diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig | 5 | ||||
-rw-r--r-- | mm/Makefile | 2 | ||||
-rw-r--r-- | mm/bounce.c | 4 | ||||
-rw-r--r-- | mm/compaction.c | 376 | ||||
-rw-r--r-- | mm/filemap.c | 470 | ||||
-rw-r--r-- | mm/fremap.c | 28 | ||||
-rw-r--r-- | mm/frontswap.c | 17 | ||||
-rw-r--r-- | mm/highmem.c | 6 | ||||
-rw-r--r-- | mm/huge_memory.c | 139 | ||||
-rw-r--r-- | mm/hugetlb.c | 89 | ||||
-rw-r--r-- | mm/internal.h | 23 | ||||
-rw-r--r-- | mm/kmemleak.c | 4 | ||||
-rw-r--r-- | mm/ksm.c | 1 | ||||
-rw-r--r-- | mm/madvise.c | 2 | ||||
-rw-r--r-- | mm/memcontrol.c | 60 | ||||
-rw-r--r-- | mm/memory-failure.c | 94 | ||||
-rw-r--r-- | mm/memory.c | 97 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 2 | ||||
-rw-r--r-- | mm/mempolicy.c | 80 | ||||
-rw-r--r-- | mm/migrate.c | 63 | ||||
-rw-r--r-- | mm/mincore.c | 20 | ||||
-rw-r--r-- | mm/mlock.c | 2 | ||||
-rw-r--r-- | mm/mmap.c | 72 | ||||
-rw-r--r-- | mm/mmu_context.c | 2 | ||||
-rw-r--r-- | mm/mremap.c | 9 | ||||
-rw-r--r-- | mm/nommu.c | 24 | ||||
-rw-r--r-- | mm/oom_kill.c | 80 | ||||
-rw-r--r-- | mm/page-writeback.c | 23 | ||||
-rw-r--r-- | mm/page_alloc.c | 712 | ||||
-rw-r--r-- | mm/page_cgroup.c | 12 | ||||
-rw-r--r-- | mm/percpu-vm.c | 22 | ||||
-rw-r--r-- | mm/percpu.c | 2 | ||||
-rw-r--r-- | mm/readahead.c | 37 | ||||
-rw-r--r-- | mm/rmap.c | 43 | ||||
-rw-r--r-- | mm/shmem.c | 241 | ||||
-rw-r--r-- | mm/slab.c | 23 | ||||
-rw-r--r-- | mm/slab.h | 4 | ||||
-rw-r--r-- | mm/slab_common.c | 2 | ||||
-rw-r--r-- | mm/slub.c | 142 | ||||
-rw-r--r-- | mm/swap.c | 135 | ||||
-rw-r--r-- | mm/swap_state.c | 65 | ||||
-rw-r--r-- | mm/swapfile.c | 224 | ||||
-rw-r--r-- | mm/truncate.c | 130 | ||||
-rw-r--r-- | mm/util.c | 9 | ||||
-rw-r--r-- | mm/vmacache.c | 114 | ||||
-rw-r--r-- | mm/vmalloc.c | 33 | ||||
-rw-r--r-- | mm/vmpressure.c | 8 | ||||
-rw-r--r-- | mm/vmscan.c | 225 | ||||
-rw-r--r-- | mm/vmstat.c | 19 |
49 files changed, 2448 insertions, 1548 deletions
@@ -254,6 +254,9 @@ config MIGRATION pages as migration can relocate pages to satisfy a huge page allocation instead of reclaiming. +config ARCH_ENABLE_HUGEPAGE_MIGRATION + boolean + config PHYS_ADDR_T_64BIT def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT @@ -384,7 +387,7 @@ config NOMMU_INITIAL_TRIM_EXCESS config TRANSPARENT_HUGEPAGE bool "Transparent Hugepage Support" - depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT_FULL + depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE select COMPACTION help Transparent Hugepages allows the kernel to use huge pages and diff --git a/mm/Makefile b/mm/Makefile index 305d10a..fb51bc6 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -16,7 +16,7 @@ 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 \ + compaction.o balloon_compaction.o vmacache.o \ interval_tree.o list_lru.o $(mmu-y) obj-y += init-mm.o diff --git a/mm/bounce.c b/mm/bounce.c index b09bb4e..5a7d58f 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -51,11 +51,11 @@ static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom) unsigned long flags; unsigned char *vto; - local_irq_save_nort(flags); + local_irq_save(flags); vto = kmap_atomic(to->bv_page); memcpy(vto + to->bv_offset, vfrom, to->bv_len); kunmap_atomic(vto); - local_irq_restore_nort(flags); + local_irq_restore(flags); } #else /* CONFIG_HIGHMEM */ diff --git a/mm/compaction.c b/mm/compaction.c index d2c6751..adb6d05 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -89,7 +89,8 @@ static void __reset_isolation_suitable(struct zone *zone) unsigned long end_pfn = zone_end_pfn(zone); unsigned long pfn; - zone->compact_cached_migrate_pfn = start_pfn; + zone->compact_cached_migrate_pfn[0] = start_pfn; + zone->compact_cached_migrate_pfn[1] = start_pfn; zone->compact_cached_free_pfn = end_pfn; zone->compact_blockskip_flush = false; @@ -131,9 +132,10 @@ void reset_isolation_suitable(pg_data_t *pgdat) */ static void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long nr_isolated, - bool migrate_scanner) + bool set_unsuitable, bool migrate_scanner) { struct zone *zone = cc->zone; + unsigned long pfn; if (cc->ignore_skip_hint) return; @@ -141,20 +143,32 @@ static void update_pageblock_skip(struct compact_control *cc, if (!page) return; - if (!nr_isolated) { - unsigned long pfn = page_to_pfn(page); + if (nr_isolated) + return; + + /* + * Only skip pageblocks when all forms of compaction will be known to + * fail in the near future. + */ + if (set_unsuitable) set_pageblock_skip(page); - /* Update where compaction should restart */ - if (migrate_scanner) { - if (!cc->finished_update_migrate && - pfn > zone->compact_cached_migrate_pfn) - zone->compact_cached_migrate_pfn = pfn; - } else { - if (!cc->finished_update_free && - pfn < zone->compact_cached_free_pfn) - zone->compact_cached_free_pfn = pfn; - } + pfn = page_to_pfn(page); + + /* Update where async and sync compaction should restart */ + if (migrate_scanner) { + if (cc->finished_update_migrate) + return; + if (pfn > zone->compact_cached_migrate_pfn[0]) + zone->compact_cached_migrate_pfn[0] = pfn; + if (cc->mode != MIGRATE_ASYNC && + pfn > zone->compact_cached_migrate_pfn[1]) + zone->compact_cached_migrate_pfn[1] = pfn; + } else { + if (cc->finished_update_free) + return; + if (pfn < zone->compact_cached_free_pfn) + zone->compact_cached_free_pfn = pfn; } } #else @@ -166,7 +180,7 @@ static inline bool isolation_suitable(struct compact_control *cc, static void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long nr_isolated, - bool migrate_scanner) + bool set_unsuitable, bool migrate_scanner) { } #endif /* CONFIG_COMPACTION */ @@ -195,7 +209,7 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags, } /* async aborts if taking too long or contended */ - if (!cc->sync) { + if (cc->mode == MIGRATE_ASYNC) { cc->contended = true; return false; } @@ -208,30 +222,39 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags, return true; } -static inline bool compact_trylock_irqsave(spinlock_t *lock, - unsigned long *flags, struct compact_control *cc) +/* + * Aside from avoiding lock contention, compaction also periodically checks + * need_resched() and either schedules in sync compaction or aborts async + * compaction. This is similar to what compact_checklock_irqsave() does, but + * is used where no lock is concerned. + * + * Returns false when no scheduling was needed, or sync compaction scheduled. + * Returns true when async compaction should abort. + */ +static inline bool compact_should_abort(struct compact_control *cc) { - return compact_checklock_irqsave(lock, flags, false, cc); + /* async compaction aborts if contended */ + if (need_resched()) { + if (cc->mode == MIGRATE_ASYNC) { + cc->contended = true; + return true; + } + + cond_resched(); + } + + return false; } /* 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 */ @@ -254,6 +277,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, struct page *cursor, *valid_page = NULL; unsigned long flags; bool locked = false; + bool checked_pageblock = false; cursor = pfn_to_page(blockpfn); @@ -285,8 +309,16 @@ 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)) @@ -330,7 +362,8 @@ isolate_fail: /* Update the pageblock-skip if the whole pageblock was scanned */ if (blockpfn == end_pfn) - update_pageblock_skip(cc, valid_page, total_isolated, false); + update_pageblock_skip(cc, valid_page, total_isolated, true, + false); count_compact_events(COMPACTFREE_SCANNED, nr_scanned); if (total_isolated) @@ -461,11 +494,14 @@ 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 set_unsuitable = true; + const isolate_mode_t mode = (cc->mode == MIGRATE_ASYNC ? + ISOLATE_ASYNC_MIGRATE : 0) | + (unevictable ? ISOLATE_UNEVICTABLE : 0); /* * Ensure that there are not too many pages isolated from the LRU @@ -474,7 +510,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, */ while (unlikely(too_many_isolated(zone))) { /* async migration should just abort */ - if (!cc->sync) + if (cc->mode == MIGRATE_ASYNC) return 0; congestion_wait(BLK_RW_ASYNC, HZ/10); @@ -483,11 +519,13 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, return 0; } + if (compact_should_abort(cc)) + return 0; + /* Time to isolate some pages for migration */ - 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; @@ -526,25 +564,31 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, /* If isolation recently failed, do not retry */ pageblock_nr = low_pfn >> pageblock_order; - if (!isolation_suitable(cc, page)) - goto next_pageblock; + if (last_pageblock_nr != pageblock_nr) { + int mt; + + last_pageblock_nr = pageblock_nr; + if (!isolation_suitable(cc, page)) + goto next_pageblock; + + /* + * For async migration, also only scan in MOVABLE + * blocks. Async migration is optimistic to see if + * the minimum amount of work satisfies the allocation + */ + mt = get_pageblock_migratetype(page); + if (cc->mode == MIGRATE_ASYNC && + !migrate_async_suitable(mt)) { + set_unsuitable = false; + goto next_pageblock; + } + } /* Skip if free */ if (PageBuddy(page)) continue; /* - * For async migration, also only scan in MOVABLE blocks. Async - * migration is optimistic to see if the minimum amount of work - * satisfies the allocation - */ - if (!cc->sync && last_pageblock_nr != pageblock_nr && - !migrate_async_suitable(get_pageblock_migratetype(page))) { - cc->finished_update_migrate = true; - goto next_pageblock; - } - - /* * Check may be lockless but that's ok as we recheck later. * It's possible to migrate LRU pages and balloon pages * Skip any other type of page @@ -553,11 +597,7 @@ 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; @@ -580,6 +620,15 @@ 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); @@ -594,12 +643,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; } - if (!cc->sync) - mode |= ISOLATE_ASYNC_MIGRATE; - - if (unevictable) - mode |= ISOLATE_UNEVICTABLE; - lruvec = mem_cgroup_page_lruvec(page, zone); /* Try isolate the page */ @@ -609,13 +652,14 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, VM_BUG_ON(PageTransCompound(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; @@ -626,7 +670,6 @@ 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); @@ -634,9 +677,13 @@ next_pageblock: if (locked) spin_unlock_irqrestore(&zone->lru_lock, flags); - /* Update the pageblock-skip if the whole pageblock was scanned */ + /* + * Update the pageblock-skip information and cached scanner pfn, + * if the whole pageblock was scanned without isolating any page. + */ if (low_pfn == end_pfn) - update_pageblock_skip(cc, valid_page, nr_isolated, true); + update_pageblock_skip(cc, valid_page, nr_isolated, + set_unsuitable, true); trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); @@ -657,44 +704,48 @@ static void isolate_freepages(struct zone *zone, struct compact_control *cc) { struct page *page; - unsigned long high_pfn, low_pfn, pfn, z_end_pfn, end_pfn; + unsigned long block_start_pfn; /* start of current pageblock */ + unsigned long block_end_pfn; /* end of current pageblock */ + unsigned long low_pfn; /* lowest pfn scanner is able to scan */ int nr_freepages = cc->nr_freepages; struct list_head *freelist = &cc->freepages; /* * Initialise the free scanner. The starting point is where we last - * scanned from (or the end of the zone if starting). The low point - * is the end of the pageblock the migration scanner is using. + * successfully isolated from, zone-cached value, or the end of the + * zone when isolating for the first time. We need this aligned to + * the pageblock boundary, because we do + * block_start_pfn -= pageblock_nr_pages in the for loop. + * For ending point, take care when isolating in last pageblock of a + * a zone which ends in the middle of a pageblock. + * The low boundary is the end of the pageblock the migration scanner + * is using. */ - pfn = cc->free_pfn; - low_pfn = cc->migrate_pfn + pageblock_nr_pages; - - /* - * Take care that if the migration scanner is at the end of the zone - * that the free scanner does not accidentally move to the next zone - * in the next isolation cycle. - */ - high_pfn = min(low_pfn, pfn); - - z_end_pfn = zone_end_pfn(zone); + block_start_pfn = cc->free_pfn & ~(pageblock_nr_pages-1); + block_end_pfn = min(block_start_pfn + pageblock_nr_pages, + zone_end_pfn(zone)); + low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages); /* * 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. */ - for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages; - pfn -= pageblock_nr_pages) { + for (; block_start_pfn >= low_pfn && cc->nr_migratepages > nr_freepages; + block_end_pfn = block_start_pfn, + block_start_pfn -= pageblock_nr_pages) { unsigned long isolated; /* * This can iterate a massively long zone without finding any * suitable migration targets, so periodically check if we need - * to schedule. + * to schedule, or even abort async compaction. */ - cond_resched(); + if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages)) + && compact_should_abort(cc)) + break; - if (!pfn_valid(pfn)) + if (!pfn_valid(block_start_pfn)) continue; /* @@ -704,7 +755,7 @@ static void isolate_freepages(struct zone *zone, * i.e. it's possible that all pages within a zones range of * pages do not belong to a single zone. */ - page = pfn_to_page(pfn); + page = pfn_to_page(block_start_pfn); if (page_zone(page) != zone) continue; @@ -717,35 +768,38 @@ static void isolate_freepages(struct zone *zone, continue; /* Found a block suitable for isolating free pages from */ - isolated = 0; + cc->free_pfn = block_start_pfn; + isolated = isolate_freepages_block(cc, block_start_pfn, + block_end_pfn, freelist, false); + nr_freepages += isolated; /* - * As pfn may not start aligned, pfn+pageblock_nr_page - * may cross a MAX_ORDER_NR_PAGES boundary and miss - * a pfn_valid check. Ensure isolate_freepages_block() - * only scans within a pageblock + * Set a flag that we successfully isolated in this pageblock. + * In the next loop iteration, zone->compact_cached_free_pfn + * will not be updated and thus it will effectively contain the + * highest pageblock we isolated pages from. */ - end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); - end_pfn = min(end_pfn, z_end_pfn); - isolated = isolate_freepages_block(cc, pfn, end_pfn, - freelist, false); - nr_freepages += isolated; + if (isolated) + cc->finished_update_free = true; /* - * Record the highest PFN we isolated pages from. When next - * looking for free pages, the search will restart here as - * page migration may have returned some pages to the allocator + * isolate_freepages_block() might have aborted due to async + * compaction being contended */ - if (isolated) { - cc->finished_update_free = true; - high_pfn = max(high_pfn, pfn); - } + if (cc->contended) + break; } /* 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 (block_start_pfn < low_pfn) + cc->free_pfn = cc->migrate_pfn; + cc->nr_freepages = nr_freepages; } @@ -760,9 +814,13 @@ static struct page *compaction_alloc(struct page *migratepage, struct compact_control *cc = (struct compact_control *)data; struct page *freepage; - /* Isolate free pages if necessary */ + /* + * Isolate free pages if necessary, and if we are not aborting due to + * contention. + */ if (list_empty(&cc->freepages)) { - isolate_freepages(cc->zone, cc); + if (!cc->contended) + isolate_freepages(cc->zone, cc); if (list_empty(&cc->freepages)) return NULL; @@ -776,23 +834,16 @@ static struct page *compaction_alloc(struct page *migratepage, } /* - * We cannot control nr_migratepages and nr_freepages fully when migration is - * running as migrate_pages() has no knowledge of compact_control. When - * migration is complete, we count the number of pages on the lists by hand. + * This is a migrate-callback that "frees" freepages back to the isolated + * freelist. All pages on the freelist are from the same zone, so there is no + * special handling needed for NUMA. */ -static void update_nr_listpages(struct compact_control *cc) +static void compaction_free(struct page *page, unsigned long data) { - int nr_migratepages = 0; - int nr_freepages = 0; - struct page *page; - - list_for_each_entry(page, &cc->migratepages, lru) - nr_migratepages++; - list_for_each_entry(page, &cc->freepages, lru) - nr_freepages++; + struct compact_control *cc = (struct compact_control *)data; - cc->nr_migratepages = nr_migratepages; - cc->nr_freepages = nr_freepages; + list_add(&page->lru, &cc->freepages); + cc->nr_freepages++; } /* possible outcome of isolate_migratepages */ @@ -839,11 +890,16 @@ static int compact_finished(struct zone *zone, unsigned int order; unsigned long watermark; - if (fatal_signal_pending(current)) + if (cc->contended || fatal_signal_pending(current)) return COMPACT_PARTIAL; /* 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[0] = zone->zone_start_pfn; + zone->compact_cached_migrate_pfn[1] = 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 @@ -941,6 +997,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) int ret; unsigned long start_pfn = zone->zone_start_pfn; unsigned long end_pfn = zone_end_pfn(zone); + const bool sync = cc->mode != MIGRATE_ASYNC; ret = compaction_suitable(zone, cc->order); switch (ret) { @@ -954,11 +1011,19 @@ 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. */ - cc->migrate_pfn = zone->compact_cached_migrate_pfn; + cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync]; cc->free_pfn = zone->compact_cached_free_pfn; if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) { cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1); @@ -966,21 +1031,15 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) } if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) { cc->migrate_pfn = start_pfn; - zone->compact_cached_migrate_pfn = cc->migrate_pfn; + zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn; + zone->compact_cached_migrate_pfn[1] = 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(); while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) { - unsigned long nr_migrate, nr_remaining; int err; switch (isolate_migratepages(zone, cc)) { @@ -995,22 +1054,25 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) ; } - nr_migrate = cc->nr_migratepages; + if (!cc->nr_migratepages) + continue; + err = migrate_pages(&cc->migratepages, compaction_alloc, - (unsigned long)cc, - cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC, + compaction_free, (unsigned long)cc, cc->mode, MR_COMPACTION); - update_nr_listpages(cc); - nr_remaining = cc->nr_migratepages; - trace_mm_compaction_migratepages(nr_migrate - nr_remaining, - nr_remaining); + trace_mm_compaction_migratepages(cc->nr_migratepages, err, + &cc->migratepages); - /* Release isolated pages not migrated */ + /* All pages were either migrated or will be released */ + cc->nr_migratepages = 0; 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; } @@ -1022,12 +1084,13 @@ out: cc->nr_freepages -= release_freepages(&cc->freepages); VM_BUG_ON(cc->nr_freepages != 0); + trace_mm_compaction_end(ret); + return ret; } -static unsigned long compact_zone_order(struct zone *zone, - int order, gfp_t gfp_mask, - bool sync, bool *contended) +static unsigned long compact_zone_order(struct zone *zone, int order, + gfp_t gfp_mask, enum migrate_mode mode, bool *contended) { unsigned long ret; struct compact_control cc = { @@ -1036,7 +1099,7 @@ static unsigned long compact_zone_order(struct zone *zone, .order = order, .migratetype = allocflags_to_migratetype(gfp_mask), .zone = zone, - .sync = sync, + .mode = mode, }; INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); @@ -1058,7 +1121,7 @@ int sysctl_extfrag_threshold = 500; * @order: The order of the current allocation * @gfp_mask: The GFP mask of the current allocation * @nodemask: The allowed nodes to allocate from - * @sync: Whether migration is synchronous or not + * @mode: The migration mode for async, sync light, or sync migration * @contended: Return value that is true if compaction was aborted due to lock contention * @page: Optionally capture a free page of the requested order during compaction * @@ -1066,7 +1129,7 @@ int sysctl_extfrag_threshold = 500; */ unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask, - bool sync, bool *contended) + enum migrate_mode mode, bool *contended) { enum zone_type high_zoneidx = gfp_zone(gfp_mask); int may_enter_fs = gfp_mask & __GFP_FS; @@ -1091,7 +1154,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, nodemask) { int status; - status = compact_zone_order(zone, order, gfp_mask, sync, + status = compact_zone_order(zone, order, gfp_mask, mode, contended); rc = max(status, rc); @@ -1127,13 +1190,9 @@ 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; - /* Currently async compaction is never deferred. */ - else if (!ok && cc->sync) - defer_compaction(zone, cc->order); + if (zone_watermark_ok(zone, cc->order, + low_wmark_pages(zone), 0, 0)) + compaction_defer_reset(zone, cc->order, false); } VM_BUG_ON(!list_empty(&cc->freepages)); @@ -1145,7 +1204,7 @@ void compact_pgdat(pg_data_t *pgdat, int order) { struct compact_control cc = { .order = order, - .sync = false, + .mode = MIGRATE_ASYNC, }; if (!order) @@ -1158,7 +1217,8 @@ static void compact_node(int nid) { struct compact_control cc = { .order = -1, - .sync = true, + .mode = MIGRATE_SYNC, + .ignore_skip_hint = true, }; __compact_pgdat(NODE_DATA(nid), &cc); diff --git a/mm/filemap.c b/mm/filemap.c index 3d2d39a..bd08e9b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -192,9 +192,11 @@ static int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ - if (test_and_clear_bit(AS_ENOSPC, &mapping->flags)) + if (test_bit(AS_ENOSPC, &mapping->flags) && + test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; - if (test_and_clear_bit(AS_EIO, &mapping->flags)) + if (test_bit(AS_EIO, &mapping->flags) && + test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } @@ -446,6 +448,29 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(replace_page_cache_page); +static int page_cache_tree_insert(struct address_space *mapping, + struct page *page) +{ + void **slot; + int error; + + slot = radix_tree_lookup_slot(&mapping->page_tree, page->index); + if (slot) { + void *p; + + p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); + if (!radix_tree_exceptional_entry(p)) + return -EEXIST; + radix_tree_replace_slot(slot, page); + mapping->nrpages++; + return 0; + } + error = radix_tree_insert(&mapping->page_tree, page->index, page); + if (!error) + mapping->nrpages++; + return error; +} + /** * add_to_page_cache_locked - add a locked page to the pagecache * @page: page to add @@ -480,11 +505,10 @@ 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); 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); @@ -520,10 +544,10 @@ 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; } @@ -620,8 +644,17 @@ EXPORT_SYMBOL(unlock_page); */ void end_page_writeback(struct page *page) { - if (TestClearPageReclaim(page)) + /* + * TestClearPageReclaim could be used here but it is an atomic + * operation and overkill in this particular case. Failing to + * shuffle a page marked for immediate reclaim is too mild to + * justify taking an atomic operation penalty at the end of + * ever page