From 8d07429319b2836604061f48f7e3dfe78acc060c Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 6 Aug 2014 16:06:10 -0700 Subject: mm: vmscan: remove remains of kswapd-managed zone->all_unreclaimable shrink_zones() has a special branch to skip the all_unreclaimable() check during hibernation, because a frozen kswapd can't mark a zone unreclaimable. But ever since commit 6e543d5780e3 ("mm: vmscan: fix do_try_to_free_pages() livelock"), determining a zone to be unreclaimable is done by directly looking at its scan history and no longer relies on kswapd setting the per-zone flag. Remove this branch and let shrink_zones() check the reclaimability of the target zones regardless of hibernation state. Signed-off-by: Johannes Weiner Acked-by: Mel Gorman Cc: Rik van Riel Acked-by: Michal Hocko Cc: Vlastimil Babka Acked-by: Minchan Kim Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 8 -------- 1 file changed, 8 deletions(-) (limited to 'mm/vmscan.c') diff --git a/mm/vmscan.c b/mm/vmscan.c index 0f16ffe8eb67..19b5b8016209 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2534,14 +2534,6 @@ out: if (sc->nr_reclaimed) return sc->nr_reclaimed; - /* - * As hibernation is going on, kswapd is freezed so that it can't mark - * the zone into all_unreclaimable. Thus bypassing all_unreclaimable - * check. - */ - if (oom_killer_disabled) - return 0; - /* Aborted reclaim to try compaction? don't OOM, then */ if (aborted_reclaim) return 1; -- cgit v1.2.3 From 0b06496a338e83627dc5f0d25323e7a1ae9cb87d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 6 Aug 2014 16:06:12 -0700 Subject: mm: vmscan: rework compaction-ready signaling in direct reclaim Page reclaim for a higher-order page runs until compaction is ready, then aborts and signals this situation through the return value of shrink_zones(). This is an oddly specific signal to encode in the return value of shrink_zones(), though, and can be quite confusing. Introduce sc->compaction_ready and signal the compactability of the zones out-of-band to free up the return value of shrink_zones() for actual zone reclaimability. Signed-off-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Mel Gorman Cc: Rik van Riel Cc: Michal Hocko Acked-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 70 ++++++++++++++++++++++++++++--------------------------------- 1 file changed, 32 insertions(+), 38 deletions(-) (limited to 'mm/vmscan.c') diff --git a/mm/vmscan.c b/mm/vmscan.c index 19b5b8016209..6f43df4a5253 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -65,6 +65,9 @@ struct scan_control { /* Number of pages freed so far during a call to shrink_zones() */ unsigned long nr_reclaimed; + /* One of the zones is ready for compaction */ + int compaction_ready; + /* How many pages shrink_list() should reclaim */ unsigned long nr_to_reclaim; @@ -2292,15 +2295,11 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc) } /* Returns true if compaction should go ahead for a high-order request */ -static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) +static inline bool compaction_ready(struct zone *zone, int order) { unsigned long balance_gap, watermark; bool watermark_ok; - /* Do not consider compaction for orders reclaim is meant to satisfy */ - if (sc->order <= PAGE_ALLOC_COSTLY_ORDER) - return false; - /* * Compaction takes time to run and there are potentially other * callers using the pages just freed. Continue reclaiming until @@ -2309,18 +2308,18 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) */ 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 = high_wmark_pages(zone) + balance_gap + (2UL << order); watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0); /* * If compaction is deferred, reclaim up to a point where * compaction will have a chance of success when re-enabled */ - if (compaction_deferred(zone, sc->order)) + if (compaction_deferred(zone, order)) return watermark_ok; /* If compaction is not ready to start, keep reclaiming */ - if (!compaction_suitable(zone, sc->order)) + if (!compaction_suitable(zone, order)) return false; return watermark_ok; @@ -2341,20 +2340,14 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. - * - * This function returns true if a zone is being reclaimed for a costly - * high-order allocation and compaction is ready to begin. This indicates to - * the caller that it should consider retrying the allocation instead of - * further reclaim. */ -static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) +static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; 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 = { @@ -2391,22 +2384,24 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) if (sc->priority != DEF_PRIORITY && !zone_reclaimable(zone)) continue; /* Let kswapd poll it */ - if (IS_ENABLED(CONFIG_COMPACTION)) { - /* - * If we already have plenty of memory free for - * compaction in this zone, don't free any more. - * Even though compaction is invoked for any - * non-zero order, only frequent costly order - * reclamation is disruptive enough to become a - * noticeable problem, like transparent huge - * page allocations. - */ - if ((zonelist_zone_idx(z) <= requested_highidx) - && compaction_ready(zone, sc)) { - aborted_reclaim = true; - continue; - } + + /* + * If we already have plenty of memory free for + * compaction in this zone, don't free any more. + * Even though compaction is invoked for any + * non-zero order, only frequent costly order + * reclamation is disruptive enough to become a + * noticeable problem, like transparent huge + * page allocations. + */ + if (IS_ENABLED(CONFIG_COMPACTION) && + sc->order > PAGE_ALLOC_COSTLY_ORDER && + zonelist_zone_idx(z) <= requested_highidx && + compaction_ready(zone, sc->order)) { + sc->compaction_ready = true; + continue; } + /* * This steals pages from memory cgroups over softlimit * and returns the number of reclaimed pages and @@ -2444,8 +2439,6 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) * promoted it to __GFP_HIGHMEM. */ sc->gfp_mask = orig_mask; - - return aborted_reclaim; } /* All zones in zonelist are unreclaimable? */ @@ -2489,7 +2482,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, { unsigned long total_scanned = 0; unsigned long writeback_threshold; - bool aborted_reclaim; delayacct_freepages_start(); @@ -2500,11 +2492,14 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, sc->priority); sc->nr_scanned = 0; - aborted_reclaim = shrink_zones(zonelist, sc); + shrink_zones(zonelist, sc); total_scanned += sc->nr_scanned; if (sc->nr_reclaimed >= sc->nr_to_reclaim) - goto out; + break; + + if (sc->compaction_ready) + break; /* * If we're getting trouble reclaiming, start doing @@ -2526,16 +2521,15 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, WB_REASON_TRY_TO_FREE_PAGES); sc->may_writepage = 1; } - } while (--sc->priority >= 0 && !aborted_reclaim); + } while (--sc->priority >= 0); -out: delayacct_freepages_end(); if (sc->nr_reclaimed) return sc->nr_reclaimed; /* Aborted reclaim to try compaction? don't OOM, then */ - if (aborted_reclaim) + if (sc->compaction_ready) return 1; /* top priority shrink_zones still had more to do? don't OOM, then */ -- cgit v1.2.3 From 2344d7e44b870f9df67e505ee4e633217de752ba Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 6 Aug 2014 16:06:15 -0700 Subject: mm: vmscan: remove all_unreclaimable() Direct reclaim currently calls shrink_zones() to reclaim all members of a zonelist, and if that wasn't successful it does another pass through the same zonelist to check overall reclaimability. Just check reclaimability in shrink_zones() directly and propagate the result through the return value. Then remove all_unreclaimable(). Signed-off-by: Johannes Weiner Cc: Mel Gorman Cc: Rik van Riel Acked-by: Michal Hocko Cc: Vlastimil Babka Acked-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 49 ++++++++++++++++++++++++------------------------- 1 file changed, 24 insertions(+), 25 deletions(-) (limited to 'mm/vmscan.c') diff --git a/mm/vmscan.c b/mm/vmscan.c index 6f43df4a5253..74a9e0ae09b0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2244,9 +2244,10 @@ static inline bool should_continue_reclaim(struct zone *zone, } } -static void shrink_zone(struct zone *zone, struct scan_control *sc) +static bool shrink_zone(struct zone *zone, struct scan_control *sc) { unsigned long nr_reclaimed, nr_scanned; + bool reclaimable = false; do { struct mem_cgroup *root = sc->target_mem_cgroup; @@ -2290,8 +2291,13 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc) sc->nr_scanned - nr_scanned, sc->nr_reclaimed - nr_reclaimed); + if (sc->nr_reclaimed - nr_reclaimed) + reclaimable = true; + } while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed, sc->nr_scanned - nr_scanned, sc)); + + return reclaimable; } /* Returns true if compaction should go ahead for a high-order request */ @@ -2340,8 +2346,10 @@ static inline bool compaction_ready(struct zone *zone, int order) * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. + * + * Returns true if a zone was reclaimable. */ -static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) +static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; @@ -2354,6 +2362,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) .gfp_mask = sc->gfp_mask, }; enum zone_type requested_highidx = gfp_zone(sc->gfp_mask); + bool reclaimable = false; /* * If the number of buffer_heads in the machine exceeds the maximum @@ -2414,10 +2423,17 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) &nr_soft_scanned); sc->nr_reclaimed += nr_soft_reclaimed; sc->nr_scanned += nr_soft_scanned; + if (nr_soft_reclaimed) + reclaimable = true; /* need some check for avoid more shrink_zone() */ } - shrink_zone(zone, sc); + if (shrink_zone(zone, sc)) + reclaimable = true; + + if (global_reclaim(sc) && + !reclaimable && zone_reclaimable(zone)) + reclaimable = true; } /* @@ -2439,26 +2455,8 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) * promoted it to __GFP_HIGHMEM. */ sc->gfp_mask = orig_mask; -} - -/* All zones in zonelist are unreclaimable? */ -static bool all_unreclaimable(struct zonelist *zonelist, - struct scan_control *sc) -{ - struct zoneref *z; - struct zone *zone; - for_each_zone_zonelist_nodemask(zone, z, zonelist, - gfp_zone(sc->gfp_mask), sc->nodemask) { - if (!populated_zone(zone)) - continue; - if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) - continue; - if (zone_reclaimable(zone)) - return false; - } - - return true; + return reclaimable; } /* @@ -2482,6 +2480,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, { unsigned long total_scanned = 0; unsigned long writeback_threshold; + bool zones_reclaimable; delayacct_freepages_start(); @@ -2492,7 +2491,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, sc->priority); sc->nr_scanned = 0; - shrink_zones(zonelist, sc); + zones_reclaimable = shrink_zones(zonelist, sc); total_scanned += sc->nr_scanned; if (sc->nr_reclaimed >= sc->nr_to_reclaim) @@ -2532,8 +2531,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, if (sc->compaction_ready) return 1; - /* top priority shrink_zones still had more to do? don't OOM, then */ - if (global_reclaim(sc) && !all_unreclaimable(zonelist, sc)) + /* Any of the zones still reclaimable? Don't OOM. */ + if (zones_reclaimable) return 1; return 0; -- cgit v1.2.3 From 02695175c79b9163c798cc1cb78c628d011c07a6 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 6 Aug 2014 16:06:17 -0700 Subject: mm: vmscan: move swappiness out of scan_control Swappiness is determined for each scanned memcg individually in shrink_zone() and is not a parameter that applies throughout the reclaim scan. Move it out of struct scan_control to prevent accidental use of a stale value. Signed-off-by: Johannes Weiner Cc: Mel Gorman Cc: Rik van Riel Acked-by: Michal Hocko Cc: Vlastimil Babka Acked-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) (limited to 'mm/vmscan.c') diff --git a/mm/vmscan.c b/mm/vmscan.c index 74a9e0ae09b0..c28b8981e56a 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -89,9 +89,6 @@ 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. @@ -1868,8 +1865,8 @@ enum scan_balance { * nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan */ -static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, - unsigned long *nr) +static void get_scan_count(struct lruvec *lruvec, int swappiness, + struct scan_control *sc, unsigned long *nr) { struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; u64 fraction[2]; @@ -1912,7 +1909,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * using the memory controller's swap limit feature would be * too expensive. */ - if (!global_reclaim(sc) && !sc->swappiness) { + if (!global_reclaim(sc) && !swappiness) { scan_balance = SCAN_FILE; goto out; } @@ -1922,7 +1919,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * system