All of lore.kernel.org
 help / color / mirror / Atom feed
* + memcg-page_alloc-skip-bulk-allocator-for-__gfp_account.patch added to -mm tree
@ 2021-10-13 21:09 akpm
  0 siblings, 0 replies; 2+ messages in thread
From: akpm @ 2021-10-13 21:09 UTC (permalink / raw)
  To: guro, hannes, mgorman, mhocko, mm-commits, shakeelb, urezki, vvs


The patch titled
     Subject: memcg: page_alloc: skip bulk allocator for __GFP_ACCOUNT
has been added to the -mm tree.  Its filename is
     memcg-page_alloc-skip-bulk-allocator-for-__gfp_account.patch

This patch should soon appear at
    https://ozlabs.org/~akpm/mmots/broken-out/memcg-page_alloc-skip-bulk-allocator-for-__gfp_account.patch
and later at
    https://ozlabs.org/~akpm/mmotm/broken-out/memcg-page_alloc-skip-bulk-allocator-for-__gfp_account.patch

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next and is updated
there every 3-4 working days

------------------------------------------------------
From: Shakeel Butt <shakeelb@google.com>
Subject: memcg: page_alloc: skip bulk allocator for __GFP_ACCOUNT

The commit 5c1f4e690eec ("mm/vmalloc: switch to bulk allocator in
__vmalloc_area_node()") switched to bulk page allocator for order 0
allocation backing vmalloc.  However bulk page allocator does not support
__GFP_ACCOUNT allocations and there are several users of
kvmalloc(__GFP_ACCOUNT).

For now make __GFP_ACCOUNT allocations bypass bulk page allocator.  In
future if there is workload that can be significantly improved with the
bulk page allocator with __GFP_ACCCOUNT support, we can revisit the
decision.

Link: https://lkml.kernel.org/r/20211013194338.1804247-1-shakeelb@google.com
Fixes: 5c1f4e690eec ("mm/vmalloc: switch to bulk allocator in __vmalloc_area_node()")
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Uladzislau Rezki <urezki@gmail.com>
Cc: Vasily Averin <vvs@virtuozzo.com>
Cc: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/page_alloc.c |    4 ++++
 1 file changed, 4 insertions(+)

--- a/mm/page_alloc.c~memcg-page_alloc-skip-bulk-allocator-for-__gfp_account
+++ a/mm/page_alloc.c
@@ -5208,6 +5208,10 @@ unsigned long __alloc_pages_bulk(gfp_t g
 	unsigned int alloc_flags = ALLOC_WMARK_LOW;
 	int nr_populated = 0, nr_account = 0;
 
+	/* Bulk allocator does not support memcg accounting. */
+	if (unlikely(gfp & __GFP_ACCOUNT))
+		goto out;
+
 	/*
 	 * Skip populated array elements to determine if any pages need
 	 * to be allocated before disabling IRQs.
_

Patches currently in -mm which might be from shakeelb@google.com are

memcg-flush-stats-only-if-updated.patch
memcg-unify-memcg-stat-flushing.patch
memcg-page_alloc-skip-bulk-allocator-for-__gfp_account.patch


^ permalink raw reply	[flat|nested] 2+ messages in thread

* + memcg-page_alloc-skip-bulk-allocator-for-__gfp_account.patch added to -mm tree
@ 2021-10-15 20:54 akpm
  0 siblings, 0 replies; 2+ messages in thread
From: akpm @ 2021-10-15 20:54 UTC (permalink / raw)
  To: david, guro, hannes, mhocko, mm-commits, shakeelb, vvs


The patch titled
     Subject: memcg: page_alloc: skip bulk allocator for __GFP_ACCOUNT
has been added to the -mm tree.  Its filename is
     memcg-page_alloc-skip-bulk-allocator-for-__gfp_account.patch

This patch should soon appear at
    https://ozlabs.org/~akpm/mmots/broken-out/memcg-page_alloc-skip-bulk-allocator-for-__gfp_account.patch
and later at
    https://ozlabs.org/~akpm/mmotm/broken-out/memcg-page_alloc-skip-bulk-allocator-for-__gfp_account.patch

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next and is updated
there every 3-4 working days

------------------------------------------------------
From: Shakeel Butt <shakeelb@google.com>
Subject: memcg: page_alloc: skip bulk allocator for __GFP_ACCOUNT

commit 5c1f4e690eec ("mm/vmalloc: switch to bulk allocator in
__vmalloc_area_node()") switched to bulk page allocator for order 0
allocation backing vmalloc.  However bulk page allocator does not support
__GFP_ACCOUNT allocations and there are several users of
kvmalloc(__GFP_ACCOUNT).

For now make __GFP_ACCOUNT allocations bypass bulk page allocator.  In
future if there is workload that can be significantly improved with the
bulk page allocator with __GFP_ACCCOUNT support, we can revisit the
decision.

Link: https://lkml.kernel.org/r/20211014151607.2171970-1-shakeelb@google.com
Fixes: 5c1f4e690eec ("mm/vmalloc: switch to bulk allocator in __vmalloc_area_node()")
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Reported-by: Vasily Averin <vvs@virtuozzo.com>
Tested-by: Vasily Averin <vvs@virtuozzo.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/page_alloc.c |    4 ++++
 1 file changed, 4 insertions(+)

--- a/mm/page_alloc.c~memcg-page_alloc-skip-bulk-allocator-for-__gfp_account
+++ a/mm/page_alloc.c
@@ -5223,6 +5223,10 @@ unsigned long __alloc_pages_bulk(gfp_t g
 	if (unlikely(page_array && nr_pages - nr_populated == 0))
 		goto out;
 
+	/* Bulk allocator does not support memcg accounting. */
+	if (memcg_kmem_enabled() && (gfp & __GFP_ACCOUNT))
+		goto failed;
+
 	/* Use the single page allocator for one page. */
 	if (nr_pages - nr_populated == 1)
 		goto failed;
_

Patches currently in -mm which might be from shakeelb@google.com are

memcg-flush-stats-only-if-updated.patch
memcg-unify-memcg-stat-flushing.patch
memcg-page_alloc-skip-bulk-allocator-for-__gfp_account.patch


^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2021-10-15 20:54 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-10-13 21:09 + memcg-page_alloc-skip-bulk-allocator-for-__gfp_account.patch added to -mm tree akpm
2021-10-15 20:54 akpm

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.