commit 4929a4e6faa0f13289a67cae98139e727f0d4a97 upstream.
The quota/period ratio is used to ensure a child task group won't get
more bandwidth than the parent task group, and is calculated as:
normalized_cfs_quota() = [(quota_us << 20) / period_us]
If the quota/period ratio was changed during this scaling due to
precision loss, it will cause inconsistency between parent and child
task groups.
See below example:
A userspace container manager (kubelet) does three operations:
1) Create a parent cgroup, set quota to 1,000us and period to 10,000us.
2) Create a few children cgroups.
3) Set quota to 1,000us and period to 10,000us on a child cgroup.
These operations are expected to succeed. However, if the scaling of
147/128 happens before step 3, quota and period of the parent cgroup
will be changed:
new_quota: 1148437ns, 1148us
new_period: 11484375ns, 11484us
And when step 3 comes in, the ratio of the child cgroup will be
104857, which will be larger than the parent cgroup ratio (104821),
and will fail.
Scaling them by a factor of 2 will fix the problem.
Tested-by: Phil Auld <pauld(a)redhat.com>
Signed-off-by: Xuewei Zhang <xueweiz(a)google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org>
Acked-by: Phil Auld <pauld(a)redhat.com>
Cc: Anton Blanchard <anton(a)ozlabs.org>
Cc: Ben Segall <bsegall(a)google.com>
Cc: Dietmar Eggemann <dietmar.eggemann(a)arm.com>
Cc: Juri Lelli <juri.lelli(a)redhat.com>
Cc: Linus Torvalds <torvalds(a)linux-foundation.org>
Cc: Mel Gorman <mgorman(a)suse.de>
Cc: Peter Zijlstra <peterz(a)infradead.org>
Cc: Steven Rostedt <rostedt(a)goodmis.org>
Cc: Thomas Gleixner <tglx(a)linutronix.de>
Cc: Vincent Guittot <vincent.guittot(a)linaro.org>
Fixes: 2e8e19226398 ("sched/fair: Limit sched_cfs_period_timer() loop to avoid hard lockup")
Link: https://lkml.kernel.org/r/20191004001243.140897-1-xueweiz@google.com
Signed-off-by: Ingo Molnar <mingo(a)kernel.org>
---
kernel/sched/fair.c | 36 ++++++++++++++++++++++--------------
1 file changed, 22 insertions(+), 14 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ea2d33aa1f55..773135f534ef 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3753,20 +3753,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
if (++count > 3) {
u64 new, old = ktime_to_ns(cfs_b->period);
- new = (old * 147) / 128; /* ~115% */
- new = min(new, max_cfs_quota_period);
-
- cfs_b->period = ns_to_ktime(new);
-
- /* since max is 1s, this is limited to 1e9^2, which fits in u64 */
- cfs_b->quota *= new;
- cfs_b->quota = div64_u64(cfs_b->quota, old);
-
- pr_warn_ratelimited(
- "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n",
- smp_processor_id(),
- div_u64(new, NSEC_PER_USEC),
- div_u64(cfs_b->quota, NSEC_PER_USEC));
+ /*
+ * Grow period by a factor of 2 to avoid losing precision.
+ * Precision loss in the quota/period ratio can cause __cfs_schedulable
+ * to fail.
