diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig | 8 | ||||
-rw-r--r-- | mm/Makefile | 6 | ||||
-rw-r--r-- | mm/backing-dev.c | 16 | ||||
-rw-r--r-- | mm/compaction.c | 116 | ||||
-rw-r--r-- | mm/early_ioremap.c | 245 | ||||
-rw-r--r-- | mm/filemap.c | 924 | ||||
-rw-r--r-- | mm/fremap.c | 28 | ||||
-rw-r--r-- | mm/huge_memory.c | 120 | ||||
-rw-r--r-- | mm/hugetlb.c | 308 | ||||
-rw-r--r-- | mm/hugetlb_cgroup.c | 11 | ||||
-rw-r--r-- | mm/internal.h | 16 | ||||
-rw-r--r-- | mm/iov_iter.c | 224 | ||||
-rw-r--r-- | mm/kmemleak.c | 140 | ||||
-rw-r--r-- | mm/ksm.c | 2 | ||||
-rw-r--r-- | mm/list_lru.c | 16 | ||||
-rw-r--r-- | mm/memblock.c | 33 | ||||
-rw-r--r-- | mm/memcontrol.c | 563 | ||||
-rw-r--r-- | mm/memory-failure.c | 16 | ||||
-rw-r--r-- | mm/memory.c | 614 | ||||
-rw-r--r-- | mm/mempolicy.c | 150 | ||||
-rw-r--r-- | mm/mempool.c | 4 | ||||
-rw-r--r-- | mm/migrate.c | 43 | ||||
-rw-r--r-- | mm/mincore.c | 20 | ||||
-rw-r--r-- | mm/mlock.c | 2 | ||||
-rw-r--r-- | mm/mmap.c | 79 | ||||
-rw-r--r-- | mm/mmu_context.c | 3 | ||||
-rw-r--r-- | mm/mprotect.c | 81 | ||||
-rw-r--r-- | mm/nobootmem.c | 2 | ||||
-rw-r--r-- | mm/nommu.c | 51 | ||||
-rw-r--r-- | mm/page-writeback.c | 9 | ||||
-rw-r--r-- | mm/page_alloc.c | 110 | ||||
-rw-r--r-- | mm/page_cgroup.c | 12 | ||||
-rw-r--r-- | mm/percpu.c | 208 | ||||
-rw-r--r-- | mm/process_vm_access.c | 278 | ||||
-rw-r--r-- | mm/readahead.c | 31 | ||||
-rw-r--r-- | mm/rmap.c | 29 | ||||
-rw-r--r-- | mm/shmem.c | 210 | ||||
-rw-r--r-- | mm/slab.c | 12 | ||||
-rw-r--r-- | mm/slab.h | 21 | ||||
-rw-r--r-- | mm/slab_common.c | 250 | ||||
-rw-r--r-- | mm/slub.c | 149 | ||||
-rw-r--r-- | mm/sparse.c | 6 | ||||
-rw-r--r-- | mm/swap.c | 57 | ||||
-rw-r--r-- | mm/swap_state.c | 63 | ||||
-rw-r--r-- | mm/swapfile.c | 11 | ||||
-rw-r--r-- | mm/truncate.c | 148 | ||||
-rw-r--r-- | mm/util.c | 53 | ||||
-rw-r--r-- | mm/vmacache.c | 112 | ||||
-rw-r--r-- | mm/vmalloc.c | 10 | ||||
-rw-r--r-- | mm/vmpressure.c | 1 | ||||
-rw-r--r-- | mm/vmscan.c | 150 | ||||
-rw-r--r-- | mm/vmstat.c | 16 | ||||
-rw-r--r-- | mm/workingset.c | 414 | ||||
-rw-r--r-- | mm/zsmalloc.c | 17 | ||||
-rw-r--r-- | mm/zswap.c | 86 |
55 files changed, 3920 insertions, 2384 deletions
@@ -216,6 +216,7 @@ config PAGEFLAGS_EXTENDED # config SPLIT_PTLOCK_CPUS int + default "999999" if !MMU default "999999" if ARM && !CPU_CACHE_VIPT default "999999" if PARISC && !PA20 default "4" @@ -575,5 +576,8 @@ config PGTABLE_MAPPING then you should select this. This causes zsmalloc to use page table mapping rather than copying for object mapping. - You can check speed with zsmalloc benchmark[1]. - [1] https://github.com/spartacus06/zsmalloc + You can check speed with zsmalloc benchmark: + https://github.com/spartacus06/zsmapbench + +config GENERIC_EARLY_IOREMAP + bool diff --git a/mm/Makefile b/mm/Makefile index 310c90a..b484452 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -16,8 +16,9 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ - compaction.o balloon_compaction.o \ - interval_tree.o list_lru.o $(mmu-y) + compaction.o balloon_compaction.o vmacache.o \ + interval_tree.o list_lru.o workingset.o \ + iov_iter.o $(mmu-y) obj-y += init-mm.o @@ -61,3 +62,4 @@ obj-$(CONFIG_CLEANCACHE) += cleancache.o obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o obj-$(CONFIG_ZBUD) += zbud.o obj-$(CONFIG_ZSMALLOC) += zsmalloc.o +obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c index ce682f7..09d9591 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -288,13 +288,19 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi) * Note, we wouldn't bother setting up the timer, but this function is on the * fast-path (used by '__mark_inode_dirty()'), so we save few context switches * by delaying the wake-up. + * + * We have to be careful not to postpone flush work if it is scheduled for + * earlier. Thus we use queue_delayed_work(). */ void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi) { unsigned long timeout; timeout = msecs_to_jiffies(dirty_writeback_interval * 10); - mod_delayed_work(bdi_wq, &bdi->wb.dwork, timeout); + spin_lock_bh(&bdi->wb_lock); + if (test_bit(BDI_registered, &bdi->state)) + queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout); + spin_unlock_bh(&bdi->wb_lock); } /* @@ -307,9 +313,6 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi) spin_unlock_bh(&bdi_lock); synchronize_rcu_expedited(); - - /* bdi_list is now unused, clear it to mark @bdi dying */ - INIT_LIST_HEAD(&bdi->bdi_list); } int bdi_register(struct backing_dev_info *bdi, struct device *parent, @@ -360,6 +363,11 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) */ bdi_remove_from_list(bdi); + /* Make sure nobody queues further work */ + spin_lock_bh(&bdi->wb_lock); + clear_bit(BDI_registered, &bdi->state); + spin_unlock_bh(&bdi->wb_lock); + /* * Drain work list and shutdown the delayed_work. At this point, * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi diff --git a/mm/compaction.c b/mm/compaction.c index b48c525..37f9762 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -217,21 +217,12 @@ static inline bool compact_trylock_irqsave(spinlock_t *lock, /* Returns true if the page is within a block suitable for migration to */ static bool suitable_migration_target(struct page *page) { - int migratetype = get_pageblock_migratetype(page); - - /* Don't interfere with memory hot-remove or the min_free_kbytes blocks */ - if (migratetype == MIGRATE_RESERVE) - return false; - - if (is_migrate_isolate(migratetype)) - return false; - - /* If the page is a large free page, then allow migration */ + /* If the page is a large free page, then disallow migration */ if (PageBuddy(page) && page_order(page) >= pageblock_order) - return true; + return false; /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ - if (migrate_async_suitable(migratetype)) + if (migrate_async_suitable(get_pageblock_migratetype(page))) return true; /* Otherwise skip the block */ @@ -251,9 +242,9 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, { int nr_scanned = 0, total_isolated = 0; struct page *cursor, *valid_page = NULL; - unsigned long nr_strict_required = end_pfn - blockpfn; unsigned long flags; bool locked = false; + bool checked_pageblock = false; cursor = pfn_to_page(blockpfn); @@ -264,11 +255,12 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, nr_scanned++; if (!pfn_valid_within(blockpfn)) - continue; + goto isolate_fail; + if (!valid_page) valid_page = page; if (!PageBuddy(page)) - continue; + goto isolate_fail; /* * The zone lock must be held to isolate freepages. @@ -284,17 +276,23 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, break; /* Recheck this is a suitable migration target under lock */ - if (!strict && !suitable_migration_target(page)) - break; + if (!strict && !checked_pageblock) { + /* + * We need to check suitability of pageblock only once + * and this isolate_freepages_block() is called with + * pageblock range, so just check once is sufficient. + */ + checked_pageblock = true; + if (!suitable_migration_target(page)) + break; + } /* Recheck this is a buddy page under lock */ if (!PageBuddy(page)) - continue; + goto isolate_fail; /* Found a free page, break it into order-0 pages */ isolated = split_free_page(page); - if (!isolated && strict) - break; total_isolated += isolated; for (i = 0; i < isolated; i++) { list_add(&page->lru, freelist); @@ -305,7 +303,15 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, if (isolated) { blockpfn += isolated - 1; cursor += isolated - 1; + continue; } + +isolate_fail: + if (strict) + break; + else + continue; + } trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated); @@ -315,7 +321,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, * pages requested were isolated. If there were any failures, 0 is * returned and CMA will fail. */ - if (strict && nr_strict_required > total_isolated) + if (strict && blockpfn < end_pfn) total_isolated = 0; if (locked) @@ -454,12 +460,13 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, unsigned long last_pageblock_nr = 0, pageblock_nr; unsigned long nr_scanned = 0, nr_isolated = 0; struct list_head *migratelist = &cc->migratepages; - isolate_mode_t mode = 0; struct lruvec *lruvec; unsigned long flags; bool locked = false; struct page *page = NULL, *valid_page = NULL; bool skipped_async_unsuitable = false; + const isolate_mode_t mode = (!cc->sync ? ISOLATE_ASYNC_MIGRATE : 0) | + (unevictable ? ISOLATE_UNEVICTABLE : 0); /* * Ensure that there are not too many pages isolated from the LRU @@ -481,7 +488,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, cond_resched(); for (; low_pfn < end_pfn; low_pfn++) { /* give a chance to irqs before checking need_resched() */ - if (locked && !((low_pfn+1) % SWAP_CLUSTER_MAX)) { + if (locked && !(low_pfn % SWAP_CLUSTER_MAX)) { if (should_release_lock(&zone->lru_lock)) { spin_unlock_irqrestore(&zone->lru_lock, flags); locked = false; @@ -520,8 +527,25 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, /* If isolation recently failed, do not retry */ pageblock_nr = low_pfn >> pageblock_order; - if (!isolation_suitable(cc, page)) - goto next_pageblock; + if (last_pageblock_nr != pageblock_nr) { + int mt; + + last_pageblock_nr = pageblock_nr; + if (!isolation_suitable(cc, page)) + goto next_pageblock; + + /* + * For async migration, also only scan in MOVABLE + * blocks. Async migration is optimistic to see if + * the minimum amount of work satisfies the allocation + */ + mt = get_pageblock_migratetype(page); + if (!cc->sync && !migrate_async_suitable(mt)) { + cc->finished_update_migrate = true; + skipped_async_unsuitable = true; + goto next_pageblock; + } + } /* * Skip if free. page_order cannot be used without zone->lock @@ -531,18 +555,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, 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 - */ - if (!cc->sync && last_pageblock_nr != pageblock_nr && - !migrate_async_suitable(get_pageblock_migratetype(page))) { - cc->finished_update_migrate = true; - skipped_async_unsuitable = true; - goto next_pageblock; - } - - /* * Check may be lockless but that's ok as we recheck later. * It's possible to migrate LRU pages and balloon pages * Skip any other type of page @@ -551,11 +563,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, if (unlikely(balloon_page_movable(page))) { if (locked && balloon_page_isolate(page)) { /* Successfully isolated */ - cc->finished_update_migrate = true; - list_add(&page->lru, migratelist); - cc->nr_migratepages++; - nr_isolated++; - goto check_compact_cluster; + goto isolate_success; } } continue; @@ -578,6 +586,15 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; } + /* + * Migration will fail if an anonymous page is pinned in memory, + * so avoid taking lru_lock and isolating it unnecessarily in an + * admittedly racy check. + */ + if (!page_mapping(page) && + page_count(page) > page_mapcount(page)) + continue; + /* Check if it is ok to still hold the lock */ locked = compact_checklock_irqsave(&zone->lru_lock, &flags, locked, cc); @@ -592,12 +609,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; } - if (!cc->sync) - mode |= ISOLATE_ASYNC_MIGRATE; - - if (unevictable) - mode |= ISOLATE_UNEVICTABLE; - lruvec = mem_cgroup_page_lruvec(page, zone); /* Try isolate the page */ @@ -607,13 +618,14 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, VM_BUG_ON_PAGE(PageTransCompound(page), page); /* Successfully isolated */ - cc->finished_update_migrate = true; del_page_from_lru_list(page, lruvec, page_lru(page)); + +isolate_success: + cc->finished_update_migrate = true; list_add(&page->lru, migratelist); cc->nr_migratepages++; nr_isolated++; -check_compact_cluster: /* Avoid isolating too much */ if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) { ++low_pfn; @@ -624,7 +636,6 @@ check_compact_cluster: next_pageblock: low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1; - last_pageblock_nr = pageblock_nr; } acct_isolated(zone, locked, cc); @@ -1180,6 +1191,7 @@ static void compact_node(int nid) struct compact_control cc = { .order = -1, .sync = true, + .ignore_skip_hint = true, }; __compact_pgdat(NODE_DATA(nid), &cc); @@ -1219,7 +1231,7 @@ int sysctl_extfrag_handler(struct ctl_table *table, int write, } #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) -ssize_t sysfs_compact_node(struct device *dev, +static ssize_t sysfs_compact_node(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c new file mode 100644 index 0000000..e10ccd2 --- /dev/null +++ b/mm/early_ioremap.c @@ -0,0 +1,245 @@ +/* + * Provide common bits of early_ioremap() support for architectures needing + * temporary mappings during boot before ioremap() is available. + * + * This is mostly a direct copy of the x86 early_ioremap implementation. + * + * (C) Copyright 1995 1996, 2014 Linus Torvalds + * + */ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/mm.h> +#include <linux/vmalloc.h> +#include <asm/fixmap.h> + +#ifdef CONFIG_MMU +static int early_ioremap_debug __initdata; + +static int __init early_ioremap_debug_setup(char *str) +{ + early_ioremap_debug = 1; + + return 0; +} +early_param("early_ioremap_debug", early_ioremap_debug_setup); + +static int after_paging_init __initdata; + +void __init __weak early_ioremap_shutdown(void) +{ +} + +void __init early_ioremap_reset(void) +{ + early_ioremap_shutdown(); + after_paging_init = 1; +} + +/* + * Generally, ioremap() is available after paging_init() has been called. + * Architectures wanting to allow early_ioremap after paging_init() can + * define __late_set_fixmap and __late_clear_fixmap to do the right thing. + */ +#ifndef __late_set_fixmap +static inline void __init __late_set_fixmap(enum fixed_addresses idx, + phys_addr_t phys, pgprot_t prot) +{ + BUG(); +} +#endif + +#ifndef __late_clear_fixmap +static inline void __init __late_clear_fixmap(enum fixed_addresses idx) +{ + BUG(); +} +#endif + +static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata; +static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata; +static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata; + +void __init early_ioremap_setup(void) +{ + int i; + + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) + if (WARN_ON(prev_map[i])) + break; + + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) + slot_virt[i] = __fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i); +} + +static int __init check_early_ioremap_leak(void) +{ + int count = 0; + int i; + + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) + if (prev_map[i]) + count++; + + if (WARN(count, KERN_WARNING + "Debug warning: early ioremap leak of %d areas detected.\n" + "please boot with early_ioremap_debug and report the dmesg.\n", + count)) + return 1; + return 0; +} +late_initcall(check_early_ioremap_leak); + +static void __init __iomem * +__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot) +{ + unsigned long offset; + resource_size_t last_addr; + unsigned int nrpages; + enum fixed_addresses idx; + int i, slot; + + WARN_ON(system_state != SYSTEM_BOOTING); + + slot = -1; + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) { + if (!prev_map[i]) { + slot = i; + break; + } + } + + if (WARN(slot < 0, "%s(%08llx, %08lx) not found slot\n", + __func__, (u64)phys_addr, size)) + return NULL; + + /* Don't allow wraparound or zero size */ + last_addr = phys_addr + size - 1; + if (WARN_ON(!size || last_addr < phys_addr)) + return NULL; + + prev_size[slot] = size; + /* + * Mappings have to be page-aligned + */ + offset = phys_addr & ~PAGE_MASK; + phys_addr &= PAGE_MASK; + size = PAGE_ALIGN(last_addr + 1) - phys_addr; + + /* + * Mappings have to fit in the FIX_BTMAP area. + */ + nrpages = size >> PAGE_SHIFT; + if (WARN_ON(nrpages > NR_FIX_BTMAPS)) + return NULL; + + /* + * Ok, go for it.. + */ + idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; + while (nrpages > 0) { + if (after_paging_init) + __late_set_fixmap(idx, phys_addr, prot); + else + __early_set_fixmap(idx, phys_addr, prot); + phys_addr += PAGE_SIZE; + --idx; + --nrpages; + } + WARN(early_ioremap_debug, "%s(%08llx, %08lx) [%d] => %08lx + %08lx\n", + __func__, (u64)phys_addr, size, slot, offset, slot_virt[slot]); + + prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]); + return prev_map[slot]; +} + +void __init early_iounmap(void __iomem *addr, unsigned long size) +{ + unsigned long virt_addr; + unsigned long offset; + unsigned int nrpages; + enum fixed_addresses idx; + int i, slot; + + slot = -1; + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) { + if (prev_map[i] == addr) { + slot = i; + break; + } + } + + if (WARN(slot < 0, "early_iounmap(%p, %08lx) not found slot\n", + addr, size)) + return; + + if (WARN(prev_size[slot] != size, + "early_iounmap(%p, %08lx) [%d] size not consistent %08lx\n", + addr, size, slot, prev_size[slot])) + return; + + WARN(early_ioremap_debug, "early_iounmap(%p, %08lx) [%d]\n", + addr, size, slot); + + virt_addr = (unsigned long)addr; + if (WARN_ON(virt_addr < fix_to_virt(FIX_BTMAP_BEGIN))) + return; + + offset = virt_addr & ~PAGE_MASK; + nrpages = PAGE_ALIGN(offset + size) >> PAGE_SHIFT; + + idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; + while (nrpages > 0) { + if (after_paging_init) + __late_clear_fixmap(idx); + else + __early_set_fixmap(idx, 0, FIXMAP_PAGE_CLEAR); + --idx; + --nrpages; + } + prev_map[slot] = NULL; +} + +/* Remap an IO device */ +void __init __iomem * +early_ioremap(resource_size_t phys_addr, unsigned long size) +{ + return __early_ioremap(phys_addr, size, FIXMAP_PAGE_IO); +} + +/* Remap memory */ +void __init * +early_memremap(resource_size_t phys_addr, unsigned long size) +{ + return (__force void *)__early_ioremap(phys_addr, size, + FIXMAP_PAGE_NORMAL); +} +#else /* CONFIG_MMU */ + +void __init __iomem * +early_ioremap(resource_size_t phys_addr, unsigned long size) +{ + return (__force void __iomem *)phys_addr; +} + +/* Remap memory */ +void __init * +early_memremap(resource_size_t phys_addr, unsigned long size) +{ + return (void *)phys_addr; +} + +void __init early_iounmap(void __iomem *addr, unsigned long size) +{ +} + +#endif /* CONFIG_MMU */ + + +void __init early_memunmap(void *addr, unsigned long size) +{ + early_iounmap((__force void __iomem *)addr, size); +} diff --git a/mm/filemap.c b/mm/filemap.c index d56d3c1..a82fbe4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -33,6 +33,7 @@ #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */ #include <linux/memcontrol.h> #include <linux/cleancache.h> +#include <linux/rmap.h> #include "internal.h" #define CREATE_TRACE_POINTS @@ -76,7 +77,7 @@ * ->mmap_sem * ->lock_page (access_process_vm) * - * ->i_mutex (generic_file_buffered_write) + * ->i_mutex (generic_perform_write) * ->mmap_sem (fault_in_pages_readable->do_page_fault) * * bdi->wb.list_lock @@ -107,12 +108,75 @@ * ->tasklist_lock (memory_failure, collect_procs_ao) */ +static void page_cache_tree_delete(struct address_space *mapping, + struct page *page, void *shadow) +{ + struct radix_tree_node *node; + unsigned long index; + unsigned int offset; + unsigned int tag; + void **slot; + + VM_BUG_ON(!PageLocked(page)); + + __radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot); + + if (shadow) { + mapping->nrshadows++; + /* + * Make sure the nrshadows update is committed before + * the nrpages update so that final truncate racing + * with reclaim does not see both counters 0 at the + * same time and miss a shadow entry. + */ + smp_wmb(); + } + mapping->nrpages--; + + if (!node) { + /* Clear direct pointer tags in root node */ + mapping->page_tree.gfp_mask &= __GFP_BITS_MASK; + radix_tree_replace_slot(slot, shadow); + return; + } + + /* Clear tree tags for the removed page */ + index = page->index; + offset = index & RADIX_TREE_MAP_MASK; + for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { + if (test_bit(offset, node->tags[tag])) + radix_tree_tag_clear(&mapping->page_tree, index, tag); + } + + /* Delete page, swap shadow entry */ + radix_tree_replace_slot(slot, shadow); + workingset_node_pages_dec(node); + if (shadow) + workingset_node_shadows_inc(node); + else + if (__radix_tree_delete_node(&mapping->page_tree, node)) + return; + + /* + * Track node that only contains shadow entries. + * + * Avoid acquiring the list_lru lock if already tracked. The + * list_empty() test is safe as node->private_list is + * protected by mapping->tree_lock. + */ + if (!workingset_node_pages(node) && + list_empty(&node->private_list)) { + node->private_data = mapping; + list_lru_add(&workingset_shadow_nodes, &node->private_list); + } +} + /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the mapping's tree_lock. */ -void __delete_from_page_cache(struct page *page) +void __delete_from_page_cache(struct page *page, void *shadow) { struct address_space *mapping = page->mapping; @@ -127,10 +191,11 @@ void __delete_from_page_cache(struct page *page) else cleancache_invalidate_page(mapping, page); - radix_tree_delete(&mapping->page_tree, page->index); + page_cache_tree_delete(mapping, page, shadow); + page->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ - mapping->nrpages--; + __dec_zone_page_state(page, NR_FILE_PAGES); if (PageSwapBacked(page)) __dec_zone_page_state(page, NR_SHMEM); @@ -166,7 +231,7 @@ void delete_from_page_cache(struct page *page) freepage = mapping->a_ops->freepage; spin_lock_irq(&mapping->tree_lock); - __delete_from_page_cache(page); + __delete_from_page_cache(page, NULL); spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); @@ -426,7 +491,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) new->index = offset; spin_lock_irq(&mapping->tree_lock); - __delete_from_page_cache(old); + __delete_from_page_cache(old, NULL); error = radix_tree_insert(&mapping->page_tree, offset, new); BUG_ON(error); mapping->nrpages++; @@ -446,25 +511,59 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(replace_page_cache_page); -/** - * add_to_page_cache_locked - add a locked page to the pagecache - * @page: page to add - * @mapping: the page's address_space - * @offset: page index - * @gfp_mask: page allocation mode - * - * This function is used to add a page to the pagecache. It must be locked. - * This function does not add the page to the LRU. The caller must do that. - */ -int add_to_page_cache_locked(struct page *page, struct address_space *mapping, - pgoff_t offset, gfp_t gfp_mask) +static int page_cache_tree_insert(struct address_space *mapping, + struct page *page, void **shadowp) +{ + struct radix_tree_node *node; + void **slot; + int error; + + error = __radix_tree_create(&mapping->page_tree, page->index, + &node, &slot); + if (error) + return error; + if (*slot) { + void *p; + + p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); + if (!radix_tree_exceptional_entry(p)) + return -EEXIST; + if (shadowp) + *shadowp = p; + mapping->nrshadows--; + if (node) + workingset_node_shadows_dec(node); + } + radix_tree_replace_slot(slot, page); + mapping->nrpages++; + if (node) { + workingset_node_pages_inc(node); + /* + * Don't track node that contains actual pages. + * + * Avoid acquiring the list_lru lock if already + * untracked. The list_empty() test is safe as + * node->private_list is protected by + * mapping->tree_lock. + */ + if (!list_empty(&node->private_list)) + list_lru_del(&workingset_shadow_nodes, + &node->private_list); + } + return 0; +} + +static int __add_to_page_cache_locked(struct page *page, + struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask, + void **shadowp) { int error; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageSwapBacked(page), page); - error = mem_cgroup_cache_charge(page, current->mm, + error = mem_cgroup_charge_file(page, current->mm, gfp_mask & GFP_RECLAIM_MASK); if (error) return error; @@ -480,11 +579,10 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, page->index = offset; spin_lock_irq(&mapping->tree_lock); - error = radix_tree_insert(&mapping->page_tree, offset, page); + error = page_cache_tree_insert(mapping, page, shadowp); radix_tree_preload_end(); if (unlikely(error)) goto err_insert; - mapping->nrpages++; __inc_zone_page_state(page, NR_FILE_PAGES); spin_unlock_irq(&mapping->tree_lock); trace_mm_filemap_add_to_page_cache(page); @@ -497,16 +595,49 @@ err_insert: page_cache_release(page); return error; } + +/** + * add_to_page_cache_locked - add a locked page to the pagecache + * @page: page to add + * @mapping: the page's address_space + * @offset: page index + * @gfp_mask: page allocation mode + * + * This function is used to add a page to the pagecache. It must be locked. + * This function does not add the page to the LRU. The caller must do that. + */ +int add_to_page_cache_locked(struct page *page, struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask) +{ + return __add_to_page_cache_locked(page, mapping, offset, + gfp_mask, NULL); +} EXPORT_SYMBOL(add_to_page_cache_locked); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { + void *shadow = NULL; int ret; - ret = add_to_page_cache(page, mapping, offset, gfp_mask); - if (ret == 0) - lru_cache_add_file(page); + __set_page_locked(page); + ret = __add_to_page_cache_locked(page, mapping, offset, + gfp_mask, &shadow); + if (unlikely(ret)) + __clear_page_locked(page); + else { + /* + * The page might have been evicted from cache only + * recently, in which case it should be activated like + * any other repeatedly accessed page. + */ + if (shadow && workingset_refault(shadow)) { + SetPageActive(page); + workingset_activation(page); + } else + ClearPageActive(page); + lru_cache_add(page); + } return ret; } EXPORT_SYMBOL_GPL(add_to_page_cache_lru); @@ -520,10 +651,10 @@ struct page *__page_cache_alloc(gfp_t gfp) if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); page = alloc_pages_exact_node(n, gfp, 0); - } while (!put_mems_allowed(cpuset_mems_cookie) && !page); + } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); return page; } @@ -686,14 +817,101 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, } /** - * find_get_page - find and get a page reference + * page_cache_next_hole - find the next hole (not-present entry) + * @mapping: mapping + * @index: index + * @max_scan: maximum range to search + * + * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the + * lowest indexed hole. + * + * Returns: the index of the hole if found, otherwise returns an index + * outside of the set specified (in which case 'return - index >= + * max_scan' will be true). In rare cases of index wrap-around, 0 will + * be returned. + * + * page_cache_next_hole may be called under rcu_read_lock. However, + * like radix_tree_gang_lookup, this will not atomically search a + * snapshot of the tree at a single point in time. For example, if a + * hole is created at index 5, then subsequently a hole is created at + * index 10, page_cache_next_hole covering both indexes may return 10 + * if called under rcu_read_lock. + */ +pgoff_t page_cache_next_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan) +{ + unsigned long i; + + for (i = 0; i < max_scan; i++) { + struct page *page; + + page = radix_tree_lookup(&mapping->page_tree, index); + if (!page || radix_tree_exceptional_entry(page)) + break; + index++; + if (index == 0) + break; + } + + return index; +} +EXPORT_SYMBOL(page_cache_next_hole); + +/** + * page_cache_prev_hole - find the prev hole (not-present entry) + * @mapping: mapping + * @index: index + * @max_scan: maximum range to search + * + * Search backwards in the range [max(index-max_scan+1, 0), index] for + * the first hole. + * + * Returns: the index of the hole if found, otherwise returns an index + * outside of the set specified (in which case 'index - return >= + * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX + * will be returned. + * + * page_cache_prev_hole may be called under rcu_read_lock. However, + * like radix_tree_gang_lookup, this will not atomically search a + * snapshot of the tree at a single point in time. For example, if a + * hole is created at index 10, then subsequently a hole is created at + * index 5, page_cache_prev_hole covering both indexes may return 5 if + * called under rcu_read_lock. + */ +pgoff_t page_cache_prev_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan) +{ + unsigned long i; + + for (i = 0; i < max_scan; i++) { + struct page *page; + + page = radix_tree_lookup(&mapping->page_tree, index); + if (!page || radix_tree_exceptional_entry(page)) + break; + index--; + if (index == ULONG_MAX) + break; + } + + return index; +} +EXPORT_SYMBOL(page_cache_prev_hole); + +/** + * find_get_entry - find and get a page cache entry * @mapping: the address_space to search - * @offset: the page index + * @offset: the page cache index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. * - * Is there a pagecache struct page at the given (mapping, offset) tuple? - * If yes, increment its refcount and return it; if no, return NULL. + * If the slot holds a shadow entry of a previously evicted page, it + * is returned. + * + * Otherwise, %NULL is returned. */ -struct page *find_get_page(struct address_space *mapping, pgoff_t offset) +struct page *find_get_entry(struct address_space *mapping, pgoff_t offset) { void **pagep; struct page *page; @@ -734,24 +952,50 @@ out: return page; } -EXPORT_SYMBOL(find_get_page); +EXPORT_SYMBOL(find_get_entry); /** - * find_lock_page - locate, pin and lock a pagecache page + * find_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index * - * Locates the desired pagecache page, locks it, increments its reference - * count and returns its address. + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. * - * Returns zero if the page was not present. find_lock_page() may sleep. + * Otherwise, %NULL is returned. */ -struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) +struct page *find_get_page(struct address_space *mapping, pgoff_t offset) +{ + struct page *page = find_get_entry(mapping, offset); + + if (radix_tree_exceptional_entry(page)) + page = NULL; + return page; +} +EXPORT_SYMBOL(find_get_page); + +/** + * find_lock_entry - locate, pin and lock a page cache entry + * @mapping: the address_space to search + * @offset: the page cache index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * If the slot holds a shadow entry of a previously evicted page, it + * is returned. + * + * Otherwise, %NULL is returned. + * + * find_lock_entry() may sleep. + */ +struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset) { struct page *page; repeat: - page = find_get_page(mapping, offset); + page = find_get_entry(mapping, offset); if (page && !radix_tree_exception(page)) { lock_page(page); /* Has the page been truncated? */ @@ -764,6 +1008,29 @@ repeat: } return page; } +EXPORT_SYMBOL(find_lock_entry); + +/** + * find_lock_page - locate, pin and lock a pagecache page + * @mapping: the address_space to search + * @offset: the page index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * Otherwise, %NULL is returned. + * + * find_lock_page() may sleep. + */ +struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) +{ + struct page *page = find_lock_entry(mapping, offset); + + if (radix_tree_exceptional_entry(page)) + page = NULL; + return page; +} EXPORT_SYMBOL(find_lock_page); /** @@ -772,16 +1039,18 @@ EXPORT_SYMBOL(find_lock_page); * @index: the page's index into the mapping * @gfp_mask: page allocation mode * - * Locates a page in the pagecache. If the page is not present, a new page - * is allocated using @gfp_mask and is added to the pagecache and to the VM's - * LRU list. The returned page is locked and has its reference count - * incremented. + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * If the page is not present, a new page is allocated using @gfp_mask + * and added to the page cache and the VM's LRU list. The page is + * returned locked and with an increased refcount. * - * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic - * allocation! + * On memory exhaustion, %NULL is returned. * - * find_or_create_page() returns the desired page's address, or zero on - * memory exhaustion. + * find_or_create_page() may sleep, even if @gfp_flags specifies an + * atomic allocation! */ struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask) @@ -814,6 +1083,76 @@ repeat: EXPORT_SYMBOL(find_or_create_page); /** + * find_get_entries - gang pagecache lookup + * @mapping: The address_space to search + * @start: The starting page cache index + * @nr_entries: The maximum number of entries + * @entries: Where the resulting entries are placed + * @indices: The cache indices corresponding to the entries in @entries + * + * find_get_entries() will search for and return a group of up to + * @nr_entries entries in the mapping. The entries are placed at + * @entries. find_get_entries() takes a reference against any actual + * pages it returns. + * + * The search returns a group of mapping-contiguous page cache entries + * with ascending indexes. There may be holes in the indices due to + * not-present pages. + * + * Any shadow entries of evicted pages are included in the returned + * array. + * + * find_get_entries() returns the number of pages and shadow entries + * which were found. + */ +unsigned find_get_entries(struct address_space *mapping, + pgoff_t start, unsigned int nr_entries, + struct page **entries, pgoff_t *indices) +{ + void **slot; + unsigned int ret = 0; + struct radix_tree_iter iter; + + if (!nr_entries) + return 0; + + rcu_read_lock(); +restart: + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + struct page *page; +repeat: + page = radix_tree_deref_slot(slot); + if (unlikely(!page)) + continue; + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) + goto restart; + /* + * Otherwise, we must be storing a swap entry + * here as an exceptional entry: so return it + * without attempting to raise page count. + */ + goto export; + } + if (!page_cache_get_speculative(page)) + goto repeat; + + /* Has the page moved? */ + if (unlikely(page != *slot)) { + page_cache_release(page); + goto repeat; + } +export: + indices[ret] = iter.index; + entries[ret] = page; + if (++ret == nr_entries) + break; + } + rcu_read_unlock(); + return ret; +} + +/** * find_get_pages - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page index @@ -1089,7 +1428,8 @@ static void shrink_readahead_size_eio(struct file *filp, * do_generic_file_read - generic file read routine * @filp: the file to read * @ppos: current file position - * @desc: read_descriptor + * @iter: data destination + * @written: already copied * * This is a generic file read routine, and uses the * mapping->a_ops->readpage() function for the actual low-level stuff. @@ -1097,8 +1437,8 @@ static void shrink_readahead_size_eio(struct file *filp, * This is really ugly. But the goto's actually try to clarify some * of the logic when it comes to error handling etc. */ -static void do_generic_file_read(struct file *filp, loff_t *ppos, - read_descriptor_t *desc) +static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos, + struct iov_iter *iter, ssize_t written) { struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; @@ -1108,12 +1448,12 @@ static void do_generic_file_read(struct file *filp, loff_t *ppos, pgoff_t prev_index; unsigned long offset; /* offset into pagecache page */ unsigned int prev_offset; - int error; + int error = 0; index = *ppos >> PAGE_CACHE_SHIFT; prev_index = ra->prev_pos >> PAGE_CACHE_SHIFT; prev_offset = ra->prev_pos & (PAGE_CACHE_SIZE-1); - last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT; + last_index = (*ppos + iter->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT; offset = *ppos & ~PAGE_CACHE_MASK; for (;;) { @@ -1148,7 +1488,7 @@ find_page: if (!page->mapping) goto page_not_up_to_date_locked; if (!mapping->a_ops->is_partially_uptodate(page, - desc, offset)) + offset, iter->count)) goto page_not_up_to_date_locked; unlock_page(page); } @@ -1198,24 +1538,23 @@ page_ok: /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... - * - * The file_read_actor routine returns how many bytes were - * actually used.. - * NOTE! This may not be the same as how much of a user buffer - * we filled up (we may be padding etc), so we can only update - * "pos" here (the actor routine has to update the user buffer - * pointers and the remaining count). */ - ret = file_read_actor(desc, page, offset, nr); + + ret = copy_page_to_iter(page, offset, nr, iter); offset += ret; index += offset >> PAGE_CACHE_SHIFT; offset &= ~PAGE_CACHE_MASK; prev_offset = offset; page_cache_release(page); - if (ret == nr && desc->count) - continue; - goto out; + written += ret; + if (!iov_iter_count(iter)) + goto out; + if (ret < nr) { + error = -EFAULT; + goto out; + } + continue; page_not_up_to_date: /* Get exclusive access to the page ... */ @@ -1250,6 +1589,7 @@ readpage: if (unlikely(error)) { if (error == AOP_TRUNCATED_PAGE) { page_cache_release(page); + error = 0; goto find_page; } goto readpage_error; @@ -1280,7 +1620,6 @@ readpage: readpage_error: /* UHHUH! A synchronous read error occurred. Report it */ - desc->error = error; page_cache_release(page); goto out; @@ -1291,16 +1630,17 @@ no_cached_page: */ page = page_cache_alloc_cold(mapping); if (!page) { - desc->error = -ENOMEM; + error = -ENOMEM; goto out; } error = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL); if (error) { page_cache_release(page); - if (error == -EEXIST) + if (error == -EEXIST) { + error = 0; goto find_page; - desc->error = error; + } goto out; } goto readpage; @@ -1313,44 +1653,7 @@ out: *ppos = ((loff_t)index << PAGE_CACHE_SHIFT) + offset; file_accessed(filp); -} - -int file_read_actor(read_descriptor_t *desc, struct page *page, - unsigned long offset, unsigned long size) -{ - char *kaddr; - unsigned long left, count = desc->count; - - if (size > count) - size = count; - - /* - * Faults on the destination of a read are common, so do it before - * taking the kmap. - */ - if (!fault_in_pages_writeable(desc->arg.buf, size)) { - kaddr = kmap_atomic(page); - left = __copy_to_user_inatomic(desc->arg.buf, - kaddr + offset, size); - kunmap_atomic(kaddr); - if (left == 0) - goto success; - } - - /* Do it the slow way */ - kaddr = kmap(page); - left = __copy_to_user(desc->arg.buf, kaddr + offset, size); - kunmap(page); - - if (left) { - size -= left; - desc->error = -EFAULT; - } -success: - desc->count = count - size; - desc->written += size; - desc->arg.buf += size; - return size; + return written ? written : error; } /* @@ -1408,14 +1711,15 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, { struct file *filp = iocb->ki_filp; ssize_t retval; - unsigned long seg = 0; size_t count; loff_t *ppos = &iocb->ki_pos; + struct iov_iter i; count = 0; retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); if (retval) return retval; + iov_iter_init(&i, iov, nr_segs, count, 0); /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (filp->f_flags & O_DIRECT) { @@ -1437,6 +1741,11 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, if (retval > 0) { *ppos = pos + retval; count -= retval; + /* + * If we did a short DIO read we need to skip the + * section of the iov that we've already read data into. + */ + iov_iter_advance(&i, retval); } /* @@ -1453,39 +1762,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, } } - count = retval; - for (seg = 0; seg < nr_segs; seg++) { - read_descriptor_t desc; - loff_t offset = 0; - - /* - * If we did a short DIO read we need to skip the section of the - * iov that we've already read data into. - */ - if (count) { - if (count > iov[seg].iov_len) { - count -= iov[seg].iov_len; - continue; - } - offset = count; - count = 0; - } - - desc.written = 0; - desc.arg.buf = iov[seg].iov_base + offset; - desc.count = iov[seg].iov_len - offset; - if (desc.count == 0) - continue; - desc.error = 0; - do_generic_file_read(filp, ppos, &desc); - retval += desc.written; - if (desc.error) { - retval = retval ?: desc.error; - break; - } - if (desc.count > 0) - break; - } + retval = do_generic_file_read(filp, ppos, &i, retval); out: return retval; } @@ -1614,11 +1891,11 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) struct inode *inode = mapping->host; pgoff_t offset = vmf->pgoff; struct page *page; - pgoff_t size; + loff_t size; int ret = 0; - size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - if (offset >= size) + size = round_up(i_size_read(inode), PAGE_CACHE_SIZE); + if (offset >= size >> PAGE_CACHE_SHIFT) return VM_FAULT_SIGBUS; /* @@ -1667,8 +1944,8 @@ retry_find: * Found the page and have a reference on it. * We must recheck i_size under page lock. */ - size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - if (unlikely(offset >= size)) { + size = round_up(i_size_read(inode), PAGE_CACHE_SIZE); + if (unlikely(offset >= size >> PAGE_CACHE_SHIFT)) { unlock_page(page); page_cache_release(page); return VM_FAULT_SIGBUS; @@ -1726,6 +2003,78 @@ page_not_uptodate: } EXPORT_SYMBOL(filemap_fault); +void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct radix_tree_iter iter; + void **slot; + struct file *file = vma->vm_file; + struct address_space *mapping = file->f_mapping; + loff_t size; + struct page *page; + unsigned long address = (unsigned long) vmf->virtual_address; + unsigned long addr; + pte_t *pte; + + rcu_read_lock(); + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, vmf->pgoff) { + if (iter.index > vmf->max_pgoff) + break; +repeat: + page = radix_tree_deref_slot(slot); + if (unlikely(!page)) + goto next; + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) + break; + else + goto next; + } + + if (!page_cache_get_speculative(page)) + goto repeat; + + /* Has the page moved? */ + if (unlikely(page != *slot)) { + page_cache_release(page); + goto repeat; + } + + if (!PageUptodate(page) || + PageReadahead(page) || + PageHWPoison(page)) + goto skip; + if (!trylock_page(page)) + goto skip; + + if (page->mapping != mapping || !PageUptodate(page)) + goto unlock; + + size = round_up(i_size_read(mapping->host), PAGE_CACHE_SIZE); + if (page->index >= size >> PAGE_CACHE_SHIFT) + goto unlock; + + pte = vmf->pte + page->index - vmf->pgoff; + if (!pte_none(*pte)) + goto unlock; + + if (file->f_ra.mmap_miss > 0) + file->f_ra.mmap_miss--; + addr = address + (page->index - vmf->pgoff) * PAGE_SIZE; + do_set_pte(vma, addr, page, pte, false, false); + unlock_page(page); + goto next; +unlock: + unlock_page(page); +skip: + page_cache_release(page); +next: + if (iter.index == vmf->max_pgoff) + break; + } + rcu_read_unlock(); +} +EXPORT_SYMBOL(filemap_map_pages); + int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { struct page *page = vmf->page; @@ -1755,6 +2104,7 @@ EXPORT_SYMBOL(filemap_page_mkwrite); const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, + .