diff options
Diffstat (limited to 'mm')
64 files changed, 6856 insertions, 3416 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 723bbe04a0b0..ebe5880c29d6 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -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" @@ -552,3 +553,31 @@ config MEM_SOFT_DIRTY it can be cleared by hands. See Documentation/vm/soft-dirty.txt for more details. + +config ZSMALLOC + bool "Memory allocator for compressed pages" + depends on MMU + default n + help + zsmalloc is a slab-based memory allocator designed to store + compressed RAM pages. zsmalloc uses virtual memory mapping + in order to reduce fragmentation. However, this results in a + non-standard allocator interface where a handle, not a pointer, is + returned by an alloc(). This handle must be mapped in order to + access the allocated space. + +config PGTABLE_MAPPING + bool "Use page table mapping to access object in zsmalloc" + depends on ZSMALLOC + help + By default, zsmalloc uses a copy-based object mapping method to + access allocations that span two pages. However, if a particular + architecture (ex, ARM) performs VM mapping faster than copying, + 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: + https://github.com/spartacus06/zsmapbench + +config GENERIC_EARLY_IOREMAP + bool diff --git a/mm/Makefile b/mm/Makefile index 305d10acd081..9e5aaf92197d 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -16,8 +16,8 @@ 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 $(mmu-y) obj-y += init-mm.o @@ -60,3 +60,5 @@ obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o 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 ce682f7a4f29..09d9591b7708 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/balloon_compaction.c b/mm/balloon_compaction.c index 07dbc8ec46cf..6e45a5074bf0 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -267,7 +267,7 @@ void balloon_page_putback(struct page *page) put_page(page); } else { WARN_ON(1); - dump_page(page); + dump_page(page, "not movable balloon page"); } unlock_page(page); } @@ -287,7 +287,7 @@ int balloon_page_migrate(struct page *newpage, BUG_ON(!trylock_page(newpage)); if (WARN_ON(!__is_movable_balloon_page(page))) { - dump_page(page); + dump_page(page, "not movable balloon page"); unlock_page(newpage); return rc; } diff --git a/mm/bounce.c b/mm/bounce.c index 5a7d58fb883b..523918b8c6dc 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -98,27 +98,24 @@ int init_emergency_isa_pool(void) static void copy_to_high_bio_irq(struct bio *to, struct bio *from) { unsigned char *vfrom; - struct bio_vec *tovec, *fromvec; - int i; - - bio_for_each_segment(tovec, to, i) { - fromvec = from->bi_io_vec + i; - - /* - * not bounced - */ - if (tovec->bv_page == fromvec->bv_page) - continue; - - /* - * fromvec->bv_offset and fromvec->bv_len might have been - * modified by the block layer, so use the original copy, - * bounce_copy_vec already uses tovec->bv_len - */ - vfrom = page_address(fromvec->bv_page) + tovec->bv_offset; + struct bio_vec tovec, *fromvec = from->bi_io_vec; + struct bvec_iter iter; + + bio_for_each_segment(tovec, to, iter) { + if (tovec.bv_page != fromvec->bv_page) { + /* + * fromvec->bv_offset and fromvec->bv_len might have + * been modified by the block layer, so use the original + * copy, bounce_copy_vec already uses tovec->bv_len + */ + vfrom = page_address(fromvec->bv_page) + + tovec.bv_offset; + + bounce_copy_vec(&tovec, vfrom); + flush_dcache_page(tovec.bv_page); + } - bounce_copy_vec(tovec, vfrom); - flush_dcache_page(tovec->bv_page); + fromvec++; } } @@ -201,13 +198,14 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, { struct bio *bio; int rw = bio_data_dir(*bio_orig); - struct bio_vec *to, *from; + struct bio_vec *to, from; + struct bvec_iter iter; unsigned i; if (force) goto bounce; - bio_for_each_segment(from, *bio_orig, i) - if (page_to_pfn(from->bv_page) > queue_bounce_pfn(q)) + bio_for_each_segment(from, *bio_orig, iter) + if (page_to_pfn(from.bv_page) > queue_bounce_pfn(q)) goto bounce; return; diff --git a/mm/cleancache.c b/mm/cleancache.c index 5875f48ce279..d0eac4350403 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -237,7 +237,7 @@ int __cleancache_get_page(struct page *page) goto out; } - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); fake_pool_id = page->mapping->host->i_sb->cleancache_poolid; if (fake_pool_id < 0) goto out; @@ -279,7 +279,7 @@ void __cleancache_put_page(struct page *page) return; } - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); fake_pool_id = page->mapping->host->i_sb->cleancache_poolid; if (fake_pool_id < 0) return; @@ -318,7 +318,7 @@ void __cleancache_invalidate_page(struct address_space *mapping, if (pool_id < 0) return; - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); if (cleancache_get_key(mapping->host, &key) >= 0) { cleancache_ops->invalidate_page(pool_id, key, page->index); diff --git a/mm/compaction.c b/mm/compaction.c index f58bcd016f43..37f976287068 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) @@ -454,11 +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 @@ -480,7 +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; @@ -519,23 +527,32 @@ 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; - /* Skip if free */ - if (PageBuddy(page)) - continue; + 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; + } + } /* - * For async migration, also only scan in MOVABLE blocks. Async - * migration is optimistic to see if the minimum amount of work - * satisfies the allocation + * Skip if free. page_order cannot be used without zone->lock + * as nothing prevents parallel allocations or buddy merging. */ - if (!cc->sync && last_pageblock_nr != pageblock_nr && - !migrate_async_suitable(get_pageblock_migratetype(page))) { - cc->finished_update_migrate = true; - goto next_pageblock; - } + if (PageBuddy(page)) + continue; /* * Check may be lockless but that's ok as we recheck later. @@ -546,11 +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; @@ -573,6 +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); @@ -587,28 +609,23 @@ 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 */ if (__isolate_lru_page(page, mode) != 0) continue; - VM_BUG_ON(PageTransCompound(page)); + 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; @@ -619,7 +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); @@ -627,8 +643,13 @@ next_pageblock: if (locked) spin_unlock_irqrestore(&zone->lru_lock, flags); - /* Update the pageblock-skip if the whole pageblock was scanned */ - if (low_pfn == end_pfn) + /* + * Update the pageblock-skip information and cached scanner pfn, + * if the whole pageblock was scanned without isolating any page. + * This is not done when pageblock was skipped due to being unsuitable + * for async compaction, so that eventual sync compaction can try. + */ + if (low_pfn == end_pfn && !skipped_async_unsuitable) update_pageblock_skip(cc, valid_page, nr_isolated, true); trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); @@ -660,7 +681,7 @@ static void isolate_freepages(struct zone *zone, * is the end of the pageblock the migration scanner is using. */ pfn = cc->free_pfn; - low_pfn = cc->migrate_pfn + pageblock_nr_pages; + low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages); /* * Take care that if the migration scanner is at the end of the zone @@ -676,7 +697,7 @@ static void isolate_freepages(struct zone *zone, * pages on cc->migratepages. We stop searching if the migrate * and free page scanners meet or enough free pages are isolated. */ - for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages; + for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages; pfn -= pageblock_nr_pages) { unsigned long isolated; @@ -738,7 +759,14 @@ static void isolate_freepages(struct zone *zone, /* split_free_page does not map the pages */ map_pages(freelist); - cc->free_pfn = high_pfn; + /* + * If we crossed the migrate scanner, we want to keep it that way + * so that compact_finished() may detect this + */ + if (pfn < low_pfn) + cc->free_pfn = max(pfn, zone->zone_start_pfn); + else + cc->free_pfn = high_pfn; cc->nr_freepages = nr_freepages; } @@ -837,6 +865,10 @@ static int compact_finished(struct zone *zone, /* Compaction run completes if the migrate and free scanner meet */ if (cc->free_pfn <= cc->migrate_pfn) { + /* Let the next compaction start anew. */ + zone->compact_cached_migrate_pfn = zone->zone_start_pfn; + zone->compact_cached_free_pfn = zone_end_pfn(zone); + /* * Mark that the PG_migrate_skip information should be cleared * by kswapd when it goes to sleep. kswapd does not set the @@ -947,6 +979,14 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) } /* + * Clear pageblock skip if there were failures recently and compaction + * is about to be retried after being deferred. kswapd does not do + * this reset as it'll reset the cached information when going to sleep. + */ + if (compaction_restarting(zone, cc->order) && !current_is_kswapd()) + __reset_isolation_suitable(zone); + + /* * Setup to move all movable pages to the end of the zone. Used cached * information on where the scanners should start but check that it * is initialised by ensuring the values are within zone boundaries. @@ -962,13 +1002,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) zone->compact_cached_migrate_pfn = cc->migrate_pfn; } - /* - * Clear pageblock skip if there were failures recently and compaction - * is about to be retried after being deferred. kswapd does not do - * this reset as it'll reset the cached information when going to sleep. - */ - if (compaction_restarting(zone, cc->order) && !current_is_kswapd()) - __reset_isolation_suitable(zone); + trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn); migrate_prep_local(); @@ -1003,7 +1037,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) if (err) { putback_movable_pages(&cc->migratepages); cc->nr_migratepages = 0; - if (err == -ENOMEM) { + /* + * migrate_pages() may return -ENOMEM when scanners meet + * and we want compact_finished() to detect it + */ + if (err == -ENOMEM && cc->free_pfn > cc->migrate_pfn) { ret = COMPACT_PARTIAL; goto out; } @@ -1015,6 +1053,8 @@ out: cc->nr_freepages -= release_freepages(&cc->freepages); VM_BUG_ON(cc->nr_freepages != 0); + trace_mm_compaction_end(ret); + return ret; } @@ -1120,12 +1160,11 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) compact_zone(zone, cc); if (cc->order > 0) { - int ok = zone_watermark_ok(zone, cc->order, - low_wmark_pages(zone), 0, 0); - if (ok && cc->order >= zone->compact_order_failed) - zone->compact_order_failed = cc->order + 1; + if (zone_watermark_ok(zone, cc->order, + low_wmark_pages(zone), 0, 0)) + compaction_defer_reset(zone, cc->order, false); /* Currently async compaction is never deferred. */ - else if (!ok && cc->sync) + else if (cc->sync) defer_compaction(zone, cc->order); } @@ -1152,6 +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); @@ -1191,7 +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 000000000000..e10ccd299d66 --- /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 b7749a92021c..27ebc0c9571b 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 @@ -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); @@ -409,9 +474,9 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) { int error; - VM_BUG_ON(!PageLocked(old)); - VM_BUG_ON(!PageLocked(new)); - VM_BUG_ON(new->mapping); + VM_BUG_ON_PAGE(!PageLocked(old), old); + VM_BUG_ON_PAGE(!PageLocked(new), new); + VM_BUG_ON_PAGE(new->mapping, new); error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM); if (!error) { @@ -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; - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(PageSwapBacked(page)); + 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; - error = mem_cgroup_cache_charge(page, current->mm, + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageSwapBacked(page), page); + + 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; } @@ -607,7 +738,7 @@ EXPORT_SYMBOL_GPL(add_page_wait_queue); */ void unlock_page(struct page *page) { - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); clear_bit_unlock(PG_locked, &page->flags); smp_mb__after_clear_bit(); wake_up_page(page, PG_locked); @@ -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 * - * Is there a pagecache struct page at the given (mapping, offset) tuple? - * If yes, increment its refcount and return it; if no, return NULL. + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. + * + * 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? */ @@ -760,10 +1004,33 @@ repeat: page_cache_release(page); goto repeat; } - VM_BUG_ON(page->index != offset); + VM_BUG_ON_PAGE(page->index != offset, page); } 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 @@ -1428,30 +1767,28 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, if (!count) goto out; /* skip atime */ size = i_size_read(inode); - if (pos < size) { - retval = filemap_write_and_wait_range(mapping, pos, + retval = filemap_write_and_wait_range(mapping, pos, pos + iov_length(iov, nr_segs) - 1); - if (!retval) { - retval = mapping->a_ops->direct_IO(READ, iocb, - iov, pos, nr_segs); - } - if (retval > 0) { - *ppos = pos + retval; - count -= retval; - } + if (!retval) { + retval = mapping->a_ops->direct_IO(READ, iocb, + iov, pos, nr_segs); + } + if (retval > 0) { + *ppos = pos + retval; + count -= retval; + } - /* - * Btrfs can have a short DIO read if we encounter - * compressed extents, so if there was an error, or if - * we've already read everything we wanted to, or if - * there was a short read because we hit EOF, go ahead - * and return. Otherwise fallthrough to buffered io for - * the rest of the read. - */ - if (retval < 0 || !count || *ppos >= size) { - file_accessed(filp); - goto out; - } + /* + * Btrfs can have a short DIO read if we encounter + * compressed extents, so if there was an error, or if + * we've already read everything we wanted to, or if + * there was a short read because we hit EOF, go ahead + * and return. Otherwise fallthrough to buffered io for + * the rest of the read. + */ + if (retval < 0 || !count || *ppos >= size) { + file_accessed(filp); + goto out; } } @@ -1616,11 +1953,11 @@ 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; /* @@ -1656,7 +1993,7 @@ retry_find: put_page(page); goto retry_find; } - VM_BUG_ON(page->index != offset); + VM_BUG_ON_PAGE(page->index != offset, page); /* * We have a locked page in the page cache, now we need to check @@ -1669,8 +2006,8 @@ 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; @@ -1728,6 +2065,78 @@ 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; @@ -1757,6 +2166,7 @@ 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, }; @@ -1797,6 +2207,18 @@ 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 *), @@ -1823,6 +2245,8 @@ repeat: if (err < 0) { page_cache_release(page); page = ERR_PTR(err); + } else { + page = wait_on_page_read(page); } } return page; @@ -1859,6 +2283,10 @@ 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); @@ -1866,40 +2294,25 @@ 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. @@ -1918,31 +2331,10 @@ 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) { @@ -2555,8 +2947,8 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, 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 bbc4d660221a..34feba60a17e 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 95d1acb0f3d2..64635f5278ff 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -130,8 +130,14 @@ static int set_recommended_min_free_kbytes(void) (unsigned long) nr_free_buffer_pages() / 20); recommended_min <<= (PAGE_SHIFT-10); - if (recommended_min > min_free_kbytes) + if (recommended_min > min_free_kbytes) { + if (user_min_free_kbytes >= 0) + pr_info("raising min_free_kbytes from %d to %lu " + "to help transparent hugepage allocations\n", + min_free_kbytes, recommended_min); + min_free_kbytes = recommended_min; + } setup_per_zone_wmarks(); return 0; } @@ -655,7 +661,7 @@ out: hugepage_exit_sysfs(hugepage_kobj); return err; } -module_init(hugepage_init) +subsys_initcall(hugepage_init); static int __init setup_transparent_hugepage(char *str) { @@ -712,7 +718,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, pgtable_t pgtable; spinlock_t *ptl; - VM_BUG_ON(!PageCompound(page)); + VM_BUG_ON_PAGE(!PageCompound(page), page); pgtable = pte_alloc_one(mm, haddr); if (unlikely(!pgtable)) return VM_FAULT_OOM; @@ -821,7 +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; @@ -893,7 +899,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, goto out; } src_page = pmd_page(pmd); - VM_BUG_ON(!PageHead(src_page)); + VM_BUG_ON_PAGE(!PageHead(src_page), src_page); get_page(src_page); page_dup_rmap(src_page); add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); @@ -935,81 +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, @@ -1037,7 +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]); @@ -1067,7 +998,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_same(*pmd, orig_pmd))) goto out_free_pages; - VM_BUG_ON(!PageHead(page)); + VM_BUG_ON_PAGE(!PageHead(page), page); pmdp_clear_flush(vma, haddr, pmd); /* leave pmd empty until pte is filled */ @@ -1133,7 +1064,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, goto out_unlock; page = pmd_page(orig_pmd); - VM_BUG_ON(!PageCompound(page) || !PageHead(page)); + VM_BUG_ON_PAGE(!PageCompound(page) || !PageHead(page), page); if (page_mapcount(page) == 1) { pmd_t entry; entry = pmd_mkyoung(orig_pmd); @@ -1155,27 +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; } @@ -1211,7 +1145,7 @@ alloc: add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR); put_huge_zero_page(); } else { - VM_BUG_ON(!PageHead(page)); + VM_BUG_ON_PAGE(!PageHead(page), page); page_remove_rmap(page); put_page(page); } @@ -1249,7 +1183,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, goto out; page = pmd_page(*pmd); - VM_BUG_ON(!PageHead(page)); + VM_BUG_ON_PAGE(!PageHead(page), page); if (flags & FOLL_TOUCH) { pmd_t _pmd; /* @@ -1274,7 +1208,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, } } page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; - VM_BUG_ON(!PageCompound(page)); + VM_BUG_ON_PAGE(!PageCompound(page), page); if (flags & FOLL_GET) get_page_foll(page); @@ -1432,9 +1366,9 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, } else { page = pmd_page(orig_pmd); page_remove_rmap(page); - VM_BUG_ON(page_mapcount(page) < 0); + VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); - VM_BUG_ON(!PageHead(page)); + VM_BUG_ON_PAGE(!PageHead(page), page); atomic_long_dec(&tlb->mm->nr_ptes); spin_unlock(ptl); tlb_remove_page(tlb, page); @@ -1502,19 +1436,15 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); pmd = pmdp_get_and_clear(mm, old_addr, old_pmd); VM_BUG_ON(!pmd_none(*new_pmd)); - set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd)); - if (new_ptl != old_ptl) { - pgtable_t pgtable; - /* - * Move preallocated PTE page table if new_pmd is on - * different PMD page table. - */ + if (pmd_move_must_withdraw(new_ptl, old_ptl)) { + pgtable_t pgtable; pgtable = pgtable_trans_huge_withdraw(mm, old_pmd); pgtable_trans_huge_deposit(mm, new_pmd, pgtable); - - spin_unlock(new_ptl); } + set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd)); + if (new_ptl != old_ptl) + spin_unlock(new_ptl); spin_unlock(old_ptl); } out: @@ -1543,6 +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); @@ -1555,16 +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); } @@ -1961,22 +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; /* @@ -2176,9 +2106,9 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, if (unlikely(!page)) goto out; - VM_BUG_ON(PageCompound(page)); - BUG_ON(!PageAnon(page)); - VM_BUG_ON(!PageSwapBacked(page)); + VM_BUG_ON_PAGE(PageCompound(page), page); + VM_BUG_ON_PAGE(!PageAnon(page), page); + VM_BUG_ON_PAGE(!PageSwapBacked(page), page); /* cannot use mapcount: can't collapse if there's a gup pin */ if (page_count(page) != 1) @@ -2201,8 +2131,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, } /* 0 stands for page_is_file_cache(page) == false */ inc_zone_page_state(page, NR_ISOLATED_ANON + 0); - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageLRU(page), page); /* If there is no mapped pte young don't collapse the page */ if (pte_young(pteval) || PageReferenced(page) || @@ -2232,7 +2162,7 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, } else { src_page = pte_page(pteval); copy_user_highpage(page, src_page, address, vma); - VM_BUG_ON(page_mapcount(src_page) != 1); + VM_BUG_ON_PAGE(page_mapcount(src_page) != 1, src_page); release_pte_page(src_page); /* * ptl mostly unnecessary, but preempt has to @@ -2311,7 +2241,7 @@ static struct page struct vm_area_struct *vma, unsigned long address, int node) { - VM_BUG_ON(*hpage); + VM_BUG_ON_PAGE(*hpage, *hpage); /* * Allocate the page while the vma is still valid and under * the mmap_sem read mode so there is no memory allocation @@ -2429,7 +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; /* @@ -2580,7 +2510,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, */ node = page_to_nid(page); khugepaged_node_load[node]++; - VM_BUG_ON(PageCompound(page)); + VM_BUG_ON_PAGE(PageCompound(page), page); if (!PageLRU(page) || PageLocked(page) || !PageAnon(page)) goto out_unmap; /* cannot use mapcount: can't collapse if there's a gup pin */ @@ -2876,7 +2806,7 @@ again: return; } page = pmd_page(*pmd); - VM_BUG_ON(!page_count(page)); + VM_BUG_ON_PAGE(!page_count(page), page); get_page(page); spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index dee6cf4e6d34..dd30f22b35e0 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; @@ -584,7 +621,7 @@ static void update_and_free_page(struct hstate *h, struct page *page) 1 << PG_active | 1 << PG_reserved | 1 << PG_private | 1 << PG_writeback); } - VM_BUG_ON(hugetlb_cgroup_from_page(page)); + VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page); set_compound_page_dtor(page, NULL); set_page_refcounted(page); arch_release_hugepage(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; @@ -690,15 +728,11 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order) */ int PageHuge(struct page *page) { - compound_page_dtor *dtor; - if (!PageCompound(page)) return 0; page = compound_head(page); - dtor = get_compound_page_dtor(page); - - return dtor == free_huge_page; + return get_compound_page_dtor(page) == free_huge_page; } EXPORT_SYMBOL_GPL(PageHuge); @@ -708,16 +742,11 @@ EXPORT_SYMBOL_GPL(PageHuge); */ int PageHeadHuge(struct page *page_head) { - compound_page_dtor *dtor; - if (!PageHead(page_head)) return 0; - dtor = get_compound_page_dtor(page_head); - - return dtor == free_huge_page; + return get_compound_page_dtor(page_head) == free_huge_page; } -EXPORT_SYMBOL_GPL(PageHeadHuge); pgoff_t __basepage_index(struct page *page) { @@ -1098,7 +1127,7 @@ retry: * no users -- drop the buddy allocator's reference. */ put_page_testzero(page); - VM_BUG_ON(page_count(page)); + VM_BUG_ON_PAGE(page_count(page), page); enqueue_huge_page(h, page); } free: @@ -1159,45 +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, @@ -1280,9 +1298,9 @@ int __weak alloc_bootmem_huge_page(struct hstate *h) for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) { void *addr; - addr = __alloc_bootmem_node_nopanic(NODE_DATA(node), - huge_page_size(h), huge_page_size(h), 0); - + addr = memblock_virt_alloc_try_nid_nopanic( + huge_page_size(h), huge_page_size(h), + 0, BOOTMEM_ALLOC_ACCESSIBLE, node); if (addr) { /* * Use the beginning of the huge page to store the @@ -1303,7 +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); @@ -1322,8 +1340,8 @@ static void __init gather_bootmem_prealloc(void) #ifdef CONFIG_HIGHMEM page = pfn_to_page(m->phys >> PAGE_SHIFT); - free_bootmem_late((unsigned long)m, - sizeof(struct huge_bootmem_page)); + memblock_free_late(__pa(m), + sizeof(struct huge_bootmem_page)); #else page = virt_to_page(m); #endif @@ -1518,6 +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)) @@ -1953,11 +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 @@ -1982,6 +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); @@ -2260,41 +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) { - start = vma_hugecache_offset(h, vma, vma->vm_start); - end = vma_hugecache_offset(h, vma, vma->vm_end); + if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + return; - reserve = (end - start) - - region_count(&resv->regions, start, end); + start = vma_hugecache_offset(h, vma, vma->vm_start); + end = vma_hugecache_offset(h, vma, vma->vm_end); - resv_map_put(vma); + reserve = (end - start) - region_count(resv, start, end); - if (reserve) { - hugetlb_acct_memory(h, -reserve); - hugepage_subpool_put_pages(spool, reserve); - } + kref_put(&resv->refs, resv_map_release); + + if (reserve) { + hugetlb_acct_memory(h, -reserve); + hugepage_subpool_put_pages(spool, reserve); } } @@ -2355,17 +2377,27 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, int cow; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); + unsigned long mmun_start; /* For mmu_notifiers */ + unsigned long mmun_end; /* For mmu_notifiers */ + int ret = 0; cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; + mmun_start = vma->vm_start; + mmun_end = vma->vm_end; + if (cow) + mmu_notifier_invalidate_range_start(src, mmun_start, mmun_end); + for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; src_pte = huge_pte_offset(src, addr); if (!src_pte) continue; dst_pte = huge_pte_alloc(dst, addr, sz); - if (!dst_pte) - goto nomem; + if (!dst_pte) { + ret = -ENOMEM; + break; + } /* If the pagetables are shared don't copy or take references */ if (dst_pte == src_pte) @@ -2386,10 +2418,11 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, spin_unlock(src_ptl); spin_unlock(dst_ptl); } - return 0; -nomem: - return -ENOMEM; + if (cow) + mmu_notifier_invalidate_range_end(src, mmun_start, mmun_end); + + return ret; } static int is_hugetlb_entry_migration(pte_t pte) @@ -2659,7 +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 @@ -2703,7 +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 */ @@ -2759,15 +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; @@ -2782,9 +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. @@ -2869,8 +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))); @@ -2894,17 +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); @@ -2923,15 +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; } @@ -3000,8 +3070,7 @@ out_ptl: put_page(page); out_mutex: - mutex_unlock(&hugetlb_instantiation_mutex); - + mutex_unlock(&htlb_fault_mutex_table[hash]); return ret; } @@ -3079,7 +3148,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, same_page: if (pages) { pages[i] = mem_map_offset(page, pfn_offset); - get_page(pages[i]); + get_page_foll(pages[i]); } if (vmas) @@ -3118,6 +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; @@ -3147,6 +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; } @@ -3159,6 +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 @@ -3174,10 +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; @@ -3220,20 +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); @@ -3444,7 +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) { @@ -3501,7 +3579,7 @@ int dequeue_hwpoisoned_huge_page(struct page *hpage) bool isolate_huge_page(struct page *page, struct list_head *list) { - VM_BUG_ON(!PageHead(page)); + VM_BUG_ON_PAGE(!PageHead(page), page); if (!get_page_unless_zero(page)) return false; spin_lock(&hugetlb_lock); @@ -3512,7 +3590,7 @@ bool isolate_huge_page(struct page *page, struct list_head *list) void putback_active_hugepage(struct page *page) { - VM_BUG_ON(!PageHead(page)); + VM_BUG_ON_PAGE(!PageHead(page), page); spin_lock(&hugetlb_lock); list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist); spin_unlock(&hugetlb_lock); @@ -3521,7 +3599,7 @@ void putback_active_hugepage(struct page *page) bool is_hugepage_active(struct page *page) { - VM_BUG_ON(!PageHuge(page)); + VM_BUG_ON_PAGE(!PageHuge(page), page); /* * This function can be called for a tail page because the caller, * scan_movable_pages, scans through a given pfn-range which typically diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index bda8e44f6fde..595d7fd795e1 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) @@ -242,26 +241,20 @@ void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, return; } -static ssize_t hugetlb_cgroup_read(struct cgroup_subsys_state *css, - struct cftype *cft, struct file *file, - char __user *buf, size_t nbytes, - loff_t *ppos) +static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) { - u64 val; - char str[64]; - int idx, name, len; + int idx, name; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); idx = MEMFILE_IDX(cft->private); name = MEMFILE_ATTR(cft->private); - val = res_counter_read_u64(&h_cg->hugepage[idx], name); - len = scnprintf(str, sizeof(str), "%llu\n", (unsigned long long)val); - return simple_read_from_buffer(buf, nbytes, ppos, str, len); + return res_counter_read_u64(&h_cg->hugepage[idx], name); } 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; @@ -337,34 +330,34 @@ static void __init __hugetlb_cgroup_file_init(int idx) cft = &h->cgroup_files[0]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf); cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT); - cft->read = hugetlb_cgroup_read; + cft->read_u64 = hugetlb_cgroup_read_u64; cft->write_string = hugetlb_cgroup_write; /* Add the usage file */ cft = &h->cgroup_files[1]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.usage_in_bytes", buf); cft->private = MEMFILE_PRIVATE(idx, RES_USAGE); - cft->read = hugetlb_cgroup_read; + cft->read_u64 = hugetlb_cgroup_read_u64; /* Add the MAX usage file */ cft = &h->cgroup_files[2]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf); cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE); cft->trigger = hugetlb_cgroup_reset; - cft->read = hugetlb_cgroup_read; + cft->read_u64 = hugetlb_cgroup_read_u64; /* Add the failcntfile */ cft = &h->cgroup_files[3]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf); cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT); cft->trigger = hugetlb_cgroup_reset; - cft->read = hugetlb_cgroup_read; + cft->read_u64 = hugetlb_cgroup_read_u64; /* NULL terminate the last cft */ 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; } @@ -396,7 +389,7 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage) if (hugetlb_cgroup_disabled()) return; - VM_BUG_ON(!PageHuge(oldhpage)); + VM_BUG_ON_PAGE(!PageHuge(oldhpage), oldhpage); spin_lock(&hugetlb_lock); h_cg = hugetlb_cgroup_from_page(oldhpage); set_hugetlb_cgroup(oldhpage, NULL); @@ -408,10 +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/hwpoison-inject.c b/mm/hwpoison-inject.c index 4c84678371eb..95487c71cad5 100644 --- a/mm/hwpoison-inject.c +++ b/mm/hwpoison-inject.c @@ -55,7 +55,7 @@ static int hwpoison_inject(void *data, u64 val) return 0; inject: - printk(KERN_INFO "Injecting memory failure at pfn %lx\n", pfn); + pr_info("Injecting memory failure at pfn %#lx\n", pfn); return memory_failure(pfn, 18, MF_COUNT_INCREASED); } diff --git a/mm/internal.h b/mm/internal.h index 684f7aa9692a..07b67361a40a 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, @@ -21,14 +22,28 @@ 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. */ static inline void set_page_refcounted(struct page *page) { - VM_BUG_ON(PageTail(page)); - VM_BUG_ON(atomic_read(&page->_count)); + VM_BUG_ON_PAGE(PageTail(page), page); + VM_BUG_ON_PAGE(atomic_read(&page->_count), page); set_page_count(page, 1); } @@ -46,12 +61,10 @@ static inline void __get_page_tail_foll(struct page *page, * speculative page access (like in * page_cache_get_speculative()) on tail pages. */ - VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0); - VM_BUG_ON(atomic_read(&page->_count) != 0); - VM_BUG_ON(page_mapcount(page) < 0); + VM_BUG_ON_PAGE(atomic_read(&page->first_page->_count) <= 0, page); if (get_page_head) atomic_inc(&page->first_page->_count); - atomic_inc(&page->_mapcount); + get_huge_page_tail(page); } /* @@ -73,7 +86,7 @@ static inline void get_page_foll(struct page *page) * Getting a normal page or the head of a compound page * requires to already have an elevated page->_count. */ - VM_BUG_ON(atomic_read(&page->_count) <= 0); + VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page); atomic_inc(&page->_count); } } @@ -85,7 +98,6 @@ extern unsigned long highest_memmap_pfn; */ extern int isolate_lru_page(struct page *page); extern void putback_lru_page(struct page *page); -extern unsigned long zone_reclaimable_pages(struct zone *zone); extern bool zone_reclaimable(struct zone *zone); /* @@ -101,6 +113,7 @@ extern void prep_compound_page(struct page *page, unsigned long order); #ifdef CONFIG_MEMORY_FAILURE extern bool is_free_buddy_page(struct page *page); #endif +extern int user_min_free_kbytes; #if defined CONFIG_COMPACTION || defined CONFIG_CMA @@ -144,9 +157,11 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, #endif /* - * function for dealing with page's order in buddy system. - * zone->lock is already acquired when we use these. - * So, we don't need atomic page->flags operations here. + * This function returns the order of a free page in the buddy system. In + * general, page_zone(page)->lock must be held by the caller to prevent the + * page from being allocated in parallel and returning garbage as the order. + * If a caller does not hold page_zone(page)->lock, it must guarantee that the + * page cannot be allocated or merged