From bff6bb83f38105b39b0cc3a9ad81103edbb56f7a Mon Sep 17 00:00:00 2001 From: Kamezawa Hiroyuki Date: Tue, 31 Jul 2012 16:41:38 -0700 Subject: memcg: rename MEM_CGROUP_STAT_SWAPOUT as MEM_CGROUP_STAT_SWAP MEM_CGROUP_STAT_SWAPOUT represents the usage of swap rather than the number of swap-out events. Rename it to be MEM_CGROUP_STAT_SWAP. Signed-off-by: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Acked-by: Hugh Dickins Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f72b5e52451..91ce7b2ee1e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -87,7 +87,7 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */ MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ - MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */ + MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, }; @@ -703,7 +703,7 @@ static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg, bool charge) { int val = (charge) ? 1 : -1; - this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAPOUT], val); + this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAP], val); } static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, @@ -3831,7 +3831,7 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS); if (swap) - val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAPOUT); + val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAP); return val << PAGE_SHIFT; } @@ -4082,7 +4082,7 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, unsigned int i; for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { - if (i == MEM_CGROUP_STAT_SWAPOUT && !do_swap_account) + if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account) continue; seq_printf(m, "%s %ld\n", mem_cgroup_stat_names[i], mem_cgroup_read_stat(memcg, i) * PAGE_SIZE); @@ -4109,7 +4109,7 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { long long val = 0; - if (i == MEM_CGROUP_STAT_SWAPOUT && !do_swap_account) + if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account) continue; for_each_mem_cgroup_tree(mi, memcg) val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE; -- cgit v1.2.3-70-g09d2 From 41326c17fc1b45289a82567553249f60d3638a23 Mon Sep 17 00:00:00 2001 From: Kamezawa Hiroyuki Date: Tue, 31 Jul 2012 16:41:40 -0700 Subject: memcg: rename MEM_CGROUP_CHARGE_TYPE_MAPPED as MEM_CGROUP_CHARGE_TYPE_ANON Now, in memcg, 2 "MAPPED" enum/macro are found MEM_CGROUP_CHARGE_TYPE_MAPPED MEM_CGROUP_STAT_FILE_MAPPED Thier names looks similar to each other but the former is used for accounting anonymous memory. rename it as TYPE_ANON. Signed-off-by: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 91ce7b2ee1e..1b3dd27ead6 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -378,7 +378,7 @@ static bool move_file(void) enum charge_type { MEM_CGROUP_CHARGE_TYPE_CACHE = 0, - MEM_CGROUP_CHARGE_TYPE_MAPPED, + MEM_CGROUP_CHARGE_TYPE_ANON, MEM_CGROUP_CHARGE_TYPE_SHMEM, /* used by page migration of shmem */ MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */ MEM_CGROUP_CHARGE_TYPE_SWAPOUT, /* for accounting swapcache */ @@ -2519,7 +2519,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, spin_unlock_irq(&zone->lru_lock); } - if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED) + if (ctype == MEM_CGROUP_CHARGE_TYPE_ANON) anon = true; else anon = false; @@ -2728,7 +2728,7 @@ int mem_cgroup_newpage_charge(struct page *page, VM_BUG_ON(page->mapping && !PageAnon(page)); VM_BUG_ON(!mm); return mem_cgroup_charge_common(page, mm, gfp_mask, - MEM_CGROUP_CHARGE_TYPE_MAPPED); + MEM_CGROUP_CHARGE_TYPE_ANON); } static void @@ -2842,7 +2842,7 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg) { __mem_cgroup_commit_charge_swapin(page, memcg, - MEM_CGROUP_CHARGE_TYPE_MAPPED); + MEM_CGROUP_CHARGE_TYPE_ANON); } void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg) @@ -2945,7 +2945,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) anon = PageAnon(page); switch (ctype) { - case MEM_CGROUP_CHARGE_TYPE_MAPPED: + case MEM_CGROUP_CHARGE_TYPE_ANON: /* * Generally PageAnon tells if it's the anon statistics to be * updated; but sometimes e.g. mem_cgroup_uncharge_page() is @@ -3005,7 +3005,7 @@ void mem_cgroup_uncharge_page(struct page *page) if (page_mapped(page)) return; VM_BUG_ON(page->mapping && !PageAnon(page)); - __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED); + __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_ANON); } void mem_cgroup_uncharge_cache_page(struct page *page) @@ -3248,7 +3248,7 @@ int mem_cgroup_prepare_migration(struct page *page, * mapcount will be finally 0 and we call uncharge in end_migration(). */ if (PageAnon(page)) - ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED; + ctype = MEM_CGROUP_CHARGE_TYPE_ANON; else if (page_is_file_cache(page)) ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; else @@ -3287,7 +3287,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg, unlock_page_cgroup(pc); anon = PageAnon(used); __mem_cgroup_uncharge_common(unused, - anon ? MEM_CGROUP_CHARGE_TYPE_MAPPED + anon ? MEM_CGROUP_CHARGE_TYPE_ANON : MEM_CGROUP_CHARGE_TYPE_CACHE); /* -- cgit v1.2.3-70-g09d2 From a7d6f529fe1d96a477614eb93f40213d133029e6 Mon Sep 17 00:00:00 2001 From: Kamezawa Hiroyuki Date: Tue, 31 Jul 2012 16:41:41 -0700 Subject: memcg: remove MEM_CGROUP_CHARGE_TYPE_FORCE There are no users since commit b24028572fb69 ("memcg: remove PCG_CACHE"). Signed-off-by: KAMEZAWA Hiroyuki Acked-by: Hugh Dickins Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 1 - 1 file changed, 1 deletion(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1b3dd27ead6..1940ba8e6f0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -380,7 +380,6 @@ enum charge_type { MEM_CGROUP_CHARGE_TYPE_CACHE = 0, MEM_CGROUP_CHARGE_TYPE_ANON, MEM_CGROUP_CHARGE_TYPE_SHMEM, /* used by page migration of shmem */ - MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */ MEM_CGROUP_CHARGE_TYPE_SWAPOUT, /* for accounting swapcache */ MEM_CGROUP_CHARGE_TYPE_DROP, /* a page was unused swap cache */ NR_CHARGE_TYPE, -- cgit v1.2.3-70-g09d2 From 59b8e85c26e77d236ebdd61866ffc5e69c5f531d Mon Sep 17 00:00:00 2001 From: Kamezawa Hiroyuki Date: Tue, 31 Jul 2012 16:42:42 -0700 Subject: memcg: remove check for signal_pending() during rmdir() After bf544fdc241da8 "memcg: move charges to root cgroup if use_hierarchy=0 in mem_cgroup_move_hugetlb_parent()", no memory reclaim will occur when removing a memory cgroup. If -EINTR is returned here, cgroup will show a warning. We don't need to handle any user interruption signal. Remove this. Signed-off-by: KAMEZAWA Hiroyuki Cc: Johannes Weiner Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1940ba8e6f0..8062d45ee7f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3691,9 +3691,6 @@ move_account: ret = -EBUSY; if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children)) goto out; - ret = -EINTR; - if (signal_pending(current)) - goto out; /* This is for making all *used* pages to be on LRU. */ lru_add_drain_all(); drain_all_stock_sync(memcg); -- cgit v1.2.3-70-g09d2 From d845aa2c75bcff87dacf098378b5706b12d1588f Mon Sep 17 00:00:00 2001 From: Kamezawa Hiroyuki Date: Tue, 31 Jul 2012 16:42:44 -0700 Subject: memcg: clean up force_empty_list() return value check After bf544fdc241da8 "memcg: move charges to root cgroup if use_hierarchy=0 in mem_cgroup_move_hugetlb_parent()" mem_cgroup_move_parent() returns only -EBUSY or -EINVAL. So we can remove the -ENOMEM and -EINTR checks. Signed-off-by: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8062d45ee7f..a1f00f0a66c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3653,8 +3653,6 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, pc = lookup_page_cgroup(page); ret = mem_cgroup_move_parent(page, pc, memcg, GFP_KERNEL); - if (ret == -ENOMEM || ret == -EINTR) - break; if (ret == -EBUSY || ret == -EINVAL) { /* found lock contention or "pc" is obsolete. */ @@ -3711,9 +3709,6 @@ move_account: } mem_cgroup_end_move(memcg); memcg_oom_recover(memcg); - /* it seems parent cgroup doesn't have enough mem */ - if (ret == -ENOMEM) - goto try_to_free; cond_resched(); /* "ret" should also be checked to ensure all lists are empty. */ } while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0 || ret); -- cgit v1.2.3-70-g09d2 From 6068bf0104becf07792b2867bc4d17c369419f8b Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 31 Jul 2012 16:42:45 -0700 Subject: memcg: mem_cgroup_move_parent() doesn't need gfp_mask Signed-off-by: KAMEZAWA Hiroyuki Cc: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a1f00f0a66c..96478663474 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2643,8 +2643,7 @@ out: static int mem_cgroup_move_parent(struct page *page, struct page_cgroup *pc, - struct mem_cgroup *child, - gfp_t gfp_mask) + struct mem_cgroup *child) { struct mem_cgroup *parent; unsigned int nr_pages; @@ -3652,7 +3651,7 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, pc = lookup_page_cgroup(page); - ret = mem_cgroup_move_parent(page, pc, memcg, GFP_KERNEL); + ret = mem_cgroup_move_parent(page, pc, memcg); if (ret == -EBUSY || ret == -EINVAL) { /* found lock contention or "pc" is obsolete. */ -- cgit v1.2.3-70-g09d2 From 3c935d189be9bb877c5a1110ac5fbf9c8e310658 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 31 Jul 2012 16:42:46 -0700 Subject: memcg: make mem_cgroup_force_empty_list() return bool mem_cgroup_force_empty_list() just returns 0 or -EBUSY and -EBUSY indicates 'you need to retry'. Make mem_cgroup_force_empty_list() return a bool to simplify the logic. [akpm@linux-foundation.org: rework mem_cgroup_force_empty_list()'s comment] Signed-off-by: KAMEZAWA Hiroyuki Cc: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 96478663474..a2677e0a638 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3609,10 +3609,12 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, } /* - * This routine traverse page_cgroup in given list and drop them all. - * *And* this routine doesn't reclaim page itself, just removes page_cgroup. + * Traverse a specified page_cgroup list and try to drop them all. This doesn't + * reclaim the pages page themselves - it just removes the page_cgroups. + * Returns true if some page_cgroups were not freed, indicating that the caller + * must retry this operation. */ -static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, +static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg, int node, int zid, enum lru_list lru) { struct mem_cgroup_per_zone *mz; @@ -3620,7 +3622,6 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, struct list_head *list; struct page *busy; struct zone *zone; - int ret = 0; zone = &NODE_DATA(node)->node_zones[zid]; mz = mem_cgroup_zoneinfo(memcg, node, zid); @@ -3634,7 +3635,6 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, struct page_cgroup *pc; struct page *page; - ret = 0; spin_lock_irqsave(&zone->lru_lock, flags); if (list_empty(list)) { spin_unlock_irqrestore(&zone->lru_lock, flags); @@ -3651,19 +3651,14 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, pc = lookup_page_cgroup(page); - ret = mem_cgroup_move_parent(page, pc, memcg); - - if (ret == -EBUSY || ret == -EINVAL) { + if (mem_cgroup_move_parent(page, pc, memcg)) { /* found lock contention or "pc" is