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, .remap_pages = generic_file_remap_pages, }; @@ -1795,6 +2145,18 @@ int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma) EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); +static struct page *wait_on_page_read(struct page *page) +{ + if (!IS_ERR(page)) { + wait_on_page_locked(page); + if (!PageUptodate(page)) { + page_cache_release(page); + page = ERR_PTR(-EIO); + } + } + return page; +} + static struct page *__read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), @@ -1821,6 +2183,8 @@ repeat: if (err < 0) { page_cache_release(page); page = ERR_PTR(err); + } else { + page = wait_on_page_read(page); } } return page; @@ -1857,6 +2221,10 @@ retry: if (err < 0) { page_cache_release(page); return ERR_PTR(err); + } else { + page = wait_on_page_read(page); + if (IS_ERR(page)) + return page; } out: mark_page_accessed(page); @@ -1864,40 +2232,25 @@ out: } /** - * read_cache_page_async - read into page cache, fill it if needed + * read_cache_page - read into page cache, fill it if needed * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read * @data: first arg to filler(data, page) function, often left as NULL * - * Same as read_cache_page, but don't wait for page to become unlocked - * after submitting it to the filler. - * * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page but don't wait for it to become unlocked. + * not set, try to fill the page and wait for it to become unlocked. * * If the page does not get brought uptodate, return -EIO. */ -struct page *read_cache_page_async(struct address_space *mapping, +struct page *read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); } -EXPORT_SYMBOL(read_cache_page_async); - -static struct page *wait_on_page_read(struct page *page) -{ - if (!IS_ERR(page)) { - wait_on_page_locked(page); - if (!PageUptodate(page)) { - page_cache_release(page); - page = ERR_PTR(-EIO); - } - } - return page; -} +EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. @@ -1916,175 +2269,10 @@ struct page *read_cache_page_gfp(struct address_space *mapping, { filler_t *filler = (filler_t *)mapping->a_ops->readpage; - return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp)); + return do_read_cache_page(mapping, index, filler, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); -/** - * read_cache_page - read into page cache, fill it if needed - * @mapping: the page's address_space - * @index: the page index - * @filler: function to perform the read - * @data: first arg to filler(data, page) function, often left as NULL - * - * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page then wait for it to become unlocked. - * - * If the page does not get brought uptodate, return -EIO. - */ -struct page *read_cache_page(struct address_space *mapping, - pgoff_t index, - int (*filler)(void *, struct page *), - void *data) -{ - return wait_on_page_read(read_cache_page_async(mapping, index, filler, data)); -} -EXPORT_SYMBOL(read_cache_page); - -static size_t __iovec_copy_from_user_inatomic(char *vaddr, - const struct iovec *iov, size_t base, size_t bytes) -{ - size_t copied = 0, left = 0; - - while (bytes) { - char __user *buf = iov->iov_base + base; - int copy = min(bytes, iov->iov_len - base); - - base = 0; - left = __copy_from_user_inatomic(vaddr, buf, copy); - copied += copy; - bytes -= copy; - vaddr += copy; - iov++; - - if (unlikely(left)) - break; - } - return copied - left; -} - -/* - * Copy as much as we can into the page and return the number of bytes which - * were successfully copied. If a fault is encountered then return the number of - * bytes which were copied. - */ -size_t iov_iter_copy_from_user_atomic(struct page *page, - struct iov_iter *i, unsigned long offset, size_t bytes) -{ - char *kaddr; - size_t copied; - - BUG_ON(!in_atomic()); - kaddr = kmap_atomic(page); - if (likely(i->nr_segs == 1)) { - int left; - char __user *buf = i->iov->iov_base + i->iov_offset; - left = __copy_from_user_inatomic(kaddr + offset, buf, bytes); - copied = bytes - left; - } else { - copied = __iovec_copy_from_user_inatomic(kaddr + offset, - i->iov, i->iov_offset, bytes); - } - kunmap_atomic(kaddr); - - return copied; -} -EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); - -/* - * This has the same sideeffects and return value as - * iov_iter_copy_from_user_atomic(). - * The difference is that it attempts to resolve faults. - * Page must not be locked. - */ -size_t iov_iter_copy_from_user(struct page *page, - struct iov_iter *i, unsigned long offset, size_t bytes) -{ - char *kaddr; - size_t copied; - - kaddr = kmap(page); - if (likely(i->nr_segs == 1)) { - int left; - char __user *buf = i->iov->iov_base + i->iov_offset; - left = __copy_from_user(kaddr + offset, buf, bytes); - copied = bytes - left; - } else { - copied = __iovec_copy_from_user_inatomic(kaddr + offset, - i->iov, i->iov_offset, bytes); - } - kunmap(page); - return copied; -} -EXPORT_SYMBOL(iov_iter_copy_from_user); - -void iov_iter_advance(struct iov_iter *i, size_t bytes) -{ - BUG_ON(i->count < bytes); - - if (likely(i->nr_segs == 1)) { - i->iov_offset += bytes; - i->count -= bytes; - } else { - const struct iovec *iov = i->iov; - size_t base = i->iov_offset; - unsigned long nr_segs = i->nr_segs; - - /* - * The !iov->iov_len check ensures we skip over unlikely - * zero-length segments (without overruning the iovec). - */ - while (bytes || unlikely(i->count && !iov->iov_len)) { - int copy; - - copy = min(bytes, iov->iov_len - base); - BUG_ON(!i->count || i->count < copy); - i->count -= copy; - bytes -= copy; - base += copy; - if (iov->iov_len == base) { - iov++; - nr_segs--; - base = 0; - } - } - i->iov = iov; - i->iov_offset = base; - i->nr_segs = nr_segs; - } -} -EXPORT_SYMBOL(iov_iter_advance); - -/* - * Fault in the first iovec of the given iov_iter, to a maximum length - * of bytes. Returns 0 on success, or non-zero if the memory could not be - * accessed (ie. because it is an invalid address). - * - * writev-intensive code may want this to prefault several iovecs -- that - * would be possible (callers must not rely on the fact that _only_ the - * first iovec will be faulted with the current implementation). - */ -int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) -{ - char __user *buf = i->iov->iov_base + i->iov_offset; - bytes = min(bytes, i->iov->iov_len - i->iov_offset); - return fault_in_pages_readable(buf, bytes); -} -EXPORT_SYMBOL(iov_iter_fault_in_readable); - -/* - * Return the count of just the current iov_iter segment. - */ -size_t iov_iter_single_seg_count(const struct iov_iter *i) -{ - const struct iovec *iov = i->iov; - if (i->nr_segs == 1) - return i->count; - else - return min(i->count, iov->iov_len - i->iov_offset); -} -EXPORT_SYMBOL(iov_iter_single_seg_count); - /* * Performs necessary checks before doing a write * @@ -2191,7 +2379,7 @@ EXPORT_SYMBOL(pagecache_write_end); ssize_t generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long *nr_segs, loff_t pos, loff_t *ppos, + unsigned long *nr_segs, loff_t pos, size_t count, size_t ocount) { struct file *file = iocb->ki_filp; @@ -2252,7 +2440,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, i_size_write(inode, pos); mark_inode_dirty(inode); } - *ppos = pos; + iocb->ki_pos = pos; } out: return written; @@ -2298,7 +2486,7 @@ found: } EXPORT_SYMBOL(grab_cache_page_write_begin); -static ssize_t generic_perform_write(struct file *file, +ssize_t generic_perform_write(struct file *file, struct iov_iter *i, loff_t pos) { struct address_space *mapping = file->f_mapping; @@ -2348,9 +2536,7 @@ again: if (mapping_writably_mapped(mapping)) flush_dcache_page(page); - pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); - pagefault_enable(); flush_dcache_page(page); mark_page_accessed(page); @@ -2388,27 +2574,7 @@ again: return written ? written : status; } - -ssize_t -generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos, loff_t *ppos, - size_t count, ssize_t written) -{ - struct file *file = iocb->ki_filp; - ssize_t status; - struct iov_iter i; - - iov_iter_init(&i, iov, nr_segs, count, written); - status = generic_perform_write(file, &i, pos); - - if (likely(status >= 0)) { - written += status; - *ppos = pos + status; - } - - return written ? written : status; -} -EXPORT_SYMBOL(generic_file_buffered_write); +EXPORT_SYMBOL(generic_perform_write); /** * __generic_file_aio_write - write data to a file @@ -2430,16 +2596,18 @@ EXPORT_SYMBOL(generic_file_buffered_write); * avoid syncing under i_mutex. */ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) + unsigned long nr_segs) { struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; size_t ocount; /* original count */ size_t count; /* after file limit checks */ struct inode *inode = mapping->host; - loff_t pos; - ssize_t written; + loff_t pos = iocb->ki_pos; + ssize_t written = 0; ssize_t err; + ssize_t status; + struct iov_iter from; ocount = 0; err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ); @@ -2447,12 +2615,9 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, return err; count = ocount; - pos = *ppos; /* We can write back this queue in page reclaim */ current->backing_dev_info = mapping->backing_dev_info; - written = 0; - err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); if (err) goto out; @@ -2468,45 +2633,47 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (err) goto out; + iov_iter_init(&from, iov, nr_segs, count, 0); + /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (unlikely(file->f_flags & O_DIRECT)) { loff_t endbyte; - ssize_t written_buffered; - written = generic_file_direct_write(iocb, iov, &nr_segs, pos, - ppos, count, ocount); + written = generic_file_direct_write(iocb, iov, &from.nr_segs, pos, + count, ocount); if (written < 0 || written == count) goto out; + iov_iter_advance(&from, written); + /* * direct-io write to a hole: fall through to buffered I/O * for completing the rest of the request. */ pos += written; count -= written; - written_buffered = generic_file_buffered_write(iocb, iov, - nr_segs, pos, ppos, count, - written); + + status = generic_perform_write(file, &from, pos); /* - * If generic_file_buffered_write() retuned a synchronous error + * If generic_perform_write() returned a synchronous error * then we want to return the number of bytes which were * direct-written, or the error code if that was zero. Note * that this differs from normal direct-io semantics, which * will return -EFOO even if some bytes were written. */ - if (written_buffered < 0) { - err = written_buffered; + if (unlikely(status < 0) && !written) { + err = status; goto out; } - + iocb->ki_pos = pos + status; /* * We need to ensure that the page cache pages are written to * disk and invalidated to preserve the expected O_DIRECT * semantics. */ - endbyte = pos + written_buffered - written - 1; + endbyte = pos + status - 1; err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte); if (err == 0) { - written = written_buffered; + written += status; invalidate_mapping_pages(mapping, pos >> PAGE_CACHE_SHIFT, endbyte >> PAGE_CACHE_SHIFT); @@ -2517,8 +2684,9 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, */ } } else { - written = generic_file_buffered_write(iocb, iov, nr_segs, - pos, ppos, count, written); + written = generic_perform_write(file, &from, pos); + if (likely(written >= 0)) + iocb->ki_pos = pos + written; } out: current->backing_dev_info = NULL; @@ -2547,14 +2715,14 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, BUG_ON(iocb->ki_pos != pos); mutex_lock(&inode->i_mutex); - ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); + ret = __generic_file_aio_write(iocb, iov, nr_segs); mutex_unlock(&inode->i_mutex); if (ret > 0) { ssize_t err; - err = generic_write_sync(file, pos, ret); - if (err < 0 && ret > 0) + err = generic_write_sync(file, iocb->ki_pos - ret, ret); + if (err < 0) ret = err; } return ret; diff --git a/mm/fremap.c b/mm/fremap.c index bbc4d66..34feba6 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -23,28 +23,44 @@ #include "internal.h" +static int mm_counter(struct page *page) +{ + return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES; +} + static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t pte = *ptep; + struct page *page; + swp_entry_t entry; if (pte_present(pte)) { - struct page *page; - flush_cache_page(vma, addr, pte_pfn(pte)); pte = ptep_clear_flush(vma, addr, ptep); page = vm_normal_page(vma, addr, pte); if (page) { if (pte_dirty(pte)) set_page_dirty(page); + update_hiwater_rss(mm); + dec_mm_counter(mm, mm_counter(page)); page_remove_rmap(page); page_cache_release(page); + } + } else { /* zap_pte() is not called when pte_none() */ + if (!pte_file(pte)) { update_hiwater_rss(mm); - dec_mm_counter(mm, MM_FILEPAGES); + entry = pte_to_swp_entry(pte); + if (non_swap_entry(entry)) { + if (is_migration_entry(entry)) { + page = migration_entry_to_page(entry); + dec_mm_counter(mm, mm_counter(page)); + } + } else { + free_swap_and_cache(entry); + dec_mm_counter(mm, MM_SWAPENTS); + } } - } else { - if (!pte_file(pte)) - free_swap_and_cache(pte_to_swp_entry(pte)); pte_clear_not_present_full(mm, addr, ptep, 0); } } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 82166bf..64635f5 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -827,7 +827,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } - if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) { + if (unlikely(mem_cgroup_charge_anon(page, mm, GFP_KERNEL))) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -941,81 +941,6 @@ unlock: spin_unlock(ptl); } -static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - pmd_t *pmd, pmd_t orig_pmd, unsigned long haddr) -{ - spinlock_t *ptl; - pgtable_t pgtable; - pmd_t _pmd; - struct page *page; - int i, ret = 0; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ - - page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); - if (!page) { - ret |= VM_FAULT_OOM; - goto out; - } - - if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) { - put_page(page); - ret |= VM_FAULT_OOM; - goto out; - } - - clear_user_highpage(page, address); - __SetPageUptodate(page); - - mmun_start = haddr; - mmun_end = haddr + HPAGE_PMD_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - - ptl = pmd_lock(mm, pmd); - if (unlikely(!pmd_same(*pmd, orig_pmd))) - goto out_free_page; - - pmdp_clear_flush(vma, haddr, pmd); - /* leave pmd empty until pte is filled */ - - pgtable = pgtable_trans_huge_withdraw(mm, pmd); - pmd_populate(mm, &_pmd, pgtable); - - for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { - pte_t *pte, entry; - if (haddr == (address & PAGE_MASK)) { - entry = mk_pte(page, vma->vm_page_prot); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); - page_add_new_anon_rmap(page, vma, haddr); - } else { - entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot); - entry = pte_mkspecial(entry); - } - pte = pte_offset_map(&_pmd, haddr); - VM_BUG_ON(!pte_none(*pte)); - set_pte_at(mm, haddr, pte, entry); - pte_unmap(pte); - } - smp_wmb(); /* make pte visible before pmd */ - pmd_populate(mm, pmd, pgtable); - spin_unlock(ptl); - put_huge_zero_page(); - inc_mm_counter(mm, MM_ANONPAGES); - - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - - ret |= VM_FAULT_WRITE; -out: - return ret; -out_free_page: - spin_unlock(ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - mem_cgroup_uncharge_page(page); - put_page(page); - goto out; -} - static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, @@ -1043,7 +968,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, __GFP_OTHER_NODE, vma, address, page_to_nid(page)); if (unlikely(!pages[i] || - mem_cgroup_newpage_charge(pages[i], mm, + mem_cgroup_charge_anon(pages[i], mm, GFP_KERNEL))) { if (pages[i]) put_page(pages[i]); @@ -1161,27 +1086,30 @@ alloc: if (unlikely(!new_page)) { if (!page) { - ret = do_huge_pmd_wp_zero_page_fallback(mm, vma, - address, pmd, orig_pmd, haddr); + split_huge_page_pmd(vma, address, pmd); + ret |= VM_FAULT_FALLBACK; } else { ret = do_huge_pmd_wp_page_fallback(mm, vma, address, pmd, orig_pmd, page, haddr); - if (ret & VM_FAULT_OOM) + if (ret & VM_FAULT_OOM) { split_huge_page(page); + ret |= VM_FAULT_FALLBACK; + } put_page(page); } count_vm_event(THP_FAULT_FALLBACK); goto out; } - if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { + if (unlikely(mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))) { put_page(new_page); if (page) { split_huge_page(page); put_page(page); - } + } else + split_huge_page_pmd(vma, address, pmd); + ret |= VM_FAULT_FALLBACK; count_vm_event(THP_FAULT_FALLBACK); - ret |= VM_FAULT_OOM; goto out; } @@ -1545,6 +1473,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, entry = pmd_mknonnuma(entry); entry = pmd_modify(entry, newprot); ret = HPAGE_PMD_NR; + set_pmd_at(mm, addr, pmd, entry); BUG_ON(pmd_write(entry)); } else { struct page *page = pmd_page(*pmd); @@ -1557,16 +1486,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, */ if (!is_huge_zero_page(page) && !pmd_numa(*pmd)) { - entry = *pmd; - entry = pmd_mknuma(entry); + pmdp_set_numa(mm, addr, pmd); ret = HPAGE_PMD_NR; } } - - /* Set PMD if cleared earlier */ - if (ret == HPAGE_PMD_NR) - set_pmd_at(mm, addr, pmd, entry); - spin_unlock(ptl); } @@ -1963,22 +1886,27 @@ out: return ret; } -#define VM_NO_THP (VM_SPECIAL|VM_MIXEDMAP|VM_HUGETLB|VM_SHARED|VM_MAYSHARE) +#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE) int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { - struct mm_struct *mm = vma->vm_mm; - switch (advice) { case MADV_HUGEPAGE: +#ifdef CONFIG_S390 + /* + * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390 + * can't handle this properly after s390_enable_sie, so we simply + * ignore the madvise to prevent qemu from causing a SIGSEGV. + */ + if (mm_has_pgste(vma->vm_mm)) + return 0; +#endif /* * Be somewhat over-protective like KSM for now! */ if (*vm_flags & (VM_HUGEPAGE | VM_NO_THP)) return -EINVAL; - if (mm->def_flags & VM_NOHUGEPAGE) - return -EINVAL; *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; /* @@ -2431,7 +2359,7 @@ static void collapse_huge_page(struct mm_struct *mm, if (!new_page) return; - if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) + if (unlikely(mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))) return; /* diff --git a/mm/hugetlb.c b/mm/hugetlb.c index c01cb9f..dd30f22 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -13,6 +13,7 @@ #include <linux/nodemask.h> #include <linux/pagemap.h> #include <linux/mempolicy.h> +#include <linux/compiler.h> #include <linux/cpuset.h> #include <linux/mutex.h> #include <linux/bootmem.h> @@ -22,6 +23,7 @@ #include <linux/swap.h> #include <linux/swapops.h> #include <linux/page-isolation.h> +#include <linux/jhash.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -53,6 +55,13 @@ static unsigned long __initdata default_hstate_size; */ DEFINE_SPINLOCK(hugetlb_lock); +/* + * Serializes faults on the same logical page. This is used to + * prevent spurious OOMs when the hugepage pool is fully utilized. + */ +static int num_fault_mutexes; +static struct mutex *htlb_fault_mutex_table ____cacheline_aligned_in_smp; + static inline void unlock_or_release_subpool(struct hugepage_subpool *spool) { bool free = (spool->count == 0) && (spool->used_hpages == 0); @@ -135,15 +144,8 @@ static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) * Region tracking -- allows tracking of reservations and instantiated pages * across the pages in a mapping. * - * The region data structures are protected by a combination of the mmap_sem - * and the hugetlb_instantiation_mutex. To access or modify a region the caller - * must either hold the mmap_sem for write, or the mmap_sem for read and - * the hugetlb_instantiation_mutex: - * - * down_write(&mm->mmap_sem); - * or - * down_read(&mm->mmap_sem); - * mutex_lock(&hugetlb_instantiation_mutex); + * The region data structures are embedded into a resv_map and + * protected by a resv_map's lock */ struct file_region { struct list_head link; @@ -151,10 +153,12 @@ struct file_region { long to; }; -static long region_add(struct list_head *head, long f, long t) +static long region_add(struct resv_map *resv, long f, long t) { + struct list_head *head = &resv->regions; struct file_region *rg, *nrg, *trg; + spin_lock(&resv->lock); /* Locate the region we are either in or before. */ list_for_each_entry(rg, head, link) if (f <= rg->to) @@ -184,14 +188,18 @@ static long region_add(struct list_head *head, long f, long t) } nrg->from = f; nrg->to = t; + spin_unlock(&resv->lock); return 0; } -static long region_chg(struct list_head *head, long f, long t) +static long region_chg(struct resv_map *resv, long f, long t) { - struct file_region *rg, *nrg; + struct list_head *head = &resv->regions; + struct file_region *rg, *nrg = NULL; long chg = 0; +retry: + spin_lock(&resv->lock); /* Locate the region we are before or in. */ list_for_each_entry(rg, head, link) if (f <= rg->to) @@ -201,15 +209,21 @@ static long region_chg(struct list_head *head, long f, long t) * Subtle, allocate a new region at the position but make it zero * size such that we can guarantee to record the reservation. */ if (&rg->link == head || t < rg->from) { - nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); - if (!nrg) - return -ENOMEM; - nrg->from = f; - nrg->to = f; - INIT_LIST_HEAD(&nrg->link); - list_add(&nrg->link, rg->link.prev); + if (!nrg) { + spin_unlock(&resv->lock); + nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); + if (!nrg) + return -ENOMEM; + + nrg->from = f; + nrg->to = f; + INIT_LIST_HEAD(&nrg->link); + goto retry; + } - return t - f; + list_add(&nrg->link, rg->link.prev); + chg = t - f; + goto out_nrg; } /* Round our left edge to the current segment if it encloses us. */ @@ -222,7 +236,7 @@ static long region_chg(struct list_head *head, long f, long t) if (&rg->link == head) break; if (rg->from > t) - return chg; + goto out; /* We overlap with this area, if it extends further than * us then we must extend ourselves. Account for its @@ -233,20 +247,30 @@ static long region_chg(struct list_head *head, long f, long t) } chg -= rg->to - rg->from; } + +out: + spin_unlock(&resv->lock); + /* We already know we raced and no longer need the new region */ + kfree(nrg); + return chg; +out_nrg: + spin_unlock(&resv->lock); return chg; } -static long region_truncate(struct list_head *head, long end) +static long region_truncate(struct resv_map *resv, long end) { + struct list_head *head = &resv->regions; struct file_region *rg, *trg; long chg = 0; + spin_lock(&resv->lock); /* Locate the region we are either in or before. */ list_for_each_entry(rg, head, link) if (end <= rg->to) break; if (&rg->link == head) - return 0; + goto out; /* If we are in the middle of a region then adjust it. */ if (end > rg->from) { @@ -263,14 +287,19 @@ static long region_truncate(struct list_head *head, long end) list_del(&rg->link); kfree(rg); } + +out: + spin_unlock(&resv->lock); return chg; } -static long region_count(struct list_head *head, long f, long t) +static long region_count(struct resv_map *resv, long f, long t) { + struct list_head *head = &resv->regions; struct file_region *rg; long chg = 0; + spin_lock(&resv->lock); /* Locate each segment we overlap with, and count that overlap. */ list_for_each_entry(rg, head, link) { long seg_from; @@ -286,6 +315,7 @@ static long region_count(struct list_head *head, long f, long t) chg += seg_to - seg_from; } + spin_unlock(&resv->lock); return chg; } @@ -376,39 +406,46 @@ static void set_vma_private_data(struct vm_area_struct *vma, vma->vm_private_data = (void *)value; } -struct resv_map { - struct kref refs; - struct list_head regions; -}; - -static struct resv_map *resv_map_alloc(void) +struct resv_map *resv_map_alloc(void) { struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL); if (!resv_map) return NULL; kref_init(&resv_map->refs); + spin_lock_init(&resv_map->lock); INIT_LIST_HEAD(&resv_map->regions); return resv_map; } -static void resv_map_release(struct kref *ref) +void resv_map_release(struct kref *ref) { struct resv_map *resv_map = container_of(ref, struct resv_map, refs); /* Clear out any active regions before we release the map. */ - region_truncate(&resv_map->regions, 0); + region_truncate(resv_map, 0); kfree(resv_map); } +static inline struct resv_map *inode_resv_map(struct inode *inode) +{ + return inode->i_mapping->private_data; +} + static struct resv_map *vma_resv_map(struct vm_area_struct *vma) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); - if (!(vma->vm_flags & VM_MAYSHARE)) + if (vma->vm_flags & VM_MAYSHARE) { + struct address_space *mapping = vma->vm_file->f_mapping; + struct inode *inode = mapping->host; + + return inode_resv_map(inode); + + } else { return (struct resv_map *)(get_vma_private_data(vma) & ~HPAGE_RESV_MASK); - return NULL; + } } static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) @@ -540,7 +577,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, goto err; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = huge_zonelist(vma, address, htlb_alloc_mask(h), &mpol, &nodemask); @@ -562,7 +599,7 @@ retry_cpuset: } mpol_cond_put(mpol); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; @@ -653,7 +690,8 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) put_page(page); /* free it into the hugepage allocator */ } -static void prep_compound_gigantic_page(struct page *page, unsigned long order) +static void __init prep_compound_gigantic_page(struct page *page, + unsigned long order) { int i; int nr_pages = 1 << order; @@ -1150,45 +1188,34 @@ static void return_unused_surplus_pages(struct hstate *h, static long vma_needs_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { - struct address_space *mapping = vma->vm_file->f_mapping; - struct inode *inode = mapping->host; - - if (vma->vm_flags & VM_MAYSHARE) { - pgoff_t idx = vma_hugecache_offset(h, vma, addr); - return region_chg(&inode->i_mapping->private_list, - idx, idx + 1); + struct resv_map *resv; + pgoff_t idx; + long chg; - } else if (!is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { + resv = vma_resv_map(vma); + if (!resv) return 1; - } else { - long err; - pgoff_t idx = vma_hugecache_offset(h, vma, addr); - struct resv_map *resv = vma_resv_map(vma); + idx = vma_hugecache_offset(h, vma, addr); + chg = region_chg(resv, idx, idx + 1); - err = region_chg(&resv->regions, idx, idx + 1); - if (err < 0) - return err; - return 0; - } + if (vma->vm_flags & VM_MAYSHARE) + return chg; + else + return chg < 0 ? chg : 0; } static void vma_commit_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { - struct address_space *mapping = vma->vm_file->f_mapping; - struct inode *inode = mapping->host; - - if (vma->vm_flags & VM_MAYSHARE) { - pgoff_t idx = vma_hugecache_offset(h, vma, addr); - region_add(&inode->i_mapping->private_list, idx, idx + 1); + struct resv_map *resv; + pgoff_t idx; - } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { - pgoff_t idx = vma_hugecache_offset(h, vma, addr); - struct resv_map *resv = vma_resv_map(vma); + resv = vma_resv_map(vma); + if (!resv) + return; - /* Mark this page used in the map. */ - region_add(&resv->regions, idx, idx + 1); - } + idx = vma_hugecache_offset(h, vma, addr); + region_add(resv, idx, idx + 1); } static struct page *alloc_huge_page(struct vm_area_struct *vma, @@ -1294,7 +1321,7 @@ found: return 1; } -static void prep_compound_huge_page(struct page *page, int order) +static void __init prep_compound_huge_page(struct page *page, int order) { if (unlikely(order > (MAX_ORDER - 1))) prep_compound_gigantic_page(page, order); @@ -1509,6 +1536,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count, while (min_count < persistent_huge_pages(h)) { if (!free_pool_huge_page(h, nodes_allowed, 0)) break; + cond_resched_lock(&hugetlb_lock); } while (count < persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, 1)) @@ -1944,11 +1972,14 @@ static void __exit hugetlb_exit(void) } kobject_put(hugepages_kobj); + kfree(htlb_fault_mutex_table); } module_exit(hugetlb_exit); static int __init hugetlb_init(void) { + int i; + /* Some platform decide whether they support huge pages at boot * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when * there is no such support @@ -1973,6 +2004,17 @@ static int __init hugetlb_init(void) hugetlb_register_all_nodes(); hugetlb_cgroup_file_init(); +#ifdef CONFIG_SMP + num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus()); +#else + num_fault_mutexes = 1; +#endif + htlb_fault_mutex_table = + kmalloc(sizeof(struct mutex) * num_fault_mutexes, GFP_KERNEL); + BUG_ON(!htlb_fault_mutex_table); + + for (i = 0; i < num_fault_mutexes; i++) + mutex_init(&htlb_fault_mutex_table[i]); return 0; } module_init(hugetlb_init); @@ -2251,41 +2293,30 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma) * after this open call completes. It is therefore safe to take a * new reference here without additional locking. */ - if (resv) + if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) kref_get(&resv->refs); } -static void resv_map_put(struct vm_area_struct *vma) -{ - struct resv_map *resv = vma_resv_map(vma); - - if (!resv) - return; - kref_put(&resv->refs, resv_map_release); -} - static void hugetlb_vm_op_close(struct vm_area_struct *vma) { struct hstate *h = hstate_vma(vma); struct resv_map *resv = vma_resv_map(vma); struct hugepage_subpool *spool = subpool_vma(vma); - unsigned long reserve; - unsigned long start; - unsigned long end; + unsigned long reserve, start, end; + + if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + return; - if (resv) { - start = vma_hugecache_offset(h, vma, vma->vm_start); - end = vma_hugecache_offset(h, vma, vma->vm_end); + start = vma_hugecache_offset(h, vma, vma->vm_start); + end = vma_hugecache_offset(h, vma, vma->vm_end); - reserve = (end - start) - - region_count(&resv->regions, start, end); + reserve = (end - start) - region_count(resv, start, end); - resv_map_put(vma); + kref_put(&resv->refs, resv_map_release); - if (reserve) { - hugetlb_acct_memory(h, -reserve); - hugepage_subpool_put_pages(spool, reserve); - } + if (reserve) { + hugetlb_acct_memory(h, -reserve); + hugepage_subpool_put_pages(spool, reserve); } } @@ -2661,7 +2692,8 @@ retry_avoidcopy: BUG_ON(huge_pte_none(pte)); spin_lock(ptl); ptep = huge_pte_offset(mm, address & huge_page_mask(h)); - if (likely(pte_same(huge_ptep_get(ptep), pte))) + if (likely(ptep && + pte_same(huge_ptep_get(ptep), pte))) goto retry_avoidcopy; /* * race occurs while re-acquiring page table @@ -2705,7 +2737,7 @@ retry_avoidcopy: */ spin_lock(ptl); ptep = huge_pte_offset(mm, address & huge_page_mask(h)); - if (likely(pte_same(huge_ptep_get(ptep), pte))) { + if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) { ClearPagePrivate(new_page); /* Break COW */ @@ -2761,15 +2793,14 @@ static bool hugetlbfs_pagecache_present(struct hstate *h, } static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *ptep, unsigned int flags) + struct address_space *mapping, pgoff_t idx, + unsigned long address, pte_t *ptep, unsigned int flags) { struct hstate *h = hstate_vma(vma); int ret = VM_FAULT_SIGBUS; int anon_rmap = 0; - pgoff_t idx; unsigned long size; struct page *page; - struct address_space *mapping; pte_t new_pte; spinlock_t *ptl; @@ -2784,9 +2815,6 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, return ret; } - mapping = vma->vm_file->f_mapping; - idx = vma_hugecache_offset(h, vma, address); - /* * Use page lock to guard against racing truncation * before we get page_table_lock. @@ -2871,8 +2899,7 @@ retry: if (anon_rmap) { ClearPagePrivate(page); hugepage_add_new_anon_rmap(page, vma, address); - } - else + } else page_dup_rmap(page); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); @@ -2896,17 +2923,53 @@ backout_unlocked: goto out; } +#ifdef CONFIG_SMP +static u32 fault_mutex_hash(struct hstate *h, struct mm_struct *mm, + struct vm_area_struct *vma, + struct address_space *mapping, + pgoff_t idx, unsigned long address) +{ + unsigned long key[2]; + u32 hash; + + if (vma->vm_flags & VM_SHARED) { + key[0] = (unsigned long) mapping; + key[1] = idx; + } else { + key[0] = (unsigned long) mm; + key[1] = address >> huge_page_shift(h); + } + + hash = jhash2((u32 *)&key, sizeof(key)/sizeof(u32), 0); + + return hash & (num_fault_mutexes - 1); +} +#else +/* + * For uniprocesor