From b8989db9d82465bf38a48a4d3ef32e7d8afc4d08 Mon Sep 17 00:00:00 2001 From: Alan Date: Mon, 20 Jan 2014 18:01:56 +0000 Subject: x86, doc, kconfig: Fix dud URL for Microcode data The actual data lives in the Intel download center, and that ought to also be a reliable way to continue to find it. Unfortunately the actual URL needed for doing it directly is about a foot long so give instructions. Signed-off-by: Alan Cox Link: http://lkml.kernel.org/r/20140120180056.7173.62222.stgit@alan.etchedpixels.co.uk Signed-off-by: H. Peter Anvin --- arch/x86/Kconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0952ecd60eca..64199bc08d66 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1064,9 +1064,9 @@ config MICROCODE_INTEL This options enables microcode patch loading support for Intel processors. - For latest news and information on obtaining all the required - Intel ingredients for this driver, check: - . + For the current Intel microcode data package go to + and search for + 'Linux Processor Microcode Data File'. config MICROCODE_AMD bool "AMD microcode loading support" -- cgit v1.2.3 From fb53a1ab88d14848dc292842e35c3bda3a665997 Mon Sep 17 00:00:00 2001 From: Aravind Gopalakrishnan Date: Thu, 23 Jan 2014 16:13:32 -0600 Subject: x86/quirks: Add workaround for AMD F16h Erratum792 The workaround for this Erratum is included in AGESA. But BIOSes spun only after Jan2014 will have the fix (atleast server versions of the chip). The erratum affects both embedded and server platforms and since we cannot say with certainity that ALL BIOSes on systems out in the field will have the fix, we should probably insulate ourselves in case BIOS does not do the right thing or someone is using old BIOSes. Refer to Revision Guide for AMD F16h models 00h-0fh, document 51810 Rev. 3.04, November2013 for details on the Erratum. Tested the patch on Fam16h server platform and it works fine. Signed-off-by: Aravind Gopalakrishnan Cc: Cc: Cc: Cc: Cc: Link: http://lkml.kernel.org/r/1390515212-1824-1-git-send-email-Aravind.Gopalakrishnan@amd.com [ Minor edits. ] Signed-off-by: Ingo Molnar --- arch/x86/kernel/quirks.c | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 04ee1e2e4c02..7c6acd4b8995 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -571,3 +571,40 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F5, quirk_amd_nb_node); #endif + +#ifdef CONFIG_PCI +/* + * Processor does not ensure DRAM scrub read/write sequence + * is atomic wrt accesses to CC6 save state area. Therefore + * if a concurrent scrub read/write access is to same address + * the entry may appear as if it is not written. This quirk + * applies to Fam16h models 00h-0Fh + * + * See "Revision Guide" for AMD F16h models 00h-0fh, + * document 51810 rev. 3.04, Nov 2013 + */ +static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev) +{ + u32 val; + + /* + * Suggested workaround: + * set D18F3x58[4:0] = 00h and set D18F3x5C[0] = 0b + */ + pci_read_config_dword(dev, 0x58, &val); + if (val & 0x1F) { + val &= ~(0x1F); + pci_write_config_dword(dev, 0x58, val); + } + + pci_read_config_dword(dev, 0x5C, &val); + if (val & BIT(0)) { + val &= ~BIT(0); + pci_write_config_dword(dev, 0x5c, val); + } +} + +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3, + amd_disable_seq_and_redirect_scrub); + +#endif -- cgit v1.2.3 From 2993ae3305ad10b41e0d0bc2662f7754ee8e30fa Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 21 Jan 2014 10:22:09 +0300 Subject: x86/AMD/NB: Fix amd_set_subcaches() parameter type This is under CAP_SYS_ADMIN, but Smatch complains that mask comes from the user and the test for "mask > 0xf" can underflow. The fix is simple: amd_set_subcaches() should hand down not an 'int' but an 'unsigned long' like it was originally indended to do. Signed-off-by: Dan Carpenter Acked-by: Borislav Petkov Cc: Borislav Petkov Cc: Daniel J Blueman Link: http://lkml.kernel.org/r/20140121072209.GA22095@elgon.mountain Signed-off-by: Ingo Molnar --- arch/x86/include/asm/amd_nb.h | 2 +- arch/x86/kernel/amd_nb.