+ */
+ new = old * 2;
+ if (new < max_cfs_quota_period) {
+ cfs_b->period = ns_to_ktime(new);
+ cfs_b->quota *= 2;
+
+ pr_warn_ratelimited(
+ "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us = %lld, cfs_quota_us = %lld)\n",
+ smp_processor_id(),
+ div_u64(new, NSEC_PER_USEC),
+ div_u64(cfs_b->quota, NSEC_PER_USEC));
+ } else {
+ pr_warn_ratelimited(
+ "cfs_period_timer[cpu%d]: period too short, but cannot scale up without losing precision (cfs_period_us = %lld, cfs_quota_us = %lld)\n",
+ smp_processor_id(),
+ div_u64(old, NSEC_PER_USEC),
+ div_u64(cfs_b->quota, NSEC_PER_USEC));
+ }
/* reset count so we don't come right back in here */
count = 0;
--
2.24.0.393.g34dc348eaf-goog
From: Yang Shi <yang.shi(a)linux.alibaba.com>
Subject: mm: move_pages: return valid node id in status if the page is already on the target node
Felix Abecassis reports move_pages() would return random status if the
pages are already on the target node by the below test program:
---8<---
int main(void)
{
const long node_id = 1;
const long page_size = sysconf(_SC_PAGESIZE);
const int64_t num_pages = 8;
unsigned long nodemask = 1 << node_id;
long ret = set_mempolicy(MPOL_BIND, &nodemask, sizeof(nodemask));
if (ret < 0)
return (EXIT_FAILURE);
void **pages = malloc(sizeof(void*) * num_pages);
for (int i = 0; i < num_pages; ++i) {
pages[i] = mmap(NULL, page_size, PROT_WRITE | PROT_READ,
MAP_PRIVATE | MAP_POPULATE | MAP_ANONYMOUS,
-1, 0);
if (pages[i] == MAP_FAILED)
return (EXIT_FAILURE);
}
ret = set_mempolicy(MPOL_DEFAULT, NULL, 0);
if (ret < 0)
return (EXIT_FAILURE);
int *nodes = malloc(sizeof(int) * num_pages);
int *status = malloc(sizeof(int) * num_pages);
for (int i = 0; i < num_pages; ++i) {
nodes[i] = node_id;
status[i] = 0xd0; /* simulate garbage values */
}
ret = move_pages(0, num_pages, pages, nodes, status, MPOL_MF_MOVE);
printf("move_pages: %ld
", ret);
for (int i = 0; i < num_pages; ++i)
printf("status[%d] = %d
", i, status[i]);
}
---8<---
Then running the program would return nonsense status values:
$ ./move_pages_bug
move_pages: 0
status[0] = 208
status[1] = 208
status[2] = 208
status[3] = 208
status[4] = 208
status[5] = 208
status[6] = 208
status[7] = 208
This is because the status is not set if the page is already on the target
node, but move_pages() should return valid status as long as it succeeds.
The valid status may be errno or node id.
We can't simply initialize status array to zero since the pages may be not
on node 0. Fix it by updating status with node id which the page is
already on.
Link: http://lkml.kernel.org/r/1575584353-125392-1-git-send-email-yang.shi@linux.…
Fixes: a49bd4d71637 ("mm, numa: rework do_pages_move")
Signed-off-by: Yang Shi <yang.shi(a)linux.alibaba.com>
Reported-by: Felix Abecassis <fabecassis(a)nvidia.com>
Tested-by: Felix Abecassis <fabecassis(a)nvidia.com>
Suggested-by: Michal Hocko <mhocko(a)suse.com>
Reviewed-by: John Hubbard <jhubbard(a)nvidia.com>
Acked-by: Christoph Lameter <cl(a)linux.com>
Acked-by: Michal Hocko <mhocko(a)suse.com>
Reviewed-by: Vlastimil Babka <vbabka(a)suse.cz>
Cc: Mel Gorman <mgorman(a)techsingularity.net>
Cc: <stable(a)vger.kernel.org> [4.17+]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/migrate.c | 23 +++++++++++++++++------
1 file changed, 17 insertions(+), 6 deletions(-)
--- a/mm/migrate.c~mm-move_pages-return-valid-node-id-in-status-if-the-page-is-already-on-the-target-node
+++ a/mm/migrate.c
@@ -1512,9 +1512,11 @@ static int do_move_pages_to_node(struct
/*
* Resolves the given address to a struct page, isolates it from the LRU and
* puts it to the given pagelist.