obsolete. */ busy = page; cond_resched(); } else busy = NULL; } - - if (!ret && !list_empty(list)) - return -EBUSY; - return ret; + return !list_empty(list); } /* -- cgit v1.2.3-70-g09d2 From c255a458055e459f65eb7b7f51dc5dbdd0caf1d8 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 31 Jul 2012 16:43:02 -0700 Subject: memcg: rename config variables Sanity: CONFIG_CGROUP_MEM_RES_CTLR -> CONFIG_MEMCG CONFIG_CGROUP_MEM_RES_CTLR_SWAP -> CONFIG_MEMCG_SWAP CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED -> CONFIG_MEMCG_SWAP_ENABLED CONFIG_CGROUP_MEM_RES_CTLR_KMEM -> CONFIG_MEMCG_KMEM [mhocko@suse.cz: fix missed bits] Cc: Glauber Costa Acked-by: Michal Hocko Cc: Johannes Weiner Cc: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Tejun Heo Cc: Aneesh Kumar K.V Cc: David Rientjes Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/memory.txt | 10 +++++----- arch/powerpc/configs/chroma_defconfig | 4 ++-- arch/s390/defconfig | 2 +- arch/sh/configs/apsh4ad0a_defconfig | 2 +- arch/sh/configs/sdk7786_defconfig | 4 ++-- arch/sh/configs/se7206_defconfig | 2 +- arch/sh/configs/shx3_defconfig | 2 +- arch/sh/configs/urquell_defconfig | 4 ++-- arch/tile/configs/tilegx_defconfig | 4 ++-- arch/tile/configs/tilepro_defconfig | 4 ++-- arch/um/defconfig | 8 ++++---- include/linux/cgroup_subsys.h | 2 +- include/linux/memcontrol.h | 14 +++++++------- include/linux/mmzone.h | 8 ++++---- include/linux/page_cgroup.h | 10 +++++----- include/linux/sched.h | 2 +- include/linux/swap.h | 6 +++--- include/net/sock.h | 4 ++-- init/Kconfig | 14 +++++++------- kernel/fork.c | 2 +- mm/Makefile | 2 +- mm/hwpoison-inject.c | 2 +- mm/memcontrol.c | 20 ++++++++++---------- mm/memory-failure.c | 2 +- mm/mmzone.c | 2 +- mm/oom_kill.c | 2 +- mm/page_cgroup.c | 2 +- mm/vmscan.c | 4 ++-- net/core/sock.c | 2 +- net/ipv4/Makefile | 2 +- net/ipv4/sysctl_net_ipv4.c | 4 ++-- net/ipv4/tcp_ipv4.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- 33 files changed, 78 insertions(+), 78 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index dd88540bb99..672676ac961 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -187,12 +187,12 @@ the cgroup that brought it in -- this will happen on memory pressure). But see section 8.2: when moving a task to another cgroup, its pages may be recharged to the new cgroup, if move_charge_at_immigrate has been chosen. -Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used. +Exception: If CONFIG_CGROUP_CGROUP_MEMCG_SWAP is not used. When you do swapoff and make swapped-out pages of shmem(tmpfs) to be backed into memory in force, charges for pages are accounted against the caller of swapoff rather than the users of shmem. -2.4 Swap Extension (CONFIG_CGROUP_MEM_RES_CTLR_SWAP) +2.4 Swap Extension (CONFIG_MEMCG_SWAP) Swap Extension allows you to record charge for swap. A swapped-in page is charged back to original page allocator if possible. @@ -259,7 +259,7 @@ When oom event notifier is registered, event will be delivered. per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by zone->lru_lock, it has no lock of its own. -2.7 Kernel Memory Extension (CONFIG_CGROUP_MEM_RES_CTLR_KMEM) +2.7 Kernel Memory Extension (CONFIG_MEMCG_KMEM) With the Kernel memory extension, the Memory Controller is able to limit the amount of kernel memory used by the system. Kernel memory is fundamentally @@ -286,8 +286,8 @@ per cgroup, instead of globally. a. Enable CONFIG_CGROUPS b. Enable CONFIG_RESOURCE_COUNTERS -c. Enable CONFIG_CGROUP_MEM_RES_CTLR -d. Enable CONFIG_CGROUP_MEM_RES_CTLR_SWAP (to use swap extension) +c. Enable CONFIG_MEMCG +d. Enable CONFIG_MEMCG_SWAP (to use swap extension) 1. Prepare the cgroups (see cgroups.txt, Why are cgroups needed?) # mount -t tmpfs none /sys/fs/cgroup diff --git a/arch/powerpc/configs/chroma_defconfig b/arch/powerpc/configs/chroma_defconfig index b1f9597fe31..29bb11ec6c6 100644 --- a/arch/powerpc/configs/chroma_defconfig +++ b/arch/powerpc/configs/chroma_defconfig @@ -21,8 +21,8 @@ CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y CONFIG_RESOURCE_COUNTERS=y -CONFIG_CGROUP_MEM_RES_CTLR=y -CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y +CONFIG_CGROUP_MEMCG=y +CONFIG_CGROUP_MEMCG_SWAP=y CONFIG_NAMESPACES=y CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 37d2bf26796..de57702a3f4 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -13,7 +13,7 @@ CONFIG_CGROUPS=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y CONFIG_RESOURCE_COUNTERS=y -CONFIG_CGROUP_MEM_RES_CTLR=y +CONFIG_CGROUP_MEMCG=y CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y CONFIG_CGROUP_SCHED=y CONFIG_RT_GROUP_SCHED=y diff --git a/arch/sh/configs/apsh4ad0a_defconfig b/arch/sh/configs/apsh4ad0a_defconfig index e7583484cc0..95ae23fcfdd 100644 --- a/arch/sh/configs/apsh4ad0a_defconfig +++ b/arch/sh/configs/apsh4ad0a_defconfig @@ -11,7 +11,7 @@ CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_RESOURCE_COUNTERS=y -CONFIG_CGROUP_MEM_RES_CTLR=y +CONFIG_CGROUP_MEMCG=y CONFIG_BLK_CGROUP=y CONFIG_NAMESPACES=y CONFIG_BLK_DEV_INITRD=y diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig index 8a7dd7b59c5..76a76a295d7 100644 --- a/arch/sh/configs/sdk7786_defconfig +++ b/arch/sh/configs/sdk7786_defconfig @@ -18,8 +18,8 @@ CONFIG_CPUSETS=y # CONFIG_PROC_PID_CPUSET is not set CONFIG_CGROUP_CPUACCT=y CONFIG_RESOURCE_COUNTERS=y -CONFIG_CGROUP_MEM_RES_CTLR=y -CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y +CONFIG_CGROUP_MEMCG=y +CONFIG_CGROUP_MEMCG_SWAP=y CONFIG_CGROUP_SCHED=y CONFIG_RT_GROUP_SCHED=y CONFIG_BLK_CGROUP=y diff --git a/arch/sh/configs/se7206_defconfig b/arch/sh/configs/se7206_defconfig index 72c3fad7383..6bc30ab9fd1 100644 --- a/arch/sh/configs/se7206_defconfig +++ b/arch/sh/configs/se7206_defconfig @@ -11,7 +11,7 @@ CONFIG_CGROUP_DEBUG=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_RESOURCE_COUNTERS=y -CONFIG_CGROUP_MEM_RES_CTLR=y +CONFIG_CGROUP_MEMCG=y CONFIG_RELAY=y CONFIG_NAMESPACES=y CONFIG_UTS_NS=y diff --git a/arch/sh/configs/shx3_defconfig b/arch/sh/configs/shx3_defconfig index 6bb41303689..cd6c519f8fa 100644 --- a/arch/sh/configs/shx3_defconfig +++ b/arch/sh/configs/shx3_defconfig @@ -13,7 +13,7 @@ CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_RESOURCE_COUNTERS=y -CONFIG_CGROUP_MEM_RES_CTLR=y +CONFIG_CGROUP_MEMCG=y CONFIG_RELAY=y CONFIG_NAMESPACES=y CONFIG_UTS_NS=y diff --git a/arch/sh/configs/urquell_defconfig b/arch/sh/configs/urquell_defconfig index 8bfa4d056d7..d7f89be9f47 100644 --- a/arch/sh/configs/urquell_defconfig +++ b/arch/sh/configs/urquell_defconfig @@ -15,8 +15,8 @@ CONFIG_CPUSETS=y # CONFIG_PROC_PID_CPUSET is not set CONFIG_CGROUP_CPUACCT=y CONFIG_RESOURCE_COUNTERS=y -CONFIG_CGROUP_MEM_RES_CTLR=y -CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y +CONFIG_CGROUP_MEMCG=y +CONFIG_CGROUP_MEMCG_SWAP=y CONFIG_CGROUP_SCHED=y CONFIG_RT_GROUP_SCHED=y CONFIG_BLK_DEV_INITRD=y diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig index b8d99aca543..0270620a169 100644 --- a/arch/tile/configs/tilegx_defconfig +++ b/arch/tile/configs/tilegx_defconfig @@ -18,8 +18,8 @@ CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y CONFIG_RESOURCE_COUNTERS=y -CONFIG_CGROUP_MEM_RES_CTLR=y -CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y +CONFIG_CGROUP_MEMCG=y +CONFIG_CGROUP_MEMCG_SWAP=y CONFIG_CGROUP_SCHED=y CONFIG_RT_GROUP_SCHED=y CONFIG_BLK_CGROUP=y diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig index 2b1fd31894f..c11de27a9bc 100644 --- a/arch/tile/configs/tilepro_defconfig +++ b/arch/tile/configs/tilepro_defconfig @@ -17,8 +17,8 @@ CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y CONFIG_RESOURCE_COUNTERS=y -CONFIG_CGROUP_MEM_RES_CTLR=y -CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y +CONFIG_CGROUP_MEMCG=y +CONFIG_CGROUP_MEMCG_SWAP=y CONFIG_CGROUP_SCHED=y CONFIG_RT_GROUP_SCHED=y CONFIG_BLK_CGROUP=y diff --git a/arch/um/defconfig b/arch/um/defconfig index 7823ab12e6a..fec0d5d2746 100644 --- a/arch/um/defconfig +++ b/arch/um/defconfig @@ -155,10 +155,10 @@ CONFIG_CPUSETS=y CONFIG_PROC_PID_CPUSET=y CONFIG_CGROUP_CPUACCT=y CONFIG_RESOURCE_COUNTERS=y -CONFIG_CGROUP_MEM_RES_CTLR=y -CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y -# CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED is not set -# CONFIG_CGROUP_MEM_RES_CTLR_KMEM is not set +CONFIG_CGROUP_MEMCG=y +CONFIG_CGROUP_MEMCG_SWAP=y +# CONFIG_CGROUP_MEMCG_SWAP_ENABLED is not set +# CONFIG_CGROUP_MEMCG_KMEM is not set CONFIG_CGROUP_SCHED=y CONFIG_FAIR_GROUP_SCHED=y # CONFIG_CFS_BANDWIDTH is not set diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index 5b41ce07902..dfae957398c 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -31,7 +31,7 @@ SUBSYS(cpuacct) /* */ -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG SUBSYS(mem_cgroup) #endif diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 83e7ba90d6e..17007622243 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -38,7 +38,7 @@ struct mem_cgroup_reclaim_cookie { unsigned int generation; }; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG /* * All "charge" functions with gfp_mask should use GFP_KERNEL or * (gfp_mask & GFP_RECLAIM_MASK). In current implementatin, memcg doesn't @@ -124,7 +124,7 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, extern void mem_cgroup_replace_page_cache(struct page *oldpage, struct page *newpage); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP extern int do_swap_account; #endif @@ -193,7 +193,7 @@ void mem_cgroup_split_huge_fixup(struct page *head); bool mem_cgroup_bad_page_check(struct page *page); void mem_cgroup_print_bad_page(struct page *page); #endif -#else /* CONFIG_CGROUP_MEM_RES_CTLR */ +#else /* CONFIG_MEMCG */ struct mem_cgroup; static inline int mem_cgroup_newpage_charge(struct page *page, @@ -384,9 +384,9 @@ static inline void mem_cgroup_replace_page_cache(struct page *oldpage, struct page *newpage) { } -#endif /* CONFIG_CGROUP_MEM_RES_CTLR */ +#endif /* CONFIG_MEMCG */ -#if !defined(CONFIG_CGROUP_MEM_RES_CTLR) || !defined(CONFIG_DEBUG_VM) +#if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM) static inline bool mem_cgroup_bad_page_check(struct page *page) { @@ -406,7 +406,7 @@ enum { }; struct sock; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM void sock_update_memcg(struct sock *sk); void sock_release_memcg(struct sock *sk); #else @@ -416,6 +416,6 @@ static inline void sock_update_memcg(struct sock *sk) static inline void sock_release_memcg(struct sock *sk) { } -#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */ +#endif /* CONFIG_MEMCG_KMEM */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 458988bd55a..3bdfa15b201 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -201,7 +201,7 @@ struct zone_reclaim_stat { struct lruvec { struct list_head lists[NR_LRU_LISTS]; struct zone_reclaim_stat reclaim_stat; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG struct zone *zone; #endif }; @@ -671,7 +671,7 @@ typedef struct pglist_data { int nr_zones; #ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */ struct page *node_mem_map; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG struct page_cgroup *node_page_cgroup; #endif #endif @@ -736,7 +736,7 @@ extern void lruvec_init(struct lruvec *lruvec, struct zone *zone); static inline struct zone *lruvec_zone(struct lruvec *lruvec) { -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG return lruvec->zone; #else return container_of(lruvec, struct zone, lruvec); @@ -1052,7 +1052,7 @@ struct mem_section { /* See declaration of similar field in struct zone */ unsigned long *pageblock_flags; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG /* * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use * section. (see memcontrol.h/page_cgroup.h about this.) diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index a88cdba2780..777a524716d 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -12,7 +12,7 @@ enum { #ifndef __GENERATING_BOUNDS_H #include -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG #include /* @@ -82,7 +82,7 @@ static inline void unlock_page_cgroup(struct page_cgroup *pc) bit_spin_unlock(PCG_LOCK, &pc->flags); } -#else /* CONFIG_CGROUP_MEM_RES_CTLR */ +#else /* CONFIG_MEMCG */ struct page_cgroup; static inline void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat) @@ -102,11 +102,11 @@ static inline void __init page_cgroup_init_flatmem(void) { } -#endif /* CONFIG_CGROUP_MEM_RES_CTLR */ +#endif /* CONFIG_MEMCG */ #include -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent, unsigned short old, unsigned short new); extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id); @@ -138,7 +138,7 @@ static inline void swap_cgroup_swapoff(int type) return; } -#endif /* CONFIG_CGROUP_MEM_RES_CTLR_SWAP */ +#endif /* CONFIG_MEMCG_SWAP */ #endif /* !