diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 17 | ||||
| -rw-r--r-- | mm/Makefile | 1 | ||||
| -rw-r--r-- | mm/bootmem.c | 6 | ||||
| -rw-r--r-- | mm/bounce.c | 8 | ||||
| -rw-r--r-- | mm/compaction.c | 147 | ||||
| -rw-r--r-- | mm/frontswap.c | 344 | ||||
| -rw-r--r-- | mm/internal.h | 9 | ||||
| -rw-r--r-- | mm/madvise.c | 18 | ||||
| -rw-r--r-- | mm/memblock.c | 115 | ||||
| -rw-r--r-- | mm/memcontrol.c | 6 | ||||
| -rw-r--r-- | mm/memory-failure.c | 14 | ||||
| -rw-r--r-- | mm/memory.c | 21 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 2 | ||||
| -rw-r--r-- | mm/mempolicy.c | 2 | ||||
| -rw-r--r-- | mm/migrate.c | 5 | ||||
| -rw-r--r-- | mm/nobootmem.c | 40 | ||||
| -rw-r--r-- | mm/nommu.c | 2 | ||||
| -rw-r--r-- | mm/oom_kill.c | 21 | ||||
| -rw-r--r-- | mm/page_alloc.c | 15 | ||||
| -rw-r--r-- | mm/page_cgroup.c | 4 | ||||
| -rw-r--r-- | mm/page_io.c | 12 | ||||
| -rw-r--r-- | mm/pagewalk.c | 1 | ||||
| -rw-r--r-- | mm/percpu-vm.c | 1 | ||||
| -rw-r--r-- | mm/shmem.c | 253 | ||||
| -rw-r--r-- | mm/sparse.c | 20 | ||||
| -rw-r--r-- | mm/swapfile.c | 66 | ||||
| -rw-r--r-- | mm/vmalloc.c | 36 | ||||
| -rw-r--r-- | mm/vmscan.c | 17 |
28 files changed, 776 insertions, 427 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index b2176374b98..82fed4eb2b6 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -389,3 +389,20 @@ config CLEANCACHE in a negligible performance hit. If unsure, say Y to enable cleancache + +config FRONTSWAP + bool "Enable frontswap to cache swap pages if tmem is present" + depends on SWAP + default n + help + Frontswap is so named because it can be thought of as the opposite + of a "backing" store for a swap device. The data is stored into + "transcendent memory", memory that is not directly accessible or + addressable by the kernel and is of unknown and possibly + time-varying size. When space in transcendent memory is available, + a significant swap I/O reduction may be achieved. When none is + available, all frontswap calls are reduced to a single pointer- + compare-against-NULL resulting in a negligible performance hit + and swap data is stored as normal on the matching swap device. + + If unsure, say Y to enable frontswap. diff --git a/mm/Makefile b/mm/Makefile index a156285ce88..2e2fbbefb99 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -29,6 +29,7 @@ obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o +obj-$(CONFIG_FRONTSWAP) += frontswap.o obj-$(CONFIG_HAS_DMA) += dmapool.o obj-$(CONFIG_HUGETLBFS) += hugetlb.o obj-$(CONFIG_NUMA) += mempolicy.o diff --git a/mm/bootmem.c b/mm/bootmem.c index ec4fcb7a56c..bcb63ac48cc 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -698,7 +698,7 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align, return ___alloc_bootmem(size, align, goal, limit); } -static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, +void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal, unsigned long limit) { @@ -710,6 +710,10 @@ again: if (ptr) return ptr; + /* do not panic in alloc_bootmem_bdata() */ + if (limit && goal + size > limit) + limit = 0; + ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, goal, limit); if (ptr) return ptr; diff --git a/mm/bounce.c b/mm/bounce.c index d1be02ca188..04208677556 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -24,23 +24,25 @@ static mempool_t *page_pool, *isa_page_pool; -#ifdef CONFIG_HIGHMEM +#if defined(CONFIG_HIGHMEM) || defined(CONFIG_NEED_BOUNCE_POOL) static __init int init_emergency_pool(void) { -#ifndef CONFIG_MEMORY_HOTPLUG +#if defined(CONFIG_HIGHMEM) && !defined(CONFIG_MEMORY_HOTPLUG) if (max_pfn <= max_low_pfn) return 0; #endif page_pool = mempool_create_page_pool(POOL_SIZE, 0); BUG_ON(!page_pool); - printk("highmem bounce pool size: %d pages\n", POOL_SIZE); + printk("bounce pool size: %d pages\n", POOL_SIZE); return 0; } __initcall(init_emergency_pool); +#endif +#ifdef CONFIG_HIGHMEM /* * highmem version, map in to vec */ diff --git a/mm/compaction.c b/mm/compaction.c index 4ac338af512..2f42d952853 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -236,7 +236,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, */ while (unlikely(too_many_isolated(zone))) { /* async migration should just abort */ - if (cc->mode != COMPACT_SYNC) + if (!cc->sync) return 0; congestion_wait(BLK_RW_ASYNC, HZ/10); @@ -304,8 +304,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, * satisfies the allocation */ pageblock_nr = low_pfn >> pageblock_order; - if (cc->mode != COMPACT_SYNC && - last_pageblock_nr != pageblock_nr && + if (!cc->sync && last_pageblock_nr != pageblock_nr && !migrate_async_suitable(get_pageblock_migratetype(page))) { low_pfn += pageblock_nr_pages; low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1; @@ -326,7 +325,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; } - if (cc->mode != COMPACT_SYNC) + if (!cc->sync) mode |= ISOLATE_ASYNC_MIGRATE; lruvec = mem_cgroup_page_lruvec(page, zone); @@ -361,90 +360,27 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, #endif /* CONFIG_COMPACTION || CONFIG_CMA */ #ifdef CONFIG_COMPACTION -/* - * Returns true if MIGRATE_UNMOVABLE pageblock was successfully - * converted to MIGRATE_MOVABLE type, false otherwise. - */ -static bool rescue_unmovable_pageblock(struct page *page) -{ - unsigned long pfn, start_pfn, end_pfn; - struct page *start_page, *end_page; - - pfn = page_to_pfn(page); - start_pfn = pfn & ~(pageblock_nr_pages - 1); - end_pfn = start_pfn + pageblock_nr_pages; - - start_page = pfn_to_page(start_pfn); - end_page = pfn_to_page(end_pfn); - - /* Do not deal with pageblocks that overlap zones */ - if (page_zone(start_page) != page_zone(end_page)) - return false; - - for (page = start_page, pfn = start_pfn; page < end_page; pfn++, - page++) { - if (!pfn_valid_within(pfn)) - continue; - - if (PageBuddy(page)) { - int order = page_order(page); - - pfn += (1 << order) - 1; - page += (1 << order) - 1; - - continue; - } else if (page_count(page) == 0 || PageLRU(page)) - continue; - - return false; - } - - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - move_freepages_block(page_zone(page), page, MIGRATE_MOVABLE); - return true; -} - -enum smt_result { - GOOD_AS_MIGRATION_TARGET, - FAIL_UNMOVABLE_TARGET, - FAIL_BAD_TARGET, -}; -/* - * Returns GOOD_AS_MIGRATION_TARGET if the page is within a block - * suitable for migration to, FAIL_UNMOVABLE_TARGET if the page - * is within a MIGRATE_UNMOVABLE block, FAIL_BAD_TARGET otherwise. - */ -static enum smt_result suitable_migration_target(struct page *page, - struct compact_control *cc) +/* 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_ISOLATE || migratetype == MIGRATE_RESERVE) - return FAIL_BAD_TARGET; + return false; /* If the page is a large free page, then allow migration */ if (PageBuddy(page) && page_order(page) >= pageblock_order) - return GOOD_AS_MIGRATION_TARGET; + return true; /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ - if (cc->mode != COMPACT_ASYNC_UNMOVABLE && - migrate_async_suitable(migratetype)) - return GOOD_AS_MIGRATION_TARGET; - - if (cc->mode == COMPACT_ASYNC_MOVABLE && - migratetype == MIGRATE_UNMOVABLE) - return FAIL_UNMOVABLE_TARGET; - - if (cc->mode != COMPACT_ASYNC_MOVABLE && - migratetype == MIGRATE_UNMOVABLE && - rescue_unmovable_pageblock(page)) - return GOOD_AS_MIGRATION_TARGET; + if (migrate_async_suitable(migratetype)) + return true; /* Otherwise skip the block */ - return FAIL_BAD_TARGET; + return false; } /* @@ -478,13 +414,6 @@ static void isolate_freepages(struct zone *zone, zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; /* - * isolate_freepages() may be called more than once during - * compact_zone_order() run and we want only the most recent - * count. - */ - cc->nr_pageblocks_skipped = 0; - - /* * Isolate free pages until enough are available to migrate the * pages on cc->migratepages. We stop searching if the migrate * and free page scanners meet or enough free pages are isolated. @@ -492,7 +421,6 @@ static void isolate_freepages(struct zone *zone, for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages; pfn -= pageblock_nr_pages) { unsigned long isolated; - enum smt_result ret; if (!pfn_valid(pfn)) continue; @@ -509,12 +437,9 @@ static void isolate_freepages(struct zone *zone, continue; /* Check the block is suitable for migration */ - ret = suitable_migration_target(page, cc); - if (ret != GOOD_AS_MIGRATION_TARGET) { - if (ret == FAIL_UNMOVABLE_TARGET) - cc->nr_pageblocks_skipped++; + if (!suitable_migration_target(page)) continue; - } + /* * Found a block suitable for isolating free pages from. Now * we disabled interrupts, double check