From 307ed94c37f842676d336cf5f2162022f4d7cdc4 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 18:36:10 -0500 Subject: memcontrol.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/memcontrol.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1b4150ff64be..d275c72c4f8e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -106,7 +106,7 @@ struct lruvec_stat { */ struct memcg_shrinker_map { struct rcu_head rcu; - unsigned long map[0]; + unsigned long map[]; }; /* @@ -148,7 +148,7 @@ struct mem_cgroup_threshold_ary { /* Size of entries[] */ unsigned int size; /* Array of thresholds */ - struct mem_cgroup_threshold entries[0]; + struct mem_cgroup_threshold entries[]; }; struct mem_cgroup_thresholds { -- cgit v1.2.3 From 04fd61a4e01028210a91f0efc408c8bc61a3018c Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Wed, 13 May 2020 17:50:34 -0700 Subject: mm, memcg: fix inconsistent oom event behavior A recent commit 9852ae3fe529 ("mm, memcg: consider subtrees in memory.events") changed the behavior of memcg events, which will now consider subtrees in memory.events. But oom_kill event is a special one as it is used in both cgroup1 and cgroup2. In cgroup1, it is displayed in memory.oom_control. The file memory.oom_control is in both root memcg and non root memcg, that is different with memory.event as it only in non-root memcg. That commit is okay for cgroup2, but it is not okay for cgroup1 as it will cause inconsistent behavior between root memcg and non-root memcg. Here's an example on why this behavior is inconsistent in cgroup1. root memcg / memcg foo / memcg bar Suppose there's an oom_kill in memcg bar, then the oon_kill will be root memcg : memory.oom_control(oom_kill) 0 / memcg foo : memory.oom_control(oom_kill) 1 / memcg bar : memory.oom_control(oom_kill) 1 For the non-root memcg, its memory.oom_control(oom_kill) includes its descendants' oom_kill, but for root memcg, it doesn't include its descendants' oom_kill. That means, memory.oom_control(oom_kill) has different meanings in different memcgs. That is inconsistent. Then the user has to know whether the memcg is root or not. If we can't fully support it in cgroup1, for example by adding memory.events.local into cgroup1 as well, then let's don't touch its original behavior. Fixes: 9852ae3fe529 ("mm, memcg: consider subtrees in memory.events") Reported-by: Randy Dunlap Signed-off-by: Yafang Shao Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Chris Down Acked-by: Michal Hocko Cc: Link: http://lkml.kernel.org/r/20200502141055.7378-1-laoar.shao@gmail.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d275c72c4f8e..977edd3b7bd8 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -783,6 +783,8 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg, atomic_long_inc(&memcg->memory_events[event]); cgroup_file_notify(&memcg->events_file); + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + break; if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) break; } while ((memcg = parent_mem_cgroup(memcg)) && -- cgit v1.2.3 From d1663a907bd348f912b7f7088e83ca1b6fd3309f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 1 Jun 2020 21:49:49 -0700 Subject: mm/memcg: move cgroup high memory limit setting into struct page_counter High memory limit is currently recorded directly in struct mem_cgroup. We are about to add a high limit for swap, move the field to struct page_counter and add some helpers. Signed-off-by: Jakub Kicinski Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Chris Down Cc: Hugh Dickins Cc: Michal Hocko Cc: Tejun Heo Link: http://lkml.kernel.org/r/20200527195846.102707-4-kuba@kernel.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 --- include/linux/page_counter.h | 8 ++++++++ mm/memcontrol.c | 19 +++++++++++-------- 3 files changed, 19 insertions(+), 11 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 977edd3b7bd8..95a09a7ec412 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -215,9 +215,6 @@ struct mem_cgroup { struct page_counter kmem; struct page_counter tcpmem; - /* Upper bound of normal memory consumption range */ - unsigned long high; - /* Range enforcement for interrupt charges */ struct work_struct high_work; diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index bab7e57f659b..85bd413e784e 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -10,6 +10,7 @@ struct page_counter { atomic_long_t usage; unsigned long min; unsigned long low; + unsigned long high; unsigned long max; struct page_counter *parent; @@ -55,6 +56,13 @@ bool page_counter_try_charge(struct page_counter *counter, void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages); void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages); void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages); + +static inline void page_counter_set_high(struct page_counter *counter, + unsigned long nr_pages) +{ + WRITE_ONCE(counter->high, nr_pages); +} + int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages); int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6a857b87428d..08cf17b186fb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2252,7 +2252,8 @@ static void reclaim_high(struct mem_cgroup *memcg, gfp_t gfp_mask) { do { - if (page_counter_read(&memcg->memory) <= READ_ONCE(memcg->high)) + if (page_counter_read(&memcg->memory) <= + READ_ONCE(memcg->memory.high)) continue; memcg_memory_event(memcg, MEMCG_HIGH); try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true); @@ -2345,7 +2346,7 @@ static u64 mem_find_max_overage(struct mem_cgroup *memcg) do { overage = calculate_overage(page_counter_read(&memcg->memory), - READ_ONCE(memcg->high)); + READ_ONCE(memcg->memory.high)); max_overage = max(overage, max_overage); } while ((memcg = parent_mem_cgroup(memcg)) && !mem_cgroup_is_root(memcg)); @@ -2604,7 +2605,8 @@ done_restock: * reclaim, the cost of mismatch is negligible. */ do { - if (page_counter_read(&memcg->memory) > READ_ONCE(memcg->high)) { + if (page_counter_read(&memcg->memory) > + READ_ONCE(memcg->memory.high)) { /* Don't bother a random interrupted task */ if (in_interrupt()) { schedule_work(&memcg->high_work); @@ -4347,7 +4349,7 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, while ((parent = parent_mem_cgroup(memcg))) { unsigned long ceiling = min(READ_ONCE(memcg->memory.max), - READ_ONCE(memcg->high)); + READ_ONCE(memcg->memory.high)); unsigned long used = page_counter_read(&memcg->memory); *pheadroom = min(*pheadroom, ceiling - min(ceiling, used)); @@ -5072,7 +5074,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) if (IS_ERR(memcg)) return ERR_CAST(memcg); - WRITE_ONCE(memcg->high, PAGE_COUNTER_MAX); + page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX); memcg->soft_limit = PAGE_COUNTER_MAX; if (parent) { memcg->swappiness = mem_cgroup_swappiness(parent); @@ -5225,7 +5227,7 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) page_counter_set_max(&memcg->tcpmem, PAGE_COUNTER_MAX); page_counter_set_min(&memcg->memory, 0); page_counter_set_low(&memcg->memory, 0); - WRITE_ONCE(memcg->high, PAGE_COUNTER_MAX); + page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX); memcg->soft_limit = PAGE_COUNTER_MAX; memcg_wb_domain_size_changed(memcg); } @@ -6024,7 +6026,8 @@ static ssize_t memory_low_write(struct kernfs_open_file *of, static int memory_high_show(struct seq_file *m, void *v) { - return seq_puts_memcg_tunable(m, READ_ONCE(mem_cgroup_from_seq(m)->high)); + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->memory.high)); } static ssize_t memory_high_write(struct kernfs_open_file *of, @@ -6041,7 +6044,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, if (err) return err; - WRITE_ONCE(memcg->high, high); + page_counter_set_high(&memcg->memory, high); for (;;) { unsigned long nr_pages = page_counter_read(&memcg->memory); -- cgit v1.2.3 From 4b82ab4f28836646eca12cb37f408568d3cdc5c3 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 1 Jun 2020 21:49:52 -0700 Subject: mm/memcg: automatically penalize tasks with high swap use Add a memory.swap.high knob, which can be used to protect the system from SWAP exhaustion. The mechanism used for penalizing is similar to memory.high penalty (sleep on return to user space). That is not to say that the knob itself is equivalent to memory.high. The objective is more to protect the system from potentially buggy tasks consuming a lot of swap and impacting other tasks, or even bringing the whole system to stand still with complete SWAP exhaustion. Hopefully without the need to find per-task hard limits. Slowing misbehaving tasks down gradually allows user space oom killers or other protection mechanisms to react. oomd and earlyoom already do killing based on swap exhaustion, and memory.swap.high protection will help implement such userspace oom policies more reliably. We can use one counter for number of pages allocated under pressure to save struct task space and avoid two separate hierarchy walks on the hot path. The exact overage is calculated on return to user space, anyway. Take the new high limit into account when determining if swap is "full". Borrowing the explanation from Johannes: The idea behind "swap full" is that as long as the workload has plenty of swap space available and it's not changing its memory contents, it makes sense to generously hold on to copies of data in the swap device, even after the swapin. A later reclaim cycle can drop the page without any IO. Trading disk space for IO. But the only two ways to reclaim a swap slot is when they're faulted in and the references go away, or by scanning the virtual address space like swapoff does - which is very expensive (one could argue it's too expensive even for swapoff, it's often more practical to just reboot). So at some point in the fill level, we have to start freeing up swap slots on fault/swapin. Otherwise we could eventually run out of swap slots while they're filled with copies of data that is also in RAM. We don't want to OOM a workload because its available swap space is filled with redundant cache. Signed-off-by: Jakub Kicinski Signed-off-by: Andrew Morton Acked-by: Johannes Weiner Cc: Tejun Heo Cc: Chris Down Cc: Shakeel Butt Cc: Michal Hocko Cc: Hugh Dickins Link: http://lkml.kernel.org/r/20200527195846.102707-5-kuba@kernel.org Signed-off-by: Linus Torvalds --- Documentation/admin-guide/cgroup-v2.rst | 20 ++++++++ include/linux/memcontrol.h | 1 + mm/memcontrol.c | 88 ++++++++++++++++++++++++++++++--- 3 files changed, 102 insertions(+), 7 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 5f12f203822e..b8c0460730f3 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1374,6 +1374,22 @@ PAGE_SIZE multiple when read back. The total amount of swap currently being used by the cgroup and its descendants. + memory.swap.high + A read-write single value file which exists on non-root + cgroups. The default is "max". + + Swap usage throttle limit. If a cgroup's swap usage exceeds + this limit, all its further allocations will be throttled to + allow userspace to implement custom out-of-memory procedures. + + This limit marks a point of no return for the cgroup. It is NOT + designed to manage the amount of swapping a workload does + during regular operation. Compare to memory.swap.max, which + prohibits swapping past a set amount, but lets the cgroup + continue unimpeded as long as other memory can be reclaimed. + + Healthy workloads are not expected to reach this limit. + memory.swap.max A read-write single value file which exists on non-root cgroups. The default is "max". @@ -1387,6 +1403,10 @@ PAGE_SIZE multiple when read back. otherwise, a value change in this file generates a file modified event. + high + The number of times the cgroup's swap usage was over + the high threshold. + max The number of times the cgroup's swap usage was about to go over the max boundary and swap allocation diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 95a09a7ec412..bfe9533bb67e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -45,6 +45,7 @@ enum memcg_memory_event { MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, + MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, MEMCG_NR_MEMORY_EVENTS, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 08cf17b186fb..f3087e22dfa9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2354,6 +2354,22 @@ static u64 mem_find_max_overage(struct mem_cgroup *memcg) return max_overage; } +static u64 swap_find_max_overage(struct mem_cgroup *memcg) +{ + u64 overage, max_overage = 0; + + do { + overage = calculate_overage(page_counter_read(&memcg->swap), + READ_ONCE(memcg->swap.high)); + if (overage) + memcg_memory_event(memcg, MEMCG_SWAP_HIGH); + max_overage = max(overage, max_overage); + } while ((memcg = parent_mem_cgroup(memcg)) && + !mem_cgroup_is_root(memcg)); + + return max_overage; +} + /* * Get the number of jiffies that we should penalise a mischievous cgroup which * is exceeding its memory.high by checking both it and its ancestors. @@ -2415,6 +2431,9 @@ void mem_cgroup_handle_over_high(void) penalty_jiffies = calculate_high_delay(memcg, nr_pages, mem_find_max_overage(memcg)); + penalty_jiffies += calculate_high_delay(memcg, nr_pages, + swap_find_max_overage(memcg)); + /* * Clamp the max delay per usermode return so as to still keep the * application moving forwards and also permit diagnostics, albeit @@ -2605,13 +2624,32 @@ done_restock: * reclaim, the cost of mismatch