_COND_EXP_OPEN; + break; + case VIRTIO_BLK_ZS_IOPEN: + zone.cond = BLK_ZONE_COND_IMP_OPEN; + break; + case VIRTIO_BLK_ZS_NOT_WP: + zone.cond = BLK_ZONE_COND_NOT_WP; + break; + case VIRTIO_BLK_ZS_RDONLY: + zone.cond = BLK_ZONE_COND_READONLY; + zone.wp = ULONG_MAX; + break; + case VIRTIO_BLK_ZS_OFFLINE: + zone.cond = BLK_ZONE_COND_OFFLINE; + zone.wp = ULONG_MAX; + break; + default: + dev_err(&vblk->vdev->dev, "zone %llu: invalid condition %#x\n", + zone.start, entry->z_state); + return -EIO; + } + /* + * The callback below checks the validity of the reported + * entry data, no need to further validate it here. + */ return cb(&zone, idx, data); } @@ -641,39 +699,47 @@ static int virtblk_report_zones(struct gendisk *disk, sector_t sector, { struct virtio_blk *vblk = disk->private_data; struct virtio_blk_zone_report *report; - unsigned int zone_sectors = vblk->zone_sectors; - unsigned int nz, i; - int ret, zone_idx = 0; + unsigned long long nz, i; size_t buflen; + unsigned int zone_idx = 0; + int ret; if (WARN_ON_ONCE(!vblk->zone_sectors)) return -EOPNOTSUPP; - report = virtblk_alloc_report_buffer(vblk, nr_zones, - zone_sectors, &buflen); + report = virtblk_alloc_report_buffer(vblk, nr_zones, &buflen); if (!report) return -ENOMEM; + mutex_lock(&vblk->vdev_mutex); + + if (!vblk->vdev) { + ret = -ENXIO; + goto fail_report; + } + while (zone_idx < nr_zones && sector < get_capacity(vblk->disk)) { memset(report, 0, buflen); ret = virtblk_submit_zone_report(vblk, (char *)report, buflen, sector); - if (ret) { - if (ret > 0) - ret = -EIO; - goto out_free; - } - nz = min((unsigned int)le64_to_cpu(report->nr_zones), nr_zones); + if (ret) + goto fail_report; + + nz = min_t(u64, virtio64_to_cpu(vblk->vdev, report->nr_zones), + nr_zones); if (!nz) break; for (i = 0; i < nz && zone_idx < nr_zones; i++) { ret = virtblk_parse_zone(vblk, &report->zones[i], - zone_idx, zone_sectors, cb, data); + zone_idx, cb, data); if (ret) - goto out_free; - sector = le64_to_cpu(report->zones[i].z_start) + zone_sectors; + goto fail_report; + + sector = virtio64_to_cpu(vblk->vdev, + report->zones[i].z_start) + + vblk->zone_sectors; zone_idx++; } } @@ -682,7 +748,8 @@ static int virtblk_report_zones(struct gendisk *disk, sector_t sector, ret = zone_idx; else ret = -EINVAL; -out_free: +fail_report: + mutex_unlock(&vblk->vdev_mutex); kvfree(report); return ret; } @@ -691,20 +758,28 @@ static void virtblk_revalidate_zones(struct virtio_blk *vblk) { u8 model; - if (!vblk->zone_sectors) - return; - virtio_cread(vblk->vdev, struct virtio_blk_config, zoned.model, &model); - if (!blk_revalidate_disk_zones(vblk->disk, NULL)) - set_capacity_and_notify(vblk->disk, 0); + switch (model) { + default: + dev_err(&vblk->vdev->dev, "unknown zone model %d\n", model); + fallthrough; + case VIRTIO_BLK_Z_NONE: + case VIRTIO_BLK_Z_HA: + disk_set_zoned(vblk->disk, BLK_ZONED_NONE); + return; + case VIRTIO_BLK_Z_HM: + WARN_ON_ONCE(!vblk->zone_sectors); + if (!blk_revalidate_disk_zones(vblk->disk, NULL)) + set_capacity_and_notify(vblk->disk, 0); + } } static int virtblk_probe_zoned_device(struct virtio_device *vdev, struct virtio_blk *vblk, struct request_queue *q) { - u32 v; + u32 v, wg; u8 model; int ret; @@ -713,16 +788,11 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev, switch (model) { case VIRTIO_BLK_Z_NONE: + case VIRTIO_BLK_Z_HA: + /* Present the host-aware device as non-zoned */ return 0; case VIRTIO_BLK_Z_HM: break; - case VIRTIO_BLK_Z_HA: - /* - * Present the host-aware device as a regular drive. - * TODO It is possible to add an option to make it appear - * in the system as a zoned drive. - */ - return 0; default: dev_err(&vdev->dev, "unsupported zone model %d\n", model); return -EINVAL; @@ -735,32 +805,31 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev, virtio_cread(vdev, struct virtio_blk_config, zoned.max_open_zones, &v); - disk_set_max_open_zones(vblk->disk, le32_to_cpu(v)); - - dev_dbg(&vdev->dev, "max open zones = %u\n", le32_to_cpu(v)); + disk_set_max_open_zones(vblk->disk, v); + dev_dbg(&vdev->dev, "max open zones = %u\n", v); virtio_cread(vdev, struct virtio_blk_config, zoned.max_active_zones, &v); - disk_set_max_active_zones(vblk->disk, le32_to_cpu(v)); - dev_dbg(&vdev->dev, "max active zones = %u\n", le32_to_cpu(v)); + disk_set_max_active_zones(vblk->disk, v); + dev_dbg(&vdev->dev, "max active zones = %u\n", v); virtio_cread(vdev, struct virtio_blk_config, - zoned.write_granularity, &v); - if (!v) { + zoned.write_granularity, &wg); + if (!wg) { dev_warn(&vdev->dev, "zero write granularity reported\n"); return -ENODEV; } - blk_queue_physical_block_size(q, le32_to_cpu(v)); - blk_queue_io_min(q, le32_to_cpu(v)); + blk_queue_physical_block_size(q, wg); + blk_queue_io_min(q, wg); - dev_dbg(&vdev->dev, "write granularity = %u\n", le32_to_cpu(v)); + dev_dbg(&vdev->dev, "write granularity = %u\n", wg); /* * virtio ZBD specification doesn't require zones to be a power of * two sectors in size, but the code in this driver expects that. */ - virtio_cread(vdev, struct virtio_blk_config, zoned.zone_sectors, &v); - vblk->zone_sectors = le32_to_cpu(v); + virtio_cread(vdev, struct virtio_blk_config, zoned.zone_sectors, + &vblk->zone_sectors); if (vblk->zone_sectors == 0 || !is_power_of_2(vblk->zone_sectors)) { dev_err(&vdev->dev, "zoned device with non power of two zone size %u\n", @@ -783,36 +852,46 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev, dev_warn(&vdev->dev, "zero max_append_sectors reported\n"); return -ENODEV; } - blk_queue_max_zone_append_sectors(q, le32_to_cpu(v)); - dev_dbg(&vdev->dev, "max append sectors = %u\n", le32_to_cpu(v)); + if ((v << SECTOR_SHIFT) < wg) { + dev_err(&vdev->dev, + "write granularity %u exceeds max_append_sectors %u limit\n", + wg, v); + return -ENODEV; + } + + blk_queue_max_zone_append_sectors(q, v); + dev_dbg(&vdev->dev, "max append sectors = %u\n", v); } return ret; } -static inline bool virtblk_has_zoned_feature(struct virtio_device *vdev) -{ - return virtio_has_feature(vdev, VIRTIO_BLK_F_ZONED); -} #else /* * Zoned block device support is not configured in this kernel. - * We only need to define a few symbols to avoid compilation errors. + * Host-managed zoned devices can't be supported, but others are + * good to go as regular block devices. */ #define virtblk_report_zones NULL + static inline void virtblk_revalidate_zones(struct virtio_blk *vblk) { } + static inline int virtblk_probe_zoned_device(struct virtio_device *vdev, struct virtio_blk *vblk, struct request_queue *q) { - return -EOPNOTSUPP; -} + u8 model; -static inline bool virtblk_has_zoned_feature(struct virtio_device *vdev) -{ - return false; + virtio_cread(vdev, struct virtio_blk_config, zoned.model, &model); + if (model == VIRTIO_BLK_Z_HM) { + dev_err(&vdev->dev, + "virtio_blk: zoned devices are not supported"); + return -EOPNOTSUPP; + } + + return 0; } #endif /* CONFIG_BLK_DEV_ZONED */ @@ -831,7 +910,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str) return PTR_ERR(req); vbr = blk_mq_rq_to_pdu(req); - vbr->in_hdr_len = sizeof(vbr->status); + vbr->in_hdr_len = sizeof(vbr->in_hdr.status); vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_GET_ID); vbr->out_hdr.sector = 0; @@ -840,7 +919,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str) goto out; blk_execute_rq(req, false); - err = blk_status_to_errno(virtblk_result(vbr->status)); + err = blk_status_to_errno(virtblk_result(vbr->in_hdr.status)); out: blk_mq_free_request(req); return err; @@ -1498,15 +1577,16 @@ static int virtblk_probe(struct virtio_device *vdev) virtblk_update_capacity(vblk, false); virtio_device_ready(vdev); - if (virtblk_has_zoned_feature(vdev)) { + /* + * All steps that follow use the VQs therefore they need to be + * placed after the virtio_device_ready() call above. + */ + if (virtio_has_feature(vdev, VIRTIO_BLK_F_ZONED)) { err = virtblk_probe_zoned_device(vdev, vblk, q); if (err) goto out_cleanup_disk; } - dev_info(&vdev->dev, "blk config size: %zu\n", - sizeof(struct virtio_blk_config)); - err = device_add_disk(&vdev->dev, vblk->disk, virtblk_attr_groups); if (err) goto out_cleanup_disk; @@ -1607,10 +1687,7 @@ static unsigned int features[] = { VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE, VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES, - VIRTIO_BLK_F_SECURE_ERASE, -#ifdef CONFIG_BLK_DEV_ZONED - VIRTIO_BLK_F_ZONED, -#endif /* CONFIG_BLK_DEV_ZONED */ + VIRTIO_BLK_F_SECURE_ERASE, VIRTIO_BLK_F_ZONED, }; static struct virtio_driver virtio_blk = { diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c index 3006e2a0f37e..43e98a598bd9 100644 --- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -511,7 +511,7 @@ static const char *btbcm_get_board_name(struct device *dev) len = strlen(tmp) + 1; board_type = devm_kzalloc(dev, len, GFP_KERNEL); strscpy(board_type, tmp, len); - for (i = 0; i < board_type[i]; i++) { + for (i = 0; i < len; i++) { if (board_type[i] == '/') board_type[i] = '-'; } diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c index 02893600db39..51000320e1ea 100644 --- a/drivers/bluetooth/btsdio.c +++ b/drivers/bluetooth/btsdio.c @@ -358,6 +358,7 @@ static void btsdio_remove(struct sdio_func *func) if (!data) return; + cancel_work_sync(&data->work); hdev = data->hdev; sdio_set_drvdata(func, NULL); diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c index 36d42484142a..cf463c1d2102 100644 --- a/drivers/bus/imx-weim.c +++ b/drivers/bus/imx-weim.c @@ -329,6 +329,12 @@ static int of_weim_notify(struct notifier_block *nb, unsigned long action, "Failed to setup timing for '%pOF'\n", rd->dn); if (!of_node_check_flag(rd->dn, OF_POPULATED)) { + /* + * Clear the flag before adding the device so that + * fw_devlink doesn't skip adding consumers to this + * device. + */ + rd->dn->fwnode.flags &= ~FWNODE_FLAG_NOT_DEVICE; if (!of_platform_device_create(rd->dn, NULL, &pdev->dev)) { dev_err(&pdev->dev, "Failed to create child device '%pOF'\n", diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c index deed4afadb29..d9cb937665cf 100644 --- a/drivers/counter/104-quad-8.c +++ b/drivers/counter/104-quad-8.c @@ -97,10 +97,6 @@ struct quad8 { struct quad8_reg __iomem *reg; }; -/* Borrow Toggle flip-flop */ -#define QUAD8_FLAG_BT BIT(0) -/* Carry Toggle flip-flop */ -#define QUAD8_FLAG_CT BIT(1) /* Error flag */ #define QUAD8_FLAG_E BIT(4) /* Up/Down flag */ @@ -133,6 +129,9 @@ struct quad8 { #define QUAD8_CMR_QUADRATURE_X2 0x10 #define QUAD8_CMR_QUADRATURE_X4 0x18 +/* Each Counter is 24 bits wide */ +#define LS7267_CNTR_MAX GENMASK(23, 0) + static int quad8_signal_read(struct counter_device *counter, struct counter_signal *signal, enum counter_signal_level *level) @@ -156,18 +155,10 @@ static int quad8_count_read(struct counter_device *counter, { struct quad8 *const priv = counter_priv(counter); struct channel_reg __iomem *const chan = priv->reg->channel + count->id; - unsigned int flags; - unsigned int borrow; - unsigned int carry; unsigned long irqflags; int i; - flags = ioread8(&chan->control); - borrow = flags & QUAD8_FLAG_BT; - carry = !!(flags & QUAD8_FLAG_CT); - - /* Borrow XOR Carry effectively doubles count range */ - *val = (unsigned long)(borrow ^ carry) << 24; + *val = 0; spin_lock_irqsave(&priv->lock, irqflags); @@ -191,8 +182,7 @@ static int quad8_count_write(struct counter_device *counter, unsigned long irqflags; int i; - /* Only 24-bit values are supported */ - if (val > 0xFFFFFF) + if (val > LS7267_CNTR_MAX) return -ERANGE; spin_lock_irqsave(&priv->lock, irqflags); @@ -378,7 +368,7 @@ static int quad8_action_read(struct counter_device *counter, /* Handle Index signals */ if (synapse->signal->id >= 16) { - if (priv->preset_enable[count->id]) + if (!priv->preset_enable[count->id]) *action = COUNTER_SYNAPSE_ACTION_RISING_EDGE; else *action = COUNTER_SYNAPSE_ACTION_NONE; @@ -806,8 +796,7 @@ static int quad8_count_preset_write(struct counter_device *counter, struct quad8 *const priv = counter_priv(counter); unsigned long irqflags; - /* Only 24-bit values are supported */ - if (preset > 0xFFFFFF) + if (preset > LS7267_CNTR_MAX) return -ERANGE; spin_lock_irqsave(&priv->lock, irqflags); @@ -834,8 +823,7 @@ static int quad8_count_ceiling_read(struct counter_device *counter, *ceiling = priv->preset[count->id]; break; default: - /* By default 0x1FFFFFF (25 bits unsigned) is maximum count */ - *ceiling = 0x1FFFFFF; + *ceiling = LS7267_CNTR_MAX; break; } @@ -850,8 +838,7 @@ static int quad8_count_ceiling_write(struct counter_device *counter, struct quad8 *const priv = counter_priv(counter); unsigned long irqflags; - /* Only 24-bit values are supported */ - if (ceiling > 0xFFFFFF) + if (ceiling > LS7267_CNTR_MAX) return -ERANGE; spin_lock_irqsave(&priv->lock, irqflags); diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index 45deda18ed32..02cc2c38b44b 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -101,25 +101,40 @@ static int map_hdm_decoder_regs(struct cxl_port *port, void __iomem *crb, BIT(CXL_CM_CAP_CAP_ID_HDM)); } -static struct cxl_hdm *devm_cxl_setup_emulated_hdm(struct cxl_port *port, - struct cxl_endpoint_dvsec_info *info) +static bool should_emulate_decoders(struct cxl_endpoint_dvsec_info *info) { - struct device *dev = &port->dev; struct cxl_hdm *cxlhdm; + void __iomem *hdm; + u32 ctrl; + int i; + if (!info) + return false; + + cxlhdm = dev_get_drvdata(&info->port->dev); + hdm = cxlhdm->regs.hdm_decoder; + + if (!hdm) + return true; + + /* + * If HDM decoders are present and the driver is in control of + * Mem_Enable skip DVSEC based emulation + */ if (!info->mem_enabled) - return ERR_PTR(-ENODEV); + return false; - cxlhdm = devm_kzalloc(dev, sizeof(*cxlhdm), GFP_KERNEL); - if (!cxlhdm) - return ERR_PTR(-ENOMEM); + /* + * If any decoders are committed already, there should not be any + * emulated DVSEC decoders. + */ + for (i = 0; i < cxlhdm->decoder_count; i++) { + ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(i)); + if (FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl)) + return false; + } - cxlhdm->port = port; - cxlhdm->decoder_count = info->ranges; - cxlhdm->target_count = info->ranges; - dev_set_drvdata(&port->dev, cxlhdm); - - return cxlhdm; + return true; } /** @@ -138,13 +153,14 @@ struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, cxlhdm = devm_kzalloc(dev, sizeof(*cxlhdm), GFP_KERNEL); if (!cxlhdm) return ERR_PTR(-ENOMEM); - cxlhdm->port = port; - crb = ioremap(port->component_reg_phys, CXL_COMPONENT_REG_BLOCK_SIZE); - if (!crb) { - if (info && info->mem_enabled) - return devm_cxl_setup_emulated_hdm(port, info); + dev_set_drvdata(dev, cxlhdm); + crb = ioremap(port->component_reg_phys, CXL_COMPONENT_REG_BLOCK_SIZE); + if (!crb && info && info->mem_enabled) { + cxlhdm->decoder_count = info->ranges; + return cxlhdm; + } else if (!crb) { dev_err(dev, "No component registers mapped\n"); return ERR_PTR(-ENXIO); } @@ -160,7 +176,15 @@ struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, return ERR_PTR(-ENXIO); } - dev_set_drvdata(dev, cxlhdm); + /* + * Now that the hdm capability is parsed, decide if range + * register emulation is needed and fixup cxlhdm accordingly. + */ + if (should_emulate_decoders(info)) { + dev_dbg(dev, "Fallback map %d range register%s\n", info->ranges, + info->ranges > 1 ? "s" : ""); + cxlhdm->decoder_count = info->ranges; + } return cxlhdm; } @@ -714,14 +738,20 @@ static int cxl_decoder_reset(struct cxl_decoder *cxld) return 0; } -static int cxl_setup_hdm_decoder_from_dvsec(struct cxl_port *port, - struct cxl_decoder *cxld, int which, - struct cxl_endpoint_dvsec_info *info) +static int cxl_setup_hdm_decoder_from_dvsec( + struct cxl_port *port, struct cxl_decoder *cxld, u64 *dpa_base, + int which, struct cxl_endpoint_dvsec_info *info) { + struct cxl_endpoint_decoder *cxled; + u64 len; + int rc; + if (!is_cxl_endpoint(port)) return -EOPNOTSUPP; - if (!range_len(&info->dvsec_range[which])) + cxled = to_cxl_endpoint_decoder(&cxld->dev); + len = range_len(&info->dvsec_range[which]); + if (!len) return -ENOENT; cxld->target_type = CXL_DECODER_EXPANDER; @@ -736,40 +766,24 @@ static int cxl_setup_hdm_decoder_from_dvsec(struct cxl_port *port, cxld->flags |= CXL_DECODER_F_ENABLE | CXL_DECODER_F_LOCK; port->commit_end = cxld->id; - return 0; -} - -static bool should_emulate_decoders(struct cxl_port *port) -{ - struct cxl_hdm *cxlhdm = dev_get_drvdata(&port->dev); - void __iomem *hdm = cxlhdm->regs.hdm_decoder; - u32 ctrl; - int i; - - if (!is_cxl_endpoint(cxlhdm->port)) - return false; - - if (!hdm) - return true; - - /* - * If any decoders are committed already, there should not be any - * emulated DVSEC decoders. - */ - for (i = 0; i < cxlhdm->decoder_count; i++) { - ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(i)); - if (FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl)) - return false; + rc = devm_cxl_dpa_reserve(cxled, *dpa_base, len, 0); + if (rc) { + dev_err(&port->dev, + "decoder%d.%d: Failed to reserve DPA range %#llx - %#llx\n (%d)", + port->id, cxld->id, *dpa_base, *dpa_base + len - 1, rc); + return rc; } + *dpa_base += len; + cxled->state = CXL_DECODER_STATE_AUTO; - return true; + return 0; } static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, int *target_map, void __iomem *hdm, int which, u64 *dpa_base, struct cxl_endpoint_dvsec_info *info) { - struct cxl_endpoint_decoder *cxled = NULL; + struct cxl_endpoint_decoder *cxled; u64 size, base, skip, dpa_size; bool committed; u32 remainder; @@ -780,11 +794,9 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, unsigned char target_id[8]; } target_list; - if (should_emulate_decoders(port)) - return cxl_setup_hdm_decoder_from_dvsec(port, cxld, which, info); - - if (is_endpoint_decoder(&cxld->dev)) - cxled = to_cxl_endpoint_decoder(&cxld->dev); + if (should_emulate_decoders(info)) + return cxl_setup_hdm_decoder_from_dvsec(port, cxld, dpa_base, + which, info); ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(which)); base = ioread64_hi_lo(hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(which)); @@ -806,9 +818,6 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, .end = base + size - 1, }; - if (cxled && !committed && range_len(&info->dvsec_range[which])) - return cxl_setup_hdm_decoder_from_dvsec(port, cxld, which, info); - /* decoders are enabled if committed */ if (committed) { cxld->flags |= CXL_DECODER_F_ENABLE; @@ -846,7 +855,7 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, if (rc) return rc; - if (!cxled) { + if (!info) { target_list.value = ioread64_hi_lo(hdm + CXL_HDM_DECODER0_TL_LOW(which)); for (i = 0; i < cxld->interleave_ways; i++) @@ -866,6 +875,7 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, return -ENXIO; } skip = ioread64_hi_lo(hdm + CXL_HDM_DECODER0_SKIP_LOW(which)); + cxled = to_cxl_endpoint_decoder(&cxld->dev); rc = devm_cxl_dpa_reserve(cxled, *dpa_base + skip, dpa_size, skip); if (rc) { dev_err(&port->dev, diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 7328a2552411..523d5b9fd7fc 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -462,7 +462,7 @@ static struct pci_doe_mb *find_cdat_doe(struct device *uport) return NULL; } -#define CDAT_DOE_REQ(entry_handle) \ +#define CDAT_DOE_REQ(entry_handle) cpu_to_le32 \ (FIELD_PREP(CXL_DOE_TABLE_ACCESS_REQ_CODE, \ CXL_DOE_TABLE_ACCESS_REQ_CODE_READ) | \ FIELD_PREP(CXL_DOE_TABLE_ACCESS_TABLE_TYPE, \ @@ -475,8 +475,8 @@ static void cxl_doe_task_complete(struct pci_doe_task *task) } struct cdat_doe_task { - u32 request_pl; - u32 response_pl[32]; + __le32 request_pl; + __le32 response_pl[32]; struct completion c; struct pci_doe_task task; }; @@ -510,10 +510,10 @@ static int cxl_cdat_get_length(struct device *dev, return rc; } wait_for_completion(&t.c); - if (t.task.rv < sizeof(u32)) + if (t.task.rv < 2 * sizeof(__le32)) return -EIO; - *length = t.response_pl[1]; + *length = le32_to_cpu(t.response_pl[1]); dev_dbg(dev, "CDAT length %zu\n", *length); return 0; @@ -524,13 +524,13 @@ static int cxl_cdat_read_table(struct device *dev, struct cxl_cdat *cdat) { size_t length = cdat->length; - u32 *data = cdat->table; + __le32 *data = cdat->table; int entry_handle = 0; do { DECLARE_CDAT_DOE_TASK(CDAT_DOE_REQ(entry_handle), t); + struct cdat_entry_header *entry; size_t entry_dw; - u32 *entry; int rc; rc = pci_doe_submit_task(cdat_doe, &t.task); @@ -539,26 +539,34 @@ static int cxl_cdat_read_table(struct device *dev, return rc; } wait_for_completion(&t.c); - /* 1 DW header + 1 DW data min */ - if (t.task.rv < (2 * sizeof(u32))) + + /* 1 DW Table Access Response Header + CDAT entry */ + entry = (struct cdat_entry_header *)(t.response_pl + 1); + if ((entry_handle == 0 && + t.task.rv != sizeof(__le32) + sizeof(struct cdat_header)) || + (entry_handle > 0 && + (t.task.rv < sizeof(__le32) + sizeof(*entry) || + t.task.rv != sizeof(__le32) + le16_to_cpu(entry->length)))) return -EIO; /* Get the CXL table access header entry handle */ entry_handle = FIELD_GET(CXL_DOE_TABLE_ACCESS_ENTRY_HANDLE, - t.response_pl[0]); - entry = t.response_pl + 1; - entry_dw = t.task.rv / sizeof(u32); + le32_to_cpu(t.response_pl[0])); + entry_dw = t.task.rv / sizeof(__le32); /* Skip Header */ entry_dw -= 1; - entry_dw = min(length / sizeof(u32), entry_dw); + entry_dw = min(length / sizeof(__le32), entry_dw); /* Prevent length < 1 DW from causing a buffer overflow */ if (entry_dw) { - memcpy(data, entry, entry_dw * sizeof(u32)); - length -= entry_dw * sizeof(u32); + memcpy(data, entry, entry_dw * sizeof(__le32)); + length -= entry_dw * sizeof(__le32); data += entry_dw; } } while (entry_handle != CXL_DOE_TABLE_ACCESS_LAST_ENTRY); + /* Length in CDAT header may exceed concatenation of CDAT entries */ + cdat->length -= length; + return 0; } diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c index c2e4b1093788..f8c38d997252 100644 --- a/drivers/cxl/core/pmem.c +++ b/drivers/cxl/core/pmem.c @@ -62,9 +62,9 @@ static int match_nvdimm_bridge(struct device *dev, void *data) return is_cxl_nvdimm_bridge(dev); } -struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct device *start) +struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_memdev *cxlmd) { - struct cxl_port *port = find_cxl_root(start); + struct cxl_port *port = find_cxl_root(dev_get_drvdata(&cxlmd->dev)); struct device *dev; if (!port) @@ -253,7 +253,7 @@ int devm_cxl_add_nvdimm(struct cxl_memdev *cxlmd) struct device *dev; int rc; - cxl_nvb = cxl_find_nvdimm_bridge(&cxlmd->dev); + cxl_nvb = cxl_find_nvdimm_bridge(cxlmd); if (!cxl_nvb) return -ENODEV; diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 8ee6b6e2e2a4..4d1f9c5b5029 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -823,41 +823,17 @@ static bool dev_is_cxl_root_child(struct device *dev) return false; } -/* Find a 2nd level CXL port that has a dport that is an ancestor of @match */ -static int match_root_child(struct device *dev, const void *match) +struct cxl_port *find_cxl_root(struct cxl_port *port) { - const struct device *iter = NULL; - struct cxl_dport *dport; - struct cxl_port *port; + struct cxl_port *iter = port; - if (!dev_is_cxl_root_child(dev)) - return 0; + while (iter && !is_cxl_root(iter)) + iter = to_cxl_port(iter->dev.parent); - port = to_cxl_port(dev); - iter = match; - while (iter) { - dport = cxl_find_dport_by_dev(port, iter); - if (dport) - break; - iter = iter->parent; - } - - return !!iter; -} - -struct cxl_port *find_cxl_root(struct device *dev) -{ - struct device *port_dev; - struct cxl_port *root; - - port_dev = bus_find_device(&cxl_bus_type, NULL, dev, match_root_child); - if (!port_dev) + if (!iter) return NULL; - - root = to_cxl_port(port_dev->parent); - get_device(&root->dev); - put_device(port_dev); - return root; + get_device(&iter->dev); + return iter; } EXPORT_SYMBOL_NS_GPL(find_cxl_root, CXL); diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index f29028148806..b2fd67fcebfb 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -134,9 +134,13 @@ static int cxl_region_decode_reset(struct cxl_region *cxlr, int count) struct cxl_endpoint_decoder *cxled = p->targets[i]; struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); struct cxl_port *iter = cxled_to_port(cxled); + struct cxl_dev_state *cxlds = cxlmd->cxlds; struct cxl_ep *ep; int rc = 0; + if (cxlds->rcd) + goto endpoint_reset; + while (!is_cxl_root(to_cxl_port(iter->dev.parent))) iter = to_cxl_port(iter->dev.parent); @@ -153,6 +157,7 @@ static int cxl_region_decode_reset(struct cxl_region *cxlr, int count) return rc; } +endpoint_reset: rc = cxled->cxld.reset(&cxled->cxld); if (rc) return rc; @@ -1199,6 +1204,7 @@ static void cxl_region_teardown_targets(struct cxl_region *cxlr) { struct cxl_region_params *p = &cxlr->params; struct cxl_endpoint_decoder *cxled; + struct cxl_dev_state *cxlds; struct cxl_memdev *cxlmd; struct cxl_port *iter; struct cxl_ep *ep; @@ -1214,6 +1220,10 @@ static void cxl_region_teardown_targets(struct cxl_region *cxlr) for (i = 0; i < p->nr_targets; i++) { cxled = p->targets[i]; cxlmd = cxled_to_memdev(cxled); + cxlds = cxlmd->cxlds; + + if (cxlds->rcd) + continue; iter = cxled_to_port(cxled); while (!is_cxl_root(to_cxl_port(iter->dev.parent))) @@ -1229,14 +1239,24 @@ static int cxl_region_setup_targets(struct cxl_region *cxlr) { struct cxl_region_params *p = &cxlr->params; struct cxl_endpoint_decoder *cxled; + struct cxl_dev_state *cxlds; + int i, rc, rch = 0, vh = 0; struct cxl_memdev *cxlmd; struct cxl_port *iter; struct cxl_ep *ep; - int i, rc; for (i = 0; i < p->nr_targets; i++) { cxled = p->targets[i]; cxlmd = cxled_to_memdev(cxled); + cxlds = cxlmd->cxlds; + + /* validate that all targets agree on topology */ + if (!cxlds->rcd) { + vh++; + } else { + rch++; + continue; + } iter = cxled_to_port(cxled); while (!is_cxl_root(to_cxl_port(iter->dev.parent))) @@ -1256,6 +1276,12 @@ static int cxl_region_setup_targets(struct cxl_region *cxlr) } } + if (rch && vh) { + dev_err(&cxlr->dev, "mismatched CXL topologies detected\n"); + cxl_region_teardown_targets(cxlr); + return -ENXIO; + } + return 0; } @@ -1648,6 +1674,7 @@ static int cxl_region_attach(struct cxl_region *cxlr, if (rc) goto err_decrement; p->state = CXL_CONFIG_ACTIVE; + set_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags); } cxled->cxld.interleave_ways = p->interleave_ways; @@ -1749,8 +1776,6 @@ static int attach_target(struct cxl_region *cxlr, down_read(&cxl_dpa_rwsem); rc = cxl_region_attach(cxlr, cxled, pos); - if (rc == 0) - set_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags); up_read(&cxl_dpa_rwsem); up_write(&cxl_region_rwsem); return rc; @@ -2251,7 +2276,7 @@ static struct cxl_pmem_region *cxl_pmem_region_alloc(struct cxl_region *cxlr) * bridge for one device is the same for all. */ if (i == 0) { - cxl_nvb = cxl_find_nvdimm_bridge(&cxlmd->dev); + cxl_nvb = cxl_find_nvdimm_bridge(cxlmd); if (!cxl_nvb) { cxlr_pmem = ERR_PTR(-ENODEV); goto out; diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index f2b0962a552d..044a92d9813e 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -658,7 +658,7 @@ struct pci_bus *cxl_port_to_pci_bus(struct cxl_port *port); struct cxl_port *devm_cxl_add_port(struct device *host, struct device *uport, resource_size_t component_reg_phys, struct cxl_dport *parent_dport); -struct cxl_port *find_cxl_root(struct device *dev); +struct cxl_port *find_cxl_root(struct cxl_port *port); int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd); void cxl_bus_rescan(void); void cxl_bus_drain(void); @@ -695,13 +695,15 @@ int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint) /** * struct cxl_endpoint_dvsec_info - Cached DVSEC info - * @mem_enabled: cached value of mem_enabled in the DVSEC, PCIE_DEVICE + * @mem_enabled: cached value of mem_enabled in the DVSEC at init time * @ranges: Number of active HDM ranges this device uses. + * @port: endpoint port associated with this info instance * @dvsec_range: cached attributes of the ranges in the DVSEC, PCIE_DEVICE */ struct cxl_endpoint_dvsec_info { bool mem_enabled; int ranges; + struct cxl_port *port; struct range dvsec_range[2]; }; @@ -758,7 +760,7 @@ struct cxl_nvdimm *to_cxl_nvdimm(struct device *dev); bool is_cxl_nvdimm(struct device *dev); bool is_cxl_nvdimm_bridge(struct device *dev); int devm_cxl_add_nvdimm(struct cxl_memdev *cxlmd); -struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct device *dev); +struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_memdev *cxlmd); #ifdef CONFIG_CXL_REGION bool is_cxl_pmem_region(struct device *dev); diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h index be6a2ef3cce3..0465ef963cd6 100644 --- a/drivers/cxl/cxlpci.h +++ b/drivers/cxl/cxlpci.h @@ -68,6 +68,20 @@ enum cxl_regloc_type { CXL_REGLOC_RBI_TYPES }; +struct cdat_header { + __le32 length; + u8 revision; + u8 checksum; + u8 reserved[6]; + __le32 sequence; +} __packed; + +struct cdat_entry_header { + u8 type; + u8 reserved; + __le16 