[Devel] [PATCH rh7 v2 12/21] ms/mm: memcontrol: remove explicit OOM parameter in charge path

[Andrey Ryabinin]

From: Michal Hocko <mhocko at suse.cz>

For the page allocator, __GFP_NORETRY implies that no OOM should be
triggered, whereas memcg has an explicit parameter to disable OOM.

The only callsites that want OOM disabled are THP charges and charge
moving.  THP already uses __GFP_NORETRY and charge moving can use it as
well - one full reclaim cycle should be plenty.  Switch it over, then
remove the OOM parameter.

Signed-off-by: Johannes Weiner <hannes at cmpxchg.org>
Signed-off-by: Michal Hocko <mhocko at suse.cz>
Cc: Hugh Dickins <hughd at google.com>
Cc: Tejun Heo <tj at kernel.org>
Cc: Vladimir Davydov <vdavydov at parallels.com>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>

https://jira.sw.ru/browse/PSBM-51558
(cherry picked from commit 0029e19ebf84dcd70b226820daa7747b28d5956d)
Signed-off-by: Andrey Ryabinin <aryabinin at virtuozzo.com>
---
 mm/memcontrol.c | 51 +++++++++++++--------------------------------------
 1 file changed, 13 insertions(+), 38 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a53d55d..a1aab9f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2748,15 +2748,13 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb,
  * mem_cgroup_try_charge - try charging a memcg
  * @memcg: memcg to charge
  * @nr_pages: number of pages to charge
- * @oom: trigger OOM if reclaim fails
  *
  * Returns 0 if @memcg was charged successfully, -EINTR if the charge
  * was bypassed to root_mem_cgroup, and -ENOMEM if the charge failed.
  */
 static int mem_cgroup_try_charge(struct mem_cgroup *memcg,
 				 gfp_t gfp_mask,
-				 unsigned int nr_pages,
-				 bool oom)
+				 unsigned int nr_pages)
 {
 	unsigned int batch = max(CHARGE_BATCH, nr_pages);
 	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
@@ -2838,9 +2836,6 @@ retry:
 	if (fatal_signal_pending(current))
 		goto bypass;
 
-	if (!oom)
-		goto nomem;
-
 	mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(batch));
 	mem_cgroup_inc_failcnt(mem_over_limit, gfp_mask, nr_pages);
 
@@ -2868,15 +2863,14 @@ done:
  */
 static struct mem_cgroup *mem_cgroup_try_charge_mm(struct mm_struct *mm,
 				 gfp_t gfp_mask,
-				 unsigned int nr_pages,
-				 bool oom)
+				 unsigned int nr_pages)
 
 {
 	struct mem_cgroup *memcg;
 	int ret;
 
 	memcg = get_mem_cgroup_from_mm(mm);
-	ret = mem_cgroup_try_charge(memcg, gfp_mask, nr_pages, oom);
+	ret = mem_cgroup_try_charge(memcg, gfp_mask, nr_pages);
 	css_put(&memcg->css);
 	if (ret == -EINTR)
 		memcg = root_mem_cgroup;
@@ -3044,15 +3038,8 @@ int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
 {
 	struct page_counter *counter;
 	int ret = 0;
-	bool may_oom;
 
-	/*
-	 * Conditions under which we can wait for the oom_killer. Those are
-	 * the same conditions tested by the core page allocator
-	 */
-	may_oom = (gfp & __GFP_FS) && !(gfp & __GFP_NORETRY);
-
-	ret = mem_cgroup_try_charge(memcg, gfp, nr_pages, may_oom);
+	ret = mem_cgroup_try_charge(memcg, gfp, nr_pages);
 	if (ret == -EINTR)  {
 		/*
 		 * mem_cgroup_try_charge() chosed to bypass to root due to
@@ -3686,7 +3673,6 @@ int mem_cgroup_newpage_charge(struct page *page,
 {
 	unsigned int nr_pages = 1;
 	struct mem_cgroup *memcg;
-	bool oom = true;
 
 	if (mem_cgroup_disabled())
 		return 0;
@@ -3698,14 +3684,9 @@ int mem_cgroup_newpage_charge(struct page *page,
 	if (PageTransHuge(page)) {
 		nr_pages <<= compound_order(page);
 		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
-		/*
-		 * Never OOM-kill a process for a huge page.  The
-		 * fault handler will fall back to regular pages.
-		 */
-		oom = false;
 	}
 
-	memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, nr_pages, oom);
+	memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, nr_pages);
 	if (!memcg)
 		return -ENOMEM;
 	__mem_cgroup_commit_charge(memcg, page, nr_pages,
@@ -3742,7 +3723,7 @@ static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm,
 		memcg = try_get_mem_cgroup_from_page(page);
 	if (!memcg)
 		memcg = get_mem_cgroup_from_mm(mm);
-	ret = mem_cgroup_try_charge(memcg, mask, 1, true);
+	ret = mem_cgroup_try_charge(memcg, mask, 1);
 	css_put(&memcg->css);
 	if (ret == -EINTR)
 		memcg = root_mem_cgroup;
@@ -3769,7 +3750,7 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page,
 	if (!PageSwapCache(page)) {
 		struct mem_cgroup *memcg;
 
-		memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true);
+		memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1);
 		if (!memcg)
 			return -ENOMEM;
 		*memcgp = memcg;
@@ -3840,17 +3821,10 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 		return 0;
 	}
 
-	/*
-	 * Page cache insertions can happen without an actual mm
-	 * context, e.g. during disk probing on boot.
-	 */
-	if (unlikely(!mm))
-		memcg = root_mem_cgroup;
-	else {
-		memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true);
-		if (!memcg)
-			return -ENOMEM;
-	}
+	memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1);
+	if (!memcg)
+		return -ENOMEM;
+
 	__mem_cgroup_commit_charge(memcg, page, 1, type, false);
 	return 0;
 }
@@ -6790,7 +6764,8 @@ one_by_one:
 			batch_count = PRECHARGE_COUNT_AT_ONCE;
 			cond_resched();
 		}
-		ret = mem_cgroup_try_charge(memcg, GFP_KERNEL, 1, false);
+		ret = mem_cgroup_try_charge(memcg,
+					    GFP_KERNEL & ~__GFP_NORETRY, 1);
 		if (ret)
 			/* mem_cgroup_clear_mc() will do uncharge later */
 			return ret;
-- 
2.10.2