__GENERATING_BOUNDS_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 68dcffaa62a..865725adb9d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1584,7 +1584,7 @@ struct task_struct { /* bitmask and counter of trace recursion */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ -#ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */ +#ifdef CONFIG_MEMCG /* memcg uses this to do batch job */ struct memcg_batch_info { int do_batch; /* incremented when batch uncharge started */ struct mem_cgroup *memcg; /* target memcg of uncharge */ diff --git a/include/linux/swap.h b/include/linux/swap.h index c84ec68eaec..9a16bb1cefd 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -301,7 +301,7 @@ static inline void scan_unevictable_unregister_node(struct node *node) extern int kswapd_run(int nid); extern void kswapd_stop(int nid); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG extern int mem_cgroup_swappiness(struct mem_cgroup *mem); #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) @@ -309,7 +309,7 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) return vm_swappiness; } #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP extern void mem_cgroup_uncharge_swap(swp_entry_t ent); #else static inline void mem_cgroup_uncharge_swap(swp_entry_t ent) @@ -360,7 +360,7 @@ extern int reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); struct backing_dev_info; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG extern void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout); #else diff --git a/include/net/sock.h b/include/net/sock.h index e067f8c18f8..cee528c119c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -913,7 +913,7 @@ struct proto { #ifdef SOCK_REFCNT_DEBUG atomic_t socks; #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM /* * cgroup specific init/deinit functions. Called once for all * protocols that implement it, from cgroups populate function. @@ -994,7 +994,7 @@ inline void sk_refcnt_debug_release(const struct sock *sk) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ -#if defined(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) && defined(CONFIG_NET) +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_NET) extern struct static_key memcg_socket_limit_enabled; static inline struct cg_proto *parent_cg_proto(struct proto *proto, struct cg_proto *cg_proto) diff --git a/init/Kconfig b/init/Kconfig index 72437760e90..af6c7f8ba01 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -686,7 +686,7 @@ config RESOURCE_COUNTERS This option enables controller independent resource accounting infrastructure that works with cgroups. -config CGROUP_MEM_RES_CTLR +config MEMCG bool "Memory Resource Controller for Control Groups" depends on RESOURCE_COUNTERS select MM_OWNER @@ -709,9 +709,9 @@ config CGROUP_MEM_RES_CTLR This config option also selects MM_OWNER config option, which could in turn add some fork/exit overhead. -config CGROUP_MEM_RES_CTLR_SWAP +config MEMCG_SWAP bool "Memory Resource Controller Swap Extension" - depends on CGROUP_MEM_RES_CTLR && SWAP + depends on MEMCG && SWAP help Add swap management feature to memory resource controller. When you enable this, you can limit mem+swap usage per cgroup. In other words, @@ -726,9 +726,9 @@ config CGROUP_MEM_RES_CTLR_SWAP if boot option "swapaccount=0" is set, swap will not be accounted. Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page size is 4096bytes, 512k per 1Gbytes of swap. -config CGROUP_MEM_RES_CTLR_SWAP_ENABLED +config MEMCG_SWAP_ENABLED bool "Memory Resource Controller Swap Extension enabled by default" - depends on CGROUP_MEM_RES_CTLR_SWAP + depends on MEMCG_SWAP default y help Memory Resource Controller Swap Extension comes with its price in @@ -739,9 +739,9 @@ config CGROUP_MEM_RES_CTLR_SWAP_ENABLED For those who want to have the feature enabled by default should select this option (if, for some reason, they need to disable it then swapaccount=0 does the trick). -config CGROUP_MEM_RES_CTLR_KMEM +config MEMCG_KMEM bool "Memory Resource Controller Kernel Memory accounting (EXPERIMENTAL)" - depends on CGROUP_MEM_RES_CTLR && EXPERIMENTAL + depends on MEMCG && EXPERIMENTAL default n help The Kernel Memory extension for Memory Resource Controller can limit diff --git a/kernel/fork.c b/kernel/fork.c index aaa8813c45d..3bd2280d79f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1306,7 +1306,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG p->memcg_batch.do_batch = 0; p->memcg_batch.memcg = NULL; #endif diff --git a/mm/Makefile b/mm/Makefile index fd6fc1c1966..290bbfe3369 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -49,7 +49,7 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o obj-$(CONFIG_QUICKLIST) += quicklist.o obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o -obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o +obj-$(CONFIG_MEMCG) += memcontrol.o page_cgroup.o obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c index cc448bb983b..3a61efc518d 100644 --- a/mm/hwpoison-inject.c +++ b/mm/hwpoison-inject.c @@ -123,7 +123,7 @@ static int pfn_inject_init(void) if (!dentry) goto fail; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP dentry = debugfs_create_u64("corrupt-filter-memcg", 0600, hwpoison_dir, &hwpoison_filter_memcg); if (!dentry) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a2677e0a638..55a85e1a342 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -61,12 +61,12 @@ struct cgroup_subsys mem_cgroup_subsys __read_mostly; #define MEM_CGROUP_RECLAIM_RETRIES 5 static struct mem_cgroup *root_mem_cgroup __read_mostly; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP /* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */ int do_swap_account __read_mostly; /* for remember boot option*/ -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED +#ifdef CONFIG_MEMCG_SWAP_ENABLED static int really_do_swap_account __initdata = 1; #else static int really_do_swap_account __initdata = 0; @@ -407,7 +407,7 @@ static void mem_cgroup_get(struct mem_cgroup *memcg); static void mem_cgroup_put(struct mem_cgroup *memcg); /* Writing them here to avoid exposing memcg's inner layout */ -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM #include #include @@ -466,9 +466,9 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg) } EXPORT_SYMBOL(tcp_proto_cgroup); #endif /* CONFIG_INET */ -#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */ +#endif /* CONFIG_MEMCG_KMEM */ -#if defined(CONFIG_INET) && defined(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) +#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM) static void disarm_sock_keys(struct mem_cgroup *memcg) { if (!memcg_proto_activated(&memcg->tcp_mem.cg_proto)) @@ -3085,7 +3085,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) } #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP /* * called from swap_entry_free(). remove record in swap_cgroup and * uncharge "memsw" account. @@ -4518,7 +4518,7 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp, return 0; } -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { return mem_cgroup_sockets_init(memcg, ss); @@ -4608,7 +4608,7 @@ static struct cftype mem_cgroup_files[] = { .read_seq_string = mem_control_numa_stat_show, }, #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP { .name = "memsw.usage_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), @@ -4795,7 +4795,7 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) } EXPORT_SYMBOL(parent_mem_cgroup); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP static void __init enable_swap_cgroup(void) { if (!mem_cgroup_disabled() && really_do_swap_account) @@ -5526,7 +5526,7 @@ struct cgroup_subsys mem_cgroup_subsys = { .__DEPRECATED_clear_css_refs = true, }; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP static int __init enable_swap_account(char *s) { /* consider enabled if no parameter or 1 is given */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index b04ff2d6f73..a6e2141a661 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -128,7 +128,7 @@ static int hwpoison_filter_flags(struct page *p) * can only guarantee that the page either belongs to the memcg tasks, or is * a freed page. */ -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP u64 hwpoison_filter_memcg; EXPORT_SYMBOL_GPL(hwpoison_filter_memcg); static int hwpoison_filter_task(struct page *p) diff --git a/mm/mmzone.c b/mm/mmzone.c index 6830eab5bf0..3cef80f6ac7 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -96,7 +96,7 @@ void lruvec_init(struct lruvec *lruvec, struct zone *zone) for_each_lru(lru) INIT_LIST_HEAD(&lruvec->lists[lru]); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG lruvec->zone = zone; #endif } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index c82ede69bf3..e6c10640e56 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -541,7 +541,7 @@ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); } -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, int order) { diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index eb750f85139..5ddad0c6daa 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -317,7 +317,7 @@ void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat) #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP static DEFINE_MUTEX(swap_cgroup_mutex); struct swap_cgroup_ctrl { diff --git a/mm/vmscan.c b/mm/vmscan.c index 347b3ff2a47..6b1f89a9121 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -133,7 +133,7 @@ long vm_total_pages; /* The total number of pages which the VM controls */ static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG static bool