length; +} __packed; + int devm_cxl_port_enumerate_dports(struct cxl_port *port); struct cxl_dev_state; int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm, diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c index 1049bb5ea496..22a7ab2bae7c 100644 --- a/drivers/cxl/port.c +++ b/drivers/cxl/port.c @@ -78,8 +78,8 @@ static int cxl_switch_port_probe(struct cxl_port *port) static int cxl_endpoint_port_probe(struct cxl_port *port) { + struct cxl_endpoint_dvsec_info info = { .port = port }; struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport); - struct cxl_endpoint_dvsec_info info = { 0 }; struct cxl_dev_state *cxlds = cxlmd->cxlds; struct cxl_hdm *cxlhdm; struct cxl_port *root; @@ -119,7 +119,7 @@ static int cxl_endpoint_port_probe(struct cxl_port *port) * This can't fail in practice as CXL root exit unregisters all * descendant ports and that in turn synchronizes with cxl_port_probe() */ - root = find_cxl_root(&cxlmd->dev); + root = find_cxl_root(port); /* * Now that all endpoint decoders are successfully enumerated, try to diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c index 90f28bda29c8..4cf8da77bdd9 100644 --- a/drivers/dma/apple-admac.c +++ b/drivers/dma/apple-admac.c @@ -75,6 +75,7 @@ #define REG_TX_INTSTATE(idx) (0x0030 + (idx) * 4) #define REG_RX_INTSTATE(idx) (0x0040 + (idx) * 4) +#define REG_GLOBAL_INTSTATE(idx) (0x0050 + (idx) * 4) #define REG_CHAN_INTSTATUS(ch, idx) (0x8010 + (ch) * 0x200 + (idx) * 4) #define REG_CHAN_INTMASK(ch, idx) (0x8020 + (ch) * 0x200 + (idx) * 4) @@ -511,7 +512,10 @@ static int admac_terminate_all(struct dma_chan *chan) admac_stop_chan(adchan); admac_reset_rings(adchan); - adchan->current_tx = NULL; + if (adchan->current_tx) { + list_add_tail(&adchan->current_tx->node, &adchan->to_free); + adchan->current_tx = NULL; + } /* * Descriptors can only be freed after the tasklet * has been killed (in admac_synchronize). @@ -672,13 +676,14 @@ static void admac_handle_chan_int(struct admac_data *ad, int no) static irqreturn_t admac_interrupt(int irq, void *devid) { struct admac_data *ad = devid; - u32 rx_intstate, tx_intstate; + u32 rx_intstate, tx_intstate, global_intstate; int i; rx_intstate = readl_relaxed(ad->base + REG_RX_INTSTATE(ad->irq_index)); tx_intstate = readl_relaxed(ad->base + REG_TX_INTSTATE(ad->irq_index)); + global_intstate = readl_relaxed(ad->base + REG_GLOBAL_INTSTATE(ad->irq_index)); - if (!tx_intstate && !rx_intstate) + if (!tx_intstate && !rx_intstate && !global_intstate) return IRQ_NONE; for (i = 0; i < ad->nchannels; i += 2) { @@ -693,6 +698,12 @@ static irqreturn_t admac_interrupt(int irq, void *devid) rx_intstate >>= 1; } + if (global_intstate) { + dev_warn(ad->dev, "clearing unknown global interrupt flag: %x\n", + global_intstate); + writel_relaxed(~(u32) 0, ad->base + REG_GLOBAL_INTSTATE(ad->irq_index)); + } + return IRQ_HANDLED; } @@ -850,6 +861,9 @@ static int admac_probe(struct platform_device *pdev) dma->directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM); dma->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST; + dma->src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | + BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | + BIT(DMA_SLAVE_BUSWIDTH_4_BYTES); dma->dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | BIT(DMA_SLAVE_BUSWIDTH_4_BYTES); diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index c24bca210104..826b98284fa1 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -1342,7 +1342,7 @@ int dmaenginem_async_device_register(struct dma_device *device) if (ret) return ret; - return devm_add_action(device->dev, dmaenginem_async_device_unregister, device); + return devm_add_action_or_reset(device->dev, dmaenginem_async_device_unregister, device); } EXPORT_SYMBOL(dmaenginem_async_device_register); diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c index 462109c61653..93ee298d52b8 100644 --- a/drivers/dma/xilinx/xdma.c +++ b/drivers/dma/xilinx/xdma.c @@ -277,7 +277,7 @@ failed: /** * xdma_xfer_start - Start DMA transfer - * @xdma_chan: DMA channel pointer + * @xchan: DMA channel pointer */ static int xdma_xfer_start(struct xdma_chan *xchan) { diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 13be729710f2..badbe0582318 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -100,7 +100,7 @@ config GPIO_GENERIC tristate config GPIO_REGMAP - depends on REGMAP + select REGMAP tristate # put drivers in the right section, in alphabetical order diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index 26b1f7465e09..43b2dc8821e6 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -324,7 +324,7 @@ static struct irq_chip gpio_irqchip = { .irq_enable = gpio_irq_enable, .irq_disable = gpio_irq_disable, .irq_set_type = gpio_irq_type, - .flags = IRQCHIP_SET_TYPE_MASKED, + .flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_SKIP_SET_WAKE, }; static void gpio_irq_handler(struct irq_desc *desc) @@ -641,9 +641,6 @@ static void davinci_gpio_save_context(struct davinci_gpio_controller *chips, context->set_falling = readl_relaxed(&g->set_falling); } - /* Clear Bank interrupt enable bit */ - writel_relaxed(0, base + BINTEN); - /* Clear all interrupt status registers */ writel_relaxed(GENMASK(31, 0), &g->intstat); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 1583157da355..efd025d8961e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -177,6 +177,40 @@ void dm_helpers_dp_update_branch_info( const struct dc_link *link) {} +static void dm_helpers_construct_old_payload( + struct dc_link *link, + int pbn_per_slot, + struct drm_dp_mst_atomic_payload *new_payload, + struct drm_dp_mst_atomic_payload *old_payload) +{ + struct link_mst_stream_allocation_table current_link_table = + link->mst_stream_alloc_table; + struct link_mst_stream_allocation *dc_alloc; + int i; + + *old_payload = *new_payload; + + /* Set correct time_slots/PBN of old payload. + * other fields (delete & dsc_enabled) in + * struct drm_dp_mst_atomic_payload are don't care fields + * while calling drm_dp_remove_payload() + */ + for (i = 0; i < current_link_table.stream_count; i++) { + dc_alloc = + ¤t_link_table.stream_allocations[i]; + + if (dc_alloc->vcp_id == new_payload->vcpi) { + old_payload->time_slots = dc_alloc->slot_count; + old_payload->pbn = dc_alloc->slot_count * pbn_per_slot; + break; + } + } + + /* make sure there is an old payload*/ + ASSERT(i != current_link_table.stream_count); + +} + /* * Writes payload allocation table in immediate downstream device. */ @@ -188,7 +222,7 @@ bool dm_helpers_dp_mst_write_payload_allocation_table( { struct amdgpu_dm_connector *aconnector; struct drm_dp_mst_topology_state *mst_state; - struct drm_dp_mst_atomic_payload *payload; + struct drm_dp_mst_atomic_payload *target_payload, *new_payload, old_payload; struct drm_dp_mst_topology_mgr *mst_mgr; aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; @@ -204,17 +238,26 @@ bool dm_helpers_dp_mst_write_payload_allocation_table( mst_state = to_drm_dp_mst_topology_state(mst_mgr->base.state); /* It's OK for this to fail */ - payload = drm_atomic_get_mst_payload_state(mst_state, aconnector->mst_output_port); - if (enable) - drm_dp_add_payload_part1(mst_mgr, mst_state, payload); - else - drm_dp_remove_payload(mst_mgr, mst_state, payload, payload); + new_payload = drm_atomic_get_mst_payload_state(mst_state, aconnector->mst_output_port); + + if (enable) { + target_payload = new_payload; + + drm_dp_add_payload_part1(mst_mgr, mst_state, new_payload); + } else { + /* construct old payload by VCPI*/ + dm_helpers_construct_old_payload(stream->link, mst_state->pbn_div, + new_payload, &old_payload); + target_payload = &old_payload; + + drm_dp_remove_payload(mst_mgr, mst_state, &old_payload, new_payload); + } /* mst_mgr->->payloads are VC payload notify MST branch using DPCD or * AUX message. The sequence is slot 1-63 allocated sequence for each * stream. AMD ASIC stream slot allocation should follow the same * sequence. copy DRM MST allocation to dc */ - fill_dc_mst_payload_table_from_drm(stream->link, enable, payload, proposed_table); + fill_dc_mst_payload_table_from_drm(stream->link, enable, target_payload, proposed_table); return true; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index f085cb97a620..85a090b9e3d9 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -61,6 +61,12 @@ #define CTF_OFFSET_HOTSPOT 5 #define CTF_OFFSET_MEM 5 +static const int pmfw_decoded_link_speed[5] = {1, 2, 3, 4, 5}; +static const int pmfw_decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16}; + +#define DECODE_GEN_SPEED(gen_speed_idx) (pmfw_decoded_link_speed[gen_speed_idx]) +#define DECODE_LANE_WIDTH(lane_width_idx) (pmfw_decoded_link_width[lane_width_idx]) + struct smu_13_0_max_sustainable_clocks { uint32_t display_clock; uint32_t phy_clock; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 27448ffe60a4..a5c97d61e92a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -1144,8 +1144,8 @@ static int smu_v13_0_0_print_clk_levels(struct smu_context *smu, (pcie_table->pcie_lane[i] == 5) ? "x12" : (pcie_table->pcie_lane[i] == 6) ? "x16" : "", pcie_table->clk_freq[i], - ((gen_speed - 1) == pcie_table->pcie_gen[i]) && - (lane_width == link_width[pcie_table->pcie_lane[i]]) ? + (gen_speed == DECODE_GEN_SPEED(pcie_table->pcie_gen[i])) && + (lane_width == DECODE_LANE_WIDTH(link_width[pcie_table->pcie_lane[i]])) ? "*" : ""); break; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 9e1967d8049e..4399416dd9b8 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -575,6 +575,14 @@ static int smu_v13_0_7_set_default_dpm_table(struct smu_context *smu) dpm_table); if (ret) return ret; + + if (skutable->DriverReportedClocks.GameClockAc && + (dpm_table->dpm_levels[dpm_table->count - 1].value > + skutable->DriverReportedClocks.GameClockAc)) { + dpm_table->dpm_levels[dpm_table->count - 1].value = + skutable->DriverReportedClocks.GameClockAc; + dpm_table->max = skutable->DriverReportedClocks.GameClockAc; + } } else { dpm_table->count = 1; dpm_table->dpm_levels[0].value = smu->smu_table.boot_values.gfxclk / 100; @@ -828,6 +836,57 @@ static int smu_v13_0_7_get_smu_metrics_data(struct smu_context *smu, return ret; } +static int smu_v13_0_7_get_dpm_ultimate_freq(struct smu_context *smu, + enum smu_clk_type clk_type, + uint32_t *min, + uint32_t *max) +{ + struct smu_13_0_dpm_context *dpm_context = + smu->smu_dpm.dpm_context; + struct smu_13_0_dpm_table *dpm_table; + + switch (clk_type) { + case SMU_MCLK: + case SMU_UCLK: + /* uclk dpm table */ + dpm_table = &dpm_context->dpm_tables.uclk_table; + break; + case SMU_GFXCLK: + case SMU_SCLK: + /* gfxclk dpm table */ + dpm_table = &dpm_context->dpm_tables.gfx_table; + break; + case SMU_SOCCLK: + /* socclk dpm table */ + dpm_table = &dpm_context->dpm_tables.soc_table; + break; + case SMU_FCLK: + /* fclk dpm table */ + dpm_table = &dpm_context->dpm_tables.fclk_table; + break; + case SMU_VCLK: + case SMU_VCLK1: + /* vclk dpm table */ + dpm_table = &dpm_context->dpm_tables.vclk_table; + break; + case SMU_DCLK: + case SMU_DCLK1: + /* dclk dpm table */ + dpm_table = &dpm_context->dpm_tables.dclk_table; + break; + default: + dev_err(smu->adev->dev, "Unsupported clock type!\n"); + return -EINVAL; + } + + if (min) + *min = dpm_table->min; + if (max) + *max = dpm_table->max; + + return 0; +} + static int smu_v13_0_7_read_sensor(struct smu_context *smu, enum amd_pp_sensors sensor, void *data, @@ -1074,8 +1133,8 @@ static int smu_v13_0_7_print_clk_levels(struct smu_context *smu, (pcie_table->pcie_lane[i] == 5) ? "x12" : (pcie_table->pcie_lane[i] == 6) ? "x16" : "", pcie_table->clk_freq[i], - (gen_speed == pcie_table->pcie_gen[i]) && - (lane_width == pcie_table->pcie_lane[i]) ? + (gen_speed == DECODE_GEN_SPEED(pcie_table->pcie_gen[i])) && + (lane_width == DECODE_LANE_WIDTH(pcie_table->pcie_lane[i])) ? "*" : ""); break; @@ -1329,9 +1388,17 @@ static int smu_v13_0_7_populate_umd_state_clk(struct smu_context *smu) &dpm_context->dpm_tables.fclk_table; struct smu_umd_pstate_table *pstate_table = &smu->pstate_table; + struct smu_table_context *table_context = &smu->smu_table; + PPTable_t *pptable = table_context->driver_pptable; + DriverReportedClocks_t driver_clocks = + pptable->SkuTable.DriverReportedClocks; pstate_table->gfxclk_pstate.min = gfx_table->min; - pstate_table->gfxclk_pstate.peak = gfx_table->max; + if (driver_clocks.GameClockAc && + (driver_clocks.GameClockAc < gfx_table->max)) + pstate_table->gfxclk_pstate.peak = driver_clocks.GameClockAc; + else + pstate_table->gfxclk_pstate.peak = gfx_table->max; pstate_table->uclk_pstate.min = mem_table->min; pstate_table->uclk_pstate.peak = mem_table->max; @@ -1348,12 +1415,12 @@ static int smu_v13_0_7_populate_umd_state_clk(struct smu_context *smu) pstate_table->fclk_pstate.min = fclk_table->min; pstate_table->fclk_pstate.peak = fclk_table->max; - /* - * For now, just use the mininum clock frequency. - * TODO: update them when the real pstate settings available - */ - pstate_table->gfxclk_pstate.standard = gfx_table->min; - pstate_table->uclk_pstate.standard = mem_table->min; + if (driver_clocks.BaseClockAc && + driver_clocks.BaseClockAc < gfx_table->max) + pstate_table->gfxclk_pstate.standard = driver_clocks.BaseClockAc; + else + pstate_table->gfxclk_pstate.standard = gfx_table->max; + pstate_table->uclk_pstate.standard = mem_table->max; pstate_table->socclk_pstate.standard = soc_table->min; pstate_table->vclk_pstate.standard = vclk_table->min; pstate_table->dclk_pstate.standard = dclk_table->min; @@ -1676,7 +1743,7 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = { .dpm_set_jpeg_enable = smu_v13_0_set_jpeg_enable, .init_pptable_microcode = smu_v13_0_init_pptable_microcode, .populate_umd_state_clk = smu_v13_0_7_populate_umd_state_clk, - .get_dpm_ultimate_freq = smu_v13_0_get_dpm_ultimate_freq, + .get_dpm_ultimate_freq = smu_v13_0_7_get_dpm_ultimate_freq, .get_vbios_bootup_values = smu_v13_0_get_vbios_bootup_values, .read_sensor = smu_v13_0_7_read_sensor, .feature_is_enabled = smu_cmn_feature_is_enabled, diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index 0643887800b4..142668cd6d7c 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -99,7 +99,6 @@ static int armada_drm_bind(struct device *dev) if (ret) { dev_err(dev, "[" DRM_NAME ":%s] can't kick out simple-fb: %d\n", __func__, ret); - kfree(priv); return ret; } diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index 468a792e6a40..fc0eaf40dc94 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -300,9 +300,21 @@ static void configure_dual_link_mode(struct intel_encoder *encoder, { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); + i915_reg_t dss_ctl1_reg, dss_ctl2_reg; u32 dss_ctl1; - dss_ctl1 = intel_de_read(dev_priv, DSS_CTL1); + /* FIXME: Move all DSS handling to intel_vdsc.c */ + if (DISPLAY_VER(dev_priv) >= 12) { + struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc); + + dss_ctl1_reg = ICL_PIPE_DSS_CTL1(crtc->pipe); + dss_ctl2_reg = ICL_PIPE_DSS_CTL2(crtc->pipe); + } else { + dss_ctl1_reg = DSS_CTL1; + dss_ctl2_reg = DSS_CTL2; + } + + dss_ctl1 = intel_de_read(dev_priv, dss_ctl1_reg); dss_ctl1 |= SPLITTER_ENABLE; dss_ctl1 &= ~OVERLAP_PIXELS_MASK; dss_ctl1 |= OVERLAP_PIXELS(intel_dsi->pixel_overlap); @@ -323,16 +335,16 @@ static void configure_dual_link_mode(struct intel_encoder *encoder, dss_ctl1 &= ~LEFT_DL_BUF_TARGET_DEPTH_MASK; dss_ctl1 |= LEFT_DL_BUF_TARGET_DEPTH(dl_buffer_depth); - dss_ctl2 = intel_de_read(dev_priv, DSS_CTL2); + dss_ctl2 = intel_de_read(dev_priv, dss_ctl2_reg); dss_ctl2 &= ~RIGHT_DL_BUF_TARGET_DEPTH_MASK; dss_ctl2 |= RIGHT_DL_BUF_TARGET_DEPTH(dl_buffer_depth); - intel_de_write(dev_priv, DSS_CTL2, dss_ctl2); + intel_de_write(dev_priv, dss_ctl2_reg, dss_ctl2); } else { /* Interleave */ dss_ctl1 |= DUAL_LINK_MODE_INTERLEAVE; } - intel_de_write(dev_priv, DSS_CTL1, dss_ctl1); + intel_de_write(dev_priv, dss_ctl1_reg, dss_ctl1); } /* aka DSI 8X clock */ diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c index 76678dd60f93..c4c6f67af7cc 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c @@ -31,6 +31,7 @@ gf108_fb = { .init = gf100_fb_init, .init_page = gf100_fb_init_page, .intr = gf100_fb_intr, + .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, .ram_new = gf108_ram_new, .default_bigpage = 17, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c index f73442ccb424..433fa966ba23 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c @@ -77,6 +77,7 @@ gk104_fb = { .init = gf100_fb_init, .init_page = gf100_fb_init_page, .intr = gf100_fb_intr, + .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, .ram_new = gk104_ram_new, .default_bigpage = 17, .clkgate_pack = gk104_fb_clkgate_pack, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c index 45d6cdffafee..4dc283dedf8b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c @@ -59,6 +59,7 @@ gk110_fb = { .init = gf100_fb_init, .init_page = gf100_fb_init_page, .intr = gf100_fb_intr, + .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, .ram_new = gk104_ram_new, .default_bigpage = 17, .clkgate_pack = gk110_fb_clkgate_pack, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c index de52462a92bf..90bfff616d35 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c @@ -31,6 +31,7 @@ gm107_fb = { .init = gf100_fb_init, .init_page = gf100_fb_init_page, .intr = gf100_fb_intr, + .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, .ram_new = gm107_ram_new, .default_bigpage = 17, }; diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 15d04a0ec623..e0a8890a62e2 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -507,12 +507,19 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job) { struct drm_sched_entity *entity = sched_job->entity; bool first; + ktime_t submit_ts; trace_drm_sched_job(sched_job, entity); atomic_inc(entity->rq->sched->score); WRITE_ONCE(entity->last_user, current->group_leader); + + /* + * After the sched_job is pushed into the entity queue, it may be + * completed and freed up at any time. We can no longer access it. + * Make sure to set the submit_ts first, to avoid a race. + */ + sched_job->submit_ts = submit_ts = ktime_get(); first = spsc_queue_push(&entity->job_queue, &sched_job->queue_node); - sched_job->submit_ts = ktime_get(); /* first job wakes up scheduler */ if (first) { @@ -529,7 +536,7 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job) spin_unlock(&entity->rq_lock); if (drm_sched_policy == DRM_SCHED_POLICY_FIFO) - drm_sched_rq_update_fifo(entity, sched_job->submit_ts); + drm_sched_rq_update_fifo(entity, submit_ts); drm_sched_wakeup(entity->rq->sched); } diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 82f64fb31fda..4ce012f83253 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -1122,7 +1122,7 @@ config HID_TOPRE tristate "Topre REALFORCE keyboards" depends on HID help - Say Y for N-key rollover support on Topre REALFORCE R2 108 key keyboards. + Say Y for N-key rollover support on Topre REALFORCE R2 108/87 key keyboards. config HID_THINGM tristate "ThingM blink(1) USB RGB LED" diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 63545cd307e5..c2e9b6d1fd7d 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -420,6 +420,9 @@ #define I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN 0x261A #define I2C_DEVICE_ID_SURFACE_GO2_TOUCHSCREEN 0x2A1C #define I2C_DEVICE_ID_LENOVO_YOGA_C630_TOUCHSCREEN 0x279F +#define I2C_DEVICE_ID_HP_SPECTRE_X360_13T_AW100 0x29F5 +#define I2C_DEVICE_ID_HP_SPECTRE_X360_14T_EA100_V1 0x2BED +#define I2C_DEVICE_ID_HP_SPECTRE_X360_14T_EA100_V2 0x2BEE #define USB_VENDOR_ID_ELECOM 0x056e #define USB_DEVICE_ID_ELECOM_BM084 0x0061 @@ -1249,6 +1252,7 @@ #define USB_VENDOR_ID_TOPRE 0x0853 #define USB_DEVICE_ID_TOPRE_REALFORCE_R2_108 0x0148 +#define USB_DEVICE_ID_TOPRE_REALFORCE_R2_87 0x0146 #define USB_VENDOR_ID_TOPSEED 0x0766 #define USB_DEVICE_ID_TOPSEED_CYBERLINK 0x0204 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 7fc967964dd8..5c65a584b3fa 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -398,6 +398,12 @@ static const struct hid_device_id hid_battery_quirks[] = { HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_LENOVO_YOGA_C630_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_13T_AW100), + HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_14T_EA100_V1), + HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_14T_EA100_V2), + HID_BATTERY_QUIRK_IGNORE }, {} }; diff --git a/drivers/hid/hid-sensor-custom.c b/drivers/hid/hid-sensor-custom.c index 3e3f89e01d81..d85398721659 100644 --- a/drivers/hid/hid-sensor-custom.c +++ b/drivers/hid/hid-sensor-custom.c @@ -940,7 +940,7 @@ hid_sensor_register_platform_device(struct platform_device *pdev, struct hid_sensor_hub_device *hsdev, const struct hid_sensor_custom_match *match) { - char real_usage[HID_SENSOR_USAGE_LENGTH]; + char real_usage[HID_SENSOR_USAGE_LENGTH] = { 0 }; struct platform_device *custom_pdev; const char *dev_name; char *c; diff --git a/drivers/hid/hid-topre.c b/drivers/hid/hid-topre.c index 88a91cdad5f8..d1d5ca310ead 100644 --- a/drivers/hid/hid-topre.c +++ b/drivers/hid/hid-topre.c @@ -36,6 +36,8 @@ static __u8 *topre_report_fixup(struct hid_device *hdev, __u8 *rdesc, static const struct hid_device_id topre_id_table[] = { { HID_USB_DEVICE(USB_VENDOR_ID_TOPRE, USB_DEVICE_ID_TOPRE_REALFORCE_R2_108) }, + { HID_USB_DEVICE(USB_VENDOR_ID_TOPRE, + USB_DEVICE_ID_TOPRE_REALFORCE_R2_87) }, { } }; MODULE_DEVICE_TABLE(hid, topre_id_table); diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index 81385ab37fa9..7fc738a22375 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -241,8 +241,8 @@ static int ishtp_cl_bus_match(struct device *dev, struct device_driver *drv) struct ishtp_cl_device *device = to_ishtp_cl_device(dev); struct ishtp_cl_driver *driver = to_ishtp_cl_driver(drv); - return guid_equal(&driver->id[0].guid, - &device->fw_client->props.protocol_name); + return(device->fw_client ? guid_equal(&driver->id[0].guid, + &device->fw_client->props.protocol_name) : 0); } /** diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index 1ea8f173cca0..4c15fae534f3 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -472,7 +472,7 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata) if (etm4x_sspcicrn_present(drvdata, i)) etm4x_relaxed_write32(csa, config->ss_pe_cmp[i], TRCSSPCICRn(i)); } - for (i = 0; i < drvdata->nr_addr_cmp; i++) { + for (i = 0; i < drvdata->nr_addr_cmp * 2; i++) { etm4x_relaxed_write64(csa, config->addr_val[i], TRCACVRn(i)); etm4x_relaxed_write64(csa, config->addr_acc[i], TRCACATRn(i)); } @@ -1070,25 +1070,21 @@ static bool etm4_init_iomem_access(struct etmv4_drvdata *drvdata, struct csdev_access *csa) { u32 devarch = readl_relaxed(drvdata->base + TRCDEVARCH); - u32 idr1 = readl_relaxed(drvdata->base + TRCIDR1); /* * All ETMs must implement TRCDEVARCH to indicate that - * the component is an ETMv4. To support any broken - * implementations we fall back to TRCIDR1 check, which - * is not really reliable. + * the component is an ETMv4. Even though TRCIDR1 also + * contains the information, it is part of the "Trace" + * register and must be accessed with the OSLK cleared, + * with MMIO. But we cannot touch the OSLK until we are + * sure this is an ETM. So rely only on the TRCDEVARCH. */ - if ((devarch & ETM_DEVARCH_ID_MASK) == ETM_DEVARCH_ETMv4x_ARCH) { - drvdata->arch = etm_devarch_to_arch(devarch); - } else { - pr_warn("CPU%d: ETM4x incompatible TRCDEVARCH: %x, falling back to TRCIDR1\n", - smp_processor_id(), devarch); - - if (ETM_TRCIDR1_ARCH_MAJOR(idr1) != ETM_TRCIDR1_ARCH_ETMv4) - return false; - drvdata->arch = etm_trcidr_to_arch(idr1); + if ((devarch & ETM_DEVARCH_ID_MASK) != ETM_DEVARCH_ETMv4x_ARCH) { + pr_warn_once("TRCDEVARCH doesn't match ETMv4 architecture\n"); + return false; } + drvdata->arch = etm_devarch_to_arch(devarch); *csa = CSDEV_ACCESS_IOMEM(drvdata->base); return true; } diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index 434f4e95ee17..27c8a9901868 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -753,14 +753,12 @@ * TRCDEVARCH - CoreSight architected register * - Bits[15:12] - Major version * - Bits[19:16] - Minor version - * TRCIDR1 - ETM architected register - * - Bits[11:8] - Major version - * - Bits[7:4] - Minor version - * We must rely on TRCDEVARCH for the version information, - * however we don't want to break the support for potential - * old implementations which might not implement it. Thus - * we fall back to TRCIDR1 if TRCDEVARCH is not implemented - * for memory mapped components. + * + * We must rely only on TRCDEVARCH for the version information. Even though, + * TRCIDR1 also provides the architecture version, it is a "Trace" register + * and as such must be accessed only with Trace power domain ON. This may + * not be available at probe time. + * * Now to make certain decisions easier based on the version * we use an internal representation of the version in the * driver, as follows : @@ -786,12 +784,6 @@ static inline u8 etm_devarch_to_arch(u32 devarch) ETM_DEVARCH_REVISION(devarch)); } -static inline u8 etm_trcidr_to_arch(u32 trcidr1) -{ - return ETM_ARCH_VERSION(ETM_TRCIDR1_ARCH_MAJOR(trcidr1), - ETM_TRCIDR1_ARCH_MINOR(trcidr1)); -} - enum etm_impdef_type { ETM4_IMPDEF_HISI_CORE_COMMIT, ETM4_IMPDEF_FEATURE_MAX, diff --git a/drivers/i2c/i2c-core-of.c b/drivers/i2c/i2c-core-of.c index bce6b796e04c..545436b7dd53 100644 --- a/drivers/i2c/i2c-core-of.c +++ b/drivers/i2c/i2c-core-of.c @@ -178,6 +178,11 @@ static int of_i2c_notify(struct notifier_block *nb, unsigned long action, return NOTIFY_OK; } + /* + * Clear the flag before adding the device so that fw_devlink + * doesn't skip adding consumers to this device. + */ + rd->dn->fwnode.flags &= ~FWNODE_FLAG_NOT_DEVICE; client = of_i2c_register_device(adap, rd->dn); if (IS_ERR(client)) { dev_err(&adap->dev, "failed to create client for '%pOF'\n", diff --git a/drivers/iio/accel/kionix-kx022a.c b/drivers/iio/accel/kionix-kx022a.c index f866859855cd..1c3a72380fb8 100644 --- a/drivers/iio/accel/kionix-kx022a.c +++ b/drivers/iio/accel/kionix-kx022a.c @@ -864,7 +864,7 @@ static irqreturn_t kx022a_trigger_handler(int irq, void *p) if (ret < 0) goto err_read; - iio_push_to_buffers_with_timestamp(idev, data->buffer, pf->timestamp); + iio_push_to_buffers_with_timestamp(idev, data->buffer, data->timestamp); err_read: iio_trigger_notify_done(idev->trig); diff --git a/drivers/iio/adc/ad7791.c b/drivers/iio/adc/ad7791.c index fee8d129a5f0..86effe8501b4 100644 --- a/drivers/iio/adc/ad7791.c +++ b/drivers/iio/adc/ad7791.c @@ -253,7 +253,7 @@ static const struct ad_sigma_delta_info ad7791_sigma_delta_info = { .has_registers = true, .addr_shift = 4, .read_mask = BIT(3), - .irq_flags = IRQF_TRIGGER_LOW, + .irq_flags = IRQF_TRIGGER_FALLING, }; static int ad7791_read_raw(struct iio_dev *indio_dev, diff --git a/drivers/iio/adc/ltc2497.c b/drivers/iio/adc/ltc2497.c index 17370c5eb6fe..ec198c6f13d6 100644 --- a/drivers/iio/adc/ltc2497.c +++ b/drivers/iio/adc/ltc2497.c @@ -28,7 +28,6 @@ struct ltc2497_driverdata { struct ltc2497core_driverdata common_ddata; struct i2c_client *client; u32 recv_size; - u32 sub_lsb; /* * DMA (thus cache coherency maintenance) may require the * transfer buffers to live in their own cache lines. @@ -65,10 +64,10 @@ static int ltc2497_result_and_measure(struct ltc2497core_driverdata *ddata, * equivalent to a sign extension. */ if (st->recv_size == 3) { - *val = (get_unaligned_be24(st->data.d8) >> st->sub_lsb) + *val = (get_unaligned_be24(st->data.d8) >> 6) - BIT(ddata->chip_info->resolution + 1); } else { - *val = (be32_to_cpu(st->data.d32) >> st->sub_lsb) + *val = (be32_to_cpu(st->data.d32) >> 6) - BIT(ddata->chip_info->resolution + 1); } @@ -122,7 +121,6 @@ static int ltc2497_probe(struct i2c_client *client) st->common_ddata.chip_info = chip_info; resolution = chip_info->resolution; - st->sub_lsb = 31 - (resolution + 1); st->recv_size = BITS_TO_BYTES(resolution) + 1; return ltc2497core_probe(dev, indio_dev); diff --git a/drivers/iio/adc/max11410.c b/drivers/iio/adc/max11410.c index b74b689ee7de..f6895bc9fc4b 100644 --- a/drivers/iio/adc/max11410.c +++ b/drivers/iio/adc/max11410.c @@ -414,13 +414,17 @@ static int max11410_sample(struct max11410_state *st, int *sample_raw, if (!ret) return -ETIMEDOUT; } else { + int ret2; + /* Wait for status register Conversion Ready flag */ - ret = read_poll_timeout(max11410_read_reg, ret, - ret || (val & MAX11410_STATUS_CONV_READY_BIT), + ret = read_poll_timeout(max11410_read_reg, ret2, + ret2 || (val & MAX11410_STATUS_CONV_READY_BIT), 5000, MAX11410_CONVERSION_TIMEOUT_MS * 1000, true, st, MAX11410_REG_STATUS, &val); if (ret) return ret; + if (ret2) + return ret2; } /* Read ADC Data */ @@ -851,17 +855,21 @@ static int max11410_init_vref(struct device *dev, static int max11410_calibrate(struct max11410_state *st, u32 cal_type) { - int ret, val; + int ret, ret2, val; ret = max11410_write_reg(st, MAX11410_REG_CAL_START, cal_type); if (ret) return ret; /* Wait for status register Calibration Ready flag */ - return read_poll_timeout(max11410_read_reg, ret, - ret || (val & MAX11410_STATUS_CAL_READY_BIT), - 50000, MAX11410_CALIB_TIMEOUT_MS * 1000, true, - st, MAX11410_REG_STATUS, &val); + ret = read_poll_timeout(max11410_read_reg, ret2, + ret2 || (val & MAX11410_STATUS_CAL_READY_BIT), + 50000, MAX11410_CALIB_TIMEOUT_MS * 1000, true, + st, MAX11410_REG_STATUS, &val); + if (ret) + return ret; + + return ret2; } static int max11410_self_calibrate(struct max11410_state *st) diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index fd000345ec5c..849a697a467e 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -639,7 +639,7 @@ out: static int palmas_gpadc_remove(struct platform_device *pdev) { - struct iio_dev *indio_dev = dev_to_iio_dev(&pdev->dev); + struct iio_dev *indio_dev = dev_get_drvdata(&pdev->dev); struct palmas_gpadc *adc = iio_priv(indio_dev); if (adc->wakeup1_enable || adc->wakeup2_enable) diff --git a/drivers/iio/adc/qcom-spmi-adc5.c b/drivers/iio/adc/qcom-spmi-adc5.c index e90c299c913a..c2d5e06f137a 100644 --- a/drivers/iio/adc/qcom-spmi-adc5.c +++ b/drivers/iio/adc/qcom-spmi-adc5.c @@ -628,12 +628,20 @@ static int adc5_get_fw_channel_data(struct adc5_chip *adc, struct fwnode_handle *fwnode, const struct adc5_data *data) { - const char *name = fwnode_get_name(fwnode), *channel_name; + const char *channel_name; + char *name; u32 chan, value, varr[2]; u32 sid = 0; int ret; struct device *dev = adc->dev; + name = devm_kasprintf(dev, GFP_KERNEL, "%pfwP", fwnode); + if (!name) + return -ENOMEM; + + /* Cut the address part */ + name[strchrnul(name, '@') - name] = '\0'; + ret = fwnode_property_read_u32(fwnode, "reg", &chan); if (ret) { dev_err(dev, "invalid channel number %s\n", name); diff --git a/drivers/iio/adc/ti-ads7950.c b/drivers/iio/adc/ti-ads7950.c index 2cc9a9bd9db6..263fc3a1b87e 100644 --- a/drivers/iio/adc/ti-ads7950.c +++ b/drivers/iio/adc/ti-ads7950.c @@ -634,6 +634,7 @@ static int ti_ads7950_probe(struct spi_device *spi) st->chip.label = dev_name(&st->spi->dev); st->chip.parent = &st->spi->dev; st->chip.owner = THIS_MODULE; + st->chip.can_sleep = true; st->chip.base = -1; st->chip.ngpio = TI_ADS7950_NUM_GPIOS; st->chip.get_direction = ti_ads7950_get_direction; diff --git a/drivers/iio/dac/cio-dac.c b/drivers/iio/dac/cio-dac.c index 791dd999cf29..18a64f72fc18 100644 --- a/drivers/iio/dac/cio-dac.c +++ b/drivers/iio/dac/cio-dac.c @@ -66,8 +66,8 @@ static int cio_dac_write_raw(struct iio_dev *indio_dev, if (mask != IIO_CHAN_INFO_RAW) return -EINVAL; - /* DAC can only accept up to a 16-bit value */ - if ((unsigned int)val > 65535) + /* DAC can only accept up to a 12-bit value */ + if ((unsigned int)val > 4095) return -EINVAL; priv->chan_out_states[chan->channel] = val; diff --git a/drivers/iio/imu/Kconfig b/drivers/iio/imu/Kconfig index f1d7d4b5e222..c2f97629e9cd 100644 --- a/drivers/iio/imu/Kconfig +++ b/drivers/iio/imu/Kconfig @@ -47,6 +47,7 @@ config ADIS16480 depends on SPI select IIO_ADIS_LIB select IIO_ADIS_LIB_BUFFER if IIO_BUFFER + select CRC32 help Say yes here to build support for Analog Devices ADIS16375, ADIS16480, ADIS16485, ADIS16488 inertial sensors. diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index 80c78bd6bbef..a7a080bed180 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -203,24 +203,27 @@ static ssize_t iio_buffer_write(struct file *filp, const char __user *buf, break; } + if (filp->f_flags & O_NONBLOCK) { + if (!written) + ret = -EAGAIN; + break; + } + wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); continue; } ret = rb->access->write(rb, n - written, buf + written); - if (ret == 0 && (filp->f_flags & O_NONBLOCK)) - ret = -EAGAIN; + if (ret < 0) + break; - if (ret > 0) { - written += ret; - if (written != n && !