diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-16 11:51:08 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-16 11:51:08 -0700 |
commit | 271ecc5253e2b317d729d366560789cd7f93836c (patch) | |
tree | d3a60bc4dfa8245ff934f357f2367db76b59e7cf /mm | |
parent | aa6865d836418eb2ba888a4cb1318a28e9aa2e0c (diff) | |
parent | 63c06227a22b098a3849c5c99e836aea161ca0d7 (diff) |
Merge branch 'akpm' (patches from Andrew)
Merge first patch-bomb from Andrew Morton:
- some misc things
- ofs2 updates
- about half of MM
- checkpatch updates
- autofs4 update
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (120 commits)
autofs4: fix string.h include in auto_dev-ioctl.h
autofs4: use pr_xxx() macros directly for logging
autofs4: change log print macros to not insert newline
autofs4: make autofs log prints consistent
autofs4: fix some white space errors
autofs4: fix invalid ioctl return in autofs4_root_ioctl_unlocked()
autofs4: fix coding style line length in autofs4_wait()
autofs4: fix coding style problem in autofs4_get_set_timeout()
autofs4: coding style fixes
autofs: show pipe inode in mount options
kallsyms: add support for relative offsets in kallsyms address table
kallsyms: don't overload absolute symbol type for percpu symbols
x86: kallsyms: disable absolute percpu symbols on !SMP
checkpatch: fix another left brace warning
checkpatch: improve UNSPECIFIED_INT test for bare signed/unsigned uses
checkpatch: warn on bare unsigned or signed declarations without int
checkpatch: exclude asm volatile from complex macro check
mm: memcontrol: drop unnecessary lru locking from mem_cgroup_migrate()
mm: migrate: consolidate mem_cgroup_migrate() calls
mm/compaction: speed up pageblock_pfn_to_page() when zone is contiguous
...
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig.debug | 57 | ||||
-rw-r--r-- | mm/Makefile | 2 | ||||
-rw-r--r-- | mm/compaction.c | 93 | ||||
-rw-r--r-- | mm/debug.c | 165 | ||||
-rw-r--r-- | mm/failslab.c | 12 | ||||
-rw-r--r-- | mm/filemap.c | 113 | ||||
-rw-r--r-- | mm/huge_memory.c | 20 | ||||
-rw-r--r-- | mm/internal.h | 18 | ||||
-rw-r--r-- | mm/kmemcheck.c | 3 | ||||
-rw-r--r-- | mm/madvise.c | 19 | ||||
-rw-r--r-- | mm/memblock.c | 8 | ||||
-rw-r--r-- | mm/memcontrol.c | 92 | ||||
-rw-r--r-- | mm/memory-failure.c | 2 | ||||
-rw-r--r-- | mm/memory.c | 7 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 30 | ||||
-rw-r--r-- | mm/mempolicy.c | 4 | ||||
-rw-r--r-- | mm/migrate.c | 23 | ||||
-rw-r--r-- | mm/oom_kill.c | 7 | ||||
-rw-r--r-- | mm/page-writeback.c | 62 | ||||
-rw-r--r-- | mm/page_alloc.c | 295 | ||||
-rw-r--r-- | mm/page_ext.c | 10 | ||||
-rw-r--r-- | mm/page_owner.c | 100 | ||||
-rw-r--r-- | mm/page_poison.c (renamed from mm/debug-pagealloc.c) | 67 | ||||
-rw-r--r-- | mm/rmap.c | 16 | ||||
-rw-r--r-- | mm/shmem.c | 2 | ||||
-rw-r--r-- | mm/slab.c | 1037 | ||||
-rw-r--r-- | mm/slab.h | 69 | ||||
-rw-r--r-- | mm/slab_common.c | 8 | ||||
-rw-r--r-- | mm/slub.c | 325 | ||||
-rw-r--r-- | mm/truncate.c | 6 | ||||
-rw-r--r-- | mm/vmscan.c | 47 | ||||
-rw-r--r-- | mm/vmstat.c | 15 | ||||
-rw-r--r-- | mm/workingset.c | 160 |
33 files changed, 1707 insertions, 1187 deletions
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index 957d3da53ddd..5c50b238b770 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -16,8 +16,8 @@ config DEBUG_PAGEALLOC select PAGE_POISONING if !ARCH_SUPPORTS_DEBUG_PAGEALLOC ---help--- Unmap pages from the kernel linear mapping after free_pages(). - This results in a large slowdown, but helps to find certain types - of memory corruption. + Depending on runtime enablement, this results in a small or large + slowdown, but helps to find certain types of memory corruption. For architectures which don't enable ARCH_SUPPORTS_DEBUG_PAGEALLOC, fill the pages with poison patterns after free_pages() and verify @@ -26,5 +26,56 @@ config DEBUG_PAGEALLOC that would result in