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index a54ee1d054d9..aaac3b2fb746 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -19,7 +19,7 @@ extern int amd_cache_northbridges(void); extern void amd_flush_garts(void); extern int amd_numa_init(void); extern int amd_get_subcaches(int); -extern int amd_set_subcaches(int, int); +extern int amd_set_subcaches(int, unsigned long); struct amd_l3_cache { unsigned indices; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 59554dca96ec..dec8de4e1663 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -179,7 +179,7 @@ int amd_get_subcaches(int cpu) return (mask >> (4 * cuid)) & 0xf; } -int amd_set_subcaches(int cpu, int mask) +int amd_set_subcaches(int cpu, unsigned long mask) { static unsigned int reset, ban; struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu)); -- cgit v1.2.3 From ec65993443736a5091b68e80ff1734548944a4b8 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 21 Jan 2014 14:33:16 -0800 Subject: mm, x86: Account for TLB flushes only when debugging Bisection between 3.11 and 3.12 fingered commit 9824cf97 ("mm: vmstats: tlb flush counters") to cause overhead problems. The counters are undeniably useful but how often do we really need to debug TLB flush related issues? It does not justify taking the penalty everywhere so make it a debugging option. Signed-off-by: Mel Gorman Tested-by: Davidlohr Bueso Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Cc: Hugh Dickins Cc: Alex Shi Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-XzxjntugxuwpxXhcrxqqh53b@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/tlbflush.h | 6 +++--- arch/x86/kernel/cpu/mtrr/generic.c | 4 ++-- arch/x86/mm/tlb.c | 14 +++++++------- include/linux/vm_event_item.h | 4 +++- include/linux/vmstat.h | 8 ++++++++ mm/vmstat.c | 4 +++- 6 files changed, 26 insertions(+), 14 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index e6d90babc245..04905bfc508b 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -62,7 +62,7 @@ static inline void __flush_tlb_all(void) static inline void __flush_tlb_one(unsigned long addr) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ONE); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); __flush_tlb_single(addr); } @@ -93,13 +93,13 @@ static inline void __flush_tlb_one(unsigned long addr) */ static inline void __flush_tlb_up(void) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); } static inline void flush_tlb_all(void) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb_all(); } diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index ce2d0a2c3e4f..0e25a1bc5ab5 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -683,7 +683,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) } /* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */ - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); /* Save MTRR state */ @@ -697,7 +697,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) static void post_set(void) __releases(set_atomicity_lock) { /* Flush TLBs (no need to flush caches - they are disabled) */ - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); /* Intel (P6) standard MTRRs */ diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index ae699b3bbac8..05446c1cccfe 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -103,7 +103,7 @@ static void flush_tlb_func(void *info) if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) return; - count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { if (f->flush_end == TLB_FLUSH_ALL) local_flush_tlb(); @@ -131,7 +131,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask, info.flush_start = start; info.flush_end = end; - count_vm_event(NR_TLB_REMOTE_FLUSH); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); if (is_uv_system()) { unsigned int cpu; @@ -151,7 +151,7 @@ void flush_tlb_current_task(void) preempt_disable(); - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); @@ -215,7 +215,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, /* tlb_flushall_shift is on balance point, details in commit log */ if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); } else { if (has_large_page(mm, start, end)) { @@ -224,7 +224,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, } /* flush range by one by one 'invlpg' */ for (addr = start; addr < end; addr += PAGE_SIZE) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ONE); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); __flush_tlb_single(addr); } @@ -262,7 +262,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) static void do_flush_tlb_all(void *info) { - count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); __flush_tlb_all(); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY) leave_mm(smp_processor_id()); @@ -270,7 +270,7 @@ static void do_flush_tlb_all(void *info) void flush_tlb_all(void) { - count_vm_event(NR_TLB_REMOTE_FLUSH); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); on_each_cpu(do_flush_tlb_all, NULL, 1); } diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index c557c6d096de..3a712e2e7d76 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -71,12 +71,14 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, #endif +#ifdef CONFIG_DEBUG_TLBFLUSH #ifdef CONFIG_SMP NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */ NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */ -#endif +#endif /* CONFIG_SMP */ NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, +#endif /* CONFIG_DEBUG_TLBFLUSH */ NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index e4b948080d20..80ebba9c2e87 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -83,6 +83,14 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ +#ifdef CONFIG_DEBUG_TLBFLUSH +#define count_vm_tlb_event(x) count_vm_event(x) +#define count_vm_tlb_events(x, y) count_vm_events(x, y) +#else +#define count_vm_tlb_event(x) do {} while (0) +#define count_vm_tlb_events(x, y) do { (void)(y); } while (0) +#endif + #define __count_zone_vm_events(item, zone, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + \ zone_idx(zone), delta) diff --git a/mm/vmstat.c b/mm/vmstat.c index 72496140ac08..def5dd2fbe61 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -851,12 +851,14 @@ const char * const vmstat_text[] = { "thp_zero_page_alloc", "thp_zero_page_alloc_failed", #endif +#ifdef CONFIG_DEBUG_TLBFLUSH #ifdef CONFIG_SMP "nr_tlb_remote_flush", "nr_tlb_remote_flush_received", -#endif +#endif /* CONFIG_SMP */ "nr_tlb_local_flush_all", "nr_tlb_local_flush_one", +#endif /* CONFIG_DEBUG_TLBFLUSH */ #endif /* CONFIG_VM_EVENTS_COUNTERS */ }; -- cgit v1.2.3 From 15aa368255f249df0b2af630c9487bb5471bd7da Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 21 Jan 2014 14:33:18 -0800 Subject: x86/mm: Clean up inconsistencies when flushing TLB ranges NR_TLB_LOCAL_FLUSH_ALL is not always accounted for correctly and the comparison with total_vm is done before taking tlb_flushall_shift into account. Clean it up. Signed-off-by: Mel Gorman Tested-by: Davidlohr Bueso Reviewed-by: Alex Shi Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Hugh Dickins Link: http://lkml.kernel.org/n/tip-Iz5gcahrgskIldvukulzi0hh@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/mm/tlb.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 05446c1cccfe..5176526ddd59 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -189,6 +189,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, { unsigned long addr; unsigned act_entries, tlb_entries = 0; + unsigned long nr_base_pages; preempt_disable(); if (current->active_mm != mm) @@ -210,18 +211,17 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, tlb_entries = tlb_lli_4k[ENTRIES]; else tlb_entries = tlb_lld_4k[ENTRIES]; + /* Assume all of TLB entries was occupied by this task */ - act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm; + act_entries = tlb_entries >> tlb_flushall_shift; + act_entries = mm->total_vm > act_entries ? act_entries : mm->total_vm; + nr_base_pages = (end - start) >> PAGE_SHIFT; /* tlb_flushall_shift is on balance point, details in commit log */ - if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) { + if (nr_base_pages > act_entries || has_large_page(mm, start, end)) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); } else { - if (has_large_page(mm, start, end)) { - local_flush_tlb(); - goto flush_all; - } /* flush range by one by one 'invlpg' */ for (addr = start; addr < end; addr += PAGE_SIZE) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); -- cgit v1.2.3 From 71b54f8263860a37dd9f50f81880a9d681fd9c10 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 21 Jan 2014 14:33:19 -0800 Subject: x86/mm: Eliminate redundant page table walk during TLB range flushing When choosing between doing an address space or ranged flush, the x86 implementation of flush_tlb_mm_range takes into account whether there are any large pages in the range. A per-page flush typically requires fewer entries than would covered by a single large page and the check is redundant. There is one potential exception. THP migration flushes single THP entries and it conceivably would benefit from flushing a single entry instead of the mm. However, this flush is after a THP allocation, copy and page table update potentially with any other threads serialised behind it. In comparison to that, the flush is noise. It makes more sense to optimise balancing to require fewer flushes than to optimise the flush itself. This patch deletes the redundant huge page check. Signed-off-by: Mel Gorman Tested-by: Davidlohr Bueso Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Cc: Alex Shi Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-sgei1drpOcburujPsfh6ovmo@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/mm/tlb.c | 28 +--------------------------- 1 file changed, 1 insertion(+), 27 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 5176526ddd59..dd8dda167a24 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -158,32 +158,6 @@ void flush_tlb_current_task(void) preempt_enable(); } -/* - * It can find out the THP large page, or - * HUGETLB page in tlb_flush when THP disabled - */ -static inline unsigned long has_large_page(struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - unsigned long addr = ALIGN(start, HPAGE_SIZE); - for (; addr < end; addr += HPAGE_SIZE) { - pgd = pgd_offset(mm, addr); - if (likely(!pgd_none(*pgd))) { - pud = pud_offset(pgd, addr); - if (likely(!pud_none(*pud))) { - pmd = pmd_offset(pud, addr); - if (likely(!pmd_none(*pmd))) - if (pmd_large(*pmd)) - return addr; - } - } - } - return 0; -} - void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag) { @@ -218,7 +192,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, nr_base_pages = (end - start) >> PAGE_SHIFT; /* tlb_flushall_shift is on balance point, details in commit log */ - if (nr_base_pages > act_entries || has_large_page(mm, start, end)) { + if (nr_base_pages > act_entries) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); } else { -- cgit v1.2.3 From f98b7a772ab51b52ca4d2a14362fc0e0c8a2e0f3 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 21 Jan 2014 14:33:21 -0800 Subject: x86: mm: change tlb_flushall_shift for IvyBridge There was a large performance regression that was bisected to commit 611ae8e3 ("x86/tlb: enable tlb flush range support for x86"). This patch simply changes the default balance point between a local and global flush for IvyBridge. In the interest of allowing the tests to be reproduced, this patch was tested using mmtests 0.15 with the following configurations configs/config-global-dhp__tlbflush-performance configs/config-global-dhp__scheduler-performance configs/config-global-dhp__network-performance Results are from two machines Ivybridge 4 threads: Intel(R) Core(TM) i3-3240 CPU @ 3.40GHz Ivybridge 8 threads: Intel(R) Core(TM) i7-3770 CPU @ 3.40GHz Page fault microbenchmark showed nothing interesting. Ebizzy was configured to run multiple iterations and threads. Thread counts ranged from 1 to NR_CPUS*2. For each thread count, it ran 100 iterations and each iteration lasted 10 seconds. Ivybridge 4 threads 3.13.0-rc7 3.13.0-rc7 vanilla altshift-v3 Mean 1 6395.44 ( 0.00%) 6789.09 ( 6.16%) Mean 2 7012.85 ( 0.00%) 8052.16 ( 14.82%) Mean 3 6403.04 ( 0.00%) 6973.74 ( 8.91%) Mean 4 6135.32 ( 0.00%) 6582.33 ( 7.29%) Mean 5 6095.69 ( 0.00%) 6526.68 ( 7.07%) Mean 6 6114.33 ( 0.00%) 6416.64 ( 4.94%) Mean 7 6085.10 ( 0.00%) 6448.51 ( 5.97%) Mean 8 6120.62 ( 0.00%) 6462.97 ( 5.59%) Ivybridge 8 threads 3.13.0-rc7 3.13.0-rc7 vanilla altshift-v3 Mean 1 7336.65 ( 0.00%) 7787.02 ( 6.14%) Mean 2 8218.41 ( 0.00%) 9484.13 ( 15.40%) Mean 3 7973.62 ( 0.00%) 8922.01 ( 11.89%) Mean 4 7798.33 ( 0.00%) 8567.03 ( 9.86%) Mean 5 7158.72 ( 0.00%) 8214.23 ( 14.74%) Mean 6 6852.27 ( 0.00%) 7952.45 ( 16.06%) Mean 7 6774.65 ( 0.00%) 7536.35 ( 11.24%) Mean 8 6510.50 ( 0.00%) 6894.05 ( 5.89%) Mean 12 6182.90 ( 0.00%) 6661.29 ( 7.74%) Mean 16 6100.09 ( 0.00%) 6608.69 ( 8.34%) Ebizzy hits the worst case scenario for TLB range flushing every time and it shows for these Ivybridge CPUs at least that the default choice is a poor on. The patch addresses the problem. Next was a tlbflush microbenchmark written by Alex Shi at http://marc.info/?l=linux-kernel&m=133727348217113 . It measures access costs while the TLB is being flushed. The expectation is that if there are always full TLB flushes that the benchmark would suffer and it benefits from range flushing There are 320 iterations of the test per thread count. The number of entries is randomly selected with a min of 1 and max of 512. To ensure a reasonably even spread of entries, the full range is broken up into 8 sections and a random number selected within that section. iteration 1, random number between 0-64 iteration 2, random number between 64-128 etc This is still a very weak methodology. When you do not know what are typical ranges, random is a reasonable choice but it can be easily argued that the opimisation was for smaller ranges and an even spread is not representative of any workload that matters. To improve this, we'd need to know the probability distribution of TLB flush range sizes for a set of workloads that are considered "common", build a synthetic trace and feed that into this benchmark. Even