From 4fd017708c4a067da51a2b5cf8aedddf4e840b1f Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 12 Oct 2011 21:06:51 +0200 Subject: mm: Check if PTE is already allocated during page fault With transparent hugepage support, handle_mm_fault() has to be careful that a normal PMD has been established before handling a PTE fault. To achieve this, it used __pte_alloc() directly instead of pte_alloc_map as pte_alloc_map is unsafe to run against a huge PMD. pte_offset_map() is called once it is known the PMD is safe. pte_alloc_map() is smart enough to check if a PTE is already present before calling __pte_alloc but this check was lost. As a consequence, PTEs may be allocated unnecessarily and the page table lock taken. Thi useless PTE does get cleaned up but it's a performance hit which is visible in page_test from aim9. This patch simply re-adds the check normally done by pte_alloc_map to check if the PTE needs to be allocated before taking the page table lock. The effect is noticable in page_test from aim9. AIM9 2.6.38-vanilla 2.6.38-checkptenone creat-clo 446.10 ( 0.00%) 424.47 (-5.10%) page_test 38.10 ( 0.00%) 42.04 ( 9.37%) brk_test 52.45 ( 0.00%) 51.57 (-1.71%) exec_test 382.00 ( 0.00%) 456.90 (16.39%) fork_test 60.11 ( 0.00%) 67.79 (11.34%) MMTests Statistics: duration Total Elapsed Time (seconds) 611.90 612.22 (While this affects 2.6.38, it is a performance rather than a functional bug and normally outside the rules -stable. While the big performance differences are to a microbench, the difference in fork and exec performance may be significant enough that -stable wants to consider the patch) Reported-by: Raz Ben Yehuda Signed-off-by: Mel Gorman Signed-off-by: Andrea Arcangeli Cc: Linus Torvalds Cc: Andrew Morton Cc: Peter Zijlstra Cc: Rik van Riel [ Picked this up from the AutoNUMA tree to help it upstream and to allow apples-to-apples performance comparisons. ] Signed-off-by: Ingo Molnar --- mm/memory.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'mm/memory.c') diff --git a/mm/memory.c b/mm/memory.c index 221fc9ffcab1..7cf762857baa 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3560,7 +3560,8 @@ retry: * run pte_offset_map on the pmd, if an huge pmd could * materialize from under us from a different thread. */ - if (unlikely(pmd_none(*pmd)) && __pte_alloc(mm, vma, pmd, address)) + if (unlikely(pmd_none(*pmd)) && + unlikely(__pte_alloc(mm, vma, pmd, address))) return VM_FAULT_OOM; /* if an huge pmd materialized from under us just retry later */ if (unlikely(pmd_trans_huge(*pmd))) -- cgit v1.2.3 From 0b9d705297b273657923518dbea2377cd03532ed Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 5 Oct 2012 21:36:27 +0200 Subject: mm: numa: Support NUMA hinting page faults from gup/gup_fast Introduce FOLL_NUMA to tell follow_page to check pte/pmd_numa. get_user_pages must use FOLL_NUMA, and it's safe to do so because it always invokes handle_mm_fault and retries the follow_page later. KVM secondary MMU page faults will trigger the NUMA hinting page faults through gup_fast -> get_user_pages -> follow_page -> handle_mm_fault. Other follow_page callers like KSM should not use FOLL_NUMA, or they would fail to get the pages if they use follow_page instead of get_user_pages. [ This patch was picked up from the AutoNUMA tree. ] Originally-by: Andrea Arcangeli Cc: Linus Torvalds Cc: Andrew Morton Cc: Peter Zijlstra Cc: Andrea Arcangeli Cc: Rik van Riel [ ported to this tree. ] Signed-off-by: Ingo Molnar Reviewed-by: Rik van Riel --- include/linux/mm.h | 1 + mm/memory.c | 17 +++++++++++++++++ 2 files changed, 18 insertions(+) (limited to 'mm/memory.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1856c62d82cd..fa1615211159 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1572,6 +1572,7 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address, #define FOLL_MLOCK 0x40 /* mark page as mlocked */ #define FOLL_SPLIT 0x80 /* don't return transhuge pages, split them */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ +#define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); diff --git a/mm/memory.c b/mm/memory.c index 7cf762857baa..cd8e0daf1912 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1517,6 +1517,8 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); goto out; } + if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) + goto no_page_table; if (pmd_trans_huge(*pmd)) { if (flags & FOLL_SPLIT) { split_huge_page_pmd(mm, pmd); @@ -1546,6 +1548,8 @@ split_fallthrough: pte = *ptep; if (!pte_present(pte)) goto no_page; + if ((flags & FOLL_NUMA) && pte_numa(pte)) + goto no_page; if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; @@ -1697,6 +1701,19 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); vm_flags &= (gup_flags & FOLL_FORCE) ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); + + /* + * If FOLL_FORCE and FOLL_NUMA are both set, handle_mm_fault + * would be called on PROT_NONE ranges. We must never invoke + * handle_mm_fault on PROT_NONE ranges or the NUMA hinting + * page faults would unprotect the PROT_NONE ranges if + * _PAGE_NUMA and _PAGE_PROTNONE are sharing the same pte/pmd + * bitflag. So to avoid that, don't set FOLL_NUMA if + * FOLL_FORCE is set. + */ + if (!(gup_flags & FOLL_FORCE)) + gup_flags |= FOLL_NUMA; + i = 0; do { -- cgit v1.2.3 From d10e63f29488b0f312a443f9507ea9b6fd3c9090 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 25 Oct 2012 14:16:31 +0200 Subject: mm: numa: Create basic numa page hinting infrastructure Note: This patch started as "mm/mpol: Create special PROT_NONE infrastructure" and preserves the basic idea but steals *very* heavily from "autonuma: numa hinting page faults entry points" for the actual fault handlers without the migration parts. The end result is barely recognisable as either patch so all Signed-off and Reviewed-bys are dropped. If Peter, Ingo and Andrea are ok with this version, I will re-add the signed-offs-by to reflect the history. In order to facilitate a lazy -- fault driven -- migration of pages, create a special transient PAGE_NUMA variant, we can then use the 'spurious' protection faults to drive our migrations from. The meaning of PAGE_NUMA depends on the