diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 33 | ||||
| -rw-r--r-- | mm/Makefile | 3 | ||||
| -rw-r--r-- | mm/backing-dev.c | 2 | ||||
| -rw-r--r-- | mm/bounce.c | 287 | ||||
| -rw-r--r-- | mm/compaction.c | 255 | ||||
| -rw-r--r-- | mm/dmapool.c | 31 | ||||
| -rw-r--r-- | mm/filemap.c | 297 | ||||
| -rw-r--r-- | mm/fremap.c | 11 | ||||
| -rw-r--r-- | mm/frontswap.c | 13 | ||||
| -rw-r--r-- | mm/gup.c | 662 | ||||
| -rw-r--r-- | mm/huge_memory.c | 34 | ||||
| -rw-r--r-- | mm/hugetlb.c | 382 | ||||
| -rw-r--r-- | mm/hugetlb_cgroup.c | 37 | ||||
| -rw-r--r-- | mm/internal.h | 36 | ||||
| -rw-r--r-- | mm/kmemleak-test.c | 36 | ||||
| -rw-r--r-- | mm/kmemleak.c | 44 | ||||
| -rw-r--r-- | mm/madvise.c | 2 | ||||
| -rw-r--r-- | mm/memblock.c | 241 | ||||
| -rw-r--r-- | mm/memcontrol.c | 737 | ||||
| -rw-r--r-- | mm/memory-failure.c | 113 | ||||
| -rw-r--r-- | mm/memory.c | 746 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 148 | ||||
| -rw-r--r-- | mm/mempolicy.c | 41 | ||||
| -rw-r--r-- | mm/mempool.c | 8 | ||||
| -rw-r--r-- | mm/migrate.c | 63 | ||||
| -rw-r--r-- | mm/mmap.c | 119 | ||||
| -rw-r--r-- | mm/mremap.c | 9 | ||||
| -rw-r--r-- | mm/msync.c | 8 | ||||
| -rw-r--r-- | mm/nobootmem.c | 2 | ||||
| -rw-r--r-- | mm/nommu.c | 5 | ||||
| -rw-r--r-- | mm/page-writeback.c | 41 | ||||
| -rw-r--r-- | mm/page_alloc.c | 406 | ||||
| -rw-r--r-- | mm/page_io.c | 21 | ||||
| -rw-r--r-- | mm/percpu.c | 2 | ||||
| -rw-r--r-- | mm/rmap.c | 58 | ||||
| -rw-r--r-- | mm/shmem.c | 8 | ||||
| -rw-r--r-- | mm/slab.c | 51 | ||||
| -rw-r--r-- | mm/slab.h | 49 | ||||
| -rw-r--r-- | mm/slab_common.c | 108 | ||||
| -rw-r--r-- | mm/slob.c | 3 | ||||
| -rw-r--r-- | mm/slub.c | 268 | ||||
| -rw-r--r-- | mm/swap.c | 238 | ||||
| -rw-r--r-- | mm/swap_state.c | 2 | ||||
| -rw-r--r-- | mm/swapfile.c | 253 | ||||
| -rw-r--r-- | mm/truncate.c | 8 | ||||
| -rw-r--r-- | mm/util.c | 10 | ||||
| -rw-r--r-- | mm/vmacache.c | 26 | ||||
| -rw-r--r-- | mm/vmalloc.c | 13 | ||||
| -rw-r--r-- | mm/vmscan.c | 236 | ||||
| -rw-r--r-- | mm/vmstat.c | 12 | ||||
| -rw-r--r-- | mm/zbud.c | 4 | ||||
| -rw-r--r-- | mm/zsmalloc.c | 4 | ||||
| -rw-r--r-- | mm/zswap.c | 2 |
53 files changed, 3280 insertions, 2948 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index ebe5880c29d6..3e9977a9d657 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -134,6 +134,9 @@ config HAVE_MEMBLOCK config HAVE_MEMBLOCK_NODE_MAP boolean +config HAVE_MEMBLOCK_PHYS_MAP + boolean + config ARCH_DISCARD_MEMBLOCK boolean @@ -264,6 +267,9 @@ 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 @@ -430,16 +436,6 @@ choice benefit. endchoice -config CROSS_MEMORY_ATTACH - bool "Cross Memory Support" - depends on MMU - default y - help - Enabling this option adds the system calls process_vm_readv and - process_vm_writev which allow a process with the correct privileges - to directly read from or write to to another process's address space. - See the man page for more details. - # # UP and nommu archs use km based percpu allocator # @@ -555,7 +551,7 @@ config MEM_SOFT_DIRTY See Documentation/vm/soft-dirty.txt for more details. config ZSMALLOC - bool "Memory allocator for compressed pages" + tristate "Memory allocator for compressed pages" depends on MMU default n help @@ -581,3 +577,18 @@ config PGTABLE_MAPPING config GENERIC_EARLY_IOREMAP bool + +config MAX_STACK_SIZE_MB + int "Maximum user stack size for 32-bit processes (MB)" + default 80 + range 8 256 if METAG + range 8 2048 + depends on STACK_GROWSUP && (!64BIT || COMPAT) + help + This is the maximum stack size in Megabytes in the VM layout of 32-bit + user processes when the stack grows upwards (currently only on parisc + and metag arch). The stack will be located at the highest memory + address minus the given value, unless the RLIMIT_STACK hard limit is + changed to a smaller value in which case that is used. + + A sane initial value is 80 MB. diff --git a/mm/Makefile b/mm/Makefile index b484452dac57..4064f3ec145e 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -3,7 +3,7 @@ # mmu-y := nommu.o -mmu-$(CONFIG_MMU) := fremap.o highmem.o madvise.o memory.o mincore.o \ +mmu-$(CONFIG_MMU) := fremap.o gup.o highmem.o madvise.o memory.o mincore.o \ mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \ vmalloc.o pagewalk.o pgtable-generic.o @@ -30,7 +30,6 @@ endif obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o -obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o obj-$(CONFIG_FRONTSWAP) += frontswap.o obj-$(CONFIG_ZSWAP) += zswap.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 09d9591b7708..1706cbbdf5f0 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -557,7 +557,7 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int sync) bit = sync ? BDI_sync_congested : BDI_async_congested; if (test_and_clear_bit(bit, &bdi->state)) atomic_dec(&nr_bdi_congested[sync]); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); if (waitqueue_active(wqh)) wake_up(wqh); } diff --git a/mm/bounce.c b/mm/bounce.c deleted file mode 100644 index 523918b8c6dc..000000000000 --- a/mm/bounce.c +++ /dev/null @@ -1,287 +0,0 @@ -/* bounce buffer handling for block devices - * - * - Split from highmem.c - */ - -#include <linux/mm.h> -#include <linux/export.h> -#include <linux/swap.h> -#include <linux/gfp.h> -#include <linux/bio.h> -#include <linux/pagemap.h> -#include <linux/mempool.h> -#include <linux/blkdev.h> -#include <linux/init.h> -#include <linux/hash.h> -#include <linux/highmem.h> -#include <linux/bootmem.h> -#include <asm/tlbflush.h> - -#include <trace/events/block.h> - -#define POOL_SIZE 64 -#define ISA_POOL_SIZE 16 - -static mempool_t *page_pool, *isa_page_pool; - -#if defined(CONFIG_HIGHMEM) || defined(CONFIG_NEED_BOUNCE_POOL) -static __init int init_emergency_pool(void) -{ -#if defined(CONFIG_HIGHMEM) && !defined(CONFIG_MEMORY_HOTPLUG) - if (max_pfn <= max_low_pfn) - return 0; -#endif - - page_pool = mempool_create_page_pool(POOL_SIZE, 0); - BUG_ON(!page_pool); - printk("bounce pool size: %d pages\n", POOL_SIZE); - - return 0; -} - -__initcall(init_emergency_pool); -#endif - -#ifdef CONFIG_HIGHMEM -/* - * highmem version, map in to vec - */ -static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom) -{ - unsigned long flags; - unsigned char *vto; - - 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(flags); -} - -#else /* CONFIG_HIGHMEM */ - -#define bounce_copy_vec(to, vfrom) \ - memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len) - -#endif /* CONFIG_HIGHMEM */ - -/* - * allocate pages in the DMA region for the ISA pool - */ -static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data) -{ - return mempool_alloc_pages(gfp_mask | GFP_DMA, data); -} - -/* - * gets called "every" time someone init's a queue with BLK_BOUNCE_ISA - * as the max address, so check if the pool has already been created. - */ -int init_emergency_isa_pool(void) -{ - if (isa_page_pool) - return 0; - - isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa, - mempool_free_pages, (void *) 0); - BUG_ON(!isa_page_pool); - - printk("isa bounce pool size: %d pages\n", ISA_POOL_SIZE); - return 0; -} - -/* - * Simple bounce buffer support for highmem pages. Depending on the - * queue gfp mask set, *to may or may not be a highmem page. kmap it - * always, it will do the Right Thing - */ -static void copy_to_high_bio_irq(struct bio *to, struct bio *from) -{ - unsigned char *vfrom; - struct bio_vec tovec, *fromvec = from->bi_io_vec; - struct bvec_iter iter; - - bio_for_each_segment(tovec, to, iter) { - if (tovec.bv_page != fromvec->bv_page) { - /* - * fromvec->bv_offset and fromvec->bv_len might have - * been modified by the block layer, so use the original - * copy, bounce_copy_vec already uses tovec->bv_len - */ - vfrom = page_address(fromvec->bv_page) + - tovec.bv_offset; - - bounce_copy_vec(&tovec, vfrom); - flush_dcache_page(tovec.bv_page); - } - - fromvec++; - } -} - -static void bounce_end_io(struct bio *bio, mempool_t *pool, int err) -{ - struct bio *bio_orig = bio->bi_private; - struct bio_vec *bvec, *org_vec; - int i; - - if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags)) - set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags); - - /* - * free up bounce indirect pages used - */ - bio_for_each_segment_all(bvec, bio, i) { - org_vec = bio_orig->bi_io_vec + i; - if (bvec->bv_page == org_vec->bv_page) - continue; - - dec_zone_page_state(bvec->bv_page, NR_BOUNCE); - mempool_free(bvec->bv_page, pool); - } - - bio_endio(bio_orig, err); - bio_put(bio); -} - -static void bounce_end_io_write(struct bio *bio, int err) -{ - bounce_end_io(bio, page_pool, err); -} - -static void bounce_end_io_write_isa(struct bio *bio, int err) -{ - - bounce_end_io(bio, isa_page_pool, err); -} - -static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err) -{ - struct bio *bio_orig = bio->bi_private; - - if (test_bit(BIO_UPTODATE, &bio->bi_flags)) - copy_to_high_bio_irq(bio_orig, bio); - - bounce_end_io(bio, pool, err); -} - -static void bounce_end_io_read(struct bio *bio, int err) -{ - __bounce_end_io_read(bio, page_pool, err); -} - -static void bounce_end_io_read_isa(struct bio *bio, int err) -{ - __bounce_end_io_read(bio, isa_page_pool, err); -} - -#ifdef CONFIG_NEED_BOUNCE_POOL -static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio) -{ - if (bio_data_dir(bio) != WRITE) - return 0; - - if (!bdi_cap_stable_pages_required(&q->backing_dev_info)) - return 0; - - return test_bit(BIO_SNAP_STABLE, &bio->bi_flags); -} -#else -static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio) -{ - return 0; -} -#endif /* CONFIG_NEED_BOUNCE_POOL */ - -static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, - mempool_t *pool, int force) -{ - struct bio *bio; - int rw = bio_data_dir(*bio_orig); - struct bio_vec *to, from; - struct bvec_iter iter; - unsigned i; - - if (force) - goto bounce; - bio_for_each_segment(from, *bio_orig, iter) - if (page_to_pfn(from.bv_page) > queue_bounce_pfn(q)) - goto bounce; - - return; -bounce: - bio = bio_clone_bioset(*bio_orig, GFP_NOIO, fs_bio_set); - - bio_for_each_segment_all(to, bio, i) { - struct page *page = to->bv_page; - - if (page_to_pfn(page) <= queue_bounce_pfn(q) && !force) - continue; - - inc_zone_page_state(to->bv_page, NR_BOUNCE); - to->bv_page = mempool_alloc(pool, q->bounce_gfp); - - if (rw == WRITE) { - char *vto, *vfrom; - - flush_dcache_page(page); - - vto = page_address(to->bv_page) + to->bv_offset; - vfrom = kmap_atomic(page) + to->bv_offset; - memcpy(vto, vfrom, to->bv_len); - kunmap_atomic(vfrom); - } - } - - trace_block_bio_bounce(q, *bio_orig); - - bio->bi_flags |= (1 << BIO_BOUNCED); - - if (pool == page_pool) { - bio->bi_end_io = bounce_end_io_write; - if (rw == READ) - bio->bi_end_io = bounce_end_io_read; - } else { - bio->bi_end_io = bounce_end_io_write_isa; - if (rw == READ) - bio->bi_end_io = bounce_end_io_read_isa; - } - - bio->bi_private = *bio_orig; - *bio_orig = bio; -} - -void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) -{ - int must_bounce; - mempool_t *pool; - - /* - * Data-less bio, nothing to bounce - */ - if (!bio_has_data(*bio_orig)) - return; - - must_bounce = must_snapshot_stable_pages(q, *bio_orig); - - /* - * for non-isa bounce case, just check if the bounce pfn is equal - * to or bigger than the highest pfn in the system -- in that case, - * don't waste time iterating over bio segments - */ - if (!(q->bounce_gfp & GFP_DMA)) { - if (queue_bounce_pfn(q) >= blk_max_pfn && !must_bounce) - return; - pool = page_pool; - } else { - BUG_ON(!isa_page_pool); - pool = isa_page_pool; - } - - /* - * slow path - */ - __blk_queue_bounce(q, bio_orig, pool, must_bounce); -} - -EXPORT_SYMBOL(blk_queue_bounce); diff --git a/mm/compaction.c b/mm/compaction.c index 37f976287068..21bf292b642a 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; } @@ -208,10 +222,28 @@ 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 */ @@ -329,7 +361,8 @@ 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) @@ -464,8 +497,9 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, unsigned long flags; bool locked = false; struct page *page = NULL, *valid_page = NULL; - bool skipped_async_unsuitable = false; - const isolate_mode_t mode = (!cc->sync ? ISOLATE_ASYNC_MIGRATE : 0) | + bool set_unsuitable = true; + const isolate_mode_t mode = (cc->mode == MIGRATE_ASYNC ? + ISOLATE_ASYNC_MIGRATE : 0) | (unevictable ? ISOLATE_UNEVICTABLE : 0); /* @@ -475,7 +509,7 @@ 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); @@ -484,8 +518,10 @@ 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 % SWAP_CLUSTER_MAX)) { @@ -540,9 +576,9 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, * the minimum amount of work satisfies the allocation */ mt = get_pageblock_migratetype(page); - if (!cc->sync && !migrate_async_suitable(mt)) { - cc->finished_update_migrate = true; - skipped_async_unsuitable = true; + if (cc->mode == MIGRATE_ASYNC && + !migrate_async_suitable(mt)) { + set_unsuitable = false; goto next_pageblock; } } @@ -646,11 +682,10 @@ next_pageblock: /* * Update the pageblock-skip information and cached scanner pfn, * if the whole pageblock was scanned without isolating any page. - * This is not done when pageblock was skipped due to being unsuitable - * for async compaction, so that eventual sync compaction can try. */ - if (low_pfn == end_pfn && !skipped_async_unsuitable) - update_pageblock_skip(cc, valid_page, nr_isolated, true); + if (low_pfn == end_pfn) + update_pageblock_skip(cc, valid_page, nr_isolated, + set_unsuitable, true); trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); @@ -671,44 +706,48 @@ 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; + 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); /* - * 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); - - /* * 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; /* @@ -718,7 +757,7 @@ 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; @@ -731,29 +770,26 @@ 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 */ @@ -763,10 +799,9 @@ static void isolate_freepages(struct zone *zone, * If we crossed the migrate scanner, we want to keep it that way * so that compact_finished() may detect this */ - if (pfn < low_pfn) - cc->free_pfn = max(pfn, zone->zone_start_pfn); - else - cc->free_pfn = high_pfn; + if (block_start_pfn < low_pfn) + cc->free_pfn = cc->migrate_pfn; + cc->nr_freepages = nr_freepages; } @@ -781,9 +816,13 @@ 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; @@ -797,23 +836,16 @@ 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 */ @@ -860,13 +892,14 @@ 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 = zone->zone_start_pfn; + 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); /* @@ -966,6 +999,7 @@ 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) { @@ -991,7 +1025,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) * 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); @@ -999,7 +1033,8 @@ 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; } trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn); @@ -1007,7 +1042,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) migrate_prep_local(); while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) { - unsigned long nr_migrate, nr_remaining; int err; switch (isolate_migratepages(zone, cc)) { @@ -1022,21 +1056,20 @@ 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; /* * migrate_pages() may return -ENOMEM when scanners meet * and we want compact_finished() to detect it @@ -1058,9 +1091,8 @@ out: 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 = { @@ -1069,7 +1101,7 @@ 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); @@ -1091,7 +1123,7 @@ 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 * @@ -1099,7 +1131,7 @@ 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; @@ -1124,7 +1156,7 @@ 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); @@ -1163,9 +1195,6 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) if (zone_watermark_ok(zone, cc->order, low_wmark_pages(zone), 0, 0)) compaction_defer_reset(zone, cc->order, false); - /* Currently async compaction is never deferred. */ - else if (cc->sync) - defer_compaction(zone, cc->order); } VM_BUG_ON(!list_empty(&cc->freepages)); @@ -1177,7 +1206,7 @@ void compact_pgdat(pg_data_t *pgdat, int order) { struct compact_control cc = { .order = order, - .sync = false, + .mode = MIGRATE_ASYNC, }; if (!order) @@ -1190,7 +1219,7 @@ static void compact_node(int nid) { struct compact_control cc = { .order = -1, - .sync = true, + .mode = MIGRATE_SYNC, .ignore_skip_hint = true, }; diff --git a/mm/dmapool.c b/mm/dmapool.c index c69781e97cf9..306baa594f95 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -170,24 +170,16 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, retval->boundary = boundary; retval->allocation = allocation; - if (dev) { - int ret; + INIT_LIST_HEAD(&retval->pools); - mutex_lock(&pools_lock); - if (list_empty(&dev->dma_pools)) - ret = device_create_file(dev, &dev_attr_pools); - else - ret = 0; - /* note: not currently insisting "name" be unique */ - if (!ret) - list_add(&retval->pools, &dev->dma_pools); - else { - kfree(retval); - retval = NULL; - } - mutex_unlock(&pools_lock); + mutex_lock(&pools_lock); + if (list_empty(&dev->dma_pools) && + device_create_file(dev, &dev_attr_pools)) { + kfree(retval); + return NULL; } else - INIT_LIST_HEAD(&retval->pools); + list_add(&retval->pools, &dev->dma_pools); + mutex_unlock(&pools_lock); return retval; } @@ -341,10 +333,10 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, continue; if (pool->dev) dev_err(pool->dev, - "dma_pool_alloc %s, %p (corruped)\n", + "dma_pool_alloc %s, %p (corrupted)\n", pool->name, retval); else - pr_err("dma_pool_alloc %s, %p (corruped)\n", + pr_err("dma_pool_alloc %s, %p (corrupted)\n", pool->name, retval); /* @@ -508,7 +500,6 @@ void dmam_pool_destroy(struct dma_pool *pool) { struct device *dev = pool->dev; - WARN_ON(devres_destroy(dev, dmam_pool_release, dmam_pool_match, pool)); - dma_pool_destroy(pool); + WARN_ON(devres_release(dev, dmam_pool_release, dmam_pool_match, pool)); } EXPORT_SYMBOL(dmam_pool_destroy); diff --git a/mm/filemap.c b/mm/filemap.c index 5020b280a771..7fadf1c62838 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -257,9 +257,11 @@ 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; } @@ -740,7 +742,7 @@ void unlock_page(struct page *page) { VM_BUG_ON_PAGE(!PageLocked(page), page); clear_bit_unlock(PG_locked, &page->flags); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); wake_up_page(page, PG_locked); } EXPORT_SYMBOL(unlock_page); @@ -751,17 +753,51 @@ 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(); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); wake_up_page(page, PG_writeback); } EXPORT_SYMBOL(end_page_writeback); +/* + * After completing I/O on a page, call this routine to update the page + * flags appropriately + */ +void page_endio(struct page *page, int rw, int err) +{ + if (rw == READ) { + if (!err) { + SetPageUptodate(page); + } else { + ClearPageUptodate(page); + SetPageError(page); + } + unlock_page(page); + } else { /* rw == WRITE */ + if (err) { + SetPageError(page); + if (page->mapping) + mapping_set_error(page->mapping, err); + } + end_page_writeback(page); + } +} +EXPORT_SYMBOL_GPL(page_endio); + /** * __lock_page - get a lock on the page, assuming we need to sleep to get it * @page: the page to lock @@ -906,8 +942,8 @@ EXPORT_SYMBOL(page_cache_prev_hole); * 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. + * If the slot holds a shadow entry of a previously evicted page, or a + * swap entry from shmem/tmpfs, it is returned. * * Otherwise, %NULL is returned. */ @@ -928,9 +964,9 @@ repeat: if (radix_tree_deref_retry(page)) goto repeat; /* - * Otherwise, shmem/tmpfs must be storing a swap entry - * here as an exceptional entry: so return it without - * attempting to raise page count. + * A shadow entry of a recently evicted page, + * or a swap entry from shmem/tmpfs. Return + * it without attempting to raise page count. */ goto out; } @@ -955,26 +991,6 @@ out: EXPORT_SYMBOL(find_get_entry); /** - * find_get_page - find and get a page reference - * @mapping: the address_space to search - * @offset: the page index - * - * Looks up the page cache slot at @mapping & @offset. If there is a - * page cache page, it is returned with an increased refcount. - * - * Otherwise, %NULL is returned. - */ -struct page *find_get_page(struct address_space *mapping, pgoff_t offset) -{ - struct page *page = find_get_entry(mapping, offset); - - if (radix_tree_exceptional_entry(page)) - page = NULL; - return page; -} -EXPORT_SYMBOL(find_get_page); - -/** * find_lock_entry - locate, pin and lock a page cache entry * @mapping: the address_space to search * @offset: the page cache index @@ -983,8 +999,8 @@ EXPORT_SYMBOL(find_get_page); * page cache page, it is returned locked and with an increased * refcount. * - * If the slot holds a shadow entry of a previously evicted page, it - * is returned. + * If the slot holds a shadow entry of a previously evicted page, or a + * swap entry from shmem/tmpfs, it is returned. * * Otherwise, %NULL is returned. * @@ -1011,66 +1027,84 @@ repeat: EXPORT_SYMBOL(find_lock_entry); /** - * find_lock_page - locate, pin and lock a pagecache page + * 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 if a page is to be allocated * - * 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. + * Looks up the page cache slot at @mapping & @offset. * - * Otherwise, %NULL is returned. + * PCG flags modify how the page is returned * - * find_lock_page() may sleep. - */ -struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) -{ - struct page *page = find_lock_entry(mapping, offset); - - if (radix_tree_exceptional_entry(page)) - page = NULL; - return page; -} -EXPORT_SYMBOL(find_lock_page); - -/** - * 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 + * 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. * - * Looks up the page cache slot at @mapping & @offset. If there is a - * page cache page, it is returned locked and with an increased - * refcount. + * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even + * if the GFP flags specified for FGP_CREAT are atomic. * - * If the page is not present, a new page is allocated using @gfp_mask - * and added to the page cache and the VM's LRU list. The page is - * returned locked and with an increased refcount. - * - * On memory exhaustion, %NULL is returned. - * - * find_or_create_page() may sleep, even if @gfp_flags specifies an - * atomic allocation! + * 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 cache_gfp_mask, gfp_t radix_gfp_mask) { struct page *page; - int err; + repeat: - page = find_lock_page(mapping, index); - if (!page) { - page = __page_cache_alloc(gfp_mask); + 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(page->index != offset, page); + } + + 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)) + cache_gfp_mask |= __GFP_WRITE; + if (fgp_flags & FGP_NOFS) { + cache_gfp_mask &= ~__GFP_FS; + radix_gfp_mask &= ~__GFP_FS; + } + + page = __page_cache_alloc(cache_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, radix_gfp_mask); if (unlikely(err)) { page_cache_release(page); page = NULL; @@ -1078,9 +1112,10 @@ repeat: goto repeat; } } + return page; } -EXPORT_SYMBOL(find_or_create_page); +EXPORT_SYMBOL(pagecache_get_page); /** * find_get_entries - gang pagecache lookup @@ -1099,8 +1134,8 @@ EXPORT_SYMBOL(find_or_create_page); * 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. + * Any shadow entries of evicted pages, or swap entries from + * shmem/tmpfs, are included in the returned array. * * find_get_entries() returns the number of pages and shadow entries * which were found. @@ -1128,9 +1163,9 @@ repeat: 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. + * A shadow entry of a recently evicted page, + * or a swap entry from shmem/tmpfs. Return + * it without attempting to raise page count. */ goto export; } @@ -1198,9 +1233,9 @@ repeat: goto restart; } /* - * Otherwise, shmem/tmpfs must be storing a swap entry - * here as an exceptional entry: so skip over it - - * we only reach this from invalidate_mapping_pages(). + * A shadow entry of a recently evicted page, + * or a swap entry from shmem/tmpfs. Skip + * over it. */ continue; } @@ -1265,9 +1300,9 @@ repeat: goto restart; } /* - * Otherwise, shmem/tmpfs must be storing a swap entry - * here as an exceptional entry: so stop looking for - * contiguous pages. + * A shadow entry of a recently evicted page, + * or a swap entry from shmem/tmpfs. Stop + * looking for contiguous pages. */ break; } @@ -1341,10 +1376,17 @@ repeat: goto restart; } /* - * This function is never used on a shmem/tmpfs - * mapping, so a swap entry won't be found here. + * A shadow entry of a recently evicted page. + * + * Those entries should never be tagged, but + * this tree walk is lockless and the tags are + * looked up in bulk, one radix tree node at a + * time, so there is a sizable window for page + * reclaim to evict a page we saw tagged. + * + * Skip over it. */ - BUG(); + continue; } if (!page_cache_get_speculative(page)) @@ -1370,39 +1412,6 @@ 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: @@ -2372,7 +2381,6 @@ 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); @@ -2454,34 +2462,18 @@ 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), + GFP_KERNEL); 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); @@ -2530,7 +2522,7 @@ 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)) @@ -2539,7 +2531,6 @@ again: copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); flush_dcache_page(page); - mark_page_accessed(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status < 0)) diff --git a/mm/fremap.c b/mm/fremap.c index 34feba60a17e..72b8fa361433 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -82,13 +82,10 @@ static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, ptfile = pgoff_to_pte(pgoff); - if (!pte_none(*pte)) { - if (pte_present(*pte) && pte_soft_dirty(*pte)) - pte_file_mksoft_dirty(ptfile); + if (!pte_none(*pte)) zap_pte(mm, vma, addr, pte); - } - set_pte_at(mm, addr, pte, ptfile); + set_pte_at(mm, addr, pte, pte_file_mksoft_dirty(ptfile)); /* * We don't need to run update_mmu_cache() here because the "file pte" * being installed by install_file_pte() is not a real pte - it's a @@ -152,6 +149,10 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, int has_write_lock = 0; vm_flags_t vm_flags = 0; + pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. " + "See Documentation/vm/remap_file_pages.txt.\n", + current->comm, current->pid); + if (prot) return err; /* diff --git a/mm/frontswap.c b/mm/frontswap.c index 1b24bdcb3197..c30eec536f03 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -327,15 +327,12 @@ 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 +344,9 @@ 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 +361,7 @@ 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 +408,7 @@ 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/gup.c b/mm/gup.c new file mode 100644 index 000000000000..cc5a9e7adea7 --- /dev/null +++ b/mm/gup.c @@ -0,0 +1,662 @@ +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/err.h> +#include <linux/spinlock.h> + +#include <linux/hugetlb.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/rmap.h> +#include <linux/swap.h> +#include <linux/swapops.h> + +#include "internal.h" + +static struct page *no_page_table(struct vm_area_struct *vma, + unsigned int flags) +{ + /* + * When core dumping an enormous anonymous area that nobody + * has touched so far, we don't want to allocate unnecessary pages or + * page tables. Return error instead of NULL to skip handle_mm_fault, + * then get_dump_page() will return NULL to leave a hole in the dump. + * But we can only make this optimization where a hole would surely + * be zero-filled if handle_mm_fault() actually did handle it. + */ + if ((flags & FOLL_DUMP) && (!vma->vm_ops || !vma->vm_ops->fault)) + return ERR_PTR(-EFAULT); + return NULL; +} + +static struct page *follow_page_pte(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, unsigned int flags) +{ + struct mm_struct *mm = vma->vm_mm; + struct page *page; + spinlock_t *ptl; + pte_t *ptep, pte; + +retry: + if (unlikely(pmd_bad(*pmd))) + return no_page_table(vma, flags); + + ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + pte = *ptep; + if (!pte_present(pte)) { + swp_entry_t entry; + /* + * KSM's break_ksm() relies upon recognizing a ksm page + * even while it is being migrated, so for that case we + * need migration_entry_wait(). + */ + if (likely(!(flags & FOLL_MIGRATION))) + goto no_page; + if (pte_none(pte) || pte_file(pte)) + goto no_page; + entry = pte_to_swp_entry(pte); + if (!is_migration_entry(entry)) + goto no_page; + pte_unmap_unlock(ptep, ptl); + migration_entry_wait(mm, pmd, address); + goto retry; + } + if ((flags & FOLL_NUMA) && pte_numa(pte)) + goto no_page; + if ((flags & FOLL_WRITE) && !pte_write(pte)) { + pte_unmap_unlock(ptep, ptl); + return NULL; + } + + page = vm_normal_page(vma, address, pte); + if (unlikely(!page)) { + if ((flags & FOLL_DUMP) || + !is_zero_pfn(pte_pfn(pte))) + goto bad_page; + page = pte_page(pte); + } + + if (flags & FOLL_GET) + get_page_foll(page); + if (flags & FOLL_TOUCH) { + if ((flags & FOLL_WRITE) && + !pte_dirty(pte) && !PageDirty(page)) + set_page_dirty(page); + /* + * pte_mkyoung() would be more correct here, but atomic care + * is needed to avoid losing the dirty bit: it is easier to use + * mark_page_accessed(). + */ + mark_page_accessed(page); + } + if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { + /* + * The preliminary mapping check is mainly to avoid the + * pointless overhead of lock_page on the ZERO_PAGE + * which might bounce very badly if there is contention. + * + * If the page is already locked, we don't need to + * handle it now - vmscan will handle it later if and + * when it attempts to reclaim the page. + */ + if (page->mapping && trylock_page(page)) { + lru_add_drain(); /* push cached pages to LRU */ + /* + * Because we lock page here, and migration is + * blocked by the pte's page reference, and we + * know the page is still mapped, we don't even + * need to check for file-cache page truncation. + */ + mlock_vma_page(page); + unlock_page(page); + } + } + pte_unmap_unlock(ptep, ptl); + return page; +bad_page: + pte_unmap_unlock(ptep, ptl); + return ERR_PTR(-EFAULT); + +no_page: + pte_unmap_unlock(ptep, ptl); + if (!pte_none(pte)) + return NULL; + return no_page_table(vma, flags); +} + +/** + * follow_page_mask - look up a page descriptor from a user-virtual address + * @vma: vm_area_struct mapping @address + * @address: virtual address to look up + * @flags: flags modifying lookup behaviour + * @page_mask: on output, *page_mask is set according to the size of the page + * + * @flags can have FOLL_ flags set, defined in <linux/mm.h> + * + * Returns the mapped (struct page *), %NULL if no mapping exists, or + * an error pointer if there is a mapping to something not represented + * by a page descriptor (see also vm_normal_page()). + */ +struct page *follow_page_mask(struct vm_area_struct *vma, + unsigned long address, unsigned int flags, + unsigned int *page_mask) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + spinlock_t *ptl; + struct page *page; + struct mm_struct *mm = vma->vm_mm; + + *page_mask = 0; + + page = follow_huge_addr(mm, address, flags & FOLL_WRITE); + if (!IS_ERR(page)) { + BUG_ON(flags & FOLL_GET); + return page; + } + + pgd = pgd_offset(mm, address); + if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) + return no_page_table(vma, flags); + + pud = pud_offset(pgd, address); + if (pud_none(*pud)) + return no_page_table(vma, flags); + if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { + if (flags & FOLL_GET) + return NULL; + page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE); + return page; + } + if (unlikely(pud_bad(*pud))) + return no_page_table(vma, flags); + + pmd = pmd_offset(pud, address); + if (pmd_none(*pmd)) + return no_page_table(vma, flags); + if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) { + page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); + if (flags & FOLL_GET) { + /* + * Refcount on tail pages are not well-defined and + * shouldn't be taken. The caller should handle a NULL + * return when trying to follow tail pages. + */ + if (PageHead(page)) + get_page(page); + else + page = NULL; + } + return page; + } + if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) + return no_page_table(vma, flags); + if (pmd_trans_huge(*pmd)) { + if (flags & FOLL_SPLIT) { + split_huge_page_pmd(vma, address, pmd); + return follow_page_pte(vma, address, pmd, flags); + } + ptl = pmd_lock(mm, pmd); + if (likely(pmd_trans_huge(*pmd))) { + if (unlikely(pmd_trans_splitting(*pmd))) { + spin_unlock(ptl); + wait_split_huge_page(vma->anon_vma, pmd); + } else { + page = follow_trans_huge_pmd(vma, address, + pmd, flags); + spin_unlock(ptl); + *page_mask = HPAGE_PMD_NR - 1; + return page; + } + } else + spin_unlock(ptl); + } + return follow_page_pte(vma, address, pmd, flags); +} + +static int get_gate_page(struct mm_struct *mm, unsigned long address, + unsigned int gup_flags, struct vm_area_struct **vma, + struct page **page) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + int ret = -EFAULT; + + /* user gate pages are read-only */ + if (gup_flags & FOLL_WRITE) + return -EFAULT; + if (address > TASK_SIZE) + pgd = pgd_offset_k(address); + else + pgd = pgd_offset_gate(mm, address); + BUG_ON(pgd_none(*pgd)); + pud = pud_offset(pgd, address); + BUG_ON(pud_none(*pud)); + pmd = pmd_offset(pud, address); + if (pmd_none(*pmd)) + return -EFAULT; + VM_BUG_ON(pmd_trans_huge(*pmd)); + pte = pte_offset_map(pmd, address); + if (pte_none(*pte)) + goto unmap; + *vma = get_gate_vma(mm); + if (!page) + goto out; + *page = vm_normal_page(*vma, address, *pte); + if (!