diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 19 | ||||
| -rw-r--r-- | mm/backing-dev.c | 651 | ||||
| -rw-r--r-- | mm/bootmem.c | 13 | ||||
| -rw-r--r-- | mm/cma.c | 10 | ||||
| -rw-r--r-- | mm/cma.h | 2 | ||||
| -rw-r--r-- | mm/cma_debug.c | 11 | ||||
| -rw-r--r-- | mm/debug.c | 2 | ||||
| -rw-r--r-- | mm/fadvise.c | 2 | ||||
| -rw-r--r-- | mm/filemap.c | 59 | ||||
| -rw-r--r-- | mm/frontswap.c | 215 | ||||
| -rw-r--r-- | mm/huge_memory.c | 29 | ||||
| -rw-r--r-- | mm/hugetlb.c | 197 | ||||
| -rw-r--r-- | mm/hwpoison-inject.c | 4 | ||||
| -rw-r--r-- | mm/internal.h | 11 | ||||
| -rw-r--r-- | mm/kasan/kasan.c | 2 | ||||
| -rw-r--r-- | mm/kasan/kasan.h | 1 | ||||
| -rw-r--r-- | mm/kasan/report.c | 2 | ||||
| -rw-r--r-- | mm/kmemleak.c | 168 | ||||
| -rw-r--r-- | mm/madvise.c | 1 | ||||
| -rw-r--r-- | mm/memblock.c | 157 | ||||
| -rw-r--r-- | mm/memcontrol.c | 288 | ||||
| -rw-r--r-- | mm/memory-failure.c | 383 | ||||
| -rw-r--r-- | mm/memory.c | 50 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 18 | ||||
| -rw-r--r-- | mm/mempolicy.c | 38 | ||||
| -rw-r--r-- | mm/memtest.c | 3 | ||||
| -rw-r--r-- | mm/migrate.c | 17 | ||||
| -rw-r--r-- | mm/mm_init.c | 9 | ||||
| -rw-r--r-- | mm/mmap.c | 6 | ||||
| -rw-r--r-- | mm/mprotect.c | 11 | ||||
| -rw-r--r-- | mm/mremap.c | 17 | ||||
| -rw-r--r-- | mm/nobootmem.c | 21 | ||||
| -rw-r--r-- | mm/nommu.c | 116 | ||||
| -rw-r--r-- | mm/oom_kill.c | 158 | ||||
| -rw-r--r-- | mm/page-writeback.c | 1233 | ||||
| -rw-r--r-- | mm/page_alloc.c | 755 | ||||
| -rw-r--r-- | mm/page_io.c | 2 | ||||
| -rw-r--r-- | mm/page_owner.c | 9 | ||||
| -rw-r--r-- | mm/percpu.c | 2 | ||||
| -rw-r--r-- | mm/pgtable-generic.c | 29 | ||||
| -rw-r--r-- | mm/readahead.c | 2 | ||||
| -rw-r--r-- | mm/rmap.c | 11 | ||||
| -rw-r--r-- | mm/shmem.c | 46 | ||||
| -rw-r--r-- | mm/slab.c | 5 | ||||
| -rw-r--r-- | mm/slab.h | 1 | ||||
| -rw-r--r-- | mm/slab_common.c | 93 | ||||
| -rw-r--r-- | mm/slub.c | 3 | ||||
| -rw-r--r-- | mm/swap.c | 1 | ||||
| -rw-r--r-- | mm/swapfile.c | 2 | ||||
| -rw-r--r-- | mm/truncate.c | 18 | ||||
| -rw-r--r-- | mm/vmscan.c | 106 | ||||
| -rw-r--r-- | mm/zbud.c | 23 | ||||
| -rw-r--r-- | mm/zpool.c | 35 | ||||
| -rw-r--r-- | mm/zsmalloc.c | 10 | ||||
| -rw-r--r-- | mm/zswap.c | 12 |
55 files changed, 3326 insertions, 1763 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 390214da4546..e79de2bd12cd 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -368,6 +368,7 @@ config MEMORY_FAILURE depends on ARCH_SUPPORTS_MEMORY_FAILURE bool "Enable recovery from hardware memory errors" select MEMORY_ISOLATION + select RAS help Enables code to recover from some memory failures on systems with MCA recovery. This allows a system to continue running @@ -635,3 +636,21 @@ config MAX_STACK_SIZE_MB changed to a smaller value in which case that is used. A sane initial value is 80 MB. + +# For architectures that support deferred memory initialisation +config ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT + bool + +config DEFERRED_STRUCT_PAGE_INIT + bool "Defer initialisation of struct pages to kswapd" + default n + depends on ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT + depends on MEMORY_HOTPLUG + help + Ordinarily all struct pages are initialised during early boot in a + single thread. On very large machines this can take a considerable + amount of time. If this option is set, large machines will bring up + a subset of memmap at boot and then initialise the rest in parallel + when kswapd starts. This has a potential performance impact on + processes running early in the lifetime of the systemm until kswapd + finishes the initialisation. diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 6dc4580df2af..dac5bf59309d 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -18,6 +18,7 @@ struct backing_dev_info noop_backing_dev_info = { .name = "noop", .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; +EXPORT_SYMBOL_GPL(noop_backing_dev_info); static struct class *bdi_class; @@ -48,7 +49,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) struct bdi_writeback *wb = &bdi->wb; unsigned long background_thresh; unsigned long dirty_thresh; - unsigned long bdi_thresh; + unsigned long wb_thresh; unsigned long nr_dirty, nr_io, nr_more_io, nr_dirty_time; struct inode *inode; @@ -66,7 +67,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) spin_unlock(&wb->list_lock); global_dirty_limits(&background_thresh, &dirty_thresh); - bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); + wb_thresh = wb_calc_thresh(wb, dirty_thresh); #define K(x) ((x) << (PAGE_SHIFT - 10)) seq_printf(m, @@ -84,19 +85,19 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) "b_dirty_time: %10lu\n" "bdi_list: %10u\n" "state: %10lx\n", - (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)), - (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)), - K(bdi_thresh), + (unsigned long) K(wb_stat(wb, WB_WRITEBACK)), + (unsigned long) K(wb_stat(wb, WB_RECLAIMABLE)), + K(wb_thresh), K(dirty_thresh), K(background_thresh), - (unsigned long) K(bdi_stat(bdi, BDI_DIRTIED)), - (unsigned long) K(bdi_stat(bdi, BDI_WRITTEN)), - (unsigned long) K(bdi->write_bandwidth), + (unsigned long) K(wb_stat(wb, WB_DIRTIED)), + (unsigned long) K(wb_stat(wb, WB_WRITTEN)), + (unsigned long) K(wb->write_bandwidth), nr_dirty, nr_io, nr_more_io, nr_dirty_time, - !list_empty(&bdi->bdi_list), bdi->state); + !list_empty(&bdi->bdi_list), bdi->wb.state); #undef K return 0; @@ -255,13 +256,8 @@ static int __init default_bdi_init(void) } subsys_initcall(default_bdi_init); -int bdi_has_dirty_io(struct backing_dev_info *bdi) -{ - return wb_has_dirty_io(&bdi->wb); -} - /* - * This function is used when the first inode for this bdi is marked dirty. It + * This function is used when the first inode for this wb is marked dirty. It * wakes-up the corresponding bdi thread which should then take care of the * periodic background write-out of dirty inodes. Since the write-out would * starts only 'dirty_writeback_interval' centisecs from now anyway, we just @@ -274,178 +270,565 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi) * We have to be careful not to postpone flush work if it is scheduled for * earlier. Thus we use queue_delayed_work(). */ -void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi) +void wb_wakeup_delayed(struct bdi_writeback *wb) { unsigned long timeout; timeout = msecs_to_jiffies(dirty_writeback_interval * 10); - spin_lock_bh(&bdi->wb_lock); - if (test_bit(BDI_registered, &bdi->state)) - queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout); - spin_unlock_bh(&bdi->wb_lock); + spin_lock_bh(&wb->work_lock); + if (test_bit(WB_registered, &wb->state)) + queue_delayed_work(bdi_wq, &wb->dwork, timeout); + spin_unlock_bh(&wb->work_lock); } /* - * Remove bdi from bdi_list, and ensure that it is no longer visible + * Initial write bandwidth: 100 MB/s */ -static void bdi_remove_from_list(struct backing_dev_info *bdi) +#define INIT_BW (100 << (20 - PAGE_SHIFT)) + +static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, + int blkcg_id, gfp_t gfp) { - spin_lock_bh(&bdi_lock); - list_del_rcu(&bdi->bdi_list); - spin_unlock_bh(&bdi_lock); + int i, err; - synchronize_rcu_expedited(); -} + memset(wb, 0, sizeof(*wb)); -int bdi_register(struct backing_dev_info *bdi, struct device *parent, - const char *fmt, ...) -{ - va_list args; - struct device *dev; + wb->bdi = bdi; + wb->last_old_flush = jiffies; + INIT_LIST_HEAD(&wb->b_dirty); + INIT_LIST_HEAD(&wb->b_io); + INIT_LIST_HEAD(&wb->b_more_io); + INIT_LIST_HEAD(&wb->b_dirty_time); + spin_lock_init(&wb->list_lock); - if (bdi->dev) /* The driver needs to use separate queues per device */ - return 0; + wb->bw_time_stamp = jiffies; + wb->balanced_dirty_ratelimit = INIT_BW; + wb->dirty_ratelimit = INIT_BW; + wb->write_bandwidth = INIT_BW; + wb->avg_write_bandwidth = INIT_BW; - va_start(args, fmt); - dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args); - va_end(args); - if (IS_ERR(dev)) - return PTR_ERR(dev); + spin_lock_init(&wb->work_lock); + INIT_LIST_HEAD(&wb->work_list); + INIT_DELAYED_WORK(&wb->dwork, wb_workfn); - bdi->dev = dev; + wb->congested = wb_congested_get_create(bdi, blkcg_id, gfp); + if (!wb->congested) + return -ENOMEM; - bdi_debug_register(bdi, dev_name(dev)); - set_bit(BDI_registered, &bdi->state); + err = fprop_local_init_percpu(&wb->completions, gfp); + if (err) + goto out_put_cong; - spin_lock_bh(&bdi_lock); - list_add_tail_rcu(&bdi->bdi_list, &bdi_list); - spin_unlock_bh(&bdi_lock); + for (i = 0; i < NR_WB_STAT_ITEMS; i++) { + err = percpu_counter_init(&wb->stat[i], 0, gfp); + if (err) + goto out_destroy_stat; + } - trace_writeback_bdi_register(bdi); return 0; -} -EXPORT_SYMBOL(bdi_register); -int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev) -{ - return bdi_register(bdi, NULL, "%u:%u", MAJOR(dev), MINOR(dev)); +out_destroy_stat: + while (--i) + percpu_counter_destroy(&wb->stat[i]); + fprop_local_destroy_percpu(&wb->completions); +out_put_cong: + wb_congested_put(wb->congested); + return err; } -EXPORT_SYMBOL(bdi_register_dev); /* * Remove bdi from the global list and shutdown any threads we have running */ -static void bdi_wb_shutdown(struct backing_dev_info *bdi) +static void wb_shutdown(struct bdi_writeback *wb) { /* Make sure nobody queues further work */ - spin_lock_bh(&bdi->wb_lock); - if (!test_and_clear_bit(BDI_registered, &bdi->state)) { - spin_unlock_bh(&bdi->wb_lock); + spin_lock_bh(&wb->work_lock); + if (!test_and_clear_bit(WB_registered, &wb->state)) { + spin_unlock_bh(&wb->work_lock); return; } - spin_unlock_bh(&bdi->wb_lock); + spin_unlock_bh(&wb->work_lock); /* - * Make sure nobody finds us on the bdi_list anymore + * Drain work list and shutdown the delayed_work. !WB_registered + * tells wb_workfn() that @wb is dying and its work_list needs to + * be drained no matter what. */ - bdi_remove_from_list(bdi); + mod_delayed_work(bdi_wq, &wb->dwork, 0); + flush_delayed_work(&wb->dwork); + WARN_ON(!list_empty(&wb->work_list)); +} - /* - * Drain work list and shutdown the delayed_work. At this point, - * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi - * is dying and its work_list needs to be drained no matter what. - */ - mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); - flush_delayed_work(&bdi->wb.dwork); +static void wb_exit(struct bdi_writeback *wb) +{ + int i; + + WARN_ON(delayed_work_pending(&wb->dwork)); + + for (i = 0; i < NR_WB_STAT_ITEMS; i++) + percpu_counter_destroy(&wb->stat[i]); + + fprop_local_destroy_percpu(&wb->completions); + wb_congested_put(wb->congested); } +#ifdef CONFIG_CGROUP_WRITEBACK + +#include <linux/memcontrol.h> + /* - * Called when the device behind @bdi has been removed or ejected. + * 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. + */ +static DEFINE_SPINLOCK(cgwb_lock); +static DECLARE_WAIT_QUEUE_HEAD(cgwb_release_wait); + +/** + * wb_congested_get_create - get or create a wb_congested + * @bdi: associated bdi + * @blkcg_id: ID of the associated blkcg + * @gfp: allocation mask + * + * Look up the wb_congested for @blkcg_id on @bdi. If missing, create one. + * The returned wb_congested has its reference count incremented. Returns + * NULL on failure. + */ +struct bdi_writeback_congested * +wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) +{ + struct bdi_writeback_congested *new_congested = NULL, *congested; + struct rb_node **node, *parent; + unsigned long flags; +retry: + spin_lock_irqsave(&cgwb_lock, flags); + + node = &bdi->cgwb_congested_tree.rb_node; + parent = NULL; + + while (*node != NULL) { + parent = *node; + congested = container_of(parent, struct bdi_writeback_congested, + rb_node); + if (congested->blkcg_id < blkcg_id) + node = &parent->rb_left; + else if (congested->blkcg_id > blkcg_id) + node = &parent->rb_right; + else + goto found; + } + + if (new_congested) { + /* !found and storage for new one already allocated, insert */ + congested = new_congested; + new_congested = NULL; + rb_link_node(&congested->rb_node, parent, node); + rb_insert_color(&congested->rb_node, &bdi->cgwb_congested_tree); + goto found; + } + + spin_unlock_irqrestore(&cgwb_lock, flags); + + /* allocate storage for new one and retry */ + new_congested = kzalloc(sizeof(*new_congested), gfp); + if (!new_congested) + return NULL; + + atomic_set(&new_congested->refcnt, 0); + new_congested->bdi = bdi; + new_congested->blkcg_id = blkcg_id; + goto retry; + +found: + atomic_inc(&congested->refcnt); + spin_unlock_irqrestore(&cgwb_lock, flags); + kfree(new_congested); + return congested; +} + +/** + * wb_congested_put - put a wb_congested + * @congested: wb_congested to put * - * We can't really do much here except for reducing the dirty ratio at - * the moment. In the future we should be able to set a flag so that - * the filesystem can handle errors at mark_inode_dirty time instead - * of only at writeback time. + * Put @congested and destroy it if the refcnt reaches zero. */ -void bdi_unregister(struct backing_dev_info *bdi) +void wb_congested_put(struct bdi_writeback_congested *congested) { - if (WARN_ON_ONCE(!bdi->dev)) + unsigned long flags; + + local_irq_save(flags); + if (!atomic_dec_and_lock(&congested->refcnt, &cgwb_lock)) { + local_irq_restore(flags); return; + } - bdi_set_min_ratio(bdi, 0); + /* bdi might already have been destroyed leaving @congested unlinked */ + if (congested->bdi) { + rb_erase(&congested->rb_node, + &congested->bdi->cgwb_congested_tree); + congested->bdi = NULL; + } + + spin_unlock_irqrestore(&cgwb_lock, flags); + kfree(congested); } -EXPORT_SYMBOL(bdi_unregister); -static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi) +static void cgwb_release_workfn(struct work_struct *work) { - memset(wb, 0, sizeof(*wb)); + struct bdi_writeback *wb = container_of(work, struct bdi_writeback, + release_work); + struct backing_dev_info *bdi = wb->bdi; - wb->bdi = bdi; - wb->last_old_flush = jiffies; - INIT_LIST_HEAD(&wb->b_dirty); - INIT_LIST_HEAD(&wb->b_io); - INIT_LIST_HEAD(&wb->b_more_io); - INIT_LIST_HEAD(&wb->b_dirty_time); - spin_lock_init(&wb->list_lock); - INIT_DELAYED_WORK(&wb->dwork, bdi_writeback_workfn); + wb_shutdown(wb); + + css_put(wb->memcg_css); + css_put(wb->blkcg_css); + + fprop_local_destroy_percpu(&wb->memcg_completions); + 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); } -/* - * Initial write bandwidth: 100 MB/s +static void cgwb_release(struct percpu_ref *refcnt) +{ + struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback, + refcnt); + schedule_work(&wb->release_work); +} + +static void cgwb_kill(struct bdi_writeback *wb) +{ + lockdep_assert_held(&cgwb_lock); + + WARN_ON(!radix_tree_delete(&wb->bdi->cgwb_tree, wb->memcg_css->id)); + list_del(&wb->memcg_node); + list_del(&wb->blkcg_node); + percpu_ref_kill(&wb->refcnt); +} + +static int cgwb_create(struct backing_dev_info *bdi, + struct cgroup_subsys_state *memcg_css, gfp_t gfp) +{ + struct mem_cgroup *memcg; + struct cgroup_subsys_state *blkcg_css; + struct blkcg *blkcg; + struct list_head *memcg_cgwb_list, *blkcg_cgwb_list; + struct bdi_writeback *wb; + unsigned long flags; + int ret = 0; + + memcg = mem_cgroup_from_css(memcg_css); + blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &blkio_cgrp_subsys); + blkcg = css_to_blkcg(blkcg_css); + memcg_cgwb_list = mem_cgroup_cgwb_list(memcg); + blkcg_cgwb_list = &blkcg->cgwb_list; + + /* look up again under lock and discard on blkcg mismatch */ + spin_lock_irqsave(&cgwb_lock, flags); + wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); + if (wb && wb->blkcg_css != blkcg_css) { + cgwb_kill(wb); + wb = NULL; + } + spin_unlock_irqrestore(&cgwb_lock, flags); + if (wb) + goto out_put; + + /* need to create a new one */ + wb = kmalloc(sizeof(*wb), gfp); + if (!wb) + return -ENOMEM; + + ret = wb_init(wb, bdi, blkcg_css->id, gfp); + if (ret) + goto err_free; + + ret = percpu_ref_init(&wb->refcnt, cgwb_release, 0, gfp); + if (ret) + goto err_wb_exit; + + ret = fprop_local_init_percpu(&wb->memcg_completions, gfp); + if (ret) + goto err_ref_exit; + + wb->memcg_css = memcg_css; + wb->blkcg_css = blkcg_css; + INIT_WORK(&wb->release_work, cgwb_release_workfn); + set_bit(WB_registered, &wb->state); + + /* + * The root wb determines the registered state of the whole bdi and + * memcg_cgwb_list and blkcg_cgwb_list's next pointers indicate + * whether they're still online. Don't link @wb if any is dead. + * See wb_memcg_offline() and wb_blkcg_offline(). + */ + ret = -ENODEV; + spin_lock_irqsave(&cgwb_lock, flags); + if (test_bit(WB_registered, &bdi->wb.state) && + blkcg_cgwb_list->next && memcg_cgwb_list->next) { + /* 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(&wb->memcg_node, memcg_cgwb_list); + list_add(&wb->blkcg_node, blkcg_cgwb_list); + css_get(memcg_css); + css_get(blkcg_css); + } + } + spin_unlock_irqrestore(&cgwb_lock, flags); + if (ret) { + if (ret == -EEXIST) + ret = 0; + goto err_fprop_exit; + } + goto out_put; + +err_fprop_exit: + fprop_local_destroy_percpu(&wb->memcg_completions); +err_ref_exit: + percpu_ref_exit(&wb->refcnt); +err_wb_exit: + wb_exit(wb); +err_free: + kfree(wb); +out_put: + css_put(blkcg_css); + return ret; +} + +/** + * wb_get_create - get wb for a given memcg, create if necessary + * @bdi: target bdi + * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) + * @gfp: allocation mask to use + * + * Try to get the wb for @memcg_css on @bdi. If it doesn't exist, try to + * create one. The returned wb has its refcount incremented. + * + * This function uses css_get() on @memcg_css and thus expects its refcnt + * to be positive on invocation. IOW, rcu_read_lock() protection on + * @memcg_css isn't enough. try_get it before calling this function. + * + * A wb is keyed by its associated memcg. As blkcg implicitly enables + * memcg on the default hierarchy, memcg association is guaranteed to be + * more specific (equal or descendant to the associated blkcg) and thus can + * identify both the memcg and blkcg associations. + * + * Because the blkcg associated with a memcg may change as blkcg is enabled + * and disabled closer to root in the hierarchy, each wb keeps track of + * both the memcg and blkcg associated with it and verifies the blkcg on + * each lookup. On mismatch, the existing wb is discarded and a new one is + * created. */ -#define INIT_BW (100 << (20 - PAGE_SHIFT)) +struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, + struct cgroup_subsys_state *memcg_css, + gfp_t gfp) +{ + struct bdi_writeback *wb; + + might_sleep_if(gfp & __GFP_WAIT); + + if (!memcg_css->parent) + return &bdi->wb; + + do { + rcu_read_lock(); + wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); + if (wb) { + struct cgroup_subsys_state *blkcg_css; + + /* see whether the blkcg association has changed */ + blkcg_css = cgroup_get_e_css(memcg_css->cgroup, + &blkio_cgrp_subsys); + if (unlikely(wb->blkcg_css != blkcg_css || + !wb_tryget(wb))) + wb = NULL; + css_put(blkcg_css); + } + rcu_read_unlock(); + } while (!wb && !cgwb_create(bdi, memcg_css, gfp)); + + return wb; +} -int bdi_init(struct backing_dev_info *bdi) +static int cgwb_bdi_init(struct backing_dev_info *bdi) { - int i, err; + int ret; + + 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) { + bdi->wb.memcg_css = mem_cgroup_root_css; + bdi->wb.blkcg_css = blkcg_root_css; + } + return ret; +} + +static void cgwb_bdi_destroy(struct backing_dev_info *bdi) +{ + struct radix_tree_iter iter; + struct bdi_writeback_congested *congested, *congested_n; + void **slot; + + 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); + rbtree_postorder_for_each_entry_safe(congested, congested_n, + &bdi->cgwb_congested_tree, rb_node) { + rb_erase(&congested->rb_node, &bdi->cgwb_congested_tree); + congested->bdi = NULL; /* mark @congested unlinked */ + } + + 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)); +} + +/** + * wb_memcg_offline - kill all wb's associated with a memcg being offlined + * @memcg: memcg being offlined + * + * Also prevents creation of any new wb's associated with @memcg. + */ +void wb_memcg_offline(struct mem_cgroup *memcg) +{ + LIST_HEAD(to_destroy); + struct list_head *memcg_cgwb_list = mem_cgroup_cgwb_list(memcg); + struct bdi_writeback *wb, *next; + + spin_lock_irq(&cgwb_lock); + list_for_each_entry_safe(wb, next, memcg_cgwb_list, memcg_node) + cgwb_kill(wb); + memcg_cgwb_list->next = NULL; /* prevent new wb's */ + spin_unlock_irq(&cgwb_lock); +} + +/** + * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined + * @blkcg: blkcg being offlined + * + * Also prevents creation of any new wb's associated with @blkcg. + */ +void wb_blkcg_offline(struct blkcg *blkcg) +{ + LIST_HEAD(to_destroy); + struct bdi_writeback *wb, *next; + + spin_lock_irq(&cgwb_lock); + list_for_each_entry_safe(wb, next, &blkcg->cgwb_list, blkcg_node) + cgwb_kill(wb); + blkcg->cgwb_list.next = NULL; /* prevent new wb's */ + spin_unlock_irq(&cgwb_lock); +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static int cgwb_bdi_init(struct backing_dev_info *bdi) +{ + int err; + + bdi->wb_congested = kzalloc(sizeof(*bdi->wb_congested), GFP_KERNEL); + if (!bdi->wb_congested) + return -ENOMEM; + + err = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); + if (err) { + kfree(bdi->wb_congested); + return err; + } + return 0; +} + +static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { } + +#endif /* CONFIG_CGROUP_WRITEBACK */ + +int bdi_init(struct backing_dev_info *bdi) +{ bdi->dev = NULL; bdi->min_ratio = 0; bdi->max_ratio = 100; bdi->max_prop_frac = FPROP_FRAC_BASE; - spin_lock_init(&bdi->wb_lock); INIT_LIST_HEAD(&bdi->bdi_list); - INIT_LIST_HEAD(&bdi->work_list); + init_waitqueue_head(&bdi->wb_waitq); - bdi_wb_init(&bdi->wb, bdi); + return cgwb_bdi_init(bdi); +} +EXPORT_SYMBOL(bdi_init); - for (i = 0; i < NR_BDI_STAT_ITEMS; i++) { - err = percpu_counter_init(&bdi->bdi_stat[i], 0, GFP_KERNEL); - if (err) - goto err; - } +int bdi_register(struct backing_dev_info *bdi, struct device *parent, + const char *fmt, ...) +{ + va_list args; + struct device *dev; - bdi->dirty_exceeded = 0; + if (bdi->dev) /* The driver needs to use separate queues per device */ + return 0; - bdi->bw_time_stamp = jiffies; - bdi->written_stamp = 0; + va_start(args, fmt); + dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args); + va_end(args); + if (IS_ERR(dev)) + return PTR_ERR(dev); - bdi->balanced_dirty_ratelimit = INIT_BW; - bdi->dirty_ratelimit = INIT_BW; - bdi->write_bandwidth = INIT_BW; - bdi->avg_write_bandwidth = INIT_BW; + bdi->dev = dev; - err = fprop_local_init_percpu(&bdi->completions, GFP_KERNEL); + bdi_debug_register(bdi, dev_name(dev)); + set_bit(WB_registered, &bdi->wb.state); - if (err) { -err: - while (i--) - percpu_counter_destroy(&bdi->bdi_stat[i]); - } + spin_lock_bh(&bdi_lock); + list_add_tail_rcu(&bdi->bdi_list, &bdi_list); + spin_unlock_bh(&bdi_lock); - return err; + trace_writeback_bdi_register(bdi); + return 0; } -EXPORT_SYMBOL(bdi_init); +EXPORT_SYMBOL(bdi_register); -void bdi_destroy(struct backing_dev_info *bdi) +int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev) { - int i; + return bdi_register(bdi, NULL, "%u:%u", MAJOR(dev), MINOR(dev)); +} +EXPORT_SYMBOL(bdi_register_dev); - bdi_wb_shutdown(bdi); +/* + * Remove bdi from bdi_list, and ensure that it is no longer visible + */ +static void bdi_remove_from_list(struct backing_dev_info *bdi) +{ + spin_lock_bh(&bdi_lock); + list_del_rcu(&bdi->bdi_list); + spin_unlock_bh(&bdi_lock); - WARN_ON(!list_empty(&bdi->work_list)); - WARN_ON(delayed_work_pending(&bdi->wb.dwork)); + synchronize_rcu_expedited(); +} + +void bdi_destroy(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); if (bdi->dev) { bdi_debug_unregister(bdi); @@ -453,9 +836,7 @@ void bdi_destroy(struct backing_dev_info *bdi) bdi->dev = NULL; } - for (i = 0; i < NR_BDI_STAT_ITEMS; i++) - percpu_counter_destroy(&bdi->bdi_stat[i]); - fprop_local_destroy_percpu(&bdi->completions); + wb_exit(&bdi->wb); } EXPORT_SYMBOL(bdi_destroy); @@ -488,31 +869,31 @@ static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) }; -static atomic_t nr_bdi_congested[2]; +static atomic_t nr_wb_congested[2]; -void clear_bdi_congested(struct backing_dev_info *bdi, int sync) +void clear_wb_congested(struct bdi_writeback_congested *congested, int sync) { - enum bdi_state bit; wait_queue_head_t *wqh = &congestion_wqh[sync]; + enum wb_state bit; - bit = sync ? BDI_sync_congested : BDI_async_congested; - if (test_and_clear_bit(bit, &bdi->state)) - atomic_dec(&nr_bdi_congested[sync]); + bit = sync ? WB_sync_congested : WB_async_congested; + if (test_and_clear_bit(bit, &congested->state)) + atomic_dec(&nr_wb_congested[sync]); smp_mb__after_atomic(); if (waitqueue_active(wqh)) wake_up(wqh); } -EXPORT_SYMBOL(clear_bdi_congested); +EXPORT_SYMBOL(clear_wb_congested); -void set_bdi_congested(struct backing_dev_info *bdi, int sync) +void set_wb_congested(struct bdi_writeback_congested *congested, int sync) { - enum bdi_state bit; + enum wb_state bit; - bit = sync ? BDI_sync_congested : BDI_async_congested; - if (!test_and_set_bit(bit, &bdi->state)) - atomic_inc(&nr_bdi_congested[sync]); + bit = sync ? WB_sync_congested : WB_async_congested; + if (!test_and_set_bit(bit, &congested->state)) + atomic_inc(&nr_wb_congested[sync]); } -EXPORT_SYMBOL(set_bdi_congested); +EXPORT_SYMBOL(set_wb_congested); /** * congestion_wait - wait for a backing_dev to become uncongested @@ -571,7 +952,7 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout) * encountered in the current zone, yield if necessary instead * of sleeping on the congestion queue */ - if (atomic_read(&nr_bdi_congested[sync]) == 0 || + if (atomic_read(&nr_wb_congested[sync]) == 0 || !test_bit(ZONE_CONGESTED, &zone->flags)) { cond_resched(); diff --git a/mm/bootmem.c b/mm/bootmem.c index 477be696511d..a23dd1934654 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -164,7 +164,7 @@ void __init free_bootmem_late(unsigned long physaddr, unsigned long size) end = PFN_DOWN(physaddr + size); for (; cursor < end; cursor++) { - __free_pages_bootmem(pfn_to_page(cursor), 0); + __free_pages_bootmem(pfn_to_page(cursor), cursor, 0); totalram_pages++; } } @@ -172,7 +172,7 @@ void __init free_bootmem_late(unsigned long physaddr, unsigned long size) static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) { struct page *page; - unsigned long *map, start, end, pages, count = 0; + unsigned long *map, start, end, pages, cur, count = 0; if (!bdata->node_bootmem_map) return 0; @@ -210,17 +210,17 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) { int order = ilog2(BITS_PER_LONG); - __free_pages_bootmem(pfn_to_page(start), order); + __free_pages_bootmem(pfn_to_page(start), start, order); count += BITS_PER_LONG; start += BITS_PER_LONG; } else { - unsigned long cur = start; + cur = start; start = ALIGN(start + 1, BITS_PER_LONG); while (vec && cur != start) { if (vec & 1) { page = pfn_to_page(cur); - __free_pages_bootmem(page, 0); + __free_pages_bootmem(page, cur, 0); count++; } vec >>= 1; @@ -229,12 +229,13 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) } } + cur = bdata->node_min_pfn; page = virt_to_page(bdata->node_bootmem_map); pages = bdata->node_low_pfn - bdata->node_min_pfn; pages = bootmem_bootmap_pages(pages); count += pages; while (pages--) - __free_pages_bootmem(page++, 0); + __free_pages_bootmem(page++, cur++, 0); bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count); @@ -182,7 +182,7 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, if (!size || !memblock_is_region_reserved(base, size)) return -EINVAL; - /* ensure minimal alignment requied by mm core */ + /* ensure minimal alignment required by mm core */ alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order); /* alignment should be aligned with order_per_bit */ @@ -238,7 +238,7 @@ int __init cma_declare_contiguous(phys_addr_t base, /* * high_memory isn't direct mapped memory so retrieving its physical * address isn't appropriate. But it would be useful to check the - * physical address of the highmem boundary so it's justfiable to get + * physical address of the highmem boundary so it's justifiable to get * the physical address from it. On x86 there is a validation check for * this case, so the following workaround is needed to avoid it. */ @@ -316,13 +316,15 @@ int __init cma_declare_contiguous(phys_addr_t base, */ if (base < highmem_start && limit > highmem_start) { addr = memblock_alloc_range(size, alignment, - highmem_start, limit); + highmem_start, limit, + MEMBLOCK_NONE); limit = highmem_start; } if (!addr) { addr = memblock_alloc_range(size, alignment, base, - limit); + limit, + MEMBLOCK_NONE); if (!addr) { ret = -ENOMEM; goto err; @@ -16,7 +16,7 @@ struct cma { extern struct cma cma_areas[MAX_CMA_AREAS]; extern unsigned cma_area_count; -static unsigned long cma_bitmap_maxno(struct cma *cma) +static inline unsigned long cma_bitmap_maxno(struct cma *cma) { return cma->count >> cma->order_per_bit; } diff --git a/mm/cma_debug.c b/mm/cma_debug.c index 7621ee34daa0..f8e4b60db167 100644 --- a/mm/cma_debug.c +++ b/mm/cma_debug.c @@ -39,7 +39,7 @@ static int cma_used_get(void *data, u64 *val) mutex_lock(&cma->lock); /* pages counter is smaller than sizeof(int) */ - used = bitmap_weight(cma->bitmap, (int)cma->count); + used = bitmap_weight(cma->bitmap, (int)cma_bitmap_maxno(cma)); mutex_unlock(&cma->lock); *val = (u64)used << cma->order_per_bit; @@ -52,13 +52,14 @@ static int cma_maxchunk_get(void *data, u64 *val) struct cma *cma = data; unsigned long maxchunk = 0; unsigned long start, end = 0; + unsigned long bitmap_maxno = cma_bitmap_maxno(cma); mutex_lock(&cma->lock); for (;;) { - start = find_next_zero_bit(cma->bitmap, cma->count, end); + start = find_next_zero_bit(cma->bitmap, bitmap_maxno, end); if (start >= cma->count) break; - end = find_next_bit(cma->bitmap, cma->count, start); + end = find_next_bit(cma->bitmap, bitmap_maxno, start); maxchunk = max(end - start, maxchunk); } mutex_unlock(&cma->lock); @@ -170,10 +171,10 @@ static void cma_debugfs_add_one(struct cma *cma, int idx) tmp = debugfs_create_dir(name, cma_debugfs_root); - debugfs_create_file("alloc", S_IWUSR, cma_debugfs_root, cma, + debugfs_create_file("alloc", S_IWUSR, tmp, cma, &cma_alloc_fops); - debugfs_create_file("free", S_IWUSR, cma_debugfs_root, cma, + debugfs_create_file("free", S_IWUSR, tmp, cma, &cma_free_fops); debugfs_create_file("base_pfn", S_IRUGO, tmp, diff --git a/mm/debug.c b/mm/debug.c index 3eb3ac2fcee7..76089ddf99ea 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -7,7 +7,7 @@ #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/ftrace_event.h> +#include <linux/trace_events.h> #include <linux/memcontrol.h> static const struct trace_print_flags pageflag_names[] = { diff --git a/mm/fadvise.c b/mm/fadvise.c index 4a3907cf79f8..b8a5bc66b0c0 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -115,7 +115,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) case POSIX_FADV_NOREUSE: break; case POSIX_FADV_DONTNEED: - if (!bdi_write_congested(bdi)) + if (!inode_write_congested(mapping->host)) __filemap_fdatawrite_range(mapping, offset, endbyte, WB_SYNC_NONE); diff --git a/mm/filemap.c b/mm/filemap.c index 6bf5e42d560a..1283fc825458 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -100,6 +100,7 @@ * ->tree_lock (page_remove_rmap->set_page_dirty) * bdi.wb->list_lock (page_remove_rmap->set_page_dirty) * ->inode->i_lock (page_remove_rmap->set_page_dirty) + * ->memcg->move_lock (page_remove_rmap->mem_cgroup_begin_page_stat) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->__set_page_dirty_buffers) @@ -174,9 +175,11 @@ static void page_cache_tree_delete(struct address_space *mapping, /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage - * is safe. The caller must hold the mapping's tree_lock. + * is safe. The caller must hold the mapping's tree_lock and + * mem_cgroup_begin_page_stat(). */ -void __delete_from_page_cache(struct page *page, void *shadow) +void __delete_from_page_cache(struct page *page, void *shadow, + struct mem_cgroup *memcg) { struct address_space *mapping = page->mapping; @@ -196,7 +199,9 @@ void __delete_from_page_cache(struct page *page, void *shadow) page->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ - __dec_zone_page_state(page, NR_FILE_PAGES); + /* hugetlb pages do not participate in page cache accounting. */ + if (!PageHuge(page)) + __dec_zone_page_state(page, NR_FILE_PAGES); if (PageSwapBacked(page)) __dec_zone_page_state(page, NR_SHMEM); BUG_ON(page_mapped(page)); @@ -210,7 +215,8 @@ void __delete_from_page_cache(struct page *page, void *shadow) * anyway will be cleared before returning page into buddy allocator. */ if (WARN_ON_ONCE(PageDirty(page))) - account_page_cleaned(page, mapping); + account_page_cleaned(page, mapping, memcg, + inode_to_wb(mapping->host)); } /** @@ -224,14 +230,20 @@ void __delete_from_page_cache(struct page *page, void *shadow) void delete_from_page_cache(struct page *page) { struct address_space *mapping = page->mapping; + struct mem_cgroup *memcg; + unsigned long flags; + void (*freepage)(struct page *); BUG_ON(!PageLocked(page)); freepage = mapping->a_ops->freepage; - spin_lock_irq(&mapping->tree_lock); - __delete_from_page_cache(page, NULL); - spin_unlock_irq(&mapping->tree_lock); + + memcg = mem_cgroup_begin_page_stat(page); + spin_lock_irqsave(&mapping->tree_lock, flags); + __delete_from_page_cache(page, NULL, memcg); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); if (freepage) freepage(page); @@ -281,7 +293,9 @@ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, if (!mapping_cap_writeback_dirty(mapping)) return 0; + wbc_attach_fdatawrite_inode(&wbc, mapping->host); ret = do_writepages(mapping, &wbc); + wbc_detach_inode(&wbc); return ret; } @@ -470,6 +484,8 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) if (!error) { struct address_space *mapping = old->mapping; void (*freepage)(struct page *); + struct mem_cgroup *memcg; + unsigned long flags; pgoff_t offset = old->index; freepage = mapping->a_ops->freepage; @@ -478,15 +494,22 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) new->mapping = mapping; new->index = offset; - spin_lock_irq(&mapping->tree_lock); - __delete_from_page_cache(old, NULL); + memcg = mem_cgroup_begin_page_stat(old); + spin_lock_irqsave(&mapping->tree_lock, flags); + __delete_from_page_cache(old, NULL, memcg); error = radix_tree_insert(&mapping->page_tree, offset, new); BUG_ON(error); mapping->nrpages++; - __inc_zone_page_state(new, NR_FILE_PAGES); + + /* + * hugetlb pages do not participate in page cache accounting. + */ + if (!PageHuge(new)) + __inc_zone_page_state(new, NR_FILE_PAGES); if (PageSwapBacked(new)) __inc_zone_page_state(new, NR_SHMEM); - spin_unlock_irq(&mapping->tree_lock); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); mem_cgroup_migrate(old, new, true); radix_tree_preload_end(); if (freepage) @@ -575,7 +598,10 @@ static int __add_to_page_cache_locked(struct page *page, radix_tree_preload_end(); if (unlikely(error)) goto err_insert; - __inc_zone_page_state(page, NR_FILE_PAGES); + + /* hugetlb pages do not participate in page cache accounting. */ + if (!huge) + __inc_zone_page_state(page, NR_FILE_PAGES); spin_unlock_irq(&mapping->tree_lock); if (!huge) mem_cgroup_commit_charge(page, memcg, false); @@ -1654,8 +1680,8 @@ no_cached_page: error = -ENOMEM; goto out; } - error = add_to_page_cache_lru(page, mapping, - index, GFP_KERNEL); + error = add_to_page_cache_lru(page, mapping, index, + GFP_KERNEL & mapping_gfp_mask(mapping)); if (error) { page_cache_release(page); if (error == -EEXIST) { @@ -1756,7 +1782,8 @@ static int page_cache_read(struct file *file, pgoff_t offset) if (!page) return -ENOMEM; - ret = add_to_page_cache_lru(page, mapping, offset, GFP_KERNEL); + ret = add_to_page_cache_lru(page, mapping, offset, + GFP_KERNEL & mapping_gfp_mask(mapping)); if (ret == 0) ret = mapping->a_ops->readpage(file, page); else if (ret == -EEXIST) @@ -2536,7 +2563,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) /* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); - err = file_remove_suid(file); + err = file_remove_privs(file); if (err) goto out; diff --git a/mm/frontswap.c b/mm/frontswap.c index 8d82809eb085..27a9924caf61 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -21,11 +21,16 @@ #include <linux/swapfile.h> /* - * frontswap_ops is set by frontswap_register_ops to contain the pointers - * to the frontswap "backend" implementation functions. + * frontswap_ops are added by frontswap_register_ops, and provide the + * frontswap "backend" implementation functions. Multiple implementations + * may be registered, but implementations can never deregister. This + * is a simple singly-linked list of all registered implementations. */ static struct frontswap_ops *frontswap_ops __read_mostly; +#define for_each_frontswap_ops(ops) \ + for ((ops) = frontswap_ops; (ops); (ops) = (ops)->next) + /* * If enabled, frontswap_store will return failure even on success. As * a result, the swap subsystem will always write the page to swap, in @@ -79,15 +84,6 @@ static inline void inc_frontswap_invalidates(void) { } * on all frontswap functions to not call the backend until the backend * has registered. * - * Specifically when no backend is registered (nobody called - * frontswap_register_ops) all calls to frontswap_init (which is done via - * swapon -> enable_swap_info -> frontswap_init) are registered and remembered - * (via the setting of need_init bitmap) but fail to create tmem_pools. When a - * backend registers with frontswap at some later point the previous - * calls to frontswap_init are executed (by iterating over the need_init - * bitmap) to create tmem_pools and set the respective poolids. All of that is - * guarded by us using atomic bit operations on the 'need_init' bitmap. - * * This would not guards us against the user deciding to call swapoff right as * we are calling the backend to initialize (so swapon is in action). * Fortunatly for us, the swapon_mutex has been taked by the callee so we are @@ -106,37 +102,64 @@ static inline void inc_frontswap_invalidates(void) { } * * Obviously the opposite (unloading the backend) must be done after all * the frontswap_[store|load|invalidate_area|invalidate_page] start - * ignorning or failing the requests - at which point frontswap_ops - * would have to be made in some fashion atomic. + * ignoring or failing the requests. However, there is currently no way + * to unload a backend once it is registered. */ -static DECLARE_BITMAP(need_init, MAX_SWAPFILES); /* - * Register operations for frontswap, returning previous thus allowing - * detection of multiple backends and possible nesting. + * Register operations for frontswap */ -struct frontswap_ops *frontswap_register_ops(struct frontswap_ops *ops) +void frontswap_register_ops(struct frontswap_ops *ops) { - struct frontswap_ops *old = frontswap_ops; - int i; - - for (i = 0; i < MAX_SWAPFILES; i++) { - if (test_and_clear_bit(i, need_init)) { - struct swap_info_struct *sis = swap_info[i]; - /* __frontswap_init _should_ have set it! */ - if (!sis->frontswap_map) - return ERR_PTR(-EINVAL); - ops->init(i); - } + DECLARE_BITMAP(a, MAX_SWAPFILES); + DECLARE_BITMAP(b, MAX_SWAPFILES); + struct swap_info_struct *si; + unsigned int i; + + bitmap_zero(a, MAX_SWAPFILES); + bitmap_zero(b, MAX_SWAPFILES); + + spin_lock(&swap_lock); + plist_for_each_entry(si, &swap_active_head, list) { + if (!WARN_ON(!si->frontswap_map)) + set_bit(si->type, a); } + spin_unlock(&swap_lock); + + /* the new ops needs to know the currently active swap devices */ + for_each_set_bit(i, a, MAX_SWAPFILES) + ops->init(i); + /* - * We MUST have frontswap_ops set _after_ the frontswap_init's - * have been called. Otherwise __frontswap_store might fail. Hence - * the barrier to make sure compiler does not re-order us. + * Setting frontswap_ops must happen after the ops->init() calls + * above; cmpxchg implies smp_mb() which will ensure the init is + * complete at this point. */ - barrier(); - frontswap_ops = ops; - return old; + do { + ops->next = frontswap_ops; + } while (cmpxchg(&frontswap_ops, ops->next, ops) != ops->next); + + spin_lock(&swap_lock); + plist_for_each_entry(si, &swap_active_head, list) { + if (si->frontswap_map) + set_bit(si->type, b); + } + spin_unlock(&swap_lock); + + /* + * On the very unlikely chance that a swap device was added or + * removed between setting the "a" list bits and the ops init + * calls, we re-check and do init or invalidate for any changed + * bits. + */ + if (unlikely(!bitmap_equal(a, b, MAX_SWAPFILES))) { + for (i = 0; i < MAX_SWAPFILES; i++) { + if (!test_bit(i, a) && test_bit(i, b)) + ops->init(i); + else if (test_bit(i, a) && !test_bit(i, b)) + ops->invalidate_area(i); + } + } } EXPORT_SYMBOL(frontswap_register_ops); @@ -164,6 +187,7 @@ EXPORT_SYMBOL(frontswap_tmem_exclusive_gets); void __frontswap_init(unsigned type, unsigned long *map) { struct swap_info_struct *sis = swap_info[type]; + struct frontswap_ops *ops; BUG_ON(sis == NULL); @@ -179,28 +203,30 @@ void __frontswap_init(unsigned type, unsigned long *map) * p->frontswap set to something valid to work properly. */ frontswap_map_set(sis, map); - if (frontswap_ops) - frontswap_ops->init(type); - else { - BUG_ON(type >= MAX_SWAPFILES); - set_bit(type, need_init); - } + + for_each_frontswap_ops(ops) + ops->init(type); } EXPORT_SYMBOL(__frontswap_init); bool __frontswap_test(struct swap_info_struct *sis, pgoff_t offset) { - bool ret = false; - - if (frontswap_ops && sis->frontswap_map) - ret = test_bit(offset, sis->frontswap_map); - return ret; + if (sis->frontswap_map) + return test_bit(offset, sis->frontswap_map); + return false; } EXPORT_SYMBOL(__frontswap_test); +static inline void __frontswap_set(struct swap_info_struct *sis, + pgoff_t offset) +{ + set_bit(offset, sis->frontswap_map); + atomic_inc(&sis->frontswap_pages); +} + static inline void __frontswap_clear(struct swap_info_struct *sis, - pgoff_t offset) + pgoff_t offset) { clear_bit(offset, sis->frontswap_map); atomic_dec(&sis->frontswap_pages); @@ -215,39 +241,46 @@ static inline void __frontswap_clear(struct swap_info_struct *sis, */ int __frontswap_store(struct page *page) { - int ret = -1, dup = 0; + int ret = -1; swp_entry_t entry = { .val = page_private(page), }; int type = swp_type(entry); struct swap_info_struct *sis = swap_info[type]; pgoff_t offset = swp_offset(entry); + struct frontswap_ops *ops; /* * Return if no backend registed. * Don't need to inc frontswap_failed_stores here. */ if (!frontswap_ops) - return ret; + return -1; BUG_ON(!PageLocked(page)); BUG_ON(sis == NULL); - if (__frontswap_test(sis, offset)) - dup = 1; - ret = frontswap_ops->store(type, offset, page); + + /* + * If a dup, we must remove the old page first; we can't leave the + * old page no matter if the store of the new page succeeds or fails, + * and we can't rely on the new page replacing the old page as we may + * not store to the same implementation that contains the old page. + */ + if (__frontswap_test(sis, offset)) { + __frontswap_clear(sis, offset); + for_each_frontswap_ops(ops) + ops->invalidate_page(type, offset); + } + + /* Try to store in each implementation, until one succeeds. */ + for_each_frontswap_ops(ops) { + ret = ops->store(type, offset, page); + if (!ret) /* successful store */ + break; + } if (ret == 0) { - set_bit(offset, sis->frontswap_map); + __frontswap_set(sis, offset); inc_frontswap_succ_stores(); - if (!dup) - atomic_inc(&sis->frontswap_pages); } else { - /* - failed dup always results in automatic invalidate of - the (older) page from frontswap - */ inc_frontswap_failed_stores(); - if (dup) { - __frontswap_clear(sis, offset); - frontswap_ops->invalidate_page(type, offset); - } } if (frontswap_writethrough_enabled) /* report failure so swap also writes to swap device */ @@ -268,14 +301,22 @@ int __frontswap_load(struct page *page) int type = swp_type(entry); struct swap_info_struct *sis = swap_info[type]; pgoff_t offset = swp_offset(entry); + struct frontswap_ops *ops; + + if (!frontswap_ops) + return -1; BUG_ON(!PageLocked(page)); BUG_ON(sis == NULL); - /* - * __frontswap_test() will check whether there is backend registered - */ - if (__frontswap_test(sis, offset)) - ret = frontswap_ops->load(type, offset, page); + if (!__frontswap_test(sis, offset)) + return -1; + + /* Try loading from each implementation, until one succeeds. */ + for_each_frontswap_ops(ops) { + ret = ops->load(type, offset, page); + if (!ret) /* successful load */ + break; + } if (ret == 0) { inc_frontswap_loads(); if (frontswap_tmem_exclusive_gets_enabled) { @@ -294,16 +335,19 @@ EXPORT_SYMBOL(__frontswap_load); void __frontswap_invalidate_page(unsigned type, pgoff_t offset) { struct swap_info_struct *sis = swap_info[type]; + struct frontswap_ops *ops; + + if (!frontswap_ops) + return; BUG_ON(sis == NULL); - /* - * __frontswap_test() will check whether there is backend registered - */ - if (__frontswap_test(sis, offset)) { - frontswap_ops->invalidate_page(type, offset); - __frontswap_clear(sis, offset); - inc_frontswap_invalidates(); - } + if (!__frontswap_test(sis, offset)) + return; + + for_each_frontswap_ops(ops) + ops->invalidate_page(type, offset); + __frontswap_clear(sis, offset); + inc_frontswap_invalidates(); } EXPORT_SYMBOL(__frontswap_invalidate_page); @@ -314,16 +358,19 @@ EXPORT_SYMBOL(__frontswap_invalidate_page); void __frontswap_invalidate_area(unsigned type) { struct swap_info_struct *sis = swap_info[type]; + struct frontswap_ops *ops; - if (frontswap_ops) { - BUG_ON(sis == NULL); - if (sis->frontswap_map == NULL) - return; - frontswap_ops->invalidate_area(type); - atomic_set(&sis->frontswap_pages, 0); - bitmap_zero(sis->frontswap_map, sis->max); - } - clear_bit(type, need_init); + if (!frontswap_ops) + return; + + BUG_ON(sis == NULL); + if (sis->frontswap_map == NULL) + return; + + for_each_frontswap_ops(ops) + ops->invalidate_area(type); + atomic_set(&sis->frontswap_pages, 0); + bitmap_zero(sis->frontswap_map, sis->max); } EXPORT_SYMBOL(__frontswap_invalidate_area); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 078832cf3636..097c7a4bfbd9 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1031,7 +1031,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, goto out_free_pages; VM_BUG_ON_PAGE(!PageHead(page), page); - pmdp_clear_flush_notify(vma, haddr, pmd); + pmdp_huge_clear_flush_notify(vma, haddr, pmd); /* leave pmd empty until pte is filled */ pgtable = pgtable_trans_huge_withdraw(mm, pmd); @@ -1174,7 +1174,7 @@ alloc: pmd_t entry; entry = mk_huge_pmd(new_page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - pmdp_clear_flush_notify(vma, haddr, pmd); + pmdp_huge_clear_flush_notify(vma, haddr, pmd); page_add_new_anon_rmap(new_page, vma, haddr); mem_cgroup_commit_charge(new_page, memcg, false); lru_cache_add_active_or_unevictable(new_page, vma); @@ -1396,12 +1396,12 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t orig_pmd; /* * For architectures like ppc64 we look at deposited pgtable - * when calling pmdp_get_and_clear. So do the + * when calling pmdp_huge_get_and_clear. So do the * pgtable_trans_huge_withdraw after finishing pmdp related * operations. */ - orig_pmd = pmdp_get_and_clear_full(tlb->mm, addr, pmd, - tlb->fullmm); + orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd, + tlb->fullmm); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd); if (is_huge_zero_pmd(orig_pmd)) { @@ -1459,7 +1459,7 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, new_ptl = pmd_lockptr(mm, new_pmd); if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); - pmd = pmdp_get_and_clear(mm, old_addr, old_pmd); + pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd); VM_BUG_ON(!pmd_none(*new_pmd)); if (pmd_move_must_withdraw(new_ptl, old_ptl)) { @@ -1505,7 +1505,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, } if (!prot_numa || !pmd_protnone(*pmd)) { - entry = pmdp_get_and_clear_notify(mm, addr, pmd); + entry = pmdp_huge_get_and_clear_notify(mm, addr, pmd); entry = pmd_modify(entry, newprot); if (preserve_write) entry = pmd_mkwrite(entry); @@ -1676,12 +1676,7 @@ static void __split_huge_page_refcount(struct page *page, /* after clearing PageTail the gup refcount can be released */ smp_mb__after_atomic(); - /* - * retain hwpoison flag of the poisoned tail page: - * fix for the unsuitable process killed on Guest Machine(KVM) - * by the memory-failure. - */ - page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON; + page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; page_tail->flags |= (page->flags & ((1L << PG_referenced) | (1L << PG_swapbacked) | @@ -2499,7 +2494,7 @@ static void collapse_huge_page(struct mm_struct *mm, * huge and small TLB entries for the same virtual address * to avoid the risk of CPU bugs in that area. */ - _pmd = pmdp_clear_flush(vma, address, pmd); + _pmd = pmdp_collapse_flush(vma, address, pmd); spin_unlock(pmd_ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); @@ -2799,7 +2794,7 @@ static void khugepaged_do_scan(void) cond_resched(); - if (unlikely(kthread_should_stop() || freezing(current))) + if (unlikely(kthread_should_stop() || try_to_freeze())) break; spin_lock(&khugepaged_mm_lock); @@ -2820,8 +2815,6 @@ static void khugepaged_do_scan(void) static void khugepaged_wait_work(void) { - try_to_freeze(); - if (khugepaged_has_work()) { if (!khugepaged_scan_sleep_millisecs) return; @@ -2865,7 +2858,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, pmd_t _pmd; int i; - pmdp_clear_flush_notify(vma, haddr, pmd); + pmdp_huge_clear_flush_notify(vma, haddr, pmd); /* leave pmd empty until pte is filled */ pgtable = pgtable_trans_huge_withdraw(mm, pmd); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 271e4432734c..a8c3087089d8 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -40,6 +40,11 @@ int hugepages_treat_as_movable; int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; struct hstate hstates[HUGE_MAX_HSTATE]; +/* + * Minimum page order among possible hugepage sizes, set to a proper value + * at boot time. + */ +static unsigned int minimum_order __read_mostly = UINT_MAX; __initdata LIST_HEAD(huge_boot_pages); @@ -212,8 +217,20 @@ static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) * Region tracking -- allows tracking of reservations and instantiated pages * across the pages in a mapping. * - * The region data structures are embedded into a resv_map and - * protected by a resv_map's lock + * The region data structures are embedded into a resv_map and protected + * by a resv_map's lock. The set of regions within the resv_map represent + * reservations for huge pages, or huge pages that have already been + * instantiated within the map. The from and to elements are huge page + * indicies into the associated mapping. from indicates the starting index + * of the region. to represents the first index past the end of the region. + * + * For example, a file region structure with from == 0 and to == 4 represents + * four huge pages in a mapping. It is important to note that the to element + * represents the first element past the end of the region. This is used in + * arithmetic as 4(to) - 0(from) = 4 huge pages in the region. + * + * Interval notation of the form [from, to) will be used to indicate that + * the endpoint from is inclusive and to is exclusive. */ struct file_region { struct list_head link; @@ -221,10 +238,22 @@ struct file_region { long to; }; +/* + * Add the huge page range represented by [f, t) to the reserve + * map. Existing regions will be expanded to accommodate the + * specified range. We know only existing regions need to be + * expanded, because region_add is only called after region_chg + * with the same range. If a new file_region structure must + * be allocated, it is done in region_chg. + * + * Return the number of new huge pages added to the map. This + * number is greater than or equal to zero. + */ static long region_add(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg, *nrg, *trg; + long add = 0; spin_lock(&resv->lock); /* Locate the region we are either in or before. */ @@ -250,16 +279,45 @@ static long region_add(struct resv_map *resv, long f, long t) if (rg->to > t) t = rg->to; if (rg != nrg) { + /* Decrement return value by the deleted range. + * Another range will span this area so that by + * end of routine add will be >= zero + */ + add -= (rg->to - rg->from); list_del(&rg->link); kfree(rg); } } + + add += (nrg->from - f); /* Added to beginning of region */ nrg->from = f; + add += t - nrg->to; /* Added to end of region */ nrg->to = t; + spin_unlock(&resv->lock); - return 0; + VM_BUG_ON(add < 0); + return add; } +/* + * Examine the existing reserve map and determine how many + * huge pages in the specified range [f, t) are NOT currently + * represented. This routine is called before a subsequent + * call to region_add that will actually modify the reserve + * map to add the specified range [f, t). region_chg does + * not change the number of huge pages represented by the + * map. However, if the existing regions in the map can not + * be expanded to represent the new range, a new file_region + * structure is added to the map as a placeholder. This is + * so that the subsequent region_add call will have all the + * regions it needs and will not fail. + * + * Returns the number of huge pages that need to be added + * to the existing reservation map for the range [f, t). + * This number is greater or equal to zero. -ENOMEM is + * returned if a new file_region structure is needed and can + * not be allocated. + */ static long region_chg(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; @@ -326,6 +384,11 @@ out_nrg: return chg; } +/* + * Truncate the reserve map at index 'end'. Modify/truncate any + * region which contains end. Delete any regions past end. + * Return the number of huge pages removed from the map. + */ static long region_truncate(struct resv_map *resv, long end) { struct list_head *head = &resv->regions; @@ -361,6 +424,10 @@ out: return chg; } +/* + * Count and return the number of huge pages in the reserve map + * that intersect with the range [f, t). + */ static long region_count(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; @@ -908,7 +975,6 @@ static void update_and_free_page(struct hstate *h, struct page *page) destroy_compound_gigantic_page(page, huge_page_order(h)); free_gigantic_page(page, huge_page_order(h)); } else { - arch_release_hugepage(page); __free_pages(page, huge_page_order(h)); } } @@ -1093,10 +1159,6 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); if (page) { - if (arch_prepare_hugepage(page)) { - __free_pages(page, huge_page_order(h)); - return NULL; - } prep_new_huge_page(h, page, nid); } @@ -1188,19 +1250,13 @@ static void dissolve_free_huge_page(struct page *page) */ void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) { - unsigned int order = 8 * sizeof(void *); unsigned long pfn; - struct hstate *h; if (!hugepages_supported()) return; - /* Set scan step to minimum hugepage size */ - for_each_hstate(h) - if (order > huge_page_order(h)) - order = huge_page_order(h); - VM_BUG_ON(!IS_ALIGNED(start_pfn, 1 << order)); - for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) + VM_BUG_ON(!IS_ALIGNED(start_pfn, 1 << minimum_order)); + for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) dissolve_free_huge_page(pfn_to_page(pfn)); } @@ -1254,11 +1310,6 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); - if (page && arch_prepare_hugepage(page)) { - __free_pages(page, huge_page_order(h)); - page = NULL; - } - spin_lock(&hugetlb_lock); if (page) { INIT_LIST_HEAD(&page->lru); @@ -1423,46 +1474,56 @@ static void return_unused_surplus_pages(struct hstate *h, } /* - * Determine if the huge page at addr within the vma has an associated - * reservation. Where it does not we will need to logically increase - * reservation and actually increase subpool usage before an allocation - * can occur. Where any new reservation would be required the - * reservation change is prepared, but not committed. Once the page - * has been allocated from the subpool and instantiated the change should - * be committed via vma_commit_reservation. No action is required on - * failure. + * vma_needs_reservation and vma_commit_reservation are used by the huge + * page allocation routines to manage reservations. + * + * vma_needs_reservation is called to determine if the huge page at addr + * within the vma has an associated reservation. If a reservation is + * needed, the value 1 is returned. The caller is then responsible for + * managing the global reservation and subpool usage counts. After + * the huge page has been allocated, vma_commit_reservation is called + * to add the page to the reservation map. + * + * In the normal case, vma_commit_reservation returns the same value + * as the preceding vma_needs_reservation call. The only time this + * is not the case is if a reserve map was changed between calls. It + * is the responsibility of the caller to notice the difference and + * take appropriate action. */ -static long vma_needs_reservation(struct hstate *h, - struct vm_area_struct *vma, unsigned long addr) +static long __vma_reservation_common(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr, + bool commit) { struct resv_map *resv; pgoff_t idx; - long chg; + long ret; resv = vma_resv_map(vma); if (!resv) return 1; idx = vma_hugecache_offset(h, vma, addr); - chg = region_chg(resv, idx, idx + 1); + if (commit) + ret = region_add(resv, idx, idx + 1); + else + ret = region_chg(resv, idx, idx + 1); if (vma->vm_flags & VM_MAYSHARE) - return chg; + return ret; else - return chg < 0 ? chg : 0; + return ret < 0 ? ret : 0; } -static void vma_commit_reservation(struct hstate *h, + +static long vma_needs_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { - struct resv_map *resv; - pgoff_t idx; - - resv = vma_resv_map(vma); - if (!resv) - return; + return __vma_reservation_common(h, vma, addr, false); +} - idx = vma_hugecache_offset(h, vma, addr); - region_add(resv, idx, idx + 1); +static long vma_commit_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) +{ + return __vma_reservation_common(h, vma, addr, true); } static struct page *alloc_huge_page(struct vm_area_struct *vma, @@ -1471,7 +1532,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct page *page; - long chg; + long chg, commit; int ret, idx; struct hugetlb_cgroup *h_cg; @@ -1512,7 +1573,22 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, set_page_private(page, (unsigned long)spool); - vma_commit_reservation(h, vma, addr); + commit = vma_commit_reservation(h, vma, addr); + if (unlikely(chg > commit)) { + /* + * The page was added to the reservation map between + * vma_needs_reservation and vma_commit_reservation. + * This indicates a race with hugetlb_reserve_pages. + * Adjust for the subpool count incremented above AND + * in hugetlb_reserve_pages for the same page. Also, + * the reservation count added in hugetlb_reserve_pages + * no longer applies. + */ + long rsv_adjust; + + rsv_adjust = hugepage_subpool_put_pages(spool, 1); + hugetlb_acct_memory(h, -rsv_adjust); + } return page; out_uncharge_cgroup: @@ -1627,10 +1703,14 @@ static void __init hugetlb_init_hstates(void) struct hstate *h; for_each_hstate(h) { + if (minimum_order > huge_page_order(h)) + minimum_order = huge_page_order(h); + /* oversize hugepages were init'ed in early boot */ if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); } + VM_BUG_ON(minimum_order == UINT_MAX); } static char * __init memfmt(char *buf, unsigned long n) @@ -3626,8 +3706,24 @@ int hugetlb_reserve_pages(struct inode *inode, * consumed reservations are stored in the map. Hence, nothing * else has to be done for private mappings here */ - if (!vma || vma->vm_flags & VM_MAYSHARE) - region_add(resv_map, from, to); + if (!vma || vma->vm_flags & VM_MAYSHARE) { + long add = region_add(resv_map, from, to); + + if (unlikely(chg > add)) { + /* + * pages in this range were added to the reserve + * map between region_chg and region_add. This + * indicates a race with alloc_huge_page. Adjust + * the subpool and reserve counts modified above + * based on the difference. + */ + long rsv_adjust; + + rsv_adjust = hugepage_subpool_put_pages(spool, + chg - add); + hugetlb_acct_memory(h, -rsv_adjust); + } + } return 0; out_err: if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) @@ -3789,6 +3885,11 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) { return NULL; } + +int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) +{ + return 0; +} #define want_pmd_share() (0) #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c index 4ca5fe0042e1..bf73ac17dad4 100644 --- a/mm/hwpoison-inject.c +++ b/mm/hwpoison-inject.c @@ -28,7 +28,7 @@ static int hwpoison_inject(void *data, u64 val) /* * This implies unable to support free buddy pages. */ - if (!get_page_unless_zero(hpage)) + if (!get_hwpoison_page(p)) return 0; if (!hwpoison_filter_enable) @@ -58,7 +58,7 @@ inject: pr_info("Injecting memory failure at pfn %#lx\n", pfn); return memory_failure(pfn, 18, MF_COUNT_INCREASED); put_out: - put_page(hpage); + put_page(p); return 0; } diff --git a/mm/internal.h b/mm/internal.h index a25e359a4039..36b23f1e2ca6 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -155,7 +155,8 @@ __find_buddy_index(unsigned long page_idx, unsigned int order) } extern int __isolate_free_page(struct page *page, unsigned int order); -extern void __free_pages_bootmem(struct page *page, unsigned int order); +extern void __free_pages_bootmem(struct page *page, unsigned long pfn, + unsigned int order); extern void prep_compound_page(struct page *page, unsigned long order); #ifdef CONFIG_MEMORY_FAILURE extern bool is_free_buddy_page(struct page *page); @@ -361,10 +362,7 @@ do { \ } while (0) extern void mminit_verify_pageflags_layout(void); -extern void mminit_verify_page_links(struct page *page, - enum zone_type zone, unsigned long nid, unsigned long pfn); extern void mminit_verify_zonelist(void); - #else static inline void mminit_dprintk(enum mminit_level level, @@ -376,11 +374,6 @@ static inline void mminit_verify_pageflags_layout(void) { } -static inline void mminit_verify_page_links(struct page *page, - enum zone_type zone, unsigned long nid, unsigned long pfn) -{ -} - static inline void mminit_verify_zonelist(void) { } diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 6c513a63ea84..7b28e9cdf1c7 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -2,7 +2,7 @@ * This file contains shadow memory manipulation code. * * Copyright (c) 2014 Samsung Electronics Co., Ltd. - * Author: Andrey Ryabinin <a.ryabinin@samsung.com> + * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com> * * Some of code borrowed from https://github.com/xairy/linux by * Andrey Konovalov <adech.fo@gmail.com> diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 4986b0acab21..c242adf6bc85 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -7,7 +7,6 @@ #define KASAN_SHADOW_MASK (KASAN_SHADOW_SCALE_SIZE - 1) #define KASAN_FREE_PAGE 0xFF /* page was freed */ -#define KASAN_FREE_PAGE 0xFF /* page was freed */ #define KASAN_PAGE_REDZONE 0xFE /* redzone for kmalloc_large allocations */ #define KASAN_KMALLOC_REDZONE 0xFC /* redzone inside slub object */ #define KASAN_KMALLOC_FREE 0xFB /* object was freed (kmem_cache_free/kfree) */ diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 680ceedf810a..e07c94fbd0ac 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -2,7 +2,7 @@ * This file contains error reporting code. * * Copyright (c) 2014 Samsung Electronics Co., Ltd. - * Author: Andrey Ryabinin <a.ryabinin@samsung.com> + * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com> * * Some of code borrowed from https://github.com/xairy/linux by * Andrey Konovalov <adech.fo@gmail.com> diff --git a/mm/kmemleak.c b/mm/kmemleak.c index f0fe4f2c1fa7..cf79f110157c 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -53,6 +53,13 @@ * modifications to the memory scanning parameters including the scan_thread * pointer * + * Locks and mutexes are acquired/nested in the following order: + * + * scan_mutex [-> object->lock] -> kmemleak_lock -> other_object->lock (SINGLE_DEPTH_NESTING) + * + * No kmemleak_lock and object->lock nesting is allowed outside scan_mutex + * regions. + * * The kmemleak_object structures have a use_count incremented or decremented * using the get_object()/put_object() functions. When the use_count becomes * 0, this count can no longer be incremented and put_object() schedules the @@ -195,6 +202,8 @@ static struct kmem_cache *scan_area_cache; /* set if tracing memory operations is enabled */ static int kmemleak_enabled; +/* same as above but only for the kmemleak_free() callback */ +static int kmemleak_free_enabled; /* set in the late_initcall if there were no errors */ static int kmemleak_initialized; /* enables or disables early logging of the memory operations */ @@ -483,8 +492,7 @@ static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias) rcu_read_lock(); read_lock_irqsave(&kmemleak_lock, flags); - if (ptr >= min_addr && ptr < max_addr) - object = lookup_object(ptr, alias); + object = lookup_object(ptr, alias); read_unlock_irqrestore(&kmemleak_lock, flags); /* check whether the object is still available */ @@ -496,6 +504,27 @@ static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias) } /* + * Look up an object in the object search tree and remove it from both + * object_tree_root and object_list. The returned object's use_count should be + * at least 1, as initially set by create_object(). + */ +static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int alias) +{ + unsigned long flags; + struct kmemleak_object *object; + + write_lock_irqsave(&kmemleak_lock, flags); + object = lookup_object(ptr, alias); + if (object) { + rb_erase(&object->rb_node, &object_tree_root); + list_del_rcu(&object->object_list); + } + write_unlock_irqrestore(&kmemleak_lock, flags); + + return object; +} + +/* * Save stack trace to the given array of MAX_TRACE size. */ static int __save_stack_trace(unsigned long *trace) @@ -580,11 +609,13 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, kmemleak_stop("Cannot insert 0x%lx into the object " "search tree (overlaps existing)\n", ptr); + /* + * No need for parent->lock here since "parent" cannot + * be freed while the kmemleak_lock is held. + */ + dump_object_info(parent); kmem_cache_free(object_cache, object); - object = parent; - spin_lock(&object->lock); - dump_object_info(object); - spin_unlock(&object->lock); + object = NULL; goto out; } } @@ -598,20 +629,14 @@ out: } /* - * Remove the metadata (struct kmemleak_object) for a memory block from the - * object_list and object_tree_root and decrement its use_count. + * Mark the object as not allocated and schedule RCU freeing via put_object(). */ static void __delete_object(struct kmemleak_object *object) { unsigned long flags; - write_lock_irqsave(&kmemleak_lock, flags); - rb_erase(&object->rb_node, &object_tree_root); - list_del_rcu(&object->object_list); - write_unlock_irqrestore(&kmemleak_lock, flags); - WARN_ON(!