(filp->f_flags & O_NONBLOCK)) - continue; - } - } while (ret == 0); + written += ret; + + } while (written != n); remove_wait_queue(&rb->pollq, &wait); - return ret < 0 ? ret : n; + return ret < 0 ? ret : written; } /** diff --git a/drivers/iio/light/cm32181.c b/drivers/iio/light/cm32181.c index b1674a5bfa36..d4a34a3bf00d 100644 --- a/drivers/iio/light/cm32181.c +++ b/drivers/iio/light/cm32181.c @@ -429,6 +429,14 @@ static const struct iio_info cm32181_info = { .attrs = &cm32181_attribute_group, }; +static void cm32181_unregister_dummy_client(void *data) +{ + struct i2c_client *client = data; + + /* Unregister the dummy client */ + i2c_unregister_device(client); +} + static int cm32181_probe(struct i2c_client *client) { struct device *dev = &client->dev; @@ -460,6 +468,10 @@ static int cm32181_probe(struct i2c_client *client) client = i2c_acpi_new_device(dev, 1, &board_info); if (IS_ERR(client)) return PTR_ERR(client); + + ret = devm_add_action_or_reset(dev, cm32181_unregister_dummy_client, client); + if (ret) + return ret; } cm32181 = iio_priv(indio_dev); diff --git a/drivers/iio/light/vcnl4000.c b/drivers/iio/light/vcnl4000.c index 6bdfce9747f9..5c44a36ab5b3 100644 --- a/drivers/iio/light/vcnl4000.c +++ b/drivers/iio/light/vcnl4000.c @@ -208,7 +208,6 @@ static int vcnl4000_init(struct vcnl4000_data *data) data->rev = ret & 0xf; data->al_scale = 250000; - mutex_init(&data->vcnl4000_lock); return data->chip_spec->set_power_state(data, true); }; @@ -1367,6 +1366,8 @@ static int vcnl4000_probe(struct i2c_client *client) data->id = id->driver_data; data->chip_spec = &vcnl4000_chip_spec_cfg[data->id]; + mutex_init(&data->vcnl4000_lock); + ret = data->chip_spec->init(data); if (ret < 0) return ret; diff --git a/drivers/mtd/mtdblock.c b/drivers/mtd/mtdblock.c index 1e94e7d10b8b..a0a1194dc1d9 100644 --- a/drivers/mtd/mtdblock.c +++ b/drivers/mtd/mtdblock.c @@ -153,7 +153,7 @@ static int do_cached_write (struct mtdblk_dev *mtdblk, unsigned long pos, mtdblk->cache_state = STATE_EMPTY; ret = mtd_read(mtd, sect_start, sect_size, &retlen, mtdblk->cache_data); - if (ret) + if (ret && !mtd_is_bitflip(ret)) return ret; if (retlen != sect_size) return -EIO; @@ -188,8 +188,12 @@ static int do_cached_read (struct mtdblk_dev *mtdblk, unsigned long pos, pr_debug("mtdblock: read on \"%s\" at 0x%lx, size 0x%x\n", mtd->name, pos, len); - if (!sect_size) - return mtd_read(mtd, pos, len, &retlen, buf); + if (!sect_size) { + ret = mtd_read(mtd, pos, len, &retlen, buf); + if (ret && !mtd_is_bitflip(ret)) + return ret; + return 0; + } while (len > 0) { unsigned long sect_start = (pos/sect_size)*sect_size; @@ -209,7 +213,7 @@ static int do_cached_read (struct mtdblk_dev *mtdblk, unsigned long pos, memcpy (buf, mtdblk->cache_data + offset, size); } else { ret = mtd_read(mtd, pos, size, &retlen, buf); - if (ret) + if (ret && !mtd_is_bitflip(ret)) return ret; if (retlen != size) return -EIO; diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index a28574c00900..074e14225c06 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -280,7 +280,7 @@ static void meson_nfc_cmd_access(struct nand_chip *nand, int raw, bool dir, if (raw) { len = mtd->writesize + mtd->oobsize; - cmd = (len & GENMASK(5, 0)) | scrambler | DMA_DIR(dir); + cmd = (len & GENMASK(13, 0)) | scrambler | DMA_DIR(dir); writel(cmd, nfc->reg_base + NFC_REG_CMD); return; } @@ -544,7 +544,7 @@ static int meson_nfc_read_buf(struct nand_chip *nand, u8 *buf, int len) if (ret) goto out; - cmd = NFC_CMD_N2M | (len & GENMASK(5, 0)); + cmd = NFC_CMD_N2M | (len & GENMASK(13, 0)); writel(cmd, nfc->reg_base + NFC_REG_CMD); meson_nfc_drain_cmd(nfc); @@ -568,7 +568,7 @@ static int meson_nfc_write_buf(struct nand_chip *nand, u8 *buf, int len) if (ret) return ret; - cmd = NFC_CMD_M2N | (len & GENMASK(5, 0)); + cmd = NFC_CMD_M2N | (len & GENMASK(13, 0)); writel(cmd, nfc->reg_base + NFC_REG_CMD); meson_nfc_drain_cmd(nfc); diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c index 5d627048c420..9e74bcd90aaa 100644 --- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c +++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c @@ -1531,6 +1531,9 @@ static int stm32_fmc2_nfc_setup_interface(struct nand_chip *chip, int chipnr, if (IS_ERR(sdrt)) return PTR_ERR(sdrt); + if (conf->timings.mode > 3) + return -EOPNOTSUPP; + if (chipnr == NAND_DATA_IFACE_CHECK_ONLY) return 0; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 236e5219c811..8cc9a74789b7 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3269,7 +3269,8 @@ static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, combined = skb_header_pointer(skb, 0, sizeof(_combined), &_combined); if (!combined || combined->ip6.nexthdr != NEXTHDR_ICMP || - combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT) + (combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION && + combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT)) goto out; saddr = &combined->ip6.saddr; @@ -3291,7 +3292,7 @@ static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, else if (curr_active_slave && time_after(slave_last_rx(bond, curr_active_slave), curr_active_slave->last_link_up)) - bond_validate_na(bond, slave, saddr, daddr); + bond_validate_na(bond, slave, daddr, saddr); else if (curr_arp_slave && bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1)) bond_validate_na(bond, slave, saddr, daddr); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index f77bd1223c8f..541e4dda7950 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1063,6 +1063,10 @@ static dma_addr_t macb_get_addr(struct macb *bp, struct macb_dma_desc *desc) } #endif addr |= MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, desc->addr)); +#ifdef CONFIG_MACB_USE_HWSTAMP + if (bp->hw_dma_cap & HW_DMA_CAP_PTP) + addr &= ~GEM_BIT(DMA_RXVALID); +#endif return addr; } diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index da9d4b310fcd..838750a03cf6 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -989,6 +989,20 @@ static int enetc_get_mm(struct net_device *ndev, struct ethtool_mm_state *state) return 0; } +/* FIXME: Workaround for the link partner's verification failing if ENETC + * priorly received too much express traffic. The documentation doesn't + * suggest this is needed. + */ +static void enetc_restart_emac_rx(struct enetc_si *si) +{ + u32 val = enetc_port_rd(&si->hw, ENETC_PM0_CMD_CFG); + + enetc_port_wr(&si->hw, ENETC_PM0_CMD_CFG, val & ~ENETC_PM0_RX_EN); + + if (val & ENETC_PM0_RX_EN) + enetc_port_wr(&si->hw, ENETC_PM0_CMD_CFG, val); +} + static int enetc_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack) { @@ -1040,6 +1054,8 @@ static int enetc_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg, enetc_port_wr(hw, ENETC_MMCSR, val); + enetc_restart_emac_rx(priv->si); + mutex_unlock(&priv->mm_lock); return 0; diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 2cdce251472c..9abaff1f2aff 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -58,8 +58,6 @@ enum iavf_vsi_state_t { struct iavf_vsi { struct iavf_adapter *back; struct net_device *netdev; - unsigned long active_cvlans[BITS_TO_LONGS(VLAN_N_VID)]; - unsigned long active_svlans[BITS_TO_LONGS(VLAN_N_VID)]; u16 seid; u16 id; DECLARE_BITMAP(state, __IAVF_VSI_STATE_SIZE__); @@ -157,15 +155,20 @@ struct iavf_vlan { u16 tpid; }; +enum iavf_vlan_state_t { + IAVF_VLAN_INVALID, + IAVF_VLAN_ADD, /* filter needs to be added */ + IAVF_VLAN_IS_NEW, /* filter is new, wait for PF answer */ + IAVF_VLAN_ACTIVE, /* filter is accepted by PF */ + IAVF_VLAN_DISABLE, /* filter needs to be deleted by PF, then marked INACTIVE */ + IAVF_VLAN_INACTIVE, /* filter is inactive, we are in IFF_DOWN */ + IAVF_VLAN_REMOVE, /* filter needs to be removed from list */ +}; + struct iavf_vlan_filter { struct list_head list; struct iavf_vlan vlan; - struct { - u8 is_new_vlan:1; /* filter is new, wait for PF answer */ - u8 remove:1; /* filter needs to be removed */ - u8 add:1; /* filter needs to be added */ - u8 padding:5; - }; + enum iavf_vlan_state_t state; }; #define IAVF_MAX_TRAFFIC_CLASS 4 @@ -257,6 +260,7 @@ struct iavf_adapter { wait_queue_head_t vc_waitqueue; struct iavf_q_vector *q_vectors; struct list_head vlan_filter_list; + int num_vlan_filters; struct list_head mac_filter_list; struct mutex crit_lock; struct mutex client_lock; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 095201e83c9d..2de4baff4c20 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -791,7 +791,8 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, f->vlan = vlan; list_add_tail(&f->list, &adapter->vlan_filter_list); - f->add = true; + f->state = IAVF_VLAN_ADD; + adapter->num_vlan_filters++; adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; } @@ -813,7 +814,7 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) f = iavf_find_vlan(adapter, vlan); if (f) { - f->remove = true; + f->state = IAVF_VLAN_REMOVE; adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; } @@ -828,14 +829,18 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) **/ static void iavf_restore_filters(struct iavf_adapter *adapter) { - u16 vid; + struct iavf_vlan_filter *f; /* re-add all VLAN filters */ - for_each_set_bit(vid, adapter->vsi.active_cvlans, VLAN_N_VID) - iavf_add_vlan(adapter, IAVF_VLAN(vid, ETH_P_8021Q)); + spin_lock_bh(&adapter->mac_vlan_list_lock); - for_each_set_bit(vid, adapter->vsi.active_svlans, VLAN_N_VID) - iavf_add_vlan(adapter, IAVF_VLAN(vid, ETH_P_8021AD)); + list_for_each_entry(f, &adapter->vlan_filter_list, list) { + if (f->state == IAVF_VLAN_INACTIVE) + f->state = IAVF_VLAN_ADD; + } + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; } /** @@ -844,8 +849,7 @@ static void iavf_restore_filters(struct iavf_adapter *adapter) */ u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter) { - return bitmap_weight(adapter->vsi.active_cvlans, VLAN_N_VID) + - bitmap_weight(adapter->vsi.active_svlans, VLAN_N_VID); + return adapter->num_vlan_filters; } /** @@ -928,11 +932,6 @@ static int iavf_vlan_rx_kill_vid(struct net_device *netdev, return 0; iavf_del_vlan(adapter, IAVF_VLAN(vid, be16_to_cpu(proto))); - if (proto == cpu_to_be16(ETH_P_8021Q)) - clear_bit(vid, adapter->vsi.active_cvlans); - else - clear_bit(vid, adapter->vsi.active_svlans); - return 0; } @@ -1293,16 +1292,11 @@ static void iavf_clear_mac_vlan_filters(struct iavf_adapter *adapter) } } - /* remove all VLAN filters */ + /* disable all VLAN filters */ list_for_each_entry_safe(vlf, vlftmp, &adapter->vlan_filter_list, - list) { - if (vlf->add) { - list_del(&vlf->list); - kfree(vlf); - } else { - vlf->remove = true; - } - } + list) + vlf->state = IAVF_VLAN_DISABLE; + spin_unlock_bh(&adapter->mac_vlan_list_lock); } @@ -2914,6 +2908,7 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) list_del(&fv->list); kfree(fv); } + adapter->num_vlan_filters = 0; spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -3131,9 +3126,6 @@ continue_reset: adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; iavf_misc_irq_enable(adapter); - bitmap_clear(adapter->vsi.active_cvlans, 0, VLAN_N_VID); - bitmap_clear(adapter->vsi.active_svlans, 0, VLAN_N_VID); - mod_delayed_work(adapter->wq, &adapter->watchdog_task, 2); /* We were running when the reset started, so we need to restore some diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 4e17d006c52d..9afbbdac3590 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -642,16 +642,10 @@ static void iavf_vlan_add_reject(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->is_new_vlan) { - if (f->vlan.tpid == ETH_P_8021Q) - clear_bit(f->vlan.vid, - adapter->vsi.active_cvlans); - else - clear_bit(f->vlan.vid, - adapter->vsi.active_svlans); - + if (f->state == IAVF_VLAN_IS_NEW) { list_del(&f->list); kfree(f); + adapter->num_vlan_filters--; } } spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -679,7 +673,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->add) + if (f->state == IAVF_VLAN_ADD) count++; } if (!count || !VLAN_FILTERING_ALLOWED(adapter)) { @@ -710,11 +704,10 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vvfl->vsi_id = adapter->vsi_res->vsi_id; vvfl->num_elements = count; list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->add) { + if (f->state == IAVF_VLAN_ADD) { vvfl->vlan_id[i] = f->vlan.vid; i++; - f->add = false; - f->is_new_vlan = true; + f->state = IAVF_VLAN_IS_NEW; if (i == count) break; } @@ -760,7 +753,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vvfl_v2->vport_id = adapter->vsi_res->vsi_id; vvfl_v2->num_elements = count; list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->add) { + if (f->state == IAVF_VLAN_ADD) { struct virtchnl_vlan_supported_caps *filtering_support = &adapter->vlan_v2_caps.filtering.filtering_support; struct virtchnl_vlan *vlan; @@ -778,8 +771,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vlan->tpid = f->vlan.tpid; i++; - f->add = false; - f->is_new_vlan = true; + f->state = IAVF_VLAN_IS_NEW; } } @@ -822,10 +814,16 @@ void iavf_del_vlans(struct iavf_adapter *adapter) * filters marked for removal to enable bailing out before * sending a virtchnl message */ - if (f->remove && !VLAN_FILTERING_ALLOWED(adapter)) { + if (f->state == IAVF_VLAN_REMOVE && + !VLAN_FILTERING_ALLOWED(adapter)) { list_del(&f->list); kfree(f); - } else if (f->remove) { + adapter->num_vlan_filters--; + } else if (f->state == IAVF_VLAN_DISABLE && + !VLAN_FILTERING_ALLOWED(adapter)) { + f->state = IAVF_VLAN_INACTIVE; + } else if (f->state == IAVF_VLAN_REMOVE || + f->state == IAVF_VLAN_DISABLE) { count++; } } @@ -857,11 +855,18 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl->vsi_id = adapter->vsi_res->vsi_id; vvfl->num_elements = count; list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->remove) { + if (f->state == IAVF_VLAN_DISABLE) { vvfl->vlan_id[i] = f->vlan.vid; + f->state = IAVF_VLAN_INACTIVE; i++; + if (i == count) + break; + } else if (f->state == IAVF_VLAN_REMOVE) { + vvfl->vlan_id[i] = f->vlan.vid; list_del(&f->list); kfree(f); + adapter->num_vlan_filters--; + i++; if (i == count) break; } @@ -901,7 +906,8 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl_v2->vport_id = adapter->vsi_res->vsi_id; vvfl_v2->num_elements = count; list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->remove) { + if (f->state == IAVF_VLAN_DISABLE || + f->state == IAVF_VLAN_REMOVE) { struct virtchnl_vlan_supported_caps *filtering_support = &adapter->vlan_v2_caps.filtering.filtering_support; struct virtchnl_vlan *vlan; @@ -915,8 +921,13 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vlan->tci = f->vlan.vid; vlan->tpid = f->vlan.tpid; - list_del(&f->list); - kfree(f); + if (f->state == IAVF_VLAN_DISABLE) { + f->state = IAVF_VLAN_INACTIVE; + } else { + list_del(&f->list); + kfree(f); + adapter->num_vlan_filters--; + } i++; if (i == count) break; @@ -2192,7 +2203,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list_for_each_entry(vlf, &adapter->vlan_filter_list, list) - vlf->add = true; + vlf->state = IAVF_VLAN_ADD; adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; @@ -2260,7 +2271,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list_for_each_entry(vlf, &adapter->vlan_filter_list, list) - vlf->add = true; + vlf->state = IAVF_VLAN_ADD; aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; } @@ -2444,15 +2455,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->is_new_vlan) { - f->is_new_vlan = false; - if (f->vlan.tpid == ETH_P_8021Q) - set_bit(f->vlan.vid, - adapter->vsi.active_cvlans); - else - set_bit(f->vlan.vid, - adapter->vsi.active_svlans); - } + if (f->state == IAVF_VLAN_IS_NEW) + f->state = IAVF_VLAN_ACTIVE; } spin_unlock_bh(&adapter->mac_vlan_list_lock); } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 4b5e459b6d49..332472fe4990 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -681,14 +681,32 @@ int mlx4_en_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) return 0; } -int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash) +int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) { struct mlx4_en_xdp_buff *_ctx = (void *)ctx; + struct mlx4_cqe *cqe = _ctx->cqe; + enum xdp_rss_hash_type xht = 0; + __be16 status; if (unlikely(!(_ctx->dev->features & NETIF_F_RXHASH))) return -ENODATA; - *hash = be32_to_cpu(_ctx->cqe->immed_rss_invalid); + *hash = be32_to_cpu(cqe->immed_rss_invalid); + status = cqe->status; + if (status & cpu_to_be16(MLX4_CQE_STATUS_TCP)) + xht = XDP_RSS_L4_TCP; + if (status & cpu_to_be16(MLX4_CQE_STATUS_UDP)) + xht = XDP_RSS_L4_UDP; + if (status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 | MLX4_CQE_STATUS_IPV4F)) + xht |= XDP_RSS_L3_IPV4; + if (status & cpu_to_be16(MLX4_CQE_STATUS_IPV6)) { + xht |= XDP_RSS_L3_IPV6; + if (cqe->ipv6_ext_mask) + xht |= XDP_RSS_L3_DYNHDR; + } + *rss_type = xht; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 034733b13b1a..321f801c1d7c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -798,7 +798,8 @@ int mlx4_en_netdev_event(struct notifier_block *this, struct xdp_md; int mlx4_en_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp); -int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash); +int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type); /* * Functions for time stamping diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 15d15d0e5ef9..c8b532cea7d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -34,6 +34,7 @@ #include #include "en/xdp.h" #include "en/params.h" +#include int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) { @@ -169,14 +170,72 @@ static int mlx5e_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) return 0; } -static int mlx5e_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash) +/* Mapping HW RSS Type bits CQE_RSS_HTYPE_IP + CQE_RSS_HTYPE_L4 into 4-bits*/ +#define RSS_TYPE_MAX_TABLE 16 /* 4-bits max 16 entries */ +#define RSS_L4 GENMASK(1, 0) +#define RSS_L3 GENMASK(3, 2) /* Same as CQE_RSS_HTYPE_IP */ + +/* Valid combinations of CQE_RSS_HTYPE_IP + CQE_RSS_HTYPE_L4 sorted numerical */ +enum mlx5_rss_hash_type { + RSS_TYPE_NO_HASH = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IP_NONE) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_NONE)), + RSS_TYPE_L3_IPV4 = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_NONE)), + RSS_TYPE_L4_IPV4_TCP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_TCP)), + RSS_TYPE_L4_IPV4_UDP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_UDP)), + RSS_TYPE_L4_IPV4_IPSEC = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_IPSEC)), + RSS_TYPE_L3_IPV6 = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_NONE)), + RSS_TYPE_L4_IPV6_TCP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_TCP)), + RSS_TYPE_L4_IPV6_UDP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_UDP)), + RSS_TYPE_L4_IPV6_IPSEC = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_IPSEC)), +}; + +/* Invalid combinations will simply return zero, allows no boundary checks */ +static const enum xdp_rss_hash_type mlx5_xdp_rss_type[RSS_TYPE_MAX_TABLE] = { + [RSS_TYPE_NO_HASH] = XDP_RSS_TYPE_NONE, + [1] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [2] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [3] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [RSS_TYPE_L3_IPV4] = XDP_RSS_TYPE_L3_IPV4, + [RSS_TYPE_L4_IPV4_TCP] = XDP_RSS_TYPE_L4_IPV4_TCP, + [RSS_TYPE_L4_IPV4_UDP] = XDP_RSS_TYPE_L4_IPV4_UDP, + [RSS_TYPE_L4_IPV4_IPSEC] = XDP_RSS_TYPE_L4_IPV4_IPSEC, + [RSS_TYPE_L3_IPV6] = XDP_RSS_TYPE_L3_IPV6, + [RSS_TYPE_L4_IPV6_TCP] = XDP_RSS_TYPE_L4_IPV6_TCP, + [RSS_TYPE_L4_IPV6_UDP] = XDP_RSS_TYPE_L4_IPV6_UDP, + [RSS_TYPE_L4_IPV6_IPSEC] = XDP_RSS_TYPE_L4_IPV6_IPSEC, + [12] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [13] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [14] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [15] = XDP_RSS_TYPE_NONE, /* Implicit zero */ +}; + +static int mlx5e_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) { const struct mlx5e_xdp_buff *_ctx = (void *)ctx; + const struct mlx5_cqe64 *cqe = _ctx->cqe; + u32 hash_type, l4_type, ip_type, lookup; if (unlikely(!(_ctx->xdp.rxq->dev->features & NETIF_F_RXHASH))) return -ENODATA; - *hash = be32_to_cpu(_ctx->cqe->rss_hash_result); + *hash = be32_to_cpu(cqe->rss_hash_result); + + hash_type = cqe->rss_hash_type; + BUILD_BUG_ON(CQE_RSS_HTYPE_IP != RSS_L3); /* same mask */ + ip_type = hash_type & CQE_RSS_HTYPE_IP; + l4_type = FIELD_GET(CQE_RSS_HTYPE_L4, hash_type); + lookup = ip_type | l4_type; + *rss_type = mlx5_xdp_rss_type[lookup]; + return 0; } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c index 87f76bac2e46..eb827b86ecae 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c @@ -628,7 +628,13 @@ int qlcnic_fw_create_ctx(struct qlcnic_adapter *dev) int i, err, ring; if (dev->flags & QLCNIC_NEED_FLR) { - pci_reset_function(dev->pdev); + err = pci_reset_function(dev->pdev); + if (err) { + dev_err(&dev->pdev->dev, + "Adapter reset failed (%d). Please reboot\n", + err); + return err; + } dev->flags &= ~QLCNIC_NEED_FLR; } diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index ab8b09a9ef61..7a2e76776297 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -4522,7 +4522,7 @@ static int niu_alloc_channels(struct niu *np) err = niu_rbr_fill(np, rp, GFP_KERNEL); if (err) - return err; + goto out_err; } tx_rings = kcalloc(num_tx_rings, sizeof(struct tx_ring_info), diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 37f0b62ec5d6..f9cd566d1c9b 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -27,7 +27,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 35128dd45ffc..c61e4e44a78f 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -23,7 +24,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index 5813b07242ce..029875a59ff8 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -191,7 +191,7 @@ #define MAX_ID_PS 2260U #define DEFAULT_ID_PS 2000U -#define PPM_TO_SUBNS_INC(ppb) div_u64(GENMASK(31, 0) * (ppb) * \ +#define PPM_TO_SUBNS_INC(ppb) div_u64(GENMASK_ULL(31, 0) * (ppb) * \ PTP_CLK_PERIOD_100BT1, NSEC_PER_SEC) #define NXP_C45_SKB_CB(skb) ((struct nxp_c45_skb_cb *)(skb)->cb) @@ -1337,6 +1337,17 @@ no_ptp_support: return ret; } +static void nxp_c45_remove(struct phy_device *phydev) +{ + struct nxp_c45_phy *priv = phydev->priv; + + if (priv->ptp_clock) + ptp_clock_unregister(priv->ptp_clock); + + skb_queue_purge(&priv->tx_queue); + skb_queue_purge(&priv->rx_queue); +} + static struct phy_driver nxp_c45_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_TJA_1103), @@ -1359,6 +1370,7 @@ static struct phy_driver nxp_c45_driver[] = { .set_loopback = genphy_c45_loopback, .get_sqi = nxp_c45_get_sqi, .get_sqi_max = nxp_c45_get_sqi_max, + .remove = nxp_c45_remove, }, }; diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index cc9d29b71098..89636dc71e48 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -210,6 +210,12 @@ static const enum gpiod_flags gpio_flags[] = { #define SFP_PHY_ADDR 22 #define SFP_PHY_ADDR_ROLLBALL 17 +/* SFP_EEPROM_BLOCK_SIZE is the size of data chunk to read the EEPROM + * at a time. Some SFP modules and also some Linux I2C drivers do not like + * reads longer than 16 bytes. + */ +#define SFP_EEPROM_BLOCK_SIZE 16 + struct sff_data { unsigned int gpios; bool (*module_supported)(const struct sfp_eeprom_id *id); @@ -1951,11 +1957,7 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report) u8 check; int ret; - /* Some SFP modules and also some Linux I2C drivers do not like reads - * longer than 16 bytes, so read the EEPROM in chunks of 16 bytes at - * a time. - */ - sfp->i2c_block_size = 16; + sfp->i2c_block_size = SFP_EEPROM_BLOCK_SIZE; ret = sfp_read(sfp, false, 0, &id.base, sizeof(id.base)); if (ret < 0) { @@ -2513,6 +2515,9 @@ static int sfp_module_eeprom(struct sfp *sfp, struct ethtool_eeprom *ee, unsigned int first, last, len; int ret; + if (!(sfp->state & SFP_F_PRESENT)) + return -ENODEV; + if (ee->len == 0) return -EINVAL; @@ -2545,6 +2550,9 @@ static int sfp_module_eeprom_by_page(struct sfp *sfp, const struct ethtool_module_eeprom *page, struct netlink_ext_ack *extack) { + if (!(sfp->state & SFP_F_PRESENT)) + return -ENODEV; + if (page->bank) { NL_SET_ERR_MSG(extack, "Banks not supported"); return -EOPNOTSUPP; @@ -2649,6 +2657,7 @@ static struct sfp *sfp_alloc(struct device *dev) return ERR_PTR(-ENOMEM); sfp->dev = dev; + sfp->i2c_block_size = SFP_EEPROM_BLOCK_SIZE; mutex_init(&sfp->sm_mutex); mutex_init(&sfp->st_mutex); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index decb5ba56a25..0fc4b959edc1 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1943,7 +1943,7 @@ static struct rx_agg *alloc_rx_agg(struct r8152 *tp, gfp_t mflags) if (!rx_agg) return NULL; - rx_agg->page = alloc_pages(mflags | __GFP_COMP, order); + rx_agg->page = alloc_pages(mflags | __GFP_COMP | __GFP_NOWARN, order); if (!rx_agg->page) goto free_rx; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index c1178915496d..e1b38fbf1dd9 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1648,14 +1648,18 @@ static int veth_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) return 0; } -static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash) +static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) { struct veth_xdp_buff *_ctx = (void *)ctx; + struct sk_buff *skb = _ctx->skb; - if (!