diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 40 | ||||
| -rw-r--r-- | mm/Makefile | 3 | ||||
| -rw-r--r-- | mm/compaction.c | 185 | ||||
| -rw-r--r-- | mm/dmapool.c | 16 | ||||
| -rw-r--r-- | mm/filemap.c | 20 | ||||
| -rw-r--r-- | mm/huge_memory.c | 2351 | ||||
| -rw-r--r-- | mm/hugetlb.c | 111 | ||||
| -rw-r--r-- | mm/internal.h | 7 | ||||
| -rw-r--r-- | mm/kmemleak-test.c | 6 | ||||
| -rw-r--r-- | mm/kmemleak.c | 13 | ||||
| -rw-r--r-- | mm/ksm.c | 81 | ||||
| -rw-r--r-- | mm/madvise.c | 10 | ||||
| -rw-r--r-- | mm/memblock.c | 10 | ||||
| -rw-r--r-- | mm/memcontrol.c | 428 | ||||
| -rw-r--r-- | mm/memory-failure.c | 110 | ||||
| -rw-r--r-- | mm/memory.c | 360 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 21 | ||||
| -rw-r--r-- | mm/mempolicy.c | 23 | ||||
| -rw-r--r-- | mm/migrate.c | 132 | ||||
| -rw-r--r-- | mm/mincore.c | 7 | ||||
| -rw-r--r-- | mm/mlock.c | 170 | ||||
| -rw-r--r-- | mm/mmap.c | 17 | ||||
| -rw-r--r-- | mm/mmu_notifier.c | 20 | ||||
| -rw-r--r-- | mm/mmzone.c | 21 | ||||
| -rw-r--r-- | mm/mprotect.c | 20 | ||||
| -rw-r--r-- | mm/mremap.c | 9 | ||||
| -rw-r--r-- | mm/nommu.c | 6 | ||||
| -rw-r--r-- | mm/page-writeback.c | 9 | ||||
| -rw-r--r-- | mm/page_alloc.c | 183 | ||||
| -rw-r--r-- | mm/pagewalk.c | 1 | ||||
| -rw-r--r-- | mm/percpu-vm.c | 2 | ||||
| -rw-r--r-- | mm/percpu.c | 10 | ||||
| -rw-r--r-- | mm/pgtable-generic.c | 121 | ||||
| -rw-r--r-- | mm/rmap.c | 93 | ||||
| -rw-r--r-- | mm/shmem.c | 9 | ||||
| -rw-r--r-- | mm/slab.c | 82 | ||||
| -rw-r--r-- | mm/slob.c | 5 | ||||
| -rw-r--r-- | mm/slub.c | 85 | ||||
| -rw-r--r-- | mm/sparse-vmemmap.c | 2 | ||||
| -rw-r--r-- | mm/sparse.c | 4 | ||||
| -rw-r--r-- | mm/swap.c | 131 | ||||
| -rw-r--r-- | mm/swap_state.c | 6 | ||||
| -rw-r--r-- | mm/swapfile.c | 9 | ||||
| -rw-r--r-- | mm/truncate.c | 11 | ||||
| -rw-r--r-- | mm/util.c | 21 | ||||
| -rw-r--r-- | mm/vmalloc.c | 90 | ||||
| -rw-r--r-- | mm/vmscan.c | 428 | ||||
| -rw-r--r-- | mm/vmstat.c | 202 |
48 files changed, 4632 insertions, 1069 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index c2c8a4a1189..e9c0c61f2dd 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -179,7 +179,7 @@ config SPLIT_PTLOCK_CPUS config COMPACTION bool "Allow for memory compaction" select MIGRATION - depends on EXPERIMENTAL && HUGETLB_PAGE && MMU + depends on MMU help Allows the compaction of memory for the allocation of huge pages. @@ -302,6 +302,44 @@ config NOMMU_INITIAL_TRIM_EXCESS See Documentation/nommu-mmap.txt for more information. +config TRANSPARENT_HUGEPAGE + bool "Transparent Hugepage Support" + depends on X86 && MMU + select COMPACTION + help + Transparent Hugepages allows the kernel to use huge pages and + huge tlb transparently to the applications whenever possible. + This feature can improve computing performance to certain + applications by speeding up page faults during memory + allocation, by reducing the number of tlb misses and by speeding + up the pagetable walking. + + If memory constrained on embedded, you may want to say N. + +choice + prompt "Transparent Hugepage Support sysfs defaults" + depends on TRANSPARENT_HUGEPAGE + default TRANSPARENT_HUGEPAGE_ALWAYS + help + Selects the sysfs defaults for Transparent Hugepage Support. + + config TRANSPARENT_HUGEPAGE_ALWAYS + bool "always" + help + Enabling Transparent Hugepage always, can increase the + memory footprint of applications without a guaranteed + benefit but it will work automatically for all applications. + + config TRANSPARENT_HUGEPAGE_MADVISE + bool "madvise" + help + Enabling Transparent Hugepage madvise, will only provide a + performance improvement benefit to the applications using + madvise(MADV_HUGEPAGE) but it won't risk to increase the + memory footprint of applications without a guaranteed + benefit. +endchoice + # # UP and nommu archs use km based percpu allocator # diff --git a/mm/Makefile b/mm/Makefile index f73f75a29f8..2b1b575ae71 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -5,7 +5,7 @@ mmu-y := nommu.o mmu-$(CONFIG_MMU) := fremap.o highmem.o madvise.o memory.o mincore.o \ mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \ - vmalloc.o pagewalk.o + vmalloc.o pagewalk.o pgtable-generic.o obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page_alloc.o page-writeback.o \ @@ -37,6 +37,7 @@ obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o obj-$(CONFIG_QUICKLIST) += quicklist.o +obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o diff --git a/mm/compaction.c b/mm/compaction.c index 1a8894eadf7..8be430b812d 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -16,6 +16,9 @@ #include <linux/sysfs.h> #include "internal.h" +#define CREATE_TRACE_POINTS +#include <trace/events/compaction.h> + /* * compact_control is used to track pages being migrated and the free pages * they are being migrated to during memory compaction. The free_pfn starts @@ -30,6 +33,7 @@ struct compact_control { unsigned long nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ unsigned long migrate_pfn; /* isolate_migratepages search base */ + bool sync; /* Synchronous migration */ /* Account for isolated anon and file pages */ unsigned long nr_anon; @@ -38,6 +42,8 @@ struct compact_control { unsigned int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ struct zone *zone; + + int compact_mode; }; static unsigned long release_freepages(struct list_head *freelist) @@ -60,7 +66,7 @@ static unsigned long isolate_freepages_block(struct zone *zone, struct list_head *freelist) { unsigned long zone_end_pfn, end_pfn; - int total_isolated = 0; + int nr_scanned = 0, total_isolated = 0; struct page *cursor; /* Get the last PFN we should scan for free pages at */ @@ -81,6 +87,7 @@ static unsigned long isolate_freepages_block(struct zone *zone, if (!pfn_valid_within(blockpfn)) continue; + nr_scanned++; if (!PageBuddy(page)) continue; @@ -100,6 +107,7 @@ static unsigned long isolate_freepages_block(struct zone *zone, } } + trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated); return total_isolated; } @@ -234,6 +242,8 @@ static unsigned long isolate_migratepages(struct zone *zone, struct compact_control *cc) { unsigned long low_pfn, end_pfn; + unsigned long last_pageblock_nr = 0, pageblock_nr; + unsigned long nr_scanned = 0, nr_isolated = 0; struct list_head *migratelist = &cc->migratepages; /* Do not scan outside zone boundaries */ @@ -266,20 +276,51 @@ static unsigned long isolate_migratepages(struct zone *zone, struct page *page; if (!pfn_valid_within(low_pfn)) continue; + nr_scanned++; /* Get the page and skip if free */ page = pfn_to_page(low_pfn); if (PageBuddy(page)) continue; + /* + * For async migration, also only scan in MOVABLE blocks. Async + * migration is optimistic to see if the minimum amount of work + * satisfies the allocation + */ + pageblock_nr = low_pfn >> pageblock_order; + if (!cc->sync && last_pageblock_nr != pageblock_nr && + get_pageblock_migratetype(page) != MIGRATE_MOVABLE) { + low_pfn += pageblock_nr_pages; + low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1; + last_pageblock_nr = pageblock_nr; + continue; + } + + if (!PageLRU(page)) + continue; + + /* + * PageLRU is set, and lru_lock excludes isolation, + * splitting and collapsing (collapsing has already + * happened if PageLRU is set). + */ + if (PageTransHuge(page)) { + low_pfn += (1 << compound_order(page)) - 1; + continue; + } + /* Try isolate the page */ if (__isolate_lru_page(page, ISOLATE_BOTH, 0) != 0) continue; + VM_BUG_ON(PageTransCompound(page)); + /* Successfully isolated */ del_page_from_lru_list(zone, page, page_lru(page)); list_add(&page->lru, migratelist); cc->nr_migratepages++; + nr_isolated++; /* Avoid isolating too much */ if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) @@ -291,6 +332,8 @@ static unsigned long isolate_migratepages(struct zone *zone, spin_unlock_irq(&zone->lru_lock); cc->migrate_pfn = low_pfn; + trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); + return cc->nr_migratepages; } @@ -341,10 +384,10 @@ static void update_nr_listpages(struct compact_control *cc) } static int compact_finished(struct zone *zone, - struct compact_control *cc) + struct compact_control *cc) { unsigned int order; - unsigned long watermark = low_wmark_pages(zone) + (1 << cc->order); + unsigned long watermark; if (fatal_signal_pending(current)) return COMPACT_PARTIAL; @@ -354,12 +397,31 @@ static int compact_finished(struct zone *zone, return COMPACT_COMPLETE; /* Compaction run is not finished if the watermark is not met */ + if (cc->compact_mode != COMPACT_MODE_KSWAPD) + watermark = low_wmark_pages(zone); + else + watermark = high_wmark_pages(zone); + watermark += (1 << cc->order); + if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0)) return COMPACT_CONTINUE; + /* + * order == -1 is expected when compacting via + * /proc/sys/vm/compact_memory + */ if (cc->order == -1) return COMPACT_CONTINUE; + /* + * Generating only one page of the right order is not enough + * for kswapd, we must continue until we're above the high + * watermark as a pool for high order GFP_ATOMIC allocations + * too. + */ + if (cc->compact_mode == COMPACT_MODE_KSWAPD) + return COMPACT_CONTINUE; + /* Direct compactor: Is a suitable page free? */ for (order = cc->order; order < MAX_ORDER; order++) { /* Job done if page is free of the right migratetype */ @@ -374,10 +436,69 @@ static int compact_finished(struct zone *zone, return COMPACT_CONTINUE; } +/* + * compaction_suitable: Is this suitable to run compaction on this zone now? + * Returns + * COMPACT_SKIPPED - If there are too few free pages for compaction + * COMPACT_PARTIAL - If the allocation would succeed without compaction + * COMPACT_CONTINUE - If compaction should run now + */ +unsigned long compaction_suitable(struct zone *zone, int order) +{ + int fragindex; + unsigned long watermark; + + /* + * Watermarks for order-0 must be met for compaction. Note the 2UL. + * This is because during migration, copies of pages need to be + * allocated and for a short time, the footprint is higher + */ + watermark = low_wmark_pages(zone) + (2UL << order); + if (!zone_watermark_ok(zone, 0, watermark, 0, 0)) + return COMPACT_SKIPPED; + + /* + * order == -1 is expected when compacting via + * /proc/sys/vm/compact_memory + */ + if (order == -1) + return COMPACT_CONTINUE; + + /* + * fragmentation index determines if allocation failures are due to + * low memory or external fragmentation + * + * index of -1 implies allocations might succeed dependingon watermarks + * index towards 0 implies failure is due to lack of memory + * index towards 1000 implies failure is due to fragmentation + * + * Only compact if a failure would be due to fragmentation. + */ + fragindex = fragmentation_index(zone, order); + if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) + return COMPACT_SKIPPED; + + if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0)) + return COMPACT_PARTIAL; + + return COMPACT_CONTINUE; +} + static int compact_zone(struct zone *zone, struct compact_control *cc) { int ret; + ret = compaction_suitable(zone, cc->order); + switch (ret) { + case COMPACT_PARTIAL: + case COMPACT_SKIPPED: + /* Compaction is likely to fail */ + return ret; + case COMPACT_CONTINUE: + /* Fall through to compaction */ + ; + } + /* Setup to move all movable pages to the end of the zone */ cc->migrate_pfn = zone->zone_start_pfn; cc->free_pfn = cc->migrate_pfn + zone->spanned_pages; @@ -393,7 +514,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) nr_migrate = cc->nr_migratepages; migrate_pages(&cc->migratepages, compaction_alloc, - (unsigned long)cc, 0); + (unsigned long)cc, false, + cc->sync); update_nr_listpages(cc); nr_remaining = cc->nr_migratepages; @@ -401,6 +523,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) count_vm_events(COMPACTPAGES, nr_migrate - nr_remaining); if (nr_remaining) count_vm_events(COMPACTPAGEFAILED, nr_remaining); + trace_mm_compaction_migratepages(nr_migrate - nr_remaining, + nr_remaining); /* Release LRU pages not migrated */ if (!list_empty(&cc->migratepages)) { @@ -417,8 +541,10 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) return ret; } -static unsigned long compact_zone_order(struct zone *zone, - int order, gfp_t gfp_mask) +unsigned long compact_zone_order(struct zone *zone, + int order, gfp_t gfp_mask, + bool sync, + int compact_mode) { struct compact_control cc = { .nr_freepages = 0, @@ -426,6 +552,8 @@ static unsigned long compact_zone_order(struct zone *zone, .order = order, .migratetype = allocflags_to_migratetype(gfp_mask), .zone = zone, + .sync = sync, + .compact_mode = compact_mode, }; INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); @@ -441,16 +569,17 @@ int sysctl_extfrag_threshold = 500; * @order: The order of the current allocation * @gfp_mask: The GFP mask of the current allocation * @nodemask: The allowed nodes to allocate from + * @sync: Whether migration is synchronous or not * * This is the main entry point for direct page compaction. */ unsigned long try_to_compact_pages(struct zonelist *zonelist, - int order, gfp_t gfp_mask, nodemask_t *nodemask) + int order, gfp_t gfp_mask, nodemask_t *nodemask, + bool sync) { enum zone_type high_zoneidx = gfp_zone(gfp_mask); int may_enter_fs = gfp_mask & __GFP_FS; int may_perform_io = gfp_mask & __GFP_IO; - unsigned long watermark; struct zoneref *z; struct zone *zone; int rc = COMPACT_SKIPPED; @@ -460,7 +589,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, * made because an assumption is made that the page allocator can satisfy * the "cheaper" orders without taking special steps */ - if (order <= PAGE_ALLOC_COSTLY_ORDER || !may_enter_fs || !may_perform_io) + if (!order || !may_enter_fs || !may_perform_io) return rc; count_vm_event(COMPACTSTALL); @@ -468,43 +597,14 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, /* Compact each zone in the list */ for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx, nodemask) { - int fragindex; int status; - /* - * Watermarks for order-0 must be met for compaction. Note - * the 2UL. This is because during migration, copies of - * pages need to be allocated and for a short time, the - * footprint is higher - */ - watermark = low_wmark_pages(zone) + (2UL << order); - if (!zone_watermark_ok(zone, 0, watermark, 0, 0)) - continue; - - /* - * fragmentation index determines if allocation failures are - * due to low memory or external fragmentation - * - * index of -1 implies allocations might succeed depending - * on watermarks - * index towards 0 implies failure is due to lack of memory - * index towards 1000 implies failure is due to fragmentation - * - * Only compact if a failure would be due to fragmentation. - */ - fragindex = fragmentation_index(zone, order); - if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) - continue; - - if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0)) { - rc = COMPACT_PARTIAL; - break; - } - - status = compact_zone_order(zone, order, gfp_mask); + status = compact_zone_order(zone, order, gfp_mask, sync, + COMPACT_MODE_DIRECT_RECLAIM); rc = max(status, rc); - if (zone_watermark_ok(zone, order, watermark, 0, 0)) + /* If a normal allocation would succeed, stop compacting */ + if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0)) break; } @@ -531,6 +631,7 @@ static int compact_node(int nid) .nr_freepages = 0, .nr_migratepages = 0, .order = -1, + .compact_mode = COMPACT_MODE_DIRECT_RECLAIM, }; zone = &pgdat->node_zones[zoneid]; diff --git a/mm/dmapool.c b/mm/dmapool.c index 4df2de77e06..03bf3bb4519 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -324,7 +324,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, if (mem_flags & __GFP_WAIT) { DECLARE_WAITQUEUE(wait, current); - __set_current_state(TASK_INTERRUPTIBLE); + __set_current_state(TASK_UNINTERRUPTIBLE); __add_wait_queue(&pool->waitq, &wait); spin_unlock_irqrestore(&pool->lock, flags); @@ -355,20 +355,15 @@ EXPORT_SYMBOL(dma_pool_alloc); static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma) { - unsigned long flags; struct dma_page *page; - spin_lock_irqsave(&pool->lock, flags); list_for_each_entry(page, &pool->page_list, page_list) { if (dma < page->dma) continue; if (dma < (page->dma + pool->allocation)) - goto done; + return page; } - page = NULL; - done: - spin_unlock_irqrestore(&pool->lock, flags); - return page; + return NULL; } /** @@ -386,8 +381,10 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) unsigned long flags; unsigned int offset; + spin_lock_irqsave(&pool->lock, flags); page = pool_find_page(pool, dma); if (!page) { + spin_unlock_irqrestore(&pool->lock, flags); if (pool->dev) dev_err(pool->dev, "dma_pool_free %s, %p/%lx (bad dma)\n", @@ -401,6 +398,7 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) offset = vaddr - page->vaddr; #ifdef DMAPOOL_DEBUG if ((dma - page->dma) != offset) { + spin_unlock_irqrestore(&pool->lock, flags); if (pool->dev) dev_err(pool->dev, "dma_pool_free %s, %p (bad vaddr)/%Lx\n", @@ -418,6 +416,7 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) chain = *(int *)(page->vaddr + chain); continue; } + spin_unlock_irqrestore(&pool->lock, flags); if (pool->dev) dev_err(pool->dev, "dma_pool_free %s, dma %Lx " "already free\n", pool->name, @@ -432,7 +431,6 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) memset(vaddr, POOL_POISON_FREED, pool->size); #endif - spin_lock_irqsave(&pool->lock, flags); page->in_use--; *(int *)vaddr = page->offset; page->offset = offset; diff --git a/mm/filemap.c b/mm/filemap.c index 6b9aee20f24..83a45d35468 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -102,9 +102,6 @@ * ->inode_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->__set_page_dirty_buffers) * - * ->task->proc_lock - * ->dcache_lock (proc_pid_lookup) - * * (code doesn't rely on that order, so you could switch it around) * ->tasklist_lock (memory_failure, collect_procs_ao) * ->i_mmap_lock @@ -301,7 +298,7 @@ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, continue; wait_on_page_writeback(page); - if (PageError(page)) + if (TestClearPageError(page)) ret = -EIO; } pagevec_release(&pvec); @@ -840,9 +837,6 @@ repeat: if (radix_tree_deref_retry(page)) goto restart; - if (page->mapping == NULL || page->index != index) - break; - if (!page_cache_get_speculative(page)) goto repeat; @@ -852,6 +846,16 @@ repeat: goto repeat; } + /* + * must check mapping and index after taking the ref. + * otherwise we can get both false positives and false + * negatives, which is just confusing to the caller. + */ + if (page->mapping == NULL || page->index != index) { + page_cache_release(page); + break; + } + pages[ret] = page; ret++; index++; @@ -2223,7 +2227,7 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping, gfp_notmask = __GFP_FS; repeat: page = find_lock_page(mapping, index); - if (likely(page)) + if (page) return page; page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~gfp_notmask); diff --git a/mm/huge_memory.c b/mm/huge_memory.c new file mode 100644 index 00000000000..3e29781ee76 --- /dev/null +++ b/mm/huge_memory.c @@ -0,0 +1,2351 @@ +/* + * Copyright (C) 2009 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/mm.h> +#include <linux/sched.h> +#include <linux/highmem.h> +#include <linux/hugetlb.h> +#include <linux/mmu_notifier.h> +#include <linux/rmap.h> +#include <linux/swap.h> +#include <linux/mm_inline.h> +#include <linux/kthread.h> +#include <linux/khugepaged.h> +#include <linux/freezer.h> +#include <linux/mman.h> +#include <asm/tlb.h> +#include <asm/pgalloc.h> +#include "internal.h" + +/* + * By default transparent hugepage support is enabled for all mappings + * and khugepaged scans all mappings. Defrag is only invoked by + * khugepaged hugepage allocations and by page faults inside + * MADV_HUGEPAGE regions to avoid the risk of slowing down short lived + * allocations. + */ +unsigned long transparent_hugepage_flags __read_mostly = +#ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS + (1<<TRANSPARENT_HUGEPAGE_FLAG)| +#endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE_MADVISE + (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)| +#endif + (1<<TRANSPARENT_HUGEPAGE_DEFRAG_FLAG)| + (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); + +/* default scan 8*512 pte (or vmas) every 30 second */ +static unsigned int khugepaged_pages_to_scan __read_mostly = HPAGE_PMD_NR*8; +static unsigned int khugepaged_pages_collapsed; +static unsigned int khugepaged_full_scans; +static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000; +/* during fragmentation poll the hugepage allocator once every minute */ +static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000; +static struct task_struct *khugepaged_thread __read_mostly; +static DEFINE_MUTEX(khugepaged_mutex); +static DEFINE_SPINLOCK(khugepaged_mm_lock); +static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); +/* + * default collapse hugepages if there is at least one pte mapped like + * it would have happened if the vma was large enough during page + * fault. + */ +static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1; + +static int khugepaged(void *none); +static int mm_slots_hash_init(void); +static int khugepaged_slab_init(void); +static void khugepaged_slab_free(void); + +#define MM_SLOTS_HASH_HEADS 1024 +static struct hlist_head *mm_slots_hash __read_mostly; +static struct kmem_cache *mm_slot_cache __read_mostly; + +/** + * struct mm_slot - hash lookup from mm to mm_slot + * @hash: hash collision list + * @mm_node: khugepaged scan list headed in khugepaged_scan.mm_head + * @mm: the mm that this information is valid for + */ +struct mm_slot { + struct hlist_node hash; + struct list_head mm_node; + struct mm_struct *mm; +}; + +/** + * struct khugepaged_scan - cursor for scanning + * @mm_head: the head of the mm list to scan + * @mm_slot: the current mm_slot we are scanning + * @address: the next address inside that to be scanned + * + * There is only the one khugepaged_scan instance of this cursor structure. + */ +struct khugepaged_scan { + struct list_head mm_head; + struct mm_slot *mm_slot; + unsigned long address; +} khugepaged_scan = { + .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), +}; + + +static int set_recommended_min_free_kbytes(void) +{ + struct zone *zone; + int nr_zones = 0; + unsigned long recommended_min; + extern int min_free_kbytes; + + if (!test_bit(TRANSPARENT_HUGEPAGE_FLAG, + &transparent_hugepage_flags) && + !test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, + &transparent_hugepage_flags)) + return 0; + + for_each_populated_zone(zone) + nr_zones++; + + /* Make sure at least 2 hugepages are free for MIGRATE_RESERVE */ + recommended_min = pageblock_nr_pages * nr_zones * 2; + + /* + * Make sure that on average at least two pageblocks are almost free + * of another type, one for a migratetype to fall back to and a + * second to avoid subsequent fallbacks of other types There are 3 + * MIGRATE_TYPES we care about. + */ + recommended_min += pageblock_nr_pages * nr_zones * + MIGRATE_PCPTYPES * MIGRATE_PCPTYPES; + + /* don't ever allow to reserve more than 5% of the lowmem */ + recommended_min = min(recommended_min, + (unsigned long) nr_free_buffer_pages() / 20); + recommended_min <<= (PAGE_SHIFT-10); + + if (recommended_min > min_free_kbytes) + min_free_kbytes = recommended_min; + setup_per_zone_wmarks(); + return 0; +} +late_initcall(set_recommended_min_free_kbytes); + +static int start_khugepaged(void) +{ + int err = 0; + if (khugepaged_enabled()) { + int wakeup; + if (unlikely(!mm_slot_cache || !mm_slots_hash)) { + err = -ENOMEM; + goto out; + } + mutex_lock(&khugepaged_mutex); + if (!khugepaged_thread) + khugepaged_thread = kthread_run(khugepaged, NULL, + "khugepaged"); + if (unlikely(IS_ERR(khugepaged_thread))) { + printk(KERN_ERR + "khugepaged: kthread_run(khugepaged) failed\n"); + err = PTR_ERR(khugepaged_thread); + khugepaged_thread = NULL; + } + wakeup = !list_empty(&khugepaged_scan.mm_head); + mutex_unlock(&khugepaged_mutex); + if (wakeup) + wake_up_interruptible(&khugepaged_wait); + + set_recommended_min_free_kbytes(); + } else + /* wakeup to exit */ + wake_up_interruptible(&khugepaged_wait); +out: + return err; +} + +#ifdef CONFIG_SYSFS + +static ssize_t double_flag_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf, + enum transparent_hugepage_flag enabled, + enum transparent_hugepage_flag req_madv) +{ + if (test_bit(enabled, &transparent_hugepage_flags)) { + VM_BUG_ON(test_bit(req_madv, &transparent_hugepage_flags)); + return sprintf(buf, "[always] madvise never\n"); + } else if (test_bit(req_madv, &transparent_hugepage_flags)) + return sprintf(buf, "always [madvise] never\n"); + else + return sprintf(buf, "always madvise [never]\n"); +} +static ssize_t double_flag_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count, + enum transparent_hugepage_flag enabled, + enum transparent_hugepage_flag req_madv) +{ + if (!memcmp("always", buf, + min(sizeof("always")-1, count))) { + set_bit(enabled, &transparent_hugepage_flags); + clear_bit(req_madv, &transparent_hugepage_flags); + } else if (!memcmp("madvise", buf, + min(sizeof("madvise")-1, count))) { + clear_bit(enabled, &transparent_hugepage_flags); + set_bit(req_madv, &transparent_hugepage_flags); + } else if (!memcmp("never", buf, + min(sizeof("never")-1, count))) { + clear_bit(enabled, &transparent_hugepage_flags); + clear_bit(req_madv, &transparent_hugepage_flags); + } else + return -EINVAL; + + return count; +} + +static ssize_t enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return double_flag_show(kobj, attr, buf, + TRANSPARENT_HUGEPAGE_FLAG, + TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG); +} +static ssize_t enabled_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + ssize_t ret; + + ret = double_flag_store(kobj, attr, buf, count, + TRANSPARENT_HUGEPAGE_FLAG, + TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG); + + if (ret > 0) { + int err = start_khugepaged(); + if (err) + ret = err; + } + + if (ret > 0 && + (test_bit(TRANSPARENT_HUGEPAGE_FLAG, + &transparent_hugepage_flags) || + test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, + &transparent_hugepage_flags))) + set_recommended_min_free_kbytes(); + + return ret; +} +static struct kobj_attribute enabled_attr = + __ATTR(enabled, 0644, enabled_show, enabled_store); + +static ssize_t single_flag_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf, + enum transparent_hugepage_flag flag) +{ + if (test_bit(flag, &transparent_hugepage_flags)) + return sprintf(buf, "[yes] no\n"); + else + return sprintf(buf, "yes [no]\n"); +} +static ssize_t single_flag_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count, + enum transparent_hugepage_flag flag) +{ + if (!memcmp("yes", buf, + min(sizeof("yes")-1, count))) { + set_bit(flag, &transparent_hugepage_flags); + } else if (!memcmp("no", buf, + min(sizeof("no")-1, count))) { + clear_bit(flag, &transparent_hugepage_flags); + } else + return -EINVAL; + + return count; +} + +/* + * Currently defrag only disables __GFP_NOWAIT for allocation. A blind + * __GFP_REPEAT is too aggressive, it's never worth swapping tons of + * memory just to allocate one more hugepage. + */ +static ssize_t defrag_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return double_flag_show(kobj, attr, buf, + TRANSPARENT_HUGEPAGE_DEFRAG_FLAG, + TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG); +} +static ssize_t defrag_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + return double_flag_store(kobj, attr, buf, count, + TRANSPARENT_HUGEPAGE_DEFRAG_FLAG, + TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG); +} +static struct kobj_attribute defrag_attr = + __ATTR(defrag, 0644, defrag_show, defrag_store); + +#ifdef CONFIG_DEBUG_VM +static ssize_t debug_cow_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return single_flag_show(kobj, attr, buf, + TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG); +} +static ssize_t debug_cow_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + return single_flag_store(kobj, attr, buf, count, + TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG); +} +static struct kobj_attribute debug_cow_attr = + __ATTR(debug_cow, 0644, debug_cow_show, debug_cow_store); +#endif /* CONFIG_DEBUG_VM */ + +static struct attribute *hugepage_attr[] = { + &enabled_attr.attr, + &defrag_attr.attr, +#ifdef CONFIG_DEBUG_VM + &debug_cow_attr.attr, +#endif + NULL, +}; + +static struct attribute_group hugepage_attr_group = { + .attrs = hugepage_attr, +}; + +static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_scan_sleep_millisecs); +} + +static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long msecs; + int err; + + err = strict_strtoul(buf, 10, &msecs); + if (err || msecs > UINT_MAX) + return -EINVAL; + + khugepaged_scan_sleep_millisecs = msecs; + wake_up_interruptible(&khugepaged_wait); + + return count; +} +static struct kobj_attribute scan_sleep_millisecs_attr = + __ATTR(scan_sleep_millisecs, 0644, scan_sleep_millisecs_show, + scan_sleep_millisecs_store); + +static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_alloc_sleep_millisecs); +} + +static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long msecs; + int err; + + err = strict_strtoul(buf, 10, &msecs); + if (err || msecs > UINT_MAX) + return -EINVAL; + + khugepaged_alloc_sleep_millisecs = msecs; + wake_up_interruptible(&khugepaged_wait); + + return count; +} +static struct kobj_attribute alloc_sleep_millisecs_attr = + __ATTR(alloc_sleep_millisecs, 0644, alloc_sleep_millisecs_show, + alloc_sleep_millisecs_store); + +static ssize_t pages_to_scan_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_pages_to_scan); +} +static ssize_t pages_to_scan_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long pages; + + err = strict_strtoul(buf, 10, &pages); + if (err || !pages || pages > UINT_MAX) + return -EINVAL; + + khugepaged_pages_to_scan = pages; + + return count; +} +static struct kobj_attribute pages_to_scan_attr = + __ATTR(pages_to_scan, 0644, pages_to_scan_show, + pages_to_scan_store); + +static ssize_t pages_collapsed_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_pages_collapsed); +} +static struct kobj_attribute pages_collapsed_attr = + __ATTR_RO(pages_collapsed); + +static ssize_t full_scans_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_full_scans); +} +static struct kobj_attribute full_scans_attr = + __ATTR_RO(full_scans); + +static ssize_t khugepaged_defrag_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return single_flag_show(kobj, attr, buf, + TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); +} +static ssize_t khugepaged_defrag_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + return single_flag_store(kobj, attr, buf, count, + TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); +} +static struct kobj_attribute khugepaged_defrag_attr = + __ATTR(defrag, 0644, khugepaged_defrag_show, + khugepaged_defrag_store); + +/* + * max_ptes_none controls if khugepaged should collapse hugepages over + * any unmapped ptes in turn potentially increasing the memory + * footprint of the vmas. When max_ptes_none is 0 khugepaged will not + * reduce the available free memory in the system as it + * runs. Increasing max_ptes_none will instead potentially reduce the + * free memory in the system during the khugepaged scan. + */ +static ssize_t khugepaged_max_ptes_none_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_max_ptes_none); +} +static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long max_ptes_none; + + err = strict_strtoul(buf, 10, &max_ptes_none); + if (err || max_ptes_none > HPAGE_PMD_NR-1) + return -EINVAL; + + khugepaged_max_ptes_none = max_ptes_none; + + return count; +} +static struct kobj_attribute khugepaged_max_ptes_none_attr = + __ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show, + khugepaged_max_ptes_none_store); + +static struct attribute *khugepaged_attr[] = { + &khugepaged_defrag_attr.attr, + &khugepaged_max_ptes_none_attr.attr, + &pages_to_scan_attr.attr, + &pages_collapsed_attr.attr, + &full_scans_attr.attr, + &scan_sleep_millisecs_attr.attr, + &alloc_sleep_millisecs_attr.attr, + NULL, +}; + +static struct attribute_group khugepaged_attr_group = { + .attrs = khugepaged_attr, + .name = "khugepaged", +}; +#endif /* CONFIG_SYSFS */ + +static int __init hugepage_init(void) +{ + int err; +#ifdef CONFIG_SYSFS + static struct kobject *hugepage_kobj; +#endif + + err = -EINVAL; + if (!has_transparent_hugepage()) { + transparent_hugepage_flags = 0; + goto out; + } + +#ifdef CONFIG_SYSFS + err = -ENOMEM; + hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj); + if (unlikely(!hugepage_kobj)) { + printk(KERN_ERR "hugepage: failed kobject create\n"); + goto out; + } + + err = sysfs_create_group(hugepage_kobj, &hugepage_attr_group); + if (err) { + printk(KERN_ERR "hugepage: failed register hugeage group\n"); + goto out; + } + + err = sysfs_create_group(hugepage_kobj, &khugepaged_attr_group); + if (err) { + printk(KERN_ERR "hugepage: failed register hugeage group\n"); + goto out; + } +#endif + + err = khugepaged_slab_init(); + if (err) + goto out; + + err = mm_slots_hash_init(); + if (err) { + khugepaged_slab_free(); + goto out; + } + + /* + * By default disable transparent hugepages on smaller systems, + * where the extra memory used could hurt more than TLB overhead + * is likely to save. The admin can still enable it through /sys. + */ + if (totalram_pages < (512 << (20 - PAGE_SHIFT))) + transparent_hugepage_flags = 0; + + start_khugepaged(); + + set_recommended_min_free_kbytes(); + +out: + return err; +} +module_init(hugepage_init) + +static int __init setup_transparent_hugepage(char *str) +{ + int ret = 0; + if (!str) + goto out; + if (!strcmp(str, "always")) { + set_bit(TRANSPARENT_HUGEPAGE_FLAG, + &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, + &transparent_hugepage_flags); + ret = 1; + } else if (!strcmp(str, "madvise")) { + clear_bit(TRANSPARENT_HUGEPAGE_FLAG, + &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, + &transparent_hugepage_flags); + ret = 1; + } else if (!strcmp(str, "never")) { + clear_bit(TRANSPARENT_HUGEPAGE_FLAG, + &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, + &transparent_hugepage_flags); + ret = 1; + } +out: + if (!ret) + printk(KERN_WARNING + "transparent_hugepage= cannot parse, ignored\n"); + return ret; +} +__setup("transparent_hugepage=", setup_transparent_hugepage); + +static void prepare_pmd_huge_pte(pgtable_t pgtable, + struct mm_struct *mm) +{ + assert_spin_locked(&mm->page_table_lock); + + /* FIFO */ + if (!mm->pmd_huge_pte) + INIT_LIST_HEAD(&pgtable->lru); + else + list_add(&pgtable->lru, &mm->pmd_huge_pte->lru); + mm->pmd_huge_pte = pgtable; +} + +static inline pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) +{ + if (likely(vma->vm_flags & VM_WRITE)) + pmd = pmd_mkwrite(pmd); + return pmd; +} + +static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long haddr, pmd_t *pmd, + struct page *page) +{ + int ret = 0; + pgtable_t pgtable; + + VM_BUG_ON(!PageCompound(page)); + pgtable = pte_alloc_one(mm, haddr); + if (unlikely(!pgtable)) { + mem_cgroup_uncharge_page(page); + put_page(page); + return VM_FAULT_OOM; + } + + clear_huge_page(page, haddr, HPAGE_PMD_NR); + __SetPageUptodate(page); + + spin_lock(&mm->page_table_lock); + if (unlikely(!pmd_none(*pmd))) { + spin_unlock(&mm->page_table_lock); + mem_cgroup_uncharge_page(page); + put_page(page); + pte_free(mm, pgtable); + } else { + pmd_t entry; + entry = mk_pmd(page, vma->vm_page_prot); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + entry = pmd_mkhuge(entry); + /* + * The spinlocking to take the lru_lock inside + * page_add_new_anon_rmap() acts as a full memory + * barrier to be sure clear_huge_page writes become + * visible after the set_pmd_at() write. + */ + page_add_new_anon_rmap(page, vma, haddr); + set_pmd_at(mm, haddr, pmd, entry); + prepare_pmd_huge_pte(pgtable, mm); + add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR); + spin_unlock(&mm->page_table_lock); + } + + return ret; +} + +static inline gfp_t alloc_hugepage_gfpmask(int defrag) +{ + return GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT); +} + +static inline struct page *alloc_hugepage_vma(int defrag, + struct vm_area_struct *vma, + unsigned long haddr) +{ + return alloc_pages_vma(alloc_hugepage_gfpmask(defrag), + HPAGE_PMD_ORDER, vma, haddr); +} + +#ifndef CONFIG_NUMA +static inline struct page *alloc_hugepage(int defrag) +{ + return alloc_pages(alloc_hugepage_gfpmask(defrag), + HPAGE_PMD_ORDER); +} +#endif + +int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + unsigned int flags) +{ + struct page *page; + unsigned long haddr = address & HPAGE_PMD_MASK; + pte_t *pte; + + if (haddr >= vma->vm_start && haddr + HPAGE_PMD_SIZE <= vma->vm_end) { + if (unlikely(anon_vma_prepare(vma))) + return VM_FAULT_OOM; + if (unlikely(khugepaged_enter(vma))) + return VM_FAULT_OOM; + page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), + vma, haddr); + if (unlikely(!page)) + goto out; + if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) { + put_page(page); + goto out; + } + + return __do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page); + } +out: + /* + * Use __pte_alloc instead of pte_alloc_map, because we can't + * run pte_offset_map on the pmd, if an huge pmd could + * materialize from under us from a different thread. + */ + if (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))) + return 0; + /* + * A regular pmd is established and it can't morph into a huge pmd + * from under us anymore at this point because we hold the mmap_sem + * read mode and khugepaged takes it in write mode. So now it's + * safe to run pte_offset_map(). + */ + pte = pte_offset_map(pmd, address); + return handle_pte_fault(mm, vma, address, pte, pmd, flags); +} + +int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, + struct vm_area_struct *vma) +{ + struct page *src_page; + pmd_t pmd; + pgtable_t pgtable; + int ret; + + ret = -ENOMEM; + pgtable = pte_alloc_one(dst_mm, addr); + if (unlikely(!pgtable)) + goto out; + + spin_lock(&dst_mm->page_table_lock); + spin_lock_nested(&src_mm->page_table_lock, SINGLE_DEPTH_NESTING); + + ret = -EAGAIN; + pmd = *src_pmd; + if (unlikely(!pmd_trans_huge(pmd))) { + pte_free(dst_mm, pgtable); + goto out_unlock; + } + if (unlikely(pmd_trans_splitting(pmd))) { + /* split huge page running from under us */ + spin_unlock(&src_mm->page_table_lock); + spin_unlock(&dst_mm->page_table_lock); + pte_free(dst_mm, pgtable); + + wait_split_huge_page(vma->anon_vma, src_pmd); /* src_vma */ + goto out; + } + src_page = pmd_page(pmd); + VM_BUG_ON(!PageHead(src_page)); + get_page(src_page); + page_dup_rmap(src_page); + add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); + + pmdp_set_wrprotect(src_mm, addr, src_pmd); + pmd = pmd_mkold(pmd_wrprotect(pmd)); + set_pmd_at(dst_mm, addr, dst_pmd, pmd); + prepare_pmd_huge_pte(pgtable, dst_mm); + + ret = 0; +out_unlock: + spin_unlock(&src_mm->page_table_lock); + spin_unlock(&dst_mm->page_table_lock); +out: + return ret; +} + +/* no "address" argument so destroys page coloring of some arch */ +pgtable_t get_pmd_huge_pte(struct mm_struct *mm) +{ + pgtable_t pgtable; + + assert_spin_locked(&mm->page_table_lock); + + /* FIFO */ + pgtable = mm->pmd_huge_pte; + if (list_empty(&pgtable->lru)) + mm->pmd_huge_pte = NULL; + else { + mm->pmd_huge_pte = list_entry(pgtable->lru.next, + struct page, lru); + list_del(&pgtable->lru); + } + return pgtable; +} + +static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmd, pmd_t orig_pmd, + struct page *page, + unsigned long haddr) +{ + pgtable_t pgtable; + pmd_t _pmd; + int ret = 0, i; + struct page **pages; + + pages = kmalloc(sizeof(struct page *) * HPAGE_PMD_NR, + GFP_KERNEL); + if (unlikely(!pages)) { + ret |= VM_FAULT_OOM; + goto out; + } + + for (i = 0; i < HPAGE_PMD_NR; i++) { + pages[i] = alloc_page_vma(GFP_HIGHUSER_MOVABLE, + vma, address); + if (unlikely(!pages[i] || + mem_cgroup_newpage_charge(pages[i], mm, + GFP_KERNEL))) { + if (pages[i]) + put_page(pages[i]); + mem_cgroup_uncharge_start(); + while (--i >= 0) { + mem_cgroup_uncharge_page(pages[i]); + put_page(pages[i]); + } + mem_cgroup_uncharge_end(); + kfree(pages); + ret |= VM_FAULT_OOM; + goto out; + } + } + + for (i = 0; i < HPAGE_PMD_NR; i++) { + copy_user_highpage(pages[i], page + i, + haddr + PAGE_SHIFT*i, vma); + __SetPageUptodate(pages[i]); + cond_resched(); + } + + spin_lock(&mm->page_table_lock); + if (unlikely(!pmd_same(*pmd, orig_pmd))) + goto out_free_pages; + VM_BUG_ON(!PageHead(page)); + + pmdp_clear_flush_notify(vma, haddr, pmd); + /* leave pmd empty until pte is filled */ + + pgtable = get_pmd_huge_pte(mm); + pmd_populate(mm, &_pmd, pgtable); + + for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { + pte_t *pte, entry; + entry = mk_pte(pages[i], vma->vm_page_prot); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + page_add_new_anon_rmap(pages[i], vma, haddr); + pte = pte_offset_map(&_pmd, haddr); + VM_BUG_ON(!pte_none(*pte)); + set_pte_at(mm, haddr, pte, entry); + pte_unmap(pte); + } + kfree(pages); + + mm->nr_ptes++; + smp_wmb(); /* make pte visible before pmd */ + pmd_populate(mm, pmd, pgtable); + page_remove_rmap(page); + spin_unlock(&mm->page_table_lock); + + ret |= VM_FAULT_WRITE; + put_page(page); + +out: + return ret; + +out_free_pages: + spin_unlock(&mm->page_table_lock); + mem_cgroup_uncharge_start(); + for (i = 0; i < HPAGE_PMD_NR; i++) { + mem_cgroup_uncharge_page(pages[i]); + put_page(pages[i]); + } + mem_cgroup_uncharge_end(); + kfree(pages); + goto out; +} + +int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, pmd_t orig_pmd) +{ + int ret = 0; + struct page *page, *new_page; + unsigned long haddr; + + VM_BUG_ON(!vma->anon_vma); + spin_lock(&mm->page_table_lock); + if (unlikely(!pmd_same(*pmd, orig_pmd))) + goto out_unlock; + + page = pmd_page(orig_pmd); + VM_BUG_ON(!PageCompound(page) || !PageHead(page)); + haddr = address & HPAGE_PMD_MASK; + if (page_mapcount(page) == 1) { + pmd_t entry; + entry = pmd_mkyoung(orig_pmd); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + if (pmdp_set_access_flags(vma, haddr, pmd, entry, 1)) + update_mmu_cache(vma, address, entry); + ret |= VM_FAULT_WRITE; + goto out_unlock; + } + get_page(page); + spin_unlock(&mm->page_table_lock); + + if (transparent_hugepage_enabled(vma) && + !transparent_hugepage_debug_cow()) + new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), + vma, haddr); + else + new_page = NULL; + + if (unlikely(!new_page)) { + ret = do_huge_pmd_wp_page_fallback(mm, vma, address, + pmd, orig_pmd, page, haddr); + put_page(page); + goto out; + } + + if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { + put_page(new_page); + put_page(page); + ret |= VM_FAULT_OOM; + goto out; + } + + copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR); + __SetPageUptodate(new_page); + + spin_lock(&mm->page_table_lock); + put_page(page); + if (unlikely(!pmd_same(*pmd, orig_pmd))) { + mem_cgroup_uncharge_page(new_page); + put_page(new_page); + } else { + pmd_t entry; + VM_BUG_ON(!PageHead(page)); + entry = mk_pmd(new_page, vma->vm_page_prot); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + entry = pmd_mkhuge(entry); + pmdp_clear_flush_notify(vma, haddr, pmd); + page_add_new_anon_rmap(new_page, vma, haddr); + set_pmd_at(mm, haddr, pmd, entry); + update_mmu_cache(vma, address, entry); + page_remove_rmap(page); + put_page(page); + ret |= VM_FAULT_WRITE; + } +out_unlock: + spin_unlock(&mm->page_table_lock); +out: + return ret; +} + +struct page *follow_trans_huge_pmd(struct mm_struct *mm, + unsigned long addr, + pmd_t *pmd, + unsigned int flags) +{ + struct page *page = NULL; + + assert_spin_locked(&mm->page_table_lock); + + if (flags & FOLL_WRITE && !pmd_write(*pmd)) + goto out; + + page = pmd_page(*pmd); + VM_BUG_ON(!PageHead(page)); + if (flags & FOLL_TOUCH) { + pmd_t _pmd; + /* + * We should set the dirty bit only for FOLL_WRITE but + * for now the dirty bit in the pmd is meaningless. + * And if the dirty bit will become meaningful and + * we'll only set it with FOLL_WRITE, an atomic + * set_bit will be required on the pmd to set the + * young bit, instead of the current set_pmd_at. + */ + _pmd = pmd_mkyoung(pmd_mkdirty(*pmd)); + set_pmd_at(mm, addr & HPAGE_PMD_MASK, pmd, _pmd); + } + page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; + VM_BUG_ON(!PageCompound(page)); + if (flags & FOLL_GET) + get_page(page); + +out: + return page; +} + +int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, + pmd_t *pmd) +{ + int ret = 0; + + spin_lock(&tlb->mm->page_table_lock); + if (likely(pmd_trans_huge(*pmd))) { + if (unlikely(pmd_trans_splitting(*pmd))) { + spin_unlock(&tlb->mm->page_table_lock); + wait_split_huge_page(vma->anon_vma, + pmd); + } else { + struct page *page; + pgtable_t pgtable; + pgtable = get_pmd_huge_pte(tlb->mm); + page = pmd_page(*pmd); + pmd_clear(pmd); + page_remove_rmap(page); + VM_BUG_ON(page_mapcount(page) < 0); + add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); + VM_BUG_ON(!PageHead(page)); + spin_unlock(&tlb->mm->page_table_lock); + tlb_remove_page(tlb, page); + pte_free(tlb->mm, pgtable); + ret = 1; + } + } else + spin_unlock(&tlb->mm->page_table_lock); + + return ret; +} + +int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr, unsigned long end, + unsigned char *vec) +{ + int ret = 0; + + spin_lock(&vma->vm_mm->page_table_lock); + if (likely(pmd_trans_huge(*pmd))) { + ret = !pmd_trans_splitting(*pmd); + spin_unlock(&vma->vm_mm->page_table_lock); + if (unlikely(!ret)) + wait_split_huge_page(vma->anon_vma, pmd); + else { + /* + * All logical pages in the range are present + * if backed by a huge page. + */ + memset(vec, 1, (end - addr) >> PAGE_SHIFT); + } + } else + spin_unlock(&vma->vm_mm->page_table_lock); + + return ret; +} + +int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr, pgprot_t newprot) +{ + struct mm_struct *mm = vma->vm_mm; + int ret = 0; + + spin_lock(&mm->page_table_lock); + if (likely(pmd_trans_huge(*pmd))) { + if (unlikely(pmd_trans_splitting(*pmd))) { + spin_unlock(&mm->page_table_lock); + wait_split_huge_page(vma->anon_vma, pmd); + } else { + pmd_t entry; + + entry = pmdp_get_and_clear(mm, addr, pmd); + entry = pmd_modify(entry, newprot); + set_pmd_at(mm, addr, pmd, entry); + spin_unlock(&vma->vm_mm->page_table_lock); + flush_tlb_range(vma, addr, addr + HPAGE_PMD_SIZE); + ret = 1; + } + } else + spin_unlock(&vma->vm_mm->page_table_lock); + + return ret; +} + +pmd_t *page_check_address_pmd(struct page *page, + struct mm_struct *mm, + unsigned long address, + enum page_check_address_pmd_flag flag) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd, *ret = NULL; + + if (address & ~HPAGE_PMD_MASK) + goto out; + + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + goto out; + + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + goto out; + + pmd = pmd_offset(pud, address); + if (pmd_none(*pmd)) + goto out; + if (pmd_page(*pmd) != page) + goto out; + /* + * split_vma() may create temporary aliased mappings. There is + * no risk as long as all huge pmd are found and have their + * splitting bit set before __split_huge_page_refcount + * runs. Finding the same huge pmd more than once during the + * same rmap walk is not a problem. + */ + if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG && + pmd_trans_splitting(*pmd)) + goto out; + if (pmd_trans_huge(*pmd)) { + VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG && + !pmd_trans_splitting(*pmd)); + ret = pmd; + } +out: + return ret; +} + +static int __split_huge_page_splitting(struct page *page, + struct vm_area_struct *vma, + unsigned long address) +{ + struct mm_struct *mm = vma->vm_mm; + pmd_t *pmd; + int ret = 0; + + spin_lock(&mm->page_table_lock); + pmd = page_check_address_pmd(page, mm, address, + PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG); + if (pmd) { + /* + * We can't temporarily set the pmd to null in order + * to split it, the pmd must remain marked huge at all + * times or the VM won't take the pmd_trans_huge paths + * and it won't wait on the anon_vma->root->lock to + * serialize against split_huge_page*. + */ + pmdp_splitting_flush_notify(vma, address, pmd); + ret = 1; + } + spin_unlock(&mm->page_table_lock); + + return ret; +} + +static void __split_huge_page_refcount(struct page *page) +{ + int i; + unsigned long head_index = page->index; + struct zone *zone = page_zone(page); + int zonestat; + + /* prevent PageLRU to go away from under us, and freeze lru stats */ + spin_lock_irq(&zone->lru_lock); + compound_lock(page); + + for (i = 1; i < HPAGE_PMD_NR; i++) { + struct page *page_tail = page + i; + + /* tail_page->_count cannot change */ + atomic_sub(atomic_read(&page_tail->_count), &page->_count); + BUG_ON(page_count(page) <= 0); + atomic_add(page_mapcount(page) + 1, &page_tail->_count); + BUG_ON(atomic_read(&page_tail->_count) <= 0); + + /* after clearing PageTail the gup refcount can be released */ + smp_mb(); + + /* + * retain hwpoison flag of the poisoned tail page: + * fix for the unsuitable process killed on Guest Machine(KVM) + * by the memory-failure. + */ + page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON; + page_tail->flags |= (page->flags & + ((1L << PG_referenced) | + (1L << PG_swapbacked) | + (1L << PG_mlocked) | + (1L << PG_uptodate))); + page_tail->flags |= (1L << PG_dirty); + + /* + * 1) clear PageTail before overwriting first_page + * 2) clear PageTail before clearing PageHead for VM_BUG_ON + */ + smp_wmb(); + + /* + * __split_huge_page_splitting() already set the + * splitting bit in all pmd that could map this + * hugepage, that will ensure no CPU can alter the + * mapcount on the head page. The mapcount is only + * accounted in the head page and it has to be + * transferred to all tail pages in the below code. So + * for this code to be safe, the split the mapcount + * can't change. But that doesn't mean userland can't + * keep changing and reading the page contents while + * we transfer the mapcount, so the pmd splitting + * status is achieved setting a reserved bit in the + * pmd, not by clearing the present bit. + */ + BUG_ON(page_mapcount(page_tail)); + page_tail->_mapcount = page->_mapcount; + + BUG_ON(page_tail->mapping); + page_tail->mapping = page->mapping; + + page_tail->index = ++head_index; + + BUG_ON(!PageAnon(page_tail)); + BUG_ON(!PageUptodate(page_tail)); + BUG_ON(!PageDirty(page_tail)); + BUG_ON(!PageSwapBacked(page_tail)); + + mem_cgroup_split_huge_fixup(page, page_tail); + + lru_add_page_tail(zone, page, page_tail); + } + + __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + __mod_zone_page_state(zone, NR_ANON_PAGES, HPAGE_PMD_NR); + + /* + * A hugepage counts for HPAGE_PMD_NR pages on the LRU statistics, + * so adjust those appropriately if this page is on the LRU. + */ + if (PageLRU(page)) { + zonestat = NR_LRU_BASE + page_lru(page); + __mod_zone_page_state(zone, zonestat, -(HPAGE_PMD_NR-1)); + } + + ClearPageCompound(page); + compound_unlock(page); + spin_unlock_irq(&zone->lru_lock); + + for (i = 1; i < HPAGE_PMD_NR; i++) { + struct page *page_tail = page + i; + BUG_ON(page_count(page_tail) <= 0); + /* + * Tail pages may be freed if there wasn't any mapping + * like if add_to_swap() is running on a lru page that + * had its mapping zapped. And freeing these pages + * requires taking the lru_lock so we do the put_page + * of the tail pages after the split is complete. + */ + put_page(page_tail); + } + + /* + * Only the head page (now become a regular page) is required + * to be pinned by the caller. + */ + BUG_ON(page_count(page) <= 0); +} + +static int __split_huge_page_map(struct page *page, + struct vm_area_struct *vma, + unsigned long address) +{ + struct mm_struct *mm = vma->vm_mm; + pmd_t *pmd, _pmd; + int ret = 0, i; + pgtable_t pgtable; + unsigned long haddr; + + spin_lock(&mm->page_table_lock); + pmd = page_check_address_pmd(page, mm, address, + PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG); + if (pmd) { + pgtable = get_pmd_huge_pte(mm); + pmd_populate(mm, &_pmd, pgtable); + + for (i = 0, haddr = address; i < HPAGE_PMD_NR; + i++, haddr += PAGE_SIZE) { + pte_t *pte, entry; + BUG_ON(PageCompound(page+i)); + entry = mk_pte(page + i, vma->vm_page_prot); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (!pmd_write(*pmd)) + entry = pte_wrprotect(entry); + else + BUG_ON(page_mapcount(page) != 1); + if (!pmd_young(*pmd)) + entry = pte_mkold(entry); + pte = pte_offset_map(&_pmd, haddr); + BUG_ON(!pte_none(*pte)); + set_pte_at(mm, haddr, pte, entry); + pte_unmap(pte); + } + + mm->nr_ptes++; + smp_wmb(); /* make pte visible before pmd */ + /* + * Up to this point the pmd is present and huge and + * userland has the whole access to the hugepage + * during the split (which happens in place). If we + * overwrite the pmd with the not-huge version + * pointing to the pte here (which of course we could + * if all CPUs were bug free), userland could trigger + * a small page size TLB miss on the small sized TLB + * while the hugepage TLB entry is still established + * in the huge TLB. Some CPU doesn't like that. See + * http://support.amd.com/us/Processor_TechDocs/41322.pdf, + * Erratum 383 on page 93. Intel should be safe but is + * also warns that it's only safe if the permission + * and cache attributes of the two entries loaded in + * the two TLB is identical (which should be the case + * here). But it is generally safer to never allow + * small and huge TLB entries for the same virtual + * address to be loaded simultaneously. So instead of + * doing "pmd_populate(); flush_tlb_range();" we first + * mark the current pmd notpresent (atomically because + * here the pmd_trans_huge and pmd_trans_splitting + * must remain set at all times on the pmd until the + * split is complete for this pmd), then we flush the + * SMP TLB and finally we write the non-huge version + * of the pmd entry with pmd_populate. + */ + set_pmd_at(mm, address, pmd, pmd_mknotpresent(*pmd)); + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + pmd_populate(mm, pmd, pgtable); + ret = 1; + } + spin_unlock(&mm->page_table_lock); + + return ret; +} + +/* must be called with anon_vma->root->lock hold */ +static void __split_huge_page(struct page *page, + struct anon_vma *anon_vma) +{ + int mapcount, mapcount2; + struct anon_vma_chain *avc; + + BUG_ON(!PageHead(page)); + BUG_ON(PageTail(page)); + + mapcount = 0; + list_for_each_entry(avc, &anon_vma->head, same_anon_vma) { + struct vm_area_struct *vma = avc->vma; + unsigned long addr = vma_address(page, vma); + BUG_ON(is_vma_temporary_stack(vma)); + if (addr == -EFAULT) + continue; + mapcount += __split_huge_page_splitting(page, vma, addr); + } + /* + * It is critical that new vmas are added to the tail of the + * anon_vma list. This guarantes that if copy_huge_pmd() runs + * and establishes a child pmd before + * __split_huge_page_splitting() freezes the parent pmd (so if + * we fail to prevent copy_huge_pmd() from running until the + * whole __split_huge_page() is complete), we will still see + * the newly established pmd of the child later during the + * walk, to be able to set it as pmd_trans_splitting too. + */ + if (mapcount != page_mapcount(page)) + printk(KERN_ERR "mapcount %d page_mapcount %d\n", + mapcount, page_mapcount(page)); + BUG_ON(mapcount != page_mapcount(page)); + + __split_huge_page_refcount(page); + + mapcount2 = 0; + list_for_each_entry(avc, &anon_vma->head, same_anon_vma) { + struct vm_area_struct *vma = avc->vma; + unsigned long addr = vma_address(page, vma); + BUG_ON(is_vma_temporary_stack(vma)); + if (addr == -EFAULT) + continue; + mapcount2 += __split_huge_page_map(page, vma, addr); + } + if (mapcount != mapcount2) + printk(KERN_ERR "mapcount %d mapcount2 %d page_mapcount %d\n", + mapcount, mapcount2, page_mapcount(page)); + BUG_ON(mapcount != mapcount2); +} + +int split_huge_page(struct page *page) +{ + struct anon_vma *anon_vma; + int ret = 1; + + BUG_ON(!PageAnon(page)); + anon_vma = page_lock_anon_vma(page); + if (!anon_vma) + goto out; + ret = 0; + if (!PageCompound(page)) + goto out_unlock; + + BUG_ON(!PageSwapBacked(page)); + __split_huge_page(page, anon_vma); + + BUG_ON(PageCompound(page)); +out_unlock: + page_unlock_anon_vma(anon_vma); +out: + return ret; +} + +int hugepage_madvise(struct vm_area_struct *vma, + unsigned long *vm_flags, int advice) +{ + switch (advice) { + case MADV_HUGEPAGE: + /* + * Be somewhat over-protective like KSM for now! + */ + if (*vm_flags & (VM_HUGEPAGE | + VM_SHARED | VM_MAYSHARE | + VM_PFNMAP | VM_IO | VM_DONTEXPAND | + VM_RESERVED | VM_HUGETLB | VM_INSERTPAGE | + VM_MIXEDMAP | VM_SAO)) + return -EINVAL; + *vm_flags &= ~VM_NOHUGEPAGE; + *vm_flags |= VM_HUGEPAGE; + /* + * If the vma become good for khugepaged to scan, + * register it here without waiting a page fault that + * may not happen any time soon. + */ + if (unlikely(khugepaged_enter_vma_merge(vma))) + return -ENOMEM; + break; + case MADV_NOHUGEPAGE: + /* + * Be somewhat over-protective like KSM for now! + */ + if (*vm_flags & (VM_NOHUGEPAGE | + VM_SHARED | VM_MAYSHARE | + VM_PFNMAP | VM_IO | VM_DONTEXPAND | + VM_RESERVED | VM_HUGETLB | VM_INSERTPAGE | + VM_MIXEDMAP | VM_SAO)) + return -EINVAL; + *vm_flags &= ~VM_HUGEPAGE; + *vm_flags |= VM_NOHUGEPAGE; + /* + * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning + * this vma even if we leave the mm registered in khugepaged if + * it got registered before VM_NOHUGEPAGE was set. + */ + break; + } + + return 0; +} + +static int __init khugepaged_slab_init(void) +{ + mm_slot_cache = kmem_cache_create("khugepaged_mm_slot", + sizeof(struct mm_slot), + __alignof__(struct mm_slot), 0, NULL); + if (!mm_slot_cache) + return -ENOMEM; + + return 0; +} + +static void __init khugepaged_slab_free(void) +{ + kmem_cache_destroy(mm_slot_cache); + mm_slot_cache = NULL; +} + +static inline struct mm_slot *alloc_mm_slot(void) +{ + if (!mm_slot_cache) /* initialization failed */ + return NULL; + return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL); +} + +static inline void free_mm_slot(struct mm_slot *mm_slot) +{ + kmem_cache_free(mm_slot_cache, mm_slot); +} + +static int __init mm_slots_hash_init(void) +{ + mm_slots_hash = kzalloc(MM_SLOTS_HASH_HEADS * sizeof(struct hlist_head), + GFP_KERNEL); + if (!mm_slots_hash) + return -ENOMEM; + return 0; +} + +#if 0 +static void __init mm_slots_hash_free(void) +{ + kfree(mm_slots_hash); + mm_slots_hash = NULL; +} +#endif + +static struct mm_slot *get_mm_slot(struct mm_struct *mm) +{ + struct mm_slot *mm_slot; + struct hlist_head *bucket; + struct hlist_node *node; + + bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct)) + % MM_SLOTS_HASH_HEADS]; + hlist_for_each_entry(mm_slot, node, bucket, hash) { + if (mm == mm_slot->mm) + return mm_slot; + } + return NULL; +} + +static void insert_to_mm_slots_hash(struct mm_struct *mm, + struct mm_slot *mm_slot) +{ + struct hlist_head *bucket; + + bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct)) + % MM_SLOTS_HASH_HEADS]; + mm_slot->mm = mm; + hlist_add_head(&mm_slot->hash, bucket); +} + +static inline int khugepaged_test_exit(struct mm_struct *mm) +{ + return atomic_read(&mm->mm_users) == 0; +} + +int __khugepaged_enter(struct mm_struct *mm) +{ + struct mm_slot *mm_slot; + int wakeup; + + mm_slot = alloc_mm_slot(); + if (!mm_slot) + return -ENOMEM; + + /* __khugepaged_exit() must not run from under us */ + VM_BUG_ON(khugepaged_test_exit(mm)); + if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) { + free_mm_slot(mm_slot); + return 0; + } + + spin_lock(&khugepaged_mm_lock); + insert_to_mm_slots_hash(mm, mm_slot); + /* + * Insert just behind the scanning cursor, to let the area settle + * down a little. + */ + wakeup = list_empty(&khugepaged_scan.mm_head); + list_add_tail(&mm_slot->mm_node, &khugepaged_scan.mm_head); + spin_unlock(&khugepaged_mm_lock); + + atomic_inc(&mm->mm_count); + if (wakeup) + wake_up_interruptible(&khugepaged_wait); + + return 0; +} + +int khugepaged_enter_vma_merge(struct vm_area_struct *vma) +{ + unsigned long hstart, hend; + if (!vma->anon_vma) + /* + * Not yet faulted in so we will register later in the + * page fault if needed. + */ + return 0; + if (vma->vm_file || vma->vm_ops) + /* khugepaged not yet working on file or special mappings */ + return 0; + VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma)); + hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; + hend = vma->vm_end & HPAGE_PMD_MASK; + if (hstart < hend) + return khugepaged_enter(vma); + return 0; +} + +void __khugepaged_exit(struct mm_struct *mm) +{ + struct mm_slot *mm_slot; + int free = 0; + + spin_lock(&khugepaged_mm_lock); + mm_slot = get_mm_slot(mm); + if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { + hlist_del(&mm_slot->hash); + list_del(&mm_slot->mm_node); + free = 1; + } + + if (free) { + spin_unlock(&khugepaged_mm_lock); + clear_bit(MMF_VM_HUGEPAGE, &mm->flags); + free_mm_slot(mm_slot); + mmdrop(mm); + } else if (mm_slot) { + spin_unlock(&khugepaged_mm_lock); + /* + * This is required to serialize against + * khugepaged_test_exit() (which is guaranteed to run + * under mmap sem read mode). Stop here (after we + * return all pagetables will be destroyed) until + * khugepaged has finished working on the pagetables + * under the mmap_sem. + */ + down_write(&mm->mmap_sem); + up_write(&mm->mmap_sem); + } else + spin_unlock(&khugepaged_mm_lock); +} + +static void release_pte_page(struct page *page) +{ + /* 0 stands for page_is_file_cache(page) == false */ + dec_zone_page_state(page, NR_ISOLATED_ANON + 0); + unlock_page(page); + putback_lru_page(page); +} + +static void release_pte_pages(pte_t *pte, pte_t *_pte) +{ + while (--_pte >= pte) { + pte_t pteval = *_pte; + if (!pte_none(pteval)) + release_pte_page(pte_page(pteval)); + } +} + +static void release_all_pte_pages(pte_t *pte) +{ + release_pte_pages(pte, pte + HPAGE_PMD_NR); +} + +static int __collapse_huge_page_isolate(struct vm_area_struct *vma, + unsigned long address, + pte_t *pte) +{ + struct page *page; + pte_t *_pte; + int referenced = 0, isolated = 0, none = 0; + for (_pte = pte; _pte < pte+HPAGE_PMD_NR; + _pte++, address += PAGE_SIZE) { + pte_t pteval = *_pte; + if (pte_none(pteval)) { + if (++none <= khugepaged_max_ptes_none) + continue; + else { + release_pte_pages(pte, _pte); + goto out; + } + } + if (!pte_present(pteval) || !pte_write(pteval)) { + release_pte_pages(pte, _pte); + goto out; + } + page = vm_normal_page(vma, address, pteval); + if (unlikely(!page)) { + release_pte_pages(pte, _pte); + goto out; + } + VM_BUG_ON(PageCompound(page)); + BUG_ON(!PageAnon(page)); + VM_BUG_ON(!PageSwapBacked(page)); + + /* cannot use mapcount: can't collapse if there's a gup pin */ + if (page_count(page) != 1) { + release_pte_pages(pte, _pte); + goto out; + } + /* + * We can do it before isolate_lru_page because the + * page can't be freed from under us. NOTE: PG_lock + * is needed to serialize against split_huge_page + * when invoked from the VM. + */ + if (!trylock_page(page)) { + release_pte_pages(pte, _pte); + goto out; + } + /* + * Isolate the page to avoid collapsing an hugepage + * currently in use by the VM. + */ + if (isolate_lru_page(page)) { + unlock_page(page); + release_pte_pages(pte, _pte); + goto out; + } + /* 0 stands for page_is_file_cache(page) == false */ + inc_zone_page_state(page, NR_ISOLATED_ANON + 0); + VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON(PageLRU(page)); + + /* If there is no mapped pte young don't collapse the page */ + if (pte_young(pteval) || PageReferenced(page) || + mmu_notifier_test_young(vma->vm_mm, address)) + referenced = 1; + } + if (unlikely(!referenced)) + release_all_pte_pages(pte); + else + isolated = 1; +out: + return isolated; +} + +static void __collapse_huge_page_copy(pte_t *pte, struct page *page, + struct vm_area_struct *vma, + unsigned long address, + spinlock_t *ptl) +{ + pte_t *_pte; + for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++) { + pte_t pteval = *_pte; + struct page *src_page; + + if (pte_none(pteval)) { + clear_user_highpage(page, address); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); + } else { + src_page = pte_page(pteval); + copy_user_highpage(page, src_page, address, vma); + VM_BUG_ON(page_mapcount(src_page) != 1); + VM_BUG_ON(page_count(src_page) != 2); + release_pte_page(src_page); + /* + * ptl mostly unnecessary, but preempt has to + * be disabled to update the per-cpu stats + * inside page_remove_rmap(). + */ + spin_lock(ptl); + /* + * paravirt calls inside pte_clear here are + * superfluous. + */ + pte_clear(vma->vm_mm, address, _pte); + page_remove_rmap(src_page); + spin_unlock(ptl); + free_page_and_swap_cache(src_page); + } + + address += PAGE_SIZE; + page++; + } +} + +static void collapse_huge_page(struct mm_struct *mm, + unsigned long address, + struct page **hpage, + struct vm_area_struct *vma) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd, _pmd; + pte_t *pte; + pgtable_t pgtable; + struct page *new_page; + spinlock_t *ptl; + int isolated; + unsigned long hstart, hend; + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); +#ifndef CONFIG_NUMA + VM_BUG_ON(!