1 files changed, 112 insertions, 56 deletions

diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index 835f6cc2fb66..fa5226c198cc 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -38,11 +38,6 @@ module_param(bbm_block_size, ulong, 0444);
 MODULE_PARM_DESC(bbm_block_size,
 		 "Big Block size in bytes. Default is 0 (auto-detection).");
 
-static bool bbm_safe_unplug = true;
-module_param(bbm_safe_unplug, bool, 0444);
-MODULE_PARM_DESC(bbm_safe_unplug,
-	     "Use a safe unplug mechanism in BBM, avoiding long/endless loops");
-
 /*
  * virtio-mem currently supports the following modes of operation:
  *
@@ -173,6 +168,13 @@ struct virtio_mem {
 			/* The number of subblocks per Linux memory block. */
 			uint32_t sbs_per_mb;
 
+			/*
+			 * Some of the Linux memory blocks tracked as "partially
+			 * plugged" are completely unplugged and can be offlined
+			 * and removed -- which previously failed.
+			 */
+			bool have_unplugged_mb;
+
 			/* Summary of all memory block states. */
 			unsigned long mb_count[VIRTIO_MEM_SBM_MB_COUNT];
 
@@ -746,11 +748,15 @@ static int virtio_mem_offline_and_remove_memory(struct virtio_mem *vm,
 		 * immediately instead of waiting.
 		 */
 		virtio_mem_retry(vm);
-	} else {
-		dev_dbg(&vm->vdev->dev,
-			"offlining and removing memory failed: %d\n", rc);
+		return 0;
 	}
-	return rc;
+	dev_dbg(&vm->vdev->dev, "offlining and removing memory failed: %d\n", rc);
+	/*
+	 * We don't really expect this to fail, because we fake-offlined all
+	 * memory already. But it could fail in corner cases.
+	 */
+	WARN_ON_ONCE(rc != -ENOMEM && rc != -EBUSY);
+	return rc == -ENOMEM ? -ENOMEM : -EBUSY;
 }
 
 /*
@@ -767,6 +773,34 @@ static int virtio_mem_sbm_offline_and_remove_mb(struct virtio_mem *vm,
 }
 
 /*
+ * Try (offlining and) removing memory from Linux in case all subblocks are
+ * unplugged. Can be called on online and offline memory blocks.
+ *
+ * May modify the state of memory blocks in virtio-mem.
+ */
+static int virtio_mem_sbm_try_remove_unplugged_mb(struct virtio_mem *vm,
+						  unsigned long mb_id)
+{
+	int rc;
+
+	/*
+	 * Once all subblocks of a memory block were unplugged, offline and
+	 * remove it.
+	 */
+	if (!virtio_mem_sbm_test_sb_unplugged(vm, mb_id, 0, vm->sbm.sbs_per_mb))
+		return 0;
+
+	/* offline_and_remove_memory() works for online and offline memory. */
+	mutex_unlock(&vm->hotplug_mutex);
+	rc = virtio_mem_sbm_offline_and_remove_mb(vm, mb_id);
+	mutex_lock(&vm->hotplug_mutex);
+	if (!rc)
+		virtio_mem_sbm_set_mb_state(vm, mb_id,
+					    VIRTIO_MEM_SBM_MB_UNUSED);
+	return rc;
+}
+
+/*
  * See virtio_mem_offline_and_remove_memory(): Try to offline and remove a
  * all Linux memory blocks covered by the big block.
  */
@@ -1155,7 +1189,8 @@ static void virtio_mem_fake_online(unsigned long pfn, unsigned long nr_pages)
  * Try to allocate a range, marking pages fake-offline, effectively
  * fake-offlining them.
  */
-static int virtio_mem_fake_offline(unsigned long pfn, unsigned long nr_pages)
+static int virtio_mem_fake_offline(struct virtio_mem *vm, unsigned long pfn,
+				   unsigned long nr_pages)
 {
 	const bool is_movable = is_zone_movable_page(pfn_to_page(pfn));
 	int rc, retry_count;
@@ -1168,6 +1203,14 @@ static int virtio_mem_fake_offline(unsigned long pfn, unsigned long nr_pages)
 	 * some guarantees.
 	 */
 	for (retry_count = 0; retry_count < 5; retry_count++) {
+		/*
+		 * If the config changed, stop immediately and go back to the
+		 * main loop: avoid trying to keep unplugging if the device
+		 * might have decided to not remove any more memory.
+		 */
+		if (atomic_read(&vm->config_changed))
+			return -EAGAIN;
+
 		rc = alloc_contig_range(pfn, pfn + nr_pages, MIGRATE_MOVABLE,
 					GFP_KERNEL);
 		if (rc == -ENOMEM)
@@ -1917,7 +1960,7 @@ static int virtio_mem_sbm_unplug_sb_online(struct virtio_mem *vm,
 	start_pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) +
 			     sb_id * vm->sbm.sb_size);
 