_ctx->skb) + if (!skb) return -ENODATA; - *hash = skb_get_hash(_ctx->skb); + *hash = skb_get_hash(skb); + *rss_type = skb->l4_hash ? XDP_RSS_TYPE_L4_ANY : XDP_RSS_TYPE_NONE; + return 0; } diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c index 5bf5a93937c9..04517bd3325a 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_pcie.c +++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c @@ -295,7 +295,7 @@ static int ipc_pcie_probe(struct pci_dev *pci, ret = dma_set_mask(ipc_pcie->dev, DMA_BIT_MASK(64)); if (ret) { dev_err(ipc_pcie->dev, "Could not set PCI DMA mask: %d", ret); - return ret; + goto set_mask_fail; } ipc_pcie_config_aspm(ipc_pcie); @@ -323,6 +323,7 @@ static int ipc_pcie_probe(struct pci_dev *pci, imem_init_fail: ipc_pcie_resources_release(ipc_pcie); resources_req_fail: +set_mask_fail: pci_disable_device(pci); pci_enable_fail: kfree(ipc_pcie); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 53ef028596c6..d6a9bac91a4c 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1674,6 +1674,9 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns) struct request_queue *queue = disk->queue; u32 size = queue_logical_block_size(queue); + if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns, UINT_MAX)) + ctrl->max_discard_sectors = nvme_lba_to_sect(ns, ctrl->dmrsl); + if (ctrl->max_discard_sectors == 0) { blk_queue_max_discard_sectors(queue, 0); return; @@ -1688,9 +1691,6 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns) if (queue->limits.max_discard_sectors) return; - if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns, UINT_MAX)) - ctrl->max_discard_sectors = nvme_lba_to_sect(ns, ctrl->dmrsl); - blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors); blk_queue_max_discard_segments(queue, ctrl->max_discard_segments); diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index 07d93753b12f..e311d406b170 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -226,6 +226,7 @@ static void __of_attach_node(struct device_node *np) np->sibling = np->parent->child; np->parent->child = np; of_node_clear_flag(np, OF_DETACHED); + np->fwnode.flags |= FWNODE_FLAG_NOT_DEVICE; } /** diff --git a/drivers/of/platform.c b/drivers/of/platform.c index b2bd2e783445..78ae84187449 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -737,6 +737,11 @@ static int of_platform_notify(struct notifier_block *nb, if (of_node_check_flag(rd->dn, OF_POPULATED)) return NOTIFY_OK; + /* + * Clear the flag before adding the device so that fw_devlink + * doesn't skip adding consumers to this device. + */ + rd->dn->fwnode.flags &= ~FWNODE_FLAG_NOT_DEVICE; /* pdev_parent may be NULL when no bus platform device */ pdev_parent = of_find_device_by_node(rd->dn->parent); pdev = of_platform_device_create(rd->dn, NULL, diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c index 66d9ab288646..e5e9b287b976 100644 --- a/drivers/pci/doe.c +++ b/drivers/pci/doe.c @@ -128,7 +128,7 @@ static int pci_doe_send_req(struct pci_doe_mb *doe_mb, return -EIO; /* Length is 2 DW of header + length of payload in DW */ - length = 2 + task->request_pl_sz / sizeof(u32); + length = 2 + task->request_pl_sz / sizeof(__le32); if (length > PCI_DOE_MAX_LENGTH) return -EIO; if (length == PCI_DOE_MAX_LENGTH) @@ -141,9 +141,9 @@ static int pci_doe_send_req(struct pci_doe_mb *doe_mb, pci_write_config_dword(pdev, offset + PCI_DOE_WRITE, FIELD_PREP(PCI_DOE_DATA_OBJECT_HEADER_2_LENGTH, length)); - for (i = 0; i < task->request_pl_sz / sizeof(u32); i++) + for (i = 0; i < task->request_pl_sz / sizeof(__le32); i++) pci_write_config_dword(pdev, offset + PCI_DOE_WRITE, - task->request_pl[i]); + le32_to_cpu(task->request_pl[i])); pci_doe_write_ctrl(doe_mb, PCI_DOE_CTRL_GO); @@ -195,11 +195,11 @@ static int pci_doe_recv_resp(struct pci_doe_mb *doe_mb, struct pci_doe_task *tas /* First 2 dwords have already been read */ length -= 2; - payload_length = min(length, task->response_pl_sz / sizeof(u32)); + payload_length = min(length, task->response_pl_sz / sizeof(__le32)); /* Read the rest of the response payload */ for (i = 0; i < payload_length; i++) { - pci_read_config_dword(pdev, offset + PCI_DOE_READ, - &task->response_pl[i]); + pci_read_config_dword(pdev, offset + PCI_DOE_READ, &val); + task->response_pl[i] = cpu_to_le32(val); /* Prior to the last ack, ensure Data Object Ready */ if (i == (payload_length - 1) && !pci_doe_data_obj_ready(doe_mb)) return -EIO; @@ -217,13 +217,14 @@ static int pci_doe_recv_resp(struct pci_doe_mb *doe_mb, struct pci_doe_task *tas if (FIELD_GET(PCI_DOE_STATUS_ERROR, val)) return -EIO; - return min(length, task->response_pl_sz / sizeof(u32)) * sizeof(u32); + return min(length, task->response_pl_sz / sizeof(__le32)) * sizeof(__le32); } static void signal_task_complete(struct pci_doe_task *task, int rv) { task->rv = rv; task->complete(task); + destroy_work_on_stack(&task->work); } static void signal_task_abort(struct pci_doe_task *task, int rv) @@ -317,14 +318,16 @@ static int pci_doe_discovery(struct pci_doe_mb *doe_mb, u8 *index, u16 *vid, { u32 request_pl = FIELD_PREP(PCI_DOE_DATA_OBJECT_DISC_REQ_3_INDEX, *index); + __le32 request_pl_le = cpu_to_le32(request_pl); + __le32 response_pl_le; u32 response_pl; DECLARE_COMPLETION_ONSTACK(c); struct pci_doe_task task = { .prot.vid = PCI_VENDOR_ID_PCI_SIG, .prot.type = PCI_DOE_PROTOCOL_DISCOVERY, - .request_pl = &request_pl, + .request_pl = &request_pl_le, .request_pl_sz = sizeof(request_pl), - .response_pl = &response_pl, + .response_pl = &response_pl_le, .response_pl_sz = sizeof(response_pl), .complete = pci_doe_task_complete, .private = &c, @@ -340,6 +343,7 @@ static int pci_doe_discovery(struct pci_doe_mb *doe_mb, u8 *index, u16 *vid, if (task.rv != sizeof(response_pl)) return -EIO; + response_pl = le32_to_cpu(response_pl_le); *vid = FIELD_GET(PCI_DOE_DATA_OBJECT_DISC_RSP_3_VID, response_pl); *protocol = FIELD_GET(PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL, response_pl); @@ -520,6 +524,8 @@ EXPORT_SYMBOL_GPL(pci_doe_supports_prot); * task->complete will be called when the state machine is done processing this * task. * + * @task must be allocated on the stack. + * * Excess data will be discarded. * * RETURNS: 0 when task has been successfully queued, -ERRNO on error @@ -533,15 +539,15 @@ int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task) * DOE requests must be a whole number of DW and the response needs to * be big enough for at least 1 DW */ - if (task->request_pl_sz % sizeof(u32) || - task->response_pl_sz < sizeof(u32)) + if (task->request_pl_sz % sizeof(__le32) || + task->response_pl_sz < sizeof(__le32)) return -EINVAL; if (test_bit(PCI_DOE_FLAG_DEAD, &doe_mb->flags)) return -EIO; task->doe_mb = doe_mb; - INIT_WORK(&task->work, doe_statemachine_work); + INIT_WORK_ONSTACK(&task->work, doe_statemachine_work); queue_work(doe_mb->work_queue, &task->work); return 0; } diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 0145aef1b930..22d39e12b236 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -157,8 +157,6 @@ void pci_remove_root_bus(struct pci_bus *bus) list_for_each_entry_safe(child, tmp, &bus->devices, bus_list) pci_remove_bus_device(child); - pci_remove_bus(bus); - host_bridge->bus = NULL; #ifdef CONFIG_PCI_DOMAINS_GENERIC /* Release domain_nr if it was dynamically allocated */ @@ -166,6 +164,9 @@ void pci_remove_root_bus(struct pci_bus *bus) pci_bus_release_domain_nr(bus, host_bridge->dev.parent); #endif + pci_remove_bus(bus); + host_bridge->bus = NULL; + /* remove the host bridge */ device_del(&host_bridge->dev); } diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 609821b756c2..9236a132c7ba 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -872,34 +872,32 @@ static const struct pinconf_ops amd_pinconf_ops = { .pin_config_group_set = amd_pinconf_group_set, }; -static void amd_gpio_irq_init_pin(struct amd_gpio *gpio_dev, int pin) +static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) { - const struct pin_desc *pd; + struct pinctrl_desc *desc = gpio_dev->pctrl->desc; unsigned long flags; u32 pin_reg, mask; + int i; mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3) | BIT(INTERRUPT_MASK_OFF) | BIT(INTERRUPT_ENABLE_OFF) | BIT(WAKE_CNTRL_OFF_S4); - pd = pin_desc_get(gpio_dev->pctrl, pin); - if (!pd) - return; + for (i = 0; i < desc->npins; i++) { + int pin = desc->pins[i].number; + const struct pin_desc *pd = pin_desc_get(gpio_dev->pctrl, pin); - raw_spin_lock_irqsave(&gpio_dev->lock, flags); - pin_reg = readl(gpio_dev->base + pin * 4); - pin_reg &= ~mask; - writel(pin_reg, gpio_dev->base + pin * 4); - raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); -} + if (!pd) + continue; -static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) -{ - struct pinctrl_desc *desc = gpio_dev->pctrl->desc; - int i; + raw_spin_lock_irqsave(&gpio_dev->lock, flags); - for (i = 0; i < desc->npins; i++) - amd_gpio_irq_init_pin(gpio_dev, i); + pin_reg = readl(gpio_dev->base + i * 4); + pin_reg &= ~mask; + writel(pin_reg, gpio_dev->base + i * 4); + + raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); + } } #ifdef CONFIG_PM_SLEEP @@ -952,10 +950,8 @@ static int amd_gpio_resume(struct device *dev) for (i = 0; i < desc->npins; i++) { int pin = desc->pins[i].number; - if (!amd_gpio_should_save(gpio_dev, pin)) { - amd_gpio_irq_init_pin(gpio_dev, pin); + if (!amd_gpio_should_save(gpio_dev, pin)) continue; - } raw_spin_lock_irqsave(&gpio_dev->lock, flags); gpio_dev->saved_regs[i] |= readl(gpio_dev->base + pin * 4) & PIN_IRQ_PENDING; diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index c76f82fb8b63..15f452908926 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -771,13 +771,12 @@ static int iscsi_sw_tcp_conn_set_param(struct iscsi_cls_conn *cls_conn, iscsi_set_param(cls_conn, param, buf, buflen); break; case ISCSI_PARAM_DATADGST_EN: - iscsi_set_param(cls_conn, param, buf, buflen); - mutex_lock(&tcp_sw_conn->sock_lock); if (!tcp_sw_conn->sock) { mutex_unlock(&tcp_sw_conn->sock_lock); return -ENOTCONN; } + iscsi_set_param(cls_conn, param, buf, buflen); tcp_sw_conn->sendpage = conn->datadgst_en ? sock_no_sendpage : tcp_sw_conn->sock->ops->sendpage; mutex_unlock(&tcp_sw_conn->sock_lock); diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index a565817aa56d..d109a4ceb72b 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -2526,7 +2526,7 @@ static void mpi3mr_watchdog_work(struct work_struct *work) mrioc->unrecoverable = 1; goto schedule_work; case MPI3_SYSIF_FAULT_CODE_SOFT_RESET_IN_PROGRESS: - return; + goto schedule_work; case MPI3_SYSIF_FAULT_CODE_CI_ACTIVATION_RESET: reset_reason = MPI3MR_RESET_FROM_CIACTIV_FAULT; break; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index bee1b8a82020..d0cdbfe771a9 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3617,6 +3617,7 @@ skip_dpc: probe_failed: qla_enode_stop(base_vha); qla_edb_stop(base_vha); + vfree(base_vha->scan.l); if (base_vha->gnl.l) { dma_free_coherent(&ha->pdev->dev, base_vha->gnl.size, base_vha->gnl.l, base_vha->gnl.ldma); diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 44b85a8d47f1..7bc14fb309a6 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -4456,6 +4456,11 @@ static int of_spi_notify(struct notifier_block *nb, unsigned long action, return NOTIFY_OK; } + /* + * Clear the flag before adding the device so that fw_devlink + * doesn't skip adding consumers to this device. + */ + rd->dn->fwnode.flags &= ~FWNODE_FLAG_NOT_DEVICE; spi = of_register_spi_device(ctlr, rd->dn); put_device(&ctlr->dev); diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index fa43df05342b..3ba9c8b93ae6 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1903,6 +1903,17 @@ EXPORT_SYMBOL_GPL(serial8250_modem_status); static bool handle_rx_dma(struct uart_8250_port *up, unsigned int iir) { switch (iir & 0x3f) { + case UART_IIR_THRI: + /* + * Postpone DMA or not decision to IIR_RDI or IIR_RX_TIMEOUT + * because it's impossible to do an informed decision about + * that with IIR_THRI. + * + * This also fixes one known DMA Rx corruption issue where + * DR is asserted but DMA Rx only gets a corrupted zero byte + * (too early DR?). + */ + return false; case UART_IIR_RDI: if (!up->dma->rx_running) break; diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 56e6ba3250cd..074bfed57fc9 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -858,11 +858,17 @@ static unsigned int lpuart32_tx_empty(struct uart_port *port) struct lpuart_port, port); unsigned long stat = lpuart32_read(port, UARTSTAT); unsigned long sfifo = lpuart32_read(port, UARTFIFO); + unsigned long ctrl = lpuart32_read(port, UARTCTRL); if (sport->dma_tx_in_progress) return 0; - if (stat & UARTSTAT_TC && sfifo & UARTFIFO_TXEMPT) + /* + * LPUART Transmission Complete Flag may never be set while queuing a break + * character, so avoid checking for transmission complete when UARTCTRL_SBK + * is asserted. + */ + if ((stat & UARTSTAT_TC && sfifo & UARTFIFO_TXEMPT) || ctrl & UARTCTRL_SBK) return TIOCSER_TEMT; return 0; @@ -2942,7 +2948,7 @@ static bool lpuart_uport_is_active(struct lpuart_port *sport) tty = tty_port_tty_get(port); if (tty) { tty_dev = tty->dev; - may_wake = device_may_wakeup(tty_dev); + may_wake = tty_dev && device_may_wakeup(tty_dev); tty_kref_put(tty); } diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 7bd080720929..caa09a0c48f4 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -2864,6 +2865,13 @@ static int sci_init_single(struct platform_device *dev, sci_port->irqs[i] = platform_get_irq(dev, i); } + /* + * The fourth interrupt on SCI port is transmit end interrupt, so + * shuffle the interrupts. + */ + if (p->type == PORT_SCI) + swap(sci_port->irqs[SCIx_BRI_IRQ], sci_port->irqs[SCIx_TEI_IRQ]); + /* The SCI generates several interrupts. They can be muxed together or * connected to different interrupt lines. In the muxed case only one * interrupt resource is specified as there is only one interrupt ID. @@ -2929,7 +2937,7 @@ static int sci_init_single(struct platform_device *dev, port->flags = UPF_FIXED_PORT | UPF_BOOT_AUTOCONF | p->flags; port->fifosize = sci_port->params->fifosize; - if (port->type == PORT_SCI) { + if (port->type == PORT_SCI && !dev->dev.of_node) { if (sci_port->reg_size >= 0x20) port->regshift = 2; else diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 37e178a9ac47..70b112038792 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -1409,13 +1409,6 @@ static int ufshcd_devfreq_target(struct device *dev, struct ufs_clk_info *clki; unsigned long irq_flags; - /* - * Skip devfreq if UFS initialization is not finished. - * Otherwise ufs could be in a inconsistent state. - */ - if (!smp_load_acquire(&hba->logical_unit_scan_finished)) - return 0; - if (!ufshcd_is_clkscaling_supported(hba)) return -EINVAL; @@ -8399,6 +8392,22 @@ static int ufshcd_add_lus(struct ufs_hba *hba) if (ret) goto out; + /* Initialize devfreq after UFS device is detected */ + if (ufshcd_is_clkscaling_supported(hba)) { + memcpy(&hba->clk_scaling.saved_pwr_info.info, + &hba->pwr_info, + sizeof(struct ufs_pa_layer_attr)); + hba->clk_scaling.saved_pwr_info.is_valid = true; + hba->clk_scaling.is_allowed = true; + + ret = ufshcd_devfreq_init(hba); + if (ret) + goto out; + + hba->clk_scaling.is_enabled = true; + ufshcd_init_clk_scaling_sysfs(hba); + } + ufs_bsg_probe(hba); ufshpb_init(hba); scsi_scan_host(hba->host); @@ -8670,12 +8679,6 @@ out: if (ret) { pm_runtime_put_sync(hba->dev); ufshcd_hba_exit(hba); - } else { - /* - * Make sure that when reader code sees UFS initialization has finished, - * all initialization steps have really been executed. - */ - smp_store_release(&hba->logical_unit_scan_finished, true); } } @@ -10316,30 +10319,12 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) */ ufshcd_set_ufs_dev_active(hba); - /* Initialize devfreq */ - if (ufshcd_is_clkscaling_supported(hba)) { - memcpy(&hba->clk_scaling.saved_pwr_info.info, - &hba->pwr_info, - sizeof(struct ufs_pa_layer_attr)); - hba->clk_scaling.saved_pwr_info.is_valid = true; - hba->clk_scaling.is_allowed = true; - - err = ufshcd_devfreq_init(hba); - if (err) - goto rpm_put_sync; - - hba->clk_scaling.is_enabled = true; - ufshcd_init_clk_scaling_sysfs(hba); - } - async_schedule(ufshcd_async_scan, hba); ufs_sysfs_add_nodes(hba->dev); device_enable_async_suspend(dev); return 0; -rpm_put_sync: - pm_runtime_put_sync(dev); free_tmf_queue: blk_mq_destroy_queue(hba->tmf_queue); blk_put_queue(hba->tmf_queue); diff --git a/drivers/usb/cdns3/cdnsp-ep0.c b/drivers/usb/cdns3/cdnsp-ep0.c index d63d5d92f255..f317d3c84781 100644 --- a/drivers/usb/cdns3/cdnsp-ep0.c +++ b/drivers/usb/cdns3/cdnsp-ep0.c @@ -414,7 +414,7 @@ static int cdnsp_ep0_std_request(struct cdnsp_device *pdev, void cdnsp_setup_analyze(struct cdnsp_device *pdev) { struct usb_ctrlrequest *ctrl = &pdev->setup; - int ret = 0; + int ret = -EINVAL; u16 len; trace_cdnsp_ctrl_req(ctrl); @@ -424,7 +424,6 @@ void cdnsp_setup_analyze(struct cdnsp_device *pdev) if (pdev->gadget.state == USB_STATE_NOTATTACHED) { dev_err(pdev->dev, "ERR: Setup detected in unattached state\n"); - ret = -EINVAL; goto out; } diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index a23ddbb81979..560793545362 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -49,6 +49,7 @@ #define PCI_DEVICE_ID_INTEL_RPLS 0x7a61 #define PCI_DEVICE_ID_INTEL_MTLM 0x7eb1 #define PCI_DEVICE_ID_INTEL_MTLP 0x7ec1 +#define PCI_DEVICE_ID_INTEL_MTLS 0x7f6f #define PCI_DEVICE_ID_INTEL_MTL 0x7e7e #define PCI_DEVICE_ID_INTEL_TGL 0x9a15 #define PCI_DEVICE_ID_AMD_MR 0x163a @@ -474,6 +475,9 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTLP), (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTLS), + (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTL), (kernel_ulong_t) &dwc3_pci_intel_swnode, }, diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index ddfc537c7526..56cdfb2e4211 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1251,7 +1251,7 @@ static ssize_t ffs_epfile_read_iter(struct kiocb *kiocb, struct iov_iter *to) p->kiocb = kiocb; if (p->aio) { p->to_free = dup_iter(&p->data, to, GFP_KERNEL); - if (!p->to_free) { + if (!iter_is_ubuf(&p->data) && !p->to_free) { kfree(p); return -ENOMEM; } diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index d605bc2e7e8f..28249d0bf062 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -614,7 +614,7 @@ ep_read_iter(struct kiocb *iocb, struct iov_iter *to) if (!priv) goto fail; priv->to_free = dup_iter(&priv->to, to, GFP_KERNEL); - if (!priv->to_free) { + if (!iter_is_ubuf(&priv->to) && !priv->to_free) { kfree(priv); goto fail; } diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index fb988e4ea924..6db07ca419c3 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -771,12 +771,11 @@ static struct pci_driver xhci_pci_driver = { /* suspend and resume implemented later */ .shutdown = usb_hcd_pci_shutdown, - .driver = { #ifdef CONFIG_PM - .pm = &usb_hcd_pci_pm_ops, -#endif - .probe_type = PROBE_PREFER_ASYNCHRONOUS, + .driver = { + .pm = &usb_hcd_pci_pm_ops }, +#endif }; static int __init xhci_pci_init(void) diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 1ff22f675930..a88c39e525c2 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1360,6 +1360,9 @@ static void tegra_xhci_id_work(struct work_struct *work) mutex_unlock(&tegra->lock); + tegra->otg_usb3_port = tegra_xusb_padctl_get_usb3_companion(tegra->padctl, + tegra->otg_usb2_port); + if (tegra->host_mode) { /* switch to host mode */ if (tegra->otg_usb3_port >= 0) { @@ -1474,9 +1477,6 @@ static int tegra_xhci_id_notify(struct notifier_block *nb, } tegra->otg_usb2_port = tegra_xusb_get_usb2_port(tegra, usbphy); - tegra->otg_usb3_port = tegra_xusb_padctl_get_usb3_companion( - tegra->padctl, - tegra->otg_usb2_port); tegra->host_mode = (usbphy->last_event == USB_EVENT_ID) ? true : false; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 6183ce8574b1..6307bae9cddf 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -9,6 +9,7 @@ */ #include +#include #include #include #include @@ -228,6 +229,7 @@ int xhci_reset(struct xhci_hcd *xhci, u64 timeout_us) static void xhci_zero_64b_regs(struct xhci_hcd *xhci) { struct device *dev = xhci_to_hcd(xhci)->self.sysdev; + struct iommu_domain *domain; int err, i; u64 val; u32 intrs; @@ -246,7 +248,9 @@ static void xhci_zero_64b_regs(struct xhci_hcd *xhci) * an iommu. Doing anything when there is no iommu is definitely * unsafe... */ - if (!(xhci->quirks & XHCI_ZERO_64B_REGS) || !device_iommu_mapped(dev)) + domain = iommu_get_domain_for_dev(dev); + if (!(xhci->quirks & XHCI_ZERO_64B_REGS) || !domain || + domain->type == IOMMU_DOMAIN_IDENTITY) return; xhci_info(xhci, "Zeroing 64bit base registers, expecting fault\n"); @@ -4438,6 +4442,7 @@ static int __maybe_unused xhci_change_max_exit_latency(struct xhci_hcd *xhci, if (!virt_dev || max_exit_latency == virt_dev->current_mel) { spin_unlock_irqrestore(&xhci->lock, flags); + xhci_free_command(xhci, command); return 0; } diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 832ad592b7ef..cdea1bff3b70 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -120,6 +120,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x826B) }, /* Cygnal Integrated Products, Inc., Fasttrax GPS demonstration module */ { USB_DEVICE(0x10C4, 0x8281) }, /* Nanotec Plug & Drive */ { USB_DEVICE(0x10C4, 0x8293) }, /* Telegesis ETRX2USB */ + { USB_DEVICE(0x10C4, 0x82AA) }, /* Silicon Labs IFS-USB-DATACABLE used with Quint UPS */ { USB_DEVICE(0x10C4, 0x82EF) }, /* CESINEL FALCO 6105 AC Power Supply */ { USB_DEVICE(0x10C4, 0x82F1) }, /* CESINEL MEDCAL EFD Earth Fault Detector */ { USB_DEVICE(0x10C4, 0x82F2) }, /* CESINEL MEDCAL ST Network Analyzer */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index e6d8d9b35ad0..f31cc3c76329 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1198,6 +1198,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, 0x0900, 0xff, 0, 0), /* RM500U-CN */ + .driver_info = ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200U, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200S_CN, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) }, @@ -1300,6 +1302,14 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff), /* Telit FN990 (PCIe) */ .driver_info = RSVD(0) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1080, 0xff), /* Telit FE990 (rmnet) */ + .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1081, 0xff), /* Telit FE990 (MBIM) */ + .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1082, 0xff), /* Telit FE990 (RNDIS) */ + .driver_info = NCTRL(2) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1083, 0xff), /* Telit FE990 (ECM) */ + .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 662cd043b50e..8f3e884222ad 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -112,8 +112,12 @@ static int dp_altmode_configure(struct dp_altmode *dp, u8 con) if (dp->data.status & DP_STATUS_PREFER_MULTI_FUNC && pin_assign & DP_PIN_ASSIGN_MULTI_FUNC_MASK) pin_assign &= DP_PIN_ASSIGN_MULTI_FUNC_MASK; - else if (pin_assign & DP_PIN_ASSIGN_DP_ONLY_MASK) + else if (pin_assign & DP_PIN_ASSIGN_DP_ONLY_MASK) { pin_assign &= DP_PIN_ASSIGN_DP_ONLY_MASK; + /* Default to pin assign C if available */ + if (pin_assign & BIT(DP_PIN_ASSIGN_C)) + pin_assign = BIT(DP_PIN_ASSIGN_C); + } if (!pin_assign) return -EINVAL; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 520646ae7fa0..195963b82b63 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -2467,10 +2467,11 @@ static int setup_driver(struct mlx5_vdpa_dev *mvdev) err = 0; goto out; } + mlx5_vdpa_add_debugfs(ndev); err = setup_virtqueues(mvdev); if (err) { mlx5_vdpa_warn(mvdev, "setup_virtqueues\n"); - goto out; + goto err_setup; } err = create_rqt(ndev); @@ -2500,6 +2501,8 @@ err_tir: destroy_rqt(ndev); err_rqt: teardown_virtqueues(ndev); +err_setup: + mlx5_vdpa_remove_debugfs(ndev->debugfs); out: return err; } @@ -2513,6 +2516,8 @@ static void teardown_driver(struct mlx5_vdpa_net *ndev) if (!ndev->setup) return; + mlx5_vdpa_remove_debugfs(ndev->debugfs); + ndev->debugfs = NULL; teardown_steering(ndev); destroy_tir(ndev); destroy_rqt(ndev); @@ -3261,7 +3266,6 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, if (err) goto err_reg; - mlx5_vdpa_add_debugfs(ndev); mgtdev->ndev = ndev; return 0; diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c index 862f405362de..dfe2ce341803 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c @@ -466,16 +466,21 @@ static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, vdpasim_net_setup_config(simdev, config); - ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_NET_VQ_NUM); - if (ret) - goto reg_err; - net = sim_to_net(simdev); u64_stats_init(&net->tx_stats.syncp); u64_stats_init(&net->rx_stats.syncp); u64_stats_init(&net->cq_stats.syncp); + /* + * Initialization must be completed before this call, since it can + * connect the device to the vDPA bus, so requests can arrive after + * this call. + */ + ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_NET_VQ_NUM); + if (ret) + goto reg_err; + return 0; reg_err: diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index b244e7c0f514..32d0be968103 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -125,7 +125,6 @@ struct vhost_scsi_tpg { struct se_portal_group se_tpg; /* Pointer back to vhost_scsi, protected by tv_tpg_mutex */ struct vhost_scsi *vhost_scsi; - struct list_head tmf_queue; }; struct vhost_scsi_tport { @@ -206,10 +205,8 @@ struct vhost_scsi { struct vhost_scsi_tmf { struct vhost_work vwork; - struct vhost_scsi_tpg *tpg; struct vhost_scsi *vhost; struct vhost_scsi_virtqueue *svq; - struct list_head queue_entry; struct se_cmd se_cmd; u8 scsi_resp; @@ -352,12 +349,9 @@ static void vhost_scsi_release_cmd_res(struct se_cmd *se_cmd) static void vhost_scsi_release_tmf_res(struct vhost_scsi_tmf *tmf) { - struct vhost_scsi_tpg *tpg = tmf->tpg; struct vhost_scsi_inflight *inflight = tmf->inflight; - mutex_lock(&tpg->tv_tpg_mutex); - list_add_tail(&tpg->tmf_queue, &tmf->queue_entry); - mutex_unlock(&tpg->tv_tpg_mutex); + kfree(tmf); vhost_scsi_put_inflight(inflight); } @@ -1194,19 +1188,11 @@ vhost_scsi_handle_tmf(struct vhost_scsi *vs, struct vhost_scsi_tpg *tpg, goto send_reject; } - mutex_lock(&tpg->tv_tpg_mutex); - if (list_empty(&tpg->tmf_queue)) { - pr_err("Missing reserve TMF. Could not handle LUN RESET.