(object->flags & OBJECT_ALLOCATED)); - WARN_ON(atomic_read(&object->use_count) < 2); + WARN_ON(atomic_read(&object->use_count) < 1); /* * Locking here also ensures that the corresponding memory block @@ -631,7 +656,7 @@ static void delete_object_full(unsigned long ptr) { struct kmemleak_object *object; - object = find_and_get_object(ptr, 0); + object = find_and_remove_object(ptr, 0); if (!object) { #ifdef DEBUG kmemleak_warn("Freeing unknown object at 0x%08lx\n", @@ -640,7 +665,6 @@ static void delete_object_full(unsigned long ptr) return; } __delete_object(object); - put_object(object); } /* @@ -653,7 +677,7 @@ static void delete_object_part(unsigned long ptr, size_t size) struct kmemleak_object *object; unsigned long start, end; - object = find_and_get_object(ptr, 1); + object = find_and_remove_object(ptr, 1); if (!object) { #ifdef DEBUG kmemleak_warn("Partially freeing unknown object at 0x%08lx " @@ -661,7 +685,6 @@ static void delete_object_part(unsigned long ptr, size_t size) #endif return; } - __delete_object(object); /* * Create one or two objects that may result from the memory block @@ -679,7 +702,7 @@ static void delete_object_part(unsigned long ptr, size_t size) create_object(ptr + size, end - ptr - size, object->min_count, GFP_KERNEL); - put_object(object); + __delete_object(object); } static void __paint_it(struct kmemleak_object *object, int color) @@ -907,12 +930,13 @@ EXPORT_SYMBOL_GPL(kmemleak_alloc); * kmemleak_alloc_percpu - register a newly allocated __percpu object * @ptr: __percpu pointer to beginning of the object * @size: size of the object + * @gfp: flags used for kmemleak internal memory allocations * * This function is called from the kernel percpu allocator when a new object - * (memory block) is allocated (alloc_percpu). It assumes GFP_KERNEL - * allocation. + * (memory block) is allocated (alloc_percpu). */ -void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size) +void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, + gfp_t gfp) { unsigned int cpu; @@ -925,7 +949,7 @@ void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size) if (kmemleak_enabled && ptr && !IS_ERR(ptr)) for_each_possible_cpu(cpu) create_object((unsigned long)per_cpu_ptr(ptr, cpu), - size, 0, GFP_KERNEL); + size, 0, gfp); else if (kmemleak_early_log) log_early(KMEMLEAK_ALLOC_PERCPU, ptr, size, 0); } @@ -942,7 +966,7 @@ void __ref kmemleak_free(const void *ptr) { pr_debug("%s(0x%p)\n", __func__, ptr); - if (kmemleak_enabled && ptr && !IS_ERR(ptr)) + if (kmemleak_free_enabled && ptr && !IS_ERR(ptr)) delete_object_full((unsigned long)ptr); else if (kmemleak_early_log) log_early(KMEMLEAK_FREE, ptr, 0, 0); @@ -982,7 +1006,7 @@ void __ref kmemleak_free_percpu(const void __percpu *ptr) pr_debug("%s(0x%p)\n", __func__, ptr); - if (kmemleak_enabled && ptr && !IS_ERR(ptr)) + if (kmemleak_free_enabled && ptr && !IS_ERR(ptr)) for_each_possible_cpu(cpu) delete_object_full((unsigned long)per_cpu_ptr(ptr, cpu)); @@ -1148,19 +1172,18 @@ static int scan_should_stop(void) * found to the gray list. */ static void scan_block(void *_start, void *_end, - struct kmemleak_object *scanned, int allow_resched) + struct kmemleak_object *scanned) { unsigned long *ptr; unsigned long *start = PTR_ALIGN(_start, BYTES_PER_POINTER); unsigned long *end = _end - (BYTES_PER_POINTER - 1); + unsigned long flags; + read_lock_irqsave(&kmemleak_lock, flags); for (ptr = start; ptr < end; ptr++) { struct kmemleak_object *object; - unsigned long flags; unsigned long pointer; - if (allow_resched) - cond_resched(); if (scan_should_stop()) break; @@ -1173,26 +1196,31 @@ static void scan_block(void *_start, void *_end, pointer = *ptr; kasan_enable_current(); - object = find_and_get_object(pointer, 1); + if (pointer < min_addr || pointer >= max_addr) + continue; + + /* + * No need for get_object() here since we hold kmemleak_lock. + * object->use_count cannot be dropped to 0 while the object + * is still present in object_tree_root and object_list + * (with updates protected by kmemleak_lock). + */ + object = lookup_object(pointer, 1); if (!object) continue; - if (object == scanned) { + if (object == scanned) /* self referenced, ignore */ - put_object(object); continue; - } /* * Avoid the lockdep recursive warning on object->lock being * previously acquired in scan_object(). These locks are * enclosed by scan_mutex. */ - spin_lock_irqsave_nested(&object->lock, flags, - SINGLE_DEPTH_NESTING); + spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING); if (!color_white(object)) { /* non-orphan, ignored or new */ - spin_unlock_irqrestore(&object->lock, flags); - put_object(object); + spin_unlock(&object->lock); continue; } @@ -1204,13 +1232,27 @@ static void scan_block(void *_start, void *_end, */ object->count++; if (color_gray(object)) { + /* put_object() called when removing from gray_list */ + WARN_ON(!get_object(object)); list_add_tail(&object->gray_list, &gray_list); - spin_unlock_irqrestore(&object->lock, flags); - continue; } + spin_unlock(&object->lock); + } + read_unlock_irqrestore(&kmemleak_lock, flags); +} - spin_unlock_irqrestore(&object->lock, flags); - put_object(object); +/* + * Scan a large memory block in MAX_SCAN_SIZE chunks to reduce the latency. + */ +static void scan_large_block(void *start, void *end) +{ + void *next; + + while (start < end) { + next = min(start + MAX_SCAN_SIZE, end); + scan_block(start, next, NULL); + start = next; + cond_resched(); } } @@ -1236,22 +1278,25 @@ static void scan_object(struct kmemleak_object *object) if (hlist_empty(&object->area_list)) { void *start = (void *)object->pointer; void *end = (void *)(object->pointer + object->size); + void *next; - while (start < end && (object->flags & OBJECT_ALLOCATED) && - !(object->flags & OBJECT_NO_SCAN)) { - scan_block(start, min(start + MAX_SCAN_SIZE, end), - object, 0); - start += MAX_SCAN_SIZE; + do { + next = min(start + MAX_SCAN_SIZE, end); + scan_block(start, next, object); + + start = next; + if (start >= end) + break; spin_unlock_irqrestore(&object->lock, flags); cond_resched(); spin_lock_irqsave(&object->lock, flags); - } + } while (object->flags & OBJECT_ALLOCATED); } else hlist_for_each_entry(area, &object->area_list, node) scan_block((void *)area->start, (void *)(area->start + area->size), - object, 0); + object); out: spin_unlock_irqrestore(&object->lock, flags); } @@ -1328,14 +1373,14 @@ static void kmemleak_scan(void) rcu_read_unlock(); /* data/bss scanning */ - scan_block(_sdata, _edata, NULL, 1); - scan_block(__bss_start, __bss_stop, NULL, 1); + scan_large_block(_sdata, _edata); + scan_large_block(__bss_start, __bss_stop); #ifdef CONFIG_SMP /* per-cpu sections scanning */ for_each_possible_cpu(i) - scan_block(__per_cpu_start + per_cpu_offset(i), - __per_cpu_end + per_cpu_offset(i), NULL, 1); + scan_large_block(__per_cpu_start + per_cpu_offset(i), + __per_cpu_end + per_cpu_offset(i)); #endif /* @@ -1356,7 +1401,7 @@ static void kmemleak_scan(void) /* only scan if page is in use */ if (page_count(page) == 0) continue; - scan_block(page, page + 1, NULL, 1); + scan_block(page, page + 1, NULL); } } put_online_mems(); @@ -1370,7 +1415,7 @@ static void kmemleak_scan(void) read_lock(&tasklist_lock); do_each_thread(g, p) { scan_block(task_stack_page(p), task_stack_page(p) + - THREAD_SIZE, NULL, 0); + THREAD_SIZE, NULL); } while_each_thread(g, p); read_unlock(&tasklist_lock); } @@ -1747,15 +1792,20 @@ static void __kmemleak_do_cleanup(void) */ static void kmemleak_do_cleanup(struct work_struct *work) { - mutex_lock(&scan_mutex); stop_scan_thread(); + /* + * Once the scan thread has stopped, it is safe to no longer track + * object freeing. Ordering of the scan thread stopping and the memory + * accesses below is guaranteed by the kthread_stop() function. + */ + kmemleak_free_enabled = 0; + if (!kmemleak_found_leaks) __kmemleak_do_cleanup(); else pr_info("Kmemleak disabled without freeing internal data. " "Reclaim the memory with \"echo clear > /sys/kernel/debug/kmemleak\"\n"); - mutex_unlock(&scan_mutex); } static DECLARE_WORK(cleanup_work, kmemleak_do_cleanup); @@ -1776,6 +1826,8 @@ static void kmemleak_disable(void) /* check whether it is too early for a kernel thread */ if (kmemleak_initialized) schedule_work(&cleanup_work); + else + kmemleak_free_enabled = 0; pr_info("Kernel memory leak detector disabled\n"); } @@ -1840,8 +1892,10 @@ void __init kmemleak_init(void) if (kmemleak_error) { local_irq_restore(flags); return; - } else + } else { kmemleak_enabled = 1; + kmemleak_free_enabled = 1; + } local_irq_restore(flags); /* diff --git a/mm/madvise.c b/mm/madvise.c index d551475517bf..64bb8a22110c 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -17,6 +17,7 @@ #include <linux/fs.h> #include <linux/file.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/swap.h> #include <linux/swapops.h> diff --git a/mm/memblock.c b/mm/memblock.c index 9318b567ed79..87108e77e476 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -54,10 +54,16 @@ int memblock_debug __initdata_memblock; #ifdef CONFIG_MOVABLE_NODE bool movable_node_enabled __initdata_memblock = false; #endif +static bool system_has_some_mirror __initdata_memblock = false; static int memblock_can_resize __initdata_memblock; static int memblock_memory_in_slab __initdata_memblock = 0; static int memblock_reserved_in_slab __initdata_memblock = 0; +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) @@ -107,6 +113,7 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type, * @size: size of free area to find * @align: alignment of free area to find * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * @flags: pick from blocks based on memory attributes * * Utility called from memblock_find_in_range_node(), find free area bottom-up. * @@ -115,12 +122,13 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type, */ static phys_addr_t __init_memblock __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, - phys_addr_t size, phys_addr_t align, int nid) + phys_addr_t size, phys_addr_t align, int nid, + ulong flags) { phys_addr_t this_start, this_end, cand; u64 i; - for_each_free_mem_range(i, nid, &this_start, &this_end, NULL) { + for_each_free_mem_range(i, nid, flags, &this_start, &this_end, NULL) { this_start = clamp(this_start, start, end); this_end = clamp(this_end, start, end); @@ -139,6 +147,7 @@ __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, * @size: size of free area to find * @align: alignment of free area to find * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * @flags: pick from blocks based on memory attributes * * Utility called from memblock_find_in_range_node(), find free area top-down. * @@ -147,12 +156,14 @@ __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, */ static phys_addr_t __init_memblock __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, - phys_addr_t size, phys_addr_t align, int nid) + phys_addr_t size, phys_addr_t align, int nid, + ulong flags) { phys_addr_t this_start, this_end, cand; u64 i; - for_each_free_mem_range_reverse(i, nid, &this_start, &this_end, NULL) { + for_each_free_mem_range_reverse(i, nid, flags, &this_start, &this_end, + NULL) { this_start = clamp(this_start, start, end); this_end = clamp(this_end, start, end); @@ -174,6 +185,7 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * @flags: pick from blocks based on memory attributes * * Find @size free area aligned to @align in the specified range and node. * @@ -190,7 +202,7 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, */ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, phys_addr_t start, - phys_addr_t end, int nid) + phys_addr_t end, int nid, ulong flags) { phys_addr_t kernel_end, ret; @@ -215,7 +227,7 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, /* ok, try bottom-up allocation first */ ret = __memblock_find_range_bottom_up(bottom_up_start, end, - size, align, nid); + size, align, nid, flags); if (ret) return ret; @@ -233,7 +245,8 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, "memory hotunplug may be affected\n"); } - return __memblock_find_range_top_down(start, end, size, align, nid); + return __memblock_find_range_top_down(start, end, size, align, nid, + flags); } /** @@ -252,8 +265,21 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align) { - return memblock_find_in_range_node(size, align, start, end, - NUMA_NO_NODE); + phys_addr_t ret; + ulong flags = choose_memblock_flags(); + +again: + ret = memblock_find_in_range_node(size, align, start, end, + NUMA_NO_NODE, flags); + + if (!ret && (flags & MEMBLOCK_MIRROR)) { + pr_warn("Could not allocate %pap bytes of mirrored memory\n", + &size); + flags &= ~MEMBLOCK_MIRROR; + goto again; + } + + return ret; } static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r) @@ -779,9 +805,57 @@ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) } /** + * memblock_mark_mirror - Mark mirrored memory with flag MEMBLOCK_MIRROR. + * @base: the base phys addr of the region + * @size: the size of the region + * + * Return 0 on succees, -errno on failure. + */ +int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) +{ + system_has_some_mirror = true; + + return memblock_setclr_flag(base, size, 1, MEMBLOCK_MIRROR); +} + + +/** + * __next_reserved_mem_region - next function for for_each_reserved_region() + * @idx: pointer to u64 loop variable + * @out_start: ptr to phys_addr_t for start address of the region, can be %NULL + * @out_end: ptr to phys_addr_t for end address of the region, can be %NULL + * + * Iterate over all reserved memory regions. + */ +void __init_memblock __next_reserved_mem_region(u64 *idx, + phys_addr_t *out_start, + phys_addr_t *out_end) +{ + struct memblock_type *rsv = &memblock.reserved; + + if (*idx >= 0 && *idx < rsv->cnt) { + struct memblock_region *r = &rsv->regions[*idx]; + phys_addr_t base = r->base; + phys_addr_t size = r->size; + + if (out_start) + *out_start = base; + if (out_end) + *out_end = base + size - 1; + + *idx += 1; + return; + } + + /* signal end of iteration */ + *idx = ULLONG_MAX; +} + +/** * __next__mem_range - next function for for_each_free_mem_range() etc. * @idx: pointer to u64 loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes + * @flags: pick from blocks based on memory attributes * @type_a: pointer to memblock_type from where the range is taken * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL @@ -803,7 +877,7 @@ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) * As both region arrays are sorted, the function advances the two indices * in lockstep and returns each intersection. */ -void __init_memblock __next_mem_range(u64 *idx, int nid, +void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, @@ -831,6 +905,10 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, if (movable_node_is_enabled() && memblock_is_hotpluggable(m)) continue; + /* if we want mirror memory skip non-mirror memory regions */ + if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m)) + continue; + if (!type_b) { if (out_start) *out_start = m_start; @@ -895,6 +973,7 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, * * @idx: pointer to u64 loop variable * @nid: nid: node selector, %NUMA_NO_NODE for all nodes + * @flags: pick from blocks based on memory attributes * @type_a: pointer to memblock_type from where the range is taken * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL @@ -903,7 +982,7 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, * * Reverse of __next_mem_range(). */ -void __init_memblock __next_mem_range_rev(u64 *idx, int nid, +void __init_memblock __next_mem_range_rev(u64 *idx, int nid, ulong flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, @@ -935,6 +1014,10 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, if (movable_node_is_enabled() && memblock_is_hotpluggable(m)) continue; + /* if we want mirror memory skip non-mirror memory regions */ + if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m)) + continue; + if (!type_b) { if (out_start) *out_start = m_start; @@ -1050,14 +1133,15 @@ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, phys_addr_t align, phys_addr_t start, - phys_addr_t end, int nid) + phys_addr_t end, int nid, ulong flags) { phys_addr_t found; if (!align) align = SMP_CACHE_BYTES; - found = memblock_find_in_range_node(size, align, start, end, nid); + found = memblock_find_in_range_node(size, align, start, end, nid, + flags); if (found && !memblock_reserve(found, size)) { /* * The min_count is set to 0 so that memblock allocations are @@ -1070,26 +1154,40 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, } phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align, - phys_addr_t start, phys_addr_t end) + phys_addr_t start, phys_addr_t end, + ulong flags) { - return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE); + return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE, + flags); } static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr, - int nid) + int nid, ulong flags) { - return memblock_alloc_range_nid(size, align, 0, max_addr, nid); + return memblock_alloc_range_nid(size, align, 0, max_addr, nid, flags); } phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid) { - return memblock_alloc_base_nid(size, align, MEMBLOCK_ALLOC_ACCESSIBLE, nid); + ulong flags = choose_memblock_flags(); + phys_addr_t ret; + +again: + ret = memblock_alloc_base_nid(size, align, MEMBLOCK_ALLOC_ACCESSIBLE, + nid, flags); + + if (!ret && (flags & MEMBLOCK_MIRROR)) { + flags &= ~MEMBLOCK_MIRROR; + goto again; + } + return ret; } phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr) { - return memblock_alloc_base_nid(size, align, max_addr, NUMA_NO_NODE); + return memblock_alloc_base_nid(size, align, max_addr, NUMA_NO_NODE, + MEMBLOCK_NONE); } phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr) @@ -1153,6 +1251,7 @@ static void * __init memblock_virt_alloc_internal( { phys_addr_t alloc; void *ptr; + ulong flags = choose_memblock_flags(); if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) nid = NUMA_NO_NODE; @@ -1173,13 +1272,14 @@ static void * __init memblock_virt_alloc_internal( again: alloc = memblock_find_in_range_node(size, align, min_addr, max_addr, - nid); + nid, flags); if (alloc) goto done; if (nid != NUMA_NO_NODE) { alloc = memblock_find_in_range_node(size, align, min_addr, - max_addr, NUMA_NO_NODE); + max_addr, NUMA_NO_NODE, + flags); if (alloc) goto done; } @@ -1187,10 +1287,16 @@ again: if (min_addr) { min_addr = 0; goto again; - } else { - goto error; } + if (flags & MEMBLOCK_MIRROR) { + flags &= ~MEMBLOCK_MIRROR; + pr_warn("Could not allocate %pap bytes of mirrored memory\n", + &size); + goto again; + } + + return NULL; done: memblock_reserve(alloc, size); ptr = phys_to_virt(alloc); @@ -1205,9 +1311,6 @@ done: kmemleak_alloc(ptr, size, 0, 0); return ptr; - -error: - return NULL; } /** @@ -1316,7 +1419,7 @@ void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) end = PFN_DOWN(base + size); for (; cursor < end; cursor++) { - __free_pages_bootmem(pfn_to_page(cursor), 0); + __free_pages_bootmem(pfn_to_page(cursor), cursor, 0); totalram_pages++; } } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 14c2f2017e37..acb93c554f6e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -77,6 +77,7 @@ EXPORT_SYMBOL(memory_cgrp_subsys); #define MEM_CGROUP_RECLAIM_RETRIES 5 static struct mem_cgroup *root_mem_cgroup __read_mostly; +struct cgroup_subsys_state *mem_cgroup_root_css __read_mostly; /* Whether the swap controller is active */ #ifdef CONFIG_MEMCG_SWAP @@ -90,6 +91,7 @@ static const char * const mem_cgroup_stat_names[] = { "rss", "rss_huge", "mapped_file", + "dirty", "writeback", "swap", }; @@ -285,9 +287,9 @@ struct mem_cgroup { */ bool use_hierarchy; + /* protected by memcg_oom_lock */ bool oom_lock; - atomic_t under_oom; - atomic_t oom_wakeups; + int under_oom; int swappiness; /* OOM-Killer disable */ @@ -322,11 +324,6 @@ struct mem_cgroup { * percpu counter. */ struct mem_cgroup_stat_cpu __percpu *stat; - /* - * used when a cpu is offlined or other synchronizations - * See mem_cgroup_read_stat(). - */ - struct mem_cgroup_stat_cpu nocpu_base; spinlock_t pcp_counter_lock; #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) @@ -346,6 +343,11 @@ struct mem_cgroup { atomic_t numainfo_updating; #endif +#ifdef CONFIG_CGROUP_WRITEBACK + struct list_head cgwb_list; + struct wb_domain cgwb_domain; +#endif + /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; @@ -596,6 +598,39 @@ struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg) return &memcg->css; } +/** + * mem_cgroup_css_from_page - css of the memcg associated with a page + * @page: page of interest + * + * If memcg is bound to the default hierarchy, css of the memcg associated + * with @page is returned. The returned css remains associated with @page + * until it is released. + * + * If memcg is bound to a traditional hierarchy, the css of root_mem_cgroup + * is returned. + * + * XXX: The above description of behavior on the default hierarchy isn't + * strictly true yet as replace_page_cache_page() can modify the + * association before @page is released even on the default hierarchy; + * however, the current and planned usages don't mix the the two functions + * and replace_page_cache_page() will soon be updated to make the invariant + * actually true. + */ +struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page) +{ + struct mem_cgroup *memcg; + + rcu_read_lock(); + + memcg = page->mem_cgroup; + + if (!memcg || !cgroup_on_dfl(memcg->css.cgroup)) + memcg = root_mem_cgroup; + + rcu_read_unlock(); + return &memcg->css; +} + static struct mem_cgroup_per_zone * mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page) { @@ -795,15 +830,8 @@ static long mem_cgroup_read_stat(struct mem_cgroup *memcg, long val = 0; int cpu; - get_online_cpus(); - for_each_online_cpu(cpu) + for_each_possible_cpu(cpu) val += per_cpu(memcg->stat->count[idx], cpu); -#ifdef CONFIG_HOTPLUG_CPU - spin_lock(&memcg->pcp_counter_lock); - val += memcg->nocpu_base.count[idx]; - spin_unlock(&memcg->pcp_counter_lock); -#endif - put_online_cpus(); return val; } @@ -813,15 +841,8 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, unsigned long val = 0; int cpu; - get_online_cpus(); - for_each_online_cpu(cpu) + for_each_possible_cpu(cpu) val += per_cpu(memcg->stat->events[idx], cpu); -#ifdef CONFIG_HOTPLUG_CPU - spin_lock(&memcg->pcp_counter_lock); - val += memcg->nocpu_base.events[idx]; - spin_unlock(&memcg->pcp_counter_lock); -#endif - put_online_cpus(); return val; } @@ -1530,14 +1551,16 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, unsigned int points = 0; struct task_struct *chosen = NULL; + mutex_lock(&oom_lock); + /* * If current has a pending SIGKILL or is exiting, then automatically * select it. The goal is to allow it to allocate so that it may * quickly exit and free its memory. */ if (fatal_signal_pending(current) || task_will_free_mem(current)) { - mark_tsk_oom_victim(current); - return; + mark_oom_victim(current); + goto unlock; } check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL, memcg); @@ -1564,7 +1587,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, mem_cgroup_iter_break(memcg, iter); if (chosen) put_task_struct(chosen); - return; + goto unlock; case OOM_SCAN_OK: break; }; @@ -1585,11 +1608,13 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, css_task_iter_end(&it); } - if (!chosen) - return; - points = chosen_points * 1000 / totalpages; - oom_kill_process(chosen, gfp_mask, order, points, totalpages, memcg, - NULL, "Memory cgroup out of memory"); + if (chosen) { + points = chosen_points * 1000 / totalpages; + oom_kill_process(chosen, gfp_mask, order, points, totalpages, + memcg, NULL, "Memory cgroup out of memory"); + } +unlock: + mutex_unlock(&oom_lock); } #if MAX_NUMNODES > 1 @@ -1806,8 +1831,10 @@ static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg) { struct mem_cgroup *iter; + spin_lock(&memcg_oom_lock); for_each_mem_cgroup_tree(iter, memcg) - atomic_inc(&iter->under_oom); + iter->under_oom++; + spin_unlock(&memcg_oom_lock); } static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg) @@ -1816,11 +1843,13 @@ static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg) /* * When a new child is created while the hierarchy is under oom, - * mem_cgroup_oom_lock() may not be called. We have to use - * atomic_add_unless() here. + * mem_cgroup_oom_lock() may not be called. Watch for underflow. */ + spin_lock(&memcg_oom_lock); for_each_mem_cgroup_tree(iter, memcg) - atomic_add_unless(&iter->under_oom, -1, 0); + if (iter->under_oom > 0) + iter->under_oom--; + spin_unlock(&memcg_oom_lock); } static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq); @@ -1846,17 +1875,18 @@ static int memcg_oom_wake_function(wait_queue_t *wait, return autoremove_wake_function(wait, mode, sync, arg); } -static void memcg_wakeup_oom(struct mem_cgroup *memcg) -{ - atomic_inc(&memcg->oom_wakeups); - /* for filtering, pass "memcg" as argument. */ - __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg); -} - static void memcg_oom_recover(struct mem_cgroup *memcg) { - if (memcg && atomic_read(&memcg->under_oom)) - memcg_wakeup_oom(memcg); + /* + * For the following lockless ->under_oom test, the only required + * guarantee is that it must see the state asserted by an OOM when + * this function is called as a result of userland actions + * triggered by the notification of the OOM. This is trivially + * achieved by invoking mem_cgroup_mark_under_oom() before + * triggering notification. + */ + if (memcg && memcg->under_oom) + __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg); } static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order) @@ -2011,6 +2041,7 @@ again: return memcg; } +EXPORT_SYMBOL(mem_cgroup_begin_page_stat); /** * mem_cgroup_end_page_stat - finish a page state statistics transaction @@ -2029,6 +2060,7 @@ void mem_cgroup_end_page_stat(struct mem_cgroup *memcg) rcu_read_unlock(); } +EXPORT_SYMBOL(mem_cgroup_end_page_stat); /** * mem_cgroup_update_page_stat - update page state statistics @@ -2169,37 +2201,12 @@ static void drain_all_stock(struct mem_cgroup *root_memcg) mutex_unlock(&percpu_charge_mutex); } -/* - * This function drains percpu counter value from DEAD cpu and - * move it to local cpu. Note that this function can be preempted. - */ -static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *memcg, int cpu) -{ - int i; - - spin_lock(&memcg->pcp_counter_lock); - for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { - long x = per_cpu(memcg->stat->count[i], cpu); - - per_cpu(memcg->stat->count[i], cpu) = 0; - memcg->nocpu_base.count[i] += x; - } - for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) { - unsigned long x = per_cpu(memcg->stat->events[i], cpu); - - per_cpu(memcg->stat->events[i], cpu) = 0; - memcg->nocpu_base.events[i] += x; - } - spin_unlock(&memcg->pcp_counter_lock); -} - static int memcg_cpu_hotplug_callback(struct notifier_block *nb, unsigned long action, void *hcpu) { int cpu = (unsigned long)hcpu; struct memcg_stock_pcp *stock; - struct mem_cgroup *iter; if (action == CPU_ONLINE) return NOTIFY_OK; @@ -2207,9 +2214,6 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb, if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) return NOTIFY_OK; - for_each_mem_cgroup(iter) - mem_cgroup_drain_pcp_counter(iter, cpu); - stock = &per_cpu(memcg_stock, cpu); drain_stock(stock); return NOTIFY_OK; @@ -2323,6 +2327,8 @@ done_restock: css_get_many(&memcg->css, batch); if (batch > nr_pages) refill_stock(memcg, batch - nr_pages); + if (!(gfp_mask & __GFP_WAIT)) + goto done; /* * If the hierarchy is above the normal consumption range, * make the charging task trim their excess contribution. @@ -3862,7 +3868,7 @@ static int mem_cgroup_oom_register_event(struct mem_cgroup *memcg, list_add(&event->list, &memcg->oom_notify); /* already in OOM ? */ - if (atomic_read(&memcg->under_oom)) + if (memcg->under_oom) eventfd_signal(eventfd, 1); spin_unlock(&memcg_oom_lock); @@ -3891,7 +3897,7 @@ static int mem_cgroup_oom_control_read(struct seq_file *sf, void *v) struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(sf)); seq_printf(sf, "oom_kill_disable %d\n", memcg->oom_kill_disable); - seq_printf(sf, "under_oom %d\n", (bool)atomic_read(&memcg->under_oom)); + seq_printf(sf, "under_oom %d\n", (bool)memcg->under_oom); return 0; } @@ -3993,6 +3999,98 @@ static void memcg_destroy_kmem(struct mem_cgroup *memcg) } #endif +#ifdef CONFIG_CGROUP_WRITEBACK + +struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg) +{ + return &memcg->cgwb_list; +} + +static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp) +{ + return wb_domain_init(&memcg->cgwb_domain, gfp); +} + +static void memcg_wb_domain_exit(struct mem_cgroup *memcg) +{ + wb_domain_exit(&memcg->cgwb_domain); +} + +static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg) +{ + wb_domain_size_changed(&memcg->cgwb_domain); +} + +struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); + + if (!memcg->css.parent) + return NULL; + + return &memcg->cgwb_domain; +} + +/** + * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg + * @wb: bdi_writeback in question + * @pavail: out parameter for number of available pages + * @pdirty: out parameter for number of dirty pages + * @pwriteback: out parameter for number of pages under writeback + * + * Determine the numbers of available, dirty, and writeback pages in @wb's + * memcg. Dirty and writeback are self-explanatory. Available is a bit + * more involved. + * + * A memcg's headroom is "min(max, high) - used". The available memory is + * calculated as the lowest headroom of itself and the ancestors plus the + * number of pages already being used for file pages. Note that this + * doesn't consider the actual amount of available memory in the system. + * The caller should further cap *@pavail accordingly. + */ +void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pavail, + unsigned long *pdirty, unsigned long *pwriteback) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); + struct mem_cgroup *parent; + unsigned long head_room = PAGE_COUNTER_MAX; + unsigned long file_pages; + + *pdirty = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_DIRTY); + + /* this should eventually include NR_UNSTABLE_NFS */ + *pwriteback = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_WRITEBACK); + + file_pages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) | + (1 << LRU_ACTIVE_FILE)); + while ((parent = parent_mem_cgroup(memcg))) { + unsigned long ceiling = min(memcg->memory.limit, memcg->high); + unsigned long used = page_counter_read(&memcg->memory); + + head_room = min(head_room, ceiling - min(ceiling, used)); + memcg = parent; + } + + *pavail = file_pages + head_room; +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp) +{ + return 0; +} + +static void memcg_wb_domain_exit(struct mem_cgroup *memcg) +{ +} + +static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg) +{ +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + /* * DO NOT USE IN NEW FILES. * @@ -4377,9 +4475,15 @@ static struct mem_cgroup *mem_cgroup_alloc(void) memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu); if (!memcg->stat) goto out_free; + + if (memcg_wb_domain_init(memcg, GFP_KERNEL)) + goto out_free_stat; + spin_lock_init(&memcg->pcp_counter_lock); return memcg; +out_free_stat: + free_percpu(memcg->stat); out_free: kfree(memcg); return NULL; @@ -4406,6 +4510,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) free_mem_cgroup_per_zone_info(memcg, node); free_percpu(memcg->stat); + memcg_wb_domain_exit(memcg); kfree(memcg); } @@ -4438,6 +4543,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) /* root ? */ if (parent_css == NULL) { root_mem_cgroup = memcg; + mem_cgroup_root_css = &memcg->css; page_counter_init(&memcg->memory, NULL); memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; @@ -4456,7 +4562,9 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) #ifdef CONFIG_MEMCG_KMEM memcg->kmemcg_id = -1; #endif - +#ifdef CONFIG_CGROUP_WRITEBACK + INIT_LIST_HEAD(&memcg->cgwb_list); +#endif return &memcg->css; free_out: @@ -4544,6 +4652,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) vmpressure_cleanup(&memcg->vmpressure); memcg_deactivate_kmem(memcg); + + wb_memcg_offline(memcg); } static void mem_cgroup_css_free(struct cgroup_subsys_state *css) @@ -4577,6 +4687,7 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) memcg->low = 0; memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; + memcg_wb_domain_size_changed(memcg); } #ifdef CONFIG_MMU @@ -4746,6 +4857,7 @@ static int mem_cgroup_move_account(struct page *page, { unsigned long flags; int ret; + bool anon; VM_BUG_ON(from == to); VM_BUG_ON_PAGE(PageLRU(page), page); @@ -4771,15 +4883,33 @@ static int mem_cgroup_move_account(struct page *page, if (page->mem_cgroup != from) goto out_unlock; + anon = PageAnon(page); + spin_lock_irqsave(&from->move_lock, flags); - if (!PageAnon(page) && page_mapped(page)) { + 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); } + /* + * move_lock grabbed above and caller set from->moving_account, so + * mem_cgroup_update_page_stat() 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], + nr_pages); + __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_DIRTY], + nr_pages); + } + } + if (PageWriteback(page)) { __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_WRITEBACK], nr_pages); @@ -5295,6 +5425,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, memcg->high = high; + memcg_wb_domain_size_changed(memcg); return nbytes; } @@ -5327,6 +5458,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, if (err) return err; + memcg_wb_domain_size_changed(memcg); return nbytes; } @@ -5833,9 +5965,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) if (!mem_cgroup_is_root(memcg)) page_counter_uncharge(&memcg->memory, 1); - /* XXX: caller holds IRQ-safe mapping->tree_lock */ - VM_BUG_ON(!irqs_disabled()); - + /* Caller disabled preemption with mapping->tree_lock */ mem_cgroup_charge_statistics(memcg, page, -1); memcg_check_events(memcg, page); } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 501820c815b3..1f4446a90cef 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -20,6 +20,14 @@ * this code has to be extremely careful. Generally it tries to use * normal locking rules, as in get the standard locks, even if that means * the error handling takes potentially a long time. + * + * It can be very tempting to add handling for obscure cases here. + * In general any code for handling new cases should only be added iff: + * - You know how to test it. + * - You have a test that can be added to mce-test + * https://git.kernel.org/cgit/utils/cpu/mce/mce-test.git/ + * - The case actually shows up as a frequent (top 10) page state in + * tools/vm/page-types when running a real workload. * * There are several operations here with exponential complexity because * of unsuitable VM data structures. For example the operation to map back @@ -28,13 +36,6 @@ * are rare we hope to get away with this. This avoids impacting the core * VM. */ - -/* - * Notebook: - * - hugetlb needs more code - * - kcore/oldmem/vmcore/mem/kmem check for hwpoison pages - * - pass bad pages to kdump next kernel - */ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/page-flags.h> @@ -56,6 +57,7 @@ #include <linux/mm_inline.h> #include <linux/kfifo.h> #include "internal.h" +#include "ras/ras_event.h" int sysctl_memory_failure_early_kill __read_mostly = 0; @@ -503,68 +505,34 @@ static void collect_procs(struct page *page, struct list_head *tokill, kfree(tk); } -/* - * Error handlers for various types of pages. - */ - -enum outcome { - IGNORED, /* Error: cannot be handled */ - FAILED, /* Error: handling failed */ - DELAYED, /* Will be handled later */ - RECOVERED, /* Successfully recovered */ -}; - static const char *action_name[] = { - [IGNORED] = "Ignored", - [FAILED] = "Failed", - [DELAYED] = "Delayed", - [RECOVERED] = "Recovered", -}; - -enum action_page_type { - MSG_KERNEL, - MSG_KERNEL_HIGH_ORDER, - MSG_SLAB, - MSG_DIFFERENT_COMPOUND, - MSG_POISONED_HUGE, - MSG_HUGE, - MSG_FREE_HUGE, - MSG_UNMAP_FAILED, - MSG_DIRTY_SWAPCACHE, - MSG_CLEAN_SWAPCACHE, - MSG_DIRTY_MLOCKED_LRU, - MSG_CLEAN_MLOCKED_LRU, - MSG_DIRTY_UNEVICTABLE_LRU, - MSG_CLEAN_UNEVICTABLE_LRU, - MSG_DIRTY_LRU, - MSG_CLEAN_LRU, - MSG_TRUNCATED_LRU, - MSG_BUDDY, - MSG_BUDDY_2ND, - MSG_UNKNOWN, + [MF_IGNORED] = "Ignored", + [MF_FAILED] = "Failed", + [MF_DELAYED] = "Delayed", + [MF_RECOVERED] = "Recovered", }; static const char * const action_page_types[] = { - [MSG_KERNEL] = "reserved kernel page", - [MSG_KERNEL_HIGH_ORDER] = "high-order kernel page", - [MSG_SLAB] = "kernel slab page", - [MSG_DIFFERENT_COMPOUND] = "different compound page after locking", - [MSG_POISONED_HUGE] = "huge page already hardware poisoned", - [MSG_HUGE] = "huge page", - [MSG_FREE_HUGE] = "free huge page", - [MSG_UNMAP_FAILED] = "unmapping failed page", - [MSG_DIRTY_SWAPCACHE] = "dirty swapcache page", - [MSG_CLEAN_SWAPCACHE] = "clean swapcache page", - [MSG_DIRTY_MLOCKED_LRU] = "dirty mlocked LRU page", - [MSG_CLEAN_MLOCKED_LRU] = "clean mlocked LRU page", - [MSG_DIRTY_UNEVICTABLE_LRU] = "dirty unevictable LRU page", - [MSG_CLEAN_UNEVICTABLE_LRU] = "clean unevictable LRU page", - [MSG_DIRTY_LRU] = "dirty LRU page", - [MSG_CLEAN_LRU] = "clean LRU page", - [MSG_TRUNCATED_LRU] = "already truncated LRU page", - [MSG_BUDDY] = "free buddy page", - [MSG_BUDDY_2ND] = "free buddy page (2nd try)", - [MSG_UNKNOWN] = "unknown page", + [MF_MSG_KERNEL] = "reserved kernel page", + [MF_MSG_KERNEL_HIGH_ORDER] = "high-order kernel page", + [MF_MSG_SLAB] = "kernel slab page", + [MF_MSG_DIFFERENT_COMPOUND] = "different compound page after locking", + [MF_MSG_POISONED_HUGE] = "huge page already hardware poisoned", + [MF_MSG_HUGE] = "huge page", + [MF_MSG_FREE_HUGE] = "free huge page", + [MF_MSG_UNMAP_FAILED] = "unmapping failed page", + [MF_MSG_DIRTY_SWAPCACHE] = "dirty swapcache page", + [MF_MSG_CLEAN_SWAPCACHE] = "clean swapcache page", + [MF_MSG_DIRTY_MLOCKED_LRU] = "dirty mlocked LRU page", + [MF_MSG_CLEAN_MLOCKED_LRU] = "clean mlocked LRU page", + [MF_MSG_DIRTY_UNEVICTABLE_LRU] = "dirty unevictable LRU page", + [MF_MSG_CLEAN_UNEVICTABLE_LRU] = "clean unevictable LRU page", + [MF_MSG_DIRTY_LRU] = "dirty LRU page", + [MF_MSG_CLEAN_LRU] = "clean LRU page", + [MF_MSG_TRUNCATED_LRU] = "already truncated LRU page", + [MF_MSG_BUDDY] = "free buddy page", + [MF_MSG_BUDDY_2ND] = "free buddy page (2nd try)", + [MF_MSG_UNKNOWN] = "unknown page", }; /* @@ -598,7 +566,7 @@ static int delete_from_lru_cache(struct page *p) */ static int me_kernel(struct page *p, unsigned long pfn) { - return IGNORED; + return MF_IGNORED; } /* @@ -607,7 +575,7 @@ static int me_kernel(struct page *p, unsigned long pfn) static int me_unknown(struct page *p, unsigned long pfn) { printk(KERN_ERR "MCE %#lx: Unknown page state\n", pfn); - return FAILED; + return MF_FAILED; } /* @@ -616,7 +584,7 @@ static int me_unknown(struct page *p, unsigned long pfn) static int me_pagecache_clean(struct page *p, unsigned long pfn) { int err; - int ret = FAILED; + int ret = MF_FAILED; struct address_space *mapping; delete_from_lru_cache(p); @@ -626,7 +594,7 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * should be the one m_f() holds. */ if (PageAnon(p)) - return RECOVERED; + return MF_RECOVERED; /* * Now truncate the page in the page cache. This is really @@ -640,7 +608,7 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) /* * Page has been teared down in the meanwhile */ - return FAILED; + return MF_FAILED; } /* @@ -657,7 +625,7 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) !try_to_release_page(p, GFP_NOIO)) { pr_info("MCE %#lx: failed to release buffers\n", pfn); } else { - ret = RECOVERED; + ret = MF_RECOVERED; } } else { /* @@ -665,7 +633,7 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * This fails on dirty or anything with private pages */ if (invalidate_inode_page(p)) - ret = RECOVERED; + ret = MF_RECOVERED; else printk(KERN_INFO "MCE %#lx: Failed to invalidate\n", pfn); @@ -751,9 +719,9 @@ static int me_swapcache_dirty(struct page *p, unsigned long pfn) ClearPageUptodate(p); if (!delete_from_lru_cache(p)) - return DELAYED; + return MF_DELAYED; else - return FAILED; + return MF_FAILED; } static int me_swapcache_clean(struct page *p, unsigned long pfn) @@ -761,9 +729,9 @@ static int me_swapcache_clean(struct page *p, unsigned long pfn) delete_from_swap_cache(p); if (!delete_from_lru_cache(p)) - return RECOVERED; + return MF_RECOVERED; else - return FAILED; + return MF_FAILED; } /* @@ -776,6 +744,10 @@ static int me_huge_page(struct page *p, unsigned long pfn) { int res = 0; struct page *hpage = compound_head(p); + + if (!PageHuge(hpage)) + return MF_DELAYED; + /* * We can safely recover from error on free or reserved (i.e. * not in-use) hugepage by dequeuing it from freelist. @@ -789,9 +761,9 @@ static int me_huge_page(struct page *p, unsigned long pfn) if (!