writeback. + */ + if (PageReclaim(page)) { + ClearPageReclaim(page); rotate_reclaimable_page(page); + } if (!test_clear_page_writeback(page)) BUG(); @@ -686,14 +719,101 @@ 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 +854,30 @@ out: return page; } -EXPORT_SYMBOL(find_get_page); +EXPORT_SYMBOL(find_get_entry); /** - * find_lock_page - locate, pin and lock a pagecache page + * find_lock_entry - locate, pin and lock a page cache entry * @mapping: the address_space to search - * @offset: the page index + * @offset: the page cache 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 locked and with an increased + * refcount. * - * Returns zero if the page was not present. find_lock_page() may sleep. + * 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_page(struct address_space *mapping, pgoff_t offset) +struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset) { struct page *page; repeat: - page = find_get_page(mapping, offset); + page = find_get_entry(mapping, offset); if (page && !radix_tree_exception(page)) { lock_page(page); /* Has the page been truncated? */ @@ -764,44 +890,86 @@ repeat: } return page; } -EXPORT_SYMBOL(find_lock_page); +EXPORT_SYMBOL(find_lock_entry); /** - * find_or_create_page - locate or add a pagecache page - * @mapping: the page's address_space - * @index: the page's index into the mapping - * @gfp_mask: page allocation mode + * pagecache_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * @fgp_flags: PCG flags + * @gfp_mask: gfp mask to use for the page cache data page allocation + * + * Looks up the page cache slot at @mapping & @offset. * - * 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. + * PCG flags modify how the page is returned * - * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic - * allocation! + * FGP_ACCESSED: the page will be marked accessed + * FGP_LOCK: Page is return locked + * FGP_CREAT: If page is not present then 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. Otherwise, %NULL is returned. * - * find_or_create_page() returns the desired page's address, or zero on - * memory exhaustion. + * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even + * if the GFP flags specified for FGP_CREAT are atomic. + * + * If there is a page cache page, it is returned with an increased refcount. */ -struct page *find_or_create_page(struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask) +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, + int fgp_flags, gfp_t gfp_mask) { struct page *page; - int err; + repeat: - page = find_lock_page(mapping, index); - if (!page) { + page = find_get_entry(mapping, offset); + if (radix_tree_exceptional_entry(page)) + page = NULL; + if (!page) + goto no_page; + + if (fgp_flags & FGP_LOCK) { + if (fgp_flags & FGP_NOWAIT) { + if (!trylock_page(page)) { + page_cache_release(page); + return NULL; + } + } else { + lock_page(page); + } + + /* Has the page been truncated? */ + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + page_cache_release(page); + goto repeat; + } + VM_BUG_ON(page->index != offset); + } + + if (page && (fgp_flags & FGP_ACCESSED)) + mark_page_accessed(page); + +no_page: + if (!page && (fgp_flags & FGP_CREAT)) { + int err; + if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping)) + gfp_mask |= __GFP_WRITE; + if (fgp_flags & FGP_NOFS) + gfp_mask &= ~__GFP_FS; + page = __page_cache_alloc(gfp_mask); if (!page) return NULL; - /* - * We want a regular kernel memory (not highmem or DMA etc) - * allocation for the radix tree nodes, but we need to honour - * the context-specific requirements the caller has asked for. - * GFP_RECLAIM_MASK collects those requirements. - */ - err = add_to_page_cache_lru(page, mapping, index, - (gfp_mask & GFP_RECLAIM_MASK)); + + if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK))) + fgp_flags |= FGP_LOCK; + + /* Init accessed so avoit atomic mark_page_accessed later */ + if (fgp_flags & FGP_ACCESSED) + init_page_accessed(page); + + err = add_to_page_cache_lru(page, mapping, offset, + gfp_mask & GFP_RECLAIM_MASK); if (unlikely(err)) { page_cache_release(page); page = NULL; @@ -809,9 +977,80 @@ repeat: goto repeat; } } + return page; } -EXPORT_SYMBOL(find_or_create_page); +EXPORT_SYMBOL(pagecache_get_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 @@ -1031,39 +1270,6 @@ repeat: } EXPORT_SYMBOL(find_get_pages_tag); -/** - * grab_cache_page_nowait - returns locked page at given index in given cache - * @mapping: target address_space - * @index: the page index - * - * Same as grab_cache_page(), but do not wait if the page is unavailable. - * This is intended for speculative data generators, where the data can - * be regenerated if the page couldn't be grabbed. This routine should - * be safe to call while holding the lock for another page. - * - * Clear __GFP_FS when allocating the page to avoid recursion into the fs - * and deadlock against the caller's locked page. - */ -struct page * -grab_cache_page_nowait(struct address_space *mapping, pgoff_t index) -{ - struct page *page = find_get_page(mapping, index); - - if (page) { - if (trylock_page(page)) - return page; - page_cache_release(page); - return NULL; - } - page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS); - if (page && add_to_page_cache_lru(page, mapping, index, GFP_NOFS)) { - page_cache_release(page); - page = NULL; - } - return page; -} -EXPORT_SYMBOL(grab_cache_page_nowait); - /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: @@ -1797,6 +2003,18 @@ 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 +2041,8 @@ repeat: if (err < 0) { page_cache_release(page); page = ERR_PTR(err); + } else { + page = wait_on_page_read(page); } } return page; @@ -1859,6 +2079,10 @@ 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 +2090,25 @@ 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 +2127,10 @@ 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) { @@ -1976,7 +2164,6 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, char *kaddr; size_t copied; - BUG_ON(!pagefault_disabled()); kaddr = kmap_atomic(page); if (likely(i->nr_segs == 1)) { int left; @@ -2186,7 +2373,6 @@ int pagecache_write_end(struct file *file, struct address_space *mapping, { const struct address_space_operations *aops = mapping->a_ops; - mark_page_accessed(page); return aops->write_end(file, mapping, pos, len, copied, page, fsdata); } EXPORT_SYMBOL(pagecache_write_end); @@ -2268,34 +2454,17 @@ EXPORT_SYMBOL(generic_file_direct_write); struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags) { - int status; - gfp_t gfp_mask; struct page *page; - gfp_t gfp_notmask = 0; + int fgp_flags = FGP_LOCK|FGP_ACCESSED|FGP_WRITE|FGP_CREAT; - gfp_mask = mapping_gfp_mask(mapping); - if (mapping_cap_account_dirty(mapping)) - gfp_mask |= __GFP_WRITE; if (flags & AOP_FLAG_NOFS) - gfp_notmask = __GFP_FS; -repeat: - page = find_lock_page(mapping, index); + fgp_flags |= FGP_NOFS; + + page = pagecache_get_page(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); if (page) - goto found; + wait_for_stable_page(page); - page = __page_cache_alloc(gfp_mask & ~gfp_notmask); - if (!page) - return NULL; - status = add_to_page_cache_lru(page, mapping, index, - GFP_KERNEL & ~gfp_notmask); - if (unlikely(status)) { - page_cache_release(page); - if (status == -EEXIST) - goto repeat; - return NULL; - } -found: - wait_for_stable_page(page); return page; } EXPORT_SYMBOL(grab_cache_page_write_begin); @@ -2344,18 +2513,15 @@ again: status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); - if (unlikely(status)) + if (unlikely(status < 0)) break; if (mapping_writably_mapped(mapping)) flush_dcache_page(page); - pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); - pagefault_enable(); flush_dcache_page(page); - mark_page_accessed(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status < 0)) @@ -2555,8 +2721,8 @@ 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 bbc4d66..34feba6 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -23,28 +23,44 @@ #include "internal.h" +static int mm_counter(struct page *page) +{ + return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES; +} + static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t pte = *ptep; + struct page *page; + swp_entry_t entry; if (pte_present(pte)) { - struct page *page; - flush_cache_page(vma, addr, pte_pfn(pte)); pte = ptep_clear_flush(vma, addr, ptep); page = vm_normal_page(vma, addr, pte); if (page) { if (pte_dirty(pte)) set_page_dirty(page); + update_hiwater_rss(mm); + dec_mm_counter(mm, mm_counter(page)); page_remove_rmap(page); page_cache_release(page); + } + } else { /* zap_pte() is not called when pte_none() */ + if (!pte_file(pte)) { update_hiwater_rss(mm); - dec_mm_counter(mm, MM_FILEPAGES); + entry = pte_to_swp_entry(pte); + if (non_swap_entry(entry)) { + if (is_migration_entry(entry)) { + page = migration_entry_to_page(entry); + dec_mm_counter(mm, mm_counter(page)); + } + } else { + free_swap_and_cache(entry); + dec_mm_counter(mm, MM_SWAPENTS); + } } - } else { - if (!pte_file(pte)) - free_swap_and_cache(pte_to_swp_entry(pte)); pte_clear_not_present_full(mm, addr, ptep, 0); } } diff --git a/mm/frontswap.c b/mm/frontswap.c index 1b24bdc..f2a3571 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -244,8 +244,10 @@ int __frontswap_store(struct page *page) the (older) page from frontswap */ inc_frontswap_failed_stores(); - if (dup) + if (dup) { __frontswap_clear(sis, offset); + frontswap_ops->invalidate_page(type, offset); + } } if (frontswap_writethrough_enabled) /* report failure so swap also writes to swap device */ @@ -327,15 +329,12 @@ 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]; + plist_for_each_entry(si, &swap_active_head, list) totalpages += atomic_read(&si->frontswap_pages); - } return totalpages; } @@ -347,11 +346,9 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, 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]; + plist_for_each_entry(si, &swap_active_head, list) { si_frontswap_pages = atomic_read(&si->frontswap_pages); if (total_pages_to_unuse < si_frontswap_pages) { pages = pages_to_unuse = total_pages_to_unuse; @@ -366,7 +363,7 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, } vm_unacct_memory(pages); *unused = pages_to_unuse; - *swapid = type; + *swapid = si->type; ret = 0; break; } @@ -413,7 +410,7 @@ void frontswap_shrink(unsigned long target_pages) /* * 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 + * so restart scan from swap_active_head each time */ spin_lock(&swap_lock); ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type); diff --git a/mm/highmem.c b/mm/highmem.c index b1c7d43..b32b70c 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -29,11 +29,10 @@ #include <linux/kgdb.h> #include <asm/tlbflush.h> -#ifndef CONFIG_PREEMPT_RT_FULL + #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) DEFINE_PER_CPU(int, __kmap_atomic_idx); #endif -#endif /* * Virtual_count is not a pure "count". @@ -48,9 +47,8 @@ DEFINE_PER_CPU(int, __kmap_atomic_idx); unsigned long totalhigh_pages __read_mostly; EXPORT_SYMBOL(totalhigh_pages); -#ifndef CONFIG_PREEMPT_RT_FULL + EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx); -#endif unsigned int nr_free_highpages (void) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 389973f..04535b6 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -192,7 +192,7 @@ retry: preempt_disable(); if (cmpxchg(&huge_zero_page, NULL, zero_page)) { preempt_enable(); - __free_page(zero_page); + __free_pages(zero_page, compound_order(zero_page)); goto retry; } @@ -224,7 +224,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct page *zero_page = xchg(&huge_zero_page, NULL); BUG_ON(zero_page == NULL); - __free_page(zero_page); + __free_pages(zero_page, compound_order(zero_page)); return HPAGE_PMD_NR; } @@ -758,14 +758,6 @@ static inline struct page *alloc_hugepage_vma(int defrag, HPAGE_PMD_ORDER, vma, haddr, nd); } -#ifndef CONFIG_NUMA -static inline struct page *alloc_hugepage(int defrag) -{ - return alloc_pages(alloc_hugepage_gfpmask(defrag, 0), - HPAGE_PMD_ORDER); -} -#endif - static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, struct page *zero_page) @@ -1549,15 +1541,22 @@ pmd_t *page_check_address_pmd(struct page *page, unsigned long address, enum page_check_address_pmd_flag flag) { + pgd_t *pgd; + pud_t *pud; pmd_t *pmd, *ret = NULL; if (address & ~HPAGE_PMD_MASK) goto out; - pmd = mm_find_pmd(mm, address); - if (!pmd) + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + goto out; + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) goto out; - if (pmd_none(*pmd)) + pmd = pmd_offset(pud, address); + + if (!pmd_present(*pmd)) goto out; if (pmd_page(*pmd) != page) goto out; @@ -1748,21 +1747,24 @@ static int __split_huge_page_map(struct page *page, if (pmd) { pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); + if (pmd_write(*pmd)) + BUG_ON(page_mapcount(page) != 1); haddr = address; for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { pte_t *pte, entry; BUG_ON(PageCompound(page+i)); + /* + * Note that pmd_numa is not transferred deliberately + * to avoid any possibility that pte_numa leaks to + * a PROT_NONE VMA by accident. + */ entry = mk_pte(page + i, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (!pmd_write(*pmd)) entry = pte_wrprotect(entry); - else - BUG_ON(page_mapcount(page) != 1); if (!pmd_young(*pmd)) entry = pte_mkold(entry); - if (pmd_numa(*pmd)) - entry = pte_mknuma(entry); pte = pte_offset_map(&_pmd, haddr); BUG_ON(!pte_none(*pte)); set_pte_at(mm, haddr, pte, entry); @@ -2197,7 +2199,58 @@ static void khugepaged_alloc_sleep(void) msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); } +static int khugepaged_node_load[MAX_NUMNODES]; + +static bool khugepaged_scan_abort(int nid) +{ + int i; + + /* + * If zone_reclaim_mode is disabled, then no extra effort is made to + * allocate memory locally. + */ + if (!zone_reclaim_mode) + return false; + + /* If there is a count for this node already, it must be acceptable */ + if (khugepaged_node_load[nid]) + return false; + + for (i = 0; i < MAX_NUMNODES; i++) { + if (!khugepaged_node_load[i]) + continue; + if (node_distance(nid, i) > RECLAIM_DISTANCE) + return true; + } + return false; +} + #ifdef CONFIG_NUMA +static int khugepaged_find_target_node(void) +{ + static int last_khugepaged_target_node = NUMA_NO_NODE; + int nid, target_node = 0, max_value = 0; + + /* find first node with max normal pages hit */ + for (nid = 0; nid < MAX_NUMNODES; nid++) + if (khugepaged_node_load[nid] > max_value) { + max_value = khugepaged_node_load[nid]; + target_node = nid; + } + + /* do some balance if several nodes have the same hit record */ + if (target_node <= last_khugepaged_target_node) + for (nid = last_khugepaged_target_node + 1; nid < MAX_NUMNODES; + nid++) + if (max_value == khugepaged_node_load[nid]) { + target_node = nid; + break; + } + + last_khugepaged_target_node = target_node; + return target_node; +} + static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) { if (IS_ERR(*hpage)) { @@ -2231,9 +2284,8 @@ static struct page * mmap_sem in read mode is good idea also to allow greater * scalability. */ - *hpage = alloc_hugepage_vma(khugepaged_defrag(), vma, address, - node, __GFP_OTHER_NODE); - + *hpage = alloc_pages_exact_node(node, alloc_hugepage_gfpmask( + khugepaged_defrag(), __GFP_OTHER_NODE), HPAGE_PMD_ORDER); /* * After allocating the hugepage, release the mmap_sem read lock in * preparation for taking it in write mode. @@ -2249,6 +2301,17 @@ static struct page return *hpage; } #else +static int khugepaged_find_target_node(void) +{ + return 0; +} + +static inline struct page *alloc_hugepage(int defrag) +{ + return alloc_pages(alloc_hugepage_gfpmask(defrag, 0), + HPAGE_PMD_ORDER); +} + static struct page *khugepaged_alloc_hugepage(bool *wait) { struct page *hpage; @@ -2352,8 +2415,6 @@ static void collapse_huge_page(struct mm_struct *mm, pmd = mm_find_pmd(mm, address); if (!pmd) goto out; - if (pmd_trans_huge(*pmd)) - goto out; anon_vma_lock_write(vma->anon_vma); @@ -2452,9 +2513,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, pmd = mm_find_pmd(mm, address); if (!pmd) goto out; - if (pmd_trans_huge(*pmd)) - goto out; + memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); pte = pte_offset_map_lock(mm, pmd, address, &ptl); for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { @@ -2471,12 +2531,15 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, if (unlikely(!page)) goto out_unmap; /* - * Chose the node of the first page. This could - * be more sophisticated and look at more pages, - * but isn't for now. + * Record which node the original page is from and save this + * information to khugepaged_node_load[]. + * Khupaged will allocate hugepage from the node has the max + * hit record. */ - if (node == NUMA_NO_NODE) - node = page_to_nid(page); + node = page_to_nid(page); + if (khugepaged_scan_abort(node)) + goto out_unmap; + khugepaged_node_load[node]++; VM_BUG_ON(PageCompound(page)); if (!PageLRU(page) || PageLocked(page) || !PageAnon(page)) goto out_unmap; @@ -2491,9 +2554,11 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, ret = 1; out_unmap: pte_unmap_unlock(pte, ptl); - if (ret) + if (ret) { + node = khugepaged_find_target_node(); /* collapse_huge_page will return with the mmap_sem released */ collapse_huge_page(mm, address, hpage, vma, node); + } out: return ret; } @@ -2801,12 +2866,22 @@ void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, static void split_huge_page_address(struct mm_struct *mm, unsigned long address) { + pgd_t *pgd; + pud_t *pud; pmd_t *pmd; VM_BUG_ON(!(address & ~HPAGE_PMD_MASK)); - pmd = mm_find_pmd(mm, address); - if (!pmd) + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + return; + + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + return; + + pmd = pmd_offset(pud, address); + if (!pmd_present(*pmd)) return; /* * Caller holds the mmap_sem write mode, so a huge pmd cannot diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f0a4ca4..c33d8a6 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -574,7 +574,7 @@ 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); @@ -596,7 +596,7 @@ 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; @@ -1177,6 +1177,7 @@ static void return_unused_surplus_pages(struct hstate *h, while (nr_pages--) { if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1)) break; + cond_resched_lock(&hugetlb_lock); } } @@ -1552,6 +1553,7 @@ 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)) @@ -2112,6 +2114,9 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, unsigned long tmp; int ret; + if (!hugepages_supported()) + return -ENOTSUPP; + tmp = h->max_huge_pages; if (write && h->order >= MAX_ORDER) @@ -2165,6 +2170,9 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, unsigned long tmp; int ret; + if (!hugepages_supported()) + return -ENOTSUPP; + tmp = h->nr_overcommit_huge_pages; if (write && h->order >= MAX_ORDER) @@ -2190,6 +2198,8 @@ out: void hugetlb_report_meminfo(struct seq_file *m) { struct hstate *h = &default_hstate; + if (!hugepages_supported()) + return; seq_printf(m, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" @@ -2206,6 +2216,8 @@ void hugetlb_report_meminfo(struct seq_file *m) int hugetlb_report_node_meminfo(int nid, char *buf) { struct hstate *h = &default_hstate; + if (!hugepages_supported()) + return 0; return sprintf(buf, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" @@ -2220,6 +2232,9 @@ void hugetlb_show_meminfo(void) struct hstate *h; int nid; + if (!hugepages_supported()) + return; + for_each_node_state(nid, N_MEMORY) for_each_hstate(h) pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", @@ -2379,6 +2394,31 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma, update_mmu_cache(vma, address, ptep); } +static int is_hugetlb_entry_migration(pte_t pte) +{ + swp_entry_t swp; + + if (huge_pte_none(pte) || pte_present(pte)) + return 0; + swp = pte_to_swp_entry(pte); + if (non_swap_entry(swp) && is_migration_entry(swp)) + return 1; + else + return 0; +} + +static int is_hugetlb_entry_hwpoisoned(pte_t pte) +{ + swp_entry_t swp; + + if (huge_pte_none(pte) || pte_present(pte)) + return 0; + swp = pte_to_swp_entry(pte); + if (non_swap_entry(swp) && is_hwpoison_entry(swp)) + return 1; + else + return 0; +} int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma) @@ -2406,7 +2446,24 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, spin_lock(&dst->page_table_lock); spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING); - if (!huge_pte_none(huge_ptep_get(src_pte))) { + entry = huge_ptep_get(src_pte); + if (huge_pte_none(entry)) { /* skip none entry */ + ; + } else if (unlikely(is_hugetlb_entry_migration(entry) || + is_hugetlb_entry_hwpoisoned(entry))) { + swp_entry_t swp_entry = pte_to_swp_entry(entry); + + if (is_write_migration_entry(swp_entry) && cow) { + /* + * COW mappings require pages in both + * parent and child to be set to read. + */ + make_migration_entry_read(&swp_entry); + entry = swp_entry_to_pte(swp_entry); + set_huge_pte_at(src, addr, src_pte, entry); + } + set_huge_pte_at(dst, addr, dst_pte, entry); + } else { if (cow) huge_ptep_set_wrprotect(src, addr, src_pte); entry = huge_ptep_get(src_pte); @@ -2424,32 +2481,6 @@ nomem: return -ENOMEM; } -static int is_hugetlb_entry_migration(pte_t pte) -{ - swp_entry_t swp; - - if (huge_pte_none(pte) || pte_present(pte)) - return 0; - swp = pte_to_swp_entry(pte); - if (non_swap_entry(swp) && is_migration_entry(swp)) - return 1; - else - return 0; -} - -static int is_hugetlb_entry_hwpoisoned(pte_t pte) -{ - swp_entry_t swp; - - if (huge_pte_none(pte) || pte_present(pte)) - return 0; - swp = pte_to_swp_entry(pte); - if (non_swap_entry(swp) && is_hwpoison_entry(swp)) - return 1; - else - return 0; -} - void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) diff --git a/mm/internal.h b/mm/internal.h index 8b6cfd6..d610f7c 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -11,6 +11,7 @@ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H +#include <linux/fs.h> #include <linux/mm.h> void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, @@ -21,6 +22,20 @@ static inline void set_page_count(struct page *page, int v) atomic_set(&page->_count, v); } +extern int __do_page_cache_readahead(struct address_space *mapping, + struct file *filp, pgoff_t offset, unsigned long nr_to_read, + unsigned long lookahead_size); + +/* + * Submit IO for the read-ahead request in file_ra_state. + */ +static inline unsigned long ra_submit(struct file_ra_state *ra, + struct address_space *mapping, struct file *filp) +{ + return __do_page_cache_readahead(mapping, filp, + ra->start, ra->size, ra->async_size); +} + /* * Turn a non-refcounted page (->_count == 0) into refcounted with * a count of one. @@ -120,7 +135,7 @@ struct compact_control { unsigned long nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ unsigned long migrate_pfn; /* isolate_migratepages search base */ - bool sync; /* Synchronous migration */ + enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool finished_update_free; /* True when the zone cached pfns are * no longer being updated @@ -130,7 +145,10 @@ struct compact_control { int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ struct zone *zone; - bool contended; /* True if a lock was contended */ + bool contended; /* True if a lock was contended, or + * need_resched() true during async + * compaction + */ }; unsigned long @@ -369,5 +387,6 @@ 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 e126b0e..31f01c5 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -753,7 +753,9 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp) } spin_lock_irqsave(&object->lock, flags); - if (ptr + size > object->pointer + object->size) { + if (size == SIZE_MAX) { + size = object->pointer + object->size - ptr; + } else if (ptr + size > object->pointer + object->size) { kmemleak_warn("Scan area larger than object 0x%08lx\n", ptr); dump_object_info(object); kmem_cache_free(scan_area_cache, area); @@ -945,7 +945,6 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, pmd = mm_find_pmd(mm, addr); if (!pmd) goto out; - BUG_ON(pmd_trans_huge(*pmd)); mmun_start = addr; mmun_end = addr + PAGE_SIZE; diff --git a/mm/madvise.c b/mm/madvise.c index 539eeb9..a402f8f 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -195,7 +195,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma, for (; start < end; start += PAGE_SIZE) { index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - page = find_get_page(mapping, index); + page = find_get_entry(mapping, index); if (!radix_tree_exceptional_entry(page)) { if (page) page_cache_release(page); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bc16ebc..ff64896 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -250,6 +250,9 @@ struct mem_cgroup { /* vmpressure notifications */ struct vmpressure vmpressure; + /* css_online() has been completed */ + int initialized; + /* * the counter to account for mem+swap usage. */ @@ -1089,9 +1092,23 @@ skip_node: * skipping css reference should be safe. */ if (next_css) { - if ((next_css == &root->css) || - ((next_css->flags & CSS_ONLINE) && css_tryget(next_css))) - return mem_cgroup_from_css(next_css); + struct mem_cgroup *memcg = mem_cgroup_from_css(next_css); + + if (next_css == &root->css) + return memcg; + + if (css_tryget(next_css)) { + if (memcg->initialized) { + /* + * Make sure the memcg is initialized: + * mem_cgroup_css_online() orders the the + * initialization against setting the flag. + */ + smp_rmb(); + return memcg; + } + css_put(next_css); + } prev_css = next_css; goto skip_node; @@ -1820,13 +1837,18 @@ 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); } @@ -2473,7 +2495,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync) /* Notify other cpus that system-wide "drain" is running */ get_online_cpus(); - curcpu = get_cpu_light(); + curcpu = get_cpu(); for_each_online_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); struct mem_cgroup *memcg; @@ -2490,7 +2512,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync) schedule_work_on(cpu, &stock->work); } } - put_cpu_light(); + put_cpu(); if (!sync) goto out; @@ -5643,8 +5665,12 @@ static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg) { struct mem_cgroup_eventfd_list *ev; + spin_lock(&memcg_oom_lock); + list_for_each_entry(ev, &memcg->oom_notify, list) eventfd_signal(ev->eventfd, 1); + + spin_unlock(&memcg_oom_lock); return 0; } @@ -6322,6 +6348,16 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) error = memcg_init_kmem(memcg, &mem_cgroup_subsys); mutex_unlock(&memcg_create_mutex); + + if (!error) { + /* + * Make sure the memcg is initialized: mem_cgroup_iter() + * orders reading memcg->initialized against its callers + * reading the memcg members. + */ + smp_wmb(); + memcg->initialized = 1; + } return error; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 5ea3cf7..4ab233d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -208,9 +208,9 @@ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno, #endif si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT; - if ((flags & MF_ACTION_REQUIRED) && t == current) { + if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) { si.si_code = BUS_MCEERR_AR; - ret = force_sig_info(SIGBUS, &si, t); + ret = force_sig_info(SIGBUS, &si, current); } else { /* * Don't use force here, it's convenient if the signal @@ -384,20 +384,51 @@ static void kill_procs(struct list_head *to_kill, int forcekill, int trapno, } } -static int task_early_kill(struct task_struct *tsk) +/* + * Find a dedicated thread which is supposed to handle SIGBUS(BUS_MCEERR_AO) + * on behalf of the thread group. Return task_struct of the (first found) + * dedicated thread if found, and return NULL otherwise. + * + * We already hold read_lock(&tasklist_lock) in the caller, so we don't + * have to call rcu_read_lock/unlock() in this function. + */ +static struct task_struct *find_early_kill_thread(struct task_struct *tsk) { + struct task_struct *t; + + for_each_thread(tsk, t) + if ((t->flags & PF_MCE_PROCESS) && (t->flags & PF_MCE_EARLY)) + return t; + return NULL; +} + +/* + * Determine whether a given process is "early kill" process which expects + * to be signaled when some page under the process is hwpoisoned. + * Return task_struct of the dedicated thread (main thread unless explicitly + * specified) if the process is "early kill," and otherwise returns NULL. + */ +static struct task_struct *task_early_kill(struct task_struct *tsk, + int force_early) +{ + struct task_struct *t; if (!tsk->mm) - return 0; - if (tsk->flags & PF_MCE_PROCESS) - return !!(tsk->flags & PF_MCE_EARLY); - return sysctl_memory_failure_early_kill; + return NULL; + if (force_early) + return tsk; + t = find_early_kill_thread(tsk); + if (t) + return t; + if (sysctl_memory_failure_early_kill) + return tsk; + return NULL; } /* * Collect processes when the error hit an anonymous page. */ static void collect_procs_anon(struct page *page, struct list_head *to_kill, - struct to_kill **tkc) + struct to_kill **tkc, int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; @@ -412,16 +443,17 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, read_lock(&tasklist_lock); for_each_process (tsk) { struct anon_vma_chain *vmac; + struct task_struct *t = task_early_kill(tsk, force_early); - if (!task_early_kill(tsk)) + if (!t) continue; anon_vma_interval_tree_foreach(vmac, &av->rb_root, pgoff, pgoff) { vma = vmac->vma; if (!page_mapped_in_vma(page, vma)) continue; - if (vma->vm_mm == tsk->mm) - add_to_kill(tsk, page, vma, to_kill, tkc); + if (vma->vm_mm == t->mm) + add_to_kill(t, page, vma, to_kill, tkc); } } read_unlock(&tasklist_lock); @@ -432,7 +464,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, * Collect processes when the error hit a file mapped page. */ static void collect_procs_file(struct page *page, struct list_head *to_kill, - struct to_kill **tkc) + struct to_kill **tkc, int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; @@ -442,10 +474,10 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, read_lock(&tasklist_lock); for_each_process(tsk) { pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + struct task_struct *t = task_early_kill(tsk, force_early); - if (!task_early_kill(tsk)) + if (!t) continue; - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { /* @@ -455,8 +487,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, * Assume applications who requested early kill want * to be informed of all such data corruptions. */ - if (vma->vm_mm == tsk->mm) - add_to_kill(tsk, page, vma, to_kill, tkc); + if (vma->vm_mm == t->mm) + add_to_kill(t, page, vma, to_kill, tkc); } } read_unlock(&tasklist_lock); @@ -469,7 +501,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, * First preallocate one tokill structure outside the spin locks, * so that we can kill at least one process reasonably reliable. */ -static void collect_procs(struct page *page, struct list_head *tokill) +static void collect_procs(struct page *page, struct list_head *tokill, + int force_early) { struct to_kill *tk; @@ -480,9 +513,9 @@ static void collect_procs(struct page *page, struct list_head *tokill) if (!tk) return; if (PageAnon(page)) - collect_procs_anon(page, tokill, &tk); + collect_procs_anon(page, tokill, &tk, force_early); else - collect_procs_file(page, tokill, &tk); + collect_procs_file(page, tokill, &tk, force_early); kfree(tk); } @@ -967,7 +1000,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * there's nothing that can be done. */ if (kill) - collect_procs(ppage, &tokill); + collect_procs(ppage, &tokill, flags & MF_ACTION_REQUIRED); ret = try_to_unmap(ppage, ttu); if (ret != SWAP_SUCCESS) @@ -1085,15 +1118,16 @@ int memory_failure(unsigned long pfn, int trapno, int flags) return 0; } else if (PageHuge(hpage)) { /* - * Check "just unpoisoned", "filter hit", and - * "race with other subpage." + * Check "filter hit" and "race with other subpage." */ lock_page(hpage); - if (!PageHWPoison(hpage) - || (hwpoison_filter(p) && TestClearPageHWPoison(p)) - || (p != hpage && TestSetPageHWPoison(hpage))) { - atomic_long_sub(nr_pages, &num_poisoned_pages); - return 0; + if (PageHWPoison(hpage)) { + if ((hwpoison_filter(p) && TestClearPageHWPoison(p)) + || (p != hpage && TestSetPageHWPoison(hpage))) { + atomic_long_sub(nr_pages, &num_poisoned_pages); + unlock_page(hpage); + return 0; + } } set_page_hwpoison_huge_page(hpage); res = dequeue_hwpoisoned_huge_page(hpage); @@ -1156,6 +1190,8 @@ int memory_failure(unsigned long pfn, int trapno, int flags) */ if (!PageHWPoison(p)) { printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn); + atomic_long_sub(nr_pages, &num_poisoned_pages); + put_page(hpage); res = 0; goto out; } @@ -1518,7 +1554,7 @@ static int soft_offline_huge_page(struct page *page, int flags) /* Keep page count to indicate a given hugepage is isolated. */ list_move(&hpage->lru, &pagelist); - ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, + ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { pr_info("soft offline: %#lx: migration failed %d, type %lx\n", @@ -1599,7 +1635,7 @@ static int __soft_offline_page(struct page *page, int flags) inc_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); list_add(&page->lru, &pagelist); - ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, + ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { putback_lru_pages(&pagelist); diff --git a/mm/memory.c b/mm/memory.c index 0dcdc84..db2916f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -808,20 +808,20 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (!pte_file(pte)) { swp_entry_t entry = pte_to_swp_entry(pte); - if (swap_duplicate(entry) < 0) - return entry.val; - - /* make sure dst_mm is on swapoff's mmlist. */ - if (unlikely(list_empty(&dst_mm->mmlist))) { - spin_lock(&mmlist_lock); - if (list_empty(&dst_mm->mmlist)) - list_add(&dst_mm->mmlist, - &src_mm->mmlist); - spin_unlock(&mmlist_lock); - } - if (likely(!non_swap_entry(entry))) + if (likely(!non_swap_entry(entry))) { + if (swap_duplicate(entry) < 0) + return entry.val; + + /* make sure dst_mm is on swapoff's mmlist. */ + if (unlikely(list_empty(&dst_mm->mmlist))) { + spin_lock(&mmlist_lock); + if (list_empty(&dst_mm->mmlist)) + list_add(&dst_mm->mmlist, + &src_mm->mmlist); + spin_unlock(&mmlist_lock); + } rss[MM_SWAPENTS]++; - else if (is_migration_entry(entry)) { + } else if (is_migration_entry(entry)) { page = migration_entry_to_page(entry); if (PageAnon(page)) @@ -878,7 +878,7 @@ out_set_pte: return 0; } -int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, +static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { @@ -1929,12 +1929,17 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, unsigned long address, unsigned int fault_flags) { struct vm_area_struct *vma; + vm_flags_t vm_flags; int ret; vma = find_extend_vma(mm, address); if (!vma || address < vma->vm_start) return -EFAULT; + vm_flags = (fault_flags & FAULT_FLAG_WRITE) ? VM_WRITE : VM_READ; + if (!(vm_flags & vma->vm_flags)) + return -EFAULT; + ret = handle_mm_fault(mm, vma, address, fault_flags); if (ret & VM_FAULT_ERROR) { if (ret & VM_FAULT_OOM) @@ -3189,7 +3194,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo if (prev && prev->vm_end == address) return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM; - expand_downwards(vma, address - PAGE_SIZE); + return expand_downwards(vma, address - PAGE_SIZE); } if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) { struct vm_area_struct *next = vma->vm_next; @@ -3198,7 +3203,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo if (next && next->vm_start == address + PAGE_SIZE) return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM; - expand_upwards(vma, address + PAGE_SIZE); + return expand_upwards(vma, address + PAGE_SIZE); } return 0; } @@ -3693,7 +3698,7 @@ static int handle_pte_fault(struct mm_struct *mm, pte_t entry; spinlock_t *ptl; - entry = *pte; + entry = ACCESS_ONCE(*pte); if (!pte_present(entry)) { if (pte_none(entry)) { if (vma->vm_ops) { @@ -3742,32 +3747,6 @@ unlock: return 0; } -#ifdef CONFIG_PREEMPT_RT_FULL -void pagefault_disable(void) -{ - migrate_disable(); - current->pagefault_disabled++; - /* - * make sure to have issued the store before a pagefault - * can hit. - */ - barrier(); -} -EXPORT_SYMBOL(pagefault_disable); - -void pagefault_enable(void) -{ - /* - * make sure to issue those last loads/stores before enabling - * the pagefault handler again. - */ - barrier(); - current->pagefault_disabled--; - migrate_enable(); -} -EXPORT_SYMBOL(pagefault_enable); -#endif - /* * By the time we get here, we already hold the mm semaphore */ @@ -4344,35 +4323,3 @@ void copy_user_huge_page(struct page *dst, struct page *src, } } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ - -#if defined(CONFIG_PREEMPT_RT_FULL) && (USE_SPLIT_PTLOCKS > 0) -/* - * Heinous hack, relies on the caller doing something like: - * - * pte = alloc_pages(PGALLOC_GFP, 0); - * if (pte) - * pgtable_page_ctor(pte); - * return pte; - * - * This ensures we release the page and return NULL when the - * lock allocation fails. - */ -struct page *pte_lock_init(struct page *page) -{ - page->ptl = kmalloc(sizeof(spinlock_t), GFP_KERNEL); - if (page->ptl) { - spin_lock_init(__pte_lockptr(page)); - } else { - __free_page(page); - page = NULL; - } - return page; -} - -void pte_lock_deinit(struct page *page) -{ - kfree(page->ptl); - page->mapping = NULL; -} - -#endif diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index ed85fe3..d317305 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1321,7 +1321,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) * alloc_migrate_target should be improooooved!! * migrate_pages returns # of failed pages. */ - ret = migrate_pages(&source, alloc_migrate_target, 0, + ret = migrate_pages(&source, alloc_migrate_target, NULL, 0, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); if (ret) putback_movable_pages(&source); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 927a69c..3650036 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -525,9 +525,13 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma, #ifdef CONFIG_HUGETLB_PAGE int nid; struct page *page; + pte_t entry; spin_lock(&vma->vm_mm->page_table_lock); - page = pte_page(huge_ptep_get((pte_t *)pmd)); + entry = huge_ptep_get((pte_t *)pmd); + if (!pte_present(entry)) + goto unlock; + page = pte_page(entry); nid = page_to_nid(page); if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT)) goto unlock; @@ -649,19 +653,18 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma, * @nodes and @flags,) it's isolated and queued to the pagelist which is * passed via @private.) */ -static struct vm_area_struct * +static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) { - int err; - struct vm_area_struct *first, *vma, *prev; - + int err = 0; + struct vm_area_struct *vma, *prev; - first = find_vma(mm, start); - if (!first) - return ERR_PTR(-EFAULT); + vma = find_vma(mm, start); + if (!vma) + return -EFAULT; prev = NULL; - for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) { + for (; vma && vma->vm_start < end; vma = vma->vm_next) { unsigned long endvma = vma->vm_end; if (endvma > end) @@ -671,9 +674,9 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, if (!(flags & MPOL_MF_DISCONTIG_OK)) { if (!vma->vm_next && vma->vm_end < end) - return ERR_PTR(-EFAULT); + return -EFAULT; if (prev && prev->vm_end < vma->vm_start) - return ERR_PTR(-EFAULT); + return -EFAULT; } if (flags & MPOL_MF_LAZY) { @@ -687,15 +690,13 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, err = queue_pages_pgd_range(vma, start, endvma, nodes, flags, private); - if (err) { - first = ERR_PTR(err); + if (err) break; - } } next: prev = vma; } - return first; + return err; } /* @@ -1059,7 +1060,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, flags | MPOL_MF_DISCONTIG_OK, &pagelist); if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, new_node_page, dest, + err = migrate_pages(&pagelist, new_node_page, NULL, dest, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(&pagelist); @@ -1180,30 +1181,31 @@ out: /* * Allocate a new page for page migration based on vma policy. - * Start assuming that page is mapped by vma pointed to by @private. + * Start by assuming the page is mapped by the same vma as contains @start. * Search forward from there, if not. N.B., this assumes that the * list of pages handed to migrate_pages()--which is how we get here-- * is in virtual address order. */ -static struct page *new_vma_page(struct page *page, unsigned long private, int **x) +static struct page *new_page(struct page *page, unsigned long start, int **x) { - struct vm_area_struct *vma = (struct vm_area_struct *)private; + struct vm_area_struct *vma; unsigned long uninitialized_var(address); + vma = find_vma(current->mm, start); while (vma) { address = page_address_in_vma(page, vma); if (address != -EFAULT) break; vma = vma->vm_next; } - /* - * queue_pages_range() confirms that @page belongs to some vma, - * so vma shouldn't be NULL. - */ - BUG_ON(!vma); - if (PageHuge(page)) + if (PageHuge(page)) { + BUG_ON(!vma); return alloc_huge_page_noerr(vma, address, 1); + } + /* + * if !vma, alloc_page_vma() will use task or system default policy + */ return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); } #else @@ -1219,7 +1221,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, return -ENOSYS; } -static struct page *new_vma_page(struct page *page, unsigned long private, int **x) +static struct page *new_page(struct page *page, unsigned long start, int **x) { return NULL; } @@ -1229,7 +1231,6 @@ static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { - struct vm_area_struct *vma; struct mm_struct *mm = current->mm; struct mempolicy *new; unsigned long end; @@ -1295,11 +1296,9 @@ static long do_mbind(unsigned long start, unsigned long len, if (err) goto mpol_out; - vma = queue_pages_range(mm, start, end, nmask, + err = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); - - err = PTR_ERR(vma); /* maybe ... */ - if (!IS_ERR(vma)) + if (!err) err = mbind_range(mm, start, end, new); if (!err) { @@ -1307,9 +1306,8 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { WARN_ON_ONCE(flags & MPOL_MF_LAZY); - nr_failed = migrate_pages(&pagelist, new_vma_page, - (unsigned long)vma, - MIGRATE_SYNC, MR_MEMPOLICY_MBIND); + nr_failed = migrate_pages(&pagelist, new_page, NULL, + start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) putback_movable_pages(&pagelist); } @@ -1875,7 +1873,7 @@ 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, @@ -2039,7 +2037,7 @@ 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; @@ -2047,7 +2045,7 @@ 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; @@ -2057,7 +2055,7 @@ 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; } @@ -2091,7 +2089,7 @@ 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 @@ -2104,7 +2102,7 @@ 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; @@ -2148,7 +2146,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old) } else *new = *old; - rcu_read_lock(); if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); if (new->flags & MPOL_F_REBINDING) @@ -2156,7 +2153,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old) else mpol_rebind_policy(new, &mems, MPOL_REBIND_ONCE); } - rcu_read_unlock(); atomic_set(&new->refcnt, 1); return new; } diff --git a/mm/migrate.c b/mm/migrate.c index e3cf71d..fac5fa0 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -136,8 +136,6 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, pmd = mm_find_pmd(mm, addr); if (!pmd) goto out; - if (pmd_trans_huge(*pmd)) - goto out; ptep = pte_offset_map(pmd, addr); @@ -164,8 +162,11 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, pte = pte_mkold(mk_pte(new, vma->vm_page_prot)); if (pte_swp_soft_dirty(*ptep)) pte = pte_mksoft_dirty(pte); + + /* Recheck VMA as permissions can change since migration started */ if (is_write_migration_entry(entry)) - pte = pte_mkwrite(pte); + pte = maybe_mkwrite(pte, vma); + #ifdef CONFIG_HUGETLB_PAGE if (PageHuge(new)) { pte = pte_mkhuge(pte); @@ -867,8 +868,9 @@ out: * Obtain the lock on page, remove all ptes and migrate the page * to the newly allocated page in newpage. */ -static int unmap_and_move(new_page_t get_new_page, unsigned long private, - struct page *page, int force, enum migrate_mode mode) +static int unmap_and_move(new_page_t get_new_page, free_page_t put_new_page, + unsigned long private, struct page *page, int force, + enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -912,11 +914,18 @@ out: page_is_file_cache(page)); putback_lru_page(page); } + /* - * Move the new page to the LRU. If migration was not successful - * then this will free the page. + * If migration was not successful and there's a freeing callback, use + * it. Otherwise, putback_lru_page() will drop the reference grabbed + * during isolation. */ - putback_lru_page(newpage); + if (rc != MIGRATEPAGE_SUCCESS && put_new_page) { + ClearPageSwapBacked(newpage); + put_new_page(newpage, private); + } else + putback_lru_page(newpage); + if (result) { if (rc) *result = rc; @@ -945,8 +954,9 @@ out: * will wait in the page fault for migration to complete. */ static int unmap_and_move_huge_page(new_page_t get_new_page, - unsigned long private, struct page *hpage, - int force, enum migrate_mode mode) + free_page_t put_new_page, unsigned long private, + struct page *hpage, int force, + enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -982,20 +992,30 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (!page_mapped(hpage)) rc = move_to_new_page(new_hpage, hpage, 1, mode); - if (rc) + if (rc != MIGRATEPAGE_SUCCESS) remove_migration_ptes(hpage, hpage); if (anon_vma) put_anon_vma(anon_vma); - if (!rc) + if (rc == MIGRATEPAGE_SUCCESS) hugetlb_cgroup_migrate(hpage, new_hpage); unlock_page(hpage); out: if (rc != -EAGAIN) putback_active_hugepage(hpage); - put_page(new_hpage); + + /* + * If migration was not successful and there's a freeing callback, use + * it. Otherwise, put_page() will drop the reference grabbed during + * isolation. + */ + if (rc != MIGRATEPAGE_SUCCESS && put_new_page) + put_new_page(new_hpage, private); + else + put_page(new_hpage); + if (result) { if (rc) *result = rc; @@ -1012,6 +1032,8 @@ out: * @from: The list of pages to be migrated. * @get_new_page: The function used to allocate free pages to be used * as the target of the page migration. + * @put_new_page: The function used to free target pages if migration + * fails, or NULL if no special handling is necessary. * @private: Private data to be passed on to get_new_page() * @mode: The migration mode that specifies the constraints for * page migration, if any. @@ -1025,7 +1047,8 @@ out: * Returns the number of pages that were not migrated, or an error code. */ int migrate_pages(struct list_head *from, new_page_t get_new_page, - unsigned long private, enum migrate_mode mode, int reason) + free_page_t put_new_page, unsigned long private, + enum migrate_mode mode, int reason) { int retry = 1; int nr_failed = 0; @@ -1047,10 +1070,11 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, if (PageHuge(page)) rc = unmap_and_move_huge_page(get_new_page, - private, page, pass > 2, mode); + put_new_page, private, page, + pass > 2, mode); else - rc = unmap_and_move(get_new_page, private, - page, pass > 2, mode); + rc = unmap_and_move(get_new_page, put_new_page, + private, page, pass > 2, mode); switch(rc) { case -ENOMEM: @@ -1194,7 +1218,7 @@ set_status: err = 0; if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, new_page_node, + err = migrate_pages(&pagelist, new_page_node, NULL, (unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(&pagelist); @@ -1643,7 +1667,8 @@ int migrate_misplaced_page(struct page *page, int node) list_add(&page->lru, &migratepages); nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, - node, MIGRATE_ASYNC, MR_NUMA_MISPLACED); + NULL, node, MIGRATE_ASYNC, + MR_NUMA_MISPLACED); if (nr_remaining) { putback_lru_pages(&migratepages); isolated = 0; diff --git a/mm/mincore.c b/mm/mincore.c index da2be56..06cb810 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -70,13 +70,21 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) * any other file mapping (ie. marked !present and faulted in with * tmpfs's .fault). So swapped out tmpfs mappings are tested here. */ - page = find_get_page(mapping, pgoff); #ifdef CONFIG_SWAP - /* shmem/tmpfs may return swap: account for swapcache page too. */ - if (radix_tree_exceptional_entry(page)) { - swp_entry_t swap = radix_to_swp_entry(page); - page = find_get_page(swap_address_space(swap), swap.val); - } + if (shmem_mapping(mapping)) { + page = find_get_entry(mapping, pgoff); + /* + * shmem/tmpfs may return swap: account for swapcache + * page too. + */ + if (radix_tree_exceptional_entry(page)) { + swp_entry_t swp = radix_to_swp_entry(page); + page = find_get_page(swap_address_space(swp), swp.val); + } + } else + page = find_get_page(mapping, pgoff); +#else + page = find_get_page(mapping, pgoff); #endif if (page) { present = PageUptodate(page); @@ -79,6 +79,7 @@ void clear_page_mlock(struct page *page) */ void mlock_vma_page(struct page *page) { + /* Serialize with page migration */ BUG_ON(!PageLocked(page)); if (!TestSetPageMlocked(page)) { @@ -153,6 +154,7 @@ unsigned int munlock_vma_page(struct page *page) { unsigned int nr_pages; + /* For try_to_munlock() and to serialize with page migration */ BUG_ON(!PageLocked(page)); if (TestClearPageMlocked(page)) { @@ -10,6 +10,7 @@ #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/shm.h> #include <linux/mman.h> #include <linux/pagemap.h> @@ -682,8 +683,9 @@ __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); } /* @@ -744,8 +746,11 @@ again: remove_next = 1 + (end > next->vm_end); * shrinking vma had, to cover any anon pages imported. */ if (exporter && exporter->anon_vma && !importer->anon_vma) { - if (anon_vma_clone(importer, exporter)) - return -ENOMEM; + int error; + + error = anon_vma_clone(importer, exporter); + if (error) + return error; importer->anon_vma = exporter->anon_vma; } } @@ -1980,34 +1985,33 @@ 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; } @@ -2045,14 +2049,17 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns { struct mm_struct *mm = vma->vm_mm; struct rlimit *rlim = current->signal->rlim; - unsigned long new_start; + unsigned long new_start, actual_size; /* address space limit tests */ if (!may_expand_vm(mm, grow)) return -ENOMEM; /* Stack limit test */ - if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur)) + actual_size = size; + if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN))) + actual_size -= PAGE_SIZE; + if (actual_size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur)) return -ENOMEM; /* mlock limit tests */ @@ -2379,7 +2386,9 @@ 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); } /* @@ -2416,7 +2425,8 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, if (err) goto out_free_vma; - if (anon_vma_clone(new, vma)) + err = anon_vma_clone(new, vma); + if (err) goto out_free_mpol; if (new->vm_file) diff --git a/mm/mmu_context.c b/mm/mmu_context.c index adfce87..8a8cd02 100644 --- a/mm/mmu_context.c +++ b/mm/mmu_context.c @@ -23,7 +23,6 @@ void use_mm(struct mm_struct *mm) struct task_struct *tsk = current; task_lock(tsk); - preempt_disable_rt(); active_mm = tsk->active_mm; if (active_mm != mm) { atomic_inc(&mm->mm_count); @@ -31,7 +30,6 @@ void use_mm(struct mm_struct *mm) } tsk->mm = mm; switch_mm(active_mm, mm, tsk); - preempt_enable_rt(); task_unlock(tsk); if (active_mm != mm) diff --git a/mm/mremap.c b/mm/mremap.c index 0843feb..05f1180 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -194,10 +194,17 @@ unsigned long move_page_tables(struct vm_area_struct *vma, break; if (pmd_trans_huge(*old_pmd)) { int err = 0; - if (extent == HPAGE_PMD_SIZE) + if (extent == HPAGE_PMD_SIZE) { + VM_BUG_ON(vma->vm_file || !vma->anon_vma); + /* See comment in move_ptes() */ + if (need_rmap_locks) + anon_vma_lock_write(vma->anon_vma); err = move_huge_pmd(vma, new_vma, old_addr, new_addr, old_end, old_pmd, new_pmd); + if (need_rmap_locks) + anon_vma_unlock_write(vma->anon_vma); + } if (err > 0) { need_flush = true; continue; @@ -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> @@ -767,16 +768,23 @@ 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 +832,8 @@ 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 +842,7 @@ 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 +881,8 @@ 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 +893,7 @@ 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; } } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index e73f01c..712a0f8 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. */ @@ -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(); @@ -394,6 +406,23 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, dump_tasks(memcg, nodemask); } +/* + * Number of OOM killer invocations (including memcg OOM killer). + * Primarily used by PM freezer to check for potential races with + * OOM killed frozen task. + */ +static atomic_t oom_kills = ATOMIC_INIT(0); + +int oom_kills_count(void) +{ + return atomic_read(&oom_kills); +} + +void note_oom_kill(void) +{ + atomic_inc(&oom_kills); +} + #define K(x) ((x) << (PAGE_SHIFT-10)) /* * Must be called while holding a reference to p, which will be released upon @@ -406,7 +435,7 @@ 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 +466,7 @@ 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 +484,11 @@ 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 +514,7 @@ 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 7106cb1..9f45f87 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -593,14 +593,14 @@ unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty) * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) * => fast response on large errors; small oscillation near setpoint */ -static inline long long pos_ratio_polynom(unsigned long setpoint, +static long long pos_ratio_polynom(unsigned long setpoint, unsigned long dirty, unsigned long limit) { long long pos_ratio; long x; - x = div_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, + x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, limit - setpoint + 1); pos_ratio = x; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; @@ -842,7 +842,7 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi, x_intercept = bdi_setpoint + span; if (bdi_dirty < x_intercept - span / 4) { - pos_ratio = div_u64(pos_ratio * (x_intercept - bdi_dirty), + pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty), x_intercept - bdi_setpoint + 1); } else pos_ratio /= 4; @@ -1324,9 +1324,9 @@ static inline void bdi_dirty_limits(struct backing_dev_info *bdi, *bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); if (bdi_bg_thresh) - *bdi_bg_thresh = div_u64((u64)*bdi_thresh * - background_thresh, - dirty_thresh); + *bdi_bg_thresh = dirty_thresh ? div_u64((u64)*bdi_thresh * + background_thresh, + dirty_thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need @@ -2398,7 +2398,7 @@ int test_clear_page_writeback(struct page *page) return ret; } -int test_set_page_writeback(struct page *page) +int __test_set_page_writeback(struct page *page, bool keep_write) { struct address_space *mapping = page_mapping(page); int ret; @@ -2423,9 +2423,10 @@ int test_set_page_writeback(struct page *page) radix_tree_tag_clear(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); - radix_tree_tag_clear(&mapping->page_tree, - page_index(page), - PAGECACHE_TAG_TOWRITE); + if (!keep_write) + radix_tree_tag_clear(&mapping->page_tree, + page_index(page), + PAGECACHE_TAG_TOWRITE); spin_unlock_irqrestore(&mapping->tree_lock, flags); } else { ret = TestSetPageWriteback(page); @@ -2436,7 +2437,7 @@ int test_set_page_writeback(struct page *page) return ret; } -EXPORT_SYMBOL(test_set_page_writeback); +EXPORT_SYMBOL(__test_set_page_writeback); /* * Return true if any of the pages in the mapping are marked with the diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 36c40eb..7abab3b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -61,7 +61,6 @@ #include <linux/page-debug-flags.h> #include <linux/hugetlb.h> #include <linux/sched/rt.h> -#include <linux/locallock.h> #include <asm/sections.h> #include <asm/tlbflush.h> @@ -70,6 +69,7 @@ /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */ static DEFINE_MUTEX(pcp_batch_high_lock); +#define MIN_PERCPU_PAGELIST_FRACTION (8) #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); @@ -231,18 +231,6 @@ EXPORT_SYMBOL(nr_node_ids); EXPORT_SYMBOL(nr_online_nodes); #endif -static DEFINE_LOCAL_IRQ_LOCK(pa_lock); - -#ifdef CONFIG_PREEMPT_RT_BASE -# define cpu_lock_irqsave(cpu, flags) \ - local_lock_irqsave_on(pa_lock, flags, cpu) -# define cpu_unlock_irqrestore(cpu, flags) \ - local_unlock_irqrestore_on(pa_lock, flags, cpu) -#else -# define cpu_lock_irqsave(cpu, flags) local_irq_save(flags) -# define cpu_unlock_irqrestore(cpu, flags) local_irq_restore(flags) -#endif - int page_group_by_mobility_disabled __read_mostly; void set_pageblock_migratetype(struct page *page, int migratetype) @@ -417,7 +405,8 @@ static int destroy_compound_page(struct page *page, unsigned long order) return bad; } -static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags) +static inline void prep_zero_page(struct page *page, unsigned int order, + gfp_t gfp_flags) { int i; @@ -461,7 +450,7 @@ static inline void set_page_guard_flag(struct page *page) { } static inline void clear_page_guard_flag(struct page *page) { } #endif -static inline void set_page_order(struct page *page, int order) +static inline void set_page_order(struct page *page, unsigned int order) { set_page_private(page, order); __SetPageBuddy(page); @@ -512,21 +501,31 @@ __find_buddy_index(unsigned long page_idx, unsigned int order) * For recording page's order, we use page_private(page). */ static inline int page_is_buddy(struct page *page, struct page *buddy, - int order) + unsigned int order) { if (!pfn_valid_within(page_to_pfn(buddy))) return 0; - if (page_zone_id(page) != page_zone_id(buddy)) - return 0; - if (page_is_guard(buddy) && page_order(buddy) == order) { VM_BUG_ON(page_count(buddy) != 0); + + if (page_zone_id(page) != page_zone_id(buddy)) + return 0; + return 1; } if (PageBuddy(buddy) && page_order(buddy) == order) { VM_BUG_ON(page_count(buddy) != 0); + + /* + * zone check is done late to avoid uselessly + * calculating zone/node ids for pages that could + * never merge. + */ + if (page_zone_id(page) != page_zone_id(buddy)) + return 0; + return 1; } return 0; @@ -558,6 +557,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, */ static inline void __free_one_page(struct page *page, + unsigned long pfn, struct zone *zone, unsigned int order, int migratetype) { @@ -574,7 +574,7 @@ static inline void __free_one_page(struct page *page, VM_BUG_ON(migratetype == -1); - page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); + page_idx = pfn & ((1 << MAX_ORDER) - 1); VM_BUG_ON(page_idx & ((1 << order) - 1)); VM_BUG_ON(bad_range(zone, page)); @@ -648,7 +648,7 @@ static inline int free_pages_check(struct page *page) } /* - * Frees a number of pages which have been collected from the pcp lists. + * Frees a number of pages from the PCP lists * Assumes all pages on list are in same zone, and of same order. * count is the number of pages to free. * @@ -659,48 +659,17 @@ static inline int free_pages_check(struct page *page) * pinned" detection logic. */ static void free_pcppages_bulk(struct zone *zone, int count, - struct list_head *list) + struct per_cpu_pages *pcp) { + int migratetype = 0; + int batch_free = 0; int to_free = count; - unsigned long flags; - - spin_lock_irqsave(&zone->lock, flags); - zone->pages_scanned = 0; - - while (!list_empty(list)) { - struct page *page = list_first_entry(list, struct page, lru); - int mt; /* migratetype of the to-be-freed page */ - - /* must delete as __free_one_page list manipulates */ - list_del(&page->lru); - - mt = get_freepage_migratetype(page); - /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ - __free_one_page(page, zone, 0, mt); - trace_mm_page_pcpu_drain(page, 0, mt); - if (likely(!is_migrate_isolate_page(page))) { - __mod_zone_page_state(zone, NR_FREE_PAGES, 1); - if (is_migrate_cma(mt)) - __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1); - } - - to_free--; - } - WARN_ON(to_free != 0); - spin_unlock_irqrestore(&zone->lock, flags); -} + unsigned long nr_scanned; -/* - * Moves a number of pages from the PCP lists to free list which - * is freed outside of the locked region. - * - * Assumes all pages on list are in same zone, and of same order. - * count is the number of pages to free. - */ -static void isolate_pcp_pages(int to_free, struct per_cpu_pages *src, - struct list_head *dst) -{ - int migratetype = 0, batch_free = 0; + spin_lock(&zone->lock); + nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + if (nr_scanned) + __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); while (to_free) { struct page *page; @@ -717,7 +686,7 @@ static void isolate_pcp_pages(int to_free, struct per_cpu_pages *src, batch_free++; if (++migratetype == MIGRATE_PCPTYPES) migratetype = 0; - list = &src->lists[migratetype]; + list = &pcp->lists[migratetype]; } while (list_empty(list)); /* This is the only non-empty list. Free them all. */ @@ -725,25 +694,40 @@ static void isolate_pcp_pages(int to_free, struct per_cpu_pages *src, batch_free = to_free; do { - page = list_last_entry(list, struct page, lru); + int mt; /* migratetype of the to-be-freed page */ + + page = list_entry(list->prev, struct page, lru); + /* must delete as __free_one_page list manipulates */ list_del(&page->lru); - list_add(&page->lru, dst); + mt = get_freepage_migratetype(page); + /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ + __free_one_page(page, page_to_pfn(page), zone, 0, mt); + trace_mm_page_pcpu_drain(page, 0, mt); + if (likely(!is_migrate_isolate_page(page))) { + __mod_zone_page_state(zone, NR_FREE_PAGES, 1); + if (is_migrate_cma(mt)) + __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1); + } } while (--to_free && --batch_free && !list_empty(list)); } + spin_unlock(&zone->lock); } -static void free_one_page(struct zone *zone, struct page *page, int order, +static void free_one_page(struct zone *zone, + struct page *page, unsigned long pfn, + unsigned int order, int migratetype) { - unsigned long flags; - - spin_lock_irqsave(&zone->lock, flags); - zone->pages_scanned = 0; + unsigned long nr_scanned; + spin_lock(&zone->lock); + nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + if (nr_scanned) + __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); - __free_one_page(page, zone, order, migratetype); + __free_one_page(page, pfn, zone, order, migratetype); if (unlikely(!is_migrate_isolate(migratetype))) __mod_zone_freepage_state(zone, 1 << order, migratetype); - spin_unlock_irqrestore(&zone->lock, flags); + spin_unlock(&zone->lock); } static bool free_pages_prepare(struct page *page, unsigned int order) @@ -777,16 +761,17 @@ static void __free_pages_ok(struct page *page, unsigned int order) { unsigned long flags; int migratetype; + unsigned long pfn = page_to_pfn(page); if (!free_pages_prepare(page, order)) return; - local_lock_irqsave(pa_lock, flags); + migratetype = get_pfnblock_migratetype(page, pfn); + local_irq_save(flags); __count_vm_events(PGFREE, 1 << order); - migratetype = get_pageblock_migratetype(page); set_freepage_migratetype(page, migratetype); - free_one_page(page_zone(page), page, order, migratetype); - local_unlock_irqrestore(pa_lock, flags); + free_one_page(page_zone(page), page, pfn, order, migratetype); + local_irq_restore(flags); } void __init __free_pages_bootmem(struct page *page, unsigned int order) @@ -821,9 +806,21 @@ void __init init_cma_reserved_pageblock(struct page *page) set_page_count(p, 0); } while (++p, --i); - set_page_refcounted(page); set_pageblock_migratetype(page, MIGRATE_CMA); - __free_pages(page, pageblock_order); + + if (pageblock_order >= MAX_ORDER) { + i = pageblock_nr_pages; + p = page; + do { + set_page_refcounted(p); + __free_pages(p, MAX_ORDER - 1); + p += MAX_ORDER_NR_PAGES; + } while (i -= MAX_ORDER_NR_PAGES); + } else { + set_page_refcounted(page); + __free_pages(page, pageblock_order); + } + adjust_managed_page_count(page, pageblock_nr_pages); } #endif @@ -893,7 +890,7 @@ static inline int check_new_page(struct page *page) return 0; } -static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) +static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags) { int i; @@ -942,6 +939,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, rmv_page_order(page); area->nr_free--; expand(zone, page, order, current_order, area, migratetype); + set_freepage_migratetype(page, migratetype); return page; } @@ -1066,6 +1064,12 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page, { int current_order = page_order(page); + /* + * When borrowing from MIGRATE_CMA, we need to release the excess + * buddy pages to CMA itself. We also ensure the freepage_migratetype + * is set to CMA so it is returned to the correct freelist in case + * the page ends up being not actually allocated from the pcp lists. + */ if (is_migrate_cma(fallback_type)) return fallback_type; @@ -1097,16 +1101,17 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page, /* Remove an element from the buddy allocator from the fallback list */ static inline struct page * -__rmqueue_fallback(struct zone *zone, int order, int start_migratetype) +__rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) { struct free_area *area; - int current_order; + unsigned int current_order; struct page *page; int migratetype, new_type, i; /* Find the largest possible block of pages in the other list */ - for (current_order = MAX_ORDER-1; current_order >= order; - --current_order) { + for (current_order = MAX_ORDER-1; + current_order >= order && current_order <= MAX_ORDER-1; + --current_order) { for (i = 0;; i++) { migratetype = fallbacks[start_migratetype][i]; @@ -1130,21 +1135,17 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) list_del(&page->lru); rmv_page_order(page); - /* - * Borrow the excess buddy pages as well, irrespective - * of whether we stole freepages, or took ownership of - * the pageblock or not. - * - * Exception: When borrowing from MIGRATE_CMA, release - * the excess buddy pages to CMA itself. - */ expand(zone, page, order, current_order, area, - is_migrate_cma(migratetype) - ? migratetype : start_migratetype); + new_type); + /* The freepage_migratetype may differ from pageblock's + * migratetype depending on the decisions in + * try_to_steal_freepages. This is OK as long as it does + * not differ for MIGRATE_CMA type. + */ + set_freepage_migratetype(page, new_type); - trace_mm_page_alloc_extfrag(page, order, - current_order, start_migratetype, migratetype, - new_type == start_migratetype); + trace_mm_page_alloc_extfrag(page, order, current_order, + start_migratetype, migratetype, new_type); return page; } @@ -1190,9 +1191,9 @@ retry_reserve: */ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, - int migratetype, int cold) + int migratetype, bool cold) { - int mt = migratetype, i; + int i; spin_lock(&zone->lock); for (i = 0; i < count; ++i) { @@ -1209,18 +1210,12 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * merge IO requests if the physical pages are ordered * properly. */ - if (likely(cold == 0)) + if (likely(!cold)) list_add(&page->lru, list); else list_add_tail(&page->lru, list); - if (IS_ENABLED(CONFIG_CMA)) { - mt = get_pageblock_migratetype(page); - if (!is_migrate_cma(mt) && !is_migrate_isolate(mt)) - mt = migratetype; - } - set_freepage_migratetype(page, mt); list = &page->lru; - if (is_migrate_cma(mt)) + if (is_migrate_cma(get_freepage_migratetype(page))) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, -(1 << order)); } @@ -1241,31 +1236,20 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) { unsigned long flags; - LIST_HEAD(dst); int to_drain; unsigned long batch; - local_lock_irqsave(pa_lock, flags); + local_irq_save(flags); batch = ACCESS_ONCE(pcp->batch); if (pcp->count >= batch) to_drain = batch; else to_drain = pcp->count; if (to_drain > 0) { - isolate_pcp_pages(to_drain, pcp, &dst); + free_pcppages_bulk(zone, to_drain, pcp); pcp->count -= to_drain; } - local_unlock_irqrestore(pa_lock, flags); - free_pcppages_bulk(zone, to_drain, &dst); -} -static bool gfp_thisnode_allocation(gfp_t gfp_mask) -{ - return (gfp_mask & GFP_THISNODE) == GFP_THISNODE; -} -#else -static bool gfp_thisnode_allocation(gfp_t gfp_mask) -{ - return false; + local_irq_restore(flags); } #endif @@ -1284,21 +1268,16 @@ static void drain_pages(unsigned int cpu) for_each_populated_zone(zone) { struct per_cpu_pageset *pset; struct per_cpu_pages *pcp; - LIST_HEAD(dst); - int count; - cpu_lock_irqsave(cpu, flags); + local_irq_save(flags); pset = per_cpu_ptr(zone->pageset, cpu); pcp = &pset->pcp; - count = pcp->count; - if (count) { - isolate_pcp_pages(count, pcp, &dst); + if (pcp->count) { + free_pcppages_bulk(zone, pcp->count, pcp); pcp->count = 0; } - cpu_unlock_irqrestore(cpu, flags); - if (count) - free_pcppages_bulk(zone, count, &dst); + local_irq_restore(flags); } } @@ -1351,12 +1330,7 @@ void drain_all_pages(void) else cpumask_clear_cpu(cpu, &cpus_with_pcps); } -#ifndef CONFIG_PREEMPT_RT_BASE on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1); -#else - for_each_cpu(cpu, &cpus_with_pcps) - drain_pages(cpu); -#endif } #ifdef CONFIG_HIBERNATION @@ -1365,7 +1339,7 @@ void mark_free_pages(struct zone *zone) { unsigned long pfn, max_zone_pfn; unsigned long flags; - int order, t; + unsigned int order, t; struct list_head *curr; if (zone_is_empty(zone)) @@ -1397,21 +1371,22 @@ void mark_free_pages(struct zone *zone) /* * Free a 0-order page - * cold == 1 ? free a cold page : free a hot page + * cold == true ? free a cold page : free a hot page */ -void free_hot_cold_page(struct page *page, int cold) +void free_hot_cold_page(struct page *page, bool cold) { struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; unsigned long flags; + unsigned long pfn = page_to_pfn(page); int migratetype; if (!free_pages_prepare(page, 0)) return; - migratetype = get_pageblock_migratetype(page); + migratetype = get_pfnblock_migratetype(page, pfn); set_freepage_migratetype(page, migratetype); - local_lock_irqsave(pa_lock, flags); + local_irq_save(flags); __count_vm_event(PGFREE); /* @@ -1423,37 +1398,32 @@ void free_hot_cold_page(struct page *page, int cold) */ if (migratetype >= MIGRATE_PCPTYPES) { if (unlikely(is_migrate_isolate(migratetype))) { - free_one_page(zone, page, 0, migratetype); + free_one_page(zone, page, pfn, 0, migratetype); goto out; } migratetype = MIGRATE_MOVABLE; } pcp = &this_cpu_ptr(zone->pageset)->pcp; - if (cold) - list_add_tail(&page->lru, &pcp->lists[migratetype]); - else + if (!cold) list_add(&page->lru, &pcp->lists[migratetype]); + else + list_add_tail(&page->lru, &pcp->lists[migratetype]); pcp->count++; if (pcp->count >= pcp->high) { unsigned long batch = ACCESS_ONCE(pcp->batch); - LIST_HEAD(dst); - - isolate_pcp_pages(batch, pcp, &dst); + free_pcppages_bulk(zone, batch, pcp); pcp->count -= batch; - local_unlock_irqrestore(pa_lock, flags); - free_pcppages_bulk(zone, batch, &dst); - return; } out: - local_unlock_irqrestore(pa_lock, flags); + local_irq_restore(flags); } /* * Free a list of 0-order pages */ -void free_hot_cold_page_list(struct list_head *list, int cold) +void free_hot_cold_page_list(struct list_head *list, bool cold) { struct page *page, *next; @@ -1565,19 +1535,19 @@ int split_free_page(struct page *page) */ static inline struct page *buffered_rmqueue(struct zone *preferred_zone, - struct zone *zone, int order, gfp_t gfp_flags, - int migratetype) + struct zone *zone, unsigned int order, + gfp_t gfp_flags, int migratetype) { unsigned long flags; struct page *page; - int cold = !!