diff options
Diffstat (limited to 'mm')
63 files changed, 1746 insertions, 1349 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 9b8fccb969dc..beb7a455915d 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -312,7 +312,6 @@ config NEED_BOUNCE_POOL config NR_QUICK int depends on QUICKLIST - default "2" if AVR32 default "1" config VIRT_TO_BUS diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index 79d0fd13b5b3..5b0adf1435de 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -42,7 +42,6 @@ config DEBUG_PAGEALLOC_ENABLE_DEFAULT config PAGE_POISONING bool "Poison pages after freeing" - select PAGE_EXTENSION select PAGE_POISONING_NO_SANITY if HIBERNATION ---help--- Fill the pages with poison patterns after free_pages() and verify diff --git a/mm/backing-dev.c b/mm/backing-dev.c index c6f2a37028c2..f028a9a472fd 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -12,8 +12,6 @@ #include <linux/device.h> #include <trace/events/writeback.h> -static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); - struct backing_dev_info noop_backing_dev_info = { .name = "noop", .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, @@ -242,6 +240,8 @@ static __init int bdi_class_init(void) } postcore_initcall(bdi_class_init); +static int bdi_init(struct backing_dev_info *bdi); + static int __init default_bdi_init(void) { int err; @@ -294,6 +294,8 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, memset(wb, 0, sizeof(*wb)); + if (wb != &bdi->wb) + bdi_get(bdi); wb->bdi = bdi; wb->last_old_flush = jiffies; INIT_LIST_HEAD(&wb->b_dirty); @@ -314,8 +316,10 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, wb->dirty_sleep = jiffies; wb->congested = wb_congested_get_create(bdi, blkcg_id, gfp); - if (!wb->congested) - return -ENOMEM; + if (!wb->congested) { + err = -ENOMEM; + goto out_put_bdi; + } err = fprop_local_init_percpu(&wb->completions, gfp); if (err) @@ -335,9 +339,14 @@ out_destroy_stat: fprop_local_destroy_percpu(&wb->completions); out_put_cong: wb_congested_put(wb->congested); +out_put_bdi: + if (wb != &bdi->wb) + bdi_put(bdi); return err; } +static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb); + /* * Remove bdi from the global list and shutdown any threads we have running */ @@ -347,10 +356,18 @@ static void wb_shutdown(struct bdi_writeback *wb) spin_lock_bh(&wb->work_lock); if (!test_and_clear_bit(WB_registered, &wb->state)) { spin_unlock_bh(&wb->work_lock); + /* + * Wait for wb shutdown to finish if someone else is just + * running wb_shutdown(). Otherwise we could proceed to wb / + * bdi destruction before wb_shutdown() is finished. + */ + wait_on_bit(&wb->state, WB_shutting_down, TASK_UNINTERRUPTIBLE); return; } + set_bit(WB_shutting_down, &wb->state); spin_unlock_bh(&wb->work_lock); + cgwb_remove_from_bdi_list(wb); /* * Drain work list and shutdown the delayed_work. !WB_registered * tells wb_workfn() that @wb is dying and its work_list needs to @@ -359,6 +376,12 @@ static void wb_shutdown(struct bdi_writeback *wb) mod_delayed_work(bdi_wq, &wb->dwork, 0); flush_delayed_work(&wb->dwork); WARN_ON(!list_empty(&wb->work_list)); + /* + * Make sure bit gets cleared after shutdown is finished. Matches with + * the barrier provided by test_and_clear_bit() above. + */ + smp_wmb(); + clear_bit(WB_shutting_down, &wb->state); } static void wb_exit(struct bdi_writeback *wb) @@ -372,6 +395,8 @@ static void wb_exit(struct bdi_writeback *wb) fprop_local_destroy_percpu(&wb->completions); wb_congested_put(wb->congested); + if (wb != &wb->bdi->wb) + bdi_put(wb->bdi); } #ifdef CONFIG_CGROUP_WRITEBACK @@ -381,11 +406,9 @@ static void wb_exit(struct bdi_writeback *wb) /* * cgwb_lock protects bdi->cgwb_tree, bdi->cgwb_congested_tree, * blkcg->cgwb_list, and memcg->cgwb_list. bdi->cgwb_tree is also RCU - * protected. cgwb_release_wait is used to wait for the completion of cgwb - * releases from bdi destruction path. + * protected. */ static DEFINE_SPINLOCK(cgwb_lock); -static DECLARE_WAIT_QUEUE_HEAD(cgwb_release_wait); /** * wb_congested_get_create - get or create a wb_congested @@ -438,7 +461,7 @@ retry: return NULL; atomic_set(&new_congested->refcnt, 0); - new_congested->bdi = bdi; + new_congested->__bdi = bdi; new_congested->blkcg_id = blkcg_id; goto retry; @@ -466,10 +489,10 @@ void wb_congested_put(struct bdi_writeback_congested *congested) } /* bdi might already have been destroyed leaving @congested unlinked */ - if (congested->bdi) { + if (congested->__bdi) { rb_erase(&congested->rb_node, - &congested->bdi->cgwb_congested_tree); - congested->bdi = NULL; + &congested->__bdi->cgwb_congested_tree); + congested->__bdi = NULL; } spin_unlock_irqrestore(&cgwb_lock, flags); @@ -480,11 +503,6 @@ static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); - struct backing_dev_info *bdi = wb->bdi; - - spin_lock_irq(&cgwb_lock); - list_del_rcu(&wb->bdi_node); - spin_unlock_irq(&cgwb_lock); wb_shutdown(wb); @@ -495,9 +513,6 @@ static void cgwb_release_workfn(struct work_struct *work) percpu_ref_exit(&wb->refcnt); wb_exit(wb); kfree_rcu(wb, rcu); - - if (atomic_dec_and_test(&bdi->usage_cnt)) - wake_up_all(&cgwb_release_wait); } static void cgwb_release(struct percpu_ref *refcnt) @@ -517,6 +532,13 @@ static void cgwb_kill(struct bdi_writeback *wb) percpu_ref_kill(&wb->refcnt); } +static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) +{ + spin_lock_irq(&cgwb_lock); + list_del_rcu(&wb->bdi_node); + spin_unlock_irq(&cgwb_lock); +} + static int cgwb_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) { @@ -580,7 +602,6 @@ static int cgwb_create(struct backing_dev_info *bdi, /* we might have raced another instance of this function */ ret = radix_tree_insert(&bdi->cgwb_tree, memcg_css->id, wb); if (!ret) { - atomic_inc(&bdi->usage_cnt); list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); @@ -670,7 +691,6 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); bdi->cgwb_congested_tree = RB_ROOT; - atomic_set(&bdi->usage_cnt, 1); ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); if (!ret) { @@ -680,29 +700,26 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) return ret; } -static void cgwb_bdi_destroy(struct backing_dev_info *bdi) +static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { struct radix_tree_iter iter; void **slot; + struct bdi_writeback *wb; WARN_ON(test_bit(WB_registered, &bdi->wb.state)); spin_lock_irq(&cgwb_lock); radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); - spin_unlock_irq(&cgwb_lock); - /* - * All cgwb's must be shutdown and released before returning. Drain - * the usage counter to wait for all cgwb's ever created on @bdi. - */ - atomic_dec(&bdi->usage_cnt); - wait_event(cgwb_release_wait, !atomic_read(&bdi->usage_cnt)); - /* - * Grab back our reference so that we hold it when @bdi gets - * re-registered. - */ - atomic_inc(&bdi->usage_cnt); + while (!list_empty(&bdi->wb_list)) { + wb = list_first_entry(&bdi->wb_list, struct bdi_writeback, + bdi_node); + spin_unlock_irq(&cgwb_lock); + wb_shutdown(wb); + spin_lock_irq(&cgwb_lock); + } + spin_unlock_irq(&cgwb_lock); } /** @@ -752,11 +769,18 @@ static void cgwb_bdi_exit(struct backing_dev_info *bdi) rb_entry(rbn, struct bdi_writeback_congested, rb_node); rb_erase(rbn, &bdi->cgwb_congested_tree); - congested->bdi = NULL; /* mark @congested unlinked */ + congested->__bdi = NULL; /* mark @congested unlinked */ } spin_unlock_irq(&cgwb_lock); } +static void cgwb_bdi_register(struct backing_dev_info *bdi) +{ + spin_lock_irq(&cgwb_lock); + list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); + spin_unlock_irq(&cgwb_lock); +} + #else /* CONFIG_CGROUP_WRITEBACK */ static int cgwb_bdi_init(struct backing_dev_info *bdi) @@ -777,16 +801,26 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) return 0; } -static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { } +static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { } static void cgwb_bdi_exit(struct backing_dev_info *bdi) { wb_congested_put(bdi->wb_congested); } +static void cgwb_bdi_register(struct backing_dev_info *bdi) +{ + list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); +} + +static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) +{ + list_del_rcu(&wb->bdi_node); +} + #endif /* CONFIG_CGROUP_WRITEBACK */ -int bdi_init(struct backing_dev_info *bdi) +static int bdi_init(struct backing_dev_info *bdi) { int ret; @@ -802,11 +836,8 @@ int bdi_init(struct backing_dev_info *bdi) ret = cgwb_bdi_init(bdi); - list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); - return ret; } -EXPORT_SYMBOL(bdi_init); struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id) { @@ -823,22 +854,20 @@ struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id) } return bdi; } +EXPORT_SYMBOL(bdi_alloc_node); -int bdi_register(struct backing_dev_info *bdi, struct device *parent, - const char *fmt, ...) +int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) { - va_list args; struct device *dev; if (bdi->dev) /* The driver needs to use separate queues per device */ return 0; - va_start(args, fmt); - dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args); - va_end(args); + dev = device_create_vargs(bdi_class, NULL, MKDEV(0, 0), bdi, fmt, args); if (IS_ERR(dev)) return PTR_ERR(dev); + cgwb_bdi_register(bdi); bdi->dev = dev; bdi_debug_register(bdi, dev_name(dev)); @@ -851,20 +880,25 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, trace_writeback_bdi_register(bdi); return 0; } -EXPORT_SYMBOL(bdi_register); +EXPORT_SYMBOL(bdi_register_va); -int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev) +int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...) { - return bdi_register(bdi, NULL, "%u:%u", MAJOR(dev), MINOR(dev)); + va_list args; + int ret; + + va_start(args, fmt); + ret = bdi_register_va(bdi, fmt, args); + va_end(args); + return ret; } -EXPORT_SYMBOL(bdi_register_dev); +EXPORT_SYMBOL(bdi_register); int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner) { int rc; - rc = bdi_register(bdi, NULL, "%u:%u", MAJOR(owner->devt), - MINOR(owner->devt)); + rc = bdi_register(bdi, "%u:%u", MAJOR(owner->devt), MINOR(owner->devt)); if (rc) return rc; /* Leaking owner reference... */ @@ -892,7 +926,7 @@ void bdi_unregister(struct backing_dev_info *bdi) /* make sure nobody finds us on the bdi_list anymore */ bdi_remove_from_list(bdi); wb_shutdown(&bdi->wb); - cgwb_bdi_destroy(bdi); + cgwb_bdi_unregister(bdi); if (bdi->dev) { bdi_debug_unregister(bdi); @@ -906,19 +940,16 @@ void bdi_unregister(struct backing_dev_info *bdi) } } -static void bdi_exit(struct backing_dev_info *bdi) -{ - WARN_ON_ONCE(bdi->dev); - wb_exit(&bdi->wb); - cgwb_bdi_exit(bdi); -} - static void release_bdi(struct kref *ref) { struct backing_dev_info *bdi = container_of(ref, struct backing_dev_info, refcnt); - bdi_exit(bdi); + if (test_bit(WB_registered, &bdi->wb.state)) + bdi_unregister(bdi); + WARN_ON_ONCE(bdi->dev); + wb_exit(&bdi->wb); + cgwb_bdi_exit(bdi); kfree(bdi); } @@ -926,38 +957,7 @@ void bdi_put(struct backing_dev_info *bdi) { kref_put(&bdi->refcnt, release_bdi); } - -void bdi_destroy(struct backing_dev_info *bdi) -{ - bdi_unregister(bdi); - bdi_exit(bdi); -} -EXPORT_SYMBOL(bdi_destroy); - -/* - * For use from filesystems to quickly init and register a bdi associated - * with dirty writeback - */ -int bdi_setup_and_register(struct backing_dev_info *bdi, char *name) -{ - int err; - - bdi->name = name; - bdi->capabilities = 0; - err = bdi_init(bdi); - if (err) - return err; - - err = bdi_register(bdi, NULL, "%.28s-%ld", name, - atomic_long_inc_return(&bdi_seq)); - if (err) { - bdi_destroy(bdi); - return err; - } - - return 0; -} -EXPORT_SYMBOL(bdi_setup_and_register); +EXPORT_SYMBOL(bdi_put); static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), @@ -53,6 +53,11 @@ unsigned long cma_get_size(const struct cma *cma) return cma->count << PAGE_SHIFT; } +const char *cma_get_name(const struct cma *cma) +{ + return cma->name ? cma->name : "(undefined)"; +} + static unsigned long cma_bitmap_aligned_mask(const struct cma *cma, int align_order) { @@ -168,6 +173,7 @@ core_initcall(cma_init_reserved_areas); */ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, unsigned int order_per_bit, + const char *name, struct cma **res_cma) { struct cma *cma; @@ -198,6 +204,13 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, * subsystems (like slab allocator) are available. */ cma = &cma_areas[cma_area_count]; + if (name) { + cma->name = name; + } else { + cma->name = kasprintf(GFP_KERNEL, "cma%d\n", cma_area_count); + if (!cma->name) + return -ENOMEM; + } cma->base_pfn = PFN_DOWN(base); cma->count = size >> PAGE_SHIFT; cma->order_per_bit = order_per_bit; @@ -229,7 +242,7 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, int __init cma_declare_contiguous(phys_addr_t base, phys_addr_t size, phys_addr_t limit, phys_addr_t alignment, unsigned int order_per_bit, - bool fixed, struct cma **res_cma) + bool fixed, const char *name, struct cma **res_cma) { phys_addr_t memblock_end = memblock_end_of_DRAM(); phys_addr_t highmem_start; @@ -335,7 +348,7 @@ int __init cma_declare_contiguous(phys_addr_t base, base = addr; } - ret = cma_init_reserved_mem(base, size, order_per_bit, res_cma); + ret = cma_init_reserved_mem(base, size, order_per_bit, name, res_cma); if (ret) goto err; @@ -491,3 +504,17 @@ bool cma_release(struct cma *cma, const struct page *pages, unsigned int count) return true; } + +int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data) +{ + int i; + + for (i = 0; i < cma_area_count; i++) { + int ret = it(&cma_areas[i], data); + + if (ret) + return ret; + } + + return 0; +} @@ -11,6 +11,7 @@ struct cma { struct hlist_head mem_head; spinlock_t mem_head_lock; #endif + const char *name; }; extern struct cma cma_areas[MAX_CMA_AREAS]; diff --git a/mm/cma_debug.c b/mm/cma_debug.c index ffc0c3d0ae64..595b757bef72 100644 --- a/mm/cma_debug.c +++ b/mm/cma_debug.c @@ -167,7 +167,7 @@ static void cma_debugfs_add_one(struct cma *cma, int idx) char name[16]; int u32s; - sprintf(name, "cma-%d", idx); + sprintf(name, "cma-%s", cma->name); tmp = debugfs_create_dir(name, cma_debugfs_root); diff --git a/mm/compaction.c b/mm/compaction.c index 81e1eaa2a2cf..613c59e928cb 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -89,11 +89,6 @@ static void map_pages(struct list_head *list) list_splice(&tmp_list, list); } -static inline bool migrate_async_suitable(int migratetype) -{ - return is_migrate_cma(migratetype) || migratetype == MIGRATE_MOVABLE; -} - #ifdef CONFIG_COMPACTION int PageMovable(struct page *page) @@ -988,13 +983,26 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, #endif /* CONFIG_COMPACTION || CONFIG_CMA */ #ifdef CONFIG_COMPACTION -/* Returns true if the page is within a block suitable for migration to */ -static bool suitable_migration_target(struct compact_control *cc, +static bool suitable_migration_source(struct compact_control *cc, struct page *page) { - if (cc->ignore_block_suitable) + int block_mt; + + if ((cc->mode != MIGRATE_ASYNC) || !cc->direct_compaction) return true; + block_mt = get_pageblock_migratetype(page); + + if (cc->migratetype == MIGRATE_MOVABLE) + return is_migrate_movable(block_mt); + else + return block_mt == cc->migratetype; +} + +/* Returns true if the page is within a block suitable for migration to */ +static bool suitable_migration_target(struct compact_control *cc, + struct page *page) +{ /* If the page is a large free page, then disallow migration */ if (PageBuddy(page)) { /* @@ -1006,8 +1014,11 @@ static bool suitable_migration_target(struct compact_control *cc, return false; } + if (cc->ignore_block_suitable) + return true; + /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ - if (migrate_async_suitable(get_pageblock_migratetype(page))) + if (is_migrate_movable(get_pageblock_migratetype(page))) return true; /* Otherwise skip the block */ @@ -1242,8 +1253,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, * Async compaction is optimistic to see if the minimum amount * of work satisfies the allocation. */ - if (cc->mode == MIGRATE_ASYNC && - !migrate_async_suitable(get_pageblock_migratetype(page))) + if (!suitable_migration_source(cc, page)) continue; /* Perform the isolation */ @@ -1276,11 +1286,11 @@ static inline bool is_via_compact_memory(int order) return order == -1; } -static enum compact_result __compact_finished(struct zone *zone, struct compact_control *cc, - const int migratetype) +static enum compact_result __compact_finished(struct zone *zone, + struct compact_control *cc) { unsigned int order; - unsigned long watermark; + const int migratetype = cc->migratetype; if (cc->contended || fatal_signal_pending(current)) return COMPACT_CONTENDED; @@ -1308,12 +1318,16 @@ static enum compact_result __compact_finished(struct zone *zone, struct compact_ if (is_via_compact_memory(cc->order)) return COMPACT_CONTINUE; - /* Compaction run is not finished if the watermark is not met */ - watermark = zone->watermark[cc->alloc_flags & ALLOC_WMARK_MASK]; - - if (!zone_watermark_ok(zone, cc->order, watermark, cc->classzone_idx, - cc->alloc_flags)) - return COMPACT_CONTINUE; + if (cc->finishing_block) { + /* + * We have finished the pageblock, but better check again that + * we really succeeded. + */ + if (IS_ALIGNED(cc->migrate_pfn, pageblock_nr_pages)) + cc->finishing_block = false; + else + return COMPACT_CONTINUE; + } /* Direct compactor: Is a suitable page free? */ for (order = cc->order; order < MAX_ORDER; order++) { @@ -1335,20 +1349,40 @@ static enum compact_result __compact_finished(struct zone *zone, struct compact_ * other migratetype buddy lists. */ if (find_suitable_fallback(area, order, migratetype, - true, &can_steal) != -1) - return COMPACT_SUCCESS; + true, &can_steal) != -1) { + + /* movable pages are OK in any pageblock */ + if (migratetype == MIGRATE_MOVABLE) + return COMPACT_SUCCESS; + + /* + * We are stealing for a non-movable allocation. Make + * sure we finish compacting the current pageblock + * first so it is as free as possible and we won't + * have to steal another one soon. This only applies + * to sync compaction, as async compaction operates + * on pageblocks of the same migratetype. + */ + if (cc->mode == MIGRATE_ASYNC || + IS_ALIGNED(cc->migrate_pfn, + pageblock_nr_pages)) { + return COMPACT_SUCCESS; + } + + cc->finishing_block = true; + return COMPACT_CONTINUE; + } } return COMPACT_NO_SUITABLE_PAGE; } static enum compact_result compact_finished(struct zone *zone, - struct compact_control *cc, - const int migratetype) + struct compact_control *cc) { int ret; - ret = __compact_finished(zone, cc, migratetype); + ret = __compact_finished(zone, cc); trace_mm_compaction_finished(zone, cc->order, ret); if (ret == COMPACT_NO_SUITABLE_PAGE) ret = COMPACT_CONTINUE; @@ -1481,9 +1515,9 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro enum compact_result ret; unsigned long start_pfn = zone->zone_start_pfn; unsigned long end_pfn = zone_end_pfn(zone); - const int migratetype = gfpflags_to_migratetype(cc->gfp_mask); const bool sync = cc->mode != MIGRATE_ASYNC; + cc->migratetype = gfpflags_to_migratetype(cc->gfp_mask); ret = compaction_suitable(zone, cc->order, cc->alloc_flags, cc->classzone_idx); /* Compaction is likely to fail */ @@ -1533,8 +1567,7 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro migrate_prep_local(); - while ((ret = compact_finished(zone, cc, migratetype)) == - COMPACT_CONTINUE) { + while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) { int err; switch (isolate_migratepages(zone, cc)) { diff --git a/mm/filemap.c b/mm/filemap.c index 1694623a6289..6f1be573a5e6 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -519,7 +519,7 @@ EXPORT_SYMBOL(filemap_write_and_wait); * * Write out and wait upon file offsets lstart->lend, inclusive. * - * Note that `lend' is inclusive (describes the last byte to be written) so + * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). */ int filemap_write_and_wait_range(struct address_space *mapping, @@ -1277,12 +1277,14 @@ EXPORT_SYMBOL(find_lock_entry); * * PCG flags modify how the page is returned. * - * 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. + * @fgp_flags can be: + * + * - 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. * * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even * if the GFP flags specified for FGP_CREAT are atomic. @@ -2033,7 +2035,6 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) if (iocb->ki_flags & IOCB_DIRECT) { struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - struct iov_iter data = *iter; loff_t size; size = i_size_read(inode); @@ -2044,11 +2045,12 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) file_accessed(file); - retval = mapping->a_ops->direct_IO(iocb, &data); + retval = mapping->a_ops->direct_IO(iocb, iter); if (retval >= 0) { iocb->ki_pos += retval; - iov_iter_advance(iter, retval); + count -= retval; } + iov_iter_revert(iter, count - iov_iter_count(iter)); /* * Btrfs can have a short DIO read if we encounter @@ -2059,7 +2061,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ - if (retval < 0 || !iov_iter_count(iter) || iocb->ki_pos >= size || + if (retval < 0 || !count || iocb->ki_pos >= size || IS_DAX(inode)) goto out; } @@ -2202,12 +2204,12 @@ int filemap_fault(struct vm_fault *vmf) struct file_ra_state *ra = &file->f_ra; struct inode *inode = mapping->host; pgoff_t offset = vmf->pgoff; + pgoff_t max_off; struct page *page; - loff_t size; int ret = 0; - size = round_up(i_size_read(inode), PAGE_SIZE); - if (offset >= size >> PAGE_SHIFT) + max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + if (unlikely(offset >= max_off)) return VM_FAULT_SIGBUS; /* @@ -2256,8 +2258,8 @@ retry_find: * Found the page and have a reference on it. * We must recheck i_size under page lock. */ - size = round_up(i_size_read(inode), PAGE_SIZE); - if (unlikely(offset >= size >> PAGE_SHIFT)) { + max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + if (unlikely(offset >= max_off)) { unlock_page(page); put_page(page); return VM_FAULT_SIGBUS; @@ -2323,7 +2325,7 @@ void filemap_map_pages(struct vm_fault *vmf, struct file *file = vmf->vma->vm_file; struct address_space *mapping = file->f_mapping; pgoff_t last_pgoff = start_pgoff; - loff_t size; + unsigned long max_idx; struct page *head, *page; rcu_read_lock(); @@ -2369,8 +2371,8 @@ repeat: if (page->mapping != mapping || !PageUptodate(page)) goto unlock; - size = round_up(i_size_read(mapping->host), PAGE_SIZE); - if (page->index >= size >> PAGE_SHIFT) + max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); + if (page->index >= max_idx) goto unlock; if (file->f_ra.mmap_miss > 0) @@ -2704,7 +2706,6 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) ssize_t written; size_t write_len; pgoff_t end; - struct iov_iter data; write_len = iov_iter_count(from); end = (pos + write_len - 1) >> PAGE_SHIFT; @@ -2719,22 +2720,19 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) * about to write. We do this *before* the write so that we can return * without clobbering -EIOCBQUEUED from ->direct_IO(). */ - if (mapping->nrpages) { - written = invalidate_inode_pages2_range(mapping, + written = invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end); - /* - * If a page can not be invalidated, return 0 to fall back - * to buffered write. - */ - if (written) { - if (written == -EBUSY) - return 0; - goto out; - } + /* + * If a page can not be invalidated, return 0 to fall back + * to buffered write. + */ + if (written) { + if (written == -EBUSY) + return 0; + goto out; } - data = *from; - written = mapping->a_ops->direct_IO(iocb, &data); + written = mapping->a_ops->direct_IO(iocb, from); /* * Finally, try again to invalidate clean pages which might have been @@ -2744,20 +2742,19 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... */ - if (mapping->nrpages) { - invalidate_inode_pages2_range(mapping, - pos >> PAGE_SHIFT, end); - } + invalidate_inode_pages2_range(mapping, + pos >> PAGE_SHIFT, end); if (written > 0) { pos += written; - iov_iter_advance(from, written); + write_len -= written; if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } iocb->ki_pos = pos; } + iov_iter_revert(from, write_len - iov_iter_count(from)); out: return written; } @@ -2794,12 +2791,6 @@ ssize_t generic_perform_write(struct file *file, ssize_t written = 0; unsigned int flags = 0; - /* - * Copies from kernel address space cannot fail (NFSD is a big user). - */ - if (!iter_is_iovec(i)) - flags |= AOP_FLAG_UNINTERRUPTIBLE; - do { struct page *page; unsigned long offset; /* Offset into pagecache page */ @@ -3001,7 +2992,7 @@ EXPORT_SYMBOL(generic_file_write_iter); * @gfp_mask: memory allocation flags (and I/O mode) * * The address_space is to try to release any data against the page - * (presumably at page->private). If the release was successful, return `1'. + * (presumably at page->private). If the release was successful, return '1'. * Otherwise return zero. * * This may also be called if PG_fscache is set on a page, indicating that the diff --git a/mm/frame_vector.c b/mm/frame_vector.c index db77dcb38afd..72ebec18629c 100644 --- a/mm/frame_vector.c +++ b/mm/frame_vector.c @@ -200,10 +200,7 @@ struct frame_vector *frame_vector_create(unsigned int nr_frames) * Avoid higher order allocations, use vmalloc instead. It should * be rare anyway. */ - if (size <= PAGE_SIZE) - vec = kmalloc(size, GFP_KERNEL); - else - vec = vmalloc(size); + vec = kvmalloc(size, GFP_KERNEL); if (!vec) return NULL; vec->nr_allocated = nr_frames; @@ -1189,34 +1189,57 @@ struct page *get_dump_page(unsigned long addr) */ #ifdef CONFIG_HAVE_GENERIC_RCU_GUP +#ifndef gup_get_pte +/* + * We assume that the PTE can be read atomically. If this is not the case for + * your architecture, please provide the helper. + */ +static inline pte_t gup_get_pte(pte_t *ptep) +{ + return READ_ONCE(*ptep); +} +#endif + +static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) +{ + while ((*nr) - nr_start) { + struct page *page = pages[--(*nr)]; + + ClearPageReferenced(page); + put_page(page); + } +} + #ifdef __HAVE_ARCH_PTE_SPECIAL static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { + struct dev_pagemap *pgmap = NULL; + int nr_start = *nr, ret = 0; pte_t *ptep, *ptem; - int ret = 0; ptem = ptep = pte_offset_map(&pmd, addr); do { - /* - * In the line below we are assuming that the pte can be read - * atomically. If this is not the case for your architecture, - * please wrap this in a helper function! - * - * for an example see gup_get_pte in arch/x86/mm/gup.c - */ - pte_t pte = READ_ONCE(*ptep); + pte_t pte = gup_get_pte(ptep); struct page *head, *page; /* * Similar to the PMD case below, NUMA hinting must take slow * path using the pte_protnone check. */ - if (!pte_present(pte) || pte_special(pte) || - pte_protnone(pte) || (write && !pte_write(pte))) + if (pte_protnone(pte)) goto pte_unmap; - if (!arch_pte_access_permitted(pte, write)) + if (!pte_access_permitted(pte, write)) + goto pte_unmap; + + if (pte_devmap(pte)) { + pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, pages); + goto pte_unmap; + } + } else if (pte_special(pte)) goto pte_unmap; VM_BUG_ON(!pfn_valid(pte_pfn(pte))); @@ -1232,6 +1255,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, } VM_BUG_ON_PAGE(compound_head(page) != head, page); + + put_dev_pagemap(pgmap); + SetPageReferenced(page); pages[*nr] = page; (*nr)++; @@ -1261,15 +1287,76 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, } #endif /* __HAVE_ARCH_PTE_SPECIAL */ +#ifdef __HAVE_ARCH_PTE_DEVMAP +static int __gup_device_huge(unsigned long pfn, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + int nr_start = *nr; + struct dev_pagemap *pgmap = NULL; + + do { + struct page *page = pfn_to_page(pfn); + + pgmap = get_dev_pagemap(pfn, pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, pages); + return 0; + } + SetPageReferenced(page); + pages[*nr] = page; + get_page(page); + put_dev_pagemap(pgmap); + (*nr)++; + pfn++; + } while (addr += PAGE_SIZE, addr != end); + return 1; +} + +static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + unsigned long fault_pfn; + + fault_pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + return __gup_device_huge(fault_pfn, addr, end, pages, nr); +} + +static int __gup_device_huge_pud(pud_t pud, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + unsigned long fault_pfn; + + fault_pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + return __gup_device_huge(fault_pfn, addr, end, pages, nr); +} +#else +static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + BUILD_BUG(); + return 0; +} + +static int __gup_device_huge_pud(pud_t pud, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + BUILD_BUG(); + return 0; +} +#endif + static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { struct page *head, *page; int refs; - if (write && !pmd_write(orig)) + if (!pmd_access_permitted(orig, write)) return 0; + if (pmd_devmap(orig)) + return __gup_device_huge_pmd(orig, addr, end, pages, nr); + refs = 0; head = pmd_page(orig); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); @@ -1293,6 +1380,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, return 0; } + SetPageReferenced(head); return 1; } @@ -1302,9 +1390,12 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, struct page *head, *page; int refs; - if (write && !pud_write(orig)) + if (!pud_access_permitted(orig, write)) return 0; + if (pud_devmap(orig)) + return __gup_device_huge_pud(orig, addr, end, pages, nr); + refs = 0; head = pud_page(orig); page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); @@ -1328,6 +1419,7 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return 0; } + SetPageReferenced(head); return 1; } @@ -1338,9 +1430,10 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, int refs; struct page *head, *page; - if (write && !pgd_write(orig)) + if (!pgd_access_permitted(orig, write)) return 0; + BUILD_BUG_ON(pgd_devmap(orig)); refs = 0; head = pgd_page(orig); page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT); @@ -1364,6 +1457,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 0; } + SetPageReferenced(head); return 1; } @@ -1481,7 +1575,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, end = start + len; if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ, - start, len))) + (void __user *)start, len))) return 0; /* @@ -1520,6 +1614,21 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, return nr; } +#ifndef gup_fast_permitted +/* + * Check if it's allowed to use __get_user_pages_fast() for the range, or + * we need to fall back to the slow version: + */ +bool gup_fast_permitted(unsigned long start, int nr_pages, int write) +{ + unsigned long len, end; + + len = (unsigned long) nr_pages << PAGE_SHIFT; + end = start + len; + return end >= start; +} +#endif + /** * get_user_pages_fast() - pin user pages in memory * @start: starting user address @@ -1539,11 +1648,14 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { - int nr, ret; + int nr = 0, ret = 0; start &= PAGE_MASK; - nr = __get_user_pages_fast(start, nr_pages, write, pages); - ret = nr; + + if (gup_fast_permitted(start, nr_pages, write)) { + nr = __get_user_pages_fast(start, nr_pages, write, pages); + ret = nr; + } if (nr < nr_pages) { /* Try to get the remaining pages with get_user_pages */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1ebc93e179f3..a84909cf20d3 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -240,18 +240,18 @@ static ssize_t defrag_store(struct kobject *kobj, clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("defer", buf, - min(sizeof("defer")-1, count))) { - clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); - clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); - clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); - set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); } else if (!memcmp("defer+madvise", buf, min(sizeof("defer+madvise")-1, count))) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + } else if (!memcmp("defer", buf, + min(sizeof("defer")-1, count))) { + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); } else if (!memcmp("madvise", buf, min(sizeof("madvise")-1, count))) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); @@ -715,7 +715,8 @@ int do_huge_pmd_anonymous_page(struct vm_fault *vmf) } static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write) + pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write, + pgtable_t pgtable) { struct mm_struct *mm = vma->vm_mm; pmd_t entry; @@ -729,6 +730,12 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, entry = pmd_mkyoung(pmd_mkdirty(entry)); entry = maybe_pmd_mkwrite(entry, vma); } + + if (pgtable) { + pgtable_trans_huge_deposit(mm, pmd, pgtable); + atomic_long_inc(&mm->nr_ptes); + } + set_pmd_at(mm, addr, pmd, entry); update_mmu_cache_pmd(vma, addr, pmd); spin_unlock(ptl); @@ -738,6 +745,7 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, pfn_t pfn, bool write) { pgprot_t pgprot = vma->vm_page_prot; + pgtable_t pgtable = NULL; /* * If we had pmd_special, we could avoid all these restrictions, * but we need to be consistent with PTEs and architectures that @@ -752,9 +760,15 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; + if (arch_needs_pgtable_deposit()) { + pgtable = pte_alloc_one(vma->vm_mm, addr); + if (!pgtable) + return VM_FAULT_OOM; + } + track_pfn_insert(vma, &pgprot, pfn); - insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write); + insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write, pgtable); return VM_FAULT_NOPAGE; } EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd); @@ -1564,18 +1578,16 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, ClearPageDirty(page); unlock_page(page); - if (PageActive(page)) - deactivate_page(page); - if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) { - orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd, - tlb->fullmm); + pmdp_invalidate(vma, addr, pmd); orig_pmd = pmd_mkold(orig_pmd); orig_pmd = pmd_mkclean(orig_pmd); set_pmd_at(mm, addr, pmd, orig_pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); } + + mark_page_lazyfree(page); ret = true; out: spin_unlock(ptl); @@ -1613,12 +1625,13 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, tlb->fullmm); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); if (vma_is_dax(vma)) { + if (arch_needs_pgtable_deposit()) + zap_deposited_table(tlb->mm, pmd); spin_unlock(ptl); if (is_huge_zero_pmd(orig_pmd)) tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE); } else if (is_huge_zero_pmd(orig_pmd)) { - pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd)); - atomic_long_dec(&tlb->mm->nr_ptes); + zap_deposited_table(tlb->mm, pmd); spin_unlock(ptl); tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE); } else { @@ -1627,10 +1640,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); VM_BUG_ON_PAGE(!PageHead(page), page); if (PageAnon(page)) { - pgtable_t pgtable; - pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd); - pte_free(tlb->mm, pgtable); - atomic_long_dec(&tlb->mm->nr_ptes); + zap_deposited_table(tlb->mm, pmd); add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); } else { if (arch_needs_pgtable_deposit()) @@ -1724,37 +1734,69 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, { struct mm_struct *mm = vma->vm_mm; spinlock_t *ptl; - int ret = 0; + pmd_t entry; + bool preserve_write; + int ret; ptl = __pmd_trans_huge_lock(pmd, vma); - if (ptl) { - pmd_t entry; - bool preserve_write = prot_numa && pmd_write(*pmd); - ret = 1; + if (!ptl) + return 0; - /* - * Avoid trapping faults against the zero page. The read-only - * data is likely to be read-cached on the local CPU and - * local/remote hits to the zero page are not interesting. - */ - if (prot_numa && is_huge_zero_pmd(*pmd)) { - spin_unlock(ptl); - return ret; - } + preserve_write = prot_numa && pmd_write(*pmd); + ret = 1; - if (!prot_numa || !pmd_protnone(*pmd)) { - entry = pmdp_huge_get_and_clear_notify(mm, addr, pmd); - entry = pmd_modify(entry, newprot); - if (preserve_write) - entry = pmd_mk_savedwrite(entry); - ret = HPAGE_PMD_NR; - set_pmd_at(mm, addr, pmd, entry); - BUG_ON(vma_is_anonymous(vma) && !preserve_write && - pmd_write(entry)); - } - spin_unlock(ptl); - } + /* + * Avoid trapping faults against the zero page. The read-only + * data is likely to be read-cached on the local CPU and + * local/remote hits to the zero page are not interesting. + */ + if (prot_numa && is_huge_zero_pmd(*pmd)) + goto unlock; + + if (prot_numa && pmd_protnone(*pmd)) + goto unlock; + /* + * In case prot_numa, we are under down_read(mmap_sem). It's critical + * to not clear pmd intermittently to avoid race with MADV_DONTNEED + * which is also under down_read(mmap_sem): + * + * CPU0: CPU1: + * change_huge_pmd(prot_numa=1) + * pmdp_huge_get_and_clear_notify() + * madvise_dontneed() + * zap_pmd_range() + * pmd_trans_huge(*pmd) == 0 (without ptl) + * // skip the pmd + * set_pmd_at(); + * // pmd is re-established + * + * The race makes MADV_DONTNEED miss the huge pmd and don't clear it + * which may break userspace. + * + * pmdp_invalidate() is required to make sure we don't miss + * dirty/young flags set by hardware. + */ + entry = *pmd; + pmdp_invalidate(vma, addr, pmd); + + /* + * Recover dirty/young flags. It relies on pmdp_invalidate to not + * corrupt them. + */ + if (pmd_dirty(*pmd)) + entry = pmd_mkdirty(entry); + if (pmd_young(*pmd)) + entry = pmd_mkyoung(entry); + + entry = pmd_modify(entry, newprot); + if (preserve_write) + entry = pmd_mk_savedwrite(entry); + ret = HPAGE_PMD_NR; + set_pmd_at(mm, addr, pmd, entry); + BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry)); +unlock: + spin_unlock(ptl); return ret; } @@ -2114,15 +2156,15 @@ static void freeze_page(struct page *page) { enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS | TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD; - int ret; + bool unmap_success; VM_BUG_ON_PAGE(!PageHead(page), page); if (PageAnon(page)) ttu_flags |= TTU_MIGRATION; - ret = try_to_unmap(page, ttu_flags); - VM_BUG_ON_PAGE(ret, page); + unmap_success = try_to_unmap(page, ttu_flags); + VM_BUG_ON_PAGE(!unmap_success, page); } static void unfreeze_page(struct page *page) @@ -2368,7 +2410,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) VM_BUG_ON_PAGE(is_huge_zero_page(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(!PageSwapBacked(page), page); VM_BUG_ON_PAGE(!PageCompound(page), page); if (PageAnon(head)) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3d0aab9ee80d..e5828875f7bb 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4403,7 +4403,9 @@ int hugetlb_reserve_pages(struct inode *inode, return 0; out_err: if (!vma || vma->vm_flags & VM_MAYSHARE) - region_abort(resv_map, from, to); + /* Don't call region_abort if region_chg failed */ + if (chg >= 0) + region_abort(resv_map, from, to); if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) kref_put(&resv_map->refs, resv_map_release); return ret; @@ -4651,6 +4653,7 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, { struct page *page = NULL; spinlock_t *ptl; + pte_t pte; retry: ptl = pmd_lockptr(mm, pmd); spin_lock(ptl); @@ -4660,12 +4663,13 @@ retry: */ if (!pmd_huge(*pmd)) goto out; - if (pmd_present(*pmd)) { + pte = huge_ptep_get((pte_t *)pmd); + if (pte_present(pte)) { page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT); if (flags & FOLL_GET) get_page(page); } else { - if (is_hugetlb_entry_migration(huge_ptep_get((pte_t *)pmd))) { + if (is_hugetlb_entry_migration(pte)) { spin_unlock(ptl); __migration_entry_wait(mm, (pte_t *)pmd, ptl); goto retry; diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c index 9d26fd9fefe4..356df057a2a8 100644 --- a/mm/hwpoison-inject.c +++ b/mm/hwpoison-inject.c @@ -34,8 +34,7 @@ static int hwpoison_inject(void *data, u64 val) if (!hwpoison_filter_enable) goto inject; - if (!PageLRU(hpage) && !PageHuge(p)) - shake_page(hpage, 0); + shake_page(hpage, 0); /* * This implies unable to support non-LRU pages. */ diff --git a/mm/internal.h b/mm/internal.h index ccfc2a2969f4..0e4f558412fb 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -81,11 +81,16 @@ static inline void set_page_refcounted(struct page *page) extern unsigned long highest_memmap_pfn; /* + * Maximum number of reclaim retries without progress before the OOM + * killer is consider the only way forward. + */ +#define MAX_RECLAIM_RETRIES 16 + +/* * in mm/vmscan.c: */ extern int isolate_lru_page(struct page *page); extern void putback_lru_page(struct page *page); -extern bool pgdat_reclaimable(struct pglist_data *pgdat); /* * in mm/rmap.c: @@ -178,6 +183,7 @@ extern int user_min_free_kbytes; struct compact_control { struct list_head freepages; /* List of free pages to migrate to */ struct list_head migratepages; /* List of pages being migrated */ + struct zone *zone; unsigned long nr_freepages; /* Number of isolated free pages */ unsigned long nr_migratepages; /* Number of pages to migrate */ unsigned long total_migrate_scanned; @@ -185,17 +191,18 @@ struct compact_control { unsigned long free_pfn; /* isolate_freepages search base */ unsigned long migrate_pfn; /* isolate_migratepages search base */ unsigned long last_migrated_pfn;/* Not yet flushed page being freed */ + const gfp_t gfp_mask; /* gfp mask of a direct compactor */ + int order; /* order a direct compactor needs */ + int migratetype; /* migratetype of direct compactor */ + const unsigned int alloc_flags; /* alloc flags of a direct compactor */ + const int classzone_idx; /* zone index of a direct compactor */ enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool ignore_block_suitable; /* Scan blocks considered unsuitable */ bool direct_compaction; /* False from kcompactd or /proc/... */ bool whole_zone; /* Whole zone should/has been scanned */ - int order; /* order a direct compactor needs */ - const gfp_t gfp_mask; /* gfp mask of a direct compactor */ - const unsigned int alloc_flags; /* alloc flags of a direct compactor */ - const int classzone_idx; /* zone index of a direct compactor */ - struct zone *zone; bool contended; /* Signal lock or sched contention */ + bool finishing_block; /* Finishing current pageblock */ }; unsigned long @@ -481,6 +488,13 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, enum ttu_flags; struct tlbflush_unmap_batch; + +/* + * only for MM internal work items which do not depend on + * any allocations or locks which might depend on allocations + */ +extern struct workqueue_struct *mm_percpu_wq; + #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); @@ -498,4 +512,14 @@ extern const struct trace_print_flags pageflag_names[]; extern const struct trace_print_flags vmaflag_names[]; extern const struct trace_print_flags gfpflag_names[]; +static inline bool is_migrate_highatomic(enum migratetype migratetype) +{ + return migratetype == MIGRATE_HIGHATOMIC; +} + +static inline bool is_migrate_highatomic_page(struct page *page) +{ + return get_pageblock_migratetype(page) == MIGRATE_HIGHATOMIC; +} + #endif /* __MM_INTERNAL_H */ diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 98b27195e38b..c81549d5c833 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -413,7 +413,7 @@ void kasan_cache_create(struct kmem_cache *cache, size_t *size, *size += sizeof(struct kasan_alloc_meta); /* Add free meta. */ - if (cache->flags & SLAB_DESTROY_BY_RCU || cache->ctor || + if (cache->flags & SLAB_TYPESAFE_BY_RCU || cache->ctor || cache->object_size < sizeof(struct kasan_free_meta)) { cache->kasan_info.free_meta_offset = *size; *size += sizeof(struct kasan_free_meta); @@ -561,7 +561,7 @@ static void kasan_poison_slab_free(struct kmem_cache *cache, void *object) unsigned long rounded_up_size = round_up(size, KASAN_SHADOW_SCALE_SIZE); /* RCU slabs could be legally used after free within the RCU period */ - if (unlikely(cache->flags & SLAB_DESTROY_BY_RCU)) + if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU)) return; kasan_poison_shadow(object, rounded_up_size, KASAN_KMALLOC_FREE); @@ -572,12 +572,13 @@ bool kasan_slab_free(struct kmem_cache *cache, void *object) s8 shadow_byte; /* RCU slabs could be legally used after free within the RCU period */ - if (unlikely(cache->flags & SLAB_DESTROY_BY_RCU)) + if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU)) return false; shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(object)); if (shadow_byte < 0 || shadow_byte >= KASAN_SHADOW_SCALE_SIZE) { - kasan_report_double_free(cache, object, shadow_byte); + kasan_report_double_free(cache, object, + __builtin_return_address(1)); return true; } @@ -690,7 +691,7 @@ int kasan_module_alloc(void *addr, size_t size) ret = __vmalloc_node_range(shadow_size, 1, shadow_start, shadow_start + shadow_size, - GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, + GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE, __builtin_return_address(0)); diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 1c260e6b3b3c..1229298cce64 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -96,15 +96,10 @@ static inline const void *kasan_shadow_to_mem(const void *shadow_addr) << KASAN_SHADOW_SCALE_SHIFT); } -static inline bool kasan_report_enabled(void) -{ - return !current->kasan_depth; -} - void kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip); void kasan_report_double_free(struct kmem_cache *cache, void *object, - s8 shadow); + void *ip); #if defined(CONFIG_SLAB) || defined(CONFIG_SLUB) void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache); diff --git a/mm/kasan/report.c b/mm/kasan/report.c index f479365530b6..beee0e980e2d 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -13,7 +13,9 @@ * */ +#include <linux/bitops.h> #include <linux/ftrace.h> +#include <linux/init.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/printk.h> @@ -49,7 +51,13 @@ static const void *find_first_bad_addr(const void *addr, size_t size) return first_bad_addr; } -static void print_error_description(struct kasan_access_info *info) +static bool addr_has_shadow(struct kasan_access_info *info) +{ + return (info->access_addr >= + kasan_shadow_to_mem((void *)KASAN_SHADOW_START)); +} + +static const char *get_shadow_bug_type(struct kasan_access_info *info) { const char *bug_type = "unknown-crash"; u8 *shadow_addr; @@ -96,12 +104,39 @@ static void print_error_description(struct kasan_access_info *info) break; } - pr_err("BUG: KASAN: %s in %pS at addr %p\n", - bug_type, (void *)info->ip, - info->access_addr); - pr_err("%s of size %zu by task %s/%d\n", - info->is_write ? "Write" : "Read", - info->access_size, current->comm, task_pid_nr(current)); + return bug_type; +} + +const char *get_wild_bug_type(struct kasan_access_info *info) +{ + const char *bug_type = "unknown-crash"; + + if ((unsigned long)info->access_addr < PAGE_SIZE) + bug_type = "null-ptr-deref"; + else if ((unsigned long)info->access_addr < TASK_SIZE) + bug_type = "user-memory-access"; + else + bug_type = "wild-memory-access"; + + return bug_type; +} + +static const char *get_bug_type(struct kasan_access_info *info) +{ + if (addr_has_shadow(info)) + return get_shadow_bug_type(info); + return get_wild_bug_type(info); +} + +static void print_error_description(struct kasan_access_info *info) +{ + const char *bug_type = get_bug_type(info); + + pr_err("BUG: KASAN: %s in %pS\n", + bug_type, (void *)info->ip); + pr_err("%s of size %zu at addr %p by task %s/%d\n", + info->is_write ? "Write" : "Read", info->access_size, + info->access_addr, current->comm, task_pid_nr(current)); } static inline bool kernel_or_module_addr(const void *addr) @@ -142,9 +177,9 @@ static void kasan_end_report(unsigned long *flags) kasan_enable_current(); } -static void print_track(struct kasan_track *track) +static void print_track(struct kasan_track *track, const char *prefix) { - pr_err("PID = %u\n", track->pid); + pr_err("%s by task %u:\n", prefix, track->pid); if (track->stack) { struct stack_trace trace; @@ -155,59 +190,84 @@ static void print_track(struct kasan_track *track) } } -static void kasan_object_err(struct kmem_cache *cache, void *object) +static struct page *addr_to_page(const void *addr) { - struct kasan_alloc_meta *alloc_info = get_alloc_info(cache, object); + if ((addr >= (void *)PAGE_OFFSET) && + (addr < high_memory)) + return virt_to_head_page(addr); + return NULL; +} - dump_stack(); - pr_err("Object at %p, in cache %s size: %d\n", object, cache->name, - cache->object_size); +static void describe_object_addr(struct kmem_cache *cache, void *object, + const void *addr) +{ + unsigned long access_addr = (unsigned long)addr; + unsigned long object_addr = (unsigned long)object; + const char *rel_type; + int rel_bytes; + + pr_err("The buggy address belongs to the object at %p\n" + " which belongs to the cache %s of size %d\n", + object, cache->name, cache->object_size); - if (!