Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index f1b810d..419a814 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -26,6 +26,7 @@
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/sched/task.h>
+#include <linux/sched/debug.h>
#include <linux/swap.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
@@ -127,7 +128,7 @@
/*
* The process p may have detached its own ->mm while exiting or through
- * use_mm(), but one or more of its subthreads may still have a valid
+ * kthread_use_mm(), but one or more of its subthreads may still have a valid
* pointer. Return p, or any of its subthreads with a valid ->mm, with
* task_lock() held.
*/
@@ -185,7 +186,7 @@
global_node_page_state(NR_ISOLATED_FILE) +
global_node_page_state(NR_UNEVICTABLE);
- return (global_node_page_state(NR_SLAB_UNRECLAIMABLE) > nr_lru);
+ return (global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B) > nr_lru);
}
/**
@@ -251,7 +252,7 @@
{
struct zone *zone;
struct zoneref *z;
- enum zone_type high_zoneidx = gfp_zone(oc->gfp_mask);
+ enum zone_type highest_zoneidx = gfp_zone(oc->gfp_mask);
bool cpuset_limited = false;
int nid;
@@ -291,7 +292,7 @@
/* Check this allocation failure is caused by cpuset's wall function */
for_each_zone_zonelist_nodemask(zone, z, oc->zonelist,
- high_zoneidx, oc->nodemask)
+ highest_zoneidx, oc->nodemask)
if (!cpuset_zone_allowed(zone, oc->gfp_mask))
cpuset_limited = true;
@@ -568,7 +569,7 @@
{
bool ret = true;
- if (!down_read_trylock(&mm->mmap_sem)) {
+ if (!mmap_read_trylock(mm)) {
trace_skip_task_reaping(tsk->pid);
return false;
}
@@ -576,8 +577,8 @@
/*
* MMF_OOM_SKIP is set by exit_mmap when the OOM reaper can't
* work on the mm anymore. The check for MMF_OOM_SKIP must run
- * under mmap_sem for reading because it serializes against the
- * down_write();up_write() cycle in exit_mmap().
+ * under mmap_lock for reading because it serializes against the
+ * mmap_write_lock();mmap_write_unlock() cycle in exit_mmap().
*/
if (test_bit(MMF_OOM_SKIP, &mm->flags)) {
trace_skip_task_reaping(tsk->pid);
@@ -599,7 +600,7 @@
out_finish:
trace_finish_task_reaping(tsk->pid);
out_unlock:
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
return ret;
}
@@ -610,7 +611,7 @@
int attempts = 0;
struct mm_struct *mm = tsk->signal->oom_mm;
- /* Retry the down_read_trylock(mmap_sem) a few times */
+ /* Retry the mmap_read_trylock(mm) a few times */
while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm))
schedule_timeout_idle(HZ/10);
@@ -620,6 +621,7 @@
pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
task_pid_nr(tsk), tsk->comm);
+ sched_show_task(tsk);
debug_show_all_locks();
done:
@@ -627,7 +629,7 @@
/*
* Hide this mm from OOM killer because it has been either reaped or
- * somebody can't call up_write(mmap_sem).
+ * somebody can't call mmap_write_unlock(mm).
*/
set_bit(MMF_OOM_SKIP, &mm->flags);
@@ -861,6 +863,8 @@
p = find_lock_task_mm(victim);
if (!p) {
+ pr_info("%s: OOM victim %d (%s) is already exiting. Skip killing the task\n",
+ message, task_pid_nr(victim), victim->comm);
put_task_struct(victim);
return;
} else if (victim != p) {
@@ -896,7 +900,7 @@
/*
* Kill all user processes sharing victim->mm in other thread groups, if
* any. They don't get access to memory reserves, though, to avoid
- * depletion of all memory. This prevents mm->mmap_sem livelock when an
+ * depletion of all memory. This prevents mm->mmap_lock livelock when an
* oom killed thread cannot exit because it requires the semaphore and
* its contended by another thread trying to allocate memory itself.
* That thread will now get access to memory reserves since it has a
@@ -917,8 +921,8 @@
continue;
}
/*
- * No use_mm() user needs to read from the userspace so we are
- * ok to reap it.
+ * No kthead_use_mm() user needs to read from the userspace so
+ * we are ok to reap it.
*/
if (unlikely(p->flags & PF_KTHREAD))
continue;
@@ -1114,25 +1118,22 @@
}
/*
- * The pagefault handler calls here because it is out of memory, so kill a
- * memory-hogging task. If oom_lock is held by somebody else, a parallel oom
- * killing is already in progress so do nothing.
+ * The pagefault handler calls here because some allocation has failed. We have
+ * to take care of the memcg OOM here because this is the only safe context without
+ * any locks held but let the oom killer triggered from the allocation context care
+ * about the global OOM.
*/
void pagefault_out_of_memory(void)
{
- struct oom_control oc = {
- .zonelist = NULL,
- .nodemask = NULL,
- .memcg = NULL,
- .gfp_mask = 0,
- .order = 0,
- };
+ static DEFINE_RATELIMIT_STATE(pfoom_rs, DEFAULT_RATELIMIT_INTERVAL,
+ DEFAULT_RATELIMIT_BURST);
if (mem_cgroup_oom_synchronize(true))
return;
- if (!mutex_trylock(&oom_lock))
+ if (fatal_signal_pending(current))
return;
- out_of_memory(&oc);
- mutex_unlock(&oom_lock);
+
+ if (__ratelimit(&pfoom_rs))
+ pr_warn("Huh VM_FAULT_OOM leaked out to the #PF handler. Retrying PF\n");
}