From d3bb89ea9c13e5a98d2b7a0ba8e50a77893132cb Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 7 Dec 2023 23:25:25 +0800 Subject: mm: fix VMA heap bounds checking After converting selinux to VMA heap check helper, the gcl triggers an execheap SELinux denial, which is caused by a changed logic check. Previously selinux only checked that the VMA range was within the VMA heap range, and the implementation checks the intersection between the two ranges, but the corner case (vm_end=start_brk, brk=vm_start) isn't handled correctly. Since commit 11250fd12eb8 ("mm: factor out VMA stack and heap checks") was only a function extraction, it seems that the issue was introduced by commit 0db0c01b53a1 ("procfs: fix /proc//maps heap check"). Let's fix above corner cases, meanwhile, correct the wrong indentation of the stack and heap check helpers. Fixes: 11250fd12eb8 ("mm: factor out VMA stack and heap checks") Signed-off-by: Kefeng Wang Reported-by: Ondrej Mosnacek Closes: https://lore.kernel.org/selinux/CAFqZXNv0SVT0fkOK6neP9AXbj3nxJ61JAY4+zJzvxqJaeuhbFw@mail.gmail.com/ Tested-by: Ondrej Mosnacek Link: https://lkml.kernel.org/r/20231207152525.2607420-1-wangkefeng.wang@huawei.com Cc: David Hildenbrand Cc: Paul Moore Cc: Peter Zijlstra Cc: Stephen Smalley Signed-off-by: Andrew Morton --- include/linux/mm.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 418d26608ece..da5219b48d52 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -886,8 +886,8 @@ static inline bool vma_is_anonymous(struct vm_area_struct *vma) */ static inline bool vma_is_initial_heap(const struct vm_area_struct *vma) { - return vma->vm_start <= vma->vm_mm->brk && - vma->vm_end >= vma->vm_mm->start_brk; + return vma->vm_start < vma->vm_mm->brk && + vma->vm_end > vma->vm_mm->start_brk; } /* @@ -901,8 +901,8 @@ static inline bool vma_is_initial_stack(const struct vm_area_struct *vma) * its "stack". It's not even well-defined for programs written * languages like Go. */ - return vma->vm_start <= vma->vm_mm->start_stack && - vma->vm_end >= vma->vm_mm->start_stack; + return vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack; } static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) -- cgit v1.2.3-73-gaa49b From 6376a824595607e99d032a39ba3394988b4fce96 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 8 Dec 2023 17:50:18 +0000 Subject: mm/damon/core: make damon_start() waits until kdamond_fn() starts The cleanup tasks of kdamond threads including reset of corresponding DAMON context's ->kdamond field and decrease of global nr_running_ctxs counter is supposed to be executed by kdamond_fn(). However, commit 0f91d13366a4 ("mm/damon: simplify stop mechanism") made neither damon_start() nor damon_stop() ensure the corresponding kdamond has started the execution of kdamond_fn(). As a result, the cleanup can be skipped if damon_stop() is called fast enough after the previous damon_start(). Especially the skipped reset of ->kdamond could cause a use-after-free. Fix it by waiting for start of kdamond_fn() execution from damon_start(). Link: https://lkml.kernel.org/r/20231208175018.63880-1-sj@kernel.org Fixes: 0f91d13366a4 ("mm/damon: simplify stop mechanism") Signed-off-by: SeongJae Park Reported-by: Jakub Acs Cc: Changbin Du Cc: Jakub Acs Cc: # 5.15.x Signed-off-by: Andrew Morton --- include/linux/damon.h | 2 ++ mm/damon/core.c | 6 ++++++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index ab2f17d9926b..e00ddf1ed39c 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -559,6 +559,8 @@ struct damon_ctx { * update */ unsigned long next_ops_update_sis; + /* for waiting until the execution of the kdamond_fn is started */ + struct completion kdamond_started; /* public: */ struct task_struct *kdamond; diff --git a/mm/damon/core.c b/mm/damon/core.c index ce1562783e7e..3a05e71509b9 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -445,6 +445,8 @@ struct damon_ctx *damon_new_ctx(void) if (!ctx) return NULL; + init_completion(&ctx->kdamond_started); + ctx->attrs.sample_interval = 5 * 1000; ctx->attrs.aggr_interval = 100 * 1000; ctx->attrs.ops_update_interval = 60 * 1000 * 1000; @@ -668,11 +670,14 @@ static int __damon_start(struct damon_ctx *ctx) mutex_lock(&ctx->kdamond_lock); if (!ctx->kdamond) { err = 0; + reinit_completion(&ctx->kdamond_started); ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d", nr_running_ctxs); if (IS_ERR(ctx->kdamond)) { err = PTR_ERR(ctx->kdamond); ctx->kdamond = NULL; + } else { + wait_for_completion(&ctx->kdamond_started); } } mutex_unlock(&ctx->kdamond_lock); @@ -1433,6 +1438,7 @@ static int kdamond_fn(void *data) pr_debug("kdamond (%d) starts\n", current->pid); + complete(&ctx->kdamond_started); kdamond_init_intervals_sis(ctx); if (ctx->ops.init) -- cgit v1.2.3-73-gaa49b From 081488051d28d32569ebb7c7a23572778b2e7d57 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Thu, 7 Dec 2023 23:14:04 -0700 Subject: mm/mglru: fix underprotected page cache Unmapped folios accessed through file descriptors can be underprotected. Those folios are added to the oldest generation based on: 1. The fact that they are less costly to reclaim (no need to walk the rmap and flush the TLB) and have less impact on performance (don't cause major PFs and can be non-blocking if needed again). 2. The observation that they are likely to be single-use. E.g., for client use cases like Android, its apps parse configuration files and store the data in heap (anon); for server use cases like MySQL, it reads from InnoDB files and holds the cached data for tables in buffer pools (anon). However, the oldest generation can be very short lived, and if so, it doesn't provide the PID controller with enough time to respond to a surge of refaults. (Note that the PID controller uses weighted refaults and those from evicted generations only take a half of the whole weight.) In other words, for a short lived generation, the moving average smooths out the spike quickly. To fix the problem: 1. For folios that are already on LRU, if they can be beyond the tracking range of tiers, i.e., five accesses through file descriptors, move them to the second oldest generation to give them more time to age. (Note that tiers are used by the PID controller to statistically determine whether folios accessed multiple times through file descriptors are worth protecting.) 2. When adding unmapped folios to LRU, adjust the placement of them so that they are not too close to the tail. The effect of this is similar to the above. On Android, launching 55 apps sequentially: Before After Change workingset_refault_anon 25641024 25598972 0% workingset_refault_file 115016834 106178438 -8% Link: https://lkml.kernel.org/r/20231208061407.2125867-1-yuzhao@google.com Fixes: ac35a4902374 ("mm: multi-gen LRU: minimal implementation") Signed-off-by: Yu Zhao Reported-by: Charan Teja Kalla Tested-by: Kalesh Singh Cc: T.J. Mercier Cc: Kairui Song Cc: Hillf Danton Cc: Jaroslav Pulchart Cc: Signed-off-by: Andrew Morton --- include/linux/mm_inline.h | 23 ++++++++++++++--------- mm/vmscan.c | 2 +- mm/workingset.c | 6 +++--- 3 files changed, 18 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 9ae7def16cb2..f4fe593c1400 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -232,22 +232,27 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, if (folio_test_unevictable(folio) || !lrugen->enabled) return false; /* - * There are three common cases for this page: - * 1. If it's hot, e.g., freshly faulted in or previously hot and - * migrated, add it to the youngest generation. - * 2. If it's cold but can't be evicted immediately, i.e., an anon page - * not in swapcache or a dirty page pending writeback, add it to the - * second oldest generation. - * 3. Everything else (clean, cold) is added to the oldest generation. + * There are four common cases for this page: + * 1. If it's hot, i.e., freshly faulted in, add it to the youngest + * generation, and it's protected over the rest below. + * 2. If it can't be evicted immediately, i.e., a dirty page pending + * writeback, add it to the second youngest generation. + * 3. If it should be evicted first, e.g., cold and clean from + * folio_rotate_reclaimable(), add it to the oldest generation. + * 4. Everything else falls between 2 & 3 above and is added to the + * second oldest generation if it's considered inactive, or the + * oldest generation otherwise. See lru_gen_is_active(). */ if (folio_test_active(folio)) seq = lrugen->max_seq; else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) || (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio)))) - seq = lrugen->min_seq[type] + 1; - else + seq = lrugen->max_seq - 1; + else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq) seq = lrugen->min_seq[type]; + else + seq = lrugen->min_seq[type] + 1; gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; diff --git a/mm/vmscan.c b/mm/vmscan.c index 506f8220c5fe..540333f5415c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4232,7 +4232,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c } /* protected */ - if (tier > tier_idx) { + if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) { int hist = lru_hist_from_seq(lrugen->min_seq[type]); gen = folio_inc_gen(lruvec, folio, false); diff --git a/mm/workingset.c b/mm/workingset.c index b192e44a0e7c..33baad203277 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -313,10 +313,10 @@ static void lru_gen_refault(struct folio *folio, void *shadow) * 1. For pages accessed through page tables, hotter pages pushed out * hot pages which refaulted immediately. * 2. For pages accessed multiple times through file descriptors, - * numbers of accesses might have been out of the range. + * they would have been protected by sort_folio(). */ - if (lru_gen_in_fault() || refs == BIT(LRU_REFS_WIDTH)) { - folio_set_workingset(folio); + if (lru_gen_in_fault() || refs >= BIT(LRU_REFS_WIDTH) - 1) { + set_mask_bits(&folio->flags, 0, LRU_REFS_MASK | BIT(PG_workingset)); mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta); } unlock: -- cgit v1.2.3-73-gaa49b From 8aa420617918d12d1f5d55030a503c9418e73c2c Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Thu, 7 Dec 2023 23:14:06 -0700 Subject: mm/mglru: respect min_ttl_ms with memcgs While investigating kswapd "consuming 100% CPU" [1] (also see "mm/mglru: try to stop at high watermarks"), it was discovered that the memcg LRU can breach the thrashing protection imposed by min_ttl_ms. Before the memcg LRU: kswapd() shrink_node_memcgs() mem_cgroup_iter() inc_max_seq() // always hit a different memcg lru_gen_age_node() mem_cgroup_iter() check the timestamp of the oldest generation After the memcg LRU: kswapd() shrink_many() restart: iterate the memcg LRU: inc_max_seq() // occasionally hit the same memcg if raced with lru_gen_rotate_memcg(): goto restart lru_gen_age_node() mem_cgroup_iter() check the timestamp of the oldest generation Specifically, when the restart happens in shrink_many(), it needs to stick with the (memcg LRU) generation it began with. In other words, it should neither re-read memcg_lru->seq nor age an lruvec of a different generation. Otherwise it can hit the same memcg multiple times without giving lru_gen_age_node() a chance to check the timestamp of that memcg's oldest generation (against min_ttl_ms). [1] https://lore.kernel.org/CAK8fFZ4DY+GtBA40Pm7Nn5xCHy+51w3sfxPqkqpqakSXYyX+Wg@mail.gmail.com/ Link: https://lkml.kernel.org/r/20231208061407.2125867-3-yuzhao@google.com Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists") Signed-off-by: Yu Zhao Tested-by: T.J. Mercier Cc: Charan Teja Kalla Cc: Hillf Danton Cc: Jaroslav Pulchart Cc: Kairui Song Cc: Kalesh Singh Cc: Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 30 +++++++++++++++++------------- mm/vmscan.c | 30 ++++++++++++++++-------------- 2 files changed, 33 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3c25226beeed..23533b12bee2 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -505,33 +505,37 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); * the old generation, is incremented when all its bins become empty. * * There are four operations: - * 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its + * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its * current generation (old or young) and updates its "seg" to "head"; - * 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its + * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its * current generation (old or young) and updates its "seg" to "tail"; - * 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old + * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old * generation, updates its "gen" to "old" and resets its "seg" to "default"; - * 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the + * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the * young generation, updates its "gen" to "young" and resets its "seg" to * "default". * * The events that trigger the above operations are: * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; - * 2. The first attempt to reclaim an memcg below low, which triggers + * 2. The first attempt to reclaim a memcg below low, which triggers * MEMCG_LRU_TAIL; - * 3. The first attempt to reclaim an memcg below reclaimable size threshold, + * 3. The first attempt to reclaim a memcg below reclaimable size threshold, * which triggers MEMCG_LRU_TAIL; - * 4. The second attempt to reclaim an memcg below reclaimable size threshold, + * 4. The second attempt to reclaim a memcg below reclaimable size threshold, * which triggers MEMCG_LRU_YOUNG; - * 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG; + * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG; * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; - * 7. Offlining an memcg, which triggers MEMCG_LRU_OLD. + * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD. * - * Note that memcg LRU only applies to global reclaim, and the round-robin - * incrementing of their max_seq counters ensures the eventual fairness to all - * eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). + * Notes: + * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing + * of their max_seq counters ensures the eventual fairness to all eligible + * memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). + * 2. There are only two valid generations: old (seq) and young (seq+1). + * MEMCG_NR_GENS is set to three so that when reading the generation counter + * locklessly, a stale value (seq-1) does not wraparound to young. */ -#define MEMCG_NR_GENS 2 +#define MEMCG_NR_GENS 3 #define MEMCG_NR_BINS 8 struct lru_gen_memcg { diff --git a/mm/vmscan.c b/mm/vmscan.c index bb7dacd8f753..e5fe4a94345f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4089,6 +4089,9 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) else VM_WARN_ON_ONCE(true); + WRITE_ONCE(lruvec->lrugen.seg, seg); + WRITE_ONCE(lruvec->lrugen.gen, new); + hlist_nulls_del_rcu(&lruvec->lrugen.list); if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD) @@ -4099,9 +4102,6 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) pgdat->memcg_lru.nr_memcgs[old]--; pgdat->memcg_lru.nr_memcgs[new]++; - lruvec->lrugen.gen = new; - WRITE_ONCE(lruvec->lrugen.seg, seg); - if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); @@ -4124,11 +4124,11 @@ void lru_gen_online_memcg(struct mem_cgroup *memcg) gen = get_memcg_gen(pgdat->memcg_lru.seq); + lruvec->lrugen.gen = gen; + hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]); pgdat->memcg_lru.nr_memcgs[gen]++; - lruvec->lrugen.gen = gen; - spin_unlock_irq(&pgdat->memcg_lru.lock); } } @@ -4635,7 +4635,7 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool DEFINE_MAX_SEQ(lruvec); if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg)) - return 0; + return -1; if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan)) return nr_to_scan; @@ -4710,7 +4710,7 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) cond_resched(); } - /* whether try_to_inc_max_seq() was successful */ + /* whether this lruvec should be rotated */ return nr_to_scan < 0; } @@ -4764,13 +4764,13 @@ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc) struct lruvec *lruvec; struct lru_gen_folio *lrugen; struct mem_cgroup *memcg; - const struct hlist_nulls_node *pos; + struct hlist_nulls_node *pos; + gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); bin = first_bin = get_random_u32_below(MEMCG_NR_BINS); restart: op = 0; memcg = NULL; - gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); rcu_read_lock(); @@ -4781,6 +4781,10 @@ restart: } mem_cgroup_put(memcg); + memcg = NULL; + + if (gen != READ_ONCE(lrugen->gen)) + continue; lruvec = container_of(lrugen, struct lruvec, lrugen); memcg = lruvec_memcg(lruvec); @@ -4865,16 +4869,14 @@ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH) return; /* - * Determine the initial priority based on ((total / MEMCG_NR_GENS) >> - * priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, where the - * estimated reclaimed_to_scanned_ratio = inactive / total. + * Determine the initial priority based on + * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, + * where reclaimed_to_scanned_ratio = inactive / total. */ reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE); if (get_swappiness(lruvec, sc)) reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON); - reclaimable /= MEMCG_NR_GENS; - /* round down reclaimable and round up sc->nr_to_reclaim */ priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1); -- cgit v1.2.3-73-gaa49b From 4376807bf2d5371c3e00080c972be568c3f8a7d1 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Thu, 7 Dec 2023 23:14:07 -0700 Subject: mm/mglru: reclaim offlined memcgs harder In the effort to reduce zombie memcgs [1], it was discovered that the memcg LRU doesn't apply enough pressure on offlined memcgs. Specifically, instead of rotating them to the tail of the current generation (MEMCG_LRU_TAIL) for a second attempt, it moves them to the next generation (MEMCG_LRU_YOUNG) after the first attempt. Not applying enough pressure on offlined memcgs can cause them to build up, and this can be particularly harmful to memory-constrained systems. On Pixel 8 Pro, launching apps for 50 cycles: Before After Change Zombie memcgs 45 35 -22% [1] https://lore.kernel.org/CABdmKX2M6koq4Q0Cmp_-=wbP0Qa190HdEGGaHfxNS05gAkUtPA@mail.gmail.com/ Link: https://lkml.kernel.org/r/20231208061407.2125867-4-yuzhao@google.com Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists") Signed-off-by: Yu Zhao Reported-by: T.J. Mercier Tested-by: T.J. Mercier Cc: Charan Teja Kalla Cc: Hillf Danton Cc: Jaroslav Pulchart Cc: Kairui Song Cc: Kalesh Singh Cc: Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 8 ++++---- mm/vmscan.c | 24 ++++++++++++++++-------- 2 files changed, 20 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 23533b12bee2..9db36e197712 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -519,10 +519,10 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; * 2. The first attempt to reclaim a memcg below low, which triggers * MEMCG_LRU_TAIL; - * 3. The first attempt to reclaim a memcg below reclaimable size threshold, - * which triggers MEMCG_LRU_TAIL; - * 4. The second attempt to reclaim a memcg below reclaimable size threshold, - * which triggers MEMCG_LRU_YOUNG; + * 3. The first attempt to reclaim a memcg offlined or below reclaimable size + * threshold, which triggers MEMCG_LRU_TAIL; + * 4. The second attempt to reclaim a memcg offlined or below reclaimable size + * threshold, which triggers MEMCG_LRU_YOUNG; * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG; * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD. diff --git a/mm/vmscan.c b/mm/vmscan.c index e5fe4a94345f..9dd8977de5a2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4598,7 +4598,12 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, } /* try to scrape all its memory if this memcg was deleted */ - *nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total; + if (!mem_cgroup_online(memcg)) { + *nr_to_scan = total; + return false; + } + + *nr_to_scan = total >> sc->priority; /* * The aging tries to be lazy to reduce the overhead, while the eviction @@ -4719,14 +4724,9 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) bool success; unsigned long scanned = sc->nr_scanned; unsigned long reclaimed = sc->nr_reclaimed; - int seg = lru_gen_memcg_seg(lruvec); struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); - /* see the comment on MEMCG_NR_GENS */ - if (!lruvec_is_sizable(lruvec, sc)) - return seg != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; - mem_cgroup_calculate_protection(NULL, memcg); if (mem_cgroup_below_min(NULL, memcg)) @@ -4734,7 +4734,7 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) if (mem_cgroup_below_low(NULL, memcg)) { /* see the comment on MEMCG_NR_GENS */ - if (seg != MEMCG_LRU_TAIL) + if (lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL) return MEMCG_LRU_TAIL; memcg_memory_event(memcg, MEMCG_LOW); @@ -4750,7 +4750,15 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) flush_reclaim_state(sc); - return success ? MEMCG_LRU_YOUNG : 0; + if (success && mem_cgroup_online(memcg)) + return MEMCG_LRU_YOUNG; + + if (!success && lruvec_is_sizable(lruvec, sc)) + return 0; + + /* one retry if offlined or too small */ + return lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL ? + MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; } #ifdef CONFIG_MEMCG -- cgit v1.2.3-73-gaa49b