[PATCHSET] mm, memcontrol: Implement memory.swap.events

[PATCHSET] mm, memcontrol: Implement memory.swap.events

[Tejun Heo]

Hello,

This patchset implements memory.swap.events which contains max and
fail events so that userland can monitor and respond to swap running
out.  It contains the following two patches.

 0001-mm-memcontrol-Move-swap-charge-handling-into-get_swa.patch
 0002-mm-memcontrol-Implement-memory.swap.events.patch

This patchset is on top of the "cgroup/for-4.17: Make cgroup_rstat
available to controllers" patchset[1] and "mm, memcontrol: Make
cgroup_rstat available to controllers" patchset[2] and also available
in the following git branch.

 git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git review-memcg-swap.events

diffstat follows.

 Documentation/cgroup-v2.txt |   16 ++++++++++++++++
 include/linux/memcontrol.h  |    5 +++++
 mm/memcontrol.c             |   25 +++++++++++++++++++++++++
 mm/shmem.c                  |    4 ----
 mm/swap_slots.c             |   10 +++++++---
 mm/swap_state.c             |    3 ---
 6 files changed, 53 insertions(+), 10 deletions(-)

Thanks.

--
tejun

[1] http://lkml.kernel.org/r/20180323231313.1254142-1-tj@kernel.org
[2] http://lkml.kernel.org/r/20180324160901.512135-1-tj@kernel.org

[PATCH 1/2] mm, memcontrol: Move swap charge handling into get_swap_page()

[Tejun Heo]

get_swap_page() is always followed by mem_cgroup_try_charge_swap().
This patch moves mem_cgroup_try_charge_swap() into get_swap_page() and
makes get_swap_page() call the function even after swap allocation
failure.

This simplifies the callers and consolidates memcg related logic and
will ease adding swap related memcg events.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memcontrol.c |  3 +++
 mm/shmem.c      |  4 ----
 mm/swap_slots.c | 10 +++++++---
 mm/swap_state.c |  3 ---
 4 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d5bf01d..9f9c8a7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5987,6 +5987,9 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 	if (!memcg)
 		return 0;
 
+	if (!entry.val)
+		return 0;
+
 	memcg = mem_cgroup_id_get_online(memcg);
 
 	if (!mem_cgroup_is_root(memcg) &&
diff --git a/mm/shmem.c b/mm/shmem.c
index 1907688..4a07d21 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1313,9 +1313,6 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	if (!swap.val)
 		goto redirty;
 
-	if (mem_cgroup_try_charge_swap(page, swap))
-		goto free_swap;
-
 	/*
 	 * Add inode to shmem_unuse()'s list of swapped-out inodes,
 	 * if it's not already there.  Do it now before the page is
@@ -1344,7 +1341,6 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	}
 
 	mutex_unlock(&shmem_swaplist_mutex);
-free_swap:
 	put_swap_page(page, swap);
 redirty:
 	set_page_dirty(page);
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index bebc192..7546eb2 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -319,7 +319,7 @@ swp_entry_t get_swap_page(struct page *page)
 	if (PageTransHuge(page)) {
 		if (IS_ENABLED(CONFIG_THP_SWAP))
 			get_swap_pages(1, true, &entry);
-		return entry;
+		goto out;
 	}
 
 	/*
@@ -349,11 +349,15 @@ swp_entry_t get_swap_page(struct page *page)
 		}
 		mutex_unlock(&cache->alloc_lock);
 		if (entry.val)
-			return entry;
+			goto out;
 	}
 
 	get_swap_pages(1, false, &entry);
-
+out:
+	if (mem_cgroup_try_charge_swap(page, entry)) {
+		put_swap_page(page, entry);
+		entry.val = 0;
+	}
 	return entry;
 }
 
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 39ae7cf..41f0809 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -216,9 +216,6 @@ int add_to_swap(struct page *page)
 	if (!entry.val)
 		return 0;
 
-	if (mem_cgroup_try_charge_swap(page, entry))
-		goto fail;
-
 	/*
 	 * Radix-tree node allocations from PF_MEMALLOC contexts could
 	 * completely exhaust the page allocator. __GFP_NOMEMALLOC
-- 
2.9.5

[PATCH 2/2] mm, memcontrol: Implement memory.swap.events

[Tejun Heo]

Add swap max and fail events so that userland can monitor and respond
to running out of swap.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-api@vger.kernel.org
---
 Documentation/cgroup-v2.txt | 16 ++++++++++++++++
 include/linux/memcontrol.h  |  5 +++++
 mm/memcontrol.c             | 24 +++++++++++++++++++++++-
 3 files changed, 44 insertions(+), 1 deletion(-)

diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
index 74cdeae..b0dda10 100644
--- a/Documentation/cgroup-v2.txt
+++ b/Documentation/cgroup-v2.txt
@@ -1199,6 +1199,22 @@ PAGE_SIZE multiple when read back.
 	Swap usage hard limit.  If a cgroup's swap usage reaches this
 	limit, anonymous memory of the cgroup will not be swapped out.
 
