diff options
Diffstat (limited to 'mm/vmscan.c')
| -rw-r--r-- | mm/vmscan.c | 1690 |
1 files changed, 1007 insertions, 683 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c index cbf84e152f0..0f16ffe8eb6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -11,6 +11,8 @@ * Multiqueue VM started 5.8.00, Rik van Riel. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/mm.h> #include <linux/module.h> #include <linux/gfp.h> @@ -19,6 +21,7 @@ #include <linux/pagemap.h> #include <linux/init.h> #include <linux/highmem.h> +#include <linux/vmpressure.h> #include <linux/vmstat.h> #include <linux/file.h> #include <linux/writeback.h> @@ -42,11 +45,13 @@ #include <linux/sysctl.h> #include <linux/oom.h> #include <linux/prefetch.h> +#include <linux/printk.h> #include <asm/tlbflush.h> #include <asm/div64.h> #include <linux/swapops.h> +#include <linux/balloon_compaction.h> #include "internal.h" @@ -81,6 +86,9 @@ struct scan_control { /* Scan (total_size >> priority) pages at once */ int priority; + /* anon vs. file LRUs scanning "ratio" */ + int swappiness; + /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. @@ -128,7 +136,7 @@ struct scan_control { * From 0 .. 100. Higher means more swappy. */ int vm_swappiness = 60; -long vm_total_pages; /* The total number of pages which the VM controls */ +unsigned long vm_total_pages; /* The total number of pages which the VM controls */ static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); @@ -145,6 +153,25 @@ static bool global_reclaim(struct scan_control *sc) } #endif +static unsigned long zone_reclaimable_pages(struct zone *zone) +{ + int nr; + + nr = zone_page_state(zone, NR_ACTIVE_FILE) + + zone_page_state(zone, NR_INACTIVE_FILE); + + if (get_nr_swap_pages() > 0) + nr += zone_page_state(zone, NR_ACTIVE_ANON) + + zone_page_state(zone, NR_INACTIVE_ANON); + + return nr; +} + +bool zone_reclaimable(struct zone *zone) +{ + return zone->pages_scanned < zone_reclaimable_pages(zone) * 6; +} + static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru) { if (!mem_cgroup_disabled()) @@ -154,14 +181,31 @@ static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru) } /* - * Add a shrinker callback to be called from the vm + * Add a shrinker callback to be called from the vm. */ -void register_shrinker(struct shrinker *shrinker) +int register_shrinker(struct shrinker *shrinker) { - atomic_long_set(&shrinker->nr_in_batch, 0); + size_t size = sizeof(*shrinker->nr_deferred); + + /* + * If we only have one possible node in the system anyway, save + * ourselves the trouble and disable NUMA aware behavior. This way we + * will save memory and some small loop time later. + */ + if (nr_node_ids == 1) + shrinker->flags &= ~SHRINKER_NUMA_AWARE; + + if (shrinker->flags & SHRINKER_NUMA_AWARE) + size *= nr_node_ids; + + shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); + if (!shrinker->nr_deferred) + return -ENOMEM; + down_write(&shrinker_rwsem); list_add_tail(&shrinker->list, &shrinker_list); up_write(&shrinker_rwsem); + return 0; } EXPORT_SYMBOL(register_shrinker); @@ -173,18 +217,123 @@ void unregister_shrinker(struct shrinker *shrinker) down_write(&shrinker_rwsem); list_del(&shrinker->list); up_write(&shrinker_rwsem); + kfree(shrinker->nr_deferred); } EXPORT_SYMBOL(unregister_shrinker); -static inline int do_shrinker_shrink(struct shrinker *shrinker, - struct shrink_control *sc, - unsigned long nr_to_scan) -{ - sc->nr_to_scan = nr_to_scan; - return (*shrinker->shrink)(shrinker, sc); +#define SHRINK_BATCH 128 + +static unsigned long +shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, + unsigned long nr_pages_scanned, unsigned long lru_pages) +{ + unsigned long freed = 0; + unsigned long long delta; + long total_scan; + long freeable; + long nr; + long new_nr; + int nid = shrinkctl->nid; + long batch_size = shrinker->batch ? shrinker->batch + : SHRINK_BATCH; + + freeable = shrinker->count_objects(shrinker, shrinkctl); + if (freeable == 0) + return 0; + + /* + * copy the current shrinker scan count into a local variable + * and zero it so that other concurrent shrinker invocations + * don't also do this scanning work. + */ + nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0); + + total_scan = nr; + delta = (4 * nr_pages_scanned) / shrinker->seeks; + delta *= freeable; + do_div(delta, lru_pages + 1); + total_scan += delta; + if (total_scan < 0) { + printk(KERN_ERR + "shrink_slab: %pF negative objects to delete nr=%ld\n", + shrinker->scan_objects, total_scan); + total_scan = freeable; + } + + /* + * We need to avoid excessive windup on filesystem shrinkers + * due to large numbers of GFP_NOFS allocations causing the + * shrinkers to return -1 all the time. This results in a large + * nr being built up so when a shrink that can do some work + * comes along it empties the entire cache due to nr >>> + * freeable. This is bad for sustaining a working set in + * memory. + * + * Hence only allow the shrinker to scan the entire cache when + * a large delta change is calculated directly. + */ + if (delta < freeable / 4) + total_scan = min(total_scan, freeable / 2); + + /* + * Avoid risking looping forever due to too large nr value: + * never try to free more than twice the estimate number of + * freeable entries. + */ + if (total_scan > freeable * 2) + total_scan = freeable * 2; + + trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, + nr_pages_scanned, lru_pages, + freeable, delta, total_scan); + + /* + * Normally, we should not scan less than batch_size objects in one + * pass to avoid too frequent shrinker calls, but if the slab has less + * than batch_size objects in total and we are really tight on memory, + * we will try to reclaim all available objects, otherwise we can end + * up failing allocations although there are plenty of reclaimable + * objects spread over several slabs with usage less than the + * batch_size. + * + * We detect the "tight on memory" situations by looking at the total + * number of objects we want to scan (total_scan). If it is greater + * than the total number of objects on slab (freeable), we must be + * scanning at high prio and therefore should try to reclaim as much as + * possible. + */ + while (total_scan >= batch_size || + total_scan >= freeable) { + unsigned long ret; + unsigned long nr_to_scan = min(batch_size, total_scan); + + shrinkctl->nr_to_scan = nr_to_scan; + ret = shrinker->scan_objects(shrinker, shrinkctl); + if (ret == SHRINK_STOP) + break; + freed += ret; + + count_vm_events(SLABS_SCANNED, nr_to_scan); + total_scan -= nr_to_scan; + + cond_resched(); + } + + /* + * move the unused scan count back into the shrinker in a + * manner that handles concurrent updates. If we exhausted the + * scan, there is no need to do an update. + */ + if (total_scan > 0) + new_nr = atomic_long_add_return(total_scan, + &shrinker->nr_deferred[nid]); + else + new_nr = atomic_long_read(&shrinker->nr_deferred[nid]); + + trace_mm_shrink_slab_end(shrinker, nid, freed, nr, new_nr, total_scan); + return freed; } -#define SHRINK_BATCH 128 /* * Call the shrink functions to age shrinkable caches * @@ -204,115 +353,46 @@ static inline int do_shrinker_shrink(struct shrinker *shrinker, * * Returns the number of slab objects which we shrunk. */ -unsigned long shrink_slab(struct shrink_control *shrink, +unsigned long shrink_slab(struct shrink_control *shrinkctl, unsigned long nr_pages_scanned, unsigned long lru_pages) { struct shrinker *shrinker; - unsigned long ret = 0; + unsigned long freed = 0; if (nr_pages_scanned == 0) nr_pages_scanned = SWAP_CLUSTER_MAX; if (!down_read_trylock(&shrinker_rwsem)) { - /* Assume we'll be able to shrink next time */ - ret = 1; + /* + * If we would return 0, our callers would understand that we + * have nothing else to shrink and give up trying. By returning + * 1 we keep it going and assume we'll be able to shrink next + * time. + */ + freed = 1; goto out; } list_for_each_entry(shrinker, &shrinker_list, list) { - unsigned long long delta; - long total_scan; - long max_pass; - int shrink_ret = 0; - long nr; - long new_nr; - long batch_size = shrinker->batch ? shrinker->batch - : SHRINK_BATCH; - - max_pass = do_shrinker_shrink(shrinker, shrink, 0); - if (max_pass <= 0) + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) { + shrinkctl->nid = 0; + freed += shrink_slab_node(shrinkctl, shrinker, + nr_pages_scanned, lru_pages); continue; - - /* - * copy the current shrinker scan count into a local variable - * and zero it so that other concurrent shrinker invocations - * don't also do this scanning work. - */ - nr = atomic_long_xchg(&shrinker->nr_in_batch, 0); - - total_scan = nr; - delta = (4 * nr_pages_scanned) / shrinker->seeks; - delta *= max_pass; - do_div(delta, lru_pages + 1); - total_scan += delta; - if (total_scan < 0) { - printk(KERN_ERR "shrink_slab: %pF negative objects to " - "delete nr=%ld\n", - shrinker->shrink, total_scan); - total_scan = max_pass; } - /* - * We need to avoid excessive windup on filesystem shrinkers - * due to large numbers of GFP_NOFS allocations causing the - * shrinkers to return -1 all the time. This results in a large - * nr being built up so when a shrink that can do some work - * comes along it empties the entire cache due to nr >>> - * max_pass. This is bad for sustaining a working set in - * memory. - * - * Hence only allow the shrinker to scan the entire cache when - * a large delta change is calculated directly. - */ - if (delta < max_pass / 4) - total_scan = min(total_scan, max_pass / 2); - - /* - * Avoid risking looping forever due to too