diff options
Diffstat (limited to 'mm')
80 files changed, 6215 insertions, 2974 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 afcc550877ff..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 @@ -90,3 +89,9 @@ config DEBUG_PAGE_REF careful when enabling this feature because it adds about 30 KB to the kernel code. However the runtime performance overhead is virtually nil until the tracepoints are actually enabled. + +config DEBUG_RODATA_TEST + bool "Testcase for the marking rodata read-only" + depends on STRICT_KERNEL_RWX + ---help--- + This option enables a testcase for the setting rodata read-only. diff --git a/mm/Makefile b/mm/Makefile index 295bd7a9f76b..026f6a828a50 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -23,8 +23,10 @@ KCOV_INSTRUMENT_vmstat.o := n mmu-y := nommu.o mmu-$(CONFIG_MMU) := gup.o highmem.o memory.o mincore.o \ - mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \ - vmalloc.o pagewalk.o pgtable-generic.o + mlock.o mmap.o mprotect.o mremap.o msync.o \ + page_vma_mapped.o pagewalk.o pgtable-generic.o \ + rmap.o vmalloc.o + ifdef CONFIG_CROSS_MEMORY_ATTACH mmu-$(CONFIG_MMU) += process_vm_access.o @@ -35,7 +37,7 @@ obj-y := filemap.o mempool.o oom_kill.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ - compaction.o vmacache.o \ + compaction.o vmacache.o swap_slots.o \ interval_tree.o list_lru.o workingset.o \ debug.o $(mmu-y) @@ -83,6 +85,7 @@ obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o +obj-$(CONFIG_DEBUG_RODATA_TEST) += rodata_test.o obj-$(CONFIG_PAGE_OWNER) += page_owner.o obj-$(CONFIG_CLEANCACHE) += cleancache.o obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 39ce616a9d71..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 @@ -411,8 +434,8 @@ retry: while (*node != NULL) { parent = *node; - congested = container_of(parent, struct bdi_writeback_congested, - rb_node); + congested = rb_entry(parent, struct bdi_writeback_congested, + rb_node); if (congested->blkcg_id < blkcg_id) node = &parent->rb_left; else if (congested->blkcg_id > blkcg_id) @@ -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) { @@ -680,36 +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; - struct rb_node *rbn; 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); - while ((rbn = rb_first(&bdi->cgwb_congested_tree))) { - struct bdi_writeback_congested *congested = - rb_entry(rbn, struct bdi_writeback_congested, rb_node); - - rb_erase(rbn, &bdi->cgwb_congested_tree); - congested->bdi = NULL; /* mark @congested unlinked */ + 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); - - /* - * All cgwb's and their congested states must be shutdown and - * released before returning. Drain the usage counter to wait for - * all cgwb's and cgwb_congested's ever created on @bdi. - */ - atomic_dec(&bdi->usage_cnt); - wait_event(cgwb_release_wait, !atomic_read(&bdi->usage_cnt)); } /** @@ -749,6 +759,28 @@ void wb_blkcg_offline(struct blkcg *blkcg) spin_unlock_irq(&cgwb_lock); } +static void cgwb_bdi_exit(struct backing_dev_info *bdi) +{ + struct rb_node *rbn; + + spin_lock_irq(&cgwb_lock); + while ((rbn = rb_first(&bdi->cgwb_congested_tree))) { + struct bdi_writeback_congested *congested = + rb_entry(rbn, struct bdi_writeback_congested, rb_node); + + rb_erase(rbn, &bdi->cgwb_congested_tree); + 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) @@ -769,14 +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; @@ -792,11 +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) { @@ -813,22 +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)); @@ -841,22 +880,29 @@ 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... */ + WARN_ON(bdi->owner); bdi->owner = owner; get_device(owner); return 0; @@ -880,7 +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); @@ -894,18 +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); -} - 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); } @@ -913,38 +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]), diff --git a/mm/bootmem.c b/mm/bootmem.c index e8a55a3c9feb..9fedb27c6451 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -53,7 +53,7 @@ early_param("bootmem_debug", bootmem_debug_setup); static unsigned long __init bootmap_bytes(unsigned long pages) { - unsigned long bytes = DIV_ROUND_UP(pages, 8); + unsigned long bytes = DIV_ROUND_UP(pages, BITS_PER_BYTE); return ALIGN(bytes, sizeof(long)); } @@ -348,6 +348,32 @@ err: return ret; } +#ifdef CONFIG_CMA_DEBUG +static void cma_debug_show_areas(struct cma *cma) +{ + unsigned long next_zero_bit, next_set_bit; + unsigned long start = 0; + unsigned int nr_zero, nr_total = 0; + + mutex_lock(&cma->lock); + pr_info("number of available pages: "); + for (;;) { + next_zero_bit = find_next_zero_bit(cma->bitmap, cma->count, start); + if (next_zero_bit >= cma->count) + break; + next_set_bit = find_next_bit(cma->bitmap, cma->count, next_zero_bit); + nr_zero = next_set_bit - next_zero_bit; + pr_cont("%s%u@%lu", nr_total ? "+" : "", nr_zero, next_zero_bit); + nr_total += nr_zero; + start = next_zero_bit + nr_zero; + } + pr_cont("=> %u free of %lu total pages\n", nr_total, cma->count); + mutex_unlock(&cma->lock); +} +#else +static inline void cma_debug_show_areas(struct cma *cma) { } +#endif + /** * cma_alloc() - allocate pages from contiguous area * @cma: Contiguous memory region for which the allocation is performed. @@ -357,14 +383,15 @@ err: * This function allocates part of contiguous memory on specific * contiguous memory area. */ -struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align) +struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, + gfp_t gfp_mask) { unsigned long mask, offset; unsigned long pfn = -1; unsigned long start = 0; unsigned long bitmap_maxno, bitmap_no, bitmap_count; struct page *page = NULL; - int ret; + int ret = -ENOMEM; if (!cma || !cma->count) return NULL; @@ -402,7 +429,8 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align) pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit); mutex_lock(&cma_mutex); - ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA); + ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA, + gfp_mask); mutex_unlock(&cma_mutex); if (ret == 0) { page = pfn_to_page(pfn); @@ -421,6 +449,12 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align) trace_cma_alloc(pfn, page, count, align); + if (ret) { + pr_info("%s: alloc failed, req-size: %zu pages, ret: %d\n", + __func__, count, ret); + cma_debug_show_areas(cma); + } + pr_debug("%s(): returned %p\n", __func__, page); return page; } diff --git a/mm/cma_debug.c b/mm/cma_debug.c index f8e4b60db167..ffc0c3d0ae64 100644 --- a/mm/cma_debug.c +++ b/mm/cma_debug.c @@ -138,7 +138,7 @@ static int cma_alloc_mem(struct cma *cma, int count) if (!mem) return -ENOMEM; - p = cma_alloc(cma, count, 0); + p = cma_alloc(cma, count, 0, GFP_KERNEL); if (!p) { kfree(mem); return -ENOMEM; diff --git a/mm/compaction.c b/mm/compaction.c index 949198d01260..09c5282ebdd2 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -12,6 +12,7 @@ #include <linux/migrate.h> #include <linux/compaction.h> #include <linux/mm_inline.h> +#include <linux/sched/signal.h> #include <linux/backing-dev.h> #include <linux/sysctl.h> #include <linux/sysfs.h> @@ -548,7 +549,7 @@ isolate_fail: if (blockpfn == end_pfn) update_pageblock_skip(cc, valid_page, total_isolated, false); - count_compact_events(COMPACTFREE_SCANNED, nr_scanned); + cc->total_free_scanned += nr_scanned; if (total_isolated) count_compact_events(COMPACTISOLATED, total_isolated); return total_isolated; @@ -802,7 +803,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, locked = false; } - if (isolate_movable_page(page, isolate_mode)) + if (!isolate_movable_page(page, isolate_mode)) goto isolate_success; } @@ -931,7 +932,7 @@ isolate_fail: trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn, nr_scanned, nr_isolated); - count_compact_events(COMPACTMIGRATE_SCANNED, nr_scanned); + cc->total_migrate_scanned += nr_scanned; if (nr_isolated) count_compact_events(COMPACTISOLATED, nr_isolated); @@ -991,9 +992,6 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, static bool suitable_migration_target(struct compact_control *cc, struct page *page) { - if (cc->ignore_block_suitable) - return true; - /* If the page is a large free page, then disallow migration */ if (PageBuddy(page)) { /* @@ -1005,6 +1003,9 @@ 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))) return true; @@ -1631,6 +1632,9 @@ out: zone->compact_cached_free_pfn = free_pfn; } + count_compact_events(COMPACTMIGRATE_SCANNED, cc->total_migrate_scanned); + count_compact_events(COMPACTFREE_SCANNED, cc->total_free_scanned); + trace_mm_compaction_end(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn, sync, ret); @@ -1645,6 +1649,8 @@ static enum compact_result compact_zone_order(struct zone *zone, int order, struct compact_control cc = { .nr_freepages = 0, .nr_migratepages = 0, + .total_migrate_scanned = 0, + .total_free_scanned = 0, .order = order, .gfp_mask = gfp_mask, .zone = zone, @@ -1757,6 +1763,8 @@ static void compact_node(int nid) struct zone *zone; struct compact_control cc = { .order = -1, + .total_migrate_scanned = 0, + .total_free_scanned = 0, .mode = MIGRATE_SYNC, .ignore_skip_hint = true, .whole_zone = true, @@ -1883,6 +1891,8 @@ static void kcompactd_do_work(pg_data_t *pgdat) struct zone *zone; struct compact_control cc = { .order = pgdat->kcompactd_max_order, + .total_migrate_scanned = 0, + .total_free_scanned = 0, .classzone_idx = pgdat->kcompactd_classzone_idx, .mode = MIGRATE_SYNC_LIGHT, .ignore_skip_hint = true, @@ -1891,7 +1901,7 @@ static void kcompactd_do_work(pg_data_t *pgdat) }; trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order, cc.classzone_idx); - count_vm_event(KCOMPACTD_WAKE); + count_compact_event(KCOMPACTD_WAKE); for (zoneid = 0; zoneid <= cc.classzone_idx; zoneid++) { int status; @@ -1909,6 +1919,8 @@ static void kcompactd_do_work(pg_data_t *pgdat) cc.nr_freepages = 0; cc.nr_migratepages = 0; + cc.total_migrate_scanned = 0; + cc.total_free_scanned = 0; cc.zone = zone; INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); @@ -1927,6 +1939,11 @@ static void kcompactd_do_work(pg_data_t *pgdat) defer_compaction(zone, cc.order); } + count_compact_events(KCOMPACTD_MIGRATE_SCANNED, + cc.total_migrate_scanned); + count_compact_events(KCOMPACTD_FREE_SCANNED, + cc.total_free_scanned); + VM_BUG_ON(!list_empty(&cc.freepages)); VM_BUG_ON(!list_empty(&cc.migratepages)); } @@ -1950,6 +1967,13 @@ void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx) if (pgdat->kcompactd_max_order < order) pgdat->kcompactd_max_order = order; + /* + * Pairs with implicit barrier in wait_event_freezable() + * such that wakeups are not missed in the lockless + * waitqueue_active() call. + */ + smp_acquire__after_ctrl_dep(); + if (pgdat->kcompactd_classzone_idx > classzone_idx) pgdat->kcompactd_classzone_idx = classzone_idx; diff --git a/mm/dmapool.c b/mm/dmapool.c index abcbfe86c25a..4d90a64b2fdc 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -93,7 +93,7 @@ show_pools(struct device *dev, struct device_attribute *attr, char *buf) spin_unlock_irq(&pool->lock); /* per-pool info, no real statistics yet */ - temp = scnprintf(next, size, "%-16s %4u %4Zu %4Zu %2u\n", + temp = scnprintf(next, size, "%-16s %4u %4zu %4zu %2u\n", pool->name, blocks, pages * (pool->allocation / pool->size), pool->size, pages); @@ -434,11 +434,11 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) spin_unlock_irqrestore(&pool->lock, flags); if (pool->dev) dev_err(pool->dev, - "dma_pool_free %s, %p (bad vaddr)/%Lx\n", - pool->name, vaddr, (unsigned long long)dma); + "dma_pool_free %s, %p (bad vaddr)/%pad\n", + pool->name, vaddr, &dma); else - pr_err("dma_pool_free %s, %p (bad vaddr)/%Lx\n", - pool->name, vaddr, (unsigned long long)dma); + pr_err("dma_pool_free %s, %p (bad vaddr)/%pad\n", + pool->name, vaddr, &dma); return; } { @@ -450,11 +450,11 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) } spin_unlock_irqrestore(&pool->lock, flags); if (pool->dev) - dev_err(pool->dev, "dma_pool_free %s, dma %Lx already free\n", - pool->name, (unsigned long long)dma); + dev_err(pool->dev, "dma_pool_free %s, dma %pad already free\n", + pool->name, &dma); else - pr_err("dma_pool_free %s, dma %Lx already free\n", - pool->name, (unsigned long long)dma); + pr_err("dma_pool_free %s, dma %pad already free\n", + pool->name, &dma); return; } } diff --git a/mm/filemap.c b/mm/filemap.c index 3f9afded581b..681da61080bc 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -13,6 +13,7 @@ #include <linux/compiler.h> #include <linux/dax.h> #include <linux/fs.h> +#include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/capability.h> #include <linux/kernel_stat.h> @@ -518,7 +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, @@ -788,7 +789,7 @@ static int wake_page_function(wait_queue_t *wait, unsigned mode, int sync, void return autoremove_wake_function(wait, mode, sync, key); } -void wake_up_page_bit(struct page *page, int bit_nr) +static void wake_up_page_bit(struct page *page, int bit_nr) { wait_queue_head_t *q = page_waitqueue(page); struct wait_page_key key; @@ -821,7 +822,13 @@ void wake_up_page_bit(struct page *page, int bit_nr) } spin_unlock_irqrestore(&q->lock, flags); } -EXPORT_SYMBOL(wake_up_page_bit); + +static void wake_up_page(struct page *page, int bit) +{ + if (!PageWaiters(page)) + return; + wake_up_page_bit(page, bit); +} static inline int wait_on_page_bit_common(wait_queue_head_t *q, struct page *page, int bit_nr, int state, bool lock) @@ -1002,9 +1009,12 @@ void page_endio(struct page *page, bool is_write, int err) unlock_page(page); } else { if (err) { + struct address_space *mapping; + SetPageError(page); - if (page->mapping) - mapping_set_error(page->mapping, err); + mapping = page_mapping(page); + if (mapping) + mapping_set_error(mapping, err); } end_page_writeback(page); } @@ -1013,7 +1023,7 @@ EXPORT_SYMBOL_GPL(page_endio); /** * __lock_page - get a lock on the page, assuming we need to sleep to get it - * @page: the page to lock + * @__page: the page to lock */ void __lock_page(struct page *__page) { @@ -1267,12 +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. @@ -2023,7 +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); @@ -2034,11 +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, iov_iter_count(iter) - count); /* * Btrfs can have a short DIO read if we encounter @@ -2049,7 +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; } @@ -2163,7 +2175,6 @@ static void do_async_mmap_readahead(struct vm_area_struct *vma, /** * filemap_fault - read in file data for page fault handling - * @vma: vma in which the fault was taken * @vmf: struct vm_fault containing details of the fault * * filemap_fault() is invoked via the vma operations vector for a @@ -2185,20 +2196,20 @@ static void do_async_mmap_readahead(struct vm_area_struct *vma, * * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set. */ -int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +int filemap_fault(struct vm_fault *vmf) { int error; - struct file *file = vma->vm_file; + struct file *file = vmf->vma->vm_file; struct address_space *mapping = file->f_mapping; 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; /* @@ -2210,12 +2221,12 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) * We found the page, so try async readahead before * waiting for the lock. */ - do_async_mmap_readahead(vma, ra, file, page, offset); + do_async_mmap_readahead(vmf->vma, ra, file, page, offset); } else if (!page) { /* No page in the page cache at all */ - do_sync_mmap_readahead(vma, ra, file, offset); + do_sync_mmap_readahead(vmf->vma, ra, file, offset); count_vm_event(PGMAJFAULT); - mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); + mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; retry_find: page = find_get_page(mapping, offset); @@ -2223,7 +2234,7 @@ retry_find: goto no_cached_page; } - if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) { + if (!lock_page_or_retry(page, vmf->vma->vm_mm, vmf->flags)) { put_page(page); return ret | VM_FAULT_RETRY; } @@ -2247,8 +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; @@ -2314,7 +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(); @@ -2360,8 +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) @@ -2390,14 +2401,14 @@ next: } EXPORT_SYMBOL(filemap_map_pages); -int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +int filemap_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); int ret = VM_FAULT_LOCKED; sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); + file_update_time(vmf->vma->vm_file); lock_page(page); if (page->mapping != inode->i_mapping) { unlock_page(page); @@ -2695,7 +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; @@ -2710,22 +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 @@ -2735,20 +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; } @@ -2992,7 +2998,7 @@ 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 @@ -10,7 +10,7 @@ #include <linux/swap.h> #include <linux/swapops.h> -#include <linux/sched.h> +#include <linux/sched/signal.h> #include <linux/rwsem.h> #include <linux/hugetlb.h> @@ -226,6 +226,7 @@ struct page *follow_page_mask(struct vm_area_struct *vma, unsigned int *page_mask) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; spinlock_t *ptl; @@ -243,8 +244,13 @@ struct page *follow_page_mask(struct vm_area_struct *vma, pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) return no_page_table(vma, flags); - - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (p4d_none(*p4d)) + return no_page_table(vma, flags); + BUILD_BUG_ON(p4d_huge(*p4d)); + if (unlikely(p4d_bad(*p4d))) + return no_page_table(vma, flags); + pud = pud_offset(p4d, address); if (pud_none(*pud)) return no_page_table(vma, flags); if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { @@ -253,6 +259,13 @@ struct page *follow_page_mask(struct vm_area_struct *vma, return page; return no_page_table(vma, flags); } + if (pud_devmap(*pud)) { + ptl = pud_lock(mm, pud); + page = follow_devmap_pud(vma, address, pud, flags); + spin_unlock(ptl); + if (page) + return page; + } if (unlikely(pud_bad(*pud))) return no_page_table(vma, flags); @@ -265,8 +278,6 @@ struct page *follow_page_mask(struct vm_area_struct *vma, return page; return no_page_table(vma, flags); } - if ((flags & FOLL_NUMA) && pmd_protnone(*pmd)) - return no_page_table(vma, flags); if (pmd_devmap(*pmd)) { ptl = pmd_lock(mm, pmd); page = follow_devmap_pmd(vma, address, pmd, flags); @@ -277,6 +288,9 @@ struct page *follow_page_mask(struct vm_area_struct *vma, if (likely(!pmd_trans_huge(*pmd))) return follow_page_pte(vma, address, pmd, flags); + if ((flags & FOLL_NUMA) && pmd_protnone(*pmd)) + return no_page_table(vma, flags); + ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_trans_huge(*pmd))) { spin_unlock(ptl); @@ -317,6 +331,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, struct page **page) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -330,7 +345,9 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, else pgd = pgd_offset_gate(mm, address); BUG_ON(pgd_none(*pgd)); - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + BUG_ON(p4d_none(*p4d)); + pud = pud_offset(p4d, address); BUG_ON(pud_none(*pud)); pmd = pmd_offset(pud, address); if (pmd_none(*pmd)) @@ -572,7 +589,7 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (is_vm_hugetlb_page(vma)) { i = follow_hugetlb_page(mm, vma, pages, vmas, &start, &nr_pages, i, - gup_flags); + gup_flags, nonblocking); continue; } } @@ -1172,34 +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))); @@ -1215,6 +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)++; @@ -1244,15 +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); @@ -1276,6 +1380,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, return 0; } + SetPageReferenced(head); return 1; } @@ -1285,9 +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); @@ -1311,6 +1419,7 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return 0; } + SetPageReferenced(head); return 1; } @@ -1321,9 +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); @@ -1347,6 +1457,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 0; } + SetPageReferenced(head); return 1; } @@ -1392,13 +1503,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, return 1; } -static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, +static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; - pudp = pud_offset(&pgd, addr); + pudp = pud_offset(&p4d, addr); do { pud_t pud = READ_ONCE(*pudp); @@ -1420,6 +1531,31 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, return 1; } +static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + p4d_t *p4dp; + + p4dp = p4d_offset(&pgd, addr); + do { + p4d_t p4d = READ_ONCE(*p4dp); + + next = p4d_addr_end(addr, end); + if (p4d_none(p4d)) + return 0; + BUILD_BUG_ON(p4d_huge(p4d)); + if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) { + if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr, + P4D_SHIFT, next, write, pages, nr)) + return 0; + } else if (!gup_pud_range(p4d, addr, next, write, pages, nr)) + return 0; + } while (p4dp++, addr = next, addr != end); + + return 1; +} + /* * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to * the regular GUP. It will only return non-negative values. @@ -1439,7 +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; /* @@ -1470,7 +1606,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr, PGDIR_SHIFT, next, write, pages, &nr)) break; - } else if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + } else if (!gup_p4d_range(pgd, addr, next, write, pages, &nr)) break; } while (pgdp++, addr = next, addr != end); local_irq_restore(flags); @@ -1478,6 +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 @@ -1497,11 +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 5f3ad65c85de..b787c4cfda0e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -9,6 +9,8 @@ #include <linux/mm.h> #include <linux/sched.h> +#include <linux/sched/coredump.h> +#include <linux/sched/numa_balancing.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/mmu_notifier.h> @@ -142,42 +144,6 @@ static struct shrinker huge_zero_page_shrinker = { }; #ifdef CONFIG_SYSFS - -static ssize_t triple_flag_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count, - enum transparent_hugepage_flag enabled, - enum transparent_hugepage_flag deferred, - enum transparent_hugepage_flag req_madv) -{ - if (!memcmp("defer", buf, - min(sizeof("defer")-1, count))) { - if (enabled == deferred) - return -EINVAL; - clear_bit(enabled, &transparent_hugepage_flags); - clear_bit(req_madv, &transparent_hugepage_flags); - set_bit(deferred, &transparent_hugepage_flags); - } else if (!memcmp("always", buf, - min(sizeof("always")-1, count))) { - clear_bit(deferred, &transparent_hugepage_flags); - clear_bit(req_madv, &transparent_hugepage_flags); - set_bit(enabled, &transparent_hugepage_flags); - } else if (!memcmp("madvise", buf, - min(sizeof("madvise")-1, count))) { - clear_bit(enabled, &transparent_hugepage_flags); - clear_bit(deferred, &transparent_hugepage_flags); - set_bit(req_madv, &transparent_hugepage_flags); - } else if (!memcmp("never", buf, - min(sizeof("never")-1, count))) { - clear_bit(enabled, &transparent_hugepage_flags); - clear_bit(req_madv, &transparent_hugepage_flags); - clear_bit(deferred, &transparent_hugepage_flags); - } else - return -EINVAL; - - return count; -} - static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -193,19 +159,28 @@ static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - ssize_t ret; + ssize_t ret = count; - ret = triple_flag_store(kobj, attr, buf, count, - TRANSPARENT_HUGEPAGE_FLAG, - TRANSPARENT_HUGEPAGE_FLAG, - TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG); + if (!memcmp("always", buf, + min(sizeof("always")-1, count))) { + clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); + } else if (!memcmp("madvise", buf, + min(sizeof("madvise")-1, count))) { + clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); + } else if (!memcmp("never", buf, + min(sizeof("never")-1, count))) { + clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); + } else + ret = -EINVAL; if (ret > 0) { int err = start_stop_khugepaged(); if (err) ret = err; } - return ret; } static struct kobj_attribute enabled_attr = @@ -241,32 +216,58 @@ ssize_t single_hugepage_flag_store(struct kobject *kobj, return count; } -/* - * Currently defrag only disables __GFP_NOWAIT for allocation. A blind - * __GFP_REPEAT is too aggressive, it's never worth swapping tons of - * memory just to allocate one more hugepage. - */ static ssize_t defrag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) - return sprintf(buf, "[always] defer madvise never\n"); + return sprintf(buf, "[always] defer defer+madvise madvise never\n"); if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) - return sprintf(buf, "always [defer] madvise never\n"); - else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) - return sprintf(buf, "always defer [madvise] never\n"); - else - return sprintf(buf, "always defer madvise [never]\n"); - + return sprintf(buf, "always [defer] defer+madvise madvise never\n"); + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) + return sprintf(buf, "always defer [defer+madvise] madvise never\n"); + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) + return sprintf(buf, "always defer defer+madvise [madvise] never\n"); + return sprintf(buf, "always defer defer+madvise madvise [never]\n"); } + static ssize_t defrag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - return triple_flag_store(kobj, attr, buf, count, - TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, - TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, - TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG); + if (!memcmp("always", buf, + min(sizeof("always")-1, count))) { + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_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_DIRECT_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); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); + } else if (!memcmp("never", buf, + min(sizeof("never")-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_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); + } else + return -EINVAL; + + return count; } static struct kobj_attribute defrag_attr = __ATTR(defrag, 0644, defrag_show, defrag_store); @@ -612,25 +613,28 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page, } /* - * If THP defrag is set to always then directly reclaim/compact as necessary - * If set to defer then do only background reclaim/compact and defer to khugepaged - * If set to madvise and the VMA is flagged then directly reclaim/compact - * When direct reclaim/compact is allowed, don't retry except for flagged VMA's + * always: directly stall for all thp allocations + * defer: wake kswapd and fail if not immediately available + * defer+madvise: wake kswapd and directly stall for MADV_HUGEPAGE, otherwise + * fail if not immediately available + * madvise: directly stall for MADV_HUGEPAGE, otherwise fail if not immediately + * available + * never: never stall for any thp allocation */ static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) { - bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); + const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); - if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, - &transparent_hugepage_flags) && vma_madvised) - return GFP_TRANSHUGE; - else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, - &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; - else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, - &transparent_hugepage_flags)) + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); - + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) + return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) + return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : + __GFP_KSWAPD_RECLAIM); + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) + return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : + 0); return GFP_TRANSHUGE_LIGHT; } @@ -755,6 +759,60 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, } EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd); +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma) +{ + if (likely(vma->vm_flags & VM_WRITE)) + pud = pud_mkwrite(pud); + return pud; +} + +static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, pfn_t pfn, pgprot_t prot, bool write) +{ + struct mm_struct *mm = vma->vm_mm; + pud_t entry; + spinlock_t *ptl; + + ptl = pud_lock(mm, pud); + entry = pud_mkhuge(pfn_t_pud(pfn, prot)); + if (pfn_t_devmap(pfn)) + entry = pud_mkdevmap(entry); + if (write) { + entry = pud_mkyoung(pud_mkdirty(entry)); + entry = maybe_pud_mkwrite(entry, vma); + } + set_pud_at(mm, addr, pud, entry); + update_mmu_cache_pud(vma, addr, pud); + spin_unlock(ptl); +} + +int vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, pfn_t pfn, bool write) +{ + pgprot_t pgprot = vma->vm_page_prot; + /* + * If we had pud_special, we could avoid all these restrictions, + * but we need to be consistent with PTEs and architectures that + * can't support a 'special' bit. + */ + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); + BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == + (VM_PFNMAP|VM_MIXEDMAP)); + BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); + BUG_ON(!pfn_t_devmap(pfn)); + + if (addr < vma->vm_start || addr >= vma->vm_end) + return VM_FAULT_SIGBUS; + + track_pfn_insert(vma, &pgprot, pfn); + + insert_pfn_pud(vma, addr, pud, pfn, pgprot, write); + return VM_FAULT_NOPAGE; +} +EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud); +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ + static void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) { @@ -885,6 +943,123 @@ out: return ret; } +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static void touch_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud) +{ + pud_t _pud; + + /* + * We should set the dirty bit only for FOLL_WRITE but for now + * the dirty bit in the pud is meaningless. And if the dirty + * bit will become meaningful and we'll only set it with + * FOLL_WRITE, an atomic set_bit will be required on the pud to + * set the young bit, instead of the current set_pud_at. + */ + _pud = pud_mkyoung(pud_mkdirty(*pud)); + if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK, + pud, _pud, 1)) + update_mmu_cache_pud(vma, addr, pud); +} + +struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, int flags) +{ + unsigned long pfn = pud_pfn(*pud); + struct mm_struct *mm = vma->vm_mm; + struct dev_pagemap *pgmap; + struct page *page; + + assert_spin_locked(pud_lockptr(mm, pud)); + + if (flags & FOLL_WRITE && !pud_write(*pud)) + return NULL; + + if (pud_present(*pud) && pud_devmap(*pud)) + /* pass */; + else + return NULL; + + if (flags & FOLL_TOUCH) + touch_pud(vma, addr, pud); + + /* + * device mapped pages can only be returned if the + * caller will manage the page reference count. + */ + if (!(flags & FOLL_GET)) + return ERR_PTR(-EEXIST); + + pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; + pgmap = get_dev_pagemap(pfn, NULL); + if (!pgmap) + return ERR_PTR(-EFAULT); + page = pfn_to_page(pfn); + get_page(page); + put_dev_pagemap(pgmap); + + return page; +} + +int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pud_t *dst_pud, pud_t *src_pud, unsigned long addr, + struct vm_area_struct *vma) +{ + spinlock_t *dst_ptl, *src_ptl; + pud_t pud; + int ret; + + dst_ptl = pud_lock(dst_mm, dst_pud); + src_ptl = pud_lockptr(src_mm, src_pud); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + + ret = -EAGAIN; + pud = *src_pud; + if (unlikely(!pud_trans_huge(pud) && !pud_devmap(pud))) + goto out_unlock; + + /* + * When page table lock is held, the huge zero pud should not be + * under splitting since we don't split the page itself, only pud to + * a page table. + */ + if (is_huge_zero_pud(pud)) { + /* No huge zero pud yet */ + } + + pudp_set_wrprotect(src_mm, addr, src_pud); + pud = pud_mkold(pud_wrprotect(pud)); + set_pud_at(dst_mm, addr, dst_pud, pud); + + ret = 0; +out_unlock: + spin_unlock(src_ptl); + spin_unlock(dst_ptl); + return ret; +} + +void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) +{ + pud_t entry; + unsigned long haddr; + bool write = vmf->flags & FAULT_FLAG_WRITE; + + vmf->ptl = pud_lock(vmf->vma->vm_mm, vmf->pud); + if (unlikely(!pud_same(*vmf->pud, orig_pud))) + goto unlock; + + entry = pud_mkyoung(orig_pud); + if (write) + entry = pud_mkdirty(entry); + haddr = vmf->address & HPAGE_PUD_MASK; + if (pudp_set_access_flags(vmf->vma, haddr, vmf->pud, entry, write)) + update_mmu_cache_pud(vmf->vma, vmf->address, vmf->pud); + +unlock: + spin_unlock(vmf->ptl); +} +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ + void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd) { pmd_t entry; @@ -1253,7 +1428,7 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) } /* See similar comment in do_numa_page for explanation */ - if (!pmd_write(pmd)) + if (!pmd_savedwrite(pmd)) flags |= TNF_NO_GROUP; /* @@ -1316,7 +1491,7 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) goto out; clear_pmdnuma: BUG_ON(!PageLocked(page)); - was_writable = pmd_write(pmd); + was_writable = pmd_savedwrite(pmd); pmd = pmd_modify(pmd, vma->vm_page_prot); pmd = pmd_mkyoung(pmd); if (was_writable) @@ -1333,7 +1508,7 @@ out: if (page_nid != -1) task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, - vmf->flags); + flags); return 0; } @@ -1389,18 +1564,16 @@ 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); @@ -1549,37 +1722,69 @@ 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_mkwrite(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; } @@ -1599,6 +1804,84 @@ spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) return NULL; } +/* + * Returns true if a given pud maps a thp, false otherwise. + * + * Note that if it returns true, this routine returns without unlocking page + * table lock. So callers must unlock it. + */ +spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) +{ + spinlock_t *ptl; + + ptl = pud_lock(vma->vm_mm, pud); + if (likely(pud_trans_huge(*pud) || pud_devmap(*pud))) + return ptl; + spin_unlock(ptl); + return NULL; +} + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, + pud_t *pud, unsigned long addr) +{ + pud_t orig_pud; + spinlock_t *ptl; + + ptl = __pud_trans_huge_lock(pud, vma); + if (!ptl) + return 0; + /* + * For architectures like ppc64 we look at deposited pgtable + * when calling pudp_huge_get_and_clear. So do the + * pgtable_trans_huge_withdraw after finishing pudp related + * operations. + */ + orig_pud = pudp_huge_get_and_clear_full(tlb->mm, addr, pud, + tlb->fullmm); + tlb_remove_pud_tlb_entry(tlb, pud, addr); + if (vma_is_dax(vma)) { + spin_unlock(ptl); + /* No zero page support yet */ + } else { + /* No support for anonymous PUD pages yet */ + BUG(); + } + return 1; +} + +static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud, + unsigned long haddr) +{ + VM_BUG_ON(haddr & ~HPAGE_PUD_MASK); + VM_BUG_ON_VMA(vma->vm_start > haddr, vma); + VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma); + VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud)); + + count_vm_event(THP_SPLIT_PUD); + + pudp_huge_clear_flush_notify(vma, haddr, pud); +} + +void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, + unsigned long address) +{ + spinlock_t *ptl; + struct mm_struct *mm = vma->vm_mm; + unsigned long haddr = address & HPAGE_PUD_MASK; + + mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PUD_SIZE); + ptl = pud_lock(mm, pud); + if (unlikely(!pud_trans_huge(*pud) && !pud_devmap(*pud))) + goto out; + __split_huge_pud_locked(vma, pud, haddr); + +out: + spin_unlock(ptl); + mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PUD_SIZE); +} +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ + static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd) { @@ -1795,6 +2078,7 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct page *page) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -1802,7 +2086,11 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, if (!pgd_present(*pgd)) return; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + return; + + pud = pud_offset(p4d, address); if (!pud_present(*pud)) return; @@ -1855,32 +2143,27 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, static void freeze_page(struct page *page) { enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS | - TTU_RMAP_LOCKED; - int i, ret; + TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD; + bool unmap_success; VM_BUG_ON_PAGE(!PageHead(page), page); if (PageAnon(page)) ttu_flags |= TTU_MIGRATION; - /* We only need TTU_SPLIT_HUGE_PMD once */ - ret = try_to_unmap(page, ttu_flags | TTU_SPLIT_HUGE_PMD); - for (i = 1; !ret && i < HPAGE_PMD_NR; i++) { - /* Cut short if the page is unmapped */ - if (page_count(page) == 1) - return; - - ret = try_to_unmap(page + i, ttu_flags); - } - VM_BUG_ON_PAGE(ret, page + i - 1); + unmap_success = try_to_unmap(page, ttu_flags); + VM_BUG_ON_PAGE(!unmap_success, page); } static void unfreeze_page(struct page *page) { int i; - - for (i = 0; i < HPAGE_PMD_NR; i++) - remove_migration_ptes(page + i, page + i, true); + if (PageTransHuge(page)) { + remove_migration_ptes(page, page, true); + } else { + for (i = 0; i < HPAGE_PMD_NR; i++) + remove_migration_ptes(page + i, page + i, true); + } } static void __split_huge_page_tail(struct page *head, int tail, @@ -2115,7 +2398,6 @@ 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 c7025c132670..e5828875f7bb 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -18,6 +18,7 @@ #include <linux/bootmem.h> #include <linux/sysfs.h> #include <linux/slab.h> +#include <linux/sched/signal.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> @@ -32,6 +33,7 @@ #include <linux/hugetlb.h> #include <linux/hugetlb_cgroup.h> #include <linux/node.h> +#include <linux/userfaultfd_k.h> #include "internal.h" int hugepages_treat_as_movable; @@ -1051,7 +1053,8 @@ static int __alloc_gigantic_page(unsigned long start_pfn, unsigned long nr_pages) { unsigned long end_pfn = start_pfn + nr_pages; - return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE); + return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE, + GFP_KERNEL); } static bool pfn_range_valid_gigantic(struct zone *z, @@ -3141,7 +3144,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma) * hugegpage VMA. do_page_fault() is supposed to trap this, so BUG is we get * this far. */ -static int hugetlb_vm_op_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +static int hugetlb_vm_op_fault(struct vm_fault *vmf) { BUG(); return 0; @@ -3680,6 +3683,38 @@ retry: size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) goto out; + + /* + * Check for page in userfault range + */ + if (userfaultfd_missing(vma)) { + u32 hash; + struct vm_fault vmf = { + .vma = vma, + .address = address, + .flags = flags, + /* + * Hard to debug if it ends up being + * used by a callee that assumes + * something about the other + * uninitialized fields... same as in + * memory.c + */ + }; + + /* + * hugetlb_fault_mutex must be dropped before + * handling userfault. Reacquire after handling + * fault to make calling code simpler. + */ + hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping, + idx, address); + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + ret = handle_userfault(&vmf, VM_UFFD_MISSING); + mutex_lock(&hugetlb_fault_mutex_table[hash]); + goto out; + } + page = alloc_huge_page(vma, address, 0); if (IS_ERR(page)) { ret = PTR_ERR(page); @@ -3948,10 +3983,113 @@ out_mutex: return ret; } +/* + * Used by userfaultfd UFFDIO_COPY. Based on mcopy_atomic_pte with + * modifications for huge pages. + */ +int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, + pte_t *dst_pte, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + struct page **pagep) +{ + int vm_shared = dst_vma->vm_flags & VM_SHARED; + struct hstate *h = hstate_vma(dst_vma); + pte_t _dst_pte; + spinlock_t *ptl; + int ret; + struct page *page; + + if (!*pagep) { + ret = -ENOMEM; + page = alloc_huge_page(dst_vma, dst_addr, 0); + if (IS_ERR(page)) + goto out; + + ret = copy_huge_page_from_user(page, + (const void __user *) src_addr, + pages_per_huge_page(h), false); + + /* fallback to copy_from_user outside mmap_sem */ + if (unlikely(ret)) { + ret = -EFAULT; + *pagep = page; + /* don't free the page */ + goto out; + } + } else { + page = *pagep; + *pagep = NULL; + } + + /* + * The memory barrier inside __SetPageUptodate makes sure that + * preceding stores to the page contents become visible before + * the set_pte_at() write. + */ + __SetPageUptodate(page); + set_page_huge_active(page); + + /* + * If shared, add to page cache + */ + if (vm_shared) { + struct address_space *mapping = dst_vma->vm_file->f_mapping; + pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr); + + ret = huge_add_to_page_cache(page, mapping, idx); + if (ret) + goto out_release_nounlock; + } + + ptl = huge_pte_lockptr(h, dst_mm, dst_pte); + spin_lock(ptl); + + ret = -EEXIST; + if (!huge_pte_none(huge_ptep_get(dst_pte))) + goto out_release_unlock; + + if (vm_shared) { + page_dup_rmap(page, true); + } else { + ClearPagePrivate(page); + hugepage_add_new_anon_rmap(page, dst_vma, dst_addr); + } + + _dst_pte = make_huge_pte(dst_vma, page, dst_vma->vm_flags & VM_WRITE); + if (dst_vma->vm_flags & VM_WRITE) + _dst_pte = huge_pte_mkdirty(_dst_pte); + _dst_pte = pte_mkyoung(_dst_pte); + + set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); + + (void)huge_ptep_set_access_flags(dst_vma, dst_addr, dst_pte, _dst_pte, + dst_vma->vm_flags & VM_WRITE); + hugetlb_count_add(pages_per_huge_page(h), dst_mm); + + /* No need to invalidate - it was non-present before */ + update_mmu_cache(dst_vma, dst_addr, dst_pte); + + spin_unlock(ptl); + if (vm_shared) + unlock_page(page); + ret = 0; +out: + return ret; +out_release_unlock: + spin_unlock(ptl); +out_release_nounlock: + if (vm_shared) + unlock_page(page); + put_page(page); + goto out; +} + long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page **pages, struct vm_area_struct **vmas, unsigned long *position, unsigned long *nr_pages, - long i, unsigned int flags) + long i, unsigned int flags, int *nonblocking) { unsigned long pfn_offset; unsigned long vaddr = *position; @@ -4014,16 +4152,43 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, ((flags & FOLL_WRITE) && !huge_pte_write(huge_ptep_get(pte)))) { int ret; + unsigned int fault_flags = 0; if (pte) spin_unlock(ptl); - ret = hugetlb_fault(mm, vma, vaddr, - (flags & FOLL_WRITE) ? FAULT_FLAG_WRITE : 0); - if (!(ret & VM_FAULT_ERROR)) - continue; - - remainder = 0; - break; + if (flags & FOLL_WRITE) + fault_flags |= FAULT_FLAG_WRITE; + if (nonblocking) + fault_flags |= FAULT_FLAG_ALLOW_RETRY; + if (flags & FOLL_NOWAIT) + fault_flags |= FAULT_FLAG_ALLOW_RETRY | + FAULT_FLAG_RETRY_NOWAIT; + if (flags & FOLL_TRIED) { + VM_WARN_ON_ONCE(fault_flags & + FAULT_FLAG_ALLOW_RETRY); + fault_flags |= FAULT_FLAG_TRIED; + } + ret = hugetlb_fault(mm, vma, vaddr, fault_flags); + if (ret & VM_FAULT_ERROR) { + remainder = 0; + break; + } + if (ret & VM_FAULT_RETRY) { + if (nonblocking) + *nonblocking = 0; + *nr_pages = 0; + /* + * VM_FAULT_RETRY must not return an + * error, it will return zero + * instead. + * + * No need to update "position" as the + * caller will not check it after + * *nr_pages is set to 0. + */ + return i; + } + continue; } pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT; @@ -4052,6 +4217,11 @@ same_page: spin_unlock(ptl); } *nr_pages = remainder; + /* + * setting position is actually required only if remainder is + * not zero but it's faster not to add a "if (remainder)" + * branch. + */ *position = vaddr; return i ? i : -EFAULT; @@ -4233,7 +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; @@ -4385,7 +4557,8 @@ out: int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) { pgd_t *pgd = pgd_offset(mm, *addr); - pud_t *pud = pud_offset(pgd, *addr); + p4d_t *p4d = p4d_offset(pgd, *addr); + pud_t *pud = pud_offset(p4d, *addr); BUG_ON(page_count(virt_to_page(ptep)) == 0); if (page_count(virt_to_page(ptep)) == 1) @@ -4416,11 +4589,13 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pte_t *pte = NULL; pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); + p4d = p4d_offset(pgd, addr); + pud = pud_alloc(mm, p4d, addr); if (pud) { if (sz == PUD_SIZE) { pte = (pte_t *)pud; @@ -4440,18 +4615,22 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; - pmd_t *pmd = NULL; + pmd_t *pmd; pgd = pgd_offset(mm, addr); - if (pgd_present(*pgd)) { - pud = pud_offset(pgd, addr); - if (pud_present(*pud)) { - if (pud_huge(*pud)) - return (pte_t *)pud; - pmd = pmd_offset(pud, addr); - } - } + if (!pgd_present(*pgd)) + return NULL; + p4d = p4d_offset(pgd, addr); + if (!p4d_present(*p4d)) + return NULL; + pud = pud_offset(p4d, addr); + if (!pud_present(*pud)) + return NULL; + if (pud_huge(*pud)) + return (pte_t *)pud; + pmd = pmd_offset(pud, addr); return (pte_t *) pmd; } @@ -4474,6 +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); @@ -4483,12 +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 7aa2ea0a8623..04d08ef91224 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -43,6 +43,11 @@ int do_swap_page(struct vm_fault *vmf); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); +static inline bool can_madv_dontneed_vma(struct vm_area_struct *vma) +{ + return !(vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)); +} + void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, @@ -76,11 +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: @@ -133,9 +143,9 @@ struct alloc_context { * Assumption: *_mem_map is contiguous at least up to MAX_ORDER */ static inline unsigned long -__find_buddy_index(unsigned long page_idx, unsigned int order) +__find_buddy_pfn(unsigned long page_pfn, unsigned int order) { - return page_idx ^ (1 << order); + return page_pfn ^ (1 << order); } extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn, @@ -175,6 +185,8 @@ struct compact_control { struct list_head migratepages; /* List of pages being migrated */ unsigned long nr_freepages; /* Number of isolated free pages */ unsigned long nr_migratepages; /* Number of pages to migrate */ + unsigned long total_migrate_scanned; + unsigned long total_free_scanned; 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 */ @@ -328,12 +340,15 @@ __vma_address(struct page *page, struct vm_area_struct *vma) static inline unsigned long vma_address(struct page *page, struct vm_area_struct *vma) { - unsigned long address = __vma_address(page, vma); + unsigned long start, end; + + start = __vma_address(page, vma); + end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1); /* page should be within @vma mapping range */ - VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); + VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma); - return address; + return max(start, vma->vm_start); } #else /* !CONFIG_MMU */ @@ -471,6 +486,13 @@ 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); @@ -488,4 +510,14 @@ 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 b2a0cff2bb35..9348d27088c1 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -29,6 +29,7 @@ #include <linux/module.h> #include <linux/printk.h> #include <linux/sched.h> +#include <linux/sched/task_stack.h> #include <linux/slab.h> #include <linux/stacktrace.h> #include <linux/string.h> @@ -39,6 +40,16 @@ #include "kasan.h" #include "../slab.h" +void kasan_enable_current(void) +{ + current->kasan_depth++; +} + +void kasan_disable_current(void) +{ + current->kasan_depth--; +} + /* * Poisons the shadow memory for 'size' bytes starting from 'addr'. * Memory addresses should be aligned to KASAN_SHADOW_SCALE_SIZE. @@ -435,7 +446,7 @@ void kasan_cache_shrink(struct kmem_cache *cache) quarantine_remove_cache(cache); } -void kasan_cache_destroy(struct kmem_cache *cache) +void kasan_cache_shutdown(struct kmem_cache *cache) { quarantine_remove_cache(cache); } @@ -566,7 +577,8 @@ bool kasan_slab_free(struct kmem_cache *cache, void *object) 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; } 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/kasan_init.c b/mm/kasan/kasan_init.c index 31238dad85fb..b96a5f773d88 100644 --- a/mm/kasan/kasan_init.c +++ b/mm/kasan/kasan_init.c @@ -30,6 +30,9 @@ */ unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss; +#if CONFIG_PGTABLE_LEVELS > 4 +p4d_t kasan_zero_p4d[PTRS_PER_P4D] __page_aligned_bss; +#endif #if CONFIG_PGTABLE_LEVELS > 3 pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss; #endif @@ -82,10 +85,10 @@ static void __init zero_pmd_populate(pud_t *pud, unsigned long addr, } while (pmd++, addr = next, addr != end); } -static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr, +static void __init zero_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long end) { - pud_t *pud = pud_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); unsigned long next; do { @@ -107,6 +110,23 @@ static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr, } while (pud++, addr = next, addr != end); } +static void __init zero_p4d_populate(pgd_t *pgd, unsigned long addr, + unsigned long end) +{ + p4d_t *p4d = p4d_offset(pgd, addr); + unsigned long next; + + do { + next = p4d_addr_end(addr, end); + + if (p4d_none(*p4d)) { + p4d_populate(&init_mm, p4d, + early_alloc(PAGE_SIZE, NUMA_NO_NODE)); + } + zero_pud_populate(p4d, addr, next); + } while (p4d++, addr = next, addr != end); +} + /** * kasan_populate_zero_shadow - populate shadow memory region with * kasan_zero_page @@ -125,6 +145,7 @@ void __init kasan_populate_zero_shadow(const void *shadow_start, next = pgd_addr_end(addr, end); if (IS_ALIGNED(addr, PGDIR_SIZE) && end - addr >= PGDIR_SIZE) { + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -135,9 +156,22 @@ void __init kasan_populate_zero_shadow(const void *shadow_start, * 3,2 - level page tables where we don't have * puds,pmds, so pgd_populate(), pud_populate() * is noops. + * + * The ifndef is required to avoid build breakage. + * + * With 5level-fixup.h, pgd_populate() is not nop and + * we reference kasan_zero_p4d. It's not defined + * unless 5-level paging enabled. + * + * The ifndef can be dropped once all KASAN-enabled + * architectures will switch to pgtable-nop4d.h. */ - pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_pud)); - pud = pud_offset(pgd, addr); +#ifndef __ARCH_HAS_5LEVEL_HACK + pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_p4d)); +#endif + p4d = p4d_offset(pgd, addr); + p4d_populate(&init_mm, p4d, lm_alias(kasan_zero_pud)); + pud = pud_offset(p4d, addr); pud_populate(&init_mm, pud, lm_alias(kasan_zero_pmd)); pmd = pmd_offset(pud, addr); pmd_populate_kernel(&init_mm, pmd, lm_alias(kasan_zero_pte)); @@ -148,6 +182,6 @@ void __init kasan_populate_zero_shadow(const void *shadow_start, pgd_populate(&init_mm, pgd, early_alloc(PAGE_SIZE, NUMA_NO_NODE)); } - zero_pud_populate(pgd, addr, next); + zero_p4d_populate(pgd, addr, next); } while (pgd++, addr = next, addr != end); } diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index dae929c02bbb..3a8ddf8baf7d 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -25,6 +25,7 @@ #include <linux/printk.h> #include <linux/shrinker.h> #include <linux/slab.h> +#include <linux/srcu.h> #include <linux/string.h> #include <linux/types.h> @@ -103,6 +104,7 @@ static int quarantine_tail; /* Total size of all objects in global_quarantine across all batches. */ static unsigned long quarantine_size; static DEFINE_SPINLOCK(quarantine_lock); +DEFINE_STATIC_SRCU(remove_cache_srcu); /* Maximum size of the global queue. */ static unsigned long quarantine_max_size; @@ -173,17 +175,22 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) struct qlist_head *q; struct qlist_head temp = QLIST_INIT; + /* + * Note: irq must be disabled until after we move the batch to the + * global quarantine. Otherwise quarantine_remove_cache() can miss + * some objects belonging to the cache if they are in our local temp + * list. quarantine_remove_cache() executes on_each_cpu() at the + * beginning which ensures that it either sees the objects in per-cpu + * lists or in the global quarantine. + */ local_irq_save(flags); q = this_cpu_ptr(&cpu_quarantine); qlist_put(q, &info->quarantine_link, cache->size); - if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) + if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) { qlist_move_all(q, &temp); - local_irq_restore(flags); - - if (unlikely(!qlist_empty(&temp))) { - spin_lock_irqsave(&quarantine_lock, flags); + spin_lock(&quarantine_lock); WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes); qlist_move_all(&temp, &global_quarantine[quarantine_tail]); if (global_quarantine[quarantine_tail].bytes >= @@ -196,20 +203,33 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) if (new_tail != quarantine_head) quarantine_tail = new_tail; } - spin_unlock_irqrestore(&quarantine_lock, flags); + spin_unlock(&quarantine_lock); } + + local_irq_restore(flags); } void quarantine_reduce(void) { size_t total_size, new_quarantine_size, percpu_quarantines; unsigned long flags; + int srcu_idx; struct qlist_head to_free = QLIST_INIT; if (likely(READ_ONCE(quarantine_size) <= READ_ONCE(quarantine_max_size))) return; + /* + * srcu critical section ensures that quarantine_remove_cache() + * will not miss objects belonging to the cache while they are in our + * local to_free list. srcu is chosen because (1) it gives us private + * grace period domain that does not interfere with anything else, + * and (2) it allows synchronize_srcu() to return without waiting + * if there are no pending read critical sections (which is the + * expected case). + */ + srcu_idx = srcu_read_lock(&remove_cache_srcu); spin_lock_irqsave(&quarantine_lock, flags); /* @@ -237,6 +257,7 @@ void quarantine_reduce(void) spin_unlock_irqrestore(&quarantine_lock, flags); qlist_free_all(&to_free, NULL); + srcu_read_unlock(&remove_cache_srcu, srcu_idx); } static void qlist_move_cache(struct qlist_head *from, @@ -274,17 +295,34 @@ static void per_cpu_remove_cache(void *arg) qlist_free_all(&to_free, cache); } +/* Free all quarantined objects belonging to cache. */ void quarantine_remove_cache(struct kmem_cache *cache) { unsigned long flags, i; struct qlist_head to_free = QLIST_INIT; + /* + * Must be careful to not miss any objects that are being moved from + * per-cpu list to the global quarantine in quarantine_put(), + * nor objects being freed in quarantine_reduce(). on_each_cpu() + * achieves the first goal, while synchronize_srcu() achieves the + * second. + */ on_each_cpu(per_cpu_remove_cache, cache, 1); spin_lock_irqsave(&quarantine_lock, flags); - for (i = 0; i < QUARANTINE_BATCHES; i++) + for (i = 0; i < QUARANTINE_BATCHES; i++) { + if (qlist_empty(&global_quarantine[i])) + continue; qlist_move_cache(&global_quarantine[i], &to_free, cache); + /* Scanning whole quarantine can take a while. */ + spin_unlock_irqrestore(&quarantine_lock, flags); + cond_resched(); + spin_lock_irqsave(&quarantine_lock, flags); + } spin_unlock_irqrestore(&quarantine_lock, flags); qlist_free_all(&to_free, cache); + + synchronize_srcu(&remove_cache_srcu); } 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 77ae3239c3de..7cb9c88bb4a3 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2,6 +2,8 @@ #include <linux/mm.h> #include <linux/sched.h> +#include <linux/sched/mm.h> +#include <linux/sched/coredump.h> #include <linux/mmu_notifier.h> #include <linux/rmap.h> #include <linux/swap.h> @@ -420,7 +422,7 @@ int __khugepaged_enter(struct mm_struct *mm) list_add_tail(&mm_slot->mm_node, &khugepaged_scan.mm_head); spin_unlock(&khugepaged_mm_lock); - atomic_inc(&mm->mm_count); + mmgrab(mm); if (wakeup) wake_up_interruptible(&khugepaged_wait); @@ -481,8 +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); } @@ -530,7 +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 @@ -548,7 +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; @@ -577,8 +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); @@ -1181,7 +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/kmemleak.c b/mm/kmemleak.c index da3436953022..20036d4f9f13 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -73,7 +73,9 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/list.h> -#include <linux/sched.h> +#include <linux/sched/signal.h> +#include <linux/sched/task.h> +#include <linux/sched/task_stack.h> #include <linux/jiffies.h> #include <linux/delay.h> #include <linux/export.h> @@ -1414,7 +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 */ @@ -19,6 +19,8 @@ #include <linux/fs.h> #include <linux/mman.h> #include <linux/sched.h> +#include <linux/sched/mm.h> +#include <linux/sched/coredump.h> #include <linux/rwsem.h> #include <linux/pagemap.h> #include <linux/rmap.h> @@ -223,6 +225,12 @@ static unsigned int ksm_thread_pages_to_scan = 100; /* Milliseconds ksmd should sleep between batches */ static unsigned int ksm_thread_sleep_millisecs = 20; +/* Checksum of an empty (zeroed) page */ +static unsigned int zero_checksum __read_mostly; + +/* Whether to merge empty (zeroed) pages with actual zero pages */ +static bool ksm_use_zero_pages __read_mostly; + #ifdef CONFIG_NUMA /* Zeroed when merging across nodes is not allowed */ static unsigned int ksm_merge_across_nodes = 1; @@ -850,33 +858,36 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, pte_t *orig_pte) { struct mm_struct *mm = vma->vm_mm; - unsigned long addr; - pte_t *ptep; - spinlock_t *ptl; + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + }; int swapped; int err = -EFAULT; unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ - addr = page_address_in_vma(page, vma); - if (addr == -EFAULT) + pvmw.address = page_address_in_vma(page, vma); + if (pvmw.address == -EFAULT) goto out; BUG_ON(PageTransCompound(page)); - mmun_start = addr; - mmun_end = addr + PAGE_SIZE; + mmun_start = pvmw.address; + mmun_end = pvmw.address + PAGE_SIZE; mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - ptep = page_check_address(page, mm, addr, &ptl, 0); - if (!ptep) + if (!page_vma_mapped_walk(&pvmw)) goto out_mn; + if (WARN_ONCE(!pvmw.pte, "Unexpected PMD mapping?")) + goto out_unlock; - if (pte_write(*ptep) || pte_dirty(*ptep)) { + if (pte_write(*pvmw.pte) || pte_dirty(*pvmw.pte) || + (pte_protnone(*pvmw.pte) && pte_savedwrite(*pvmw.pte))) { pte_t entry; swapped = PageSwapCache(page); - flush_cache_page(vma, addr, page_to_pfn(page)); + flush_cache_page(vma, pvmw.address, page_to_pfn(page)); /* * Ok this is tricky, when get_user_pages_fast() run it doesn't * take any lock, therefore the check that we are going to make @@ -886,25 +897,29 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, * this assure us that no O_DIRECT can happen after the check * or in the middle of the check. */ - entry = ptep_clear_flush_notify(vma, addr, ptep); + entry = ptep_clear_flush_notify(vma, pvmw.address, pvmw.pte); /* * Check that no O_DIRECT or similar I/O is in progress on the * page */ if (page_mapcount(page) + 1 + swapped != page_count(page)) { - set_pte_at(mm, addr, ptep, entry); + set_pte_at(mm, pvmw.address, pvmw.pte, entry); goto out_unlock; } if (pte_dirty(entry)) set_page_dirty(page); - entry = pte_mkclean(pte_wrprotect(entry)); - set_pte_at_notify(mm, addr, ptep, entry); + + if (pte_protnone(entry)) + entry = pte_mkclean(pte_clear_savedwrite(entry)); + else + entry = pte_mkclean(pte_wrprotect(entry)); + set_pte_at_notify(mm, pvmw.address, pvmw.pte, entry); } - *orig_pte = *ptep; + *orig_pte = *pvmw.pte; err = 0; out_unlock: - pte_unmap_unlock(ptep, ptl); + page_vma_mapped_walk_done(&pvmw); out_mn: mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); out: @@ -926,6 +941,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, struct mm_struct *mm = vma->vm_mm; pmd_t *pmd; pte_t *ptep; + pte_t newpte; spinlock_t *ptl; unsigned long addr; int err = -EFAULT; @@ -950,12 +966,22 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, goto out_mn; } - get_page(kpage); - page_add_anon_rmap(kpage, vma, addr, false); + /* + * No need to check ksm_use_zero_pages here: we can only have a + * zero_page here if ksm_use_zero_pages was enabled alreaady. + */ + if (!is_zero_pfn(page_to_pfn(kpage))) { + get_page(kpage); + page_add_anon_rmap(kpage, vma, addr, false); + newpte = mk_pte(kpage, vma->vm_page_prot); + } else { + newpte = pte_mkspecial(pfn_pte(page_to_pfn(kpage), + vma->vm_page_prot)); + } flush_cache_page(vma, addr, pte_pfn(*ptep)); ptep_clear_flush_notify(vma, addr, ptep); - set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot)); + set_pte_at_notify(mm, addr, ptep, newpte); page_remove_rmap(page, false); if (!page_mapped(page)) @@ -1467,6 +1493,23 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item) return; } + /* + * Same checksum as an empty page. We attempt to merge it with the + * appropriate zero page if the user enabled this via sysfs. + */ + if (ksm_use_zero_pages && (checksum == zero_checksum)) { + struct vm_area_struct *vma; + + vma = find_mergeable_vma(rmap_item->mm, rmap_item->address); + err = try_to_merge_one_page(vma, page, + ZERO_PAGE(rmap_item->address)); + /* + * In case of failure, the page was not really empty, so we + * need to continue. Otherwise we're done. + */ + if (!err) + return; + } tree_rmap_item = unstable_tree_search_insert(rmap_item, page, &tree_page); if (tree_rmap_item) { @@ -1813,7 +1856,7 @@ int __ksm_enter(struct mm_struct *mm) spin_unlock(&ksm_mmlist_lock); set_bit(MMF_VM_MERGEABLE, &mm->flags); - atomic_inc(&mm->mm_count); + mmgrab(mm); if (needs_wakeup) wake_up_interruptible(&ksm_thread_wait); @@ -1890,11 +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); @@ -1907,7 +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; @@ -1935,23 +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 @@ -2233,6 +2272,28 @@ static ssize_t merge_across_nodes_store(struct kobject *kobj, KSM_ATTR(merge_across_nodes); #endif +static ssize_t use_zero_pages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", ksm_use_zero_pages); +} +static ssize_t use_zero_pages_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + bool value; + + err = kstrtobool(buf, &value); + if (err) + return -EINVAL; + + ksm_use_zero_pages = value; + + return count; +} +KSM_ATTR(use_zero_pages); + static ssize_t pages_shared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -2290,6 +2351,7 @@ static struct attribute *ksm_attrs[] = { #ifdef CONFIG_NUMA &merge_across_nodes_attr.attr, #endif + &use_zero_pages_attr.attr, NULL, }; @@ -2304,6 +2366,11 @@ static int __init ksm_init(void) struct task_struct *ksm_thread; int err; + /* The correct value depends on page size and endianness */ + zero_checksum = calc_checksum(ZERO_PAGE(0)); + /* Default to false for backwards compatibility */ + ksm_use_zero_pages = false; + err = ksm_slab_init(); if (err) goto out; diff --git a/mm/madvise.c b/mm/madvise.c index 0e3828eae9f8..25b78ee4fc2c 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -10,6 +10,7 @@ #include <linux/syscalls.h> #include <linux/mempolicy.h> #include <linux/page-isolation.h> +#include <linux/userfaultfd_k.h> #include <linux/hugetlb.h> #include <linux/falloc.h> #include <linux/sched.h> @@ -20,10 +21,13 @@ #include <linux/backing-dev.h> #include <linux/swap.h> #include <linux/swapops.h> +#include <linux/shmem_fs.h> #include <linux/mmu_notifier.h> #include <asm/tlb.h> +#include "internal.h" + /* * Any behaviour which results in changes to the vma->vm_flags needs to * take mmap_sem for writing. Others, which simply traverse vmas, need @@ -89,14 +93,28 @@ static long madvise_behavior(struct vm_area_struct *vma, case MADV_MERGEABLE: case MADV_UNMERGEABLE: error = ksm_madvise(vma, start, end, behavior, &new_flags); - if (error) + if (error) { + /* + * madvise() returns EAGAIN if kernel resources, such as + * slab, are temporarily unavailable. + */ + if (error == -ENOMEM) + error = -EAGAIN; goto out; + } break; case MADV_HUGEPAGE: case MADV_NOHUGEPAGE: error = hugepage_madvise(vma, &new_flags, behavior); - if (error) + if (error) { + /* + * madvise() returns EAGAIN if kernel resources, such as + * slab, are temporarily unavailable. + */ + if (error == -ENOMEM) + error = -EAGAIN; goto out; + } break; } @@ -117,15 +135,37 @@ static long madvise_behavior(struct vm_area_struct *vma, *prev = vma; if (start != vma->vm_start) { - error = split_vma(mm, vma, start, 1); - if (error) + if (unlikely(mm->map_count >= sysctl_max_map_count)) { + error = -ENOMEM; + goto out; + } + error = __split_vma(mm, vma, start, 1); + if (error) { + /* + * madvise() returns EAGAIN if kernel resources, such as + * slab, are temporarily unavailable. + */ + if (error == -ENOMEM) + error = -EAGAIN; goto out; + } } if (end != vma->vm_end) { - error = split_vma(mm, vma, end, 0); - if (error) + if (unlikely(mm->map_count >= sysctl_max_map_count)) { + error = -ENOMEM; goto out; + } + error = __split_vma(mm, vma, end, 0); + if (error) { + /* + * madvise() returns EAGAIN if kernel resources, such as + * slab, are temporarily unavailable. + */ + if (error == -ENOMEM) + error = -EAGAIN; + goto out; + } } success: @@ -133,10 +173,7 @@ success: * vm_flags is protected by the mmap_sem held in write mode. */ vma->vm_flags = new_flags; - out: - if (error == -ENOMEM) - error = -EAGAIN; return error; } @@ -374,10 +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) { @@ -473,10 +509,47 @@ static long madvise_dontneed(struct vm_area_struct *vma, unsigned long start, unsigned long end) { *prev = vma; - if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)) + if (!can_madv_dontneed_vma(vma)) return -EINVAL; - zap_page_range(vma, start, end - start, NULL); + if (!userfaultfd_remove(vma, start, end)) { + *prev = NULL; /* mmap_sem has been dropped, prev is stale */ + + down_read(¤t->mm->mmap_sem); + vma = find_vma(current->mm, start); + if (!vma) + return -ENOMEM; + if (start < vma->vm_start) { + /* + * This "vma" under revalidation is the one + * with the lowest vma->vm_start where start + * is also < vma->vm_end. If start < + * vma->vm_start it means an hole materialized + * in the user address space within the + * virtual range passed to MADV_DONTNEED. + */ + return -ENOMEM; + } + if (!can_madv_dontneed_vma(vma)) + return -EINVAL; + if (end > vma->vm_end) { + /* + * Don't fail if end > vma->vm_end. If the old + * vma was splitted while the mmap_sem was + * released the effect of the concurrent + * operation may not cause MADV_DONTNEED to + * have an undefined result. There may be an + * adjacent next vma that we'll walk + * next. userfaultfd_remove() will generate an + * UFFD_EVENT_REMOVE repetition on the + * end-vma->vm_end range, but the manager can + * handle a repetition fine. + */ + end = vma->vm_end; + } + VM_WARN_ON(start >= end); + } + zap_page_range(vma, start, end - start); return 0; } @@ -516,7 +589,10 @@ static long madvise_remove(struct vm_area_struct *vma, * mmap_sem. */ get_file(f); - up_read(¤t->mm->mmap_sem); + if (userfaultfd_remove(vma, start, end)) { + /* mmap_sem was not released by userfaultfd_remove() */ + up_read(¤t->mm->mmap_sem); + } error = vfs_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); @@ -529,34 +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; } @@ -574,13 +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: @@ -611,6 +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: @@ -684,10 +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; @@ -707,6 +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/memblock.c b/mm/memblock.c index 7608bc305936..696f06d17c4e 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -35,15 +35,18 @@ struct memblock memblock __initdata_memblock = { .memory.regions = memblock_memory_init_regions, .memory.cnt = 1, /* empty dummy entry */ .memory.max = INIT_MEMBLOCK_REGIONS, + .memory.name = "memory", .reserved.regions = memblock_reserved_init_regions, .reserved.cnt = 1, /* empty dummy entry */ .reserved.max = INIT_MEMBLOCK_REGIONS, + .reserved.name = "reserved", #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP .physmem.regions = memblock_physmem_init_regions, .physmem.cnt = 1, /* empty dummy entry */ .physmem.max = INIT_PHYSMEM_REGIONS, + .physmem.name = "physmem", #endif .bottom_up = false, @@ -64,18 +67,6 @@ ulong __init_memblock choose_memblock_flags(void) return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE; } -/* inline so we don't get a warning when pr_debug is compiled out */ -static __init_memblock const char * -memblock_type_name(struct memblock_type *type) -{ - if (type == &memblock.memory) - return "memory"; - else if (type == &memblock.reserved) - return "reserved"; - else - return "unknown"; -} - /* adjust *@size so that (@base + *@size) doesn't overflow, return new size */ static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size) { @@ -402,12 +393,12 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, } if (!addr) { pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n", - memblock_type_name(type), type->max, type->max * 2); + type->name, type->max, type->max * 2); return -1; } memblock_dbg("memblock: %s is doubled to %ld at [%#010llx-%#010llx]", - memblock_type_name(type), type->max * 2, (u64)addr, + type->name, type->max * 2, (u64)addr, (u64)addr + new_size - 1); /* @@ -611,10 +602,10 @@ int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) { - memblock_dbg("memblock_add: [%#016llx-%#016llx] flags %#02lx %pF\n", - (unsigned long long)base, - (unsigned long long)base + size - 1, - 0UL, (void *)_RET_IP_); + phys_addr_t end = base + size - 1; + + memblock_dbg("memblock_add: [%pa-%pa] %pF\n", + &base, &end, (void *)_RET_IP_); return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0); } @@ -718,10 +709,10 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) { - memblock_dbg(" memblock_free: [%#016llx-%#016llx] %pF\n", - (unsigned long long)base, - (unsigned long long)base + size - 1, - (void *)_RET_IP_); + phys_addr_t end = base + size - 1; + + memblock_dbg(" memblock_free: [%pa-%pa] %pF\n", + &base, &end, (void *)_RET_IP_); kmemleak_free_part_phys(base, size); return memblock_remove_range(&memblock.reserved, base, size); @@ -729,10 +720,10 @@ int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) { - memblock_dbg("memblock_reserve: [%#016llx-%#016llx] flags %#02lx %pF\n", - (unsigned long long)base, - (unsigned long long)base + size - 1, - 0UL, (void *)_RET_IP_); + phys_addr_t end = base + size - 1; + + memblock_dbg("memblock_reserve: [%pa-%pa] %pF\n", + &base, &end, (void *)_RET_IP_); return memblock_add_range(&memblock.reserved, base, size, MAX_NUMNODES, 0); } @@ -1105,6 +1096,34 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid, *out_nid = r->nid; } +unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn, + unsigned long max_pfn) +{ + struct memblock_type *type = &memblock.memory; + unsigned int right = type->cnt; + unsigned int mid, left = 0; + phys_addr_t addr = PFN_PHYS(pfn + 1); + + do { + mid = (right + left) / 2; + + if (addr < type->regions[mid].base) + right = mid; + else if (addr >= (type->regions[mid].base + + type->regions[mid].size)) + left = mid + 1; + else { + /* addr is within the region, so pfn + 1 is valid */ + return min(pfn + 1, max_pfn); + } + } while (left < right); + + if (right == type->cnt) + return max_pfn; + else + return min(PHYS_PFN(type->regions[right].base), max_pfn); +} + /** * memblock_set_node - set node ID on memblock regions * @base: base of area to set node ID for @@ -1202,8 +1221,8 @@ phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys alloc = __memblock_alloc_base(size, align, max_addr); if (alloc == 0) - panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n", - (unsigned long long) size, (unsigned long long) max_addr); + panic("ERROR: Failed to allocate %pa bytes below %pa.\n", + &size, &max_addr); return alloc; } @@ -1274,18 +1293,17 @@ static void * __init memblock_virt_alloc_internal( if (max_addr > memblock.current_limit) max_addr = memblock.current_limit; - again: alloc = memblock_find_in_range_node(size, align, min_addr, max_addr, nid, flags); - if (alloc) + if (alloc && !memblock_reserve(alloc, size)) goto done; if (nid != NUMA_NO_NODE) { alloc = memblock_find_in_range_node(size, align, min_addr, max_addr, NUMA_NO_NODE, flags); - if (alloc) + if (alloc && !memblock_reserve(alloc, size)) goto done; } @@ -1303,7 +1321,6 @@ again: return NULL; done: - memblock_reserve(alloc, size); ptr = phys_to_virt(alloc); memset(ptr, 0, size); @@ -1615,8 +1632,7 @@ int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size if (idx == -1) return 0; - return memblock.memory.regions[idx].base <= base && - (memblock.memory.regions[idx].base + + return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size) >= end; } @@ -1671,40 +1687,44 @@ phys_addr_t __init_memblock memblock_get_current_limit(void) return memblock.current_limit; } -static void __init_memblock memblock_dump(struct memblock_type *type, char *name) +static void __init_memblock memblock_dump(struct memblock_type *type) { - unsigned long long base, size; + phys_addr_t base, end, size; unsigned long flags; int idx; struct memblock_region *rgn; - pr_info(" %s.cnt = 0x%lx\n", name, type->cnt); + pr_info(" %s.cnt = 0x%lx\n", type->name, type->cnt); for_each_memblock_type(type, rgn) { char nid_buf[32] = ""; base = rgn->base; size = rgn->size; + end = base + size - 1; flags = rgn->flags; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP if (memblock_get_region_node(rgn) != MAX_NUMNODES) snprintf(nid_buf, sizeof(nid_buf), " on node %d", memblock_get_region_node(rgn)); #endif - pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s flags: %#lx\n", - name, idx, base, base + size - 1, size, nid_buf, flags); + pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#lx\n", + type->name, idx, &base, &end, &size, nid_buf, flags); } } void __init_memblock __memblock_dump_all(void) { pr_info("MEMBLOCK configuration:\n"); - pr_info(" memory size = %#llx reserved size = %#llx\n", - (unsigned long long)memblock.memory.total_size, - (unsigned long long)memblock.reserved.total_size); + pr_info(" memory size = %pa reserved size = %pa\n", + &memblock.memory.total_size, + &memblock.reserved.total_size); - memblock_dump(&memblock.memory, "memory"); - memblock_dump(&memblock.reserved, "reserved"); + memblock_dump(&memblock.memory); + memblock_dump(&memblock.reserved); +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP + memblock_dump(&memblock.physmem); +#endif } void __init memblock_allow_resize(void) @@ -1727,19 +1747,14 @@ static int memblock_debug_show(struct seq_file *m, void *private) struct memblock_type *type = m->private; struct memblock_region *reg; int i; + phys_addr_t end; for (i = 0; i < type->cnt; i++) { reg = &type->regions[i]; - seq_printf(m, "%4d: ", i); - if (sizeof(phys_addr_t) == 4) - seq_printf(m, "0x%08lx..0x%08lx\n", - (unsigned long)reg->base, - (unsigned long)(reg->base + reg->size - 1)); - else - seq_printf(m, "0x%016llx..0x%016llx\n", - (unsigned long long)reg->base, - (unsigned long long)(reg->base + reg->size - 1)); + end = reg->base + reg->size - 1; + seq_printf(m, "%4d: ", i); + seq_printf(m, "%pa..%pa\n", ®->base, &end); } return 0; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b822e158b319..ff73899af61a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -35,6 +35,8 @@ #include <linux/memcontrol.h> #include <linux/cgroup.h> #include <linux/mm.h> +#include <linux/sched/mm.h> +#include <linux/shmem_fs.h> #include <linux/hugetlb.h> #include <linux/pagemap.h> #include <linux/smp.h> @@ -98,24 +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", @@ -317,6 +302,8 @@ void memcg_put_cache_ids(void) DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key); EXPORT_SYMBOL(memcg_kmem_enabled_key); +struct workqueue_struct *memcg_kmem_cache_wq; + #endif /* !CONFIG_SLOB */ /** @@ -462,6 +449,8 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) struct mem_cgroup_tree_per_node *mctz; mctz = soft_limit_tree_from_page(page); + if (!mctz) + return; /* * Necessary to update all ancestors when hierarchy is used. * because their event counter is not touched. @@ -499,7 +488,8 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) for_each_node(nid) { mz = mem_cgroup_nodeinfo(memcg, nid); mctz = soft_limit_tree_node(nid); - mem_cgroup_remove_exceeded(mz, mctz); + if (mctz) + mem_cgroup_remove_exceeded(mz, mctz); } } @@ -561,32 +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; } @@ -599,23 +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 */ } @@ -1137,6 +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. @@ -1181,11 +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++) @@ -1830,7 +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))); } @@ -1921,7 +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); @@ -1964,7 +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)); @@ -2143,8 +2138,6 @@ struct memcg_kmem_cache_create_work { struct work_struct work; }; -static struct workqueue_struct *memcg_kmem_cache_create_wq; - static void memcg_kmem_cache_create_func(struct work_struct *w) { struct memcg_kmem_cache_create_work *cw = @@ -2176,7 +2169,7 @@ static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, cw->cachep = cachep; INIT_WORK(&cw->work, memcg_kmem_cache_create_func); - queue_work(memcg_kmem_cache_create_wq, &cw->work); + queue_work(memcg_kmem_cache_wq, &cw->work); } static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, @@ -2376,7 +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 */ @@ -2386,7 +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); } /** @@ -2556,7 +2549,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, * is empty. Do it lockless to prevent lock bouncing. Races * are acceptable as soft limit is best effort anyway. */ - if (RB_EMPTY_ROOT(&mctz->rb_root)) + if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root)) return 0; /* @@ -2720,7 +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); } } @@ -2733,7 +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); } } @@ -2745,13 +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) @@ -2837,6 +2827,7 @@ static int memcg_online_kmem(struct mem_cgroup *memcg) */ memcg->kmemcg_id = memcg_id; memcg->kmem_state = KMEM_ONLINE; + INIT_LIST_HEAD(&memcg->kmem_caches); return 0; } @@ -3125,6 +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)); @@ -3132,22 +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], @@ -3165,23 +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++) { @@ -3646,10 +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; @@ -4002,9 +4006,9 @@ static struct cftype mem_cgroup_legacy_files[] = { #ifdef CONFIG_SLABINFO { .name = "kmem.slabinfo", - .seq_start = slab_start, - .seq_next = slab_next, - .seq_stop = slab_stop, + .seq_start = memcg_slab_start, + .seq_next = memcg_slab_next, + .seq_stop = memcg_slab_stop, .seq_show = memcg_slab_show, }, #endif @@ -4132,17 +4136,22 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) kfree(memcg->nodeinfo[node]); } -static void mem_cgroup_free(struct mem_cgroup *memcg) +static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; - memcg_wb_domain_exit(memcg); for_each_node(node) free_mem_cgroup_per_node_info(memcg, node); free_percpu(memcg->stat); kfree(memcg); } +static void mem_cgroup_free(struct mem_cgroup *memcg) +{ + memcg_wb_domain_exit(memcg); + __mem_cgroup_free(memcg); +} + static struct mem_cgroup *mem_cgroup_alloc(void) { struct mem_cgroup *memcg; @@ -4193,7 +4202,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) fail: if (memcg->id.id > 0) idr_remove(&mem_cgroup_idr, memcg->id.id); - mem_cgroup_free(memcg); + __mem_cgroup_free(memcg); return NULL; } @@ -4500,33 +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); } /* @@ -5143,7 +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; } @@ -5156,10 +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; } @@ -5186,9 +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", @@ -5197,12 +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; @@ -5221,10 +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; } @@ -5465,8 +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; @@ -5481,10 +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); @@ -5496,6 +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; @@ -5528,9 +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; } @@ -5544,8 +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); @@ -5557,7 +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); } /** @@ -5777,12 +5794,12 @@ static int __init mem_cgroup_init(void) #ifndef CONFIG_SLOB /* * Kmem cache creation is mostly done with the slab_mutex held, - * so use a special workqueue to avoid stalling all worker - * threads in case lots of cgroups are created simultaneously. + * so use a workqueue with limited concurrency to avoid stalling + * all worker threads in case lots of cgroups are created and + * destroyed simultaneously. */ - memcg_kmem_cache_create_wq = - alloc_ordered_workqueue("memcg_kmem_cache_create", 0); - BUG_ON(!memcg_kmem_cache_create_wq); + memcg_kmem_cache_wq = alloc_workqueue("memcg_kmem_cache", 0, 1); + BUG_ON(!memcg_kmem_cache_wq); #endif cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL, diff --git a/mm/memory-failure.c b/mm/memory-failure.c index f283c7e0a2a3..73066b80d14a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -40,7 +40,8 @@ #include <linux/mm.h> #include <linux/page-flags.h> #include <linux/kernel-page-flags.h> -#include <linux/sched.h> +#include <linux/sched/signal.h> +#include <linux/sched/task.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/export.h> @@ -219,6 +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)) @@ -321,7 +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; @@ -903,35 +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)) { @@ -970,12 +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 @@ -986,10 +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) @@ -1137,22 +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); @@ -1229,8 +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; @@ -1527,7 +1529,8 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags) { int ret = __get_any_page(page, pfn, flags); - if (ret == 1 && !PageHuge(page) && !PageLRU(page)) { + if (ret == 1 && !PageHuge(page) && + !PageLRU(page) && !__PageMovable(page)) { /* * Try to free it. */ @@ -1541,8 +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; } } @@ -1583,8 +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 @@ -1649,7 +1652,10 @@ static int __soft_offline_page(struct page *page, int flags) * Try to migrate to a new page instead. migrate.c * handles a large number of cases for us. */ - ret = isolate_lru_page(page); + if (PageLRU(page)) + ret = isolate_lru_page(page); + else + ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE); /* * Drop page reference which is came from get_any_page() * successful isolate_lru_page() already took another one. @@ -1657,27 +1663,29 @@ static int __soft_offline_page(struct page *page, int flags) put_hwpoison_page(page); if (!ret) { LIST_HEAD(pagelist); - inc_node_page_state(page, NR_ISOLATED_ANON + - page_is_file_cache(page)); + /* + * After isolated lru page, the PageLRU will be cleared, + * so use !__PageMovable instead for LRU page's mapping + * cannot have PAGE_MAPPING_MOVABLE. + */ + if (!