From 3e32cb2e0a12b6915056ff04601cf1bb9b44f967 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 10 Dec 2014 15:42:31 -0800 Subject: mm: memcontrol: lockless page counters Memory is internally accounted in bytes, using spinlock-protected 64-bit counters, even though the smallest accounting delta is a page. The counter interface is also convoluted and does too many things. Introduce a new lockless word-sized page counter API, then change all memory accounting over to it. The translation from and to bytes then only happens when interfacing with userspace. The removed locking overhead is noticable when scaling beyond the per-cpu charge caches - on a 4-socket machine with 144-threads, the following test shows the performance differences of 288 memcgs concurrently running a page fault benchmark: vanilla: 18631648.500498 task-clock (msec) # 140.643 CPUs utilized ( +- 0.33% ) 1,380,638 context-switches # 0.074 K/sec ( +- 0.75% ) 24,390 cpu-migrations # 0.001 K/sec ( +- 8.44% ) 1,843,305,768 page-faults # 0.099 M/sec ( +- 0.00% ) 50,134,994,088,218 cycles # 2.691 GHz ( +- 0.33% ) stalled-cycles-frontend stalled-cycles-backend 8,049,712,224,651 instructions # 0.16 insns per cycle ( +- 0.04% ) 1,586,970,584,979 branches # 85.176 M/sec ( +- 0.05% ) 1,724,989,949 branch-misses # 0.11% of all branches ( +- 0.48% ) 132.474343877 seconds time elapsed ( +- 0.21% ) lockless: 12195979.037525 task-clock (msec) # 133.480 CPUs utilized ( +- 0.18% ) 832,850 context-switches # 0.068 K/sec ( +- 0.54% ) 15,624 cpu-migrations # 0.001 K/sec ( +- 10.17% ) 1,843,304,774 page-faults # 0.151 M/sec ( +- 0.00% ) 32,811,216,801,141 cycles # 2.690 GHz ( +- 0.18% ) stalled-cycles-frontend stalled-cycles-backend 9,999,265,091,727 instructions # 0.30 insns per cycle ( +- 0.10% ) 2,076,759,325,203 branches # 170.282 M/sec ( +- 0.12% ) 1,656,917,214 branch-misses # 0.08% of all branches ( +- 0.55% ) 91.369330729 seconds time elapsed ( +- 0.45% ) On top of improved scalability, this also gets rid of the icky long long types in the very heart of memcg, which is great for 32 bit and also makes the code a lot more readable. Notable differences between the old and new API: - res_counter_charge() and res_counter_charge_nofail() become page_counter_try_charge() and page_counter_charge() resp. to match the more common kernel naming scheme of try_do()/do() - res_counter_uncharge_until() is only ever used to cancel a local counter and never to uncharge bigger segments of a hierarchy, so it's replaced by the simpler page_counter_cancel() - res_counter_set_limit() is replaced by page_counter_limit(), which expects its callers to serialize against themselves - res_counter_memparse_write_strategy() is replaced by page_counter_limit(), which rounds down to the nearest page size - rather than up. This is more reasonable for explicitely requested hard upper limits. - to keep charging light-weight, page_counter_try_charge() charges speculatively, only to roll back if the result exceeds the limit. Because of this, a failing bigger charge can temporarily lock out smaller charges that would otherwise succeed. The error is bounded to the difference between the smallest and the biggest possible charge size, so for memcg, this means that a failing THP charge can send base page charges into reclaim upto 2MB (4MB) before the limit would have been reached. This should be acceptable. [akpm@linux-foundation.org: add includes for WARN_ON_ONCE and memparse] [akpm@linux-foundation.org: add includes for WARN_ON_ONCE, memparse, strncmp, and PAGE_SIZE] Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Acked-by: Vladimir Davydov Cc: Tejun Heo Cc: David Rientjes Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 ++--- include/linux/page_counter.h | 51 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+), 3 deletions(-) create mode 100644 include/linux/page_counter.h (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6b75640ef5ab..ea007615e8f9 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -447,9 +447,8 @@ memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order) /* * __GFP_NOFAIL allocations will move on even if charging is not * possible. Therefore we don't even try, and have this allocation - * unaccounted. We could in theory charge it with - * res_counter_charge_nofail, but we hope those allocations are rare, - * and won't be worth the trouble. + * unaccounted. We could in theory charge it forcibly, but we hope + * those allocations are rare, and won't be worth the trouble. */ if (gfp & __GFP_NOFAIL) return true; diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h new file mode 100644 index 000000000000..7cce3be99ff3 --- /dev/null +++ b/include/linux/page_counter.h @@ -0,0 +1,51 @@ +#ifndef _LINUX_PAGE_COUNTER_H +#define _LINUX_PAGE_COUNTER_H + +#include +#include +#include + +struct page_counter { + atomic_long_t count; + unsigned long limit; + struct page_counter *parent; + + /* legacy */ + unsigned long watermark; + unsigned long failcnt; +}; + +#if BITS_PER_LONG == 32 +#define PAGE_COUNTER_MAX LONG_MAX +#else +#define PAGE_COUNTER_MAX (LONG_MAX / PAGE_SIZE) +#endif + +static inline void page_counter_init(struct page_counter *counter, + struct page_counter *parent) +{ + atomic_long_set(&counter->count, 0); + counter->limit = PAGE_COUNTER_MAX; + counter->parent = parent; +} + +static inline unsigned long page_counter_read(struct page_counter *counter) +{ + return atomic_long_read(&counter->count); +} + +int page_counter_cancel(struct page_counter *counter, unsigned long nr_pages); +void page_counter_charge(struct page_counter *counter, unsigned long nr_pages); +int page_counter_try_charge(struct page_counter *counter, + unsigned long nr_pages, + struct page_counter **fail); +int page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages); +int page_counter_limit(struct page_counter *counter, unsigned long limit); +int page_counter_memparse(const char *buf, unsigned long *nr_pages); + +static inline void page_counter_reset_watermark(struct page_counter *counter) +{ + counter->watermark = page_counter_read(counter); +} + +#endif /* _LINUX_PAGE_COUNTER_H */ -- cgit v1.2.3 From 71f87bee38edddb21d97895fa938744cf3f477bb Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 10 Dec 2014 15:42:34 -0800 Subject: mm: hugetlb_cgroup: convert to lockless page counters Abandon the spinlock-protected byte counters in favor of the unlocked page counters in the hugetlb controller as well. Signed-off-by: Johannes Weiner Reviewed-by: Vladimir Davydov Acked-by: Michal Hocko Cc: Tejun Heo Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb_cgroup.