linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Roman Gushchin <guro@fb.com>
To: <linux-mm@kvack.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Shakeel Butt <shakeelb@google.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Michal Hocko <mhocko@kernel.org>, Tejun Heo <tj@kernel.org>,
	<linux-kernel@vger.kernel.org>, <kernel-team@fb.com>,
	Roman Gushchin <guro@fb.com>
Subject: [PATCH rfc 1/3] mm: memcg: deprecate the non-hierarchical mode
Date: Tue, 3 Nov 2020 13:27:23 -0800	[thread overview]
Message-ID: <20201103212725.3716088-2-guro@fb.com> (raw)
In-Reply-To: <20201103212725.3716088-1-guro@fb.com>

The non-hierarchical cgroup v1 mode is a legacy of early days
of the memory controller and doesn't bring any value today.
However, it complicates the code and creates many edge cases
all over the memory controller code.

It's a good time to deprecate it completely.

Functionally this patch enabled is by default for all cgroups
and forbids switching it off. Nothing changes if cgroup v2 is used:
hierarchical mode was enforced from scratch.

To protect the ABI memory.use_hierarchy interface is preserved
with a limited functionality: reading always returns "1", writing
of "1" passes silently, writing of any other value fails with
-EINVAL and a warning to dmesg (on the first occasion).

Signed-off-by: Roman Gushchin <guro@fb.com>
---
 include/linux/memcontrol.h |  7 ---
 kernel/cgroup/cgroup.c     |  5 ---
 mm/memcontrol.c            | 90 ++++++--------------------------------
 3 files changed, 13 insertions(+), 89 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 0f4dd7829fb2..31000929db4b 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -234,11 +234,6 @@ struct mem_cgroup {
 	/* vmpressure notifications */
 	struct vmpressure vmpressure;
 
-	/*
-	 * Should the accounting and control be hierarchical, per subtree?
-	 */
-	bool use_hierarchy;
-
 	/*
 	 * Should the OOM killer kill all belonging tasks, had it kill one?
 	 */
@@ -758,8 +753,6 @@ static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
 {
 	if (root == memcg)
 		return true;
-	if (!root->use_hierarchy)
-		return false;
 	return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup);
 }
 
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index f2eeff74d713..621a586e3529 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -281,9 +281,6 @@ bool cgroup_ssid_enabled(int ssid)
  * - cpuset: a task can be moved into an empty cpuset, and again it takes
  *   masks of ancestors.
  *
- * - memcg: use_hierarchy is on by default and the cgroup file for the flag
- *   is not created.
- *
  * - blkcg: blk-throttle becomes properly hierarchical.
  *
  * - debug: disallowed on the default hierarchy.
@@ -5156,8 +5153,6 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 	    cgroup_parent(parent)) {
 		pr_warn("%s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
 			current->comm, current->pid, ss->name);
-		if (!strcmp(ss->name, "memory"))
-			pr_warn("\"memory\" requires setting use_hierarchy to 1 on the root\n");
 		ss->warned_broken_hierarchy = true;
 	}
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4b0cd4b78d47..2a37785e9abd 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1127,12 +1127,6 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 	if (prev && !reclaim)
 		pos = prev;
 
-	if (!root->use_hierarchy && root != root_mem_cgroup) {
-		if (prev)
-			goto out;
-		return root;
-	}
-
 	rcu_read_lock();
 
 	if (reclaim) {
@@ -1212,7 +1206,6 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 
 out_unlock:
 	rcu_read_unlock();
-out:
 	if (prev && prev != root)
 		css_put(&prev->css);
 
@@ -3440,10 +3433,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 }
 
 /*
- * Test whether @memcg has children, dead or alive.  Note that this
- * function doesn't care whether @memcg has use_hierarchy enabled and
- * returns %true if there are child csses according to the cgroup
- * hierarchy.  Testing use_hierarchy is the caller's responsibility.
+ * Test whether @memcg has children, dead or alive.
  */
 static inline bool memcg_has_children(struct mem_cgroup *memcg)
 {
@@ -3503,37 +3493,20 @@ static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of,
 static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css,
 				     struct cftype *cft)
 {
-	return mem_cgroup_from_css(css)->use_hierarchy;
+	return 1;
 }
 
 static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css,
 				      struct cftype *cft, u64 val)
 {
-	int retval = 0;
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
-	struct mem_cgroup *parent_memcg = mem_cgroup_from_css(memcg->css.parent);
-
-	if (memcg->use_hierarchy == val)
+	if (val == 1)
 		return 0;
 
-	/*
-	 * If parent's use_hierarchy is set, we can't make any modifications
-	 * in the child subtrees. If it is unset, then the change can
-	 * occur, provided the current cgroup has no children.
-	 *
-	 * For the root cgroup, parent_mem is NULL, we allow value to be
-	 * set if there are no children.
-	 */
-	if ((!parent_memcg || !parent_memcg->use_hierarchy) &&
-				(val == 1 || val == 0)) {
-		if (!memcg_has_children(memcg))
-			memcg->use_hierarchy = val;
-		else
-			retval = -EBUSY;
-	} else
-		retval = -EINVAL;
+	pr_warn_once("Non-hierarchical mode is deprecated. "
+		     "Please report your usecase to linux-mm@kvack.org if you "
+		     "depend on this functionality.\n");
 