large nr value: - * never try to free more than twice the estimate number of - * freeable entries. - */ - if (total_scan > max_pass * 2) - total_scan = max_pass * 2; - - trace_mm_shrink_slab_start(shrinker, shrink, nr, - nr_pages_scanned, lru_pages, - max_pass, delta, total_scan); - - while (total_scan >= batch_size) { - int nr_before; - - nr_before = do_shrinker_shrink(shrinker, shrink, 0); - shrink_ret = do_shrinker_shrink(shrinker, shrink, - batch_size); - if (shrink_ret == -1) - break; - if (shrink_ret < nr_before) - ret += nr_before - shrink_ret; - count_vm_events(SLABS_SCANNED, batch_size); - total_scan -= batch_size; + for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) { + if (node_online(shrinkctl->nid)) + freed += shrink_slab_node(shrinkctl, shrinker, + nr_pages_scanned, lru_pages); - cond_resched(); } - - /* - * move the unused scan count back into the shrinker in a - * manner that handles concurrent updates. If we exhausted the - * scan, there is no need to do an update. - */ - if (total_scan > 0) - new_nr = atomic_long_add_return(total_scan, - &shrinker->nr_in_batch); - else - new_nr = atomic_long_read(&shrinker->nr_in_batch); - - trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr); } up_read(&shrinker_rwsem); out: cond_resched(); - return ret; + return freed; } static inline int is_page_cache_freeable(struct page *page) @@ -384,7 +464,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, * stalls if we need to run get_block(). We could test * PagePrivate for that. * - * If this process is currently in __generic_file_aio_write() against + * If this process is currently in __generic_file_write_iter() against * this page's queue, we can perform writeback even if that * will block. * @@ -403,7 +483,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, if (page_has_private(page)) { if (try_to_free_buffers(page)) { ClearPageDirty(page); - printk("%s: orphaned page\n", __func__); + pr_info("%s: orphaned page\n", __func__); return PAGE_CLEAN; } } @@ -449,7 +529,8 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, * Same as remove_mapping, but if the page is removed from the mapping, it * gets returned with a refcount of 0. */ -static int __remove_mapping(struct address_space *mapping, struct page *page) +static int __remove_mapping(struct address_space *mapping, struct page *page, + bool reclaimed) { BUG_ON(!PageLocked(page)); BUG_ON(mapping != page_mapping(page)); @@ -495,10 +576,23 @@ static int __remove_mapping(struct address_space *mapping, struct page *page) swapcache_free(swap, page); } else { void (*freepage)(struct page *); + void *shadow = NULL; freepage = mapping->a_ops->freepage; - - __delete_from_page_cache(page); + /* + * Remember a shadow entry for reclaimed file cache in + * order to detect refaults, thus thrashing, later on. + * + * But don't store shadows in an address space that is + * already exiting. This is not just an optizimation, + * inode reclaim needs to empty out the radix tree or + * the nodes are lost. Don't plant shadows behind its + * back. + */ + 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); mem_cgroup_uncharge_cache_page(page); @@ -521,7 +615,7 @@ cannot_free: */ int remove_mapping(struct address_space *mapping, struct page *page) { - if (__remove_mapping(mapping, page)) { + if (__remove_mapping(mapping, page, false)) { /* * Unfreezing the refcount with 1 rather than 2 effectively * drops the pagecache ref for us without requiring another @@ -544,11 +638,10 @@ int remove_mapping(struct address_space *mapping, struct page *page) */ void putback_lru_page(struct page *page) { - int lru; - int active = !!TestClearPageActive(page); + bool is_unevictable; int was_unevictable = PageUnevictable(page); - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); redo: ClearPageUnevictable(page); @@ -560,14 +653,14 @@ redo: * unevictable page on [in]active list. * We know how to handle that. */ - lru = active + page_lru_base_type(page); - lru_cache_add_lru(page, lru); + is_unevictable = false; + lru_cache_add(page); } else { /* * Put unevictable pages directly on zone's unevictable * list. */ - lru = LRU_UNEVICTABLE; + is_unevictable = true; add_page_to_unevictable_list(page); /* * When racing with an mlock or AS_UNEVICTABLE clearing @@ -587,7 +680,7 @@ redo: * page is on unevictable list, it never be freed. To avoid that, * check after we added it to the list, again. */ - if (lru == LRU_UNEVICTABLE && page_evictable(page)) { + if (is_unevictable && page_evictable(page)) { if (!isolate_lru_page(page)) { put_page(page); goto redo; @@ -598,9 +691,9 @@ redo: */ } - if (was_unevictable && lru != LRU_UNEVICTABLE) + if (was_unevictable && !is_unevictable) count_vm_event(UNEVICTABLE_PGRESCUED); - else if (!was_unevictable && lru == LRU_UNEVICTABLE) + else if (!was_unevictable && is_unevictable) count_vm_event(UNEVICTABLE_PGCULLED); put_page(page); /* drop ref from isolate */ @@ -668,6 +761,35 @@ static enum page_references page_check_references(struct page *page, return PAGEREF_RECLAIM; } +/* Check if a page is dirty or under writeback */ +static void page_check_dirty_writeback(struct page *page, + bool *dirty, bool *writeback) +{ + struct address_space *mapping; + + /* + * Anonymous pages are not handled by flushers and must be written + * from reclaim context. Do not stall reclaim based on them + */ + if (!page_is_file_cache(page)) { + *dirty = false; + *writeback = false; + return; + } + + /* By default assume that the page flags are accurate */ + *dirty = PageDirty(page); + *writeback = PageWriteback(page); + + /* Verify dirty/writeback state if the filesystem supports it */ + if (!page_has_private(page)) + return; + + mapping = page_mapping(page); + if (mapping && mapping->a_ops->is_dirty_writeback) + mapping->a_ops->is_dirty_writeback(page, dirty, writeback); +} + /* * shrink_page_list() returns the number of reclaimed pages */ @@ -676,16 +798,21 @@ static unsigned long shrink_page_list(struct list_head *page_list, struct scan_control *sc, enum ttu_flags ttu_flags, unsigned long *ret_nr_dirty, + unsigned long *ret_nr_unqueued_dirty, + unsigned long *ret_nr_congested, unsigned long *ret_nr_writeback, + unsigned long *ret_nr_immediate, bool force_reclaim) { LIST_HEAD(ret_pages); LIST_HEAD(free_pages); int pgactivate = 0; + unsigned long nr_unqueued_dirty = 0; unsigned long nr_dirty = 0; unsigned long nr_congested = 0; unsigned long nr_reclaimed = 0; unsigned long nr_writeback = 0; + unsigned long nr_immediate = 0; cond_resched(); @@ -695,6 +822,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, struct page *page; int may_enter_fs; enum page_references references = PAGEREF_RECLAIM_CLEAN; + bool dirty, writeback; cond_resched(); @@ -704,8 +832,8 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (!trylock_page(page)) goto keep; - VM_BUG_ON(PageActive(page)); - VM_BUG_ON(page_zone(page) != zone); + VM_BUG_ON_PAGE(PageActive(page), page); + VM_BUG_ON_PAGE(page_zone(page) != zone, page); sc->nr_scanned++; @@ -722,25 +850,77 @@ static unsigned long shrink_page_list(struct list_head *page_list, may_enter_fs = (sc->gfp_mask & __GFP_FS) || (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO)); + /* + * The number of dirty pages determines if a zone is marked + * reclaim_congested which affects wait_iff_congested. kswapd + * will stall and start writing pages if the tail of the LRU + * is all dirty unqueued pages. + */ + page_check_dirty_writeback(page, &dirty, &writeback); + if (dirty || writeback) + nr_dirty++; + + if (dirty && !writeback) + nr_unqueued_dirty++; + + /* + * Treat this page as congested if the underlying BDI is or if + * pages are cycling through the LRU so quickly that the + * pages marked for immediate reclaim are making it to the + * end of the LRU a second time. + */ + mapping = page_mapping(page); + if ((mapping && bdi_write_congested(mapping->backing_dev_info)) || + (writeback && PageReclaim(page))) + nr_congested++; + + /* + * If a page at the tail of the LRU is under writeback, there + * are three cases to consider. + * + * 1) If reclaim is encountering an excessive number of pages + * under writeback and this page is both under writeback and + * PageReclaim then it indicates that pages are being queued + * for IO but are being recycled through the LRU before the + * IO can complete. Waiting on the page itself risks an + * indefinite stall if it is impossible to writeback the + * page due to IO error or disconnected storage so instead + * 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. + * + * __GFP_IO is checked because a loop driver thread 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 + * 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 + * reclaim. Wait for the writeback to complete. + */ if (PageWriteback(page)) { - /* - * memcg doesn't have any dirty pages throttling so we - * could easily OOM just because too many pages are in - * writeback and there is nothing else to reclaim. - * - * Check __GFP_IO, certainly because a loop driver - * thread 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. - */ - if (global_reclaim(sc) || + /* Case 1 above */ + if (current_is_kswapd() && + PageReclaim(page) && + zone_is_reclaim_writeback(zone)) { + nr_immediate++; + goto keep_locked; + + /* Case 2 above */ + } else if (global_reclaim(sc) || !PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) { /* * This is slightly racy - end_page_writeback() @@ -755,9 +935,13 @@ static unsigned long shrink_page_list(struct list_head *page_list, */ SetPageReclaim(page); nr_writeback++; + goto