From 8a7c5ef3ba8cca8f9c4f91ddef3d081f517914ae Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Tue, 19 Aug 2008 02:13:55 +0200 Subject: [PATCH 01/20] x86 iommu: remove unneeded parenthesis The parenthesis in __iommu_queue_command() are not needed when assigning into 'target' variable. Signed-off-by: Jiri Kosina Signed-off-by: Ingo Molnar --- arch/x86/kernel/amd_iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index de39e1f2ede5..69b4d060b21c 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -65,7 +65,7 @@ static int __iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd) u8 *target; tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET); - target = (iommu->cmd_buf + tail); + target = iommu->cmd_buf + tail; memcpy_toio(target, cmd, sizeof(*cmd)); tail = (tail + sizeof(*cmd)) % iommu->cmd_buf_size; head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET); From c6744955d0ec0cb485c28c51eeb7185e260f6172 Mon Sep 17 00:00:00 2001 From: Samuel Sieb Date: Wed, 6 Aug 2008 22:06:29 -0700 Subject: [PATCH 02/20] x86: fix "kernel won't boot on a Cyrix MediaGXm (Geode)" Cyrix MediaGXm/Cx5530 Unicorn Revision 1.19.3B has stopped booting starting at v2.6.22. The reason is this commit: > commit f25f64ed5bd3c2932493681bdfdb483ea707da0a > Author: Juergen Beisert > Date: Sun Jul 22 11:12:38 2007 +0200 > > x86: Replace NSC/Cyrix specific chipset access macros by inlined functions. this commit activated a macro which was dormant before due to (buggy) macro side-effects. I've looked through various datasheets and found that the GXm and GXLV Geode processors don't have an incrementor. Remove the incrementor setup entirely. As the incrementor value differs according to clock speed and we would hope that the BIOS configures it correctly, it is probably the right solution. Cc: Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/cyrix.c | 18 ------------------ 1 file changed, 18 deletions(-) diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 3fd7a67bb06a..e710a21bb6e8 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -134,23 +134,6 @@ static void __cpuinit set_cx86_memwb(void) setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14); } -static void __cpuinit set_cx86_inc(void) -{ - unsigned char ccr3; - - printk(KERN_INFO "Enable Incrementor on Cyrix/NSC processor.\n"); - - ccr3 = getCx86(CX86_CCR3); - setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ - /* PCR1 -- Performance Control */ - /* Incrementor on, whatever that is */ - setCx86(CX86_PCR1, getCx86(CX86_PCR1) | 0x02); - /* PCR0 -- Performance Control */ - /* Incrementor Margin 10 */ - setCx86(CX86_PCR0, getCx86(CX86_PCR0) | 0x04); - setCx86(CX86_CCR3, ccr3); /* disable MAPEN */ -} - /* * Configure later MediaGX and/or Geode processor. */ @@ -174,7 +157,6 @@ static void __cpuinit geode_configure(void) set_cx86_memwb(); set_cx86_reorder(); - set_cx86_inc(); local_irq_restore(flags); } From 80c5e73d6028e0f03ab0c70e7c4cbf98ac2e0c43 Mon Sep 17 00:00:00 2001 From: Venki Pallipadi Date: Tue, 19 Aug 2008 16:28:01 -0700 Subject: [PATCH 03/20] x86: fix Xorg startup/shutdown slowdown with PAT Rene Herman reported significant Xorg startup/shutdown slowdown due to PAT. It turns out that the memtype list has thousands of entries. Add cached_entry to list add routine, in order to speed up the lookup for sequential reserve_memtype calls. Reported-by: Rene Herman Signed-off-by: Venkatesh Pallipadi Signed-off-by: Ingo Molnar --- arch/x86/mm/pat.c | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 2fe30916d4b6..bb6e8a267bfe 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -207,6 +207,9 @@ static int chk_conflict(struct memtype *new, struct memtype *entry, return -EBUSY; } +static struct memtype *cached_entry; +static u64 cached_start; + /* * req_type typically has one of the: * - _PAGE_CACHE_WB @@ -280,11 +283,17 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, spin_lock(&memtype_lock); + if (cached_entry && start >= cached_start) + entry = cached_entry; + else + entry = list_entry(&memtype_list, struct memtype, nd); + /* Search for existing mapping that overlaps the current range */ where = NULL; - list_for_each_entry(entry, &memtype_list, nd) { + list_for_each_entry_continue(entry, &memtype_list, nd) { if (end <= entry->start) { where = entry->nd.prev; + cached_entry = list_entry(where, struct memtype, nd); break; } else if (start <= entry->start) { /* end > entry->start */ err = chk_conflict(new, entry, new_type); @@ -292,6 +301,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, dprintk("Overlap at 0x%Lx-0x%Lx\n", entry->start, entry->end); where = entry->nd.prev; + cached_entry = list_entry(where, + struct memtype, nd); } break; } else if (start < entry->end) { /* start > entry->start */ @@ -299,7 +310,20 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, if (!err) { dprintk("Overlap at 0x%Lx-0x%Lx\n", entry->start, entry->end); - where = &entry->nd; + cached_entry = list_entry(entry->nd.prev, + struct memtype, nd); + + /* + * Move to right position in the linked + * list to add this new entry + */ + list_for_each_entry_continue(entry, + &memtype_list, nd) { + if (start <= entry->start) { + where = entry->nd.prev; + break; + } + } } break; } @@ -314,6 +338,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, return err; } + cached_start = start; + if (where) list_add(&new->nd, where); else @@ -343,6 +369,9 @@ int free_memtype(u64 start, u64 end) spin_lock(&memtype_lock); list_for_each_entry(entry, &memtype_list, nd) { if (entry->start == start && entry->end == end) { + if (cached_entry == entry || cached_start == start) + cached_entry = NULL; + list_del(&entry->nd); kfree(entry); err = 0; From 99dd8713306a89f3e106143581244e550e00a644 Mon Sep 17 00:00:00 2001 From: Cliff Wickman Date: Tue, 19 Aug 2008 12:51:59 -0500 Subject: [PATCH 04/20] x86, SGI UV: hardcode the TLB flush interrupt system vector The UV TLB shootdown mechanism needs a system interrupt vector. Its vector had been hardcoded as 200, but needs to moved to the reserved system vector range so that it does not collide with some device vector. This is still temporary until dynamic system IRQ allocation is provided. But it will be needed when real UV hardware becomes available and runs 2.6.27. Signed-off-by: Cliff Wickman Signed-off-by: Ingo Molnar --- arch/x86/kernel/tlb_uv.c | 3 ++- include/asm-x86/irq_vectors.h | 1 + include/asm-x86/uv/uv_bau.h | 5 ----- 3 files changed, 3 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index d0fbb7712ab0..8b8c0d6640fa 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -17,6 +17,7 @@ #include #include #include +#include #include @@ -783,7 +784,7 @@ static int __init uv_bau_init(void) uv_init_blade(blade, node, cur_cpu); cur_cpu += uv_blade_nr_possible_cpus(blade); } - set_intr_gate(UV_BAU_MESSAGE, uv_bau_message_intr1); + alloc_intr_gate(UV_BAU_MESSAGE, uv_bau_message_intr1); uv_enable_timeouts(); return 0; diff --git a/include/asm-x86/irq_vectors.h b/include/asm-x86/irq_vectors.h index b95d167b7fb2..a48c7f2dbdc0 100644 --- a/include/asm-x86/irq_vectors.h +++ b/include/asm-x86/irq_vectors.h @@ -76,6 +76,7 @@ #define CALL_FUNCTION_SINGLE_VECTOR 0xfb #define THERMAL_APIC_VECTOR 0xfa #define THRESHOLD_APIC_VECTOR 0xf9 +#define UV_BAU_MESSAGE 0xf8 #define INVALIDATE_TLB_VECTOR_END 0xf7 #define INVALIDATE_TLB_VECTOR_START 0xf0 /* f0-f7 used for TLB flush */ diff --git a/include/asm-x86/uv/uv_bau.h b/include/asm-x86/uv/uv_bau.h index 91ac0dfb7588..610b6b308e93 100644 --- a/include/asm-x86/uv/uv_bau.h +++ b/include/asm-x86/uv/uv_bau.h @@ -40,11 +40,6 @@ #define UV_ACTIVATION_DESCRIPTOR_SIZE 32 #define UV_DISTRIBUTION_SIZE 256 #define UV_SW_ACK_NPENDING 8 -#define UV_BAU_MESSAGE 200 -/* - * Messaging irq; see irq_64.h and include/asm-x86/hw_irq_64.h - * To be dynamically allocated in the future - */ #define UV_NET_ENDPOINT_INTD 0x38 #define UV_DESC_BASE_PNODE_SHIFT 49 #define UV_PAYLOADQ_PNODE_SHIFT 49 From 80a8c9fffa78f57d7d4351af2f15a56386805ceb Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 19 Aug 2008 03:13:38 +0200 Subject: [PATCH 05/20] x86: fix oprofile + hibernation badness Vegard Nossum reported oprofile + hibernation problems: > Now some warnings: > > ------------[ cut here ]------------ > WARNING: at /uio/arkimedes/s29/vegardno/git-working/linux-2.6/kernel/smp.c:328 s > mp_call_function_mask+0x194/0x1a0() The usual problem: the suspend function when interrupts are already disabled calls smp_call_function which is not allowed with interrupt off. But at this point all the other CPUs should be already down anyways, so it should be enough to just drop that. This patch should fix that problem at least by fixing cpu hotplug& suspend support. [ mingo@elte.hu: fixed 5 coding style errors. ] Signed-off-by: Andi Kleen Tested-by: Vegard Nossum Signed-off-by: Ingo Molnar --- arch/x86/oprofile/nmi_int.c | 39 ++++++++++++++++++++++++++++++++++--- 1 file changed, 36 insertions(+), 3 deletions(-) diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 