things are ok and @@ -523,14 +448,12 @@ static void isolate_freepages(struct zone *zone, */ isolated = 0; spin_lock_irqsave(&zone->lock, flags); - ret = suitable_migration_target(page, cc); - if (ret == GOOD_AS_MIGRATION_TARGET) { + if (suitable_migration_target(page)) { end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn); isolated = isolate_freepages_block(pfn, end_pfn, freelist, false); nr_freepages += isolated; - } else if (ret == FAIL_UNMOVABLE_TARGET) - cc->nr_pageblocks_skipped++; + } spin_unlock_irqrestore(&zone->lock, flags); /* @@ -762,9 +685,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) nr_migrate = cc->nr_migratepages; err = migrate_pages(&cc->migratepages, compaction_alloc, - (unsigned long)&cc->freepages, false, - (cc->mode == COMPACT_SYNC) ? MIGRATE_SYNC_LIGHT - : MIGRATE_ASYNC); + (unsigned long)cc, false, + cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC); update_nr_listpages(cc); nr_remaining = cc->nr_migratepages; @@ -779,8 +701,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) if (err) { putback_lru_pages(&cc->migratepages); cc->nr_migratepages = 0; + if (err == -ENOMEM) { + ret = COMPACT_PARTIAL; + goto out; + } } - } out: @@ -793,8 +718,7 @@ out: static unsigned long compact_zone_order(struct zone *zone, int order, gfp_t gfp_mask, - enum compact_mode mode, - unsigned long *nr_pageblocks_skipped) + bool sync) { struct compact_control cc = { .nr_freepages = 0, @@ -802,17 +726,12 @@ static unsigned long compact_zone_order(struct zone *zone, .order = order, .migratetype = allocflags_to_migratetype(gfp_mask), .zone = zone, - .mode = mode, + .sync = sync, }; - unsigned long rc; - INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); - rc = compact_zone(zone, &cc); - *nr_pageblocks_skipped = cc.nr_pageblocks_skipped; - - return rc; + return compact_zone(zone, &cc); } int sysctl_extfrag_threshold = 500; @@ -837,8 +756,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, struct zoneref *z; struct zone *zone; int rc = COMPACT_SKIPPED; - unsigned long nr_pageblocks_skipped; - enum compact_mode mode; /* * Check whether it is worth even starting compaction. The order check is @@ -855,22 +772,12 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, nodemask) { int status; - mode = sync ? COMPACT_SYNC : COMPACT_ASYNC_MOVABLE; -retry: - status = compact_zone_order(zone, order, gfp_mask, mode, - &nr_pageblocks_skipped); + status = compact_zone_order(zone, order, gfp_mask, sync); rc = max(status, rc); /* If a normal allocation would succeed, stop compacting */ if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0)) break; - - if (rc == COMPACT_COMPLETE && mode == COMPACT_ASYNC_MOVABLE) { - if (nr_pageblocks_skipped) { - mode = COMPACT_ASYNC_UNMOVABLE; - goto retry; - } - } } return rc; @@ -904,7 +811,7 @@ static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) if (ok && cc->order > zone->compact_order_failed) zone->compact_order_failed = cc->order + 1; /* Currently async compaction is never deferred. */ - else if (!ok && cc->mode == COMPACT_SYNC) + else if (!ok && cc->sync) defer_compaction(zone, cc->order); } @@ -919,7 +826,7 @@ int compact_pgdat(pg_data_t *pgdat, int order) { struct compact_control cc = { .order = order, - .mode = COMPACT_ASYNC_MOVABLE, + .sync = false, }; return __compact_pgdat(pgdat, &cc); @@ -929,7 +836,7 @@ static int compact_node(int nid) { struct compact_control cc = { .order = -1, - .mode = COMPACT_SYNC, + .sync = true, }; return __compact_pgdat(NODE_DATA(nid), &cc); diff --git a/mm/frontswap.c b/mm/frontswap.c new file mode 100644 index 00000000000..6b3e71a2cd4 --- /dev/null +++ b/mm/frontswap.c @@ -0,0 +1,344 @@ +/* + * Frontswap frontend + * + * This code provides the generic "frontend" layer to call a matching + * "backend" driver implementation of frontswap. See + * Documentation/vm/frontswap.txt for more information. + * + * Copyright (C) 2009-2012 Oracle Corp. All rights reserved. + * Author: Dan Magenheimer + * + * This work is licensed under the terms of the GNU GPL, version 2. + */ + +#include <linux/mman.h> +#include <linux/swap.h> +#include <linux/swapops.h> +#include <linux/security.h> +#include <linux/module.h> +#include <linux/debugfs.h> +#include <linux/frontswap.h> +#include <linux/swapfile.h> + +/* + * frontswap_ops is set by frontswap_register_ops to contain the pointers + * to the frontswap "backend" implementation functions. + */ +static struct frontswap_ops frontswap_ops __read_mostly; + +/* + * This global enablement flag reduces overhead on systems where frontswap_ops + * has not been registered, so is preferred to the slower alternative: a + * function call that checks a non-global. + */ +bool frontswap_enabled __read_mostly; +EXPORT_SYMBOL(frontswap_enabled); + +/* + * If enabled, frontswap_store will return failure even on success. As + * a result, the swap subsystem will always write the page to swap, in + * effect converting frontswap into a writethrough cache. In this mode, + * there is no direct reduction in swap writes, but a frontswap backend + * can unilaterally "reclaim" any pages in use with no data loss, thus + * providing increases control over maximum memory usage due to frontswap. + */ +static bool frontswap_writethrough_enabled __read_mostly; + +#ifdef CONFIG_DEBUG_FS +/* + * Counters available via /sys/kernel/debug/frontswap (if debugfs is + * properly configured). These are for information only so are not protected + * against increment races. + */ +static u64 frontswap_loads; +static u64 frontswap_succ_stores; +static u64 frontswap_failed_stores; +static u64 frontswap_invalidates; + +static inline void inc_frontswap_loads(void) { + frontswap_loads++; +} +static inline void inc_frontswap_succ_stores(void) { + frontswap_succ_stores++; +} +static inline void inc_frontswap_failed_stores(void) { + frontswap_failed_stores++; +} +static inline void inc_frontswap_invalidates(void) { + frontswap_invalidates++; +} +#else +static inline void inc_frontswap_loads(void) { } +static inline void inc_frontswap_succ_stores(void) { } +static inline void inc_frontswap_failed_stores(void) { } +static inline void inc_frontswap_invalidates(void) { } +#endif +/* + * Register operations for frontswap, returning previous thus allowing + * detection of multiple backends and possible nesting. + */ +struct frontswap_ops frontswap_register_ops(struct frontswap_ops *ops) +{ + struct frontswap_ops old = frontswap_ops; + + frontswap_ops = *ops; + frontswap_enabled = true; + return old; +} +EXPORT_SYMBOL(frontswap_register_ops); + +/* + * Enable/disable frontswap writethrough (see above). + */ +void frontswap_writethrough(bool enable) +{ + frontswap_writethrough_enabled = enable; +} +EXPORT_SYMBOL(frontswap_writethrough); + +/* + * Called when a swap device is swapon'd. + */ +void __frontswap_init(unsigned type) +{ + struct swap_info_struct *sis = swap_info[type]; + + BUG_ON(sis == NULL); + if (sis->frontswap_map == NULL) + return; + frontswap_ops.init(type); +} +EXPORT_SYMBOL(__frontswap_init); + +static inline void __frontswap_clear(struct swap_info_struct *sis, pgoff_t offset) +{ + frontswap_clear(sis, offset); + atomic_dec(&sis->frontswap_pages); +} + +/* + * "Store" data from a page to frontswap and associate it with the page's + * swaptype and offset. Page must be locked and in the swap cache. + * If frontswap already contains a page with matching swaptype and + * offset, the frontswap implementation may either overwrite the data and + * return success or invalidate the page from frontswap and return failure. + */ +int __frontswap_store(struct page *page) +{ + int ret = -1, dup = 0; + swp_entry_t entry = { .val = page_private(page), }; + int type = swp_type(entry); + struct swap_info_struct *sis = swap_info[type]; + pgoff_t offset = swp_offset(entry); + + BUG_ON(!PageLocked(page)); + BUG_ON(sis == NULL); + if (frontswap_test(sis, offset)) + dup = 1; + ret = frontswap_ops.store(type, offset, page); + if (ret == 0) { + frontswap_set(sis, offset); + inc_frontswap_succ_stores(); + if (!dup) + atomic_inc(&sis->frontswap_pages); + } else { + /* + failed dup always results in automatic invalidate of + the (older) page from frontswap + */ + inc_frontswap_failed_stores(); + if (dup) + __frontswap_clear(sis, offset); + } + if (frontswap_writethrough_enabled) + /* report failure so swap also writes to swap device */ + ret = -1; + return ret; +} +EXPORT_SYMBOL(__frontswap_store); + +/* + * "Get" data from frontswap associated with swaptype and offset that were + * specified when the data was put to frontswap and use it to fill the + * specified page with data. Page must be locked and in the swap