(page_mapping(hpage) || PageAnon(hpage))) { res = dequeue_hwpoisoned_huge_page(hpage); if (!res) - return RECOVERED; + return MF_RECOVERED; } - return DELAYED; + return MF_DELAYED; } /* @@ -823,10 +795,10 @@ static int me_huge_page(struct page *p, unsigned long pfn) static struct page_state { unsigned long mask; unsigned long res; - enum action_page_type type; + enum mf_action_page_type type; int (*action)(struct page *p, unsigned long pfn); } error_states[] = { - { reserved, reserved, MSG_KERNEL, me_kernel }, + { reserved, reserved, MF_MSG_KERNEL, me_kernel }, /* * free pages are specially detected outside this table: * PG_buddy pages only make a small fraction of all free pages. @@ -837,31 +809,31 @@ static struct page_state { * currently unused objects without touching them. But just * treat it as standard kernel for now. */ - { slab, slab, MSG_SLAB, me_kernel }, + { slab, slab, MF_MSG_SLAB, me_kernel }, #ifdef CONFIG_PAGEFLAGS_EXTENDED - { head, head, MSG_HUGE, me_huge_page }, - { tail, tail, MSG_HUGE, me_huge_page }, + { head, head, MF_MSG_HUGE, me_huge_page }, + { tail, tail, MF_MSG_HUGE, me_huge_page }, #else - { compound, compound, MSG_HUGE, me_huge_page }, + { compound, compound, MF_MSG_HUGE, me_huge_page }, #endif - { sc|dirty, sc|dirty, MSG_DIRTY_SWAPCACHE, me_swapcache_dirty }, - { sc|dirty, sc, MSG_CLEAN_SWAPCACHE, me_swapcache_clean }, + { sc|dirty, sc|dirty, MF_MSG_DIRTY_SWAPCACHE, me_swapcache_dirty }, + { sc|dirty, sc, MF_MSG_CLEAN_SWAPCACHE, me_swapcache_clean }, - { mlock|dirty, mlock|dirty, MSG_DIRTY_MLOCKED_LRU, me_pagecache_dirty }, - { mlock|dirty, mlock, MSG_CLEAN_MLOCKED_LRU, me_pagecache_clean }, + { mlock|dirty, mlock|dirty, MF_MSG_DIRTY_MLOCKED_LRU, me_pagecache_dirty }, + { mlock|dirty, mlock, MF_MSG_CLEAN_MLOCKED_LRU, me_pagecache_clean }, - { unevict|dirty, unevict|dirty, MSG_DIRTY_UNEVICTABLE_LRU, me_pagecache_dirty }, - { unevict|dirty, unevict, MSG_CLEAN_UNEVICTABLE_LRU, me_pagecache_clean }, + { unevict|dirty, unevict|dirty, MF_MSG_DIRTY_UNEVICTABLE_LRU, me_pagecache_dirty }, + { unevict|dirty, unevict, MF_MSG_CLEAN_UNEVICTABLE_LRU, me_pagecache_clean }, - { lru|dirty, lru|dirty, MSG_DIRTY_LRU, me_pagecache_dirty }, - { lru|dirty, lru, MSG_CLEAN_LRU, me_pagecache_clean }, + { lru|dirty, lru|dirty, MF_MSG_DIRTY_LRU, me_pagecache_dirty }, + { lru|dirty, lru, MF_MSG_CLEAN_LRU, me_pagecache_clean }, /* * Catchall entry: must be at end. */ - { 0, 0, MSG_UNKNOWN, me_unknown }, + { 0, 0, MF_MSG_UNKNOWN, me_unknown }, }; #undef dirty @@ -881,8 +853,11 @@ static struct page_state { * "Dirty/Clean" indication is not 100% accurate due to the possibility of * setting PG_dirty outside page lock. See also comment above set_page_dirty(). */ -static void action_result(unsigned long pfn, enum action_page_type type, int result) +static void action_result(unsigned long pfn, enum mf_action_page_type type, + enum mf_result result) { + trace_memory_failure_event(pfn, type, result); + pr_err("MCE %#lx: recovery action for %s: %s\n", pfn, action_page_types[type], action_name[result]); } @@ -896,13 +871,13 @@ static int page_action(struct page_state *ps, struct page *p, result = ps->action(p, pfn); count = page_count(p) - 1; - if (ps->action == me_swapcache_dirty && result == DELAYED) + if (ps->action == me_swapcache_dirty && result == MF_DELAYED) count--; if (count != 0) { printk(KERN_ERR "MCE %#lx: %s still referenced by %d users\n", pfn, action_page_types[ps->type], count); - result = FAILED; + result = MF_FAILED; } action_result(pfn, ps->type, result); @@ -911,9 +886,54 @@ static int page_action(struct page_state *ps, struct page *p, * Could adjust zone counters here to correct for the missing page. */ - return (result == RECOVERED || result == DELAYED) ? 0 : -EBUSY; + return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY; } +/** + * get_hwpoison_page() - Get refcount for memory error handling: + * @page: raw error page (hit by memory error) + * + * Return: return 0 if failed to grab the refcount, otherwise true (some + * non-zero value.) + */ +int get_hwpoison_page(struct page *page) +{ + struct page *head = compound_head(page); + + if (PageHuge(head)) + return get_page_unless_zero(head); + + /* + * Thp tail page has special refcounting rule (refcount of tail pages + * is stored in ->_mapcount,) so we can't call get_page_unless_zero() + * directly for tail pages. + */ + if (PageTransHuge(head)) { + /* + * Non anonymous thp exists only in allocation/free time. We + * can't handle such a case correctly, so let's give it up. + * This should be better than triggering BUG_ON when kernel + * tries to touch the "partially handled" page. + */ + if (!PageAnon(head)) { + pr_err("MCE: %#lx: non anonymous thp\n", + page_to_pfn(page)); + return 0; + } + + if (get_page_unless_zero(head)) { + if (PageTail(page)) + get_page(page); + return 1; + } else { + return 0; + } + } + + return get_page_unless_zero(page); +} +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. @@ -927,7 +947,6 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, int ret; int kill = 1, forcekill; struct page *hpage = *hpagep; - struct page *ppage; /* * Here we are interested only in user-mapped pages, so skip any @@ -977,59 +996,6 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, } /* - * ppage: poisoned page - * if p is regular page(4k page) - * ppage == real poisoned page; - * else p is hugetlb or THP, ppage == head page. - */ - ppage = hpage; - - if (PageTransHuge(hpage)) { - /* - * Verify that this isn't a hugetlbfs head page, the check for - * PageAnon is just for avoid tripping a split_huge_page - * internal debug check, as split_huge_page refuses to deal with - * anything that isn't an anon page. PageAnon can't go away fro - * under us because we hold a refcount on the hpage, without a - * refcount on the hpage. split_huge_page can't be safely called - * in the first place, having a refcount on the tail isn't - * enough * to be safe. - */ - if (!PageHuge(hpage) && PageAnon(hpage)) { - if (unlikely(split_huge_page(hpage))) { - /* - * FIXME: if splitting THP is failed, it is - * better to stop the following operation rather - * than causing panic by unmapping. System might - * survive if the page is freed later. - */ - printk(KERN_INFO - "MCE %#lx: failed to split THP\n", pfn); - - BUG_ON(!PageHWPoison(p)); - return SWAP_FAIL; - } - /* - * We pinned the head page for hwpoison handling, - * now we split the thp and we are interested in - * the hwpoisoned raw page, so move the refcount - * to it. Similarly, page lock is shifted. - */ - if (hpage != p) { - if (!(flags & MF_COUNT_INCREASED)) { - put_page(hpage); - get_page(p); - } - lock_page(p); - unlock_page(hpage); - *hpagep = p; - } - /* THP is split, so ppage should be the real poisoned page. */ - ppage = p; - } - } - - /* * First collect all the processes that have the page * mapped in dirty form. This has to be done before try_to_unmap, * because ttu takes the rmap data structures down. @@ -1038,12 +1004,12 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * there's nothing that can be done. */ if (kill) - collect_procs(ppage, &tokill, flags & MF_ACTION_REQUIRED); + collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED); - ret = try_to_unmap(ppage, ttu); + ret = try_to_unmap(hpage, ttu); if (ret != SWAP_SUCCESS) printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n", - pfn, page_mapcount(ppage)); + pfn, page_mapcount(hpage)); /* * Now that the dirty bit has been propagated to the @@ -1055,7 +1021,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * use a more force-full uncatchable kill to prevent * any accesses to the poisoned memory. */ - forcekill = PageDirty(ppage) || (flags & MF_MUST_KILL); + forcekill = PageDirty(hpage) || (flags & MF_MUST_KILL); kill_procs(&tokill, forcekill, trapno, ret != SWAP_SUCCESS, p, pfn, flags); @@ -1101,6 +1067,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) struct page_state *ps; struct page *p; struct page *hpage; + struct page *orig_head; int res; unsigned int nr_pages; unsigned long page_flags; @@ -1116,7 +1083,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) } p = pfn_to_page(pfn); - hpage = compound_head(p); + orig_head = hpage = compound_head(p); if (TestSetPageHWPoison(p)) { printk(KERN_ERR "MCE %#lx: already hardware poisoned\n", pfn); return 0; @@ -1149,10 +1116,9 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * In fact it's dangerous to directly bump up page count from 0, * that may make page_freeze_refs()/page_unfreeze_refs() mismatch. */ - if (!(flags & MF_COUNT_INCREASED) && - !get_page_unless_zero(hpage)) { + if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p)) { if (is_free_buddy_page(p)) { - action_result(pfn, MSG_BUDDY, DELAYED); + action_result(pfn, MF_MSG_BUDDY, MF_DELAYED); return 0; } else if (PageHuge(hpage)) { /* @@ -1169,14 +1135,31 @@ int memory_failure(unsigned long pfn, int trapno, int flags) } set_page_hwpoison_huge_page(hpage); res = dequeue_hwpoisoned_huge_page(hpage); - action_result(pfn, MSG_FREE_HUGE, - res ? IGNORED : DELAYED); + action_result(pfn, MF_MSG_FREE_HUGE, + res ? MF_IGNORED : MF_DELAYED); unlock_page(hpage); return res; } else { - action_result(pfn, MSG_KERNEL_HIGH_ORDER, IGNORED); + action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED); + return -EBUSY; + } + } + + if (!PageHuge(p) && PageTransHuge(hpage)) { + if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) { + if (!PageAnon(hpage)) + pr_err("MCE: %#lx: non anonymous thp\n", pfn); + else + pr_err("MCE: %#lx: thp split failed\n", pfn); + if (TestClearPageHWPoison(p)) + atomic_long_sub(nr_pages, &num_poisoned_pages); + put_page(p); + if (p != hpage) + put_page(hpage); return -EBUSY; } + VM_BUG_ON_PAGE(!page_count(p), p); + hpage = compound_head(p); } /* @@ -1188,18 +1171,18 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * walked by the page reclaim code, however that's not a big loss. */ if (!PageHuge(p)) { - if (!PageLRU(hpage)) - shake_page(hpage, 0); - if (!PageLRU(hpage)) { + 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, MSG_BUDDY, DELAYED); + action_result(pfn, MF_MSG_BUDDY, MF_DELAYED); else - action_result(pfn, MSG_BUDDY_2ND, - DELAYED); + action_result(pfn, MF_MSG_BUDDY_2ND, + MF_DELAYED); return 0; } } @@ -1211,8 +1194,8 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * The page could have changed compound pages during the locking. * If this happens just bail out. */ - if (compound_head(p) != hpage) { - action_result(pfn, MSG_DIFFERENT_COMPOUND, IGNORED); + if (PageCompound(p) && compound_head(p) != orig_head) { + action_result(pfn, MF_MSG_DIFFERENT_COMPOUND, MF_IGNORED); res = -EBUSY; goto out; } @@ -1232,9 +1215,9 @@ int memory_failure(unsigned long pfn, int trapno, int flags) if (!PageHWPoison(p)) { printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn); atomic_long_sub(nr_pages, &num_poisoned_pages); + unlock_page(hpage); put_page(hpage); - res = 0; - goto out; + return 0; } if (hwpoison_filter(p)) { if (TestClearPageHWPoison(p)) @@ -1252,7 +1235,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * on the head page to show that the hugepage is hwpoisoned */ if (PageHuge(p) && PageTail(p) && TestSetPageHWPoison(hpage)) { - action_result(pfn, MSG_POISONED_HUGE, IGNORED); + action_result(pfn, MF_MSG_POISONED_HUGE, MF_IGNORED); unlock_page(hpage); put_page(hpage); return 0; @@ -1281,7 +1264,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) */ if (hwpoison_user_mappings(p, pfn, trapno, flags, &hpage) != SWAP_SUCCESS) { - action_result(pfn, MSG_UNMAP_FAILED, IGNORED); + action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED); res = -EBUSY; goto out; } @@ -1290,7 +1273,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * Torn down by someone else? */ if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) { - action_result(pfn, MSG_TRUNCATED_LRU, IGNORED); + action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED); res = -EBUSY; goto out; } @@ -1450,12 +1433,12 @@ int unpoison_memory(unsigned long pfn) */ if (!PageHuge(page) && PageTransHuge(page)) { pr_info("MCE: Memory failure is now running on %#lx\n", pfn); - return 0; + return 0; } nr_pages = 1 << compound_order(page); - if (!get_page_unless_zero(page)) { + if (!get_hwpoison_page(p)) { /* * Since HWPoisoned hugepage should have non-zero refcount, * race between memory failure and unpoison seems to happen. @@ -1523,7 +1506,7 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags) * When the target page is a free hugepage, just remove it * from free hugepage list. */ - if (!get_page_unless_zero(compound_head(p))) { + if (!get_hwpoison_page(p)) { if (PageHuge(p)) { pr_info("%s: %#lx free huge page\n", __func__, pfn); ret = 0; @@ -1558,6 +1541,8 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags) */ ret = __get_any_page(page, pfn, 0); if (!PageLRU(page)) { + /* Drop page reference which is from __get_any_page() */ + put_page(page); pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", pfn, page->flags); return -EIO; @@ -1587,13 +1572,12 @@ static int soft_offline_huge_page(struct page *page, int flags) unlock_page(hpage); ret = isolate_huge_page(hpage, &pagelist); - if (ret) { - /* - * get_any_page() and isolate_huge_page() takes a refcount each, - * so need to drop one here. - */ - put_page(hpage); - } else { + /* + * get_any_page() and isolate_huge_page() takes a refcount each, + * so need to drop one here. + */ + put_page(hpage); + if (!ret) { pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn); return -EBUSY; } @@ -1679,6 +1663,8 @@ static int __soft_offline_page(struct page *page, int flags) inc_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); list_add(&page->lru, &pagelist); + if (!TestSetPageHWPoison(page)) + atomic_long_inc(&num_poisoned_pages); ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { @@ -1693,22 +1679,8 @@ static int __soft_offline_page(struct page *page, int flags) pfn, ret, page->flags); if (ret > 0) ret = -EIO; - } else { - /* - * After page migration succeeds, the source page can - * be trapped in pagevec and actual freeing is delayed. - * Freeing code works differently based on PG_hwpoison, - * so there's a race. We need to make sure that the - * source page should be freed back to buddy before - * setting PG_hwpoison. - */ - if (!is_free_buddy_page(page)) - drain_all_pages(page_zone(page)); - SetPageHWPoison(page); - if (!is_free_buddy_page(page)) - pr_info("soft offline: %#lx: page leaked\n", - pfn); - atomic_long_inc(&num_poisoned_pages); + if (TestClearPageHWPoison(page)) + atomic_long_dec(&num_poisoned_pages); } } else { pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n", @@ -1759,14 +1731,6 @@ int soft_offline_page(struct page *page, int flags) get_online_mems(); - /* - * Isolate the page, so that it doesn't get reallocated if it - * was free. This flag should be kept set until the source page - * is freed and PG_hwpoison on it is set. - */ - if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE) - set_migratetype_isolate(page, true); - ret = get_any_page(page, pfn, flags); put_online_mems(); if (ret > 0) { /* for in-use pages */ @@ -1785,6 +1749,5 @@ int soft_offline_page(struct page *page, int flags) atomic_long_inc(&num_poisoned_pages); } } - unset_migratetype_isolate(page, MIGRATE_MOVABLE); return ret; } diff --git a/mm/memory.c b/mm/memory.c index 22e037e3364e..388dcf9aa283 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2081,11 +2081,12 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, goto oom; cow_user_page(new_page, old_page, address, vma); } - __SetPageUptodate(new_page); if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg)) goto oom_free_new; + __SetPageUptodate(new_page); + mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); /* @@ -2669,6 +2670,10 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, pte_unmap(page_table); + /* File mapping without ->vm_ops ? */ + if (vma->vm_flags & VM_SHARED) + return VM_FAULT_SIGBUS; + /* Check if we need to add a guard page to the stack */ if (check_stack_guard_page(vma, address) < 0) return VM_FAULT_SIGSEGV; @@ -2689,6 +2694,10 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, page = alloc_zeroed_user_highpage_movable(vma, address); if (!page) goto oom; + + if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg)) + goto oom_free_page; + /* * The memory barrier inside __SetPageUptodate makes sure that * preceeding stores to the page contents become visible before @@ -2696,9 +2705,6 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, */ __SetPageUptodate(page); - if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg)) - goto oom_free_page; - entry = mk_pte(page, vma->vm_page_prot); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); @@ -3097,6 +3103,9 @@ static int do_fault(struct mm_struct *mm, struct vm_area_struct *vma, - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; pte_unmap(page_table); + /* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */ + if (!vma->vm_ops->fault) + return VM_FAULT_SIGBUS; if (!(flags & FAULT_FLAG_WRITE)) return do_read_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); @@ -3242,13 +3251,12 @@ static int handle_pte_fault(struct mm_struct *mm, barrier(); if (!pte_present(entry)) { if (pte_none(entry)) { - if (vma->vm_ops) { - if (likely(vma->vm_ops->fault)) - return do_fault(mm, vma, address, pte, - pmd, flags, entry); - } - return do_anonymous_page(mm, vma, address, - pte, pmd, flags); + if (vma->vm_ops) + return do_fault(mm, vma, address, pte, pmd, + flags, entry); + + return do_anonymous_page(mm, vma, address, pte, pmd, + flags); } return do_swap_page(mm, vma, address, pte, pmd, flags, entry); @@ -3724,7 +3732,7 @@ void print_vma_addr(char *prefix, unsigned long ip) if (buf) { char *p; - p = d_path(&f->f_path, buf, PAGE_SIZE); + p = file_path(f, buf, PAGE_SIZE); if (IS_ERR(p)) p = "?"; printk("%s%s[%lx+%lx]", prefix, kbasename(p), @@ -3737,7 +3745,7 @@ void print_vma_addr(char *prefix, unsigned long ip) } #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) -void might_fault(void) +void __might_fault(const char *file, int line) { /* * Some code (nfs/sunrpc) uses socket ops on kernel memory while @@ -3747,21 +3755,15 @@ void might_fault(void) */ if (segment_eq(get_fs(), KERNEL_DS)) return; - - /* - * it would be nicer only to annotate paths which are not under - * pagefault_disable, however that requires a larger audit and - * providing helpers like get_user_atomic. - */ - if (in_atomic()) + if (pagefault_disabled()) return; - - __might_sleep(__FILE__, __LINE__, 0); - + __might_sleep(file, line, 0); +#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) if (current->mm) might_lock_read(¤t->mm->mmap_sem); +#endif } -EXPORT_SYMBOL(might_fault); +EXPORT_SYMBOL(__might_fault); #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 457bde530cbe..6da82bcb0a8b 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -446,7 +446,7 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn) int nr_pages = PAGES_PER_SECTION; int nid = pgdat->node_id; int zone_type; - unsigned long flags; + unsigned long flags, pfn; int ret; zone_type = zone - pgdat->node_zones; @@ -461,6 +461,14 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn) pgdat_resize_unlock(zone->zone_pgdat, &flags); memmap_init_zone(nr_pages, nid, zone_type, phys_start_pfn, MEMMAP_HOTPLUG); + + /* online_page_range is called later and expects pages reserved */ + for (pfn = phys_start_pfn; pfn < phys_start_pfn + nr_pages; pfn++) { + if (!pfn_valid(pfn)) + continue; + + SetPageReserved(pfn_to_page(pfn)); + } return 0; } @@ -513,6 +521,7 @@ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn, break; err = 0; } + vmemmap_populate_print_last(); return err; } @@ -1268,6 +1277,7 @@ int __ref add_memory(int nid, u64 start, u64 size) /* create new memmap entry */ firmware_map_add_hotplug(start, start + size, "System RAM"); + memblock_add_node(start, size, nid); goto out; @@ -1969,8 +1979,10 @@ void try_offline_node(int nid) * wait_table may be allocated from boot memory, * here only free if it's allocated by vmalloc. */ - if (is_vmalloc_addr(zone->wait_table)) + if (is_vmalloc_addr(zone->wait_table)) { vfree(zone->wait_table); + zone->wait_table = NULL; + } } } EXPORT_SYMBOL(try_offline_node); @@ -2002,6 +2014,8 @@ void __ref remove_memory(int nid, u64 start, u64 size) /* remove memmap entry */ firmware_map_remove(start, start + size, "System RAM"); + memblock_free(start, size); + memblock_remove(start, size); arch_remove_memory(start, size); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 747743237d9f..99d4c1d0b858 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1972,35 +1972,41 @@ retry_cpuset: pol = get_vma_policy(vma, addr); cpuset_mems_cookie = read_mems_allowed_begin(); - if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage && - pol->mode != MPOL_INTERLEAVE)) { + if (pol->mode == MPOL_INTERLEAVE) { + unsigned nid; + + nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); + mpol_cond_put(pol); + page = alloc_page_interleave(gfp, order, nid); + goto out; + } + + if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) { + int hpage_node = node; + /* * For hugepage allocation and non-interleave policy which - * allows the current node, we only try to allocate from the - * current node and don't fall back to other nodes, as the - * cost of remote accesses would likely offset THP benefits. + * allows the current node (or other explicitly preferred + * node) we only try to allocate from the current/preferred + * node and don't fall back to other nodes, as the cost of + * remote accesses would likely offset THP benefits. * * If the policy is interleave, or does not allow the current * node in its nodemask, we allocate the standard way. */ + if (pol->mode == MPOL_PREFERRED && + !(pol->flags & MPOL_F_LOCAL)) + hpage_node = pol->v.preferred_node; + nmask = policy_nodemask(gfp, pol); - if (!nmask || node_isset(node, *nmask)) { + if (!nmask || node_isset(hpage_node, *nmask)) { mpol_cond_put(pol); - page = alloc_pages_exact_node(node, + page = alloc_pages_exact_node(hpage_node, gfp | __GFP_THISNODE, order); goto out; } } - if (pol->mode == MPOL_INTERLEAVE) { - unsigned nid; - - nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); - mpol_cond_put(pol); - page = alloc_page_interleave(gfp, order, nid); - goto out; - } - nmask = policy_nodemask(gfp, pol); zl = policy_zonelist(gfp, pol, node); mpol_cond_put(pol); diff --git a/mm/memtest.c b/mm/memtest.c index 1997d934b13b..0a1cc133f6d7 100644 --- a/mm/memtest.c +++ b/mm/memtest.c @@ -74,7 +74,8 @@ static void __init do_one_pass(u64 pattern, phys_addr_t start, phys_addr_t end) u64 i; phys_addr_t this_start, this_end; - for_each_free_mem_range(i, NUMA_NO_NODE, &this_start, &this_end, NULL) { + for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &this_start, + &this_end, NULL) { this_start = clamp(this_start, start, end); this_end = clamp(this_end, start, end); if (this_start < this_end) { diff --git a/mm/migrate.c b/mm/migrate.c index f53838fe3dfe..eb4267107d1f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -880,7 +880,8 @@ static int __unmap_and_move(struct page *page, struct page *newpage, /* Establish migration ptes or remove ptes */ if (page_mapped(page)) { try_to_unmap(page, - TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS); + TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS| + TTU_IGNORE_HWPOISON); page_was_mapped = 1; } @@ -918,7 +919,8 @@ out: static ICE_noinline int unmap_and_move(new_page_t get_new_page, free_page_t put_new_page, unsigned long private, struct page *page, - int force, enum migrate_mode mode) + int force, enum migrate_mode mode, + enum migrate_reason reason) { int rc = 0; int *result = NULL; @@ -949,7 +951,11 @@ out: list_del(&page->lru); dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); - putback_lru_page(page); + /* Soft-offlined page shouldn't go through lru cache list */ + if (reason == MR_MEMORY_FAILURE) + put_page(page); + else + putback_lru_page(page); } /* @@ -1122,7 +1128,8 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, pass > 2, mode); else rc = unmap_and_move(get_new_page, put_new_page, - private, page, pass > 2, mode); + private, page, pass > 2, mode, + reason); switch(rc) { case -ENOMEM: @@ -1796,7 +1803,7 @@ fail_putback: */ flush_cache_range(vma, mmun_start, mmun_end); page_add_anon_rmap(new_page, vma, mmun_start); - pmdp_clear_flush_notify(vma, mmun_start, pmd); + pmdp_huge_clear_flush_notify(vma, mmun_start, pmd); set_pmd_at(mm, mmun_start, pmd, entry); flush_tlb_range(vma, mmun_start, mmun_end); update_mmu_cache_pmd(vma, address, &entry); diff --git a/mm/mm_init.c b/mm/mm_init.c index 5f420f7fafa1..fdadf918de76 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -11,6 +11,7 @@ #include <linux/export.h> #include <linux/memory.h> #include <linux/notifier.h> +#include <linux/sched.h> #include "internal.h" #ifdef CONFIG_DEBUG_MEMORY_INIT @@ -130,14 +131,6 @@ void __init mminit_verify_pageflags_layout(void) BUG_ON(or_mask != add_mask); } -void __meminit mminit_verify_page_links(struct page *page, enum zone_type zone, - unsigned long nid, unsigned long pfn) -{ - BUG_ON(page_to_nid(page) != nid); - BUG_ON(page_zonenum(page) != zone); - BUG_ON(page_to_pfn(page) != pfn); -} - static __init int set_mminit_loglevel(char *str) { get_option(&str, &mminit_loglevel); diff --git a/mm/mmap.c b/mm/mmap.c index bb50cacc3ea5..aa632ade2be7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1258,6 +1258,9 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, *populate = 0; + if (!len) + return -EINVAL; + /* * Does the application expect PROT_READ to imply PROT_EXEC? * @@ -1268,9 +1271,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, if (!(file && (file->f_path.mnt->mnt_flags & MNT_NOEXEC))) prot |= PROT_EXEC; - if (!len) - return -EINVAL; - if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); diff --git a/mm/mprotect.c b/mm/mprotect.c index 88584838e704..e7d6f1171ecb 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -29,6 +29,8 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> +#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 @@ -322,6 +324,15 @@ success: change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable, 0); + /* + * Private VM_LOCKED VMA becoming writable: trigger COW to avoid major + * fault on access. + */ + if ((oldflags & (VM_WRITE | VM_SHARED | VM_LOCKED)) == VM_LOCKED && + (newflags & VM_WRITE)) { + populate_vma_page_range(vma, start, end, NULL); + } + vm_stat_account(mm, oldflags, vma->vm_file, -nrpages); vm_stat_account(mm, newflags, vma->vm_file, nrpages); perf_event_mmap(vma); diff --git a/mm/mremap.c b/mm/mremap.c index 034e2d360652..a7c93eceb1c8 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -22,6 +22,7 @@ #include <linux/mmu_notifier.h> #include <linux/sched/sysctl.h> #include <linux/uaccess.h> +#include <linux/mm-arch-hooks.