3f90289410e6..0227694f7dab 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -28,23 +29,48 @@ static DEFINE_PER_CPU(unsigned long, saved_lvtpc); static int nmi_start(void); static void nmi_stop(void); +static void nmi_cpu_start(void *dummy); +static void nmi_cpu_stop(void *dummy); /* 0 == registered but off, 1 == registered and on */ static int nmi_enabled = 0; +#ifdef CONFIG_SMP +static int oprofile_cpu_notifier(struct notifier_block *b, unsigned long action, + void *data) +{ + int cpu = (unsigned long)data; + switch (action) { + case CPU_DOWN_FAILED: + case CPU_ONLINE: + smp_call_function_single(cpu, nmi_cpu_start, NULL, 0); + break; + case CPU_DOWN_PREPARE: + smp_call_function_single(cpu, nmi_cpu_stop, NULL, 1); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block oprofile_cpu_nb = { + .notifier_call = oprofile_cpu_notifier +}; +#endif + #ifdef CONFIG_PM static int nmi_suspend(struct sys_device *dev, pm_message_t state) { + /* Only one CPU left, just stop that one */ if (nmi_enabled == 1) - nmi_stop(); + nmi_cpu_stop(NULL); return 0; } static int nmi_resume(struct sys_device *dev) { if (nmi_enabled == 1) - nmi_start(); + nmi_cpu_start(NULL); return 0; } @@ -463,6 +489,9 @@ int __init op_nmi_init(struct oprofile_operations *ops) } init_sysfs(); +#ifdef CONFIG_SMP + register_cpu_notifier(&oprofile_cpu_nb); +#endif using_nmi = 1; ops->create_files = nmi_create_files; ops->setup = nmi_setup; @@ -476,6 +505,10 @@ int __init op_nmi_init(struct oprofile_operations *ops) void op_nmi_exit(void) { - if (using_nmi) + if (using_nmi) { exit_sysfs(); +#ifdef CONFIG_SMP + unregister_cpu_notifier(&oprofile_cpu_nb); +#endif + } } From 85d577979a8a94a32ca1d828a91c2eb8300bc9f2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 18 Aug 2008 11:58:17 +0200 Subject: [PATCH 06/20] werror: fix pci calgary Fix an integer comparison always false warning in the PCI Calgary 64 driver. A u8 is being compared to something that's 512 by default, resulting in the following warning: arch/x86/kernel/pci-calgary_64.c:1285: warning: comparison is always false due to limited range of data type This was introduced by patch b34e90b8f0f30151349134f87b5dc6ef75a5218c. Signed-off-by: David Howells Signed-off-by: Ingo Molnar --- arch/x86/kernel/pci-calgary_64.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 218d783ed7a8..363a74ec7a76 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -1269,13 +1269,15 @@ static inline int __init determine_tce_table_size(u64 ram) static int __init build_detail_arrays(void) { unsigned long ptr; - int i, scal_detail_size, rio_detail_size; + unsigned numnodes, i; + int scal_detail_size, rio_detail_size; - if (rio_table_hdr->num_scal_dev > MAX_NUMNODES){ + numnodes = rio_table_hdr->num_scal_dev; + if (numnodes > MAX_NUMNODES){ printk(KERN_WARNING "Calgary: MAX_NUMNODES too low! Defined as %d, " "but system has %d nodes.\n", - MAX_NUMNODES, rio_table_hdr->num_scal_dev); + MAX_NUMNODES, numnodes); return -ENODEV; } @@ -1296,8 +1298,7 @@ static int __init build_detail_arrays(void) } ptr = ((unsigned long)rio_table_hdr) + 3; - for (i = 0; i < rio_table_hdr->num_scal_dev; - i++, ptr += scal_detail_size) + for (i = 0; i < numnodes; i++, ptr += scal_detail_size) scal_devs[i] = (struct scal_detail *)ptr; for (i = 0; i < rio_table_hdr->num_rio_dev; From 0c072bb452f0cfd4959bc01ff3627d6385255b20 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Tue, 8 Jul 2008 09:50:22 -0700 Subject: [PATCH 07/20] x86: use WARN() in arch/x86/mm/ioremap.c Use WARN() instead of a printk+WARN_ON() pair; this way the message becomes part of the warning section for better reporting/collection. Signed-off-by: Arjan van de Ven Cc: akpm@linux-foundation.org Signed-off-by: Ingo Molnar --- arch/x86/mm/ioremap.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 6ba6f889c79d..d4b6e6a29ae3 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -553,13 +553,11 @@ static int __init check_early_ioremap_leak(void) { if (!early_ioremap_nested) return 0; - - printk(KERN_WARNING + WARN(1, KERN_WARNING "Debug warning: early ioremap leak of %d areas detected.\n", - early_ioremap_nested); + early_ioremap_nested); printk(KERN_WARNING - "please boot with early_ioremap_debug and report the dmesg.\n"); - WARN_ON(1); + "please boot with early_ioremap_debug and report the dmesg.