systems we always use a single mutex, so just + * return 0 and avoid the hashing overhead. + */ +static u32 fault_mutex_hash(struct hstate *h, struct mm_struct *mm, + struct vm_area_struct *vma, + struct address_space *mapping, + pgoff_t idx, unsigned long address) +{ + return 0; +} +#endif + int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { - pte_t *ptep; - pte_t entry; + pte_t *ptep, entry; spinlock_t *ptl; int ret; + u32 hash; + pgoff_t idx; struct page *page = NULL; struct page *pagecache_page = NULL; - static DEFINE_MUTEX(hugetlb_instantiation_mutex); struct hstate *h = hstate_vma(vma); + struct address_space *mapping; address &= huge_page_mask(h); @@ -2925,15 +2988,20 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (!ptep) return VM_FAULT_OOM; + mapping = vma->vm_file->f_mapping; + idx = vma_hugecache_offset(h, vma, address); + /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ - mutex_lock(&hugetlb_instantiation_mutex); + hash = fault_mutex_hash(h, mm, vma, mapping, idx, address); + mutex_lock(&htlb_fault_mutex_table[hash]); + entry = huge_ptep_get(ptep); if (huge_pte_none(entry)) { - ret = hugetlb_no_page(mm, vma, address, ptep, flags); + ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags); goto out_mutex; } @@ -3002,8 +3070,7 @@ out_ptl: put_page(page); out_mutex: - mutex_unlock(&hugetlb_instantiation_mutex); - + mutex_unlock(&htlb_fault_mutex_table[hash]); return ret; } @@ -3120,6 +3187,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, BUG_ON(address >= end); flush_cache_range(vma, address, end); + mmu_notifier_invalidate_range_start(mm, start, end); mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex); for (; address < end; address += huge_page_size(h)) { spinlock_t *ptl; @@ -3149,6 +3217,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, */ flush_tlb_range(vma, start, end); mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); + mmu_notifier_invalidate_range_end(mm, start, end); return pages << h->order; } @@ -3161,6 +3230,7 @@ int hugetlb_reserve_pages(struct inode *inode, long ret, chg; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); + struct resv_map *resv_map; /* * Only apply hugepage reservation if asked. At fault time, an @@ -3176,10 +3246,13 @@ int hugetlb_reserve_pages(struct inode *inode, * to reserve the full area even if read-only as mprotect() may be * called to make the mapping read-write. Assume !vma is a shm mapping */ - if (!vma || vma->vm_flags & VM_MAYSHARE) - chg = region_chg(&inode->i_mapping->private_list, from, to); - else { - struct resv_map *resv_map = resv_map_alloc(); + if (!vma || vma->vm_flags & VM_MAYSHARE) { + resv_map = inode_resv_map(inode); + + chg = region_chg(resv_map, from, to); + + } else { + resv_map = resv_map_alloc(); if (!resv_map) return -ENOMEM; @@ -3222,20 +3295,23 @@ int hugetlb_reserve_pages(struct inode *inode, * else has to be done for private mappings here */ if (!vma || vma->vm_flags & VM_MAYSHARE) - region_add(&inode->i_mapping->private_list, from, to); + region_add(resv_map, from, to); return 0; out_err: - if (vma) - resv_map_put(vma); + if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + kref_put(&resv_map->refs, resv_map_release); return ret; } void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) { struct hstate *h = hstate_inode(inode); - long chg = region_truncate(&inode->i_mapping->private_list, offset); + struct resv_map *resv_map = inode_resv_map(inode); + long chg = 0; struct hugepage_subpool *spool = subpool_inode(inode); + if (resv_map) + chg = region_truncate(resv_map, offset); spin_lock(&inode->i_lock); inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); @@ -3446,7 +3522,7 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address, #else /* !CONFIG_ARCH_WANT_GENERAL_HUGETLB */ /* Can be overriden by architectures */ -__attribute__((weak)) struct page * +struct page * __weak follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int write) { diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index cb00829..595d7fd 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -30,7 +30,6 @@ struct hugetlb_cgroup { #define MEMFILE_IDX(val) (((val) >> 16) & 0xffff) #define MEMFILE_ATTR(val) ((val) & 0xffff) -struct cgroup_subsys hugetlb_subsys __read_mostly; static struct hugetlb_cgroup *root_h_cgroup __read_mostly; static inline @@ -42,7 +41,7 @@ struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s) static inline struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task) { - return hugetlb_cgroup_from_css(task_css(task, hugetlb_subsys_id)); + return hugetlb_cgroup_from_css(task_css(task, hugetlb_cgrp_id)); } static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg) @@ -255,7 +254,7 @@ static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css, } static int hugetlb_cgroup_write(struct cgroup_subsys_state *css, - struct cftype *cft, const char *buffer) + struct cftype *cft, char *buffer) { int idx, name, ret; unsigned long long val; @@ -358,7 +357,7 @@ static void __init __hugetlb_cgroup_file_init(int idx) cft = &h->cgroup_files[4]; memset(cft, 0, sizeof(*cft)); - WARN_ON(cgroup_add_cftypes(&hugetlb_subsys, h->cgroup_files)); + WARN_ON(cgroup_add_cftypes(&hugetlb_cgrp_subsys, h->cgroup_files)); return; } @@ -402,10 +401,8 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage) return; } -struct cgroup_subsys hugetlb_subsys = { - .name = "hugetlb", +struct cgroup_subsys hugetlb_cgrp_subsys = { .css_alloc = hugetlb_cgroup_css_alloc, .css_offline = hugetlb_cgroup_css_offline, .css_free = hugetlb_cgroup_css_free, - .subsys_id = hugetlb_subsys_id, }; diff --git a/mm/internal.h b/mm/internal.h index 29e1e76..07b6736 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -11,6 +11,7 @@ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H +#include <linux/fs.h> #include <linux/mm.h> void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, @@ -21,6 +22,20 @@ static inline void set_page_count(struct page *page, int v) atomic_set(&page->_count, v); } +extern int __do_page_cache_readahead(struct address_space *mapping, + struct file *filp, pgoff_t offset, unsigned long nr_to_read, + unsigned long lookahead_size); + +/* + * Submit IO for the read-ahead request in file_ra_state. + */ +static inline unsigned long ra_submit(struct file_ra_state *ra, + struct address_space *mapping, struct file *filp) +{ + return __do_page_cache_readahead(mapping, filp, + ra->start, ra->size, ra->async_size); +} + /* * Turn a non-refcounted page (->_count == 0) into refcounted with * a count of one. @@ -370,5 +385,6 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, #define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ +#define ALLOC_FAIR 0x100 /* fair zone allocation */ #endif /* __MM_INTERNAL_H */ diff --git a/mm/iov_iter.c b/mm/iov_iter.c new file mode 100644 index 0000000..10e46cd --- /dev/null +++ b/mm/iov_iter.c @@ -0,0 +1,224 @@ +#include <linux/export.h> +#include <linux/uio.h> +#include <linux/pagemap.h> + +size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i) +{ + size_t skip, copy, left, wanted; + const struct iovec *iov; + char __user *buf; + void *kaddr, *from; + + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + wanted = bytes; + iov = i->iov; + skip = i->iov_offset; + buf = iov->iov_base + skip; + copy = min(bytes, iov->iov_len - skip); + + if (!fault_in_pages_writeable(buf, copy)) { + kaddr = kmap_atomic(page); + from = kaddr + offset; + + /* first chunk, usually the only one */ + left = __copy_to_user_inatomic(buf, from, copy); + copy -= left; + skip += copy; + from += copy; + bytes -= copy; + + while (unlikely(!left && bytes)) { + iov++; + buf = iov->iov_base; + copy = min(bytes, iov->iov_len); + left = __copy_to_user_inatomic(buf, from, copy); + copy -= left; + skip = copy; + from += copy; + bytes -= copy; + } + if (likely(!bytes)) { + kunmap_atomic(kaddr); + goto done; + } + offset = from - kaddr; + buf += copy; + kunmap_atomic(kaddr); + copy = min(bytes, iov->iov_len - skip); + } + /* Too bad - revert to non-atomic kmap */ + kaddr = kmap(page); + from = kaddr + offset; + left = __copy_to_user(buf, from, copy); + copy -= left; + skip += copy; + from += copy; + bytes -= copy; + while (unlikely(!left && bytes)) { + iov++; + buf = iov->iov_base; + copy = min(bytes, iov->iov_len); + left = __copy_to_user(buf, from, copy); + copy -= left; + skip = copy; + from += copy; + bytes -= copy; + } + kunmap(page); +done: + i->count -= wanted - bytes; + i->nr_segs -= iov - i->iov; + i->iov = iov; + i->iov_offset = skip; + return wanted - bytes; +} +EXPORT_SYMBOL(copy_page_to_iter); + +static size_t __iovec_copy_from_user_inatomic(char *vaddr, + const struct iovec *iov, size_t base, size_t bytes) +{ + size_t copied = 0, left = 0; + + while (bytes) { + char __user *buf = iov->iov_base + base; + int copy = min(bytes, iov->iov_len - base); + + base = 0; + left = __copy_from_user_inatomic(vaddr, buf, copy); + copied += copy; + bytes -= copy; + vaddr += copy; + iov++; + + if (unlikely(left)) + break; + } + return copied - left; +} + +/* + * Copy as much as we can into the page and return the number of bytes which + * were successfully copied. If a fault is encountered then return the number of + * bytes which were copied. + */ +size_t iov_iter_copy_from_user_atomic(struct page *page, + struct iov_iter *i, unsigned long offset, size_t bytes) +{ + char *kaddr; + size_t copied; + + kaddr = kmap_atomic(page); + if (likely(i->nr_segs == 1)) { + int left; + char __user *buf = i->iov->iov_base + i->iov_offset; + left = __copy_from_user_inatomic(kaddr + offset, buf, bytes); + copied = bytes - left; + } else { + copied = __iovec_copy_from_user_inatomic(kaddr + offset, + i->iov, i->iov_offset, bytes); + } + kunmap_atomic(kaddr); + + return copied; +} +EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); + +/* + * This has the same sideeffects and return value as + * iov_iter_copy_from_user_atomic(). + * The difference is that it attempts to resolve faults. + * Page must not be locked. + */ +size_t iov_iter_copy_from_user(struct page *page, + struct iov_iter *i, unsigned long offset, size_t bytes) +{ + char *kaddr; + size_t copied; + + kaddr = kmap(page); + if (likely(i->nr_segs == 1)) { + int left; + char __user *buf = i->iov->iov_base + i->iov_offset; + left = __copy_from_user(kaddr + offset, buf, bytes); + copied = bytes - left; + } else { + copied = __iovec_copy_from_user_inatomic(kaddr + offset, + i->iov, i->iov_offset, bytes); + } + kunmap(page); + return copied; +} +EXPORT_SYMBOL(iov_iter_copy_from_user); + +void iov_iter_advance(struct iov_iter *i, size_t bytes) +{ + BUG_ON(i->count < bytes); + + if (likely(i->nr_segs == 1)) { + i->iov_offset += bytes; + i->count -= bytes; + } else { + const struct iovec *iov = i->iov; + size_t base = i->iov_offset; + unsigned long nr_segs = i->nr_segs; + + /* + * The !iov->iov_len check ensures we skip over unlikely + * zero-length segments (without overruning the iovec). + */ + while (bytes || unlikely(i->count && !iov->iov_len)) { + int copy; + + copy = min(bytes, iov->iov_len - base); + BUG_ON(!i->count || i->count < copy); + i->count -= copy; + bytes -= copy; + base += copy; + if (iov->iov_len == base) { + iov++; + nr_segs--; + base = 0; + } + } + i->iov = iov; + i->iov_offset = base; + i->nr_segs = nr_segs; + } +} +EXPORT_SYMBOL(iov_iter_advance); + +/* + * Fault in the first iovec of the given iov_iter, to a maximum length + * of bytes. Returns 0 on success, or non-zero if the memory could not be + * accessed (ie. because it is an invalid address). + * + * writev-intensive code may want this to prefault several iovecs -- that + * would be possible (callers must not rely on the fact that _only_ the + * first iovec will be faulted with the current implementation). + */ +int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) +{ + char __user *buf = i->iov->iov_base + i->iov_offset; + bytes = min(bytes, i->iov->iov_len - i->iov_offset); + return fault_in_pages_readable(buf, bytes); +} +EXPORT_SYMBOL(iov_iter_fault_in_readable); + +/* + * Return the count of just the current iov_iter segment. + */ +size_t iov_iter_single_seg_count(const struct iov_iter *i) +{ + const struct iovec *iov = i->iov; + if (i->nr_segs == 1) + return i->count; + else + return min(i->count, iov->iov_len - i->iov_offset); +} +EXPORT_SYMBOL(iov_iter_single_seg_count); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 31f01c5..91d67ea 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -192,15 +192,15 @@ static struct kmem_cache *object_cache; static struct kmem_cache *scan_area_cache; /* set if tracing memory operations is enabled */ -static atomic_t kmemleak_enabled = ATOMIC_INIT(0); +static int kmemleak_enabled; /* set in the late_initcall if there were no errors */ -static atomic_t kmemleak_initialized = ATOMIC_INIT(0); +static int kmemleak_initialized; /* enables or disables early logging of the memory operations */ -static atomic_t kmemleak_early_log = ATOMIC_INIT(1); +static int kmemleak_early_log = 1; /* set if a kmemleak warning was issued */ -static atomic_t kmemleak_warning = ATOMIC_INIT(0); +static int kmemleak_warning; /* set if a fatal kmemleak error has occurred */ -static atomic_t kmemleak_error = ATOMIC_INIT(0); +static int kmemleak_error; /* minimum and maximum address that may be valid pointers */ static unsigned long min_addr = ULONG_MAX; @@ -218,7 +218,8 @@ static int kmemleak_stack_scan = 1; static DEFINE_MUTEX(scan_mutex); /* setting kmemleak=on, will set this var, skipping the disable */ static int kmemleak_skip_disable; - +/* If there are leaks that can be reported */ +static bool kmemleak_found_leaks; /* * Early object allocation/freeing logging. Kmemleak is initialized after the @@ -267,7 +268,7 @@ static void kmemleak_disable(void); #define kmemleak_warn(x...) do { \ pr_warning(x); \ dump_stack(); \ - atomic_set(&kmemleak_warning, 1); \ + kmemleak_warning = 1; \ } while (0) /* @@ -805,7 +806,7 @@ static void __init log_early(int op_type, const void *ptr, size_t size, unsigned long flags; struct early_log *log; - if (atomic_read(&kmemleak_error)) { + if (kmemleak_error) { /* kmemleak stopped recording, just count the requests */ crt_early_log++; return; @@ -840,7 +841,7 @@ static void early_alloc(struct early_log *log) unsigned long flags; int i; - if (!atomic_read(&kmemleak_enabled) || !log->ptr || IS_ERR(log->ptr)) + if (!kmemleak_enabled || !log->ptr || IS_ERR(log->ptr)) return; /* @@ -893,9 +894,9 @@ void __ref kmemleak_alloc(const void *ptr, size_t size, int min_count, { pr_debug("%s(0x%p, %zu, %d)\n", __func__, ptr, size, min_count); - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) create_object((unsigned long)ptr, size, min_count, gfp); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_ALLOC, ptr, size, min_count); } EXPORT_SYMBOL_GPL(kmemleak_alloc); @@ -919,11 +920,11 @@ void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size) * Percpu allocations are only scanned and not reported as leaks * (min_count is set to 0). */ - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) for_each_possible_cpu(cpu) create_object((unsigned long)per_cpu_ptr(ptr, cpu), size, 0, GFP_KERNEL); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_ALLOC_PERCPU, ptr, size, 0); } EXPORT_SYMBOL_GPL(kmemleak_alloc_percpu); @@ -939,9 +940,9 @@ void __ref kmemleak_free(const void *ptr) { pr_debug("%s(0x%p)\n", __func__, ptr); - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) delete_object_full((unsigned long)ptr); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_FREE, ptr, 0, 0); } EXPORT_SYMBOL_GPL(kmemleak_free); @@ -959,9 +960,9 @@ void __ref kmemleak_free_part(const void *ptr, size_t size) { pr_debug("%s(0x%p)\n", __func__, ptr); - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) delete_object_part((unsigned long)ptr, size); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_FREE_PART, ptr, size, 0); } EXPORT_SYMBOL_GPL(kmemleak_free_part); @@ -979,11 +980,11 @@ void __ref kmemleak_free_percpu(const void __percpu *ptr) pr_debug("%s(0x%p)\n", __func__, ptr); - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) for_each_possible_cpu(cpu) delete_object_full((unsigned long)per_cpu_ptr(ptr, cpu)); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_FREE_PERCPU, ptr, 0, 0); } EXPORT_SYMBOL_GPL(kmemleak_free_percpu); @@ -999,9 +1000,9 @@ void __ref kmemleak_not_leak(const void *ptr) { pr_debug("%s(0x%p)\n", __func__, ptr); - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) make_gray_object((unsigned long)ptr); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_NOT_LEAK, ptr, 0, 0); } EXPORT_SYMBOL(kmemleak_not_leak); @@ -1019,9 +1020,9 @@ void __ref kmemleak_ignore(const void *ptr) { pr_debug("%s(0x%p)\n", __func__, ptr); - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) make_black_object((unsigned long)ptr); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_IGNORE, ptr, 0, 0); } EXPORT_SYMBOL(kmemleak_ignore); @@ -1041,9 +1042,9 @@ void __ref kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) { pr_debug("%s(0x%p)\n", __func__, ptr); - if (atomic_read(&kmemleak_enabled) && ptr && size && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && size && !IS_ERR(ptr)) add_scan_area((unsigned long)ptr, size, gfp); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_SCAN_AREA, ptr, size, 0); } EXPORT_SYMBOL(kmemleak_scan_area); @@ -1061,9 +1062,9 @@ void __ref kmemleak_no_scan(const void *ptr) { pr_debug("%s(0x%p)\n", __func__, ptr); - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) object_no_scan((unsigned long)ptr); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_NO_SCAN, ptr, 0, 0); } EXPORT_SYMBOL(kmemleak_no_scan); @@ -1088,7 +1089,7 @@ static bool update_checksum(struct kmemleak_object *object) */ static int scan_should_stop(void) { - if (!atomic_read(&kmemleak_enabled)) + if (!kmemleak_enabled) return 1; /* @@ -1382,9 +1383,12 @@ static void kmemleak_scan(void) } rcu_read_unlock(); - if (new_leaks) + if (new_leaks) { + kmemleak_found_leaks = true; + pr_info("%d new suspected memory leaks (see " "/sys/kernel/debug/kmemleak)\n", new_leaks); + } } @@ -1545,11 +1549,6 @@ static int kmemleak_open(struct inode *inode, struct file *file) return seq_open(file, &kmemleak_seq_ops); } -static int kmemleak_release(struct inode *inode, struct file *file) -{ - return seq_release(inode, file); -} - static int dump_str_object_info(const char *str) { unsigned long flags; @@ -1592,8 +1591,12 @@ static void kmemleak_clear(void) spin_unlock_irqrestore(&object->lock, flags); } rcu_read_unlock(); + + kmemleak_found_leaks = false; } +static void __kmemleak_do_cleanup(void); + /* * File write operation to configure kmemleak at run-time. The following * commands can be written to the /sys/kernel/debug/kmemleak file: @@ -1606,7 +1609,8 @@ static void kmemleak_clear(void) * disable it) * scan - trigger a memory scan * clear - mark all current reported unreferenced kmemleak objects as - * grey to ignore printing them + * grey to ignore printing them, or free all kmemleak objects + * if kmemleak has been disabled. * dump=... - dump information about the object found at the given address */ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, @@ -1616,9 +1620,6 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, int buf_size; int ret; - if (!atomic_read(&kmemleak_enabled)) - return -EBUSY; - buf_size = min(size, (sizeof(buf) - 1)); if (strncpy_from_user(buf, user_buf, buf_size) < 0) return -EFAULT; @@ -1628,6 +1629,19 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, if (ret < 0) return ret; + if (strncmp(buf, "clear", 5) == 0) { + if (kmemleak_enabled) + kmemleak_clear(); + else + __kmemleak_do_cleanup(); + goto out; + } + + if (!kmemleak_enabled) { + ret = -EBUSY; + goto out; + } + if (strncmp(buf, "off", 3) == 0) kmemleak_disable(); else if (strncmp(buf, "stack=on", 8) == 0) @@ -1651,8 +1665,6 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, } } else if (strncmp(buf, "scan", 4) == 0) kmemleak_scan(); - else if (strncmp(buf, "clear", 5) == 0) - kmemleak_clear(); else if (strncmp(buf, "dump=", 5) == 0) ret = dump_str_object_info(buf + 5); else @@ -1674,9 +1686,19 @@ static const struct file_operations kmemleak_fops = { .read = seq_read, .write = kmemleak_write, .llseek = seq_lseek, - .release = kmemleak_release, + .release = seq_release, }; +static void __kmemleak_do_cleanup(void) +{ + struct kmemleak_object *object; + + rcu_read_lock(); + list_for_each_entry_rcu(object, &object_list, object_list) + delete_object_full(object->pointer); + rcu_read_unlock(); +} + /* * Stop the memory scanning thread and free the kmemleak internal objects if * no previous scan thread (otherwise, kmemleak may still have some useful @@ -1684,18 +1706,14 @@ static const struct file_operations kmemleak_fops = { */ static void kmemleak_do_cleanup(struct work_struct *work) { - struct kmemleak_object *object; - bool cleanup = scan_thread == NULL; - mutex_lock(&scan_mutex); stop_scan_thread(); - if (cleanup) { - rcu_read_lock(); - list_for_each_entry_rcu(object, &object_list, object_list) - delete_object_full(object->pointer); - rcu_read_unlock(); - } + if (!kmemleak_found_leaks) + __kmemleak_do_cleanup(); + else + pr_info("Kmemleak disabled without freeing internal data. " + "Reclaim the memory with \"echo clear > /sys/kernel/debug/kmemleak\"\n"); mutex_unlock(&scan_mutex); } @@ -1708,14 +1726,14 @@ static DECLARE_WORK(cleanup_work, kmemleak_do_cleanup); static void kmemleak_disable(void) { /* atomically check whether it was already invoked */ - if (atomic_cmpxchg(&kmemleak_error, 0, 1)) + if (cmpxchg(&kmemleak_error, 0, 1)) return; /* stop any memory operation tracing */ - atomic_set(&kmemleak_enabled, 0); + kmemleak_enabled = 0; /* check whether it is too early for a kernel thread */ - if (atomic_read(&kmemleak_initialized)) + if (kmemleak_initialized) schedule_work(&cleanup_work); pr_info("Kernel memory leak detector disabled\n"); @@ -1757,9 +1775,10 @@ void __init kmemleak_init(void) int i; unsigned long flags; + kmemleak_early_log = 0; + #ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF if (!kmemleak_skip_disable) { - atomic_set(&kmemleak_early_log, 0); kmemleak_disable(); return; } @@ -1777,12 +1796,11 @@ void __init kmemleak_init(void) /* the kernel is still in UP mode, so disabling the IRQs is enough */ local_irq_save(flags); - atomic_set(&kmemleak_early_log, 0); - if (atomic_read(&kmemleak_error)) { + if (kmemleak_error) { local_irq_restore(flags); return; } else - atomic_set(&kmemleak_enabled, 1); + kmemleak_enabled = 1; local_irq_restore(flags); /* @@ -1826,9 +1844,9 @@ void __init kmemleak_init(void) log->op_type); } - if (atomic_read(&kmemleak_warning)) { + if (kmemleak_warning) { print_log_trace(log); - atomic_set(&kmemleak_warning, 0); + kmemleak_warning = 0; } } } @@ -1840,9 +1858,9 @@ static int __init kmemleak_late_init(void) { struct dentry *dentry; - atomic_set(&kmemleak_initialized, 1); + kmemleak_initialized = 1; - if (atomic_read(&kmemleak_error)) { + if (kmemleak_error) { /* * Some error occurred and kmemleak was disabled. There is a * small chance that kmemleak_disable() was called immediately @@ -444,7 +444,7 @@ static void break_cow(struct rmap_item *rmap_item) static struct page *page_trans_compound_anon(struct page *page) { if (PageTransCompound(page)) { - struct page *head = compound_trans_head(page); + struct page *head = compound_head(page); /* * head may actually be splitted and freed from under * us but it's ok here. diff --git a/mm/list_lru.c b/mm/list_lru.c index 72f9dec..f1a0db1 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -87,11 +87,20 @@ restart: ret = isolate(item, &nlru->lock, cb_arg); switch (ret) { + case LRU_REMOVED_RETRY: + assert_spin_locked(&nlru->lock); case LRU_REMOVED: if (--nlru->nr_items == 0) node_clear(nid, lru->active_nodes); WARN_ON_ONCE(nlru->nr_items < 0); isolated++; + /* + * If the lru lock has been dropped, our list + * traversal is now invalid and so we have to + * restart from scratch. + */ + if (ret == LRU_REMOVED_RETRY) + goto restart; break; case LRU_ROTATE: list_move_tail(item, &nlru->list); @@ -103,6 +112,7 @@ restart: * The lru lock has been dropped, our list traversal is * now invalid and so we have to restart from scratch. */ + assert_spin_locked(&nlru->lock); goto restart; default: BUG(); @@ -114,7 +124,7 @@ restart: } EXPORT_SYMBOL_GPL(list_lru_walk_node); -int list_lru_init(struct list_lru *lru) +int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key) { int i; size_t size = sizeof(*lru->node) * nr_node_ids; @@ -126,12 +136,14 @@ int list_lru_init(struct list_lru *lru) nodes_clear(lru->active_nodes); for (i = 0; i < nr_node_ids; i++) { spin_lock_init(&lru->node[i].lock); + if (key) + lockdep_set_class(&lru->node[i].lock, key); INIT_LIST_HEAD(&lru->node[i].list); lru->node[i].nr_items = 0; } return 0; } -EXPORT_SYMBOL_GPL(list_lru_init); +EXPORT_SYMBOL_GPL(list_lru_init_key); void list_lru_destroy(struct list_lru *lru) { diff --git a/mm/memblock.c b/mm/memblock.c index 39a31e7..e9d6ca9 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1253,7 +1253,7 @@ phys_addr_t __init memblock_mem_size(unsigned long limit_pfn) pages += end_pfn - start_pfn; } - return (phys_addr_t)pages << PAGE_SHIFT; + return PFN_PHYS(pages); } /* lowest address */ @@ -1271,16 +1271,14 @@ phys_addr_t __init_memblock memblock_end_of_DRAM(void) void __init memblock_enforce_memory_limit(phys_addr_t limit) { - unsigned long i; phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX; + struct memblock_region *r; if (!limit) return; /* find out max address */ - for (i = 0; i < memblock.memory.cnt; i++) { - struct memblock_region *r = &memblock.memory.regions[i]; - + for_each_memblock(memory, r) { if (limit <= r->size) { max_addr = r->base + limit; break; @@ -1326,7 +1324,7 @@ int __init_memblock memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn) { struct memblock_type *type = &memblock.memory; - int mid = memblock_search(type, (phys_addr_t)pfn << PAGE_SHIFT); + int mid = memblock_search(type, PFN_PHYS(pfn)); if (mid == -1) return -1; @@ -1379,13 +1377,12 @@ int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t si void __init_memblock memblock_trim_memory(phys_addr_t align) { - int i; phys_addr_t start, end, orig_start, orig_end; - struct memblock_type *mem = &memblock.memory; + struct memblock_region *r; - for (i = 0; i < mem->cnt; i++) { - orig_start = mem->regions[i].base; - orig_end = mem->regions[i].base + mem->regions[i].size; + for_each_memblock(memory, r) { + orig_start = r->base; + orig_end = r->base + r->size; start = round_up(orig_start, align); end = round_down(orig_end, align); @@ -1393,11 +1390,12 @@ void __init_memblock memblock_trim_memory(phys_addr_t align) continue; if (start < end) { - mem->regions[i].base = start; - mem->regions[i].size = end - start; + r->base = start; + r->size = end - start; } else { - memblock_remove_region(mem, i); - i--; + memblock_remove_region(&memblock.memory, + r - memblock.memory.regions); + r--; } } } @@ -1407,6 +1405,11 @@ void __init_memblock memblock_set_current_limit(phys_addr_t limit) memblock.current_limit = limit; } +phys_addr_t __init_memblock memblock_get_current_limit(void) +{ + return memblock.current_limit; +} + static void __init_memblock memblock_dump(struct memblock_type *type, char *name) { unsigned long long base, size; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 53385cd..29501f0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -66,8 +66,8 @@ #include <trace/events/vmscan.h> -struct cgroup_subsys mem_cgroup_subsys __read_mostly; -EXPORT_SYMBOL(mem_cgroup_subsys); +struct cgroup_subsys memory_cgrp_subsys __read_mostly; +EXPORT_SYMBOL(memory_cgrp_subsys); #define MEM_CGROUP_RECLAIM_RETRIES 5 static struct mem_cgroup *root_mem_cgroup __read_mostly; @@ -538,7 +538,7 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) { struct cgroup_subsys_state *css; - css = css_from_id(id - 1, &mem_cgroup_subsys); + css = css_from_id(id - 1, &memory_cgrp_subsys); return mem_cgroup_from_css(css); } @@ -921,8 +921,6 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, struct page *page, bool anon, int nr_pages) { - preempt_disable(); - /* * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is * counted as CACHE even if it's on ANON LRU. @@ -947,8 +945,6 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, } __this_cpu_add(memcg->stat->nr_page_events, nr_pages); - - preempt_enable(); } unsigned long @@ -1072,25 +1068,18 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) if (unlikely(!p)) return NULL; - return mem_cgroup_from_css(task_css(p, mem_cgroup_subsys_id)); + return mem_cgroup_from_css(task_css(p, memory_cgrp_id)); } -struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) +static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { struct mem_cgroup *memcg = NULL; - if (!mm) - return NULL; - /* - * Because we have no locks, mm->owner's may be being moved to other - * cgroup. We use css_tryget() here even if this looks - * pessimistic (rather than adding locks here). - */ rcu_read_lock(); do { memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (unlikely(!memcg)) - break; + memcg = root_mem_cgroup; } while (!css_tryget(&memcg->css)); rcu_read_unlock(); return memcg; @@ -1127,8 +1116,8 @@ skip_node: * skipping css reference should be safe. */ if (next_css) { - if ((next_css->flags & CSS_ONLINE) && - (next_css == &root->css || css_tryget(next_css))) + if ((next_css == &root->css) || + ((next_css->flags & CSS_ONLINE) && css_tryget(next_css))) return mem_cgroup_from_css(next_css); prev_css = next_css; @@ -1486,7 +1475,7 @@ bool task_in_mem_cgroup(struct task_struct *task, p = find_lock_task_mm(task); if (p) { - curr = try_get_mem_cgroup_from_mm(p->mm); + curr = get_mem_cgroup_from_mm(p->mm); task_unlock(p); } else { /* @@ -1500,8 +1489,6 @@ bool task_in_mem_cgroup(struct task_struct *task, css_get(&curr->css); rcu_read_unlock(); } - if (!curr) - return false; /* * We should check use_hierarchy of "memcg" not "curr". Because checking * use_hierarchy of "curr" here make this function true if hierarchy is @@ -1683,54 +1670,25 @@ static void move_unlock_mem_cgroup(struct mem_cgroup *memcg, */ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { - /* - * protects memcg_name and makes sure that parallel ooms do not - * interleave - */ - static DEFINE_SPINLOCK(oom_info_lock); - struct cgroup *task_cgrp; - struct cgroup *mem_cgrp; - static char memcg_name[PATH_MAX]; - int ret; + /* oom_info_lock ensures that parallel ooms do not interleave */ + static DEFINE_MUTEX(oom_info_lock); struct mem_cgroup *iter; unsigned int i; if (!p) return; - spin_lock(&oom_info_lock); + mutex_lock(&oom_info_lock); rcu_read_lock(); - mem_cgrp = memcg->css.cgroup; - task_cgrp = task_cgroup(p, mem_cgroup_subsys_id); + pr_info("Task in "); + pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id)); + pr_info(" killed as a result of limit of "); + pr_cont_cgroup_path(memcg->css.cgroup); + pr_info("\n"); - ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX); - if (ret < 0) { - /* - * Unfortunately, we are unable to convert to a useful name - * But we'll still print out the usage information - */ - rcu_read_unlock(); - goto done; - } - rcu_read_unlock(); - - pr_info("Task in %s killed", memcg_name); - - rcu_read_lock(); - ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX); - if (ret < 0) { - rcu_read_unlock(); - goto done; - } rcu_read_unlock(); - /* - * Continues from above, so we don't need an KERN_ level - */ - pr_cont(" as a result of limit of %s\n", memcg_name); -done: - pr_info("memory: usage %llukB, limit %llukB, failcnt %llu\n", res_counter_read_u64(&memcg->res, RES_USAGE) >> 10, res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10, @@ -1745,13 +1703,8 @@ done: res_counter_read_u64(&memcg->kmem, RES_FAILCNT)); for_each_mem_cgroup_tree(iter, memcg) { - pr_info("Memory cgroup stats"); - - rcu_read_lock(); - ret = cgroup_path(iter->css.cgroup, memcg_name, PATH_MAX); - if (!ret) - pr_cont(" for %s", memcg_name); - rcu_read_unlock(); + pr_info("Memory cgroup stats for "); + pr_cont_cgroup_path(iter->css.cgroup); pr_cont(":"); for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { @@ -1767,7 +1720,7 @@ done: pr_cont("\n"); } - spin_unlock(&oom_info_lock); + mutex_unlock(&oom_info_lock); } /* @@ -2622,7 +2575,7 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb, } -/* See __mem_cgroup_try_charge() for details */ +/* See mem_cgroup_try_charge() for details */ enum { CHARGE_OK, /* success */ CHARGE_RETRY, /* need to retry but retry is not bad */ @@ -2695,45 +2648,34 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, return CHARGE_NOMEM; } -/* - * __mem_cgroup_try_charge() does - * 1. detect memcg to be charged against from passed *mm and *ptr, - * 2. update res_counter - * 3. call memory reclaim if necessary. - * - * In some special case, if the task is fatal, fatal_signal_pending() or - * has TIF_MEMDIE, this function returns -EINTR while writing root_mem_cgroup - * to *ptr. There are two reasons for this. 1: fatal threads should quit as soon - * as possible without any hazards. 2: all pages should have a valid - * pc->mem_cgroup. If mm is NULL and the caller doesn't pass a valid memcg - * pointer, that is treated as a charge to root_mem_cgroup. - * - * So __mem_cgroup_try_charge() will return - * 0 ... on success, filling *ptr with a valid memcg pointer. - * -ENOMEM ... charge failure because of resource limits. - * -EINTR ... if thread is fatal. *ptr is filled with root_mem_cgroup. +/** + * mem_cgroup_try_charge - try charging a memcg + * @memcg: memcg to charge + * @nr_pages: number of pages to charge + * @oom: trigger OOM if reclaim fails * - * Unlike the exported interface, an "oom" parameter is added. if oom==true, - * the oom-killer can be invoked. + * Returns 0 if @memcg was charged successfully, -EINTR if the charge + * was bypassed to root_mem_cgroup, and -ENOMEM if the charge failed. */ -static int __mem_cgroup_try_charge(struct mm_struct *mm, - gfp_t gfp_mask, - unsigned int nr_pages, - struct mem_cgroup **ptr, - bool oom) +static int mem_cgroup_try_charge(struct mem_cgroup *memcg, + gfp_t gfp_mask, + unsigned int nr_pages, + bool oom) { unsigned int batch = max(CHARGE_BATCH, nr_pages); int nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES; - struct mem_cgroup *memcg = NULL; int ret; + if (mem_cgroup_is_root(memcg)) + goto done; /* - * Unlike gloval-vm's OOM-kill, we're not in memory shortage - * in system level. So, allow to go ahead dying process in addition to - * MEMDIE process. + * Unlike in global OOM situations, memcg is not in a physical + * memory shortage. Allow dying and OOM-killed tasks to + * bypass the last charges so that they can exit quickly and + * free their memory. */ - if (unlikely(test_thread_flag(TIF_MEMDIE) - || fatal_signal_pending(current))) + if (unlikely(test_thread_flag(TIF_MEMDIE) || + fatal_signal_pending(current))) goto bypass; if (unlikely(task_in_memcg_oom(current))) @@ -2741,73 +2683,16 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, if (gfp_mask & __GFP_NOFAIL) oom = false; - - /* - * We always charge the cgroup the mm_struct belongs to. - * The mm_struct's mem_cgroup changes on task migration if the - * thread group leader migrates. It's possible that mm is not - * set, if so charge the root memcg (happens for pagecache usage). - */ - if (!*ptr && !mm) - *ptr = root_mem_cgroup; again: - if (*ptr) { /* css should be a valid one */ - memcg = *ptr; - if (mem_cgroup_is_root(memcg)) - goto done; - if (consume_stock(memcg, nr_pages)) - goto done; - css_get(&memcg->css); - } else { - struct task_struct *p; - - rcu_read_lock(); - p = rcu_dereference(mm->owner); - /* - * Because we don't have task_lock(), "p" can exit. - * In that case, "memcg" can point to root or p can be NULL with - * race with swapoff. Then, we have small risk of mis-accouning. - * But such kind of mis-account by race always happens because - * we don't have cgroup_mutex(). It's overkill and we allo that - * small race, here. - * (*) swapoff at el will charge against mm-struct not against - * task-struct. So, mm->owner can be NULL. - */ - memcg = mem_cgroup_from_task(p); - if (!memcg) - memcg = root_mem_cgroup; - if (mem_cgroup_is_root(memcg)) { - rcu_read_unlock(); - goto done; - } - if (consume_stock(memcg, nr_pages)) { - /* - * It seems dagerous to access memcg without css_get(). - * But considering how consume_stok works, it's not - * necessary. If consume_stock success, some charges - * from this memcg are cached on this cpu. So, we - * don't need to call css_get()/css_tryget() before - * calling consume_stock(). - */ - rcu_read_unlock(); - goto done; - } - /* after here, we may be blocked. we need to get refcnt */ - if (!css_tryget(&memcg->css)) { - rcu_read_unlock(); - goto again; - } - rcu_read_unlock(); - } + if (consume_stock(memcg, nr_pages)) + goto done; do { bool invoke_oom = oom && !nr_oom_retries; /* If killed, bypass charge */ - if (fatal_signal_pending(current)) { - css_put(&memcg->css); + if (fatal_signal_pending(current)) goto bypass; - } ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, nr_pages, invoke_oom); @@ -2816,17 +2701,12 @@ again: break; case CHARGE_RETRY: /* not in OOM situation but retry */ batch = nr_pages; - css_put(&memcg->css); - memcg = NULL; goto again; case CHARGE_WOULDBLOCK: /* !