(cache->flags & SLAB_KASAN)) + if (!addr) return; - pr_err("Allocated:\n"); - print_track(&alloc_info->alloc_track); - pr_err("Freed:\n"); - print_track(&alloc_info->free_track); + if (access_addr < object_addr) { + rel_type = "to the left"; + rel_bytes = object_addr - access_addr; + } else if (access_addr >= object_addr + cache->object_size) { + rel_type = "to the right"; + rel_bytes = access_addr - (object_addr + cache->object_size); + } else { + rel_type = "inside"; + rel_bytes = access_addr - object_addr; + } + + pr_err("The buggy address is located %d bytes %s of\n" + " %d-byte region [%p, %p)\n", + rel_bytes, rel_type, cache->object_size, (void *)object_addr, + (void *)(object_addr + cache->object_size)); } -void kasan_report_double_free(struct kmem_cache *cache, void *object, - s8 shadow) +static void describe_object(struct kmem_cache *cache, void *object, + const void *addr) { - unsigned long flags; + struct kasan_alloc_meta *alloc_info = get_alloc_info(cache, object); - kasan_start_report(&flags); - pr_err("BUG: Double free or freeing an invalid pointer\n"); - pr_err("Unexpected shadow byte: 0x%hhX\n", shadow); - kasan_object_err(cache, object); - kasan_end_report(&flags); + if (cache->flags & SLAB_KASAN) { + print_track(&alloc_info->alloc_track, "Allocated"); + pr_err("\n"); + print_track(&alloc_info->free_track, "Freed"); + pr_err("\n"); + } + + describe_object_addr(cache, object, addr); } -static void print_address_description(struct kasan_access_info *info) +static void print_address_description(void *addr) { - const void *addr = info->access_addr; + struct page *page = addr_to_page(addr); - if ((addr >= (void *)PAGE_OFFSET) && - (addr < high_memory)) { - struct page *page = virt_to_head_page(addr); - - if (PageSlab(page)) { - void *object; - struct kmem_cache *cache = page->slab_cache; - object = nearest_obj(cache, page, - (void *)info->access_addr); - kasan_object_err(cache, object); - return; - } - dump_page(page, "kasan: bad access detected"); + dump_stack(); + pr_err("\n"); + + if (page && PageSlab(page)) { + struct kmem_cache *cache = page->slab_cache; + void *object = nearest_obj(cache, page, addr); + + describe_object(cache, object, addr); } - if (kernel_or_module_addr(addr)) { - if (!init_task_stack_addr(addr)) - pr_err("Address belongs to variable %pS\n", addr); + if (kernel_or_module_addr(addr) && !init_task_stack_addr(addr)) { + pr_err("The buggy address belongs to the variable:\n"); + pr_err(" %pS\n", addr); + } + + if (page) { + pr_err("The buggy address belongs to the page:\n"); + dump_page(page, "kasan: bad access detected"); } - dump_stack(); } static bool row_is_guilty(const void *row, const void *guilty) @@ -262,37 +322,74 @@ static void print_shadow_for_address(const void *addr) } } +void kasan_report_double_free(struct kmem_cache *cache, void *object, + void *ip) +{ + unsigned long flags; + + kasan_start_report(&flags); + pr_err("BUG: KASAN: double-free or invalid-free in %pS\n", ip); + pr_err("\n"); + print_address_description(object); + pr_err("\n"); + print_shadow_for_address(object); + kasan_end_report(&flags); +} + static void kasan_report_error(struct kasan_access_info *info) { unsigned long flags; - const char *bug_type; kasan_start_report(&flags); - if (info->access_addr < - kasan_shadow_to_mem((void *)KASAN_SHADOW_START)) { - if ((unsigned long)info->access_addr < PAGE_SIZE) - bug_type = "null-ptr-deref"; - else if ((unsigned long)info->access_addr < TASK_SIZE) - bug_type = "user-memory-access"; - else - bug_type = "wild-memory-access"; - pr_err("BUG: KASAN: %s on address %p\n", - bug_type, info->access_addr); - pr_err("%s of size %zu by task %s/%d\n", - info->is_write ? "Write" : "Read", - info->access_size, current->comm, - task_pid_nr(current)); + print_error_description(info); + pr_err("\n"); + + if (!addr_has_shadow(info)) { dump_stack(); } else { - print_error_description(info); - print_address_description(info); + print_address_description((void *)info->access_addr); + pr_err("\n"); print_shadow_for_address(info->first_bad_addr); } kasan_end_report(&flags); } +static unsigned long kasan_flags; + +#define KASAN_BIT_REPORTED 0 +#define KASAN_BIT_MULTI_SHOT 1 + +bool kasan_save_enable_multi_shot(void) +{ + return test_and_set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags); +} +EXPORT_SYMBOL_GPL(kasan_save_enable_multi_shot); + +void kasan_restore_multi_shot(bool enabled) +{ + if (!enabled) + clear_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags); +} +EXPORT_SYMBOL_GPL(kasan_restore_multi_shot); + +static int __init kasan_set_multi_shot(char *str) +{ + set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags); + return 1; +} +__setup("kasan_multi_shot", kasan_set_multi_shot); + +static inline bool kasan_report_enabled(void) +{ + if (current->kasan_depth) + return false; + if (test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags)) + return true; + return !test_and_set_bit(KASAN_BIT_REPORTED, &kasan_flags); +} + void kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip) { diff --git a/mm/khugepaged.c b/mm/khugepaged.c index ba40b7f673f4..7cb9c88bb4a3 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -483,8 +483,7 @@ void __khugepaged_exit(struct mm_struct *mm) static void release_pte_page(struct page *page) { - /* 0 stands for page_is_file_cache(page) == false */ - dec_node_page_state(page, NR_ISOLATED_ANON + 0); + dec_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); unlock_page(page); putback_lru_page(page); } @@ -532,7 +531,6 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, VM_BUG_ON_PAGE(PageCompound(page), page); VM_BUG_ON_PAGE(!PageAnon(page), page); - VM_BUG_ON_PAGE(!PageSwapBacked(page), page); /* * We can do it before isolate_lru_page because the @@ -550,7 +548,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, * The page must only be referenced by the scanned process * and page swap cache. */ - if (page_count(page) != 1 + !!PageSwapCache(page)) { + if (page_count(page) != 1 + PageSwapCache(page)) { unlock_page(page); result = SCAN_PAGE_COUNT; goto out; @@ -579,8 +577,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, result = SCAN_DEL_PAGE_LRU; goto out; } - /* 0 stands for page_is_file_cache(page) == false */ - inc_node_page_state(page, NR_ISOLATED_ANON + 0); + inc_node_page_state(page, + NR_ISOLATED_ANON + page_is_file_cache(page)); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageLRU(page), page); @@ -1183,7 +1181,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, * The page must only be referenced by the scanned process * and page swap cache. */ - if (page_count(page) != 1 + !!PageSwapCache(page)) { + if (page_count(page) != 1 + PageSwapCache(page)) { result = SCAN_PAGE_COUNT; goto out_unmap; } diff --git a/mm/kmemcheck.c b/mm/kmemcheck.c index 5bf191756a4a..2d5959c5f7c5 100644 --- a/mm/kmemcheck.c +++ b/mm/kmemcheck.c @@ -95,7 +95,7 @@ void kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object, void kmemcheck_slab_free(struct kmem_cache *s, void *object, size_t size) { /* TODO: RCU freeing is unsupported for now; hide false positives. */ - if (!s->ctor && !(s->flags & SLAB_DESTROY_BY_RCU)) + if (!s->ctor && !(s->flags & SLAB_TYPESAFE_BY_RCU)) kmemcheck_mark_freed(object, size); } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 26c874e90b12..20036d4f9f13 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1416,7 +1416,7 @@ static void kmemleak_scan(void) /* data/bss scanning */ scan_large_block(_sdata, _edata); scan_large_block(__bss_start, __bss_stop); - scan_large_block(__start_data_ro_after_init, __end_data_ro_after_init); + scan_large_block(__start_ro_after_init, __end_ro_after_init); #ifdef CONFIG_SMP /* per-cpu sections scanning */ @@ -1933,11 +1933,10 @@ struct page *ksm_might_need_to_copy(struct page *page, return new_page; } -int rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc) +void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc) { struct stable_node *stable_node; struct rmap_item *rmap_item; - int ret = SWAP_AGAIN; int search_new_forks = 0; VM_BUG_ON_PAGE(!PageKsm(page), page); @@ -1950,7 +1949,7 @@ int rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc) stable_node = page_stable_node(page); if (!stable_node) - return ret; + return; again: hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { struct anon_vma *anon_vma = rmap_item->anon_vma; @@ -1978,23 +1977,20 @@ again: if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; - ret = rwc->rmap_one(page, vma, - rmap_item->address, rwc->arg); - if (ret != SWAP_AGAIN) { + if (!rwc->rmap_one(page, vma, + rmap_item->address, rwc->arg)) { anon_vma_unlock_read(anon_vma); - goto out; + return; } if (rwc->done && rwc->done(page)) { anon_vma_unlock_read(anon_vma); - goto out; + return; } } anon_vma_unlock_read(anon_vma); } if (!search_new_forks++) goto again; -out: - return ret; } #ifdef CONFIG_MIGRATION diff --git a/mm/madvise.c b/mm/madvise.c index 7a2abf0127ae..25b78ee4fc2c 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -411,10 +411,9 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, ptent = pte_mkold(ptent); ptent = pte_mkclean(ptent); set_pte_at(mm, addr, pte, ptent); - if (PageActive(page)) - deactivate_page(page); tlb_remove_tlb_entry(tlb, pte, addr); } + mark_page_lazyfree(page); } out: if (nr_swap) { @@ -606,34 +605,40 @@ static long madvise_remove(struct vm_area_struct *vma, /* * Error injection support for memory error handling. */ -static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end) +static int madvise_inject_error(int behavior, + unsigned long start, unsigned long end) { - struct page *p; + struct page *page; + if (!capable(CAP_SYS_ADMIN)) return -EPERM; + for (; start < end; start += PAGE_SIZE << - compound_order(compound_head(p))) { + compound_order(compound_head(page))) { int ret; - ret = get_user_pages_fast(start, 1, 0, &p); + ret = get_user_pages_fast(start, 1, 0, &page); if (ret != 1) return ret; - if (PageHWPoison(p)) { - put_page(p); + if (PageHWPoison(page)) { + put_page(page); continue; } - if (bhv == MADV_SOFT_OFFLINE) { - pr_info("Soft offlining page %#lx at %#lx\n", - page_to_pfn(p), start); - ret = soft_offline_page(p, MF_COUNT_INCREASED); + + if (behavior == MADV_SOFT_OFFLINE) { + pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n", + page_to_pfn(page), start); + + ret = soft_offline_page(page, MF_COUNT_INCREASED); if (ret) return ret; continue; } - pr_info("Injecting memory failure for page %#lx at %#lx\n", - page_to_pfn(p), start); - ret = memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED); + pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n", + page_to_pfn(page), start); + + ret = memory_failure(page_to_pfn(page), 0, MF_COUNT_INCREASED); if (ret) return ret; } @@ -651,13 +656,7 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, case MADV_WILLNEED: return madvise_willneed(vma, prev, start, end); case MADV_FREE: - /* - * XXX: In this implementation, MADV_FREE works like - * MADV_DONTNEED on swapless system or full swap. - */ - if (get_nr_swap_pages() > 0) - return madvise_free(vma, prev, start, end); - /* passthrough */ + return madvise_free(vma, prev, start, end); case MADV_DONTNEED: return madvise_dontneed(vma, prev, start, end); default: @@ -688,6 +687,10 @@ madvise_behavior_valid(int behavior) #endif case MADV_DONTDUMP: case MADV_DODUMP: +#ifdef CONFIG_MEMORY_FAILURE + case MADV_SOFT_OFFLINE: + case MADV_HWPOISON: +#endif return true; default: @@ -761,10 +764,6 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) size_t len; struct blk_plug plug; -#ifdef CONFIG_MEMORY_FAILURE - if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE) - return madvise_hwpoison(behavior, start, start+len_in); -#endif if (!madvise_behavior_valid(behavior)) return error; @@ -784,6 +783,11 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) if (end == start) return error; +#ifdef CONFIG_MEMORY_FAILURE + if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE) + return madvise_inject_error(behavior, start, start + len_in); +#endif + write = madvise_need_mmap_write(behavior); if (write) { if (down_write_killable(¤t->mm->mmap_sem)) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2bd7541d7c11..ff73899af61a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -100,24 +100,7 @@ static bool do_memsw_account(void) return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && do_swap_account; } -static const char * const mem_cgroup_stat_names[] = { - "cache", - "rss", - "rss_huge", - "mapped_file", - "dirty", - "writeback", - "swap", -}; - -static const char * const mem_cgroup_events_names[] = { - "pgpgin", - "pgpgout", - "pgfault", - "pgmajfault", -}; - -static const char * const mem_cgroup_lru_names[] = { +static const char *const mem_cgroup_lru_names[] = { "inactive_anon", "active_anon", "inactive_file", @@ -568,32 +551,15 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz) * common workload, threshold and synchronization as vmstat[] should be * implemented. */ -static unsigned long -mem_cgroup_read_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) -{ - long val = 0; - int cpu; - - /* Per-cpu values can be negative, use a signed accumulator */ - for_each_possible_cpu(cpu) - val += per_cpu(memcg->stat->count[idx], cpu); - /* - * Summing races with updates, so val may be negative. Avoid exposing - * transient negative values. - */ - if (val < 0) - val = 0; - return val; -} -static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, - enum mem_cgroup_events_index idx) +static unsigned long memcg_sum_events(struct mem_cgroup *memcg, + enum memcg_event_item event) { unsigned long val = 0; int cpu; for_each_possible_cpu(cpu) - val += per_cpu(memcg->stat->events[idx], cpu); + val += per_cpu(memcg->stat->events[event], cpu); return val; } @@ -606,23 +572,23 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, * counted as CACHE even if it's on ANON LRU. */ if (PageAnon(page)) - __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS], - nr_pages); - else - __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE], - nr_pages); + __this_cpu_add(memcg->stat->count[MEMCG_RSS], nr_pages); + else { + __this_cpu_add(memcg->stat->count[MEMCG_CACHE], nr_pages); + if (PageSwapBacked(page)) + __this_cpu_add(memcg->stat->count[NR_SHMEM], nr_pages); + } if (compound) { VM_BUG_ON_PAGE(!PageTransHuge(page), page); - __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], - nr_pages); + __this_cpu_add(memcg->stat->count[MEMCG_RSS_HUGE], nr_pages); } /* pagein of a big page is an event. So, ignore page size */ if (nr_pages > 0) - __this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGIN]); + __this_cpu_inc(memcg->stat->events[PGPGIN]); else { - __this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT]); + __this_cpu_inc(memcg->stat->events[PGPGOUT]); nr_pages = -nr_pages; /* for event */ } @@ -1144,6 +1110,28 @@ static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg) return false; } +unsigned int memcg1_stats[] = { + MEMCG_CACHE, + MEMCG_RSS, + MEMCG_RSS_HUGE, + NR_SHMEM, + NR_FILE_MAPPED, + NR_FILE_DIRTY, + NR_WRITEBACK, + MEMCG_SWAP, +}; + +static const char *const memcg1_stat_names[] = { + "cache", + "rss", + "rss_huge", + "shmem", + "mapped_file", + "dirty", + "writeback", + "swap", +}; + #define K(x) ((x) << (PAGE_SHIFT-10)) /** * mem_cgroup_print_oom_info: Print OOM information relevant to memory controller. @@ -1188,11 +1176,11 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) pr_cont_cgroup_path(iter->css.cgroup); pr_cont(":"); - for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { - if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account) + for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { + if (memcg1_stats[i] == MEMCG_SWAP && !do_swap_account) continue; - pr_cont(" %s:%luKB", mem_cgroup_stat_names[i], - K(mem_cgroup_read_stat(iter, i))); + pr_cont(" %s:%luKB", memcg1_stat_names[i], + K(memcg_page_state(iter, memcg1_stats[i]))); } for (i = 0; i < NR_LRU_LISTS; i++) @@ -1837,7 +1825,7 @@ static void reclaim_high(struct mem_cgroup *memcg, do { if (page_counter_read(&memcg->memory) <= memcg->high) continue; - mem_cgroup_events(memcg, MEMCG_HIGH, 1); + mem_cgroup_event(memcg, MEMCG_HIGH); try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true); } while ((memcg = parent_mem_cgroup(memcg))); } @@ -1928,7 +1916,7 @@ retry: if (!gfpflags_allow_blocking(gfp_mask)) goto nomem; - mem_cgroup_events(mem_over_limit, MEMCG_MAX, 1); + mem_cgroup_event(mem_over_limit, MEMCG_MAX); nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, gfp_mask, may_swap); @@ -1971,7 +1959,7 @@ retry: if (fatal_signal_pending(current)) goto force; - mem_cgroup_events(mem_over_limit, MEMCG_OOM, 1); + mem_cgroup_event(mem_over_limit, MEMCG_OOM); mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(nr_pages * PAGE_SIZE)); @@ -2381,7 +2369,7 @@ void mem_cgroup_split_huge_fixup(struct page *head) for (i = 1; i < HPAGE_PMD_NR; i++) head[i].mem_cgroup = head->mem_cgroup; - __this_cpu_sub(head->mem_cgroup->stat->count[MEM_CGROUP_STAT_RSS_HUGE], + __this_cpu_sub(head->mem_cgroup->stat->count[MEMCG_RSS_HUGE], HPAGE_PMD_NR); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -2391,7 +2379,7 @@ static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg, bool charge) { int val = (charge) ? 1 : -1; - this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAP], val); + this_cpu_add(memcg->stat->count[MEMCG_SWAP], val); } /** @@ -2725,7 +2713,7 @@ static void tree_stat(struct mem_cgroup *memcg, unsigned long *stat) for_each_mem_cgroup_tree(iter, memcg) { for (i = 0; i < MEMCG_NR_STAT; i++) - stat[i] += mem_cgroup_read_stat(iter, i); + stat[i] += memcg_page_state(iter, i); } } @@ -2738,7 +2726,7 @@ static void tree_events(struct mem_cgroup *memcg, unsigned long *events) for_each_mem_cgroup_tree(iter, memcg) { for (i = 0; i < MEMCG_NR_EVENTS; i++) - events[i] += mem_cgroup_read_events(iter, i); + events[i] += memcg_sum_events(iter, i); } } @@ -2750,13 +2738,10 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) struct mem_cgroup *iter; for_each_mem_cgroup_tree(iter, memcg) { - val += mem_cgroup_read_stat(iter, - MEM_CGROUP_STAT_CACHE); - val += mem_cgroup_read_stat(iter, - MEM_CGROUP_STAT_RSS); + val += memcg_page_state(iter, MEMCG_CACHE); + val += memcg_page_state(iter, MEMCG_RSS); if (swap) - val += mem_cgroup_read_stat(iter, - MEM_CGROUP_STAT_SWAP); + val += memcg_page_state(iter, MEMCG_SWAP); } } else { if (!swap) @@ -3131,6 +3116,21 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v) } #endif /* CONFIG_NUMA */ +/* Universal VM events cgroup1 shows, original sort order */ +unsigned int memcg1_events[] = { + PGPGIN, + PGPGOUT, + PGFAULT, + PGMAJFAULT, +}; + +static const char *const memcg1_event_names[] = { + "pgpgin", + "pgpgout", + "pgfault", + "pgmajfault", +}; + static int memcg_stat_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); @@ -3138,22 +3138,20 @@ static int memcg_stat_show(struct seq_file *m, void *v) struct mem_cgroup *mi; unsigned int i; - BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_stat_names) != - MEM_CGROUP_STAT_NSTATS); - BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_events_names) != - MEM_CGROUP_EVENTS_NSTATS); + BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats)); BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); - for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { - if (i == MEM_CGROUP_STAT_SWAP && !do_memsw_account()) + for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { + if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) continue; - seq_printf(m, "%s %lu\n", mem_cgroup_stat_names[i], - mem_cgroup_read_stat(memcg, i) * PAGE_SIZE); + seq_printf(m, "%s %lu\n", memcg1_stat_names[i], + memcg_page_state(memcg, memcg1_stats[i]) * + PAGE_SIZE); } - for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) - seq_printf(m, "%s %lu\n", mem_cgroup_events_names[i], - mem_cgroup_read_events(memcg, i)); + for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) + seq_printf(m, "%s %lu\n", memcg1_event_names[i], + memcg_sum_events(memcg, memcg1_events[i])); for (i = 0; i < NR_LRU_LISTS; i++) seq_printf(m, "%s %lu\n", mem_cgroup_lru_names[i], @@ -3171,23 +3169,23 @@ static int memcg_stat_show(struct seq_file *m, void *v) seq_printf(m, "hierarchical_memsw_limit %llu\n", (u64)memsw * PAGE_SIZE); - for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { + for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { unsigned long long val = 0; - if (i == MEM_CGROUP_STAT_SWAP && !do_memsw_account()) + if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) continue; for_each_mem_cgroup_tree(mi, memcg) - val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE; - seq_printf(m, "total_%s %llu\n", mem_cgroup_stat_names[i], val); + val += memcg_page_state(mi, memcg1_stats[i]) * + PAGE_SIZE; + seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i], val); } - for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) { + for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) { unsigned long long val = 0; for_each_mem_cgroup_tree(mi, memcg) - val += mem_cgroup_read_events(mi, i); - seq_printf(m, "total_%s %llu\n", - mem_cgroup_events_names[i], val); + val += memcg_sum_events(mi, memcg1_events[i]); + seq_printf(m, "total_%s %llu\n", memcg1_event_names[i], val); } for (i = 0; i < NR_LRU_LISTS; i++) { @@ -3652,10 +3650,10 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); struct mem_cgroup *parent; - *pdirty = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_DIRTY); + *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY); /* this should eventually include NR_UNSTABLE_NFS */ - *pwriteback = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_WRITEBACK); + *pwriteback = memcg_page_state(memcg, NR_WRITEBACK); *pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) | (1 << LRU_ACTIVE_FILE)); *pheadroom = PAGE_COUNTER_MAX; @@ -4511,33 +4509,29 @@ static int mem_cgroup_move_account(struct page *page, spin_lock_irqsave(&from->move_lock, flags); if (!anon && page_mapped(page)) { - __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], - nr_pages); - __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], - nr_pages); + __this_cpu_sub(from->stat->count[NR_FILE_MAPPED], nr_pages); + __this_cpu_add(to->stat->count[NR_FILE_MAPPED], nr_pages); } /* * move_lock grabbed above and caller set from->moving_account, so - * mem_cgroup_update_page_stat() will serialize updates to PageDirty. + * mod_memcg_page_state will serialize updates to PageDirty. * So mapping should be stable for dirty pages. */ if (!anon && PageDirty(page)) { struct address_space *mapping = page_mapping(page); if (mapping_cap_account_dirty(mapping)) { - __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_DIRTY], + __this_cpu_sub(from->stat->count[NR_FILE_DIRTY], nr_pages); - __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_DIRTY], + __this_cpu_add(to->stat->count[NR_FILE_DIRTY], nr_pages); } } if (PageWriteback(page)) { - __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_WRITEBACK], - nr_pages); - __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_WRITEBACK], - nr_pages); + __this_cpu_sub(from->stat->count[NR_WRITEBACK], nr_pages); + __this_cpu_add(to->stat->count[NR_WRITEBACK], nr_pages); } /* @@ -5154,7 +5148,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, continue; } - mem_cgroup_events(memcg, MEMCG_OOM, 1); + mem_cgroup_event(memcg, MEMCG_OOM); if (!mem_cgroup_out_of_memory(memcg, GFP_KERNEL, 0)) break; } @@ -5167,10 +5161,10 @@ static int memory_events_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - seq_printf(m, "low %lu\n", mem_cgroup_read_events(memcg, MEMCG_LOW)); - seq_printf(m, "high %lu\n", mem_cgroup_read_events(memcg, MEMCG_HIGH)); - seq_printf(m, "max %lu\n", mem_cgroup_read_events(memcg, MEMCG_MAX)); - seq_printf(m, "oom %lu\n", mem_cgroup_read_events(memcg, MEMCG_OOM)); + seq_printf(m, "low %lu\n", memcg_sum_events(memcg, MEMCG_LOW)); + seq_printf(m, "high %lu\n", memcg_sum_events(memcg, MEMCG_HIGH)); + seq_printf(m, "max %lu\n", memcg_sum_events(memcg, MEMCG_MAX)); + seq_printf(m, "oom %lu\n", memcg_sum_events(memcg, MEMCG_OOM)); return 0; } @@ -5197,9 +5191,9 @@ static int memory_stat_show(struct seq_file *m, void *v) tree_events(memcg, events); seq_printf(m, "anon %llu\n", - (u64)stat[MEM_CGROUP_STAT_RSS] * PAGE_SIZE); + (u64)stat[MEMCG_RSS] * PAGE_SIZE); seq_printf(m, "file %llu\n", - (u64)stat[MEM_CGROUP_STAT_CACHE] * PAGE_SIZE); + (u64)stat[MEMCG_CACHE] * PAGE_SIZE); seq_printf(m, "kernel_stack %llu\n", (u64)stat[MEMCG_KERNEL_STACK_KB] * 1024); seq_printf(m, "slab %llu\n", @@ -5208,12 +5202,14 @@ static int memory_stat_show(struct seq_file *m, void *v) seq_printf(m, "sock %llu\n", (u64)stat[MEMCG_SOCK] * PAGE_SIZE); + seq_printf(m, "shmem %llu\n", + (u64)stat[NR_SHMEM] * PAGE_SIZE); seq_printf(m, "file_mapped %llu\n", - (u64)stat[MEM_CGROUP_STAT_FILE_MAPPED] * PAGE_SIZE); + (u64)stat[NR_FILE_MAPPED] * PAGE_SIZE); seq_printf(m, "file_dirty %llu\n", - (u64)stat[MEM_CGROUP_STAT_DIRTY] * PAGE_SIZE); + (u64)stat[NR_FILE_DIRTY] * PAGE_SIZE); seq_printf(m, "file_writeback %llu\n", - (u64)stat[MEM_CGROUP_STAT_WRITEBACK] * PAGE_SIZE); + (u64)stat[NR_WRITEBACK] * PAGE_SIZE); for (i = 0; i < NR_LRU_LISTS; i++) { struct mem_cgroup *mi; @@ -5232,10 +5228,15 @@ static int memory_stat_show(struct seq_file *m, void *v) /* Accumulated memory events */ - seq_printf(m, "pgfault %lu\n", - events[MEM_CGROUP_EVENTS_PGFAULT]); - seq_printf(m, "pgmajfault %lu\n", - events[MEM_CGROUP_EVENTS_PGMAJFAULT]); + seq_printf(m, "pgfault %lu\n", events[PGFAULT]); + seq_printf(m, "pgmajfault %lu\n", events[PGMAJFAULT]); + + seq_printf(m, "workingset_refault %lu\n", + stat[WORKINGSET_REFAULT]); + seq_printf(m, "workingset_activate %lu\n", + stat[WORKINGSET_ACTIVATE]); + seq_printf(m, "workingset_nodereclaim %lu\n", + stat[WORKINGSET_NODERECLAIM]); return 0; } @@ -5476,8 +5477,8 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout, unsigned long nr_anon, unsigned long nr_file, - unsigned long nr_huge, unsigned long nr_kmem, - struct page *dummy_page) + unsigned long nr_kmem, unsigned long nr_huge, + unsigned long nr_shmem, struct page *dummy_page) { unsigned long nr_pages = nr_anon + nr_file + nr_kmem; unsigned long flags; @@ -5492,10 +5493,11 @@ static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout, } local_irq_save(flags); - __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS], nr_anon); - __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_file); - __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], nr_huge); - __this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT], pgpgout); + __this_cpu_sub(memcg->stat->count[MEMCG_RSS], nr_anon); + __this_cpu_sub(memcg->stat->count[MEMCG_CACHE], nr_file); + __this_cpu_sub(memcg->stat->count[MEMCG_RSS_HUGE], nr_huge); + __this_cpu_sub(memcg->stat->count[NR_SHMEM], nr_shmem); + __this_cpu_add(memcg->stat->events[PGPGOUT], pgpgout); __this_cpu_add(memcg->stat->nr_page_events, nr_pages); memcg_check_events(memcg, dummy_page); local_irq_restore(flags); @@ -5507,6 +5509,7 @@ static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout, static void uncharge_list(struct list_head *page_list) { struct mem_cgroup *memcg = NULL; + unsigned long nr_shmem = 0; unsigned long nr_anon = 0; unsigned long nr_file = 0; unsigned long nr_huge = 0; @@ -5539,9 +5542,9 @@ static void uncharge_list(struct list_head *page_list) if (memcg != page->mem_cgroup) { if (memcg) { uncharge_batch(memcg, pgpgout, nr_anon, nr_file, - nr_huge, nr_kmem, page); - pgpgout = nr_anon = nr_file = - nr_huge = nr_kmem = 0; + nr_kmem, nr_huge, nr_shmem, page); + pgpgout = nr_anon = nr_file = nr_kmem = 0; + nr_huge = nr_shmem = 0; } memcg = page->mem_cgroup; } @@ -5555,8 +5558,11 @@ static void uncharge_list(struct list_head *page_list) } if (PageAnon(page)) nr_anon += nr_pages; - else + else { nr_file += nr_pages; + if (PageSwapBacked(page)) + nr_shmem += nr_pages; + } pgpgout++; } else { nr_kmem += 1 << compound_order(page); @@ -5568,7 +5574,7 @@ static void uncharge_list(struct list_head *page_list) if (memcg) uncharge_batch(memcg, pgpgout, nr_anon, nr_file, - nr_huge, nr_kmem, page); + nr_kmem, nr_huge, nr_shmem, page); } /** diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 27f7210e7fab..73066b80d14a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -220,6 +220,9 @@ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno, */ void shake_page(struct page *p, int access) { + if (PageHuge(p)) + return; + if (!PageSlab(p)) { lru_add_drain_all(); if (PageLRU(p)) @@ -322,7 +325,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, * wrong earlier. */ static void kill_procs(struct list_head *to_kill, int forcekill, int trapno, - int fail, struct page *page, unsigned long pfn, + bool fail, struct page *page, unsigned long pfn, int flags) { struct to_kill *tk, *next; @@ -904,35 +907,36 @@ EXPORT_SYMBOL_GPL(get_hwpoison_page); * Do all that is necessary to remove user space mappings. Unmap * the pages and send SIGBUS to the processes if the data was dirty. */ -static int hwpoison_user_mappings(struct page *p, unsigned long pfn, +static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, int trapno, int flags, struct page **hpagep) { - enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS; + enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS; struct address_space *mapping; LIST_HEAD(tokill); - int ret; + bool unmap_success; int kill = 1, forcekill; struct page *hpage = *hpagep; + bool mlocked = PageMlocked(hpage); /* * Here we are interested only in user-mapped pages, so skip any * other types of pages. */ if (PageReserved(p) || PageSlab(p)) - return SWAP_SUCCESS; + return true; if (!