*page) { + if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(*pte))) + goto unmap; + *page = pte_page(*pte); + } + get_page(*page); +out: + ret = 0; +unmap: + pte_unmap(pte); + return ret; +} + +static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, + unsigned long address, unsigned int *flags, int *nonblocking) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned int fault_flags = 0; + int ret; + + /* For mlock, just skip the stack guard page. */ + if ((*flags & FOLL_MLOCK) && + (stack_guard_page_start(vma, address) || + stack_guard_page_end(vma, address + PAGE_SIZE))) + return -ENOENT; + if (*flags & FOLL_WRITE) + fault_flags |= FAULT_FLAG_WRITE; + if (nonblocking) + fault_flags |= FAULT_FLAG_ALLOW_RETRY; + if (*flags & FOLL_NOWAIT) + fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; + + ret = handle_mm_fault(mm, vma, address, fault_flags); + if (ret & VM_FAULT_ERROR) { + if (ret & VM_FAULT_OOM) + return -ENOMEM; + if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) + return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT; + if (ret & VM_FAULT_SIGBUS) + return -EFAULT; + BUG(); + } + + if (tsk) { + if (ret & VM_FAULT_MAJOR) + tsk->maj_flt++; + else + tsk->min_flt++; + } + + if (ret & VM_FAULT_RETRY) { + if (nonblocking) + *nonblocking = 0; + return -EBUSY; + } + + /* + * The VM_FAULT_WRITE bit tells us that do_wp_page has broken COW when + * necessary, even if maybe_mkwrite decided not to set pte_write. We + * can thus safely do subsequent page lookups as if they were reads. + * But only do so when looping for pte_write is futile: in some cases + * userspace may also be wanting to write to the gotten user page, + * which a read fault here might prevent (a readonly page might get + * reCOWed by userspace write). + */ + if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE)) + *flags &= ~FOLL_WRITE; + return 0; +} + +static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) +{ + vm_flags_t vm_flags = vma->vm_flags; + + if (vm_flags & (VM_IO | VM_PFNMAP)) + return -EFAULT; + + if (gup_flags & FOLL_WRITE) { + if (!(vm_flags & VM_WRITE)) { + if (!(gup_flags & FOLL_FORCE)) + return -EFAULT; + /* + * We used to let the write,force case do COW in a + * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could + * set a breakpoint in a read-only mapping of an + * executable, without corrupting the file (yet only + * when that file had been opened for writing!). + * Anon pages in shared mappings are surprising: now + * just reject it. + */ + if (!is_cow_mapping(vm_flags)) { + WARN_ON_ONCE(vm_flags & VM_MAYWRITE); + return -EFAULT; + } + } + } else if (!(vm_flags & VM_READ)) { + if (!(gup_flags & FOLL_FORCE)) + return -EFAULT; + /* + * Is there actually any vma we can reach here which does not + * have VM_MAYREAD set? + */ + if (!(vm_flags & VM_MAYREAD)) + return -EFAULT; + } + return 0; +} + +/** + * __get_user_pages() - pin user pages in memory + * @tsk: task_struct of target task + * @mm: mm_struct of target mm + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @gup_flags: flags modifying pin behaviour + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. Or NULL, if caller + * only intends to ensure the pages are faulted in. + * @vmas: array of pointers to vmas corresponding to each page. + * Or NULL if the caller does not require them. + * @nonblocking: whether waiting for disk IO or mmap_sem contention + * + * Returns number of pages pinned. This may be fewer than the number + * requested. If nr_pages is 0 or negative, returns 0. If no pages + * were pinned, returns -errno. Each page returned must be released + * with a put_page() call when it is finished with. vmas will only + * remain valid while mmap_sem is held. + * + * Must be called with mmap_sem held for read or write. + * + * __get_user_pages walks a process's page tables and takes a reference to + * each struct page that each user address corresponds to at a given + * instant. That is, it takes the page that would be accessed if a user + * thread accesses the given user virtual address at that instant. + * + * This does not guarantee that the page exists in the user mappings when + * __get_user_pages returns, and there may even be a completely different + * page there in some cases (eg. if mmapped pagecache has been invalidated + * and subsequently re faulted). However it does guarantee that the page + * won't be freed completely. And mostly callers simply care that the page + * contains data that was valid *at some point in time*. Typically, an IO + * or similar operation cannot guarantee anything stronger anyway because + * locks can't be held over the syscall boundary. + * + * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If + * the page is written to, set_page_dirty (or set_page_dirty_lock, as + * appropriate) must be called after the page is finished with, and + * before put_page is called. + * + * If @nonblocking != NULL, __get_user_pages will not wait for disk IO + * or mmap_sem contention, and if waiting is needed to pin all pages, + * *@nonblocking will be set to 0. + * + * In most cases, get_user_pages or get_user_pages_fast should be used + * instead of __get_user_pages. __get_user_pages should be used only if + * you need some special @gup_flags. + */ +long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *nonblocking) +{ + long i = 0; + unsigned int page_mask; + struct vm_area_struct *vma = NULL; + + if (!nr_pages) + return 0; + + VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET)); + + /* + * If FOLL_FORCE is set then do not force a full fault as the hinting + * fault information is unrelated to the reference behaviour of a task + * using the address space + */ + if (!(gup_flags & FOLL_FORCE)) + gup_flags |= FOLL_NUMA; + + do { + struct page *page; + unsigned int foll_flags = gup_flags; + unsigned int page_increm; + + /* first iteration or cross vma bound */ + if (!vma || start >= vma->vm_end) { + vma = find_extend_vma(mm, start); + if (!vma && in_gate_area(mm, start)) { + int ret; + ret = get_gate_page(mm, start & PAGE_MASK, + gup_flags, &vma, + pages ? &pages[i] : NULL); + if (ret) + return i ? : ret; + page_mask = 0; + goto next_page; + } + + if (!vma || check_vma_flags(vma, gup_flags)) + return i ? : -EFAULT; + if (is_vm_hugetlb_page(vma)) { + i = follow_hugetlb_page(mm, vma, pages, vmas, + &start, &nr_pages, i, + gup_flags); + continue; + } + } +retry: + /* + * If we have a pending SIGKILL, don't keep faulting pages and + * potentially allocating memory. + */ + if (unlikely(fatal_signal_pending(current))) + return i ? i : -ERESTARTSYS; + cond_resched(); + page = follow_page_mask(vma, start, foll_flags, &page_mask); + if (!page) { + int ret; + ret = faultin_page(tsk, vma, start, &foll_flags, + nonblocking); + switch (ret) { + case 0: + goto retry; + case -EFAULT: + case -ENOMEM: + case -EHWPOISON: + return i ? i : ret; + case -EBUSY: + return i; + case -ENOENT: + goto next_page; + } + BUG(); + } + if (IS_ERR(page)) + return i ? i : PTR_ERR(page); + if (pages) { + pages[i] = page; + flush_anon_page(vma, page, start); + flush_dcache_page(page); + page_mask = 0; + } +next_page: + if (vmas) { + vmas[i] = vma; + page_mask = 0; + } + page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask); + if (page_increm > nr_pages) + page_increm = nr_pages; + i += page_increm; + start += page_increm * PAGE_SIZE; + nr_pages -= page_increm; + } while (nr_pages); + return i; +} +EXPORT_SYMBOL(__get_user_pages); + +/* + * fixup_user_fault() - manually resolve a user page fault + * @tsk: the task_struct to use for page fault accounting, or + * NULL if faults are not to be recorded. + * @mm: mm_struct of target mm + * @address: user address + * @fault_flags:flags to pass down to handle_mm_fault() + * + * This is meant to be called in the specific scenario where for locking reasons + * we try to access user memory in atomic context (within a pagefault_disable() + * section), this returns -EFAULT, and we want to resolve the user fault before + * trying again. + * + * Typically this is meant to be used by the futex code. + * + * The main difference with get_user_pages() is that this function will + * unconditionally call handle_mm_fault() which will in turn perform all the + * necessary SW fixup of the dirty and young bits in the PTE, while + * handle_mm_fault() only guarantees to update these in the struct page. + * + * This is important for some architectures where those bits also gate the + * access permission to the page because they are maintained in software. On + * such architectures, gup() will not be enough to make a subsequent access + * succeed. + * + * This should be called with the mm_sem held for read. + */ +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) + return -ENOMEM; + if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) + return -EHWPOISON; + if (ret & VM_FAULT_SIGBUS) + return -EFAULT; + BUG(); + } + if (tsk) { + if (ret & VM_FAULT_MAJOR) + tsk->maj_flt++; + else + tsk->min_flt++; + } + return 0; +} + +/* + * get_user_pages() - pin user pages in memory + * @tsk: the task_struct to use for page fault accounting, or + * NULL if faults are not to be recorded. + * @mm: mm_struct of target mm + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @write: whether pages will be written to by the caller + * @force: whether to force access even when user mapping is currently + * protected (but never forces write access to shared mapping). + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. Or NULL, if caller + * only intends to ensure the pages are faulted in. + * @vmas: array of pointers to vmas corresponding to each page. + * Or NULL if the caller does not require them. + * + * Returns number of pages pinned. This may be fewer than the number + * requested. If nr_pages is 0 or negative, returns 0. If no pages + * were pinned, returns -errno. Each page returned must be released + * with a put_page() call when it is finished with. vmas will only + * remain valid while mmap_sem is held. + * + * Must be called with mmap_sem held for read or write. + * + * get_user_pages walks a process's page tables and takes a reference to + * each struct page that each user address corresponds to at a given + * instant. That is, it takes the page that would be accessed if a user + * thread accesses the given user virtual address at that instant. + * + * This does not guarantee that the page exists in the user mappings when + * get_user_pages returns, and there may even be a completely different + * page there in some cases (eg. if mmapped pagecache has been invalidated + * and subsequently re faulted). However it does guarantee that the page + * won't be freed completely. And mostly callers simply care that the page + * contains data that was valid *at some point in time*. Typically, an IO + * or similar operation cannot guarantee anything stronger anyway because + * locks can't be held over the syscall boundary. + * + * If write=0, the page must not be written to. If the page is written to, + * set_page_dirty (or set_page_dirty_lock, as appropriate) must be called + * after the page is finished with, and before put_page is called. + * + * get_user_pages is typically used for fewer-copy IO operations, to get a + * handle on the memory by some means other than accesses via the user virtual + * addresses. The pages may be submitted for DMA to devices or accessed via + * their kernel linear mapping (via the kmap APIs). Care should be taken to + * use the correct cache flushing APIs. + * + * See also get_user_pages_fast, for performance critical applications. + */ +long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, int write, + int force, struct page **pages, struct vm_area_struct **vmas) +{ + int flags = FOLL_TOUCH; + + if (pages) + flags |= FOLL_GET; + if (write) + flags |= FOLL_WRITE; + if (force) + flags |= FOLL_FORCE; + + return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas, + NULL); +} +EXPORT_SYMBOL(get_user_pages); + +/** + * get_dump_page() - pin user page in memory while writing it to core dump + * @addr: user address + * + * Returns struct page pointer of user page pinned for dump, + * to be freed afterwards by page_cache_release() or put_page(). + * + * Returns NULL on any kind of failure - a hole must then be inserted into + * the corefile, to preserve alignment with its headers; and also returns + * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - + * allowing a hole to be left in the corefile to save diskspace. + * + * Called without mmap_sem, but after all other threads have been killed. + */ +#ifdef CONFIG_ELF_CORE +struct page *get_dump_page(unsigned long addr) +{ + struct vm_area_struct *vma; + struct page *page; + + if (__get_user_pages(current, current->mm, addr, 1, + FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma, + NULL) < 1) + return NULL; + flush_cache_page(vma, addr, page_to_pfn(page)); + return page; +} +#endif /* CONFIG_ELF_CORE */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b4b1feba6472..e60837dc785c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -5,6 +5,8 @@ * the COPYING file in the top-level directory. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/mm.h> #include <linux/sched.h> #include <linux/highmem.h> @@ -151,8 +153,7 @@ static int start_khugepaged(void) khugepaged_thread = kthread_run(khugepaged, NULL, "khugepaged"); if (unlikely(IS_ERR(khugepaged_thread))) { - printk(KERN_ERR - "khugepaged: kthread_run(khugepaged) failed\n"); + pr_err("khugepaged: kthread_run(khugepaged) failed\n"); err = PTR_ERR(khugepaged_thread); khugepaged_thread = NULL; } @@ -584,19 +585,19 @@ static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj) *hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj); if (unlikely(!*hugepage_kobj)) { - printk(KERN_ERR "hugepage: failed to create transparent hugepage kobject\n"); + pr_err("failed to create transparent hugepage kobject\n"); return -ENOMEM; } err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group); if (err) { - printk(KERN_ERR "hugepage: failed to register transparent hugepage group\n"); + pr_err("failed to register transparent hugepage group\n"); goto delete_obj; } err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group); if (err) { - printk(KERN_ERR "hugepage: failed to register transparent hugepage group\n"); + pr_err("failed to register transparent hugepage group\n"); goto remove_hp_group; } @@ -689,8 +690,7 @@ static int __init setup_transparent_hugepage(char *str) } out: if (!ret) - printk(KERN_WARNING - "transparent_hugepage= cannot parse, ignored\n"); + pr_warn("transparent_hugepage= cannot parse, ignored\n"); return ret; } __setup("transparent_hugepage=", setup_transparent_hugepage); @@ -1830,10 +1830,11 @@ static void __split_huge_page(struct page *page, * the newly established pmd of the child later during the * walk, to be able to set it as pmd_trans_splitting too. */ - if (mapcount != page_mapcount(page)) - printk(KERN_ERR "mapcount %d page_mapcount %d\n", - mapcount, page_mapcount(page)); - BUG_ON(mapcount != page_mapcount(page)); + if (mapcount != page_mapcount(page)) { + pr_err("mapcount %d page_mapcount %d\n", + mapcount, page_mapcount(page)); + BUG(); + } __split_huge_page_refcount(page, list); @@ -1844,10 +1845,11 @@ static void __split_huge_page(struct page *page, BUG_ON(is_vma_temporary_stack(vma)); mapcount2 += __split_huge_page_map(page, vma, addr); } - if (mapcount != mapcount2) - printk(KERN_ERR "mapcount %d mapcount2 %d page_mapcount %d\n", - mapcount, mapcount2, page_mapcount(page)); - BUG_ON(mapcount != mapcount2); + if (mapcount != mapcount2) { + pr_err("mapcount %d mapcount2 %d page_mapcount %d\n", + mapcount, mapcount2, page_mapcount(page)); + BUG(); + } } /* @@ -2740,7 +2742,7 @@ static int khugepaged(void *none) struct mm_slot *mm_slot; set_freezable(); - set_user_nice(current, 19); + set_user_nice(current, MAX_NICE); while (!kthread_should_stop()) { khugepaged_do_scan(); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 246192929a2d..226910cb7c9b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -544,7 +544,7 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid) /* Movability of hugepages depends on migration support. */ static inline gfp_t htlb_alloc_mask(struct hstate *h) { - if (hugepages_treat_as_movable || hugepage_migration_support(h)) + if (hugepages_treat_as_movable || hugepage_migration_supported(h)) return GFP_HIGHUSER_MOVABLE; else return GFP_HIGHUSER; @@ -607,25 +607,242 @@ err: return NULL; } +/* + * common helper functions for hstate_next_node_to_{alloc|free}. + * We may have allocated or freed a huge page based on a different + * nodes_allowed previously, so h->next_node_to_{alloc|free} might + * be outside of *nodes_allowed. Ensure that we use an allowed + * node for alloc or free. + */ +static int next_node_allowed(int nid, nodemask_t *nodes_allowed) +{ + nid = next_node(nid, *nodes_allowed); + if (nid == MAX_NUMNODES) + nid = first_node(*nodes_allowed); + VM_BUG_ON(nid >= MAX_NUMNODES); + + return nid; +} + +static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed) +{ + if (!node_isset(nid, *nodes_allowed)) + nid = next_node_allowed(nid, nodes_allowed); + return nid; +} + +/* + * returns the previously saved node ["this node"] from which to + * allocate a persistent huge page for the pool and advance the + * next node from which to allocate, handling wrap at end of node + * mask. + */ +static int hstate_next_node_to_alloc(struct hstate *h, + nodemask_t *nodes_allowed) +{ + int nid; + + VM_BUG_ON(!nodes_allowed); + + nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed); + h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed); + + return nid; +} + +/* + * helper for free_pool_huge_page() - return the previously saved + * node ["this node"] from which to free a huge page. Advance the + * next node id whether or not we find a free huge page to free so + * that the next attempt to free addresses the next node. + */ +static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) +{ + int nid; + + VM_BUG_ON(!nodes_allowed); + + nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed); + h->next_nid_to_free = next_node_allowed(nid, nodes_allowed); + + return nid; +} + +#define for_each_node_mask_to_alloc(hs, nr_nodes, node, mask) \ + for (nr_nodes = nodes_weight(*mask); \ + nr_nodes > 0 && \ + ((node = hstate_next_node_to_alloc(hs, mask)) || 1); \ + nr_nodes--) + +#define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \ + for (nr_nodes = nodes_weight(*mask); \ + nr_nodes > 0 && \ + ((node = hstate_next_node_to_free(hs, mask)) || 1); \ + nr_nodes--) + +#if defined(CONFIG_CMA) && defined(CONFIG_X86_64) +static void destroy_compound_gigantic_page(struct page *page, + unsigned long order) +{ + int i; + int nr_pages = 1 << order; + struct page *p = page + 1; + + for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { + __ClearPageTail(p); + set_page_refcounted(p); + p->first_page = NULL; + } + + set_compound_order(page, 0); + __ClearPageHead(page); +} + +static void free_gigantic_page(struct page *page, unsigned order) +{ + free_contig_range(page_to_pfn(page), 1 << order); +} + +static int __alloc_gigantic_page(unsigned long start_pfn, + unsigned long nr_pages) +{ + unsigned long end_pfn = start_pfn + nr_pages; + return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE); +} + +static bool pfn_range_valid_gigantic(unsigned long start_pfn, + unsigned long nr_pages) +{ + unsigned long i, end_pfn = start_pfn + nr_pages; + struct page *page; + + for (i = start_pfn; i < end_pfn; i++) { + if (!pfn_valid(i)) + return false; + + page = pfn_to_page(i); + + if (PageReserved(page)) + return false; + + if (page_count(page) > 0) + return false; + + if (PageHuge(page)) + return false; + } + + return true; +} + +static bool zone_spans_last_pfn(const struct zone *zone, + unsigned long start_pfn, unsigned long nr_pages) +{ + unsigned long last_pfn = start_pfn + nr_pages - 1; + return zone_spans_pfn(zone, last_pfn); +} + +static struct page *alloc_gigantic_page(int nid, unsigned order) +{ + unsigned long nr_pages = 1 << order; + unsigned long ret, pfn, flags; + struct zone *z; + + z = NODE_DATA(nid)->node_zones; + for (; z - NODE_DATA(nid)->node_zones < MAX_NR_ZONES; z++) { + spin_lock_irqsave(&z->lock, flags); + + pfn = ALIGN(z->zone_start_pfn, nr_pages); + while (zone_spans_last_pfn(z, pfn, nr_pages)) { + if (pfn_range_valid_gigantic(pfn, nr_pages)) { + /* + * We release the zone lock here because + * alloc_contig_range() will also lock the zone + * at some point. If there's an allocation + * spinning on this lock, it may win the race + * and cause alloc_contig_range() to fail... + */ + spin_unlock_irqrestore(&z->lock, flags); + ret = __alloc_gigantic_page(pfn, nr_pages); + if (!ret) + return pfn_to_page(pfn); + spin_lock_irqsave(&z->lock, flags); + } + pfn += nr_pages; + } + + spin_unlock_irqrestore(&z->lock, flags); + } + + return NULL; +} + +static void prep_new_huge_page(struct hstate *h, struct page *page, int nid); +static void prep_compound_gigantic_page(struct page *page, unsigned long order); + +static struct page *alloc_fresh_gigantic_page_node(struct hstate *h, int nid) +{ + struct page *page; + + page = alloc_gigantic_page(nid, huge_page_order(h)); + if (page) { + prep_compound_gigantic_page(page, huge_page_order(h)); + prep_new_huge_page(h, page, nid); + } + + return page; +} + +static int alloc_fresh_gigantic_page(struct hstate *h, + nodemask_t *nodes_allowed) +{ + struct page *page = NULL; + int nr_nodes, node; + + for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { + page = alloc_fresh_gigantic_page_node(h, node); + if (page) + return 1; + } + + return 0; +} + +static inline bool gigantic_page_supported(void) { return true; } +#else +static inline bool gigantic_page_supported(void) { return false; } +static inline void free_gigantic_page(struct page *page, unsigned order) { } +static inline void destroy_compound_gigantic_page(struct page *page, + unsigned long order) { } +static inline int alloc_fresh_gigantic_page(struct hstate *h, + nodemask_t *nodes_allowed) { return 0; } +#endif + static void update_and_free_page(struct hstate *h, struct page *page) { int i; - VM_BUG_ON(h->order >= MAX_ORDER); + if (hstate_is_gigantic(h) && !gigantic_page_supported()) + return; h->nr_huge_pages--; h->nr_huge_pages_node[page_to_nid(page)]--; for (i = 0; i < pages_per_huge_page(h); i++) { page[i].flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced | 1 << PG_dirty | - 1 << PG_active | 1 << PG_reserved | - 1 << PG_private | 1 << PG_writeback); + 1 << PG_active | 1 << PG_private | + 1 << PG_writeback); } VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page); set_compound_page_dtor(page, NULL); set_page_refcounted(page); - arch_release_hugepage(page); - __free_pages(page, huge_page_order(h)); + if (hstate_is_gigantic(h)) { + destroy_compound_gigantic_page(page, huge_page_order(h)); + free_gigantic_page(page, huge_page_order(h)); + } else { + arch_release_hugepage(page); + __free_pages(page, huge_page_order(h)); + } } struct hstate *size_to_hstate(unsigned long size) @@ -664,7 +881,7 @@ static void free_huge_page(struct page *page) if (restore_reserve) h->resv_huge_pages++; - if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) { + if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ list_del(&page->lru); update_and_free_page(h, page); @@ -690,8 +907,7 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) put_page(page); /* free it into the hugepage allocator */ } -static void __init prep_compound_gigantic_page(struct page *page, - unsigned long order) +static void prep_compound_gigantic_page(struct page *page, unsigned long order) { int i; int nr_pages = 1 << order; @@ -769,9 +985,6 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) { struct page *page; - if (h->order >= MAX_ORDER) - return NULL; - page = alloc_pages_exact_node(nid, htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, @@ -787,79 +1000,6 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) return page; } -/* - * common helper functions for hstate_next_node_to_{alloc|free}. - * We may have allocated or freed a huge page based on a different - * nodes_allowed previously, so h->next_node_to_{alloc|free} might - * be outside of *nodes_allowed. Ensure that we use an allowed - * node for alloc or free. - */ -static int next_node_allowed(int nid, nodemask_t *nodes_allowed) -{ - nid = next_node(nid, *nodes_allowed); - if (nid == MAX_NUMNODES) - nid = first_node(*nodes_allowed); - VM_BUG_ON(nid >= MAX_NUMNODES); - - return nid; -} - -static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed) -{ - if (!node_isset(nid, *nodes_allowed)) - nid = next_node_allowed(nid, nodes_allowed); - return nid; -} - -/* - * returns the previously saved node ["this node"] from which to - * allocate a persistent huge page for the pool and advance the - * next node from which to allocate, handling wrap at end of node - * mask. - */ -static int hstate_next_node_to_alloc(struct hstate *h, - nodemask_t *nodes_allowed) -{ - int nid; - - VM_BUG_ON(!nodes_allowed); - - nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed); - h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed); - - return nid; -} - -/* - * helper for free_pool_huge_page() - return the previously saved - * node ["this node"] from which to free a huge page. Advance the - * next node id whether or not we find a free huge page to free so - * that the next attempt to free addresses the next node. - */ -static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) -{ - int nid; - - VM_BUG_ON(!nodes_allowed); - - nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed); - h->next_nid_to_free = next_node_allowed(nid, nodes_allowed); - - return nid; -} - -#define for_each_node_mask_to_alloc(hs, nr_nodes, node, mask) \ - for (nr_nodes = nodes_weight(*mask); \ - nr_nodes > 0 && \ - ((node = hstate_next_node_to_alloc(hs, mask)) || 1); \ - nr_nodes--) - -#define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \ - for (nr_nodes = nodes_weight(*mask); \ - nr_nodes > 0 && \ - ((node = hstate_next_node_to_free(hs, mask)) || 1); \ - nr_nodes--) - static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed) { struct page *page; @@ -963,7 +1103,7 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) struct page *page; unsigned int r_nid; - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h)) return NULL; /* @@ -1156,7 +1296,7 @@ static void return_unused_surplus_pages(struct hstate *h, h->resv_huge_pages -= unused_resv_pages; /* Cannot return gigantic pages currently */ - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h)) return; nr_pages = min(unused_resv_pages, h->surplus_huge_pages); @@ -1246,24 +1386,17 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, return ERR_PTR(-ENOSPC); ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); - if (ret) { - if (chg || avoid_reserve) - hugepage_subpool_put_pages(spool, 1); - return ERR_PTR(-ENOSPC); - } + if (ret) + goto out_subpool_put; + spin_lock(&hugetlb_lock); page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, chg); if (!page) { spin_unlock(&hugetlb_lock); page = alloc_buddy_huge_page(h, NUMA_NO_NODE); - if (!page) { - hugetlb_cgroup_uncharge_cgroup(idx, - pages_per_huge_page(h), - h_cg); - if (chg || avoid_reserve) - hugepage_subpool_put_pages(spool, 1); - return ERR_PTR(-ENOSPC); - } + if (!page) + goto out_uncharge_cgroup; + spin_lock(&hugetlb_lock); list_move(&page->lru, &h->hugepage_activelist); /* Fall through */ @@ -1275,6 +1408,13 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, vma_commit_reservation(h, vma, addr); return page; + +out_uncharge_cgroup: + hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); +out_subpool_put: + if (chg || avoid_reserve) + hugepage_subpool_put_pages(spool, 1); + return ERR_PTR(-ENOSPC); } /* @@ -1356,7 +1496,7 @@ static void __init gather_bootmem_prealloc(void) * fix confusing memory reports from free(1) and another * side-effects, like CommitLimit going negative. */ - if (h->order > (MAX_ORDER - 1)) + if (hstate_is_gigantic(h)) adjust_managed_page_count(page, 1 << h->order); } } @@ -1366,7 +1506,7 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) unsigned long i; for (i = 0; i < h->max_huge_pages; ++i) { - if (h->order >= MAX_ORDER) { + if (hstate_is_gigantic(h)) { if (!alloc_bootmem_huge_page(h)) break; } else if (!alloc_fresh_huge_page(h, @@ -1382,7 +1522,7 @@ static void __init hugetlb_init_hstates(void) for_each_hstate(h) { /* oversize hugepages were init'ed in early boot */ - if (h->order < MAX_ORDER) + if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); } } @@ -1416,7 +1556,7 @@ static void try_to_free_low(struct hstate *h, unsigned long count, { int i; - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h)) return; for_each_node_mask(i, *nodes_allowed) { @@ -1479,7 +1619,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count, { unsigned long min_count, ret; - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h) && !gigantic_page_supported()) return h->max_huge_pages; /* @@ -1506,7 +1646,10 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count, * and reducing the surplus. */ spin_unlock(&hugetlb_lock); - ret = alloc_fresh_huge_page(h, nodes_allowed); + if (hstate_is_gigantic(h)) + ret = alloc_fresh_gigantic_page(h, nodes_allowed); + else + ret = alloc_fresh_huge_page(h, nodes_allowed); spin_lock(&hugetlb_lock); if (!ret) goto out; @@ -1606,7 +1749,7 @@ static ssize_t nr_hugepages_store_common(bool obey_mempolicy, goto out; h = kobj_to_hstate(kobj, &nid); - if (h->order >= MAX_ORDER) { + if (hstate_is_gigantic(h) && !gigantic_page_supported()) { err = -EINVAL; goto out; } @@ -1689,7 +1832,7 @@ static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, unsigned long input; struct hstate *h = kobj_to_hstate(kobj, NULL); - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h)) return -EINVAL; err = kstrtoul(buf, 10, &input); @@ -1981,11 +2124,7 @@ static int __init hugetlb_init(void) { int i; - /* Some platform decide whether they support huge pages at boot - * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when - * there is no such support - */ - if (HPAGE_SHIFT == 0) + if (!hugepages_supported()) return 0; if (!size_to_hstate(default_hstate_size)) { @@ -2112,9 +2251,12 @@ 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) + if (write && hstate_is_gigantic(h) && !gigantic_page_supported()) return -EINVAL; table->data = &tmp; @@ -2165,9 +2307,12 @@ 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) + if (write && hstate_is_gigantic(h)) return -EINVAL; table->data = &tmp; @@ -2190,6 +2335,8 @@ 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 +2353,8 @@ 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 +2369,9 @@ 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", diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 595d7fd795e1..493f758445e7 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -52,7 +52,7 @@ static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg) static inline struct hugetlb_cgroup * parent_hugetlb_cgroup(struct hugetlb_cgroup *h_cg) { - return hugetlb_cgroup_from_css(css_parent(&h_cg->css)); + return hugetlb_cgroup_from_css(h_cg->css.parent); } static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg) @@ -181,7 +181,7 @@ int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, again: rcu_read_lock(); h_cg = hugetlb_cgroup_from_task(current); - if (!css_tryget(&h_cg->css)) { + if (!css_tryget_online(&h_cg->css)) { rcu_read_unlock(); goto again; } @@ -253,15 +253,16 @@ static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css, return res_counter_read_u64(&h_cg->hugepage[idx], name); } -static int hugetlb_cgroup_write(struct cgroup_subsys_state *css, - struct cftype *cft, char *buffer) +static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { int idx, name, ret; unsigned long long val; - struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); - idx = MEMFILE_IDX(cft->private); - name = MEMFILE_ATTR(cft->private); + buf = strstrip(buf); + idx = MEMFILE_IDX(of_cft(of)->private); + name = MEMFILE_ATTR(of_cft(of)->private); switch (name) { case RES_LIMIT: @@ -271,7 +272,7 @@ static int hugetlb_cgroup_write(struct cgroup_subsys_state *css, break; } /* This function does all necessary parse...reuse it */ - ret = res_counter_memparse_write_strategy(buffer, &val); + ret = res_counter_memparse_write_strategy(buf, &val); if (ret) break; ret = res_counter_set_limit(&h_cg->hugepage[idx], val); @@ -280,17 +281,17 @@ static int hugetlb_cgroup_write(struct cgroup_subsys_state *css, ret = -EINVAL; break; } - return ret; + return ret ?: nbytes; } -static int hugetlb_cgroup_reset(struct cgroup_subsys_state *css, - unsigned int event) +static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { int idx, name, ret = 0; - struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); - idx = MEMFILE_IDX(event); - name = MEMFILE_ATTR(event); + idx = MEMFILE_IDX(of_cft(of)->private); + name = MEMFILE_ATTR(of_cft(of)->private); switch (name) { case RES_MAX_USAGE: @@ -303,7 +304,7 @@ static int hugetlb_cgroup_reset(struct cgroup_subsys_state *css, ret = -EINVAL; break; } - return ret; + return ret ?: nbytes; } static char *mem_fmt(char *buf, int size, unsigned long hsize) @@ -331,7 +332,7 @@ static void __init __hugetlb_cgroup_file_init(int idx) snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf); cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT); cft->read_u64 = hugetlb_cgroup_read_u64; - cft->write_string = hugetlb_cgroup_write; + cft->write = hugetlb_cgroup_write; /* Add the usage file */ cft = &h->cgroup_files[1]; @@ -343,14 +344,14 @@ static void __init __hugetlb_cgroup_file_init(int idx) cft = &h->cgroup_files[2]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf); cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE); - cft->trigger = hugetlb_cgroup_reset; + cft->write = hugetlb_cgroup_reset; cft->read_u64 = hugetlb_cgroup_read_u64; /* Add the failcntfile */ cft = &h->cgroup_files[3]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf); cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT); - cft->trigger = hugetlb_cgroup_reset; + cft->write = hugetlb_cgroup_reset; cft->read_u64 = hugetlb_cgroup_read_u64; /* NULL terminate the last cft */ diff --git a/mm/internal.h b/mm/internal.h index 07b67361a40a..7f22a11fcc66 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -134,7 +134,7 @@ 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 @@ -144,7 +144,10 @@ 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 @@ -169,6 +172,11 @@ static inline unsigned long page_order(struct page *page) return page_private(page); } +static inline bool is_cow_mapping(vm_flags_t flags) +{ + return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; +} + /* mm/util.c */ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node *rb_parent); @@ -184,26 +192,6 @@ static inline void munlock_vma_pages_all(struct vm_area_struct *vma) } /* - * Called only in fault path, to determine if a new page is being - * mapped into a LOCKED vma. If it is, mark page as mlocked. - */ -static inline int mlocked_vma_newpage(struct vm_area_struct *vma, - struct page *page) -{ - VM_BUG_ON_PAGE(PageLRU(page), page); - - if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) - return 0; - - if (!TestSetPageMlocked(page)) { - mod_zone_page_state(page_zone(page), NR_MLOCK, - hpage_nr_pages(page)); - count_vm_event(UNEVICTABLE_PGMLOCKED); - } - return 1; -} - -/* * must be called with vma's mmap_sem held for read or write, and page locked. */ extern void mlock_vma_page(struct page *page); @@ -245,10 +233,6 @@ extern unsigned long vma_address(struct page *page, struct vm_area_struct *vma); #endif #else /* !CONFIG_MMU */ -static inline int mlocked_vma_newpage(struct vm_area_struct *v, struct page *p) -{ - return 0; -} static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page) { } static inline void mlock_migrate_page(struct page *new, struct page *old) { } diff --git a/mm/kmemleak-test.c b/mm/kmemleak-test.c index ff0d9779cec8..dcdcadb69533 100644 --- a/mm/kmemleak-test.c +++ b/mm/kmemleak-test.c @@ -18,6 +18,8 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#define pr_fmt(fmt) "kmemleak: " fmt + #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> @@ -50,25 +52,25 @@ static int __init kmemleak_test_init(void) printk(KERN_INFO "Kmemleak testing\n"); /* make some orphan objects */ - pr_info("kmemleak: kmalloc(32) = %p\n", kmalloc(32, GFP_KERNEL)); - pr_info("kmemleak: kmalloc(32) = %p\n", kmalloc(32, GFP_KERNEL)); - pr_info("kmemleak: kmalloc(1024) = %p\n", kmalloc(1024, GFP_KERNEL)); - pr_info("kmemleak: kmalloc(1024) = %p\n", kmalloc(1024, GFP_KERNEL)); - pr_info("kmemleak: kmalloc(2048) = %p\n", kmalloc(2048, GFP_KERNEL)); - pr_info("kmemleak: kmalloc(2048) = %p\n", kmalloc(2048, GFP_KERNEL)); - pr_info("kmemleak: kmalloc(4096) = %p\n", kmalloc(4096, GFP_KERNEL)); - pr_info("kmemleak: kmalloc(4096) = %p\n", kmalloc(4096, GFP_KERNEL)); + pr_info("kmalloc(32) = %p\n", kmalloc(32, GFP_KERNEL)); + pr_info("kmalloc(32) = %p\n", kmalloc(32, GFP_KERNEL)); + pr_info("kmalloc(1024) = %p\n", kmalloc(1024, GFP_KERNEL)); + pr_info("kmalloc(1024) = %p\n", kmalloc(1024, GFP_KERNEL)); + pr_info("kmalloc(2048) = %p\n", kmalloc(2048, GFP_KERNEL)); + pr_info("kmalloc(2048) = %p\n", kmalloc(2048, GFP_KERNEL)); + pr_info("kmalloc(4096) = %p\n", kmalloc(4096, GFP_KERNEL)); + pr_info("kmalloc(4096) = %p\n", kmalloc(4096, GFP_KERNEL)); #ifndef CONFIG_MODULES - pr_info("kmemleak: kmem_cache_alloc(files_cachep) = %p\n", + pr_info("kmem_cache_alloc(files_cachep) = %p\n", kmem_cache_alloc(files_cachep, GFP_KERNEL)); - pr_info("kmemleak: kmem_cache_alloc(files_cachep) = %p\n", + pr_info("kmem_cache_alloc(files_cachep) = %p\n", kmem_cache_alloc(files_cachep, GFP_KERNEL)); #endif - pr_info("kmemleak: vmalloc(64) = %p\n", vmalloc(64)); - pr_info("kmemleak: vmalloc(64) = %p\n", vmalloc(64)); - pr_info("kmemleak: vmalloc(64) = %p\n", vmalloc(64)); - pr_info("kmemleak: vmalloc(64) = %p\n", vmalloc(64)); - pr_info("kmemleak: vmalloc(64) = %p\n", vmalloc(64)); + pr_info("vmalloc(64) = %p\n", vmalloc(64)); + pr_info("vmalloc(64) = %p\n", vmalloc(64)); + pr_info("vmalloc(64) = %p\n", vmalloc(64)); + pr_info("vmalloc(64) = %p\n", vmalloc(64)); + pr_info("vmalloc(64) = %p\n", vmalloc(64)); /* * Add elements to a list. They should only appear as orphan @@ -76,7 +78,7 @@ static int __init kmemleak_test_init(void) */ for (i = 0; i < 10; i++) { elem = kzalloc(sizeof(*elem), GFP_KERNEL); - pr_info("kmemleak: kzalloc(sizeof(*elem)) = %p\n", elem); + pr_info("kzalloc(sizeof(*elem)) = %p\n", elem); if (!elem) return -ENOMEM; INIT_LIST_HEAD(&elem->list); @@ -85,7 +87,7 @@ static int __init kmemleak_test_init(void) for_each_possible_cpu(i) { per_cpu(kmemleak_test_pointer, i) = kmalloc(129, GFP_KERNEL); - pr_info("kmemleak: kmalloc(129) = %p\n", + pr_info("kmalloc(129) = %p\n", per_cpu(kmemleak_test_pointer, i)); } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 91d67eaee050..3cda50c1e394 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -387,7 +387,7 @@ static void dump_object_info(struct kmemleak_object *object) pr_notice(" min_count = %d\n", object->min_count); pr_notice(" count = %d\n", object->count); pr_notice(" flags = 0x%lx\n", object->flags); - pr_notice(" checksum = %d\n", object->checksum); + pr_notice(" checksum = %u\n", object->checksum); pr_notice(" backtrace:\n"); print_stack_trace(&trace, 4); } @@ -990,6 +990,40 @@ void __ref kmemleak_free_percpu(const void __percpu *ptr) EXPORT_SYMBOL_GPL(kmemleak_free_percpu); /** + * kmemleak_update_trace - update object allocation stack trace + * @ptr: pointer to beginning of the object + * + * Override the object allocation stack trace for cases where the actual + * allocation place is not always useful. + */ +void __ref kmemleak_update_trace(const void *ptr) +{ + struct kmemleak_object *object; + unsigned long flags; + + pr_debug("%s(0x%p)\n", __func__, ptr); + + if (!kmemleak_enabled || IS_ERR_OR_NULL(ptr)) + return; + + object = find_and_get_object((unsigned long)ptr, 1); + if (!object) { +#ifdef DEBUG + kmemleak_warn("Updating stack trace for unknown object at %p\n", + ptr); +#endif + return; + } + + spin_lock_irqsave(&object->lock, flags); + object->trace_len = __save_stack_trace(object->trace); + spin_unlock_irqrestore(&object->lock, flags); + + put_object(object); +} +EXPORT_SYMBOL(kmemleak_update_trace); + +/** * kmemleak_not_leak - mark an allocated object as false positive * @ptr: pointer to beginning of the object * @@ -1300,7 +1334,7 @@ static void kmemleak_scan(void) /* * Struct page scanning for each node. */ - lock_memory_hotplug(); + get_online_mems(); for_each_online_node(i) { unsigned long start_pfn = node_start_pfn(i); unsigned long end_pfn = node_end_pfn(i); @@ -1318,7 +1352,7 @@ static void kmemleak_scan(void) scan_block(page, page + 1, NULL, 1); } } - unlock_memory_hotplug(); + put_online_mems(); /* * Scanning the task stacks (may introduce false negatives). @@ -1775,10 +1809,9 @@ void __init kmemleak_init(void) int i; unsigned long flags; - kmemleak_early_log = 0; - #ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF if (!kmemleak_skip_disable) { + kmemleak_early_log = 0; kmemleak_disable(); return; } @@ -1796,6 +1829,7 @@ void __init kmemleak_init(void) /* the kernel is still in UP mode, so disabling the IRQs is enough */ local_irq_save(flags); + kmemleak_early_log = 0; if (kmemleak_error) { local_irq_restore(flags); return; diff --git a/mm/madvise.c b/mm/madvise.c index 539eeb96b323..a402f8fdc68e 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/memblock.c b/mm/memblock.c index e9d6ca9a01a9..6d2f219a48b0 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -27,6 +27,9 @@ static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP +static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS] __initdata_memblock; +#endif struct memblock memblock __initdata_memblock = { .memory.regions = memblock_memory_init_regions, @@ -37,6 +40,12 @@ struct memblock memblock __initdata_memblock = { .reserved.cnt = 1, /* empty dummy entry */ .reserved.max = INIT_MEMBLOCK_REGIONS, +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP + .physmem.regions = memblock_physmem_init_regions, + .physmem.cnt = 1, /* empty dummy entry */ + .physmem.max = INIT_PHYSMEM_REGIONS, +#endif + .bottom_up = false, .current_limit = MEMBLOCK_ALLOC_ANYWHERE, }; @@ -472,7 +481,7 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type, } /** - * memblock_add_region - add new memblock region + * memblock_add_range - add new memblock region * @type: memblock type to add new region into * @base: base address of the new region * @size: size of the new region @@ -487,7 +496,7 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type, * RETURNS: * 0 on success, -errno on failure. */ -static int __init_memblock memblock_add_region(struct memblock_type *type, +int __init_memblock memblock_add_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int nid, unsigned long flags) { @@ -569,12 +578,12 @@ repeat: int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, int nid) { - return memblock_add_region(&memblock.memory, base, size, nid, 0); + return memblock_add_range(&memblock.memory, base, size, nid, 0); } int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) { - return memblock_add_region(&memblock.memory, base, size, + return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0); } @@ -654,8 +663,8 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, return 0; } -static int __init_memblock __memblock_remove(struct memblock_type *type, - phys_addr_t base, phys_addr_t size) +int __init_memblock memblock_remove_range(struct memblock_type *type, + phys_addr_t base, phys_addr_t size) { int start_rgn, end_rgn; int i, ret; @@ -671,9 +680,10 @@ static int __init_memblock __memblock_remove(struct memblock_type *type, int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) { - return __memblock_remove(&memblock.memory, base, size); + return memblock_remove_range(&memblock.memory, base, size); } + int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) { memblock_dbg(" memblock_free: [%#016llx-%#016llx] %pF\n", @@ -681,7 +691,8 @@ int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) (unsigned long long)base + size - 1, (void *)_RET_IP_); - return __memblock_remove(&memblock.reserved, base, size); + kmemleak_free_part(__va(base), size); + return memblock_remove_range(&memblock.reserved, base, size); } static int __init_memblock memblock_reserve_region(phys_addr_t base, @@ -696,7 +707,7 @@ static int __init_memblock memblock_reserve_region(phys_addr_t base, (unsigned long long)base + size - 1, flags, (void *)_RET_IP_); - return memblock_add_region(_rgn, base, size, nid, flags); + return memblock_add_range(_rgn, base, size, nid, flags); } int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) @@ -758,17 +769,19 @@ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) } /** - * __next_free_mem_range - next function for for_each_free_mem_range() + * __next__mem_range - next function for for_each_free_mem_range() etc. * @idx: pointer to u64 loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes + * @type_a: pointer to memblock_type from where the range is taken + * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * - * Find the first free area from *@idx which matches @nid, fill the out + * Find the first area from *@idx which matches @nid, fill the out * parameters, and update *@idx for the next iteration. The lower 32bit of - * *@idx contains index into memory region and the upper 32bit indexes the - * areas before each reserved region. For example, if reserved regions + * *@idx contains index into type_a and the upper 32bit indexes the + * areas before each region in type_b. For example, if type_b regions * look like the following, * * 0:[0-16), 1:[32-48), 2:[128-130) @@ -780,53 +793,77 @@ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) * As both region arrays are sorted, the function advances the two indices * in lockstep and returns each intersection. */ -void __init_memblock __next_free_mem_range(u64 *idx, int nid, - phys_addr_t *out_start, - phys_addr_t *out_end, int *out_nid) +void __init_memblock __next_mem_range(u64 *idx, int nid, + struct memblock_type *type_a, + struct memblock_type *type_b, + phys_addr_t *out_start, + phys_addr_t *out_end, int *out_nid) { - struct memblock_type *mem = &memblock.memory; - struct memblock_type *rsv = &memblock.reserved; - int mi = *idx & 0xffffffff; - int ri = *idx >> 32; + int idx_a = *idx & 0xffffffff; + int idx_b = *idx >> 32; - if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) + if (WARN_ONCE(nid == MAX_NUMNODES, + "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) nid = NUMA_NO_NODE; - for ( ; mi < mem->cnt; mi++) { - struct memblock_region *m = &mem->regions[mi]; + for (; idx_a < type_a->cnt; idx_a++) { + struct memblock_region *m = &type_a->regions[idx_a]; + phys_addr_t m_start = m->base; phys_addr_t m_end = m->base + m->size; + int m_nid = memblock_get_region_node(m); /* only memory regions are associated with nodes, check it */ - if (nid != NUMA_NO_NODE && nid != memblock_get_region_node(m)) + if (nid != NUMA_NO_NODE && nid != m_nid) continue; - /* scan areas before each reservation for intersection */ - for ( ; ri < rsv->cnt + 1; ri++) { - struct memblock_region *r = &rsv->regions[ri]; - phys_addr_t r_start = ri ? r[-1].base + r[-1].size : 0; - phys_addr_t r_end = ri < rsv->cnt ? r->base : ULLONG_MAX; + if (!type_b) { + if (out_start) + *out_start = m_start; + if (out_end) + *out_end = m_end; + if (out_nid) + *out_nid = m_nid; + idx_a++; + *idx = (u32)idx_a | (u64)idx_b << 32; + return; + } + + /* scan areas before each reservation */ + for (; idx_b < type_b->cnt + 1; idx_b++) { + struct memblock_region *r; + phys_addr_t r_start; + phys_addr_t r_end; - /* if ri advanced past mi, break out to advance mi */ + r = &type_b->regions[idx_b]; + r_start = idx_b ? r[-1].base + r[-1].size : 0; + r_end = idx_b < type_b->cnt ? + r->base : ULLONG_MAX; + + /* + * if idx_b advanced past idx_a, + * break out to advance idx_a + */ if (r_start >= m_end) break; /* if the two regions intersect, we're done */ if (m_start < r_end) { if (out_start) - *out_start = max(m_start, r_start); + *out_start = + max(m_start, r_start); if (out_end) *out_end = min(m_end, r_end); if (out_nid) - *out_nid = memblock_get_region_node(m); + *out_nid = m_nid; /* - * The region which ends first is advanced - * for the next iteration. + * The region which ends first is + * advanced for the next iteration. */ if (m_end <= r_end) - mi++; + idx_a++; else - ri++; - *idx = (u32)mi | (u64)ri << 32; + idx_b++; + *idx = (u32)idx_a | (u64)idx_b << 32; return; } } @@ -837,57 +874,80 @@ void __init_memblock __next_free_mem_range(u64 *idx, int nid, } /** - * __next_free_mem_range_rev - next function for for_each_free_mem_range_reverse() + * __next_mem_range_rev - generic next function for for_each_*_range_rev() + * + * Finds the next range from type_a which is not marked as unsuitable + * in type_b. + * * @idx: pointer to u64 loop variable * @nid: nid: node selector, %NUMA_NO_NODE for all nodes + * @type_a: pointer to memblock_type from where the range is taken + * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * - * Reverse of __next_free_mem_range(). - * - * Linux kernel cannot migrate pages used by itself. Memory hotplug users won't - * be able to hot-remove hotpluggable memory used by the kernel. So this - * function skip hotpluggable regions if needed when allocating memory for the - * kernel. + * Reverse of __next_mem_range(). */ -void __init_memblock __next_free_mem_range_rev(u64 *idx, int nid, - phys_addr_t *out_start, - phys_addr_t *out_end, int *out_nid) +void __init_memblock __next_mem_range_rev(u64 *idx, int nid, + struct memblock_type *type_a, + struct memblock_type *type_b, + phys_addr_t *out_start, + phys_addr_t *out_end, int *out_nid) { - struct memblock_type *mem = &memblock.memory; - struct memblock_type *rsv = &memblock.reserved; - int mi = *idx & 0xffffffff; - int ri = *idx >> 32; + int idx_a = *idx & 0xffffffff; + int idx_b = *idx >> 32; if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) nid = NUMA_NO_NODE; if (*idx == (u64)ULLONG_MAX) { - mi = mem->cnt - 1; - ri = rsv->cnt; + idx_a = type_a->cnt - 1; + idx_b = type_b->cnt; } - for ( ; mi >= 0; mi--) { - struct memblock_region *m = &mem->regions[mi]; + for (; idx_a >= 0; idx_a--) { + struct memblock_region *m = &type_a->regions[idx_a]; + phys_addr_t m_start = m->base; phys_addr_t m_end = m->base + m->size; + int m_nid = memblock_get_region_node(m); /* only memory regions are associated with nodes, check it */ - if (nid != NUMA_NO_NODE && nid != memblock_get_region_node(m)) + if (nid != NUMA_NO_NODE && nid != m_nid) continue; /* skip hotpluggable memory regions if needed */ if (movable_node_is_enabled() && memblock_is_hotpluggable(m)) continue; - /* scan areas before each reservation for intersection */ - for ( ; ri >= 0; ri--) { - struct memblock_region *r = &rsv->regions[ri]; - phys_addr_t r_start = ri ? r[-1].base + r[-1].size : 0; - phys_addr_t r_end = ri < rsv->cnt ? r->base : ULLONG_MAX; + if (!type_b) { + if (out_start) + *out_start = m_start; + if (out_end) + *out_end = m_end; + if (out_nid) + *out_nid = m_nid; + idx_a++; + *idx = (u32)idx_a | (u64)idx_b << 32; + return; + } + + /* scan areas before each reservation */ + for (; idx_b >= 0; idx_b--) { + struct memblock_region *r; + phys_addr_t r_start; + phys_addr_t r_end; + + r = &type_b->regions[idx_b]; + r_start = idx_b ? r[-1].base + r[-1].size : 0; + r_end = idx_b < type_b->cnt ? + r->base : ULLONG_MAX; + /* + * if idx_b advanced past idx_a, + * break out to advance idx_a + */ - /* if ri advanced past mi, break out to advance mi */ if (r_end <= m_start) break; /* if the two regions intersect, we're done */ @@ -897,18 +957,17 @@ void __init_memblock __next_free_mem_range_rev(u64 *idx, int nid, if (out_end) *out_end = min(m_end, r_end); if (out_nid) - *out_nid = memblock_get_region_node(m); - + *out_nid = m_nid; if (m_start >= r_start) - mi--; + idx_a--; else - ri--; - *idx = (u32)mi | (u64)ri << 32; + idx_b--; + *idx = (u32)idx_a | (u64)idx_b << 32; return; } } } - + /* signal end of iteration */ *idx = ULLONG_MAX; } @@ -975,22 +1034,40 @@ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, } #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ -static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size, - phys_addr_t align, phys_addr_t max_addr, - int nid) +static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, + phys_addr_t align, phys_addr_t start, + phys_addr_t end, int nid) { phys_addr_t found; if (!align) align = SMP_CACHE_BYTES; - found = memblock_find_in_range_node(size, align, 0, max_addr, nid); - if (found && !memblock_reserve(found, size)) + found = memblock_find_in_range_node(size, align, start, end, nid); + if (found && !memblock_reserve(found, size)) { + /* + * The min_count is set to 0 so that memblock allocations are + * never reported as leaks. + */ + kmemleak_alloc(__va(found), size, 0, 0); return found; - + } return 0; } +phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align, + phys_addr_t start, phys_addr_t end) +{ + return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE); +} + +static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size, + phys_addr_t align, phys_addr_t max_addr, + int nid) +{ + return memblock_alloc_range_nid(size, align, 0, max_addr, nid); +} + phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid) { return memblock_alloc_base_nid(size, align, MEMBLOCK_ALLOC_ACCESSIBLE, nid); @@ -1201,7 +1278,7 @@ void __init __memblock_free_early(phys_addr_t base, phys_addr_t size) __func__, (u64)base, (u64)base + size - 1, (void *)_RET_IP_); kmemleak_free_part(__va(base), size); - __memblock_remove(&memblock.reserved, base, size); + memblock_remove_range(&memblock.reserved, base, size); } /* @@ -1287,8 +1364,10 @@ void __init memblock_enforce_memory_limit(phys_addr_t limit) } /* truncate both memory and reserved regions */ - __memblock_remove(&memblock.memory, max_addr, (phys_addr_t)ULLONG_MAX); - __memblock_remove(&memblock.reserved, max_addr, (phys_addr_t)ULLONG_MAX); + memblock_remove_range(&memblock.memory, max_addr, + (phys_addr_t)ULLONG_MAX); + memblock_remove_range(&memblock.reserved, max_addr, + (phys_addr_t)ULLONG_MAX); } static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr) @@ -1329,9 +1408,8 @@ int __init_memblock memblock_search_pfn_nid(unsigned long pfn, if (mid == -1) return -1; - *start_pfn = type->regions[mid].base >> PAGE_SHIFT; - *end_pfn = (type->regions[mid].base + type->regions[mid].size) - >> PAGE_SHIFT; + *start_pfn = PFN_DOWN(type->regions[mid].base); + *end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size); return type->regions[mid].nid; } @@ -1502,6 +1580,9 @@ static int __init memblock_init_debugfs(void) return -ENXIO; debugfs_create_file("memory", S_IRUGO, root, &memblock.memory, &memblock_debug_fops); debugfs_create_file("reserved", S_IRUGO, root, &memblock.reserved, &memblock_debug_fops); +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP + debugfs_create_file("physmem", S_IRUGO, root, &memblock.physmem, &memblock_debug_fops); +#endif return 0; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 29501f040568..a2c7bcb0e6eb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -80,7 +80,7 @@ int do_swap_account __read_mostly; #ifdef CONFIG_MEMCG_SWAP_ENABLED static int really_do_swap_account __initdata = 1; #else -static int really_do_swap_account __initdata = 0; +static int really_do_swap_account __initdata; #endif #else @@ -357,10 +357,9 @@ struct mem_cgroup { struct cg_proto tcp_mem; #endif #if defined(CONFIG_MEMCG_KMEM) - /* analogous to slab_common's slab_caches list. per-memcg */ + /* analogous to slab_common's slab_caches list, but per-memcg; + * protected by memcg_slab_mutex */ struct list_head memcg_slab_caches; - /* Not a spinlock, we can take a lot of time walking the list */ - struct mutex slab_caches_mutex; /* Index in the kmem_cache->memcg_params->memcg_caches array */ int kmemcg_id; #endif @@ -527,18 +526,14 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { - /* - * The ID of the root cgroup is 0, but memcg treat 0 as an - * invalid ID, so we return (cgroup_id + 1). - */ - return memcg->css.cgroup->id + 1; + return memcg->css.id; } static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) { struct cgroup_subsys_state *css; - css = css_from_id(id - 1, &memory_cgrp_subsys); + css = css_from_id(id, &memory_cgrp_subsys); return mem_cgroup_from_css(css); } @@ -571,7 +566,8 @@ void sock_update_memcg(struct sock *sk) memcg = mem_cgroup_from_task(current); cg_proto = sk->sk_prot->proto_cgroup(memcg); if (!mem_cgroup_is_root(memcg) && - memcg_proto_active(cg_proto) && css_tryget(&memcg->css)) { + memcg_proto_active(cg_proto) && + css_tryget_online(&memcg->css)) { sk->sk_cgrp = cg_proto; } rcu_read_unlock(); @@ -677,9 +673,11 @@ static void disarm_static_keys(struct mem_cgroup *memcg) static void drain_all_stock_async(struct mem_cgroup *memcg); static struct mem_cgroup_per_zone * -mem_cgroup_zoneinfo(struct mem_cgroup *memcg, int nid, int zid) +mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) { - VM_BUG_ON((unsigned)nid >= nr_node_ids); + int nid = zone_to_nid(zone); + int zid = zone_idx(zone); + return &memcg->nodeinfo[nid]->zoneinfo[zid]; } @@ -689,12 +687,12 @@ struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg) } static struct mem_cgroup_per_zone * -page_cgroup_zoneinfo(struct mem_cgroup *memcg, struct page *page) +mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page) { int nid = page_to_nid(page); int zid = page_zonenum(page); - return mem_cgroup_zoneinfo(memcg, nid, zid); + return &memcg->nodeinfo[nid]->zoneinfo[zid]; } static struct mem_cgroup_tree_per_zone * @@ -712,11 +710,9 @@ soft_limit_tree_from_page(struct page *page) return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; } -static void -__mem_cgroup_insert_exceeded(struct mem_cgroup *memcg, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz, - unsigned long long new_usage_in_excess) +static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz, + unsigned long long new_usage_in_excess) { struct rb_node **p = &mctz->rb_root.rb_node; struct rb_node *parent = NULL; @@ -746,10 +742,8 @@ __mem_cgroup_insert_exceeded(struct mem_cgroup *memcg, mz->on_tree = true; } -static void -__mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) +static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) { if (!mz->on_tree) return; @@ -757,13 +751,11 @@ __mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, mz->on_tree = false; } -static void -mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) +static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) { spin_lock(&mctz->lock); - __mem_cgroup_remove_exceeded(memcg, mz, mctz); + __mem_cgroup_remove_exceeded(mz, mctz); spin_unlock(&mctz->lock); } @@ -773,16 +765,14 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) unsigned long long excess; struct mem_cgroup_per_zone *mz; struct mem_cgroup_tree_per_zone *mctz; - int nid = page_to_nid(page); - int zid = page_zonenum(page); - mctz = soft_limit_tree_from_page(page); + mctz = soft_limit_tree_from_page(page); /* * Necessary to update all ancestors when hierarchy is used. * because their event counter is not touched. */ for (; memcg; memcg = parent_mem_cgroup(memcg)) { - mz = mem_cgroup_zoneinfo(memcg, nid, zid); + mz = mem_cgroup_page_zoneinfo(memcg, page); excess = res_counter_soft_limit_excess(&memcg->res); /* * We have to update the tree if mz is on RB-tree or @@ -792,12 +782,12 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) spin_lock(&mctz->lock); /* if on-tree, remove it */ if (mz->on_tree) - __mem_cgroup_remove_exceeded(memcg, mz, mctz); + __mem_cgroup_remove_exceeded(mz, mctz); /* * Insert again. mz->usage_in_excess will be updated. * If excess is 0, no tree ops. */ - __mem_cgroup_insert_exceeded(memcg, mz, mctz, excess); + __mem_cgroup_insert_exceeded(mz, mctz, excess); spin_unlock(&mctz->lock); } } @@ -805,15 +795,15 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) { - int node, zone; - struct mem_cgroup_per_zone *mz; struct mem_cgroup_tree_per_zone *mctz; + struct mem_cgroup_per_zone *mz; + int nid, zid; - for_each_node(node) { - for (zone = 0; zone < MAX_NR_ZONES; zone++) { - mz = mem_cgroup_zoneinfo(memcg, node, zone); - mctz = soft_limit_tree_node_zone(node, zone); - mem_cgroup_remove_exceeded(memcg, mz, mctz); + for_each_node(nid) { + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; + mctz = soft_limit_tree_node_zone(nid, zid); + mem_cgroup_remove_exceeded(mz, mctz); } } } @@ -836,9 +826,9 @@ retry: * we will to add it back at the end of reclaim to its correct * position in the tree. */ - __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz); + __mem_cgroup_remove_exceeded(mz, mctz); if (!res_counter_soft_limit_excess(&mz->memcg->res) || - !css_tryget(&mz->memcg->css)) + !css_tryget_online(&mz->memcg->css)) goto retry; done: return mz; @@ -947,8 +937,7 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, __this_cpu_add(memcg->stat->nr_page_events, nr_pages); } -unsigned long -mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) +unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { struct mem_cgroup_per_zone *mz; @@ -956,46 +945,38 @@ mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) return mz->lru_size[lru]; } -static unsigned long -mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid, - unsigned int lru_mask) -{ - struct mem_cgroup_per_zone *mz; - enum lru_list lru; - unsigned long ret = 0; - - mz = mem_cgroup_zoneinfo(memcg, nid, zid); - - for_each_lru(lru) { - if (BIT(lru) & lru_mask) - ret += mz->lru_size[lru]; - } - return ret; -} - -static unsigned long -mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, - int nid, unsigned int lru_mask) +static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, + int nid, + unsigned int lru_mask) { - u64 total = 0; + unsigned long nr = 0; int zid; - for (zid = 0; zid < MAX_NR_ZONES; zid++) - total += mem_cgroup_zone_nr_lru_pages(memcg, - nid, zid, lru_mask); + VM_BUG_ON((unsigned)nid >= nr_node_ids); - return total; + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + struct mem_cgroup_per_zone *mz; + enum lru_list lru; + + for_each_lru(lru) { + if (!(BIT(lru) & lru_mask)) + continue; + mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; + nr += mz->lru_size[lru]; + } + } + return nr; } static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg, unsigned int lru_mask) { + unsigned long nr = 0; int nid; - u64 total = 0; for_each_node_state(nid, N_MEMORY) - total += mem_cgroup_node_nr_lru_pages(memcg, nid, lru_mask); - return total; + nr += mem_cgroup_node_nr_lru_pages(memcg, nid, lru_mask); + return nr; } static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, @@ -1077,10 +1058,19 @@ static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) rcu_read_lock(); do { - memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); - if (unlikely(!memcg)) + /* + * Page cache insertions can happen withou an + * actual mm context, e.g. during disk probing + * on boot, loopback IO, acct() writes etc. + */ + if (unlikely(!mm)) memcg = root_mem_cgroup; - } while (!css_tryget(&memcg->css)); + else { + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (unlikely(!memcg)) + memcg = root_mem_cgroup; + } + } while (!css_tryget_online(&memcg->css)); rcu_read_unlock(); return memcg; } @@ -1117,7 +1107,8 @@ skip_node: */ if (next_css) { if ((next_css == &root->css) || - ((next_css->flags & CSS_ONLINE) && css_tryget(next_css))) + ((next_css->flags & CSS_ONLINE) && + css_tryget_online(next_css))) return mem_cgroup_from_css(next_css); prev_css = next_css; @@ -1163,7 +1154,7 @@ mem_cgroup_iter_load(struct mem_cgroup_reclaim_iter *iter, * would be returned all the time. */ if (position && position != root && - !css_tryget(&position->css)) + !css_tryget_online(&position->css)) position = NULL; } return position; @@ -1234,11 +1225,9 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, int uninitialized_var(seq); if (reclaim) { - int nid = zone_to_nid(reclaim->zone); - int zid = zone_idx(reclaim->zone); struct mem_cgroup_per_zone *mz; - mz = mem_cgroup_zoneinfo(root, nid, zid); + mz = mem_cgroup_zone_zoneinfo(root, reclaim->zone); iter = &mz->reclaim_iter[reclaim->priority]; if (prev && reclaim->generation != iter->generation) { iter->last_visited = NULL; @@ -1345,7 +1334,7 @@ struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, goto out; } - mz = mem_cgroup_zoneinfo(memcg, zone_to_nid(zone), zone_idx(zone)); + mz = mem_cgroup_zone_zoneinfo(memcg, zone); lruvec = &mz->lruvec; out: /* @@ -1404,7 +1393,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone) if (!PageLRU(page) && !PageCgroupUsed(pc) && memcg != root_mem_cgroup) pc->mem_cgroup = memcg = root_mem_cgroup; - mz = page_cgroup_zoneinfo(memcg, page); + mz = mem_cgroup_page_zoneinfo(memcg, page); lruvec = &mz->lruvec; out: /* @@ -1542,7 +1531,7 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* root ? */ - if (!css_parent(&memcg->css)) + if (mem_cgroup_disabled() || !memcg->css.parent) return vm_swappiness; return memcg->swappiness; @@ -1586,23 +1575,12 @@ static void mem_cgroup_end_move(struct mem_cgroup *memcg) } /* - * 2 routines for checking "mem" is under move_account() or not. + * A routine for checking "mem" is under move_account() or not. * - * mem_cgroup_stolen() - checking whether a cgroup is mc.from or not. This - * is used for avoiding races in accounting. If true, - * pc->mem_cgroup may be overwritten. - * - * mem_cgroup_under_move() - checking a cgroup is mc.from or mc.to or - * under hierarchy of moving cgroups. This is for - * waiting at hith-memory prressure caused by "move". + * Checking a cgroup is mc.from or mc.to or under hierarchy of + * moving cgroups. This is for waiting at high-memory pressure + * caused by "move". */ - -static bool mem_cgroup_stolen(struct mem_cgroup *memcg) -{ - VM_BUG_ON(!rcu_read_lock_held()); - return atomic_read(&memcg->moving_account) > 0; -} - static bool mem_cgroup_under_move(struct mem_cgroup *memcg) { struct mem_cgroup *from; @@ -1645,7 +1623,6 @@ static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg) * Take this lock when * - a code tries to modify page's memcg while it's USED. * - a code tries to modify page state accounting in a memcg. - * see mem_cgroup_stolen(), too. */ static void move_lock_mem_cgroup(struct mem_cgroup *memcg, unsigned long *flags) @@ -2280,12 +2257,11 @@ cleanup: } /* - * Currently used to update mapped file statistics, but the routine can be - * generalized to update other statistics as well. + * Used to update mapped file or writeback or other statistics. * * Notes: Race condition * - * We usually use page_cgroup_lock() for accessing page_cgroup member but + * We usually use lock_page_cgroup() for accessing page_cgroup member but * it tends to be costly. But considering some conditions, we doesn't need * to do so _always_. * @@ -2299,8 +2275,8 @@ cleanup: * by flags. * * Considering "move", this is an only case we see a race. To make the race - * small, we check mm->moving_account and detect there are possibility of race - * If there is, we take a lock. + * small, we check memcg->moving_account and detect there are possibility + * of race or not. If there is, we take a lock. */ void __mem_cgroup_begin_update_page_stat(struct page *page, @@ -2318,9 +2294,10 @@ again: * If this memory cgroup is not under account moving, we don't * need to take move_lock_mem_cgroup(). Because we already hold * rcu_read_lock(), any calls to move_account will be delayed until - * rcu_read_unlock() if mem_cgroup_stolen() == true. + * rcu_read_unlock(). */ - if (!mem_cgroup_stolen(memcg)) + VM_BUG_ON(!rcu_read_lock_held()); + if (atomic_read(&memcg->moving_account) <= 0) return; move_lock_mem_cgroup(memcg, flags); @@ -2428,7 +2405,7 @@ static void drain_stock(struct memcg_stock_pcp *stock) */ static void drain_local_stock(struct work_struct *dummy) { - struct memcg_stock_pcp *stock = &__get_cpu_var(memcg_stock); + struct memcg_stock_pcp *stock = this_cpu_ptr(&memcg_stock); drain_stock(stock); clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); } @@ -2675,7 +2652,8 @@ static int mem_cgroup_try_charge(struct mem_cgroup *memcg, * free their memory. */ if (unlikely(test_thread_flag(TIF_MEMDIE) || - fatal_signal_pending(current))) + fatal_signal_pending(current) || + current->flags & PF_EXITING)) goto bypass; if (unlikely(task_in_memcg_oom(current))) @@ -2789,9 +2767,9 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg, /* * A helper function to get mem_cgroup from ID. must be called under - * rcu_read_lock(). The caller is responsible for calling css_tryget if - * the mem_cgroup is used for charging. (dropping refcnt from swap can be - * called against removed memcg.) + * rcu_read_lock(). The caller is responsible for calling + * css_tryget_online() if the mem_cgroup is used for charging. (dropping + * refcnt from swap can be called against removed memcg.) */ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) { @@ -2814,14 +2792,14 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) lock_page_cgroup(pc); if (PageCgroupUsed(pc)) { memcg = pc->mem_cgroup; - if (memcg && !css_tryget(&memcg->css)) + if (memcg && !css_tryget_online(&memcg->css)) memcg = NULL; } else if (PageSwapCache(page)) { ent.val = page_private(page); id = lookup_swap_cgroup_id(ent); rcu_read_lock(); memcg = mem_cgroup_lookup(id); - if (memcg && !css_tryget(&memcg->css)) + if (memcg && !css_tryget_online(&memcg->css)) memcg = NULL; rcu_read_unlock(); } @@ -2903,6 +2881,12 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, static DEFINE_MUTEX(set_limit_mutex); #ifdef CONFIG_MEMCG_KMEM +/* + * The memcg_slab_mutex is held whenever a per memcg kmem cache is created or + * destroyed. It protects memcg_caches arrays and memcg_slab_caches lists. + */ +static DEFINE_MUTEX(memcg_slab_mutex); + static DEFINE_MUTEX(activate_kmem_mutex); static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg) @@ -2935,10 +2919,10 @@ static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v) print_slabinfo_header(m); - mutex_lock(&memcg->slab_caches_mutex); + mutex_lock(&memcg_slab_mutex); list_for_each_entry(params, &memcg->memcg_slab_caches, list) cache_show(memcg_params_to_cache(params), m); - mutex_unlock(&memcg->slab_caches_mutex); + mutex_unlock(&memcg_slab_mutex); return 0; } @@ -3040,8 +3024,6 @@ void memcg_update_array_size(int num) memcg_limited_groups_array_size = memcg_caches_array_size(num); } -static void kmem_cache_destroy_work_func(struct work_struct *w); - int memcg_update_cache_size(struct kmem_cache *s, int num_groups) { struct memcg_cache_params *cur_params = s->memcg_params; @@ -3094,29 +3076,6 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups) return 0; } -char *memcg_create_cache_name(struct mem_cgroup *memcg, - struct kmem_cache *root_cache) -{ - static char *buf = NULL; - - /* - * We need a mutex here to protect the shared buffer. Since this is - * expected to be called only on cache creation, we can employ the - * slab_mutex for that purpose. - */ - lockdep_assert_held(&slab_mutex); - - if (!buf) { - buf = kmalloc(NAME_MAX + 1, GFP_KERNEL); - if (!buf) - return NULL; - } - - cgroup_name(memcg->css.cgroup, buf, NAME_MAX + 1); - return kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, - memcg_cache_id(memcg), buf); -} - int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, struct kmem_cache *root_cache) { @@ -3138,8 +3097,6 @@ int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, if (memcg) { s->memcg_params->memcg = memcg; s->memcg_params->root_cache = root_cache; - INIT_WORK(&s->memcg_params->destroy, - kmem_cache_destroy_work_func); css_get(&memcg->css); } else s->memcg_params->is_root_cache = true; @@ -3156,24 +3113,37 @@ void memcg_free_cache_params(struct kmem_cache *s) kfree(s->memcg_params); } -void memcg_register_cache(struct kmem_cache *s) +static void memcg_register_cache(struct mem_cgroup *memcg, + struct kmem_cache *root_cache) { - struct kmem_cache *root; - struct mem_cgroup *memcg; + static char memcg_name_buf[NAME_MAX + 1]; /* protected by + memcg_slab_mutex */ + struct kmem_cache *cachep; int id; - if (is_root_cache(s)) + lockdep_assert_held(&memcg_slab_mutex); + + id = memcg_cache_id(memcg); + + /* + * Since per-memcg caches are created asynchronously on first + * allocation (see memcg_kmem_get_cache()), several threads can try to + * create the same cache, but only one of them may succeed. + */ + if (cache_from_memcg_idx(root_cache, id)) return; + cgroup_name(memcg->css.cgroup, memcg_name_buf, NAME_MAX + 1); + cachep = memcg_create_kmem_cache(memcg, root_cache, memcg_name_buf); /* - * Holding the slab_mutex assures nobody will touch the memcg_caches - * array while we are modifying it. + * If we could not create a memcg cache, do not complain, because + * that's not critical at all as we can always proceed with the root + * cache. */ - lockdep_assert_held(&slab_mutex); + if (!cachep) + return; - root = s->memcg_params->root_cache; - memcg = s->memcg_params->memcg; - id = memcg_cache_id(memcg); + list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches); /* * Since readers won't lock (see cache_from_memcg_idx()), we need a @@ -3182,49 +3152,30 @@ void memcg_register_cache(struct kmem_cache *s) */ smp_wmb(); - /* - * Initialize the pointer to this cache in its parent's memcg_params - * before adding it to the memcg_slab_caches list, otherwise we can - * fail to convert memcg_params_to_cache() while traversing the list. - */ - VM_BUG_ON(root->memcg_params->memcg_caches[id]); - root->memcg_params->memcg_caches[id] = s; - - mutex_lock(&memcg->slab_caches_mutex); - list_add(&s->memcg_params->list, &memcg->memcg_slab_caches); - mutex_unlock(&memcg->slab_caches_mutex); + BUG_ON(root_cache->memcg_params->memcg_caches[id]); + root_cache->memcg_params->memcg_caches[id] = cachep; } -void memcg_unregister_cache(struct kmem_cache *s) +static void memcg_unregister_cache(struct kmem_cache *cachep) { - struct kmem_cache *root; + struct kmem_cache *root_cache; struct mem_cgroup *memcg; int id; - if (is_root_cache(s)) - return; + lockdep_assert_held(&memcg_slab_mutex); - /* - * Holding the slab_mutex assures nobody will touch the memcg_caches - * array while we are modifying it. - */ - lockdep_assert_held(&slab_mutex); + BUG_ON(is_root_cache(cachep)); - root = s->memcg_params->root_cache; - memcg = s->memcg_params->memcg; + root_cache = cachep->memcg_params->root_cache; + memcg = cachep->memcg_params->memcg; id = memcg_cache_id(memcg); - mutex_lock(&memcg->slab_caches_mutex); - list_del(&s->memcg_params->list); - mutex_unlock(&memcg->slab_caches_mutex); + BUG_ON(root_cache->memcg_params->memcg_caches[id] != cachep); + root_cache->memcg_params->memcg_caches[id] = NULL; - /* - * Clear the pointer to this cache in its parent's memcg_params only - * after removing it from the memcg_slab_caches list, otherwise we can - * fail to convert memcg_params_to_cache() while traversing the list. - */ - VM_BUG_ON(root->memcg_params->memcg_caches[id] != s); - root->memcg_params->memcg_caches[id] = NULL; + list_del(&cachep->memcg_params->list); + + kmem_cache_destroy(cachep); } /* @@ -3258,144 +3209,61 @@ static inline void memcg_resume_kmem_account(void) current->memcg_kmem_skip_account--; } -static void kmem_cache_destroy_work_func(struct work_struct *w) -{ - struct kmem_cache *cachep; - struct memcg_cache_params *p; - - p = container_of(w, struct memcg_cache_params, destroy); - - cachep = memcg_params_to_cache(p); - - /* - * If we get down to 0 after shrink, we could delete right away. - * However, memcg_release_pages() already puts us back in the workqueue - * in that case. If we proceed deleting, we'll get a dangling - * reference, and removing the object from the workqueue in that case - * is unnecessary complication. We are not a fast path. - * - * Note that this case is fundamentally different from racing with - * shrink_slab(): if memcg_cgroup_destroy_cache() is called in - * kmem_cache_shrink, not only we would be reinserting a dead cache - * into the queue, but doing so from inside the worker racing to - * destroy it. - * - * So if we aren't down to zero, we'll just schedule a worker and try - * again - */ - if (atomic_read(&cachep->memcg_params->nr_pages) != 0) - kmem_cache_shrink(cachep); - else - kmem_cache_destroy(cachep); -} - -void mem_cgroup_destroy_cache(struct kmem_cache *cachep) -{ - if (!cachep->memcg_params->dead) - return; - - /* - * There are many ways in which we can get here. - * - * We can get to a memory-pressure situation while the delayed work is - * still pending to run. The vmscan shrinkers can then release all - * cache memory and get us to destruction. If this is the case, we'll - * be executed twice, which is a bug (the second time will execute over - * bogus data). In this case, cancelling the work should be fine. - * - * But we can also get here from the worker itself, if - * kmem_cache_shrink is enough to shake all the remaining objects and - * get the page count to 0. In this case, we'll deadlock if we try to - * cancel the work (the worker runs with an internal lock held, which - * is the same lock we would hold for cancel_work_sync().) - * - * Since we can't possibly know who got us here, just refrain from - * running if there is already work pending - */ - if (work_pending(&cachep->memcg_params->destroy)) - return; - /* - * We have to defer the actual destroying to a workqueue, because - * we might currently be in a context that cannot sleep. - */ - schedule_work(&cachep->memcg_params->destroy); -} - -int __kmem_cache_destroy_memcg_children(struct kmem_cache *s) +int __memcg_cleanup_cache_params(struct kmem_cache *s) { struct kmem_cache *c; int i, failed = 0; - /* - * If the cache is being destroyed, we trust that there is no one else - * requesting objects from it. Even if there are, the sanity checks in - * kmem_cache_destroy should caught this ill-case. - * - * Still, we don't want anyone else freeing memcg_caches under our - * noses, which can happen if a new memcg comes to life. As usual, - * we'll take the activate_kmem_mutex to protect ourselves against - * this. - */ - mutex_lock(&activate_kmem_mutex); + mutex_lock(&memcg_slab_mutex); for_each_memcg_cache_index(i) { c = cache_from_memcg_idx(s, i); if (!c) continue; - /* - * We will now manually delete the caches, so to avoid races - * we need to cancel all pending destruction workers and - * proceed with destruction ourselves. - * - * kmem_cache_destroy() will call kmem_cache_shrink internally, - * and that could spawn the workers again: it is likely that - * the cache still have active pages until this very moment. - * This would lead us back to mem_cgroup_destroy_cache. - * - * But that will not execute at all if the "dead" flag is not - * set, so flip it down to guarantee we are in control. - */ - c->memcg_params->dead = false; - cancel_work_sync(&c->memcg_params->destroy); - kmem_cache_destroy(c); + memcg_unregister_cache(c); if (cache_from_memcg_idx(s, i)) failed++; } - mutex_unlock(&activate_kmem_mutex); + mutex_unlock(&memcg_slab_mutex); return failed; } -static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg) +static void memcg_unregister_all_caches(struct mem_cgroup *memcg) { struct kmem_cache *cachep; - struct memcg_cache_params *params; + struct memcg_cache_params *params, *tmp; if (!memcg_kmem_is_active(memcg)) return; - mutex_lock(&memcg->slab_caches_mutex); - list_for_each_entry(params, &memcg->memcg_slab_caches, list) { + mutex_lock(&memcg_slab_mutex); + list_for_each_entry_safe(params, tmp, &memcg->memcg_slab_caches, list) { cachep = memcg_params_to_cache(params); - cachep->memcg_params->dead = true; - schedule_work(&cachep->memcg_params->destroy); + kmem_cache_shrink(cachep); + if (atomic_read(&cachep->memcg_params->nr_pages) == 0) + memcg_unregister_cache(cachep); } - mutex_unlock(&memcg->slab_caches_mutex); + mutex_unlock(&memcg_slab_mutex); } -struct create_work { +struct memcg_register_cache_work { struct mem_cgroup *memcg; struct kmem_cache *cachep; struct work_struct work; }; -static void memcg_create_cache_work_func(struct work_struct *w) +static void memcg_register_cache_func(struct work_struct *w) { - struct create_work *cw = container_of(w, struct create_work, work); + struct memcg_register_cache_work *cw = + container_of(w, struct memcg_register_cache_work, work); struct mem_cgroup *memcg = cw->memcg; struct kmem_cache *cachep = cw->cachep; - kmem_cache_create_memcg(memcg, cachep); + mutex_lock(&memcg_slab_mutex); + memcg_register_cache(memcg, cachep); + mutex_unlock(&memcg_slab_mutex); + css_put(&memcg->css); kfree(cw); } @@ -3403,12 +3271,12 @@ static void memcg_create_cache_work_func(struct work_struct *w) /* * Enqueue the creation of a per-memcg kmem_cache. */ -static void __memcg_create_cache_enqueue(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void __memcg_schedule_register_cache(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { - struct create_work *cw; + struct memcg_register_cache_work *cw; - cw = kmalloc(sizeof(struct create_work), GFP_NOWAIT); + cw = kmalloc(sizeof(*cw), GFP_NOWAIT); if (cw == NULL) { css_put(&memcg->css); return; @@ -3417,17 +3285,17 @@ static void __memcg_create_cache_enqueue(struct mem_cgroup *memcg, cw->memcg = memcg; cw->cachep = cachep; - INIT_WORK(&cw->work, memcg_create_cache_work_func); + INIT_WORK(&cw->work, memcg_register_cache_func); schedule_work(&cw->work); } -static void memcg_create_cache_enqueue(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void memcg_schedule_register_cache(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { /* * We need to stop accounting when we kmalloc, because if the * corresponding kmalloc cache is not yet created, the first allocation - * in __memcg_create_cache_enqueue will recurse. + * in __memcg_schedule_register_cache will recurse. * * However, it is better to enclose the whole function. Depending on * the debugging options enabled, INIT_WORK(), for instance, can @@ -3436,9 +3304,27 @@ static void memcg_create_cache_enqueue(struct mem_cgroup *memcg, * the safest choice is to do it like this, wrapping the whole function. */ memcg_stop_kmem_account(); - __memcg_create_cache_enqueue(memcg, cachep); + __memcg_schedule_register_cache(memcg, cachep); memcg_resume_kmem_account(); } + +int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order) +{ + int res; + + res = memcg_charge_kmem(cachep->memcg_params->memcg, gfp, + PAGE_SIZE << order); + if (!res) + atomic_add(1 << order, &cachep->memcg_params->nr_pages); + return res; +} + +void __memcg_uncharge_slab(struct kmem_cache *cachep, int order) +{ + memcg_uncharge_kmem(cachep->memcg_params->memcg, PAGE_SIZE << order); + atomic_sub(1 << order, &cachep->memcg_params->nr_pages); +} + /* * Return the kmem_cache we're supposed to use for a slab allocation. * We try to use the current memcg's version of the cache. @@ -3477,7 +3363,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, } /* The corresponding put will be done in the workqueue. */ - if (!css_tryget(&memcg->css)) + if (!css_tryget_online(&memcg->css)) goto out; rcu_read_unlock(); @@ -3489,22 +3375,16 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, * * However, there are some clashes that can arrive from locking. * For instance, because we acquire the slab_mutex while doing - * kmem_cache_dup, this means no further allocation could happen - * with the slab_mutex held. - * - * Also, because cache creation issue get_online_cpus(), this - * creates a lock chain: memcg_slab_mutex -> cpu_hotplug_mutex, - * that ends up reversed during cpu hotplug. (cpuset allocates - * a bunch of GFP_KERNEL memory during cpuup). Due to all that, - * better to defer everything. + * memcg_create_kmem_cache, this means no further allocation + * could happen with the slab_mutex held. So it's better to + * defer everything. */ - memcg_create_cache_enqueue(memcg, cachep); + memcg_schedule_register_cache(memcg, cachep); return cachep; out: rcu_read_unlock(); return cachep; } -EXPORT_SYMBOL(__memcg_kmem_get_cache); /* * We need to verify if the allocation against current->mm->owner's memcg is @@ -3531,11 +3411,12 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order) /* * Disabling accounting is only relevant for some specific memcg * internal allocations. Therefore we would initially not have such - * check here, since direct calls to the page allocator that are marked - * with GFP_KMEMCG only happen outside memcg core. We are mostly - * concerned with cache allocations, and by having this test at - * memcg_kmem_get_cache, we are already able to relay the allocation to - * the root cache and bypass the memcg cache altogether. + * check here, since direct calls to the page allocator that are + * accounted to kmemcg (alloc_kmem_pages and friends) only happen + * outside memcg core. We are mostly concerned with cache allocations, + * and by having this test at memcg_kmem_get_cache, we are already able + * to relay the allocation to the root cache and bypass the memcg cache + * altogether. * * There is one exception, though: the SLUB allocator does not create * large order caches, but rather service large kmallocs directly from @@ -3622,7 +3503,7 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order) memcg_uncharge_kmem(memcg, PAGE_SIZE << order); } #else -static inline void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg) +static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg) { } #endif /* CONFIG_MEMCG_KMEM */ @@ -3958,17 +3839,9 @@ int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm, return 0; } - /* - * Page cache insertions can happen without an actual mm - * context, e.g. during disk probing on boot. - */ - if (unlikely(!mm)) - memcg = root_mem_cgroup; - else { - memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true); - if (!memcg) - return -ENOMEM; - } + memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true); + if (!memcg) + return -ENOMEM; __mem_cgroup_commit_charge(memcg, page, 1, type, false); return 0; } @@ -4250,8 +4123,8 @@ void mem_cgroup_uncharge_swap(swp_entry_t ent) memcg = mem_cgroup_lookup(id); if (memcg) { /* - * We uncharge this because swap is freed. - * This memcg can be obsolete one. We avoid calling css_tryget + * We uncharge this because swap is freed. This memcg can + * be obsolete one. We avoid calling css_tryget_online(). */ if (!mem_cgroup_is_root(memcg)) res_counter_uncharge(&memcg->memsw, PAGE_SIZE); @@ -4705,7 +4578,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, break; } while (1); } - __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz); + __mem_cgroup_remove_exceeded(mz, mctz); excess = res_counter_soft_limit_excess(&mz->memcg->res); /* * One school of thought says that we should not add @@ -4716,7 +4589,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, * term TODO. */ /* If excess == 0, no tree ops */ - __mem_cgroup_insert_exceeded(mz->memcg, mz, mctz, excess); + __mem_cgroup_insert_exceeded(mz, mctz, excess); spin_unlock(&mctz->lock); css_put(&mz->memcg->css); loop++; @@ -4783,9 +4656,9 @@ static void mem_cgroup_force_empty_list(struct mem_cgroup *memcg, if (mem_cgroup_move_parent(page, pc, memcg)) { /* found lock contention or "pc" is obsolete. */ busy = page; - cond_resched(); } else busy = NULL; + cond_resched(); } while (!list_empty(list)); } @@ -4836,18 +4709,28 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg) } while (usage > 0); } +/* + * Test whether @memcg has children, dead or alive. Note that this + * function doesn't care whether @memcg has use_hierarchy enabled and + * returns %true if there are child csses according to the cgroup + * hierarchy. Testing use_hierarchy is the caller's responsiblity. + */ static inline bool memcg_has_children(struct mem_cgroup *memcg) { - lockdep_assert_held(&memcg_create_mutex); + bool ret; + /* - * The lock does not prevent addition or deletion to the list - * of children, but it prevents a new child from being - * initialized based on this parent in css_online(), so it's - * enough to decide whether hierarchically inherited - * attributes can still be changed or not. + * The lock does not prevent addition or deletion of children, but + * it prevents a new child from being initialized based on this + * parent in css_online(), so it's enough to decide whether + * hierarchically inherited attributes can still be changed or not. */ - return memcg->use_hierarchy && - !list_empty(&memcg->css.cgroup->children); + lockdep_assert_held(&memcg_create_mutex); + + rcu_read_lock(); + ret = css_next_child(NULL, &memcg->css); + rcu_read_unlock(); + return ret; } /* @@ -4859,11 +4742,6 @@ static inline bool memcg_has_children(struct mem_cgroup *memcg) static int mem_cgroup_force_empty(struct mem_cgroup *memcg) { int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; - struct cgroup *cgrp = memcg->css.cgroup; - - /* returns EBUSY if there is a task or if we come here twice. */ - if (cgroup_has_tasks(cgrp) || !list_empty(&cgrp->children)) - return -EBUSY; /* we call try-to-free pages for make this cgroup empty */ lru_add_drain_all(); @@ -4883,20 +4761,19 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) } } - lru_add_drain(); - mem_cgroup_reparent_charges(memcg); return 0; } -static int mem_cgroup_force_empty_write(struct cgroup_subsys_state *css, - unsigned int event) +static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); if (mem_cgroup_is_root(memcg)) return -EINVAL; - return mem_cgroup_force_empty(memcg); + return mem_cgroup_force_empty(memcg) ?: nbytes; } static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css, @@ -4910,7 +4787,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, { int retval = 0; struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct mem_cgroup *parent_memcg = mem_cgroup_from_css(css_parent(&memcg->css)); + struct mem_cgroup *parent_memcg = mem_cgroup_from_css(memcg->css.parent); mutex_lock(&memcg_create_mutex); @@ -4927,7 +4804,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, */ if ((!parent_memcg || !parent_memcg->use_hierarchy) && (val == 1 || val == 0)) { - if (list_empty(&memcg->css.cgroup->children)) + if (!memcg_has_children(memcg)) memcg->use_hierarchy = val; else retval = -EBUSY; @@ -5044,7 +4921,8 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg, * of course permitted. */ mutex_lock(&memcg_create_mutex); - if (cgroup_has_tasks(memcg->css.cgroup) || memcg_has_children(memcg)) + if (cgroup_has_tasks(memcg->css.cgroup) || + (memcg->use_hierarchy && memcg_has_children(memcg))) err = -EBUSY; mutex_unlock(&memcg_create_mutex); if (err) @@ -5061,13 +4939,14 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg, * Make sure we have enough space for this cgroup in each root cache's * memcg_params. */ + mutex_lock(&memcg_slab_mutex); err = memcg_update_all_caches(memcg_id + 1); + mutex_unlock(&memcg_slab_mutex); if (err) goto out_rmid; memcg->kmemcg_id = memcg_id; INIT_LIST_HEAD(&memcg->memcg_slab_caches); - mutex_init(&memcg->slab_caches_mutex); /* * We couldn't have accounted to this cgroup, because it hasn't got the @@ -5145,17 +5024,18 @@ static int memcg_update_kmem_limit(struct mem_cgroup *memcg, * The user of this function is... * RES_LIMIT. */ -static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, - char *buffer) +static ssize_t mem_cgroup_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); enum res_type type; int name; unsigned long long val; int ret; - type = MEMFILE_TYPE(cft->private); - name = MEMFILE_ATTR(cft->private); + buf = strstrip(buf); + type = MEMFILE_TYPE(of_cft(of)->private); + name = MEMFILE_ATTR(of_cft(of)->private); switch (name) { case RES_LIMIT: @@ -5164,7 +5044,7 @@ static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, break; } /* This function does all necessary parse...reuse it */ - ret = res_counter_memparse_write_strategy(buffer, &val); + ret = res_counter_memparse_write_strategy(buf, &val); if (ret) break; if (type == _MEM) @@ -5177,7 +5057,7 @@ static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, return -EINVAL; break; case RES_SOFT_LIMIT: - ret = res_counter_memparse_write_strategy(buffer, &val); + ret = res_counter_memparse_write_strategy(buf, &val); if (ret) break; /* @@ -5194,7 +5074,7 @@ static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, ret = -EINVAL; /* should be BUG() ? */ break; } - return ret; + return ret ?: nbytes; } static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg, @@ -5207,8 +5087,8 @@ static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg, if (!memcg->use_hierarchy) goto out; - while (css_parent(&memcg->css)) { - memcg = mem_cgroup_from_css(css_parent(&memcg->css)); + while (memcg->css.parent) { + memcg = mem_cgroup_from_css(memcg->css.parent); if (!memcg->use_hierarchy) break; tmp = res_counter_read_u64(&memcg->res, RES_LIMIT); @@ -5221,14 +5101,15 @@ out: *memsw_limit = min_memsw_limit; } -static int mem_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event) +static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); int name; enum res_type type; - type = MEMFILE_TYPE(event); - name = MEMFILE_ATTR(event); + type = MEMFILE_TYPE(of_cft(of)->private); + name = MEMFILE_ATTR(of_cft(of)->private); switch (name) { case RES_MAX_USAGE: @@ -5253,7 +5134,7 @@ static int mem_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event) break; } - return 0; + return nbytes; } static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css, @@ -5412,7 +5293,7 @@ static int memcg_stat_show(struct seq_file *m, void *v) for_each_online_node(nid) for (zid = 0; zid < MAX_NR_ZONES; zid++) { - mz = mem_cgroup_zoneinfo(memcg, nid, zid); + mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; rstat = &mz->lruvec.reclaim_stat; recent_rotated[0] += rstat->recent_rotated[0]; @@ -5442,22 +5323,14 @@ static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css)); - - if (val > 100 || !parent) - return -EINVAL; - - mutex_lock(&memcg_create_mutex); - /* If under hierarchy, only empty-root can set this value */ - if ((parent->use_hierarchy) || memcg_has_children(memcg)) { - mutex_unlock(&memcg_create_mutex); + if (val > 100) return -EINVAL; - } - - memcg->swappiness = val; - mutex_unlock(&memcg_create_mutex); + if (css->parent) + memcg->swappiness = val; + else + vm_swappiness = val; return 0; } @@ -5789,22 +5662,15 @@ static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css)); /* cannot set to root cgroup and only 0 and 1 are allowed */ - if (!parent || !((val == 0) || (val == 1))) + if (!css->parent || !((val == 0) || (val == 1))) return -EINVAL; - mutex_lock(&memcg_create_mutex); - /* oom-kill-disable is a flag for subhierarchy. */ - if ((parent->use_hierarchy) || memcg_has_children(memcg)) { - mutex_unlock(&memcg_create_mutex); - return -EINVAL; - } memcg->oom_kill_disable = val; if (!val) memcg_oom_recover(memcg); - mutex_unlock(&memcg_create_mutex); + return 0; } @@ -5844,10 +5710,10 @@ static void kmem_cgroup_css_offline(struct mem_cgroup *memcg) * which is then paired with css_put during uncharge resp. here. * * Although this might sound strange as this path is called from - * css_offline() when the referencemight have dropped down to 0 - * and shouldn't be incremented anymore (css_tryget would fail) - * we do not have other options because of the kmem allocations - * lifetime. + * css_offline() when the referencemight have dropped down to 0 and + * shouldn't be incremented anymore (css_tryget_online() would + * fail) we do not have other options because of the kmem + * allocations lifetime. */ css_get(&memcg->css); @@ -5966,9 +5832,10 @@ static void memcg_event_ptable_queue_proc(struct file *file, * Input must be in format '<event_fd> <control_fd> <args>'. * Interpretation of args is defined by control file implementation. */ -static int memcg_write_event_control(struct cgroup_subsys_state *css, - struct cftype *cft, char *buffer) +static ssize_t memcg_write_event_control(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { + struct cgroup_subsys_state *css = of_css(of); struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup_event *event; struct cgroup_subsys_state *cfile_css; @@ -5979,15 +5846,17 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css, char *endp; int ret; - efd = simple_strtoul(buffer, &endp, 10); + buf = strstrip(buf); + + efd = simple_strtoul(buf, &endp, 10); if (*endp != ' ') return -EINVAL; - buffer = endp + 1; + buf = endp + 1; - cfd = simple_strtoul(buffer, &endp, 10); + cfd = simple_strtoul(buf, &endp, 10); if ((*endp != ' ') && (*endp != '\0')) return -EINVAL; - buffer = endp + 1; + buf = endp + 1; event = kzalloc(sizeof(*event), GFP_KERNEL); if (!event) @@ -6055,8 +5924,8 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css, * automatically removed on cgroup destruction but the removal is * asynchronous, so take an extra ref on @css. */ - cfile_css = css_tryget_from_dir(cfile.file->f_dentry->d_parent, - &memory_cgrp_subsys); + cfile_css = css_tryget_online_from_dir(cfile.file->f_dentry->d_parent, + &memory_cgrp_subsys); ret = -EINVAL; if (IS_ERR(cfile_css)) goto out_put_cfile; @@ -6065,7 +5934,7 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css, goto out_put_cfile; } - ret = event->register_event(memcg, event->eventfd, buffer); + ret = event->register_event(memcg, event->eventfd, buf); if (ret) goto out_put_css; @@ -6078,7 +5947,7 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css, fdput(cfile); fdput(efile); - return 0; + return nbytes; out_put_css: css_put(css); @@ -6103,25 +5972,25 @@ static struct cftype mem_cgroup_files[] = { { .name = "max_usage_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, { .name = "limit_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_LIMIT), - .write_string = mem_cgroup_write, + .write = mem_cgroup_write, .read_u64 = mem_cgroup_read_u64, }, { .name = "soft_limit_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT), - .write_string = mem_cgroup_write, + .write = mem_cgroup_write, .read_u64 = mem_cgroup_read_u64, }, { .name = "failcnt", .private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, { @@ -6130,7 +5999,7 @@ static struct cftype mem_cgroup_files[] = { }, { .name = "force_empty", - .trigger = mem_cgroup_force_empty_write, + .write = mem_cgroup_force_empty_write, }, { .name = "use_hierarchy", @@ -6140,7 +6009,7 @@ static struct cftype mem_cgroup_files[] = { }, { .name = "cgroup.event_control", /* XXX: for compat */ - .write_string = memcg_write_event_control, + .write = memcg_write_event_control, .flags = CFTYPE_NO_PREFIX, .mode = S_IWUGO, }, @@ -6173,7 +6042,7 @@ static struct cftype mem_cgroup_files[] = { { .name = "kmem.limit_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT), - .write_string = mem_cgroup_write, + .write = mem_cgroup_write, .read_u64 = mem_cgroup_read_u64, }, { @@ -6184,13 +6053,13 @@ static struct cftype mem_cgroup_files[] = { { .name = "kmem.failcnt", .private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, { .name = "kmem.max_usage_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, #ifdef CONFIG_SLABINFO @@ -6213,19 +6082,19 @@ static struct cftype memsw_cgroup_files[] = { { .name = "memsw.max_usage_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, { .name = "memsw.limit_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), - .write_string = mem_cgroup_write, + .write = mem_cgroup_write, .read_u64 = mem_cgroup_read_u64, }, { .name = "memsw.failcnt", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, { }, /* terminate */ @@ -6403,9 +6272,9 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css)); + struct mem_cgroup *parent = mem_cgroup_from_css(css->parent); - if (css->cgroup->id > MEM_CGROUP_ID_MAX) + if (css->id > MEM_CGROUP_ID_MAX) return -ENOSPC; if (!parent) @@ -6490,7 +6359,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) css_for_each_descendant_post(iter, css) mem_cgroup_reparent_charges(mem_cgroup_from_css(iter)); - mem_cgroup_destroy_all_caches(memcg); + memcg_unregister_all_caches(memcg); vmpressure_cleanup(&memcg->vmpressure); } @@ -6500,7 +6369,7 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) /* * XXX: css_offline() would be where we should reparent all * memory to prepare the cgroup for destruction. However, - * memcg does not do css_tryget() and res_counter charging + * memcg does not do css_tryget_online() and res_counter charging * under the same RCU lock region, which means that charging * could race with offlining. Offlining only happens to * cgroups with no tasks in them but charges can show up @@ -6514,9 +6383,9 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) * lookup_swap_cgroup_id() * rcu_read_lock() * mem_cgroup_lookup() - * css_tryget() + * css_tryget_online() * rcu_read_unlock() - * disable css_tryget() + * disable css_tryget_online() * call_rcu() * offline_css() * reparent_charges() @@ -6686,16 +6555,20 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, pgoff = pte_to_pgoff(ptent); /* page is moved even if it's not RSS of this task(page-faulted). */ - page = find_get_page(mapping, pgoff); - #ifdef CONFIG_SWAP /* shmem/tmpfs may report page out on swap: account for that too. */ - if (radix_tree_exceptional_entry(page)) { - swp_entry_t swap = radix_to_swp_entry(page); - if (do_swap_account) - *entry = swap; - page = find_get_page(swap_address_space(swap), swap.val); - } + if (shmem_mapping(mapping)) { + page = find_get_entry(mapping, pgoff); + if (radix_tree_exceptional_entry(page)) { + swp_entry_t swp = radix_to_swp_entry(page); + if (do_swap_account) + *entry = swp; + 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 return page; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 35ef28acf137..cd8989c1027e 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -204,9 +204,9 @@ 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 @@ -380,20 +380,51 @@ 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; @@ -408,16 +439,17 @@ 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); @@ -428,7 +460,7 @@ 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; @@ -438,10 +470,10 @@ 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) { /* @@ -451,8 +483,8 @@ 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); @@ -465,7 +497,8 @@ 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; @@ -476,9 +509,9 @@ 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); } @@ -963,7 +996,7 @@ 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) @@ -1081,15 +1114,16 @@ 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); @@ -1131,11 +1165,6 @@ int memory_failure(unsigned long pfn, int trapno, int flags) } } - /* - * Lock the page and wait for writeback to finish. - * It's very difficult to mess with pages currently under IO - * and in many cases impossible, so we just avoid it here. - */ lock_page(hpage); /* @@ -1152,6 +1181,8 @@ 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; } @@ -1183,6 +1214,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags) if (PageHuge(p)) set_page_hwpoison_huge_page(hpage); + /* + * It's very difficult to mess with pages currently under IO + * and in many cases impossible, so we just avoid it here. + */ wait_on_page_writeback(p); /* @@ -1295,7 +1330,7 @@ static void memory_failure_work_func(struct work_struct *work) unsigned long proc_flags; int gotten; - mf_cpu = &__get_cpu_var(memory_failure_cpu); + mf_cpu = this_cpu_ptr(&memory_failure_cpu); for (;;) { spin_lock_irqsave(&mf_cpu->lock, proc_flags); gotten = kfifo_get(&mf_cpu->fifo, &entry); @@ -1500,7 +1535,7 @@ 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", @@ -1581,7 +1616,7 @@ 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) { if (!list_empty(&pagelist)) { @@ -1661,11 +1696,7 @@ int soft_offline_page(struct page *page, int flags) } } - /* - * The lock_memory_hotplug prevents a race with memory hotplug. - * This is a big hammer, a better would be nicer. - */ - lock_memory_hotplug(); + get_online_mems(); /* * Isolate the page, so that it doesn't get reallocated if it @@ -1676,7 +1707,7 @@ int soft_offline_page(struct page *page, int flags) set_migratetype_isolate(page, true); ret = get_any_page(page, pfn, flags); - unlock_memory_hotplug(); + put_online_mems(); if (ret > 0) { /* for in-use pages */ if (PageHuge(page)) ret = soft_offline_huge_page(page, flags); diff --git a/mm/memory.c b/mm/memory.c index 037b812a9531..d67fd9fcf1f2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -698,11 +698,6 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } -static inline bool is_cow_mapping(vm_flags_t flags) -{ - return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; -} - /* * vm_normal_page -- This function gets the "struct page" associated with a pte. * @@ -756,7 +751,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn = pte_pfn(pte); if (HAVE_PTE_SPECIAL) { - if (likely(!pte_special(pte))) + if (likely(!pte_special(pte) || pte_numa(pte))) goto check_pfn; if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; @@ -782,14 +777,15 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, } } - if (is_zero_pfn(pfn)) - return NULL; check_pfn: if (unlikely(pfn > highest_memmap_pfn)) { print_bad_pte(vma, addr, pte, NULL); return NULL; } + if (is_zero_pfn(pfn)) + return NULL; + /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. @@ -1457,646 +1453,6 @@ int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, } EXPORT_SYMBOL_GPL(zap_vma_ptes); -/** - * follow_page_mask - look up a page descriptor from a user-virtual address - * @vma: vm_area_struct mapping @address - * @address: virtual address to look up - * @flags: flags modifying lookup behaviour - * @page_mask: on output, *page_mask is set according to the size of the page - * - * @flags can have FOLL_ flags set, defined in <linux/mm.h> - * - * Returns the mapped (struct page *), %NULL if no mapping exists, or - * an error pointer if there is a mapping to something not represented - * by a page descriptor (see also vm_normal_page()). - */ -struct page *follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int flags, - unsigned int *page_mask) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *ptep, pte; - spinlock_t *ptl; - struct page *page; - struct mm_struct *mm = vma->vm_mm; - - *page_mask = 0; - - page = follow_huge_addr(mm, address, flags & FOLL_WRITE); - if (!IS_ERR(page)) { - BUG_ON(flags & FOLL_GET); - goto out; - } - - page = NULL; - pgd = pgd_offset(mm, address); - if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - goto no_page_table; - - pud = pud_offset(pgd, address); - if (pud_none(*pud)) - goto no_page_table; - if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { - if (flags & FOLL_GET) - goto out; - page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE); - goto out; - } - if (unlikely(pud_bad(*pud))) - goto no_page_table; - - pmd = pmd_offset(pud, address); - if (pmd_none(*pmd)) - goto no_page_table; - if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) { - page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); - if (flags & FOLL_GET) { - /* - * Refcount on tail pages are not well-defined and - * shouldn't be taken. The caller should handle a NULL - * return when trying to follow tail pages. - */ - if (PageHead(page)) - get_page(page); - else { - page = NULL; - goto out; - } - } - goto out; - } - if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) - goto no_page_table; - if (pmd_trans_huge(*pmd)) { - if (flags & FOLL_SPLIT) { - split_huge_page_pmd(vma, address, pmd); - goto split_fallthrough; - } - ptl = pmd_lock(mm, pmd); - if (likely(pmd_trans_huge(*pmd))) { - if (unlikely(pmd_trans_splitting(*pmd))) { - spin_unlock(ptl); - wait_split_huge_page(vma->anon_vma, pmd); - } else { - page = follow_trans_huge_pmd(vma, address, - pmd, flags); - spin_unlock(ptl); - *page_mask = HPAGE_PMD_NR - 1; - goto out; - } - } else - spin_unlock(ptl); - /* fall through */ - } -split_fallthrough: - if (unlikely(pmd_bad(*pmd))) - goto no_page_table; - - ptep = pte_offset_map_lock(mm, pmd, address, &ptl); - - pte = *ptep; - if (!pte_present(pte)) { - swp_entry_t entry; - /* - * KSM's break_ksm() relies upon recognizing a ksm page - * even while it is being migrated, so for that case we - * need migration_entry_wait(). - */ - if (likely(!(flags & FOLL_MIGRATION))) - goto no_page; - if (pte_none(pte) || pte_file(pte)) - goto no_page; - entry = pte_to_swp_entry(pte); - if (!is_migration_entry(entry)) - goto no_page; - pte_unmap_unlock(ptep, ptl); - migration_entry_wait(mm, pmd, address); - goto split_fallthrough; - } - if ((flags & FOLL_NUMA) && pte_numa(pte)) - goto no_page; - if ((flags & FOLL_WRITE) && !pte_write(pte)) - goto unlock; - - page = vm_normal_page(vma, address, pte); - if (unlikely(!page)) { - if ((flags & FOLL_DUMP) || - !is_zero_pfn(pte_pfn(pte))) - goto bad_page; - page = pte_page(pte); - } - - if (flags & FOLL_GET) - get_page_foll(page); - if (flags & FOLL_TOUCH) { - if ((flags & FOLL_WRITE) && - !pte_dirty(pte) && !PageDirty(page)) - set_page_dirty(page); - /* - * pte_mkyoung() would be more correct here, but atomic care - * is needed to avoid losing the dirty bit: it is easier to use - * mark_page_accessed(). - */ - mark_page_accessed(page); - } - if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { - /* - * The preliminary mapping check is mainly to avoid the - * pointless overhead of lock_page on the ZERO_PAGE - * which might bounce very badly if there is contention. - * - * If the page is already locked, we don't need to - * handle it now - vmscan will handle it later if and - * when it attempts to reclaim the page. - */ - if (page->mapping && trylock_page(page)) { - lru_add_drain(); /* push cached pages to LRU */ - /* - * Because we lock page here, and migration is - * blocked by the pte's page reference, and we - * know the page is still mapped, we don't even - * need to check for file-cache page truncation. - */ - mlock_vma_page(page); - unlock_page(page); - } - } -unlock: - pte_unmap_unlock(ptep, ptl); -out: - return page; - -bad_page: - pte_unmap_unlock(ptep, ptl); - return ERR_PTR(-EFAULT); - -no_page: - pte_unmap_unlock(ptep, ptl); - if (!pte_none(pte)) - return page; - -no_page_table: - /* - * When core dumping an enormous anonymous area that nobody - * has touched so far, we don't want to allocate unnecessary pages or - * page tables. Return error instead of NULL to skip handle_mm_fault, - * then get_dump_page() will return NULL to leave a hole in the dump. - * But we can only make this optimization where a hole would surely - * be zero-filled if handle_mm_fault() actually did handle it. - */ - if ((flags & FOLL_DUMP) && - (!vma->vm_ops || !vma->vm_ops->fault)) - return ERR_PTR(-EFAULT); - return page; -} - -static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr) -{ - return stack_guard_page_start(vma, addr) || - stack_guard_page_end(vma, addr+PAGE_SIZE); -} - -/** - * __get_user_pages() - pin user pages in memory - * @tsk: task_struct of target task - * @mm: mm_struct of target mm - * @start: starting user address - * @nr_pages: number of pages from start to pin - * @gup_flags: flags modifying pin behaviour - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. Or NULL, if caller - * only intends to ensure the pages are faulted in. - * @vmas: array of pointers to vmas corresponding to each page. - * Or NULL if the caller does not require them. - * @nonblocking: whether waiting for disk IO or mmap_sem contention - * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. Each page returned must be released - * with a put_page() call when it is finished with. vmas will only - * remain valid while mmap_sem is held. - * - * Must be called with mmap_sem held for read or write. - * - * __get_user_pages walks a process's page tables and takes a reference to - * each struct page that each user address corresponds to at a given - * instant. That is, it takes the page that would be accessed if a user - * thread accesses the given user virtual address at that instant. - * - * This does not guarantee that the page exists in the user mappings when - * __get_user_pages returns, and there may even be a completely different - * page there in some cases (eg. if mmapped pagecache has been invalidated - * and subsequently re faulted). However it does guarantee that the page - * won't be freed completely. And mostly callers simply care that the page - * contains data that was valid *at some point in time*. Typically, an IO - * or similar operation cannot guarantee anything stronger anyway because - * locks can't be held over the syscall boundary. - * - * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If - * the page is written to, set_page_dirty (or set_page_dirty_lock, as - * appropriate) must be called after the page is finished with, and - * before put_page is called. - * - * If @nonblocking != NULL, __get_user_pages will not wait for disk IO - * or mmap_sem contention, and if waiting is needed to pin all pages, - * *@nonblocking will be set to 0. - * - * In most cases, get_user_pages or get_user_pages_fast should be used - * instead of __get_user_pages. __get_user_pages should be used only if - * you need some special @gup_flags. - */ -long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas, int *nonblocking) -{ - long i; - unsigned long vm_flags; - unsigned int page_mask; - - if (!nr_pages) - return 0; - - VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET)); - - /* - * If FOLL_FORCE and FOLL_NUMA are both set, handle_mm_fault - * would be called on PROT_NONE ranges. We must never invoke - * handle_mm_fault on PROT_NONE ranges or the NUMA hinting - * page faults would unprotect the PROT_NONE ranges if - * _PAGE_NUMA and _PAGE_PROTNONE are sharing the same pte/pmd - * bitflag. So to avoid that, don't set FOLL_NUMA if - * FOLL_FORCE is set. - */ - if (!(gup_flags & FOLL_FORCE)) - gup_flags |= FOLL_NUMA; - - i = 0; - - do { - struct vm_area_struct *vma; - - vma = find_extend_vma(mm, start); - if (!vma && in_gate_area(mm, start)) { - unsigned long pg = start & PAGE_MASK; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - /* user gate pages are read-only */ - if (gup_flags & FOLL_WRITE) - goto efault; - if (pg > TASK_SIZE) - pgd = pgd_offset_k(pg); - else - pgd = pgd_offset_gate(mm, pg); - BUG_ON(pgd_none(*pgd)); - pud = pud_offset(pgd, pg); - BUG_ON(pud_none(*pud)); - pmd = pmd_offset(pud, pg); - if (pmd_none(*pmd)) - goto efault; - VM_BUG_ON(pmd_trans_huge(*pmd)); - pte = pte_offset_map(pmd, pg); - if (pte_none(*pte)) { - pte_unmap(pte); - goto efault; - } - vma = get_gate_vma(mm); - if (pages) { - struct page *page; - - page = vm_normal_page(vma, start, *pte); - if (!page) { - if (!(gup_flags & FOLL_DUMP) && - is_zero_pfn(pte_pfn(*pte))) - page = pte_page(*pte); - else { - pte_unmap(pte); - goto efault; - } - } - pages[i] = page; - get_page(page); - } - pte_unmap(pte); - page_mask = 0; - goto next_page; - } - - if (!vma) - goto efault; - vm_flags = vma->vm_flags; - if (vm_flags & (VM_IO | VM_PFNMAP)) - goto efault; - - if (gup_flags & FOLL_WRITE) { - if (!(vm_flags & VM_WRITE)) { - if (!(gup_flags & FOLL_FORCE)) - goto efault; - /* - * We used to let the write,force case do COW - * in a VM_MAYWRITE VM_SHARED !VM_WRITE vma, so - * ptrace could set a breakpoint in a read-only - * mapping of an executable, without corrupting - * the file (yet only when that file had been - * opened for writing!). Anon pages in shared - * mappings are surprising: now just reject it. - */ - if (!is_cow_mapping(vm_flags)) { - WARN_ON_ONCE(vm_flags & VM_MAYWRITE); - goto efault; - } - } - } else { - if (!(vm_flags & VM_READ)) { - if (!(gup_flags & FOLL_FORCE)) - goto efault; - /* - * Is there actually any vma we can reach here - * which does not have VM_MAYREAD set? - */ - if (!(vm_flags & VM_MAYREAD)) - goto efault; - } - } - - if (is_vm_hugetlb_page(vma)) { - i = follow_hugetlb_page(mm, vma, pages, vmas, - &start, &nr_pages, i, gup_flags); - continue; - } - - do { - struct page *page; - unsigned int foll_flags = gup_flags; - unsigned int page_increm; - - /* - * If we have a pending SIGKILL, don't keep faulting - * pages and potentially allocating memory. - */ - if (unlikely(fatal_signal_pending(current))) - return i ? i : -ERESTARTSYS; - - cond_resched(); - while (!(page = follow_page_mask(vma, start, - foll_flags, &page_mask))) { - int ret; - unsigned int fault_flags = 0; - - /* For mlock, just skip the stack guard page. */ - if (foll_flags & FOLL_MLOCK) { - if (stack_guard_page(vma, start)) - goto next_page; - } - if (foll_flags & FOLL_WRITE) - fault_flags |= FAULT_FLAG_WRITE; - if (nonblocking) - fault_flags |= FAULT_FLAG_ALLOW_RETRY; - if (foll_flags & FOLL_NOWAIT) - fault_flags |= (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT); - - ret = handle_mm_fault(mm, vma, start, - fault_flags); - - if (ret & VM_FAULT_ERROR) { - if (ret & VM_FAULT_OOM) - return i ? i : -ENOMEM; - if (ret & (VM_FAULT_HWPOISON | - VM_FAULT_HWPOISON_LARGE)) { - if (i) - return i; - else if (gup_flags & FOLL_HWPOISON) - return -EHWPOISON; - else - return -EFAULT; - } - if (ret & VM_FAULT_SIGBUS) - goto efault; - BUG(); - } - - if (tsk) { - if (ret & VM_FAULT_MAJOR) - tsk->maj_flt++; - else - tsk->min_flt++; - } - - if (ret & VM_FAULT_RETRY) { - if (nonblocking) - *nonblocking = 0; - return i; - } - - /* - * The VM_FAULT_WRITE bit tells us that - * do_wp_page has broken COW when necessary, - * even if maybe_mkwrite decided not to set - * pte_write. We can thus safely do subsequent - * page lookups as if they were reads. But only - * do so when looping for pte_write is futile: - * in some cases userspace may also be wanting - * to write to the gotten user page, which a - * read fault here might prevent (a readonly - * page might get reCOWed by userspace write). - */ - if ((ret & VM_FAULT_WRITE) && - !(vma->vm_flags & VM_WRITE)) - foll_flags &= ~FOLL_WRITE; - - cond_resched(); - } - if (IS_ERR(page)) - return i ? i : PTR_ERR(page); - if (pages) { - pages[i] = page; - - flush_anon_page(vma, page, start); - flush_dcache_page(page); - page_mask = 0; - } -next_page: - if (vmas) { - vmas[i] = vma; - page_mask = 0; - } - page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask); - if (page_increm > nr_pages) - page_increm = nr_pages; - i += page_increm; - start += page_increm * PAGE_SIZE; - nr_pages -= page_increm; - } while (nr_pages && start < vma->vm_end); - } while (nr_pages); - return i; -efault: - return i ? : -EFAULT; -} -EXPORT_SYMBOL(__get_user_pages); - -/* - * fixup_user_fault() - manually resolve a user page fault - * @tsk: the task_struct to use for page fault accounting, or - * NULL if faults are not to be recorded. - * @mm: mm_struct of target mm - * @address: user address - * @fault_flags:flags to pass down to handle_mm_fault() - * - * This is meant to be called in the specific scenario where for locking reasons - * we try to access user memory in atomic context (within a pagefault_disable() - * section), this returns -EFAULT, and we want to resolve the user fault before - * trying again. - * - * Typically this is meant to be used by the futex code. - * - * The main difference with get_user_pages() is that this function will - * unconditionally call handle_mm_fault() which will in turn perform all the - * necessary SW fixup of the dirty and young bits in the PTE, while - * handle_mm_fault() only guarantees to update these in the struct page. - * - * This is important for some architectures where those bits also gate the - * access permission to the page because they are maintained in software. On - * such architectures, gup() will not be enough to make a subsequent access - * succeed. - * - * This should be called with the mm_sem held for read. - */ -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) - return -ENOMEM; - if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) - return -EHWPOISON; - if (ret & VM_FAULT_SIGBUS) - return -EFAULT; - BUG(); - } - if (tsk) { - if (ret & VM_FAULT_MAJOR) - tsk->maj_flt++; - else - tsk->min_flt++; - } - return 0; -} - -/* - * get_user_pages() - pin user pages in memory - * @tsk: the task_struct to use for page fault accounting, or - * NULL if faults are not to be recorded. - * @mm: mm_struct of target mm - * @start: starting user address - * @nr_pages: number of pages from start to pin - * @write: whether pages will be written to by the caller - * @force: whether to force access even when user mapping is currently - * protected (but never forces write access to shared mapping). - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. Or NULL, if caller - * only intends to ensure the pages are faulted in. - * @vmas: array of pointers to vmas corresponding to each page. - * Or NULL if the caller does not require them. - * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. Each page returned must be released - * with a put_page() call when it is finished with. vmas will only - * remain valid while mmap_sem is held. - * - * Must be called with mmap_sem held for read or write. - * - * get_user_pages walks a process's page tables and takes a reference to - * each struct page that each user address corresponds to at a given - * instant. That is, it takes the page that would be accessed if a user - * thread accesses the given user virtual address at that instant. - * - * This does not guarantee that the page exists in the user mappings when - * get_user_pages returns, and there may even be a completely different - * page there in some cases (eg. if mmapped pagecache has been invalidated - * and subsequently re faulted). However it does guarantee that the page - * won't be freed completely. And mostly callers simply care that the page - * contains data that was valid *at some point in time*. Typically, an IO - * or similar operation cannot guarantee anything stronger anyway because - * locks can't be held over the syscall boundary. - * - * If write=0, the page must not be written to. If the page is written to, - * set_page_dirty (or set_page_dirty_lock, as appropriate) must be called - * after the page is finished with, and before put_page is called. - * - * get_user_pages is typically used for fewer-copy IO operations, to get a - * handle on the memory by some means other than accesses via the user virtual - * addresses. The pages may be submitted for DMA to devices or accessed via - * their kernel linear mapping (via the kmap APIs). Care should be taken to - * use the correct cache flushing APIs. - * - * See also get_user_pages_fast, for performance critical applications. - */ -long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, int write, - int force, struct page **pages, struct vm_area_struct **vmas) -{ - int flags = FOLL_TOUCH; - - if (pages) - flags |= FOLL_GET; - if (write) - flags |= FOLL_WRITE; - if (force) - flags |= FOLL_FORCE; - - return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas, - NULL); -} -EXPORT_SYMBOL(get_user_pages); - -/** - * get_dump_page() - pin user page in memory while writing it to core dump - * @addr: user address - * - * Returns struct page pointer of user page pinned for dump, - * to be freed afterwards by page_cache_release() or put_page(). - * - * Returns NULL on any kind of failure - a hole must then be inserted into - * the corefile, to preserve alignment with its headers; and also returns - * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - - * allowing a hole to be left in the corefile to save diskspace. - * - * Called without mmap_sem, but after all other threads have been killed. - */ -#ifdef CONFIG_ELF_CORE -struct page *get_dump_page(unsigned long addr) -{ - struct vm_area_struct *vma; - struct page *page; - - if (__get_user_pages(current, current->mm, addr, 1, - FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma, - NULL) < 1) - return NULL; - flush_cache_page(vma, addr, page_to_pfn(page)); - return page; -} -#endif /* CONFIG_ELF_CORE */ - pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { @@ -3402,65 +2758,76 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address, update_mmu_cache(vma, address, pte); } -#define FAULT_AROUND_ORDER 4 +static unsigned long fault_around_bytes = 65536; -#ifdef CONFIG_DEBUG_FS -static unsigned int fault_around_order = FAULT_AROUND_ORDER; +/* + * fault_around_pages() and fault_around_mask() round down fault_around_bytes + * to nearest page order. It's what do_fault_around() expects to see. + */ +static inline unsigned long fault_around_pages(void) +{ + return rounddown_pow_of_two(fault_around_bytes) / PAGE_SIZE; +} + +static inline unsigned long fault_around_mask(void) +{ + return ~(rounddown_pow_of_two(fault_around_bytes) - 1) & PAGE_MASK; +} -static int fault_around_order_get(void *data, u64 *val) + +#ifdef CONFIG_DEBUG_FS +static int fault_around_bytes_get(void *data, u64 *val) { - *val = fault_around_order; + *val = fault_around_bytes; return 0; } -static int fault_around_order_set(void *data, u64 val) +static int fault_around_bytes_set(void *data, u64 val) { - BUILD_BUG_ON((1UL << FAULT_AROUND_ORDER) > PTRS_PER_PTE); - if (1UL << val > PTRS_PER_PTE) + if (val / PAGE_SIZE > PTRS_PER_PTE) return -EINVAL; - fault_around_order = val; + fault_around_bytes = val; return 0; } -DEFINE_SIMPLE_ATTRIBUTE(fault_around_order_fops, - fault_around_order_get, fault_around_order_set, "%llu\n"); +DEFINE_SIMPLE_ATTRIBUTE(fault_around_bytes_fops, + fault_around_bytes_get, fault_around_bytes_set, "%llu\n"); static int __init fault_around_debugfs(void) { void *ret; - ret = debugfs_create_file("fault_around_order", 0644, NULL, NULL, - &fault_around_order_fops); + ret = debugfs_create_file("fault_around_bytes", 0644, NULL, NULL, + &fault_around_bytes_fops); if (!ret) - pr_warn("Failed to create fault_around_order in debugfs"); + pr_warn("Failed to create fault_around_bytes in debugfs"); return 0; } late_initcall(fault_around_debugfs); - -static inline unsigned long fault_around_pages(void) -{ - return 1UL << fault_around_order; -} - -static inline unsigned long fault_around_mask(void) -{ - return ~((1UL << (PAGE_SHIFT + fault_around_order)) - 1); -} -#else -static inline unsigned long fault_around_pages(void) -{ - unsigned long nr_pages; - - nr_pages = 1UL << FAULT_AROUND_ORDER; - BUILD_BUG_ON(nr_pages > PTRS_PER_PTE); - return nr_pages; -} - -static inline unsigned long fault_around_mask(void) -{ - return ~((1UL << (PAGE_SHIFT + FAULT_AROUND_ORDER)) - 1); -} #endif +/* + * do_fault_around() tries to map few pages around the fault address. The hope + * is that the pages will be needed soon and this will lower the number of + * faults to handle. + * + * It uses vm_ops->map_pages() to map the pages, which skips the page if it's + * not ready to be mapped: not up-to-date, locked, etc. + * + * This function is called with the page table lock taken. In the split ptlock + * case the page table lock only protects only those entries which belong to + * the page table corresponding to the fault address. + * + * This function doesn't cross the VMA boundaries, in order to call map_pages() + * only once. + * + * fault_around_pages() defines how many pages we'll try to map. + * do_fault_around() expects it to return a power of two less than or equal to + * PTRS_PER_PTE. + * + * The virtual address of the area that we map is naturally aligned to the + * fault_around_pages() value (and therefore to page order). This way it's + * easier to guarantee that we don't cross page table boundaries. + */ static void do_fault_around(struct vm_area_struct *vma, unsigned long address, pte_t *pte, pgoff_t pgoff, unsigned int flags) { @@ -3476,7 +2843,7 @@ static void do_fault_around(struct vm_area_struct *vma, unsigned long address, /* * max_pgoff is either end of page table or end of vma - * or fault_around_pages() from pgoff, depending what is neast. + * or fault_around_pages() from pgoff, depending what is nearest. */ max_pgoff = pgoff - ((start_addr >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + PTRS_PER_PTE - 1; @@ -3515,7 +2882,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, * if page by the offset is not ready to be mapped (cold cache or * something). */ - if (vma->vm_ops->map_pages) { + if (vma->vm_ops->map_pages && fault_around_pages() > 1) { pte = pte_offset_map_lock(mm, pmd, address, &ptl); do_fault_around(vma, address, pte, pgoff, flags); if (!pte_same(*pte, orig_pte)) @@ -3920,9 +3287,6 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, } } - /* THP should already have been handled */ - BUG_ON(pmd_numa(*pmd)); - /* * Use __pte_alloc instead of pte_alloc_map, because we can't * run pte_offset_map on the pmd, if an huge pmd could diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a650db29606f..469bbf505f85 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -46,19 +46,84 @@ static void generic_online_page(struct page *page); static online_page_callback_t online_page_callback = generic_online_page; +static DEFINE_MUTEX(online_page_callback_lock); -DEFINE_MUTEX(mem_hotplug_mutex); +/* The same as the cpu_hotplug lock, but for memory hotplug. */ +static struct { + struct task_struct *active_writer; + struct mutex lock; /* Synchronizes accesses to refcount, */ + /* + * Also blocks the new readers during + * an ongoing mem hotplug operation. + */ + int refcount; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} mem_hotplug = { + .active_writer = NULL, + .lock = __MUTEX_INITIALIZER(mem_hotplug.lock), + .refcount = 0, +#ifdef CONFIG_DEBUG_LOCK_ALLOC + .dep_map = {.name = "mem_hotplug.lock" }, +#endif +}; + +/* Lockdep annotations for get/put_online_mems() and mem_hotplug_begin/end() */ +#define memhp_lock_acquire_read() lock_map_acquire_read(&mem_hotplug.dep_map) +#define memhp_lock_acquire() lock_map_acquire(&mem_hotplug.dep_map) +#define memhp_lock_release() lock_map_release(&mem_hotplug.dep_map) + +void get_online_mems(void) +{ + might_sleep(); + if (mem_hotplug.active_writer == current) + return; + memhp_lock_acquire_read(); + mutex_lock(&mem_hotplug.lock); + mem_hotplug.refcount++; + mutex_unlock(&mem_hotplug.lock); + +} -void lock_memory_hotplug(void) +void put_online_mems(void) { - mutex_lock(&mem_hotplug_mutex); + if (mem_hotplug.active_writer == current) + return; + mutex_lock(&mem_hotplug.lock); + + if (WARN_ON(!mem_hotplug.refcount)) + mem_hotplug.refcount++; /* try to fix things up */ + + if (!--mem_hotplug.refcount && unlikely(mem_hotplug.active_writer)) + wake_up_process(mem_hotplug.active_writer); + mutex_unlock(&mem_hotplug.lock); + memhp_lock_release(); + } -void unlock_memory_hotplug(void) +static void mem_hotplug_begin(void) { - mutex_unlock(&mem_hotplug_mutex); + mem_hotplug.active_writer = current; + + memhp_lock_acquire(); + for (;;) { + mutex_lock(&mem_hotplug.lock); + if (likely(!mem_hotplug.refcount)) + break; + __set_current_state(TASK_UNINTERRUPTIBLE); + mutex_unlock(&mem_hotplug.lock); + schedule(); + } } +static void mem_hotplug_done(void) +{ + mem_hotplug.active_writer = NULL; + mutex_unlock(&mem_hotplug.lock); + memhp_lock_release(); +} /* add this memory to iomem resource */ static struct resource *register_memory_resource(u64 start, u64 size) @@ -727,14 +792,16 @@ int set_online_page_callback(online_page_callback_t callback) { int rc = -EINVAL; - lock_memory_hotplug(); + get_online_mems(); + mutex_lock(&online_page_callback_lock); if (online_page_callback == generic_online_page) { online_page_callback = callback; rc = 0; } - unlock_memory_hotplug(); + mutex_unlock(&online_page_callback_lock); + put_online_mems(); return rc; } @@ -744,14 +811,16 @@ int restore_online_page_callback(online_page_callback_t callback) { int rc = -EINVAL; - lock_memory_hotplug(); + get_online_mems(); + mutex_lock(&online_page_callback_lock); if (online_page_callback == callback) { online_page_callback = generic_online_page; rc = 0; } - unlock_memory_hotplug(); + mutex_unlock(&online_page_callback_lock); + put_online_mems(); return rc; } @@ -899,7 +968,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ int ret; struct memory_notify arg; - lock_memory_hotplug(); + mem_hotplug_begin(); /* * This doesn't need a lock to do pfn_to_page(). * The section can't be removed here because of the @@ -907,23 +976,18 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ */ zone = page_zone(pfn_to_page(pfn)); + ret = -EINVAL; if ((zone_idx(zone) > ZONE_NORMAL || online_type == ONLINE_MOVABLE) && - !can_online_high_movable(zone)) { - unlock_memory_hotplug(); - return -EINVAL; - } + !can_online_high_movable(zone)) + goto out; if (online_type == ONLINE_KERNEL && zone_idx(zone) == ZONE_MOVABLE) { - if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) { - unlock_memory_hotplug(); - return -EINVAL; - } + if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) + goto out; } if (online_type == ONLINE_MOVABLE && zone_idx(zone) == ZONE_MOVABLE - 1) { - if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages)) { - unlock_memory_hotplug(); - return -EINVAL; - } + if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages)) + goto out; } /* Previous code may changed the zone of the pfn range */ @@ -939,8 +1003,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ ret = notifier_to_errno(ret); if (ret) { memory_notify(MEM_CANCEL_ONLINE, &arg); - unlock_memory_hotplug(); - return ret; + goto out; } /* * If this zone is not populated, then it is not in zonelist. @@ -964,8 +1027,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); - unlock_memory_hotplug(); - return ret; + goto out; } zone->present_pages += onlined_pages; @@ -995,9 +1057,9 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ if (onlined_pages) memory_notify(MEM_ONLINE, &arg); - unlock_memory_hotplug(); - - return 0; +out: + mem_hotplug_done(); + return ret; } #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ @@ -1007,7 +1069,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) struct pglist_data *pgdat; unsigned long zones_size[MAX_NR_ZONES] = {0}; unsigned long zholes_size[MAX_NR_ZONES] = {0}; - unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long start_pfn = PFN_DOWN(start); pgdat = NODE_DATA(nid); if (!pgdat) { @@ -1055,7 +1117,7 @@ int try_online_node(int nid) if (node_online(nid)) return 0; - lock_memory_hotplug(); + mem_hotplug_begin(); pgdat = hotadd_new_pgdat(nid, 0); if (!pgdat) { pr_err("Cannot online node %d due to NULL pgdat\n", nid); @@ -1073,13 +1135,13 @@ int try_online_node(int nid) } out: - unlock_memory_hotplug(); + mem_hotplug_done(); return ret; } static int check_hotplug_memory_range(u64 start, u64 size) { - u64 start_pfn = start >> PAGE_SHIFT; + u64 start_pfn = PFN_DOWN(start); u64 nr_pages = size >> PAGE_SHIFT; /* Memory range must be aligned with section */ @@ -1117,7 +1179,7 @@ int __ref add_memory(int nid, u64 start, u64 size) new_pgdat = !p; } - lock_memory_hotplug(); + mem_hotplug_begin(); new_node = !node_online(nid); if (new_node) { @@ -1158,7 +1220,7 @@ error: release_memory_resource(res); out: - unlock_memory_hotplug(); + mem_hotplug_done(); return ret; } EXPORT_SYMBOL_GPL(add_memory); @@ -1332,7 +1394,7 @@ 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); @@ -1565,7 +1627,7 @@ static int __ref __offline_pages(unsigned long start_pfn, if (!test_pages_in_a_zone(start_pfn, end_pfn)) return -EINVAL; - lock_memory_hotplug(); + mem_hotplug_begin(); zone = page_zone(pfn_to_page(start_pfn)); node = zone_to_nid(zone); @@ -1672,7 +1734,7 @@ repeat: writeback_set_ratelimit(); memory_notify(MEM_OFFLINE, &arg); - unlock_memory_hotplug(); + mem_hotplug_done(); return 0; failed_removal: @@ -1684,7 +1746,7 @@ failed_removal: undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); out: - unlock_memory_hotplug(); + mem_hotplug_done(); return ret; } @@ -1888,7 +1950,7 @@ void __ref remove_memory(int nid, u64 start, u64 size) BUG_ON(check_hotplug_memory_range(start, size)); - lock_memory_hotplug(); + mem_hotplug_begin(); /* * All memory blocks must be offlined before removing memory. Check @@ -1897,10 +1959,8 @@ void __ref remove_memory(int nid, u64 start, u64 size) */ ret = walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL, check_memblock_offlined_cb); - if (ret) { - unlock_memory_hotplug(); + if (ret) BUG(); - } /* remove memmap entry */ firmware_map_remove(start, start + size, "System RAM"); @@ -1909,7 +1969,7 @@ void __ref remove_memory(int nid, u64 start, u64 size) try_offline_node(nid); - unlock_memory_hotplug(); + mem_hotplug_done(); } EXPORT_SYMBOL_GPL(remove_memory); #endif /* CONFIG_MEMORY_HOTREMOVE */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 78e1472933ea..284974230459 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -65,6 +65,8 @@ kernel is not always grateful with that. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/mempolicy.h> #include <linux/mm.h> #include <linux/highmem.h> @@ -91,6 +93,7 @@ #include <linux/ctype.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> +#include <linux/printk.h> #include <asm/tlbflush.h> #include <asm/uaccess.h> @@ -526,9 +529,13 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma, int nid; struct page *page; spinlock_t *ptl; + pte_t entry; ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd); - 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; @@ -1028,7 +1035,7 @@ 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); @@ -1277,7 +1284,7 @@ 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, + NULL, (unsigned long)vma, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) putback_movable_pages(&pagelist); @@ -1362,7 +1369,7 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, - unsigned long, mode, unsigned long __user *, nmask, + unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned, flags) { nodemask_t nodes; @@ -1383,7 +1390,7 @@ SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, } /* Set the process memory policy */ -SYSCALL_DEFINE3(set_mempolicy, int, mode, unsigned long __user *, nmask, +SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { int err; @@ -1606,9 +1613,9 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, /* * get_vma_policy(@task, @vma, @addr) - * @task - task for fallback if vma policy == default - * @vma - virtual memory area whose policy is sought - * @addr - address in @vma for shared policy lookup + * @task: task for fallback if vma policy == default + * @vma: virtual memory area whose policy is sought + * @addr: address in @vma for shared policy lookup * * Returns effective policy for a VMA at specified address. * Falls back to @task or system default policy, as necessary. @@ -1854,11 +1861,11 @@ int node_random(const nodemask_t *maskp) #ifdef CONFIG_HUGETLBFS /* * huge_zonelist(@vma, @addr, @gfp_flags, @mpol) - * @vma = virtual memory area whose policy is sought - * @addr = address in @vma for shared policy lookup and interleave policy - * @gfp_flags = for requested zone - * @mpol = pointer to mempolicy pointer for reference counted mempolicy - * @nodemask = pointer to nodemask pointer for MPOL_BIND nodemask + * @vma: virtual memory area whose policy is sought + * @addr: address in @vma for shared policy lookup and interleave policy + * @gfp_flags: for requested zone + * @mpol: pointer to mempolicy pointer for reference counted mempolicy + * @nodemask: pointer to nodemask pointer for MPOL_BIND nodemask * * Returns a zonelist suitable for a huge page allocation and a pointer * to the struct mempolicy for conditional unref after allocation. @@ -2270,9 +2277,9 @@ static void sp_free(struct sp_node *n) /** * mpol_misplaced - check whether current page node is valid in policy * - * @page - page to be checked - * @vma - vm area where page mapped - * @addr - virtual address where page mapped + * @page: page to be checked + * @vma: vm area where page mapped + * @addr: virtual address where page mapped * * Lookup current policy node id for vma,addr and "compare to" page's * node id. @@ -2645,7 +2652,7 @@ void __init numa_policy_init(void) node_set(prefer, interleave_nodes); if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) - printk("numa_policy_init: interleaving failed\n"); + pr_err("%s: interleaving failed\n", __func__); check_numabalancing_enable(); } diff --git a/mm/mempool.c b/mm/mempool.c index 905434f18c97..e209c98c7203 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -10,6 +10,7 @@ #include <linux/mm.h> #include <linux/slab.h> +#include <linux/kmemleak.h> #include <linux/export.h> #include <linux/mempool.h> #include <linux/blkdev.h> @@ -192,6 +193,7 @@ EXPORT_SYMBOL(mempool_resize); * returns NULL. Note that due to preallocation, this function * *never* fails when called from process contexts. (it might * fail if called from an IRQ context.) + * Note: using __GFP_ZERO is not supported. */ void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask) { @@ -200,6 +202,7 @@ void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask) wait_queue_t wait; gfp_t gfp_temp; + VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO); might_sleep_if(gfp_mask & __GFP_WAIT); gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */ @@ -220,6 +223,11 @@ repeat_alloc: spin_unlock_irqrestore(&pool->lock, flags); /* paired with rmb in mempool_free(), read comment there */ smp_wmb(); + /* + * Update the allocation stack trace as this is more useful + * for debugging. + */ + kmemleak_update_trace(element); return element; } diff --git a/mm/migrate.c b/mm/migrate.c index bed48809e5d0..63f0cd559999 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -938,8 +938,9 @@ 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; @@ -983,11 +984,17 @@ 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) + put_new_page(newpage, private); + else + putback_lru_page(newpage); + if (result) { if (rc) *result = rc; @@ -1016,8 +1023,9 @@ 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; @@ -1031,7 +1039,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, * tables or check whether the hugepage is pmd-based or not before * kicking migration. */ - if (!hugepage_migration_support(page_hstate(hpage))) { + if (!hugepage_migration_supported(page_hstate(hpage))) { putback_active_hugepage(hpage); return -ENOSYS; } @@ -1056,20 +1064,30 @@ 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; @@ -1086,6 +1104,8 @@ 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. @@ -1099,7 +1119,8 @@ 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; @@ -1121,10 +1142,11 @@ 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: @@ -1273,7 +1295,7 @@ 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); @@ -1729,7 +1751,8 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, 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) { if (!list_empty(&migratepages)) { list_del(&page->lru); @@ -1852,7 +1875,7 @@ fail_putback: * guarantee the copy is visible before the pagetable update. */ flush_cache_range(vma, mmun_start, mmun_end); - page_add_new_anon_rmap(new_page, vma, mmun_start); + page_add_anon_rmap(new_page, vma, mmun_start); pmdp_clear_flush(vma, mmun_start, pmd); set_pmd_at(mm, mmun_start, pmd, entry); flush_tlb_range(vma, mmun_start, mmun_end); @@ -1877,6 +1900,10 @@ fail_putback: spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + /* Take an "isolate" reference and put new page on the LRU. */ + get_page(new_page); + putback_lru_page(new_page); + unlock_page(new_page); unlock_page(page); put_page(page); /* Drop the rmap reference */ diff --git a/mm/mmap.c b/mm/mmap.c index b1202cf81f4b..129b847d30cc 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -6,6 +6,8 @@ * Address space accounting code <alan@lxorguk.ukuu.org.uk> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/slab.h> #include <linux/backing-dev.h> @@ -37,6 +39,7 @@ #include <linux/sched/sysctl.h> #include <linux/notifier.h> #include <linux/memory.h> +#include <linux/printk.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> @@ -361,20 +364,20 @@ static int browse_rb(struct rb_root *root) struct vm_area_struct *vma; vma = rb_entry(nd, struct vm_area_struct, vm_rb); if (vma->vm_start < prev) { - printk("vm_start %lx prev %lx\n", vma->vm_start, prev); + pr_info("vm_start %lx prev %lx\n", vma->vm_start, prev); bug = 1; } if (vma->vm_start < pend) { - printk("vm_start %lx pend %lx\n", vma->vm_start, pend); + pr_info("vm_start %lx pend %lx\n", vma->vm_start, pend); bug = 1; } if (vma->vm_start > vma->vm_end) { - printk("vm_end %lx < vm_start %lx\n", + pr_info("vm_end %lx < vm_start %lx\n", vma->vm_end, vma->vm_start); bug = 1; } if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) { - printk("free gap %lx, correct %lx\n", + pr_info("free gap %lx, correct %lx\n", vma->rb_subtree_gap, vma_compute_subtree_gap(vma)); bug = 1; @@ -388,7 +391,7 @@ static int browse_rb(struct rb_root *root) for (nd = pn; nd; nd = rb_prev(nd)) j++; if (i != j) { - printk("backwards %d, forwards %d\n", j, i); + pr_info("backwards %d, forwards %d\n", j, i); bug = 1; } return bug ? -1 : i; @@ -423,17 +426,17 @@ static void validate_mm(struct mm_struct *mm) i++; } if (i != mm->map_count) { - printk("map_count %d vm_next %d\n", mm->map_count, i); + pr_info("map_count %d vm_next %d\n", mm->map_count, i); bug = 1; } if (highest_address != mm->highest_vm_end) { - printk("mm->highest_vm_end %lx, found %lx\n", + pr_info("mm->highest_vm_end %lx, found %lx\n", mm->highest_vm_end, highest_address); bug = 1; } i = browse_rb(&mm->mm_rb); if (i != mm->map_count) { - printk("map_count %d rb %d\n", mm->map_count, i); + pr_info("map_count %d rb %d\n", mm->map_count, i); bug = 1; } BUG_ON(bug); @@ -640,11 +643,10 @@ static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma, { struct address_space *mapping = NULL; - if (vma->vm_file) + if (vma->vm_file) { mapping = vma->vm_file->f_mapping; - - if (mapping) mutex_lock(&mapping->i_mmap_mutex); + } __vma_link(mm, vma, prev, rb_link, rb_parent); __vma_link_file(vma); @@ -2872,6 +2874,31 @@ int may_expand_vm(struct mm_struct *mm, unsigned long npages) return 1; } +static int special_mapping_fault(struct vm_area_struct *vma, + struct vm_fault *vmf); + +/* + * Having a close hook prevents vma merging regardless of flags. + */ +static void special_mapping_close(struct vm_area_struct *vma) +{ +} + +static const char *special_mapping_name(struct vm_area_struct *vma) +{ + return ((struct vm_special_mapping *)vma->vm_private_data)->name; +} + +static const struct vm_operations_struct special_mapping_vmops = { + .close = special_mapping_close, + .fault = special_mapping_fault, + .name = special_mapping_name, +}; + +static const struct vm_operations_struct legacy_special_mapping_vmops = { + .close = special_mapping_close, + .fault = special_mapping_fault, +}; static int special_mapping_fault(struct vm_area_struct *vma, struct vm_fault *vmf) @@ -2887,7 +2914,13 @@ static int special_mapping_fault(struct vm_area_struct *vma, */ pgoff = vmf->pgoff - vma->vm_pgoff; - for (pages = vma->vm_private_data; pgoff && *pages; ++pages) + if (vma->vm_ops == &legacy_special_mapping_vmops) + pages = vma->vm_private_data; + else + pages = ((struct vm_special_mapping *)vma->vm_private_data)-> + pages; + + for (; pgoff && *pages; ++pages) pgoff--; if (*pages) { @@ -2900,30 +2933,11 @@ static int special_mapping_fault(struct vm_area_struct *vma, return VM_FAULT_SIGBUS; } -/* - * Having a close hook prevents vma merging regardless of flags. - */ -static void special_mapping_close(struct vm_area_struct *vma) -{ -} - -static const struct vm_operations_struct special_mapping_vmops = { - .close = special_mapping_close, - .fault = special_mapping_fault, -}; - -/* - * Called with mm->mmap_sem held for writing. - * Insert a new vma covering the given region, with the given flags. - * Its pages are supplied by the given array of struct page *. - * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated. - * The region past the last page supplied will always produce SIGBUS. - * The array pointer and the pages it points to are assumed to stay alive - * for as long as this mapping might exist. - */ -struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, - unsigned long addr, unsigned long len, - unsigned long vm_flags, struct page **pages) +static struct vm_area_struct *__install_special_mapping( + struct mm_struct *mm, + unsigned long addr, unsigned long len, + unsigned long vm_flags, const struct vm_operations_struct *ops, + void *priv) { int ret; struct vm_area_struct *vma; @@ -2940,8 +2954,8 @@ struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); - vma->vm_ops = &special_mapping_vmops; - vma->vm_private_data = pages; + vma->vm_ops = ops; + vma->vm_private_data = priv; ret = insert_vm_struct(mm, vma); if (ret) @@ -2958,16 +2972,33 @@ out: return ERR_PTR(ret); } +/* + * Called with mm->mmap_sem held for writing. + * Insert a new vma covering the given region, with the given flags. + * Its pages are supplied by the given array of struct page *. + * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated. + * The region past the last page supplied will always produce SIGBUS. + * The array pointer and the pages it points to are assumed to stay alive + * for as long as this mapping might exist. + */ +struct vm_area_struct *_install_special_mapping( + struct mm_struct *mm, + unsigned long addr, unsigned long len, + unsigned long vm_flags, const struct vm_special_mapping *spec) +{ + return __install_special_mapping(mm, addr, len, vm_flags, + &special_mapping_vmops, (void *)spec); +} + int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, struct page **pages) { - struct vm_area_struct *vma = _install_special_mapping(mm, - addr, len, vm_flags, pages); + struct vm_area_struct *vma = __install_special_mapping( + mm, addr, len, vm_flags, &legacy_special_mapping_vmops, + (void *)pages); - if (IS_ERR(vma)) - return PTR_ERR(vma); - return 0; + return PTR_ERR_OR_ZERO(vma); } static DEFINE_MUTEX(mm_all_locks_mutex); @@ -3252,7 +3283,7 @@ static struct notifier_block reserve_mem_nb = { static int __meminit init_reserve_notifier(void) { if (register_hotmemory_notifier(&reserve_mem_nb)) - printk("Failed registering memory add/remove notifier for admin reserve"); + pr_err("Failed registering memory add/remove notifier for admin reserve\n"); return 0; } diff --git a/mm/mremap.c b/mm/mremap.c index 0843feb66f3d..05f1180e9f21 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; diff --git a/mm/msync.c b/mm/msync.c index 632df4527c01..a5c673669ca6 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -58,6 +58,7 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) vma = find_vma(mm, start); for (;;) { struct file *file; + loff_t fstart, fend; /* Still start < end. */ error = -ENOMEM; @@ -77,12 +78,17 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) goto out_unlock; } file = vma->vm_file; + fstart = start + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); + fend = fstart + (min(end, vma->vm_end) - start) - 1; start = vma->vm_end; if ((flags & MS_SYNC) && file && (vma->vm_flags & VM_SHARED)) { get_file(file); up_read(&mm->mmap_sem); - error = vfs_fsync(file, 0); + if (vma->vm_flags & VM_NONLINEAR) + error = vfs_fsync(file, 1); + else + error = vfs_fsync_range(file, fstart, fend, 1); fput(file); if (error || start >= end) goto out; diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 04a9d94333a5..7ed58602e71b 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -197,7 +197,6 @@ unsigned long __init free_all_bootmem(void) void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, unsigned long size) { - kmemleak_free_part(__va(physaddr), size); memblock_free(physaddr, size); } @@ -212,7 +211,6 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, */ void __init free_bootmem(unsigned long addr, unsigned long size) { - kmemleak_free_part(__va(addr), size); memblock_free(addr, size); } diff --git a/mm/nommu.c b/mm/nommu.c index 85f8d6698d48..b78e3a8f5ee7 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -13,6 +13,8 @@ * Copyright (c) 2007-2010 Paul Mundt <lethal@linux-sh.org> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/export.h> #include <linux/mm.h> #include <linux/vmacache.h> @@ -32,6 +34,7 @@ #include <linux/syscalls.h> #include <linux/audit.h> #include <linux/sched/sysctl.h> +#include <linux/printk.h> #include <asm/uaccess.h> #include <asm/tlb.h> @@ -1246,7 +1249,7 @@ error_free: return ret; enomem: - printk("Allocation of length %lu from process %d (%s) failed\n", + pr_err("Allocation of length %lu from process %d (%s) failed\n", len, current->pid, current->comm); show_free_areas(0); return -ENOMEM; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index ef413492a149..518e2c3f4c75 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -156,24 +156,6 @@ static unsigned long writeout_period_time = 0; #define VM_COMPLETIONS_PERIOD_LEN (3*HZ) /* - * Work out the current dirty-memory clamping and background writeout - * thresholds. - * - * The main aim here is to lower them aggressively if there is a lot of mapped - * memory around. To avoid stressing page reclaim with lots of unreclaimable - * pages. It is better to clamp down on writers than to start swapping, and - * performing lots of scanning. - * - * We only allow 1/2 of the currently-unmapped memory to be dirtied. - * - * We don't permit the clamping level to fall below 5% - that is getting rather - * excessive. - * - * We make sure that the background writeout level is below the adjusted - * clamping level. - */ - -/* * In a memory zone, there is a certain amount of pages we consider * available for the page cache, which is essentially the number of * free and reclaimable pages, minus some zone reserves to protect @@ -593,14 +575,14 @@ 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 +824,7 @@ 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; @@ -1623,7 +1605,7 @@ void balance_dirty_pages_ratelimited(struct address_space *mapping) * 1000+ tasks, all of them start dirtying pages at exactly the same * time, hence all honoured too large initial task->nr_dirtied_pause. */ - p = &__get_cpu_var(bdp_ratelimits); + p = this_cpu_ptr(&bdp_ratelimits); if (unlikely(current->nr_dirtied >= ratelimit)) *p = 0; else if (unlikely(*p >= ratelimit_pages)) { @@ -1635,7 +1617,7 @@ void balance_dirty_pages_ratelimited(struct address_space *mapping) * short-lived tasks (eg. gcc invocations in a kernel build) escaping * the dirty throttling and livelock other long-run dirtiers. */ - p = &__get_cpu_var(dirty_throttle_leaks); + p = this_cpu_ptr(&dirty_throttle_leaks); if (*p > 0 && current->nr_dirtied < ratelimit) { unsigned long nr_pages_dirtied; nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied); @@ -1682,7 +1664,7 @@ void throttle_vm_writeout(gfp_t gfp_mask) /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ -int dirty_writeback_centisecs_handler(ctl_table *table, int write, +int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec(table, write, buffer, length, ppos); @@ -2398,7 +2380,7 @@ 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 +2405,10 @@ 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 +2419,7 @@ 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 5dba2933c9c0..4f59fa29eda8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -261,8 +261,9 @@ static int page_outside_zone_boundaries(struct zone *zone, struct page *page) } while (zone_span_seqretry(zone, seq)); if (ret) - pr_err("page %lu outside zone [ %lu - %lu ]\n", - pfn, start_pfn, start_pfn + sp); + pr_err("page 0x%lx outside node %d zone %s [ 0x%lx - 0x%lx ]\n", + pfn, zone_to_nid(zone), zone->name, + start_pfn, start_pfn + sp); return ret; } @@ -408,7 +409,8 @@ 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; @@ -452,7 +454,7 @@ 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); @@ -503,21 +505,31 @@ __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(page_count(buddy) != 0, buddy); + + if (page_zone_id(page) != page_zone_id(buddy)) + return 0; + return 1; } if (PageBuddy(buddy) && page_order(buddy) == order) { VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + + /* + * 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; @@ -549,6 +561,7 @@ 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) { @@ -565,7 +578,7 @@ 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(page_idx & ((1 << order) - 1), page); VM_BUG_ON_PAGE(bad_range(zone, page), page); @@ -700,7 +713,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, list_del(&page->lru); mt = get_freepage_migratetype(page); /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ - __free_one_page(page, zone, 0, mt); + __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); @@ -712,13 +725,15 @@ static void free_pcppages_bulk(struct zone *zone, int count, 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) { spin_lock(&zone->lock); zone->pages_scanned = 0; - __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(&zone->lock); @@ -755,15 +770,16 @@ 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; + 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); + free_one_page(page_zone(page), page, pfn, order, migratetype); local_irq_restore(flags); } @@ -882,7 +898,7 @@ 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; @@ -931,6 +947,7 @@ 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; } @@ -1057,7 +1074,9 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page, /* * When borrowing from MIGRATE_CMA, we need to release the excess - * buddy pages to CMA itself. + * 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; @@ -1090,16 +1109,17 @@ 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]; @@ -1125,6 +1145,12 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) expand(zone, page, order, current_order, area, 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); @@ -1173,9 +1199,9 @@ 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) { @@ -1192,18 +1218,12 @@ 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)); } @@ -1327,7 +1347,7 @@ 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)) @@ -1359,19 +1379,20 @@ 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_irq_save(flags); __count_vm_event(PGFREE); @@ -1385,17 +1406,17 @@ 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); @@ -1410,7 +1431,7 @@ out: /* * 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; @@ -1522,12 +1543,12 @@ 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)) { @@ -1572,7 +1593,7 @@ again: if (!page) goto failed; __mod_zone_freepage_state(zone, -(1 << order), - get_pageblock_migratetype(page)); + get_freepage_migratetype(page)); } __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); @@ -1672,8 +1693,9 @@ 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; @@ -1707,15 +1729,15 @@ 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); @@ -1850,18 +1872,8 @@ static bool zone_local(struct zone *local_zone, struct zone *zone) static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { - return node_isset(local_zone->node, zone->zone_pgdat->reclaim_nodes); -} - -static void __paginginit init_zone_allows_reclaim(int nid) -{ - int i; - - for_each_node_state(i, N_MEMORY) - if (node_distance(nid, i) <= RECLAIM_DISTANCE) - node_set(i, NODE_DATA(nid)->reclaim_nodes); - else - zone_reclaim_mode = 1; + return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) < + RECLAIM_DISTANCE; } #else /* CONFIG_NUMA */ @@ -1895,9 +1907,6 @@ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) return true; } -static inline void init_zone_allows_reclaim(int nid) -{ -} #endif /* CONFIG_NUMA */ /* @@ -1907,17 +1916,17 @@ 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); - classzone_idx = zone_idx(preferred_zone); zonelist_scan: /* * Scan zonelist, looking for a zone with enough free. @@ -1930,12 +1939,10 @@ 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 @@ -1974,15 +1981,19 @@ 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) { /* @@ -2044,7 +2055,7 @@ 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); } @@ -2173,7 +2184,7 @@ 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; @@ -2191,7 +2202,7 @@ __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; @@ -2226,7 +2237,7 @@ 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) { @@ -2240,7 +2251,7 @@ __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; @@ -2254,7 +2265,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, 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; compaction_defer_reset(preferred_zone, order, true); @@ -2273,7 +2284,7 @@ __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(); @@ -2286,9 +2297,9 @@ 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; } @@ -2327,7 +2338,7 @@ 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; @@ -2345,7 +2356,8 @@ 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 @@ -2368,14 +2380,14 @@ 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); @@ -2476,14 +2488,14 @@ 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; @@ -2525,15 +2537,18 @@ 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; @@ -2548,7 +2563,7 @@ 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; } @@ -2577,17 +2592,23 @@ 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; + + /* + * It can become very expensive to allocate transparent hugepages at + * fault, so use asynchronous memory compaction for THP unless it is + * khugepaged trying to collapse. + */ + if (!(gfp_mask & __GFP_NO_KSWAPD) || (current->flags & PF_KTHREAD)) + migration_mode = MIGRATE_SYNC_LIGHT; /* * If compaction is deferred for high-order allocations, it is because @@ -2604,7 +2625,8 @@ rebalance: zonelist, high_zoneidx, nodemask, alloc_flags, preferred_zone, - migratetype, &did_some_progress); + classzone_idx, migratetype, + &did_some_progress); if (page) goto got_pg; @@ -2623,7 +2645,7 @@ rebalance: page = __alloc_pages_may_oom(gfp_mask, order, zonelist, high_zoneidx, nodemask, preferred_zone, - migratetype); + classzone_idx, migratetype); if (page) goto got_pg; @@ -2662,12 +2684,11 @@ 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) @@ -2693,11 +2714,12 @@ __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|ALLOC_FAIR; - struct mem_cgroup *memcg = NULL; + int classzone_idx; gfp_mask &= gfp_allowed_mask; @@ -2716,22 +2738,16 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, if (unlikely(!zonelist->_zonerefs->zone)) return NULL; - /* - * Will only have any effect when __GFP_KMEMCG is set. This is - * verified in the (always inline) callee - */ - if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order)) - return NULL; - retry_cpuset: 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) @@ -2741,7 +2757,7 @@ retry: /* 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)) { /* * The first pass makes sure allocations are spread @@ -2767,7 +2783,7 @@ retry: 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); @@ -2782,8 +2798,6 @@ out: if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; - memcg_kmem_commit_charge(page, memcg, order); - return page; } EXPORT_SYMBOL(__alloc_pages_nodemask); @@ -2818,7 +2832,7 @@ 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); } @@ -2837,27 +2851,51 @@ void free_pages(unsigned long addr, unsigned int order) EXPORT_SYMBOL(free_pages); /* - * __free_memcg_kmem_pages and free_memcg_kmem_pages will free - * pages allocated with __GFP_KMEMCG. - * - * Those pages are accounted to a particular memcg, embedded in the - * corresponding page_cgroup. To avoid adding a hit in the allocator to search - * for that information only to find out that it is NULL for users who have no - * interest in that whatsoever, we provide these functions. + * alloc_kmem_pages charges newly allocated pages to the kmem resource counter + * of the current memory cgroup. * - * The caller knows better which flags it relies on. + * It should be used when the caller would like to use kmalloc, but since the + * allocation is large, it has to fall back to the page allocator. */ -void __free_memcg_kmem_pages(struct page *page, unsigned int order) +struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order) +{ + struct page *page; + struct mem_cgroup *memcg = NULL; + + if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order)) + return NULL; + page = alloc_pages(gfp_mask, order); + memcg_kmem_commit_charge(page, memcg, order); + return page; +} + +struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, unsigned int order) +{ + struct page *page; + struct mem_cgroup *memcg = NULL; + + if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order)) + return NULL; + page = alloc_pages_node(nid, gfp_mask, order); + memcg_kmem_commit_charge(page, memcg, order); + return page; +} + +/* + * __free_kmem_pages and free_kmem_pages will free pages allocated with + * alloc_kmem_pages. + */ +void __free_kmem_pages(struct page *page, unsigned int order) { memcg_kmem_uncharge_pages(page, order); __free_pages(page, order); } -void free_memcg_kmem_pages(unsigned long addr, unsigned int order) +void free_kmem_pages(unsigned long addr, unsigned int order) { if (addr != 0) { VM_BUG_ON(!virt_addr_valid((void *)addr)); - __free_memcg_kmem_pages(virt_to_page((void *)addr), order); + __free_kmem_pages(virt_to_page((void *)addr), order); } } @@ -3351,7 +3389,7 @@ early_param("numa_zonelist_order", setup_numa_zonelist_order); /* * sysctl handler for numa_zonelist_order */ -int numa_zonelist_order_handler(ctl_table *table, int write, +int numa_zonelist_order_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { @@ -4095,7 +4133,7 @@ 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; @@ -4349,9 +4387,6 @@ int __meminit init_currently_empty_zone(struct zone *zone, #ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID /* * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. - * Architectures may implement their own version but if add_active_range() - * was used and there are no special requirements, this is a convenient - * alternative */ int __meminit __early_pfn_to_nid(unsigned long pfn) { @@ -4406,10 +4441,9 @@ bool __meminit early_pfn_in_nid(unsigned long pfn, int node) * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed. * @max_low_pfn: The highest PFN that will be passed to memblock_free_early_nid * - * If an architecture guarantees that all ranges registered with - * add_active_ranges() contain no holes and may be freed, this - * this function may be used instead of calling memblock_free_early_nid() - * manually. + * If an architecture guarantees that all ranges registered contain no holes + * and may be freed, this this function may be used instead of calling + * memblock_free_early_nid() manually. */ void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn) { @@ -4431,9 +4465,8 @@ void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn) * sparse_memory_present_with_active_regions - Call memory_present for each active range * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used. * - * If an architecture guarantees that all ranges registered with - * add_active_ranges() contain no holes and may be freed, this - * function may be used instead of calling memory_present() manually. + * If an architecture guarantees that all ranges registered contain no holes and may + * be freed, this function may be used instead of calling memory_present() manually. */ void __init sparse_memory_present_with_active_regions(int nid) { @@ -4451,7 +4484,7 @@ void __init sparse_memory_present_with_active_regions(int nid) * @end_pfn: Passed by reference. On return, it will have the node end_pfn. * * It returns the start and end page frame of a node based on information - * provided by an arch calling add_active_range(). If called for a node + * provided by memblock_set_node(). If called for a node * with no available memory, a warning is printed and the start and end * PFNs will be 0. */ @@ -4921,8 +4954,6 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; - 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 @@ -5030,7 +5061,7 @@ static unsigned long __init find_min_pfn_for_node(int nid) * find_min_pfn_with_active_regions - Find the minimum PFN registered * * It returns the minimum PFN based on information provided via - * add_active_range(). + * memblock_set_node(). */ unsigned long __init find_min_pfn_with_active_regions(void) { @@ -5251,7 +5282,7 @@ static void check_for_memory(pg_data_t *pgdat, int nid) * @max_zone_pfn: an array of max PFNs for each zone * * This will call free_area_init_node() for each active node in the system. - * Using the page ranges provided by add_active_range(), the size of each + * Using the page ranges provided by memblock_set_node(), the size of each * zone in each node and their holes is calculated. If the maximum PFN * between two adjacent zones match, it is assumed that the zone is empty. * For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed @@ -5774,7 +5805,7 @@ module_init(init_per_zone_wmark_min) * that we can call two helper functions whenever min_free_kbytes * changes. */ -int min_free_kbytes_sysctl_handler(ctl_table *table, int write, +int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { int rc; @@ -5791,7 +5822,7 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write, } #ifdef CONFIG_NUMA -int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write, +int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; @@ -5807,7 +5838,7 @@ int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write, return 0; } -int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, +int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; @@ -5833,7 +5864,7 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, * minimum watermarks. The lowmem reserve ratio can only make sense * if in function of the boot time zone sizes. */ -int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write, +int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec_minmax(table, write, buffer, length, ppos); @@ -5846,7 +5877,7 @@ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write, * cpu. It is the fraction of total pages in each zone that a hot per cpu * pagelist can have before it gets flushed back to buddy allocator. */ -int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write, +int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; @@ -6009,53 +6040,64 @@ 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_PAGE(!zone_spans_pfn(zone, pfn), page); - 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; + } } /* @@ -6215,7 +6257,7 @@ 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); @@ -6254,7 +6296,7 @@ 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); @@ -6409,7 +6451,7 @@ __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 */ @@ -6461,7 +6503,7 @@ 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_io.c b/mm/page_io.c index 7c59ef681381..58b50d2901fe 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -248,11 +248,16 @@ out: return ret; } +static sector_t swap_page_sector(struct page *page) +{ + return (sector_t)__page_file_index(page) << (PAGE_CACHE_SHIFT - 9); +} + int __swap_writepage(struct page *page, struct writeback_control *wbc, void (*end_write_func)(struct bio *, int)) { struct bio *bio; - int ret = 0, rw = WRITE; + int ret, rw = WRITE; struct swap_info_struct *sis = page_swap_info(page); if (sis->flags & SWP_FILE) { @@ -297,6 +302,13 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, return ret; } + ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc); + if (!ret) { + count_vm_event(PSWPOUT); + return 0; + } + + ret = 0; bio = get_swap_bio(GFP_NOIO, page, end_write_func); if (bio == NULL) { set_page_dirty(page); @@ -338,6 +350,13 @@ int swap_readpage(struct page *page) return ret; } + ret = bdev_read_page(sis->bdev, swap_page_sector(page), page); + if (!ret) { + count_vm_event(PSWPIN); + return 0; + } + + ret = 0; bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read); if (bio == NULL) { unlock_page(page); diff --git a/mm/percpu.c b/mm/percpu.c index 63e24fb4387b..2ddf9a990dbd 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -610,7 +610,7 @@ 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/rmap.c b/mm/rmap.c index 9c3e77396d1a..bf05fc872ae8 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -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); @@ -426,8 +427,9 @@ 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 +479,9 @@ 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 */ @@ -669,7 +671,7 @@ struct page_referenced_arg { /* * arg: page_referenced_arg will be passed */ -int page_referenced_one(struct page *page, struct vm_area_struct *vma, +static int page_referenced_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; @@ -986,6 +988,12 @@ void do_page_add_anon_rmap(struct page *page, { int first = atomic_inc_and_test(&page->_mapcount); if (first) { + /* + * We use the irq-unsafe __{inc|mod}_zone_page_stat because + * these counters are not modified in interrupt context, and + * pte lock(a spinlock) is held, which implies preemption + * disabled. + */ if (PageTransHuge(page)) __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); @@ -1024,11 +1032,25 @@ void page_add_new_anon_rmap(struct page *page, __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, hpage_nr_pages(page)); __page_set_anon_rmap(page, vma, address, 1); - if (!mlocked_vma_newpage(vma, page)) { + + VM_BUG_ON_PAGE(PageLRU(page), page); + if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) { SetPageActive(page); lru_cache_add(page); - } else - add_page_to_unevictable_list(page); + return; + } + + if (!TestSetPageMlocked(page)) { + /* + * We use the irq-unsafe __mod_zone_page_stat because this + * counter is not modified from interrupt context, and the pte + * lock is held(spinlock), which implies preemption disabled. + */ + __mod_zone_page_state(page_zone(page), NR_MLOCK, + hpage_nr_pages(page)); + count_vm_event(UNEVICTABLE_PGMLOCKED); + } + add_page_to_unevictable_list(page); } /** @@ -1077,6 +1099,11 @@ void page_remove_rmap(struct page *page) /* * Hugepages are not counted in NR_ANON_PAGES nor NR_FILE_MAPPED * and not charged by memcg for now. + * + * We use the irq-unsafe __{inc|mod}_zone_page_stat because + * these counters are not modified in interrupt context, and + * these counters are not modified in interrupt context, and + * pte lock(a spinlock) is held, which implies preemption disabled. */ if (unlikely(PageHuge(page))) goto out; @@ -1112,7 +1139,7 @@ out: /* * @arg: enum ttu_flags will be passed to this argument */ -int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, +static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; @@ -1135,7 +1162,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (vma->vm_flags & VM_LOCKED) goto out_mlock; - if (TTU_ACTION(flags) == TTU_MUNLOCK) + if (flags & TTU_MUNLOCK) goto out_unmap; } if (!