Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: Chris Down <chris@chrisdown.name>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>,
	Michal Hocko <mhocko@kernel.org>, Roman Gushchin <guro@fb.com>,
	Yafang Shao <laoar.shao@gmail.com>,
	linux-mm@kvack.org, cgroups@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH v4 2/2] mm, memcg: Decouple e{low,min} state mutations from protection checks
Date: Mon, 13 Jul 2020 12:06:01 +0100
Message-ID: <ff3f915097fcee9f6d7041c084ef92d16aaeb56a.1594638158.git.chris@chrisdown.name> (raw)
In-Reply-To: <cover.1594638158.git.chris@chrisdown.name>

mem_cgroup_protected currently is both used to set effective low and min
and return a mem_cgroup_protection based on the result.  As a user, this
can be a little unexpected: it appears to be a simple predicate function,
if not for the big warning in the comment above about the order in which
it must be executed.

This change makes it so that we separate the state mutations from the
actual protection checks, which makes it more obvious where we need to be
careful mutating internal state, and where we are simply checking and
don't need to worry about that.

[mhocko@suse.com - don't check protection on root memcgs]
Signed-off-by: Chris Down <chris@chrisdown.name>
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Roman Gushchin <guro@fb.com>
---
 include/linux/memcontrol.h | 53 ++++++++++++++++++++++++++++++--------
 mm/memcontrol.c            | 28 +++++---------------
 mm/vmscan.c                | 17 +++---------
 3 files changed, 53 insertions(+), 45 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 33d834a187e5..d7887888ce99 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -55,12 +55,6 @@ enum memcg_memory_event {
 	MEMCG_NR_MEMORY_EVENTS,
 };
 
-enum mem_cgroup_protection {
-	MEMCG_PROT_NONE,
-	MEMCG_PROT_LOW,
-	MEMCG_PROT_MIN,
-};
-
 struct mem_cgroup_reclaim_cookie {
 	pg_data_t *pgdat;
 	unsigned int generation;
@@ -413,8 +407,36 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
 		   READ_ONCE(memcg->memory.elow));
 }
 
-enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
-						struct mem_cgroup *memcg);
+void mem_cgroup_calculate_protection(struct mem_cgroup *root,
+				     struct mem_cgroup *memcg);
+
+static inline bool mem_cgroup_supports_protection(struct mem_cgroup *memcg)
+{
+	/*
+	 * The root memcg doesn't account charges, and doesn't support
+	 * protection.
+	 */
+	return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg);
+
+}
+
+static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
+{
+	if (!mem_cgroup_supports_protection(memcg))
+		return false;
+
+	return READ_ONCE(memcg->memory.elow) >=
+		page_counter_read(&memcg->memory);
+}
+
+static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
+{
+	if (!mem_cgroup_supports_protection(memcg))
+		return false;
+
+	return READ_ONCE(memcg->memory.emin) >=
+		page_counter_read(&memcg->memory);
+}
 
 int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask);
 
@@ -943,10 +965,19 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
 	return 0;
 }
 
-static inline enum mem_cgroup_protection mem_cgroup_protected(
-	struct mem_cgroup *root, struct mem_cgroup *memcg)
+static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root,
+						   struct mem_cgroup *memcg)
 {
-	return MEMCG_PROT_NONE;
+}
+
+static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
+{
+	return false;
+}
+
+static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
+{
+	return false;
 }
 
 static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 21b620e36aa0..1f101078b217 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6548,21 +6548,15 @@ static unsigned long effective_protection(unsigned long usage,
  *
  * WARNING: This function is not stateless! It can only be used as part
  *          of a top-down tree iteration, not for isolated queries.
- *
- * Returns one of the following:
- *   MEMCG_PROT_NONE: cgroup memory is not protected
- *   MEMCG_PROT_LOW: cgroup memory is protected as long there is
- *     an unprotected supply of reclaimable memory from other cgroups.
- *   MEMCG_PROT_MIN: cgroup memory is protected
  */
-enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
-						struct mem_cgroup *memcg)
+void mem_cgroup_calculate_protection(struct mem_cgroup *root,
+				     struct mem_cgroup *memcg)
 {
 	unsigned long usage, parent_usage;
 	struct mem_cgroup *parent;
 
 	if (mem_cgroup_disabled())
-		return MEMCG_PROT_NONE;
+		return;
 
 	if (!root)
 		root = root_mem_cgroup;
@@ -6575,21 +6569,21 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 	 * that special casing.
 	 */
 	if (memcg == root)
-		return MEMCG_PROT_NONE;
+		return;
 
 	usage = page_counter_read(&memcg->memory);
 	if (!usage)
-		return MEMCG_PROT_NONE;
+		return;
 
 	parent = parent_mem_cgroup(memcg);
 	/* No parent means a non-hierarchical mode on v1 memcg */
 	if (!parent)
-		return MEMCG_PROT_NONE;
+		return;
 
 	if (parent == root) {
 		memcg->memory.emin = READ_ONCE(memcg->memory.min);
 		memcg->memory.elow = READ_ONCE(memcg->memory.low);
-		goto out;
+		return;
 	}
 
 	parent_usage = page_counter_read(&parent->memory);
@@ -6603,14 +6597,6 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 			READ_ONCE(memcg->memory.low),
 			READ_ONCE(parent->memory.elow),
 			atomic_long_read(&parent->memory.children_low_usage)));
-
-out:
-	if (usage <= memcg->memory.emin)
-		return MEMCG_PROT_MIN;
-	else if (usage <= memcg->memory.elow)
-		return MEMCG_PROT_LOW;
-	else
-		return MEMCG_PROT_NONE;
 }
 
 /**
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 89921a12acae..626bdde485b3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2615,14 +2615,15 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 		unsigned long reclaimed;
 		unsigned long scanned;
 
-		switch (mem_cgroup_protected(target_memcg, memcg)) {
-		case MEMCG_PROT_MIN:
+		mem_cgroup_calculate_protection(target_memcg, memcg);
+
+		if (mem_cgroup_below_min(memcg)) {
 			/*
 			 * Hard protection.
 			 * If there is no reclaimable memory, OOM.
 			 */
 			continue;
-		case MEMCG_PROT_LOW:
+		} else if (mem_cgroup_below_low(memcg)) {
 			/*
 			 * Soft protection.
 			 * Respect the protection only as long as
@@ -2634,16 +2635,6 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 				continue;
 			}
 			memcg_memory_event(memcg, MEMCG_LOW);
-			break;
-		case MEMCG_PROT_NONE:
-			/*
-			 * All protection thresholds breached. We may
-			 * still choose to vary the scan pressure
-			 * applied based on by how much the cgroup in
-			 * question has exceeded its protection
-			 * thresholds (see get_scan_count).
-			 */
-			break;
 		}
 
 		reclaimed = sc->nr_reclaimed;
-- 
2.27.0



      parent reply index

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-13 11:04 [PATCH v4 0/2] mm, memcg: memory.{low,min} reclaim fix & cleanup Chris Down
2020-07-13 11:05 ` [PATCH v4 1/2] mm, memcg: Avoid stale protection values when cgroup is above protection Yafang Shao
2020-07-13 11:06 ` Chris Down [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=ff3f915097fcee9f6d7041c084ef92d16aaeb56a.1594638158.git.chris@chrisdown.name \
    --to=chris@chrisdown.name \
    --cc=akpm@linux-foundation.org \
    --cc=cgroups@vger.kernel.org \
    --cc=guro@fb.com \
    --cc=hannes@cmpxchg.org \
    --cc=laoar.shao@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org
	public-inbox-index linux-mm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git