in parallel. */ static inline unsigned long page_order(struct page *page) { @@ -175,7 +190,7 @@ static inline void munlock_vma_pages_all(struct vm_area_struct *vma) static inline int mlocked_vma_newpage(struct vm_area_struct *vma, struct page *page) { - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) return 0; @@ -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/kmemleak.c b/mm/kmemleak.c index 31f01c5011e5..91d67eaee050 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. @@ -1891,21 +1891,24 @@ struct page *ksm_might_need_to_copy(struct page *page, return new_page; } -int page_referenced_ksm(struct page *page, struct mem_cgroup *memcg, - unsigned long *vm_flags) +int rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc) { struct stable_node *stable_node; struct rmap_item *rmap_item; - unsigned int mapcount = page_mapcount(page); - int referenced = 0; + int ret = SWAP_AGAIN; int search_new_forks = 0; - VM_BUG_ON(!PageKsm(page)); - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageKsm(page), page); + + /* + * Rely on the page lock to protect against concurrent modifications + * to that page's node of the stable tree. + */ + VM_BUG_ON_PAGE(!PageLocked(page), page); stable_node = page_stable_node(page); if (!stable_node) - return 0; + return ret; again: hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { struct anon_vma *anon_vma = rmap_item->anon_vma; @@ -1928,113 +1931,16 @@ again: if ((rmap_item->mm == vma->vm_mm) == search_new_forks) continue; - if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) - continue; - - referenced += page_referenced_one(page, vma, - rmap_item->address, &mapcount, vm_flags); - if (!search_new_forks || !mapcount) - break; - } - anon_vma_unlock_read(anon_vma); - if (!mapcount) - goto out; - } - if (!search_new_forks++) - goto again; -out: - return referenced; -} - -int try_to_unmap_ksm(struct page *page, enum ttu_flags flags) -{ - struct stable_node *stable_node; - struct rmap_item *rmap_item; - int ret = SWAP_AGAIN; - int search_new_forks = 0; - - VM_BUG_ON(!PageKsm(page)); - VM_BUG_ON(!PageLocked(page)); - - stable_node = page_stable_node(page); - if (!stable_node) - return SWAP_FAIL; -again: - hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { - struct anon_vma *anon_vma = rmap_item->anon_vma; - struct anon_vma_chain *vmac; - struct vm_area_struct *vma; - - anon_vma_lock_read(anon_vma); - anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root, - 0, ULONG_MAX) { - vma = vmac->vma; - if (rmap_item->address < vma->vm_start || - rmap_item->address >= vma->vm_end) - continue; - /* - * Initially we examine only the vma which covers this - * rmap_item; but later, if there is still work to do, - * we examine covering vmas in other mms: in case they - * were forked from the original since ksmd passed. - */ - if ((rmap_item->mm == vma->vm_mm) == search_new_forks) + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; - ret = try_to_unmap_one(page, vma, - rmap_item->address, flags); - if (ret != SWAP_AGAIN || !page_mapped(page)) { + ret = rwc->rmap_one(page, vma, + rmap_item->address, rwc->arg); + if (ret != SWAP_AGAIN) { anon_vma_unlock_read(anon_vma); goto out; } - } - anon_vma_unlock_read(anon_vma); - } - if (!search_new_forks++) - goto again; -out: - return ret; -} - -#ifdef CONFIG_MIGRATION -int rmap_walk_ksm(struct page *page, int (*rmap_one)(struct page *, - struct vm_area_struct *, unsigned long, void *), void *arg) -{ - struct stable_node *stable_node; - struct rmap_item *rmap_item; - int ret = SWAP_AGAIN; - int search_new_forks = 0; - - VM_BUG_ON(!PageKsm(page)); - VM_BUG_ON(!PageLocked(page)); - - stable_node = page_stable_node(page); - if (!stable_node) - return ret; -again: - hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { - struct anon_vma *anon_vma = rmap_item->anon_vma; - struct anon_vma_chain *vmac; - struct vm_area_struct *vma; - - anon_vma_lock_read(anon_vma); - anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root, - 0, ULONG_MAX) { - vma = vmac->vma; - if (rmap_item->address < vma->vm_start || - rmap_item->address >= vma->vm_end) - continue; - /* - * Initially we examine only the vma which covers this - * rmap_item; but later, if there is still work to do, - * we examine covering vmas in other mms: in case they - * were forked from the original since ksmd passed. - */ - if ((rmap_item->mm == vma->vm_mm) == search_new_forks) - continue; - - ret = rmap_one(page, vma, rmap_item->address, arg); - if (ret != SWAP_AGAIN) { + if (rwc->done && rwc->done(page)) { anon_vma_unlock_read(anon_vma); goto out; } @@ -2047,17 +1953,18 @@ out: return ret; } +#ifdef CONFIG_MIGRATION void ksm_migrate_page(struct page *newpage, struct page *oldpage) { struct stable_node *stable_node; - VM_BUG_ON(!PageLocked(oldpage)); - VM_BUG_ON(!PageLocked(newpage)); - VM_BUG_ON(newpage->mapping != oldpage->mapping); + VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); + VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); + VM_BUG_ON_PAGE(newpage->mapping != oldpage->mapping, newpage); stable_node = page_stable_node(newpage); if (stable_node) { - VM_BUG_ON(stable_node->kpfn != page_to_pfn(oldpage)); + VM_BUG_ON_PAGE(stable_node->kpfn != page_to_pfn(oldpage), oldpage); stable_node->kpfn = page_to_pfn(newpage); /* * newpage->mapping was set in advance; now we need smp_wmb() @@ -2438,4 +2345,4 @@ out_free: out: return err; } -module_init(ksm_init) +subsys_initcall(ksm_init); diff --git a/mm/list_lru.c b/mm/list_lru.c index 72f9decb0104..f1a0db194173 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 53e477bb5558..e9d6ca9a01a9 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -21,6 +21,9 @@ #include <linux/memblock.h> #include <asm-generic/sections.h> +#include <linux/io.h> + +#include "internal.h" static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; @@ -39,6 +42,9 @@ struct memblock memblock __initdata_memblock = { }; int memblock_debug __initdata_memblock; +#ifdef CONFIG_MOVABLE_NODE +bool movable_node_enabled __initdata_memblock = false; +#endif static int memblock_can_resize __initdata_memblock; static int memblock_memory_in_slab __initdata_memblock = 0; static int memblock_reserved_in_slab __initdata_memblock = 0; @@ -91,7 +97,7 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type, * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} * @size: size of free area to find * @align: alignment of free area to find - * @nid: nid of the free area to find, %MAX_NUMNODES for any node + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Utility called from memblock_find_in_range_node(), find free area bottom-up. * @@ -123,7 +129,7 @@ __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} * @size: size of free area to find * @align: alignment of free area to find - * @nid: nid of the free area to find, %MAX_NUMNODES for any node + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Utility called from memblock_find_in_range_node(), find free area top-down. * @@ -154,11 +160,11 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, /** * memblock_find_in_range_node - find free area in given range and node - * @start: start of candidate range - * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} * @size: size of free area to find * @align: alignment of free area to find - * @nid: nid of the free area to find, %MAX_NUMNODES for any node + * @start: start of candidate range + * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Find @size free area aligned to @align in the specified range and node. * @@ -173,9 +179,9 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, * RETURNS: * Found address on success, 0 on failure. */ -phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start, - phys_addr_t end, phys_addr_t size, - phys_addr_t align, int nid) +phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, + phys_addr_t align, phys_addr_t start, + phys_addr_t end, int nid) { int ret; phys_addr_t kernel_end; @@ -238,8 +244,8 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align) { - return memblock_find_in_range_node(start, end, size, align, - MAX_NUMNODES); + return memblock_find_in_range_node(size, align, start, end, + NUMA_NO_NODE); } static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r) @@ -255,10 +261,13 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u type->cnt = 1; type->regions[0].base = 0; type->regions[0].size = 0; + type->regions[0].flags = 0; memblock_set_region_node(&type->regions[0], MAX_NUMNODES); } } +#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK + phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info( phys_addr_t *addr) { @@ -271,6 +280,20 @@ phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info( memblock.reserved.max); } +phys_addr_t __init_memblock get_allocated_memblock_memory_regions_info( + phys_addr_t *addr) +{ + if (memblock.memory.regions == memblock_memory_init_regions) + return 0; + + *addr = __pa(memblock.memory.regions); + + return PAGE_ALIGN(sizeof(struct memblock_region) * + memblock.memory.max); +} + +#endif + /** * memblock_double_array - double the size of the memblock regions array * @type: memblock type of the regions array being doubled @@ -405,7 +428,8 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type) if (this->base + this->size != next->base || memblock_get_region_node(this) != - memblock_get_region_node(next)) { + memblock_get_region_node(next) || + this->flags != next->flags) { BUG_ON(this->base + this->size > next->base); i++; continue; @@ -425,13 +449,15 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type) * @base: base address of the new region * @size: size of the new region * @nid: node id of the new region + * @flags: flags of the new region * * Insert new memblock region [@base,@base+@size) into @type at @idx. * @type must already have extra room to accomodate the new region. */ static void __init_memblock memblock_insert_region(struct memblock_type *type, int idx, phys_addr_t base, - phys_addr_t size, int nid) + phys_addr_t size, + int nid, unsigned long flags) { struct memblock_region *rgn = &type->regions[idx]; @@ -439,6 +465,7 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type, memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn)); rgn->base = base; rgn->size = size; + rgn->flags = flags; memblock_set_region_node(rgn, nid); type->cnt++; type->total_size += size; @@ -450,6 +477,7 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type, * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region + * @flags: flags of the new region * * Add new memblock region [@base,@base+@size) into @type. The new region * is allowed to overlap with existing ones - overlaps don't affect already @@ -460,7 +488,8 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type, * 0 on success, -errno on failure. */ static int __init_memblock memblock_add_region(struct memblock_type *type, - phys_addr_t base, phys_addr_t size, int nid) + phys_addr_t base, phys_addr_t size, + int nid, unsigned long flags) { bool insert = false; phys_addr_t obase = base; @@ -475,6 +504,7 @@ static int __init_memblock memblock_add_region(struct memblock_type *type, WARN_ON(type->cnt != 1 || type->total_size); type->regions[0].base = base; type->regions[0].size = size; + type->regions[0].flags = flags; memblock_set_region_node(&type->regions[0], nid); type->total_size = size; return 0; @@ -505,7 +535,8 @@ repeat: nr_new++; if (insert) memblock_insert_region(type, i++, base, - rbase - base, nid); + rbase - base, nid, + flags); } /* area below @rend is dealt with, forget about it */ base = min(rend, end); @@ -515,7 +546,8 @@ repeat: if (base < end) { nr_new++; if (insert) - memblock_insert_region(type, i, base, end - base, nid); + memblock_insert_region(type, i, base, end - base, + nid, flags); } /* @@ -537,12 +569,13 @@ repeat: int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, int nid) { - return memblock_add_region(&memblock.memory, base, size, nid); + return memblock_add_region(&memblock.memory, base, size, nid, 0); } int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) { - return memblock_add_region(&memblock.memory, base, size, MAX_NUMNODES); + return memblock_add_region(&memblock.memory, base, size, + MAX_NUMNODES, 0); } /** @@ -597,7 +630,8 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, rgn->size -= base - rbase; type->total_size -= base - rbase; memblock_insert_region(type, i, rbase, base - rbase, - memblock_get_region_node(rgn)); + memblock_get_region_node(rgn), + rgn->flags); } else if (rend > end) { /* * @rgn intersects from above. Split and redo the @@ -607,7 +641,8 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, rgn->size -= end - rbase; type->total_size -= end - rbase; memblock_insert_region(type, i--, rbase, end - rbase, - memblock_get_region_node(rgn)); + memblock_get_region_node(rgn), + rgn->flags); } else { /* @rgn is fully contained, record it */ if (!*end_rgn) @@ -643,28 +678,89 @@ int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) { memblock_dbg(" memblock_free: [%#016llx-%#016llx] %pF\n", (unsigned long long)base, - (unsigned long long)base + size, + (unsigned long long)base + size - 1, (void *)_RET_IP_); return __memblock_remove(&memblock.reserved, base, size); } -int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) +static int __init_memblock memblock_reserve_region(phys_addr_t base, + phys_addr_t size, + int nid, + unsigned long flags) { struct memblock_type *_rgn = &memblock.reserved; - memblock_dbg("memblock_reserve: [%#016llx-%#016llx] %pF\n", + memblock_dbg("memblock_reserve: [%#016llx-%#016llx] flags %#02lx %pF\n", (unsigned long long)base, - (unsigned long long)base + size, - (void *)_RET_IP_); + (unsigned long long)base + size - 1, + flags, (void *)_RET_IP_); + + return memblock_add_region(_rgn, base, size, nid, flags); +} + +int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) +{ + return memblock_reserve_region(base, size, MAX_NUMNODES, 0); +} + +/** + * memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG. + * @base: the base phys addr of the region + * @size: the size of the region + * + * This function isolates region [@base, @base + @size), and mark it with flag + * MEMBLOCK_HOTPLUG. + * + * Return 0 on succees, -errno on failure. + */ +int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) +{ + struct memblock_type *type = &memblock.memory; + int i, ret, start_rgn, end_rgn; + + ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); + if (ret) + return ret; + + for (i = start_rgn; i < end_rgn; i++) + memblock_set_region_flags(&type->regions[i], MEMBLOCK_HOTPLUG); + + memblock_merge_regions(type); + return 0; +} + +/** + * memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region. + * @base: the base phys addr of the region + * @size: the size of the region + * + * This function isolates region [@base, @base + @size), and clear flag + * MEMBLOCK_HOTPLUG for the isolated regions. + * + * Return 0 on succees, -errno on failure. + */ +int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) +{ + struct memblock_type *type = &memblock.memory; + int i, ret, start_rgn, end_rgn; + + ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); + if (ret) + return ret; + + for (i = start_rgn; i < end_rgn; i++) + memblock_clear_region_flags(&type->regions[i], + MEMBLOCK_HOTPLUG); - return memblock_add_region(_rgn, base, size, MAX_NUMNODES); + memblock_merge_regions(type); + return 0; } /** * __next_free_mem_range - next function for for_each_free_mem_range() * @idx: pointer to u64 loop variable - * @nid: node selector, %MAX_NUMNODES for all nodes + * @nid: node selector, %NUMA_NO_NODE for all nodes * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL @@ -693,13 +789,16 @@ void __init_memblock __next_free_mem_range(u64 *idx, int nid, int mi = *idx & 0xffffffff; int ri = *idx >> 32; + if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) + nid = NUMA_NO_NODE; + for ( ; mi < mem->cnt; mi++) { struct memblock_region *m = &mem->regions[mi]; phys_addr_t m_start = m->base; phys_addr_t m_end = m->base + m->size; /* only memory regions are associated with nodes, check it */ - if (nid != MAX_NUMNODES && nid != memblock_get_region_node(m)) + if (nid != NUMA_NO_NODE && nid != memblock_get_region_node(m)) continue; /* scan areas before each reservation for intersection */ @@ -740,12 +839,17 @@ void __init_memblock __next_free_mem_range(u64 *idx, int nid, /** * __next_free_mem_range_rev - next function for for_each_free_mem_range_reverse() * @idx: pointer to u64 loop variable - * @nid: nid: node selector, %MAX_NUMNODES for all nodes + * @nid: nid: node selector, %NUMA_NO_NODE for all nodes * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * * Reverse of __next_free_mem_range(). + * + * Linux kernel cannot migrate pages used by itself. Memory hotplug users won't + * be able to hot-remove hotpluggable memory used by the kernel. So this + * function skip hotpluggable regions if needed when allocating memory for the + * kernel. */ void __init_memblock __next_free_mem_range_rev(u64 *idx, int nid, phys_addr_t *out_start, @@ -756,6 +860,9 @@ void __init_memblock __next_free_mem_range_rev(u64 *idx, int nid, int mi = *idx & 0xffffffff; int ri = *idx >> 32; + if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) + nid = NUMA_NO_NODE; + if (*idx == (u64)ULLONG_MAX) { mi = mem->cnt - 1; ri = rsv->cnt; @@ -767,7 +874,11 @@ void __init_memblock __next_free_mem_range_rev(u64 *idx, int nid, phys_addr_t m_end = m->base + m->size; /* only memory regions are associated with nodes, check it */ - if (nid != MAX_NUMNODES && nid != memblock_get_region_node(m)) + if (nid != NUMA_NO_NODE && nid != memblock_get_region_node(m)) + continue; + + /* skip hotpluggable memory regions if needed */ + if (movable_node_is_enabled() && memblock_is_hotpluggable(m)) continue; /* scan areas before each reservation for intersection */ @@ -837,18 +948,18 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid, * memblock_set_node - set node ID on memblock regions * @base: base of area to set node ID for * @size: size of area to set node ID for + * @type: memblock type to set node ID for * @nid: node ID to set * - * Set the nid of memblock memory regions in [@base,@base+@size) to @nid. + * Set the nid of memblock @type regions in [@base,@base+@size) to @nid. * Regions which cross the area boundaries are split as necessary. * * RETURNS: * 0 on success, -errno on failure. */ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, - int nid) + struct memblock_type *type, int nid) { - struct memblock_type *type = &memblock.memory; int start_rgn, end_rgn; int i, ret; @@ -870,13 +981,10 @@ static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size, { phys_addr_t found; - if (WARN_ON(!align)) - align = __alignof__(long long); + if (!align) + align = SMP_CACHE_BYTES; - /* align @size to avoid excessive fragmentation on reserved array */ - size = round_up(size, align); - - found = memblock_find_in_range_node(0, max_addr, size, align, nid); + found = memblock_find_in_range_node(size, align, 0, max_addr, nid); if (found && !memblock_reserve(found, size)) return found; @@ -890,7 +998,7 @@ phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int n phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr) { - return memblock_alloc_base_nid(size, align, max_addr, MAX_NUMNODES); + return memblock_alloc_base_nid(size, align, max_addr, NUMA_NO_NODE); } phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr) @@ -920,6 +1028,207 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); } +/** + * memblock_virt_alloc_internal - allocate boot memory block + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @min_addr: the lower bound of the memory region to allocate (phys address) + * @max_addr: the upper bound of the memory region to allocate (phys address) + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * + * The @min_addr limit is dropped if it can not be satisfied and the allocation + * will fall back to memory below @min_addr. Also, allocation may fall back + * to any node in the system if the specified node can not + * hold the requested memory. + * + * The allocation is performed from memory region limited by + * memblock.current_limit if @max_addr == %BOOTMEM_ALLOC_ACCESSIBLE. + * + * The memory block is aligned on SMP_CACHE_BYTES if @align == 0. + * + * The phys address of allocated boot memory block is converted to virtual and + * allocated memory is reset to 0. + * + * In addition, function sets the min_count to 0 using kmemleak_alloc for + * allocated boot memory block, so that it is never reported as leaks. + * + * RETURNS: + * Virtual address of allocated memory block on success, NULL on failure. + */ +static void * __init memblock_virt_alloc_internal( + phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid) +{ + phys_addr_t alloc; + void *ptr; + + if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) + nid = NUMA_NO_NODE; + + /* + * Detect any accidental use of these APIs after slab is ready, as at + * this moment memblock may be deinitialized already and its + * internal data may be destroyed (after execution of free_all_bootmem) + */ + if (WARN_ON_ONCE(slab_is_available())) + return kzalloc_node(size, GFP_NOWAIT, nid); + + if (!align) + align = SMP_CACHE_BYTES; + + if (max_addr > memblock.current_limit) + max_addr = memblock.current_limit; + +again: + alloc = memblock_find_in_range_node(size, align, min_addr, max_addr, + nid); + if (alloc) + goto done; + + if (nid != NUMA_NO_NODE) { + alloc = memblock_find_in_range_node(size, align, min_addr, + max_addr, NUMA_NO_NODE); + if (alloc) + goto done; + } + + if (min_addr) { + min_addr = 0; + goto again; + } else { + goto error; + } + +done: + memblock_reserve(alloc, size); + ptr = phys_to_virt(alloc); + memset(ptr, 0, size); + + /* + * The min_count is set to 0 so that bootmem allocated blocks + * are never reported as leaks. This is because many of these blocks + * are only referred via the physical address which is not + * looked up by kmemleak. + */ + kmemleak_alloc(ptr, size, 0, 0); + + return ptr; + +error: + return NULL; +} + +/** + * memblock_virt_alloc_try_nid_nopanic - allocate boot memory block + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @min_addr: the lower bound of the memory region from where the allocation + * is preferred (phys address) + * @max_addr: the upper bound of the memory region from where the allocation + * is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to + * allocate only from memory limited by memblock.current_limit value + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * + * Public version of _memblock_virt_alloc_try_nid_nopanic() which provides + * additional debug information (including caller info), if enabled. + * + * RETURNS: + * Virtual address of allocated memory block on success, NULL on failure. + */ +void * __init memblock_virt_alloc_try_nid_nopanic( + phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid) +{ + memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=0x%llx max_addr=0x%llx %pF\n", + __func__, (u64)size, (u64)align, nid, (u64)min_addr, + (u64)max_addr, (void *)_RET_IP_); + return memblock_virt_alloc_internal(size, align, min_addr, + max_addr, nid); +} + +/** + * memblock_virt_alloc_try_nid - allocate boot memory block with panicking + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @min_addr: the lower bound of the memory region from where the allocation + * is preferred (phys address) + * @max_addr: the upper bound of the memory region from where the allocation + * is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to + * allocate only from memory limited by memblock.current_limit value + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * + * Public panicking version of _memblock_virt_alloc_try_nid_nopanic() + * which provides debug information (including caller info), if enabled, + * and panics if the request can not be satisfied. + * + * RETURNS: + * Virtual address of allocated memory block on success, NULL on failure. + */ +void * __init memblock_virt_alloc_try_nid( + phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid) +{ + void *ptr; + + memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=0x%llx max_addr=0x%llx %pF\n", + __func__, (u64)size, (u64)align, nid, (u64)min_addr, + (u64)max_addr, (void *)_RET_IP_); + ptr = memblock_virt_alloc_internal(size, align, + min_addr, max_addr, nid); + if (ptr) + return ptr; + + panic("%s: Failed to allocate %llu bytes align=0x%llx nid=%d from=0x%llx max_addr=0x%llx\n", + __func__, (u64)size, (u64)align, nid, (u64)min_addr, + (u64)max_addr); + return NULL; +} + +/** + * __memblock_free_early - free boot memory block + * @base: phys starting address of the boot memory block + * @size: size of the boot memory block in bytes + * + * Free boot memory block previously allocated by memblock_virt_alloc_xx() API. + * The freeing memory will not be released to the buddy allocator. + */ +void __init __memblock_free_early(phys_addr_t base, phys_addr_t size) +{ + memblock_dbg("%s: [%#016llx-%#016llx] %pF\n", + __func__, (u64)base, (u64)base + size - 1, + (void *)_RET_IP_); + kmemleak_free_part(__va(base), size); + __memblock_remove(&memblock.reserved, base, size); +} + +/* + * __memblock_free_late - free bootmem block pages directly to buddy allocator + * @addr: phys starting address of the boot memory block + * @size: size of the boot memory block in bytes + * + * This is only useful when the bootmem allocator has already been torn + * down, but we are still initializing the system. Pages are released directly + * to the buddy allocator, no bootmem metadata is updated because it is gone. + */ +void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) +{ + u64 cursor, end; + + memblock_dbg("%s: [%#016llx-%#016llx] %pF\n", + __func__, (u64)base, (u64)base + size - 1, + (void *)_RET_IP_); + kmemleak_free_part(__va(base), size); + cursor = PFN_UP(base); + end = PFN_DOWN(base + size); + + for (; cursor < end; cursor++) { + __free_pages_bootmem(pfn_to_page(cursor), 0); + totalram_pages++; + } +} /* * Remaining API functions @@ -944,7 +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 */ @@ -962,16 +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; @@ -1017,7 +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; @@ -1070,13 +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); @@ -1084,11 +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--; } } } @@ -1098,9 +1405,15 @@ 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; + unsigned long flags; int i; pr_info(" %s.cnt = 0x%lx\n", name, type->cnt); @@ -1111,13 +1424,14 @@ static void __init_memblock memblock_dump(struct memblock_type *type, char *name base = rgn->base; size = rgn->size; + flags = rgn->flags; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP if (memblock_get_region_node(rgn) != MAX_NUMNODES) snprintf(nid_buf, sizeof(nid_buf), " on node %d", memblock_get_region_node(rgn)); #endif - pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s\n", - name, i, base, base + size - 1, size, nid_buf); + pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s flags: %#lx\n", + name, i, base, base + size - 1, size, nid_buf, flags); } } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7f1a356153c0..29501f040568 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -45,16 +45,17 @@ #include <linux/swapops.h> #include <linux/spinlock.h> #include <linux/eventfd.h> +#include <linux/poll.h> #include <linux/sort.h> #include <linux/fs.h> #include <linux/seq_file.h> -#include <linux/vmalloc.h> #include <linux/vmpressure.h> #include <linux/mm_inline.h> #include <linux/page_cgroup.h> #include <linux/cpu.h> #include <linux/oom.h> #include <linux/lockdep.h> +#include <linux/file.h> #include "internal.h" #include <net/sock.h> #include <net/ip.h> @@ -65,8 +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; @@ -148,7 +149,7 @@ struct mem_cgroup_reclaim_iter { * matches memcg->dead_count of the hierarchy root group. */ struct mem_cgroup *last_visited; - unsigned long last_dead_count; + int last_dead_count; /* scan generation, increased every round-trip */ unsigned int generation; @@ -227,6 +228,46 @@ struct mem_cgroup_eventfd_list { struct eventfd_ctx *eventfd; }; +/* + * cgroup_event represents events which userspace want to receive. + */ +struct mem_cgroup_event { + /* + * memcg which the event belongs to. + */ + struct mem_cgroup *memcg; + /* + * eventfd to signal userspace about the event. + */ + struct eventfd_ctx *eventfd; + /* + * Each of these stored in a list by the cgroup. + */ + struct list_head list; + /* + * register_event() callback will be used to add new userspace + * waiter for changes related to this event. Use eventfd_signal() + * on eventfd to send notification to userspace. + */ + int (*register_event)(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args); + /* + * unregister_event() callback will be called when userspace closes + * the eventfd or on cgroup removing. This callback must be set, + * if you want provide notification functionality. + */ + void (*unregister_event)(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd); + /* + * All fields below needed to unregister event when + * userspace closes eventfd. + */ + poll_table pt; + wait_queue_head_t *wqh; + wait_queue_t wait; + struct work_struct remove; +}; + static void mem_cgroup_threshold(struct mem_cgroup *memcg); static void mem_cgroup_oom_notify(struct mem_cgroup *memcg); @@ -331,27 +372,20 @@ struct mem_cgroup { atomic_t numainfo_updating; #endif + /* List of events which userspace want to receive */ + struct list_head event_list; + spinlock_t event_list_lock; + struct mem_cgroup_per_node *nodeinfo[0]; /* WARNING: nodeinfo must be the last member here */ }; -static size_t memcg_size(void) -{ - return sizeof(struct mem_cgroup) + - nr_node_ids * sizeof(struct mem_cgroup_per_node *); -} - /* internal only representation about the status of kmem accounting. */ enum { - KMEM_ACCOUNTED_ACTIVE = 0, /* accounted by this cgroup itself */ - KMEM_ACCOUNTED_ACTIVATED, /* static key enabled. */ + KMEM_ACCOUNTED_ACTIVE, /* accounted by this cgroup itself */ KMEM_ACCOUNTED_DEAD, /* dead memcg with pending kmem charges */ }; -/* We account when limit is on, but only after call sites are patched */ -#define KMEM_ACCOUNTED_MASK \ - ((1 << KMEM_ACCOUNTED_ACTIVE) | (1 << KMEM_ACCOUNTED_ACTIVATED)) - #ifdef CONFIG_MEMCG_KMEM static inline void memcg_kmem_set_active(struct mem_cgroup *memcg) { @@ -363,16 +397,6 @@ static bool memcg_kmem_is_active(struct mem_cgroup *memcg) return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags); } -static void memcg_kmem_set_activated(struct mem_cgroup *memcg) -{ - set_bit(KMEM_ACCOUNTED_ACTIVATED, &memcg->kmem_account_flags); -} - -static void memcg_kmem_clear_activated(struct mem_cgroup *memcg) -{ - clear_bit(KMEM_ACCOUNTED_ACTIVATED, &memcg->kmem_account_flags); -} - static void memcg_kmem_mark_dead(struct mem_cgroup *memcg) { /* @@ -490,11 +514,6 @@ struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr) return &container_of(vmpr, struct mem_cgroup, vmpressure)->css; } -struct vmpressure *css_to_vmpressure(struct cgroup_subsys_state *css) -{ - return &mem_cgroup_from_css(css)->vmpressure; -} - static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); @@ -519,7 +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); } @@ -902,8 +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. @@ -928,8 +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 @@ -1053,25 +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; @@ -1098,16 +1106,22 @@ skip_node: * skipped and we should continue the tree walk. * last_visited css is safe to use because it is * protected by css_get and the tree walk is rcu safe. + * + * We do not take a reference on the root of the tree walk + * because we might race with the root removal when it would + * be the only node in the iterated hierarchy and mem_cgroup_iter + * would end up in an endless loop because it expects that at + * least one valid node will be returned. Root cannot disappear + * because caller of the iterator should hold it already so + * skipping css reference should be safe. */ if (next_css) { - struct mem_cgroup *mem = mem_cgroup_from_css(next_css); + if ((next_css == &root->css) || + ((next_css->flags & CSS_ONLINE) && css_tryget(next_css))) + return mem_cgroup_from_css(next_css); - if (css_tryget(&mem->css)) - return mem; - else { - prev_css = next_css; - goto skip_node; - } + prev_css = next_css; + goto skip_node; } return NULL; @@ -1141,7 +1155,15 @@ mem_cgroup_iter_load(struct mem_cgroup_reclaim_iter *iter, if (iter->last_dead_count == *sequence) { smp_rmb(); position = iter->last_visited; - if (position && !css_tryget(&position->css)) + + /* + * We cannot take a reference to root because we might race + * with root removal and returning NULL would end up in + * an endless loop on the iterator user level when root + * would be returned all the time. + */ + if (position && position != root && + !css_tryget(&position->css)) position = NULL; } return position; @@ -1150,9 +1172,11 @@ mem_cgroup_iter_load(struct mem_cgroup_reclaim_iter *iter, static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter, struct mem_cgroup *last_visited, struct mem_cgroup *new_position, + struct mem_cgroup *root, int sequence) { - if (last_visited) + /* root reference counting symmetric to mem_cgroup_iter_load */ + if (last_visited && last_visited != root) css_put(&last_visited->css); /* * We store the sequence count from the time @last_visited was @@ -1227,7 +1251,8 