__PageMovable(page)) + inc_node_page_state(page, NR_ISOLATED_ANON + + page_is_file_cache(page)); list_add(&page->lru, &pagelist); ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { - if (!list_empty(&pagelist)) { - list_del(&page->lru); - dec_node_page_state(page, NR_ISOLATED_ANON + - page_is_file_cache(page)); - putback_lru_page(page); - } + 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 6bf2b471e30c..6ff5d729ded0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -30,7 +30,7 @@ /* * 05.04.94 - Multi-page memory management added for v1.1. - * Idea by Alex Bligh (alex@cconcepts.co.uk) + * Idea by Alex Bligh (alex@cconcepts.co.uk) * * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG * (Gerhard.Wichert@pdb.siemens.de) @@ -40,6 +40,10 @@ #include <linux/kernel_stat.h> #include <linux/mm.h> +#include <linux/sched/mm.h> +#include <linux/sched/coredump.h> +#include <linux/sched/numa_balancing.h> +#include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/swap.h> @@ -82,9 +86,9 @@ #ifndef CONFIG_NEED_MULTIPLE_NODES /* use the per-pgdat data instead for discontigmem - mbligh */ unsigned long max_mapnr; -struct page *mem_map; - EXPORT_SYMBOL(max_mapnr); + +struct page *mem_map; EXPORT_SYMBOL(mem_map); #endif @@ -95,8 +99,7 @@ EXPORT_SYMBOL(mem_map); * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL * and ZONE_HIGHMEM. */ -void * high_memory; - +void *high_memory; EXPORT_SYMBOL(high_memory); /* @@ -120,10 +123,10 @@ static int __init disable_randmaps(char *s) __setup("norandmaps", disable_randmaps); unsigned long zero_pfn __read_mostly; -unsigned long highest_memmap_pfn __read_mostly; - EXPORT_SYMBOL(zero_pfn); +unsigned long highest_memmap_pfn __read_mostly; + /* * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init() */ @@ -442,7 +445,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, mm_dec_nr_pmds(tlb->mm); } -static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, +static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { @@ -451,7 +454,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, unsigned long start; start = addr; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) @@ -459,6 +462,39 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, free_pmd_range(tlb, pud, addr, next, floor, ceiling); } while (pud++, addr = next, addr != end); + start &= P4D_MASK; + if (start < floor) + return; + if (ceiling) { + ceiling &= P4D_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + return; + + pud = pud_offset(p4d, start); + p4d_clear(p4d); + pud_free_tlb(tlb, pud, start); +} + +static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + p4d_t *p4d; + unsigned long next; + unsigned long start; + + start = addr; + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + free_pud_range(tlb, p4d, addr, next, floor, ceiling); + } while (p4d++, addr = next, addr != end); + start &= PGDIR_MASK; if (start < floor) return; @@ -470,9 +506,9 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, if (end - 1 > ceiling - 1) return; - pud = pud_offset(pgd, start); + p4d = p4d_offset(pgd, start); pgd_clear(pgd); - pud_free_tlb(tlb, pud, start); + p4d_free_tlb(tlb, p4d, start); } /* @@ -536,7 +572,7 @@ void free_pgd_range(struct mmu_gather *tlb, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - free_pud_range(tlb, pgd, addr, next, floor, ceiling); + free_p4d_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } @@ -556,7 +592,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, if (is_vm_hugetlb_page(vma)) { hugetlb_free_pgd_range(tlb, addr, vma->vm_end, - floor, next? next->vm_start: ceiling); + floor, next ? next->vm_start : ceiling); } else { /* * Optimization: gather nearby vmas into one call down @@ -569,7 +605,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, unlink_file_vma(vma); } free_pgd_range(tlb, addr, vma->vm_end, - floor, next? next->vm_start: ceiling); + floor, next ? next->vm_start : ceiling); } vma = next; } @@ -655,7 +691,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, pte_t pte, struct page *page) { pgd_t *pgd = pgd_offset(vma->vm_mm, addr); - pud_t *pud = pud_offset(pgd, addr); + p4d_t *p4d = p4d_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); pmd_t *pmd = pmd_offset(pud, addr); struct address_space *mapping; pgoff_t index; @@ -1001,7 +1038,7 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src next = pmd_addr_end(addr, end); if (pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) { int err; - VM_BUG_ON(next-addr != HPAGE_PMD_SIZE); + VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, vma); err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd, addr, vma); if (err == -ENOMEM) @@ -1020,18 +1057,30 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src } static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, + p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { pud_t *src_pud, *dst_pud; unsigned long next; - dst_pud = pud_alloc(dst_mm, dst_pgd, addr); + dst_pud = pud_alloc(dst_mm, dst_p4d, addr); if (!dst_pud) return -ENOMEM; - src_pud = pud_offset(src_pgd, addr); + src_pud = pud_offset(src_p4d, addr); do { next = pud_addr_end(addr, end); + if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { + int err; + + VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, vma); + err = copy_huge_pud(dst_mm, src_mm, + dst_pud, src_pud, addr, vma); + if (err == -ENOMEM) + return -ENOMEM; + if (!err) + continue; + /* fall through */ + } if (pud_none_or_clear_bad(src_pud)) continue; if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud, @@ -1041,6 +1090,28 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src return 0; } +static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + p4d_t *src_p4d, *dst_p4d; + unsigned long next; + + dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr); + if (!dst_p4d) + return -ENOMEM; + src_p4d = p4d_offset(src_pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(src_p4d)) + continue; + if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d, + vma, addr, next)) + return -ENOMEM; + } while (dst_p4d++, src_p4d++, addr = next, addr != end); + return 0; +} + int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, struct vm_area_struct *vma) { @@ -1096,7 +1167,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; - if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, + if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd, vma, addr, next))) { ret = -ENOMEM; break; @@ -1129,9 +1200,8 @@ again: arch_enter_lazy_mmu_mode(); do { pte_t ptent = *pte; - if (pte_none(ptent)) { + if (pte_none(ptent)) continue; - } if (pte_present(ptent)) { struct page *page; @@ -1155,12 +1225,6 @@ again: if (!PageAnon(page)) { if (pte_dirty(ptent)) { - /* - * oom_reaper cannot tear down dirty - * pages - */ - if (unlikely(details && details->ignore_dirty)) - continue; force_flush = 1; set_page_dirty(page); } @@ -1179,8 +1243,8 @@ again: } continue; } - /* only check swap_entries if explicitly asked for in details */ - if (unlikely(details && !details->check_swap_entries)) + /* If details->check_mapping, we leave swap entries. */ + if (unlikely(details)) continue; entry = pte_to_swp_entry(ptent); @@ -1259,24 +1323,53 @@ next: } static inline unsigned long zap_pud_range(struct mmu_gather *tlb, - struct vm_area_struct *vma, pgd_t *pgd, + struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, struct zap_details *details) { pud_t *pud; unsigned long next; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); + if (pud_trans_huge(*pud) || pud_devmap(*pud)) { + if (next - addr != HPAGE_PUD_SIZE) { + VM_BUG_ON_VMA(!rwsem_is_locked(&tlb->mm->mmap_sem), vma); + split_huge_pud(vma, pud, addr); + } else if (zap_huge_pud(tlb, vma, pud, addr)) + goto next; + /* fall through */ + } if (pud_none_or_clear_bad(pud)) continue; next = zap_pmd_range(tlb, vma, pud, addr, next, details); +next: + cond_resched(); } while (pud++, addr = next, addr != end); return addr; } +static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pgd_t *pgd, + unsigned long addr, unsigned long end, + struct zap_details *details) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + next = zap_pud_range(tlb, vma, p4d, addr, next, details); + } while (p4d++, addr = next, addr != end); + + return addr; +} + void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, @@ -1292,7 +1385,7 @@ void unmap_page_range(struct mmu_gather *tlb, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - next = zap_pud_range(tlb, vma, pgd, addr, next, details); + next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); } @@ -1376,12 +1469,11 @@ void unmap_vmas(struct mmu_gather *tlb, * @vma: vm_area_struct holding the applicable pages * @start: starting address of pages to zap * @size: number of bytes to zap - * @details: details of shared cache invalidation * * Caller must protect the VMA list */ void zap_page_range(struct vm_area_struct *vma, unsigned long start, - unsigned long size, struct zap_details *details) + unsigned long size) { struct mm_struct *mm = vma->vm_mm; struct mmu_gather tlb; @@ -1392,7 +1484,7 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start, update_hiwater_rss(mm); mmu_notifier_invalidate_range_start(mm, start, end); for ( ; vma && vma->vm_start < end; vma = vma->vm_next) - unmap_single_vma(&tlb, vma, start, end, details); + unmap_single_vma(&tlb, vma, start, end, NULL); mmu_notifier_invalidate_range_end(mm, start, end); tlb_finish_mmu(&tlb, start, end); } @@ -1448,16 +1540,24 @@ EXPORT_SYMBOL_GPL(zap_vma_ptes); pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { - pgd_t * pgd = pgd_offset(mm, addr); - pud_t * pud = pud_alloc(mm, pgd, addr); - if (pud) { - pmd_t * pmd = pmd_alloc(mm, pud, addr); - if (pmd) { - VM_BUG_ON(pmd_trans_huge(*pmd)); - return pte_alloc_map_lock(mm, pmd, addr, ptl); - } - } - return NULL; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset(mm, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, addr); + if (!pud) + return NULL; + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return NULL; + + VM_BUG_ON(pmd_trans_huge(*pmd)); + return pte_alloc_map_lock(mm, pmd, addr, ptl); } /* @@ -1723,7 +1823,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, return 0; } -static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, +static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { @@ -1731,7 +1831,7 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, unsigned long next; pfn -= addr >> PAGE_SHIFT; - pud = pud_alloc(mm, pgd, addr); + pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { @@ -1743,6 +1843,26 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, return 0; } +static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) +{ + p4d_t *p4d; + unsigned long next; + + pfn -= addr >> PAGE_SHIFT; + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + if (remap_pud_range(mm, p4d, addr, next, + pfn + (addr >> PAGE_SHIFT), prot)) + return -ENOMEM; + } while (p4d++, addr = next, addr != end); + return 0; +} + /** * remap_pfn_range - remap kernel memory to userspace * @vma: user vma to map to @@ -1799,7 +1919,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); - err = remap_pud_range(mm, pgd, addr, next, + err = remap_p4d_range(mm, pgd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) break; @@ -1915,7 +2035,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, return err; } -static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, +static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, pte_fn_t fn, void *data) { @@ -1923,7 +2043,7 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, unsigned long next; int err; - pud = pud_alloc(mm, pgd, addr); + pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { @@ -1935,6 +2055,26 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, return err; } +static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data) +{ + p4d_t *p4d; + unsigned long next; + int err; + + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + err = apply_to_pud_range(mm, p4d, addr, next, fn, data); + if (err) + break; + } while (p4d++, addr = next, addr != end); + return err; +} + /* * Scan a region of virtual memory, filling in page tables as necessary * and calling a provided function on each leaf page table. @@ -1953,7 +2093,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); - err = apply_to_pud_range(mm, pgd, addr, next, fn, data); + err = apply_to_p4d_range(mm, pgd, addr, next, fn, data); if (err) break; } while (pgd++, addr = next, addr != end); @@ -2042,7 +2182,7 @@ static int do_page_mkwrite(struct vm_fault *vmf) vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; - ret = vmf->vma->vm_ops->page_mkwrite(vmf->vma, vmf); + ret = vmf->vma->vm_ops->page_mkwrite(vmf); /* Restore original flags so that caller is not surprised */ vmf->flags = old_flags; if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) @@ -2314,7 +2454,7 @@ static int wp_pfn_shared(struct vm_fault *vmf) pte_unmap_unlock(vmf->pte, vmf->ptl); vmf->flags |= FAULT_FLAG_MKWRITE; - ret = vma->vm_ops->pfn_mkwrite(vma, vmf); + ret = vma->vm_ops->pfn_mkwrite(vmf); if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)) return ret; return finish_mkwrite_fault(vmf); @@ -2510,7 +2650,7 @@ void unmap_mapping_range(struct address_space *mapping, hlen = ULONG_MAX - hba + 1; } - details.check_mapping = even_cows? NULL: mapping; + details.check_mapping = even_cows ? NULL : mapping; details.first_index = hba; details.last_index = hba + hlen - 1; if (details.last_index < details.first_index) @@ -2868,7 +3008,7 @@ static int __do_fault(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; int ret; - ret = vma->vm_ops->fault(vma, vmf); + ret = vma->vm_ops->fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY | VM_FAULT_DONE_COW))) return ret; @@ -2905,7 +3045,7 @@ static int pte_alloc_one_map(struct vm_fault *vmf) atomic_long_inc(&vma->vm_mm->nr_ptes); pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); spin_unlock(vmf->ptl); - vmf->prealloc_pte = 0; + vmf->prealloc_pte = NULL; } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd, vmf->address))) { return VM_FAULT_OOM; } @@ -2953,7 +3093,7 @@ static void deposit_prealloc_pte(struct vm_fault *vmf) * count that as nr_ptes. */ atomic_long_inc(&vma->vm_mm->nr_ptes); - vmf->prealloc_pte = 0; + vmf->prealloc_pte = NULL; } static int do_set_pmd(struct vm_fault *vmf, struct page *page) @@ -3359,7 +3499,7 @@ static int do_fault(struct vm_fault *vmf) /* preallocated pagetable is unused: free it */ if (vmf->prealloc_pte) { pte_free(vma->vm_mm, vmf->prealloc_pte); - vmf->prealloc_pte = 0; + vmf->prealloc_pte = NULL; } return ret; } @@ -3387,32 +3527,32 @@ static int do_numa_page(struct vm_fault *vmf) int last_cpupid; int target_nid; bool migrated = false; - pte_t pte = vmf->orig_pte; - bool was_writable = pte_write(pte); + pte_t pte; + bool was_writable = pte_savedwrite(vmf->orig_pte); int flags = 0; /* - * The "pte" at this point cannot be used safely without - * validation through pte_unmap_same(). It's of NUMA type but - * the pfn may be screwed if the read is non atomic. - * - * We can safely just do a "set_pte_at()", because the old - * page table entry is not accessible, so there would be no - * concurrent hardware modifications to the PTE. - */ + * The "pte" at this point cannot be used safely without + * validation through pte_unmap_same(). It's of NUMA type but + * the pfn may be screwed if the read is non atomic. + */ vmf->ptl = pte_lockptr(vma->vm_mm, vmf->pmd); spin_lock(vmf->ptl); - if (unlikely(!pte_same(*vmf->pte, pte))) { + if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); goto out; } - /* Make it present again */ + /* + * Make it present again, Depending on how arch implementes non + * accessible ptes, some can allow access by kernel mode. + */ + pte = ptep_modify_prot_start(vma->vm_mm, vmf->address, vmf->pte); pte = pte_modify(pte, vma->vm_page_prot); pte = pte_mkyoung(pte); if (was_writable) pte = pte_mkwrite(pte); - set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); + ptep_modify_prot_commit(vma->vm_mm, vmf->address, vmf->pte, pte); update_mmu_cache(vma, vmf->address, vmf->pte); page = vm_normal_page(vma, vmf->address, pte); @@ -3471,12 +3611,10 @@ out: static int create_huge_pmd(struct vm_fault *vmf) { - struct vm_area_struct *vma = vmf->vma; - if (vma_is_anonymous(vma)) + if (vma_is_anonymous(vmf->vma)) return do_huge_pmd_anonymous_page(vmf); - if (vma->vm_ops->pmd_fault) - return vma->vm_ops->pmd_fault(vma, vmf->address, vmf->pmd, - vmf->flags); + if (vmf->vma->vm_ops->huge_fault) + return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); return VM_FAULT_FALLBACK; } @@ -3484,9 +3622,8 @@ static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd) { if (vma_is_anonymous(vmf->vma)) return do_huge_pmd_wp_page(vmf, orig_pmd); - if (vmf->vma->vm_ops->pmd_fault) - return vmf->vma->vm_ops->pmd_fault(vmf->vma, vmf->address, - vmf->pmd, vmf->flags); + if (vmf->vma->vm_ops->huge_fault) + return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); /* COW handled on pte level: split pmd */ VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma); @@ -3500,6 +3637,30 @@ static inline bool vma_is_accessible(struct vm_area_struct *vma) return vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE); } +static int create_huge_pud(struct vm_fault *vmf) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + /* No support for anonymous transparent PUD pages yet */ + if (vma_is_anonymous(vmf->vma)) + return VM_FAULT_FALLBACK; + if (vmf->vma->vm_ops->huge_fault) + return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + return VM_FAULT_FALLBACK; +} + +static int wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + /* No support for anonymous transparent PUD pages yet */ + if (vma_is_anonymous(vmf->vma)) + return VM_FAULT_FALLBACK; + if (vmf->vma->vm_ops->huge_fault) + return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + return VM_FAULT_FALLBACK; +} + /* * These routines also need to handle stuff like marking pages dirty * and/or accessed for architectures that don't do it in hardware (most @@ -3615,22 +3776,50 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, }; struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; - pud_t *pud; + p4d_t *p4d; + int ret; pgd = pgd_offset(mm, address); - pud = pud_alloc(mm, pgd, address); - if (!pud) + p4d = p4d_alloc(mm, pgd, address); + if (!p4d) + return VM_FAULT_OOM; + + vmf.pud = pud_alloc(mm, p4d, address); + if (!vmf.pud) return VM_FAULT_OOM; - vmf.pmd = pmd_alloc(mm, pud, address); + if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) { + ret = create_huge_pud(&vmf); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } else { + pud_t orig_pud = *vmf.pud; + + barrier(); + if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) { + unsigned int dirty = flags & FAULT_FLAG_WRITE; + + /* NUMA case for anonymous PUDs would go here */ + + if (dirty && !pud_write(orig_pud)) { + ret = wp_huge_pud(&vmf, orig_pud); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } else { + huge_pud_set_accessed(&vmf, orig_pud); + return 0; + } + } + } + + vmf.pmd = pmd_alloc(mm, vmf.pud, address); if (!vmf.pmd) return VM_FAULT_OOM; if (pmd_none(*vmf.pmd) && transparent_hugepage_enabled(vma)) { - int ret = create_huge_pmd(&vmf); + ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { pmd_t orig_pmd = *vmf.pmd; - int ret; barrier(); if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) { @@ -3690,14 +3879,14 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address, if (flags & FAULT_FLAG_USER) { mem_cgroup_oom_disable(); - /* - * The task may have entered a memcg OOM situation but - * if the allocation error was handled gracefully (no - * VM_FAULT_OOM), there is no need to kill anything. - * Just clean up the OOM state peacefully. - */ - if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) - mem_cgroup_oom_synchronize(false); + /* + * The task may have entered a memcg OOM situation but + * if the allocation error was handled gracefully (no + * VM_FAULT_OOM), there is no need to kill anything. + * Just clean up the OOM state peacefully. + */ + if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) + mem_cgroup_oom_synchronize(false); } /* @@ -3717,12 +3906,35 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address, } EXPORT_SYMBOL_GPL(handle_mm_fault); +#ifndef __PAGETABLE_P4D_FOLDED +/* + * Allocate p4d page table. + * We've already handled the fast-path in-line. + */ +int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +{ + p4d_t *new = p4d_alloc_one(mm, address); + if (!new) + return -ENOMEM; + + smp_wmb(); /* See comment in __pte_alloc */ + + spin_lock(&mm->page_table_lock); + if (pgd_present(*pgd)) /* Another has populated it */ + p4d_free(mm, new); + else + pgd_populate(mm, pgd, new); + spin_unlock(&mm->page_table_lock); + return 0; +} +#endif /* __PAGETABLE_P4D_FOLDED */ + #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. * We've already handled the fast-path in-line. */ -int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { pud_t *new = pud_alloc_one(mm, address); if (!new) @@ -3731,10 +3943,17 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&mm->page_table_lock); - if (pgd_present(*pgd)) /* Another has populated it */ +#ifndef __ARCH_HAS_5LEVEL_HACK + if (p4d_present(*p4d)) /* Another has populated it */ pud_free(mm, new); else - pgd_populate(mm, pgd, new); + p4d_populate(mm, p4d, new); +#else + if (pgd_present(*p4d)) /* Another has populated it */ + pud_free(mm, new); + else + pgd_populate(mm, p4d, new); +#endif /* __ARCH_HAS_5LEVEL_HACK */ spin_unlock(&mm->page_table_lock); return 0; } @@ -3747,13 +3966,14 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) */ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { + spinlock_t *ptl; pmd_t *new = pmd_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ - spin_lock(&mm->page_table_lock); + ptl = pud_lock(mm, pud); #ifndef __ARCH_HAS_4LEVEL_HACK if (!pud_present(*pud)) { mm_inc_nr_pmds(mm); @@ -3767,7 +3987,7 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) } else /* Another has populated it */ pmd_free(mm, new); #endif /* __ARCH_HAS_4LEVEL_HACK */ - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); return 0; } #endif /* __PAGETABLE_PMD_FOLDED */ @@ -3776,6 +3996,7 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *ptep; @@ -3784,7 +4005,11 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) goto out; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d))) + goto out; + + pud = pud_offset(p4d, address); if (pud_none(*pud) || unlikely(pud_bad(*pud))) goto out; @@ -4073,7 +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; @@ -4155,6 +4380,38 @@ void copy_user_huge_page(struct page *dst, struct page *src, copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma); } } + +long copy_huge_page_from_user(struct page *dst_page, + const void __user *usr_src, + unsigned int pages_per_huge_page, + bool allow_pagefault) +{ + void *src = (void *)usr_src; + void *page_kaddr; + unsigned long i, rc = 0; + unsigned long ret_val = pages_per_huge_page * PAGE_SIZE; + + for (i = 0; i < pages_per_huge_page; i++) { + if (allow_pagefault) + page_kaddr = kmap(dst_page + i); + else + page_kaddr = kmap_atomic(dst_page + i); + rc = copy_from_user(page_kaddr, + (const void __user *)(src + i * PAGE_SIZE), + PAGE_SIZE); + if (allow_pagefault) + kunmap(dst_page + i); + else + kunmap_atomic(page_kaddr); + + ret_val -= (PAGE_SIZE - rc); + if (rc) + break; + + cond_resched(); + } + return ret_val; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b8c11e063ff0..b63d7d1239df 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -6,6 +6,7 @@ #include <linux/stddef.h> #include <linux/mm.h> +#include <linux/sched/signal.h> #include <linux/swap.h> #include <linux/interrupt.h> #include <linux/pagemap.h> @@ -124,8 +125,13 @@ void put_online_mems(void) } +/* Serializes write accesses to mem_hotplug.active_writer. */ +static DEFINE_MUTEX(memory_add_remove_lock); + void mem_hotplug_begin(void) { + mutex_lock(&memory_add_remove_lock); + mem_hotplug.active_writer = current; memhp_lock_acquire(); @@ -144,6 +150,7 @@ void mem_hotplug_done(void) mem_hotplug.active_writer = NULL; mutex_unlock(&mem_hotplug.lock); memhp_lock_release(); + mutex_unlock(&memory_add_remove_lock); } /* add this memory to iomem resource */ @@ -179,7 +186,7 @@ static void release_memory_resource(struct resource *res) void get_page_bootmem(unsigned long info, struct page *page, unsigned long type) { - page->lru.next = (struct list_head *) type; + page->freelist = (void *)type; SetPagePrivate(page); set_page_private(page, info); page_ref_inc(page); @@ -189,11 +196,12 @@ void put_page_bootmem(struct page *page) { unsigned long type; - type = (unsigned long) page->lru.next; + type = (unsigned long) page->freelist; BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE); if (page_ref_dec_return(page) == 1) { + page->freelist = NULL; ClearPagePrivate(page); set_page_private(page, 0); INIT_LIST_HEAD(&page->lru); @@ -861,7 +869,6 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, return ret; } -EXPORT_SYMBOL_GPL(__remove_pages); #endif /* CONFIG_MEMORY_HOTREMOVE */ int set_online_page_callback(online_page_callback_t callback) @@ -1201,7 +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; @@ -1335,7 +1346,7 @@ int zone_for_memory(int nid, u64 start, u64 size, int zone_default, static int online_memory_block(struct memory_block *mem, void *arg) { - return memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE); + return device_online(&mem->dev); } /* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ @@ -1507,7 +1518,7 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, while ((i < MAX_ORDER_NR_PAGES) && !pfn_valid_within(pfn + i)) i++; - if (i == MAX_ORDER_NR_PAGES) + if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn) continue; page = pfn_to_page(pfn + i); if (zone && page_zone(page) != zone) @@ -1521,7 +1532,7 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, if (zone) { *valid_start = start; - *valid_end = end; + *valid_end = min(end, end_pfn); return 1; } else { return 0; @@ -1529,10 +1540,10 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, } /* - * Scan pfn range [start,end) to find movable/migratable pages (LRU pages - * and hugepages). We scan pfn because it's much easier than scanning over - * linked list. This function returns the pfn of the first found movable - * page if it's found, otherwise 0. + * Scan pfn range [start,end) to find movable/migratable pages (LRU pages, + * non-lru movable pages and hugepages). We scan pfn because it's much + * easier than scanning over linked list. This function returns the pfn + * of the first found movable page if it's found, otherwise 0. */ static unsigned long scan_movable_pages(unsigned long start, unsigned long end) { @@ -1543,6 +1554,8 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end) page = pfn_to_page(pfn); if (PageLRU(page)) return pfn; + if (__PageMovable(page)) + return pfn; if (PageHuge(page)) { if (page_huge_active(page)) return pfn; @@ -1619,21 +1632,25 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) if (!get_page_unless_zero(page)) continue; /* - * We can skip free pages. And we can only deal with pages on - * LRU. + * We can skip free pages. And we can deal with pages on + * LRU and non-lru movable pages. */ - ret = isolate_lru_page(page); + if (PageLRU(page)) + ret = isolate_lru_page(page); + else + ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE); if (!ret) { /* Success */ put_page(page); list_add_tail(&page->lru, &source); move_pages--; - inc_node_page_state(page, NR_ISOLATED_ANON + - page_is_file_cache(page)); + if (!__PageMovable(page)) + inc_node_page_state(page, NR_ISOLATED_ANON + + page_is_file_cache(page)); } else { #ifdef CONFIG_DEBUG_VM - pr_alert("removing pfn %lx from LRU failed\n", pfn); - dump_page(page, "failed to remove from LRU"); + pr_alert("failed to isolate pfn %lx\n", pfn); + dump_page(page, "isolation failed"); #endif put_page(page); /* Because we don't have big zone->lock. we should diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 1e7873e40c9a..37d0b334bfe9 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -73,6 +73,9 @@ #include <linux/hugetlb.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/sched/mm.h> +#include <linux/sched/numa_balancing.h> +#include <linux/sched/task.h> #include <linux/nodemask.h> #include <linux/cpuset.h> #include <linux/slab.h> @@ -1526,7 +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); @@ -1535,14 +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); } @@ -1550,7 +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; @@ -1559,14 +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 87f4d0f81819..89a0a1707f4c 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -40,6 +40,7 @@ #include <linux/mmu_notifier.h> #include <linux/page_idle.h> #include <linux/page_owner.h> +#include <linux/sched/mm.h> #include <asm/tlbflush.h> @@ -74,7 +75,7 @@ int migrate_prep_local(void) return 0; } -bool isolate_movable_page(struct page *page, isolate_mode_t mode) +int isolate_movable_page(struct page *page, isolate_mode_t mode) { struct address_space *mapping; @@ -125,14 +126,14 @@ bool isolate_movable_page(struct page *page, isolate_mode_t mode) __SetPageIsolated(page); unlock_page(page); - return true; + return 0; out_no_isolated: unlock_page(page); out_putpage: put_page(page); out: - return false; + return -EBUSY; } /* It should be called on page which is PG_movable */ @@ -183,9 +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); } } } @@ -193,83 +194,66 @@ 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 *new, struct vm_area_struct *vma, +static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *old) { - struct mm_struct *mm = vma->vm_mm; + struct page_vma_mapped_walk pvmw = { + .page = old, + .vma = vma, + .address = addr, + .flags = PVMW_SYNC | PVMW_MIGRATION, + }; + struct page *new; + pte_t pte; swp_entry_t entry; - pmd_t *pmd; - pte_t *ptep, pte; - spinlock_t *ptl; - if (unlikely(PageHuge(new))) { - ptep = huge_pte_offset(mm, addr); - if (!ptep) - goto out; - ptl = huge_pte_lockptr(hstate_vma(vma), mm, ptep); - } else { - pmd = mm_find_pmd(mm, addr); - if (!pmd) - goto out; + VM_BUG_ON_PAGE(PageTail(page), page); + while (page_vma_mapped_walk(&pvmw)) { + if (PageKsm(page)) + new = page; + else + new = page - pvmw.page->index + + linear_page_index(vma, pvmw.address); - ptep = pte_offset_map(pmd, addr); + get_page(new); + pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot))); + if (pte_swp_soft_dirty(*pvmw.pte)) + pte = pte_mksoft_dirty(pte); /* - * Peek to check is_swap_pte() before taking ptlock? No, we - * can race mremap's move_ptes(), which skips anon_vma lock. + * Recheck VMA as permissions can change since migration started */ - - ptl = pte_lockptr(mm, pmd); - } - - spin_lock(ptl); - pte = *ptep; - if (!is_swap_pte(pte)) - goto unlock; - - entry = pte_to_swp_entry(pte); - - if (!is_migration_entry(entry) || - migration_entry_to_page(entry) != old) - goto unlock; - - get_page(new); - pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot))); - if (pte_swp_soft_dirty(*ptep)) - pte = pte_mksoft_dirty(pte); - - /* Recheck VMA as permissions can change since migration started */ - if (is_write_migration_entry(entry)) - pte = maybe_mkwrite(pte, vma); + entry = pte_to_swp_entry(*pvmw.pte); + if (is_write_migration_entry(entry)) + pte = maybe_mkwrite(pte, vma); #ifdef CONFIG_HUGETLB_PAGE - if (PageHuge(new)) { - pte = pte_mkhuge(pte); - pte = arch_make_huge_pte(pte, vma, new, 0); - } + if (PageHuge(new)) { + pte = pte_mkhuge(pte); + pte = arch_make_huge_pte(pte, vma, new, 0); + } #endif - flush_dcache_page(new); - set_pte_at(mm, addr, ptep, pte); + flush_dcache_page(new); + set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); - if (PageHuge(new)) { - if (PageAnon(new)) - hugepage_add_anon_rmap(new, vma, addr); + if (PageHuge(new)) { + if (PageAnon(new)) + hugepage_add_anon_rmap(new, vma, pvmw.address); + else + page_dup_rmap(new, true); + } else if (PageAnon(new)) + page_add_anon_rmap(new, vma, pvmw.address, false); else - page_dup_rmap(new, true); - } else if (PageAnon(new)) - page_add_anon_rmap(new, vma, addr, false); - else - page_add_file_rmap(new, false); + page_add_file_rmap(new, false); - if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new)) - mlock_vma_page(new); + if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new)) + mlock_vma_page(new); - /* No need to invalidate - it was non-present before */ - update_mmu_cache(vma, addr, ptep); -unlock: - pte_unmap_unlock(ptep, ptl); -out: - return SWAP_AGAIN; + /* No need to invalidate - it was non-present before */ + update_mmu_cache(vma, pvmw.address, pvmw.pte); + } + + return true; } /* @@ -1738,9 +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; @@ -1963,7 +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/mincore.c b/mm/mincore.c index ddb872da3f5b..c5687c45c326 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -14,6 +14,7 @@ #include <linux/syscalls.h> #include <linux/swap.h> #include <linux/swapops.h> +#include <linux/shmem_fs.h> #include <linux/hugetlb.h> #include <linux/uaccess.h> diff --git a/mm/mlock.c b/mm/mlock.c index cdbed8aaa426..c483c5c20b4b 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -8,6 +8,7 @@ #include <linux/capability.h> #include <linux/mman.h> #include <linux/mm.h> +#include <linux/sched/user.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/pagemap.h> @@ -122,17 +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); @@ -379,6 +378,7 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec, pte = get_locked_pte(vma->vm_mm, start, &ptl); /* Make sure we do not cross the page table boundary */ end = pgd_addr_end(start, end); + end = p4d_addr_end(start, end); end = pud_addr_end(start, end); end = pmd_addr_end(start, end); @@ -441,7 +441,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, while (start < end) { struct page *page; - unsigned int page_mask; + unsigned int page_mask = 0; unsigned long page_increm; struct pagevec pvec; struct zone *zone; @@ -455,8 +455,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, * suits munlock very well (and if somehow an abnormal page * has sneaked into the range, we won't oops here: great). */ - page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP, - &page_mask); + page = follow_page(vma, start, FOLL_GET | FOLL_DUMP); if (page && !IS_ERR(page)) { if (PageTransTail(page)) { @@ -467,8 +466,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, /* * Any THP page found by follow_page_mask() may * have gotten split before reaching - * munlock_vma_page(), so we need to recompute - * the page_mask here. + * munlock_vma_page(), so we need to compute + * the page_mask here instead. */ page_mask = munlock_vma_page(page); unlock_page(page); diff --git a/mm/mmap.c b/mm/mmap.c index dc4291dcc99b..f82741e199c0 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -176,7 +176,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) return next; } -static int do_brk(unsigned long addr, unsigned long len); +static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf); SYSCALL_DEFINE1(brk, unsigned long, brk) { @@ -185,6 +185,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) struct mm_struct *mm = current->mm; unsigned long min_brk; bool populate; + LIST_HEAD(uf); if (down_write_killable(&mm->mmap_sem)) return -EINTR; @@ -222,7 +223,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) /* Always allow shrinking brk. */ if (brk <= mm->brk) { - if (!do_munmap(mm, newbrk, oldbrk-newbrk)) + if (!do_munmap(mm, newbrk, oldbrk-newbrk, &uf)) goto set_brk; goto out; } @@ -232,13 +233,14 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) goto out; /* Ok, looks good - let it rip. */ - if (do_brk(oldbrk, newbrk-oldbrk) < 0) + if (do_brk(oldbrk, newbrk-oldbrk, &uf) < 0) goto out; set_brk: mm->brk = brk; populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0; up_write(&mm->mmap_sem); + userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(oldbrk, newbrk - oldbrk); return brk; @@ -1304,7 +1306,8 @@ static inline int mlock_future_check(struct mm_struct *mm, unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, - unsigned long pgoff, unsigned long *populate) + unsigned long pgoff, unsigned long *populate, + struct list_head *uf) { struct mm_struct *mm = current->mm; int pkey = 0; @@ -1447,7 +1450,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, vm_flags |= VM_NORESERVE; } - addr = mmap_region(file, addr, len, vm_flags, pgoff); + addr = mmap_region(file, addr, len, vm_flags, pgoff, uf); if (!IS_ERR_VALUE(addr) && ((vm_flags & VM_LOCKED) || (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE)) @@ -1476,7 +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; @@ -1583,7 +1586,8 @@ static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags) } unsigned long mmap_region(struct file *file, unsigned long addr, - unsigned long len, vm_flags_t vm_flags, unsigned long pgoff) + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, + struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; @@ -1609,7 +1613,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, /* Clear old maps */ while (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) { - if (do_munmap(mm, addr, len)) + if (do_munmap(mm, addr, len, uf)) return -ENOMEM; } @@ -1668,7 +1672,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, * new file must not have been exposed to user-space, yet. */ vma->vm_file = get_file(file); - error = file->f_op->mmap(file, vma); + error = call_mmap(file, vma); if (error) goto unmap_and_free_vma; @@ -2495,11 +2499,11 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, } /* - * __split_vma() bypasses sysctl_max_map_count checking. We use this on the - * munmap path where it doesn't make sense to fail. + * __split_vma() bypasses sysctl_max_map_count checking. We use this where it + * has already been checked or doesn't make sense to fail. */ -static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, int new_below) +int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, int new_below) { struct vm_area_struct *new; int err; @@ -2579,7 +2583,8 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, * work. This now handles partial unmappings. * Jeremy Fitzhardinge <jeremy@goop.org> */ -int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) +int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, + struct list_head *uf) { unsigned long end; struct vm_area_struct *vma, *prev, *last; @@ -2603,6 +2608,13 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) if (vma->vm_start >= end) return 0; + if (uf) { + int error = userfaultfd_unmap_prep(vma, start, end, uf); + + if (error) + return error; + } + /* * If we need to split any vma, do it now to save pain later. * @@ -2668,27 +2680,22 @@ int vm_munmap(unsigned long start, size_t len) { int ret; struct mm_struct *mm = current->mm; + LIST_HEAD(uf); if (down_write_killable(&mm->mmap_sem)) return -EINTR; - ret = do_munmap(mm, start, len); + ret = do_munmap(mm, start, len, &uf); up_write(&mm->mmap_sem); + userfaultfd_unmap_complete(mm, &uf); return ret; } EXPORT_SYMBOL(vm_munmap); SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { - int ret; - struct mm_struct *mm = current->mm; - profile_munmap(addr); - if (down_write_killable(&mm->mmap_sem)) - return -EINTR; - ret = do_munmap(mm, addr, len); - up_write(&mm->mmap_sem); - return ret; + return vm_munmap(addr, len); } @@ -2780,7 +2787,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, file = get_file(vma->vm_file); ret = do_mmap_pgoff(vma->vm_file, start, size, - prot, flags, pgoff, &populate); + prot, flags, pgoff, &populate, NULL); fput(file); out: up_write(&mm->mmap_sem); @@ -2806,11 +2813,11 @@ static inline void verify_mm_writelocked(struct mm_struct *mm) * anonymous maps. eventually we may be able to do some * brk-specific accounting here. */ -static int do_brk(unsigned long addr, unsigned long request) +static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; - unsigned long flags, len; + unsigned long len; struct rb_node **rb_link, *rb_parent; pgoff_t pgoff = addr >> PAGE_SHIFT; int error; @@ -2821,7 +2828,10 @@ static int do_brk(unsigned long addr, unsigned long request) if (!len) return 0; - flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; + /* Until we need other flags, refuse anything except VM_EXEC. */ + if ((flags & (~VM_EXEC)) != 0) + return -EINVAL; + flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); if (offset_in_page(error)) @@ -2842,7 +2852,7 @@ static int do_brk(unsigned long addr, unsigned long request) */ while (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) { - if (do_munmap(mm, addr, len)) + if (do_munmap(mm, addr, len, uf)) return -ENOMEM; } @@ -2889,22 +2899,35 @@ out: return 0; } -int vm_brk(unsigned long addr, unsigned long len) +static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf) +{ + return do_brk_flags(addr, len, 0, uf); +} + +int vm_brk_flags(unsigned long addr, unsigned long len, unsigned long flags) { struct mm_struct *mm = current->mm; int ret; bool populate; + LIST_HEAD(uf); if (down_write_killable(&mm->mmap_sem)) return -EINTR; - ret = do_brk(addr, len); + ret = do_brk_flags(addr, len, flags, &uf); populate = ((mm->def_flags & VM_LOCKED) != 0); up_write(&mm->mmap_sem); + userfaultfd_unmap_complete(mm, &uf); if (populate && !ret) mm_populate(addr, len); return ret; } +EXPORT_SYMBOL(vm_brk_flags); + +int vm_brk(unsigned long addr, unsigned long len) +{ + return vm_brk_flags(addr, len, 0); +} EXPORT_SYMBOL(vm_brk); /* Release all mmaps. */ @@ -3111,8 +3134,7 @@ void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) mm->data_vm += npages; } -static int special_mapping_fault(struct vm_area_struct *vma, - struct vm_fault *vmf); +static int special_mapping_fault(struct vm_fault *vmf); /* * Having a close hook prevents vma merging regardless of flags. @@ -3147,9 +3169,9 @@ static const struct vm_operations_struct legacy_special_mapping_vmops = { .fault = special_mapping_fault, }; -static int special_mapping_fault(struct vm_area_struct *vma, - struct vm_fault *vmf) +static int special_mapping_fault(struct vm_fault *vmf) { + struct vm_area_struct *vma = vmf->vma; pgoff_t pgoff; struct page **pages; @@ -3159,7 +3181,7 @@ static int special_mapping_fault(struct vm_area_struct *vma, struct vm_special_mapping *sm = vma->vm_private_data; if (sm->fault) - return sm->fault(sm, vma, vmf); + return sm->fault(sm, vmf->vma, vmf); pages = sm->pages; } @@ -3433,7 +3455,7 @@ void mm_drop_all_locks(struct mm_struct *mm) } /* - * initialise the VMA slab + * initialise the percpu counter for VM */ void __init mmap_init(void) { diff --git a/mm/mmu_context.c b/mm/mmu_context.c index 6f4d27c5bb32..3e612ae748e9 100644 --- a/mm/mmu_context.c +++ b/mm/mmu_context.c @@ -5,6 +5,8 @@ #include <linux/mm.h> #include <linux/sched.h> +#include <linux/sched/mm.h> +#include <linux/sched/task.h> #include <linux/mmu_context.h> #include <linux/export.h> @@ -25,7 +27,7 @@ void use_mm(struct mm_struct *mm) task_lock(tsk); active_mm = tsk->active_mm; if (active_mm != mm) { - atomic_inc(&mm->mm_count); + mmgrab(mm); tsk->active_mm = mm; } tsk->mm = mm; diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index f4259e496f83..a7652acd2ab9 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -17,6 +17,7 @@ #include <linux/srcu.h> #include <linux/rcupdate.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/slab.h> /* global SRCU for all MMs */ @@ -275,7 +276,7 @@ static int do_mmu_notifier_register(struct mmu_notifier *mn, mm->mmu_notifier_mm = mmu_notifier_mm; mmu_notifier_mm = NULL; } - atomic_inc(&mm->mm_count); + mmgrab(mm); /* * Serialize the update against mmu_notifier_unregister. A diff --git a/mm/mmzone.c b/mm/mmzone.c index 5652be858e5e..a51c0a67ea3d 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -60,7 +60,7 @@ struct zoneref *__next_zones_zonelist(struct zoneref *z, * Find the next suitable zone to use for the allocation. * Only filter based on nodemask if it's set */ - if (likely(nodes == NULL)) + if (unlikely(nodes == NULL)) while (zonelist_zone_idx(z) > highest_zoneidx) z++; else diff --git a/mm/mprotect.c b/mm/mprotect.c index f9c07f54dd62..8edd0d576254 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -33,34 +33,6 @@ #include "internal.h" -/* - * For a prot_numa update we only hold mmap_sem for read so there is a - * potential race with faulting where a pmd was temporarily none. This - * function checks for a transhuge pmd under the appropriate lock. It - * returns a pte if it was successfully locked or NULL if it raced with - * a transhuge insertion. - */ -static pte_t *lock_pte_protection(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, int prot_numa, spinlock_t **ptl) -{ - pte_t *pte; - spinlock_t *pmdl; - - /* !prot_numa is protected by mmap_sem held for write */ - if (!prot_numa) - return pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl); - - pmdl = pmd_lock(vma->vm_mm, pmd); - if (unlikely(pmd_trans_huge(*pmd) || pmd_none(*pmd))) { - spin_unlock(pmdl); - return NULL; - } - - pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl); - spin_unlock(pmdl); - return pte; -} - static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) @@ -71,7 +43,21 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long pages = 0; int target_node = NUMA_NO_NODE; - pte = lock_pte_protection(vma, pmd, addr, prot_numa, &ptl); + /* + * Can be called with only the mmap_sem for reading by + * prot_numa so we must check the pmd isn't constantly + * changing from under us from pmd_none to pmd_trans_huge + * and/or the other way around. + */ + if (pmd_trans_unstable(pmd)) + return 0; + + /* + * The pmd points to a regular pte so the pmd can't change + * from under us even if the mmap_sem is only hold for + * reading. + */ + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!pte) return 0; @@ -113,7 +99,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, ptent = ptep_modify_prot_start(mm, addr, pte); ptent = pte_modify(ptent, newprot); if (preserve_write) - ptent = pte_mkwrite(ptent); + ptent = pte_mk_savedwrite(ptent); /* Avoid taking write faults for known dirty pages */ if (dirty_accountable && pte_dirty(ptent) && @@ -177,8 +163,6 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) { __split_huge_pmd(vma, pmd, addr, false, NULL); - if (pmd_trans_unstable(pmd)) - continue; } else { int nr_ptes = change_huge_pmd(vma, pmd, addr, newprot, prot_numa); @@ -209,14 +193,14 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, } static inline unsigned long change_pud_range(struct vm_area_struct *vma, - pgd_t *pgd, unsigned long addr, unsigned long end, + p4d_t *p4d, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) { pud_t *pud; unsigned long next; unsigned long pages = 0; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) @@ -228,6 +212,26 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma, return pages; } +static inline unsigned long change_p4d_range(struct vm_area_struct *vma, + pgd_t *pgd, unsigned long addr, unsigned long end, + pgprot_t newprot, int dirty_accountable, int prot_numa) +{ + p4d_t *p4d; + unsigned long next; + unsigned long pages = 0; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + pages += change_pud_range(vma, p4d, addr, next, newprot, + dirty_accountable, prot_numa); + } while (p4d++, addr = next, addr != end); + + return pages; +} + static unsigned long change_protection_range(struct vm_area_struct *vma, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) @@ -246,7 +250,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - pages += change_pud_range(vma, pgd, addr, next, newprot, + pages += change_p4d_range(vma, pgd, addr, next, newprot, dirty_accountable, prot_numa); } while (pgd++, addr = next, addr != end); diff --git a/mm/mremap.c b/mm/mremap.c index 30d7d2482eea..cd8a1b199ef9 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -22,6 +22,7 @@ #include <linux/mmu_notifier.h> #include <linux/uaccess.h> #include <linux/mm-arch-hooks.h> +#include <linux/userfaultfd_k.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> @@ -31,6 +32,7 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -38,7 +40,11 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr) if (pgd_none_or_clear_bad(pgd)) return NULL; - pud = pud_offset(pgd, addr); + p4d = p4d_offset(pgd, addr); + if (p4d_none_or_clear_bad(p4d)) + return NULL; + + pud = pud_offset(p4d, addr); if (pud_none_or_clear_bad(pud)) return NULL; @@ -53,11 +59,15 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, addr); if (!pud) return NULL; @@ -250,7 +260,9 @@ unsigned long move_page_tables(struct vm_area_struct *vma, static unsigned long move_vma(struct vm_area_struct *vma, unsigned long old_addr, unsigned long old_len, - unsigned long new_len, unsigned long new_addr, bool *locked) + unsigned long new_len, unsigned long new_addr, + bool *locked, struct vm_userfaultfd_ctx *uf, + struct list_head *uf_unmap) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma; @@ -309,6 +321,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, old_addr = new_addr; new_addr = err; } else { + mremap_userfaultfd_prep(new_vma, uf); arch_remap(mm, old_addr, old_addr + old_len, new_addr, new_addr + new_len); } @@ -338,7 +351,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, if (unlikely(vma->vm_flags & VM_PFNMAP)) untrack_pfn_moved(vma); - if (do_munmap(mm, old_addr, old_len) < 0) { + if (do_munmap(mm, old_addr, old_len, uf_unmap) < 0) { /* OOM: unable to split vma, just get accounts right */ vm_unacct_memory(excess >> PAGE_SHIFT); excess = 0; @@ -413,7 +426,9 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, } static unsigned long mremap_to(unsigned long addr, unsigned long old_len, - unsigned long new_addr, unsigned long new_len, bool *locked) + unsigned long new_addr, unsigned long new_len, bool *locked, + struct vm_userfaultfd_ctx *uf, + struct list_head *uf_unmap) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; @@ -431,12 +446,12 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len, if (addr + old_len > new_addr && new_addr + new_len > addr) goto out; - ret = do_munmap(mm, new_addr, new_len); + ret = do_munmap(mm, new_addr, new_len, NULL); if (ret) goto out; if (old_len >= new_len) { - ret = do_munmap(mm, addr+new_len, old_len - new_len); + ret = do_munmap(mm, addr+new_len, old_len - new_len, uf_unmap); if (ret && old_len != new_len) goto out; old_len = new_len; @@ -458,7 +473,8 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len, if (offset_in_page(ret)) goto out1; - ret = move_vma(vma, addr, old_len, new_len, new_addr, locked); + ret = move_vma(vma, addr, old_len, new_len, new_addr, locked, uf, + uf_unmap); if (!