\n"); - mutex_unlock(&tpg->tv_tpg_mutex); + tmf = kzalloc(sizeof(*tmf), GFP_KERNEL); + if (!tmf) goto send_reject; - } - tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf, - queue_entry); - list_del_init(&tmf->queue_entry); - mutex_unlock(&tpg->tv_tpg_mutex); - - tmf->tpg = tpg; + vhost_work_init(&tmf->vwork, vhost_scsi_tmf_resp_work); tmf->vhost = vs; tmf->svq = svq; tmf->resp_iov = vq->iov[vc->out]; @@ -1658,7 +1644,10 @@ undepend: for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) { tpg = vs_tpg[i]; if (tpg) { + mutex_lock(&tpg->tv_tpg_mutex); + tpg->vhost_scsi = NULL; tpg->tv_tpg_vhost_count--; + mutex_unlock(&tpg->tv_tpg_mutex); target_undepend_item(&tpg->se_tpg.tpg_group.cg_item); } } @@ -2032,19 +2021,11 @@ static int vhost_scsi_port_link(struct se_portal_group *se_tpg, { struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); - struct vhost_scsi_tmf *tmf; - - tmf = kzalloc(sizeof(*tmf), GFP_KERNEL); - if (!tmf) - return -ENOMEM; - INIT_LIST_HEAD(&tmf->queue_entry); - vhost_work_init(&tmf->vwork, vhost_scsi_tmf_resp_work); mutex_lock(&vhost_scsi_mutex); mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count++; - list_add_tail(&tmf->queue_entry, &tpg->tmf_queue); mutex_unlock(&tpg->tv_tpg_mutex); vhost_scsi_hotplug(tpg, lun); @@ -2059,16 +2040,11 @@ static void vhost_scsi_port_unlink(struct se_portal_group *se_tpg, { struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); - struct vhost_scsi_tmf *tmf; mutex_lock(&vhost_scsi_mutex); mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count--; - tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf, - queue_entry); - list_del(&tmf->queue_entry); - kfree(tmf); mutex_unlock(&tpg->tv_tpg_mutex); vhost_scsi_hotunplug(tpg, lun); @@ -2329,7 +2305,6 @@ vhost_scsi_make_tpg(struct se_wwn *wwn, const char *name) } mutex_init(&tpg->tv_tpg_mutex); INIT_LIST_HEAD(&tpg->tv_tpg_list); - INIT_LIST_HEAD(&tpg->tmf_queue); tpg->tport = tport; tpg->tport_tpgt = tpgt; diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 0a2c47df01f4..eb565a10e5cd 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -823,7 +823,7 @@ static int set_con2fb_map(int unit, int newidx, int user) int oldidx = con2fb_map[unit]; struct fb_info *info = fbcon_registered_fb[newidx]; struct fb_info *oldinfo = NULL; - int found, err = 0, show_logo; + int err = 0, show_logo; WARN_CONSOLE_UNLOCKED(); @@ -841,26 +841,26 @@ static int set_con2fb_map(int unit, int newidx, int user) if (oldidx != -1) oldinfo = fbcon_registered_fb[oldidx]; - found = search_fb_in_map(newidx); - - if (!err && !found) { + if (!search_fb_in_map(newidx)) { err = con2fb_acquire_newinfo(vc, info, unit); - if (!err) - con2fb_map[unit] = newidx; + if (err) + return err; + + fbcon_add_cursor_work(info); } + con2fb_map[unit] = newidx; + /* * If old fb is not mapped to any of the consoles, * fbcon should release it. */ - if (!err && oldinfo && !search_fb_in_map(oldidx)) + if (oldinfo && !search_fb_in_map(oldidx)) con2fb_release_oldinfo(vc, oldinfo, info); show_logo = (fg_console == 0 && !user && logo_shown != FBCON_LOGO_DONTSHOW); - if (!found) - fbcon_add_cursor_work(info); con2fb_map_boot[unit] = newidx; con2fb_init_display(vc, info, unit, show_logo); diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 875541ff185b..3fd95a79e4c3 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1116,6 +1116,8 @@ static long do_fb_ioctl(struct fb_info *info, unsigned int cmd, case FBIOPUT_VSCREENINFO: if (copy_from_user(&var, argp, sizeof(var))) return -EFAULT; + /* only for kernel-internal use */ + var.activate &= ~FB_ACTIVATE_KD_TEXT; console_lock(); lock_fb_info(info); ret = fbcon_modechange_possible(info, &var); diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index 50f7f3f6b55e..1974a38bce20 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -35,10 +35,12 @@ ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name, return retval; } if (attr_size > buffer_size) { - if (!buffer_size) /* request to get the attr_size */ - retval = attr_size; - else + if (buffer_size) retval = -ERANGE; + else if (attr_size > SSIZE_MAX) + retval = -EOVERFLOW; + else /* request to get the attr_size */ + retval = attr_size; } else { iov_iter_truncate(&to, attr_size); retval = p9_client_read(attr_fid, 0, &to, &err); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b53f0e30ce2b..9e1596bb208d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2250,6 +2250,20 @@ static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type) fs_info->csum_shash = csum_shash; + /* + * Check if the checksum implementation is a fast accelerated one. + * As-is this is a bit of a hack and should be replaced once the csum + * implementations provide that information themselves. + */ + switch (csum_type) { + case BTRFS_CSUM_TYPE_CRC32: + if (!strstr(crypto_shash_driver_name(csum_shash), "generic")) + set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); + break; + default: + break; + } + btrfs_info(fs_info, "using %s (%s) checksum algorithm", btrfs_super_csum_name(csum_type), crypto_shash_driver_name(csum_shash)); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 581845bc206a..366fb4cde145 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1516,8 +1516,6 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", fs_type->name, s->s_id); btrfs_sb(s)->bdev_holder = fs_type; - if (!strstr(crc32c_impl(), "generic")) - set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); error = btrfs_fill_super(s, fs_devices, data); } if (!error) @@ -1631,6 +1629,8 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info, btrfs_workqueue_set_max(fs_info->hipri_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size); + workqueue_set_max_active(fs_info->endio_workers, new_pool_size); + workqueue_set_max_active(fs_info->endio_meta_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->endio_write_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->endio_freespace_worker, new_pool_size); btrfs_workqueue_set_max(fs_info->delayed_workers, new_pool_size); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 0d30b17494e4..9d963caec35c 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -120,7 +120,7 @@ again: spin_lock(&server->srv_lock); if (server->tcpStatus == CifsNeedReconnect) { spin_unlock(&server->srv_lock); - mutex_lock(&ses->session_mutex); + mutex_unlock(&ses->session_mutex); if (tcon->retry) goto again; diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 6d13f8207e96..ace11a1a7c8a 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -441,13 +441,14 @@ out: * but there are some bugs that prevent rename from working if there are * multiple delimiters. * - * Returns a sanitized duplicate of @path. The caller is responsible for - * cleaning up the original. + * Returns a sanitized duplicate of @path. @gfp indicates the GFP_* flags + * for kstrdup. + * The caller is responsible for freeing the original. */ #define IS_DELIM(c) ((c) == '/' || (c) == '\\') -static char *sanitize_path(char *path) +char *cifs_sanitize_prepath(char *prepath, gfp_t gfp) { - char *cursor1 = path, *cursor2 = path; + char *cursor1 = prepath, *cursor2 = prepath; /* skip all prepended delimiters */ while (IS_DELIM(*cursor1)) @@ -469,7 +470,7 @@ static char *sanitize_path(char *path) cursor2--; *(cursor2) = '\0'; - return kstrdup(path, GFP_KERNEL); + return kstrdup(prepath, gfp); } /* @@ -531,7 +532,7 @@ smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx) if (!*pos) return 0; - ctx->prepath = sanitize_path(pos); + ctx->prepath = cifs_sanitize_prepath(pos, GFP_KERNEL); if (!ctx->prepath) return -ENOMEM; diff --git a/fs/cifs/fs_context.h b/fs/cifs/fs_context.h index 3de00e7127ec..f4eaf8558902 100644 --- a/fs/cifs/fs_context.h +++ b/fs/cifs/fs_context.h @@ -287,4 +287,7 @@ extern void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb); */ #define SMB3_MAX_DCLOSETIMEO (1 << 30) #define SMB3_DEF_DCLOSETIMEO (1 * HZ) /* even 1 sec enough to help eg open/write/close/open/read */ + +extern char *cifs_sanitize_prepath(char *prepath, gfp_t gfp); + #endif diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index b44fb51968bf..7f085ed2d866 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -1195,7 +1195,7 @@ int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix) kfree(cifs_sb->prepath); if (prefix && *prefix) { - cifs_sb->prepath = kstrdup(prefix, GFP_ATOMIC); + cifs_sb->prepath = cifs_sanitize_prepath(prefix, GFP_ATOMIC); if (!cifs_sb->prepath) return -ENOMEM; diff --git a/fs/dax.c b/fs/dax.c index 3e457a16c7d1..2ababb89918d 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -781,6 +781,33 @@ out: return ret; } +static int __dax_clear_dirty_range(struct address_space *mapping, + pgoff_t start, pgoff_t end) +{ + XA_STATE(xas, &mapping->i_pages, start); + unsigned int scanned = 0; + void *entry; + + xas_lock_irq(&xas); + xas_for_each(&xas, entry, end) { + entry = get_unlocked_entry(&xas, 0); + xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); + xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); + put_unlocked_entry(&xas, entry, WAKE_NEXT); + + if (++scanned % XA_CHECK_SCHED) + continue; + + xas_pause(&xas); + xas_unlock_irq(&xas); + cond_resched(); + xas_lock_irq(&xas); + } + xas_unlock_irq(&xas); + + return 0; +} + /* * Delete DAX entry at @index from @mapping. Wait for it * to be unlocked before deleting it. @@ -1258,15 +1285,20 @@ static s64 dax_unshare_iter(struct iomap_iter *iter) /* don't bother with blocks that are not shared to start with */ if (!(iomap->flags & IOMAP_F_SHARED)) return length; - /* don't bother with holes or unwritten extents */ - if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) - return length; id = dax_read_lock(); ret = dax_iomap_direct_access(iomap, pos, length, &daddr, NULL); if (ret < 0) goto out_unlock; + /* zero the distance if srcmap is HOLE or UNWRITTEN */ + if (srcmap->flags & IOMAP_F_SHARED || srcmap->type == IOMAP_UNWRITTEN) { + memset(daddr, 0, length); + dax_flush(iomap->dax_dev, daddr, length); + ret = length; + goto out_unlock; + } + ret = dax_iomap_direct_access(srcmap, pos, length, &saddr, NULL); if (ret < 0) goto out_unlock; @@ -1435,6 +1467,16 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, * written by write(2) is visible in mmap. */ if (iomap->flags & IOMAP_F_NEW || cow) { + /* + * Filesystem allows CoW on non-shared extents. The src extents + * may have been mmapped with dirty mark before. To be able to + * invalidate its dax entries, we need to clear the dirty mark + * in advance. + */ + if (cow) + __dax_clear_dirty_range(iomi->inode->i_mapping, + pos >> PAGE_SHIFT, + (end - 1) >> PAGE_SHIFT); invalidate_inode_pages2_range(iomi->inode->i_mapping, pos >> PAGE_SHIFT, (end - 1) >> PAGE_SHIFT); @@ -2022,8 +2064,8 @@ int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, while ((ret = iomap_iter(&src_iter, ops)) > 0 && (ret = iomap_iter(&dst_iter, ops)) > 0) { - compared = dax_range_compare_iter(&src_iter, &dst_iter, len, - same); + compared = dax_range_compare_iter(&src_iter, &dst_iter, + min(src_iter.len, dst_iter.len), same); if (compared < 0) return ret; src_iter.processed = dst_iter.processed = compared; diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index 115a67d2cf78..365ac32af505 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -112,10 +112,8 @@ void ksmbd_conn_enqueue_request(struct ksmbd_work *work) struct ksmbd_conn *conn = work->conn; struct list_head *requests_queue = NULL; - if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) { + if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) requests_queue = &conn->requests; - work->synchronous = true; - } if (requests_queue) { atomic_inc(&conn->req_running); @@ -136,14 +134,14 @@ int ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) if (!work->multiRsp) atomic_dec(&conn->req_running); - spin_lock(&conn->request_lock); if (!work->multiRsp) { + spin_lock(&conn->request_lock); list_del_init(&work->request_entry); - if (!work->synchronous) - list_del_init(&work->async_request_entry); + spin_unlock(&conn->request_lock); + if (work->asynchronous) + release_async_work(work); ret = 0; } - spin_unlock(&conn->request_lock); wake_up_all(&conn->req_running_q); return ret; @@ -326,10 +324,7 @@ int ksmbd_conn_handler_loop(void *p) /* 4 for rfc1002 length field */ size = pdu_size + 4; - conn->request_buf = kvmalloc(size, - GFP_KERNEL | - __GFP_NOWARN | - __GFP_NORETRY); + conn->request_buf = kvmalloc(size, GFP_KERNEL); if (!conn->request_buf) break; diff --git a/fs/ksmbd/ksmbd_work.h b/fs/ksmbd/ksmbd_work.h index 3234f2cf6327..f8ae6144c0ae 100644 --- a/fs/ksmbd/ksmbd_work.h +++ b/fs/ksmbd/ksmbd_work.h @@ -68,7 +68,7 @@ struct ksmbd_work { /* Request is encrypted */ bool encrypted:1; /* Is this SYNC or ASYNC ksmbd_work */ - bool synchronous:1; + bool asynchronous:1; bool need_invalidate_rkey:1; unsigned int remote_key; diff --git a/fs/ksmbd/server.c b/fs/ksmbd/server.c index 394b6ceac431..0d8242789dc8 100644 --- a/fs/ksmbd/server.c +++ b/fs/ksmbd/server.c @@ -289,10 +289,7 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn) work->request_buf = conn->request_buf; conn->request_buf = NULL; - if (ksmbd_init_smb_server(work)) { - ksmbd_free_work_struct(work); - return -EINVAL; - } + ksmbd_init_smb_server(work); ksmbd_conn_enqueue_request(work); atomic_inc(&conn->r_count); diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 97c9d1b5bcc0..8af939a181be 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -229,9 +229,6 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) struct smb2_negotiate_rsp *rsp; struct ksmbd_conn *conn = work->conn; - if (conn->need_neg == false) - return -EINVAL; - *(__be32 *)work->response_buf = cpu_to_be32(conn->vals->header_size); @@ -498,12 +495,6 @@ int init_smb2_rsp_hdr(struct ksmbd_work *work) rsp_hdr->SessionId = rcv_hdr->SessionId; memcpy(rsp_hdr->Signature, rcv_hdr->Signature, 16); - work->synchronous = true; - if (work->async_id) { - ksmbd_release_id(&conn->async_ida, work->async_id); - work->async_id = 0; - } - return 0; } @@ -644,7 +635,7 @@ int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg) pr_err("Failed to alloc async message id\n"); return id; } - work->synchronous = false; + work->asynchronous = true; work->async_id = id; rsp_hdr->Id.AsyncId = cpu_to_le64(id); @@ -664,6 +655,24 @@ int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg) return 0; } +void release_async_work(struct ksmbd_work *work) +{ + struct ksmbd_conn *conn = work->conn; + + spin_lock(&conn->request_lock); + list_del_init(&work->async_request_entry); + spin_unlock(&conn->request_lock); + + work->asynchronous = 0; + work->cancel_fn = NULL; + kfree(work->cancel_argv); + work->cancel_argv = NULL; + if (work->async_id) { + ksmbd_release_id(&conn->async_ida, work->async_id); + work->async_id = 0; + } +} + void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status) { struct smb2_hdr *rsp_hdr; @@ -7045,13 +7054,9 @@ skip: ksmbd_vfs_posix_lock_wait(flock); - spin_lock(&work->conn->request_lock); spin_lock(&fp->f_lock); list_del(&work->fp_entry); - work->cancel_fn = NULL; - kfree(argv); spin_unlock(&fp->f_lock); - spin_unlock(&work->conn->request_lock); if (work->state != KSMBD_WORK_ACTIVE) { list_del(&smb_lock->llist); @@ -7069,6 +7074,7 @@ skip: work->send_no_response = 1; goto out; } + init_smb2_rsp_hdr(work); smb2_set_err_rsp(work); rsp->hdr.Status = @@ -7081,7 +7087,7 @@ skip: spin_lock(&work->conn->llist_lock); list_del(&smb_lock->clist); spin_unlock(&work->conn->llist_lock); - + release_async_work(work); goto retry; } else if (!rc) { spin_lock(&work->conn->llist_lock); diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index 0c8a770fe318..9420dd2813fb 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -486,6 +486,7 @@ int find_matching_smb2_dialect(int start_index, __le16 *cli_dialects, struct file_lock *smb_flock_init(struct file *f); int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg); +void release_async_work(struct ksmbd_work *work); void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status); struct channel *lookup_chann_list(struct ksmbd_session *sess, struct ksmbd_conn *conn); diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c index 9c1ce6d199ce..af0c2a9b8529 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/ksmbd/smb_common.c @@ -283,20 +283,121 @@ err_out: return BAD_PROT_ID; } -int ksmbd_init_smb_server(struct ksmbd_work *work) -{ - struct ksmbd_conn *conn = work->conn; +#define SMB_COM_NEGOTIATE_EX 0x0 - if (conn->need_neg == false) +/** + * get_smb1_cmd_val() - get smb command value from smb header + * @work: smb work containing smb header + * + * Return: smb command value + */ +static u16 get_smb1_cmd_val(struct ksmbd_work *work) +{ + return SMB_COM_NEGOTIATE_EX; +} + +/** + * init_smb1_rsp_hdr() - initialize smb negotiate response header + * @work: smb work containing smb request + * + * Return: 0 on success, otherwise -EINVAL + */ +static int init_smb1_rsp_hdr(struct ksmbd_work *work) +{ + struct smb_hdr *rsp_hdr = (struct smb_hdr *)work->response_buf; + struct smb_hdr *rcv_hdr = (struct smb_hdr *)work->request_buf; + + /* + * Remove 4 byte direct TCP header. + */ + *(__be32 *)work->response_buf = + cpu_to_be32(sizeof(struct smb_hdr) - 4); + + rsp_hdr->Command = SMB_COM_NEGOTIATE; + *(__le32 *)rsp_hdr->Protocol = SMB1_PROTO_NUMBER; + rsp_hdr->Flags = SMBFLG_RESPONSE; + rsp_hdr->Flags2 = SMBFLG2_UNICODE | SMBFLG2_ERR_STATUS | + SMBFLG2_EXT_SEC | SMBFLG2_IS_LONG_NAME; + rsp_hdr->Pid = rcv_hdr->Pid; + rsp_hdr->Mid = rcv_hdr->Mid; + return 0; +} + +/** + * smb1_check_user_session() - check for valid session for a user + * @work: smb work containing smb request buffer + * + * Return: 0 on success, otherwise error + */ +static int smb1_check_user_session(struct ksmbd_work *work) +{ + unsigned int cmd = work->conn->ops->get_cmd_val(work); + + if (cmd == SMB_COM_NEGOTIATE_EX) return 0; - init_smb3_11_server(conn); + return -EINVAL; +} + +/** + * smb1_allocate_rsp_buf() - allocate response buffer for a command + * @work: smb work containing smb request + * + * Return: 0 on success, otherwise -ENOMEM + */ +static int smb1_allocate_rsp_buf(struct ksmbd_work *work) +{ + work->response_buf = kmalloc(MAX_CIFS_SMALL_BUFFER_SIZE, + GFP_KERNEL | __GFP_ZERO); + work->response_sz = MAX_CIFS_SMALL_BUFFER_SIZE; + + if (!work->response_buf) { + pr_err("Failed to allocate %u bytes buffer\n", + MAX_CIFS_SMALL_BUFFER_SIZE); + return -ENOMEM; + } - if (conn->ops->get_cmd_val(work) != SMB_COM_NEGOTIATE) - conn->need_neg = false; return 0; } +static struct smb_version_ops smb1_server_ops = { + .get_cmd_val = get_smb1_cmd_val, + .init_rsp_hdr = init_smb1_rsp_hdr, + .allocate_rsp_buf = smb1_allocate_rsp_buf, + .check_user_session = smb1_check_user_session, +}; + +static int smb1_negotiate(struct ksmbd_work *work) +{ + return ksmbd_smb_negotiate_common(work, SMB_COM_NEGOTIATE); +} + +static struct smb_version_cmds smb1_server_cmds[1] = { + [SMB_COM_NEGOTIATE_EX] = { .proc = smb1_negotiate, }, +}; + +static void init_smb1_server(struct ksmbd_conn *conn) +{ + conn->ops = &smb1_server_ops; + conn->cmds = smb1_server_cmds; + conn->max_cmds = ARRAY_SIZE(smb1_server_cmds); +} + +void ksmbd_init_smb_server(struct ksmbd_work *work) +{ + struct ksmbd_conn *conn = work->conn; + __le32 proto; + + if (conn->need_neg == false) + return; + + proto = *(__le32 *)((struct smb_hdr *)work->request_buf)->Protocol; + if (proto == SMB1_PROTO_NUMBER) + init_smb1_server(conn); + else + init_smb3_11_server(conn); +} + int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, struct ksmbd_file *dir, struct ksmbd_dir_info *d_info, @@ -444,20 +545,10 @@ static int smb_handle_negotiate(struct ksmbd_work *work) ksmbd_debug(SMB, "Unsupported SMB1 protocol\n"); - /* - * Remove 4 byte direct TCP header, add 2 byte bcc and - * 2 byte DialectIndex. - */ - *(__be32 *)work->response_buf = - cpu_to_be32(sizeof(struct smb_hdr) - 4 + 2 + 2); + /* Add 2 byte bcc and 2 byte DialectIndex. */ + inc_rfc1001_len(work->response_buf, 4); neg_rsp->hdr.Status.CifsError = STATUS_SUCCESS; - neg_rsp->hdr.Command = SMB_COM_NEGOTIATE; - *(__le32 *)neg_rsp->hdr.Protocol = SMB1_PROTO_NUMBER; - neg_rsp->hdr.Flags = SMBFLG_RESPONSE; - neg_rsp->hdr.Flags2 = SMBFLG2_UNICODE | SMBFLG2_ERR_STATUS | - SMBFLG2_EXT_SEC | SMBFLG2_IS_LONG_NAME; - neg_rsp->hdr.WordCount = 1; neg_rsp->DialectIndex = cpu_to_le16(work->conn->dialect); neg_rsp->ByteCount = 0; @@ -473,24 +564,13 @@ int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command) ksmbd_negotiate_smb_dialect(work->request_buf); ksmbd_debug(SMB, "conn->dialect 0x%x\n", conn->dialect); - if (command == SMB2_NEGOTIATE_HE) { - struct smb2_hdr *smb2_hdr = smb2_get_msg(work->request_buf); - - if (smb2_hdr->ProtocolId != SMB2_PROTO_NUMBER) { - ksmbd_debug(SMB, "Downgrade to SMB1 negotiation\n"); - command = SMB_COM_NEGOTIATE; - } - } - if (command == SMB2_NEGOTIATE_HE) { ret = smb2_handle_negotiate(work); - init_smb2_neg_rsp(work); return ret; } if (command == SMB_COM_NEGOTIATE) { if (__smb2_negotiate(conn)) { - conn->need_neg = true; init_smb3_11_server(conn); init_smb2_neg_rsp(work); ksmbd_debug(SMB, "Upgrade to SMB2 negotiation\n"); diff --git a/fs/ksmbd/smb_common.h b/fs/ksmbd/smb_common.h index d30ce4c1a151..9130d2e3cd78 100644 --- a/fs/ksmbd/smb_common.h +++ b/fs/ksmbd/smb_common.h @@ -427,7 +427,7 @@ bool ksmbd_smb_request(struct ksmbd_conn *conn); int ksmbd_lookup_dialect_by_id(__le16 *cli_dialects, __le16 dialects_count); -int ksmbd_init_smb_server(struct ksmbd_work *work); +void ksmbd_init_smb_server(struct ksmbd_work *work); struct ksmbd_kstat; int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, diff --git a/fs/ksmbd/unicode.c b/fs/ksmbd/unicode.c index a0db699ddafd..9ae676906ed3 100644 --- a/fs/ksmbd/unicode.c +++ b/fs/ksmbd/unicode.c @@ -113,24 +113,6 @@ cp_convert: goto out; } -/* - * is_char_allowed() - check for valid character - * @ch: input character to be checked - * - * Return: 1 if char is allowed, otherwise 0 - */ -static inline int is_char_allowed(char *ch) -{ - /* check for control chars, wildcards etc. */ - if (!(*ch & 0x80) && - (*ch <= 0x1f || - *ch == '?' || *ch == '"' || *ch == '<' || - *ch == '>' || *ch == '|')) - return 0; - - return 1; -} - /* * smb_from_utf16() - convert utf16le string to local charset * @to: destination buffer diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index e9a45dea748a..8a4c86687429 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -139,7 +139,7 @@ static ssize_t netfs_extract_user_to_sg(struct iov_iter *iter, size_t seg = min_t(size_t, PAGE_SIZE - off, len); *pages++ = NULL; - sg_set_page(sg, page, len, off); + sg_set_page(sg, page, seg, off); sgtable->nents++; sg++; len -= seg; diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 2681a449edc1..13592e82eaf6 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -2219,6 +2219,7 @@ static int nilfs_btree_assign_p(struct nilfs_bmap *btree, /* on-disk format */ binfo->bi_dat.bi_blkoff = cpu_to_le64(key); binfo->bi_dat.bi_level = level; + memset(binfo->bi_dat.bi_pad, 0, sizeof(binfo->bi_dat.bi_pad)); return 0; } diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index a35f2795b242..4c85914f2abc 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -314,6 +314,7 @@ static int nilfs_direct_assign_p(struct nilfs_bmap *direct, binfo->bi_dat.bi_blkoff = cpu_to_le64(key); binfo->bi_dat.bi_level = 0; + memset(binfo->bi_dat.bi_pad, 0, sizeof(binfo->bi_dat.bi_pad)); return 0; } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 19446a8243d7..6ad41390fa74 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2609,11 +2609,10 @@ static int nilfs_segctor_thread(void *arg) goto loop; end_thread: - spin_unlock(&sci->sc_state_lock); - /* end sync. */ sci->sc_task = NULL; wake_up(&sci->sc_wait_task); /* for nilfs_segctor_kill_thread() */ + spin_unlock(&sci->sc_state_lock); return 0; } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 1422b8ba24ed..77f1e5778d1c 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -482,6 +482,7 @@ static void nilfs_put_super(struct super_block *sb) up_write(&nilfs->ns_sem); } + nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); @@ -1105,6 +1106,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) nilfs_put_root(fsroot); failed_unload: + nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 3a4c9c150cbf..2894152a6b25 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -87,7 +87,6 @@ void destroy_nilfs(struct the_nilfs *nilfs) { might_sleep(); if (nilfs_init(nilfs)) { - nilfs_sysfs_delete_device_group(nilfs); brelse(nilfs->ns_sbh[0]); brelse(nilfs->ns_sbh[1]); } @@ -305,6 +304,10 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) goto failed; } + err = nilfs_sysfs_create_device_group(sb); + if (unlikely(err)) + goto sysfs_error; + if (valid_fs) goto skip_recovery; @@ -366,6 +369,9 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) goto failed; failed_unload: + nilfs_sysfs_delete_device_group(nilfs); + + sysfs_error: iput(nilfs->ns_cpfile); iput(nilfs->ns_sufile); iput(nilfs->ns_dat); @@ -697,10 +703,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) if (err) goto failed_sbh; - err = nilfs_sysfs_create_device_group(sb); - if (err) - goto failed_sbh; - set_nilfs_init(nilfs); err = 0; out: diff --git a/include/acpi/video.h b/include/acpi/video.h index 8ed9bec03e53..ff5a8da5d883 100644 --- a/include/acpi/video.h +++ b/include/acpi/video.h @@ -59,8 +59,6 @@ extern void acpi_video_unregister(void); extern void acpi_video_register_backlight(void); extern int acpi_video_get_edid(struct acpi_device *device, int type, int device_id, void **edid); -extern enum acpi_backlight_type acpi_video_get_backlight_type(void); -extern bool acpi_video_backlight_use_native(void); /* * Note: The value returned by acpi_video_handles_brightness_key_presses() * may change over time and should not be cached. @@ -69,6 +67,19 @@ extern bool acpi_video_handles_brightness_key_presses(void); extern int acpi_video_get_levels(struct acpi_device *device, struct acpi_video_device_brightness **dev_br, int *pmax_level); + +extern enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, + bool *auto_detect); + +static inline enum acpi_backlight_type acpi_video_get_backlight_type(void) +{ + return __acpi_video_get_backlight_type(false, NULL); +} + +static inline bool acpi_video_backlight_use_native(void) +{ + return __acpi_video_get_backlight_type(true, NULL) == acpi_backlight_native; +} #else static inline void acpi_video_report_nolcd(void) { return; }; static inline int acpi_video_register(void) { return -ENODEV; } diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index af4dd536a52c..10ec6dcf40bb 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -36,6 +36,7 @@ #include #include #include +#include #if defined(__LITTLE_ENDIAN) #define MLX5_SET_HOST_ENDIANNESS 0 @@ -980,14 +981,23 @@ enum { }; enum { - CQE_RSS_HTYPE_IP = 0x3 << 2, + CQE_RSS_HTYPE_IP = GENMASK(3, 2), /* cqe->rss_hash_type[3:2] - IP destination selected for hash * (00 = none, 01 = IPv4, 10 = IPv6, 11 = Reserved) */ - CQE_RSS_HTYPE_L4 = 0x3 << 6, + CQE_RSS_IP_NONE = 0x0, + CQE_RSS_IPV4 = 0x1, + CQE_RSS_IPV6 = 0x2, + CQE_RSS_RESERVED = 0x3, + + CQE_RSS_HTYPE_L4 = GENMASK(7, 6), /* cqe->rss_hash_type[7:6] - L4 destination selected for hash * (00 = none, 01 = TCP. 10 = UDP, 11 = IPSEC.SPI */ + CQE_RSS_L4_NONE = 0x0, + CQE_RSS_L4_TCP = 0x1, + CQE_RSS_L4_UDP = 0x2, + CQE_RSS_L4_IPSEC = 0x3, }; enum { diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0722859c3647..a57e6ae78e65 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -774,7 +774,8 @@ struct mm_struct { unsigned long cpu_bitmap[]; }; -#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN) +#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | \ + MT_FLAGS_USE_RCU) extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fe355592dfde..96d27d558b0c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1650,7 +1650,8 @@ struct net_device_ops { struct xdp_metadata_ops { int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); - int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash); + int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type); }; /** diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h index ed9b4df792b8..43765eaf2342 100644 --- a/include/linux/pci-doe.h +++ b/include/linux/pci-doe.h @@ -34,6 +34,10 @@ struct pci_doe_mb; * @work: Used internally by the mailbox * @doe_mb: Used internally by the mailbox * + * Payloads are treated as opaque byte streams which are transmitted verbatim, + * without byte-swapping. If payloads contain little-endian register values, + * the caller is responsible for conversion with cpu_to_le32() / le32_to_cpu(). + * * The payload sizes and rv are specified in bytes with the following * restrictions concerning the protocol. * @@ -45,9 +49,9 @@ struct pci_doe_mb; */ struct pci_doe_task { struct pci_doe_protocol prot; - u32 *request_pl; + __le32 *request_pl; size_t request_pl_sz; - u32 *response_pl; + __le32 *response_pl; size_t response_pl_sz; int rv; void (*complete)(struct pci_doe_task *task); diff --git a/include/linux/pci.h b/include/linux/pci.h index b50e5c79f7e3..a5dda515fcd1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1624,6 +1624,8 @@ pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, flags, NULL); } +static inline bool pci_msix_can_alloc_dyn(struct pci_dev *dev) +{ return false; } static inline struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index, const struct irq_affinity_desc *affdesc) { diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index f0c87baaf6c0..3d6cf306cd55 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -25,7 +25,8 @@ void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex, u32 portid, u32 seq); + int new_ifindex, u32 portid, + const struct nlmsghdr *nlh); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags, u32 portid, const struct nlmsghdr *nlh); diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 6ed9b4d546a7..d5311ceb21c6 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -954,6 +954,7 @@ enum { HCI_CONN_STK_ENCRYPT, HCI_CONN_AUTH_INITIATOR, HCI_CONN_DROP, + HCI_CONN_CANCEL, HCI_CONN_PARAM_REMOVAL_PEND, HCI_CONN_NEW_LINK_KEY, HCI_CONN_SCANNING, diff --git a/include/net/bonding.h b/include/net/bonding.h index ea36ab7f9e72..c3843239517d 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -761,13 +761,17 @@ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) #if IS_ENABLED(CONFIG_IPV6) static inline int bond_get_targets_ip6(struct in6_addr *targets, struct in6_addr *ip) { + struct in6_addr mcaddr; int i; - for (i = 0; i < BOND_MAX_NS_TARGETS; i++) - if (ipv6_addr_equal(&targets[i], ip)) + for (i = 0; i < BOND_MAX_NS_TARGETS; i++) { + addrconf_addr_solict_mult(&targets[i], &mcaddr); + if ((ipv6_addr_equal(&targets[i], ip)) || + (ipv6_addr_equal(&mcaddr, ip))) return i; else if (ipv6_addr_any(&targets[i])) break; + } return -1; } diff --git a/include/net/xdp.h b/include/net/xdp.h index 41c57b8b1671..76aa748e7923 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -8,6 +8,7 @@ #include /* skb_shared_info */ #include +#include /** * DOC: XDP RX-queue information @@ -425,6 +426,52 @@ XDP_METADATA_KFUNC_xxx MAX_XDP_METADATA_KFUNC, }; +enum xdp_rss_hash_type { + /* First part: Individual bits for L3/L4 types */ + XDP_RSS_L3_IPV4 = BIT(0), + XDP_RSS_L3_IPV6 = BIT(1), + + /* The fixed (L3) IPv4 and IPv6 headers can both be followed by + * variable/dynamic headers, IPv4 called Options and IPv6 called + * Extension Headers. HW RSS type can contain this info. + */ + XDP_RSS_L3_DYNHDR = BIT(2), + + /* When RSS hash covers L4 then drivers MUST set XDP_RSS_L4 bit in + * addition to the protocol specific bit. This ease interaction with + * SKBs and avoids reserving a fixed mask for future L4 protocol bits. + */ + XDP_RSS_L4 = BIT(3), /* L4 based hash, proto can be unknown */ + XDP_RSS_L4_TCP = BIT(4), + XDP_RSS_L4_UDP = BIT(5), + XDP_RSS_L4_SCTP = BIT(6), + XDP_RSS_L4_IPSEC = BIT(7), /* L4 based hash include IPSEC SPI */ + + /* Second part: RSS hash type combinations used for driver HW mapping */ + XDP_RSS_TYPE_NONE = 0, + XDP_RSS_TYPE_L2 = XDP_RSS_TYPE_NONE, + + XDP_RSS_TYPE_L3_IPV4 = XDP_RSS_L3_IPV4, + XDP_RSS_TYPE_L3_IPV6 = XDP_RSS_L3_IPV6, + XDP_RSS_TYPE_L3_IPV4_OPT = XDP_RSS_L3_IPV4 | XDP_RSS_L3_DYNHDR, + XDP_RSS_TYPE_L3_IPV6_EX = XDP_RSS_L3_IPV6 | XDP_RSS_L3_DYNHDR, + + XDP_RSS_TYPE_L4_ANY = XDP_RSS_L4, + XDP_RSS_TYPE_L4_IPV4_TCP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_TCP, + XDP_RSS_TYPE_L4_IPV4_UDP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_UDP, + XDP_RSS_TYPE_L4_IPV4_SCTP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, + XDP_RSS_TYPE_L4_IPV4_IPSEC = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, + + XDP_RSS_TYPE_L4_IPV6_TCP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_TCP, + XDP_RSS_TYPE_L4_IPV6_UDP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_UDP, + XDP_RSS_TYPE_L4_IPV6_SCTP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, + XDP_RSS_TYPE_L4_IPV6_IPSEC = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, + + XDP_RSS_TYPE_L4_IPV6_TCP_EX = XDP_RSS_TYPE_L4_IPV6_TCP | XDP_RSS_L3_DYNHDR, + XDP_RSS_TYPE_L4_IPV6_UDP_EX = XDP_RSS_TYPE_L4_IPV6_UDP | XDP_RSS_L3_DYNHDR, + XDP_RSS_TYPE_L4_IPV6_SCTP_EX = XDP_RSS_TYPE_L4_IPV6_SCTP | XDP_RSS_L3_DYNHDR, +}; + #ifdef CONFIG_NET u32 bpf_xdp_metadata_kfunc_id(int id); bool bpf_dev_bound_kfunc_id(u32 btf_id); diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h index 5af2a0300bb9..3744e4da1b2a 100644 --- a/include/uapi/linux/virtio_blk.h +++ b/include/uapi/linux/virtio_blk.h @@ -140,11 +140,11 @@ struct virtio_blk_config { /* Zoned block device characteristics (if VIRTIO_BLK_F_ZONED) */ struct virtio_blk_zoned_characteristics { - __le32 zone_sectors; - __le32 max_open_zones; - __le32 max_active_zones; - __le32 max_append_sectors; - __le32 write_granularity; + __virtio32 zone_sectors; + __virtio32 max_open_zones; + __virtio32 max_active_zones; + __virtio32 max_append_sectors; + __virtio32 write_granularity; __u8 model; __u8 unused2[3]; } zoned; @@ -241,11 +241,11 @@ struct virtio_blk_outhdr { */ struct virtio_blk_zone_descriptor { /* Zone capacity */ - __le64 z_cap; + __virtio64 z_cap; /* The starting sector of the zone */ - __le64 z_start; + __virtio64 z_start; /* Zone write pointer position in sectors */ - __le64 z_wp; + __virtio64 z_wp; /* Zone type */ __u8 z_type; /* Zone state */ @@ -254,7 +254,7 @@ struct virtio_blk_zone_descriptor { }; struct virtio_blk_zone_report { - __le64 nr_zones; + __virtio64 nr_zones; __u8 reserved[56]; struct virtio_blk_zone_descriptor zones[]; }; diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index 25aab8ec4f86..431c3afb2ce0 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -979,7 +979,6 @@ struct ufs_hba { struct completion *uic_async_done; enum ufshcd_state ufshcd_state; - bool logical_unit_scan_finished; u32 eh_flags; u32 intr_mask; u16 ee_ctrl_mask; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 722624b6d0dc..2a8b8c304d2a 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2789,8 +2789,8 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_eventfd_unregister(ctx); io_alloc_cache_free(&ctx->apoll_cache, io_apoll_cache_free); io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free); - mutex_unlock(&ctx->uring_lock); io_destroy_buffers(ctx); + mutex_unlock(&ctx->uring_lock); if (ctx->sq_creds) put_cred(ctx->sq_creds); if (ctx->submitter_task) diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index 3002dc827195..a90c820ce99e 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -228,17 +228,18 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, return i; } - /* the head kbuf is the list itself */ + /* protects io_buffers_cache */ + lockdep_assert_held(&ctx->uring_lock); + while (!list_empty(&bl->buf_list)) { struct io_buffer *nxt; nxt = list_first_entry(&bl->buf_list, struct io_buffer, list); - list_del(&nxt->list); + list_move(&nxt->list, &ctx->io_buffers_cache); if (++i == nbufs) return i; cond_resched(); } - i++; return i; } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 5b919ef832b6..dac42a2ad588 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -623,7 +623,7 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index, phys_to_dma_unencrypted(dev, mem->start) & boundary_mask; unsigned long max_slots = get_max_slots(boundary_mask); unsigned int iotlb_align_mask = - dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1); + dma_get_min_align_mask(dev) | alloc_align_mask; unsigned int nslots = nr_slots(alloc_size), stride; unsigned int offset = swiotlb_align_offset(dev, orig_addr); unsigned int index, slots_checked, count = 0, i; @@ -639,8 +639,8 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index, * allocations. */ if (alloc_size >= PAGE_SIZE) - iotlb_align_mask &= PAGE_MASK; - iotlb_align_mask &= alloc_align_mask; + iotlb_align_mask |= ~PAGE_MASK; + iotlb_align_mask &= ~(IO_TLB_SIZE - 1); /* * For mappings with an alignment requirement don't bother looping to diff --git a/kernel/events/core.c b/kernel/events/core.c index fb3e436bcd4a..435815d3be3f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -12173,7 +12173,7 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event) /* * If its not a per-cpu rb, it must be the same task. */ - if (output_event->cpu == -1 && output_event->ctx != event->ctx) + if (output_event->cpu == -1 && output_event->hw.target != event->hw.target) goto out; /* @@ -12893,12 +12893,14 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) __perf_pmu_remove(src_ctx, src_cpu, pmu, &src_ctx->pinned_groups, &events); __perf_pmu_remove(src_ctx, src_cpu, pmu, &src_ctx->flexible_groups, &events); - /* - * Wait for the events to quiesce before re-instating them. - */ - synchronize_rcu(); + if (!list_empty(&events)) { + /* + * Wait for the events to quiesce before re-instating them. + */ + synchronize_rcu(); - __perf_pmu_install(dst_ctx, dst_cpu, pmu, &events); + __perf_pmu_install(dst_ctx, dst_cpu, pmu, &events); + } mutex_unlock(&dst_ctx->mutex); mutex_unlock(&src_ctx->mutex); diff --git a/kernel/fork.c b/kernel/fork.c index c0257cbee093..0c92f224c68c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -617,6 +617,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, if (retval) goto out; + mt_clear_in_rcu(vmi.mas.tree); for_each_vma(old_vmi, mpnt) { struct file *file; @@ -700,6 +701,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, retval = arch_dup_mmap(oldmm, mm); loop_out: vma_iter_free(&vmi); + if (!retval) + mt_set_in_rcu(vmi.mas.tree); out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 8e880c09ab59..7b95ee98a1a5 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3024,6 +3024,18 @@ need_offload_krc(struct kfree_rcu_cpu *krcp) return !!READ_ONCE(krcp->head); } +static bool +need_wait_for_krwp_work(struct kfree_rcu_cpu_work *krwp) +{ + int i; + + for (i = 0; i < FREE_N_CHANNELS; i++) + if (!list_empty(&krwp->bulk_head_free[i])) + return true; + + return !!krwp->head_free; +} + static int krc_count(struct kfree_rcu_cpu *krcp) { int sum = atomic_read(&krcp->head_count); @@ -3107,15 +3119,14 @@ static void kfree_rcu_monitor(struct work_struct *work) for (i = 0; i < KFREE_N_BATCHES; i++) { struct kfree_rcu_cpu_work *krwp = &(krcp->krw_arr[i]); - // Try to detach bulk_head or head and attach it over any - // available corresponding free channel. It can be that - // a previous RCU batch is in progress, it means that - // immediately to queue another one is not possible so - // in that case the monitor work is rearmed. - if ((!list_empty(&krcp->bulk_head[0]) && list_empty(&krwp->bulk_head_free[0])) || - (!list_empty(&krcp->bulk_head[1]) && list_empty(&krwp->bulk_head_free[1])) || - (READ_ONCE(krcp->head) && !krwp->head_free)) { + // Try to detach bulk_head or head and attach it, only when + // all channels are free. Any channel is not free means at krwp + // there is on-going rcu work to handle krwp's free business. + if (need_wait_for_krwp_work(krwp)) + continue; + // kvfree_rcu_drain_ready() might handle this krcp, if so give up. + if (need_offload_krc(krcp)) { // Channel 1 corresponds to the SLAB-pointer bulk path. // Channel 2 corresponds to vmalloc-pointer bulk path. for (j = 0; j < FREE_N_CHANNELS; j++) { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 0feea145bb29..c67bcc89a771 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5667,12 +5667,15 @@ int modify_ftrace_direct(unsigned long ip, ret = 0; } - if (unlikely(ret && new_direct)) { - direct->count++; - list_del_rcu(&new_direct->next); - synchronize_rcu_tasks(); - kfree(new_direct); - ftrace_direct_func_count--; + if (ret) { + direct->addr = old_addr; + if (unlikely(new_direct)) { + direct->count++; + list_del_rcu(&new_direct->next); + synchronize_rcu_tasks(); + kfree(new_direct); + ftrace_direct_func_count--; + } } out_unlock: diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index f0ff730125bf..d6a70aff2410 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -44,7 +44,7 @@ enum { ERRORS }; static const char *err_text[] = { ERRORS }; -DEFINE_MUTEX(lastcmd_mutex); +static DEFINE_MUTEX(lastcmd_mutex); static char *last_cmd; static int errpos(const char *str) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c8b379e2e9ad..39d1d93164bd 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1143,7 +1143,7 @@ menu "Scheduler Debugging" config SCHED_DEBUG bool "Collect scheduler debugging info" - depends on DEBUG_KERNEL && PROC_FS + depends on DEBUG_KERNEL && DEBUG_FS default y help If you say Y here, the /sys/kernel/debug/sched file will be provided @@ -1392,7 +1392,7 @@ config LOCKDEP_STACK_TRACE_HASH_BITS range 10 30 default 14 help - Try increasing this value if you need large MAX_STACK_TRACE_ENTRIES. + Try increasing this value if you need large STACK_TRACE_HASH_SIZE. config LOCKDEP_CIRCULAR_QUEUE_BITS int "Bitsize for elements in circular_queue struct" diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 9e2735cbc2b4..db60edb55f2f 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -185,7 +185,7 @@ static void mt_free_rcu(struct rcu_head *head) */ static void ma_free_rcu(struct maple_node *node) { - node->parent = ma_parent_ptr(node); + WARN_ON(node->parent != ma_parent_ptr(node)); call_rcu(&node->rcu, mt_free_rcu); } @@ -539,11 +539,14 @@ static inline struct maple_node *mte_parent(const struct maple_enode *enode) */ static inline bool ma_dead_node(const struct maple_node *node) { - struct maple_node *parent = (void *)((unsigned long) - node->parent & ~MAPLE_NODE_MASK); + struct maple_node *parent; + /* Do not reorder reads from the node prior to the parent check */ + smp_rmb(); + parent = (void *)((unsigned long) node->parent & ~MAPLE_NODE_MASK); return (parent == node); } + /* * mte_dead_node() - check if the @enode is dead. * @enode: The encoded maple node @@ -555,6 +558,8 @@ static inline bool mte_dead_node(const struct maple_enode *enode) struct maple_node *parent, *node; node = mte_to_node(enode); + /* Do not reorder reads from the node prior to the parent check */ + smp_rmb(); parent = mte_parent(enode); return (parent == node); } @@ -625,6 +630,8 @@ static inline unsigned int mas_alloc_req(const struct ma_state *mas) * @node - the maple node * @type - the node type * + * In the event of a dead node, this array may be %NULL + * * Return: A pointer to the maple node pivots */ static inline unsigned long *ma_pivots(struct maple_node *node, @@ -817,6 +824,11 @@ static inline void *mt_slot(const struct maple_tree *mt, return rcu_dereference_check(slots[offset], mt_locked(mt)); } +static inline void *mt_slot_locked(struct maple_tree *mt, void __rcu **slots, + unsigned char offset) +{ + return rcu_dereference_protected(slots[offset], mt_locked(mt)); +} /* * mas_slot_locked() - Get the slot value when holding the maple tree lock. * @mas: The maple state @@ -828,7 +840,7 @@ static inline void *mt_slot(const struct maple_tree *mt, static inline void *mas_slot_locked(struct ma_state *mas, void __rcu **slots, unsigned char offset) { - return rcu_dereference_protected(slots[offset], mt_locked(mas->tree)); + return mt_slot_locked(mas->tree, slots, offset); } /* @@ -899,6 +911,45 @@ static inline void ma_set_meta(struct maple_node *mn, enum maple_type mt, meta->end = end; } +/* + * mt_clear_meta() - clear the metadata information of a node, if it exists + * @mt: The maple tree + * @mn: The maple node + * @type: The maple node type + * @offset: The offset of the highest sub-gap in this node. + * @end: The end of the data in this node. + */ +static inline void mt_clear_meta(struct maple_tree *mt, struct maple_node *mn, + enum maple_type type) +{ + struct maple_metadata *meta; + unsigned long *pivots; + void __rcu **slots; + void *next; + + switch (type) { + case maple_range_64: + pivots = mn->mr64.pivot; + if (unlikely(pivots[MAPLE_RANGE64_SLOTS - 2])) { + slots = mn->mr64.slot; + next = mt_slot_locked(mt, slots, + MAPLE_RANGE64_SLOTS - 1); + if (unlikely((mte_to_node(next) && + mte_node_type(next)))) + return; /* no metadata, could be node */ + } + fallthrough; + case maple_arange_64: + meta = ma_meta(mn, type); + break; + default: + return; + } + + meta->gap = 0; + meta->end = 0; +} + /* * ma_meta_end() - Get the data end of a node from the metadata * @mn: The maple node @@ -1096,8 +1147,11 @@ static int mas_ascend(struct ma_state *mas) a_type = mas_parent_enum(mas, p_enode); a_node = mte_parent(p_enode); a_slot = mte_parent_slot(p_enode); - pivots = ma_pivots(a_node, a_type); a_enode = mt_mk_node(a_node, a_type); + pivots = ma_pivots(a_node, a_type); + + if (unlikely(ma_dead_node(a_node))) + return 1; if (!set_min && a_slot) { set_min = true; @@ -1354,12 +1408,16 @@ static inline struct maple_enode *mas_start(struct ma_state *mas) mas->max = ULONG_MAX; mas->depth = 0; +retry: root = mas_root(mas); /* Tree with nodes */ if (likely(xa_is_node(root))) { mas->depth = 1; mas->node = mte_safe_root(root); mas->offset = 0; + if (mte_dead_node(mas->node)) + goto retry; + return NULL; } @@ -1401,6 +1459,9 @@ static inline unsigned char ma_data_end(struct maple_node *node, { unsigned char offset; + if (!pivots) + return 0; + if (type == maple_arange_64) return ma_meta_end(node, type); @@ -1436,6 +1497,9 @@ static inline unsigned char mas_data_end(struct ma_state *mas) return ma_meta_end(node, type); pivots = ma_pivots(node, type); + if (unlikely(ma_dead_node(node))) + return 0; + offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); @@ -1724,8 +1788,10 @@ static inline void mas_replace(struct ma_state *mas, bool advanced) rcu_assign_pointer(slots[offset], mas->node); } - if (!advanced) + if (!advanced) { + mte_set_node_dead(old_enode); mas_free(mas, old_enode); + } } /* @@ -3659,10 +3725,9 @@ static inline int mas_root_expand(struct ma_state *mas, void *entry) slot++; mas->depth = 1; mas_set_height(mas); - + ma_set_meta(node, maple_leaf_64, 0, slot); /* swap the new root into the tree */ rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); - ma_set_meta(node, maple_leaf_64, 0, slot); return slot; } @@ -3875,18 +3940,13 @@ static inline void *mtree_lookup_walk(struct ma_state *mas) end = ma_data_end(node, type, pivots, max); if (unlikely(ma_dead_node(node))) goto dead_node; - - if (pivots[offset] >= mas->index) - goto next; - do { - offset++; - } while ((offset < end) && (pivots[offset] < mas->index)); + if (pivots[offset] >= mas->index) { + max = pivots[offset]; + break; + } + } while (++offset < end); - if (likely(offset > end)) - max = pivots[offset]; - -next: slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) @@ -4164,6 +4224,7 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas) done: mas_leaf_set_meta(mas, newnode, dst_pivots, maple_leaf_64, new_end); if (in_rcu) { + mte_set_node_dead(mas->node); mas->node = mt_mk_node(newnode, wr_mas->type); mas_replace(mas, false); } else { @@ -4505,6 +4566,9 @@ static inline int mas_prev_node(struct ma_state *mas, unsigned long min) node = mas_mn(mas); slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); + if (unlikely(ma_dead_node(node))) + return 1; + mas->max = pivots[offset]; if (offset) mas->min = pivots[offset - 1] + 1; @@ -4526,6 +4590,9 @@ static inline int mas_prev_node(struct ma_state *mas, unsigned long min) slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); offset = ma_data_end(node, mt, pivots, mas->max); + if (unlikely(ma_dead_node(node))) + return 1; + if (offset) mas->min = pivots[offset - 1] + 1; @@ -4574,6 +4641,7 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node, struct maple_enode *enode; int level = 0; unsigned char offset; + unsigned char node_end; enum maple_type mt; void __rcu **slots; @@ -4597,7 +4665,11 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node, node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); - } while (unlikely(offset == ma_data_end(node, mt, pivots, mas->max))); + node_end = ma_data_end(node, mt, pivots, mas->max); + if (unlikely(ma_dead_node(node))) + return 1; + + } while (unlikely(offset == node_end)); slots = ma_slots(node, mt); pivot = mas_safe_pivot(mas, pivots, ++offset, mt); @@ -4613,6 +4685,9 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node, mt = mte_node_type(mas->node); slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); + if (unlikely(ma_dead_node(node))) + return 1; + offset = 0; pivot = pivots[0]; } @@ -4659,11 +4734,14 @@ static inline void *mas_next_nentry(struct ma_state *mas, return NULL; } - pivots = ma_pivots(node, type); slots = ma_slots(node, type); - mas->index = mas_safe_min(mas, pivots, mas->offset); + pivots = ma_pivots(node, type); count = ma_data_end(node, type, pivots, mas->max); - if (ma_dead_node(node)) + if (unlikely(ma_dead_node(node))) + return NULL; + + mas->index = mas_safe_min(mas, pivots, mas->offset); + if (unlikely(ma_dead_node(node))) return NULL; if (mas->index > max) @@ -4817,6 +4895,11 @@ retry: slots = ma_slots(mn, mt); pivots = ma_pivots(mn, mt); + if (unlikely(ma_dead_node(mn))) { + mas_rewalk(mas, index); + goto retry; + } + if (offset == mt_pivots[mt]) pivot = mas->max; else @@ -5400,24 +5483,26 @@ no_gap: } /* - * mas_dead_leaves() - Mark all leaves of a node as dead. + * mte_dead_leaves() - Mark all leaves of a node as dead. * @mas: The maple state * @slots: Pointer to the slot array + * @type: The maple node type * * Must hold the write lock. * * Return: The number of leaves marked as dead. */ static inline -unsigned char mas_dead_leaves(struct ma_state *mas, void __rcu **slots) +unsigned char mte_dead_leaves(struct maple_enode *enode, struct maple_tree *mt, + void __rcu **slots) { struct maple_node *node; enum maple_type type; void *entry; int offset; - for (offset = 0; offset < mt_slot_count(mas->node); offset++) { - entry = mas_slot_locked(mas, slots, offset); + for (offset = 0; offset < mt_slot_count(enode); offset++) { + entry = mt_slot(mt, slots, offset); type = mte_node_type(entry); node = mte_to_node(entry); /* Use both node and type to catch LE & BE metadata */ @@ -5425,7 +5510,6 @@ unsigned char mas_dead_leaves(struct ma_state *mas, void __rcu **slots) break; mte_set_node_dead(entry); - smp_wmb(); /* Needed for RCU */ node->type = type; rcu_assign_pointer(slots[offset], node); } @@ -5433,151 +5517,160 @@ unsigned char mas_dead_leaves(struct ma_state *mas, void __rcu **slots) return offset; } -static void __rcu **mas_dead_walk(struct ma_state *mas, unsigned char offset) +/** + * mte_dead_walk() - Walk down a dead tree to just before the leaves + * @enode: The maple encoded node + * @offset: The starting offset + * + * Note: This can only be used from the RCU callback context. + */ +static void __rcu **mte_dead_walk(struct maple_enode **enode, unsigned char offset) { struct maple_node *node, *next; void __rcu **slots = NULL; - next = mas_mn(mas); + next = mte_to_node(*enode); do { - mas->node = ma_enode_ptr(next); - node = mas_mn(mas); + *enode = ma_enode_ptr(next); + node = mte_to_node(*enode); slots = ma_slots(node, node->type); - next = mas_slot_locked(mas, slots, offset); + next = rcu_dereference_protected(slots[offset], + lock_is_held(&rcu_callback_map)); offset = 0; } while (!ma_is_leaf(next->type)); return slots; } +/** + * mt_free_walk() - Walk & free a tree in the RCU callback context + * @head: The RCU head that's within the node. + * + * Note: This can only be used from the RCU callback context. + */ static void mt_free_walk(struct rcu_head *head) { void __rcu **slots; struct maple_node *node, *start; - struct maple_tree mt; + struct maple_enode *enode; unsigned char offset; enum maple_type type; - MA_STATE(mas, &mt, 0, 0); node = container_of(head, struct maple_node, rcu); if (ma_is_leaf(node->type)) goto free_leaf; - mt_init_flags(&mt, node->ma_flags); - mas_lock(&mas); start = node; - mas.node = mt_mk_node(node, node->type); - slots = mas_dead_walk(&mas, 0); - node = mas_mn(&mas); + enode = mt_mk_node(node, node->type); + slots = mte_dead_walk(&enode, 0); + node = mte_to_node(enode); do { mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; - mas.node = node->piv_parent; - if (mas_mn(&mas) == node) - goto start_slots_free; + enode = node->piv_parent; + if (mte_to_node(enode) == node) + goto free_leaf; - type = mte_node_type(mas.node); - slots = ma_slots(mte_to_node(mas.node), type); - if ((offset < mt_slots[type]) && (slots[offset])) - slots = mas_dead_walk(&mas, offset); - - node = mas_mn(&mas); + type = mte_node_type(enode); + slots = ma_slots(mte_to_node(enode), type); + if ((offset < mt_slots[type]) && + rcu_dereference_protected(slots[offset], + lock_is_held(&rcu_callback_map))) + slots = mte_dead_walk(&enode, offset); + node = mte_to_node(enode); } while ((node != start) || (node->slot_len < offset)); slots = ma_slots(node, node->type); mt_free_bulk(node->slot_len, slots); -start_slots_free: - mas_unlock(&mas); free_leaf: mt_free_rcu(&node->rcu); } -static inline void __rcu **mas_destroy_descend(struct ma_state *mas, - struct maple_enode *prev, unsigned char offset) +static inline void __rcu **mte_destroy_descend(struct maple_enode **enode, + struct maple_tree *mt, struct maple_enode *prev, unsigned char offset) { struct maple_node *node; - struct maple_enode *next = mas->node; + struct maple_enode *next = *enode; void __rcu **slots = NULL; + enum maple_type type; + unsigned char next_offset = 0; do { - mas->node = next; - node = mas_mn(mas); - slots = ma_slots(node, mte_node_type(mas->node)); - next = mas_slot_locked(mas, slots, 0); + *enode = next; + node = mte_to_node(*enode); + type = mte_node_type(*enode); + slots = ma_slots(node, type); + next = mt_slot_locked(mt, slots, next_offset); if ((mte_dead_node(next))) - next = mas_slot_locked(mas, slots, 1); + next = mt_slot_locked(mt, slots, ++next_offset); - mte_set_node_dead(mas->node); - node->type = mte_node_type(mas->node); + mte_set_node_dead(*enode); + node->type = type; node->piv_parent = prev; node->parent_slot = offset; - offset = 0; - prev = mas->node; + offset = next_offset; + next_offset = 0; + prev = *enode; } while (!mte_is_leaf(next)); return slots; } -static void mt_destroy_walk(struct maple_enode *enode, unsigned char ma_flags, +static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free) { void __rcu **slots; struct maple_node *node = mte_to_node(enode); struct maple_enode *start; - struct maple_tree mt; - MA_STATE(mas, &mt, 0, 0); - - if (mte_is_leaf(enode)) + if (mte_is_leaf(enode)) { + node->type = mte_node_type(enode); goto free_leaf; + } - mt_init_flags(&mt, ma_flags); - mas_lock(&mas); - - mas.node = start = enode; - slots = mas_destroy_descend(&mas, start, 0); - node = mas_mn(&mas); + start = enode; + slots = mte_destroy_descend(&enode, mt, start, 0); + node = mte_to_node(enode); // Updated in the above call. do { enum maple_type type; unsigned char offset; struct maple_enode *parent, *tmp; - node->slot_len = mas_dead_leaves(&mas, slots); + node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; - mas.node = node->piv_parent; - if (mas_mn(&mas) == node) - goto start_slots_free; + enode = node->piv_parent; + if (mte_to_node(enode) == node) + goto free_leaf; - type = mte_node_type(mas.node); - slots = ma_slots(mte_to_node(mas.node), type); + type = mte_node_type(enode); + slots = ma_slots(mte_to_node(enode), type); if (offset >= mt_slots[type]) goto next; - tmp = mas_slot_locked(&mas, slots, offset); + tmp = mt_slot_locked(mt, slots, offset); if (mte_node_type(tmp) && mte_to_node(tmp)) { - parent = mas.node; - mas.node = tmp; - slots = mas_destroy_descend(&mas, parent, offset); + parent = enode; + enode = tmp; + slots = mte_destroy_descend(&enode, mt, parent, offset); } next: - node = mas_mn(&mas); - } while (start != mas.node); + node = mte_to_node(enode); + } while (start != enode); - node = mas_mn(&mas); - node->slot_len = mas_dead_leaves(&mas, slots); + node = mte_to_node(enode); + node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); -start_slots_free: - mas_unlock(&mas); - free_leaf: if (free) mt_free_rcu(&node->rcu); + else + mt_clear_meta(mt, node, node->type); } /* @@ -5593,10 +5686,10 @@ static inline void mte_destroy_walk(struct maple_enode *enode, struct maple_node *node = mte_to_node(enode); if (mt_in_rcu(mt)) { - mt_destroy_walk(enode, mt->ma_flags, false); + mt_destroy_walk(enode, mt, false); call_rcu(&node->rcu, mt_free_walk); } else { - mt_destroy_walk(enode, mt->ma_flags, true); + mt_destroy_walk(enode, mt, true); } } @@ -6617,11 +6710,11 @@ static inline void *mas_first_entry(struct ma_state *mas, struct maple_node *mn, while (likely(!ma_is_leaf(mt))) { MT_BUG_ON(mas->tree, mte_dead_node(mas->node)); slots = ma_slots(mn, mt); - pivots = ma_pivots(mn, mt); - max = pivots[0]; entry = mas_slot(mas, slots, 0); + pivots = ma_pivots(mn, mt); if (unlikely(ma_dead_node(mn))) return NULL; + max = pivots[0]; mas->node = entry; mn = mas_mn(mas); mt = mte_node_type(mas->node); @@ -6641,13 +6734,13 @@ static inline void *mas_first_entry(struct ma_state *mas, struct maple_node *mn, if (likely(entry)) return entry; - pivots = ma_pivots(mn, mt); - mas->index = pivots[0] + 1; mas->offset = 1; entry = mas_slot(mas, slots, 1); + pivots = ma_pivots(mn, mt); if (unlikely(ma_dead_node(mn))) return NULL; + mas->index = pivots[0] + 1; if (mas->index > limit) goto none; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 07abcb6eb203..245038a9fe4e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5478,7 +5478,7 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, struct folio *pagecache_folio, spinlock_t *ptl) { const bool unshare = flags & FAULT_FLAG_UNSHARE; - pte_t pte; + pte_t pte = huge_ptep_get(ptep); struct hstate *h = hstate_vma(vma); struct page *old_page; struct folio *new_folio; @@ -5487,6 +5487,17 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr = address & huge_page_mask(h); struct mmu_notifier_range range; + /* + * Never handle CoW for uffd-wp protected pages. It should be only + * handled when the uffd-wp protection is removed. + * + * Note that only the CoW optimization path (in hugetlb_no_page()) + * can trigger this, because hugetlb_fault() will always resolve + * uffd-wp bit first. + */ + if (!unshare && huge_pte_uffd_wp(pte)) + return 0; + /* * hugetlb does not support FOLL_FORCE-style write faults that keep the * PTE mapped R/O such as maybe_mkwrite() would do. @@ -5500,7 +5511,6 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, return 0; } - pte = huge_ptep_get(ptep); old_page = pte_page(pte); delayacct_wpcopy_start(); diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 79c94ee55f97..1065e0568d05 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -556,15 +556,11 @@ static unsigned long kfence_init_pool(void) * enters __slab_free() slow-path. */ for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) { - struct slab *slab = page_slab(&pages[i]); + struct slab *slab = page_slab(nth_page(pages, i)); if (!i || (i % 2)) continue; - /* Verify we do not have a compound head page. */ - if (WARN_ON(compound_head(&pages[i]) != &pages[i])) - return addr; - __folio_set_slab(slab_folio(slab)); #ifdef CONFIG_MEMCG slab->memcg_data = (unsigned long)&kfence_metadata[i / 2 - 1].objcg | @@ -597,12 +593,26 @@ static unsigned long kfence_init_pool(void) /* Protect the right redzone. */ if (unlikely(!kfence_protect(addr + PAGE_SIZE))) - return addr; + goto reset_slab; addr += 2 * PAGE_SIZE; } return 0; + +reset_slab: + for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) { + struct slab *slab = page_slab(nth_page(pages, i)); + + if (!i || (i % 2)) + continue; +#ifdef CONFIG_MEMCG + slab->memcg_data = 0; +#endif + __folio_clear_slab(slab_folio(slab)); + } + + return addr; } static bool __init kfence_init_pool_early(void) @@ -632,16 +642,6 @@ static bool __init kfence_init_pool_early(void) * fails for the first page, and therefore expect addr==__kfence_pool in * most failure cases. */ - for (char *p = (char *)addr; p < __kfence_pool + KFENCE_POOL_SIZE; p += PAGE_SIZE) { - struct slab *slab = virt_to_slab(p); - - if (!slab) - continue; -#ifdef CONFIG_MEMCG - slab->memcg_data = 0; -#endif - __folio_clear_slab(slab_folio(slab)); - } memblock_free_late(__pa(addr), KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool)); __kfence_pool = NULL; return false; diff --git a/mm/memory.c b/mm/memory.c index f456f3b5049c..01a23ad48a04 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3563,8 +3563,21 @@ static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct mmu_notifier_range range; - if (!folio_lock_or_retry(folio, vma->vm_mm, vmf->flags)) + /* + * We need a reference to lock the folio because we don't hold + * the PTL so a racing thread can remove the device-exclusive + * entry and unmap it. If the folio is free the entry must + * have been removed already. If it happens to have already + * been re-allocated after being freed all we do is lock and + * unlock it. + */ + if (!folio_try_get(folio)) + return 0; + + if (!folio_lock_or_retry(folio, vma->vm_mm, vmf->flags)) { + folio_put(folio); return VM_FAULT_RETRY; + } mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma->vm_mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE, NULL); @@ -3577,6 +3590,7 @@ static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf) pte_unmap_unlock(vmf->pte, vmf->ptl); folio_unlock(folio); + folio_put(folio); mmu_notifier_invalidate_range_end(&range); return 0; diff --git a/mm/mmap.c b/mm/mmap.c index ad499f7b767f..ff68a67a2a7c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2277,7 +2277,7 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, int count = 0; int error = -ENOMEM; MA_STATE(mas_detach, &mt_detach, 0, 0); - mt_init_flags(&mt_detach, MT_FLAGS_LOCK_EXTERN); + mt_init_flags(&mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_set_external_lock(&mt_detach, &mm->mmap_lock); /* @@ -3037,6 +3037,7 @@ void exit_mmap(struct mm_struct *mm) */ set_bit(MMF_OOM_SKIP, &mm->flags); mmap_write_lock(mm); + mt_clear_in_rcu(&mm->mm_mt); free_pgtables(&tlb, &mm->mm_mt, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb); diff --git a/mm/swapfile.c b/mm/swapfile.c index 62ba2bf577d7..2c718f45745f 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -679,6 +679,7 @@ static void __del_from_avail_list(struct swap_info_struct *p) { int nid; + assert_spin_locked(&p->lock); for_each_node(nid) plist_del(&p->avail_lists[nid], &swap_avail_heads[nid]); } @@ -2434,8 +2435,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); goto out_dput; } - del_from_avail_list(p); spin_lock(&p->lock); + del_from_avail_list(p); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index bef6cf2b4d46..a50072066221 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3042,9 +3042,11 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, * allocation request, free them via vfree() if any. */ if (area->nr_pages != nr_small_pages) { - warn_alloc(gfp_mask, NULL, - "vmalloc error: size %lu, page order %u, failed to allocate pages", - area->nr_pages * PAGE_SIZE, page_order); + /* vm_area_alloc_pages() can also fail due to a fatal signal */ + if (!fatal_signal_pending(current)) + warn_alloc(gfp_mask, NULL, + "vmalloc error: size %lu, page order %u, failed to allocate pages", + area->nr_pages * PAGE_SIZE, page_order); goto fail; } diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index c64050e839ac..1fffe2bed5b0 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -280,6 +280,10 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) write_unlock(&xen_9pfs_lock); for (i = 0; i < priv->num_rings; i++) { + struct xen_9pfs_dataring *ring = &priv->rings[i]; + + cancel_work_sync(&ring->work); + if (!priv->rings[i].intf) break; if (priv->rings[i].irq > 0) diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 17b946f9ba31..8455ba141ee6 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -68,7 +68,7 @@ static const struct sco_param esco_param_msbc[] = { }; /* This function requires the caller holds hdev->lock */ -static void hci_connect_le_scan_cleanup(struct hci_conn *conn) +static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) { struct hci_conn_params *params; struct hci_dev *hdev = conn->hdev; @@ -88,9 +88,28 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn) params = hci_pend_le_action_lookup(&hdev->pend_le_conns, bdaddr, bdaddr_type); - if (!params || !params->explicit_connect) + if (!params) return; + if (params->conn) { + hci_conn_drop(params->conn); + hci_conn_put(params->conn); + params->conn = NULL; + } + + if (!params->explicit_connect) + return; + + /* If the status indicates successful cancellation of + * the attempt (i.e. Unknown Connection Id) there's no point of + * notifying failure since we'll go back to keep trying to + * connect. The only exception is explicit connect requests + * where a timeout + cancel does indicate an actual failure. + */ + if (status && status != HCI_ERROR_UNKNOWN_CONN_ID) + mgmt_connect_failed(hdev, &conn->dst, conn->type, + conn->dst_type, status); + /* The connection attempt was doing scan for new RPA, and is * in scan phase. If params are not associated with any other * autoconnect action, remove them completely. If they are, just unmark @@ -178,7 +197,7 @@ static void le_scan_cleanup(struct work_struct *work) rcu_read_unlock(); if (c == conn) { - hci_connect_le_scan_cleanup(conn); + hci_connect_le_scan_cleanup(conn, 0x00); hci_conn_cleanup(conn); } @@ -1049,6 +1068,17 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, return conn; } +static bool hci_conn_unlink(struct hci_conn *conn) +{ + if (!conn->link) + return false; + + conn->link->link = NULL; + conn->link = NULL; + + return true; +} + int hci_conn_del(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; @@ -1060,15 +1090,16 @@ int hci_conn_del(struct hci_conn *conn) cancel_delayed_work_sync(&conn->idle_work); if (conn->type == ACL_LINK) { - struct hci_conn *sco = conn->link; - if (sco) { - sco->link = NULL; + struct hci_conn *link = conn->link; + + if (link) { + hci_conn_unlink(conn); /* Due to race, SCO connection might be not established * yet at this point. Delete it now, otherwise it is * possible for it to be stuck and can't be deleted. */ - if (sco->handle == HCI_CONN_HANDLE_UNSET) - hci_conn_del(sco); + if (link->handle == HCI_CONN_HANDLE_UNSET) + hci_conn_del(link); } /* Unacked frames */ @@ -1084,7 +1115,7 @@ int hci_conn_del(struct hci_conn *conn) struct hci_conn *acl = conn->link; if (acl) { - acl->link = NULL; + hci_conn_unlink(conn); hci_conn_drop(acl); } @@ -1179,31 +1210,8 @@ EXPORT_SYMBOL(hci_get_route); static void hci_le_conn_failed(struct hci_conn *conn, u8 status) { struct hci_dev *hdev = conn->hdev; - struct hci_conn_params *params; - params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst, - conn->dst_type); - if (params && params->conn) { - hci_conn_drop(params->conn); - hci_conn_put(params->conn); - params->conn = NULL; - } - - /* If the status indicates successful cancellation of - * the attempt (i.e. Unknown Connection Id) there's no point of - * notifying failure since we'll go back to keep trying to - * connect. The only exception is explicit connect requests - * where a timeout + cancel does indicate an actual failure. - */ - if (status != HCI_ERROR_UNKNOWN_CONN_ID || - (params && params->explicit_connect)) - mgmt_connect_failed(hdev, &conn->dst, conn->type, - conn->dst_type, status); - - /* Since we may have temporarily stopped the background scanning in - * favor of connection establishment, we should restart it. - */ - hci_update_passive_scan(hdev); + hci_connect_le_scan_cleanup(conn, status); /* Enable advertising in case this was a failed connection * attempt as a peripheral. @@ -1237,15 +1245,15 @@ static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) { struct hci_conn *conn = data; + bt_dev_dbg(hdev, "err %d", err); + hci_dev_lock(hdev); if (!err) { - hci_connect_le_scan_cleanup(conn); + hci_connect_le_scan_cleanup(conn, 0x00); goto done; } - bt_dev_err(hdev, "request failed to create LE connection: err %d", err); - /* Check if connection is still pending */ if (conn != hci_lookup_le_connect(hdev)) goto done; @@ -2438,6 +2446,12 @@ void hci_conn_hash_flush(struct hci_dev *hdev) c->state = BT_CLOSED; hci_disconn_cfm(c, HCI_ERROR_LOCAL_HOST_TERM); + + /* Unlink before deleting otherwise it is possible that + * hci_conn_del removes the link which may cause the list to + * contain items already freed. + */ + hci_conn_unlink(c); hci_conn_del(c); } } @@ -2775,6 +2789,9 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) { int r = 0; + if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + return 0; + switch (conn->state) { case BT_CONNECTED: case BT_CONFIG: diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index ad92a4be5851..e87c928c9e17 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2881,16 +2881,6 @@ static void cs_le_create_conn(struct hci_dev *hdev, bdaddr_t *peer_addr, conn->resp_addr_type = peer_addr_type; bacpy(&conn->resp_addr, peer_addr); - - /* We don't want the connection attempt to stick around - * indefinitely since LE doesn't have a page timeout concept - * like BR/EDR. Set a timer for any connection that doesn't use - * the accept list for connecting. - */ - if (filter_policy == HCI_LE_USE_PEER_ADDR) - queue_delayed_work(conn->hdev->workqueue, - &conn->le_conn_timeout, - conn->conn_timeout); } static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) @@ -5902,6 +5892,12 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, if (status) goto unlock; + /* Drop the connection if it has been aborted */ + if (test_bit(HCI_CONN_CANCEL, &conn->flags)) { + hci_conn_drop(conn); + goto unlock; + } + if (conn->dst_type == ADDR_LE_DEV_PUBLIC) addr_type = BDADDR_LE_PUBLIC; else @@ -6995,7 +6991,7 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, bis->iso_qos.in.latency = le16_to_cpu(ev->interval) * 125 / 100; bis->iso_qos.in.sdu = le16_to_cpu(ev->max_pdu); - hci_connect_cfm(bis, ev->status); + hci_iso_setup_path(bis); } hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 5a6aa1627791..632be1267288 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -246,8 +246,9 @@ int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen, skb = __hci_cmd_sync_sk(hdev, opcode, plen, param, event, timeout, sk); if (IS_ERR(skb)) { - bt_dev_err(hdev, "Opcode 0x%4x failed: %ld", opcode, - PTR_ERR(skb)); + if (!event) + bt_dev_err(hdev, "Opcode 0x%4x failed: %ld", opcode, + PTR_ERR(skb)); return PTR_ERR(skb); } @@ -5126,8 +5127,11 @@ static int hci_le_connect_cancel_sync(struct hci_dev *hdev, if (test_bit(HCI_CONN_SCANNING, &conn->flags)) return 0; + if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + return 0; + return __hci_cmd_sync_status(hdev, HCI_OP_LE_CREATE_CONN_CANCEL, - 6, &conn->dst, HCI_CMD_TIMEOUT); + 0, NULL, HCI_CMD_TIMEOUT); } static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn) @@ -6102,6 +6106,9 @@ int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) conn->conn_timeout, NULL); done: + if (err == -ETIMEDOUT) + hci_le_connect_cancel_sync(hdev, conn); + /* Re-enable advertising after the connection attempt is finished. */ hci_resume_advertising_sync(hdev); return err; diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index bed1a7b9205c..707f229f896a 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -433,7 +433,7 @@ static void hidp_set_timer(struct hidp_session *session) static void hidp_del_timer(struct hidp_session *session) { if (session->idle_to > 0) - del_timer(&session->timer); + del_timer_sync(&session->timer); } static void hidp_process_report(struct hidp_session *session, int type, diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 49926f59cc12..55a7226233f9 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4652,33 +4652,27 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, BT_DBG("scid 0x%4.4x dcid 0x%4.4x", scid, dcid); - mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, dcid); + chan = l2cap_get_chan_by_scid(conn, dcid); if (!chan) { - mutex_unlock(&conn->chan_lock); cmd_reject_invalid_cid(conn, cmd->ident, dcid, scid); return 0; } - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - rsp.dcid = cpu_to_le16(chan->scid); rsp.scid = cpu_to_le16(chan->dcid); l2cap_send_cmd(conn, cmd->ident, L2CAP_DISCONN_RSP, sizeof(rsp), &rsp); chan->ops->set_shutdown(chan); + mutex_lock(&conn->chan_lock); l2cap_chan_del(chan, ECONNRESET); + mutex_unlock(&conn->chan_lock); chan->ops->close(chan); l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); - return 0; } @@ -4698,33 +4692,27 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, BT_DBG("dcid 0x%4.4x scid 0x%4.4x", dcid, scid); - mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, scid); + chan = l2cap_get_chan_by_scid(conn, scid); if (!chan) { mutex_unlock(&conn->chan_lock); return 0; } - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - if (chan->state != BT_DISCONN) { l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); return 0; } + mutex_lock(&conn->chan_lock); l2cap_chan_del(chan, 0); + mutex_unlock(&conn->chan_lock); chan->ops->close(chan); l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); - return 0; } diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 1111da4e2f2b..cd1a27ac555d 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -235,27 +235,41 @@ static int sco_chan_add(struct sco_conn *conn, struct sock *sk, return err; } -static int sco_connect(struct hci_dev *hdev, struct sock *sk) +static int sco_connect(struct sock *sk) { struct sco_conn *conn; struct hci_conn *hcon; + struct hci_dev *hdev; int err, type; BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst); + hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); + if (!hdev) + return -EHOSTUNREACH; + + hci_dev_lock(hdev); + if (lmp_esco_capable(hdev) && !disable_esco) type = ESCO_LINK; else type = SCO_LINK; if (sco_pi(sk)->setting == BT_VOICE_TRANSPARENT && - (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) - return -EOPNOTSUPP; + (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) { + err = -EOPNOTSUPP; + goto unlock; + } hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, sco_pi(sk)->setting, &sco_pi(sk)->codec); - if (IS_ERR(hcon)) - return PTR_ERR(hcon); + if (IS_ERR(hcon)) { + err = PTR_ERR(hcon); + goto unlock; + } + + hci_dev_unlock(hdev); + hci_dev_put(hdev); conn = sco_conn_add(hcon); if (!conn) { @@ -263,13 +277,15 @@ static int sco_connect(struct hci_dev *hdev, struct sock *sk) return -ENOMEM; } - /* Update source addr of the socket */ - bacpy(&sco_pi(sk)->src, &hcon->src); - err = sco_chan_add(conn, sk, NULL); if (err) return err; + lock_sock(sk); + + /* Update source addr of the socket */ + bacpy(&sco_pi(sk)->src, &hcon->src); + if (hcon->state == BT_CONNECTED) { sco_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; @@ -278,6 +294,13 @@ static int sco_connect(struct hci_dev *hdev, struct sock *sk) sco_sock_set_timer(sk, sk->sk_sndtimeo); } + release_sock(sk); + + return err; + +unlock: + hci_dev_unlock(hdev); + hci_dev_put(hdev); return err; } @@ -565,7 +588,6 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; - struct hci_dev *hdev; int err; BT_DBG("sk %p", sk); @@ -574,37 +596,26 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen addr->sa_family != AF_BLUETOOTH) return -EINVAL; - lock_sock(sk); - if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) { - err = -EBADFD; - goto done; - } + if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) + return -EBADFD; - if (sk->sk_type != SOCK_SEQPACKET) { + if (sk->sk_type != SOCK_SEQPACKET) err = -EINVAL; - goto done; - } - - hdev = hci_get_route(&sa->sco_bdaddr, &sco_pi(sk)->src, BDADDR_BREDR); - if (!hdev) { - err = -EHOSTUNREACH; - goto done; - } - hci_dev_lock(hdev); + lock_sock(sk); /* Set destination address and psm */ bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr); + release_sock(sk); - err = sco_connect(hdev, sk); - hci_dev_unlock(hdev); - hci_dev_put(hdev); + err = sco_connect(sk); if (err) - goto done; + return err; + + lock_sock(sk); err = bt_sock_wait_state(sk, BT_CONNECTED, sock_sndtimeo(sk, flags & O_NONBLOCK)); -done: release_sock(sk); return err; } @@ -1129,6 +1140,8 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, break; } + release_sock(sk); + /* find total buffer size required to copy codec + caps */ hci_dev_lock(hdev); list_for_each_entry(c, &hdev->local_codecs, list) { @@ -1146,15 +1159,13 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, buf_len += sizeof(struct bt_codecs); if (buf_len > len) { hci_dev_put(hdev); - err = -ENOBUFS; - break; + return -ENOBUFS; } ptr = optval; if (put_user(num_codecs, ptr)) { hci_dev_put(hdev); - err = -EFAULT; - break; + return -EFAULT; } ptr += sizeof(num_codecs); @@ -1194,12 +1205,14 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, ptr += len; } - if (!err && put_user(buf_len, optlen)) - err = -EFAULT; - hci_dev_unlock(hdev); hci_dev_put(hdev); + lock_sock(sk); + + if (!err && put_user(buf_len, optlen)) + err = -EFAULT; + break; default: diff --git a/net/core/dev.c b/net/core/dev.c index 480600a075ce..c7f13742b56c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3197,6 +3197,7 @@ static u16 skb_tx_hash(const struct net_device *dev, } if (skb_rx_queue_recorded(skb)) { + DEBUG_NET_WARN_ON_ONCE(qcount == 0); hash = skb_get_rx_queue(skb); if (hash >= qoffset) hash -= qoffset; @@ -10870,7 +10871,7 @@ void unregister_netdevice_many_notify(struct list_head *head, dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, GFP_KERNEL, NULL, 0, - portid, nlmsg_seq(nlh)); + portid, nlh); /* * Flush the unicast and multicast chains diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 906aebdc566b..e844d75220fb 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3975,16 +3975,23 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned int change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex, u32 portid, u32 seq) + int new_ifindex, u32 portid, + const struct nlmsghdr *nlh) { struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; + u32 seq = 0; skb = nlmsg_new(if_nlmsg_size(dev, 0), flags); if (skb == NULL) goto errout; + if (nlmsg_report(nlh)) + seq = nlmsg_seq(nlh); + else + portid = 0; + err = rtnl_fill_ifinfo(skb, dev, dev_net(dev), type, portid, seq, change, 0, 0, event, new_nsid, new_ifindex, -1, flags); @@ -4020,7 +4027,7 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev, return; skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid, - new_ifindex, portid, nlmsg_seq(nlh)); + new_ifindex, portid, nlh); if (skb) rtmsg_ifinfo_send(skb, dev, flags, portid, nlh); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 050a875d09c5..78238a13dbcf 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5597,18 +5597,18 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_cloned(to)) return false; - /* In general, avoid mixing slab allocated and page_pool allocated - * pages within the same SKB. However when @to is not pp_recycle and - * @from is cloned, we can transition frag pages from page_pool to - * reference counted. - * - * On the other hand, don't allow coalescing two pp_recycle SKBs if - * @from is cloned, in case the SKB is using page_pool fragment + /* In general, avoid mixing page_pool and non-page_pool allocated + * pages within the same SKB. Additionally avoid dealing with clones + * with page_pool pages, in case the SKB is using page_pool fragment * references (PP_FLAG_PAGE_FRAG). Since we only take full page * references for cloned SKBs at the moment that would result in * inconsistent reference counts. + * In theory we could take full references if @from is cloned and + * !@to->pp_recycle but its tricky (due to potential race with + * the clone disappearing) and rare, so not worth dealing with. */ - if (to->pp_recycle != (from->pp_recycle && !skb_cloned(from))) + if (to->pp_recycle != from->pp_recycle || + (from->pp_recycle && skb_cloned(from))) return false; if (len <= skb_tailroom(to)) { diff --git a/net/core/xdp.c b/net/core/xdp.c index 528d4b37983d..fb85aca81961 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -734,13 +734,21 @@ __bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *tim * bpf_xdp_metadata_rx_hash - Read XDP frame RX hash. * @ctx: XDP context pointer. * @hash: Return value pointer. + * @rss_type: Return value pointer for RSS type. + * + * The RSS hash type (@rss_type) specifies what portion of packet headers NIC + * hardware used when calculating RSS hash value. The RSS type can be decoded + * via &enum xdp_rss_hash_type either matching on individual L3/L4 bits + * ``XDP_RSS_L*`` or by combined traditional *RSS Hashing Types* + * ``XDP_RSS_TYPE_L*``. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : means device driver doesn't implement kfunc * * ``-ENODATA`` : means no RX-hash available for this frame */ -__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash) +__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) { return -EOPNOTSUPP; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0d0cc4ef2b85..40fe70fc2015 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -25,6 +25,7 @@ static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; static int tcp_adv_win_scale_min = -31; static int tcp_adv_win_scale_max = 31; +static int tcp_app_win_max = 31; static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS; static int tcp_min_snd_mss_max = 65535; static int ip_privileged_port_min; @@ -1198,6 +1199,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &tcp_app_win_max, }, { .procname = "tcp_adv_win_scale", diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 89daa6b953ff..39bda2b1066e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2780,7 +2780,7 @@ static int tcp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, static void bpf_iter_tcp_put_batch(struct bpf_tcp_iter_state *iter) { while (iter->cur_sk < iter->end_sk) - sock_put(iter->batch[iter->cur_sk++]); + sock_gen_put(iter->batch[iter->cur_sk++]); } static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter, @@ -2941,7 +2941,7 @@ static void *bpf_iter_tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) * st->bucket. See tcp_seek_last_pos(). */ st->offset++; - sock_put(iter->batch[iter->cur_sk++]); + sock_gen_put(iter->batch[iter->cur_sk++]); } if (iter->cur_sk < iter->end_sk) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 4caa70a1b871..e5a337e6b970 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1397,9 +1397,11 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); do_udp_sendmsg: - if (ipv6_only_sock(sk)) - return -ENETUNREACH; - return udp_sendmsg(sk, msg, len); + err = ipv6_only_sock(sk) ? + -ENETUNREACH : udp_sendmsg(sk, msg, len); + msg->msg_name = sin6; + msg->msg_namelen = addr_len; + return err; } } diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index d237d142171c..bceaab8dd8e4 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -9,11 +9,18 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow, struct request_sock *req) { - struct sock *ssk = subflow->tcp_sock; - struct sock *sk = subflow->conn; + struct sock *sk, *ssk; struct sk_buff *skb; struct tcp_sock *tp; + /* on early fallback the subflow context is deleted by + * subflow_syn_recv_sock() + */ + if (!subflow) + return; + + ssk = subflow->tcp_sock; + sk = subflow->conn; tp = tcp_sk(ssk); subflow->is_mptfo = 1; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index b30cea2fbf3f..355f798d575a 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1192,9 +1192,8 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) */ if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { if (mp_opt.data_fin && mp_opt.data_len == 1 && - mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64) && - schedule_work(&msk->work)) - sock_hold(subflow->conn); + mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64)) + mptcp_schedule_work((struct sock *)msk); return true; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 2d26b9114373..e6cb36784a68 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2626,7 +2626,7 @@ static void mptcp_worker(struct work_struct *work) lock_sock(sk); state = sk->sk_state; - if (unlikely(state == TCP_CLOSE)) + if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN))) goto unlock; mptcp_check_data_fin_ack(sk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 33dd27765116..f46d8f6c40aa 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -408,9 +408,8 @@ void mptcp_subflow_reset(struct sock *ssk) tcp_send_active_reset(ssk, GFP_ATOMIC); tcp_done(ssk); - if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags) && - schedule_work(&mptcp_sk(sk)->work)) - return; /* worker will put sk for us */ + if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags)) + mptcp_schedule_work(sk); sock_put(sk); } @@ -1101,8 +1100,8 @@ static enum mapping_status get_mapping_status(struct sock *ssk, skb_ext_del(skb, SKB_EXT_MPTCP); return MAPPING_OK; } else { - if (updated && schedule_work(&msk->work)) - sock_hold((struct sock *)msk); + if (updated) + mptcp_schedule_work((struct sock *)msk); return MAPPING_DATA_FIN; } @@ -1205,17 +1204,12 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, /* sched mptcp worker to remove the subflow if no more data is pending */ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk) { - struct sock *sk = (struct sock *)msk; - if (likely(ssk->sk_state != TCP_CLOSE)) return; if (skb_queue_empty(&ssk->sk_receive_queue) && - !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) { - sock_hold(sk); - if (!schedule_work(&msk->work)) - sock_put(sk); - } + !