incorrect warnings of memory corruption after a resume because free pages are not saved to the suspend image. + By default this option will have a small overhead, e.g. by not + allowing the kernel mapping to be backed by large pages on some + architectures. Even bigger overhead comes when the debugging is + enabled by DEBUG_PAGEALLOC_ENABLE_DEFAULT or the debug_pagealloc + command line parameter. + +config DEBUG_PAGEALLOC_ENABLE_DEFAULT + bool "Enable debug page memory allocations by default?" + default n + depends on DEBUG_PAGEALLOC + ---help--- + Enable debug page memory allocations by default? This value + can be overridden by debug_pagealloc=off|on. + config PAGE_POISONING - bool + bool "Poison pages after freeing" + select PAGE_EXTENSION + select PAGE_POISONING_NO_SANITY if HIBERNATION + ---help--- + Fill the pages with poison patterns after free_pages() and verify + the patterns before alloc_pages. The filling of the memory helps + reduce the risk of information leaks from freed data. This does + have a potential performance impact. + + Note that "poison" here is not the same thing as the "HWPoison" + for CONFIG_MEMORY_FAILURE. This is software poisoning only. + + If unsure, say N + +config PAGE_POISONING_NO_SANITY + depends on PAGE_POISONING + bool "Only poison, don't sanity check" + ---help--- + Skip the sanity checking on alloc, only fill the pages with + poison on free. This reduces some of the overhead of the + poisoning feature. + + If you are only interested in sanitization, say Y. Otherwise + say N. + +config PAGE_POISONING_ZERO + bool "Use zero for poisoning instead of random data" + depends on PAGE_POISONING + ---help--- + Instead of using the existing poison value, fill the pages with + zeros. This makes it harder to detect when errors are occurring + due to sanitization but the zeroing at free means that it is + no longer necessary to write zeros when GFP_ZERO is used on + allocation. + + Enabling page poisoning with this option will disable hibernation + + If unsure, say N diff --git a/mm/Makefile b/mm/Makefile index 2ed43191fc3b..cfdd481d27a5 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -48,7 +48,7 @@ obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o obj-$(CONFIG_SLOB) += slob.o obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o obj-$(CONFIG_KSM) += ksm.o -obj-$(CONFIG_PAGE_POISONING) += debug-pagealloc.o +obj-$(CONFIG_PAGE_POISONING) += page_poison.o obj-$(CONFIG_SLAB) += slab.o obj-$(CONFIG_SLUB) += slub.o obj-$(CONFIG_KMEMCHECK) += kmemcheck.o diff --git a/mm/compaction.c b/mm/compaction.c index 585de54dbe8c..93f71d968098 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -71,49 +71,6 @@ static inline bool migrate_async_suitable(int migratetype) return is_migrate_cma(migratetype) || migratetype == MIGRATE_MOVABLE; } -/* - * Check that the whole (or subset of) a pageblock given by the interval of - * [start_pfn, end_pfn) is valid and within the same zone, before scanning it - * with the migration of free compaction scanner. The scanners then need to - * use only pfn_valid_within() check for arches that allow holes within - * pageblocks. - * - * Return struct page pointer of start_pfn, or NULL if checks were not passed. - * - * It's possible on some configurations to have a setup like node0 node1 node0 - * i.e. it's possible that all pages within a zones range of pages do not - * belong to a single zone. We assume that a border between node0 and node1 - * can occur within a single pageblock, but not a node0 node1 node0 - * interleaving within a single pageblock. It is therefore sufficient to check - * the first and last page of a pageblock and avoid checking each individual - * page in a pageblock. - */ -static struct page *pageblock_pfn_to_page(unsigned long start_pfn, - unsigned long end_pfn, struct zone *zone) -{ - struct page *start_page; - struct page *end_page; - - /* end_pfn