The patch titled
Subject: memcg: simplify move_account() check
has been added to the -mm tree. Its filename is
memcg-simplify-move_account-check.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Subject: memcg: simplify move_account() check
In memcg, for avoiding take-lock-irq-off at accessing page_cgroup, a
logic, flag + rcu_read_lock(), is used. This works as following
CPU-A CPU-B
rcu_read_lock()
set flag
if(flag is set)
take heavy lock
do job.
synchronize_rcu() rcu_read_unlock()
take heavy lock.
In recent discussion, it's argued that using per-cpu value for this flag
just complicates the code because 'set flag' is very rare.
This patch changes 'flag' implementation from percpu to atomic_t. This
will be much simpler.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Acked-by: Greg Thelen <gthelen@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxx>
Cc: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Cc: Ying Han <yinghan@xxxxxxxxxx>
Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 70 +++++++++++++++++++---------------------------
1 file changed, 30 insertions(+), 40 deletions(-)
diff -puN mm/memcontrol.c~memcg-simplify-move_account-check mm/memcontrol.c
--- a/mm/memcontrol.c~memcg-simplify-move_account-check
+++ a/mm/memcontrol.c
@@ -89,7 +89,6 @@ enum mem_cgroup_stat_index {
MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */
MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */
MEM_CGROUP_STAT_DATA, /* end of data requires synchronization */
- MEM_CGROUP_ON_MOVE, /* someone is moving account between groups */
MEM_CGROUP_STAT_NSTATS,
};
@@ -278,6 +277,10 @@ struct mem_cgroup {
*/
unsigned long move_charge_at_immigrate;
/*
+ * set > 0 if pages under this cgroup are moving to other cgroup.
+ */
+ atomic_t moving_account;
+ /*
* percpu counter.
*/
struct mem_cgroup_stat_cpu *stat;
@@ -1253,36 +1256,37 @@ int mem_cgroup_swappiness(struct mem_cgr
return memcg->swappiness;
}
+/*
+ * memcg->moving_account is used for checking possibility that some thread is
+ * calling move_account(). When a thread on CPU-A starts moving pages under
+ * a memcg, other threads should check memcg->moving_account under
+ * rcu_read_lock(), like this:
+ *
+ * CPU-A CPU-B
+ * rcu_read_lock()
+ * memcg->moving_account+1 if (memcg->mocing_account)
+ * take heavy locks.
+ * synchronize_rcu() update something.
+ * rcu_read_unlock()
+ * start move here.
+ */
static void mem_cgroup_start_move(struct mem_cgroup *memcg)
{
- int cpu;
-
- get_online_cpus();
- spin_lock(&memcg->pcp_counter_lock);
- for_each_online_cpu(cpu)
- per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) += 1;
- memcg->nocpu_base.count[MEM_CGROUP_ON_MOVE] += 1;
- spin_unlock(&memcg->pcp_counter_lock);
- put_online_cpus();
-
+ atomic_inc(&memcg->moving_account);
synchronize_rcu();
}
static void mem_cgroup_end_move(struct mem_cgroup *memcg)
{
- int cpu;
-
- if (!memcg)
- return;
- get_online_cpus();
- spin_lock(&memcg->pcp_counter_lock);
- for_each_online_cpu(cpu)
- per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) -= 1;
- memcg->nocpu_base.count[MEM_CGROUP_ON_MOVE] -= 1;
- spin_unlock(&memcg->pcp_counter_lock);
- put_online_cpus();
+ /*
+ * 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_account);
}
+
/*
* 2 routines for checking "mem" is under move_account() or not.
*
@@ -1298,7 +1302,7 @@ static void mem_cgroup_end_move(struct m
static bool mem_cgroup_stealed(struct mem_cgroup *memcg)
{
VM_BUG_ON(!rcu_read_lock_held());
- return this_cpu_read(memcg->stat->count[MEM_CGROUP_ON_MOVE]) > 0;
+ return atomic_read(&memcg->moving_account) > 0;
}
static bool mem_cgroup_under_move(struct mem_cgroup *memcg)
@@ -1849,8 +1853,8 @@ bool mem_cgroup_handle_oom(struct mem_cg
* by flags.
*
* Considering "move", this is an only case we see a race. To make the race
- * small, we check MEM_CGROUP_ON_MOVE percpu value and detect there are
- * possibility of race condition. If there is, we take a lock.
+ * small, we check mm->moving_account and detect there are possibility of race
+ * If there is, we take a lock.
