1 files changed, 111 insertions, 70 deletions

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 100368eb799..5f59f1e3e5b 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -26,22 +26,8 @@
 #define KEYS_PER_NODE (NODE_SIZE / sizeof(sector_t))
 #define CHILDREN_PER_NODE (KEYS_PER_NODE + 1)
 
-/*
- * The table has always exactly one reference from either mapped_device->map
- * or hash_cell->new_map. This reference is not counted in table->holders.
- * A pair of dm_create_table/dm_destroy_table functions is used for table
- * creation/destruction.
- *
- * Temporary references from the other code increase table->holders. A pair
- * of dm_table_get/dm_table_put functions is used to manipulate it.
- *
- * When the table is about to be destroyed, we wait for table->holders to
- * drop to zero.
- */
-
 struct dm_table {
 	struct mapped_device *md;
-	atomic_t holders;
 	unsigned type;
 
 	/* btree table */
@@ -169,7 +155,6 @@ static int alloc_targets(struct dm_table *t, unsigned int num)
 {
 	sector_t *n_highs;
 	struct dm_target *n_targets;
-	int n = t->num_targets;
 
 	/*
 	 * Allocate both the target array and offset array at once.
@@ -183,12 +168,7 @@ static int alloc_targets(struct dm_table *t, unsigned int num)
 
 	n_targets = (struct dm_target *) (n_highs + num);
 
-	if (n) {
-		memcpy(n_highs, t->highs, sizeof(*n_highs) * n);
-		memcpy(n_targets, t->targets, sizeof(*n_targets) * n);
-	}
-
-	memset(n_highs + n, -1, sizeof(*n_highs) * (num - n));
+	memset(n_highs, -1, sizeof(*n_highs) * num);
 	vfree(t->highs);
 
 	t->num_allocated = num;
@@ -208,16 +188,19 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 
 	INIT_LIST_HEAD(&t->devices);
 	INIT_LIST_HEAD(&t->target_callbacks);
-	atomic_set(&t->holders, 0);
 
 	if (!num_targets)
 		num_targets = KEYS_PER_NODE;
 
 	num_targets = dm_round_up(num_targets, KEYS_PER_NODE);
 
+	if (!num_targets) {
+		kfree(t);
+		return -ENOMEM;
+	}
+
 	if (alloc_targets(t, num_targets)) {
 		kfree(t);
-		t = NULL;
 		return -ENOMEM;
 	}
 
@@ -247,10 +230,6 @@ void dm_table_destroy(struct dm_table *t)
 	if (!t)
 		return;
 
-	while (atomic_read(&t->holders))
-		msleep(1);
-	smp_mb();
-
 	/* free the indexes */
 	if (t->depth >= 2)
 		vfree(t->index[t->depth - 2]);
@@ -275,33 +254,6 @@ void dm_table_destroy(struct dm_table *t)
 	kfree(t);
 }
 
-void dm_table_get(struct dm_table *t)
-{
-	atomic_inc(&t->holders);
-}
-EXPORT_SYMBOL(dm_table_get);
-
-void dm_table_put(struct dm_table *t)
-{
-	if (!t)
-		return;
-
-	smp_mb__before_atomic_dec();
-	atomic_dec(&t->holders);
-}
-EXPORT_SYMBOL(dm_table_put);
-
-/*
- * Checks to see if we need to extend highs or targets.
- */
-static inline int check_space(struct dm_table *t)
-{
-	if (t->num_targets >= t->num_allocated)
-		return alloc_targets(t, t->num_allocated * 2);
-
-	return 0;
-}
-
 /*
  * See if we've already got a device in the list.
  */
@@ -513,8 +465,8 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
 }
 EXPORT_SYMBOL(dm_get_device);
 
-int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
-			 sector_t start, sector_t len, void *data)
+static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
+				sector_t start, sector_t len, void *data)
 {
 	struct queue_limits *limits = data;
 	struct block_device *bdev = dev->bdev;
@@ -547,7 +499,6 @@ int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 					  (unsigned int) (PAGE_SIZE >> 9));
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dm_set_device_limits);
 