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> @@ -286,13 +287,17 @@ static unsigned long move_vma(struct vm_area_struct *vma, old_len = new_len; old_addr = new_addr; new_addr = -ENOMEM; - } else if (vma->vm_file && vma->vm_file->f_op->mremap) { - err = vma->vm_file->f_op->mremap(vma->vm_file, new_vma); - if (err < 0) { - move_page_tables(new_vma, new_addr, vma, old_addr, - moved_len, true); - return err; + } else { + if (vma->vm_file && vma->vm_file->f_op->mremap) { + err = vma->vm_file->f_op->mremap(vma->vm_file, new_vma); + if (err < 0) { + move_page_tables(new_vma, new_addr, vma, + old_addr, moved_len, true); + return err; + } } + arch_remap(mm, old_addr, old_addr + old_len, + new_addr, new_addr + new_len); } /* Conceal VM_ACCOUNT so old reservation is not undone */ diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 90b50468333e..e57cf24babd6 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -37,11 +37,20 @@ static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, { void *ptr; u64 addr; + ulong flags = choose_memblock_flags(); if (limit > memblock.current_limit) limit = memblock.current_limit; - addr = memblock_find_in_range_node(size, align, goal, limit, nid); +again: + addr = memblock_find_in_range_node(size, align, goal, limit, nid, + flags); + if (!addr && (flags & MEMBLOCK_MIRROR)) { + flags &= ~MEMBLOCK_MIRROR; + pr_warn("Could not allocate %pap bytes of mirrored memory\n", + &size); + goto again; + } if (!addr) return NULL; @@ -77,7 +86,7 @@ void __init free_bootmem_late(unsigned long addr, unsigned long size) end = PFN_DOWN(addr + size); for (; cursor < end; cursor++) { - __free_pages_bootmem(pfn_to_page(cursor), 0); + __free_pages_bootmem(pfn_to_page(cursor), cursor, 0); totalram_pages++; } } @@ -92,7 +101,7 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end) while (start + (1UL << order) > end) order--; - __free_pages_bootmem(pfn_to_page(start), order); + __free_pages_bootmem(pfn_to_page(start), start, order); start += (1UL << order); } @@ -121,7 +130,11 @@ static unsigned long __init free_low_memory_core_early(void) memblock_clear_hotplug(0, -1); - for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL) + for_each_reserved_mem_region(i, &start, &end) + reserve_bootmem_region(start, end); + + for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, + NULL) count += __free_memory_core(start, end); #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK diff --git a/mm/nommu.c b/mm/nommu.c index e544508e2a4b..58ea3643b9e9 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -42,22 +42,6 @@ #include <asm/mmu_context.h> #include "internal.h" -#if 0 -#define kenter(FMT, ...) \ - printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__) -#define kleave(FMT, ...) \ - printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__) -#define kdebug(FMT, ...) \ - printk(KERN_DEBUG "xxx" FMT"yyy\n", ##__VA_ARGS__) -#else -#define kenter(FMT, ...) \ - no_printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__) -#define kleave(FMT, ...) \ - no_printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__) -#define kdebug(FMT, ...) \ - no_printk(KERN_DEBUG FMT"\n", ##__VA_ARGS__) -#endif - void *high_memory; EXPORT_SYMBOL(high_memory); struct page *mem_map; @@ -665,11 +649,7 @@ static void free_page_series(unsigned long from, unsigned long to) for (; from < to; from += PAGE_SIZE) { struct page *page = virt_to_page(from); - kdebug("- free %lx", from); atomic_long_dec(&mmap_pages_allocated); - if (page_count(page) != 1) - kdebug("free page %p: refcount not one: %d", - page, page_count(page)); put_page(page); } } @@ -683,8 +663,6 @@ static void free_page_series(unsigned long from, unsigned long to) static void __put_nommu_region(struct vm_region *region) __releases(nommu_region_sem) { - kenter("%p{%d}", region, region->vm_usage); - BUG_ON(!nommu_region_tree.rb_node); if (--region->vm_usage == 0) { @@ -697,10 +675,8 @@ static void __put_nommu_region(struct vm_region *region) /* IO memory and memory shared directly out of the pagecache * from ramfs/tmpfs mustn't be released here */ - if (region->vm_flags & VM_MAPPED_COPY) { - kdebug("free series"); + if (region->vm_flags & VM_MAPPED_COPY) free_page_series(region->vm_start, region->vm_top); - } kmem_cache_free(vm_region_jar, region); } else { up_write(&nommu_region_sem); @@ -744,8 +720,6 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) struct address_space *mapping; struct rb_node **p, *parent, *rb_prev; - kenter(",%p", vma); - BUG_ON(!vma->vm_region); mm->map_count++; @@ -813,8 +787,6 @@ static void delete_vma_from_mm(struct vm_area_struct *vma) struct mm_struct *mm = vma->vm_mm; struct task_struct *curr = current; - kenter("%p", vma); - protect_vma(vma, 0); mm->map_count--; @@ -854,7 +826,6 @@ static void delete_vma_from_mm(struct vm_area_struct *vma) */ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) { - kenter("%p", vma); if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); if (vma->vm_file) @@ -957,12 +928,8 @@ static int validate_mmap_request(struct file *file, int ret; /* do the simple checks first */ - if (flags & MAP_FIXED) { - printk(KERN_DEBUG - "%d: Can't do fixed-address/overlay mmap of RAM\n", - current->pid); + if (flags & MAP_FIXED) return -EINVAL; - } if ((flags & MAP_TYPE) != MAP_PRIVATE && (flags & MAP_TYPE) != MAP_SHARED) @@ -1060,8 +1027,7 @@ static int validate_mmap_request(struct file *file, ) { capabilities &= ~NOMMU_MAP_DIRECT; if (flags & MAP_SHARED) { - printk(KERN_WARNING - "MAP_SHARED not completely supported on !MMU\n"); + pr_warn("MAP_SHARED not completely supported on !MMU\n"); return -EINVAL; } } @@ -1205,16 +1171,12 @@ static int do_mmap_private(struct vm_area_struct *vma, * we're allocating is smaller than a page */ order = get_order(len); - kdebug("alloc order %d for %lx", order, len); - total = 1 << order; point = len >> PAGE_SHIFT; /* we don't want to allocate a power-of-2 sized page set */ - if (sysctl_nr_trim_pages && total - point >= sysctl_nr_trim_pages) { + if (sysctl_nr_trim_pages && total - point >= sysctl_nr_trim_pages) total = point; - kdebug("try to alloc exact %lu pages", total); - } base = alloc_pages_exact(total << PAGE_SHIFT, GFP_KERNEL); if (!base) @@ -1285,18 +1247,14 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long capabilities, vm_flags, result; int ret; - kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff); - *populate = 0; /* decide whether we should attempt the mapping, and if so what sort of * mapping */ ret = validate_mmap_request(file, addr, len, prot, flags, pgoff, &capabilities); - if (ret < 0) { - kleave(" = %d [val]", ret); + if (ret < 0) return ret; - } /* we ignore the address hint */ addr = 0; @@ -1383,11 +1341,9 @@ unsigned long do_mmap_pgoff(struct file *file, vma->vm_start = start; vma->vm_end = start + len; - if (pregion->vm_flags & VM_MAPPED_COPY) { - kdebug("share copy"); + if (pregion->vm_flags & VM_MAPPED_COPY) vma->vm_flags |= VM_MAPPED_COPY; - } else { - kdebug("share mmap"); + else { ret = do_mmap_shared_file(vma); if (ret < 0) { vma->vm_region = NULL; @@ -1467,7 +1423,6 @@ share: up_write(&nommu_region_sem); - kleave(" = %lx", result); return result; error_just_free: @@ -1479,27 +1434,24 @@ error: if (vma->vm_file) fput(vma->vm_file); kmem_cache_free(vm_area_cachep, vma); - kleave(" = %d", ret); return ret; sharing_violation: up_write(&nommu_region_sem); - printk(KERN_WARNING "Attempt to share mismatched mappings\n"); + pr_warn("Attempt to share mismatched mappings\n"); ret = -EINVAL; goto error; error_getting_vma: kmem_cache_free(vm_region_jar, region); - printk(KERN_WARNING "Allocation of vma for %lu byte allocation" - " from process %d failed\n", - len, current->pid); + pr_warn("Allocation of vma for %lu byte allocation from process %d failed\n", + len, current->pid); show_free_areas(0); return -ENOMEM; error_getting_region: - printk(KERN_WARNING "Allocation of vm region for %lu byte allocation" - " from process %d failed\n", - len, current->pid); + pr_warn("Allocation of vm region for %lu byte allocation from process %d failed\n", + len, current->pid); show_free_areas(0); return -ENOMEM; } @@ -1563,8 +1515,6 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_region *region; unsigned long npages; - kenter(""); - /* we're only permitted to split anonymous regions (these should have * only a single usage on the region) */ if (vma->vm_file) @@ -1628,8 +1578,6 @@ static int shrink_vma(struct mm_struct *mm, { struct vm_region *region; - kenter(""); - /* adjust the VMA's pointers, which may reposition it in the MM's tree * and list */ delete_vma_from_mm(vma); @@ -1669,8 +1617,6 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) unsigned long end; int ret; - kenter(",%lx,%zx", start, len); - len = PAGE_ALIGN(len); if (len == 0) return -EINVAL; @@ -1682,11 +1628,9 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) if (!vma) { static int limit; if (limit < 5) { - printk(KERN_WARNING - "munmap of memory not mmapped by process %d" - " (%s): 0x%lx-0x%lx\n", - current->pid, current->comm, - start, start + len - 1); + pr_warn("munmap of memory not mmapped by process %d (%s): 0x%lx-0x%lx\n", + current->pid, current->comm, + start, start + len - 1); limit++; } return -EINVAL; @@ -1695,38 +1639,27 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) /* we're allowed to split an anonymous VMA but not a file-backed one */ if (vma->vm_file) { do { - if (start > vma->vm_start) { - kleave(" = -EINVAL [miss]"); + if (start > vma->vm_start) return -EINVAL; - } if (end == vma->vm_end) goto erase_whole_vma; vma = vma->vm_next; } while (vma); - kleave(" = -EINVAL [split file]"); return -EINVAL; } else { /* the chunk must be a subset of the VMA found */ if (start == vma->vm_start && end == vma->vm_end) goto erase_whole_vma; - if (start < vma->vm_start || end > vma->vm_end) { - kleave(" = -EINVAL [superset]"); + if (start < vma->vm_start || end > vma->vm_end) return -EINVAL; - } - if (start & ~PAGE_MASK) { - kleave(" = -EINVAL [unaligned start]"); + if (start & ~PAGE_MASK) return -EINVAL; - } - if (end != vma->vm_end && end & ~PAGE_MASK) { - kleave(" = -EINVAL [unaligned split]"); + if (end != vma->vm_end && end & ~PAGE_MASK) return -EINVAL; - } if (start != vma->vm_start && end != vma->vm_end) { ret = split_vma(mm, vma, start, 1); - if (ret < 0) { - kleave(" = %d [split]", ret); + if (ret < 0) return ret; - } } return shrink_vma(mm, vma, start, end); } @@ -1734,7 +1667,6 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) erase_whole_vma: delete_vma_from_mm(vma); delete_vma(mm, vma); - kleave(" = 0"); return 0; } EXPORT_SYMBOL(do_munmap); @@ -1766,8 +1698,6 @@ void exit_mmap(struct mm_struct *mm) if (!mm) return; - kenter(""); - mm->total_vm = 0; while ((vma = mm->mmap)) { @@ -1776,8 +1706,6 @@ void exit_mmap(struct mm_struct *mm) delete_vma(mm, vma); cond_resched(); } - - kleave(""); } unsigned long vm_brk(unsigned long addr, unsigned long len) @@ -2157,7 +2085,7 @@ static int __meminit init_user_reserve(void) sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17); return 0; } -module_init(init_user_reserve) +subsys_initcall(init_user_reserve); /* * Initialise sysctl_admin_reserve_kbytes. @@ -2178,4 +2106,4 @@ static int __meminit init_admin_reserve(void) sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13); return 0; } -module_init(init_admin_reserve) +subsys_initcall(init_admin_reserve); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 2b665da1b3c9..dff991e0681e 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -42,7 +42,8 @@ int sysctl_panic_on_oom; int sysctl_oom_kill_allocating_task; int sysctl_oom_dump_tasks = 1; -static DEFINE_SPINLOCK(zone_scan_lock); + +DEFINE_MUTEX(oom_lock); #ifdef CONFIG_NUMA /** @@ -405,16 +406,15 @@ static atomic_t oom_victims = ATOMIC_INIT(0); static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait); bool oom_killer_disabled __read_mostly; -static DECLARE_RWSEM(oom_sem); /** - * mark_tsk_oom_victim - marks the given task as OOM victim. + * mark_oom_victim - mark the given task as OOM victim * @tsk: task to mark * - * Has to be called with oom_sem taken for read and never after + * Has to be called with oom_lock held and never after * oom has been disabled already. */ -void mark_tsk_oom_victim(struct task_struct *tsk) +void mark_oom_victim(struct task_struct *tsk) { WARN_ON(oom_killer_disabled); /* OOM killer might race with memcg OOM */ @@ -431,23 +431,14 @@ void mark_tsk_oom_victim(struct task_struct *tsk) } /** - * unmark_oom_victim - unmarks the current task as OOM victim. - * - * Wakes up all waiters in oom_killer_disable() + * exit_oom_victim - note the exit of an OOM victim */ -void unmark_oom_victim(void) +void exit_oom_victim(void) { - if (!test_and_clear_thread_flag(TIF_MEMDIE)) - return; + clear_thread_flag(TIF_MEMDIE); - down_read(&oom_sem); - /* - * There is no need to signal the lasst oom_victim if there - * is nobody who cares. - */ - if (!atomic_dec_return(&oom_victims) && oom_killer_disabled) + if (!atomic_dec_return(&oom_victims)) wake_up_all(&oom_victims_wait); - up_read(&oom_sem); } /** @@ -469,14 +460,14 @@ bool oom_killer_disable(void) * Make sure to not race with an ongoing OOM killer * and that the current is not the victim. */ - down_write(&oom_sem); + mutex_lock(&oom_lock); if (test_thread_flag(TIF_MEMDIE)) { - up_write(&oom_sem); + mutex_unlock(&oom_lock); return false; } oom_killer_disabled = true; - up_write(&oom_sem); + mutex_unlock(&oom_lock); wait_event(oom_victims_wait, !atomic_read(&oom_victims)); @@ -488,9 +479,7 @@ bool oom_killer_disable(void) */ void oom_killer_enable(void) { - down_write(&oom_sem); oom_killer_disabled = false; - up_write(&oom_sem); } #define K(x) ((x) << (PAGE_SHIFT-10)) @@ -517,7 +506,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, */ task_lock(p); if (p->mm && task_will_free_mem(p)) { - mark_tsk_oom_victim(p); + mark_oom_victim(p); task_unlock(p); put_task_struct(p); return; @@ -528,7 +517,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, dump_header(p, gfp_mask, order, memcg, nodemask); task_lock(p); - pr_err("%s: Kill process %d (%s) score %d or sacrifice child\n", + pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n", message, task_pid_nr(p), p->comm, points); task_unlock(p); @@ -572,7 +561,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, /* mm cannot safely be dereferenced after task_unlock(victim) */ mm = victim->mm; - mark_tsk_oom_victim(victim); + mark_oom_victim(victim); pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n", task_pid_nr(victim), victim->comm, K(victim->mm->total_vm), K(get_mm_counter(victim->mm, MM_ANONPAGES)), @@ -645,52 +634,6 @@ int unregister_oom_notifier(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(unregister_oom_notifier); -/* - * Try to acquire the OOM killer lock for the zones in zonelist. Returns zero - * if a parallel OOM killing is already taking place that includes a zone in - * the zonelist. Otherwise, locks all zones in the zonelist and returns 1. - */ -bool oom_zonelist_trylock(struct zonelist *zonelist, gfp_t gfp_mask) -{ - struct zoneref *z; - struct zone *zone; - bool ret = true; - - spin_lock(&zone_scan_lock); - for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) - if (test_bit(ZONE_OOM_LOCKED, &zone->flags)) { - ret = false; - goto out; - } - - /* - * Lock each zone in the zonelist under zone_scan_lock so a parallel - * call to oom_zonelist_trylock() doesn't succeed when it shouldn't. - */ - for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) - set_bit(ZONE_OOM_LOCKED, &zone->flags); - -out: - spin_unlock(&zone_scan_lock); - return ret; -} - -/* - * Clears the ZONE_OOM_LOCKED flag for all zones in the zonelist so that failed - * allocation attempts with zonelists containing them may now recall the OOM - * killer, if necessary. - */ -void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask) -{ - struct zoneref *z; - struct zone *zone; - - spin_lock(&zone_scan_lock); - for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) - clear_bit(ZONE_OOM_LOCKED, &zone->flags); - spin_unlock(&zone_scan_lock); -} - /** * __out_of_memory - kill the "best" process when we run out of memory * @zonelist: zonelist pointer @@ -704,8 +647,8 @@ void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask) * OR try to be smart about which process to kill. Note that we * don't have to be perfect here, we just have to be good. */ -static void __out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, - int order, nodemask_t *nodemask, bool force_kill) +bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, + int order, nodemask_t *nodemask, bool force_kill) { const nodemask_t *mpol_mask; struct task_struct *p; @@ -715,10 +658,13 @@ static void __out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, enum oom_constraint constraint = CONSTRAINT_NONE; int killed = 0; + if (oom_killer_disabled) + return false; + blocking_notifier_call_chain(&oom_notify_list, 0, &freed); if (freed > 0) /* Got some memory back in the last second. */ - return; + goto out; /* * If current has a pending SIGKILL or is exiting, then automatically @@ -730,8 +676,8 @@ static void __out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, */ if (current->mm && (fatal_signal_pending(current) || task_will_free_mem(current))) { - mark_tsk_oom_victim(current); - return; + mark_oom_victim(current); + goto out; } /* @@ -771,32 +717,8 @@ out: */ if (killed) schedule_timeout_killable(1); -} - -/** - * out_of_memory - tries to invoke OOM killer. - * @zonelist: zonelist pointer - * @gfp_mask: memory allocation flags - * @order: amount of memory being requested as a power of 2 - * @nodemask: nodemask passed to page allocator - * @force_kill: true if a task must be killed, even if others are exiting - * - * invokes __out_of_memory if the OOM is not disabled by oom_killer_disable() - * when it returns false. Otherwise returns true. - */ -bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, - int order, nodemask_t *nodemask, bool force_kill) -{ - bool ret = false; - - down_read(&oom_sem); - if (!oom_killer_disabled) { - __out_of_memory(zonelist, gfp_mask, order, nodemask, force_kill); - ret = true; - } - up_read(&oom_sem); - return ret; + return true; } /* @@ -806,27 +728,21 @@ bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, */ void pagefault_out_of_memory(void) { - struct zonelist *zonelist; - - down_read(&oom_sem); if (mem_cgroup_oom_synchronize(true)) - goto unlock; + return; - zonelist = node_zonelist(first_memory_node, GFP_KERNEL); - if (oom_zonelist_trylock(zonelist, GFP_KERNEL)) { - if (!oom_killer_disabled) - __out_of_memory(NULL, 0, 0, NULL, false); - else - /* - * There shouldn't be any user tasks runable while the - * OOM killer is disabled so the current task has to - * be a racing OOM victim for which oom_killer_disable() - * is waiting for. - */ - WARN_ON(test_thread_flag(TIF_MEMDIE)); + if (!mutex_trylock(&oom_lock)) + return; - oom_zonelist_unlock(zonelist, GFP_KERNEL); + if (!out_of_memory(NULL, 0, 0, NULL, false)) { + /* + * There shouldn't be any user tasks runnable while the + * OOM killer is disabled, so the current task has to + * be a racing OOM victim for which oom_killer_disable() + * is waiting for. + */ + WARN_ON(test_thread_flag(TIF_MEMDIE)); } -unlock: - up_read(&oom_sem); + + mutex_unlock(&oom_lock); } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index eb59f7eea508..5cccc127ef81 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -122,31 +122,31 @@ EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ -unsigned long global_dirty_limit; +struct wb_domain global_wb_domain; -/* - * Scale the writeback cache size proportional to the relative writeout speeds. - * - * We do this by keeping a floating proportion between BDIs, based on page - * writeback completions [end_page_writeback()]. Those devices that write out - * pages fastest will get the larger share, while the slower will get a smaller - * share. - * - * We use page writeout completions because we are interested in getting rid of - * dirty pages. Having them written out is the primary goal. - * - * We introduce a concept of time, a period over which we measure these events, - * because demand can/will vary over time. The length of this period itself is - * measured in page writeback completions. - * - */ -static struct fprop_global writeout_completions; +/* consolidated parameters for balance_dirty_pages() and its subroutines */ +struct dirty_throttle_control { +#ifdef CONFIG_CGROUP_WRITEBACK + struct wb_domain *dom; + struct dirty_throttle_control *gdtc; /* only set in memcg dtc's */ +#endif + struct bdi_writeback *wb; + struct fprop_local_percpu *wb_completions; -static void writeout_period(unsigned long t); -/* Timer for aging of writeout_completions */ -static struct timer_list writeout_period_timer = - TIMER_DEFERRED_INITIALIZER(writeout_period, 0, 0); -static unsigned long writeout_period_time = 0; + unsigned long avail; /* dirtyable */ + unsigned long dirty; /* file_dirty + write + nfs */ + unsigned long thresh; /* dirty threshold */ + unsigned long bg_thresh; /* dirty background threshold */ + + unsigned long wb_dirty; /* per-wb counterparts */ + unsigned long wb_thresh; + unsigned long wb_bg_thresh; + + unsigned long pos_ratio; +}; + +#define DTC_INIT_COMMON(__wb) .wb = (__wb), \ + .wb_completions = &(__wb)->completions /* * Length of period for aging writeout fractions of bdis. This is an @@ -155,6 +155,97 @@ static unsigned long writeout_period_time = 0; */ #define VM_COMPLETIONS_PERIOD_LEN (3*HZ) +#ifdef CONFIG_CGROUP_WRITEBACK + +#define GDTC_INIT(__wb) .dom = &global_wb_domain, \ + DTC_INIT_COMMON(__wb) +#define GDTC_INIT_NO_WB .dom = &global_wb_domain +#define MDTC_INIT(__wb, __gdtc) .dom = mem_cgroup_wb_domain(__wb), \ + .gdtc = __gdtc, \ + DTC_INIT_COMMON(__wb) + +static bool mdtc_valid(struct dirty_throttle_control *dtc) +{ + return dtc->dom; +} + +static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) +{ + return dtc->dom; +} + +static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) +{ + return mdtc->gdtc; +} + +static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) +{ + return &wb->memcg_completions; +} + +static void wb_min_max_ratio(struct bdi_writeback *wb, + unsigned long *minp, unsigned long *maxp) +{ + unsigned long this_bw = wb->avg_write_bandwidth; + unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); + unsigned long long min = wb->bdi->min_ratio; + unsigned long long max = wb->bdi->max_ratio; + + /* + * @wb may already be clean by the time control reaches here and + * the total may not include its bw. + */ + if (this_bw < tot_bw) { + if (min) { + min *= this_bw; + do_div(min, tot_bw); + } + if (max < 100) { + max *= this_bw; + do_div(max, tot_bw); + } + } + + *minp = min; + *maxp = max; +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +#define GDTC_INIT(__wb) DTC_INIT_COMMON(__wb) +#define GDTC_INIT_NO_WB +#define MDTC_INIT(__wb, __gdtc) + +static bool mdtc_valid(struct dirty_throttle_control *dtc) +{ + return false; +} + +static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) +{ + return &global_wb_domain; +} + +static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) +{ + return NULL; +} + +static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) +{ + return NULL; +} + +static void wb_min_max_ratio(struct bdi_writeback *wb, + unsigned long *minp, unsigned long *maxp) +{ + *minp = wb->bdi->min_ratio; + *maxp = wb->bdi->max_ratio; +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + /* * In a memory zone, there is a certain amount of pages we consider * available for the page cache, which is essentially the number of @@ -250,42 +341,88 @@ static unsigned long global_dirtyable_memory(void) return x + 1; /* Ensure that we never return 0 */ } -/* - * global_dirty_limits - background-writeback and dirty-throttling thresholds +/** + * domain_dirty_limits - calculate thresh and bg_thresh for a wb_domain + * @dtc: dirty_throttle_control of interest * - * Calculate the dirty thresholds based on sysctl parameters - * - vm.dirty_background_ratio or vm.dirty_background_bytes - * - vm.dirty_ratio or vm.dirty_bytes - * The dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and + * Calculate @dtc->thresh and ->bg_thresh considering + * vm_dirty_{bytes|ratio} and dirty_background_{bytes|ratio}. The caller + * must ensure that @dtc->avail is set before calling this function. The + * dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and * real-time tasks. */ -void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) +static void domain_dirty_limits(struct dirty_throttle_control *dtc) { - const unsigned long available_memory = global_dirtyable_memory(); - unsigned long background; - unsigned long dirty; + const unsigned long available_memory = dtc->avail; + struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc); + unsigned long bytes = vm_dirty_bytes; + unsigned long bg_bytes = dirty_background_bytes; + unsigned long ratio = vm_dirty_ratio; + unsigned long bg_ratio = dirty_background_ratio; + unsigned long thresh; + unsigned long bg_thresh; struct task_struct *tsk; - if (vm_dirty_bytes) - dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE); + /* gdtc is !NULL iff @dtc is for memcg domain */ + if (gdtc) { + unsigned long global_avail = gdtc->avail; + + /* + * The byte settings can't be applied directly to memcg + * domains. Convert them to ratios by scaling against + * globally available memory. + */ + if (bytes) + ratio = min(DIV_ROUND_UP(bytes, PAGE_SIZE) * 100 / + global_avail, 100UL); + if (bg_bytes) + bg_ratio = min(DIV_ROUND_UP(bg_bytes, PAGE_SIZE) * 100 / + global_avail, 100UL); + bytes = bg_bytes = 0; + } + + if (bytes) + thresh = DIV_ROUND_UP(bytes, PAGE_SIZE); else - dirty = (vm_dirty_ratio * available_memory) / 100; + thresh = (ratio * available_memory) / 100; - if (dirty_background_bytes) - background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE); + if (bg_bytes) + bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE); else - background = (dirty_background_ratio * available_memory) / 100; + bg_thresh = (bg_ratio * available_memory) / 100; - if (background >= dirty) - background = dirty / 2; + if (bg_thresh >= thresh) + bg_thresh = thresh / 2; tsk = current; if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) { - background += background / 4; - dirty += dirty / 4; + bg_thresh += bg_thresh / 4; + thresh += thresh / 4; } - *pbackground = background; - *pdirty = dirty; - trace_global_dirty_state(background, dirty); + dtc->thresh = thresh; + dtc->bg_thresh = bg_thresh; + + /* we should eventually report the domain in the TP */ + if (!gdtc) + trace_global_dirty_state(bg_thresh, thresh); +} + +/** + * global_dirty_limits - background-writeback and dirty-throttling thresholds + * @pbackground: out parameter for bg_thresh + * @pdirty: out parameter for thresh + * + * Calculate bg_thresh and thresh for global_wb_domain. See + * domain_dirty_limits() for details. + */ +void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) +{ + struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; + + gdtc.avail = global_dirtyable_memory(); + domain_dirty_limits(&gdtc); + + *pbackground = gdtc.bg_thresh; + *pdirty = gdtc.thresh; } /** @@ -392,47 +529,52 @@ static unsigned long wp_next_time(unsigned long cur_time) return cur_time; } -/* - * Increment the BDI's writeout completion count and the global writeout - * completion count. Called from test_clear_page_writeback(). - */ -static inline void __bdi_writeout_inc(struct backing_dev_info *bdi) +static void wb_domain_writeout_inc(struct wb_domain *dom, + struct fprop_local_percpu *completions, + unsigned int max_prop_frac) { - __inc_bdi_stat(bdi, BDI_WRITTEN); - __fprop_inc_percpu_max(&writeout_completions, &bdi->completions, - bdi->max_prop_frac); + __fprop_inc_percpu_max(&dom->completions, completions, + max_prop_frac); /* First event after period switching was turned off? */ - if (!unlikely(writeout_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 * timer will fire and what is in writeout_period_time will be * roughly the same. */ - writeout_period_time = wp_next_time(jiffies); - mod_timer(&writeout_period_timer, writeout_period_time); + dom->period_time = wp_next_time(jiffies); + mod_timer(&dom->period_timer, dom->period_time); } } -void bdi_writeout_inc(struct backing_dev_info *bdi) +/* + * Increment @wb's writeout completion count and the global writeout + * completion count. Called from test_clear_page_writeback(). + */ +static inline void __wb_writeout_inc(struct bdi_writeback *wb) { - unsigned long flags; + struct wb_domain *cgdom; - local_irq_save(flags); - __bdi_writeout_inc(bdi); - local_irq_restore(flags); + __inc_wb_stat(wb, WB_WRITTEN); + wb_domain_writeout_inc(&global_wb_domain, &wb->completions, + wb->bdi->max_prop_frac); + + cgdom = mem_cgroup_wb_domain(wb); + if (cgdom) + wb_domain_writeout_inc(cgdom, wb_memcg_completions(wb), + wb->bdi->max_prop_frac); } -EXPORT_SYMBOL_GPL(bdi_writeout_inc); -/* - * Obtain an accurate fraction of the BDI's portion. - */ -static void bdi_writeout_fraction(struct backing_dev_info *bdi, - long *numerator, long *denominator) +void wb_writeout_inc(struct bdi_writeback *wb) { - fprop_fraction_percpu(&writeout_completions, &bdi->completions, - numerator, denominator); + unsigned long flags; + + local_irq_save(flags); + __wb_writeout_inc(wb); + local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(wb_writeout_inc); /* * On idle system, we can be called long after we scheduled because we use @@ -440,22 +582,46 @@ static void bdi_writeout_fraction(struct backing_dev_info *bdi, */ static void writeout_period(unsigned long t) { - int miss_periods = (jiffies - writeout_period_time) / + struct wb_domain *dom = (void *)t; + int miss_periods = (jiffies - dom->period_time) / VM_COMPLETIONS_PERIOD_LEN; - if (fprop_new_period(&writeout_completions, miss_periods + 1)) { - writeout_period_time = wp_next_time(writeout_period_time + + if (fprop_new_period(&dom->completions, miss_periods + 1)) { + dom->period_time = wp_next_time(dom->period_time + miss_periods * VM_COMPLETIONS_PERIOD_LEN); - mod_timer(&writeout_period_timer, writeout_period_time); + mod_timer(&dom->period_timer, dom->period_time); } else { /* * Aging has zeroed all fractions. Stop wasting CPU on period * updates. */ - writeout_period_time = 0; + dom->period_time = 0; } } +int wb_domain_init(struct wb_domain *dom, gfp_t gfp) +{ + memset(dom, 0, sizeof(*dom)); + + spin_lock_init(&dom->lock); + + init_timer_deferrable(&dom->period_timer); + dom->period_timer.function = writeout_period; + dom->period_timer.data = (unsigned long)dom; + + dom->dirty_limit_tstamp = jiffies; + + return fprop_global_init(&dom->completions, gfp); +} + +#ifdef CONFIG_CGROUP_WRITEBACK +void wb_domain_exit(struct wb_domain *dom) +{ + del_timer_sync(&dom->period_timer); + fprop_global_destroy(&dom->completions); +} +#endif + /* * bdi_min_ratio keeps the sum of the minimum dirty shares of all * registered backing devices, which, for obvious reasons, can not @@ -510,17 +676,26 @@ static unsigned long dirty_freerun_ceiling(unsigned long thresh, return (thresh + bg_thresh) / 2; } -static unsigned long hard_dirty_limit(unsigned long thresh) +static unsigned long hard_dirty_limit(struct wb_domain *dom, + unsigned long thresh) { - return max(thresh, global_dirty_limit); + return max(thresh, dom->dirty_limit); +} + +/* memory available to a memcg domain is capped by system-wide clean memory */ +static void mdtc_cap_avail(struct dirty_throttle_control *mdtc) +{ + struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc); + unsigned long clean = gdtc->avail - min(gdtc->avail, gdtc->dirty); + + mdtc->avail = min(mdtc->avail, clean); } /** - * bdi_dirty_limit - @bdi's share of dirty throttling threshold - * @bdi: the backing_dev_info to query - * @dirty: global dirty limit in pages + * __wb_calc_thresh - @wb's share of dirty throttling threshold + * @dtc: dirty_throttle_context of interest * - * Returns @bdi's dirty limit in pages. The term "dirty" in the context of + * Returns @wb's dirty limit in pages. The term "dirty" in the context of * dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages. * * Note that balance_dirty_pages() will only seriously take it as a hard limit @@ -528,34 +703,47 @@ static unsigned long hard_dirty_limit(unsigned long thresh) * control. For example, when the device is completely stalled due to some error * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key. * In the other normal situations, it acts more gently by throttling the tasks - * more (rather than completely block them) when the bdi dirty pages go high. + * more (rather than completely block them) when the wb dirty pages go high. * * It allocates high/low dirty limits to fast/slow devices, in order to prevent * - starving fast devices * - piling up dirty pages (that will take long time to sync) on slow devices * - * The bdi's share of dirty limit will be adapting to its throughput and + * The wb's share of dirty limit will be adapting to its throughput and * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set. */ -unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty) +static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc) { - u64 bdi_dirty; + struct wb_domain *dom = dtc_dom(dtc); + unsigned long thresh = dtc->thresh; + u64 wb_thresh; long numerator, denominator; + unsigned long wb_min_ratio, wb_max_ratio; /* - * Calculate this BDI's share of the dirty ratio. + * Calculate this BDI's share of the thresh ratio. */ - bdi_writeout_fraction(bdi, &numerator, &denominator); + fprop_fraction_percpu(&dom->completions, dtc->wb_completions, + &numerator, &denominator); - bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100; - bdi_dirty *= numerator; - do_div(bdi_dirty, denominator); + wb_thresh = (thresh * (100 - bdi_min_ratio)) / 100; + wb_thresh *= numerator; + do_div(wb_thresh, denominator); - bdi_dirty += (dirty * bdi->min_ratio) / 100; - if (bdi_dirty > (dirty * bdi->max_ratio) / 100) - bdi_dirty = dirty * bdi->max_ratio / 100; + wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio); - return bdi_dirty; + wb_thresh += (thresh * wb_min_ratio) / 100; + if (wb_thresh > (thresh * wb_max_ratio) / 100) + wb_thresh = thresh * wb_max_ratio / 100; + + return wb_thresh; +} + +unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh) +{ + struct dirty_throttle_control gdtc = { GDTC_INIT(wb), + .thresh = thresh }; + return __wb_calc_thresh(&gdtc); } /* @@ -594,7 +782,7 @@ static long long pos_ratio_polynom(unsigned long setpoint, * * (o) global/bdi setpoints * - * We want the dirty pages be balanced around the global/bdi setpoints. + * We want the dirty pages be balanced around the global/wb setpoints. * When the number of dirty pages is higher/lower than the setpoint, the * dirty position control ratio (and hence task dirty ratelimit) will be * decreased/increased to bring the dirty pages back to the setpoint. @@ -604,8 +792,8 @@ static long long pos_ratio_polynom(unsigned long setpoint, * if (dirty < setpoint) scale up pos_ratio * if (dirty > setpoint) scale down pos_ratio * - * if (bdi_dirty < bdi_setpoint) scale up pos_ratio - * if (bdi_dirty > bdi_setpoint) scale down pos_ratio + * if (wb_dirty < wb_setpoint) scale up pos_ratio + * if (wb_dirty > wb_setpoint) scale down pos_ratio * * task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT * @@ -630,7 +818,7 @@ static long long pos_ratio_polynom(unsigned long setpoint, * 0 +------------.------------------.----------------------*-------------> * freerun^ setpoint^ limit^ dirty pages * - * (o) bdi control line + * (o) wb control line * * ^ pos_ratio * | @@ -656,33 +844,32 @@ static long long pos_ratio_polynom(unsigned long setpoint, * | . . * | . . * 0 +----------------------.-------------------------------.