keep_locked; + + /* Case 3 above */ + } else { + wait_on_page_writeback(page); } - wait_on_page_writeback(page); } if (!force_reclaim) @@ -780,12 +964,13 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (PageAnon(page) && !PageSwapCache(page)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; - if (!add_to_swap(page)) + if (!add_to_swap(page, page_list)) goto activate_locked; may_enter_fs = 1; - } - mapping = page_mapping(page); + /* Adding to swap updated mapping */ + mapping = page_mapping(page); + } /* * The page is mapped into the page tables of one or more @@ -805,16 +990,14 @@ static unsigned long shrink_page_list(struct list_head *page_list, } if (PageDirty(page)) { - nr_dirty++; - /* * Only kswapd can writeback filesystem pages to - * avoid risk of stack overflow but do not writeback - * unless under significant pressure. + * avoid risk of stack overflow but only writeback + * if many dirty pages have been encountered. */ if (page_is_file_cache(page) && (!current_is_kswapd() || - sc->priority >= DEF_PRIORITY - 2)) { + !zone_is_reclaim_dirty(zone))) { /* * Immediately reclaim when written back. * Similar in principal to deactivate_page() @@ -837,7 +1020,6 @@ static unsigned long shrink_page_list(struct list_head *page_list, /* Page is dirty, try to write it out here */ switch (pageout(page, mapping, sc)) { case PAGE_KEEP: - nr_congested++; goto keep_locked; case PAGE_ACTIVATE: goto activate_locked; @@ -903,7 +1085,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, } } - if (!mapping || !__remove_mapping(mapping, page)) + if (!mapping || !__remove_mapping(mapping, page, true)) goto keep_locked; /* @@ -935,32 +1117,26 @@ activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ if (PageSwapCache(page) && vm_swap_full()) try_to_free_swap(page); - VM_BUG_ON(PageActive(page)); + VM_BUG_ON_PAGE(PageActive(page), page); SetPageActive(page); pgactivate++; keep_locked: unlock_page(page); keep: list_add(&page->lru, &ret_pages); - VM_BUG_ON(PageLRU(page) || PageUnevictable(page)); + VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); } - /* - * Tag a zone as congested if all the dirty pages encountered were - * backed by a congested BDI. In this case, reclaimers should just - * back off and wait for congestion to clear because further reclaim - * will encounter the same problem - */ - if (nr_dirty && nr_dirty == nr_congested && global_reclaim(sc)) - zone_set_flag(zone, ZONE_CONGESTED); - - free_hot_cold_page_list(&free_pages, 1); + free_hot_cold_page_list(&free_pages, true); list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); mem_cgroup_uncharge_end(); *ret_nr_dirty += nr_dirty; + *ret_nr_congested += nr_congested; + *ret_nr_unqueued_dirty += nr_unqueued_dirty; *ret_nr_writeback += nr_writeback; + *ret_nr_immediate += nr_immediate; return nr_reclaimed; } @@ -972,22 +1148,23 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, .priority = DEF_PRIORITY, .may_unmap = 1, }; - unsigned long ret, dummy1, dummy2; + unsigned long ret, dummy1, dummy2, dummy3, dummy4, dummy5; struct page *page, *next; LIST_HEAD(clean_pages); list_for_each_entry_safe(page, next, page_list, lru) { - if (page_is_file_cache(page) && !PageDirty(page)) { + if (page_is_file_cache(page) && !PageDirty(page) && + !isolated_balloon_page(page)) { ClearPageActive(page); list_move(&page->lru, &clean_pages); } } ret = shrink_page_list(&clean_pages, zone, &sc, - TTU_UNMAP|TTU_IGNORE_ACCESS, - &dummy1, &dummy2, true); + TTU_UNMAP|TTU_IGNORE_ACCESS, + &dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true); list_splice(&clean_pages, page_list); - __mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret); + mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret); return ret; } @@ -1101,7 +1278,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, page = lru_to_page(src); prefetchw_prev_lru_page(page, src, flags); - VM_BUG_ON(!PageLRU(page)); + VM_BUG_ON_PAGE(!PageLRU(page), page); switch (__isolate_lru_page(page, mode)) { case 0: @@ -1156,7 +1333,7 @@ int isolate_lru_page(struct page *page) { int ret = -EBUSY; - VM_BUG_ON(!page_count(page)); + VM_BUG_ON_PAGE(!page_count(page), page); if (PageLRU(page)) { struct zone *zone = page_zone(page); @@ -1177,7 +1354,11 @@ int isolate_lru_page(struct page *page) } /* - * Are there way too many processes in the direct reclaim path already? + * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and + * then get resheduled. When there are massive number of tasks doing page + * allocation, such sleeping direct reclaimers may keep piling up on each CPU, + * the LRU list will go small and be scanned faster than necessary, leading to + * unnecessary swapping, thrashing and OOM. */ static int too_many_isolated(struct zone *zone, int file, struct scan_control *sc) @@ -1198,6 +1379,14 @@ static int too_many_isolated(struct zone *zone, int file, isolated = zone_page_state(zone, NR_ISOLATED_ANON); } + /* + * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they + * won't get blocked by normal direct-reclaimers, forming a circular + * deadlock. + */ + if ((sc->gfp_mask & GFP_IOFS) == GFP_IOFS) + inactive >>= 3; + return isolated > inactive; } @@ -1215,7 +1404,7 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) struct page *page = lru_to_page(page_list); int lru; - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); list_del(&page->lru); if (unlikely(!page_evictable(page))) { spin_unlock_irq(&zone->lru_lock); @@ -1256,6 +1445,19 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) } /* + * If a kernel thread (such as nfsd for loop-back mounts) services + * a backing device by writing to the page cache it sets PF_LESS_THROTTLE. + * In that case we should only throttle if the backing device it is + * writing to is congested. In other cases it is safe to throttle. + */ +static int current_may_throttle(void) +{ + return !(current->flags & PF_LESS_THROTTLE) || + current->backing_dev_info == NULL || + bdi_write_congested(current->backing_dev_info); +} + +/* * shrink_inactive_list() is a helper for shrink_zone(). It returns the number * of reclaimed pages */ @@ -1268,7 +1470,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, unsigned long nr_reclaimed = 0; unsigned long nr_taken; unsigned long nr_dirty = 0; + unsigned long nr_congested = 0; + unsigned long nr_unqueued_dirty = 0; unsigned long nr_writeback = 0; + unsigned long nr_immediate = 0; isolate_mode_t isolate_mode = 0; int file = is_file_lru(lru); struct zone *zone = lruvec_zone(lruvec); @@ -1310,7 +1515,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, return 0; nr_reclaimed = shrink_page_list(&page_list, zone, sc, TTU_UNMAP, - &nr_dirty, &nr_writeback, false); + &nr_dirty, &nr_unqueued_dirty, &nr_congested, + &nr_writeback, &nr_immediate, + false); spin_lock_irq(&zone->lru_lock); @@ -1331,7 +1538,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, spin_unlock_irq(&zone->lru_lock); - free_hot_cold_page_list(&page_list, 1); + free_hot_cold_page_list(&page_list, true); /* * If reclaim is isolating dirty pages under writeback, it implies @@ -1343,21 +1550,51 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * as there is no guarantee the dirtying process is throttled in the * same way balance_dirty_pages() manages. * - * This scales the number of dirty pages that must be under writeback - * before throttling depending on priority. It is a simple backoff - * function that has the most effect in the range DEF_PRIORITY to - * DEF_PRIORITY-2 which is the priority reclaim is considered to be - * in trouble and reclaim is considered to be in trouble. - * - * DEF_PRIORITY 100% isolated pages must be PageWriteback to throttle - * DEF_PRIORITY-1 50% must be PageWriteback - * DEF_PRIORITY-2 25% must be PageWriteback, kswapd in trouble - * ... - * DEF_PRIORITY-6 For SWAP_CLUSTER_MAX isolated pages, throttle if any - * isolated page is PageWriteback + * Once a zone is flagged ZONE_WRITEBACK, kswapd will count the number + * of pages under pages flagged for immediate reclaim and stall if any + * are encountered in the nr_immediate check below. + */ + if (nr_writeback && nr_writeback == nr_taken) + zone_set_flag(zone, ZONE_WRITEBACK); + + /* + * memcg will stall in page writeback so only consider forcibly + * stalling for global reclaim + */ + if (global_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. + */ + if (nr_dirty && nr_dirty == nr_congested) + zone_set_flag(zone, ZONE_CONGESTED); + + /* + * If dirty pages are scanned that are not queued for IO, it + * implies that flushers are not keeping up. In this case, flag + * the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing + * pages from reclaim context. + */ + if (nr_unqueued_dirty == nr_taken) + zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY); + + /* + * If kswapd scans pages marked marked for immediate + * reclaim and under writeback (nr_immediate), it implies + * that pages are cycling through the LRU faster than + * they are written so also forcibly stall. + */ + if (nr_immediate && current_may_throttle()) + congestion_wait(BLK_RW_ASYNC, HZ/10); + } + + /* + * Stall direct reclaim for IO completions if underlying BDIs or zone + * is congested. Allow kswapd to continue until it starts encountering + * unqueued dirty pages or cycling through the LRU too quickly. */ - if (nr_writeback && nr_writeback >= - (nr_taken >> (DEF_PRIORITY - sc->priority))) + if (!sc->hibernation_mode && !current_is_kswapd() && + current_may_throttle()) wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10); trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id, @@ -1400,7 +1637,7 @@ static void move_active_pages_to_lru(struct lruvec *lruvec, page = lru_to_page(list); lruvec = mem_cgroup_page_lruvec(page, zone); - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); SetPageLRU(page); nr_pages = hpage_nr_pages(page); @@ -1522,7 +1759,7 @@ static void shrink_active_list(unsigned long nr_to_scan, __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&zone->lru_lock); - free_hot_cold_page_list(&l_hold, 1); + free_hot_cold_page_list(&l_hold, true); } #ifdef CONFIG_SWAP @@ -1567,16 +1804,6 @@ static inline int inactive_anon_is_low(struct lruvec *lruvec) } #endif -static int inactive_file_is_low_global(struct zone *zone) -{ - unsigned long active, inactive; - - active = zone_page_state(zone, NR_ACTIVE_FILE); - inactive = zone_page_state(zone, NR_INACTIVE_FILE); - - return (active > inactive); -} - /** * inactive_file_is_low - check if file pages need to be deactivated * @lruvec: LRU vector to check @@ -1593,10 +1820,13 @@ static int inactive_file_is_low_global(struct zone *zone) */ static int inactive_file_is_low(struct lruvec *lruvec) { - if (!mem_cgroup_disabled()) - return mem_cgroup_inactive_file_is_low(lruvec); + unsigned long inactive; + unsigned long active; + + inactive = get_lru_size(lruvec, LRU_INACTIVE_FILE); + active = get_lru_size(lruvec, LRU_ACTIVE_FILE); - return inactive_file_is_low_global(lruvec_zone(lruvec)); + return active > inactive; } static int inactive_list_is_low(struct lruvec *lruvec, enum lru_list lru) @@ -1619,12 +1849,12 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } -static int vmscan_swappiness(struct scan_control *sc) -{ - if (global_reclaim(sc)) - return vm_swappiness; - return mem_cgroup_swappiness(sc->target_mem_cgroup); -} +enum scan_balance { + SCAN_EQUAL, + SCAN_FRACT, + SCAN_ANON, + SCAN_FILE, +}; /* * Determine how aggressively the anon and file LRU lists should be @@ -1638,15 +1868,18 @@ static int vmscan_swappiness(struct scan_control *sc) static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) { - unsigned long anon, file, free; + struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; + u64 fraction[2]; + u64 denominator = 0; /* gcc */ + struct zone *zone = lruvec_zone(lruvec); unsigned long anon_prio, file_prio; + enum scan_balance scan_balance; + unsigned long anon, file; + bool force_scan = false; unsigned long ap, fp; - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; - u64 fraction[2], denominator; enum lru_list lru; - int noswap = 0; - bool force_scan = false; - struct zone *zone = lruvec_zone(lruvec); + bool some_scanned; + int pass; /* * If the zone or memcg is small, nr[l] can be 0. This @@ -1658,17 +1891,36 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * latencies, so it's better to scan a minimum amount there as * well. */ - if (current_is_kswapd() && zone->all_unreclaimable) + if (current_is_kswapd() && !zone_reclaimable(zone)) force_scan = true; if (!global_reclaim(sc)) force_scan = true; /* If we have no swap space, do not bother scanning anon pages. */ - if (!sc->may_swap || (nr_swap_pages <= 0)) { - noswap = 1; - fraction[0] = 0; - fraction[1] = 1; - denominator = 1; + if (!sc->may_swap || (get_nr_swap_pages() <= 0)) { + scan_balance = SCAN_FILE; + goto out; + } + + /* + * Global reclaim will swap to prevent OOM even with no + * swappiness, but memcg users want to use this knob to + * disable swapping for individual groups completely when + * using the memory controller's swap limit feature would be + * too expensive. + */ + if (!global_reclaim(sc) && !sc->swappiness) { + scan_balance = SCAN_FILE; + goto out; + } + + /* + * Do not apply any pressure balancing cleverness when the + * system is close to OOM, scan both anon and file equally + * (unless the swappiness setting disagrees with swapping). + */ + if (!sc->priority && sc->swappiness) { + scan_balance = SCAN_EQUAL; goto out; } @@ -1677,23 +1929,40 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, file = get_lru_size(lruvec, LRU_ACTIVE_FILE) + get_lru_size(lruvec, LRU_INACTIVE_FILE); + /* + * Prevent the reclaimer from falling into the cache trap: as + * cache pages start out inactive, every cache fault will tip + * the scan balance towards the file LRU. And as the file LRU + * shrinks, so does the window for rotation from references. + * This means we have a runaway feedback loop where a tiny + * thrashing file LRU becomes infinitely more attractive than + * anon pages. Try to detect this based on file LRU size. + */ if (global_reclaim(sc)) { - free = zone_page_state(zone, NR_FREE_PAGES); - /* If we have very few page cache pages, - force-scan anon pages. */ + unsigned long free = zone_page_state(zone, NR_FREE_PAGES); + if (unlikely(file + free <= high_wmark_pages(zone))) { - fraction[0] = 1; - fraction[1] = 0; - denominator = 1; + scan_balance = SCAN_ANON; goto out; } } /* + * There is enough inactive page cache, do not reclaim + * anything from the anonymous working set right now. + */ + if (!inactive_file_is_low(lruvec)) { + scan_balance = SCAN_FILE; + goto out; + } + + scan_balance = SCAN_FRACT; + + /* * With swappiness at 100, anonymous and file have the same priority. * This scanning priority is essentially the inverse of IO cost. */ - anon_prio = vmscan_swappiness(sc); + anon_prio = sc->swappiness; file_prio = 200 - anon_prio; /* @@ -1734,25 +2003,173 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, fraction[1] = fp; denominator = ap + fp + 1; out: - for_each_evictable_lru(lru) { - int file = is_file_lru(lru); - unsigned long scan; - - scan = get_lru_size(lruvec, lru); - if (sc->priority || noswap || !vmscan_swappiness(sc)) { - scan >>= sc->priority; - if (!scan && force_scan) - scan = SWAP_CLUSTER_MAX; - scan = div64_u64(scan * fraction[file], denominator); + some_scanned = false; + /* Only use force_scan on second pass. */ + for (pass = 0; !some_scanned && pass < 2; pass++) { + for_each_evictable_lru(lru) { + int file = is_file_lru(lru); + unsigned long size; + unsigned long scan; + + size = get_lru_size(lruvec, lru); + scan = size >> sc->priority; + + if (!scan && pass && force_scan) + scan = min(size, SWAP_CLUSTER_MAX); + + switch (scan_balance) { + case SCAN_EQUAL: + /* Scan lists relative to size */ + break; + case SCAN_FRACT: + /* + * Scan types proportional to swappiness and + * their relative recent reclaim efficiency. + */ + scan = div64_u64(scan * fraction[file], + denominator); + break; + case SCAN_FILE: + case SCAN_ANON: + /* Scan one type exclusively */ + if ((scan_balance == SCAN_FILE) != file) + scan = 0; + break; + default: + /* Look ma, no brain */ + BUG(); + } + nr[lru] = scan; + /* + * Skip the second pass and don't force_scan, + * if we found something to scan. + */ + some_scanned |= !!scan; } - nr[lru] = scan; } } +/* + * This is a basic per-zone page freer. Used by both kswapd and direct reclaim. + */ +static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) +{ + unsigned long nr[NR_LRU_LISTS]; + unsigned long targets[NR_LRU_LISTS]; + unsigned long nr_to_scan; + enum lru_list lru; + unsigned long nr_reclaimed = 0; + unsigned long nr_to_reclaim = sc->nr_to_reclaim; + struct blk_plug plug; + bool scan_adjusted; + + get_scan_count(lruvec, sc, nr); + + /* Record the original scan target for proportional adjustments later */ + memcpy(targets, nr, sizeof(nr)); + + /* + * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal + * event that can occur when there is little memory pressure e.g. + * multiple streaming readers/writers. Hence, we do not abort scanning + * when the requested number of pages are reclaimed when scanning at + * DEF_PRIORITY on the assumption that the fact we are direct + * reclaiming implies that kswapd is not keeping up and it is best to + * do a batch of work at once. For memcg reclaim one check is made to + * abort proportional reclaim if either the file or anon lru has already + * dropped to zero at the first pass. + */ + scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() && + sc->priority == DEF_PRIORITY); + + blk_start_plug(&plug); + while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || + nr[LRU_INACTIVE_FILE]) { + unsigned long nr_anon, nr_file, percentage; + unsigned long nr_scanned; + + for_each_evictable_lru(lru) { + if (nr[lru]) { + nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX); + nr[lru] -= nr_to_scan; + + nr_reclaimed += shrink_list(lru, nr_to_scan, + lruvec, sc); + } + } + + if (nr_reclaimed < nr_to_reclaim || scan_adjusted) + continue; + + /* + * For kswapd and memcg, reclaim at least the number of pages + * requested. Ensure that the anon and file LRUs are scanned + * proportionally what was requested by get_scan_count(). We + * stop reclaiming one LRU and reduce the amount scanning + * proportional to the original scan target. + */ + nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; + nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; + + /* + * It's just vindictive to attack the larger once the smaller + * has gone to zero. And given the way we stop scanning the + * smaller below, this makes sure that we only make one nudge + * towards proportionality once we've got nr_to_reclaim. + */ + if (!nr_file || !nr_anon) + break; + + if (nr_file > nr_anon) { + unsigned long scan_target = targets[LRU_INACTIVE_ANON] + + targets[LRU_ACTIVE_ANON] + 1; + lru = LRU_BASE; + percentage = nr_anon * 100 / scan_target; + } else { + unsigned long scan_target = targets[LRU_INACTIVE_FILE] + + targets[LRU_ACTIVE_FILE] + 1; + lru = LRU_FILE; + percentage = nr_file * 100 / scan_target; + } + + /* Stop scanning the smaller of the LRU */ + nr[lru] = 0; + nr[lru + LRU_ACTIVE] = 0; + + /* + * Recalculate the other LRU scan count based on its original + * scan target and the percentage scanning already complete + */ + lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE; + nr_scanned = targets[lru] - nr[lru]; + nr[lru] = targets[lru] * (100 - percentage) / 100; + nr[lru] -= min(nr[lru], nr_scanned); + + lru += LRU_ACTIVE; + nr_scanned = targets[lru] - nr[lru]; + nr[lru] = targets[lru] * (100 - percentage) / 100; + nr[lru] -= min(nr[lru], nr_scanned); + + scan_adjusted = true; + } + blk_finish_plug(&plug); + sc->nr_reclaimed += nr_reclaimed; + + /* + * Even if we did not try to evict anon pages at all, we want to + * rebalance the anon lru active/inactive ratio. + */ + if (inactive_anon_is_low(lruvec)) + shrink_active_list(SWAP_CLUSTER_MAX, lruvec, + sc, LRU_ACTIVE_ANON); + + throttle_vm_writeout(sc->gfp_mask); +} + /* Use reclaim/compaction for costly allocs or under memory pressure */ static bool in_reclaim_compaction(struct scan_control *sc) { - if (COMPACTION_BUILD && sc->order && + if (IS_ENABLED(CONFIG_COMPACTION) && sc->order && (sc->order > PAGE_ALLOC_COSTLY_ORDER || sc->priority < DEF_PRIORITY - 2)) return true; @@ -1767,7 +2184,7 @@ static bool in_reclaim_compaction(struct scan_control *sc) * calls try_to_compact_zone() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ -static inline bool should_continue_reclaim(struct lruvec *lruvec, +static inline bool should_continue_reclaim(struct zone *zone, unsigned long nr_reclaimed, unsigned long nr_scanned, struct scan_control *sc) @@ -1807,15 +2224,15 @@ static inline bool should_continue_reclaim(struct lruvec *lruvec, * inactive lists are large enough, continue reclaiming */ pages_for_compaction = (2UL << sc->order); - inactive_lru_pages = get_lru_size(lruvec, LRU_INACTIVE_FILE); - if (nr_swap_pages > 0) - inactive_lru_pages += get_lru_size(lruvec, LRU_INACTIVE_ANON); + inactive_lru_pages = zone_page_state(zone, NR_INACTIVE_FILE); + if (get_nr_swap_pages() > 0) + inactive_lru_pages += zone_page_state(zone, NR_INACTIVE_ANON); if (sc->nr_reclaimed < pages_for_compaction && inactive_lru_pages > pages_for_compaction) return true; /* If compaction would go ahead or the allocation would succeed, stop */ - switch (compaction_suitable(lruvec_zone(lruvec), sc->order)) { + switch (compaction_suitable(zone, sc->order)) { case COMPACT_PARTIAL: case COMPACT_CONTINUE: return false; @@ -1824,98 +2241,54 @@ static inline bool should_continue_reclaim(struct lruvec *lruvec, } } -/* - * This is a basic per-zone page freer. Used by both kswapd and direct reclaim. - */ -static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) +static void shrink_zone(struct zone *zone, struct scan_control *sc) { - unsigned long nr[NR_LRU_LISTS]; - unsigned long nr_to_scan; - enum lru_list lru; unsigned long nr_reclaimed, nr_scanned; - unsigned long nr_to_reclaim = sc->nr_to_reclaim; - struct blk_plug plug; - -restart: - nr_reclaimed = 0; - nr_scanned = sc->nr_scanned; - get_scan_count(lruvec, sc, nr); - blk_start_plug(&plug); - while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || - nr[LRU_INACTIVE_FILE]) { - for_each_evictable_lru(lru) { - if (nr[lru]) { - nr_to_scan = min_t(unsigned long, - nr[lru], SWAP_CLUSTER_MAX); - nr[lru] -= nr_to_scan; - - nr_reclaimed += shrink_list(lru, nr_to_scan, - lruvec, sc); - } - } - /* - * On large memory systems, scan >> priority can become - * really large. This is fine for the starting priority; - * we want to put equal scanning pressure on each zone. - * However, if the VM has a harder time of freeing pages, - * with multiple processes reclaiming pages, the total - * freeing target can get unreasonably large. - */ - if (nr_reclaimed >= nr_to_reclaim && - sc->priority < DEF_PRIORITY) - break; - } - blk_finish_plug(&plug); - sc->nr_reclaimed += nr_reclaimed; + do { + struct mem_cgroup *root = sc->target_mem_cgroup; + struct mem_cgroup_reclaim_cookie reclaim = { + .zone = zone, + .priority = sc->priority, + }; + struct mem_cgroup *memcg; - /* - * Even if we did not try to evict anon pages at all, we want to - * rebalance the anon lru active/inactive ratio. - */ - if (inactive_anon_is_low(lruvec)) - shrink_active_list(SWAP_CLUSTER_MAX, lruvec, - sc, LRU_ACTIVE_ANON); + nr_reclaimed = sc->nr_reclaimed; + nr_scanned = sc->nr_scanned; - /* reclaim/compaction might need reclaim to continue */ - if (should_continue_reclaim(lruvec, nr_reclaimed, - sc->nr_scanned - nr_scanned, sc)) - goto restart; + memcg = mem_cgroup_iter(root, NULL, &reclaim); + do { + struct lruvec *lruvec; - throttle_vm_writeout(sc->gfp_mask); -} + lruvec = mem_cgroup_zone_lruvec(zone, memcg); -static void shrink_zone(struct zone *zone, struct scan_control *sc) -{ - struct mem_cgroup *root = sc->target_mem_cgroup; - struct mem_cgroup_reclaim_cookie reclaim = { - .zone = zone, - .priority = sc->priority, - }; - struct mem_cgroup *memcg; + sc->swappiness = mem_cgroup_swappiness(memcg); + shrink_lruvec(lruvec, sc); - memcg = mem_cgroup_iter(root, NULL, &reclaim); - do { - struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); + /* + * Direct reclaim and kswapd have to scan all memory + * cgroups to fulfill the overall scan target for the + * zone. + * + * Limit reclaim, on the other hand, only cares about + * nr_to_reclaim pages to be reclaimed and it will + * retry with decreasing priority if one round over the + * whole hierarchy is not sufficient. + */ + if (!global_reclaim(sc) && + sc->nr_reclaimed >= sc->nr_to_reclaim) { + mem_cgroup_iter_break(root, memcg); + break; + } + memcg = mem_cgroup_iter(root, memcg, &reclaim); + } while (memcg); - shrink_lruvec(lruvec, sc); + vmpressure(sc->gfp_mask, sc->target_mem_cgroup, + sc->nr_scanned - nr_scanned, + sc->nr_reclaimed - nr_reclaimed); - /* - * Limit reclaim has historically picked one memcg and - * scanned it with decreasing priority levels until - * nr_to_reclaim had been reclaimed. This priority - * cycle is thus over after a single memcg. - * - * Direct reclaim and kswapd, on the other hand, have - * to scan all memory cgroups to fulfill the overall - * scan target for the zone. - */ - if (!global_reclaim(sc)) { - mem_cgroup_iter_break(root, memcg); - break; - } - memcg = mem_cgroup_iter(root, memcg, &reclaim); - } while (memcg); + } while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed, + sc->nr_scanned - nr_scanned, sc)); } /* Returns true if compaction should go ahead for a high-order request */ @@ -1934,9 +2307,8 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) * there is a buffer of free pages available to give compaction * a reasonable chance of completing and allocating the page */ - balance_gap = min(low_wmark_pages(zone), - (zone->present_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / - KSWAPD_ZONE_BALANCE_GAP_RATIO); + balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP( + zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO)); watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order); watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0); @@ -1981,16 +2353,26 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; + unsigned long lru_pages = 0; bool aborted_reclaim = false; + struct reclaim_state *reclaim_state = current->reclaim_state; + gfp_t orig_mask; + struct shrink_control shrink = { + .gfp_mask = sc->gfp_mask, + }; + enum zone_type requested_highidx = gfp_zone(sc->gfp_mask); /* * If the number of buffer_heads in the machine exceeds the maximum * allowed level, force direct reclaim to scan the highmem zone as * highmem pages could be pinning lowmem pages storing buffer_heads */ + orig_mask = sc->gfp_mask; if (buffer_heads_over_limit) sc->gfp_mask |= __GFP_HIGHMEM; + nodes_clear(shrink.nodes_to_scan); + for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(sc->gfp_mask), sc->nodemask) { if (!populated_zone(zone)) @@ -2002,10 +2384,14 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) if (global_reclaim(sc)) { if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; - if (zone->all_unreclaimable && - sc->priority != DEF_PRIORITY) + + lru_pages += zone_reclaimable_pages(zone); + node_set(zone_to_nid(zone), shrink.nodes_to_scan); + + if (sc->priority != DEF_PRIORITY && + !zone_reclaimable(zone)) continue; /* Let kswapd poll it */ - if (COMPACTION_BUILD) { + if (IS_ENABLED(CONFIG_COMPACTION)) { /* * If we already have plenty of memory free for * compaction in this zone, don't free any more. @@ -2015,7 +2401,8 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) * noticeable problem, like transparent huge * page allocations. */ - if (compaction_ready(zone, sc)) { + if ((zonelist_zone_idx(z) <= requested_highidx) + && compaction_ready(zone, sc)) { aborted_reclaim = true; continue; } @@ -2038,12 +2425,27 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) shrink_zone(zone, sc); } - return aborted_reclaim; -} + /* + * Don't shrink slabs when reclaiming memory from over limit cgroups + * but do shrink slab at least once when aborting reclaim for + * compaction to avoid unevenly scanning file/anon LRU pages over slab + * pages. + */ + if (global_reclaim(sc)) { + shrink_slab(&shrink, sc->nr_scanned, lru_pages); + if (reclaim_state) { + sc->nr_reclaimed += reclaim_state->reclaimed_slab; + reclaim_state->reclaimed_slab = 0; + } + } -static bool zone_reclaimable(struct zone *zone) -{ - return zone->pages_scanned < zone_reclaimable_pages(zone) * 6; + /* + * Restore to original mask to avoid the impact on