 /*
  * Decrement a device's use count and remove it if necessary.
@@ -581,14 +532,28 @@ static int adjoin(struct dm_table *table, struct dm_target *ti)
 
 /*
  * Used to dynamically allocate the arg array.
+ *
+ * We do first allocation with GFP_NOIO because dm-mpath and dm-thin must
+ * process messages even if some device is suspended. These messages have a
+ * small fixed number of arguments.
+ *
+ * On the other hand, dm-switch needs to process bulk data using messages and
+ * excessive use of GFP_NOIO could cause trouble.
  */
 static char **realloc_argv(unsigned *array_size, char **old_argv)
 {
 	char **argv;
 	unsigned new_size;
+	gfp_t gfp;
 
-	new_size = *array_size ? *array_size * 2 : 64;
-	argv = kmalloc(new_size * sizeof(*argv), GFP_KERNEL);
+	if (*array_size) {
+		new_size = *array_size * 2;
+		gfp = GFP_KERNEL;
+	} else {
+		new_size = 8;
+		gfp = GFP_NOIO;
+	}
+	argv = kmalloc(new_size * sizeof(*argv), gfp);
 	if (argv) {
 		memcpy(argv, old_argv, *array_size * sizeof(*argv));
 		*array_size = new_size;
@@ -748,8 +713,7 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 		return -EINVAL;
 	}
 
-	if ((r = check_space(t)))
-		return r;
+	BUG_ON(t->num_targets >= t->num_allocated);
 
 	tgt = t->targets + t->num_targets;
 	memset(tgt, 0, sizeof(*tgt));
@@ -823,8 +787,8 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 
 	t->highs[t->num_targets++] = tgt->begin + tgt->len - 1;
 
-	if (!tgt->num_discard_requests && tgt->discards_supported)
-		DMWARN("%s: %s: ignoring discards_supported because num_discard_requests is zero.",
+	if (!tgt->num_discard_bios && tgt->discards_supported)
+		DMWARN("%s: %s: ignoring discards_supported because num_discard_bios is zero.",
 		       dm_device_name(t->md), type);
 
 	return 0;
@@ -896,14 +860,17 @@ EXPORT_SYMBOL(dm_consume_args);
 static int dm_table_set_type(struct dm_table *t)
 {
 	unsigned i;
-	unsigned bio_based = 0, request_based = 0;
+	unsigned bio_based = 0, request_based = 0, hybrid = 0;
 	struct dm_target *tgt;
 	struct dm_dev_internal *dd;
 	struct list_head *devices;
+	unsigned live_md_type;
 
 	for (i = 0; i < t->num_targets; i++) {
 		tgt = t->targets + i;
-		if (dm_target_request_based(tgt))
+		if (dm_target_hybrid(tgt))
+			hybrid = 1;
+		else if (dm_target_request_based(tgt))
 			request_based = 1;
 		else
 			bio_based = 1;
@@ -915,6 +882,19 @@ static int dm_table_set_type(struct dm_table *t)
 		}
 	}
 
+	if (hybrid && !bio_based && !request_based) {
+		/*
+		 * The targets can work either way.
+		 * Determine the type from the live device.
+		 * Default to bio-based if device is new.
+		 */
+		live_md_type = dm_get_md_type(t->md);
+		if (live_md_type == DM_TYPE_REQUEST_BASED)
+			request_based = 1;
+		else
+			bio_based = 1;
+	}
+
 	if (bio_based) {
 		/* We must use this table as bio-based */
 		t->type = DM_TYPE_BIO_BASED;
@@ -964,16 +944,25 @@ bool dm_table_request_based(struct dm_table *t)
 	return dm_table_get_type(t) == DM_TYPE_REQUEST_BASED;
 }
 