(flags & TTU_IGNORE_ACCESS)) { @@ -1203,7 +1230,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ - BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION); + BUG_ON(!(flags & TTU_MIGRATION)); entry = make_migration_entry(page, pte_write(pteval)); } swp_pte = swp_entry_to_pte(entry); @@ -1212,7 +1239,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, set_pte_at(mm, address, pte, swp_pte); BUG_ON(pte_file(*pte)); } else if (IS_ENABLED(CONFIG_MIGRATION) && - (TTU_ACTION(flags) == TTU_MIGRATION)) { + (flags & TTU_MIGRATION)) { /* Establish migration entry for a file page */ swp_entry_t entry; entry = make_migration_entry(page, pte_write(pteval)); @@ -1225,7 +1252,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, out_unmap: pte_unmap_unlock(pte, ptl); - if (ret != SWAP_FAIL) + if (ret != SWAP_FAIL && !(flags & TTU_MUNLOCK)) mmu_notifier_invalidate_page(mm, address); out: return ret; @@ -1359,7 +1386,7 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, if (page->index != linear_page_index(vma, address)) { pte_t ptfile = pgoff_to_pte(page->index); if (pte_soft_dirty(pteval)) - pte_file_mksoft_dirty(ptfile); + ptfile = pte_file_mksoft_dirty(ptfile); set_pte_at(mm, address, pte, ptfile); } @@ -1512,7 +1539,7 @@ int try_to_unmap(struct page *page, enum ttu_flags flags) * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ - if (flags & TTU_MIGRATION && !PageKsm(page) && PageAnon(page)) + if ((flags & TTU_MIGRATION) && !PageKsm(page) && PageAnon(page)) rwc.invalid_vma = invalid_migration_vma; ret = rmap_walk(page, &rwc); @@ -1564,10 +1591,9 @@ 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); } static struct anon_vma *rmap_walk_anon_lock(struct page *page, diff --git a/mm/shmem.c b/mm/shmem.c index 9f70e02111c6..5402481c28d1 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1132,7 +1132,7 @@ repeat: goto decused; } - SetPageSwapBacked(page); + __SetPageSwapBacked(page); __set_page_locked(page); error = mem_cgroup_charge_file(page, current->mm, gfp & GFP_RECLAIM_MASK); @@ -1372,9 +1372,13 @@ shmem_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { + int ret; struct inode *inode = mapping->host; pgoff_t index = pos >> PAGE_CACHE_SHIFT; - return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); + ret = shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); + if (ret == 0 && *pagep) + init_page_accessed(*pagep); + return ret; } static int diff --git a/mm/slab.c b/mm/slab.c index 388cb1ae6fbc..9ca3b87edabc 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -166,7 +166,7 @@ typedef unsigned char freelist_idx_t; typedef unsigned short freelist_idx_t; #endif -#define SLAB_OBJ_MAX_NUM (1 << sizeof(freelist_idx_t) * BITS_PER_BYTE) +#define SLAB_OBJ_MAX_NUM ((1 << sizeof(freelist_idx_t) * BITS_PER_BYTE) - 1) /* * true if a page was allocated from pfmemalloc reserves for network-based @@ -1621,10 +1621,16 @@ __initcall(cpucache_init); static noinline void slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid) { +#if DEBUG struct kmem_cache_node *n; struct page *page; unsigned long flags; int node; + static DEFINE_RATELIMIT_STATE(slab_oom_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + + if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slab_oom_rs)) + return; printk(KERN_WARNING "SLAB: Unable to allocate memory on node %d (gfp=0x%x)\n", @@ -1662,6 +1668,7 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid) node, active_slabs, num_slabs, active_objs, num_objs, free_objects); } +#endif } /* @@ -1681,10 +1688,13 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, if (cachep->flags & SLAB_RECLAIM_ACCOUNT) flags |= __GFP_RECLAIMABLE; + if (memcg_charge_slab(cachep, flags, cachep->gfporder)) + return NULL; + page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder); if (!page) { - if (!(flags & __GFP_NOWARN) && printk_ratelimit()) - slab_out_of_memory(cachep, flags, nodeid); + memcg_uncharge_slab(cachep, cachep->gfporder); + slab_out_of_memory(cachep, flags, nodeid); return NULL; } @@ -1702,7 +1712,6 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, __SetPageSlab(page); if (page->pfmemalloc) SetPageSlabPfmemalloc(page); - memcg_bind_pages(cachep, cachep->gfporder); if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) { kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid); @@ -1738,10 +1747,10 @@ static void kmem_freepages(struct kmem_cache *cachep, struct page *page) page_mapcount_reset(page); page->mapping = NULL; - memcg_release_pages(cachep, cachep->gfporder); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += nr_freed; - __free_memcg_kmem_pages(page, cachep->gfporder); + __free_pages(page, cachep->gfporder); + memcg_uncharge_slab(cachep, cachep->gfporder); } static void kmem_rcu_free(struct rcu_head *head) @@ -2469,8 +2478,7 @@ out: return nr_freed; } -/* Called with slab_mutex held to protect against cpu hotplug */ -static int __cache_shrink(struct kmem_cache *cachep) +int __kmem_cache_shrink(struct kmem_cache *cachep) { int ret = 0, i = 0; struct kmem_cache_node *n; @@ -2491,32 +2499,11 @@ static int __cache_shrink(struct kmem_cache *cachep) return (ret ? 1 : 0); } -/** - * kmem_cache_shrink - Shrink a cache. - * @cachep: The cache to shrink. - * - * Releases as many slabs as possible for a cache. - * To help debugging, a zero exit status indicates all slabs were released. - */ -int kmem_cache_shrink(struct kmem_cache *cachep) -{ - int ret; - BUG_ON(!cachep || in_interrupt()); - - get_online_cpus(); - mutex_lock(&slab_mutex); - ret = __cache_shrink(cachep); - mutex_unlock(&slab_mutex); - put_online_cpus(); - return ret; -} -EXPORT_SYMBOL(kmem_cache_shrink); - int __kmem_cache_shutdown(struct kmem_cache *cachep) { int i; struct kmem_cache_node *n; - int rc = __cache_shrink(cachep); + int rc = __kmem_cache_shrink(cachep); if (rc) return rc; @@ -2572,13 +2559,13 @@ static void *alloc_slabmgmt(struct kmem_cache *cachep, return freelist; } -static inline freelist_idx_t get_free_obj(struct page *page, unsigned char idx) +static inline freelist_idx_t get_free_obj(struct page *page, unsigned int idx) { return ((freelist_idx_t *)page->freelist)[idx]; } static inline void set_free_obj(struct page *page, - unsigned char idx, freelist_idx_t val) + unsigned int idx, freelist_idx_t val) { ((freelist_idx_t *)(page->freelist))[idx] = val; } diff --git a/mm/slab.h b/mm/slab.h index 3045316b7c9d..961a3fb1f5a2 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -91,6 +91,8 @@ __kmem_cache_alias(const char *name, size_t size, size_t align, #define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS) int __kmem_cache_shutdown(struct kmem_cache *); +int __kmem_cache_shrink(struct kmem_cache *); +void slab_kmem_cache_release(struct kmem_cache *); struct seq_file; struct file; @@ -119,21 +121,6 @@ static inline bool is_root_cache(struct kmem_cache *s) return !s->memcg_params || s->memcg_params->is_root_cache; } -static inline void memcg_bind_pages(struct kmem_cache *s, int order) -{ - if (!is_root_cache(s)) - atomic_add(1 << order, &s->memcg_params->nr_pages); -} - -static inline void memcg_release_pages(struct kmem_cache *s, int order) -{ - if (is_root_cache(s)) - return; - - if (atomic_sub_and_test((1 << order), &s->memcg_params->nr_pages)) - mem_cgroup_destroy_cache(s); -} - static inline bool slab_equal_or_root(struct kmem_cache *s, struct kmem_cache *p) { @@ -191,18 +178,29 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) return s; return s->memcg_params->root_cache; } -#else -static inline bool is_root_cache(struct kmem_cache *s) + +static __always_inline int memcg_charge_slab(struct kmem_cache *s, + gfp_t gfp, int order) { - return true; + if (!memcg_kmem_enabled()) + return 0; + if (is_root_cache(s)) + return 0; + return __memcg_charge_slab(s, gfp, order); } -static inline void memcg_bind_pages(struct kmem_cache *s, int order) +static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order) { + if (!memcg_kmem_enabled()) + return; + if (is_root_cache(s)) + return; + __memcg_uncharge_slab(s, order); } - -static inline void memcg_release_pages(struct kmem_cache *s, int order) +#else +static inline bool is_root_cache(struct kmem_cache *s) { + return true; } static inline bool slab_equal_or_root(struct kmem_cache *s, @@ -226,6 +224,15 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) { return s; } + +static inline int memcg_charge_slab(struct kmem_cache *s, gfp_t gfp, int order) +{ + return 0; +} + +static inline void memcg_uncharge_slab(struct kmem_cache *s, int order) +{ +} #endif static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x) diff --git a/mm/slab_common.c b/mm/slab_common.c index f3cfccf76dda..735e01a0db6f 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -160,7 +160,6 @@ do_kmem_cache_create(char *name, size_t object_size, size_t size, size_t align, s->refcount = 1; list_add(&s->list, &slab_caches); - memcg_register_cache(s); out: if (err) return ERR_PTR(err); @@ -205,6 +204,8 @@ kmem_cache_create(const char *name, size_t size, size_t align, int err; get_online_cpus(); + get_online_mems(); + mutex_lock(&slab_mutex); err = kmem_cache_sanity_check(name, size); @@ -239,6 +240,8 @@ kmem_cache_create(const char *name, size_t size, size_t align, out_unlock: mutex_unlock(&slab_mutex); + + put_online_mems(); put_online_cpus(); if (err) { @@ -258,31 +261,29 @@ EXPORT_SYMBOL(kmem_cache_create); #ifdef CONFIG_MEMCG_KMEM /* - * kmem_cache_create_memcg - Create a cache for a memory cgroup. + * memcg_create_kmem_cache - Create a cache for a memory cgroup. * @memcg: The memory cgroup the new cache is for. * @root_cache: The parent of the new cache. + * @memcg_name: The name of the memory cgroup (used for naming the new cache). * * This function attempts to create a kmem cache that will serve allocation * requests going from @memcg to @root_cache. The new cache inherits properties * from its parent. */ -void kmem_cache_create_memcg(struct mem_cgroup *memcg, struct kmem_cache *root_cache) +struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, + struct kmem_cache *root_cache, + const char *memcg_name) { - struct kmem_cache *s; + struct kmem_cache *s = NULL; char *cache_name; get_online_cpus(); - mutex_lock(&slab_mutex); + get_online_mems(); - /* - * Since per-memcg caches are created asynchronously on first - * allocation (see memcg_kmem_get_cache()), several threads can try to - * create the same cache, but only one of them may succeed. - */ - if (cache_from_memcg_idx(root_cache, memcg_cache_id(memcg))) - goto out_unlock; + mutex_lock(&slab_mutex); - cache_name = memcg_create_cache_name(memcg, root_cache); + cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, + memcg_cache_id(memcg), memcg_name); if (!cache_name) goto out_unlock; @@ -292,17 +293,19 @@ void kmem_cache_create_memcg(struct mem_cgroup *memcg, struct kmem_cache *root_c memcg, root_cache); if (IS_ERR(s)) { kfree(cache_name); - goto out_unlock; + s = NULL; } - s->allocflags |= __GFP_KMEMCG; - out_unlock: mutex_unlock(&slab_mutex); + + put_online_mems(); put_online_cpus(); + + return s; } -static int kmem_cache_destroy_memcg_children(struct kmem_cache *s) +static int memcg_cleanup_cache_params(struct kmem_cache *s) { int rc; @@ -311,58 +314,87 @@ static int kmem_cache_destroy_memcg_children(struct kmem_cache *s) return 0; mutex_unlock(&slab_mutex); - rc = __kmem_cache_destroy_memcg_children(s); + rc = __memcg_cleanup_cache_params(s); mutex_lock(&slab_mutex); return rc; } #else -static int kmem_cache_destroy_memcg_children(struct kmem_cache *s) +static int memcg_cleanup_cache_params(struct kmem_cache *s) { return 0; } #endif /* CONFIG_MEMCG_KMEM */ +void slab_kmem_cache_release(struct kmem_cache *s) +{ + kfree(s->name); + kmem_cache_free(kmem_cache, s); +} + void kmem_cache_destroy(struct kmem_cache *s) { get_online_cpus(); + get_online_mems(); + mutex_lock(&slab_mutex); s->refcount--; if (s->refcount) goto out_unlock; - if (kmem_cache_destroy_memcg_children(s) != 0) + if (memcg_cleanup_cache_params(s) != 0) goto out_unlock; - list_del(&s->list); - memcg_unregister_cache(s); - if (__kmem_cache_shutdown(s) != 0) { - list_add(&s->list, &slab_caches); - memcg_register_cache(s); printk(KERN_ERR "kmem_cache_destroy %s: " "Slab cache still has objects\n", s->name); dump_stack(); goto out_unlock; } + list_del(&s->list); + mutex_unlock(&slab_mutex); if (s->flags & SLAB_DESTROY_BY_RCU) rcu_barrier(); memcg_free_cache_params(s); - kfree(s->name); - kmem_cache_free(kmem_cache, s); - goto out_put_cpus; +#ifdef SLAB_SUPPORTS_SYSFS + sysfs_slab_remove(s); +#else + slab_kmem_cache_release(s); +#endif + goto out; out_unlock: mutex_unlock(&slab_mutex); -out_put_cpus: +out: + put_online_mems(); put_online_cpus(); } EXPORT_SYMBOL(kmem_cache_destroy); +/** + * kmem_cache_shrink - Shrink a cache. + * @cachep: The cache to shrink. + * + * Releases as many slabs as possible for a cache. + * To help debugging, a zero exit status indicates all slabs were released. + */ +int kmem_cache_shrink(struct kmem_cache *cachep) +{ + int ret; + + get_online_cpus(); + get_online_mems(); + ret = __kmem_cache_shrink(cachep); + put_online_mems(); + put_online_cpus(); + return ret; +} +EXPORT_SYMBOL(kmem_cache_shrink); + int slab_is_available(void) { return slab_state >= UP; @@ -577,6 +609,24 @@ void __init create_kmalloc_caches(unsigned long flags) } #endif /* !CONFIG_SLOB */ +/* + * To avoid unnecessary overhead, we pass through large allocation requests + * directly to the page allocator. We use __GFP_COMP, because we will need to + * know the allocation order to free the pages properly in kfree. + */ +void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) +{ + void *ret; + struct page *page; + + flags |= __GFP_COMP; + page = alloc_kmem_pages(flags, order); + ret = page ? page_address(page) : NULL; + kmemleak_alloc(ret, size, 1, flags); + return ret; +} +EXPORT_SYMBOL(kmalloc_order); + #ifdef CONFIG_TRACING void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) { diff --git a/mm/slob.c b/mm/slob.c index 730cad45d4be..21980e0f39a8 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -620,11 +620,10 @@ int __kmem_cache_shutdown(struct kmem_cache *c) return 0; } -int kmem_cache_shrink(struct kmem_cache *d) +int __kmem_cache_shrink(struct kmem_cache *d) { return 0; } -EXPORT_SYMBOL(kmem_cache_shrink); struct kmem_cache kmem_cache_boot = { .name = "kmem_cache", diff --git a/mm/slub.c b/mm/slub.c index 5e234f1f8853..b2b047327d76 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -210,14 +210,11 @@ enum track_item { TRACK_ALLOC, TRACK_FREE }; #ifdef CONFIG_SYSFS static int sysfs_slab_add(struct kmem_cache *); static int sysfs_slab_alias(struct kmem_cache *, const char *); -static void sysfs_slab_remove(struct kmem_cache *); static void memcg_propagate_slab_attrs(struct kmem_cache *s); #else static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; } static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p) { return 0; } -static inline void sysfs_slab_remove(struct kmem_cache *s) { } - static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { } #endif @@ -406,7 +403,7 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page stat(s, CMPXCHG_DOUBLE_FAIL); #ifdef SLUB_DEBUG_CMPXCHG - printk(KERN_INFO "%s %s: cmpxchg double redo ", n, s->name); + pr_info("%s %s: cmpxchg double redo ", n, s->name); #endif return 0; @@ -447,7 +444,7 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, stat(s, CMPXCHG_DOUBLE_FAIL); #ifdef SLUB_DEBUG_CMPXCHG - printk(KERN_INFO "%s %s: cmpxchg double redo ", n, s->name); + pr_info("%s %s: cmpxchg double redo ", n, s->name); #endif return 0; @@ -549,14 +546,14 @@ static void print_track(const char *s, struct track *t) if (!t->addr) return; - printk(KERN_ERR "INFO: %s in %pS age=%lu cpu=%u pid=%d\n", - s, (void *)t->addr, jiffies - t->when, t->cpu, t->pid); + pr_err("INFO: %s in %pS age=%lu cpu=%u pid=%d\n", + s, (void *)t->addr, jiffies - t->when, t->cpu, t->pid); #ifdef CONFIG_STACKTRACE { int i; for (i = 0; i < TRACK_ADDRS_COUNT; i++) if (t->addrs[i]) - printk(KERN_ERR "\t%pS\n", (void *)t->addrs[i]); + pr_err("\t%pS\n", (void *)t->addrs[i]); else break; } @@ -574,38 +571,37 @@ static void print_tracking(struct kmem_cache *s, void *object) static void print_page_info(struct page *page) { - printk(KERN_ERR - "INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n", + pr_err("INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n", page, page->objects, page->inuse, page->freelist, page->flags); } static void slab_bug(struct kmem_cache *s, char *fmt, ...) { + struct va_format vaf; va_list args; - char buf[100]; va_start(args, fmt); - vsnprintf(buf, sizeof(buf), fmt, args); - va_end(args); - printk(KERN_ERR "========================================" - "=====================================\n"); - printk(KERN_ERR "BUG %s (%s): %s\n", s->name, print_tainted(), buf); - printk(KERN_ERR "----------------------------------------" - "-------------------------------------\n\n"); + vaf.fmt = fmt; + vaf.va = &args; + pr_err("=============================================================================\n"); + pr_err("BUG %s (%s): %pV\n", s->name, print_tainted(), &vaf); + pr_err("-----------------------------------------------------------------------------\n\n"); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); + va_end(args); } static void slab_fix(struct kmem_cache *s, char *fmt, ...) { + struct va_format vaf; va_list args; - char buf[100]; va_start(args, fmt); - vsnprintf(buf, sizeof(buf), fmt, args); + vaf.fmt = fmt; + vaf.va = &args; + pr_err("FIX %s: %pV\n", s->name, &vaf); va_end(args); - printk(KERN_ERR "FIX %s: %s\n", s->name, buf); } static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) @@ -617,8 +613,8 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) print_page_info(page); - printk(KERN_ERR "INFO: Object 0x%p @offset=%tu fp=0x%p\n\n", - p, p - addr, get_freepointer(s, p)); + pr_err("INFO: Object 0x%p @offset=%tu fp=0x%p\n\n", + p, p - addr, get_freepointer(s, p)); if (p > addr + 16) print_section("Bytes b4 ", p - 16, 16); @@ -701,7 +697,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, end--; slab_bug(s, "%s overwritten", what); - printk(KERN_ERR "INFO: 0x%p-0x%p. First byte 0x%x instead of 0x%x\n", + pr_err("INFO: 0x%p-0x%p. First byte 0x%x instead of 0x%x\n", fault, end - 1, fault[0], value); print_trailer(s, page, object); @@ -934,7 +930,7 @@ static void trace(struct kmem_cache *s, struct page *page, void *object, int alloc) { if (s->flags & SLAB_TRACE) { - printk(KERN_INFO "TRACE %s %s 0x%p inuse=%d fp=0x%p\n", + pr_info("TRACE %s %s 0x%p inuse=%d fp=0x%p\n", s->name, alloc ? "alloc" : "free", object, page->inuse, @@ -1137,9 +1133,8 @@ static noinline struct kmem_cache_node *free_debug_processing( slab_err(s, page, "Attempt to free object(0x%p) " "outside of slab", object); } else if (!page->slab_cache) { - printk(KERN_ERR - "SLUB <none>: no slab for object 0x%p.\n", - object); + pr_err("SLUB <none>: no slab for object 0x%p.\n", + object); dump_stack(); } else object_err(s, page, object, @@ -1222,8 +1217,8 @@ static int __init setup_slub_debug(char *str) slub_debug |= SLAB_FAILSLAB; break; default: - printk(KERN_ERR "slub_debug option '%c' " - "unknown. skipped\n", *str); + pr_err("slub_debug option '%c' unknown. skipped\n", + *str); } } @@ -1317,17 +1312,26 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) /* * Slab allocation and freeing */ -static inline struct page *alloc_slab_page(gfp_t flags, int node, - struct kmem_cache_order_objects oo) +static inline struct page *alloc_slab_page(struct kmem_cache *s, + gfp_t flags, int node, struct kmem_cache_order_objects oo) { + struct page *page; int order = oo_order(oo); flags |= __GFP_NOTRACK; + if (memcg_charge_slab(s, flags, order)) + return NULL; + if (node == NUMA_NO_NODE) - return alloc_pages(flags, order); + page = alloc_pages(flags, order); else - return alloc_pages_exact_node(node, flags, order); + page = alloc_pages_exact_node(node, flags, order); + + if (!page) + memcg_uncharge_slab(s, order); + + return page; } static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) @@ -1349,7 +1353,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) */ alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL; - page = alloc_slab_page(alloc_gfp, node, oo); + page = alloc_slab_page(s, alloc_gfp, node, oo); if (unlikely(!page)) { oo = s->min; alloc_gfp = flags; @@ -1357,7 +1361,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) * Allocation may have failed due to fragmentation. * Try a lower order alloc if possible */ - page = alloc_slab_page(alloc_gfp, node, oo); + page = alloc_slab_page(s, alloc_gfp, node, oo); if (page) stat(s, ORDER_FALLBACK); @@ -1418,7 +1422,6 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) order = compound_order(page); inc_slabs_node(s, page_to_nid(page), page->objects); - memcg_bind_pages(s, order); page->slab_cache = s; __SetPageSlab(page); if (page->pfmemalloc) @@ -1469,11 +1472,11 @@ static void __free_slab(struct kmem_cache *s, struct page *page) __ClearPageSlabPfmemalloc(page); __ClearPageSlab(page); - memcg_release_pages(s, order); page_mapcount_reset(page); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += pages; - __free_memcg_kmem_pages(page, order); + __free_pages(page, order); + memcg_uncharge_slab(s, order); } #define need_reserve_slab_rcu \ @@ -1723,7 +1726,7 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node, struct kmem_cache_cpu *c) { void *object; - int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node; + int searchnode = (node == NUMA_NO_NODE) ? numa_mem_id() : node; object = get_partial_node(s, get_node(s, searchnode), c, flags); if (object || node != NUMA_NO_NODE) @@ -1773,19 +1776,19 @@ static inline void note_cmpxchg_failure(const char *n, #ifdef SLUB_DEBUG_CMPXCHG unsigned long actual_tid = __this_cpu_read(s->cpu_slab->tid); - printk(KERN_INFO "%s %s: cmpxchg redo ", n, s->name); + pr_info("%s %s: cmpxchg redo ", n, s->name); #ifdef CONFIG_PREEMPT if (tid_to_cpu(tid) != tid_to_cpu(actual_tid)) - printk("due to cpu change %d -> %d\n", + pr_warn("due to cpu change %d -> %d\n", tid_to_cpu(tid), tid_to_cpu(actual_tid)); else #endif if (tid_to_event(tid) != tid_to_event(actual_tid)) - printk("due to cpu running other code. Event %ld->%ld\n", + pr_warn("due to cpu running other code. Event %ld->%ld\n", tid_to_event(tid), tid_to_event(actual_tid)); else - printk("for unknown reason: actual=%lx was=%lx target=%lx\n", + pr_warn("for unknown reason: actual=%lx was=%lx target=%lx\n", actual_tid, tid, next_tid(tid)); #endif stat(s, CMPXCHG_DOUBLE_CPU_FAIL); @@ -2124,11 +2127,19 @@ static inline int node_match(struct page *page, int node) return 1; } +#ifdef CONFIG_SLUB_DEBUG static int count_free(struct page *page) { return page->objects - page->inuse; } +static inline unsigned long node_nr_objs(struct kmem_cache_node *n) +{ + return atomic_long_read(&n->total_objects); +} +#endif /* CONFIG_SLUB_DEBUG */ + +#if defined(CONFIG_SLUB_DEBUG) || defined(CONFIG_SYSFS) static unsigned long count_partial(struct kmem_cache_node *n, int (*get_count)(struct page *)) { @@ -2142,31 +2153,28 @@ static unsigned long count_partial(struct kmem_cache_node *n, spin_unlock_irqrestore(&n->list_lock, flags); return x; } - -static inline unsigned long node_nr_objs(struct kmem_cache_node *n) -{ -#ifdef CONFIG_SLUB_DEBUG - return atomic_long_read(&n->total_objects); -#else - return 0; -#endif -} +#endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */ static noinline void slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) { +#ifdef CONFIG_SLUB_DEBUG + static DEFINE_RATELIMIT_STATE(slub_oom_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); int node; - printk(KERN_WARNING - "SLUB: Unable to allocate memory on node %d (gfp=0x%x)\n", + if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slub_oom_rs)) + return; + + pr_warn("SLUB: Unable to allocate memory on node %d (gfp=0x%x)\n", nid, gfpflags); - printk(KERN_WARNING " cache: %s, object size: %d, buffer size: %d, " - "default order: %d, min order: %d\n", s->name, s->object_size, - s->size, oo_order(s->oo), oo_order(s->min)); + pr_warn(" cache: %s, object size: %d, buffer size: %d, default order: %d, min order: %d\n", + s->name, s->object_size, s->size, oo_order(s->oo), + oo_order(s->min)); if (oo_order(s->min) > get_order(s->object_size)) - printk(KERN_WARNING " %s debugging increased min order, use " - "slub_debug=O to disable.\n", s->name); + pr_warn(" %s debugging increased min order, use slub_debug=O to disable.\n", + s->name); for_each_online_node(node) { struct kmem_cache_node *n = get_node(s, node); @@ -2181,10 +2189,10 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) nr_slabs = node_nr_slabs(n); nr_objs = node_nr_objs(n); - printk(KERN_WARNING - " node %d: slabs: %ld, objs: %ld, free: %ld\n", + pr_warn(" node %d: slabs: %ld, objs: %ld, free: %ld\n", node, nr_slabs, nr_objs, nr_free); } +#endif } static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags, @@ -2201,7 +2209,7 @@ static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags, page = new_slab(s, flags, node); if (page) { - c = __this_cpu_ptr(s->cpu_slab); + c = raw_cpu_ptr(s->cpu_slab); if (c->page) flush_slab(s, c); @@ -2326,8 +2334,6 @@ redo: if (freelist) goto load_freelist; - stat(s, ALLOC_SLOWPATH); - freelist = get_freelist(s, page); if (!freelist) { @@ -2363,9 +2369,7 @@ new_slab: freelist = new_slab_objects(s, gfpflags, node, &c); if (unlikely(!freelist)) { - if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit()) - slab_out_of_memory(s, gfpflags, node); - + slab_out_of_memory(s, gfpflags, node); local_irq_restore(flags); return NULL; } @@ -2421,7 +2425,7 @@ redo: * and the retrieval of the tid. */ preempt_disable(); - c = __this_cpu_ptr(s->cpu_slab); + c = this_cpu_ptr(s->cpu_slab); /* * The transaction ids are globally unique per cpu and per operation on @@ -2434,10 +2438,10 @@ redo: object = c->freelist; page = c->page; - if (unlikely(!object || !node_match(page, node))) + if (unlikely(!object || !node_match(page, node))) { object = __slab_alloc(s, gfpflags, node, addr, c); - - else { + stat(s, ALLOC_SLOWPATH); + } else { void *next_object = get_freepointer_safe(s, object); /* @@ -2677,7 +2681,7 @@ redo: * during the cmpxchg then the free will succedd. */ preempt_disable(); - c = __this_cpu_ptr(s->cpu_slab); + c = this_cpu_ptr(s->cpu_slab); tid = c->tid; preempt_enable(); @@ -2897,10 +2901,8 @@ static void early_kmem_cache_node_alloc(int node) BUG_ON(!page); if (page_to_nid(page) != node) { - printk(KERN_ERR "SLUB: Unable to allocate memory from " - "node %d\n", node); - printk(KERN_ERR "SLUB: Allocating a useless per node structure " - "in order to be able to continue\n"); + pr_err("SLUB: Unable to allocate memory from node %d\n", node); + pr_err("SLUB: Allocating a useless per node structure in order to be able to continue\n"); } n = page->freelist; @@ -3185,8 +3187,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, for_each_object(p, s, addr, page->objects) { if (!test_bit(slab_index(p, s, addr), map)) { - printk(KERN_ERR "INFO: Object 0x%p @offset=%tu\n", - p, p - addr); + pr_err("INFO: Object 0x%p @offset=%tu\n", p, p - addr); print_tracking(s, p); } } @@ -3238,24 +3239,7 @@ static inline int kmem_cache_close(struct kmem_cache *s) int __kmem_cache_shutdown(struct kmem_cache *s) { - int rc = kmem_cache_close(s); - - if (!rc) { - /* - * Since slab_attr_store may take the slab_mutex, we should - * release the lock while removing the sysfs entry in order to - * avoid a deadlock. Because this is pretty much the last - * operation we do and the lock will be released shortly after - * that in slab_common.c, we could just move sysfs_slab_remove - * to a later point in common code. We should do that when we - * have a common sysfs framework for all allocators. - */ - mutex_unlock(&slab_mutex); - sysfs_slab_remove(s); - mutex_lock(&slab_mutex); - } - - return rc; + return kmem_cache_close(s); } /******************************************************************** @@ -3325,8 +3309,8 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node) struct page *page; void *ptr = NULL; - flags |= __GFP_COMP | __GFP_NOTRACK | __GFP_KMEMCG; - page = alloc_pages_node(node, flags, get_order(size)); + flags |= __GFP_COMP | __GFP_NOTRACK; + page = alloc_kmem_pages_node(node, flags, get_order(size)); if (page) ptr = page_address(page); @@ -3395,7 +3379,7 @@ void kfree(const void *x) if (unlikely(!PageSlab(page))) { BUG_ON(!PageCompound(page)); kfree_hook(x); - __free_memcg_kmem_pages(page, compound_order(page)); + __free_kmem_pages(page, compound_order(page)); return; } slab_free(page->slab_cache, page, object, _RET_IP_); @@ -3412,7 +3396,7 @@ EXPORT_SYMBOL(kfree); * being allocated from last increasing the chance that the last objects * are freed in them. */ -int kmem_cache_shrink(struct kmem_cache *s) +int __kmem_cache_shrink(struct kmem_cache *s) { int node; int i; @@ -3468,7 +3452,6 @@ int kmem_cache_shrink(struct kmem_cache *s) kfree(slabs_by_inuse); return 0; } -EXPORT_SYMBOL(kmem_cache_shrink); static int slab_mem_going_offline_callback(void *arg) { @@ -3476,7 +3459,7 @@ static int slab_mem_going_offline_callback(void *arg) mutex_lock(&slab_mutex); list_for_each_entry(s, &slab_caches, list) - kmem_cache_shrink(s); + __kmem_cache_shrink(s); mutex_unlock(&slab_mutex); return 0; @@ -3670,9 +3653,7 @@ void __init kmem_cache_init(void) register_cpu_notifier(&slab_notifier); #endif - printk(KERN_INFO - "SLUB: HWalign=%d, Order=%d-%d, MinObjects=%d," - " CPUs=%d, Nodes=%d\n", + pr_info("SLUB: HWalign=%d, Order=%d-%d, MinObjects=%d, CPUs=%d, Nodes=%d\n", cache_line_size(), slub_min_order, slub_max_order, slub_min_objects, nr_cpu_ids, nr_node_ids); @@ -3954,8 +3935,8 @@ static int validate_slab_node(struct kmem_cache *s, count++; } if (count != n->nr_partial) - printk(KERN_ERR "SLUB %s: %ld partial slabs counted but " - "counter=%ld\n", s->name, count, n->nr_partial); + pr_err("SLUB %s: %ld partial slabs counted but counter=%ld\n", + s->name, count, n->nr_partial); if (!