(offset_in_page(ret))) goto out; out1: @@ -497,6 +513,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, unsigned long ret = -EINVAL; unsigned long charged = 0; bool locked = false; + struct vm_userfaultfd_ctx uf = NULL_VM_UFFD_CTX; + LIST_HEAD(uf_unmap); if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE)) return ret; @@ -523,7 +541,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, if (flags & MREMAP_FIXED) { ret = mremap_to(addr, old_len, new_addr, new_len, - &locked); + &locked, &uf, &uf_unmap); goto out; } @@ -533,7 +551,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, * do_munmap does all the needed commit accounting */ if (old_len >= new_len) { - ret = do_munmap(mm, addr+new_len, old_len - new_len); + ret = do_munmap(mm, addr+new_len, old_len - new_len, &uf_unmap); if (ret && old_len != new_len) goto out; ret = addr; @@ -592,7 +610,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, goto out; } - ret = move_vma(vma, addr, old_len, new_len, new_addr, &locked); + ret = move_vma(vma, addr, old_len, new_len, new_addr, + &locked, &uf, &uf_unmap); } out: if (offset_in_page(ret)) { @@ -602,5 +621,7 @@ out: up_write(¤t->mm->mmap_sem); if (locked && new_len > old_len) mm_populate(new_addr + old_len, new_len - old_len); + mremap_userfaultfd_complete(&uf, addr, new_addr, old_len); + userfaultfd_unmap_complete(mm, &uf_unmap); return ret; } diff --git a/mm/nommu.c b/mm/nommu.c index 24f9f5f39145..2d131b97a851 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -17,6 +17,7 @@ #include <linux/export.h> #include <linux/mm.h> +#include <linux/sched/mm.h> #include <linux/vmacache.h> #include <linux/mman.h> #include <linux/swap.h> @@ -517,7 +518,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) } /* - * initialise the VMA and region record slabs + * initialise the percpu counter for VM and region record slabs */ void __init mmap_init(void) { @@ -757,7 +758,7 @@ static void delete_vma_from_mm(struct vm_area_struct *vma) mm->map_count--; for (i = 0; i < VMACACHE_SIZE; i++) { /* if the vma is cached, invalidate the entire cache */ - if (curr->vmacache[i] == vma) { + if (curr->vmacache.vmas[i] == vma) { vmacache_invalidate(mm); break; } @@ -1084,7 +1085,7 @@ static int do_mmap_shared_file(struct vm_area_struct *vma) { int ret; - ret = vma->vm_file->f_op->mmap(vma->vm_file, vma); + ret = call_mmap(vma->vm_file, vma); if (ret == 0) { vma->vm_region->vm_top = vma->vm_region->vm_end; return 0; @@ -1115,7 +1116,7 @@ static int do_mmap_private(struct vm_area_struct *vma, * - VM_MAYSHARE will be set if it may attempt to share */ if (capabilities & NOMMU_MAP_DIRECT) { - ret = vma->vm_file->f_op->mmap(vma->vm_file, vma); + ret = call_mmap(vma->vm_file, vma); if (ret == 0) { /* shouldn't return success if we're not sharing */ BUG_ON(!(vma->vm_flags & VM_MAYSHARE)); @@ -1191,7 +1192,7 @@ error_free: enomem: pr_err("Allocation of length %lu from process %d (%s) failed\n", len, current->pid, current->comm); - show_free_areas(0); + show_free_areas(0, NULL); return -ENOMEM; } @@ -1205,7 +1206,8 @@ unsigned long do_mmap(struct file *file, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, - unsigned long *populate) + unsigned long *populate, + struct list_head *uf) { struct vm_area_struct *vma; struct vm_region *region; @@ -1412,13 +1414,13 @@ error_getting_vma: kmem_cache_free(vm_region_jar, region); pr_warn("Allocation of vma for %lu byte allocation from process %d failed\n", len, current->pid); - show_free_areas(0); + show_free_areas(0, NULL); return -ENOMEM; error_getting_region: pr_warn("Allocation of vm region for %lu byte allocation from process %d failed\n", len, current->pid); - show_free_areas(0); + show_free_areas(0, NULL); return -ENOMEM; } @@ -1577,7 +1579,7 @@ static int shrink_vma(struct mm_struct *mm, * - under NOMMU conditions the chunk to be unmapped must be backed by a single * VMA, though it need not cover the whole VMA */ -int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) +int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf) { struct vm_area_struct *vma; unsigned long end; @@ -1643,7 +1645,7 @@ int vm_munmap(unsigned long addr, size_t len) int ret; down_write(&mm->mmap_sem); - ret = do_munmap(mm, addr, len); + ret = do_munmap(mm, addr, len, NULL); up_write(&mm->mmap_sem); return ret; } @@ -1794,7 +1796,7 @@ void unmap_mapping_range(struct address_space *mapping, } EXPORT_SYMBOL(unmap_mapping_range); -int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +int filemap_fault(struct vm_fault *vmf) { BUG(); return 0; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index ec9f11d4f094..04c9143a8625 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -22,6 +22,9 @@ #include <linux/err.h> #include <linux/gfp.h> #include <linux/sched.h> +#include <linux/sched/mm.h> +#include <linux/sched/coredump.h> +#include <linux/sched/task.h> #include <linux/swap.h> #include <linux/timex.h> #include <linux/jiffies.h> @@ -403,12 +406,14 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask) static void dump_header(struct oom_control *oc, struct task_struct *p) { - nodemask_t *nm = (oc->nodemask) ? oc->nodemask : &cpuset_current_mems_allowed; - - pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), nodemask=%*pbl, order=%d, oom_score_adj=%hd\n", - current->comm, oc->gfp_mask, &oc->gfp_mask, - nodemask_pr_args(nm), oc->order, - current->signal->oom_score_adj); + pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), nodemask=", + current->comm, oc->gfp_mask, &oc->gfp_mask); + if (oc->nodemask) + pr_cont("%*pbl", nodemask_pr_args(oc->nodemask)); + else + pr_cont("(null)"); + pr_cont(", order=%d, oom_score_adj=%hd\n", + oc->order, current->signal->oom_score_adj); if (!IS_ENABLED(CONFIG_COMPACTION) && oc->order) pr_warn("COMPACTION is disabled!!!\n"); @@ -417,7 +422,7 @@ static void dump_header(struct oom_control *oc, struct task_struct *p) if (oc->memcg) mem_cgroup_print_oom_info(oc->memcg, p); else - show_mem(SHOW_MEM_FILTER_NODES); + show_mem(SHOW_MEM_FILTER_NODES, oc->nodemask); if (sysctl_oom_dump_tasks) dump_tasks(oc->memcg, oc->nodemask); } @@ -465,8 +470,6 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) { struct mmu_gather tlb; struct vm_area_struct *vma; - struct zap_details details = {.check_swap_entries = true, - .ignore_dirty = true}; bool ret = true; /* @@ -510,14 +513,7 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) tlb_gather_mmu(&tlb, mm, 0, -1); for (vma = mm->mmap ; vma; vma = vma->vm_next) { - if (is_vm_hugetlb_page(vma)) - continue; - - /* - * mlocked VMAs require explicit munlocking before unmap. - * Let's keep it simple here and skip such VMAs. - */ - if (vma->vm_flags & VM_LOCKED) + if (!can_madv_dontneed_vma(vma)) continue; /* @@ -532,7 +528,7 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) */ if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) unmap_page_range(&tlb, vma, vma->vm_start, vma->vm_end, - &details); + NULL); } tlb_finish_mmu(&tlb, 0, -1); pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n", @@ -660,7 +656,7 @@ static void mark_oom_victim(struct task_struct *tsk) /* oom_mm is bound to the signal struct life time. */ if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) - atomic_inc(&tsk->signal->oom_mm->mm_count); + mmgrab(tsk->signal->oom_mm); /* * Make sure that the task is woken up from uninterruptible sleep @@ -689,6 +685,7 @@ void exit_oom_victim(void) void oom_killer_enable(void) { oom_killer_disabled = false; + pr_info("OOM killer enabled.\n"); } /** @@ -725,6 +722,7 @@ bool oom_killer_disable(signed long timeout) oom_killer_enable(); return false; } + pr_info("OOM killer disabled.\n"); return true; } @@ -877,7 +875,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) /* Get a reference to safely compare mm after task_unlock(victim) */ mm = victim->mm; - atomic_inc(&mm->mm_count); + mmgrab(mm); /* * We should send SIGKILL before setting TIF_MEMDIE in order to prevent * the OOM victim from depleting the memory reserves from the user @@ -1013,7 +1011,7 @@ bool out_of_memory(struct oom_control *oc) * make sure exclude 0 mask - all other users should have at least * ___GFP_DIRECT_RECLAIM to get here. */ - if (oc->gfp_mask && !(oc->gfp_mask & (__GFP_FS|__GFP_NOFAIL))) + if (oc->gfp_mask && !(oc->gfp_mask & __GFP_FS)) return true; /* diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 216449825859..2359608d2568 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -36,6 +36,7 @@ #include <linux/pagevec.h> #include <linux/timer.h> #include <linux/sched/rt.h> +#include <linux/sched/signal.h> #include <linux/mm_inline.h> #include <trace/events/writeback.h> @@ -580,7 +581,7 @@ static void wb_domain_writeout_inc(struct wb_domain *dom, __fprop_inc_percpu_max(&dom->completions, completions, max_prop_frac); /* First event after period switching was turned off? */ - if (!unlikely(dom->period_time)) { + if (unlikely(!dom->period_time)) { /* * We can race with other __bdi_writeout_inc calls here but * it does not cause any harm since the resulting time when @@ -649,9 +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; @@ -1797,7 +1797,7 @@ pause: * pages exceeds dirty_thresh, give the other good wb's a pipe * to go through, so that tasks on them still remain responsive. * - * In theory 1 page is enough to keep the comsumer-producer + * In theory 1 page is enough to keep the consumer-producer * pipe going: the flusher cleans 1 page => the task dirties 1 * more page. However wb_dirty has accounting errors. So use * the larger and more IO friendly wb_stat_error. @@ -2427,7 +2427,7 @@ 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); @@ -2449,7 +2449,7 @@ 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); @@ -2706,7 +2706,7 @@ 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); @@ -2753,7 +2753,7 @@ 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); @@ -2808,7 +2808,7 @@ 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 f3e0c69a97b7..1e2af704938d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -55,12 +55,13 @@ #include <linux/kmemleak.h> #include <linux/compaction.h> #include <trace/events/kmem.h> +#include <trace/events/oom.h> #include <linux/prefetch.h> #include <linux/mm_inline.h> #include <linux/migrate.h> -#include <linux/page_ext.h> #include <linux/hugetlb.h> #include <linux/sched/rt.h> +#include <linux/sched/mm.h> #include <linux/page_owner.h> #include <linux/kthread.h> #include <linux/memcontrol.h> @@ -91,6 +92,10 @@ EXPORT_PER_CPU_SYMBOL(_numa_mem_); int _node_numa_mem_[MAX_NUMNODES]; #endif +/* work_structs for global per-cpu drains */ +DEFINE_MUTEX(pcpu_drain_mutex); +DEFINE_PER_CPU(struct work_struct, pcpu_drain); + #ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY volatile unsigned long latent_entropy __latent_entropy; EXPORT_SYMBOL(latent_entropy); @@ -714,7 +719,7 @@ static inline void rmv_page_order(struct page *page) /* * This function checks whether a page is free && is the buddy * we can do coalesce a page and its buddy if - * (a) the buddy is not in a hole && + * (a) the buddy is not in a hole (check before calling!) && * (b) the buddy is in the buddy system && * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. @@ -729,9 +734,6 @@ static inline void rmv_page_order(struct page *page) static inline int page_is_buddy(struct page *page, struct page *buddy, unsigned int order) { - if (!pfn_valid_within(page_to_pfn(buddy))) - return 0; - if (page_is_guard(buddy) && page_order(buddy) == order) { if (page_zone_id(page) != page_zone_id(buddy)) return 0; @@ -787,9 +789,8 @@ static inline void __free_one_page(struct page *page, struct zone *zone, unsigned int order, int migratetype) { - unsigned long page_idx; - unsigned long combined_idx; - unsigned long uninitialized_var(buddy_idx); + unsigned long combined_pfn; + unsigned long uninitialized_var(buddy_pfn); struct page *buddy; unsigned int max_order; @@ -802,15 +803,16 @@ static inline void __free_one_page(struct page *page, if (likely(!is_migrate_isolate(migratetype))) __mod_zone_freepage_state(zone, 1 << order, migratetype); - page_idx = pfn & ((1 << MAX_ORDER) - 1); - - VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page); + VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page); VM_BUG_ON_PAGE(bad_range(zone, page), page); continue_merging: while (order < max_order - 1) { - buddy_idx = __find_buddy_index(page_idx, order); - buddy = page + (buddy_idx - page_idx); + buddy_pfn = __find_buddy_pfn(pfn, order); + buddy = page + (buddy_pfn - pfn); + + if (!pfn_valid_within(buddy_pfn)) + goto done_merging; if (!page_is_buddy(page, buddy, order)) goto done_merging; /* @@ -824,9 +826,9 @@ continue_merging: zone->free_area[order].nr_free--; rmv_page_order(buddy); } - combined_idx = buddy_idx & page_idx; - page = page + (combined_idx - page_idx); - page_idx = combined_idx; + combined_pfn = buddy_pfn & pfn; + page = page + (combined_pfn - pfn); + pfn = combined_pfn; order++; } if (max_order < MAX_ORDER) { @@ -841,8 +843,8 @@ continue_merging: if (unlikely(has_isolate_pageblock(zone))) { int buddy_mt; - buddy_idx = __find_buddy_index(page_idx, order); - buddy = page + (buddy_idx - page_idx); + buddy_pfn = __find_buddy_pfn(pfn, order); + buddy = page + (buddy_pfn - pfn); buddy_mt = get_pageblock_migratetype(buddy); if (migratetype != buddy_mt @@ -865,13 +867,14 @@ done_merging: * so it's less likely to be used soon and more likely to be merged * as a higher order page */ - if ((order < MAX_ORDER-2) && pfn_valid_within(page_to_pfn(buddy))) { + if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)) { struct page *higher_page, *higher_buddy; - combined_idx = buddy_idx & page_idx; - higher_page = page + (combined_idx - page_idx); - buddy_idx = __find_buddy_index(combined_idx, order + 1); - higher_buddy = higher_page + (buddy_idx - combined_idx); - if (page_is_buddy(higher_page, higher_buddy, order + 1)) { + combined_pfn = buddy_pfn & pfn; + higher_page = page + (combined_pfn - pfn); + buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1); + higher_buddy = higher_page + (buddy_pfn - combined_pfn); + if (pfn_valid_within(buddy_pfn) && + page_is_buddy(higher_page, higher_buddy, order + 1)) { list_add_tail(&page->lru, &zone->free_area[order].free_list[migratetype]); goto out; @@ -1087,14 +1090,10 @@ static void free_pcppages_bulk(struct zone *zone, int count, { int migratetype = 0; int batch_free = 0; - unsigned long nr_scanned; bool isolated_pageblocks; 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; @@ -1147,12 +1146,7 @@ static void free_one_page(struct zone *zone, unsigned int order, int migratetype) { - unsigned long nr_scanned; spin_lock(&zone->lock); - 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); - if (unlikely(has_isolate_pageblock(zone) || is_migrate_isolate(migratetype))) { migratetype = get_pfnblock_migratetype(page, pfn); @@ -1695,10 +1689,10 @@ 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 +1746,10 @@ 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); @@ -2042,8 +2029,8 @@ 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); @@ -2100,8 +2087,7 @@ 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 @@ -2158,8 +2144,7 @@ __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) + if (can_steal && !is_migrate_highatomic_page(page)) steal_suitable_fallback(zone, page, start_migratetype); /* Remove the page from the freelists */ @@ -2341,16 +2326,26 @@ void drain_local_pages(struct zone *zone) drain_pages(cpu); } +static void drain_local_pages_wq(struct work_struct *work) +{ + /* + * drain_all_pages doesn't use proper cpu hotplug protection so + * we can race with cpu offline when the WQ can move this from + * a cpu pinned worker to an unbound one. We can operate on a different + * cpu which is allright but we also have to make sure to not move to + * a different one. + */ + preempt_disable(); + drain_local_pages(NULL); + preempt_enable(); +} + /* * Spill all the per-cpu pages from all CPUs back into the buddy allocator. * * When zone parameter is non-NULL, spill just the single zone's pages. * - * Note that this code is protected against sending an IPI to an offline - * CPU but does not guarantee sending an IPI to newly hotplugged CPUs: - * on_each_cpu_mask() blocks hotplug and won't talk to offlined CPUs but - * nothing keeps CPUs from showing up after we populated the cpumask and - * before the call to on_each_cpu_mask(). + * Note that this can be extremely slow as the draining happens in a workqueue. */ void drain_all_pages(struct zone *zone) { @@ -2363,6 +2358,28 @@ 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; + + /* + * Do not drain if one is already in progress unless it's specific to + * a zone. Such callers are primarily CMA and memory hotplug and need + * the drain to be complete when the call returns. + */ + if (unlikely(!mutex_trylock(&pcpu_drain_mutex))) { + if (!zone) + return; + mutex_lock(&pcpu_drain_mutex); + } + + /* * We don't care about racing with CPU hotplug event * as offline notification will cause the notified * cpu to drain that CPU pcps and on_each_cpu_mask @@ -2392,8 +2409,16 @@ void drain_all_pages(struct zone *zone) else cpumask_clear_cpu(cpu, &cpus_with_pcps); } - on_each_cpu_mask(&cpus_with_pcps, (smp_call_func_t) drain_local_pages, - zone, 1); + + for_each_cpu(cpu, &cpus_with_pcps) { + struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu); + INIT_WORK(work, drain_local_pages_wq); + queue_work_on(cpu, mm_percpu_wq, work); + } + for_each_cpu(cpu, &cpus_with_pcps) + flush_work(per_cpu_ptr(&pcpu_drain, cpu)); + + mutex_unlock(&pcpu_drain_mutex); } #ifdef CONFIG_HIBERNATION @@ -2459,7 +2484,7 @@ void free_hot_cold_page(struct page *page, bool cold) /* * 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 */ @@ -2569,7 +2594,7 @@ 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); } @@ -2602,74 +2627,104 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z) #endif } +/* Remove page from the per-cpu list, caller must protect the list */ +static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, + bool cold, struct per_cpu_pages *pcp, + struct list_head *list) +{ + struct page *page; + + do { + if (list_empty(list)) { + pcp->count += rmqueue_bulk(zone, 0, + pcp->batch, list, + migratetype, cold); + if (unlikely(list_empty(list))) + return NULL; + } + + if (cold) + page = list_last_entry(list, struct page, lru); + else + page = list_first_entry(list, struct page, lru); + + list_del(&page->lru); + pcp->count--; + } while (check_new_pcp(page)); + + return page; +} + +/* Lock and remove page from the per-cpu list */ +static struct page *rmqueue_pcplist(struct zone *preferred_zone, + struct zone *zone, unsigned int order, + gfp_t gfp_flags, int migratetype) +{ + struct per_cpu_pages *pcp; + struct list_head *list; + bool cold = ((gfp_flags & __GFP_COLD) != 0); + struct page *page; + unsigned long flags; + + local_irq_save(flags); + pcp = &this_cpu_ptr(zone->pageset)->pcp; + list = &pcp->lists[migratetype]; + page = __rmqueue_pcplist(zone, migratetype, cold, pcp, list); + if (page) { + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); + zone_statistics(preferred_zone, zone); + } + local_irq_restore(flags); + return page; +} + /* * Allocate a page from the given zone. Use pcplists for order-0 allocations. */ static inline -struct page *buffered_rmqueue(struct zone *preferred_zone, +struct page *rmqueue(struct zone *preferred_zone, struct zone *zone, unsigned int order, gfp_t gfp_flags, unsigned int alloc_flags, int migratetype) { unsigned long flags; struct page *page; - bool cold = ((gfp_flags & __GFP_COLD) != 0); if (likely(order == 0)) { - struct per_cpu_pages *pcp; - struct list_head *list; - - local_irq_save(flags); - do { - pcp = &this_cpu_ptr(zone->pageset)->pcp; - list = &pcp->lists[migratetype]; - if (list_empty(list)) { - pcp->count += rmqueue_bulk(zone, 0, - pcp->batch, list, - migratetype, cold); - if (unlikely(list_empty(list))) - goto failed; - } - - if (cold) - page = list_last_entry(list, struct page, lru); - else - page = list_first_entry(list, struct page, lru); - - list_del(&page->lru); - pcp->count--; + page = rmqueue_pcplist(preferred_zone, zone, order, + gfp_flags, migratetype); + goto out; + } - } while (check_new_pcp(page)); - } else { - /* - * We most definitely don't want callers attempting to - * allocate greater than order-1 page units with __GFP_NOFAIL. - */ - WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); - spin_lock_irqsave(&zone->lock, flags); + /* + * We most definitely don't want callers attempting to + * allocate greater than order-1 page units with __GFP_NOFAIL. + */ + WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); + spin_lock_irqsave(&zone->lock, flags); - do { - page = NULL; - if (alloc_flags & ALLOC_HARDER) { - page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); - if (page) - trace_mm_page_alloc_zone_locked(page, order, migratetype); - } - if (!page) - page = __rmqueue(zone, order, migratetype); - } while (page && check_new_pages(page, order)); - spin_unlock(&zone->lock); + do { + page = NULL; + if (alloc_flags & ALLOC_HARDER) { + page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); + if (page) + trace_mm_page_alloc_zone_locked(page, order, migratetype); + } if (!page) - goto failed; - __mod_zone_freepage_state(zone, -(1 << order), - get_pcppage_migratetype(page)); - } + page = __rmqueue(zone, order, migratetype); + } while (page && check_new_pages(page, order)); + spin_unlock(&zone->lock); + if (!page) + goto failed; + __mod_zone_freepage_state(zone, -(1 << order), + get_pcppage_migratetype(page)); __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); zone_statistics(preferred_zone, zone); local_irq_restore(flags); - VM_BUG_ON_PAGE(bad_range(zone, page), page); +out: + VM_BUG_ON_PAGE(page && bad_range(zone, page), page); return page; failed: @@ -2877,7 +2932,7 @@ bool zone_watermark_ok_safe(struct zone *z, unsigned int order, #ifdef CONFIG_NUMA static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { - return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) < + return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <= RECLAIM_DISTANCE; } #else /* CONFIG_NUMA */ @@ -2974,7 +3029,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, } try_this_zone: - page = buffered_rmqueue(ac->preferred_zoneref->zone, zone, order, + page = rmqueue(ac->preferred_zoneref->zone, zone, order, gfp_mask, alloc_flags, ac->migratetype); if (page) { prep_new_page(page, order, gfp_mask, alloc_flags); @@ -3007,18 +3062,12 @@ static inline bool should_suppress_show_mem(void) return ret; } -static DEFINE_RATELIMIT_STATE(nopage_rs, - DEFAULT_RATELIMIT_INTERVAL, - DEFAULT_RATELIMIT_BURST); - -void warn_alloc(gfp_t gfp_mask, const char *fmt, ...) +static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask) { unsigned int filter = SHOW_MEM_FILTER_NODES; - struct va_format vaf; - va_list args; + static DEFINE_RATELIMIT_STATE(show_mem_rs, HZ, 1); - if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs) || - debug_guardpage_minorder() > 0) + if (should_suppress_show_mem() || !__ratelimit(&show_mem_rs)) return; /* @@ -3033,6 +3082,19 @@ void warn_alloc(gfp_t gfp_mask, const char *fmt, ...) if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM)) filter &= ~SHOW_MEM_FILTER_NODES; + show_mem(filter, nodemask); +} + +void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + static DEFINE_RATELIMIT_STATE(nopage_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + + if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs)) + return; + pr_warn("%s: ", current->comm); va_start(args, fmt); @@ -3041,11 +3103,36 @@ void warn_alloc(gfp_t gfp_mask, const char *fmt, ...) pr_cont("%pV", &vaf); va_end(args); - pr_cont(", mode:%#x(%pGg)\n", gfp_mask, &gfp_mask); + pr_cont(", mode:%#x(%pGg), nodemask=", gfp_mask, &gfp_mask); + if (nodemask) + pr_cont("%*pbl\n", nodemask_pr_args(nodemask)); + else + pr_cont("(null)\n"); + + cpuset_print_current_mems_allowed(); dump_stack(); - if (!should_suppress_show_mem()) - show_mem(filter); + warn_alloc_show_mem(gfp_mask, nodemask); +} + +static inline struct page * +__alloc_pages_cpuset_fallback(gfp_t gfp_mask, unsigned int order, + unsigned int alloc_flags, + const struct alloc_context *ac) +{ + struct page *page; + + page = get_page_from_freelist(gfp_mask, order, + alloc_flags|ALLOC_CPUSET, ac); + /* + * fallback to ignore cpuset restriction if our nodes + * are depleted + */ + if (!page) + page = get_page_from_freelist(gfp_mask, order, + alloc_flags, ac); + + return page; } static inline struct page * @@ -3083,47 +3170,42 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, if (page) goto out; - if (!(gfp_mask & __GFP_NOFAIL)) { - /* Coredumps can quickly deplete all memory reserves */ - if (current->flags & PF_DUMPCORE) - goto out; - /* The OOM killer will not help higher order allocs */ - if (order > PAGE_ALLOC_COSTLY_ORDER) - goto out; - /* The OOM killer does not needlessly kill tasks for lowmem */ - if (ac->high_zoneidx < ZONE_NORMAL) - goto out; - if (pm_suspended_storage()) - goto out; - /* - * XXX: GFP_NOFS allocations should rather fail than rely on - * other request to make a forward progress. - * We are in an unfortunate situation where out_of_memory cannot - * do much for this context but let's try it to at least get - * access to memory reserved if the current task is killed (see - * out_of_memory). Once filesystems are ready to handle allocation - * failures more gracefully we should just bail out here. - */ + /* Coredumps can quickly deplete all memory reserves */ + if (current->flags & PF_DUMPCORE) + goto out; + /* The OOM killer will not help higher order allocs */ + if (order > PAGE_ALLOC_COSTLY_ORDER) + goto out; + /* The OOM killer does not needlessly kill tasks for lowmem */ + if (ac->high_zoneidx < ZONE_NORMAL) + goto out; + if (pm_suspended_storage()) + goto out; + /* + * XXX: GFP_NOFS allocations should rather fail than rely on + * other request to make a forward progress. + * We are in an unfortunate situation where out_of_memory cannot + * do much for this context but let's try it to at least get + * access to memory reserved if the current task is killed (see + * out_of_memory). Once filesystems are ready to handle allocation + * failures more gracefully we should just bail out here. + */ + + /* The OOM killer may not free memory on a specific node */ + if (gfp_mask & __GFP_THISNODE) + goto out; - /* The OOM killer may not free memory on a specific node */ - if (gfp_mask & __GFP_THISNODE) - goto out; - } /* Exhausted what can be done so it's blamo time */ if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) { *did_some_progress = 1; - if (gfp_mask & __GFP_NOFAIL) { - page = get_page_from_freelist(gfp_mask, order, - ALLOC_NO_WATERMARKS|ALLOC_CPUSET, ac); - /* - * fallback to ignore cpuset restriction if our nodes - * are depleted - */ - if (!page) - page = get_page_from_freelist(gfp_mask, order, + /* + * Help non-failing allocations by giving them access to memory + * reserves + */ + if (gfp_mask & __GFP_NOFAIL) + page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_NO_WATERMARKS, ac); - } } out: mutex_unlock(&oom_lock); @@ -3192,6 +3274,9 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, { int max_retries = MAX_COMPACT_RETRIES; int min_priority; + bool ret = false; + int retries = *compaction_retries; + enum compact_priority priority = *compact_priority; if (!order) return false; @@ -3213,8 +3298,10 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, * But do not retry if the given zonelist is not suitable for * compaction. */ - if (compaction_withdrawn(compact_result)) - return compaction_zonelist_suitable(ac, order, alloc_flags); + if (compaction_withdrawn(compact_result)) { + ret = compaction_zonelist_suitable(ac, order, alloc_flags); + goto out; + } /* * !costly requests are much more important than __GFP_REPEAT @@ -3226,8 +3313,10 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, */ if (order > PAGE_ALLOC_COSTLY_ORDER) max_retries /= 4; - if (*compaction_retries <= max_retries) - return true; + if (*compaction_retries <= max_retries) { + ret = true; + goto out; + } /* * Make sure there are attempts at the highest priority if we exhausted @@ -3236,12 +3325,15 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, check_priority: min_priority = (order > PAGE_ALLOC_COSTLY_ORDER) ? MIN_COMPACT_COSTLY_PRIORITY : MIN_COMPACT_PRIORITY; + if (*compact_priority > min_priority) { (*compact_priority)--; *compaction_retries = 0; - return true; + ret = true; } - return false; +out: + trace_compact_retry(order, priority, compact_result, retries, max_retries, ret); + return ret; } #else static inline struct page * @@ -3411,19 +3503,12 @@ 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. */ @@ -3464,18 +3549,21 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, ac->nodemask) { unsigned long available; unsigned long reclaimable; + unsigned long min_wmark = min_wmark_pages(zone); + 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? */ - if (__zone_watermark_ok(zone, order, min_wmark_pages(zone), - ac_classzone_idx(ac), alloc_flags, available)) { + wmark = __zone_watermark_ok(zone, order, min_wmark, + ac_classzone_idx(ac), alloc_flags, available); + trace_reclaim_retry_zone(z, order, reclaimable, + available, min_wmark, *no_progress_loops, wmark); + if (wmark) { /* * If we didn't make any progress and have a lot of * dirty + writeback pages then we should wait for @@ -3555,6 +3643,14 @@ retry_cpuset: no_progress_loops = 0; compact_priority = DEF_COMPACT_PRIORITY; cpuset_mems_cookie = read_mems_allowed_begin(); + + /* + * The fast path uses conservative alloc_flags to succeed only until + * kswapd needs to be woken up, and to avoid the cost of setting up + * alloc_flags precisely. So we do that now. + */ + alloc_flags = gfp_to_alloc_flags(gfp_mask); + /* * We need to recalculate the starting point for the zonelist iterator * because we might have used different nodemask in the fast path, or @@ -3566,14 +3662,6 @@ retry_cpuset: if (!ac->preferred_zoneref->zone) goto nopage; - - /* - * The fast path uses conservative alloc_flags to succeed only until - * kswapd needs to be woken up, and to avoid the cost of setting up - * alloc_flags precisely. So we do that now. - */ - alloc_flags = gfp_to_alloc_flags(gfp_mask); - if (gfp_mask & __GFP_KSWAPD_RECLAIM) wake_all_kswapds(order, ac); @@ -3650,35 +3738,21 @@ retry: goto got_pg; /* Caller is not willing to reclaim, we can't balance anything */ - if (!can_direct_reclaim) { - /* - * All existing users of the __GFP_NOFAIL are blockable, so warn - * of any new users that actually allow this type of allocation - * to fail. - */ - WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL); + if (!can_direct_reclaim) goto nopage; - } - /* Avoid recursion of direct reclaim */ - if (current->flags & PF_MEMALLOC) { - /* - * __GFP_NOFAIL request from this context is rather bizarre - * because we cannot reclaim anything and only can loop waiting - * for somebody to do a work for us. - */ - if (WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) { - cond_resched(); - goto retry; - } - goto nopage; + /* Make sure we know about allocations which stall for too long */ + if (time_after(jiffies, alloc_start + stall_timeout)) { + 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; } - /* Avoid allocations with no watermarks from looping endlessly */ - if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL)) + /* Avoid recursion of direct reclaim */ + if (current->flags & PF_MEMALLOC) goto nopage; - /* Try direct reclaim and then allocating */ page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac, &did_some_progress); @@ -3702,14 +3776,6 @@ retry: if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_REPEAT)) goto nopage; - /* Make sure we know about allocations which stall for too long */ - if (time_after(jiffies, alloc_start + stall_timeout)) { - warn_alloc(gfp_mask, - "page allocation stalls for %ums, order:%u", - jiffies_to_msecs(jiffies-alloc_start), order); - stall_timeout += 10 * HZ; - } - if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags, did_some_progress > 0, &no_progress_loops)) goto retry; @@ -3738,6 +3804,10 @@ retry: if (page) goto got_pg; + /* Avoid allocations with no watermarks from looping endlessly */ + if (test_thread_flag(TIF_MEMDIE)) + goto nopage; + /* Retry as long as the OOM killer is making progress */ if (did_some_progress) { no_progress_loops = 0; @@ -3755,87 +3825,130 @@ nopage: if (read_mems_allowed_retry(cpuset_mems_cookie)) goto retry_cpuset; - warn_alloc(gfp_mask, + /* + * Make sure that __GFP_NOFAIL request doesn't leak out and make sure + * we always retry + */ + if (gfp_mask & __GFP_NOFAIL) { + /* + * All existing users of the __GFP_NOFAIL are blockable, so warn + * of any new users that actually require GFP_NOWAIT + */ + if (WARN_ON_ONCE(!can_direct_reclaim)) + goto fail; + + /* + * PF_MEMALLOC request from this context is rather bizarre + * because we cannot reclaim anything and only can loop waiting + * for somebody to do a work for us + */ + WARN_ON_ONCE(current->flags & PF_MEMALLOC); + + /* + * non failing costly orders are a hard requirement which we + * are not prepared for much so let's warn about these users + * so that we can identify them and convert them to something + * else. + */ + WARN_ON_ONCE(order > PAGE_ALLOC_COSTLY_ORDER); + + /* + * Help non-failing allocations by giving them access to memory + * reserves but do not use ALLOC_NO_WATERMARKS because this + * could deplete whole memory reserves which would just make + * the situation worse + */ + page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_HARDER, ac); + if (page) + goto got_pg; + + cond_resched(); + goto retry; + } +fail: + warn_alloc(gfp_mask, ac->nodemask, "page allocation failure: order:%u", order); got_pg: return page; } -/* - * This is the 'heart' of the zoned buddy allocator. - */ -struct page * -__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, nodemask_t *nodemask) +static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, nodemask_t *nodemask, + struct alloc_context *ac, gfp_t *alloc_mask, + unsigned int *alloc_flags) { - struct page *page; - unsigned int alloc_flags = ALLOC_WMARK_LOW; - gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */ - struct alloc_context ac = { - .high_zoneidx = gfp_zone(gfp_mask), - .zonelist = zonelist, - .nodemask = nodemask, - .migratetype = gfpflags_to_migratetype(gfp_mask), - }; + ac->high_zoneidx = gfp_zone(gfp_mask); + ac->zonelist = zonelist; + ac->nodemask = nodemask; + ac->migratetype = gfpflags_to_migratetype(gfp_mask); if (cpusets_enabled()) { - alloc_mask |= __GFP_HARDWALL; - alloc_flags |= ALLOC_CPUSET; - if (!ac.nodemask) - ac.nodemask = &cpuset_current_mems_allowed; + *alloc_mask |= __GFP_HARDWALL; + if (!ac->nodemask) + ac->nodemask = &cpuset_current_mems_allowed; + else + *alloc_flags |= ALLOC_CPUSET; } - gfp_mask &= gfp_allowed_mask; - lockdep_trace_alloc(gfp_mask); might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM); if (should_fail_alloc_page(gfp_mask, order)) - return NULL; + return false; - /* - * Check the zones suitable for the gfp_mask contain at least one - * valid zone. It's possible to have an empty zonelist as a result - * of __GFP_THISNODE and a memoryless node - */ - if (unlikely(!zonelist->_zonerefs->zone)) - return NULL; + if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE) + *alloc_flags |= ALLOC_CMA; - if (IS_ENABLED(CONFIG_CMA) && ac.migratetype == MIGRATE_MOVABLE) - alloc_flags |= ALLOC_CMA; + return true; +} +/* Determine whether to spread dirty pages and what the first usable zone */ +static inline void finalise_ac(gfp_t gfp_mask, + unsigned int order, struct alloc_context *ac) +{ /* Dirty zone balancing only done in the fast path */ - ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE); + ac->spread_dirty_pages = (gfp_mask & __GFP_WRITE); /* * The preferred zone is used for statistics but crucially it is * also used as the starting point for the zonelist iterator. It * may get reset for allocations that ignore memory policies. */ - ac.preferred_zoneref = first_zones_zonelist(ac.zonelist, - ac.high_zoneidx, ac.nodemask); - if (!ac.preferred_zoneref->zone) { - page = NULL; - /* - * This might be due to race with cpuset_current_mems_allowed - * update, so make sure we retry with original nodemask in the - * slow path. - */ - goto no_zone; - } + ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, + ac->high_zoneidx, ac->nodemask); +} + +/* + * This is the 'heart' of the zoned buddy allocator. + */ +struct page * +__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, nodemask_t *nodemask) +{ + struct page *page; + unsigned int alloc_flags = ALLOC_WMARK_LOW; + gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */ + struct alloc_context ac = { }; + + gfp_mask &= gfp_allowed_mask; + if (!prepare_alloc_pages(gfp_mask, order, zonelist, nodemask, &ac, &alloc_mask, &alloc_flags)) + return NULL; + + finalise_ac(gfp_mask, order, &ac); /* First allocation attempt */ page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac); if (likely(page)) goto out; -no_zone: /* - * 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; /* @@ -4108,7 +4221,8 @@ 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) { @@ -4252,20 +4366,20 @@ void si_meminfo_node(struct sysinfo *val, int nid) * Determine whether the node should be displayed or not, depending on whether * SHOW_MEM_FILTER_NODES was passed to show_free_areas(). */ -bool skip_free_areas_node(unsigned int flags, int nid) +static bool show_mem_node_skip(unsigned int flags, int nid, nodemask_t *nodemask) { - bool ret = false; - unsigned int cpuset_mems_cookie; - if (!(flags & SHOW_MEM_FILTER_NODES)) - goto out; + return false; - do { - cpuset_mems_cookie = read_mems_allowed_begin(); - ret = !node_isset(nid, cpuset_current_mems_allowed); - } while (read_mems_allowed_retry(cpuset_mems_cookie)); -out: - return ret; + /* + * no node mask - aka implicit memory numa policy. Do not bother with + * the synchronization - read_mems_allowed_begin - because we do not + * have to be precise here. + */ + if (!nodemask) + nodemask = &cpuset_current_mems_allowed; + + return !node_isset(nid, *nodemask); } #define K(x) ((x) << (PAGE_SHIFT-10)) @@ -4306,7 +4420,7 @@ static void show_migration_types(unsigned char type) * SHOW_MEM_FILTER_NODES: suppress nodes that are not allowed by current's * cpuset. */ -void show_free_areas(unsigned int filter) +void show_free_areas(unsigned int filter, nodemask_t *nodemask) { unsigned long free_pcp = 0; int cpu; @@ -4314,7 +4428,7 @@ void show_free_areas(unsigned int filter) pg_data_t *pgdat; for_each_populated_zone(zone) { - if (skip_free_areas_node(filter, zone_to_nid(zone))) + if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask)) continue; for_each_online_cpu(cpu) @@ -4348,6 +4462,9 @@ void show_free_areas(unsigned int filter) global_page_state(NR_FREE_CMA_PAGES)); for_each_online_pgdat(pgdat) { + if (show_mem_node_skip(filter, pgdat->node_id, nodemask)) + continue; + printk("Node %d" " active_anon:%lukB" " inactive_anon:%lukB" @@ -4367,7 +4484,6 @@ void show_free_areas(unsigned int filter) #endif " writeback_tmp:%lukB" " unstable:%lukB" - " pages_scanned:%lu" " all_unreclaimable? %s" "\n", pgdat->node_id, @@ -4381,23 +4497,23 @@ void show_free_areas(unsigned int filter) 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) { int i; - if (skip_free_areas_node(filter, zone_to_nid(zone))) + if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask)) continue; free_pcp = 0; @@ -4462,7 +4578,7 @@ void show_free_areas(unsigned int filter) unsigned long nr[MAX_ORDER], flags, total = 0; unsigned char types[MAX_ORDER]; - if (skip_free_areas_node(filter, zone_to_nid(zone))) + if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask)) continue; show_node(zone); printk(KERN_CONT "%s: ", zone->name); @@ -5083,8 +5199,17 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, if (context != MEMMAP_EARLY) goto not_early; - if (!early_pfn_valid(pfn)) + if (!early_pfn_valid(pfn)) { +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP + /* + * Skip to the pfn preceding the next valid one (or + * end_pfn), such that we hit a valid pfn (or end_pfn) + * on our next iteration of the loop. + */ + pfn = memblock_next_valid_pfn(pfn, end_pfn) - 1; +#endif continue; + } if (!early_pfn_in_nid(pfn, nid)) continue; if (!update_defer_init(pgdat, pfn, end_pfn, &nr_initialised)) @@ -5780,7 +5905,7 @@ static unsigned long __paginginit calc_memmap_size(unsigned long spanned_pages, * the zone and SPARSEMEM is in use. If there are holes within the * zone, each populated memory region may cost us one or two extra * memmap pages due to alignment because memmap pages for each - * populated regions may not naturally algined on page boundary. + * populated regions may not be naturally aligned on page boundary. * So the (present_pages >> 4) heuristic is a tradeoff for that. */ if (spanned_pages > present_pages + (present_pages >> 4) && @@ -6344,8 +6469,6 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) start_pfn = end_pfn; } - arch_zone_lowest_possible_pfn[ZONE_MOVABLE] = 0; - arch_zone_highest_possible_pfn[ZONE_MOVABLE] = 0; /* Find the PFNs that ZONE_MOVABLE begins at in each node */ memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn)); @@ -7081,8 +7204,9 @@ void *__init alloc_large_system_hash(const char *tablename, * If @count is not zero, it is okay to include less @count unmovable pages * * PageLRU check without isolation or lru_lock could race so that - * MIGRATE_MOVABLE block might include unmovable pages. It means you can't - * expect this function should be exact. + * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable + * check without lock_page also may miss some movable non-lru pages at + * race condition. So you can't expect this function should be exact. */ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, bool skip_hwpoisoned_pages) @@ -7138,6 +7262,9 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, if (skip_hwpoisoned_pages && PageHWPoison(page)) continue; + if (__PageMovable(page)) + continue; + if (!PageLRU(page)) found++; /* @@ -7249,6 +7376,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, * #MIGRATE_MOVABLE or #MIGRATE_CMA). All pageblocks * in range must have the same migratetype and it must * be either of the two. + * @gfp_mask: GFP mask to use during compaction * * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES * aligned, however it's the caller's responsibility to guarantee that @@ -7262,7 +7390,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, * need to be freed with free_contig_range(). */ int alloc_contig_range(unsigned long start, unsigned long end, - unsigned migratetype) + unsigned migratetype, gfp_t gfp_mask) { unsigned long outer_start, outer_end; unsigned int order; @@ -7274,7 +7402,7 @@ 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 = GFP_KERNEL, + .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 ae11aa914e55..1b0f48c62316 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -50,31 +50,31 @@ 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) { - struct mm_struct *mm = vma->vm_mm; - pmd_t *pmd; - pte_t *pte; - spinlock_t *ptl; + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = addr, + }; bool referenced = false; - if (!page_check_address_transhuge(page, mm, addr, &pmd, &pte, &ptl)) - return SWAP_AGAIN; - - if (pte) { - referenced = ptep_clear_young_notify(vma, addr, pte); - pte_unmap(pte); - } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { - referenced = pmdp_clear_young_notify(vma, addr, pmd); - } else { - /* unexpected pmd-mapped page? */ - WARN_ON_ONCE(1); + while (page_vma_mapped_walk(&pvmw)) { + addr = pvmw.address; + if (pvmw.pte) { + referenced = ptep_clear_young_notify(vma, addr, + pvmw.pte); + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + referenced = pmdp_clear_young_notify(vma, addr, + pvmw.pmd); + } else { + /* unexpected pmd-mapped page? */ + WARN_ON_ONCE(1); + } } - spin_unlock(ptl); - if (referenced) { clear_page_idle(page); /* @@ -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 a5594bfcc5ed..7927bbb54a4e 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -83,12 +83,12 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype) unsigned long flags, nr_pages; bool isolated_page = false; unsigned int order; - unsigned long page_idx, buddy_idx; + unsigned long pfn, buddy_pfn; struct page *buddy; 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; /* @@ -102,11 +102,11 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype) if (PageBuddy(page)) { order = page_order(page); if (order >= pageblock_order) { - page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); - buddy_idx = __find_buddy_index(page_idx, order); - buddy = page + (buddy_idx - page_idx); + pfn = page_to_pfn(page); + buddy_pfn = __find_buddy_pfn(pfn, order); + buddy = page + (buddy_pfn - pfn); - if (pfn_valid_within(page_to_pfn(buddy)) && + if (pfn_valid_within(buddy_pfn) && !is_migrate_isolate_page(buddy)) { __isolate_free_page(page, order); isolated_page = true; @@ -205,7 +205,7 @@ 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 +262,7 @@ 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 new file mode 100644 index 000000000000..de9c40d7304a --- /dev/null +++ b/mm/page_vma_mapped.c @@ -0,0 +1,223 @@ +#include <linux/mm.h> +#include <linux/rmap.h> +#include <linux/hugetlb.h> +#include <linux/swap.h> +#include <linux/swapops.h> + +#include "internal.h" + +static inline bool check_pmd(struct page_vma_mapped_walk *pvmw) +{ + pmd_t pmde; + /* + * Make sure we don't re-load pmd between present and !trans_huge check. + * We need a consistent view. + */ + pmde = READ_ONCE(*pvmw->pmd); + return pmd_present(pmde) && !pmd_trans_huge(pmde); +} + +static inline bool not_found(struct page_vma_mapped_walk *pvmw) +{ + page_vma_mapped_walk_done(pvmw); + return false; +} + +static bool map_pte(struct page_vma_mapped_walk *pvmw) +{ + pvmw->pte = pte_offset_map(pvmw->pmd, pvmw->address); + if (!