arm64 can take an NMI-like error notification when user-space steps in
some corrupt memory. APEI's GHES code will call memory_failure_queue()
to schedule the recovery work. We then return to user-space, possibly
taking the fault again.
Currently the arch code unconditionally signals user-space from this
path, so we don't get stuck in this loop, but the affected process
never benefits from memory_failure()s recovery work. To fix this we
need to know the recovery work will run before we get back to user-space.
Increase the priority of the recovery work by scheduling it on the
system_highpri_wq, then try to bump the current task off this CPU
so that the recover work starts immediately.
Reported-by: Xie XiuQi <xiexiuqi@xxxxxxxxxx>
Signed-off-by: James Morse <james.morse@xxxxxxx>
CC: Xie XiuQi <xiexiuqi@xxxxxxxxxx>
CC: gengdongjiu <gengdongjiu@xxxxxxxxxx>
---
mm/memory-failure.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 4b80ccee4535..14f44d841e8b 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -55,6 +55,7 @@
#include <linux/hugetlb.h>
#include <linux/memory_hotplug.h>
#include <linux/mm_inline.h>
+#include <linux/preempt.h>
#include <linux/kfifo.h>
#include <linux/ratelimit.h>
#include "internal.h"
@@ -1319,6 +1320,7 @@ static DEFINE_PER_CPU(struct memory_failure_cpu, memory_failure_cpu);
*/
void memory_failure_queue(unsigned long pfn, int flags)
{
+ int cpu = smp_processor_id();
struct memory_failure_cpu *mf_cpu;
unsigned long proc_flags;
struct memory_failure_entry entry = {
@@ -1328,11 +1330,14 @@ void memory_failure_queue(unsigned long pfn, int flags)
mf_cpu = &get_cpu_var(memory_failure_cpu);
spin_lock_irqsave(&mf_cpu->lock, proc_flags);
- if (kfifo_put(&mf_cpu->fifo, entry))
- schedule_work_on(smp_processor_id(), &mf_cpu->work);
- else
+ if (kfifo_put(&mf_cpu->fifo, entry)) {
+ queue_work_on(cpu, system_highpri_wq, &mf_cpu->work);
+ set_tsk_need_resched(current);
+ preempt_set_need_resched();
+ } else {
pr_err("Memory failure: buffer overflow when queuing memory failure at %#lx\n",
pfn);
+ }
spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
put_cpu_var(memory_failure_cpu);
}
--
2.15.1
--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