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, memcg = __mem_cgroup_iter_next(root, last_visited); if (reclaim) { - mem_cgroup_iter_update(iter, last_visited, memcg, seq); + mem_cgroup_iter_update(iter, last_visited, memcg, root, + seq); if (!memcg) iter->generation++; @@ -1450,7 +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 { /* @@ -1464,8 +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 @@ -1647,53 +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) { - struct cgroup *task_cgrp; - struct cgroup *mem_cgrp; - /* - * Need a buffer in BSS, can't rely on allocations. The code relies - * on the assumption that OOM is serialized for memory controller. - * If this assumption is broken, revisit this code. - */ - 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; + mutex_lock(&oom_info_lock); rcu_read_lock(); - mem_cgrp = memcg->css.cgroup; - task_cgrp = task_cgroup(p, mem_cgroup_subsys_id); - - 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); + 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"); - 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, @@ -1708,13 +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++) { @@ -1730,6 +1720,7 @@ done: pr_cont("\n"); } + mutex_unlock(&oom_info_lock); } /* @@ -1822,13 +1813,18 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, break; }; points = oom_badness(task, memcg, NULL, totalpages); - if (points > chosen_points) { - if (chosen) - put_task_struct(chosen); - chosen = task; - chosen_points = points; - get_task_struct(chosen); - } + if (!points || points < chosen_points) + continue; + /* Prefer thread group leaders for display purposes */ + if (points == chosen_points && + thread_group_leader(chosen)) + continue; + + if (chosen) + put_task_struct(chosen); + chosen = task; + chosen_points = points; + get_task_struct(chosen); } css_task_iter_end(&it); } @@ -2579,7 +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 */ @@ -2652,45 +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))) @@ -2698,73 +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); @@ -2773,17 +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; } @@ -2791,20 +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. @@ -2861,7 +2808,7 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) unsigned short id; swp_entry_t ent; - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); pc = lookup_page_cgroup(page); lock_page_cgroup(pc); @@ -2895,7 +2842,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, bool anon; lock_page_cgroup(pc); - VM_BUG_ON(PageCgroupUsed(pc)); + VM_BUG_ON_PAGE(PageCgroupUsed(pc), page); /* * we don't need page_cgroup_lock about tail pages, becase they are not * accessed by any other context at this point. @@ -2930,7 +2877,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, if (lrucare) { if (was_on_lru) { lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup); - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); SetPageLRU(page); add_page_to_lru_list(page, lruvec, page_lru(page)); } @@ -2956,10 +2903,12 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, static DEFINE_MUTEX(set_limit_mutex); #ifdef CONFIG_MEMCG_KMEM +static DEFINE_MUTEX(activate_kmem_mutex); + static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg) { return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg) && - (memcg->kmem_account_flags & KMEM_ACCOUNTED_MASK); + memcg_kmem_is_active(memcg); } /* @@ -2976,10 +2925,9 @@ static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p) } #ifdef CONFIG_SLABINFO -static int mem_cgroup_slabinfo_read(struct cgroup_subsys_state *css, - struct cftype *cft, struct seq_file *m) +static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); struct memcg_cache_params *params; if (!memcg_can_account_kmem(memcg)) @@ -2999,20 +2947,17 @@ static int mem_cgroup_slabinfo_read(struct cgroup_subsys_state *css, 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 @@ -3022,7 +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 */ @@ -3059,16 +3004,6 @@ static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size) css_put(&memcg->css); } -void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep) -{ - if (!memcg) - return; - - mutex_lock(&memcg->slab_caches_mutex); - list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches); - mutex_unlock(&memcg->slab_caches_mutex); -} - /* * helper for acessing a memcg's index. It will be used as an index in the * child cache array in kmem_cache, and also to derive its name. This function @@ -3079,43 +3014,6 @@ int memcg_cache_id(struct mem_cgroup *memcg) return memcg ? memcg->kmemcg_id : -1; } -/* - * This ends up being protected by the set_limit mutex, during normal - * operation, because that is its main call site. - * - * But when we create a new cache, we can call this as well if its parent - * is kmem-limited. That will have to hold set_limit_mutex as well. - */ -int memcg_update_cache_sizes(struct mem_cgroup *memcg) -{ - int num, ret; - - num = ida_simple_get(&kmem_limited_groups, - 0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL); - if (num < 0) - return num; - /* - * After this point, kmem_accounted (that we test atomically in - * the beginning of this conditional), is no longer 0. This - * guarantees only one process will set the following boolean - * to true. We don't need test_and_set because we're protected - * by the set_limit_mutex anyway. - */ - memcg_kmem_set_activated(memcg); - - ret = memcg_update_all_caches(num+1); - if (ret) { - ida_simple_remove(&kmem_limited_groups, num); - memcg_kmem_clear_activated(memcg); - return ret; - } - - memcg->kmemcg_id = num; - INIT_LIST_HEAD(&memcg->memcg_slab_caches); - mutex_init(&memcg->slab_caches_mutex); - return 0; -} - static size_t memcg_caches_array_size(int num_groups) { ssize_t size; @@ -3152,18 +3050,17 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups) if (num_groups > memcg_limited_groups_array_size) { int i; + struct memcg_cache_params *new_params; ssize_t size = memcg_caches_array_size(num_groups); size *= sizeof(void *); size += offsetof(struct memcg_cache_params, memcg_caches); - s->memcg_params = kzalloc(size, GFP_KERNEL); - if (!s->memcg_params) { - s->memcg_params = cur_params; + new_params = kzalloc(size, GFP_KERNEL); + if (!new_params) return -ENOMEM; - } - s->memcg_params->is_root_cache = true; + new_params->is_root_cache = true; /* * There is the chance it will be bigger than @@ -3177,7 +3074,7 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups) for (i = 0; i < memcg_limited_groups_array_size; i++) { if (!cur_params->memcg_caches[i]) continue; - s->memcg_params->memcg_caches[i] = + new_params->memcg_caches[i] = cur_params->memcg_caches[i]; } @@ -3190,13 +3087,38 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups) * bigger than the others. And all updates will reset this * anyway. */ - kfree(cur_params); + rcu_assign_pointer(s->memcg_params, new_params); + if (cur_params) + kfree_rcu(cur_params, rcu_head); } return 0; } -int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s, - struct kmem_cache *root_cache) +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) { size_t size; @@ -3218,41 +3140,91 @@ int memcg_register_cache(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; return 0; } -void memcg_release_cache(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); +} + +void memcg_register_cache(struct kmem_cache *s) { struct kmem_cache *root; struct mem_cgroup *memcg; int id; - /* - * This happens, for instance, when a root cache goes away before we - * add any memcg. - */ - if (!s->memcg_params) + if (is_root_cache(s)) return; - if (s->memcg_params->is_root_cache) - goto out; + /* + * Holding the slab_mutex assures nobody will touch the memcg_caches + * array while we are modifying it. + */ + lockdep_assert_held(&slab_mutex); + root = s->memcg_params->root_cache; memcg = s->memcg_params->memcg; - id = memcg_cache_id(memcg); + id = memcg_cache_id(memcg); + + /* + * Since readers won't lock (see cache_from_memcg_idx()), we need a + * barrier here to ensure nobody will see the kmem_cache partially + * initialized. + */ + smp_wmb(); + + /* + * Initialize the pointer to this cache in its parent's memcg_params + * before adding it to 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]); + root->memcg_params->memcg_caches[id] = s; + + mutex_lock(&memcg->slab_caches_mutex); + list_add(&s->memcg_params->list, &memcg->memcg_slab_caches); + mutex_unlock(&memcg->slab_caches_mutex); +} + +void memcg_unregister_cache(struct kmem_cache *s) +{ + struct kmem_cache *root; + struct mem_cgroup *memcg; + int id; + + if (is_root_cache(s)) + return; + + /* + * Holding the slab_mutex assures nobody will touch the memcg_caches + * array while we are modifying it. + */ + lockdep_assert_held(&slab_mutex); root = s->memcg_params->root_cache; - root->memcg_params->memcg_caches[id] = NULL; + memcg = s->memcg_params->memcg; + id = memcg_cache_id(memcg); mutex_lock(&memcg->slab_caches_mutex); list_del(&s->memcg_params->list); mutex_unlock(&memcg->slab_caches_mutex); - css_put(&memcg->css); -out: - kfree(s->memcg_params); + /* + * Clear the pointer to this cache in its parent's memcg_params only + * 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] != s); + root->memcg_params->memcg_caches[id] = NULL; } /* @@ -3311,11 +3283,9 @@ static void kmem_cache_destroy_work_func(struct work_struct *w) * So if we aren't down to zero, we'll just schedule a worker and try * again */ - if (atomic_read(&cachep->memcg_params->nr_pages) != 0) { + if (atomic_read(&cachep->memcg_params->nr_pages) != 0) kmem_cache_shrink(cachep); - if (atomic_read(&cachep->memcg_params->nr_pages) == 0) - return; - } else + else kmem_cache_destroy(cachep); } @@ -3351,99 +3321,10 @@ void mem_cgroup_destroy_cache(struct kmem_cache *cachep) schedule_work(&cachep->memcg_params->destroy); } -/* - * This lock protects updaters, not readers. We want readers to be as fast as - * they can, and they will either see NULL or a valid cache value. Our model - * allow them to see NULL, in which case the root memcg will be selected. - * - * We need this lock because multiple allocations to the same cache from a non - * will span more than one worker. Only one of them can create the cache. - */ -static DEFINE_MUTEX(memcg_cache_mutex); - -/* - * Called with memcg_cache_mutex held - */ -static struct kmem_cache *kmem_cache_dup(struct mem_cgroup *memcg, - struct kmem_cache *s) -{ - struct kmem_cache *new; - static char *tmp_name = NULL; - - lockdep_assert_held(&memcg_cache_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) - return NULL; - } - - 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; - - return new; -} - -static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, - struct kmem_cache *cachep) -{ - struct kmem_cache *new_cachep; - int idx; - - BUG_ON(!memcg_can_account_kmem(memcg)); - - idx = memcg_cache_id(memcg); - - mutex_lock(&memcg_cache_mutex); - new_cachep = cache_from_memcg_idx(cachep, idx); - if (new_cachep) { - css_put(&memcg->css); - goto out; - } - - new_cachep = kmem_cache_dup(memcg, cachep); - if (new_cachep == NULL) { - new_cachep = cachep; - css_put(&memcg->css); - goto out; - } - - atomic_set(&new_cachep->memcg_params->nr_pages , 0); - - cachep->memcg_params->memcg_caches[idx] = new_cachep; - /* - * the readers won't lock, make sure everybody sees the updated value, - * so they won't put stuff in the queue again for no reason - */ - wmb(); -out: - mutex_unlock(&memcg_cache_mutex); - return new_cachep; -} - -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 @@ -3452,9 +3333,10 @@ void kmem_cache_destroy_memcg_children(struct kmem_cache *s) * * Still, we don't want anyone else freeing memcg_caches under our * noses, which can happen if a new memcg comes to life. As usual, - * we'll take the set_limit_mutex to protect ourselves against this. + * we'll take the activate_kmem_mutex to protect ourselves against + * this. */ - mutex_lock(&set_limit_mutex); + mutex_lock(&activate_kmem_mutex); for_each_memcg_cache_index(i) { c = cache_from_memcg_idx(s, i); if (!c) @@ -3476,16 +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(&set_limit_mutex); + 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; @@ -3503,12 +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); + kmem_cache_create_memcg(memcg, cachep); + css_put(&memcg->css); kfree(cw); } @@ -3568,7 +3456,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) { struct mem_cgroup *memcg; - int idx; + struct kmem_cache *memcg_cachep; VM_BUG_ON(!cachep->memcg_params); VM_BUG_ON(!cachep->memcg_params->is_root_cache); @@ -3582,15 +3470,9 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, if (!memcg_can_account_kmem(memcg)) goto out; - idx = memcg_cache_id(memcg); - - /* - * barrier to mare sure we're always seeing the up to date value. The - * code updating memcg_caches will issue a write barrier to match this. - */ - read_barrier_depends(); - if (likely(cache_from_memcg_idx(cachep, idx))) { - cachep = cache_from_memcg_idx(cachep, idx); + memcg_cachep = cache_from_memcg_idx(cachep, memcg_cache_id(memcg)); + if (likely(memcg_cachep)) { + cachep = memcg_cachep; goto out; } @@ -3673,15 +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); @@ -3744,7 +3618,7 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order) if (!memcg) return; - VM_BUG_ON(mem_cgroup_is_root(memcg)); + VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page); memcg_uncharge_kmem(memcg, PAGE_SIZE << order); } #else @@ -3784,19 +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 @@ -3823,7 +3684,7 @@ static int mem_cgroup_move_account(struct page *page, bool anon = PageAnon(page); VM_BUG_ON(from == to); - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); /* * The page is isolated from LRU. So, collapse function * will not handle this page. But page splitting can happen. @@ -3842,13 +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); @@ -3916,7 +3783,7 @@ static int mem_cgroup_move_parent(struct page *page, parent = root_mem_cgroup; if (nr_pages > 1) { - VM_BUG_ON(!PageTransHuge(page)); + VM_BUG_ON_PAGE(!PageTransHuge(page), page); flags = compound_lock_irqsave(page); } @@ -3934,23 +3801,23 @@ 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); - VM_BUG_ON(!PageTransHuge(page)); + VM_BUG_ON_PAGE(!PageTransHuge(page), page); /* * Never OOM-kill a process for a huge page. The * fault handler will fall back to regular pages. @@ -3958,25 +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_mapped(page)); - VM_BUG_ON(page->mapping && !PageAnon(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 @@ -3988,7 +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; @@ -4001,31 +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 @@ -4033,12 +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); } @@ -4082,11 +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()) @@ -4094,15 +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, @@ -4175,7 +4043,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype, if (PageTransHuge(page)) { nr_pages <<= compound_order(page); - VM_BUG_ON(!PageTransHuge(page)); + VM_BUG_ON_PAGE(!PageTransHuge(page), page); } /* * Check if our page_cgroup is valid @@ -4267,7 +4135,7 @@ void mem_cgroup_uncharge_page(struct page *page) /* early check. */ if (page_mapped(page)) return; - VM_BUG_ON(page->mapping && !PageAnon(page)); + VM_BUG_ON_PAGE(page->mapping && !PageAnon(page), page); /* * If the page is in swap cache, uncharge should be deferred * to the swap path, which also properly accounts swap usage @@ -4287,8 +4155,8 @@ void mem_cgroup_uncharge_page(struct page *page) void mem_cgroup_uncharge_cache_page(struct page *page) { - VM_BUG_ON(page_mapped(page)); - VM_BUG_ON(page->mapping); + VM_BUG_ON_PAGE(page_mapped(page), page); + VM_BUG_ON_PAGE(page->mapping, page); __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE, false); } @@ -4994,7 +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 */ @@ -5112,14 +4980,12 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) return val << PAGE_SHIFT; } -static ssize_t mem_cgroup_read(struct cgroup_subsys_state *css, - struct cftype *cft, struct file *file, - char __user *buf, size_t nbytes, loff_t *ppos) +static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - char str[64]; u64 val; - int name, len; + int name; enum res_type type; type = MEMFILE_TYPE(cft->private); @@ -5145,15 +5011,26 @@ static ssize_t mem_cgroup_read(struct cgroup_subsys_state *css, BUG(); } - len = scnprintf(str, sizeof(str), "%llu\n", (unsigned long long)val); - return simple_read_from_buffer(buf, nbytes, ppos, str, len); + return val; } -static int memcg_update_kmem_limit(struct cgroup_subsys_state *css, u64 val) -{ - int ret = -EINVAL; #ifdef CONFIG_MEMCG_KMEM - struct mem_cgroup *memcg = mem_cgroup_from_css(css); +/* should be called with activate_kmem_mutex held */ +static int __memcg_activate_kmem(struct mem_cgroup *memcg, + unsigned long long limit) +{ + int err = 0; + int memcg_id; + + if (memcg_kmem_is_active(memcg)) + return 0; + + /* + * We are going to allocate memory for data shared by all memory + * cgroups so let's stop accounting here. + */ + memcg_stop_kmem_account(); + /* * For simplicity, we won't allow this to be disabled. It also can't * be changed if the cgroup has children already, or if tasks had @@ -5167,72 +5044,101 @@ static int memcg_update_kmem_limit(struct cgroup_subsys_state *css, u64 val) * of course permitted. */ mutex_lock(&memcg_create_mutex); - mutex_lock(&set_limit_mutex); - if (!memcg->kmem_account_flags && val != RES_COUNTER_MAX) { - if (cgroup_task_count(css->cgroup) || memcg_has_children(memcg)) { - ret = -EBUSY; - goto out; - } - ret = res_counter_set_limit(&memcg->kmem, val); - VM_BUG_ON(ret); + if (cgroup_has_tasks(memcg->css.cgroup) || memcg_has_children(memcg)) + err = -EBUSY; + mutex_unlock(&memcg_create_mutex); + if (err) + goto out; - ret = memcg_update_cache_sizes(memcg); - if (ret) { - res_counter_set_limit(&memcg->kmem, RES_COUNTER_MAX); - goto out; - } - static_key_slow_inc(&memcg_kmem_enabled_key); - /* - * setting the active bit after the inc will guarantee no one - * starts accounting before all call sites are patched - */ - memcg_kmem_set_active(memcg); - } else - ret = res_counter_set_limit(&memcg->kmem, val); + memcg_id = ida_simple_get(&kmem_limited_groups, + 0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL); + if (memcg_id < 0) { + err = memcg_id; + goto out; + } + + /* + * Make sure we have enough space for this cgroup in each root cache's + * memcg_params. + */ + err = memcg_update_all_caches(memcg_id + 1); + if (err) + goto out_rmid; + + memcg->kmemcg_id = memcg_id; + INIT_LIST_HEAD(&memcg->memcg_slab_caches); + mutex_init(&memcg->slab_caches_mutex); + + /* + * We couldn't have accounted to this cgroup, because it hasn't got the + * active bit set yet, so this should succeed. + */ + err = res_counter_set_limit(&memcg->kmem, limit); + VM_BUG_ON(err); + + static_key_slow_inc(&memcg_kmem_enabled_key); + /* + * Setting the active bit after enabling static branching will + * guarantee no one starts accounting before all call sites are + * patched. + */ + memcg_kmem_set_active(memcg); out: - mutex_unlock(&set_limit_mutex); - mutex_unlock(&memcg_create_mutex); -#endif + memcg_resume_kmem_account(); + return err; + +out_rmid: + ida_simple_remove(&kmem_limited_groups, memcg_id); + goto out; +} + +static int memcg_activate_kmem(struct mem_cgroup *memcg, + unsigned long long limit) +{ + int ret; + + mutex_lock(&activate_kmem_mutex); + ret = __memcg_activate_kmem(memcg, limit); + mutex_unlock(&activate_kmem_mutex); + return ret; +} + +static int memcg_update_kmem_limit(struct mem_cgroup *memcg, + unsigned long long val) +{ + int ret; + + if (!memcg_kmem_is_active(memcg)) + ret = memcg_activate_kmem(memcg, val); + else + ret = res_counter_set_limit(&memcg->kmem, val); return ret; } -#ifdef CONFIG_MEMCG_KMEM static int memcg_propagate_kmem(struct mem_cgroup *memcg) { int ret = 0; struct mem_cgroup *parent = parent_mem_cgroup(memcg); - if (!parent) - goto out; - memcg->kmem_account_flags = parent->kmem_account_flags; - /* - * When that happen, we need to disable the static branch only on those - * memcgs that enabled it. To achieve this, we would be forced to - * complicate the code by keeping track of which memcgs were the ones - * that actually enabled limits, and which ones got it from its - * parents. - * - * It is a lot simpler just to do static_key_slow_inc() on every child - * that is accounted. - */ - if (!memcg_kmem_is_active(memcg)) - goto out; + if (!parent) + return 0; + mutex_lock(&activate_kmem_mutex); /* - * __mem_cgroup_free() will issue static_key_slow_dec() because this - * memcg is active already. If the later initialization fails then the - * cgroup core triggers the cleanup so we do not have to do it here. + * If the parent cgroup is not kmem-active now, it cannot be activated + * after this point, because it has at least one child already. */ - static_key_slow_inc(&memcg_kmem_enabled_key); - - mutex_lock(&set_limit_mutex); - memcg_stop_kmem_account(); - ret = memcg_update_cache_sizes(memcg); - memcg_resume_kmem_account(); - mutex_unlock(&set_limit_mutex); -out: + if (memcg_kmem_is_active(parent)) + ret = __memcg_activate_kmem(memcg, RES_COUNTER_MAX); + mutex_unlock(&activate_kmem_mutex); return ret; } +#else +static int memcg_update_kmem_limit(struct mem_cgroup *memcg, + unsigned long long val) +{ + return -EINVAL; +} #endif /* CONFIG_MEMCG_KMEM */ /* @@ -5240,7 +5146,7 @@ out: * 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; @@ -5266,7 +5172,7 @@ static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, else if (type == _MEMSWAP) ret = mem_cgroup_resize_memsw_limit(memcg, val); else if (type == _KMEM) - ret = memcg_update_kmem_limit(css, val); + ret = memcg_update_kmem_limit(memcg, val); else return -EINVAL; break; @@ -5383,8 +5289,7 @@ static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, #endif #ifdef CONFIG_NUMA -static int memcg_numa_stat_show(struct cgroup_subsys_state *css, - struct cftype *cft, struct seq_file *m) +static int memcg_numa_stat_show(struct seq_file *m, void *v) { struct numa_stat { const char *name; @@ -5400,7 +5305,7 @@ static int memcg_numa_stat_show(struct cgroup_subsys_state *css, const struct numa_stat *stat; int nid; unsigned long nr; - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) { nr = mem_cgroup_nr_lru_pages(memcg, stat->lru_mask); @@ -5439,10 +5344,9 @@ static inline void mem_cgroup_lru_names_not_uptodate(void) BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); } -static int memcg_stat_show(struct cgroup_subsys_state *css, struct cftype *cft, - struct seq_file *m) +static int memcg_stat_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); struct mem_cgroup *mi; unsigned int i; @@ -5651,13 +5555,11 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg) mem_cgroup_oom_notify_cb(iter); } -static int mem_cgroup_usage_register_event(struct cgroup_subsys_state *css, - struct cftype *cft, struct eventfd_ctx *eventfd, const char *args) +static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args, enum res_type type) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup_thresholds *thresholds; struct mem_cgroup_threshold_ary *new; - enum res_type type = MEMFILE_TYPE(cft->private); u64 threshold, usage; int i, size, ret; @@ -5734,13 +5636,23 @@ unlock: return ret; } -static void mem_cgroup_usage_unregister_event(struct cgroup_subsys_state *css, - struct cftype *cft, struct eventfd_ctx *eventfd) +static int mem_cgroup_usage_register_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args) +{ + return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEM); +} + +static int memsw_cgroup_usage_register_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args) +{ + return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEMSWAP); +} + +static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, enum res_type type) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup_thresholds *thresholds; struct mem_cgroup_threshold_ary *new; - enum res_type type = MEMFILE_TYPE(cft->private); u64 usage; int i, j, size; @@ -5813,14 +5725,23 @@ unlock: mutex_unlock(&memcg->thresholds_lock); } -static int mem_cgroup_oom_register_event(struct cgroup_subsys_state *css, - struct cftype *cft, struct eventfd_ctx *eventfd, const char *args) +static void mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd) +{ + return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEM); +} + +static void memsw_cgroup_usage_unregister_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd) +{ + return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEMSWAP); +} + +static int mem_cgroup_oom_register_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup_eventfd_list *event; - enum res_type type = MEMFILE_TYPE(cft->private); - BUG_ON(type != _OOM_TYPE); event = kmalloc(sizeof(*event), GFP_KERNEL); if (!event) return -ENOMEM; @@ -5838,14 +5759,10 @@ static int mem_cgroup_oom_register_event(struct cgroup_subsys_state *css, return 0; } -static void mem_cgroup_oom_unregister_event(struct cgroup_subsys_state *css, - struct cftype *cft, struct eventfd_ctx *eventfd) +static void mem_cgroup_oom_unregister_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup_eventfd_list *ev, *tmp; - enum res_type type = MEMFILE_TYPE(cft->private); - - BUG_ON(type != _OOM_TYPE); spin_lock(&memcg_oom_lock); @@ -5859,17 +5776,12 @@ static void mem_cgroup_oom_unregister_event(struct cgroup_subsys_state *css, spin_unlock(&memcg_oom_lock); } -static int mem_cgroup_oom_control_read(struct cgroup_subsys_state *css, - struct cftype *cft, struct cgroup_map_cb *cb) +static int mem_cgroup_oom_control_read(struct seq_file *sf, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(sf)); - cb->fill(cb, "oom_kill_disable", memcg->oom_kill_disable); - - if (atomic_read(&memcg->under_oom)) - cb->fill(cb, "under_oom", 1); - else - cb->fill(cb, "under_oom", 0); + seq_printf(sf, "oom_kill_disable %d\n", memcg->oom_kill_disable); + seq_printf(sf, "under_oom %d\n", (bool)atomic_read(&memcg->under_oom)); return 0; } @@ -5962,41 +5874,259 @@ static void kmem_cgroup_css_offline(struct mem_cgroup *memcg) } #endif +/* + * DO NOT USE IN NEW FILES. + * + * "cgroup.event_control" implementation. + * + * This is way over-engineered. It tries to support fully configurable + * events for each user. Such level of flexibility is completely + * unnecessary especially in the light of the planned unified hierarchy. + * + * Please deprecate this and replace with something simpler if at all + * possible. + */ + +/* + * Unregister event and free resources. + * + * Gets called from workqueue. + */ +static void memcg_event_remove(struct work_struct *work) +{ + struct mem_cgroup_event *event = + container_of(work, struct mem_cgroup_event, remove); + struct mem_cgroup *memcg = event->memcg; + + remove_wait_queue(event->wqh, &event->wait); + + event->unregister_event(memcg, event->eventfd); + + /* Notify userspace the event is going away. */ + eventfd_signal(event->eventfd, 1); + + eventfd_ctx_put(event->eventfd); + kfree(event); + css_put(&memcg->css); +} + +/* + * Gets called on POLLHUP on eventfd when user closes it. + * + * Called with wqh->lock held and interrupts disabled. + */ +static int memcg_event_wake(wait_queue_t *wait, unsigned mode, + int sync, void *key) +{ + struct mem_cgroup_event *event = + container_of(wait, struct mem_cgroup_event, wait); + struct mem_cgroup *memcg = event->memcg; + unsigned long flags = (unsigned long)key; + + if (flags & POLLHUP) { + /* + * If the event has been detached at cgroup removal, we + * can simply return knowing the other side will cleanup + * for us. + * + * We can't race against event freeing since the other + * side will require wqh->lock via remove_wait_queue(), + * which we hold. + */ + spin_lock(&memcg->event_list_lock); + if (!list_empty(&event->list)) { + list_del_init(&event->list); + /* + * We are in atomic context, but cgroup_event_remove() + * may sleep, so we have to call it in workqueue. + */ + schedule_work(&event->remove); + } + spin_unlock(&memcg->event_list_lock); + } + + return 0; +} + +static void memcg_event_ptable_queue_proc(struct file *file, + wait_queue_head_t *wqh, poll_table *pt) +{ + struct mem_cgroup_event *event = + container_of(pt, struct mem_cgroup_event, pt); + + event->wqh = wqh; + add_wait_queue(wqh, &event->wait); +} + +/* + * DO NOT USE IN NEW FILES. + * + * Parse input and register new cgroup event handler. + * + * Input must be in format '<event_fd> <control_fd> <args>'. + * Interpretation of args is defined by control file implementation. + */ +static int memcg_write_event_control(struct cgroup_subsys_state *css, + struct cftype *cft, char *buffer) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup_event *event; + struct cgroup_subsys_state *cfile_css; + unsigned int efd, cfd; + struct fd efile; + struct fd cfile; + const char *name; + char *endp; + int ret; + + efd = simple_strtoul(buffer, &endp, 10); + if (*endp != ' ') + return -EINVAL; + buffer = endp + 1; + + cfd = simple_strtoul(buffer, &endp, 10); + if ((*endp != ' ') && (*endp != '\0')) + return -EINVAL; + buffer = endp + 1; + + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (!event) + return -ENOMEM; + + event->memcg = memcg; + INIT_LIST_HEAD(&event->list); + init_poll_funcptr(&event->pt, memcg_event_ptable_queue_proc); + init_waitqueue_func_entry(&event->wait, memcg_event_wake); + INIT_WORK(&event->remove, memcg_event_remove); + + efile = fdget(efd); + if (!efile.file) { + ret = -EBADF; + goto out_kfree; + } + + event->eventfd = eventfd_ctx_fileget(efile.file); + if (IS_ERR(event->eventfd)) { + ret = PTR_ERR(event->eventfd); + goto out_put_efile; + } + + cfile = fdget(cfd); + if (!cfile.file) { + ret = -EBADF; + goto out_put_eventfd; + } + + /* the process need read permission on control file */ + /* AV: shouldn't we check that it's been opened for read instead? */ + ret = inode_permission(file_inode(cfile.file), MAY_READ); + if (ret < 0) + goto out_put_cfile; + + /* + * Determine the event callbacks and set them in @event. This used + * to be done via struct cftype but cgroup core no longer knows + * about these events. The following is crude but the whole thing + * is for compatibility anyway. + * + * DO NOT ADD NEW FILES. + */ + name = cfile.file->f_dentry->d_name.name; + + if (!strcmp(name, "memory.usage_in_bytes")) { + event->register_event = mem_cgroup_usage_register_event; + event->unregister_event = mem_cgroup_usage_unregister_event; + } else if (!strcmp(name, "memory.oom_control")) { + event->register_event = mem_cgroup_oom_register_event; + event->unregister_event = mem_cgroup_oom_unregister_event; + } else if (!strcmp(name, "memory.pressure_level")) { + event->register_event = vmpressure_register_event; + event->unregister_event = vmpressure_unregister_event; + } else if (!strcmp(name, "memory.memsw.usage_in_bytes")) { + event->register_event = memsw_cgroup_usage_register_event; + event->unregister_event = memsw_cgroup_usage_unregister_event; + } else { + ret = -EINVAL; + goto out_put_cfile; + } + + /* + * Verify @cfile should belong to @css. Also, remaining events are + * automatically removed on cgroup destruction but the removal is + * asynchronous, so take an extra ref on @css. + */ + cfile_css = css_tryget_from_dir(cfile.file->f_dentry->d_parent, + &memory_cgrp_subsys); + ret = -EINVAL; + 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) + goto out_put_css; + + efile.file->f_op->poll(efile.file, &event->pt); + + spin_lock(&memcg->event_list_lock); + list_add(&event->list, &memcg->event_list); + spin_unlock(&memcg->event_list_lock); + + fdput(cfile); + fdput(efile); + + return 0; + +out_put_css: + css_put(css); +out_put_cfile: + fdput(cfile); +out_put_eventfd: + eventfd_ctx_put(event->eventfd); +out_put_efile: + fdput(efile); +out_kfree: + kfree(event); + + return ret; +} + static struct cftype mem_cgroup_files[] = { { .name = "usage_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_USAGE), - .read = mem_cgroup_read, - .register_event = mem_cgroup_usage_register_event, - .unregister_event = mem_cgroup_usage_unregister_event, + .read_u64 = mem_cgroup_read_u64, }, { .name = "max_usage_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE), .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, + .read_u64 = mem_cgroup_read_u64, }, { .name = "limit_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_LIMIT), .write_string = mem_cgroup_write, - .read = mem_cgroup_read, + .read_u64 = mem_cgroup_read_u64, }, { .name = "soft_limit_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT), .write_string = mem_cgroup_write, - .read = mem_cgroup_read, + .read_u64 = mem_cgroup_read_u64, }, { .name = "failcnt", .private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT), .