(pvmw->flags & PVMW_SYNC)) { + if (pvmw->flags & PVMW_MIGRATION) { + if (!is_swap_pte(*pvmw->pte)) + return false; + } else { + if (!pte_present(*pvmw->pte)) + return false; + } + } + pvmw->ptl = pte_lockptr(pvmw->vma->vm_mm, pvmw->pmd); + spin_lock(pvmw->ptl); + return true; +} + +static bool check_pte(struct page_vma_mapped_walk *pvmw) +{ + if (pvmw->flags & PVMW_MIGRATION) { +#ifdef CONFIG_MIGRATION + swp_entry_t entry; + if (!is_swap_pte(*pvmw->pte)) + return false; + entry = pte_to_swp_entry(*pvmw->pte); + if (!is_migration_entry(entry)) + return false; + if (migration_entry_to_page(entry) - pvmw->page >= + hpage_nr_pages(pvmw->page)) { + return false; + } + if (migration_entry_to_page(entry) < pvmw->page) + return false; +#else + WARN_ON_ONCE(1); +#endif + } else { + if (!pte_present(*pvmw->pte)) + return false; + + /* THP can be referenced by any subpage */ + if (pte_page(*pvmw->pte) - pvmw->page >= + hpage_nr_pages(pvmw->page)) { + return false; + } + if (pte_page(*pvmw->pte) < pvmw->page) + return false; + } + + return true; +} + +/** + * page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at + * @pvmw->address + * @pvmw: pointer to struct page_vma_mapped_walk. page, vma, address and flags + * must be set. pmd, pte and ptl must be NULL. + * + * Returns true if the page is mapped in the vma. @pvmw->pmd and @pvmw->pte point + * to relevant page table entries. @pvmw->ptl is locked. @pvmw->address is + * adjusted if needed (for PTE-mapped THPs). + * + * If @pvmw->pmd is set but @pvmw->pte is not, you have found PMD-mapped page + * (usually THP). For PTE-mapped THP, you should run page_vma_mapped_walk() in + * a loop to find all PTEs that map the THP. + * + * For HugeTLB pages, @pvmw->pte is set to the relevant page table entry + * regardless of which page table level the page is mapped at. @pvmw->pmd is + * NULL. + * + * Retruns false if there are no more page table entries for the page in + * the vma. @pvmw->ptl is unlocked and @pvmw->pte is unmapped. + * + * If you need to stop the walk before page_vma_mapped_walk() returned false, + * use page_vma_mapped_walk_done(). It will do the housekeeping. + */ +bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) +{ + struct mm_struct *mm = pvmw->vma->vm_mm; + struct page *page = pvmw->page; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + + /* The only possible pmd mapping has been handled on last iteration */ + if (pvmw->pmd && !pvmw->pte) + return not_found(pvmw); + + if (pvmw->pte) + goto next_pte; + + if (unlikely(PageHuge(pvmw->page))) { + /* when pud is not present, pte will be NULL */ + pvmw->pte = huge_pte_offset(mm, pvmw->address); + if (!pvmw->pte) + return false; + + pvmw->ptl = huge_pte_lockptr(page_hstate(page), mm, pvmw->pte); + spin_lock(pvmw->ptl); + if (!check_pte(pvmw)) + return not_found(pvmw); + return true; + } +restart: + pgd = pgd_offset(mm, pvmw->address); + if (!pgd_present(*pgd)) + return false; + p4d = p4d_offset(pgd, pvmw->address); + if (!p4d_present(*p4d)) + return false; + pud = pud_offset(p4d, pvmw->address); + if (!pud_present(*pud)) + return false; + pvmw->pmd = pmd_offset(pud, pvmw->address); + if (pmd_trans_huge(*pvmw->pmd)) { + pvmw->ptl = pmd_lock(mm, pvmw->pmd); + if (!pmd_present(*pvmw->pmd)) + return not_found(pvmw); + if (likely(pmd_trans_huge(*pvmw->pmd))) { + if (pvmw->flags & PVMW_MIGRATION) + return not_found(pvmw); + if (pmd_page(*pvmw->pmd) != page) + return not_found(pvmw); + return true; + } else { + /* THP pmd was split under us: handle on pte level */ + spin_unlock(pvmw->ptl); + pvmw->ptl = NULL; + } + } else { + if (!check_pmd(pvmw)) + return false; + } + if (!map_pte(pvmw)) + goto next_pte; + while (1) { + if (check_pte(pvmw)) + return true; +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 >= pvmw->vma->vm_end || + pvmw->address >= + __vma_address(pvmw->page, pvmw->vma) + + hpage_nr_pages(pvmw->page) * PAGE_SIZE) + return not_found(pvmw); + /* Did we cross page table boundary? */ + if (pvmw->address % PMD_SIZE == 0) { + pte_unmap(pvmw->pte); + if (pvmw->ptl) { + spin_unlock(pvmw->ptl); + pvmw->ptl = NULL; + } + goto restart; + } else { + pvmw->pte++; + } + } while (pte_none(*pvmw->pte)); + + if (!pvmw->ptl) { + pvmw->ptl = pte_lockptr(mm, pvmw->pmd); + spin_lock(pvmw->ptl); + } + } +} + +/** + * page_mapped_in_vma - check whether a page is really mapped in a VMA + * @page: the page to test + * @vma: the VMA to test + * + * Returns 1 if the page is mapped into the page tables of the VMA, 0 + * if the page is not mapped into the page tables of this VMA. Only + * valid for normal file or anonymous VMAs. + */ +int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) +{ + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .flags = PVMW_SYNC, + }; + unsigned long start, end; + + start = __vma_address(page, vma); + end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1); + + if (unlikely(end < vma->vm_start || start >= vma->vm_end)) + return 0; + pvmw.address = max(start, vma->vm_start); + if (!page_vma_mapped_walk(&pvmw)) + return 0; + page_vma_mapped_walk_done(&pvmw); + return 1; +} diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 207244489a68..60f7856e508f 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -69,23 +69,41 @@ again: return err; } -static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, +static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, struct mm_walk *walk) { pud_t *pud; unsigned long next; int err = 0; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { + again: next = pud_addr_end(addr, end); - if (pud_none_or_clear_bad(pud)) { + if (pud_none(*pud) || !walk->vma) { if (walk->pte_hole) err = walk->pte_hole(addr, next, walk); if (err) break; continue; } + + if (walk->pud_entry) { + spinlock_t *ptl = pud_trans_huge_lock(pud, walk->vma); + + if (ptl) { + err = walk->pud_entry(pud, addr, next, walk); + spin_unlock(ptl); + if (err) + break; + continue; + } + } + + split_huge_pud(walk->vma, pud, addr); + if (pud_none(*pud)) + goto again; + if (walk->pmd_entry || walk->pte_entry) err = walk_pmd_range(pud, addr, next, walk); if (err) @@ -95,6 +113,32 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, return err; } +static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + p4d_t *p4d; + unsigned long next; + int err = 0; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) { + if (walk->pte_hole) + err = walk->pte_hole(addr, next, walk); + if (err) + break; + continue; + } + if (walk->pmd_entry || walk->pte_entry) + err = walk_pud_range(p4d, addr, next, walk); + if (err) + break; + } while (p4d++, addr = next, addr != end); + + return err; +} + static int walk_pgd_range(unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -113,7 +157,7 @@ static int walk_pgd_range(unsigned long addr, unsigned long end, continue; } if (walk->pmd_entry || walk->pte_entry) - err = walk_pud_range(pgd, addr, next, walk); + err = walk_p4d_range(pgd, addr, next, walk); if (err) break; } while (pgd++, addr = next, addr != end); diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index 538998a137d2..9ac639499bd1 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -21,7 +21,6 @@ static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, /** * pcpu_get_pages - get temp pages array - * @chunk: chunk of interest * * Returns pointer to array of pointers to struct page which can be indexed * with pcpu_page_idx(). Note that there is only one array and accesses @@ -30,7 +29,7 @@ static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, * RETURNS: * Pointer to temp pages array on success. */ -static struct page **pcpu_get_pages(struct pcpu_chunk *chunk_alloc) +static struct page **pcpu_get_pages(void) { static struct page **pages; size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]); @@ -275,7 +274,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, { struct page **pages; - pages = pcpu_get_pages(chunk); + pages = pcpu_get_pages(); if (!pages) return -ENOMEM; @@ -313,7 +312,7 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, * successful population attempt so the temp pages array must * be available now. */ - pages = pcpu_get_pages(chunk); + pages = pcpu_get_pages(); BUG_ON(!pages); /* unmap and free */ diff --git a/mm/percpu.c b/mm/percpu.c index 0686f566d347..e0aa8ae7bde7 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -43,7 +43,7 @@ * Chunks can be determined from the address using the index field * in the page struct. The index field contains a pointer to the chunk. * - * To use this allocator, arch code should do the followings. + * To use this allocator, arch code should do the following: * * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate * regular address to percpu pointer and back if they need to be @@ -1011,8 +1011,11 @@ area_found: mutex_unlock(&pcpu_alloc_mutex); } - if (chunk != pcpu_reserved_chunk) + if (chunk != pcpu_reserved_chunk) { + spin_lock_irqsave(&pcpu_lock, flags); pcpu_nr_empty_pop_pages -= occ_pages; + spin_unlock_irqrestore(&pcpu_lock, flags); + } if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW) pcpu_schedule_balance_work(); @@ -1281,18 +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; @@ -1301,16 +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/pgtable-generic.c b/mm/pgtable-generic.c index 71c5f9109f2a..c99d9512a45b 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -22,6 +22,12 @@ void pgd_clear_bad(pgd_t *pgd) pgd_clear(pgd); } +void p4d_clear_bad(p4d_t *p4d) +{ + p4d_ERROR(*p4d); + p4d_clear(p4d); +} + void pud_clear_bad(pud_t *pud) { pud_ERROR(*pud); @@ -123,6 +129,20 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; } + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, + pud_t *pudp) +{ + pud_t pud; + + VM_BUG_ON(address & ~HPAGE_PUD_MASK); + VM_BUG_ON(!pud_trans_huge(*pudp) && !pud_devmap(*pudp)); + pud = pudp_huge_get_and_clear(vma->vm_mm, address, pudp); + flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE); + return pud; +} +#endif #endif #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index 84d0c7eada2b..8973cd231ece 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -12,6 +12,7 @@ #include <linux/mm.h> #include <linux/uio.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/highmem.h> #include <linux/ptrace.h> #include <linux/slab.h> diff --git a/mm/rmap.c b/mm/rmap.c index 91619fd70939..3ff241f714eb 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -46,6 +46,8 @@ */ #include <linux/mm.h> +#include <linux/sched/mm.h> +#include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/swapops.h> @@ -607,8 +609,7 @@ void try_to_unmap_flush_dirty(void) try_to_unmap_flush(); } -static void set_tlb_ubc_flush_pending(struct mm_struct *mm, - struct page *page, bool writable) +static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; @@ -643,8 +644,7 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) return should_defer; } #else -static void set_tlb_ubc_flush_pending(struct mm_struct *mm, - struct page *page, bool writable) +static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) { } @@ -684,6 +684,7 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd = NULL; pmd_t pmde; @@ -692,7 +693,11 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) if (!pgd_present(*pgd)) goto out; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + goto out; + + pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; @@ -710,170 +715,6 @@ out: return pmd; } -/* - * Check that @page is mapped at @address into @mm. - * - * If @sync is false, page_check_address may perform a racy check to avoid - * the page table lock when the pte is not present (helpful when reclaiming - * highly shared pages). - * - * On success returns with pte mapped and locked. - */ -pte_t *__page_check_address(struct page *page, struct mm_struct *mm, - unsigned long address, spinlock_t **ptlp, int sync) -{ - pmd_t *pmd; - pte_t *pte; - spinlock_t *ptl; - - if (unlikely(PageHuge(page))) { - /* when pud is not present, pte will be NULL */ - pte = huge_pte_offset(mm, address); - if (!pte) - return NULL; - - ptl = huge_pte_lockptr(page_hstate(page), mm, pte); - goto check; - } - - pmd = mm_find_pmd(mm, address); - if (!pmd) - return NULL; - - pte = pte_offset_map(pmd, address); - /* Make a quick check before getting the lock */ - if (!sync && !pte_present(*pte)) { - pte_unmap(pte); - return NULL; - } - - ptl = pte_lockptr(mm, pmd); -check: - spin_lock(ptl); - if (pte_present(*pte) && page_to_pfn(page) == pte_pfn(*pte)) { - *ptlp = ptl; - return pte; - } - pte_unmap_unlock(pte, ptl); - return NULL; -} - -/** - * page_mapped_in_vma - check whether a page is really mapped in a VMA - * @page: the page to test - * @vma: the VMA to test - * - * Returns 1 if the page is mapped into the page tables of the VMA, 0 - * if the page is not mapped into the page tables of this VMA. Only - * valid for normal file or anonymous VMAs. - */ -int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) -{ - unsigned long address; - pte_t *pte; - spinlock_t *ptl; - - address = __vma_address(page, vma); - if (unlikely(address < vma->vm_start || address >= vma->vm_end)) - return 0; - pte = page_check_address(page, vma->vm_mm, address, &ptl, 1); - if (!pte) /* the page is not in this mm */ - return 0; - pte_unmap_unlock(pte, ptl); - - return 1; -} - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -/* - * Check that @page is mapped at @address into @mm. In contrast to - * page_check_address(), this function can handle transparent huge pages. - * - * On success returns true with pte mapped and locked. For PMD-mapped - * transparent huge pages *@ptep is set to NULL. - */ -bool page_check_address_transhuge(struct page *page, struct mm_struct *mm, - unsigned long address, pmd_t **pmdp, - pte_t **ptep, spinlock_t **ptlp) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - spinlock_t *ptl; - - if (unlikely(PageHuge(page))) { - /* when pud is not present, pte will be NULL */ - pte = huge_pte_offset(mm, address); - if (!pte) - return false; - - ptl = huge_pte_lockptr(page_hstate(page), mm, pte); - pmd = NULL; - goto check_pte; - } - - pgd = pgd_offset(mm, address); - if (!pgd_present(*pgd)) - return false; - pud = pud_offset(pgd, address); - if (!pud_present(*pud)) - return false; - pmd = pmd_offset(pud, address); - - if (pmd_trans_huge(*pmd)) { - ptl = pmd_lock(mm, pmd); - if (!pmd_present(*pmd)) - goto unlock_pmd; - if (unlikely(!pmd_trans_huge(*pmd))) { - spin_unlock(ptl); - goto map_pte; - } - - if (pmd_page(*pmd) != page) - goto unlock_pmd; - - pte = NULL; - goto found; -unlock_pmd: - spin_unlock(ptl); - return false; - } else { - pmd_t pmde = *pmd; - - barrier(); - if (!pmd_present(pmde) || pmd_trans_huge(pmde)) - return false; - } -map_pte: - pte = pte_offset_map(pmd, address); - if (!pte_present(*pte)) { - pte_unmap(pte); - return false; - } - - ptl = pte_lockptr(mm, pmd); -check_pte: - spin_lock(ptl); - - if (!pte_present(*pte)) { - pte_unmap_unlock(pte, ptl); - return false; - } - - /* THP can be referenced by any subpage */ - if (pte_pfn(*pte) - page_to_pfn(page) >= hpage_nr_pages(page)) { - pte_unmap_unlock(pte, ptl); - return false; - } -found: - *ptep = pte; - *pmdp = pmd; - *ptlp = ptl; - return true; -} -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ - struct page_referenced_arg { int mapcount; int referenced; @@ -883,48 +724,51 @@ 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 mm_struct *mm = vma->vm_mm; struct page_referenced_arg *pra = arg; - pmd_t *pmd; - pte_t *pte; - spinlock_t *ptl; + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = address, + }; int referenced = 0; - if (!page_check_address_transhuge(page, mm, address, &pmd, &pte, &ptl)) - return SWAP_AGAIN; + while (page_vma_mapped_walk(&pvmw)) { + address = pvmw.address; - if (vma->vm_flags & VM_LOCKED) { - if (pte) - pte_unmap(pte); - spin_unlock(ptl); - pra->vm_flags |= VM_LOCKED; - return SWAP_FAIL; /* To break the loop */ - } + if (vma->vm_flags & VM_LOCKED) { + page_vma_mapped_walk_done(&pvmw); + pra->vm_flags |= VM_LOCKED; + return false; /* To break the loop */ + } - if (pte) { - if (ptep_clear_flush_young_notify(vma, address, pte)) { - /* - * Don't treat a reference through a sequentially read - * mapping as such. If the page has been used in - * another mapping, we will catch it; if this other - * mapping is already gone, the unmap path will have - * set PG_referenced or activated the page. - */ - if (likely(!(vma->vm_flags & VM_SEQ_READ))) + if (pvmw.pte) { + if (ptep_clear_flush_young_notify(vma, address, + pvmw.pte)) { + /* + * Don't treat a reference through + * a sequentially read mapping as such. + * If the page has been used in another mapping, + * we will catch it; if this other mapping is + * already gone, the unmap path will have set + * PG_referenced or activated the page. + */ + if (likely(!(vma->vm_flags & VM_SEQ_READ))) + referenced++; + } + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + if (pmdp_clear_flush_young_notify(vma, address, + pvmw.pmd)) referenced++; + } else { + /* unexpected pmd-mapped page? */ + WARN_ON_ONCE(1); } - pte_unmap(pte); - } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { - if (pmdp_clear_flush_young_notify(vma, address, pmd)) - referenced++; - } else { - /* unexpected pmd-mapped page? */ - WARN_ON_ONCE(1); + + pra->mapcount--; } - spin_unlock(ptl); if (referenced) clear_page_idle(page); @@ -936,11 +780,10 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma, pra->vm_flags |= vma->vm_flags; } - pra->mapcount--; 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) @@ -969,7 +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), @@ -1003,7 +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) @@ -1012,38 +854,60 @@ 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 mm_struct *mm = vma->vm_mm; - pte_t *pte; - spinlock_t *ptl; - int ret = 0; + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = address, + .flags = PVMW_SYNC, + }; int *cleaned = arg; - pte = page_check_address(page, mm, address, &ptl, 1); - if (!pte) - goto out; - - if (pte_dirty(*pte) || pte_write(*pte)) { - pte_t entry; + while (page_vma_mapped_walk(&pvmw)) { + int ret = 0; + address = pvmw.address; + if (pvmw.pte) { + pte_t entry; + pte_t *pte = pvmw.pte; + + if (!pte_dirty(*pte) && !pte_write(*pte)) + continue; + + flush_cache_page(vma, address, pte_pfn(*pte)); + entry = ptep_clear_flush(vma, address, pte); + entry = pte_wrprotect(entry); + entry = pte_mkclean(entry); + set_pte_at(vma->vm_mm, address, pte, entry); + ret = 1; + } else { +#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE + pmd_t *pmd = pvmw.pmd; + pmd_t entry; + + if (!pmd_dirty(*pmd) && !pmd_write(*pmd)) + continue; + + flush_cache_page(vma, address, page_to_pfn(page)); + entry = pmdp_huge_clear_flush(vma, address, pmd); + entry = pmd_wrprotect(entry); + entry = pmd_mkclean(entry); + set_pmd_at(vma->vm_mm, address, pmd, entry); + ret = 1; +#else + /* unexpected pmd-mapped page? */ + WARN_ON_ONCE(1); +#endif + } - flush_cache_page(vma, address, pte_pfn(*pte)); - entry = ptep_clear_flush(vma, address, pte); - entry = pte_wrprotect(entry); - entry = pte_mkclean(entry); - set_pte_at(mm, address, pte, entry); - ret = 1; + if (ret) { + mmu_notifier_invalidate_page(vma->vm_mm, address); + (*cleaned)++; + } } - pte_unmap_unlock(pte, ptl); - - if (ret) { - mmu_notifier_invalidate_page(mm, address); - (*cleaned)++; - } -out: - return SWAP_AGAIN; + return true; } static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) @@ -1294,7 +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); } @@ -1334,7 +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); @@ -1423,167 +1287,186 @@ 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; - pte_t *pte; + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = address, + }; pte_t pteval; - spinlock_t *ptl; - int ret = SWAP_AGAIN; - struct rmap_private *rp = arg; - enum ttu_flags flags = rp->flags; + struct page *subpage; + 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)) - goto out; + return true; if (flags & TTU_SPLIT_HUGE_PMD) { split_huge_pmd_address(vma, address, flags & TTU_MIGRATION, page); - /* check if we have anything to do after split */ - if (page_mapcount(page) == 0) - goto out; } - pte = page_check_address(page, mm, address, &ptl, - PageTransCompound(page)); - if (!pte) - goto out; - - /* - * If the page is mlock()d, we cannot swap it out. - * If it's recently referenced (perhaps page_referenced - * skipped over this mm) then we should reactivate it. - */ - if (!(flags & TTU_IGNORE_MLOCK)) { - if (vma->vm_flags & VM_LOCKED) { - /* PTE-mapped THP are never mlocked */ - if (!PageTransCompound(page)) { - /* - * Holding pte lock, we do *not* need - * mmap_sem here - */ - mlock_vma_page(page); + while (page_vma_mapped_walk(&pvmw)) { + /* + * If the page is mlock()d, we cannot swap it out. + * If it's recently referenced (perhaps page_referenced + * skipped over this mm) then we should reactivate it. + */ + if (!(flags & TTU_IGNORE_MLOCK)) { + if (vma->vm_flags & VM_LOCKED) { + /* PTE-mapped THP are never mlocked */ + if (!PageTransCompound(page)) { + /* + * Holding pte lock, we do *not* need + * mmap_sem here + */ + mlock_vma_page(page); + } + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; } - ret = SWAP_MLOCK; - goto out_unmap; + if (flags & TTU_MUNLOCK) + continue; } - if (flags & TTU_MUNLOCK) - goto out_unmap; - } - if (!(flags & TTU_IGNORE_ACCESS)) { - if (ptep_clear_flush_young_notify(vma, address, pte)) { - ret = SWAP_FAIL; - goto out_unmap; - } - } - /* Nuke the page table entry. */ - flush_cache_page(vma, address, page_to_pfn(page)); - if (should_defer_flush(mm, flags)) { - /* - * We clear the PTE but do not flush so potentially a remote - * CPU could still be writing to the page. If the entry was - * previously clean then the architecture must guarantee that - * a clear->dirty transition on a cached TLB entry is written - * through and traps if the PTE is unmapped. - */ - pteval = ptep_get_and_clear(mm, address, pte); + /* Unexpected PMD-mapped THP? */ + VM_BUG_ON_PAGE(!pvmw.pte, page); + + subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); + address = pvmw.address; - set_tlb_ubc_flush_pending(mm, page, pte_dirty(pteval)); - } else { - pteval = ptep_clear_flush(vma, address, pte); - } - /* Move the dirty bit to the physical page now the pte is gone. */ - if (pte_dirty(pteval)) - set_page_dirty(page); + if (!(flags & TTU_IGNORE_ACCESS)) { + if (ptep_clear_flush_young_notify(vma, address, + pvmw.pte)) { + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + } - /* Update high watermark before we lower rss */ - update_hiwater_rss(mm); + /* Nuke the page table entry. */ + flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); + if (should_defer_flush(mm, flags)) { + /* + * We clear the PTE but do not flush so potentially + * a remote CPU could still be writing to the page. + * If the entry was previously clean then the + * architecture must guarantee that a clear->dirty + * transition on a cached TLB entry is written through + * and traps if the PTE is unmapped. + */ + pteval = ptep_get_and_clear(mm, address, pvmw.pte); - if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) { - if (PageHuge(page)) { - hugetlb_count_sub(1 << compound_order(page), mm); + set_tlb_ubc_flush_pending(mm, pte_dirty(pteval)); } else { - dec_mm_counter(mm, mm_counter(page)); + pteval = ptep_clear_flush(vma, address, pvmw.pte); } - set_pte_at(mm, address, pte, - swp_entry_to_pte(make_hwpoison_entry(page))); - } else if (pte_unused(pteval)) { - /* - * The guest indicated that the page content is of no - * interest anymore. Simply discard the pte, vmscan - * will take care of the rest. - */ - dec_mm_counter(mm, mm_counter(page)); - } else if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION)) { - swp_entry_t entry; - pte_t swp_pte; - /* - * Store the pfn of the page in a special migration - * pte. do_swap_page() will wait until the migration - * pte is removed and then restart fault handling. - */ - entry = make_migration_entry(page, pte_write(pteval)); - swp_pte = swp_entry_to_pte(entry); - if (pte_soft_dirty(pteval)) - swp_pte = pte_swp_mksoft_dirty(swp_pte); - set_pte_at(mm, address, pte, swp_pte); - } else if (PageAnon(page)) { - swp_entry_t entry = { .val = page_private(page) }; - pte_t swp_pte; - /* - * Store the swap location in the pte. - * See handle_pte_fault() ... - */ - VM_BUG_ON_PAGE(!PageSwapCache(page), page); - if (!PageDirty(page) && (flags & TTU_LZFREE)) { - /* It's a freeable page by MADV_FREE */ - dec_mm_counter(mm, MM_ANONPAGES); - rp->lazyfreed++; - goto discard; - } + /* Move the dirty bit to the page. Now the pte is gone. */ + if (pte_dirty(pteval)) + set_page_dirty(page); - if (swap_duplicate(entry) < 0) { - set_pte_at(mm, address, pte, pteval); - ret = SWAP_FAIL; - goto out_unmap; - } - if (list_empty(&mm->mmlist)) { - spin_lock(&mmlist_lock); - if (list_empty(&mm->mmlist)) - list_add(&mm->mmlist, &init_mm.mmlist); - spin_unlock(&mmlist_lock); - } - dec_mm_counter(mm, MM_ANONPAGES); - inc_mm_counter(mm, MM_SWAPENTS); - swp_pte = swp_entry_to_pte(entry); - if (pte_soft_dirty(pteval)) - swp_pte = pte_swp_mksoft_dirty(swp_pte); - set_pte_at(mm, address, pte, swp_pte); - } else - dec_mm_counter(mm, mm_counter_file(page)); + /* Update high watermark before we lower rss */ + update_hiwater_rss(mm); -discard: - page_remove_rmap(page, PageHuge(page)); - put_page(page); + if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) { + if (PageHuge(page)) { + int nr = 1 << compound_order(page); + hugetlb_count_sub(nr, mm); + } else { + dec_mm_counter(mm, mm_counter(page)); + } + + pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); + set_pte_at(mm, address, pvmw.pte, pteval); + } else if (pte_unused(pteval)) { + /* + * The guest indicated that the page content is of no + * interest anymore. Simply discard the pte, vmscan + * will take care of the rest. + */ + dec_mm_counter(mm, mm_counter(page)); + } else if (IS_ENABLED(CONFIG_MIGRATION) && + (flags & TTU_MIGRATION)) { + swp_entry_t entry; + pte_t swp_pte; + /* + * Store the pfn of the page in a special migration + * pte. do_swap_page() will wait until the migration + * pte is removed and then restart fault handling. + */ + entry = make_migration_entry(subpage, + pte_write(pteval)); + swp_pte = swp_entry_to_pte(entry); + if (pte_soft_dirty(pteval)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + set_pte_at(mm, address, pvmw.pte, swp_pte); + } else if (PageAnon(page)) { + swp_entry_t entry = { .val = page_private(subpage) }; + pte_t swp_pte; + /* + * Store the swap location in the pte. + * See handle_pte_fault() ... + */ + 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 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; + } -out_unmap: - pte_unmap_unlock(pte, ptl); - if (ret != SWAP_FAIL && ret != SWAP_MLOCK && !(flags & TTU_MUNLOCK)) + if (swap_duplicate(entry) < 0) { + set_pte_at(mm, address, pvmw.pte, pteval); + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + if (list_empty(&mm->mmlist)) { + spin_lock(&mmlist_lock); + if (list_empty(&mm->mmlist)) + list_add(&mm->mmlist, &init_mm.mmlist); + spin_unlock(&mmlist_lock); + } + dec_mm_counter(mm, MM_ANONPAGES); + inc_mm_counter(mm, MM_SWAPENTS); + swp_pte = swp_entry_to_pte(entry); + if (pte_soft_dirty(pteval)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + set_pte_at(mm, address, pvmw.pte, swp_pte); + } else + dec_mm_counter(mm, mm_counter_file(page)); +discard: + page_remove_rmap(subpage, PageHuge(page)); + put_page(page); mmu_notifier_invalidate_page(mm, address); -out: + } return ret; } @@ -1608,7 +1491,7 @@ static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) static int page_mapcount_is_zero(struct page *page) { - return !page_mapcount(page); + return !total_mapcount(page); } /** @@ -1618,24 +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, }; @@ -1652,16 +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) @@ -1676,34 +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) @@ -1751,13 +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; + pgoff_t pgoff_start, pgoff_end; struct anon_vma_chain *avc; - int ret = SWAP_AGAIN; if (locked) { anon_vma = page_anon_vma(page); @@ -1767,10 +1622,12 @@ 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 = page_to_pgoff(page); - anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { + pgoff_start = page_to_pgoff(page); + pgoff_end = pgoff_start + hpage_nr_pages(page) - 1; + anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, + pgoff_start, pgoff_end) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); @@ -1779,8 +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; @@ -1788,7 +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; } /* @@ -1804,13 +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; + 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 @@ -1821,12 +1675,14 @@ 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 = page_to_pgoff(page); + pgoff_start = page_to_pgoff(page); + pgoff_end = pgoff_start + hpage_nr_pages(page) - 1; if (!locked) i_mmap_lock_read(mapping); - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { + vma_interval_tree_foreach(vma, &mapping->i_mmap, + pgoff_start, pgoff_end) { unsigned long address = vma_address(page, vma); cond_resched(); @@ -1834,8 +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; @@ -1844,28 +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 new file mode 100644 index 000000000000..6bb4deb12e78 --- /dev/null +++ b/mm/rodata_test.c @@ -0,0 +1,57 @@ +/* + * rodata_test.c: functional test for mark_rodata_ro function + * + * (C) Copyright 2008 Intel Corporation + * Author: Arjan van de Ven <arjan@linux.intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * 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; + +void rodata_test(void) +{ + unsigned long start, end; + int zero = 0; + + /* test 1: read the value */ + /* If this test fails, some previous testrun has clobbered the state */ + if (!rodata_test_data) { + 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("test data was not read only\n"); + return; + } + + /* test 3: check the value hasn't changed */ + if (rodata_test_data == zero) { + pr_err("test data was changed\n"); + return; + } + + /* test 4: check if the rodata section is PAGE_SIZE aligned */ + start = (unsigned long)__start_rodata; + end = (unsigned long)__end_rodata; + if (start & (PAGE_SIZE - 1)) { + pr_err("start of .rodata is not page size aligned\n"); + return; + } + if (end & (PAGE_SIZE - 1)) { + pr_err("end of .rodata is not page size aligned\n"); + return; + } + + pr_info("all tests were successful\n"); +} diff --git a/mm/shmem.c b/mm/shmem.c index 3a7587a0314d..e67d6ba4e98e 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -29,11 +29,14 @@ #include <linux/pagemap.h> #include <linux/file.h> #include <linux/mm.h> +#include <linux/sched/signal.h> #include <linux/export.h> #include <linux/swap.h> #include <linux/uio.h> #include <linux/khugepaged.h> +#include <asm/tlbflush.h> /* for arch/microblaze update_mmu_cache() */ + static struct vfsmount *shm_mnt; #ifdef CONFIG_SHMEM @@ -70,6 +73,8 @@ static struct vfsmount *shm_mnt; #include <linux/syscalls.h> #include <linux/fcntl.h> #include <uapi/linux/memfd.h> +#include <linux/userfaultfd_k.h> +#include <linux/rmap.h> #include <linux/uaccess.h> #include <asm/pgtable.h> @@ -115,13 +120,14 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index); static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, - gfp_t gfp, struct mm_struct *fault_mm, int *fault_type); + gfp_t gfp, struct vm_area_struct *vma, + struct vm_fault *vmf, int *fault_type); int shmem_getpage(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp) { return shmem_getpage_gfp(inode, index, pagep, sgp, - mapping_gfp_mask(inode->i_mapping), NULL, NULL); + mapping_gfp_mask(inode->i_mapping), NULL, NULL, NULL); } static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) @@ -190,6 +196,11 @@ static const struct inode_operations shmem_special_inode_operations; static const struct vm_operations_struct shmem_vm_ops; static struct file_system_type shmem_fs_type; +bool vma_is_shmem(struct vm_area_struct *vma) +{ + return vma->vm_ops == &shmem_vm_ops; +} + static LIST_HEAD(shmem_swaplist); static DEFINE_MUTEX(shmem_swaplist_mutex); @@ -948,10 +959,10 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) } EXPORT_SYMBOL_GPL(shmem_truncate_range); -static int shmem_getattr(struct vfsmount *mnt, struct dentry *dentry, - struct kstat *stat) +static int shmem_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int query_flags) { - struct inode *inode = dentry->d_inode; + struct inode *inode = path->dentry->d_inode; struct shmem_inode_info *info = SHMEM_I(inode); if (info->alloced - info->swapped != inode->i_mapping->nrpages) { @@ -1570,7 +1581,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, */ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, - struct mm_struct *fault_mm, int *fault_type) + struct vm_area_struct *vma, struct vm_fault *vmf, int *fault_type) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); @@ -1624,7 +1635,7 @@ repeat: * bring it back from swap or allocate. */ sbinfo = SHMEM_SB(inode->i_sb); - charge_mm = fault_mm ? : current->mm; + charge_mm = vma ? vma->vm_mm : current->mm; if (swap.val) { /* Look it up and read it in.. */ @@ -1634,7 +1645,8 @@ repeat: if (fault_type) { *fault_type |= VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); - mem_cgroup_count_vm_event(fault_mm, PGMAJFAULT); + mem_cgroup_count_vm_event(charge_mm, + PGMAJFAULT); } /* Here we actually start the io */ page = shmem_swapin(swap, gfp, info, index); @@ -1703,6 +1715,11 @@ repeat: swap_free(swap); } else { + if (vma && userfaultfd_missing(vma)) { + *fault_type = handle_userfault(vmf, VM_UFFD_MISSING); + return 0; + } + /* shmem_symlink() */ if (mapping->a_ops != &shmem_aops) goto alloc_nohuge; @@ -1892,8 +1909,9 @@ static int synchronous_wake_function(wait_queue_t *wait, unsigned mode, int sync return ret; } -static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +static int shmem_fault(struct vm_fault *vmf) { + struct vm_area_struct *vma = vmf->vma; struct inode *inode = file_inode(vma->vm_file); gfp_t gfp = mapping_gfp_mask(inode->i_mapping); enum sgp_type sgp; @@ -1965,7 +1983,7 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) sgp = SGP_NOHUGE; error = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp, - gfp, vma->vm_mm, &ret); + gfp, vma, vmf, &ret); if (error) return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS); return ret; @@ -2175,10 +2193,123 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode bool shmem_mapping(struct address_space *mapping) { - if (!mapping->host) - return false; + return mapping->a_ops == &shmem_aops; +} - return mapping->host->i_sb->s_op == &shmem_ops; +int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + struct page **pagep) +{ + struct inode *inode = file_inode(dst_vma->vm_file); + struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + struct address_space *mapping = inode->i_mapping; + gfp_t gfp = mapping_gfp_mask(mapping); + pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); + struct mem_cgroup *memcg; + spinlock_t *ptl; + void *page_kaddr; + struct page *page; + pte_t _dst_pte, *dst_pte; + int ret; + + ret = -ENOMEM; + if (shmem_acct_block(info->flags, 1)) + goto out; + if (sbinfo->max_blocks) { + if (percpu_counter_compare(&sbinfo->used_blocks, + sbinfo->max_blocks) >= 0) + goto out_unacct_blocks; + percpu_counter_inc(&sbinfo->used_blocks); + } + + if (!*pagep) { + page = shmem_alloc_page(gfp, info, pgoff); + if (!page) + goto out_dec_used_blocks; + + page_kaddr = kmap_atomic(page); + ret = copy_from_user(page_kaddr, (const void __user *)src_addr, + PAGE_SIZE); + kunmap_atomic(page_kaddr); + + /* fallback to copy_from_user outside mmap_sem */ + if (unlikely(ret)) { + *pagep = page; + if (sbinfo->max_blocks) + percpu_counter_add(&sbinfo->used_blocks, -1); + shmem_unacct_blocks(info->flags, 1); + /* don't free the page */ + return -EFAULT; + } + } else { + page = *pagep; + *pagep = NULL; + } + + VM_BUG_ON(PageLocked(page) || PageSwapBacked(page)); + __SetPageLocked(page); + __SetPageSwapBacked(page); + __SetPageUptodate(page); + + ret = mem_cgroup_try_charge(page, dst_mm, gfp, &memcg, false); + if (ret) + goto out_release; + + ret = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK); + if (!ret) { + ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL); + radix_tree_preload_end(); + } + if (ret) + goto out_release_uncharge; + + mem_cgroup_commit_charge(page, memcg, false, false); + + _dst_pte = mk_pte(page, dst_vma->vm_page_prot); + if (dst_vma->vm_flags & VM_WRITE) + _dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte)); + + ret = -EEXIST; + dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); + if (!pte_none(*dst_pte)) + goto out_release_uncharge_unlock; + + lru_cache_add_anon(page); + + spin_lock(&info->lock); + info->alloced++; + inode->i_blocks += BLOCKS_PER_PAGE; + shmem_recalc_inode(inode); + spin_unlock(&info->lock); + + inc_mm_counter(dst_mm, mm_counter_file(page)); + page_add_file_rmap(page, false); + set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); + + /* No need to invalidate - it was non-present before */ + update_mmu_cache(dst_vma, dst_addr, dst_pte); + unlock_page(page); + pte_unmap_unlock(dst_pte, ptl); + ret = 0; +out: + return ret; +out_release_uncharge_unlock: + pte_unmap_unlock(dst_pte, ptl); +out_release_uncharge: + mem_cgroup_cancel_charge(page, memcg, false); +out_release: + unlock_page(page); + put_page(page); +out_dec_used_blocks: + if (sbinfo->max_blocks) + percpu_counter_add(&sbinfo->used_blocks, -1); +out_unacct_blocks: + shmem_unacct_blocks(info->flags, 1); + goto out; } #ifdef CONFIG_TMPFS @@ -2201,7 +2332,7 @@ shmem_write_begin(struct file *file, struct address_space *mapping, pgoff_t index = pos >> PAGE_SHIFT; /* i_mutex is held by caller */ - if (unlikely(info->seals)) { + if (unlikely(info->seals & (F_SEAL_WRITE | F_SEAL_GROW))) { if (info->seals & F_SEAL_WRITE) return -EPERM; if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size) @@ -4140,7 +4271,7 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, BUG_ON(mapping->a_ops != &shmem_aops); error = shmem_getpage_gfp(inode, index, &page, SGP_CACHE, - gfp, NULL, NULL); + gfp, NULL, NULL, NULL); if (error) page = ERR_PTR(error); else diff --git a/mm/slab.c b/mm/slab.c index 4f2ec6bb46eb..1880d482a0cb 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -116,6 +116,7 @@ #include <linux/kmemcheck.h> #include <linux/memory.h> #include <linux/prefetch.h> +#include <linux/sched/task_stack.h> #include <net/sock.h> @@ -1288,7 +1289,8 @@ void __init kmem_cache_init(void) * Initialize the caches that provide memory for the kmem_cache_node * structures first. Without this, further allocations will bug. */ - kmalloc_caches[INDEX_NODE] = create_kmalloc_cache("kmalloc-node", + kmalloc_caches[INDEX_NODE] = create_kmalloc_cache( + kmalloc_info[INDEX_NODE].name, kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS); slab_state = PARTIAL_NODE; setup_kmalloc_cache_index_table(); @@ -2332,6 +2334,13 @@ int __kmem_cache_shrink(struct kmem_cache *cachep) return (ret ? 1 : 0); } +#ifdef CONFIG_MEMCG +void __kmemcg_cache_deactivate(struct kmem_cache *cachep) +{ + __kmem_cache_shrink(cachep); +} +#endif + int __kmem_cache_shutdown(struct kmem_cache *cachep) { return __kmem_cache_shrink(cachep); @@ -3870,7 +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 de6579dc362c..65e7c3fcac72 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -71,6 +71,12 @@ extern struct list_head slab_caches; /* The slab cache that manages slab cache information */ extern struct kmem_cache *kmem_cache; +/* A table of kmalloc cache names and sizes */ +extern const struct kmalloc_info_struct { + const char *name; + unsigned long size; +} kmalloc_info[]; + unsigned long calculate_alignment(unsigned long flags, unsigned long align, unsigned long size); @@ -162,6 +168,7 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size, int __kmem_cache_shutdown(struct kmem_cache *); void __kmem_cache_release(struct kmem_cache *); int __kmem_cache_shrink(struct kmem_cache *); +void __kmemcg_cache_deactivate(struct kmem_cache *s); void slab_kmem_cache_release(struct kmem_cache *); struct seq_file; @@ -195,17 +202,22 @@ void __kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) + +/* List of all root caches. */ +extern struct list_head slab_root_caches; +#define root_caches_node memcg_params.