is negligible. */ do { - if (page_counter_read(&memcg->memory) > - READ_ONCE(memcg->memory.high)) { - /* Don't bother a random interrupted task */ - if (in_interrupt()) { + bool mem_high, swap_high; + + mem_high = page_counter_read(&memcg->memory) > + READ_ONCE(memcg->memory.high); + swap_high = page_counter_read(&memcg->swap) > + READ_ONCE(memcg->swap.high); + + /* Don't bother a random interrupted task */ + if (in_interrupt()) { + if (mem_high) { schedule_work(&memcg->high_work); break; } + continue; + } + + if (mem_high || swap_high) { + /* + * The allocating tasks in this cgroup will need to do + * reclaim or be throttled to prevent further growth + * of the memory or swap footprints. + * + * Target some best-effort fairness between the tasks, + * and distribute reclaim work and delay penalties + * based on how much each task is actually allocating. + */ current->memcg_nr_pages_over_high += batch; set_notify_resume(current); break; @@ -5076,6 +5114,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX); memcg->soft_limit = PAGE_COUNTER_MAX; + page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX); if (parent) { memcg->swappiness = mem_cgroup_swappiness(parent); memcg->oom_kill_disable = parent->oom_kill_disable; @@ -5229,6 +5268,7 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) page_counter_set_low(&memcg->memory, 0); page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX); memcg->soft_limit = PAGE_COUNTER_MAX; + page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX); memcg_wb_domain_size_changed(memcg); } @@ -7142,10 +7182,13 @@ bool mem_cgroup_swap_full(struct page *page) if (!memcg) return false; - for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) - if (page_counter_read(&memcg->swap) * 2 >= - READ_ONCE(memcg->swap.max)) + for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) { + unsigned long usage = page_counter_read(&memcg->swap); + + if (usage * 2 >= READ_ONCE(memcg->swap.high) || + usage * 2 >= READ_ONCE(memcg->swap.max)) return true; + } return false; } @@ -7175,6 +7218,29 @@ static u64 swap_current_read(struct cgroup_subsys_state *css, return (u64)page_counter_read(&memcg->swap) * PAGE_SIZE; } +static int swap_high_show(struct seq_file *m, void *v) +{ + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->swap.high)); +} + +static ssize_t swap_high_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long high; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "max", &high); + if (err) + return err; + + page_counter_set_high(&memcg->swap, high); + + return nbytes; +} + static int swap_max_show(struct seq_file *m, void *v) { return seq_puts_memcg_tunable(m, @@ -7202,6 +7268,8 @@ static int swap_events_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + seq_printf(m, "high %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_SWAP_HIGH])); seq_printf(m, "max %lu\n", atomic_long_read(&memcg->memory_events[MEMCG_SWAP_MAX])); seq_printf(m, "fail %lu\n", @@ -7216,6 +7284,12 @@ static struct cftype swap_files[] = { .flags = CFTYPE_NOT_ON_ROOT, .read_u64 = swap_current_read, }, + { + .name = "swap.high", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = swap_high_show, + .write = swap_high_write, + }, { .name = "swap.max", .flags = CFTYPE_NOT_ON_ROOT, -- cgit v1.2.3 From 3fba69a56e16e8dcf182fe6ca77735dd65a898aa Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:31 -0700 Subject: mm: memcontrol: drop @compound parameter from memcg charging API The memcg charging API carries a boolean @compound parameter that tells whether the page we're dealing with is a hugepage. mem_cgroup_commit_charge() has another boolean @lrucare that indicates whether the page needs LRU locking or not while charging. The majority of callsites know those parameters at compile time, which results in a lot of naked "false, false" argument lists. This makes for cryptic code and is a breeding ground for subtle mistakes. Thankfully, the huge page state can be inferred from the page itself and doesn't need to be passed along. This is safe because charging completes before the page is published and somebody may split it. Simplify the callsites by removing @compound, and let memcg infer the state by using hpage_nr_pages() unconditionally. That function does PageTransHuge() to identify huge pages, which also helpfully asserts that nobody passes in tail pages by accident. The following patches will introduce a new charging API, best not to carry over unnecessary weight. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Alex Shi Reviewed-by: Joonsoo Kim Reviewed-by: Shakeel Butt Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-4-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 22 ++++++++-------------- kernel/events/uprobes.c | 6 +++--- mm/filemap.c | 6 +++--- mm/huge_memory.c | 8 ++++---- mm/khugepaged.c | 20 ++++++++++---------- mm/memcontrol.c | 38 +++++++++++++++----------------------- mm/memory.c | 32 +++++++++++++++----------------- mm/migrate.c | 6 +++--- mm/shmem.c | 22 +++++++++------------- mm/swapfile.c | 9 ++++----- mm/userfaultfd.c | 6 +++--- 11 files changed, 77 insertions(+), 98 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index bfe9533bb67e..fc400002c7be 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -359,15 +359,12 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound); + gfp_t gfp_mask, struct mem_cgroup **memcgp); int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound); + gfp_t gfp_mask, struct mem_cgroup **memcgp); void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare, bool compound); -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, - bool compound); + bool lrucare); +void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -849,8 +846,7 @@ static inline enum mem_cgroup_protection mem_cgroup_protected( static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - struct mem_cgroup **memcgp, - bool compound) + struct mem_cgroup **memcgp) { *memcgp = NULL; return 0; @@ -859,8 +855,7 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, static inline int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - struct mem_cgroup **memcgp, - bool compound) + struct mem_cgroup **memcgp) { *memcgp = NULL; return 0; @@ -868,13 +863,12 @@ static inline int mem_cgroup_try_charge_delay(struct page *page, static inline void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare, bool compound) + bool lrucare) { } static inline void mem_cgroup_cancel_charge(struct page *page, - struct mem_cgroup *memcg, - bool compound) + struct mem_cgroup *memcg) { } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index ece7e13f6e4a..40e7488ce467 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -169,7 +169,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, if (new_page) { err = mem_cgroup_try_charge(new_page, vma->vm_mm, GFP_KERNEL, - &memcg, false); + &memcg); if (err) return err; } @@ -181,7 +181,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, err = -EAGAIN; if (!page_vma_mapped_walk(&pvmw)) { if (new_page) - mem_cgroup_cancel_charge(new_page, memcg, false); + mem_cgroup_cancel_charge(new_page, memcg); goto unlock; } VM_BUG_ON_PAGE(addr != pvmw.address, old_page); @@ -189,7 +189,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, if (new_page) { get_page(new_page); page_add_new_anon_rmap(new_page, vma, addr, false); - mem_cgroup_commit_charge(new_page, memcg, false, false); + mem_cgroup_commit_charge(new_page, memcg, false); lru_cache_add_active_or_unevictable(new_page, vma); } else /* no new page, just dec_mm_counter for old_page */ diff --git a/mm/filemap.c b/mm/filemap.c index 9af4af660ef1..f268cfffbc6e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -842,7 +842,7 @@ static int __add_to_page_cache_locked(struct page *page, if (!huge) { error = mem_cgroup_try_charge(page, current->mm, - gfp_mask, &memcg, false); + gfp_mask, &memcg); if (error) return error; } @@ -878,14 +878,14 @@ unlock: goto error; if (!huge) - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); trace_mm_filemap_add_to_page_cache(page); return 0; error: page->mapping = NULL; /* Leave page->index set: truncation relies upon it */ if (!huge) - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); put_page(page); return xas_error(&xas); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 693c0ff2256c..672e34932b53 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -594,7 +594,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) { + if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); @@ -630,7 +630,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, vm_fault_t ret2; spin_unlock(vmf->ptl); - mem_cgroup_cancel_charge(page, memcg, true); + mem_cgroup_cancel_charge(page, memcg); put_page(page); pte_free(vma->vm_mm, pgtable); ret2 = handle_userfault(vmf, VM_UFFD_MISSING); @@ -641,7 +641,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); page_add_new_anon_rmap(page, vma, haddr, true); - mem_cgroup_commit_charge(page, memcg, false, true); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); @@ -658,7 +658,7 @@ unlock_release: release: if (pgtable) pte_free(vma->vm_mm, pgtable); - mem_cgroup_cancel_charge(page, memcg, true); + mem_cgroup_cancel_charge(page, memcg); put_page(page); return ret; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index e7897a7dfbec..0a29b51494fd 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1060,7 +1060,7 @@ static void collapse_huge_page(struct mm_struct *mm, goto out_nolock; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } @@ -1068,7 +1068,7 @@ static void collapse_huge_page(struct mm_struct *mm, down_read(&mm->mmap_sem); result = hugepage_vma_revalidate(mm, address, &vma); if (result) { - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); up_read(&mm->mmap_sem); goto out_nolock; } @@ -1076,7 +1076,7 @@ static void collapse_huge_page(struct mm_struct *mm, pmd = mm_find_pmd(mm, address); if (!pmd) { result = SCAN_PMD_NULL; - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); up_read(&mm->mmap_sem); goto out_nolock; } @@ -1088,7 +1088,7 @@ static void collapse_huge_page(struct mm_struct *mm, */ if (unmapped && !__collapse_huge_page_swapin(mm, vma, address, pmd, referenced)) { - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); up_read(&mm->mmap_sem); goto out_nolock; } @@ -1176,7 +1176,7 @@ static void collapse_huge_page(struct mm_struct *mm, spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); page_add_new_anon_rmap(new_page, vma, address, true); - mem_cgroup_commit_charge(new_page, memcg, false, true); + mem_cgroup_commit_charge(new_page, memcg, false); count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1); lru_cache_add_active_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); @@ -1194,7 +1194,7 @@ out_nolock: trace_mm_collapse_huge_page(mm, isolated, result); return; out: - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); goto out_up_write; } @@ -1637,7 +1637,7 @@ static void collapse_file(struct mm_struct *mm, goto out; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out; } @@ -1650,7 +1650,7 @@ static void collapse_file(struct mm_struct *mm, break; xas_unlock_irq(&xas); if (!xas_nomem(&xas, GFP_KERNEL)) { - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); result = SCAN_FAIL; goto out; } @@ -1887,7 +1887,7 @@ xa_unlocked: SetPageUptodate(new_page); page_ref_add(new_page, HPAGE_PMD_NR - 1); - mem_cgroup_commit_charge(new_page, memcg, false, true); + mem_cgroup_commit_charge(new_page, memcg, false); if (is_shmem) { set_page_dirty(new_page); @@ -1942,7 +1942,7 @@ xa_unlocked: VM_BUG_ON(nr_none); xas_unlock_irq(&xas); - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); new_page->mapping = NULL; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8f95896c5aa1..340c580f8363 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -834,7 +834,7 @@ static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event) static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, struct page *page, - bool compound, int nr_pages) + int nr_pages) { /* * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is @@ -848,7 +848,7 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, __mod_memcg_state(memcg, NR_SHMEM, nr_pages); } - if (compound) { + if (abs(nr_pages) > 1) { VM_BUG_ON_PAGE(!PageTransHuge(page), page); __mod_memcg_state(memcg, MEMCG_RSS_HUGE, nr_pages); } @@ -5501,9 +5501,9 @@ static int mem_cgroup_move_account(struct page *page, ret = 0; local_irq_disable(); - mem_cgroup_charge_statistics(to, page, compound, nr_pages); + mem_cgroup_charge_statistics(to, page, nr_pages); memcg_check_events(to, page); - mem_cgroup_charge_statistics(from, page, compound, -nr_pages); + mem_cgroup_charge_statistics(from, page, -nr_pages); memcg_check_events(from, page); local_irq_enable(); out_unlock: @@ -6494,7 +6494,6 @@ out: * @mm: mm context of the victim * @gfp_mask: reclaim mode * @memcgp: charged memcg return - * @compound: charge the page as compound or small page * * Try to charge @page to the memcg that @mm belongs to, reclaiming * pages according to @gfp_mask if necessary. @@ -6507,11 +6506,10 @@ out: * with mem_cgroup_cancel_charge() in case page instantiation fails. */ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound) + gfp_t gfp_mask, struct mem_cgroup **memcgp) { + unsigned int nr_pages = hpage_nr_pages(page); struct mem_cgroup *memcg = NULL; - unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; int