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index 0129f89cf98d..bcc853eccc85 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -16,7 +16,6 @@ #define _LINUX_HUGETLB_CGROUP_H #include -#include struct hugetlb_cgroup; /* -- cgit v1.2.3 From 5b1efc027c0b51ca3e76f4e00c83358f8349f543 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 10 Dec 2014 15:42:37 -0800 Subject: kernel: res_counter: remove the unused API All memory accounting and limiting has been switched over to the lockless page counters. Bye, res_counter! [akpm@linux-foundation.org: update Documentation/cgroups/memory.txt] [mhocko@suse.cz: ditch the last remainings of res_counter] Signed-off-by: Johannes Weiner Acked-by: Vladimir Davydov Acked-by: Michal Hocko Cc: Tejun Heo Cc: David Rientjes Cc: Paul Bolle Signed-off-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/res_counter.h | 223 -------------------------------------------- 1 file changed, 223 deletions(-) delete mode 100644 include/linux/res_counter.h (limited to 'include/linux') diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h deleted file mode 100644 index 56b7bc32db4f..000000000000 --- a/include/linux/res_counter.h +++ /dev/null @@ -1,223 +0,0 @@ -#ifndef __RES_COUNTER_H__ -#define __RES_COUNTER_H__ - -/* - * Resource Counters - * Contain common data types and routines for resource accounting - * - * Copyright 2007 OpenVZ SWsoft Inc - * - * Author: Pavel Emelianov - * - * See Documentation/cgroups/resource_counter.txt for more - * info about what this counter is. - */ - -#include -#include - -/* - * The core object. the cgroup that wishes to account for some - * resource may include this counter into its structures and use - * the helpers described beyond - */ - -struct res_counter { - /* - * the current resource consumption level - */ - unsigned long long usage; - /* - * the maximal value of the usage from the counter creation - */ - unsigned long long max_usage; - /* - * the limit that usage cannot exceed - */ - unsigned long long limit; - /* - * the limit that usage can be exceed - */ - unsigned long long soft_limit; - /* - * the number of unsuccessful attempts to consume the resource - */ - unsigned long long failcnt; - /* - * the lock to protect all of the above. - * the routines below consider this to be IRQ-safe - */ - spinlock_t lock; - /* - * Parent counter, used for hierarchial resource accounting - */ - struct res_counter *parent; -}; - -#define RES_COUNTER_MAX ULLONG_MAX - -/** - * Helpers to interact with userspace - * res_counter_read_u64() - returns the value of the specified member. - * res_counter_read/_write - put/get the specified fields from the - * res_counter struct to/from the user - * - * @counter: the counter in question - * @member: the field to work with (see RES_xxx below) - * @buf: the buffer to opeate on,... - * @nbytes: its size... - * @pos: and the offset. - */ - -u64 res_counter_read_u64(struct res_counter *counter, int member); - -ssize_t res_counter_read(struct res_counter *counter, int member, - const char __user *buf, size_t nbytes, loff_t *pos, - int (*read_strategy)(unsigned long long val, char *s)); - -int res_counter_memparse_write_strategy(const char *buf, - unsigned long long *res); - -/* - * the field descriptors. one for each member of res_counter - */ - -enum { - RES_USAGE, - RES_MAX_USAGE, - RES_LIMIT, - RES_FAILCNT, - RES_SOFT_LIMIT, -}; - -/* - * helpers for accounting - */ - -void res_counter_init(struct res_counter *counter, struct res_counter *parent); - -/* - * charge - try to consume more resource. - * - * @counter: the counter - * @val: the amount of the resource. each controller defines its own - * units, e.g. numbers, bytes, Kbytes, etc - * - * returns 0 on success and <0 if the counter->usage will exceed the - * counter->limit - * - * charge_nofail works the same, except that it charges the resource - * counter unconditionally, and returns < 0 if the after the current - * charge we are over limit. - */ - -int __must_check res_counter_charge(struct res_counter *counter, - unsigned long val, struct res_counter **limit_fail_at); -int res_counter_charge_nofail(struct res_counter *counter, - unsigned long val, struct res_counter **limit_fail_at); - -/* - * uncharge - tell that some portion of the resource is released - * - * @counter: the counter - * @val: the amount of the resource - * - * these calls check for usage underflow and show a warning on the console - * - * returns the total charges still present in @counter. - */ - -u64 res_counter_uncharge(struct res_counter *counter, unsigned long val); - -u64 res_counter_uncharge_until(struct res_counter *counter, - struct res_counter *top, - unsigned long val); -/** - * res_counter_margin - calculate chargeable space of a counter - * @cnt: the counter - * - * Returns the difference between the hard limit and the current usage - * of resource counter @cnt. - */ -static inline unsigned long long res_counter_margin(struct res_counter *cnt) -{ - unsigned long long margin; - unsigned long flags; - - spin_lock_irqsave(&cnt->lock, flags); - if (cnt->limit > cnt->usage) - margin = cnt->limit - cnt->usage; - else - margin = 0; - spin_unlock_irqrestore(&cnt->lock, flags); - return margin; -} - -/** - * Get the difference between the usage and the soft limit - * @cnt: The counter - * - * Returns 0 if usage is less than or equal to soft limit - * The difference between usage and soft limit, otherwise. - */ -static inline unsigned long long -res_counter_soft_limit_excess(struct res_counter *cnt) -{ - unsigned long long excess; - unsigned long flags; - - spin_lock_irqsave(&cnt->lock, flags); - if (cnt->usage <= cnt->soft_limit) - excess = 0; - else - excess = cnt->usage - cnt->soft_limit; - spin_unlock_irqrestore(&cnt->lock, flags); - return excess; -} - -static inline void res_counter_reset_max(struct res_counter *cnt) -{ - unsigned long flags; - - spin_lock_irqsave(&cnt->lock, flags); - cnt->max_usage = cnt->usage; - spin_unlock_irqrestore(&cnt->lock, flags); -} - -static inline void res_counter_reset_failcnt(struct res_counter *cnt) -{ - unsigned long flags; - - spin_lock_irqsave(&cnt->lock, flags); - cnt->failcnt = 0; - spin_unlock_irqrestore(&cnt->lock, flags); -} - -static inline int res_counter_set_limit(struct res_counter *cnt, - unsigned long long limit) -{ - unsigned long flags; - int ret = -EBUSY; - - spin_lock_irqsave(&cnt->lock, flags); - if (cnt->usage <= limit) { - cnt->limit = limit; - ret = 0; - } - spin_unlock_irqrestore(&cnt->lock, flags); - return ret; -} - -static inline int -res_counter_set_soft_limit(struct res_counter *cnt, - unsigned long long soft_limit) -{ - unsigned long flags; - - spin_lock_irqsave(&cnt->lock, flags); - cnt->soft_limit = soft_limit; - spin_unlock_irqrestore(&cnt->lock, flags); - return 0; -} - -#endif -- cgit v1.2.3 From e8ea14cc6eadfe2ea63e9989e16e62625a2619f8 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 10 Dec 2014 15:42:42 -0800 Subject: mm: memcontrol: take a css reference for each charged page Charges currently pin the css indirectly by playing tricks during css_offline(): user pages stall the offlining process until all of them have been reparented, whereas kmemcg acquires a keep-alive reference if outstanding kernel pages are detected at that point. In preparation for removing all this complexity, make the pinning explicit and acquire a css references for every charged page. Signed-off-by: Johannes Weiner Reviewed-by: Vladimir Davydov Acked-by: Michal Hocko Cc: David Rientjes Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 26 +++++++++++++++++++++++ include/linux/percpu-refcount.h | 47 +++++++++++++++++++++++++++++++++-------- 2 files changed, 64 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 1d5196889048..9f96b25965c2 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -112,6 +112,19 @@ static inline void css_get(struct cgroup_subsys_state *css) percpu_ref_get(&css->refcnt); } +/** + * css_get_many - obtain references on the specified css + * @css: target css + * @n: number of references to get + * + * The caller must already have a reference. + */ +static inline void css_get_many(struct cgroup_subsys_state *css, unsigned int n) +{ + if (!