+  memory.swap.events
+	A read-only flat-keyed file which exists on non-root cgroups.
+	The following entries are defined.  Unless specified
+	otherwise, a value change in this file generates a file
+	modified event.
+
+	  max
+		The number of times the cgroup's swap usage was about
+		to go over the max boundary and swap allocation
+		failed.
+
+	  fail
+		The number of times swap allocation failed either
+		because of running out of swap system-wide or max
+		limit.
+
 
 Usage Guidelines
 ~~~~~~~~~~~~~~~~
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 85a8f00..f198339 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -54,6 +54,8 @@ enum memcg_event_item {
 	MEMCG_HIGH,
 	MEMCG_MAX,
 	MEMCG_OOM,
+	MEMCG_SWAP_MAX,
+	MEMCG_SWAP_FAIL,
 	MEMCG_NR_EVENTS,
 };
 
@@ -202,6 +204,9 @@ struct mem_cgroup {
 	/* handle for "memory.events" */
 	struct cgroup_file events_file;
 
+	/* handle for "memory.swap.events" */
+	struct cgroup_file swap_events_file;
+
 	/* protect arrays of thresholds */
 	struct mutex thresholds_lock;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9f9c8a7..1a14d4a4 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5987,13 +5987,17 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 	if (!memcg)
 		return 0;
 
-	if (!entry.val)
+	if (!entry.val) {
+		mem_cgroup_event(memcg, MEMCG_SWAP_FAIL);
 		return 0;
+	}
 
 	memcg = mem_cgroup_id_get_online(memcg);
 
 	if (!mem_cgroup_is_root(memcg) &&
 	    !page_counter_try_charge(&memcg->swap, nr_pages, &counter)) {
+		mem_cgroup_event(memcg, MEMCG_SWAP_MAX);
+		mem_cgroup_event(memcg, MEMCG_SWAP_FAIL);
 		mem_cgroup_id_put(memcg);
 		return -ENOMEM;
 	}
@@ -6131,6 +6135,18 @@ static ssize_t swap_max_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
+static int swap_events_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+
+	memcg_stat_flush(memcg);
+
+	seq_printf(m, "max %llu\n", memcg->events[MEMCG_SWAP_MAX]);
+	seq_printf(m, "fail %llu\n", memcg->events[MEMCG_SWAP_FAIL]);
+
+	return 0;
+}
+
 static struct cftype swap_files[] = {
 	{
 		.name = "swap.current",
@@ -6143,6 +6159,12 @@ static struct cftype swap_files[] = {
 		.seq_show = swap_max_show,
 		.write = swap_max_write,
 	},
+	{
+		.name = "swap.events",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.file_offset = offsetof(struct mem_cgroup, swap_events_file),
+		.seq_show = swap_events_show,
+	},
 	{ }	/* terminate */
 };
 
-- 
2.9.5

Re: [PATCHSET] mm, memcontrol: Implement memory.swap.events

[Andrew Morton]

On Sat, 24 Mar 2018 09:51:25 -0700 Tejun Heo <tj@kernel.org> wrote:

> This patchset implements memory.swap.events which contains max and
> fail events so that userland can monitor and respond to swap running
> out.  It contains the following two patches.
> 
>  0001-mm-memcontrol-Move-swap-charge-handling-into-get_swa.patch
>  0002-mm-memcontrol-Implement-memory.swap.events.patch
> 
> This patchset is on top of the "cgroup/for-4.17: Make cgroup_rstat
> available to controllers" patchset[1] and "mm, memcontrol: Make
> cgroup_rstat available to controllers" patchset[2] and also available
> in the following git branch.
> 
>  git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git review-memcg-swap.events

This doesn't appear to be in linux-next yet.  It should be by now if it's
targeted at 4.17?

Re: [PATCHSET] mm, memcontrol: Implement memory.swap.events

[Tejun Heo]

On Mon, Mar 26, 2018 at 02:39:31PM -0700, Andrew Morton wrote:
> On Sat, 24 Mar 2018 09:51:25 -0700 Tejun Heo <tj@kernel.org> wrote:
> 
> > This patchset implements memory.swap.events which contains max and
> > fail events so that userland can monitor and respond to swap running
> > out.  It contains the following two patches.
> > 
> >  0001-mm-memcontrol-Move-swap-charge-handling-into-get_swa.patch
> >  0002-mm-memcontrol-Implement-memory.swap.events.patch
> > 
> > This patchset is on top of the "cgroup/for-4.17: Make cgroup_rstat
> > available to controllers" patchset[1] and "mm, memcontrol: Make
> > cgroup_rstat available to controllers" patchset[2] and also available
> > in the following git branch.
> > 
> >  git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git review-memcg-swap.events
> 
> This doesn't appear to be in linux-next yet.  It should be by now if it's
> targeted at 4.17?

You're right.  It's too late for 4.17.  Let's aim for 4.18.

Thanks.

-- 
tejun

Re: [PATCHSET] mm, memcontrol: Implement memory.swap.events

[Michal Hocko]

Hi Tejun,