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) + mptcp_schedule_work((struct sock *)msk); } static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index ca3ebfdb3023..a8cf9a88758e 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -913,7 +913,7 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, { struct vport *vport = ovs_vport_rcu(dp, out_port); - if (likely(vport)) { + if (likely(vport && netif_carrier_ok(vport->dev))) { u16 mru = OVS_CB(skb)->mru; u32 cutlen = OVS_CB(skb)->cutlen; diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index 3a70255c8d02..76f0434d3d06 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -498,6 +498,11 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (!size || len != ALIGN(size, 4) + hdrlen) goto err; + if ((cb->type == QRTR_TYPE_NEW_SERVER || + cb->type == QRTR_TYPE_RESUME_TX) && + size < sizeof(struct qrtr_ctrl_pkt)) + goto err; + if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA && cb->type != QRTR_TYPE_RESUME_TX) goto err; @@ -510,9 +515,6 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) /* Remote node endpoint can bridge other distant nodes */ const struct qrtr_ctrl_pkt *pkt; - if (size < sizeof(*pkt)) - goto err; - pkt = data + hdrlen; qrtr_node_assign(node, le32_to_cpu(pkt->server.node)); } diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c index 94727feb07b3..b046b11200c9 100644 --- a/net/sctp/stream_interleave.c +++ b/net/sctp/stream_interleave.c @@ -1154,7 +1154,8 @@ static void sctp_generate_iftsn(struct sctp_outq *q, __u32 ctsn) #define _sctp_walk_ifwdtsn(pos, chunk, end) \ for (pos = chunk->subh.ifwdtsn_hdr->skip; \ - (void *)pos < (void *)chunk->subh.ifwdtsn_hdr->skip + (end); pos++) + (void *)pos <= (void *)chunk->subh.ifwdtsn_hdr->skip + (end) - \ + sizeof(struct sctp_ifwdtsn_skip); pos++) #define sctp_walk_ifwdtsn(pos, ch) \ _sctp_walk_ifwdtsn((pos), (ch), ntohs((ch)->chunk_hdr->length) - \ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c6b4a62276f6..50c38b624f77 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -3270,6 +3270,17 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol, sk_common_release(sk); goto out; } + + /* smc_clcsock_release() does not wait smc->clcsock->sk's + * destruction; its sk_state might not be TCP_CLOSE after + * smc->sk is close()d, and TCP timers can be fired later, + * which need net ref. + */ + sk = smc->clcsock->sk; + __netns_tracker_free(net, &sk->ns_tracker, false); + sk->sk_net_refcnt = 1; + get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); } else { smc->clcsock = clcsock; } diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 958ee9bdb316..4c89ff333f6f 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -108,6 +108,7 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mn->slot[1] != NULL); MT_BUG_ON(mt, mas_allocated(&mas) != 0); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); mas.node = MAS_START; mas_nomem(&mas, GFP_KERNEL); @@ -160,6 +161,7 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas_allocated(&mas) != i); MT_BUG_ON(mt, !mn); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } @@ -192,6 +194,7 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, not_empty(mn)); MT_BUG_ON(mt, mas_allocated(&mas) != i - 1); MT_BUG_ON(mt, !mn); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } @@ -210,6 +213,7 @@ static noinline void check_new_node(struct maple_tree *mt) mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); MT_BUG_ON(mt, mas_allocated(&mas) != j - 1); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } MT_BUG_ON(mt, mas_allocated(&mas) != 0); @@ -233,6 +237,7 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas_allocated(&mas) != i - j); mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); MT_BUG_ON(mt, mas_allocated(&mas) != i - j - 1); } @@ -269,6 +274,7 @@ static noinline void check_new_node(struct maple_tree *mt) mn = mas_pop_node(&mas); /* get the next node. */ MT_BUG_ON(mt, mn == NULL); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } MT_BUG_ON(mt, mas_allocated(&mas) != 0); @@ -294,6 +300,7 @@ static noinline void check_new_node(struct maple_tree *mt) mn = mas_pop_node(&mas2); /* get the next node. */ MT_BUG_ON(mt, mn == NULL); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } MT_BUG_ON(mt, mas_allocated(&mas2) != 0); @@ -334,10 +341,12 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 2); mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); for (i = 1; i <= MAPLE_ALLOC_SLOTS + 1; i++) { mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } MT_BUG_ON(mt, mas_allocated(&mas) != 0); @@ -375,6 +384,7 @@ static noinline void check_new_node(struct maple_tree *mt) mas_node_count(&mas, i); /* Request */ mas_nomem(&mas, GFP_KERNEL); /* Fill request */ mn = mas_pop_node(&mas); /* get the next node. */ + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); mas_destroy(&mas); @@ -382,10 +392,13 @@ static noinline void check_new_node(struct maple_tree *mt) mas_node_count(&mas, i); /* Request */ mas_nomem(&mas, GFP_KERNEL); /* Fill request */ mn = mas_pop_node(&mas); /* get the next node. */ + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); mn = mas_pop_node(&mas); /* get the next node. */ + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); mn = mas_pop_node(&mas); /* get the next node. */ + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); mas_destroy(&mas); } @@ -35369,6 +35382,7 @@ static noinline void check_prealloc(struct maple_tree *mt) MT_BUG_ON(mt, allocated != 1 + height * 3); mn = mas_pop_node(&mas); MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); mas_destroy(&mas); @@ -35386,6 +35400,7 @@ static noinline void check_prealloc(struct maple_tree *mt) mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); @@ -35756,6 +35771,7 @@ void farmer_tests(void) tree.ma_root = mt_mk_node(node, maple_leaf_64); mt_dump(&tree); + node->parent = ma_parent_ptr(node); ma_free_rcu(node); /* Check things that will make lockdep angry */ diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c index 662b6c6c5ed7..fde13010980d 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c @@ -159,8 +159,7 @@ void test_xdp_do_redirect(void) if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | - NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | - NETDEV_XDP_ACT_NDO_XMIT_SG, + NETDEV_XDP_ACT_RX_SG, "veth_src query_opts.feature_flags")) goto out; @@ -168,11 +167,36 @@ void test_xdp_do_redirect(void) if (!ASSERT_OK(err, "veth_dst bpf_xdp_query")) goto out; + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG, + "veth_dst query_opts.feature_flags")) + goto out; + + /* Enable GRO */ + SYS("ethtool -K veth_src gro on"); + SYS("ethtool -K veth_dst gro on"); + + err = bpf_xdp_query(ifindex_src, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "veth_src bpf_xdp_query gro on")) + goto out; + if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | NETDEV_XDP_ACT_NDO_XMIT_SG, - "veth_dst query_opts.feature_flags")) + "veth_src query_opts.feature_flags gro on")) + goto out; + + err = bpf_xdp_query(ifindex_dst, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "veth_dst bpf_xdp_query gro on")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "veth_dst query_opts.feature_flags gro on")) goto out; memcpy(skel->rodata->expect_dst, &pkt_udp.eth.h_dest, ETH_ALEN); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c index 490e851dc27d..626c461fa34d 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -268,6 +268,8 @@ static int verify_xsk_metadata(struct xsk *xsk) if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash")) return -1; + ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type"); + xsk_ring_cons__release(&xsk->rx, 1); refill_rx(xsk, comp_addr); diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index 4c55b4d79d3d..e1c787815e44 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -12,10 +12,14 @@ struct { __type(value, __u32); } xsk SEC(".maps"); +__u64 pkts_skip = 0; +__u64 pkts_fail = 0; +__u64 pkts_redir = 0; + extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, __u64 *timestamp) __ksym; -extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, - __u32 *hash) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; SEC("xdp") int rx(struct xdp_md *ctx) @@ -26,7 +30,7 @@ int rx(struct xdp_md *ctx) struct udphdr *udp = NULL; struct iphdr *iph = NULL; struct xdp_meta *meta; - int ret; + int err; data = (void *)(long)ctx->data; data_end = (void *)(long)ctx->data_end; @@ -46,17 +50,20 @@ int rx(struct xdp_md *ctx) udp = NULL; } - if (!udp) + if (!udp) { + __sync_add_and_fetch(&pkts_skip, 1); return XDP_PASS; + } - if (udp->dest != bpf_htons(9091)) + /* Forwarding UDP:9091 to AF_XDP */ + if (udp->dest != bpf_htons(9091)) { + __sync_add_and_fetch(&pkts_skip, 1); return XDP_PASS; + } - bpf_printk("forwarding UDP:9091 to AF_XDP"); - - ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta)); - if (ret != 0) { - bpf_printk("bpf_xdp_adjust_meta returned %d", ret); + err = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta)); + if (err) { + __sync_add_and_fetch(&pkts_fail, 1); return XDP_PASS; } @@ -65,20 +72,19 @@ int rx(struct xdp_md *ctx) meta = data_meta; if (meta + 1 > data) { - bpf_printk("bpf_xdp_adjust_meta doesn't appear to work"); + __sync_add_and_fetch(&pkts_fail, 1); return XDP_PASS; } - if (!bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp)) - bpf_printk("populated rx_timestamp with %llu", meta->rx_timestamp); - else + err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp); + if (err) meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */ - if (!bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash)) - bpf_printk("populated rx_hash with %u", meta->rx_hash); - else - meta->rx_hash = 0; /* Used by AF_XDP as not avail signal */ + err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); + if (err < 0) + meta->rx_hash_err = err; /* Used by AF_XDP as no hash signal */ + __sync_add_and_fetch(&pkts_redir, 1); return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); } diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c index 77678b034389..d151d406a123 100644 --- a/tools/testing/selftests/bpf/progs/xdp_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c @@ -21,8 +21,8 @@ struct { extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, __u64 *timestamp) __ksym; -extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, - __u32 *hash) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; SEC("xdp") int rx(struct xdp_md *ctx) @@ -56,7 +56,7 @@ int rx(struct xdp_md *ctx) if (timestamp == 0) meta->rx_timestamp = 1; - bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash); + bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); } diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata2.c b/tools/testing/selftests/bpf/progs/xdp_metadata2.c index cf69d05451c3..85f88d9d7a78 100644 --- a/tools/testing/selftests/bpf/progs/xdp_metadata2.c +++ b/tools/testing/selftests/bpf/progs/xdp_metadata2.c @@ -5,17 +5,18 @@ #include #include -extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, - __u32 *hash) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; int called; SEC("freplace/rx") int freplace_rx(struct xdp_md *ctx) { + enum xdp_rss_hash_type type = 0; u32 hash = 0; /* Call _any_ metadata function to make sure we don't crash. */ - bpf_xdp_metadata_rx_hash(ctx, &hash); + bpf_xdp_metadata_rx_hash(ctx, &hash, &type); called++; return XDP_PASS; } diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 1c8acb68b977..987cf0db5ebc 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -141,7 +141,11 @@ static void verify_xdp_metadata(void *data) meta = data - sizeof(*meta); printf("rx_timestamp: %llu\n", meta->rx_timestamp); - printf("rx_hash: %u\n", meta->rx_hash); + if (meta->rx_hash_err < 0) + printf("No rx_hash err=%d\n", meta->rx_hash_err); + else + printf("rx_hash: 0x%X with RSS type:0x%X\n", + meta->rx_hash, meta->rx_hash_type); } static void verify_skb_metadata(int fd) @@ -212,7 +216,9 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd) while (true) { errno = 0; ret = poll(fds, rxq + 1, 1000); - printf("poll: %d (%d)\n", ret, errno); + printf("poll: %d (%d) skip=%llu fail=%llu redir=%llu\n", + ret, errno, bpf_obj->bss->pkts_skip, + bpf_obj->bss->pkts_fail, bpf_obj->bss->pkts_redir); if (ret < 0) break; if (ret == 0) diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h index f6780fbb0a21..0c4624dc6f2f 100644 --- a/tools/testing/selftests/bpf/xdp_metadata.h +++ b/tools/testing/selftests/bpf/xdp_metadata.h @@ -12,4 +12,8 @@ struct xdp_meta { __u64 rx_timestamp; __u32 rx_hash; + union { + __u32 rx_hash_type; + __s32 rx_hash_err; + }; }; diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index a39bb2560d9b..03f92d7aeb19 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -8,11 +8,12 @@ TEST_PROGS := \ dev_addr_lists.sh \ mode-1-recovery-updelay.sh \ mode-2-recovery-updelay.sh \ - option_prio.sh \ + bond_options.sh \ bond-eth-type-change.sh TEST_FILES := \ lag_lib.sh \ + bond_topo_3d1c.sh \ net_forwarding_lib.sh include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh new file mode 100755 index 000000000000..db29a3146a86 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -0,0 +1,264 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test bonding options with mode 1,5,6 + +ALL_TESTS=" + prio + arp_validate +" + +REQUIRE_MZ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +source ${lib_dir}/net_forwarding_lib.sh +source ${lib_dir}/bond_topo_3d1c.sh + +skip_prio() +{ + local skip=1 + + # check if iproute support prio option + ip -n ${s_ns} link set eth0 type bond_slave prio 10 + [[ $? -ne 0 ]] && skip=0 + + # check if kernel support prio option + ip -n ${s_ns} -d link show eth0 | grep -q "prio 10" + [[ $? -ne 0 ]] && skip=0 + + return $skip +} + +skip_ns() +{ + local skip=1 + + # check if iproute support ns_ip6_target option + ip -n ${s_ns} link add bond1 type bond ns_ip6_target ${g_ip6} + [[ $? -ne 0 ]] && skip=0 + + # check if kernel support ns_ip6_target option + ip -n ${s_ns} -d link show bond1 | grep -q "ns_ip6_target ${g_ip6}" + [[ $? -ne 0 ]] && skip=0 + + ip -n ${s_ns} link del bond1 + + return $skip +} + +active_slave="" +check_active_slave() +{ + local target_active_slave=$1 + active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + test "$active_slave" = "$target_active_slave" + check_err $? "Current active slave is $active_slave but not $target_active_slave" +} + + +# Test bonding prio option +prio_test() +{ + local param="$1" + RET=0 + + # create bond + bond_reset "${param}" + + # check bonding member prio value + ip -n ${s_ns} link set eth0 type bond_slave prio 0 + ip -n ${s_ns} link set eth1 type bond_slave prio 10 + ip -n ${s_ns} link set eth2 type bond_slave prio 11 + cmd_jq "ip -n ${s_ns} -d -j link show eth0" \ + ".[].linkinfo.info_slave_data | select (.prio == 0)" "-e" &> /dev/null + check_err $? "eth0 prio is not 0" + cmd_jq "ip -n ${s_ns} -d -j link show eth1" \ + ".[].linkinfo.info_slave_data | select (.prio == 10)" "-e" &> /dev/null + check_err $? "eth1 prio is not 10" + cmd_jq "ip -n ${s_ns} -d -j link show eth2" \ + ".[].linkinfo.info_slave_data | select (.prio == 11)" "-e" &> /dev/null + check_err $? "eth2 prio is not 11" + + bond_check_connection "setup" + + # active slave should be the primary slave + check_active_slave eth1 + + # active slave should be the higher prio slave + ip -n ${s_ns} link set $active_slave down + bond_check_connection "fail over" + check_active_slave eth2 + + # when only 1 slave is up + ip -n ${s_ns} link set $active_slave down + bond_check_connection "only 1 slave up" + check_active_slave eth0 + + # when a higher prio slave change to up + ip -n ${s_ns} link set eth2 up + bond_check_connection "higher prio slave up" + case $primary_reselect in + "0") + check_active_slave "eth2" + ;; + "1") + check_active_slave "eth0" + ;; + "2") + check_active_slave "eth0" + ;; + esac + local pre_active_slave=$active_slave + + # when the primary slave change to up + ip -n ${s_ns} link set eth1 up + bond_check_connection "primary slave up" + case $primary_reselect in + "0") + check_active_slave "eth1" + ;; + "1") + check_active_slave "$pre_active_slave" + ;; + "2") + check_active_slave "$pre_active_slave" + ip -n ${s_ns} link set $active_slave down + bond_check_connection "pre_active slave down" + check_active_slave "eth1" + ;; + esac + + # Test changing bond slave prio + if [[ "$primary_reselect" == "0" ]];then + ip -n ${s_ns} link set eth0 type bond_slave prio 1000000 + ip -n ${s_ns} link set eth1 type bond_slave prio 0 + ip -n ${s_ns} link set eth2 type bond_slave prio -50 + ip -n ${s_ns} -d link show eth0 | grep -q 'prio 1000000' + check_err $? "eth0 prio is not 1000000" + ip -n ${s_ns} -d link show eth1 | grep -q 'prio 0' + check_err $? "eth1 prio is not 0" + ip -n ${s_ns} -d link show eth2 | grep -q 'prio -50' + check_err $? "eth3 prio is not -50" + check_active_slave "eth1" + + ip -n ${s_ns} link set $active_slave down + bond_check_connection "change slave prio" + check_active_slave "eth0" + fi +} + +prio_miimon() +{ + local primary_reselect + local mode=$1 + + for primary_reselect in 0 1 2; do + prio_test "mode $mode miimon 100 primary eth1 primary_reselect $primary_reselect" + log_test "prio" "$mode miimon primary_reselect $primary_reselect" + done +} + +prio_arp() +{ + local primary_reselect + local mode=$1 + + for primary_reselect in 0 1 2; do + prio_test "mode active-backup arp_interval 100 arp_ip_target ${g_ip4} primary eth1 primary_reselect $primary_reselect" + log_test "prio" "$mode arp_ip_target primary_reselect $primary_reselect" + done +} + +prio_ns() +{ + local primary_reselect + local mode=$1 + + if skip_ns; then + log_test_skip "prio ns" "Current iproute or kernel doesn't support bond option 'ns_ip6_target'." + return 0 + fi + + for primary_reselect in 0 1 2; do + prio_test "mode active-backup arp_interval 100 ns_ip6_target ${g_ip6} primary eth1 primary_reselect $primary_reselect" + log_test "prio" "$mode ns_ip6_target primary_reselect $primary_reselect" + done +} + +prio() +{ + local mode modes="active-backup balance-tlb balance-alb" + + if skip_prio; then + log_test_skip "prio" "Current iproute or kernel doesn't support bond option 'prio'." + return 0 + fi + + for mode in $modes; do + prio_miimon $mode + prio_arp $mode + prio_ns $mode + done +} + +arp_validate_test() +{ + local param="$1" + RET=0 + + # create bond + bond_reset "${param}" + + bond_check_connection + [ $RET -ne 0 ] && log_test "arp_validate" "$retmsg" + + # wait for a while to make sure the mii status stable + sleep 5 + for i in $(seq 0 2); do + mii_status=$(cmd_jq "ip -n ${s_ns} -j -d link show eth$i" ".[].linkinfo.info_slave_data.mii_status") + if [ ${mii_status} != "UP" ]; then + RET=1 + log_test "arp_validate" "interface eth$i mii_status $mii_status" + fi + done +} + +arp_validate_arp() +{ + local mode=$1 + local val + for val in $(seq 0 6); do + arp_validate_test "mode $mode arp_interval 100 arp_ip_target ${g_ip4} arp_validate $val" + log_test "arp_validate" "$mode arp_ip_target arp_validate $val" + done +} + +arp_validate_ns() +{ + local mode=$1 + local val + + if skip_ns; then + log_test_skip "arp_validate ns" "Current iproute or kernel doesn't support bond option 'ns_ip6_target'." + return 0 + fi + + for val in $(seq 0 6); do + arp_validate_test "mode $mode arp_interval 100 ns_ip6_target ${g_ip6} arp_validate $val" + log_test "arp_validate" "$mode ns_ip6_target arp_validate $val" + done +} + +arp_validate() +{ + arp_validate_arp "active-backup" + arp_validate_ns "active-backup" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh new file mode 100644 index 000000000000..4045ca97fb22 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh @@ -0,0 +1,143 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Topology for Bond mode 1,5,6 testing +# +# +-------------------------------------+ +# | bond0 | +# | + | Server +# | eth0 | eth1 eth2 | 192.0.2.1/24 +# | +-------------------+ | 2001:db8::1/24 +# | | | | | +# +-------------------------------------+ +# | | | +# +-------------------------------------+ +# | | | | | +# | +---+---------+---------+---+ | Gateway +# | | br0 | | 192.0.2.254/24 +# | +-------------+-------------+ | 2001:db8::254/24 +# | | | +# +-------------------------------------+ +# | +# +-------------------------------------+ +# | | | Client +# | + | 192.0.2.10/24 +# | eth0 | 2001:db8::10/24 +# +-------------------------------------+ + +s_ns="s-$(mktemp -u XXXXXX)" +c_ns="c-$(mktemp -u XXXXXX)" +g_ns="g-$(mktemp -u XXXXXX)" +s_ip4="192.0.2.1" +c_ip4="192.0.2.10" +g_ip4="192.0.2.254" +s_ip6="2001:db8::1" +c_ip6="2001:db8::10" +g_ip6="2001:db8::254" + +gateway_create() +{ + ip netns add ${g_ns} + ip -n ${g_ns} link add br0 type bridge + ip -n ${g_ns} link set br0 up + ip -n ${g_ns} addr add ${g_ip4}/24 dev br0 + ip -n ${g_ns} addr add ${g_ip6}/24 dev br0 +} + +gateway_destroy() +{ + ip -n ${g_ns} link del br0 + ip netns del ${g_ns} +} + +server_create() +{ + ip netns add ${s_ns} + ip -n ${s_ns} link add bond0 type bond mode active-backup miimon 100 + + for i in $(seq 0 2); do + ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns} + + ip -n ${g_ns} link set s${i} up + ip -n ${g_ns} link set s${i} master br0 + ip -n ${s_ns} link set eth${i} master bond0 + done + + ip -n ${s_ns} link set bond0 up + ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0 + ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0 + sleep 2 +} + +# Reset bond with new mode and options +bond_reset() +{ + local param="$1" + + ip -n ${s_ns} link set bond0 down + ip -n ${s_ns} link del bond0 + + ip -n ${s_ns} link add bond0 type bond $param + for i in $(seq 0 2); do + ip -n ${s_ns} link set eth$i master bond0 + done + + ip -n ${s_ns} link set bond0 up + ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0 + ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0 + sleep 2 +} + +server_destroy() +{ + for i in $(seq 0 2); do + ip -n ${s_ns} link del eth${i} + done + ip netns del ${s_ns} +} + +client_create() +{ + ip netns add ${c_ns} + ip -n ${c_ns} link add eth0 type veth peer name c0 netns ${g_ns} + + ip -n ${g_ns} link set c0 up + ip -n ${g_ns} link set c0 master br0 + + ip -n ${c_ns} link set eth0 up + ip -n ${c_ns} addr add ${c_ip4}/24 dev eth0 + ip -n ${c_ns} addr add ${c_ip6}/24 dev eth0 +} + +client_destroy() +{ + ip -n ${c_ns} link del eth0 + ip netns del ${c_ns} +} + +setup_prepare() +{ + gateway_create + server_create + client_create +} + +cleanup() +{ + pre_cleanup + + client_destroy + server_destroy + gateway_destroy +} + +bond_check_connection() +{ + local msg=${1:-"check connection"} + + sleep 2 + ip netns exec ${s_ns} ping ${c_ip4} -c5 -i 0.1 &>/dev/null + check_err $? "${msg}: ping failed" + ip netns exec ${s_ns} ping6 ${c_ip6} -c5 -i 0.1 &>/dev/null + check_err $? "${msg}: ping6 failed" +} diff --git a/tools/testing/selftests/drivers/net/bonding/option_prio.sh b/tools/testing/selftests/drivers/net/bonding/option_prio.sh deleted file mode 100755 index c32eebff5005..000000000000 --- a/tools/testing/selftests/drivers/net/bonding/option_prio.sh +++ /dev/null @@ -1,245 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# Test bonding option prio -# - -ALL_TESTS=" - prio_arp_ip_target_test - prio_miimon_test -" - -REQUIRE_MZ=no -REQUIRE_JQ=no -NUM_NETIFS=0 -lib_dir=$(dirname "$0") -source "$lib_dir"/net_forwarding_lib.sh - -destroy() -{ - ip link del bond0 &>/dev/null - ip link del br0 &>/dev/null - ip link del veth0 &>/dev/null - ip link del veth1 &>/dev/null - ip link del veth2 &>/dev/null - ip netns del ns1 &>/dev/null - ip link del veth3 &>/dev/null -} - -cleanup() -{ - pre_cleanup - - destroy -} - -skip() -{ - local skip=1 - ip link add name bond0 type bond mode 1 miimon 100 &>/dev/null - ip link add name veth0 type veth peer name veth0_p - ip link set veth0 master bond0 - - # check if iproute support prio option - ip link set dev veth0 type bond_slave prio 10 - [[ $? -ne 0 ]] && skip=0 - - # check if bonding support prio option - ip -d link show veth0 | grep -q "prio 10" - [[ $? -ne 0 ]] && skip=0 - - ip link del bond0 &>/dev/null - ip link del veth0 - - return $skip -} - -active_slave="" -check_active_slave() -{ - local target_active_slave=$1 - active_slave="$(cat /sys/class/net/bond0/bonding/active_slave)" - test "$active_slave" = "$target_active_slave" - check_err $? "Current active slave is $active_slave but not $target_active_slave" -} - - -# Test bonding prio option with mode=$mode monitor=$monitor -# and primary_reselect=$primary_reselect -prio_test() -{ - RET=0 - - local monitor=$1 - local mode=$2 - local primary_reselect=$3 - - local bond_ip4="192.169.1.2" - local peer_ip4="192.169.1.1" - local bond_ip6="2009:0a:0b::02" - local peer_ip6="2009:0a:0b::01" - - - # create veths - ip link add name veth0 type veth peer name veth0_p - ip link add name veth1 type veth peer name veth1_p - ip link add name veth2 type veth peer name veth2_p - - # create bond - if [[ "$monitor" == "miimon" ]];then - ip link add name bond0 type bond mode $mode miimon 100 primary veth1 primary_reselect $primary_reselect - elif [[ "$monitor" == "arp_ip_target" ]];then - ip link add name bond0 type bond mode $mode arp_interval 1000 arp_ip_target $peer_ip4 primary veth1 primary_reselect $primary_reselect - elif [[ "$monitor" == "ns_ip6_target" ]];then - ip link add name bond0 type bond mode $mode arp_interval 1000 ns_ip6_target $peer_ip6 primary veth1 primary_reselect $primary_reselect - fi - ip link set bond0 up - ip link set veth0 master bond0 - ip link set veth1 master bond0 - ip link set veth2 master bond0 - # check bonding member prio value - ip link set dev veth0 type bond_slave prio 0 - ip link set dev veth1 type bond_slave prio 10 - ip link set dev veth2 type bond_slave prio 11 - ip -d link show veth0 | grep -q 'prio 0' - check_err $? "veth0 prio is not 0" - ip -d link show veth1 | grep -q 'prio 10' - check_err $? "veth0 prio is not 10" - ip -d link show veth2 | grep -q 'prio 11' - check_err $? "veth0 prio is not 11" - - ip link set veth0 up - ip link set veth1 up - ip link set veth2 up - ip link set veth0_p up - ip link set veth1_p up - ip link set veth2_p up - - # prepare ping target - ip link add name br0 type bridge - ip link set br0 up - ip link set veth0_p master br0 - ip link set veth1_p master br0 - ip link set veth2_p master br0 - ip link add name veth3 type veth peer name veth3_p - ip netns add ns1 - ip link set veth3_p master br0 up - ip link set veth3 netns ns1 up - ip netns exec ns1 ip addr add $peer_ip4/24 dev veth3 - ip netns exec ns1 ip addr add $peer_ip6/64 dev veth3 - ip addr add $bond_ip4/24 dev bond0 - ip addr add $bond_ip6/64 dev bond0 - sleep 5 - - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 1." - ping6 $peer_ip6 -c5 -I bond0 &>/dev/null - check_err $? "ping6 failed 1." - - # active salve should be the primary slave - check_active_slave veth1 - - # active slave should be the higher prio slave - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 2." - check_active_slave veth2 - - # when only 1 slave is up - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 3." - check_active_slave veth0 - - # when a higher prio slave change to up - ip link set veth2 up - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 4." - case $primary_reselect in - "0") - check_active_slave "veth2" - ;; - "1") - check_active_slave "veth0" - ;; - "2") - check_active_slave "veth0" - ;; - esac - local pre_active_slave=$active_slave - - # when the primary slave change to up - ip link set veth1 up - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 5." - case $primary_reselect in - "0") - check_active_slave "veth1" - ;; - "1") - check_active_slave "$pre_active_slave" - ;; - "2") - check_active_slave "$pre_active_slave" - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 6." - check_active_slave "veth1" - ;; - esac - - # Test changing bond salve prio - if [[ "$primary_reselect" == "0" ]];then - ip link set dev veth0 type bond_slave prio 1000000 - ip link set dev veth1 type bond_slave prio 0 - ip link set dev veth2 type bond_slave prio -50 - ip -d link show veth0 | grep -q 'prio 1000000' - check_err $? "veth0 prio is not 1000000" - ip -d link show veth1 | grep -q 'prio 0' - check_err $? "veth1 prio is not 0" - ip -d link show veth2 | grep -q 'prio -50' - check_err $? "veth3 prio is not -50" - check_active_slave "veth1" - - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 7." - check_active_slave "veth0" - fi - - cleanup - - log_test "prio_test" "Test bonding option 'prio' with mode=$mode monitor=$monitor and primary_reselect=$primary_reselect" -} - -prio_miimon_test() -{ - local mode - local primary_reselect - - for mode in 1 5 6; do - for primary_reselect in 0 1 2; do - prio_test "miimon" $mode $primary_reselect - done - done -} - -prio_arp_ip_target_test() -{ - local primary_reselect - - for primary_reselect in 0 1 2; do - prio_test "arp_ip_target" 1 $primary_reselect - done -} - -if skip;then - log_test_skip "option_prio.sh" "Current iproute doesn't support 'prio'." - exit 0 -fi - -trap cleanup EXIT - -tests_run - -exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 4c7ce07afa2f..d1d421ec10a3 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -49,3 +49,4 @@ CONFIG_IPV6_IOAM6_LWTUNNEL=y CONFIG_CRYPTO_SM4_GENERIC=y CONFIG_AMT=m CONFIG_VXLAN=m +CONFIG_IP_SCTP=m diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 48e52f995a98..b1eb7bce599d 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -913,6 +913,7 @@ test_listener() $client4_port > /dev/null 2>&1 & local listener_pid=$! + sleep 0.5 verify_listener_events $client_evts $LISTENER_CREATED $AF_INET 10.0.2.2 $client4_port # ADD_ADDR from client to server machine reusing the subflow port @@ -928,6 +929,7 @@ test_listener() # Delete the listener from the client ns, if one was created kill_wait $listener_pid + sleep 0.5 verify_listener_events $client_evts $LISTENER_CLOSED $AF_INET 10.0.2.2 $client4_port } diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index 3243c90d449e..5d467d1993cb 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -62,7 +62,7 @@ class OvsDatapath(GenericNetlinkSocket): nla_map = ( ("OVS_DP_ATTR_UNSPEC", "none"), ("OVS_DP_ATTR_NAME", "asciiz"), - ("OVS_DP_ATTR_UPCALL_PID", "uint32"), + ("OVS_DP_ATTR_UPCALL_PID", "array(uint32)"), ("OVS_DP_ATTR_STATS", "dpstats"), ("OVS_DP_ATTR_MEGAFLOW_STATS", "megaflowstats"), ("OVS_DP_ATTR_USER_FEATURES", "uint32"), diff --git a/tools/virtio/virtio-trace/README b/tools/virtio/virtio-trace/README index b64845b823ab..4fb9368bf751 100644 --- a/tools/virtio/virtio-trace/README +++ b/tools/virtio/virtio-trace/README @@ -61,7 +61,7 @@ and id=channel0,name=agent-ctl-path\ ##data path## -chardev pipe,id=charchannel1,path=/tmp/virtio-trace/trace-path-cpu0\ - -device virtserialport,bus=virtio-serial0.0,nr=2,chardev=charchannel0,\ + -device virtserialport,bus=virtio-serial0.0,nr=2,chardev=charchannel1,\ id=channel1,name=trace-path-cpu0\ ...