__GFP_WAIT */ - css_put(&memcg->css); goto nomem; case CHARGE_NOMEM: /* OOM routine works */ - if (!oom || invoke_oom) { - css_put(&memcg->css); + if (!oom || invoke_oom) goto nomem; - } nr_oom_retries--; break; } @@ -2834,20 +2714,44 @@ again: if (batch > nr_pages) refill_stock(memcg, batch - nr_pages); - css_put(&memcg->css); done: - *ptr = memcg; return 0; nomem: - if (!(gfp_mask & __GFP_NOFAIL)) { - *ptr = NULL; + if (!(gfp_mask & __GFP_NOFAIL)) return -ENOMEM; - } bypass: - *ptr = root_mem_cgroup; return -EINTR; } +/** + * mem_cgroup_try_charge_mm - try charging a mm + * @mm: mm_struct to charge + * @nr_pages: number of pages to charge + * @oom: trigger OOM if reclaim fails + * + * Returns the charged mem_cgroup associated with the given mm_struct or + * NULL the charge failed. + */ +static struct mem_cgroup *mem_cgroup_try_charge_mm(struct mm_struct *mm, + gfp_t gfp_mask, + unsigned int nr_pages, + bool oom) + +{ + struct mem_cgroup *memcg; + int ret; + + memcg = get_mem_cgroup_from_mm(mm); + ret = mem_cgroup_try_charge(memcg, gfp_mask, nr_pages, oom); + css_put(&memcg->css); + if (ret == -EINTR) + memcg = root_mem_cgroup; + else if (ret) + memcg = NULL; + + return memcg; +} + /* * Somemtimes we have to undo a charge we got by try_charge(). * This function is for that and do uncharge, put css's refcnt. @@ -3043,20 +2947,17 @@ static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v) static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size) { struct res_counter *fail_res; - struct mem_cgroup *_memcg; int ret = 0; ret = res_counter_charge(&memcg->kmem, size, &fail_res); if (ret) return ret; - _memcg = memcg; - ret = __mem_cgroup_try_charge(NULL, gfp, size >> PAGE_SHIFT, - &_memcg, oom_gfp_allowed(gfp)); - + ret = mem_cgroup_try_charge(memcg, gfp, size >> PAGE_SHIFT, + oom_gfp_allowed(gfp)); if (ret == -EINTR) { /* - * __mem_cgroup_try_charge() chosed to bypass to root due to + * mem_cgroup_try_charge() chosed to bypass to root due to * OOM kill or fatal signal. Since our only options are to * either fail the allocation or charge it to this cgroup, do * it as a temporary condition. But we can't fail. From a @@ -3066,7 +2967,7 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size) * * This condition will only trigger if the task entered * memcg_charge_kmem in a sane state, but was OOM-killed during - * __mem_cgroup_try_charge() above. Tasks that were already + * mem_cgroup_try_charge() above. Tasks that were already * dying when the allocation triggers should have been already * directed to the root cgroup in memcontrol.h */ @@ -3193,6 +3094,29 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups) return 0; } +char *memcg_create_cache_name(struct mem_cgroup *memcg, + struct kmem_cache *root_cache) +{ + static char *buf = NULL; + + /* + * We need a mutex here to protect the shared buffer. Since this is + * expected to be called only on cache creation, we can employ the + * slab_mutex for that purpose. + */ + lockdep_assert_held(&slab_mutex); + + if (!buf) { + buf = kmalloc(NAME_MAX + 1, GFP_KERNEL); + if (!buf) + return NULL; + } + + cgroup_name(memcg->css.cgroup, buf, NAME_MAX + 1); + return kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, + memcg_cache_id(memcg), buf); +} + int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, struct kmem_cache *root_cache) { @@ -3216,6 +3140,7 @@ int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, s->memcg_params->root_cache = root_cache; INIT_WORK(&s->memcg_params->destroy, kmem_cache_destroy_work_func); + css_get(&memcg->css); } else s->memcg_params->is_root_cache = true; @@ -3224,6 +3149,10 @@ int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, void memcg_free_cache_params(struct kmem_cache *s) { + if (!s->memcg_params) + return; + if (!s->memcg_params->is_root_cache) + css_put(&s->memcg_params->memcg->css); kfree(s->memcg_params); } @@ -3246,9 +3175,6 @@ void memcg_register_cache(struct kmem_cache *s) memcg = s->memcg_params->memcg; id = memcg_cache_id(memcg); - css_get(&memcg->css); - - /* * Since readers won't lock (see cache_from_memcg_idx()), we need a * barrier here to ensure nobody will see the kmem_cache partially @@ -3297,10 +3223,8 @@ void memcg_unregister_cache(struct kmem_cache *s) * after removing it from the memcg_slab_caches list, otherwise we can * fail to convert memcg_params_to_cache() while traversing the list. */ - VM_BUG_ON(!root->memcg_params->memcg_caches[id]); + VM_BUG_ON(root->memcg_params->memcg_caches[id] != s); root->memcg_params->memcg_caches[id] = NULL; - - css_put(&memcg->css); } /* @@ -3397,53 +3321,10 @@ void mem_cgroup_destroy_cache(struct kmem_cache *cachep) schedule_work(&cachep->memcg_params->destroy); } -static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, - struct kmem_cache *s) -{ - struct kmem_cache *new = NULL; - static char *tmp_name = NULL; - static DEFINE_MUTEX(mutex); /* protects tmp_name */ - - BUG_ON(!memcg_can_account_kmem(memcg)); - - mutex_lock(&mutex); - /* - * kmem_cache_create_memcg duplicates the given name and - * cgroup_name for this name requires RCU context. - * This static temporary buffer is used to prevent from - * pointless shortliving allocation. - */ - if (!tmp_name) { - tmp_name = kmalloc(PATH_MAX, GFP_KERNEL); - if (!tmp_name) - goto out; - } - - rcu_read_lock(); - snprintf(tmp_name, PATH_MAX, "%s(%d:%s)", s->name, - memcg_cache_id(memcg), cgroup_name(memcg->css.cgroup)); - rcu_read_unlock(); - - new = kmem_cache_create_memcg(memcg, tmp_name, s->object_size, s->align, - (s->flags & ~SLAB_PANIC), s->ctor, s); - if (new) - new->allocflags |= __GFP_KMEMCG; - else - new = s; -out: - mutex_unlock(&mutex); - return new; -} - -void kmem_cache_destroy_memcg_children(struct kmem_cache *s) +int __kmem_cache_destroy_memcg_children(struct kmem_cache *s) { struct kmem_cache *c; - int i; - - if (!s->memcg_params) - return; - if (!s->memcg_params->is_root_cache) - return; + int i, failed = 0; /* * If the cache is being destroyed, we trust that there is no one else @@ -3477,16 +3358,14 @@ void kmem_cache_destroy_memcg_children(struct kmem_cache *s) c->memcg_params->dead = false; cancel_work_sync(&c->memcg_params->destroy); kmem_cache_destroy(c); + + if (cache_from_memcg_idx(s, i)) + failed++; } mutex_unlock(&activate_kmem_mutex); + return failed; } -struct create_work { - struct mem_cgroup *memcg; - struct kmem_cache *cachep; - struct work_struct work; -}; - static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg) { struct kmem_cache *cachep; @@ -3504,13 +3383,20 @@ static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg) mutex_unlock(&memcg->slab_caches_mutex); } +struct create_work { + struct mem_cgroup *memcg; + struct kmem_cache *cachep; + struct work_struct work; +}; + static void memcg_create_cache_work_func(struct work_struct *w) { - struct create_work *cw; + struct create_work *cw = container_of(w, struct create_work, work); + struct mem_cgroup *memcg = cw->memcg; + struct kmem_cache *cachep = cw->cachep; - cw = container_of(w, struct create_work, work); - memcg_create_kmem_cache(cw->memcg, cw->cachep); - css_put(&cw->memcg->css); + kmem_cache_create_memcg(memcg, cachep); + css_put(&memcg->css); kfree(cw); } @@ -3669,15 +3555,7 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order) if (!current->mm || current->memcg_kmem_skip_account) return true; - memcg = try_get_mem_cgroup_from_mm(current->mm); - - /* - * very rare case described in mem_cgroup_from_task. Unfortunately there - * isn't much we can do without complicating this too much, and it would - * be gfp-dependent anyway. Just let it go - */ - if (unlikely(!memcg)) - return true; + memcg = get_mem_cgroup_from_mm(current->mm); if (!memcg_can_account_kmem(memcg)) { css_put(&memcg->css); @@ -3780,19 +3658,6 @@ void mem_cgroup_split_huge_fixup(struct page *head) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline -void mem_cgroup_move_account_page_stat(struct mem_cgroup *from, - struct mem_cgroup *to, - unsigned int nr_pages, - enum mem_cgroup_stat_index idx) -{ - /* Update stat data for mem_cgroup */ - preempt_disable(); - __this_cpu_sub(from->stat->count[idx], nr_pages); - __this_cpu_add(to->stat->count[idx], nr_pages); - preempt_enable(); -} - /** * mem_cgroup_move_account - move account of the page * @page: the page @@ -3838,13 +3703,19 @@ static int mem_cgroup_move_account(struct page *page, move_lock_mem_cgroup(from, &flags); - if (!anon && page_mapped(page)) - mem_cgroup_move_account_page_stat(from, to, nr_pages, - MEM_CGROUP_STAT_FILE_MAPPED); + if (!anon && page_mapped(page)) { + __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], + nr_pages); + __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], + nr_pages); + } - if (PageWriteback(page)) - mem_cgroup_move_account_page_stat(from, to, nr_pages, - MEM_CGROUP_STAT_WRITEBACK); + if (PageWriteback(page)) { + __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_WRITEBACK], + nr_pages); + __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_WRITEBACK], + nr_pages); + } mem_cgroup_charge_statistics(from, page, anon, -nr_pages); @@ -3930,19 +3801,19 @@ out: return ret; } -/* - * Charge the memory controller for page usage. - * Return - * 0 if the charge was successful - * < 0 if the cgroup is over its limit - */ -static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, enum charge_type ctype) +int mem_cgroup_charge_anon(struct page *page, + struct mm_struct *mm, gfp_t gfp_mask) { - struct mem_cgroup *memcg = NULL; unsigned int nr_pages = 1; + struct mem_cgroup *memcg; bool oom = true; - int ret; + + if (mem_cgroup_disabled()) + return 0; + + VM_BUG_ON_PAGE(page_mapped(page), page); + VM_BUG_ON_PAGE(page->mapping && !PageAnon(page), page); + VM_BUG_ON(!mm); if (PageTransHuge(page)) { nr_pages <<= compound_order(page); @@ -3954,25 +3825,14 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, oom = false; } - ret = __mem_cgroup_try_charge(mm, gfp_mask, nr_pages, &memcg, oom); - if (ret == -ENOMEM) - return ret; - __mem_cgroup_commit_charge(memcg, page, nr_pages, ctype, false); + memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, nr_pages, oom); + if (!memcg) + return -ENOMEM; + __mem_cgroup_commit_charge(memcg, page, nr_pages, + MEM_CGROUP_CHARGE_TYPE_ANON, false); return 0; } -int mem_cgroup_newpage_charge(struct page *page, - struct mm_struct *mm, gfp_t gfp_mask) -{ - if (mem_cgroup_disabled()) - return 0; - VM_BUG_ON_PAGE(page_mapped(page), page); - VM_BUG_ON_PAGE(page->mapping && !PageAnon(page), page); - VM_BUG_ON(!mm); - return mem_cgroup_charge_common(page, mm, gfp_mask, - MEM_CGROUP_CHARGE_TYPE_ANON); -} - /* * While swap-in, try_charge -> commit or cancel, the page is locked. * And when try_charge() successfully returns, one refcnt to memcg without @@ -3984,7 +3844,7 @@ static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm, gfp_t mask, struct mem_cgroup **memcgp) { - struct mem_cgroup *memcg; + struct mem_cgroup *memcg = NULL; struct page_cgroup *pc; int ret; @@ -3997,31 +3857,29 @@ static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm, * in turn serializes uncharging. */ if (PageCgroupUsed(pc)) - return 0; - if (!do_swap_account) - goto charge_cur_mm; - memcg = try_get_mem_cgroup_from_page(page); + goto out; + if (do_swap_account) + memcg = try_get_mem_cgroup_from_page(page); if (!memcg) - goto charge_cur_mm; - *memcgp = memcg; - ret = __mem_cgroup_try_charge(NULL, mask, 1, memcgp, true); + memcg = get_mem_cgroup_from_mm(mm); + ret = mem_cgroup_try_charge(memcg, mask, 1, true); css_put(&memcg->css); if (ret == -EINTR) - ret = 0; - return ret; -charge_cur_mm: - ret = __mem_cgroup_try_charge(mm, mask, 1, memcgp, true); - if (ret == -EINTR) - ret = 0; - return ret; + memcg = root_mem_cgroup; + else if (ret) + return ret; +out: + *memcgp = memcg; + return 0; } int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page, gfp_t gfp_mask, struct mem_cgroup **memcgp) { - *memcgp = NULL; - if (mem_cgroup_disabled()) + if (mem_cgroup_disabled()) { + *memcgp = NULL; return 0; + } /* * A racing thread's fault, or swapoff, may have already * updated the pte, and even removed page from swap cache: in @@ -4029,12 +3887,13 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page, * there's also a KSM case which does need to charge the page. */ if (!PageSwapCache(page)) { - int ret; + struct mem_cgroup *memcg; - ret = __mem_cgroup_try_charge(mm, gfp_mask, 1, memcgp, true); - if (ret == -EINTR) - ret = 0; - return ret; + memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true); + if (!memcg) + return -ENOMEM; + *memcgp = memcg; + return 0; } return __mem_cgroup_try_charge_swapin(mm, page, gfp_mask, memcgp); } @@ -4078,11 +3937,11 @@ void mem_cgroup_commit_charge_swapin(struct page *page, MEM_CGROUP_CHARGE_TYPE_ANON); } -int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, +int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { - struct mem_cgroup *memcg = NULL; enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE; + struct mem_cgroup *memcg; int ret; if (mem_cgroup_disabled()) @@ -4090,15 +3949,28 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, if (PageCompound(page)) return 0; - if (!PageSwapCache(page)) - ret = mem_cgroup_charge_common(page, mm, gfp_mask, type); - else { /* page is swapcache/shmem */ + if (PageSwapCache(page)) { /* shmem */ ret = __mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &memcg); - if (!ret) - __mem_cgroup_commit_charge_swapin(page, memcg, type); + if (ret) + return ret; + __mem_cgroup_commit_charge_swapin(page, memcg, type); + return 0; } - return ret; + + /* + * Page cache insertions can happen without an actual mm + * context, e.g. during disk probing on boot. + */ + if (unlikely(!mm)) + memcg = root_mem_cgroup; + else { + memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true); + if (!memcg) + return -ENOMEM; + } + __mem_cgroup_commit_charge(memcg, page, 1, type, false); + return 0; } static void mem_cgroup_do_uncharge(struct mem_cgroup *memcg, @@ -4990,7 +4862,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) struct cgroup *cgrp = memcg->css.cgroup; /* returns EBUSY if there is a task or if we come here twice. */ - if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children)) + if (cgroup_has_tasks(cgrp) || !list_empty(&cgrp->children)) return -EBUSY; /* we call try-to-free pages for make this cgroup empty */ @@ -5172,7 +5044,7 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg, * of course permitted. */ mutex_lock(&memcg_create_mutex); - if (cgroup_task_count(memcg->css.cgroup) || memcg_has_children(memcg)) + if (cgroup_has_tasks(memcg->css.cgroup) || memcg_has_children(memcg)) err = -EBUSY; mutex_unlock(&memcg_create_mutex); if (err) @@ -5274,7 +5146,7 @@ static int memcg_update_kmem_limit(struct mem_cgroup *memcg, * RES_LIMIT. */ static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, - const char *buffer) + char *buffer) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); enum res_type type; @@ -6095,7 +5967,7 @@ static void memcg_event_ptable_queue_proc(struct file *file, * Interpretation of args is defined by control file implementation. */ static int memcg_write_event_control(struct cgroup_subsys_state *css, - struct cftype *cft, const char *buffer) + struct cftype *cft, char *buffer) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup_event *event; @@ -6183,17 +6055,15 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css, * automatically removed on cgroup destruction but the removal is * asynchronous, so take an extra ref on @css. */ - rcu_read_lock(); - + cfile_css = css_tryget_from_dir(cfile.file->f_dentry->d_parent, + &memory_cgrp_subsys); ret = -EINVAL; - cfile_css = css_from_dir(cfile.file->f_dentry->d_parent, - &mem_cgroup_subsys); - if (cfile_css == css && css_tryget(css)) - ret = 0; - - rcu_read_unlock(); - if (ret) + if (IS_ERR(cfile_css)) goto out_put_cfile; + if (cfile_css != css) { + css_put(cfile_css); + goto out_put_cfile; + } ret = event->register_event(memcg, event->eventfd, buffer); if (ret) @@ -6566,11 +6436,11 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) * unfortunate state in our controller. */ if (parent != root_mem_cgroup) - mem_cgroup_subsys.broken_hierarchy = true; + memory_cgrp_subsys.broken_hierarchy = true; } mutex_unlock(&memcg_create_mutex); - return memcg_init_kmem(memcg, &mem_cgroup_subsys); + return memcg_init_kmem(memcg, &memory_cgrp_subsys); } /* @@ -6595,6 +6465,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup_event *event, *tmp; + struct cgroup_subsys_state *iter; /* * Unregister events and notify userspace. @@ -6611,7 +6482,14 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) kmem_cgroup_css_offline(memcg); mem_cgroup_invalidate_reclaim_iterators(memcg); - mem_cgroup_reparent_charges(memcg); + + /* + * This requires that offlining is serialized. Right now that is + * guaranteed because css_killed_work_fn() holds the cgroup_mutex. + */ + css_for_each_descendant_post(iter, css) + mem_cgroup_reparent_charges(mem_cgroup_from_css(iter)); + mem_cgroup_destroy_all_caches(memcg); vmpressure_cleanup(&memcg->vmpressure); } @@ -6704,8 +6582,7 @@ one_by_one: batch_count = PRECHARGE_COUNT_AT_ONCE; cond_resched(); } - ret = __mem_cgroup_try_charge(NULL, - GFP_KERNEL, 1, &memcg, false); + ret = mem_cgroup_try_charge(memcg, GFP_KERNEL, 1, false); if (ret) /* mem_cgroup_clear_mc() will do uncharge later */ return ret; @@ -7264,9 +7141,7 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css) mem_cgroup_from_css(root_css)->use_hierarchy = true; } -struct cgroup_subsys mem_cgroup_subsys = { - .name = "memory", - .subsys_id = mem_cgroup_subsys_id, +struct cgroup_subsys memory_cgrp_subsys = { .css_alloc = mem_cgroup_css_alloc, .css_online = mem_cgroup_css_online, .css_offline = mem_cgroup_css_offline, @@ -7292,7 +7167,7 @@ __setup("swapaccount=", enable_swap_account); static void __init memsw_file_init(void) { - WARN_ON(cgroup_add_cftypes(&mem_cgroup_subsys, memsw_cgroup_files)); + WARN_ON(cgroup_add_cftypes(&memory_cgrp_subsys, memsw_cgroup_files)); } static void __init enable_swap_cgroup(void) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 4f08a2d..35ef28a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -145,14 +145,10 @@ static int hwpoison_filter_task(struct page *p) return -EINVAL; css = mem_cgroup_css(mem); - /* root_mem_cgroup has NULL dentries */ - if (!css->cgroup->dentry) - return -EINVAL; - - ino = css->cgroup->dentry->d_inode->i_ino; + ino = cgroup_ino(css->cgroup); css_put(css); - if (ino != hwpoison_filter_memcg) + if (!ino || ino != hwpoison_filter_memcg) return -EINVAL; return 0; @@ -945,8 +941,10 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * to it. Similarly, page lock is shifted. */ if (hpage != p) { - put_page(hpage); - get_page(p); + if (!(flags & MF_COUNT_INCREASED)) { + put_page(hpage); + get_page(p); + } lock_page(p); unlock_page(hpage); *hpagep = p; @@ -1649,7 +1647,7 @@ int soft_offline_page(struct page *page, int flags) { int ret; unsigned long pfn = page_to_pfn(page); - struct page *hpage = compound_trans_head(page); + struct page *hpage = compound_head(page); if (PageHWPoison(page)) { pr_info("soft offline: %#lx page already poisoned\n", pfn); diff --git a/mm/memory.c b/mm/memory.c index be6a0c0..d0f0bef 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -60,6 +60,7 @@ #include <linux/migrate.h> #include <linux/string.h> #include <linux/dma-debug.h> +#include <linux/debugfs.h> #include <asm/io.h> #include <asm/pgalloc.h> @@ -1320,9 +1321,9 @@ static void unmap_single_vma(struct mmu_gather *tlb, * It is undesirable to test vma->vm_file as it * should be non-null for valid hugetlb area. * However, vm_file will be NULL in the error - * cleanup path of do_mmap_pgoff. When + * cleanup path of mmap_region. When * hugetlbfs ->mmap method fails, - * do_mmap_pgoff() nullifies vma->vm_file + * mmap_region() nullifies vma->vm_file * before calling this function to clean up. * Since no pte has actually been setup, it is * safe to do nothing in this case. @@ -1705,15 +1706,6 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET)); - /* - * Require read or write permissions. - * If FOLL_FORCE is set, we only require the "MAY" flags. - */ - vm_flags = (gup_flags & FOLL_WRITE) ? - (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); - vm_flags &= (gup_flags & FOLL_FORCE) ? - (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); - /* * If FOLL_FORCE and FOLL_NUMA are both set, handle_mm_fault * would be called on PROT_NONE ranges. We must never invoke @@ -1741,7 +1733,7 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, /* user gate pages are read-only */ if (gup_flags & FOLL_WRITE) - return i ? : -EFAULT; + goto efault; if (pg > TASK_SIZE) pgd = pgd_offset_k(pg); else @@ -1751,12 +1743,12 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, BUG_ON(pud_none(*pud)); pmd = pmd_offset(pud, pg); if (pmd_none(*pmd)) - return i ? : -EFAULT; + goto efault; VM_BUG_ON(pmd_trans_huge(*pmd)); pte = pte_offset_map(pmd, pg); if (pte_none(*pte)) { pte_unmap(pte); - return i ? : -EFAULT; + goto efault; } vma = get_gate_vma(mm); if (pages) { @@ -1769,7 +1761,7 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, page = pte_page(*pte); else { pte_unmap(pte); - return i ? : -EFAULT; + goto efault; } } pages[i] = page; @@ -1780,10 +1772,42 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, goto next_page; } - if (!vma || - (vma->vm_flags & (VM_IO | VM_PFNMAP)) || - !(vm_flags & vma->vm_flags)) - return i ? : -EFAULT; + if (!vma) + goto efault; + vm_flags = vma->vm_flags; + if (vm_flags & (VM_IO | VM_PFNMAP)) + goto efault; + + if (gup_flags & FOLL_WRITE) { + if (!(vm_flags & VM_WRITE)) { + if (!(gup_flags & FOLL_FORCE)) + goto efault; + /* + * We used to let the write,force case do COW + * in a VM_MAYWRITE VM_SHARED !VM_WRITE vma, so + * ptrace could set a breakpoint in a read-only + * mapping of an executable, without corrupting + * the file (yet only when that file had been + * opened for writing!). Anon pages in shared + * mappings are surprising: now just reject it. + */ + if (!is_cow_mapping(vm_flags)) { + WARN_ON_ONCE(vm_flags & VM_MAYWRITE); + goto efault; + } + } + } else { + if (!(vm_flags & VM_READ)) { + if (!(gup_flags & FOLL_FORCE)) + goto efault; + /* + * Is there actually any vma we can reach here + * which does not have VM_MAYREAD set? + */ + if (!(vm_flags & VM_MAYREAD)) + goto efault; + } + } if (is_vm_hugetlb_page(vma)) { i = follow_hugetlb_page(mm, vma, pages, vmas, @@ -1837,7 +1861,7 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, return -EFAULT; } if (ret & VM_FAULT_SIGBUS) - return i ? i : -EFAULT; + goto efault; BUG(); } @@ -1895,6 +1919,8 @@ next_page: } while (nr_pages && start < vma->vm_end); } while (nr_pages); return i; +efault: + return i ? : -EFAULT; } EXPORT_SYMBOL(__get_user_pages); @@ -1962,9 +1988,8 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, * @start: starting user address * @nr_pages: number of pages from start to pin * @write: whether pages will be written to by the caller - * @force: whether to force write access even if user mapping is - * readonly. This will result in the page being COWed even - * in MAP_SHARED mappings. You do not want this. + * @force: whether to force access even when user mapping is currently + * protected (but never forces write access to shared mapping). * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. @@ -2587,6 +2612,38 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo } /* + * Notify the address space that the page is about to become writable so that + * it can prohibit this or wait for the page to get into an appropriate state. + * + * We do this without the lock held, so that it can sleep if it needs to. + */ +static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page, + unsigned long address) +{ + struct vm_fault vmf; + int ret; + + vmf.virtual_address = (void __user *)(address & PAGE_MASK); + vmf.pgoff = page->index; + vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; + vmf.page = page; + + ret = vma->vm_ops->page_mkwrite(vma, &vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) + return ret; + if (unlikely(!(ret & VM_FAULT_LOCKED))) { + lock_page(page); + if (!page->mapping) { + unlock_page(page); + return 0; /* retry */ + } + ret |= VM_FAULT_LOCKED; + } else + VM_BUG_ON_PAGE(!PageLocked(page), page); + return ret; +} + +/* * This routine handles present pages, when users try to write * to a shared page. It is done by copying the page to a new address * and decrementing the shared-page counter for the old page. @@ -2668,42 +2725,15 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, * get_user_pages(.write=1, .force=1). */ if (vma->vm_ops && vma->vm_ops->page_mkwrite) { - struct vm_fault vmf; int tmp; - - vmf.virtual_address = (void __user *)(address & - PAGE_MASK); - vmf.pgoff = old_page->index; - vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; - vmf.page = old_page; - - /* - * Notify the address space that the page is about to - * become writable so that it can prohibit this or wait - * for the page to get into an appropriate state. - * - * We do this without the lock held, so that it can - * sleep if it needs to. - */ page_cache_get(old_page); pte_unmap_unlock(page_table, ptl); - - tmp = vma->vm_ops->page_mkwrite(vma, &vmf); - if (unlikely(tmp & - (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { - ret = tmp; - goto unwritable_page; + tmp = do_page_mkwrite(vma, old_page, address); + if (unlikely(!tmp || (tmp & + (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { + page_cache_release(old_page); + return tmp; } - if (unlikely(!(tmp & VM_FAULT_LOCKED))) { - lock_page(old_page); - if (!old_page->mapping) { - ret = 0; /* retry the fault */ - unlock_page(old_page); - goto unwritable_page; - } - } else - VM_BUG_ON_PAGE(!PageLocked(old_page), old_page); - /* * Since we dropped the lock we need to revalidate * the PTE as someone else may have changed it. If @@ -2748,11 +2778,11 @@ reuse: * bit after it clear all dirty ptes, but before a racing * do_wp_page installs a dirty pte. * - * __do_fault is protected similarly. + * do_shared_fault is protected similarly. */ if (!page_mkwrite) { wait_on_page_locked(dirty_page); - set_page_dirty_balance(dirty_page, page_mkwrite); + set_page_dirty_balance(dirty_page); /* file_update_time outside page_lock */ if (vma->vm_file) file_update_time(vma->vm_file); @@ -2798,7 +2828,7 @@ gotten: } __SetPageUptodate(new_page); - if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL)) + if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL)) goto oom_free_new; mmun_start = address & PAGE_MASK; @@ -2892,10 +2922,6 @@ oom: if (old_page) page_cache_release(old_page); return VM_FAULT_OOM; - -unwritable_page: - page_cache_release(old_page); - return ret; } static void unmap_mapping_range_vma(struct vm_area_struct *vma, @@ -3255,7 +3281,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, */ __SetPageUptodate(page); - if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) + if (mem_cgroup_charge_anon(page, mm, GFP_KERNEL)) goto oom_free_page; entry = mk_pte(page, vma->vm_page_prot); @@ -3286,53 +3312,11 @@ oom: return VM_FAULT_OOM; } -/* - * __do_fault() tries to create a new page mapping. It aggressively - * tries to share with existing pages, but makes a separate copy if - * the FAULT_FLAG_WRITE is set in the flags parameter in order to avoid - * the next page fault. - * - * As this is called only for pages that do not currently exist, we - * do not need to flush old virtual caches or the TLB. - * - * We enter with non-exclusive mmap_sem (to exclude vma changes, - * but allow concurrent faults), and pte neither mapped nor locked. - * We return with mmap_sem still held, but pte unmapped and unlocked. - */ -static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, - pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +static int __do_fault(struct vm_area_struct *vma, unsigned long address, + pgoff_t pgoff, unsigned int flags, struct page **page) { - pte_t *page_table; - spinlock_t *ptl; - struct page *page; - struct page *cow_page; - pte_t entry; - int anon = 0; - struct page *dirty_page = NULL; struct vm_fault vmf; int ret; - int page_mkwrite = 0; - - /* - * If we do COW later, allocate page befor taking lock_page() - * on the file cache page. This will reduce lock holding time. - */ - if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { - - if (unlikely(anon_vma_prepare(vma))) - return VM_FAULT_OOM; - - cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); - if (!cow_page) - return VM_FAULT_OOM; - - if (mem_cgroup_newpage_charge(cow_page, mm, GFP_KERNEL)) { - page_cache_release(cow_page); - return VM_FAULT_OOM; - } - } else - cow_page = NULL; vmf.virtual_address = (void __user *)(address & PAGE_MASK); vmf.pgoff = pgoff; @@ -3340,150 +3324,304 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, vmf.page = NULL; ret = vma->vm_ops->fault(vma, &vmf); - if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | - VM_FAULT_RETRY))) - goto uncharge_out; + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + return ret; if (unlikely(PageHWPoison(vmf.page))) { if (ret & VM_FAULT_LOCKED) unlock_page(vmf.page); - ret = VM_FAULT_HWPOISON; - goto uncharge_out; + page_cache_release(vmf.page); + return VM_FAULT_HWPOISON; } - /* - * For consistency in subsequent calls, make the faulted page always - * locked. - */ if (unlikely(!(ret & VM_FAULT_LOCKED))) lock_page(vmf.page); else VM_BUG_ON_PAGE(!PageLocked(vmf.page), vmf.page); + *page = vmf.page; + return ret; +} + +/** + * do_set_pte - setup new PTE entry for given page and add reverse page mapping. + * + * @vma: virtual memory area + * @address: user virtual address + * @page: page to map + * @pte: pointer to target page table entry + * @write: true, if new entry is writable + * @anon: true, if it's anonymous page + * + * Caller must hold page table lock relevant for @pte. + * + * Target users are page handler itself and implementations of + * vm_ops->map_pages. + */ +void do_set_pte(struct vm_area_struct *vma, unsigned long address, + struct page *page, pte_t *pte, bool write, bool anon) +{ + pte_t entry; + + flush_icache_page(vma, page); + entry = mk_pte(page, vma->vm_page_prot); + if (write) + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + else if (pte_file(*pte) && pte_file_soft_dirty(*pte)) + pte_mksoft_dirty(entry); + if (anon) { + inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); + page_add_new_anon_rmap(page, vma, address); + } else { + inc_mm_counter_fast(vma->vm_mm, MM_FILEPAGES); + page_add_file_rmap(page); + } + set_pte_at(vma->vm_mm, address, pte, entry); + + /* no need to invalidate: a not-present page won't be cached */ + update_mmu_cache(vma, address, pte); +} + +#define FAULT_AROUND_ORDER 4 + +#ifdef CONFIG_DEBUG_FS +static unsigned int fault_around_order = FAULT_AROUND_ORDER; + +static int fault_around_order_get(void *data, u64 *val) +{ + *val = fault_around_order; + return 0; +} + +static int fault_around_order_set(void *data, u64 val) +{ + BUILD_BUG_ON((1UL << FAULT_AROUND_ORDER) > PTRS_PER_PTE); + if (1UL << val > PTRS_PER_PTE) + return -EINVAL; + fault_around_order = val; + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(fault_around_order_fops, + fault_around_order_get, fault_around_order_set, "%llu\n"); + +static int __init fault_around_debugfs(void) +{ + void *ret; + + ret = debugfs_create_file("fault_around_order", 0644, NULL, NULL, + &fault_around_order_fops); + if (!ret) + pr_warn("Failed to create fault_around_order in debugfs"); + return 0; +} +late_initcall(fault_around_debugfs); + +static inline unsigned long fault_around_pages(void) +{ + return 1UL << fault_around_order; +} + +static inline unsigned long fault_around_mask(void) +{ + return ~((1UL << (PAGE_SHIFT + fault_around_order)) - 1); +} +#else +static inline unsigned long fault_around_pages(void) +{ + unsigned long nr_pages; + + nr_pages = 1UL << FAULT_AROUND_ORDER; + BUILD_BUG_ON(nr_pages > PTRS_PER_PTE); + return nr_pages; +} + +static inline unsigned long fault_around_mask(void) +{ + return ~((1UL << (PAGE_SHIFT + FAULT_AROUND_ORDER)) - 1); +} +#endif + +static void do_fault_around(struct vm_area_struct *vma, unsigned long address, + pte_t *pte, pgoff_t pgoff, unsigned int flags) +{ + unsigned long start_addr; + pgoff_t max_pgoff; + struct vm_fault vmf; + int off; + + start_addr = max(address & fault_around_mask(), vma->vm_start); + off = ((address - start_addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); + pte -= off; + pgoff -= off; + /* - * Should we do an early C-O-W break? + * max_pgoff is either end of page table or end of vma + * or fault_around_pages() from pgoff, depending what is neast. */ - page = vmf.page; - if (flags & FAULT_FLAG_WRITE) { - if (!(vma->vm_flags & VM_SHARED)) { - page = cow_page; - anon = 1; - copy_user_highpage(page, vmf.page, address, vma); - __SetPageUptodate(page); - } else { - /* - * If the page will be shareable, see if the backing - * address space wants to know that the page is about - * to become writable - */ - if (vma->vm_ops->page_mkwrite) { - int tmp; - - unlock_page(page); - vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; - tmp = vma->vm_ops->page_mkwrite(vma, &vmf); - if (unlikely(tmp & - (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { - ret = tmp; - goto unwritable_page; - } - if (unlikely(!(tmp & VM_FAULT_LOCKED))) { - lock_page(page); - if (!page->mapping) { - ret = 0; /* retry the fault */ - unlock_page(page); - goto unwritable_page; - } - } else - VM_BUG_ON_PAGE(!PageLocked(page), page); - page_mkwrite = 1; - } - } - + max_pgoff = pgoff - ((start_addr >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + + PTRS_PER_PTE - 1; + max_pgoff = min3(max_pgoff, vma_pages(vma) + vma->vm_pgoff - 1, + pgoff + fault_around_pages() - 1); + + /* Check if it makes any sense to call ->map_pages */ + while (!pte_none(*pte)) { + if (++pgoff > max_pgoff) + return; + start_addr += PAGE_SIZE; + if (start_addr >= vma->vm_end) + return; + pte++; } - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + vmf.virtual_address = (void __user *) start_addr; + vmf.pte = pte; + vmf.pgoff = pgoff; + vmf.max_pgoff = max_pgoff; + vmf.flags = flags; + vma->vm_ops->map_pages(vma, &vmf); +} + +static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +{ + struct page *fault_page; + spinlock_t *ptl; + pte_t *pte; + int ret = 0; /* - * This silly early PAGE_DIRTY setting removes a race - * due to the bad i386 page protection. But it's valid - * for other architectures too. - * - * Note that if FAULT_FLAG_WRITE is set, we either now have - * an exclusive copy of the page, or this is a shared mapping, - * so we can make it writable and dirty to avoid having to - * handle that later. + * Let's call ->map_pages() first and use ->fault() as fallback + * if page by the offset is not ready to be mapped (cold cache or + * something). */ - /* Only go through if we didn't race with anybody else... */ - if (likely(pte_same(*page_table, orig_pte))) { - flush_icache_page(vma, page); - entry = mk_pte(page, vma->vm_page_prot); - if (flags & FAULT_FLAG_WRITE) - entry = maybe_mkwrite(pte_mkdirty(entry), vma); - else if (pte_file(orig_pte) && pte_file_soft_dirty(orig_pte)) - pte_mksoft_dirty(entry); - if (anon) { - inc_mm_counter_fast(mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, address); - } else { - inc_mm_counter_fast(mm, MM_FILEPAGES); - page_add_file_rmap(page); - if (flags & FAULT_FLAG_WRITE) { - dirty_page = page; - get_page(dirty_page); - } - } - set_pte_at(mm, address, page_table, entry); + if (vma->vm_ops->map_pages) { + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + do_fault_around(vma, address, pte, pgoff, flags); + if (!pte_same(*pte, orig_pte)) + goto unlock_out; + pte_unmap_unlock(pte, ptl); + } - /* no need to invalidate: a not-present page won't be cached */ - update_mmu_cache(vma, address, page_table); - } else { - if (cow_page) - mem_cgroup_uncharge_page(cow_page); - if (anon) - page_cache_release(page); - else - anon = 1; /* no anon but release faulted_page */ + ret = __do_fault(vma, address, pgoff, flags, &fault_page); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + return ret; + + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + if (unlikely(!pte_same(*pte, orig_pte))) { + pte_unmap_unlock(pte, ptl); + unlock_page(fault_page); + page_cache_release(fault_page); + return ret; } + do_set_pte(vma, address, fault_page, pte, false, false); + unlock_page(fault_page); +unlock_out: + pte_unmap_unlock(pte, ptl); + return ret; +} - pte_unmap_unlock(page_table, ptl); +static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +{ + struct page *fault_page, *new_page; + spinlock_t *ptl; + pte_t *pte; + int ret; - if (dirty_page) { - struct address_space *mapping = page->mapping; - int dirtied = 0; + if (unlikely(anon_vma_prepare(vma))) + return VM_FAULT_OOM; - if (set_page_dirty(dirty_page)) - dirtied = 1; - unlock_page(dirty_page); - put_page(dirty_page); - if ((dirtied || page_mkwrite) && mapping) { - /* - * Some device drivers do not set page.mapping but still - * dirty their pages - */ - balance_dirty_pages_ratelimited(mapping); - } + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); + if (!new_page) + return VM_FAULT_OOM; - /* file_update_time outside page_lock */ - if (vma->vm_file && !page_mkwrite) - file_update_time(vma->vm_file); - } else { - unlock_page(vmf.page); - if (anon) - page_cache_release(vmf.page); + if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL)) { + page_cache_release(new_page); + return VM_FAULT_OOM; } - return ret; + ret = __do_fault(vma, address, pgoff, flags, &fault_page); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + goto uncharge_out; -unwritable_page: - page_cache_release(page); + copy_user_highpage(new_page, fault_page, address, vma); + __SetPageUptodate(new_page); + + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + if (unlikely(!pte_same(*pte, orig_pte))) { + pte_unmap_unlock(pte, ptl); + unlock_page(fault_page); + page_cache_release(fault_page); + goto uncharge_out; + } + do_set_pte(vma, address, new_page, pte, true, true); + pte_unmap_unlock(pte, ptl); + unlock_page(fault_page); + page_cache_release(fault_page); return ret; uncharge_out: - /* fs's fault handler get error */ - if (cow_page) { - mem_cgroup_uncharge_page(cow_page); - page_cache_release(cow_page); + mem_cgroup_uncharge_page(new_page); + page_cache_release(new_page); + return ret; +} + +static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +{ + struct page *fault_page; + struct address_space *mapping; + spinlock_t *ptl; + pte_t *pte; + int dirtied = 0; + int ret, tmp; + + ret = __do_fault(vma, address, pgoff, flags, &fault_page); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + return ret; + + /* + * Check if the backing address space wants to know that the page is + * about to become writable + */ + if (vma->vm_ops->page_mkwrite) { + unlock_page(fault_page); + tmp = do_page_mkwrite(vma, fault_page, address); + if (unlikely(!tmp || + (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { + page_cache_release(fault_page); + return tmp; + } } + + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + if (unlikely(!pte_same(*pte, orig_pte))) { + pte_unmap_unlock(pte, ptl); + unlock_page(fault_page); + page_cache_release(fault_page); + return ret; + } + do_set_pte(vma, address, fault_page, pte, true, false); + pte_unmap_unlock(pte, ptl); + + if (set_page_dirty(fault_page)) + dirtied = 1; + mapping = fault_page->mapping; + unlock_page(fault_page); + if ((dirtied || vma->vm_ops->page_mkwrite) && 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 && !vma->vm_ops->page_mkwrite) + file_update_time(vma->vm_file); + return ret; } @@ -3495,7 +3633,13 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; pte_unmap(page_table); - return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); + if (!