global_reclaim(struct scan_control *sc) { return !sc->target_mem_cgroup; @@ -2142,7 +2142,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, return nr_reclaimed; } -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, gfp_t gfp_mask, bool noswap, diff --git a/net/core/sock.c b/net/core/sock.c index 2676a88f533..a67b06280e4 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -142,7 +142,7 @@ static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { struct proto *proto; diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index ae2ccf2890e..15ca63ec604 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -49,7 +49,7 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o -obj-$(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) += tcp_memcontrol.o +obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 5840c325572..ed7db3f1b6f 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -184,7 +184,7 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, int ret; unsigned long vec[3]; struct net *net = current->nsproxy->net_ns; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM struct mem_cgroup *memcg; #endif @@ -203,7 +203,7 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, if (ret) return ret; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM rcu_read_lock(); memcg = mem_cgroup_from_task(current); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 2fbd9921253..4bc8f6769b5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2633,7 +2633,7 @@ struct proto tcp_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM .init_cgroup = tcp_init_cgroup, .destroy_cgroup = tcp_destroy_cgroup, .proto_cgroup = tcp_proto_cgroup, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 221224e7250..61c7b6d8317 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2015,7 +2015,7 @@ struct proto tcpv6_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM .proto_cgroup = tcp_proto_cgroup, #endif }; -- cgit v1.2.3-70-g09d2 From 567fb435bb7a37afda35902b884562c40756dc45 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Tue, 31 Jul 2012 16:43:07 -0700 Subject: memcg: fix bad behavior in use_hierarchy file I have an application that does the following: * copy the state of all controllers attached to a hierarchy * replicate it as a child of the current level. I would expect writes to the files to mostly succeed, since they are inheriting sane values from parents. But that is not the case for use_hierarchy. If it is set to 0, we succeed ok. If we're set to 1, the value of the file is automatically set to 1 in the children, but if userspace tries to write the very same 1, it will fail. That same situation happens if we set use_hierarchy, create a child, and then try to write 1 again. Now, there is no reason whatsoever for failing to write a value that is already there. It doesn't even match the comments, that states: /* If parent's use_hierarchy is set, we can't make any modifications * in the child subtrees... since we are not changing anything. So test the new value against the one we're storing, and automatically return 0 if we're not proposing a change. Signed-off-by: Glauber Costa Cc: Dhaval Giani Acked-by: Michal Hocko Cc: Kamezawa Hiroyuki Acked-by: Johannes Weiner Cc: Ying Han Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 55a85e1a342..6d3dd54ec42 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3764,6 +3764,10 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, parent_memcg = mem_cgroup_from_cont(parent); cgroup_lock(); + + if (memcg->use_hierarchy == val) + goto out; + /* * If parent's use_hierarchy is set, we can't make any modifications * in the child subtrees. If it is unset, then the change can @@ -3780,6 +3784,8 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, retval = -EBUSY; } else retval = -EINVAL; + +out: cgroup_unlock(); return retval; -- cgit v1.2.3-70-g09d2 From ab2158848775c7918288f2c423d3e4dbbc7d34eb Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Tue, 31 Jul 2012 16:43:09 -0700 Subject: memcg: rename mem_control_xxx to memcg_xxx Replace memory_cgroup_xxx() with memcg_xxx() Signed-off-by: Wanpeng Li Acked-by: Johannes Weiner Acked-by: Michal Hocko Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6d3dd54ec42..b11fb2fe77c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4006,7 +4006,7 @@ static int mem_cgroup_move_charge_write(struct cgroup *cgrp, #endif #ifdef CONFIG_NUMA -static int mem_control_numa_stat_show(struct cgroup *cont, struct cftype *cft, +static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft, struct seq_file *m) { int nid; @@ -4065,7 +4065,7 @@ static inline void mem_cgroup_lru_names_not_uptodate(void) BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); } -static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, +static int memcg_stat_show(struct cgroup *cont, struct cftype *cft, struct seq_file *m) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); @@ -4579,7 +4579,7 @@ static struct cftype mem_cgroup_files[] = { }, { .name = "stat", - .read_seq_string = mem_control_stat_show, + .read_seq_string = memcg_stat_show, }, { .name = "force_empty", @@ -4611,7 +4611,7 @@ static struct cftype mem_cgroup_files[] = { #ifdef CONFIG_NUMA { .name = "numa_stat", - .read_seq_string = mem_control_numa_stat_show, + .read_seq_string = memcg_numa_stat_show, }, #endif #ifdef CONFIG_MEMCG_SWAP -- cgit v1.2.3-70-g09d2 From aaad153e3408a4b8784de4c8446a40e70d57481f Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Tue, 31 Jul 2012 16:43:23 -0700 Subject: mm/memcg: mem_cgroup_relize_xxx_limit can guarantee memcg->res.limit <= memcg->memsw.limit Signed-off-by: Wanpeng Li Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b11fb2fe77c..ac87e79b00d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3416,7 +3416,7 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, /* * Rather than hide all in some function, I do this in * open coded manner. You see what this really does. - * We have to guarantee memcg->res.limit < memcg->memsw.limit. + * We have to guarantee memcg->res.limit <= memcg->memsw.limit. */ mutex_lock(&set_limit_mutex); memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT); @@ -3477,7 +3477,7 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, /* * Rather than hide all in some function, I do this in * open coded manner. You see what this really does. - * We have to guarantee memcg->res.limit < memcg->memsw.limit. + * We have to guarantee memcg->res.limit <= memcg->memsw.limit. */ mutex_lock(&set_limit_mutex); memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT); -- cgit v1.2.3-70-g09d2 From da92c47d069890106484cb6605df701a54d24499 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Tue, 31 Jul 2012 16:43:26 -0700 Subject: mm/memcg: replace inexistence move_lock_page_cgroup() by move_lock_mem_cgroup() in comment Signed-off-by: Wanpeng Li Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ac87e79b00d..4f73c823c59 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1898,7 +1898,7 @@ again: return; /* * If this memory cgroup is not under account moving, we don't - * need to take move_lock_page_cgroup(). Because we already hold + * need to take move_lock_mem_cgroup(). Because we already hold * rcu_read_lock(), any calls to move_account will be delayed until * rcu_read_unlock() if mem_cgroup_stolen() == true. */ @@ -1920,7 +1920,7 @@ void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags) /* * It's guaranteed that pc->mem_cgroup never changes while * lock is held because a routine modifies pc->mem_cgroup - * should take move_lock_page_cgroup(). + * should take move_lock_mem_cgroup(). */ move_unlock_mem_cgroup(pc->mem_cgroup, flags); } -- cgit v1.2.3-70-g09d2 From 9cbb78bb314360a860a8b23723971cb6fcb54176 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 31 Jul 2012 16:43:44 -0700 Subject: mm, memcg: introduce own oom handler to iterate only over its own threads The global oom killer is serialized by the per-zonelist try_set_zonelist_oom() which is used in the page allocator. Concurrent oom kills are thus a rare event and only occur in systems using mempolicies and with a large number of nodes. Memory controller oom kills, however, can frequently be concurrent since there is no serialization once the oom killer is called for oom conditions in several different memcgs in parallel. This creates a massive contention on tasklist_lock since the oom killer requires the readside for the tasklist iteration. If several memcgs are calling the oom killer, this lock can be held for a substantial amount of time, especially if threads continue to enter it as other threads are exiting. Since the exit path grabs the writeside of the lock with irqs disabled in a few different places, this can cause a soft lockup on cpus as a result of tasklist_lock starvation. The kernel lacks unfair writelocks, and successful calls to the oom killer usually result in at least one thread entering the exit path, so an alternative solution is needed. This patch introduces a seperate oom handler for memcgs so that they do not require tasklist_lock for as much time. Instead, it iterates only over the threads attached to the oom memcg and grabs a reference to the selected thread before calling oom_kill_process() to ensure it doesn't prematurely exit. This still requires tasklist_lock for the tasklist dump, iterating children of the selected process, and killing all other threads on the system sharing the same memory as the selected victim. So while this isn't a complete solution to tasklist_lock starvation, it significantly reduces the amount of time that it is held. Acked-by: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Signed-off-by: David Rientjes Cc: Oleg Nesterov Cc: KOSAKI Motohiro Reviewed-by: Sha Zhengju Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 9 ++----- include/linux/oom.h | 16 ++++++++++++ mm/memcontrol.c | 61 +++++++++++++++++++++++++++++++++++++++++++++- mm/oom_kill.c | 48 ++++++++++++------------------------ 4 files changed, 93 insertions(+), 41 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index c0bff8976a6..2a80544aec9 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -180,7 +180,8 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, gfp_t gfp_mask, unsigned long *total_scanned); -u64 mem_cgroup_get_limit(struct mem_cgroup *memcg); +extern void __mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, + int order); void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -364,12 +365,6 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, return 0; } -static inline -u64 mem_cgroup_get_limit(struct mem_cgroup *memcg) -{ - return 0; -} - static inline void mem_cgroup_split_huge_fixup(struct page *head) { } diff --git a/include/linux/oom.h b/include/linux/oom.h index eb9dc14362c..5dc0e384ae9 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -40,17 +40,33 @@ enum oom_constraint { CONSTRAINT_MEMCG, }; +enum oom_scan_t { + OOM_SCAN_OK, /* scan thread and find its badness */ + OOM_SCAN_CONTINUE, /* do not consider thread for oom kill */ + OOM_SCAN_ABORT, /* abort the iteration and return */ + OOM_SCAN_SELECT, /* always select this thread first */ +}; + extern void compare_swap_oom_score_adj(int