ret = 0; if (mem_cgroup_disabled()) @@ -6553,13 +6551,12 @@ out: } int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound) + gfp_t gfp_mask, struct mem_cgroup **memcgp) { struct mem_cgroup *memcg; int ret; - ret = mem_cgroup_try_charge(page, mm, gfp_mask, memcgp, compound); + ret = mem_cgroup_try_charge(page, mm, gfp_mask, memcgp); memcg = *memcgp; mem_cgroup_throttle_swaprate(memcg, page_to_nid(page), gfp_mask); return ret; @@ -6570,7 +6567,6 @@ int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, * @page: page to charge * @memcg: memcg to charge the page to * @lrucare: page might be on LRU already - * @compound: charge the page as compound or small page * * Finalize a charge transaction started by mem_cgroup_try_charge(), * after page->mapping has been set up. This must happen atomically @@ -6583,9 +6579,9 @@ int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, * Use mem_cgroup_cancel_charge() to cancel the transaction instead. */ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare, bool compound) + bool lrucare) { - unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; + unsigned int nr_pages = hpage_nr_pages(page); VM_BUG_ON_PAGE(!page->mapping, page); VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); @@ -6603,7 +6599,7 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, commit_charge(page, memcg, lrucare); local_irq_disable(); - mem_cgroup_charge_statistics(memcg, page, compound, nr_pages); + mem_cgroup_charge_statistics(memcg, page, nr_pages); memcg_check_events(memcg, page); local_irq_enable(); @@ -6622,14 +6618,12 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, * mem_cgroup_cancel_charge - cancel a page charge * @page: page to charge * @memcg: memcg to charge the page to - * @compound: charge the page as compound or small page * * Cancel a charge transaction started by mem_cgroup_try_charge(). */ -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, - bool compound) +void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) { - unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; + unsigned int nr_pages = hpage_nr_pages(page); if (mem_cgroup_disabled()) return; @@ -6844,8 +6838,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) commit_charge(newpage, memcg, false); local_irq_save(flags); - mem_cgroup_charge_statistics(memcg, newpage, PageTransHuge(newpage), - nr_pages); + mem_cgroup_charge_statistics(memcg, newpage, nr_pages); memcg_check_events(memcg, newpage); local_irq_restore(flags); } @@ -7075,8 +7068,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) * only synchronisation we have for updating the per-CPU variables. */ VM_BUG_ON(!irqs_disabled()); - mem_cgroup_charge_statistics(memcg, page, PageTransHuge(page), - -nr_entries); + mem_cgroup_charge_statistics(memcg, page, -nr_entries); memcg_check_events(memcg, page); if (!mem_cgroup_is_root(memcg)) diff --git a/mm/memory.c b/mm/memory.c index 21438278afca..6b8c5900e9a4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2676,7 +2676,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } } - if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false)) + if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg)) goto oom_free_new; __SetPageUptodate(new_page); @@ -2711,7 +2711,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); page_add_new_anon_rmap(new_page, vma, vmf->address, false); - mem_cgroup_commit_charge(new_page, memcg, false, false); + mem_cgroup_commit_charge(new_page, memcg, false); lru_cache_add_active_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary @@ -2750,7 +2750,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) new_page = old_page; page_copied = 1; } else { - mem_cgroup_cancel_charge(new_page, memcg, false); + mem_cgroup_cancel_charge(new_page, memcg); } if (new_page) @@ -3193,8 +3193,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) goto out_page; } - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, - &memcg, false)) { + if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg)) { ret = VM_FAULT_OOM; goto out_page; } @@ -3245,11 +3244,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { page_add_new_anon_rmap(page, vma, vmf->address, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, vma); } else { do_page_add_anon_rmap(page, vma, vmf->address, exclusive); - mem_cgroup_commit_charge(page, memcg, true, false); + mem_cgroup_commit_charge(page, memcg, true); activate_page(page); } @@ -3285,7 +3284,7 @@ unlock: out: return ret; out_nomap: - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: unlock_page(page); @@ -3359,8 +3358,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) if (!page) goto oom; - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg, - false)) + if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg)) goto oom_free_page; /* @@ -3386,14 +3384,14 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); put_page(page); return handle_userfault(vmf, VM_UFFD_MISSING); } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); @@ -3404,7 +3402,7 @@ unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; release: - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); put_page(page); goto unlock; oom_free_page: @@ -3655,7 +3653,7 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); @@ -3864,8 +3862,8 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) if (!vmf->cow_page) return VM_FAULT_OOM; - if (mem_cgroup_try_charge_delay(vmf->cow_page, vma->vm_mm, GFP_KERNEL, - &vmf->memcg, false)) { + if (mem_cgroup_try_charge_delay(vmf->cow_page, vma->vm_mm, + GFP_KERNEL, &vmf->memcg)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } @@ -3886,7 +3884,7 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) goto uncharge_out; return ret; uncharge_out: - mem_cgroup_cancel_charge(vmf->cow_page, vmf->memcg, false); + mem_cgroup_cancel_charge(vmf->cow_page, vmf->memcg); put_page(vmf->cow_page); return ret; } diff --git a/mm/migrate.c b/mm/migrate.c index 846af96b84a5..93c732213d12 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2780,7 +2780,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, if (unlikely(anon_vma_prepare(vma))) goto abort; - if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg, false)) + if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg)) goto abort; /* @@ -2826,7 +2826,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, inc_mm_counter(mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, addr, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); if (!is_zone_device_page(page)) lru_cache_add_active_or_unevictable(page, vma); get_page(page); @@ -2848,7 +2848,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, unlock_abort: pte_unmap_unlock(ptep, ptl); - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); abort: *src &= ~MIGRATE_PFN_MIGRATE; } diff --git a/mm/shmem.c b/mm/shmem.c index bd8840082c94..d505b6cce4ab 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1664,8 +1664,7 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, goto failed; } - error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg, - false); + error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, swp_to_radix_entry(swap), gfp); @@ -1680,14 +1679,14 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, * the rest. */ if (error) { - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); delete_from_swap_cache(page); } } if (error) goto failed; - mem_cgroup_commit_charge(page, memcg, true, false); + mem_cgroup_commit_charge(page, memcg, true); spin_lock_irq(&info->lock); info->swapped--; @@ -1859,8 +1858,7 @@ alloc_nohuge: if (sgp == SGP_WRITE) __SetPageReferenced(page); - error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg, - PageTransHuge(page)); + error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg); if (error) { if (PageTransHuge(page)) { count_vm_event(THP_FILE_FALLBACK); @@ -1871,12 +1869,10 @@ alloc_nohuge: error = shmem_add_to_page_cache(page, mapping, hindex, NULL, gfp & GFP_RECLAIM_MASK); if (error) { - mem_cgroup_cancel_charge(page, memcg, - PageTransHuge(page)); + mem_cgroup_cancel_charge(page, memcg); goto unacct; } - mem_cgroup_commit_charge(page, memcg, false, - PageTransHuge(page)); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_anon(page); spin_lock_irq(&info->lock); @@ -2364,7 +2360,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (unlikely(offset >= max_off)) goto out_release; - ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg, false); + ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg); if (ret) goto out_release; @@ -2373,7 +2369,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (ret) goto out_release_uncharge; - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); _dst_pte = mk_pte(page, dst_vma->vm_page_prot); if (dst_vma->vm_flags & VM_WRITE) @@ -2424,7 +2420,7 @@ out_release_uncharge_unlock: ClearPageDirty(page); delete_from_page_cache(page); out_release_uncharge: - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); out_release: unlock_page(page); put_page(page); diff --git a/mm/swapfile.c b/mm/swapfile.c index 63ac67208453..40a80617cb03 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1902,15 +1902,14 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, if (unlikely(!page)) return -ENOMEM; - if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, - &memcg, false)) { + if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg)) { ret = -ENOMEM; goto out_nolock; } pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) { - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); ret = 0; goto out; } @@ -1922,10 +1921,10 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, pte_mkold(mk_pte(page, vma->vm_page_prot))); if (page == swapcache) { page_add_anon_rmap(page, vma, addr, false); - mem_cgroup_commit_charge(page, memcg, true, false); + mem_cgroup_commit_charge(page, memcg, true); } else { /* ksm created a completely new copy */ page_add_new_anon_rmap(page, vma, addr, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, vma); } swap_free(entry); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 512576e171ce..bb57d0a3fca7 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -97,7 +97,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, __SetPageUptodate(page); ret = -ENOMEM; - if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg, false)) + if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg)) goto out_release; _dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot)); @@ -124,7 +124,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, inc_mm_counter(dst_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, dst_vma, dst_addr, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, dst_vma); set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); @@ -138,7 +138,7 @@ out: return ret; out_release_uncharge_unlock: pte_unmap_unlock(dst_pte, ptl); - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); out_release: put_page(page); goto out; -- cgit v1.2.3 From 3fea5a499d57dec46043fcdb08e38eac1767bb0d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:41 -0700 Subject: mm: memcontrol: convert page cache to a new mem_cgroup_charge() API The try/commit/cancel protocol that memcg uses dates back to when pages used to be uncharged upon removal from the page cache, and thus couldn't be committed before the insertion had succeeded. Nowadays, pages are uncharged when they are physically freed; it doesn't matter whether the insertion was successful or not. For the page cache, the transaction dance has become unnecessary. Introduce a mem_cgroup_charge() function that simply charges a newly allocated page to a cgroup and sets up page->mem_cgroup in one single step. If the insertion fails, the caller doesn't have to do anything but free/put the page. Then switch the page cache over to this new API. Subsequent patches will also convert anon pages, but it needs a bit more prep work. Right now, memcg depends on page->mapping being already set up at the time of charging, so that it can maintain its own MEMCG_CACHE and MEMCG_RSS counters. For anon, page->mapping is set under the same pte lock under which the page is publishd, so a single charge point that can block doesn't work there just yet. The following prep patches will replace the private memcg counters with the generic vmstat counters, thus removing the page->mapping dependency, then complete the transition to the new single-point charge API and delete the old transactional scheme. v2: leave shmem swapcache when charging fails to avoid double IO (Joonsoo) v3: rebase on preceeding shmem simplification patch Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Alex Shi Cc: Hugh Dickins Cc: Joonsoo Kim Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-6-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 +++++++ mm/filemap.c | 24 +++++++-------- mm/memcontrol.c | 29 ++++++++++++++++-- mm/shmem.c | 73 +++++++++++++++++++--------------------------- 4 files changed, 77 insertions(+), 59 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index fc400002c7be..898925bdd676 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -365,6 +365,10 @@ int mem_cgroup_try_charge_delay(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); + +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, + bool lrucare); + void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -872,6 +876,12 @@ static inline void