(flags & FAULT_FLAG_WRITE)) + return do_read_fault(mm, vma, address, pmd, pgoff, flags, + orig_pte); + if (!(vma->vm_flags & VM_SHARED)) + return do_cow_fault(mm, vma, address, pmd, pgoff, flags, + orig_pte); + return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); } /* @@ -3527,10 +3671,16 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, } pgoff = pte_to_pgoff(orig_pte); - return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); + if (!(flags & FAULT_FLAG_WRITE)) + return do_read_fault(mm, vma, address, pmd, pgoff, flags, + orig_pte); + if (!(vma->vm_flags & VM_SHARED)) + return do_cow_fault(mm, vma, address, pmd, pgoff, flags, + orig_pte); + return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); } -int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, +static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags) { @@ -3545,7 +3695,7 @@ int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, return mpol_misplaced(page, vma, addr); } -int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, +static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd) { struct page *page = NULL; @@ -3703,7 +3853,6 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(is_vm_hugetlb_page(vma))) return hugetlb_fault(mm, vma, address, flags); -retry: pgd = pgd_offset(mm, address); pud = pud_alloc(mm, pgd, address); if (!pud) @@ -3741,20 +3890,13 @@ retry: if (dirty && !pmd_write(orig_pmd)) { ret = do_huge_pmd_wp_page(mm, vma, address, pmd, orig_pmd); - /* - * If COW results in an oom, the huge pmd will - * have been split, so retry the fault on the - * pte for a smaller charge. - */ - if (unlikely(ret & VM_FAULT_OOM)) - goto retry; - return ret; + if (!(ret & VM_FAULT_FALLBACK)) + return ret; } else { huge_pmd_set_accessed(mm, vma, address, pmd, orig_pmd, dirty); + return 0; } - - return 0; } } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index ae3c8f3..78e1472 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -795,36 +795,6 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, return err; } -/* - * Update task->flags PF_MEMPOLICY bit: set iff non-default - * mempolicy. Allows more rapid checking of this (combined perhaps - * with other PF_* flag bits) on memory allocation hot code paths. - * - * If called from outside this file, the task 'p' should -only- be - * a newly forked child not yet visible on the task list, because - * manipulating the task flags of a visible task is not safe. - * - * The above limitation is why this routine has the funny name - * mpol_fix_fork_child_flag(). - * - * It is also safe to call this with a task pointer of current, - * which the static wrapper mpol_set_task_struct_flag() does, - * for use within this file. - */ - -void mpol_fix_fork_child_flag(struct task_struct *p) -{ - if (p->mempolicy) - p->flags |= PF_MEMPOLICY; - else - p->flags &= ~PF_MEMPOLICY; -} - -static void mpol_set_task_struct_flag(void) -{ - mpol_fix_fork_child_flag(current); -} - /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) @@ -861,7 +831,6 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags, } old = current->mempolicy; current->mempolicy = new; - mpol_set_task_struct_flag(); if (new && new->mode == MPOL_INTERLEAVE && nodes_weight(new->v.nodes)) current->il_next = first_node(new->v.nodes); @@ -1556,10 +1525,10 @@ SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, #ifdef CONFIG_COMPAT -asmlinkage long compat_sys_get_mempolicy(int __user *policy, - compat_ulong_t __user *nmask, - compat_ulong_t maxnode, - compat_ulong_t addr, compat_ulong_t flags) +COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, + compat_ulong_t __user *, nmask, + compat_ulong_t, maxnode, + compat_ulong_t, addr, compat_ulong_t, flags) { long err; unsigned long __user *nm = NULL; @@ -1586,8 +1555,8 @@ asmlinkage long compat_sys_get_mempolicy(int __user *policy, return err; } -asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask, - compat_ulong_t maxnode) +COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, + compat_ulong_t, maxnode) { long err = 0; unsigned long __user *nm = NULL; @@ -1609,9 +1578,9 @@ asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask, return sys_set_mempolicy(mode, nm, nr_bits+1); } -asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len, - compat_ulong_t mode, compat_ulong_t __user *nmask, - compat_ulong_t maxnode, compat_ulong_t flags) +COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, + compat_ulong_t, mode, compat_ulong_t __user *, nmask, + compat_ulong_t, maxnode, compat_ulong_t, flags) { long err = 0; unsigned long __user *nm = NULL; @@ -1782,21 +1751,18 @@ static unsigned interleave_nodes(struct mempolicy *policy) /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. - * @policy must be protected by freeing by the caller. If @policy is - * the current task's mempolicy, this protection is implicit, as only the - * task can change it's policy. The system default policy requires no - * such protection. */ -unsigned slab_node(void) +unsigned int mempolicy_slab_node(void) { struct mempolicy *policy; + int node = numa_mem_id(); if (in_interrupt()) - return numa_node_id(); + return node; policy = current->mempolicy; if (!policy || policy->flags & MPOL_F_LOCAL) - return numa_node_id(); + return node; switch (policy->mode) { case MPOL_PREFERRED: @@ -1816,11 +1782,11 @@ unsigned slab_node(void) struct zonelist *zonelist; struct zone *zone; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); - zonelist = &NODE_DATA(numa_node_id())->node_zonelists[0]; + zonelist = &NODE_DATA(node)->node_zonelists[0]; (void)first_zones_zonelist(zonelist, highest_zoneidx, &policy->v.nodes, &zone); - return zone ? zone->node : numa_node_id(); + return zone ? zone->node : node; } default: @@ -1899,7 +1865,7 @@ int node_random(const nodemask_t *maskp) * If the effective policy is 'BIND, returns a pointer to the mempolicy's * @nodemask for filtering the zonelist. * - * Must be protected by get_mems_allowed() + * Must be protected by read_mems_allowed_begin() */ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, @@ -2063,7 +2029,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, retry_cpuset: pol = get_vma_policy(current, vma, addr); - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); if (unlikely(pol->mode == MPOL_INTERLEAVE)) { unsigned nid; @@ -2071,7 +2037,7 @@ retry_cpuset: nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); page = alloc_page_interleave(gfp, order, nid); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; @@ -2081,7 +2047,7 @@ retry_cpuset: policy_nodemask(gfp, pol)); if (unlikely(mpol_needs_cond_ref(pol))) __mpol_put(pol); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; } @@ -2115,7 +2081,7 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order) pol = &default_policy; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); /* * No reference counting needed for current->mempolicy @@ -2128,7 +2094,7 @@ retry_cpuset: policy_zonelist(gfp, pol, numa_node_id()), policy_nodemask(gfp, pol)); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; @@ -2301,35 +2267,6 @@ static void sp_free(struct sp_node *n) kmem_cache_free(sn_cache, n); } -#ifdef CONFIG_NUMA_BALANCING -static bool numa_migrate_deferred(struct task_struct *p, int last_cpupid) -{ - /* Never defer a private fault */ - if (cpupid_match_pid(p, last_cpupid)) - return false; - - if (p->numa_migrate_deferred) { - p->numa_migrate_deferred--; - return true; - } - return false; -} - -static inline void defer_numa_migrate(struct task_struct *p) -{ - p->numa_migrate_deferred = sysctl_numa_balancing_migrate_deferred; -} -#else -static inline bool numa_migrate_deferred(struct task_struct *p, int last_cpupid) -{ - return false; -} - -static inline void defer_numa_migrate(struct task_struct *p) -{ -} -#endif /* CONFIG_NUMA_BALANCING */ - /** * mpol_misplaced - check whether current page node is valid in policy * @@ -2403,52 +2340,9 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long /* Migrate the page towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { - int last_cpupid; - int this_cpupid; - polnid = thisnid; - this_cpupid = cpu_pid_to_cpupid(thiscpu, current->pid); - - /* - * Multi-stage node selection is used in conjunction - * with a periodic migration fault to build a temporal - * task<->page relation. By using a two-stage filter we - * remove short/unlikely relations. - * - * Using P(p) ~ n_p / n_t as per frequentist - * probability, we can equate a task's usage of a - * particular page (n_p) per total usage of this - * page (n_t) (in a given time-span) to a probability. - * - * Our periodic faults will sample this probability and - * getting the same result twice in a row, given these - * samples are fully independent, is then given by - * P(n)^2, provided our sample period is sufficiently - * short compared to the usage pattern. - * - * This quadric squishes small probabilities, making - * it less likely we act on an unlikely task<->page - * relation. - */ - last_cpupid = page_cpupid_xchg_last(page, this_cpupid); - if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid) { - - /* See sysctl_numa_balancing_migrate_deferred comment */ - if (!cpupid_match_pid(current, last_cpupid)) - defer_numa_migrate(current); - goto out; - } - - /* - * The quadratic filter above reduces extraneous migration - * of shared pages somewhat. This code reduces it even more, - * reducing the overhead of page migrations of shared pages. - * This makes workloads with shared pages rely more on - * "move task near its memory", and less on "move memory - * towards its task", which is exactly what we want. - */ - if (numa_migrate_deferred(current, last_cpupid)) + if (!should_numa_migrate_memory(current, page, curnid, thiscpu)) goto out; } diff --git a/mm/mempool.c b/mm/mempool.c index 659aa42..905434f 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -304,9 +304,9 @@ void mempool_free(void *element, mempool_t *pool) * ensures that there will be frees which return elements to the * pool waking up the waiters. */ - if (pool->curr_nr < pool->min_nr) { + if (unlikely(pool->curr_nr < pool->min_nr)) { spin_lock_irqsave(&pool->lock, flags); - if (pool->curr_nr < pool->min_nr) { + if (likely(pool->curr_nr < pool->min_nr)) { add_element(pool, element); spin_unlock_irqrestore(&pool->lock, flags); wake_up(&pool->wait); diff --git a/mm/migrate.c b/mm/migrate.c index 482a33d..bed4880 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -178,6 +178,37 @@ out: } /* + * Congratulations to trinity for discovering this bug. + * mm/fremap.c's remap_file_pages() accepts any range within a single vma to + * convert that vma to VM_NONLINEAR; and generic_file_remap_pages() will then + * replace the specified range by file ptes throughout (maybe populated after). + * If page migration finds a page within that range, while it's still located + * by vma_interval_tree rather than lost to i_mmap_nonlinear list, no problem: + * zap_pte() clears the temporary migration entry before mmap_sem is dropped. + * But if the migrating page is in a part of the vma outside the range to be + * remapped, then it will not be cleared, and remove_migration_ptes() needs to + * deal with it. Fortunately, this part of the vma is of course still linear, + * so we just need to use linear location on the nonlinear list. + */ +static int remove_linear_migration_ptes_from_nonlinear(struct page *page, + struct address_space *mapping, void *arg) +{ + struct vm_area_struct *vma; + /* hugetlbfs does not support remap_pages, so no huge pgoff worries */ + pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + unsigned long addr; + + list_for_each_entry(vma, + &mapping->i_mmap_nonlinear, shared.nonlinear) { + + addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + if (addr >= vma->vm_start && addr < vma->vm_end) + remove_migration_pte(page, vma, addr, arg); + } + return SWAP_AGAIN; +} + +/* * Get rid of all migration entries and replace them by * references to the indicated page. */ @@ -186,6 +217,7 @@ static void remove_migration_ptes(struct page *old, struct page *new) struct rmap_walk_control rwc = { .rmap_one = remove_migration_pte, .arg = old, + .file_nonlinear = remove_linear_migration_ptes_from_nonlinear, }; rmap_walk(new, &rwc); @@ -1158,7 +1190,7 @@ static struct page *new_page_node(struct page *p, unsigned long private, pm->node); else return alloc_pages_exact_node(pm->node, - GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0); + GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0); } /* @@ -1544,9 +1576,9 @@ static struct page *alloc_misplaced_dst_page(struct page *page, struct page *newpage; newpage = alloc_pages_exact_node(nid, - (GFP_HIGHUSER_MOVABLE | GFP_THISNODE | - __GFP_NOMEMALLOC | __GFP_NORETRY | - __GFP_NOWARN) & + (GFP_HIGHUSER_MOVABLE | + __GFP_THISNODE | __GFP_NOMEMALLOC | + __GFP_NORETRY | __GFP_NOWARN) & ~GFP_IOFS, 0); return newpage; @@ -1747,7 +1779,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, goto out_dropref; new_page = alloc_pages_node(node, - (GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER); + (GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_WAIT, + HPAGE_PMD_ORDER); if (!new_page) goto out_fail; diff --git a/mm/mincore.c b/mm/mincore.c index 1016233..725c809 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -70,13 +70,21 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) * any other file mapping (ie. marked !present and faulted in with * tmpfs's .fault). So swapped out tmpfs mappings are tested here. */ - page = find_get_page(mapping, pgoff); #ifdef CONFIG_SWAP - /* shmem/tmpfs may return swap: account for swapcache page too. */ - if (radix_tree_exceptional_entry(page)) { - swp_entry_t swap = radix_to_swp_entry(page); - page = find_get_page(swap_address_space(swap), swap.val); - } + if (shmem_mapping(mapping)) { + page = find_get_entry(mapping, pgoff); + /* + * shmem/tmpfs may return swap: account for swapcache + * page too. + */ + if (radix_tree_exceptional_entry(page)) { + swp_entry_t swp = radix_to_swp_entry(page); + page = find_get_page(swap_address_space(swp), swp.val); + } + } else + page = find_get_page(mapping, pgoff); +#else + page = find_get_page(mapping, pgoff); #endif if (page) { present = PageUptodate(page); @@ -79,6 +79,7 @@ void clear_page_mlock(struct page *page) */ void mlock_vma_page(struct page *page) { + /* Serialize with page migration */ BUG_ON(!PageLocked(page)); if (!TestSetPageMlocked(page)) { @@ -174,6 +175,7 @@ unsigned int munlock_vma_page(struct page *page) unsigned int nr_pages; struct zone *zone = page_zone(page); + /* For try_to_munlock() and to serialize with page migration */ BUG_ON(!PageLocked(page)); /* @@ -10,6 +10,7 @@ #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/shm.h> #include <linux/mman.h> #include <linux/pagemap.h> @@ -405,7 +406,7 @@ static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore) } } -void validate_mm(struct mm_struct *mm) +static void validate_mm(struct mm_struct *mm) { int bug = 0; int i = 0; @@ -681,8 +682,9 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, prev->vm_next = next = vma->vm_next; if (next) next->vm_prev = prev; - if (mm->mmap_cache == vma) - mm->mmap_cache = prev; + + /* Kill the cache */ + vmacache_invalidate(mm); } /* @@ -1299,7 +1301,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, /* * Make sure there are no mandatory locks on the file. */ - if (locks_verify_locked(inode)) + if (locks_verify_locked(file)) return -EAGAIN; vm_flags |= VM_SHARED | VM_MAYSHARE; @@ -1989,34 +1991,33 @@ EXPORT_SYMBOL(get_unmapped_area); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { - struct vm_area_struct *vma = NULL; + struct rb_node *rb_node; + struct vm_area_struct *vma; /* Check the cache first. */ - /* (Cache hit rate is typically around 35%.) */ - vma = ACCESS_ONCE(mm->mmap_cache); - if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) { - struct rb_node *rb_node; + vma = vmacache_find(mm, addr); + if (likely(vma)) + return vma; - rb_node = mm->mm_rb.rb_node; - vma = NULL; + rb_node = mm->mm_rb.rb_node; + vma = NULL; - while (rb_node) { - struct vm_area_struct *vma_tmp; - - vma_tmp = rb_entry(rb_node, - struct vm_area_struct, vm_rb); - - if (vma_tmp->vm_end > addr) { - vma = vma_tmp; - if (vma_tmp->vm_start <= addr) - break; - rb_node = rb_node->rb_left; - } else - rb_node = rb_node->rb_right; - } - if (vma) - mm->mmap_cache = vma; + while (rb_node) { + struct vm_area_struct *tmp; + + tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb); + + if (tmp->vm_end > addr) { + vma = tmp; + if (tmp->vm_start <= addr) + break; + rb_node = rb_node->rb_left; + } else + rb_node = rb_node->rb_right; } + + if (vma) + vmacache_update(addr, vma); return vma; } @@ -2388,7 +2389,9 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, } else mm->highest_vm_end = prev ? prev->vm_end : 0; tail_vma->vm_next = NULL; - mm->mmap_cache = NULL; /* Kill the cache. */ + + /* Kill the cache */ + vmacache_invalidate(mm); } /* @@ -2918,7 +2921,7 @@ static const struct vm_operations_struct special_mapping_vmops = { * The array pointer and the pages it points to are assumed to stay alive * for as long as this mapping might exist. */ -int install_special_mapping(struct mm_struct *mm, +struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, struct page **pages) { @@ -2927,7 +2930,7 @@ int install_special_mapping(struct mm_struct *mm, vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); if (unlikely(vma == NULL)) - return -ENOMEM; + return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = mm; @@ -2948,11 +2951,23 @@ int install_special_mapping(struct mm_struct *mm, perf_event_mmap(vma); - return 0; + return vma; out: kmem_cache_free(vm_area_cachep, vma); - return ret; + return ERR_PTR(ret); +} + +int install_special_mapping(struct mm_struct *mm, + unsigned long addr, unsigned long len, + unsigned long vm_flags, struct page **pages) +{ + struct vm_area_struct *vma = _install_special_mapping(mm, + addr, len, vm_flags, pages); + + if (IS_ERR(vma)) + return PTR_ERR(vma); + return 0; } static DEFINE_MUTEX(mm_all_locks_mutex); diff --git a/mm/mmu_context.c b/mm/mmu_context.c index 8a8cd02..f802c2d 100644 --- a/mm/mmu_context.c +++ b/mm/mmu_context.c @@ -31,6 +31,9 @@ void use_mm(struct mm_struct *mm) tsk->mm = mm; switch_mm(active_mm, mm, tsk); task_unlock(tsk); +#ifdef finish_arch_post_lock_switch + finish_arch_post_lock_switch(); +#endif if (active_mm != mm) mmdrop(active_mm); diff --git a/mm/mprotect.c b/mm/mprotect.c index 7332c17..c43d557 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -36,6 +36,34 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) } #endif +/* + * For a prot_numa update we only hold mmap_sem for read so there is a + * potential race with faulting where a pmd was temporarily none. This + * function checks for a transhuge pmd under the appropriate lock. It + * returns a pte if it was successfully locked or NULL if it raced with + * a transhuge insertion. + */ +static pte_t *lock_pte_protection(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr, int prot_numa, spinlock_t **ptl) +{ + pte_t *pte; + spinlock_t *pmdl; + + /* !prot_numa is protected by mmap_sem held for write */ + if (!prot_numa) + return pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl); + + pmdl = pmd_lock(vma->vm_mm, pmd); + if (unlikely(pmd_trans_huge(*pmd) || pmd_none(*pmd))) { + spin_unlock(pmdl); + return NULL; + } + + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl); + spin_unlock(pmdl); + return pte; +} + static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) @@ -45,7 +73,10 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, spinlock_t *ptl; unsigned long pages = 0; - pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + pte = lock_pte_protection(vma, pmd, addr, prot_numa, &ptl); + if (!pte) + return 0; + arch_enter_lazy_mmu_mode(); do { oldpte = *pte; @@ -58,36 +89,27 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, if (pte_numa(ptent)) ptent = pte_mknonnuma(ptent); ptent = pte_modify(ptent, newprot); + /* + * Avoid taking write faults for pages we + * know to be dirty. + */ + if (dirty_accountable && pte_dirty(ptent)) + ptent = pte_mkwrite(ptent); + ptep_modify_prot_commit(mm, addr, pte, ptent); updated = true; } else { struct page *page; - ptent = *pte; page = vm_normal_page(vma, addr, oldpte); if (page && !PageKsm(page)) { if (!pte_numa(oldpte)) { - ptent = pte_mknuma(ptent); - set_pte_at(mm, addr, pte, ptent); + ptep_set_numa(mm, addr, pte); updated = true; } } } - - /* - * Avoid taking write faults for pages we know to be - * dirty. - */ - if (dirty_accountable && pte_dirty(ptent)) { - ptent = pte_mkwrite(ptent); - updated = true; - } - if (updated) pages++; - - /* Only !prot_numa always clears the pte */ - if (!prot_numa) - ptep_modify_prot_commit(mm, addr, pte, ptent); } else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) { swp_entry_t entry = pte_to_swp_entry(oldpte); @@ -118,15 +140,26 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pgprot_t newprot, int dirty_accountable, int prot_numa) { pmd_t *pmd; + struct mm_struct *mm = vma->vm_mm; unsigned long next; unsigned long pages = 0; unsigned long nr_huge_updates = 0; + unsigned long mni_start = 0; pmd = pmd_offset(pud, addr); do { unsigned long this_pages; next = pmd_addr_end(addr, end); + if (!pmd_trans_huge(*pmd) && pmd_none_or_clear_bad(pmd)) + continue; + + /* invoke the mmu notifier if the pmd is populated */ + if (!mni_start) { + mni_start = addr; + mmu_notifier_invalidate_range_start(mm, mni_start, end); + } + if (pmd_trans_huge(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) split_huge_page_pmd(vma, addr, pmd); @@ -139,18 +172,21 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pages += HPAGE_PMD_NR; nr_huge_updates++; } + + /* huge pmd was handled */ continue; } } - /* fall through */ + /* fall through, the trans huge pmd just split */ } - if (pmd_none_or_clear_bad(pmd)) - continue; this_pages = change_pte_range(vma, pmd, addr, next, newprot, dirty_accountable, prot_numa); pages += this_pages; } while (pmd++, addr = next, addr != end); + if (mni_start) + mmu_notifier_invalidate_range_end(mm, mni_start, end); + if (nr_huge_updates) count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates); return pages; @@ -210,15 +246,12 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) { - struct mm_struct *mm = vma->vm_mm; unsigned long pages; - mmu_notifier_invalidate_range_start(mm, start, end); if (is_vm_hugetlb_page(vma)) pages = hugetlb_change_protection(vma, start, end, newprot); else pages = change_protection_range(vma, start, end, newprot, dirty_accountable, prot_numa); - mmu_notifier_invalidate_range_end(mm, start, end); return pages; } diff --git a/mm/nobootmem.c b/mm/nobootmem.c index f73f298..04a9d94 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -334,7 +334,7 @@ void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0); } -void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, +static void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal, unsigned long limit) { @@ -15,6 +15,7 @@ #include <linux/export.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/file.h> @@ -24,6 +25,7 @@ #include <linux/vmalloc.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> +#include <linux/compiler.h> #include <linux/mount.h> #include <linux/personality.h> #include <linux/security.h> @@ -296,7 +298,7 @@ long vwrite(char *buf, char *addr, unsigned long count) count = -(unsigned long) addr; memcpy(addr, buf, count); - return(count); + return count; } /* @@ -459,7 +461,7 @@ EXPORT_SYMBOL_GPL(vm_unmap_aliases); * Implement a stub for vmalloc_sync_all() if the architecture chose not to * have one. */ -void __attribute__((weak)) vmalloc_sync_all(void) +void __weak vmalloc_sync_all(void) { } @@ -768,16 +770,23 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) */ static void delete_vma_from_mm(struct vm_area_struct *vma) { + int i; struct address_space *mapping; struct mm_struct *mm = vma->vm_mm; + struct task_struct *curr = current; kenter("%p", vma); protect_vma(vma, 0); mm->map_count--; - if (mm->mmap_cache == vma) - mm->mmap_cache = NULL; + for (i = 0; i < VMACACHE_SIZE; i++) { + /* if the vma is cached, invalidate the entire cache */ + if (curr->vmacache[i] == vma) { + vmacache_invalidate(curr->mm); + break; + } + } /* remove the VMA from the mapping */ if (vma->vm_file) { @@ -825,8 +834,8 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) struct vm_area_struct *vma; /* check the cache first */ - vma = ACCESS_ONCE(mm->mmap_cache); - if (vma && vma->vm_start <= addr && vma->vm_end > addr) + vma = vmacache_find(mm, addr); + if (likely(vma)) return vma; /* trawl the list (there may be multiple mappings in which addr @@ -835,7 +844,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) if (vma->vm_start > addr) return NULL; if (vma->vm_end > addr) { - mm->mmap_cache = vma; + vmacache_update(addr, vma); return vma; } } @@ -874,8 +883,8 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, unsigned long end = addr + len; /* check the cache first */ - vma = mm->mmap_cache; - if (vma && vma->vm_start == addr && vma->vm_end == end) + vma = vmacache_find_exact(mm, addr, end); + if (vma) return vma; /* trawl the list (there may be multiple mappings in which addr @@ -886,7 +895,7 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, if (vma->vm_start > addr) return NULL; if (vma->vm_end == end) { - mm->mmap_cache = vma; + vmacache_update(addr, vma); return vma; } } @@ -995,7 +1004,7 @@ static int validate_mmap_request(struct file *file, (file->f_mode & FMODE_WRITE)) return -EACCES; - if (locks_verify_locked(file_inode(file))) + if (locks_verify_locked(file)) return -EAGAIN; if (!(capabilities & BDI_CAP_MAP_DIRECT)) @@ -1003,8 +1012,7 @@ static int validate_mmap_request(struct file *file, /* we mustn't privatise shared mappings */ capabilities &= ~BDI_CAP_MAP_COPY; - } - else { + } else { /* we're going to read the file into private memory we * allocate */ if (!(capabilities & BDI_CAP_MAP_COPY)) @@ -1035,23 +1043,20 @@ static int validate_mmap_request(struct file *file, if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) { if (prot & PROT_EXEC) return -EPERM; - } - else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) { + } else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) { /* handle implication of PROT_EXEC by PROT_READ */ if (current->personality & READ_IMPLIES_EXEC) { if (capabilities & BDI_CAP_EXEC_MAP) prot |= PROT_EXEC; } - } - else if ((prot & PROT_READ) && + } else if ((prot & PROT_READ) && (prot & PROT_EXEC) && !(capabilities & BDI_CAP_EXEC_MAP) ) { /* backing file is not executable, try to copy */ capabilities &= ~BDI_CAP_MAP_DIRECT; } - } - else { + } else { /* anonymous mappings are always memory backed and can be * privately mapped */ @@ -1659,7 +1664,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) /* find the first potentially overlapping VMA */ vma = find_vma(mm, start); if (!vma) { - static int limit = 0; + static int limit; if (limit < 5) { printk(KERN_WARNING "munmap of memory not mmapped by process %d" @@ -1985,6 +1990,12 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } EXPORT_SYMBOL(filemap_fault); +void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + BUG(); +} +EXPORT_SYMBOL(filemap_map_pages); + int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr, unsigned long size, pgoff_t pgoff) { diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 2d30e2c..ef41349 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1562,9 +1562,9 @@ pause: bdi_start_background_writeback(bdi); } -void set_page_dirty_balance(struct page *page, int page_mkwrite) +void set_page_dirty_balance(struct page *page) { - if (set_page_dirty(page) || page_mkwrite) { + if (set_page_dirty(page)) { struct address_space *mapping = page_mapping(page); if (mapping) @@ -2173,11 +2173,12 @@ int __set_page_dirty_nobuffers(struct page *page) if (!TestSetPageDirty(page)) { struct address_space *mapping = page_mapping(page); struct address_space *mapping2; + unsigned long flags; if (!mapping) return 1; - spin_lock_irq(&mapping->tree_lock); + spin_lock_irqsave(&mapping->tree_lock, flags); mapping2 = page_mapping(page); if (mapping2) { /* Race with truncate? */ BUG_ON(mapping2 != mapping); @@ -2186,7 +2187,7 @@ int __set_page_dirty_nobuffers(struct page *page) radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); } - spin_unlock_irq(&mapping->tree_lock); + spin_unlock_irqrestore(&mapping->tree_lock, flags); if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e3758a0..5dba293 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -295,7 +295,8 @@ static inline int bad_range(struct zone *zone, struct page *page) } #endif -static void bad_page(struct page *page, char *reason, unsigned long bad_flags) +static void bad_page(struct page *page, const char *reason, + unsigned long bad_flags) { static unsigned long resume; static unsigned long nr_shown; @@ -369,9 +370,11 @@ void prep_compound_page(struct page *page, unsigned long order) __SetPageHead(page); for (i = 1; i < nr_pages; i++) { struct page *p = page + i; - __SetPageTail(p); set_page_count(p, 0); p->first_page = page; + /* Make sure p->first_page is always valid for PageTail() */ + smp_wmb(); + __SetPageTail(p); } } @@ -621,7 +624,7 @@ out: static inline int free_pages_check(struct page *page) { - char *bad_reason = NULL; + const char *bad_reason = NULL; unsigned long bad_flags = 0; if (unlikely(page_mapcount(page))) @@ -857,7 +860,7 @@ static inline void expand(struct zone *zone, struct page *page, */ static inline int check_new_page(struct page *page) { - char *bad_reason = NULL; + const char *bad_reason = NULL; unsigned long bad_flags = 0; if (unlikely(page_mapcount(page))) @@ -1573,6 +1576,7 @@ again: } __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); + __count_zone_vm_events(PGALLOC, zone, 1 << order); zone_statistics(preferred_zone, zone, gfp_flags); local_irq_restore(flags); @@ -1853,7 +1857,7 @@ static void __paginginit init_zone_allows_reclaim(int nid) { int i; - for_each_online_node(i) + for_each_node_state(i, N_MEMORY) if (node_distance(nid, i) <= RECLAIM_DISTANCE) node_set(i, NODE_DATA(nid)->reclaim_nodes); else @@ -1937,19 +1941,12 @@ zonelist_scan: * zone size to ensure fair page aging. The zone a * page was allocated in should have no effect on the * time the page has in memory before being reclaimed. - * - * Try to stay in local zones in the fastpath. If - * that fails, the slowpath is entered, which will do - * another pass starting with the local zones, but - * ultimately fall back to remote zones that do not - * partake in the fairness round-robin cycle of this - * zonelist. */ - if (alloc_flags & ALLOC_WMARK_LOW) { - if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0) - continue; + if (alloc_flags & ALLOC_FAIR) { if (!zone_local(preferred_zone, zone)) continue; + if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0) + continue; } /* * When allocating a page cache page for writing, we @@ -2387,32 +2384,40 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, return page; } -static void prepare_slowpath(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, - enum zone_type high_zoneidx, - struct zone *preferred_zone) +static void reset_alloc_batches(struct zonelist *zonelist, + enum zone_type high_zoneidx, + struct zone *preferred_zone) { struct zoneref *z; struct zone *zone; for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { - if (!(gfp_mask & __GFP_NO_KSWAPD)) - wakeup_kswapd(zone, order, zone_idx(preferred_zone)); /* * Only reset the batches of zones that were actually - * considered in the fast path, we don't want to - * thrash fairness information for zones that are not + * considered in the fairness pass, we don't want to + * trash fairness information for zones that are not * actually part of this zonelist's round-robin cycle. */ if (!zone_local(preferred_zone, zone)) continue; mod_zone_page_state(zone, NR_ALLOC_BATCH, - high_wmark_pages(zone) - - low_wmark_pages(zone) - - zone_page_state(zone, NR_ALLOC_BATCH)); + high_wmark_pages(zone) - low_wmark_pages(zone) - + atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); } } +static void wake_all_kswapds(unsigned int order, + struct zonelist *zonelist, + enum zone_type high_zoneidx, + struct zone *preferred_zone) +{ + struct zoneref *z; + struct zone *zone; + + for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) + wakeup_kswapd(zone, order, zone_idx(preferred_zone)); +} + static inline int gfp_to_alloc_flags(gfp_t gfp_mask) { @@ -2502,12 +2507,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, * over allocated. */ if (IS_ENABLED(CONFIG_NUMA) && - (gfp_mask & GFP_THISNODE) == GFP_THISNODE) + (gfp_mask & GFP_THISNODE) == GFP_THISNODE) goto nopage; restart: - prepare_slowpath(gfp_mask, order, zonelist, - high_zoneidx, preferred_zone); + if (!