is one past the range we are checking */ - end_pfn--; - - if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn)) - return NULL; - - start_page = pfn_to_page(start_pfn); - - if (page_zone(start_page) != zone) - return NULL; - - end_page = pfn_to_page(end_pfn); - - /* This gives a shorter code than deriving page_zone(end_page) */ - if (page_zone_id(start_page) != page_zone_id(end_page)) - return NULL; - - return start_page; -} - #ifdef CONFIG_COMPACTION /* Do not skip compaction more than 64 times */ @@ -200,7 +157,8 @@ static void reset_cached_positions(struct zone *zone) { zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn; zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn; - zone->compact_cached_free_pfn = zone_end_pfn(zone); + zone->compact_cached_free_pfn = + round_down(zone_end_pfn(zone) - 1, pageblock_nr_pages); } /* @@ -554,13 +512,17 @@ unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn) { - unsigned long isolated, pfn, block_end_pfn; + unsigned long isolated, pfn, block_start_pfn, block_end_pfn; LIST_HEAD(freelist); pfn = start_pfn; + block_start_pfn = pfn & ~(pageblock_nr_pages - 1); + if (block_start_pfn < cc->zone->zone_start_pfn) + block_start_pfn = cc->zone->zone_start_pfn; block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); for (; pfn < end_pfn; pfn += isolated, + block_start_pfn = block_end_pfn, block_end_pfn += pageblock_nr_pages) { /* Protect pfn from changing by isolate_freepages_block */ unsigned long isolate_start_pfn = pfn; @@ -573,11 +535,13 @@ isolate_freepages_range(struct compact_control *cc, * scanning range to right one. */ if (pfn >= block_end_pfn) { + block_start_pfn = pfn & ~(pageblock_nr_pages - 1); block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); block_end_pfn = min(block_end_pfn, end_pfn); } - if (!pageblock_pfn_to_page(pfn, block_end_pfn, cc->zone)) + if (!pageblock_pfn_to_page(block_start_pfn, + block_end_pfn, cc->zone)) break; isolated = isolate_freepages_block(cc, &isolate_start_pfn, @@ -863,18 +827,23 @@ unsigned long isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn) { - unsigned long pfn, block_end_pfn; + unsigned long pfn, block_start_pfn, block_end_pfn; /* Scan block by block. First and last block may be incomplete */ pfn = start_pfn; + block_start_pfn = pfn & ~(pageblock_nr_pages - 1); + if (block_start_pfn < cc->zone->zone_start_pfn) + block_start_pfn = cc->zone->zone_start_pfn; block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); for (; pfn < end_pfn; pfn = block_end_pfn, + block_start_pfn = block_end_pfn, block_end_pfn += pageblock_nr_pages) { block_end_pfn = min(block_end_pfn, end_pfn); - if (!pageblock_pfn_to_page(pfn, block_end_pfn, cc->zone)) + if (!pageblock_pfn_to_page(block_start_pfn, + block_end_pfn, cc->zone)) continue; pfn = isolate_migratepages_block(cc, pfn, block_end_pfn, @@ -1103,7 +1072,9 @@ int sysctl_compact_unevictable_allowed __read_mostly = 1; static isolate_migrate_t isolate_migratepages(struct zone *zone, struct compact_control *cc) { - unsigned long low_pfn, end_pfn; + unsigned long block_start_pfn; + unsigned long block_end_pfn; + unsigned long low_pfn; unsigned long isolate_start_pfn; struct page *page; const isolate_mode_t isolate_mode = @@ -1115,16 +1086,21 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, * initialized by compact_zone() */ low_pfn = cc->migrate_pfn; + block_start_pfn = cc->migrate_pfn & ~(pageblock_nr_pages - 1); + if (block_start_pfn < zone->zone_start_pfn) + block_start_pfn = zone->zone_start_pfn; /* Only scan within a pageblock boundary */ - end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages); + block_end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages); /* * Iterate over whole pageblocks until we find the first suitable. * Do not cross the free scanner. */ - for (; end_pfn <= cc->free_pfn; - low_pfn = end_pfn, end_pfn += pageblock_nr_pages) { + for (; block_end_pfn <= cc->free_pfn; + low_pfn = block_end_pfn, + block_start_pfn = block_end_pfn, + block_end_pfn += pageblock_nr_pages) { /* * This can potentially iterate a massively long zone with @@ -1135,7 +1111,8 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, && compact_should_abort(cc)) break; - page = pageblock_pfn_to_page(low_pfn, end_pfn, zone); + page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn, + zone); if (!page) continue; @@ -1154,8 +1131,8 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, /* Perform the isolation */ isolate_start_pfn = low_pfn; - low_pfn = isolate_migratepages_block(cc, low_pfn, end_pfn, - isolate_mode); + low_pfn = isolate_migratepages_block(cc, low_pfn, + block_end_pfn, isolate_mode); if (!low_pfn || cc->contended) { acct_isolated(zone, cc); @@ -1371,11 +1348,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) */ cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync]; cc->free_pfn = zone->compact_cached_free_pfn; - if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) { - cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1); + if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) { + cc->free_pfn = round_down(end_pfn - 1, pageblock_nr_pages); zone->compact_cached_free_pfn = cc->free_pfn; } - if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) { + if (cc->migrate_pfn < start_pfn || cc->migrate_pfn >= end_pfn) { cc->migrate_pfn = start_pfn; zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn; zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; diff --git a/mm/debug.c b/mm/debug.c index f05b2d5d6481..df7247b0b532 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -9,75 +9,38 @@ #include <linux/mm.h> #include <linux/trace_events.h> #include <linux/memcontrol.h> - -static const struct trace_print_flags pageflag_names[] = { - {1UL << PG_locked, "locked" }, - {1UL << PG_error, "error" }, - {1UL << PG_referenced, "referenced" }, - {1UL << PG_uptodate, "uptodate" }, - {1UL << PG_dirty, "dirty" }, - {1UL << PG_lru, "lru" }, - {1UL << PG_active, "active" }, - {1UL << PG_slab, "slab" }, - {1UL << PG_owner_priv_1, "owner_priv_1" }, - {1UL << PG_arch_1, "arch_1" }, - {1UL << PG_reserved, "reserved" }, - {1UL << PG_private, "private" }, - {1UL << PG_private_2, "private_2" }, - {1UL << PG_writeback, "writeback" }, - {1UL << PG_head, "head" }, - {1UL << PG_swapcache, "swapcache" }, - {1UL << PG_mappedtodisk, "mappedtodisk" }, - {1UL << PG_reclaim, "reclaim" }, - {1UL << PG_swapbacked, "swapbacked" }, - {1UL << PG_unevictable, "unevictable" }, -#ifdef CONFIG_MMU - {1UL << PG_mlocked, "mlocked" }, -#endif -#ifdef CONFIG_ARCH_USES_PG_UNCACHED - {1UL << PG_uncached, "uncached" }, -#endif -#ifdef CONFIG_MEMORY_FAILURE - {1UL << PG_hwpoison, "hwpoison" }, -#endif -#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) - {1UL << PG_young, "young" }, - {1UL << PG_idle, "idle" }, -#endif +#include <trace/events/mmflags.h> +#include <linux/migrate.h> +#include <linux/page_owner.h> + +#include "internal.h" + +char *migrate_reason_names[MR_TYPES] = { + "compaction", + "memory_failure", + "memory_hotplug", + "syscall_or_cpuset", + "mempolicy_mbind", + "numa_misplaced", + "cma", }; -static void dump_flags(unsigned long flags, - const struct trace_print_flags *names, int count) -{ - const char *delim = ""; - unsigned long mask; - int i; - - pr_emerg("flags: %#lx(", flags); - - /* remove zone id */ - flags &= (1UL << NR_PAGEFLAGS) - 1; - - for (i = 0; i < count && flags; i++) { - - mask = names[i].mask; - if ((flags & mask) != mask) - continue; - - flags &= ~mask; - pr_cont("%s%s", delim, names[i].name); - delim = "|"; - } +const struct trace_print_flags pageflag_names[] = { + __def_pageflag_names, + {0, NULL} +}; - /* check for left over flags */ - if (flags) - pr_cont("%s%#lx", delim, flags); +const struct trace_print_flags