(css->flags & CSS_NO_REF)) + percpu_ref_get_many(&css->refcnt, n); +} + /** * css_tryget - try to obtain a reference on the specified css * @css: target css @@ -159,6 +172,19 @@ static inline void css_put(struct cgroup_subsys_state *css) percpu_ref_put(&css->refcnt); } +/** + * css_put_many - put css references + * @css: target css + * @n: number of references to put + * + * Put references obtained via css_get() and css_tryget_online(). + */ +static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n) +{ + if (!(css->flags & CSS_NO_REF)) + percpu_ref_put_many(&css->refcnt, n); +} + /* bits in struct cgroup flags field */ enum { /* Control Group requires release notifications to userspace */ diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 51ce60c35f4c..530b249f7ea4 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -147,27 +147,41 @@ static inline bool __ref_is_percpu(struct percpu_ref *ref, } /** - * percpu_ref_get - increment a percpu refcount + * percpu_ref_get_many - increment a percpu refcount * @ref: percpu_ref to get + * @nr: number of references to get * - * Analagous to atomic_long_inc(). + * Analogous to atomic_long_add(). * * This function is safe to call as long as @ref is between init and exit. */ -static inline void percpu_ref_get(struct percpu_ref *ref) +static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock_sched(); if (__ref_is_percpu(ref, &percpu_count)) - this_cpu_inc(*percpu_count); + this_cpu_add(*percpu_count, nr); else - atomic_long_inc(&ref->count); + atomic_long_add(nr, &ref->count); rcu_read_unlock_sched(); } +/** + * percpu_ref_get - increment a percpu refcount + * @ref: percpu_ref to get + * + * Analagous to atomic_long_inc(). + * + * This function is safe to call as long as @ref is between init and exit. + */ +static inline void percpu_ref_get(struct percpu_ref *ref) +{ + percpu_ref_get_many(ref, 1); +} + /** * percpu_ref_tryget - try to increment a percpu refcount * @ref: percpu_ref to try-get @@ -231,28 +245,43 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) } /** - * percpu_ref_put - decrement a percpu refcount + * percpu_ref_put_many - decrement a percpu refcount * @ref: percpu_ref to put + * @nr: number of references to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ -static inline void percpu_ref_put(struct percpu_ref *ref) +static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock_sched(); if (__ref_is_percpu(ref, &percpu_count)) - this_cpu_dec(*percpu_count); - else if (unlikely(atomic_long_dec_and_test(&ref->count))) + this_cpu_sub(*percpu_count, nr); + else if (unlikely(atomic_long_sub_and_test(nr, &ref->count))) ref->release(ref); rcu_read_unlock_sched(); } +/** + * percpu_ref_put - decrement a percpu refcount + * @ref: percpu_ref to put + * + * Decrement the refcount, and if 0, call the release function (which was passed + * to percpu_ref_init()) + * + * This function is safe to call as long as @ref is between init and exit. + */ +static inline void percpu_ref_put(struct percpu_ref *ref) +{ + percpu_ref_put_many(ref, 1); +} + /** * percpu_ref_is_zero - test whether a percpu refcount reached zero * @ref: percpu_ref to test -- cgit v1.2.3 From 64f2199389414341ed3a570663f23616c131ba25 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 10 Dec 2014 15:42:45 -0800 Subject: mm: memcontrol: remove obsolete kmemcg pinning tricks As charges now pin the css explicitely, there is no more need for kmemcg to acquire a proxy reference for outstanding pages during offlining, or maintain state to identify such "dead" groups. This was the last user of the uncharge functions' return values, so remove them as well. Signed-off-by: Johannes Weiner Reviewed-by: Vladimir Davydov Acked-by: Michal Hocko Cc: David Rientjes Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_counter.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 7cce3be99ff3..955421575d16 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -34,12 +34,12 @@ static inline unsigned long page_counter_read(struct page_counter *counter) return atomic_long_read(&counter->count); } -int page_counter_cancel(struct page_counter *counter, unsigned long nr_pages); +void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages); void page_counter_charge(struct page_counter *counter, unsigned long nr_pages); int page_counter_try_charge(struct page_counter *counter, unsigned long nr_pages, struct page_counter **fail); -int page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages); +void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages); int page_counter_limit(struct page_counter *counter, unsigned long limit); int page_counter_memparse(const char *buf, unsigned long *nr_pages); -- cgit v1.2.3 From 93481ff0e5a0c7636359a7ee52248856da5e7859 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 10 Dec 2014 15:43:01 -0800 Subject: mm: introduce single zone pcplists drain The functions for draining per-cpu pages back to buddy allocators currently always operate on all zones. There are however several cases where the drain is only needed in the context of a single zone, and spilling other pcplists is a waste of time both due to the extra spilling and later refilling. This patch introduces new zone pointer parameter to drain_all_pages() and changes the dummy parameter of drain_local_pages() to be also a zone pointer. When NULL is passed, the functions operate on all zones as usual. Passing a specific zone pointer reduces the work to the single zone. All callers are updated to pass the NULL pointer in this patch. Conversion to single zone (where appropriate) is done in further patches. Signed-off-by: Vlastimil Babka Cc: Naoya Horiguchi Cc: Mel Gorman Cc: Rik van Riel Cc: Yasuaki Ishimatsu Cc: Zhang Yanfei Cc: Xishi Qiu Cc: Vladimir Davydov Cc: Joonsoo Kim Cc: Michal Nazarewicz Cc: Marek Szyprowski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 41b30fd4d041..07d2699cdb51 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -381,8 +381,8 @@ extern void free_kmem_pages(unsigned long addr, unsigned int order); void page_alloc_init(void); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); -void drain_all_pages(void); -void drain_local_pages(void *dummy); +void drain_all_pages(struct zone *zone); +void drain_local_pages(struct zone *zone); /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what -- cgit v1.2.3 From ebff398017c69a3810bcbc5200ba224d5ccaa207 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 10 Dec 2014 15:43:22 -0800 Subject: mm, compaction: pass classzone_idx and alloc_flags to watermark checking Compaction relies on zone watermark checks for decisions such as if it's worth to start compacting in compaction_suitable() or whether compaction should stop in compact_finished(). The watermark checks take classzone_idx and alloc_flags parameters, which are related to the memory allocation request. But from the context of compaction they are currently passed as 