(gfp_mask & __GFP_NO_KSWAPD)) + wake_all_kswapds(order, zonelist, high_zoneidx, preferred_zone); /* * OK, we're below the kswapd watermark and have kicked background @@ -2691,7 +2696,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, struct page *page = NULL; int migratetype = allocflags_to_migratetype(gfp_mask); unsigned int cpuset_mems_cookie; - int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET; + int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR; struct mem_cgroup *memcg = NULL; gfp_mask &= gfp_allowed_mask; @@ -2719,7 +2724,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, return NULL; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); /* The preferred zone is used for statistics later */ first_zones_zonelist(zonelist, high_zoneidx, @@ -2732,12 +2737,29 @@ retry_cpuset: if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE) alloc_flags |= ALLOC_CMA; #endif +retry: /* First allocation attempt */ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, zonelist, high_zoneidx, alloc_flags, preferred_zone, migratetype); if (unlikely(!page)) { /* + * The first pass makes sure allocations are spread + * fairly within the local node. However, the local + * node might have free pages left after the fairness + * batches are exhausted, and remote zones haven't + * even been considered yet. Try once more without + * fairness, and include remote zones now, before + * entering the slowpath and waking kswapd: prefer + * spilling to a remote zone over swapping locally. + */ + if (alloc_flags & ALLOC_FAIR) { + reset_alloc_batches(zonelist, high_zoneidx, + preferred_zone); + alloc_flags &= ~ALLOC_FAIR; + goto retry; + } + /* * Runtime PM, block IO and its error handling path * can deadlock because I/O on the device might not * complete. @@ -2757,7 +2779,7 @@ out: * the mask is being updated. If a page allocation is about to fail, * check if the cpuset changed during allocation and if so, retry. */ - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; memcg_kmem_commit_charge(page, memcg, order); @@ -3025,9 +3047,9 @@ bool skip_free_areas_node(unsigned int flags, int nid) goto out; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); ret = !node_isset(nid, cpuset_current_mems_allowed); - } while (!put_mems_allowed(cpuset_mems_cookie)); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); out: return ret; } @@ -4899,7 +4921,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; - init_zone_allows_reclaim(nid); + if (node_state(nid, N_MEMORY)) + init_zone_allows_reclaim(nid); #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); #endif @@ -5050,7 +5073,7 @@ static void __init find_zone_movable_pfns_for_nodes(void) nodemask_t saved_node_state = node_states[N_MEMORY]; unsigned long totalpages = early_calculate_totalpages(); int usable_nodes = nodes_weight(node_states[N_MEMORY]); - struct memblock_type *type = &memblock.memory; + struct memblock_region *r; /* Need to find movable_zone earlier when movable_node is specified. */ find_usable_zone_for_movable(); @@ -5060,13 +5083,13 @@ static void __init find_zone_movable_pfns_for_nodes(void) * options. */ if (movable_node_is_enabled()) { - for (i = 0; i < type->cnt; i++) { - if (!memblock_is_hotpluggable(&type->regions[i])) + for_each_memblock(memory, r) { + if (!memblock_is_hotpluggable(r)) continue; - nid = type->regions[i].nid; + nid = r->nid; - usable_startpfn = PFN_DOWN(type->regions[i].base); + usable_startpfn = PFN_DOWN(r->base); zone_movable_pfn[nid] = zone_movable_pfn[nid] ? min(usable_startpfn, zone_movable_pfn[nid]) : usable_startpfn; @@ -6524,7 +6547,8 @@ static void dump_page_flags(unsigned long flags) printk(")\n"); } -void dump_page_badflags(struct page *page, char *reason, unsigned long badflags) +void dump_page_badflags(struct page *page, const char *reason, + unsigned long badflags) { printk(KERN_ALERT "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n", @@ -6540,8 +6564,8 @@ void dump_page_badflags(struct page *page, char *reason, unsigned long badflags) mem_cgroup_print_bad_page(page); } -void dump_page(struct page *page, char *reason) +void dump_page(struct page *page, const char *reason) { dump_page_badflags(page, reason, 0); } -EXPORT_SYMBOL_GPL(dump_page); +EXPORT_SYMBOL(dump_page); diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index cfd1628..3708264 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -175,7 +175,7 @@ static void free_page_cgroup(void *addr) } } -void __free_page_cgroup(unsigned long pfn) +static void __free_page_cgroup(unsigned long pfn) { struct mem_section *ms; struct page_cgroup *base; @@ -188,9 +188,9 @@ void __free_page_cgroup(unsigned long pfn) ms->page_cgroup = NULL; } -int __meminit online_page_cgroup(unsigned long start_pfn, - unsigned long nr_pages, - int nid) +static int __meminit online_page_cgroup(unsigned long start_pfn, + unsigned long nr_pages, + int nid) { unsigned long start, end, pfn; int fail = 0; @@ -223,8 +223,8 @@ int __meminit online_page_cgroup(unsigned long start_pfn, return -ENOMEM; } -int __meminit offline_page_cgroup(unsigned long start_pfn, - unsigned long nr_pages, int nid) +static int __meminit offline_page_cgroup(unsigned long start_pfn, + unsigned long nr_pages, int nid) { unsigned long start, end, pfn; diff --git a/mm/percpu.c b/mm/percpu.c index 036cfe0..63e24fb 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -102,10 +102,11 @@ struct pcpu_chunk { int free_size; /* free bytes in the chunk */ int contig_hint; /* max contiguous size hint */ void *base_addr; /* base address of this chunk */ - int map_used; /* # of map entries used */ + int map_used; /* # of map entries used before the sentry */ int map_alloc; /* # of map entries allocated */ int *map; /* allocation map */ void *data; /* chunk data */ + int first_free; /* no free below this */ bool immutable; /* no [de]population allowed */ unsigned long populated[]; /* populated bitmap */ }; @@ -356,11 +357,11 @@ static int pcpu_need_to_extend(struct pcpu_chunk *chunk) { int new_alloc; - if (chunk->map_alloc >= chunk->map_used + 2) + if (chunk->map_alloc >= chunk->map_used + 3) return 0; new_alloc = PCPU_DFL_MAP_ALLOC; - while (new_alloc < chunk->map_used + 2) + while (new_alloc < chunk->map_used + 3) new_alloc *= 2; return new_alloc; @@ -418,48 +419,6 @@ out_unlock: } /** - * pcpu_split_block - split a map block - * @chunk: chunk of interest - * @i: index of map block to split - * @head: head size in bytes (can be 0) - * @tail: tail size in bytes (can be 0) - * - * Split the @i'th map block into two or three blocks. If @head is - * non-zero, @head bytes block is inserted before block @i moving it - * to @i+1 and reducing its size by @head bytes. - * - * If @tail is non-zero, the target block, which can be @i or @i+1 - * depending on @head, is reduced by @tail bytes and @tail byte block - * is inserted after the target block. - * - * @chunk->map must have enough free slots to accommodate the split. - * - * CONTEXT: - * pcpu_lock. - */ -static void pcpu_split_block(struct pcpu_chunk *chunk, int i, - int head, int tail) -{ - int nr_extra = !!head + !!tail; - - BUG_ON(chunk->map_alloc < chunk->map_used + nr_extra); - - /* insert new subblocks */ - memmove(&chunk->map[i + nr_extra], &chunk->map[i], - sizeof(chunk->map[0]) * (chunk->map_used - i)); - chunk->map_used += nr_extra; - - if (head) { - chunk->map[i + 1] = chunk->map[i] - head; - chunk->map[i++] = head; - } - if (tail) { - chunk->map[i++] -= tail; - chunk->map[i] = tail; - } -} - -/** * pcpu_alloc_area - allocate area from a pcpu_chunk * @chunk: chunk of interest * @size: wanted size in bytes @@ -483,19 +442,27 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align) int oslot = pcpu_chunk_slot(chunk); int max_contig = 0; int i, off; + bool seen_free = false; + int *p; - for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) { - bool is_last = i + 1 == chunk->map_used; + for (i = chunk->first_free, p = chunk->map + i; i < chunk->map_used; i++, p++) { int head, tail; + int this_size; + + off = *p; + if (off & 1) + continue; /* extra for alignment requirement */ head = ALIGN(off, align) - off; - BUG_ON(i == 0 && head != 0); - if (chunk->map[i] < 0) - continue; - if (chunk->map[i] < head + size) { - max_contig = max(chunk->map[i], max_contig); + this_size = (p[1] & ~1) - off; + if (this_size < head + size) { + if (!seen_free) { + chunk->first_free = i; + seen_free = true; + } + max_contig = max(this_size, max_contig); continue; } @@ -505,44 +472,59 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align) * than sizeof(int), which is very small but isn't too * uncommon for percpu allocations. */ - if (head && (head < sizeof(int) || chunk->map[i - 1] > 0)) { - if (chunk->map[i - 1] > 0) - chunk->map[i - 1] += head; - else { - chunk->map[i - 1] -= head; + if (head && (head < sizeof(int) || !(p[-1] & 1))) { + *p = off += head; + if (p[-1] & 1) chunk->free_size -= head; - } - chunk->map[i] -= head; - off += head; + else + max_contig = max(*p - p[-1], max_contig); + this_size -= head; head = 0; } /* if tail is small, just keep it around */ - tail = chunk->map[i] - head - size; - if (tail < sizeof(int)) + tail = this_size - head - size; + if (tail < sizeof(int)) { tail = 0; + size = this_size - head; + } /* split if warranted */ if (head || tail) { - pcpu_split_block(chunk, i, head, tail); + int nr_extra = !!head + !!tail; + + /* insert new subblocks */ + memmove(p + nr_extra + 1, p + 1, + sizeof(chunk->map[0]) * (chunk->map_used - i)); + chunk->map_used += nr_extra; + if (head) { - i++; - off += head; - max_contig = max(chunk->map[i - 1], max_contig); + if (!seen_free) { + chunk->first_free = i; + seen_free = true; + } + *++p = off += head; + ++i; + max_contig = max(head, max_contig); + } + if (tail) { + p[1] = off + size; + max_contig = max(tail, max_contig); } - if (tail) - max_contig = max(chunk->map[i + 1], max_contig); } + if (!seen_free) + chunk->first_free = i + 1; + /* update hint and mark allocated */ - if (is_last) + if (i + 1 == chunk->map_used) chunk->contig_hint = max_contig; /* fully scanned */ else chunk->contig_hint = max(chunk->contig_hint, max_contig); - chunk->free_size -= chunk->map[i]; - chunk->map[i] = -chunk->map[i]; + chunk->free_size -= size; + *p |= 1; pcpu_chunk_relocate(chunk, oslot); return off; @@ -570,34 +552,50 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align) static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme) { int oslot = pcpu_chunk_slot(chunk); - int i, off; - - for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) - if (off == freeme) - break; + int off = 0; + unsigned i, j; + int to_free = 0; + int *p; + + freeme |= 1; /* we are searching for <given offset, in use> pair */ + + i = 0; + j = chunk->map_used; + while (i != j) { + unsigned k = (i + j) / 2; + off = chunk->map[k]; + if (off < freeme) + i = k + 1; + else if (off > freeme) + j = k; + else + i = j = k; + } BUG_ON(off != freeme); - BUG_ON(chunk->map[i] > 0); - chunk->map[i] = -chunk->map[i]; - chunk->free_size += chunk->map[i]; + if (i < chunk->first_free) + chunk->first_free = i; + p = chunk->map + i; + *p = off &= ~1; + chunk->free_size += (p[1] & ~1) - off; + + /* merge with next? */ + if (!(p[1] & 1)) + to_free++; /* merge with previous? */ - if (i > 0 && chunk->map[i - 1] >= 0) { - chunk->map[i - 1] += chunk->map[i]; - chunk->map_used--; - memmove(&chunk->map[i], &chunk->map[i + 1], - (chunk->map_used - i) * sizeof(chunk->map[0])); + if (i > 0 && !(p[-1] & 1)) { + to_free++; i--; + p--; } - /* merge with next? */ - if (i + 1 < chunk->map_used && chunk->map[i + 1] >= 0) { - chunk->map[i] += chunk->map[i + 1]; - chunk->map_used--; - memmove(&chunk->map[i + 1], &chunk->map[i + 2], - (chunk->map_used - (i + 1)) * sizeof(chunk->map[0])); + if (to_free) { + chunk->map_used -= to_free; + memmove(p + 1, p + 1 + to_free, + (chunk->map_used - i) * sizeof(chunk->map[0])); } - chunk->contig_hint = max(chunk->map[i], chunk->contig_hint); + chunk->contig_hint = max(chunk->map[i + 1] - chunk->map[i] - 1, chunk->contig_hint); pcpu_chunk_relocate(chunk, oslot); } @@ -617,7 +615,9 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void) } chunk->map_alloc = PCPU_DFL_MAP_ALLOC; - chunk->map[chunk->map_used++] = pcpu_unit_size; + chunk->map[0] = 0; + chunk->map[1] = pcpu_unit_size | 1; + chunk->map_used = 1; INIT_LIST_HEAD(&chunk->list); chunk->free_size = pcpu_unit_size; @@ -713,6 +713,16 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved) unsigned long flags; void __percpu *ptr; + /* + * We want the lowest bit of offset available for in-use/free + * indicator, so force >= 16bit alignment and make size even. + */ + if (unlikely(align < 2)) + align = 2; + + if (unlikely(size & 1)) + size++; + if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) { WARN(true, "illegal size (%zu) or align (%zu) for " "percpu allocation\n", size, align); @@ -1343,9 +1353,13 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, } schunk->contig_hint = schunk->free_size; - schunk->map[schunk->map_used++] = -ai->static_size; + schunk->map[0] = 1; + schunk->map[1] = ai->static_size; + schunk->map_used = 1; if (schunk->free_size) - schunk->map[schunk->map_used++] = schunk->free_size; + schunk->map[++schunk->map_used] = 1 | (ai->static_size + schunk->free_size); + else + schunk->map[1] |= 1; /* init dynamic chunk if necessary */ if (dyn_size) { @@ -1358,8 +1372,10 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, bitmap_fill(dchunk->populated, pcpu_unit_pages); dchunk->contig_hint = dchunk->free_size = dyn_size; - dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit; - dchunk->map[dchunk->map_used++] = dchunk->free_size; + dchunk->map[0] = 1; + dchunk->map[1] = pcpu_reserved_chunk_limit; + dchunk->map[2] = (pcpu_reserved_chunk_limit + dchunk->free_size) | 1; + dchunk->map_used = 2; } /* link the first chunk in */ diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index fd26d04..8505c92 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -23,129 +23,44 @@ /** * process_vm_rw_pages - read/write pages from task specified - * @task: task to read/write from - * @mm: mm for task - * @process_pages: struct pages area that can store at least - * nr_pages_to_copy struct page pointers - * @pa: address of page in task to start copying from/to + * @pages: array of pointers to pages we want to copy * @start_offset: offset in page to start copying from/to * @len: number of bytes to copy - * @lvec: iovec array specifying where to copy to/from - * @lvec_cnt: number of elements in iovec array - * @lvec_current: index in iovec array we are up to - * @lvec_offset: offset in bytes from current iovec iov_base we are up to + * @iter: where to copy to/from locally * @vm_write: 0 means copy from, 1 means copy to - * @nr_pages_to_copy: number of pages to copy - * @bytes_copied: returns number of bytes successfully copied * Returns 0 on success, error code otherwise */ -static int process_vm_rw_pages(struct task_struct *task, - struct mm_struct *mm, - struct page **process_pages, - unsigned long pa, - unsigned long start_offset, - unsigned long len, - const struct iovec *lvec, - unsigned long lvec_cnt, - unsigned long *lvec_current, - size_t *lvec_offset, - int vm_write, - unsigned int nr_pages_to_copy, - ssize_t *bytes_copied) +static int process_vm_rw_pages(struct page **pages, + unsigned offset, + size_t len, + struct iov_iter *iter, + int vm_write) { - int pages_pinned; - void *target_kaddr; - int pgs_copied = 0; - int j; - int ret; - ssize_t bytes_to_copy; - ssize_t rc = 0; - - *bytes_copied = 0; - - /* Get the pages we're interested in */ - down_read(&mm->mmap_sem); - pages_pinned = get_user_pages(task, mm, pa, - nr_pages_to_copy, - vm_write, 0, process_pages, NULL); - up_read(&mm->mmap_sem); - - if (pages_pinned != nr_pages_to_copy) { - rc = -EFAULT; - goto end; - } - /* Do the copy for each page */ - for (pgs_copied = 0; - (pgs_copied < nr_pages_to_copy) && (*lvec_current < lvec_cnt); - pgs_copied++) { - /* Make sure we have a non zero length iovec */ - while (*lvec_current < lvec_cnt - && lvec[*lvec_current].iov_len == 0) - (*lvec_current)++; - if (*lvec_current == lvec_cnt) - break; - - /* - * Will copy smallest of: - * - bytes remaining in page - * - bytes remaining in destination iovec - */ - bytes_to_copy = min_t(ssize_t, PAGE_SIZE - start_offset, - len - *bytes_copied); - bytes_to_copy = min_t(ssize_t, bytes_to_copy, - lvec[*lvec_current].iov_len - - *lvec_offset); - - target_kaddr = kmap(process_pages[pgs_copied]) + start_offset; - - if (vm_write) - ret = copy_from_user(target_kaddr, - lvec[*lvec_current].iov_base - + *lvec_offset, - bytes_to_copy); - else - ret = copy_to_user(lvec[*lvec_current].iov_base - + *lvec_offset, - target_kaddr, bytes_to_copy); - kunmap(process_pages[pgs_copied]); - if (ret) { - *bytes_copied += bytes_to_copy - ret; - pgs_copied++; - rc = -EFAULT; - goto end; - } - *bytes_copied += bytes_to_copy; - *lvec_offset += bytes_to_copy; - if (*lvec_offset == lvec[*lvec_current].iov_len) { - /* - * Need to copy remaining part of page into the - * next iovec if there are any bytes left in page - */ - (*lvec_current)++; - *lvec_offset = 0; - start_offset = (start_offset + bytes_to_copy) - % PAGE_SIZE; - if (start_offset) - pgs_copied--; + while (len && iov_iter_count(iter)) { + struct page *page = *pages++; + size_t copy = PAGE_SIZE - offset; + size_t copied; + + if (copy > len) + copy = len; + + if (vm_write) { + if (copy > iov_iter_count(iter)) + copy = iov_iter_count(iter); + copied = iov_iter_copy_from_user(page, iter, + offset, copy); + iov_iter_advance(iter, copied); + set_page_dirty_lock(page); } else { - start_offset = 0; + copied = copy_page_to_iter(page, offset, copy, iter); } + len -= copied; + if (copied < copy && iov_iter_count(iter)) + return -EFAULT; + offset = 0; } - -end: - if (vm_write) { - for (j = 0; j < pages_pinned; j++) { - if (j < pgs_copied) - set_page_dirty_lock(process_pages[j]); - put_page(process_pages[j]); - } - } else { - for (j = 0; j < pages_pinned; j++) - put_page(process_pages[j]); - } - - return rc; + return 0; } /* Maximum number of pages kmalloc'd to hold struct page's during copy */ @@ -155,67 +70,60 @@ end: * process_vm_rw_single_vec - read/write pages from task specified * @addr: start memory address of target process * @len: size of area to copy to/from - * @lvec: iovec array specifying where to copy to/from locally - * @lvec_cnt: number of elements in iovec array - * @lvec_current: index in iovec array we are up to - * @lvec_offset: offset in bytes from current iovec iov_base we are up to + * @iter: where to copy to/from locally * @process_pages: struct pages area that can store at least * nr_pages_to_copy struct page pointers * @mm: mm for task * @task: task to read/write from * @vm_write: 0 means copy from, 1 means copy to - * @bytes_copied: returns number of bytes successfully copied * Returns 0 on success or on failure error code */ static int process_vm_rw_single_vec(unsigned long addr, unsigned long len, - const struct iovec *lvec, - unsigned long lvec_cnt, - unsigned long *lvec_current, - size_t *lvec_offset, + struct iov_iter *iter, struct page **process_pages, struct mm_struct *mm, struct task_struct *task, - int vm_write, - ssize_t *bytes_copied) + int vm_write) { unsigned long pa = addr & PAGE_MASK; unsigned long start_offset = addr - pa; unsigned long nr_pages; - ssize_t bytes_copied_loop; ssize_t rc = 0; - unsigned long nr_pages_copied = 0; - unsigned long nr_pages_to_copy; unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES / sizeof(struct pages *); - *bytes_copied = 0; - /* Work out address and page range required */ if (len == 0) return 0; nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1; - while ((nr_pages_copied < nr_pages) && (*lvec_current < lvec_cnt)) { - nr_pages_to_copy = min(nr_pages - nr_pages_copied, - max_pages_per_loop); + while (!rc && nr_pages && iov_iter_count(iter)) { + int pages = min(nr_pages, max_pages_per_loop); + size_t bytes; - rc = process_vm_rw_pages(task, mm, process_pages, pa, - start_offset, len, - lvec, lvec_cnt, - lvec_current, lvec_offset, - vm_write, nr_pages_to_copy, - &bytes_copied_loop); - start_offset = 0; - *bytes_copied += bytes_copied_loop; + /* Get the pages we're interested in */ + down_read(&mm->mmap_sem); + pages = get_user_pages(task, mm, pa, pages, + vm_write, 0, process_pages, NULL); + up_read(&mm->mmap_sem); - if (rc < 0) { - return rc; - } else { - len -= bytes_copied_loop; - nr_pages_copied += nr_pages_to_copy; - pa += nr_pages_to_copy * PAGE_SIZE; - } + if (pages <= 0) + return -EFAULT; + + bytes = pages * PAGE_SIZE - start_offset; + if (bytes > len) + bytes = len; + + rc = process_vm_rw_pages(process_pages, + start_offset, bytes, iter, + vm_write); + len -= bytes; + start_offset = 0; + nr_pages -= pages; + pa += pages * PAGE_SIZE; + while (pages) + put_page(process_pages[--pages]); } return rc; @@ -228,8 +136,7 @@ static int process_vm_rw_single_vec(unsigned long addr, /** * process_vm_rw_core - core of reading/writing pages from task specified * @pid: PID of process to read/write from/to - * @lvec: iovec array specifying where to copy to/from locally - * @liovcnt: size of lvec array + * @iter: where to copy to/from locally * @rvec: iovec array specifying where to copy to/from in the other process * @riovcnt: size of rvec array * @flags: currently unused @@ -238,8 +145,7 @@ static int process_vm_rw_single_vec(unsigned long addr, * return less bytes than expected if an error occurs during the copying * process. */ -static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec, - unsigned long liovcnt, +static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter, const struct iovec *rvec, unsigned long riovcnt, unsigned long flags, int vm_write) @@ -250,13 +156,10 @@ static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec, struct mm_struct *mm; unsigned long i; ssize_t rc = 0; - ssize_t bytes_copied_loop; - ssize_t bytes_copied = 0; unsigned long nr_pages = 0; unsigned long nr_pages_iov; - unsigned long iov_l_curr_idx = 0; - size_t iov_l_curr_offset = 0; ssize_t iov_len; + size_t total_len = iov_iter_count(iter); /* * Work out how many pages of struct pages we're going to need @@ -310,24 +213,20 @@ static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec, goto put_task_struct; } - for (i = 0; i < riovcnt && iov_l_curr_idx < liovcnt; i++) { + for (i = 0; i < riovcnt && iov_iter_count(iter) && !rc; i++) rc = process_vm_rw_single_vec( (unsigned long)rvec[i].iov_base, rvec[i].iov_len, - lvec, liovcnt, &iov_l_curr_idx, &iov_l_curr_offset, - process_pages, mm, task, vm_write, &bytes_copied_loop); - bytes_copied += bytes_copied_loop; - if (rc != 0) { - /* If we have managed to copy any data at all then - we return the number of bytes copied. Otherwise - we return the error code */ - if (bytes_copied) - rc = bytes_copied; - goto put_mm; - } - } + iter, process_pages, mm, task, vm_write); + + /* copied = space before - space after */ + total_len -= iov_iter_count(iter); + + /* If we have managed to copy any data at all then + we return the number of bytes copied. Otherwise + we return the error code */ + if (total_len) + rc = total_len; - rc = bytes_copied; -put_mm: mmput(mm); put_task_struct: @@ -363,6 +262,7 @@ static ssize_t process_vm_rw(pid_t pid, struct iovec iovstack_r[UIO_FASTIOV]; struct iovec *iov_l = iovstack_l; struct iovec *iov_r = iovstack_r; + struct iov_iter iter; ssize_t rc; if (flags != 0) @@ -378,13 +278,14 @@ static ssize_t process_vm_rw(pid_t pid, if (rc <= 0) goto free_iovecs; + iov_iter_init(&iter, iov_l, liovcnt, rc, 0); + rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV, iovstack_r, &iov_r); if (rc <= 0) goto free_iovecs; - rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags, - vm_write); + rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write); free_iovecs: if (iov_r != iovstack_r) @@ -412,7 +313,7 @@ SYSCALL_DEFINE6(process_vm_writev, pid_t, pid, #ifdef CONFIG_COMPAT -asmlinkage ssize_t +static ssize_t compat_process_vm_rw(compat_pid_t pid, const struct compat_iovec __user *lvec, unsigned long liovcnt, @@ -424,6 +325,7 @@ compat_process_vm_rw(compat_pid_t pid, struct iovec iovstack_r[UIO_FASTIOV]; struct iovec *iov_l = iovstack_l; struct iovec *iov_r = iovstack_r; + struct iov_iter iter; ssize_t rc = -EFAULT; if (flags != 0) @@ -439,14 +341,14 @@ compat_process_vm_rw(compat_pid_t pid, &iov_l); if (rc <= 0) goto free_iovecs; + iov_iter_init(&iter, iov_l, liovcnt, rc, 0); rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV, iovstack_r, &iov_r); if (rc <= 0) goto free_iovecs; - rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags, - vm_write); + rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write); free_iovecs: if (iov_r != iovstack_r) @@ -456,25 +358,23 @@ free_iovecs: return rc; } -asmlinkage ssize_t -compat_sys_process_vm_readv(compat_pid_t pid, - const struct compat_iovec __user *lvec, - unsigned long liovcnt, - const struct compat_iovec __user *rvec, - unsigned long riovcnt, - unsigned long flags) +COMPAT_SYSCALL_DEFINE6(process_vm_readv, compat_pid_t, pid, + const struct compat_iovec __user *, lvec, + compat_ulong_t, liovcnt, + const struct compat_iovec __user *, rvec, + compat_ulong_t, riovcnt, + compat_ulong_t, flags) { return compat_process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 0); } -asmlinkage ssize_t -compat_sys_process_vm_writev(compat_pid_t pid, - const struct compat_iovec __user *lvec, - unsigned long liovcnt, - const struct compat_iovec __user *rvec, - unsigned long riovcnt, - unsigned long flags) +COMPAT_SYSCALL_DEFINE6(process_vm_writev, compat_pid_t, pid, + const struct compat_iovec __user *, lvec, + compat_ulong_t, liovcnt, + const struct compat_iovec __user *, rvec, + compat_ulong_t, riovcnt, + compat_ulong_t, flags) { return compat_process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 1); diff --git a/mm/readahead.c b/mm/readahead.c index 0de2360..0ca36a7 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -8,9 +8,7 @@ */ #include <linux/kernel.h> -#include <linux/fs.h> #include <linux/gfp.h> -#include <linux/mm.h> #include <linux/export.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> @@ -20,6 +18,8 @@ #include <linux/syscalls.h> #include <linux/file.h> +#include "internal.h" + /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. @@ -149,8 +149,7 @@ out: * * Returns the number of pages requested, or the maximum amount of I/O allowed. */ -static int -__do_page_cache_readahead(struct address_space *mapping, struct file *filp, +int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read, unsigned long lookahead_size) { @@ -179,7 +178,7 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp, rcu_read_lock(); page = radix_tree_lookup(&mapping->page_tree, page_offset); rcu_read_unlock(); - if (page) + if (page && !radix_tree_exceptional_entry(page)) continue; page = page_cache_alloc_readahead(mapping); @@ -233,28 +232,14 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp, return 0; } +#define MAX_READAHEAD ((512*4096)/PAGE_CACHE_SIZE) /* * Given a desired number of PAGE_CACHE_SIZE readahead pages, return a * sensible upper limit. */ unsigned long max_sane_readahead(unsigned long nr) { - return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE_FILE) - + node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2); -} - -/* - * Submit IO for the read-ahead request in file_ra_state. - */ -unsigned long ra_submit(struct file_ra_state *ra, - struct address_space *mapping, struct file *filp) -{ - int actual; - - actual = __do_page_cache_readahead(mapping, filp, - ra->start, ra->size, ra->async_size); - - return actual; + return min(nr, MAX_READAHEAD); } /* @@ -347,7 +332,7 @@ static pgoff_t count_history_pages(struct address_space *mapping, pgoff_t head; rcu_read_lock(); - head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max); + head = page_cache_prev_hole(mapping, offset - 1, max); rcu_read_unlock(); return offset - 1 - head; @@ -427,7 +412,7 @@ ondemand_readahead(struct address_space *mapping, pgoff_t start; rcu_read_lock(); - start = radix_tree_next_hole(&mapping->page_tree, offset+1,max); + start = page_cache_next_hole(mapping, offset + 1, max); rcu_read_unlock(); if (!start || start - offset > max) @@ -1165,6 +1165,16 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } set_pte_at(mm, address, pte, swp_entry_to_pte(make_hwpoison_entry(page))); + } else if (pte_unused(pteval)) { + /* + * The guest indicated that the page content is of no + * interest anymore. Simply discard the pte, vmscan + * will take care of the rest. + */ + if (PageAnon(page)) + dec_mm_counter(mm, MM_ANONPAGES); + else + dec_mm_counter(mm, MM_FILEPAGES); } else if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(page) }; pte_t swp_pte; @@ -1322,9 +1332,19 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, BUG_ON(!page || PageAnon(page)); if (locked_vma) { - mlock_vma_page(page); /* no-op if already mlocked */ - if (page == check_page) + if (page == check_page) { + /* we know we have check_page locked */ + mlock_vma_page(page); ret = SWAP_MLOCK; + } else if (trylock_page(page)) { + /* + * If we can lock the page, perform mlock. + * Otherwise leave the page alone, it will be + * eventually encountered again later. + */ + mlock_vma_page(page); + unlock_page(page); + } continue; /* don't unmap */ } @@ -1360,8 +1380,9 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, } static int try_to_unmap_nonlinear(struct page *page, - struct address_space *mapping, struct vm_area_struct *vma) + struct address_space *mapping, void *arg) { + struct vm_area_struct *vma; int ret = SWAP_AGAIN; unsigned long cursor; unsigned long max_nl_cursor = 0; @@ -1663,7 +1684,7 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) if (list_empty(&mapping->i_mmap_nonlinear)) goto done; - ret = rwc->file_nonlinear(page, mapping, vma); + ret = rwc->file_nonlinear(page, mapping, rwc->arg); done: mutex_unlock(&mapping->i_mmap_mutex); @@ -242,19 +242,17 @@ static int shmem_radix_tree_replace(struct address_space *mapping, pgoff_t index, void *expected, void *replacement) { void **pslot; - void *item = NULL; + void *item; VM_BUG_ON(!expected); + VM_BUG_ON(!replacement); pslot = radix_tree_lookup_slot(&mapping->page_tree, index); - if (pslot) - item = radix_tree_deref_slot_protected(pslot, - &mapping->tree_lock); + if (!pslot) + return -ENOENT; + item = radix_tree_deref_slot_protected(pslot, &mapping->tree_lock); if (item != expected) return -ENOENT; - if (replacement) - radix_tree_replace_slot(pslot, replacement); - else - radix_tree_delete(&mapping->page_tree, index); + radix_tree_replace_slot(pslot, replacement); return 0; } @@ -331,84 +329,20 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap) } /* - * Like find_get_pages, but collecting swap entries as well as pages. - */ -static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping, - pgoff_t start, unsigned int nr_pages, - struct page **pages, pgoff_t *indices) -{ - void **slot; - unsigned int ret = 0; - struct radix_tree_iter iter; - - if (!nr_pages) - return 0; - - rcu_read_lock(); -restart: - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { - struct page *page; -repeat: - page = radix_tree_deref_slot(slot); - if (unlikely(!page)) - continue; - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) - goto restart; - /* - * Otherwise, we must be storing a swap entry - * here as an exceptional entry: so return it - * without attempting to raise page count. - */ - goto export; - } - if (!page_cache_get_speculative(page)) - goto repeat; - - /* Has the page moved? */ - if (unlikely(page != *slot)) { - page_cache_release(page); - goto repeat; - } -export: - indices[ret] = iter.index; - pages[ret] = page; - if (++ret == nr_pages) - break; - } - rcu_read_unlock(); - return ret; -} - -/* * Remove swap entry from radix tree, free the swap and its page cache. */ static int shmem_free_swap(struct address_space *mapping, pgoff_t index, void *radswap) { - int error; + void *old; spin_lock_irq(&mapping->tree_lock); - error = shmem_radix_tree_replace(mapping, index, radswap, NULL); + old = radix_tree_delete_item(&mapping->page_tree, index, radswap); spin_unlock_irq(&mapping->tree_lock); - if (!error) - free_swap_and_cache(radix_to_swp_entry(radswap)); - return error; -} - -/* - * Pagevec may contain swap entries, so shuffle up pages before releasing. - */ -static void shmem_deswap_pagevec(struct pagevec *pvec) -{ - int i, j; - - for (i = 0, j = 0; i < pagevec_count(pvec); i++) { - struct page *page = pvec->pages[i]; - if (!radix_tree_exceptional_entry(page)) - pvec->pages[j++] = page; - } - pvec->nr = j; + if (old != radswap) + return -ENOENT; + free_swap_and_cache(radix_to_swp_entry(radswap)); + return 0; } /* @@ -429,12 +363,12 @@ void shmem_unlock_mapping(struct address_space *mapping) * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it * has finished, if it hits a row of PAGEVEC_SIZE swap entries. */ - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - PAGEVEC_SIZE, pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, + PAGEVEC_SIZE, pvec.pages, indices); if (!pvec.nr) break; index = indices[pvec.nr - 1] + 1; - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); check_move_unevictable_pages(pvec.pages, pvec.nr); pagevec_release(&pvec); cond_resched(); @@ -466,9 +400,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, pagevec_init(&pvec, 0); index = start; while (index < end) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + pvec.pages, indices); if (!pvec.nr) break; mem_cgroup_uncharge_start(); @@ -497,7 +431,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -535,9 +469,10 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, index = start; for ( ; ; ) { cond_resched(); - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + + pvec.nr = find_get_entries(mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.pages, indices); if (!pvec.nr) { if (index == start || unfalloc) break; @@ -545,7 +480,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, continue; } if ((index == start || unfalloc) && indices[0] >= end) { - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); break; } @@ -574,7 +509,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; @@ -748,7 +683,7 @@ int shmem_unuse(swp_entry_t swap, struct page *page) * the shmem_swaplist_mutex which might hold up shmem_writepage(). * Charged back to the user (not to caller) when swap account is used. */ - error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL); + error = mem_cgroup_charge_file(page, current->mm, GFP_KERNEL); if (error) goto out; /* No radix_tree_preload: swap entry keeps a place for page in tree */ @@ -1080,7 +1015,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, return -EFBIG; repeat: swap.val = 0; - page = find_lock_page(mapping, index); + page = find_lock_entry(mapping, index); if (radix_tree_exceptional_entry(page)) { swap = radix_to_swp_entry(page); page = NULL; @@ -1145,7 +1080,7 @@ repeat: goto failed; } - error = mem_cgroup_cache_charge(page, current->mm, + error = mem_cgroup_charge_file(page, current->mm, gfp & GFP_RECLAIM_MASK); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, @@ -1199,7 +1134,7 @@ repeat: SetPageSwapBacked(page); __set_page_locked(page); - error = mem_cgroup_cache_charge(page, current->mm, + error = mem_cgroup_charge_file(page, current->mm, gfp & GFP_RECLAIM_MASK); if (error) goto decused; @@ -1417,6 +1352,11 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode return inode; } +bool shmem_mapping(struct address_space *mapping) +{ + return mapping->backing_dev_info == &shmem_backing_dev_info; +} + #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; @@ -1462,13 +1402,25 @@ shmem_write_end(struct file *file, struct address_space *mapping, return copied; } -static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc, read_actor_t actor) +static ssize_t shmem_file_aio_read(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, loff_t pos) { - struct inode *inode = file_inode(filp); + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; pgoff_t index; unsigned long offset; enum sgp_type sgp = SGP_READ; + int error; + ssize_t retval; + size_t count; + loff_t *ppos = &iocb->ki_pos; + struct iov_iter iter; + + retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); + if (retval) + return retval; + iov_iter_init(&iter, iov, nr_segs, count, 0); /* * Might this read be for a stacking filesystem? Then when reading @@ -1496,10 +1448,10 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ break; } - desc->error = shmem_getpage(inode, index, &page, sgp, NULL); - if (desc->error) { - if (desc->error == -EINVAL) - desc->error = 0; + error = shmem_getpage(inode, index, &page, sgp, NULL); + if (error) { + if (error == -EINVAL) + error = 0; break; } if (page) @@ -1543,61 +1495,26 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... - * - * The actor routine returns how many bytes were actually used.. - * NOTE! This may not be the same as how much of a user buffer - * we filled up (we may be padding etc), so we can only update - * "pos" here (the actor routine has to update the user buffer - * pointers and the remaining count). */ - ret = actor(desc, page, offset, nr); + ret = copy_page_to_iter(page, offset, nr, &iter); + retval += ret; offset += ret; index += offset >> PAGE_CACHE_SHIFT; offset &= ~PAGE_CACHE_MASK; page_cache_release(page); - if (ret != nr || !desc->count) + if (!iov_iter_count(&iter)) break; - + if (ret < nr) { + error = -EFAULT; + break; + } cond_resched(); } *ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset; - file_accessed(filp); -} - -static ssize_t shmem_file_aio_read(struct kiocb *iocb, - const struct iovec *iov, unsigned long nr_segs, loff_t pos) -{ - struct file *filp = iocb->ki_filp; - ssize_t retval; - unsigned long seg; - size_t count; - loff_t *ppos = &iocb->ki_pos; - - retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); - if (retval) - return retval; - - for (seg = 0; seg < nr_segs; seg++) { - read_descriptor_t desc; - - desc.written = 0; - desc.arg.buf = iov[seg].iov_base; - desc.count = iov[seg].iov_len; - if (desc.count == 0) - continue; - desc.error = 0; - do_shmem_file_read(filp, ppos, &desc, file_read_actor); - retval += desc.written; - if (desc.error) { - retval = retval ?: desc.error; - break; - } - if (desc.count > 0) - break; - } - return retval; + file_accessed(file); + return retval ? retval : error; } static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, @@ -1636,7 +1553,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, index = *ppos >> PAGE_CACHE_SHIFT; loff = *ppos & ~PAGE_CACHE_MASK; req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - nr_pages = min(req_pages, pipe->buffers); + nr_pages = min(req_pages, spd.nr_pages_max); spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, spd.pages); @@ -1729,7 +1646,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, pagevec_init(&pvec, 0); pvec.nr = 1; /* start small: we may be there already */ while (!done) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + pvec.nr = find_get_entries(mapping, index, pvec.nr, pvec.pages, indices); if (!pvec.nr) { if (whence == SEEK_DATA) @@ -1756,7 +1673,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, break; } } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); pvec.nr = PAGEVEC_SIZE; cond_resched(); @@ -2783,6 +2700,7 @@ static const struct super_operations shmem_ops = { static const struct vm_operations_struct shmem_vm_ops = { .fault = shmem_fault, + .map_pages = filemap_map_pages, #ifdef CONFIG_NUMA .