sorry for the late response. Are you plannig to repost?

On Sat 24-03-18 09:51:25, Tejun Heo wrote:
> Hello,
> 
> This patchset implements memory.swap.events which contains max and
> fail events so that userland can monitor and respond to swap running
> out.  It contains the following two patches.
> 
>  0001-mm-memcontrol-Move-swap-charge-handling-into-get_swa.patch
>  0002-mm-memcontrol-Implement-memory.swap.events.patch
> 
> This patchset is on top of the "cgroup/for-4.17: Make cgroup_rstat
> available to controllers" patchset[1] and "mm, memcontrol: Make
> cgroup_rstat available to controllers" patchset[2] and also available
> in the following git branch.
> 
>  git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git review-memcg-swap.events
> 
> diffstat follows.
> 
>  Documentation/cgroup-v2.txt |   16 ++++++++++++++++
>  include/linux/memcontrol.h  |    5 +++++
>  mm/memcontrol.c             |   25 +++++++++++++++++++++++++
>  mm/shmem.c                  |    4 ----
>  mm/swap_slots.c             |   10 +++++++---
>  mm/swap_state.c             |    3 ---
>  6 files changed, 53 insertions(+), 10 deletions(-)
> 
> Thanks.
> 
> --
> tejun
> 
> [1] http://lkml.kernel.org/r/20180323231313.1254142-1-tj@kernel.org
> [2] http://lkml.kernel.org/r/20180324160901.512135-1-tj@kernel.org

-- 
Michal Hocko
SUSE Labs

Re: [PATCHSET] mm, memcontrol: Implement memory.swap.events

[Tejun Heo]

On Thu, Apr 12, 2018 at 04:13:45PM +0200, Michal Hocko wrote:
> Hi Tejun,
> sorry for the late response. Are you plannig to repost?

Yeah, will do later.

Thanks.

-- 
tejun

[PATCHSET v2] mm, memcontrol: Implement memory.swap.events

[Tejun Heo]

Hello,

Rebased on top of e27be240df53 ("mm: memcg: make sure memory.events is
uptodate when waking pollers").

This patchset implements memory.swap.events which contains max and
fail events so that userland can monitor and respond to swap running
out.  It contains the following two patches.

 0001-mm-memcontrol-Move-swap-charge-handling-into-get_swa.patch
 0002-mm-memcontrol-Implement-memory.swap.events.patch

This patchset is on top of the current linus#master
(a27fc14219f2e3c4a46ba9177b04d9b52c875532).

Thanks.

-- 
tejun

[PATCH 1/2] mm, memcontrol: Move swap charge handling into get_swap_page()

[Tejun Heo]

get_swap_page() is always followed by mem_cgroup_try_charge_swap().
This patch moves mem_cgroup_try_charge_swap() into get_swap_page() and
makes get_swap_page() call the function even after swap allocation
failure.

This simplifies the callers and consolidates memcg related logic and
will ease adding swap related memcg events.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memcontrol.c |    3 +++
 mm/shmem.c      |    4 ----
 mm/swap_slots.c |   10 +++++++---
 mm/swap_state.c |    3 ---
 4 files changed, 10 insertions(+), 10 deletions(-)

--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6012,6 +6012,9 @@ int mem_cgroup_try_charge_swap(struct pa
 	if (!memcg)
 		return 0;
 
+	if (!entry.val)
+		return 0;
+
 	memcg = mem_cgroup_id_get_online(memcg);
 
 	if (!mem_cgroup_is_root(memcg) &&
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1322,9 +1322,6 @@ static int shmem_writepage(struct page *
 	if (!swap.val)
 		goto redirty;
 
-	if (mem_cgroup_try_charge_swap(page, swap))
-		goto free_swap;
-
 	/*
 	 * Add inode to shmem_unuse()'s list of swapped-out inodes,
 	 * if it's not already there.  Do it now before the page is
@@ -1353,7 +1350,6 @@ static int shmem_writepage(struct page *
 	}
 
 	mutex_unlock(&shmem_swaplist_mutex);
-free_swap:
 	put_swap_page(page, swap);
 redirty:
 	set_page_dirty(page);
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -317,7 +317,7 @@ swp_entry_t get_swap_page(struct page *p
 	if (PageTransHuge(page)) {
 		if (IS_ENABLED(CONFIG_THP_SWAP))
 			get_swap_pages(1, true, &entry);
-		return entry;
+		goto out;
 	}
 
 	/*
@@ -347,10 +347,14 @@ repeat:
 		}
 		mutex_unlock(&cache->alloc_lock);
 		if (entry.val)
-			return entry;
+			goto out;
 	}
 
 	get_swap_pages(1, false, &entry);
-
+out:
+	if (mem_cgroup_try_charge_swap(page, entry)) {
+		put_swap_page(page, entry);
+		entry.val = 0;
+	}
 	return entry;
 }
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -216,9 +216,6 @@ int add_to_swap(struct page *page)
 	if (!entry.val)
 		return 0;
 
-	if (mem_cgroup_try_charge_swap(page, entry))
-		goto fail;
-
 	/*
 	 * Radix-tree node allocations from PF_MEMALLOC contexts could
 	 * completely exhaust the page allocator. __GFP_NOMEMALLOC