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, + .read_u64 = mem_cgroup_read_u64, }, { .name = "stat", - .read_seq_string = memcg_stat_show, + .seq_show = memcg_stat_show, }, { .name = "force_empty", @@ -6009,6 +6139,12 @@ static struct cftype mem_cgroup_files[] = { .read_u64 = mem_cgroup_hierarchy_read, }, { + .name = "cgroup.event_control", /* XXX: for compat */ + .write_string = memcg_write_event_control, + .flags = CFTYPE_NO_PREFIX, + .mode = S_IWUGO, + }, + { .name = "swappiness", .read_u64 = mem_cgroup_swappiness_read, .write_u64 = mem_cgroup_swappiness_write, @@ -6020,21 +6156,17 @@ static struct cftype mem_cgroup_files[] = { }, { .name = "oom_control", - .read_map = mem_cgroup_oom_control_read, + .seq_show = mem_cgroup_oom_control_read, .write_u64 = mem_cgroup_oom_control_write, - .register_event = mem_cgroup_oom_register_event, - .unregister_event = mem_cgroup_oom_unregister_event, .private = MEMFILE_PRIVATE(_OOM_TYPE, OOM_CONTROL), }, { .name = "pressure_level", - .register_event = vmpressure_register_event, - .unregister_event = vmpressure_unregister_event, }, #ifdef CONFIG_NUMA { .name = "numa_stat", - .read_seq_string = memcg_numa_stat_show, + .seq_show = memcg_numa_stat_show, }, #endif #ifdef CONFIG_MEMCG_KMEM @@ -6042,29 +6174,29 @@ static struct cftype mem_cgroup_files[] = { .name = "kmem.limit_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT), .write_string = mem_cgroup_write, - .read = mem_cgroup_read, + .read_u64 = mem_cgroup_read_u64, }, { .name = "kmem.usage_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_USAGE), - .read = mem_cgroup_read, + .read_u64 = mem_cgroup_read_u64, }, { .name = "kmem.failcnt", .private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT), .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, + .read_u64 = mem_cgroup_read_u64, }, { .name = "kmem.max_usage_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE), .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, + .read_u64 = mem_cgroup_read_u64, }, #ifdef CONFIG_SLABINFO { .name = "kmem.slabinfo", - .read_seq_string = mem_cgroup_slabinfo_read, + .seq_show = mem_cgroup_slabinfo_read, }, #endif #endif @@ -6076,27 +6208,25 @@ static struct cftype memsw_cgroup_files[] = { { .name = "memsw.usage_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), - .read = mem_cgroup_read, - .register_event = mem_cgroup_usage_register_event, - .unregister_event = mem_cgroup_usage_unregister_event, + .read_u64 = mem_cgroup_read_u64, }, { .name = "memsw.max_usage_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, + .read_u64 = mem_cgroup_read_u64, }, { .name = "memsw.limit_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), .write_string = mem_cgroup_write, - .read = mem_cgroup_read, + .read_u64 = mem_cgroup_read_u64, }, { .name = "memsw.failcnt", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, + .read_u64 = mem_cgroup_read_u64, }, { }, /* terminate */ }; @@ -6139,14 +6269,12 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) static struct mem_cgroup *mem_cgroup_alloc(void) { struct mem_cgroup *memcg; - size_t size = memcg_size(); + size_t size; - /* Can be very big if nr_node_ids is very big */ - if (size < PAGE_SIZE) - memcg = kzalloc(size, GFP_KERNEL); - else - memcg = vzalloc(size); + size = sizeof(struct mem_cgroup); + size += nr_node_ids * sizeof(struct mem_cgroup_per_node *); + memcg = kzalloc(size, GFP_KERNEL); if (!memcg) return NULL; @@ -6157,10 +6285,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) return memcg; out_free: - if (size < PAGE_SIZE) - kfree(memcg); - else - vfree(memcg); + kfree(memcg); return NULL; } @@ -6178,7 +6303,6 @@ out_free: static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; - size_t size = memcg_size(); mem_cgroup_remove_from_trees(memcg); @@ -6199,10 +6323,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) * the cgroup_lock. */ disarm_static_keys(memcg); - if (size < PAGE_SIZE) - kfree(memcg); - else - vfree(memcg); + kfree(memcg); } /* @@ -6268,6 +6389,8 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) mutex_init(&memcg->thresholds_lock); spin_lock_init(&memcg->move_lock); vmpressure_init(&memcg->vmpressure); + INIT_LIST_HEAD(&memcg->event_list); + spin_lock_init(&memcg->event_list_lock); return &memcg->css; @@ -6281,7 +6404,6 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css)); - int error = 0; if (css->cgroup->id > MEM_CGROUP_ID_MAX) return -ENOSPC; @@ -6314,12 +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; } - - error = memcg_init_kmem(memcg, &mem_cgroup_subsys); mutex_unlock(&memcg_create_mutex); - return error; + + return memcg_init_kmem(memcg, &memory_cgrp_subsys); } /* @@ -6343,11 +6464,32 @@ static void mem_cgroup_invalidate_reclaim_iterators(struct mem_cgroup *memcg) 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. + * Notify userspace about cgroup removing only after rmdir of cgroup + * directory to avoid race between userspace and kernelspace. + */ + spin_lock(&memcg->event_list_lock); + list_for_each_entry_safe(event, tmp, &memcg->event_list, list) { + list_del_init(&event->list); + schedule_work(&event->remove); + } + spin_unlock(&memcg->event_list_lock); 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); } @@ -6440,8 +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; @@ -6615,7 +6756,7 @@ static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma, enum mc_target_type ret = MC_TARGET_NONE; page = pmd_page(pmd); - VM_BUG_ON(!page || !PageHead(page)); + VM_BUG_ON_PAGE(!page || !PageHead(page), page); if (!move_anon()) return ret; pc = lookup_page_cgroup(page); @@ -7000,9 +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, @@ -7028,7 +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 fabe55046c1d..35ef28acf137 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; @@ -611,7 +607,7 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) } /* - * Dirty cache page page + * Dirty pagecache page * Issues: when the error hit a hole page the error is not properly * propagated. */ @@ -856,14 +852,14 @@ static int page_action(struct page_state *ps, struct page *p, * the pages and send SIGBUS to the processes if the data was dirty. */ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, - int trapno, int flags) + int trapno, int flags, struct page **hpagep) { enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS; struct address_space *mapping; LIST_HEAD(tokill); int ret; int kill = 1, forcekill; - struct page *hpage = compound_head(p); + struct page *hpage = *hpagep; struct page *ppage; if (PageReserved(p) || PageSlab(p)) @@ -942,11 +938,16 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * We pinned the head page for hwpoison handling, * now we split the thp and we are interested in * the hwpoisoned raw page, so move the refcount - * to it. + * 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; } /* THP is split, so ppage should be the real poisoned page. */ ppage = p; @@ -964,17 +965,11 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, if (kill) collect_procs(ppage, &tokill); - if (hpage != ppage) - lock_page(ppage); - ret = try_to_unmap(ppage, ttu); if (ret != SWAP_SUCCESS) printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n", pfn, page_mapcount(ppage)); - if (hpage != ppage) - unlock_page(ppage); - /* * Now that the dirty bit has been propagated to the * struct page and all unmaps done we can decide if @@ -1193,8 +1188,12 @@ int memory_failure(unsigned long pfn, int trapno, int flags) /* * Now take care of user space mappings. * Abort on fail: __delete_from_page_cache() assumes unmapped page. + * + * When the raw error page is thp tail page, hpage points to the raw + * page after thp split. */ - if (hwpoison_user_mappings(p, pfn, trapno, flags) != SWAP_SUCCESS) { + if (hwpoison_user_mappings(p, pfn, trapno, flags, &hpage) + != SWAP_SUCCESS) { printk(KERN_ERR "MCE %#lx: cannot unmap page, give up\n", pfn); res = -EBUSY; goto out; @@ -1585,7 +1584,13 @@ static int __soft_offline_page(struct page *page, int flags) ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { - putback_lru_pages(&pagelist); + if (!list_empty(&pagelist)) { + list_del(&page->lru); + dec_zone_page_state(page, NR_ISOLATED_ANON + + page_is_file_cache(page)); + putback_lru_page(page); + } + pr_info("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); if (ret > 0) @@ -1642,7 +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 6768ce9e57d2..d0f0bef3be48 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -59,6 +59,8 @@ #include <linux/gfp.h> #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> @@ -288,7 +290,7 @@ int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) return 0; batch = tlb->active; } - VM_BUG_ON(batch->nr > batch->max); + VM_BUG_ON_PAGE(batch->nr > batch->max, page); return batch->max - batch->nr; } @@ -670,7 +672,7 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, current->comm, (long long)pte_val(pte), (long long)pmd_val(*pmd)); if (page) - dump_page(page); + dump_page(page, "bad pte"); printk(KERN_ALERT "addr:%p vm_flags:%08lx anon_vma:%p mapping:%p index:%lx\n", (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); @@ -1319,9 +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. @@ -1704,15 +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 @@ -1740,7 +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 @@ -1750,12 +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) { @@ -1768,7 +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; @@ -1779,10 +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, @@ -1836,7 +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(); } @@ -1894,6 +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); @@ -1961,9 +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. @@ -2559,6 +2585,8 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma) { + debug_dma_assert_idle(src); + /* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by @@ -2584,6 +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. @@ -2665,42 +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(!PageLocked(old_page)); - /* * Since we dropped the lock we need to revalidate * the PTE as someone else may have changed it. If @@ -2745,11 +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); @@ -2795,7 +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; @@ -2889,10 +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, @@ -3252,7 +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); @@ -3283,53 +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; @@ -3337,150 +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(!PageLocked(vmf.page)); + 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(!PageLocked(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; } @@ -3492,7 +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); } /* @@ -3524,10 +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) { @@ -3542,7 +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; @@ -3700,7 +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) @@ -3738,20 +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; } } @@ -4272,11 +4417,20 @@ void copy_user_huge_page(struct page *dst, struct page *src, #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS + +static struct kmem_cache *page_ptl_cachep; + +void __init ptlock_cache_init(void) +{ + page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0, + SLAB_PANIC, NULL); +} + bool ptlock_alloc(struct page *page) { spinlock_t *ptl; - ptl = kmalloc(sizeof(spinlock_t), GFP_KERNEL); + ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL); if (!ptl) return false; page->ptl = ptl; @@ -4285,6 +4439,6 @@ bool ptlock_alloc(struct page *page) void ptlock_free(struct page *page) { - kfree(page->ptl); + kmem_cache_free(page_ptl_cachep, page->ptl); } #endif diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 489f235502db..a650db29606f 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -9,7 +9,6 @@ #include <linux/swap.h> #include <linux/interrupt.h> #include <linux/pagemap.h> -#include <linux/bootmem.h> #include <linux/compiler.h> #include <linux/export.h> #include <linux/pagevec.h> @@ -269,7 +268,7 @@ static void fix_zone_id(struct zone *zone, unsigned long start_pfn, } /* Can fail with -ENOMEM from allocating a wait table with vmalloc() or - * alloc_bootmem_node_nopanic() */ + * alloc_bootmem_node_nopanic()/memblock_virt_alloc_node_nopanic() */ static int __ref ensure_zone_is_initialized(struct zone *zone, unsigned long start_pfn, unsigned long num_pages) { @@ -1108,17 +1107,18 @@ int __ref add_memory(int nid, u64 start, u64 size) if (ret) return ret; - lock_memory_hotplug(); - res = register_memory_resource(start, size); ret = -EEXIST; if (!res) - goto out; + return ret; { /* Stupid hack to suppress address-never-null warning */ void *p = NODE_DATA(nid); new_pgdat = !p; } + + lock_memory_hotplug(); + new_node = !node_online(nid); if (new_node) { pgdat = hotadd_new_pgdat(nid, start); @@ -1310,7 +1310,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) #ifdef CONFIG_DEBUG_VM printk(KERN_ALERT "removing pfn %lx from LRU failed\n", pfn); - dump_page(page); + dump_page(page, "failed to remove from LRU"); #endif put_page(page); /* Because we don't have big zone->lock. we should @@ -1446,6 +1446,7 @@ static int __init cmdline_parse_movable_node(char *p) * the kernel away from hotpluggable memory. */ memblock_set_bottom_up(true); + movable_node_enabled = true; #else pr_warn("movable_node option not supported\n"); #endif diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 0cd2c4d4e270..78e1472933ea 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -613,7 +613,7 @@ static inline int queue_pages_pgd_range(struct vm_area_struct *vma, return 0; } -#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE +#ifdef CONFIG_NUMA_BALANCING /* * This is used to mark a range of virtual addresses to be inaccessible. * These are later cleared by a NUMA hinting fault. Depending on these @@ -627,7 +627,6 @@ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { int nr_updated; - BUILD_BUG_ON(_PAGE_NUMA != _PAGE_PROTNONE); nr_updated = change_protection(vma, addr, end, vma->vm_page_prot, 0, 1); if (nr_updated) @@ -641,7 +640,7 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma, { return 0; } -#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */ +#endif /* CONFIG_NUMA_BALANCING */ /* * Walk through page tables and collect pages to be migrated. @@ -796,36 +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) @@ -862,7 +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); @@ -1199,10 +1167,8 @@ static struct page *new_vma_page(struct page *page, unsigned long private, int * } if (PageHuge(page)) { - if (vma) - return alloc_huge_page_noerr(vma, address, 1); - else - return NULL; + BUG_ON(!vma); + return alloc_huge_page_noerr(vma, address, 1); } /* * if !vma, alloc_page_vma() will use task or system default policy @@ -1559,10 +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; @@ -1589,8 +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; @@ -1612,9 +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; @@ -1785,21 +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: @@ -1819,11 +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: @@ -1902,7 +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, @@ -2066,7 +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; @@ -2074,7 +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; @@ -2084,7 +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; } @@ -2118,7 +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 @@ -2131,7 +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; @@ -2304,35 +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 * @@ -2406,52 +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; } @@ -2657,7 +2548,7 @@ void mpol_free_shared_policy(struct shared_policy *p) } #ifdef CONFIG_NUMA_BALANCING -static bool __initdata numabalancing_override; +static int __initdata numabalancing_override; static void __init check_numabalancing_enable(void) { @@ -2666,9 +2557,15 @@ static void __init check_numabalancing_enable(void) if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) numabalancing_default = true; + /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ + if (numabalancing_override) + set_numabalancing_state(numabalancing_override == 1); + if (nr_node_ids > 1 && !numabalancing_override) { - printk(KERN_INFO "Enabling automatic NUMA balancing. " - "Configure with numa_balancing= or sysctl"); + pr_info("%s automatic NUMA balancing. " + "Configure with numa_balancing= or the " + "kernel.numa_balancing sysctl", + numabalancing_default ? "Enabling" : "Disabling"); set_numabalancing_state(numabalancing_default); } } @@ -2678,18 +2575,17 @@ static int __init setup_numabalancing(char *str) int ret = 0; if (!str) goto out; - numabalancing_override = true; if (!strcmp(str, "enable")) { - set_numabalancing_state(true); + numabalancing_override = 1; ret = 1; } else if (!strcmp(str, "disable")) { - set_numabalancing_state(false); + numabalancing_override = -1; ret = 1; } out: if (!ret) - printk(KERN_WARNING "Unable to parse numa_balancing=\n"); + pr_warn("Unable to parse numa_balancing=\n"); return ret; } @@ -2928,7 +2824,7 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) unsigned short mode = MPOL_DEFAULT; unsigned short flags = 0; - if (pol && pol != &default_policy) { + if (pol && pol != &default_policy && !(pol->flags & MPOL_F_MORON)) { mode = pol->mode; flags = pol->flags; } diff --git a/mm/mempool.c b/mm/mempool.c index 659aa42bad16..905434f18c97 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 9194375b2307..bed48809e5d0 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -72,28 +72,12 @@ int migrate_prep_local(void) } /* - * Add isolated pages on the list back to the LRU under page lock - * to avoid leaking evictable pages back onto unevictable list. - */ -void putback_lru_pages(struct list_head *l) -{ - struct page *page; - struct page *page2; - - list_for_each_entry_safe(page, page2, l, lru) { - list_del(&page->lru); - dec_zone_page_state(page, NR_ISOLATED_ANON + - page_is_file_cache(page)); - putback_lru_page(page); - } -} - -/* * Put previously isolated pages back onto the appropriate lists * from where they were once taken off for compaction/migration. * - * This function shall be used instead of putback_lru_pages(), - * whenever the isolated pageset has been built by isolate_migratepages_range() + * This function shall be used whenever the isolated pageset has been + * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range() + * and isolate_huge_page(). */ void putback_movable_pages(struct list_head *l) { @@ -194,12 +178,49 @@ 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. */ static void remove_migration_ptes(struct page *old, struct page *new) { - rmap_walk(new, remove_migration_pte, old); + struct rmap_walk_control rwc = { + .rmap_one = remove_migration_pte, + .arg = old, + .file_nonlinear = remove_linear_migration_ptes_from_nonlinear, + }; + + rmap_walk(new, &rwc); } /* @@ -510,7 +531,7 @@ void migrate_page_copy(struct page *newpage, struct page *page) if (PageUptodate(page)) SetPageUptodate(newpage); if (TestClearPageActive(page)) { - VM_BUG_ON(PageUnevictable(page)); + VM_BUG_ON_PAGE(PageUnevictable(page), page); SetPageActive(newpage); } else if (TestClearPageUnevictable(page)) SetPageUnevictable(newpage); @@ -563,14 +584,6 @@ void migrate_page_copy(struct page *newpage, struct page *page) * Migration functions ***********************************************************/ -/* Always fail migration. Used for mappings that are not movable */ -int fail_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page) -{ - return -EIO; -} -EXPORT_SYMBOL(fail_migrate_page); - /* * Common logic to directly migrate a single page suitable for * pages that do not use PagePrivate/PagePrivate2. @@ -890,7 +903,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, * free the metadata, so the page can be freed. */ if (!page->mapping) { - VM_BUG_ON(PageAnon(page)); + VM_BUG_ON_PAGE(PageAnon(page), page); if (page_has_private(page)) { try_to_free_buffers(page); goto uncharge; @@ -1008,7 +1021,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, { int rc = 0; int *result = NULL; - struct page *new_hpage = get_new_page(hpage, private, &result); + struct page *new_hpage; struct anon_vma *anon_vma = NULL; /* @@ -1018,9 +1031,12 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, * tables or check whether the hugepage is pmd-based or not before * kicking migration. */ - if (!hugepage_migration_support(page_hstate(hpage))) + if (!hugepage_migration_support(page_hstate(hpage))) { + putback_active_hugepage(hpage); return -ENOSYS; + } + new_hpage = get_new_page(hpage, private, &result); if (!new_hpage) return -ENOMEM; @@ -1120,7 +1136,12 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, nr_succeeded++; break; default: - /* Permanent failure */ + /* + * Permanent failure (-EBUSY, -ENOSYS, etc.): + * unlike -EAGAIN case, the failed page is + * removed from migration page list and not + * retried in the next outer loop. + */ nr_failed++; break; } @@ -1169,7 +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); } /* @@ -1555,12 +1576,10 @@ 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); - if (newpage) - page_cpupid_xchg_last(newpage, page_cpupid_last(page)); return newpage; } @@ -1594,35 +1613,42 @@ bool migrate_ratelimited(int node) } /* Returns true if the node is migrate rate-limited after the update */ -bool numamigrate_update_ratelimit(pg_data_t *pgdat, unsigned long nr_pages) +static bool numamigrate_update_ratelimit(pg_data_t *pgdat, + unsigned long nr_pages) { - bool rate_limited = false; - /* * Rate-limit the amount of data that is being migrated to a node. * Optimal placement is no good if the memory bus is saturated and * all the time is being spent migrating! */ - spin_lock(&pgdat->numabalancing_migrate_lock); if (time_after(jiffies, pgdat->numabalancing_migrate_next_window)) { + spin_lock(&pgdat->numabalancing_migrate_lock); pgdat->numabalancing_migrate_nr_pages = 0; pgdat->numabalancing_migrate_next_window = jiffies + msecs_to_jiffies(migrate_interval_millisecs); + spin_unlock(&pgdat->numabalancing_migrate_lock); } - if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) - rate_limited = true; - else - pgdat->numabalancing_migrate_nr_pages += nr_pages; - spin_unlock(&pgdat->numabalancing_migrate_lock); - - return rate_limited; + if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) { + trace_mm_numa_migrate_ratelimit(current, pgdat->node_id, + nr_pages); + return true; + } + + /* + * This is an unlocked non-atomic update so errors are possible. + * The consequences are failing to migrate when we potentiall should + * have which is not severe enough to warrant locking. If it is ever + * a problem, it can be converted to a per-cpu counter. + */ + pgdat->numabalancing_migrate_nr_pages += nr_pages; + return false; } -int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) +static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) { int page_lru; - VM_BUG_ON(compound_order(page) && !PageTransHuge(page)); + VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page); /* Avoid migrating to a node that is nearly full */ if (!migrate_balanced_pgdat(pgdat, 1UL << compound_order(page))) @@ -1705,7 +1731,12 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, node, MIGRATE_ASYNC, MR_NUMA_MISPLACED); if (nr_remaining) { - putback_lru_pages(&migratepages); + if (!list_empty(&migratepages)) { + list_del(&page->lru); + dec_zone_page_state(page, NR_ISOLATED_ANON + + page_is_file_cache(page)); + putback_lru_page(page); + } isolated = 0; } else count_vm_numa_event(NUMA_PAGE_MIGRATE); @@ -1748,12 +1779,11 @@ 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; - page_cpupid_xchg_last(new_page, page_cpupid_last(page)); - isolated = numamigrate_isolate_page(pgdat, page); if (!isolated) { put_page(new_page); diff --git a/mm/mincore.c b/mm/mincore.c index da2be56a7b8f..725c80961048 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); @@ -225,13 +233,6 @@ static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *v end = min(vma->vm_end, addr + (pages << PAGE_SHIFT)); - if (is_vm_hugetlb_page(vma)) { - mincore_hugetlb_page_range(vma, addr, end, vec); - return (end - addr) >> PAGE_SHIFT; - } - - end = pmd_addr_end(addr, end); - if (is_vm_hugetlb_page(vma)) mincore_hugetlb_page_range(vma, addr, end, vec); else diff --git a/mm/mlock.c b/mm/mlock.c index 192e6eebe4f2..b1eb53634005 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -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)) { @@ -91,6 +92,26 @@ void mlock_vma_page(struct page *page) } /* + * Isolate a page from LRU with optional get_page() pin. + * Assumes lru_lock already held and page already pinned. + */ +static bool __munlock_isolate_lru_page(struct page *page, bool getpage) +{ + if (PageLRU(page)) { + struct lruvec *lruvec; + + lruvec = mem_cgroup_page_lruvec(page, page_zone(page)); + if (getpage) + get_page(page); + ClearPageLRU(page); + del_page_from_lru_list(page, lruvec, page_lru(page)); + return true; + } + + return false; +} + +/* * Finish munlock after successful page isolation * * Page must be locked. This is a wrapper for try_to_munlock() @@ -126,9 +147,9 @@ static void __munlock_isolated_page(struct page *page) static void __munlock_isolation_failed(struct page *page) { if (PageUnevictable(page)) - count_vm_event(UNEVICTABLE_PGSTRANDED); + __count_vm_event(UNEVICTABLE_PGSTRANDED); else - count_vm_event(UNEVICTABLE_PGMUNLOCKED); + __count_vm_event(UNEVICTABLE_PGMUNLOCKED); } /** @@ -152,28 +173,35 @@ static void __munlock_isolation_failed(struct page *page) 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)); - if (TestClearPageMlocked(page)) { - nr_pages = hpage_nr_pages(page); - mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); - if (!isolate_lru_page(page)) - __munlock_isolated_page(page); - else - __munlock_isolation_failed(page); - } else { - nr_pages = hpage_nr_pages(page); - } - /* - * Regardless of the original PageMlocked flag, we determine nr_pages - * after touching the flag. This leaves a possible race with a THP page - * split, such that a whole THP page was munlocked, but nr_pages == 1. - * Returning a smaller mask due to that is OK, the worst that can - * happen is subsequent useless scanning of the former tail pages. - * The NR_MLOCK accounting can however become broken. + * Serialize with any parallel __split_huge_page_refcount() which + * might otherwise copy PageMlocked to part of the tail pages before + * we clear it in the head page. It also stabilizes hpage_nr_pages(). */ + spin_lock_irq(&zone->lru_lock); + + nr_pages = hpage_nr_pages(page); + if (!TestClearPageMlocked(page)) + goto unlock_out; + + __mod_zone_page_state(zone, NR_MLOCK, -nr_pages); + + if (__munlock_isolate_lru_page(page, true)) { + spin_unlock_irq(&zone->lru_lock); + __munlock_isolated_page(page); + goto out; + } + __munlock_isolation_failed(page); + +unlock_out: + spin_unlock_irq(&zone->lru_lock); + +out: return nr_pages - 1; } @@ -253,8 +281,8 @@ static int __mlock_posix_error_return(long retval) static bool __putback_lru_fast_prepare(struct page *page, struct pagevec *pvec, int *pgrescued) { - VM_BUG_ON(PageLRU(page)); - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(!PageLocked(page), page); if (page_mapcount(page) <= 1 && page_evictable(page)) { pagevec_add(pvec, page); @@ -310,34 +338,24 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) struct page *page = pvec->pages[i]; if (TestClearPageMlocked(page)) { - struct lruvec *lruvec; - int lru; - - if (PageLRU(page)) { - lruvec = mem_cgroup_page_lruvec(page, zone); - lru = page_lru(page); - /* - * We already have pin from follow_page_mask() - * so we can spare the get_page() here. - */ - ClearPageLRU(page); - del_page_from_lru_list(page, lruvec, lru); - } else { - __munlock_isolation_failed(page); - goto skip_munlock; - } - - } else { -skip_munlock: /* - * We won't be munlocking this page in the next phase - * but we still need to release the follow_page_mask() - * pin. We cannot do it under lru_lock however. If it's - * the last pin, __page_cache_release would deadlock. + * We already have pin from follow_page_mask() + * so we can spare the get_page() here. */ - pagevec_add(&pvec_putback, pvec->pages[i]); - pvec->pages[i] = NULL; + if (__munlock_isolate_lru_page(page, false)) + continue; + else + __munlock_isolation_failed(page); } + + /* + * We won't be munlocking this page in the next phase + * but we still need to release the follow_page_mask() + * pin. We cannot do it under lru_lock however. If it's + * the last pin, __page_cache_release() would deadlock. + */ + pagevec_add(&pvec_putback, pvec->pages[i]); + pvec->pages[i] = NULL; } delta_munlocked = -nr + pagevec_count(&pvec_putback); __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked); @@ -709,19 +727,21 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) lru_add_drain_all(); /* flush pagevec */ - down_write(¤t->mm->mmap_sem); len = PAGE_ALIGN(len + (start & ~PAGE_MASK)); start &= PAGE_MASK; - locked = len >> PAGE_SHIFT; - locked += current->mm->locked_vm; - lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; + locked = len >> PAGE_SHIFT; + + down_write(¤t->mm->mmap_sem); + + locked += current->mm->locked_vm; /* check against resource limits */ if ((locked <= lock_limit) || capable(CAP_IPC_LOCK)) error = do_mlock(start, len, 1); + up_write(¤t->mm->mmap_sem); if (!error) error = __mm_populate(start, len, 0); @@ -732,11 +752,13 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) { int ret; - down_write(¤t->mm->mmap_sem); len = PAGE_ALIGN(len + (start & ~PAGE_MASK)); start &= PAGE_MASK; + + down_write(¤t->mm->mmap_sem); ret = do_mlock(start, len, 0); up_write(¤t->mm->mmap_sem); + return ret; } @@ -781,12 +803,12 @@ SYSCALL_DEFINE1(mlockall, int, flags) if (flags & MCL_CURRENT) lru_add_drain_all(); /* flush pagevec */ - down_write(¤t->mm->mmap_sem); - lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; ret = -ENOMEM; + down_write(¤t->mm->mmap_sem); + if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) || capable(CAP_IPC_LOCK)) ret = do_mlockall(flags); diff --git a/mm/mm_init.c b/mm/mm_init.c index 68562e92d50c..4074caf9936b 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -202,5 +202,4 @@ static int __init mm_sysfs_init(void) return 0; } - -__initcall(mm_sysfs_init); +postcore_initcall(mm_sysfs_init); diff --git a/mm/mmap.c b/mm/mmap.c index 834b2d785f1e..b1202cf81f4b 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -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> @@ -86,6 +87,7 @@ EXPORT_SYMBOL(vm_get_page_prot); int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; /* heuristic overcommit */ int sysctl_overcommit_ratio __read_mostly = 50; /* default is 50% */ +unsigned long sysctl_overcommit_kbytes __read_mostly; int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */ unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */ @@ -404,7 +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; @@ -680,8 +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); } /* @@ -893,7 +896,15 @@ again: remove_next = 1 + (end > next->vm_end); static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags) { - if (vma->vm_flags ^ vm_flags) + /* + * VM_SOFTDIRTY should not prevent from VMA merging, if we + * match the flags but dirty bit -- the caller should mark + * merged VMA as dirty. If dirty bit won't be excluded from + * comparison, we increase pressue on the memory system forcing + * the kernel to generate new VMAs when old one could be + * extended instead. + */ + if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY) return 0; if (vma->vm_file != file) return 0; @@ -1082,7 +1093,7 @@ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct * return a->vm_end == b->vm_start && mpol_equal(vma_policy(a), vma_policy(b)) && a->vm_file == b->vm_file && - !((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC)) && + !