-	rc = virtio_mem_fake_offline(start_pfn, nr_pages);
+	rc = virtio_mem_fake_offline(vm, start_pfn, nr_pages);
 	if (rc)
 		return rc;
 
@@ -1989,20 +2032,10 @@ static int virtio_mem_sbm_unplug_any_sb_online(struct virtio_mem *vm,
 	}
 
 unplugged:
-	/*
-	 * Once all subblocks of a memory block were unplugged, offline and
-	 * remove it. This will usually not fail, as no memory is in use
-	 * anymore - however some other notifiers might NACK the request.
-	 */
-	if (virtio_mem_sbm_test_sb_unplugged(vm, mb_id, 0, vm->sbm.sbs_per_mb)) {
-		mutex_unlock(&vm->hotplug_mutex);
-		rc = virtio_mem_sbm_offline_and_remove_mb(vm, mb_id);
-		mutex_lock(&vm->hotplug_mutex);
-		if (!rc)
-			virtio_mem_sbm_set_mb_state(vm, mb_id,
-						    VIRTIO_MEM_SBM_MB_UNUSED);
-	}
-
+	rc = virtio_mem_sbm_try_remove_unplugged_mb(vm, mb_id);
+	if (rc)
+		vm->sbm.have_unplugged_mb = 1;
+	/* Ignore errors, this is not critical. We'll retry later. */
 	return 0;
 }
 
@@ -2111,38 +2144,32 @@ static int virtio_mem_bbm_offline_remove_and_unplug_bb(struct virtio_mem *vm,
 			 VIRTIO_MEM_BBM_BB_ADDED))
 		return -EINVAL;
 
-	if (bbm_safe_unplug) {
-		/*
-		 * Start by fake-offlining all memory. Once we marked the device
-		 * block as fake-offline, all newly onlined memory will
-		 * automatically be kept fake-offline. Protect from concurrent
-		 * onlining/offlining until we have a consistent state.
-		 */
-		mutex_lock(&vm->hotplug_mutex);
-		virtio_mem_bbm_set_bb_state(vm, bb_id,
-					    VIRTIO_MEM_BBM_BB_FAKE_OFFLINE);
+	/*
+	 * Start by fake-offlining all memory. Once we marked the device
+	 * block as fake-offline, all newly onlined memory will
+	 * automatically be kept fake-offline. Protect from concurrent
+	 * onlining/offlining until we have a consistent state.
+	 */
+	mutex_lock(&vm->hotplug_mutex);
+	virtio_mem_bbm_set_bb_state(vm, bb_id, VIRTIO_MEM_BBM_BB_FAKE_OFFLINE);
 
-		for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
-			page = pfn_to_online_page(pfn);
-			if (!page)
-				continue;
+	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		page = pfn_to_online_page(pfn);
+		if (!page)
+			continue;
 