0, including the direct compaction which is invoked to satisfy the allocation request, and could therefore know the proper values. The lack of proper values can lead to mismatch between decisions taken during compaction and decisions related to the allocation request. Lack of proper classzone_idx value means that lowmem_reserve is not taken into account. This has manifested (during recent changes to deferred compaction) when DMA zone was used as fallback for preferred Normal zone. compaction_suitable() without proper classzone_idx would think that the watermarks are already satisfied, but watermark check in get_page_from_freelist() would fail. Because of this problem, deferring compaction has extra complexity that can be removed in the following patch. The issue (not confirmed in practice) with missing alloc_flags is opposite in nature. For allocations that include ALLOC_HIGH, ALLOC_HIGHER or ALLOC_CMA in alloc_flags (the last includes all MOVABLE allocations on CMA-enabled systems) the watermark checking in compaction with 0 passed will be stricter than in get_page_from_freelist(). In these cases compaction might be running for a longer time than is really needed. Another issue compaction_suitable() is that the check for "does the zone need compaction at all?" comes only after the check "does the zone have enough free free pages to succeed compaction". The latter considers extra pages for migration and can therefore in some situations fail and return COMPACT_SKIPPED, although the high-order allocation would succeed and we should return COMPACT_PARTIAL. This patch fixes these problems by adding alloc_flags and classzone_idx to struct compact_control and related functions involved in direct compaction and watermark checking. Where possible, all other callers of compaction_suitable() pass proper values where those are known. This is currently limited to classzone_idx, which is sometimes known in kswapd context. However, the direct reclaim callers should_continue_reclaim() and compaction_ready() do not currently know the proper values, so the coordination between reclaim and compaction may still not be as accurate as it could. This can be fixed later, if it's shown to be an issue. Additionaly the checks in compact_suitable() are reordered to address the second issue described above. The effect of this patch should be slightly better high-order allocation success rates and/or less compaction overhead, depending on the type of allocations and presence of CMA. It allows simplifying deferred compaction code in a followup patch. When testing with stress-highalloc, there was some slight improvement (which might be just due to variance) in success rates of non-THP-like allocations. Signed-off-by: Vlastimil Babka Cc: Minchan Kim Cc: Mel Gorman Cc: Joonsoo Kim Cc: Michal Nazarewicz Cc: Naoya Horiguchi Cc: Christoph Lameter Acked-by: Rik van Riel Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 60bdf8dc02a3..d896765a15b0 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -33,10 +33,12 @@ extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask, enum migrate_mode mode, int *contended, + int alloc_flags, int classzone_idx, struct zone **candidate_zone); extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); -extern unsigned long compaction_suitable(struct zone *zone, int order); +extern unsigned long compaction_suitable(struct zone *zone, int order, + int alloc_flags, int classzone_idx); /* Do not skip compaction more than 64 times */ #define COMPACT_MAX_DEFER_SHIFT 6 @@ -103,6 +105,7 @@ static inline bool compaction_restarting(struct zone *zone, int order) static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask, enum migrate_mode mode, int *contended, + int alloc_flags, int classzone_idx, struct zone **candidate_zone) { return COMPACT_CONTINUE; @@ -116,7 +119,8 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat) { } -static inline unsigned long compaction_suitable(struct zone *zone, int order) +static inline unsigned long compaction_suitable(struct zone *zone, int order, + int alloc_flags, int classzone_idx) { return COMPACT_SKIPPED; } -- cgit v1.2.3 From 97d47a65be1e513edd02325ae828c9997878b578 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 10 Dec 2014 15:43:25 -0800 Subject: mm, compaction: simplify deferred compaction Since commit 53853e2d2bfb ("mm, compaction: defer each zone individually instead of preferred zone"), compaction is deferred for each zone where sync direct compaction fails, and reset where it succeeds. However, it was observed that for DMA zone compaction often appeared to succeed while subsequent allocation attempt would not, due to different outcome of watermark check. In order to properly defer compaction in this zone, the candidate zone has to be passed back to __alloc_pages_direct_compact() and compaction deferred in the zone after the allocation attempt fails. The large source of mismatch between watermark check in compaction and allocation was the lack of alloc_flags and classzone_idx values in compaction, which has been fixed in the previous patch. So with this problem fixed, we can simplify the code by removing the candidate_zone parameter and deferring in __alloc_pages_direct_compact(). After this patch, the compaction activity during stress-highalloc benchmark is still somewhat increased, but it's negligible compared to the increase that occurred without the better watermark checking. This suggests that it is still possible to apparently succeed in compaction but fail to allocate, possibly due to parallel allocation activity. [akpm@linux-foundation.org: fix build] Suggested-by: Joonsoo Kim Signed-off-by: Vlastimil Babka Cc: Minchan Kim Cc: Mel Gorman Cc: Michal Nazarewicz Cc: Naoya Horiguchi Cc: Christoph Lameter Cc: Rik van Riel Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index d896765a15b0..3238ffa33f68 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -33,8 +33,7 @@ extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask, enum migrate_mode mode, int *contended, - int alloc_flags, int classzone_idx, - struct zone **candidate_zone); + int alloc_flags, int classzone_idx); extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order, @@ -105,8 +104,7 @@ static inline bool compaction_restarting(struct zone *zone, int order) static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask, enum migrate_mode mode, int *contended, - int alloc_flags, int classzone_idx, - struct zone **candidate_zone) + int alloc_flags, int classzone_idx) { return COMPACT_CONTINUE; } -- cgit v1.2.3 From 18eca2e636f921e6350dc31b5b450bb4102d664f Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 10 Dec 2014 15:43:57 -0800 Subject: mm: memcontrol: remove unnecessary PCG_MEMSW memory+swap charge flag Now that mem_cgroup_swapout() fully uncharges the page, every page that is still in use when reaching mem_cgroup_uncharge() is known to carry both the memory and the memory+swap charge. Simplify the uncharge path and remove the PCG_MEMSW page flag accordingly. Signed-off-by: Johannes Weiner Cc: Hugh Dickins Acked-by: Michal Hocko Reviewed-by: Vladimir Davydov Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_cgroup.