-	return retval;
+	return -EINVAL;
 }
 
 static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
@@ -3727,8 +3700,6 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 		child = mem_cgroup_from_css(css);
 		BUG_ON(child->kmemcg_id != kmemcg_id);
 		child->kmemcg_id = parent->kmemcg_id;
-		if (!memcg->use_hierarchy)
-			break;
 	}
 	rcu_read_unlock();
 
@@ -5319,38 +5290,22 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	if (parent) {
 		memcg->swappiness = mem_cgroup_swappiness(parent);
 		memcg->oom_kill_disable = parent->oom_kill_disable;
-	}
-	if (!parent) {
-		page_counter_init(&memcg->memory, NULL);
-		page_counter_init(&memcg->swap, NULL);
-		page_counter_init(&memcg->kmem, NULL);
-		page_counter_init(&memcg->tcpmem, NULL);
-	} else if (parent->use_hierarchy) {
-		memcg->use_hierarchy = true;
+
 		page_counter_init(&memcg->memory, &parent->memory);
 		page_counter_init(&memcg->swap, &parent->swap);
 		page_counter_init(&memcg->kmem, &parent->kmem);
 		page_counter_init(&memcg->tcpmem, &parent->tcpmem);
 	} else {
-		page_counter_init(&memcg->memory, &root_mem_cgroup->memory);
-		page_counter_init(&memcg->swap, &root_mem_cgroup->swap);
-		page_counter_init(&memcg->kmem, &root_mem_cgroup->kmem);
-		page_counter_init(&memcg->tcpmem, &root_mem_cgroup->tcpmem);
-		/*
-		 * Deeper hierachy with use_hierarchy == false doesn't make
-		 * much sense so let cgroup subsystem know about this
-		 * unfortunate state in our controller.
-		 */
-		if (parent != root_mem_cgroup)
-			memory_cgrp_subsys.broken_hierarchy = true;
-	}
+		page_counter_init(&memcg->memory, NULL);
+		page_counter_init(&memcg->swap, NULL);
+		page_counter_init(&memcg->kmem, NULL);
+		page_counter_init(&memcg->tcpmem, NULL);
 
-	/* The following stuff does not apply to the root */
-	if (!parent) {
 		root_mem_cgroup = memcg;
 		return &memcg->css;
 	}
 
+	/* The following stuff does not apply to the root */
 	error = memcg_online_kmem(memcg);
 	if (error)
 		goto fail;
@@ -6187,24 +6142,6 @@ static void mem_cgroup_move_task(void)
 }
 #endif
 
-/*
- * Cgroup retains root cgroups across [un]mount cycles making it necessary
- * to verify whether we're attached to the default hierarchy on each mount
- * attempt.
- */
-static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
-{
-	/*
-	 * use_hierarchy is forced on the default hierarchy.  cgroup core
-	 * guarantees that @root doesn't have any children, so turning it
-	 * on for the root memcg is enough.
-	 */
-	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
-		root_mem_cgroup->use_hierarchy = true;
-	else
-		root_mem_cgroup->use_hierarchy = false;
-}
-
 static int seq_puts_memcg_tunable(struct seq_file *m, unsigned long value)
 {
 	if (value == PAGE_COUNTER_MAX)
@@ -6542,7 +6479,6 @@ struct cgroup_subsys memory_cgrp_subsys = {
 	.can_attach = mem_cgroup_can_attach,
 	.cancel_attach = mem_cgroup_cancel_attach,
 	.post_attach = mem_cgroup_move_task,
-	.bind = mem_cgroup_bind,
 	.dfl_cftypes = memory_files,
 	.legacy_cftypes = mem_cgroup_legacy_files,
 	.early_init = 0,
-- 
2.26.2



  reply	other threads:[~2020-11-03 21:27 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-03 21:27 [PATCH rfc 0/3] mm: memcg: deprecate cgroup v1 non-hierarchical mode Roman Gushchin
2020-11-03 21:27 ` Roman Gushchin [this message]
2020-11-04  8:37   ` [PATCH rfc 1/3] mm: memcg: deprecate the " Michal Hocko
2020-11-04 14:58   ` Shakeel Butt
2020-11-03 21:27 ` [PATCH rfc 2/3] docs: cgroup-v1: reflect the deprecation of " Roman Gushchin
2020-11-04  8:39   ` Michal Hocko
2020-11-04 15:00   ` Shakeel Butt
2020-11-03 21:27 ` [PATCH rfc 3/3] cgroup: remove obsoleted broken_hierarchy and warned_broken_hierarchy Roman Gushchin
2020-11-04 15:01   ` Shakeel Butt

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=20201103212725.3716088-2-guro@fb.com \
    --to=guro@fb.com \
    --cc=akpm@linux-foundation.org \
    --cc=hannes@cmpxchg.org \
    --cc=kernel-team@fb.com \
    --cc=linux-kernel@vger.kernel.org \
    --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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).