\n"); return 1; } From bde78a79a6eb015f33aa4660df1b06f5135def20 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Tue, 8 Jul 2008 09:51:56 -0700 Subject: [PATCH 08/20] x86: use WARN() in arch/x86/kernel Use WARN() instead of a printk+WARN_ON() pair; this way the message becomes part of the warning section for better reporting/collection. This also allowed the folding of some if()'s into the WARN() Signed-off-by: Arjan van de Ven Cc: akpm@linux-foundation.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mtrr/main.c | 5 +---- arch/x86/kernel/pci-calgary_64.c | 3 +-- arch/x86/kernel/tsc_sync.c | 6 ++---- 3 files changed, 4 insertions(+), 10 deletions(-) diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 6f23969c8faf..b117d7f8a564 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -1496,11 +1496,8 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) /* kvm/qemu doesn't have mtrr set right, don't trim them all */ if (!highest_pfn) { - if (!kvm_para_available()) { - printk(KERN_WARNING + WARN(!kvm_para_available(), KERN_WARNING "WARNING: strange, CPU MTRRs all blank?\n"); - WARN_ON(1); - } return 0; } diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 363a74ec7a76..dcdac6c826e9 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -343,9 +343,8 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, /* were we called with bad_dma_address? */ badend = bad_dma_address + (EMERGENCY_PAGES * PAGE_SIZE); if (unlikely((dma_addr >= bad_dma_address) && (dma_addr < badend))) { - printk(KERN_ERR "Calgary: driver tried unmapping bad DMA " + WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA " "address 0x%Lx\n", dma_addr); - WARN_ON(1); return; } diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 0577825cf89b..9ffb01c31c40 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -88,11 +88,9 @@ static __cpuinit void check_tsc_warp(void) __raw_spin_unlock(&sync_lock); } } - if (!(now-start)) { - printk("Warning: zero tsc calibration delta: %Ld [max: %Ld]\n", + WARN(!(now-start), + "Warning: zero tsc calibration delta: %Ld [max: %Ld]\n", now-start, end-start); - WARN_ON(1); - } } /* From 7701e8c59b0e7cbcf21c1bc49d8b8c6db43027a4 Mon Sep 17 00:00:00 2001 From: Marcin Slusarz Date: Wed, 20 Aug 2008 21:07:47 +0200 Subject: [PATCH 09/20] x86, mmiotrace: silence section mismatch warning - leave_uniprocessor WARNING: vmlinux.o(.text+0x180af): Section mismatch in reference from the function leave_uniprocessor() to the function .cpuinit.text:cpu_up() The function leave_uniprocessor() references the function __cpuinit cpu_up(). This is often because leave_uniprocessor lacks a __cpuinit annotation or the annotation of cpu_up is wrong. leave_uniprocessor calls cpu_up only when CONFIG_HOTPLUG_CPU is set, so it can be safely annotated as __ref Signed-off-by: Marcin Slusarz Cc: Pekka Paalanen Signed-off-by: Ingo Molnar Cc: Ingo Molnar Cc: Pekka Paalanen --- arch/x86/mm/mmio-mod.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index e7397e108beb..635b50e85581 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -430,7 +430,9 @@ static void enter_uniprocessor(void) "may miss events.\n"); } -static void leave_uniprocessor(void) +/* __ref because leave_uniprocessor calls cpu_up which is __cpuinit, + but this whole function is ifdefed CONFIG_HOTPLUG_CPU */ +static void __ref leave_uniprocessor(void) { int cpu; int err; From 7946612de2087e163308e26034286fc2dc9dacf1 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Wed, 20 Aug 2008 11:31:07 -0700 Subject: [PATCH 10/20] x86: export pv_lock_ops non-GPL None of the spinlock API is exported GPL, so there's no reason for pv_lock_ops to be. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar Cc: drago01 --- arch/x86/kernel/paravirt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 94da4d52d798..300da17e61cb 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -471,7 +471,7 @@ struct pv_lock_ops pv_lock_ops = { .spin_unlock = __ticket_spin_unlock, #endif }; -EXPORT_SYMBOL_GPL(pv_lock_ops); +EXPORT_SYMBOL(pv_lock_ops); EXPORT_SYMBOL_GPL(pv_time_ops); EXPORT_SYMBOL (pv_cpu_ops); From b2a6a58ca6a3ddf4e278a53199c5b8fd39adbc0e Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Wed, 20 Aug 2008 18:18:26 +0200 Subject: [PATCH 11/20] x86: fix BUG: unable to handle kernel paging request (numaq_tsc_disable) This section mismatch: >> Seems to be a section mismatch; init_intel() is __cpuinit while >> numaq_tsc_disable() is __init. Seems to be introduced in: >> >> commit 64898a8bad8c94ad7a4bd5cc86b66edfbb081f4a >> Author: Yinghai Lu >> Date: Sat Jul 19 18:01:16 2008 -0700 >> >> x86: extend and use x86_quirks to clean up NUMAQ code > > Oops, I am wrong about numaq_tsc_disable() being __init. Still, I > believe that Yinghai might be able to say what's really wrong :-) Would lead to this crash: BUG: unable to handle kernel paging request at c08a45f0 IP: [] numaq_tsc_disable+0x0/0x40 Fixed by the patch below. Signed-off-by: Vegard Nossum Signed-off-by: Ingo Molnar --- arch/x86/kernel/numaq_32.