*hpage); + new_page = *hpage; +#else + VM_BUG_ON(*hpage); + /* + * Allocate the page while the vma is still valid and under + * the mmap_sem read mode so there is no memory allocation + * later when we take the mmap_sem in write mode. This is more + * friendly behavior (OTOH it may actually hide bugs) to + * filesystems in userland with daemons allocating memory in + * the userland I/O paths. Allocating memory with the + * mmap_sem in read mode is good idea also to allow greater + * scalability. + */ + new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address); + if (unlikely(!new_page)) { + up_read(&mm->mmap_sem); + *hpage = ERR_PTR(-ENOMEM); + return; + } +#endif + if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { + up_read(&mm->mmap_sem); + put_page(new_page); + return; + } + + /* after allocating the hugepage upgrade to mmap_sem write mode */ + up_read(&mm->mmap_sem); + + /* + * Prevent all access to pagetables with the exception of + * gup_fast later hanlded by the ptep_clear_flush and the VM + * handled by the anon_vma lock + PG_lock. + */ + down_write(&mm->mmap_sem); + if (unlikely(khugepaged_test_exit(mm))) + goto out; + + vma = find_vma(mm, address); + hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; + hend = vma->vm_end & HPAGE_PMD_MASK; + if (address < hstart || address + HPAGE_PMD_SIZE > hend) + goto out; + + if ((!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) || + (vma->vm_flags & VM_NOHUGEPAGE)) + goto out; + + /* VM_PFNMAP vmas may have vm_ops null but vm_file set */ + if (!vma->anon_vma || vma->vm_ops || vma->vm_file) + goto out; + if (is_vma_temporary_stack(vma)) + goto out; + VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma)); + + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + goto out; + + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + goto out; + + pmd = pmd_offset(pud, address); + /* pmd can't go away or become huge under us */ + if (!pmd_present(*pmd) || pmd_trans_huge(*pmd)) + goto out; + + anon_vma_lock(vma->anon_vma); + + pte = pte_offset_map(pmd, address); + ptl = pte_lockptr(mm, pmd); + + spin_lock(&mm->page_table_lock); /* probably unnecessary */ + /* + * After this gup_fast can't run anymore. This also removes + * any huge TLB entry from the CPU so we won't allow + * huge and small TLB entries for the same virtual address + * to avoid the risk of CPU bugs in that area. + */ + _pmd = pmdp_clear_flush_notify(vma, address, pmd); + spin_unlock(&mm->page_table_lock); + + spin_lock(ptl); + isolated = __collapse_huge_page_isolate(vma, address, pte); + spin_unlock(ptl); + + if (unlikely(!isolated)) { + pte_unmap(pte); + spin_lock(&mm->page_table_lock); + BUG_ON(!pmd_none(*pmd)); + set_pmd_at(mm, address, pmd, _pmd); + spin_unlock(&mm->page_table_lock); + anon_vma_unlock(vma->anon_vma); + goto out; + } + + /* + * All pages are isolated and locked so anon_vma rmap + * can't run anymore. + */ + anon_vma_unlock(vma->anon_vma); + + __collapse_huge_page_copy(pte, new_page, vma, address, ptl); + pte_unmap(pte); + __SetPageUptodate(new_page); + pgtable = pmd_pgtable(_pmd); + VM_BUG_ON(page_count(pgtable) != 1); + VM_BUG_ON(page_mapcount(pgtable) != 0); + + _pmd = mk_pmd(new_page, vma->vm_page_prot); + _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); + _pmd = pmd_mkhuge(_pmd); + + /* + * spin_lock() below is not the equivalent of smp_wmb(), so + * this is needed to avoid the copy_huge_page writes to become + * visible after the set_pmd_at() write. + */ + smp_wmb(); + + spin_lock(&mm->page_table_lock); + BUG_ON(!pmd_none(*pmd)); + page_add_new_anon_rmap(new_page, vma, address); + set_pmd_at(mm, address, pmd, _pmd); + update_mmu_cache(vma, address, entry); + prepare_pmd_huge_pte(pgtable, mm); + mm->nr_ptes--; + spin_unlock(&mm->page_table_lock); + +#ifndef CONFIG_NUMA + *hpage = NULL; +#endif + khugepaged_pages_collapsed++; +out_up_write: + up_write(&mm->mmap_sem); + return; + +out: + mem_cgroup_uncharge_page(new_page); +#ifdef CONFIG_NUMA + put_page(new_page); +#endif + goto out_up_write; +} + +static int khugepaged_scan_pmd(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long address, + struct page **hpage) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte, *_pte; + int ret = 0, referenced = 0, none = 0; + struct page *page; + unsigned long _address; + spinlock_t *ptl; + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + goto out; + + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + goto out; + + pmd = pmd_offset(pud, address); + if (!pmd_present(*pmd) || pmd_trans_huge(*pmd)) + goto out; + + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR; + _pte++, _address += PAGE_SIZE) { + pte_t pteval = *_pte; + if (pte_none(pteval)) { + if (++none <= khugepaged_max_ptes_none) + continue; + else + goto out_unmap; + } + if (!pte_present(pteval) || !pte_write(pteval)) + goto out_unmap; + page = vm_normal_page(vma, _address, pteval); + if (unlikely(!page)) + goto out_unmap; + VM_BUG_ON(PageCompound(page)); + if (!PageLRU(page) || PageLocked(page) || !PageAnon(page)) + goto out_unmap; + /* cannot use mapcount: can't collapse if there's a gup pin */ + if (page_count(page) != 1) + goto out_unmap; + if (pte_young(pteval) || PageReferenced(page) || + mmu_notifier_test_young(vma->vm_mm, address)) + referenced = 1; + } + if (referenced) + ret = 1; +out_unmap: + pte_unmap_unlock(pte, ptl); + if (ret) + /* collapse_huge_page will return with the mmap_sem released */ + collapse_huge_page(mm, address, hpage, vma); +out: + return ret; +} + +static void collect_mm_slot(struct mm_slot *mm_slot) +{ + struct mm_struct *mm = mm_slot->mm; + + VM_BUG_ON(!spin_is_locked(&khugepaged_mm_lock)); + + if (khugepaged_test_exit(mm)) { + /* free mm_slot */ + hlist_del(&mm_slot->hash); + list_del(&mm_slot->mm_node); + + /* + * Not strictly needed because the mm exited already. + * + * clear_bit(MMF_VM_HUGEPAGE, &mm->flags); + */ + + /* khugepaged_mm_lock actually not necessary for the below */ + free_mm_slot(mm_slot); + mmdrop(mm); + } +} + +static unsigned int khugepaged_scan_mm_slot(unsigned int pages, + struct page **hpage) +{ + struct mm_slot *mm_slot; + struct mm_struct *mm; + struct vm_area_struct *vma; + int progress = 0; + + VM_BUG_ON(!pages); + VM_BUG_ON(!spin_is_locked(&khugepaged_mm_lock)); + + if (khugepaged_scan.mm_slot) + mm_slot = khugepaged_scan.mm_slot; + else { + mm_slot = list_entry(khugepaged_scan.mm_head.next, + struct mm_slot, mm_node); + khugepaged_scan.address = 0; + khugepaged_scan.mm_slot = mm_slot; + } + spin_unlock(&khugepaged_mm_lock); + + mm = mm_slot->mm; + down_read(&mm->mmap_sem); + if (unlikely(khugepaged_test_exit(mm))) + vma = NULL; + else + vma = find_vma(mm, khugepaged_scan.address); + + progress++; + for (; vma; vma = vma->vm_next) { + unsigned long hstart, hend; + + cond_resched(); + if (unlikely(khugepaged_test_exit(mm))) { + progress++; + break; + } + + if ((!(vma->vm_flags & VM_HUGEPAGE) && + !khugepaged_always()) || + (vma->vm_flags & VM_NOHUGEPAGE)) { + skip: + progress++; + continue; + } + /* VM_PFNMAP vmas may have vm_ops null but vm_file set */ + if (!vma->anon_vma || vma->vm_ops || vma->vm_file) + goto skip; + if (is_vma_temporary_stack(vma)) + goto skip; + + VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma)); + + hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; + hend = vma->vm_end & HPAGE_PMD_MASK; + if (hstart >= hend) + goto skip; + if (khugepaged_scan.address > hend) + goto skip; + if (khugepaged_scan.address < hstart) + khugepaged_scan.address = hstart; + VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); + + while (khugepaged_scan.address < hend) { + int ret; + cond_resched(); + if (unlikely(khugepaged_test_exit(mm))) + goto breakouterloop; + + VM_BUG_ON(khugepaged_scan.address < hstart || + khugepaged_scan.address + HPAGE_PMD_SIZE > + hend); + ret = khugepaged_scan_pmd(mm, vma, + khugepaged_scan.address, + hpage); + /* move to next address */ + khugepaged_scan.address += HPAGE_PMD_SIZE; + progress += HPAGE_PMD_NR; + if (ret) + /* we released mmap_sem so break loop */ + goto breakouterloop_mmap_sem; + if (progress >= pages) + goto breakouterloop; + } + } +breakouterloop: + up_read(&mm->mmap_sem); /* exit_mmap will destroy ptes after this */ +breakouterloop_mmap_sem: + + spin_lock(&khugepaged_mm_lock); + VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot); + /* + * Release the current mm_slot if this mm is about to die, or + * if we scanned all vmas of this mm. + */ + if (khugepaged_test_exit(mm) || !vma) { + /* + * Make sure that if mm_users is reaching zero while + * khugepaged runs here, khugepaged_exit will find + * mm_slot not pointing to the exiting mm. + */ + if (mm_slot->mm_node.next != &khugepaged_scan.mm_head) { + khugepaged_scan.mm_slot = list_entry( + mm_slot->mm_node.next, + struct mm_slot, mm_node); + khugepaged_scan.address = 0; + } else { + khugepaged_scan.mm_slot = NULL; + khugepaged_full_scans++; + } + + collect_mm_slot(mm_slot); + } + + return progress; +} + +static int khugepaged_has_work(void) +{ + return !list_empty(&khugepaged_scan.mm_head) && + khugepaged_enabled(); +} + +static int khugepaged_wait_event(void) +{ + return !list_empty(&khugepaged_scan.mm_head) || + !khugepaged_enabled(); +} + +static void khugepaged_do_scan(struct page **hpage) +{ + unsigned int progress = 0, pass_through_head = 0; + unsigned int pages = khugepaged_pages_to_scan; + + barrier(); /* write khugepaged_pages_to_scan to local stack */ + + while (progress < pages) { + cond_resched(); + +#ifndef CONFIG_NUMA + if (!*hpage) { + *hpage = alloc_hugepage(khugepaged_defrag()); + if (unlikely(!*hpage)) + break; + } +#else + if (IS_ERR(*hpage)) + break; +#endif + + if (unlikely(kthread_should_stop() || freezing(current))) + break; + + spin_lock(&khugepaged_mm_lock); + if (!khugepaged_scan.mm_slot) + pass_through_head++; + if (khugepaged_has_work() && + pass_through_head < 2) + progress += khugepaged_scan_mm_slot(pages - progress, + hpage); + else + progress = pages; + spin_unlock(&khugepaged_mm_lock); + } +} + +static void khugepaged_alloc_sleep(void) +{ + DEFINE_WAIT(wait); + add_wait_queue(&khugepaged_wait, &wait); + schedule_timeout_interruptible( + msecs_to_jiffies( + khugepaged_alloc_sleep_millisecs)); + remove_wait_queue(&khugepaged_wait, &wait); +} + +#ifndef CONFIG_NUMA +static struct page *khugepaged_alloc_hugepage(void) +{ + struct page *hpage; + + do { + hpage = alloc_hugepage(khugepaged_defrag()); + if (!hpage) + khugepaged_alloc_sleep(); + } while (unlikely(!hpage) && + likely(khugepaged_enabled())); + return hpage; +} +#endif + +static void khugepaged_loop(void) +{ + struct page *hpage; + +#ifdef CONFIG_NUMA + hpage = NULL; +#endif + while (likely(khugepaged_enabled())) { +#ifndef CONFIG_NUMA + hpage = khugepaged_alloc_hugepage(); + if (unlikely(!hpage)) + break; +#else + if (IS_ERR(hpage)) { + khugepaged_alloc_sleep(); + hpage = NULL; + } +#endif + + khugepaged_do_scan(&hpage); +#ifndef CONFIG_NUMA + if (hpage) + put_page(hpage); +#endif + try_to_freeze(); + if (unlikely(kthread_should_stop())) + break; + if (khugepaged_has_work()) { + DEFINE_WAIT(wait); + if (!khugepaged_scan_sleep_millisecs) + continue; + add_wait_queue(&khugepaged_wait, &wait); + schedule_timeout_interruptible( + msecs_to_jiffies( + khugepaged_scan_sleep_millisecs)); + remove_wait_queue(&khugepaged_wait, &wait); + } else if (khugepaged_enabled()) + wait_event_freezable(khugepaged_wait, + khugepaged_wait_event()); + } +} + +static int khugepaged(void *none) +{ + struct mm_slot *mm_slot; + + set_freezable(); + set_user_nice(current, 19); + + /* serialize with start_khugepaged() */ + mutex_lock(&khugepaged_mutex); + + for (;;) { + mutex_unlock(&khugepaged_mutex); + VM_BUG_ON(khugepaged_thread != current); + khugepaged_loop(); + VM_BUG_ON(khugepaged_thread != current); + + mutex_lock(&khugepaged_mutex); + if (!khugepaged_enabled()) + break; + if (unlikely(kthread_should_stop())) + break; + } + + spin_lock(&khugepaged_mm_lock); + mm_slot = khugepaged_scan.mm_slot; + khugepaged_scan.mm_slot = NULL; + if (mm_slot) + collect_mm_slot(mm_slot); + spin_unlock(&khugepaged_mm_lock); + + khugepaged_thread = NULL; + mutex_unlock(&khugepaged_mutex); + + return 0; +} + +void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd) +{ + struct page *page; + + spin_lock(&mm->page_table_lock); + if (unlikely(!pmd_trans_huge(*pmd))) { + spin_unlock(&mm->page_table_lock); + return; + } + page = pmd_page(*pmd); + VM_BUG_ON(!page_count(page)); + get_page(page); + spin_unlock(&mm->page_table_lock); + + split_huge_page(page); + + put_page(page); + BUG_ON(pmd_trans_huge(*pmd)); +} + +static void split_huge_page_address(struct mm_struct *mm, + unsigned long address) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + + VM_BUG_ON(!(address & ~HPAGE_PMD_MASK)); + + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + return; + + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + return; + + pmd = pmd_offset(pud, address); + if (!pmd_present(*pmd)) + return; + /* + * Caller holds the mmap_sem write mode, so a huge pmd cannot + * materialize from under us. + */ + split_huge_page_pmd(mm, pmd); +} + +void __vma_adjust_trans_huge(struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + long adjust_next) +{ + /* + * If the new start address isn't hpage aligned and it could + * previously contain an hugepage: check if we need to split + * an huge pmd. + */ + if (start & ~HPAGE_PMD_MASK && + (start & HPAGE_PMD_MASK) >= vma->vm_start && + (start & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end) + split_huge_page_address(vma->vm_mm, start); + + /* + * If the new end address isn't hpage aligned and it could + * previously contain an hugepage: check if we need to split + * an huge pmd. + */ + if (end & ~HPAGE_PMD_MASK && + (end & HPAGE_PMD_MASK) >= vma->vm_start && + (end & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end) + split_huge_page_address(vma->vm_mm, end); + + /* + * If we're also updating the vma->vm_next->vm_start, if the new + * vm_next->vm_start isn't page aligned and it could previously + * contain an hugepage: check if we need to split an huge pmd. + */ + if (adjust_next > 0) { + struct vm_area_struct *next = vma->vm_next; + unsigned long nstart = next->vm_start; + nstart += adjust_next << PAGE_SHIFT; + if (nstart & ~HPAGE_PMD_MASK && + (nstart & HPAGE_PMD_MASK) >= next->vm_start && + (nstart & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= next->vm_end) + split_huge_page_address(next->vm_mm, nstart); + } +} diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 85855240933..bb0b7c12801 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -394,71 +394,6 @@ static int vma_has_reserves(struct vm_area_struct *vma) return 0; } -static void clear_gigantic_page(struct page *page, - unsigned long addr, unsigned long sz) -{ - int i; - struct page *p = page; - - might_sleep(); - for (i = 0; i < sz/PAGE_SIZE; i++, p = mem_map_next(p, page, i)) { - cond_resched(); - clear_user_highpage(p, addr + i * PAGE_SIZE); - } -} -static void clear_huge_page(struct page *page, - unsigned long addr, unsigned long sz) -{ - int i; - - if (unlikely(sz/PAGE_SIZE > MAX_ORDER_NR_PAGES)) { - clear_gigantic_page(page, addr, sz); - return; - } - - might_sleep(); - for (i = 0; i < sz/PAGE_SIZE; i++) { - cond_resched(); - clear_user_highpage(page + i, addr + i * PAGE_SIZE); - } -} - -static void copy_user_gigantic_page(struct page *dst, struct page *src, - unsigned long addr, struct vm_area_struct *vma) -{ - int i; - struct hstate *h = hstate_vma(vma); - struct page *dst_base = dst; - struct page *src_base = src; - - for (i = 0; i < pages_per_huge_page(h); ) { - cond_resched(); - copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); - - i++; - dst = mem_map_next(dst, dst_base, i); - src = mem_map_next(src, src_base, i); - } -} - -static void copy_user_huge_page(struct page *dst, struct page *src, - unsigned long addr, struct vm_area_struct *vma) -{ - int i; - struct hstate *h = hstate_vma(vma); - - if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) { - copy_user_gigantic_page(dst, src, addr, vma); - return; - } - - might_sleep(); - for (i = 0; i < pages_per_huge_page(h); i++) { - cond_resched(); - copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma); - } -} - static void copy_gigantic_page(struct page *dst, struct page *src) { int i; @@ -1428,6 +1363,7 @@ static ssize_t nr_hugepages_show_common(struct kobject *kobj, return sprintf(buf, "%lu\n", nr_huge_pages); } + static ssize_t nr_hugepages_store_common(bool obey_mempolicy, struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) @@ -1440,9 +1376,14 @@ static ssize_t nr_hugepages_store_common(bool obey_mempolicy, err = strict_strtoul(buf, 10, &count); if (err) - return 0; + goto out; h = kobj_to_hstate(kobj, &nid); + if (h->order >= MAX_ORDER) { + err = -EINVAL; + goto out; + } + if (nid == NUMA_NO_NODE) { /* * global hstate attribute @@ -1468,6 +1409,9 @@ static ssize_t nr_hugepages_store_common(bool obey_mempolicy, NODEMASK_FREE(nodes_allowed); return len; +out: + NODEMASK_FREE(nodes_allowed); + return err; } static ssize_t nr_hugepages_show(struct kobject *kobj, @@ -1510,6 +1454,7 @@ static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj, struct hstate *h = kobj_to_hstate(kobj, NULL); return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages); } + static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { @@ -1517,9 +1462,12 @@ static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, unsigned long input; struct hstate *h = kobj_to_hstate(kobj, NULL); + if (h->order >= MAX_ORDER) + return -EINVAL; + err = strict_strtoul(buf, 10, &input); if (err) - return 0; + return err; spin_lock(&hugetlb_lock); h->nr_overcommit_huge_pages = input; @@ -1922,13 +1870,19 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, { struct hstate *h = &default_hstate; unsigned long tmp; + int ret; if (!write) tmp = h->max_huge_pages; + if (write && h->order >= MAX_ORDER) + return -EINVAL; + table->data = &tmp; table->maxlen = sizeof(unsigned long); - proc_doulongvec_minmax(table, write, buffer, length, ppos); + ret = proc_doulongvec_minmax(table, write, buffer, length, ppos); + if (ret) + goto out; if (write) { NODEMASK_ALLOC(nodemask_t, nodes_allowed, @@ -1943,8 +1897,8 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, if (nodes_allowed != &node_states[N_HIGH_MEMORY]) NODEMASK_FREE(nodes_allowed); } - - return 0; +out: + return ret; } int hugetlb_sysctl_handler(struct ctl_table *table, int write, @@ -1982,21 +1936,27 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, { struct hstate *h = &default_hstate; unsigned long tmp; + int ret; if (!write) tmp = h->nr_overcommit_huge_pages; + if (write && h->order >= MAX_ORDER) + return -EINVAL; + table->data = &tmp; table->maxlen = sizeof(unsigned long); - proc_doulongvec_minmax(table, write, buffer, length, ppos); + ret = proc_doulongvec_minmax(table, write, buffer, length, ppos); + if (ret) + goto out; if (write) { spin_lock(&hugetlb_lock); h->nr_overcommit_huge_pages = tmp; spin_unlock(&hugetlb_lock); } - - return 0; +out: + return ret; } #endif /* CONFIG_SYSCTL */ @@ -2454,7 +2414,8 @@ retry_avoidcopy: return VM_FAULT_OOM; } - copy_user_huge_page(new_page, old_page, address, vma); + copy_user_huge_page(new_page, old_page, address, vma, + pages_per_huge_page(h)); __SetPageUptodate(new_page); /* @@ -2558,7 +2519,7 @@ retry: ret = -PTR_ERR(page); goto out; } - clear_huge_page(page, address, huge_page_size(h)); + clear_huge_page(page, address, pages_per_huge_page(h)); __SetPageUptodate(page); if (vma->vm_flags & VM_MAYSHARE) { diff --git a/mm/internal.h b/mm/internal.h index dedb0aff673..69488205723 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -134,6 +134,10 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page) } } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern unsigned long vma_address(struct page *page, + struct vm_area_struct *vma); +#endif #else /* !CONFIG_MMU */ static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p) { @@ -243,7 +247,8 @@ static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn, int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int len, unsigned int foll_flags, - struct page **pages, struct vm_area_struct **vmas); + struct page **pages, struct vm_area_struct **vmas, + int *nonblocking); #define ZONE_RECLAIM_NOSCAN -2 #define ZONE_RECLAIM_FULL -1 diff --git a/mm/kmemleak-test.c b/mm/kmemleak-test.c index 177a5169bbd..ff0d9779cec 100644 --- a/mm/kmemleak-test.c +++ b/mm/kmemleak-test.c @@ -75,13 +75,11 @@ static int __init kmemleak_test_init(void) * after the module is removed. */ for (i = 0; i < 10; i++) { - elem = kmalloc(sizeof(*elem), GFP_KERNEL); - pr_info("kmemleak: kmalloc(sizeof(*elem)) = %p\n", elem); + elem = kzalloc(sizeof(*elem), GFP_KERNEL); + pr_info("kmemleak: kzalloc(sizeof(*elem)) = %p\n", elem); if (!elem) return -ENOMEM; - memset(elem, 0, sizeof(*elem)); INIT_LIST_HEAD(&elem->list); - list_add_tail(&elem->list, &test_list); } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index bd9bc214091..84225f3b719 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -113,7 +113,9 @@ #define BYTES_PER_POINTER sizeof(void *) /* GFP bitmask for kmemleak internal allocations */ -#define GFP_KMEMLEAK_MASK (GFP_KERNEL | GFP_ATOMIC) +#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \ + __GFP_NORETRY | __GFP_NOMEMALLOC | \ + __GFP_NOWARN) /* scanning area inside a memory block */ struct kmemleak_scan_area { @@ -511,9 +513,10 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, struct kmemleak_object *object; struct prio_tree_node *node; - object = kmem_cache_alloc(object_cache, gfp & GFP_KMEMLEAK_MASK); + object = kmem_cache_alloc(object_cache, gfp_kmemleak_mask(gfp)); if (!object) { - kmemleak_stop("Cannot allocate a kmemleak_object structure\n"); + pr_warning("Cannot allocate a kmemleak_object structure\n"); + kmemleak_disable(); return NULL; } @@ -734,9 +737,9 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp) return; } - area = kmem_cache_alloc(scan_area_cache, gfp & GFP_KMEMLEAK_MASK); + area = kmem_cache_alloc(scan_area_cache, gfp_kmemleak_mask(gfp)); if (!area) { - kmemleak_warn("Cannot allocate a scan area\n"); + pr_warning("Cannot allocate a scan area\n"); goto out; } @@ -34,6 +34,7 @@ #include <linux/swap.h> #include <linux/ksm.h> #include <linux/hash.h> +#include <linux/freezer.h> #include <asm/tlbflush.h> #include "internal.h" @@ -411,6 +412,20 @@ out: up_read(&mm->mmap_sem); } +static struct page *page_trans_compound_anon(struct page *page) +{ + if (PageTransCompound(page)) { + struct page *head = compound_trans_head(page); + /* + * head may actually be splitted and freed from under + * us but it's ok here. + */ + if (PageAnon(head)) + return head; + } + return NULL; +} + static struct page *get_mergeable_page(struct rmap_item *rmap_item) { struct mm_struct *mm = rmap_item->mm; @@ -430,7 +445,7 @@ static struct page *get_mergeable_page(struct rmap_item *rmap_item) page = follow_page(vma, addr, FOLL_GET); if (IS_ERR_OR_NULL(page)) goto out; - if (PageAnon(page)) { + if (PageAnon(page) || page_trans_compound_anon(page)) { flush_anon_page(vma, page, addr); flush_dcache_page(page); } else { @@ -708,6 +723,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, if (addr == -EFAULT) goto out; + BUG_ON(PageTransCompound(page)); ptep = page_check_address(page, mm, addr, &ptl, 0); if (!ptep) goto out; @@ -783,6 +799,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, goto out; pmd = pmd_offset(pud, addr); + BUG_ON(pmd_trans_huge(*pmd)); if (!pmd_present(*pmd)) goto out; @@ -800,6 +817,8 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot)); page_remove_rmap(page); + if (!page_mapped(page)) + try_to_free_swap(page); put_page(page); pte_unmap_unlock(ptep, ptl); @@ -808,6 +827,33 @@ out: return err; } +static int page_trans_compound_anon_split(struct page *page) +{ + int ret = 0; + struct page *transhuge_head = page_trans_compound_anon(page); + if (transhuge_head) { + /* Get the reference on the head to split it. */ + if (get_page_unless_zero(transhuge_head)) { + /* + * Recheck we got the reference while the head + * was still anonymous. + */ + if (PageAnon(transhuge_head)) + ret = split_huge_page(transhuge_head); + else + /* + * Retry later if split_huge_page run + * from under us. + */ + ret = 1; + put_page(transhuge_head); + } else + /* Retry later if split_huge_page run from under us. */ + ret = 1; + } + return ret; +} + /* * try_to_merge_one_page - take two pages and merge them into one * @vma: the vma that holds the pte pointing to page @@ -828,6 +874,9 @@ static int try_to_merge_one_page(struct vm_area_struct *vma, if (!(vma->vm_flags & VM_MERGEABLE)) goto out; + if (PageTransCompound(page) && page_trans_compound_anon_split(page)) + goto out; + BUG_ON(PageTransCompound(page)); if (!PageAnon(page)) goto out; @@ -1247,6 +1296,18 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page) slot = ksm_scan.mm_slot; if (slot == &ksm_mm_head) { + /* + * A number of pages can hang around indefinitely on per-cpu + * pagevecs, raised page count preventing write_protect_page + * from merging them. Though it doesn't really matter much, + * it is puzzling to see some stuck in pages_volatile until + * other activity jostles them out, and they also prevented + * LTP's KSM test from succeeding deterministically; so drain + * them here (here rather than on entry to ksm_do_scan(), + * so we don't IPI too often when pages_to_scan is set low). + */ + lru_add_drain_all(); + root_unstable_tree = RB_ROOT; spin_lock(&ksm_mmlist_lock); @@ -1277,7 +1338,13 @@ next_mm: if (ksm_test_exit(mm)) break; *page = follow_page(vma, ksm_scan.address, FOLL_GET); - if (!IS_ERR_OR_NULL(*page) && PageAnon(*page)) { + if (IS_ERR_OR_NULL(*page)) { + ksm_scan.address += PAGE_SIZE; + cond_resched(); + continue; + } + if (PageAnon(*page) || + page_trans_compound_anon(*page)) { flush_anon_page(vma, *page, ksm_scan.address); flush_dcache_page(*page); rmap_item = get_next_rmap_item(slot, @@ -1291,8 +1358,7 @@ next_mm: up_read(&mm->mmap_sem); return rmap_item; } - if (!IS_ERR_OR_NULL(*page)) - put_page(*page); + put_page(*page); ksm_scan.address += PAGE_SIZE; cond_resched(); } @@ -1352,7 +1418,7 @@ static void ksm_do_scan(unsigned int scan_npages) struct rmap_item *rmap_item; struct page *uninitialized_var(page); - while (scan_npages--) { + while (scan_npages-- && likely(!freezing(current))) { cond_resched(); rmap_item = scan_get_next_rmap_item(&page); if (!rmap_item) @@ -1370,6 +1436,7 @@ static int ksmd_should_run(void) static int ksm_scan_thread(void *nothing) { + set_freezable(); set_user_nice(current, 5); while (!kthread_should_stop()) { @@ -1378,11 +1445,13 @@ static int ksm_scan_thread(void *nothing) ksm_do_scan(ksm_thread_pages_to_scan); mutex_unlock(&ksm_thread_mutex); + try_to_freeze(); + if (ksmd_should_run()) { schedule_timeout_interruptible( msecs_to_jiffies(ksm_thread_sleep_millisecs)); } else { - wait_event_interruptible(ksm_thread_wait, + wait_event_freezable(ksm_thread_wait, ksmd_should_run() || kthread_should_stop()); } } diff --git a/mm/madvise.c b/mm/madvise.c index 319528b8db7..2221491ed50 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -71,6 +71,12 @@ static long madvise_behavior(struct vm_area_struct * vma, if (error) goto out; break; + case MADV_HUGEPAGE: + case MADV_NOHUGEPAGE: + error = hugepage_madvise(vma, &new_flags, behavior); + if (error) + goto out; + break; } if (new_flags == vma->vm_flags) { @@ -283,6 +289,10 @@ madvise_behavior_valid(int behavior) case MADV_MERGEABLE: case MADV_UNMERGEABLE: #endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + case MADV_HUGEPAGE: + case MADV_NOHUGEPAGE: +#endif return 1; default: diff --git a/mm/memblock.c b/mm/memblock.c index 400dc62697d..4618fda975a 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -137,8 +137,6 @@ static phys_addr_t __init_memblock memblock_find_base(phys_addr_t size, BUG_ON(0 == size); - size = memblock_align_up(size, align); - /* Pump up max_addr */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE) end = memblock.current_limit; @@ -683,13 +681,13 @@ int __init_memblock memblock_is_memory(phys_addr_t addr) int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size) { - int idx = memblock_search(&memblock.reserved, base); + int idx = memblock_search(&memblock.memory, base); if (idx == -1) return 0; - return memblock.reserved.regions[idx].base <= base && - (memblock.reserved.regions[idx].base + - memblock.reserved.regions[idx].size) >= (base + size); + return memblock.memory.regions[idx].base <= base && + (memblock.memory.regions[idx].base + + memblock.memory.regions[idx].size) >= (base + size); } int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 00bb8a64d02..da53a252b25 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -292,7 +292,6 @@ static struct move_charge_struct { unsigned long moved_charge; unsigned long moved_swap; struct task_struct *moving_task; /* a task moving charges */ - struct mm_struct *mm; wait_queue_head_t waitq; /* a waitq for other context */ } mc = { .lock = __SPIN_LOCK_UNLOCKED(mc.lock), @@ -601,23 +600,24 @@ static void mem_cgroup_swap_statistics(struct mem_cgroup *mem, } static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, - struct page_cgroup *pc, - bool charge) + bool file, int nr_pages) { - int val = (charge) ? 