summaryrefslogtreecommitdiff
path: root/drivers/virtio/virtio_mem.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/virtio/virtio_mem.c')
-rw-r--r--drivers/virtio/virtio_mem.c95
1 files changed, 63 insertions, 32 deletions
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index f86654af8b6b..cbd0aa5eb95c 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -51,6 +51,7 @@ struct virtio_mem {
/* Workqueue that processes the plug/unplug requests. */
struct work_struct wq;
+ atomic_t wq_active;
atomic_t config_changed;
/* Virtqueue for guest->host requests. */
@@ -99,7 +100,15 @@ struct virtio_mem {
/* Summary of all memory block states. */
unsigned long nb_mb_state[VIRTIO_MEM_MB_STATE_COUNT];
-#define VIRTIO_MEM_NB_OFFLINE_THRESHOLD 10
+
+ /*
+ * We don't want to add too much memory if it's not getting onlined,
+ * to avoid running OOM. Besides this threshold, we allow to have at
+ * least two offline blocks at a time (whatever is bigger).
+ */
+#define VIRTIO_MEM_DEFAULT_OFFLINE_THRESHOLD (1024 * 1024 * 1024)
+ atomic64_t offline_size;
+ uint64_t offline_threshold;
/*
* One byte state per memory block.
@@ -406,6 +415,18 @@ static int virtio_mem_sb_bitmap_prepare_next_mb(struct virtio_mem *vm)
}
/*
+ * Test if we could add memory without creating too much offline memory -
+ * to avoid running OOM if memory is getting onlined deferred.
+ */
+static bool virtio_mem_could_add_memory(struct virtio_mem *vm, uint64_t size)
+{
+ if (WARN_ON_ONCE(size > vm->offline_threshold))
+ return false;
+
+ return atomic64_read(&vm->offline_size) + size <= vm->offline_threshold;
+}
+
+/*
* Try to add a memory block to Linux. This will usually only fail
* if out of memory.
*
@@ -417,6 +438,8 @@ static int virtio_mem_sb_bitmap_prepare_next_mb(struct virtio_mem *vm)
static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id)
{
const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id);
+ const uint64_t size = memory_block_size_bytes();
+ int rc;
/*
* When force-unloading the driver and we still have memory added to
@@ -430,10 +453,13 @@ static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id)
}
dev_dbg(&vm->vdev->dev, "adding memory block: %lu\n", mb_id);
- return add_memory_driver_managed(vm->nid, addr,
- memory_block_size_bytes(),
- vm->resource_name,
- MEMHP_MERGE_RESOURCE);
+ /* Memory might get onlined immediately. */
+ atomic64_add(size, &vm->offline_size);
+ rc = add_memory_driver_managed(vm->nid, addr, size, vm->resource_name,
+ MEMHP_MERGE_RESOURCE);
+ if (rc)
+ atomic64_sub(size, &vm->offline_size);
+ return rc;
}
/*
@@ -448,16 +474,19 @@ static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id)
static int virtio_mem_mb_remove(struct virtio_mem *vm, unsigned long mb_id)
{
const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id);
+ const uint64_t size = memory_block_size_bytes();
int rc;
dev_dbg(&vm->vdev->dev, "removing memory block: %lu\n", mb_id);
- rc = remove_memory(vm->nid, addr, memory_block_size_bytes());
- if (!rc)
+ rc = remove_memory(vm->nid, addr, size);
+ if (!rc) {
+ atomic64_sub(size, &vm->offline_size);
/*
* We might have freed up memory we can now unplug, retry
* immediately instead of waiting.
*/
virtio_mem_retry(vm);
+ }
return rc;
}
@@ -473,18 +502,20 @@ static int virtio_mem_mb_offline_and_remove(struct virtio_mem *vm,
unsigned long mb_id)
{
const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id);
+ const uint64_t size = memory_block_size_bytes();
int rc;
dev_dbg(&vm->vdev->dev, "offlining and removing memory block: %lu\n",
mb_id);
- rc = offline_and_remove_memory(vm->nid, addr,
- memory_block_size_bytes());
- if (!rc)
+ rc = offline_and_remove_memory(vm->nid, addr, size);
+ if (!rc) {
+ atomic64_sub(size, &vm->offline_size);
/*
* We might have freed up memory we can now unplug, retry
* immediately instead of waiting.