-------------> - * bdi_setpoint^ x_intercept^ + * wb_setpoint^ x_intercept^ * - * The bdi control line won't drop below pos_ratio=1/4, so that bdi_dirty can + * The wb control line won't drop below pos_ratio=1/4, so that wb_dirty can * be smoothly throttled down to normal if it starts high in situations like * - start writing to a slow SD card and a fast disk at the same time. The SD - * card's bdi_dirty may rush to many times higher than bdi_setpoint. - * - the bdi dirty thresh drops quickly due to change of JBOD workload + * card's wb_dirty may rush to many times higher than wb_setpoint. + * - the wb dirty thresh drops quickly due to change of JBOD workload */ -static unsigned long bdi_position_ratio(struct backing_dev_info *bdi, - unsigned long thresh, - unsigned long bg_thresh, - unsigned long dirty, - unsigned long bdi_thresh, - unsigned long bdi_dirty) -{ - unsigned long write_bw = bdi->avg_write_bandwidth; - unsigned long freerun = dirty_freerun_ceiling(thresh, bg_thresh); - unsigned long limit = hard_dirty_limit(thresh); +static void wb_position_ratio(struct dirty_throttle_control *dtc) +{ + struct bdi_writeback *wb = dtc->wb; + unsigned long write_bw = wb->avg_write_bandwidth; + unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); + unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); + unsigned long wb_thresh = dtc->wb_thresh; unsigned long x_intercept; unsigned long setpoint; /* dirty pages' target balance point */ - unsigned long bdi_setpoint; + unsigned long wb_setpoint; unsigned long span; long long pos_ratio; /* for scaling up/down the rate limit */ long x; - if (unlikely(dirty >= limit)) - return 0; + dtc->pos_ratio = 0; + + if (unlikely(dtc->dirty >= limit)) + return; /* * global setpoint @@ -690,165 +877,167 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi, * See comment for pos_ratio_polynom(). */ setpoint = (freerun + limit) / 2; - pos_ratio = pos_ratio_polynom(setpoint, dirty, limit); + pos_ratio = pos_ratio_polynom(setpoint, dtc->dirty, limit); /* * The strictlimit feature is a tool preventing mistrusted filesystems * from growing a large number of dirty pages before throttling. For - * such filesystems balance_dirty_pages always checks bdi counters - * against bdi limits. Even if global "nr_dirty" is under "freerun". + * such filesystems balance_dirty_pages always checks wb counters + * against wb limits. Even if global "nr_dirty" is under "freerun". * This is especially important for fuse which sets bdi->max_ratio to * 1% by default. Without strictlimit feature, fuse writeback may * consume arbitrary amount of RAM because it is accounted in * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty". * - * Here, in bdi_position_ratio(), we calculate pos_ratio based on - * two values: bdi_dirty and bdi_thresh. Let's consider an example: + * Here, in wb_position_ratio(), we calculate pos_ratio based on + * two values: wb_dirty and wb_thresh. Let's consider an example: * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global * limits are set by default to 10% and 20% (background and throttle). - * Then bdi_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. - * bdi_dirty_limit(bdi, bg_thresh) is about ~4K pages. bdi_setpoint is - * about ~6K pages (as the average of background and throttle bdi + * Then wb_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. + * wb_calc_thresh(wb, bg_thresh) is about ~4K pages. wb_setpoint is + * about ~6K pages (as the average of background and throttle wb * limits). The 3rd order polynomial will provide positive feedback if - * bdi_dirty is under bdi_setpoint and vice versa. + * wb_dirty is under wb_setpoint and vice versa. * * Note, that we cannot use global counters in these calculations - * because we want to throttle process writing to a strictlimit BDI + * because we want to throttle process writing to a strictlimit wb * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB * in the example above). */ - if (unlikely(bdi->capabilities & BDI_CAP_STRICTLIMIT)) { - long long bdi_pos_ratio; - unsigned long bdi_bg_thresh; + if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { + long long wb_pos_ratio; - if (bdi_dirty < 8) - return min_t(long long, pos_ratio * 2, - 2 << RATELIMIT_CALC_SHIFT); + if (dtc->wb_dirty < 8) { + dtc->pos_ratio = min_t(long long, pos_ratio * 2, + 2 << RATELIMIT_CALC_SHIFT); + return; + } - if (bdi_dirty >= bdi_thresh) - return 0; + if (dtc->wb_dirty >= wb_thresh) + return; - bdi_bg_thresh = div_u64((u64)bdi_thresh * bg_thresh, thresh); - bdi_setpoint = dirty_freerun_ceiling(bdi_thresh, - bdi_bg_thresh); + wb_setpoint = dirty_freerun_ceiling(wb_thresh, + dtc->wb_bg_thresh); - if (bdi_setpoint == 0 || bdi_setpoint == bdi_thresh) - return 0; + if (wb_setpoint == 0 || wb_setpoint == wb_thresh) + return; - bdi_pos_ratio = pos_ratio_polynom(bdi_setpoint, bdi_dirty, - bdi_thresh); + wb_pos_ratio = pos_ratio_polynom(wb_setpoint, dtc->wb_dirty, + wb_thresh); /* - * Typically, for strictlimit case, bdi_setpoint << setpoint - * and pos_ratio >> bdi_pos_ratio. In the other words global + * Typically, for strictlimit case, wb_setpoint << setpoint + * and pos_ratio >> wb_pos_ratio. In the other words global * state ("dirty") is not limiting factor and we have to - * make decision based on bdi counters. But there is an + * make decision based on wb counters. But there is an * important case when global pos_ratio should get precedence: * global limits are exceeded (e.g. due to activities on other - * BDIs) while given strictlimit BDI is below limit. + * wb's) while given strictlimit wb is below limit. * - * "pos_ratio * bdi_pos_ratio" would work for the case above, + * "pos_ratio * wb_pos_ratio" would work for the case above, * but it would look too non-natural for the case of all - * activity in the system coming from a single strictlimit BDI + * activity in the system coming from a single strictlimit wb * with bdi->max_ratio == 100%. * * Note that min() below somewhat changes the dynamics of the * control system. Normally, pos_ratio value can be well over 3 - * (when globally we are at freerun and bdi is well below bdi + * (when globally we are at freerun and wb is well below wb * setpoint). Now the maximum pos_ratio in the same situation * is 2. We might want to tweak this if we observe the control * system is too slow to adapt. */ - return min(pos_ratio, bdi_pos_ratio); + dtc->pos_ratio = min(pos_ratio, wb_pos_ratio); + return; } /* * We have computed basic pos_ratio above based on global situation. If - * the bdi is over/under its share of dirty pages, we want to scale + * the wb is over/under its share of dirty pages, we want to scale * pos_ratio further down/up. That is done by the following mechanism. */ /* - * bdi setpoint + * wb setpoint * - * f(bdi_dirty) := 1.0 + k * (bdi_dirty - bdi_setpoint) + * f(wb_dirty) := 1.0 + k * (wb_dirty - wb_setpoint) * - * x_intercept - bdi_dirty + * x_intercept - wb_dirty * := -------------------------- - * x_intercept - bdi_setpoint + * x_intercept - wb_setpoint * - * The main bdi control line is a linear function that subjects to + * The main wb control line is a linear function that subjects to * - * (1) f(bdi_setpoint) = 1.0 - * (2) k = - 1 / (8 * write_bw) (in single bdi case) - * or equally: x_intercept = bdi_setpoint + 8 * write_bw + * (1) f(wb_setpoint) = 1.0 + * (2) k = - 1 / (8 * write_bw) (in single wb case) + * or equally: x_intercept = wb_setpoint + 8 * write_bw * - * For single bdi case, the dirty pages are observed to fluctuate + * For single wb case, the dirty pages are observed to fluctuate * regularly within range - * [bdi_setpoint - write_bw/2, bdi_setpoint + write_bw/2] + * [wb_setpoint - write_bw/2, wb_setpoint + write_bw/2] * for various filesystems, where (2) can yield in a reasonable 12.5% * fluctuation range for pos_ratio. * - * For JBOD case, bdi_thresh (not bdi_dirty!) could fluctuate up to its + * For JBOD case, wb_thresh (not wb_dirty!) could fluctuate up to its * own size, so move the slope over accordingly and choose a slope that - * yields 100% pos_ratio fluctuation on suddenly doubled bdi_thresh. + * yields 100% pos_ratio fluctuation on suddenly doubled wb_thresh. */ - if (unlikely(bdi_thresh > thresh)) - bdi_thresh = thresh; + if (unlikely(wb_thresh > dtc->thresh)) + wb_thresh = dtc->thresh; /* - * It's very possible that bdi_thresh is close to 0 not because the + * It's very possible that wb_thresh is close to 0 not because the * device is slow, but that it has remained inactive for long time. * Honour such devices a reasonable good (hopefully IO efficient) * threshold, so that the occasional writes won't be blocked and active * writes can rampup the threshold quickly. */ - bdi_thresh = max(bdi_thresh, (limit - dirty) / 8); + wb_thresh = max(wb_thresh, (limit - dtc->dirty) / 8); /* - * scale global setpoint to bdi's: - * bdi_setpoint = setpoint * bdi_thresh / thresh + * scale global setpoint to wb's: + * wb_setpoint = setpoint * wb_thresh / thresh */ - x = div_u64((u64)bdi_thresh << 16, thresh | 1); - bdi_setpoint = setpoint * (u64)x >> 16; + x = div_u64((u64)wb_thresh << 16, dtc->thresh | 1); + wb_setpoint = setpoint * (u64)x >> 16; /* - * Use span=(8*write_bw) in single bdi case as indicated by - * (thresh - bdi_thresh ~= 0) and transit to bdi_thresh in JBOD case. + * Use span=(8*write_bw) in single wb case as indicated by + * (thresh - wb_thresh ~= 0) and transit to wb_thresh in JBOD case. * - * bdi_thresh thresh - bdi_thresh - * span = ---------- * (8 * write_bw) + ------------------- * bdi_thresh - * thresh thresh + * wb_thresh thresh - wb_thresh + * span = --------- * (8 * write_bw) + ------------------ * wb_thresh + * thresh thresh */ - span = (thresh - bdi_thresh + 8 * write_bw) * (u64)x >> 16; - x_intercept = bdi_setpoint + span; + span = (dtc->thresh - wb_thresh + 8 * write_bw) * (u64)x >> 16; + x_intercept = wb_setpoint + span; - if (bdi_dirty < x_intercept - span / 4) { - pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty), - (x_intercept - bdi_setpoint) | 1); + if (dtc->wb_dirty < x_intercept - span / 4) { + pos_ratio = div64_u64(pos_ratio * (x_intercept - dtc->wb_dirty), + (x_intercept - wb_setpoint) | 1); } else pos_ratio /= 4; /* - * bdi reserve area, safeguard against dirty pool underrun and disk idle + * wb reserve area, safeguard against dirty pool underrun and disk idle * It may push the desired control point of global dirty pages higher * than setpoint. */ - x_intercept = bdi_thresh / 2; - if (bdi_dirty < x_intercept) { - if (bdi_dirty > x_intercept / 8) - pos_ratio = div_u64(pos_ratio * x_intercept, bdi_dirty); + x_intercept = wb_thresh / 2; + if (dtc->wb_dirty < x_intercept) { + if (dtc->wb_dirty > x_intercept / 8) + pos_ratio = div_u64(pos_ratio * x_intercept, + dtc->wb_dirty); else pos_ratio *= 8; } - return pos_ratio; + dtc->pos_ratio = pos_ratio; } -static void bdi_update_write_bandwidth(struct backing_dev_info *bdi, - unsigned long elapsed, - unsigned long written) +static void wb_update_write_bandwidth(struct bdi_writeback *wb, + unsigned long elapsed, + unsigned long written) { const unsigned long period = roundup_pow_of_two(3 * HZ); - unsigned long avg = bdi->avg_write_bandwidth; - unsigned long old = bdi->write_bandwidth; + unsigned long avg = wb->avg_write_bandwidth; + unsigned long old = wb->write_bandwidth; u64 bw; /* @@ -861,14 +1050,14 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi, * @written may have decreased due to account_page_redirty(). * Avoid underflowing @bw calculation. */ - bw = written - min(written, bdi->written_stamp); + bw = written - min(written, wb->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { do_div(bw, elapsed); avg = bw; goto out; } - bw += (u64)bdi->write_bandwidth * (period - elapsed); + bw += (u64)wb->write_bandwidth * (period - elapsed); bw >>= ilog2(period); /* @@ -881,21 +1070,22 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi, avg += (old - avg) >> 3; out: - bdi->write_bandwidth = bw; - bdi->avg_write_bandwidth = avg; + /* keep avg > 0 to guarantee that tot > 0 if there are dirty wbs */ + avg = max(avg, 1LU); + if (wb_has_dirty_io(wb)) { + long delta = avg - wb->avg_write_bandwidth; + WARN_ON_ONCE(atomic_long_add_return(delta, + &wb->bdi->tot_write_bandwidth) <= 0); + } + wb->write_bandwidth = bw; + wb->avg_write_bandwidth = avg; } -/* - * The global dirtyable memory and dirty threshold could be suddenly knocked - * down by a large amount (eg. on the startup of KVM in a swapless system). - * This may throw the system into deep dirty exceeded state and throttle - * heavy/light dirtiers alike. To retain good responsiveness, maintain - * global_dirty_limit for tracking slowly down to the knocked down dirty - * threshold. - */ -static void update_dirty_limit(unsigned long thresh, unsigned long dirty) +static void update_dirty_limit(struct dirty_throttle_control *dtc) { - unsigned long limit = global_dirty_limit; + struct wb_domain *dom = dtc_dom(dtc); + unsigned long thresh = dtc->thresh; + unsigned long limit = dom->dirty_limit; /* * Follow up in one step. @@ -908,63 +1098,57 @@ static void update_dirty_limit(unsigned long thresh, unsigned long dirty) /* * Follow down slowly. Use the higher one as the target, because thresh * may drop below dirty. This is exactly the reason to introduce - * global_dirty_limit which is guaranteed to lie above the dirty pages. + * dom->dirty_limit which is guaranteed to lie above the dirty pages. */ - thresh = max(thresh, dirty); + thresh = max(thresh, dtc->dirty); if (limit > thresh) { limit -= (limit - thresh) >> 5; goto update; } return; update: - global_dirty_limit = limit; + dom->dirty_limit = limit; } -static void global_update_bandwidth(unsigned long thresh, - unsigned long dirty, +static void domain_update_bandwidth(struct dirty_throttle_control *dtc, unsigned long now) { - static DEFINE_SPINLOCK(dirty_lock); - static unsigned long update_time = INITIAL_JIFFIES; + struct wb_domain *dom = dtc_dom(dtc); /* * check locklessly first to optimize away locking for the most time */ - if (time_before(now, update_time + BANDWIDTH_INTERVAL)) + if (time_before(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) return; - spin_lock(&dirty_lock); - if (time_after_eq(now, update_time + BANDWIDTH_INTERVAL)) { - update_dirty_limit(thresh, dirty); - update_time = now; + spin_lock(&dom->lock); + if (time_after_eq(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) { + update_dirty_limit(dtc); + dom->dirty_limit_tstamp = now; } - spin_unlock(&dirty_lock); + spin_unlock(&dom->lock); } /* - * Maintain bdi->dirty_ratelimit, the base dirty throttle rate. + * Maintain wb->dirty_ratelimit, the base dirty throttle rate. * - * Normal bdi tasks will be curbed at or below it in long term. + * Normal wb tasks will be curbed at or below it in long term. * Obviously it should be around (write_bw / N) when there are N dd tasks. */ -static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi, - unsigned long thresh, - unsigned long bg_thresh, - unsigned long dirty, - unsigned long bdi_thresh, - unsigned long bdi_dirty, - unsigned long dirtied, - unsigned long elapsed) -{ - unsigned long freerun = dirty_freerun_ceiling(thresh, bg_thresh); - unsigned long limit = hard_dirty_limit(thresh); +static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, + unsigned long dirtied, + unsigned long elapsed) +{ + struct bdi_writeback *wb = dtc->wb; + unsigned long dirty = dtc->dirty; + unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); + unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long setpoint = (freerun + limit) / 2; - unsigned long write_bw = bdi->avg_write_bandwidth; - unsigned long dirty_ratelimit = bdi->dirty_ratelimit; + unsigned long write_bw = wb->avg_write_bandwidth; + unsigned long dirty_ratelimit = wb->dirty_ratelimit; unsigned long dirty_rate; unsigned long task_ratelimit; unsigned long balanced_dirty_ratelimit; - unsigned long pos_ratio; unsigned long step; unsigned long x; @@ -972,20 +1156,18 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi, * The dirty rate will match the writeout rate in long term, except * when dirty pages are truncated by userspace or re-dirtied by FS. */ - dirty_rate = (dirtied - bdi->dirtied_stamp) * HZ / elapsed; + dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed; - pos_ratio = bdi_position_ratio(bdi, thresh, bg_thresh, dirty, - bdi_thresh, bdi_dirty); /* * task_ratelimit reflects each dd's dirty rate for the past 200ms. */ task_ratelimit = (u64)dirty_ratelimit * - pos_ratio >> RATELIMIT_CALC_SHIFT; + dtc->pos_ratio >> RATELIMIT_CALC_SHIFT; task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */ /* * A linear estimation of the "balanced" throttle rate. The theory is, - * if there are N dd tasks, each throttled at task_ratelimit, the bdi's + * if there are N dd tasks, each throttled at task_ratelimit, the wb's * dirty_rate will be measured to be (N * task_ratelimit). So the below * formula will yield the balanced rate limit (write_bw / N). * @@ -1024,7 +1206,7 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi, /* * We could safely do this and return immediately: * - * bdi->dirty_ratelimit = balanced_dirty_ratelimit; + * wb->dirty_ratelimit = balanced_dirty_ratelimit; * * However to get a more stable dirty_ratelimit, the below elaborated * code makes use of task_ratelimit to filter out singular points and @@ -1058,32 +1240,31 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi, step = 0; /* - * For strictlimit case, calculations above were based on bdi counters - * and limits (starting from pos_ratio = bdi_position_ratio() and up to + * For strictlimit case, calculations above were based on wb counters + * and limits (starting from pos_ratio = wb_position_ratio() and up to * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate). - * Hence, to calculate "step" properly, we have to use bdi_dirty as - * "dirty" and bdi_setpoint as "setpoint". + * Hence, to calculate "step" properly, we have to use wb_dirty as + * "dirty" and wb_setpoint as "setpoint". * - * We rampup dirty_ratelimit forcibly if bdi_dirty is low because - * it's possible that bdi_thresh is close to zero due to inactivity - * of backing device (see the implementation of bdi_dirty_limit()). + * We rampup dirty_ratelimit forcibly if wb_dirty is low because + * it's possible that wb_thresh is close to zero due to inactivity + * of backing device. */ - if (unlikely(bdi->capabilities & BDI_CAP_STRICTLIMIT)) { - dirty = bdi_dirty; - if (bdi_dirty < 8) - setpoint = bdi_dirty + 1; + if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { + dirty = dtc->wb_dirty; + if (dtc->wb_dirty < 8) + setpoint = dtc->wb_dirty + 1; else - setpoint = (bdi_thresh + - bdi_dirty_limit(bdi, bg_thresh)) / 2; + setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2; } if (dirty < setpoint) { - x = min3(bdi->balanced_dirty_ratelimit, + x = min3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit < x) step = x - dirty_ratelimit; } else { - x = max3(bdi->balanced_dirty_ratelimit, + x = max3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit > x) step = dirty_ratelimit - x; @@ -1105,69 +1286,67 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi, else dirty_ratelimit -= step; - bdi->dirty_ratelimit = max(dirty_ratelimit, 1UL); - bdi->balanced_dirty_ratelimit = balanced_dirty_ratelimit; + wb->dirty_ratelimit = max(dirty_ratelimit, 1UL); + wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit; - trace_bdi_dirty_ratelimit(bdi, dirty_rate, task_ratelimit); + trace_bdi_dirty_ratelimit(wb->bdi, dirty_rate, task_ratelimit); } -void __bdi_update_bandwidth(struct backing_dev_info *bdi, - unsigned long thresh, - unsigned long bg_thresh, - unsigned long dirty, - unsigned long bdi_thresh, - unsigned long bdi_dirty, - unsigned long start_time) +static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, + struct dirty_throttle_control *mdtc, + unsigned long start_time, + bool update_ratelimit) { + struct bdi_writeback *wb = gdtc->wb; unsigned long now = jiffies; - unsigned long elapsed = now - bdi->bw_time_stamp; + unsigned long elapsed = now - wb->bw_time_stamp; unsigned long dirtied; unsigned long written; + lockdep_assert_held(&wb->list_lock); + /* * rate-limit, only update once every 200ms. */ if (elapsed < BANDWIDTH_INTERVAL) return; - dirtied = percpu_counter_read(&bdi->bdi_stat[BDI_DIRTIED]); - written = percpu_counter_read(&bdi->bdi_stat[BDI_WRITTEN]); + dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]); + written = percpu_counter_read(&wb->stat[WB_WRITTEN]); /* * Skip quiet periods when disk bandwidth is under-utilized. * (at least 1s idle time between two flusher runs) */ - if (elapsed > HZ && time_before(bdi->bw_time_stamp, start_time)) + if (elapsed > HZ && time_before(wb->bw_time_stamp, start_time)) goto snapshot; - if (thresh) { - global_update_bandwidth(thresh, dirty, now); - bdi_update_dirty_ratelimit(bdi, thresh, bg_thresh, dirty, - bdi_thresh, bdi_dirty, - dirtied, elapsed); + if (update_ratelimit) { + domain_update_bandwidth(gdtc, now); + wb_update_dirty_ratelimit(gdtc, dirtied, elapsed); + + /* + * @mdtc is always NULL if !CGROUP_WRITEBACK but the + * compiler has no way to figure that out. Help it. + */ + if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) { + domain_update_bandwidth(mdtc, now); + wb_update_dirty_ratelimit(mdtc, dirtied, elapsed); + } } - bdi_update_write_bandwidth(bdi, elapsed, written); + wb_update_write_bandwidth(wb, elapsed, written); snapshot: - bdi->dirtied_stamp = dirtied; - bdi->written_stamp = written; - bdi->bw_time_stamp = now; + wb->dirtied_stamp = dirtied; + wb->written_stamp = written; + wb->bw_time_stamp = now; } -static void bdi_update_bandwidth(struct backing_dev_info *bdi, - unsigned long thresh, - unsigned long bg_thresh, - unsigned long dirty, - unsigned long bdi_thresh, - unsigned long bdi_dirty, - unsigned long start_time) +void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time) { - if (time_is_after_eq_jiffies(bdi->bw_time_stamp + BANDWIDTH_INTERVAL)) - return; - spin_lock(&bdi->wb.list_lock); - __bdi_update_bandwidth(bdi, thresh, bg_thresh, dirty, - bdi_thresh, bdi_dirty, start_time); - spin_unlock(&bdi->wb.list_lock); + struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; + + __wb_update_bandwidth(&gdtc, NULL, start_time, false); } /* @@ -1187,10 +1366,10 @@ static unsigned long dirty_poll_interval(unsigned long dirty, return 1; } -static unsigned long bdi_max_pause(struct backing_dev_info *bdi, - unsigned long bdi_dirty) +static unsigned long wb_max_pause(struct bdi_writeback *wb, + unsigned long wb_dirty) { - unsigned long bw = bdi->avg_write_bandwidth; + unsigned long bw = wb->avg_write_bandwidth; unsigned long t; /* @@ -1200,20 +1379,20 @@ static unsigned long bdi_max_pause(struct backing_dev_info *bdi, * * 8 serves as the safety ratio. */ - t = bdi_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); + t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); t++; return min_t(unsigned long, t, MAX_PAUSE); } -static long bdi_min_pause(struct backing_dev_info *bdi, - long max_pause, - unsigned long task_ratelimit, - unsigned long dirty_ratelimit, - int *nr_dirtied_pause) +static long wb_min_pause(struct bdi_writeback *wb, + long max_pause, + unsigned long task_ratelimit, + unsigned long dirty_ratelimit, + int *nr_dirtied_pause) { - long hi = ilog2(bdi->avg_write_bandwidth); - long lo = ilog2(bdi->dirty_ratelimit); + long hi = ilog2(wb->avg_write_bandwidth); + long lo = ilog2(wb->dirty_ratelimit); long t; /* target pause */ long pause; /* estimated next pause */ int pages; /* target nr_dirtied_pause */ @@ -1281,34 +1460,27 @@ static long bdi_min_pause(struct backing_dev_info *bdi, return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t; } -static inline void bdi_dirty_limits(struct backing_dev_info *bdi, - unsigned long dirty_thresh, - unsigned long background_thresh, - unsigned long *bdi_dirty, - unsigned long *bdi_thresh, - unsigned long *bdi_bg_thresh) +static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) { - unsigned long bdi_reclaimable; + struct bdi_writeback *wb = dtc->wb; + unsigned long wb_reclaimable; /* - * bdi_thresh is not treated as some limiting factor as + * wb_thresh is not treated as some limiting factor as * dirty_thresh, due to reasons - * - in JBOD setup, bdi_thresh can fluctuate a lot + * - in JBOD setup, wb_thresh can fluctuate a lot * - in a system with HDD and USB key, the USB key may somehow - * go into state (bdi_dirty >> bdi_thresh) either because - * bdi_dirty starts high, or because bdi_thresh drops low. + * go into state (wb_dirty >> wb_thresh) either because + * wb_dirty starts high, or because wb_thresh drops low. * In this case we don't want to hard throttle the USB key - * dirtiers for 100 seconds until bdi_dirty drops under - * bdi_thresh. Instead the auxiliary bdi control line in - * bdi_position_ratio() will let the dirtier task progress - * at some rate <= (write_bw / 2) for bringing down bdi_dirty. + * dirtiers for 100 seconds until wb_dirty drops under + * wb_thresh. Instead the auxiliary wb control line in + * wb_position_ratio() will let the dirtier task progress + * at some rate <= (write_bw / 2) for bringing down wb_dirty. */ - *bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); - - if (bdi_bg_thresh) - *bdi_bg_thresh = dirty_thresh ? div_u64((u64)*bdi_thresh * - background_thresh, - dirty_thresh) : 0; + dtc->wb_thresh = __wb_calc_thresh(dtc); + dtc->wb_bg_thresh = dtc->thresh ? + div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need @@ -1320,14 +1492,12 @@ static inline void bdi_dirty_limits(struct backing_dev_info *bdi, * actually dirty; with m+n sitting in the percpu * deltas. */ - if (*bdi_thresh < 2 * bdi_stat_error(bdi)) { - bdi_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE); - *bdi_dirty = bdi_reclaimable + - bdi_stat_sum(bdi, BDI_WRITEBACK); + if (dtc->wb_thresh < 2 * wb_stat_error(wb)) { + wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); + dtc->wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK); } else { - bdi_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); - *bdi_dirty = bdi_reclaimable + - bdi_stat(bdi, BDI_WRITEBACK); + wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE); + dtc->wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK); } } @@ -1339,12 +1509,16 @@ static inline void bdi_dirty_limits(struct backing_dev_info *bdi, * perform some writeout. */ static void balance_dirty_pages(struct address_space *mapping, + struct bdi_writeback *wb, unsigned long pages_dirtied) { + struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; + struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; + struct dirty_throttle_control * const gdtc = &gdtc_stor; + struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? + &mdtc_stor : NULL; + struct dirty_throttle_control *sdtc; unsigned long nr_reclaimable; /* = file_dirty + unstable_nfs */ - unsigned long nr_dirty; /* = file_dirty + writeback + unstable_nfs */ - unsigned long background_thresh; - unsigned long dirty_thresh; long period; long pause; long max_pause; @@ -1353,18 +1527,14 @@ static void balance_dirty_pages(struct address_space *mapping, bool dirty_exceeded = false; unsigned long task_ratelimit; unsigned long dirty_ratelimit; - unsigned long pos_ratio; - struct backing_dev_info *bdi = inode_to_bdi(mapping->host); + struct backing_dev_info *bdi = wb->bdi; bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; unsigned long start_time = jiffies; for (;;) { unsigned long now = jiffies; - unsigned long uninitialized_var(bdi_thresh); - unsigned long thresh; - unsigned long uninitialized_var(bdi_dirty); - unsigned long dirty; - unsigned long bg_thresh; + unsigned long dirty, thresh, bg_thresh; + unsigned long m_dirty, m_thresh, m_bg_thresh; /* * Unstable writes are a feature of certain networked @@ -1374,65 +1544,127 @@ static void balance_dirty_pages(struct address_space *mapping, */ nr_reclaimable = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS); - nr_dirty = nr_reclaimable + global_page_state(NR_WRITEBACK); + gdtc->avail = global_dirtyable_memory(); + gdtc->dirty = nr_reclaimable + global_page_state(NR_WRITEBACK); - global_dirty_limits(&background_thresh, &dirty_thresh); + domain_dirty_limits(gdtc); if (unlikely(strictlimit)) { - bdi_dirty_limits(bdi, dirty_thresh, background_thresh, - &bdi_dirty, &bdi_thresh, &bg_thresh); + wb_dirty_limits(gdtc); - dirty = bdi_dirty; - thresh = bdi_thresh; + dirty = gdtc->wb_dirty; + thresh = gdtc->wb_thresh; + bg_thresh = gdtc->wb_bg_thresh; } else { - dirty = nr_dirty; - thresh = dirty_thresh; - bg_thresh = background_thresh; + dirty = gdtc->dirty; + thresh = gdtc->thresh; + bg_thresh = gdtc->bg_thresh; + } + + if (mdtc) { + unsigned long writeback; + + /* + * If @wb belongs to !root memcg, repeat the same + * basic calculations for the memcg domain. + */ + mem_cgroup_wb_stats(wb, &mdtc->avail, &mdtc->dirty, + &writeback); + mdtc_cap_avail(mdtc); + mdtc->dirty += writeback; + + domain_dirty_limits(mdtc); + + if (unlikely(strictlimit)) { + wb_dirty_limits(mdtc); + m_dirty = mdtc->wb_dirty; + m_thresh = mdtc->wb_thresh; + m_bg_thresh = mdtc->wb_bg_thresh; + } else { + m_dirty = mdtc->dirty; + m_thresh = mdtc->thresh; + m_bg_thresh = mdtc->bg_thresh; + } } /* * Throttle it only when the background writeback cannot * catch-up. This avoids (excessively) small writeouts - * when the bdi limits are ramping up in case of !strictlimit. + * when the wb limits are ramping up in case of !strictlimit. * - * In strictlimit case make decision based on the bdi counters - * and limits. Small writeouts when the bdi limits are ramping + * In strictlimit case make decision based on the wb counters + * and limits. Small writeouts when the wb limits are ramping * up are the price we consciously pay for strictlimit-ing. + * + * If memcg domain is in effect, @dirty should be under + * both global and memcg freerun ceilings. */ - if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh)) { + if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh) && + (!mdtc || + m_dirty <= dirty_freerun_ceiling(m_thresh, m_bg_thresh))) { + unsigned long intv = dirty_poll_interval(dirty, thresh); + unsigned long m_intv = ULONG_MAX; + current->dirty_paused_when = now; current->nr_dirtied = 0; - current->nr_dirtied_pause = - dirty_poll_interval(dirty, thresh); + if (mdtc) + m_intv = dirty_poll_interval(m_dirty, m_thresh); + current->nr_dirtied_pause = min(intv, m_intv); break; } - if (unlikely(!writeback_in_progress(bdi))) - bdi_start_background_writeback(bdi); + if (unlikely(!writeback_in_progress(wb))) + wb_start_background_writeback(wb); + /* + * Calculate global domain's pos_ratio and select the + * global dtc by default. + */ if (!strictlimit) - bdi_dirty_limits(bdi, dirty_thresh, background_thresh, - &bdi_dirty, &bdi_thresh, NULL); - - dirty_exceeded = (bdi_dirty > bdi_thresh) && - ((nr_dirty > dirty_thresh) || strictlimit); - if (dirty_exceeded && !bdi->dirty_exceeded) - bdi->dirty_exceeded = 1; - - bdi_update_bandwidth(bdi, dirty_thresh, background_thresh, - nr_dirty, bdi_thresh, bdi_dirty, - start_time); - - dirty_ratelimit = bdi->dirty_ratelimit; - pos_ratio = bdi_position_ratio(bdi, dirty_thresh, - background_thresh, nr_dirty, - bdi_thresh, bdi_dirty); - task_ratelimit = ((u64)dirty_ratelimit * pos_ratio) >> + wb_dirty_limits(gdtc); + + dirty_exceeded = (gdtc->wb_dirty > gdtc->wb_thresh) && + ((gdtc->dirty > gdtc->thresh) || strictlimit); + + wb_position_ratio(gdtc); + sdtc = gdtc; + + if (mdtc) { + /* + * If memcg domain is in effect, calculate its + * pos_ratio. @wb should satisfy constraints from + * both global and memcg domains. Choose the one + * w/ lower pos_ratio. + */ + if (!strictlimit) + wb_dirty_limits(mdtc); + + dirty_exceeded |= (mdtc->wb_dirty > mdtc->wb_thresh) && + ((mdtc->dirty > mdtc->thresh) || strictlimit); + + wb_position_ratio(mdtc); + if (mdtc->pos_ratio < gdtc->pos_ratio) + sdtc = mdtc; + } + + if (dirty_exceeded && !wb->dirty_exceeded) + wb->dirty_exceeded = 1; + + if (time_is_before_jiffies(wb->bw_time_stamp + + BANDWIDTH_INTERVAL)) { + spin_lock(&wb->list_lock); + __wb_update_bandwidth(gdtc, mdtc, start_time, true); + spin_unlock(&wb->list_lock); + } + + /* throttle according to the chosen dtc */ + dirty_ratelimit = wb->dirty_ratelimit; + task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >> RATELIMIT_CALC_SHIFT; - max_pause = bdi_max_pause(bdi, bdi_dirty); - min_pause = bdi_min_pause(bdi, max_pause, - task_ratelimit, dirty_ratelimit, - &nr_dirtied_pause); + max_pause = wb_max_pause(wb, sdtc->wb_dirty); + min_pause = wb_min_pause(wb, max_pause, + task_ratelimit, dirty_ratelimit, + &nr_dirtied_pause); if (unlikely(task_ratelimit == 0)) { period = max_pause; @@ -1452,11 +1684,11 @@ static void balance_dirty_pages(struct address_space *mapping, */ if (pause < min_pause) { trace_balance_dirty_pages(bdi, - dirty_thresh, - background_thresh, - nr_dirty, - bdi_thresh, - bdi_dirty, + sdtc->thresh, + sdtc->bg_thresh, + sdtc->dirty, + sdtc->wb_thresh, + sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, @@ -1481,11 +1713,11 @@ static void balance_dirty_pages(struct address_space *mapping, pause: trace_balance_dirty_pages(bdi, - dirty_thresh, - background_thresh, - nr_dirty, - bdi_thresh, - bdi_dirty, + sdtc->thresh, + sdtc->bg_thresh, + sdtc->dirty, + sdtc->wb_thresh, + sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, @@ -1500,33 +1732,33 @@ pause: current->nr_dirtied_pause = nr_dirtied_pause; /* - * This is typically equal to (nr_dirty < dirty_thresh) and can - * also keep "1000+ dd on a slow USB stick" under control. + * This is typically equal to (dirty < thresh) and can also + * keep "1000+ dd on a slow USB stick" under control. */ if (task_ratelimit) break; /* * In the case of an unresponding NFS server and the NFS dirty - * pages exceeds dirty_thresh, give the other good bdi's a pipe + * 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 * pipe going: the flusher cleans 1 page => the task dirties 1 - * more page. However bdi_dirty has accounting errors. So use - * the larger and more IO friendly bdi_stat_error. + * more page. However wb_dirty has accounting errors. So use + * the larger and more IO friendly wb_stat_error. */ - if (bdi_dirty <= bdi_stat_error(bdi)) + if (sdtc->wb_dirty <= wb_stat_error(wb)) break; if (fatal_signal_pending(current)) break; } - if (!dirty_exceeded && bdi->dirty_exceeded) - bdi->dirty_exceeded = 0; + if (!dirty_exceeded && wb->dirty_exceeded) + wb->dirty_exceeded = 0; - if (writeback_in_progress(bdi)) + if (writeback_in_progress(wb)) return; /* @@ -1540,8 +1772,8 @@ pause: if (laptop_mode) return; - if (nr_reclaimable > background_thresh) - bdi_start_background_writeback(bdi); + if (nr_reclaimable > gdtc->bg_thresh) + wb_start_background_writeback(wb); } static DEFINE_PER_CPU(int, bdp_ratelimits); @@ -1577,15 +1809,22 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; */ void balance_dirty_pages_ratelimited(struct address_space *mapping) { - struct backing_dev_info *bdi = inode_to_bdi(mapping->host); + struct inode *inode = mapping->host; + struct backing_dev_info *bdi = inode_to_bdi(inode); + struct bdi_writeback *wb = NULL; int ratelimit; int *p; if (!bdi_cap_account_dirty(bdi)) return; + if (inode_cgwb_enabled(inode)) + wb = wb_get_create_current(bdi, GFP_KERNEL); + if (!wb) + wb = &bdi->wb; + ratelimit = current->nr_dirtied_pause; - if (bdi->dirty_exceeded) + if (wb->dirty_exceeded) ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10)); preempt_disable(); @@ -1617,10 +1856,59 @@ void balance_dirty_pages_ratelimited(struct address_space *mapping) preempt_enable(); if (unlikely(current->nr_dirtied >= ratelimit)) - balance_dirty_pages(mapping, current->nr_dirtied); + balance_dirty_pages(mapping, wb, current->nr_dirtied); + + wb_put(wb); } EXPORT_SYMBOL(balance_dirty_pages_ratelimited); +/** + * wb_over_bg_thresh - does @wb need to be written back? + * @wb: bdi_writeback of interest + * + * Determines whether background writeback should keep writing @wb or it's + * clean enough. Returns %true if writeback should continue. + */ +bool wb_over_bg_thresh(struct bdi_writeback *wb) +{ + struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; + struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; + struct dirty_throttle_control * const gdtc = &gdtc_stor; + struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? + &mdtc_stor : NULL; + + /* + * Similar to balance_dirty_pages() but ignores pages being written + * as we're trying to decide whether to put more under writeback. + */ + gdtc->avail = global_dirtyable_memory(); + gdtc->dirty = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS); + domain_dirty_limits(gdtc); + + if (gdtc->dirty > gdtc->bg_thresh) + return true; + + if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(gdtc)) + return true; + + if (mdtc) { + unsigned long writeback; + + mem_cgroup_wb_stats(wb, &mdtc->avail, &mdtc->dirty, &writeback); + mdtc_cap_avail(mdtc); + domain_dirty_limits(mdtc); /* ditto, ignore writeback */ + + if (mdtc->dirty > mdtc->bg_thresh) + return true; + + if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(mdtc)) + return