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, @@ -3027,7 +3027,7 @@ out: #ifdef CONFIG_NUMA /* - * Try allocating on another node if PF_SPREAD_SLAB|PF_MEMPOLICY. + * Try allocating on another node if PF_SPREAD_SLAB is a mempolicy is set. * * If we are in_interrupt, then process context, including cpusets and * mempolicy, may not apply and should not be used for allocation policy. @@ -3042,7 +3042,7 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags) if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD)) nid_alloc = cpuset_slab_spread_node(); else if (current->mempolicy) - nid_alloc = slab_node(); + nid_alloc = mempolicy_slab_node(); if (nid_alloc != nid_here) return ____cache_alloc_node(cachep, flags, nid_alloc); return NULL; @@ -3073,8 +3073,8 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK); retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); - zonelist = node_zonelist(slab_node(), flags); + cpuset_mems_cookie = read_mems_allowed_begin(); + zonelist = node_zonelist(mempolicy_slab_node(), flags); retry: /* @@ -3131,7 +3131,7 @@ retry: } } - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj)) + if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return obj; } @@ -3259,7 +3259,7 @@ __do_cache_alloc(struct kmem_cache *cache, gfp_t flags) { void *objp; - if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) { + if (current->mempolicy || unlikely(current->flags & PF_SPREAD_SLAB)) { objp = alternate_node_alloc(cache, flags); if (objp) goto out; @@ -55,12 +55,12 @@ extern void create_boot_cache(struct kmem_cache *, const char *name, struct mem_cgroup; #ifdef CONFIG_SLUB struct kmem_cache * -__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size, - size_t align, unsigned long flags, void (*ctor)(void *)); +__kmem_cache_alias(const char *name, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *)); #else static inline struct kmem_cache * -__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size, - size_t align, unsigned long flags, void (*ctor)(void *)) +__kmem_cache_alias(const char *name, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *)) { return NULL; } #endif @@ -119,13 +119,6 @@ static inline bool is_root_cache(struct kmem_cache *s) return !s->memcg_params || s->memcg_params->is_root_cache; } -static inline bool cache_match_memcg(struct kmem_cache *cachep, - struct mem_cgroup *memcg) -{ - return (is_root_cache(cachep) && !memcg) || - (cachep->memcg_params->memcg == memcg); -} - static inline void memcg_bind_pages(struct kmem_cache *s, int order) { if (!is_root_cache(s)) @@ -204,12 +197,6 @@ static inline bool is_root_cache(struct kmem_cache *s) return true; } -static inline bool cache_match_memcg(struct kmem_cache *cachep, - struct mem_cgroup *memcg) -{ - return true; -} - static inline void memcg_bind_pages(struct kmem_cache *s, int order) { } diff --git a/mm/slab_common.c b/mm/slab_common.c index 1ec3c61..f3cfccf 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -29,8 +29,7 @@ DEFINE_MUTEX(slab_mutex); struct kmem_cache *kmem_cache; #ifdef CONFIG_DEBUG_VM -static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, - size_t size) +static int kmem_cache_sanity_check(const char *name, size_t size) { struct kmem_cache *s = NULL; @@ -57,13 +56,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, } #if !defined(CONFIG_SLUB) || !defined(CONFIG_SLUB_DEBUG_ON) - /* - * For simplicity, we won't check this in the list of memcg - * caches. We have control over memcg naming, and if there - * aren't duplicates in the global list, there won't be any - * duplicates in the memcg lists as well. - */ - if (!memcg && !strcmp(s->name, name)) { + if (!strcmp(s->name, name)) { pr_err("%s (%s): Cache name already exists.\n", __func__, name); dump_stack(); @@ -77,8 +70,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, return 0; } #else -static inline int kmem_cache_sanity_check(struct mem_cgroup *memcg, - const char *name, size_t size) +static inline int kmem_cache_sanity_check(const char *name, size_t size) { return 0; } @@ -139,6 +131,46 @@ unsigned long calculate_alignment(unsigned long flags, return ALIGN(align, sizeof(void *)); } +static struct kmem_cache * +do_kmem_cache_create(char *name, size_t object_size, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *), + struct mem_cgroup *memcg, struct kmem_cache *root_cache) +{ + struct kmem_cache *s; + int err; + + err = -ENOMEM; + s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL); + if (!s) + goto out; + + s->name = name; + s->object_size = object_size; + s->size = size; + s->align = align; + s->ctor = ctor; + + err = memcg_alloc_cache_params(memcg, s, root_cache); + if (err) + goto out_free_cache; + + err = __kmem_cache_create(s, flags); + if (err) + goto out_free_cache; + + s->refcount = 1; + list_add(&s->list, &slab_caches); + memcg_register_cache(s); +out: + if (err) + return ERR_PTR(err); + return s; + +out_free_cache: + memcg_free_cache_params(s); + kfree(s); + goto out; +} /* * kmem_cache_create - Create a cache. @@ -164,34 +196,21 @@ unsigned long calculate_alignment(unsigned long flags, * cacheline. This can be beneficial if you're counting cycles as closely * as davem. */ - struct kmem_cache * -kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size, - size_t align, unsigned long flags, void (*ctor)(void *), - struct kmem_cache *parent_cache) +kmem_cache_create(const char *name, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *)) { - struct kmem_cache *s = NULL; + struct kmem_cache *s; + char *cache_name; int err; get_online_cpus(); mutex_lock(&slab_mutex); - err = kmem_cache_sanity_check(memcg, name, size); + err = kmem_cache_sanity_check(name, size); if (err) goto out_unlock; - if (memcg) { - /* - * Since per-memcg caches are created asynchronously on first - * allocation (see memcg_kmem_get_cache()), several threads can - * try to create the same cache, but only one of them may - * succeed. Therefore if we get here and see the cache has - * already been created, we silently return NULL. - */ - if (cache_from_memcg_idx(parent_cache, memcg_cache_id(memcg))) - goto out_unlock; - } - /* * Some allocators will constraint the set of valid flags to a subset * of all flags. We expect them to define CACHE_CREATE_MASK in this @@ -200,50 +219,29 @@ kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size, */ flags &= CACHE_CREATE_MASK; - s = __kmem_cache_alias(memcg, name, size, align, flags, ctor); + s = __kmem_cache_alias(name, size, align, flags, ctor); if (s) goto out_unlock; - err = -ENOMEM; - s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL); - if (!s) + cache_name = kstrdup(name, GFP_KERNEL); + if (!cache_name) { + err = -ENOMEM; goto out_unlock; + } - s->object_size = s->size = size; - s->align = calculate_alignment(flags, align, size); - s->ctor = ctor; - - s->name = kstrdup(name, GFP_KERNEL); - if (!s->name) - goto out_free_cache; - - err = memcg_alloc_cache_params(memcg, s, parent_cache); - if (err) - goto out_free_cache; - - err = __kmem_cache_create(s, flags); - if (err) - goto out_free_cache; - - s->refcount = 1; - list_add(&s->list, &slab_caches); - memcg_register_cache(s); + s = do_kmem_cache_create(cache_name, size, size, + calculate_alignment(flags, align, size), + flags, ctor, NULL, NULL); + if (IS_ERR(s)) { + err = PTR_ERR(s); + kfree(cache_name); + } out_unlock: mutex_unlock(&slab_mutex); put_online_cpus(); if (err) { - /* - * There is no point in flooding logs with warnings or - * especially crashing the system if we fail to create a cache - * for a memcg. In this case we will be accounting the memcg - * allocation to the root cgroup until we succeed to create its - * own cache, but it isn't that critical. - */ - if (!memcg) - return NULL; - if (flags & SLAB_PANIC) panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n", name, err); @@ -255,52 +253,112 @@ out_unlock: return NULL; } return s; +} +EXPORT_SYMBOL(kmem_cache_create); -out_free_cache: - memcg_free_cache_params(s); - kfree(s->name); - kmem_cache_free(kmem_cache, s); - goto out_unlock; +#ifdef CONFIG_MEMCG_KMEM +/* + * kmem_cache_create_memcg - Create a cache for a memory cgroup. + * @memcg: The memory cgroup the new cache is for. + * @root_cache: The parent of the new cache. + * + * This function attempts to create a kmem cache that will serve allocation + * requests going from @memcg to @root_cache. The new cache inherits properties + * from its parent. + */ +void kmem_cache_create_memcg(struct mem_cgroup *memcg, struct kmem_cache *root_cache) +{ + struct kmem_cache *s; + char *cache_name; + + get_online_cpus(); + mutex_lock(&slab_mutex); + + /* + * Since per-memcg caches are created asynchronously on first + * allocation (see memcg_kmem_get_cache()), several threads can try to + * create the same cache, but only one of them may succeed. + */ + if (cache_from_memcg_idx(root_cache, memcg_cache_id(memcg))) + goto out_unlock; + + cache_name = memcg_create_cache_name(memcg, root_cache); + if (!cache_name) + goto out_unlock; + + s = do_kmem_cache_create(cache_name, root_cache->object_size, + root_cache->size, root_cache->align, + root_cache->flags, root_cache->ctor, + memcg, root_cache); + if (IS_ERR(s)) { + kfree(cache_name); + goto out_unlock; + } + + s->allocflags |= __GFP_KMEMCG; + +out_unlock: + mutex_unlock(&slab_mutex); + put_online_cpus(); } -struct kmem_cache * -kmem_cache_create(const char *name, size_t size, size_t align, - unsigned long flags, void (*ctor)(void *)) +static int kmem_cache_destroy_memcg_children(struct kmem_cache *s) { - return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor, NULL); + int rc; + + if (!s->memcg_params || + !s->memcg_params->is_root_cache) + return 0; + + mutex_unlock(&slab_mutex); + rc = __kmem_cache_destroy_memcg_children(s); + mutex_lock(&slab_mutex); + + return rc; } -EXPORT_SYMBOL(kmem_cache_create); +#else +static int kmem_cache_destroy_memcg_children(struct kmem_cache *s) +{ + return 0; +} +#endif /* CONFIG_MEMCG_KMEM */ void kmem_cache_destroy(struct kmem_cache *s) { - /* Destroy all the children caches if we aren't a memcg cache */ - kmem_cache_destroy_memcg_children(s); - get_online_cpus(); mutex_lock(&slab_mutex); + s->refcount--; - if (!s->refcount) { - list_del(&s->list); - - if (!__kmem_cache_shutdown(s)) { - memcg_unregister_cache(s); - mutex_unlock(&slab_mutex); - if (s->flags & SLAB_DESTROY_BY_RCU) - rcu_barrier(); - - memcg_free_cache_params(s); - kfree(s->name); - kmem_cache_free(kmem_cache, s); - } else { - list_add(&s->list, &slab_caches); - mutex_unlock(&slab_mutex); - printk(KERN_ERR "kmem_cache_destroy %s: Slab cache still has objects\n", - s->name); - dump_stack(); - } - } else { - mutex_unlock(&slab_mutex); + if (s->refcount) + goto out_unlock; + + if (kmem_cache_destroy_memcg_children(s) != 0) + goto out_unlock; + + list_del(&s->list); + memcg_unregister_cache(s); + + if (__kmem_cache_shutdown(s) != 0) { + list_add(&s->list, &slab_caches); + memcg_register_cache(s); + printk(KERN_ERR "kmem_cache_destroy %s: " + "Slab cache still has objects\n", s->name); + dump_stack(); + goto out_unlock; } + + mutex_unlock(&slab_mutex); + if (s->flags & SLAB_DESTROY_BY_RCU) + rcu_barrier(); + + memcg_free_cache_params(s); + kfree(s->name); + kmem_cache_free(kmem_cache, s); + goto out_put_cpus; + +out_unlock: + mutex_unlock(&slab_mutex); +out_put_cpus: put_online_cpus(); } EXPORT_SYMBOL(kmem_cache_destroy); @@ -224,7 +224,11 @@ static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { } static inline void stat(const struct kmem_cache *s, enum stat_item si) { #ifdef CONFIG_SLUB_STATS - __this_cpu_inc(s->cpu_slab->stat[si]); + /* + * The rmw is racy on a preemptible kernel but this is acceptable, so + * avoid this_cpu_add()'s irq-disable overhead. + */ + raw_cpu_inc(s->cpu_slab->stat[si]); #endif } @@ -1004,21 +1008,19 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) static void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) { - lockdep_assert_held(&n->list_lock); - if (!(s->flags & SLAB_STORE_USER)) return; + lockdep_assert_held(&n->list_lock); list_add(&page->lru, &n->full); } static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) { - lockdep_assert_held(&n->list_lock); - if (!(s->flags & SLAB_STORE_USER)) return; + lockdep_assert_held(&n->list_lock); list_del(&page->lru); } @@ -1520,11 +1522,9 @@ static void discard_slab(struct kmem_cache *s, struct page *page) /* * Management of partially allocated slabs. */ -static inline void add_partial(struct kmem_cache_node *n, - struct page *page, int tail) +static inline void +__add_partial(struct kmem_cache_node *n, struct page *page, int tail) { - lockdep_assert_held(&n->list_lock); - n->nr_partial++; if (tail == DEACTIVATE_TO_TAIL) list_add_tail(&page->lru, &n->partial); @@ -1532,15 +1532,27 @@ static inline void add_partial(struct kmem_cache_node *n, list_add(&page->lru, &n->partial); } -static inline void remove_partial(struct kmem_cache_node *n, - struct page *page) +static inline void add_partial(struct kmem_cache_node *n, + struct page *page, int tail) { lockdep_assert_held(&n->list_lock); + __add_partial(n, page, tail); +} +static inline void +__remove_partial(struct kmem_cache_node *n, struct page *page) +{ list_del(&page->lru); n->nr_partial--; } +static inline void remove_partial(struct kmem_cache_node *n, + struct page *page) +{ + lockdep_assert_held(&n->list_lock); + __remove_partial(n, page); +} + /* * Remove slab from the partial list, freeze it and * return the pointer to the freelist. @@ -1676,8 +1688,8 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, return NULL; do { - cpuset_mems_cookie = get_mems_allowed(); - zonelist = node_zonelist(slab_node(), flags); + cpuset_mems_cookie = read_mems_allowed_begin(); + zonelist = node_zonelist(mempolicy_slab_node(), flags); for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { struct kmem_cache_node *n; @@ -1688,19 +1700,17 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, object = get_partial_node(s, n, c, flags); if (object) { /* - * Return the object even if - * put_mems_allowed indicated that - * the cpuset mems_allowed was - * updated in parallel. It's a - * harmless race between the alloc - * and the cpuset update. + * Don't check read_mems_allowed_retry() + * here - if mems_allowed was updated in + * parallel, that was a harmless race + * between allocation and the cpuset + * update */ - put_mems_allowed(cpuset_mems_cookie); return object; } } } - } while (!put_mems_allowed(cpuset_mems_cookie)); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); #endif return NULL; } @@ -2906,12 +2916,10 @@ static void early_kmem_cache_node_alloc(int node) inc_slabs_node(kmem_cache_node, node, page->objects); /* - * the lock is for lockdep's sake, not for any actual - * race protection + * No locks need to be taken here as it has just been + * initialized and there is no concurrent access. */ - spin_lock(&n->list_lock); - add_partial(n, page, DEACTIVATE_TO_HEAD); - spin_unlock(&n->list_lock); + __add_partial(n, page, DEACTIVATE_TO_HEAD); } static void free_kmem_cache_nodes(struct kmem_cache *s) @@ -3197,7 +3205,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) list_for_each_entry_safe(page, h, &n->partial, lru) { if (!page->inuse) { - remove_partial(n, page); + __remove_partial(n, page); discard_slab(s, page); } else { list_slab_objects(s, page, @@ -3233,8 +3241,9 @@ int __kmem_cache_shutdown(struct kmem_cache *s) if (!rc) { /* - * We do the same lock strategy around sysfs_slab_add, see - * __kmem_cache_create. Because this is pretty much the last + * Since slab_attr_store may take the slab_mutex, we should + * release the lock while removing the sysfs entry in order to + * avoid a deadlock. Because this is pretty much the last * operation we do and the lock will be released shortly after * that in slab_common.c, we could just move sysfs_slab_remove * to a later point in common code. We should do that when we @@ -3680,6 +3689,9 @@ static int slab_unmergeable(struct kmem_cache *s) if (slub_nomerge || (s->flags & SLUB_NEVER_MERGE)) return 1; + if (!is_root_cache(s)) + return 1; + if (s->ctor) return 1; @@ -3692,9 +3704,8 @@ static int slab_unmergeable(struct kmem_cache *s) return 0; } -static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size, - size_t align, unsigned long flags, const char *name, - void (*ctor)(void *)) +static struct kmem_cache *find_mergeable(size_t size, size_t align, + unsigned long flags, const char *name, void (*ctor)(void *)) { struct kmem_cache *s; @@ -3717,7 +3728,7 @@ static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size, continue; if ((flags & SLUB_MERGE_SAME) != (s->flags & SLUB_MERGE_SAME)) - continue; + continue; /* * Check if alignment is compatible. * Courtesy of Adrian Drzewiecki @@ -3728,23 +3739,24 @@ static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size, if (s->size - size >= sizeof(void *)) continue; - if (!cache_match_memcg(s, memcg)) - continue; - return s; } return NULL; } struct kmem_cache * -__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size, - size_t align, unsigned long flags, void (*ctor)(void *)) +__kmem_cache_alias(const char *name, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *)) { struct kmem_cache *s; - s = find_mergeable(memcg, size, align, flags, name, ctor); + s = find_mergeable(size, align, flags, name, ctor); if (s) { + int i; + struct kmem_cache *c; + s->refcount++; + /* * Adjust the object sizes so that we clear * the complete object on kzalloc. @@ -3752,6 +3764,15 @@ __kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size, s->object_size = max(s->object_size, (int)size); s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *))); + for_each_memcg_cache_index(i) { + c = cache_from_memcg_idx(s, i); + if (!c) + continue; + c->object_size = s->object_size; + c->inuse = max_t(int, c->inuse, + ALIGN(size, sizeof(void *))); + } + if (sysfs_slab_alias(s, name)) { s->refcount--; s = NULL; @@ -3774,10 +3795,7 @@ int __kmem_cache_create(struct kmem_cache *s, unsigned long flags) return 0; memcg_propagate_slab_attrs(s); - mutex_unlock(&slab_mutex); err = sysfs_slab_add(s); - mutex_lock(&slab_mutex); - if (err) kmem_cache_close(s); @@ -5124,6 +5142,15 @@ static const struct kset_uevent_ops slab_uevent_ops = { static struct kset *slab_kset; +static inline struct kset *cache_kset(struct kmem_cache *s) +{ +#ifdef CONFIG_MEMCG_KMEM + if (!is_root_cache(s)) + return s->memcg_params->root_cache->memcg_kset; +#endif + return slab_kset; +} + #define ID_STR_LENGTH 64 /* Create a unique string id for a slab cache: @@ -5189,26 +5216,39 @@ static int sysfs_slab_add(struct kmem_cache *s) name = create_unique_id(s); } - s->kobj.kset = slab_kset; + s->kobj.kset = cache_kset(s); err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name); - if (err) { - kobject_put(&s->kobj); - return err; - } + if (err) + goto out_put_kobj; err = sysfs_create_group(&s->kobj, &slab_attr_group); - if (err) { - kobject_del(&s->kobj); - kobject_put(&s->kobj); - return err; + if (err) + goto out_del_kobj; + +#ifdef CONFIG_MEMCG_KMEM + if (is_root_cache(s)) { + s->memcg_kset = kset_create_and_add("cgroup", NULL, &s->kobj); + if (!s->memcg_kset) { + err = -ENOMEM; + goto out_del_kobj; + } } +#endif + kobject_uevent(&s->kobj, KOBJ_ADD); if (!unmergeable) { /* Setup first alias */ sysfs_slab_alias(s, s->name); - kfree(name); } - return 0; +out: + if (!unmergeable) + kfree(name); + return err; +out_del_kobj: + kobject_del(&s->kobj); +out_put_kobj: + kobject_put(&s->kobj); + goto out; } static void sysfs_slab_remove(struct kmem_cache *s) @@ -5220,6 +5260,9 @@ static void sysfs_slab_remove(struct kmem_cache *s) */ return; +#ifdef CONFIG_MEMCG_KMEM + kset_unregister(s->memcg_kset); +#endif kobject_uevent(&s->kobj, KOBJ_REMOVE); kobject_del(&s->kobj); kobject_put(&s->kobj); diff --git a/mm/sparse.c b/mm/sparse.c index 63c3ea5..d1b48b6 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -5,10 +5,12 @@ #include <linux/slab.h> #include <linux/mmzone.h> #include <linux/bootmem.h> +#include <linux/compiler.h> #include <linux/highmem.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> + #include "internal.h" #include <asm/dma.h> #include <asm/pgalloc.h> @@ -268,7 +270,7 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, /* * A page may contain usemaps for other sections preventing the * page being freed and making a section unremovable while - * other sections referencing the usemap retmain active. Similarly, + * other sections referencing the usemap remain active. Similarly, * a pgdat can prevent a section being removed. If section A * contains a pgdat and section B contains the usemap, both * sections become inter-dependent. This allocates usemaps @@ -461,7 +463,7 @@ static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum) } #endif -void __attribute__((weak)) __meminit vmemmap_populate_print_last(void) +void __weak __meminit vmemmap_populate_print_last(void) { } @@ -98,7 +98,7 @@ static void put_compound_page(struct page *page) } /* __split_huge_page_refcount can run under us */ - page_head = compound_trans_head(page); + page_head = compound_head(page); /* * THP can not break up slab pages so avoid taking @@ -253,7 +253,7 @@ bool __get_page_tail(struct page *page) */ unsigned long flags; bool got; - struct page *page_head = compound_trans_head(page); + struct page *page_head = compound_head(page); /* Ref to put_compound_page() comment. */ if (!__compound_tail_refcounted(page_head)) { @@ -574,6 +574,8 @@ void mark_page_accessed(struct page *page) else __lru_cache_activate_page(page); ClearPageReferenced(page); + if (page_is_file_cache(page)) + workingset_activation(page); } else if (!PageReferenced(page)) { SetPageReferenced(page); } @@ -948,6 +950,57 @@ void __pagevec_lru_add(struct pagevec *pvec) EXPORT_SYMBOL(__pagevec_lru_add); /** + * pagevec_lookup_entries - gang pagecache lookup + * @pvec: Where the resulting entries are placed + * @mapping: The address_space to search + * @start: The starting entry index + * @nr_entries: The maximum number of entries + * @indices: The cache indices corresponding to the entries in @pvec + * + * pagevec_lookup_entries() will search for and return a group of up + * to @nr_entries pages and shadow entries in the mapping. All + * entries are placed in @pvec. pagevec_lookup_entries() takes a + * reference against actual pages in @pvec. + * + * The search returns a group of mapping-contiguous entries with + * ascending indexes. There may be holes in the indices due to + * not-present entries. + * + * pagevec_lookup_entries() returns the number of entries which were + * found. + */ +unsigned pagevec_lookup_entries(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t start, unsigned nr_pages, + pgoff_t *indices) +{ + pvec->nr = find_get_entries(mapping, start, nr_pages, + pvec->pages, indices); + return pagevec_count(pvec); +} + +/** + * pagevec_remove_exceptionals - pagevec exceptionals pruning + * @pvec: The pagevec to prune + * + * pagevec_lookup_entries() fills both pages and exceptional radix + * tree entries into the pagevec. This function prunes all + * exceptionals from @pvec without leaving holes, so that it can be + * passed on to page-only pagevec operations. + */ +void pagevec_remove_exceptionals(struct pagevec *pvec) +{ + int i, j; + + for (i = 0, j = 0; i < pagevec_count(pvec); i++) { + struct page *page = pvec->pages[i]; + if (!radix_tree_exceptional_entry(page)) + pvec->pages[j++] = page; + } + pvec->nr = j; +} + +/** * pagevec_lookup - gang pagecache lookup * @pvec: Where the resulting pages are placed * @mapping: The address_space to search diff --git a/mm/swap_state.c b/mm/swap_state.c index 98e85e9..e76ace3 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -63,6 +63,8 @@ unsigned long total_swapcache_pages(void) return ret; } +static atomic_t swapin_readahead_hits = ATOMIC_INIT(4); + void show_swap_cache_info(void) { printk("%lu pages in swap cache\n", total_swapcache_pages()); @@ -286,8 +288,11 @@ struct page * lookup_swap_cache(swp_entry_t entry) page = find_get_page(swap_address_space(entry), entry.val); - if (page) + if (page) { INC_CACHE_INFO(find_success); + if (TestClearPageReadahead(page)) + atomic_inc(&swapin_readahead_hits); + } INC_CACHE_INFO(find_total); return page; @@ -389,6 +394,50 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, return found_page; } +static unsigned long swapin_nr_pages(unsigned long offset) +{ + static unsigned long prev_offset; + unsigned int pages, max_pages, last_ra; + static atomic_t last_readahead_pages; + + max_pages = 1 << ACCESS_ONCE(page_cluster); + if (max_pages <= 1) + return 1; + + /* + * This heuristic has been found to work well on both sequential and + * random loads, swapping to hard disk or to SSD: please don't ask + * what the "+ 2" means, it just happens to work well, that's all. + */ + pages = atomic_xchg(&swapin_readahead_hits, 0) + 2; + if (pages == 2) { + /* + * We can have no readahead hits to judge by: but must not get + * stuck here forever, so check for an adjacent offset instead + * (and don't even bother to check whether swap type is same). + */ + if (offset != prev_offset + 1 && offset != prev_offset - 1) + pages = 1; + prev_offset = offset; + } else { + unsigned int roundup = 4; + while (roundup < pages) + roundup <<= 1; + pages = roundup; + } + + if (pages > max_pages) + pages = max_pages; + + /* Don't shrink readahead too fast */ + last_ra = atomic_read(&last_readahead_pages) / 2; + if (pages < last_ra) + pages = last_ra; + atomic_set(&last_readahead_pages, pages); + + return pages; +} + /** * swapin_readahead - swap in pages in hope we need them soon * @entry: swap entry of this memory @@ -412,11 +461,16 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr) { struct page *page; - unsigned long offset = swp_offset(entry); + unsigned long entry_offset = swp_offset(entry); + unsigned long offset = entry_offset; unsigned long start_offset, end_offset; - unsigned long mask = (1UL << page_cluster) - 1; + unsigned long mask; struct blk_plug plug; + mask = swapin_nr_pages(offset) - 1; + if (!mask) + goto skip; + /* Read a page_cluster sized and aligned cluster around offset. */ start_offset = offset & ~mask; end_offset = offset | mask; @@ -430,10 +484,13 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, gfp_mask, vma, addr); if (!page) continue; + if (offset != entry_offset) + SetPageReadahead(page); page_cache_release(page); } blk_finish_plug(&plug); lru_add_drain(); /* Push any new pages onto the LRU now */ +skip: return read_swap_cache_async(entry, gfp_mask, vma, addr); } diff --git a/mm/swapfile.c b/mm/swapfile.c index c6c13b05..4a7f7e6 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1923,7 +1923,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) p->swap_map = NULL; cluster_info = p->cluster_info; p->cluster_info = NULL; - p->flags = 0; frontswap_map = frontswap_map_get(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); @@ -1949,6 +1948,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) mutex_unlock(&inode->i_mutex); } filp_close(swap_file, NULL); + + /* + * Clear the SWP_USED flag after all resources are freed so that swapon + * can reuse this swap_info in alloc_swap_info() safely. It is ok to + * not hold p->lock after we cleared its SWP_WRITEOK. + */ + spin_lock(&swap_lock); + p->flags = 0; + spin_unlock(&swap_lock); + err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); diff --git a/mm/truncate.c b/mm/truncate.c index 353b683..e5cc39a 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -22,6 +22,45 @@ #include <linux/cleancache.h> #include "internal.h" +static void clear_exceptional_entry(struct address_space *mapping, + pgoff_t index, void *entry) +{ + struct radix_tree_node *node; + void **slot; + + /* Handled by shmem itself */ + if (shmem_mapping(mapping)) + return; + + spin_lock_irq(&mapping->tree_lock); + /* + * Regular page slots are stabilized by the page lock even + * without the tree itself locked. These unlocked entries + * need verification under the tree lock. + */ + if (!__radix_tree_lookup(&mapping->page_tree, index, &node, &slot)) + goto unlock; + if (*slot != entry) + goto unlock; + radix_tree_replace_slot(slot, NULL); + mapping->nrshadows--; + if (!node) + goto unlock; + workingset_node_shadows_dec(node); + /* + * Don't track node without shadow entries. + * + * Avoid acquiring the list_lru lock if already untracked. + * The list_empty() test is safe as node->private_list is + * protected by mapping->tree_lock. + */ + if (!workingset_node_shadows(node) && + !list_empty(&node->private_list)) + list_lru_del(&workingset_shadow_nodes, &node->private_list); + __radix_tree_delete_node(&mapping->page_tree, node); +unlock: + spin_unlock_irq(&mapping->tree_lock); +} /** * do_invalidatepage - invalidate part or all of a page @@ -208,11 +247,12 @@ void truncate_inode_pages_range(struct address_space *mapping, unsigned int partial_start; /* inclusive */ unsigned int partial_end; /* exclusive */ struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index; int i; cleancache_invalidate_inode(mapping); - if (mapping->nrpages == 0) + if (mapping->nrpages == 0 && mapping->nrshadows == 0) return; /* Offsets within partial pages */ @@ -238,17 +278,23 @@ void truncate_inode_pages_range(struct address_space *mapping, pagevec_init(&pvec, 0); index = start; - while (index < end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE))) { + while (index < end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index >= end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + if (!trylock_page(page)) continue; WARN_ON(page->index != index); @@ -259,6 +305,7 @@ void truncate_inode_pages_range(struct address_space *mapping, truncate_inode_page(mapping, page); unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -307,14 +354,16 @@ void truncate_inode_pages_range(struct address_space *mapping, index = start; for ( ; ; ) { cond_resched(); - if (!pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE))) { + if (!pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + indices)) { if (index == start) break; index = start; continue; } - if (index == start && pvec.pages[0]->index >= end) { + if (index == start && indices[0] >= end) { + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); break; } @@ -323,16 +372,22 @@ void truncate_inode_pages_range(struct address_space *mapping, struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index >= end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + lock_page(page); WARN_ON(page->index != index); wait_on_page_writeback(page); truncate_inode_page(mapping, page); unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; @@ -360,6 +415,53 @@ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) EXPORT_SYMBOL(truncate_inode_pages); /** + * truncate_inode_pages_final - truncate *all* pages before inode dies + * @mapping: mapping to truncate + * + * Called under (and serialized by) inode->i_mutex. + * + * Filesystems have to use this in the .evict_inode path to inform the + * VM that this is the final truncate and the inode is going away. + */ +void truncate_inode_pages_final(struct address_space *mapping) +{ + unsigned long nrshadows; + unsigned long nrpages; + + /* + * Page reclaim can not participate in regular inode lifetime + * management (can't call iput()) and thus can race with the + * inode teardown. Tell it when the address space is exiting, + * so that it does not install eviction information after the + * final truncate has begun. + */ + mapping_set_exiting(mapping); + + /* + * When reclaim installs eviction entries, it increases + * nrshadows first, then decreases nrpages. Make sure we see + * this in the right order or we might miss an entry. + */ + nrpages = mapping->nrpages; + smp_rmb(); + nrshadows = mapping->nrshadows; + + if (nrpages || nrshadows) { + /* + * As truncation uses a lockless tree lookup, cycle + * the tree lock to make sure any ongoing tree + * modification that does not see AS_EXITING is + * completed before starting the final truncate. + */ + spin_lock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); + + truncate_inode_pages(mapping, 0); + } +} +EXPORT_SYMBOL(truncate_inode_pages_final); + +/** * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode * @mapping: the address_space which holds the pages to invalidate * @start: the offset 'from' which to invalidate @@ -375,6 +477,7 @@ EXPORT_SYMBOL(truncate_inode_pages); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end) { + pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index = start; unsigned long ret; @@ -390,17 +493,23 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, */ pagevec_init(&pvec, 0); - while (index <= end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index > end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + if (!trylock_page(page)) continue; WARN_ON(page->index != index); @@ -414,6 +523,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, deactivate_page(page); count += ret; } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -444,7 +554,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) goto failed; BUG_ON(page_has_private(page)); - __delete_from_page_cache(page); + __delete_from_page_cache(page, NULL); spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); @@ -481,6 +591,7 @@ static int do_launder_page(struct address_space *mapping, struct page *page) int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { + pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index; int i; @@ -491,17 +602,23 @@ int invalidate_inode_pages2_range(struct address_space *mapping, cleancache_invalidate_inode(mapping); pagevec_init(&pvec, 0); index = start; - while (index <= end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index > end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + lock_page(page); WARN_ON(page->index != index); if (page->mapping != mapping) { @@ -539,6 +656,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, ret = ret2; unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -1,6 +1,7 @@ #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> +#include <linux/compiler.h> #include <linux/export.h> #include <linux/err.h> #include <linux/sched.h> @@ -307,7 +308,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm) * If the architecture not support this function, simply return with no * page pinned */ -int __attribute__((weak)) __get_user_pages_fast(unsigned long start, +int __weak __get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { return 0; @@ -338,7 +339,7 @@ EXPORT_SYMBOL_GPL(__get_user_pages_fast); * callers need to carefully consider what to use. On many architectures, * get_user_pages_fast simply falls back to get_user_pages. */ -int __attribute__((weak)) get_user_pages_fast(unsigned long start, +int __weak get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { struct mm_struct *mm = current->mm; @@ -445,6 +446,54 @@ unsigned long vm_commit_limit(void) return allowed; } +/** + * get_cmdline() - copy the cmdline value to a buffer. + * @task: the task whose cmdline value to copy. + * @buffer: the buffer to copy to. + * @buflen: the length of the buffer. Larger cmdline values are truncated + * to this length. + * Returns the size of the cmdline field copied. Note that the copy does + * not guarantee an ending NULL byte. + */ +int get_cmdline(struct task_struct *task, char *buffer, int buflen) +{ + int res = 0; + unsigned int len; + struct mm_struct *mm = get_task_mm(task); + if (!mm) + goto out; + if (!mm->arg_end) + goto out_mm; /* Shh! No looking before we're done */ + + len = mm->arg_end - mm->arg_start; + + if (len > buflen) + len = buflen; + + res = access_process_vm(task, mm->arg_start, buffer, len, 0); + + /* + * If the nul at the end of args has been overwritten, then + * assume application is using setproctitle(3). + */ + if (res > 0 && buffer[res-1] != '\0' && len < buflen) { + len = strnlen(buffer, res); + if (len < res) { + res = len; + } else { + len = mm->env_end - mm->env_start; + if (len > buflen - res) + len = buflen - res; + res += access_process_vm(task, mm->env_start, + buffer+res, len, 0); + res = strnlen(buffer, res); + } + } +out_mm: + mmput(mm); +out: + return res; +} /* Tracepoints definitions. */ EXPORT_TRACEPOINT_SYMBOL(kmalloc); diff --git a/mm/vmacache.c b/mm/vmacache.c new file mode 100644 index 0000000..d4224b3 --- /dev/null +++ b/mm/vmacache.c @@ -0,0 +1,112 @@ +/* + * Copyright (C) 2014 Davidlohr Bueso. + */ +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmacache.h> + +/* + * Flush vma caches for threads that share a given mm. + * + * The operation is safe because the caller holds the mmap_sem + * exclusively and other threads accessing the vma cache will + * have mmap_sem held at least for read, so no extra locking + * is required to maintain the vma cache. + */ +void vmacache_flush_all(struct mm_struct *mm) +{ + struct task_struct *g, *p; + + rcu_read_lock(); + for_each_process_thread(g, p) { + /* + * Only flush the vmacache pointers as the + * mm seqnum is already set and curr's will + * be set upon invalidation when the next + * lookup is done. + */ + if (mm == p->mm) + vmacache_flush(p); + } + rcu_read_unlock(); +} + +/* + * This task may be accessing a foreign mm via (for example) + * get_user_pages()->find_vma(). The vmacache is task-local and this + * task's vmacache pertains to a different mm (ie, its own). There is + * nothing we can do here. + * + * Also handle the case where a kernel thread has adopted this mm via use_mm(). + * That kernel thread's vmacache is not applicable to this mm. + */ +static bool vmacache_valid_mm(struct mm_struct *mm) +{ + return current->mm == mm && !