__root_caches_node + /* * Iterate over all memcg caches of the given root cache. The caller must hold * slab_mutex. */ #define for_each_memcg_cache(iter, root) \ - list_for_each_entry(iter, &(root)->memcg_params.list, \ - memcg_params.list) + list_for_each_entry(iter, &(root)->memcg_params.children, \ + memcg_params.children_node) static inline bool is_root_cache(struct kmem_cache *s) { - return s->memcg_params.is_root_cache; + return !s->memcg_params.root_cache; } static inline bool slab_equal_or_root(struct kmem_cache *s, @@ -294,9 +306,16 @@ static __always_inline void memcg_uncharge_slab(struct page *page, int order, } extern void slab_init_memcg_params(struct kmem_cache *); +extern void memcg_link_cache(struct kmem_cache *s); +extern void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s, + void (*deact_fn)(struct kmem_cache *)); #else /* CONFIG_MEMCG && !CONFIG_SLOB */ +/* If !memcg, all caches are root. */ +#define slab_root_caches slab_caches +#define root_caches_node list + #define for_each_memcg_cache(iter, root) \ for ((void)(iter), (void)(root); 0; ) @@ -341,6 +360,11 @@ static inline void memcg_uncharge_slab(struct page *page, int order, static inline void slab_init_memcg_params(struct kmem_cache *s) { } + +static inline void memcg_link_cache(struct kmem_cache *s) +{ +} + #endif /* CONFIG_MEMCG && !CONFIG_SLOB */ static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x) @@ -488,6 +512,9 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node) void *slab_start(struct seq_file *m, loff_t *pos); void *slab_next(struct seq_file *m, void *p, loff_t *pos); void slab_stop(struct seq_file *m, void *p); +void *memcg_slab_start(struct seq_file *m, loff_t *pos); +void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos); +void memcg_slab_stop(struct seq_file *m, void *p); int memcg_slab_show(struct seq_file *m, void *p); void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr); diff --git a/mm/slab_common.c b/mm/slab_common.c index ae323841adb1..09d0e849b07f 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -30,6 +30,11 @@ LIST_HEAD(slab_caches); DEFINE_MUTEX(slab_mutex); struct kmem_cache *kmem_cache; +static LIST_HEAD(slab_caches_to_rcu_destroy); +static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work); +static DECLARE_WORK(slab_caches_to_rcu_destroy_work, + slab_caches_to_rcu_destroy_workfn); + /* * Set of flags that will prevent slab merging */ @@ -133,11 +138,14 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr, } #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) + +LIST_HEAD(slab_root_caches); + void slab_init_memcg_params(struct kmem_cache *s) { - s->memcg_params.is_root_cache = true; - INIT_LIST_HEAD(&s->memcg_params.list); + s->memcg_params.root_cache = NULL; RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL); + INIT_LIST_HEAD(&s->memcg_params.children); } static int init_memcg_params(struct kmem_cache *s, @@ -145,10 +153,11 @@ static int init_memcg_params(struct kmem_cache *s, { struct memcg_cache_array *arr; - if (memcg) { - s->memcg_params.is_root_cache = false; - s->memcg_params.memcg = memcg; + if (root_cache) { s->memcg_params.root_cache = root_cache; + s->memcg_params.memcg = memcg; + INIT_LIST_HEAD(&s->memcg_params.children_node); + INIT_LIST_HEAD(&s->memcg_params.kmem_caches_node); return 0; } @@ -177,9 +186,6 @@ static int update_memcg_params(struct kmem_cache *s, int new_array_size) { struct memcg_cache_array *old, *new; - if (!is_root_cache(s)) - return 0; - new = kzalloc(sizeof(struct memcg_cache_array) + new_array_size * sizeof(void *), GFP_KERNEL); if (!new) @@ -203,7 +209,7 @@ int memcg_update_all_caches(int num_memcgs) int ret = 0; mutex_lock(&slab_mutex); - list_for_each_entry(s, &slab_caches, list) { + list_for_each_entry(s, &slab_root_caches, root_caches_node) { ret = update_memcg_params(s, num_memcgs); /* * Instead of freeing the memory, we'll just leave the caches @@ -215,6 +221,28 @@ int memcg_update_all_caches(int num_memcgs) mutex_unlock(&slab_mutex); return ret; } + +void memcg_link_cache(struct kmem_cache *s) +{ + if (is_root_cache(s)) { + list_add(&s->root_caches_node, &slab_root_caches); + } else { + list_add(&s->memcg_params.children_node, + &s->memcg_params.root_cache->memcg_params.children); + list_add(&s->memcg_params.kmem_caches_node, + &s->memcg_params.memcg->kmem_caches); + } +} + +static void memcg_unlink_cache(struct kmem_cache *s) +{ + if (is_root_cache(s)) { + list_del(&s->root_caches_node); + } else { + list_del(&s->memcg_params.children_node); + list_del(&s->memcg_params.kmem_caches_node); + } +} #else static inline int init_memcg_params(struct kmem_cache *s, struct mem_cgroup *memcg, struct kmem_cache *root_cache) @@ -225,6 +253,10 @@ static inline int init_memcg_params(struct kmem_cache *s, static inline void destroy_memcg_params(struct kmem_cache *s) { } + +static inline void memcg_unlink_cache(struct kmem_cache *s) +{ +} #endif /* CONFIG_MEMCG && !CONFIG_SLOB */ /* @@ -255,7 +287,7 @@ struct kmem_cache *find_mergeable(size_t size, size_t align, { struct kmem_cache *s; - if (slab_nomerge || (flags & SLAB_NEVER_MERGE)) + if (slab_nomerge) return NULL; if (ctor) @@ -266,7 +298,10 @@ struct kmem_cache *find_mergeable(size_t size, size_t align, size = ALIGN(size, align); flags = kmem_cache_flags(size, flags, name, NULL); - list_for_each_entry_reverse(s, &slab_caches, list) { + if (flags & SLAB_NEVER_MERGE) + return NULL; + + list_for_each_entry_reverse(s, &slab_root_caches, root_caches_node) { if (slab_unmergeable(s)) continue; @@ -350,6 +385,7 @@ static struct kmem_cache *create_cache(const char *name, s->refcount = 1; list_add(&s->list, &slab_caches); + memcg_link_cache(s); out: if (err) return ERR_PTR(err); @@ -458,33 +494,61 @@ out_unlock: } EXPORT_SYMBOL(kmem_cache_create); -static int shutdown_cache(struct kmem_cache *s, - struct list_head *release, bool *need_rcu_barrier) +static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work) { - if (__kmem_cache_shutdown(s) != 0) - return -EBUSY; + LIST_HEAD(to_destroy); + struct kmem_cache *s, *s2; + + /* + * On destruction, SLAB_DESTROY_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 + * after the pending RCU operations are finished. As rcu_barrier() + * is a pretty slow operation, we batch all pending destructions + * asynchronously. + */ + mutex_lock(&slab_mutex); + list_splice_init(&slab_caches_to_rcu_destroy, &to_destroy); + mutex_unlock(&slab_mutex); + + if (list_empty(&to_destroy)) + return; - if (s->flags & SLAB_DESTROY_BY_RCU) - *need_rcu_barrier = true; + rcu_barrier(); - list_move(&s->list, release); - return 0; + list_for_each_entry_safe(s, s2, &to_destroy, list) { +#ifdef SLAB_SUPPORTS_SYSFS + sysfs_slab_release(s); +#else + slab_kmem_cache_release(s); +#endif + } } -static void release_caches(struct list_head *release, bool need_rcu_barrier) +static int shutdown_cache(struct kmem_cache *s) { - struct kmem_cache *s, *s2; + /* free asan quarantined objects */ + kasan_cache_shutdown(s); - if (need_rcu_barrier) - rcu_barrier(); + if (__kmem_cache_shutdown(s) != 0) + return -EBUSY; - list_for_each_entry_safe(s, s2, release, list) { + memcg_unlink_cache(s); + list_del(&s->list); + + if (s->flags & SLAB_DESTROY_BY_RCU) { + list_add_tail(&s->list, &slab_caches_to_rcu_destroy); + schedule_work(&slab_caches_to_rcu_destroy_work); + } else { #ifdef SLAB_SUPPORTS_SYSFS - sysfs_slab_remove(s); + sysfs_slab_release(s); #else slab_kmem_cache_release(s); #endif } + + return 0; } #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) @@ -551,8 +615,6 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg, goto out_unlock; } - list_add(&s->memcg_params.list, &root_cache->memcg_params.list); - /* * Since readers won't lock (see cache_from_memcg_idx()), we need a * barrier here to ensure nobody will see the kmem_cache partially @@ -568,6 +630,66 @@ out_unlock: put_online_cpus(); } +static void kmemcg_deactivate_workfn(struct work_struct *work) +{ + struct kmem_cache *s = container_of(work, struct kmem_cache, + memcg_params.deact_work); + + get_online_cpus(); + get_online_mems(); + + mutex_lock(&slab_mutex); + + s->memcg_params.deact_fn(s); + + mutex_unlock(&slab_mutex); + + put_online_mems(); + put_online_cpus(); + + /* done, put the ref from slab_deactivate_memcg_cache_rcu_sched() */ + css_put(&s->memcg_params.memcg->css); +} + +static void kmemcg_deactivate_rcufn(struct rcu_head *head) +{ + struct kmem_cache *s = container_of(head, struct kmem_cache, + memcg_params.deact_rcu_head); + + /* + * We need to grab blocking locks. Bounce to ->deact_work. The + * work item shares the space with the RCU head and can't be + * initialized eariler. + */ + INIT_WORK(&s->memcg_params.deact_work, kmemcg_deactivate_workfn); + queue_work(memcg_kmem_cache_wq, &s->memcg_params.deact_work); +} + +/** + * slab_deactivate_memcg_cache_rcu_sched - schedule deactivation after a + * sched RCU grace period + * @s: target kmem_cache + * @deact_fn: deactivation function to call + * + * Schedule @deact_fn to be invoked with online cpus, mems and slab_mutex + * held after a sched RCU grace period. The slab is guaranteed to stay + * alive until @deact_fn is finished. This is to be used from + * __kmemcg_cache_deactivate(). + */ +void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s, + void (*deact_fn)(struct kmem_cache *)) +{ + if (WARN_ON_ONCE(is_root_cache(s)) || + WARN_ON_ONCE(s->memcg_params.deact_fn)) + return; + + /* pin memcg so that @s doesn't get destroyed in the middle */ + css_get(&s->memcg_params.memcg->css); + + s->memcg_params.deact_fn = deact_fn; + call_rcu_sched(&s->memcg_params.deact_rcu_head, kmemcg_deactivate_rcufn); +} + void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg) { int idx; @@ -579,41 +701,15 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg) get_online_cpus(); get_online_mems(); -#ifdef CONFIG_SLUB - /* - * In case of SLUB, we need to disable empty slab caching to - * avoid pinning the offline memory cgroup by freeable kmem - * pages charged to it. SLAB doesn't need this, as it - * periodically purges unused slabs. - */ - mutex_lock(&slab_mutex); - list_for_each_entry(s, &slab_caches, list) { - c = is_root_cache(s) ? cache_from_memcg_idx(s, idx) : NULL; - if (c) { - c->cpu_partial = 0; - c->min_partial = 0; - } - } - mutex_unlock(&slab_mutex); - /* - * kmem_cache->cpu_partial is checked locklessly (see - * put_cpu_partial()). Make sure the change is visible. - */ - synchronize_sched(); -#endif - mutex_lock(&slab_mutex); - list_for_each_entry(s, &slab_caches, list) { - if (!is_root_cache(s)) - continue; - + list_for_each_entry(s, &slab_root_caches, root_caches_node) { arr = rcu_dereference_protected(s->memcg_params.memcg_caches, lockdep_is_held(&slab_mutex)); c = arr->entries[idx]; if (!c) continue; - __kmem_cache_shrink(c); + __kmemcg_cache_deactivate(c); arr->entries[idx] = NULL; } mutex_unlock(&slab_mutex); @@ -622,47 +718,29 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg) put_online_cpus(); } -static int __shutdown_memcg_cache(struct kmem_cache *s, - struct list_head *release, bool *need_rcu_barrier) -{ - BUG_ON(is_root_cache(s)); - - if (shutdown_cache(s, release, need_rcu_barrier)) - return -EBUSY; - - list_del(&s->memcg_params.list); - return 0; -} - void memcg_destroy_kmem_caches(struct mem_cgroup *memcg) { - LIST_HEAD(release); - bool need_rcu_barrier = false; struct kmem_cache *s, *s2; get_online_cpus(); get_online_mems(); mutex_lock(&slab_mutex); - list_for_each_entry_safe(s, s2, &slab_caches, list) { - if (is_root_cache(s) || s->memcg_params.memcg != memcg) - continue; + list_for_each_entry_safe(s, s2, &memcg->kmem_caches, + memcg_params.kmem_caches_node) { /* * The cgroup is about to be freed and therefore has no charges * left. Hence, all its caches must be empty by now. */ - BUG_ON(__shutdown_memcg_cache(s, &release, &need_rcu_barrier)); + BUG_ON(shutdown_cache(s)); } mutex_unlock(&slab_mutex); put_online_mems(); put_online_cpus(); - - release_caches(&release, need_rcu_barrier); } -static int shutdown_memcg_caches(struct kmem_cache *s, - struct list_head *release, bool *need_rcu_barrier) +static int shutdown_memcg_caches(struct kmem_cache *s) { struct memcg_cache_array *arr; struct kmem_cache *c, *c2; @@ -681,13 +759,13 @@ static int shutdown_memcg_caches(struct kmem_cache *s, c = arr->entries[i]; if (!c) continue; - if (__shutdown_memcg_cache(c, release, need_rcu_barrier)) + if (shutdown_cache(c)) /* * The cache still has objects. Move it to a temporary * list so as not to try to destroy it for a second * time while iterating over inactive caches below. */ - list_move(&c->memcg_params.list, &busy); + list_move(&c->memcg_params.children_node, &busy); else /* * The cache is empty and will be destroyed soon. Clear @@ -702,23 +780,22 @@ static int shutdown_memcg_caches(struct kmem_cache *s, * Second, shutdown all caches left from memory cgroups that are now * offline. */ - list_for_each_entry_safe(c, c2, &s->memcg_params.list, - memcg_params.list) - __shutdown_memcg_cache(c, release, need_rcu_barrier); + list_for_each_entry_safe(c, c2, &s->memcg_params.children, + memcg_params.children_node) + shutdown_cache(c); - list_splice(&busy, &s->memcg_params.list); + list_splice(&busy, &s->memcg_params.children); /* * A cache being destroyed must be empty. In particular, this means * that all per memcg caches attached to it must be empty too. */ - if (!list_empty(&s->memcg_params.list)) + if (!list_empty(&s->memcg_params.children)) return -EBUSY; return 0; } #else -static inline int shutdown_memcg_caches(struct kmem_cache *s, - struct list_head *release, bool *need_rcu_barrier) +static inline int shutdown_memcg_caches(struct kmem_cache *s) { return 0; } @@ -734,8 +811,6 @@ void slab_kmem_cache_release(struct kmem_cache *s) void kmem_cache_destroy(struct kmem_cache *s) { - LIST_HEAD(release); - bool need_rcu_barrier = false; int err; if (unlikely(!s)) @@ -744,16 +819,15 @@ void kmem_cache_destroy(struct kmem_cache *s) get_online_cpus(); get_online_mems(); - kasan_cache_destroy(s); mutex_lock(&slab_mutex); s->refcount--; if (s->refcount) goto out_unlock; - err = shutdown_memcg_caches(s, &release, &need_rcu_barrier); + err = shutdown_memcg_caches(s); if (!err) - err = shutdown_cache(s, &release, &need_rcu_barrier); + err = shutdown_cache(s); if (err) { pr_err("kmem_cache_destroy %s: Slab cache still has objects\n", @@ -765,8 +839,6 @@ out_unlock: put_online_mems(); put_online_cpus(); - - release_caches(&release, need_rcu_barrier); } EXPORT_SYMBOL(kmem_cache_destroy); @@ -828,6 +900,7 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size, create_boot_cache(s, name, size, flags); list_add(&s->list, &slab_caches); + memcg_link_cache(s); s->refcount = 1; return s; } @@ -912,10 +985,7 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags) * kmalloc_index() supports up to 2^26=64MB, so the final entry of the table is * kmalloc-67108864. */ -static struct { - const char *name; - unsigned long size; -} const kmalloc_info[] __initconst = { +const struct kmalloc_info_struct kmalloc_info[] __initconst = { {NULL, 0}, {"kmalloc-96", 96}, {"kmalloc-192", 192}, {"kmalloc-8", 8}, {"kmalloc-16", 16}, {"kmalloc-32", 32}, @@ -1138,12 +1208,12 @@ static void print_slabinfo_header(struct seq_file *m) void *slab_start(struct seq_file *m, loff_t *pos) { mutex_lock(&slab_mutex); - return seq_list_start(&slab_caches, *pos); + return seq_list_start(&slab_root_caches, *pos); } void *slab_next(struct seq_file *m, void *p, loff_t *pos) { - return seq_list_next(p, &slab_caches, pos); + return seq_list_next(p, &slab_root_caches, pos); } void slab_stop(struct seq_file *m, void *p) @@ -1195,25 +1265,44 @@ static void cache_show(struct kmem_cache *s, struct seq_file *m) static int slab_show(struct seq_file *m, void *p) { - struct kmem_cache *s = list_entry(p, struct kmem_cache, list); + struct kmem_cache *s = list_entry(p, struct kmem_cache, root_caches_node); - if (p == slab_caches.next) + if (p == slab_root_caches.next) print_slabinfo_header(m); - if (is_root_cache(s)) - cache_show(s, m); + cache_show(s, m); return 0; } #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) +void *memcg_slab_start(struct seq_file *m, loff_t *pos) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + + mutex_lock(&slab_mutex); + return seq_list_start(&memcg->kmem_caches, *pos); +} + +void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + + return seq_list_next(p, &memcg->kmem_caches, pos); +} + +void memcg_slab_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&slab_mutex); +} + int memcg_slab_show(struct seq_file *m, void *p) { - struct kmem_cache *s = list_entry(p, struct kmem_cache, list); + struct kmem_cache *s = list_entry(p, struct kmem_cache, + memcg_params.kmem_caches_node); struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - if (p == slab_caches.next) + if (p == memcg->kmem_caches.next) print_slabinfo_header(m); - if (!is_root_cache(s) && s->memcg_params.memcg == memcg) - cache_show(s, m); + cache_show(s, m); return 0; } #endif diff --git a/mm/slub.c b/mm/slub.c index 7ec0a965c6a3..7f4bc7027ed5 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -214,11 +214,13 @@ enum track_item { TRACK_ALLOC, TRACK_FREE }; static int sysfs_slab_add(struct kmem_cache *); static int sysfs_slab_alias(struct kmem_cache *, const char *); static void memcg_propagate_slab_attrs(struct kmem_cache *s); +static void sysfs_slab_remove(struct kmem_cache *s); #else static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; } static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p) { return 0; } static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { } +static inline void sysfs_slab_remove(struct kmem_cache *s) { } #endif static inline void stat(const struct kmem_cache *s, enum stat_item si) @@ -1630,6 +1632,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) flags &= ~GFP_SLAB_BUG_MASK; pr_warn("Unexpected gfp: %#x (%pGg). Fixing up to gfp: %#x (%pGg). Fix your code!\n", invalid_mask, &invalid_mask, flags, &flags); + dump_stack(); } return allocate_slab(s, @@ -3686,6 +3689,7 @@ int __kmem_cache_shutdown(struct kmem_cache *s) if (n->nr_partial || slabs_node(s, node)) return 1; } + sysfs_slab_remove(s); return 0; } @@ -3952,6 +3956,42 @@ int __kmem_cache_shrink(struct kmem_cache *s) return ret; } +#ifdef CONFIG_MEMCG +static void kmemcg_cache_deact_after_rcu(struct kmem_cache *s) +{ + /* + * Called with all the locks held after a sched RCU grace period. + * Even if @s becomes empty after shrinking, we can't know that @s + * doesn't have allocations already in-flight and thus can't + * destroy @s until the associated memcg is released. + * + * However, let's remove the sysfs files for empty caches here. + * Each cache has a lot of interface files which aren't + * particularly useful for empty draining caches; otherwise, we can + * easily end up with millions of unnecessary sysfs files on + * systems which have a lot of memory and transient cgroups. + */ + if (!__kmem_cache_shrink(s)) + sysfs_slab_remove(s); +} + +void __kmemcg_cache_deactivate(struct kmem_cache *s) +{ + /* + * Disable empty slabs caching. Used to avoid pinning offline + * memory cgroups by kmem pages that can be freed. + */ + s->cpu_partial = 0; + s->min_partial = 0; + + /* + * s->cpu_partial is checked locklessly (see put_cpu_partial), so + * we have to make sure the change is visible before shrinking. + */ + slab_deactivate_memcg_cache_rcu_sched(s, kmemcg_cache_deact_after_rcu); +} +#endif + static int slab_mem_going_offline_callback(void *arg) { struct kmem_cache *s; @@ -4108,6 +4148,7 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache) } slab_init_memcg_params(s); list_add(&s->list, &slab_caches); + memcg_link_cache(s); return s; } @@ -4667,6 +4708,22 @@ enum slab_stat_type { #define SO_OBJECTS (1 << SL_OBJECTS) #define SO_TOTAL (1 << SL_TOTAL) +#ifdef CONFIG_MEMCG +static bool memcg_sysfs_enabled = IS_ENABLED(CONFIG_SLUB_MEMCG_SYSFS_ON); + +static int __init setup_slub_memcg_sysfs(char *str) +{ + int v; + + if (get_option(&str, &v) > 0) + memcg_sysfs_enabled = v; + + return 1; +} + +__setup("slub_memcg_sysfs=", setup_slub_memcg_sysfs); +#endif + static ssize_t show_slab_objects(struct kmem_cache *s, char *buf, unsigned long flags) { @@ -5570,8 +5627,14 @@ static int sysfs_slab_add(struct kmem_cache *s) { int err; const char *name; + struct kset *kset = cache_kset(s); int unmergeable = slab_unmergeable(s); + if (!kset) { + kobject_init(&s->kobj, &slab_ktype); + return 0; + } + if (unmergeable) { /* * Slabcache can never be merged so we can use the name proper. @@ -5588,7 +5651,7 @@ static int sysfs_slab_add(struct kmem_cache *s) name = create_unique_id(s); } - s->kobj.kset = cache_kset(s); + s->kobj.kset = kset; err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name); if (err) goto out; @@ -5598,7 +5661,7 @@ static int sysfs_slab_add(struct kmem_cache *s) goto out_del_kobj; #ifdef CONFIG_MEMCG - if (is_root_cache(s)) { + if (is_root_cache(s) && memcg_sysfs_enabled) { s->memcg_kset = kset_create_and_add("cgroup", NULL, &s->kobj); if (!s->memcg_kset) { err = -ENOMEM; @@ -5621,7 +5684,7 @@ out_del_kobj: goto out; } -void sysfs_slab_remove(struct kmem_cache *s) +static void sysfs_slab_remove(struct kmem_cache *s) { if (slab_state < FULL) /* @@ -5630,12 +5693,26 @@ void sysfs_slab_remove(struct kmem_cache *s) */ return; + if (!s->kobj.state_in_sysfs) + /* + * For a memcg cache, this may be called during + * deactivation and again on shutdown. Remove only once. + * A cache is never shut down before deactivation is + * complete, so no need to worry about synchronization. + */ + return; + #ifdef CONFIG_MEMCG kset_unregister(s->memcg_kset); #endif kobject_uevent(&s->kobj, KOBJ_REMOVE); kobject_del(&s->kobj); - kobject_put(&s->kobj); +} + +void sysfs_slab_release(struct kmem_cache *s) +{ + if (slab_state >= FULL) + kobject_put(&s->kobj); } /* diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 574c67b663fe..a56c3989f773 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -196,9 +196,9 @@ pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node) return pmd; } -pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node) +pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node) { - pud_t *pud = pud_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); if (pud_none(*pud)) { void *p = vmemmap_alloc_block(PAGE_SIZE, node); if (!p) @@ -208,6 +208,18 @@ pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node) return pud; } +p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) +{ + p4d_t *p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) { + void *p = vmemmap_alloc_block(PAGE_SIZE, node); + if (!p) + return NULL; + p4d_populate(&init_mm, p4d, p); + } + return p4d; +} + pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) { pgd_t *pgd = pgd_offset_k(addr); @@ -225,6 +237,7 @@ int __meminit vmemmap_populate_basepages(unsigned long start, { unsigned long addr = start; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -233,7 +246,10 @@ int __meminit vmemmap_populate_basepages(unsigned long start, pgd = vmemmap_pgd_populate(addr, node); if (!pgd) return -ENOMEM; - pud = vmemmap_pud_populate(pgd, addr, node); + p4d = vmemmap_p4d_populate(pgd, addr, node); + if (!p4d) + return -ENOMEM; + pud = vmemmap_pud_populate(p4d, addr, node); if (!pud) return -ENOMEM; pmd = vmemmap_pmd_populate(pud, addr, node); diff --git a/mm/sparse.c b/mm/sparse.c index 1e168bf2779a..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 @@ -662,12 +659,12 @@ static void free_map_bootmem(struct page *memmap) >> PAGE_SHIFT; for (i = 0; i < nr_pages; i++, page++) { - magic = (unsigned long) page->lru.next; + magic = (unsigned long) page->freelist; BUG_ON(magic == NODE_INFO); maps_section_nr = pfn_to_section_nr(page_to_pfn(page)); - removing_section_nr = page->private; + removing_section_nr = page_private(page); /* * When this function is called, the removing section is diff --git a/mm/swap.c b/mm/swap.c index 844baedd2429..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 @@ -209,9 +219,10 @@ static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec, { int *pgmoved = arg; - if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { - enum lru_list lru = page_lru_base_type(page); - list_move_tail(&page->lru, &lruvec->lists[lru]); + if (PageLRU(page) && !PageUnevictable(page)) { + del_page_from_lru_list(page, lruvec, page_lru(page)); + ClearPageActive(page); + add_page_to_lru_list_tail(page, lruvec, page_lru(page)); (*pgmoved)++; } } @@ -235,7 +246,7 @@ static void pagevec_move_tail(struct pagevec *pvec) */ void rotate_reclaimable_page(struct page *page) { - if (!PageLocked(page) && !PageDirty(page) && !PageActive(page) && + if (!PageLocked(page) && !PageDirty(page) && !PageUnevictable(page) && PageLRU(page)) { struct pagevec *pvec; unsigned long flags; @@ -560,20 +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); } } @@ -603,9 +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); } @@ -637,22 +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); } } @@ -669,30 +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); @@ -703,10 +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); } } @@ -971,12 +978,6 @@ EXPORT_SYMBOL(pagevec_lookup_tag); void __init swap_setup(void) { unsigned long megs = totalram_pages >> (20 - PAGE_SHIFT); -#ifdef CONFIG_SWAP - int i; - - for (i = 0; i < MAX_SWAPFILES; i++) - spin_lock_init(&swapper_spaces[i].tree_lock); -#endif /* Use a smaller cluster for small-memory machines */ if (megs < 16) 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 new file mode 100644 index 000000000000..aa1c415f4abd --- /dev/null +++ b/mm/swap_slots.c @@ -0,0 +1,342 @@ +/* + * Manage cache of swap slots to be used for and returned from + * swap. + * + * Copyright(c) 2016 Intel Corporation. + * + * Author: Tim Chen <tim.c.chen@linux.intel.com> + * + * We allocate the swap slots from the global pool and put + * it into local per cpu caches. This has the advantage + * of no needing to acquire the swap_info lock every time + * we need a new slot. + * + * There is also opportunity to simply return the slot + * to local caches without needing to acquire swap_info + * lock. We do not reuse the returned slots directly but + * move them back to the global pool in a batch. This + * allows the slots to coaellesce and reduce fragmentation. + * + * The swap entry allocated is marked with SWAP_HAS_CACHE + * flag in map_count that prevents it from being allocated + * again from the global pool. + * + * The swap slots cache is protected by a mutex instead of + * a spin lock as when we search for slots with scan_swap_map, + * we can possibly sleep. + */ + +#include <linux/swap_slots.h> +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/vmalloc.h> +#include <linux/mutex.h> + +#ifdef CONFIG_SWAP + +static DEFINE_PER_CPU(struct swap_slots_cache, swp_slots); +static bool swap_slot_cache_active; +bool swap_slot_cache_enabled; +static bool swap_slot_cache_initialized; +DEFINE_MUTEX(swap_slots_cache_mutex); +/* Serialize swap slots cache enable/disable operations */ +DEFINE_MUTEX(swap_slots_cache_enable_mutex); + +static void __drain_swap_slots_cache(unsigned int type); +static void deactivate_swap_slots_cache(void); +static void reactivate_swap_slots_cache(void); + +#define use_swap_slot_cache (swap_slot_cache_active && \ + swap_slot_cache_enabled && swap_slot_cache_initialized) +#define SLOTS_CACHE 0x1 +#define SLOTS_CACHE_RET 0x2 + +static void deactivate_swap_slots_cache(void) +{ + mutex_lock(&swap_slots_cache_mutex); + swap_slot_cache_active = false; + __drain_swap_slots_cache(SLOTS_CACHE|SLOTS_CACHE_RET); + mutex_unlock(&swap_slots_cache_mutex); +} + +static void reactivate_swap_slots_cache(void) +{ + mutex_lock(&swap_slots_cache_mutex); + swap_slot_cache_active = true; + mutex_unlock(&swap_slots_cache_mutex); +} + +/* Must not be called with cpu hot plug lock */ +void disable_swap_slots_cache_lock(void) +{ + mutex_lock(&swap_slots_cache_enable_mutex); + swap_slot_cache_enabled = false; + if (swap_slot_cache_initialized) { + /* serialize with cpu hotplug operations */ + get_online_cpus(); + __drain_swap_slots_cache(SLOTS_CACHE|SLOTS_CACHE_RET); + put_online_cpus(); + } +} + +static void __reenable_swap_slots_cache(void) +{ + swap_slot_cache_enabled = has_usable_swap(); +} + +void reenable_swap_slots_cache_unlock(void) +{ + __reenable_swap_slots_cache(); + mutex_unlock(&swap_slots_cache_enable_mutex); +} + +static bool check_cache_active(void) +{ + long pages; + + if (!swap_slot_cache_enabled || !swap_slot_cache_initialized) + return false; + + pages = get_nr_swap_pages(); + if (!swap_slot_cache_active) { + if (pages > num_online_cpus() * + THRESHOLD_ACTIVATE_SWAP_SLOTS_CACHE) + reactivate_swap_slots_cache(); + goto out; + } + + /* if global pool of slot caches too low, deactivate cache */ + if (pages < num_online_cpus() * THRESHOLD_DEACTIVATE_SWAP_SLOTS_CACHE) + deactivate_swap_slots_cache(); +out: + return swap_slot_cache_active; +} + +static int alloc_swap_slot_cache(unsigned int cpu) +{ + struct swap_slots_cache *cache; + swp_entry_t *slots, *slots_ret; + + /* + * Do allocation outside swap_slots_cache_mutex + * as vzalloc could trigger reclaim and get_swap_page, + * which can lock swap_slots_cache_mutex. + */ + slots = vzalloc(sizeof(swp_entry_t) * SWAP_SLOTS_CACHE_SIZE); + if (!slots) + return -ENOMEM; + + slots_ret = vzalloc(sizeof(swp_entry_t) * SWAP_SLOTS_CACHE_SIZE); + if (!slots_ret) { + vfree(slots); + return -ENOMEM; + } + + mutex_lock(&swap_slots_cache_mutex); + cache = &per_cpu(swp_slots, cpu); + if (cache->slots || cache->slots_ret) + /* cache already allocated */ + goto out; + if (!cache->lock_initialized) { + mutex_init(&cache->alloc_lock); + spin_lock_init(&cache->free_lock); + cache->lock_initialized = true; + } + cache->nr = 0; + cache->cur = 0; + cache->n_ret = 0; + cache->slots = slots; + slots = NULL; + cache->slots_ret = slots_ret; + slots_ret = NULL; +out: + mutex_unlock(&swap_slots_cache_mutex); + if (slots) + vfree(slots); + if (slots_ret) + vfree(slots_ret); + return 0; +} + +static void drain_slots_cache_cpu(unsigned int cpu, unsigned int type, + bool free_slots) +{ + struct swap_slots_cache *cache; + swp_entry_t *slots = NULL; + + cache = &per_cpu(swp_slots, cpu); + if ((type & SLOTS_CACHE) && cache->slots) { + mutex_lock(&cache->alloc_lock); + swapcache_free_entries(cache->slots + cache->cur, cache->nr); + cache->cur = 0; + cache->nr = 0; + if (free_slots && cache->slots) { + vfree(cache->slots); + cache->slots = NULL; + } + mutex_unlock(&cache->alloc_lock); + } + if ((type & SLOTS_CACHE_RET) && cache->slots_ret) { + spin_lock_irq(&cache->free_lock); + swapcache_free_entries(cache->slots_ret, cache->n_ret); + cache->n_ret = 0; + if (free_slots && cache->slots_ret) { + slots = cache->slots_ret; + cache->slots_ret = NULL; + } + spin_unlock_irq(&cache->free_lock); + if (slots) + vfree(slots); + } +} + +static void __drain_swap_slots_cache(unsigned int type) +{ + unsigned int cpu; + + /* + * This function is called during + * 1) swapoff, when we have to make sure no + * left over slots are in cache when we remove + * a swap device; + * 2) disabling of swap slot cache, when we run low + * on swap slots when allocating memory and need + * to return swap slots to global pool. + * + * We cannot acquire cpu hot plug lock here as + * this function can be invoked in the cpu + * hot plug path: + * cpu_up -> lock cpu_hotplug -> cpu hotplug state callback + * -> memory allocation -> direct reclaim -> get_swap_page + * -> drain_swap_slots_cache + * + * Hence the loop over current online cpu below could miss cpu that + * is being brought online but not yet marked as online. + * That is okay as we do not schedule and run anything on a + * cpu before it has been marked online. Hence, we will not + * fill any swap slots in slots cache of such cpu. + * There are no slots on such cpu that need to be drained. + */ + for_each_online_cpu(cpu) + drain_slots_cache_cpu(cpu, type, false); +} + +static int free_slot_cache(unsigned int cpu) +{ + mutex_lock(&swap_slots_cache_mutex); + drain_slots_cache_cpu(cpu, SLOTS_CACHE | SLOTS_CACHE_RET, true); + mutex_unlock(&swap_slots_cache_mutex); + return 0; +} + +int enable_swap_slots_cache(void) +{ + int ret = 0; + + mutex_lock(&swap_slots_cache_enable_mutex); + if (swap_slot_cache_initialized) { + __reenable_swap_slots_cache(); + goto out_unlock; + } + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "swap_slots_cache", + alloc_swap_slot_cache, free_slot_cache); + 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: + mutex_unlock(&swap_slots_cache_enable_mutex); + return 0; +} + +/* called with swap slot cache's alloc lock held */ +static int refill_swap_slots_cache(struct swap_slots_cache *cache) +{ + if (!use_swap_slot_cache || cache->nr) + return 0; + + cache->cur = 0; + if (swap_slot_cache_active) + cache->nr = get_swap_pages(SWAP_SLOTS_CACHE_SIZE, cache->slots); + + return cache->nr; +} + +int free_swap_slot(swp_entry_t entry) +{ + struct swap_slots_cache *cache; + + cache = &get_cpu_var(swp_slots); + if (use_swap_slot_cache && cache->slots_ret) { + spin_lock_irq(&cache->free_lock); + /* Swap slots cache may be deactivated before acquiring lock */ + if (!use_swap_slot_cache) { + spin_unlock_irq(&cache->free_lock); + goto direct_free; + } + if (cache->n_ret >= SWAP_SLOTS_CACHE_SIZE) { + /* + * Return slots to global pool. + * The current swap_map value is SWAP_HAS_CACHE. + * Set it to 0 to indicate it is available for + * allocation in global pool + */ + swapcache_free_entries(cache->slots_ret, cache->n_ret); + cache->n_ret = 0; + } + cache->slots_ret[cache->n_ret++] = entry; + spin_unlock_irq(&cache->free_lock); + } else { +direct_free: + swapcache_free_entries(&entry, 1); + } + put_cpu_var(swp_slots); + + return 0; +} + +swp_entry_t get_swap_page(void) +{ + swp_entry_t entry, *pentry; + struct swap_slots_cache *cache; + + /* + * Preemption is allowed here, because we may sleep + * in refill_swap_slots_cache(). But it is safe, because + * accesses to the per-CPU data structure are protected by the + * mutex cache->alloc_lock. + * + * The alloc path here does not touch cache->slots_ret + * so cache->free_lock is not taken. + */ + cache = raw_cpu_ptr(&swp_slots); + + entry.val = 0; + if (check_cache_active()) { + mutex_lock(&cache->alloc_lock); + if (cache->slots) { +repeat: + if (cache->nr) { + pentry = &cache->slots[cache->cur++]; + entry = *pentry; + pentry->val = 0; + cache->nr--; + } else { + if (refill_swap_slots_cache(cache)) + goto repeat; + } + } + mutex_unlock(&cache->alloc_lock); + if (entry.val) + return entry; + } + + get_swap_pages(1, &entry); + + return entry; +} + +#endif /* CONFIG_SWAP */ diff --git a/mm/swap_state.c b/mm/swap_state.c index 35d7e0ee1c77..7bfb9bd1ca21 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -17,6 +17,8 @@ #include <linux/blkdev.h> #include <linux/pagevec.h> #include <linux/migrate.h> +#include <linux/vmalloc.h> +#include <linux/swap_slots.h> #include <asm/pgtable.h> @@ -32,15 +34,8 @@ static const struct address_space_operations swap_aops = { #endif }; -struct address_space swapper_spaces[MAX_SWAPFILES] = { - [0 ... MAX_SWAPFILES - 1] = { - .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN), - .i_mmap_writable = ATOMIC_INIT(0), - .a_ops = &swap_aops, - /* swap cache doesn't use writeback related tags */ - .flags = 1 << AS_NO_WRITEBACK_TAGS, - } -}; +struct address_space *swapper_spaces[MAX_SWAPFILES]; +static unsigned int nr_swapper_spaces[MAX_SWAPFILES]; #define INC_CACHE_INFO(x) do { swap_cache_info.x++; } while (0) @@ -53,11 +48,26 @@ static struct { unsigned long total_swapcache_pages(void) { - int i; + unsigned int i, j, nr; unsigned long ret = 0; + struct address_space *spaces; - for (i = 0; i < MAX_SWAPFILES; i++) - ret += swapper_spaces[i].nrpages; + rcu_read_lock(); + for (i = 0; i < MAX_SWAPFILES; i++) { + /* + * The corresponding entries in nr_swapper_spaces and + * swapper_spaces will be reused only after at least + * one grace period. So it is impossible for them + * belongs to different usage. + */ + nr = nr_swapper_spaces[i]; + spaces = rcu_dereference(swapper_spaces[i]); + if (!nr || !spaces) + continue; + for (j = 0; j < nr; j++) + ret += spaces[j].nrpages; + } + rcu_read_unlock(); return ret; } @@ -315,6 +325,17 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, break; /* + * Just skip read ahead for unused swap slot. + * During swap_off when swap_slot_cache is disabled, + * we have to handle the race between putting + * swap entry in swap cache and marking swap slot + * as SWAP_HAS_CACHE. That's done in later part of code or + * else swap_off will be aborted if we return NULL. + */ + if (!__swp_swapcount(entry) && swap_slot_cache_enabled) + break; + + /* * Get a new page to read into from swap. */ if (!new_page) { @@ -339,17 +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; @@ -505,3 +516,38 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, skip: return read_swap_cache_async(entry, gfp_mask, vma, addr); } + +int init_swap_address_space(unsigned int type, unsigned long nr_pages) +{ + struct address_space *spaces, *space; + unsigned int i, nr; + + nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES); + spaces = vzalloc(sizeof(struct address_space) * nr); + if (!spaces) + return -ENOMEM; + for (i = 0; i < nr; i++) { + space = spaces + i; + INIT_RADIX_TREE(&space->page_tree, GFP_ATOMIC|__GFP_NOWARN); + atomic_set(&space->i_mmap_writable, 0); + space->a_ops = &swap_aops; + /* swap cache doesn't use writeback related tags */ + mapping_set_no_writeback_tags(space); + spin_lock_init(&space->tree_lock); + } + nr_swapper_spaces[type] = nr; + rcu_assign_pointer(swapper_spaces[type], spaces); + + return 0; +} + +void exit_swap_address_space(unsigned int type) +{ + struct address_space *spaces; + + spaces = swapper_spaces[type]; + nr_swapper_spaces[type] = 0; + rcu_assign_pointer(swapper_spaces[type], NULL); + synchronize_rcu(); + kvfree(spaces); +} diff --git a/mm/swapfile.c b/mm/swapfile.c index 4761701d1721..b86b2aca3fb9 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -6,6 +6,8 @@ */ #include <linux/mm.h> +#include <linux/sched/mm.h> +#include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> @@ -34,6 +36,7 @@ #include <linux/frontswap.h> #include <linux/swapfile.h> #include <linux/export.h> +#include <linux/swap_slots.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -257,6 +260,47 @@ static inline void cluster_set_null(struct swap_cluster_info *info) info->data = 0; } +static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, + unsigned long offset) +{ + struct swap_cluster_info *ci; + + ci = si->cluster_info; + if (ci) { + ci += offset / SWAPFILE_CLUSTER; + spin_lock(&ci->lock); + } + return ci; +} + +static inline void unlock_cluster(struct swap_cluster_info *ci) +{ + if (ci) + spin_unlock(&ci->lock); +} + +static inline struct swap_cluster_info *lock_cluster_or_swap_info( + struct swap_info_struct *si, + unsigned long offset) +{ + struct swap_cluster_info *ci; + + ci = lock_cluster(si, offset); + if (!ci) + spin_lock(&si->lock); + + return ci; +} + +static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, + struct swap_cluster_info *ci) +{ + if (ci) + unlock_cluster(ci); + else + spin_unlock(&si->lock); +} + static inline bool cluster_list_empty(struct swap_cluster_list *list) { return cluster_is_null(&list->head); @@ -281,9 +325,17 @@ static void cluster_list_add_tail(struct swap_cluster_list *list, cluster_set_next_flag(&list->head, idx, 0); cluster_set_next_flag(&list->tail, idx, 0); } else { + struct swap_cluster_info *ci_tail; unsigned int tail = cluster_next(&list->tail); - cluster_set_next(&ci[tail], idx); + /* + * Nested cluster lock, but both cluster locks are + * only acquired when we held swap_info_struct->lock + */ + ci_tail = ci + tail; + spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING); + cluster_set_next(ci_tail, idx); + spin_unlock(&ci_tail->lock); cluster_set_next_flag(&list->tail, idx, 0); } } @@ -328,7 +380,7 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si, */ static void swap_do_scheduled_discard(struct swap_info_struct *si) { - struct swap_cluster_info *info; + struct swap_cluster_info *info, *ci; unsigned int idx; info = si->cluster_info; @@ -341,10 +393,14 @@ static void swap_do_scheduled_discard(struct swap_info_struct *si) SWAPFILE_CLUSTER); spin_lock(&si->lock); - cluster_set_flag(&info[idx], CLUSTER_FLAG_FREE); + ci = lock_cluster(si, idx * SWAPFILE_CLUSTER); + cluster_set_flag(ci, CLUSTER_FLAG_FREE); + unlock_cluster(ci); cluster_list_add_tail(&si->free_clusters, info, idx); + ci = lock_cluster(si, idx * SWAPFILE_CLUSTER); memset(si->swap_map + idx * SWAPFILE_CLUSTER, 0, SWAPFILE_CLUSTER); + unlock_cluster(ci); } } @@ -443,12 +499,13 @@ scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, * Try to get a swap entry from current cpu's swap entry pool (a cluster). This * might involve allocating a new cluster for current CPU too. */ -static void scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, +static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, unsigned long *offset, unsigned long *scan_base) { struct percpu_cluster *cluster; + struct swap_cluster_info *ci; bool found_free; - unsigned long tmp; + unsigned long tmp, max; new_cluster: cluster = this_cpu_ptr(si->percpu_cluster); @@ -466,7 +523,7 @@ new_cluster: *scan_base = *offset = si->cluster_next; goto new_cluster; } else - return; + return false; } found_free = false; @@ -476,14 +533,21 @@ new_cluster: * check if there is still free entry in the cluster */ tmp = cluster->next; - while (tmp < si->max && tmp < (cluster_next(&cluster->index) + 1) * - SWAPFILE_CLUSTER) { + max = min_t(unsigned long, si->max, + (cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER); + if (tmp >= max) { + cluster_set_null(&cluster->index); + goto new_cluster; + } + ci = lock_cluster(si, tmp); + while (tmp < max) { if (!si->swap_map[tmp]) { found_free = true; break; } tmp++; } + unlock_cluster(ci); if (!found_free) { cluster_set_null(&cluster->index); goto new_cluster; @@ -491,15 +555,22 @@ new_cluster: cluster->next = tmp + 1; *offset = tmp; *scan_base = tmp; + return found_free; } -static unsigned long scan_swap_map(struct swap_info_struct *si, - unsigned char usage) +static int scan_swap_map_slots(struct swap_info_struct *si, + unsigned char usage, int nr, + swp_entry_t slots[]) { + struct swap_cluster_info *ci; unsigned long offset; unsigned long scan_base; unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; + int n_ret = 0; + + if (nr > SWAP_BATCH) + nr = SWAP_BATCH; /* * We try to cluster swap pages by allocating them sequentially @@ -517,8 +588,10 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, /* SSD algorithm */ if (si->cluster_info) { - scan_swap_map_try_ssd_cluster(si, &offset, &scan_base); - goto checks; + if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) + goto checks; + else + goto scan; } if (unlikely(!si->cluster_nr--)) { @@ -562,8 +635,14 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, checks: if (si->cluster_info) { - while (scan_swap_map_ssd_cluster_conflict(si, offset)) - scan_swap_map_try_ssd_cluster(si, &offset, &scan_base); + while (scan_swap_map_ssd_cluster_conflict(si, offset)) { + /* take a break if we already got some slots */ + if (n_ret) + goto done; + if (!scan_swap_map_try_ssd_cluster(si, &offset, + &scan_base)) + goto scan; + } } if (!(si->flags & SWP_WRITEOK)) goto no_page; @@ -572,9 +651,11 @@ checks: if (offset > si->highest_bit) scan_base = offset = si->lowest_bit; + ci = lock_cluster(si, offset); /* reuse swap entry of cache-only swap if not busy. */ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { int swap_was_freed; + unlock_cluster(ci); spin_unlock(&si->lock); swap_was_freed = __try_to_reclaim_swap(si, offset); spin_lock(&si->lock); @@ -584,8 +665,16 @@ checks: goto scan; /* check next one */ } - if (si->swap_map[offset]) - goto scan; + if (si->swap_map[offset]) { + unlock_cluster(ci); + if (!n_ret) + goto scan; + 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++; @@ -599,12 +688,44 @@ 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); si->cluster_next = offset + 1; - si->flags -= SWP_SCANNING; + slots[n_ret++] = swp_entry(si->type, offset); + + /* got enough slots or reach max slots? */ + if ((n_ret == nr) || (offset >= si->highest_bit)) + goto done; + + /* search for next available slot */ + + /* time to take a break? */ + if (unlikely(--latency_ration < 0)) { + if (n_ret) + goto done; + spin_unlock(&si->lock); + cond_resched(); + spin_lock(&si->lock); + latency_ration = LATENCY_LIMIT; + } + + /* try to get more slots in cluster */ + if (si->cluster_info) { + if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) + goto checks; + else + goto done; + } + /* non-ssd case */ + ++offset; + + /* non-ssd case, still more slots in cluster? */ + if (si->cluster_nr && !si->swap_map[offset]) { + --si->cluster_nr; + goto checks; + } - return offset; +done: + si->flags -= SWP_SCANNING; + return n_ret; scan: spin_unlock(&si->lock); @@ -642,17 +763,41 @@ scan: no_page: si->flags -= SWP_SCANNING; - return 0; + return n_ret; } -swp_entry_t get_swap_page(void) +static unsigned long scan_swap_map(struct swap_info_struct *si, + unsigned char usage) +{ + swp_entry_t entry; + int n_ret; + + n_ret = scan_swap_map_slots(si, usage, 1, &entry); + + if (n_ret) + return swp_offset(entry); + else + return 0; + +} + +int get_swap_pages(int n_goal, swp_entry_t swp_entries[]) { struct swap_info_struct *si, *next; - pgoff_t offset; + long avail_pgs; + int n_ret = 0; - if (atomic_long_read(&nr_swap_pages) <= 0) + avail_pgs = atomic_long_read(&nr_swap_pages); + if (avail_pgs <= 0) goto noswap; - atomic_long_dec(&nr_swap_pages); + + if (n_goal > SWAP_BATCH) + n_goal = SWAP_BATCH; + + if (n_goal > avail_pgs) + n_goal = avail_pgs; + + atomic_long_sub(n_goal, &nr_swap_pages); spin_lock(&swap_avail_lock); @@ -678,14 +823,14 @@ start_over: spin_unlock(&si->lock); goto nextsi; } - - /* This is called for allocating swap entry for cache */ - offset = scan_swap_map(si, SWAP_HAS_CACHE); + n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, + n_goal, swp_entries); spin_unlock(&si->lock); - if (offset) - return swp_entry(si->type, offset); + if (n_ret) + goto check_out; pr_debug("scan_swap_map of si %d failed to find offset\n", - si->type); + si->type); + spin_lock(&swap_avail_lock); nextsi: /* @@ -696,7 +841,8 @@ nextsi: * up between us dropping swap_avail_lock and taking si->lock. * Since we dropped the swap_avail_lock, the swap_avail_head * list may have been modified; so if next is still in the - * swap_avail_head list then try it, otherwise start over. + * swap_avail_head list then try it, otherwise start over + * if we have not gotten any slots. */ if (plist_node_empty(&next->avail_list)) goto start_over; @@ -704,9 +850,11 @@ nextsi: spin_unlock(&swap_avail_lock); - atomic_long_inc(&nr_swap_pages); +check_out: + if (n_ret < n_goal) + atomic_long_add((long) (n_goal-n_ret), &nr_swap_pages); noswap: - return (swp_entry_t) {0}; + return n_ret; } /* The only caller of this function is now suspend routine */ @@ -731,7 +879,7 @@ swp_entry_t get_swap_page_of_type(int type) return (swp_entry_t) {0}; } -static struct swap_info_struct *swap_info_get(swp_entry_t entry) +static struct swap_info_struct *__swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; unsigned long offset, type; @@ -747,34 +895,76 @@ static struct swap_info_struct *swap_info_get(swp_entry_t entry) offset = swp_offset(entry); if (offset >= p->max) goto bad_offset; - if (!p->swap_map[offset]) - goto bad_free; - spin_lock(&p->lock); return p; -bad_free: - pr_err("swap_free: %s%08lx\n", Unused_offset, entry.val); - goto out; bad_offset: - pr_err("swap_free: %s%08lx\n", Bad_offset, entry.val); + pr_err("swap_info_get: %s%08lx\n", Bad_offset, entry.val); goto out; bad_device: - pr_err("swap_free: %s%08lx\n", Unused_file, entry.val); + pr_err("swap_info_get: %s%08lx\n", Unused_file, entry.val); goto out; bad_nofile: - pr_err("swap_free: %s%08lx\n", Bad_file, entry.val); + pr_err("swap_info_get: %s%08lx\n", Bad_file, entry.val); +out: + return NULL; +} + +static struct swap_info_struct *_swap_info_get(swp_entry_t entry) +{ + struct swap_info_struct *p; + + p = __swap_info_get(entry); + if (!p) + goto out; + if (!p->swap_map[swp_offset(entry)]) + goto bad_free; + return p; + +bad_free: + pr_err("swap_info_get: %s%08lx\n", Unused_offset, entry.val); + goto out; out: return NULL; } -static unsigned char swap_entry_free(struct swap_info_struct *p, - swp_entry_t entry, unsigned char usage) +static struct swap_info_struct *swap_info_get(swp_entry_t entry) { + struct swap_info_struct *p; + + p = _swap_info_get(entry); + if (p) + spin_lock(&p->lock); + return p; +} + +static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, + struct swap_info_struct *q) +{ + struct swap_info_struct *p; + + p = _swap_info_get(entry); + + if (p != q) { + if (q != NULL) + spin_unlock(&q->lock); + if (p != NULL) + spin_lock(&p->lock); + } + return p; +} + +static unsigned char __swap_entry_free(struct swap_info_struct *p, + swp_entry_t entry, unsigned char usage) +{ + struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char count; unsigned char has_cache; + ci = lock_cluster_or_swap_info(p, offset); + count = p->swap_map[offset]; + has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; @@ -798,38 +988,52 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, } usage = count | has_cache; - p->swap_map[offset] = usage; - - /* free if no reference */ - if (!usage) { - mem_cgroup_uncharge_swap(entry); - dec_cluster_info_page(p, p->cluster_info, offset); - if (offset < p->lowest_bit) - p->lowest_bit = offset; - if (offset > p->highest_bit) { - bool was_full = !p->highest_bit; - p->highest_bit = offset; - if (was_full && (p->flags & SWP_WRITEOK)) { - spin_lock(&swap_avail_lock); - WARN_ON(!plist_node_empty(&p->avail_list)); - if (plist_node_empty(&p->avail_list)) - plist_add(&p->avail_list, - &swap_avail_head); - spin_unlock(&swap_avail_lock); - } - } - atomic_long_inc(&nr_swap_pages); - p->inuse_pages--; - frontswap_invalidate_page(p->type, offset); - if (p->flags & SWP_BLKDEV) { - struct gendisk *disk = p->bdev->bd_disk; - if (disk->fops->swap_slot_free_notify) - disk->fops->swap_slot_free_notify(p->bdev, - offset); + p->swap_map[offset] = usage ? : SWAP_HAS_CACHE; + + unlock_cluster_or_swap_info(p, ci); + + return usage; +} + +static void swap_entry_free(struct swap_info_struct *p, swp_entry_t entry) +{ + struct swap_cluster_info *ci; + unsigned long offset = swp_offset(entry); + unsigned char count; + + ci = lock_cluster(p, offset); + count = p->swap_map[offset]; + VM_BUG_ON(count != SWAP_HAS_CACHE); + p->swap_map[offset] = 0; + dec_cluster_info_page(p, p->cluster_info, offset); + unlock_cluster(ci); + + mem_cgroup_uncharge_swap(entry); + if (offset < p->lowest_bit) + p->lowest_bit = offset; + if (offset > p->highest_bit) { + bool was_full = !p->highest_bit; + + p->highest_bit = offset; + if (was_full && (p->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + WARN_ON(!plist_node_empty(&p->avail_list)); + if (plist_node_empty(&p->avail_list)) + plist_add(&p->avail_list, + &swap_avail_head); + spin_unlock(&swap_avail_lock); } } + atomic_long_inc(&nr_swap_pages); + p->inuse_pages--; + frontswap_invalidate_page(p->type, offset); + if (p->flags & SWP_BLKDEV) { + struct gendisk *disk = p->bdev->bd_disk; - return usage; + if (disk->fops->swap_slot_free_notify) + disk->fops->swap_slot_free_notify(p->bdev, + offset); + } } /* @@ -840,10 +1044,10 @@ void swap_free(swp_entry_t entry) { struct swap_info_struct *p; - p = swap_info_get(entry); + p = _swap_info_get(entry); if (p) { - swap_entry_free(p, entry, 1); - spin_unlock(&p->lock); + if (!