that is not perfect because it would not account for the time between flushes but there are limits of what can be reasonably done and still be doing something useful. If a representative synthetic trace is provided then this benchmark could be revisited and the shift values retuned. Ivybridge 4 threads 3.13.0-rc7 3.13.0-rc7 vanilla altshift-v3 Mean 1 10.50 ( 0.00%) 10.50 ( 0.03%) Mean 2 17.59 ( 0.00%) 17.18 ( 2.34%) Mean 3 22.98 ( 0.00%) 21.74 ( 5.41%) Mean 5 47.13 ( 0.00%) 46.23 ( 1.92%) Mean 8 43.30 ( 0.00%) 42.56 ( 1.72%) Ivybridge 8 threads 3.13.0-rc7 3.13.0-rc7 vanilla altshift-v3 Mean 1 9.45 ( 0.00%) 9.36 ( 0.93%) Mean 2 9.37 ( 0.00%) 9.70 ( -3.54%) Mean 3 9.36 ( 0.00%) 9.29 ( 0.70%) Mean 5 14.49 ( 0.00%) 15.04 ( -3.75%) Mean 8 41.08 ( 0.00%) 38.73 ( 5.71%) Mean 13 32.04 ( 0.00%) 31.24 ( 2.49%) Mean 16 40.05 ( 0.00%) 39.04 ( 2.51%) For both CPUs, average access time is reduced which is good as this is the benchmark that was used to tune the shift values in the first place albeit it is now known *how* the benchmark was used. The scheduler benchmarks were somewhat inconclusive. They showed gains and losses and makes me reconsider how stable those benchmarks really are or if something else might be interfering with the test results recently. Network benchmarks were inconclusive. Almost all results were flat except for netperf-udp tests on the 4 thread machine. These results were unstable and showed large variations between reboots. It is unknown if this is a recent problems but I've noticed before that netperf-udp results tend to vary. Based on these results, changing the default for Ivybridge seems like a logical choice. Signed-off-by: Mel Gorman Tested-by: Davidlohr Bueso Reviewed-by: Alex Shi Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-cqnadffh1tiqrshthRj3Esge@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/intel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index ea04b342c026..bbe1b8b1f1c4 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -628,7 +628,7 @@ static void intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) tlb_flushall_shift = 5; break; case 0x63a: /* Ivybridge */ - tlb_flushall_shift = 1; + tlb_flushall_shift = 2; break; default: tlb_flushall_shift = 6; -- cgit v1.2.3 From b9a3b4c976c1209957326537ad5c0bb633dfd764 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 21 Jan 2014 14:33:22 -0800 Subject: mm, x86: Revisit tlb_flushall_shift tuning for page flushes except on IvyBridge There was a large ebizzy performance regression that was bisected to commit 611ae8e3 (x86/tlb: enable tlb flush range support for x86). The problem was related to the tlb_flushall_shift tuning for IvyBridge which was altered. The problem is that it is not clear if the tuning values for each CPU family is correct as the methodology used to tune the values is unclear. This patch uses a conservative tlb_flushall_shift value for all CPU families except IvyBridge so the decision can be revisited if any regression is found as a result of this change. IvyBridge is an exception as testing with one methodology determined that the value of 2 is acceptable. Details are in the changelog for the patch "x86: mm: Change tlb_flushall_shift for IvyBridge". One important aspect of this to watch out for is Xen. The original commit log mentioned large performance gains on Xen. It's possible Xen is more sensitive to this value if it flushes small ranges of pages more frequently than workloads on bare metal typically do. Signed-off-by: Mel Gorman Tested-by: Davidlohr Bueso Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Cc: Alex Shi Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-dyzMww3fqugnhbhgo6Gxmtkw@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/amd.c | 5 +---- arch/x86/kernel/cpu/intel.c | 10 +++------- 2 files changed, 4 insertions(+), 11 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 59bfebc8c805..96abccaada33 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -768,10 +768,7 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) static void cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c) { - tlb_flushall_shift = 5; - - if (c->x86 <= 0x11) - tlb_flushall_shift = 4; + tlb_flushall_shift = 6; } static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index bbe1b8b1f1c4..d358a3928b8f 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -615,21 +615,17 @@ static void intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) case 0x61d: /* six-core 45 nm xeon "Dunnington" */ tlb_flushall_shift = -1; break; + case 0x63a: /* Ivybridge */ + tlb_flushall_shift = 2; + break; case 0x61a: /* 45 nm nehalem, "Bloomfield" */ case 0x61e: /* 45 nm nehalem, "Lynnfield" */ case 0x625: /* 32 nm nehalem, "Clarkdale" */ case 0x62c: /* 32 nm nehalem, "Gulftown" */ case 0x62e: /* 45 nm nehalem-ex, "Beckton" */ case 0x62f: /* 32 nm Xeon E7 */ - tlb_flushall_shift = 6; - break; case 0x62a: /* SandyBridge */ case 0x62d: /* SandyBridge, "Romely-EP" */ - tlb_flushall_shift = 5; - break; - case 0x63a: /* Ivybridge */ - tlb_flushall_shift = 2; - break; default: tlb_flushall_shift = 6; } -- cgit v1.2.3 From a85eba8814631d0d48361c8b9a7ee0984e80c03c Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Tue, 21 Jan 2014 14:33:15 -0800 Subject: arch/x86/mm/srat: Skip NUMA_NO_NODE while parsing SLIT When ACPI SLIT table has an I/O locality (i.e. a locality unique to an I/O device), numa_set_distance() emits this warning message: NUMA: Warning: node ids are out of bound, from=-1 to=-1 distance=10 acpi_numa_slit_init() calls numa_set_distance() with pxm_to_node(), which assumes that all localities have been parsed with SRAT previously. SRAT does not list I/O localities, where as SLIT lists all localities including I/Os. Hence, pxm_to_node() returns NUMA_NO_NODE (-1) for an I/O locality. I/O localities are not supported and are ignored today, but emitting such warning message leads to unnecessary confusion. Change acpi_numa_slit_init() to avoid calling numa_set_distance() with NUMA_NO_NODE. Signed-off-by: Toshi Kani Acked-by: David Rientjes Signed-off-by: Andrew Morton Cc: Yinghai Lu Link: http://lkml.kernel.org/n/tip-dSvpjjvp8aMzs1ybkftxohlh@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/mm/srat.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 266ca912f62e..5ecf65117e6f 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -42,15 +42,25 @@ static __init inline int srat_disabled(void) return acpi_numa < 0; } -/* Callback for SLIT parsing */ +/* + * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for + * I/O localities since SRAT does not list them. I/O localities are + * not supported at this point. + */ void __init acpi_numa_slit_init(struct acpi_table_slit *slit) { int i, j; - for (i = 0; i < slit->locality_count; i++) - for (j = 0; j < slit->locality_count; j++) + for (i = 0; i < slit->locality_count; i++) { + if (pxm_to_node(i) == NUMA_NO_NODE) + continue; + for (j = 0; j < slit->locality_count; j++) { + if (pxm_to_node(j) == NUMA_NO_NODE) + continue; numa_set_distance(pxm_to_node(i), pxm_to_node(j), slit->entry[slit->locality_count * i + j]); + } + } } /* Callback for Proximity Domain -> x2APIC mapping */ -- cgit v1.2.3 From edc6bc784028f2ef80dff0ff697363ff5a06e3a3 Mon Sep 17 00:00:00 2001 From: David Cohen Date: Tue, 21 Jan 2014 10:41:39 -0800 Subject: x86/intel/mid: Fix X86_INTEL_MID dependencies This patch fixes the following warning: warning: (X86_INTEL_MID) selects INTEL_SCU_IPC which has unmet direct dependencies (X86 && X86_PLATFORM_DEVICES && X86_INTEL_MID) It happens because when selected, X86_INTEL_MID tries to select INTEL_SCU_IPC regardless all its dependencies are met or not. This patch fixes it by adding the missing X86_PLATFORM_DEVICES dependency to X86_INTEL_MID. Reported-by: kbuild test robot Signed-off-by: David Cohen Link: http://lkml.kernel.org/r/1390329699-20782-1-git-send-email-david.a.cohen@linux.intel.com Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cb9af474dfca..3b6922ebf170 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -443,6 +443,7 @@ config X86_INTEL_MID bool "Intel MID platform support" depends on X86_32 depends on X86_EXTENDED_PLATFORM + depends on X86_PLATFORM_DEVICES depends on PCI depends on PCI_GOANY depends on X86_IO_APIC -- cgit v1.2.3 From 39424e89d64661faa0a2e00c5ad1e6dbeebfa972 Mon Sep 17 00:00:00 2001 From: Prarit Bhargava Date: Tue, 28 Jan 2014 08:22:11 -0500 Subject: x86, cpu hotplug: Fix stack frame warning in check_irq_vectors_for_cpu_disable() Further discussion here: http://marc.info/?l=linux-kernel&m=139073901101034&w=2 kbuild, 0day kernel build service, outputs the warning: arch/x86/kernel/irq.c:333:1: warning: the frame size of 2056 bytes is larger than 2048 bytes [-Wframe-larger-than=] because check_irq_vectors_for_cpu_disable() allocates two cpumasks on the stack. Fix this by moving the two cpumasks to a global file context. Reported-by: Fengguang Wu Tested-by: David Rientjes Signed-off-by: Prarit Bhargava Link: http://lkml.kernel.org/r/1390915331-27375-1-git-send-email-prarit@redhat.com Cc: Andi Kleen Cc: Michel Lespinasse Cc: Seiji Aguchi Cc: Yang Zhang Cc: Paul Gortmaker Cc: Janet Morgan Cc: Tony Luck Cc: Ruiv Wang Cc: Gong Chen Cc: Yinghai Lu Signed-off-by: H. Peter Anvin --- arch/x86/kernel/irq.