mem_cgroup_cancel_charge(struct page *page, { } +static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask, bool lrucare) +{ + return 0; +} + static inline void mem_cgroup_uncharge(struct page *page) { } diff --git a/mm/filemap.c b/mm/filemap.c index f268cfffbc6e..38e6a37336a6 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -832,7 +832,6 @@ static int __add_to_page_cache_locked(struct page *page, { XA_STATE(xas, &mapping->i_pages, offset); int huge = PageHuge(page); - struct mem_cgroup *memcg; int error; void *old; @@ -840,17 +839,16 @@ static int __add_to_page_cache_locked(struct page *page, VM_BUG_ON_PAGE(PageSwapBacked(page), page); mapping_set_update(&xas, mapping); - if (!huge) { - error = mem_cgroup_try_charge(page, current->mm, - gfp_mask, &memcg); - if (error) - return error; - } - get_page(page); page->mapping = mapping; page->index = offset; + if (!huge) { + error = mem_cgroup_charge(page, current->mm, gfp_mask, false); + if (error) + goto error; + } + do { xas_lock_irq(&xas); old = xas_load(&xas); @@ -874,20 +872,18 @@ unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp_mask & GFP_RECLAIM_MASK)); - if (xas_error(&xas)) + if (xas_error(&xas)) { + error = xas_error(&xas); goto error; + } - if (!huge) - mem_cgroup_commit_charge(page, memcg, false); trace_mm_filemap_add_to_page_cache(page); return 0; error: page->mapping = NULL; /* Leave page->index set: truncation relies upon it */ - if (!huge) - mem_cgroup_cancel_charge(page, memcg); put_page(page); - return xas_error(&xas); + return error; } ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bc0f55d0cc08..c414b7f85e48 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6637,6 +6637,33 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) cancel_charge(memcg, nr_pages); } +/** + * mem_cgroup_charge - charge a newly allocated page to a cgroup + * @page: page to charge + * @mm: mm context of the victim + * @gfp_mask: reclaim mode + * @lrucare: page might be on the LRU already + * + * Try to charge @page to the memcg that @mm belongs to, reclaiming + * pages according to @gfp_mask if necessary. + * + * Returns 0 on success. Otherwise, an error code is returned. + */ +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, + bool lrucare) +{ + struct mem_cgroup *memcg; + int ret; + + VM_BUG_ON_PAGE(!page->mapping, page); + + ret = mem_cgroup_try_charge(page, mm, gfp_mask, &memcg); + if (ret) + return ret; + mem_cgroup_commit_charge(page, memcg, lrucare); + return 0; +} + struct uncharge_gather { struct mem_cgroup *memcg; unsigned long pgpgout; @@ -6684,8 +6711,6 @@ static void uncharge_batch(const struct uncharge_gather *ug) static void uncharge_page(struct page *page, struct uncharge_gather *ug) { VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON_PAGE(page_count(page) && !is_zone_device_page(page) && - !PageHWPoison(page) , page); if (!page->mem_cgroup) return; diff --git a/mm/shmem.c b/mm/shmem.c index 729bbb3513cd..0d9615723152 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -605,11 +605,13 @@ static inline bool is_huge_enabled(struct shmem_sb_info *sbinfo) */ static int shmem_add_to_page_cache(struct page *page, struct address_space *mapping, - pgoff_t index, void *expected, gfp_t gfp) + pgoff_t index, void *expected, gfp_t gfp, + struct mm_struct *charge_mm) { XA_STATE_ORDER(xas, &mapping->i_pages, index, compound_order(page)); unsigned long i = 0; unsigned long nr = compound_nr(page); + int error; VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(index != round_down(index, nr), page); @@ -621,6 +623,16 @@ static int shmem_add_to_page_cache(struct page *page, page->mapping = mapping; page->index = index; + error = mem_cgroup_charge(page, charge_mm, gfp, PageSwapCache(page)); + if (error) { + if (!PageSwapCache(page) && PageTransHuge(page)) { + count_vm_event(THP_FILE_FALLBACK); + count_vm_event(THP_FILE_FALLBACK_CHARGE); + } + goto error; + } + cgroup_throttle_swaprate(page, gfp); + do { void *entry; xas_lock_irq(&xas); @@ -648,12 +660,15 @@ unlock: } while (xas_nomem(&xas, gfp)); if (xas_error(&xas)) { - page->mapping = NULL; - page_ref_sub(page, nr); - return xas_error(&xas); + error = xas_error(&xas); + goto error; } return 0; +error: + page->mapping = NULL; + page_ref_sub(page, nr); + return error; } /* @@ -1619,7 +1634,6 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); struct mm_struct *charge_mm = vma ? vma->vm_mm : current->mm; - struct mem_cgroup *memcg; struct page *page; swp_entry_t swap; int error; @@ -1664,18 +1678,11 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, goto failed; } - error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg); - if (error) - goto failed; - error = shmem_add_to_page_cache(page, mapping, index, - swp_to_radix_entry(swap), gfp); - if (error) { - mem_cgroup_cancel_charge(page, memcg); + swp_to_radix_entry(swap), gfp, + charge_mm); + if (error) goto failed; - } - - mem_cgroup_commit_charge(page, memcg, true); spin_lock_irq(&info->lock); info->swapped--; @@ -1722,7 +1729,6 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo; struct mm_struct *charge_mm; - struct mem_cgroup *memcg; struct page *page; enum sgp_type sgp_huge = sgp; pgoff_t hindex = index; @@ -1847,21 +1853,11 @@ alloc_nohuge: if (sgp == SGP_WRITE) __SetPageReferenced(page); - error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg); - if (error) { - if (PageTransHuge(page)) { - count_vm_event(THP_FILE_FALLBACK); - count_vm_event(THP_FILE_FALLBACK_CHARGE); - } - goto unacct; - } error = shmem_add_to_page_cache(page, mapping, hindex, - NULL, gfp & GFP_RECLAIM_MASK); - if (error) { - mem_cgroup_cancel_charge(page, memcg); + NULL, gfp & GFP_RECLAIM_MASK, + charge_mm); + if (error) goto unacct; - } - mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_anon(page); spin_lock_irq(&info->lock); @@ -2299,7 +2295,6 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, struct address_space *mapping = inode->i_mapping; gfp_t gfp = mapping_gfp_mask(mapping); pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); - struct mem_cgroup *memcg; spinlock_t *ptl; void *page_kaddr; struct page *page; @@ -2349,16 +2344,10 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (unlikely(offset >= max_off)) goto out_release; - ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg); - if (ret) - goto out_release; - ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL, - gfp & GFP_RECLAIM_MASK); + gfp & GFP_RECLAIM_MASK, dst_mm); if (ret) - goto out_release_uncharge; - - mem_cgroup_commit_charge(page, memcg, false); + goto out_release; _dst_pte = mk_pte(page, dst_vma->vm_page_prot); if (dst_vma->vm_flags & VM_WRITE) @@ -2379,11 +2368,11 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, ret = -EFAULT; max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(offset >= max_off)) - goto out_release_uncharge_unlock; + goto out_release_unlock; ret = -EEXIST; if (!pte_none(*dst_pte)) - goto out_release_uncharge_unlock; + goto out_release_unlock; lru_cache_add_anon(page); @@ -2404,12 +2393,10 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, ret = 0; out: return ret; -out_release_uncharge_unlock: +out_release_unlock: pte_unmap_unlock(dst_pte, ptl); ClearPageDirty(page); delete_from_page_cache(page); -out_release_uncharge: - mem_cgroup_cancel_charge(page, memcg); out_release: unlock_page(page); put_page(page); -- cgit v1.2.3 From 9da7b5216869f80e91f78403a57c72b42357758c Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:51 -0700 Subject: mm: memcontrol: prepare cgroup vmstat infrastructure for native anon counters Anonymous compound pages can be mapped by ptes, which means that if we want to track NR_MAPPED_ANON, NR_ANON_THPS on a per-cgroup basis, we have to be prepared to see tail pages in our accounting functions. Make mod_lruvec_page_state() and lock_page_memcg() deal with tail pages correctly, namely by redirecting to the head page which has the page->mem_cgroup set up. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-9-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 +++-- mm/memcontrol.c | 9 ++++++--- 2 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 898925bdd676..8f00dd755818 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -709,16 +709,17 @@ static inline void mod_lruvec_state(struct lruvec *lruvec, static inline void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { + struct page *head = compound_head(page); /* rmap on tail pages */ pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; /* Untracked pages have no memcg, no lruvec. Update only the node */ - if (!page->mem_cgroup) { + if (!head->mem_cgroup) { __mod_node_page_state(pgdat, idx, val); return; } - lruvec = mem_cgroup_lruvec(page->mem_cgroup, pgdat); + lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat); __mod_lruvec_state(lruvec, idx, val); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f82ae3723760..a875a97067a3 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1981,6 +1981,7 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) */ struct mem_cgroup *lock_page_memcg(struct page *page) { + struct page *head = compound_head(page); /* rmap on tail pages */ struct mem_cgroup *memcg; unsigned long flags; @@ -2000,7 +2001,7 @@ struct mem_cgroup *lock_page_memcg(struct page *page) if (mem_cgroup_disabled()) return NULL; again: - memcg = page->mem_cgroup; + memcg = head->mem_cgroup; if (unlikely(!memcg)) return NULL; @@ -2008,7 +2009,7 @@ again: return memcg; spin_lock_irqsave(&memcg->move_lock, flags); - if (memcg != page->mem_cgroup) { + if (memcg != head->mem_cgroup) { spin_unlock_irqrestore(&memcg->move_lock, flags); goto again; } @@ -2051,7 +2052,9 @@ void __unlock_page_memcg(struct mem_cgroup *memcg) */ void unlock_page_memcg(struct page *page) { - __unlock_page_memcg(page->mem_cgroup); + struct page *head = compound_head(page); + + __unlock_page_memcg(head->mem_cgroup); } EXPORT_SYMBOL(unlock_page_memcg); -- cgit v1.2.3 From 0d1c20722ab333ac0ac03ae2188922c1021d3abc Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:54 -0700 Subject: mm: memcontrol: switch to native NR_FILE_PAGES and NR_SHMEM counters Memcg maintains private MEMCG_CACHE and NR_SHMEM counters. This divergence from the generic VM accounting means unnecessary code overhead, and creates a dependency for memcg that page->mapping is set up at the time of charging, so that page types can be told apart. Convert the generic accounting sites to mod_lruvec_page_state and friends to maintain the per-cgroup vmstat counters of NR_FILE_PAGES and NR_SHMEM. The page is already locked in these places, so page->mem_cgroup is stable; we only need minimal tweaks of two mem_cgroup_migrate() calls to ensure it's set up in time. Then replace MEMCG_CACHE with NR_FILE_PAGES and delete the private NR_SHMEM accounting sites. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-10-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- mm/filemap.c | 17 +++++++++-------- mm/khugepaged.c | 16 +++++++++++----- mm/memcontrol.c | 28 +++++++++++----------------- mm/migrate.c | 15 +++++++++++---- mm/shmem.c | 14 +++++++------- 6 files changed, 50 insertions(+), 43 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 8f00dd755818..f6ea68ceed2c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -29,8 +29,7 @@ struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { - MEMCG_CACHE = NR_VM_NODE_STAT_ITEMS, - MEMCG_RSS, + MEMCG_RSS = NR_VM_NODE_STAT_ITEMS, MEMCG_RSS_HUGE, MEMCG_SWAP, MEMCG_SOCK, diff --git a/mm/filemap.c b/mm/filemap.c index 38e6a37336a6..a6565890cdf0 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -199,9 +199,9 @@ static void unaccount_page_cache_page(struct address_space *mapping, nr = hpage_nr_pages(page); - __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr); + __mod_lruvec_page_state(page, NR_FILE_PAGES, -nr); if (PageSwapBacked(page)) { - __mod_node_page_state(page_pgdat(page), NR_SHMEM, -nr); + __mod_lruvec_page_state(page, NR_SHMEM, -nr); if (PageTransHuge(page)) __dec_node_page_state(page, NR_SHMEM_THPS); } else if (PageTransHuge(page)) { @@ -802,21 +802,22 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) new->mapping = mapping; new->index = offset; + mem_cgroup_migrate(old, new); + xas_lock_irqsave(&xas, flags); xas_store(&xas, new); old->mapping = NULL; /* hugetlb pages do not participate in page cache accounting. */ if (!PageHuge(old)) - __dec_node_page_state(old, NR_FILE_PAGES); + __dec_lruvec_page_state(old, NR_FILE_PAGES); if (!PageHuge(new)) - __inc_node_page_state(new, NR_FILE_PAGES); + __inc_lruvec_page_state(new, NR_FILE_PAGES); if (PageSwapBacked(old)) - __dec_node_page_state(old, NR_SHMEM); + __dec_lruvec_page_state(old, NR_SHMEM); if (PageSwapBacked(new)) - __inc_node_page_state(new, NR_SHMEM); + __inc_lruvec_page_state(new, NR_SHMEM); xas_unlock_irqrestore(&xas, flags); - mem_cgroup_migrate(old, new); if (freepage) freepage(old); put_page(old); @@ -867,7 +868,7 @@ static int __add_to_page_cache_locked(struct page *page, /* hugetlb pages do not participate in page cache accounting */ if (!huge) - __inc_node_page_state(page, NR_FILE_PAGES); + __inc_lruvec_page_state(page, NR_FILE_PAGES); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp_mask & GFP_RECLAIM_MASK)); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 0a29b51494fd..ddbdc1e3a694 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1844,12 +1844,18 @@ out_unlock: } if (nr_none) { - struct