old_val, int new_val); extern int test_set_oom_score_adj(int new_val); extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); +extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, + unsigned int points, unsigned long totalpages, + struct mem_cgroup *memcg, nodemask_t *nodemask, + const char *message); + extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); +extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task, + unsigned long totalpages, const nodemask_t *nodemask, + bool force_kill); extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, int order); + extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order, nodemask_t *mask, bool force_kill); extern int register_oom_notifier(struct notifier_block *nb); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4f73c823c59..b78972e2f43 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1453,7 +1453,7 @@ static int mem_cgroup_count_children(struct mem_cgroup *memcg) /* * Return the memory (and swap, if configured) limit for a memcg. */ -u64 mem_cgroup_get_limit(struct mem_cgroup *memcg) +static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg) { u64 limit; u64 memsw; @@ -1469,6 +1469,65 @@ u64 mem_cgroup_get_limit(struct mem_cgroup *memcg) return min(limit, memsw); } +void __mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, + int order) +{ + struct mem_cgroup *iter; + unsigned long chosen_points = 0; + unsigned long totalpages; + unsigned int points = 0; + struct task_struct *chosen = NULL; + + totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1; + for_each_mem_cgroup_tree(iter, memcg) { + struct cgroup *cgroup = iter->css.cgroup; + struct cgroup_iter it; + struct task_struct *task; + + cgroup_iter_start(cgroup, &it); + while ((task = cgroup_iter_next(cgroup, &it))) { + switch (oom_scan_process_thread(task, totalpages, NULL, + false)) { + case OOM_SCAN_SELECT: + if (chosen) + put_task_struct(chosen); + chosen = task; + chosen_points = ULONG_MAX; + get_task_struct(chosen); + /* fall through */ + case OOM_SCAN_CONTINUE: + continue; + case OOM_SCAN_ABORT: + cgroup_iter_end(cgroup, &it); + mem_cgroup_iter_break(memcg, iter); + if (chosen) + put_task_struct(chosen); + return; + case OOM_SCAN_OK: + break; + }; + points = oom_badness(task, memcg, NULL, totalpages); + if (points > chosen_points) { + if (chosen) + put_task_struct(chosen); + chosen = task; + chosen_points = points; + get_task_struct(chosen); + } + } + cgroup_iter_end(cgroup, &it); + } + + if (!chosen) + return; + points = chosen_points * 1000 / totalpages; + read_lock(&tasklist_lock); + oom_kill_process(chosen, gfp_mask, order, points, totalpages, memcg, + NULL, "Memory cgroup out of memory"); + read_unlock(&tasklist_lock); + put_task_struct(chosen); +} + static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg, gfp_t gfp_mask, unsigned long flags) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index f8eba9651c0..c0c97aea837 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -288,20 +288,13 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist, } #endif -enum oom_scan_t { - OOM_SCAN_OK, /* scan thread and find its badness */ - OOM_SCAN_CONTINUE, /* do not consider thread for oom kill */ - OOM_SCAN_ABORT, /* abort the iteration and return */ - OOM_SCAN_SELECT, /* always select this thread first */ -}; - -static enum oom_scan_t oom_scan_process_thread(struct task_struct *task, - struct mem_cgroup *memcg, unsigned long totalpages, - const nodemask_t *nodemask, bool force_kill) +enum oom_scan_t oom_scan_process_thread(struct task_struct *task, + unsigned long totalpages, const nodemask_t *nodemask, + bool force_kill) { if (task->exit_state) return OOM_SCAN_CONTINUE; - if (oom_unkillable_task(task, memcg, nodemask)) + if (oom_unkillable_task(task, NULL, nodemask)) return OOM_SCAN_CONTINUE; /* @@ -348,8 +341,8 @@ static enum oom_scan_t oom_scan_process_thread(struct task_struct *task, * (not docbooked, we don't want this one cluttering up the manual) */ static struct task_struct *select_bad_process(unsigned int *ppoints, - unsigned long totalpages, struct mem_cgroup *memcg, - const nodemask_t *nodemask, bool force_kill) + unsigned long totalpages, const nodemask_t *nodemask, + bool force_kill) { struct task_struct *g, *p; struct task_struct *chosen = NULL; @@ -358,7 +351,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, do_each_thread(g, p) { unsigned int points; - switch (oom_scan_process_thread(p, memcg, totalpages, nodemask, + switch (oom_scan_process_thread(p, totalpages, nodemask, force_kill)) { case OOM_SCAN_SELECT: chosen = p; @@ -371,7 +364,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, case OOM_SCAN_OK: break; }; - points = oom_badness(p, memcg, nodemask, totalpages); + points = oom_badness(p, NULL, nodemask, totalpages); if (points > chosen_points) { chosen = p; chosen_points = points; @@ -443,10 +436,10 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, } #define K(x) ((x) << (PAGE_SHIFT-10)) -static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, - unsigned int points, unsigned long totalpages, - struct mem_cgroup *memcg, nodemask_t *nodemask, - const char *message) +void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, + unsigned int points, unsigned long totalpages, + struct mem_cgroup *memcg, nodemask_t *nodemask, + const char *message) { struct task_struct *victim = p; struct task_struct *child; @@ -564,10 +557,6 @@ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, int order) { - unsigned long limit; - unsigned int points = 0; - struct task_struct *p; - /* * If current has a pending SIGKILL, then automatically select it. The * goal is to allow it to allocate so that it may quickly exit and free @@ -579,13 +568,7 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, } check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL); - limit = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1; - read_lock(&tasklist_lock); - p = select_bad_process(&points, limit, memcg, NULL, false); - if (p && PTR_ERR(p) != -1UL) - oom_kill_process(p, gfp_mask, order, points, limit, memcg, NULL, - "Memory cgroup out of memory"); - read_unlock(&tasklist_lock); + __mem_cgroup_out_of_memory(memcg, gfp_mask, order); } #endif @@ -710,7 +693,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, struct task_struct *p; unsigned long totalpages; unsigned long freed = 0; - unsigned int points; + unsigned int uninitialized_var(points); enum oom_constraint constraint = CONSTRAINT_NONE; int killed = 0; @@ -748,8 +731,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, goto out; } - p = select_bad_process(&points, totalpages, NULL, mpol_mask, - force_kill); + p = select_bad_process(&points, totalpages, mpol_mask, force_kill); /* Found nothing?!?! Either we hang forever, or we panic. */ if (!p) { dump_header(NULL, gfp_mask, order, NULL, mpol_mask); -- cgit v1.2.3-70-g09d2 From 6b0c81b3be114a93f79bd4c5639ade5107d77c21 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 31 Jul 2012 16:43:45 -0700 Subject: mm, oom: reduce dependency on tasklist_lock Since exiting tasks require write_lock_irq(&tasklist_lock) several times, try to reduce the amount of time the readside is held for oom kills. This makes the interface with the memcg oom handler more consistent since it now never needs to take tasklist_lock unnecessarily. The only time the oom killer now takes tasklist_lock is when iterating the children of the selected task, everything else is protected by rcu_read_lock(). This requires that a reference to the selected process, p, is grabbed before calling oom_kill_process(). It may release it and grab a reference on another one of p's threads if !p->mm, but it also guarantees that it will release the reference before returning. [hughd@google.com: fix duplicate put_task_struct()] Signed-off-by: David Rientjes Cc: KAMEZAWA Hiroyuki Reviewed-by: Michal Hocko Cc: Oleg Nesterov Cc: KOSAKI Motohiro Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 3 --- mm/oom_kill.c | 41 ++++++++++++++++++++++++++++++----------- 2 files changed, 30 insertions(+), 14 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b78972e2f43..77a29cea5d7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1521,11 +1521,8 @@ void __mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, if (!chosen) return; points = chosen_points * 1000 / totalpages; - read_lock(&tasklist_lock); oom_kill_process(chosen, gfp_mask, order, points, totalpages, memcg, NULL, "Memory cgroup out of memory"); - read_unlock(&tasklist_lock); - put_task_struct(chosen); } static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg, diff --git a/mm/oom_kill.c b/mm/oom_kill.c index c0c97aea837..a3a32ae02e9 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -336,7 +336,7 @@ enum oom_scan_t oom_scan_process_thread(struct task_struct *task, /* * Simple selection loop. We chose the process with the highest - * number of 'points'. We expect the caller will lock the tasklist. + * number of 'points'. * * (not docbooked, we don't want this one cluttering up the manual) */ @@ -348,6 +348,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, struct task_struct *chosen = NULL; unsigned long chosen_points = 0; + rcu_read_lock(); do_each_thread(g, p) { unsigned int points; @@ -360,6 +361,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, case OOM_SCAN_CONTINUE: continue; case OOM_SCAN_ABORT: + rcu_read_unlock(); return ERR_PTR(-1UL); case OOM_SCAN_OK: break; @@ -370,6 +372,9 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, chosen_points = points; } } while_each_thread(g, p); + if (chosen) + get_task_struct(chosen); + rcu_read_unlock(); *ppoints = chosen_points * 1000 / totalpages; return chosen; @@ -385,8 +390,6 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, * are not shown. * State information includes task's pid, uid, tgid, vm size, rss, nr_ptes, * swapents, oom_score_adj value, and name. - * - * Call with tasklist_lock read-locked. */ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemask) { @@ -394,6 +397,7 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas struct task_struct *task; pr_info("[ pid ] uid tgid total_vm rss nr_ptes swapents oom_score_adj name\n"); + rcu_read_lock(); for_each_process(p) { if (oom_unkillable_task(p, memcg, nodemask)) continue; @@ -416,6 +420,7 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas task->signal->oom_score_adj, task->comm); task_unlock(task); } + rcu_read_unlock(); } static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, @@ -436,6 +441,10 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, } #define K(x) ((x) << (PAGE_SHIFT-10)) +/* + * Must be called while holding a reference to p, which will be released upon + * returning. + */ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, unsigned int points, unsigned long totalpages, struct mem_cgroup *memcg, nodemask_t *nodemask, @@ -455,6 +464,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, */ if (p->flags & PF_EXITING) { set_tsk_thread_flag(p, TIF_MEMDIE); + put_task_struct(p); return; } @@ -472,6 +482,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, * parent. This attempts to lose the minimal amount of work done while * still freeing