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index dbb60878b744..d99f31d9a750 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -266,6 +266,14 @@ __visible void smp_trace_x86_platform_ipi(struct pt_regs *regs) EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq); #ifdef CONFIG_HOTPLUG_CPU + +/* These two declarations are only used in check_irq_vectors_for_cpu_disable() + * below, which is protected by stop_machine(). Putting them on the stack + * results in a stack frame overflow. Dynamically allocating could result in a + * failure so declare these two cpumasks as global. + */ +static struct cpumask affinity_new, online_new; + /* * This cpu is going to be removed and its vectors migrated to the remaining * online cpus. Check to see if there are enough vectors in the remaining cpus. @@ -277,7 +285,6 @@ int check_irq_vectors_for_cpu_disable(void) unsigned int this_cpu, vector, this_count, count; struct irq_desc *desc; struct irq_data *data; - struct cpumask affinity_new, online_new; this_cpu = smp_processor_id(); cpumask_copy(&online_new, cpu_online_mask); -- cgit v1.2.3 From 85fc73a2cdf10cf42bc36fb3bca3896b2095a1c2 Mon Sep 17 00:00:00 2001 From: Petr Tesarik Date: Sat, 1 Feb 2014 13:30:19 +0100 Subject: x86: Fix the initialization of physnode_map With DISCONTIGMEM, the mapping between a pfn and its owning node is initialized using data provided by the BIOS. However, the initialization may fail if the extents are not aligned to section boundary (64M). The symptom of this bug is an early boot failure in pfn_to_page(), as it tries to access NODE_DATA(__nid) using index from an unitialized element of the physnode_map[] array. While the bug is always present, it is more likely to be hit in kdump kernels on large machines, because: 1. The memory map for a kdump kernel is specified as exactmap, and exactmap is more likely to be unaligned. 2. Large reservations are more likely to span across a 64M boundary. [ hpa: fixed incorrect use of "pfn" instead of "start" ] Signed-off-by: Petr Tesarik Link: http://lkml.kernel.org/r/20140201133019.32e56f86@hananiah.suse.cz Acked-by: David Rientjes Signed-off-by: H. Peter Anvin --- arch/x86/mm/numa_32.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 0342d27ca798..47b6436e41c2 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -52,6 +52,8 @@ void memory_present(int nid, unsigned long start, unsigned long end) nid, start, end); printk(KERN_DEBUG " Setting physnode_map array to node %d for pfns:\n", nid); printk(KERN_DEBUG " "); + start = round_down(start, PAGES_PER_SECTION); + end = round_up(end, PAGES_PER_SECTION); for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) { physnode_map[pfn / PAGES_PER_SECTION] = nid; printk(KERN_CONT "%lx ", pfn); -- cgit v1.2.3 From 081cd62a010f97b5bc1d2b0cd123c5abc692b68a Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Tue, 14 Jan 2014 12:40:09 +0000 Subject: x86/efi: Allow mapping BGRT on x86-32 CONFIG_X86_32 doesn't map the boot services regions into the EFI memory map (see commit 700870119f49 ("x86, efi: Don't map Boot Services on i386")), and so efi_lookup_mapped_addr() will fail to return a valid address. Executing the ioremap() path in efi_bgrt_init() causes the following warning on x86-32 because we're trying to ioremap() RAM, WARNING: CPU: 0 PID: 0 at arch/x86/mm/ioremap.c:102 __ioremap_caller+0x2ad/0x2c0() Modules linked in: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.13.0-0.rc5.git0.1.2.fc21.i686 #1 Hardware name: DellInc. Venue 8 Pro 5830/09RP78, BIOS A02 10/17/2013 00000000 00000000 c0c0df08 c09a5196 00000000 c0c0df38 c0448c1e c0b41310 00000000 00000000 c0b37bc1 00000066 c043bbfd c043bbfd 00e7dfe0 00073eff 00073eff c0c0df48 c0448ce2 00000009 00000000 c0c0df9c c043bbfd 00078d88 Call Trace: [] dump_stack+0x41/0x52 [] warn_slowpath_common+0x7e/0xa0 [] ? __ioremap_caller+0x2ad/0x2c0 [] ? __ioremap_caller+0x2ad/0x2c0 [] warn_slowpath_null+0x22/0x30 [] __ioremap_caller+0x2ad/0x2c0 [] ? acpi_tb_verify_table+0x1c/0x43 [] ? acpi_get_table_with_size+0x63/0xb5 [] ? efi_lookup_mapped_addr+0xe/0xf0 [] ioremap_nocache+0x1b/0x20 [] ? efi_bgrt_init+0x83/0x10c [] efi_bgrt_init+0x83/0x10c [] efi_late_init+0x8/0xa [] start_kernel+0x3ae/0x3c3 [] ? repair_env_string+0x51/0x51 [] i386_start_kernel+0x12e/0x131 Switch to using early_memremap(), which won't trigger this warning, and has the added benefit of more accurately conveying what we're trying to do - map a chunk of memory. This patch addresses the following bug report, https://bugzilla.kernel.org/show_bug.cgi?id=67911 Reported-by: Adam Williamson Cc: Josh Triplett Cc: Matthew Garrett Cc: Rafael J. Wysocki Signed-off-by: Matt Fleming --- arch/x86/platform/efi/efi-bgrt.