is close to OOM, scan both anon and file equally * (unless the swappiness setting disagrees with swapping). */ - if (!sc->priority && sc->swappiness) { + if (!sc->priority && swappiness) { scan_balance = SCAN_EQUAL; goto out; } @@ -1965,7 +1962,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * With swappiness at 100, anonymous and file have the same priority. * This scanning priority is essentially the inverse of IO cost. */ - anon_prio = sc->swappiness; + anon_prio = swappiness; file_prio = 200 - anon_prio; /* @@ -2055,7 +2052,8 @@ out: /* * 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_lruvec(struct lruvec *lruvec, int swappiness, + struct scan_control *sc) { unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; @@ -2066,7 +2064,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) struct blk_plug plug; bool scan_adjusted; - get_scan_count(lruvec, sc, nr); + get_scan_count(lruvec, swappiness, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); @@ -2263,11 +2261,12 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc) memcg = mem_cgroup_iter(root, NULL, &reclaim); do { struct lruvec *lruvec; + int swappiness; lruvec = mem_cgroup_zone_lruvec(zone, memcg); + swappiness = mem_cgroup_swappiness(memcg); - sc->swappiness = mem_cgroup_swappiness(memcg); - shrink_lruvec(lruvec, sc); + shrink_lruvec(lruvec, swappiness, sc); /* * Direct reclaim and kswapd have to scan all memory @@ -2714,10 +2713,10 @@ 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); + int swappiness = mem_cgroup_swappiness(memcg); sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); @@ -2733,7 +2732,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ - shrink_lruvec(lruvec, &sc); + shrink_lruvec(lruvec, swappiness, &sc); trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); -- cgit v1.2.3 From ee814fe23daf08abd3ea6c6b1f900f4f25b524d7 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 6 Aug 2014 16:06:19 -0700 Subject: mm: vmscan: clean up struct scan_control Reorder the members by input and output, then turn the individual integers for may_writepage, may_unmap, may_swap, compaction_ready, hibernation_mode into bit fields to save stack space: +72/-296 -224 kswapd 104 176 +72 try_to_free_pages 80 56 -24 try_to_free_mem_cgroup_pages 80 56 -24 shrink_all_memory 88 64 -24 reclaim_clean_pages_from_list 168 144 -24 mem_cgroup_shrink_node_zone 104 80 -24 __zone_reclaim 176 152 -24 balance_pgdat 152 - -152 Signed-off-by: Johannes Weiner Suggested-by: Mel Gorman Acked-by: Mel Gorman Acked-by: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 99 ++++++++++++++++++++++++++++--------------------------------- 1 file changed, 46 insertions(+), 53 deletions(-) (limited to 'mm/vmscan.c') diff --git a/mm/vmscan.c b/mm/vmscan.c index c28b8981e56a..81dd858b9d17 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -59,35 +59,20 @@ #include struct scan_control { - /* Incremented by the number of inactive pages that were scanned */ - unsigned long nr_scanned; - - /* Number of pages freed so far during a call to shrink_zones() */ - unsigned long nr_reclaimed; - - /* One of the zones is ready for compaction */ - int compaction_ready; - /* How many pages shrink_list() should reclaim */ unsigned long nr_to_reclaim; - unsigned long hibernation_mode; - /* This context's GFP mask */ gfp_t gfp_mask; - int may_writepage; - - /* Can mapped pages be reclaimed? */ - int may_unmap; - - /* Can pages be swapped as part of reclaim? */ - int may_swap; - + /* Allocation order */ int order; - /* Scan (total_size >> priority) pages at once */ - int priority; + /* + * Nodemask of nodes allowed by the caller. If NULL, all nodes + * are scanned. + */ + nodemask_t *nodemask; /* * The memory cgroup that hit its limit and as a result is the @@ -95,11 +80,27 @@ struct scan_control { */ struct mem_cgroup *target_mem_cgroup; - /* - * Nodemask of nodes allowed by the caller. If NULL, all nodes - * are scanned. - */ - nodemask_t *nodemask; + /* Scan (total_size >> priority) pages at once */ + int priority; + + unsigned int may_writepage:1; + + /* Can mapped pages be reclaimed? */ + unsigned int may_unmap:1; + + /* Can pages be swapped as part of reclaim? */ + unsigned int may_swap:1; + + unsigned int hibernation_mode:1; + + /* One of the zones is ready for compaction */ + unsigned int compaction_ready:1; + + /* Incremented by the number of inactive pages that were scanned */ + unsigned long nr_scanned; + + /* Number of pages freed so far during a call to shrink_zones() */ + unsigned long nr_reclaimed; }; #define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru)) @@ -2668,15 +2669,14 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, { unsigned long nr_reclaimed; struct scan_control sc = { + .nr_to_reclaim = SWAP_CLUSTER_MAX, .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)), + .order = order, + .nodemask = nodemask, + .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, - .nr_to_reclaim = SWAP_CLUSTER_MAX, .may_unmap = 1, .may_swap = 1, - .order = order, - .priority = DEF_PRIORITY, - .target_mem_cgroup = NULL, - .nodemask = nodemask, }; /* @@ -2706,14 +2706,11 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, unsigned long *nr_scanned) { struct scan_control sc = { - .nr_scanned = 0, .nr_to_reclaim = SWAP_CLUSTER_MAX, + .target_mem_cgroup = memcg, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = !noswap, - .order = 0, - .priority = 0, - .target_mem_cgroup = memcg, }; struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); int swappiness = mem_cgroup_swappiness(memcg); @@ -2748,16 +2745,14 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_reclaimed; int nid; struct scan_control sc = { - .may_writepage = !laptop_mode, - .may_unmap = 1, - .may_swap = !noswap, .nr_to_reclaim = SWAP_CLUSTER_MAX, - .order = 0, - .priority = DEF_PRIORITY, - .target_mem_cgroup = memcg, - .nodemask = NULL, /* we don't care the placement */ .gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), + .target_mem_cgroup = memcg, + .priority = DEF_PRIORITY, + .may_writepage = !laptop_mode, + .may_unmap = 1, + .may_swap = !noswap, }; /* @@ -3015,12 +3010,11 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, unsigned long nr_soft_scanned; struct scan_control sc = { .gfp_mask = GFP_KERNEL, + .order = order, .priority = DEF_PRIORITY, + .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = 1, - .may_writepage = !laptop_mode, - .order = order, - .target_mem_cgroup = NULL, }; count_vm_event(PAGEOUTRUN); @@ -3401,14 +3395,13 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) { struct reclaim_state reclaim_state; struct scan_control sc = { + .nr_to_reclaim = nr_to_reclaim, .gfp_mask = GFP_HIGHUSER_MOVABLE, - .may_swap = 1, - .may_unmap = 1, + .priority = DEF_PRIORITY, .may_writepage = 1, - .nr_to_reclaim = nr_to_reclaim, + .may_unmap = 1, + .may_swap = 1, .hibernation_mode = 1, - .order = 0, - .priority = DEF_PRIORITY, }; struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); struct task_struct *p = current; @@ -3588,13 +3581,13 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) struct task_struct *p = current; struct reclaim_state reclaim_state; struct scan_control sc = { - .may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE), - .may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP), - .may_swap = 1, .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)), .order = order, .priority = ZONE_RECLAIM_PRIORITY, + .may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE), + .may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP), + .may_swap = 1, }; struct shrink_control shrink = { .gfp_mask = sc.gfp_mask, -- cgit v1.2.3 From d0480be44a90af81a425f426c9107fb8f0899f65 Mon Sep 17 00:00:00 2001 From: Wang Sheng-Hui Date: Wed, 6 Aug 2014 16:07:07 -0700 Subject: mm: update the description for vm_total_pages vm_total_pages is calculated by nr_free_pagecache_pages(), which counts the number of pages which are beyond the high watermark within all zones. So vm_total_pages is not equal to total number of pages which the VM controls. Signed-off-by: Wang Sheng-Hui Cc: Mel Gorman Cc: Rik van Riel Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'mm/vmscan.c') diff --git a/mm/vmscan.c b/mm/vmscan.c index 81dd858b9d17..5fec1ba9951f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -137,7 +137,11 @@ struct scan_control { * From 0 .. 100. Higher means more swappy. */ int vm_swappiness = 60; -unsigned long vm_total_pages; /* The total number of pages which the VM controls */ +/* + * The total number of pages which are beyond the high watermark within all + * zones. + */ +unsigned long vm_total_pages; static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); -- cgit v1.2.3 From 0d5d823ab4e608ec7b52ac4410de4cb74bbe0edd Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 6 Aug 2014 16:07:16 -0700 Subject: mm: move zone->pages_scanned into a vmstat counter zone->pages_scanned is a write-intensive cache line during page reclaim and it's also updated during page free. Move the counter into vmstat to take advantage of the per-cpu updates and do not update it in the free paths unless necessary. On a small UMA machine running tiobench the difference is marginal. On a 4-node machine the overhead is more noticable. Note that automatic NUMA balancing was disabled for this test as otherwise the system CPU overhead is unpredictable. 3.16.0-rc3 3.16.0-rc3 3.16.0-rc3 vanillarearrange-v5 vmstat-v5 User 746.94 759.78 774.56 System 65336.22 58350.98 32847.27 Elapsed 27553.52 27282.02 27415.04 Note that the overhead reduction will vary depending on where exactly pages are allocated and freed. Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- mm/page_alloc.c | 12 +++++++++--- mm/vmscan.c | 7 ++++--- mm/vmstat.c | 3 ++- 4 files changed, 16 insertions(+), 8 deletions(-) (limited to 'mm/vmscan.c') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ed0876bb902c..0bd77f730b38 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -143,6 +143,7 @@ enum zone_stat_item { NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ + NR_PAGES_SCANNED, /* pages scanned since last reclaim */ #ifdef CONFIG_NUMA NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ @@ -480,7 +481,6 @@ struct zone { /* Fields commonly accessed by the page reclaim scanner */ spinlock_t lru_lock; - unsigned long pages_scanned; /* since last reclaim */ struct lruvec lruvec; /* Evictions & activations on the inactive file list */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index b7381d11f021..daa016063793 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -680,9 +680,12 @@ static void free_pcppages_bulk(struct zone *zone, int count, int migratetype = 0; int batch_free = 0; int to_free = count; + unsigned long nr_scanned; spin_lock(&zone->lock); - zone->pages_scanned = 0; + nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + if (nr_scanned) + __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); while (to_free) { struct page *page; @@ -731,8 +734,11 @@ static void free_one_page(struct zone *zone, unsigned int order, int migratetype) { + unsigned long nr_scanned; spin_lock(&zone->lock); - zone->pages_scanned = 0; + nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + if (nr_scanned) + __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); __free_one_page(page, pfn, zone, order, migratetype); if (unlikely(!is_migrate_isolate(migratetype))) @@ -3248,7 +3254,7 @@ void show_free_areas(unsigned int filter) K(zone_page_state(zone, NR_BOUNCE)), K(zone_page_state(zone, NR_FREE_CMA_PAGES)), K(zone_page_state(zone, NR_WRITEBACK_TEMP)), - zone->pages_scanned, + K(zone_page_state(zone, NR_PAGES_SCANNED)), (!zone_reclaimable(zone) ? "yes" : "no") ); printk("lowmem_reserve[]:"); diff --git a/mm/vmscan.c b/mm/vmscan.c index 5fec1ba9951f..9c8222b499b4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -174,7 +174,8 @@ static unsigned long zone_reclaimable_pages(struct zone *zone) bool zone_reclaimable(struct zone *zone) { - return zone->pages_scanned < zone_reclaimable_pages(zone) * 6; + return zone_page_state(zone, NR_PAGES_SCANNED) < + zone_reclaimable_pages(zone) * 6; } static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru) @@ -1508,7 +1509,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken); if (global_reclaim(sc)) { - zone->pages_scanned += nr_scanned; + __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned); if (current_is_kswapd()) __count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scanned); else @@ -1698,7 +1699,7 @@ static void shrink_active_list(unsigned long nr_to_scan, nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, isolate_mode, lru); if (global_reclaim(sc)) - zone->pages_scanned += nr_scanned; + __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned); reclaim_stat->recent_scanned[file] += nr_taken; diff --git a/mm/vmstat.c b/mm/vmstat.c index 8267f77d1875..e574e883fa70 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -763,6 +763,7 @@ const char * const vmstat_text[] = { "nr_shmem", "nr_dirtied", "nr_written", + "nr_pages_scanned", #ifdef CONFIG_NUMA "numa_hit", @@ -1067,7 +1068,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), - zone->pages_scanned, + zone_page_state(zone, NR_PAGES_SCANNED), zone->spanned_pages, zone->present_pages, zone->managed_pages); -- cgit v1.2.3 From 7c0db9e917f77e6de2a524b33b5436491850dc79 Mon Sep 17 00:00:00 2001 From: Jerome Marchand Date: Wed, 6 Aug 2014 16:08:01 -0700 Subject: mm, vmscan: fix an outdated comment still mentioning get_scan_ratio Quite a while ago, get_scan_ratio() has been renamed get_scan_count(), however a comment in shrink_active_list() still mention it. This patch fixes the outdated comment. Signed-off-by: Jerome Marchand Cc: Michal Hocko Cc: Johannes Weiner Cc: Rik van Riel Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/vmscan.c') diff --git a/mm/vmscan.c b/mm/vmscan.c index 9c8222b499b4..88ab53c9949a 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1756,7 +1756,7 @@ static void shrink_active_list(unsigned long nr_to_scan, * Count referenced pages from currently used mappings as rotated, * even though only some of them are actually re-activated. This * helps balance scan pressure between file and anonymous pages in - * get_scan_ratio. + * get_scan_count. */ reclaim_stat->recent_rotated[file] += nr_rotated; -- cgit v1.2.3 From 2ab051e11bfa3cbb7b24177f3d6aaed10a0d743e Mon Sep 17 00:00:00 2001 From: Jerome Marchand Date: Wed, 6 Aug 2014 16:08:03 -0700 Subject: memcg, vmscan: Fix forced scan of anonymous pages When memory cgoups are enabled, the code that decides to force to scan anonymous pages in get_scan_count() compares global values (free, high_watermark) to a value that is restricted to a memory cgroup (file). It make the code over-eager to force anon scan. For instance, it will force anon scan when scanning a memcg that is mainly populated by anonymous page, even when there is plenty of file pages to get rid of in others memcgs, even when swappiness == 0. It breaks user's expectation about swappiness and hurts performance. This patch makes sure that forced anon scan only happens when there not enough file pages for the all zone, not just in one random memcg. [hannes@cmpxchg.org: cleanups] Signed-off-by: Jerome Marchand Acked-by: Michal Hocko Acked-by: Johannes Weiner Reviewed-by: Rik van Riel Cc: Mel Gorman Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) (limited to 'mm/vmscan.c') diff --git a/mm/vmscan.c b/mm/vmscan.c index 88ab53c9949a..d2f65c856350 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1930,11 +1930,6 @@ static void get_scan_count(struct lruvec *lruvec, int swappiness, goto out; } - anon = get_lru_size(lruvec, LRU_ACTIVE_ANON) + - get_lru_size(lruvec, LRU_INACTIVE_ANON); - 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 @@ -1945,9 +1940,14 @@ static void get_scan_count(struct lruvec *lruvec, int swappiness, * anon pages. Try to detect this based on file LRU size. */ if (global_reclaim(sc)) { - unsigned long free = zone_page_state(zone, NR_FREE_PAGES); + unsigned long zonefile; + unsigned long zonefree; + + zonefree = zone_page_state(zone, NR_FREE_PAGES); + zonefile = zone_page_state(zone, NR_ACTIVE_FILE) + + zone_page_state(zone, NR_INACTIVE_FILE); - if (unlikely(file + free <= high_wmark_pages(zone))) { + if (unlikely(zonefile + zonefree <= high_wmark_pages(zone))) { scan_balance = SCAN_ANON; goto out; } @@ -1982,6 +1982,12 @@ static void get_scan_count(struct lruvec *lruvec, int swappiness, * * anon in [0], file in [1] */ + + anon = get_lru_size(lruvec, LRU_ACTIVE_ANON) + + get_lru_size(lruvec, LRU_INACTIVE_ANON); + file = get_lru_size(lruvec, LRU_ACTIVE_FILE) + + get_lru_size(lruvec, LRU_INACTIVE_FILE); + spin_lock_irq(&zone->lru_lock); if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) { reclaim_stat->recent_scanned[0] /= 2; -- cgit v1.2.3 From 0a31bc97c80c3fa87b32c091d9a930ac19cd0c40 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 8 Aug 2014 14:19:22 -0700 Subject: mm: memcontrol: rewrite uncharge API The memcg uncharging code that is involved towards the end of a page's lifetime - truncation, reclaim, swapout, migration - is impressively complicated and fragile. Because anonymous and file pages were always charged before they had their page->mapping established, uncharges had to happen when the page type could still be known from the context; as in unmap for anonymous, page cache removal for file and shmem pages, and swap cache truncation for swap pages. However, these operations happen well before the page is actually freed, and so a lot of synchronization is necessary: - Charging, uncharging, page migration, and charge migration all need to take a per-page bit spinlock as they could race with uncharging. - Swap cache truncation happens during both swap-in and swap-out, and possibly repeatedly before the page is actually freed. This means that the memcg swapout code is called from many contexts that make no sense and it has to figure out the direction from page state to make sure memory and memory+swap are always correctly charged. - On page migration, the old page might be unmapped but then reused, so memcg code has to prevent untimely uncharging in that case. Because this code - which should be a simple charge transfer - is so special-cased, it is not reusable for replace_page_cache(). But now that charged pages always have a page->mapping, introduce mem_cgroup_uncharge(), which is called after the final put_page(), when we know for sure that nobody is looking at the page anymore. For page migration, introduce mem_cgroup_migrate(), which is called after the migration is successful and the new page is fully rmapped. Because the old page is no longer uncharged after migration, prevent double charges by decoupling the page's memcg association (PCG_USED and pc->mem_cgroup) from the page holding an actual charge. The new bits PCG_MEM and PCG_MEMSW represent the respective charges and are transferred to the new page during migration. mem_cgroup_migrate() is suitable for replace_page_cache() as well, which gets rid of mem_cgroup_replace_page_cache(). However, care needs to be taken because both the source and the target page can already be charged and on the LRU when fuse is splicing: grab the page lock on the charge moving side to prevent changing pc->mem_cgroup of a page under migration. Also, the lruvecs of both pages change as we uncharge the old and charge the new during migration, and putback may race with us, so grab the lru lock and isolate the pages iff on LRU to prevent races and ensure the pages are on the right lruvec afterward. Swap accounting is massively simplified: because the page is no longer uncharged as early as swap cache deletion, a new mem_cgroup_swapout() can transfer the page's memory+swap charge (PCG_MEMSW) to the swap entry before the final put_page() in page reclaim. Finally, page_cgroup changes are now protected by whatever protection the page itself offers: anonymous pages are charged under the page table lock, whereas page cache insertions, swapin, and migration hold the page lock. Uncharging happens under full exclusion with no outstanding references. Charging and uncharging also ensure that the page is off-LRU, which serializes against charge migration. Remove the very costly page_cgroup lock and set pc->flags non-atomically. [mhocko@suse.cz: mem_cgroup_charge_statistics needs preempt_disable] [vdavydov@parallels.com: fix flags definition] Signed-off-by: Johannes Weiner Cc: Hugh Dickins Cc: Tejun Heo Cc: Vladimir Davydov Tested-by: Jet Chen Acked-by: Michal Hocko Tested-by: Felipe Balbi Signed-off-by: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/memcg_test.txt | 128 +----- include/linux/memcontrol.h | 49 +-- include/linux/page_cgroup.h | 43 +- include/linux/swap.h | 12 +- mm/filemap.c | 4 +- mm/memcontrol.c | 828 ++++++++++++++--------------------- mm/memory.c | 2 - mm/migrate.c | 38 +- mm/rmap.c | 1 - mm/shmem.c | 8 +- mm/swap.c | 6 + mm/swap_state.c | 8 +- mm/swapfile.c | 7 +- mm/truncate.c | 9 - mm/vmscan.c | 12 +- mm/zswap.c | 2 +- 16 files changed, 389 insertions(+), 768 deletions(-) (limited to 'mm/vmscan.c') diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt index bcf750d3cecd..8870b0212150 100644 --- a/Documentation/cgroups/memcg_test.txt +++ b/Documentation/cgroups/memcg_test.txt @@ -29,28 +29,13 @@ Please note that implementation details can be changed. 2. Uncharge a page/swp_entry may be uncharged (usage -= PAGE_SIZE) by - mem_cgroup_uncharge_page() - Called when an anonymous page is fully unmapped. I.e., mapcount goes - to 0. If the page is SwapCache, uncharge is delayed until - mem_cgroup_uncharge_swapcache(). - - mem_cgroup_uncharge_cache_page() - Called when a page-cache is deleted from radix-tree. If the page is - SwapCache, uncharge is delayed until mem_cgroup_uncharge_swapcache(). - - mem_cgroup_uncharge_swapcache() - Called when SwapCache is removed from radix-tree. The charge itself - is moved to swap_cgroup. (If mem+swap controller is disabled, no - charge to swap occurs.) + mem_cgroup_uncharge() + Called when a page's refcount goes down to 0. mem_cgroup_uncharge_swap() Called when swp_entry's refcnt goes down to 0. A charge against swap disappears. - mem_cgroup_end_migration(old, new) - At success of migration old is uncharged (if necessary), a charge - to new page is committed. At failure, charge to old page is committed. - 3. charge-commit-cancel Memcg pages are charged in two steps: mem_cgroup_try_charge() @@ -69,18 +54,6 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. Anonymous page is newly allocated at - page fault into MAP_ANONYMOUS mapping. - Copy-On-Write. - It is charged right after it's allocated before doing any page table - related operations. Of course, it's uncharged when another page is used - for the fault address. - - At freeing anonymous page (by exit() or munmap()), zap_pte() is called - and pages for ptes are freed one by one.(see mm/memory.c). Uncharges - are done at page_remove_rmap() when page_mapcount() goes down to 0. - - Another page freeing is by page-reclaim (vmscan.c) and anonymous - pages are swapped out. In this case, the page is marked as - PageSwapCache(). uncharge() routine doesn't uncharge the page marked - as SwapCache(). It's delayed until __delete_from_swap_cache(). 4.1 Swap-in. At swap-in, the page is taken from swap-cache. There are 2 cases. @@ -89,41 +62,6 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. (b) If the SwapCache has been mapped by processes, it has been charged already. - This swap-in is one of the most complicated work. In do_swap_page(), - following events occur when pte is unchanged. - - (1) the page (SwapCache) is looked up. - (2) lock_page() - (3) try_charge_swapin() - (4) reuse_swap_page() (may call delete_swap_cache()) - (5) commit_charge_swapin() - (6) swap_free(). - - Considering following situation for example. - - (A) The page has not been charged before (2) and reuse_swap_page() - doesn't call delete_from_swap_cache(). - (B) The page has not been charged before (2) and reuse_swap_page() - calls delete_from_swap_cache(). - (C) The page has been charged before (2) and reuse_swap_page() doesn't - call delete_from_swap_cache(). - (D) The page has been charged before (2) and reuse_swap_page() calls - delete_from_swap_cache(). - - memory.usage/memsw.usage changes to this page/swp_entry will be - Case (A) (B) (C) (D) - Event - Before (2) 0/ 1 0/ 1 1/ 1 1/ 1 - =========================================== - (3) +1/+1 +1/+1 +1/+1 +1/+1 - (4) - 0/ 0 - -1/ 0 - (5) 0/-1 0/ 0 -1/-1 0/ 0 - (6) - 0/-1 - 0/-1 - =========================================== - Result 1/ 1 1/ 1 1/ 1 1/ 1 - - In any cases, charges to this page should be 1/ 1. - 4.2 Swap-out. At swap-out, typical state transition is below. @@ -136,28 +74,20 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. swp_entry's refcnt -= 1. - At (b), the page is marked as SwapCache and not uncharged. - At (d), the page is removed from SwapCache and a charge in page_cgroup - is moved to swap_cgroup. - Finally, at task exit, (e) zap_pte() is called and swp_entry's refcnt -=1 -> 0. - Here, a charge in swap_cgroup disappears. 5. Page Cache Page Cache is charged at - add_to_page_cache_locked(). - uncharged at - - __remove_from_page_cache(). - The logic is very clear. (About migration, see below) Note: __remove_from_page_cache() is called by remove_from_page_cache() and __remove_mapping(). 