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/numaq_32.c b/arch/x86/kernel/numaq_32.c index b8c45610b20a..eecc8c18f010 100644 --- a/arch/x86/kernel/numaq_32.c +++ b/arch/x86/kernel/numaq_32.c @@ -73,7 +73,7 @@ static void __init smp_dump_qct(void) } -void __init numaq_tsc_disable(void) +void __cpuinit numaq_tsc_disable(void) { if (!found_numaq) return; From c15238df3b65e34fadb1021b0fb0d5aebc7c42c6 Mon Sep 17 00:00:00 2001 From: "venkatesh.pallipadi@intel.com" Date: Wed, 20 Aug 2008 16:45:51 -0700 Subject: [PATCH 12/20] x86: PAT proper tracking of set_memory_uc and friends Big thinko in pat memtype tracking code. reserve_memtype should be called with physical address and not virtual address. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha Signed-off-by: Ingo Molnar --- arch/x86/mm/pageattr.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index f5f5154ea11e..43e2f8483e4f 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -849,7 +849,7 @@ int set_memory_uc(unsigned long addr, int numpages) /* * for now UC MINUS. see comments in ioremap_nocache() */ - if (reserve_memtype(addr, addr + numpages * PAGE_SIZE, + if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, _PAGE_CACHE_UC_MINUS, NULL)) return -EINVAL; @@ -868,7 +868,7 @@ int set_memory_wc(unsigned long addr, int numpages) if (!pat_enabled) return set_memory_uc(addr, numpages); - if (reserve_memtype(addr, addr + numpages * PAGE_SIZE, + if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, _PAGE_CACHE_WC, NULL)) return -EINVAL; @@ -884,7 +884,7 @@ int _set_memory_wb(unsigned long addr, int numpages) int set_memory_wb(unsigned long addr, int numpages) { - free_memtype(addr, addr + numpages * PAGE_SIZE); + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); return _set_memory_wb(addr, numpages); } From 28df82ebab79c6a2b4295dd94fd8de88196a49df Mon Sep 17 00:00:00 2001 From: "venkatesh.pallipadi@intel.com" Date: Wed, 20 Aug 2008 16:45:52 -0700 Subject: [PATCH 13/20] devmem, x86: PAT Change /dev/mem mmap with O_SYNC to use UC_MINUS All kernel mappings like ioremap(), etc uses UC_MINUS as the type. /dev/mem mappings with /dev/mem being opened with O_SYNC however was using UC, resulting in a conflict with /dev/mem mmap failing. This seems to be affecting some apps (one being flashrom) which are using O_SYNC and which were working before. Switch /dev/mem with O_SYNC also to UC_MINUS. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Ingo Molnar --- arch/x86/mm/pat.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index bb6e8a267bfe..2a50e0fa64a5 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -390,14 +390,6 @@ int free_memtype(u64 start, u64 end) } -/* - * /dev/mem mmap interface. The memtype used for mapping varies: - * - Use UC for mappings with O_SYNC flag - * - Without O_SYNC flag, if there is any conflict in reserve_memtype, - * inherit the memtype from existing mapping. - * - Else use UC_MINUS memtype (for backward compatibility with existing - * X drivers. - */ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { @@ -435,14 +427,14 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot) { u64 offset = ((u64) pfn) << PAGE_SHIFT; - unsigned long flags = _PAGE_CACHE_UC_MINUS; + unsigned long flags = -1; int retval; if (!range_is_allowed(pfn, size)) return 0; if (file->f_flags & O_SYNC) { - flags = _PAGE_CACHE_UC; + flags = _PAGE_CACHE_UC_MINUS; } #ifdef CONFIG_X86_32 @@ -465,13 +457,14 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, #endif /* - * With O_SYNC, we can only take UC mapping. Fail if we cannot. + * With O_SYNC, we can only take UC_MINUS mapping. Fail if we cannot. + * * Without O_SYNC, we want to get * - WB for WB-able memory and no other conflicting mappings * - UC_MINUS for non-WB-able memory with no other conflicting mappings * - Inherit from confliting mappings otherwise */ - if (flags != _PAGE_CACHE_UC_MINUS) { + if (flags != -1) { retval = reserve_memtype(offset, offset + size, flags, NULL); } else { retval = reserve_memtype(offset, offset + size, -1, &flags); From 8323444b5dba3fe55e56a95d20d8f55c1d6745af Mon Sep 17 00:00:00 2001 From: "venkatesh.pallipadi@intel.com" Date: Wed, 20 Aug 2008 16:45:53 -0700 Subject: [PATCH 14/20] x86: PAT Update validate_pat_support for intel CPUs Pentium III and Core Solo/Duo CPUs have an erratum " Page with PAT set to WC while associated MTRR is UC may consolidate to UC " which can result in WC setting in PAT to be ineffective. We will disable PAT on such CPUs, so that we can continue to use MTRR WC setting. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/addon_cpuid_features.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c index 84a8220a6072..a6ef672adbba 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/addon_cpuid_features.c @@ -56,9 +56,22 @@ void __cpuinit validate_pat_support(struct cpuinfo_x86 *c) switch (c->x86_vendor) { case X86_VENDOR_INTEL: - if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15)) + /* + * There is a known erratum on Pentium III and Core Solo + * and Core Duo CPUs. + * " Page with PAT set to WC while associated MTRR is UC + * may consolidate to UC " + * Because of this erratum, it is better to stick with + * setting WC in MTRR rather than using PAT on these CPUs. + * + * Enable PAT WC only on P4, Core 2 or later CPUs. + */ + if (c->x86 > 0x6 || (c->x86 == 6 && c->x86_model >= 15)) return; - break; + + pat_disable("PAT WC disabled due to known CPU erratum."); + return; + case X86_VENDOR_AMD: case X86_VENDOR_CENTAUR: case X86_VENDOR_TRANSMETA: From 38cc1c3df77c1bb739a4766788eb9fa49f16ffdf Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 21 Aug 2008 20:24:24 -0700 Subject: [PATCH 15/20] x86: work around MTRR mask setting Joshua Hoblitt reported that only 3 GB of his 16 GB of RAM is usable. Booting with mtrr_show showed us the BIOS-initialized MTRR settings - which are all wrong. So the root cause is that the BIOS has not set the mask correctly: > [ 0.429971] MSR00000200: 00000000d0000000 > [ 0.433305] MSR00000201: 0000000ff0000800 > should be ==> [ 0.433305] MSR00000201: 0000003ff0000800 > > [ 0.436638] MSR00000202: 00000000e0000000 > [ 0.439971] MSR00000203: 0000000fe0000800 > should be ==> [ 0.439971] MSR00000203: 0000003fe0000800 > > [ 0.443304] MSR00000204: 0000000000000006 > [ 0.446637] MSR00000205: 0000000c00000800 > should be ==> [ 0.446637] MSR00000205: 0000003c00000800 > > [ 0.449970] MSR00000206: 0000000400000006 > [ 0.453303] MSR00000207: 0000000fe0000800 > should be ==> [ 0.453303] MSR00000207: 0000003fe0000800 > > [ 0.456636] MSR00000208: 0000000420000006 > [ 0.459970] MSR00000209: 0000000ff0000800 > should be ==> [ 0.459970] MSR00000209: 0000003ff0000800 So detect this borkage and add the prefix 111. Signed-off-by: Yinghai Lu Cc: Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mtrr/generic.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 509bd3d9eacd..43102e03e2d1 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -379,6 +379,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, unsigned long *size, mtrr_type *type) { unsigned int mask_lo, mask_hi, base_lo, base_hi; + unsigned int tmp, hi; rdmsr(MTRRphysMask_MSR(reg), mask_lo, mask_hi); if ((mask_lo & 0x800) == 0) { @@ -392,8 +393,18 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, rdmsr(MTRRphysBase_MSR(reg), base_lo, base_hi); /* Work out the shifted address mask. */ - mask_lo = size_or_mask | mask_hi << (32 - PAGE_SHIFT) - | mask_lo >> PAGE_SHIFT; + tmp = mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT; + mask_lo = size_or_mask | tmp; + /* Expand tmp with high bits to all 1s*/ + hi = fls(tmp); + if (hi > 0) { + tmp |= ~((1<<(hi - 1)) - 1); + + if (tmp != mask_lo) { + WARN_ON("mtrr: your BIOS has set up an incorrect mask, fixing it up.\n"); + mask_lo = tmp; + } + } /* This works correctly if size is a power of two, i.e. a contiguous range. */ From 8ae3a5a8dff2c92bd1087bb97c4a3bb61174303e Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Thu, 21 Aug 2008 14:27:22 +0100 Subject: [PATCH 16/20] x86: fix 1:1 mapping init on 64-bit (memory hotplug case) While I don't have a hotplug capable system at hand, I think two issues need fixing: - pud_phys (in kernel_physical_ampping_init()) would remain uninitialized in the after_bootmem case - the locking done just around phys_pmd_{init,update}() would leave out pgd updates, and it was needlessly covering code portions that do allocations (perhaps using a more friendly gfp value in alloc_low_page() would then be possible) Signed-off-by: Jan Beulich Signed-off-by: Ingo Molnar --- arch/x86/mm/init_64.