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index 7145ec63c520..4df9591eadad 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -49,7 +49,8 @@ void __init efi_bgrt_init(void) image = efi_lookup_mapped_addr(bgrt_tab->image_address); if (!image) { - image = ioremap(bgrt_tab->image_address, sizeof(bmp_header)); + image = early_memremap(bgrt_tab->image_address, + sizeof(bmp_header)); ioremapped = true; if (!image) return; @@ -57,7 +58,7 @@ void __init efi_bgrt_init(void) memcpy_fromio(&bmp_header, image, sizeof(bmp_header)); if (ioremapped) - iounmap(image); + early_iounmap(image, sizeof(bmp_header)); bgrt_image_size = bmp_header.size; bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL); @@ -65,7 +66,8 @@ void __init efi_bgrt_init(void) return; if (ioremapped) { - image = ioremap(bgrt_tab->image_address, bmp_header.size); + image = early_memremap(bgrt_tab->image_address, + bmp_header.size); if (!image) { kfree(bgrt_image); bgrt_image = NULL; @@ -75,5 +77,5 @@ void __init efi_bgrt_init(void) memcpy_fromio(bgrt_image, image, bgrt_image_size); if (ioremapped) - iounmap(image); + early_iounmap(image, bmp_header.size); } -- cgit v1.2.3 From 75a1ba5b2c529db60ca49626bcaf0bddf4548438 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 3 Feb 2014 21:41:44 +0100 Subject: x86, microcode, AMD: Unify valid container checks For additional coverage, BorisO and friends unknowlingly did swap AMD microcode with Intel microcode blobs in order to see what happens. What did happen on 32-bit was [ 5.722656] BUG: unable to handle kernel paging request at be3a6008 [ 5.722693] IP: [] load_microcode_amd+0x24/0x3f0 [ 5.722716] *pdpt = 0000000000000000 *pde = 0000000000000000 because there was a valid initrd there but without valid microcode in it and the container check happened *after* the relocated ramdisk handling on 32-bit, which was clearly wrong. While at it, take care of the ramdisk relocation on both 32- and 64-bit as it is done on both. Also, comment what we're doing because this code is a bit tricky. Reported-and-tested-by: Boris Ostrovsky Signed-off-by: Borislav Petkov Link: http://lkml.kernel.org/r/1391460104-7261-1-git-send-email-bp@alien8.de Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/microcode/amd_early.c | 43 +++++++++++++++++++++---------- 1 file changed, 29 insertions(+), 14 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 8384c0fa206f..617a9e284245 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -285,6 +285,15 @@ static void __init collect_cpu_sig_on_bsp(void *arg) uci->cpu_sig.sig = cpuid_eax(0x00000001); } + +static void __init get_bsp_sig(void) +{ + unsigned int bsp = boot_cpu_data.cpu_index; + struct ucode_cpu_info *uci = ucode_cpu_info + bsp; + + if (!uci->cpu_sig.sig) + smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1); +} #else void load_ucode_amd_ap(void) { @@ -337,31 +346,37 @@ void load_ucode_amd_ap(void) int __init save_microcode_in_initrd_amd(void) { + unsigned long cont; enum ucode_state ret; u32 eax; -#ifdef CONFIG_X86_32 - unsigned int bsp = boot_cpu_data.cpu_index; - struct ucode_cpu_info *uci = ucode_cpu_info + bsp; - - if (!uci->cpu_sig.sig) - smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1); + if (!container) + return -EINVAL; +#ifdef CONFIG_X86_32 + get_bsp_sig(); + cont = (unsigned long)container; +#else /* - * Take into account the fact that the ramdisk might get relocated - * and therefore we need to recompute the container's position in - * virtual memory space. + * We need the physical address of the container for both bitness since + * boot_params.hdr.ramdisk_image is a physical address. */ - container = (u8 *)(__va((u32)relocated_ramdisk) + - ((u32)container - boot_params.hdr.ramdisk_image)); + cont = __pa(container); #endif + + /* + * Take into account the fact that the ramdisk might get relocated and + * therefore we need to recompute the container's position in virtual + * memory space. + */ + if (relocated_ramdisk) + container = (u8 *)(__va(relocated_ramdisk) + + (cont - boot_params.hdr.ramdisk_image)); + if (ucode_new_rev) pr_info("microcode: updated early to new patch_level=0x%08x\n", ucode_new_rev); - if (!container) - return -EINVAL; - eax = cpuid_eax(0x00000001); eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); -- cgit v1.2.3