From: Marco Elver <elver(a)google.com>
Subject: kfence: fix is_kfence_address() for addresses below KFENCE_POOL_SIZE
Originally the addr != NULL check was meant to take care of the case where
__kfence_pool == NULL (KFENCE is disabled). However, this does not work
for addresses where addr > 0 && addr < KFENCE_POOL_SIZE.
This can be the case on NULL-deref where addr > 0 && addr < PAGE_SIZE or
any other faulting access with addr < KFENCE_POOL_SIZE. While the kernel
would likely crash, the stack traces and report might be confusing due to
double faults upon KFENCE's attempt to unprotect such an address.
Fix it by just checking that __kfence_pool != NULL instead.
Link: https://lkml.kernel.org/r/20210818130300.2482437-1-elver@google.com
Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure")
Signed-off-by: Marco Elver <elver(a)google.com>
Reported-by: Kuan-Ying Lee <Kuan-Ying.Lee(a)mediatek.com>
Acked-by: Alexander Potapenko <glider(a)google.com>
Cc: Dmitry Vyukov <dvyukov(a)google.com>
Cc: <stable(a)vger.kernel.org> [5.12+]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
include/linux/kfence.h | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
--- a/include/linux/kfence.h~kfence-fix-is_kfence_address-for-addresses-below-kfence_pool_size
+++ a/include/linux/kfence.h
@@ -51,10 +51,11 @@ extern atomic_t kfence_allocation_gate;
static __always_inline bool is_kfence_address(const void *addr)
{
/*
- * The non-NULL check is required in case the __kfence_pool pointer was
- * never initialized; keep it in the slow-path after the range-check.
+ * The __kfence_pool != NULL check is required to deal with the case
+ * where __kfence_pool == NULL && addr < KFENCE_POOL_SIZE. Keep it in
+ * the slow-path after the range-check!
*/
- return unlikely((unsigned long)((char *)addr - __kfence_pool) < KFENCE_POOL_SIZE && addr);
+ return unlikely((unsigned long)((char *)addr - __kfence_pool) < KFENCE_POOL_SIZE && __kfence_pool);
}
/**
_
From: Naoya Horiguchi <naoya.horiguchi(a)nec.com>
Subject: mm/hwpoison: retry with shake_page() for unhandlable pages
HWPoisonHandlable() sometimes returns false for typical user pages due to
races with average memory events like transfers over LRU lists. This
causes failures in hwpoison handling.
There's retry code for such a case but does not work because the retry
loop reaches the retry limit too quickly before the page settles down to
handlable state. Let get_any_page() call shake_page() to fix it.
[naoya.horiguchi(a)nec.com: get_any_page(): return -EIO when retry limit reached]
Link: https://lkml.kernel.org/r/20210819001958.2365157-1-naoya.horiguchi@linux.dev
Link: https://lkml.kernel.org/r/20210817053703.2267588-1-naoya.horiguchi@linux.dev
Fixes: 25182f05ffed ("mm,hwpoison: fix race with hugetlb page allocation")
Signed-off-by: Naoya Horiguchi <naoya.horiguchi(a)nec.com>
Reported-by: Tony Luck <tony.luck(a)intel.com>
Reviewed-by: Yang Shi <shy828301(a)gmail.com>
Cc: Oscar Salvador <osalvador(a)suse.de>
Cc: Muchun Song <songmuchun(a)bytedance.com>
Cc: Mike Kravetz <mike.kravetz(a)oracle.com>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: <stable(a)vger.kernel.org> [5.13+]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/memory-failure.c | 12 +++++++++---
1 file changed, 9 insertions(+), 3 deletions(-)
--- a/mm/memory-failure.c~mm-hwpoison-retry-with-shake_page-for-unhandlable-pages
+++ a/mm/memory-failure.c
@@ -1146,7 +1146,7 @@ static int __get_hwpoison_page(struct pa
* unexpected races caused by taking a page refcount.
*/
if (!HWPoisonHandlable(head))
- return 0;
+ return -EBUSY;
if (PageTransHuge(head)) {
/*
@@ -1199,9 +1199,15 @@ try_again:
}
goto out;
} else if (ret == -EBUSY) {
- /* We raced with freeing huge page to buddy, retry. */
- if (pass++ < 3)
+ /*
+ * We raced with (possibly temporary) unhandlable
+ * page, retry.
+ */
+ if (pass++ < 3) {
+ shake_page(p, 1);
goto try_again;
+ }
+ ret = -EIO;
goto out;
}
}
_
From: Johannes Weiner <hannes(a)cmpxchg.org>
Subject: mm: memcontrol: fix occasional OOMs due to proportional memory.low reclaim
We've noticed occasional OOM killing when memory.low settings are in
effect for cgroups. This is unexpected and undesirable as memory.low
is supposed to express non-OOMing memory priorities between cgroups.
The reason for this is proportional memory.low reclaim. When cgroups
are below their memory.low threshold, reclaim passes them over in the
first round, and then retries if it couldn't find pages anywhere else.
But when cgroups are slightly above their memory.low setting, page scan
force is scaled down and diminished in proportion to the overage, to
the point where it can cause reclaim to fail as well - only in that
case we currently don't retry, and instead trigger OOM.