true; + } + + return false; +} + void throttle_vm_writeout(gfp_t gfp_mask) { unsigned long background_thresh; @@ -1628,7 +1916,7 @@ void throttle_vm_writeout(gfp_t gfp_mask) for ( ; ; ) { global_dirty_limits(&background_thresh, &dirty_thresh); - dirty_thresh = hard_dirty_limit(dirty_thresh); + dirty_thresh = hard_dirty_limit(&global_wb_domain, dirty_thresh); /* * Boost the allowable dirty threshold a bit for page @@ -1667,14 +1955,20 @@ void laptop_mode_timer_fn(unsigned long data) struct request_queue *q = (struct request_queue *)data; int nr_pages = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS); + struct bdi_writeback *wb; + struct wb_iter iter; /* * We want to write everything out, not just down to the dirty * threshold */ - if (bdi_has_dirty_io(&q->backing_dev_info)) - bdi_start_writeback(&q->backing_dev_info, nr_pages, - WB_REASON_LAPTOP_TIMER); + if (!bdi_has_dirty_io(&q->backing_dev_info)) + return; + + bdi_for_each_wb(wb, &q->backing_dev_info, &iter, 0) + if (wb_has_dirty_io(wb)) + wb_start_writeback(wb, nr_pages, true, + WB_REASON_LAPTOP_TIMER); } /* @@ -1718,10 +2012,12 @@ void laptop_sync_completion(void) void writeback_set_ratelimit(void) { + struct wb_domain *dom = &global_wb_domain; unsigned long background_thresh; unsigned long dirty_thresh; + global_dirty_limits(&background_thresh, &dirty_thresh); - global_dirty_limit = dirty_thresh; + dom->dirty_limit = dirty_thresh; ratelimit_pages = dirty_thresh / (num_online_cpus() * 32); if (ratelimit_pages < 16) ratelimit_pages = 16; @@ -1767,10 +2063,10 @@ static struct notifier_block ratelimit_nb = { */ void __init page_writeback_init(void) { + BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL)); + writeback_set_ratelimit(); register_cpu_notifier(&ratelimit_nb); - - fprop_global_init(&writeout_completions, GFP_KERNEL); } /** @@ -2090,19 +2386,29 @@ int __set_page_dirty_no_writeback(struct page *page) /* * Helper function for set_page_dirty family. + * + * Caller must hold mem_cgroup_begin_page_stat(). + * * NOTE: This relies on being atomic wrt interrupts. */ -void account_page_dirtied(struct page *page, struct address_space *mapping) +void account_page_dirtied(struct page *page, struct address_space *mapping, + struct mem_cgroup *memcg) { + struct inode *inode = mapping->host; + trace_writeback_dirty_page(page, mapping); if (mapping_cap_account_dirty(mapping)) { - struct backing_dev_info *bdi = inode_to_bdi(mapping->host); + struct bdi_writeback *wb; + + inode_attach_wb(inode, page); + wb = inode_to_wb(inode); + mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_DIRTY); __inc_zone_page_state(page, NR_FILE_DIRTY); __inc_zone_page_state(page, NR_DIRTIED); - __inc_bdi_stat(bdi, BDI_RECLAIMABLE); - __inc_bdi_stat(bdi, BDI_DIRTIED); + __inc_wb_stat(wb, WB_RECLAIMABLE); + __inc_wb_stat(wb, WB_DIRTIED); task_io_account_write(PAGE_CACHE_SIZE); current->nr_dirtied++; this_cpu_inc(bdp_ratelimits); @@ -2113,21 +2419,18 @@ EXPORT_SYMBOL(account_page_dirtied); /* * Helper function for deaccounting dirty page without writeback. * - * Doing this should *normally* only ever be done when a page - * is truncated, and is not actually mapped anywhere at all. However, - * fs/buffer.c does this when it notices that somebody has cleaned - * out all the buffers on a page without actually doing it through - * the VM. Can you say "ext3 is horribly ugly"? Thought you could. + * Caller must hold mem_cgroup_begin_page_stat(). */ -void account_page_cleaned(struct page *page, struct address_space *mapping) +void account_page_cleaned(struct page *page, struct address_space *mapping, + struct mem_cgroup *memcg, struct bdi_writeback *wb) { if (mapping_cap_account_dirty(mapping)) { + mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_DIRTY); dec_zone_page_state(page, NR_FILE_DIRTY); - dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE); + dec_wb_stat(wb, WB_RECLAIMABLE); task_io_account_cancelled_write(PAGE_CACHE_SIZE); } } -EXPORT_SYMBOL(account_page_cleaned); /* * For address_spaces which do not use buffers. Just tag the page as dirty in @@ -2143,26 +2446,34 @@ EXPORT_SYMBOL(account_page_cleaned); */ int __set_page_dirty_nobuffers(struct page *page) { + struct mem_cgroup *memcg; + + memcg = mem_cgroup_begin_page_stat(page); if (!TestSetPageDirty(page)) { struct address_space *mapping = page_mapping(page); unsigned long flags; - if (!mapping) + if (!mapping) { + mem_cgroup_end_page_stat(memcg); return 1; + } spin_lock_irqsave(&mapping->tree_lock, flags); BUG_ON(page_mapping(page) != mapping); WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); - account_page_dirtied(page, mapping); + account_page_dirtied(page, mapping, memcg); radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); + if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } return 1; } + mem_cgroup_end_page_stat(memcg); return 0; } EXPORT_SYMBOL(__set_page_dirty_nobuffers); @@ -2177,10 +2488,17 @@ EXPORT_SYMBOL(__set_page_dirty_nobuffers); void account_page_redirty(struct page *page) { struct address_space *mapping = page->mapping; + if (mapping && mapping_cap_account_dirty(mapping)) { + struct inode *inode = mapping->host; + struct bdi_writeback *wb; + bool locked; + + wb = unlocked_inode_to_wb_begin(inode, &locked); current->nr_dirtied--; dec_zone_page_state(page, NR_DIRTIED); - dec_bdi_stat(inode_to_bdi(mapping->host), BDI_DIRTIED); + dec_wb_stat(wb, WB_DIRTIED); + unlocked_inode_to_wb_end(inode, locked); } } EXPORT_SYMBOL(account_page_redirty); @@ -2266,6 +2584,43 @@ int set_page_dirty_lock(struct page *page) EXPORT_SYMBOL(set_page_dirty_lock); /* + * This cancels just the dirty bit on the kernel page itself, it does NOT + * actually remove dirty bits on any mmap's that may be around. It also + * leaves the page tagged dirty, so any sync activity will still find it on + * the dirty lists, and in particular, clear_page_dirty_for_io() will still + * look at the dirty bits in the VM. + * + * Doing this should *normally* only ever be done when a page is truncated, + * and is not actually mapped anywhere at all. However, fs/buffer.c does + * this when it notices that somebody has cleaned out all the buffers on a + * page without actually doing it through the VM. Can you say "ext3 is + * horribly ugly"? Thought you could. + */ +void cancel_dirty_page(struct page *page) +{ + struct address_space *mapping = page_mapping(page); + + if (mapping_cap_account_dirty(mapping)) { + struct inode *inode = mapping->host; + struct bdi_writeback *wb; + struct mem_cgroup *memcg; + bool locked; + + memcg = mem_cgroup_begin_page_stat(page); + wb = unlocked_inode_to_wb_begin(inode, &locked); + + if (TestClearPageDirty(page)) + account_page_cleaned(page, mapping, memcg, wb); + + unlocked_inode_to_wb_end(inode, locked); + mem_cgroup_end_page_stat(memcg); + } else { + ClearPageDirty(page); + } +} +EXPORT_SYMBOL(cancel_dirty_page); + +/* * Clear a page's dirty flag, while caring for dirty memory accounting. * Returns true if the page was previously dirty. * @@ -2282,10 +2637,16 @@ EXPORT_SYMBOL(set_page_dirty_lock); int clear_page_dirty_for_io(struct page *page) { struct address_space *mapping = page_mapping(page); + int ret = 0; BUG_ON(!PageLocked(page)); if (mapping && mapping_cap_account_dirty(mapping)) { + struct inode *inode = mapping->host; + struct bdi_writeback *wb; + struct mem_cgroup *memcg; + bool locked; + /* * Yes, Virginia, this is indeed insane. * @@ -2321,13 +2682,17 @@ int clear_page_dirty_for_io(struct page *page) * always locked coming in here, so we get the desired * exclusion. */ + memcg = mem_cgroup_begin_page_stat(page); + wb = unlocked_inode_to_wb_begin(inode, &locked); if (TestClearPageDirty(page)) { + mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_DIRTY); dec_zone_page_state(page, NR_FILE_DIRTY); - dec_bdi_stat(inode_to_bdi(mapping->host), - BDI_RECLAIMABLE); - return 1; + dec_wb_stat(wb, WB_RECLAIMABLE); + ret = 1; } - return 0; + unlocked_inode_to_wb_end(inode, locked); + mem_cgroup_end_page_stat(memcg); + return ret; } return TestClearPageDirty(page); } @@ -2341,7 +2706,8 @@ int test_clear_page_writeback(struct page *page) memcg = mem_cgroup_begin_page_stat(page); if (mapping) { - struct backing_dev_info *bdi = inode_to_bdi(mapping->host); + struct inode *inode = mapping->host; + struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; spin_lock_irqsave(&mapping->tree_lock, flags); @@ -2351,8 +2717,10 @@ int test_clear_page_writeback(struct page *page) page_index(page), PAGECACHE_TAG_WRITEBACK); if (bdi_cap_account_writeback(bdi)) { - __dec_bdi_stat(bdi, BDI_WRITEBACK); - __bdi_writeout_inc(bdi); + struct bdi_writeback *wb = inode_to_wb(inode); + + __dec_wb_stat(wb, WB_WRITEBACK); + __wb_writeout_inc(wb); } } spin_unlock_irqrestore(&mapping->tree_lock, flags); @@ -2376,7 +2744,8 @@ int __test_set_page_writeback(struct page *page, bool keep_write) memcg = mem_cgroup_begin_page_stat(page); if (mapping) { - struct backing_dev_info *bdi = inode_to_bdi(mapping->host); + struct inode *inode = mapping->host; + struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; spin_lock_irqsave(&mapping->tree_lock, flags); @@ -2386,7 +2755,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) page_index(page), PAGECACHE_TAG_WRITEBACK); if (bdi_cap_account_writeback(bdi)) - __inc_bdi_stat(bdi, BDI_WRITEBACK); + __inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); } if (!PageDirty(page)) radix_tree_tag_clear(&mapping->page_tree, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ebffa0e4a9c0..5b5240b7f642 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -61,6 +61,7 @@ #include <linux/hugetlb.h> #include <linux/sched/rt.h> #include <linux/page_owner.h> +#include <linux/kthread.h> #include <asm/sections.h> #include <asm/tlbflush.h> @@ -235,6 +236,75 @@ EXPORT_SYMBOL(nr_online_nodes); int page_group_by_mobility_disabled __read_mostly; +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +static inline void reset_deferred_meminit(pg_data_t *pgdat) +{ + pgdat->first_deferred_pfn = ULONG_MAX; +} + +/* Returns true if the struct page for the pfn is uninitialised */ +static inline bool __meminit early_page_uninitialised(unsigned long pfn) +{ + if (pfn >= NODE_DATA(early_pfn_to_nid(pfn))->first_deferred_pfn) + return true; + + return false; +} + +static inline bool early_page_nid_uninitialised(unsigned long pfn, int nid) +{ + if (pfn >= NODE_DATA(nid)->first_deferred_pfn) + return true; + + return false; +} + +/* + * Returns false when the remaining initialisation should be deferred until + * later in the boot cycle when it can be parallelised. + */ +static inline bool update_defer_init(pg_data_t *pgdat, + unsigned long pfn, unsigned long zone_end, + unsigned long *nr_initialised) +{ + /* Always populate low zones for address-contrained allocations */ + if (zone_end < pgdat_end_pfn(pgdat)) + return true; + + /* Initialise at least 2G of the highest zone */ + (*nr_initialised)++; + if (*nr_initialised > (2UL << (30 - PAGE_SHIFT)) && + (pfn & (PAGES_PER_SECTION - 1)) == 0) { + pgdat->first_deferred_pfn = pfn; + return false; + } + + return true; +} +#else +static inline void reset_deferred_meminit(pg_data_t *pgdat) +{ +} + +static inline bool early_page_uninitialised(unsigned long pfn) +{ + return false; +} + +static inline bool early_page_nid_uninitialised(unsigned long pfn, int nid) +{ + return false; +} + +static inline bool update_defer_init(pg_data_t *pgdat, + unsigned long pfn, unsigned long zone_end, + unsigned long *nr_initialised) +{ + return true; +} +#endif + + void set_pageblock_migratetype(struct page *page, int migratetype) { if (unlikely(page_group_by_mobility_disabled && @@ -380,20 +450,6 @@ void prep_compound_page(struct page *page, unsigned long order) } } -static inline void prep_zero_page(struct page *page, unsigned int order, - gfp_t gfp_flags) -{ - int i; - - /* - * clear_highpage() will use KM_USER0, so it's a bug to use __GFP_ZERO - * and __GFP_HIGHMEM from hard or soft interrupt context. - */ - VM_BUG_ON((gfp_flags & __GFP_HIGHMEM) && in_interrupt()); - for (i = 0; i < (1 << order); i++) - clear_highpage(page + i); -} - #ifdef CONFIG_DEBUG_PAGEALLOC unsigned int _debug_guardpage_minorder; bool _debug_pagealloc_enabled __read_mostly; @@ -778,6 +834,75 @@ static int free_tail_pages_check(struct page *head_page, struct page *page) return 0; } +static void __meminit __init_single_page(struct page *page, unsigned long pfn, + unsigned long zone, int nid) +{ + set_page_links(page, zone, nid, pfn); + init_page_count(page); + page_mapcount_reset(page); + page_cpupid_reset_last(page); + + INIT_LIST_HEAD(&page->lru); +#ifdef WANT_PAGE_VIRTUAL + /* The shift won't overflow because ZONE_NORMAL is below 4G. */ + if (!is_highmem_idx(zone)) + set_page_address(page, __va(pfn << PAGE_SHIFT)); +#endif +} + +static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone, + int nid) +{ + return __init_single_page(pfn_to_page(pfn), pfn, zone, nid); +} + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +static void init_reserved_page(unsigned long pfn) +{ + pg_data_t *pgdat; + int nid, zid; + + if (!early_page_uninitialised(pfn)) + return; + + nid = early_pfn_to_nid(pfn); + pgdat = NODE_DATA(nid); + + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + struct zone *zone = &pgdat->node_zones[zid]; + + if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone)) + break; + } + __init_single_pfn(pfn, zid, nid); +} +#else +static inline void init_reserved_page(unsigned long pfn) +{ +} +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + +/* + * Initialised pages do not have PageReserved set. This function is + * called for each range allocated by the bootmem allocator and + * marks the pages PageReserved. The remaining valid pages are later + * sent to the buddy page allocator. + */ +void __meminit reserve_bootmem_region(unsigned long start, unsigned long end) +{ + unsigned long start_pfn = PFN_DOWN(start); + unsigned long end_pfn = PFN_UP(end); + + for (; start_pfn < end_pfn; start_pfn++) { + if (pfn_valid(start_pfn)) { + struct page *page = pfn_to_page(start_pfn); + + init_reserved_page(start_pfn); + SetPageReserved(page); + } + } +} + static bool free_pages_prepare(struct page *page, unsigned int order) { bool compound = PageCompound(page); @@ -832,7 +957,8 @@ static void __free_pages_ok(struct page *page, unsigned int order) local_irq_restore(flags); } -void __init __free_pages_bootmem(struct page *page, unsigned int order) +static void __init __free_pages_boot_core(struct page *page, + unsigned long pfn, unsigned int order) { unsigned int nr_pages = 1 << order; struct page *p = page; @@ -852,6 +978,235 @@ void __init __free_pages_bootmem(struct page *page, unsigned int order) __free_pages(page, order); } +#if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \ + defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) + +static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata; + +int __meminit early_pfn_to_nid(unsigned long pfn) +{ + static DEFINE_SPINLOCK(early_pfn_lock); + int nid; + + spin_lock(&early_pfn_lock); + nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); + if (nid < 0) + nid = 0; + spin_unlock(&early_pfn_lock); + + return nid; +} +#endif + +#ifdef CONFIG_NODES_SPAN_OTHER_NODES +static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node, + struct mminit_pfnnid_cache *state) +{ + int nid; + + nid = __early_pfn_to_nid(pfn, state); + if (nid >= 0 && nid != node) + return false; + return true; +} + +/* Only safe to use early in boot when initialisation is single-threaded */ +static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node) +{ + return meminit_pfn_in_nid(pfn, node, &early_pfnnid_cache); +} + +#else + +static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node) +{ + return true; +} +static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node, + struct mminit_pfnnid_cache *state) +{ + return true; +} +#endif + + +void __init __free_pages_bootmem(struct page *page, unsigned long pfn, + unsigned int order) +{ + if (early_page_uninitialised(pfn)) + return; + return __free_pages_boot_core(page, pfn, order); +} + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +static void __init deferred_free_range(struct page *page, + unsigned long pfn, int nr_pages) +{ + int i; + + if (!page) + return; + + /* Free a large naturally-aligned chunk if possible */ + if (nr_pages == MAX_ORDER_NR_PAGES && + (pfn & (MAX_ORDER_NR_PAGES-1)) == 0) { + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + __free_pages_boot_core(page, pfn, MAX_ORDER-1); + return; + } + + for (i = 0; i < nr_pages; i++, page++, pfn++) + __free_pages_boot_core(page, pfn, 0); +} + +/* Completion tracking for deferred_init_memmap() threads */ +static atomic_t pgdat_init_n_undone __initdata; +static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp); + +static inline void __init pgdat_init_report_one_done(void) +{ + if (atomic_dec_and_test(&pgdat_init_n_undone)) + complete(&pgdat_init_all_done_comp); +} + +/* Initialise remaining memory on a node */ +static int __init deferred_init_memmap(void *data) +{ + pg_data_t *pgdat = data; + int nid = pgdat->node_id; + struct mminit_pfnnid_cache nid_init_state = { }; + unsigned long start = jiffies; + unsigned long nr_pages = 0; + unsigned long walk_start, walk_end; + int i, zid; + struct zone *zone; + unsigned long first_init_pfn = pgdat->first_deferred_pfn; + const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); + + if (first_init_pfn == ULONG_MAX) { + pgdat_init_report_one_done(); + return 0; + } + + /* Bind memory initialisation thread to a local node if possible */ + if (!cpumask_empty(cpumask)) + set_cpus_allowed_ptr(current, cpumask); + + /* Sanity check boundaries */ + BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn); + BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat)); + pgdat->first_deferred_pfn = ULONG_MAX; + + /* Only the highest zone is deferred so find it */ + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + zone = pgdat->node_zones + zid; + if (first_init_pfn < zone_end_pfn(zone)) + break; + } + + for_each_mem_pfn_range(i, nid, &walk_start, &walk_end, NULL) { + unsigned long pfn, end_pfn; + struct page *page = NULL; + struct page *free_base_page = NULL; + unsigned long free_base_pfn = 0; + int nr_to_free = 0; + + end_pfn = min(walk_end, zone_end_pfn(zone)); + pfn = first_init_pfn; + if (pfn < walk_start) + pfn = walk_start; + if (pfn < zone->zone_start_pfn) + pfn = zone->zone_start_pfn; + + for (; pfn < end_pfn; pfn++) { + if (!pfn_valid_within(pfn)) + goto free_range; + + /* + * Ensure pfn_valid is checked every + * MAX_ORDER_NR_PAGES for memory holes + */ + if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) { + if (!pfn_valid(pfn)) { + page = NULL; + goto free_range; + } + } + + if (!meminit_pfn_in_nid(pfn, nid, &nid_init_state)) { + page = NULL; + goto free_range; + } + + /* Minimise pfn page lookups and scheduler checks */ + if (page && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) { + page++; + } else { + nr_pages += nr_to_free; + deferred_free_range(free_base_page, + free_base_pfn, nr_to_free); + free_base_page = NULL; + free_base_pfn = nr_to_free = 0; + + page = pfn_to_page(pfn); + cond_resched(); + } + + if (page->flags) { + VM_BUG_ON(page_zone(page) != zone); + goto free_range; + } + + __init_single_page(page, pfn, zid, nid); + if (!free_base_page) { + free_base_page = page; + free_base_pfn = pfn; + nr_to_free = 0; + } + nr_to_free++; + + /* Where possible, batch up pages for a single free */ + continue; +free_range: + /* Free the current block of pages to allocator */ + nr_pages += nr_to_free; + deferred_free_range(free_base_page, free_base_pfn, + nr_to_free); + free_base_page = NULL; + free_base_pfn = nr_to_free = 0; + } + + first_init_pfn = max(end_pfn, first_init_pfn); + } + + /* Sanity check that the next zone really is unpopulated */ + WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone)); + + pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages, + jiffies_to_msecs(jiffies - start)); + + pgdat_init_report_one_done(); + return 0; +} + +void __init page_alloc_init_late(void) +{ + int nid; + + /* There will be num_node_state(N_MEMORY) threads */ + atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY)); + for_each_node_state(nid, N_MEMORY) { + kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid); + } + + /* Block until all are initialised */ + wait_for_completion(&pgdat_init_all_done_comp); + + /* Reinit limits that are based on free pages after the kernel is up */ + files_maxfiles_init(); +} +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + #ifdef CONFIG_CMA /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void __init init_cma_reserved_pageblock(struct page *page) @@ -941,6 +1296,10 @@ static inline int check_new_page(struct page *page) bad_reason = "non-NULL mapping"; if (unlikely(atomic_read(&page->_count) != 0)) bad_reason = "nonzero _count"; + if (unlikely(page->flags & __PG_HWPOISON)) { + bad_reason = "HWPoisoned (hardware-corrupted)"; + bad_flags = __PG_HWPOISON; + } if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) { bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set"; bad_flags = PAGE_FLAGS_CHECK_AT_PREP; @@ -975,7 +1334,8 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, kasan_alloc_pages(page, order); if (gfp_flags & __GFP_ZERO) - prep_zero_page(page, order, gfp_flags); + for (i = 0; i < (1 << order); i++) + clear_highpage(page + i); if (order && (gfp_flags & __GFP_COMP)) prep_compound_page(page, order); @@ -983,12 +1343,15 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, set_page_owner(page, order, gfp_flags); /* - * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was necessary to + * page is set pfmemalloc when ALLOC_NO_WATERMARKS was necessary to * allocate the page. The expectation is that the caller is taking * steps that will free more memory. The caller should avoid the page * being used for !PFMEMALLOC purposes. */ - page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS); + if (alloc_flags & ALLOC_NO_WATERMARKS) + set_page_pfmemalloc(page); + else + clear_page_pfmemalloc(page); return 0; } @@ -1603,6 +1966,7 @@ void free_hot_cold_page_list(struct list_head *list, bool cold) void split_page(struct page *page, unsigned int order) { int i; + gfp_t gfp_mask; VM_BUG_ON_PAGE(PageCompound(page), page); VM_BUG_ON_PAGE(!page_count(page), page); @@ -1616,10 +1980,11 @@ void split_page(struct page *page, unsigned int order) split_page(virt_to_page(page[0].shadow), order); #endif - set_page_owner(page, 0, 0); + gfp_mask = get_page_owner_gfp(page); + set_page_owner(page, 0, gfp_mask); for (i = 1; i < (1 << order); i++) { set_page_refcounted(page + i); - set_page_owner(page + i, 0, 0); + set_page_owner(page + i, 0, gfp_mask); } } EXPORT_SYMBOL_GPL(split_page); @@ -1649,6 +2014,8 @@ int __isolate_free_page(struct page *page, unsigned int order) zone->free_area[order].nr_free--; rmv_page_order(page); + set_page_owner(page, order, __GFP_MOVABLE); + /* Set the pageblock if the isolated page is at least a pageblock */ if (order >= pageblock_order - 1) { struct page *endpage = page + (1 << order) - 1; @@ -1660,7 +2027,7 @@ int __isolate_free_page(struct page *page, unsigned int order) } } - set_page_owner(page, order, 0); + return 1UL << order; } @@ -2322,48 +2689,6 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...) show_mem(filter); } -static inline int -should_alloc_retry(gfp_t gfp_mask, unsigned int order, - unsigned long did_some_progress, - unsigned long pages_reclaimed) -{ - /* Do not loop if specifically requested */ - if (gfp_mask & __GFP_NORETRY) - return 0; - - /* Always retry if specifically requested */ - if (gfp_mask & __GFP_NOFAIL) - return 1; - - /* - * Suspend converts GFP_KERNEL to __GFP_WAIT which can prevent reclaim - * making forward progress without invoking OOM. Suspend also disables - * storage devices so kswapd will not help. Bail if we are suspending. - */ - if (!did_some_progress && pm_suspended_storage()) - return 0; - - /* - * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER - * means __GFP_NOFAIL, but that may not be true in other - * implementations. - */ - if (order <= PAGE_ALLOC_COSTLY_ORDER) - return 1; - - /* - * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is - * specified, then we retry until we no longer reclaim any pages - * (above), or we've reclaimed an order of pages at least as - * large as the allocation's order. In both cases, if the - * allocation still fails, we stop retrying. - */ - if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order)) - return 1; - - return 0; -} - static inline struct page * __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, const struct alloc_context *ac, unsigned long *did_some_progress) @@ -2373,10 +2698,10 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, *did_some_progress = 0; /* - * Acquire the per-zone oom lock for each zone. If that - * fails, somebody else is making progress for us. + * Acquire the oom lock. If that fails, somebody else is + * making progress for us. */ - if (!oom_zonelist_trylock(ac->zonelist, gfp_mask)) { + if (!mutex_trylock(&oom_lock)) { *did_some_progress = 1; schedule_timeout_uninterruptible(1); return NULL; @@ -2402,16 +2727,18 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, /* The OOM killer does not needlessly kill tasks for lowmem */ if (ac->high_zoneidx < ZONE_NORMAL) goto out; - /* The OOM killer does not compensate for light reclaim */ + /* The OOM killer does not compensate for IO-less reclaim */ if (!(gfp_mask & __GFP_FS)) { /* * XXX: Page reclaim didn't yield anything, * and the OOM killer can't be invoked, but - * keep looping as per should_alloc_retry(). + * keep looping as per tradition. */ *did_some_progress = 1; goto out; } + if (pm_suspended_storage()) + goto out; /* The OOM killer may not free memory on a specific node */ if (gfp_mask & __GFP_THISNODE) goto out; @@ -2421,7 +2748,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) *did_some_progress = 1; out: - oom_zonelist_unlock(ac->zonelist, gfp_mask); + mutex_unlock(&oom_lock); return page; } @@ -2794,40 +3121,40 @@ retry: if (page) goto got_pg; - /* Check if we should retry the allocation */ + /* Do not loop if specifically requested */ + if (gfp_mask & __GFP_NORETRY) + goto noretry; + + /* Keep reclaiming pages as long as there is reasonable progress */ pages_reclaimed += did_some_progress; - if (should_alloc_retry(gfp_mask, order, did_some_progress, - pages_reclaimed)) { - /* - * If we fail to make progress by freeing individual - * pages, but the allocation wants us to keep going, - * start OOM killing tasks. - */ - if (!did_some_progress) { - page = __alloc_pages_may_oom(gfp_mask, order, ac, - &did_some_progress); - if (page) - goto got_pg; - if (!did_some_progress) - goto nopage; - } + if ((did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER) || + ((gfp_mask & __GFP_REPEAT) && pages_reclaimed < (1 << order))) { /* Wait for some write requests to complete then retry */ wait_iff_congested(ac->preferred_zone, BLK_RW_ASYNC, HZ/50); goto retry; - } else { - /* - * High-order allocations do not necessarily loop after - * direct reclaim and reclaim/compaction depends on compaction - * being called after reclaim so call directly if necessary - */ - page = __alloc_pages_direct_compact(gfp_mask, order, - alloc_flags, ac, migration_mode, - &contended_compaction, - &deferred_compaction); - if (page) - goto got_pg; } + /* Reclaim has failed us, start killing things */ + page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress); + if (page) + goto got_pg; + + /* Retry as long as the OOM killer is making progress */ + if (did_some_progress) + goto retry; + +noretry: + /* + * High-order allocations do not necessarily loop after + * direct reclaim and reclaim/compaction depends on compaction + * being called after reclaim so call directly if necessary + */ + page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags, + ac, migration_mode, + &contended_compaction, + &deferred_compaction); + if (page) + goto got_pg; nopage: warn_alloc_failed(gfp_mask, order, NULL); got_pg: @@ -2967,6 +3294,104 @@ void free_pages(unsigned long addr, unsigned int order) EXPORT_SYMBOL(free_pages); /* + * Page Fragment: + * An arbitrary-length arbitrary-offset area of memory which resides + * within a 0 or higher order page. Multiple fragments within that page + * are individually refcounted, in the page's reference counter. + * + * The page_frag functions below provide a simple allocation framework for + * page fragments. This is used by the network stack and network device + * drivers to provide a backing region of memory for use as either an + * sk_buff->head, or to be used in the "frags" portion of skb_shared_info. + */ +static struct page *__page_frag_refill(struct page_frag_cache *nc, + gfp_t gfp_mask) +{ + struct page *page = NULL; + gfp_t gfp = gfp_mask; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY | + __GFP_NOMEMALLOC; + page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, + PAGE_FRAG_CACHE_MAX_ORDER); + nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; +#endif + if (unlikely(!page)) + page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); + + nc->va = page ? page_address(page) : NULL; + + return page; +} + +void *__alloc_page_frag(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask) +{ + unsigned int size = PAGE_SIZE; + struct page *page; + int offset; + + if (unlikely(!nc->va)) { +refill: + page = __page_frag_refill(nc, gfp_mask); + if (!page) + return NULL; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size = nc->size; +#endif + /* Even if we own the page, we do not use atomic_set(). + * This would break get_page_unless_zero() users. + */ + atomic_add(size - 1, &page->_count); + + /* reset page count bias and offset to start of new frag */ + nc->pfmemalloc = page_is_pfmemalloc(page); + nc->pagecnt_bias = size; + nc->offset = size; + } + + offset = nc->offset - fragsz; + if (unlikely(offset < 0)) { + page = virt_to_page(nc->va); + + if (!atomic_sub_and_test(nc->pagecnt_bias, &page->_count)) + goto refill; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size = nc->size; +#endif + /* OK, page count is 0, we can safely set it */ + atomic_set(&page->_count, size); + + /* reset page count bias and offset to start of new frag */ + nc->pagecnt_bias = size; + offset = size - fragsz; + } + + nc->pagecnt_bias--; + nc->offset = offset; + + return nc->va + offset; +} +EXPORT_SYMBOL(__alloc_page_frag); + +/* + * Frees a page fragment allocated out of either a compound or order 0 page. + */ +void __free_page_frag(void *addr) +{ + struct page *page = virt_to_head_page(addr); + + if (unlikely(put_page_testzero(page))) + __free_pages_ok(page, compound_order(page)); +} +EXPORT_SYMBOL(__free_page_frag); + +/* * alloc_kmem_pages charges newly allocated pages to the kmem resource counter * of the current memory cgroup. * @@ -4105,6 +4530,9 @@ static void setup_zone_migrate_reserve(struct zone *zone) zone->nr_migrate_reserve_block = reserve; for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { + if (!early_page_nid_uninitialised(pfn, zone_to_nid(zone))) + return; + if (!pfn_valid(pfn)) continue; page = pfn_to_page(pfn); @@ -4167,15 +4595,16 @@ static void setup_zone_migrate_reserve(struct zone *zone) void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, unsigned long start_pfn, enum memmap_context context) { - struct page *page; + pg_data_t *pgdat = NODE_DATA(nid); unsigned long end_pfn = start_pfn + size; unsigned long pfn; struct zone *z; + unsigned long nr_initialised = 0; if (highest_memmap_pfn < end_pfn - 1) highest_memmap_pfn = end_pfn - 1; - z = &NODE_DATA(nid)->node_zones[zone]; + z = &pgdat->node_zones[zone]; for (pfn = start_pfn; pfn < end_pfn; pfn++) { /* * There can be holes in boot-time mem_map[]s @@ -4187,14 +4616,11 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, continue; if (!early_pfn_in_nid(pfn, nid)) continue; + if (!update_defer_init(pgdat, pfn, end_pfn, + &nr_initialised)) + break; } - page = pfn_to_page(pfn); - set_page_links(page, zone, nid, pfn); - mminit_verify_page_links(page, zone, nid, pfn); - init_page_count(page); - page_mapcount_reset(page); - page_cpupid_reset_last(page); - SetPageReserved(page); + /* * Mark the block movable so that blocks are reserved for * movable at startup. This will force kernel allocations @@ -4209,17 +4635,14 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, * check here not to call set_pageblock_migratetype() against * pfn out of zone. */ - if ((z->zone_start_pfn <= pfn) - && (pfn < zone_end_pfn(z)) - && !(pfn & (pageblock_nr_pages - 1))) - set_pageblock_migratetype(page, MIGRATE_MOVABLE); + if (!