cache. + */ +int __frontswap_load(struct page *page) +{ + int ret = -1; + swp_entry_t entry = { .val = page_private(page), }; + int type = swp_type(entry); + struct swap_info_struct *sis = swap_info[type]; + pgoff_t offset = swp_offset(entry); + + BUG_ON(!PageLocked(page)); + BUG_ON(sis == NULL); + if (frontswap_test(sis, offset)) + ret = frontswap_ops.load(type, offset, page); + if (ret == 0) + inc_frontswap_loads(); + return ret; +} +EXPORT_SYMBOL(__frontswap_load); + +/* + * Invalidate any data from frontswap associated with the specified swaptype + * and offset so that a subsequent "get" will fail. + */ +void __frontswap_invalidate_page(unsigned type, pgoff_t offset) +{ + struct swap_info_struct *sis = swap_info[type]; + + BUG_ON(sis == NULL); + if (frontswap_test(sis, offset)) { + frontswap_ops.invalidate_page(type, offset); + __frontswap_clear(sis, offset); + inc_frontswap_invalidates(); + } +} +EXPORT_SYMBOL(__frontswap_invalidate_page); + +/* + * Invalidate all data from frontswap associated with all offsets for the + * specified swaptype. + */ +void __frontswap_invalidate_area(unsigned type) +{ + struct swap_info_struct *sis = swap_info[type]; + + BUG_ON(sis == NULL); + if (sis->frontswap_map == NULL) + return; + frontswap_ops.invalidate_area(type); + atomic_set(&sis->frontswap_pages, 0); + memset(sis->frontswap_map, 0, sis->max / sizeof(long)); +} +EXPORT_SYMBOL(__frontswap_invalidate_area); + +static unsigned long __frontswap_curr_pages(void) +{ + int type; + unsigned long totalpages = 0; + struct swap_info_struct *si = NULL; + + assert_spin_locked(&swap_lock); + for (type = swap_list.head; type >= 0; type = si->next) { + si = swap_info[type]; + totalpages += atomic_read(&si->frontswap_pages); + } + return totalpages; +} + +static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, + int *swapid) +{ + int ret = -EINVAL; + struct swap_info_struct *si = NULL; + int si_frontswap_pages; + unsigned long total_pages_to_unuse = total; + unsigned long pages = 0, pages_to_unuse = 0; + int type; + + assert_spin_locked(&swap_lock); + for (type = swap_list.head; type >= 0; type = si->next) { + si = swap_info[type]; + si_frontswap_pages = atomic_read(&si->frontswap_pages); + if (total_pages_to_unuse < si_frontswap_pages) { + pages = pages_to_unuse = total_pages_to_unuse; + } else { + pages = si_frontswap_pages; + pages_to_unuse = 0; /* unuse all */ + } + /* ensure there is enough RAM to fetch pages from frontswap */ + if (security_vm_enough_memory_mm(current->mm, pages)) { + ret = -ENOMEM; + continue; + } + vm_unacct_memory(pages); + *unused = pages_to_unuse; + *swapid = type; + ret = 0; + break; + } + + return ret; +} + +static int __frontswap_shrink(unsigned long target_pages, + unsigned long *pages_to_unuse, + int *type) +{ + unsigned long total_pages = 0, total_pages_to_unuse; + + assert_spin_locked(&swap_lock); + + total_pages = __frontswap_curr_pages(); + if (total_pages <= target_pages) { + /* Nothing to do */ + *pages_to_unuse = 0; + return 0; + } + total_pages_to_unuse = total_pages - target_pages; + return __frontswap_unuse_pages(total_pages_to_unuse, pages_to_unuse, type); +} + +/* + * Frontswap, like a true swap device, may unnecessarily retain pages + * under certain circumstances; "shrink" frontswap is essentially a + * "partial swapoff" and works by calling try_to_unuse to attempt to + * unuse enough frontswap pages to attempt to -- subject to memory + * constraints -- reduce the number of pages in frontswap to the + * number given in the parameter target_pages. + */ +void frontswap_shrink(unsigned long target_pages) +{ + unsigned long pages_to_unuse = 0; + int type, ret; + + /* + * we don't want to hold swap_lock while doing a very + * lengthy try_to_unuse, but swap_list may change + * so restart scan from swap_list.head each time + */ + spin_lock(&swap_lock); + ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type); + spin_unlock(&swap_lock); + if (ret == 0 && pages_to_unuse) + try_to_unuse(type, true, pages_to_unuse); + return; +} +EXPORT_SYMBOL(frontswap_shrink); + +/* + * Count and return the number of frontswap pages across all + * swap devices. This is exported so that backend drivers can + * determine current usage without reading debugfs. + */ +unsigned long frontswap_curr_pages(void) +{ + unsigned long totalpages = 0; + + spin_lock(&swap_lock); + totalpages = __frontswap_curr_pages(); + spin_unlock(&swap_lock); + + return totalpages; +} +EXPORT_SYMBOL(frontswap_curr_pages); + +static int __init init_frontswap(void) +{ +#ifdef CONFIG_DEBUG_FS + struct dentry *root = debugfs_create_dir("frontswap", NULL); + if (root == NULL) + return -ENXIO; + debugfs_create_u64("loads", S_IRUGO, root, &frontswap_loads); + debugfs_create_u64("succ_stores", S_IRUGO, root, &frontswap_succ_stores); + debugfs_create_u64("failed_stores", S_IRUGO, root, + &frontswap_failed_stores); + debugfs_create_u64("invalidates", S_IRUGO, + root, &frontswap_invalidates); +#endif + return 0; +} + +module_init(init_frontswap); diff --git a/mm/internal.h b/mm/internal.h index 5cbb7819004..2ba87fbfb75 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -94,9 +94,6 @@ extern void putback_lru_page(struct page *page); /* * in mm/page_alloc.c */ -extern void set_pageblock_migratetype(struct page *page, int migratetype); -extern int move_freepages_block(struct zone *zone, struct page *page, - int migratetype); extern void __free_pages_bootmem(struct page *page, unsigned int order); extern void prep_compound_page(struct page *page, unsigned long order); #ifdef CONFIG_MEMORY_FAILURE @@ -104,7 +101,6 @@ extern bool is_free_buddy_page(struct page *page); #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA -#include <linux/compaction.h> /* * in mm/compaction.c @@ -123,14 +119,11 @@ struct compact_control { unsigned long nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ unsigned long migrate_pfn; /* isolate_migratepages search base */ - enum compact_mode mode; /* Compaction mode */ + bool sync; /* Synchronous migration */ int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ struct zone *zone; - - /* Number of UNMOVABLE destination pageblocks skipped during scan */ - unsigned long nr_pageblocks_skipped; }; unsigned long diff --git a/mm/madvise.c b/mm/madvise.c index deff1b64a08..14d260fa0d1 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -15,6 +15,7 @@ #include <linux/sched.h> #include <linux/ksm.h> #include <linux/fs.h> +#include <linux/file.h> /* * Any behaviour which results in changes to the vma->vm_flags needs to @@ -204,14 +205,16 @@ static long madvise_remove(struct vm_area_struct *vma, { loff_t offset; int error; + struct file *f; *prev = NULL; /* tell sys_madvise we drop mmap_sem */ if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB)) return -EINVAL; - if (!vma->vm_file || !vma->vm_file->f_mapping - || !vma->vm_file->f_mapping->host) { + f = vma->vm_file; + + if (!f || !f->f_mapping || !f->f_mapping->host) { return -EINVAL; } @@ -221,11 +224,18 @@ static long madvise_remove(struct vm_area_struct *vma, offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); - /* filesystem's fallocate may need to take i_mutex */ + /* + * Filesystem's fallocate may need to take i_mutex. We need to + * explicitly grab a reference because the vma (and hence the + * vma's reference to the file) can go away as soon as we drop + * mmap_sem. + */ + get_file(f); up_read(¤t->mm->mmap_sem); - error = do_fallocate(vma->vm_file, + error = do_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); + fput(f); down_read(¤t->mm->mmap_sem); return error; } diff --git a/mm/memblock.c b/mm/memblock.c index 952123eba43..5cc6731b00c 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -143,30 +143,6 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, MAX_NUMNODES); } -/* - * Free memblock.reserved.regions - */ -int __init_memblock memblock_free_reserved_regions(void) -{ - if (memblock.reserved.regions == memblock_reserved_init_regions) - return 0; - - return memblock_free(__pa(memblock.reserved.regions), - sizeof(struct memblock_region) * memblock.reserved.max); -} - -/* - * Reserve memblock.reserved.regions - */ -int __init_memblock memblock_reserve_reserved_regions(void) -{ - if (memblock.reserved.regions == memblock_reserved_init_regions) - return 0; - - return memblock_reserve(__pa(memblock.reserved.regions), - sizeof(struct memblock_region) * memblock.reserved.max); -} - static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r) { type->total_size -= type->regions[r].size; @@ -184,9 +160,39 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u } } -static int __init_memblock