__swap_entry_free(p, entry, 1)) + free_swap_slot(entry); } } @@ -854,13 +1058,33 @@ void swapcache_free(swp_entry_t entry) { struct swap_info_struct *p; - p = swap_info_get(entry); + p = _swap_info_get(entry); if (p) { - swap_entry_free(p, entry, SWAP_HAS_CACHE); - spin_unlock(&p->lock); + if (!__swap_entry_free(p, entry, SWAP_HAS_CACHE)) + free_swap_slot(entry); } } +void swapcache_free_entries(swp_entry_t *entries, int n) +{ + struct swap_info_struct *p, *prev; + int i; + + if (n <= 0) + return; + + prev = NULL; + p = NULL; + for (i = 0; i < n; ++i) { + p = swap_info_get_cont(entries[i], prev); + if (p) + swap_entry_free(p, entries[i]); + prev = p; + } + if (p) + spin_unlock(&p->lock); +} + /* * How many references to page are currently swapped out? * This does not give an exact answer when swap count is continued, @@ -870,17 +1094,49 @@ int page_swapcount(struct page *page) { int count = 0; struct swap_info_struct *p; + struct swap_cluster_info *ci; swp_entry_t entry; + unsigned long offset; entry.val = page_private(page); - p = swap_info_get(entry); + p = _swap_info_get(entry); if (p) { - count = swap_count(p->swap_map[swp_offset(entry)]); - spin_unlock(&p->lock); + offset = swp_offset(entry); + ci = lock_cluster_or_swap_info(p, offset); + count = swap_count(p->swap_map[offset]); + unlock_cluster_or_swap_info(p, ci); } 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, + * but does include the high COUNT_CONTINUED flag to allow for that. + */ +int __swp_swapcount(swp_entry_t entry) +{ + int count = 0; + struct swap_info_struct *si; + + si = __swap_info_get(entry); + if (si) + count = swap_swapcount(si, entry); + return count; +} + /* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. @@ -889,22 +1145,26 @@ int swp_swapcount(swp_entry_t entry) { int count, tmp_count, n; struct swap_info_struct *p; + struct swap_cluster_info *ci; struct page *page; pgoff_t offset; unsigned char *map; - p = swap_info_get(entry); + p = _swap_info_get(entry); if (!p) return 0; - count = swap_count(p->swap_map[swp_offset(entry)]); + offset = swp_offset(entry); + + ci = lock_cluster_or_swap_info(p, offset); + + count = swap_count(p->swap_map[offset]); if (!(count & COUNT_CONTINUED)) goto out; count &= ~COUNT_CONTINUED; n = SWAP_MAP_MAX + 1; - offset = swp_offset(entry); page = vmalloc_to_page(p->swap_map + offset); offset &= ~PAGE_MASK; VM_BUG_ON(page_private(page) != SWP_CONTINUED); @@ -919,7 +1179,7 @@ int swp_swapcount(swp_entry_t entry) n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: - spin_unlock(&p->lock); + unlock_cluster_or_swap_info(p, ci); return count; } @@ -1011,21 +1271,23 @@ int free_swap_and_cache(swp_entry_t entry) { struct swap_info_struct *p; struct page *page = NULL; + unsigned char count; if (non_swap_entry(entry)) return 1; - p = swap_info_get(entry); + p = _swap_info_get(entry); if (p) { - if (swap_entry_free(p, entry, 1) == SWAP_HAS_CACHE) { + count = __swap_entry_free(p, entry, 1); + if (count == SWAP_HAS_CACHE) { page = find_get_page(swap_address_space(entry), swp_offset(entry)); if (page && !trylock_page(page)) { put_page(page); page = NULL; } - } - spin_unlock(&p->lock); + } else if (!count) + free_swap_slot(entry); } if (page) { /* @@ -1033,7 +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); } @@ -1259,7 +1522,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, return 0; } -static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd, +static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, swp_entry_t entry, struct page *page) { @@ -1267,7 +1530,7 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long next; int ret; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) @@ -1279,6 +1542,26 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd, return 0; } +static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, + unsigned long addr, unsigned long end, + swp_entry_t entry, struct page *page) +{ + p4d_t *p4d; + unsigned long next; + int ret; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + ret = unuse_pud_range(vma, p4d, addr, next, entry, page); + if (ret) + return ret; + } while (p4d++, addr = next, addr != end); + return 0; +} + static int unuse_vma(struct vm_area_struct *vma, swp_entry_t entry, struct page *page) { @@ -1302,7 +1585,7 @@ static int unuse_vma(struct vm_area_struct *vma, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - ret = unuse_pud_range(vma, pgd, addr, next, entry, page); + ret = unuse_p4d_range(vma, pgd, addr, next, entry, page); if (ret) return ret; } while (pgd++, addr = next, addr != end); @@ -1415,7 +1698,7 @@ int try_to_unuse(unsigned int type, bool frontswap, * that. */ start_mm = &init_mm; - atomic_inc(&init_mm.mm_users); + mmget(&init_mm); /* * Keep on scanning until all entries have gone. Usually, @@ -1464,7 +1747,7 @@ int try_to_unuse(unsigned int type, bool frontswap, if (atomic_read(&start_mm->mm_users) == 1) { mmput(start_mm); start_mm = &init_mm; - atomic_inc(&init_mm.mm_users); + mmget(&init_mm); } /* @@ -1501,13 +1784,13 @@ int try_to_unuse(unsigned int type, bool frontswap, struct mm_struct *prev_mm = start_mm; struct mm_struct *mm; - atomic_inc(&new_start_mm->mm_users); - atomic_inc(&prev_mm->mm_users); + mmget(new_start_mm); + mmget(prev_mm); spin_lock(&mmlist_lock); while (swap_count(*swap_map) && !retval && (p = p->next) != &start_mm->mmlist) { mm = list_entry(p, struct mm_struct, mmlist); - if (!atomic_inc_not_zero(&mm->mm_users)) + if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); @@ -1525,7 +1808,7 @@ int try_to_unuse(unsigned int type, bool frontswap, if (set_start_mm && *swap_map < swcount) { mmput(new_start_mm); - atomic_inc(&mm->mm_users); + mmget(mm); new_start_mm = mm; set_start_mm = 0; } @@ -1853,6 +2136,17 @@ static void reinsert_swap_info(struct swap_info_struct *p) spin_unlock(&swap_lock); } +bool has_usable_swap(void) +{ + bool ret = true; + + spin_lock(&swap_lock); + if (plist_head_empty(&swap_active_head)) + ret = false; + spin_unlock(&swap_lock); + return ret; +} + SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; @@ -1923,6 +2217,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&p->lock); spin_unlock(&swap_lock); + disable_swap_slots_cache_lock(); + set_current_oom_origin(); err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ clear_current_oom_origin(); @@ -1930,9 +2226,12 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); + reenable_swap_slots_cache_unlock(); goto out_dput; } + reenable_swap_slots_cache_unlock(); + flush_work(&p->discard_work); destroy_swap_extents(p); @@ -1975,6 +2274,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) vfree(frontswap_map); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); + exit_swap_address_space(p->type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { @@ -2298,6 +2598,13 @@ static unsigned long read_swap_header(struct swap_info_struct *p, return maxpages; } +#define SWAP_CLUSTER_INFO_COLS \ + DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info)) +#define SWAP_CLUSTER_SPACE_COLS \ + DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER) +#define SWAP_CLUSTER_COLS \ + max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS) + static int setup_swap_map_and_extents(struct swap_info_struct *p, union swap_header *swap_header, unsigned char *swap_map, @@ -2305,11 +2612,12 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, unsigned long maxpages, sector_t *span) { - int i; + unsigned int j, k; unsigned int nr_good_pages; int nr_extents; unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); - unsigned long idx = p->cluster_next / SWAPFILE_CLUSTER; + unsigned long col = p->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS; + unsigned long i, idx; nr_good_pages = maxpages - 1; /* omit header page */ @@ -2357,15 +2665,23 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, if (!cluster_info) return nr_extents; - for (i = 0; i < nr_clusters; i++) { - if (!cluster_count(&cluster_info[idx])) { + + /* + * Reduce false cache line sharing between cluster_info and + * sharing same address space. + */ + for (k = 0; k < SWAP_CLUSTER_COLS; k++) { + j = (k + col) % SWAP_CLUSTER_COLS; + for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { + idx = i * SWAP_CLUSTER_COLS + j; + if (idx >= nr_clusters) + continue; + if (cluster_count(&cluster_info[idx])) + continue; cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); cluster_list_add_tail(&p->free_clusters, cluster_info, idx); } - idx++; - if (idx == nr_clusters) - idx = 0; } return nr_extents; } @@ -2468,6 +2784,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) { int cpu; + unsigned long ci, nr_cluster; p->flags |= SWP_SOLIDSTATE; /* @@ -2475,13 +2792,17 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) * SSD */ p->cluster_next = 1 + (prandom_u32() % p->highest_bit); + nr_cluster = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); - cluster_info = vzalloc(DIV_ROUND_UP(maxpages, - SWAPFILE_CLUSTER) * sizeof(*cluster_info)); + cluster_info = vzalloc(nr_cluster * sizeof(*cluster_info)); if (!cluster_info) { error = -ENOMEM; goto bad_swap; } + + for (ci = 0; ci < nr_cluster; ci++) + spin_lock_init(&((cluster_info + ci)->lock)); + p->percpu_cluster = alloc_percpu(struct percpu_cluster); if (!p->percpu_cluster) { error = -ENOMEM; @@ -2538,6 +2859,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) } } + error = init_swap_address_space(p->type, maxpages); + if (error) + goto bad_swap; + mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER) @@ -2593,6 +2918,8 @@ out: putname(name); if (inode && S_ISREG(inode->i_mode)) inode_unlock(inode); + if (!error) + enable_swap_slots_cache(); return error; } @@ -2627,6 +2954,7 @@ void si_swapinfo(struct sysinfo *val) static int __swap_duplicate(swp_entry_t entry, unsigned char usage) { struct swap_info_struct *p; + struct swap_cluster_info *ci; unsigned long offset, type; unsigned char count; unsigned char has_cache; @@ -2640,10 +2968,10 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) goto bad_file; p = swap_info[type]; offset = swp_offset(entry); - - spin_lock(&p->lock); if (unlikely(offset >= p->max)) - goto unlock_out; + goto out; + + ci = lock_cluster_or_swap_info(p, offset); count = p->swap_map[offset]; @@ -2686,7 +3014,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) p->swap_map[offset] = count | has_cache; unlock_out: - spin_unlock(&p->lock); + unlock_cluster_or_swap_info(p, ci); out: return err; @@ -2775,6 +3103,7 @@ EXPORT_SYMBOL_GPL(__page_file_index); int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; + struct swap_cluster_info *ci; struct page *head; struct page *page; struct page *list_page; @@ -2798,6 +3127,9 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) } offset = swp_offset(entry); + + ci = lock_cluster(si, offset); + count = si->swap_map[offset] & ~SWAP_HAS_CACHE; if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { @@ -2810,6 +3142,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) } if (!page) { + unlock_cluster(ci); spin_unlock(&si->lock); return -ENOMEM; } @@ -2858,6 +3191,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out: + unlock_cluster(ci); spin_unlock(&si->lock); outer: if (page) @@ -2871,7 +3205,8 @@ outer: * into, carry if so, or else fail until a new continuation page is allocated; * when the original swap_map count is decremented from 0 with continuation, * borrow from the continuation and report whether it still holds more. - * Called while __swap_duplicate() or swap_entry_free() holds swap_lock. + * Called while __swap_duplicate() or swap_entry_free() holds swap or cluster + * lock. */ static bool swap_count_continued(struct swap_info_struct *si, pgoff_t offset, unsigned char count) diff --git a/mm/truncate.c b/mm/truncate.c index dd7b24e083c5..83a059e8cd1d 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -20,6 +20,7 @@ #include <linux/task_io_accounting_ops.h> #include <linux/buffer_head.h> /* grr. try_to_release_page, do_invalidatepage */ +#include <linux/shmem_fs.h> #include <linux/cleancache.h> #include <linux/rmap.h> #include "internal.h" @@ -265,9 +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); @@ -362,7 +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 ( ; ; ) { @@ -409,6 +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); @@ -622,7 +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, @@ -685,6 +689,8 @@ int invalidate_inode_pages2_range(struct address_space *mapping, cond_resched(); index++; } + +out: cleancache_invalidate_inode(mapping); return ret; } @@ -785,7 +791,7 @@ EXPORT_SYMBOL(truncate_setsize); */ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) { - int bsize = 1 << inode->i_blkbits; + int bsize = i_blocksize(inode); loff_t rounded_from; struct page *page; pgoff_t index; diff --git a/mm/usercopy.c b/mm/usercopy.c index 8345299e3e3b..a9852b24715d 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -16,15 +16,12 @@ #include <linux/mm.h> #include <linux/slab.h> +#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). @@ -203,17 +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/userfaultfd.c b/mm/userfaultfd.c index af817e5060fb..8bcb501bce60 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -8,12 +8,16 @@ */ #include <linux/mm.h> +#include <linux/sched/signal.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/userfaultfd_k.h> #include <linux/mmu_notifier.h> +#include <linux/hugetlb.h> +#include <linux/pagemap.h> +#include <linux/shmem_fs.h> #include <asm/tlbflush.h> #include "internal.h" @@ -124,20 +128,248 @@ out_unlock: static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; - pmd_t *pmd = NULL; pgd = pgd_offset(mm, address); - pud = pud_alloc(mm, pgd, address); - if (pud) + p4d = p4d_alloc(mm, pgd, address); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, address); + if (!pud) + return NULL; + /* + * Note that we didn't run this because the pmd was + * missing, the *pmd may be already established and in + * turn it may also be a trans_huge_pmd. + */ + return pmd_alloc(mm, pud, address); +} + +#ifdef CONFIG_HUGETLB_PAGE +/* + * __mcopy_atomic processing for HUGETLB vmas. Note that this routine is + * called with mmap_sem held, it will release mmap_sem before returning. + */ +static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, + struct vm_area_struct *dst_vma, + unsigned long dst_start, + unsigned long src_start, + unsigned long len, + bool zeropage) +{ + int vm_alloc_shared = dst_vma->vm_flags & VM_SHARED; + int vm_shared = dst_vma->vm_flags & VM_SHARED; + ssize_t err; + pte_t *dst_pte; + unsigned long src_addr, dst_addr; + long copied; + struct page *page; + struct hstate *h; + unsigned long vma_hpagesize; + pgoff_t idx; + u32 hash; + struct address_space *mapping; + + /* + * There is no default zero huge page for all huge page sizes as + * supported by hugetlb. A PMD_SIZE huge pages may exist as used + * by THP. Since we can not reliably insert a zero page, this + * feature is not supported. + */ + if (zeropage) { + up_read(&dst_mm->mmap_sem); + return -EINVAL; + } + + src_addr = src_start; + dst_addr = dst_start; + copied = 0; + page = NULL; + vma_hpagesize = vma_kernel_pagesize(dst_vma); + + /* + * Validate alignment based on huge page size + */ + err = -EINVAL; + if (dst_start & (vma_hpagesize - 1) || len & (vma_hpagesize - 1)) + goto out_unlock; + +retry: + /* + * On routine entry dst_vma is set. If we had to drop mmap_sem and + * retry, dst_vma will be set to NULL and we must lookup again. + */ + if (!dst_vma) { + err = -ENOENT; + dst_vma = find_vma(dst_mm, dst_start); + if (!dst_vma || !is_vm_hugetlb_page(dst_vma)) + goto out_unlock; + /* + * Only allow __mcopy_atomic_hugetlb on userfaultfd + * registered ranges. + */ + if (!dst_vma->vm_userfaultfd_ctx.ctx) + goto out_unlock; + + if (dst_start < dst_vma->vm_start || + dst_start + len > dst_vma->vm_end) + goto out_unlock; + + err = -EINVAL; + if (vma_hpagesize != vma_kernel_pagesize(dst_vma)) + goto out_unlock; + + vm_shared = dst_vma->vm_flags & VM_SHARED; + } + + if (WARN_ON(dst_addr & (vma_hpagesize - 1) || + (len - copied) & (vma_hpagesize - 1))) + goto out_unlock; + + /* + * If not shared, ensure the dst_vma has a anon_vma. + */ + err = -ENOMEM; + if (!vm_shared) { + if (unlikely(anon_vma_prepare(dst_vma))) + goto out_unlock; + } + + h = hstate_vma(dst_vma); + + while (src_addr < src_start + len) { + pte_t dst_pteval; + + BUG_ON(dst_addr >= dst_start + len); + VM_BUG_ON(dst_addr & ~huge_page_mask(h)); + + /* + * Serialize via hugetlb_fault_mutex + */ + idx = linear_page_index(dst_vma, dst_addr); + mapping = dst_vma->vm_file->f_mapping; + hash = hugetlb_fault_mutex_hash(h, dst_mm, dst_vma, mapping, + idx, dst_addr); + mutex_lock(&hugetlb_fault_mutex_table[hash]); + + err = -ENOMEM; + dst_pte = huge_pte_alloc(dst_mm, dst_addr, huge_page_size(h)); + if (!dst_pte) { + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + goto out_unlock; + } + + err = -EEXIST; + dst_pteval = huge_ptep_get(dst_pte); + if (!huge_pte_none(dst_pteval)) { + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + goto out_unlock; + } + + err = hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, + dst_addr, src_addr, &page); + + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + vm_alloc_shared = vm_shared; + + cond_resched(); + + if (unlikely(err == -EFAULT)) { + up_read(&dst_mm->mmap_sem); + BUG_ON(!page); + + err = copy_huge_page_from_user(page, + (const void __user *)src_addr, + pages_per_huge_page(h), true); + if (unlikely(err)) { + err = -EFAULT; + goto out; + } + down_read(&dst_mm->mmap_sem); + + dst_vma = NULL; + goto retry; + } else + BUG_ON(page); + + if (!err) { + dst_addr += vma_hpagesize; + src_addr += vma_hpagesize; + copied += vma_hpagesize; + + if (fatal_signal_pending(current)) + err = -EINTR; + } + if (err) + break; + } + +out_unlock: + up_read(&dst_mm->mmap_sem); +out: + if (page) { /* - * Note that we didn't run this because the pmd was - * missing, the *pmd may be already established and in - * turn it may also be a trans_huge_pmd. + * We encountered an error and are about to free a newly + * allocated huge page. + * + * Reservation handling is very subtle, and is different for + * private and shared mappings. See the routine + * restore_reserve_on_error for details. Unfortunately, we + * can not call restore_reserve_on_error now as it would + * require holding mmap_sem. + * + * If a reservation for the page existed in the reservation + * map of a private mapping, the map was modified to indicate + * the reservation was consumed when the page was allocated. + * We clear the PagePrivate flag now so that the global + * reserve count will not be incremented in free_huge_page. + * The reservation map will still indicate the reservation + * was consumed and possibly prevent later page allocation. + * This is better than leaking a global reservation. If no + * reservation existed, it is still safe to clear PagePrivate + * as no adjustments to reservation counts were made during + * allocation. + * + * The reservation map for shared mappings indicates which + * pages have reservations. When a huge page is allocated + * for an address with a reservation, no change is made to + * the reserve map. In this case PagePrivate will be set + * to indicate that the global reservation count should be + * incremented when the page is freed. This is the desired + * behavior. However, when a huge page is allocated for an + * address without a reservation a reservation entry is added + * to the reservation map, and PagePrivate will not be set. + * When the page is freed, the global reserve count will NOT + * be incremented and it will appear as though we have leaked + * reserved page. In this case, set PagePrivate so that the + * global reserve count will be incremented to match the + * reservation map entry which was created. + * + * Note that vm_alloc_shared is based on the flags of the vma + * for which the page was originally allocated. dst_vma could + * be different or NULL on error. */ - pmd = pmd_alloc(mm, pud, address); - return pmd; + if (vm_alloc_shared) + SetPagePrivate(page); + else + ClearPagePrivate(page); + put_page(page); + } + BUG_ON(copied < 0); + BUG_ON(err > 0); + BUG_ON(!copied && !err); + return copied ? copied : err; } +#else /* !CONFIG_HUGETLB_PAGE */ +/* fail at build time if gcc attempts to use this */ +extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, + struct vm_area_struct *dst_vma, + unsigned long dst_start, + unsigned long src_start, + unsigned long len, + bool zeropage); +#endif /* CONFIG_HUGETLB_PAGE */ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, @@ -173,14 +405,10 @@ retry: * Make sure the vma is not shared, that the dst range is * both valid and fully within a single existing vma. */ - err = -EINVAL; + err = -ENOENT; dst_vma = find_vma(dst_mm, dst_start); - if (!dst_vma || (dst_vma->vm_flags & VM_SHARED)) - goto out_unlock; - if (dst_start < dst_vma->vm_start || - dst_start + len > dst_vma->vm_end) + if (!dst_vma) goto out_unlock; - /* * Be strict and only allow __mcopy_atomic on userfaultfd * registered ranges to prevent userland errors going @@ -193,11 +421,27 @@ retry: if (!dst_vma->vm_userfaultfd_ctx.ctx) goto out_unlock; + if (dst_start < dst_vma->vm_start || + dst_start + len > dst_vma->vm_end) + goto out_unlock; + + err = -EINVAL; + /* + * shmem_zero_setup is invoked in mmap for MAP_ANONYMOUS|MAP_SHARED but + * it will overwrite vm_ops, so vma_is_anonymous must return false. + */ + if (WARN_ON_ONCE(vma_is_anonymous(dst_vma) && + dst_vma->vm_flags & VM_SHARED)) + goto out_unlock; + /* - * FIXME: only allow copying on anonymous vmas, tmpfs should - * be added. + * If this is a HUGETLB vma, pass off to appropriate routine */ - if (dst_vma->vm_ops) + if (is_vm_hugetlb_page(dst_vma)) + return __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start, + src_start, len, zeropage); + + if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; /* @@ -206,7 +450,7 @@ retry: * dst_vma. */ err = -ENOMEM; - if (unlikely(anon_vma_prepare(dst_vma))) + if (vma_is_anonymous(dst_vma) && unlikely(anon_vma_prepare(dst_vma))) goto out_unlock; while (src_addr < src_start + len) { @@ -243,12 +487,21 @@ retry: BUG_ON(pmd_none(*dst_pmd)); BUG_ON(pmd_trans_huge(*dst_pmd)); - if (!zeropage) - err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, - dst_addr, src_addr, &page); - else - err = mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, - dst_addr); + if (vma_is_anonymous(dst_vma)) { + if (!zeropage) + err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, + dst_addr, src_addr, + &page); + else + err = mfill_zeropage_pte(dst_mm, dst_pmd, + dst_vma, dst_addr); + } else { + err = -EINVAL; /* if zeropage is true return -EINVAL */ + if (likely(!zeropage)) + err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd, + dst_vma, dst_addr, + src_addr, &page); + } cond_resched(); diff --git a/mm/util.c b/mm/util.c index 3cb2164f4099..656dc5e37a87 100644 --- a/mm/util.c +++ b/mm/util.c @@ -5,12 +5,15 @@ #include <linux/export.h> #include <linux/err.h> #include <linux/sched.h> +#include <linux/sched/mm.h> +#include <linux/sched/task_stack.h> #include <linux/security.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/mman.h> #include <linux/hugetlb.h> #include <linux/vmalloc.h> +#include <linux/userfaultfd_k.h> #include <asm/sections.h> #include <linux/uaccess.h> @@ -297,14 +300,16 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, unsigned long ret; struct mm_struct *mm = current->mm; unsigned long populate; + LIST_HEAD(uf); ret = security_mmap_file(file, prot, flag); if (!ret) { if (down_write_killable(&mm->mmap_sem)) return -EINTR; ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff, - &populate); + &populate, &uf); up_write(&mm->mmap_sem); + userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(ret, populate); } diff --git a/mm/vmacache.c b/mm/vmacache.c index 035fdeb35b43..7ffa0ee341b5 100644 --- a/mm/vmacache.c +++ b/mm/vmacache.c @@ -1,7 +1,8 @@ /* * Copyright (C) 2014 Davidlohr Bueso. */ -#include <linux/sched.h> +#include <linux/sched/signal.h> +#include <linux/sched/task.h> #include <linux/mm.h> #include <linux/vmacache.h> @@ -60,7 +61,7 @@ static inline bool vmacache_valid_mm(struct mm_struct *mm) void vmacache_update(unsigned long addr, struct vm_area_struct *newvma) { if (vmacache_valid_mm(newvma->vm_mm)) - current->vmacache[VMACACHE_HASH(addr)] = newvma; + current->vmacache.vmas[VMACACHE_HASH(addr)] = newvma; } static bool vmacache_valid(struct mm_struct *mm) @@ -71,12 +72,12 @@ static bool vmacache_valid(struct mm_struct *mm) return false; curr = current; - if (mm->vmacache_seqnum != curr->vmacache_seqnum) { + if (mm->vmacache_seqnum != curr->vmacache.seqnum) { /* * First attempt will always be invalid, initialize * the new cache for this task here. */ - curr->vmacache_seqnum = mm->vmacache_seqnum; + curr->vmacache.seqnum = mm->vmacache_seqnum; vmacache_flush(curr); return false; } @@ -93,7 +94,7 @@ struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr) return NULL; for (i = 0; i < VMACACHE_SIZE; i++) { - struct vm_area_struct *vma = current->vmacache[i]; + struct vm_area_struct *vma = current->vmacache.vmas[i]; if (!vma) continue; @@ -121,7 +122,7 @@ struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, return NULL; for (i = 0; i < VMACACHE_SIZE; i++) { - struct vm_area_struct *vma = current->vmacache[i]; + struct vm_area_struct *vma = current->vmacache.vmas[i]; if (vma && vma->vm_start == start && vma->vm_end == end) { count_vm_vmacache_event(VMACACHE_FIND_HITS); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 3ca82d44edd3..b52aeed3f58e 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -12,7 +12,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/highmem.h> -#include <linux/sched.h> +#include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/interrupt.h> @@ -86,12 +86,12 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end) } while (pmd++, addr = next, addr != end); } -static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end) +static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end) { pud_t *pud; unsigned long next; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_clear_huge(pud)) @@ -102,6 +102,22 @@ static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end) } while (pud++, addr = next, addr != end); } +static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_clear_huge(p4d)) + continue; + if (p4d_none_or_clear_bad(p4d)) + continue; + vunmap_pud_range(p4d, addr, next); + } while (p4d++, addr = next, addr != end); +} + static void vunmap_page_range(unsigned long addr, unsigned long end) { pgd_t *pgd; @@ -113,7 +129,7 @@ static void vunmap_page_range(unsigned long addr, unsigned long end) next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - vunmap_pud_range(pgd, addr, next); + vunmap_p4d_range(pgd, addr, next); } while (pgd++, addr = next, addr != end); } @@ -160,13 +176,13 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, return 0; } -static int vmap_pud_range(pgd_t *pgd, unsigned long addr, +static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr) { pud_t *pud; unsigned long next; - pud = pud_alloc(&init_mm, pgd, addr); + pud = pud_alloc(&init_mm, p4d, addr); if (!pud) return -ENOMEM; do { @@ -177,6 +193,23 @@ static int vmap_pud_range(pgd_t *pgd, unsigned long addr, return 0; } +static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, + unsigned long end, pgprot_t prot, struct page **pages, int *nr) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_alloc(&init_mm, pgd, addr); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + if (vmap_pud_range(p4d, addr, next, prot, pages, nr)) + return -ENOMEM; + } while (p4d++, addr = next, addr != end); + return 0; +} + /* * Set up page tables in kva (addr, end). The ptes shall have prot "prot", and * will have pfns corresponding to the "pages" array. @@ -196,7 +229,7 @@ static int vmap_page_range_noflush(unsigned long start, unsigned long end, pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); - err = vmap_pud_range(pgd, addr, next, prot, pages, &nr); + err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr); if (err) return err; } while (pgd++, addr = next, addr != end); @@ -237,6 +270,10 @@ struct page *vmalloc_to_page(const void *vmalloc_addr) unsigned long addr = (unsigned long) vmalloc_addr; struct page *page = NULL; pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *ptep, pte; /* * XXX we might need to change this if we add VIRTUAL_BUG_ON for @@ -244,21 +281,23 @@ struct page *vmalloc_to_page(const void *vmalloc_addr) */ VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr)); - if (!pgd_none(*pgd)) { - pud_t *pud = pud_offset(pgd, addr); - if (!pud_none(*pud)) { - pmd_t *pmd = pmd_offset(pud, addr); - if (!pmd_none(*pmd)) { - pte_t *ptep, pte; - - ptep = pte_offset_map(pmd, addr); - pte = *ptep; - if (pte_present(pte)) - page = pte_page(pte); - pte_unmap(ptep); - } - } - } + if (pgd_none(*pgd)) + return NULL; + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) + return NULL; + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) + return NULL; + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return NULL; + + ptep = pte_offset_map(pmd, addr); + pte = *ptep; + if (pte_present(pte)) + page = pte_page(pte); + pte_unmap(ptep); return page; } EXPORT_SYMBOL(vmalloc_to_page); @@ -1540,7 +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) { @@ -1642,6 +1681,11 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, for (i = 0; i < area->nr_pages; i++) { struct page *page; + if (fatal_signal_pending(current)) { + area->nr_pages = i; + goto fail_no_warn; + } + if (node == NUMA_NO_NODE) page = alloc_page(alloc_mask); else @@ -1662,9 +1706,10 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, return area->addr; fail: - warn_alloc(gfp_mask, + warn_alloc(gfp_mask, NULL, "vmalloc: allocation failure, allocated %ld of %ld bytes", (area->nr_pages*PAGE_SIZE), area->size); +fail_no_warn: vfree(area->addr); return NULL; } @@ -1724,7 +1769,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, return addr; fail: - warn_alloc(gfp_mask, + warn_alloc(gfp_mask, NULL, "vmalloc: allocation failure: %lu bytes", real_size); return NULL; } @@ -2309,7 +2354,7 @@ EXPORT_SYMBOL_GPL(free_vm_area); #ifdef CONFIG_SMP static struct vmap_area *node_to_va(struct rb_node *n) { - return n ? rb_entry(n, struct vmap_area, rb_node) : NULL; + return rb_entry_safe(n, struct vmap_area, rb_node); } /** @@ -2654,7 +2699,7 @@ static int s_show(struct seq_file *m, void *p) seq_printf(m, " pages=%d", v->nr_pages); if (v->phys_addr) - seq_printf(m, " phys=%llx", (unsigned long long)v->phys_addr); + seq_printf(m, " phys=%pa", &v->phys_addr); if (v->flags & VM_IOREMAP) seq_puts(m, " ioremap"); diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 149fdf6c5c56..6063581f705c 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -112,9 +112,16 @@ static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned, unsigned long reclaimed) { unsigned long scale = scanned + reclaimed; - unsigned long pressure; + unsigned long pressure = 0; /* + * reclaimed can be greater than scanned in cases + * like THP, where the scanned is 1 and reclaimed + * could be 512 + */ + if (reclaimed >= scanned) + goto out; + /* * We calculate the ratio (in percents) of how many pages were * scanned vs. reclaimed in a given time frame (window). Note that * time is in VM reclaimer's "ticks", i.e. number of pages @@ -124,6 +131,7 @@ static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned, pressure = scale - (reclaimed * scale / scanned); pressure = pressure * 100 / scale; +out: pr_debug("%s: %3lu (s: %lu r: %lu)\n", __func__, pressure, scanned, reclaimed); diff --git a/mm/vmscan.c b/mm/vmscan.c index 532a2a750952..4e7ed65842af 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -14,6 +14,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> +#include <linux/sched/mm.h> #include <linux/module.h> #include <linux/gfp.h> #include <linux/kernel_stat.h> @@ -87,6 +88,7 @@ struct scan_control { /* The highest zone to isolate pages for reclaim from */ enum zone_type reclaim_idx; + /* Writepage batching in laptop mode; RECLAIM_WRITE */ unsigned int may_writepage:1; /* Can mapped pages be reclaimed? */ @@ -95,8 +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; @@ -228,28 +235,39 @@ unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat) return nr; } -bool pgdat_reclaimable(struct pglist_data *pgdat) +/** + * lruvec_lru_size - Returns the number of pages on the given LRU list. + * @lruvec: lru vector + * @lru: lru to use + * @zone_idx: zones to consider (use MAX_NR_ZONES for the whole LRU list) + */ +unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { - return node_page_state_snapshot(pgdat, NR_PAGES_SCANNED) < - pgdat_reclaimable_pages(pgdat) * 6; -} + unsigned long lru_size; + int zid; -unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru) -{ if (!mem_cgroup_disabled()) - return mem_cgroup_get_lru_size(lruvec, lru); + lru_size = mem_cgroup_get_lru_size(lruvec, lru); + else + lru_size = node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru); - return node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru); -} + for (zid = zone_idx + 1; zid < MAX_NR_ZONES; zid++) { + struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid]; + unsigned long size; -unsigned long lruvec_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, - int zone_idx) -{ - if (!mem_cgroup_disabled()) - return mem_cgroup_get_zone_lru_size(lruvec, lru, zone_idx); + if (!managed_zone(zone)) + continue; + + if (!mem_cgroup_disabled()) + size = mem_cgroup_get_zone_lru_size(lruvec, lru, zid); + else + size = zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zid], + NR_ZONE_LRU_BASE + lru); + lru_size -= min(size, lru_size); + } + + return lru_size; - return zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zone_idx], - NR_ZONE_LRU_BASE + lru); } /* @@ -893,7 +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; @@ -912,6 +931,17 @@ static void page_check_dirty_writeback(struct page *page, mapping->a_ops->is_dirty_writeback(page, dirty, writeback); } +struct reclaim_stat { + unsigned nr_dirty; + unsigned nr_unqueued_dirty; + unsigned nr_congested; + unsigned nr_writeback; + unsigned nr_immediate; + unsigned nr_activate; + unsigned nr_ref_keep; + unsigned nr_unmap_fail; +}; + /* * shrink_page_list() returns the number of reclaimed pages */ @@ -919,22 +949,20 @@ static unsigned long shrink_page_list(struct list_head *page_list, struct pglist_data *pgdat, struct scan_control *sc, enum ttu_flags ttu_flags, - unsigned long *ret_nr_dirty, - unsigned long *ret_nr_unqueued_dirty, - unsigned long *ret_nr_congested, - unsigned long *ret_nr_writeback, - unsigned long *ret_nr_immediate, + struct reclaim_stat *stat, bool force_reclaim) { LIST_HEAD(ret_pages); LIST_HEAD(free_pages); int pgactivate = 0; - unsigned long nr_unqueued_dirty = 0; - unsigned long nr_dirty = 0; - unsigned long nr_congested = 0; - unsigned long nr_reclaimed = 0; - unsigned long nr_writeback = 0; - unsigned long nr_immediate = 0; + unsigned nr_unqueued_dirty = 0; + unsigned nr_dirty = 0; + unsigned nr_congested = 0; + unsigned nr_reclaimed = 0; + unsigned nr_writeback = 0; + unsigned nr_immediate = 0; + unsigned nr_ref_keep = 0; + unsigned nr_unmap_fail = 0; cond_resched(); @@ -944,8 +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(); @@ -960,13 +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) || @@ -1029,6 +1056,15 @@ static unsigned long shrink_page_list(struct list_head *page_list, * throttling so we could easily OOM just because too many * pages are in writeback and there is nothing else to * reclaim. Wait for the writeback to complete. + * + * In cases 1) and 2) we activate the pages to get them out of + * the way while we continue scanning for clean pages on the + * inactive list and refilling from the active list. The + * observation here is that waiting for disk writes is more + * expensive than potentially causing reloads down the line. + * Since they're marked for immediate reclaim, they won't put + * memory pressure on the cache working set any longer than it + * takes to write them to disk. */ if (PageWriteback(page)) { /* Case 1 above */ @@ -1036,7 +1072,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, PageReclaim(page) && test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { nr_immediate++; - goto keep_locked; + goto activate_locked; /* Case 2 above */ } else if (sane_reclaim(sc) || @@ -1054,7 +1090,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, */ SetPageReclaim(page); nr_writeback++; - goto keep_locked; + goto activate_locked; /* Case 3 above */ } else { @@ -1073,6 +1109,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, case PAGEREF_ACTIVATE: goto activate_locked; case PAGEREF_KEEP: + nr_ref_keep++; goto keep_locked; case PAGEREF_RECLAIM: case PAGEREF_RECLAIM_CLEAN: @@ -1082,13 +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 */ @@ -1105,32 +1143,27 @@ 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 */ } } if (PageDirty(page)) { /* - * Only kswapd can writeback filesystem pages to - * avoid risk of stack overflow but only writeback - * if many dirty pages have been encountered. + * Only kswapd can writeback filesystem pages + * to avoid risk of stack overflow. But avoid + * injecting inefficient single-page IO into + * flusher writeback as much as possible: only + * write pages when we've encountered many + * dirty pages, and when we've already scanned + * the rest of the LRU for clean pages and see + * the same dirty pages again (PageReclaim). */ if (page_is_file_cache(page) && - (!current_is_kswapd() || - !test_bit(PGDAT_DIRTY, &pgdat->flags))) { + (!current_is_kswapd() || !PageReclaim(page) || + !test_bit(PGDAT_DIRTY, &pgdat->flags))) { /* * Immediately reclaim when written back. * Similar in principal to deactivate_page() @@ -1140,7 +1173,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, inc_node_page_state(page, NR_VMSCAN_IMMEDIATE); SetPageReclaim(page); - goto keep_locked; + goto activate_locked; } if (references == PAGEREF_RECLAIM_CLEAN) @@ -1223,10 +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 @@ -1236,9 +1277,6 @@ lazyfree: */ __ClearPageLocked(page); free_it: - if (ret == SWAP_LZFREE) - count_vm_event(PGLAZYFREED); - nr_reclaimed++; /* @@ -1248,20 +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: @@ -1276,11 +1310,16 @@ keep: list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); - *ret_nr_dirty += nr_dirty; - *ret_nr_congested += nr_congested; - *ret_nr_unqueued_dirty += nr_unqueued_dirty; - *ret_nr_writeback += nr_writeback; - *ret_nr_immediate += nr_immediate; + if (stat) { + stat->nr_dirty = nr_dirty; + stat->nr_congested = nr_congested; + stat->nr_unqueued_dirty = nr_unqueued_dirty; + stat->nr_writeback = nr_writeback; + stat->nr_immediate = nr_immediate; + stat->nr_activate = pgactivate; + stat->nr_ref_keep = nr_ref_keep; + stat->nr_unmap_fail = nr_unmap_fail; + } return nr_reclaimed; } @@ -1292,7 +1331,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, .priority = DEF_PRIORITY, .may_unmap = 1, }; - unsigned long ret, dummy1, dummy2, dummy3, dummy4, dummy5; + unsigned long ret; struct page *page, *next; LIST_HEAD(clean_pages); @@ -1305,8 +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, - &dummy1, &dummy2, &dummy3, &dummy4, &dummy5, 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; @@ -1341,13 +1379,10 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode) * wants to isolate pages it will be able to operate on without * blocking - clean pages for the most part. * - * ISOLATE_CLEAN means that only clean pages should be isolated. This - * is used by reclaim when it is cannot write to backing storage - * * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages * that it is possible to migrate without blocking */ - if (mode & (ISOLATE_CLEAN|ISOLATE_ASYNC_MIGRATE)) { + if (mode & ISOLATE_ASYNC_MIGRATE) { /* All the caller can do on PageWriteback is block */ if (PageWriteback(page)) return ret; @@ -1355,10 +1390,6 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode) if (PageDirty(page)) { struct address_space *mapping; - /* ISOLATE_CLEAN means only clean pages */ - if (mode & ISOLATE_CLEAN) - return ret; - /* * Only pages without mappings or that have a * ->migratepage callback are possible to migrate @@ -1437,11 +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; 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); @@ -1455,12 +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); @@ -1488,28 +1514,19 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, */ if (!list_empty(&pages_skipped)) { int zid; - unsigned long total_skipped = 0; + list_splice(&pages_skipped, src); for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_skipped[zid]) continue; __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]); - total_skipped += 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. - */ - scan += list_empty(src) ? total_skipped : total_skipped >> 2; - - list_splice(&pages_skipped, src); } *nr_scanned = scan; - trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan, - nr_taken, mode, is_file_lru(lru)); + 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); return