(PageLRU(hpage) || PageHuge(p))) - return SWAP_SUCCESS; + return true; /* * This check implies we don't kill processes if their pages * are in the swap cache early. Those are always late kills. */ if (!page_mapped(hpage)) - return SWAP_SUCCESS; + return true; if (PageKsm(p)) { pr_err("Memory failure: %#lx: can't handle KSM pages.\n", pfn); - return SWAP_FAIL; + return false; } if (PageSwapCache(p)) { @@ -971,12 +975,19 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, if (kill) collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED); - ret = try_to_unmap(hpage, ttu); - if (ret != SWAP_SUCCESS) + unmap_success = try_to_unmap(hpage, ttu); + if (!unmap_success) pr_err("Memory failure: %#lx: failed to unmap page (mapcount=%d)\n", pfn, page_mapcount(hpage)); /* + * try_to_unmap() might put mlocked page in lru cache, so call + * shake_page() again to ensure that it's flushed. + */ + if (mlocked) + shake_page(hpage, 0); + + /* * Now that the dirty bit has been propagated to the * struct page and all unmaps done we can decide if * killing is needed or not. Only kill when the page @@ -987,10 +998,9 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * any accesses to the poisoned memory. */ forcekill = PageDirty(hpage) || (flags & MF_MUST_KILL); - kill_procs(&tokill, forcekill, trapno, - ret != SWAP_SUCCESS, p, pfn, flags); + kill_procs(&tokill, forcekill, trapno, !unmap_success, p, pfn, flags); - return ret; + return unmap_success; } static void set_page_hwpoison_huge_page(struct page *hpage) @@ -1138,22 +1148,14 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * The check (unnecessarily) ignores LRU pages being isolated and * walked by the page reclaim code, however that's not a big loss. */ - if (!PageHuge(p)) { - if (!PageLRU(p)) - shake_page(p, 0); - if (!PageLRU(p)) { - /* - * shake_page could have turned it free. - */ - if (is_free_buddy_page(p)) { - if (flags & MF_COUNT_INCREASED) - action_result(pfn, MF_MSG_BUDDY, MF_DELAYED); - else - action_result(pfn, MF_MSG_BUDDY_2ND, - MF_DELAYED); - return 0; - } - } + shake_page(p, 0); + /* shake_page could have turned it free. */ + if (!PageLRU(p) && is_free_buddy_page(p)) { + if (flags & MF_COUNT_INCREASED) + action_result(pfn, MF_MSG_BUDDY, MF_DELAYED); + else + action_result(pfn, MF_MSG_BUDDY_2ND, MF_DELAYED); + return 0; } lock_page(hpage); @@ -1230,8 +1232,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * When the raw error page is thp tail page, hpage points to the raw * page after thp split. */ - if (hwpoison_user_mappings(p, pfn, trapno, flags, &hpage) - != SWAP_SUCCESS) { + if (!hwpoison_user_mappings(p, pfn, trapno, flags, &hpage)) { action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED); res = -EBUSY; goto out; @@ -1543,8 +1544,8 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags) if (ret == 1 && !PageLRU(page)) { /* Drop page reference which is from __get_any_page() */ put_hwpoison_page(page); - pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", - pfn, page->flags); + pr_info("soft_offline: %#lx: unknown non LRU page type %lx (%pGp)\n", + pfn, page->flags, &page->flags); return -EIO; } } @@ -1585,8 +1586,8 @@ static int soft_offline_huge_page(struct page *page, int flags) 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", - pfn, ret, page->flags); + pr_info("soft offline: %#lx: migration failed %d, type %lx (%pGp)\n", + pfn, ret, page->flags, &page->flags); /* * We know that soft_offline_huge_page() tries to migrate * only one hugepage pointed to by hpage, so we need not @@ -1677,14 +1678,14 @@ static int __soft_offline_page(struct page *page, int flags) if (!list_empty(&pagelist)) putback_movable_pages(&pagelist); - pr_info("soft offline: %#lx: migration failed %d, type %lx\n", - pfn, ret, page->flags); + pr_info("soft offline: %#lx: migration failed %d, type %lx (%pGp)\n", + pfn, ret, page->flags, &page->flags); if (ret > 0) ret = -EIO; } } else { - pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n", - pfn, ret, page_count(page), page->flags); + pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx (%pGp)\n", + pfn, ret, page_count(page), page->flags, &page->flags); } return ret; } diff --git a/mm/memory.c b/mm/memory.c index 235ba51b2fbf..6ff5d729ded0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4298,7 +4298,7 @@ void __might_fault(const char *file, int line) * get paged out, therefore we'll never actually fault, and the * below annotations will generate false positives. */ - if (segment_eq(get_fs(), KERNEL_DS)) + if (uaccess_kernel()) return; if (pagefault_disabled()) return; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 6fa7208bcd56..b63d7d1239df 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1208,7 +1208,11 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) arch_refresh_nodedata(nid, pgdat); } else { - /* Reset the nr_zones, order and classzone_idx before reuse */ + /* + * Reset the nr_zones, order and classzone_idx before reuse. + * Note that kswapd will init kswapd_classzone_idx properly + * when it starts in the near future. + */ pgdat->nr_zones = 0; pgdat->kswapd_order = 0; pgdat->kswapd_classzone_idx = 0; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 75b2745bac41..37d0b334bfe9 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1529,7 +1529,6 @@ COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode) { - long err = 0; unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; DECLARE_BITMAP(bm, MAX_NUMNODES); @@ -1538,14 +1537,13 @@ COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) { - err = compat_get_bitmap(bm, nmask, nr_bits); + if (compat_get_bitmap(bm, nmask, nr_bits)) + return -EFAULT; nm = compat_alloc_user_space(alloc_size); - err |= copy_to_user(nm, bm, alloc_size); + if (copy_to_user(nm, bm, alloc_size)) + return -EFAULT; } - if (err) - return -EFAULT; - return sys_set_mempolicy(mode, nm, nr_bits+1); } @@ -1553,7 +1551,6 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, compat_ulong_t, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode, compat_ulong_t, flags) { - long err = 0; unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; nodemask_t bm; @@ -1562,14 +1559,13 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) { - err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits); + if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits)) + return -EFAULT; nm = compat_alloc_user_space(alloc_size); - err |= copy_to_user(nm, nodes_addr(bm), alloc_size); + if (copy_to_user(nm, nodes_addr(bm), alloc_size)) + return -EFAULT; } - if (err) - return -EFAULT; - return sys_mbind(start, len, mode, nm, nr_bits+1, flags); } diff --git a/mm/migrate.c b/mm/migrate.c index 9a0897a14d37..89a0a1707f4c 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -184,9 +184,9 @@ void putback_movable_pages(struct list_head *l) unlock_page(page); put_page(page); } else { - putback_lru_page(page); dec_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); + putback_lru_page(page); } } } @@ -194,7 +194,7 @@ void putback_movable_pages(struct list_head *l) /* * Restore a potential migration pte to a working pte entry */ -static int remove_migration_pte(struct page *page, struct vm_area_struct *vma, +static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *old) { struct page_vma_mapped_walk pvmw = { @@ -209,8 +209,11 @@ static int remove_migration_pte(struct page *page, struct vm_area_struct *vma, VM_BUG_ON_PAGE(PageTail(page), page); while (page_vma_mapped_walk(&pvmw)) { - new = page - pvmw.page->index + - linear_page_index(vma, pvmw.address); + if (PageKsm(page)) + new = page; + else + new = page - pvmw.page->index + + linear_page_index(vma, pvmw.address); get_page(new); pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot))); @@ -250,7 +253,7 @@ static int remove_migration_pte(struct page *page, struct vm_area_struct *vma, update_mmu_cache(vma, pvmw.address, pvmw.pte); } - return SWAP_AGAIN; + return true; } /* @@ -1719,9 +1722,6 @@ static bool migrate_balanced_pgdat(struct pglist_data *pgdat, { int z; - if (!pgdat_reclaimable(pgdat)) - return false; - for (z = pgdat->nr_zones - 1; z >= 0; z--) { struct zone *zone = pgdat->node_zones + z; @@ -1944,7 +1944,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, /* Prepare a page as a migration target */ __SetPageLocked(new_page); - __SetPageSwapBacked(new_page); + if (PageSwapBacked(page)) + __SetPageSwapBacked(new_page); /* anon mapping, we can simply copy page->mapping to the new page: */ new_page->mapping = page->mapping; diff --git a/mm/mlock.c b/mm/mlock.c index 0dd9ca18e19e..c483c5c20b4b 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -123,17 +123,15 @@ static bool __munlock_isolate_lru_page(struct page *page, bool getpage) */ static void __munlock_isolated_page(struct page *page) { - int ret = SWAP_AGAIN; - /* * Optimization: if the page was mapped just once, that's our mapping * and we don't need to check all the other vmas. */ if (page_mapcount(page) > 1) - ret = try_to_munlock(page); + try_to_munlock(page); /* Did try_to_unlock() succeed or punt? */ - if (ret != SWAP_MLOCK) + if (!PageMlocked(page)) count_vm_event(UNEVICTABLE_PGMUNLOCKED); putback_lru_page(page); diff --git a/mm/mmap.c b/mm/mmap.c index bfbe8856d134..f82741e199c0 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1479,7 +1479,7 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, struct user_struct *user = NULL; struct hstate *hs; - hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & SHM_HUGE_MASK); + hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (!hs) return -EINVAL; diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index a7652acd2ab9..54ca54562928 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -21,7 +21,7 @@ #include <linux/slab.h> /* global SRCU for all MMs */ -static struct srcu_struct srcu; +DEFINE_STATIC_SRCU(srcu); /* * This function allows mmu_notifier::release callback to delay a call to @@ -252,12 +252,6 @@ static int do_mmu_notifier_register(struct mmu_notifier *mn, BUG_ON(atomic_read(&mm->mm_users) <= 0); - /* - * Verify that mmu_notifier_init() already run and the global srcu is - * initialized. - */ - BUG_ON(!srcu.per_cpu_ref); - ret = -ENOMEM; mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL); if (unlikely(!mmu_notifier_mm)) @@ -406,9 +400,3 @@ void mmu_notifier_unregister_no_release(struct mmu_notifier *mn, mmdrop(mm); } EXPORT_SYMBOL_GPL(mmu_notifier_unregister_no_release); - -static int __init mmu_notifier_init(void) -{ - return init_srcu_struct(&srcu); -} -subsys_initcall(mmu_notifier_init); diff --git a/mm/nommu.c b/mm/nommu.c index 2d131b97a851..fc184f597d59 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -237,12 +237,16 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) } EXPORT_SYMBOL(__vmalloc); +void *__vmalloc_node_flags(unsigned long size, int node, gfp_t flags) +{ + return __vmalloc(size, flags, PAGE_KERNEL); +} + void *vmalloc_user(unsigned long size) { void *ret; - ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, - PAGE_KERNEL); + ret = __vmalloc(size, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL); if (ret) { struct vm_area_struct *vma; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index d083714a2bb9..04c9143a8625 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -685,6 +685,7 @@ void exit_oom_victim(void) void oom_killer_enable(void) { oom_killer_disabled = false; + pr_info("OOM killer enabled.\n"); } /** @@ -721,6 +722,7 @@ bool oom_killer_disable(signed long timeout) oom_killer_enable(); return false; } + pr_info("OOM killer disabled.\n"); return true; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index d8ac2a7fb9e7..143c1c25d680 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -650,9 +650,8 @@ int wb_domain_init(struct wb_domain *dom, gfp_t gfp) spin_lock_init(&dom->lock); - init_timer_deferrable(&dom->period_timer); - dom->period_timer.function = writeout_period; - dom->period_timer.data = (unsigned long)dom; + setup_deferrable_timer(&dom->period_timer, writeout_period, + (unsigned long)dom); dom->dirty_limit_tstamp = jiffies; @@ -2353,10 +2352,16 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) if (wbc->nr_to_write <= 0) return 0; - if (mapping->a_ops->writepages) - ret = mapping->a_ops->writepages(mapping, wbc); - else - ret = generic_writepages(mapping, wbc); + while (1) { + if (mapping->a_ops->writepages) + ret = mapping->a_ops->writepages(mapping, wbc); + else + ret = generic_writepages(mapping, wbc); + if ((ret != -ENOMEM) || (wbc->sync_mode != WB_SYNC_ALL)) + break; + cond_resched(); + congestion_wait(BLK_RW_ASYNC, HZ/50); + } return ret; } @@ -2428,7 +2433,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) inode_attach_wb(inode, page); wb = inode_to_wb(inode); - mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_DIRTY); + inc_memcg_page_state(page, NR_FILE_DIRTY); __inc_node_page_state(page, NR_FILE_DIRTY); __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); __inc_node_page_state(page, NR_DIRTIED); @@ -2450,7 +2455,7 @@ void account_page_cleaned(struct page *page, struct address_space *mapping, struct bdi_writeback *wb) { if (mapping_cap_account_dirty(mapping)) { - mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY); + dec_memcg_page_state(page, NR_FILE_DIRTY); dec_node_page_state(page, NR_FILE_DIRTY); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); dec_wb_stat(wb, WB_RECLAIMABLE); @@ -2707,7 +2712,7 @@ int clear_page_dirty_for_io(struct page *page) */ wb = unlocked_inode_to_wb_begin(inode, &locked); if (TestClearPageDirty(page)) { - mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY); + dec_memcg_page_state(page, NR_FILE_DIRTY); dec_node_page_state(page, NR_FILE_DIRTY); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); dec_wb_stat(wb, WB_RECLAIMABLE); @@ -2754,7 +2759,7 @@ int test_clear_page_writeback(struct page *page) ret = TestClearPageWriteback(page); } if (ret) { - mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK); + dec_memcg_page_state(page, NR_WRITEBACK); dec_node_page_state(page, NR_WRITEBACK); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); inc_node_page_state(page, NR_WRITTEN); @@ -2809,7 +2814,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) ret = TestSetPageWriteback(page); } if (!ret) { - mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK); + inc_memcg_page_state(page, NR_WRITEBACK); inc_node_page_state(page, NR_WRITEBACK); inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6cbde310abed..f9e450c6b6e4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -65,6 +65,7 @@ #include <linux/page_owner.h> #include <linux/kthread.h> #include <linux/memcontrol.h> +#include <linux/ftrace.h> #include <asm/sections.h> #include <asm/tlbflush.h> @@ -1090,14 +1091,10 @@ static void free_pcppages_bulk(struct zone *zone, int count, { int migratetype = 0; int batch_free = 0; - unsigned long nr_scanned, flags; bool isolated_pageblocks; - spin_lock_irqsave(&zone->lock, flags); + spin_lock(&zone->lock); isolated_pageblocks = has_isolate_pageblock(zone); - nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED); - if (nr_scanned) - __mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned); while (count) { struct page *page; @@ -1142,7 +1139,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, trace_mm_page_pcpu_drain(page, 0, mt); } while (--count && --batch_free && !list_empty(list)); } - spin_unlock_irqrestore(&zone->lock, flags); + spin_unlock(&zone->lock); } static void free_one_page(struct zone *zone, @@ -1150,19 +1147,13 @@ static void free_one_page(struct zone *zone, unsigned int order, int migratetype) { - unsigned long nr_scanned, flags; - spin_lock_irqsave(&zone->lock, flags); - __count_vm_events(PGFREE, 1 << order); - nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED); - if (nr_scanned) - __mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned); - + spin_lock(&zone->lock); if (unlikely(has_isolate_pageblock(zone) || is_migrate_isolate(migratetype))) { migratetype = get_pfnblock_migratetype(page, pfn); } __free_one_page(page, pfn, zone, order, migratetype); - spin_unlock_irqrestore(&zone->lock, flags); + spin_unlock(&zone->lock); } static void __meminit __init_single_page(struct page *page, unsigned long pfn, @@ -1240,6 +1231,7 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end) static void __free_pages_ok(struct page *page, unsigned int order) { + unsigned long flags; int migratetype; unsigned long pfn = page_to_pfn(page); @@ -1247,7 +1239,10 @@ static void __free_pages_ok(struct page *page, unsigned int order) return; migratetype = get_pfnblock_migratetype(page, pfn); + local_irq_save(flags); + __count_vm_events(PGFREE, 1 << order); free_one_page(page_zone(page), page, pfn, order, migratetype); + local_irq_restore(flags); } static void __init __free_pages_boot_core(struct page *page, unsigned int order) @@ -1695,10 +1690,10 @@ static inline int check_new_page(struct page *page) return 1; } -static inline bool free_pages_prezeroed(bool poisoned) +static inline bool free_pages_prezeroed(void) { return IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) && - page_poisoning_enabled() && poisoned; + page_poisoning_enabled(); } #ifdef CONFIG_DEBUG_VM @@ -1752,17 +1747,10 @@ static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags unsigned int alloc_flags) { int i; - bool poisoned = true; - - for (i = 0; i < (1 << order); i++) { - struct page *p = page + i; - if (poisoned) - poisoned &= page_is_poisoned(p); - } post_alloc_hook(page, order, gfp_flags); - if (!free_pages_prezeroed(poisoned) && (gfp_flags & __GFP_ZERO)) + if (!free_pages_prezeroed() && (gfp_flags & __GFP_ZERO)) for (i = 0; i < (1 << order); i++) clear_highpage(page + i); @@ -1844,9 +1832,9 @@ static inline struct page *__rmqueue_cma_fallback(struct zone *zone, * Note that start_page and end_pages are not aligned on a pageblock * boundary. If alignment is required, use move_freepages_block() */ -int move_freepages(struct zone *zone, +static int move_freepages(struct zone *zone, struct page *start_page, struct page *end_page, - int migratetype) + int migratetype, int *num_movable) { struct page *page; unsigned int order; @@ -1863,6 +1851,9 @@ int move_freepages(struct zone *zone, VM_BUG_ON(page_zone(start_page) != page_zone(end_page)); #endif + if (num_movable) + *num_movable = 0; + for (page = start_page; page <= end_page;) { if (!pfn_valid_within(page_to_pfn(page))) { page++; @@ -1873,6 +1864,15 @@ int move_freepages(struct zone *zone, VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page); if (!PageBuddy(page)) { + /* + * We assume that pages that could be isolated for + * migration are movable. But we don't actually try + * isolating, as that would be expensive. + */ + if (num_movable && + (PageLRU(page) || __PageMovable(page))) + (*num_movable)++; + page++; continue; } @@ -1888,7 +1888,7 @@ int move_freepages(struct zone *zone, } int move_freepages_block(struct zone *zone, struct page *page, - int migratetype) + int migratetype, int *num_movable) { unsigned long start_pfn, end_pfn; struct page *start_page, *end_page; @@ -1905,7 +1905,8 @@ int move_freepages_block(struct zone *zone, struct page *page, if (!zone_spans_pfn(zone, end_pfn)) return 0; - return move_freepages(zone, start_page, end_page, migratetype); + return move_freepages(zone, start_page, end_page, migratetype, + num_movable); } static void change_pageblock_range(struct page *pageblock_page, @@ -1955,28 +1956,79 @@ static bool can_steal_fallback(unsigned int order, int start_mt) /* * This function implements actual steal behaviour. If order is large enough, * we can steal whole pageblock. If not, we first move freepages in this - * pageblock and check whether half of pages are moved or not. If half of - * pages are moved, we can change migratetype of pageblock and permanently - * use it's pages as requested migratetype in the future. + * pageblock to our migratetype and determine how many already-allocated pages + * are there in the pageblock with a compatible migratetype. If at least half + * of pages are free or compatible, we can change migratetype of the pageblock + * itself, so pages freed in the future will be put on the correct free list. */ static void steal_suitable_fallback(struct zone *zone, struct page *page, - int start_type) + int start_type, bool whole_block) { unsigned int current_order = page_order(page); - int pages; + struct free_area *area; + int free_pages, movable_pages, alike_pages; + int old_block_type; + + old_block_type = get_pageblock_migratetype(page); + + /* + * This can happen due to races and we want to prevent broken + * highatomic accounting. + */ + if (is_migrate_highatomic(old_block_type)) + goto single_page; /* Take ownership for orders >= pageblock_order */ if (current_order >= pageblock_order) { change_pageblock_range(page, current_order, start_type); - return; + goto single_page; + } + + /* We are not allowed to try stealing from the whole block */ + if (!whole_block) + goto single_page; + + free_pages = move_freepages_block(zone, page, start_type, + &movable_pages); + /* + * Determine how many pages are compatible with our allocation. + * For movable allocation, it's the number of movable pages which + * we just obtained. For other types it's a bit more tricky. + */ + if (start_type == MIGRATE_MOVABLE) { + alike_pages = movable_pages; + } else { + /* + * If we are falling back a RECLAIMABLE or UNMOVABLE allocation + * to MOVABLE pageblock, consider all non-movable pages as + * compatible. If it's UNMOVABLE falling back to RECLAIMABLE or + * vice versa, be conservative since we can't distinguish the + * exact migratetype of non-movable pages. + */ + if (old_block_type == MIGRATE_MOVABLE) + alike_pages = pageblock_nr_pages + - (free_pages + movable_pages); + else + alike_pages = 0; } - pages = move_freepages_block(zone, page, start_type); + /* moving whole block can fail due to zone boundary conditions */ + if (!free_pages) + goto single_page; - /* Claim the whole block if over half of it is free */ - if (pages >= (1 << (pageblock_order-1)) || + /* + * If a sufficient number of pages in the block are either free or of + * comparable migratability as our allocation, claim the whole block. + */ + if (free_pages + alike_pages >= (1 << (pageblock_order-1)) || page_group_by_mobility_disabled) set_pageblock_migratetype(page, start_type); + + return; + +single_page: + area = &zone->free_area[current_order]; + list_move(&page->lru, &area->free_list[start_type]); } /* @@ -2042,11 +2094,11 @@ static void reserve_highatomic_pageblock(struct page *page, struct zone *zone, /* Yoink! */ mt = get_pageblock_migratetype(page); - if (mt != MIGRATE_HIGHATOMIC && - !is_migrate_isolate(mt) && !is_migrate_cma(mt)) { + if (!is_migrate_highatomic(mt) && !is_migrate_isolate(mt) + && !is_migrate_cma(mt)) { zone->nr_reserved_highatomic += pageblock_nr_pages; set_pageblock_migratetype(page, MIGRATE_HIGHATOMIC); - move_freepages_block(zone, page, MIGRATE_HIGHATOMIC); + move_freepages_block(zone, page, MIGRATE_HIGHATOMIC, NULL); } out_unlock: @@ -2100,8 +2152,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, * from highatomic to ac->migratetype. So we should * adjust the count once. */ - if (get_pageblock_migratetype(page) == - MIGRATE_HIGHATOMIC) { + if (is_migrate_highatomic_page(page)) { /* * It should never happen but changes to * locking could inadvertently allow a per-cpu @@ -2124,7 +2175,8 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, * may increase. */ set_pageblock_migratetype(page, ac->migratetype); - ret = move_freepages_block(zone, page, ac->migratetype); + ret = move_freepages_block(zone, page, ac->migratetype, + NULL); if (ret) { spin_unlock_irqrestore(&zone->lock, flags); return ret; @@ -2136,8 +2188,13 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, return false; } -/* Remove an element from the buddy allocator from the fallback list */ -static inline struct page * +/* + * Try finding a free buddy page on the fallback list and put it on the free + * list of requested migratetype, possibly along with other pages from the same + * block, depending on fragmentation avoidance heuristics. Returns true if + * fallback was found so that __rmqueue_smallest() can grab it. + */ +static inline bool __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) { struct free_area *area; @@ -2158,33 +2215,17 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) page = list_first_entry(&area->free_list[fallback_mt], struct page, lru); - if (can_steal && - get_pageblock_migratetype(page) != MIGRATE_HIGHATOMIC) - steal_suitable_fallback(zone, page, start_migratetype); - /* Remove the page from the freelists */ - area->nr_free--; - list_del(&page->lru); - rmv_page_order(page); - - expand(zone, page, order, current_order, area, - start_migratetype); - /* - * The