*/
virtio_mem_retry(vm);
+ }
return rc;
}
@@ -567,8 +598,6 @@ static void virtio_mem_notify_offline(struct virtio_mem *vm,
static void virtio_mem_notify_online(struct virtio_mem *vm, unsigned long mb_id)
{
- unsigned long nb_offline;
-
switch (virtio_mem_mb_get_state(vm, mb_id)) {
case VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL:
virtio_mem_mb_set_state(vm, mb_id,
@@ -581,12 +610,6 @@ static void virtio_mem_notify_online(struct virtio_mem *vm, unsigned long mb_id)
BUG();
break;
}
- nb_offline = vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] +
- vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL];
-
- /* see if we can add new blocks now that we onlined one block */
- if (nb_offline == VIRTIO_MEM_NB_OFFLINE_THRESHOLD - 1)
- virtio_mem_retry(vm);
}
static void virtio_mem_notify_going_offline(struct virtio_mem *vm,
@@ -681,6 +704,7 @@ static int virtio_mem_memory_notifier_cb(struct notifier_block *nb,
case MEM_OFFLINE:
virtio_mem_notify_offline(vm, mb_id);
+ atomic64_add(size, &vm->offline_size);
/*
* Trigger the workqueue. Now that we have some offline memory,
* maybe we can handle pending unplug requests.
@@ -693,6 +717,18 @@ static int virtio_mem_memory_notifier_cb(struct notifier_block *nb,
break;
case MEM_ONLINE:
virtio_mem_notify_online(vm, mb_id);
+
+ atomic64_sub(size, &vm->offline_size);
+ /*
+ * Start adding more memory once we onlined half of our
+ * threshold. Don't trigger if it's possibly due to our actipn
+ * (e.g., us adding memory which gets onlined immediately from
+ * the core).
+ */
+ if (!atomic_read(&vm->wq_active) &&
+ virtio_mem_could_add_memory(vm, vm->offline_threshold / 2))
+ virtio_mem_retry(vm);
+
vm->hotplug_active = false;
mutex_unlock(&vm->hotplug_mutex);
break;
@@ -1152,18 +1188,6 @@ static int virtio_mem_prepare_next_mb(struct virtio_mem *vm,
}
/*
- * Don't add too many blocks that are not onlined yet to avoid running OOM.
- */
-static bool virtio_mem_too_many_mb_offline(struct virtio_mem *vm)
-{
- unsigned long nb_offline;
-
- nb_offline = vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] +
- vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL];
- return nb_offline >= VIRTIO_MEM_NB_OFFLINE_THRESHOLD;
-}
-
-/*
* Try to plug the desired number of subblocks and add the memory block
* to Linux.
*
@@ -1316,7 +1340,7 @@ static int virtio_mem_plug_request(struct virtio_mem *vm, uint64_t diff)
/* Try to plug and add unused blocks */
virtio_mem_for_each_mb_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED) {
- if (virtio_mem_too_many_mb_offline(vm))
+ if (!virtio_mem_could_add_memory(vm, memory_block_size_bytes()))
return -ENOSPC;
rc = virtio_mem_mb_plug_and_add(vm, mb_id, &nb_sb);
@@ -1327,7 +1351,7 @@ static int virtio_mem_plug_request(struct virtio_mem *vm, uint64_t diff)
/* Try to prepare, plug and add new blocks */
while (nb_sb) {
- if (virtio_mem_too_many_mb_offline(vm))
+ if (!virtio_mem_could_add_memory(vm, memory_block_size_bytes()))
return -ENOSPC;
rc = virtio_mem_prepare_next_mb(vm, &mb_id);
@@ -1620,6 +1644,7 @@ static void virtio_mem_run_wq(struct work_struct *work)
if (vm->broken)
return;
+ atomic_set(&vm->wq_active, 1);
retry:
rc = 0;
@@ -1680,6 +1705,8 @@ retry:
"unknown error, marking device broken: %d\n", rc);
vm->broken = true;
}
+
+ atomic_set(&vm->wq_active, 0);
}
static enum hrtimer_restart virtio_mem_timer_expired(struct hrtimer *timer)
@@ -1788,6 +1815,10 @@ static int virtio_mem_init(struct virtio_mem *vm)
memory_block_size_bytes());
vm->next_mb_id = vm->first_mb_id;
+ /* Prepare the offline threshold - make sure we can add two blocks. */
+ vm->offline_threshold = max_t(uint64_t, 2 * memory_block_size_bytes(),
+ VIRTIO_MEM_DEFAULT_OFFLINE_THRESHOLD);
+
dev_info(&vm->vdev->dev, "start address: 0x%llx", vm->addr);
dev_info(&vm->vdev->dev, "region size: 0x%llx", vm->region_size);
dev_info(&vm->vdev->dev, "device block size: 0x%llx",