memblock_double_array(struct memblock_type *type) +phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info( + phys_addr_t *addr) +{ + if (memblock.reserved.regions == memblock_reserved_init_regions) + return 0; + + *addr = __pa(memblock.reserved.regions); + + return PAGE_ALIGN(sizeof(struct memblock_region) * + memblock.reserved.max); +} + +/** + * memblock_double_array - double the size of the memblock regions array + * @type: memblock type of the regions array being doubled + * @new_area_start: starting address of memory range to avoid overlap with + * @new_area_size: size of memory range to avoid overlap with + * + * Double the size of the @type regions array. If memblock is being used to + * allocate memory for a new reserved regions array and there is a previously + * allocated memory range [@new_area_start,@new_area_start+@new_area_size] + * waiting to be reserved, ensure the memory used by the new array does + * not overlap. + * + * RETURNS: + * 0 on success, -1 on failure. + */ +static int __init_memblock memblock_double_array(struct memblock_type *type, + phys_addr_t new_area_start, + phys_addr_t new_area_size) { struct memblock_region *new_array, *old_array; + phys_addr_t old_alloc_size, new_alloc_size; phys_addr_t old_size, new_size, addr; int use_slab = slab_is_available(); int *in_slab; @@ -200,6 +206,12 @@ static int __init_memblock memblock_double_array(struct memblock_type *type) /* Calculate new doubled size */ old_size = type->max * sizeof(struct memblock_region); new_size = old_size << 1; + /* + * We need to allocated new one align to PAGE_SIZE, + * so we can free them completely later. + */ + old_alloc_size = PAGE_ALIGN(old_size); + new_alloc_size = PAGE_ALIGN(new_size); /* Retrieve the slab flag */ if (type == &memblock.memory) @@ -222,7 +234,18 @@ static int __init_memblock memblock_double_array(struct memblock_type *type) new_array = kmalloc(new_size, GFP_KERNEL); addr = new_array ? __pa(new_array) : 0; } else { - addr = memblock_find_in_range(0, MEMBLOCK_ALLOC_ACCESSIBLE, new_size, sizeof(phys_addr_t)); + /* only exclude range when trying to double reserved.regions */ + if (type != &memblock.reserved) + new_area_start = new_area_size = 0; + + addr = memblock_find_in_range(new_area_start + new_area_size, + memblock.current_limit, + new_alloc_size, PAGE_SIZE); + if (!addr && new_area_size) + addr = memblock_find_in_range(0, + min(new_area_start, memblock.current_limit), + new_alloc_size, PAGE_SIZE); + new_array = addr ? __va(addr) : 0; } if (!addr) { @@ -251,13 +274,13 @@ static int __init_memblock memblock_double_array(struct memblock_type *type) kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) - memblock_free(__pa(old_array), old_size); + memblock_free(__pa(old_array), old_alloc_size); /* Reserve the new array if that comes from the memblock. * Otherwise, we needn't do it */ if (!use_slab) - BUG_ON(memblock_reserve(addr, new_size)); + BUG_ON(memblock_reserve(addr, new_alloc_size)); /* Update slab flag */ *in_slab = use_slab; @@ -399,7 +422,7 @@ repeat: */ if (!insert) { while (type->cnt + nr_new > type->max) - if (memblock_double_array(type) < 0) + if (memblock_double_array(type, obase, size) < 0) return -ENOMEM; insert = true; goto repeat; @@ -450,7 +473,7 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, /* we'll create at most two more regions */ while (type->cnt + 2 > type->max) - if (memblock_double_array(type) < 0) + if (memblock_double_array(type, base, size) < 0) return -ENOMEM; for (i = 0; i < type->cnt; i++) { @@ -540,9 +563,9 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) * __next_free_mem_range - next function for for_each_free_mem_range() * @idx: pointer to u64 loop variable * @nid: nid: node selector, %MAX_NUMNODES for all nodes - * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL - * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL - * @p_nid: ptr to int for nid of the range, can be %NULL + * @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 * * Find the first free area from *@idx which matches @nid, fill the out * parameters, and update *@idx for the next iteration. The lower 32bit of @@ -616,9 +639,9 @@ 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 - * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL - * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL - * @p_nid: ptr to int for nid of the range, can be %NULL + * @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(). */ @@ -867,6 +890,16 @@ int __init_memblock memblock_is_memory(phys_addr_t addr) return memblock_search(&memblock.memory, addr) != -1; } +/** + * memblock_is_region_memory - check if a region is a subset of memory + * @base: base of region to check + * @size: size of region to check + * + * Check if the region [@base, @base+@size) is a subset of a memory block. + * + * RETURNS: + * 0 if false, non-zero if true + */ int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size) { int idx = memblock_search(&memblock.memory, base); @@ -879,6 +912,16 @@ int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size memblock.memory.regions[idx].size) >= end; } +/** + * memblock_is_region_reserved - check if a region intersects reserved memory + * @base: base of region to check + * @size: size of region to check + * + * Check if the region [@base, @base+@size) intersects a reserved memory block. + * + * RETURNS: + * 0 if false, non-zero if true + */ int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size) { memblock_cap_size(base, &size); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ac35bccadb7..f72b5e52451 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1148,7 +1148,7 @@ bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, { if (root_memcg == memcg) return true; - if (!root_memcg->use_hierarchy) + if (!root_memcg->use_hierarchy || !memcg) return false; return css_is_ancestor(&memcg->css, &root_memcg->css); } @@ -1234,7 +1234,7 @@ int mem_cgroup_inactive_file_is_low(struct lruvec *lruvec) /** * mem_cgroup_margin - calculate chargeable space of a memory cgroup - * @mem: the memory cgroup + * @memcg: the memory cgroup * * Returns the maximum amount of memory @mem can be charged with, in * pages. @@ -1508,7 +1508,7 @@ static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg, /** * test_mem_cgroup_node_reclaimable - * @mem: the target memcg + * @memcg: the target memcg * @nid: the node ID to be checked. * @noswap : specify true here if the user wants flle only information. * diff --git a/mm/memory-failure.c b/mm/memory-failure.c index ab1e7145e29..de4ce705845 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -345,14 +345,14 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, * Also when FAIL is set do a force kill because something went * wrong earlier. */ -static void kill_procs(struct list_head *to_kill, int doit, int trapno, +static void kill_procs(struct list_head *to_kill, int forcekill, int trapno, int fail, struct page *page, unsigned long pfn, int flags) { struct to_kill *tk, *next; list_for_each_entry_safe (tk, next, to_kill, nd) { - if (doit) { + if (forcekill) { /* * In case something went wrong with munmapping * make sure the process doesn't catch the @@ -858,7 +858,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, struct address_space *mapping; LIST_HEAD(tokill); int ret; - int kill = 1; + int kill = 1, forcekill; struct page *hpage = compound_head(p); struct page *ppage; @@ -888,7 +888,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * be called inside page lock (it's recommended but not enforced). */ mapping = page_mapping(hpage); - if (!PageDirty(hpage) && mapping && + if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping && mapping_cap_writeback_dirty(mapping)) { if (page_mkclean(hpage)) { SetPageDirty(hpage); @@ -965,12 +965,14 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * Now that the dirty bit has been propagated to the * struct page and all unmaps done we can decide if * killing is needed or not. Only kill when the page - * was dirty, otherwise the tokill list is merely + * was dirty or the process is not restartable, + * otherwise the tokill list is merely * freed. When there was a problem unmapping earlier * use a more force-full uncatchable kill to prevent * any accesses to the poisoned memory. */ - kill_procs(&tokill, !!PageDirty(ppage), trapno, + forcekill = PageDirty(ppage) || (flags & MF_MUST_KILL); + kill_procs(&tokill, forcekill, trapno, ret != SWAP_SUCCESS, p, pfn, flags); return ret; diff --git a/mm/memory.c b/mm/memory.c index 1b7dc662bf9..91f69459d3e 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -206,6 +206,8 