nr_taken; } @@ -1669,30 +1686,6 @@ static int current_may_throttle(void) bdi_write_congested(current->backing_dev_info); } -static bool inactive_reclaimable_pages(struct lruvec *lruvec, - struct scan_control *sc, enum lru_list lru) -{ - int zid; - struct zone *zone; - int file = is_file_lru(lru); - struct pglist_data *pgdat = lruvec_pgdat(lruvec); - - if (!global_reclaim(sc)) - return true; - - for (zid = sc->reclaim_idx; zid >= 0; zid--) { - zone = &pgdat->node_zones[zid]; - if (!managed_zone(zone)) - continue; - - if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE + - LRU_FILE * file) >= SWAP_CLUSTER_MAX) - return true; - } - - return false; -} - /* * shrink_inactive_list() is a helper for shrink_node(). It returns the number * of reclaimed pages @@ -1705,19 +1698,12 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, unsigned long nr_scanned; unsigned long nr_reclaimed = 0; unsigned long nr_taken; - unsigned long nr_dirty = 0; - unsigned long nr_congested = 0; - unsigned long nr_unqueued_dirty = 0; - unsigned long nr_writeback = 0; - unsigned long nr_immediate = 0; + struct reclaim_stat stat = {}; isolate_mode_t isolate_mode = 0; int file = is_file_lru(lru); struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; - if (!inactive_reclaimable_pages(lruvec, sc, lru)) - return 0; - while (unlikely(too_many_isolated(pgdat, file, sc))) { congestion_wait(BLK_RW_ASYNC, HZ/10); @@ -1730,8 +1716,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, if (!sc->may_unmap) isolate_mode |= ISOLATE_UNMAPPED; - if (!sc->may_writepage) - isolate_mode |= ISOLATE_CLEAN; spin_lock_irq(&pgdat->lru_lock); @@ -1742,7 +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 @@ -1753,10 +1736,8 @@ 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_dirty, &nr_unqueued_dirty, &nr_congested, - &nr_writeback, &nr_immediate, - false); + nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, 0, + &stat, false); spin_lock_irq(&pgdat->lru_lock); @@ -1790,7 +1771,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * of pages under pages flagged for immediate reclaim and stall if any * are encountered in the nr_immediate check below. */ - if (nr_writeback && nr_writeback == nr_taken) + if (stat.nr_writeback && stat.nr_writeback == nr_taken) set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* @@ -1802,17 +1783,25 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * Tag a zone as congested if all the dirty pages scanned were * backed by a congested BDI and wait_iff_congested will stall. */ - if (nr_dirty && nr_dirty == nr_congested) + if (stat.nr_dirty && stat.nr_dirty == stat.nr_congested) set_bit(PGDAT_CONGESTED, &pgdat->flags); /* * If dirty pages are scanned that are not queued for IO, it - * implies that flushers are not keeping up. In this case, flag - * the pgdat PGDAT_DIRTY and kswapd will start writing pages from - * reclaim context. + * implies that flushers are not doing their job. This can + * happen when memory pressure pushes dirty pages to the end of + * the LRU before the dirty limits are breached and the dirty + * data has expired. It can also happen when the proportion of + * dirty pages grows not through writes but through memory + * pressure reclaiming all the clean cache. And in some cases, + * the flushers simply cannot keep up with the allocation + * rate. Nudge the flusher threads in case they are asleep, but + * also allow kswapd to start writing pages during reclaim. */ - if (nr_unqueued_dirty == nr_taken) + if (stat.nr_unqueued_dirty == nr_taken) { + wakeup_flusher_threads(0, WB_REASON_VMSCAN); set_bit(PGDAT_DIRTY, &pgdat->flags); + } /* * If kswapd scans pages marked marked for immediate @@ -1820,7 +1809,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * that pages are cycling through the LRU faster than * they are written so also forcibly stall. */ - if (nr_immediate && current_may_throttle()) + if (stat.nr_immediate && current_may_throttle()) congestion_wait(BLK_RW_ASYNC, HZ/10); } @@ -1835,6 +1824,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, nr_scanned, nr_reclaimed, + stat.nr_dirty, stat.nr_writeback, + stat.nr_congested, stat.nr_immediate, + stat.nr_activate, stat.nr_ref_keep, + stat.nr_unmap_fail, sc->priority, file); return nr_reclaimed; } @@ -1855,17 +1848,19 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * * The downside is that we have to touch page->_refcount against each page. * But we had to alter page->flags anyway. + * + * Returns the number of pages moved to the given lru. */ -static void move_active_pages_to_lru(struct lruvec *lruvec, +static unsigned move_active_pages_to_lru(struct lruvec *lruvec, struct list_head *list, struct list_head *pages_to_free, enum lru_list lru) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); - unsigned long pgmoved = 0; struct page *page; int nr_pages; + int nr_moved = 0; while (!list_empty(list)) { page = lru_to_page(list); @@ -1877,7 +1872,6 @@ static void move_active_pages_to_lru(struct lruvec *lruvec, nr_pages = hpage_nr_pages(page); update_lru_size(lruvec, lru, page_zonenum(page), nr_pages); list_move(&page->lru, &lruvec->lists[lru]); - pgmoved += nr_pages; if (put_page_testzero(page)) { __ClearPageLRU(page); @@ -1891,11 +1885,15 @@ static void move_active_pages_to_lru(struct lruvec *lruvec, spin_lock_irq(&pgdat->lru_lock); } else list_add(&page->lru, pages_to_free); + } else { + nr_moved += nr_pages; } } if (!is_active_lru(lru)) - __count_vm_events(PGDEACTIVATE, pgmoved); + __count_vm_events(PGDEACTIVATE, nr_moved); + + return nr_moved; } static void shrink_active_list(unsigned long nr_to_scan, @@ -1911,7 +1909,8 @@ static void shrink_active_list(unsigned long nr_to_scan, LIST_HEAD(l_inactive); struct page *page; struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; - unsigned long nr_rotated = 0; + unsigned nr_deactivate, nr_activate; + unsigned nr_rotated = 0; isolate_mode_t isolate_mode = 0; int file = is_file_lru(lru); struct pglist_data *pgdat = lruvec_pgdat(lruvec); @@ -1920,8 +1919,6 @@ static void shrink_active_list(unsigned long nr_to_scan, if (!sc->may_unmap) isolate_mode |= ISOLATE_UNMAPPED; - if (!sc->may_writepage) - isolate_mode |= ISOLATE_CLEAN; spin_lock_irq(&pgdat->lru_lock); @@ -1931,8 +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); @@ -1989,13 +1984,15 @@ static void shrink_active_list(unsigned long nr_to_scan, */ reclaim_stat->recent_rotated[file] += nr_rotated; - move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru); - move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE); + nr_activate = move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru); + nr_deactivate = move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&pgdat->lru_lock); mem_cgroup_uncharge_list(&l_hold); free_hot_cold_page_list(&l_hold, true); + trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate, + nr_deactivate, nr_rotated, sc->priority, file); } /* @@ -2009,6 +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. @@ -2025,14 +2024,16 @@ 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) + struct mem_cgroup *memcg, + struct scan_control *sc, bool actual_reclaim) { + 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 inactive; - unsigned long active; + unsigned long refaults; unsigned long gb; - struct pglist_data *pgdat = lruvec_pgdat(lruvec); - int zid; /* * If we don't have swap space, anonymous page deactivation @@ -2041,42 +2042,45 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, if (!file && !total_swap_pages) return false; - inactive = lruvec_lru_size(lruvec, file * LRU_FILE); - active = lruvec_lru_size(lruvec, file * LRU_FILE + LRU_ACTIVE); + inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx); + active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx); + + if (memcg) + refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE); + else + refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE); /* - * For zone-constrained allocations, it is necessary to check if - * deactivations are required for lowmem to be reclaimed. This - * calculates the inactive/active pages available in eligible zones. + * 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. */ - for (zid = sc->reclaim_idx + 1; zid < MAX_NR_ZONES; zid++) { - struct zone *zone = &pgdat->node_zones[zid]; - unsigned long inactive_zone, active_zone; - - if (!managed_zone(zone)) - continue; - - inactive_zone = lruvec_zone_lru_size(lruvec, file * LRU_FILE, zid); - active_zone = lruvec_zone_lru_size(lruvec, (file * LRU_FILE) + LRU_ACTIVE, zid); - - inactive -= min(inactive, inactive_zone); - active -= min(active, active_zone); + 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; } - gb = (inactive + active) >> (30 - PAGE_SHIFT); - if (gb) - inactive_ratio = int_sqrt(10 * gb); - else - inactive_ratio = 1; + 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)) + if (inactive_list_is_low(lruvec, is_file_lru(lru), + memcg, sc, true)) shrink_active_list(nr_to_scan, lruvec, sc, lru); return 0; } @@ -2112,30 +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) { @@ -2207,8 +2189,8 @@ 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) && - lruvec_lru_size(lruvec, LRU_INACTIVE_FILE) >> sc->priority) { + 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; } @@ -2234,10 +2216,10 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, * anon in [0], file in [1] */ - anon = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON) + - lruvec_lru_size(lruvec, LRU_INACTIVE_ANON); - file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE) + - lruvec_lru_size(lruvec, LRU_INACTIVE_FILE); + anon = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON, MAX_NR_ZONES) + + lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, MAX_NR_ZONES); + file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) + + lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES); spin_lock_irq(&pgdat->lru_lock); if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) { @@ -2266,55 +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); - 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 += size; - nr[lru] = scan; + *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 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; } } @@ -2365,7 +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); } } @@ -2432,7 +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)) + if (inactive_list_is_low(lruvec, false, memcg, sc, true)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } @@ -2546,9 +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; @@ -2609,6 +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; } @@ -2683,10 +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. @@ -2741,6 +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. * @@ -2761,8 +2762,9 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { int initial_priority = sc->priority; - unsigned long total_scanned = 0; - unsigned long writeback_threshold; + pg_data_t *last_pgdat; + struct zoneref *z; + struct zone *zone; retry: delayacct_freepages_start(); @@ -2775,7 +2777,6 @@ retry: sc->nr_scanned = 0; shrink_zones(zonelist, sc); - total_scanned += sc->nr_scanned; if (sc->nr_reclaimed >= sc->nr_to_reclaim) break; @@ -2788,22 +2789,17 @@ retry: */ if (sc->priority < DEF_PRIORITY - 2) sc->may_writepage = 1; - - /* - * Try to write back as many pages as we just scanned. This - * tends to cause slow streaming writers to write data to the - * disk smoothly, at the dirtying rate, which is nice. But - * that's undesirable in laptop mode, where we *want* lumpy - * writeout. So in laptop mode, write out the whole world. - */ - writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2; - if (total_scanned > writeback_threshold) { - wakeup_flusher_threads(laptop_mode ? 0 : total_scanned, - WB_REASON_TRY_TO_FREE_PAGES); - 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) @@ -2814,16 +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; @@ -2831,10 +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); @@ -2911,7 +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; } @@ -2933,14 +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)) @@ -2956,7 +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, @@ -3036,7 +3038,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, int nid; 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, @@ -3082,7 +3084,7 @@ 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)) + if (inactive_list_is_low(lruvec, false, memcg, sc, true)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); @@ -3090,21 +3092,44 @@ 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); + 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); } /* @@ -3115,11 +3140,9 @@ 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 @@ -3133,17 +3156,16 @@ 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; } /* @@ -3219,9 +3241,9 @@ 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; /* @@ -3246,23 +3268,12 @@ 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 @@ -3276,7 +3287,7 @@ 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. */ @@ -3300,7 +3311,7 @@ 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 */ @@ -3311,11 +3322,16 @@ 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 @@ -3325,6 +3341,22 @@ 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) { @@ -3336,7 +3368,13 @@ 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 @@ -3360,7 +3398,7 @@ 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); } @@ -3414,7 +3452,8 @@ 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; @@ -3444,20 +3483,23 @@ 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()) @@ -3483,9 +3525,6 @@ 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); @@ -3501,7 +3540,6 @@ 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; @@ -3509,22 +3547,20 @@ 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); } @@ -3730,7 +3766,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in int classzone_idx = gfp_zone(gfp_mask); 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), @@ -3784,9 +3820,6 @@ 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 7c28df36f50f..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", @@ -1038,6 +1038,8 @@ const char * const vmstat_text[] = { "compact_fail", "compact_success", "compact_daemon_wake", + "compact_daemon_migrate_scanned", + "compact_daemon_free_scanned", #endif #ifdef CONFIG_HUGETLB_PAGE @@ -1063,6 +1065,9 @@ const char * const vmstat_text[] = { "thp_split_page_failed", "thp_deferred_split_page", "thp_split_pmd", +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD + "thp_split_pud", +#endif "thp_zero_page_alloc", "thp_zero_page_alloc_failed", #endif @@ -1119,8 +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; @@ -1128,7 +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); @@ -1156,7 +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; } @@ -1197,7 +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; } @@ -1249,7 +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; } @@ -1275,7 +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 */ } @@ -1373,7 +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", @@ -1381,23 +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; @@ -1420,19 +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; } @@ -1547,7 +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; @@ -1582,22 +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) @@ -1618,7 +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)); } @@ -1697,7 +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(); @@ -1713,7 +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)); } @@ -1759,11 +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) @@ -1787,9 +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) @@ -1851,7 +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; } @@ -1903,7 +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 abb58ffa3c64..b8c9ab678479 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -6,6 +6,7 @@ #include <linux/memcontrol.h> #include <linux/writeback.h> +#include <linux/shmem_fs.h> #include <linux/pagemap.h> #include <linux/atomic.h> #include <linux/module.h> @@ -267,8 +268,7 @@ 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); - rcu_read_unlock(); + active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES); /* * The unsigned subtraction here gives an accurate distance @@ -289,11 +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; } @@ -354,10 +358,8 @@ void workingset_update_node(struct radix_tree_node *node, void *private) * as node->private_list is protected by &mapping->tree_lock. */ if (node->count && node->count == node->exceptional) { - if (list_empty(&node->private_list)) { - node->private_data = mapping; + if (list_empty(&node->private_list)) list_lru_add(&shadow_nodes, &node->private_list); - } } else { if (!list_empty(&node->private_list)) list_lru_del(&shadow_nodes, &node->private_list); @@ -435,7 +437,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, */ node = container_of(item, struct radix_tree_node, private_list); - mapping = node->private_data; + mapping = container_of(node->root, struct address_space, page_tree); /* Coming from the list, invert the lock order */ if (!spin_trylock(&mapping->tree_lock)) { @@ -473,6 +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); @@ -533,7 +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 8f9e89ca1d31..54f63c4a809a 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -34,28 +34,61 @@ /***************** * Structures *****************/ +struct z3fold_pool; +struct z3fold_ops { + int (*evict)(struct z3fold_pool *pool, unsigned long handle); +}; + +enum buddy { + HEADLESS = 0, + FIRST, + MIDDLE, + LAST, + BUDDIES_MAX +}; + +/* + * struct z3fold_header - z3fold page metadata occupying the first chunk of each + * z3fold page, except for HEADLESS pages + * @buddy: links the z3fold page into the relevant list in the pool + * @page_lock: per-page lock + * @refcount: reference cound for the z3fold page + * @first_chunks: the size of the first buddy in chunks, 0 if free + * @middle_chunks: the size of the middle buddy in chunks, 0 if free + * @last_chunks: the size of the last buddy in chunks, 0 if free + * @first_num: the starting number (for the first handle) + */ +struct z3fold_header { + struct list_head buddy; + spinlock_t page_lock; + struct kref refcount; + unsigned short first_chunks; + unsigned short middle_chunks; + unsigned short last_chunks; + unsigned short start_middle; + unsigned short first_num:2; +}; + /* * NCHUNKS_ORDER determines the internal allocation granularity, effectively * adjusting internal fragmentation. It also determines the number of * freelists maintained in each pool. NCHUNKS_ORDER of 6 means that the - * allocation granularity will be in chunks of size PAGE_SIZE/64. As one chunk - * in allocated page is occupied by z3fold header, NCHUNKS will be calculated - * to 63 which shows the max number of free chunks in z3fold page, also there - * will be 63 freelists per pool. + * allocation granularity will be in chunks of size PAGE_SIZE/64. Some chunks + * in the beginning of an allocated page are occupied by z3fold header, so + * NCHUNKS will be calculated to 63 (or 62 in case CONFIG_DEBUG_SPINLOCK=y), + * which shows the max number of free chunks in z3fold page, also there will + * be 63, or 62, respectively, freelists per pool. */ #define NCHUNKS_ORDER 6 #define CHUNK_SHIFT (PAGE_SHIFT - NCHUNKS_ORDER) #define CHUNK_SIZE (1 << CHUNK_SHIFT) -#define ZHDR_SIZE_ALIGNED CHUNK_SIZE +#define ZHDR_SIZE_ALIGNED round_up(sizeof(struct z3fold_header), CHUNK_SIZE) +#define ZHDR_CHUNKS (ZHDR_SIZE_ALIGNED >> CHUNK_SHIFT) +#define TOTAL_CHUNKS (PAGE_SIZE >> CHUNK_SHIFT) #define NCHUNKS ((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT) -#define BUDDY_MASK ((1 << NCHUNKS_ORDER) - 1) - -struct z3fold_pool; -struct z3fold_ops { - int (*evict)(struct z3fold_pool *pool, unsigned long handle); -}; +#define BUDDY_MASK (0x3) /** * struct z3fold_pool - stores metadata for each z3fold pool @@ -64,8 +97,6 @@ struct z3fold_ops { * @unbuddied: array of lists tracking z3fold pages that contain 2- buddies; * the lists each z3fold page is added to depends on the size of * its free region. - * @buddied: list tracking the z3fold pages that contain 3 buddies; - * these z3fold pages are full * @lru: list tracking the z3fold pages in LRU order by most recently * added buddy. * @pages_nr: number of z3fold pages in the pool. @@ -78,49 +109,22 @@ struct z3fold_ops { struct z3fold_pool { spinlock_t lock; struct list_head unbuddied[NCHUNKS]; - struct list_head buddied; struct list_head lru; - u64 pages_nr; + atomic64_t pages_nr; const struct z3fold_ops *ops; struct zpool *zpool; const struct zpool_ops *zpool_ops; }; -enum buddy { - HEADLESS = 0, - FIRST, - MIDDLE, - LAST, - BUDDIES_MAX -}; - -/* - * struct z3fold_header - z3fold page metadata occupying the first chunk of each - * z3fold page, except for HEADLESS pages - * @buddy: links the z3fold page into the relevant list in the pool - * @first_chunks: the size of the first buddy in chunks, 0 if free - * @middle_chunks: the size of the middle buddy in chunks, 0 if free - * @last_chunks: the size of the last buddy in chunks, 0 if free - * @first_num: the starting number (for the first handle) - */ -struct z3fold_header { - struct list_head buddy; - unsigned short first_chunks; - unsigned short middle_chunks; - unsigned short last_chunks; - unsigned short start_middle; - unsigned short first_num:NCHUNKS_ORDER; -}; - /* * Internal z3fold page flags */ enum z3fold_page_flags { - UNDER_RECLAIM = 0, - PAGE_HEADLESS, + PAGE_HEADLESS = 0, MIDDLE_CHUNK_MAPPED, }; + /***************** * Helpers *****************/ @@ -140,10 +144,11 @@ static struct z3fold_header *init_z3fold_page(struct page *page) struct z3fold_header *zhdr = page_address(page); INIT_LIST_HEAD(&page->lru); - clear_bit(UNDER_RECLAIM, &page->private); clear_bit(PAGE_HEADLESS, &page->private); clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); + spin_lock_init(&zhdr->page_lock); + kref_init(&zhdr->refcount); zhdr->first_chunks = 0; zhdr->middle_chunks = 0; zhdr->last_chunks = 0; @@ -154,9 +159,42 @@ static struct z3fold_header *init_z3fold_page(struct page *page) } /* Resets the struct page fields and frees the page */ -static void free_z3fold_page(struct z3fold_header *zhdr) +static void free_z3fold_page(struct page *page) { - __free_page(virt_to_page(zhdr)); + __free_page(page); +} + +static void release_z3fold_page(struct kref *ref) +{ + struct z3fold_header *zhdr; + struct page *page; + + zhdr = container_of(ref, struct z3fold_header, refcount); + page = virt_to_page(zhdr); + + if (!list_empty(&zhdr->buddy)) + list_del(&zhdr->buddy); + if (!list_empty(&page->lru)) + list_del(&page->lru); + free_z3fold_page(page); +} + +/* Lock a z3fold page */ +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) +{ + spin_unlock(&zhdr->page_lock); } /* @@ -179,7 +217,11 @@ static struct z3fold_header *handle_to_z3fold_header(unsigned long handle) return (struct z3fold_header *)(handle & PAGE_MASK); } -/* Returns buddy number */ +/* + * (handle & BUDDY_MASK) < zhdr->first_num is possible in encode_handle + * but that doesn't matter. because the masking will result in the + * correct buddy number. + */ static enum buddy handle_to_buddy(unsigned long handle) { struct z3fold_header *zhdr = handle_to_z3fold_header(handle); @@ -200,9 +242,10 @@ static int num_free_chunks(struct z3fold_header *zhdr) */ if (zhdr->middle_chunks != 0) { int nfree_before = zhdr->first_chunks ? - 0 : zhdr->start_middle - 1; + 0 : zhdr->start_middle - ZHDR_CHUNKS; int nfree_after = zhdr->last_chunks ? - 0 : NCHUNKS - zhdr->start_middle - zhdr->middle_chunks; + 0 : TOTAL_CHUNKS - + (zhdr->start_middle + zhdr->middle_chunks); nfree = max(nfree_before, nfree_after); } else nfree = NCHUNKS - zhdr->first_chunks - zhdr->last_chunks; @@ -232,9 +275,8 @@ static struct z3fold_pool *z3fold_create_pool(gfp_t gfp, spin_lock_init(&pool->lock); for_each_unbuddied_list(i, 0) INIT_LIST_HEAD(&pool->unbuddied[i]); - INIT_LIST_HEAD(&pool->buddied); INIT_LIST_HEAD(&pool->lru); - pool->pages_nr = 0; + atomic64_set(&pool->pages_nr, 0); pool->ops = ops; return pool; } @@ -250,25 +292,58 @@ static void z3fold_destroy_pool(struct z3fold_pool *pool) kfree(pool); } +static inline void *mchunk_memmove(struct z3fold_header *zhdr, + unsigned short dst_chunk) +{ + void *beg = zhdr; + return memmove(beg + (dst_chunk << CHUNK_SHIFT), + beg + (zhdr->start_middle << CHUNK_SHIFT), + zhdr->middle_chunks << CHUNK_SHIFT); +} + +#define BIG_CHUNK_GAP 3 /* Has to be called with lock held */ static int z3fold_compact_page(struct z3fold_header *zhdr) { struct page *page = virt_to_page(zhdr); - void *beg = zhdr; + if (test_bit(MIDDLE_CHUNK_MAPPED, &page->private)) + return 0; /* can't move middle chunk, it's used */ + + if (zhdr->middle_chunks == 0) + return 0; /* nothing to compact */ - if (!test_bit(MIDDLE_CHUNK_MAPPED, &page->private) && - zhdr->middle_chunks != 0 && - zhdr->first_chunks == 0 && zhdr->last_chunks == 0) { - memmove(beg + ZHDR_SIZE_ALIGNED, - beg + (zhdr->start_middle << CHUNK_SHIFT), - zhdr->middle_chunks << CHUNK_SHIFT); + if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) { + /* move to the beginning */ + mchunk_memmove(zhdr, ZHDR_CHUNKS); zhdr->first_chunks = zhdr->middle_chunks; zhdr->middle_chunks = 0; zhdr->start_middle = 0; zhdr->first_num++; return 1; } + + /* + * moving data is expensive, so let's only do that if + * there's substantial gain (at least BIG_CHUNK_GAP chunks) + */ + if (zhdr->first_chunks != 0 && zhdr->last_chunks == 0 && + zhdr->start_middle - (zhdr->first_chunks + ZHDR_CHUNKS) >= + BIG_CHUNK_GAP) { + mchunk_memmove(zhdr, zhdr->first_chunks + ZHDR_CHUNKS); + zhdr->start_middle = zhdr->first_chunks + ZHDR_CHUNKS; + return 1; + } else if (zhdr->last_chunks != 0 && zhdr->first_chunks == 0 && + TOTAL_CHUNKS - (zhdr->last_chunks + zhdr->start_middle + + zhdr->middle_chunks) >= + BIG_CHUNK_GAP) { + unsigned short new_start = TOTAL_CHUNKS - zhdr->last_chunks - + zhdr->middle_chunks; + mchunk_memmove(zhdr, new_start); + zhdr->start_middle = new_start; + return 1; + } + return 0; } @@ -309,50 +384,62 @@ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp, bud = HEADLESS; else { chunks = size_to_chunks(size); - spin_lock(&pool->lock); /* First, try to find an unbuddied z3fold page. */ zhdr = NULL; for_each_unbuddied_list(i, chunks) { - if (!list_empty(&pool->unbuddied[i])) { - zhdr = list_first_entry(&pool->unbuddied[i], + spin_lock(&pool->lock); + zhdr = list_first_entry_or_null(&pool->unbuddied[i], struct z3fold_header, buddy); - page = virt_to_page(zhdr); - if (zhdr->first_chunks == 0) { - if (zhdr->middle_chunks != 0 && - chunks >= zhdr->start_middle) - bud = LAST; - else - bud = FIRST; - } else if (zhdr->last_chunks == 0) + if (!zhdr || !z3fold_page_trylock(zhdr)) { + spin_unlock(&pool->lock); + continue; + } + kref_get(&zhdr->refcount); + list_del_init(&zhdr->buddy); + spin_unlock(&pool->lock); + + page = virt_to_page(zhdr); + if (zhdr->first_chunks == 0) { + if (zhdr->middle_chunks != 0 && + chunks >= zhdr->start_middle) bud = LAST; - else if (zhdr->middle_chunks == 0) - bud = MIDDLE; - else { - pr_err("No free chunks in unbuddied\n"); - WARN_ON(1); - continue; - } - list_del(&zhdr->buddy); - goto found; + else + bud = FIRST; + } else if (zhdr->last_chunks == 0) + bud = LAST; + else if (zhdr->middle_chunks == 0) + bud = MIDDLE; + else { + z3fold_page_unlock(zhdr); + spin_lock(&pool->lock); + if (kref_put(&zhdr->refcount, + release_z3fold_page)) + atomic64_dec(&pool->pages_nr); + spin_unlock(&pool->lock); + pr_err("No free chunks in unbuddied\n"); + WARN_ON(1); + continue; } + goto found; } bud = FIRST; - spin_unlock(&pool->lock); } /* Couldn't find unbuddied z3fold page, create new one */ page = alloc_page(gfp); if (!page) return -ENOMEM; - spin_lock(&pool->lock); - pool->pages_nr++; + + atomic64_inc(&pool->pages_nr); zhdr = init_z3fold_page(page); if (bud == HEADLESS) { set_bit(PAGE_HEADLESS, &page->private); + spin_lock(&pool->lock); goto headless; } + z3fold_page_lock(zhdr); found: if (bud == FIRST) @@ -361,17 +448,15 @@ found: zhdr->last_chunks = chunks; else { zhdr->middle_chunks = chunks; - zhdr->start_middle = zhdr->first_chunks + 1; + zhdr->start_middle = zhdr->first_chunks + ZHDR_CHUNKS; } + spin_lock(&pool->lock); if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0 || zhdr->middle_chunks == 0) { /* Add to unbuddied list */ freechunks = num_free_chunks(zhdr); list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); - } else { - /* Add to buddied list */ - list_add(&zhdr->buddy, &pool->buddied); } headless: @@ -383,6 +468,8 @@ headless: *handle = encode_handle(zhdr, bud); spin_unlock(&pool->lock); + if (bud != HEADLESS) + z3fold_page_unlock(zhdr); return 0; } @@ -404,7 +491,6 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) struct page *page; enum buddy bud; - spin_lock(&pool->lock); zhdr = handle_to_z3fold_header(handle); page = virt_to_page(zhdr); @@ -412,6 +498,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) /* HEADLESS page stored */ bud = HEADLESS; } else { + z3fold_page_lock(zhdr); bud = handle_to_buddy(handle); switch (bud) { @@ -428,38 +515,36 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) default: pr_err("%s: unknown bud %d\n", __func__, bud); WARN_ON(1); - spin_unlock(&pool->lock); + z3fold_page_unlock(zhdr); return; } } - if (test_bit(UNDER_RECLAIM, &page->private)) { - /* z3fold page is under reclaim, reclaim will free */ - spin_unlock(&pool->lock); - return; - } - - if (bud != HEADLESS) { - /* Remove from existing buddy list */ - list_del(&zhdr->buddy); - } - - if (bud == HEADLESS || - (zhdr->first_chunks == 0 && zhdr->middle_chunks == 0 && - zhdr->last_chunks == 0)) { - /* z3fold page is empty, free */ + if (bud == HEADLESS) { + spin_lock(&pool->lock); list_del(&page->lru); - clear_bit(PAGE_HEADLESS, &page->private); - free_z3fold_page(zhdr); - pool->pages_nr--; + spin_unlock(&pool->lock); + free_z3fold_page(page); + atomic64_dec(&pool->pages_nr); } else { - z3fold_compact_page(zhdr); - /* Add to the unbuddied list */ - freechunks = num_free_chunks(zhdr); - list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + if (zhdr->first_chunks != 0 || zhdr->middle_chunks != 0 || + zhdr->last_chunks != 0) { + z3fold_compact_page(zhdr); + /* Add to the unbuddied list */ + spin_lock(&pool->lock); + if (!list_empty(&zhdr->buddy)) + list_del(&zhdr->buddy); + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + spin_unlock(&pool->lock); + } + z3fold_page_unlock(zhdr); + spin_lock(&pool->lock); + if (kref_put(&zhdr->refcount, release_z3fold_page)) + atomic64_dec(&pool->pages_nr); + spin_unlock(&pool->lock); } - spin_unlock(&pool->lock); } /** @@ -506,20 +591,25 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) unsigned long first_handle = 0, middle_handle = 0, last_handle = 0; spin_lock(&pool->lock); - if (!pool->ops || !pool->ops->evict || list_empty(&pool->lru) || - retries == 0) { + if (!pool->ops || !pool->ops->evict || retries == 0) { spin_unlock(&pool->lock); return -EINVAL; } for (i = 0; i < retries; i++) { + if (list_empty(&pool->lru)) { + spin_unlock(&pool->lock); + return -EINVAL; + } page = list_last_entry(&pool->lru, struct page, lru); - list_del(&page->lru); + list_del_init(&page->lru); - /* Protect z3fold page against free */ - set_bit(UNDER_RECLAIM, &page->private); zhdr = page_address(page); if (!test_bit(PAGE_HEADLESS, &page->private)) { - list_del(&zhdr->buddy); + if (!list_empty(&zhdr->buddy)) + list_del_init(&zhdr->buddy); + kref_get(&zhdr->refcount); + spin_unlock(&pool->lock); + z3fold_page_lock(zhdr); /* * We need encode the handles before unlocking, since * we can race with free that will set @@ -534,13 +624,13 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) middle_handle = encode_handle(zhdr, MIDDLE); if (zhdr->last_chunks) last_handle = encode_handle(zhdr, LAST); + z3fold_page_unlock(zhdr); } else { first_handle = encode_handle(zhdr, HEADLESS); last_handle = middle_handle = 0; + spin_unlock(&pool->lock); } - spin_unlock(&pool->lock); - /* Issue the eviction callback(s) */ if (middle_handle) { ret = pool->ops->evict(pool, middle_handle); @@ -558,36 +648,41 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) goto next; } next: - spin_lock(&pool->lock); - clear_bit(UNDER_RECLAIM, &page->private); - if ((test_bit(PAGE_HEADLESS, &page->private) && ret == 0) || - (zhdr->first_chunks == 0 && zhdr->last_chunks == 0 && - zhdr->middle_chunks == 0)) { - /* - * All buddies are now free, free the z3fold page and - * return success. - */ - clear_bit(PAGE_HEADLESS, &page->private); - free_z3fold_page(zhdr); - pool->pages_nr--; - spin_unlock(&pool->lock); - return 0; - } else if (!test_bit(PAGE_HEADLESS, &page->private)) { - if (zhdr->first_chunks != 0 && - zhdr->last_chunks != 0 && - zhdr->middle_chunks != 0) { - /* Full, add to buddied list */ - list_add(&zhdr->buddy, &pool->buddied); + if (test_bit(PAGE_HEADLESS, &page->private)) { + if (ret == 0) { + free_z3fold_page(page); + return 0; } else { + spin_lock(&pool->lock); + } + } else { + z3fold_page_lock(zhdr); + if ((zhdr->first_chunks || zhdr->last_chunks || + zhdr->middle_chunks) && + !(zhdr->first_chunks && zhdr->last_chunks && + zhdr->middle_chunks)) { z3fold_compact_page(zhdr); /* add to unbuddied list */ + spin_lock(&pool->lock); freechunks = num_free_chunks(zhdr); list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + spin_unlock(&pool->lock); + } + z3fold_page_unlock(zhdr); + spin_lock(&pool->lock); + if (kref_put(&zhdr->refcount, release_z3fold_page)) { + spin_unlock(&pool->lock); + atomic64_dec(&pool->pages_nr); + return 0; } } - /* add to beginning of LRU */ + /* + * Add to the beginning of LRU. + * Pool lock has to be kept here to ensure the page has + * not already been released + */ list_add(&page->lru, &pool->lru); } spin_unlock(&pool->lock); @@ -611,7 +706,6 @@ static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle) void *addr; enum buddy buddy; - spin_lock(&pool->lock); zhdr = handle_to_z3fold_header(handle); addr = zhdr; page = virt_to_page(zhdr); @@ -619,6 +713,7 @@ static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle) if (test_bit(PAGE_HEADLESS, &page->private)) goto out; + z3fold_page_lock(zhdr); buddy = handle_to_buddy(handle); switch (buddy) { case FIRST: @@ -637,8 +732,9 @@ static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle) addr = NULL; break; } + + z3fold_page_unlock(zhdr); out: - spin_unlock(&pool->lock); return addr; } @@ -653,31 +749,28 @@ static void z3fold_unmap(struct z3fold_pool *pool, unsigned long handle) struct page *page; enum buddy buddy; - spin_lock(&pool->lock); zhdr = handle_to_z3fold_header(handle); page = virt_to_page(zhdr); - if (test_bit(PAGE_HEADLESS, &page->private)) { - spin_unlock(&pool->lock); + if (test_bit(PAGE_HEADLESS, &page->private)) return; - } + z3fold_page_lock(zhdr); buddy = handle_to_buddy(handle); if (buddy == MIDDLE) clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); - spin_unlock(&pool->lock); + z3fold_page_unlock(zhdr); } /** * z3fold_get_pool_size() - gets the z3fold pool size in pages * @pool: pool whose size is being queried * - * Returns: size in pages of the given pool. The pool lock need not be - * taken to access pages_nr. + * Returns: size in pages of the given pool. */ static u64 z3fold_get_pool_size(struct z3fold_pool *pool) { - return pool->pages_nr; + return atomic64_read(&pool->pages_nr); } /***************** @@ -776,8 +869,8 @@ MODULE_ALIAS("zpool-z3fold"); static int __init init_z3fold(void) { - /* Make sure the z3fold header will fit in one chunk */ - BUILD_BUG_ON(sizeof(struct z3fold_header) > ZHDR_SIZE_ALIGNED); + /* Make sure the z3fold header is not larger than the page size */ + BUILD_BUG_ON(ZHDR_SIZE_ALIGNED > PAGE_SIZE); zpool_register_driver(&z3fold_zpool_driver); return 0; diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 9cc3c0b2c2c1..d41edd28298b 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -24,8 +24,7 @@ * * Usage of struct page flags: * PG_private: identifies the first component page - * PG_private2: identifies the last component page - * PG_owner_priv_1: indentifies the huge component page + * PG_owner_priv_1: identifies the huge component page * */ @@ -34,6 +33,7 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/magic.h> #include <linux/bitops.h> #include <linux/errno.h> #include <linux/highmem.h> @@ -268,10 +268,6 @@ struct zs_pool { #endif }; -/* - * A zspage's class index and fullness group - * are encoded in its (first)page->mapping - */ #define FULLNESS_BITS 2 #define CLASS_BITS 8 #define ISOLATED_BITS 3 @@ -280,7 +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; }; @@ -364,7 +360,7 @@ static struct zspage *cache_alloc_zspage(struct zs_pool *pool, gfp_t flags) { return kmem_cache_alloc(pool->zspage_cachep, flags & ~(__GFP_HIGHMEM|__GFP_MOVABLE)); -}; +} static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage) { @@ -938,7 +934,6 @@ static void reset_page(struct page *page) { __ClearPageMovable(page); ClearPagePrivate(page); - ClearPagePrivate2(page); set_page_private(page, 0); page_mapcount_reset(page); ClearPageHugeObject(page); @@ -1085,7 +1080,7 @@ static void create_page_chain(struct size_class *class, struct zspage *zspage, * 2. each sub-page point to zspage using page->private * * we set PG_private to identify the first page (i.e. no other sub-page - * has this flag set) and PG_private_2 to identify the last page. + * has this flag set). */ for (i = 0; i < nr_pages; i++) { page = pages[i]; @@ -1100,8 +1095,6 @@ static void create_page_chain(struct size_class *class, struct zspage *zspage, } else { prev_page->freelist = page; } - if (i == nr_pages - 1) - SetPagePrivate2(page); prev_page = page; } } @@ -2383,7 +2376,7 @@ struct zs_pool *zs_create_pool(const char *name) goto err; /* - * Iterate reversly, because, size of size_class that we want to use + * Iterate reversely, because, size of size_class that we want to use * for merging should be larger or equal to current size. */ for (i = zs_size_classes - 1; i >= 0; i--) { diff --git a/mm/zswap.c b/mm/zswap.c index cabf09e0128b..eedc27894b10 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -76,6 +76,8 @@ static u64 zswap_duplicate_entry; * tunables **********************************/ +#define ZSWAP_PARAM_UNSET "" + /* Enable/disable zswap (disabled by default) */ static bool zswap_enabled; static int zswap_enabled_param_set(const char *, @@ -185,6 +187,9 @@ static bool zswap_init_started; /* fatal error during init */ static bool zswap_init_failed; +/* init completed, but couldn't create the initial pool */ +static bool zswap_has_pool; + /********************************* * helpers and fwd declarations **********************************/ @@ -424,7 +429,8 @@ static struct zswap_pool *__zswap_pool_current(void) struct zswap_pool *pool; pool = list_first_or_null_rcu(&zswap_pools, typeof(*pool), list); - WARN_ON(!pool); + WARN_ONCE(!pool && zswap_has_pool, + "%s: no page storage pool!\n", __func__); return pool; } @@ -443,7 +449,7 @@ static struct zswap_pool *zswap_pool_current_get(void) rcu_read_lock(); pool = __zswap_pool_current(); - if (!pool || !zswap_pool_get(pool)) + if (!zswap_pool_get(pool)) pool = NULL; rcu_read_unlock(); @@ -459,7 +465,9 @@ static struct zswap_pool *zswap_pool_last_get(void) list_for_each_entry_rcu(pool, &zswap_pools, list) last = pool; - if (!WARN_ON(!last) && !zswap_pool_get(last)) + WARN_ONCE(!last && zswap_has_pool, + "%s: no page storage pool!\n", __func__); + if (!zswap_pool_get(last)) last = NULL; rcu_read_unlock(); @@ -495,6 +503,17 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; int ret; + if (!zswap_has_pool) { + /* if either are unset, pool initialization failed, and we + * need both params to be set correctly before trying to + * create a pool. + */ + if (!strcmp(type, ZSWAP_PARAM_UNSET)) + return NULL; + if (!strcmp(compressor, ZSWAP_PARAM_UNSET)) + return NULL; + } + pool = kzalloc(sizeof(*pool), GFP_KERNEL); if (!pool) { pr_err("pool alloc failed\n"); @@ -544,29 +563,41 @@ error: static __init struct zswap_pool *__zswap_pool_create_fallback(void) { - if (!crypto_has_comp(zswap_compressor, 0, 0)) { - if (!strcmp(zswap_compressor, ZSWAP_COMPRESSOR_DEFAULT)) { - pr_err("default compressor %s not available\n", - zswap_compressor); - return NULL; - } + bool has_comp, has_zpool; + + has_comp = crypto_has_comp(zswap_compressor, 0, 0); + if (!has_comp && strcmp(zswap_compressor, ZSWAP_COMPRESSOR_DEFAULT)) { pr_err("compressor %s not available, using default %s\n", zswap_compressor, ZSWAP_COMPRESSOR_DEFAULT); param_free_charp(&zswap_compressor); zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT; + has_comp = crypto_has_comp(zswap_compressor, 0, 0); } - if (!zpool_has_pool(zswap_zpool_type)) { - if (!strcmp(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT)) { - pr_err("default zpool %s not available\n", - zswap_zpool_type); - return NULL; - } + if (!has_comp) { + pr_err("default compressor %s not available\n", + zswap_compressor); + param_free_charp(&zswap_compressor); + zswap_compressor = ZSWAP_PARAM_UNSET; + } + + has_zpool = zpool_has_pool(zswap_zpool_type); + if (!has_zpool && strcmp(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT)) { pr_err("zpool %s not available, using default %s\n", zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT); param_free_charp(&zswap_zpool_type); zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT; + has_zpool = zpool_has_pool(zswap_zpool_type); + } + if (!has_zpool) { + pr_err("default zpool %s not available\n", + zswap_zpool_type); + param_free_charp(&zswap_zpool_type); + zswap_zpool_type = ZSWAP_PARAM_UNSET; } + if (!has_comp || !has_zpool) + return NULL; + return zswap_pool_create(zswap_zpool_type, zswap_compressor); } @@ -582,6 +613,9 @@ static void zswap_pool_destroy(struct zswap_pool *pool) static int __must_check zswap_pool_get(struct zswap_pool *pool) { + if (!pool) + return 0; + return kref_get_unless_zero(&pool->kref); } @@ -639,7 +673,7 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp, } /* no change required */ - if (!strcmp(s, *(char **)kp->arg)) + if (!strcmp(s, *(char **)kp->arg) && zswap_has_pool) return 0; /* if this is load-time (pre-init) param setting, @@ -670,21 +704,26 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp, pool = zswap_pool_find_get(type, compressor); if (pool) { zswap_pool_debug("using existing", pool); + WARN_ON(pool == zswap_pool_current()); list_del_rcu(&pool->list); - } else { - spin_unlock(&zswap_pools_lock); - pool = zswap_pool_create(type, compressor); - spin_lock(&zswap_pools_lock); } + spin_unlock(&zswap_pools_lock); + + if (!pool) + pool = zswap_pool_create(type, compressor); + if (pool) ret = param_set_charp(s, kp); else ret = -EINVAL; + spin_lock(&zswap_pools_lock); + if (!ret) { put_pool = zswap_pool_current(); list_add_rcu(&pool->list, &zswap_pools); + zswap_has_pool = true; } else if (pool) { /* add the possibly pre-existing pool to the end of the pools * list; if it's new (and empty) then it'll be removed and @@ -696,6 +735,17 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp, spin_unlock(&zswap_pools_lock); + if (!zswap_has_pool && !pool) { + /* if initial pool creation failed, and this pool creation also + * failed, maybe both compressor and zpool params were bad. + * Allow changing this param, so pool creation will succeed + * when the other param is changed. We already verified this + * param is ok in the zpool_has_pool() or crypto_has_comp() + * checks above. + */ + ret = param_set_charp(s, kp); + } + /* drop the ref from either the old current pool, * or the new pool we failed to add */ @@ -724,6 +774,10 @@ static int zswap_enabled_param_set(const char *val, pr_err("can't enable, initialization failed\n"); return -ENODEV; } + if (!zswap_has_pool && zswap_init_started) { + pr_err("can't enable, no pool configured\n"); + return -ENODEV; + } return param_set_bool(val, kp); } @@ -1205,22 +1259,21 @@ static int __init init_zswap(void) goto hp_fail; pool = __zswap_pool_create_fallback(); - if (!pool) { + if (pool) { + pr_info("loaded using pool %s/%s\n", pool->tfm_name, + zpool_get_type(pool->zpool)); + list_add(&pool->list, &zswap_pools); + zswap_has_pool = true; + } else { pr_err("pool creation failed\n"); - goto pool_fail; + zswap_enabled = false; } - pr_info("loaded using pool %s/%s\n", pool->tfm_name, - zpool_get_type(pool->zpool)); - - list_add(&pool->list, &zswap_pools); frontswap_register_ops(&zswap_frontswap_ops); if (zswap_debugfs_init()) pr_warn("debugfs initialization failed\n"); return 0; -pool_fail: - cpuhp_remove_state_nocalls(CPUHP_MM_ZSWP_POOL_PREPARE); hp_fail: cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE); dstmem_fail: |