(current->flags & PF_KTHREAD); +} + +void vmacache_update(unsigned long addr, struct vm_area_struct *newvma) +{ + if (vmacache_valid_mm(newvma->vm_mm)) + current->vmacache[VMACACHE_HASH(addr)] = newvma; +} + +static bool vmacache_valid(struct mm_struct *mm) +{ + struct task_struct *curr; + + if (!vmacache_valid_mm(mm)) + return false; + + curr = current; + if (mm->vmacache_seqnum != curr->vmacache_seqnum) { + /* + * First attempt will always be invalid, initialize + * the new cache for this task here. + */ + curr->vmacache_seqnum = mm->vmacache_seqnum; + vmacache_flush(curr); + return false; + } + return true; +} + +struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr) +{ + int i; + + if (!vmacache_valid(mm)) + return NULL; + + for (i = 0; i < VMACACHE_SIZE; i++) { + struct vm_area_struct *vma = current->vmacache[i]; + + if (vma && vma->vm_start <= addr && vma->vm_end > addr) { + BUG_ON(vma->vm_mm != mm); + return vma; + } + } + + return NULL; +} + +#ifndef CONFIG_MMU +struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + int i; + + if (!vmacache_valid(mm)) + return NULL; + + for (i = 0; i < VMACACHE_SIZE; i++) { + struct vm_area_struct *vma = current->vmacache[i]; + + if (vma && vma->vm_start == start && vma->vm_end == end) + return vma; + } + + return NULL; +} +#endif diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 0fdf968..bf233b2 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -27,7 +27,9 @@ #include <linux/pfn.h> #include <linux/kmemleak.h> #include <linux/atomic.h> +#include <linux/compiler.h> #include <linux/llist.h> + #include <asm/uaccess.h> #include <asm/tlbflush.h> #include <asm/shmparam.h> @@ -1083,6 +1085,12 @@ EXPORT_SYMBOL(vm_unmap_ram); * @node: prefer to allocate data structures on this node * @prot: memory protection to use. PAGE_KERNEL for regular RAM * + * If you use this function for less than VMAP_MAX_ALLOC pages, it could be + * faster than vmap so it's good. But if you mix long-life and short-life + * objects with vm_map_ram(), it could consume lots of address space through + * fragmentation (especially on a 32bit machine). You could see failures in + * the end. Please use this function for short-lived objects. + * * Returns: a pointer to the address that has been mapped, or %NULL on failure */ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot) @@ -2181,7 +2189,7 @@ EXPORT_SYMBOL(remap_vmalloc_range); * Implement a stub for vmalloc_sync_all() if the architecture chose not to * have one. */ -void __attribute__((weak)) vmalloc_sync_all(void) +void __weak vmalloc_sync_all(void) { } diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 196970a..d4042e7 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -19,6 +19,7 @@ #include <linux/mm.h> #include <linux/vmstat.h> #include <linux/eventfd.h> +#include <linux/slab.h> #include <linux/swap.h> #include <linux/printk.h> #include <linux/vmpressure.h> diff --git a/mm/vmscan.c b/mm/vmscan.c index a9c74b4..9b6497e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -224,15 +224,15 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, unsigned long freed = 0; unsigned long long delta; long total_scan; - long max_pass; + long freeable; long nr; long new_nr; int nid = shrinkctl->nid; long batch_size = shrinker->batch ? shrinker->batch : SHRINK_BATCH; - max_pass = shrinker->count_objects(shrinker, shrinkctl); - if (max_pass == 0) + freeable = shrinker->count_objects(shrinker, shrinkctl); + if (freeable == 0) return 0; /* @@ -244,14 +244,14 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, total_scan = nr; delta = (4 * nr_pages_scanned) / shrinker->seeks; - delta *= max_pass; + delta *= freeable; do_div(delta, lru_pages + 1); total_scan += delta; if (total_scan < 0) { printk(KERN_ERR "shrink_slab: %pF negative objects to delete nr=%ld\n", shrinker->scan_objects, total_scan); - total_scan = max_pass; + total_scan = freeable; } /* @@ -260,26 +260,26 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, * shrinkers to return -1 all the time. This results in a large * nr being built up so when a shrink that can do some work * comes along it empties the entire cache due to nr >>> - * max_pass. This is bad for sustaining a working set in + * freeable. This is bad for sustaining a working set in * memory. * * Hence only allow the shrinker to scan the entire cache when * a large delta change is calculated directly. */ - if (delta < max_pass / 4) - total_scan = min(total_scan, max_pass / 2); + if (delta < freeable / 4) + total_scan = min(total_scan, freeable / 2); /* * Avoid risking looping forever due to too large nr value: * never try to free more than twice the estimate number of * freeable entries. */ - if (total_scan > max_pass * 2) - total_scan = max_pass * 2; + if (total_scan > freeable * 2) + total_scan = freeable * 2; trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, nr_pages_scanned, lru_pages, - max_pass, delta, total_scan); + freeable, delta, total_scan); /* * Normally, we should not scan less than batch_size objects in one @@ -292,12 +292,12 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, * * We detect the "tight on memory" situations by looking at the total * number of objects we want to scan (total_scan). If it is greater - * than the total number of objects on slab (max_pass), we must be + * than the total number of objects on slab (freeable), we must be * scanning at high prio and therefore should try to reclaim as much as * possible. */ while (total_scan >= batch_size || - total_scan >= max_pass) { + total_scan >= freeable) { unsigned long ret; unsigned long nr_to_scan = min(batch_size, total_scan); @@ -523,7 +523,8 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, * Same as remove_mapping, but if the page is removed from the mapping, it * gets returned with a refcount of 0. */ -static int __remove_mapping(struct address_space *mapping, struct page *page) +static int __remove_mapping(struct address_space *mapping, struct page *page, + bool reclaimed) { BUG_ON(!PageLocked(page)); BUG_ON(mapping != page_mapping(page)); @@ -569,10 +570,23 @@ static int __remove_mapping(struct address_space *mapping, struct page *page) swapcache_free(swap, page); } else { void (*freepage)(struct page *); + void *shadow = NULL; freepage = mapping->a_ops->freepage; - - __delete_from_page_cache(page); + /* + * Remember a shadow entry for reclaimed file cache in + * order to detect refaults, thus thrashing, later on. + * + * But don't store shadows in an address space that is + * already exiting. This is not just an optizimation, + * inode reclaim needs to empty out the radix tree or + * the nodes are lost. Don't plant shadows behind its + * back. + */ + if (reclaimed && page_is_file_cache(page) && + !mapping_exiting(mapping)) + shadow = workingset_eviction(mapping, page); + __delete_from_page_cache(page, shadow); spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); @@ -595,7 +609,7 @@ cannot_free: */ int remove_mapping(struct address_space *mapping, struct page *page) { - if (__remove_mapping(mapping, page)) { + if (__remove_mapping(mapping, page, false)) { /* * Unfreezing the refcount with 1 rather than 2 effectively * drops the pagecache ref for us without requiring another @@ -1065,7 +1079,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, } } - if (!mapping || !__remove_mapping(mapping, page)) + if (!mapping || !__remove_mapping(mapping, page, true)) goto keep_locked; /* @@ -1848,7 +1862,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, struct zone *zone = lruvec_zone(lruvec); unsigned long anon_prio, file_prio; enum scan_balance scan_balance; - unsigned long anon, file, free; + unsigned long anon, file; bool force_scan = false; unsigned long ap, fp; enum lru_list lru; @@ -1902,20 +1916,6 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, get_lru_size(lruvec, LRU_INACTIVE_FILE); /* - * If it's foreseeable that reclaiming the file cache won't be - * enough to get the zone back into a desirable shape, we have - * to swap. Better start now and leave the - probably heavily - * thrashing - remaining file pages alone. - */ - if (global_reclaim(sc)) { - free = zone_page_state(zone, NR_FREE_PAGES); - if (unlikely(file + free <= high_wmark_pages(zone))) { - scan_balance = SCAN_ANON; - goto out; - } - } - - /* * There is enough inactive page cache, do not reclaim * anything from the anonymous working set right now. */ @@ -2297,16 +2297,26 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; + unsigned long lru_pages = 0; bool aborted_reclaim = false; + struct reclaim_state *reclaim_state = current->reclaim_state; + gfp_t orig_mask; + struct shrink_control shrink = { + .gfp_mask = sc->gfp_mask, + }; + enum zone_type requested_highidx = gfp_zone(sc->gfp_mask); /* * If the number of buffer_heads in the machine exceeds the maximum * allowed level, force direct reclaim to scan the highmem zone as * highmem pages could be pinning lowmem pages storing buffer_heads */ + orig_mask = sc->gfp_mask; if (buffer_heads_over_limit) sc->gfp_mask |= __GFP_HIGHMEM; + nodes_clear(shrink.nodes_to_scan); + for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(sc->gfp_mask), sc->nodemask) { if (!populated_zone(zone)) @@ -2318,6 +2328,10 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) if (global_reclaim(sc)) { if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; + + lru_pages += zone_reclaimable_pages(zone); + node_set(zone_to_nid(zone), shrink.nodes_to_scan); + if (sc->priority != DEF_PRIORITY && !zone_reclaimable(zone)) continue; /* Let kswapd poll it */ @@ -2331,7 +2345,8 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) * noticeable problem, like transparent huge * page allocations. */ - if (compaction_ready(zone, sc)) { + if ((zonelist_zone_idx(z) <= requested_highidx) + && compaction_ready(zone, sc)) { aborted_reclaim = true; continue; } @@ -2354,6 +2369,26 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) shrink_zone(zone, sc); } + /* + * Don't shrink slabs when reclaiming memory from over limit cgroups + * but do shrink slab at least once when aborting reclaim for + * compaction to avoid unevenly scanning file/anon LRU pages over slab + * pages. + */ + if (global_reclaim(sc)) { + shrink_slab(&shrink, sc->nr_scanned, lru_pages); + if (reclaim_state) { + sc->nr_reclaimed += reclaim_state->reclaimed_slab; + reclaim_state->reclaimed_slab = 0; + } + } + + /* + * Restore to original mask to avoid the impact on the caller if we + * promoted it to __GFP_HIGHMEM. + */ + sc->gfp_mask = orig_mask; + return aborted_reclaim; } @@ -2394,13 +2429,9 @@ static bool all_unreclaimable(struct zonelist *zonelist, * else, the number of pages reclaimed */ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, - struct scan_control *sc, - struct shrink_control *shrink) + struct scan_control *sc) { unsigned long total_scanned = 0; - struct reclaim_state *reclaim_state = current->reclaim_state; - struct zoneref *z; - struct zone *zone; unsigned long writeback_threshold; bool aborted_reclaim; @@ -2415,32 +2446,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, sc->nr_scanned = 0; aborted_reclaim = shrink_zones(zonelist, sc); - /* - * Don't shrink slabs when reclaiming memory from over limit - * cgroups but do shrink slab at least once when aborting - * reclaim for compaction to avoid unevenly scanning file/anon - * LRU pages over slab pages. - */ - if (global_reclaim(sc)) { - unsigned long lru_pages = 0; - - nodes_clear(shrink->nodes_to_scan); - for_each_zone_zonelist(zone, z, zonelist, - gfp_zone(sc->gfp_mask)) { - if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) - continue; - - lru_pages += zone_reclaimable_pages(zone); - node_set(zone_to_nid(zone), - shrink->nodes_to_scan); - } - - shrink_slab(shrink, sc->nr_scanned, lru_pages); - if (reclaim_state) { - sc->nr_reclaimed += reclaim_state->reclaimed_slab; - reclaim_state->reclaimed_slab = 0; - } - } total_scanned += sc->nr_scanned; if (sc->nr_reclaimed >= sc->nr_to_reclaim) goto out; @@ -2602,9 +2607,6 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, .target_mem_cgroup = NULL, .nodemask = nodemask, }; - struct shrink_control shrink = { - .gfp_mask = sc.gfp_mask, - }; /* * Do not enter reclaim if fatal signal was delivered while throttled. @@ -2618,7 +2620,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, sc.may_writepage, gfp_mask); - nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink); + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); @@ -2685,9 +2687,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, .gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), }; - struct shrink_control shrink = { - .gfp_mask = sc.gfp_mask, - }; /* * Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't @@ -2702,7 +2701,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, sc.may_writepage, sc.gfp_mask); - nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink); + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); @@ -3337,9 +3336,6 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) .order = 0, .priority = DEF_PRIORITY, }; - struct shrink_control shrink = { - .gfp_mask = sc.gfp_mask, - }; struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); struct task_struct *p = current; unsigned long nr_reclaimed; @@ -3349,7 +3345,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) reclaim_state.reclaimed_slab = 0; p->reclaim_state = &reclaim_state; - nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink); + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); p->reclaim_state = NULL; lockdep_clear_current_reclaim_state(); diff --git a/mm/vmstat.c b/mm/vmstat.c index 7249614..302dd07 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -770,6 +770,9 @@ const char * const vmstat_text[] = { "numa_local", "numa_other", #endif + "workingset_refault", + "workingset_activate", + "workingset_nodereclaim", "nr_anon_transparent_hugepages", "nr_free_cma", "nr_dirty_threshold", @@ -810,6 +813,9 @@ const char * const vmstat_text[] = { "pgrotated", + "drop_pagecache", + "drop_slab", + #ifdef CONFIG_NUMA_BALANCING "numa_pte_updates", "numa_huge_pte_updates", @@ -851,12 +857,14 @@ const char * const vmstat_text[] = { "thp_zero_page_alloc", "thp_zero_page_alloc_failed", #endif +#ifdef CONFIG_DEBUG_TLBFLUSH #ifdef CONFIG_SMP "nr_tlb_remote_flush", "nr_tlb_remote_flush_received", -#endif +#endif /* CONFIG_SMP */ "nr_tlb_local_flush_all", "nr_tlb_local_flush_one", +#endif /* CONFIG_DEBUG_TLBFLUSH */ #endif /* CONFIG_VM_EVENTS_COUNTERS */ }; @@ -1290,14 +1298,14 @@ static int __init setup_vmstat(void) #ifdef CONFIG_SMP int cpu; - register_cpu_notifier(&vmstat_notifier); + cpu_notifier_register_begin(); + __register_cpu_notifier(&vmstat_notifier); - get_online_cpus(); for_each_online_cpu(cpu) { start_cpu_timer(cpu); node_set_state(cpu_to_node(cpu), N_CPU); } - put_online_cpus(); + cpu_notifier_register_done(); #endif #ifdef CONFIG_PROC_FS proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations); diff --git a/mm/workingset.c b/mm/workingset.c new file mode 100644 index 0000000..f7216fa --- /dev/null +++ b/mm/workingset.c @@ -0,0 +1,414 @@ +/* + * Workingset detection + * + * Copyright (C) 2013 Red Hat, Inc., Johannes Weiner + */ + +#include <linux/memcontrol.h> +#include <linux/writeback.h> +#include <linux/pagemap.h> +#include <linux/atomic.h> +#include <linux/module.h> +#include <linux/swap.h> +#include <linux/fs.h> +#include <linux/mm.h> + +/* + * Double CLOCK lists + * + * Per zone, two clock lists are maintained for file pages: the + * inactive and the active list. Freshly faulted pages start out at + * the head of the inactive list and page reclaim scans pages from the + * tail. Pages that are accessed multiple times on the inactive list + * are promoted to the active list, to protect them from reclaim, + * whereas active pages are demoted to the inactive list when the + * active list grows too big. + * + * fault ------------------------+ + * | + * +--------------+ | +-------------+ + * reclaim <- | inactive | <-+-- demotion | active | <--+ + * +--------------+ +-------------+ | + * | | + * +-------------- promotion ------------------+ + * + * + * Access frequency and refault distance + * + * A workload is thrashing when its pages are frequently used but they + * are evicted from the inactive list every time before another access + * would have promoted them to the active list. + * + * In cases where the average access distance between thrashing pages + * is bigger than the size of memory there is nothing that can be + * done - the thrashing set could never fit into memory under any + * circumstance. + * + * However, the average access distance could be bigger than the + * inactive list, yet smaller than the size of memory. In this case, + * the set could fit into memory if it weren't for the currently + * active pages - which may be used more, hopefully less frequently: + * + * +-memory available to cache-+ + * | | + * +-inactive------+-active----+ + * a b | c d e f g h i | J K L M N | + * +---------------+-----------+ + * + * It is prohibitively expensive to accurately track access frequency + * of pages. But a reasonable approximation can be made to measure + * thrashing on the inactive list, after which refaulting pages can be + * activated optimistically to compete with the existing active pages. + * + * Approximating inactive page access frequency - Observations: + * + * 1. When a page is accessed for the first time, it is added to the + * head of the inactive list, slides every existing inactive page + * towards the tail by one slot, and pushes the current tail page + * out of memory. + * + * 2. When a page is accessed for the second time, it is promoted to + * the active list, shrinking the inactive list by one slot. This + * also slides all inactive pages that were faulted into the cache + * more recently than the activated page towards the tail of the + * inactive list. + * + * Thus: + * + * 1. The sum of evictions and activations between any two points in + * time indicate the minimum number of inactive pages accessed in + * between. + * + * 2. Moving one inactive page N page slots towards the tail of the + * list requires at least N inactive page accesses. + * + * Combining these: + * + * 1. When a page is finally evicted from memory, the number of + * inactive pages accessed while the page was in cache is at least + * the number of page slots on the inactive list. + * + * 2. In addition, measuring the sum of evictions and activations (E) + * at the time of a page's eviction, and comparing it to another + * reading (R) at the time the page faults back into memory tells + * the minimum number of accesses while the page was not cached. + * This is called the refault distance. + * + * Because the first access of the page was the fault and the second + * access the refault, we combine the in-cache distance with the + * out-of-cache distance to get the complete minimum access distance + * of this page: + * + * NR_inactive + (R - E) + * + * And knowing the minimum access distance of a page, we can easily + * tell if the page would be able to stay in cache assuming all page + * slots in the cache were available: + * + * NR_inactive + (R - E) <= NR_inactive + NR_active + * + * which can be further simplified to + * + * (R - E) <= NR_active + * + * Put into words, the refault distance (out-of-cache) can be seen as + * a deficit in inactive list space (in-cache). If the inactive list + * had (R - E) more page slots, the page would not have been evicted + * in between accesses, but activated instead. And on a full system, + * the only thing eating into inactive list space is active pages. + * + * + * Activating refaulting pages + * + * All that is known about the active list is that the pages have been + * accessed more than once in the past. This means that at any given + * time there is actually a good chance that pages on the active list + * are no longer in active use. + * + * So when a refault distance of (R - E) is observed and there are at + * least (R - E) active pages, the refaulting page is activated + * optimistically in the hope that (R - E) active pages are actually + * used less frequently than the refaulting page - or even not used at + * all anymore. + * + * If this is wrong and demotion kicks in, the pages which are truly + * used more frequently will be reactivated while the less frequently + * used once will be evicted from memory. + * + * But if this is right, the stale pages will be pushed out of memory + * and the used pages get to stay in cache. + * + * + * Implementation + * + * For each zone's file LRU lists, a counter for inactive evictions + * and activations is maintained (zone->inactive_age). + * + * On eviction, a snapshot of this counter (along with some bits to + * identify the zone) is stored in the now empty page cache radix tree + * slot of the evicted page. This is called a shadow entry. + * + * On cache misses for which there are shadow entries, an eligible + * refault distance will immediately activate the refaulting page. + */ + +static void *pack_shadow(unsigned long eviction, struct zone *zone) +{ + eviction = (eviction << NODES_SHIFT) | zone_to_nid(zone); + eviction = (eviction << ZONES_SHIFT) | zone_idx(zone); + eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT); + + return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY); +} + +static void unpack_shadow(void *shadow, + struct zone **zone, + unsigned long *distance) +{ + unsigned long entry = (unsigned long)shadow; + unsigned long eviction; + unsigned long refault; + unsigned long mask; + int zid, nid; + + entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT; + zid = entry & ((1UL << ZONES_SHIFT) - 1); + entry >>= ZONES_SHIFT; + nid = entry & ((1UL << NODES_SHIFT) - 1); + entry >>= NODES_SHIFT; + eviction = entry; + + *zone = NODE_DATA(nid)->node_zones + zid; + + refault = atomic_long_read(&(*zone)->inactive_age); + mask = ~0UL >> (NODES_SHIFT + ZONES_SHIFT + + RADIX_TREE_EXCEPTIONAL_SHIFT); + /* + * The unsigned subtraction here gives an accurate distance + * across inactive_age overflows in most cases. + * + * There is a special case: usually, shadow entries have a + * short lifetime and are either refaulted or reclaimed along + * with the inode before they get too old. But it is not + * impossible for the inactive_age to lap a shadow entry in + * the field, which can then can result in a false small + * refault distance, leading to a false activation should this + * old entry actually refault again. However, earlier kernels + * used to deactivate unconditionally with *every* reclaim + * invocation for the longest time, so the occasional + * inappropriate activation leading to pressure on the active + * list is not a problem. + */ + *distance = (refault - eviction) & mask; +} + +/** + * workingset_eviction - note the eviction of a page from memory + * @mapping: address space the page was backing + * @page: the page being evicted + * + * Returns a shadow entry to be stored in @mapping->page_tree in place + * of the evicted @page so that a later refault can be detected. + */ +void *workingset_eviction(struct address_space *mapping, struct page *page) +{ + struct zone *zone = page_zone(page); + unsigned long eviction; + + eviction = atomic_long_inc_return(&zone->inactive_age); + return pack_shadow(eviction, zone); +} + +/** + * workingset_refault - evaluate the refault of a previously evicted page + * @shadow: shadow entry of the evicted page + * + * Calculates and evaluates the refault distance of the previously + * evicted page in the context of the zone it was allocated in. + * + * Returns %true if the page should be activated, %false otherwise. + */ +bool workingset_refault(void *shadow) +{ + unsigned long refault_distance; + struct zone *zone; + + unpack_shadow(shadow, &zone, &refault_distance); + inc_zone_state(zone, WORKINGSET_REFAULT); + + if (refault_distance <= zone_page_state(zone, NR_ACTIVE_FILE)) { + inc_zone_state(zone, WORKINGSET_ACTIVATE); + return true; + } + return false; +} + +/** + * workingset_activation - note a page activation + * @page: page that is being activated + */ +void workingset_activation(struct page *page) +{ + atomic_long_inc(&page_zone(page)->inactive_age); +} + +/* + * Shadow entries reflect the share of the working set that does not + * fit into memory, so their number depends on the access pattern of + * the workload. In most cases, they will refault or get reclaimed + * along with the inode, but a (malicious) workload that streams + * through files with a total size several times that of available + * memory, while preventing the inodes from being reclaimed, can + * create excessive amounts of shadow nodes. To keep a lid on this, + * track shadow nodes and reclaim them when they grow way past the + * point where they would still be useful. + */ + +struct list_lru workingset_shadow_nodes; + +static unsigned long count_shadow_nodes(struct shrinker *shrinker, + struct shrink_control *sc) +{ + unsigned long shadow_nodes; + unsigned long max_nodes; + unsigned long pages; + + /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ + local_irq_disable(); + shadow_nodes = list_lru_count_node(&workingset_shadow_nodes, sc->nid); + local_irq_enable(); + + pages = node_present_pages(sc->nid); + /* + * Active cache pages are limited to 50% of memory, and shadow + * entries that represent a refault distance bigger than that + * do not have any effect. Limit the number of shadow nodes + * such that shadow entries do not exceed the number of active + * cache pages, assuming a worst-case node population density + * of 1/8th on average. + * + * On 64-bit with 7 radix_tree_nodes per page and 64 slots + * each, this will reclaim shadow entries when they consume + * ~2% of available memory: + * + * PAGE_SIZE / radix_tree_nodes / node_entries / PAGE_SIZE + */ + max_nodes = pages >> (1 + RADIX_TREE_MAP_SHIFT - 3); + + if (shadow_nodes <= max_nodes) + return 0; + + return shadow_nodes - max_nodes; +} + +static enum lru_status shadow_lru_isolate(struct list_head *item, + spinlock_t *lru_lock, + void *arg) +{ + struct address_space *mapping; + struct radix_tree_node *node; + unsigned int i; + int ret; + + /* + * Page cache insertions and deletions synchroneously maintain + * the shadow node LRU under the mapping->tree_lock and the + * lru_lock. Because the page cache tree is emptied before + * the inode can be destroyed, holding the lru_lock pins any + * address_space that has radix tree nodes on the LRU. + * + * We can then safely transition to the mapping->tree_lock to + * pin only the address_space of the particular node we want + * to reclaim, take the node off-LRU, and drop the lru_lock. + */ + + node = container_of(item, struct radix_tree_node, private_list); + mapping = node->private_data; + + /* Coming from the list, invert the lock order */ + if (!spin_trylock(&mapping->tree_lock)) { + spin_unlock(lru_lock); + ret = LRU_RETRY; + goto out; + } + + list_del_init(item); + spin_unlock(lru_lock); + + /* + * The nodes should only contain one or more shadow entries, + * no pages, so we expect to be able to remove them all and + * delete and free the empty node afterwards. + */ + + BUG_ON(!node->count); + BUG_ON(node->count & RADIX_TREE_COUNT_MASK); + + for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { + if (node->slots[i]) { + BUG_ON(!radix_tree_exceptional_entry(node->slots[i])); + node->slots[i] = NULL; + BUG_ON(node->count < (1U << RADIX_TREE_COUNT_SHIFT)); + node->count -= 1U << RADIX_TREE_COUNT_SHIFT; + BUG_ON(!mapping->nrshadows); + mapping->nrshadows--; + } + } + BUG_ON(node->count); + inc_zone_state(page_zone(virt_to_page(node)), WORKINGSET_NODERECLAIM); + if (!__radix_tree_delete_node(&mapping->page_tree, node)) + BUG(); + + spin_unlock(&mapping->tree_lock); + ret = LRU_REMOVED_RETRY; +out: + local_irq_enable(); + cond_resched(); + local_irq_disable(); + spin_lock(lru_lock); + return ret; +} + +static unsigned long scan_shadow_nodes(struct shrinker *shrinker, + struct shrink_control *sc) +{ + unsigned long ret; + + /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ + local_irq_disable(); + ret = list_lru_walk_node(&workingset_shadow_nodes, sc->nid, + shadow_lru_isolate, NULL, &sc->nr_to_scan); + local_irq_enable(); + return ret; +} + +static struct shrinker workingset_shadow_shrinker = { + .count_objects = count_shadow_nodes, + .scan_objects = scan_shadow_nodes, + .seeks = DEFAULT_SEEKS, + .flags = SHRINKER_NUMA_AWARE, +}; + +/* + * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe + * mapping->tree_lock. + */ +static struct lock_class_key shadow_nodes_key; + +static int __init workingset_init(void) +{ + int ret; + + ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key); + if (ret) + goto err; + ret = register_shrinker(&workingset_shadow_shrinker); + if (ret) + goto err_list_lru; + return 0; +err_list_lru: + list_lru_destroy(&workingset_shadow_nodes); +err: + return ret; +} +module_init(workingset_init); diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index c03ca5e..36b4591 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -814,21 +814,32 @@ static void zs_exit(void) { int cpu; + cpu_notifier_register_begin(); + for_each_online_cpu(cpu) zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu); - unregister_cpu_notifier(&zs_cpu_nb); + __unregister_cpu_notifier(&zs_cpu_nb); + + cpu_notifier_register_done(); } static int zs_init(void) { int cpu, ret; - register_cpu_notifier(&zs_cpu_nb); + cpu_notifier_register_begin(); + + __register_cpu_notifier(&zs_cpu_nb); for_each_online_cpu(cpu) { ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu); - if (notifier_to_errno(ret)) + if (notifier_to_errno(ret)) { + cpu_notifier_register_done(); goto fail; + } } + + cpu_notifier_register_done(); + return 0; fail: zs_exit(); @@ -89,6 +89,9 @@ static unsigned int zswap_max_pool_percent = 20; module_param_named(max_pool_percent, zswap_max_pool_percent, uint, 0644); +/* zbud_pool is shared by all of zswap backend */ +static struct zbud_pool *zswap_pool; + /********************************* * compression functions **********************************/ @@ -160,14 +163,14 @@ static void zswap_comp_exit(void) * rbnode - links the entry into red-black tree for the appropriate swap type * refcount - the number of outstanding reference to the entry. This is needed * to protect against premature freeing of the entry by code - * concurent calls to load, invalidate, and writeback. The lock + * concurrent calls to load, invalidate, and writeback. The lock * for the zswap_tree structure that contains the entry must * be held while changing the refcount. Since the lock must * be held, there is no reason to also make refcount atomic. * offset - the swap offset for the entry. Index into the red-black tree. - * handle - zsmalloc allocation handle that stores the compressed page data + * handle - zbud allocation handle that stores the compressed page data * length - the length in bytes of the compressed page data. Needed during - * decompression + * decompression */ struct zswap_entry { struct rb_node rbnode; @@ -189,7 +192,6 @@ struct zswap_header { struct zswap_tree { struct rb_root rbroot; spinlock_t lock; - struct zbud_pool *pool; }; static struct zswap_tree *zswap_trees[MAX_SWAPFILES]; @@ -202,7 +204,7 @@ static struct kmem_cache *zswap_entry_cache; static int zswap_entry_cache_create(void) { zswap_entry_cache = KMEM_CACHE(zswap_entry, 0); - return (zswap_entry_cache == NULL); + return zswap_entry_cache == NULL; } static void zswap_entry_cache_destory(void) @@ -282,16 +284,15 @@ static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry) } /* - * Carries out the common pattern of freeing and entry's zsmalloc allocation, + * Carries out the common pattern of freeing and entry's zbud allocation, * freeing the entry itself, and decrementing the number of stored pages. */ -static void zswap_free_entry(struct zswap_tree *tree, - struct zswap_entry *entry) +static void zswap_free_entry(struct zswap_entry *entry) { - zbud_free(tree->pool, entry->handle); + zbud_free(zswap_pool, entry->handle); zswap_entry_cache_free(entry); atomic_dec(&zswap_stored_pages); - zswap_pool_pages = zbud_get_pool_size(tree->pool); + zswap_pool_pages = zbud_get_pool_size(zswap_pool); } /* caller must hold the tree lock */ @@ -311,7 +312,7 @@ static void zswap_entry_put(struct zswap_tree *tree, BUG_ON(refcount < 0); if (refcount == 0) { zswap_rb_erase(&tree->rbroot, entry); - zswap_free_entry(tree, entry); + zswap_free_entry(entry); } } @@ -387,18 +388,18 @@ static int zswap_cpu_init(void) { unsigned long cpu; - get_online_cpus(); + cpu_notifier_register_begin(); for_each_online_cpu(cpu) if (__zswap_cpu_notifier(CPU_UP_PREPARE, cpu) != NOTIFY_OK) goto cleanup; - register_cpu_notifier(&zswap_cpu_notifier_block); - put_online_cpus(); + __register_cpu_notifier(&zswap_cpu_notifier_block); + cpu_notifier_register_done(); return 0; cleanup: for_each_online_cpu(cpu) __zswap_cpu_notifier(CPU_UP_CANCELED, cpu); - put_online_cpus(); + cpu_notifier_register_done(); return -ENOMEM; } @@ -407,8 +408,8 @@ cleanup: **********************************/ static bool zswap_is_full(void) { - return (totalram_pages * zswap_max_pool_percent / 100 < - zswap_pool_pages); + return totalram_pages * zswap_max_pool_percent / 100 < + zswap_pool_pages; } /********************************* @@ -545,7 +546,6 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle) zbud_unmap(pool, handle); tree = zswap_trees[swp_type(swpentry)]; offset = swp_offset(swpentry); - BUG_ON(pool != tree->pool); /* find and ref zswap entry */ spin_lock(&tree->lock); @@ -573,13 +573,13 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle) case ZSWAP_SWAPCACHE_NEW: /* page is locked */ /* decompress */ dlen = PAGE_SIZE; - src = (u8 *)zbud_map(tree->pool, entry->handle) + + src = (u8 *)zbud_map(zswap_pool, entry->handle) + sizeof(struct zswap_header); dst = kmap_atomic(page); ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, entry->length, dst, &dlen); kunmap_atomic(dst); - zbud_unmap(tree->pool, entry->handle); + zbud_unmap(zswap_pool, entry->handle); BUG_ON(ret); BUG_ON(dlen != PAGE_SIZE); @@ -652,7 +652,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, /* reclaim space if needed */ if (zswap_is_full()) { zswap_pool_limit_hit++; - if (zbud_reclaim_page(tree->pool, 8)) { + if (zbud_reclaim_page(zswap_pool, 8)) { zswap_reject_reclaim_fail++; ret = -ENOMEM; goto reject; @@ -679,7 +679,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, /* store */ len = dlen + sizeof(struct zswap_header); - ret = zbud_alloc(tree->pool, len, __GFP_NORETRY | __GFP_NOWARN, + ret = zbud_alloc(zswap_pool, len, __GFP_NORETRY | __GFP_NOWARN, &handle); if (ret == -ENOSPC) { zswap_reject_compress_poor++; @@ -689,11 +689,11 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, zswap_reject_alloc_fail++; goto freepage; } - zhdr = zbud_map(tree->pool, handle); + zhdr = zbud_map(zswap_pool, handle); zhdr->swpentry = swp_entry(type, offset); buf = (u8 *)(zhdr + 1); memcpy(buf, dst, dlen); - zbud_unmap(tree->pool, handle); + zbud_unmap(zswap_pool, handle); put_cpu_var(zswap_dstmem); /* populate entry */ @@ -716,7 +716,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, /* update stats */ atomic_inc(&zswap_stored_pages); - zswap_pool_pages = zbud_get_pool_size(tree->pool); + zswap_pool_pages = zbud_get_pool_size(zswap_pool); return 0; @@ -752,13 +752,13 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, /* decompress */ dlen = PAGE_SIZE; - src = (u8 *)zbud_map(tree->pool, entry->handle) + + src = (u8 *)zbud_map(zswap_pool, entry->handle) + sizeof(struct zswap_header); dst = kmap_atomic(page); ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, entry->length, dst, &dlen); kunmap_atomic(dst); - zbud_unmap(tree->pool, entry->handle); + zbud_unmap(zswap_pool, entry->handle); BUG_ON(ret); spin_lock(&tree->lock); @@ -804,11 +804,9 @@ static void zswap_frontswap_invalidate_area(unsigned type) /* walk the tree and free everything */ spin_lock(&tree->lock); rbtree_postorder_for_each_entry_safe(entry, n, &tree->rbroot, rbnode) - zswap_free_entry(tree, entry); + zswap_free_entry(entry); tree->rbroot = RB_ROOT; spin_unlock(&tree->lock); - - zbud_destroy_pool(tree->pool); kfree(tree); zswap_trees[type] = NULL; } @@ -822,20 +820,14 @@ static void zswap_frontswap_init(unsigned type) struct zswap_tree *tree; tree = kzalloc(sizeof(struct zswap_tree), GFP_KERNEL); - if (!tree) - goto err; - tree->pool = zbud_create_pool(GFP_KERNEL, &zswap_zbud_ops); - if (!tree->pool) - goto freetree; + if (!tree) { + pr_err("alloc failed, zswap disabled for swap type %d\n", type); + return; + } + tree->rbroot = RB_ROOT; spin_lock_init(&tree->lock); zswap_trees[type] = tree; - return; - -freetree: - kfree(tree); -err: - pr_err("alloc failed, zswap disabled for swap type %d\n", type); } static struct frontswap_ops zswap_frontswap_ops = { @@ -907,9 +899,16 @@ static int __init init_zswap(void) return 0; pr_info("loading zswap\n"); + + zswap_pool = zbud_create_pool(GFP_KERNEL, &zswap_zbud_ops); + if (!zswap_pool) { + pr_err("zbud pool creation failed\n"); + goto error; + } + if (zswap_entry_cache_create()) { pr_err("entry cache creation failed\n"); - goto error; + goto cachefail; } if (zswap_comp_init()) { pr_err("compressor initialization failed\n"); @@ -919,6 +918,7 @@ static int __init init_zswap(void) pr_err("per-cpu initialization failed\n"); goto pcpufail; } + frontswap_register_ops(&zswap_frontswap_ops); if (zswap_debugfs_init()) pr_warn("debugfs initialization failed\n"); @@ -927,6 +927,8 @@ pcpufail: zswap_comp_exit(); compfail: zswap_entry_cache_destory(); +cachefail: + zbud_destroy_pool(zswap_pool); error: return -ENOMEM; } |