mm/memory-failure: Add memory_failure_queue_kick()

James Morse · rafaeljw · commit 062022315e8a · 2020-05-19T19:51:10.000+02:00
The GHES code calls memory_failure_queue() from IRQ context to schedule
work on the current CPU so that memory_failure() can sleep.

For synchronous memory errors the arch code needs to know any signals
that memory_failure() will trigger are pending before it returns to
user-space, possibly when exiting from the IRQ.

Add a helper to kick the memory failure queue, to ensure the scheduled
work has happened. This has to be called from process context, so may
have been migrated from the original cpu. Pass the cpu the work was
queued on.

Change memory_failure_work_func() to permit being called on the 'wrong'
cpu.

Signed-off-by: James Morse &lt;james.morse@arm.com&gt;
Tested-by: Tyler Baicar &lt;baicar@os.amperecomputing.com&gt;
Acked-by: Naoya Horiguchi &lt;naoya.horiguchi@nec.com&gt;
Signed-off-by: Rafael J. Wysocki &lt;rafael.j.wysocki@intel.com&gt;
diff --git a/include/linux/mm.h b/include/linux/mm.h
@@ -3012,6 +3012,7 @@ enum mf_flags {
 };
 extern int memory_failure(unsigned long pfn, int flags);
 extern void memory_failure_queue(unsigned long pfn, int flags);
+extern void memory_failure_queue_kick(int cpu);
 extern int unpoison_memory(unsigned long pfn);
 extern int get_hwpoison_page(struct page *page);
 #define put_hwpoison_page(page)	put_page(page)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
@@ -1493,7 +1493,7 @@ static void memory_failure_work_func(struct work_struct *work)
 	unsigned long proc_flags;
 	int gotten;
 
-	mf_cpu = this_cpu_ptr(&memory_failure_cpu);
+	mf_cpu = container_of(work, struct memory_failure_cpu, work);
 	for (;;) {
 		spin_lock_irqsave(&mf_cpu->lock, proc_flags);
 		gotten = kfifo_get(&mf_cpu->fifo, &entry);
@@ -1507,6 +1507,19 @@ static void memory_failure_work_func(struct work_struct *work)
 	}
 }
 
+/*
+ * Process memory_failure work queued on the specified CPU.
+ * Used to avoid return-to-userspace racing with the memory_failure workqueue.
+ */
+void memory_failure_queue_kick(int cpu)
+{
+	struct memory_failure_cpu *mf_cpu;
+
+	mf_cpu = &per_cpu(memory_failure_cpu, cpu);
+	cancel_work_sync(&mf_cpu->work);
+	memory_failure_work_func(&mf_cpu->work);
+}
+
 static int __init memory_failure_init(void)
 {
 	struct memory_failure_cpu *mf_cpu;