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index 5c831f1eca79..da62ee2be28b 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -5,7 +5,6 @@ enum { /* flags for mem_cgroup */ PCG_USED = 0x01, /* This page is charged to a memcg */ PCG_MEM = 0x02, /* This page holds a memory charge */ - PCG_MEMSW = 0x04, /* This page holds a memory+swap charge */ }; struct pglist_data; -- cgit v1.2.3 From f4aaa8b43d90294ca7546317997c452600e9a8a7 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 10 Dec 2014 15:44:00 -0800 Subject: mm: memcontrol: remove unnecessary PCG_MEM memory charge flag PCG_MEM is a remnant from an earlier version of 0a31bc97c80c ("mm: memcontrol: rewrite uncharge API"), used to tell whether migration cleared a charge while leaving pc->mem_cgroup valid and PCG_USED set. But in the final version, mem_cgroup_migrate() directly uncharges the source page, rendering this distinction unnecessary. Remove it. Signed-off-by: Johannes Weiner Cc: Hugh Dickins Acked-by: Michal Hocko Reviewed-by: Vladimir Davydov Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_cgroup.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index da62ee2be28b..97536e685843 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -4,7 +4,6 @@ enum { /* flags for mem_cgroup */ PCG_USED = 0x01, /* This page is charged to a memcg */ - PCG_MEM = 0x02, /* This page holds a memory charge */ }; struct pglist_data; -- cgit v1.2.3 From 2983331575bfb248abfb02efb5140b4a299e3f45 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 10 Dec 2014 15:44:02 -0800 Subject: mm: memcontrol: remove unnecessary PCG_USED pc->mem_cgroup valid flag pc->mem_cgroup had to be left intact after uncharge for the final LRU removal, and !PCG_USED indicated whether the page was uncharged. But since commit 0a31bc97c80c ("mm: memcontrol: rewrite uncharge API") pages are uncharged after the final LRU removal. Uncharge can simply clear the pointer and the PCG_USED/PageCgroupUsed sites can test that instead. Because this is the last page_cgroup flag, this patch reduces the memcg per-page overhead to a single pointer. [akpm@linux-foundation.org: remove unneeded initialization of `memcg', per Michal] Signed-off-by: Johannes Weiner Cc: Hugh Dickins Acked-by: Michal Hocko Reviewed-by: Vladimir Davydov Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_cgroup.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index 97536e685843..1289be6b436c 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -1,11 +1,6 @@ #ifndef __LINUX_PAGE_CGROUP_H #define __LINUX_PAGE_CGROUP_H -enum { - /* flags for mem_cgroup */ - PCG_USED = 0x01, /* This page is charged to a memcg */ -}; - struct pglist_data; #ifdef CONFIG_MEMCG @@ -19,7 +14,6 @@ struct mem_cgroup; * then the page cgroup for pfn always exists. */ struct page_cgroup { - unsigned long flags; struct mem_cgroup *mem_cgroup; }; @@ -39,10 +33,6 @@ static inline void page_cgroup_init(void) struct page_cgroup *lookup_page_cgroup(struct page *page); -static inline int PageCgroupUsed(struct page_cgroup *pc) -{ - return !!(pc->flags & PCG_USED); -} #else /* !CONFIG_MEMCG */ struct page_cgroup; -- cgit v1.2.3 From 97ad2be1daf8e6f2d297aa349101b340e1327917 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Wed, 10 Dec 2014 15:44:13 -0800 Subject: mm, hugetlb: correct bit shift in hstate_sizelog() hstate_sizelog() would shift left an int rather than long, triggering undefined behaviour and passing an incorrect value when the requested page size was more than 4GB, thus breaking >4GB pages. Signed-off-by: Sasha Levin Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6e6d338641fe..cdd149ca5cc0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -311,7 +311,8 @@ static inline struct hstate *hstate_sizelog(int page_size_log) { if (!page_size_log) return &default_hstate; - return size_to_hstate(1 << page_size_log); + + return size_to_hstate(1UL << page_size_log); } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) -- cgit v1.2.3 From b047501cd9f11d5e1d54ea0f90e2b10754021a0e Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 10 Dec 2014 15:44:19 -0800 Subject: memcg: use generic slab iterators for showing slabinfo Let's use generic slab_start/next/stop for showing memcg caches info. In contrast to the current implementation, this will work even if all memcg caches' info doesn't fit into a seq buffer (a page), plus it simply looks neater. Actually, the main reason I do this isn't mere cleanup. I'm going to zap the memcg_slab_caches list, because I find it useless provided we have the slab_caches list, and this patch is a step in this direction. It should be noted that before this patch an attempt to read memory.kmem.slabinfo of a cgroup that doesn't have kmem limit set resulted in -EIO, while after this patch it will silently show nothing except the header, but I don't think it will frustrate anyone. Signed-off-by: Vladimir Davydov Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index c265bec6a57d..8a2457d42fc8 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -513,10 +513,6 @@ struct memcg_cache_params { int memcg_update_all_caches(int num_memcgs); -struct seq_file; -int cache_show(struct kmem_cache *s, struct seq_file *m); -void print_slabinfo_header(struct seq_file *m); - /** * kmalloc_array - allocate memory for an array. * @n: number of elements. -- cgit v1.2.3 From 413918bb61b4fa027baa3e79546c47f15e4b9ea8 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 10 Dec 2014 15:44:30 -0800 Subject: mm: memcontrol: pull the NULL check from __mem_cgroup_same_or_subtree() The NULL in mm_match_cgroup() comes from a possibly exiting mm->owner. It makes a lot more sense to check where it's looked up, rather than check for it in __mem_cgroup_same_or_subtree() where it's unexpected. No other callsite passes NULL to __mem_cgroup_same_or_subtree(). Signed-off-by: Johannes Weiner Reviewed-by: Vladimir Davydov Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ea007615e8f9..e32ab948f589 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -83,11 +83,12 @@ static inline bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg) { struct mem_cgroup *task_memcg; - bool match; + bool match = false; rcu_read_lock(); task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); - match = __mem_cgroup_same_or_subtree(memcg, task_memcg); + if (task_memcg) + match = __mem_cgroup_same_or_subtree(memcg, task_memcg); rcu_read_unlock(); return match; } -- cgit v1.2.3 From 2314b42db67be30b747122d65c6cd2c85da34538 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 10 Dec 2014 15:44:33 -0800 Subject: mm: memcontrol: drop bogus RCU locking from mem_cgroup_same_or_subtree() None of the mem_cgroup_same_or_subtree() callers actually require it to take the RCU lock, either because they hold it themselves or they have css references. Remove it. To make the API change clear, rename the leftover helper to mem_cgroup_is_descendant() to match cgroup_is_descendant(). Signed-off-by: Johannes Weiner Reviewed-by: Vladimir Davydov Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e32ab948f589..d4575a1d6e99 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -68,10 +68,9 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage, struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *); struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); -bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, - struct