1 : -1; - preempt_disable(); - if (PageCgroupCache(pc)) - __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_CACHE], val); + if (file) + __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_CACHE], nr_pages); else - __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_RSS], val); + __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_RSS], nr_pages); - if (charge) + /* pagein of a big page is an event. So, ignore page size */ + if (nr_pages > 0) __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGIN_COUNT]); - else + else { __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGOUT_COUNT]); - __this_cpu_inc(mem->stat->count[MEM_CGROUP_EVENTS]); + nr_pages = -nr_pages; /* for event */ + } + + __this_cpu_add(mem->stat->count[MEM_CGROUP_EVENTS], nr_pages); preempt_enable(); } @@ -816,12 +816,12 @@ void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru) * removed from global LRU. */ mz = page_cgroup_zoneinfo(pc); - MEM_CGROUP_ZSTAT(mz, lru) -= 1; + /* huge page split is done under lru_lock. so, we have no races. */ + MEM_CGROUP_ZSTAT(mz, lru) -= 1 << compound_order(page); if (mem_cgroup_is_root(pc->mem_cgroup)) return; VM_BUG_ON(list_empty(&pc->lru)); list_del_init(&pc->lru); - return; } void mem_cgroup_del_lru(struct page *page) @@ -838,13 +838,12 @@ void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru) return; pc = lookup_page_cgroup(page); - /* - * Used bit is set without atomic ops but after smp_wmb(). - * For making pc->mem_cgroup visible, insert smp_rmb() here. - */ - smp_rmb(); /* unused or root page is not rotated. */ - if (!PageCgroupUsed(pc) || mem_cgroup_is_root(pc->mem_cgroup)) + if (!PageCgroupUsed(pc)) + return; + /* Ensure pc->mem_cgroup is visible after reading PCG_USED. */ + smp_rmb(); + if (mem_cgroup_is_root(pc->mem_cgroup)) return; mz = page_cgroup_zoneinfo(pc); list_move(&pc->lru, &mz->lists[lru]); @@ -859,16 +858,13 @@ void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru) return; pc = lookup_page_cgroup(page); VM_BUG_ON(PageCgroupAcctLRU(pc)); - /* - * Used bit is set without atomic ops but after smp_wmb(). - * For making pc->mem_cgroup visible, insert smp_rmb() here. - */ - smp_rmb(); if (!PageCgroupUsed(pc)) return; - + /* Ensure pc->mem_cgroup is visible after reading PCG_USED. */ + smp_rmb(); mz = page_cgroup_zoneinfo(pc); - MEM_CGROUP_ZSTAT(mz, lru) += 1; + /* huge page split is done under lru_lock. so, we have no races. */ + MEM_CGROUP_ZSTAT(mz, lru) += 1 << compound_order(page); SetPageCgroupAcctLRU(pc); if (mem_cgroup_is_root(pc->mem_cgroup)) return; @@ -1032,14 +1028,10 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page) return NULL; pc = lookup_page_cgroup(page); - /* - * Used bit is set without atomic ops but after smp_wmb(). - * For making pc->mem_cgroup visible, insert smp_rmb() here. - */ - smp_rmb(); if (!PageCgroupUsed(pc)) return NULL; - + /* Ensure pc->mem_cgroup is visible after reading PCG_USED. */ + smp_rmb(); mz = page_cgroup_zoneinfo(pc); if (!mz) return NULL; @@ -1087,7 +1079,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, case 0: list_move(&page->lru, dst); mem_cgroup_del_lru(page); - nr_taken++; + nr_taken += hpage_nr_pages(page); break; case -EBUSY: /* we don't affect global LRU but rotate in our LRU */ @@ -1121,6 +1113,23 @@ static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem) return false; } +/** + * mem_cgroup_check_margin - check if the memory cgroup allows charging + * @mem: memory cgroup to check + * @bytes: the number of bytes the caller intends to charge + * + * Returns a boolean value on whether @mem can be charged @bytes or + * whether this would exceed the limit. + */ +static bool mem_cgroup_check_margin(struct mem_cgroup *mem, unsigned long bytes) +{ + if (!res_counter_check_margin(&mem->res, bytes)) + return false; + if (do_swap_account && !res_counter_check_margin(&mem->memsw, bytes)) + return false; + return true; +} + static unsigned int get_swappiness(struct mem_cgroup *memcg) { struct cgroup *cgrp = memcg->css.cgroup; @@ -1312,8 +1321,9 @@ u64 mem_cgroup_get_limit(struct mem_cgroup *memcg) u64 limit; u64 memsw; - limit = res_counter_read_u64(&memcg->res, RES_LIMIT) + - total_swap_pages; + limit = res_counter_read_u64(&memcg->res, RES_LIMIT); + limit += total_swap_pages << PAGE_SHIFT; + memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT); /* * If memsw is finite and limits the amount of swap space available @@ -1600,11 +1610,13 @@ bool mem_cgroup_handle_oom(struct mem_cgroup *mem, gfp_t mask) * possibility of race condition. If there is, we take a lock. */ -static void mem_cgroup_update_file_stat(struct page *page, int idx, int val) +void mem_cgroup_update_page_stat(struct page *page, + enum mem_cgroup_page_stat_item idx, int val) { struct mem_cgroup *mem; struct page_cgroup *pc = lookup_page_cgroup(page); bool need_unlock = false; + unsigned long uninitialized_var(flags); if (unlikely(!pc)) return; @@ -1614,39 +1626,36 @@ static void mem_cgroup_update_file_stat(struct page *page, int idx, int val) if (unlikely(!mem || !PageCgroupUsed(pc))) goto out; /* pc->mem_cgroup is unstable ? */ - if (unlikely(mem_cgroup_stealed(mem))) { + if (unlikely(mem_cgroup_stealed(mem)) || PageTransHuge(page)) { /* take a lock against to access pc->mem_cgroup */ - lock_page_cgroup(pc); + move_lock_page_cgroup(pc, &flags); need_unlock = true; mem = pc->mem_cgroup; if (!mem || !PageCgroupUsed(pc)) goto out; } - this_cpu_add(mem->stat->count[idx], val); - switch (idx) { - case MEM_CGROUP_STAT_FILE_MAPPED: + case MEMCG_NR_FILE_MAPPED: if (val > 0) SetPageCgroupFileMapped(pc); else if (!page_mapped(page)) ClearPageCgroupFileMapped(pc); + idx = MEM_CGROUP_STAT_FILE_MAPPED; break; default: BUG(); } + this_cpu_add(mem->stat->count[idx], val); + out: if (unlikely(need_unlock)) - unlock_page_cgroup(pc); + move_unlock_page_cgroup(pc, &flags); rcu_read_unlock(); return; } - -void mem_cgroup_update_file_mapped(struct page *page, int val) -{ - mem_cgroup_update_file_stat(page, MEM_CGROUP_STAT_FILE_MAPPED, val); -} +EXPORT_SYMBOL(mem_cgroup_update_page_stat); /* * size of first charge trial. "32" comes from vmscan.c's magic value. @@ -1842,27 +1851,39 @@ static int __mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask, if (likely(!ret)) return CHARGE_OK; + res_counter_uncharge(&mem->res, csize); mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw); flags |= MEM_CGROUP_RECLAIM_NOSWAP; } else mem_over_limit = mem_cgroup_from_res_counter(fail_res, res); - - if (csize > PAGE_SIZE) /* change csize and retry */ + /* + * csize can be either a huge page (HPAGE_SIZE), a batch of + * regular pages (CHARGE_SIZE), or a single regular page + * (PAGE_SIZE). + * + * Never reclaim on behalf of optional batching, retry with a + * single page instead. + */ + if (csize == CHARGE_SIZE) return CHARGE_RETRY; if (!(gfp_mask & __GFP_WAIT)) return CHARGE_WOULDBLOCK; ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, NULL, - gfp_mask, flags); + gfp_mask, flags); + if (mem_cgroup_check_margin(mem_over_limit, csize)) + return CHARGE_RETRY; /* - * try_to_free_mem_cgroup_pages() might not give us a full - * picture of reclaim. Some pages are reclaimed and might be - * moved to swap cache or just unmapped from the cgroup. - * Check the limit again to see if the reclaim reduced the - * current usage of the cgroup before giving up + * Even though the limit is exceeded at this point, reclaim + * may have been able to free some pages. Retry the charge + * before killing the task. + * + * Only for regular pages, though: huge pages are rather + * unlikely to succeed so close to the limit, and we fall back + * to regular pages anyway in case of failure. */ - if (ret || mem_cgroup_check_under_limit(mem_over_limit)) + if (csize == PAGE_SIZE && ret) return CHARGE_RETRY; /* @@ -1887,12 +1908,14 @@ static int __mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask, * oom-killer can be invoked. */ static int __mem_cgroup_try_charge(struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcg, bool oom) + gfp_t gfp_mask, + struct mem_cgroup **memcg, bool oom, + int page_size) { int nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES; struct mem_cgroup *mem = NULL; int ret; - int csize = CHARGE_SIZE; + int csize = max(CHARGE_SIZE, (unsigned long) page_size); /* * Unlike gloval-vm's OOM-kill, we're not in memory shortage @@ -1917,7 +1940,7 @@ again: VM_BUG_ON(css_is_removed(&mem->css)); if (mem_cgroup_is_root(mem)) goto done; - if (consume_stock(mem)) + if (page_size == PAGE_SIZE && consume_stock(mem)) goto done; css_get(&mem->css); } else { @@ -1940,7 +1963,7 @@ again: rcu_read_unlock(); goto done; } - if (consume_stock(mem)) { + if (page_size == PAGE_SIZE && consume_stock(mem)) { /* * It seems dagerous to access memcg without css_get(). * But considering how consume_stok works, it's not @@ -1981,7 +2004,7 @@ again: case CHARGE_OK: break; case CHARGE_RETRY: /* not in OOM situation but retry */ - csize = PAGE_SIZE; + csize = page_size; css_put(&mem->css); mem = NULL; goto again; @@ -2002,8 +2025,8 @@ again: } } while (ret != CHARGE_OK); - if (csize > PAGE_SIZE) - refill_stock(mem, csize - PAGE_SIZE); + if (csize > page_size) + refill_stock(mem, csize - page_size); css_put(&mem->css); done: *memcg = mem; @@ -2031,9 +2054,10 @@ static void __mem_cgroup_cancel_charge(struct mem_cgroup *mem, } } -static void mem_cgroup_cancel_charge(struct mem_cgroup *mem) +static void mem_cgroup_cancel_charge(struct mem_cgroup *mem, + int page_size) { - __mem_cgroup_cancel_charge(mem, 1); + __mem_cgroup_cancel_charge(mem, page_size >> PAGE_SHIFT); } /* @@ -2083,15 +2107,13 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) return mem; } -/* - * commit a charge got by __mem_cgroup_try_charge() and makes page_cgroup to be - * USED state. If already USED, uncharge and return. - */ - static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, - struct page_cgroup *pc, - enum charge_type ctype) + struct page_cgroup *pc, + enum charge_type ctype, + int page_size) { + int nr_pages = page_size >> PAGE_SHIFT; + /* try_charge() can return NULL to *memcg, taking care of it. */ if (!mem) return; @@ -2099,10 +2121,13 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, lock_page_cgroup(pc); if (unlikely(PageCgroupUsed(pc))) { unlock_page_cgroup(pc); - mem_cgroup_cancel_charge(mem); + mem_cgroup_cancel_charge(mem, page_size); return; } - + /* + * we don't need page_cgroup_lock about tail pages, becase they are not + * accessed by any other context at this point. + */ pc->mem_cgroup = mem; /* * We access a page_cgroup asynchronously without lock_page_cgroup(). @@ -2126,8 +2151,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, break; } - mem_cgroup_charge_statistics(mem, pc, true); - + mem_cgroup_charge_statistics(mem, PageCgroupCache(pc), nr_pages); unlock_page_cgroup(pc); /* * "charge_statistics" updated event counter. Then, check it. @@ -2137,6 +2161,48 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, memcg_check_events(mem, pc->page); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + +#define PCGF_NOCOPY_AT_SPLIT ((1 << PCG_LOCK) | (1 << PCG_MOVE_LOCK) |\ + (1 << PCG_ACCT_LRU) | (1 << PCG_MIGRATION)) +/* + * Because tail pages are not marked as "used", set it. We're under + * zone->lru_lock, 'splitting on pmd' and compund_lock. + */ +void mem_cgroup_split_huge_fixup(struct page *head, struct page *tail) +{ + struct page_cgroup *head_pc = lookup_page_cgroup(head); + struct page_cgroup *tail_pc = lookup_page_cgroup(tail); + unsigned long flags; + + if (mem_cgroup_disabled()) + return; + /* + * We have no races with charge/uncharge but will have races with + * page state accounting. + */ + move_lock_page_cgroup(head_pc, &flags); + + tail_pc->mem_cgroup = head_pc->mem_cgroup; + smp_wmb(); /* see __commit_charge() */ + if (PageCgroupAcctLRU(head_pc)) { + enum lru_list lru; + struct mem_cgroup_per_zone *mz; + + /* + * LRU flags cannot be copied because we need to add tail + *.page to LRU by generic call and our hook will be called. + * We hold lru_lock, then, reduce counter directly. + */ + lru = page_lru(head); + mz = page_cgroup_zoneinfo(head_pc); + MEM_CGROUP_ZSTAT(mz, lru) -= 1; + } + tail_pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT; + move_unlock_page_cgroup(head_pc, &flags); +} +#endif + /** * __mem_cgroup_move_account - move account of the page * @pc: page_cgroup of the page. @@ -2155,8 +2221,11 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, */ static void __mem_cgroup_move_account(struct page_cgroup *pc, - struct mem_cgroup *from, struct mem_cgroup *to, bool uncharge) + struct mem_cgroup *from, struct mem_cgroup *to, bool uncharge, + int charge_size) { + int nr_pages = charge_size >> PAGE_SHIFT; + VM_BUG_ON(from == to); VM_BUG_ON(PageLRU(pc->page)); VM_BUG_ON(!page_is_cgroup_locked(pc)); @@ -2170,14 +2239,14 @@ static void __mem_cgroup_move_account(struct page_cgroup *pc, __this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); preempt_enable(); } - mem_cgroup_charge_statistics(from, pc, false); + mem_cgroup_charge_statistics(from, PageCgroupCache(pc), -nr_pages); if (uncharge) /* This is not "cancel", but cancel_charge does all we need. */ - mem_cgroup_cancel_charge(from); + mem_cgroup_cancel_charge(from, charge_size); /* caller should have done css_get */ pc->mem_cgroup = to; - mem_cgroup_charge_statistics(to, pc, true); + mem_cgroup_charge_statistics(to, PageCgroupCache(pc), nr_pages); /* * We charges against "to" which may not have any tasks. Then, "to" * can be under rmdir(). But in current implementation, caller of @@ -2192,12 +2261,25 @@ static void __mem_cgroup_move_account(struct page_cgroup *pc, * __mem_cgroup_move_account() */ static int mem_cgroup_move_account(struct page_cgroup *pc, - struct mem_cgroup *from, struct mem_cgroup *to, bool uncharge) + struct mem_cgroup *from, struct mem_cgroup *to, + bool uncharge, int charge_size) { int ret = -EINVAL; + unsigned long flags; + /* + * The page is isolated from LRU. So, collapse function + * will not handle this page. But page splitting can happen. + * Do this check under compound_page_lock(). The caller should + * hold it. + */ + if ((charge_size > PAGE_SIZE) && !PageTransHuge(pc->page)) + return -EBUSY; + lock_page_cgroup(pc); if (PageCgroupUsed(pc) && pc->mem_cgroup == from) { - __mem_cgroup_move_account(pc, from, to, uncharge); + move_lock_page_cgroup(pc, &flags); + __mem_cgroup_move_account(pc, from, to, uncharge, charge_size); + move_unlock_page_cgroup(pc, &flags); ret = 0; } unlock_page_cgroup(pc); @@ -2221,6 +2303,8 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc, struct cgroup *cg = child->css.cgroup; struct cgroup *pcg = cg->parent; struct mem_cgroup *parent; + int page_size = PAGE_SIZE; + unsigned long flags; int ret; /* Is ROOT ? */ @@ -2233,14 +2317,24 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc, if (isolate_lru_page(page)) goto put; + if (PageTransHuge(page)) + page_size = HPAGE_SIZE; + parent = mem_cgroup_from_cont(pcg); - ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false); + ret = __mem_cgroup_try_charge(NULL, gfp_mask, + &parent, false, page_size); if (ret || !parent) goto put_back; - ret = mem_cgroup_move_account(pc, child, parent, true); + if (page_size > PAGE_SIZE) + flags = compound_lock_irqsave(page); + + ret = mem_cgroup_move_account(pc, child, parent, true, page_size); if (ret) - mem_cgroup_cancel_charge(parent); + mem_cgroup_cancel_charge(parent, page_size); + + if (page_size > PAGE_SIZE) + compound_unlock_irqrestore(page, flags); put_back: putback_lru_page(page); put: @@ -2259,20 +2353,32 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, enum charge_type ctype) { struct mem_cgroup *mem = NULL; + int page_size = PAGE_SIZE; struct page_cgroup *pc; + bool oom = true; int ret; + if (PageTransHuge(page)) { + page_size <<= compound_order(page); + VM_BUG_ON(!PageTransHuge(page)); + /* + * Never OOM-kill a process for a huge page. The + * fault handler will fall back to regular pages. + */ + oom = false; + } + pc = lookup_page_cgroup(page); /* can happen at boot */ if (unlikely(!pc)) return 0; prefetchw(pc); - ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true); + ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, oom, page_size); if (ret || !mem) return ret; - __mem_cgroup_commit_charge(mem, pc, ctype); + __mem_cgroup_commit_charge(mem, pc, ctype, page_size); return 0; } @@ -2281,8 +2387,6 @@ int mem_cgroup_newpage_charge(struct page *page, { if (mem_cgroup_disabled()) return 0; - if (PageCompound(page)) - return 0; /* * If already mapped, we don't have to account. * If page cache, page->mapping has address_space. @@ -2388,13 +2492,13 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, if (!mem) goto charge_cur_mm; *ptr = mem; - ret = __mem_cgroup_try_charge(NULL, mask, ptr, true); + ret = __mem_cgroup_try_charge(NULL, mask, ptr, true, PAGE_SIZE); css_put(&mem->css); return ret; charge_cur_mm: if (unlikely(!mm)) mm = &init_mm; - return __mem_cgroup_try_charge(mm, mask, ptr, true); + return __mem_cgroup_try_charge(mm, mask, ptr, true, PAGE_SIZE); } static void @@ -2410,7 +2514,7 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, cgroup_exclude_rmdir(&ptr->css); pc = lookup_page_cgroup(page); mem_cgroup_lru_del_before_commit_swapcache(page); - __mem_cgroup_commit_charge(ptr, pc, ctype); + __mem_cgroup_commit_charge(ptr, pc, ctype, PAGE_SIZE); mem_cgroup_lru_add_after_commit_swapcache(page); /* * Now swap is on-memory. This means this page may be @@ -2459,11 +2563,12 @@ void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) return; if (!mem) return; - mem_cgroup_cancel_charge(mem); + mem_cgroup_cancel_charge(mem, PAGE_SIZE); } static void -__do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype) +__do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype, + int page_size) { struct memcg_batch_info *batch = NULL; bool uncharge_memsw = true; @@ -2490,6 +2595,9 @@ __do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype) if (!batch->do_batch || test_thread_flag(TIF_MEMDIE)) goto direct_uncharge; + if (page_size != PAGE_SIZE) + goto direct_uncharge; + /* * In typical case, batch->memcg == mem. This means we can * merge a series of uncharges to an uncharge of res_counter. @@ -2503,9 +2611,9 @@ __do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype) batch->memsw_bytes += PAGE_SIZE; return; direct_uncharge: - res_counter_uncharge(&mem->res, PAGE_SIZE); + res_counter_uncharge(&mem->res, page_size); if (uncharge_memsw) - res_counter_uncharge(&mem->memsw, PAGE_SIZE); + res_counter_uncharge(&mem->memsw, page_size); if (unlikely(batch->memcg != mem)) memcg_oom_recover(mem); return; @@ -2517,8 +2625,10 @@ direct_uncharge: static struct mem_cgroup * __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) { + int count; struct page_cgroup *pc; struct mem_cgroup *mem = NULL; + int page_size = PAGE_SIZE; if (mem_cgroup_disabled()) return NULL; @@ -2526,6 +2636,12 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) if (PageSwapCache(page)) return NULL; + if (PageTransHuge(page)) { + page_size <<= compound_order(page); + VM_BUG_ON(!PageTransHuge(page)); + } + + count = page_size >> PAGE_SHIFT; /* * Check if our page_cgroup is valid */ @@ -2558,7 +2674,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) break; } - mem_cgroup_charge_statistics(mem, pc, false); + mem_cgroup_charge_statistics(mem, PageCgroupCache(pc), -count); ClearPageCgroupUsed(pc); /* @@ -2579,7 +2695,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) mem_cgroup_get(mem); } if (!mem_cgroup_is_root(mem)) - __do_uncharge(mem, ctype); + __do_uncharge(mem, ctype, page_size); return mem; @@ -2774,6 +2890,7 @@ int mem_cgroup_prepare_migration(struct page *page, enum charge_type ctype; int ret = 0; + VM_BUG_ON(PageTransHuge(page)); if (mem_cgroup_disabled()) return 0; @@ -2823,7 +2940,7 @@ int mem_cgroup_prepare_migration(struct page *page, return 0; *ptr = mem; - ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, ptr, false); + ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, ptr, false, PAGE_SIZE); css_put(&mem->css);/* drop extra refcnt */ if (ret || *ptr == NULL) { if (PageAnon(page)) { @@ -2850,13 +2967,13 @@ int mem_cgroup_prepare_migration(struct page *page, ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; else ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM; - __mem_cgroup_commit_charge(mem, pc, ctype); + __mem_cgroup_commit_charge(mem, pc, ctype, PAGE_SIZE); return ret; } /* remove redundant charge if migration failed*/ void mem_cgroup_end_migration(struct mem_cgroup *mem, - struct page *oldpage, struct page *newpage) + struct page *oldpage, struct page *newpage, bool migration_ok) { struct page *used, *unused; struct page_cgroup *pc; @@ -2865,8 +2982,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem, return; /* blocks rmdir() */ cgroup_exclude_rmdir(&mem->css); - /* at migration success, oldpage->mapping is NULL. */ - if (oldpage->mapping) { + if (!migration_ok) { used = oldpage; unused = newpage; } else { @@ -4176,13 +4292,11 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) */ if (!node_state(node, N_NORMAL_MEMORY)) tmp = -1; - pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, tmp); + pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, tmp); if (!pn) return 1; mem->info.nodeinfo[node] = pn; - memset(pn, 0, sizeof(*pn)); - for (zone = 0; zone < MAX_NR_ZONES; zone++) { mz = &pn->zoneinfo[zone]; for_each_lru(l) @@ -4206,14 +4320,13 @@ static struct mem_cgroup *mem_cgroup_alloc(void) /* Can be very big if MAX_NUMNODES is very big */ if (size < PAGE_SIZE) - mem = kmalloc(size, GFP_KERNEL); + mem = kzalloc(size, GFP_KERNEL); else - mem = vmalloc(size); + mem = vzalloc(size); if (!mem) return NULL; - memset(mem, 0, size); mem->stat = alloc_percpu(struct mem_cgroup_stat_cpu); if (!mem->stat) goto out_free; @@ -4461,7 +4574,8 @@ one_by_one: batch_count = PRECHARGE_COUNT_AT_ONCE; cond_resched(); } - ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false); + ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false, + PAGE_SIZE); if (ret || !mem) /* mem_cgroup_clear_mc() will do uncharge later */ return -ENOMEM; @@ -4623,6 +4737,7 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, pte_t *pte; spinlock_t *ptl; + VM_BUG_ON(pmd_trans_huge(*pmd)); pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) if (is_target_pte_for_mc(vma, addr, *pte, NULL)) @@ -4638,7 +4753,7 @@ static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm) unsigned long precharge; struct vm_area_struct *vma; - /* We've already held the mmap_sem */ + down_read(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) { struct mm_walk mem_cgroup_count_precharge_walk = { .pmd_entry = mem_cgroup_count_precharge_pte_range, @@ -4650,6 +4765,7 @@ static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm) walk_page_range(vma->vm_start, vma->vm_end, &mem_cgroup_count_precharge_walk); } + up_read(&mm->mmap_sem); precharge = mc.precharge; mc.precharge = 0; @@ -4659,10 +4775,15 @@ static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm) static int mem_cgroup_precharge_mc(struct mm_struct *mm) { - return mem_cgroup_do_precharge(mem_cgroup_count_precharge(mm)); + unsigned long precharge = mem_cgroup_count_precharge(mm); + + VM_BUG_ON(mc.moving_task); + mc.moving_task = current; + return mem_cgroup_do_precharge(precharge); } -static void mem_cgroup_clear_mc(void) +/* cancels all extra charges on mc.from and mc.to, and wakes up all waiters. */ +static void __mem_cgroup_clear_mc(void) { struct mem_cgroup *from = mc.from; struct mem_cgroup *to = mc.to; @@ -4697,23 +4818,28 @@ static void mem_cgroup_clear_mc(void) PAGE_SIZE * mc.moved_swap); } /* we've already done mem_cgroup_get(mc.to) */ - mc.moved_swap = 0; } - if (mc.mm) { - up_read(&mc.mm->mmap_sem); - mmput(mc.mm); - } + memcg_oom_recover(from); + memcg_oom_recover(to); + wake_up_all(&mc.waitq); +} + +static void mem_cgroup_clear_mc(void) +{ + struct mem_cgroup *from = mc.from; + + /* + * we must clear moving_task before waking up waiters at the end of + * task migration. + */ + mc.moving_task = NULL; + __mem_cgroup_clear_mc(); spin_lock(&mc.lock); mc.from = NULL; mc.to = NULL; spin_unlock(&mc.lock); - mc.moving_task = NULL; - mc.mm = NULL; mem_cgroup_end_move(from); - memcg_oom_recover(from); - memcg_oom_recover(to); - wake_up_all(&mc.waitq); } static int mem_cgroup_can_attach(struct cgroup_subsys *ss, @@ -4735,38 +4861,23 @@ static int mem_cgroup_can_attach(struct cgroup_subsys *ss, return 0; /* We move charges only when we move a owner of the mm */ if (mm->owner == p) { - /* - * We do all the move charge works under one mmap_sem to - * avoid deadlock with down_write(&mmap_sem) - * -> try_charge() -> if (mc.moving_task) -> sleep. - */ - down_read(&mm->mmap_sem); - VM_BUG_ON(mc.from); VM_BUG_ON(mc.to); VM_BUG_ON(mc.precharge); VM_BUG_ON(mc.moved_charge); VM_BUG_ON(mc.moved_swap); - VM_BUG_ON(mc.moving_task); - VM_BUG_ON(mc.mm); - mem_cgroup_start_move(from); spin_lock(&mc.lock); mc.from = from; mc.to = mem; - mc.precharge = 0; - mc.moved_charge = 0; - mc.moved_swap = 0; spin_unlock(&mc.lock); - mc.moving_task = current; - mc.mm = mm; + /* We set mc.moving_task later */ ret = mem_cgroup_precharge_mc(mm); if (ret) mem_cgroup_clear_mc(); - /* We call up_read() and mmput() in clear_mc(). */ - } else - mmput(mm); + } + mmput(mm); } return ret; } @@ -4789,6 +4900,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, spinlock_t *ptl; retry: + VM_BUG_ON(pmd_trans_huge(*pmd)); pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); for (; addr != end; addr += PAGE_SIZE) { pte_t ptent = *(pte++); @@ -4809,7 +4921,7 @@ retry: goto put; pc = lookup_page_cgroup(page); if (!mem_cgroup_move_account(pc, - mc.from, mc.to, false)) { + mc.from, mc.to, false, PAGE_SIZE)) { mc.precharge--; /* we uncharge from mc.from later. */ mc.moved_charge++; @@ -4854,7 +4966,19 @@ static void mem_cgroup_move_charge(struct mm_struct *mm) struct vm_area_struct *vma; lru_add_drain_all(); - /* We've already held the mmap_sem */ +retry: + if (unlikely(!down_read_trylock(&mm->mmap_sem))) { + /* + * Someone who are holding the mmap_sem might be waiting in + * waitq. So we cancel all extra charges, wake up all waiters, + * and retry. Because we cancel precharges, we might not be able + * to move enough charges, but moving charge is a best-effort + * feature anyway, so it wouldn't be a big problem. + */ + __mem_cgroup_clear_mc(); + cond_resched(); + goto retry; + } for (vma = mm->mmap; vma; vma = vma->vm_next) { int ret; struct mm_walk mem_cgroup_move_charge_walk = { @@ -4873,6 +4997,7 @@ static void mem_cgroup_move_charge(struct mm_struct *mm) */ break; } + up_read(&mm->mmap_sem); } static void mem_cgroup_move_task(struct cgroup_subsys *ss, @@ -4881,11 +5006,17 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss, struct task_struct *p, bool threadgroup) { - if (!mc.mm) + struct mm_struct *mm; + + if (!mc.to) /* no need to move charge */ return; - mem_cgroup_move_charge(mc.mm); + mm = get_task_mm(p); + if (mm) { + mem_cgroup_move_charge(mm); + mmput(mm); + } mem_cgroup_clear_mc(); } #else /* !CONFIG_MMU */ @@ -4929,9 +5060,9 @@ struct cgroup_subsys mem_cgroup_subsys = { static int __init enable_swap_account(char *s) { /* consider enabled if no parameter or 1 is given */ - if (!s || !strcmp(s, "1")) + if (!(*s) || !strcmp(s, "=1")) really_do_swap_account = 1; - else if (!strcmp(s, "0")) + else if (!strcmp(s, "=0")) really_do_swap_account = 0; return 1; } @@ -4939,7 +5070,8 @@ __setup("swapaccount", enable_swap_account); static int __init disable_swap_account(char *s) { - enable_swap_account("0"); + printk_once("noswapaccount is deprecated and will be removed in 2.6.40. Use swapaccount=0 instead\n"); + enable_swap_account("=0"); return 1; } __setup("noswapaccount", disable_swap_account); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 46ab2c044b0..0207c2f6f8b 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -203,7 +203,7 @@ static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno, #ifdef __ARCH_SI_TRAPNO si.si_trapno = trapno; #endif - si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT; + si.si_addr_lsb = compound_trans_order(compound_head(page)) + PAGE_SHIFT; /* * Don't use force here, it's convenient if the signal * can be temporarily blocked. @@ -233,8 +233,8 @@ void shake_page(struct page *p, int access) } /* - * Only all shrink_slab here (which would also - * shrink other caches) if access is not potentially fatal. + * Only call shrink_slab here (which would also shrink other caches) if + * access is not potentially fatal. */ if (access) { int nr; @@ -854,6 +854,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, int ret; int kill = 1; struct page *hpage = compound_head(p); + struct page *ppage; if (PageReserved(p) || PageSlab(p)) return SWAP_SUCCESS; @@ -895,6 +896,44 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, } /* + * ppage: poisoned page + * if p is regular page(4k page) + * ppage == real poisoned page; + * else p is hugetlb or THP, ppage == head page. + */ + ppage = hpage; + + if (PageTransHuge(hpage)) { + /* + * Verify that this isn't a hugetlbfs head page, the check for + * PageAnon is just for avoid tripping a split_huge_page + * internal debug check, as split_huge_page refuses to deal with + * anything that isn't an anon page. PageAnon can't go away fro + * under us because we hold a refcount on the hpage, without a + * refcount on the hpage. split_huge_page can't be safely called + * in the first place, having a refcount on the tail isn't + * enough * to be safe. + */ + if (!PageHuge(hpage) && PageAnon(hpage)) { + if (unlikely(split_huge_page(hpage))) { + /* + * FIXME: if splitting THP is failed, it is + * better to stop the following operation rather + * than causing panic by unmapping. System might + * survive if the page is freed later. + */ + printk(KERN_INFO + "MCE %#lx: failed to split THP\n", pfn); + + BUG_ON(!PageHWPoison(p)); + return SWAP_FAIL; + } + /* THP is split, so ppage should be the real poisoned page. */ + ppage = p; + } + } + + /* * First collect all the processes that have the page * mapped in dirty form. This has to be done before try_to_unmap, * because ttu takes the rmap data structures down. @@ -903,12 +942,18 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * there's nothing that can be done. */ if (kill) - collect_procs(hpage, &tokill); + collect_procs(ppage, &tokill); - ret = try_to_unmap(hpage, ttu); + if (hpage != ppage) + lock_page_nosync(ppage); + + ret = try_to_unmap(ppage, ttu); if (ret != SWAP_SUCCESS) printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n", - pfn, page_mapcount(hpage)); + pfn, page_mapcount(ppage)); + + if (hpage != ppage) + unlock_page(ppage); /* * Now that the dirty bit has been propagated to the @@ -919,7 +964,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * use a more force-full uncatchable kill to prevent * any accesses to the poisoned memory. */ - kill_procs_ao(&tokill, !!PageDirty(hpage), trapno, + kill_procs_ao(&tokill, !!PageDirty(ppage), trapno, ret != SWAP_SUCCESS, p, pfn); return ret; @@ -928,7 +973,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, static void set_page_hwpoison_huge_page(struct page *hpage) { int i; - int nr_pages = 1 << compound_order(hpage); + int nr_pages = 1 << compound_trans_order(hpage); for (i = 0; i < nr_pages; i++) SetPageHWPoison(hpage + i); } @@ -936,7 +981,7 @@ static void set_page_hwpoison_huge_page(struct page *hpage) static void clear_page_hwpoison_huge_page(struct page *hpage) { int i; - int nr_pages = 1 << compound_order(hpage); + int nr_pages = 1 << compound_trans_order(hpage); for (i = 0; i < nr_pages; i++) ClearPageHWPoison(hpage + i); } @@ -966,7 +1011,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags) return 0; } - nr_pages = 1 << compound_order(hpage); + nr_pages = 1 << compound_trans_order(hpage); atomic_long_add(nr_pages, &mce_bad_pages); /* @@ -1020,19 +1065,22 @@ int __memory_failure(unsigned long pfn, int trapno, int flags) * The check (unnecessarily) ignores LRU pages being isolated and * walked by the page reclaim code, however that's not a big loss. */ - if (!PageLRU(p) && !PageHuge(p)) - shake_page(p, 0); - if (!PageLRU(p) && !PageHuge(p)) { - /* - * shake_page could have turned it free. - */ - if (is_free_buddy_page(p)) { - action_result(pfn, "free buddy, 2nd try", DELAYED); - return 0; + if (!PageHuge(p) && !PageTransCompound(p)) { + if (!PageLRU(p)) + shake_page(p, 0); + if (!PageLRU(p)) { + /* + * shake_page could have turned it free. + */ + if (is_free_buddy_page(p)) { + action_result(pfn, "free buddy, 2nd try", + DELAYED); + return 0; + } + action_result(pfn, "non LRU", IGNORED); + put_page(p); + return -EBUSY; } - action_result(pfn, "non LRU", IGNORED); - put_page(p); - return -EBUSY; } /* @@ -1062,7 +1110,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags) * For error on the tail page, we should set PG_hwpoison * on the head page to show that the hugepage is hwpoisoned */ - if (PageTail(p) && TestSetPageHWPoison(hpage)) { + if (PageHuge(p) && PageTail(p) && TestSetPageHWPoison(hpage)) { action_result(pfn, "hugepage already hardware poisoned", IGNORED); unlock_page(hpage); @@ -1164,7 +1212,7 @@ int unpoison_memory(unsigned long pfn) return 0; } - nr_pages = 1 << compound_order(page); + nr_pages = 1 << compound_trans_order(page); if (!get_page_unless_zero(page)) { /* @@ -1290,9 +1338,13 @@ static int soft_offline_huge_page(struct page *page, int flags) /* Keep page count to indicate a given hugepage is isolated. */ list_add(&hpage->lru, &pagelist); - ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0); + ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0, + true); if (ret) { - putback_lru_pages(&pagelist); + struct page *page1, *page2; + list_for_each_entry_safe(page1, page2, &pagelist, lru) + put_page(page1); + pr_debug("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); if (ret > 0) @@ -1301,7 +1353,7 @@ static int soft_offline_huge_page(struct page *page, int flags) } done: if (!PageHWPoison(hpage)) - atomic_long_add(1 << compound_order(hpage), &mce_bad_pages); + atomic_long_add(1 << compound_trans_order(hpage), &mce_bad_pages); set_page_hwpoison_huge_page(hpage); dequeue_hwpoisoned_huge_page(hpage); /* keep elevated page count for bad page */ @@ -1413,8 +1465,10 @@ int soft_offline_page(struct page *page, int