architecture but on x86 it is effectively PROT_NONE. Actual PROT_NONE mappings will not generate these NUMA faults for the reason that the page fault code checks the permission on the VMA (and will throw a segmentation fault on actual PROT_NONE mappings), before it ever calls handle_mm_fault. [dhillf@gmail.com: Fix typo] Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel --- include/linux/huge_mm.h | 10 +++++ mm/huge_memory.c | 22 ++++++++++ mm/memory.c | 112 ++++++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 141 insertions(+), 3 deletions(-) (limited to 'mm/memory.c') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index b31cb7da0346..a1d26a98c655 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -159,6 +159,10 @@ static inline struct page *compound_trans_head(struct page *page) } return page; } + +extern int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr, + pmd_t pmd, pmd_t *pmdp); + #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) @@ -195,6 +199,12 @@ static inline int pmd_trans_huge_lock(pmd_t *pmd, { return 0; } + +static inline int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr, + pmd_t pmd, pmd_t *pmdp) +{ +} + #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_HUGE_MM_H */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index cd24aa562144..f5f37630c54d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1018,6 +1018,28 @@ out: return page; } +/* NUMA hinting page fault entry point for trans huge pmds */ +int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr, + pmd_t pmd, pmd_t *pmdp) +{ + struct page *page; + unsigned long haddr = addr & HPAGE_PMD_MASK; + + spin_lock(&mm->page_table_lock); + if (unlikely(!pmd_same(pmd, *pmdp))) + goto out_unlock; + + page = pmd_page(pmd); + pmd = pmd_mknonnuma(pmd); + set_pmd_at(mm, haddr, pmdp, pmd); + VM_BUG_ON(pmd_numa(*pmdp)); + update_mmu_cache_pmd(vma, addr, pmdp); + +out_unlock: + spin_unlock(&mm->page_table_lock); + return 0; +} + int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr) { diff --git a/mm/memory.c b/mm/memory.c index cd8e0daf1912..e30616f2cc3d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3448,6 +3448,103 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); } +int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd) +{ + struct page *page; + spinlock_t *ptl; + + /* + * The "pte" at this point cannot be used safely without + * validation through pte_unmap_same(). It's of NUMA type but + * the pfn may be screwed if the read is non atomic. + * + * ptep_modify_prot_start is not called as this is clearing + * the _PAGE_NUMA bit and it is not really expected that there + * would be concurrent hardware modifications to the PTE. + */ + ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + if (unlikely(!pte_same(*ptep, pte))) + goto out_unlock; + pte = pte_mknonnuma(pte); + set_pte_at(mm, addr, ptep, pte); + update_mmu_cache(vma, addr, ptep); + + page = vm_normal_page(vma, addr, pte); + if (!page) { + pte_unmap_unlock(ptep, ptl); + return 0; + } + +out_unlock: + pte_unmap_unlock(ptep, ptl); + return 0; +} + +/* NUMA hinting page fault entry point for regular pmds */ +#ifdef CONFIG_NUMA_BALANCING +static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp) +{ + pmd_t pmd; + pte_t *pte, *orig_pte; + unsigned long _addr = addr & PMD_MASK; + unsigned long offset; + spinlock_t *ptl; + bool numa = false; + + spin_lock(&mm->page_table_lock); + pmd = *pmdp; + if (pmd_numa(pmd)) { + set_pmd_at(mm, _addr, pmdp, pmd_mknonnuma(pmd)); + numa = true; + } + spin_unlock(&mm->page_table_lock); + + if (!numa) + return 0; + + /* we're in a page fault so some vma must be in the range */ + BUG_ON(!vma); + BUG_ON(vma->vm_start >= _addr + PMD_SIZE); + offset = max(_addr, vma->vm_start) & ~PMD_MASK; + VM_BUG_ON(offset >= PMD_SIZE); + orig_pte = pte = pte_offset_map_lock(mm, pmdp, _addr, &ptl); + pte += offset >> PAGE_SHIFT; + for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) { + pte_t pteval = *pte; + struct page *page; + if (!pte_present(pteval)) + continue; + if (!pte_numa(pteval)) + continue; + if (addr >= vma->vm_end) { + vma = find_vma(mm, addr); + /* there's a pte present so there must be a vma */ + BUG_ON(!vma); + BUG_ON(addr < vma->vm_start); + } + if (pte_numa(pteval)) { + pteval = pte_mknonnuma(pteval); + set_pte_at(mm, addr, pte, pteval); + } + page = vm_normal_page(vma, addr, pteval); + if (unlikely(!page)) + continue; + } + pte_unmap_unlock(orig_pte, ptl); + + return 0; +} +#else +static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp) +{ + BUG(); +} +#endif /* CONFIG_NUMA_BALANCING */ + /* * These routines also need to handle stuff like marking pages dirty * and/or accessed for architectures that don't do it in hardware (most @@ -3486,6 +3583,9 @@ int handle_pte_fault(struct mm_struct *mm, pte, pmd, flags, entry); } + if (pte_numa(entry)) + return do_numa_page(mm, vma, address, entry, pte, pmd); + ptl = pte_lockptr(mm, pmd); spin_lock(ptl); if (unlikely(!pte_same(*pte, entry))) @@ -3554,9 +3654,11 @@ retry: barrier(); if (pmd_trans_huge(orig_pmd)) { - if (flags & FAULT_FLAG_WRITE && - !pmd_write(orig_pmd) && - !pmd_trans_splitting(orig_pmd)) { + if (pmd_numa(*pmd)) + return do_huge_pmd_numa_page(mm, address, + orig_pmd, pmd); + + if ((flags & FAULT_FLAG_WRITE) && !pmd_write(orig_pmd)) { ret = do_huge_pmd_wp_page(mm, vma, address, pmd, orig_pmd); /* @@ -3568,10 +3670,14 @@ retry: goto retry; return ret; } + return 0; } } + if (pmd_numa(*pmd)) + return do_pmd_numa_page(mm, vma, address, pmd); + /* * Use __pte_alloc instead of pte_alloc_map, because we can't * run pte_offset_map on the pmd, if an huge pmd could -- cgit v1.2.3 From 4daae3b4b9e49b7e0935499a352f1c59d90287d2 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 2 Nov 2012 11:33:45 +0000 Subject: mm: mempolicy: Use _PAGE_NUMA to migrate pages Note: Based on "mm/mpol: Use special PROT_NONE to migrate pages" but sufficiently different that the signed-off-bys were dropped Combine our previous _PAGE_NUMA, mpol_misplaced and migrate_misplaced_page() pieces into an effective migrate on fault scheme. Note that (on x86) we rely on PROT_NONE pages being !present and avoid the TLB flush from