mem_cgroup *memcg); -bool task_in_mem_cgroup(struct task_struct *task, - const struct mem_cgroup *memcg); +bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, + struct mem_cgroup *root); +bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg); extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page); extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); @@ -79,8 +78,8 @@ extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css); -static inline -bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg) +static inline bool mm_match_cgroup(struct mm_struct *mm, + struct mem_cgroup *memcg) { struct mem_cgroup *task_memcg; bool match = false; @@ -88,7 +87,7 @@ bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg) rcu_read_lock(); task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (task_memcg) - match = __mem_cgroup_same_or_subtree(memcg, task_memcg); + match = mem_cgroup_is_descendant(task_memcg, memcg); rcu_read_unlock(); return match; } -- cgit v1.2.3 From e4bd6a0248b2a026e07c19995c41a4cb5a49d797 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 10 Dec 2014 15:44:39 -0800 Subject: mm, memcg: fix potential undefined behaviour in page stat accounting Since commit d7365e783edb ("mm: memcontrol: fix missed end-writeback page accounting") mem_cgroup_end_page_stat consumes locked and flags variables directly rather than via pointers which might trigger C undefined behavior as those variables are initialized only in the slow path of mem_cgroup_begin_page_stat. Although mem_cgroup_end_page_stat handles parameters correctly and touches them only when they hold a sensible value it is caller which loads a potentially uninitialized value which then might allow compiler to do crazy things. I haven't seen any warning from gcc and it seems that the current version (4.9) doesn't exploit this type undefined behavior but Sasha has reported the following: UBSan: Undefined behaviour in mm/rmap.c:1084:2 load of value 255 is not a valid value for type '_Bool' CPU: 4 PID: 8304 Comm: rngd Not tainted 3.18.0-rc2-next-20141029-sasha-00039-g77ed13d-dirty #1427 Call Trace: dump_stack (lib/dump_stack.c:52) ubsan_epilogue (lib/ubsan.c:159) __ubsan_handle_load_invalid_value (lib/ubsan.c:482) page_remove_rmap (mm/rmap.c:1084 mm/rmap.c:1096) unmap_page_range (./arch/x86/include/asm/atomic.h:27 include/linux/mm.h:463 mm/memory.c:1146 mm/memory.c:1258 mm/memory.c:1279 mm/memory.c:1303) unmap_single_vma (mm/memory.c:1348) unmap_vmas (mm/memory.c:1377 (discriminator 3)) exit_mmap (mm/mmap.c:2837) mmput (kernel/fork.c:659) do_exit (./arch/x86/include/asm/thread_info.h:168 kernel/exit.c:462 kernel/exit.c:747) do_group_exit (include/linux/sched.h:775 kernel/exit.c:873) SyS_exit_group (kernel/exit.c:901) tracesys_phase2 (arch/x86/kernel/entry_64.S:529) Fix this by using pointer parameters for both locked and flags and be more robust for future compiler changes even though the current code is implemented correctly. Signed-off-by: Michal Hocko Reported-by: Sasha Levin Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d4575a1d6e99..de018766be45 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -141,8 +141,8 @@ static inline bool mem_cgroup_disabled(void) struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, bool *locked, unsigned long *flags); -void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool locked, - unsigned long flags); +void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool *locked, + unsigned long *flags); void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx, int val); @@ -297,7 +297,7 @@ static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, } static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, - bool locked, unsigned long flags) + bool *locked, unsigned long *flags) { } -- cgit v1.2.3 From 1306a85aed3ec3db98945aafb7dfbe5648a1203c Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 10 Dec 2014 15:44:52 -0800 Subject: mm: embed the memcg pointer directly into struct page Memory cgroups used to have 5 per-page pointers. To allow users to disable that amount of overhead during runtime, those pointers were allocated in a separate array, with a translation layer between them and struct page. There is now only one page pointer remaining: the memcg pointer, that indicates which cgroup the page is associated with when charged. The complexity of runtime allocation and the runtime translation overhead is no longer justified to save that *potential* 0.19% of memory. With CONFIG_SLUB, page->mem_cgroup actually sits in the doubleword padding after the page->private member and doesn't even increase struct page, and then this patch actually saves space. Remaining users that care can still compile their kernels without CONFIG_MEMCG. text data bss dec hex filename 8828345 1725264 983040 11536649 b00909 vmlinux.old 8827425 1725264 966656 11519345 afc571 vmlinux.new [mhocko@suse.cz: update Documentation/cgroups/memory.txt] Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Acked-by: Vladimir Davydov Acked-by: David S. Miller Acked-by: KAMEZAWA Hiroyuki Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Vladimir Davydov Cc: Tejun Heo Cc: Joonsoo Kim Acked-by: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 +---- include/linux/mm_types.h | 5 +++++ include/linux/mmzone.h | 12 ---------- include/linux/page_cgroup.h | 53 --------------------------------------------- 4 files changed, 6 insertions(+), 70 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index de018766be45..c4d080875164 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -25,7 +25,6 @@ #include struct mem_cgroup; -struct page_cgroup; struct page; struct mm_struct; struct kmem_cache; @@ -466,8 +465,6 @@ memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order) * memcg_kmem_uncharge_pages: uncharge pages from memcg * @page: pointer to struct page being freed * @order: allocation order. - * - * there is no need to specify memcg here, since it is embedded in page_cgroup */ static inline void memcg_kmem_uncharge_pages(struct page *page, int order) @@ -484,8 +481,7 @@ memcg_kmem_uncharge_pages(struct page *page, int order) * * Needs to be called after memcg_kmem_newpage_charge, regardless of success or * failure of the allocation. if @page is NULL, this function will revert the - * charges. Otherwise, it will commit the memcg given by @memcg to the - * corresponding page_cgroup. + * charges. Otherwise, it will commit @page to @memcg. */ static inline void memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 004e9d17b47e..bf9f57529dcf 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -22,6 +22,7 @@ #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1)) struct address_space; +struct mem_cgroup; #define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) #define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ @@ -167,6 +168,10 @@ struct page { struct page *first_page; /* Compound tail pages */ }; +#ifdef CONFIG_MEMCG + struct mem_cgroup *mem_cgroup; +#endif + /* * On machines where all RAM is mapped into kernel address space, * we can simply calculate the virtual address. On machines with diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ffe66e381c04..3879d7664dfc 