To fix this, hook proportional reclaim into the same retry logic we
have in place for when cgroups are skipped entirely. This way if
reclaim fails and some cgroups were scanned with diminished pressure,
we'll try another full-force cycle before giving up and OOMing.
[akpm(a)linux-foundation.org: coding-style fixes]
Link: https://lkml.kernel.org/r/20210817180506.220056-1-hannes@cmpxchg.org
Fixes: 9783aa9917f8 ("mm, memcg: proportional memory.{low,min} reclaim")
Signed-off-by: Johannes Weiner <hannes(a)cmpxchg.org>
Reported-by: Leon Yang <lnyng(a)fb.com>
Reviewed-by: Rik van Riel <riel(a)surriel.com>
Reviewed-by: Shakeel Butt <shakeelb(a)google.com>
Acked-by: Roman Gushchin <guro(a)fb.com>
Acked-by: Chris Down <chris(a)chrisdown.name>
Acked-by: Michal Hocko <mhocko(a)suse.com>
Cc: <stable(a)vger.kernel.org> [5.4+]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
include/linux/memcontrol.h | 29 +++++++++++++++--------------
mm/vmscan.c | 27 +++++++++++++++++++--------
2 files changed, 34 insertions(+), 22 deletions(-)
--- a/include/linux/memcontrol.h~mm-memcontrol-fix-occasional-ooms-due-to-proportional-memorylow-reclaim
+++ a/include/linux/memcontrol.h
@@ -612,12 +612,15 @@ static inline bool mem_cgroup_disabled(v
return !cgroup_subsys_enabled(memory_cgrp_subsys);
}
-static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
- struct mem_cgroup *memcg,
- bool in_low_reclaim)
+static inline void mem_cgroup_protection(struct mem_cgroup *root,
+ struct mem_cgroup *memcg,
+ unsigned long *min,
+ unsigned long *low)
{
+ *min = *low = 0;
+
if (mem_cgroup_disabled())
- return 0;
+ return;
/*
* There is no reclaim protection applied to a targeted reclaim.
@@ -653,13 +656,10 @@ static inline unsigned long mem_cgroup_p
*
*/
if (root == memcg)
- return 0;
-
- if (in_low_reclaim)
- return READ_ONCE(memcg->memory.emin);
+ return;
- return max(READ_ONCE(memcg->memory.emin),
- READ_ONCE(memcg->memory.elow));
+ *min = READ_ONCE(memcg->memory.emin);
+ *low = READ_ONCE(memcg->memory.elow);
}
void mem_cgroup_calculate_protection(struct mem_cgroup *root,
@@ -1147,11 +1147,12 @@ static inline void memcg_memory_event_mm
{
}
-static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
- struct mem_cgroup *memcg,
- bool in_low_reclaim)
+static inline void mem_cgroup_protection(struct mem_cgroup *root,
+ struct mem_cgroup *memcg,
+ unsigned long *min,
+ unsigned long *low)
{
- return 0;
+ *min = *low = 0;
}
static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root,
--- a/mm/vmscan.c~mm-memcontrol-fix-occasional-ooms-due-to-proportional-memorylow-reclaim
+++ a/mm/vmscan.c
@@ -100,9 +100,12 @@ struct scan_control {
unsigned int may_swap:1;
/*
- * Cgroups are not reclaimed below their configured memory.low,
- * unless we threaten to OOM. If any cgroups are skipped due to
- * memory.low and nothing was reclaimed, go back for memory.low.
+ * Cgroup memory below memory.low is protected as long as we
+ * don't threaten to OOM. If any cgroup is reclaimed at
+ * reduced force or passed over entirely due to its memory.low
+ * setting (memcg_low_skipped), and nothing is reclaimed as a
+ * result, then go back for one more cycle that reclaims the protected
+ * memory (memcg_low_reclaim) to avert OOM.
*/
unsigned int memcg_low_reclaim:1;
unsigned int memcg_low_skipped:1;
@@ -2537,15 +2540,14 @@ out:
for_each_evictable_lru(lru) {
int file = is_file_lru(lru);
unsigned long lruvec_size;
+ unsigned long low, min;
unsigned long scan;
- unsigned long protection;
lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
- protection = mem_cgroup_protection(sc->target_mem_cgroup,
- memcg,
- sc->memcg_low_reclaim);
+ mem_cgroup_protection(sc->target_mem_cgroup, memcg,
+ &min, &low);
- if (protection) {
+ if (min || low) {
/*
* Scale a cgroup's reclaim pressure by proportioning
* its current usage to its memory.low or memory.min
@@ -2576,6 +2578,15 @@ out:
* hard protection.
*/
unsigned long cgroup_size = mem_cgroup_size(memcg);
+ unsigned long protection;
+
+ /* memory.low scaling, make sure we retry before OOM */
+ if (!sc->memcg_low_reclaim && low > min) {
+ protection = low;
+ sc->memcg_low_skipped = 1;
+ } else {
+ protection = min;
+ }
/* Avoid TOCTOU with earlier protection check */
cgroup_size = max(cgroup_size, protection);
_