-			rc = virtio_mem_fake_offline(pfn, PAGES_PER_SECTION);
-			if (rc) {
-				end_pfn = pfn;
-				goto rollback_safe_unplug;
-			}
+		rc = virtio_mem_fake_offline(vm, pfn, PAGES_PER_SECTION);
+		if (rc) {
+			end_pfn = pfn;
+			goto rollback;
 		}
-		mutex_unlock(&vm->hotplug_mutex);
 	}
+	mutex_unlock(&vm->hotplug_mutex);
 
 	rc = virtio_mem_bbm_offline_and_remove_bb(vm, bb_id);
 	if (rc) {
-		if (bbm_safe_unplug) {
-			mutex_lock(&vm->hotplug_mutex);
-			goto rollback_safe_unplug;
-		}
-		return rc;
+		mutex_lock(&vm->hotplug_mutex);
+		goto rollback;
 	}
 
 	rc = virtio_mem_bbm_unplug_bb(vm, bb_id);
@@ -2154,7 +2181,7 @@ static int virtio_mem_bbm_offline_remove_and_unplug_bb(struct virtio_mem *vm,
 					    VIRTIO_MEM_BBM_BB_UNUSED);
 	return rc;
 
-rollback_safe_unplug:
+rollback:
 	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
 		page = pfn_to_online_page(pfn);
 		if (!page)
@@ -2260,12 +2287,13 @@ static int virtio_mem_unplug_request(struct virtio_mem *vm, uint64_t diff)
 
 /*
  * Try to unplug all blocks that couldn't be unplugged before, for example,
- * because the hypervisor was busy.
+ * because the hypervisor was busy. Further, offline and remove any memory
+ * blocks where we previously failed.
  */
-static int virtio_mem_unplug_pending_mb(struct virtio_mem *vm)
+static int virtio_mem_cleanup_pending_mb(struct virtio_mem *vm)
 {
 	unsigned long id;
-	int rc;
+	int rc = 0;
 
 	if (!vm->in_sbm) {
 		virtio_mem_bbm_for_each_bb(vm, id,
@@ -2287,6 +2315,27 @@ static int virtio_mem_unplug_pending_mb(struct virtio_mem *vm)
 					    VIRTIO_MEM_SBM_MB_UNUSED);
 	}
 
+	if (!vm->sbm.have_unplugged_mb)
+		return 0;
+
+	/*
+	 * Let's retry (offlining and) removing completely unplugged Linux
+	 * memory blocks.
+	 */
+	vm->sbm.have_unplugged_mb = false;
+
+	mutex_lock(&vm->hotplug_mutex);
+	virtio_mem_sbm_for_each_mb(vm, id, VIRTIO_MEM_SBM_MB_MOVABLE_PARTIAL)
+		rc |= virtio_mem_sbm_try_remove_unplugged_mb(vm, id);
+	virtio_mem_sbm_for_each_mb(vm, id, VIRTIO_MEM_SBM_MB_KERNEL_PARTIAL)
+		rc |= virtio_mem_sbm_try_remove_unplugged_mb(vm, id);
+	virtio_mem_sbm_for_each_mb(vm, id, VIRTIO_MEM_SBM_MB_OFFLINE_PARTIAL)
+		rc |= virtio_mem_sbm_try_remove_unplugged_mb(vm, id);
+	mutex_unlock(&vm->hotplug_mutex);
+
+	if (rc)
+		vm->sbm.have_unplugged_mb = true;
+	/* Ignore errors, this is not critical. We'll retry later. */
 	return 0;
 }
 
@@ -2368,9 +2417,9 @@ retry:
 		virtio_mem_refresh_config(vm);
 	}
 
-	/* Unplug any leftovers from previous runs */
+	/* Cleanup any leftovers from previous runs */
 	if (!rc)
-		rc = virtio_mem_unplug_pending_mb(vm);
+		rc = virtio_mem_cleanup_pending_mb(vm);
 
 	if (!rc && vm->requested_size != vm->plugged_size) {
 		if (vm->requested_size > vm->plugged_size) {
@@ -2382,6 +2431,13 @@ retry:
 		}
 	}
 
+	/*
+	 * Keep retrying to offline and remove completely unplugged Linux
+	 * memory blocks.
+	 */
+	if (!rc && vm->in_sbm && vm->sbm.have_unplugged_mb)
+		rc = -EBUSY;
+
 	switch (rc) {
 	case 0:
 		vm->retry_timer_ms = VIRTIO_MEM_RETRY_TIMER_MIN_MS;