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a87ea0e4b3dc..8f487705c3e6 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -336,9 +336,12 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, } if (pmd_val(*pmd)) { - if (!pmd_large(*pmd)) + if (!pmd_large(*pmd)) { + spin_lock(&init_mm.page_table_lock); last_map_addr = phys_pte_update(pmd, address, - end); + end); + spin_unlock(&init_mm.page_table_lock); + } /* Count entries we're using from level2_ident_pgt */ if (start == 0) pages++; @@ -347,8 +350,10 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, if (page_size_mask & (1<> PAGE_SHIFT, PAGE_KERNEL_LARGE)); + spin_unlock(&init_mm.page_table_lock); last_map_addr = (address & PMD_MASK) + PMD_SIZE; continue; } @@ -357,7 +362,9 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, last_map_addr = phys_pte_init(pte, address, end); unmap_low_page(pte); + spin_lock(&init_mm.page_table_lock); pmd_populate_kernel(&init_mm, pmd, __va(pte_phys)); + spin_unlock(&init_mm.page_table_lock); } update_page_count(PG_LEVEL_2M, pages); return last_map_addr; @@ -370,9 +377,7 @@ phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end, pmd_t *pmd = pmd_offset(pud, 0); unsigned long last_map_addr; - spin_lock(&init_mm.page_table_lock); last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask); - spin_unlock(&init_mm.page_table_lock); __flush_tlb_all(); return last_map_addr; } @@ -408,20 +413,21 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end, if (page_size_mask & (1<> PAGE_SHIFT, PAGE_KERNEL_LARGE)); + spin_unlock(&init_mm.page_table_lock); last_map_addr = (addr & PUD_MASK) + PUD_SIZE; continue; } pmd = alloc_low_page(&pmd_phys); - - spin_lock(&init_mm.page_table_lock); last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask); unmap_low_page(pmd); + + spin_lock(&init_mm.page_table_lock); pud_populate(&init_mm, pud, __va(pmd_phys)); spin_unlock(&init_mm.page_table_lock); - } __flush_tlb_all(); update_page_count(PG_LEVEL_1G, pages); @@ -513,16 +519,14 @@ static unsigned long __init kernel_physical_mapping_init(unsigned long start, continue; } - if (after_bootmem) - pud = pud_offset(pgd, start & PGDIR_MASK); - else - pud = alloc_low_page(&pud_phys); - + pud = alloc_low_page(&pud_phys); last_map_addr = phys_pud_init(pud, __pa(start), __pa(next), page_size_mask); unmap_low_page(pud); - pgd_populate(&init_mm, pgd_offset_k(start), - __va(pud_phys)); + + spin_lock(&init_mm.page_table_lock); + pgd_populate(&init_mm, pgd, __va(pud_phys)); + spin_unlock(&init_mm.page_table_lock); } return last_map_addr; From 9482ac6e34dd1890a9a956d460a135bf992cb54a Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Thu, 21 Aug 2008 14:28:42 +0100 Subject: [PATCH 17/20] x86: fix two modpost warnings in mm/init_64.c early_io{re,un}map() are __init and hence can't be called from __meminit functions. Signed-off-by: Jan Beulich Signed-off-by: Ingo Molnar --- arch/x86/mm/init_64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 8f487705c3e6..d3746efb060d 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -241,7 +241,7 @@ static unsigned long __initdata table_start; static unsigned long __meminitdata table_end; static unsigned long __meminitdata table_top; -static __meminit void *alloc_low_page(unsigned long *phys) +static __ref void *alloc_low_page(unsigned long *phys) { unsigned long pfn = table_end++; void *adr; @@ -262,7 +262,7 @@ static __meminit void *alloc_low_page(unsigned long *phys) return adr; } -static __meminit void unmap_low_page(void *adr) +static __ref void unmap_low_page(void *adr) { if (after_bootmem) return; From 3a6ddd5f18405ca92e004416af8ed44b9c9783d7 Mon Sep 17 00:00:00 2001 From: Alok Kataria Date: Thu, 21 Aug 2008 11:32:26 -0700 Subject: [PATCH 18/20] x86: fix VMI for early params while fixing a different bug i moved the call to vmi_init before early params could be parsed. This broke the vmi specific commandline parameters. Fix that, by moving vmi initialization after kernel has got a chance to parse early parameters. Signed-off-by: Alok N Kataria Signed-off-by: Ingo Molnar --- arch/x86/kernel/setup.