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm) tlb->mm = mm; tlb->fullmm = fullmm; + tlb->start = -1UL; + tlb->end = 0; tlb->need_flush = 0; tlb->fast_mode = (num_possible_cpus() == 1); tlb->local.next = NULL; @@ -248,6 +250,8 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e { struct mmu_gather_batch *batch, *next; + tlb->start = start; + tlb->end = end; tlb_flush_mmu(tlb); /* keep the page table cache within bounds */ @@ -1204,6 +1208,11 @@ again: */ if (force_flush) { force_flush = 0; + +#ifdef HAVE_GENERIC_MMU_GATHER + tlb->start = addr; + tlb->end = end; +#endif tlb_flush_mmu(tlb); if (addr != end) goto again; @@ -1225,7 +1234,15 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) { - VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem)); +#ifdef CONFIG_DEBUG_VM + if (!rwsem_is_locked(&tlb->mm->mmap_sem)) { + pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n", + __func__, addr, end, + vma->vm_start, + vma->vm_end); + BUG(); + } +#endif split_huge_page_pmd(vma->vm_mm, pmd); } else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; @@ -1366,7 +1383,7 @@ void unmap_vmas(struct mmu_gather *tlb, /** * zap_page_range - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages - * @address: starting address of pages to zap + * @start: starting address of pages to zap * @size: number of bytes to zap * @details: details of nonlinear truncation or shared cache invalidation * diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0d7e3ec8e0f..427bb291dd0 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -618,7 +618,7 @@ int __ref add_memory(int nid, u64 start, u64 size) pgdat = hotadd_new_pgdat(nid, start); ret = -ENOMEM; if (!pgdat) - goto out; + goto error; new_pgdat = 1; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f15c1b24ca1..1d771e4200d 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1177,7 +1177,7 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { nr_failed = migrate_pages(&pagelist, new_vma_page, (unsigned long)vma, - false, true); + false, MIGRATE_SYNC); if (nr_failed) putback_lru_pages(&pagelist); } diff --git a/mm/migrate.c b/mm/migrate.c index ab81d482ae6..be26d5cbe56 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -436,7 +436,10 @@ void migrate_page_copy(struct page *newpage, struct page *page) * is actually a signal that all of the page has become dirty. * Whereas only part of our page may be dirty. */ - __set_page_dirty_nobuffers(newpage); + if (PageSwapBacked(page)) + SetPageDirty(newpage); + else + __set_page_dirty_nobuffers(newpage); } mlock_migrate_page(newpage, page); diff --git a/mm/nobootmem.c b/mm/nobootmem.c index d23415c001b..405573010f9 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -105,27 +105,35 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end) __free_pages_bootmem(pfn_to_page(i), 0); } +static unsigned long __init __free_memory_core(phys_addr_t start, + phys_addr_t end) +{ + unsigned long start_pfn = PFN_UP(start); + unsigned long end_pfn = min_t(unsigned long, + PFN_DOWN(end), max_low_pfn); + + if (start_pfn > end_pfn) + return 0; + + __free_pages_memory(start_pfn, end_pfn); + + return end_pfn - start_pfn; +} + unsigned long __init free_low_memory_core_early(int nodeid) { unsigned long count = 0; - phys_addr_t start, end; + phys_addr_t start, end, size; u64 i; - /* free reserved array temporarily so that it's treated as free area */ - memblock_free_reserved_regions(); - - for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) { - unsigned long start_pfn = PFN_UP(start); - unsigned long end_pfn = min_t(unsigned long, - PFN_DOWN(end), max_low_pfn); - if (start_pfn < end_pfn) { - __free_pages_memory(start_pfn, end_pfn); - count += end_pfn - start_pfn; - } - } + for_each_free_mem_range(i, MAX_NUMNODES, &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); - /* put region array back? */ - memblock_reserve_reserved_regions(); return count; } @@ -274,7 +282,7 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align, return ___alloc_bootmem(size, align, goal, limit); } -static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, +void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal, diff --git a/mm/nommu.c b/mm/nommu.c index c4acfbc0997..d4b0c10872d 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1486,7 +1486,7 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); - ret = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); + retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); if (file) fput(file); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index ed0e1967736..ac300c99baf 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -183,7 +183,8 @@ static bool oom_unkillable_task(struct task_struct *p, unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages) { - unsigned long points; + long points; + long adj; if (oom_unkillable_task(p, memcg, nodemask)) return 0; @@ -192,7 +193,8 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, if (!p) return 0; - if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) { + adj = p->signal->oom_score_adj; + if (adj == OOM_SCORE_ADJ_MIN) { task_unlock(p); return 0; } @@ -210,20 +212,17 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, * implementation used by LSMs. */ if (has_capability_noaudit(p, CAP_SYS_ADMIN)) - points -= 30 * totalpages / 1000; + adj -= 30; - /* - * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may - * either completely disable oom killing or always prefer a certain - * task. - */ - points += p->signal->oom_score_adj * totalpages / 1000; + /* Normalize to oom_score_adj units */ + adj *= totalpages / 1000; + points += adj; /* * Never return 0 for an eligible task regardless of the root bonus and * oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here). */ - return points ? points : 1; + return points > 0 ? points : 1; } /* @@ -366,7 +365,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, /** * dump_tasks - dump current memory state of all system tasks - * @mem: current's memory controller, if constrained + * @memcg: current's memory controller, if constrained * @nodemask: nodemask passed to page allocator for mempolicy ooms * * Dumps the current memory state of all eligible tasks. Tasks not in the same diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6092f331b32..4a4f9219683 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -219,7 +219,7 @@ EXPORT_SYMBOL(nr_online_nodes); int page_group_by_mobility_disabled __read_mostly; -void set_pageblock_migratetype(struct page *page, int migratetype) +static void set_pageblock_migratetype(struct page *page, int migratetype) { if (unlikely(page_group_by_mobility_disabled)) @@ -954,8 +954,8 @@ static int move_freepages(struct zone *zone, return pages_moved; } -int move_freepages_block(struct zone *zone, struct page *page, - int migratetype) +static int move_freepages_block(struct zone *zone, struct page *page, + int migratetype) { unsigned long start_pfn, end_pfn; struct page *start_page, *end_page; @@ -5635,7 +5635,12 @@ static struct page * __alloc_contig_migrate_alloc(struct page *page, unsigned long private, int **resultp) { - return alloc_page(GFP_HIGHUSER_MOVABLE); + gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE; + + if (PageHighMem(page)) + gfp_mask |= __GFP_HIGHMEM; + + return alloc_page(gfp_mask); } /* [start, end) must belong to a single zone. */ @@ -5651,7 +5656,7 @@ static int __alloc_contig_migrate_range(unsigned long start, unsigned long end) .nr_migratepages = 0, .order = -1, .zone = page_zone(pfn_to_page(start)), - .mode = COMPACT_SYNC, + .sync = true, }; INIT_LIST_HEAD(&cc.migratepages); diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 1ccbd714059..eb750f85139 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -392,7 +392,7 @@ static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent, /** * swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry. - * @end: swap entry to be cmpxchged + * @ent: swap entry to be cmpxchged * @old: old id * @new: new id * @@ -422,7 +422,7 @@ unsigned short swap_cgroup_cmpxchg(swp_entry_t ent, /** * swap_cgroup_record - record mem_cgroup for this swp_entry. * @ent: swap entry to be recorded into - * @mem: mem_cgroup to be recorded + * @id: mem_cgroup to be recorded * * Returns old value at success, 0 at failure. * (Of course, old value can be 0.) diff --git a/mm/page_io.c b/mm/page_io.c index dc76b4d0611..34f02923744 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -18,6 +18,7 @@ #include <linux/bio.h> #include <linux/swapops.h> #include <linux/writeback.h> +#include <linux/frontswap.h> #include <asm/pgtable.h> static struct bio *get_swap_bio(gfp_t gfp_flags, @@ -98,6 +99,12 