the caller if we + * promoted it to __GFP_HIGHMEM. + */ + sc->gfp_mask = orig_mask; + + return aborted_reclaim; } /* All zones in zonelist are unreclaimable? */ @@ -2059,7 +2461,7 @@ static bool all_unreclaimable(struct zonelist *zonelist, continue; if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; - if (!zone->all_unreclaimable) + if (zone_reclaimable(zone)) return false; } @@ -2083,13 +2485,9 @@ static bool all_unreclaimable(struct zonelist *zonelist, * else, the number of pages reclaimed */ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, - struct scan_control *sc, - struct shrink_control *shrink) + struct scan_control *sc) { unsigned long total_scanned = 0; - struct reclaim_state *reclaim_state = current->reclaim_state; - struct zoneref *z; - struct zone *zone; unsigned long writeback_threshold; bool aborted_reclaim; @@ -2099,34 +2497,23 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, count_vm_event(ALLOCSTALL); do { + vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, + sc->priority); sc->nr_scanned = 0; aborted_reclaim = shrink_zones(zonelist, sc); - /* - * Don't shrink slabs when reclaiming memory from - * over limit cgroups - */ - if (global_reclaim(sc)) { - unsigned long lru_pages = 0; - for_each_zone_zonelist(zone, z, zonelist, - gfp_zone(sc->gfp_mask)) { - if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) - continue; - - lru_pages += zone_reclaimable_pages(zone); - } - - shrink_slab(shrink, sc->nr_scanned, lru_pages); - if (reclaim_state) { - sc->nr_reclaimed += reclaim_state->reclaimed_slab; - reclaim_state->reclaimed_slab = 0; - } - } total_scanned += sc->nr_scanned; if (sc->nr_reclaimed >= sc->nr_to_reclaim) goto out; /* + * If we're getting trouble reclaiming, start doing + * writepage even in laptop mode. + */ + if (sc->priority < DEF_PRIORITY - 2) + sc->may_writepage = 1; + + /* * Try to write back as many pages as we just scanned. This * tends to cause slow streaming writers to write data to the * disk smoothly, at the dirtying rate, which is nice. But @@ -2139,18 +2526,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, WB_REASON_TRY_TO_FREE_PAGES); sc->may_writepage = 1; } - - /* Take a nap, wait for some writeback to complete */ - if (!sc->hibernation_mode && sc->nr_scanned && - sc->priority < DEF_PRIORITY - 2) { - struct zone *preferred_zone; - - first_zones_zonelist(zonelist, gfp_zone(sc->gfp_mask), - &cpuset_current_mems_allowed, - &preferred_zone); - wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/10); - } - } while (--sc->priority >= 0); + } while (--sc->priority >= 0 && !aborted_reclaim); out: delayacct_freepages_end(); @@ -2187,10 +2563,17 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; + if (!populated_zone(zone)) + continue; + pfmemalloc_reserve += min_wmark_pages(zone); free_pages += zone_page_state(zone, NR_FREE_PAGES); } + /* If there are no reserves (unexpected config) then do not throttle */ + if (!pfmemalloc_reserve) + return true; + wmark_ok = free_pages > pfmemalloc_reserve / 2; /* kswapd must be awake if processes are being throttled */ @@ -2215,9 +2598,9 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, nodemask_t *nodemask) { + struct zoneref *z; struct zone *zone; - int high_zoneidx = gfp_zone(gfp_mask); - pg_data_t *pgdat; + pg_data_t *pgdat = NULL; /* * Kernel threads should not be throttled as they may be indirectly @@ -2236,10 +2619,34 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, if (fatal_signal_pending(current)) goto out; - /* Check if the pfmemalloc reserves are ok */ - first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone); - pgdat = zone->zone_pgdat; - if (pfmemalloc_watermark_ok(pgdat)) + /* + * Check if the pfmemalloc reserves are ok by finding the first node + * with a usable ZONE_NORMAL or lower zone. The expectation is that + * GFP_KERNEL will be required for allocating network buffers when + * swapping over the network so ZONE_HIGHMEM is unusable. + * + * Throttling is based on the first usable node and throttled processes + * wait on a queue until kswapd makes progress and wakes them. There + * is an affinity then between processes waking up and where reclaim + * progress has been made assuming the process wakes on the same node. + * More importantly, processes running on remote nodes will not compete + * for remote pfmemalloc reserves and processes on different nodes + * should make reasonable progress. + */ + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_mask, nodemask) { + if (zone_idx(zone) > ZONE_NORMAL) + continue; + + /* Throttle based on the first usable node */ + pgdat = zone->zone_pgdat; + if (pfmemalloc_watermark_ok(pgdat)) + goto out; + break; + } + + /* If no zone was usable by the allocation flags then do not throttle */ + if (!pgdat) goto out; /* Account for the throttling */ @@ -2277,7 +2684,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, { unsigned long nr_reclaimed; struct scan_control sc = { - .gfp_mask = gfp_mask, + .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)), .may_writepage = !laptop_mode, .nr_to_reclaim = SWAP_CLUSTER_MAX, .may_unmap = 1, @@ -2287,9 +2694,6 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, .target_mem_cgroup = NULL, .nodemask = nodemask, }; - struct shrink_control shrink = { - .gfp_mask = sc.gfp_mask, - }; /* * Do not enter reclaim if fatal signal was delivered while throttled. @@ -2303,7 +2707,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, sc.may_writepage, gfp_mask); - nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink); + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); @@ -2325,6 +2729,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, .may_swap = !noswap, .order = 0, .priority = 0, + .swappiness = mem_cgroup_swappiness(memcg), .target_mem_cgroup = memcg, }; struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); @@ -2370,9 +2775,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, .gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), }; - struct shrink_control shrink = { - .gfp_mask = sc.gfp_mask, - }; /* * Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't @@ -2387,7 +2789,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, sc.may_writepage, sc.gfp_mask); - nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink); + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); @@ -2414,13 +2816,31 @@ static void age_active_anon(struct zone *zone, struct scan_control *sc) } while (memcg); } +static bool zone_balanced(struct zone *zone, int order, + unsigned long balance_gap, int classzone_idx) +{ + if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone) + + balance_gap, classzone_idx, 0)) + return false; + + if (IS_ENABLED(CONFIG_COMPACTION) && order && + !compaction_suitable(zone, order)) + return false; + + return true; +} + /* - * pgdat_balanced is used when checking if a node is balanced for high-order - * allocations. Only zones that meet watermarks and are in a zone allowed - * by the callers classzone_idx are added to balanced_pages. The total of - * balanced pages must be at least 25% of the zones allowed by classzone_idx - * for the node to be considered balanced. Forcing all zones to be balanced - * for high orders can cause excessive reclaim when there are imbalanced zones. + * pgdat_balanced() is used when checking if a node is balanced. + * + * For order-0, all zones must be balanced! + * + * For high-order allocations only zones that meet watermarks and are in a + * zone allowed by the callers classzone_idx are added to balanced_pages. The + * total of balanced pages must be at least 25% of the zones allowed by + * classzone_idx for the node to be considered balanced. Forcing all zones to + * be balanced for high orders can cause excessive reclaim when there are + * imbalanced zones. * The choice of 25% is due to * o a 16M DMA zone that is balanced will not balance a zone on any * reasonable sized machine @@ -2430,17 +2850,43 @@ static void age_active_anon(struct zone *zone, struct scan_control *sc) * Similarly, on x86-64 the Normal zone would need to be at least 1G * to balance a node on its own. These seemed like reasonable ratios. */ -static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages, - int classzone_idx) +static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) { - unsigned long present_pages = 0; + unsigned long managed_pages = 0; + unsigned long balanced_pages = 0; int i; - for (i = 0; i <= classzone_idx; i++) - present_pages += pgdat->node_zones[i].present_pages; + /* Check the watermark levels */ + for (i = 0; i <= classzone_idx; i++) { + struct zone *zone = pgdat->node_zones + i; + + if (!populated_zone(zone)) + continue; - /* A special case here: if zone has no page, we think it's balanced */ - return balanced_pages >= (present_pages >> 2); + managed_pages += zone->managed_pages; + + /* + * A special case here: + * + * balance_pgdat() skips over all_unreclaimable after + * DEF_PRIORITY. Effectively, it considers them balanced so + * they must be considered balanced here as well! + */ + if (!zone_reclaimable(zone)) { + balanced_pages += zone->managed_pages; + continue; + } + + if (zone_balanced(zone, order, 0, i)) + balanced_pages += zone->managed_pages; + else if (!order) + return false; + } + + if (order) + return balanced_pages >= (managed_pages >> 2); + else + return true; } /* @@ -2452,10 +2898,6 @@ static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages, static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, int classzone_idx) { - int i; - unsigned long balanced = 