pcppage_migratetype may differ from pageblock's - * migratetype depending on the decisions in - * find_suitable_fallback(). This is OK as long as it does not - * differ for MIGRATE_CMA pageblocks. Those can be used as - * fallback only via special __rmqueue_cma_fallback() function - */ - set_pcppage_migratetype(page, start_migratetype); + steal_suitable_fallback(zone, page, start_migratetype, + can_steal); trace_mm_page_alloc_extfrag(page, order, current_order, start_migratetype, fallback_mt); - return page; + return true; } - return NULL; + return false; } /* @@ -2196,13 +2237,14 @@ static struct page *__rmqueue(struct zone *zone, unsigned int order, { struct page *page; +retry: page = __rmqueue_smallest(zone, order, migratetype); if (unlikely(!page)) { if (migratetype == MIGRATE_MOVABLE) page = __rmqueue_cma_fallback(zone, order); - if (!page) - page = __rmqueue_fallback(zone, order, migratetype); + if (!page && __rmqueue_fallback(zone, order, migratetype)) + goto retry; } trace_mm_page_alloc_zone_locked(page, order, migratetype); @@ -2219,9 +2261,8 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, int migratetype, bool cold) { int i, alloced = 0; - unsigned long flags; - spin_lock_irqsave(&zone->lock, flags); + spin_lock(&zone->lock); for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype); if (unlikely(page == NULL)) @@ -2257,7 +2298,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * pages added to the pcp list. */ __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); - spin_unlock_irqrestore(&zone->lock, flags); + spin_unlock(&zone->lock); return alloced; } @@ -2373,6 +2414,13 @@ void drain_all_pages(struct zone *zone) */ static cpumask_t cpus_with_pcps; + /* + * Make sure nobody triggers this path before mm_percpu_wq is fully + * initialized. + */ + if (WARN_ON_ONCE(!mm_percpu_wq)) + return; + /* Workqueues cannot recurse */ if (current->flags & PF_WQ_WORKER) return; @@ -2422,7 +2470,7 @@ void drain_all_pages(struct zone *zone) for_each_cpu(cpu, &cpus_with_pcps) { struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu); INIT_WORK(work, drain_local_pages_wq); - schedule_work_on(cpu, work); + queue_work_on(cpu, mm_percpu_wq, work); } for_each_cpu(cpu, &cpus_with_pcps) flush_work(per_cpu_ptr(&pcpu_drain, cpu)); @@ -2478,25 +2526,22 @@ 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 (in_interrupt()) { - __free_pages_ok(page, 0); - return; - } - if (!free_pcp_prepare(page)) return; migratetype = get_pfnblock_migratetype(page, pfn); set_pcppage_migratetype(page, migratetype); - preempt_disable(); + local_irq_save(flags); + __count_vm_event(PGFREE); /* * We only track unmovable, reclaimable and movable on pcp lists. * Free ISOLATE pages back to the allocator because they are being - * offlined but treat RESERVE as movable pages so we can get those + * offlined but treat HIGHATOMIC as movable pages so we can get those * areas back if necessary. Otherwise, we may have to free * excessively into the page allocator */ @@ -2508,7 +2553,6 @@ void free_hot_cold_page(struct page *page, bool cold) migratetype = MIGRATE_MOVABLE; } - __count_vm_event(PGFREE); pcp = &this_cpu_ptr(zone->pageset)->pcp; if (!cold) list_add(&page->lru, &pcp->lists[migratetype]); @@ -2522,7 +2566,7 @@ void free_hot_cold_page(struct page *page, bool cold) } out: - preempt_enable(); + local_irq_restore(flags); } /* @@ -2607,7 +2651,7 @@ int __isolate_free_page(struct page *page, unsigned int order) for (; page < endpage; page += pageblock_nr_pages) { int mt = get_pageblock_migratetype(page); if (!is_migrate_isolate(mt) && !is_migrate_cma(mt) - && mt != MIGRATE_HIGHATOMIC) + && !is_migrate_highatomic(mt)) set_pageblock_migratetype(page, MIGRATE_MOVABLE); } @@ -2647,8 +2691,6 @@ static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, { struct page *page; - VM_BUG_ON(in_interrupt()); - do { if (list_empty(list)) { pcp->count += rmqueue_bulk(zone, 0, @@ -2679,8 +2721,9 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, struct list_head *list; bool cold = ((gfp_flags & __GFP_COLD) != 0); struct page *page; + unsigned long flags; - preempt_disable(); + local_irq_save(flags); pcp = &this_cpu_ptr(zone->pageset)->pcp; list = &pcp->lists[migratetype]; page = __rmqueue_pcplist(zone, migratetype, cold, pcp, list); @@ -2688,7 +2731,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); zone_statistics(preferred_zone, zone); } - preempt_enable(); + local_irq_restore(flags); return page; } @@ -2704,7 +2747,7 @@ struct page *rmqueue(struct zone *preferred_zone, unsigned long flags; struct page *page; - if (likely(order == 0) && !in_interrupt()) { + if (likely(order == 0)) { page = rmqueue_pcplist(preferred_zone, zone, order, gfp_flags, migratetype); goto out; @@ -3106,8 +3149,7 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...) static DEFINE_RATELIMIT_STATE(nopage_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); - if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs) || - debug_guardpage_minorder() > 0) + if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs)) return; pr_warn("%s: ", current->comm); @@ -3241,14 +3283,15 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, enum compact_priority prio, enum compact_result *compact_result) { struct page *page; + unsigned int noreclaim_flag; if (!order) return NULL; - current->flags |= PF_MEMALLOC; + noreclaim_flag = memalloc_noreclaim_save(); *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, prio); - current->flags &= ~PF_MEMALLOC; + memalloc_noreclaim_restore(noreclaim_flag); if (*compact_result <= COMPACT_INACTIVE) return NULL; @@ -3395,12 +3438,13 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, { struct reclaim_state reclaim_state; int progress; + unsigned int noreclaim_flag; cond_resched(); /* We now go into synchronous reclaim */ cpuset_memory_pressure_bump(); - current->flags |= PF_MEMALLOC; + noreclaim_flag = memalloc_noreclaim_save(); lockdep_set_current_reclaim_state(gfp_mask); reclaim_state.reclaimed_slab = 0; current->reclaim_state = &reclaim_state; @@ -3410,7 +3454,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, current->reclaim_state = NULL; lockdep_clear_current_reclaim_state(); - current->flags &= ~PF_MEMALLOC; + memalloc_noreclaim_restore(noreclaim_flag); cond_resched(); @@ -3518,19 +3562,12 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask) } /* - * Maximum number of reclaim retries without any progress before OOM killer - * is consider as the only way to move forward. - */ -#define MAX_RECLAIM_RETRIES 16 - -/* * Checks whether it makes sense to retry the reclaim to make a forward progress * for the given allocation request. - * The reclaim feedback represented by did_some_progress (any progress during - * the last reclaim round) and no_progress_loops (number of reclaim rounds without - * any progress in a row) is considered as well as the reclaimable pages on the - * applicable zone list (with a backoff mechanism which is a function of - * no_progress_loops). + * + * We give up when we either have tried MAX_RECLAIM_RETRIES in a row + * without success, or when we couldn't even meet the watermark if we + * reclaimed all remaining pages on the LRU lists. * * Returns true if a retry is viable or false to enter the oom path. */ @@ -3575,13 +3612,11 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, bool wmark; available = reclaimable = zone_reclaimable_pages(zone); - available -= DIV_ROUND_UP((*no_progress_loops) * available, - MAX_RECLAIM_RETRIES); available += zone_page_state_snapshot(zone, NR_FREE_PAGES); /* - * Would the allocation succeed if we reclaimed the whole - * available? + * Would the allocation succeed if we reclaimed all + * reclaimable pages? */ wmark = __zone_watermark_ok(zone, order, min_wmark, ac_classzone_idx(ac), alloc_flags, available); @@ -3632,6 +3667,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct alloc_context *ac) { bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM; + const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER; struct page *page = NULL; unsigned int alloc_flags; unsigned long did_some_progress; @@ -3699,12 +3735,17 @@ retry_cpuset: /* * For costly allocations, try direct compaction first, as it's likely - * that we have enough base pages and don't need to reclaim. Don't try - * that for allocations that are allowed to ignore watermarks, as the - * ALLOC_NO_WATERMARKS attempt didn't yet happen. + * that we have enough base pages and don't need to reclaim. For non- + * movable high-order allocations, do that as well, as compaction will + * try prevent permanent fragmentation by migrating from blocks of the + * same migratetype. + * Don't try this for allocations that are allowed to ignore + * watermarks, as the ALLOC_NO_WATERMARKS attempt didn't yet happen. */ - if (can_direct_reclaim && order > PAGE_ALLOC_COSTLY_ORDER && - !gfp_pfmemalloc_allowed(gfp_mask)) { + if (can_direct_reclaim && + (costly_order || + (order > 0 && ac->migratetype != MIGRATE_MOVABLE)) + && !gfp_pfmemalloc_allowed(gfp_mask)) { page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags, ac, INIT_COMPACT_PRIORITY, @@ -3716,7 +3757,7 @@ retry_cpuset: * Checks for costly allocations with __GFP_NORETRY, which * includes THP page fault allocations */ - if (gfp_mask & __GFP_NORETRY) { + if (costly_order && (gfp_mask & __GFP_NORETRY)) { /* * If compaction is deferred for high-order allocations, * it is because sync compaction recently failed. If @@ -3767,7 +3808,7 @@ retry: /* Make sure we know about allocations which stall for too long */ if (time_after(jiffies, alloc_start + stall_timeout)) { - warn_alloc(gfp_mask, ac->nodemask, + warn_alloc(gfp_mask & ~__GFP_NOWARN, ac->nodemask, "page allocation stalls for %ums, order:%u", jiffies_to_msecs(jiffies-alloc_start), order); stall_timeout += 10 * HZ; @@ -3797,7 +3838,7 @@ retry: * Do not retry costly high order allocations unless they are * __GFP_REPEAT */ - if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_REPEAT)) + if (costly_order && !(gfp_mask & __GFP_REPEAT)) goto nopage; if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags, @@ -3967,10 +4008,12 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, goto out; /* - * Runtime PM, block IO and its error handling path can deadlock - * because I/O on the device might not complete. + * Apply scoped allocation constraints. This is mainly about GFP_NOFS + * resp. GFP_NOIO which has to be inherited for all allocation requests + * from a particular context which has been marked by + * memalloc_no{fs,io}_{save,restore}. */ - alloc_mask = memalloc_noio_flags(gfp_mask); + alloc_mask = current_gfp_context(gfp_mask); ac.spread_dirty_pages = false; /* @@ -4243,7 +4286,8 @@ EXPORT_SYMBOL(free_pages_exact); * nr_free_zone_pages() counts the number of counts pages which are beyond the * high watermark within all zones at or below a given zone index. For each * zone, the number of pages is calculated as: - * managed_pages - high_pages + * + * nr_free_zone_pages = managed_pages - high_pages */ static unsigned long nr_free_zone_pages(int offset) { @@ -4505,7 +4549,6 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) #endif " writeback_tmp:%lukB" " unstable:%lukB" - " pages_scanned:%lu" " all_unreclaimable? %s" "\n", pgdat->node_id, @@ -4519,17 +4562,17 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) K(node_page_state(pgdat, NR_FILE_MAPPED)), K(node_page_state(pgdat, NR_FILE_DIRTY)), K(node_page_state(pgdat, NR_WRITEBACK)), + K(node_page_state(pgdat, NR_SHMEM)), #ifdef CONFIG_TRANSPARENT_HUGEPAGE K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR), K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR), K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR), #endif - K(node_page_state(pgdat, NR_SHMEM)), K(node_page_state(pgdat, NR_WRITEBACK_TEMP)), K(node_page_state(pgdat, NR_UNSTABLE_NFS)), - node_page_state(pgdat, NR_PAGES_SCANNED), - !pgdat_reclaimable(pgdat) ? "yes" : "no"); + pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ? + "yes" : "no"); } for_each_populated_zone(zone) { @@ -7424,7 +7467,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, .zone = page_zone(pfn_to_page(start)), .mode = MIGRATE_SYNC, .ignore_skip_hint = true, - .gfp_mask = memalloc_noio_flags(gfp_mask), + .gfp_mask = current_gfp_context(gfp_mask), }; INIT_LIST_HEAD(&cc.migratepages); diff --git a/mm/page_ext.c b/mm/page_ext.c index 121dcffc4ec1..88ccc044b09a 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -59,9 +59,6 @@ static struct page_ext_operations *page_ext_ops[] = { &debug_guardpage_ops, -#ifdef CONFIG_PAGE_POISONING - &page_poisoning_ops, -#endif #ifdef CONFIG_PAGE_OWNER &page_owner_ops, #endif @@ -127,15 +124,12 @@ struct page_ext *lookup_page_ext(struct page *page) struct page_ext *base; base = NODE_DATA(page_to_nid(page))->node_page_ext; -#if defined(CONFIG_DEBUG_VM) || defined(CONFIG_PAGE_POISONING) +#if defined(CONFIG_DEBUG_VM) /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are * allocated when feeding a range of pages to the allocator * for the first time during bootup or memory hotplug. - * - * This check is also necessary for ensuring page poisoning - * works as expected when enabled */ if (unlikely(!base)) return NULL; @@ -204,15 +198,12 @@ struct page_ext *lookup_page_ext(struct page *page) { unsigned long pfn = page_to_pfn(page); struct mem_section *section = __pfn_to_section(pfn); -#if defined(CONFIG_DEBUG_VM) || defined(CONFIG_PAGE_POISONING) +#if defined(CONFIG_DEBUG_VM) /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are * allocated when feeding a range of pages to the allocator * for the first time during bootup or memory hotplug. - * - * This check is also necessary for ensuring page poisoning - * works as expected when enabled */ if (!section->page_ext) return NULL; diff --git a/mm/page_idle.c b/mm/page_idle.c index b0ee56c56b58..1b0f48c62316 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -50,7 +50,7 @@ static struct page *page_idle_get_page(unsigned long pfn) return page; } -static int page_idle_clear_pte_refs_one(struct page *page, +static bool page_idle_clear_pte_refs_one(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *arg) { @@ -84,7 +84,7 @@ static int page_idle_clear_pte_refs_one(struct page *page, */ set_page_young(page); } - return SWAP_AGAIN; + return true; } static void page_idle_clear_pte_refs(struct page *page) diff --git a/mm/page_isolation.c b/mm/page_isolation.c index f4e17a57926a..5092e4ef00c8 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -66,7 +66,8 @@ out: set_pageblock_migratetype(page, MIGRATE_ISOLATE); zone->nr_isolate_pageblock++; - nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE); + nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE, + NULL); __mod_zone_freepage_state(zone, -nr_pages, migratetype); } @@ -88,7 +89,7 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype) zone = page_zone(page); spin_lock_irqsave(&zone->lock, flags); - if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE) + if (!is_migrate_isolate_page(page)) goto out; /* @@ -120,7 +121,7 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype) * pageblock scanning for freepage moving. */ if (!isolated_page) { - nr_pages = move_freepages_block(zone, page, migratetype); + nr_pages = move_freepages_block(zone, page, migratetype, NULL); __mod_zone_freepage_state(zone, nr_pages, migratetype); } set_pageblock_migratetype(page, migratetype); @@ -205,7 +206,7 @@ int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, pfn < end_pfn; pfn += pageblock_nr_pages) { page = __first_valid_page(pfn, pageblock_nr_pages); - if (!page || get_pageblock_migratetype(page) != MIGRATE_ISOLATE) + if (!page || !is_migrate_isolate_page(page)) continue; unset_migratetype_isolate(page, migratetype); } @@ -262,7 +263,7 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, */ for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { page = __first_valid_page(pfn, pageblock_nr_pages); - if (page && get_pageblock_migratetype(page) != MIGRATE_ISOLATE) + if (page && !is_migrate_isolate_page(page)) break; } page = __first_valid_page(start_pfn, end_pfn - start_pfn); diff --git a/mm/page_poison.c b/mm/page_poison.c index 2e647c65916b..be19e989ccff 100644 --- a/mm/page_poison.c +++ b/mm/page_poison.c @@ -6,7 +6,6 @@ #include <linux/poison.h> #include <linux/ratelimit.h> -static bool __page_poisoning_enabled __read_mostly; static bool want_page_poisoning __read_mostly; static int early_page_poison_param(char *buf) @@ -19,74 +18,21 @@ early_param("page_poison", early_page_poison_param); bool page_poisoning_enabled(void) { - return __page_poisoning_enabled; -} - -static bool need_page_poisoning(void) -{ - return want_page_poisoning; -} - -static void init_page_poisoning(void) -{ /* - * page poisoning is debug page alloc for some arches. If either - * of those options are enabled, enable poisoning + * Assumes that debug_pagealloc_enabled is set before + * free_all_bootmem. + * Page poisoning is debug page alloc for some arches. If + * either of those options are enabled, enable poisoning. */ - if (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC)) { - if (!want_page_poisoning && !debug_pagealloc_enabled()) - return; - } else { - if (!want_page_poisoning) - return; - } - - __page_poisoning_enabled = true; -} - -struct page_ext_operations page_poisoning_ops = { - .need = need_page_poisoning, - .init = init_page_poisoning, -}; - -static inline void set_page_poison(struct page *page) -{ - struct page_ext *page_ext; - - page_ext = lookup_page_ext(page); - if (unlikely(!page_ext)) - return; - - __set_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags); -} - -static inline void clear_page_poison(struct page *page) -{ - struct page_ext *page_ext; - - page_ext = lookup_page_ext(page); - if (unlikely(!page_ext)) - return; - - __clear_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags); -} - -bool page_is_poisoned(struct page *page) -{ - struct page_ext *page_ext; - - page_ext = lookup_page_ext(page); - if (unlikely(!page_ext)) - return false; - - return test_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags); + return (want_page_poisoning || + (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) && + debug_pagealloc_enabled())); } static void poison_page(struct page *page) { void *addr = kmap_atomic(page); - set_page_poison(page); memset(addr, PAGE_POISON, PAGE_SIZE); kunmap_atomic(addr); } @@ -140,12 +86,13 @@ static void unpoison_page(struct page *page) { void *addr; - if (!page_is_poisoned(page)) - return; - addr = kmap_atomic(page); + /* + * Page poisoning when enabled poisons each and every page + * that is freed to buddy. Thus no extra check is done to + * see if a page was posioned. + */ check_poison_mem(addr, PAGE_SIZE); - clear_page_poison(page); kunmap_atomic(addr); } diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index c4c9def8ffea..de9c40d7304a 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -111,12 +111,8 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (pvmw->pmd && !pvmw->pte) return not_found(pvmw); - /* Only for THP, seek to next pte entry makes sense */ - if (pvmw->pte) { - if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) - return not_found(pvmw); + if (pvmw->pte) goto next_pte; - } if (unlikely(PageHuge(pvmw->page))) { /* when pud is not present, pte will be NULL */ @@ -165,9 +161,14 @@ restart: while (1) { if (check_pte(pvmw)) return true; -next_pte: do { +next_pte: + /* Seek to next pte only makes sense for THP */ + if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) + return not_found(pvmw); + do { pvmw->address += PAGE_SIZE; - if (pvmw->address >= + if (pvmw->address >= pvmw->vma->vm_end || + pvmw->address >= __vma_address(pvmw->page, pvmw->vma) + hpage_nr_pages(pvmw->page) * PAGE_SIZE) return not_found(pvmw); diff --git a/mm/percpu.c b/mm/percpu.c index 60a6488e9e6d..e0aa8ae7bde7 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1284,18 +1284,7 @@ void free_percpu(void __percpu *ptr) } EXPORT_SYMBOL_GPL(free_percpu); -/** - * is_kernel_percpu_address - test whether address is from static percpu area - * @addr: address to test - * - * Test whether @addr belongs to in-kernel static percpu area. Module - * static percpu areas are not considered. For those, use - * is_module_percpu_address(). - * - * RETURNS: - * %true if @addr is from in-kernel static percpu area, %false otherwise. - */ -bool is_kernel_percpu_address(unsigned long addr) +bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr) { #ifdef CONFIG_SMP const size_t static_size = __per_cpu_end - __per_cpu_start; @@ -1304,16 +1293,39 @@ bool is_kernel_percpu_address(unsigned long addr) for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); + void *va = (void *)addr; - if ((void *)addr >= start && (void *)addr < start + static_size) + if (va >= start && va < start + static_size) { + if (can_addr) { + *can_addr = (unsigned long) (va - start); + *can_addr += (unsigned long) + per_cpu_ptr(base, get_boot_cpu_id()); + } return true; - } + } + } #endif /* on UP, can't distinguish from other static vars, always false */ return false; } /** + * is_kernel_percpu_address - test whether address is from static percpu area + * @addr: address to test + * + * Test whether @addr belongs to in-kernel static percpu area. Module + * static percpu areas are not considered. For those, use + * is_module_percpu_address(). + * + * RETURNS: + * %true if @addr is from in-kernel static percpu area, %false otherwise. + */ +bool is_kernel_percpu_address(unsigned long addr) +{ + return __is_kernel_percpu_address(addr, NULL); +} + +/** * per_cpu_ptr_to_phys - convert translated percpu address to physical address * @addr: the address to be converted to physical address * diff --git a/mm/rmap.c b/mm/rmap.c index 49ed681ccc7b..d405f0e0ee96 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -430,7 +430,7 @@ static void anon_vma_ctor(void *data) void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), - 0, SLAB_DESTROY_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, + 0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, anon_vma_ctor); anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC|SLAB_ACCOUNT); @@ -481,7 +481,7 @@ struct anon_vma *page_get_anon_vma(struct page *page) * If this page is still mapped, then its anon_vma cannot have been * freed. But if it has been unmapped, we have no security against the * anon_vma structure being freed and reused (for another anon_vma: - * SLAB_DESTROY_BY_RCU guarantees that - so the atomic_inc_not_zero() + * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero() * above cannot corrupt). */ if (!page_mapped(page)) { @@ -724,7 +724,7 @@ struct page_referenced_arg { /* * arg: page_referenced_arg will be passed */ -static int page_referenced_one(struct page *page, struct vm_area_struct *vma, +static bool page_referenced_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct page_referenced_arg *pra = arg; @@ -741,7 +741,7 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma, if (vma->vm_flags & VM_LOCKED) { page_vma_mapped_walk_done(&pvmw); pra->vm_flags |= VM_LOCKED; - return SWAP_FAIL; /* To break the loop */ + return false; /* To break the loop */ } if (pvmw.pte) { @@ -781,9 +781,9 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma, } if (!pra->mapcount) - return SWAP_SUCCESS; /* To break the loop */ + return false; /* To break the loop */ - return SWAP_AGAIN; + return true; } static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg) @@ -812,7 +812,6 @@ int page_referenced(struct page *page, struct mem_cgroup *memcg, unsigned long *vm_flags) { - int ret; int we_locked = 0; struct page_referenced_arg pra = { .mapcount = total_mapcount(page), @@ -846,7 +845,7 @@ int page_referenced(struct page *page, rwc.invalid_vma = invalid_page_referenced_vma; } - ret = rmap_walk(page, &rwc); + rmap_walk(page, &rwc); *vm_flags = pra.vm_flags; if (we_locked) @@ -855,7 +854,7 @@ int page_referenced(struct page *page, return pra.referenced; } -static int page_mkclean_one(struct page *page, struct vm_area_struct *vma, +static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct page_vma_mapped_walk pvmw = { @@ -908,7 +907,7 @@ static int page_mkclean_one(struct page *page, struct vm_area_struct *vma, } } - return SWAP_AGAIN; + return true; } static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) @@ -1159,7 +1158,7 @@ void page_add_file_rmap(struct page *page, bool compound) goto out; } __mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, nr); - mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); + mod_memcg_page_state(page, NR_FILE_MAPPED, nr); out: unlock_page_memcg(page); } @@ -1199,7 +1198,7 @@ static void page_remove_file_rmap(struct page *page, bool compound) * pte lock(a spinlock) is held, which implies preemption disabled. */ __mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, -nr); - mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); + mod_memcg_page_state(page, NR_FILE_MAPPED, -nr); if (unlikely(PageMlocked(page))) clear_page_mlock(page); @@ -1288,15 +1287,10 @@ void page_remove_rmap(struct page *page, bool compound) */ } -struct rmap_private { - enum ttu_flags flags; - int lazyfreed; -}; - /* * @arg: enum ttu_flags will be passed to this argument */ -static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, +static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; @@ -1307,13 +1301,12 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, }; pte_t pteval; struct page *subpage; - int ret = SWAP_AGAIN; - struct rmap_private *rp = arg; - enum ttu_flags flags = rp->flags; + bool ret = true; + enum ttu_flags flags = (enum ttu_flags)arg; /* munlock has nothing to gain from examining un-locked vmas */ if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED)) - return SWAP_AGAIN; + return true; if (flags & TTU_SPLIT_HUGE_PMD) { split_huge_pmd_address(vma, address, @@ -1336,7 +1329,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, */ mlock_vma_page(page); } - ret = SWAP_MLOCK; + ret = false; page_vma_mapped_walk_done(&pvmw); break; } @@ -1354,7 +1347,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (!(flags & TTU_IGNORE_ACCESS)) { if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) { - ret = SWAP_FAIL; + ret = false; page_vma_mapped_walk_done(&pvmw); break; } @@ -1424,18 +1417,34 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * Store the swap location in the pte. * See handle_pte_fault() ... */ - VM_BUG_ON_PAGE(!PageSwapCache(page), page); + if (unlikely(PageSwapBacked(page) != PageSwapCache(page))) { + WARN_ON_ONCE(1); + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + + /* MADV_FREE page check */ + if (!PageSwapBacked(page)) { + if (!PageDirty(page)) { + dec_mm_counter(mm, MM_ANONPAGES); + goto discard; + } - if (!PageDirty(page) && (flags & TTU_LZFREE)) { - /* It's a freeable page by MADV_FREE */ - dec_mm_counter(mm, MM_ANONPAGES); - rp->lazyfreed++; - goto discard; + /* + * If the page was redirtied, it cannot be + * discarded. Remap the page to page table. + */ + set_pte_at(mm, address, pvmw.pte, pteval); + SetPageSwapBacked(page); + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; } if (swap_duplicate(entry) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); - ret = SWAP_FAIL; + ret = false; page_vma_mapped_walk_done(&pvmw); break; } @@ -1492,24 +1501,14 @@ static int page_mapcount_is_zero(struct page *page) * * Tries to remove all the page table entries which are mapping this * page, used in the pageout path. Caller must hold the page lock. - * Return values are: * - * SWAP_SUCCESS - we succeeded in removing all mappings - * SWAP_AGAIN - we missed a mapping, try again later - * SWAP_FAIL - the page is unswappable - * SWAP_MLOCK - page is mlocked. + * If unmap is successful, return true. Otherwise, false. */ -int try_to_unmap(struct page *page, enum ttu_flags flags) +bool try_to_unmap(struct page *page, enum ttu_flags flags) { - int ret; - struct rmap_private rp = { - .flags = flags, - .lazyfreed = 0, - }; - struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, - .arg = &rp, + .arg = (void *)flags, .done = page_mapcount_is_zero, .anon_lock = page_lock_anon_vma_read, }; @@ -1526,16 +1525,11 @@ int try_to_unmap(struct page *page, enum ttu_flags flags) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) - ret = rmap_walk_locked(page, &rwc); + rmap_walk_locked(page, &rwc); else - ret = rmap_walk(page, &rwc); + rmap_walk(page, &rwc); - if (ret != SWAP_MLOCK && !page_mapcount(page)) { - ret = SWAP_SUCCESS; - if (rp.lazyfreed && !PageDirty(page)) - ret = SWAP_LZFREE; - } - return ret; + return !page_mapcount(page) ? true : false; } static int page_not_mapped(struct page *page) @@ -1550,34 +1544,22 @@ static int page_not_mapped(struct page *page) * Called from munlock code. Checks all of the VMAs mapping the page * to make sure nobody else has this page mlocked. The page will be * returned with PG_mlocked cleared if no other vmas have it mlocked. - * - * Return values are: - * - * SWAP_AGAIN - no vma is holding page mlocked, or, - * SWAP_AGAIN - page mapped in mlocked vma -- couldn't acquire mmap sem - * SWAP_FAIL - page cannot be located at present - * SWAP_MLOCK - page is now mlocked. */ -int try_to_munlock(struct page *page) -{ - int ret; - struct rmap_private rp = { - .flags = TTU_MUNLOCK, - .lazyfreed = 0, - }; +void try_to_munlock(struct page *page) +{ struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, - .arg = &rp, + .arg = (void *)TTU_MUNLOCK, .done = page_not_mapped, .anon_lock = page_lock_anon_vma_read, }; VM_BUG_ON_PAGE(!PageLocked(page) || PageLRU(page), page); + VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page); - ret = rmap_walk(page, &rwc); - return ret; + rmap_walk(page, &rwc); } void __put_anon_vma(struct anon_vma *anon_vma) @@ -1625,13 +1607,12 @@ static struct anon_vma *rmap_walk_anon_lock(struct page *page, * vm_flags for that VMA. That should be OK, because that vma shouldn't be * LOCKED. */ -static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, +static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, bool locked) { struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; struct anon_vma_chain *avc; - int ret = SWAP_AGAIN; if (locked) { anon_vma = page_anon_vma(page); @@ -1641,7 +1622,7 @@ static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, anon_vma = rmap_walk_anon_lock(page, rwc); } if (!anon_vma) - return ret; + return; pgoff_start = page_to_pgoff(page); pgoff_end = pgoff_start + hpage_nr_pages(page) - 1; @@ -1655,8 +1636,7 @@ static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; - ret = rwc->rmap_one(page, vma, address, rwc->arg); - if (ret != SWAP_AGAIN) + if (!rwc->rmap_one(page, vma, address, rwc->arg)) break; if (rwc->done && rwc->done(page)) break; @@ -1664,7 +1644,6 @@ static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, if (!locked) anon_vma_unlock_read(anon_vma); - return ret; } /* @@ -1680,13 +1659,12 @@ static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, * vm_flags for that VMA. That should be OK, because that vma shouldn't be * LOCKED. */ -static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, +static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, bool locked) { struct address_space *mapping = page_mapping(page); pgoff_t pgoff_start, pgoff_end; struct vm_area_struct *vma; - int ret = SWAP_AGAIN; /* * The page lock not only makes sure that page->mapping cannot @@ -1697,7 +1675,7 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, VM_BUG_ON_PAGE(!PageLocked(page), page); if (!mapping) - return ret; + return; pgoff_start = page_to_pgoff(page); pgoff_end = pgoff_start + hpage_nr_pages(page) - 1; @@ -1712,8 +1690,7 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; - ret = rwc->rmap_one(page, vma, address, rwc->arg); - if (ret != SWAP_AGAIN) + if (!rwc->rmap_one(page, vma, address, rwc->arg)) goto done; if (rwc->done && rwc->done(page)) goto done; @@ -1722,28 +1699,27 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, done: if (!locked) i_mmap_unlock_read(mapping); - return ret; } -int rmap_walk(struct page *page, struct rmap_walk_control *rwc) +void rmap_walk(struct page *page, struct rmap_walk_control *rwc) { if (unlikely(PageKsm(page))) - return rmap_walk_ksm(page, rwc); + rmap_walk_ksm(page, rwc); else if (PageAnon(page)) - return rmap_walk_anon(page, rwc, false); + rmap_walk_anon(page, rwc, false); else - return rmap_walk_file(page, rwc, false); + rmap_walk_file(page, rwc, false); } /* Like rmap_walk, but caller holds relevant rmap lock */ -int rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc) +void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc) { /* no ksm support for now */ VM_BUG_ON_PAGE(PageKsm(page), page); if (PageAnon(page)) - return rmap_walk_anon(page, rwc, true); + rmap_walk_anon(page, rwc, true); else - return rmap_walk_file(page, rwc, true); + rmap_walk_file(page, rwc, true); } #ifdef CONFIG_HUGETLB_PAGE diff --git a/mm/rodata_test.c b/mm/rodata_test.c index 0fd21670b513..6bb4deb12e78 100644 --- a/mm/rodata_test.c +++ b/mm/rodata_test.c @@ -9,11 +9,12 @@ * as published by the Free Software Foundation; version 2 * of the License. */ +#define pr_fmt(fmt) "rodata_test: " fmt + #include <linux/uaccess.h> #include <asm/sections.h> const int rodata_test_data = 0xC3; -EXPORT_SYMBOL_GPL(rodata_test_data); void rodata_test(void) { @@ -23,20 +24,20 @@ void rodata_test(void) /* test 1: read the value */ /* If this test fails, some previous testrun has clobbered the state */ if (!rodata_test_data) { - pr_err("rodata_test: test 1 fails (start data)\n"); + pr_err("test 1 fails (start data)\n"); return; } /* test 2: write to the variable; this should fault */ if (!probe_kernel_write((void *)&rodata_test_data, - (void *)&zero, sizeof(zero))) { - pr_err("rodata_test: test data was not read only\n"); + (void *)&zero, sizeof(zero))) { + pr_err("test data was not read only\n"); return; } /* test 3: check the value hasn't changed */ if (rodata_test_data == zero) { - pr_err("rodata_test: test data was changed\n"); + pr_err("test data was changed\n"); return; } @@ -44,13 +45,13 @@ void rodata_test(void) start = (unsigned long)__start_rodata; end = (unsigned long)__end_rodata; if (start & (PAGE_SIZE - 1)) { - pr_err("rodata_test: start of .rodata is not page size aligned\n"); + pr_err("start of .rodata is not page size aligned\n"); return; } if (end & (PAGE_SIZE - 1)) { - pr_err("rodata_test: end of .rodata is not page size aligned\n"); + pr_err("end of .rodata is not page size aligned\n"); return; } - pr_info("rodata_test: all tests were successful\n"); + pr_info("all tests were successful\n"); } diff --git a/mm/slab.c b/mm/slab.c index 807d86c76908..2a31ee3c5814 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1728,7 +1728,7 @@ static void slab_destroy(struct kmem_cache *cachep, struct page *page) freelist = page->freelist; slab_destroy_debugcheck(cachep, page); - if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) + if (unlikely(cachep->flags & SLAB_TYPESAFE_BY_RCU)) call_rcu(&page->rcu_head, kmem_rcu_free); else kmem_freepages(cachep, page); @@ -1924,7 +1924,7 @@ static bool set_objfreelist_slab_cache(struct kmem_cache *cachep, cachep->num = 0; - if (cachep->ctor || flags & SLAB_DESTROY_BY_RCU) + if (cachep->ctor || flags & SLAB_TYPESAFE_BY_RCU) return false; left = calculate_slab_order(cachep, size, @@ -2030,7 +2030,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) if (size < 4096 || fls(size - 1) == fls(size-1 + REDZONE_ALIGN + 2 * sizeof(unsigned long long))) flags |= SLAB_RED_ZONE | SLAB_STORE_USER; - if (!(flags & SLAB_DESTROY_BY_RCU)) + if (!(flags & SLAB_TYPESAFE_BY_RCU)) flags |= SLAB_POISON; #endif #endif @@ -3879,7 +3879,12 @@ static int __do_tune_cpucache(struct kmem_cache *cachep, int limit, prev = cachep->cpu_cache; cachep->cpu_cache = cpu_cache; - kick_all_cpus_sync(); + /* + * Without a previous cpu_cache there's no need to synchronize remote + * cpus, so skip the IPIs. + */ + if (prev) + kick_all_cpus_sync(); check_irq_on(); cachep->batchcount = batchcount; diff --git a/mm/slab.h b/mm/slab.h index 65e7c3fcac72..9cfcf099709c 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -126,7 +126,7 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size, /* Legal flag mask for kmem_cache_create(), for various configurations */ #define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | SLAB_PANIC | \ - SLAB_DESTROY_BY_RCU | SLAB_DEBUG_OBJECTS ) + SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS ) #if defined(CONFIG_DEBUG_SLAB) #define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER) @@ -415,7 +415,7 @@ static inline size_t slab_ksize(const struct kmem_cache *s) * back there or track user information then we can * only use the space before that information. */ - if (s->flags & (SLAB_DESTROY_BY_RCU | SLAB_STORE_USER)) + if (s->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_STORE_USER)) return s->inuse; /* * Else we can use all the padding etc for the allocation diff --git a/mm/slab_common.c b/mm/slab_common.c index 09d0e849b07f..01a0fe2eb332 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -39,7 +39,7 @@ static DECLARE_WORK(slab_caches_to_rcu_destroy_work, * Set of flags that will prevent slab merging */ #define SLAB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \ - SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \ + SLAB_TRACE | SLAB_TYPESAFE_BY_RCU | SLAB_NOLEAKTRACE | \ SLAB_FAILSLAB | SLAB_KASAN) #define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \ @@ -500,7 +500,7 @@ static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work) struct kmem_cache *s, *s2; /* - * On destruction, SLAB_DESTROY_BY_RCU kmem_caches are put on the + * On destruction, SLAB_TYPESAFE_BY_RCU kmem_caches are put on the * @slab_caches_to_rcu_destroy list. The slab pages are freed * through RCU and and the associated kmem_cache are dereferenced * while freeing the pages, so the kmem_caches should be freed only @@ -537,7 +537,7 @@ static int shutdown_cache(struct kmem_cache *s) memcg_unlink_cache(s); list_del(&s->list); - if (s->flags & SLAB_DESTROY_BY_RCU) { + if (s->flags & SLAB_TYPESAFE_BY_RCU) { list_add_tail(&s->list, &slab_caches_to_rcu_destroy); schedule_work(&slab_caches_to_rcu_destroy_work); } else { diff --git a/mm/slob.c b/mm/slob.c index eac04d4357ec..1bae78d71096 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -126,7 +126,7 @@ static inline void clear_slob_page_free(struct page *sp) /* * struct slob_rcu is inserted at the tail of allocated slob blocks, which - * were created with a SLAB_DESTROY_BY_RCU slab. slob_rcu is used to free + * were created with a SLAB_TYPESAFE_BY_RCU slab. slob_rcu is used to free * the block using call_rcu. */ struct slob_rcu { @@ -524,7 +524,7 @@ EXPORT_SYMBOL(ksize); int __kmem_cache_create(struct kmem_cache *c, unsigned long flags) { - if (flags & SLAB_DESTROY_BY_RCU) { + if (flags & SLAB_TYPESAFE_BY_RCU) { /* leave room for rcu footer at the end of object */ c->size += sizeof(struct slob_rcu); } @@ -598,7 +598,7 @@ static void kmem_rcu_free(struct rcu_head *head) void kmem_cache_free(struct kmem_cache *c, void *b) { kmemleak_free_recursive(b, c->flags); - if (unlikely(c->flags & SLAB_DESTROY_BY_RCU)) { + if (unlikely(c->flags & SLAB_TYPESAFE_BY_RCU)) { struct slob_rcu *slob_rcu; slob_rcu = b + (c->size - sizeof(struct slob_rcu)); slob_rcu->size = c->size; diff --git a/mm/slub.c b/mm/slub.c index 7f4bc7027ed5..57e5156f02be 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1687,7 +1687,7 @@ static void rcu_free_slab(struct rcu_head *h) static void free_slab(struct kmem_cache *s, struct page *page) { - if (unlikely(s->flags & SLAB_DESTROY_BY_RCU)) { + if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU)) { struct rcu_head *head; if (need_reserve_slab_rcu) { @@ -2963,7 +2963,7 @@ static __always_inline void slab_free(struct kmem_cache *s, struct page *page, * slab_free_freelist_hook() could have put the items into quarantine. * If so, no need to free them. */ - if (s->flags & SLAB_KASAN && !(s->flags & SLAB_DESTROY_BY_RCU)) + if (s->flags & SLAB_KASAN && !(s->flags & SLAB_TYPESAFE_BY_RCU)) return; do_slab_free(s, page, head, tail, cnt, addr); } @@ -3433,7 +3433,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * the slab may touch the object after free or before allocation * then we should never poison the object itself. */ - if ((flags & SLAB_POISON) && !(flags & SLAB_DESTROY_BY_RCU) && + if ((flags & SLAB_POISON) && !(flags & SLAB_TYPESAFE_BY_RCU) && !s->ctor) s->flags |= __OBJECT_POISON; else @@ -3455,7 +3455,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) */ s->inuse = size; - if (((flags & (SLAB_DESTROY_BY_RCU | SLAB_POISON)) || + if (((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) || s->ctor)) { /* * Relocate free pointer after the object if it is not @@ -3537,7 +3537,7 @@ static int kmem_cache_open(struct kmem_cache *s, unsigned long flags) s->flags = kmem_cache_flags(s->size, flags, s->name, s->ctor); s->reserved = 0; - if (need_reserve_slab_rcu && (s->flags & SLAB_DESTROY_BY_RCU)) + if (need_reserve_slab_rcu && (s->flags & SLAB_TYPESAFE_BY_RCU)) s->reserved = sizeof(struct rcu_head); if (!calculate_sizes(s, -1)) @@ -5042,7 +5042,7 @@ SLAB_ATTR_RO(cache_dma); static ssize_t destroy_by_rcu_show(struct kmem_cache *s, char *buf) { - return sprintf(buf, "%d\n", !!(s->flags & SLAB_DESTROY_BY_RCU)); + return sprintf(buf, "%d\n", !!(s->flags & SLAB_TYPESAFE_BY_RCU)); } SLAB_ATTR_RO(destroy_by_rcu); diff --git a/mm/sparse.c b/mm/sparse.c index db6bf3c97ea2..6903c8fc3085 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -248,10 +248,7 @@ static int __meminit sparse_init_one_section(struct mem_section *ms, unsigned long usemap_size(void) { - unsigned long size_bytes; - size_bytes = roundup(SECTION_BLOCKFLAGS_BITS, 8) / 8; - size_bytes = roundup(size_bytes, sizeof(unsigned long)); - return size_bytes; + return BITS_TO_LONGS(SECTION_BLOCKFLAGS_BITS) * sizeof(unsigned long); } #ifdef CONFIG_MEMORY_HOTPLUG diff --git a/mm/swap.c b/mm/swap.c index c4910f14f957..98d08b4579fa 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -46,7 +46,7 @@ int page_cluster; static DEFINE_PER_CPU(struct pagevec, lru_add_pvec); static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs); -static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs); +static DEFINE_PER_CPU(struct pagevec, lru_lazyfree_pvecs); #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs); #endif @@ -97,6 +97,16 @@ static void __put_compound_page(struct page *page) void __put_page(struct page *page) { + if (is_zone_device_page(page)) { + put_dev_pagemap(page->pgmap); + + /* + * The page belongs to the device that created pgmap. Do + * not return it to page allocator. + */ + return; + } + if (unlikely(PageCompound(page))) __put_compound_page(page); else @@ -561,20 +571,27 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, } -static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, +static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec, void *arg) { - if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { - int file = page_is_file_cache(page); - int lru = page_lru_base_type(page); + if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && + !PageUnevictable(page)) { + bool active = PageActive(page); - del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE); + del_page_from_lru_list(page, lruvec, + LRU_INACTIVE_ANON + active); ClearPageActive(page); ClearPageReferenced(page); - add_page_to_lru_list(page, lruvec, lru); + /* + * lazyfree pages are clean anonymous pages. They have + * SwapBacked flag cleared to distinguish normal anonymous + * pages + */ + ClearPageSwapBacked(page); + add_page_to_lru_list(page, lruvec, LRU_INACTIVE_FILE); - __count_vm_event(PGDEACTIVATE); - update_page_reclaim_stat(lruvec, file, 0); + __count_vm_events(PGLAZYFREE, hpage_nr_pages(page)); + update_page_reclaim_stat(lruvec, 1, 0); } } @@ -604,9 +621,9 @@ void lru_add_drain_cpu(int cpu) if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); - pvec = &per_cpu(lru_deactivate_pvecs, cpu); + pvec = &per_cpu(lru_lazyfree_pvecs, cpu); if (pagevec_count(pvec)) - pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); + pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); activate_page_drain(cpu); } @@ -638,22 +655,22 @@ void deactivate_file_page(struct page *page) } /** - * deactivate_page - deactivate a page + * mark_page_lazyfree - make an anon page lazyfree * @page: page to deactivate * - * deactivate_page() moves @page to the inactive list if @page was on the active - * list and was not an unevictable page. This is done to accelerate the reclaim - * of @page. + * mark_page_lazyfree() moves @page to the inactive file list. + * This is done to accelerate the reclaim of @page. */ -void deactivate_page(struct page *page) +void mark_page_lazyfree(struct page *page) { - if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { - struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs); + if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && + !PageUnevictable(page)) { + struct pagevec *pvec = &get_cpu_var(lru_lazyfree_pvecs); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) - pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); - put_cpu_var(lru_deactivate_pvecs); + pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); + put_cpu_var(lru_lazyfree_pvecs); } } @@ -670,30 +687,19 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy) static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); -/* - * lru_add_drain_wq is used to do lru_add_drain_all() from a WQ_MEM_RECLAIM - * workqueue, aiding in getting memory freed. - */ -static struct workqueue_struct *lru_add_drain_wq; - -static int __init lru_init(void) -{ - lru_add_drain_wq = alloc_workqueue("lru-add-drain", WQ_MEM_RECLAIM, 0); - - if (WARN(!lru_add_drain_wq, - "Failed to create workqueue lru_add_drain_wq")) - return -ENOMEM; - - return 0; -} -early_initcall(lru_init); - void lru_add_drain_all(void) { static DEFINE_MUTEX(lock); static struct cpumask has_work; int cpu; + /* + * Make sure nobody triggers this path before mm_percpu_wq is fully + * initialized. + */ + if (WARN_ON(!mm_percpu_wq)) + return; + mutex_lock(&lock); get_online_cpus(); cpumask_clear(&has_work); @@ -704,10 +710,10 @@ void lru_add_drain_all(void) if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) || - pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_lazyfree_pvecs, cpu)) || need_activate_page_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); - queue_work_on(cpu, lru_add_drain_wq, work); + queue_work_on(cpu, mm_percpu_wq, work); cpumask_set_cpu(cpu, &has_work); } } diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c index 310ac0b8f974..ac6318a064d3 100644 --- a/mm/swap_cgroup.c +++ b/mm/swap_cgroup.c @@ -201,6 +201,8 @@ void swap_cgroup_swapoff(int type) struct page *page = map[i]; if (page) __free_page(page); + if (!(i % SWAP_CLUSTER_MAX)) + cond_resched(); } vfree(map); } diff --git a/mm/swap_slots.c b/mm/swap_slots.c index 7ebb23836f68..58f6c78f1dad 100644 --- a/mm/swap_slots.c +++ b/mm/swap_slots.c @@ -31,6 +31,7 @@ #include <linux/cpumask.h> #include <linux/vmalloc.h> #include <linux/mutex.h> +#include <linux/mm.h> #ifdef CONFIG_SWAP @@ -119,16 +120,18 @@ static int alloc_swap_slot_cache(unsigned int cpu) /* * Do allocation outside swap_slots_cache_mutex - * as vzalloc could trigger reclaim and get_swap_page, + * as kvzalloc could trigger reclaim and get_swap_page, * which can lock swap_slots_cache_mutex. */ - slots = vzalloc(sizeof(swp_entry_t) * SWAP_SLOTS_CACHE_SIZE); + slots = kvzalloc(sizeof(swp_entry_t) * SWAP_SLOTS_CACHE_SIZE, + GFP_KERNEL); if (!slots) return -ENOMEM; - slots_ret = vzalloc(sizeof(swp_entry_t) * SWAP_SLOTS_CACHE_SIZE); + slots_ret = kvzalloc(sizeof(swp_entry_t) * SWAP_SLOTS_CACHE_SIZE, + GFP_KERNEL); if (!slots_ret) { - vfree(slots); + kvfree(slots); return -ENOMEM; } @@ -152,9 +155,9 @@ static int alloc_swap_slot_cache(unsigned int cpu) out: mutex_unlock(&swap_slots_cache_mutex); if (slots) - vfree(slots); + kvfree(slots); if (slots_ret) - vfree(slots_ret); + kvfree(slots_ret); return 0; } @@ -171,7 +174,7 @@ static void drain_slots_cache_cpu(unsigned int cpu, unsigned int type, cache->cur = 0; cache->nr = 0; if (free_slots && cache->slots) { - vfree(cache->slots); + kvfree(cache->slots); cache->slots = NULL; } mutex_unlock(&cache->alloc_lock); @@ -186,7 +189,7 @@ static void drain_slots_cache_cpu(unsigned int cpu, unsigned int type, } spin_unlock_irq(&cache->free_lock); if (slots) - vfree(slots); + kvfree(slots); } } @@ -241,8 +244,10 @@ int enable_swap_slots_cache(void) ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "swap_slots_cache", alloc_swap_slot_cache, free_slot_cache); - if (ret < 0) + if (WARN_ONCE(ret < 0, "Cache allocation failed (%s), operating " + "without swap slots cache.