(pfn & (pageblock_nr_pages - 1))) { + struct page *page = pfn_to_page(pfn); - INIT_LIST_HEAD(&page->lru); -#ifdef WANT_PAGE_VIRTUAL - /* The shift won't overflow because ZONE_NORMAL is below 4G. */ - if (!is_highmem_idx(zone)) - set_page_address(page, __va(pfn << PAGE_SHIFT)); -#endif + __init_single_page(page, pfn, zone, nid); + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + } else { + __init_single_pfn(pfn, zone, nid); + } } } @@ -4477,57 +4900,30 @@ int __meminit init_currently_empty_zone(struct zone *zone, #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP #ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID + /* * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. */ -int __meminit __early_pfn_to_nid(unsigned long pfn) +int __meminit __early_pfn_to_nid(unsigned long pfn, + struct mminit_pfnnid_cache *state) { unsigned long start_pfn, end_pfn; int nid; - /* - * NOTE: The following SMP-unsafe globals are only used early in boot - * when the kernel is running single-threaded. - */ - static unsigned long __meminitdata last_start_pfn, last_end_pfn; - static int __meminitdata last_nid; - if (last_start_pfn <= pfn && pfn < last_end_pfn) - return last_nid; + if (state->last_start <= pfn && pfn < state->last_end) + return state->last_nid; nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn); if (nid != -1) { - last_start_pfn = start_pfn; - last_end_pfn = end_pfn; - last_nid = nid; + state->last_start = start_pfn; + state->last_end = end_pfn; + state->last_nid = nid; } return nid; } #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ -int __meminit early_pfn_to_nid(unsigned long pfn) -{ - int nid; - - nid = __early_pfn_to_nid(pfn); - if (nid >= 0) - return nid; - /* just returns 0 */ - return 0; -} - -#ifdef CONFIG_NODES_SPAN_OTHER_NODES -bool __meminit early_pfn_in_nid(unsigned long pfn, int node) -{ - int nid; - - nid = __early_pfn_to_nid(pfn); - if (nid >= 0 && nid != node) - return false; - return true; -} -#endif - /** * free_bootmem_with_active_regions - Call memblock_free_early_nid for each active range * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed. @@ -4667,6 +5063,10 @@ static unsigned long __meminit zone_spanned_pages_in_node(int nid, { unsigned long zone_start_pfn, zone_end_pfn; + /* When hotadd a new node, the node should be empty */ + if (!node_start_pfn && !node_end_pfn) + return 0; + /* Get the start and end of the zone */ zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type]; zone_end_pfn = arch_zone_highest_possible_pfn[zone_type]; @@ -4730,6 +5130,10 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid, unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; unsigned long zone_start_pfn, zone_end_pfn; + /* When hotadd a new node, the node should be empty */ + if (!node_start_pfn && !node_end_pfn) + return 0; + zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high); zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high); @@ -4769,22 +5173,28 @@ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat, unsigned long *zones_size, unsigned long *zholes_size) { - unsigned long realtotalpages, totalpages = 0; + unsigned long realtotalpages = 0, totalpages = 0; enum zone_type i; - for (i = 0; i < MAX_NR_ZONES; i++) - totalpages += zone_spanned_pages_in_node(pgdat->node_id, i, - node_start_pfn, - node_end_pfn, - zones_size); - pgdat->node_spanned_pages = totalpages; - - realtotalpages = totalpages; - for (i = 0; i < MAX_NR_ZONES; i++) - realtotalpages -= - zone_absent_pages_in_node(pgdat->node_id, i, + for (i = 0; i < MAX_NR_ZONES; i++) { + struct zone *zone = pgdat->node_zones + i; + unsigned long size, real_size; + + size = zone_spanned_pages_in_node(pgdat->node_id, i, + node_start_pfn, + node_end_pfn, + zones_size); + real_size = size - zone_absent_pages_in_node(pgdat->node_id, i, node_start_pfn, node_end_pfn, zholes_size); + zone->spanned_pages = size; + zone->present_pages = real_size; + + totalpages += size; + realtotalpages += real_size; + } + + pgdat->node_spanned_pages = totalpages; pgdat->node_present_pages = realtotalpages; printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages); @@ -4894,8 +5304,7 @@ static unsigned long __paginginit calc_memmap_size(unsigned long spanned_pages, * NOTE: pgdat should get zeroed by caller. */ static void __paginginit free_area_init_core(struct pglist_data *pgdat, - unsigned long node_start_pfn, unsigned long node_end_pfn, - unsigned long *zones_size, unsigned long *zholes_size) + unsigned long node_start_pfn, unsigned long node_end_pfn) { enum zone_type j; int nid = pgdat->node_id; @@ -4916,12 +5325,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, struct zone *zone = pgdat->node_zones + j; unsigned long size, realsize, freesize, memmap_pages; - size = zone_spanned_pages_in_node(nid, j, node_start_pfn, - node_end_pfn, zones_size); - realsize = freesize = size - zone_absent_pages_in_node(nid, j, - node_start_pfn, - node_end_pfn, - zholes_size); + size = zone->spanned_pages; + realsize = freesize = zone->present_pages; /* * Adjust freesize so that it accounts for how much memory @@ -4956,8 +5361,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, nr_kernel_pages -= memmap_pages; nr_all_pages += freesize; - zone->spanned_pages = size; - zone->present_pages = realsize; /* * Set an approximate value for lowmem here, it will be adjusted * when the bootmem allocator frees pages into the buddy system. @@ -5046,6 +5449,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, /* pg_data_t should be reset to zero when it's allocated */ WARN_ON(pgdat->nr_zones || pgdat->classzone_idx); + reset_deferred_meminit(pgdat); pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP @@ -5063,8 +5467,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, (unsigned long)pgdat->node_mem_map); #endif - free_area_init_core(pgdat, start_pfn, end_pfn, - zones_size, zholes_size); + free_area_init_core(pgdat, start_pfn, end_pfn); } #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP @@ -6013,9 +6416,9 @@ out: return ret; } +#ifdef CONFIG_NUMA int hashdist = HASHDIST_DEFAULT; -#ifdef CONFIG_NUMA static int __init set_hashdist(char *str) { if (!str) diff --git a/mm/page_io.c b/mm/page_io.c index 6424869e275e..520baa4b04d7 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -69,7 +69,7 @@ void end_swap_bio_write(struct bio *bio, int err) bio_put(bio); } -void end_swap_bio_read(struct bio *bio, int err) +static void end_swap_bio_read(struct bio *bio, int err) { const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct page *page = bio->bi_io_vec[0].bv_page; diff --git a/mm/page_owner.c b/mm/page_owner.c index 0993f5f36b01..983c3a10fa07 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -76,6 +76,13 @@ void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) __set_bit(PAGE_EXT_OWNER, &page_ext->flags); } +gfp_t __get_page_owner_gfp(struct page *page) +{ + struct page_ext *page_ext = lookup_page_ext(page); + + return page_ext->gfp_mask; +} + static ssize_t print_page_owner(char __user *buf, size_t count, unsigned long pfn, struct page *page, struct page_ext *page_ext) @@ -310,4 +317,4 @@ static int __init pageowner_init(void) return 0; } -module_init(pageowner_init) +late_initcall(pageowner_init) diff --git a/mm/percpu.c b/mm/percpu.c index dfd02484e8de..2dd74487a0af 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1030,7 +1030,7 @@ area_found: memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size); ptr = __addr_to_pcpu_ptr(chunk->base_addr + off); - kmemleak_alloc_percpu(ptr, size); + kmemleak_alloc_percpu(ptr, size, gfp); return ptr; fail_unlock: diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index c25f94b33811..6b674e00153c 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -119,14 +119,15 @@ pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, } #endif -#ifndef __HAVE_ARCH_PMDP_CLEAR_FLUSH +#ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH #ifdef CONFIG_TRANSPARENT_HUGEPAGE -pmd_t pmdp_clear_flush(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmdp) +pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) { pmd_t pmd; VM_BUG_ON(address & ~HPAGE_PMD_MASK); - pmd = pmdp_get_and_clear(vma->vm_mm, address, pmdp); + VM_BUG_ON(!pmd_trans_huge(*pmdp)); + pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; } @@ -198,3 +199,23 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif + +#ifndef pmdp_collapse_flush +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + /* + * pmd and hugepage pte format are same. So we could + * use the same function. + */ + pmd_t pmd; + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + VM_BUG_ON(pmd_trans_huge(*pmdp)); + pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + return pmd; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif diff --git a/mm/readahead.c b/mm/readahead.c index 935675844b2e..60cd846a9a44 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -541,7 +541,7 @@ page_cache_async_readahead(struct address_space *mapping, /* * Defer asynchronous read-ahead on IO congestion. */ - if (bdi_read_congested(inode_to_bdi(mapping->host))) + if (inode_read_congested(mapping->host)) return; /* do read-ahead */ diff --git a/mm/rmap.c b/mm/rmap.c index 24dd3f9fee27..171b68768df1 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -30,6 +30,8 @@ * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in __set_page_dirty_buffers) + * mem_cgroup_{begin,end}_page_stat (memcg->move_lock) + * mapping->tree_lock (widely used) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) @@ -625,7 +627,7 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) pmd = pmd_offset(pud, address); /* - * Some THP functions use the sequence pmdp_clear_flush(), set_pmd_at() + * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at() * without holding anon_vma lock for write. So when looking for a * genuine pmde (in which to find pte), test present and !THP together. */ @@ -950,7 +952,12 @@ void page_move_anon_rmap(struct page *page, VM_BUG_ON_PAGE(page->index != linear_page_index(vma, address), page); anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; - page->mapping = (struct address_space *) anon_vma; + /* + * Ensure that anon_vma and the PAGE_MAPPING_ANON bit are written + * simultaneously, so a concurrent reader (eg page_referenced()'s + * PageAnon()) will not see one without the other. + */ + WRITE_ONCE(page->mapping, (struct address_space *) anon_vma); } /** diff --git a/mm/shmem.c b/mm/shmem.c index de981370fbc5..dbe0c1e8349c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -569,7 +569,7 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) i_size_write(inode, newsize); inode->i_ctime = inode->i_mtime = CURRENT_TIME; } - if (newsize < oldsize) { + if (newsize <= oldsize) { loff_t holebegin = round_up(newsize, PAGE_SIZE); unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); shmem_truncate_range(inode, newsize, (loff_t)-1); @@ -2451,6 +2451,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s return -ENOMEM; } inode->i_op = &shmem_short_symlink_operations; + inode->i_link = info->symlink; } else { error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL); if (error) { @@ -2474,30 +2475,23 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s return 0; } -static void *shmem_follow_short_symlink(struct dentry *dentry, struct nameidata *nd) -{ - nd_set_link(nd, SHMEM_I(d_inode(dentry))->symlink); - return NULL; -} - -static void *shmem_follow_link(struct dentry *dentry, struct nameidata *nd) +static const char *shmem_follow_link(struct dentry *dentry, void **cookie) { struct page *page = NULL; int error = shmem_getpage(d_inode(dentry), 0, &page, SGP_READ, NULL); - nd_set_link(nd, error ? ERR_PTR(error) : kmap(page)); - if (page) - unlock_page(page); - return page; + if (error) + return ERR_PTR(error); + unlock_page(page); + *cookie = page; + return kmap(page); } -static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie) +static void shmem_put_link(struct inode *unused, void *cookie) { - if (!IS_ERR(nd_get_link(nd))) { - struct page *page = cookie; - kunmap(page); - mark_page_accessed(page); - page_cache_release(page); - } + struct page *page = cookie; + kunmap(page); + mark_page_accessed(page); + page_cache_release(page); } #ifdef CONFIG_TMPFS_XATTR @@ -2642,7 +2636,7 @@ static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size) static const struct inode_operations shmem_short_symlink_operations = { .readlink = generic_readlink, - .follow_link = shmem_follow_short_symlink, + .follow_link = simple_follow_link, #ifdef CONFIG_TMPFS_XATTR .setxattr = shmem_setxattr, .getxattr = shmem_getxattr, @@ -3369,8 +3363,8 @@ put_path: * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be * kernel internal. There will be NO LSM permission checks against the * underlying inode. So users of this interface must do LSM checks at a - * higher layer. The one user is the big_key implementation. LSM checks - * are provided at the key level rather than the inode level. + * higher layer. The users are the big_key and shm implementations. LSM + * checks are provided at the key or shm level rather than the inode. * @name: name for dentry (to be seen in /proc/<pid>/maps * @size: size to be set for the file * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size @@ -3401,7 +3395,13 @@ int shmem_zero_setup(struct vm_area_struct *vma) struct file *file; loff_t size = vma->vm_end - vma->vm_start; - file = shmem_file_setup("dev/zero", size, vma->vm_flags); + /* + * Cloning a new file under mmap_sem leads to a lock ordering conflict + * between XFS directory reading and selinux: since this file is only + * accessible to the user through its mapping, use S_PRIVATE flag to + * bypass file security, in the same way as shmem_kernel_file_setup(). + */ + file = __shmem_file_setup("dev/zero", size, vma->vm_flags, S_PRIVATE); if (IS_ERR(file)) return PTR_ERR(file); diff --git a/mm/slab.c b/mm/slab.c index 7eb38dd1cefa..bbd0b47dc6a9 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1454,6 +1454,7 @@ void __init kmem_cache_init(void) kmalloc_caches[INDEX_NODE] = create_kmalloc_cache("kmalloc-node", kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS); slab_state = PARTIAL_NODE; + setup_kmalloc_cache_index_table(); slab_early_init = 0; @@ -1602,7 +1603,7 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, } /* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */ - if (unlikely(page->pfmemalloc)) + if (page_is_pfmemalloc(page)) pfmemalloc_active = true; nr_pages = (1 << cachep->gfporder); @@ -1613,7 +1614,7 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, add_zone_page_state(page_zone(page), NR_SLAB_UNRECLAIMABLE, nr_pages); __SetPageSlab(page); - if (page->pfmemalloc) + if (page_is_pfmemalloc(page)) SetPageSlabPfmemalloc(page); if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) { diff --git a/mm/slab.h b/mm/slab.h index 4c3ac12dd644..8da63e4e470f 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -71,6 +71,7 @@ unsigned long calculate_alignment(unsigned long flags, #ifndef CONFIG_SLOB /* Kmalloc array related functions */ +void setup_kmalloc_cache_index_table(void); void create_kmalloc_caches(unsigned long); /* Find the kmalloc slab corresponding for a certain size */ diff --git a/mm/slab_common.c b/mm/slab_common.c index 999bb3424d44..86831105a09f 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -37,8 +37,7 @@ struct kmem_cache *kmem_cache; SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \ SLAB_FAILSLAB) -#define SLAB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \ - SLAB_CACHE_DMA | SLAB_NOTRACK) +#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | SLAB_NOTRACK) /* * Merge control. If this is set then no merging of slab caches will occur. @@ -784,25 +783,45 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags) } /* - * Create the kmalloc array. Some of the regular kmalloc arrays - * may already have been created because they were needed to - * enable allocations for slab creation. + * kmalloc_info[] is to make slub_debug=,kmalloc-xx option work at boot time. + * kmalloc_index() supports up to 2^26=64MB, so the final entry of the table is + * kmalloc-67108864. */ -void __init create_kmalloc_caches(unsigned long flags) +static struct { + const char *name; + unsigned long size; +} const kmalloc_info[] __initconst = { + {NULL, 0}, {"kmalloc-96", 96}, + {"kmalloc-192", 192}, {"kmalloc-8", 8}, + {"kmalloc-16", 16}, {"kmalloc-32", 32}, + {"kmalloc-64", 64}, {"kmalloc-128", 128}, + {"kmalloc-256", 256}, {"kmalloc-512", 512}, + {"kmalloc-1024", 1024}, {"kmalloc-2048", 2048}, + {"kmalloc-4096", 4096}, {"kmalloc-8192", 8192}, + {"kmalloc-16384", 16384}, {"kmalloc-32768", 32768}, + {"kmalloc-65536", 65536}, {"kmalloc-131072", 131072}, + {"kmalloc-262144", 262144}, {"kmalloc-524288", 524288}, + {"kmalloc-1048576", 1048576}, {"kmalloc-2097152", 2097152}, + {"kmalloc-4194304", 4194304}, {"kmalloc-8388608", 8388608}, + {"kmalloc-16777216", 16777216}, {"kmalloc-33554432", 33554432}, + {"kmalloc-67108864", 67108864} +}; + +/* + * Patch up the size_index table if we have strange large alignment + * requirements for the kmalloc array. This is only the case for + * MIPS it seems. The standard arches will not generate any code here. + * + * Largest permitted alignment is 256 bytes due to the way we + * handle the index determination for the smaller caches. + * + * Make sure that nothing crazy happens if someone starts tinkering + * around with ARCH_KMALLOC_MINALIGN + */ +void __init setup_kmalloc_cache_index_table(void) { int i; - /* - * Patch up the size_index table if we have strange large alignment - * requirements for the kmalloc array. This is only the case for - * MIPS it seems. The standard arches will not generate any code here. - * - * Largest permitted alignment is 256 bytes due to the way we - * handle the index determination for the smaller caches. - * - * Make sure that nothing crazy happens if someone starts tinkering - * around with ARCH_KMALLOC_MINALIGN - */ BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 || (KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1))); @@ -833,11 +852,26 @@ void __init create_kmalloc_caches(unsigned long flags) for (i = 128 + 8; i <= 192; i += 8) size_index[size_index_elem(i)] = 8; } +} + +static void __init new_kmalloc_cache(int idx, unsigned long flags) +{ + kmalloc_caches[idx] = create_kmalloc_cache(kmalloc_info[idx].name, + kmalloc_info[idx].size, flags); +} + +/* + * Create the kmalloc array. Some of the regular kmalloc arrays + * may already have been created because they were needed to + * enable allocations for slab creation. + */ +void __init create_kmalloc_caches(unsigned long flags) +{ + int i; + for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { - if (!kmalloc_caches[i]) { - kmalloc_caches[i] = create_kmalloc_cache(NULL, - 1 << i, flags); - } + if (!kmalloc_caches[i]) + new_kmalloc_cache(i, flags); /* * Caches that are not of the two-to-the-power-of size. @@ -845,27 +879,14 @@ void __init create_kmalloc_caches(unsigned long flags) * earlier power of two caches */ if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[1] && i == 6) - kmalloc_caches[1] = create_kmalloc_cache(NULL, 96, flags); - + new_kmalloc_cache(1, flags); if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[2] && i == 7) - kmalloc_caches[2] = create_kmalloc_cache(NULL, 192, flags); + new_kmalloc_cache(2, flags); } /* Kmalloc array is now usable */ slab_state = UP; - for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) { - struct kmem_cache *s = kmalloc_caches[i]; - char *n; - - if (s) { - n = kasprintf(GFP_NOWAIT, "kmalloc-%d", kmalloc_size(i)); - - BUG_ON(!n); - s->name = n; - } - } - #ifdef CONFIG_ZONE_DMA for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) { struct kmem_cache *s = kmalloc_caches[i]; diff --git a/mm/slub.c b/mm/slub.c index 54c0876b43d5..f68c0e50f3c0 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1427,7 +1427,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) inc_slabs_node(s, page_to_nid(page), page->objects); page->slab_cache = s; __SetPageSlab(page); - if (page->pfmemalloc) + if (page_is_pfmemalloc(page)) SetPageSlabPfmemalloc(page); start = page_address(page); @@ -3700,6 +3700,7 @@ void __init kmem_cache_init(void) kmem_cache_node = bootstrap(&boot_kmem_cache_node); /* Now we can use the kmem_cache to allocate kmalloc slabs */ + setup_kmalloc_cache_index_table(); create_kmalloc_caches(0); #ifdef CONFIG_SMP diff --git a/mm/swap.c b/mm/swap.c index a7251a8ed532..a3a0a2f1f7c3 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -131,7 +131,6 @@ void put_unrefcounted_compound_page(struct page *page_head, struct page *page) * here, see the comment above this function. */ VM_BUG_ON_PAGE(!PageHead(page_head), page_head); - VM_BUG_ON_PAGE(page_mapcount(page) != 0, page); if (put_page_testzero(page_head)) { /* * If this is the tail of a slab THP page, diff --git a/mm/swapfile.c b/mm/swapfile.c index a7e72103f23b..41e4581af7c5 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2032,7 +2032,7 @@ static int swap_show(struct seq_file *swap, void *v) } file = si->swap_file; - len = seq_path(swap, &file->f_path, " \t\n\\"); + len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%u\t%u\t%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? diff --git a/mm/truncate.c b/mm/truncate.c index 66af9031fae8..76e35ad97102 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -116,9 +116,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page) * the VM has canceled the dirty bit (eg ext3 journaling). * Hence dirty accounting check is placed after invalidation. */ - if (TestClearPageDirty(page)) - account_page_cleaned(page, mapping); - + cancel_dirty_page(page); ClearPageMappedToDisk(page); delete_from_page_cache(page); return 0; @@ -512,19 +510,24 @@ EXPORT_SYMBOL(invalidate_mapping_pages); static int invalidate_complete_page2(struct address_space *mapping, struct page *page) { + struct mem_cgroup *memcg; + unsigned long flags; + if (page->mapping != mapping) return 0; if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) return 0; - spin_lock_irq(&mapping->tree_lock); + memcg = mem_cgroup_begin_page_stat(page); + spin_lock_irqsave(&mapping->tree_lock, flags); if (PageDirty(page)) goto failed; BUG_ON(page_has_private(page)); - __delete_from_page_cache(page, NULL); - spin_unlock_irq(&mapping->tree_lock); + __delete_from_page_cache(page, NULL, memcg); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); if (mapping->a_ops->freepage) mapping->a_ops->freepage(page); @@ -532,7 +535,8 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) page_cache_release(page); /* pagecache ref */ return 1; failed: - spin_unlock_irq(&mapping->tree_lock); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); return 0; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 5e8eadd71bac..8286938c70de 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -154,11 +154,42 @@ static bool global_reclaim(struct scan_control *sc) { return !sc->target_mem_cgroup; } + +/** + * sane_reclaim - is the usual dirty throttling mechanism operational? + * @sc: scan_control in question + * + * The normal page dirty throttling mechanism in balance_dirty_pages() is + * completely broken with the legacy memcg and direct stalling in + * shrink_page_list() is used for throttling instead, which lacks all the + * niceties such as fairness, adaptive pausing, bandwidth proportional + * allocation and configurability. + * + * This function tests whether the vmscan currently in progress can assume + * that the normal dirty throttling mechanism is operational. + */ +static bool sane_reclaim(struct scan_control *sc) +{ + struct mem_cgroup *memcg = sc->target_mem_cgroup; + + if (!memcg) + return true; +#ifdef CONFIG_CGROUP_WRITEBACK + if (cgroup_on_dfl(mem_cgroup_css(memcg)->cgroup)) + return true; +#endif + return false; +} #else static bool global_reclaim(struct scan_control *sc) { return true; } + +static bool sane_reclaim(struct scan_control *sc) +{ + return true; +} #endif static unsigned long zone_reclaimable_pages(struct zone *zone) @@ -452,14 +483,13 @@ static inline int is_page_cache_freeable(struct page *page) return page_count(page) - page_has_private(page) == 2; } -static int may_write_to_queue(struct backing_dev_info *bdi, - struct scan_control *sc) +static int may_write_to_inode(struct inode *inode, struct scan_control *sc) { if (current->flags & PF_SWAPWRITE) return 1; - if (!bdi_write_congested(bdi)) + if (!inode_write_congested(inode)) return 1; - if (bdi == current->backing_dev_info) + if (inode_to_bdi(inode) == current->backing_dev_info) return 1; return 0; } @@ -538,7 +568,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; - if (!may_write_to_queue(inode_to_bdi(mapping->host), sc)) + if (!may_write_to_inode(mapping->host, sc)) return PAGE_KEEP; if (clear_page_dirty_for_io(page)) { @@ -579,10 +609,14 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, static int __remove_mapping(struct address_space *mapping, struct page *page, bool reclaimed) { + unsigned long flags; + struct mem_cgroup *memcg; + BUG_ON(!PageLocked(page)); BUG_ON(mapping != page_mapping(page)); - spin_lock_irq(&mapping->tree_lock); + memcg = mem_cgroup_begin_page_stat(page); + spin_lock_irqsave(&mapping->tree_lock, flags); /* * The non racy check for a busy page. * @@ -620,7 +654,8 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, swp_entry_t swap = { .val = page_private(page) }; mem_cgroup_swapout(page, swap); __delete_from_swap_cache(page); - spin_unlock_irq(&mapping->tree_lock); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); swapcache_free(swap); } else { void (*freepage)(struct page *); @@ -640,8 +675,9 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, if (reclaimed && page_is_file_cache(page) && !mapping_exiting(mapping)) shadow = workingset_eviction(mapping, page); - __delete_from_page_cache(page, shadow); - spin_unlock_irq(&mapping->tree_lock); + __delete_from_page_cache(page, shadow, memcg); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); if (freepage != NULL) freepage(page); @@ -650,7 +686,8 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, return 1; cannot_free: - spin_unlock_irq(&mapping->tree_lock); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); return 0; } @@ -917,7 +954,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, */ mapping = page_mapping(page); if (((dirty || writeback) && mapping && - bdi_write_congested(inode_to_bdi(mapping->host))) || + inode_write_congested(mapping->host)) || (writeback && PageReclaim(page))) nr_congested++; @@ -935,24 +972,20 @@ static unsigned long shrink_page_list(struct list_head *page_list, * note that the LRU is being scanned too quickly and the * caller can stall after page list has been processed. * - * 2) Global reclaim encounters a page, memcg encounters a - * page that is not marked for immediate reclaim or - * the caller does not have __GFP_IO. In this case mark - * the page for immediate reclaim and continue scanning. + * 2) Global or new memcg reclaim encounters a page that is + * not marked for immediate reclaim, or the caller does not + * have __GFP_FS (or __GFP_IO if it's simply going to swap, + * not to fs). In this case mark the page for immediate + * reclaim and continue scanning. * - * __GFP_IO is checked because a loop driver thread might + * Require may_enter_fs because we would wait on fs, which + * may not have submitted IO yet. And the loop driver might * enter reclaim, and deadlock if it waits on a page for * which it is needed to do the write (loop masks off * __GFP_IO|__GFP_FS for this reason); but more thought * would probably show more reasons. * - * Don't require __GFP_FS, since we're not going into the - * FS, just waiting on its writeback completion. Worryingly, - * ext4 gfs2 and xfs allocate pages with - * grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so testing - * may_enter_fs here is liable to OOM on them. - * - * 3) memcg encounters a page that is not already marked + * 3) Legacy memcg encounters a page that is not already marked * PageReclaim. memcg does not have any dirty pages * throttling so we could easily OOM just because too many * pages are in writeback and there is nothing else to @@ -967,8 +1000,8 @@ static unsigned long shrink_page_list(struct list_head *page_list, goto keep_locked; /* Case 2 above */ - } else if (global_reclaim(sc) || - !PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) { + } else if (sane_reclaim(sc) || + !PageReclaim(page) || !may_enter_fs) { /* * This is slightly racy - end_page_writeback() * might have just cleared PageReclaim, then @@ -1416,7 +1449,7 @@ static int too_many_isolated(struct zone *zone, int file, if (current_is_kswapd()) return 0; - if (!global_reclaim(sc)) + if (!sane_reclaim(sc)) return 0; if (file) { @@ -1608,10 +1641,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, set_bit(ZONE_WRITEBACK, &zone->flags); /* - * memcg will stall in page writeback so only consider forcibly - * stalling for global reclaim + * Legacy memcg will stall in page writeback so avoid forcibly + * stalling here. */ - if (global_reclaim(sc)) { + if (sane_reclaim(sc)) { /* * Tag a zone as congested if all the dirty pages scanned were * backed by a congested BDI and wait_iff_congested will stall. @@ -2646,7 +2679,8 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; - if (!populated_zone(zone)) + if (!populated_zone(zone) || + zone_reclaimable_pages(zone) == 0) continue; pfmemalloc_reserve += min_wmark_pages(zone); @@ -3596,7 +3630,7 @@ int zone_reclaim_mode __read_mostly; #define RECLAIM_OFF 0 #define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */ #define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */ -#define RECLAIM_SWAP (1<<2) /* Swap pages out during reclaim */ +#define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */ /* * Priority for ZONE_RECLAIM. This determines the fraction of pages @@ -3638,12 +3672,12 @@ static long zone_pagecache_reclaimable(struct zone *zone) long delta = 0; /* - * If RECLAIM_SWAP is set, then all file pages are considered + * If RECLAIM_UNMAP is set, then all file pages are considered * potentially reclaimable. Otherwise, we have to worry about * pages like swapcache and zone_unmapped_file_pages() provides * a better estimate */ - if (zone_reclaim_mode & RECLAIM_SWAP) + if (zone_reclaim_mode & RECLAIM_UNMAP) nr_pagecache_reclaimable = zone_page_state(zone, NR_FILE_PAGES); else nr_pagecache_reclaimable = zone_unmapped_file_pages(zone); @@ -3674,15 +3708,15 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) .order = order, .priority = ZONE_RECLAIM_PRIORITY, .may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE), - .may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP), + .may_unmap = !!(zone_reclaim_mode & RECLAIM_UNMAP), .may_swap = 1, }; cond_resched(); /* - * We need to be able to allocate from the reserves for RECLAIM_SWAP + * We need to be able to allocate from the reserves for RECLAIM_UNMAP * and we also need to be able to write out pages for RECLAIM_WRITE - * and RECLAIM_SWAP. + * and RECLAIM_UNMAP. */ p->flags |= PF_MEMALLOC | PF_SWAPWRITE; lockdep_set_current_reclaim_state(gfp_mask); diff --git a/mm/zbud.c b/mm/zbud.c index 2ee4e4520493..f3bf6f7627d8 100644 --- a/mm/zbud.c +++ b/mm/zbud.c @@ -97,6 +97,10 @@ struct zbud_pool { struct list_head lru; u64 pages_nr; struct zbud_ops *ops; +#ifdef CONFIG_ZPOOL + struct zpool *zpool; + struct zpool_ops *zpool_ops; +#endif }; /* @@ -123,7 +127,10 @@ struct zbud_header { static int zbud_zpool_evict(struct zbud_pool *pool, unsigned long handle) { - return zpool_evict(pool, handle); + if (pool->zpool && pool->zpool_ops && pool->zpool_ops->evict) + return pool->zpool_ops->evict(pool->zpool, handle); + else + return -ENOENT; } static struct zbud_ops zbud_zpool_ops = { @@ -131,9 +138,17 @@ static struct zbud_ops zbud_zpool_ops = { }; static void *zbud_zpool_create(char *name, gfp_t gfp, - struct zpool_ops *zpool_ops) + struct zpool_ops *zpool_ops, + struct zpool *zpool) { - return zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL); + struct zbud_pool *pool; + + pool = zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL); + if (pool) { + pool->zpool = zpool; + pool->zpool_ops = zpool_ops; + } + return pool; } static void zbud_zpool_destroy(void *pool) @@ -292,7 +307,7 @@ struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops) struct zbud_pool *pool; int i; - pool = kmalloc(sizeof(struct zbud_pool), gfp); + pool = kzalloc(sizeof(struct zbud_pool), gfp); if (!pool) return NULL; spin_lock_init(&pool->lock); diff --git a/mm/zpool.c b/mm/zpool.c index bacdab6e47de..722a4f60e90b 100644 --- a/mm/zpool.c +++ b/mm/zpool.c @@ -73,33 +73,6 @@ int zpool_unregister_driver(struct zpool_driver *driver) } EXPORT_SYMBOL(zpool_unregister_driver); -/** - * zpool_evict() - evict callback from a zpool implementation. - * @pool: pool to evict from. - * @handle: handle to evict. - * - * This can be used by zpool implementations to call the - * user's evict zpool_ops struct evict callback. - */ -int zpool_evict(void *pool, unsigned long handle) -{ - struct zpool *zpool; - - spin_lock(&pools_lock); - list_for_each_entry(zpool, &pools_head, list) { - if (zpool->pool == pool) { - spin_unlock(&pools_lock); - if (!zpool->ops || !zpool->ops->evict) - return -EINVAL; - return zpool->ops->evict(zpool, handle); - } - } - spin_unlock(&pools_lock); - - return -ENOENT; -} -EXPORT_SYMBOL(zpool_evict); - static struct zpool_driver *zpool_get_driver(char *type) { struct zpool_driver *driver; @@ -147,7 +120,7 @@ struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp, struct zpool_driver *driver; struct zpool *zpool; - pr_info("creating pool type %s\n", type); + pr_debug("creating pool type %s\n", type); driver = zpool_get_driver(type); @@ -170,7 +143,7 @@ struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp, zpool->type = driver->type; zpool->driver = driver; - zpool->pool = driver->create(name, gfp, ops); + zpool->pool = driver->create(name, gfp, ops, zpool); zpool->ops = ops; if (!zpool->pool) { @@ -180,7 +153,7 @@ struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp, return NULL; } - pr_info("created %s pool\n", type); + pr_debug("created pool type %s\n", type); spin_lock(&pools_lock); list_add(&zpool->list, &pools_head); @@ -202,7 +175,7 @@ struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp, */ void zpool_destroy_pool(struct zpool *zpool) { - pr_info("destroying pool type %s\n", zpool->type); + pr_debug("destroying pool type %s\n", zpool->type); spin_lock(&pools_lock); list_del(&zpool->list); diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 08bd7a3d464a..0a7f81aa2249 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -45,10 +45,6 @@ * */ -#ifdef CONFIG_ZSMALLOC_DEBUG -#define DEBUG -#endif - #include <linux/module.h> #include <linux/kernel.h> #include <linux/sched.h> @@ -289,7 +285,8 @@ static int create_handle_cache(struct zs_pool *pool) static void destroy_handle_cache(struct zs_pool *pool) { - kmem_cache_destroy(pool->handle_cachep); + if (pool->handle_cachep) + kmem_cache_destroy(pool->handle_cachep); } static unsigned long alloc_handle(struct zs_pool *pool) @@ -312,7 +309,8 @@ static void record_obj(unsigned long handle, unsigned long obj) #ifdef CONFIG_ZPOOL -static void *zs_zpool_create(char *name, gfp_t gfp, struct zpool_ops *zpool_ops) +static void *zs_zpool_create(char *name, gfp_t gfp, struct zpool_ops *zpool_ops, + struct zpool *zpool) { return zs_create_pool(name, gfp); } diff --git a/mm/zswap.c b/mm/zswap.c index 4249e82ff934..2d5727baed59 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -75,9 +75,10 @@ static u64 zswap_duplicate_entry; /********************************* * tunables **********************************/ -/* Enable/disable zswap (disabled by default, fixed at boot for now) */ -static bool zswap_enabled __read_mostly; -module_param_named(enabled, zswap_enabled, bool, 0444); + +/* Enable/disable zswap (disabled by default) */ +static bool zswap_enabled; +module_param_named(enabled, zswap_enabled, bool, 0644); /* Compressor to be used by zswap (fixed at boot for now) */ #define ZSWAP_COMPRESSOR_DEFAULT "lzo" @@ -648,7 +649,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, u8 *src, *dst; struct zswap_header *zhdr; - if (!tree) { + if (!zswap_enabled || !tree) { ret = -ENODEV; goto reject; } @@ -901,9 +902,6 @@ static int __init init_zswap(void) { gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN; - if (!zswap_enabled) - return 0; - pr_info("loading zswap\n"); zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp, |