*/
void mem_cgroup_update_page_stat(struct page *page,
@@ -2067,17 +2071,6 @@ static void mem_cgroup_drain_pcp_counter
per_cpu(memcg->stat->events[i], cpu) = 0;
memcg->nocpu_base.events[i] += x;
}
- /* need to clear ON_MOVE value, works as a kind of lock. */
- per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) = 0;
- spin_unlock(&memcg->pcp_counter_lock);
-}
-
-static void synchronize_mem_cgroup_on_move(struct mem_cgroup *memcg, int cpu)
-{
- int idx = MEM_CGROUP_ON_MOVE;
-
- spin_lock(&memcg->pcp_counter_lock);
- per_cpu(memcg->stat->count[idx], cpu) = memcg->nocpu_base.count[idx];
spin_unlock(&memcg->pcp_counter_lock);
}
@@ -2089,11 +2082,8 @@ static int __cpuinit memcg_cpu_hotplug_c
struct memcg_stock_pcp *stock;
struct mem_cgroup *iter;
- if ((action == CPU_ONLINE)) {
- for_each_mem_cgroup(iter)
- synchronize_mem_cgroup_on_move(iter, cpu);
+ if (action == CPU_ONLINE)
return NOTIFY_OK;
- }
if ((action != CPU_DEAD) || action != CPU_DEAD_FROZEN)
return NOTIFY_OK;
_
Subject: Subject: memcg: simplify move_account() check
Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are
linux-next.patch
mm-oom-avoid-looping-when-chosen-thread-detaches-its-mm.patch
mm-oom-fold-oom_kill_task-into-oom_kill_process.patch
mm-oom-do-not-emit-oom-killer-warning-if-chosen-thread-is-already-exiting.patch
mm-oom-introduce-independent-oom-killer-ratelimit-state.patch
mm-add-rss-counters-consistency-check.patch
mm-vmscanc-cleanup-with-s-reclaim_mode-isolate_mode.patch
mm-make-get_mm_counter-static-inline.patch
mm-vmscan-fix-misused-nr_reclaimed-in-shrink_mem_cgroup_zone.patch
hugetlbfs-fix-hugetlb_get_unmapped_area.patch
hugetlb-drop-prev_vma-in-hugetlb_get_unmapped_area_topdown.patch
hugetlb-try-to-search-again-if-it-is-really-needed.patch
hugetlb-try-to-search-again-if-it-is-really-needed-fix.patch
mm-do-not-reset-cached_hole_size-when-vma-is-unmapped.patch
mm-search-from-free_area_cache-for-the-bigger-size.patch
pagemap-avoid-splitting-thp-when-reading-proc-pid-pagemap.patch
thp-optimize-away-unnecessary-page-table-locking.patch
pagemap-export-kpf_thp.patch
pagemap-document-kpf_thp-and-make-page-types-aware-of-it.patch
pagemap-introduce-data-structure-for-pagemap-entry.patch
mm-hugetlb-defer-freeing-pages-when-gathering-surplus-pages.patch
rmap-anon_vma_prepare-reduce-code-duplication-by-calling-anon_vma_chain_link.patch
memcg-replace-mem_cont-by-mem_res_ctlr.patch
memcg-replace-mem-and-mem_cont-stragglers.patch
memcg-lru_size-instead-of-mem_cgroup_zstat.patch
memcg-enum-lru_list-lru.patch
memcg-remove-redundant-returns.patch
memcg-remove-unnecessary-thp-check-in-page-stat-accounting.patch
idr-make-idr_get_next-good-for-rcu_read_lock.patch
cgroup-revert-ss_id_lock-to-spinlock.patch
memcg-let-css_get_next-rely-upon-rcu_read_lock.patch
memcg-remove-pcg_cache-page_cgroup-flag.patch
memcg-remove-pcg_cache-page_cgroup-flag-checkpatch-fixes.patch
memcg-remove-export_symbolmem_cgroup_update_page_stat.patch
memcg-simplify-move_account-check.patch
memcg-remove-pcg_move_lock-flag-from-page_cgroup.patch
memcg-use-new-logic-for-page-stat-accounting.patch
memcg-use-new-logic-for-page-stat-accounting-fix.patch
memcg-remove-pcg_file_mapped.patch
memcg-fix-performance-of-mem_cgroup_begin_update_page_stat.patch
memcg-fix-performance-of-mem_cgroup_begin_update_page_stat-fix.patch
mm-memcontrolc-s-stealed-stolen.patch
proc-speedup-proc-stat-handling.patch
procfs-add-num_to_str-to-speed-up-proc-stat.patch
procfs-add-num_to_str-to-speed-up-proc-stat-fix.patch
procfs-add-num_to_str-to-speed-up-proc-stat-fix-2.patch
procfs-speed-up-proc-pid-stat-statm.patch
procfs-speed-up-proc-pid-stat-statm-checkpatch-fixes.patch
seq_file-add-seq_set_overflow-seq_overflow.patch
seq_file-add-seq_set_overflow-seq_overflow-fix.patch
fs-proc-introduce-proc-pid-task-tid-children-entry-v9.patch
c-r-procfs-add-arg_start-end-env_start-end-and-exit_code-members-to-proc-pid-stat.patch
c-r-prctl-extend-pr_set_mm-to-set-up-more-mm_struct-entries-v2.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