6. Shmem(tmpfs) Page Cache - Memcg's charge/uncharge have special handlers of shmem. The best way - to understand shmem's page state transition is to read mm/shmem.c. + The best way to understand shmem's page state transition is to read + mm/shmem.c. But brief explanation of the behavior of memcg around shmem will be helpful to understand the logic. @@ -170,56 +100,10 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. It's charged when... - A new page is added to shmem's radix-tree. - A swp page is read. (move a charge from swap_cgroup to page_cgroup) - It's uncharged when - - A page is removed from radix-tree and not SwapCache. - - When SwapCache is removed, a charge is moved to swap_cgroup. - - When swp_entry's refcnt goes down to 0, a charge in swap_cgroup - disappears. 7. Page Migration - One of the most complicated functions is page-migration-handler. - Memcg has 2 routines. Assume that we are migrating a page's contents - from OLDPAGE to NEWPAGE. - - Usual migration logic is.. - (a) remove the page from LRU. - (b) allocate NEWPAGE (migration target) - (c) lock by lock_page(). - (d) unmap all mappings. - (e-1) If necessary, replace entry in radix-tree. - (e-2) move contents of a page. - (f) map all mappings again. - (g) pushback the page to LRU. - (-) OLDPAGE will be freed. - - Before (g), memcg should complete all necessary charge/uncharge to - NEWPAGE/OLDPAGE. - - The point is.... - - If OLDPAGE is anonymous, all charges will be dropped at (d) because - try_to_unmap() drops all mapcount and the page will not be - SwapCache. - - - If OLDPAGE is SwapCache, charges will be kept at (g) because - __delete_from_swap_cache() isn't called at (e-1) - - - If OLDPAGE is page-cache, charges will be kept at (g) because - remove_from_swap_cache() isn't called at (e-1) - - memcg provides following hooks. - - - mem_cgroup_prepare_migration(OLDPAGE) - Called after (b) to account a charge (usage += PAGE_SIZE) against - memcg which OLDPAGE belongs to. - - - mem_cgroup_end_migration(OLDPAGE, NEWPAGE) - Called after (f) before (g). - If OLDPAGE is used, commit OLDPAGE again. If OLDPAGE is already - charged, a charge by prepare_migration() is automatically canceled. - If NEWPAGE is used, commit NEWPAGE and uncharge OLDPAGE. - - But zap_pte() (by exit or munmap) can be called while migration, - we have to check if OLDPAGE/NEWPAGE is a valid page after commit(). + + mem_cgroup_migrate() 8. LRU Each memcg has its own private LRU. Now, its handling is under global diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1a9a096858e0..806b8fa15c5f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -60,15 +60,17 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, bool lrucare); void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); -struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *); -struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); +void mem_cgroup_uncharge(struct page *page); + +/* Batched uncharging */ +void mem_cgroup_uncharge_start(void); +void mem_cgroup_uncharge_end(void); -/* For coalescing uncharge for reducing memcg' overhead*/ -extern void mem_cgroup_uncharge_start(void); -extern void mem_cgroup_uncharge_end(void); +void mem_cgroup_migrate(struct page *oldpage, struct page *newpage, + bool lrucare); -extern void mem_cgroup_uncharge_page(struct page *page); -extern void mem_cgroup_uncharge_cache_page(struct page *page); +struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *); +struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, struct mem_cgroup *memcg); @@ -96,12 +98,6 @@ bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg) extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg); -extern void -mem_cgroup_prepare_migration(struct page *page, struct page *newpage, - struct mem_cgroup **memcgp); -extern void mem_cgroup_end_migration(struct mem_cgroup *memcg, - struct page *oldpage, struct page *newpage, bool migration_ok); - struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); @@ -116,8 +112,6 @@ unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list); void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int); extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p); -extern void mem_cgroup_replace_page_cache(struct page *oldpage, - struct page *newpage); static inline void mem_cgroup_oom_enable(void) { @@ -235,19 +229,21 @@ static inline void mem_cgroup_cancel_charge(struct page *page, { } -static inline void mem_cgroup_uncharge_start(void) +static inline void mem_cgroup_uncharge(struct page *page) { } -static inline void mem_cgroup_uncharge_end(void) +static inline void mem_cgroup_uncharge_start(void) { } -static inline void mem_cgroup_uncharge_page(struct page *page) +static inline void mem_cgroup_uncharge_end(void) { } -static inline void mem_cgroup_uncharge_cache_page(struct page *page) +static inline void mem_cgroup_migrate(struct page *oldpage, + struct page *newpage, + bool lrucare) { } @@ -286,17 +282,6 @@ static inline struct cgroup_subsys_state return NULL; } -static inline void -mem_cgroup_prepare_migration(struct page *page, struct page *newpage, - struct mem_cgroup **memcgp) -{ -} - -static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg, - struct page *oldpage, struct page *newpage, bool migration_ok) -{ -} - static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, @@ -392,10 +377,6 @@ static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx) { } -static inline void mem_cgroup_replace_page_cache(struct page *oldpage, - struct page *newpage) -{ -} #endif /* CONFIG_MEMCG */ #if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM) diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index 777a524716db..9bfb8e68a595 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -3,9 +3,9 @@ enum { /* flags for mem_cgroup */ - PCG_LOCK, /* Lock for pc->mem_cgroup and following bits. */ - PCG_USED, /* this object is in use. */ - PCG_MIGRATION, /* under page migration */ + PCG_USED = 0x01, /* This page is charged to a memcg */ + PCG_MEM = 0x02, /* This page holds a memory charge */ + PCG_MEMSW = 0x04, /* This page holds a memory+swap charge */ __NR_PCG_FLAGS, }; @@ -44,42 +44,9 @@ static inline void __init page_cgroup_init(void) struct page_cgroup *lookup_page_cgroup(struct page *page); struct page *lookup_cgroup_page(struct page_cgroup *pc); -#define TESTPCGFLAG(uname, lname) \ -static inline int PageCgroup##uname(struct page_cgroup *pc) \ - { return test_bit(PCG_##lname, &pc->flags); } - -#define SETPCGFLAG(uname, lname) \ -static inline void SetPageCgroup##uname(struct page_cgroup *pc)\ - { set_bit(PCG_##lname, &pc->flags); } - -#define CLEARPCGFLAG(uname, lname) \ -static inline void ClearPageCgroup##uname(struct page_cgroup *pc) \ - { clear_bit(PCG_##lname, &pc->flags); } - -#define TESTCLEARPCGFLAG(uname, lname) \ -static inline int TestClearPageCgroup##uname(struct page_cgroup *pc) \ - { return test_and_clear_bit(PCG_##lname, &pc->flags); } - -TESTPCGFLAG(Used, USED) -CLEARPCGFLAG(Used, USED) -SETPCGFLAG(Used, USED) - -SETPCGFLAG(Migration, MIGRATION) -CLEARPCGFLAG(Migration, MIGRATION) -TESTPCGFLAG(Migration, MIGRATION) - -static inline void lock_page_cgroup(struct page_cgroup *pc) -{ - /* - * Don't take this lock in IRQ context. - * This lock is for pc->mem_cgroup, USED, MIGRATION - */ - bit_spin_lock(PCG_LOCK, &pc->flags); -} - -static inline void unlock_page_cgroup(struct page_cgroup *pc) +static inline int PageCgroupUsed(struct page_cgroup *pc) { - bit_spin_unlock(PCG_LOCK, &pc->flags); + return !!(pc->flags & PCG_USED); } #else /* CONFIG_MEMCG */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 46a649e4e8cd..1b72060f093a 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -381,9 +381,13 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) } #endif #ifdef CONFIG_MEMCG_SWAP -extern void mem_cgroup_uncharge_swap(swp_entry_t ent); +extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry); +extern void mem_cgroup_uncharge_swap(swp_entry_t entry); #else -static inline void mem_cgroup_uncharge_swap(swp_entry_t ent) +static inline void mem_cgroup_swapout(struct page *page, swp_entry_t entry) +{ +} +static inline void mem_cgroup_uncharge_swap(swp_entry_t entry) { } #endif @@ -443,7 +447,7 @@ extern void swap_shmem_alloc(swp_entry_t); extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t); extern void swap_free(swp_entry_t); -extern void swapcache_free(swp_entry_t, struct page *page); +extern void swapcache_free(swp_entry_t); extern int free_swap_and_cache(swp_entry_t); extern int swap_type_of(dev_t, sector_t, struct block_device **); extern unsigned int count_swap_pages(int, int); @@ -507,7 +511,7 @@ static inline void swap_free(swp_entry_t swp) { } -static inline void swapcache_free(swp_entry_t swp, struct page *page) +static inline void swapcache_free(swp_entry_t swp) { } diff --git a/mm/filemap.c b/mm/filemap.c index 349a40e35545..f501b56ec2c6 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -234,7 +234,6 @@ void delete_from_page_cache(struct page *page) spin_lock_irq(&mapping->tree_lock); __delete_from_page_cache(page, NULL); spin_unlock_irq(&mapping->tree_lock); - mem_cgroup_uncharge_cache_page(page); if (freepage) freepage(page); @@ -490,8 +489,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) if (PageSwapBacked(new)) __inc_zone_page_state(new, NR_SHMEM); spin_unlock_irq(&mapping->tree_lock); - /* mem_cgroup codes must not be called under tree_lock */ - mem_cgroup_replace_page_cache(old, new); + mem_cgroup_migrate(old, new, true); radix_tree_preload_end(); if (freepage) freepage(old); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1cbe1e54ff5f..9106f1b12f56 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -754,9 +754,11 @@ static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, struct mem_cgroup_tree_per_zone *mctz) { - spin_lock(&mctz->lock); + unsigned long flags; + + spin_lock_irqsave(&mctz->lock, flags); __mem_cgroup_remove_exceeded(mz, mctz); - spin_unlock(&mctz->lock); + spin_unlock_irqrestore(&mctz->lock, flags); } @@ -779,7 +781,9 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) * mem is over its softlimit. */ if (excess || mz->on_tree) { - spin_lock(&mctz->lock); + unsigned long flags; + + spin_lock_irqsave(&mctz->lock, flags); /* if on-tree, remove it */ if (mz->on_tree) __mem_cgroup_remove_exceeded(mz, mctz); @@ -788,7 +792,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) * If excess is 0, no tree ops. */ __mem_cgroup_insert_exceeded(mz, mctz, excess); - spin_unlock(&mctz->lock); + spin_unlock_irqrestore(&mctz->lock, flags); } } } @@ -839,9 +843,9 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) { struct mem_cgroup_per_zone *mz; - spin_lock(&mctz->lock); + spin_lock_irq(&mctz->lock); mz = __mem_cgroup_largest_soft_limit_node(mctz); - spin_unlock(&mctz->lock); + spin_unlock_irq(&mctz->lock); return mz; } @@ -882,13 +886,6 @@ static long mem_cgroup_read_stat(struct mem_cgroup *memcg, return val; } -static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg, - bool charge) -{ - int val = (charge) ? 1 : -1; - this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAP], val); -} - static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, enum mem_cgroup_events_index idx) { @@ -909,13 +906,13 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, struct page *page, - bool anon, int nr_pages) + int nr_pages) { /* * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is * counted as CACHE even if it's on ANON LRU. */ - if (anon) + if (PageAnon(page)) __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS], nr_pages); else @@ -1013,7 +1010,6 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, */ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) { - preempt_disable(); /* threshold event is triggered in finer grain than soft limit */ if (unlikely(mem_cgroup_event_ratelimit(memcg, MEM_CGROUP_TARGET_THRESH))) { @@ -1026,8 +1022,6 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) do_numainfo = mem_cgroup_event_ratelimit(memcg, MEM_CGROUP_TARGET_NUMAINFO); #endif - preempt_enable(); - mem_cgroup_threshold(memcg); if (unlikely(do_softlimit)) mem_cgroup_update_tree(memcg, page); @@ -1035,8 +1029,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) if (unlikely(do_numainfo)) atomic_inc(&memcg->numainfo_events); #endif - } else - preempt_enable(); + } } struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) @@ -1347,20 +1340,6 @@ out: return lruvec; } -/* - * Following LRU functions are allowed to be used without PCG_LOCK. - * Operations are called by routine of global LRU independently from memcg. - * What we have to take care of here is validness of pc->mem_cgroup. - * - * Changes to pc->mem_cgroup happens when - * 1. charge - * 2. moving account - * In typical case, "charge" is done before add-to-lru. Exception is SwapCache. - * It is added to LRU before charge. - * If PCG_USED bit is not set, page_cgroup is not added to this private LRU. - * When moving account, the page is not on LRU. It's isolated. - */ - /** * mem_cgroup_page_lruvec - return lruvec for adding an lru page * @page: the page @@ -2261,22 +2240,14 @@ cleanup: * * Notes: Race condition * - * We usually use lock_page_cgroup() for accessing page_cgroup member but - * it tends to be costly. But considering some conditions, we doesn't need - * to do so _always_. - * - * Considering "charge", lock_page_cgroup() is not required because all - * file-stat operations happen after a page is attached to radix-tree. There - * are no race with "charge". + * Charging occurs during page instantiation, while the page is + * unmapped and locked in page migration, or while the page table is + * locked in THP migration. No race is possible. * - * Considering "uncharge", we know that memcg doesn't clear pc->mem_cgroup - * at "uncharge" intentionally. So, we always see valid pc->mem_cgroup even - * if there are race with "uncharge". Statistics itself is properly handled - * by flags. + * Uncharge happens to pages with zero references, no race possible. * - * Considering "move", this is an only case we see a race. To make the race - * small, we check memcg->moving_account and detect there are possibility - * of race or not. If there is, we take a lock. + * Charge moving between groups is protected by checking mm->moving + * account and taking the move_lock in the slowpath. */ void __mem_cgroup_begin_update_page_stat(struct page *page, @@ -2689,6 +2660,16 @@ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) return mem_cgroup_from_id(id); } +/* + * try_get_mem_cgroup_from_page - look up page's memcg association + * @page: the page + * + * Look up, get a css reference, and return the memcg that owns @page. + * + * The page must be locked to prevent racing with swap-in and page + * cache charges. If coming from an unlocked page table, the caller + * must ensure the page is on the LRU or this can race with charging. + */ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) { struct mem_cgroup *memcg = NULL; @@ -2699,7 +2680,6 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) VM_BUG_ON_PAGE(!PageLocked(page), page); pc = lookup_page_cgroup(page); - lock_page_cgroup(pc); if (PageCgroupUsed(pc)) { memcg = pc->mem_cgroup; if (memcg && !css_tryget_online(&memcg->css)) @@ -2713,19 +2693,46 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) memcg = NULL; rcu_read_unlock(); } - unlock_page_cgroup(pc); return memcg; } +static void lock_page_lru(struct page *page, int *isolated) +{ + struct zone *zone = page_zone(page); + + spin_lock_irq(&zone->lru_lock); + if (PageLRU(page)) { + struct lruvec *lruvec; + + lruvec = mem_cgroup_page_lruvec(page, zone); + ClearPageLRU(page); + del_page_from_lru_list(page, lruvec, page_lru(page)); + *isolated = 1; + } else + *isolated = 0; +} + +static void unlock_page_lru(struct page *page, int isolated) +{ + struct zone *zone = page_zone(page); + + if (isolated) { + struct lruvec *lruvec; + + lruvec = mem_cgroup_page_lruvec(page, zone); + VM_BUG_ON_PAGE(PageLRU(page), page); + SetPageLRU(page); + add_page_to_lru_list(page, lruvec, page_lru(page)); + } + spin_unlock_irq(&zone->lru_lock); +} + static void commit_charge(struct page *page, struct mem_cgroup *memcg, - unsigned int nr_pages, bool anon, bool lrucare) + unsigned int nr_pages, bool lrucare) { struct page_cgroup *pc = lookup_page_cgroup(page); - struct zone *uninitialized_var(zone); - struct lruvec *lruvec; - bool was_on_lru = false; + int isolated; - lock_page_cgroup(pc); VM_BUG_ON_PAGE(PageCgroupUsed(pc), page); /* * we don't need page_cgroup_lock about tail pages, becase they are not @@ -2736,39 +2743,38 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg, * In some cases, SwapCache and FUSE(splice_buf->radixtree), the page * may already be on some other mem_cgroup's LRU. Take care of it. */ - if (lrucare) { - zone = page_zone(page); - spin_lock_irq(&zone->lru_lock); - if (PageLRU(page)) { - lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup); - ClearPageLRU(page); - del_page_from_lru_list(page, lruvec, page_lru(page)); - was_on_lru = true; - } - } + if (lrucare) + lock_page_lru(page, &isolated); + /* + * Nobody should be changing or seriously looking at + * pc->mem_cgroup and pc->flags at this point: + * + * - the page is uncharged + * + * - the page is off-LRU + * + * - an anonymous fault has exclusive page access, except for + * a locked page table + * + * - a page cache insertion, a swapin fault, or a migration + * have the page locked + */ pc->mem_cgroup = memcg; - SetPageCgroupUsed(pc); - - if (lrucare) { - if (was_on_lru) { - lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup); - VM_BUG_ON_PAGE(PageLRU(page), page); - SetPageLRU(page); - add_page_to_lru_list(page, lruvec, page_lru(page)); - } - spin_unlock_irq(&zone->lru_lock); - } + pc->flags = PCG_USED | PCG_MEM | (do_swap_account ? PCG_MEMSW : 0); - mem_cgroup_charge_statistics(memcg, page, anon, nr_pages); - unlock_page_cgroup(pc); + if (lrucare) + unlock_page_lru(page, isolated); + local_irq_disable(); + mem_cgroup_charge_statistics(memcg, page, nr_pages); /* * "charge_statistics" updated event counter. Then, check it. * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree. * if they exceeds softlimit. */ memcg_check_events(memcg, page); + local_irq_enable(); } static DEFINE_MUTEX(set_limit_mutex); @@ -3395,7 +3401,6 @@ static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg) #ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define PCGF_NOCOPY_AT_SPLIT (1 << PCG_LOCK | 1 << PCG_MIGRATION) /* * Because tail pages are not marked as "used", set it. We're under * zone->lru_lock, 'splitting on pmd' and compound_lock. @@ -3416,7 +3421,7 @@ void mem_cgroup_split_huge_fixup(struct page *head) for (i = 1; i < HPAGE_PMD_NR; i++) { pc = head_pc + i; pc->mem_cgroup = memcg; - pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT; + pc->flags = head_pc->flags; } __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], HPAGE_PMD_NR); @@ -3446,7 +3451,6 @@ static int mem_cgroup_move_account(struct page *page, { unsigned long flags; int ret; - bool anon = PageAnon(page); VM_BUG_ON(from == to); VM_BUG_ON_PAGE(PageLRU(page), page); @@ -3460,15 +3464,21 @@ static int mem_cgroup_move_account(struct page *page, if (nr_pages > 1 && !PageTransHuge(page)) goto out; - lock_page_cgroup(pc); + /* + * Prevent mem_cgroup_migrate() from looking at pc->mem_cgroup + * of its source page while we change it: page migration takes + * both pages off the LRU, but page cache replacement doesn't. + */ + if (!trylock_page(page)) + goto out; ret = -EINVAL; if (!PageCgroupUsed(pc) || pc->mem_cgroup != from) - goto unlock; + goto out_unlock; move_lock_mem_cgroup(from, &flags); - if (!anon && page_mapped(page)) { + if (!PageAnon(page) && 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], @@ -3482,20 +3492,25 @@ static int mem_cgroup_move_account(struct page *page, nr_pages); } - mem_cgroup_charge_statistics(from, page, anon, -nr_pages); + /* + * It is safe to change pc->mem_cgroup here because the page + * is referenced, charged, and isolated - we can't race with + * uncharging, charging, migration, or LRU putback. + */ /* caller should have done css_get */ pc->mem_cgroup = to; - mem_cgroup_charge_statistics(to, page, anon, nr_pages); move_unlock_mem_cgroup(from, &flags); ret = 0; -unlock: - unlock_page_cgroup(pc); - /* - * check events - */ + + local_irq_disable(); + mem_cgroup_charge_statistics(to, page, nr_pages); memcg_check_events(to, page); + mem_cgroup_charge_statistics(from, page, -nr_pages); memcg_check_events(from, page); + local_irq_enable(); +out_unlock: + unlock_page(page); out: return ret; } @@ -3566,193 +3581,6 @@ out: return ret; } -static void mem_cgroup_do_uncharge(struct mem_cgroup *memcg, - unsigned int nr_pages, - const enum charge_type ctype) -{ - struct memcg_batch_info *batch = NULL; - bool uncharge_memsw = true; - - /* If swapout, usage of swap doesn't decrease */ - if (!do_swap_account || ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) - uncharge_memsw = false; - - batch = ¤t->memcg_batch; - /* - * In usual, we do css_get() when we remember memcg pointer. - * But in this case, we keep res->usage until end of a series of - * uncharges. Then, it's ok to ignore memcg's refcnt. - */ - if (!batch->memcg) - batch->memcg = memcg; - /* - * do_batch > 0 when unmapping pages or inode invalidate/truncate. - * In those cases, all pages freed continuously can be expected to be in - * the same cgroup and we have chance to coalesce uncharges. - * But we do uncharge one by one if this is killed by OOM(TIF_MEMDIE) - * because we want to do uncharge as soon as possible. - */ - - if (!batch->do_batch || test_thread_flag(TIF_MEMDIE)) - goto direct_uncharge; - - if (nr_pages > 1) - goto direct_uncharge; - - /* - * In typical case, batch->memcg == mem. This means we can - * merge a series of uncharges to an uncharge of res_counter. - * If not, we uncharge res_counter ony by one. - */ - if (batch->memcg != memcg) - goto direct_uncharge; - /* remember freed charge and uncharge it later */ - batch->nr_pages++; - if (uncharge_memsw) - batch->memsw_nr_pages++; - return; -direct_uncharge: - res_counter_uncharge(&memcg->res, nr_pages * PAGE_SIZE); - if (uncharge_memsw) - res_counter_uncharge(&memcg->memsw, nr_pages * PAGE_SIZE); - if (unlikely(batch->memcg != memcg)) - memcg_oom_recover(memcg); -} - -/* - * uncharge if !page_mapped(page) - */ -static struct mem_cgroup * -__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype, - bool end_migration) -{ - struct mem_cgroup *memcg = NULL; - unsigned int nr_pages = 1; - struct page_cgroup *pc; - bool anon; - - if (mem_cgroup_disabled()) - return NULL; - - if (PageTransHuge(page)) { - nr_pages <<= compound_order(page); - VM_BUG_ON_PAGE(!PageTransHuge(page), page); - } - /* - * Check if our page_cgroup is valid - */ - pc = lookup_page_cgroup(page); - if (unlikely(!PageCgroupUsed(pc))) - return NULL; - - lock_page_cgroup(pc); - - memcg = pc->mem_cgroup; - - if (!PageCgroupUsed(pc)) - goto unlock_out; - - anon = PageAnon(page); - - switch (ctype) { - case MEM_CGROUP_CHARGE_TYPE_ANON: - /* - * Generally PageAnon tells if it's the anon statistics to be - * updated; but sometimes e.g. mem_cgroup_uncharge_page() is - * used before page reached the stage of being marked PageAnon. - */ - anon = true; - /* fallthrough */ - case MEM_CGROUP_CHARGE_TYPE_DROP: - /* See mem_cgroup_prepare_migration() */ - if (page_mapped(page)) - goto unlock_out; - /* - * Pages under migration may not be uncharged. But - * end_migration() /must/ be the one uncharging the - * unused post-migration page and so it has to call - * here with the migration bit still set. See the - * res_counter handling below. - */ - if (!end_migration && PageCgroupMigration(pc)) - goto unlock_out; - break; - case MEM_CGROUP_CHARGE_TYPE_SWAPOUT: - if (!PageAnon(page)) { /* Shared memory */ - if (page->mapping && !page_is_file_cache(page)) - goto unlock_out; - } else if (page_mapped(page)) /* Anon */ - goto unlock_out; - break; - default: - break; - } - - mem_cgroup_charge_statistics(memcg, page, anon, -nr_pages); - - ClearPageCgroupUsed(pc); - /* - * pc->mem_cgroup is not cleared here. It will be accessed when it's - * freed from LRU. This is safe because uncharged page is expected not - * to be reused (freed soon). Exception is SwapCache, it's handled by - * special functions. - */ - - unlock_page_cgroup(pc); - /* - * even after unlock, we have memcg->res.usage here and this memcg - * will never be freed, so it's safe to call css_get(). - */ - memcg_check_events(memcg, page); - if (do_swap_account && ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) { - mem_cgroup_swap_statistics(memcg, true); - css_get(&memcg->css); - } - /* - * Migration does not charge the res_counter for the - * replacement page, so leave it alone when phasing out the - * page that is unused after the migration. - */ - if (!end_migration) - mem_cgroup_do_uncharge(memcg, nr_pages, ctype); - - return memcg; - -unlock_out: - unlock_page_cgroup(pc); - return NULL; -} - -void mem_cgroup_uncharge_page(struct page *page) -{ - /* early check. */ - if (page_mapped(page)) - return; - VM_BUG_ON_PAGE(page->mapping && !PageAnon(page), page); - /* - * If the page is in swap cache, uncharge should be deferred - * to the swap path, which also properly accounts swap usage - * and handles memcg lifetime. - * - * Note that this check is not stable and reclaim may add the - * page to swap cache at any time after this. However, if the - * page is not in swap cache by the time page->mapcount hits - * 0, there won't be any page table references to the swap - * slot, and reclaim will free it and not actually write the - * page to disk. - */ - if (PageSwapCache(page)) - return; - __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_ANON, false); -} - -void