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -722,9 +722,6 @@ typedef struct pglist_data { int nr_zones; #ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */ struct page *node_mem_map; -#ifdef CONFIG_MEMCG - struct page_cgroup *node_page_cgroup; -#endif #endif #ifndef CONFIG_NO_BOOTMEM struct bootmem_data *bdata; @@ -1078,7 +1075,6 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) struct page; -struct page_cgroup; struct mem_section { /* * This is, logically, a pointer to an array of struct @@ -1096,14 +1092,6 @@ struct mem_section { /* See declaration of similar field in struct zone */ unsigned long *pageblock_flags; -#ifdef CONFIG_MEMCG - /* - * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use - * section. (see memcontrol.h/page_cgroup.h about this.) - */ - struct page_cgroup *page_cgroup; - unsigned long pad; -#endif /* * WARNING: mem_section must be a power-of-2 in size for the * calculation and use of SECTION_ROOT_MASK to make sense. diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index 1289be6b436c..65be35785c86 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -1,59 +1,6 @@ #ifndef __LINUX_PAGE_CGROUP_H #define __LINUX_PAGE_CGROUP_H -struct pglist_data; - -#ifdef CONFIG_MEMCG -struct mem_cgroup; - -/* - * Page Cgroup can be considered as an extended mem_map. - * A page_cgroup page is associated with every page descriptor. The - * page_cgroup helps us identify information about the cgroup - * All page cgroups are allocated at boot or memory hotplug event, - * then the page cgroup for pfn always exists. - */ -struct page_cgroup { - struct mem_cgroup *mem_cgroup; -}; - -extern void pgdat_page_cgroup_init(struct pglist_data *pgdat); - -#ifdef CONFIG_SPARSEMEM -static inline void page_cgroup_init_flatmem(void) -{ -} -extern void page_cgroup_init(void); -#else -extern void page_cgroup_init_flatmem(void); -static inline void page_cgroup_init(void) -{ -} -#endif - -struct page_cgroup *lookup_page_cgroup(struct page *page); - -#else /* !CONFIG_MEMCG */ -struct page_cgroup; - -static inline void pgdat_page_cgroup_init(struct pglist_data *pgdat) -{ -} - -static inline struct page_cgroup *lookup_page_cgroup(struct page *page) -{ - return NULL; -} - -static inline void page_cgroup_init(void) -{ -} - -static inline void page_cgroup_init_flatmem(void) -{ -} -#endif /* CONFIG_MEMCG */ - #include #ifdef CONFIG_MEMCG_SWAP -- cgit v1.2.3 From 5d1ea48bdde67898e87d6d8f511fd097fa64c749 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 10 Dec 2014 15:44:55 -0800 Subject: mm: page_cgroup: rename file to mm/swap_cgroup.c Now that the external page_cgroup data structure and its lookup is gone, the only code remaining in there is swap slot accounting. Rename it and move the conditional compilation into mm/Makefile. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Acked-by: Vladimir Davydov Acked-by: David S. Miller Acked-by: KAMEZAWA Hiroyuki Cc: "Kirill A. Shutemov" Cc: Tejun Heo Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_cgroup.h | 40 ---------------------------------------- include/linux/swap_cgroup.h | 42 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+), 40 deletions(-) delete mode 100644 include/linux/page_cgroup.h create mode 100644 include/linux/swap_cgroup.h (limited to 'include/linux') diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h deleted file mode 100644 index 65be35785c86..000000000000 --- a/include/linux/page_cgroup.h +++ /dev/null @@ -1,40 +0,0 @@ -#ifndef __LINUX_PAGE_CGROUP_H -#define __LINUX_PAGE_CGROUP_H - -#include - -#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); -extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent); -extern int swap_cgroup_swapon(int type, unsigned long max_pages); -extern void swap_cgroup_swapoff(int type); -#else - -static inline -unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id) -{ - return 0; -} - -static inline -unsigned short lookup_swap_cgroup_id(swp_entry_t ent) -{ - return 0; -} - -static inline int -swap_cgroup_swapon(int type, unsigned long max_pages) -{ - return 0; -} - -static inline void swap_cgroup_swapoff(int type) -{ - return; -} - -#endif /* CONFIG_MEMCG_SWAP */ - -#endif /* __LINUX_PAGE_CGROUP_H */ diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h new file mode 100644 index 000000000000..145306bdc92f --- /dev/null +++ b/include/linux/swap_cgroup.h @@ -0,0 +1,42 @@ +#ifndef __LINUX_SWAP_CGROUP_H +#define __LINUX_SWAP_CGROUP_H + +#include + +#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); +extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent); +extern int swap_cgroup_swapon(int type, unsigned long max_pages); +extern void swap_cgroup_swapoff(int type); + +#else + +static inline +unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id) +{ + return 0; +} + +static inline +unsigned short lookup_swap_cgroup_id(swp_entry_t ent) +{ + return 0; +} + +static inline int +swap_cgroup_swapon(int type, unsigned long max_pages) +{ + return 0; +} + +static inline void swap_cgroup_swapoff(int type) +{ + return; +} + +#endif /* CONFIG_MEMCG_SWAP */ + +#endif /* __LINUX_SWAP_CGROUP_H */ -- cgit v1.2.3 From 9edad6ea0f1416415f6fe31cc9d1dbc3817803ed Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 10 Dec 2014 15:44:58 -0800 Subject: mm: move page->mem_cgroup bad page handling into generic code Now that the external page_cgroup data structure and its lookup is gone, let the generic bad_page() check for page->mem_cgroup sanity. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Acked-by: Vladimir Davydov Acked-by: David S. Miller Cc: KAMEZAWA Hiroyuki Cc: "Kirill A. Shutemov" Cc: Tejun Heo Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index c4d080875164..6ea9f919e888 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -173,10 +173,6 @@ static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, void mem_cgroup_split_huge_fixup(struct page *head); #endif -#ifdef CONFIG_DEBUG_VM -bool mem_cgroup_bad_page_check(struct page *page); -void mem_cgroup_print_bad_page(struct page *page); -#endif #else /* CONFIG_MEMCG */ struct mem_cgroup; @@ -346,19 +342,6 @@ void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx) } #endif /* CONFIG_MEMCG */ -#if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM) -static inline bool -mem_cgroup_bad_page_check(struct page *page) -{ - return false; -} - -static inline void -mem_cgroup_print_bad_page(struct page *page) -{ -} -#endif - enum { UNDER_LIMIT, SOFT_LIMIT, -- cgit v1.2.3 From 7c8bd2322c7fd973d089b27de55e29c92c667a06 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 10 Dec 2014 15:45:33 -0800 Subject: exit: ptrace: shift "reap dead" code from exit_ptrace() to forget_original_parent() Now that forget_original_parent() uses ->ptrace_entry for EXIT_DEAD tasks, we can simply pass "dead_children" list to exit_ptrace() and remove another release_task() loop. Plus this way we do not need to drop and reacquire tasklist_lock. Also shift the list_empty(ptraced) check, if we want this optimization it makes sense to eliminate the function call altogether. Signed-off-by: Oleg Nesterov Cc: Aaron Tomlin Cc: Alexey Dobriyan Cc: "Eric W. Biederman" , Cc: Sterling Alexander Cc: Peter