(gfp_flags & __GFP_COLD); + bool cold = ((gfp_flags & __GFP_COLD) != 0); again: if (likely(order == 0)) { struct per_cpu_pages *pcp; struct list_head *list; - local_lock_irqsave(pa_lock, flags); + local_irq_save(flags); pcp = &this_cpu_ptr(zone->pageset)->pcp; list = &pcp->lists[migratetype]; if (list_empty(list)) { @@ -1609,27 +1579,23 @@ again: */ WARN_ON_ONCE(order > 1); } - local_spin_lock_irqsave(pa_lock, &zone->lock, flags); + spin_lock_irqsave(&zone->lock, flags); page = __rmqueue(zone, order, migratetype); - if (!page) { - spin_unlock(&zone->lock); + spin_unlock(&zone->lock); + if (!page) goto failed; - } __mod_zone_freepage_state(zone, -(1 << order), - get_pageblock_migratetype(page)); - spin_unlock(&zone->lock); + get_freepage_migratetype(page)); } - /* - * NOTE: GFP_THISNODE allocations do not partake in the kswapd - * aging protocol, so they can't be fair. - */ - if (!gfp_thisnode_allocation(gfp_flags)) - __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); + __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); + if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0 && + !zone_is_fair_depleted(zone)) + zone_set_flag(zone, ZONE_FAIR_DEPLETED); __count_zone_vm_events(PGALLOC, zone, 1 << order); zone_statistics(preferred_zone, zone, gfp_flags); - local_unlock_irqrestore(pa_lock, flags); + local_irq_restore(flags); VM_BUG_ON(bad_range(zone, page)); if (prep_new_page(page, order, gfp_flags)) @@ -1637,7 +1603,7 @@ again: return page; failed: - local_unlock_irqrestore(pa_lock, flags); + local_irq_restore(flags); return NULL; } @@ -1722,12 +1688,12 @@ static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) * Return true if free pages are above 'mark'. This takes into account the order * of the allocation. */ -static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags, long free_pages) +static bool __zone_watermark_ok(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags, + long free_pages) { /* free_pages my go negative - that's OK */ long min = mark; - long lowmem_reserve = z->lowmem_reserve[classzone_idx]; int o; long free_cma = 0; @@ -1742,7 +1708,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, free_cma = zone_page_state(z, NR_FREE_CMA_PAGES); #endif - if (free_pages - free_cma <= min + lowmem_reserve) + if (free_pages - free_cma <= min + z->lowmem_reserve[classzone_idx]) return false; for (o = 0; o < order; o++) { /* At the next order, this order's pages become unavailable */ @@ -1757,15 +1723,15 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, return true; } -bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, +bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int classzone_idx, int alloc_flags) { return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, zone_page_state(z, NR_FREE_PAGES)); } -bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags) +bool zone_watermark_ok_safe(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags) { long free_pages = zone_page_state(z, NR_FREE_PAGES); @@ -1907,7 +1873,7 @@ 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 @@ -1950,6 +1916,18 @@ static inline void init_zone_allows_reclaim(int nid) } #endif /* CONFIG_NUMA */ +static void reset_alloc_batches(struct zone *preferred_zone) +{ + struct zone *zone = preferred_zone->zone_pgdat->node_zones; + + do { + mod_zone_page_state(zone, NR_ALLOC_BATCH, + high_wmark_pages(zone) - low_wmark_pages(zone) - + atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); + zone_clear_flag(zone, ZONE_FAIR_DEPLETED); + } while (zone++ != preferred_zone); +} + /* * get_page_from_freelist goes through the zonelist trying to allocate * a page. @@ -1957,18 +1935,22 @@ static inline void init_zone_allows_reclaim(int nid) static struct page * get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order, struct zonelist *zonelist, int high_zoneidx, int alloc_flags, - struct zone *preferred_zone, int migratetype) + struct zone *preferred_zone, int classzone_idx, int migratetype) { struct zoneref *z; struct page *page = NULL; - int classzone_idx; struct zone *zone; nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */ int zlc_active = 0; /* set if using zonelist_cache */ int did_zlc_setup = 0; /* just call zlc_setup() one time */ + bool consider_zone_dirty = (alloc_flags & ALLOC_WMARK_LOW) && + (gfp_mask & __GFP_WRITE); + int nr_fair_skipped = 0; + bool zonelist_rescan; - classzone_idx = zone_idx(preferred_zone); zonelist_scan: + zonelist_rescan = false; + /* * Scan zonelist, looking for a zone with enough free. * See also __cpuset_node_allowed_softwall() comment in kernel/cpuset.c. @@ -1980,34 +1962,23 @@ zonelist_scan: if (IS_ENABLED(CONFIG_NUMA) && zlc_active && !zlc_zone_worth_trying(zonelist, z, allowednodes)) continue; - if ((alloc_flags & ALLOC_CPUSET) && + if (cpusets_enabled() && + (alloc_flags & ALLOC_CPUSET) && !cpuset_zone_allowed_softwall(zone, gfp_mask)) continue; - BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); - if (unlikely(alloc_flags & ALLOC_NO_WATERMARKS)) - goto try_this_zone; /* * Distribute pages in proportion to the individual * 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. - * - * NOTE: GFP_THISNODE allocations do not partake in - * the kswapd aging protocol, so they can't be fair. */ - if ((alloc_flags & ALLOC_WMARK_LOW) && - !gfp_thisnode_allocation(gfp_mask)) { - if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0) - continue; + if (alloc_flags & ALLOC_FAIR) { if (!zone_local(preferred_zone, zone)) + break; + if (zone_is_fair_depleted(zone)) { + nr_fair_skipped++; continue; + } } /* * When allocating a page cache page for writing, we @@ -2035,15 +2006,19 @@ zonelist_scan: * will require awareness of zones in the * dirty-throttling and the flusher threads. */ - if ((alloc_flags & ALLOC_WMARK_LOW) && - (gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone)) - goto this_zone_full; + if (consider_zone_dirty && !zone_dirty_ok(zone)) + continue; mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; if (!zone_watermark_ok(zone, order, mark, classzone_idx, alloc_flags)) { int ret; + /* Checked here to keep the fast path fast */ + BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); + if (alloc_flags & ALLOC_NO_WATERMARKS) + goto try_this_zone; + if (IS_ENABLED(CONFIG_NUMA) && !did_zlc_setup && nr_online_nodes > 1) { /* @@ -2105,17 +2080,11 @@ try_this_zone: if (page) break; this_zone_full: - if (IS_ENABLED(CONFIG_NUMA)) + if (IS_ENABLED(CONFIG_NUMA) && zlc_active) zlc_mark_zone_full(zonelist, z); } - if (unlikely(IS_ENABLED(CONFIG_NUMA) && page == NULL && zlc_active)) { - /* Disable zlc cache for second zonelist scan */ - zlc_active = 0; - goto zonelist_scan; - } - - if (page) + if (page) { /* * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was * necessary to allocate the page. The expectation is @@ -2124,8 +2093,37 @@ this_zone_full: * for !PFMEMALLOC purposes. */ page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS); + return page; + } - return 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) { + alloc_flags &= ~ALLOC_FAIR; + if (nr_fair_skipped) { + zonelist_rescan = true; + reset_alloc_batches(preferred_zone); + } + if (nr_online_nodes > 1) + zonelist_rescan = true; + } + + if (unlikely(IS_ENABLED(CONFIG_NUMA) && zlc_active)) { + /* Disable zlc cache for second zonelist scan */ + zlc_active = 0; + zonelist_rescan = true; + } + + if (zonelist_rescan) + goto zonelist_scan; + + return NULL; } /* @@ -2241,7 +2239,7 @@ static inline struct page * __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + int classzone_idx, int migratetype) { struct page *page; @@ -2252,6 +2250,14 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, } /* + * PM-freezer should be notified that there might be an OOM killer on + * its way to kill and wake somebody up. This is too early and we might + * end up not killing anything but false positives are acceptable. + * See freeze_processes. + */ + note_oom_kill(); + + /* * Go through the zonelist yet one more time, keep very high watermark * here, this is only to catch a parallel oom killing, we must fail if * we're still under heavy pressure. @@ -2259,7 +2265,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, zonelist, high_zoneidx, ALLOC_WMARK_HIGH|ALLOC_CPUSET, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) goto out; @@ -2294,7 +2300,7 @@ static struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, bool sync_migration, + int classzone_idx, int migratetype, enum migrate_mode mode, bool *contended_compaction, bool *deferred_compaction, unsigned long *did_some_progress) { @@ -2308,7 +2314,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, current->flags |= PF_MEMALLOC; *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, - nodemask, sync_migration, + nodemask, mode, contended_compaction); current->flags &= ~PF_MEMALLOC; @@ -2316,19 +2322,16 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct page *page; /* Page migration frees to the PCP lists but we want merging */ - drain_pages(get_cpu_light()); - put_cpu_light(); + drain_pages(get_cpu()); + put_cpu(); page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, 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; } @@ -2344,7 +2347,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, * As async compaction considers a subset of pageblocks, only * defer if the failure was a sync compaction failure. */ - if (sync_migration) + if (mode != MIGRATE_ASYNC) defer_compaction(preferred_zone, order); cond_resched(); @@ -2357,9 +2360,9 @@ static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, bool sync_migration, - bool *contended_compaction, bool *deferred_compaction, - unsigned long *did_some_progress) + int classzone_idx, int migratetype, + enum migrate_mode mode, bool *contended_compaction, + bool *deferred_compaction, unsigned long *did_some_progress) { return NULL; } @@ -2398,7 +2401,7 @@ static inline struct page * __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress) + int classzone_idx, int migratetype, unsigned long *did_some_progress) { struct page *page = NULL; bool drained = false; @@ -2416,7 +2419,8 @@ retry: page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, + migratetype); /* * If an allocation failed after direct reclaim, it could be because @@ -2439,14 +2443,14 @@ static inline struct page * __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + int classzone_idx, int migratetype) { struct page *page; do { page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (!page && gfp_mask & __GFP_NOFAIL) wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); @@ -2455,7 +2459,7 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, return page; } -static void prepare_slowpath(gfp_t gfp_mask, unsigned int order, +static void wake_all_kswapds(unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, struct zone *preferred_zone) @@ -2463,29 +2467,15 @@ static void prepare_slowpath(gfp_t gfp_mask, unsigned int order, 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 - * 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)); - } + 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) { int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; - const gfp_t wait = gfp_mask & __GFP_WAIT; + const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD)); /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH); @@ -2494,20 +2484,20 @@ gfp_to_alloc_flags(gfp_t gfp_mask) * The caller may dip into page reserves a bit more if the caller * cannot run direct reclaim, or if the caller has realtime scheduling * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will - * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH). + * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH). */ alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); - if (!wait) { + if (atomic) { /* - * Not worth trying to allocate harder for - * __GFP_NOMEMALLOC even if it can't schedule. + * Not worth trying to allocate harder for __GFP_NOMEMALLOC even + * if it can't schedule. */ - if (!(gfp_mask & __GFP_NOMEMALLOC)) + if (!(gfp_mask & __GFP_NOMEMALLOC)) alloc_flags |= ALLOC_HARDER; /* - * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. - * See also cpuset_zone_allowed() comment in kernel/cpuset.c. + * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the + * comment for __cpuset_node_allowed_softwall(). */ alloc_flags &= ~ALLOC_CPUSET; } else if (unlikely(rt_task(current)) && !in_interrupt()) @@ -2539,14 +2529,14 @@ static inline struct page * __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + int classzone_idx, int migratetype) { const gfp_t wait = gfp_mask & __GFP_WAIT; struct page *page = NULL; int alloc_flags; unsigned long pages_reclaimed = 0; unsigned long did_some_progress; - bool sync_migration = false; + enum migrate_mode migration_mode = MIGRATE_ASYNC; bool deferred_compaction = false; bool contended_compaction = false; @@ -2569,12 +2559,13 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, * allowed per node queues are empty and that nodes are * over allocated. */ - if (gfp_thisnode_allocation(gfp_mask)) + if (IS_ENABLED(CONFIG_NUMA) && + (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 @@ -2587,15 +2578,19 @@ restart: * Find the true preferred zone if the allocation is unconstrained by * cpusets. */ - if (!(alloc_flags & ALLOC_CPUSET) && !nodemask) - first_zones_zonelist(zonelist, high_zoneidx, NULL, - &preferred_zone); + if (!(alloc_flags & ALLOC_CPUSET) && !nodemask) { + struct zoneref *preferred_zoneref; + preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx, + NULL, + &preferred_zone); + classzone_idx = zonelist_zone_idx(preferred_zoneref); + } rebalance: /* This is the last chance, in general, before the goto nopage. */ page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) goto got_pg; @@ -2610,7 +2605,7 @@ rebalance: page = __alloc_pages_high_priority(gfp_mask, order, zonelist, high_zoneidx, nodemask, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) { goto got_pg; } @@ -2632,17 +2627,16 @@ rebalance: * Try direct compaction. The first pass is asynchronous. Subsequent * attempts after direct reclaim are synchronous */ - page = __alloc_pages_direct_compact(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, sync_migration, - &contended_compaction, + page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, + high_zoneidx, nodemask, alloc_flags, + preferred_zone, + classzone_idx, migratetype, + migration_mode, &contended_compaction, &deferred_compaction, &did_some_progress); if (page) goto got_pg; - sync_migration = true; + migration_mode = MIGRATE_SYNC_LIGHT; /* * If compaction is deferred for high-order allocations, it is because @@ -2659,7 +2653,8 @@ rebalance: zonelist, high_zoneidx, nodemask, alloc_flags, preferred_zone, - migratetype, &did_some_progress); + classzone_idx, migratetype, + &did_some_progress); if (page) goto got_pg; @@ -2678,7 +2673,7 @@ rebalance: page = __alloc_pages_may_oom(gfp_mask, order, zonelist, high_zoneidx, nodemask, preferred_zone, - migratetype); + classzone_idx, migratetype); if (page) goto got_pg; @@ -2717,12 +2712,11 @@ rebalance: * direct reclaim and reclaim/compaction depends on compaction * being called after reclaim so call directly if necessary */ - page = __alloc_pages_direct_compact(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, sync_migration, - &contended_compaction, + page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, + high_zoneidx, nodemask, alloc_flags, + preferred_zone, + classzone_idx, migratetype, + migration_mode, &contended_compaction, &deferred_compaction, &did_some_progress); if (page) @@ -2748,11 +2742,13 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, { enum zone_type high_zoneidx = gfp_zone(gfp_mask); struct zone *preferred_zone; + struct zoneref *preferred_zoneref; 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; + int classzone_idx; gfp_mask &= gfp_allowed_mask; @@ -2779,14 +2775,15 @@ __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, + preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx, nodemask ? : &cpuset_current_mems_allowed, &preferred_zone); if (!preferred_zone) goto out; + classzone_idx = zonelist_zone_idx(preferred_zoneref); #ifdef CONFIG_CMA if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE) @@ -2795,7 +2792,7 @@ retry_cpuset: /* First allocation attempt */ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, zonelist, high_zoneidx, alloc_flags, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (unlikely(!page)) { /* * Runtime PM, block IO and its error handling path @@ -2805,7 +2802,7 @@ retry_cpuset: gfp_mask = memalloc_noio_flags(gfp_mask); page = __alloc_pages_slowpath(gfp_mask, order, zonelist, high_zoneidx, nodemask, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); } trace_mm_page_alloc(page, order, gfp_mask, migratetype); @@ -2817,7 +2814,7 @@ 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); @@ -2856,7 +2853,7 @@ void __free_pages(struct page *page, unsigned int order) { if (put_page_testzero(page)) { if (order == 0) - free_hot_cold_page(page, 0); + free_hot_cold_page(page, false); else __free_pages_ok(page, order); } @@ -3085,9 +3082,9 @@ 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; } @@ -3240,12 +3237,12 @@ void show_free_areas(unsigned int filter) K(zone_page_state(zone, NR_BOUNCE)), K(zone_page_state(zone, NR_FREE_CMA_PAGES)), K(zone_page_state(zone, NR_WRITEBACK_TEMP)), - zone->pages_scanned, + K(zone_page_state(zone, NR_PAGES_SCANNED)), (!zone_reclaimable(zone) ? "yes" : "no") ); printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) - printk(" %lu", zone->lowmem_reserve[i]); + printk(" %ld", zone->lowmem_reserve[i]); printk("\n"); } @@ -3985,6 +3982,7 @@ 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 @@ -4006,6 +4004,12 @@ 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)) @@ -4043,6 +4047,12 @@ 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; } /* @@ -4122,7 +4132,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, static void __meminit zone_init_free_lists(struct zone *zone) { - int order, t; + unsigned int order, t; for_each_migratetype_order(order, t) { INIT_LIST_HEAD(&zone->free_area[order].free_list[t]); zone->free_area[order].nr_free = 0; @@ -4134,7 +4144,7 @@ static void __meminit zone_init_free_lists(struct zone *zone) memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY) #endif -static int __meminit zone_batchsize(struct zone *zone) +static int zone_batchsize(struct zone *zone) { #ifdef CONFIG_MMU int batch; @@ -4250,8 +4260,8 @@ static void pageset_set_high(struct per_cpu_pageset *p, pageset_update(&p->pcp, high, batch); } -static void __meminit pageset_set_high_and_batch(struct zone *zone, - struct per_cpu_pageset *pcp) +static void pageset_set_high_and_batch(struct zone *zone, + struct per_cpu_pageset *pcp) { if (percpu_pagelist_fraction) pageset_set_high(pcp, @@ -4945,7 +4955,8 @@ 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 @@ -5519,7 +5530,6 @@ static int page_alloc_cpu_notify(struct notifier_block *self, void __init page_alloc_init(void) { hotcpu_notifier(page_alloc_cpu_notify, 0); - local_irq_lock_init(pa_lock); } /* @@ -5535,7 +5545,7 @@ static void calculate_totalreserve_pages(void) for_each_online_pgdat(pgdat) { for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; - unsigned long max = 0; + long max = 0; /* Find valid and maximum lowmem_reserve in the zone */ for (j = i; j < MAX_NR_ZONES; j++) { @@ -5650,9 +5660,8 @@ static void __setup_per_zone_wmarks(void) zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); __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])); setup_zone_migrate_reserve(zone); spin_unlock_irqrestore(&zone->lock, flags); @@ -5777,7 +5786,12 @@ 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(); @@ -5845,23 +5859,38 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; - unsigned int cpu; + int old_percpu_pagelist_fraction; int ret; + mutex_lock(&pcp_batch_high_lock); + old_percpu_pagelist_fraction = percpu_pagelist_fraction; + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); - if (!write || (ret < 0)) - return ret; + if (!write || ret < 0) + goto out; + + /* Sanity checking to avoid pcp imbalance */ + if (percpu_pagelist_fraction && + percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) { + percpu_pagelist_fraction = old_percpu_pagelist_fraction; + ret = -EINVAL; + goto out; + } + + /* No change? */ + if (percpu_pagelist_fraction == old_percpu_pagelist_fraction) + goto out; - mutex_lock(&pcp_batch_high_lock); for_each_populated_zone(zone) { - unsigned long high; - high = zone->managed_pages / percpu_pagelist_fraction; + unsigned int cpu; + for_each_possible_cpu(cpu) - pageset_set_high(per_cpu_ptr(zone->pageset, cpu), - high); + pageset_set_high_and_batch(zone, + per_cpu_ptr(zone->pageset, cpu)); } +out: mutex_unlock(&pcp_batch_high_lock); - return 0; + return ret; } int hashdist = HASHDIST_DEFAULT; @@ -6004,53 +6033,64 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn) * @end_bitidx: The last bit of interest * returns pageblock_bits flags */ -unsigned long get_pageblock_flags_group(struct page *page, - int start_bitidx, int end_bitidx) +unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, + unsigned long end_bitidx, + unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx; - unsigned long flags = 0; - unsigned long value = 1; + unsigned long bitidx, word_bitidx; + unsigned long word; zone = page_zone(page); - pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); - for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) - if (test_bit(bitidx + start_bitidx, bitmap)) - flags |= value; - - return flags; + word = bitmap[word_bitidx]; + bitidx += end_bitidx; + return (word >> (BITS_PER_LONG - bitidx - 1)) & mask; } /** - * set_pageblock_flags_group - Set the requested group of flags for a pageblock_nr_pages block of pages + * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages * @page: The page within the block of interest * @start_bitidx: The first bit of interest * @end_bitidx: The last bit of interest * @flags: The flags to set */ -void set_pageblock_flags_group(struct page *page, unsigned long flags, - int start_bitidx, int end_bitidx) +void set_pfnblock_flags_mask(struct page *page, unsigned long flags, + unsigned long pfn, + unsigned long end_bitidx, + unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx; - unsigned long value = 1; + unsigned long bitidx, word_bitidx; + unsigned long old_word, word; + + BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); zone = page_zone(page); - pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); + VM_BUG_ON(!zone_spans_pfn(zone, pfn)); - for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) - if (flags & value) - __set_bit(bitidx + start_bitidx, bitmap); - else - __clear_bit(bitidx + start_bitidx, bitmap); + bitidx += end_bitidx; + mask <<= (BITS_PER_LONG - bitidx - 1); + flags <<= (BITS_PER_LONG - bitidx - 1); + + word = ACCESS_ONCE(bitmap[word_bitidx]); + for (;;) { + old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags); + if (word == old_word) + break; + word = old_word; + } } /* @@ -6210,7 +6250,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, cc->nr_migratepages -= nr_reclaimed; ret = migrate_pages(&cc->migratepages, alloc_migrate_target, - 0, MIGRATE_SYNC, MR_CMA); + NULL, 0, cc->mode, MR_CMA); } if (ret < 0) { putback_movable_pages(&cc->migratepages); @@ -6249,7 +6289,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, .nr_migratepages = 0, .order = -1, .zone = page_zone(pfn_to_page(start)), - .sync = true, + .mode = MIGRATE_SYNC, .ignore_skip_hint = true, }; INIT_LIST_HEAD(&cc.migratepages); @@ -6383,7 +6423,7 @@ void zone_pcp_reset(struct zone *zone) struct per_cpu_pageset *pset; /* avoid races with drain_pages() */ - local_lock_irqsave(pa_lock, flags); + local_irq_save(flags); if (zone->pageset != &boot_pageset) { for_each_online_cpu(cpu) { pset = per_cpu_ptr(zone->pageset, cpu); @@ -6392,7 +6432,7 @@ void zone_pcp_reset(struct zone *zone) free_percpu(zone->pageset); zone->pageset = &boot_pageset; } - local_unlock_irqrestore(pa_lock, flags); + local_irq_restore(flags); } #ifdef CONFIG_MEMORY_HOTREMOVE @@ -6404,7 +6444,7 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) { struct page *page; struct zone *zone; - int order, i; + unsigned int order, i; unsigned long pfn; unsigned long flags; /* find the first valid pfn */ @@ -6456,7 +6496,7 @@ bool is_free_buddy_page(struct page *page) struct zone *zone = page_zone(page); unsigned long pfn = page_to_pfn(page); unsigned long flags; - int order; + unsigned int order; spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 98caeee..e007236 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -13,14 +13,6 @@ static unsigned long total_usage; -static void page_cgroup_lock_init(struct page_cgroup *pc, int nr_pages) -{ -#ifdef CONFIG_PREEMPT_RT_BASE - for (; nr_pages; nr_pages--, pc++) - spin_lock_init(&pc->pcg_lock); -#endif -} - #if !defined(CONFIG_SPARSEMEM) @@ -68,7 +60,6 @@ static int __init alloc_node_page_cgroup(int nid) return -ENOMEM; NODE_DATA(nid)->node_page_cgroup = base; total_usage += table_size; - page_cgroup_lock_init(base, nr_pages); return 0; } @@ -159,8 +150,6 @@ static int __meminit init_section_page_cgroup(unsigned long pfn, int nid) return -ENOMEM; } - page_cgroup_lock_init(base, PAGES_PER_SECTION); - /* * The passed "pfn" may not be aligned to SECTION. For the calculation * we need to apply a mask. @@ -181,6 +170,7 @@ static void free_page_cgroup(void *addr) sizeof(struct page_cgroup) * PAGES_PER_SECTION; BUG_ON(PageReserved(page)); + kmemleak_free(addr); free_pages_exact(addr, table_size); } } diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index 3707c71..5110816 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -108,7 +108,7 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk, int page_start, int page_end) { const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD; - unsigned int cpu; + unsigned int cpu, tcpu; int i; for_each_possible_cpu(cpu) { @@ -116,14 +116,23 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk, struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); - if (!*pagep) { - pcpu_free_pages(chunk, pages, populated, - page_start, page_end); - return -ENOMEM; - } + if (!*pagep) + goto err; } } return 0; + +err: + while (--i >= page_start) + __free_page(pages[pcpu_page_idx(cpu, i)]); + + for_each_possible_cpu(tcpu) { + if (tcpu == cpu) + break; + for (i = page_start; i < page_end; i++) + __free_page(pages[pcpu_page_idx(tcpu, i)]); + } + return -ENOMEM; } /** @@ -263,6 +272,7 @@ err: __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), page_end - page_start); } + pcpu_post_unmap_tlb_flush(chunk, page_start, page_end); return err; } diff --git a/mm/percpu.c b/mm/percpu.c index 8c8e08f..25e2ea5 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -612,7 +612,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void) chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); if (!chunk->map) { - kfree(chunk); + pcpu_mem_free(chunk, pcpu_chunk_struct_size); return NULL; } diff --git a/mm/readahead.c b/mm/readahead.c index e4ed041..0f35e98 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); @@ -237,28 +236,14 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp, return ret; } +#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 +336,7 @@ 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; @@ -401,6 +386,7 @@ ondemand_readahead(struct address_space *mapping, unsigned long req_size) { unsigned long max = max_sane_readahead(ra->ra_pages); + pgoff_t prev_offset; /* * start of file @@ -430,7 +416,7 @@ 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) @@ -452,8 +438,11 @@ ondemand_readahead(struct address_space *mapping, /* * sequential cache miss + * trivial case: (offset - prev_offset) == 1 + * unaligned reads: (offset - prev_offset) == 0 */ - if (offset - (ra->prev_pos >> PAGE_CACHE_SHIFT) <= 1UL) + prev_offset = (unsigned long long)ra->prev_pos >> PAGE_CACHE_SHIFT; + if (offset - prev_offset <= 1UL) goto initial_readahead; /* @@ -103,6 +103,7 @@ static inline void anon_vma_free(struct anon_vma *anon_vma) * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ + might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); anon_vma_unlock_write(anon_vma); @@ -273,6 +274,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { struct anon_vma_chain *avc; struct anon_vma *anon_vma; + int error; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) @@ -282,8 +284,9 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ - if (anon_vma_clone(vma, pvma)) - return -ENOMEM; + error = anon_vma_clone(vma, pvma); + if (error) + return error; /* Then add our own anon_vma. */ anon_vma = anon_vma_alloc(); @@ -426,8 +429,9 @@ struct anon_vma *page_get_anon_vma(struct page *page) * above cannot corrupt). */ if (!page_mapped(page)) { + rcu_read_unlock(); put_anon_vma(anon_vma); - anon_vma = NULL; + return NULL; } out: rcu_read_unlock(); @@ -477,9 +481,9 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page) } if (!page_mapped(page)) { + rcu_read_unlock(); put_anon_vma(anon_vma); - anon_vma = NULL; - goto out; + return NULL; } /* we pinned the anon_vma, its safe to sleep */ @@ -567,6 +571,7 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) pgd_t *pgd; pud_t *pud; pmd_t *pmd = NULL; + pmd_t pmde; pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) @@ -577,7 +582,13 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) goto out; pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd)) + /* + * Some THP functions use the sequence pmdp_clear_flush(), set_pmd_at() + * without holding anon_vma lock for write. So when looking for a + * genuine pmde (in which to find pte), test present and !THP together. + */ + pmde = ACCESS_ONCE(*pmd); + if (!pmd_present(pmde) || pmd_trans_huge(pmde)) pmd = NULL; out: return pmd; @@ -613,9 +624,6 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm, if (!pmd) return NULL; - if (pmd_trans_huge(*pmd)) - return NULL; - pte = pte_offset_map(pmd, address); /* Make a quick check before getting the lock */ if (!sync && !pte_present(*pte)) { @@ -1392,9 +1400,19 @@ 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 */ } @@ -1671,10 +1689,9 @@ void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; + anon_vma_free(anon_vma); if (root != anon_vma && atomic_dec_and_test(&root->refcount)) anon_vma_free(root); - - anon_vma_free(anon_vma); } #ifdef CONFIG_MIGRATION @@ -80,11 +80,12 @@ static struct vfsmount *shm_mnt; #define SHORT_SYMLINK_LEN 128 /* - * shmem_fallocate and shmem_writepage communicate via inode->i_private - * (with i_mutex making sure that it has only one user at a time): - * we would prefer not to enlarge the shmem inode just for that. + * shmem_fallocate communicates with shmem_fault or shmem_writepage via + * inode->i_private (with i_mutex making sure that it has only one user at + * a time): we would prefer not to enlarge the shmem inode just for that. */ struct shmem_falloc { + wait_queue_head_t *waitq; /* faults into hole wait for punch to end */ pgoff_t start; /* start of range currently being fallocated */ pgoff_t next; /* the next page offset to be fallocated */ pgoff_t nr_falloced; /* how many new pages have been fallocated */ @@ -242,19 +243,17 @@ static int shmem_radix_tree_replace(struct address_space *mapping, pgoff_t index, void *expected, void *replacement) { void **pslot; - void *item = NULL; + void *item; VM_BUG_ON(!expected); + VM_BUG_ON(!replacement); pslot = radix_tree_lookup_slot(&mapping->page_tree, index); - if (pslot) - item = radix_tree_deref_slot_protected(pslot, - &mapping->tree_lock); + if (!pslot) + return -ENOENT; + item = radix_tree_deref_slot_protected(pslot, &mapping->tree_lock); if (item != expected) return -ENOENT; - if (replacement) - radix_tree_replace_slot(pslot, replacement); - else - radix_tree_delete(&mapping->page_tree, index); + radix_tree_replace_slot(pslot, replacement); return 0; } @@ -331,84 +330,20 @@ 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 +364,12 @@ 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 +401,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, pagevec_init(&pvec, 0); index = start; while (index < end) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + pvec.pages, indices); if (!pvec.nr) break; mem_cgroup_uncharge_start(); @@ -497,7 +432,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -533,22 +468,20 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, return; index = start; - for ( ; ; ) { + while (index < end) { 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) + /* If all gone or hole-punch or unfalloc, we're done */ + if (index == start || end != -1) break; + /* But if truncating, restart to make sure all gone */ index = start; continue; } - if ((index == start || unfalloc) && indices[0] >= end) { - shmem_deswap_pagevec(&pvec); - pagevec_release(&pvec); - break; - } mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; @@ -560,8 +493,12 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (radix_tree_exceptional_entry(page)) { if (unfalloc) continue; - nr_swaps_freed += !shmem_free_swap(mapping, - index, page); + if (shmem_free_swap(mapping, index, page)) { + /* Swap was replaced by page: retry */ + index--; + break; + } + nr_swaps_freed++; continue; } @@ -570,11 +507,16 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (page->mapping == mapping) { VM_BUG_ON(PageWriteback(page)); truncate_inode_page(mapping, page); + } else { + /* Page was replaced by swap: retry */ + unlock_page(page); + index--; + break; } } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; @@ -826,6 +768,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) spin_lock(&inode->i_lock); shmem_falloc = inode->i_private; if (shmem_falloc && + !shmem_falloc->waitq && index >= shmem_falloc->start && index < shmem_falloc->next) shmem_falloc->nr_unswapped++; @@ -1082,7 +1025,7 @@ 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; @@ -1094,6 +1037,9 @@ repeat: goto failed; } + if (page && sgp == SGP_WRITE) + mark_page_accessed(page); + /* fallocated page? */ if (page && !PageUptodate(page)) { if (sgp != SGP_READ) @@ -1175,6 +1121,9 @@ repeat: shmem_recalc_inode(inode); spin_unlock(&info->lock); + if (sgp == SGP_WRITE) + mark_page_accessed(page); + delete_from_swap_cache(page); set_page_dirty(page); swap_free(swap); @@ -1199,8 +1148,11 @@ repeat: goto decused; } - SetPageSwapBacked(page); + __SetPageSwapBacked(page); __set_page_locked(page); + if (sgp == SGP_WRITE) + init_page_accessed(page); + error = mem_cgroup_cache_charge(page, current->mm, gfp & GFP_RECLAIM_MASK); if (error) @@ -1300,6 +1252,64 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) int error; int ret = VM_FAULT_LOCKED; + /* + * Trinity finds that probing a hole which tmpfs is punching can + * prevent the hole-punch from ever completing: which in turn + * locks writers out with its hold on i_mutex. So refrain from + * faulting pages into the hole while it's being punched. Although + * shmem_undo_range() does remove the additions, it may be unable to + * keep up, as each new page needs its own unmap_mapping_range() call, + * and the i_mmap tree grows ever slower to scan if new vmas are added. + * + * It does not matter if we sometimes reach this check just before the + * hole-punch begins, so that one fault then races with the punch: + * we just need to make racing faults a rare case. + * + * The implementation below would be much simpler if we just used a + * standard mutex or completion: but we cannot take i_mutex in fault, + * and bloating every shmem inode for this unlikely case would be sad. + */ + if (unlikely(inode->i_private)) { + struct shmem_falloc *shmem_falloc; + + spin_lock(&inode->i_lock); + shmem_falloc = inode->i_private; + if (shmem_falloc && + shmem_falloc->waitq && + vmf->pgoff >= shmem_falloc->start && + vmf->pgoff < shmem_falloc->next) { + wait_queue_head_t *shmem_falloc_waitq; + DEFINE_WAIT(shmem_fault_wait); + + ret = VM_FAULT_NOPAGE; + if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) && + !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) { + /* It's polite to up mmap_sem if we can */ + up_read(&vma->vm_mm->mmap_sem); + ret = VM_FAULT_RETRY; + } + + shmem_falloc_waitq = shmem_falloc->waitq; + prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait, + TASK_UNINTERRUPTIBLE); + spin_unlock(&inode->i_lock); + schedule(); + + /* + * shmem_falloc_waitq points into the shmem_fallocate() + * stack of the hole-punching task: shmem_falloc_waitq + * is usually invalid by the time we reach here, but + * finish_wait() does not dereference it in that case; + * though i_lock needed lest racing with wake_up_all(). + */ + spin_lock(&inode->i_lock); + finish_wait(shmem_falloc_waitq, &shmem_fault_wait); + spin_unlock(&inode->i_lock); + return ret; + } + spin_unlock(&inode->i_lock); + } + error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret); if (error) return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS); @@ -1419,6 +1429,11 @@ 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 +1746,7 @@ 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 +1773,7 @@ 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(); @@ -1819,12 +1834,25 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, struct address_space *mapping = file->f_mapping; loff_t unmap_start = round_up(offset, PAGE_SIZE); loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1; + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq); + + shmem_falloc.waitq = &shmem_falloc_waitq; + shmem_falloc.start = unmap_start >> PAGE_SHIFT; + shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT; + spin_lock(&inode->i_lock); + inode->i_private = &shmem_falloc; + spin_unlock(&inode->i_lock); if ((u64)unmap_end > (u64)unmap_start) unmap_mapping_range(mapping, unmap_start, 1 + unmap_end - unmap_start, 0); shmem_truncate_range(inode, offset, offset + len - 1); /* No need to unmap again: hole-punching leaves COWed pages */ + + spin_lock(&inode->i_lock); + inode->i_private = NULL; + wake_up_all(&shmem_falloc_waitq); + spin_unlock(&inode->i_lock); error = 0; goto out; } @@ -1842,6 +1870,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, goto out; } + shmem_falloc.waitq = NULL; shmem_falloc.start = start; shmem_falloc.next = start; shmem_falloc.nr_falloced = 0; @@ -2077,8 +2106,10 @@ static int shmem_rename(struct inode *old_dir, struct dentry *old_dentry, struct if (new_dentry->d_inode) { (void) shmem_unlink(new_dir, new_dentry); - if (they_are_dirs) + if (they_are_dirs) { + drop_nlink(new_dentry->d_inode); drop_nlink(old_dir); + } } else if (they_are_dirs) { drop_nlink(old_dir); inc_nlink(new_dir); @@ -930,7 +930,8 @@ static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac, { if (unlikely(pfmemalloc_active)) { /* Some pfmemalloc slabs exist, check if this is one */ - struct page *page = virt_to_head_page(objp); + struct slab *slabp = virt_to_slab(objp); + struct page *page = virt_to_head_page(slabp->s_mem); if (PageSlabPfmemalloc(page)) set_obj_pfmemalloc(&objp); } @@ -1776,7 +1777,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) __SetPageSlab(page + i); if (page->pfmemalloc) - SetPageSlabPfmemalloc(page + i); + SetPageSlabPfmemalloc(page); } memcg_bind_pages(cachep, cachep->gfporder); @@ -1809,9 +1810,10 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr) else sub_zone_page_state(page_zone(page), NR_SLAB_UNRECLAIMABLE, nr_freed); + + __ClearPageSlabPfmemalloc(page); while (i--) { BUG_ON(!PageSlab(page)); - __ClearPageSlabPfmemalloc(page); __ClearPageSlab(page); page++; } @@ -2220,7 +2222,8 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) int __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) { - size_t left_over, slab_size, ralign; + size_t left_over, slab_size; + size_t ralign = BYTES_PER_WORD; gfp_t gfp; int err; size_t size = cachep->size; @@ -2253,14 +2256,6 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) size &= ~(BYTES_PER_WORD - 1); } - /* - * Redzoning and user store require word alignment or possibly larger. - * Note this will be overridden by architecture or caller mandated - * alignment if either is greater than BYTES_PER_WORD. - */ - if (flags & SLAB_STORE_USER) - ralign = BYTES_PER_WORD; - if (flags & SLAB_RED_ZONE) { ralign = REDZONE_ALIGN; /* If redzoning, ensure that the second redzone is suitably @@ -3220,7 +3215,7 @@ 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(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = node_zonelist(slab_node(), flags); retry: @@ -3276,7 +3271,7 @@ 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; } @@ -247,11 +247,7 @@ static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x) * The slab lists for all objects. */ struct kmem_cache_node { -#ifdef CONFIG_SLUB - raw_spinlock_t list_lock; -#else spinlock_t list_lock; -#endif #ifdef CONFIG_SLAB struct list_head slabs_partial; /* partial list first, better asm code */ diff --git a/mm/slab_common.c b/mm/slab_common.c index e2e98af..97e5f5e 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -56,7 +56,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, continue; } -#if !defined(CONFIG_SLUB) || !defined(CONFIG_SLUB_DEBUG_ON) +#if !defined(CONFIG_SLUB) /* * For simplicity, we won't check this in the list of memcg * caches. We have control over memcg naming, and if there @@ -1087,7 +1087,7 @@ static noinline struct kmem_cache_node *free_debug_processing( { struct kmem_cache_node *n = get_node(s, page_to_nid(page)); - raw_spin_lock_irqsave(&n->list_lock, *flags); + spin_lock_irqsave(&n->list_lock, *flags); slab_lock(page); if (!check_slab(s, page)) @@ -1135,7 +1135,7 @@ out: fail: slab_unlock(page); - raw_spin_unlock_irqrestore(&n->list_lock, *flags); + spin_unlock_irqrestore(&n->list_lock, *flags); slab_fix(s, "Object at 0x%p not freed", object); return NULL; } @@ -1270,12 +1270,6 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) {} #endif /* CONFIG_SLUB_DEBUG */ -struct slub_free_list { - raw_spinlock_t lock; - struct list_head list; -}; -static DEFINE_PER_CPU(struct slub_free_list, slub_free_list); - /* * Slab allocation and freeing */ @@ -1297,15 +1291,10 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) struct page *page; struct kmem_cache_order_objects oo = s->oo; gfp_t alloc_gfp; - bool enableirqs; flags &= gfp_allowed_mask; - enableirqs = (flags & __GFP_WAIT) != 0; -#ifdef CONFIG_PREEMPT_RT_FULL - enableirqs |= system_state == SYSTEM_RUNNING; -#endif - if (enableirqs) + if (flags & __GFP_WAIT) local_irq_enable(); flags |= s->allocflags; @@ -1345,7 +1334,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) kmemcheck_mark_unallocated_pages(page, pages); } - if (enableirqs) + if (flags & __GFP_WAIT) local_irq_disable(); if (!page) return NULL; @@ -1363,10 +1352,8 @@ static void setup_object(struct kmem_cache *s, struct page *page, void *object) { setup_object_debug(s, page, object); -#ifndef CONFIG_PREEMPT_RT_FULL if (unlikely(s->ctor)) s->ctor(object); -#endif } static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) @@ -1444,16 +1431,6 @@ static void __free_slab(struct kmem_cache *s, struct page *page) __free_memcg_kmem_pages(page, order); } -static void free_delayed(struct list_head *h) -{ - while(!list_empty(h)) { - struct page *page = list_first_entry(h, struct page, lru); - - list_del(&page->lru); - __free_slab(page->slab_cache, page); - } -} - #define need_reserve_slab_rcu \ (sizeof(((struct page *)NULL)->lru) < sizeof(struct rcu_head)) @@ -1488,12 +1465,6 @@ static void free_slab(struct kmem_cache *s, struct page *page) } call_rcu(head, rcu_free_slab); - } else if (irqs_disabled()) { - struct slub_free_list *f = &__get_cpu_var(slub_free_list); - - raw_spin_lock(&f->lock); - list_add(&page->lru, &f->list); - raw_spin_unlock(&f->lock); } else __free_slab(s, page); } @@ -1598,7 +1569,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, if (!n || !n->nr_partial) return NULL; - raw_spin_lock(&n->list_lock); + spin_lock(&n->list_lock); list_for_each_entry_safe(page, page2, &n->partial, lru) { void *t; @@ -1623,7 +1594,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, break; } - raw_spin_unlock(&n->list_lock); + spin_unlock(&n->list_lock); return object; } @@ -1664,7 +1635,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, return NULL; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = node_zonelist(slab_node(), flags); for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { struct kmem_cache_node *n; @@ -1676,19 +1647,17 @@ 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; } @@ -1866,7 +1835,7 @@ redo: * that acquire_slab() will see a slab page that * is frozen */ - raw_spin_lock(&n->list_lock); + spin_lock(&n->list_lock); } } else { m = M_FULL; @@ -1877,7 +1846,7 @@ redo: * slabs from diagnostic functions will not see * any frozen slabs. */ - raw_spin_lock(&n->list_lock); + spin_lock(&n->list_lock); } } @@ -1912,7 +1881,7 @@ redo: goto redo; if (lock) - raw_spin_unlock(&n->list_lock); + spin_unlock(&n->list_lock); if (m == M_FREE) { stat(s, DEACTIVATE_EMPTY); @@ -1944,10 +1913,10 @@ static void unfreeze_partials(struct kmem_cache *s, n2 = get_node(s, page_to_nid(page)); if (n != n2) { if (n) - raw_spin_unlock(&n->list_lock); + spin_unlock(&n->list_lock); n = n2; - raw_spin_lock(&n->list_lock); + spin_lock(&n->list_lock); } do { @@ -1976,7 +1945,7 @@ static void unfreeze_partials(struct kmem_cache *s, } if (n) - raw_spin_unlock(&n->list_lock); + spin_unlock(&n->list_lock); while (discard_page) { page = discard_page; @@ -2014,21 +1983,14 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) pobjects = oldpage->pobjects; pages = oldpage->pages; if (drain && pobjects > s->cpu_partial) { - struct slub_free_list *f; unsigned long flags; - LIST_HEAD(tofree); /* * partial array is full. Move the existing * set to the per node partial list. */ local_irq_save(flags); unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); - f = &__get_cpu_var(slub_free_list); - raw_spin_lock(&f->lock); - list_splice_init(&f->list, &tofree); - raw_spin_unlock(&f->lock); local_irq_restore(flags); - free_delayed(&tofree); oldpage = NULL; pobjects = 0; pages = 0; @@ -2092,22 +2054,7 @@ static bool has_cpu_slab(int cpu, void *info) static void flush_all(struct kmem_cache *s) { - LIST_HEAD(tofree); - int cpu; - on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC); - for_each_online_cpu(cpu) { - struct slub_free_list *f; - - if (!has_cpu_slab(cpu, s)) - continue; - - f = &per_cpu(slub_free_list, cpu); - raw_spin_lock_irq(&f->lock); - list_splice_init(&f->list, &tofree); - raw_spin_unlock_irq(&f->lock); - free_delayed(&tofree); - } } /* @@ -2135,10 +2082,10 @@ static unsigned long count_partial(struct kmem_cache_node *n, unsigned long x = 0; struct page *page; - raw_spin_lock_irqsave(&n->list_lock, flags); + spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, lru) x += get_count(page); - raw_spin_unlock_irqrestore(&n->list_lock, flags); + spin_unlock_irqrestore(&n->list_lock, flags); return x; } @@ -2281,11 +2228,9 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page) static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr, struct kmem_cache_cpu *c) { - struct slub_free_list *f; void *freelist; struct page *page; unsigned long flags; - LIST_HEAD(tofree); local_irq_save(flags); #ifdef CONFIG_PREEMPT @@ -2348,13 +2293,7 @@ load_freelist: VM_BUG_ON(!c->page->frozen); c->freelist = get_freepointer(s, freelist); c->tid = next_tid(c->tid); -out: - f = &__get_cpu_var(slub_free_list); - raw_spin_lock(&f->lock); - list_splice_init(&f->list, &tofree); - raw_spin_unlock(&f->lock); local_irq_restore(flags); - free_delayed(&tofree); return freelist; new_slab: @@ -2372,7 +2311,9 @@ new_slab: if (unlikely(!freelist)) { if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit()) slab_out_of_memory(s, gfpflags, node); - goto out; + + local_irq_restore(flags); + return NULL; } page = c->page; @@ -2387,7 +2328,8 @@ new_slab: deactivate_slab(s, page, get_freepointer(s, freelist)); c->page = NULL; c->freelist = NULL; - goto out; + local_irq_restore(flags); + return freelist; } /* @@ -2472,10 +2414,6 @@ redo: if (unlikely(gfpflags & __GFP_ZERO) && object) memset(object, 0, s->object_size); -#ifdef CONFIG_PREEMPT_RT_FULL - if (unlikely(s->ctor) && object) - s->ctor(object); -#endif slab_post_alloc_hook(s, gfpflags, object); @@ -2563,7 +2501,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, do { if (unlikely(n)) { - raw_spin_unlock_irqrestore(&n->list_lock, flags); + spin_unlock_irqrestore(&n->list_lock, flags); n = NULL; } prior = page->freelist; @@ -2595,7 +2533,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, * Otherwise the list_lock will synchronize with * other processors updating the list of slabs. */ - raw_spin_lock_irqsave(&n->list_lock, flags); + spin_lock_irqsave(&n->list_lock, flags); } } @@ -2637,7 +2575,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, add_partial(n, page, DEACTIVATE_TO_TAIL); stat(s, FREE_ADD_PARTIAL); } - raw_spin_unlock_irqrestore(&n->list_lock, flags); + spin_unlock_irqrestore(&n->list_lock, flags); return; slab_empty: @@ -2651,7 +2589,7 @@ slab_empty: /* Slab must be on the full list */ remove_full(s, page); - raw_spin_unlock_irqrestore(&n->list_lock, flags); + spin_unlock_irqrestore(&n->list_lock, flags); stat(s, FREE_SLAB); discard_slab(s, page); } @@ -2853,7 +2791,7 @@ static void init_kmem_cache_node(struct kmem_cache_node *n) { n->nr_partial = 0; - raw_spin_lock_init(&n->list_lock); + spin_lock_init(&n->list_lock); INIT_LIST_HEAD(&n->partial); #ifdef CONFIG_SLUB_DEBUG atomic_long_set(&n->nr_slabs, 0); @@ -3439,7 +3377,7 @@ int kmem_cache_shrink(struct kmem_cache *s) for (i = 0; i < objects; i++) INIT_LIST_HEAD(slabs_by_inuse + i); - raw_spin_lock_irqsave(&n->list_lock, flags); + spin_lock_irqsave(&n->list_lock, flags); /* * Build lists indexed by the items in use in each slab. @@ -3460,7 +3398,7 @@ int kmem_cache_shrink(struct kmem_cache *s) for (i = objects - 1; i > 0; i--) list_splice(slabs_by_inuse + i, n->partial.prev); - raw_spin_unlock_irqrestore(&n->list_lock, flags); + spin_unlock_irqrestore(&n->list_lock, flags); /* Release empty slabs */ list_for_each_entry_safe(page, t, slabs_by_inuse, lru) @@ -3636,12 +3574,6 @@ void __init kmem_cache_init(void) { static __initdata struct kmem_cache boot_kmem_cache, boot_kmem_cache_node; - int cpu; - - for_each_possible_cpu(cpu) { - raw_spin_lock_init(&per_cpu(slub_free_list, cpu).lock); - INIT_LIST_HEAD(&per_cpu(slub_free_list, cpu).list); - } if (debug_guardpage_minorder()) slub_max_order = 0; @@ -3946,7 +3878,7 @@ static int validate_slab_node(struct kmem_cache *s, struct page *page; unsigned long flags; - raw_spin_lock_irqsave(&n->list_lock, flags); + spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, lru) { validate_slab_slab(s, page, map); @@ -3969,7 +3901,7 @@ static int validate_slab_node(struct kmem_cache *s, atomic_long_read(&n->nr_slabs)); out: - raw_spin_unlock_irqrestore(&n->list_lock, flags); + spin_unlock_irqrestore(&n->list_lock, flags); return count; } @@ -4159,12 +4091,12 @@ static int list_locations(struct kmem_cache *s, char *buf, if (!atomic_long_read(&n->nr_slabs)) continue; - raw_spin_lock_irqsave(&n->list_lock, flags); + spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, lru) process_slab(&t, s, page, alloc, map); list_for_each_entry(page, &n->full, lru) process_slab(&t, s, page, alloc, map); - raw_spin_unlock_irqrestore(&n->list_lock, flags); + spin_unlock_irqrestore(&n->list_lock, flags); } for (i = 0; i < t.count; i++) { @@ -32,7 +32,6 @@ #include <linux/gfp.h> #include <linux/uio.h> #include <linux/hugetlb.h> -#include <linux/locallock.h> #include "internal.h" @@ -46,9 +45,6 @@ static DEFINE_PER_CPU(struct pagevec, lru_add_pvec); static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs); -static DEFINE_LOCAL_IRQ_LOCK(rotate_lock); -static DEFINE_LOCAL_IRQ_LOCK(swapvec_lock); - /* * This path almost never happens for VM activity - pages are normally * freed via pagevecs. But it gets used by networking. @@ -72,7 +68,7 @@ static void __page_cache_release(struct page *page) static void __put_single_page(struct page *page) { __page_cache_release(page); - free_hot_cold_page(page, 0); + free_hot_cold_page(page, false); } static void __put_compound_page(struct page *page) @@ -412,11 +408,11 @@ void rotate_reclaimable_page(struct page *page) unsigned long flags; page_cache_get(page); - local_lock_irqsave(rotate_lock, flags); + local_irq_save(flags); pvec = &__get_cpu_var(lru_rotate_pvecs); if (!pagevec_add(pvec, page)) pagevec_move_tail(pvec); - local_unlock_irqrestore(rotate_lock, flags); + local_irq_restore(flags); } } @@ -441,7 +437,7 @@ static void __activate_page(struct page *page, struct lruvec *lruvec, SetPageActive(page); lru += LRU_ACTIVE; add_page_to_lru_list(page, lruvec, lru); - trace_mm_lru_activate(page, page_to_pfn(page)); + trace_mm_lru_activate(page); __count_vm_event(PGACTIVATE); update_page_reclaim_stat(lruvec, file, 1); @@ -467,13 +463,12 @@ static bool need_activate_page_drain(int cpu) void activate_page(struct page *page) { if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { - struct pagevec *pvec = &get_locked_var(swapvec_lock, - activate_page_pvecs); + struct pagevec *pvec = &get_cpu_var(activate_page_pvecs); page_cache_get(page); if (!pagevec_add(pvec, page)) pagevec_lru_move_fn(pvec, __activate_page, NULL); - put_locked_var(swapvec_lock, activate_page_pvecs); + put_cpu_var(activate_page_pvecs); } } @@ -499,7 +494,7 @@ void activate_page(struct page *page) static void __lru_cache_activate_page(struct page *page) { - struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); + struct pagevec *pvec = &get_cpu_var(lru_add_pvec); int i; /* @@ -521,7 +516,7 @@ static void __lru_cache_activate_page(struct page *page) } } - put_locked_var(swapvec_lock, lru_add_pvec); + put_cpu_var(lru_add_pvec); } /* @@ -554,26 +549,54 @@ void mark_page_accessed(struct page *page) EXPORT_SYMBOL(mark_page_accessed); /* - * Queue the page for addition to the LRU via pagevec. The decision on whether - * to add the page to the [in]active [file|anon] list is deferred until the - * pagevec is drained. This gives a chance for the caller of __lru_cache_add() - * have the page added to the active list using mark_page_accessed(). + * Used to mark_page_accessed(page) that is not visible yet and when it is + * still safe to use non-atomic ops */ -void __lru_cache_add(struct page *page) +void init_page_accessed(struct page *page) { - struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); + if (!PageReferenced(page)) + __SetPageReferenced(page); +} +EXPORT_SYMBOL(init_page_accessed); + +static void __lru_cache_add(struct page *page) +{ + struct pagevec *pvec = &get_cpu_var(lru_add_pvec); page_cache_get(page); if (!pagevec_space(pvec)) __pagevec_lru_add(pvec); pagevec_add(pvec, page); - put_locked_var(swapvec_lock, lru_add_pvec); + put_cpu_var(lru_add_pvec); +} + +/** + * lru_cache_add: add a page to the page lists + * @page: the page to add + */ +void lru_cache_add_anon(struct page *page) +{ + if (PageActive(page)) + ClearPageActive(page); + __lru_cache_add(page); } -EXPORT_SYMBOL(__lru_cache_add); + +void lru_cache_add_file(struct page *page) +{ + if (PageActive(page)) + ClearPageActive(page); + __lru_cache_add(page); +} +EXPORT_SYMBOL(lru_cache_add_file); /** * lru_cache_add - add a page to a page list * @page: the page to be added to the LRU. + * + * Queue the page for addition to the LRU via pagevec. The decision on whether + * to add the page to the [in]active [file|anon] list is deferred until the + * pagevec is drained. This gives a chance for the caller of lru_cache_add() + * have the page added to the active list using mark_page_accessed(). */ void lru_cache_add(struct page *page) { @@ -690,9 +713,9 @@ void lru_add_drain_cpu(int cpu) unsigned long flags; /* No harm done if a racing interrupt already did this */ - local_lock_irqsave(rotate_lock, flags); + local_irq_save(flags); pagevec_move_tail(pvec); - local_unlock_irqrestore(rotate_lock, flags); + local_irq_restore(flags); } pvec = &per_cpu(lru_deactivate_pvecs, cpu); @@ -720,19 +743,18 @@ void deactivate_page(struct page *page) return; if (likely(get_page_unless_zero(page))) { - struct pagevec *pvec = &get_locked_var(swapvec_lock, - lru_deactivate_pvecs); + struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs); if (!pagevec_add(pvec, page)) pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); - put_locked_var(swapvec_lock, lru_deactivate_pvecs); + put_cpu_var(lru_deactivate_pvecs); } } void lru_add_drain(void) { - lru_add_drain_cpu(local_lock_cpu(swapvec_lock)); - local_unlock_cpu(swapvec_lock); + lru_add_drain_cpu(get_cpu()); + put_cpu(); } static void lru_add_drain_per_cpu(struct work_struct *dummy) @@ -785,7 +807,7 @@ void lru_add_drain_all(void) * grabbed the page via the LRU. If it did, give up: shrink_inactive_list() * will free it. */ -void release_pages(struct page **pages, int nr, int cold) +void release_pages(struct page **pages, int nr, bool cold) { int i; LIST_HEAD(pages_to_free); @@ -826,7 +848,7 @@ void release_pages(struct page **pages, int nr, int cold) } /* Clear Active bit in case of parallel mark_page_accessed */ - ClearPageActive(page); + __ClearPageActive(page); list_add(&page->lru, &pages_to_free); } @@ -908,7 +930,7 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec, SetPageLRU(page); add_page_to_lru_list(page, lruvec, lru); update_page_reclaim_stat(lruvec, file, active); - trace_mm_lru_insertion(page, page_to_pfn(page), lru, trace_pagemap_flags(page)); + trace_mm_lru_insertion(page, lru); } /* @@ -922,6 +944,57 @@ 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 e6f15f8..4079edf 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()); @@ -268,7 +270,7 @@ void free_pages_and_swap_cache(struct page **pages, int nr) for (i = 0; i < todo; i++) free_swap_cache(pagep[i]); - release_pages(pagep, todo, 0); + release_pages(pagep, todo, false); pagep += todo; nr -= todo; } @@ -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 0ec2eaf..660b9c0 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -51,14 +51,32 @@ atomic_long_t nr_swap_pages; /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority; -static atomic_t highest_priority_index = ATOMIC_INIT(-1); static const char Bad_file[] = "Bad swap file entry "; 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 "; -struct swap_list_t swap_list = {-1, -1}; +/* + * all active swap_info_structs + * protected with swap_lock, and ordered by priority. + */ +PLIST_HEAD(swap_active_head); + +/* + * all available (active, not full) swap_info_structs + * protected with swap_avail_lock, ordered by priority. + * This is used by get_swap_page() instead of swap_active_head + * because swap_active_head includes all swap_info_structs, + * but get_swap_page() doesn't need to look at full ones. + * This uses its own lock instead of swap_lock because when a + * swap_info_struct changes between not-full/full, it needs to + * add/remove itself to/from this list, but the swap_info_struct->lock + * is held and the locking order requires swap_lock to be taken + * before any swap_info_struct->lock. + */ +static PLIST_HEAD(swap_avail_head); +static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; @@ -591,6 +609,9 @@ checks: if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; + spin_lock(&swap_avail_lock); + plist_del(&si->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); } si->swap_map[offset] = usage; inc_cluster_info_page(si, si->cluster_info, offset); @@ -639,71 +660,65 @@ no_page: swp_entry_t get_swap_page(void) { - struct swap_info_struct *si; + struct swap_info_struct *si, *next; pgoff_t offset; - int type, next; - int wrapped = 0; - int hp_index; - spin_lock(&swap_lock); if (atomic_long_read(&nr_swap_pages) <= 0) goto noswap; atomic_long_dec(&nr_swap_pages); - for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) { - hp_index = atomic_xchg(&highest_priority_index, -1); - /* - * highest_priority_index records current highest priority swap - * type which just frees swap entries. If its priority is - * higher than that of swap_list.next swap type, we use it. It - * isn't protected by swap_lock, so it can be an invalid value - * if the corresponding swap type is swapoff. We double check - * the flags here. It's even possible the swap type is swapoff - * and swapon again and its priority is changed. In such rare - * case, low prority swap type might be used, but eventually - * high priority swap will be used after several rounds of - * swap. - */ - if (hp_index != -1 && hp_index != type && - swap_info[type]->prio < swap_info[hp_index]->prio && - (swap_info[hp_index]->flags & SWP_WRITEOK)) { - type = hp_index; - swap_list.next = type; - } - - si = swap_info[type]; - next = si->next; - if (next < 0 || - (!wrapped && si->prio != swap_info[next]->prio)) { - next = swap_list.head; - wrapped++; - } + spin_lock(&swap_avail_lock); +start_over: + plist_for_each_entry_safe(si, next, &swap_avail_head, avail_list) { + /* requeue si to after same-priority siblings */ + plist_requeue(&si->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); spin_lock(&si->lock); - if (!si->highest_bit) { + if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + if (plist_node_empty(&si->avail_list)) { + spin_unlock(&si->lock); + goto nextsi; + } + WARN(!si->highest_bit, + "swap_info %d in list but !highest_bit\n", + si->type); + WARN(!(si->flags & SWP_WRITEOK), + "swap_info %d in list but !SWP_WRITEOK\n", + si->type); + plist_del(&si->avail_list, &swap_avail_head); spin_unlock(&si->lock); - continue; + goto nextsi; } - if (!(si->flags & SWP_WRITEOK)) { - spin_unlock(&si->lock); - continue; - } - - swap_list.next = next; - spin_unlock(&swap_lock); /* This is called for allocating swap entry for cache */ offset = scan_swap_map(si, SWAP_HAS_CACHE); spin_unlock(&si->lock); if (offset) - return swp_entry(type, offset); - spin_lock(&swap_lock); - next = swap_list.next; + return swp_entry(si->type, offset); + pr_debug("scan_swap_map of si %d failed to find offset\n", + si->type); + spin_lock(&swap_avail_lock); +nextsi: + /* + * if we got here, it's likely that si was almost full before, + * and since scan_swap_map() can drop the si->lock, multiple + * callers probably all tried to get a page from the same si + * and it filled up before we could get one; or, the si filled + * up between us dropping swap_avail_lock and taking si->lock. + * Since we dropped the swap_avail_lock, the swap_avail_head + * list may have been modified; so if next is still in the + * swap_avail_head list then try it, otherwise start over. + */ + if (plist_node_empty(&next->avail_list)) + goto start_over; } + spin_unlock(&swap_avail_lock); + atomic_long_inc(&nr_swap_pages); noswap: - spin_unlock(&swap_lock); return (swp_entry_t) {0}; } @@ -765,27 +780,6 @@ out: return NULL; } -/* - * This swap type frees swap entry, check if it is the highest priority swap - * type which just frees swap entry. get_swap_page() uses - * highest_priority_index to search highest priority swap type. The - * swap_info_struct.lock can't protect us if there are multiple swap types - * active, so we use atomic_cmpxchg. - */ -static void set_highest_priority_index(int type) -{ - int old_hp_index, new_hp_index; - - do { - old_hp_index = atomic_read(&highest_priority_index); - if (old_hp_index != -1 && - swap_info[old_hp_index]->prio >= swap_info[type]->prio) - break; - new_hp_index = type; - } while (atomic_cmpxchg(&highest_priority_index, - old_hp_index, new_hp_index) != old_hp_index); -} - static unsigned char swap_entry_free(struct swap_info_struct *p, swp_entry_t entry, unsigned char usage) { @@ -827,9 +821,18 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, dec_cluster_info_page(p, p->cluster_info, offset); if (offset < p->lowest_bit) p->lowest_bit = offset; - if (offset > p->highest_bit) + if (offset > p->highest_bit) { + bool was_full = !p->highest_bit; p->highest_bit = offset; - set_highest_priority_index(p->type); + if (was_full && (p->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + WARN_ON(!plist_node_empty(&p->avail_list)); + if (plist_node_empty(&p->avail_list)) + plist_add(&p->avail_list, + &swap_avail_head); + spin_unlock(&swap_avail_lock); + } + } atomic_long_inc(&nr_swap_pages); p->inuse_pages--; frontswap_invalidate_page(p->type, offset); @@ -1764,30 +1767,37 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info) { - int i, prev; - if (prio >= 0) p->prio = prio; else p->prio = --least_priority; + /* + * the plist prio is negated because plist ordering is + * low-to-high, while swap ordering is high-to-low + */ + p->list.prio = -p->prio; + p->avail_list.prio = -p->prio; p->swap_map = swap_map; p->cluster_info = cluster_info; p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; - /* insert swap space into swap_list: */ - prev = -1; - for (i = swap_list.head; i >= 0; i = swap_info[i]->next) { - if (p->prio >= swap_info[i]->prio) - break; - prev = i; - } - p->next = i; - if (prev < 0) - swap_list.head = swap_list.next = p->type; - else - swap_info[prev]->next = p->type; + assert_spin_locked(&swap_lock); + /* + * both lists are plists, and thus priority ordered. + * swap_active_head needs to be priority ordered for swapoff(), + * which on removal of any swap_info_struct with an auto-assigned + * (i.e. negative) priority increments the auto-assigned priority + * of any lower-priority swap_info_structs. + * swap_avail_head needs to be priority ordered for get_swap_page(), + * which allocates swap pages from the highest available priority + * swap_info_struct. + */ + plist_add(&p->list, &swap_active_head); + spin_lock(&swap_avail_lock); + plist_add(&p->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); } static void enable_swap_info(struct swap_info_struct *p, int prio, @@ -1822,8 +1832,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) struct address_space *mapping; struct inode *inode; struct filename *pathname; - int i, type, prev; - int err; + int err, found = 0; unsigned int old_block_size; if (!capable(CAP_SYS_ADMIN)) @@ -1841,17 +1850,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) goto out; mapping = victim->f_mapping; - prev = -1; spin_lock(&swap_lock); - for (type = swap_list.head; type >= 0; type = swap_info[type]->next) { - p = swap_info[type]; + plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { - if (p->swap_file->f_mapping == mapping) + if (p->swap_file->f_mapping == mapping) { + found = 1; break; + } } - prev = type; } - if (type < 0) { + if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; @@ -1863,20 +1871,21 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); goto out_dput; } - if (prev < 0) - swap_list.head = p->next; - else - swap_info[prev]->next = p->next; - if (type == swap_list.next) { - /* just pick something that's safe... */ - swap_list.next = swap_list.head; - } + spin_lock(&swap_avail_lock); + plist_del(&p->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); spin_lock(&p->lock); if (p->prio < 0) { - for (i = p->next; i >= 0; i = swap_info[i]->next) - swap_info[i]->prio = p->prio--; + struct swap_info_struct *si = p; + + plist_for_each_entry_continue(si, &swap_active_head, list) { + si->prio++; + si->list.prio--; + si->avail_list.prio--; + } least_priority++; } + plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; @@ -1884,7 +1893,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); set_current_oom_origin(); - err = try_to_unuse(type, false, 0); /* force all pages to be unused */ + err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ clear_current_oom_origin(); if (err) { @@ -1926,7 +1935,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) frontswap_map_set(p, NULL); spin_unlock(&p->lock); spin_unlock(&swap_lock); - frontswap_invalidate_area(type); + frontswap_invalidate_area(p->type); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; @@ -1934,7 +1943,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) vfree(cluster_info); vfree(frontswap_map); /* Destroy swap account informatin */ - swap_cgroup_swapoff(type); + swap_cgroup_swapoff(p->type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { @@ -2141,8 +2150,9 @@ static struct swap_info_struct *alloc_swap_info(void) */ } INIT_LIST_HEAD(&p->first_swap_extent.list); + plist_node_init(&p->list, 0); + plist_node_init(&p->avail_list, 0); p->flags = SWP_USED; - p->next = -1; spin_unlock(&swap_lock); spin_lock_init(&p->lock); diff --git a/mm/truncate.c b/mm/truncate.c index 353b683..827ad8d 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -20,8 +20,25 @@ #include <linux/buffer_head.h> /* grr. try_to_release_page, do_invalidatepage */ #include <linux/cleancache.h> +#include <linux/rmap.h> #include "internal.h" +static void clear_exceptional_entry(struct address_space *mapping, + pgoff_t index, void *entry) +{ + /* 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. + */ + radix_tree_delete_item(&mapping->page_tree, index, entry); + spin_unlock_irq(&mapping->tree_lock); +} /** * do_invalidatepage - invalidate part or all of a page @@ -208,6 +225,7 @@ 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; @@ -238,17 +256,23 @@ 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 +283,7 @@ 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 +332,16 @@ 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 +350,22 @@ 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++; @@ -375,6 +408,7 @@ 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 +424,23 @@ 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 +454,7 @@ 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(); @@ -481,6 +522,7 @@ 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 +533,23 @@ 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 +587,7 @@ 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(); @@ -613,12 +662,67 @@ EXPORT_SYMBOL(truncate_pagecache); */ void truncate_setsize(struct inode *inode, loff_t newsize) { + loff_t oldsize = inode->i_size; + i_size_write(inode, newsize); + if (newsize > oldsize) + pagecache_isize_extended(inode, oldsize, newsize); truncate_pagecache(inode, newsize); } EXPORT_SYMBOL(truncate_setsize); /** + * pagecache_isize_extended - update pagecache after extension of i_size + * @inode: inode for which i_size was extended + * @from: original inode size + * @to: new inode size + * + * Handle extension of inode size either caused by extending truncate or by + * write starting after current i_size. We mark the page straddling current + * i_size RO so that page_mkwrite() is called on the nearest write access to + * the page. This way filesystem can be sure that page_mkwrite() is called on + * the page before user writes to the page via mmap after the i_size has been + * changed. + * + * The function must be called after i_size is updated so that page fault + * coming after we unlock the page will already see the new i_size. + * The function must be called while we still hold i_mutex - this not only + * makes sure i_size is stable but also that userspace cannot observe new + * i_size value before we are prepared to store mmap writes at new inode size. + */ +void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) +{ + int bsize = 1 << inode->i_blkbits; + loff_t rounded_from; + struct page *page; + pgoff_t index; + + WARN_ON(to > inode->i_size); + + if (from >= to || bsize == PAGE_CACHE_SIZE) + return; + /* Page straddling @from will not have any hole block created? */ + rounded_from = round_up(from, bsize); + if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1))) + return; + + index = from >> PAGE_CACHE_SHIFT; + page = find_lock_page(inode->i_mapping, index); + /* Page not cached? Nothing to do */ + if (!page) + return; + /* + * See clear_page_dirty_for_io() for details why set_page_dirty() + * is needed. + */ + if (page_mkclean(page)) + set_page_dirty(page); + unlock_page(page); + page_cache_release(page); +} +EXPORT_SYMBOL(pagecache_isize_extended); + +/** * truncate_pagecache_range - unmap and remove pagecache that is hole-punched * @inode: inode * @lstart: offset of beginning of hole @@ -272,17 +272,14 @@ pid_t vm_is_stack(struct task_struct *task, if (in_group) { struct task_struct *t; - rcu_read_lock(); - if (!pid_alive(task)) - goto done; - t = task; - do { + rcu_read_lock(); + for_each_thread(task, t) { if (vm_is_stack_for_task(t, vma)) { ret = t->pid; goto done; } - } while_each_thread(task, t); + } done: rcu_read_unlock(); } diff --git a/mm/vmacache.c b/mm/vmacache.c new file mode 100644 index 0000000..1037a3ba --- /dev/null +++ b/mm/vmacache.c @@ -0,0 +1,114 @@ +/* + * 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) + continue; + if (WARN_ON_ONCE(vma->vm_mm != mm)) + break; + if (vma->vm_start <= addr && vma->vm_end > addr) + 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 d64289d..060dc36 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -359,6 +359,12 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, if (unlikely(!va)) return ERR_PTR(-ENOMEM); + /* + * Only scan the relevant parts containing pointers to other objects + * to avoid false negatives. + */ + kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask & GFP_RECLAIM_MASK); + retry: spin_lock(&vmap_area_lock); /* @@ -790,7 +796,7 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) struct vmap_block *vb; struct vmap_area *va; unsigned long vb_idx; - int node, err, cpu; + int node, err; node = numa_node_id(); @@ -828,12 +834,11 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) BUG_ON(err); radix_tree_preload_end(); - cpu = get_cpu_light(); - vbq = &__get_cpu_var(vmap_block_queue); + vbq = &get_cpu_var(vmap_block_queue); spin_lock(&vbq->lock); list_add_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); - put_cpu_light(); + put_cpu_var(vmap_block_queue); return vb; } @@ -901,7 +906,6 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) struct vmap_block *vb; unsigned long addr = 0; unsigned int order; - int cpu = 0; BUG_ON(size & ~PAGE_MASK); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); @@ -917,8 +921,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) again: rcu_read_lock(); - cpu = get_cpu_light(); - vbq = &__get_cpu_var(vmap_block_queue); + vbq = &get_cpu_var(vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { int i; @@ -942,7 +945,7 @@ next: spin_unlock(&vb->lock); } - put_cpu_light(); + put_cpu_var(vmap_block_queue); rcu_read_unlock(); if (!addr) { @@ -1649,11 +1652,11 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, clear_vm_uninitialized_flag(area); /* - * A ref_count = 3 is needed because the vm_struct and vmap_area - * structures allocated in the __get_vm_area_node() function contain - * references to the virtual address of the vmalloc'ed block. + * A ref_count = 2 is needed because vm_struct allocated in + * __get_vm_area_node() contains a reference to the virtual address of + * the vmalloc'ed block. */ - kmemleak_alloc(addr, real_size, 3, gfp_mask); + kmemleak_alloc(addr, real_size, 2, gfp_mask); return addr; @@ -2682,14 +2685,14 @@ void get_vmalloc_info(struct vmalloc_info *vmi) prev_end = VMALLOC_START; - spin_lock(&vmap_area_lock); + rcu_read_lock(); if (list_empty(&vmap_area_list)) { vmi->largest_chunk = VMALLOC_TOTAL; goto out; } - list_for_each_entry(va, &vmap_area_list, list) { + list_for_each_entry_rcu(va, &vmap_area_list, list) { unsigned long addr = va->va_start; /* @@ -2716,7 +2719,7 @@ void get_vmalloc_info(struct vmalloc_info *vmi) vmi->largest_chunk = VMALLOC_END - prev_end; out: - spin_unlock(&vmap_area_lock); + rcu_read_unlock(); } #endif diff --git a/mm/vmpressure.c b/mm/vmpressure.c index e0f6283..c98b14e 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -164,6 +164,7 @@ static void vmpressure_work_fn(struct work_struct *work) unsigned long scanned; unsigned long reclaimed; + spin_lock(&vmpr->sr_lock); /* * Several contexts might be calling vmpressure(), so it is * possible that the work was rescheduled again before the old @@ -172,11 +173,12 @@ static void vmpressure_work_fn(struct work_struct *work) * here. No need for any locks here since we don't care if * vmpr->reclaimed is in sync. */ - if (!vmpr->scanned) + scanned = vmpr->scanned; + if (!scanned) { + spin_unlock(&vmpr->sr_lock); return; + } - spin_lock(&vmpr->sr_lock); - scanned = vmpr->scanned; reclaimed = vmpr->reclaimed; vmpr->scanned = 0; vmpr->reclaimed = 0; diff --git a/mm/vmscan.c b/mm/vmscan.c index 05e6095..ee8363f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -163,7 +163,8 @@ static unsigned long zone_reclaimable_pages(struct zone *zone) bool zone_reclaimable(struct zone *zone) { - return zone->pages_scanned < zone_reclaimable_pages(zone) * 6; + return zone_page_state(zone, NR_PAGES_SCANNED) < + zone_reclaimable_pages(zone) * 6; } static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru) @@ -224,15 +225,15 @@ 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 +245,14 @@ 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 +261,55 @@ 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 +370,17 @@ 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); } } @@ -1089,7 +1108,7 @@ keep: VM_BUG_ON(PageLRU(page) || PageUnevictable(page)); } - free_hot_cold_page_list(&free_pages, 1); + free_hot_cold_page_list(&free_pages, true); list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); @@ -1126,7 +1145,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, TTU_UNMAP|TTU_IGNORE_ACCESS, &dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true); list_splice(&clean_pages, page_list); - __mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret); + mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret); return ret; } @@ -1452,7 +1471,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken); if (global_reclaim(sc)) { - zone->pages_scanned += nr_scanned; + __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned); if (current_is_kswapd()) __count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scanned); else @@ -1487,7 +1506,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, spin_unlock_irq(&zone->lru_lock); - free_hot_cold_page_list(&page_list, 1); + free_hot_cold_page_list(&page_list, true); /* * If reclaim is isolating dirty pages under writeback, it implies @@ -1522,19 +1541,18 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * If dirty pages are scanned that are not queued for IO, it * implies that flushers are not keeping up. In this case, flag * the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing - * pages from reclaim context. It will forcibly stall in the - * next check. + * pages from reclaim context. */ if (nr_unqueued_dirty == nr_taken) zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY); /* - * In addition, if kswapd scans pages marked marked for - * immediate reclaim and under writeback (nr_immediate), it - * implies that pages are cycling through the LRU faster than + * If kswapd scans pages marked marked for immediate + * reclaim and under writeback (nr_immediate), it implies + * that pages are cycling through the LRU faster than * they are written so also forcibly stall. */ - if (nr_unqueued_dirty == nr_taken || nr_immediate) + if (nr_immediate) congestion_wait(BLK_RW_ASYNC, HZ/10); } @@ -1642,7 +1660,7 @@ static void shrink_active_list(unsigned long nr_to_scan, nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, isolate_mode, lru); if (global_reclaim(sc)) - zone->pages_scanned += nr_scanned; + __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned); reclaim_stat->recent_scanned[file] += nr_taken; @@ -1708,7 +1726,7 @@ static void shrink_active_list(unsigned long nr_to_scan, __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&zone->lru_lock); - free_hot_cold_page_list(&l_hold, 1); + free_hot_cold_page_list(&l_hold, true); } #ifdef CONFIG_SWAP @@ -1830,7 +1848,7 @@ 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; @@ -1878,11 +1896,6 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, goto out; } - anon = get_lru_size(lruvec, LRU_ACTIVE_ANON) + - get_lru_size(lruvec, LRU_INACTIVE_ANON); - file = get_lru_size(lruvec, LRU_ACTIVE_FILE) + - 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 @@ -1890,8 +1903,14 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * 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))) { + unsigned long zonefile; + unsigned long zonefree; + + zonefree = zone_page_state(zone, NR_FREE_PAGES); + zonefile = zone_page_state(zone, NR_ACTIVE_FILE) + + zone_page_state(zone, NR_INACTIVE_FILE); + + if (unlikely(zonefile + zonefree <= high_wmark_pages(zone))) { scan_balance = SCAN_ANON; goto out; } @@ -1926,6 +1945,12 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * * anon in [0], file in [1] */ + + anon = get_lru_size(lruvec, LRU_ACTIVE_ANON) + + get_lru_size(lruvec, LRU_INACTIVE_ANON); + file = get_lru_size(lruvec, LRU_ACTIVE_FILE) + + get_lru_size(lruvec, LRU_INACTIVE_FILE); + spin_lock_irq(&zone->lru_lock); if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) { reclaim_stat->recent_scanned[0] /= 2; @@ -2001,13 +2026,27 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; struct blk_plug plug; - bool scan_adjusted = false; + bool scan_adjusted; get_scan_count(lruvec, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); + /* + * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal + * event that can occur when there is little memory pressure e.g. + * multiple streaming readers/writers. Hence, we do not abort scanning + * when the requested number of pages are reclaimed when scanning at + * DEF_PRIORITY on the assumption that the fact we are direct + * reclaiming implies that kswapd is not keeping up and it is best to + * do a batch of work at once. For memcg reclaim one check is made to + * abort proportional reclaim if either the file or anon lru has already + * dropped to zero at the first pass. + */ + scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() && + sc->priority == DEF_PRIORITY); + blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { @@ -2028,17 +2067,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) continue; /* - * For global direct reclaim, reclaim only the number of pages - * requested. Less care is taken to scan proportionally as it - * is more important to minimise direct reclaim stall latency - * than it is to properly age the LRU lists. - */ - if (global_reclaim(sc) && !current_is_kswapd()) - break; - - /* * For kswapd and memcg, reclaim at least the number of pages - * requested. Ensure that the anon and file LRUs shrink + * requested. Ensure that the anon and file LRUs are scanned * proportionally what was requested by get_scan_count(). We * stop reclaiming one LRU and reduce the amount scanning * proportional to the original scan target. @@ -2046,6 +2076,15 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; + /* + * It's just vindictive to attack the larger once the smaller + * has gone to zero. And given the way we stop scanning the + * smaller below, this makes sure that we only make one nudge + * towards proportionality once we've got nr_to_reclaim. + */ + if (!nr_file || !nr_anon) + break; + if (nr_file > nr_anon) { unsigned long scan_target = targets[LRU_INACTIVE_ANON] + targets[LRU_ACTIVE_ANON] + 1; @@ -2407,8 +2446,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, unsigned long lru_pages = 0; nodes_clear(shrink->nodes_to_scan); - for_each_zone_zonelist(zone, z, zonelist, - gfp_zone(sc->gfp_mask)) { + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_zone(sc->gfp_mask), sc->nodemask) { if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; @@ -2484,10 +2523,17 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; + if (!populated_zone(zone)) + continue; + pfmemalloc_reserve += min_wmark_pages(zone); free_pages += zone_page_state(zone, NR_FREE_PAGES); } + /* If there are no reserves (unexpected config) then do not throttle */ + if (!pfmemalloc_reserve) + return true; + wmark_ok = free_pages > pfmemalloc_reserve / 2; /* kswapd must be awake if processes are being throttled */ @@ -2512,9 +2558,9 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, nodemask_t *nodemask) { + struct zoneref *z; struct zone *zone; - int high_zoneidx = gfp_zone(gfp_mask); - pg_data_t *pgdat; + pg_data_t *pgdat = NULL; /* * Kernel threads should not be throttled as they may be indirectly @@ -2533,10 +2579,34 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, if (fatal_signal_pending(current)) goto out; - /* Check if the pfmemalloc reserves are ok */ - first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone); - pgdat = zone->zone_pgdat; - if (pfmemalloc_watermark_ok(pgdat)) + /* + * Check if the pfmemalloc reserves are ok by finding the first node + * with a usable ZONE_NORMAL or lower zone. The expectation is that + * GFP_KERNEL will be required for allocating network buffers when + * swapping over the network so ZONE_HIGHMEM is unusable. + * + * Throttling is based on the first usable node and throttled processes + * wait on a queue until kswapd makes progress and wakes them. There + * is an affinity then between processes waking up and where reclaim + * progress has been made assuming the process wakes on the same node. + * More importantly, processes running on remote nodes will not compete + * for remote pfmemalloc reserves and processes on different nodes + * should make reasonable progress. + */ + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_mask, nodemask) { + if (zone_idx(zone) > ZONE_NORMAL) + continue; + + /* Throttle based on the first usable node */ + pgdat = zone->zone_pgdat; + if (pfmemalloc_watermark_ok(pgdat)) + goto out; + break; + } + + /* If no zone was usable by the allocation flags then do not throttle */ + if (!pgdat) goto out; /* Account for the throttling */ @@ -2798,18 +2868,20 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, return false; /* - * There is a potential race between when kswapd checks its watermarks - * and a process gets throttled. There is also a potential race if - * processes get throttled, kswapd wakes, a large process exits therby - * balancing the zones that causes kswapd to miss a wakeup. If kswapd - * is going to sleep, no process should be sleeping on pfmemalloc_wait - * so wake them now if necessary. If necessary, processes will wake - * kswapd and get throttled again + * The throttled processes are normally woken up in balance_pgdat() as + * soon as pfmemalloc_watermark_ok() is true. But there is a potential + * race between when kswapd checks the watermarks and a process gets + * throttled. There is also a potential race if processes get + * throttled, kswapd wakes, a large process exits thereby balancing the + * zones, which causes kswapd to exit balance_pgdat() before reaching + * the wake up checks. If kswapd is going to sleep, no process should + * be sleeping on pfmemalloc_wait, so wake them now if necessary. If + * the wake up is premature, processes will wake kswapd and get + * throttled again. The difference from wake ups in balance_pgdat() is + * that here we are under prepare_to_wait(). */ - if (waitqueue_active(&pgdat->pfmemalloc_wait)) { - wake_up(&pgdat->pfmemalloc_wait); - return false; - } + if (waitqueue_active(&pgdat->pfmemalloc_wait)) + wake_up_all(&pgdat->pfmemalloc_wait); return pgdat_balanced(pgdat, order, classzone_idx); } @@ -3267,7 +3339,10 @@ static int kswapd(void *p) } } + tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD); current->reclaim_state = NULL; + lockdep_clear_current_reclaim_state(); + return 0; } diff --git a/mm/vmstat.c b/mm/vmstat.c index efea337..f7ca044 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -200,7 +200,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, continue; threshold = (*calculate_pressure)(zone); - for_each_possible_cpu(cpu) + for_each_online_cpu(cpu) per_cpu_ptr(zone->pageset, cpu)->stat_threshold = threshold; } @@ -217,7 +217,6 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long x; long t; - preempt_disable_rt(); x = delta + __this_cpu_read(*p); t = __this_cpu_read(pcp->stat_threshold); @@ -227,7 +226,6 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, x = 0; } __this_cpu_write(*p, x); - preempt_enable_rt(); } EXPORT_SYMBOL(__mod_zone_page_state); @@ -260,7 +258,6 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) s8 __percpu *p = pcp->vm_stat_diff + item; s8 v, t; - preempt_disable_rt(); v = __this_cpu_inc_return(*p); t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v > t)) { @@ -269,7 +266,6 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) zone_page_state_add(v + overstep, zone, item); __this_cpu_write(*p, -overstep); } - preempt_enable_rt(); } void __inc_zone_page_state(struct page *page, enum zone_stat_item item) @@ -284,7 +280,6 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item) s8 __percpu *p = pcp->vm_stat_diff + item; s8 v, t; - preempt_disable_rt(); v = __this_cpu_dec_return(*p); t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v < - t)) { @@ -293,7 +288,6 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item) zone_page_state_add(v - overstep, zone, item); __this_cpu_write(*p, overstep); } - preempt_enable_rt(); } void __dec_zone_page_state(struct page *page, enum zone_stat_item item) @@ -767,6 +761,7 @@ const char * const vmstat_text[] = { "nr_shmem", "nr_dirtied", "nr_written", + "nr_pages_scanned", #ifdef CONFIG_NUMA "numa_hit", @@ -857,12 +852,14 @@ 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 */ }; @@ -1059,7 +1056,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), - zone->pages_scanned, + zone_page_state(zone, NR_PAGES_SCANNED), zone->spanned_pages, zone->present_pages, zone->managed_pages); @@ -1069,10 +1066,10 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, zone_page_state(zone, i)); seq_printf(m, - "\n protection: (%lu", + "\n protection: (%ld", zone->lowmem_reserve[0]); for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++) - seq_printf(m, ", %lu", zone->lowmem_reserve[i]); + seq_printf(m, ", %ld", zone->lowmem_reserve[i]); seq_printf(m, ")" "\n pagesets"); |