mem_cgroup_uncharge_cache_page(struct page *page) -{ - VM_BUG_ON_PAGE(page_mapped(page), page); - VM_BUG_ON_PAGE(page->mapping, page); - __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE, false); -} - /* * Batch_start/batch_end is called in unmap_page_range/invlidate/trucate. * In that cases, pages are freed continuously and we can expect pages @@ -3763,6 +3591,9 @@ void mem_cgroup_uncharge_cache_page(struct page *page) void mem_cgroup_uncharge_start(void) { + unsigned long flags; + + local_irq_save(flags); current->memcg_batch.do_batch++; /* We can do nest. */ if (current->memcg_batch.do_batch == 1) { @@ -3770,21 +3601,18 @@ void mem_cgroup_uncharge_start(void) current->memcg_batch.nr_pages = 0; current->memcg_batch.memsw_nr_pages = 0; } + local_irq_restore(flags); } void mem_cgroup_uncharge_end(void) { struct memcg_batch_info *batch = ¤t->memcg_batch; + unsigned long flags; - if (!batch->do_batch) - return; - - batch->do_batch--; - if (batch->do_batch) /* If stacked, do nothing. */ - return; - - if (!batch->memcg) - return; + local_irq_save(flags); + VM_BUG_ON(!batch->do_batch); + if (--batch->do_batch) /* If stacked, do nothing */ + goto out; /* * This "batch->memcg" is valid without any css_get/put etc... * bacause we hide charges behind us. @@ -3796,61 +3624,16 @@ void mem_cgroup_uncharge_end(void) res_counter_uncharge(&batch->memcg->memsw, batch->memsw_nr_pages * PAGE_SIZE); memcg_oom_recover(batch->memcg); - /* forget this pointer (for sanity check) */ - batch->memcg = NULL; -} - -#ifdef CONFIG_SWAP -/* - * called after __delete_from_swap_cache() and drop "page" account. - * memcg information is recorded to swap_cgroup of "ent" - */ -void -mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) -{ - struct mem_cgroup *memcg; - int ctype = MEM_CGROUP_CHARGE_TYPE_SWAPOUT; - - if (!swapout) /* this was a swap cache but the swap is unused ! */ - ctype = MEM_CGROUP_CHARGE_TYPE_DROP; - - memcg = __mem_cgroup_uncharge_common(page, ctype, false); - - /* - * record memcg information, if swapout && memcg != NULL, - * css_get() was called in uncharge(). - */ - if (do_swap_account && swapout && memcg) - swap_cgroup_record(ent, mem_cgroup_id(memcg)); +out: + local_irq_restore(flags); } -#endif #ifdef CONFIG_MEMCG_SWAP -/* - * called from swap_entry_free(). remove record in swap_cgroup and - * uncharge "memsw" account. - */ -void mem_cgroup_uncharge_swap(swp_entry_t ent) +static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg, + bool charge) { - struct mem_cgroup *memcg; - unsigned short id; - - if (!do_swap_account) - return; - - id = swap_cgroup_record(ent, 0); - rcu_read_lock(); - memcg = mem_cgroup_lookup(id); - if (memcg) { - /* - * We uncharge this because swap is freed. This memcg can - * be obsolete one. We avoid calling css_tryget_online(). - */ - res_counter_uncharge(&memcg->memsw, PAGE_SIZE); - mem_cgroup_swap_statistics(memcg, false); - css_put(&memcg->css); - } - rcu_read_unlock(); + int val = (charge) ? 1 : -1; + this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAP], val); } /** @@ -3902,169 +3685,6 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry, } #endif -/* - * Before starting migration, account PAGE_SIZE to mem_cgroup that the old - * page belongs to. - */ -void mem_cgroup_prepare_migration(struct page *page, struct page *newpage, - struct mem_cgroup **memcgp) -{ - struct mem_cgroup *memcg = NULL; - unsigned int nr_pages = 1; - struct page_cgroup *pc; - - *memcgp = NULL; - - if (mem_cgroup_disabled()) - return; - - if (PageTransHuge(page)) - nr_pages <<= compound_order(page); - - pc = lookup_page_cgroup(page); - lock_page_cgroup(pc); - if (PageCgroupUsed(pc)) { - memcg = pc->mem_cgroup; - css_get(&memcg->css); - /* - * At migrating an anonymous page, its mapcount goes down - * to 0 and uncharge() will be called. But, even if it's fully - * unmapped, migration may fail and this page has to be - * charged again. We set MIGRATION flag here and delay uncharge - * until end_migration() is called - * - * Corner Case Thinking - * A) - * When the old page was mapped as Anon and it's unmap-and-freed - * while migration was ongoing. - * If unmap finds the old page, uncharge() of it will be delayed - * until end_migration(). If unmap finds a new page, it's - * uncharged when it make mapcount to be 1->0. If unmap code - * finds swap_migration_entry, the new page will not be mapped - * and end_migration() will find it(mapcount==0). - * - * B) - * When the old page was mapped but migraion fails, the kernel - * remaps it. A charge for it is kept by MIGRATION flag even - * if mapcount goes down to 0. We can do remap successfully - * without charging it again. - * - * C) - * The "old" page is under lock_page() until the end of - * migration, so, the old page itself will not be swapped-out. - * If the new page is swapped out before end_migraton, our - * hook to usual swap-out path will catch the event. - */ - if (PageAnon(page)) - SetPageCgroupMigration(pc); - } - unlock_page_cgroup(pc); - /* - * If the page is not charged at this point, - * we return here. - */ - if (!memcg) - return; - - *memcgp = memcg; - /* - * We charge new page before it's used/mapped. So, even if unlock_page() - * is called before end_migration, we can catch all events on this new - * page. In the case new page is migrated but not remapped, new page's - * mapcount will be finally 0 and we call uncharge in end_migration(). - */ - /* - * The page is committed to the memcg, but it's not actually - * charged to the res_counter since we plan on replacing the - * old one and only one page is going to be left afterwards. - */ - commit_charge(newpage, memcg, nr_pages, PageAnon(page), false); -} - -/* remove redundant charge if migration failed*/ -void mem_cgroup_end_migration(struct mem_cgroup *memcg, - struct page *oldpage, struct page *newpage, bool migration_ok) -{ - struct page *used, *unused; - struct page_cgroup *pc; - bool anon; - - if (!memcg) - return; - - if (!migration_ok) { - used = oldpage; - unused = newpage; - } else { - used = newpage; - unused = oldpage; - } - anon = PageAnon(used); - __mem_cgroup_uncharge_common(unused, - anon ? MEM_CGROUP_CHARGE_TYPE_ANON - : MEM_CGROUP_CHARGE_TYPE_CACHE, - true); - css_put(&memcg->css); - /* - * We disallowed uncharge of pages under migration because mapcount - * of the page goes down to zero, temporarly. - * Clear the flag and check the page should be charged. - */ - pc = lookup_page_cgroup(oldpage); - lock_page_cgroup(pc); - ClearPageCgroupMigration(pc); - unlock_page_cgroup(pc); - - /* - * If a page is a file cache, radix-tree replacement is very atomic - * and we can skip this check. When it was an Anon page, its mapcount - * goes down to 0. But because we added MIGRATION flage, it's not - * uncharged yet. There are several case but page->mapcount check - * and USED bit check in mem_cgroup_uncharge_page() will do enough - * check. (see prepare_charge() also) - */ - if (anon) - mem_cgroup_uncharge_page(used); -} - -/* - * At replace page cache, newpage is not under any memcg but it's on - * LRU. So, this function doesn't touch res_counter but handles LRU - * in correct way. Both pages are locked so we cannot race with uncharge. - */ -void mem_cgroup_replace_page_cache(struct page *oldpage, - struct page *newpage) -{ - struct mem_cgroup *memcg = NULL; - struct page_cgroup *pc; - - if (mem_cgroup_disabled()) - return; - - pc = lookup_page_cgroup(oldpage); - /* fix accounting on old pages */ - lock_page_cgroup(pc); - if (PageCgroupUsed(pc)) { - memcg = pc->mem_cgroup; - mem_cgroup_charge_statistics(memcg, oldpage, false, -1); - ClearPageCgroupUsed(pc); - } - unlock_page_cgroup(pc); - - /* - * When called from shmem_replace_page(), in some cases the - * oldpage has already been charged, and in some cases not. - */ - if (!memcg) - return; - /* - * Even if newpage->mapping was NULL before starting replacement, - * the newpage may be on LRU(or pagevec for LRU) already. We lock - * LRU while we overwrite pc->mem_cgroup. - */ - commit_charge(newpage, memcg, 1, false, true); -} - #ifdef CONFIG_DEBUG_VM static struct page_cgroup *lookup_page_cgroup_used(struct page *page) { @@ -4263,7 +3883,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, gfp_mask, &nr_scanned); nr_reclaimed += reclaimed; *total_scanned += nr_scanned; - spin_lock(&mctz->lock); + spin_lock_irq(&mctz->lock); /* * If we failed to reclaim anything from this memory cgroup @@ -4303,7 +3923,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, */ /* If excess == 0, no tree ops */ __mem_cgroup_insert_exceeded(mz, mctz, excess); - spin_unlock(&mctz->lock); + spin_unlock_irq(&mctz->lock); css_put(&mz->memcg->css); loop++; /* @@ -6265,9 +5885,9 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, if (page) { pc = lookup_page_cgroup(page); /* - * Do only loose check w/o page_cgroup lock. - * mem_cgroup_move_account() checks the pc is valid or not under - * the lock. + * Do only loose check w/o serialization. + * mem_cgroup_move_account() checks the pc is valid or + * not under LRU exclusion. */ if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) { ret = MC_TARGET_PAGE; @@ -6729,6 +6349,67 @@ static void __init enable_swap_cgroup(void) } #endif +#ifdef CONFIG_MEMCG_SWAP +/** + * mem_cgroup_swapout - transfer a memsw charge to swap + * @page: page whose memsw charge to transfer + * @entry: swap entry to move the charge to + * + * Transfer the memsw charge of @page to @entry. + */ +void mem_cgroup_swapout(struct page *page, swp_entry_t entry) +{ + struct page_cgroup *pc; + unsigned short oldid; + + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(page_count(page), page); + + if (!do_swap_account) + return; + + pc = lookup_page_cgroup(page); + + /* Readahead page, never charged */ + if (!PageCgroupUsed(pc)) + return; + + VM_BUG_ON_PAGE(!(pc->flags & PCG_MEMSW), page); + + oldid = swap_cgroup_record(entry, mem_cgroup_id(pc->mem_cgroup)); + VM_BUG_ON_PAGE(oldid, page); + + pc->flags &= ~PCG_MEMSW; + css_get(&pc->mem_cgroup->css); + mem_cgroup_swap_statistics(pc->mem_cgroup, true); +} + +/** + * mem_cgroup_uncharge_swap - uncharge a swap entry + * @entry: swap entry to uncharge + * + * Drop the memsw charge associated with @entry. + */ +void mem_cgroup_uncharge_swap(swp_entry_t entry) +{ + struct mem_cgroup *memcg; + unsigned short id; + + if (!do_swap_account) + return; + + id = swap_cgroup_record(entry, 0); + rcu_read_lock(); + memcg = mem_cgroup_lookup(id); + if (memcg) { + res_counter_uncharge(&memcg->memsw, PAGE_SIZE); + mem_cgroup_swap_statistics(memcg, false); + css_put(&memcg->css); + } + rcu_read_unlock(); +} +#endif + /** * mem_cgroup_try_charge - try charging a page * @page: page to charge @@ -6831,7 +6512,7 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, VM_BUG_ON_PAGE(!PageTransHuge(page), page); } - commit_charge(page, memcg, nr_pages, PageAnon(page), lrucare); + commit_charge(page, memcg, nr_pages, lrucare); if (do_swap_account && PageSwapCache(page)) { swp_entry_t entry = { .val = page_private(page) }; @@ -6873,6 +6554,139 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) cancel_charge(memcg, nr_pages); } +/** + * mem_cgroup_uncharge - uncharge a page + * @page: page to uncharge + * + * Uncharge a page previously charged with mem_cgroup_try_charge() and + * mem_cgroup_commit_charge(). + */ +void mem_cgroup_uncharge(struct page *page) +{ + struct memcg_batch_info *batch; + unsigned int nr_pages = 1; + struct mem_cgroup *memcg; + struct page_cgroup *pc; + unsigned long pc_flags; + unsigned long flags; + + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(page_count(page), page); + + if (mem_cgroup_disabled()) + return; + + pc = lookup_page_cgroup(page); + + /* Every final put_page() ends up here */ + if (!PageCgroupUsed(pc)) + return; + + if (PageTransHuge(page)) { + nr_pages <<= compound_order(page); + VM_BUG_ON_PAGE(!PageTransHuge(page), page); + } + /* + * Nobody should be changing or seriously looking at + * pc->mem_cgroup and pc->flags at this point, we have fully + * exclusive access to the page. + */ + memcg = pc->mem_cgroup; + pc_flags = pc->flags; + pc->flags = 0; + + local_irq_save(flags); + + if (nr_pages > 1) + goto direct; + if (unlikely(test_thread_flag(TIF_MEMDIE))) + goto direct; + batch = ¤t->memcg_batch; + if (!batch->do_batch) + goto direct; + if (batch->memcg && batch->memcg != memcg) + goto direct; + if (!batch->memcg) + batch->memcg = memcg; + if (pc_flags & PCG_MEM) + batch->nr_pages++; + if (pc_flags & PCG_MEMSW) + batch->memsw_nr_pages++; + goto out; +direct: + if (pc_flags & PCG_MEM) + res_counter_uncharge(&memcg->res, nr_pages * PAGE_SIZE); + if (pc_flags & PCG_MEMSW) + res_counter_uncharge(&memcg->memsw, nr_pages * PAGE_SIZE); + memcg_oom_recover(memcg); +out: + mem_cgroup_charge_statistics(memcg, page, -nr_pages); + memcg_check_events(memcg, page); + + local_irq_restore(flags); +} + +/** + * mem_cgroup_migrate - migrate a charge to another page + * @oldpage: currently charged page + * @newpage: page to transfer the charge to + * @lrucare: both pages might be on the LRU already + * + * Migrate the charge from @oldpage to @newpage. + * + * Both pages must be locked, @newpage->mapping must be set up. + */ +void mem_cgroup_migrate(struct page *oldpage, struct page *newpage, + bool lrucare) +{ + unsigned int nr_pages = 1; + struct page_cgroup *pc; + int isolated; + + VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); + VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); + VM_BUG_ON_PAGE(!lrucare && PageLRU(oldpage), oldpage); + VM_BUG_ON_PAGE(!lrucare && PageLRU(newpage), newpage); + VM_BUG_ON_PAGE(PageAnon(oldpage) != PageAnon(newpage), newpage); + + if (mem_cgroup_disabled()) + return; + + /* Page cache replacement: new page already charged? */ + pc = lookup_page_cgroup(newpage); + if (PageCgroupUsed(pc)) + return; + + /* Re-entrant migration: old page already uncharged? */ + pc = lookup_page_cgroup(oldpage); + if (!PageCgroupUsed(pc)) + return; + + VM_BUG_ON_PAGE(!