flags) LIST_HEAD(pagelist); list_add(&page->lru, &pagelist); - ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0); + ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, + 0, true); if (ret) { + putback_lru_pages(&pagelist); pr_info("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); if (ret > 0) diff --git a/mm/memory.c b/mm/memory.c index 02e48aa0ed1..8e8c1832486 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -394,9 +394,11 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, } } -int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address) +int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long address) { pgtable_t new = pte_alloc_one(mm, address); + int wait_split_huge_page; if (!new) return -ENOMEM; @@ -416,14 +418,18 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address) smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ spin_lock(&mm->page_table_lock); - if (!pmd_present(*pmd)) { /* Has another populated it ? */ + wait_split_huge_page = 0; + if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ mm->nr_ptes++; pmd_populate(mm, pmd, new); new = NULL; - } + } else if (unlikely(pmd_trans_splitting(*pmd))) + wait_split_huge_page = 1; spin_unlock(&mm->page_table_lock); if (new) pte_free(mm, new); + if (wait_split_huge_page) + wait_split_huge_page(vma->anon_vma, pmd); return 0; } @@ -436,10 +442,11 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address) smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&init_mm.page_table_lock); - if (!pmd_present(*pmd)) { /* Has another populated it ? */ + if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ pmd_populate_kernel(&init_mm, pmd, new); new = NULL; - } + } else + VM_BUG_ON(pmd_trans_splitting(*pmd)); spin_unlock(&init_mm.page_table_lock); if (new) pte_free_kernel(&init_mm, new); @@ -719,9 +726,9 @@ out_set_pte: return 0; } -static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, - unsigned long addr, unsigned long end) +int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, + unsigned long addr, unsigned long end) { pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; @@ -795,6 +802,17 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src src_pmd = pmd_offset(src_pud, addr); do { next = pmd_addr_end(addr, end); + if (pmd_trans_huge(*src_pmd)) { + int err; + VM_BUG_ON(next-addr != HPAGE_PMD_SIZE); + err = copy_huge_pmd(dst_mm, src_mm, + dst_pmd, src_pmd, addr, vma); + if (err == -ENOMEM) + return -ENOMEM; + if (!err) + continue; + /* fall through */ + } if (pmd_none_or_clear_bad(src_pmd)) continue; if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd, @@ -997,6 +1015,16 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); + if (pmd_trans_huge(*pmd)) { + if (next-addr != HPAGE_PMD_SIZE) { + VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem)); + split_huge_page_pmd(vma->vm_mm, pmd); + } else if (zap_huge_pmd(tlb, vma, pmd)) { + (*zap_work)--; + continue; + } + /* fall through */ + } if (pmd_none_or_clear_bad(pmd)) { (*zap_work)--; continue; @@ -1262,7 +1290,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, pud = pud_offset(pgd, address); if (pud_none(*pud)) goto no_page_table; - if (pud_huge(*pud)) { + if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { BUG_ON(flags & FOLL_GET); page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE); goto out; @@ -1273,11 +1301,32 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, pmd = pmd_offset(pud, address); if (pmd_none(*pmd)) goto no_page_table; - if (pmd_huge(*pmd)) { + if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) { BUG_ON(flags & FOLL_GET); page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); goto out; } + if (pmd_trans_huge(*pmd)) { + if (flags & FOLL_SPLIT) { + split_huge_page_pmd(mm, pmd); + goto split_fallthrough; + } + spin_lock(&mm->page_table_lock); + if (likely(pmd_trans_huge(*pmd))) { + if (unlikely(pmd_trans_splitting(*pmd))) { + spin_unlock(&mm->page_table_lock); + wait_split_huge_page(vma->anon_vma, pmd); + } else { + page = follow_trans_huge_pmd(mm, address, + pmd, flags); + spin_unlock(&mm->page_table_lock); + goto out; + } + } else + spin_unlock(&mm->page_table_lock); + /* fall through */ + } +split_fallthrough: if (unlikely(pmd_bad(*pmd))) goto no_page_table; @@ -1310,6 +1359,28 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, */ mark_page_accessed(page); } + if (flags & FOLL_MLOCK) { + /* + * The preliminary mapping check is mainly to avoid the + * pointless overhead of lock_page on the ZERO_PAGE + * which might bounce very badly if there is contention. + * + * If the page is already locked, we don't need to + * handle it now - vmscan will handle it later if and + * when it attempts to reclaim the page. + */ + if (page->mapping && trylock_page(page)) { + lru_add_drain(); /* push cached pages to LRU */ + /* + * Because we lock page here and migration is + * blocked by the pte's page reference, we need + * only check for file-cache page truncation. + */ + if (page->mapping) + mlock_vma_page(page); + unlock_page(page); + } + } unlock: pte_unmap_unlock(ptep, ptl); out: @@ -1341,7 +1412,8 @@ no_page_table: int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int nr_pages, unsigned int gup_flags, - struct page **pages, struct vm_area_struct **vmas) + struct page **pages, struct vm_area_struct **vmas, + int *nonblocking) { int i; unsigned long vm_flags; @@ -1386,6 +1458,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, pmd = pmd_offset(pud, pg); if (pmd_none(*pmd)) return i ? : -EFAULT; + VM_BUG_ON(pmd_trans_huge(*pmd)); pte = pte_offset_map(pmd, pg); if (pte_none(*pte)) { pte_unmap(pte); @@ -1441,10 +1514,15 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, cond_resched(); while (!(page = follow_page(vma, start, foll_flags))) { int ret; + unsigned int fault_flags = 0; + + if (foll_flags & FOLL_WRITE) + fault_flags |= FAULT_FLAG_WRITE; + if (nonblocking) + fault_flags |= FAULT_FLAG_ALLOW_RETRY; ret = handle_mm_fault(mm, vma, start, - (foll_flags & FOLL_WRITE) ? - FAULT_FLAG_WRITE : 0); + fault_flags); if (ret & VM_FAULT_ERROR) { if (ret & VM_FAULT_OOM) @@ -1460,6 +1538,11 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, else tsk->min_flt++; + if (ret & VM_FAULT_RETRY) { + *nonblocking = 0; + return i; + } + /* * The VM_FAULT_WRITE bit tells us that * do_wp_page has broken COW when necessary, @@ -1559,7 +1642,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (force) flags |= FOLL_FORCE; - return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas); + return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas, + NULL); } EXPORT_SYMBOL(get_user_pages); @@ -1584,7 +1668,8 @@ struct page *get_dump_page(unsigned long addr) struct page *page; if (__get_user_pages(current, current->mm, addr, 1, - FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma) < 1) + FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma, + NULL) < 1) return NULL; flush_cache_page(vma, addr, page_to_pfn(page)); return page; @@ -1598,8 +1683,10 @@ pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, pud_t * pud = pud_alloc(mm, pgd, addr); if (pud) { pmd_t * pmd = pmd_alloc(mm, pud, addr); - if (pmd) + if (pmd) { + VM_BUG_ON(pmd_trans_huge(*pmd)); return pte_alloc_map_lock(mm, pmd, addr, ptl); + } } return NULL; } @@ -1818,6 +1905,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, pmd = pmd_alloc(mm, pud, addr); if (!pmd) return -ENOMEM; + VM_BUG_ON(pmd_trans_huge(*pmd)); do { next = pmd_addr_end(addr, end); if (remap_pte_range(mm, pmd, addr, next, @@ -2048,19 +2136,6 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, return same; } -/* - * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when - * servicing faults for write access. In the normal case, do always want - * pte_mkwrite. But get_user_pages can cause write faults for mappings - * that do not have writing enabled, when used by access_process_vm. - */ -static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) -{ - if (likely(vma->vm_flags & VM_WRITE)) - pte = pte_mkwrite(pte); - return pte; -} - static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma) { /* @@ -2112,7 +2187,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, { struct page *old_page, *new_page; pte_t entry; - int reuse = 0, ret = 0; + int ret = 0; int page_mkwrite = 0; struct page *dirty_page = NULL; @@ -2144,19 +2219,20 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, &ptl); if (!pte_same(*page_table, orig_pte)) { unlock_page(old_page); - page_cache_release(old_page); goto unlock; } page_cache_release(old_page); } - reuse = reuse_swap_page(old_page); - if (reuse) + if (reuse_swap_page(old_page)) { /* * The page is all ours. Move it to our anon_vma so * the rmap code will not search our parent or siblings. * Protected against the rmap code by the page lock. */ page_move_anon_rmap(old_page, vma, address); + unlock_page(old_page); + goto reuse; + } unlock_page(old_page); } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { @@ -2212,7 +2288,6 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, &ptl); if (!pte_same(*page_table, orig_pte)) { unlock_page(old_page); - page_cache_release(old_page); goto unlock; } @@ -2220,18 +2295,52 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, } dirty_page = old_page; get_page(dirty_page); - reuse = 1; - } - if (reuse) { reuse: flush_cache_page(vma, address, pte_pfn(orig_pte)); entry = pte_mkyoung(orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, address, page_table, entry,1)) update_mmu_cache(vma, address, page_table); + pte_unmap_unlock(page_table, ptl); ret |= VM_FAULT_WRITE; - goto unlock; + + if (!dirty_page) + return ret; + + /* + * Yes, Virginia, this is actually required to prevent a race + * with clear_page_dirty_for_io() from clearing the page dirty + * bit after it clear all dirty ptes, but before a racing + * do_wp_page installs a dirty pte. + * + * do_no_page is protected similarly. + */ + if (!page_mkwrite) { + wait_on_page_locked(dirty_page); + set_page_dirty_balance(dirty_page, page_mkwrite); + } + put_page(dirty_page); + if (page_mkwrite) { + struct address_space *mapping = dirty_page->mapping; + + set_page_dirty(dirty_page); + unlock_page(dirty_page); + page_cache_release(dirty_page); + if (mapping) { + /* + * Some device drivers do not set page.mapping + * but still dirty their pages + */ + balance_dirty_pages_ratelimited(mapping); + } + } + + /* file_update_time outside page_lock */ + if (vma->vm_file) + file_update_time(vma->vm_file); + + return ret; } /* @@ -2256,16 +2365,6 @@ gotten: } __SetPageUptodate(new_page); - /* - * Don't let another task, with possibly unlocked vma, - * keep the mlocked page. - */ - if ((vma->vm_flags & VM_LOCKED) && old_page) { - lock_page(old_page); /* for LRU manipulation */ - clear_page_mlock(old_page); - unlock_page(old_page); - } - if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL)) goto oom_free_new; @@ -2333,42 +2432,19 @@ gotten: if (new_page) page_cache_release(new_page); - if (old_page) - page_cache_release(old_page); unlock: pte_unmap_unlock(page_table, ptl); - if (dirty_page) { + if (old_page) { /* - * Yes, Virginia, this is actually required to prevent a race - * with clear_page_dirty_for_io() from clearing the page dirty - * bit after it clear all dirty ptes, but before a racing - * do_wp_page installs a dirty pte. - * - * do_no_page is protected similarly. + * Don't let another task, with possibly unlocked vma, + * keep the mlocked page. */ - if (!page_mkwrite) { - wait_on_page_locked(dirty_page); - set_page_dirty_balance(dirty_page, page_mkwrite); - } - put_page(dirty_page); - if (page_mkwrite) { - struct address_space *mapping = dirty_page->mapping; - - set_page_dirty(dirty_page); - unlock_page(dirty_page); - page_cache_release(dirty_page); - if (mapping) { - /* - * Some device drivers do not set page.mapping - * but still dirty their pages - */ - balance_dirty_pages_ratelimited(mapping); - } + if ((ret & VM_FAULT_WRITE) && (vma->vm_flags & VM_LOCKED)) { + lock_page(old_page); /* LRU manipulation */ + munlock_vma_page(old_page); + unlock_page(old_page); } - - /* file_update_time outside page_lock */ - if (vma->vm_file) - file_update_time(vma->vm_file); + page_cache_release(old_page); } return ret; oom_free_new: @@ -2975,12 +3051,6 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, goto out; } charged = 1; - /* - * Don't let another task, with possibly unlocked vma, - * keep the mlocked page. - */ - if (vma->vm_flags & VM_LOCKED) - clear_page_mlock(vmf.page); copy_user_highpage(page, vmf.page, address, vma); __SetPageUptodate(page); } else { @@ -3147,9 +3217,9 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_sem still held, but pte unmapped and unlocked. */ -static inline int handle_pte_fault(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - pte_t *pte, pmd_t *pmd, unsigned int flags) +int handle_pte_fault(struct mm_struct *mm, + struct vm_area_struct *vma, unsigned long address, + pte_t *pte, pmd_t *pmd, unsigned int flags) { pte_t entry; spinlock_t *ptl; @@ -3228,9 +3298,40 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, pmd = pmd_alloc(mm, pud, address); if (!pmd) return VM_FAULT_OOM; - pte = pte_alloc_map(mm, pmd, address); - if (!pte) + if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) { + if (!vma->vm_ops) + return do_huge_pmd_anonymous_page(mm, vma, address, + pmd, flags); + } else { + pmd_t orig_pmd = *pmd; + barrier(); + if (pmd_trans_huge(orig_pmd)) { + if (flags & FAULT_FLAG_WRITE && + !pmd_write(orig_pmd) && + !pmd_trans_splitting(orig_pmd)) + return do_huge_pmd_wp_page(mm, vma, address, + pmd, orig_pmd); + return 0; + } + } + + /* + * Use __pte_alloc instead of pte_alloc_map, because we can't + * run pte_offset_map on the pmd, if an huge pmd could + * materialize from under us from a different thread. + */ + if (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))) + return 0; + /* + * A regular pmd is established and it can't morph into a huge pmd + * from under us anymore at this point because we hold the mmap_sem + * read mode and khugepaged takes it in write mode. So now it's + * safe to run pte_offset_map(). + */ + pte = pte_offset_map(pmd, address); return handle_pte_fault(mm, vma, address, pte, pmd, flags); } @@ -3296,7 +3397,12 @@ int make_pages_present(unsigned long addr, unsigned long end) vma = find_vma(current->mm, addr); if (!vma) return -ENOMEM; - write = (vma->vm_flags & VM_WRITE) != 0; + /* + * We want to touch writable mappings with a write fault in order + * to break COW, except for shared mappings because these don't COW + * and we would not want to dirty them for nothing. + */ + write = (vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE; BUG_ON(addr >= end); BUG_ON(end > vma->vm_end); len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE; @@ -3368,6 +3474,7 @@ static int __follow_pte(struct mm_struct *mm, unsigned long address, goto out; pmd = pmd_offset(pud, address); + VM_BUG_ON(pmd_trans_huge(*pmd)); if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) goto out; @@ -3608,3 +3715,74 @@ void might_fault(void) } EXPORT_SYMBOL(might_fault); #endif + +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) +static void clear_gigantic_page(struct page *page, + unsigned long addr, + unsigned int pages_per_huge_page) +{ + int i; + struct page *p = page; + + might_sleep(); + for (i = 0; i < pages_per_huge_page; + i++, p = mem_map_next(p, page, i)) { + cond_resched(); + clear_user_highpage(p, addr + i * PAGE_SIZE); + } +} +void clear_huge_page(struct page *page, + unsigned long addr, unsigned int pages_per_huge_page) +{ + int i; + + if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { + clear_gigantic_page(page, addr, pages_per_huge_page); + return; + } + + might_sleep(); + for (i = 0; i < pages_per_huge_page; i++) { + cond_resched(); + clear_user_highpage(page + i, addr + i * PAGE_SIZE); + } +} + +static void copy_user_gigantic_page(struct page *dst, struct page *src, + unsigned long addr, + struct vm_area_struct *vma, + unsigned int pages_per_huge_page) +{ + int i; + struct page *dst_base = dst; + struct page *src_base = src; + + for (i = 0; i < pages_per_huge_page; ) { + cond_resched(); + copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); + + i++; + dst = mem_map_next(dst, dst_base, i); + src = mem_map_next(src, src_base, i); + } +} + +void copy_user_huge_page(struct page *dst, struct page *src, + unsigned long addr, struct vm_area_struct *vma, + unsigned int pages_per_huge_page) +{ + int i; + + if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { + copy_user_gigantic_page(dst, src, addr, vma, + pages_per_huge_page); + return; + } + + might_sleep(); + for (i = 0; i < pages_per_huge_page; i++) { + cond_resched(); + copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma); + } +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 2c6523af547..321fc7455df 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -82,9 +82,10 @@ static void release_memory_resource(struct resource *res) #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE #ifndef CONFIG_SPARSEMEM_VMEMMAP -static void get_page_bootmem(unsigned long info, struct page *page, int type) +static void get_page_bootmem(unsigned long info, struct page *page, + unsigned long type) { - atomic_set(&page->_mapcount, type); + page->lru.next = (struct list_head *) type; SetPagePrivate(page); set_page_private(page, info); atomic_inc(&page->_count); @@ -94,15 +95,16 @@ static void get_page_bootmem(unsigned long info, struct page *page, int type) * so use __ref to tell modpost not to generate a warning */ void __ref put_page_bootmem(struct page *page) { - int type; + unsigned long type; - type = atomic_read(&page->_mapcount); - BUG_ON(type >= -1); + type = (unsigned long) page->lru.next; + BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || + type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE); if (atomic_dec_return(&page->_count) == 1) { ClearPagePrivate(page); set_page_private(page, 0); - reset_page_mapcount(page); + INIT_LIST_HEAD(&page->lru); __free_pages_bootmem(page, 0); } @@ -407,6 +409,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) int ret; struct memory_notify arg; + lock_memory_hotplug(); arg.start_pfn = pfn; arg.nr_pages = nr_pages; arg.status_change_nid = -1; @@ -419,6 +422,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) ret = notifier_to_errno(ret); if (ret) { memory_notify(MEM_CANCEL_ONLINE, &arg); + unlock_memory_hotplug(); return ret; } /* @@ -443,6 +447,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) printk(KERN_DEBUG "online_pages %lx at %lx failed\n", nr_pages, pfn); memory_notify(MEM_CANCEL_ONLINE, &arg); + unlock_memory_hotplug(); return ret; } @@ -467,6 +472,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) if (onlined_pages) memory_notify(MEM_ONLINE, &arg); + unlock_memory_hotplug(); return 0; } @@ -733,7 +739,8 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) goto out; } /* this function returns # of failed pages */ - ret = migrate_pages(&source, hotremove_migrate_alloc, 0, 1); + ret = migrate_pages(&source, hotremove_migrate_alloc, 0, + true, true); if (ret) putback_lru_pages(&source); } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 11ff260fb28..368fc9d2361 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -514,6 +514,7 @@ static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); + split_huge_page_pmd(vma->vm_mm, pmd); if (pmd_none_or_clear_bad(pmd)) continue; if (check_pte_range(vma, pmd, addr, next, nodes, @@ -935,7 +936,8 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, return PTR_ERR(vma); if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, new_node_page, dest, 0); + err = migrate_pages(&pagelist, new_node_page, dest, + false, true); if (err) putback_lru_pages(&pagelist); } @@ -1155,7 +1157,8 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { nr_failed = migrate_pages(&pagelist, new_vma_page, - (unsigned long)vma, 0); + (unsigned long)vma, + false, true); if (nr_failed) putback_lru_pages(&pagelist); } @@ -1308,16 +1311,13 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, /* Find the mm_struct */ rcu_read_lock(); - read_lock(&tasklist_lock); task = pid ? find_task_by_vpid(pid) : current; if (!task) { - read_unlock(&tasklist_lock); rcu_read_unlock(); err = -ESRCH; goto out; } mm = get_task_mm(task); - read_unlock(&tasklist_lock); rcu_read_unlock(); err = -EINVAL; @@ -1796,7 +1796,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, } /** - * alloc_page_vma - Allocate a page for a VMA. + * alloc_pages_vma - Allocate a page for a VMA. * * @gfp: * %GFP_USER user allocation. @@ -1805,6 +1805,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * %GFP_FS allocation should not call back into a file system. * %GFP_ATOMIC don't sleep. * + * @order:Order of the GFP allocation. * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. * @@ -1818,7 +1819,8 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * Should be called with the mm_sem of the vma hold. */ struct page * -alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) +alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr) { struct mempolicy *pol = get_vma_policy(current, vma, addr); struct zonelist *zl; @@ -1830,7 +1832,7 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) nid = interleave_nid(pol, vma, addr, PAGE_SHIFT); mpol_cond_put(pol); - page = alloc_page_interleave(gfp, 0, nid); + page = alloc_page_interleave(gfp, order, nid); put_mems_allowed(); return page; } @@ -1839,7 +1841,7 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) /* * slow path: ref counted shared policy */ - struct page *page = __alloc_pages_nodemask(gfp, 0, + struct page *page = __alloc_pages_nodemask(gfp, order, zl, policy_nodemask(gfp, pol)); __mpol_put(pol); put_mems_allowed(); @@ -1848,7 +1850,8 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) /* * fast path: default or task policy */ - page = __alloc_pages_nodemask(gfp, 0, zl, policy_nodemask(gfp, pol)); + page = __alloc_pages_nodemask(gfp, order, zl, + policy_nodemask(gfp, pol)); put_mems_allowed(); return page; } diff --git a/mm/migrate.c b/mm/migrate.c index 6ae8a66a704..76611525380 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -113,6 +113,8 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, goto out; pmd = pmd_offset(pud, addr); + if (pmd_trans_huge(*pmd)) + goto out; if (!pmd_present(*pmd)) goto out; @@ -246,7 +248,7 @@ static int migrate_page_move_mapping(struct address_space *mapping, expected_count = 2 + page_has_private(page); if (page_count(page) != expected_count || - (struct page *)radix_tree_deref_slot(pslot) != page) { + radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) { spin_unlock_irq(&mapping->tree_lock); return -EAGAIN; } @@ -318,7 +320,7 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, expected_count = 2 + page_has_private(page); if (page_count(page) != expected_count || - (struct page *)radix_tree_deref_slot(pslot) != page) { + radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) { spin_unlock_irq(&mapping->tree_lock); return -EAGAIN; } @@ -614,13 +616,12 @@ static int move_to_new_page(struct page *newpage, struct page *page, * to the newly allocated page in newpage. */ static int unmap_and_move(new_page_t get_new_page, unsigned long private, - struct page *page, int force, int offlining) + struct page *page, int force, bool offlining, bool sync) { int rc = 0; int *result = NULL; struct page *newpage = get_new_page(page, private, &result); int remap_swapcache = 1; - int rcu_locked = 0; int charge = 0; struct mem_cgroup *mem = NULL; struct anon_vma *anon_vma = NULL; @@ -632,6 +633,9 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, /* page was freed from under us. So we are done. */ goto move_newpage; } + if (unlikely(PageTransHuge(page))) + if (unlikely(split_huge_page(page))) + goto move_newpage; /* prepare cgroup just returns 0 or -ENOMEM */ rc = -EAGAIN; @@ -639,6 +643,23 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, if (!trylock_page(page)) { if (!force) goto move_newpage; + + /* + * It's not safe for direct compaction to call lock_page. + * For example, during page readahead pages are added locked + * to the LRU. Later, when the IO completes the pages are + * marked uptodate and unlocked. However, the queueing + * could be merging multiple pages for one bio (e.g. + * mpage_readpages). If an allocation happens for the + * second or third page, the process can end up locking + * the same page twice and deadlocking. Rather than + * trying to be clever about what pages can be locked, + * avoid the use of lock_page for direct compaction + * altogether. + */ + if (current->flags & PF_MEMALLOC) + goto move_newpage; + lock_page(page); } @@ -665,27 +686,33 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, BUG_ON(charge); if (PageWriteback(page)) { - if (!force) + if (!force || !sync) goto uncharge; wait_on_page_writeback(page); } /* * By try_to_unmap(), page->mapcount goes down to 0 here. In this case, * we cannot notice that anon_vma is freed while we migrates a page. - * This rcu_read_lock() delays freeing anon_vma pointer until the end + * This get_anon_vma() delays freeing anon_vma pointer until the end * of migration. File cache pages are no problem because of page_lock() * File Caches may use write_page() or lock_page() in migration, then, * just care Anon page here. */ if (PageAnon(page)) { - rcu_read_lock(); - rcu_locked = 1; - - /* Determine how to safely use anon_vma */ - if (!page_mapped(page)) { - if (!PageSwapCache(page)) - goto rcu_unlock; - + /* + * Only page_lock_anon_vma() understands the subtleties of + * getting a hold on an anon_vma from outside one of its mms. + */ + anon_vma = page_lock_anon_vma(page); + if (anon_vma) { + /* + * Take a reference count on the anon_vma if the + * page is mapped so that it is guaranteed to + * exist when the page is remapped later + */ + get_anon_vma(anon_vma); + page_unlock_anon_vma(anon_vma); + } else if (PageSwapCache(page)) { /* * We cannot be sure that the anon_vma of an unmapped * swapcache page is safe to use because we don't @@ -700,13 +727,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, */ remap_swapcache = 0; } else { - /* - * Take a reference count on the anon_vma if the - * page is mapped so that it is guaranteed to - * exist when the page is remapped later - */ - anon_vma = page_anon_vma(page); - get_anon_vma(anon_vma); + goto uncharge; } } @@ -723,16 +744,10 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, * free the metadata, so the page can be freed. */ if (!page->mapping) { - if (!PageAnon(page) && page_has_private(page)) { - /* - * Go direct to try_to_free_buffers() here because - * a) that's what try_to_release_page() would do anyway - * b) we may be under rcu_read_lock() here, so we can't - * use GFP_KERNEL which is what try_to_release_page() - * needs to be effective. - */ + VM_BUG_ON(PageAnon(page)); + if (page_has_private(page)) { try_to_free_buffers(page); - goto rcu_unlock; + goto uncharge; } goto skip_unmap; } @@ -746,20 +761,18 @@ skip_unmap: if (rc && remap_swapcache) remove_migration_ptes(page, page); -rcu_unlock: /* Drop an anon_vma reference if we took one */ if (anon_vma) drop_anon_vma(anon_vma); - if (rcu_locked) - rcu_read_unlock(); uncharge: if (!charge) - mem_cgroup_end_migration(mem, page, newpage); + mem_cgroup_end_migration(mem, page, newpage, rc == 0); unlock: unlock_page(page); +move_newpage: if (rc != -EAGAIN) { /* * A page that has been migrated has all references @@ -773,8 +786,6 @@ unlock: putback_lru_page(page); } -move_newpage: - /* * Move the new page to the LRU. If migration was not successful * then this will free the page. @@ -810,12 +821,11 @@ move_newpage: */ static int unmap_and_move_huge_page(new_page_t get_new_page, unsigned long private, struct page *hpage, - int force, int offlining) + int force, bool offlining, bool sync) { int rc = 0; int *result = NULL; struct page *new_hpage = get_new_page(hpage, private, &result); - int rcu_locked = 0; struct anon_vma *anon_vma = NULL; if (!new_hpage) @@ -824,18 +834,16 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, rc = -EAGAIN; if (!trylock_page(hpage)) { - if (!force) + if (!force || !sync) goto out; lock_page(hpage); } if (PageAnon(hpage)) { - rcu_read_lock(); - rcu_locked = 1; - - if (page_mapped(hpage)) { - anon_vma = page_anon_vma(hpage); - atomic_inc(&anon_vma->external_refcount); + anon_vma = page_lock_anon_vma(hpage); + if (anon_vma) { + get_anon_vma(anon_vma); + page_unlock_anon_vma(anon_vma); } } @@ -847,16 +855,8 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (rc) remove_migration_ptes(hpage, hpage); - if (anon_vma && atomic_dec_and_lock(&anon_vma->external_refcount, - &anon_vma->lock)) { - int empty = list_empty(&anon_vma->head); - spin_unlock(&anon_vma->lock); - if (empty) - anon_vma_free(anon_vma); - } - - if (rcu_locked) - rcu_read_unlock(); + if (anon_vma) + drop_anon_vma(anon_vma); out: unlock_page(hpage); @@ -887,12 +887,13 @@ out: * are movable anymore because to has become empty * or no retryable pages exist anymore. * Caller should call putback_lru_pages to return pages to the LRU - * or free list. + * or free list only if ret != 0. * * Return: Number of pages not migrated or error code. */ int migrate_pages(struct list_head *from, - new_page_t get_new_page, unsigned long private, int offlining) + new_page_t get_new_page, unsigned long private, bool offlining, + bool sync) { int retry = 1; int nr_failed = 0; @@ -912,7 +913,8 @@ int migrate_pages(struct list_head *from, cond_resched(); rc = unmap_and_move(get_new_page, private, - page, pass > 2, offlining); + page, pass > 2, offlining, + sync); switch(rc) { case -ENOMEM: @@ -941,7 +943,8 @@ out: } int migrate_huge_pages(struct list_head *from, - new_page_t get_new_page, unsigned long private, int offlining) + new_page_t get_new_page, unsigned long private, bool offlining, + bool sync) { int retry = 1; int nr_failed = 0; @@ -957,7 +960,8 @@ int migrate_huge_pages(struct list_head *from, cond_resched(); rc = unmap_and_move_huge_page(get_new_page, - private, page, pass > 2, offlining); + private, page, pass > 2, offlining, + sync); switch(rc) { case -ENOMEM: @@ -976,10 +980,6 @@ int migrate_huge_pages(struct list_head *from, } rc = 0; out: - - list_for_each_entry_safe(page, page2, from, lru) - put_page(page); - if (rc) return rc; @@ -1042,7 +1042,7 @@ static int do_move_page_to_node_array(struct mm_struct *mm, if (!vma || pp->addr < vma->vm_start || !vma_migratable(vma)) goto set_status; - page = follow_page(vma, pp->addr, FOLL_GET); + page = follow_page(vma, pp->addr, FOLL_GET|FOLL_SPLIT); err = PTR_ERR(page); if (IS_ERR(page)) @@ -1090,7 +1090,7 @@ set_status: err = 0; if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, new_page_node, - (unsigned long)pm, 0); + (unsigned long)pm, 0, true); if (err) putback_lru_pages(&pagelist); } diff --git a/mm/mincore.c b/mm/mincore.c index 9ac42dc6d7b..a4e6b9d75c7 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -154,6 +154,13 @@ static void mincore_pmd_range(struct vm_area_struct *vma, pud_t *pud, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); + if (pmd_trans_huge(*pmd)) { + if (mincore_huge_pmd(vma, pmd, addr, next, vec)) { + vec += (next - addr) >> PAGE_SHIFT; + continue; + } + /* fall through */ + } if (pmd_none_or_clear_bad(pmd)) mincore_unmapped_range(vma, addr, next, vec); else diff --git a/mm/mlock.c b/mm/mlock.c index b70919ce4f7..c3924c7f00b 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -155,13 +155,12 @@ static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long add * vma->vm_mm->mmap_sem must be held for at least read. */ static long __mlock_vma_pages_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) + unsigned long start, unsigned long end, + int *nonblocking) { struct mm_struct *mm = vma->vm_mm; unsigned long addr = start; - struct page *pages[16]; /* 16 gives a reasonable batch */ int nr_pages = (end - start) / PAGE_SIZE; - int ret = 0; int gup_flags; VM_BUG_ON(start & ~PAGE_MASK); @@ -170,73 +169,33 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma, VM_BUG_ON(end > vma->vm_end); VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem)); - gup_flags = FOLL_TOUCH | FOLL_GET; - if (vma->vm_flags & VM_WRITE) + gup_flags = FOLL_TOUCH; + /* + * We want to touch writable mappings with a write fault in order + * to break COW, except for shared mappings because these don't COW + * and we would not want to dirty them for nothing. + */ + if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) gup_flags |= FOLL_WRITE; + /* + * We want mlock to succeed for regions that have any permissions + * other than PROT_NONE. + */ + if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) + gup_flags |= FOLL_FORCE; + + if (vma->vm_flags & VM_LOCKED) + gup_flags |= FOLL_MLOCK; + /* We don't try to access the guard page of a stack vma */ if (stack_guard_page(vma, start)) { addr += PAGE_SIZE; nr_pages--; } - while (nr_pages > 0) { - int i; - - cond_resched(); - - /* - * get_user_pages makes pages present if we are - * setting mlock. and this extra reference count will - * disable migration of this page. However, page may - * still be truncated out from under us. - */ - ret = __get_user_pages(current, mm, addr, - min_t(int, nr_pages, ARRAY_SIZE(pages)), - gup_flags, pages, NULL); - /* - * This can happen for, e.g., VM_NONLINEAR regions before - * a page has been allocated and mapped at a given offset, - * or for addresses that map beyond end of a file. - * We'll mlock the pages if/when they get faulted in. - */ - if (ret < 0) - break; - - lru_add_drain(); /* push cached pages to LRU */ - - for (i = 0; i < ret; i++) { - struct page *page = pages[i]; - - if (page->mapping) { - /* - * That preliminary check is mainly to avoid - * the pointless overhead of lock_page on the - * ZERO_PAGE: which might bounce very badly if - * there is contention. However, we're still - * dirtying its cacheline with get/put_page: - * we'll add another __get_user_pages flag to - * avoid it if that case turns out to matter. - */ - lock_page(page); - /* - * Because we lock page here and migration is - * blocked by the elevated reference, we need - * only check for file-cache page truncation. - */ - if (page->mapping) - mlock_vma_page(page); - unlock_page(page); - } - put_page(page); /* ref from get_user_pages() */ - } - - addr += ret * PAGE_SIZE; - nr_pages -= ret; - ret = 0; - } - - return ret; /* 0 or negative error code */ + return __get_user_pages(current, mm, addr, nr_pages, gup_flags, + NULL, NULL, nonblocking); } /* @@ -280,7 +239,7 @@ long mlock_vma_pages_range(struct vm_area_struct *vma, is_vm_hugetlb_page(vma) || vma == get_gate_vma(current))) { - __mlock_vma_pages_range(vma, start, end); + __mlock_vma_pages_range(vma, start, end, NULL); /* Hide errors from mmap() and other callers */ return 0; @@ -372,18 +331,10 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev, int ret = 0; int lock = newflags & VM_LOCKED; - if (newflags == vma->vm_flags || - (vma->vm_flags & (VM_IO | VM_PFNMAP))) + if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) || + is_vm_hugetlb_page(vma) || vma == get_gate_vma(current)) goto out; /* don't set VM_LOCKED, don't count */ - if ((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) || - is_vm_hugetlb_page(vma) || - vma == get_gate_vma(current)) { - if (lock) - make_pages_present(start, end); - goto out; /* don't set VM_LOCKED, don't count */ - } - pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma)); @@ -419,14 +370,10 @@ success: * set VM_LOCKED, __mlock_vma_pages_range will bring it back. */ - if (lock) { + if (lock) vma->vm_flags = newflags; - ret = __mlock_vma_pages_range(vma, start, end); - if (ret < 0) - ret = __mlock_posix_error_return(ret); - } else { + else munlock_vma_pages_range(vma, start, end); - } out: *prev = vma; @@ -439,7 +386,8 @@ static int do_mlock(unsigned long start, size_t len, int on) struct vm_area_struct * vma, * prev; int error; - len = PAGE_ALIGN(len); + VM_BUG_ON(start & ~PAGE_MASK); + VM_BUG_ON(len != PAGE_ALIGN(len)); end = start + len; if (end < start) return -EINVAL; @@ -482,6 +430,62 @@ static int do_mlock(unsigned long start, size_t len, int on) return error; } +static int do_mlock_pages(unsigned long start, size_t len, int ignore_errors) +{ + struct mm_struct *mm = current->mm; + unsigned long end, nstart, nend; + struct vm_area_struct *vma = NULL; + int locked = 0; + int ret = 0; + + VM_BUG_ON(start & ~PAGE_MASK); + VM_BUG_ON(len != PAGE_ALIGN(len)); + end = start + len; + + for (nstart = start; nstart < end; nstart = nend) { + /* + * We want to fault in pages for [nstart; end) address range. + * Find first corresponding VMA. + */ + if (!locked) { + locked = 1; + down_read(&mm->mmap_sem); + vma = find_vma(mm, nstart); + } else if (nstart >= vma->vm_end) + vma = vma->vm_next; + if (!vma || vma->vm_start >= end) + break; + /* + * Set [nstart; nend) to intersection of desired address + * range with the first VMA. Also, skip undesirable VMA types. + */ + nend = min(end, vma->vm_end); + if (vma->vm_flags & (VM_IO | VM_PFNMAP)) + continue; + if (nstart < vma->vm_start) + nstart = vma->vm_start; + /* + * Now fault in a range of pages. __mlock_vma_pages_range() + * double checks the vma flags, so that it won't mlock pages + * if the vma was already munlocked. + */ + ret = __mlock_vma_pages_range(vma, nstart, nend, &locked); + if (ret < 0) { + if (ignore_errors) { + ret = 0; + continue; /* continue at next VMA */ + } + ret = __mlock_posix_error_return(ret); + break; + } + nend = nstart + ret * PAGE_SIZE; + ret = 0; + } + if (locked) + up_read(&mm->mmap_sem); + return ret; /* 0 or negative error code */ +} + SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) { unsigned long locked; @@ -507,6 +511,8 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) if ((locked <= lock_limit) || capable(CAP_IPC_LOCK)) error = do_mlock(start, len, 1); up_write(¤t->mm->mmap_sem); + if (!error) + error = do_mlock_pages(start, len, 0); return error; } @@ -571,6 +577,10 @@ SYSCALL_DEFINE1(mlockall, int, flags) capable(CAP_IPC_LOCK)) ret = do_mlockall(flags); up_write(¤t->mm->mmap_sem); + if (!ret && (flags & MCL_CURRENT)) { + /* Ignore errors */ + do_mlock_pages(0, TASK_SIZE, 1); + } out: return ret; } diff --git a/mm/mmap.c b/mm/mmap.c index 50a4aa0255a..2ec8eb5a9cd 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -29,6 +29,7 @@ #include <linux/mmu_notifier.h> #include <linux/perf_event.h> #include <linux/audit.h> +#include <linux/khugepaged.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> @@ -253,7 +254,15 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) down_write(&mm->mmap_sem); #ifdef CONFIG_COMPAT_BRK - min_brk = mm->end_code; + /* + * CONFIG_COMPAT_BRK can still be overridden by setting + * randomize_va_space to 2, which will still cause mm->start_brk + * to be arbitrarily shifted + */ + if (mm->start_brk > PAGE_ALIGN(mm->end_data)) + min_brk = mm->start_brk; + else + min_brk = mm->end_data; #else min_brk = mm->start_brk; #endif @@ -588,6 +597,8 @@ again: remove_next = 1 + (end > next->vm_end); } } + vma_adjust_trans_huge(vma, start, end, adjust_next); + /* * When changing only vma->vm_end, we don't really need anon_vma * lock. This is a fairly rare case by itself, but the anon_vma @@ -815,6 +826,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, end, prev->vm_pgoff, NULL); if (err) return NULL; + khugepaged_enter_vma_merge(prev); return prev; } @@ -833,6 +845,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, next->vm_pgoff - pglen, NULL); if (err) return NULL; + khugepaged_enter_vma_merge(area); return area; } @@ -1761,6 +1774,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) } } vma_unlock_anon_vma(vma); + khugepaged_enter_vma_merge(vma); return error; } #endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */ @@ -1808,6 +1822,7 @@ static int expand_downwards(struct vm_area_struct *vma, } } vma_unlock_anon_vma(vma); + khugepaged_enter_vma_merge(vma); return error; } diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 438951d366f..8d032de4088 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -100,6 +100,26 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm, return young; } +int __mmu_notifier_test_young(struct mm_struct *mm, + unsigned long address) +{ + struct mmu_notifier *mn; + struct hlist_node *n; + int young = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops->test_young) { + young = mn->ops->test_young(mn, mm, address); + if (young) + break; + } + } + rcu_read_unlock(); + + return young; +} + void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte) { diff --git a/mm/mmzone.c b/mm/mmzone.c index e35bfb82c85..f5b7d176021 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -87,24 +87,3 @@ int memmap_valid_within(unsigned long pfn, return 1; } #endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */ - -#ifdef CONFIG_SMP -/* Called when a more accurate view of NR_FREE_PAGES is needed */ -unsigned long zone_nr_free_pages(struct zone *zone) -{ - unsigned long nr_free_pages = zone_page_state(zone, NR_FREE_PAGES); - - /* - * While kswapd is awake, it is considered the zone is under some - * memory pressure. Under pressure, there is a risk that - * per-cpu-counter-drift will allow the min watermark to be breached - * potentially causing a live-lock. While kswapd is awake and - * free pages are low, get a better estimate for free pages - */ - if (nr_free_pages < zone->percpu_drift_mark && - !waitqueue_active(&zone->zone_pgdat->kswapd_wait)) - return zone_page_state_snapshot(zone, NR_FREE_PAGES); - - return nr_free_pages; -} -#endif /* CONFIG_SMP */ diff --git a/mm/mprotect.c b/mm/mprotect.c index 4c513387309..5a688a2756b 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -78,7 +78,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd, pte_unmap_unlock(pte - 1, ptl); } -static inline void change_pmd_range(struct mm_struct *mm, pud_t *pud, +static inline void change_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable) { @@ -88,13 +88,21 @@ static inline void change_pmd_range(struct mm_struct *mm, pud_t *pud, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); + if (pmd_trans_huge(*pmd)) { + if (next - addr != HPAGE_PMD_SIZE) + split_huge_page_pmd(vma->vm_mm, pmd); + else if (change_huge_pmd(vma, pmd, addr, newprot)) + continue; + /* fall through */ + } if (pmd_none_or_clear_bad(pmd)) continue; - change_pte_range(mm, pmd, addr, next, newprot, dirty_accountable); + change_pte_range(vma->vm_mm, pmd, addr, next, newprot, + dirty_accountable); } while (pmd++, addr = next, addr != end); } -static inline void change_pud_range(struct mm_struct *mm, pgd_t *pgd, +static inline void change_pud_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable) { @@ -106,7 +114,8 @@ static inline void change_pud_range(struct mm_struct *mm, pgd_t *pgd, next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; - change_pmd_range(mm, pud, addr, next, newprot, dirty_accountable); + change_pmd_range(vma, pud, addr, next, newprot, + dirty_accountable); } while (pud++, addr = next, addr != end); } @@ -126,7 +135,8 @@ static void change_protection(struct vm_area_struct *vma, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - change_pud_range(mm, pgd, addr, next, newprot, dirty_accountable); + change_pud_range(vma, pgd, addr, next, newprot, + dirty_accountable); } while (pgd++, addr = next, addr != end); flush_tlb_range(vma, start, end); } diff --git a/mm/mremap.c b/mm/mremap.c index 563fbdd6293..9925b6391b8 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -41,13 +41,15 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr) return NULL; pmd = pmd_offset(pud, addr); + split_huge_page_pmd(mm, pmd); if (pmd_none_or_clear_bad(pmd)) return NULL; return pmd; } -static pmd_t *alloc_new_pmd(struct mm_struct *mm, unsigned long addr) +static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr) { pgd_t *pgd; pud_t *pud; @@ -62,7 +64,8 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, unsigned long addr) if (!pmd) return NULL; - if (!pmd_present(*pmd) && __pte_alloc(mm, pmd, addr)) + VM_BUG_ON(pmd_trans_huge(*pmd)); + if (pmd_none(*pmd) && __pte_alloc(mm, vma, pmd, addr)) return NULL; return pmd; @@ -147,7 +150,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma, old_pmd = get_old_pmd(vma->vm_mm, old_addr); if (!old_pmd) continue; - new_pmd = alloc_new_pmd(vma->vm_mm, new_addr); + new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr); if (!new_pmd) break; next = (new_addr + PMD_SIZE) & PMD_MASK; diff --git a/mm/nommu.c b/mm/nommu.c index ef4045d010d..f59e1424d3d 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -127,7 +127,8 @@ unsigned int kobjsize(const void *objp) int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int nr_pages, unsigned int foll_flags, - struct page **pages, struct vm_area_struct **vmas) + struct page **pages, struct vm_area_struct **vmas, + int *retry) { struct vm_area_struct *vma; unsigned long vm_flags; @@ -185,7 +186,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (force) flags |= FOLL_FORCE; - return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas); + return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas, + NULL); } EXPORT_SYMBOL(get_user_pages); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index b4edfe7ce06..2cb01f6ec5d 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -404,15 +404,18 @@ unsigned long determine_dirtyable_memory(void) * - vm.dirty_background_ratio or vm.dirty_background_bytes * - vm.dirty_ratio or vm.dirty_bytes * The dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and - * runtime tasks. + * real-time tasks. */ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) { unsigned long background; unsigned long dirty; - unsigned long available_memory = determine_dirtyable_memory(); + unsigned long uninitialized_var(available_memory); struct task_struct *tsk; + if (!vm_dirty_bytes || !dirty_background_bytes) + available_memory = determine_dirtyable_memory(); + if (vm_dirty_bytes) dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE); else @@ -1103,7 +1106,7 @@ EXPORT_SYMBOL(write_one_page); int __set_page_dirty_no_writeback(struct page *page) { if (!PageDirty(page)) - SetPageDirty(page); + return !TestSetPageDirty(page); return 0; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ff7e1587239..a873e61e312 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -357,6 +357,7 @@ void prep_compound_page(struct page *page, unsigned long order) } } +/* update __split_huge_page_refcount if you change this function */ static int destroy_compound_page(struct page *page, unsigned long order) { int i; @@ -426,18 +427,10 @@ static inline void rmv_page_order(struct page *page) * * Assumption: *_mem_map is contiguous at least up to MAX_ORDER */ -static inline struct page * -__page_find_buddy(struct page *page, unsigned long page_idx, unsigned int order) -{ - unsigned long buddy_idx = page_idx ^ (1 << order); - - return page + (buddy_idx - page_idx); -} - static inline unsigned long -__find_combined_index(unsigned long page_idx, unsigned int order) +__find_buddy_index(unsigned long page_idx, unsigned int order) { - return (page_idx & ~(1 << order)); + return page_idx ^ (1 << order); } /* @@ -448,8 +441,8 @@ __find_combined_index(unsigned long page_idx, unsigned int order) * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. * - * For recording whether a page is in the buddy system, we use PG_buddy. - * Setting, clearing, and testing PG_buddy is serialized by zone->lock. + * For recording whether a page is in the buddy system, we set ->_mapcount -2. + * Setting, clearing, and testing _mapcount -2 is serialized by zone->lock. * * For recording page's order, we use page_private(page). */ @@ -482,7 +475,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, * as necessary, plus some accounting needed to play nicely with other * parts of the VM system. * At each level, we keep a list of pages, which are heads of continuous - * free pages of length of (1 << order) and marked with PG_buddy. Page's + * free pages of length of (1 << order) and marked with _mapcount -2. Page's * order is recorded in page_private(page) field. * So when we are allocating or freeing one, we can derive the state of the * other. That is, if we allocate a small block, and both were @@ -499,6 +492,7 @@ static inline void __free_one_page(struct page *page, { unsigned long page_idx; unsigned long combined_idx; + unsigned long uninitialized_var(buddy_idx); struct page *buddy; if (unlikely(PageCompound(page))) @@ -513,7 +507,8 @@ static inline void __free_one_page(struct page *page, VM_BUG_ON(bad_range(zone, page)); while (order < MAX_ORDER-1) { - buddy = __page_find_buddy(page, page_idx, order); + buddy_idx = __find_buddy_index(page_idx, order); + buddy = page + (buddy_idx - page_idx); if (!page_is_buddy(page, buddy, order)) break; @@ -521,7 +516,7 @@ static inline void __free_one_page(struct page *page, list_del(&buddy->lru); zone->free_area[order].nr_free--; rmv_page_order(buddy); - combined_idx = __find_combined_index(page_idx, order); + combined_idx = buddy_idx & page_idx; page = page + (combined_idx - page_idx); page_idx = combined_idx; order++; @@ -538,9 +533,10 @@ static inline void __free_one_page(struct page *page, */ if ((order < MAX_ORDER-2) && pfn_valid_within(page_to_pfn(buddy))) { struct page *higher_page, *higher_buddy; - combined_idx = __find_combined_index(page_idx, order); - higher_page = page + combined_idx - page_idx; - higher_buddy = __page_find_buddy(higher_page, combined_idx, order + 1); + combined_idx = buddy_idx & page_idx; + higher_page = page + (combined_idx - page_idx); + buddy_idx = __find_buddy_index(combined_idx, order + 1); + higher_buddy = page + (buddy_idx - combined_idx); if (page_is_buddy(higher_page, higher_buddy, order + 1)) { list_add_tail(&page->lru, &zone->free_area[order].free_list[migratetype]); @@ -651,13 +647,10 @@ static bool free_pages_prepare(struct page *page, unsigned int order) trace_mm_page_free_direct(page, order); kmemcheck_free_shadow(page, order); - for (i = 0; i < (1 << order); i++) { - struct page *pg = page + i; - - if (PageAnon(pg)) - pg->mapping = NULL; - bad += free_pages_check(pg); - } + if (PageAnon(page)) + page->mapping = NULL; + for (i = 0; i < (1 << order); i++) + bad += free_pages_check(page + i); if (bad) return false; @@ -1095,8 +1088,10 @@ static void drain_pages(unsigned int cpu) pset = per_cpu_ptr(zone->pageset, cpu); pcp = &pset->pcp; - free_pcppages_bulk(zone, pcp->count, pcp); - pcp->count = 0; + if (pcp->count) { + free_pcppages_bulk(zone, pcp->count, pcp); + pcp->count = 0; + } local_irq_restore(flags); } } @@ -1460,24 +1455,24 @@ static inline int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) #endif /* CONFIG_FAIL_PAGE_ALLOC */ /* - * Return 1 if free pages are above 'mark'. This takes into account the order + * Return true if free pages are above 'mark'. This takes into account the order * of the allocation. */ -int zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags) +static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, + int classzone_idx, int alloc_flags, long free_pages) { /* free_pages my go negative - that's OK */ long min = mark; - long free_pages = zone_nr_free_pages(z) - (1 << order) + 1; int o; + free_pages -= (1 << order) + 1; if (alloc_flags & ALLOC_HIGH) min -= min / 2; if (alloc_flags & ALLOC_HARDER) min -= min / 4; if (free_pages <= min + z->lowmem_reserve[classzone_idx]) - return 0; + return false; for (o = 0; o < order; o++) { /* At the next order, this order's pages become unavailable */ free_pages -= z->free_area[o].nr_free << o; @@ -1486,9 +1481,28 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark, min >>= 1; if (free_pages <= min) - return 0; + return false; } - return 1; + return true; +} + +bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, + int classzone_idx, int alloc_flags) +{ + return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, + zone_page_state(z, NR_FREE_PAGES)); +} + +bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, + int classzone_idx, int alloc_flags) +{ + long free_pages = zone_page_state(z, NR_FREE_PAGES); + + if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark) + free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES); + + return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, + free_pages); } #ifdef CONFIG_NUMA @@ -1793,15 +1807,18 @@ static struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress) + int migratetype, unsigned long *did_some_progress, + bool sync_migration) { struct page *page; if (!order || compaction_deferred(preferred_zone)) return NULL; + current->flags |= PF_MEMALLOC; *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, - nodemask); + nodemask, sync_migration); + current->flags &= ~PF_MEMALLOC; if (*did_some_progress != COMPACT_SKIPPED) { /* Page migration frees to the PCP lists but we want merging */ @@ -1837,7 +1854,8 @@ static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress) + int migratetype, unsigned long *did_some_progress, + bool sync_migration) { return NULL; } @@ -1852,23 +1870,22 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, { struct page *page = NULL; struct reclaim_state reclaim_state; - struct task_struct *p = current; bool drained = false; cond_resched(); /* We now go into synchronous reclaim */ cpuset_memory_pressure_bump(); - p->flags |= PF_MEMALLOC; + current->flags |= PF_MEMALLOC; lockdep_set_current_reclaim_state(gfp_mask); reclaim_state.reclaimed_slab = 0; - p->reclaim_state = &reclaim_state; + current->reclaim_state = &reclaim_state; *did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask); - p->reclaim_state = NULL; + current->reclaim_state = NULL; lockdep_clear_current_reclaim_state(); - p->flags &= ~PF_MEMALLOC; + current->flags &= ~PF_MEMALLOC; cond_resched(); @@ -1920,19 +1937,19 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, static inline void wake_all_kswapd(unsigned int order, struct zonelist *zonelist, - enum zone_type high_zoneidx) + enum zone_type high_zoneidx, + enum zone_type classzone_idx) { struct zoneref *z; struct zone *zone; for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) - wakeup_kswapd(zone, order); + wakeup_kswapd(zone, order, classzone_idx); } static inline int gfp_to_alloc_flags(gfp_t gfp_mask) { - struct task_struct *p = current; int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; const gfp_t wait = gfp_mask & __GFP_WAIT; @@ -1948,18 +1965,23 @@ gfp_to_alloc_flags(gfp_t gfp_mask) alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); if (!wait) { - alloc_flags |= ALLOC_HARDER; + /* + * Not worth trying to allocate harder for + * __GFP_NOMEMALLOC even if it can't schedule. + */ + if (!(gfp_mask & __GFP_NOMEMALLOC)) + alloc_flags |= ALLOC_HARDER; /* * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. * See also cpuset_zone_allowed() comment in kernel/cpuset.c. */ alloc_flags &= ~ALLOC_CPUSET; - } else if (unlikely(rt_task(p)) && !in_interrupt()) + } else if (unlikely(rt_task(current)) && !in_interrupt()) alloc_flags |= ALLOC_HARDER; if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) { if (!in_interrupt() && - ((p->flags & PF_MEMALLOC) || + ((current->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))) alloc_flags |= ALLOC_NO_WATERMARKS; } @@ -1978,7 +2000,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, int alloc_flags; unsigned long pages_reclaimed = 0; unsigned long did_some_progress; - struct task_struct *p = current; + bool sync_migration = false; /* * In the slowpath, we sanity check order to avoid ever trying to @@ -2003,7 +2025,9 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, goto nopage; restart: - wake_all_kswapd(order, zonelist, high_zoneidx); + if (!(gfp_mask & __GFP_NO_KSWAPD)) + wake_all_kswapd(order, zonelist, high_zoneidx, + zone_idx(preferred_zone)); /* * OK, we're below the kswapd watermark and have kicked background @@ -2012,6 +2036,14 @@ restart: */ alloc_flags = gfp_to_alloc_flags(gfp_mask); + /* + * Find the true preferred zone if the allocation is unconstrained by + * cpusets. + */ + if (!(alloc_flags & ALLOC_CPUSET) && !nodemask) + first_zones_zonelist(zonelist, high_zoneidx, NULL, + &preferred_zone); + /* This is the last chance, in general, before the goto nopage. */ page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, @@ -2034,21 +2066,26 @@ rebalance: goto nopage; /* Avoid recursion of direct reclaim */ - if (p->flags & PF_MEMALLOC) + if (current->flags & PF_MEMALLOC) goto nopage; /* Avoid allocations with no watermarks from looping endlessly */ if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL)) goto nopage; - /* Try direct compaction */ + /* + * Try direct compaction. The first pass is asynchronous. Subsequent + * attempts after direct reclaim are synchronous + */ page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, high_zoneidx, nodemask, alloc_flags, preferred_zone, - migratetype, &did_some_progress); + migratetype, &did_some_progress, + sync_migration); if (page) goto got_pg; + sync_migration = true; /* Try direct reclaim and then allocating */ page = __alloc_pages_direct_reclaim(gfp_mask, order, @@ -2102,13 +2139,27 @@ rebalance: /* Wait for some write requests to complete then retry */ wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); goto rebalance; + } else { + /* + * High-order allocations do not necessarily loop after + * direct reclaim and reclaim/compaction depends on compaction + * being called after reclaim so call directly if necessary + */ + page = __alloc_pages_direct_compact(gfp_mask, order, + zonelist, high_zoneidx, + nodemask, + alloc_flags, preferred_zone, + migratetype, &did_some_progress, + sync_migration); + if (page) + goto got_pg; } nopage: if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) { printk(KERN_WARNING "%s: page allocation failure." " order:%d, mode:0x%x\n", - p->comm, order, gfp_mask); + current->comm, order, gfp_mask); dump_stack(); show_mem(); } @@ -2151,7 +2202,9 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, get_mems_allowed(); /* The preferred zone is used for statistics later */ - first_zones_zonelist(zonelist, high_zoneidx, nodemask, &preferred_zone); + first_zones_zonelist(zonelist, high_zoneidx, + nodemask ? : &cpuset_current_mems_allowed, + &preferred_zone); if (!preferred_zone) { put_mems_allowed(); return NULL; @@ -2442,7 +2495,7 @@ void show_free_areas(void) " all_unreclaimable? %s" "\n", zone->name, - K(zone_nr_free_pages(zone)), + K(zone_page_state(zone, NR_FREE_PAGES)), K(min_wmark_pages(zone)), K(low_wmark_pages(zone)), K(high_wmark_pages(zone)), @@ -2585,9 +2638,16 @@ static int __parse_numa_zonelist_order(char *s) static __init int setup_numa_zonelist_order(char *s) { - if (s) - return __parse_numa_zonelist_order(s); - return 0; + int ret; + + if (!s) + return 0; + + ret = __parse_numa_zonelist_order(s); + if (ret == 0) + strlcpy(numa_zonelist_order, s, NUMA_ZONELIST_ORDER_LEN); + + return ret; } early_param("numa_zonelist_order", setup_numa_zonelist_order); @@ -4014,7 +4074,7 @@ static void __init setup_usemap(struct pglist_data *pgdat, zone->pageblock_flags = alloc_bootmem_node(pgdat, usemapsize); } #else -static void inline setup_usemap(struct pglist_data *pgdat, +static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone, unsigned long zonesize) {} #endif /* CONFIG_SPARSEMEM */ @@ -5517,7 +5577,6 @@ static struct trace_print_flags pageflag_names[] = { {1UL << PG_swapcache, "swapcache" }, {1UL << PG_mappedtodisk, "mappedtodisk" }, {1UL << PG_reclaim, "reclaim" }, - {1UL << PG_buddy, "buddy" }, {1UL << PG_swapbacked, "swapbacked" }, {1UL << PG_unevictable, "unevictable" }, #ifdef CONFIG_MMU @@ -5565,7 +5624,7 @@ void dump_page(struct page *page) { printk(KERN_ALERT "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n", - page, page_count(page), page_mapcount(page), + page, atomic_read(&page->_count), page_mapcount(page), page->mapping, page->index); dump_page_flags(page->flags); } diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 38cc58b8b2b..7cfa6ae0230 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -34,6 +34,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); + split_huge_page_pmd(walk->mm, pmd); if (pmd_none_or_clear_bad(pmd)) { if (walk->pte_hole) err = walk->pte_hole(addr, next, walk); diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index 7d9c1d0ebd3..ea534960a04 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -421,7 +421,7 @@ static struct pcpu_chunk *pcpu_create_chunk(void) return NULL; vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, - pcpu_nr_groups, pcpu_atom_size, GFP_KERNEL); + pcpu_nr_groups, pcpu_atom_size); if (!vms) { pcpu_free_chunk(chunk); return NULL; diff --git a/mm/percpu.c b/mm/percpu.c index 02ba91230b9..3f930018aa6 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -258,7 +258,7 @@ static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk, /* * (Un)populated page region iterators. Iterate over (un)populated - * page regions betwen @start and @end in @chunk. @rs and @re should + * page regions between @start and @end in @chunk. @rs and @re should * be integer variables and will be set to start and end page index of * the current region. */ @@ -293,12 +293,8 @@ static void *pcpu_mem_alloc(size_t size) if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); - else { - void *ptr = vmalloc(size); - if (ptr) - memset(ptr, 0, size); - return ptr; - } + else + return vzalloc(size); } /** diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c new file mode 100644 index 00000000000..eb663fb533e --- /dev/null +++ b/mm/pgtable-generic.c @@ -0,0 +1,121 @@ +/* + * mm/pgtable-generic.c + * + * Generic pgtable methods declared in asm-generic/pgtable.h + * + * Copyright (C) 2010 Linus Torvalds + */ + +#include <linux/pagemap.h> +#include <asm/tlb.h> +#include <asm-generic/pgtable.h> + +#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +/* + * Only sets the access flags (dirty, accessed, and + * writable). Furthermore, we know it always gets set to a "more + * permissive" setting, which allows most architectures to optimize + * this. We return whether the PTE actually changed, which in turn + * instructs the caller to do things like update__mmu_cache. This + * used to be done in the caller, but sparc needs minor faults to + * force that call on sun4c so we changed this macro slightly + */ +int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty) +{ + int changed = !pte_same(*ptep, entry); + if (changed) { + set_pte_at(vma->vm_mm, address, ptep, entry); + flush_tlb_page(vma, address); + } + return changed; +} +#endif + +#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS +int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + int changed = !pmd_same(*pmdp, entry); + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + if (changed) { + set_pmd_at(vma->vm_mm, address, pmdp, entry); + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + } + return changed; +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ + BUG(); + return 0; +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +} +#endif + +#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +int ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ + int young; + young = ptep_test_and_clear_young(vma, address, ptep); + if (young) + flush_tlb_page(vma, address); + return young; +} +#endif + +#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH +int pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + int young; +#ifndef CONFIG_TRANSPARENT_HUGEPAGE + BUG(); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + young = pmdp_test_and_clear_young(vma, address, pmdp); + if (young) + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + return young; +} +#endif + +#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH +pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep) +{ + pte_t pte; + pte = ptep_get_and_clear((vma)->vm_mm, address, ptep); + flush_tlb_page(vma, address); + return pte; +} +#endif + +#ifndef __HAVE_ARCH_PMDP_CLEAR_FLUSH +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +pmd_t pmdp_clear_flush(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + pmd_t pmd; + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + pmd = pmdp_get_and_clear(vma->vm_mm, address, pmdp); + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + return pmd; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif + +#ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +pmd_t pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + pmd_t pmd = pmd_mksplitting(*pmdp); + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + set_pmd_at(vma->vm_mm, address, pmdp, pmd); + /* tlb flush only to serialize against gup-fast */ + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif diff --git a/mm/rmap.c b/mm/rmap.c index 1a8bf76bfd0..f21f4a1d6a1 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -94,7 +94,7 @@ static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, but if - * if not we either need to find an adjacent mapping that we + * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * allocate a new one. @@ -177,6 +177,10 @@ static void anon_vma_chain_link(struct vm_area_struct *vma, list_add(&avc->same_vma, &vma->anon_vma_chain); anon_vma_lock(anon_vma); + /* + * It's critical to add new vmas to the tail of the anon_vma, + * see comment in huge_memory.c:__split_huge_page(). + */ list_add_tail(&avc->same_anon_vma, &anon_vma->head); anon_vma_unlock(anon_vma); } @@ -360,7 +364,7 @@ void page_unlock_anon_vma(struct anon_vma *anon_vma) * Returns virtual address or -EFAULT if page's index/offset is not * within the range mapped the @vma. */ -static inline unsigned long +inline unsigned long vma_address(struct page *page, struct vm_area_struct *vma) { pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); @@ -435,6 +439,8 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm, pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return NULL; + if (pmd_trans_huge(*pmd)) + return NULL; pte = pte_offset_map(pmd, address); /* Make a quick check before getting the lock */ @@ -489,35 +495,17 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, unsigned long *vm_flags) { struct mm_struct *mm = vma->vm_mm; - pte_t *pte; - spinlock_t *ptl; int referenced = 0; - pte = page_check_address(page, mm, address, &ptl, 0); - if (!pte) - goto out; - /* * Don't want to elevate referenced for mlocked page that gets this far, * in order that it progresses to try_to_unmap and is moved to the * unevictable list. */ if (vma->vm_flags & VM_LOCKED) { - *mapcount = 1; /* break early from loop */ + *mapcount = 0; /* break early from loop */ *vm_flags |= VM_LOCKED; - goto out_unmap; - } - - if (ptep_clear_flush_young_notify(vma, address, pte)) { - /* - * Don't treat a reference through a sequentially read - * mapping as such. If the page has been used in - * another mapping, we will catch it; if this other - * mapping is already gone, the unmap path will have - * set PG_referenced or activated the page. - */ - if (likely(!VM_SequentialReadHint(vma))) - referenced++; + goto out; } /* Pretend the page is referenced if the task has the @@ -526,9 +514,39 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, rwsem_is_locked(&mm->mmap_sem)) referenced++; -out_unmap: + if (unlikely(PageTransHuge(page))) { + pmd_t *pmd; + + spin_lock(&mm->page_table_lock); + pmd = page_check_address_pmd(page, mm, address, + PAGE_CHECK_ADDRESS_PMD_FLAG); + if (pmd && !pmd_trans_splitting(*pmd) && + pmdp_clear_flush_young_notify(vma, address, pmd)) + referenced++; + spin_unlock(&mm->page_table_lock); + } else { + pte_t *pte; + spinlock_t *ptl; + + pte = page_check_address(page, mm, address, &ptl, 0); + if (!pte) + goto out; + + if (ptep_clear_flush_young_notify(vma, address, pte)) { + /* + * Don't treat a reference through a sequentially read + * mapping as such. If the page has been used in + * another mapping, we will catch it; if this other + * mapping is already gone, the unmap path will have + * set PG_referenced or activated the page. + */ + if (likely(!VM_SequentialReadHint(vma))) + referenced++; + } + pte_unmap_unlock(pte, ptl); + } + (*mapcount)--; - pte_unmap_unlock(pte, ptl); if (referenced) *vm_flags |= vma->vm_flags; @@ -864,8 +882,13 @@ void do_page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, int exclusive) { int first = atomic_inc_and_test(&page->_mapcount); - if (first) - __inc_zone_page_state(page, NR_ANON_PAGES); + if (first) { + if (!PageTransHuge(page)) + __inc_zone_page_state(page, NR_ANON_PAGES); + else + __inc_zone_page_state(page, + NR_ANON_TRANSPARENT_HUGEPAGES); + } if (unlikely(PageKsm(page))) return; @@ -893,7 +916,10 @@ void page_add_new_anon_rmap(struct page *page, VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end); SetPageSwapBacked(page); atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */ - __inc_zone_page_state(page, NR_ANON_PAGES); + if (!PageTransHuge(page)) + __inc_zone_page_state(page, NR_ANON_PAGES); + else + __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); __page_set_anon_rmap(page, vma, address, 1); if (page_evictable(page, vma)) lru_cache_add_lru(page, LRU_ACTIVE_ANON); @@ -911,7 +937,7 @@ void page_add_file_rmap(struct page *page) { if (atomic_inc_and_test(&page->_mapcount)) { __inc_zone_page_state(page, NR_FILE_MAPPED); - mem_cgroup_update_file_mapped(page, 1); + mem_cgroup_inc_page_stat(page, MEMCG_NR_FILE_MAPPED); } } @@ -946,10 +972,14 @@ void page_remove_rmap(struct page *page) return; if (PageAnon(page)) { mem_cgroup_uncharge_page(page); - __dec_zone_page_state(page, NR_ANON_PAGES); + if (!PageTransHuge(page)) + __dec_zone_page_state(page, NR_ANON_PAGES); + else + __dec_zone_page_state(page, + NR_ANON_TRANSPARENT_HUGEPAGES); } else { __dec_zone_page_state(page, NR_FILE_MAPPED); - mem_cgroup_update_file_mapped(page, -1); + mem_cgroup_dec_page_stat(page, MEMCG_NR_FILE_MAPPED); } /* * It would be tidy to reset the PageAnon mapping here, @@ -1202,7 +1232,7 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, return ret; } -static bool is_vma_temporary_stack(struct vm_area_struct *vma) +bool is_vma_temporary_stack(struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); @@ -1400,6 +1430,7 @@ int try_to_unmap(struct page *page, enum ttu_flags flags) int ret; BUG_ON(!PageLocked(page)); + VM_BUG_ON(!PageHuge(page) && PageTransHuge(page)); if (unlikely(PageKsm(page))) ret = try_to_unmap_ksm(page, flags); diff --git a/mm/shmem.c b/mm/shmem.c index 47fdeeb9d63..5ee67c99060 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2415,13 +2415,20 @@ static struct inode *shmem_alloc_inode(struct super_block *sb) return &p->vfs_inode; } +static void shmem_i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + INIT_LIST_HEAD(&inode->i_dentry); + kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); +} + static void shmem_destroy_inode(struct inode *inode) { if ((inode->i_mode & S_IFMT) == S_IFREG) { /* only struct inode is valid if it's an inline symlink */ mpol_free_shared_policy(&SHMEM_I(inode)->policy); } - kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); + call_rcu(&inode->i_rcu, shmem_i_callback); } static void init_once(void *foo) diff --git a/mm/slab.c b/mm/slab.c index b1e40dafbab..37961d1f584 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -284,7 +284,7 @@ struct kmem_list3 { * Need this for bootstrapping a per node allocator. */ #define NUM_INIT_LISTS (3 * MAX_NUMNODES) -struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS]; +static struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS]; #define CACHE_CACHE 0 #define SIZE_AC MAX_NUMNODES #define SIZE_L3 (2 * MAX_NUMNODES) @@ -829,12 +829,12 @@ static void init_reap_node(int cpu) static void next_reap_node(void) { - int node = __get_cpu_var(slab_reap_node); + int node = __this_cpu_read(slab_reap_node); node = next_node(node, node_online_map); if (unlikely(node >= MAX_NUMNODES)) node = first_node(node_online_map); - __get_cpu_var(slab_reap_node) = node; + __this_cpu_write(slab_reap_node, node); } #else @@ -1012,7 +1012,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep, */ static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3) { - int node = __get_cpu_var(slab_reap_node); + int node = __this_cpu_read(slab_reap_node); if (l3->alien) { struct array_cache *ac = l3->alien[node]; @@ -1293,7 +1293,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb, * anything expensive but will only modify reap_work * and reschedule the timer. */ - cancel_rearming_delayed_work(&per_cpu(slab_reap_work, cpu)); + cancel_delayed_work_sync(&per_cpu(slab_reap_work, cpu)); /* Now the cache_reaper is guaranteed to be not running. */ per_cpu(slab_reap_work, cpu).work.func = NULL; break; @@ -2781,7 +2781,7 @@ static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp, /* * Map pages beginning at addr to the given cache and slab. This is required * for the slab allocator to be able to lookup the cache and slab of a - * virtual address for kfree, ksize, kmem_ptr_validate, and slab debugging. + * virtual address for kfree, ksize, and slab debugging. */ static void slab_map_pages(struct kmem_cache *cache, struct slab *slab, void *addr) @@ -3653,42 +3653,19 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) EXPORT_SYMBOL(kmem_cache_alloc); #ifdef CONFIG_TRACING -void *kmem_cache_alloc_notrace(struct kmem_cache *cachep, gfp_t flags) +void * +kmem_cache_alloc_trace(size_t size, struct kmem_cache *cachep, gfp_t flags) { - return __cache_alloc(cachep, flags, __builtin_return_address(0)); -} -EXPORT_SYMBOL(kmem_cache_alloc_notrace); -#endif + void *ret; -/** - * kmem_ptr_validate - check if an untrusted pointer might be a slab entry. - * @cachep: the cache we're checking against - * @ptr: pointer to validate - * - * This verifies that the untrusted pointer looks sane; - * it is _not_ a guarantee that the pointer is actually - * part of the slab cache in question, but it at least - * validates that the pointer can be dereferenced and - * looks half-way sane. - * - * Currently only used for dentry validation. - */ -int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr) -{ - unsigned long size = cachep->buffer_size; - struct page *page; + ret = __cache_alloc(cachep, flags, __builtin_return_address(0)); - if (unlikely(!kern_ptr_validate(ptr, size))) - goto out; - page = virt_to_page(ptr); - if (unlikely(!PageSlab(page))) - goto out; - if (unlikely(page_get_cache(page) != cachep)) - goto out; - return 1; -out: - return 0; + trace_kmalloc(_RET_IP_, ret, + size, slab_buffer_size(cachep), flags); + return ret; } +EXPORT_SYMBOL(kmem_cache_alloc_trace); +#endif #ifdef CONFIG_NUMA void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) @@ -3705,31 +3682,32 @@ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) EXPORT_SYMBOL(kmem_cache_alloc_node); #ifdef CONFIG_TRACING -void *kmem_cache_alloc_node_notrace(struct kmem_cache *cachep, - gfp_t flags, - int nodeid) +void *kmem_cache_alloc_node_trace(size_t size, + struct kmem_cache *cachep, + gfp_t flags, + int nodeid) { - return __cache_alloc_node(cachep, flags, nodeid, + void *ret; + + ret = __cache_alloc_node(cachep, flags, nodeid, __builtin_return_address(0)); + trace_kmalloc_node(_RET_IP_, ret, + size, slab_buffer_size(cachep), + flags, nodeid); + return ret; } -EXPORT_SYMBOL(kmem_cache_alloc_node_notrace); +EXPORT_SYMBOL(kmem_cache_alloc_node_trace); #endif static __always_inline void * __do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller) { struct kmem_cache *cachep; - void *ret; cachep = kmem_find_general_cachep(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; - ret = kmem_cache_alloc_node_notrace(cachep, flags, node); - - trace_kmalloc_node((unsigned long) caller, ret, - size, cachep->buffer_size, flags, node); - - return ret; + return kmem_cache_alloc_node_trace(size, cachep, flags, node); } #if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_TRACING) @@ -4075,7 +4053,7 @@ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp) * necessary. Note that the l3 listlock also protects the array_cache * if drain_array() is used on the shared array. */ -void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3, +static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3, struct array_cache *ac, int force, int node) { int tofree; @@ -4339,7 +4317,7 @@ static const struct seq_operations slabinfo_op = { * @count: data length * @ppos: unused */ -ssize_t slabinfo_write(struct file *file, const char __user * buffer, +static ssize_t slabinfo_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { char kbuf[MAX_SLABINFO_WRITE + 1], *tmp; diff --git a/mm/slob.c b/mm/slob.c index 617b6d6c42c..3588eaaef72 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -678,11 +678,6 @@ int kmem_cache_shrink(struct kmem_cache *d) } EXPORT_SYMBOL(kmem_cache_shrink); -int kmem_ptr_validate(struct kmem_cache *a, const void *b) -{ - return 0; -} - static unsigned int slob_ready __read_mostly; int slab_is_available(void) diff --git a/mm/slub.c b/mm/slub.c index bec0e355fba..e15aa7f193c 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -28,6 +28,8 @@ #include <linux/math64.h> #include <linux/fault-inject.h> +#include <trace/events/kmem.h> + /* * Lock order: * 1. slab_lock(page) @@ -1774,11 +1776,21 @@ void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) EXPORT_SYMBOL(kmem_cache_alloc); #ifdef CONFIG_TRACING -void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags) +void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) +{ + void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_); + trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags); + return ret; +} +EXPORT_SYMBOL(kmem_cache_alloc_trace); + +void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) { - return slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_); + void *ret = kmalloc_order(size, flags, order); + trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags); + return ret; } -EXPORT_SYMBOL(kmem_cache_alloc_notrace); +EXPORT_SYMBOL(kmalloc_order_trace); #endif #ifdef CONFIG_NUMA @@ -1794,13 +1806,17 @@ void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node) EXPORT_SYMBOL(kmem_cache_alloc_node); #ifdef CONFIG_TRACING -void *kmem_cache_alloc_node_notrace(struct kmem_cache *s, +void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node) + int node, size_t size) { - return slab_alloc(s, gfpflags, node, _RET_IP_); + void *ret = slab_alloc(s, gfpflags, node, _RET_IP_); + + trace_kmalloc_node(_RET_IP_, ret, + size, s->size, gfpflags, node); + return ret; } -EXPORT_SYMBOL(kmem_cache_alloc_node_notrace); +EXPORT_SYMBOL(kmem_cache_alloc_node_trace); #endif #endif @@ -1917,17 +1933,6 @@ void kmem_cache_free(struct kmem_cache *s, void *x) } EXPORT_SYMBOL(kmem_cache_free); -/* Figure out on which slab page the object resides */ -static struct page *get_object_page(const void *x) -{ - struct page *page = virt_to_head_page(x); - - if (!PageSlab(page)) - return NULL; - - return page; -} - /* * Object placement in a slab is made very easy because we always start at * offset 0. If we tune the size of the object to the alignment then we can @@ -2386,35 +2391,6 @@ error: } /* - * Check if a given pointer is valid - */ -int kmem_ptr_validate(struct kmem_cache *s, const void *object) -{ - struct page *page; - - if (!kern_ptr_validate(object, s->size)) - return 0; - - page = get_object_page(object); - - if (!page || s != page->slab) - /* No slab or wrong slab */ - return 0; - - if (!check_valid_pointer(s, page, object)) - return 0; - - /* - * We could also check if the object is on the slabs freelist. - * But this would be too expensive and it seems that the main - * purpose of kmem_ptr_valid() is to check if the object belongs - * to a certain slab. - */ - return 1; -} -EXPORT_SYMBOL(kmem_ptr_validate); - -/* * Determine the size of a slab object */ unsigned int kmem_cache_size(struct kmem_cache *s) @@ -3660,7 +3636,7 @@ static int list_locations(struct kmem_cache *s, char *buf, len += sprintf(buf + len, "%7ld ", l->count); if (l->addr) - len += sprint_symbol(buf + len, (unsigned long)l->addr); + len += sprintf(buf + len, "%pS", (void *)l->addr); else len += sprintf(buf + len, "<not-available>"); @@ -3821,7 +3797,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s, } } - down_read(&slub_lock); + lock_memory_hotplug(); #ifdef CONFIG_SLUB_DEBUG if (flags & SO_ALL) { for_each_node_state(node, N_NORMAL_MEMORY) { @@ -3862,7 +3838,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s, x += sprintf(buf + x, " N%d=%lu", node, nodes[node]); #endif - up_read(&slub_lock); + unlock_memory_hotplug(); kfree(nodes); return x + sprintf(buf + x, "\n"); } @@ -3970,12 +3946,9 @@ SLAB_ATTR(min_partial); static ssize_t ctor_show(struct kmem_cache *s, char *buf) { - if (s->ctor) { - int n = sprint_symbol(buf, (unsigned long)s->ctor); - - return n + sprintf(buf + n, "\n"); - } - return 0; + if (!s->ctor) + return 0; + return sprintf(buf, "%pS\n", s->ctor); } SLAB_ATTR_RO(ctor); diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 29d6cbffb28..64b984091ed 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -9,7 +9,7 @@ * * However, virtual mappings need a page table and TLBs. Many Linux * architectures already map their physical space using 1-1 mappings - * via TLBs. For those arches the virtual memmory map is essentially + * via TLBs. For those arches the virtual memory map is essentially * for free if we use the same page size as the 1-1 mappings. In that * case the overhead consists of a few additional pages that are * allocated to create a view of memory for vmemmap. diff --git a/mm/sparse.c b/mm/sparse.c index 95ac219af37..93250207c5c 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -671,10 +671,10 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) static void free_map_bootmem(struct page *page, unsigned long nr_pages) { unsigned long maps_section_nr, removing_section_nr, i; - int magic; + unsigned long magic; for (i = 0; i < nr_pages; i++, page++) { - magic = atomic_read(&page->_mapcount); + magic = (unsigned long) page->lru.next; BUG_ON(magic == NODE_INFO); diff --git a/mm/swap.c b/mm/swap.c index 3f4854205b1..c02f93611a8 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -56,17 +56,97 @@ static void __page_cache_release(struct page *page) del_page_from_lru(zone, page); spin_unlock_irqrestore(&zone->lru_lock, flags); } +} + +static void __put_single_page(struct page *page) +{ + __page_cache_release(page); free_hot_cold_page(page, 0); } -static void put_compound_page(struct page *page) +static void __put_compound_page(struct page *page) { - page = compound_head(page); - if (put_page_testzero(page)) { - compound_page_dtor *dtor; + compound_page_dtor *dtor; - dtor = get_compound_page_dtor(page); - (*dtor)(page); + __page_cache_release(page); + dtor = get_compound_page_dtor(page); + (*dtor)(page); +} + +static void put_compound_page(struct page *page) +{ + if (unlikely(PageTail(page))) { + /* __split_huge_page_refcount can run under us */ + struct page *page_head = page->first_page; + smp_rmb(); + /* + * If PageTail is still set after smp_rmb() we can be sure + * that the page->first_page we read wasn't a dangling pointer. + * See __split_huge_page_refcount() smp_wmb(). + */ + if (likely(PageTail(page) && get_page_unless_zero(page_head))) { + unsigned long flags; + /* + * Verify that our page_head wasn't converted + * to a a regular page before we got a + * reference on it. + */ + if (unlikely(!PageHead(page_head))) { + /* PageHead is cleared after PageTail */ + smp_rmb(); + VM_BUG_ON(PageTail(page)); + goto out_put_head; + } + /* + * Only run compound_lock on a valid PageHead, + * after having it pinned with + * get_page_unless_zero() above. + */ + smp_mb(); + /* page_head wasn't a dangling pointer */ + flags = compound_lock_irqsave(page_head); + if (unlikely(!PageTail(page))) { + /* __split_huge_page_refcount run before us */ + compound_unlock_irqrestore(page_head, flags); + VM_BUG_ON(PageHead(page_head)); + out_put_head: + if (put_page_testzero(page_head)) + __put_single_page(page_head); + out_put_single: + if (put_page_testzero(page)) + __put_single_page(page); + return; + } + VM_BUG_ON(page_head != page->first_page); + /* + * We can release the refcount taken by + * get_page_unless_zero now that + * split_huge_page_refcount is blocked on the + * compound_lock. + */ + if (put_page_testzero(page_head)) + VM_BUG_ON(1); + /* __split_huge_page_refcount will wait now */ + VM_BUG_ON(atomic_read(&page->_count) <= 0); + atomic_dec(&page->_count); + VM_BUG_ON(atomic_read(&page_head->_count) <= 0); + compound_unlock_irqrestore(page_head, flags); + if (put_page_testzero(page_head)) { + if (PageHead(page_head)) + __put_compound_page(page_head); + else + __put_single_page(page_head); + } + } else { + /* page_head is a dangling pointer */ + VM_BUG_ON(PageTail(page)); + goto out_put_single; + } + } else if (put_page_testzero(page)) { + if (PageHead(page)) + __put_compound_page(page); + else + __put_single_page(page); } } @@ -75,7 +155,7 @@ void put_page(struct page *page) if (unlikely(PageCompound(page))) put_compound_page(page); else if (put_page_testzero(page)) - __page_cache_release(page); + __put_single_page(page); } EXPORT_SYMBOL(put_page); @@ -399,6 +479,43 @@ void __pagevec_release(struct pagevec *pvec) EXPORT_SYMBOL(__pagevec_release); +/* used by __split_huge_page_refcount() */ +void lru_add_page_tail(struct zone* zone, + struct page *page, struct page *page_tail) +{ + int active; + enum lru_list lru; + const int file = 0; + struct list_head *head; + + VM_BUG_ON(!PageHead(page)); + VM_BUG_ON(PageCompound(page_tail)); + VM_BUG_ON(PageLRU(page_tail)); + VM_BUG_ON(!spin_is_locked(&zone->lru_lock)); + + SetPageLRU(page_tail); + + if (page_evictable(page_tail, NULL)) { + if (PageActive(page)) { + SetPageActive(page_tail); + active = 1; + lru = LRU_ACTIVE_ANON; + } else { + active = 0; + lru = LRU_INACTIVE_ANON; + } + update_page_reclaim_stat(zone, page_tail, file, active); + if (likely(PageLRU(page))) + head = page->lru.prev; + else + head = &zone->lru[lru].list; + __add_page_to_lru_list(zone, page_tail, lru, head); + } else { + SetPageUnevictable(page_tail); + add_page_to_lru_list(zone, page_tail, LRU_UNEVICTABLE); + } +} + /* * Add the passed pages to the LRU, then drop the caller's refcount * on them. Reinitialises the caller's pagevec. diff --git a/mm/swap_state.c b/mm/swap_state.c index e10f5833167..5c8cfabbc9b 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -157,6 +157,12 @@ int add_to_swap(struct page *page) if (!entry.val) return 0; + if (unlikely(PageTransHuge(page))) + if (unlikely(split_huge_page(page))) { + swapcache_free(entry, NULL); + return 0; + } + /* * Radix-tree node allocations from PF_MEMALLOC contexts could * completely exhaust the page allocator. __GFP_NOMEMALLOC diff --git a/mm/swapfile.c b/mm/swapfile.c index 67ddaaf98c7..07a458d72fa 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -964,6 +964,8 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); + if (unlikely(pmd_trans_huge(*pmd))) + continue; if (pmd_none_or_clear_bad(pmd)) continue; ret = unuse_pte_range(vma, pmd, addr, next, entry, page); @@ -1677,7 +1679,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) if (S_ISBLK(inode->i_mode)) { struct block_device *bdev = I_BDEV(inode); set_blocksize(bdev, p->old_block_size); - bd_release(bdev); + blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } else { mutex_lock(&inode->i_mutex); inode->i_flags &= ~S_SWAPFILE; @@ -1939,7 +1941,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = -EINVAL; if (S_ISBLK(inode->i_mode)) { bdev = I_BDEV(inode); - error = bd_claim(bdev, sys_swapon); + error = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, + sys_swapon); if (error < 0) { bdev = NULL; error = -EINVAL; @@ -2136,7 +2139,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) bad_swap: if (bdev) { set_blocksize(bdev, p->old_block_size); - bd_release(bdev); + blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } destroy_swap_extents(p); swap_cgroup_swapoff(type); diff --git a/mm/truncate.c b/mm/truncate.c index 3c2d5ddfa0d..49feb46e77b 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -549,13 +549,12 @@ EXPORT_SYMBOL(truncate_pagecache); * @inode: inode * @newsize: new file size * - * truncate_setsize updastes i_size update and performs pagecache - * truncation (if necessary) for a file size updates. It will be - * typically be called from the filesystem's setattr function when - * ATTR_SIZE is passed in. + * truncate_setsize updates i_size and performs pagecache truncation (if + * necessary) to @newsize. It will be typically be called from the filesystem's + * setattr function when ATTR_SIZE is passed in. * - * Must be called with inode_mutex held and after all filesystem - * specific block truncation has been performed. + * Must be called with inode_mutex held and before all filesystem specific + * block truncation has been performed. */ void truncate_setsize(struct inode *inode, loff_t newsize) { diff --git a/mm/util.c b/mm/util.c index 73dac81e9f7..f126975ef23 100644 --- a/mm/util.c +++ b/mm/util.c @@ -186,27 +186,6 @@ void kzfree(const void *p) } EXPORT_SYMBOL(kzfree); -int kern_ptr_validate(const void *ptr, unsigned long size) -{ - unsigned long addr = (unsigned long)ptr; - unsigned long min_addr = PAGE_OFFSET; - unsigned long align_mask = sizeof(void *) - 1; - - if (unlikely(addr < min_addr)) - goto out; - if (unlikely(addr > (unsigned long)high_memory - size)) - goto out; - if (unlikely(addr & align_mask)) - goto out; - if (unlikely(!kern_addr_valid(addr))) - goto out; - if (unlikely(!kern_addr_valid(addr + size - 1))) - goto out; - return 1; -out: - return 0; -} - /* * strndup_user - duplicate an existing string from user space * @s: The string to duplicate diff --git a/mm/vmalloc.c b/mm/vmalloc.c index eb5cc7d00c5..f9b166732e7 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -748,7 +748,7 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE, VMALLOC_START, VMALLOC_END, node, gfp_mask); - if (unlikely(IS_ERR(va))) { + if (IS_ERR(va)) { kfree(vb); return ERR_CAST(va); } @@ -1175,6 +1175,7 @@ void unmap_kernel_range_noflush(unsigned long addr, unsigned long size) { vunmap_page_range(addr, addr + size); } +EXPORT_SYMBOL_GPL(unmap_kernel_range_noflush); /** * unmap_kernel_range - unmap kernel VM area and flush cache and TLB @@ -1315,13 +1316,6 @@ struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, -1, GFP_KERNEL, caller); } -struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags, - int node, gfp_t gfp_mask) -{ - return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, - node, gfp_mask, __builtin_return_address(0)); -} - static struct vm_struct *find_vm_area(const void *addr) { struct vmap_area *va; @@ -1537,25 +1531,12 @@ fail: return NULL; } -void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot) -{ - void *addr = __vmalloc_area_node(area, gfp_mask, prot, -1, - __builtin_return_address(0)); - - /* - * A ref_count = 3 is needed because the vm_struct and vmap_area - * structures allocated in the __get_vm_area_node() function contain - * references to the virtual address of the vmalloc'ed block. - */ - kmemleak_alloc(addr, area->size - PAGE_SIZE, 3, gfp_mask); - - return addr; -} - /** - * __vmalloc_node - allocate virtually contiguous memory + * __vmalloc_node_range - allocate virtually contiguous memory * @size: allocation size * @align: desired alignment + * @start: vm area range start + * @end: vm area range end * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages * @node: node to use for allocation or -1 @@ -1565,9 +1546,9 @@ void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot) * allocator with @gfp_mask flags. Map them into contiguous * kernel virtual space, using a pagetable protection of @prot. */ -static void *__vmalloc_node(unsigned long size, unsigned long align, - gfp_t gfp_mask, pgprot_t prot, - int node, void *caller) +void *__vmalloc_node_range(unsigned long size, unsigned long align, + unsigned long start, unsigned long end, gfp_t gfp_mask, + pgprot_t prot, int node, void *caller) { struct vm_struct *area; void *addr; @@ -1577,8 +1558,8 @@ static void *__vmalloc_node(unsigned long size, unsigned long align, if (!size || (size >> PAGE_SHIFT) > totalram_pages) return NULL; - area = __get_vm_area_node(size, align, VM_ALLOC, VMALLOC_START, - VMALLOC_END, node, gfp_mask, caller); + area = __get_vm_area_node(size, align, VM_ALLOC, start, end, node, + gfp_mask, caller); if (!area) return NULL; @@ -1595,6 +1576,27 @@ static void *__vmalloc_node(unsigned long size, unsigned long align, return addr; } +/** + * __vmalloc_node - allocate virtually contiguous memory + * @size: allocation size + * @align: desired alignment + * @gfp_mask: flags for the page level allocator + * @prot: protection mask for the allocated pages + * @node: node to use for allocation or -1 + * @caller: caller's return address + * + * Allocate enough pages to cover @size from the page level + * allocator with @gfp_mask flags. Map them into contiguous + * kernel virtual space, using a pagetable protection of @prot. + */ +static void *__vmalloc_node(unsigned long size, unsigned long align, + gfp_t gfp_mask, pgprot_t prot, + int node, void *caller) +{ + return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, + gfp_mask, prot, node, caller); +} + void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) { return __vmalloc_node(size, 1, gfp_mask, prot, -1, @@ -2203,17 +2205,16 @@ static unsigned long pvm_determine_end(struct vmap_area **pnext, * @sizes: array containing size of each area * @nr_vms: the number of areas to allocate * @align: alignment, all entries in @offsets and @sizes must be aligned to this - * @gfp_mask: allocation mask * * Returns: kmalloc'd vm_struct pointer array pointing to allocated * vm_structs on success, %NULL on failure * * Percpu allocator wants to use congruent vm areas so that it can * maintain the offsets among percpu areas. This function allocates - * congruent vmalloc areas for it. These areas tend to be scattered - * pretty far, distance between two areas easily going up to - * gigabytes. To avoid interacting with regular vmallocs, these areas - * are allocated from top. + * congruent vmalloc areas for it with GFP_KERNEL. These areas tend to + * be scattered pretty far, distance between two areas easily going up + * to gigabytes. To avoid interacting with regular vmallocs, these + * areas are allocated from top. * * Despite its complicated look, this allocator is rather simple. It * does everything top-down and scans areas from the end looking for @@ -2224,7 +2225,7 @@ static unsigned long pvm_determine_end(struct vmap_area **pnext, */ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, - size_t align, gfp_t gfp_mask) + size_t align) { const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align); const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); @@ -2234,8 +2235,6 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, unsigned long base, start, end, last_end; bool purged = false; - gfp_mask &= GFP_RECLAIM_MASK; - /* verify parameters and allocate data structures */ BUG_ON(align & ~PAGE_MASK || !is_power_of_2(align)); for (last_area = 0, area = 0; area < nr_vms; area++) { @@ -2268,14 +2267,14 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, return NULL; } - vms = kzalloc(sizeof(vms[0]) * nr_vms, gfp_mask); - vas = kzalloc(sizeof(vas[0]) * nr_vms, gfp_mask); + vms = kzalloc(sizeof(vms[0]) * nr_vms, GFP_KERNEL); + vas = kzalloc(sizeof(vas[0]) * nr_vms, GFP_KERNEL); if (!vas || !vms) goto err_free; for (area = 0; area < nr_vms; area++) { - vas[area] = kzalloc(sizeof(struct vmap_area), gfp_mask); - vms[area] = kzalloc(sizeof(struct vm_struct), gfp_mask); + vas[area] = kzalloc(sizeof(struct vmap_area), GFP_KERNEL); + vms[area] = kzalloc(sizeof(struct vm_struct), GFP_KERNEL); if (!vas[area] || !vms[area]) goto err_free; } @@ -2456,13 +2455,8 @@ static int s_show(struct seq_file *m, void *p) seq_printf(m, "0x%p-0x%p %7ld", v->addr, v->addr + v->size, v->size); - if (v->caller) { - char buff[KSYM_SYMBOL_LEN]; - - seq_putc(m, ' '); - sprint_symbol(buff, (unsigned long)v->caller); - seq_puts(m, buff); - } + if (v->caller) + seq_printf(m, " %pS", v->caller); if (v->nr_pages) seq_printf(m, " pages=%d", v->nr_pages); diff --git a/mm/vmscan.c b/mm/vmscan.c index 9ca587c6927..17497d0cd8b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -32,6 +32,7 @@ #include <linux/topology.h> #include <linux/cpu.h> #include <linux/cpuset.h> +#include <linux/compaction.h> #include <linux/notifier.h> #include <linux/rwsem.h> #include <linux/delay.h> @@ -51,11 +52,23 @@ #define CREATE_TRACE_POINTS #include <trace/events/vmscan.h> -enum lumpy_mode { - LUMPY_MODE_NONE, - LUMPY_MODE_ASYNC, - LUMPY_MODE_SYNC, -}; +/* + * reclaim_mode determines how the inactive list is shrunk + * RECLAIM_MODE_SINGLE: Reclaim only order-0 pages + * RECLAIM_MODE_ASYNC: Do not block + * RECLAIM_MODE_SYNC: Allow blocking e.g. call wait_on_page_writeback + * RECLAIM_MODE_LUMPYRECLAIM: For high-order allocations, take a reference + * page from the LRU and reclaim all pages within a + * naturally aligned range + * RECLAIM_MODE_COMPACTION: For high-order allocations, reclaim a number of + * order-0 pages and then compact the zone + */ +typedef unsigned __bitwise__ reclaim_mode_t; +#define RECLAIM_MODE_SINGLE ((__force reclaim_mode_t)0x01u) +#define RECLAIM_MODE_ASYNC ((__force reclaim_mode_t)0x02u) +#define RECLAIM_MODE_SYNC ((__force reclaim_mode_t)0x04u) +#define RECLAIM_MODE_LUMPYRECLAIM ((__force reclaim_mode_t)0x08u) +#define RECLAIM_MODE_COMPACTION ((__force reclaim_mode_t)0x10u) struct scan_control { /* Incremented by the number of inactive pages that were scanned */ @@ -88,7 +101,7 @@ struct scan_control { * Intend to reclaim enough continuous memory rather than reclaim * enough amount of memory. i.e, mode for high order allocation. */ - enum lumpy_mode lumpy_reclaim_mode; + reclaim_mode_t reclaim_mode; /* Which cgroup do we reclaim from */ struct mem_cgroup *mem_cgroup; @@ -271,34 +284,37 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, return ret; } -static void set_lumpy_reclaim_mode(int priority, struct scan_control *sc, +static void set_reclaim_mode(int priority, struct scan_control *sc, bool sync) { - enum lumpy_mode mode = sync ? LUMPY_MODE_SYNC : LUMPY_MODE_ASYNC; + reclaim_mode_t syncmode = sync ? RECLAIM_MODE_SYNC : RECLAIM_MODE_ASYNC; /* - * Some reclaim have alredy been failed. No worth to try synchronous - * lumpy reclaim. + * Initially assume we are entering either lumpy reclaim or + * reclaim/compaction.Depending on the order, we will either set the + * sync mode or just reclaim order-0 pages later. */ - if (sync && sc->lumpy_reclaim_mode == LUMPY_MODE_NONE) - return; + if (COMPACTION_BUILD) + sc->reclaim_mode = RECLAIM_MODE_COMPACTION; + else + sc->reclaim_mode = RECLAIM_MODE_LUMPYRECLAIM; /* - * If we need a large contiguous chunk of memory, or have - * trouble getting a small set of contiguous pages, we - * will reclaim both active and inactive pages. + * Avoid using lumpy reclaim or reclaim/compaction if possible by + * restricting when its set to either costly allocations or when + * under memory pressure */ if (sc->order > PAGE_ALLOC_COSTLY_ORDER) - sc->lumpy_reclaim_mode = mode; + sc->reclaim_mode |= syncmode; else if (sc->order && priority < DEF_PRIORITY - 2) - sc->lumpy_reclaim_mode = mode; + sc->reclaim_mode |= syncmode; else - sc->lumpy_reclaim_mode = LUMPY_MODE_NONE; + sc->reclaim_mode = RECLAIM_MODE_SINGLE | RECLAIM_MODE_ASYNC; } -static void disable_lumpy_reclaim_mode(struct scan_control *sc) +static void reset_reclaim_mode(struct scan_control *sc) { - sc->lumpy_reclaim_mode = LUMPY_MODE_NONE; + sc->reclaim_mode = RECLAIM_MODE_SINGLE | RECLAIM_MODE_ASYNC; } static inline int is_page_cache_freeable(struct page *page) @@ -429,7 +445,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, * first attempt to free a range of pages fails. */ if (PageWriteback(page) && - sc->lumpy_reclaim_mode == LUMPY_MODE_SYNC) + (sc->reclaim_mode & RECLAIM_MODE_SYNC)) wait_on_page_writeback(page); if (!PageWriteback(page)) { @@ -437,7 +453,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, ClearPageReclaim(page); } trace_mm_vmscan_writepage(page, - trace_reclaim_flags(page, sc->lumpy_reclaim_mode)); + trace_reclaim_flags(page, sc->reclaim_mode)); inc_zone_page_state(page, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } @@ -622,7 +638,7 @@ static enum page_references page_check_references(struct page *page, referenced_page = TestClearPageReferenced(page); /* Lumpy reclaim - ignore references */ - if (sc->lumpy_reclaim_mode != LUMPY_MODE_NONE) + if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM) return PAGEREF_RECLAIM; /* @@ -739,7 +755,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, * for any page for which writeback has already * started. */ - if (sc->lumpy_reclaim_mode == LUMPY_MODE_SYNC && + if ((sc->reclaim_mode & RECLAIM_MODE_SYNC) && may_enter_fs) wait_on_page_writeback(page); else { @@ -895,7 +911,7 @@ cull_mlocked: try_to_free_swap(page); unlock_page(page); putback_lru_page(page); - disable_lumpy_reclaim_mode(sc); + reset_reclaim_mode(sc); continue; activate_locked: @@ -908,7 +924,7 @@ activate_locked: keep_locked: unlock_page(page); keep: - disable_lumpy_reclaim_mode(sc); + reset_reclaim_mode(sc); keep_lumpy: list_add(&page->lru, &ret_pages); VM_BUG_ON(PageLRU(page) || PageUnevictable(page)); @@ -1028,7 +1044,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, case 0: list_move(&page->lru, dst); mem_cgroup_del_lru(page); - nr_taken++; + nr_taken += hpage_nr_pages(page); break; case -EBUSY: @@ -1086,7 +1102,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, if (__isolate_lru_page(cursor_page, mode, file) == 0) { list_move(&cursor_page->lru, dst); mem_cgroup_del_lru(cursor_page); - nr_taken++; + nr_taken += hpage_nr_pages(page); nr_lumpy_taken++; if (PageDirty(cursor_page)) nr_lumpy_dirty++; @@ -1141,14 +1157,15 @@ static unsigned long clear_active_flags(struct list_head *page_list, struct page *page; list_for_each_entry(page, page_list, lru) { + int numpages = hpage_nr_pages(page); lru = page_lru_base_type(page); if (PageActive(page)) { lru += LRU_ACTIVE; ClearPageActive(page); - nr_active++; + nr_active += numpages; } if (count) - count[lru]++; + count[lru] += numpages; } return nr_active; @@ -1258,7 +1275,8 @@ putback_lru_pages(struct zone *zone, struct scan_control *sc, add_page_to_lru_list(zone, page, lru); if (is_active_lru(lru)) { int file = is_file_lru(lru); - reclaim_stat->recent_rotated[file]++; + int numpages = hpage_nr_pages(page); + reclaim_stat->recent_rotated[file] += numpages; } if (!pagevec_add(&pvec, page)) { spin_unlock_irq(&zone->lru_lock); @@ -1324,7 +1342,7 @@ static inline bool should_reclaim_stall(unsigned long nr_taken, return false; /* Only stall on lumpy reclaim */ - if (sc->lumpy_reclaim_mode == LUMPY_MODE_NONE) + if (sc->reclaim_mode & RECLAIM_MODE_SINGLE) return false; /* If we have relaimed everything on the isolated list, no stall */ @@ -1368,15 +1386,15 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, return SWAP_CLUSTER_MAX; } - set_lumpy_reclaim_mode(priority, sc, false); + set_reclaim_mode(priority, sc, false); lru_add_drain(); spin_lock_irq(&zone->lru_lock); if (scanning_global_lru(sc)) { nr_taken = isolate_pages_global(nr_to_scan, &page_list, &nr_scanned, sc->order, - sc->lumpy_reclaim_mode == LUMPY_MODE_NONE ? - ISOLATE_INACTIVE : ISOLATE_BOTH, + sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ? + ISOLATE_BOTH : ISOLATE_INACTIVE, zone, 0, file); zone->pages_scanned += nr_scanned; if (current_is_kswapd()) @@ -1388,8 +1406,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, } else { nr_taken = mem_cgroup_isolate_pages(nr_to_scan, &page_list, &nr_scanned, sc->order, - sc->lumpy_reclaim_mode == LUMPY_MODE_NONE ? - ISOLATE_INACTIVE : ISOLATE_BOTH, + sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ? + ISOLATE_BOTH : ISOLATE_INACTIVE, zone, sc->mem_cgroup, 0, file); /* @@ -1411,7 +1429,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, /* Check if we should syncronously wait for writeback */ if (should_reclaim_stall(nr_taken, nr_reclaimed, priority, sc)) { - set_lumpy_reclaim_mode(priority, sc, true); + set_reclaim_mode(priority, sc, true); nr_reclaimed += shrink_page_list(&page_list, zone, sc); } @@ -1426,7 +1444,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, zone_idx(zone), nr_scanned, nr_reclaimed, priority, - trace_shrink_flags(file, sc->lumpy_reclaim_mode)); + trace_shrink_flags(file, sc->reclaim_mode)); return nr_reclaimed; } @@ -1466,7 +1484,7 @@ static void move_active_pages_to_lru(struct zone *zone, list_move(&page->lru, &zone->lru[lru].list); mem_cgroup_add_lru_list(page, lru); - pgmoved++; + pgmoved += hpage_nr_pages(page); if (!pagevec_add(&pvec, page) || list_empty(list)) { spin_unlock_irq(&zone->lru_lock); @@ -1534,7 +1552,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, } if (page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) { - nr_rotated++; + nr_rotated += hpage_nr_pages(page); /* * Identify referenced, file-backed active pages and * give them one more trip around the active list. So @@ -1805,6 +1823,57 @@ out: } /* + * Reclaim/compaction depends on a number of pages being freed. To avoid + * disruption to the system, a small number of order-0 pages continue to be + * rotated and reclaimed in the normal fashion. However, by the time we get + * back to the allocator and call try_to_compact_zone(), we ensure that + * there are enough free pages for it to be likely successful + */ +static inline bool should_continue_reclaim(struct zone *zone, + unsigned long nr_reclaimed, + unsigned long nr_scanned, + struct scan_control *sc) +{ + unsigned long pages_for_compaction; + unsigned long inactive_lru_pages; + + /* If not in reclaim/compaction mode, stop */ + if (!(sc->reclaim_mode & RECLAIM_MODE_COMPACTION)) + return false; + + /* + * If we failed to reclaim and have scanned the full list, stop. + * NOTE: Checking just nr_reclaimed would exit reclaim/compaction far + * faster but obviously would be less likely to succeed + * allocation. If this is desirable, use GFP_REPEAT to decide + * if both reclaimed and scanned should be checked or just + * reclaimed + */ + if (!nr_reclaimed && !nr_scanned) + return false; + + /* + * If we have not reclaimed enough pages for compaction and the + * inactive lists are large enough, continue reclaiming + */ + pages_for_compaction = (2UL << sc->order); + inactive_lru_pages = zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON) + + zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE); + if (sc->nr_reclaimed < pages_for_compaction && + inactive_lru_pages > pages_for_compaction) + return true; + + /* If compaction would go ahead or the allocation would succeed, stop */ + switch (compaction_suitable(zone, sc->order)) { + case COMPACT_PARTIAL: + case COMPACT_CONTINUE: + return false; + default: + return true; + } +} + +/* * This is a basic per-zone page freer. Used by both kswapd and direct reclaim. */ static void shrink_zone(int priority, struct zone *zone, @@ -1813,9 +1882,12 @@ static void shrink_zone(int priority, struct zone *zone, unsigned long nr[NR_LRU_LISTS]; unsigned long nr_to_scan; enum lru_list l; - unsigned long nr_reclaimed = sc->nr_reclaimed; + unsigned long nr_reclaimed, nr_scanned; unsigned long nr_to_reclaim = sc->nr_to_reclaim; +restart: + nr_reclaimed = 0; + nr_scanned = sc->nr_scanned; get_scan_count(zone, sc, nr, priority); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || @@ -1841,8 +1913,7 @@ static void shrink_zone(int priority, struct zone *zone, if (nr_reclaimed >= nr_to_reclaim && priority < DEF_PRIORITY) break; } - - sc->nr_reclaimed = nr_reclaimed; + sc->nr_reclaimed += nr_reclaimed; /* * Even if we did not try to evict anon pages at all, we want to @@ -1851,6 +1922,11 @@ static void shrink_zone(int priority, struct zone *zone, if (inactive_anon_is_low(zone, sc)) shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0); + /* reclaim/compaction might need reclaim to continue */ + if (should_continue_reclaim(zone, nr_reclaimed, + sc->nr_scanned - nr_scanned, sc)) + goto restart; + throttle_vm_writeout(sc->gfp_mask); } @@ -2007,7 +2083,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct zone *preferred_zone; first_zones_zonelist(zonelist, gfp_zone(sc->gfp_mask), - NULL, &preferred_zone); + &cpuset_current_mems_allowed, + &preferred_zone); wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/10); } } @@ -2124,38 +2201,87 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, } #endif +/* + * pgdat_balanced is used when checking if a node is balanced for high-order + * allocations. Only zones that meet watermarks and are in a zone allowed + * by the callers classzone_idx are added to balanced_pages. The total of + * balanced pages must be at least 25% of the zones allowed by classzone_idx + * for the node to be considered balanced. Forcing all zones to be balanced + * for high orders can cause excessive reclaim when there are imbalanced zones. + * The choice of 25% is due to + * o a 16M DMA zone that is balanced will not balance a zone on any + * reasonable sized machine + * o On all other machines, the top zone must be at least a reasonable + * precentage of the middle zones. For example, on 32-bit x86, highmem + * would need to be at least 256M for it to be balance a whole node. + * Similarly, on x86-64 the Normal zone would need to be at least 1G + * to balance a node on its own. These seemed like reasonable ratios. + */ +static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages, + int classzone_idx) +{ + unsigned long present_pages = 0; + int i; + + for (i = 0; i <= classzone_idx; i++) + present_pages += pgdat->node_zones[i].present_pages; + + return balanced_pages > (present_pages >> 2); +} + /* is kswapd sleeping prematurely? */ -static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining) +static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining, + int classzone_idx) { int i; + unsigned long balanced = 0; + bool all_zones_ok = true; /* If a direct reclaimer woke kswapd within HZ/10, it's premature */ if (remaining) - return 1; + return true; - /* If after HZ/10, a zone is below the high mark, it's premature */ + /* Check the watermark levels */ for (i = 0; i < pgdat->nr_zones; i++) { struct zone *zone = pgdat->node_zones + i; if (!populated_zone(zone)) continue; - if (zone->all_unreclaimable) + /* + * balance_pgdat() skips over all_unreclaimable after + * DEF_PRIORITY. Effectively, it considers them balanced so + * they must be considered balanced here as well if kswapd + * is to sleep + */ + if (zone->all_unreclaimable) { + balanced += zone->present_pages; continue; + } - if (!zone_watermark_ok(zone, order, high_wmark_pages(zone), - 0, 0)) - return 1; + if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), + classzone_idx, 0)) + all_zones_ok = false; + else + balanced += zone->present_pages; } - return 0; + /* + * For high-order requests, the balanced zones must contain at least + * 25% of the nodes pages for kswapd to sleep. For order-0, all zones + * must be balanced + */ + if (order) + return pgdat_balanced(pgdat, balanced, classzone_idx); + else + return !all_zones_ok; } /* * For kswapd, balance_pgdat() will work across all this node's zones until * they are all at high_wmark_pages(zone). * - * Returns the number of pages which were actually freed. + * Returns the final order kswapd was reclaiming at * * There is special handling here for zones which are full of pinned pages. * This can happen if the pages are all mlocked, or if they are all used by @@ -2172,11 +2298,14 @@ static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining) * interoperates with the page allocator fallback scheme to ensure that aging * of pages is balanced across the zones. */ -static unsigned long balance_pgdat(pg_data_t *pgdat, int order) +static unsigned long balance_pgdat(pg_data_t *pgdat, int order, + int *classzone_idx) { int all_zones_ok; + unsigned long balanced; int priority; int i; + int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ unsigned long total_scanned; struct reclaim_state *reclaim_state = current->reclaim_state; struct scan_control sc = { @@ -2199,7 +2328,6 @@ loop_again: count_vm_event(PAGEOUTRUN); for (priority = DEF_PRIORITY; priority >= 0; priority--) { - int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ unsigned long lru_pages = 0; int has_under_min_watermark_zone = 0; @@ -2208,6 +2336,7 @@ loop_again: disable_swap_token(); all_zones_ok = 1; + balanced = 0; /* * Scan in the highmem->dma direction for the highest @@ -2230,9 +2359,10 @@ loop_again: shrink_active_list(SWAP_CLUSTER_MAX, zone, &sc, priority, 0); - if (!zone_watermark_ok(zone, order, + if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), 0, 0)) { end_zone = i; + *classzone_idx = i; break; } } @@ -2255,6 +2385,7 @@ loop_again: * cause too much scanning of the lower zones. */ for (i = 0; i <= end_zone; i++) { + int compaction; struct zone *zone = pgdat->node_zones + i; int nr_slab; @@ -2276,7 +2407,7 @@ loop_again: * We put equal pressure on every zone, unless one * zone has way too many pages free already. */ - if (!zone_watermark_ok(zone, order, + if (!zone_watermark_ok_safe(zone, order, 8*high_wmark_pages(zone), end_zone, 0)) shrink_zone(priority, zone, &sc); reclaim_state->reclaimed_slab = 0; @@ -2284,9 +2415,26 @@ loop_again: lru_pages); sc.nr_reclaimed += reclaim_state->reclaimed_slab; total_scanned += sc.nr_scanned; + + compaction = 0; + if (order && + zone_watermark_ok(zone, 0, + high_wmark_pages(zone), + end_zone, 0) && + !zone_watermark_ok(zone, order, + high_wmark_pages(zone), + end_zone, 0)) { + compact_zone_order(zone, + order, + sc.gfp_mask, false, + COMPACT_MODE_KSWAPD); + compaction = 1; + } + if (zone->all_unreclaimable) continue; - if (nr_slab == 0 && !zone_reclaimable(zone)) + if (!compaction && nr_slab == 0 && + !zone_reclaimable(zone)) zone->all_unreclaimable = 1; /* * If we've done a decent amount of scanning and @@ -2297,7 +2445,7 @@ loop_again: total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2) sc.may_writepage = 1; - if (!zone_watermark_ok(zone, order, + if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), end_zone, 0)) { all_zones_ok = 0; /* @@ -2305,7 +2453,7 @@ loop_again: * means that we have a GFP_ATOMIC allocation * failure risk. Hurry up! */ - if (!zone_watermark_ok(zone, order, + if (!zone_watermark_ok_safe(zone, order, min_wmark_pages(zone), end_zone, 0)) has_under_min_watermark_zone = 1; } else { @@ -2317,10 +2465,12 @@ loop_again: * spectulatively avoid congestion waits */ zone_clear_flag(zone, ZONE_CONGESTED); + if (i <= *classzone_idx) + balanced += zone->present_pages; } } - if (all_zones_ok) + if (all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx))) break; /* kswapd: all done */ /* * OK, kswapd is getting into trouble. Take a nap, then take @@ -2343,7 +2493,13 @@ loop_again: break; } out: - if (!all_zones_ok) { + + /* + * order-0: All zones must meet high watermark for a balanced node + * high-order: Balanced zones must make up at least 25% of the node + * for the node to be balanced + */ + if (!(all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))) { cond_resched(); try_to_freeze(); @@ -2368,7 +2524,88 @@ out: goto loop_again; } - return sc.nr_reclaimed; + /* + * If kswapd was reclaiming at a higher order, it has the option of + * sleeping without all zones being balanced. Before it does, it must + * ensure that the watermarks for order-0 on *all* zones are met and + * that the congestion flags are cleared. The congestion flag must + * be cleared as kswapd is the only mechanism that clears the flag + * and it is potentially going to sleep here. + */ + if (order) { + for (i = 0; i <= end_zone; i++) { + struct zone *zone = pgdat->node_zones + i; + + if (!populated_zone(zone)) + continue; + + if (zone->all_unreclaimable && priority != DEF_PRIORITY) + continue; + + /* Confirm the zone is balanced for order-0 */ + if (!zone_watermark_ok(zone, 0, + high_wmark_pages(zone), 0, 0)) { + order = sc.order = 0; + goto loop_again; + } + + /* If balanced, clear the congested flag */ + zone_clear_flag(zone, ZONE_CONGESTED); + } + } + + /* + * Return the order we were reclaiming at so sleeping_prematurely() + * makes a decision on the order we were last reclaiming at. However, + * if another caller entered the allocator slow path while kswapd + * was awake, order will remain at the higher level + */ + *classzone_idx = end_zone; + return order; +} + +static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) +{ + long remaining = 0; + DEFINE_WAIT(wait); + + if (freezing(current) || kthread_should_stop()) + return; + + prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); + + /* Try to sleep for a short interval */ + if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) { + remaining = schedule_timeout(HZ/10); + finish_wait(&pgdat->kswapd_wait, &wait); + prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); + } + + /* + * After a short sleep, check if it was a premature sleep. If not, then + * go fully to sleep until explicitly woken up. + */ + if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) { + trace_mm_vmscan_kswapd_sleep(pgdat->node_id); + + /* + * vmstat counters are not perfectly accurate and the estimated + * value for counters such as NR_FREE_PAGES can deviate from the + * true value by nr_online_cpus * threshold. To avoid the zone + * watermarks being breached while under pressure, we reduce the + * per-cpu vmstat threshold while kswapd is awake and restore + * them before going back to sleep. + */ + set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); + schedule(); + set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); + } else { + if (remaining) + count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY); + else + count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY); + } + finish_wait(&pgdat->kswapd_wait, &wait); } /* @@ -2387,9 +2624,10 @@ out: static int kswapd(void *p) { unsigned long order; + int classzone_idx; pg_data_t *pgdat = (pg_data_t*)p; struct task_struct *tsk = current; - DEFINE_WAIT(wait); + struct reclaim_state reclaim_state = { .reclaimed_slab = 0, }; @@ -2417,49 +2655,30 @@ static int kswapd(void *p) set_freezable(); order = 0; + classzone_idx = MAX_NR_ZONES - 1; for ( ; ; ) { unsigned long new_order; + int new_classzone_idx; int ret; - prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); new_order = pgdat->kswapd_max_order; + new_classzone_idx = pgdat->classzone_idx; pgdat->kswapd_max_order = 0; - if (order < new_order) { + pgdat->classzone_idx = MAX_NR_ZONES - 1; + if (order < new_order || classzone_idx > new_classzone_idx) { /* * Don't sleep if someone wants a larger 'order' - * allocation + * allocation or has tigher zone constraints */ order = new_order; + classzone_idx = new_classzone_idx; } else { - if (!freezing(current) && !kthread_should_stop()) { - long remaining = 0; - - /* Try to sleep for a short interval */ - if (!sleeping_prematurely(pgdat, order, remaining)) { - remaining = schedule_timeout(HZ/10); - finish_wait(&pgdat->kswapd_wait, &wait); - prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); - } - - /* - * After a short sleep, check if it was a - * premature sleep. If not, then go fully - * to sleep until explicitly woken up - */ - if (!sleeping_prematurely(pgdat, order, remaining)) { - trace_mm_vmscan_kswapd_sleep(pgdat->node_id); - schedule(); - } else { - if (remaining) - count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY); - else - count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY); - } - } - + kswapd_try_to_sleep(pgdat, order, classzone_idx); order = pgdat->kswapd_max_order; + classzone_idx = pgdat->classzone_idx; + pgdat->kswapd_max_order = 0; + pgdat->classzone_idx = MAX_NR_ZONES - 1; } - finish_wait(&pgdat->kswapd_wait, &wait); ret = try_to_freeze(); if (kthread_should_stop()) @@ -2471,7 +2690,7 @@ static int kswapd(void *p) */ if (!ret) { trace_mm_vmscan_kswapd_wake(pgdat->node_id, order); - balance_pgdat(pgdat, order); + order = balance_pgdat(pgdat, order, &classzone_idx); } } return 0; @@ -2480,23 +2699,26 @@ static int kswapd(void *p) /* * A zone is low on free memory, so wake its kswapd task to service it. */ -void wakeup_kswapd(struct zone *zone, int order) +void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) { pg_data_t *pgdat; if (!populated_zone(zone)) return; - pgdat = zone->zone_pgdat; - if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0)) - return; - if (pgdat->kswapd_max_order < order) - pgdat->kswapd_max_order = order; - trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order); if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) return; + pgdat = zone->zone_pgdat; + if (pgdat->kswapd_max_order < order) { + pgdat->kswapd_max_order = order; + pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx); + } if (!waitqueue_active(&pgdat->kswapd_wait)) return; + if (zone_watermark_ok_safe(zone, order, low_wmark_pages(zone), 0, 0)) + return; + + trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order); wake_up_interruptible(&pgdat->kswapd_wait); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 8f62f17ee1c..0c3b5048773 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -83,7 +83,31 @@ EXPORT_SYMBOL(vm_stat); #ifdef CONFIG_SMP -static int calculate_threshold(struct zone *zone) +int calculate_pressure_threshold(struct zone *zone) +{ + int threshold; + int watermark_distance; + + /* + * As vmstats are not up to date, there is drift between the estimated + * and real values. For high thresholds and a high number of CPUs, it + * is possible for the min watermark to be breached while the estimated + * value looks fine. The pressure threshold is a reduced value such + * that even the maximum amount of drift will not accidentally breach + * the min watermark + */ + watermark_distance = low_wmark_pages(zone) - min_wmark_pages(zone); + threshold = max(1, (int)(watermark_distance / num_online_cpus())); + + /* + * Maximum threshold is 125 + */ + threshold = min(125, threshold); + + return threshold; +} + +int calculate_normal_threshold(struct zone *zone) { int threshold; int mem; /* memory in 128 MB units */ @@ -142,7 +166,7 @@ static void refresh_zone_stat_thresholds(void) for_each_populated_zone(zone) { unsigned long max_drift, tolerate_drift; - threshold = calculate_threshold(zone); + threshold = calculate_normal_threshold(zone); for_each_online_cpu(cpu) per_cpu_ptr(zone->pageset, cpu)->stat_threshold @@ -161,42 +185,50 @@ static void refresh_zone_stat_thresholds(void) } } +void set_pgdat_percpu_threshold(pg_data_t *pgdat, + int (*calculate_pressure)(struct zone *)) +{ + struct zone *zone; + int cpu; + int threshold; + int i; + + for (i = 0; i < pgdat->nr_zones; i++) { + zone = &pgdat->node_zones[i]; + if (!zone->percpu_drift_mark) + continue; + + threshold = (*calculate_pressure)(zone); + for_each_possible_cpu(cpu) + per_cpu_ptr(zone->pageset, cpu)->stat_threshold + = threshold; + } +} + /* * For use when we know that interrupts are disabled. */ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, int delta) { - struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset); - - s8 *p = pcp->vm_stat_diff + item; + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; long x; + long t; + + x = delta + __this_cpu_read(*p); - x = delta + *p; + t = __this_cpu_read(pcp->stat_threshold); - if (unlikely(x > pcp->stat_threshold || x < -pcp->stat_threshold)) { + if (unlikely(x > t || x < -t)) { zone_page_state_add(x, zone, item); x = 0; } - *p = x; + __this_cpu_write(*p, x); } EXPORT_SYMBOL(__mod_zone_page_state); /* - * For an unknown interrupt state - */ -void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, - int delta) -{ - unsigned long flags; - - local_irq_save(flags); - __mod_zone_page_state(zone, item, delta); - local_irq_restore(flags); -} -EXPORT_SYMBOL(mod_zone_page_state); - -/* * Optimized increment and decrement functions. * * These are only for a single page and therefore can take a struct page * @@ -221,16 +253,17 @@ EXPORT_SYMBOL(mod_zone_page_state); */ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { - struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset); - s8 *p = pcp->vm_stat_diff + item; + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; - (*p)++; + v = __this_cpu_inc_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v > t)) { + s8 overstep = t >> 1; - if (unlikely(*p > pcp->stat_threshold)) { - int overstep = pcp->stat_threshold / 2; - - zone_page_state_add(*p + overstep, zone, item); - *p = -overstep; + zone_page_state_add(v + overstep, zone, item); + __this_cpu_write(*p, -overstep); } } @@ -242,16 +275,17 @@ EXPORT_SYMBOL(__inc_zone_page_state); void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { - struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset); - s8 *p = pcp->vm_stat_diff + item; - - (*p)--; + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; - if (unlikely(*p < - pcp->stat_threshold)) { - int overstep = pcp->stat_threshold / 2; + v = __this_cpu_dec_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v < - t)) { + s8 overstep = t >> 1; - zone_page_state_add(*p - overstep, zone, item); - *p = overstep; + zone_page_state_add(v - overstep, zone, item); + __this_cpu_write(*p, overstep); } } @@ -261,6 +295,92 @@ void __dec_zone_page_state(struct page *page, enum zone_stat_item item) } EXPORT_SYMBOL(__dec_zone_page_state); +#ifdef CONFIG_CMPXCHG_LOCAL +/* + * If we have cmpxchg_local support then we do not need to incur the overhead + * that comes with local_irq_save/restore if we use this_cpu_cmpxchg. + * + * mod_state() modifies the zone counter state through atomic per cpu + * operations. + * + * Overstep mode specifies how overstep should handled: + * 0 No overstepping + * 1 Overstepping half of threshold + * -1 Overstepping minus half of threshold +*/ +static inline void mod_state(struct zone *zone, + enum zone_stat_item item, int delta, int overstep_mode) +{ + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; + long o, n, t, z; + + do { + z = 0; /* overflow to zone counters */ + + /* + * The fetching of the stat_threshold is racy. We may apply + * a counter threshold to the wrong the cpu if we get + * rescheduled while executing here. However, the following + * will apply the threshold again and therefore bring the + * counter under the threshold. + */ + t = this_cpu_read(pcp->stat_threshold); + + o = this_cpu_read(*p); + n = delta + o; + + if (n > t || n < -t) { + int os = overstep_mode * (t >> 1) ; + + /* Overflow must be added to zone counters */ + z = n + os; + n = -os; + } + } while (this_cpu_cmpxchg(*p, o, n) != o); + + if (z) + zone_page_state_add(z, zone, item); +} + +void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, + int delta) +{ + mod_state(zone, item, delta, 0); +} +EXPORT_SYMBOL(mod_zone_page_state); + +void inc_zone_state(struct zone *zone, enum zone_stat_item item) +{ + mod_state(zone, item, 1, 1); +} + +void inc_zone_page_state(struct page *page, enum zone_stat_item item) +{ + mod_state(page_zone(page), item, 1, 1); +} +EXPORT_SYMBOL(inc_zone_page_state); + +void dec_zone_page_state(struct page *page, enum zone_stat_item item) +{ + mod_state(page_zone(page), item, -1, -1); +} +EXPORT_SYMBOL(dec_zone_page_state); +#else +/* + * Use interrupt disable to serialize counter updates + */ +void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, + int delta) +{ + unsigned long flags; + + local_irq_save(flags); + __mod_zone_page_state(zone, item, delta); + local_irq_restore(flags); +} +EXPORT_SYMBOL(mod_zone_page_state); + void inc_zone_state(struct zone *zone, enum zone_stat_item item) { unsigned long flags; @@ -291,6 +411,7 @@ void dec_zone_page_state(struct page *page, enum zone_stat_item item) local_irq_restore(flags); } EXPORT_SYMBOL(dec_zone_page_state); +#endif /* * Update the zone counters for one cpu. @@ -759,6 +880,7 @@ static const char * const vmstat_text[] = { "numa_local", "numa_other", #endif + "nr_anon_transparent_hugepages", "nr_dirty_threshold", "nr_dirty_background_threshold", @@ -834,7 +956,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n scanned %lu" "\n spanned %lu" "\n present %lu", - zone_nr_free_pages(zone), + zone_page_state(zone, NR_FREE_PAGES), min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), @@ -1033,7 +1155,7 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb, break; case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: - cancel_rearming_delayed_work(&per_cpu(vmstat_work, cpu)); + cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu)); per_cpu(vmstat_work, cpu).work.func = NULL; break; case CPU_DOWN_FAILED: |