(s->flags & SLAB_STORE_USER)) goto out; @@ -3965,9 +3946,8 @@ static int validate_slab_node(struct kmem_cache *s, count++; } if (count != atomic_long_read(&n->nr_slabs)) - printk(KERN_ERR "SLUB: %s %ld slabs counted but " - "counter=%ld\n", s->name, count, - atomic_long_read(&n->nr_slabs)); + pr_err("SLUB: %s %ld slabs counted but counter=%ld\n", + s->name, count, atomic_long_read(&n->nr_slabs)); out: spin_unlock_irqrestore(&n->list_lock, flags); @@ -4231,53 +4211,50 @@ static void resiliency_test(void) BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || KMALLOC_SHIFT_HIGH < 10); - printk(KERN_ERR "SLUB resiliency testing\n"); - printk(KERN_ERR "-----------------------\n"); - printk(KERN_ERR "A. Corruption after allocation\n"); + pr_err("SLUB resiliency testing\n"); + pr_err("-----------------------\n"); + pr_err("A. Corruption after allocation\n"); p = kzalloc(16, GFP_KERNEL); p[16] = 0x12; - printk(KERN_ERR "\n1. kmalloc-16: Clobber Redzone/next pointer" - " 0x12->0x%p\n\n", p + 16); + pr_err("\n1. kmalloc-16: Clobber Redzone/next pointer 0x12->0x%p\n\n", + p + 16); validate_slab_cache(kmalloc_caches[4]); /* Hmmm... The next two are dangerous */ p = kzalloc(32, GFP_KERNEL); p[32 + sizeof(void *)] = 0x34; - printk(KERN_ERR "\n2. kmalloc-32: Clobber next pointer/next slab" - " 0x34 -> -0x%p\n", p); - printk(KERN_ERR - "If allocated object is overwritten then not detectable\n\n"); + pr_err("\n2. kmalloc-32: Clobber next pointer/next slab 0x34 -> -0x%p\n", + p); + pr_err("If allocated object is overwritten then not detectable\n\n"); validate_slab_cache(kmalloc_caches[5]); p = kzalloc(64, GFP_KERNEL); p += 64 + (get_cycles() & 0xff) * sizeof(void *); *p = 0x56; - printk(KERN_ERR "\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n", - p); - printk(KERN_ERR - "If allocated object is overwritten then not detectable\n\n"); + pr_err("\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n", + p); + pr_err("If allocated object is overwritten then not detectable\n\n"); validate_slab_cache(kmalloc_caches[6]); - printk(KERN_ERR "\nB. Corruption after free\n"); + pr_err("\nB. Corruption after free\n"); p = kzalloc(128, GFP_KERNEL); kfree(p); *p = 0x78; - printk(KERN_ERR "1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p); + pr_err("1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p); validate_slab_cache(kmalloc_caches[7]); p = kzalloc(256, GFP_KERNEL); kfree(p); p[50] = 0x9a; - printk(KERN_ERR "\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", - p); + pr_err("\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", p); validate_slab_cache(kmalloc_caches[8]); p = kzalloc(512, GFP_KERNEL); kfree(p); p[512] = 0xab; - printk(KERN_ERR "\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p); + pr_err("\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p); validate_slab_cache(kmalloc_caches[9]); } #else @@ -4352,7 +4329,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s, } } - lock_memory_hotplug(); + get_online_mems(); #ifdef CONFIG_SLUB_DEBUG if (flags & SO_ALL) { for_each_node_state(node, N_NORMAL_MEMORY) { @@ -4392,7 +4369,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s, x += sprintf(buf + x, " N%d=%lu", node, nodes[node]); #endif - unlock_memory_hotplug(); + put_online_mems(); kfree(nodes); return x + sprintf(buf + x, "\n"); } @@ -5071,15 +5048,18 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s) #ifdef CONFIG_MEMCG_KMEM int i; char *buffer = NULL; + struct kmem_cache *root_cache; - if (!is_root_cache(s)) + if (is_root_cache(s)) return; + root_cache = s->memcg_params->root_cache; + /* * This mean this cache had no attribute written. Therefore, no point * in copying default values around */ - if (!s->max_attr_size) + if (!root_cache->max_attr_size) return; for (i = 0; i < ARRAY_SIZE(slab_attrs); i++) { @@ -5101,7 +5081,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s) */ if (buffer) buf = buffer; - else if (s->max_attr_size < ARRAY_SIZE(mbuf)) + else if (root_cache->max_attr_size < ARRAY_SIZE(mbuf)) buf = mbuf; else { buffer = (char *) get_zeroed_page(GFP_KERNEL); @@ -5110,7 +5090,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s) buf = buffer; } - attr->show(s->memcg_params->root_cache, buf); + attr->show(root_cache, buf); attr->store(s, buf, strlen(buf)); } @@ -5119,6 +5099,11 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s) #endif } +static void kmem_cache_release(struct kobject *k) +{ + slab_kmem_cache_release(to_slab(k)); +} + static const struct sysfs_ops slab_sysfs_ops = { .show = slab_attr_show, .store = slab_attr_store, @@ -5126,6 +5111,7 @@ static const struct sysfs_ops slab_sysfs_ops = { static struct kobj_type slab_ktype = { .sysfs_ops = &slab_sysfs_ops, + .release = kmem_cache_release, }; static int uevent_filter(struct kset *kset, struct kobject *kobj) @@ -5252,7 +5238,7 @@ out_put_kobj: goto out; } -static void sysfs_slab_remove(struct kmem_cache *s) +void sysfs_slab_remove(struct kmem_cache *s) { if (slab_state < FULL) /* @@ -5314,7 +5300,7 @@ static int __init slab_sysfs_init(void) slab_kset = kset_create_and_add("slab", &slab_uevent_ops, kernel_kobj); if (!slab_kset) { mutex_unlock(&slab_mutex); - printk(KERN_ERR "Cannot register slab subsystem.\n"); + pr_err("Cannot register slab subsystem.\n"); return -ENOSYS; } @@ -5323,8 +5309,8 @@ static int __init slab_sysfs_init(void) list_for_each_entry(s, &slab_caches, list) { err = sysfs_slab_add(s); if (err) - printk(KERN_ERR "SLUB: Unable to add boot slab %s" - " to sysfs\n", s->name); + pr_err("SLUB: Unable to add boot slab %s to sysfs\n", + s->name); } while (alias_list) { @@ -5333,8 +5319,8 @@ static int __init slab_sysfs_init(void) alias_list = alias_list->next; err = sysfs_slab_alias(al->s, al->name); if (err) - printk(KERN_ERR "SLUB: Unable to add boot slab alias" - " %s to sysfs\n", al->name); + pr_err("SLUB: Unable to add boot slab alias %s to sysfs\n", + al->name); kfree(al); } diff --git a/mm/swap.c b/mm/swap.c index 9ce43ba4498b..9e8e3472248b 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -67,7 +67,7 @@ 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) @@ -79,95 +79,88 @@ static void __put_compound_page(struct page *page) (*dtor)(page); } -static void put_compound_page(struct page *page) +/** + * Two special cases here: we could avoid taking compound_lock_irqsave + * and could skip the tail refcounting(in _mapcount). + * + * 1. Hugetlbfs page: + * + * PageHeadHuge will remain true until the compound page + * is released and enters the buddy allocator, and it could + * not be split by __split_huge_page_refcount(). + * + * So if we see PageHeadHuge set, and we have the tail page pin, + * then we could safely put head page. + * + * 2. Slab THP page: + * + * PG_slab is cleared before the slab frees the head page, and + * tail pin cannot be the last reference left on the head page, + * because the slab code is free to reuse the compound page + * after a kfree/kmem_cache_free without having to check if + * there's any tail pin left. In turn all tail pinsmust be always + * released while the head is still pinned by the slab code + * and so we know PG_slab will be still set too. + * + * So if we see PageSlab set, and we have the tail page pin, + * then we could safely put head page. + */ +static __always_inline +void put_unrefcounted_compound_page(struct page *page_head, struct page *page) { - struct page *page_head; - - if (likely(!PageTail(page))) { - if (put_page_testzero(page)) { - /* - * By the time all refcounts have been released - * split_huge_page cannot run anymore from under us. - */ - if (PageHead(page)) - __put_compound_page(page); - else - __put_single_page(page); - } - return; - } - - /* __split_huge_page_refcount can run under us */ - page_head = compound_head(page); - /* - * THP can not break up slab pages so avoid taking - * compound_lock() and skip the tail page refcounting (in - * _mapcount) too. Slab performs non-atomic bit ops on - * page->flags for better performance. In particular - * slab_unlock() in slub used to be a hot path. It is still - * hot on arches that do not support - * this_cpu_cmpxchg_double(). - * - * If "page" is part of a slab or hugetlbfs page it cannot be - * splitted and the head page cannot change from under us. And - * if "page" is part of a THP page under splitting, if the - * head page pointed by the THP tail isn't a THP head anymore, - * we'll find PageTail clear after smp_rmb() and we'll treat - * it as a single page. + * If @page is a THP tail, we must read the tail page + * flags after the head page flags. The + * __split_huge_page_refcount side enforces write memory barriers + * between clearing PageTail and before the head page + * can be freed and reallocated. */ - if (!__compound_tail_refcounted(page_head)) { + smp_rmb(); + if (likely(PageTail(page))) { /* - * If "page" is a THP tail, we must read the tail page - * flags after the head page flags. The - * split_huge_page side enforces write memory barriers - * between clearing PageTail and before the head page - * can be freed and reallocated. + * __split_huge_page_refcount cannot race + * here, see the comment above this function. */ - smp_rmb(); - if (likely(PageTail(page))) { - /* - * __split_huge_page_refcount cannot race - * here. - */ - VM_BUG_ON_PAGE(!PageHead(page_head), page_head); - VM_BUG_ON_PAGE(page_mapcount(page) != 0, page); - if (put_page_testzero(page_head)) { - /* - * If this is the tail of a slab - * compound page, the tail pin must - * not be the last reference held on - * the page, because the PG_slab - * cannot be cleared before all tail - * pins (which skips the _mapcount - * tail refcounting) have been - * released. For hugetlbfs the tail - * pin may be the last reference on - * the page instead, because - * PageHeadHuge will not go away until - * the compound page enters the buddy - * allocator. - */ - VM_BUG_ON_PAGE(PageSlab(page_head), page_head); - __put_compound_page(page_head); - } - return; - } else + VM_BUG_ON_PAGE(!PageHead(page_head), page_head); + VM_BUG_ON_PAGE(page_mapcount(page) != 0, page); + if (put_page_testzero(page_head)) { /* - * __split_huge_page_refcount run before us, - * "page" was a THP tail. The split page_head - * has been freed and reallocated as slab or - * hugetlbfs page of smaller order (only - * possible if reallocated as slab on x86). + * If this is the tail of a slab THP page, + * the tail pin must not be the last reference + * held on the page, because the PG_slab cannot + * be cleared before all tail pins (which skips + * the _mapcount tail refcounting) have been + * released. + * + * If this is the tail of a hugetlbfs page, + * the tail pin may be the last reference on + * the page instead, because PageHeadHuge will + * not go away until the compound page enters + * the buddy allocator. */ - goto out_put_single; - } + VM_BUG_ON_PAGE(PageSlab(page_head), page_head); + __put_compound_page(page_head); + } + } else + /* + * __split_huge_page_refcount run before us, + * @page was a THP tail. The split @page_head + * has been freed and reallocated as slab or + * hugetlbfs page of smaller order (only + * possible if reallocated as slab on x86). + */ + if (put_page_testzero(page)) + __put_single_page(page); +} +static __always_inline +void put_refcounted_compound_page(struct page *page_head, struct page *page) +{ if (likely(page != page_head && get_page_unless_zero(page_head))) { unsigned long flags; /* - * page_head wasn't a dangling pointer but it may not + * @page_head wasn't a dangling pointer but it may not * be a head page anymore by the time we obtain the * lock. That is ok as long as it can't be freed from * under us. @@ -178,7 +171,7 @@ static void put_compound_page(struct page *page) compound_unlock_irqrestore(page_head, flags); if (put_page_testzero(page_head)) { /* - * The head page may have been freed + * The @page_head may have been freed * and reallocated as a compound page * of smaller order and then freed * again. All we know is that it @@ -222,12 +215,51 @@ out_put_single: __put_single_page(page_head); } } else { - /* page_head is a dangling pointer */ + /* @page_head is a dangling pointer */ VM_BUG_ON_PAGE(PageTail(page), page); goto out_put_single; } } +static void put_compound_page(struct page *page) +{ + struct page *page_head; + + /* + * We see the PageCompound set and PageTail not set, so @page maybe: + * 1. hugetlbfs head page, or + * 2. THP head page. + */ + if (likely(!PageTail(page))) { + if (put_page_testzero(page)) { + /* + * By the time all refcounts have been released + * split_huge_page cannot run anymore from under us. + */ + if (PageHead(page)) + __put_compound_page(page); + else + __put_single_page(page); + } + return; + } + + /* + * We see the PageCompound set and PageTail set, so @page maybe: + * 1. a tail hugetlbfs page, or + * 2. a tail THP page, or + * 3. a split THP page. + * + * Case 3 is possible, as we may race with + * __split_huge_page_refcount tearing down a THP page. + */ + page_head = compound_head_by_tail(page); + if (!__compound_tail_refcounted(page_head)) + put_unrefcounted_compound_page(page_head, page); + else + put_refcounted_compound_page(page_head, page); +} + void put_page(struct page *page) { if (unlikely(PageCompound(page))) @@ -441,7 +473,7 @@ void rotate_reclaimable_page(struct page *page) page_cache_get(page); local_irq_save(flags); - pvec = &__get_cpu_var(lru_rotate_pvecs); + pvec = this_cpu_ptr(&lru_rotate_pvecs); if (!pagevec_add(pvec, page)) pagevec_move_tail(pvec); local_irq_restore(flags); @@ -583,12 +615,17 @@ 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) +{ + 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); @@ -598,11 +635,34 @@ void __lru_cache_add(struct page *page) pagevec_add(pvec, page); put_cpu_var(lru_add_pvec); } -EXPORT_SYMBOL(__lru_cache_add); + +/** + * 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); +} + +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) { @@ -813,7 +873,7 @@ 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); @@ -854,7 +914,7 @@ 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); } diff --git a/mm/swap_state.c b/mm/swap_state.c index e76ace30d436..2972eee184a4 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -270,7 +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; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 4a7f7e6992b6..4c524f7bd0bf 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]; @@ -505,13 +523,10 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, /* * If seek is expensive, start searching for new cluster from * start of partition, to minimize the span of allocated swap. - * But if seek is cheap, search from our current position, so - * that swap is allocated from all over the partition: if the - * Flash Translation Layer only remaps within limited zones, - * we don't want to wear out the first zone too quickly. + * If seek is cheap, that is the SWP_SOLIDSTATE si->cluster_info + * case, just handled by scan_swap_map_try_ssd_cluster() above. */ - if (!(si->flags & SWP_SOLIDSTATE)) - scan_base = offset = si->lowest_bit; + scan_base = offset = si->lowest_bit; last_in_cluster = offset + SWAPFILE_CLUSTER - 1; /* Locate the first empty (unaligned) cluster */ @@ -531,26 +546,6 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, } } - offset = si->lowest_bit; - last_in_cluster = offset + SWAPFILE_CLUSTER - 1; - - /* Locate the first empty (unaligned) cluster */ - for (; last_in_cluster < scan_base; offset++) { - if (si->swap_map[offset]) - last_in_cluster = offset + SWAPFILE_CLUSTER; - else if (offset == last_in_cluster) { - spin_lock(&si->lock); - offset -= SWAPFILE_CLUSTER - 1; - si->cluster_next = offset; - si->cluster_nr = SWAPFILE_CLUSTER - 1; - goto checks; - } - if (unlikely(--latency_ration < 0)) { - cond_resched(); - latency_ration = LATENCY_LIMIT; - } - } - offset = scan_base; spin_lock(&si->lock); si->cluster_nr = SWAPFILE_CLUSTER - 1; @@ -591,6 +586,9 @@ 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); @@ -640,71 +638,65 @@ 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) { - spin_unlock(&si->lock); - continue; - } - if (!(si->flags & SWP_WRITEOK)) { + 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; } - 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}; } @@ -766,27 +758,6 @@ 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) { @@ -828,9 +799,18 @@ 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); @@ -1765,30 +1745,37 @@ 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, @@ -1823,8 +1810,7 @@ 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)) @@ -1842,17 +1828,16 @@ 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; @@ -1864,20 +1849,21 @@ 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; @@ -1885,7 +1871,7 @@ 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 +1912,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) frontswap_map = frontswap_map_get(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); - frontswap_invalidate_area(type); + frontswap_invalidate_area(p->type); frontswap_map_set(p, NULL); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); @@ -1935,7 +1921,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) vfree(cluster_info); vfree(frontswap_map); /* Destroy swap account information */ - swap_cgroup_swapoff(type); + swap_cgroup_swapoff(p->type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { @@ -2142,8 +2128,9 @@ 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 e5cc39ab0751..6a78c814bebf 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -484,14 +484,6 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, unsigned long count = 0; int i; - /* - * Note: this function may get called on a shmem/tmpfs mapping: - * pagevec_lookup() might then return 0 prematurely (because it - * got a gangful of swap entries); but it's hardly worth worrying - * about - it can rarely have anything to free from such a mapping - * (most pages are dirty), and already skips over any difficulties. - */ - pagevec_init(&pvec, 0); while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, diff --git a/mm/util.c b/mm/util.c index f380af7ea779..d5ea733c5082 100644 --- a/mm/util.c +++ b/mm/util.c @@ -10,6 +10,7 @@ #include <linux/swapops.h> #include <linux/mman.h> #include <linux/hugetlb.h> +#include <linux/vmalloc.h> #include <asm/uaccess.h> @@ -387,6 +388,15 @@ unsigned long vm_mmap(struct file *file, unsigned long addr, } EXPORT_SYMBOL(vm_mmap); +void kvfree(const void *addr) +{ + if (is_vmalloc_addr(addr)) + vfree(addr); + else + kfree(addr); +} +EXPORT_SYMBOL(kvfree); + struct address_space *page_mapping(struct page *page) { struct address_space *mapping = page->mapping; diff --git a/mm/vmacache.c b/mm/vmacache.c index d4224b397c0e..9f25af825dec 100644 --- a/mm/vmacache.c +++ b/mm/vmacache.c @@ -17,6 +17,16 @@ void vmacache_flush_all(struct mm_struct *mm) { struct task_struct *g, *p; + /* + * Single threaded tasks need not iterate the entire + * list of process. We can avoid the flushing as well + * since the mm's seqnum was increased and don't have + * to worry about other threads' seqnum. Current's + * flush will occur upon the next lookup. + */ + if (atomic_read(&mm->mm_users) == 1) + return; + rcu_read_lock(); for_each_process_thread(g, p) { /* @@ -78,11 +88,17 @@ struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr) if (!vmacache_valid(mm)) return NULL; + count_vm_vmacache_event(VMACACHE_FIND_CALLS); + for (i = 0; i < VMACACHE_SIZE; i++) { struct vm_area_struct *vma = current->vmacache[i]; - if (vma && vma->vm_start <= addr && vma->vm_end > addr) { - BUG_ON(vma->vm_mm != mm); + if (!vma) + continue; + if (WARN_ON_ONCE(vma->vm_mm != mm)) + break; + if (vma->vm_start <= addr && vma->vm_end > addr) { + count_vm_vmacache_event(VMACACHE_FIND_HITS); return vma; } } @@ -100,11 +116,15 @@ struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, if (!vmacache_valid(mm)) return NULL; + count_vm_vmacache_event(VMACACHE_FIND_CALLS); + 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) + if (vma && vma->vm_start == start && vma->vm_end == end) { + count_vm_vmacache_event(VMACACHE_FIND_HITS); return vma; + } } return NULL; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index bf233b283319..f64632b67196 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1268,6 +1268,7 @@ void unmap_kernel_range(unsigned long addr, unsigned long size) vunmap_page_range(addr, end); flush_tlb_kernel_range(addr, end); } +EXPORT_SYMBOL_GPL(unmap_kernel_range); int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages) { @@ -1496,7 +1497,7 @@ void vfree(const void *addr) if (!addr) return; if (unlikely(in_interrupt())) { - struct vfree_deferred *p = &__get_cpu_var(vfree_deferred); + struct vfree_deferred *p = this_cpu_ptr(&vfree_deferred); if (llist_add((struct llist_node *)addr, &p->list)) schedule_work(&p->wq); } else @@ -2619,19 +2620,19 @@ static int s_show(struct seq_file *m, void *p) seq_printf(m, " phys=%llx", (unsigned long long)v->phys_addr); if (v->flags & VM_IOREMAP) - seq_printf(m, " ioremap"); + seq_puts(m, " ioremap"); if (v->flags & VM_ALLOC) - seq_printf(m, " vmalloc"); + seq_puts(m, " vmalloc"); if (v->flags & VM_MAP) - seq_printf(m, " vmap"); + seq_puts(m, " vmap"); if (v->flags & VM_USERMAP) - seq_printf(m, " user"); + seq_puts(m, " user"); if (v->flags & VM_VPAGES) - seq_printf(m, " vpages"); + seq_puts(m, " vpages"); show_numa_info(m, v); seq_putc(m, '\n'); diff --git a/mm/vmscan.c b/mm/vmscan.c index 3f56c8deb3c0..e01ded365440 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -11,6 +11,8 @@ * Multiqueue VM started 5.8.00, Rik van Riel. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/mm.h> #include <linux/module.h> #include <linux/gfp.h> @@ -43,6 +45,7 @@ #include <linux/sysctl.h> #include <linux/oom.h> #include <linux/prefetch.h> +#include <linux/printk.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -83,6 +86,9 @@ struct scan_control { /* Scan (total_size >> priority) pages at once */ int priority; + /* anon vs. file LRUs scanning "ratio" */ + int swappiness; + /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. @@ -324,7 +330,7 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, else new_nr = atomic_long_read(&shrinker->nr_deferred[nid]); - trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr); + trace_mm_shrink_slab_end(shrinker, nid, freed, nr, new_nr, total_scan); return freed; } @@ -477,7 +483,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, if (page_has_private(page)) { if (try_to_free_buffers(page)) { ClearPageDirty(page); - printk("%s: orphaned page\n", __func__); + pr_info("%s: orphaned page\n", __func__); return PAGE_CLEAN; } } @@ -1121,7 +1127,7 @@ keep: VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), 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); @@ -1439,6 +1445,19 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) } /* + * If a kernel thread (such as nfsd for loop-back mounts) services + * a backing device by writing to the page cache it sets PF_LESS_THROTTLE. + * In that case we should only throttle if the backing device it is + * writing to is congested. In other cases it is safe to throttle. + */ +static int current_may_throttle(void) +{ + return !(current->flags & PF_LESS_THROTTLE) || + current->backing_dev_info == NULL || + bdi_write_congested(current->backing_dev_info); +} + +/* * shrink_inactive_list() is a helper for shrink_zone(). It returns the number * of reclaimed pages */ @@ -1519,7 +1538,7 @@ 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 @@ -1554,19 +1573,18 @@ 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 && current_may_throttle()) congestion_wait(BLK_RW_ASYNC, HZ/10); } @@ -1575,7 +1593,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * is congested. Allow kswapd to continue until it starts encountering * unqueued dirty pages or cycling through the LRU too quickly. */ - if (!sc->hibernation_mode && !current_is_kswapd()) + if (!sc->hibernation_mode && !current_is_kswapd() && + current_may_throttle()) wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10); trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id, @@ -1740,7 +1759,7 @@ 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 @@ -1830,13 +1849,6 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } -static int vmscan_swappiness(struct scan_control *sc) -{ - if (global_reclaim(sc)) - return vm_swappiness; - return mem_cgroup_swappiness(sc->target_mem_cgroup); -} - enum scan_balance { SCAN_EQUAL, SCAN_FRACT, @@ -1866,6 +1878,8 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, bool force_scan = false; unsigned long ap, fp; enum lru_list lru; + bool some_scanned; + int pass; /* * If the zone or memcg is small, nr[l] can be 0. This @@ -1895,7 +1909,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * using the memory controller's swap limit feature would be * too expensive. */ - if (!global_reclaim(sc) && !vmscan_swappiness(sc)) { + if (!global_reclaim(sc) && !sc->swappiness) { scan_balance = SCAN_FILE; goto out; } @@ -1905,7 +1919,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * system is close to OOM, scan both anon and file equally * (unless the swappiness setting disagrees with swapping). */ - if (!sc->priority && vmscan_swappiness(sc)) { + if (!sc->priority && sc->swappiness) { scan_balance = SCAN_EQUAL; goto out; } @@ -1916,6 +1930,24 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, get_lru_size(lruvec, LRU_INACTIVE_FILE); /* + * Prevent the reclaimer from falling into the cache trap: as + * cache pages start out inactive, every cache fault will tip + * the scan balance towards the file LRU. And as the file LRU + * shrinks, so does the window for rotation from references. + * This means we have a runaway feedback loop where a tiny + * thrashing file LRU becomes infinitely more attractive than + * anon pages. Try to detect this based on file LRU size. + */ + if (global_reclaim(sc)) { + unsigned long free = zone_page_state(zone, NR_FREE_PAGES); + + if (unlikely(file + free <= high_wmark_pages(zone))) { + scan_balance = SCAN_ANON; + goto out; + } + } + + /* * There is enough inactive page cache, do not reclaim * anything from the anonymous working set right now. */ @@ -1930,7 +1962,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * With swappiness at 100, anonymous and file have the same priority. * This scanning priority is essentially the inverse of IO cost. */ - anon_prio = vmscan_swappiness(sc); + anon_prio = sc->swappiness; file_prio = 200 - anon_prio; /* @@ -1971,39 +2003,49 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, fraction[1] = fp; denominator = ap + fp + 1; out: - for_each_evictable_lru(lru) { - int file = is_file_lru(lru); - unsigned long size; - unsigned long scan; + some_scanned = false; + /* Only use force_scan on second pass. */ + for (pass = 0; !some_scanned && pass < 2; pass++) { + for_each_evictable_lru(lru) { + int file = is_file_lru(lru); + unsigned long size; + unsigned long scan; - size = get_lru_size(lruvec, lru); - scan = size >> sc->priority; + size = get_lru_size(lruvec, lru); + scan = size >> sc->priority; - if (!scan && force_scan) - scan = min(size, SWAP_CLUSTER_MAX); + if (!scan && pass && force_scan) + scan = min(size, SWAP_CLUSTER_MAX); - switch (scan_balance) { - case SCAN_EQUAL: - /* Scan lists relative to size */ - break; - case SCAN_FRACT: + switch (scan_balance) { + case SCAN_EQUAL: + /* Scan lists relative to size */ + break; + case SCAN_FRACT: + /* + * Scan types proportional to swappiness and + * their relative recent reclaim efficiency. + */ + scan = div64_u64(scan * fraction[file], + denominator); + break; + case SCAN_FILE: + case SCAN_ANON: + /* Scan one type exclusively */ + if ((scan_balance == SCAN_FILE) != file) + scan = 0; + break; + default: + /* Look ma, no brain */ + BUG(); + } + nr[lru] = scan; /* - * Scan types proportional to swappiness and - * their relative recent reclaim efficiency. + * Skip the second pass and don't force_scan, + * if we found something to scan. */ - scan = div64_u64(scan * fraction[file], denominator); - break; - case SCAN_FILE: - case SCAN_ANON: - /* Scan one type exclusively */ - if ((scan_balance == SCAN_FILE) != file) - scan = 0; - break; - default: - /* Look ma, no brain */ - BUG(); + some_scanned |= !!scan; } - nr[lru] = scan; } } @@ -2019,13 +2061,27 @@ 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]) { @@ -2046,17 +2102,8 @@ 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. @@ -2064,6 +2111,15 @@ 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; @@ -2206,6 +2262,7 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc) lruvec = mem_cgroup_zone_lruvec(zone, memcg); + sc->swappiness = mem_cgroup_swappiness(memcg); shrink_lruvec(lruvec, sc); /* @@ -2250,9 +2307,8 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) * there is a buffer of free pages available to give compaction * a reasonable chance of completing and allocating the page */ - balance_gap = min(low_wmark_pages(zone), - (zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / - KSWAPD_ZONE_BALANCE_GAP_RATIO); + balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP( + zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO)); watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order); watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0); @@ -2507,10 +2563,17 @@ 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 */ @@ -2535,9 +2598,9 @@ 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 @@ -2556,10 +2619,34 @@ 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 */ @@ -2642,6 +2729,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, .may_swap = !noswap, .order = 0, .priority = 0, + .swappiness = mem_cgroup_swappiness(memcg), .target_mem_cgroup = memcg, }; struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); @@ -2873,9 +2961,8 @@ static bool kswapd_shrink_zone(struct zone *zone, * high wmark plus a "gap" where the gap is either the low * watermark or 1% of the zone, whichever is smaller. */ - balance_gap = min(low_wmark_pages(zone), - (zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / - KSWAPD_ZONE_BALANCE_GAP_RATIO); + balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP( + zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO)); /* * If there is no low memory pressure or the zone is balanced then no @@ -3284,7 +3371,10 @@ static int kswapd(void *p) } } + tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD); current->reclaim_state = NULL; + lockdep_clear_current_reclaim_state(); + return 0; } @@ -3404,7 +3494,7 @@ int kswapd_run(int nid) /* * Called by memory hotplug when all memory in a node is offlined. Caller must - * hold lock_memory_hotplug(). + * hold mem_hotplug_begin/end(). */ void kswapd_stop(int nid) { diff --git a/mm/vmstat.c b/mm/vmstat.c index 302dd076b8bf..b37bd49bfd55 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -207,7 +207,9 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, } /* - * For use when we know that interrupts are disabled. + * For use when we know that interrupts are disabled, + * or when we know that preemption is disabled and that + * particular counter cannot be updated from interrupt context. */ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, int delta) @@ -489,7 +491,7 @@ static void refresh_cpu_vm_stats(void) continue; if (__this_cpu_read(p->pcp.count)) - drain_zone_pages(zone, __this_cpu_ptr(&p->pcp)); + drain_zone_pages(zone, this_cpu_ptr(&p->pcp)); #endif } fold_diff(global_diff); @@ -866,6 +868,10 @@ const char * const vmstat_text[] = { "nr_tlb_local_flush_one", #endif /* CONFIG_DEBUG_TLBFLUSH */ +#ifdef CONFIG_DEBUG_VM_VMACACHE + "vmacache_find_calls", + "vmacache_find_hits", +#endif #endif /* CONFIG_VM_EVENTS_COUNTERS */ }; #endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */ @@ -1226,7 +1232,7 @@ int sysctl_stat_interval __read_mostly = HZ; static void vmstat_update(struct work_struct *w) { refresh_cpu_vm_stats(); - schedule_delayed_work(&__get_cpu_var(vmstat_work), + schedule_delayed_work(this_cpu_ptr(&vmstat_work), round_jiffies_relative(sysctl_stat_interval)); } diff --git a/mm/zbud.c b/mm/zbud.c index 9451361e6aa7..01df13a7e2e1 100644 --- a/mm/zbud.c +++ b/mm/zbud.c @@ -247,7 +247,7 @@ void zbud_destroy_pool(struct zbud_pool *pool) * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate * a new page. */ -int zbud_alloc(struct zbud_pool *pool, int size, gfp_t gfp, +int zbud_alloc(struct zbud_pool *pool, unsigned int size, gfp_t gfp, unsigned long *handle) { int chunks, i, freechunks; @@ -255,7 +255,7 @@ int zbud_alloc(struct zbud_pool *pool, int size, gfp_t gfp, enum buddy bud; struct page *page; - if (size <= 0 || gfp & __GFP_HIGHMEM) + if (!size || (gfp & __GFP_HIGHMEM)) return -EINVAL; if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE) return -ENOSPC; diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 36b4591a7a2d..fe78189624cf 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -141,7 +141,7 @@ #define ZS_MAX_ALLOC_SIZE PAGE_SIZE /* - * On systems with 4K page size, this gives 254 size classes! There is a + * On systems with 4K page size, this gives 255 size classes! There is a * trader-off here: * - Large number of size classes is potentially wasteful as free page are * spread across these classes @@ -1082,7 +1082,7 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) class = &pool->size_class[class_idx]; off = obj_idx_to_offset(page, obj_idx, class->size); - area = &__get_cpu_var(zs_map_area); + area = this_cpu_ptr(&zs_map_area); if (off + class->size <= PAGE_SIZE) kunmap_atomic(area->vm_addr); else { diff --git a/mm/zswap.c b/mm/zswap.c index aeaef0fb5624..008388fe7b0f 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -347,7 +347,7 @@ static int __zswap_cpu_notifier(unsigned long action, unsigned long cpu) return NOTIFY_BAD; } *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = tfm; - dst = kmalloc(PAGE_SIZE * 2, GFP_KERNEL); + dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); if (!dst) { pr_err("can't allocate compressor buffer\n"); crypto_free_comp(tfm); |