((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC|VM_SOFTDIRTY)) && b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); } @@ -1190,6 +1201,24 @@ static inline unsigned long round_hint_to_min(unsigned long hint) return hint; } +static inline int mlock_future_check(struct mm_struct *mm, + unsigned long flags, + unsigned long len) +{ + unsigned long locked, lock_limit; + + /* mlock MCL_FUTURE? */ + if (flags & VM_LOCKED) { + locked = len >> PAGE_SHIFT; + locked += mm->locked_vm; + lock_limit = rlimit(RLIMIT_MEMLOCK); + lock_limit >>= PAGE_SHIFT; + if (locked > lock_limit && !capable(CAP_IPC_LOCK)) + return -EAGAIN; + } + return 0; +} + /* * The caller must hold down_write(¤t->mm->mmap_sem). */ @@ -1251,16 +1280,8 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, if (!can_do_mlock()) return -EPERM; - /* mlock MCL_FUTURE? */ - if (vm_flags & VM_LOCKED) { - unsigned long locked, lock_limit; - locked = len >> PAGE_SHIFT; - locked += mm->locked_vm; - lock_limit = rlimit(RLIMIT_MEMLOCK); - lock_limit >>= PAGE_SHIFT; - if (locked > lock_limit && !capable(CAP_IPC_LOCK)) - return -EAGAIN; - } + if (mlock_future_check(mm, vm_flags, len)) + return -EAGAIN; if (file) { struct inode *inode = file_inode(file); @@ -1280,7 +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; @@ -1970,34 +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; } @@ -2369,7 +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); } /* @@ -2591,18 +2613,9 @@ static unsigned long do_brk(unsigned long addr, unsigned long len) if (error & ~PAGE_MASK) return error; - /* - * mlock MCL_FUTURE? - */ - if (mm->def_flags & VM_LOCKED) { - unsigned long locked, lock_limit; - locked = len >> PAGE_SHIFT; - locked += mm->locked_vm; - lock_limit = rlimit(RLIMIT_MEMLOCK); - lock_limit >>= PAGE_SHIFT; - if (locked > lock_limit && !capable(CAP_IPC_LOCK)) - return -EAGAIN; - } + error = mlock_future_check(mm, mm->def_flags, len); + if (error) + return error; /* * mm->mmap_sem is required to protect against another thread @@ -2908,7 +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) { @@ -2917,7 +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; @@ -2938,11 +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); @@ -3140,7 +3165,7 @@ static int init_user_reserve(void) sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17); return 0; } -module_init(init_user_reserve) +subsys_initcall(init_user_reserve); /* * Initialise sysctl_admin_reserve_kbytes. @@ -3161,7 +3186,7 @@ static int init_admin_reserve(void) sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13); return 0; } -module_init(init_admin_reserve) +subsys_initcall(init_admin_reserve); /* * Reinititalise user and admin reserves if memory is added or removed. @@ -3231,4 +3256,4 @@ static int __meminit init_reserve_notifier(void) return 0; } -module_init(init_reserve_notifier) +subsys_initcall(init_reserve_notifier); diff --git a/mm/mmu_context.c b/mm/mmu_context.c index 8a8cd0265e52..f802c2d216a7 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/mmu_notifier.c b/mm/mmu_notifier.c index 93e6089cb456..41cefdf0aadd 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -329,5 +329,4 @@ static int __init mmu_notifier_init(void) { return init_srcu_struct(&srcu); } - -module_init(mmu_notifier_init); +subsys_initcall(mmu_notifier_init); diff --git a/mm/mprotect.c b/mm/mprotect.c index bb53a6591aea..c43d557941f8 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -23,6 +23,7 @@ #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/perf_event.h> +#include <linux/ksm.h> #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/cacheflush.h> @@ -35,6 +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) @@ -44,7 +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; @@ -57,36 +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) { + 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); @@ -117,15 +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); @@ -138,18 +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; @@ -209,15 +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 2c254d374655..04a9d94333a5 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -41,11 +41,13 @@ static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, if (limit > memblock.current_limit) limit = memblock.current_limit; - addr = memblock_find_in_range_node(goal, limit, size, align, nid); + addr = memblock_find_in_range_node(size, align, goal, limit, nid); if (!addr) return NULL; - memblock_reserve(addr, size); + if (memblock_reserve(addr, size)) + return NULL; + ptr = phys_to_virt(addr); memset(ptr, 0, size); /* @@ -114,16 +116,27 @@ static unsigned long __init __free_memory_core(phys_addr_t start, static unsigned long __init free_low_memory_core_early(void) { unsigned long count = 0; - phys_addr_t start, end, size; + phys_addr_t start, end; u64 i; - for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) + for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL) count += __free_memory_core(start, end); - /* free range that is used for reserved array if we allocate it */ - size = get_allocated_memblock_reserved_regions_info(&start); - if (size) - count += __free_memory_core(start, start + size); +#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK + { + phys_addr_t size; + + /* Free memblock.reserved array if it was allocated */ + size = get_allocated_memblock_reserved_regions_info(&start); + if (size) + count += __free_memory_core(start, start + size); + + /* Free memblock.memory array if it was allocated */ + size = get_allocated_memblock_memory_regions_info(&start); + if (size) + count += __free_memory_core(start, start + size); + } +#endif return count; } @@ -161,7 +174,7 @@ unsigned long __init free_all_bootmem(void) reset_all_zones_managed_pages(); /* - * We need to use MAX_NUMNODES instead of NODE_DATA(0)->node_id + * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id * because in some case like Node0 doesn't have RAM installed * low ram will be on Node1 */ @@ -215,7 +228,7 @@ static void * __init ___alloc_bootmem_nopanic(unsigned long size, restart: - ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, goal, limit); + ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align, goal, limit); if (ptr) return ptr; @@ -299,7 +312,7 @@ again: if (ptr) return ptr; - ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, + ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align, goal, limit); if (ptr) return ptr; @@ -321,7 +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) { diff --git a/mm/nommu.c b/mm/nommu.c index fec093adad9c..85f8d6698d48 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -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> @@ -60,6 +62,7 @@ unsigned long highest_memmap_pfn; struct percpu_counter vm_committed_as; int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */ int sysctl_overcommit_ratio = 50; /* default is 50% */ +unsigned long sysctl_overcommit_kbytes __read_mostly; int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT; int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS; unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */ @@ -295,7 +298,7 @@ long vwrite(char *buf, char *addr, unsigned long count) count = -(unsigned long) addr; memcpy(addr, buf, count); - return(count); + return count; } /* @@ -458,7 +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) { } @@ -767,16 +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) { @@ -824,8 +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 @@ -834,7 +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; } } @@ -873,8 +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 @@ -885,7 +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; } } @@ -994,7 +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)) @@ -1002,8 +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)) @@ -1034,23 +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 */ @@ -1658,7 +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" @@ -1984,6 +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/oom_kill.c b/mm/oom_kill.c index 1e4a600a6163..3291e82d4352 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -47,19 +47,21 @@ static DEFINE_SPINLOCK(zone_scan_lock); #ifdef CONFIG_NUMA /** * has_intersects_mems_allowed() - check task eligiblity for kill - * @tsk: task struct of which task to consider + * @start: task struct of which task to consider * @mask: nodemask passed to page allocator for mempolicy ooms * * Task eligibility is determined by whether or not a candidate task, @tsk, * shares the same mempolicy nodes as current if it is bound by such a policy * and whether or not it has the same set of allowed cpuset nodes. */ -static bool has_intersects_mems_allowed(struct task_struct *tsk, +static bool has_intersects_mems_allowed(struct task_struct *start, const nodemask_t *mask) { - struct task_struct *start = tsk; + struct task_struct *tsk; + bool ret = false; - do { + rcu_read_lock(); + for_each_thread(start, tsk) { if (mask) { /* * If this is a mempolicy constrained oom, tsk's @@ -67,19 +69,20 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk, * mempolicy intersects current, otherwise it may be * needlessly killed. */ - if (mempolicy_nodemask_intersects(tsk, mask)) - return true; + ret = mempolicy_nodemask_intersects(tsk, mask); } else { /* * This is not a mempolicy constrained oom, so only * check the mems of tsk's cpuset. */ - if (cpuset_mems_allowed_intersects(current, tsk)) - return true; + ret = cpuset_mems_allowed_intersects(current, tsk); } - } while_each_thread(start, tsk); + if (ret) + break; + } + rcu_read_unlock(); - return false; + return ret; } #else static bool has_intersects_mems_allowed(struct task_struct *tsk, @@ -97,16 +100,21 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk, */ struct task_struct *find_lock_task_mm(struct task_struct *p) { - struct task_struct *t = p; + struct task_struct *t; - do { + rcu_read_lock(); + + for_each_thread(p, t) { task_lock(t); if (likely(t->mm)) - return t; + goto found; task_unlock(t); - } while_each_thread(p, t); + } + t = NULL; +found: + rcu_read_unlock(); - return NULL; + return t; } /* return true if the task is not adequate as candidate victim task. */ @@ -170,7 +178,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, * implementation used by LSMs. */ if (has_capability_noaudit(p, CAP_SYS_ADMIN)) - adj -= 30; + points -= (points * 3) / 100; /* Normalize to oom_score_adj units */ adj *= totalpages / 1000; @@ -301,7 +309,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, unsigned long chosen_points = 0; rcu_read_lock(); - do_each_thread(g, p) { + for_each_process_thread(g, p) { unsigned int points; switch (oom_scan_process_thread(p, totalpages, nodemask, @@ -319,11 +327,15 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, break; }; points = oom_badness(p, NULL, nodemask, totalpages); - if (points > chosen_points) { - chosen = p; - chosen_points = points; - } - } while_each_thread(g, p); + if (!points || points < chosen_points) + continue; + /* Prefer thread group leaders for display purposes */ + if (points == chosen_points && thread_group_leader(chosen)) + continue; + + chosen = p; + chosen_points = points; + } if (chosen) get_task_struct(chosen); rcu_read_unlock(); @@ -406,7 +418,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, { struct task_struct *victim = p; struct task_struct *child; - struct task_struct *t = p; + struct task_struct *t; struct mm_struct *mm; unsigned int victim_points = 0; static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL, @@ -437,7 +449,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, * still freeing memory. */ read_lock(&tasklist_lock); - do { + for_each_thread(p, t) { list_for_each_entry(child, &t->children, sibling) { unsigned int child_points; @@ -455,13 +467,11 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, get_task_struct(victim); } } - } while_each_thread(p, t); + } read_unlock(&tasklist_lock); - rcu_read_lock(); p = find_lock_task_mm(victim); if (!p) { - rcu_read_unlock(); put_task_struct(victim); return; } else if (victim != p) { @@ -487,6 +497,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, * That thread will now get access to memory reserves since it has a * pending fatal signal. */ + rcu_read_lock(); for_each_process(p) if (p->mm == mm && !same_thread_group(p, victim) && !(p->flags & PF_KTHREAD)) { diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 63807583d8e8..ef413492a149 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -191,6 +191,26 @@ static unsigned long writeout_period_time = 0; * global dirtyable memory first. */ +/** + * zone_dirtyable_memory - number of dirtyable pages in a zone + * @zone: the zone + * + * Returns the zone's number of pages potentially available for dirty + * page cache. This is the base value for the per-zone dirty limits. + */ +static unsigned long zone_dirtyable_memory(struct zone *zone) +{ + unsigned long nr_pages; + + nr_pages = zone_page_state(zone, NR_FREE_PAGES); + nr_pages -= min(nr_pages, zone->dirty_balance_reserve); + + nr_pages += zone_page_state(zone, NR_INACTIVE_FILE); + nr_pages += zone_page_state(zone, NR_ACTIVE_FILE); + + return nr_pages; +} + static unsigned long highmem_dirtyable_memory(unsigned long total) { #ifdef CONFIG_HIGHMEM @@ -198,11 +218,9 @@ static unsigned long highmem_dirtyable_memory(unsigned long total) unsigned long x = 0; for_each_node_state(node, N_HIGH_MEMORY) { - struct zone *z = - &NODE_DATA(node)->node_zones[ZONE_HIGHMEM]; + struct zone *z = &NODE_DATA(node)->node_zones[ZONE_HIGHMEM]; - x += zone_page_state(z, NR_FREE_PAGES) + - zone_reclaimable_pages(z) - z->dirty_balance_reserve; + x += zone_dirtyable_memory(z); } /* * Unreclaimable memory (kernel memory or anonymous memory @@ -238,9 +256,12 @@ static unsigned long global_dirtyable_memory(void) { unsigned long x; - x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages(); + x = global_page_state(NR_FREE_PAGES); x -= min(x, dirty_balance_reserve); + x += global_page_state(NR_INACTIVE_FILE); + x += global_page_state(NR_ACTIVE_FILE); + if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); @@ -289,32 +310,6 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) } /** - * zone_dirtyable_memory - number of dirtyable pages in a zone - * @zone: the zone - * - * Returns the zone's number of pages potentially available for dirty - * page cache. This is the base value for the per-zone dirty limits. - */ -static unsigned long zone_dirtyable_memory(struct zone *zone) -{ - /* - * The effective global number of dirtyable pages may exclude - * highmem as a big-picture measure to keep the ratio between - * dirty memory and lowmem reasonable. - * - * But this function is purely about the individual zone and a - * highmem zone can hold its share of dirty pages, so we don't - * care about vm_highmem_is_dirtyable here. - */ - unsigned long nr_pages = zone_page_state(zone, NR_FREE_PAGES) + - zone_reclaimable_pages(zone); - - /* don't allow this to underflow */ - nr_pages -= min(nr_pages, zone->dirty_balance_reserve); - return nr_pages; -} - -/** * zone_dirty_limit - maximum number of dirty pages allowed in a zone * @zone: the zone * @@ -1567,9 +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) @@ -2178,11 +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); @@ -2191,7 +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 5248fe070aa4..5dba2933c9c0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -205,7 +205,7 @@ static char * const zone_names[MAX_NR_ZONES] = { }; int min_free_kbytes = 1024; -int user_min_free_kbytes; +int user_min_free_kbytes = -1; static unsigned long __meminitdata nr_kernel_pages; static unsigned long __meminitdata nr_all_pages; @@ -295,7 +295,8 @@ static inline int bad_range(struct zone *zone, struct page *page) } #endif -static void bad_page(struct page *page) +static void bad_page(struct page *page, const char *reason, + unsigned long bad_flags) { static unsigned long resume; static unsigned long nr_shown; @@ -329,7 +330,7 @@ static void bad_page(struct page *page) printk(KERN_ALERT "BUG: Bad page state in process %s pfn:%05lx\n", current->comm, page_to_pfn(page)); - dump_page(page); + dump_page_badflags(page, reason, bad_flags); print_modules(); dump_stack(); @@ -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); } } @@ -383,7 +386,7 @@ static int destroy_compound_page(struct page *page, unsigned long order) int bad = 0; if (unlikely(compound_order(page) != order)) { - bad_page(page); + bad_page(page, "wrong compound order", 0); bad++; } @@ -392,8 +395,11 @@ static int destroy_compound_page(struct page *page, unsigned long order) for (i = 1; i < nr_pages; i++) { struct page *p = page + i; - if (unlikely(!PageTail(p) || (p->first_page != page))) { - bad_page(page); + if (unlikely(!PageTail(p))) { + bad_page(page, "PageTail not set", 0); + bad++; + } else if (unlikely(p->first_page != page)) { + bad_page(page, "first_page not consistent", 0); bad++; } __ClearPageTail(p); @@ -506,12 +512,12 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, return 0; if (page_is_guard(buddy) && page_order(buddy) == order) { - VM_BUG_ON(page_count(buddy) != 0); + VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); return 1; } if (PageBuddy(buddy) && page_order(buddy) == order) { - VM_BUG_ON(page_count(buddy) != 0); + VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); return 1; } return 0; @@ -561,8 +567,8 @@ static inline void __free_one_page(struct page *page, page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); - VM_BUG_ON(page_idx & ((1 << order) - 1)); - VM_BUG_ON(bad_range(zone, page)); + VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page); + VM_BUG_ON_PAGE(bad_range(zone, page), page); while (order < MAX_ORDER-1) { buddy_idx = __find_buddy_index(page_idx, order); @@ -618,12 +624,23 @@ out: static inline int free_pages_check(struct page *page) { - if (unlikely(page_mapcount(page) | - (page->mapping != NULL) | - (atomic_read(&page->_count) != 0) | - (page->flags & PAGE_FLAGS_CHECK_AT_FREE) | - (mem_cgroup_bad_page_check(page)))) { - bad_page(page); + const char *bad_reason = NULL; + unsigned long bad_flags = 0; + + if (unlikely(page_mapcount(page))) + bad_reason = "nonzero mapcount"; + if (unlikely(page->mapping != NULL)) + bad_reason = "non-NULL mapping"; + if (unlikely(atomic_read(&page->_count) != 0)) + bad_reason = "nonzero _count"; + if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_FREE)) { + bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set"; + bad_flags = PAGE_FLAGS_CHECK_AT_FREE; + } + if (unlikely(mem_cgroup_bad_page_check(page))) + bad_reason = "cgroup check failed"; + if (unlikely(bad_reason)) { + bad_page(page, bad_reason, bad_flags); return 1; } page_cpupid_reset_last(page); @@ -813,7 +830,7 @@ static inline void expand(struct zone *zone, struct page *page, area--; high--; size >>= 1; - VM_BUG_ON(bad_range(zone, &page[size])); + VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]); #ifdef CONFIG_DEBUG_PAGEALLOC if (high < debug_guardpage_minorder()) { @@ -843,12 +860,23 @@ static inline void expand(struct zone *zone, struct page *page, */ static inline int check_new_page(struct page *page) { - if (unlikely(page_mapcount(page) | - (page->mapping != NULL) | - (atomic_read(&page->_count) != 0) | - (page->flags & PAGE_FLAGS_CHECK_AT_PREP) | - (mem_cgroup_bad_page_check(page)))) { - bad_page(page); + const char *bad_reason = NULL; + unsigned long bad_flags = 0; + + if (unlikely(page_mapcount(page))) + bad_reason = "nonzero mapcount"; + if (unlikely(page->mapping != NULL)) + bad_reason = "non-NULL mapping"; + if (unlikely(atomic_read(&page->_count) != 0)) + bad_reason = "nonzero _count"; + if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) { + bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set"; + bad_flags = PAGE_FLAGS_CHECK_AT_PREP; + } + if (unlikely(mem_cgroup_bad_page_check(page))) + bad_reason = "cgroup check failed"; + if (unlikely(bad_reason)) { + bad_page(page, bad_reason, bad_flags); return 1; } return 0; @@ -955,7 +983,7 @@ int move_freepages(struct zone *zone, for (page = start_page; page <= end_page;) { /* Make sure we are not inadvertently changing nodes */ - VM_BUG_ON(page_to_nid(page) != zone_to_nid(zone)); + VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page); if (!pfn_valid_within(page_to_pfn(page))) { page++; @@ -1404,8 +1432,8 @@ void split_page(struct page *page, unsigned int order) { int i; - VM_BUG_ON(PageCompound(page)); - VM_BUG_ON(!page_count(page)); + VM_BUG_ON_PAGE(PageCompound(page), page); + VM_BUG_ON_PAGE(!page_count(page), page); #ifdef CONFIG_KMEMCHECK /* @@ -1548,11 +1576,12 @@ 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); - VM_BUG_ON(bad_range(zone, page)); + VM_BUG_ON_PAGE(bad_range(zone, page), page); if (prep_new_page(page, order, gfp_flags)) goto again; return page; @@ -1828,7 +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 @@ -1912,19 +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 @@ -2072,13 +2094,6 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...) return; /* - * Walking all memory to count page types is very expensive and should - * be inhibited in non-blockable contexts. - */ - if (!(gfp_mask & __GFP_WAIT)) - filter |= SHOW_MEM_FILTER_PAGE_COUNT; - - /* * This documents exceptions given to allocations in certain * contexts that are allowed to allocate outside current's set * of allowed nodes. @@ -2242,10 +2257,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, preferred_zone, migratetype); if (page) { preferred_zone->compact_blockskip_flush = false; - preferred_zone->compact_considered = 0; - preferred_zone->compact_defer_shift = 0; - if (order >= preferred_zone->compact_order_failed) - preferred_zone->compact_order_failed = order + 1; + compaction_defer_reset(preferred_zone, order, true); count_vm_event(COMPACTSUCCESS); return page; } @@ -2372,32 +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) { @@ -2487,12 +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 @@ -2535,8 +2555,15 @@ rebalance: } /* Atomic allocations - we can't balance anything */ - if (!wait) + if (!wait) { + /* + * All existing users of the deprecated __GFP_NOFAIL are + * blockable, so warn of any new users that actually allow this + * type of allocation to fail. + */ + WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL); goto nopage; + } /* Avoid recursion of direct reclaim */ if (current->flags & PF_MEMALLOC) @@ -2669,7 +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; @@ -2697,7 +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, @@ -2710,12 +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. @@ -2735,7 +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); @@ -3003,9 +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; } @@ -3901,6 +3945,7 @@ static void setup_zone_migrate_reserve(struct zone *zone) struct page *page; unsigned long block_migratetype; int reserve; + int old_reserve; /* * Get the start pfn, end pfn and the number of blocks to reserve @@ -3922,6 +3967,12 @@ static void setup_zone_migrate_reserve(struct zone *zone) * future allocation of hugepages at runtime. */ reserve = min(2, reserve); + old_reserve = zone->nr_migrate_reserve_block; + + /* When memory hot-add, we almost always need to do nothing */ + if (reserve == old_reserve) + return; + zone->nr_migrate_reserve_block = reserve; for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { if (!pfn_valid(pfn)) @@ -3959,6 +4010,12 @@ static void setup_zone_migrate_reserve(struct zone *zone) reserve--; continue; } + } else if (!old_reserve) { + /* + * At boot time we don't need to scan the whole zone + * for turning off MIGRATE_RESERVE. + */ + break; } /* @@ -4209,7 +4266,6 @@ static noinline __init_refok int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) { int i; - struct pglist_data *pgdat = zone->zone_pgdat; size_t alloc_size; /* @@ -4225,7 +4281,8 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) if (!slab_is_available()) { zone->wait_table = (wait_queue_head_t *) - alloc_bootmem_node_nopanic(pgdat, alloc_size); + memblock_virt_alloc_node_nopanic( + alloc_size, zone->zone_pgdat->node_id); } else { /* * This case means that a zone whose size was 0 gets new memory @@ -4345,13 +4402,14 @@ bool __meminit early_pfn_in_nid(unsigned long pfn, int node) #endif /** - * free_bootmem_with_active_regions - Call free_bootmem_node for each active range + * free_bootmem_with_active_regions - Call memblock_free_early_nid for each active range * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed. - * @max_low_pfn: The highest PFN that will be passed to free_bootmem_node + * @max_low_pfn: The highest PFN that will be passed to memblock_free_early_nid * * If an architecture guarantees that all ranges registered with * add_active_ranges() contain no holes and may be freed, this - * this function may be used instead of calling free_bootmem() manually. + * this function may be used instead of calling memblock_free_early_nid() + * manually. */ void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn) { @@ -4363,9 +4421,9 @@ void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn) end_pfn = min(end_pfn, max_low_pfn); if (start_pfn < end_pfn) - free_bootmem_node(NODE_DATA(this_nid), - PFN_PHYS(start_pfn), - (end_pfn - start_pfn) << PAGE_SHIFT); + memblock_free_early_nid(PFN_PHYS(start_pfn), + (end_pfn - start_pfn) << PAGE_SHIFT, + this_nid); } } @@ -4636,8 +4694,9 @@ static void __init setup_usemap(struct pglist_data *pgdat, unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize); zone->pageblock_flags = NULL; if (usemapsize) - zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat, - usemapsize); + zone->pageblock_flags = + memblock_virt_alloc_node_nopanic(usemapsize, + pgdat->node_id); } #else static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone, @@ -4831,7 +4890,8 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat) size = (end - start) * sizeof(struct page); map = alloc_remap(pgdat->node_id, size); if (!map) - map = alloc_bootmem_node_nopanic(pgdat, size); + map = memblock_virt_alloc_node_nopanic(size, + pgdat->node_id); pgdat->node_mem_map = map + (pgdat->node_start_pfn - start); } #ifndef CONFIG_NEED_MULTIPLE_NODES @@ -4861,7 +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 @@ -5012,9 +5073,33 @@ 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_region *r; + + /* Need to find movable_zone earlier when movable_node is specified. */ + find_usable_zone_for_movable(); /* - * If movablecore was specified, calculate what size of + * If movable_node is specified, ignore kernelcore and movablecore + * options. + */ + if (movable_node_is_enabled()) { + for_each_memblock(memory, r) { + if (!memblock_is_hotpluggable(r)) + continue; + + nid = r->nid; + + usable_startpfn = PFN_DOWN(r->base); + zone_movable_pfn[nid] = zone_movable_pfn[nid] ? + min(usable_startpfn, zone_movable_pfn[nid]) : + usable_startpfn; + } + + goto out2; + } + + /* + * If movablecore=nn[KMG] was specified, calculate what size of * kernelcore that corresponds so that memory usable for * any allocation type is evenly spread. If both kernelcore * and movablecore are specified, then the value of kernelcore @@ -5040,7 +5125,6 @@ static void __init find_zone_movable_pfns_for_nodes(void) goto out; /* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */ - find_usable_zone_for_movable(); usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone]; restart: @@ -5131,6 +5215,7 @@ restart: if (usable_nodes && required_kernelcore > usable_nodes) goto restart; +out2: /* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */ for (nid = 0; nid < MAX_NUMNODES; nid++) zone_movable_pfn[nid] = @@ -5692,7 +5777,12 @@ module_init(init_per_zone_wmark_min) int min_free_kbytes_sysctl_handler(ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec(table, write, buffer, length, ppos); + int rc; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + if (write) { user_min_free_kbytes = min_free_kbytes; setup_per_zone_wmarks(); @@ -5857,7 +5947,7 @@ void *__init alloc_large_system_hash(const char *tablename, do { size = bucketsize << log2qty; if (flags & HASH_EARLY) - table = alloc_bootmem_nopanic(size); + table = memblock_virt_alloc_nopanic(size, 0); else if (hashdist) table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL); else { @@ -5959,7 +6049,7 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags, pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); - VM_BUG_ON(!zone_spans_pfn(zone, pfn)); + VM_BUG_ON_PAGE(!zone_spans_pfn(zone, pfn), page); for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) if (flags & value) @@ -6457,12 +6547,25 @@ static void dump_page_flags(unsigned long flags) printk(")\n"); } -void dump_page(struct page *page) +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", page, atomic_read(&page->_count), page_mapcount(page), page->mapping, page->index); dump_page_flags(page->flags); + if (reason) + pr_alert("page dumped because: %s\n", reason); + if (page->flags & badflags) { + pr_alert("bad because of flags:\n"); + dump_page_flags(page->flags & badflags); + } mem_cgroup_print_bad_page(page); } + +void dump_page(struct page *page, const char *reason) +{ + dump_page_badflags(page, reason, 0); +} +EXPORT_SYMBOL(dump_page); diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 6d757e3a872a..3708264d2833 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -54,8 +54,9 @@ static int __init alloc_node_page_cgroup(int nid) table_size = sizeof(struct page_cgroup) * nr_pages; - base = __alloc_bootmem_node_nopanic(NODE_DATA(nid), - table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); + base = memblock_virt_alloc_try_nid_nopanic( + table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), + BOOTMEM_ALLOC_ACCESSIBLE, nid); if (!base) return -ENOMEM; NODE_DATA(nid)->node_page_cgroup = base; @@ -174,7 +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; @@ -187,9 +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; @@ -222,8 +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; @@ -451,7 +452,7 @@ unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id) * lookup_swap_cgroup_id - lookup mem_cgroup id tied to swap entry * @ent: swap entry to be looked up. * - * Returns CSS ID of mem_cgroup at success. 0 at failure. (0 is invalid ID) + * Returns ID of mem_cgroup at success. 0 at failure. (0 is invalid ID) */ unsigned short lookup_swap_cgroup_id(swp_entry_t ent) { diff --git a/mm/page_io.c b/mm/page_io.c index 8c79a4764be0..7c59ef681381 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -31,13 +31,13 @@ static struct bio *get_swap_bio(gfp_t gfp_flags, bio = bio_alloc(gfp_flags, 1); if (bio) { - bio->bi_sector = map_swap_page(page, &bio->bi_bdev); - bio->bi_sector <<= PAGE_SHIFT - 9; + bio->bi_iter.bi_sector = map_swap_page(page, &bio->bi_bdev); + bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9; bio->bi_io_vec[0].bv_page = page; bio->bi_io_vec[0].bv_len = PAGE_SIZE; bio->bi_io_vec[0].bv_offset = 0; bio->bi_vcnt = 1; - bio->bi_size = PAGE_SIZE; + bio->bi_iter.bi_size = PAGE_SIZE; bio->bi_end_io = end_io; } return bio; @@ -62,7 +62,7 @@ void end_swap_bio_write(struct bio *bio, int err) printk(KERN_ALERT "Write-error on swap-device (%u:%u:%Lu)\n", imajor(bio->bi_bdev->bd_inode), iminor(bio->bi_bdev->bd_inode), - (unsigned long long)bio->bi_sector); + (unsigned long long)bio->bi_iter.bi_sector); ClearPageReclaim(page); } end_page_writeback(page); @@ -80,7 +80,7 @@ void end_swap_bio_read(struct bio *bio, int err) printk(KERN_ALERT "Read-error on swap-device (%u:%u:%Lu)\n", imajor(bio->bi_bdev->bd_inode), iminor(bio->bi_bdev->bd_inode), - (unsigned long long)bio->bi_sector); + (unsigned long long)bio->bi_iter.bi_sector); goto out; } @@ -320,8 +320,8 @@ int swap_readpage(struct page *page) int ret = 0; struct swap_info_struct *sis = page_swap_info(page); - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(PageUptodate(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageUptodate(page), page); if (frontswap_load(page) == 0) { SetPageUptodate(page); unlock_page(page); diff --git a/mm/percpu.c b/mm/percpu.c index 0d10defe951e..63e24fb4387b 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); @@ -1063,7 +1073,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, __alignof__(ai->groups[0].cpu_map[0])); ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]); - ptr = alloc_bootmem_nopanic(PFN_ALIGN(ai_size)); + ptr = memblock_virt_alloc_nopanic(PFN_ALIGN(ai_size), 0); if (!ptr) return NULL; ai = ptr; @@ -1088,7 +1098,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { - free_bootmem(__pa(ai), ai->__ai_size); + memblock_free_early(__pa(ai), ai->__ai_size); } /** @@ -1246,10 +1256,12 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ - group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[0])); - group_sizes = alloc_bootmem(ai->nr_groups * sizeof(group_sizes[0])); - unit_map = alloc_bootmem(nr_cpu_ids * sizeof(unit_map[0])); - unit_off = alloc_bootmem(nr_cpu_ids * sizeof(unit_off[0])); + group_offsets = memblock_virt_alloc(ai->nr_groups * + sizeof(group_offsets[0]), 0); + group_sizes = memblock_virt_alloc(ai->nr_groups * + sizeof(group_sizes[0]), 0); + unit_map = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_map[0]), 0); + unit_off = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_off[0]), 0); for (cpu = 0; cpu < nr_cpu_ids; cpu++) unit_map[cpu] = UINT_MAX; @@ -1311,7 +1323,8 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, * empty chunks. */ pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2; - pcpu_slot = alloc_bootmem(pcpu_nr_slots * sizeof(pcpu_slot[0])); + pcpu_slot = memblock_virt_alloc( + pcpu_nr_slots * sizeof(pcpu_slot[0]), 0); for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_slot[i]); @@ -1322,7 +1335,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, * covers static area + reserved area (mostly used for module * static percpu allocation). */ - schunk = alloc_bootmem(pcpu_chunk_struct_size); + schunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0); INIT_LIST_HEAD(&schunk->list); schunk->base_addr = base_addr; schunk->map = smap; @@ -1340,13 +1353,17 @@ 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) { - dchunk = alloc_bootmem(pcpu_chunk_struct_size); + dchunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0); INIT_LIST_HEAD(&dchunk->list); dchunk->base_addr = base_addr; dchunk->map = dmap; @@ -1355,8 +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 */ @@ -1626,7 +1645,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); - areas = alloc_bootmem_nopanic(areas_size); + areas = memblock_virt_alloc_nopanic(areas_size, 0); if (!areas) { rc = -ENOMEM; goto out_free; @@ -1686,10 +1705,10 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, max_distance += ai->unit_size; /* warn if maximum distance is further than 75% of vmalloc space */ - if (max_distance > (VMALLOC_END - VMALLOC_START) * 3 / 4) { + if (max_distance > VMALLOC_TOTAL * 3 / 4) { pr_warning("PERCPU: max_distance=0x%zx too large for vmalloc " "space 0x%lx\n", max_distance, - (unsigned long)(VMALLOC_END - VMALLOC_START)); + VMALLOC_TOTAL); #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK /* and fail if we have fallback */ rc = -EINVAL; @@ -1712,7 +1731,7 @@ out_free_areas: out_free: pcpu_free_alloc_info(ai); if (areas) - free_bootmem(__pa(areas), areas_size); + memblock_free_early(__pa(areas), areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ @@ -1760,7 +1779,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, /* unaligned allocations can't be freed, round up to page size */ pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * sizeof(pages[0])); - pages = alloc_bootmem(pages_size); + pages = memblock_virt_alloc(pages_size, 0); /* allocate pages */ j = 0; @@ -1823,7 +1842,7 @@ enomem: free_fn(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: - free_bootmem(__pa(pages), pages_size); + memblock_free_early(__pa(pages), pages_size); pcpu_free_alloc_info(ai); return rc; } @@ -1848,12 +1867,13 @@ EXPORT_SYMBOL(__per_cpu_offset); static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, size_t align) { - return __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS)); + return memblock_virt_alloc_from_nopanic( + size, align, __pa(MAX_DMA_ADDRESS)); } static void __init pcpu_dfl_fc_free(void *ptr, size_t size) { - free_bootmem(__pa(ptr), size); + memblock_free_early(__pa(ptr), size); } void __init setup_per_cpu_areas(void) @@ -1896,7 +1916,9 @@ void __init setup_per_cpu_areas(void) void *fc; ai = pcpu_alloc_alloc_info(1, 1); - fc = __alloc_bootmem(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); + fc = memblock_virt_alloc_from_nopanic(unit_size, + PAGE_SIZE, + __pa(MAX_DMA_ADDRESS)); if (!ai || !fc) panic("Failed to allocate memory for percpu areas."); /* kmemleak tracks the percpu allocations separately */ diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index fd26d0433509..cb79065c19e5 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -412,7 +412,7 @@ 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, @@ -456,25 +456,23 @@ 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 7cdbb44aa90b..0ca36a7770b1 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); @@ -211,8 +210,6 @@ out: int force_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read) { - int ret = 0; - if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages)) return -EINVAL; @@ -226,39 +223,23 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp, this_chunk = nr_to_read; err = __do_page_cache_readahead(mapping, filp, offset, this_chunk, 0); - if (err < 0) { - ret = err; - break; - } - ret += err; + if (err < 0) + return err; + offset += this_chunk; nr_to_read -= this_chunk; } - return ret; + 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); } /* @@ -351,7 +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; @@ -431,7 +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) @@ -576,8 +557,7 @@ do_readahead(struct address_space *mapping, struct file *filp, if (!mapping || !mapping->a_ops) return -EINVAL; - force_page_cache_readahead(mapping, filp, index, nr); - return 0; + return force_page_cache_readahead(mapping, filp, index, nr); } SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) diff --git a/mm/rmap.c b/mm/rmap.c index 068522d8502a..9c3e77396d1a 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -660,17 +660,22 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) return 1; } +struct page_referenced_arg { + int mapcount; + int referenced; + unsigned long vm_flags; + struct mem_cgroup *memcg; +}; /* - * Subfunctions of page_referenced: page_referenced_one called - * repeatedly from either page_referenced_anon or page_referenced_file. + * arg: page_referenced_arg will be passed */ int page_referenced_one(struct page *page, struct vm_area_struct *vma, - unsigned long address, unsigned int *mapcount, - unsigned long *vm_flags) + unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; spinlock_t *ptl; int referenced = 0; + struct page_referenced_arg *pra = arg; if (unlikely(PageTransHuge(page))) { pmd_t *pmd; @@ -682,13 +687,12 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, pmd = page_check_address_pmd(page, mm, address, PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl); if (!pmd) - goto out; + return SWAP_AGAIN; if (vma->vm_flags & VM_LOCKED) { spin_unlock(ptl); - *mapcount = 0; /* break early from loop */ - *vm_flags |= VM_LOCKED; - goto out; + pra->vm_flags |= VM_LOCKED; + return SWAP_FAIL; /* To break the loop */ } /* go ahead even if the pmd is pmd_trans_splitting() */ @@ -704,13 +708,12 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, */ pte = page_check_address(page, mm, address, &ptl, 0); if (!pte) - goto out; + return SWAP_AGAIN; if (vma->vm_flags & VM_LOCKED) { pte_unmap_unlock(pte, ptl); - *mapcount = 0; /* break early from loop */ - *vm_flags |= VM_LOCKED; - goto out; + pra->vm_flags |= VM_LOCKED; + return SWAP_FAIL; /* To break the loop */ } if (ptep_clear_flush_young_notify(vma, address, pte)) { @@ -727,113 +730,27 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, pte_unmap_unlock(pte, ptl); } - (*mapcount)--; - - if (referenced) - *vm_flags |= vma->vm_flags; -out: - return referenced; -} - -static int page_referenced_anon(struct page *page, - struct mem_cgroup *memcg, - unsigned long *vm_flags) -{ - unsigned int mapcount; - struct anon_vma *anon_vma; - pgoff_t pgoff; - struct anon_vma_chain *avc; - int referenced = 0; - - anon_vma = page_lock_anon_vma_read(page); - if (!anon_vma) - return referenced; - - mapcount = page_mapcount(page); - pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { - struct vm_area_struct *vma = avc->vma; - unsigned long address = vma_address(page, vma); - /* - * If we are reclaiming on behalf of a cgroup, skip - * counting on behalf of references from different - * cgroups - */ - if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) - continue; - referenced += page_referenced_one(page, vma, address, - &mapcount, vm_flags); - if (!mapcount) - break; + if (referenced) { + pra->referenced++; + pra->vm_flags |= vma->vm_flags; } - page_unlock_anon_vma_read(anon_vma); - return referenced; + pra->mapcount--; + if (!pra->mapcount) + return SWAP_SUCCESS; /* To break the loop */ + + return SWAP_AGAIN; } -/** - * page_referenced_file - referenced check for object-based rmap - * @page: the page we're checking references on. - * @memcg: target memory control group - * @vm_flags: collect encountered vma->vm_flags who actually referenced the page - * - * For an object-based mapped page, find all the places it is mapped and - * check/clear the referenced flag. This is done by following the page->mapping - * pointer, then walking the chain of vmas it holds. It returns the number - * of references it found. - * - * This function is only called from page_referenced for object-based pages. - */ -static int page_referenced_file(struct page *page, - struct mem_cgroup *memcg, - unsigned long *vm_flags) +static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg) { - unsigned int mapcount; - struct address_space *mapping = page->mapping; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - struct vm_area_struct *vma; - int referenced = 0; + struct page_referenced_arg *pra = arg; + struct mem_cgroup *memcg = pra->memcg; - /* - * The caller's checks on page->mapping and !PageAnon have made - * sure that this is a file page: the check for page->mapping - * excludes the case just before it gets set on an anon page. - */ - BUG_ON(PageAnon(page)); - - /* - * The page lock not only makes sure that page->mapping cannot - * suddenly be NULLified by truncation, it makes sure that the - * structure at mapping cannot be freed and reused yet, - * so we can safely take mapping->i_mmap_mutex. - */ - BUG_ON(!PageLocked(page)); - - mutex_lock(&mapping->i_mmap_mutex); - - /* - * i_mmap_mutex does not stabilize mapcount at all, but mapcount - * is more likely to be accurate if we note it after spinning. - */ - mapcount = page_mapcount(page); - - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { - unsigned long address = vma_address(page, vma); - /* - * If we are reclaiming on behalf of a cgroup, skip - * counting on behalf of references from different - * cgroups - */ - if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) - continue; - referenced += page_referenced_one(page, vma, address, - &mapcount, vm_flags); - if (!mapcount) - break; - } + if (!mm_match_cgroup(vma->vm_mm, memcg)) + return true; - mutex_unlock(&mapping->i_mmap_mutex); - return referenced; + return false; } /** @@ -851,41 +768,57 @@ int page_referenced(struct page *page, struct mem_cgroup *memcg, unsigned long *vm_flags) { - int referenced = 0; + int ret; int we_locked = 0; + struct page_referenced_arg pra = { + .mapcount = page_mapcount(page), + .memcg = memcg, + }; + struct rmap_walk_control rwc = { + .rmap_one = page_referenced_one, + .arg = (void *)&pra, + .anon_lock = page_lock_anon_vma_read, + }; *vm_flags = 0; - if (page_mapped(page) && page_rmapping(page)) { - if (!is_locked && (!PageAnon(page) || PageKsm(page))) { - we_locked = trylock_page(page); - if (!we_locked) { - referenced++; - goto out; - } - } - if (unlikely(PageKsm(page))) - referenced += page_referenced_ksm(page, memcg, - vm_flags); - else if (PageAnon(page)) - referenced += page_referenced_anon(page, memcg, - vm_flags); - else if (page->mapping) - referenced += page_referenced_file(page, memcg, - vm_flags); - if (we_locked) - unlock_page(page); + if (!page_mapped(page)) + return 0; + + if (!page_rmapping(page)) + return 0; + + if (!is_locked && (!PageAnon(page) || PageKsm(page))) { + we_locked = trylock_page(page); + if (!we_locked) + return 1; } -out: - return referenced; + + /* + * If we are reclaiming on behalf of a cgroup, skip + * counting on behalf of references from different + * cgroups + */ + if (memcg) { + rwc.invalid_vma = invalid_page_referenced_vma; + } + + ret = rmap_walk(page, &rwc); + *vm_flags = pra.vm_flags; + + if (we_locked) + unlock_page(page); + + return pra.referenced; } static int page_mkclean_one(struct page *page, struct vm_area_struct *vma, - unsigned long address) + unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; pte_t *pte; spinlock_t *ptl; int ret = 0; + int *cleaned = arg; pte = page_check_address(page, mm, address, &ptl, 1); if (!pte) @@ -904,44 +837,44 @@ static int page_mkclean_one(struct page *page, struct vm_area_struct *vma, pte_unmap_unlock(pte, ptl); - if (ret) + if (ret) { mmu_notifier_invalidate_page(mm, address); + (*cleaned)++; + } out: - return ret; + return SWAP_AGAIN; } -static int page_mkclean_file(struct address_space *mapping, struct page *page) +static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) { - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - struct vm_area_struct *vma; - int ret = 0; - - BUG_ON(PageAnon(page)); + if (vma->vm_flags & VM_SHARED) + return false; - mutex_lock(&mapping->i_mmap_mutex); - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { - if (vma->vm_flags & VM_SHARED) { - unsigned long address = vma_address(page, vma); - ret += page_mkclean_one(page, vma, address); - } - } - mutex_unlock(&mapping->i_mmap_mutex); - return ret; + return true; } int page_mkclean(struct page *page) { - int ret = 0; + int cleaned = 0; + struct address_space *mapping; + struct rmap_walk_control rwc = { + .arg = (void *)&cleaned, + .rmap_one = page_mkclean_one, + .invalid_vma = invalid_mkclean_vma, + }; BUG_ON(!PageLocked(page)); - if (page_mapped(page)) { - struct address_space *mapping = page_mapping(page); - if (mapping) - ret = page_mkclean_file(mapping, page); - } + if (!page_mapped(page)) + return 0; - return ret; + mapping = page_mapping(page); + if (!mapping) + return 0; + + rmap_walk(page, &rwc); + + return cleaned; } EXPORT_SYMBOL_GPL(page_mkclean); @@ -961,9 +894,9 @@ void page_move_anon_rmap(struct page *page, { struct anon_vma *anon_vma = vma->anon_vma; - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON(!anon_vma); - VM_BUG_ON(page->index != linear_page_index(vma, address)); + VM_BUG_ON_PAGE(page->index != linear_page_index(vma, address), page); anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; page->mapping = (struct address_space *) anon_vma; @@ -1062,7 +995,7 @@ void do_page_add_anon_rmap(struct page *page, if (unlikely(PageKsm(page))) return; - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); /* address might be in next vma when migration races vma_adjust */ if (first) __page_set_anon_rmap(page, vma, address, exclusive); @@ -1177,17 +1110,17 @@ out: } /* - * Subfunctions of try_to_unmap: try_to_unmap_one called - * repeatedly from try_to_unmap_ksm, try_to_unmap_anon or try_to_unmap_file. + * @arg: enum ttu_flags will be passed to this argument */ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, - unsigned long address, enum ttu_flags flags) + unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; pte_t *pte; pte_t pteval; spinlock_t *ptl; int ret = SWAP_AGAIN; + enum ttu_flags flags = (enum ttu_flags)arg; pte = page_check_address(page, mm, address, &ptl, 0); if (!pte) @@ -1232,6 +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; @@ -1389,9 +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 */ } @@ -1426,93 +1379,9 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, return ret; } -bool is_vma_temporary_stack(struct vm_area_struct *vma) -{ - int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); - - if (!maybe_stack) - return false; - - if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) == - VM_STACK_INCOMPLETE_SETUP) - return true; - - return false; -} - -/** - * try_to_unmap_anon - unmap or unlock anonymous page using the object-based - * rmap method - * @page: the page to unmap/unlock - * @flags: action and flags - * - * Find all the mappings of a page using the mapping pointer and the vma chains - * contained in the anon_vma struct it points to. - * - * This function is only called from try_to_unmap/try_to_munlock for - * anonymous pages. - * When called from try_to_munlock(), the mmap_sem of the mm containing the vma - * where the page was found will be held for write. So, we won't recheck - * vm_flags for that VMA. That should be OK, because that vma shouldn't be - * 'LOCKED. - */ -static int try_to_unmap_anon(struct page *page, enum ttu_flags flags) -{ - struct anon_vma *anon_vma; - pgoff_t pgoff; - struct anon_vma_chain *avc; - int ret = SWAP_AGAIN; - - anon_vma = page_lock_anon_vma_read(page); - if (!anon_vma) - return ret; - - pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { - struct vm_area_struct *vma = avc->vma; - unsigned long address; - - /* - * During exec, a temporary VMA is setup and later moved. - * The VMA is moved under the anon_vma lock but not the - * page tables leading to a race where migration cannot - * find the migration ptes. Rather than increasing the - * locking requirements of exec(), migration skips - * temporary VMAs until after exec() completes. - */ - if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && - is_vma_temporary_stack(vma)) - continue; - - address = vma_address(page, vma); - ret = try_to_unmap_one(page, vma, address, flags); - if (ret != SWAP_AGAIN || !page_mapped(page)) - break; - } - - page_unlock_anon_vma_read(anon_vma); - return ret; -} - -/** - * try_to_unmap_file - unmap/unlock file page using the object-based rmap method - * @page: the page to unmap/unlock - * @flags: action and flags - * - * Find all the mappings of a page using the mapping pointer and the vma chains - * contained in the address_space struct it points to. - * - * This function is only called from try_to_unmap/try_to_munlock for - * object-based pages. - * When called from try_to_munlock(), the mmap_sem of the mm containing the vma - * where the page was found will be held for write. So, we won't recheck - * vm_flags for that VMA. That should be OK, because that vma shouldn't be - * 'LOCKED. - */ -static int try_to_unmap_file(struct page *page, enum ttu_flags flags) +static int try_to_unmap_nonlinear(struct page *page, + struct address_space *mapping, void *arg) { - struct address_space *mapping = page->mapping; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); struct vm_area_struct *vma; int ret = SWAP_AGAIN; unsigned long cursor; @@ -1520,30 +1389,9 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) unsigned long max_nl_size = 0; unsigned int mapcount; - if (PageHuge(page)) - pgoff = page->index << compound_order(page); - - mutex_lock(&mapping->i_mmap_mutex); - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { - unsigned long address = vma_address(page, vma); - ret = try_to_unmap_one(page, vma, address, flags); - if (ret != SWAP_AGAIN || !page_mapped(page)) - goto out; - } - - if (list_empty(&mapping->i_mmap_nonlinear)) - goto out; - - /* - * We don't bother to try to find the munlocked page in nonlinears. - * It's costly. Instead, later, page reclaim logic may call - * try_to_unmap(TTU_MUNLOCK) and recover PG_mlocked lazily. - */ - if (TTU_ACTION(flags) == TTU_MUNLOCK) - goto out; + list_for_each_entry(vma, + &mapping->i_mmap_nonlinear, shared.nonlinear) { - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, - shared.nonlinear) { cursor = (unsigned long) vma->vm_private_data; if (cursor > max_nl_cursor) max_nl_cursor = cursor; @@ -1553,8 +1401,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) } if (max_nl_size == 0) { /* all nonlinears locked or reserved ? */ - ret = SWAP_FAIL; - goto out; + return SWAP_FAIL; } /* @@ -1566,7 +1413,8 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) */ mapcount = page_mapcount(page); if (!mapcount) - goto out; + return ret; + cond_resched(); max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK; @@ -1574,10 +1422,11 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) max_nl_cursor = CLUSTER_SIZE; do { - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, - shared.nonlinear) { + list_for_each_entry(vma, + &mapping->i_mmap_nonlinear, shared.nonlinear) { + cursor = (unsigned long) vma->vm_private_data; - while ( cursor < max_nl_cursor && + while (cursor < max_nl_cursor && cursor < vma->vm_end - vma->vm_start) { if (try_to_unmap_cluster(cursor, &mapcount, vma, page) == SWAP_MLOCK) @@ -1585,7 +1434,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) cursor += CLUSTER_SIZE; vma->vm_private_data = (void *) cursor; if ((int)mapcount <= 0) - goto out; + return ret; } vma->vm_private_data = (void *) max_nl_cursor; } @@ -1600,11 +1449,34 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) */ list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.nonlinear) vma->vm_private_data = NULL; -out: - mutex_unlock(&mapping->i_mmap_mutex); + return ret; } +bool is_vma_temporary_stack(struct vm_area_struct *vma) +{ + int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); + + if (!maybe_stack) + return false; + + if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) == + VM_STACK_INCOMPLETE_SETUP) + return true; + + return false; +} + +static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) +{ + return is_vma_temporary_stack(vma); +} + +static int page_not_mapped(struct page *page) +{ + return !page_mapped(page); +}; + /** * try_to_unmap - try to remove all page table mappings to a page * @page: the page to get unmapped @@ -1622,16 +1494,29 @@ out: int try_to_unmap(struct page *page, enum ttu_flags flags) { int ret; + struct rmap_walk_control rwc = { + .rmap_one = try_to_unmap_one, + .arg = (void *)flags, + .done = page_not_mapped, + .file_nonlinear = try_to_unmap_nonlinear, + .anon_lock = page_lock_anon_vma_read, + }; - BUG_ON(!PageLocked(page)); - VM_BUG_ON(!PageHuge(page) && PageTransHuge(page)); + VM_BUG_ON_PAGE(!PageHuge(page) && PageTransHuge(page), page); + + /* + * During exec, a temporary VMA is setup and later moved. + * The VMA is moved under the anon_vma lock but not the + * page tables leading to a race where migration cannot + * find the migration ptes. Rather than increasing the + * locking requirements of exec(), migration skips + * temporary VMAs until after exec() completes. + */ + if (flags & TTU_MIGRATION && !PageKsm(page) && PageAnon(page)) + rwc.invalid_vma = invalid_migration_vma; + + ret = rmap_walk(page, &rwc); - if (unlikely(PageKsm(page))) - ret = try_to_unmap_ksm(page, flags); - else if (PageAnon(page)) - ret = try_to_unmap_anon(page, flags); - else - ret = try_to_unmap_file(page, flags); if (ret != SWAP_MLOCK && !page_mapped(page)) ret = SWAP_SUCCESS; return ret; @@ -1654,14 +1539,25 @@ int try_to_unmap(struct page *page, enum ttu_flags flags) */ int try_to_munlock(struct page *page) { - VM_BUG_ON(!PageLocked(page) || PageLRU(page)); + int ret; + struct rmap_walk_control rwc = { + .rmap_one = try_to_unmap_one, + .arg = (void *)TTU_MUNLOCK, + .done = page_not_mapped, + /* + * We don't bother to try to find the munlocked page in + * nonlinears. It's costly. Instead, later, page reclaim logic + * may call try_to_unmap() and recover PG_mlocked lazily. + */ + .file_nonlinear = NULL, + .anon_lock = page_lock_anon_vma_read, - if (unlikely(PageKsm(page))) - return try_to_unmap_ksm(page, TTU_MUNLOCK); - else if (PageAnon(page)) - return try_to_unmap_anon(page, TTU_MUNLOCK); - else - return try_to_unmap_file(page, TTU_MUNLOCK); + }; + + VM_BUG_ON_PAGE(!PageLocked(page) || PageLRU(page), page); + + ret = rmap_walk(page, &rwc); + return ret; } void __put_anon_vma(struct anon_vma *anon_vma) @@ -1674,18 +1570,13 @@ void __put_anon_vma(struct anon_vma *anon_vma) anon_vma_free(anon_vma); } -#ifdef CONFIG_MIGRATION -/* - * rmap_walk() and its helpers rmap_walk_anon() and rmap_walk_file(): - * Called by migrate.c to remove migration ptes, but might be used more later. - */ -static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *, - struct vm_area_struct *, unsigned long, void *), void *arg) +static struct anon_vma *rmap_walk_anon_lock(struct page *page, + struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - struct anon_vma_chain *avc; - int ret = SWAP_AGAIN; + + if (rwc->anon_lock) + return rwc->anon_lock(page); /* * Note: remove_migration_ptes() cannot use page_lock_anon_vma_read() @@ -1695,58 +1586,120 @@ static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *, */ anon_vma = page_anon_vma(page); if (!anon_vma) - return ret; + return NULL; + anon_vma_lock_read(anon_vma); + return anon_vma; +} + +/* + * rmap_walk_anon - do something to anonymous page using the object-based + * rmap method + * @page: the page to be handled + * @rwc: control variable according to each walk type + * + * Find all the mappings of a page using the mapping pointer and the vma chains + * contained in the anon_vma struct it points to. + * + * When called from try_to_munlock(), the mmap_sem of the mm containing the vma + * where the page was found will be held for write. So, we won't recheck + * vm_flags for that VMA. That should be OK, because that vma shouldn't be + * LOCKED. + */ +static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc) +{ + struct anon_vma *anon_vma; + pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + struct anon_vma_chain *avc; + int ret = SWAP_AGAIN; + + anon_vma = rmap_walk_anon_lock(page, rwc); + if (!anon_vma) + return ret; + anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); - ret = rmap_one(page, vma, address, arg); + + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) + continue; + + ret = rwc->rmap_one(page, vma, address, rwc->arg); if (ret != SWAP_AGAIN) break; + if (rwc->done && rwc->done(page)) + break; } anon_vma_unlock_read(anon_vma); return ret; } -static int rmap_walk_file(struct page *page, int (*rmap_one)(struct page *, - struct vm_area_struct *, unsigned long, void *), void *arg) +/* + * rmap_walk_file - do something to file page using the object-based rmap method + * @page: the page to be handled + * @rwc: control variable according to each walk type + * + * Find all the mappings of a page using the mapping pointer and the vma chains + * contained in the address_space struct it points to. + * + * When called from try_to_munlock(), the mmap_sem of the mm containing the vma + * where the page was found will be held for write. So, we won't recheck + * vm_flags for that VMA. That should be OK, because that vma shouldn't be + * LOCKED. + */ +static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) { struct address_space *mapping = page->mapping; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff_t pgoff = page->index << compound_order(page); struct vm_area_struct *vma; int ret = SWAP_AGAIN; + /* + * The page lock not only makes sure that page->mapping cannot + * suddenly be NULLified by truncation, it makes sure that the + * structure at mapping cannot be freed and reused yet, + * so we can safely take mapping->i_mmap_mutex. + */ + VM_BUG_ON(!PageLocked(page)); + if (!mapping) return ret; mutex_lock(&mapping->i_mmap_mutex); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { unsigned long address = vma_address(page, vma); - ret = rmap_one(page, vma, address, arg); + + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) + continue; + + ret = rwc->rmap_one(page, vma, address, rwc->arg); if (ret != SWAP_AGAIN) - break; + goto done; + if (rwc->done && rwc->done(page)) + goto done; } - /* - * No nonlinear handling: being always shared, nonlinear vmas - * never contain migration ptes. Decide what to do about this - * limitation to linear when we need rmap_walk() on nonlinear. - */ + + if (!rwc->file_nonlinear) + goto done; + + if (list_empty(&mapping->i_mmap_nonlinear)) + goto done; + + ret = rwc->file_nonlinear(page, mapping, rwc->arg); + +done: mutex_unlock(&mapping->i_mmap_mutex); return ret; } -int rmap_walk(struct page *page, int (*rmap_one)(struct page *, - struct vm_area_struct *, unsigned long, void *), void *arg) +int rmap_walk(struct page *page, struct rmap_walk_control *rwc) { - VM_BUG_ON(!PageLocked(page)); - if (unlikely(PageKsm(page))) - return rmap_walk_ksm(page, rmap_one, arg); + return rmap_walk_ksm(page, rwc); else if (PageAnon(page)) - return rmap_walk_anon(page, rmap_one, arg); + return rmap_walk_anon(page, rwc); else - return rmap_walk_file(page, rmap_one, arg); + return rmap_walk_file(page, rwc); } -#endif /* CONFIG_MIGRATION */ #ifdef CONFIG_HUGETLB_PAGE /* diff --git a/mm/shmem.c b/mm/shmem.c index 902a14842b74..70273f8df586 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -45,7 +45,7 @@ static struct vfsmount *shm_mnt; #include <linux/xattr.h> #include <linux/exportfs.h> #include <linux/posix_acl.h> -#include <linux/generic_acl.h> +#include <linux/posix_acl_xattr.h> #include <linux/mman.h> #include <linux/string.h> #include <linux/slab.h> @@ -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; } @@ -285,8 +283,8 @@ static int shmem_add_to_page_cache(struct page *page, { int error; - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(!PageSwapBacked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageSwapBacked(page), page); page_cache_get(page); page->mapping = mapping; @@ -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(); @@ -491,13 +425,13 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, continue; if (!unfalloc || !PageUptodate(page)) { if (page->mapping == mapping) { - VM_BUG_ON(PageWriteback(page)); + VM_BUG_ON_PAGE(PageWriteback(page), page); truncate_inode_page(mapping, page); } } 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; } @@ -568,13 +503,13 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, lock_page(page); if (!unfalloc || !PageUptodate(page)) { if (page->mapping == mapping) { - VM_BUG_ON(PageWriteback(page)); + VM_BUG_ON_PAGE(PageWriteback(page), page); truncate_inode_page(mapping, page); } } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; @@ -620,10 +555,8 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) } setattr_copy(inode, attr); -#ifdef CONFIG_TMPFS_POSIX_ACL if (attr->ia_valid & ATTR_MODE) - error = generic_acl_chmod(inode); -#endif + error = posix_acl_chmod(inode, inode->i_mode); return error; } @@ -750,7 +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 */ @@ -1082,7 +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; @@ -1147,7 +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, @@ -1201,7 +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; @@ -1419,6 +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; @@ -1731,7 +1669,7 @@ 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) @@ -1758,7 +1696,7 @@ 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(); @@ -1937,22 +1875,14 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE); if (inode) { -#ifdef CONFIG_TMPFS_POSIX_ACL - error = generic_acl_init(inode, dir); - if (error) { - iput(inode); - return error; - } -#endif + error = simple_acl_create(dir, inode); + if (error) + goto out_iput; error = security_inode_init_security(inode, dir, &dentry->d_name, shmem_initxattrs, NULL); - if (error) { - if (error != -EOPNOTSUPP) { - iput(inode); - return error; - } - } + if (error && error != -EOPNOTSUPP) + goto out_iput; error = 0; dir->i_size += BOGO_DIRENT_SIZE; @@ -1961,6 +1891,9 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) dget(dentry); /* Extra count - pin the dentry in core */ } return error; +out_iput: + iput(inode); + return error; } static int @@ -1974,24 +1907,17 @@ shmem_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) error = security_inode_init_security(inode, dir, NULL, shmem_initxattrs, NULL); - if (error) { - if (error != -EOPNOTSUPP) { - iput(inode); - return error; - } - } -#ifdef CONFIG_TMPFS_POSIX_ACL - error = generic_acl_init(inode, dir); - if (error) { - iput(inode); - return error; - } -#else - error = 0; -#endif + if (error && error != -EOPNOTSUPP) + goto out_iput; + error = simple_acl_create(dir, inode); + if (error) + goto out_iput; d_tmpfile(dentry, inode); } return error; +out_iput: + iput(inode); + return error; } static int shmem_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) @@ -2223,8 +2149,8 @@ static int shmem_initxattrs(struct inode *inode, static const struct xattr_handler *shmem_xattr_handlers[] = { #ifdef CONFIG_TMPFS_POSIX_ACL - &generic_acl_access_handler, - &generic_acl_default_handler, + &posix_acl_access_xattr_handler, + &posix_acl_default_xattr_handler, #endif NULL }; @@ -2740,6 +2666,7 @@ static const struct inode_operations shmem_inode_operations = { .getxattr = shmem_getxattr, .listxattr = shmem_listxattr, .removexattr = shmem_removexattr, + .set_acl = simple_set_acl, #endif }; @@ -2764,6 +2691,7 @@ static const struct inode_operations shmem_dir_inode_operations = { #endif #ifdef CONFIG_TMPFS_POSIX_ACL .setattr = shmem_setattr, + .set_acl = simple_set_acl, #endif }; @@ -2776,6 +2704,7 @@ static const struct inode_operations shmem_special_inode_operations = { #endif #ifdef CONFIG_TMPFS_POSIX_ACL .setattr = shmem_setattr, + .set_acl = simple_set_acl, #endif }; @@ -2794,6 +2723,7 @@ 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, diff --git a/mm/slab.c b/mm/slab.c index eb043bf05f4c..3db4cb06e32e 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1946,7 +1946,7 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep, /** * slab_destroy - destroy and release all objects in a slab * @cachep: cache pointer being destroyed - * @slabp: slab pointer being destroyed + * @page: page pointer being destroyed * * Destroy all the objs in a slab, and release the mem back to the system. * Before calling the slab must have been unlinked from the cache. The @@ -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; diff --git a/mm/slab.h b/mm/slab.h index 0859c4241ba1..3045316b7c9d 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -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)) @@ -160,12 +153,36 @@ static inline const char *cache_name(struct kmem_cache *s) return s->name; } +/* + * Note, we protect with RCU only the memcg_caches array, not per-memcg caches. + * That said the caller must assure the memcg's cache won't go away. Since once + * created a memcg's cache is destroyed only along with the root cache, it is + * true if we are going to allocate from the cache or hold a reference to the + * root cache by other means. Otherwise, we should hold either the slab_mutex + * or the memcg's slab_caches_mutex while calling this function and accessing + * the returned value. + */ static inline struct kmem_cache * cache_from_memcg_idx(struct kmem_cache *s, int idx) { + struct kmem_cache *cachep; + struct memcg_cache_params *params; + if (!s->memcg_params) return NULL; - return s->memcg_params->memcg_caches[idx]; + + rcu_read_lock(); + params = rcu_dereference(s->memcg_params); + cachep = params->memcg_caches[idx]; + rcu_read_unlock(); + + /* + * Make sure we will access the up-to-date value. The code updating + * memcg_caches issues a write barrier to match this (see + * memcg_register_cache()). + */ + smp_read_barrier_depends(); + return cachep; } static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) @@ -180,12 +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 0b7bb399b0e4..f3cfccf76dda 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. @@ -164,20 +196,20 @@ 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; - int err = 0; + struct kmem_cache *s; + char *cache_name; + int err; get_online_cpus(); mutex_lock(&slab_mutex); - if (!kmem_cache_sanity_check(memcg, name, size) == 0) - goto out_locked; + err = kmem_cache_sanity_check(name, size); + if (err) + goto out_unlock; /* * Some allocators will constraint the set of valid flags to a subset @@ -187,47 +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_locked; - - s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL); - if (s) { - s->object_size = s->size = size; - s->align = calculate_alignment(flags, align, size); - s->ctor = ctor; - - if (memcg_register_cache(memcg, s, parent_cache)) { - kmem_cache_free(kmem_cache, s); - err = -ENOMEM; - goto out_locked; - } + goto out_unlock; - s->name = kstrdup(name, GFP_KERNEL); - if (!s->name) { - kmem_cache_free(kmem_cache, s); - err = -ENOMEM; - goto out_locked; - } - - err = __kmem_cache_create(s, flags); - if (!err) { - s->refcount = 1; - list_add(&s->list, &slab_caches); - memcg_cache_list_add(memcg, s); - } else { - kfree(s->name); - kmem_cache_free(kmem_cache, s); - } - } else + cache_name = kstrdup(name, GFP_KERNEL); + if (!cache_name) { err = -ENOMEM; + goto out_unlock; + } -out_locked: + 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) { - if (flags & SLAB_PANIC) panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n", name, err); @@ -236,50 +250,115 @@ out_locked: name, err); dump_stack(); } - return NULL; } - return s; } +EXPORT_SYMBOL(kmem_cache_create); -struct kmem_cache * -kmem_cache_create(const char *name, size_t size, size_t align, - unsigned long flags, void (*ctor)(void *)) +#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) { - return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor, NULL); + 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(); } -EXPORT_SYMBOL(kmem_cache_create); -void kmem_cache_destroy(struct kmem_cache *s) +static int kmem_cache_destroy_memcg_children(struct kmem_cache *s) { - /* Destroy all the children caches if we aren't a memcg cache */ - kmem_cache_destroy_memcg_children(s); + 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; +} +#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) +{ get_online_cpus(); mutex_lock(&slab_mutex); + s->refcount--; - if (!s->refcount) { - list_del(&s->list); - - if (!