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) unlock_page(page); goto out; } + if (frontswap_store(page) == 0) { + set_page_writeback(page); + unlock_page(page); + end_page_writeback(page); + goto out; + } bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write); if (bio == NULL) { set_page_dirty(page); @@ -122,6 +129,11 @@ int swap_readpage(struct page *page) VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(PageUptodate(page)); + if (frontswap_load(page) == 0) { + SetPageUptodate(page); + unlock_page(page); + goto out; + } bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read); if (bio == NULL) { unlock_page(page); diff --git a/mm/pagewalk.c b/mm/pagewalk.c index aa9701e1271..6c118d012bb 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -162,7 +162,6 @@ static int walk_hugetlb_range(struct vm_area_struct *vma, /** * walk_page_range - walk a memory map's page tables with a callback - * @mm: memory map to walk * @addr: starting address * @end: ending address * @walk: set of callbacks to invoke for each level of the tree diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index 405d331804c..3707c71ae4c 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -360,7 +360,6 @@ err_free: * @chunk: chunk to depopulate * @off: offset to the area to depopulate * @size: size of the area to depopulate in bytes - * @flush: whether to flush cache and tlb or not * * For each cpu, depopulate and unmap pages [@page_start,@page_end) * from @chunk. If @flush is true, vcache is flushed before unmapping diff --git a/mm/shmem.c b/mm/shmem.c index 585bd220a21..c15b998e5a8 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -264,46 +264,55 @@ static int shmem_radix_tree_replace(struct address_space *mapping, } /* + * Sometimes, before we decide whether to proceed or to fail, we must check + * that an entry was not already brought back from swap by a racing thread. + * + * Checking page is not enough: by the time a SwapCache page is locked, it + * might be reused, and again be SwapCache, using the same swap as before. + */ +static bool shmem_confirm_swap(struct address_space *mapping, + pgoff_t index, swp_entry_t swap) +{ + void *item; + + rcu_read_lock(); + item = radix_tree_lookup(&mapping->page_tree, index); + rcu_read_unlock(); + return item == swp_to_radix_entry(swap); +} + +/* * Like add_to_page_cache_locked, but error if expected item has gone. */ static int shmem_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp, void *expected) { - int error = 0; + int error; VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(!PageSwapBacked(page)); + page_cache_get(page); + page->mapping = mapping; + page->index = index; + + spin_lock_irq(&mapping->tree_lock); if (!expected) - error = radix_tree_preload(gfp & GFP_RECLAIM_MASK); + error = radix_tree_insert(&mapping->page_tree, index, page); + else + error = shmem_radix_tree_replace(mapping, index, expected, + page); if (!error) { - page_cache_get(page); - page->mapping = mapping; - page->index = index; - - spin_lock_irq(&mapping->tree_lock); - if (!expected) - error = radix_tree_insert(&mapping->page_tree, - index, page); - else - error = shmem_radix_tree_replace(mapping, index, - expected, page); - if (!error) { - mapping->nrpages++; - __inc_zone_page_state(page, NR_FILE_PAGES); - __inc_zone_page_state(page, NR_SHMEM); - spin_unlock_irq(&mapping->tree_lock); - } else { - page->mapping = NULL; - spin_unlock_irq(&mapping->tree_lock); - page_cache_release(page); - } - if (!expected) - radix_tree_preload_end(); + mapping->nrpages++; + __inc_zone_page_state(page, NR_FILE_PAGES); + __inc_zone_page_state(page, NR_SHMEM); + spin_unlock_irq(&mapping->tree_lock); + } else { + page->mapping = NULL; + spin_unlock_irq(&mapping->tree_lock); + page_cache_release(page); } - if (error) - mem_cgroup_uncharge_cache_page(page); return error; } @@ -683,10 +692,21 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, mutex_lock(&shmem_swaplist_mutex); /* * We needed to drop mutex to make that restrictive page - * allocation; but the inode might already be freed by now, - * and we cannot refer to inode or mapping or info to check. - * However, we do hold page lock on the PageSwapCache page, - * so can check if that still has our reference remaining. + * allocation, but the inode might have been freed while we + * dropped it: although a racing shmem_evict_inode() cannot + * complete without emptying the radix_tree, our page lock + * on this swapcache page is not enough to prevent that - + * free_swap_and_cache() of our swap entry will only + * trylock_page(), removing swap from radix_tree whatever. + * + * We must not proceed to shmem_add_to_page_cache() if the + * inode has been freed, but of course we cannot rely on + * inode or mapping or info to check that. However, we can + * safely check if our swap entry is still in use (and here + * it can't have got reused for another page): if it's still + * in use, then the inode cannot have been freed yet, and we + * can safely proceed (if it's no longer in use, that tells + * nothing about the inode, but we don't need to unuse swap). */ if (!page_swapcount(*pagep)) error = -ENOENT; @@ -730,9 +750,9 @@ int shmem_unuse(swp_entry_t swap, struct page *page) /* * There's a faint possibility that swap page was replaced before - * caller locked it: it will come back later with the right page. + * caller locked it: caller will come back later with the right page. */ - if (unlikely(!PageSwapCache(page))) + if (unlikely(!PageSwapCache(page) || page_private(page) != swap.val)) goto out; /* @@ -995,21 +1015,15 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, newpage = shmem_alloc_page(gfp, info, index); if (!newpage) return -ENOMEM; - VM_BUG_ON(shmem_should_replace_page(newpage, gfp)); - *pagep = newpage; page_cache_get(newpage); copy_highpage(newpage, oldpage); + flush_dcache_page(newpage); - VM_BUG_ON(!PageLocked(oldpage)); __set_page_locked(newpage); - VM_BUG_ON(!PageUptodate(oldpage)); SetPageUptodate(newpage); - VM_BUG_ON(!PageSwapBacked(oldpage)); SetPageSwapBacked(newpage); - VM_BUG_ON(!swap_index); set_page_private(newpage, swap_index); - VM_BUG_ON(!PageSwapCache(oldpage)); SetPageSwapCache(newpage); /* @@ -1019,13 +1033,24 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, spin_lock_irq(&swap_mapping->tree_lock); error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage, newpage); - __inc_zone_page_state(newpage, NR_FILE_PAGES); - __dec_zone_page_state(oldpage, NR_FILE_PAGES); + if (!error) { + __inc_zone_page_state(newpage, NR_FILE_PAGES); + __dec_zone_page_state(oldpage, NR_FILE_PAGES); + } spin_unlock_irq(&swap_mapping->tree_lock); - BUG_ON(error); - mem_cgroup_replace_page_cache(oldpage, newpage); - lru_cache_add_anon(newpage); + if (unlikely(error)) { + /* + * Is this possible? I think not, now that our callers check + * both PageSwapCache and page_private after getting page lock; + * but be defensive. Reverse old to newpage for clear and free. + */ + oldpage = newpage; + } else { + mem_cgroup_replace_page_cache(oldpage, newpage); + lru_cache_add_anon(newpage); + *pagep = newpage; + } ClearPageSwapCache(oldpage); set_page_private(oldpage, 0); @@ -1033,7 +1058,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, unlock_page(oldpage); page_cache_release(oldpage); page_cache_release(oldpage); - return 0; + return error; } /* @@ -1107,9 +1132,10 @@ repeat: /* We have to do this with page locked to prevent races */ lock_page(page); - if (!PageSwapCache(page) || page->mapping) { + if (!PageSwapCache(page) || page_private(page) != swap.val || + !shmem_confirm_swap(mapping, index, swap)) { error = -EEXIST; /* try again */ - goto failed; + goto unlock; } if (!PageUptodate(page)) { error = -EIO; @@ -1125,9 +1151,12 @@ repeat: error = mem_cgroup_cache_charge(page, current->mm, gfp & GFP_RECLAIM_MASK); - if (!error) + if (!error) { error = shmem_add_to_page_cache(page, mapping, index, gfp, swp_to_radix_entry(swap)); + /* We already confirmed swap, and make no allocation */ + VM_BUG_ON(error); + } if (error) goto failed; @@ -1164,11 +1193,18 @@ repeat: __set_page_locked(page); error = mem_cgroup_cache_charge(page, current->mm, gfp & GFP_RECLAIM_MASK); - if (!error) - error = shmem_add_to_page_cache(page, mapping, index, - gfp, NULL); if (error) goto decused; + error = radix_tree_preload(gfp & GFP_RECLAIM_MASK); + if (!error) { + error = shmem_add_to_page_cache(page, mapping, index, + gfp, NULL); + radix_tree_preload_end(); + } + if (error) { + mem_cgroup_uncharge_cache_page(page); + goto decused; + } lru_cache_add_anon(page); spin_lock(&info->lock); @@ -1228,14 +1264,10 @@ decused: unacct: shmem_unacct_blocks(info->flags, 1); failed: - if (swap.val && error != -EINVAL) { - struct page *test = find_get_page(mapping, index); - if (test && !radix_tree_exceptional_entry(test)) - page_cache_release(test); - /* Have another try if the entry has changed */ - if (test != swp_to_radix_entry(swap)) - error = -EEXIST; - } + if (swap.val && error != -EINVAL && + !shmem_confirm_swap(mapping, index, swap)) + error = -EEXIST; +unlock: if (page) { unlock_page(page); page_cache_release(page); @@ -1247,7 +1279,7 @@ failed: spin_unlock(&info->lock); goto repeat; } - if (error == -EEXIST) + if (error == -EEXIST) /* from above or from radix_tree_insert */ goto repeat; return error; } @@ -1577,6 +1609,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &page_cache_pipe_buf_ops, .spd_release = spd_release_page, @@ -1665,7 +1698,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, if (spd.nr_pages) error = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); if (error > 0) { *ppos += error; @@ -1674,98 +1707,6 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, return error; } -/* - * llseek SEEK_DATA or SEEK_HOLE through the radix_tree. - */ -static pgoff_t shmem_seek_hole_data(struct address_space *mapping, - pgoff_t index, pgoff_t end, int origin) -{ - struct page *page; - struct pagevec pvec; - pgoff_t indices[PAGEVEC_SIZE]; - bool done = false; - int i; - - 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, pvec.pages, indices); - if (!pvec.nr) { - if (origin == SEEK_DATA) - index = end; - break; - } - for (i = 0; i < pvec.nr; i++, index++) { - if (index < indices[i]) { - if (origin == SEEK_HOLE) { - done = true; - break; - } - index = indices[i]; - } - page = pvec.pages[i]; - if (page && !radix_tree_exceptional_entry(page)) { - if (!PageUptodate(page)) - page = NULL; - } - if (index >= end || - (page && origin == SEEK_DATA) || - (!page && origin == SEEK_HOLE)) { - done = true; - break; - } - } - shmem_deswap_pagevec(&pvec); - pagevec_release(&pvec); - pvec.nr = PAGEVEC_SIZE; - cond_resched(); - } - return index; -} - -static loff_t shmem_file_llseek(struct file *file, loff_t offset, int origin) -{ - struct address_space *mapping; - struct inode *inode; - pgoff_t start, end; - loff_t new_offset; - - if (origin != SEEK_DATA && origin != SEEK_HOLE) - return generic_file_llseek_size(file, offset, origin, - MAX_LFS_FILESIZE); - mapping = file->f_mapping; - inode = mapping->host; - mutex_lock(&inode->i_mutex); - /* We're holding i_mutex so we can access i_size directly */ - - if (offset < 0) - offset = -EINVAL; - else if (offset >= inode->i_size) - offset = -ENXIO; - else { - start = offset >> PAGE_CACHE_SHIFT; - end = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - new_offset = shmem_seek_hole_data(mapping, start, end, origin); - new_offset <<= PAGE_CACHE_SHIFT; - if (new_offset > offset) { - if (new_offset < inode->i_size) - offset = new_offset; - else if (origin == SEEK_DATA) - offset = -ENXIO; - else - offset = inode->i_size; - } - } - - if (offset >= 0 && offset != file->f_pos) { - file->f_pos = offset; - file->f_version = 0; - } - mutex_unlock(&inode->i_mutex); - return offset; -} - static long shmem_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { @@ -1936,7 +1877,7 @@ static int shmem_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) } static int shmem_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { return shmem_mknod(dir, dentry, mode | S_IFREG, 0); } @@ -2769,7 +2710,7 @@ static const struct address_space_operations shmem_aops = { static const struct file_operations shmem_file_operations = { .mmap = shmem_mmap, #ifdef CONFIG_TMPFS - .llseek = shmem_file_llseek, + .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, .aio_read = shmem_file_aio_read, diff --git a/mm/sparse.c b/mm/sparse.c index 6a4bf9160e8..c7bb952400c 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -275,8 +275,9 @@ static unsigned long * __init sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, unsigned long size) { - pg_data_t *host_pgdat; - unsigned long goal; + unsigned long goal, limit; + unsigned long *p; + int nid; /* * A page may contain usemaps for other sections preventing the * page being freed and making a section unremovable while @@ -287,10 +288,17 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, * from the same section as the pgdat where possible to avoid * this problem. */ - goal = __pa(pgdat) & PAGE_SECTION_MASK; - host_pgdat = NODE_DATA(early_pfn_to_nid(goal >> PAGE_SHIFT)); - return __alloc_bootmem_node_nopanic(host_pgdat, size, - SMP_CACHE_BYTES, goal); + goal = __pa(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT); + 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); + if (!p && limit) { + limit = 0; + goto again; + } + return p; } static void __init check_usemap_section_nr(int nid, unsigned long *usemap) diff --git a/mm/swapfile.c b/mm/swapfile.c index 457b10baef5..71373d03fce 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -31,6 +31,8 @@ #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> +#include <linux/frontswap.h> +#include <linux/swapfile.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -42,7 +44,7 @@ static bool swap_count_continued(struct swap_info_struct *, pgoff_t, static void free_swap_count_continuations(struct swap_info_struct *); static sector_t map_swap_entry(swp_entry_t, struct block_device**); -static DEFINE_SPINLOCK(swap_lock); +DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; long nr_swap_pages; long total_swap_pages; @@ -53,9 +55,9 @@ static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; -static struct swap_list_t swap_list = {-1, -1}; +struct swap_list_t swap_list = {-1, -1}; -static struct swap_info_struct *swap_info[MAX_SWAPFILES]; +struct swap_info_struct *swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); @@ -556,6 +558,7 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, swap_list.next = p->type; nr_swap_pages++; p->inuse_pages--; + frontswap_invalidate_page(p->type, offset); if ((p->flags & SWP_BLKDEV) && disk->fops->swap_slot_free_notify) disk->fops->swap_slot_free_notify(p->bdev, offset); @@ -985,11 +988,12 @@ static int unuse_mm(struct mm_struct *mm, } /* - * Scan swap_map from current position to next entry still in use. + * Scan swap_map (or frontswap_map if frontswap parameter is true) + * from current position to next entry still in use. * Recycle to start on reaching the end, returning 0 when empty. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, - unsigned int prev) + unsigned int prev, bool frontswap) { unsigned int max = si->max; unsigned int i = prev; @@ -1015,6 +1019,12 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, prev = 0; i = 1; } + if (frontswap) { + if (frontswap_test(si, i)) + break; + else + continue; + } count = si->swap_map[i]; if (count && swap_count(count) != SWAP_MAP_BAD) break; @@ -1026,8 +1036,12 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, * We completely avoid races by reading each swap page in advance, * and then search for the process using it. All the necessary * page table adjustments can then be made atomically. + * + * if the boolean frontswap is true, only unuse pages_to_unuse pages; + * pages_to_unuse==0 means all pages; ignored if frontswap is false */ -static int try_to_unuse(unsigned int type) +int try_to_unuse(unsigned int type, bool frontswap, + unsigned long pages_to_unuse) { struct swap_info_struct *si = swap_info[type]; struct mm_struct *start_mm; @@ -1060,7 +1074,7 @@ static int try_to_unuse(unsigned int type) * one pass through swap_map is enough, but not necessarily: * there are races when an instance of an entry might be missed. */ - while ((i = find_next_to_unuse(si, i)) != 0) { + while ((i = find_next_to_unuse(si, i, frontswap)) != 0) { if (signal_pending(current)) { retval = -EINTR; break; @@ -1227,6 +1241,10 @@ static int try_to_unuse(unsigned int type) * interactive performance. */ cond_resched(); + if (frontswap && pages_to_unuse > 0) { + if (!