\n", __func__)) goto out_unlock; + swap_slot_cache_initialized = true; __reenable_swap_slots_cache(); out_unlock: @@ -267,8 +272,6 @@ int free_swap_slot(swp_entry_t entry) { struct swap_slots_cache *cache; - WARN_ON_ONCE(!swap_slot_cache_initialized); - cache = &get_cpu_var(swp_slots); if (use_swap_slot_cache && cache->slots_ret) { spin_lock_irq(&cache->free_lock); diff --git a/mm/swap_state.c b/mm/swap_state.c index 473b71e052a8..539b8885e3d1 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -360,17 +360,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, /* * We might race against get_swap_page() and stumble * across a SWAP_HAS_CACHE swap_map entry whose page - * has not been brought into the swapcache yet, while - * the other end is scheduled away waiting on discard - * I/O completion at scan_swap_map(). - * - * In order to avoid turning this transitory state - * into a permanent loop around this -EEXIST case - * if !CONFIG_PREEMPT and the I/O completion happens - * to be waiting on the CPU waitqueue where we are now - * busy looping, we just conditionally invoke the - * scheduler here, if there are some more important - * tasks to run. + * has not been brought into the swapcache yet. */ cond_resched(); continue; @@ -533,7 +523,7 @@ int init_swap_address_space(unsigned int type, unsigned long nr_pages) unsigned int i, nr; nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES); - spaces = vzalloc(sizeof(struct address_space) * nr); + spaces = kvzalloc(sizeof(struct address_space) * nr, GFP_KERNEL); if (!spaces) return -ENOMEM; for (i = 0; i < nr; i++) { diff --git a/mm/swapfile.c b/mm/swapfile.c index 178130880b90..4f6cba1b6632 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -335,7 +335,7 @@ static void cluster_list_add_tail(struct swap_cluster_list *list, ci_tail = ci + tail; spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING); cluster_set_next(ci_tail, idx); - unlock_cluster(ci_tail); + spin_unlock(&ci_tail->lock); cluster_set_next_flag(&list->tail, idx, 0); } } @@ -672,6 +672,9 @@ checks: else goto done; } + si->swap_map[offset] = usage; + inc_cluster_info_page(si, si->cluster_info, offset); + unlock_cluster(ci); if (offset == si->lowest_bit) si->lowest_bit++; @@ -685,9 +688,6 @@ checks: 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); - unlock_cluster(ci); si->cluster_next = offset + 1; slots[n_ret++] = swp_entry(si->type, offset); @@ -1079,8 +1079,6 @@ void swapcache_free_entries(swp_entry_t *entries, int n) p = swap_info_get_cont(entries[i], prev); if (p) swap_entry_free(p, entries[i]); - else - break; prev = p; } if (p) @@ -1111,6 +1109,18 @@ int page_swapcount(struct page *page) return count; } +static int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) +{ + int count = 0; + pgoff_t offset = swp_offset(entry); + struct swap_cluster_info *ci; + + ci = lock_cluster_or_swap_info(si, offset); + count = swap_count(si->swap_map[offset]); + unlock_cluster_or_swap_info(si, ci); + return count; +} + /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, @@ -1119,17 +1129,11 @@ int page_swapcount(struct page *page) int __swp_swapcount(swp_entry_t entry) { int count = 0; - pgoff_t offset; struct swap_info_struct *si; - struct swap_cluster_info *ci; si = __swap_info_get(entry); - if (si) { - offset = swp_offset(entry); - ci = lock_cluster_or_swap_info(si, offset); - count = swap_count(si->swap_map[offset]); - unlock_cluster_or_swap_info(si, ci); - } + if (si) + count = swap_swapcount(si, entry); return count; } @@ -1291,7 +1295,8 @@ int free_swap_and_cache(swp_entry_t entry) * Also recheck PageSwapCache now page is locked (above). */ if (PageSwapCache(page) && !PageWriteback(page) && - (!page_mapped(page) || mem_cgroup_swap_full(page))) { + (!page_mapped(page) || mem_cgroup_swap_full(page)) && + !swap_swapcount(p, entry)) { delete_from_swap_cache(page); SetPageDirty(page); } @@ -2265,8 +2270,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; vfree(swap_map); - vfree(cluster_info); - vfree(frontswap_map); + kvfree(cluster_info); + kvfree(frontswap_map); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); exit_swap_address_space(p->type); @@ -2789,7 +2794,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) p->cluster_next = 1 + (prandom_u32() % p->highest_bit); nr_cluster = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); - cluster_info = vzalloc(nr_cluster * sizeof(*cluster_info)); + cluster_info = kvzalloc(nr_cluster * sizeof(*cluster_info), + GFP_KERNEL); if (!cluster_info) { error = -ENOMEM; goto bad_swap; @@ -2822,7 +2828,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) } /* frontswap enabled? set up bit-per-page map for frontswap */ if (IS_ENABLED(CONFIG_FRONTSWAP)) - frontswap_map = vzalloc(BITS_TO_LONGS(maxpages) * sizeof(long)); + frontswap_map = kvzalloc(BITS_TO_LONGS(maxpages) * sizeof(long), + GFP_KERNEL); if (p->bdev &&(swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { /* diff --git a/mm/truncate.c b/mm/truncate.c index 6263affdef88..83a059e8cd1d 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -266,9 +266,8 @@ void truncate_inode_pages_range(struct address_space *mapping, pgoff_t index; int i; - cleancache_invalidate_inode(mapping); if (mapping->nrpages == 0 && mapping->nrexceptional == 0) - return; + goto out; /* Offsets within partial pages */ partial_start = lstart & (PAGE_SIZE - 1); @@ -363,7 +362,7 @@ void truncate_inode_pages_range(struct address_space *mapping, * will be released, just zeroed, so we can bail out now. */ if (start >= end) - return; + goto out; index = start; for ( ; ; ) { @@ -410,6 +409,8 @@ void truncate_inode_pages_range(struct address_space *mapping, pagevec_release(&pvec); index++; } + +out: cleancache_invalidate_inode(mapping); } EXPORT_SYMBOL(truncate_inode_pages_range); @@ -623,7 +624,9 @@ int invalidate_inode_pages2_range(struct address_space *mapping, int ret2 = 0; int did_range_unmap = 0; - cleancache_invalidate_inode(mapping); + if (mapping->nrpages == 0 && mapping->nrexceptional == 0) + goto out; + pagevec_init(&pvec, 0); index = start; while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, @@ -686,6 +689,8 @@ int invalidate_inode_pages2_range(struct address_space *mapping, cond_resched(); index++; } + +out: cleancache_invalidate_inode(mapping); return ret; } diff --git a/mm/usercopy.c b/mm/usercopy.c index d155e12563b1..a9852b24715d 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -19,15 +19,9 @@ #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> +#include <linux/thread_info.h> #include <asm/sections.h> -enum { - BAD_STACK = -1, - NOT_STACK = 0, - GOOD_FRAME, - GOOD_STACK, -}; - /* * Checks if a given pointer and length is contained by the current * stack frame (if possible). @@ -206,17 +200,6 @@ static inline const char *check_heap_object(const void *ptr, unsigned long n, { struct page *page; - /* - * Some architectures (arm64) return true for virt_addr_valid() on - * vmalloced addresses. Work around this by checking for vmalloc - * first. - * - * We also need to check for module addresses explicitly since we - * may copy static data from modules to userspace - */ - if (is_vmalloc_or_module_addr(ptr)) - return NULL; - if (!virt_addr_valid(ptr)) return NULL; diff --git a/mm/util.c b/mm/util.c index 656dc5e37a87..718154debc87 100644 --- a/mm/util.c +++ b/mm/util.c @@ -329,6 +329,63 @@ unsigned long vm_mmap(struct file *file, unsigned long addr, } EXPORT_SYMBOL(vm_mmap); +/** + * kvmalloc_node - attempt to allocate physically contiguous memory, but upon + * failure, fall back to non-contiguous (vmalloc) allocation. + * @size: size of the request. + * @flags: gfp mask for the allocation - must be compatible (superset) with GFP_KERNEL. + * @node: numa node to allocate from + * + * Uses kmalloc to get the memory but if the allocation fails then falls back + * to the vmalloc allocator. Use kvfree for freeing the memory. + * + * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. __GFP_REPEAT + * is supported only for large (>32kB) allocations, and it should be used only if + * kmalloc is preferable to the vmalloc fallback, due to visible performance drawbacks. + * + * Any use of gfp flags outside of GFP_KERNEL should be consulted with mm people. + */ +void *kvmalloc_node(size_t size, gfp_t flags, int node) +{ + gfp_t kmalloc_flags = flags; + void *ret; + + /* + * vmalloc uses GFP_KERNEL for some internal allocations (e.g page tables) + * so the given set of flags has to be compatible. + */ + WARN_ON_ONCE((flags & GFP_KERNEL) != GFP_KERNEL); + + /* + * Make sure that larger requests are not too disruptive - no OOM + * killer and no allocation failure warnings as we have a fallback + */ + if (size > PAGE_SIZE) { + kmalloc_flags |= __GFP_NOWARN; + + /* + * We have to override __GFP_REPEAT by __GFP_NORETRY for !costly + * requests because there is no other way to tell the allocator + * that we want to fail rather than retry endlessly. + */ + if (!(kmalloc_flags & __GFP_REPEAT) || + (size <= PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) + kmalloc_flags |= __GFP_NORETRY; + } + + ret = kmalloc_node(size, kmalloc_flags, node); + + /* + * It doesn't really make sense to fallback to vmalloc for sub page + * requests + */ + if (ret || size <= PAGE_SIZE) + return ret; + + return __vmalloc_node_flags(size, node, flags); +} +EXPORT_SYMBOL(kvmalloc_node); + void kvfree(const void *addr) { if (is_vmalloc_addr(addr)) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index b74f1d01ef76..194c22eccb9d 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1579,7 +1579,7 @@ void vfree_atomic(const void *addr) * have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling * conventions for vfree() arch-depenedent would be a really bad idea) * - * NOTE: assumes that the object at *addr has a size >= sizeof(llist_node) + * NOTE: assumes that the object at @addr has a size >= sizeof(llist_node) */ void vfree(const void *addr) { @@ -1649,16 +1649,13 @@ void *vmap(struct page **pages, unsigned int count, } EXPORT_SYMBOL(vmap); -static void *__vmalloc_node(unsigned long size, unsigned long align, - gfp_t gfp_mask, pgprot_t prot, - int node, const void *caller); static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot, int node) { struct page **pages; unsigned int nr_pages, array_size, i; const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO; - const gfp_t alloc_mask = gfp_mask | __GFP_NOWARN; + const gfp_t alloc_mask = gfp_mask | __GFP_HIGHMEM | __GFP_NOWARN; nr_pages = get_vm_area_size(area) >> PAGE_SHIFT; array_size = (nr_pages * sizeof(struct page *)); @@ -1786,8 +1783,15 @@ fail: * Allocate enough pages to cover @size from the page level * allocator with @gfp_mask flags. Map them into contiguous * kernel virtual space, using a pagetable protection of @prot. + * + * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_REPEAT + * and __GFP_NOFAIL are not supported + * + * Any use of gfp flags outside of GFP_KERNEL should be consulted + * with mm people. + * */ -static void *__vmalloc_node(unsigned long size, unsigned long align, +void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, pgprot_t prot, int node, const void *caller) { @@ -1802,13 +1806,6 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) } EXPORT_SYMBOL(__vmalloc); -static inline void *__vmalloc_node_flags(unsigned long size, - int node, gfp_t flags) -{ - return __vmalloc_node(size, 1, flags, PAGE_KERNEL, - node, __builtin_return_address(0)); -} - /** * vmalloc - allocate virtually contiguous memory * @size: allocation size @@ -1821,7 +1818,7 @@ static inline void *__vmalloc_node_flags(unsigned long size, void *vmalloc(unsigned long size) { return __vmalloc_node_flags(size, NUMA_NO_NODE, - GFP_KERNEL | __GFP_HIGHMEM); + GFP_KERNEL); } EXPORT_SYMBOL(vmalloc); @@ -1838,7 +1835,7 @@ EXPORT_SYMBOL(vmalloc); void *vzalloc(unsigned long size) { return __vmalloc_node_flags(size, NUMA_NO_NODE, - GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); + GFP_KERNEL | __GFP_ZERO); } EXPORT_SYMBOL(vzalloc); @@ -1855,7 +1852,7 @@ void *vmalloc_user(unsigned long size) void *ret; ret = __vmalloc_node(size, SHMLBA, - GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, + GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL, NUMA_NO_NODE, __builtin_return_address(0)); if (ret) { @@ -1879,7 +1876,7 @@ EXPORT_SYMBOL(vmalloc_user); */ void *vmalloc_node(unsigned long size, int node) { - return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, + return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL, node, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_node); @@ -1899,7 +1896,7 @@ EXPORT_SYMBOL(vmalloc_node); void *vzalloc_node(unsigned long size, int node) { return __vmalloc_node_flags(size, node, - GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); + GFP_KERNEL | __GFP_ZERO); } EXPORT_SYMBOL(vzalloc_node); @@ -1921,7 +1918,7 @@ EXPORT_SYMBOL(vzalloc_node); void *vmalloc_exec(unsigned long size) { - return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, + return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL_EXEC, NUMA_NO_NODE, __builtin_return_address(0)); } diff --git a/mm/vmscan.c b/mm/vmscan.c index bc8031ef994d..2f45c0520f43 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -97,8 +97,13 @@ struct scan_control { /* Can pages be swapped as part of reclaim? */ unsigned int may_swap:1; - /* Can cgroups be reclaimed below their normal consumption range? */ - unsigned int may_thrash:1; + /* + * Cgroups are not reclaimed below their configured memory.low, + * unless we threaten to OOM. If any cgroups are skipped due to + * memory.low and nothing was reclaimed, go back for memory.low. + */ + unsigned int memcg_low_reclaim:1; + unsigned int memcg_low_skipped:1; unsigned int hibernation_mode:1; @@ -230,12 +235,6 @@ unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat) return nr; } -bool pgdat_reclaimable(struct pglist_data *pgdat) -{ - return node_page_state_snapshot(pgdat, NR_PAGES_SCANNED) < - pgdat_reclaimable_pages(pgdat) * 6; -} - /** * lruvec_lru_size - Returns the number of pages on the given LRU list. * @lruvec: lru vector @@ -912,7 +911,8 @@ static void page_check_dirty_writeback(struct page *page, * Anonymous pages are not handled by flushers and must be written * from reclaim context. Do not stall reclaim based on them */ - if (!page_is_file_cache(page)) { + if (!page_is_file_cache(page) || + (PageAnon(page) && !PageSwapBacked(page))) { *dirty = false; *writeback = false; return; @@ -972,8 +972,6 @@ static unsigned long shrink_page_list(struct list_head *page_list, int may_enter_fs; enum page_references references = PAGEREF_RECLAIM_CLEAN; bool dirty, writeback; - bool lazyfree = false; - int ret = SWAP_SUCCESS; cond_resched(); @@ -988,13 +986,14 @@ static unsigned long shrink_page_list(struct list_head *page_list, sc->nr_scanned++; if (unlikely(!page_evictable(page))) - goto cull_mlocked; + goto activate_locked; if (!sc->may_unmap && page_mapped(page)) goto keep_locked; /* Double the slab pressure for mapped and swapcache pages */ - if (page_mapped(page) || PageSwapCache(page)) + if ((page_mapped(page) || PageSwapCache(page)) && + !(PageAnon(page) && !PageSwapBacked(page))) sc->nr_scanned++; may_enter_fs = (sc->gfp_mask & __GFP_FS) || @@ -1120,13 +1119,14 @@ static unsigned long shrink_page_list(struct list_head *page_list, /* * Anonymous process memory has backing store? * Try to allocate it some swap space here. + * Lazyfree page could be freed directly */ - if (PageAnon(page) && !PageSwapCache(page)) { + if (PageAnon(page) && PageSwapBacked(page) && + !PageSwapCache(page)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; if (!add_to_swap(page, page_list)) goto activate_locked; - lazyfree = true; may_enter_fs = 1; /* Adding to swap updated mapping */ @@ -1143,21 +1143,10 @@ static unsigned long shrink_page_list(struct list_head *page_list, * The page is mapped into the page tables of one or more * processes. Try to unmap it here. */ - if (page_mapped(page) && mapping) { - switch (ret = try_to_unmap(page, lazyfree ? - (ttu_flags | TTU_BATCH_FLUSH | TTU_LZFREE) : - (ttu_flags | TTU_BATCH_FLUSH))) { - case SWAP_FAIL: + if (page_mapped(page)) { + if (!try_to_unmap(page, ttu_flags | TTU_BATCH_FLUSH)) { nr_unmap_fail++; goto activate_locked; - case SWAP_AGAIN: - goto keep_locked; - case SWAP_MLOCK: - goto cull_mlocked; - case SWAP_LZFREE: - goto lazyfree; - case SWAP_SUCCESS: - ; /* try to free the page below */ } } @@ -1267,10 +1256,18 @@ static unsigned long shrink_page_list(struct list_head *page_list, } } -lazyfree: - if (!mapping || !__remove_mapping(mapping, page, true)) - goto keep_locked; + if (PageAnon(page) && !PageSwapBacked(page)) { + /* follow __remove_mapping for reference */ + if (!page_ref_freeze(page, 1)) + goto keep_locked; + if (PageDirty(page)) { + page_ref_unfreeze(page, 1); + goto keep_locked; + } + count_vm_event(PGLAZYFREED); + } else if (!mapping || !__remove_mapping(mapping, page, true)) + goto keep_locked; /* * At this point, we have no other references and there is * no way to pick any more up (removed from LRU, removed @@ -1280,9 +1277,6 @@ lazyfree: */ __ClearPageLocked(page); free_it: - if (ret == SWAP_LZFREE) - count_vm_event(PGLAZYFREED); - nr_reclaimed++; /* @@ -1292,20 +1286,16 @@ free_it: list_add(&page->lru, &free_pages); continue; -cull_mlocked: - if (PageSwapCache(page)) - try_to_free_swap(page); - unlock_page(page); - list_add(&page->lru, &ret_pages); - continue; - activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ - if (PageSwapCache(page) && mem_cgroup_swap_full(page)) + if (PageSwapCache(page) && (mem_cgroup_swap_full(page) || + PageMlocked(page))) try_to_free_swap(page); VM_BUG_ON_PAGE(PageActive(page), page); - SetPageActive(page); - pgactivate++; + if (!PageMlocked(page)) { + SetPageActive(page); + pgactivate++; + } keep_locked: unlock_page(page); keep: @@ -1354,7 +1344,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, } ret = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, - TTU_UNMAP|TTU_IGNORE_ACCESS, NULL, true); + TTU_IGNORE_ACCESS, NULL, true); list_splice(&clean_pages, page_list); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -ret); return ret; @@ -1478,12 +1468,12 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, unsigned long nr_taken = 0; unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 }; unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; - unsigned long skipped = 0, total_skipped = 0; + unsigned long skipped = 0; unsigned long scan, nr_pages; LIST_HEAD(pages_skipped); for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan && - !list_empty(src);) { + !list_empty(src); scan++) { struct page *page; page = lru_to_page(src); @@ -1497,12 +1487,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, continue; } - /* - * Account for scanned and skipped separetly to avoid the pgdat - * being prematurely marked unreclaimable by pgdat_reclaimable. - */ - scan++; - switch (__isolate_lru_page(page, mode)) { case 0: nr_pages = hpage_nr_pages(page); @@ -1531,6 +1515,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, if (!list_empty(&pages_skipped)) { int zid; + list_splice(&pages_skipped, src); for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_skipped[zid]) continue; @@ -1538,17 +1523,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]); skipped += nr_skipped[zid]; } - - /* - * Account skipped pages as a partial scan as the pgdat may be - * close to unreclaimable. If the LRU list is empty, account - * skipped pages as a full scan. - */ - total_skipped = list_empty(src) ? skipped : skipped >> 2; - - list_splice(&pages_skipped, src); } - *nr_scanned = scan + total_skipped; + *nr_scanned = scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan, skipped, nr_taken, mode, lru); update_lru_sizes(lruvec, lru, nr_zone_taken); @@ -1750,7 +1726,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, reclaim_stat->recent_scanned[file] += nr_taken; if (global_reclaim(sc)) { - __mod_node_page_state(pgdat, NR_PAGES_SCANNED, nr_scanned); if (current_is_kswapd()) __count_vm_events(PGSCAN_KSWAPD, nr_scanned); else @@ -1761,7 +1736,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, if (nr_taken == 0) return 0; - nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, TTU_UNMAP, + nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, 0, &stat, false); spin_lock_irq(&pgdat->lru_lock); @@ -1953,8 +1928,6 @@ static void shrink_active_list(unsigned long nr_to_scan, __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); reclaim_stat->recent_scanned[file] += nr_taken; - if (global_reclaim(sc)) - __mod_node_page_state(pgdat, NR_PAGES_SCANNED, nr_scanned); __count_vm_events(PGREFILL, nr_scanned); spin_unlock_irq(&pgdat->lru_lock); @@ -2033,6 +2006,8 @@ static void shrink_active_list(unsigned long nr_to_scan, * Both inactive lists should also be large enough that each inactive * page has a chance to be referenced again before it is reclaimed. * + * If that fails and refaulting is observed, the inactive list grows. + * * The inactive_ratio is the target ratio of ACTIVE to INACTIVE pages * on this LRU, maintained by the pageout code. A zone->inactive_ratio * of 3 means 3:1 or 25% of the pages are kept on the inactive list. @@ -2049,12 +2024,15 @@ static void shrink_active_list(unsigned long nr_to_scan, * 10TB 320 32GB */ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, - struct scan_control *sc, bool trace) + struct mem_cgroup *memcg, + struct scan_control *sc, bool actual_reclaim) { - unsigned long inactive_ratio; - unsigned long inactive, active; - enum lru_list inactive_lru = file * LRU_FILE; enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE; + struct pglist_data *pgdat = lruvec_pgdat(lruvec); + enum lru_list inactive_lru = file * LRU_FILE; + unsigned long inactive, active; + unsigned long inactive_ratio; + unsigned long refaults; unsigned long gb; /* @@ -2067,27 +2045,42 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx); active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx); - gb = (inactive + active) >> (30 - PAGE_SHIFT); - if (gb) - inactive_ratio = int_sqrt(10 * gb); + if (memcg) + refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE); else - inactive_ratio = 1; + refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE); + + /* + * When refaults are being observed, it means a new workingset + * is being established. Disable active list protection to get + * rid of the stale workingset quickly. + */ + if (file && actual_reclaim && lruvec->refaults != refaults) { + inactive_ratio = 0; + } else { + gb = (inactive + active) >> (30 - PAGE_SHIFT); + if (gb) + inactive_ratio = int_sqrt(10 * gb); + else + inactive_ratio = 1; + } - if (trace) - trace_mm_vmscan_inactive_list_is_low(lruvec_pgdat(lruvec)->node_id, - sc->reclaim_idx, - lruvec_lru_size(lruvec, inactive_lru, MAX_NR_ZONES), inactive, - lruvec_lru_size(lruvec, active_lru, MAX_NR_ZONES), active, - inactive_ratio, file); + if (actual_reclaim) + trace_mm_vmscan_inactive_list_is_low(pgdat->node_id, sc->reclaim_idx, + lruvec_lru_size(lruvec, inactive_lru, MAX_NR_ZONES), inactive, + lruvec_lru_size(lruvec, active_lru, MAX_NR_ZONES), active, + inactive_ratio, file); return inactive * inactive_ratio < active; } static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, - struct lruvec *lruvec, struct scan_control *sc) + struct lruvec *lruvec, struct mem_cgroup *memcg, + struct scan_control *sc) { if (is_active_lru(lru)) { - if (inactive_list_is_low(lruvec, is_file_lru(lru), sc, true)) + if (inactive_list_is_low(lruvec, is_file_lru(lru), + memcg, sc, true)) shrink_active_list(nr_to_scan, lruvec, sc, lru); return 0; } @@ -2123,30 +2116,8 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, unsigned long anon_prio, file_prio; enum scan_balance scan_balance; unsigned long anon, file; - 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 - * results in no scanning on this priority and a potential - * priority drop. Global direct reclaim can go to the next - * zone and tends to have no problems. Global kswapd is for - * zone balancing and it needs to scan a minimum amount. When - * reclaiming for a memcg, a priority drop can cause high - * latencies, so it's better to scan a minimum amount there as - * well. - */ - if (current_is_kswapd()) { - if (!pgdat_reclaimable(pgdat)) - force_scan = true; - if (!mem_cgroup_online(memcg)) - force_scan = true; - } - if (!global_reclaim(sc)) - force_scan = true; /* If we have no swap space, do not bother scanning anon pages. */ if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) { @@ -2218,7 +2189,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, * lruvec even if it has plenty of old anonymous pages unless the * system is under heavy pressure. */ - if (!inactive_list_is_low(lruvec, true, sc, false) && + if (!inactive_list_is_low(lruvec, true, memcg, sc, false) && lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) { scan_balance = SCAN_FILE; goto out; @@ -2277,55 +2248,48 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, fraction[1] = fp; denominator = ap + fp + 1; out: - some_scanned = false; - /* Only use force_scan on second pass. */ - for (pass = 0; !some_scanned && pass < 2; pass++) { - *lru_pages = 0; - for_each_evictable_lru(lru) { - int file = is_file_lru(lru); - unsigned long size; - unsigned long scan; - - size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); - scan = size >> sc->priority; - - 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: - /* - * 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) { - size = 0; - scan = 0; - } - break; - default: - /* Look ma, no brain */ - BUG(); - } + *lru_pages = 0; + for_each_evictable_lru(lru) { + int file = is_file_lru(lru); + unsigned long size; + unsigned long scan; - *lru_pages += size; - nr[lru] = scan; + size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); + scan = size >> sc->priority; + /* + * If the cgroup's already been deleted, make sure to + * scrape out the remaining cache. + */ + if (!scan && !mem_cgroup_online(memcg)) + scan = min(size, SWAP_CLUSTER_MAX); + switch (scan_balance) { + case SCAN_EQUAL: + /* Scan lists relative to size */ + break; + case SCAN_FRACT: /* - * Skip the second pass and don't force_scan, - * if we found something to scan. + * Scan types proportional to swappiness and + * their relative recent reclaim efficiency. */ - some_scanned |= !!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) { + size = 0; + scan = 0; + } + break; + default: + /* Look ma, no brain */ + BUG(); } + + *lru_pages += size; + nr[lru] = scan; } } @@ -2376,7 +2340,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, - lruvec, sc); + lruvec, memcg, sc); } } @@ -2443,7 +2407,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ - if (inactive_list_is_low(lruvec, false, sc, true)) + if (inactive_list_is_low(lruvec, false, memcg, sc, true)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } @@ -2557,9 +2521,11 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) unsigned long scanned; if (mem_cgroup_low(root, memcg)) { - if (!sc->may_thrash) + if (!sc->memcg_low_reclaim) { + sc->memcg_low_skipped = 1; continue; - mem_cgroup_events(memcg, MEMCG_LOW, 1); + } + mem_cgroup_event(memcg, MEMCG_LOW); } reclaimed = sc->nr_reclaimed; @@ -2620,6 +2586,15 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) } while (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc->nr_scanned - nr_scanned, sc)); + /* + * Kswapd gives up on balancing particular nodes after too + * many failures to reclaim anything from them and goes to + * sleep. On reclaim progress, reset the failure counter. A + * successful direct reclaim run will revive a dormant kswapd. + */ + if (reclaimable) + pgdat->kswapd_failures = 0; + return reclaimable; } @@ -2694,10 +2669,6 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) GFP_KERNEL | __GFP_HARDWALL)) continue; - if (sc->priority != DEF_PRIORITY && - !pgdat_reclaimable(zone->zone_pgdat)) - continue; /* Let kswapd poll it */ - /* * If we already have plenty of memory free for * compaction in this zone, don't free any more. @@ -2752,6 +2723,25 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) sc->gfp_mask = orig_mask; } +static void snapshot_refaults(struct mem_cgroup *root_memcg, pg_data_t *pgdat) +{ + struct mem_cgroup *memcg; + + memcg = mem_cgroup_iter(root_memcg, NULL, NULL); + do { + unsigned long refaults; + struct lruvec *lruvec; + + if (memcg) + refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE); + else + refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE); + + lruvec = mem_cgroup_lruvec(pgdat, memcg); + lruvec->refaults = refaults; + } while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL))); +} + /* * This is the main entry point to direct page reclaim. * @@ -2772,6 +2762,9 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { int initial_priority = sc->priority; + pg_data_t *last_pgdat; + struct zoneref *z; + struct zone *zone; retry: delayacct_freepages_start(); @@ -2798,6 +2791,15 @@ retry: sc->may_writepage = 1; } while (--sc->priority >= 0); + last_pgdat = NULL; + for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, + sc->nodemask) { + if (zone->zone_pgdat == last_pgdat) + continue; + last_pgdat = zone->zone_pgdat; + snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat); + } + delayacct_freepages_end(); if (sc->nr_reclaimed) @@ -2808,16 +2810,17 @@ retry: return 1; /* Untapped cgroup reserves? Don't OOM, retry. */ - if (!sc->may_thrash) { + if (sc->memcg_low_skipped) { sc->priority = initial_priority; - sc->may_thrash = 1; + sc->memcg_low_reclaim = 1; + sc->memcg_low_skipped = 0; goto retry; } return 0; } -static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) +static bool allow_direct_reclaim(pg_data_t *pgdat) { struct zone *zone; unsigned long pfmemalloc_reserve = 0; @@ -2825,10 +2828,15 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) int i; bool wmark_ok; + if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) + return true; + for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; - if (!managed_zone(zone) || - pgdat_reclaimable_pages(pgdat) == 0) + if (!managed_zone(zone)) + continue; + + if (!zone_reclaimable_pages(zone)) continue; pfmemalloc_reserve += min_wmark_pages(zone); @@ -2905,7 +2913,7 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, /* Throttle based on the first usable node */ pgdat = zone->zone_pgdat; - if (pfmemalloc_watermark_ok(pgdat)) + if (allow_direct_reclaim(pgdat)) goto out; break; } @@ -2927,14 +2935,14 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, */ if (!