try_to_unmap(TTU_MIGRATION). This greatly improves the page-migration performance. Based-on-work-by: Peter Zijlstra Signed-off-by: Mel Gorman --- include/linux/huge_mm.h | 9 +++++---- mm/huge_memory.c | 31 ++++++++++++++++++++++++++++--- mm/memory.c | 32 +++++++++++++++++++++++++++----- 3 files changed, 60 insertions(+), 12 deletions(-) (limited to 'mm/memory.c') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index a1d26a98c655..dabb5108d6c0 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -160,8 +160,8 @@ static inline struct page *compound_trans_head(struct page *page) return page; } -extern int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr, - pmd_t pmd, pmd_t *pmdp); +extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pmd_t pmd, pmd_t *pmdp); #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) @@ -200,9 +200,10 @@ static inline int pmd_trans_huge_lock(pmd_t *pmd, return 0; } -static inline int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr, - pmd_t pmd, pmd_t *pmdp) +static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pmd_t pmd, pmd_t *pmdp) { + return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f5f37630c54d..5723b551c023 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include "internal.h" @@ -1019,17 +1020,39 @@ out: } /* NUMA hinting page fault entry point for trans huge pmds */ -int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr, - pmd_t pmd, pmd_t *pmdp) +int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pmd_t pmd, pmd_t *pmdp) { - struct page *page; + struct page *page = NULL; unsigned long haddr = addr & HPAGE_PMD_MASK; + int target_nid; spin_lock(&mm->page_table_lock); if (unlikely(!pmd_same(pmd, *pmdp))) goto out_unlock; page = pmd_page(pmd); + get_page(page); + spin_unlock(&mm->page_table_lock); + + target_nid = mpol_misplaced(page, vma, haddr); + if (target_nid == -1) + goto clear_pmdnuma; + + /* + * Due to lacking code to migrate thp pages, we'll split + * (which preserves the special PROT_NONE) and re-take the + * fault on the normal pages. + */ + split_huge_page(page); + put_page(page); + return 0; + +clear_pmdnuma: + spin_lock(&mm->page_table_lock); + if (unlikely(!pmd_same(pmd, *pmdp))) + goto out_unlock; + pmd = pmd_mknonnuma(pmd); set_pmd_at(mm, haddr, pmdp, pmd); VM_BUG_ON(pmd_numa(*pmdp)); @@ -1037,6 +1060,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr, out_unlock: spin_unlock(&mm->page_table_lock); + if (page) + put_page(page); return 0; } diff --git a/mm/memory.c b/mm/memory.c index e30616f2cc3d..d52542680e10 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -57,6 +57,7 @@ #include #include #include +#include #include #include @@ -3451,8 +3452,9 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd) { - struct page *page; + struct page *page = NULL; spinlock_t *ptl; + int current_nid, target_nid; /* * The "pte" at this point cannot be used safely without @@ -3465,8 +3467,11 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, */ ptl = pte_lockptr(mm, pmd); spin_lock(ptl); - if (unlikely(!pte_same(*ptep, pte))) - goto out_unlock; + if (unlikely(!pte_same(*ptep, pte))) { + pte_unmap_unlock(ptep, ptl); + goto out; + } + pte = pte_mknonnuma(pte); set_pte_at(mm, addr, ptep, pte); update_mmu_cache(vma, addr, ptep); @@ -3477,8 +3482,25 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, return 0; } -out_unlock: + get_page(page); + current_nid = page_to_nid(page); + target_nid = mpol_misplaced(page, vma, addr); pte_unmap_unlock(ptep, ptl); + if (target_nid == -1) { + /* + * Account for the fault against the current node if it not + * being replaced regardless of where the page is located. + */ + current_nid = numa_node_id(); + put_page(page); + goto out; + } + + /* Migrate to the requested node */ + if (migrate_misplaced_page(page, target_nid)) + current_nid = target_nid; + +out: return 0; } @@ -3655,7 +3677,7 @@ retry: barrier(); if (pmd_trans_huge(orig_pmd)) { if (pmd_numa(*pmd)) - return do_huge_pmd_numa_page(mm, address, + return do_huge_pmd_numa_page(mm, vma, address, orig_pmd, pmd); if ((flags & FAULT_FLAG_WRITE) && !pmd_write(orig_pmd)) { -- cgit v1.2.3 From cbee9f88ec1b8dd6b58f25f54e4f52c82ed77690 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 25 Oct 2012 14:16:43 +0200 Subject: mm: numa: Add fault driven placement and migration NOTE: This patch is based on "sched, numa, mm: Add fault driven placement and migration policy" but as it throws away all the policy to just leave a basic foundation I had to drop the signed-offs-by. This patch creates a bare-bones method for setting PTEs pte_numa in the context of the scheduler that when faulted later will be faulted onto the node the CPU is running on. In itself this does nothing useful but any placement policy will fundamentally depend on receiving hints on placement from fault context and doing something intelligent about it. Signed-off-by: Mel Gorman Acked-by: Rik van Riel --- arch/sh/mm/Kconfig | 1 + arch/x86/Kconfig | 2 + include/linux/mm_types.h | 11 +++++ include/linux/sched.h | 20 ++++++++ kernel/sched/core.c | 13 +++++ kernel/sched/fair.c | 125 +++++++++++++++++++++++++++++++++++++++++++++++ kernel/sched/features.h | 7 +++ kernel/sched/sched.h | 6 +++ kernel/sysctl.c | 24 ++++++++- mm/huge_memory.c | 5 +- mm/memory.c | 14 +++++- 11 files changed, 224 insertions(+), 4 deletions(-) (limited to 'mm/memory.c') diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig index cb8f9920f4dd..0f7c852f355c 100644 --- a/arch/sh/mm/Kconfig +++ b/arch/sh/mm/Kconfig @@ -111,6 +111,7 @@ config VSYSCALL config NUMA bool "Non Uniform Memory Access (NUMA) Support" depends on MMU && SYS_SUPPORTS_NUMA && EXPERIMENTAL + select ARCH_WANT_NUMA_VARIABLE_LOCALITY default n help Some SH systems have many various memories scattered around diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 46c3bff3ced2..1137028fc6d9 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -22,6 +22,8 @@ config X86 def_bool y select HAVE_AOUT if X86_32 select HAVE_UNSTABLE_SCHED_CLOCK + select ARCH_SUPPORTS_NUMA_BALANCING + select ARCH_WANTS_PROT_NUMA_PROT_NONE select HAVE_IDE select HAVE_OPROFILE select HAVE_PCSPKR_PLATFORM diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 31f8a3af7d94..ed8638c29b3e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -397,6 +397,17 @@ struct mm_struct { #endif #ifdef CONFIG_CPUMASK_OFFSTACK struct cpumask cpumask_allocation; +#endif +#ifdef CONFIG_NUMA_BALANCING + /* + * numa_next_scan is the next time when the PTEs will me marked + * pte_numa to gather statistics and migrate pages to new nodes + * if necessary + */ + unsigned long numa_next_scan; + + /* numa_scan_seq prevents two threads setting pte_numa */ + int numa_scan_seq; #endif struct uprobes_state uprobes_state; }; diff --git a/include/linux/sched.h b/include/linux/sched.h index 0dd42a02df2e..844af5b12cb2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1479,6 +1479,14 @@ struct task_struct { short il_next; short pref_node_fork; #endif +#ifdef CONFIG_NUMA_BALANCING + int numa_scan_seq; + int numa_migrate_seq; + unsigned int numa_scan_period; + u64 node_stamp; /* migration stamp */ + struct callback_head numa_work; +#endif /* CONFIG_NUMA_BALANCING */ + struct rcu_head rcu; /* @@ -1553,6 +1561,14 @@ struct task_struct { /* Future-safe accessor for struct task_struct's cpus_allowed. */ #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) +#ifdef CONFIG_NUMA_BALANCING +extern void task_numa_fault(int node, int pages); +#else +static inline void task_numa_fault(int node, int pages) +{ +} +#endif + /* * Priority of a process goes from 0..MAX_PRIO-1, valid RT * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH @@ -1990,6 +2006,10 @@ enum sched_tunable_scaling { }; extern enum sched_tunable_scaling sysctl_sched_tunable_scaling; +extern unsigned int sysctl_numa_balancing_scan_period_min; +extern unsigned int sysctl_numa_balancing_scan_period_max; +extern unsigned int sysctl_numa_balancing_settle_count; + #ifdef CONFIG_SCHED_DEBUG extern unsigned int sysctl_sched_migration_cost; extern unsigned int sysctl_sched_nr_migrate; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2d8927fda712..cad0d092ce3b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1533,6 +1533,19 @@ static void __sched_fork(struct task_struct *p) #ifdef CONFIG_PREEMPT_NOTIFIERS INIT_HLIST_HEAD(&p->preempt_notifiers); #endif + +#ifdef CONFIG_NUMA_BALANCING + if (p->mm && atomic_read(&p->mm->mm_users) == 1) { + p->mm->numa_next_scan = jiffies; + p->mm->numa_scan_seq = 0; + } + + p->node_stamp = 0ULL; + p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0; + p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0; + p->numa_scan_period = sysctl_numa_balancing_scan_period_min; + p->numa_work.next = &p->numa_work; +#endif /* CONFIG_NUMA_BALANCING */ } /* diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6b800a14b990..6831abb5dbef 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -26,6 +26,8 @@ #include #include #include +#include +#include #include @@ -776,6 +778,126 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) * Scheduling class queueing methods: */ +#ifdef CONFIG_NUMA_BALANCING +/* + * numa task sample period in ms: 5s + */ +unsigned int sysctl_numa_balancing_scan_period_min = 5000; +unsigned int sysctl_numa_balancing_scan_period_max = 5000*16; + +static void task_numa_placement(struct task_struct *p) +{ + int seq = ACCESS_ONCE(p->mm->numa_scan_seq); + + if (p->numa_scan_seq == seq) + return; + p->numa_scan_seq = seq; + + /* FIXME: Scheduling placement policy hints go here */ +} + +/* + * Got a PROT_NONE fault for a page on @node. + */ +void task_numa_fault(int node, int pages) +{ + struct task_struct *p = current; + + /* FIXME: Allocate task-specific structure for placement policy here */ + + task_numa_placement(p); +} + +/* + * The expensive part of numa migration is done from task_work context. + * Triggered from task_tick_numa(). + */ +void task_numa_work(struct callback_head *work) +{ + unsigned long migrate, next_scan, now = jiffies; + struct task_struct *p = current; + struct mm_struct *mm = p->mm; + + WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work)); + + work->next = work; /* protect against double add */ + /* + * Who cares about NUMA placement when they're dying. + * + * NOTE: make sure not to dereference p->mm before this check, + * exit_task_work() happens _after_ exit_mm() so we could be called + * without p->mm even though we still had it when we enqueued this + * work. + */ + if (p->flags & PF_EXITING) + return; + + /* + * Enforce maximal scan/migration frequency.. + */ + migrate = mm->numa_next_scan; + if (time_before(now, migrate)) + return; + + if (p->numa_scan_period == 0) + p->numa_scan_period = sysctl_numa_balancing_scan_period_min; + + next_scan = now + 2*msecs_to_jiffies(p->numa_scan_period); + if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate) + return; + + ACCESS_ONCE(mm->numa_scan_seq)++; + { + struct vm_area_struct *vma; + + down_read(&mm->mmap_sem); + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (!vma_migratable(vma)) + continue; + change_prot_numa(vma, vma->vm_start, vma->vm_end); + } + up_read(&mm->mmap_sem); + } +} + +/* + * Drive the periodic memory faults.. + */ +void task_tick_numa(struct rq *rq, struct task_struct *curr) +{ + struct callback_head *work = &curr->numa_work; + u64 period, now; + + /* + * We don't care about NUMA placement if we don't have memory. + */ + if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work) + return; + + /* + * Using runtime rather than walltime has the dual advantage that + * we (mostly) drive the selection from busy threads and that the + * task needs to have done some actual work before we bother with + * NUMA placement. + */ + now = curr->se.sum_exec_runtime; + period = (u64)curr->numa_scan_period * NSEC_PER_MSEC; + + if (now - curr->node_stamp > period) { + curr->node_stamp = now; + + if (!time_before(jiffies, curr->mm->numa_next_scan)) { + init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */ + task_work_add(curr, work, true); + } + } +} +#else +static void task_tick_numa(struct rq *rq, struct task_struct *curr) +{ +} +#endif /* CONFIG_NUMA_BALANCING */ + static void account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) { @@ -4954,6 +5076,9 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) cfs_rq = cfs_rq_of(se); entity_tick(cfs_rq, se, queued); } + + if (sched_feat_numa(NUMA)) + task_tick_numa(rq, curr); } /* diff --git a/kernel/sched/features.h b/kernel/sched/features.h index eebefcad7027..5fb7aefbec80 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -61,3 +61,10 @@ SCHED_FEAT(TTWU_QUEUE, true) SCHED_FEAT(FORCE_SD_OVERLAP, false) SCHED_FEAT(RT_RUNTIME_SHARE, true) SCHED_FEAT(LB_MIN, false) + +/* + * Apply the automatic NUMA scheduling policy + */ +#ifdef CONFIG_NUMA_BALANCING +SCHED_FEAT(NUMA, true) +#endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 7a7db09cfabc..ae31c051ff2f 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -648,6 +648,12 @@ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR]; #define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) #endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */ +#ifdef CONFIG_NUMA_BALANCING +#define sched_feat_numa(x) sched_feat(x) +#else +#define sched_feat_numa(x) (0) +#endif + static inline u64 global_rt_period(void) { return (u64)sysctl_sched_rt_period * NSEC_PER_USEC; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 26f65eaa01f9..025e1ae50ef1 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -256,9 +256,11 @@ static int min_sched_granularity_ns = 100000; /* 100 usecs */ static int max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */ static int min_wakeup_granularity_ns; /* 0 usecs */ static int max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */ +#ifdef CONFIG_SMP static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE; static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1; -#endif +#endif /* CONFIG_SMP */ +#endif /* CONFIG_SCHED_DEBUG */ #ifdef CONFIG_COMPACTION static int min_extfrag_threshold; @@ -301,6 +303,7 @@ static struct ctl_table kern_table[] = { .extra1 = &min_wakeup_granularity_ns, .extra2 = &max_wakeup_granularity_ns, }, +#ifdef CONFIG_SMP { .procname = "sched_tunable_scaling", .data = &sysctl_sched_tunable_scaling, @@ -347,7 +350,24 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &one, }, -#endif +#endif /* CONFIG_SMP */ +#ifdef CONFIG_NUMA_BALANCING + { + .procname = "numa_balancing_scan_period_min_ms", + .data = &sysctl_numa_balancing_scan_period_min, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "numa_balancing_scan_period_max_ms", + .data = &sysctl_numa_balancing_scan_period_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif /* CONFIG_NUMA_BALANCING */ +#endif /* CONFIG_SCHED_DEBUG */ { .procname = "sched_rt_period_us", .data = &sysctl_sched_rt_period, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index d79f7a55bf6f..ee8133794a56 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1046,6 +1046,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, */ split_huge_page(page); put_page(page); + return 0; clear_pmdnuma: @@ -1060,8 +1061,10 @@ clear_pmdnuma: out_unlock: spin_unlock(&mm->page_table_lock); - if (page) + if (page) { put_page(page); + task_numa_fault(numa_node_id(), HPAGE_PMD_NR); + } return 0; } diff --git a/mm/memory.c b/mm/memory.c index d52542680e10..8012c1907895 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3454,7 +3454,8 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, { struct page *page = NULL; spinlock_t *ptl; - int current_nid, target_nid; + int current_nid = -1; + int target_nid; /* * The "pte" at this point cannot be used safely without @@ -3501,6 +3502,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, current_nid = target_nid; out: + task_numa_fault(current_nid, 1); return 0; } @@ -3537,6 +3539,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) { pte_t pteval = *pte; struct page *page; + int curr_nid; if (!pte_present(pteval)) continue; if (!pte_numa(pteval)) @@ -3554,6 +3557,15 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, page = vm_normal_page(vma, addr, pteval); if (unlikely(!page)) continue; + /* only check non-shared pages */ + if (unlikely(page_mapcount(page) != 1)) + continue; + pte_unmap_unlock(pte, ptl); + + curr_nid = page_to_nid(page); + task_numa_fault(curr_nid, 1); + + pte = pte_offset_map_lock(mm, pmdp, addr, &ptl); } pte_unmap_unlock(orig_pte, ptl); -- cgit v1.2.3 From 03c5a6e16322c997bf8f264851bfa3f532ad515f Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 2 Nov 2012 14:52:48 +0000 Subject: mm: numa: Add pte updates, hinting and migration stats It is tricky to quantify the basic cost of automatic NUMA placement in a meaningful manner. This patch adds some vmstats that can be used as part of a basic costing model. u = basic unit = sizeof(void *) Ca = cost of struct page access = sizeof(struct page) / u Cpte = Cost PTE access = Ca Cupdate = Cost PTE update = (2 * Cpte) + (2 * Wlock) where Cpte is incurred twice for a read and a write and Wlock is a constant representing the cost of taking or releasing a lock Cnumahint = Cost of a minor page fault = some high constant e.g. 1000 Cpagerw = Cost to read or write a full page = Ca + PAGE_SIZE/u Ci = Cost of page isolation = Ca + Wi where Wi is a constant that should reflect the approximate cost of the locking operation Cpagecopy = Cpagerw + (Cpagerw * Wnuma) + Ci + (Ci * Wnuma) where Wnuma is the approximate NUMA factor. 1 is local. 1.2 would imply that remote accesses are 20% more expensive Balancing cost = Cpte * numa_pte_updates + Cnumahint * numa_hint_faults + Ci * numa_pages_migrated + Cpagecopy * numa_pages_migrated Note that numa_pages_migrated is used as a measure of how many pages were isolated even though it would miss pages that failed to migrate. A vmstat counter could have been added for it but the isolation cost is pretty marginal in comparison to the overall cost so it seemed overkill. The ideal way to measure automatic placement benefit would be to count the number of remote accesses versus local accesses and do something like benefit = (remote_accesses_before - remove_access_after) * Wnuma but the information is not readily available. As a workload converges, the expection would be that the number of remote numa hints would reduce to 0. convergence = numa_hint_faults_local / numa_hint_faults where this is measured for the last N number of numa hints recorded. When the workload is fully