Zijlstra Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index cc79eff4a1ad..987a73a40ef8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -52,7 +52,7 @@ extern void ptrace_notify(int exit_code); extern void __ptrace_link(struct task_struct *child, struct task_struct *new_parent); extern void __ptrace_unlink(struct task_struct *child); -extern void exit_ptrace(struct task_struct *tracer); +extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_READ 0x01 #define PTRACE_MODE_ATTACH 0x02 #define PTRACE_MODE_NOAUDIT 0x04 -- cgit v1.2.3 From f938612dd97d481b8b5bf960c992ae577f081c17 Mon Sep 17 00:00:00 2001 From: Yann Droneaud Date: Wed, 10 Dec 2014 15:45:47 -0800 Subject: include/linux/file.h: remove get_unused_fd() macro Macro get_unused_fd() is used to allocate a file descriptor with default flags. Those default flags (0) don't enable close-on-exec. This can be seen as an unsafe default: in most case close-on-exec should be enabled to not leak file descriptor across exec(). It would be better to have a "safer" default set of flags, eg. O_CLOEXEC must be used to enable close-on-exec. Instead this patch removes get_unused_fd() so that out of tree modules won't be affect by a runtime behavor change which might introduce other kind of bugs: it's better to catch the change at build time, making it easier to fix. Removing the macro will also promote use of get_unused_fd_flags() (or anon_inode_getfd()) with flags provided by userspace. Or, if flags cannot be given by userspace, with flags set to O_CLOEXEC by default. Signed-off-by: Yann Droneaud Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/file.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 4d69123377a2..f87d30882a24 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -66,7 +66,6 @@ extern void set_close_on_exec(unsigned int fd, int flag); extern bool get_close_on_exec(unsigned int fd); extern void put_filp(struct file *); extern int get_unused_fd_flags(unsigned flags); -#define get_unused_fd() get_unused_fd_flags(0) extern void put_unused_fd(unsigned int fd); extern void fd_install(unsigned int fd, struct file *file); -- cgit v1.2.3 From 9e3961a0979817c612b10b2da4f3045ec9faa779 Mon Sep 17 00:00:00 2001 From: Prarit Bhargava Date: Wed, 10 Dec 2014 15:45:50 -0800 Subject: kernel: add panic_on_warn There have been several times where I have had to rebuild a kernel to cause a panic when hitting a WARN() in the code in order to get a crash dump from a system. Sometimes this is easy to do, other times (such as in the case of a remote admin) it is not trivial to send new images to the user. A much easier method would be a switch to change the WARN() over to a panic. This makes debugging easier in that I can now test the actual image the WARN() was seen on and I do not have to engage in remote debugging. This patch adds a panic_on_warn kernel parameter and /proc/sys/kernel/panic_on_warn calls panic() in the warn_slowpath_common() path. The function will still print out the location of the warning. An example of the panic_on_warn output: The first line below is from the WARN_ON() to output the WARN_ON()'s location. After that the panic() output is displayed. WARNING: CPU: 30 PID: 11698 at /home/prarit/dummy_module/dummy-module.c:25 init_dummy+0x1f/0x30 [dummy_module]() Kernel panic - not syncing: panic_on_warn set ... CPU: 30 PID: 11698 Comm: insmod Tainted: G W OE 3.17.0+ #57 Hardware name: Intel Corporation S2600CP/S2600CP, BIOS RMLSDP.86I.00.29.D696.1311111329 11/11/2013 0000000000000000 000000008e3f87df ffff88080f093c38 ffffffff81665190 0000000000000000 ffffffff818aea3d ffff88080f093cb8 ffffffff8165e2ec ffffffff00000008 ffff88080f093cc8 ffff88080f093c68 000000008e3f87df Call Trace: [] dump_stack+0x46/0x58 [] panic+0xd0/0x204 [] ? init_dummy+0x1f/0x30 [dummy_module] [] warn_slowpath_common+0xd0/0xd0 [] ? dummy_greetings+0x40/0x40 [dummy_module] [] warn_slowpath_null+0x1a/0x20 [] init_dummy+0x1f/0x30 [dummy_module] [] do_one_initcall+0xd4/0x210 [] ? __vunmap+0xc2/0x110 [] load_module+0x16a9/0x1b30 [] ? store_uevent+0x70/0x70 [] ? copy_module_from_fd.isra.44+0x129/0x180 [] SyS_finit_module+0xa6/0xd0 [] system_call_fastpath+0x12/0x17 Successfully tested by me. hpa said: There is another very valid use for this: many operators would rather a machine shuts down than being potentially compromised either functionally or security-wise. Signed-off-by: Prarit Bhargava Cc: Jonathan Corbet Cc: Rusty Russell Cc: "H. Peter Anvin" Cc: Andi Kleen Cc: Masami Hiramatsu Acked-by: Yasuaki Ishimatsu Cc: Fabian Frederick Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 446d76a87ba1..233ea8107038 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -427,6 +427,7 @@ extern int panic_timeout; extern int panic_on_oops; extern int panic_on_unrecovered_nmi; extern int panic_on_io_nmi; +extern int panic_on_warn; extern int sysctl_panic_on_stackoverflow; /* * Only to be used by arch init code. If the user over-wrote the default -- cgit v1.2.3 From 1dc6244bd6d4f62239487fb0befc41c63e117290 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 10 Dec 2014 15:45:53 -0800 Subject: printk: remove used-once early_vprintk Eliminate the unlikely possibility of message interleaving for early_printk/early_vprintk use. early_vprintk can be done via the %pV extension so remove this unnecessary function and change early_printk to have the equivalent vprintk code. All uses of early_printk already end with a newline so also remove the unnecessary newline from the early_printk function. Signed-off-by: Joe Perches Acked-by: Chris Metcalf Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index d78125f73ac4..3dd489f2dedc 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -118,7 +118,6 @@ int no_printk(const char *fmt, ...) #ifdef CONFIG_EARLY_PRINTK extern asmlinkage __printf(1, 2) void early_printk(const char *fmt, ...); -void early_vprintk(const char *fmt, va_list ap); #else static inline __printf(1, 2) __cold void early_printk(const char *s, ...) { } -- cgit v1.2.3 From a39d4a857d4bb0a62d6655c0d69f7387fe1ad160 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 10 Dec 2014 15:50:15 -0800 Subject: printk: add and use LOGLEVEL_ defines for KERN_ equivalents Use #defines instead of magic values. Signed-off-by: Joe Perches Acked-by: Greg Kroah-Hartman Cc: Jason Baron Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kern_levels.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kern_levels.h b/include/linux/kern_levels.h index 866caaa9e2bb..c2ce155d83cc 100644 --- a/include/linux/kern_levels.h +++ b/include/linux/kern_levels.h @@ -22,4 +22,17 @@ */ #define KERN_CONT "" +/* integer equivalents of KERN_ */ +#define LOGLEVEL_SCHED -2 /* Deferred messages from sched code + * are set to this special level */ +#define LOGLEVEL_DEFAULT -1 /* default (or last) loglevel */ +#define LOGLEVEL_EMERG 0 /* system is unusable */ +#define LOGLEVEL_ALERT 1 /* action must be taken immediately */ +#define LOGLEVEL_CRIT 2 /* critical conditions */ +#define LOGLEVEL_ERR 3 /* error conditions */ +#define LOGLEVEL_WARNING 4 /* warning conditions */ +#define LOGLEVEL_NOTICE 5 /* normal but significant condition */ +#define LOGLEVEL_INFO 6 /* informational */ +#define LOGLEVEL_DEBUG 7 /* debug-level messages */ + #endif -- cgit v1.2.3