Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: Jakub Kicinski <kuba@kernel.org>
To: akpm@linux-foundation.org
Cc: linux-mm@kvack.org, kernel-team@fb.com, tj@kernel.org,
	hannes@cmpxchg.org, chris@chrisdown.name,
	cgroups@vger.kernel.org, shakeelb@google.com, mhocko@kernel.org,
	Jakub Kicinski <kuba@kernel.org>
Subject: [PATCH mm v6 3/4] mm: move cgroup high memory limit setting into struct page_counter
Date: Wed, 27 May 2020 12:58:45 -0700
Message-ID: <20200527195846.102707-4-kuba@kernel.org> (raw)
In-Reply-To: <20200527195846.102707-1-kuba@kernel.org>

High memory limit is currently recorded directly in
struct mem_cgroup. We are about to add a high limit
for swap, move the field to struct page_counter and
add some helpers.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
--
v6: remove page_counter_is_above_high()
v5: make page_counter_set_high() a static inline in the header
v4: new patch
---
 include/linux/memcontrol.h   |  3 ---
 include/linux/page_counter.h |  8 ++++++++
 mm/memcontrol.c              | 19 +++++++++++--------
 3 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 3632d062dc11..4c6da7eadaa7 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -212,9 +212,6 @@ struct mem_cgroup {
 	struct page_counter kmem;
 	struct page_counter tcpmem;
 
-	/* Upper bound of normal memory consumption range */
-	unsigned long high;
-
 	/* Range enforcement for interrupt charges */
 	struct work_struct high_work;
 
diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
index bab7e57f659b..85bd413e784e 100644
--- a/include/linux/page_counter.h
+++ b/include/linux/page_counter.h
@@ -10,6 +10,7 @@ struct page_counter {
 	atomic_long_t usage;
 	unsigned long min;
 	unsigned long low;
+	unsigned long high;
 	unsigned long max;
 	struct page_counter *parent;
 
@@ -55,6 +56,13 @@ bool page_counter_try_charge(struct page_counter *counter,
 void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages);
 void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages);
 void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages);
+
+static inline void page_counter_set_high(struct page_counter *counter,
+					 unsigned long nr_pages)
+{
+	WRITE_ONCE(counter->high, nr_pages);
+}
+
 int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages);
 int page_counter_memparse(const char *buf, const char *max,
 			  unsigned long *nr_pages);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3751e849f443..db5dc875addf 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2233,7 +2233,8 @@ static void reclaim_high(struct mem_cgroup *memcg,
 			 gfp_t gfp_mask)
 {
 	do {
-		if (page_counter_read(&memcg->memory) <= READ_ONCE(memcg->high))
+		if (page_counter_read(&memcg->memory) <=
+		    READ_ONCE(memcg->memory.high))
 			continue;
 		memcg_memory_event(memcg, MEMCG_HIGH);
 		try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true);
@@ -2326,7 +2327,7 @@ static u64 mem_find_max_overage(struct mem_cgroup *memcg)
 
 	do {
 		overage = calculate_overage(page_counter_read(&memcg->memory),
-					    READ_ONCE(memcg->high));
+					    READ_ONCE(memcg->memory.high));
 		max_overage = max(overage, max_overage);
 	} while ((memcg = parent_mem_cgroup(memcg)) &&
 		 !mem_cgroup_is_root(memcg));
@@ -2585,7 +2586,8 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	 * reclaim, the cost of mismatch is negligible.
 	 */
 	do {
-		if (page_counter_read(&memcg->memory) > READ_ONCE(memcg->high)) {
+		if (page_counter_read(&memcg->memory) >
+		    READ_ONCE(memcg->memory.high)) {
 			/* Don't bother a random interrupted task */
 			if (in_interrupt()) {
 				schedule_work(&memcg->high_work);
@@ -4280,7 +4282,7 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
 
 	while ((parent = parent_mem_cgroup(memcg))) {
 		unsigned long ceiling = min(READ_ONCE(memcg->memory.max),
-					    READ_ONCE(memcg->high));
+					    READ_ONCE(memcg->memory.high));
 		unsigned long used = page_counter_read(&memcg->memory);
 
 		*pheadroom = min(*pheadroom, ceiling - min(ceiling, used));
@@ -5005,7 +5007,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	if (IS_ERR(memcg))
 		return ERR_CAST(memcg);
 
-	WRITE_ONCE(memcg->high, PAGE_COUNTER_MAX);
+	page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
 	memcg->soft_limit = PAGE_COUNTER_MAX;
 	if (parent) {
 		memcg->swappiness = mem_cgroup_swappiness(parent);
@@ -5158,7 +5160,7 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
 	page_counter_set_max(&memcg->tcpmem, PAGE_COUNTER_MAX);
 	page_counter_set_min(&memcg->memory, 0);
 	page_counter_set_low(&memcg->memory, 0);
-	WRITE_ONCE(memcg->high, PAGE_COUNTER_MAX);
+	page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
 	memcg->soft_limit = PAGE_COUNTER_MAX;
 	memcg_wb_domain_size_changed(memcg);
 }
@@ -5978,7 +5980,8 @@ static ssize_t memory_low_write(struct kernfs_open_file *of,
 
 static int memory_high_show(struct seq_file *m, void *v)
 {
-	return seq_puts_memcg_tunable(m, READ_ONCE(mem_cgroup_from_seq(m)->high));
+	return seq_puts_memcg_tunable(m,
+		READ_ONCE(mem_cgroup_from_seq(m)->memory.high));
 }
 
 static ssize_t memory_high_write(struct kernfs_open_file *of,
@@ -5995,7 +5998,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of,
 	if (err)
 		return err;
 
-	WRITE_ONCE(memcg->high, high);
+	page_counter_set_high(&memcg->memory, high);
 
 	for (;;) {
 		unsigned long nr_pages = page_counter_read(&memcg->memory);
-- 
2.25.4



  parent reply index

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-27 19:58 [PATCH mm v6 0/4] memcg: Slow down swap allocation as the available space gets depleted Jakub Kicinski
2020-05-27 19:58 ` [PATCH mm v6 1/4] mm: prepare for swap over-high accounting and penalty calculation Jakub Kicinski
2020-05-27 19:58 ` [PATCH mm v6 2/4] mm: move penalty delay clamping out of calculate_high_delay() Jakub Kicinski
2020-05-27 19:58 ` Jakub Kicinski [this message]
2020-05-27 19:58 ` [PATCH mm v6 4/4] mm: automatically penalize tasks with high swap use Jakub Kicinski
2020-05-27 20:05   ` Johannes Weiner
2020-06-04 15:57   ` Michal Hocko

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=20200527195846.102707-4-kuba@kernel.org \
    --to=kuba@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=cgroups@vger.kernel.org \
    --cc=chris@chrisdown.name \
    --cc=hannes@cmpxchg.org \
    --cc=kernel-team@fb.com \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=shakeelb@google.com \
    --cc=tj@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