- * Returns -errno if the page cannot be found/isolated or 0 when it has been
- * queued or the page doesn't need to be migrated because it is already on
- * the target node
+ * Returns:
+ * errno - if the page cannot be found/isolated
+ * 0 - when it doesn't have to be migrated because it is already on the
+ * target node
+ * 1 - when it has been queued
*/
static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
int node, struct list_head *pagelist, bool migrate_all)
@@ -1553,7 +1555,7 @@ static int add_page_for_migration(struct
if (PageHuge(page)) {
if (PageHead(page)) {
isolate_huge_page(page, pagelist);
- err = 0;
+ err = 1;
}
} else {
struct page *head;
@@ -1563,7 +1565,7 @@ static int add_page_for_migration(struct
if (err)
goto out_putpage;
- err = 0;
+ err = 1;
list_add_tail(&head->lru, pagelist);
mod_node_page_state(page_pgdat(head),
NR_ISOLATED_ANON + page_is_file_cache(head),
@@ -1640,8 +1642,17 @@ static int do_pages_move(struct mm_struc
*/
err = add_page_for_migration(mm, addr, current_node,
&pagelist, flags & MPOL_MF_MOVE_ALL);
- if (!err)
+
+ if (!err) {
+ /* The page is already on the target node */
+ err = store_status(status, i, current_node, 1);
+ if (err)
+ goto out_flush;
continue;
+ } else if (err > 0) {
+ /* The page is successfully queued for migration */
+ continue;
+ }
err = store_status(status, i, err, 1);
if (err)
_
From: Shakeel Butt <shakeelb(a)google.com>
Subject: memcg: account security cred as well to kmemcg
The cred_jar kmem_cache is already memcg accounted in the current kernel
but cred->security is not. Account cred->security to kmemcg.
Recently we saw high root slab usage on our production and on further
inspection, we found a buggy application leaking processes. Though
that buggy application was contained within its memcg but we observe
much more system memory overhead, couple of GiBs, during that period.
This overhead can adversely impact the isolation on the system. One of
source of high overhead, we found was cred->secuity objects, which have
a lifetime of at least the life of the process which allocated them.
Link: http://lkml.kernel.org/r/20191205223721.40034-1-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb(a)google.com>
Acked-by: Chris Down <chris(a)chrisdown.name>
Reviewed-by: Roman Gushchin <guro(a)fb.com>
Acked-by: Michal Hocko <mhocko(a)suse.com>
Cc: Johannes Weiner <hannes(a)cmpxchg.org>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
kernel/cred.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
--- a/kernel/cred.c~memcg-account-security-cred-as-well-to-kmemcg
+++ a/kernel/cred.c
@@ -223,7 +223,7 @@ struct cred *cred_alloc_blank(void)
new->magic = CRED_MAGIC;
#endif
- if (security_cred_alloc_blank(new, GFP_KERNEL) < 0)
+ if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
goto error;
return new;
@@ -282,7 +282,7 @@ struct cred *prepare_creds(void)
new->security = NULL;
#endif
- if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+ if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
goto error;
validate_creds(new);
return new;
@@ -715,7 +715,7 @@ struct cred *prepare_kernel_cred(struct
#ifdef CONFIG_SECURITY
new->security = NULL;
#endif
- if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+ if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
goto error;
put_cred(old);
_
From: Chanho Min <chanho.min(a)lge.com>
Subject: mm/zsmalloc.c: fix the migrated zspage statistics.
When zspage is migrated to the other zone, the zone page state should be
updated as well, otherwise the NR_ZSPAGE for each zone shows wrong counts
including proc/zoneinfo in practice.
Link: http://lkml.kernel.org/r/1575434841-48009-1-git-send-email-chanho.min@lge.c…
Fixes: 91537fee0013 ("mm: add NR_ZSMALLOC to vmstat")
Signed-off-by: Chanho Min <chanho.min(a)lge.com>
Signed-off-by: Jinsuk Choi <jjinsuk.choi(a)lge.com>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky(a)gmail.com>
Acked-by: Minchan Kim <minchan(a)kernel.org>
Cc: <stable(a)vger.kernel.org> [4.9+]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/zsmalloc.c | 5 +++++
1 file changed, 5 insertions(+)
--- a/mm/zsmalloc.c~mm-zsmallocc-fix-the-migrated-zspage-statistics
+++ a/mm/zsmalloc.c
@@ -2069,6 +2069,11 @@ static int zs_page_migrate(struct addres
zs_pool_dec_isolated(pool);
}
+ if (page_zone(newpage) != page_zone(page)) {
+ dec_zone_page_state(page, NR_ZSPAGES);
+ inc_zone_page_state(newpage, NR_ZSPAGES);
+ }
+
reset_page(page);
put_page(page);
page = newpage;
_