(gfp_mask & __GFP_FS)) { wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, - pfmemalloc_watermark_ok(pgdat), HZ); + allow_direct_reclaim(pgdat), HZ); goto check_pending; } /* Throttle until kswapd wakes the process */ wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, - pfmemalloc_watermark_ok(pgdat)); + allow_direct_reclaim(pgdat)); check_pending: if (fatal_signal_pending(current)) @@ -2950,7 +2958,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, unsigned long nr_reclaimed; struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, - .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)), + .gfp_mask = (gfp_mask = current_gfp_context(gfp_mask)), .reclaim_idx = gfp_zone(gfp_mask), .order = order, .nodemask = nodemask, @@ -3028,9 +3036,10 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, struct zonelist *zonelist; unsigned long nr_reclaimed; int nid; + unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), - .gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | + .gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), .reclaim_idx = MAX_NR_ZONES - 1, .target_mem_cgroup = memcg, @@ -3054,9 +3063,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, sc.gfp_mask, sc.reclaim_idx); - current->flags |= PF_MEMALLOC; + noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); - current->flags &= ~PF_MEMALLOC; + memalloc_noreclaim_restore(noreclaim_flag); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); @@ -3076,7 +3085,7 @@ static void age_active_anon(struct pglist_data *pgdat, do { struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg); - if (inactive_list_is_low(lruvec, false, sc, true)) + if (inactive_list_is_low(lruvec, false, memcg, sc, true)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); @@ -3084,22 +3093,44 @@ static void age_active_anon(struct pglist_data *pgdat, } while (memcg); } -static bool zone_balanced(struct zone *zone, int order, int classzone_idx) +/* + * Returns true if there is an eligible zone balanced for the request order + * and classzone_idx + */ +static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) { - unsigned long mark = high_wmark_pages(zone); + int i; + unsigned long mark = -1; + struct zone *zone; - if (!zone_watermark_ok_safe(zone, order, mark, classzone_idx)) - return false; + for (i = 0; i <= classzone_idx; i++) { + zone = pgdat->node_zones + i; + + if (!managed_zone(zone)) + continue; + + mark = high_wmark_pages(zone); + if (zone_watermark_ok_safe(zone, order, mark, classzone_idx)) + return true; + } /* - * If any eligible zone is balanced then the node is not considered - * to be congested or dirty + * If a node has no populated zone within classzone_idx, it does not + * need balancing by definition. This can happen if a zone-restricted + * allocation tries to wake a remote kswapd. */ - clear_bit(PGDAT_CONGESTED, &zone->zone_pgdat->flags); - clear_bit(PGDAT_DIRTY, &zone->zone_pgdat->flags); - clear_bit(PGDAT_WRITEBACK, &zone->zone_pgdat->flags); + if (mark == -1) + return true; - return true; + return false; +} + +/* Clear pgdat state for congested, dirty or under writeback. */ +static void clear_pgdat_congested(pg_data_t *pgdat) +{ + clear_bit(PGDAT_CONGESTED, &pgdat->flags); + clear_bit(PGDAT_DIRTY, &pgdat->flags); + clear_bit(PGDAT_WRITEBACK, &pgdat->flags); } /* @@ -3110,11 +3141,9 @@ static bool zone_balanced(struct zone *zone, int order, int classzone_idx) */ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx) { - int i; - /* * The throttled processes are normally woken up in balance_pgdat() as - * soon as pfmemalloc_watermark_ok() is true. But there is a potential + * soon as allow_direct_reclaim() is true. But there is a potential * race between when kswapd checks the watermarks and a process gets * throttled. There is also a potential race if processes get * throttled, kswapd wakes, a large process exits thereby balancing the @@ -3128,17 +3157,16 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx) if (waitqueue_active(&pgdat->pfmemalloc_wait)) wake_up_all(&pgdat->pfmemalloc_wait); - for (i = 0; i <= classzone_idx; i++) { - struct zone *zone = pgdat->node_zones + i; - - if (!managed_zone(zone)) - continue; + /* Hopeless node, leave it to direct reclaim */ + if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) + return true; - if (!zone_balanced(zone, order, classzone_idx)) - return false; + if (pgdat_balanced(pgdat, order, classzone_idx)) { + clear_pgdat_congested(pgdat); + return true; } - return true; + return false; } /* @@ -3214,9 +3242,9 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) count_vm_event(PAGEOUTRUN); do { + unsigned long nr_reclaimed = sc.nr_reclaimed; bool raise_priority = true; - sc.nr_reclaimed = 0; sc.reclaim_idx = classzone_idx; /* @@ -3241,23 +3269,12 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) } /* - * Only reclaim if there are no eligible zones. Check from - * high to low zone as allocations prefer higher zones. - * Scanning from low to high zone would allow congestion to be - * cleared during a very small window when a small low - * zone was balanced even under extreme pressure when the - * overall node may be congested. Note that sc.reclaim_idx - * is not used as buffer_heads_over_limit may have adjusted - * it. + * Only reclaim if there are no eligible zones. Note that + * sc.reclaim_idx is not used as buffer_heads_over_limit may + * have adjusted it. */ - for (i = classzone_idx; i >= 0; i--) { - zone = pgdat->node_zones + i; - if (!managed_zone(zone)) - continue; - - if (zone_balanced(zone, sc.order, classzone_idx)) - goto out; - } + if (pgdat_balanced(pgdat, sc.order, classzone_idx)) + goto out; /* * Do some background aging of the anon list, to give @@ -3271,7 +3288,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) * If we're getting trouble reclaiming, start doing writepage * even in laptop mode. */ - if (sc.priority < DEF_PRIORITY - 2 || !pgdat_reclaimable(pgdat)) + if (sc.priority < DEF_PRIORITY - 2) sc.may_writepage = 1; /* Call soft limit reclaim before calling shrink_node. */ @@ -3295,7 +3312,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) * able to safely make forward progress. Wake them */ if (waitqueue_active(&pgdat->pfmemalloc_wait) && - pfmemalloc_watermark_ok(pgdat)) + allow_direct_reclaim(pgdat)) wake_up_all(&pgdat->pfmemalloc_wait); /* Check if kswapd should be suspending */ @@ -3306,11 +3323,16 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) * Raise priority if scanning rate is too low or there was no * progress in reclaiming pages */ - if (raise_priority || !sc.nr_reclaimed) + nr_reclaimed = sc.nr_reclaimed - nr_reclaimed; + if (raise_priority || !nr_reclaimed) sc.priority--; } while (sc.priority >= 1); + if (!sc.nr_reclaimed) + pgdat->kswapd_failures++; + out: + snapshot_refaults(NULL, pgdat); /* * Return the order kswapd stopped reclaiming at as * prepare_kswapd_sleep() takes it into account. If another caller @@ -3320,6 +3342,22 @@ out: return sc.order; } +/* + * pgdat->kswapd_classzone_idx is the highest zone index that a recent + * allocation request woke kswapd for. When kswapd has not woken recently, + * the value is MAX_NR_ZONES which is not a valid index. This compares a + * given classzone and returns it or the highest classzone index kswapd + * was recently woke for. + */ +static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat, + enum zone_type classzone_idx) +{ + if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES) + return classzone_idx; + + return max(pgdat->kswapd_classzone_idx, classzone_idx); +} + static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, unsigned int classzone_idx) { @@ -3331,7 +3369,13 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); - /* Try to sleep for a short interval */ + /* + * Try to sleep for a short interval. Note that kcompactd will only be + * woken if it is possible to sleep for a short interval. This is + * deliberate on the assumption that if reclaim cannot keep an + * eligible zone balanced that it's also unlikely that compaction will + * succeed. + */ if (prepare_kswapd_sleep(pgdat, reclaim_order, classzone_idx)) { /* * Compaction records what page blocks it recently failed to @@ -3355,7 +3399,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o * the previous request that slept prematurely. */ if (remaining) { - pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx); + pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx); pgdat->kswapd_order = max(pgdat->kswapd_order, reclaim_order); } @@ -3409,7 +3453,8 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o */ static int kswapd(void *p) { - unsigned int alloc_order, reclaim_order, classzone_idx; + unsigned int alloc_order, reclaim_order; + unsigned int classzone_idx = MAX_NR_ZONES - 1; pg_data_t *pgdat = (pg_data_t*)p; struct task_struct *tsk = current; @@ -3439,20 +3484,23 @@ static int kswapd(void *p) tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; set_freezable(); - pgdat->kswapd_order = alloc_order = reclaim_order = 0; - pgdat->kswapd_classzone_idx = classzone_idx = 0; + pgdat->kswapd_order = 0; + pgdat->kswapd_classzone_idx = MAX_NR_ZONES; for ( ; ; ) { bool ret; + alloc_order = reclaim_order = pgdat->kswapd_order; + classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx); + kswapd_try_sleep: kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, classzone_idx); /* Read the new order and classzone_idx */ alloc_order = reclaim_order = pgdat->kswapd_order; - classzone_idx = pgdat->kswapd_classzone_idx; + classzone_idx = kswapd_classzone_idx(pgdat, 0); pgdat->kswapd_order = 0; - pgdat->kswapd_classzone_idx = 0; + pgdat->kswapd_classzone_idx = MAX_NR_ZONES; ret = try_to_freeze(); if (kthread_should_stop()) @@ -3478,9 +3526,6 @@ kswapd_try_sleep: reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx); if (reclaim_order < alloc_order) goto kswapd_try_sleep; - - alloc_order = reclaim_order = pgdat->kswapd_order; - classzone_idx = pgdat->kswapd_classzone_idx; } tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD); @@ -3496,7 +3541,6 @@ kswapd_try_sleep: void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) { pg_data_t *pgdat; - int z; if (!managed_zone(zone)) return; @@ -3504,22 +3548,20 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL)) return; pgdat = zone->zone_pgdat; - pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx); + pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat, + classzone_idx); pgdat->kswapd_order = max(pgdat->kswapd_order, order); if (!waitqueue_active(&pgdat->kswapd_wait)) return; - /* Only wake kswapd if all zones are unbalanced */ - for (z = 0; z <= classzone_idx; z++) { - zone = pgdat->node_zones + z; - if (!managed_zone(zone)) - continue; + /* Hopeless node, leave it to direct reclaim */ + if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) + return; - if (zone_balanced(zone, order, classzone_idx)) - return; - } + if (pgdat_balanced(pgdat, order, classzone_idx)) + return; - trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order); + trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, classzone_idx, order); wake_up_interruptible(&pgdat->kswapd_wait); } @@ -3548,8 +3590,9 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); struct task_struct *p = current; unsigned long nr_reclaimed; + unsigned int noreclaim_flag; - p->flags |= PF_MEMALLOC; + noreclaim_flag = memalloc_noreclaim_save(); lockdep_set_current_reclaim_state(sc.gfp_mask); reclaim_state.reclaimed_slab = 0; p->reclaim_state = &reclaim_state; @@ -3558,7 +3601,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) p->reclaim_state = NULL; lockdep_clear_current_reclaim_state(); - p->flags &= ~PF_MEMALLOC; + memalloc_noreclaim_restore(noreclaim_flag); return nr_reclaimed; } @@ -3723,9 +3766,10 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in struct task_struct *p = current; struct reclaim_state reclaim_state; int classzone_idx = gfp_zone(gfp_mask); + unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), - .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)), + .gfp_mask = (gfp_mask = current_gfp_context(gfp_mask)), .order = order, .priority = NODE_RECLAIM_PRIORITY, .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE), @@ -3740,7 +3784,8 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in * and we also need to be able to write out pages for RECLAIM_WRITE * and RECLAIM_UNMAP. */ - p->flags |= PF_MEMALLOC | PF_SWAPWRITE; + noreclaim_flag = memalloc_noreclaim_save(); + p->flags |= PF_SWAPWRITE; lockdep_set_current_reclaim_state(gfp_mask); reclaim_state.reclaimed_slab = 0; p->reclaim_state = &reclaim_state; @@ -3756,7 +3801,8 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in } p->reclaim_state = NULL; - current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE); + current->flags &= ~PF_SWAPWRITE; + memalloc_noreclaim_restore(noreclaim_flag); lockdep_clear_current_reclaim_state(); return sc.nr_reclaimed >= nr_pages; } @@ -3779,9 +3825,6 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) sum_zone_node_page_state(pgdat->node_id, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages) return NODE_RECLAIM_FULL; - if (!pgdat_reclaimable(pgdat)) - return NODE_RECLAIM_FULL; - /* * Do not scan if the allocation should not be delayed. */ diff --git a/mm/vmstat.c b/mm/vmstat.c index b1947f0cbee2..f5fa1bd1eb16 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -954,7 +954,6 @@ const char * const vmstat_text[] = { "nr_unevictable", "nr_isolated_anon", "nr_isolated_file", - "nr_pages_scanned", "workingset_refault", "workingset_activate", "workingset_nodereclaim", @@ -992,6 +991,7 @@ const char * const vmstat_text[] = { "pgfree", "pgactivate", "pgdeactivate", + "pglazyfree", "pgfault", "pgmajfault", @@ -1124,8 +1124,12 @@ static void frag_stop(struct seq_file *m, void *arg) { } -/* Walk all the zones in a node and print using a callback */ +/* + * Walk zones in a node and print using a callback. + * If @assert_populated is true, only use callback for zones that are populated. + */ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, + bool assert_populated, void (*print)(struct seq_file *m, pg_data_t *, struct zone *)) { struct zone *zone; @@ -1133,7 +1137,7 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, unsigned long flags; for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { - if (!populated_zone(zone)) + if (assert_populated && !populated_zone(zone)) continue; spin_lock_irqsave(&zone->lock, flags); @@ -1161,7 +1165,7 @@ static void frag_show_print(struct seq_file *m, pg_data_t *pgdat, static int frag_show(struct seq_file *m, void *arg) { pg_data_t *pgdat = (pg_data_t *)arg; - walk_zones_in_node(m, pgdat, frag_show_print); + walk_zones_in_node(m, pgdat, true, frag_show_print); return 0; } @@ -1202,7 +1206,7 @@ static int pagetypeinfo_showfree(struct seq_file *m, void *arg) seq_printf(m, "%6d ", order); seq_putc(m, '\n'); - walk_zones_in_node(m, pgdat, pagetypeinfo_showfree_print); + walk_zones_in_node(m, pgdat, true, pagetypeinfo_showfree_print); return 0; } @@ -1254,7 +1258,7 @@ static int pagetypeinfo_showblockcount(struct seq_file *m, void *arg) for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) seq_printf(m, "%12s ", migratetype_names[mtype]); seq_putc(m, '\n'); - walk_zones_in_node(m, pgdat, pagetypeinfo_showblockcount_print); + walk_zones_in_node(m, pgdat, true, pagetypeinfo_showblockcount_print); return 0; } @@ -1280,7 +1284,7 @@ static void pagetypeinfo_showmixedcount(struct seq_file *m, pg_data_t *pgdat) seq_printf(m, "%12s ", migratetype_names[mtype]); seq_putc(m, '\n'); - walk_zones_in_node(m, pgdat, pagetypeinfo_showmixedcount_print); + walk_zones_in_node(m, pgdat, true, pagetypeinfo_showmixedcount_print); #endif /* CONFIG_PAGE_OWNER */ } @@ -1378,7 +1382,6 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n min %lu" "\n low %lu" "\n high %lu" - "\n node_scanned %lu" "\n spanned %lu" "\n present %lu" "\n managed %lu", @@ -1386,23 +1389,28 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), - node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED), zone->spanned_pages, zone->present_pages, zone->managed_pages); - for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - seq_printf(m, "\n %-12s %lu", vmstat_text[i], - zone_page_state(zone, i)); - seq_printf(m, "\n protection: (%ld", zone->lowmem_reserve[0]); for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++) seq_printf(m, ", %ld", zone->lowmem_reserve[i]); - seq_printf(m, - ")" - "\n pagesets"); + seq_putc(m, ')'); + + /* If unpopulated, no other information is useful */ + if (!populated_zone(zone)) { + seq_putc(m, '\n'); + return; + } + + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + seq_printf(m, "\n %-12s %lu", vmstat_text[i], + zone_page_state(zone, i)); + + seq_printf(m, "\n pagesets"); for_each_online_cpu(i) { struct per_cpu_pageset *pageset; @@ -1425,19 +1433,22 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n node_unreclaimable: %u" "\n start_pfn: %lu" "\n node_inactive_ratio: %u", - !pgdat_reclaimable(zone->zone_pgdat), + pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES, zone->zone_start_pfn, zone->zone_pgdat->inactive_ratio); seq_putc(m, '\n'); } /* - * Output information about zones in @pgdat. + * Output information about zones in @pgdat. All zones are printed regardless + * of whether they are populated or not: lowmem_reserve_ratio operates on the + * set of all zones and userspace would not be aware of such zones if they are + * suppressed here (zoneinfo displays the effect of lowmem_reserve_ratio). */ static int zoneinfo_show(struct seq_file *m, void *arg) { pg_data_t *pgdat = (pg_data_t *)arg; - walk_zones_in_node(m, pgdat, zoneinfo_show_print); + walk_zones_in_node(m, pgdat, false, zoneinfo_show_print); return 0; } @@ -1552,7 +1563,6 @@ static const struct file_operations proc_vmstat_file_operations = { #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SMP -static struct workqueue_struct *vmstat_wq; static DEFINE_PER_CPU(struct delayed_work, vmstat_work); int sysctl_stat_interval __read_mostly = HZ; @@ -1587,22 +1597,9 @@ int vmstat_refresh(struct ctl_table *table, int write, for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { val = atomic_long_read(&vm_zone_stat[i]); if (val < 0) { - switch (i) { - case NR_PAGES_SCANNED: - /* - * This is often seen to go negative in - * recent kernels, but not to go permanently - * negative. Whilst it would be nicer not to - * have exceptions, rooting them out would be - * another task, of rather low priority. - */ - break; - default: - pr_warn("%s: %s %ld\n", - __func__, vmstat_text[i], val); - err = -EINVAL; - break; - } + pr_warn("%s: %s %ld\n", + __func__, vmstat_text[i], val); + err = -EINVAL; } } if (err) @@ -1623,7 +1620,7 @@ static void vmstat_update(struct work_struct *w) * to occur in the future. Keep on running the * update worker thread. */ - queue_delayed_work_on(smp_processor_id(), vmstat_wq, + queue_delayed_work_on(smp_processor_id(), mm_percpu_wq, this_cpu_ptr(&vmstat_work), round_jiffies_relative(sysctl_stat_interval)); } @@ -1702,7 +1699,7 @@ static void vmstat_shepherd(struct work_struct *w) struct delayed_work *dw = &per_cpu(vmstat_work, cpu); if (!delayed_work_pending(dw) && need_update(cpu)) - queue_delayed_work_on(cpu, vmstat_wq, dw, 0); + queue_delayed_work_on(cpu, mm_percpu_wq, dw, 0); } put_online_cpus(); @@ -1718,7 +1715,6 @@ static void __init start_shepherd_timer(void) INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu), vmstat_update); - vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); schedule_delayed_work(&shepherd, round_jiffies_relative(sysctl_stat_interval)); } @@ -1764,11 +1760,15 @@ static int vmstat_cpu_dead(unsigned int cpu) #endif -static int __init setup_vmstat(void) +struct workqueue_struct *mm_percpu_wq; + +void __init init_mm_internals(void) { -#ifdef CONFIG_SMP - int ret; + int ret __maybe_unused; + + mm_percpu_wq = alloc_workqueue("mm_percpu_wq", WQ_MEM_RECLAIM, 0); +#ifdef CONFIG_SMP ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead", NULL, vmstat_cpu_dead); if (ret < 0) @@ -1792,9 +1792,7 @@ static int __init setup_vmstat(void) proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations); proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations); #endif - return 0; } -module_init(setup_vmstat) #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION) @@ -1856,7 +1854,7 @@ static int unusable_show(struct seq_file *m, void *arg) if (!node_state(pgdat->node_id, N_MEMORY)) return 0; - walk_zones_in_node(m, pgdat, unusable_show_print); + walk_zones_in_node(m, pgdat, true, unusable_show_print); return 0; } @@ -1908,7 +1906,7 @@ static int extfrag_show(struct seq_file *m, void *arg) { pg_data_t *pgdat = (pg_data_t *)arg; - walk_zones_in_node(m, pgdat, extfrag_show_print); + walk_zones_in_node(m, pgdat, true, extfrag_show_print); return 0; } diff --git a/mm/workingset.c b/mm/workingset.c index ac839fca0e76..b8c9ab678479 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -269,7 +269,6 @@ bool workingset_refault(void *shadow) lruvec = mem_cgroup_lruvec(pgdat, memcg); refault = atomic_long_read(&lruvec->inactive_age); active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES); - rcu_read_unlock(); /* * The unsigned subtraction here gives an accurate distance @@ -290,11 +289,15 @@ bool workingset_refault(void *shadow) refault_distance = (refault - eviction) & EVICTION_MASK; inc_node_state(pgdat, WORKINGSET_REFAULT); + inc_memcg_state(memcg, WORKINGSET_REFAULT); if (refault_distance <= active_file) { inc_node_state(pgdat, WORKINGSET_ACTIVATE); + inc_memcg_state(memcg, WORKINGSET_ACTIVATE); + rcu_read_unlock(); return true; } + rcu_read_unlock(); return false; } @@ -472,6 +475,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, if (WARN_ON_ONCE(node->exceptional)) goto out_invalid; inc_node_state(page_pgdat(virt_to_page(node)), WORKINGSET_NODERECLAIM); + inc_memcg_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM); __radix_tree_delete_node(&mapping->page_tree, node, workingset_update_node, mapping); @@ -532,7 +536,7 @@ static int __init workingset_init(void) pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", timestamp_bits, max_order, bucket_order); - ret = list_lru_init_key(&shadow_nodes, &shadow_nodes_key); + ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key); if (ret) goto err; ret = register_shrinker(&workingset_shadow_shrinker); diff --git a/mm/z3fold.c b/mm/z3fold.c index f9492bccfd79..54f63c4a809a 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -185,6 +185,12 @@ static inline void z3fold_page_lock(struct z3fold_header *zhdr) spin_lock(&zhdr->page_lock); } +/* Try to lock a z3fold page */ +static inline int z3fold_page_trylock(struct z3fold_header *zhdr) +{ + return spin_trylock(&zhdr->page_lock); +} + /* Unlock a z3fold page */ static inline void z3fold_page_unlock(struct z3fold_header *zhdr) { @@ -385,7 +391,7 @@ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp, spin_lock(&pool->lock); zhdr = list_first_entry_or_null(&pool->unbuddied[i], struct z3fold_header, buddy); - if (!zhdr) { + if (!zhdr || !z3fold_page_trylock(zhdr)) { spin_unlock(&pool->lock); continue; } @@ -394,7 +400,6 @@ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp, spin_unlock(&pool->lock); page = virt_to_page(zhdr); - z3fold_page_lock(zhdr); if (zhdr->first_chunks == 0) { if (zhdr->middle_chunks != 0 && chunks >= zhdr->start_middle) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index b7ee9c34dbd6..d41edd28298b 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -276,7 +276,7 @@ struct zs_pool { struct zspage { struct { unsigned int fullness:FULLNESS_BITS; - unsigned int class:CLASS_BITS; + unsigned int class:CLASS_BITS + 1; unsigned int isolated:ISOLATED_BITS; unsigned int magic:MAGIC_VAL_BITS; }; |