__kmem_cache_shutdown(s)) { - mutex_unlock(&slab_mutex); - if (s->flags & SLAB_DESTROY_BY_RCU) - rcu_barrier(); - - memcg_release_cache(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); diff --git a/mm/slub.c b/mm/slub.c index 545a170ebf9f..f620bbf4054a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -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 } @@ -355,6 +359,21 @@ static __always_inline void slab_unlock(struct page *page) __bit_spin_unlock(PG_locked, &page->flags); } +static inline void set_page_slub_counters(struct page *page, unsigned long counters_new) +{ + struct page tmp; + tmp.counters = counters_new; + /* + * page->counters can cover frozen/inuse/objects as well + * as page->_count. If we assign to ->counters directly + * we run the risk of losing updates to page->_count, so + * be careful and only assign to the fields we need. + */ + page->frozen = tmp.frozen; + page->inuse = tmp.inuse; + page->objects = tmp.objects; +} + /* Interrupts must be disabled (for the fallback code to work right) */ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page, void *freelist_old, unsigned long counters_old, @@ -376,7 +395,7 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page if (page->freelist == freelist_old && page->counters == counters_old) { page->freelist = freelist_new; - page->counters = counters_new; + set_page_slub_counters(page, counters_new); slab_unlock(page); return 1; } @@ -415,7 +434,7 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, if (page->freelist == freelist_old && page->counters == counters_old) { page->freelist = freelist_new; - page->counters = counters_new; + set_page_slub_counters(page, counters_new); slab_unlock(page); local_irq_restore(flags); return 1; @@ -985,8 +1004,6 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) /* * Tracking of fully allocated slabs for debugging purposes. - * - * list_lock must be held. */ static void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) @@ -994,17 +1011,16 @@ static void add_full(struct kmem_cache *s, if (!(s->flags & SLAB_STORE_USER)) return; + lockdep_assert_held(&n->list_lock); list_add(&page->lru, &n->full); } -/* - * list_lock must be held. - */ -static void remove_full(struct kmem_cache *s, struct page *page) +static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) { if (!(s->flags & SLAB_STORE_USER)) return; + lockdep_assert_held(&n->list_lock); list_del(&page->lru); } @@ -1250,7 +1266,8 @@ static inline int check_object(struct kmem_cache *s, struct page *page, void *object, u8 val) { return 1; } static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) {} -static inline void remove_full(struct kmem_cache *s, struct page *page) {} +static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, + struct page *page) {} static inline unsigned long kmem_cache_flags(unsigned long object_size, unsigned long flags, const char *name, void (*ctor)(void *)) @@ -1504,11 +1521,9 @@ static void discard_slab(struct kmem_cache *s, struct page *page) /* * Management of partially allocated slabs. - * - * list_lock must be held. */ -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) { n->nr_partial++; if (tail == DEACTIVATE_TO_TAIL) @@ -1517,23 +1532,32 @@ static inline void add_partial(struct kmem_cache_node *n, list_add(&page->lru, &n->partial); } -/* - * list_lock must be held. - */ -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. * * Returns a list of objects or NULL if it fails. - * - * Must hold list_lock since we modify the partial list. */ static inline void *acquire_slab(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page, @@ -1543,6 +1567,8 @@ static inline void *acquire_slab(struct kmem_cache *s, unsigned long counters; struct page new; + lockdep_assert_held(&n->list_lock); + /* * Zap the freelist and set the frozen bit. * The old freelist is the list of objects for the @@ -1662,8 +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; @@ -1674,19 +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; } @@ -1887,7 +1911,7 @@ redo: else if (l == M_FULL) - remove_full(s, page); + remove_full(s, n, page); if (m == M_PARTIAL) { @@ -2541,7 +2565,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, new.inuse--; if ((!new.inuse || !prior) && !was_frozen) { - if (kmem_cache_has_cpu_partial(s) && !prior) + if (kmem_cache_has_cpu_partial(s) && !prior) { /* * Slab was on no list before and will be @@ -2551,7 +2575,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, */ new.frozen = 1; - else { /* Needs to be taken off a list */ + } else { /* Needs to be taken off a list */ n = get_node(s, page_to_nid(page)); /* @@ -2600,7 +2624,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, */ if (!kmem_cache_has_cpu_partial(s) && unlikely(!prior)) { if (kmem_cache_debug(s)) - remove_full(s, page); + remove_full(s, n, page); add_partial(n, page, DEACTIVATE_TO_TAIL); stat(s, FREE_ADD_PARTIAL); } @@ -2614,9 +2638,10 @@ slab_empty: */ remove_partial(n, page); stat(s, FREE_REMOVE_PARTIAL); - } else + } else { /* Slab must be on the full list */ - remove_full(s, page); + remove_full(s, n, page); + } spin_unlock_irqrestore(&n->list_lock, flags); stat(s, FREE_SLAB); @@ -2890,7 +2915,11 @@ static void early_kmem_cache_node_alloc(int node) init_kmem_cache_node(n); inc_slabs_node(kmem_cache_node, node, page->objects); - add_partial(n, page, DEACTIVATE_TO_HEAD); + /* + * No locks need to be taken here as it has just been + * initialized and there is no concurrent access. + */ + __add_partial(n, page, DEACTIVATE_TO_HEAD); } static void free_kmem_cache_nodes(struct kmem_cache *s) @@ -3176,7 +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, @@ -3212,8 +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 @@ -3659,6 +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; @@ -3671,9 +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; @@ -3696,7 +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 @@ -3707,23 +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. @@ -3731,6 +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; @@ -3753,10 +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); @@ -4299,7 +4338,13 @@ static ssize_t show_slab_objects(struct kmem_cache *s, page = ACCESS_ONCE(c->partial); if (page) { - x = page->pobjects; + node = page_to_nid(page); + if (flags & SO_TOTAL) + WARN_ON_ONCE(1); + else if (flags & SO_OBJECTS) + WARN_ON_ONCE(1); + else + x = page->pages; total += x; nodes[node] += x; } @@ -5097,6 +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: @@ -5162,26 +5216,39 @@ static int sysfs_slab_add(struct kmem_cache *s) name = create_unique_id(s); } - s->kobj.kset = slab_kset; - err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, name); - if (err) { - kobject_put(&s->kobj); - return err; - } + s->kobj.kset = cache_kset(s); + err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name); + 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) @@ -5193,6 +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-vmemmap.c b/mm/sparse-vmemmap.c index 27eeab3be757..4cba9c2783a1 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -40,7 +40,8 @@ static void * __init_refok __earlyonly_bootmem_alloc(int node, unsigned long align, unsigned long goal) { - return __alloc_bootmem_node_high(NODE_DATA(node), size, align, goal); + return memblock_virt_alloc_try_nid(size, align, goal, + BOOTMEM_ALLOC_ACCESSIBLE, node); } static void *vmemmap_buf; @@ -226,7 +227,8 @@ void __init sparse_mem_maps_populate_node(struct page **map_map, if (vmemmap_buf_start) { /* need to free left buf */ - free_bootmem(__pa(vmemmap_buf), vmemmap_buf_end - vmemmap_buf); + memblock_free_early(__pa(vmemmap_buf), + vmemmap_buf_end - vmemmap_buf); vmemmap_buf = NULL; vmemmap_buf_end = NULL; } diff --git a/mm/sparse.c b/mm/sparse.c index 8cc7be0e9590..d1b48b691ac8 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> @@ -69,7 +71,7 @@ static struct mem_section noinline __init_refok *sparse_index_alloc(int nid) else section = kzalloc(array_size, GFP_KERNEL); } else { - section = alloc_bootmem_node(NODE_DATA(nid), array_size); + section = memblock_virt_alloc_node(array_size, nid); } return section; @@ -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 @@ -279,8 +281,9 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, limit = goal + (1UL << PA_SECTION_SHIFT); nid = early_pfn_to_nid(goal >> PAGE_SHIFT); again: - p = ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size, - SMP_CACHE_BYTES, goal, limit); + p = memblock_virt_alloc_try_nid_nopanic(size, + SMP_CACHE_BYTES, goal, limit, + nid); if (!p && limit) { limit = 0; goto again; @@ -331,7 +334,7 @@ static unsigned long * __init sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, unsigned long size) { - return alloc_bootmem_node_nopanic(pgdat, size); + return memblock_virt_alloc_node_nopanic(size, pgdat->node_id); } static void __init check_usemap_section_nr(int nid, unsigned long *usemap) @@ -376,8 +379,9 @@ struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid) return map; size = PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION); - map = __alloc_bootmem_node_high(NODE_DATA(nid), size, - PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); + map = memblock_virt_alloc_try_nid(size, + PAGE_SIZE, __pa(MAX_DMA_ADDRESS), + BOOTMEM_ALLOC_ACCESSIBLE, nid); return map; } void __init sparse_mem_maps_populate_node(struct page **map_map, @@ -401,8 +405,9 @@ void __init sparse_mem_maps_populate_node(struct page **map_map, } size = PAGE_ALIGN(size); - map = __alloc_bootmem_node_high(NODE_DATA(nodeid), size * map_count, - PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); + map = memblock_virt_alloc_try_nid(size * map_count, + PAGE_SIZE, __pa(MAX_DMA_ADDRESS), + BOOTMEM_ALLOC_ACCESSIBLE, nodeid); if (map) { for (pnum = pnum_begin; pnum < pnum_end; pnum++) { if (!present_section_nr(pnum)) @@ -458,7 +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) { } @@ -545,7 +550,7 @@ void __init sparse_init(void) * sparse_early_mem_map_alloc, so allocate usemap_map at first. */ size = sizeof(unsigned long *) * NR_MEM_SECTIONS; - usemap_map = alloc_bootmem(size); + usemap_map = memblock_virt_alloc(size, 0); if (!usemap_map) panic("can not allocate usemap_map\n"); alloc_usemap_and_memmap(sparse_early_usemaps_alloc_node, @@ -553,7 +558,7 @@ void __init sparse_init(void) #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER size2 = sizeof(struct page *) * NR_MEM_SECTIONS; - map_map = alloc_bootmem(size2); + map_map = memblock_virt_alloc(size2, 0); if (!map_map) panic("can not allocate map_map\n"); alloc_usemap_and_memmap(sparse_early_mem_maps_alloc_node, @@ -583,9 +588,9 @@ void __init sparse_init(void) vmemmap_populate_print_last(); #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER - free_bootmem(__pa(map_map), size2); + memblock_free_early(__pa(map_map), size2); #endif - free_bootmem(__pa(usemap_map), size); + memblock_free_early(__pa(usemap_map), size); } #ifdef CONFIG_MEMORY_HOTPLUG diff --git a/mm/swap.c b/mm/swap.c index 84b26aaabd03..9ce43ba4498b 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -31,7 +31,6 @@ #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> -#include <linux/hugetlb.h> #include "internal.h" @@ -58,7 +57,7 @@ static void __page_cache_release(struct page *page) spin_lock_irqsave(&zone->lru_lock, flags); lruvec = mem_cgroup_page_lruvec(page, zone); - VM_BUG_ON(!PageLRU(page)); + VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); spin_unlock_irqrestore(&zone->lru_lock, flags); @@ -82,118 +81,150 @@ static void __put_compound_page(struct page *page) static void put_compound_page(struct page *page) { - if (unlikely(PageTail(page))) { - /* __split_huge_page_refcount can run under us */ - struct page *page_head = compound_trans_head(page); - - if (likely(page != page_head && - get_page_unless_zero(page_head))) { - unsigned long flags; + struct page *page_head; + if (likely(!PageTail(page))) { + if (put_page_testzero(page)) { /* - * THP can not break up slab pages so avoid taking - * compound_lock(). Slab performs non-atomic bit ops - * on page->flags for better performance. In particular - * slab_unlock() in slub used to be a hot path. It is - * still hot on arches that do not support - * this_cpu_cmpxchg_double(). + * By the time all refcounts have been released + * split_huge_page cannot run anymore from under us. */ - if (PageSlab(page_head) || PageHeadHuge(page_head)) { - if (likely(PageTail(page))) { - /* - * __split_huge_page_refcount - * cannot race here. - */ - VM_BUG_ON(!PageHead(page_head)); - atomic_dec(&page->_mapcount); - if (put_page_testzero(page_head)) - VM_BUG_ON(1); - if (put_page_testzero(page_head)) - __put_compound_page(page_head); - return; - } else - /* - * __split_huge_page_refcount - * run before us, "page" was a - * THP tail. The split - * page_head has been freed - * and reallocated as slab or - * hugetlbfs page of smaller - * order (only possible if - * reallocated as slab on - * x86). - */ - goto skip_lock; - } + if (PageHead(page)) + __put_compound_page(page); + else + __put_single_page(page); + } + return; + } + + /* __split_huge_page_refcount can run under us */ + page_head = compound_head(page); + + /* + * THP can not break up slab pages so avoid taking + * compound_lock() and skip the tail page refcounting (in + * _mapcount) too. Slab performs non-atomic bit ops on + * page->flags for better performance. In particular + * slab_unlock() in slub used to be a hot path. It is still + * hot on arches that do not support + * this_cpu_cmpxchg_double(). + * + * If "page" is part of a slab or hugetlbfs page it cannot be + * splitted and the head page cannot change from under us. And + * if "page" is part of a THP page under splitting, if the + * head page pointed by the THP tail isn't a THP head anymore, + * we'll find PageTail clear after smp_rmb() and we'll treat + * it as a single page. + */ + if (!__compound_tail_refcounted(page_head)) { + /* + * If "page" is a THP tail, we must read the tail page + * flags after the head page flags. The + * split_huge_page side enforces write memory barriers + * between clearing PageTail and before the head page + * can be freed and reallocated. + */ + smp_rmb(); + if (likely(PageTail(page))) { /* - * page_head wasn't a dangling pointer but it - * may not be a head page anymore by the time - * we obtain the lock. That is ok as long as it - * can't be freed from under us. + * __split_huge_page_refcount cannot race + * here. */ - flags = compound_lock_irqsave(page_head); - if (unlikely(!PageTail(page))) { - /* __split_huge_page_refcount run before us */ - compound_unlock_irqrestore(page_head, flags); -skip_lock: - if (put_page_testzero(page_head)) { - /* - * The head page may have been - * freed and reallocated as a - * compound page of smaller - * order and then freed again. - * All we know is that it - * cannot have become: a THP - * page, a compound page of - * higher order, a tail page. - * That is because we still - * hold the refcount of the - * split THP tail and - * page_head was the THP head - * before the split. - */ - if (PageHead(page_head)) - __put_compound_page(page_head); - else - __put_single_page(page_head); - } -out_put_single: - if (put_page_testzero(page)) - __put_single_page(page); - return; + VM_BUG_ON_PAGE(!PageHead(page_head), page_head); + VM_BUG_ON_PAGE(page_mapcount(page) != 0, page); + if (put_page_testzero(page_head)) { + /* + * If this is the tail of a slab + * compound page, the tail pin must + * not be the last reference held on + * the page, because the PG_slab + * cannot be cleared before all tail + * pins (which skips the _mapcount + * tail refcounting) have been + * released. For hugetlbfs the tail + * pin may be the last reference on + * the page instead, because + * PageHeadHuge will not go away until + * the compound page enters the buddy + * allocator. + */ + VM_BUG_ON_PAGE(PageSlab(page_head), page_head); + __put_compound_page(page_head); } - VM_BUG_ON(page_head != page->first_page); + return; + } else /* - * We can release the refcount taken by - * get_page_unless_zero() now that - * __split_huge_page_refcount() is blocked on - * the compound_lock. + * __split_huge_page_refcount run before us, + * "page" was a THP tail. The split page_head + * has been freed and reallocated as slab or + * hugetlbfs page of smaller order (only + * possible if reallocated as slab on x86). */ - if (put_page_testzero(page_head)) - VM_BUG_ON(1); - /* __split_huge_page_refcount will wait now */ - VM_BUG_ON(page_mapcount(page) <= 0); - atomic_dec(&page->_mapcount); - VM_BUG_ON(atomic_read(&page_head->_count) <= 0); - VM_BUG_ON(atomic_read(&page->_count) != 0); - compound_unlock_irqrestore(page_head, flags); + goto out_put_single; + } + if (likely(page != page_head && get_page_unless_zero(page_head))) { + unsigned long flags; + + /* + * page_head wasn't a dangling pointer but it may not + * be a head page anymore by the time we obtain the + * lock. That is ok as long as it can't be freed from + * under us. + */ + flags = compound_lock_irqsave(page_head); + if (unlikely(!PageTail(page))) { + /* __split_huge_page_refcount run before us */ + compound_unlock_irqrestore(page_head, flags); if (put_page_testzero(page_head)) { + /* + * The head page may have been freed + * and reallocated as a compound page + * of smaller order and then freed + * again. All we know is that it + * cannot have become: a THP page, a + * compound page of higher order, a + * tail page. That is because we + * still hold the refcount of the + * split THP tail and page_head was + * the THP head before the split. + */ if (PageHead(page_head)) __put_compound_page(page_head); else __put_single_page(page_head); } - } else { - /* page_head is a dangling pointer */ - VM_BUG_ON(PageTail(page)); - goto out_put_single; +out_put_single: + if (put_page_testzero(page)) + __put_single_page(page); + return; } - } else if (put_page_testzero(page)) { - if (PageHead(page)) - __put_compound_page(page); - else - __put_single_page(page); + VM_BUG_ON_PAGE(page_head != page->first_page, page); + /* + * We can release the refcount taken by + * get_page_unless_zero() now that + * __split_huge_page_refcount() is blocked on the + * compound_lock. + */ + if (put_page_testzero(page_head)) + VM_BUG_ON_PAGE(1, page_head); + /* __split_huge_page_refcount will wait now */ + VM_BUG_ON_PAGE(page_mapcount(page) <= 0, page); + atomic_dec(&page->_mapcount); + VM_BUG_ON_PAGE(atomic_read(&page_head->_count) <= 0, page_head); + VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page); + compound_unlock_irqrestore(page_head, flags); + + if (put_page_testzero(page_head)) { + if (PageHead(page_head)) + __put_compound_page(page_head); + else + __put_single_page(page_head); + } + } else { + /* page_head is a dangling pointer */ + VM_BUG_ON_PAGE(PageTail(page), page); + goto out_put_single; } } @@ -221,36 +252,37 @@ bool __get_page_tail(struct page *page) * split_huge_page(). */ unsigned long flags; - bool got = false; - struct page *page_head = compound_trans_head(page); + bool got; + struct page *page_head = compound_head(page); - if (likely(page != page_head && get_page_unless_zero(page_head))) { - /* Ref to put_compound_page() comment. */ - if (PageSlab(page_head) || PageHeadHuge(page_head)) { - if (likely(PageTail(page))) { - /* - * This is a hugetlbfs page or a slab - * page. __split_huge_page_refcount - * cannot race here. - */ - VM_BUG_ON(!PageHead(page_head)); - __get_page_tail_foll(page, false); - return true; - } else { - /* - * __split_huge_page_refcount run - * before us, "page" was a THP - * tail. The split page_head has been - * freed and reallocated as slab or - * hugetlbfs page of smaller order - * (only possible if reallocated as - * slab on x86). - */ - put_page(page_head); - return false; - } + /* Ref to put_compound_page() comment. */ + if (!__compound_tail_refcounted(page_head)) { + smp_rmb(); + if (likely(PageTail(page))) { + /* + * This is a hugetlbfs page or a slab + * page. __split_huge_page_refcount + * cannot race here. + */ + VM_BUG_ON_PAGE(!PageHead(page_head), page_head); + __get_page_tail_foll(page, true); + return true; + } else { + /* + * __split_huge_page_refcount run + * before us, "page" was a THP + * tail. The split page_head has been + * freed and reallocated as slab or + * hugetlbfs page of smaller order + * (only possible if reallocated as + * slab on x86). + */ + return false; } + } + got = false; + if (likely(page != page_head && get_page_unless_zero(page_head))) { /* * page_head wasn't a dangling pointer but it * may not be a head page anymore by the time @@ -542,6 +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); } @@ -572,8 +606,8 @@ EXPORT_SYMBOL(__lru_cache_add); */ void lru_cache_add(struct page *page) { - VM_BUG_ON(PageActive(page) && PageUnevictable(page)); - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); + VM_BUG_ON_PAGE(PageLRU(page), page); __lru_cache_add(page); } @@ -814,7 +848,7 @@ void release_pages(struct page **pages, int nr, int cold) } lruvec = mem_cgroup_page_lruvec(page, zone); - VM_BUG_ON(!PageLRU(page)); + VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); } @@ -856,9 +890,9 @@ void lru_add_page_tail(struct page *page, struct page *page_tail, { const int file = 0; - VM_BUG_ON(!PageHead(page)); - VM_BUG_ON(PageCompound(page_tail)); - VM_BUG_ON(PageLRU(page_tail)); + VM_BUG_ON_PAGE(!PageHead(page), page); + VM_BUG_ON_PAGE(PageCompound(page_tail), page); + VM_BUG_ON_PAGE(PageLRU(page_tail), page); VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&lruvec_zone(lruvec)->lru_lock)); @@ -897,7 +931,7 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec, int active = PageActive(page); enum lru_list lru = page_lru(page); - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); SetPageLRU(page); add_page_to_lru_list(page, lruvec, lru); @@ -916,6 +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 e6f15f8ca2af..e76ace30d436 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()); @@ -83,9 +85,9 @@ int __add_to_swap_cache(struct page *page, swp_entry_t entry) int error; struct address_space *address_space; - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(PageSwapCache(page)); - VM_BUG_ON(!PageSwapBacked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageSwapCache(page), page); + VM_BUG_ON_PAGE(!PageSwapBacked(page), page); page_cache_get(page); SetPageSwapCache(page); @@ -139,9 +141,9 @@ void __delete_from_swap_cache(struct page *page) swp_entry_t entry; struct address_space *address_space; - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(!PageSwapCache(page)); - VM_BUG_ON(PageWriteback(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageSwapCache(page), page); + VM_BUG_ON_PAGE(PageWriteback(page), page); entry.val = page_private(page); address_space = swap_address_space(entry); @@ -165,8 +167,8 @@ int add_to_swap(struct page *page, struct list_head *list) swp_entry_t entry; int err; - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(!PageUptodate(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageUptodate(page), page); entry = get_swap_page(); if (!entry.val) @@ -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 612a7c9795f6..4a7f7e6992b6 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -616,7 +616,7 @@ scan: } } offset = si->lowest_bit; - while (++offset < scan_base) { + while (offset < scan_base) { if (!si->swap_map[offset]) { spin_lock(&si->lock); goto checks; @@ -629,6 +629,7 @@ scan: cond_resched(); latency_ration = LATENCY_LIMIT; } + offset++; } spin_lock(&si->lock); @@ -906,7 +907,7 @@ int reuse_swap_page(struct page *page) { int count; - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); if (unlikely(PageKsm(page))) return 0; count = page_mapcount(page); @@ -926,7 +927,7 @@ int reuse_swap_page(struct page *page) */ int try_to_free_swap(struct page *page) { - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); if (!PageSwapCache(page)) return 0; @@ -1922,7 +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); @@ -1948,6 +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); @@ -2714,7 +2724,7 @@ struct swap_info_struct *page_swap_info(struct page *page) */ struct address_space *__page_file_mapping(struct page *page) { - VM_BUG_ON(!PageSwapCache(page)); + VM_BUG_ON_PAGE(!PageSwapCache(page), page); return page_swap_info(page)->swap_file->f_mapping; } EXPORT_SYMBOL_GPL(__page_file_mapping); @@ -2722,7 +2732,7 @@ EXPORT_SYMBOL_GPL(__page_file_mapping); pgoff_t __page_file_index(struct page *page) { swp_entry_t swap = { .val = page_private(page) }; - VM_BUG_ON(!PageSwapCache(page)); + VM_BUG_ON_PAGE(!PageSwapCache(page), page); return swp_offset(swap); } EXPORT_SYMBOL_GPL(__page_file_index); diff --git a/mm/truncate.c b/mm/truncate.c index 353b683afd6e..e5cc39ab0751 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(); diff --git a/mm/util.c b/mm/util.c index 43b44199c5e3..f380af7ea779 100644 --- a/mm/util.c +++ b/mm/util.c @@ -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; @@ -404,13 +405,45 @@ struct address_space *page_mapping(struct page *page) return mapping; } +int overcommit_ratio_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + if (ret == 0 && write) + sysctl_overcommit_kbytes = 0; + return ret; +} + +int overcommit_kbytes_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); + if (ret == 0 && write) + sysctl_overcommit_ratio = 0; + return ret; +} + /* * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used */ unsigned long vm_commit_limit(void) { - return ((totalram_pages - hugetlb_total_pages()) - * sysctl_overcommit_ratio / 100) + total_swap_pages; + unsigned long allowed; + + if (sysctl_overcommit_kbytes) + allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10); + else + allowed = ((totalram_pages - hugetlb_total_pages()) + * sysctl_overcommit_ratio / 100); + allowed += total_swap_pages; + + return allowed; } /** diff --git a/mm/vmacache.c b/mm/vmacache.c new file mode 100644 index 000000000000..d4224b397c0e --- /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 0fdf96803c5b..bf233b283319 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 e0f62837c3f4..d4042e75f7c7 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> @@ -278,8 +279,7 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) /** * vmpressure_register_event() - Bind vmpressure notifications to an eventfd - * @css: css that is interested in vmpressure notifications - * @cft: cgroup control files handle + * @memcg: memcg that is interested in vmpressure notifications * @eventfd: eventfd context to link notifications with * @args: event arguments (used to set up a pressure level threshold) * @@ -289,15 +289,12 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) * threshold (one of vmpressure_str_levels, i.e. "low", "medium", or * "critical"). * - * This function should not be used directly, just pass it to (struct - * cftype).register_event, and then cgroup core will handle everything by - * itself. + * To be used as memcg event method. */ -int vmpressure_register_event(struct cgroup_subsys_state *css, - struct cftype *cft, struct eventfd_ctx *eventfd, - const char *args) +int vmpressure_register_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args) { - struct vmpressure *vmpr = css_to_vmpressure(css); + struct vmpressure *vmpr = memcg_to_vmpressure(memcg); struct vmpressure_event *ev; int level; @@ -325,23 +322,19 @@ int vmpressure_register_event(struct cgroup_subsys_state *css, /** * vmpressure_unregister_event() - Unbind eventfd from vmpressure - * @css: css handle - * @cft: cgroup control files handle + * @memcg: memcg handle * @eventfd: eventfd context that was used to link vmpressure with the @cg * * This function does internal manipulations to detach the @eventfd from * the vmpressure notifications, and then frees internal resources * associated with the @eventfd (but the @eventfd itself is not freed). * - * This function should not be used directly, just pass it to (struct - * cftype).unregister_event, and then cgroup core will handle everything - * by itself. + * To be used as memcg event method. */ -void vmpressure_unregister_event(struct cgroup_subsys_state *css, - struct cftype *cft, +void vmpressure_unregister_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd) { - struct vmpressure *vmpr = css_to_vmpressure(css); + struct vmpressure *vmpr = memcg_to_vmpressure(memcg); struct vmpressure_event *ev; mutex_lock(&vmpr->events_lock); diff --git a/mm/vmscan.c b/mm/vmscan.c index eea668d9cff6..9b6497eda806 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -147,7 +147,7 @@ static bool global_reclaim(struct scan_control *sc) } #endif -unsigned long zone_reclaimable_pages(struct zone *zone) +static unsigned long zone_reclaimable_pages(struct zone *zone) { int nr; @@ -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; } /* @@ -260,38 +260,55 @@ 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); - while (total_scan >= batch_size) { + /* + * Normally, we should not scan less than batch_size objects in one + * pass to avoid too frequent shrinker calls, but if the slab has less + * than batch_size objects in total and we are really tight on memory, + * we will try to reclaim all available objects, otherwise we can end + * up failing allocations although there are plenty of reclaimable + * objects spread over several slabs with usage less than the + * batch_size. + * + * 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 (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 >= freeable) { unsigned long ret; + unsigned long nr_to_scan = min(batch_size, total_scan); - shrinkctl->nr_to_scan = batch_size; + shrinkctl->nr_to_scan = nr_to_scan; ret = shrinker->scan_objects(shrinker, shrinkctl); if (ret == SHRINK_STOP) break; freed += ret; - count_vm_events(SLABS_SCANNED, batch_size); - total_scan -= batch_size; + count_vm_events(SLABS_SCANNED, nr_to_scan); + total_scan -= nr_to_scan; cond_resched(); } @@ -352,16 +369,17 @@ unsigned long shrink_slab(struct shrink_control *shrinkctl, } list_for_each_entry(shrinker, &shrinker_list, list) { - for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) { - if (!node_online(shrinkctl->nid)) - continue; - - if (!