converged the value is 1. This can measure if the placement policy is converging and how fast it is doing it. Signed-off-by: Mel Gorman Acked-by: Rik van Riel --- include/linux/vm_event_item.h | 6 ++++++ include/linux/vmstat.h | 8 ++++++++ mm/huge_memory.c | 5 +++++ mm/memory.c | 12 ++++++++++++ mm/mempolicy.c | 2 ++ mm/migrate.c | 3 ++- mm/vmstat.c | 6 ++++++ 7 files changed, 41 insertions(+), 1 deletion(-) (limited to 'mm/memory.c') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index a1f750b8e72a..55600049e794 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -38,6 +38,12 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY, KSWAPD_SKIP_CONGESTION_WAIT, PAGEOUTRUN, ALLOCSTALL, PGROTATED, +#ifdef CONFIG_NUMA_BALANCING + NUMA_PTE_UPDATES, + NUMA_HINT_FAULTS, + NUMA_HINT_FAULTS_LOCAL, + NUMA_PAGE_MIGRATE, +#endif #ifdef CONFIG_MIGRATION PGMIGRATE_SUCCESS, PGMIGRATE_FAIL, #endif diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 92a86b2cce33..a13291f7da88 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -80,6 +80,14 @@ static inline void vm_events_fold_cpu(int cpu) #endif /* CONFIG_VM_EVENT_COUNTERS */ +#ifdef CONFIG_NUMA_BALANCING +#define count_vm_numa_event(x) count_vm_event(x) +#define count_vm_numa_events(x, y) count_vm_events(x, y) +#else +#define count_vm_numa_event(x) do {} while (0) +#define count_vm_numa_events(x, y) do {} while (0) +#endif /* CONFIG_NUMA_BALANCING */ + #define __count_zone_vm_events(item, zone, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + \ zone_idx(zone), delta) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index ee8133794a56..f3a477fffd09 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1026,6 +1026,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page = NULL; unsigned long haddr = addr & HPAGE_PMD_MASK; int target_nid; + int current_nid = -1; spin_lock(&mm->page_table_lock); if (unlikely(!pmd_same(pmd, *pmdp))) @@ -1034,6 +1035,10 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, page = pmd_page(pmd); get_page(page); spin_unlock(&mm->page_table_lock); + current_nid = page_to_nid(page); + count_vm_numa_event(NUMA_HINT_FAULTS); + if (current_nid == numa_node_id()) + count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); target_nid = mpol_misplaced(page, vma, haddr); if (target_nid == -1) diff --git a/mm/memory.c b/mm/memory.c index 8012c1907895..8a7b4ccbe136 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3477,6 +3477,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, set_pte_at(mm, addr, ptep, pte); update_mmu_cache(vma, addr, ptep); + count_vm_numa_event(NUMA_HINT_FAULTS); page = vm_normal_page(vma, addr, pte); if (!page) { pte_unmap_unlock(ptep, ptl); @@ -3485,6 +3486,8 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, get_page(page); current_nid = page_to_nid(page); + if (current_nid == numa_node_id()) + count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); target_nid = mpol_misplaced(page, vma, addr); pte_unmap_unlock(ptep, ptl); if (target_nid == -1) { @@ -3517,6 +3520,9 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long offset; spinlock_t *ptl; bool numa = false; + int local_nid = numa_node_id(); + unsigned long nr_faults = 0; + unsigned long nr_faults_local = 0; spin_lock(&mm->page_table_lock); pmd = *pmdp; @@ -3565,10 +3571,16 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, curr_nid = page_to_nid(page); task_numa_fault(curr_nid, 1); + nr_faults++; + if (curr_nid == local_nid) + nr_faults_local++; + pte = pte_offset_map_lock(mm, pmdp, addr, &ptl); } pte_unmap_unlock(orig_pte, ptl); + count_vm_numa_events(NUMA_HINT_FAULTS, nr_faults); + count_vm_numa_events(NUMA_HINT_FAULTS_LOCAL, nr_faults_local); return 0; } #else diff --git a/mm/mempolicy.c b/mm/mempolicy.c index a7a62fe7c280..516491fbfaa8 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -583,6 +583,8 @@ unsigned long change_prot_numa(struct vm_area_struct *vma, BUILD_BUG_ON(_PAGE_NUMA != _PAGE_PROTNONE); nr_updated = change_protection(vma, addr, end, vma->vm_page_prot, 0, 1); + if (nr_updated) + count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); return nr_updated; } diff --git a/mm/migrate.c b/mm/migrate.c index c7d550011a64..23bba5d6edff 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1514,7 +1514,8 @@ int migrate_misplaced_page(struct page *page, int node) if (nr_remaining) { putback_lru_pages(&migratepages); isolated = 0; - } + } else + count_vm_numa_event(NUMA_PAGE_MIGRATE); } BUG_ON(!list_empty(&migratepages)); out: diff --git a/mm/vmstat.c b/mm/vmstat.c index 3a067fabe190..c0f1f6db5182 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -774,6 +774,12 @@ const char * const vmstat_text[] = { "pgrotated", +#ifdef CONFIG_NUMA_BALANCING + "numa_pte_updates", + "numa_hint_faults", + "numa_hint_faults_local", + "numa_pages_migrated", +#endif #ifdef CONFIG_MIGRATION "pgmigrate_success", "pgmigrate_fail", -- cgit v1.2.3 From 9532fec118d485ea37ab6e3ea372d68cd8b4cd0d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 15 Nov 2012 01:24:32 +0000 Subject: mm: numa: Migrate pages handled during a pmd_numa hinting fault To say that the PMD handling code was incorrectly transferred from autonuma is an understatement. The intention was to handle a PMDs worth of pages in the same fault and effectively batch the taking of the PTL and page migration. The copied version instead has the impact of clearing a number of pte_numa PTE entries and whether any page migration takes place depends on racing. This just happens to work in some cases. This patch handles pte_numa faults in batch when a pmd_numa fault is handled. The pages are migrated if they are currently misplaced. Essentially this is making an assumption that NUMA locality is on a PMD boundary but that could be addressed by only setting pmd_numa if all the pages within that PMD are on the same node if necessary. Signed-off-by: Mel Gorman --- mm/memory.c | 51 ++++++++++++++++++++++++++++++++++----------------- mm/mprotect.c | 25 ++++++++++++++++++++----- 2 files changed, 54 insertions(+), 22 deletions(-) (limited to 'mm/memory.c') diff --git a/mm/memory.c b/mm/memory.c index 8a7b4ccbe136..84c6d9eab182 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3449,6 +3449,18 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); } +int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, + unsigned long addr, int current_nid) +{ + get_page(page); + + count_vm_numa_event(NUMA_HINT_FAULTS); + if (current_nid == numa_node_id()) + count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); + + return mpol_misplaced(page, vma, addr); +} + int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd) { @@ -3477,18 +3489,14 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, set_pte_at(mm, addr, ptep, pte); update_mmu_cache(vma, addr, ptep); - count_vm_numa_event(NUMA_HINT_FAULTS); page = vm_normal_page(vma, addr, pte); if (!page) { pte_unmap_unlock(ptep, ptl); return 0; } - get_page(page); current_nid = page_to_nid(page); - if (current_nid == numa_node_id()) - count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); - target_nid = mpol_misplaced(page, vma, addr); + target_nid = numa_migrate_prep(page, vma, addr, current_nid); pte_unmap_unlock(ptep, ptl); if (target_nid == -1) { /* @@ -3505,7 +3513,8 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, current_nid = target_nid; out: - task_numa_fault(current_nid, 1); + if (current_nid != -1) + task_numa_fault(current_nid, 1); return 0; } @@ -3521,8 +3530,6 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, spinlock_t *ptl; bool numa = false; int local_nid = numa_node_id(); - unsigned long nr_faults = 0; - unsigned long nr_faults_local = 0; spin_lock(&mm->page_table_lock); pmd = *pmdp; @@ -3545,7 +3552,8 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) { pte_t pteval = *pte; struct page *page; - int curr_nid; + int curr_nid = local_nid; + int target_nid; if (!pte_present(pteval)) continue; if (!pte_numa(pteval)) @@ -3566,21 +3574,30 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* only check non-shared pages */ if (unlikely(page_mapcount(page) != 1)) continue; - pte_unmap_unlock(pte, ptl); - curr_nid = page_to_nid(page); - task_numa_fault(curr_nid, 1); + /* + * Note that the NUMA fault is later accounted to either + * the node that is currently running or where the page is + * migrated to. + */ + curr_nid = local_nid; + target_nid = numa_migrate_prep(page, vma, addr, + page_to_nid(page)); + if (target_nid == -1) { + put_page(page); + continue; + } - nr_faults++; - if (curr_nid == local_nid) - nr_faults_local++; + /* Migrate to the requested node */ + pte_unmap_unlock(pte, ptl); + if (migrate_misplaced_page(page, target_nid)) + curr_nid = target_nid; + task_numa_fault(curr_nid, 1); pte = pte_offset_map_lock(mm, pmdp, addr, &ptl); } pte_unmap_unlock(orig_pte, ptl); - count_vm_numa_events(NUMA_HINT_FAULTS, nr_faults); - count_vm_numa_events(NUMA_HINT_FAULTS_LOCAL, nr_faults_local); return 0; } #else diff --git a/mm/mprotect.c b/mm/mprotect.c index 7ef6ae964e8f..dce6fb48edc4 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -37,12 +37,14 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t newprot, - int dirty_accountable, int prot_numa) + int dirty_accountable, int prot_numa, bool *ret_all_same_node) { struct mm_struct *mm = vma->vm_mm; pte_t *pte, oldpte; spinlock_t *ptl; unsigned long pages = 0; + bool all_same_node = true; + int last_nid = -1; pte = pte_offset_map_lock(mm, pmd, addr, &ptl); arch_enter_lazy_mmu_mode(); @@ -61,6 +63,12 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, page = vm_normal_page(vma, addr, oldpte); if (page) { + int this_nid = page_to_nid(page); + if (last_nid == -1) + last_nid = this_nid; + if (last_nid != this_nid) + all_same_node = false; + /* only check non-shared pages */ if (!pte_numa(oldpte) && page_mapcount(page) == 1) { @@ -81,7 +89,6 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, if (updated) pages++; - ptep_modify_prot_commit(mm, addr, pte, ptent); } else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) { swp_entry_t entry = pte_to_swp_entry(oldpte); @@ -101,6 +108,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); + *ret_all_same_node = all_same_node; return pages; } @@ -127,6 +135,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t * pmd_t *pmd; unsigned long next; unsigned long pages = 0; + bool all_same_node; pmd = pmd_offset(pud, addr); do { @@ -143,9 +152,15 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t * if (pmd_none_or_clear_bad(pmd)) continue; pages += change_pte_range(vma, pmd, addr, next, newprot, - dirty_accountable, prot_numa); - - if (prot_numa) + dirty_accountable, prot_numa, &all_same_node); + + /* + * If we are changing protections for NUMA hinting faults then + * set pmd_numa if the examined pages were all on the same + * node. This allows a regular PMD to be handled as one fault + * and effectively batches the taking of the PTL + */ + if (prot_numa && all_same_node) change_pmd_protnuma(vma->vm_mm, addr, pmd); } while (pmd++, addr = next, addr != end); -- cgit v1.2.3 From b8593bfda1652755136333cdd362de125b283a9c Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 21 Nov 2012 01:18:23 +0000 Subject: mm: sched: Adapt the scanning rate if a NUMA hinting fault does not migrate The PTE scanning rate and fault rates are two of the biggest sources of system CPU overhead with automatic NUMA placement. Ideally a proper policy would detect if a workload was properly placed, schedule and adjust the PTE scanning rate accordingly. We do not track the necessary information to do that but we at least know if we migrated or not. This patch scans slower if a page was not migrated as the result of a NUMA hinting fault up to sysctl_numa_balancing_scan_period_max which is now higher than the previous default. Once every minute it will reset the scanner in case of phase changes. This is hilariously crude and the numbers are arbitrary. Workloads will converge quite slowly in comparison to what a proper policy should be able to do. On the plus side, we will chew up less CPU for workloads that have no need for automatic balancing. Signed-off-by: Mel Gorman --- include/linux/mm_types.h | 3 +++ include/linux/sched.h | 5 +++-- kernel/sched/core.c | 1 + kernel/sched/fair.c | 29 +++++++++++++++++++++-------- kernel/sysctl.c | 7 +++++++ mm/huge_memory.c | 2 +- mm/memory.c | 12 ++++++++---- 7 files changed, 44 insertions(+), 15 deletions(-) (limited to 'mm/memory.c') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c5fffa239861..e850a23dd6ec 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -410,6 +410,9 @@ struct mm_struct { */ unsigned long numa_next_scan; + /* numa_next_reset is when the PTE scanner period will be reset */ + unsigned long numa_next_reset; + /* Restart point for scanning and setting pte_numa */ unsigned long numa_scan_offset; diff --git a/include/linux/sched.h b/include/linux/sched.h index 7d95a232b5b9..0f4ff2bd03f6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1562,9 +1562,9 @@ struct task_struct { #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) #ifdef CONFIG_NUMA_BALANCING -extern void task_numa_fault(int node, int pages); +extern void task_numa_fault(int node, int pages, bool migrated); #else -static inline void task_numa_fault(int node, int pages) +static inline void task_numa_fault(int node, int pages, bool migrated) { } #endif @@ -2009,6 +2009,7 @@ extern enum sched_tunable_scaling sysctl_sched_tunable_scaling; extern unsigned int sysctl_numa_balancing_scan_delay; extern unsigned int sysctl_numa_balancing_scan_period_min; extern unsigned int sysctl_numa_balancing_scan_period_max; +extern unsigned int sysctl_numa_balancing_scan_period_reset; extern unsigned int sysctl_numa_balancing_scan_size; extern unsigned int sysctl_numa_balancing_settle_count; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index fbfc4843063f..9d255bc0e278 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1537,6 +1537,7 @@ static void __sched_fork(struct task_struct *p) #ifdef CONFIG_NUMA_BALANCING if (p->mm && atomic_read(&p->mm->mm_users) == 1) { p->mm->numa_next_scan = jiffies; + p->mm->numa_next_reset = jiffies; p->mm->numa_scan_seq = 0; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index dd18087fd369..4b577863933f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -784,7 +784,8 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) * numa task sample period in ms */ unsigned int sysctl_numa_balancing_scan_period_min = 100; -unsigned int sysctl_numa_balancing_scan_period_max = 100*16; +unsigned int sysctl_numa_balancing_scan_period_max = 100*50; +unsigned int sysctl_numa_balancing_scan_period_reset = 100*600; /* Portion of address space to scan in MB */ unsigned int sysctl_numa_balancing_scan_size = 256; @@ -806,20 +807,19 @@ static void task_numa_placement(struct task_struct *p) /* * Got a PROT_NONE fault for a page on @node. */ -void task_numa_fault(int node, int pages) +void task_numa_fault(int node, int pages, bool migrated) { struct task_struct *p = current; /* FIXME: Allocate task-specific structure for placement policy here */ /* - * Assume that as faults occur that pages are getting properly placed - * and fewer NUMA hints are required. Note that this is a big - * assumption, it assumes processes reach a steady steady with no - * further phase changes. + * If pages are properly placed (did not migrate) then scan slower. + * This is reset periodically in case of phase changes */ - p->numa_scan_period = min(sysctl_numa_balancing_scan_period_max, - p->numa_scan_period + jiffies_to_msecs(2)); + if (!migrated) + p->numa_scan_period = min(sysctl_numa_balancing_scan_period_max, + p->numa_scan_period + jiffies_to_msecs(10)); task_numa_placement(p); } @@ -857,6 +857,19 @@ void task_numa_work(struct callback_head *work) if (p->flags & PF_EXITING) return; + /* + * Reset the scan period if enough time has gone by. Objective is that + * scanning will be reduced if pages are properly placed. As tasks + * can enter different phases this needs to be re-examined. Lacking + * proper tracking of reference behaviour, this blunt hammer is used. + */ + migrate = mm->numa_next_reset; + if (time_after(now, migrate)) { + p->numa_scan_period = sysctl_numa_balancing_scan_period_min; + next_scan = now + msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset); + xchg(&mm->numa_next_reset, next_scan); + } + /* * Enforce maximal scan/migration frequency.. */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 48a68cc258c1..8906f90d6fa2 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -366,6 +366,13 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "numa_balancing_scan_period_reset", + .data = &sysctl_numa_balancing_scan_period_reset, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { .procname = "numa_balancing_scan_period_max_ms", .data = &sysctl_numa_balancing_scan_period_max, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 79b96064f8fc..199b261a257e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1068,7 +1068,7 @@ out_unlock: spin_unlock(&mm->page_table_lock); if (page) { put_page(page); - task_numa_fault(numa_node_id(), HPAGE_PMD_NR); + task_numa_fault(numa_node_id(), HPAGE_PMD_NR, false); } return 0; } diff --git a/mm/memory.c b/mm/memory.c index 84c6d9eab182..39edb11b63dc 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3468,6 +3468,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, spinlock_t *ptl; int current_nid = -1; int target_nid; + bool migrated = false; /* * The "pte" at this point cannot be used safely without @@ -3509,12 +3510,13 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, } /* Migrate to the requested node */ - if (migrate_misplaced_page(page, target_nid)) + migrated = migrate_misplaced_page(page, target_nid); + if (migrated) current_nid = target_nid; out: if (current_nid != -1) - task_numa_fault(current_nid, 1); + task_numa_fault(current_nid, 1, migrated); return 0; } @@ -3554,6 +3556,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page; int curr_nid = local_nid; int target_nid; + bool migrated; if (!pte_present(pteval)) continue; if (!pte_numa(pteval)) @@ -3590,9 +3593,10 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Migrate to the requested node */ pte_unmap_unlock(pte, ptl); - if (migrate_misplaced_page(page, target_nid)) + migrated = migrate_misplaced_page(page, target_nid); + if (migrated) curr_nid = target_nid; - task_numa_fault(curr_nid, 1); + task_numa_fault(curr_nid, 1, migrated); pte = pte_offset_map_lock(mm, pmdp, addr, &ptl); } -- cgit v1.2.3