virtio-mem: Better retry handling

Let's start with a retry interval of 5 seconds and double the time until
we reach 5 minutes, in case we keep getting errors. Reset the retry
interval in case we succeeded.

The two main reasons for having to retry are
- The hypervisor is busy and cannot process our request
- We cannot reach the desired requested_size (esp., not enough memory can
  get unplugged because we can't allocate any subblocks).

Tested-by: Pankaj Gupta <[email protected]>
Cc: "Michael S. Tsirkin" <[email protected]>
Cc: Jason Wang <[email protected]>
Cc: Oscar Salvador <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Igor Mammedov <[email protected]>
Cc: Dave Young <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Dan Williams <[email protected]>
Cc: Pavel Tatashin <[email protected]>
Cc: Stefan Hajnoczi <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Signed-off-by: David Hildenbrand <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Michael S. Tsirkin <[email protected]>

Author: davidhildenbrand

drivers/virtio/virtio_mem.c

@@ -141,7 +141,9 @@ struct virtio_mem {
 
 	/* Timer for retrying to plug/unplug memory. */
 	struct hrtimer retry_timer;
-#define VIRTIO_MEM_RETRY_TIMER_MS		30000
+	unsigned int retry_timer_ms;
+#define VIRTIO_MEM_RETRY_TIMER_MIN_MS		50000
+#define VIRTIO_MEM_RETRY_TIMER_MAX_MS		300000
 
 	/* Memory notifier (online/offline events). */
 	struct notifier_block memory_notifier;
@@ -1550,6 +1552,7 @@ static void virtio_mem_run_wq(struct work_struct *work)
 
 	switch (rc) {
 	case 0:
+		vm->retry_timer_ms = VIRTIO_MEM_RETRY_TIMER_MIN_MS;
 		break;
 	case -ENOSPC:
 		/*
@@ -1565,8 +1568,7 @@ static void virtio_mem_run_wq(struct work_struct *work)
 		 */
 	case -ENOMEM:
 		/* Out of memory, try again later. */
-		hrtimer_start(&vm->retry_timer,
-			      ms_to_ktime(VIRTIO_MEM_RETRY_TIMER_MS),
+		hrtimer_start(&vm->retry_timer, ms_to_ktime(vm->retry_timer_ms),
 			      HRTIMER_MODE_REL);
 		break;
 	case -EAGAIN:
@@ -1586,6 +1588,8 @@ static enum hrtimer_restart virtio_mem_timer_expired(struct hrtimer *timer)
 					     retry_timer);
 
 	virtio_mem_retry(vm);
+	vm->retry_timer_ms = min_t(unsigned int, vm->retry_timer_ms * 2,
+				   VIRTIO_MEM_RETRY_TIMER_MAX_MS);
 	return HRTIMER_NORESTART;
 }
 
@@ -1754,6 +1758,7 @@ static int virtio_mem_probe(struct virtio_device *vdev)
 	spin_lock_init(&vm->removal_lock);
 	hrtimer_init(&vm->retry_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	vm->retry_timer.function = virtio_mem_timer_expired;
+	vm->retry_timer_ms = VIRTIO_MEM_RETRY_TIMER_MIN_MS;
 
 	/* register the virtqueue */
 	rc = virtio_mem_init_vq(vm);