(pc->flags & PCG_MEM), oldpage); + VM_BUG_ON_PAGE(do_swap_account && !(pc->flags & PCG_MEMSW), oldpage); + + if (PageTransHuge(oldpage)) { + nr_pages <<= compound_order(oldpage); + VM_BUG_ON_PAGE(!PageTransHuge(oldpage), oldpage); + VM_BUG_ON_PAGE(!PageTransHuge(newpage), newpage); + } + + if (lrucare) + lock_page_lru(oldpage, &isolated); + + pc->flags = 0; + + if (lrucare) + unlock_page_lru(oldpage, isolated); + + local_irq_disable(); + mem_cgroup_charge_statistics(pc->mem_cgroup, oldpage, -nr_pages); + memcg_check_events(pc->mem_cgroup, oldpage); + local_irq_enable(); + + commit_charge(newpage, pc->mem_cgroup, nr_pages, lrucare); +} + /* * subsys_initcall() for memory controller. * diff --git a/mm/memory.c b/mm/memory.c index 6d7648773dc4..2a899e4e82ba 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1292,7 +1292,6 @@ static void unmap_page_range(struct mmu_gather *tlb, details = NULL; BUG_ON(addr >= end); - mem_cgroup_uncharge_start(); tlb_start_vma(tlb, vma); pgd = pgd_offset(vma->vm_mm, addr); do { @@ -1302,7 +1301,6 @@ static void unmap_page_range(struct mmu_gather *tlb, next = zap_pud_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); - mem_cgroup_uncharge_end(); } diff --git a/mm/migrate.c b/mm/migrate.c index be6dbf995c0c..f78ec9bd454d 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -780,6 +780,7 @@ static int move_to_new_page(struct page *newpage, struct page *page, if (rc != MIGRATEPAGE_SUCCESS) { newpage->mapping = NULL; } else { + mem_cgroup_migrate(page, newpage, false); if (remap_swapcache) remove_migration_ptes(page, newpage); page->mapping = NULL; @@ -795,7 +796,6 @@ static int __unmap_and_move(struct page *page, struct page *newpage, { int rc = -EAGAIN; int remap_swapcache = 1; - struct mem_cgroup *mem; struct anon_vma *anon_vma = NULL; if (!trylock_page(page)) { @@ -821,9 +821,6 @@ static int __unmap_and_move(struct page *page, struct page *newpage, lock_page(page); } - /* charge against new page */ - mem_cgroup_prepare_migration(page, newpage, &mem); - if (PageWriteback(page)) { /* * Only in the case of a full synchronous migration is it @@ -833,10 +830,10 @@ static int __unmap_and_move(struct page *page, struct page *newpage, */ if (mode != MIGRATE_SYNC) { rc = -EBUSY; - goto uncharge; + goto out_unlock; } if (!force) - goto uncharge; + goto out_unlock; wait_on_page_writeback(page); } /* @@ -872,7 +869,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, */ remap_swapcache = 0; } else { - goto uncharge; + goto out_unlock; } } @@ -885,7 +882,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, * the page migration right away (proteced by page lock). */ rc = balloon_page_migrate(newpage, page, mode); - goto uncharge; + goto out_unlock; } /* @@ -904,7 +901,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, VM_BUG_ON_PAGE(PageAnon(page), page); if (page_has_private(page)) { try_to_free_buffers(page); - goto uncharge; + goto out_unlock; } goto skip_unmap; } @@ -923,10 +920,7 @@ skip_unmap: if (anon_vma) put_anon_vma(anon_vma); -uncharge: - mem_cgroup_end_migration(mem, page, newpage, - (rc == MIGRATEPAGE_SUCCESS || - rc == MIGRATEPAGE_BALLOON_SUCCESS)); +out_unlock: unlock_page(page); out: return rc; @@ -1786,7 +1780,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, pg_data_t *pgdat = NODE_DATA(node); int isolated = 0; struct page *new_page = NULL; - struct mem_cgroup *memcg = NULL; int page_lru = page_is_file_cache(page); unsigned long mmun_start = address & HPAGE_PMD_MASK; unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE; @@ -1852,15 +1845,6 @@ fail_putback: goto out_unlock; } - /* - * Traditional migration needs to prepare the memcg charge - * transaction early to prevent the old page from being - * uncharged when installing migration entries. Here we can - * save the potential rollback and start the charge transfer - * only when migration is already known to end successfully. - */ - mem_cgroup_prepare_migration(page, new_page, &memcg); - orig_entry = *pmd; entry = mk_pmd(new_page, vma->vm_page_prot); entry = pmd_mkhuge(entry); @@ -1888,14 +1872,10 @@ fail_putback: goto fail_putback; } + mem_cgroup_migrate(page, new_page, false); + page_remove_rmap(page); - /* - * Finish the charge transaction under the page table lock to - * prevent split_huge_page() from dividing up the charge - * before it's fully transferred to the new page. - */ - mem_cgroup_end_migration(memcg, page, new_page, true); spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); diff --git a/mm/rmap.c b/mm/rmap.c index f56b5ed78128..3e8491c504f8 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1089,7 +1089,6 @@ void page_remove_rmap(struct page *page) if (unlikely(PageHuge(page))) goto out; if (anon) { - mem_cgroup_uncharge_page(page); if (PageTransHuge(page)) __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); diff --git a/mm/shmem.c b/mm/shmem.c index 1f1a8085538b..6dc80d298f9d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -419,7 +419,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, pvec.pages, indices); if (!pvec.nr) break; - mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; @@ -447,7 +446,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); - mem_cgroup_uncharge_end(); cond_resched(); index++; } @@ -495,7 +493,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, index = start; continue; } - mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; @@ -531,7 +528,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); - mem_cgroup_uncharge_end(); index++; } @@ -835,7 +831,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) } mutex_unlock(&shmem_swaplist_mutex); - swapcache_free(swap, NULL); + swapcache_free(swap); redirty: set_page_dirty(page); if (wbc->for_reclaim) @@ -1008,7 +1004,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, */ oldpage = newpage; } else { - mem_cgroup_replace_page_cache(oldpage, newpage); + mem_cgroup_migrate(oldpage, newpage, false); lru_cache_add_anon(newpage); *pagep = newpage; } diff --git a/mm/swap.c b/mm/swap.c index 3baca701bb78..00523fffa5ed 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -62,6 +62,7 @@ static void __page_cache_release(struct page *page) del_page_from_lru_list(page, lruvec, page_off_lru(page)); spin_unlock_irqrestore(&zone->lru_lock, flags); } + mem_cgroup_uncharge(page); } static void __put_single_page(struct page *page) @@ -907,6 +908,8 @@ void release_pages(struct page **pages, int nr, bool cold) struct lruvec *lruvec; unsigned long uninitialized_var(flags); + mem_cgroup_uncharge_start(); + for (i = 0; i < nr; i++) { struct page *page = pages[i]; @@ -938,6 +941,7 @@ void release_pages(struct page **pages, int nr, bool cold) __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); } + mem_cgroup_uncharge(page); /* Clear Active bit in case of parallel mark_page_accessed */ __ClearPageActive(page); @@ -947,6 +951,8 @@ void release_pages(struct page **pages, int nr, bool cold) if (zone) spin_unlock_irqrestore(&zone->lru_lock, flags); + mem_cgroup_uncharge_end(); + free_hot_cold_page_list(&pages_to_free, cold); } EXPORT_SYMBOL(release_pages); diff --git a/mm/swap_state.c b/mm/swap_state.c index 2972eee184a4..e160151da6b8 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -176,7 +176,7 @@ int add_to_swap(struct page *page, struct list_head *list) if (unlikely(PageTransHuge(page))) if (unlikely(split_huge_page_to_list(page, list))) { - swapcache_free(entry, NULL); + swapcache_free(entry); return 0; } @@ -202,7 +202,7 @@ int add_to_swap(struct page *page, struct list_head *list) * add_to_swap_cache() doesn't return -EEXIST, so we can safely * clear SWAP_HAS_CACHE flag. */ - swapcache_free(entry, NULL); + swapcache_free(entry); return 0; } } @@ -225,7 +225,7 @@ void delete_from_swap_cache(struct page *page) __delete_from_swap_cache(page); spin_unlock_irq(&address_space->tree_lock); - swapcache_free(entry, page); + swapcache_free(entry); page_cache_release(page); } @@ -386,7 +386,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, * add_to_swap_cache() doesn't return -EEXIST, so we can safely * clear SWAP_HAS_CACHE flag. */ - swapcache_free(entry, NULL); + swapcache_free(entry); } while (err != -ENOMEM); if (new_page) diff --git a/mm/swapfile.c b/mm/swapfile.c index 0883b4912ff7..8798b2e0ac59 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -843,16 +843,13 @@ void swap_free(swp_entry_t entry) /* * Called after dropping swapcache to decrease refcnt to swap entries. */ -void swapcache_free(swp_entry_t entry, struct page *page) +void swapcache_free(swp_entry_t entry) { struct swap_info_struct *p; - unsigned char count; p = swap_info_get(entry); if (p) { - count = swap_entry_free(p, entry, SWAP_HAS_CACHE); - if (page) - mem_cgroup_uncharge_swapcache(page, entry, count != 0); + swap_entry_free(p, entry, SWAP_HAS_CACHE); spin_unlock(&p->lock); } } diff --git a/mm/truncate.c b/mm/truncate.c index eda247307164..96d167372d89 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -281,7 +281,6 @@ void truncate_inode_pages_range(struct address_space *mapping, while (index < end && pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) { - mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; @@ -307,7 +306,6 @@ void truncate_inode_pages_range(struct address_space *mapping, } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); - mem_cgroup_uncharge_end(); cond_resched(); index++; } @@ -369,7 +367,6 @@ void truncate_inode_pages_range(struct address_space *mapping, pagevec_release(&pvec); break; } - mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; @@ -394,7 +391,6 @@ void truncate_inode_pages_range(struct address_space *mapping, } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); - mem_cgroup_uncharge_end(); index++; } cleancache_invalidate_inode(mapping); @@ -493,7 +489,6 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, indices)) { - mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; @@ -522,7 +517,6 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); - mem_cgroup_uncharge_end(); cond_resched(); index++; } @@ -553,7 +547,6 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) BUG_ON(page_has_private(page)); __delete_from_page_cache(page, NULL); spin_unlock_irq(&mapping->tree_lock); - mem_cgroup_uncharge_cache_page(page); if (mapping->a_ops->freepage) mapping->a_ops->freepage(page); @@ -602,7 +595,6 @@ int invalidate_inode_pages2_range(struct address_space *mapping, while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, indices)) { - mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; @@ -655,7 +647,6 @@ int invalidate_inode_pages2_range(struct address_space *mapping, } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); - mem_cgroup_uncharge_end(); cond_resched(); index++; } diff --git a/mm/vmscan.c b/mm/vmscan.c index d2f65c856350..7068e838d22b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -577,9 +577,10 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, if (PageSwapCache(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); - swapcache_free(swap, page); + swapcache_free(swap); } else { void (*freepage)(struct page *); void *shadow = NULL; @@ -600,7 +601,6 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, shadow = workingset_eviction(mapping, page); __delete_from_page_cache(page, shadow); spin_unlock_irq(&mapping->tree_lock); - mem_cgroup_uncharge_cache_page(page); if (freepage != NULL) freepage(page); @@ -1103,6 +1103,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, */ __clear_page_locked(page); free_it: + mem_cgroup_uncharge(page); nr_reclaimed++; /* @@ -1132,12 +1133,13 @@ keep: list_add(&page->lru, &ret_pages); VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); } + mem_cgroup_uncharge_end(); 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; @@ -1435,6 +1437,8 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) __ClearPageActive(page); del_page_from_lru_list(page, lruvec, lru); + mem_cgroup_uncharge(page); + if (unlikely(PageCompound(page))) { spin_unlock_irq(&zone->lru_lock); (*get_compound_page_dtor(page))(page); @@ -1656,6 +1660,8 @@ static void move_active_pages_to_lru(struct lruvec *lruvec, __ClearPageActive(page); del_page_from_lru_list(page, lruvec, lru); + mem_cgroup_uncharge(page); + if (unlikely(PageCompound(page))) { spin_unlock_irq(&zone->lru_lock); (*get_compound_page_dtor(page))(page); diff --git a/mm/zswap.c b/mm/zswap.c index 032c21eeab2b..9da56af24df5 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -507,7 +507,7 @@ static int zswap_get_swap_cache_page(swp_entry_t entry, * add_to_swap_cache() doesn't return -EEXIST, so we can safely * clear SWAP_HAS_CACHE flag. */ - swapcache_free(entry, NULL); + swapcache_free(entry); } while (err != -ENOMEM); if (new_page) -- cgit v1.2.3 From 747db954cab64c6b7a95b121b517165f34751898 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 8 Aug 2014 14:19:24 -0700 Subject: mm: memcontrol: use page lists for uncharge batching Pages are now uncharged at release time, and all sources of batched uncharges operate on lists of pages. Directly use those lists, and get rid of the per-task batching state. This also batches statistics accounting, in addition to the res counter charges, to reduce IRQ-disabling and re-enabling. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: Hugh Dickins Cc: Tejun Heo Cc: Vladimir Davydov Cc: Naoya Horiguchi Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 12 +-- include/linux/sched.h | 6 -- kernel/fork.c | 4 - mm/memcontrol.c | 206 ++++++++++++++++++++++++--------------------- mm/swap.c | 6 +- mm/vmscan.c | 12 ++- 6 files changed, 117 insertions(+), 129 deletions(-) (limited to 'mm/vmscan.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 806b8fa15c5f..e0752d204d9e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -59,12 +59,8 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, bool lrucare); void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); - void mem_cgroup_uncharge(struct page *page); - -/* Batched uncharging */ -void mem_cgroup_uncharge_start(void); -void mem_cgroup_uncharge_end(void); +void mem_cgroup_uncharge_list(struct list_head *page_list); void mem_cgroup_migrate(struct page *oldpage, struct page *newpage, bool lrucare); @@ -233,11 +229,7 @@ static inline void mem_cgroup_uncharge(struct page *page) { } -static inline void mem_cgroup_uncharge_start(void) -{ -} - -static inline void mem_cgroup_uncharge_end(void) +static inline void mem_cgroup_uncharge_list(struct list_head *page_list) { } diff --git a/include/linux/sched.h b/include/linux/sched.h index 7c19d552dc3f..4fcf82a4d243 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1628,12 +1628,6 @@ struct task_struct { unsigned long trace_recursion; #endif /* CONFIG_TRACING */ #ifdef CONFIG_MEMCG /* memcg uses this to do batch job */ - struct memcg_batch_info { - int do_batch; /* incremented when batch uncharge started */ - struct mem_cgroup *memcg; /* target memcg of uncharge */ - unsigned long nr_pages; /* uncharged usage */ - unsigned long memsw_nr_pages; /* uncharged mem+swap usage */ - } memcg_batch; unsigned int memcg_kmem_skip_account; struct memcg_oom_info { struct mem_cgroup *memcg; diff --git a/kernel/fork.c b/kernel/fork.c index fbd3497b221f..f6f5086c9e7d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1346,10 +1346,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif -#ifdef CONFIG_MEMCG - p->memcg_batch.do_batch = 0; - p->memcg_batch.memcg = NULL; -#endif #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9106f1b12f56..a6e2be0241af 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3581,53 +3581,6 @@ out: return ret; } -/* - * Batch_start/batch_end is called in unmap_page_range/invlidate/trucate. - * In that cases, pages are freed continuously and we can expect pages - * are in the same memcg. All these calls itself limits the number of - * pages freed at once, then uncharge_start/end() is called properly. - * This may be called prural(2) times in a context, - */ - -void mem_cgroup_uncharge_start(void) -{ - unsigned long flags; - - local_irq_save(flags); - current->memcg_batch.do_batch++; - /* We can do nest. */ - if (current->memcg_batch.do_batch == 1) { - current->memcg_batch.memcg = NULL; - current->memcg_batch.nr_pages = 0; - current->memcg_batch.memsw_nr_pages = 0; - } - local_irq_restore(flags); -} - -void mem_cgroup_uncharge_end(void) -{ - struct memcg_batch_info *batch = ¤t->memcg_batch; - unsigned long flags; - - local_irq_save(flags); - VM_BUG_ON(!batch->do_batch); - if (--batch->do_batch) /* If stacked, do nothing */ - goto out; - /* - * This "batch->memcg" is valid without any css_get/put etc... - * bacause we hide charges behind us. - */ - if (batch->nr_pages) - res_counter_uncharge(&batch->memcg->res, - batch->nr_pages * PAGE_SIZE); - if (batch->memsw_nr_pages) - res_counter_uncharge(&batch->memcg->memsw, - batch->memsw_nr_pages * PAGE_SIZE); - memcg_oom_recover(batch->memcg); -out: - local_irq_restore(flags); -} - #ifdef CONFIG_MEMCG_SWAP static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg, bool charge) @@ -6554,6 +6507,98 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) cancel_charge(memcg, nr_pages); } +static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout, + unsigned long nr_mem, unsigned long nr_memsw, + unsigned long nr_anon, unsigned long nr_file, + unsigned long nr_huge, struct page *dummy_page) +{ + unsigned long flags; + + if (nr_mem) + res_counter_uncharge(&memcg->res, nr_mem * PAGE_SIZE); + if (nr_memsw) + res_counter_uncharge(&memcg->memsw, nr_memsw * PAGE_SIZE); + + memcg_oom_recover(memcg); + + local_irq_save(flags); + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS], nr_anon); + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_file); + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], nr_huge); + __this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT], pgpgout); + __this_cpu_add(memcg->stat->nr_page_events, nr_anon + nr_file); + memcg_check_events(memcg, dummy_page); + local_irq_restore(flags); +} + +static void uncharge_list(struct list_head *page_list) +{ + struct mem_cgroup *memcg = NULL; + unsigned long nr_memsw = 0; + unsigned long nr_anon = 0; + unsigned long nr_file = 0; + unsigned long nr_huge = 0; + unsigned long pgpgout = 0; + unsigned long nr_mem = 0; + struct list_head *next; + struct page *page; + + next = page_list->next; + do { + unsigned int nr_pages = 1; + struct page_cgroup *pc; + + page = list_entry(next, struct page, lru); + next = page->lru.next; + + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(page_count(page), page); + + pc = lookup_page_cgroup(page); + if (!PageCgroupUsed(pc)) + continue; + + /* + * Nobody should be changing or seriously looking at + * pc->mem_cgroup and pc->flags at this point, we have + * fully exclusive access to the page. + */ + + if (memcg != pc->mem_cgroup) { + if (memcg) { + uncharge_batch(memcg, pgpgout, nr_mem, nr_memsw, + nr_anon, nr_file, nr_huge, page); + pgpgout = nr_mem = nr_memsw = 0; + nr_anon = nr_file = nr_huge = 0; + } + memcg = pc->mem_cgroup; + } + + if (PageTransHuge(page)) { + nr_pages <<= compound_order(page); + VM_BUG_ON_PAGE(!PageTransHuge(page), page); + nr_huge += nr_pages; + } + + if (PageAnon(page)) + nr_anon += nr_pages; + else + nr_file += nr_pages; + + if (pc->flags & PCG_MEM) + nr_mem += nr_pages; + if (pc->flags & PCG_MEMSW) + nr_memsw += nr_pages; + pc->flags = 0; + + pgpgout++; + } while (next != page_list); + + if (memcg) + uncharge_batch(memcg, pgpgout, nr_mem, nr_memsw, + nr_anon, nr_file, nr_huge, page); +} + /** * mem_cgroup_uncharge - uncharge a page * @page: page to uncharge @@ -6563,67 +6608,34 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) */ void mem_cgroup_uncharge(struct page *page) { - struct memcg_batch_info *batch; - unsigned int nr_pages = 1; - struct mem_cgroup *memcg; struct page_cgroup *pc; - unsigned long pc_flags; - unsigned long flags; - - VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON_PAGE(page_count(page), page); if (mem_cgroup_disabled()) return; + /* Don't touch page->lru of any random page, pre-check: */ pc = lookup_page_cgroup(page); - - /* Every final put_page() ends up here */ if (!PageCgroupUsed(pc)) return; - if (PageTransHuge(page)) { - nr_pages <<= compound_order(page); - VM_BUG_ON_PAGE(!PageTransHuge(page), page); - } - /* - * Nobody should be changing or seriously looking at - * pc->mem_cgroup and pc->flags at this point, we have fully - * exclusive access to the page. - */ - memcg = pc->mem_cgroup; - pc_flags = pc->flags; - pc->flags = 0; - - local_irq_save(flags); + INIT_LIST_HEAD(&page->lru); + uncharge_list(&page->lru); +} - if (nr_pages > 1) - goto direct; - if (unlikely(test_thread_flag(TIF_MEMDIE))) - goto direct; - batch = ¤t->memcg_batch; - if (!batch->do_batch) - goto direct; - if (batch->memcg && batch->memcg != memcg) - goto direct; - if (!batch->memcg) - batch->memcg = memcg; - if (pc_flags & PCG_MEM) - batch->nr_pages++; - if (pc_flags & PCG_MEMSW) - batch->memsw_nr_pages++; - goto out; -direct: - if (pc_flags & PCG_MEM) - res_counter_uncharge(&memcg->res, nr_pages * PAGE_SIZE); - if (pc_flags & PCG_MEMSW) - res_counter_uncharge(&memcg->memsw, nr_pages * PAGE_SIZE); - memcg_oom_recover(memcg); -out: - mem_cgroup_charge_statistics(memcg, page, -nr_pages); - memcg_check_events(memcg, page); +/** + * mem_cgroup_uncharge_list - uncharge a list of page + * @page_list: list of pages to uncharge + * + * Uncharge a list of pages previously charged with + * mem_cgroup_try_charge() and mem_cgroup_commit_charge(). + */ +void mem_cgroup_uncharge_list(struct list_head *page_list) +{ + if (mem_cgroup_disabled()) + return; - local_irq_restore(flags); + if (!list_empty(page_list)) + uncharge_list(page_list); } /** diff --git a/mm/swap.c b/mm/swap.c index 00523fffa5ed..6b2dc3897cd5 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -908,8 +908,6 @@ void release_pages(struct page **pages, int nr, bool cold) struct lruvec *lruvec; unsigned long uninitialized_var(flags); - mem_cgroup_uncharge_start(); - for (i = 0; i < nr; i++) { struct page *page = pages[i]; @@ -941,7 +939,6 @@ void release_pages(struct page **pages, int nr, bool cold) __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); } - mem_cgroup_uncharge(page); /* Clear Active bit in case of parallel mark_page_accessed */ __ClearPageActive(page); @@ -951,8 +948,7 @@ void release_pages(struct page **pages, int nr, bool cold) if (zone) spin_unlock_irqrestore(&zone->lru_lock, flags); - mem_cgroup_uncharge_end(); - + mem_cgroup_uncharge_list(&pages_to_free); free_hot_cold_page_list(&pages_to_free, cold); } EXPORT_SYMBOL(release_pages); diff --git a/mm/vmscan.c b/mm/vmscan.c index 7068e838d22b..2836b5373b2e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -822,7 +822,6 @@ static unsigned long shrink_page_list(struct list_head *page_list, cond_resched(); - mem_cgroup_uncharge_start(); while (!list_empty(page_list)) { struct address_space *mapping; struct page *page; @@ -1103,7 +1102,6 @@ static unsigned long shrink_page_list(struct list_head *page_list, */ __clear_page_locked(page); free_it: - mem_cgroup_uncharge(page); nr_reclaimed++; /* @@ -1133,8 +1131,8 @@ keep: list_add(&page->lru, &ret_pages); VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); } - mem_cgroup_uncharge_end(); + mem_cgroup_uncharge_list(&free_pages); free_hot_cold_page_list(&free_pages, true); list_splice(&ret_pages, page_list); @@ -1437,10 +1435,9 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) __ClearPageActive(page); del_page_from_lru_list(page, lruvec, lru); - mem_cgroup_uncharge(page); - if (unlikely(PageCompound(page))) { spin_unlock_irq(&zone->lru_lock); + mem_cgroup_uncharge(page); (*get_compound_page_dtor(page))(page); spin_lock_irq(&zone->lru_lock); } else @@ -1548,6 +1545,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, spin_unlock_irq(&zone->lru_lock); + mem_cgroup_uncharge_list(&page_list); free_hot_cold_page_list(&page_list, true); /* @@ -1660,10 +1658,9 @@ static void move_active_pages_to_lru(struct lruvec *lruvec, __ClearPageActive(page); del_page_from_lru_list(page, lruvec, lru); - mem_cgroup_uncharge(page); - if (unlikely(PageCompound(page))) { spin_unlock_irq(&zone->lru_lock); + mem_cgroup_uncharge(page); (*get_compound_page_dtor(page))(page); spin_lock_irq(&zone->lru_lock); } else @@ -1771,6 +1768,7 @@ 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); + mem_cgroup_uncharge_list(&l_hold); free_hot_cold_page_list(&l_hold, true); } -- cgit v1.2.3