zone *zone = page_zone(new_page); - - __mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none); + struct lruvec *lruvec; + /* + * XXX: We have started try_charge and pinned the + * memcg, but the page isn't committed yet so we + * cannot use mod_lruvec_page_state(). This hackery + * will be cleaned up when remove the page->mapping + * dependency from memcg and fully charge above. + */ + lruvec = mem_cgroup_lruvec(memcg, page_pgdat(new_page)); + __mod_lruvec_state(lruvec, NR_FILE_PAGES, nr_none); if (is_shmem) - __mod_node_page_state(zone->zone_pgdat, - NR_SHMEM, nr_none); + __mod_lruvec_state(lruvec, NR_SHMEM, nr_none); } xa_locked: diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a875a97067a3..ab3497ba0e35 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -842,11 +842,6 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, */ if (PageAnon(page)) __mod_memcg_state(memcg, MEMCG_RSS, nr_pages); - else { - __mod_memcg_state(memcg, MEMCG_CACHE, nr_pages); - if (PageSwapBacked(page)) - __mod_memcg_state(memcg, NR_SHMEM, nr_pages); - } if (abs(nr_pages) > 1) { VM_BUG_ON_PAGE(!PageTransHuge(page), page); @@ -1392,7 +1387,7 @@ static char *memory_stat_format(struct mem_cgroup *memcg) (u64)memcg_page_state(memcg, MEMCG_RSS) * PAGE_SIZE); seq_buf_printf(&s, "file %llu\n", - (u64)memcg_page_state(memcg, MEMCG_CACHE) * + (u64)memcg_page_state(memcg, NR_FILE_PAGES) * PAGE_SIZE); seq_buf_printf(&s, "kernel_stack %llu\n", (u64)memcg_page_state(memcg, MEMCG_KERNEL_STACK_KB) * @@ -3357,7 +3352,7 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) unsigned long val; if (mem_cgroup_is_root(memcg)) { - val = memcg_page_state(memcg, MEMCG_CACHE) + + val = memcg_page_state(memcg, NR_FILE_PAGES) + memcg_page_state(memcg, MEMCG_RSS); if (swap) val += memcg_page_state(memcg, MEMCG_SWAP); @@ -3828,7 +3823,7 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v) #endif /* CONFIG_NUMA */ static const unsigned int memcg1_stats[] = { - MEMCG_CACHE, + NR_FILE_PAGES, MEMCG_RSS, MEMCG_RSS_HUGE, NR_SHMEM, @@ -5461,6 +5456,14 @@ static int mem_cgroup_move_account(struct page *page, lock_page_memcg(page); if (!PageAnon(page)) { + __mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages); + __mod_lruvec_state(to_vec, NR_FILE_PAGES, nr_pages); + + if (PageSwapBacked(page)) { + __mod_lruvec_state(from_vec, NR_SHMEM, -nr_pages); + __mod_lruvec_state(to_vec, NR_SHMEM, nr_pages); + } + if (page_mapped(page)) { __mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages); __mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages); @@ -6673,10 +6676,8 @@ struct uncharge_gather { unsigned long nr_pages; unsigned long pgpgout; unsigned long nr_anon; - unsigned long nr_file; unsigned long nr_kmem; unsigned long nr_huge; - unsigned long nr_shmem; struct page *dummy_page; }; @@ -6700,9 +6701,7 @@ static void uncharge_batch(const struct uncharge_gather *ug) local_irq_save(flags); __mod_memcg_state(ug->memcg, MEMCG_RSS, -ug->nr_anon); - __mod_memcg_state(ug->memcg, MEMCG_CACHE, -ug->nr_file); __mod_memcg_state(ug->memcg, MEMCG_RSS_HUGE, -ug->nr_huge); - __mod_memcg_state(ug->memcg, NR_SHMEM, -ug->nr_shmem); __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages); memcg_check_events(ug->memcg, ug->dummy_page); @@ -6743,11 +6742,6 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) ug->nr_huge += nr_pages; if (PageAnon(page)) ug->nr_anon += nr_pages; - else { - ug->nr_file += nr_pages; - if (PageSwapBacked(page)) - ug->nr_shmem += nr_pages; - } ug->pgpgout++; } else { ug->nr_kmem += nr_pages; diff --git a/mm/migrate.c b/mm/migrate.c index 93c732213d12..0d1f796df75f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -490,11 +490,18 @@ int migrate_page_move_mapping(struct address_space *mapping, * are mapped to swap space. */ if (newzone != oldzone) { - __dec_node_state(oldzone->zone_pgdat, NR_FILE_PAGES); - __inc_node_state(newzone->zone_pgdat, NR_FILE_PAGES); + struct lruvec *old_lruvec, *new_lruvec; + struct mem_cgroup *memcg; + + memcg = page_memcg(page); + old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat); + new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat); + + __dec_lruvec_state(old_lruvec, NR_FILE_PAGES); + __inc_lruvec_state(new_lruvec, NR_FILE_PAGES); if (PageSwapBacked(page) && !PageSwapCache(page)) { - __dec_node_state(oldzone->zone_pgdat, NR_SHMEM); - __inc_node_state(newzone->zone_pgdat, NR_SHMEM); + __dec_lruvec_state(old_lruvec, NR_SHMEM); + __inc_lruvec_state(new_lruvec, NR_SHMEM); } if (dirty && mapping_cap_account_dirty(mapping)) { __dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY); diff --git a/mm/shmem.c b/mm/shmem.c index 0d9615723152..71842fd4a9d0 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -653,8 +653,8 @@ next: __inc_node_page_state(page, NR_SHMEM_THPS); } mapping->nrpages += nr; - __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr); - __mod_node_page_state(page_pgdat(page), NR_SHMEM, nr); + __mod_lruvec_page_state(page, NR_FILE_PAGES, nr); + __mod_lruvec_page_state(page, NR_SHMEM, nr); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); @@ -685,8 +685,8 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap) error = shmem_replace_entry(mapping, page->index, page, radswap); page->mapping = NULL; mapping->nrpages--; - __dec_node_page_state(page, NR_FILE_PAGES); - __dec_node_page_state(page, NR_SHMEM); + __dec_lruvec_page_state(page, NR_FILE_PAGES); + __dec_lruvec_page_state(page, NR_SHMEM); xa_unlock_irq(&mapping->i_pages); put_page(page); BUG_ON(error); @@ -1593,8 +1593,9 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, xa_lock_irq(&swap_mapping->i_pages); error = shmem_replace_entry(swap_mapping, swap_index, oldpage, newpage); if (!error) { - __inc_node_page_state(newpage, NR_FILE_PAGES); - __dec_node_page_state(oldpage, NR_FILE_PAGES); + mem_cgroup_migrate(oldpage, newpage); + __inc_lruvec_page_state(newpage, NR_FILE_PAGES); + __dec_lruvec_page_state(oldpage, NR_FILE_PAGES); } xa_unlock_irq(&swap_mapping->i_pages); @@ -1606,7 +1607,6 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, */ oldpage = newpage; } else { - mem_cgroup_migrate(oldpage, newpage); lru_cache_add_anon(newpage); *pagep = newpage; } -- cgit v1.2.3 From be5d0a74c62d8da43f9526a5b08cdd18e2bbc37a Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:57 -0700 Subject: mm: memcontrol: switch to native NR_ANON_MAPPED counter Memcg maintains a private MEMCG_RSS counter. This divergence from the generic VM accounting means unnecessary code overhead, and creates a dependency for memcg that page->mapping is set up at the time of charging, so that page types can be told apart. Convert the generic accounting sites to mod_lruvec_page_state and friends to maintain the per-cgroup vmstat counter of NR_ANON_MAPPED. We use lock_page_memcg() to stabilize page->mem_cgroup during rmap changes, the same way we do for NR_FILE_MAPPED. With the previous patch removing MEMCG_CACHE and the private NR_SHMEM counter, this patch finally eliminates the need to have page->mapping set up at charge time. However, we need to have page->mem_cgroup set up by the time rmap runs and does the accounting, so switch the commit and the rmap callbacks around. v2: fix temporary accounting bug by switching rmap<->commit (Joonsoo) Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Alex Shi Cc: Hugh Dickins Cc: Joonsoo Kim Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-11-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- kernel/events/uprobes.c | 2 +- mm/huge_memory.c | 2 +- mm/khugepaged.c | 2 +- mm/memcontrol.c | 27 +++++++++----------------- mm/memory.c | 10 +++++----- mm/migrate.c | 2 +- mm/rmap.c | 47 ++++++++++++++++++++++++++++------------------ mm/swapfile.c | 4 ++-- mm/userfaultfd.c | 2 +- 10 files changed, 51 insertions(+), 50 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f6ea68ceed2c..acacc3018957 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -29,8 +29,7 @@ struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { - MEMCG_RSS = NR_VM_NODE_STAT_ITEMS, - MEMCG_RSS_HUGE, + MEMCG_RSS_HUGE = NR_VM_NODE_STAT_ITEMS, MEMCG_SWAP, MEMCG_SOCK, /* XXX: why are these zone and not node counters? */ diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 40e7488ce467..89ef81b65bcb 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -188,8 +188,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, if (new_page) { get_page(new_page); - page_add_new_anon_rmap(new_page, vma, addr, false); mem_cgroup_commit_charge(new_page, memcg, false); + page_add_new_anon_rmap(new_page, vma, addr, false); lru_cache_add_active_or_unevictable(new_page, vma); } else /* no new page, just dec_mm_counter for old_page */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 672e34932b53..2caf2494db66 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -640,8 +640,8 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - page_add_new_anon_rmap(page, vma, haddr, true); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, haddr, true); lru_cache_add_active_or_unevictable(page, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index ddbdc1e3a694..34eff4dfae80 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1175,8 +1175,8 @@ static void collapse_huge_page(struct mm_struct *mm, spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); - page_add_new_anon_rmap(new_page, vma, address, true); mem_cgroup_commit_charge(new_page, memcg, false); + page_add_new_anon_rmap(new_page, vma, address, true); count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1); lru_cache_add_active_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ab3497ba0e35..b80125303c02 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -836,13 +836,6 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, struct page *page, 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 (PageAnon(page)) - __mod_memcg_state(memcg, MEMCG_RSS, nr_pages); - if (abs(nr_pages) > 1) { VM_BUG_ON_PAGE(!PageTransHuge(page), page); __mod_memcg_state(memcg, MEMCG_RSS_HUGE, nr_pages); @@ -1384,7 +1377,7 @@ static char *memory_stat_format(struct mem_cgroup *memcg) */ seq_buf_printf(&s, "anon %llu\n", - (u64)memcg_page_state(memcg, MEMCG_RSS) * + (u64)memcg_page_state(memcg, NR_ANON_MAPPED) * PAGE_SIZE); seq_buf_printf(&s, "file %llu\n", (u64)memcg_page_state(memcg, NR_FILE_PAGES) * @@ -3353,7 +3346,7 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) if (mem_cgroup_is_root(memcg)) { val = memcg_page_state(memcg, NR_FILE_PAGES) + - memcg_page_state(memcg, MEMCG_RSS); + memcg_page_state(memcg, NR_ANON_MAPPED); if (swap) val += memcg_page_state(memcg, MEMCG_SWAP); } else { @@ -3824,7 +3817,7 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v) static const unsigned int memcg1_stats[] = { NR_FILE_PAGES, - MEMCG_RSS, + NR_ANON_MAPPED, MEMCG_RSS_HUGE, NR_SHMEM, NR_FILE_MAPPED, @@ -5455,7 +5448,12 @@ static int mem_cgroup_move_account(struct page *page, lock_page_memcg(page); - if (!PageAnon(page)) { + if (PageAnon(page)) { + if (page_mapped(page)) { + __mod_lruvec_state(from_vec, NR_ANON_MAPPED, -nr_pages); + __mod_lruvec_state(to_vec, NR_ANON_MAPPED, nr_pages); + } + } else { __mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages); __mod_lruvec_state(to_vec, NR_FILE_PAGES, nr_pages); @@ -6589,7 +6587,6 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, { unsigned int nr_pages = hpage_nr_pages(page); - VM_BUG_ON_PAGE(!page->mapping, page); VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); if (mem_cgroup_disabled()) @@ -6662,8 +6659,6 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup *memcg; int ret; - VM_BUG_ON_PAGE(!page->mapping, page); - ret = mem_cgroup_try_charge(page, mm, gfp_mask, &memcg); if (ret) return ret; @@ -6675,7 +6670,6 @@ struct uncharge_gather { struct mem_cgroup *memcg; unsigned long nr_pages; unsigned long pgpgout; - unsigned long nr_anon; unsigned long nr_kmem; unsigned long nr_huge; struct page *dummy_page; @@ -6700,7 +6694,6 @@ static void uncharge_batch(const struct uncharge_gather *ug) } local_irq_save(flags); - __mod_memcg_state(ug->memcg, MEMCG_RSS, -ug->nr_anon); __mod_memcg_state(ug->memcg, MEMCG_RSS_HUGE, -ug->nr_huge); __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages); @@ -6740,8 +6733,6 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) if (!PageKmemcg(page)) { if (PageTransHuge(page)) ug->nr_huge += nr_pages; - if (PageAnon(page)) - ug->nr_anon += nr_pages; ug->pgpgout++; } else { ug->nr_kmem += nr_pages; diff --git a/mm/memory.c b/mm/memory.c index 6b8c5900e9a4..543e41b1d57a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2710,8 +2710,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) * thread doing COW. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); - page_add_new_anon_rmap(new_page, vma, vmf->address, false); mem_cgroup_commit_charge(new_page, memcg, false); + page_add_new_anon_rmap(new_page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary @@ -3243,12 +3243,12 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { - page_add_new_anon_rmap(page, vma, vmf->address, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(page, vma); } else { - do_page_add_anon_rmap(page, vma, vmf->address, exclusive); mem_cgroup_commit_charge(page, memcg, true); + do_page_add_anon_rmap(page, vma, vmf->address, exclusive); activate_page(page); } @@ -3390,8 +3390,8 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, vmf->address, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); @@ -3652,8 +3652,8 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, vmf->address, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); diff --git a/mm/migrate.c b/mm/migrate.c index 0d1f796df75f..e72ed681634f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2832,8 +2832,8 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, goto unlock_abort; inc_mm_counter(mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, addr, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, addr, false); if (!is_zone_device_page(page)) lru_cache_add_active_or_unevictable(page, vma); get_page(page); diff --git a/mm/rmap.c b/mm/rmap.c index f79a206b271a..150513d31efa 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1114,6 +1114,11 @@ void do_page_add_anon_rmap(struct page *page, bool compound = flags & RMAP_COMPOUND; bool first; + if (unlikely(PageKsm(page))) + lock_page_memcg(page); + else + VM_BUG_ON_PAGE(!PageLocked(page), page); + if (compound) { atomic_t *mapcount; VM_BUG_ON_PAGE(!PageLocked(page), page); @@ -1134,12 +1139,13 @@ void do_page_add_anon_rmap(struct page *page, */ if (compound) __inc_node_page_state(page, NR_ANON_THPS); - __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, nr); + __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); } - if (unlikely(PageKsm(page))) - return; - VM_BUG_ON_PAGE(!PageLocked(page), page); + if (unlikely(PageKsm(page))) { + unlock_page_memcg(page); + return; + } /* address might be in next vma when migration races vma_adjust */ if (first) @@ -1181,7 +1187,7 @@ void page_add_new_anon_rmap(struct page *page, /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); } - __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, nr); + __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); __page_set_anon_rmap(page, vma, address, 1); } @@ -1230,13 +1236,12 @@ static void page_remove_file_rmap(struct page *page, bool compound) int i, nr = 1; VM_BUG_ON_PAGE(compound && !PageHead(page), page); - lock_page_memcg(page); /* Hugepages are not counted in NR_FILE_MAPPED for now. */ if (unlikely(PageHuge(page))) { /* hugetlb pages are always mapped with pmds */ atomic_dec(compound_mapcount_ptr(page)); - goto out; + return; } /* page still mapped by someone else? */ @@ -1246,14 +1251,14 @@ static void page_remove_file_rmap(struct page *page, bool compound) nr++; } if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) - goto out; + return; if (PageSwapBacked(page)) __dec_node_page_state(page, NR_SHMEM_PMDMAPPED); else __dec_node_page_state(page, NR_FILE_PMDMAPPED); } else { if (!atomic_add_negative(-1, &page->_mapcount)) - goto out; + return; } /* @@ -1265,8 +1270,6 @@ static void page_remove_file_rmap(struct page *page, bool compound) if (unlikely(PageMlocked(page))) clear_page_mlock(page); -out: - unlock_page_memcg(page); } static void page_remove_anon_compound_rmap(struct page *page) @@ -1310,7 +1313,7 @@ static void page_remove_anon_compound_rmap(struct page *page) clear_page_mlock(page); if (nr) - __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, -nr); + __mod_lruvec_page_state(page, NR_ANON_MAPPED, -nr); } /** @@ -1322,22 +1325,28 @@ static void page_remove_anon_compound_rmap(struct page *page) */ void page_remove_rmap(struct page *page, bool compound) { - if (!PageAnon(page)) - return page_remove_file_rmap(page, compound); + lock_page_memcg(page); - if (compound) - return page_remove_anon_compound_rmap(page); + if (!PageAnon(page)) { + page_remove_file_rmap(page, compound); + goto out; + } + + if (compound) { + page_remove_anon_compound_rmap(page); + goto out; + } /* page still mapped by someone else? */ if (!atomic_add_negative(-1, &page->_mapcount)) - return; + goto out; /* * We use the irq-unsafe __{inc|mod}_zone_page_stat because * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption disabled. */ - __dec_node_page_state(page, NR_ANON_MAPPED); + __dec_lruvec_page_state(page, NR_ANON_MAPPED); if (unlikely(PageMlocked(page))) clear_page_mlock(page); @@ -1354,6 +1363,8 @@ void page_remove_rmap(struct page *page, bool compound) * Leaving it set also helps swapoff to reinstate ptes * faster for those pages still in swapcache. */ +out: + unlock_page_memcg(page); } /* diff --git a/mm/swapfile.c b/mm/swapfile.c index 1829fc4b3ca2..01f6538bad2d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1920,11 +1920,11 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, set_pte_at(vma->vm_mm, addr, pte, pte_mkold(mk_pte(page, vma->vm_page_prot))); if (page == swapcache) { - page_add_anon_rmap(page, vma, addr, false); mem_cgroup_commit_charge(page, memcg, true); + page_add_anon_rmap(page, vma, addr, false); } else { /* ksm created a completely new copy */ - page_add_new_anon_rmap(page, vma, addr, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, addr, false); lru_cache_add_active_or_unevictable(page, vma); } swap_free(entry); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index bb57d0a3fca7..3dea268d2850 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -123,8 +123,8 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, goto out_release_uncharge_unlock; inc_mm_counter(dst_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, dst_vma, dst_addr, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, dst_vma, dst_addr, false); lru_cache_add_active_or_unevictable(page, dst_vma); set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); -- cgit v1.2.3 From 468c398233da208521a0f84c2068012a66a7489d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:01 -0700 Subject: mm: memcontrol: switch to native NR_ANON_THPS counter With rmap memcg locking already in place for NR_ANON_MAPPED, it's just a small step to remove the MEMCG_RSS_HUGE wart and switch memcg to the native NR_ANON_THPS accounting sites. [hannes@cmpxchg.org: fixes] Link: http://lkml.kernel.org/r/20200512121750.GA397968@cmpxchg.org Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Tested-by: Naresh Kamboju Reviewed-by: Joonsoo Kim Acked-by: Randy Dunlap [build-tested] Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-12-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- mm/huge_memory.c | 4 +++- mm/memcontrol.c | 47 +++++++++++++++++++++++----------------------- mm/rmap.c | 6 +++--- 4 files changed, 31 insertions(+), 29 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index acacc3018957..63a31a6c3c69 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -29,8 +29,7 @@ struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { - MEMCG_RSS_HUGE = NR_VM_NODE_STAT_ITEMS, - MEMCG_SWAP, + MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, /* XXX: why are these zone and not node counters? */ MEMCG_KERNEL_STACK_KB, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2caf2494db66..1fe980dafe03 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2159,15 +2159,17 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, atomic_inc(&page[i]._mapcount); } + lock_page_memcg(page); if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { /* Last compound_mapcount is gone. */ - __dec_node_page_state(page, NR_ANON_THPS); + __dec_lruvec_page_state(page, NR_ANON_THPS); if (TestClearPageDoubleMap(page)) { /* No need in mapcount reference anymore */ for (i = 0; i < HPAGE_PMD_NR; i++) atomic_dec(&page[i]._mapcount); } } + unlock_page_memcg(page); smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b80125303c02..17587ea2745a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -836,11 +836,6 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, struct page *page, int nr_pages) { - if (abs(nr_pages) > 1) { - VM_BUG_ON_PAGE(!PageTransHuge(page), page); - __mod_memcg_state(memcg, MEMCG_RSS_HUGE, nr_pages); - } - /* pagein of a big page is an event. So, ignore page size */ if (nr_pages > 0) __count_memcg_events(memcg, PGPGIN, 1); @@ -1406,15 +1401,11 @@ static char *memory_stat_format(struct mem_cgroup *memcg) (u64)memcg_page_state(memcg, NR_WRITEBACK) * PAGE_SIZE); - /* - * TODO: We should eventually replace our own MEMCG_RSS_HUGE counter - * with the NR_ANON_THP vm counter, but right now it's a pain in the - * arse because it requires migrating the work out of rmap to a place - * where the page->mem_cgroup is set up and stable. - */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE seq_buf_printf(&s, "anon_thp %llu\n", - (u64)memcg_page_state(memcg, MEMCG_RSS_HUGE) * - PAGE_SIZE); + (u64)memcg_page_state(memcg, NR_ANON_THPS) * + HPAGE_PMD_SIZE); +#endif for (i = 0; i < NR_LRU_LISTS; i++) seq_buf_printf(&s, "%s %llu\n", lru_list_name(i), @@ -3061,8 +3052,6 @@ void mem_cgroup_split_huge_fixup(struct page *head) for (i = 1; i < HPAGE_PMD_NR; i++) head[i].mem_cgroup = head->mem_cgroup; - - __mod_memcg_state(head->mem_cgroup, MEMCG_RSS_HUGE, -HPAGE_PMD_NR); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -3818,7 +3807,9 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v) static const unsigned int memcg1_stats[] = { NR_FILE_PAGES, NR_ANON_MAPPED, - MEMCG_RSS_HUGE, +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + NR_ANON_THPS, +#endif NR_SHMEM, NR_FILE_MAPPED, NR_FILE_DIRTY, @@ -3829,7 +3820,9 @@ static const unsigned int memcg1_stats[] = { static const char *const memcg1_stat_names[] = { "cache", "rss", +#ifdef CONFIG_TRANSPARENT_HUGEPAGE "rss_huge", +#endif "shmem", "mapped_file", "dirty", @@ -3855,11 +3848,16 @@ static int memcg_stat_show(struct seq_file *m, void *v) BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats)); for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { + unsigned long nr; + if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) continue; - seq_printf(m, "%s %lu\n", memcg1_stat_names[i], - memcg_page_state_local(memcg, memcg1_stats[i]) * - PAGE_SIZE); + nr = memcg_page_state_local(memcg, memcg1_stats[i]); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (memcg1_stats[i] == NR_ANON_THPS) + nr *= HPAGE_PMD_NR; +#endif + seq_printf(m, "%s %lu\n", memcg1_stat_names[i], nr * PAGE_SIZE); } for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) @@ -5452,6 +5450,13 @@ static int mem_cgroup_move_account(struct page *page, if (page_mapped(page)) { __mod_lruvec_state(from_vec, NR_ANON_MAPPED, -nr_pages); __mod_lruvec_state(to_vec, NR_ANON_MAPPED, nr_pages); + if (PageTransHuge(page)) { + __mod_lruvec_state(from_vec, NR_ANON_THPS, + -nr_pages); + __mod_lruvec_state(to_vec, NR_ANON_THPS, + nr_pages); + } + } } else { __mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages); @@ -6671,7 +6676,6 @@ struct uncharge_gather { unsigned long nr_pages; unsigned long pgpgout; unsigned long nr_kmem; - unsigned long nr_huge; struct page *dummy_page; }; @@ -6694,7 +6698,6 @@ static void uncharge_batch(const struct uncharge_gather *ug) } local_irq_save(flags); - __mod_memcg_state(ug->memcg, MEMCG_RSS_HUGE, -ug->nr_huge); __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages); memcg_check_events(ug->memcg, ug->dummy_page); @@ -6731,8 +6734,6 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) ug->nr_pages += nr_pages; if (!PageKmemcg(page)) { - if (PageTransHuge(page)) - ug->nr_huge += nr_pages; ug->pgpgout++; } else { ug->nr_kmem += nr_pages; diff --git a/mm/rmap.c b/mm/rmap.c index 150513d31efa..ad4a0fdcc94c 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1138,7 +1138,7 @@ void do_page_add_anon_rmap(struct page *page, * disabled. */ if (compound) - __inc_node_page_state(page, NR_ANON_THPS); + __inc_lruvec_page_state(page, NR_ANON_THPS); __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); } @@ -1180,7 +1180,7 @@ void page_add_new_anon_rmap(struct page *page, if (hpage_pincount_available(page)) atomic_set(compound_pincount_ptr(page), 0); - __inc_node_page_state(page, NR_ANON_THPS); + __inc_lruvec_page_state(page, NR_ANON_THPS); } else { /* Anon THP always mapped first with PMD */ VM_BUG_ON_PAGE(PageTransCompound(page), page); @@ -1286,7 +1286,7 @@ static void page_remove_anon_compound_rmap(struct page *page) if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return; - __dec_node_page_state(page, NR_ANON_THPS); + __dec_lruvec_page_state(page, NR_ANON_THPS); if (TestClearPageDoubleMap(page)) { /* -- cgit v1.2.3 From f0e45fb4da29746a116e810eb91423ccfa4830fc Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:07 -0700 Subject: mm: memcontrol: drop unused try/commit/cancel charge API There are no more users. RIP in peace. [arnd@arndb.de: fix an unused-function warning] Link: http://lkml.kernel.org/r/20200528095640.151454-1-arnd@arndb.de Signed-off-by: Johannes Weiner Signed-off-by: Arnd Bergmann Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-14-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 36 ------------- mm/memcontrol.c | 128 ++++++--------------------------------------- 2 files changed, 17 insertions(+), 147 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 63a31a6c3c69..46620c6343ef 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -355,14 +355,6 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); -int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp); -int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp); -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); - int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, bool lrucare); @@ -846,34 +838,6 @@ static inline enum mem_cgroup_protection mem_cgroup_protected( return MEMCG_PROT_NONE; } -static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, - struct