memory. */ + read_lock(&tasklist_lock); do { list_for_each_entry(child, &t->children, sibling) { unsigned int child_points; @@ -484,15 +495,26 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, child_points = oom_badness(child, memcg, nodemask, totalpages); if (child_points > victim_points) { + put_task_struct(victim); victim = child; victim_points = child_points; + get_task_struct(victim); } } } while_each_thread(p, t); + read_unlock(&tasklist_lock); - victim = find_lock_task_mm(victim); - if (!victim) + rcu_read_lock(); + p = find_lock_task_mm(victim); + if (!p) { + rcu_read_unlock(); + put_task_struct(victim); return; + } else if (victim != p) { + get_task_struct(p); + put_task_struct(victim); + victim = p; + } /* mm cannot safely be dereferenced after task_unlock(victim) */ mm = victim->mm; @@ -523,9 +545,11 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, task_unlock(p); do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true); } + rcu_read_unlock(); set_tsk_thread_flag(victim, TIF_MEMDIE); do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true); + put_task_struct(victim); } #undef K @@ -546,9 +570,7 @@ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, if (constraint != CONSTRAINT_NONE) return; } - read_lock(&tasklist_lock); dump_header(NULL, gfp_mask, order, NULL, nodemask); - read_unlock(&tasklist_lock); panic("Out of memory: %s panic_on_oom is enabled\n", sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); } @@ -721,10 +743,10 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL; check_panic_on_oom(constraint, gfp_mask, order, mpol_mask); - read_lock(&tasklist_lock); if (sysctl_oom_kill_allocating_task && current->mm && !oom_unkillable_task(current, NULL, nodemask) && current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) { + get_task_struct(current); oom_kill_process(current, gfp_mask, order, 0, totalpages, NULL, nodemask, "Out of memory (oom_kill_allocating_task)"); @@ -735,7 +757,6 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, /* Found nothing?!?! Either we hang forever, or we panic. */ if (!p) { dump_header(NULL, gfp_mask, order, NULL, mpol_mask); - read_unlock(&tasklist_lock); panic("Out of memory and no killable processes...\n"); } if (PTR_ERR(p) != -1UL) { @@ -744,8 +765,6 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, killed = 1; } out: - read_unlock(&tasklist_lock); - /* * Give the killed threads a good chance of exiting before trying to * allocate memory again. -- cgit v1.2.3-70-g09d2 From 876aafbfd9ba5bb352f1b14622c27f3fe9a99013 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 31 Jul 2012 16:43:48 -0700 Subject: mm, memcg: move all oom handling to memcontrol.c By globally defining check_panic_on_oom(), the memcg oom handler can be moved entirely to mm/memcontrol.c. This removes the ugly #ifdef in the oom killer and cleans up the code. Signed-off-by: David Rientjes Cc: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Cc: Oleg Nesterov Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 -- include/linux/oom.h | 3 +++ mm/memcontrol.c | 15 +++++++++++++-- mm/oom_kill.c | 23 ++--------------------- 4 files changed, 18 insertions(+), 25 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2a80544aec9..5a3ee642363 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -180,8 +180,6 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, gfp_t gfp_mask, unsigned long *total_scanned); -extern void __mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, - int order); void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/include/linux/oom.h b/include/linux/oom.h index 5dc0e384ae9..49a3031fda5 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -61,6 +61,9 @@ extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); +extern void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, + int order, const nodemask_t *nodemask); + extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task, unsigned long totalpages, const nodemask_t *nodemask, bool force_kill); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 77a29cea5d7..0f692a2dbfc 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1469,8 +1469,8 @@ static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg) return min(limit, memsw); } -void __mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, - int order) +void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, + int order) { struct mem_cgroup *iter; unsigned long chosen_points = 0; @@ -1478,6 +1478,17 @@ void __mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, unsigned int points = 0; struct task_struct *chosen = NULL; + /* + * If current has a pending SIGKILL, then automatically select it. The + * goal is to allow it to allocate so that it may quickly exit and free + * its memory. + */ + if (fatal_signal_pending(current)) { + set_thread_flag(TIF_MEMDIE); + return; + } + + check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL); totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1; for_each_mem_cgroup_tree(iter, memcg) { struct cgroup *cgroup = iter->css.cgroup; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index a3a32ae02e9..19860086163 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -556,8 +556,8 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, /* * Determines whether the kernel must panic because of the panic_on_oom sysctl. */ -static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, - int order, const nodemask_t *nodemask) +void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, + int order, const nodemask_t *nodemask) { if (likely(!sysctl_panic_on_oom)) return; @@ -575,25 +575,6 @@ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); } -#ifdef CONFIG_MEMCG -void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, - int order) -{ - /* - * If current has a pending SIGKILL, then automatically select it. The - * goal is to allow it to allocate so that it may quickly exit and free - * its memory. - */ - if (fatal_signal_pending(current)) { - set_thread_flag(TIF_MEMDIE); - return; - } - - check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL); - __mem_cgroup_out_of_memory(memcg, gfp_mask, order); -} -#endif - static BLOCKING_NOTIFIER_HEAD(oom_notify_list); int register_oom_notifier(struct notifier_block *nb) -- cgit v1.2.3-70-g09d2 From 0030f535a5cf9b1841d2088c10a0b2f8f2987460 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 31 Jul 2012 16:45:25 -0700 Subject: mm: memcg: fix compaction/migration failing due to memcg limits Compaction (and page migration in general) can currently be hindered through pages being owned by memory cgroups that are at their limits and unreclaimable. The reason is that the replacement page is being charged against the limit while the page being replaced is also still charged. But this seems unnecessary, given that only one of the two pages will still be in use after migration finishes. This patch changes the memcg migration sequence so that the replacement page is not charged. Whatever page is still in use after successful or failed migration gets to keep the charge of the page that was going to be replaced. The replacement page will still show up temporarily in the rss/cache statistics, this can be fixed in a later patch as it's less urgent. Reported-by: David Rientjes Signed-off-by: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Cc: Hugh Dickins Cc: David Rientjes Cc: Wanpeng Li Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 11 ++++---- mm/memcontrol.c | 67 +++++++++++++++++++++++++--------------------- mm/migrate.c | 11 ++------ 3 files changed, 43 insertions(+), 46 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5a3ee642363..8d9489fdab2 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -98,9 +98,9 @@ int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup) extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg); -extern int -mem_cgroup_prepare_migration(struct page *page, - struct page *newpage, struct mem_cgroup **memcgp, gfp_t gfp_mask); +extern void +mem_cgroup_prepare_migration(struct page *page, struct page *newpage, + struct mem_cgroup **memcgp); extern void mem_cgroup_end_migration(struct mem_cgroup *memcg, struct page *oldpage, struct page *newpage, bool migration_ok); @@ -276,11 +276,10 @@ static inline struct cgroup_subsys_state return NULL; } -static inline int +static inline void mem_cgroup_prepare_migration(struct page *page, struct page *newpage, - struct mem_cgroup **memcgp, gfp_t gfp_mask) + struct mem_cgroup **memcgp) { - return 0; } static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0f692a2dbfc..7eadcdad06f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2976,7 +2976,8 @@ direct_uncharge: * uncharge if !page_mapped(page) */ static struct mem_cgroup * -__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) +__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype, + bool end_migration) { struct mem_cgroup *memcg = NULL; unsigned int nr_pages = 1; @@ -3020,7 +3021,16 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) /* fallthrough */ case MEM_CGROUP_CHARGE_TYPE_DROP: /* See mem_cgroup_prepare_migration() */ - if (page_mapped(page) || PageCgroupMigration(pc)) + if (page_mapped(page)) + goto unlock_out; + /* + * Pages under migration may not be uncharged. But + * end_migration() /must/ be the one uncharging the + * unused post-migration page and so it has to call + * here with the migration bit still set. See the + * res_counter handling below. + */ + if (!end_migration && PageCgroupMigration(pc)) goto unlock_out; break; case MEM_CGROUP_CHARGE_TYPE_SWAPOUT: @@ -3054,7 +3064,12 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) mem_cgroup_swap_statistics(memcg, true); mem_cgroup_get(memcg); } - if (!mem_cgroup_is_root(memcg)) + /* + * Migration does not charge the res_counter for the + * replacement page, so leave it alone when phasing out the + * page that is unused after the migration. + */ + if (!end_migration && !mem_cgroup_is_root(memcg)) mem_cgroup_do_uncharge(memcg, nr_pages, ctype); return memcg; @@ -3070,14 +3085,14 @@ void mem_cgroup_uncharge_page(struct page *page) if (page_mapped(page)) return; VM_BUG_ON(page->mapping && !PageAnon(page)); - __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_ANON); + __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_ANON, false); } void mem_cgroup_uncharge_cache_page(struct page *page) { VM_BUG_ON(page_mapped(page)); VM_BUG_ON(page->mapping); - __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE); + __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE, false); } /* @@ -3141,7 +3156,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) if (!swapout) /* this was a swap cache but the swap is unused ! */ ctype = MEM_CGROUP_CHARGE_TYPE_DROP; - memcg = __mem_cgroup_uncharge_common(page, ctype); + memcg = __mem_cgroup_uncharge_common(page, ctype, false); /* * record memcg information, if swapout && memcg != NULL, @@ -3231,19 +3246,18 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry, * Before starting migration, account PAGE_SIZE to mem_cgroup that the old * page belongs to. */ -int mem_cgroup_prepare_migration(struct page *page, - struct page *newpage, struct mem_cgroup **memcgp, gfp_t gfp_mask) +void mem_cgroup_prepare_migration(struct page *page, struct page *newpage, + struct mem_cgroup **memcgp) { struct mem_cgroup *memcg = NULL; struct page_cgroup *pc; enum charge_type ctype; - int ret = 0; *memcgp = NULL; VM_BUG_ON(PageTransHuge(page)); if (mem_cgroup_disabled()) - return 0; + return; pc = lookup_page_cgroup(page); lock_page_cgroup(pc); @@ -3288,24 +3302,9 @@ int mem_cgroup_prepare_migration(struct page *page, * we return here. */ if (!memcg) - return 0; + return; *memcgp = memcg; - ret = __mem_cgroup_try_charge(NULL, gfp_mask, 1, memcgp, false); - css_put(&memcg->css);/* drop extra refcnt */ - if (ret) { - if (PageAnon(page)) { - lock_page_cgroup(pc); - ClearPageCgroupMigration(pc); - unlock_page_cgroup(pc); - /* - * The old page may be fully unmapped while we kept it. - */ - mem_cgroup_uncharge_page(page); - } - /* we'll need to revisit this error code (we have -EINTR) */ - return -ENOMEM; - } /* * We charge new page before it's used/mapped. So, even if unlock_page() * is called before end_migration, we can catch all events on this new @@ -3318,8 +3317,12 @@ int mem_cgroup_prepare_migration(struct page *page, ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; else ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM; + /* + * The page is committed to the memcg, but it's not actually + * charged to the res_counter since we plan on replacing the + * old one and only one page is going to be left afterwards. + */ __mem_cgroup_commit_charge(memcg, newpage, 1, ctype, false); - return ret; } /* remove redundant charge if migration failed*/ @@ -3341,6 +3344,12 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg, used = newpage; unused = oldpage; } + anon = PageAnon(used); + __mem_cgroup_uncharge_common(unused, + anon ? MEM_CGROUP_CHARGE_TYPE_ANON + : MEM_CGROUP_CHARGE_TYPE_CACHE, + true); + css_put(&memcg->css); /* * We disallowed uncharge of pages under migration because mapcount * of the page goes down to zero, temporarly. @@ -3350,10 +3359,6 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg, lock_page_cgroup(pc); ClearPageCgroupMigration(pc); unlock_page_cgroup(pc); - anon = PageAnon(used); - __mem_cgroup_uncharge_common(unused, - anon ? MEM_CGROUP_CHARGE_TYPE_ANON - : MEM_CGROUP_CHARGE_TYPE_CACHE); /* * If a page is a file cache, radix-tree replacement is very atomic diff --git a/mm/migrate.c b/mm/migrate.c index 6c37c51565e..77ed2d77370 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -683,7 +683,6 @@ static int __unmap_and_move(struct page *page, struct page *newpage, { int rc = -EAGAIN; int remap_swapcache = 1; - int charge = 0; struct mem_cgroup *mem; struct anon_vma *anon_vma = NULL; @@ -725,12 +724,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, } /* charge against new page */ - charge = mem_cgroup_prepare_migration(page, newpage, &mem, GFP_KERNEL); - if (charge == -ENOMEM) { - rc = -ENOMEM; - goto unlock; - } - BUG_ON(charge); + mem_cgroup_prepare_migration(page, newpage, &mem); if (PageWriteback(page)) { /* @@ -820,8 +814,7 @@ skip_unmap: put_anon_vma(anon_vma); uncharge: - if (!charge) - mem_cgroup_end_migration(mem, page, newpage, rc == 0); + mem_cgroup_end_migration(mem, page, newpage, rc == 0); unlock: unlock_page(page); out: -- cgit v1.2.3-70-g09d2 From 0c59b89c81eab7fe7dcf08f2252ae22a6c081ce8 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 31 Jul 2012 16:45:31 -0700 Subject: mm: memcg: push down PageSwapCache check into uncharge entry functions Not all uncharge paths need to check if the page is swapcache, some of them can know for sure. Push down the check into all callsites of uncharge_common() so that the patch that removes some of them is more obvious. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: David Rientjes Cc: Hugh Dickins Cc: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Cc: Wanpeng Li Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7eadcdad06f..87c2ec49b48 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2987,8 +2987,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype, if (mem_cgroup_disabled()) return NULL; - if (PageSwapCache(page)) - return NULL; + VM_BUG_ON(PageSwapCache(page)); if (PageTransHuge(page)) { nr_pages <<= compound_order(page); @@ -3085,6 +3084,8 @@ void mem_cgroup_uncharge_page(struct page *page) if (page_mapped(page)) return; VM_BUG_ON(page->mapping && !PageAnon(page)); + if (PageSwapCache(page)) + return; __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_ANON, false); } @@ -3092,6 +3093,8 @@ void mem_cgroup_uncharge_cache_page(struct page *page) { VM_BUG_ON(page_mapped(page)); VM_BUG_ON(page->mapping); + if (PageSwapCache(page)) + return; __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE, false); } @@ -3156,6 +3159,8 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) if (!swapout) /* this was a swap cache but the swap is unused ! */ ctype = MEM_CGROUP_CHARGE_TYPE_DROP; + if (PageSwapCache(page)) + return; memcg = __mem_cgroup_uncharge_common(page, ctype, false); /* @@ -3345,10 +3350,11 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg, unused = oldpage; } anon = PageAnon(used); - __mem_cgroup_uncharge_common(unused, - anon ? MEM_CGROUP_CHARGE_TYPE_ANON - : MEM_CGROUP_CHARGE_TYPE_CACHE, - true); + if (!PageSwapCache(unused)) + __mem_cgroup_uncharge_common(unused, + anon ? MEM_CGROUP_CHARGE_TYPE_ANON + : MEM_CGROUP_CHARGE_TYPE_CACHE, + true); css_put(&memcg->css); /* * We disallowed uncharge of pages under migration because mapcount -- cgit v1.2.3-70-g09d2 From 7d188958bb64708577aa77e6b1ad68abbf0480f5 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 31 Jul 2012 16:45:34 -0700 Subject: mm: memcg: only check for PageSwapCache when uncharging anon Only anon pages that are uncharged at the time of the last page table mapping vanishing may be in swapcache. When shmem pages, file pages, swap-freed anon pages, or just migrated pages are uncharged, they are known for sure to be not in swapcache. Signed-off-by: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Cc: David Rientjes Cc: Hugh Dickins Cc: Johannes Weiner Cc: Wanpeng Li Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 87c2ec49b48..29bc4400378 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3093,8 +3093,6 @@ void mem_cgroup_uncharge_cache_page(struct page *page) { VM_BUG_ON(page_mapped(page)); VM_BUG_ON(page->mapping); - if (PageSwapCache(page)) - return; __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE, false); } @@ -3159,8 +3157,6 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) if (!swapout) /* this was a swap cache but the swap is unused ! */ ctype = MEM_CGROUP_CHARGE_TYPE_DROP; - if (PageSwapCache(page)) - return; memcg = __mem_cgroup_uncharge_common(page, ctype, false); /* @@ -3350,11 +3346,10 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg, unused = oldpage; } anon = PageAnon(used); - if (!PageSwapCache(unused)) - __mem_cgroup_uncharge_common(unused, - anon ? MEM_CGROUP_CHARGE_TYPE_ANON - : MEM_CGROUP_CHARGE_TYPE_CACHE, - true); + __mem_cgroup_uncharge_common(unused, + anon ? MEM_CGROUP_CHARGE_TYPE_ANON + : MEM_CGROUP_CHARGE_TYPE_CACHE, + true); css_put(&memcg->css); /* * We disallowed uncharge of pages under migration because mapcount -- cgit v1.2.3-70-g09d2 From 827a03d22e776ff7838b5b2780b71092e0b9de1e Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 31 Jul 2012 16:45:36 -0700 Subject: mm: memcg: move swapin charge functions above callsites Charging cache pages may require swapin in the shmem case. Save the forward declaration and just move the swapin functions above the cache charging functions. Signed-off-by: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Cc: David Rientjes Cc: Hugh Dickins Cc: Johannes Weiner Cc: Wanpeng Li Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 68 +++++++++++++++++++++++++++------------------------------ 1 file changed, 32 insertions(+), 36 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 29bc4400378..3be1afab852 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2796,37 +2796,6 @@ int mem_cgroup_newpage_charge(struct page *page, MEM_CGROUP_CHARGE_TYPE_ANON); } -static void -__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, - enum charge_type ctype); - -int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask) -{ - struct mem_cgroup *memcg = NULL; - enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE; - int ret; - - if (mem_cgroup_disabled()) - return 0; - if (PageCompound(page)) - return 0; - - if (unlikely(!mm)) - mm = &init_mm; - if (!page_is_file_cache(page)) - type = MEM_CGROUP_CHARGE_TYPE_SHMEM; - - if (!PageSwapCache(page)) - ret = mem_cgroup_charge_common(page, mm, gfp_mask, type); - else { /* page is swapcache/shmem */ - ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &memcg); - if (!ret) - __mem_cgroup_commit_charge_swapin(page, memcg, type); - } - return ret; -} - /* * While swap-in, try_charge -> commit or cancel, the page is locked. * And when try_charge() successfully returns, one refcnt to memcg without @@ -2873,6 +2842,15 @@ charge_cur_mm: return ret; } +void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg) +{ + if (mem_cgroup_disabled()) + return; + if (!memcg) + return; + __mem_cgroup_cancel_charge(memcg, 1); +} + static void __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg, enum charge_type ctype) @@ -2910,13 +2888,31 @@ void mem_cgroup_commit_charge_swapin(struct page *page, MEM_CGROUP_CHARGE_TYPE_ANON); } -void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg) +int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask) { + struct mem_cgroup *memcg = NULL; + enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE; + int ret; + if (mem_cgroup_disabled()) - return; - if (!memcg) - return; - __mem_cgroup_cancel_charge(memcg, 1); + return 0; + if (PageCompound(page)) + return 0; + + if (unlikely(!mm)) + mm = &init_mm; + if (!page_is_file_cache(page)) + type = MEM_CGROUP_CHARGE_TYPE_SHMEM; + + if (!PageSwapCache(page)) + ret = mem_cgroup_charge_common(page, mm, gfp_mask, type); + else { /* page is swapcache/shmem */ + ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &memcg); + if (!ret) + __mem_cgroup_commit_charge_swapin(page, memcg, type); + } + return ret; } static void mem_cgroup_do_uncharge(struct mem_cgroup *memcg, -- cgit v1.2.3-70-g09d2 From 62ba7442c8e286b6dd68fe82a3cc85c9414d909b Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 31 Jul 2012 16:45:39 -0700 Subject: mm: memcg: remove unneeded shmem charge type shmem page charges have not needed a separate charge type to tell them from regular file pages since 08e552c ("memcg: synchronized LRU"). Signed-off-by: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Cc: David Rientjes Cc: Hugh Dickins Cc: Johannes Weiner Cc: Wanpeng Li Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3be1afab852..17a79e5ed68 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -379,7 +379,6 @@ static bool move_file(void) enum charge_type { MEM_CGROUP_CHARGE_TYPE_CACHE = 0, MEM_CGROUP_CHARGE_TYPE_ANON, - MEM_CGROUP_CHARGE_TYPE_SHMEM, /* used by page migration of shmem */ MEM_CGROUP_CHARGE_TYPE_SWAPOUT, /* for accounting swapcache */ MEM_CGROUP_CHARGE_TYPE_DROP, /* a page was unused