--pages_to_unuse) + break; + } } mmput(start_mm); @@ -1486,7 +1504,8 @@ bad_bmap: } static void enable_swap_info(struct swap_info_struct *p, int prio, - unsigned char *swap_map) + unsigned char *swap_map, + unsigned long *frontswap_map) { int i, prev; @@ -1496,6 +1515,7 @@ static void enable_swap_info(struct swap_info_struct *p, int prio, else p->prio = --least_priority; p->swap_map = swap_map; + frontswap_map_set(p, frontswap_map); p->flags |= SWP_WRITEOK; nr_swap_pages += p->pages; total_swap_pages += p->pages; @@ -1512,6 +1532,7 @@ static void enable_swap_info(struct swap_info_struct *p, int prio, swap_list.head = swap_list.next = p->type; else swap_info[prev]->next = p->type; + frontswap_init(p->type); spin_unlock(&swap_lock); } @@ -1585,7 +1606,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX); - err = try_to_unuse(type); + err = try_to_unuse(type, false, 0); /* force all pages to be unused */ compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, oom_score_adj); if (err) { @@ -1596,7 +1617,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) * sys_swapoff for this swap_info_struct at this point. */ /* re-insert swap space back into swap_list */ - enable_swap_info(p, p->prio, p->swap_map); + enable_swap_info(p, p->prio, p->swap_map, frontswap_map_get(p)); goto out_dput; } @@ -1622,9 +1643,11 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) swap_map = p->swap_map; p->swap_map = NULL; p->flags = 0; + frontswap_invalidate_area(type); spin_unlock(&swap_lock); mutex_unlock(&swapon_mutex); vfree(swap_map); + vfree(frontswap_map_get(p)); /* Destroy swap account informatin */ swap_cgroup_swapoff(type); @@ -1893,24 +1916,20 @@ static unsigned long read_swap_header(struct swap_info_struct *p, /* * Find out how many pages are allowed for a single swap - * device. There are three limiting factors: 1) the number + * device. There are two limiting factors: 1) the number * of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte as defined by the - * the different architectures, and 3) the number of free bits - * in an exceptional radix_tree entry. In order to find the + * different architectures. In order to find the * largest possible bit mask, a swap entry with swap type 0 * and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap * offset is extracted. This will mask all the bits from * the initial ~0UL mask that can't be encoded in either * the swp_entry_t or the architecture definition of a - * swap pte. Then the same is done for a radix_tree entry. + * swap pte. */ maxpages = swp_offset(pte_to_swp_entry( - swp_entry_to_pte(swp_entry(0, ~0UL)))); - maxpages = swp_offset(radix_to_swp_entry( - swp_to_radix_entry(swp_entry(0, maxpages)))) + 1; - + swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; if (maxpages > swap_header->info.last_page) { maxpages = swap_header->info.last_page + 1; /* p->max is an unsigned int: don't overflow it */ @@ -1988,6 +2007,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; + unsigned long *frontswap_map = NULL; struct page *page = NULL; struct inode *inode = NULL; @@ -2071,6 +2091,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = nr_extents; goto bad_swap; } + /* frontswap enabled? set up bit-per-page map for frontswap */ + if (frontswap_enabled) + frontswap_map = vzalloc(maxpages / sizeof(long)); if (p->bdev) { if (blk_queue_nonrot(bdev_get_queue(p->bdev))) { @@ -2086,14 +2109,15 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; - enable_swap_info(p, prio, swap_map); + enable_swap_info(p, prio, swap_map, frontswap_map); printk(KERN_INFO "Adding %uk swap on %s. " - "Priority:%d extents:%d across:%lluk %s%s\n", + "Priority:%d extents:%d across:%lluk %s%s%s\n", p->pages<<(PAGE_SHIFT-10), name, p->prio, nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), (p->flags & SWP_SOLIDSTATE) ? "SS" : "", - (p->flags & SWP_DISCARDABLE) ? "D" : ""); + (p->flags & SWP_DISCARDABLE) ? "D" : "", + (frontswap_map) ? "FS" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 2aad49981b5..e03f4c7307a 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1280,7 +1280,7 @@ DEFINE_RWLOCK(vmlist_lock); struct vm_struct *vmlist; static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, - unsigned long flags, void *caller) + unsigned long flags, const void *caller) { vm->flags = flags; vm->addr = (void *)va->va_start; @@ -1306,7 +1306,7 @@ static void insert_vmalloc_vmlist(struct vm_struct *vm) } static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, - unsigned long flags, void *caller) + unsigned long flags, const void *caller) { setup_vmalloc_vm(vm, va, flags, caller); insert_vmalloc_vmlist(vm); @@ -1314,7 +1314,7 @@ static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long flags, unsigned long start, - unsigned long end, int node, gfp_t gfp_mask, void *caller) + unsigned long end, int node, gfp_t gfp_mask, const void *caller) { struct vmap_area *va; struct vm_struct *area; @@ -1375,7 +1375,7 @@ EXPORT_SYMBOL_GPL(__get_vm_area); struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, - void *caller) + const void *caller) { return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL, caller); @@ -1397,13 +1397,21 @@ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) } struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, - void *caller) + const void *caller) { return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, -1, GFP_KERNEL, caller); } -static struct vm_struct *find_vm_area(const void *addr) +/** + * find_vm_area - find a continuous kernel virtual area + * @addr: base address + * + * Search for the kernel VM area starting at @addr, and return it. + * It is up to the caller to do all required locking to keep the returned + * pointer valid. + */ +struct vm_struct *find_vm_area(const void *addr) { struct vmap_area *va; @@ -1568,9 +1576,9 @@ EXPORT_SYMBOL(vmap); static void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, pgprot_t prot, - int node, void *caller); + int node, const void *caller); static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, - pgprot_t prot, int node, void *caller) + pgprot_t prot, int node, const void *caller) { const int order = 0; struct page **pages; @@ -1643,7 +1651,7 @@ fail: */ void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, - pgprot_t prot, int node, void *caller) + pgprot_t prot, int node, const void *caller) { struct vm_struct *area; void *addr; @@ -1699,7 +1707,7 @@ fail: */ static void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, pgprot_t prot, - int node, void *caller) + int node, const void *caller) { return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, gfp_mask, prot, node, caller); @@ -1975,9 +1983,7 @@ static int aligned_vwrite(char *buf, char *addr, unsigned long count) * IOREMAP area is treated as memory hole and no copy is done. * * If [addr...addr+count) doesn't includes any intersects with alive - * vm_struct area, returns 0. - * @buf should be kernel's buffer. Because this function uses KM_USER0, - * the caller should guarantee KM_USER0 is not used. + * vm_struct area, returns 0. @buf should be kernel's buffer. * * Note: In usual ops, vread() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). @@ -2051,9 +2057,7 @@ finished: * IOREMAP area is treated as memory hole and no copy is done. * * If [addr...addr+count) doesn't includes any intersects with alive - * vm_struct area, returns 0. - * @buf should be kernel's buffer. Because this function uses KM_USER0, - * the caller should guarantee KM_USER0 is not used. + * vm_struct area, returns 0. @buf should be kernel's buffer. * * Note: In usual ops, vwrite() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). diff --git a/mm/vmscan.c b/mm/vmscan.c index eeb3bc9d1d3..347b3ff2a47 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1567,7 +1567,8 @@ static int vmscan_swappiness(struct scan_control *sc) * by looking at the fraction of the pages scanned we did rotate back * onto the active list instead of evict. * - * nr[0] = anon pages to scan; nr[1] = file pages to scan + * nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan + * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan */ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) @@ -2537,7 +2538,7 @@ loop_again: * consider it to be no longer congested. It's * possible there are dirty pages backed by * congested BDIs but as pressure is relieved, - * spectulatively avoid congestion waits + * speculatively avoid congestion waits */ zone_clear_flag(zone, ZONE_CONGESTED); if (i <= *classzone_idx) @@ -2688,7 +2689,10 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) * them before going back to sleep. */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); - schedule(); + + if (!kthread_should_stop()) + schedule(); + set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); } else { if (remaining) @@ -2955,14 +2959,17 @@ int kswapd_run(int nid) } /* - * Called by memory hotplug when all memory in a node is offlined. + * Called by memory hotplug when all memory in a node is offlined. Caller must + * hold lock_memory_hotplug(). */ void kswapd_stop(int nid) { struct task_struct *kswapd = NODE_DATA(nid)->kswapd; - if (kswapd) + if (kswapd) { kthread_stop(kswapd); + NODE_DATA(nid)->kswapd = NULL; + } } static int __init kswapd_init(void) |