(shrinker->flags & SHRINKER_NUMA_AWARE) && - (shrinkctl->nid != 0)) - break; - + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) { + shrinkctl->nid = 0; freed += shrink_slab_node(shrinkctl, shrinker, - nr_pages_scanned, lru_pages); + nr_pages_scanned, lru_pages); + continue; + } + + for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) { + if (node_online(shrinkctl->nid)) + freed += shrink_slab_node(shrinkctl, shrinker, + nr_pages_scanned, lru_pages); } } @@ -505,7 +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)); @@ -551,10 +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); @@ -577,7 +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 @@ -603,7 +635,7 @@ void putback_lru_page(struct page *page) bool is_unevictable; int was_unevictable = PageUnevictable(page); - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); redo: ClearPageUnevictable(page); @@ -794,8 +826,8 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (!trylock_page(page)) goto keep; - VM_BUG_ON(PageActive(page)); - VM_BUG_ON(page_zone(page) != zone); + VM_BUG_ON_PAGE(PageActive(page), page); + VM_BUG_ON_PAGE(page_zone(page) != zone, page); sc->nr_scanned++; @@ -1047,7 +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; /* @@ -1079,14 +1111,14 @@ activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ if (PageSwapCache(page) && vm_swap_full()) try_to_free_swap(page); - VM_BUG_ON(PageActive(page)); + VM_BUG_ON_PAGE(PageActive(page), page); SetPageActive(page); pgactivate++; keep_locked: unlock_page(page); keep: list_add(&page->lru, &ret_pages); - VM_BUG_ON(PageLRU(page) || PageUnevictable(page)); + VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); } free_hot_cold_page_list(&free_pages, 1); @@ -1240,7 +1272,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, page = lru_to_page(src); prefetchw_prev_lru_page(page, src, flags); - VM_BUG_ON(!PageLRU(page)); + VM_BUG_ON_PAGE(!PageLRU(page), page); switch (__isolate_lru_page(page, mode)) { case 0: @@ -1295,7 +1327,7 @@ int isolate_lru_page(struct page *page) { int ret = -EBUSY; - VM_BUG_ON(!page_count(page)); + VM_BUG_ON_PAGE(!page_count(page), page); if (PageLRU(page)) { struct zone *zone = page_zone(page); @@ -1366,7 +1398,7 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) struct page *page = lru_to_page(page_list); int lru; - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); list_del(&page->lru); if (unlikely(!page_evictable(page))) { spin_unlock_irq(&zone->lru_lock); @@ -1586,7 +1618,7 @@ static void move_active_pages_to_lru(struct lruvec *lruvec, page = lru_to_page(list); lruvec = mem_cgroup_page_lruvec(page, zone); - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); SetPageLRU(page); nr_pages = hpage_nr_pages(page); @@ -1830,7 +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; @@ -1884,20 +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. */ @@ -2279,16 +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)) @@ -2300,6 +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 */ @@ -2313,7 +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; } @@ -2336,6 +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; } @@ -2376,13 +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; @@ -2397,32 +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; @@ -2584,9 +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. @@ -2600,7 +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); @@ -2667,9 +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 @@ -2684,7 +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); @@ -3297,27 +3314,6 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) wake_up_interruptible(&pgdat->kswapd_wait); } -/* - * The reclaimable count would be mostly accurate. - * The less reclaimable pages may be - * - mlocked pages, which will be moved to unevictable list when encountered - * - mapped pages, which may require several travels to be reclaimed - * - dirty pages, which is not "instantly" reclaimable - */ -unsigned long global_reclaimable_pages(void) -{ - int nr; - - nr = global_page_state(NR_ACTIVE_FILE) + - global_page_state(NR_INACTIVE_FILE); - - if (get_nr_swap_pages() > 0) - nr += global_page_state(NR_ACTIVE_ANON) + - global_page_state(NR_INACTIVE_ANON); - - return nr; -} - #ifdef CONFIG_HIBERNATION /* * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of @@ -3340,9 +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; @@ -3352,7 +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(); @@ -3701,7 +3694,7 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages) if (page_evictable(page)) { enum lru_list lru = page_lru_base_type(page); - VM_BUG_ON(PageActive(page)); + VM_BUG_ON_PAGE(PageActive(page), page); ClearPageUnevictable(page); del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE); add_page_to_lru_list(page, lruvec, lru); diff --git a/mm/vmstat.c b/mm/vmstat.c index 72496140ac08..302dd076b8bf 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 000000000000..f7216fa7da27 --- /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 new file mode 100644 index 000000000000..36b4591a7a2d --- /dev/null +++ b/mm/zsmalloc.c @@ -0,0 +1,1117 @@ +/* + * zsmalloc memory allocator + * + * Copyright (C) 2011 Nitin Gupta + * Copyright (C) 2012, 2013 Minchan Kim + * + * This code is released using a dual license strategy: BSD/GPL + * You can choose the license that better fits your requirements. + * + * Released under the terms of 3-clause BSD License + * Released under the terms of GNU General Public License Version 2.0 + */ + +/* + * This allocator is designed for use with zram. Thus, the allocator is + * supposed to work well under low memory conditions. In particular, it + * never attempts higher order page allocation which is very likely to + * fail under memory pressure. On the other hand, if we just use single + * (0-order) pages, it would suffer from very high fragmentation -- + * any object of size PAGE_SIZE/2 or larger would occupy an entire page. + * This was one of the major issues with its predecessor (xvmalloc). + * + * To overcome these issues, zsmalloc allocates a bunch of 0-order pages + * and links them together using various 'struct page' fields. These linked + * pages act as a single higher-order page i.e. an object can span 0-order + * page boundaries. The code refers to these linked pages as a single entity + * called zspage. + * + * For simplicity, zsmalloc can only allocate objects of size up to PAGE_SIZE + * since this satisfies the requirements of all its current users (in the + * worst case, page is incompressible and is thus stored "as-is" i.e. in + * uncompressed form). For allocation requests larger than this size, failure + * is returned (see zs_malloc). + * + * Additionally, zs_malloc() does not return a dereferenceable pointer. + * Instead, it returns an opaque handle (unsigned long) which encodes actual + * location of the allocated object. The reason for this indirection is that + * zsmalloc does not keep zspages permanently mapped since that would cause + * issues on 32-bit systems where the VA region for kernel space mappings + * is very small. So, before using the allocating memory, the object has to + * be mapped using zs_map_object() to get a usable pointer and subsequently + * unmapped using zs_unmap_object(). + * + * Following is how we use various fields and flags of underlying + * struct page(s) to form a zspage. + * + * Usage of struct page fields: + * page->first_page: points to the first component (0-order) page + * page->index (union with page->freelist): offset of the first object + * starting in this page. For the first page, this is + * always 0, so we use this field (aka freelist) to point + * to the first free object in zspage. + * page->lru: links together all component pages (except the first page) + * of a zspage + * + * For _first_ page only: + * + * page->private (union with page->first_page): refers to the + * component page after the first page + * page->freelist: points to the first free object in zspage. + * Free objects are linked together using in-place + * metadata. + * page->objects: maximum number of objects we can store in this + * zspage (class->zspage_order * PAGE_SIZE / class->size) + * page->lru: links together first pages of various zspages. + * Basically forming list of zspages in a fullness group. + * page->mapping: class index and fullness group of the zspage + * + * Usage of struct page flags: + * PG_private: identifies the first component page + * PG_private2: identifies the last component page + * + */ + +#ifdef CONFIG_ZSMALLOC_DEBUG +#define DEBUG +#endif + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/bitops.h> +#include <linux/errno.h> +#include <linux/highmem.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <asm/tlbflush.h> +#include <asm/pgtable.h> +#include <linux/cpumask.h> +#include <linux/cpu.h> +#include <linux/vmalloc.h> +#include <linux/hardirq.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/zsmalloc.h> + +/* + * This must be power of 2 and greater than of equal to sizeof(link_free). + * These two conditions ensure that any 'struct link_free' itself doesn't + * span more than 1 page which avoids complex case of mapping 2 pages simply + * to restore link_free pointer values. + */ +#define ZS_ALIGN 8 + +/* + * A single 'zspage' is composed of up to 2^N discontiguous 0-order (single) + * pages. ZS_MAX_ZSPAGE_ORDER defines upper limit on N. + */ +#define ZS_MAX_ZSPAGE_ORDER 2 +#define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER) + +/* + * Object location (<PFN>, <obj_idx>) is encoded as + * as single (unsigned long) handle value. + * + * Note that object index <obj_idx> is relative to system + * page <PFN> it is stored in, so for each sub-page belonging + * to a zspage, obj_idx starts with 0. + * + * This is made more complicated by various memory models and PAE. + */ + +#ifndef MAX_PHYSMEM_BITS +#ifdef CONFIG_HIGHMEM64G +#define MAX_PHYSMEM_BITS 36 +#else /* !CONFIG_HIGHMEM64G */ +/* + * If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just + * be PAGE_SHIFT + */ +#define MAX_PHYSMEM_BITS BITS_PER_LONG +#endif +#endif +#define _PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) +#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS) +#define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1) + +#define MAX(a, b) ((a) >= (b) ? (a) : (b)) +/* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */ +#define ZS_MIN_ALLOC_SIZE \ + MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS)) +#define ZS_MAX_ALLOC_SIZE PAGE_SIZE + +/* + * On systems with 4K page size, this gives 254 size classes! There is a + * trader-off here: + * - Large number of size classes is potentially wasteful as free page are + * spread across these classes + * - Small number of size classes causes large internal fragmentation + * - Probably its better to use specific size classes (empirically + * determined). NOTE: all those class sizes must be set as multiple of + * ZS_ALIGN to make sure link_free itself never has to span 2 pages. + * + * ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN + * (reason above) + */ +#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> 8) +#define ZS_SIZE_CLASSES ((ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / \ + ZS_SIZE_CLASS_DELTA + 1) + +/* + * We do not maintain any list for completely empty or full pages + */ +enum fullness_group { + ZS_ALMOST_FULL, + ZS_ALMOST_EMPTY, + _ZS_NR_FULLNESS_GROUPS, + + ZS_EMPTY, + ZS_FULL +}; + +/* + * We assign a page to ZS_ALMOST_EMPTY fullness group when: + * n <= N / f, where + * n = number of allocated objects + * N = total number of objects zspage can store + * f = 1/fullness_threshold_frac + * + * Similarly, we assign zspage to: + * ZS_ALMOST_FULL when n > N / f + * ZS_EMPTY when n == 0 + * ZS_FULL when n == N + * + * (see: fix_fullness_group()) + */ +static const int fullness_threshold_frac = 4; + +struct size_class { + /* + * Size of objects stored in this class. Must be multiple + * of ZS_ALIGN. + */ + int size; + unsigned int index; + + /* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */ + int pages_per_zspage; + + spinlock_t lock; + + /* stats */ + u64 pages_allocated; + + struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS]; +}; + +/* + * Placed within free objects to form a singly linked list. + * For every zspage, first_page->freelist gives head of this list. + * + * This must be power of 2 and less than or equal to ZS_ALIGN + */ +struct link_free { + /* Handle of next free chunk (encodes <PFN, obj_idx>) */ + void *next; +}; + +struct zs_pool { + struct size_class size_class[ZS_SIZE_CLASSES]; + + gfp_t flags; /* allocation flags used when growing pool */ +}; + +/* + * A zspage's class index and fullness group + * are encoded in its (first)page->mapping + */ +#define CLASS_IDX_BITS 28 +#define FULLNESS_BITS 4 +#define CLASS_IDX_MASK ((1 << CLASS_IDX_BITS) - 1) +#define FULLNESS_MASK ((1 << FULLNESS_BITS) - 1) + +struct mapping_area { +#ifdef CONFIG_PGTABLE_MAPPING + struct vm_struct *vm; /* vm area for mapping object that span pages */ +#else + char *vm_buf; /* copy buffer for objects that span pages */ +#endif + char *vm_addr; /* address of kmap_atomic()'ed pages */ + enum zs_mapmode vm_mm; /* mapping mode */ +}; + + +/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ +static DEFINE_PER_CPU(struct mapping_area, zs_map_area); + +static int is_first_page(struct page *page) +{ + return PagePrivate(page); +} + +static int is_last_page(struct page *page) +{ + return PagePrivate2(page); +} + +static void get_zspage_mapping(struct page *page, unsigned int *class_idx, + enum fullness_group *fullness) +{ + unsigned long m; + BUG_ON(!is_first_page(page)); + + m = (unsigned long)page->mapping; + *fullness = m & FULLNESS_MASK; + *class_idx = (m >> FULLNESS_BITS) & CLASS_IDX_MASK; +} + +static void set_zspage_mapping(struct page *page, unsigned int class_idx, + enum fullness_group fullness) +{ + unsigned long m; + BUG_ON(!is_first_page(page)); + + m = ((class_idx & CLASS_IDX_MASK) << FULLNESS_BITS) | + (fullness & FULLNESS_MASK); + page->mapping = (struct address_space *)m; +} + +/* + * zsmalloc divides the pool into various size classes where each + * class maintains a list of zspages where each zspage is divided + * into equal sized chunks. Each allocation falls into one of these + * classes depending on its size. This function returns index of the + * size class which has chunk size big enough to hold the give size. + */ +static int get_size_class_index(int size) +{ + int idx = 0; + + if (likely(size > ZS_MIN_ALLOC_SIZE)) + idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE, + ZS_SIZE_CLASS_DELTA); + + return idx; +} + +/* + * For each size class, zspages are divided into different groups + * depending on how "full" they are. This was done so that we could + * easily find empty or nearly empty zspages when we try to shrink + * the pool (not yet implemented). This function returns fullness + * status of the given page. + */ +static enum fullness_group get_fullness_group(struct page *page) +{ + int inuse, max_objects; + enum fullness_group fg; + BUG_ON(!is_first_page(page)); + + inuse = page->inuse; + max_objects = page->objects; + + if (inuse == 0) + fg = ZS_EMPTY; + else if (inuse == max_objects) + fg = ZS_FULL; + else if (inuse <= max_objects / fullness_threshold_frac) + fg = ZS_ALMOST_EMPTY; + else + fg = ZS_ALMOST_FULL; + + return fg; +} + +/* + * Each size class maintains various freelists and zspages are assigned + * to one of these freelists based on the number of live objects they + * have. This functions inserts the given zspage into the freelist + * identified by <class, fullness_group>. + */ +static void insert_zspage(struct page *page, struct size_class *class, + enum fullness_group fullness) +{ + struct page **head; + + BUG_ON(!is_first_page(page)); + + if (fullness >= _ZS_NR_FULLNESS_GROUPS) + return; + + head = &class->fullness_list[fullness]; + if (*head) + list_add_tail(&page->lru, &(*head)->lru); + + *head = page; +} + +/* + * This function removes the given zspage from the freelist identified + * by <class, fullness_group>. + */ +static void remove_zspage(struct page *page, struct size_class *class, + enum fullness_group fullness) +{ + struct page **head; + + BUG_ON(!is_first_page(page)); + + if (fullness >= _ZS_NR_FULLNESS_GROUPS) + return; + + head = &class->fullness_list[fullness]; + BUG_ON(!*head); + if (list_empty(&(*head)->lru)) + *head = NULL; + else if (*head == page) + *head = (struct page *)list_entry((*head)->lru.next, + struct page, lru); + + list_del_init(&page->lru); +} + +/* + * Each size class maintains zspages in different fullness groups depending + * on the number of live objects they contain. When allocating or freeing + * objects, the fullness status of the page can change, say, from ALMOST_FULL + * to ALMOST_EMPTY when freeing an object. This function checks if such + * a status change has occurred for the given page and accordingly moves the + * page from the freelist of the old fullness group to that of the new + * fullness group. + */ +static enum fullness_group fix_fullness_group(struct zs_pool *pool, + struct page *page) +{ + int class_idx; + struct size_class *class; + enum fullness_group currfg, newfg; + + BUG_ON(!is_first_page(page)); + + get_zspage_mapping(page, &class_idx, &currfg); + newfg = get_fullness_group(page); + if (newfg == currfg) + goto out; + + class = &pool->size_class[class_idx]; + remove_zspage(page, class, currfg); + insert_zspage(page, class, newfg); + set_zspage_mapping(page, class_idx, newfg); + +out: + return newfg; +} + +/* + * We have to decide on how many pages to link together + * to form a zspage for each size class. This is important + * to reduce wastage due to unusable space left at end of + * each zspage which is given as: + * wastage = Zp - Zp % size_class + * where Zp = zspage size = k * PAGE_SIZE where k = 1, 2, ... + * + * For example, for size class of 3/8 * PAGE_SIZE, we should + * link together 3 PAGE_SIZE sized pages to form a zspage + * since then we can perfectly fit in 8 such objects. + */ +static int get_pages_per_zspage(int class_size) +{ + int i, max_usedpc = 0; + /* zspage order which gives maximum used size per KB */ + int max_usedpc_order = 1; + + for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) { + int zspage_size; + int waste, usedpc; + + zspage_size = i * PAGE_SIZE; + waste = zspage_size % class_size; + usedpc = (zspage_size - waste) * 100 / zspage_size; + + if (usedpc > max_usedpc) { + max_usedpc = usedpc; + max_usedpc_order = i; + } + } + + return max_usedpc_order; +} + +/* + * A single 'zspage' is composed of many system pages which are + * linked together using fields in struct page. This function finds + * the first/head page, given any component page of a zspage. + */ +static struct page *get_first_page(struct page *page) +{ + if (is_first_page(page)) + return page; + else + return page->first_page; +} + +static struct page *get_next_page(struct page *page) +{ + struct page *next; + + if (is_last_page(page)) + next = NULL; + else if (is_first_page(page)) + next = (struct page *)page_private(page); + else + next = list_entry(page->lru.next, struct page, lru); + + return next; +} + +/* + * Encode <page, obj_idx> as a single handle value. + * On hardware platforms with physical memory starting at 0x0 the pfn + * could be 0 so we ensure that the handle will never be 0 by adjusting the + * encoded obj_idx value before encoding. + */ +static void *obj_location_to_handle(struct page *page, unsigned long obj_idx) +{ + unsigned long handle; + + if (!page) { + BUG_ON(obj_idx); + return NULL; + } + + handle = page_to_pfn(page) << OBJ_INDEX_BITS; + handle |= ((obj_idx + 1) & OBJ_INDEX_MASK); + + return (void *)handle; +} + +/* + * Decode <page, obj_idx> pair from the given object handle. We adjust the + * decoded obj_idx back to its original value since it was adjusted in + * obj_location_to_handle(). + */ +static void obj_handle_to_location(unsigned long handle, struct page **page, + unsigned long *obj_idx) +{ + *page = pfn_to_page(handle >> OBJ_INDEX_BITS); + *obj_idx = (handle & OBJ_INDEX_MASK) - 1; +} + +static unsigned long obj_idx_to_offset(struct page *page, + unsigned long obj_idx, int class_size) +{ + unsigned long off = 0; + + if (!is_first_page(page)) + off = page->index; + + return off + obj_idx * class_size; +} + +static void reset_page(struct page *page) +{ + clear_bit(PG_private, &page->flags); + clear_bit(PG_private_2, &page->flags); + set_page_private(page, 0); + page->mapping = NULL; + page->freelist = NULL; + page_mapcount_reset(page); +} + +static void free_zspage(struct page *first_page) +{ + struct page *nextp, *tmp, *head_extra; + + BUG_ON(!is_first_page(first_page)); + BUG_ON(first_page->inuse); + + head_extra = (struct page *)page_private(first_page); + + reset_page(first_page); + __free_page(first_page); + + /* zspage with only 1 system page */ + if (!head_extra) + return; + + list_for_each_entry_safe(nextp, tmp, &head_extra->lru, lru) { + list_del(&nextp->lru); + reset_page(nextp); + __free_page(nextp); + } + reset_page(head_extra); + __free_page(head_extra); +} + +/* Initialize a newly allocated zspage */ +static void init_zspage(struct page *first_page, struct size_class *class) +{ + unsigned long off = 0; + struct page *page = first_page; + + BUG_ON(!is_first_page(first_page)); + while (page) { + struct page *next_page; + struct link_free *link; + unsigned int i, objs_on_page; + + /* + * page->index stores offset of first object starting + * in the page. For the first page, this is always 0, + * so we use first_page->index (aka ->freelist) to store + * head of corresponding zspage's freelist. + */ + if (page != first_page) + page->index = off; + + link = (struct link_free *)kmap_atomic(page) + + off / sizeof(*link); + objs_on_page = (PAGE_SIZE - off) / class->size; + + for (i = 1; i <= objs_on_page; i++) { + off += class->size; + if (off < PAGE_SIZE) { + link->next = obj_location_to_handle(page, i); + link += class->size / sizeof(*link); + } + } + + /* + * We now come to the last (full or partial) object on this + * page, which must point to the first object on the next + * page (if present) + */ + next_page = get_next_page(page); + link->next = obj_location_to_handle(next_page, 0); + kunmap_atomic(link); + page = next_page; + off = (off + class->size) % PAGE_SIZE; + } +} + +/* + * Allocate a zspage for the given size class + */ +static struct page *alloc_zspage(struct size_class *class, gfp_t flags) +{ + int i, error; + struct page *first_page = NULL, *uninitialized_var(prev_page); + + /* + * Allocate individual pages and link them together as: + * 1. first page->private = first sub-page + * 2. all sub-pages are linked together using page->lru + * 3. each sub-page is linked to the first page using page->first_page + * + * For each size class, First/Head pages are linked together using + * page->lru. Also, we set PG_private to identify the first page + * (i.e. no other sub-page has this flag set) and PG_private_2 to + * identify the last page. + */ + error = -ENOMEM; + for (i = 0; i < class->pages_per_zspage; i++) { + struct page *page; + + page = alloc_page(flags); + if (!page) + goto cleanup; + + INIT_LIST_HEAD(&page->lru); + if (i == 0) { /* first page */ + SetPagePrivate(page); + set_page_private(page, 0); + first_page = page; + first_page->inuse = 0; + } + if (i == 1) + set_page_private(first_page, (unsigned long)page); + if (i >= 1) + page->first_page = first_page; + if (i >= 2) + list_add(&page->lru, &prev_page->lru); + if (i == class->pages_per_zspage - 1) /* last page */ + SetPagePrivate2(page); + prev_page = page; + } + + init_zspage(first_page, class); + + first_page->freelist = obj_location_to_handle(first_page, 0); + /* Maximum number of objects we can store in this zspage */ + first_page->objects = class->pages_per_zspage * PAGE_SIZE / class->size; + + error = 0; /* Success */ + +cleanup: + if (unlikely(error) && first_page) { + free_zspage(first_page); + first_page = NULL; + } + + return first_page; +} + +static struct page *find_get_zspage(struct size_class *class) +{ + int i; + struct page *page; + + for (i = 0; i < _ZS_NR_FULLNESS_GROUPS; i++) { + page = class->fullness_list[i]; + if (page) + break; + } + + return page; +} + +#ifdef CONFIG_PGTABLE_MAPPING +static inline int __zs_cpu_up(struct mapping_area *area) +{ + /* + * Make sure we don't leak memory if a cpu UP notification + * and zs_init() race and both call zs_cpu_up() on the same cpu + */ + if (area->vm) + return 0; + area->vm = alloc_vm_area(PAGE_SIZE * 2, NULL); + if (!area->vm) + return -ENOMEM; + return 0; +} + +static inline void __zs_cpu_down(struct mapping_area *area) +{ + if (area->vm) + free_vm_area(area->vm); + area->vm = NULL; +} + +static inline void *__zs_map_object(struct mapping_area *area, + struct page *pages[2], int off, int size) +{ + BUG_ON(map_vm_area(area->vm, PAGE_KERNEL, &pages)); + area->vm_addr = area->vm->addr; + return area->vm_addr + off; +} + +static inline void __zs_unmap_object(struct mapping_area *area, + struct page *pages[2], int off, int size) +{ + unsigned long addr = (unsigned long)area->vm_addr; + + unmap_kernel_range(addr, PAGE_SIZE * 2); +} + +#else /* CONFIG_PGTABLE_MAPPING */ + +static inline int __zs_cpu_up(struct mapping_area *area) +{ + /* + * Make sure we don't leak memory if a cpu UP notification + * and zs_init() race and both call zs_cpu_up() on the same cpu + */ + if (area->vm_buf) + return 0; + area->vm_buf = (char *)__get_free_page(GFP_KERNEL); + if (!area->vm_buf) + return -ENOMEM; + return 0; +} + +static inline void __zs_cpu_down(struct mapping_area *area) +{ + if (area->vm_buf) + free_page((unsigned long)area->vm_buf); + area->vm_buf = NULL; +} + +static void *__zs_map_object(struct mapping_area *area, + struct page *pages[2], int off, int size) +{ + int sizes[2]; + void *addr; + char *buf = area->vm_buf; + + /* disable page faults to match kmap_atomic() return conditions */ + pagefault_disable(); + + /* no read fastpath */ + if (area->vm_mm == ZS_MM_WO) + goto out; + + sizes[0] = PAGE_SIZE - off; + sizes[1] = size - sizes[0]; + + /* copy object to per-cpu buffer */ + addr = kmap_atomic(pages[0]); + memcpy(buf, addr + off, sizes[0]); + kunmap_atomic(addr); + addr = kmap_atomic(pages[1]); + memcpy(buf + sizes[0], addr, sizes[1]); + kunmap_atomic(addr); +out: + return area->vm_buf; +} + +static void __zs_unmap_object(struct mapping_area *area, + struct page *pages[2], int off, int size) +{ + int sizes[2]; + void *addr; + char *buf = area->vm_buf; + + /* no write fastpath */ + if (area->vm_mm == ZS_MM_RO) + goto out; + + sizes[0] = PAGE_SIZE - off; + sizes[1] = size - sizes[0]; + + /* copy per-cpu buffer to object */ + addr = kmap_atomic(pages[0]); + memcpy(addr + off, buf, sizes[0]); + kunmap_atomic(addr); + addr = kmap_atomic(pages[1]); + memcpy(addr, buf + sizes[0], sizes[1]); + kunmap_atomic(addr); + +out: + /* enable page faults to match kunmap_atomic() return conditions */ + pagefault_enable(); +} + +#endif /* CONFIG_PGTABLE_MAPPING */ + +static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action, + void *pcpu) +{ + int ret, cpu = (long)pcpu; + struct mapping_area *area; + + switch (action) { + case CPU_UP_PREPARE: + area = &per_cpu(zs_map_area, cpu); + ret = __zs_cpu_up(area); + if (ret) + return notifier_from_errno(ret); + break; + case CPU_DEAD: + case CPU_UP_CANCELED: + area = &per_cpu(zs_map_area, cpu); + __zs_cpu_down(area); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block zs_cpu_nb = { + .notifier_call = zs_cpu_notifier +}; + +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); + + cpu_notifier_register_done(); +} + +static int zs_init(void) +{ + int cpu, ret; + + 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)) { + cpu_notifier_register_done(); + goto fail; + } + } + + cpu_notifier_register_done(); + + return 0; +fail: + zs_exit(); + return notifier_to_errno(ret); +} + +/** + * zs_create_pool - Creates an allocation pool to work from. + * @flags: allocation flags used to allocate pool metadata + * + * This function must be called before anything when using + * the zsmalloc allocator. + * + * On success, a pointer to the newly created pool is returned, + * otherwise NULL. + */ +struct zs_pool *zs_create_pool(gfp_t flags) +{ + int i, ovhd_size; + struct zs_pool *pool; + + ovhd_size = roundup(sizeof(*pool), PAGE_SIZE); + pool = kzalloc(ovhd_size, GFP_KERNEL); + if (!pool) + return NULL; + + for (i = 0; i < ZS_SIZE_CLASSES; i++) { + int size; + struct size_class *class; + + size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA; + if (size > ZS_MAX_ALLOC_SIZE) + size = ZS_MAX_ALLOC_SIZE; + + class = &pool->size_class[i]; + class->size = size; + class->index = i; + spin_lock_init(&class->lock); + class->pages_per_zspage = get_pages_per_zspage(size); + + } + + pool->flags = flags; + + return pool; +} +EXPORT_SYMBOL_GPL(zs_create_pool); + +void zs_destroy_pool(struct zs_pool *pool) +{ + int i; + + for (i = 0; i < ZS_SIZE_CLASSES; i++) { + int fg; + struct size_class *class = &pool->size_class[i]; + + for (fg = 0; fg < _ZS_NR_FULLNESS_GROUPS; fg++) { + if (class->fullness_list[fg]) { + pr_info("Freeing non-empty class with size %db, fullness group %d\n", + class->size, fg); + } + } + } + kfree(pool); +} +EXPORT_SYMBOL_GPL(zs_destroy_pool); + +/** + * zs_malloc - Allocate block of given size from pool. + * @pool: pool to allocate from + * @size: size of block to allocate + * + * On success, handle to the allocated object is returned, + * otherwise 0. + * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail. + */ +unsigned long zs_malloc(struct zs_pool *pool, size_t size) +{ + unsigned long obj; + struct link_free *link; + int class_idx; + struct size_class *class; + + struct page *first_page, *m_page; + unsigned long m_objidx, m_offset; + + if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE)) + return 0; + + class_idx = get_size_class_index(size); + class = &pool->size_class[class_idx]; + BUG_ON(class_idx != class->index); + + spin_lock(&class->lock); + first_page = find_get_zspage(class); + + if (!first_page) { + spin_unlock(&class->lock); + first_page = alloc_zspage(class, pool->flags); + if (unlikely(!first_page)) + return 0; + + set_zspage_mapping(first_page, class->index, ZS_EMPTY); + spin_lock(&class->lock); + class->pages_allocated += class->pages_per_zspage; + } + + obj = (unsigned long)first_page->freelist; + obj_handle_to_location(obj, &m_page, &m_objidx); + m_offset = obj_idx_to_offset(m_page, m_objidx, class->size); + + link = (struct link_free *)kmap_atomic(m_page) + + m_offset / sizeof(*link); + first_page->freelist = link->next; + memset(link, POISON_INUSE, sizeof(*link)); + kunmap_atomic(link); + + first_page->inuse++; + /* Now move the zspage to another fullness group, if required */ + fix_fullness_group(pool, first_page); + spin_unlock(&class->lock); + + return obj; +} +EXPORT_SYMBOL_GPL(zs_malloc); + +void zs_free(struct zs_pool *pool, unsigned long obj) +{ + struct link_free *link; + struct page *first_page, *f_page; + unsigned long f_objidx, f_offset; + + int class_idx; + struct size_class *class; + enum fullness_group fullness; + + if (unlikely(!obj)) + return; + + obj_handle_to_location(obj, &f_page, &f_objidx); + first_page = get_first_page(f_page); + + get_zspage_mapping(first_page, &class_idx, &fullness); + class = &pool->size_class[class_idx]; + f_offset = obj_idx_to_offset(f_page, f_objidx, class->size); + + spin_lock(&class->lock); + + /* Insert this object in containing zspage's freelist */ + link = (struct link_free *)((unsigned char *)kmap_atomic(f_page) + + f_offset); + link->next = first_page->freelist; + kunmap_atomic(link); + first_page->freelist = (void *)obj; + + first_page->inuse--; + fullness = fix_fullness_group(pool, first_page); + + if (fullness == ZS_EMPTY) + class->pages_allocated -= class->pages_per_zspage; + + spin_unlock(&class->lock); + + if (fullness == ZS_EMPTY) + free_zspage(first_page); +} +EXPORT_SYMBOL_GPL(zs_free); + +/** + * zs_map_object - get address of allocated object from handle. + * @pool: pool from which the object was allocated + * @handle: handle returned from zs_malloc + * + * Before using an object allocated from zs_malloc, it must be mapped using + * this function. When done with the object, it must be unmapped using + * zs_unmap_object. + * + * Only one object can be mapped per cpu at a time. There is no protection + * against nested mappings. + * + * This function returns with preemption and page faults disabled. + */ +void *zs_map_object(struct zs_pool *pool, unsigned long handle, + enum zs_mapmode mm) +{ + struct page *page; + unsigned long obj_idx, off; + + unsigned int class_idx; + enum fullness_group fg; + struct size_class *class; + struct mapping_area *area; + struct page *pages[2]; + + BUG_ON(!handle); + + /* + * Because we use per-cpu mapping areas shared among the + * pools/users, we can't allow mapping in interrupt context + * because it can corrupt another users mappings. + */ + BUG_ON(in_interrupt()); + + obj_handle_to_location(handle, &page, &obj_idx); + get_zspage_mapping(get_first_page(page), &class_idx, &fg); + class = &pool->size_class[class_idx]; + off = obj_idx_to_offset(page, obj_idx, class->size); + + area = &get_cpu_var(zs_map_area); + area->vm_mm = mm; + if (off + class->size <= PAGE_SIZE) { + /* this object is contained entirely within a page */ + area->vm_addr = kmap_atomic(page); + return area->vm_addr + off; + } + + /* this object spans two pages */ + pages[0] = page; + pages[1] = get_next_page(page); + BUG_ON(!pages[1]); + + return __zs_map_object(area, pages, off, class->size); +} +EXPORT_SYMBOL_GPL(zs_map_object); + +void zs_unmap_object(struct zs_pool *pool, unsigned long handle) +{ + struct page *page; + unsigned long obj_idx, off; + + unsigned int class_idx; + enum fullness_group fg; + struct size_class *class; + struct mapping_area *area; + + BUG_ON(!handle); + + obj_handle_to_location(handle, &page, &obj_idx); + get_zspage_mapping(get_first_page(page), &class_idx, &fg); + class = &pool->size_class[class_idx]; + off = obj_idx_to_offset(page, obj_idx, class->size); + + area = &__get_cpu_var(zs_map_area); + if (off + class->size <= PAGE_SIZE) + kunmap_atomic(area->vm_addr); + else { + struct page *pages[2]; + + pages[0] = page; + pages[1] = get_next_page(page); + BUG_ON(!pages[1]); + + __zs_unmap_object(area, pages, off, class->size); + } + put_cpu_var(zs_map_area); +} +EXPORT_SYMBOL_GPL(zs_unmap_object); + +u64 zs_get_total_size_bytes(struct zs_pool *pool) +{ + int i; + u64 npages = 0; + + for (i = 0; i < ZS_SIZE_CLASSES; i++) + npages += pool->size_class[i].pages_allocated; + + return npages << PAGE_SHIFT; +} +EXPORT_SYMBOL_GPL(zs_get_total_size_bytes); + +module_init(zs_init); +module_exit(zs_exit); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>"); diff --git a/mm/zswap.c b/mm/zswap.c index 5a63f78a5601..aeaef0fb5624 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -77,18 +77,21 @@ static u64 zswap_duplicate_entry; **********************************/ /* Enable/disable zswap (disabled by default, fixed at boot for now) */ static bool zswap_enabled __read_mostly; -module_param_named(enabled, zswap_enabled, bool, 0); +module_param_named(enabled, zswap_enabled, bool, 0444); /* Compressor to be used by zswap (fixed at boot for now) */ #define ZSWAP_COMPRESSOR_DEFAULT "lzo" static char *zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT; -module_param_named(compressor, zswap_compressor, charp, 0); +module_param_named(compressor, zswap_compressor, charp, 0444); /* The maximum percentage of memory that the compressed pool can occupy */ 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; } |