diff options
author | Johannes Weiner <hannes@cmpxchg.org> | 2014-10-29 21:50:48 (GMT) |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-10-29 23:33:15 (GMT) |
commit | d7365e783edb858279be1d03f61bc8d5d3383d90 (patch) | |
tree | ca8c1aea5763cace1eb63022cfea83c480eef487 /mm/memcontrol.c | |
parent | 3a3c02ecf7f2852f122d6d16fb9b3d9cb0c6f201 (diff) | |
download | linux-d7365e783edb858279be1d03f61bc8d5d3383d90.tar.xz |
mm: memcontrol: fix missed end-writeback page accounting
Commit 0a31bc97c80c ("mm: memcontrol: rewrite uncharge API") changed
page migration to uncharge the old page right away. The page is locked,
unmapped, truncated, and off the LRU, but it could race with writeback
ending, which then doesn't unaccount the page properly:
test_clear_page_writeback() migration
wait_on_page_writeback()
TestClearPageWriteback()
mem_cgroup_migrate()
clear PCG_USED
mem_cgroup_update_page_stat()
if (PageCgroupUsed(pc))
decrease memcg pages under writeback
release pc->mem_cgroup->move_lock
The per-page statistics interface is heavily optimized to avoid a
function call and a lookup_page_cgroup() in the file unmap fast path,
which means it doesn't verify whether a page is still charged before
clearing PageWriteback() and it has to do it in the stat update later.
Rework it so that it looks up the page's memcg once at the beginning of
the transaction and then uses it throughout. The charge will be
verified before clearing PageWriteback() and migration can't uncharge
the page as long as that is still set. The RCU lock will protect the
memcg past uncharge.
As far as losing the optimization goes, the following test results are
from a microbenchmark that maps, faults, and unmaps a 4GB sparse file
three times in a nested fashion, so that there are two negative passes
that don't account but still go through the new transaction overhead.
There is no actual difference:
old: 33.195102545 seconds time elapsed ( +- 0.01% )
new: 33.199231369 seconds time elapsed ( +- 0.03% )
The time spent in page_remove_rmap()'s callees still adds up to the
same, but the time spent in the function itself seems reduced:
# Children Self Command Shared Object Symbol
old: 0.12% 0.11% filemapstress [kernel.kallsyms] [k] page_remove_rmap
new: 0.12% 0.08% filemapstress [kernel.kallsyms] [k] page_remove_rmap
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: <stable@vger.kernel.org> [3.17.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/memcontrol.c')
-rw-r--r-- | mm/memcontrol.c | 105 |
1 files changed, 57 insertions, 48 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 23976fd..d6ac0e3 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1536,12 +1536,8 @@ int mem_cgroup_swappiness(struct mem_cgroup *memcg) * start move here. */ -/* for quick checking without looking up memcg */ -atomic_t memcg_moving __read_mostly; - static void mem_cgroup_start_move(struct mem_cgroup *memcg) { - atomic_inc(&memcg_moving); atomic_inc(&memcg->moving_account); synchronize_rcu(); } @@ -1552,10 +1548,8 @@ static void mem_cgroup_end_move(struct mem_cgroup *memcg) * Now, mem_cgroup_clear_mc() may call this function with NULL. * We check NULL in callee rather than caller. */ - if (memcg) { - atomic_dec(&memcg_moving); + if (memcg) atomic_dec(&memcg->moving_account); - } } /* @@ -2204,41 +2198,52 @@ cleanup: return true; } -/* - * Used to update mapped file or writeback or other statistics. +/** + * mem_cgroup_begin_page_stat - begin a page state statistics transaction + * @page: page that is going to change accounted state + * @locked: &memcg->move_lock slowpath was taken + * @flags: IRQ-state flags for &memcg->move_lock * - * Notes: Race condition + * This function must mark the beginning of an accounted page state + * change to prevent double accounting when the page is concurrently + * being moved to another memcg: * - * Charging occurs during page instantiation, while the page is - * unmapped and locked in page migration, or while the page table is - * locked in THP migration. No race is possible. + * memcg = mem_cgroup_begin_page_stat(page, &locked, &flags); + * if (TestClearPageState(page)) + * mem_cgroup_update_page_stat(memcg, state, -1); + * mem_cgroup_end_page_stat(memcg, locked, flags); * - * Uncharge happens to pages with zero references, no race possible. + * The RCU lock is held throughout the transaction. The fast path can + * get away without acquiring the memcg->move_lock (@locked is false) + * because page moving starts with an RCU grace period. * - * Charge moving between groups is protected by checking mm->moving - * account and taking the move_lock in the slowpath. + * The RCU lock also protects the memcg from being freed when the page + * state that is going to change is the only thing preventing the page + * from being uncharged. E.g. end-writeback clearing PageWriteback(), + * which allows migration to go ahead and uncharge the page before the + * account transaction might be complete. */ - -void __mem_cgroup_begin_update_page_stat(struct page *page, - bool *locked, unsigned long *flags) +struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, + bool *locked, + unsigned long *flags) { struct mem_cgroup *memcg; struct page_cgroup *pc; + rcu_read_lock(); + + if (mem_cgroup_disabled()) + return NULL; + pc = lookup_page_cgroup(page); again: memcg = pc->mem_cgroup; if (unlikely(!memcg || !PageCgroupUsed(pc))) - return; - /* - * If this memory cgroup is not under account moving, we don't - * 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(). - */ - VM_BUG_ON(!rcu_read_lock_held()); + return NULL; + + *locked = false; if (atomic_read(&memcg->moving_account) <= 0) - return; + return memcg; move_lock_mem_cgroup(memcg, flags); if (memcg != pc->mem_cgroup || !PageCgroupUsed(pc)) { @@ -2246,36 +2251,40 @@ again: goto again; } *locked = true; + + return memcg; } -void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags) +/** + * mem_cgroup_end_page_stat - finish a page state statistics transaction + * @memcg: the memcg that was accounted against + * @locked: value received from mem_cgroup_begin_page_stat() + * @flags: value received from mem_cgroup_begin_page_stat() + */ +void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool locked, + unsigned long flags) { - struct page_cgroup *pc = lookup_page_cgroup(page); + if (memcg && locked) + move_unlock_mem_cgroup(memcg, &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_mem_cgroup(). - */ - move_unlock_mem_cgroup(pc->mem_cgroup, flags); + rcu_read_unlock(); } -void mem_cgroup_update_page_stat(struct page *page, +/** + * mem_cgroup_update_page_stat - update page state statistics + * @memcg: memcg to account against + * @idx: page state item to account + * @val: number of pages (positive or negative) + * + * See mem_cgroup_begin_page_stat() for locking requirements. + */ +void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx, int val) { - struct mem_cgroup *memcg; - struct page_cgroup *pc = lookup_page_cgroup(page); - unsigned long uninitialized_var(flags); - - if (mem_cgroup_disabled()) - return; - VM_BUG_ON(!rcu_read_lock_held()); - memcg = pc->mem_cgroup; - if (unlikely(!memcg || !PageCgroupUsed(pc))) - return; - this_cpu_add(memcg->stat->count[idx], val); + if (memcg) + this_cpu_add(memcg->stat->count[idx], val); } /* |