0; - bool all_zones_ok = true; - /* If a direct reclaimer woke kswapd within HZ/10, it's premature */ if (remaining) return false; @@ -2474,40 +2916,89 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, return false; } - /* Check the watermark levels */ - for (i = 0; i <= classzone_idx; i++) { - struct zone *zone = pgdat->node_zones + i; + return pgdat_balanced(pgdat, order, classzone_idx); +} - if (!populated_zone(zone)) - continue; +/* + * kswapd shrinks the zone by the number of pages required to reach + * the high watermark. + * + * Returns true if kswapd scanned at least the requested number of pages to + * reclaim or if the lack of progress was due to pages under writeback. + * This is used to determine if the scanning priority needs to be raised. + */ +static bool kswapd_shrink_zone(struct zone *zone, + int classzone_idx, + struct scan_control *sc, + unsigned long lru_pages, + unsigned long *nr_attempted) +{ + int testorder = sc->order; + unsigned long balance_gap; + struct reclaim_state *reclaim_state = current->reclaim_state; + struct shrink_control shrink = { + .gfp_mask = sc->gfp_mask, + }; + bool lowmem_pressure; - /* - * balance_pgdat() skips over all_unreclaimable after - * DEF_PRIORITY. Effectively, it considers them balanced so - * they must be considered balanced here as well if kswapd - * is to sleep - */ - if (zone->all_unreclaimable) { - balanced += zone->present_pages; - continue; - } + /* Reclaim above the high watermark. */ + sc->nr_to_reclaim = max(SWAP_CLUSTER_MAX, high_wmark_pages(zone)); - if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), - i, 0)) - all_zones_ok = false; - else - balanced += zone->present_pages; - } + /* + * Kswapd reclaims only single pages with compaction enabled. Trying + * too hard to reclaim until contiguous free pages have become + * available can hurt performance by evicting too much useful data + * from memory. Do not reclaim more than needed for compaction. + */ + if (IS_ENABLED(CONFIG_COMPACTION) && sc->order && + compaction_suitable(zone, sc->order) != + COMPACT_SKIPPED) + testorder = 0; /* - * For high-order requests, the balanced zones must contain at least - * 25% of the nodes pages for kswapd to sleep. For order-0, all zones - * must be balanced + * We put equal pressure on every zone, unless one zone has way too + * many pages free already. The "too many pages" is defined as the + * high wmark plus a "gap" where the gap is either the low + * watermark or 1% of the zone, whichever is smaller. */ - if (order) - return pgdat_balanced(pgdat, balanced, classzone_idx); - else - return all_zones_ok; + balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP( + zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO)); + + /* + * If there is no low memory pressure or the zone is balanced then no + * reclaim is necessary + */ + lowmem_pressure = (buffer_heads_over_limit && is_highmem(zone)); + if (!lowmem_pressure && zone_balanced(zone, testorder, + balance_gap, classzone_idx)) + return true; + + shrink_zone(zone, sc); + nodes_clear(shrink.nodes_to_scan); + node_set(zone_to_nid(zone), shrink.nodes_to_scan); + + reclaim_state->reclaimed_slab = 0; + shrink_slab(&shrink, sc->nr_scanned, lru_pages); + sc->nr_reclaimed += reclaim_state->reclaimed_slab; + + /* Account for the number of pages attempted to reclaim */ + *nr_attempted += sc->nr_to_reclaim; + + zone_clear_flag(zone, ZONE_WRITEBACK); + + /* + * If a zone reaches its high watermark, consider it to be no longer + * congested. It's possible there are dirty pages backed by congested + * BDIs but as pressure is relieved, speculatively avoid congestion + * waits. + */ + if (zone_reclaimable(zone) && + zone_balanced(zone, testorder, 0, classzone_idx)) { + zone_clear_flag(zone, ZONE_CONGESTED); + zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY); + } + + return sc->nr_scanned >= sc->nr_to_reclaim; } /* @@ -2534,42 +3025,28 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, static unsigned long balance_pgdat(pg_data_t *pgdat, int order, int *classzone_idx) { - int all_zones_ok; - unsigned long balanced; int i; int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ - unsigned long total_scanned; - struct reclaim_state *reclaim_state = current->reclaim_state; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; struct scan_control sc = { .gfp_mask = GFP_KERNEL, + .priority = DEF_PRIORITY, .may_unmap = 1, .may_swap = 1, - /* - * kswapd doesn't want to be bailed out while reclaim. because - * we want to put equal scanning pressure on each zone. - */ - .nr_to_reclaim = ULONG_MAX, + .may_writepage = !laptop_mode, .order = order, .target_mem_cgroup = NULL, }; - struct shrink_control shrink = { - .gfp_mask = sc.gfp_mask, - }; -loop_again: - total_scanned = 0; - sc.priority = DEF_PRIORITY; - sc.nr_reclaimed = 0; - sc.may_writepage = !laptop_mode; count_vm_event(PAGEOUTRUN); do { unsigned long lru_pages = 0; - int has_under_min_watermark_zone = 0; + unsigned long nr_attempted = 0; + bool raise_priority = true; + bool pgdat_needs_compaction = (order > 0); - all_zones_ok = 1; - balanced = 0; + sc.nr_reclaimed = 0; /* * Scan in the highmem->dma direction for the highest @@ -2581,8 +3058,8 @@ loop_again: if (!populated_zone(zone)) continue; - if (zone->all_unreclaimable && - sc.priority != DEF_PRIORITY) + if (sc.priority != DEF_PRIORITY && + !zone_reclaimable(zone)) continue; /* @@ -2602,25 +3079,50 @@ loop_again: break; } - if (!zone_watermark_ok_safe(zone, order, - high_wmark_pages(zone), 0, 0)) { + if (!zone_balanced(zone, order, 0, 0)) { end_zone = i; break; } else { - /* If balanced, clear the congested flag */ + /* + * If balanced, clear the dirty and congested + * flags + */ zone_clear_flag(zone, ZONE_CONGESTED); + zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY); } } + if (i < 0) goto out; for (i = 0; i <= end_zone; i++) { struct zone *zone = pgdat->node_zones + i; + if (!populated_zone(zone)) + continue; + lru_pages += zone_reclaimable_pages(zone); + + /* + * If any zone is currently balanced then kswapd will + * not call compaction as it is expected that the + * necessary pages are already available. + */ + if (pgdat_needs_compaction && + zone_watermark_ok(zone, order, + low_wmark_pages(zone), + *classzone_idx, 0)) + pgdat_needs_compaction = false; } /* + * If we're getting trouble reclaiming, start doing writepage + * even in laptop mode. + */ + if (sc.priority < DEF_PRIORITY - 2) + sc.may_writepage = 1; + + /* * Now scan the zone in the dma->highmem direction, stopping * at the last zone which needs scanning. * @@ -2631,14 +3133,12 @@ loop_again: */ for (i = 0; i <= end_zone; i++) { struct zone *zone = pgdat->node_zones + i; - int nr_slab, testorder; - unsigned long balance_gap; if (!populated_zone(zone)) continue; - if (zone->all_unreclaimable && - sc.priority != DEF_PRIORITY) + if (sc.priority != DEF_PRIORITY && + !zone_reclaimable(zone)) continue; sc.nr_scanned = 0; @@ -2651,87 +3151,16 @@ loop_again: order, sc.gfp_mask, &nr_soft_scanned); sc.nr_reclaimed += nr_soft_reclaimed; - total_scanned += nr_soft_scanned; /* - * We put equal pressure on every zone, unless - * one zone has way too many pages free - * already. The "too many pages" is defined - * as the high wmark plus a "gap" where the - * gap is either the low watermark or 1% - * of the zone, whichever is smaller. + * There should be no need to raise the scanning + * priority if enough pages are already being scanned + * that that high watermark would be met at 100% + * efficiency. */ - balance_gap = min(low_wmark_pages(zone), - (zone->present_pages + - KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / - KSWAPD_ZONE_BALANCE_GAP_RATIO); - /* - * Kswapd reclaims only single pages with compaction - * enabled. Trying too hard to reclaim until contiguous - * free pages have become available can hurt performance - * by evicting too much useful data from memory. - * Do not reclaim more than needed for compaction. - */ - testorder = order; - if (COMPACTION_BUILD && order && - compaction_suitable(zone, order) != - COMPACT_SKIPPED) - testorder = 0; - - if ((buffer_heads_over_limit && is_highmem_idx(i)) || - !zone_watermark_ok_safe(zone, testorder, - high_wmark_pages(zone) + balance_gap, - end_zone, 0)) { - shrink_zone(zone, &sc); - - reclaim_state->reclaimed_slab = 0; - nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages); - sc.nr_reclaimed += reclaim_state->reclaimed_slab; - total_scanned += sc.nr_scanned; - - if (nr_slab == 0 && !zone_reclaimable(zone)) - zone->all_unreclaimable = 1; - } - - /* - * If we've done a decent amount of scanning and - * the reclaim ratio is low, start doing writepage - * even in laptop mode - */ - if (total_scanned > SWAP_CLUSTER_MAX * 2 && - total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2) - sc.may_writepage = 1; - - if (zone->all_unreclaimable) { - if (end_zone && end_zone == i) - end_zone--; - continue; - } - - if (!zone_watermark_ok_safe(zone, testorder, - high_wmark_pages(zone), end_zone, 0)) { - all_zones_ok = 0; - /* - * We are still under min water mark. This - * means that we have a GFP_ATOMIC allocation - * failure risk. Hurry up! - */ - if (!zone_watermark_ok_safe(zone, order, - min_wmark_pages(zone), end_zone, 0)) - has_under_min_watermark_zone = 1; - } else { - /* - * If a zone reaches its high watermark, - * consider it to be no longer congested. It's - * possible there are dirty pages backed by - * congested BDIs but as pressure is relieved, - * speculatively avoid congestion waits - */ - zone_clear_flag(zone, ZONE_CONGESTED); - if (i <= *classzone_idx) - balanced += zone->present_pages; - } - + if (kswapd_shrink_zone(zone, end_zone, &sc, + lru_pages, &nr_attempted)) + raise_priority = false; } /* @@ -2743,106 +3172,38 @@ loop_again: pfmemalloc_watermark_ok(pgdat)) wake_up(&pgdat->pfmemalloc_wait); - if (all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx))) - break; /* kswapd: all done */ /* - * OK, kswapd is getting into trouble. Take a nap, then take - * another pass across the zones. + * Fragmentation may mean that the system cannot be rebalanced + * for high-order allocations in all zones. If twice the + * allocation size has been reclaimed and the zones are still + * not balanced then recheck the watermarks at order-0 to + * prevent kswapd reclaiming excessively. Assume that a + * process requested a high-order can direct reclaim/compact. */ - if (total_scanned && (sc.priority < DEF_PRIORITY - 2)) { - if (has_under_min_watermark_zone) - count_vm_event(KSWAPD_SKIP_CONGESTION_WAIT); - else - congestion_wait(BLK_RW_ASYNC, HZ/10); - } + if (order && sc.nr_reclaimed >= 2UL << order) + order = sc.order = 0; - /* - * We do this so kswapd doesn't build up large priorities for - * example when it is freeing in parallel with allocators. It - * matches the direct reclaim path behaviour in terms of impact - * on zone->*_priority. - */ - if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX) + /* Check if kswapd should be suspending */ + if (try_to_freeze() || kthread_should_stop()) break; - } while (--sc.priority >= 0); -out: - - /* - * order-0: All zones must meet high watermark for a balanced node - * high-order: Balanced zones must make up at least 25% of the node - * for the node to be balanced - */ - if (!(all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))) { - cond_resched(); - - try_to_freeze(); /* - * Fragmentation may mean that the system cannot be - * rebalanced for high-order allocations in all zones. - * At this point, if nr_reclaimed < SWAP_CLUSTER_MAX, - * it means the zones have been fully scanned and are still - * not balanced. For high-order allocations, there is - * little point trying all over again as kswapd may - * infinite loop. - * - * Instead, recheck all watermarks at order-0 as they - * are the most important. If watermarks are ok, kswapd will go - * back to sleep. High-order users can still perform direct - * reclaim if they wish. + * Compact if necessary and kswapd is reclaiming at least the + * high watermark number of pages as requsted */ - if (sc.nr_reclaimed < SWAP_CLUSTER_MAX) - order = sc.order = 0; - - goto loop_again; - } - - /* - * If kswapd was reclaiming at a higher order, it has the option of - * sleeping without all zones being balanced. Before it does, it must - * ensure that the watermarks for order-0 on *all* zones are met and - * that the congestion flags are cleared. The congestion flag must - * be cleared as kswapd is the only mechanism that clears the flag - * and it is potentially going to sleep here. - */ - if (order) { - int zones_need_compaction = 1; - - for (i = 0; i <= end_zone; i++) { - struct zone *zone = pgdat->node_zones + i; - - if (!populated_zone(zone)) - continue; - - if (zone->all_unreclaimable && - sc.priority != DEF_PRIORITY) - continue; - - /* Would compaction fail due to lack of free memory? */ - if (COMPACTION_BUILD && - compaction_suitable(zone, order) == COMPACT_SKIPPED) - goto loop_again; - - /* Confirm the zone is balanced for order-0 */ - if (!zone_watermark_ok(zone, 0, - high_wmark_pages(zone), 0, 0)) { - order = sc.order = 0; - goto loop_again; - } - - /* Check if the memory needs to be defragmented. */ - if (zone_watermark_ok(zone, order, - low_wmark_pages(zone), *classzone_idx, 0)) - zones_need_compaction = 0; - - /* If balanced, clear the congested flag */ - zone_clear_flag(zone, ZONE_CONGESTED); - } - - if (zones_need_compaction) + if (pgdat_needs_compaction && sc.nr_reclaimed > nr_attempted) compact_pgdat(pgdat, order); - } + /* + * Raise priority if scanning rate is too low or there was no + * progress in reclaiming pages + */ + if (raise_priority || !sc.nr_reclaimed) + sc.priority--; + } while (sc.priority >= 1 && + !pgdat_balanced(pgdat, order, *classzone_idx)); + +out: /* * Return the order we were reclaiming at so prepare_kswapd_sleep() * makes a decision on the order we were last reclaiming at. However, @@ -2961,7 +3322,7 @@ static int kswapd(void *p) classzone_idx = new_classzone_idx = pgdat->nr_zones - 1; balanced_classzone_idx = classzone_idx; for ( ; ; ) { - int ret; + bool ret; /* * If the last balance_pgdat was unsuccessful it's unlikely a @@ -3010,7 +3371,10 @@ static int kswapd(void *p) } } + tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD); current->reclaim_state = NULL; + lockdep_clear_current_reclaim_state(); + return 0; } @@ -3033,48 +3397,13 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) } if (!waitqueue_active(&pgdat->kswapd_wait)) return; - if (zone_watermark_ok_safe(zone, order, low_wmark_pages(zone), 0, 0)) + if (zone_balanced(zone, order, 0, 0)) return; trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order); wake_up_interruptible(&pgdat->kswapd_wait); } -/* - * The reclaimable count would be mostly accurate. - * The less reclaimable pages may be - * - mlocked pages, which will be moved to unevictable list when encountered - * - mapped pages, which may require several travels to be reclaimed - * - dirty pages, which is not "instantly" reclaimable - */ -unsigned long global_reclaimable_pages(void) -{ - int nr; - - nr = global_page_state(NR_ACTIVE_FILE) + - global_page_state(NR_INACTIVE_FILE); - - if (nr_swap_pages > 0) - nr += global_page_state(NR_ACTIVE_ANON) + - global_page_state(NR_INACTIVE_ANON); - - return nr; -} - -unsigned long zone_reclaimable_pages(struct zone *zone) -{ - int nr; - - nr = zone_page_state(zone, NR_ACTIVE_FILE) + - zone_page_state(zone, NR_INACTIVE_FILE); - - if (nr_swap_pages > 0) - nr += zone_page_state(zone, NR_ACTIVE_ANON) + - zone_page_state(zone, NR_INACTIVE_ANON); - - return nr; -} - #ifdef CONFIG_HIBERNATION /* * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of @@ -3097,9 +3426,6 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) .order = 0, .priority = DEF_PRIORITY, }; - struct shrink_control shrink = { - .gfp_mask = sc.gfp_mask, - }; struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); struct task_struct *p = current; unsigned long nr_reclaimed; @@ -3109,7 +3435,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) reclaim_state.reclaimed_slab = 0; p->reclaim_state = &reclaim_state; - nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink); + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); p->reclaim_state = NULL; lockdep_clear_current_reclaim_state(); @@ -3123,13 +3449,13 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) not required for correctness. So if the last cpu in a node goes away, we get changed to run anywhere: as the first one comes back, restore their cpu bindings. */ -static int __devinit cpu_callback(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static int cpu_callback(struct notifier_block *nfb, unsigned long action, + void *hcpu) { int nid; if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) { - for_each_node_state(nid, N_HIGH_MEMORY) { + for_each_node_state(nid, N_MEMORY) { pg_data_t *pgdat = NODE_DATA(nid); const struct cpumask *mask; @@ -3159,16 +3485,16 @@ int kswapd_run(int nid) if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ BUG_ON(system_state == SYSTEM_BOOTING); - pgdat->kswapd = NULL; pr_err("Failed to start kswapd on node %d\n", nid); ret = PTR_ERR(pgdat->kswapd); + pgdat->kswapd = NULL; } return ret; } /* * Called by memory hotplug when all memory in a node is offlined. Caller must - * hold lock_memory_hotplug(). + * hold mem_hotplug_begin/end(). */ void kswapd_stop(int nid) { @@ -3185,7 +3511,7 @@ static int __init kswapd_init(void) int nid; swap_setup(); - for_each_node_state(nid, N_HIGH_MEMORY) + for_each_node_state(nid, N_MEMORY) kswapd_run(nid); hotcpu_notifier(cpu_callback, 0); return 0; @@ -3281,9 +3607,8 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) .may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE), .may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP), .may_swap = 1, - .nr_to_reclaim = max_t(unsigned long, nr_pages, - SWAP_CLUSTER_MAX), - .gfp_mask = gfp_mask, + .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), + .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)), .order = order, .priority = ZONE_RECLAIM_PRIORITY, }; @@ -3321,10 +3646,9 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) * number of slab pages and shake the slab until it is reduced * by the same nr_pages that we used for reclaiming unmapped * pages. - * - * Note that shrink_slab will free memory on all zones and may - * take a long time. */ + nodes_clear(shrink.nodes_to_scan); + node_set(zone_to_nid(zone), shrink.nodes_to_scan); for (;;) { unsigned long lru_pages = zone_reclaimable_pages(zone); @@ -3373,7 +3697,7 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages) return ZONE_RECLAIM_FULL; - if (zone->all_unreclaimable) + if (!zone_reclaimable(zone)) return ZONE_RECLAIM_FULL; /* @@ -3460,7 +3784,7 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages) if (page_evictable(page)) { enum lru_list lru = page_lru_base_type(page); - VM_BUG_ON(PageActive(page)); + VM_BUG_ON_PAGE(PageActive(page), page); ClearPageUnevictable(page); del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE); add_page_to_lru_list(page, lruvec, lru); |