swap cache */ NR_CHARGE_TYPE, @@ -2902,8 +2901,6 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, if (unlikely(!mm)) mm = &init_mm; - if (!page_is_file_cache(page)) - type = MEM_CGROUP_CHARGE_TYPE_SHMEM; if (!PageSwapCache(page)) ret = mem_cgroup_charge_common(page, mm, gfp_mask, type); @@ -3310,10 +3307,8 @@ void mem_cgroup_prepare_migration(struct page *page, struct page *newpage, */ if (PageAnon(page)) ctype = MEM_CGROUP_CHARGE_TYPE_ANON; - else if (page_is_file_cache(page)) - ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; else - ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM; + ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; /* * The page is committed to the memcg, but it's not actually * charged to the res_counter since we plan on replacing the @@ -3407,10 +3402,6 @@ void mem_cgroup_replace_page_cache(struct page *oldpage, */ if (!memcg) return; - - if (PageSwapBacked(oldpage)) - type = MEM_CGROUP_CHARGE_TYPE_SHMEM; - /* * Even if newpage->mapping was NULL before starting replacement, * the newpage may be on LRU(or pagevec for LRU) already. We lock -- cgit v1.2.3-70-g09d2 From 24467cacc03cf8b156d4c6786697e5e5d13c9321 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 31 Jul 2012 16:45:40 -0700 Subject: mm: memcg: remove needless !mm fixup to init_mm when charging It does not matter to __mem_cgroup_try_charge() if the passed mm is NULL or init_mm, it will charge the root memcg in either case. Also fix up the comment in __mem_cgroup_try_charge() that claimed the init_mm would be charged when no mm was passed. It's not really incorrect, but confusing. Clarify that the root memcg is charged in this case. Signed-off-by: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Cc: David Rientjes Cc: Hugh Dickins Cc: Johannes Weiner Cc: Wanpeng Li Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 17a79e5ed68..10b370345a5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2333,7 +2333,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, * We always charge the cgroup the mm_struct belongs to. * The mm_struct's mem_cgroup changes on task migration if the * thread group leader migrates. It's possible that mm is not - * set, if so charge the init_mm (happens for pagecache usage). + * set, if so charge the root memcg (happens for pagecache usage). */ if (!*ptr && !mm) *ptr = root_mem_cgroup; @@ -2833,8 +2833,6 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, ret = 0; return ret; charge_cur_mm: - if (unlikely(!mm)) - mm = &init_mm; ret = __mem_cgroup_try_charge(mm, mask, 1, memcgp, true); if (ret == -EINTR) ret = 0; @@ -2899,9 +2897,6 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, if (PageCompound(page)) return 0; - if (unlikely(!mm)) - mm = &init_mm; - if (!PageSwapCache(page)) ret = mem_cgroup_charge_common(page, mm, gfp_mask, type); else { /* page is swapcache/shmem */ -- cgit v1.2.3-70-g09d2 From 0435a2fdcb50f8e53a67e98c27708e5d9396b71a Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 31 Jul 2012 16:45:43 -0700 Subject: mm: memcg: split swapin charge function into private and public part When shmem is charged upon swapin, it does not need to check twice whether the memory controller is enabled. Also, shmem pages do not have to be checked for everything that regular anon pages have to be checked for, so let shmem use the internal version directly and allow future patches to move around checks that are only required when swapping in anon pages. Signed-off-by: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Cc: David Rientjes Cc: Hugh Dickins Cc: Johannes Weiner Cc: Wanpeng Li Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 10b370345a5..4cc962d566c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2801,18 +2801,14 @@ int mem_cgroup_newpage_charge(struct page *page, * struct page_cgroup is acquired. This refcnt will be consumed by * "commit()" or removed by "cancel()" */ -int mem_cgroup_try_charge_swapin(struct mm_struct *mm, - struct page *page, - gfp_t mask, struct mem_cgroup **memcgp) +static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm, + struct page *page, + gfp_t mask, + struct mem_cgroup **memcgp) { struct mem_cgroup *memcg; int ret; - *memcgp = NULL; - - if (mem_cgroup_disabled()) - return 0; - if (!do_swap_account) goto charge_cur_mm; /* @@ -2839,6 +2835,15 @@ charge_cur_mm: return ret; } +int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page, + gfp_t gfp_mask, struct mem_cgroup **memcgp) +{ + *memcgp = NULL; + if (mem_cgroup_disabled()) + return 0; + return __mem_cgroup_try_charge_swapin(mm, page, gfp_mask, memcgp); +} + void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) @@ -2900,7 +2905,8 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, if (!PageSwapCache(page)) ret = mem_cgroup_charge_common(page, mm, gfp_mask, type); else { /* page is swapcache/shmem */ - ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &memcg); + ret = __mem_cgroup_try_charge_swapin(mm, page, + gfp_mask, &memcg); if (!ret) __mem_cgroup_commit_charge_swapin(page, memcg, type); } -- cgit v1.2.3-70-g09d2 From 90deb78839faedd194b65d419dbd9cba981e1922 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 31 Jul 2012 16:45:47 -0700 Subject: mm: memcg: only check swap cache pages for repeated charging Only anon and shmem pages in the swap cache are attempted to be charged multiple times, from every swap pte fault or from shmem_unuse(). No other pages require checking PageCgroupUsed(). Charging pages in the swap cache is also serialized by the page lock, and since both the try_charge and commit_charge are called under the same page lock section, the PageCgroupUsed() check might as well happen before the counter charging, let alone reclaim. Signed-off-by: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Cc: David Rientjes Cc: Hugh Dickins Cc: Johannes Weiner Cc: Wanpeng Li Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4cc962d566c..1a2020d72ca 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2538,11 +2538,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, bool anon; lock_page_cgroup(pc); - if (unlikely(PageCgroupUsed(pc))) { - unlock_page_cgroup(pc); - __mem_cgroup_cancel_charge(memcg, nr_pages); - return; - } + VM_BUG_ON(PageCgroupUsed(pc)); /* * we don't need page_cgroup_lock about tail pages, becase they are not * accessed by any other context at this point. @@ -2807,8 +2803,19 @@ static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct mem_cgroup **memcgp) { struct mem_cgroup *memcg; + struct page_cgroup *pc; int ret; + pc = lookup_page_cgroup(page); + /* + * 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 + * in turn serializes uncharging. + */ + if (PageCgroupUsed(pc)) + return 0; if (!do_swap_account) goto charge_cur_mm; /* -- cgit v1.2.3-70-g09d2 From bdf4f4d2161a795b9323855a81a047bd68f16202 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 31 Jul 2012 16:45:50 -0700 Subject: mm: memcg: only check anon swapin page charges for swap cache shmem knows for sure that the page is in swap cache when attempting to charge a page, because the cache charge entry function has a check for it. Only anon pages may be removed from swap cache already when trying to charge their swapin. Adjust the comment, though: '4969c11 mm: fix swapin race condition' added a stable PageSwapCache check under the page lock in the do_swap_page() before calling the memory controller, so it's unuse_pte()'s pte_same() that may fail. Signed-off-by: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Cc: David Rientjes Cc: Hugh Dickins Cc: Johannes Weiner Cc: Wanpeng Li Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1a2020d72ca..b06833f2b89 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2818,14 +2818,6 @@ static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm, return 0; if (!do_swap_account) goto charge_cur_mm; - /* - * A racing thread's fault, or swapoff, may have already updated - * the pte, and even removed page from swap cache: in those cases - * do_swap_page()'s pte_same() test will fail; but there's also a - * KSM case which does need to charge the page. - */ - if (!PageSwapCache(page)) - goto charge_cur_mm; memcg = try_get_mem_cgroup_from_page(page); if (!memcg) goto charge_cur_mm; @@ -2848,6 +2840,20 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page, *memcgp = NULL; if (mem_cgroup_disabled()) return 0; + /* + * A racing thread's fault, or swapoff, may have already + * updated the pte, and even removed page from swap cache: in + * those cases unuse_pte()'s pte_same() test will fail; but + * there's also a KSM case which does need to charge the page. + */ + if (!PageSwapCache(page)) { + int ret; + + ret = __mem_cgroup_try_charge(mm, gfp_mask, 1, memcgp, true); + if (ret == -EINTR) + ret = 0; + return ret; + } return __mem_cgroup_try_charge_swapin(mm, page, gfp_mask, memcgp); } -- cgit v1.2.3-70-g09d2 From b214514592d2dcb0b9d14ee8dd14f3699e3b0a84 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Tue, 31 Jul 2012 16:46:01 -0700 Subject: memcg: add mem_cgroup_from_css() helper Add a mem_cgroup_from_css() helper to replace open-coded invokations of container_of(). To clarify the code and to add a little more type safety. [akpm@linux-foundation.org: fix extensive breakage] Signed-off-by: Wanpeng Li Acked-by: Michal Hocko Cc: Johannes Weiner Cc: KAMEZAWA Hiroyuki Cc: Gavin Shan Cc: Wanpeng Li Cc: Gavin Shan Cc: Johannes Weiner Cc: KAMEZAWA Hiroyuki Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b06833f2b89..795e525afab 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -405,6 +405,12 @@ enum charge_type { static void mem_cgroup_get(struct mem_cgroup *memcg); static void mem_cgroup_put(struct mem_cgroup *memcg); +static inline +struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s) +{ + return container_of(s, struct mem_cgroup, css); +} + /* Writing them here to avoid exposing memcg's inner layout */ #ifdef CONFIG_MEMCG_KMEM #include @@ -862,9 +868,8 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) { - return container_of(cgroup_subsys_state(cont, - mem_cgroup_subsys_id), struct mem_cgroup, - css); + return mem_cgroup_from_css( + cgroup_subsys_state(cont, mem_cgroup_subsys_id)); } struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) @@ -877,8 +882,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) if (unlikely(!p)) return NULL; - return container_of(task_subsys_state(p, mem_cgroup_subsys_id), - struct mem_cgroup, css); + return mem_cgroup_from_css(task_subsys_state(p, mem_cgroup_subsys_id)); } struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) @@ -964,8 +968,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, css = css_get_next(&mem_cgroup_subsys, id + 1, &root->css, &id); if (css) { if (css == &root->css || css_tryget(css)) - memcg = container_of(css, - struct mem_cgroup, css); + memcg = mem_cgroup_from_css(css); } else id = 0; rcu_read_unlock(); @@ -2494,7 +2497,7 @@ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) css = css_lookup(&mem_cgroup_subsys, id); if (!css) return NULL; - return container_of(css, struct mem_cgroup, css); + return mem_cgroup_from_css(css); } struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) -- cgit v1.2.3-70-g09d2