gfpflag_names[] = { + __def_gfpflag_names, + {0, NULL} +}; - pr_cont(")\n"); -} +const struct trace_print_flags vmaflag_names[] = { + __def_vmaflag_names, + {0, NULL} +}; -void dump_page_badflags(struct page *page, const char *reason, - unsigned long badflags) +void __dump_page(struct page *page, const char *reason) { pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx", page, atomic_read(&page->_count), page_mapcount(page), @@ -85,15 +48,13 @@ void dump_page_badflags(struct page *page, const char *reason, if (PageCompound(page)) pr_cont(" compound_mapcount: %d", compound_mapcount(page)); pr_cont("\n"); - BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS); - dump_flags(page->flags, pageflag_names, ARRAY_SIZE(pageflag_names)); + BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1); + + pr_emerg("flags: %#lx(%pGp)\n", page->flags, &page->flags); + if (reason) pr_alert("page dumped because: %s\n", reason); - if (page->flags & badflags) { - pr_alert("bad because of flags:\n"); - dump_flags(page->flags & badflags, - pageflag_names, ARRAY_SIZE(pageflag_names)); - } + #ifdef CONFIG_MEMCG if (page->mem_cgroup) pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup); @@ -102,67 +63,26 @@ void dump_page_badflags(struct page *page, const char *reason, void dump_page(struct page *page, const char *reason) { - dump_page_badflags(page, reason, 0); + __dump_page(page, reason); + dump_page_owner(page); } EXPORT_SYMBOL(dump_page); #ifdef CONFIG_DEBUG_VM -static const struct trace_print_flags vmaflags_names[] = { - {VM_READ, "read" }, - {VM_WRITE, "write" }, - {VM_EXEC, "exec" }, - {VM_SHARED, "shared" }, - {VM_MAYREAD, "mayread" }, - {VM_MAYWRITE, "maywrite" }, - {VM_MAYEXEC, "mayexec" }, - {VM_MAYSHARE, "mayshare" }, - {VM_GROWSDOWN, "growsdown" }, - {VM_PFNMAP, "pfnmap" }, - {VM_DENYWRITE, "denywrite" }, - {VM_LOCKONFAULT, "lockonfault" }, - {VM_LOCKED, "locked" }, - {VM_IO, "io" }, - {VM_SEQ_READ, "seqread" }, - {VM_RAND_READ, "randread" }, - {VM_DONTCOPY, "dontcopy" }, - {VM_DONTEXPAND, "dontexpand" }, - {VM_ACCOUNT, "account" }, - {VM_NORESERVE, "noreserve" }, - {VM_HUGETLB, "hugetlb" }, -#if defined(CONFIG_X86) - {VM_PAT, "pat" }, -#elif defined(CONFIG_PPC) - {VM_SAO, "sao" }, -#elif defined(CONFIG_PARISC) || defined(CONFIG_METAG) || defined(CONFIG_IA64) - {VM_GROWSUP, "growsup" }, -#elif !defined(CONFIG_MMU) - {VM_MAPPED_COPY, "mappedcopy" }, -#else - {VM_ARCH_1, "arch_1" }, -#endif - {VM_DONTDUMP, "dontdump" }, -#ifdef CONFIG_MEM_SOFT_DIRTY - {VM_SOFTDIRTY, "softdirty" }, -#endif - {VM_MIXEDMAP, "mixedmap" }, - {VM_HUGEPAGE, "hugepage" }, - {VM_NOHUGEPAGE, "nohugepage" }, - {VM_MERGEABLE, "mergeable" }, -}; - void dump_vma(const struct vm_area_struct *vma) { pr_emerg("vma %p start %p end %p\n" "next %p prev %p mm %p\n" "prot %lx anon_vma %p vm_ops %p\n" - "pgoff %lx file %p private_data %p\n", + "pgoff %lx file %p private_data %p\n" + "flags: %#lx(%pGv)\n", vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next, vma->vm_prev, vma->vm_mm, (unsigned long)pgprot_val(vma->vm_page_prot), vma->anon_vma, vma->vm_ops, vma->vm_pgoff, - vma->vm_file, vma->vm_private_data); - dump_flags(vma->vm_flags, vmaflags_names, ARRAY_SIZE(vmaflags_names)); + vma->vm_file, vma->vm_private_data, + vma->vm_flags, &vma->vm_flags); } EXPORT_SYMBOL(dump_vma); @@ -196,7 +116,7 @@ void dump_mm(const struct mm_struct *mm) #if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) "tlb_flush_pending %d\n" #endif - "%s", /* This is here to hold the comma */ + "def_flags: %#lx(%pGv)\n", mm, mm->mmap, mm->vmacache_seqnum, mm->task_size, #ifdef CONFIG_MMU @@ -230,11 +150,8 @@ void dump_mm(const struct mm_struct *mm) #if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) mm->tlb_flush_pending, #endif - "" /* This is here to not have a comma! */ - ); - - dump_flags(mm->def_flags, vmaflags_names, - ARRAY_SIZE(vmaflags_names)); + mm->def_flags, &mm->def_flags + ); } #endif /* CONFIG_DEBUG_VM */ diff --git a/mm/failslab.c b/mm/failslab.c index 79171b4a5826..b0fac98cd938 100644 --- a/mm/failslab.c +++ b/mm/failslab.c @@ -1,5 +1,7 @@ #include <linux/fault-inject.h> #include <linux/slab.h> +#include <linux/mm.h> +#include "slab.h" static struct { struct fault_attr attr; @@ -11,18 +13,22 @@ static struct { .cache_filter = false, }; -bool should_failslab(size_t size, gfp_t gfpflags, unsigned long cache_flags) +bool should_failslab(struct kmem_cache *s, gfp_t gfpflags) { + /* No fault-injection for bootstrap cache */ + if (unlikely(s == kmem_cache)) + return false; + if (gfpflags & __GFP_NOFAIL) return false; if (failslab.ignore_gfp_reclaim && (gfpflags & __GFP_RECLAIM)) return false; - if (failslab.cache_filter && !(cache_flags & SLAB_FAILSLAB)) + if (failslab.cache_filter && !(s->flags & SLAB_FAILSLAB)) return false; - return should_fail(&failslab.attr, size); + return should_fail(&failslab.attr, s->object_size); } static int __init setup_failslab(char *str) diff --git a/mm/filemap.c b/mm/filemap.c index da7a35d83de7..61b441b191ad 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -101,7 +101,7 @@ * ->tree_lock (page_remove_rmap->set_page_dirty) * bdi.wb->list_lock (page_remove_rmap->set_page_dirty) * ->inode->i_lock (page_remove_rmap->set_page_dirty) - * ->memcg->move_lock (page_remove_rmap->mem_cgroup_begin_page_stat) + * ->memcg->move_lock (page_remove_rmap->lock_page_memcg) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->__set_page_dirty_buffers) @@ -176,11 +176,9 @@ static void page_cache_tree_delete(struct address_space *mapping, /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage - * is safe. The caller must hold the mapping's tree_lock and - * mem_cgroup_begin_page_stat(). + * is safe. The caller must hold the mapping's tree_lock. */ -void __delete_from_page_cache(struct page *page, void *shadow, - struct mem_cgroup *memcg) +void __delete_from_page_cache(struct page *page, void *shadow) { struct address_space *mapping = page->mapping; @@ -239,8 +237,7 @@ void __delete_from_page_cache(struct page *page, void *shadow, * anyway will be cleared before returning page into buddy allocator. */ if (WARN_ON_ONCE(PageDirty(page))) - account_page_cleaned(page, mapping, memcg, - inode_to_wb(mapping->host)); + account_page_cleaned(page, mapping, inode_to_wb(mapping->host)); } /** @@ -254,7 +251,6 @@ void __delete_from_page_cache(struct page *page, void *shadow, void delete_from_page_cache(struct page *page) { struct address_space *mapping = page->mapping; - struct mem_cgroup *memcg; unsigned long flags; void (*freepage)(struct page *); @@ -263,11 +259,9 @@ void delete_from_page_cache(struct page *page) freepage = mapping->a_ops->freepage; - memcg = mem_cgroup_begin_page_stat(page); spin_lock_irqsave(&mapping->tree_lock, flags); - __delete_from_page_cache(page, NULL, memcg); + __delete_from_page_cache(page, NULL); spin_unlock_irqrestore(&mapping->tree_lock, flags); - mem_cgroup_end_page_stat(memcg); if (freepage) freepage(page); @@ -551,7 +545,6 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) if (!error) { struct address_space *mapping = old->mapping; void (*freepage)(struct page *); - struct mem_cgroup *memcg; unsigned long flags; pgoff_t offset = old->index; @@ -561,9 +554,8 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) new->mapping = mapping; new->index = offset; - memcg = mem_cgroup_begin_page_stat(old); spin_lock_irqsave(&mapping->tree_lock, flags); - __delete_from_page_cache(old, NULL, memcg); + __delete_from_page_cache(old, NULL); error = radix_tree_insert(&mapping->page_tree, offset, new); BUG_ON(error); mapping->nrpages++; @@ -576,8 +568,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) if (PageSwapBacked(new)) __inc_zone_page_state(new, NR_SHMEM); spin_unlock_irqrestore(&mapping->tree_lock, flags); - mem_cgroup_end_page_stat(memcg); - mem_cgroup_replace_page(old, new); + mem_cgroup_migrate(old, new); radix_tree_preload_end(); if (freepage) freepage(old); @@ -1668,6 +1659,15 @@ find_page: index, last_index - index); } if (!PageUptodate(page)) { + /* + * See comment in do_read_cache_page on why + * wait_on_page_locked is used to avoid unnecessarily + * serialisations and why it's safe. + */ + wait_on_page_locked_killable(page); + if (PageUptodate(page)) + goto page_ok; + if (inode->i_blkbits == PAGE_CACHE_SHIFT || !mapping->a_ops->is_partially_uptodate) goto page_not_up_to_date; @@ -2303,7 +2303,7 @@ static struct page *wait_on_page_read(struct page *page) return page; } -static struct page *__read_cache_page(struct address_space *mapping, +static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data, @@ -2325,53 +2325,74 @@ repeat: /* Presumably ENOMEM for radix tree node */ return ERR_PTR(err); } + +filler: err = filler(data, page); if (err < 0) { page_cache_release(page); - page = ERR_PTR(err); - } else { - page = wait_on_page_read(page); + return ERR_PTR(err); } - } - return page; -} - -static struct page *do_read_cache_page(struct address_space *mapping, - pgoff_t index, - int (*filler)(void *, struct page *), - void *data, - gfp_t gfp) -{ - struct page *page; - int err; + page = wait_on_page_read(page); + if (IS_ERR(page)) + return page; + goto out; + } + if (PageUptodate(page)) + goto out; -retry: - page = __read_cache_page(mapping, index, filler, data, gfp); - if (IS_ERR(page)) - return page; + /* + * Page is not up to date and may be locked due one of the following + * case a: Page is being filled and the page lock is held + * case b: Read/write error clearing the page uptodate status + * case c: Truncation in progress (page locked) + * case d: Reclaim in progress + * + * Case a, the page will be up to date when the page is unlocked. + * There is no need to serialise on the page lock here as the page + * is pinned so the lock gives no additional protection. Even if the + * the page is truncated, the data is still valid if PageUptodate as + * it's a race vs truncate race. + * Case b, the page will not be up to date + * Case c, the page may be truncated but in itself, the data may still + * be valid after IO completes as it's a read vs truncate race. The + * operation must restart if the page is not uptodate on unlock but + * otherwise serialising on page lock to stabilise the mapping gives + * no additional guarantees to the caller as the page lock is + * released before return. + * Case d, similar to truncation. If reclaim holds the page lock, it + * will be a race with remove_mapping that determines if the mapping + * is valid on unlock but otherwise the data is valid and there is + * no need to serialise with page lock. + * + * As the page lock gives no additional guarantee, we optimistically + * wait on the page to be unlocked and check if it's up to date and + * use the page if it is. Otherwise, the page lock is required to + * distinguish between the different cases. The motivation is that we + * avoid spurious serialisations and wakeups when multiple processes + * wait on the same page for IO to complete. + */ + wait_on_page_locked(page); if (PageUptodate(page)) goto out; + /* Distinguish between all the cases under the safety of the lock */ lock_page(page); + + /* Case c or d, restart the operation */ if (!page->mapping) { unlock_page(page); page_cache_release(page); - goto retry; + goto repeat; } + + /* Someone else locked and filled the page in a very small window */ if (PageUptodate(page)) { unlock_page(page); goto out; } - err = filler(data, page); - if (err < 0) { - page_cache_release(page); - return ERR_PTR(err); - } else { - page = wait_on_page_read(page); - if (IS_ERR(page)) - return page; - } + goto filler; + out: mark_page_accessed(page); return page; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e10a4fee88d2..1ea21e203a70 100644 --- a/mm/huge_memory.c +++ b/ |