mem_cgroup **memcgp) -{ - *memcgp = NULL; - return 0; -} - -static inline int mem_cgroup_try_charge_delay(struct page *page, - struct mm_struct *mm, - gfp_t gfp_mask, - struct mem_cgroup **memcgp) -{ - *memcgp = NULL; - return 0; -} - -static inline void mem_cgroup_commit_charge(struct page *page, - struct mem_cgroup *memcg, - bool lrucare) -{ -} - -static inline void mem_cgroup_cancel_charge(struct page *page, - struct mem_cgroup *memcg) -{ -} - static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, bool lrucare) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 17587ea2745a..1e7a10b450b2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2641,6 +2641,7 @@ done_restock: return 0; } +#if defined(CONFIG_MEMCG_KMEM) || defined(CONFIG_MMU) static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) { if (mem_cgroup_is_root(memcg)) @@ -2652,6 +2653,7 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) css_put_many(&memcg->css, nr_pages); } +#endif static void lock_page_lru(struct page *page, int *isolated) { @@ -6499,29 +6501,26 @@ out: } /** - * mem_cgroup_try_charge - try charging a page + * mem_cgroup_charge - charge a newly allocated page to a cgroup * @page: page to charge * @mm: mm context of the victim * @gfp_mask: reclaim mode - * @memcgp: charged memcg return + * @lrucare: page might be on the LRU already * * Try to charge @page to the memcg that @mm belongs to, reclaiming * pages according to @gfp_mask if necessary. * - * Returns 0 on success, with *@memcgp pointing to the charged memcg. - * Otherwise, an error code is returned. - * - * After page->mapping has been set up, the caller must finalize the - * charge with mem_cgroup_commit_charge(). Or abort the transaction - * with mem_cgroup_cancel_charge() in case page instantiation fails. + * Returns 0 on success. Otherwise, an error code is returned. */ -int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp) +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, + bool lrucare) { unsigned int nr_pages = hpage_nr_pages(page); struct mem_cgroup *memcg = NULL; int ret = 0; + VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); + if (mem_cgroup_disabled()) goto out; @@ -6553,56 +6552,8 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, memcg = get_mem_cgroup_from_mm(mm); ret = try_charge(memcg, gfp_mask, nr_pages); - - css_put(&memcg->css); -out: - *memcgp = memcg; - return ret; -} - -int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp) -{ - int ret; - - ret = mem_cgroup_try_charge(page, mm, gfp_mask, memcgp); - if (*memcgp) - cgroup_throttle_swaprate(page, gfp_mask); - return ret; -} - -/** - * mem_cgroup_commit_charge - commit a page charge - * @page: page to charge - * @memcg: memcg to charge the page to - * @lrucare: page might be on LRU already - * - * Finalize a charge transaction started by mem_cgroup_try_charge(), - * after page->mapping has been set up. This must happen atomically - * as part of the page instantiation, i.e. under the page table lock - * for anonymous pages, under the page lock for page and swap cache. - * - * In addition, the page must not be on the LRU during the commit, to - * prevent racing with task migration. If it might be, use @lrucare. - * - * Use mem_cgroup_cancel_charge() to cancel the transaction instead. - */ -void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare) -{ - unsigned int nr_pages = hpage_nr_pages(page); - - VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); - - if (mem_cgroup_disabled()) - return; - /* - * Swap faults will attempt to charge the same page multiple - * times. But reuse_swap_page() might have removed the page - * from swapcache already, so we can't check PageSwapCache(). - */ - if (!memcg) - return; + if (ret) + goto out_put; commit_charge(page, memcg, lrucare); @@ -6620,55 +6571,11 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, */ mem_cgroup_uncharge_swap(entry, nr_pages); } -} -/** - * mem_cgroup_cancel_charge - cancel a page charge - * @page: page to charge - * @memcg: memcg to charge the page to - * - * Cancel a charge transaction started by mem_cgroup_try_charge(). - */ -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) -{ - unsigned int nr_pages = hpage_nr_pages(page); - - if (mem_cgroup_disabled()) - return; - /* - * Swap faults will attempt to charge the same page multiple - * times. But reuse_swap_page() might have removed the page - * from swapcache already, so we can't check PageSwapCache(). - */ - if (!memcg) - return; - - cancel_charge(memcg, nr_pages); -} - -/** - * mem_cgroup_charge - charge a newly allocated page to a cgroup - * @page: page to charge - * @mm: mm context of the victim - * @gfp_mask: reclaim mode - * @lrucare: page might be on the LRU already - * - * Try to charge @page to the memcg that @mm belongs to, reclaiming - * pages according to @gfp_mask if necessary. - * - * Returns 0 on success. Otherwise, an error code is returned. - */ -int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - bool lrucare) -{ - struct mem_cgroup *memcg; - int ret; - - ret = mem_cgroup_try_charge(page, mm, gfp_mask, &memcg); - if (ret) - return ret; - mem_cgroup_commit_charge(page, memcg, lrucare); - return 0; +out_put: + css_put(&memcg->css); +out: + return ret; } struct uncharge_gather { @@ -6773,8 +6680,7 @@ static void uncharge_list(struct list_head *page_list) * 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(). + * Uncharge a page previously charged with mem_cgroup_charge(). */ void mem_cgroup_uncharge(struct page *page) { @@ -6797,7 +6703,7 @@ void mem_cgroup_uncharge(struct page *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(). + * mem_cgroup_charge(). */ void mem_cgroup_uncharge_list(struct list_head *page_list) { -- cgit v1.2.3 From eccb52e7880973f221ab2606e4d22ce04d96a1a9 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:11 -0700 Subject: mm: memcontrol: prepare swap controller setup for integration A few cleanups to streamline the swap controller setup: - Replace the do_swap_account flag with cgroup_memory_noswap. This brings it in line with other functionality that is usually available unless explicitly opted out of - nosocket, nokmem. - Remove the really_do_swap_account flag that stores the boot option and is later used to switch the do_swap_account. It's not clear why this indirection is/was necessary. Use do_swap_account directly. - Minor coding style polishing Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-15-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- mm/memcontrol.c | 59 ++++++++++++++++++++++------------------------ mm/swap_cgroup.c | 4 ++-- 3 files changed, 31 insertions(+), 34 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 46620c6343ef..96257f995caa 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -558,7 +558,7 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); #ifdef CONFIG_MEMCG_SWAP -extern int do_swap_account; +extern bool cgroup_memory_noswap; #endif struct mem_cgroup *lock_page_memcg(struct page *page); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1e7a10b450b2..2d035e68a127 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -83,10 +83,14 @@ static bool cgroup_memory_nokmem; /* Whether the swap controller is active */ #ifdef CONFIG_MEMCG_SWAP -int do_swap_account __read_mostly; +#ifdef CONFIG_MEMCG_SWAP_ENABLED +bool cgroup_memory_noswap __read_mostly; #else -#define do_swap_account 0 -#endif +bool cgroup_memory_noswap __read_mostly = 1; +#endif /* CONFIG_MEMCG_SWAP_ENABLED */ +#else +#define cgroup_memory_noswap 1 +#endif /* CONFIG_MEMCG_SWAP */ #ifdef CONFIG_CGROUP_WRITEBACK static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq); @@ -95,7 +99,7 @@ static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq); /* Whether legacy memory+swap accounting is active */ static bool do_memsw_account(void) { - return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && do_swap_account; + return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_noswap; } #define THRESHOLDS_EVENTS_TARGET 128 @@ -6528,18 +6532,19 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, /* * Every swap fault against a single page tries to charge the * page, bail as early as possible. shmem_unuse() encounters - * already charged pages, too. The USED bit is protected by - * the page lock, which serializes swap cache removal, which + * already charged pages, too. page->mem_cgroup is protected + * by the page lock, which serializes swap cache removal, which * in turn serializes uncharging. */ VM_BUG_ON_PAGE(!PageLocked(page), page); if (compound_head(page)->mem_cgroup) goto out; - if (do_swap_account) { + if (!cgroup_memory_noswap) { swp_entry_t ent = { .val = page_private(page), }; - unsigned short id = lookup_swap_cgroup_id(ent); + unsigned short id; + id = lookup_swap_cgroup_id(ent); rcu_read_lock(); memcg = mem_cgroup_from_id(id); if (memcg && !css_tryget_online(&memcg->css)) @@ -7012,7 +7017,7 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) struct mem_cgroup *memcg; unsigned short oldid; - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) || !do_swap_account) + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) || cgroup_memory_noswap) return 0; memcg = page->mem_cgroup; @@ -7056,7 +7061,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) struct mem_cgroup *memcg; unsigned short id; - if (!do_swap_account) + if (cgroup_memory_noswap) return; id = swap_cgroup_record(entry, 0, nr_pages); @@ -7079,7 +7084,7 @@ long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) { long nr_swap_pages = get_nr_swap_pages(); - if (!do_swap_account || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) + if (cgroup_memory_noswap || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) return nr_swap_pages; for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) nr_swap_pages = min_t(long, nr_swap_pages, @@ -7096,7 +7101,7 @@ bool mem_cgroup_swap_full(struct page *page) if (vm_swap_full()) return true; - if (!do_swap_account || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) + if (cgroup_memory_noswap || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) return false; memcg = page->mem_cgroup; @@ -7114,22 +7119,15 @@ bool mem_cgroup_swap_full(struct page *page) return false; } -/* for remember boot option*/ -#ifdef CONFIG_MEMCG_SWAP_ENABLED -static int really_do_swap_account __initdata = 1; -#else -static int really_do_swap_account __initdata; -#endif - -static int __init enable_swap_account(char *s) +static int __init setup_swap_account(char *s) { if (!strcmp(s, "1")) - really_do_swap_account = 1; + cgroup_memory_noswap = 0; else if (!strcmp(s, "0")) - really_do_swap_account = 0; + cgroup_memory_noswap = 1; return 1; } -__setup("swapaccount=", enable_swap_account); +__setup("swapaccount=", setup_swap_account); static u64 swap_current_read(struct cgroup_subsys_state *css, struct cftype *cft) @@ -7226,7 +7224,7 @@ static struct cftype swap_files[] = { { } /* terminate */ }; -static struct cftype memsw_cgroup_files[] = { +static struct cftype memsw_files[] = { { .name = "memsw.usage_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), @@ -7255,13 +7253,12 @@ static struct cftype memsw_cgroup_files[] = { static int __init mem_cgroup_swap_init(void) { - if (!mem_cgroup_disabled() && really_do_swap_account) { - do_swap_account = 1; - WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, - swap_files)); - WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, - memsw_cgroup_files)); - } + if (mem_cgroup_disabled() || cgroup_memory_noswap) + return 0; + + WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, swap_files)); + WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, memsw_files)); + return 0; } subsys_initcall(mem_cgroup_swap_init); diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c index 45affaef3bc6..7aa764f09079 100644 --- a/mm/swap_cgroup.c +++ b/mm/swap_cgroup.c @@ -171,7 +171,7 @@ int swap_cgroup_swapon(int type, unsigned long max_pages) unsigned long length; struct swap_cgroup_ctrl *ctrl; - if (!do_swap_account) + if (cgroup_memory_noswap) return 0; length = DIV_ROUND_UP(max_pages, SC_PER_PAGE); @@ -209,7 +209,7 @@ void swap_cgroup_swapoff(int type) unsigned long i, length; struct swap_cgroup_ctrl *ctrl; - if (!do_swap_account) + if (cgroup_memory_noswap) return; mutex_lock(&swap_cgroup_mutex); -- cgit v1.2.3 From d9eb1ea2bf8734afd8ec7d995270437a7242f82b Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:24 -0700 Subject: mm: memcontrol: delete unused lrucare handling Swapin faults were the last event to charge pages after they had already been put on the LRU list. Now that we charge directly on swapin, the lrucare portion of the charge code is unused. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Balbir Singh Cc: Shakeel Butt Link: http://lkml.kernel.org/r/20200508183105.225460-19-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 ++-- kernel/events/uprobes.c | 3 +-- mm/filemap.c | 2 +- mm/huge_memory.c | 2 +- mm/khugepaged.c | 4 ++-- mm/memcontrol.c | 57 ++++------------------------------------------ mm/memory.c | 8 +++---- mm/migrate.c | 2 +- mm/shmem.c | 2 +- mm/swap_state.c | 2 +- mm/userfaultfd.c | 2 +- 11 files changed, 19 insertions(+), 70 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 96257f995caa..d5bf3b5bfe6d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -355,8 +355,7 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); -int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - bool lrucare); +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -839,7 +838,7 @@ static inline enum mem_cgroup_protection mem_cgroup_protected( } static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, bool lrucare) + gfp_t gfp_mask) { return 0; } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 4253c153e985..eddc8db96027 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -167,8 +167,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, addr + PAGE_SIZE); if (new_page) { - err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL, - false); + err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL); if (err) return err; } diff --git a/mm/filemap.c b/mm/filemap.c index f08b0ca34e31..455990621989 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -845,7 +845,7 @@ static int __add_to_page_cache_locked(struct page *page, page->index = offset; if (!huge) { - error = mem_cgroup_charge(page, current->mm, gfp_mask, false); + error = mem_cgroup_charge(page, current->mm, gfp_mask); if (error) goto error; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e9201a88157e..6df182a18d2c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -593,7 +593,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_charge(page, vma->vm_mm, gfp, false)) { + if (mem_cgroup_charge(page, vma->vm_mm, gfp)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 32c85b81837a..f29038c485e0 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1059,7 +1059,7 @@ static void collapse_huge_page(struct mm_struct *mm, goto out_nolock; } - if (unlikely(mem_cgroup_charge(new_page, mm, gfp, false))) { + if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } @@ -1632,7 +1632,7 @@ static void collapse_file(struct mm_struct *mm, goto out; } - if (unlikely(mem_cgroup_charge(new_page, mm, gfp, false))) { + if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 425a265dc2a0..316a84025090 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2655,51 +2655,9 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) } #endif -static void lock_page_lru(struct page *page, int *isolated) +static void commit_charge(struct page *page, struct mem_cgroup *memcg) { - pg_data_t *pgdat = page_pgdat(page); - - spin_lock_irq(&pgdat->lru_lock); - if (PageLRU(page)) { - struct lruvec *lruvec; - - lruvec = mem_cgroup_page_lruvec(page, pgdat); - 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) -{ - pg_data_t *pgdat = page_pgdat(page); - - if (isolated) { - struct lruvec *lruvec; - - lruvec = mem_cgroup_page_lruvec(page, pgdat); - VM_BUG_ON_PAGE(PageLRU(page), page); - SetPageLRU(page); - add_page_to_lru_list(page, lruvec, page_lru(page)); - } - spin_unlock_irq(&pgdat->lru_lock); -} - -static void commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare) -{ - int isolated; - VM_BUG_ON_PAGE(page->mem_cgroup, page); - - /* - * 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) - lock_page_lru(page, &isolated); - /* * Nobody should be changing or seriously looking at * page->mem_cgroup at this point: @@ -2715,9 +2673,6 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg, * have the page locked */ page->mem_cgroup = memcg; - - if (lrucare) - unlock_page_lru(page, isolated); } #ifdef CONFIG_MEMCG_KMEM @@ -6503,22 +6458,18 @@ out: * @page: page to charge * @mm: mm context of the victim * @gfp_mask: reclaim mode - * @lrucare: page might be on the LRU already * * Try to charge @page to the memcg that @mm belongs to, reclaiming * pages according to @gfp_mask if necessary. * * Returns 0 on success. Otherwise, an error code is returned. */ -int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - bool lrucare) +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { unsigned int nr_pages = hpage_nr_pages(page); struct mem_cgroup *memcg = NULL; int ret = 0; - VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); - if (mem_cgroup_disabled()) goto out; @@ -6552,7 +6503,7 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, if (ret) goto out_put; - commit_charge(page, memcg, lrucare); + commit_charge(page, memcg); local_irq_disable(); mem_cgroup_charge_statistics(memcg, page, nr_pages); @@ -6753,7 +6704,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) page_counter_charge(&memcg->memsw, nr_pages); css_get_many(&memcg->css, nr_pages); - commit_charge(newpage, memcg, false); + commit_charge(newpage, memcg); local_irq_save(flags); mem_cgroup_charge_statistics(memcg, newpage, nr_pages); diff --git a/mm/memory.c b/mm/memory.c index 9c886e4207a2..d50d8b498af5 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2675,7 +2675,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } } - if (mem_cgroup_charge(new_page, mm, GFP_KERNEL, false)) + if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) goto oom_free_new; cgroup_throttle_swaprate(new_page, GFP_KERNEL); @@ -3134,7 +3134,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* Tell memcg to use swap ownership records */ SetPageSwapCache(page); err = mem_cgroup_charge(page, vma->vm_mm, - GFP_KERNEL, false); + GFP_KERNEL); ClearPageSwapCache(page); if (err) goto out_page; @@ -3358,7 +3358,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) if (!page) goto oom; - if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, false)) + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) goto oom_free_page; cgroup_throttle_swaprate(page, GFP_KERNEL); @@ -3854,7 +3854,7 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) if (!vmf->cow_page) return VM_FAULT_OOM; - if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL, false)) { + if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } diff --git a/mm/migrate.c b/mm/migrate.c index 44cee40221ec..7bfd0962149e 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2786,7 +2786,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, if (unlikely(anon_vma_prepare(vma))) goto abort; - if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, false)) + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) goto abort; /* diff --git a/mm/shmem.c b/mm/shmem.c index b79116185046..e83de27ce8f4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -624,7 +624,7 @@ static int shmem_add_to_page_cache(struct page *page, page->index = index; if (!PageSwapCache(page)) { - error = mem_cgroup_charge(page, charge_mm, gfp, false); + error = mem_cgroup_charge(page, charge_mm, gfp); if (error) { if (PageTransHuge(page)) { count_vm_event(THP_FILE_FALLBACK); diff --git a/mm/swap_state.c b/mm/swap_state.c index f841257a3014..ab0462819a5b 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -435,7 +435,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, goto fail_unlock; } - if (mem_cgroup_charge(page, NULL, gfp_mask, false)) { + if (mem_cgroup_charge(page, NULL, gfp_mask)) { delete_from_swap_cache(page); goto fail_unlock; } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 2745489415cc..7f5194046b01 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -96,7 +96,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, __SetPageUptodate(page); ret = -ENOMEM; - if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL, false)) + if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL)) goto out_release; _dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot)); -- cgit v1.2.3 From 7cf111bc39f6792abedcdfbc4e6291a5603b0ef0 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:03:06 -0700 Subject: mm: vmscan: determine anon/file pressure balance at the reclaim root We split the LRU lists into anon and file, and we rebalance the scan pressure between them when one of them begins thrashing: if the file cache experiences workingset refaults, we increase the pressure on anonymous pages; if the workload is stalled on swapins, we increase the pressure on the file cache instead. With cgroups and their nested LRU lists, we currently don't do this correctly. While recursive cgroup reclaim establishes a relative LRU order among the pages of all involved cgroups, LRU pressure balancing is done on an individual cgroup LRU level. As a result, when one cgroup is thrashing on the filesystem cache while a sibling may have cold anonymous pages, pressure doesn't get equalized between them. This patch moves LRU balancing decision to the root of reclaim - the same level where the LRU order is established. It does this by tracking LRU cost recursively, so that every level of the cgroup tree knows the aggregate LRU cost of all memory within its domain. When the page scanner calculates the scan balance for any given individual cgroup's LRU list, it uses the values from the ancestor cgroup that initiated the reclaim cycle. If one sibling is then thrashing on the cache, it will tip the pressure balance inside its ancestors, and the next hierarchical reclaim iteration will go more after the anon pages in the tree. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-13-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 13 +++++++++++++ mm/swap.c | 32 +++++++++++++++++++++++++++----- mm/vmscan.c | 41 +++++++++++++++++------------------------ 3 files changed, 57 insertions(+), 29 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d5bf3b5bfe6d..e77197a62809 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1242,6 +1242,19 @@ static inline void dec_lruvec_page_state(struct page *page, mod_lruvec_page_state(page, idx, -1); } +static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) +{ + struct mem_cgroup *memcg; + + memcg = lruvec_memcg(lruvec); + if (!memcg) + return NULL; + memcg = parent_mem_cgroup(memcg); + if (!memcg) + return NULL; + return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec)); +} + #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); diff --git a/mm/swap.c b/mm/swap.c index 2dc7d392642f..4dff2123f695 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -282,11 +282,33 @@ void lru_note_cost(struct page *page) { struct lruvec *lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); - /* Record new data point */ - if (page_is_file_lru(page)) - lruvec->file_cost++; - else - lruvec->anon_cost++; + do { + unsigned long lrusize; + + /* Record cost event */ + if (page_is_file_lru(page)) + lruvec->file_cost++; + else + lruvec->anon_cost++; + + /* + * Decay previous events + * + * Because workloads change over time (and to avoid + * overflow) we keep these statistics as a floating + * average, which ends up weighing recent refaults + * more than old ones. + */ + lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) + + lruvec_page_state(lruvec, NR_ACTIVE_ANON) + + lruvec_page_state(lruvec, NR_INACTIVE_FILE) + + lruvec_page_state(lruvec, NR_ACTIVE_FILE); + + if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { + lruvec->file_cost /= 2; + lruvec->anon_cost /= 2; + } + } while ((lruvec = parent_lruvec(lruvec))); } static void __activate_page(struct page *page, struct lruvec *lruvec, diff --git a/mm/vmscan.c b/mm/vmscan.c index 76e823db21a7..d08640f0235c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -79,6 +79,12 @@ struct scan_control { */ struct mem_cgroup *target_mem_cgroup; + /* + * Scan pressure balancing between anon and file LRUs + */ + unsigned long anon_cost; + unsigned long file_cost; + /* Can active pages be deactivated as part of reclaim? */ #define DEACTIVATE_ANON 1 #define DEACTIVATE_FILE 2 @@ -2231,10 +2237,8 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, int swappiness = mem_cgroup_swappiness(memcg); u64 fraction[2]; u64 denominator = 0; /* gcc */ - struct pglist_data *pgdat = lruvec_pgdat(lruvec); unsigned long anon_prio, file_prio; enum scan_balance scan_balance; - unsigned long anon, file; unsigned long totalcost; unsigned long ap, fp; enum lru_list lru; @@ -2285,7 +2289,6 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, } scan_balance = SCAN_FRACT; - /* * Calculate the pressure balance between anon and file pages. * @@ -2300,30 +2303,12 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, anon_prio = swappiness; file_prio = 200 - anon_prio; - /* - * Because workloads change over time (and to avoid overflow) - * we keep these statistics as a floating average, which ends - * up weighing recent refaults more than old ones. - */ - - anon = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON, MAX_NR_ZONES) + - lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, MAX_NR_ZONES); - file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) + - lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES); - - spin_lock_irq(&pgdat->lru_lock); - totalcost = lruvec->anon_cost + lruvec->file_cost; - if (unlikely(totalcost > (anon + file) / 4)) { - lruvec->anon_cost /= 2; - lruvec->file_cost /= 2; - totalcost /= 2; - } + totalcost = sc->anon_cost + sc->file_cost; ap = anon_prio * (totalcost + 1); - ap /= lruvec->anon_cost + 1; + ap /= sc->anon_cost + 1; fp = file_prio * (totalcost + 1); - fp /= lruvec->file_cost + 1; - spin_unlock_irq(&pgdat->lru_lock); + fp /= sc->file_cost + 1; fraction[0] = ap; fraction[1] = fp; @@ -2687,6 +2672,14 @@ again: nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; + /* + * Determine the scan balance between anon and file LRUs. + */ + spin_lock_irq(&pgdat->lru_lock); + sc->anon_cost = target_lruvec->anon_cost; + sc->file_cost = target_lruvec->file_cost; + spin_unlock_irq(&pgdat->lru_lock); + /* * Target desirable inactive:active list ratios for the anon * and file LRU lists. -- cgit v1.2.3