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index a4656adab53b..362d4e7f2d38 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -604,14 +604,6 @@ void __init setup_arch(char **cmdline_p) early_cpu_init(); early_ioremap_init(); -#if defined(CONFIG_VMI) && defined(CONFIG_X86_32) - /* - * Must be before kernel pagetables are setup - * or fixmap area is touched. - */ - vmi_init(); -#endif - ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev); screen_info = boot_params.screen_info; edid_info = boot_params.edid_info; @@ -678,6 +670,14 @@ void __init setup_arch(char **cmdline_p) parse_early_param(); +#if defined(CONFIG_VMI) && defined(CONFIG_X86_32) + /* + * Must be before kernel pagetables are setup + * or fixmap area is touched. + */ + vmi_init(); +#endif + /* after early param, so could get panic from serial */ reserve_early_setup_data(); From c4bd1fdab0deec0f69aeabab22075cb22ac8ad44 Mon Sep 17 00:00:00 2001 From: Marcin Slusarz Date: Thu, 21 Aug 2008 20:49:05 +0200 Subject: [PATCH 19/20] x86: fix section mismatch warning - uv_cpu_init WARNING: vmlinux.o(.cpuinit.text+0x3cc4): Section mismatch in reference from the function uv_cpu_init() to the function .init.text:uv_system_init() The function __cpuinit uv_cpu_init() references a function __init uv_system_init(). If uv_system_init is only used by uv_cpu_init then annotate uv_system_init with a matching annotation. uv_system_init was ment to be called only once, so do it from codepath (native_smp_prepare_cpus) which is called once, right before activation of other cpus (smp_init). Note: old code relied on uv_node_to_blade being initialized to 0, but it'a not initialized from anywhere. Signed-off-by: Marcin Slusarz Acked-by: Jack Steiner Signed-off-by: Ingo Molnar --- arch/x86/kernel/genx2apic_uv_x.c | 8 +++++--- arch/x86/kernel/smpboot.c | 3 +++ include/asm-x86/genapic_32.h | 1 + include/asm-x86/genapic_64.h | 1 + 4 files changed, 10 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c index 2d7e307c7779..bfa837cb16be 100644 --- a/arch/x86/kernel/genx2apic_uv_x.c +++ b/arch/x86/kernel/genx2apic_uv_x.c @@ -293,7 +293,9 @@ static __init void uv_rtc_init(void) sn_rtc_cycles_per_second = ticks_per_sec; } -static __init void uv_system_init(void) +static bool uv_system_inited; + +void __init uv_system_init(void) { union uvh_si_addr_map_config_u m_n_config; union uvh_node_id_u node_id; @@ -383,6 +385,7 @@ static __init void uv_system_init(void) map_mmr_high(max_pnode); map_config_high(max_pnode); map_mmioh_high(max_pnode); + uv_system_inited = true; } /* @@ -391,8 +394,7 @@ static __init void uv_system_init(void) */ void __cpuinit uv_cpu_init(void) { - if (!uv_node_to_blade) - uv_system_init(); + BUG_ON(!uv_system_inited); uv_blade_info[uv_numa_blade_id()].nr_online_cpus++; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index e139e617f422..7985c5b3f916 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1221,6 +1221,9 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) printk(KERN_INFO "CPU%d: ", 0); print_cpu_info(&cpu_data(0)); setup_boot_clock(); + + if (is_uv_system()) + uv_system_init(); out: preempt_enable(); } diff --git a/include/asm-x86/genapic_32.h b/include/asm-x86/genapic_32.h index b02ea6e17de8..754d635f90ff 100644 --- a/include/asm-x86/genapic_32.h +++ b/include/asm-x86/genapic_32.h @@ -118,6 +118,7 @@ enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC}; #define get_uv_system_type() UV_NONE #define is_uv_system() 0 #define uv_wakeup_secondary(a, b) 1 +#define uv_system_init() do {} while (0) #endif diff --git a/include/asm-x86/genapic_64.h b/include/asm-x86/genapic_64.h index 0f8504627c41..a47d63129135 100644 --- a/include/asm-x86/genapic_64.h +++ b/include/asm-x86/genapic_64.h @@ -42,6 +42,7 @@ extern int is_uv_system(void); extern struct genapic apic_x2apic_uv_x; DECLARE_PER_CPU(int, x2apic_extra_bits); extern void uv_cpu_init(void); +extern void uv_system_init(void); extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip); extern void setup_apic_routing(void); From 9754a5b840a209bc1f192d59f63e81b698a55ac8 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 22 Aug 2008 08:22:23 +0200 Subject: [PATCH 20/20] x86: work around MTRR mask setting, v2 improve the debug printout: - make it actually display something - print it only once would be nice to have a WARN_ONCE() facility, to feed such things to kerneloops.org. Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mtrr/generic.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 43102e03e2d1..cb7d3b6a80eb 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -401,7 +401,12 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, tmp |= ~((1<<(hi - 1)) - 1); if (tmp != mask_lo) { - WARN_ON("mtrr: your BIOS has set up an incorrect mask, fixing it up.\n"); + static int once = 1; + + if (once) { + printk(KERN_INFO "mtrr: your BIOS has set up an incorrect mask, fixing it up.\n"); + once = 0; + } mask_lo = tmp; } }