-int dm_table_alloc_md_mempools(struct dm_table *t)
+static int dm_table_alloc_md_mempools(struct dm_table *t)
 {
 	unsigned type = dm_table_get_type(t);
+	unsigned per_bio_data_size = 0;
+	struct dm_target *tgt;
+	unsigned i;
 
 	if (unlikely(type == DM_TYPE_NONE)) {
 		DMWARN("no table type is set, can't allocate mempools");
 		return -EINVAL;
 	}
 
-	t->mempools = dm_alloc_md_mempools(type, t->integrity_supported);
+	if (type == DM_TYPE_BIO_BASED)
+		for (i = 0; i < t->num_targets; i++) {
+			tgt = t->targets + i;
+			per_bio_data_size = max(per_bio_data_size, tgt->per_bio_data_size);
+		}
+
+	t->mempools = dm_alloc_md_mempools(type, t->integrity_supported, per_bio_data_size);
 	if (!t->mempools)
 		return -ENOMEM;
 
@@ -1351,7 +1340,7 @@ static bool dm_table_supports_flush(struct dm_table *t, unsigned flush)
 	while (i < dm_table_get_num_targets(t)) {
 		ti = dm_table_get_target(t, i++);
 
-		if (!ti->num_flush_requests)
+		if (!ti->num_flush_bios)
 			continue;
 
 		if (ti->flush_supported)
@@ -1414,6 +1403,33 @@ static bool dm_table_all_devices_attribute(struct dm_table *t,
 	return 1;
 }
 
+static int device_not_write_same_capable(struct dm_target *ti, struct dm_dev *dev,
+					 sector_t start, sector_t len, void *data)
+{
+	struct request_queue *q = bdev_get_queue(dev->bdev);
+
+	return q && !q->limits.max_write_same_sectors;
+}
+
+static bool dm_table_supports_write_same(struct dm_table *t)
+{
+	struct dm_target *ti;
+	unsigned i = 0;
+
+	while (i < dm_table_get_num_targets(t)) {
+		ti = dm_table_get_target(t, i++);
+
+		if (!ti->num_write_same_bios)
+			return false;
+
+		if (!ti->type->iterate_devices ||
+		    ti->type->iterate_devices(ti, device_not_write_same_capable, NULL))
+			return false;
+	}
+
+	return true;
+}
+
 void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			       struct queue_limits *limits)
 {
@@ -1445,6 +1461,9 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	else
 		queue_flag_clear_unlocked(QUEUE_FLAG_NONROT, q);
 
+	if (!dm_table_supports_write_same(t))
+		q->limits.max_write_same_sectors = 0;
+
 	dm_table_set_integrity(t);
 
 	/*
@@ -1529,8 +1548,11 @@ int dm_table_resume_targets(struct dm_table *t)
 			continue;
 
 		r = ti->type->preresume(ti);
-		if (r)
+		if (r) {
+			DMERR("%s: %s: preresume failed, error = %d",
+			      dm_device_name(t->md), ti->type->name, r);
 			return r;
+		}
 	}
 
 	for (i = 0; i < t->num_targets; i++) {
@@ -1595,6 +1617,25 @@ struct mapped_device *dm_table_get_md(struct dm_table *t)
 }
 EXPORT_SYMBOL(dm_table_get_md);
 
+void dm_table_run_md_queue_async(struct dm_table *t)
+{
+	struct mapped_device *md;
+	struct request_queue *queue;
+	unsigned long flags;
+
+	if (!dm_table_request_based(t))
+		return;
+
+	md = dm_table_get_md(t);
+	queue = dm_get_md_queue(md);
+	if (queue) {
+		spin_lock_irqsave(queue->queue_lock, flags);
+		blk_run_queue_async(queue);
+		spin_unlock_irqrestore(queue->queue_lock, flags);
+	}
+}
+EXPORT_SYMBOL(dm_table_run_md_queue_async);
+
 static int device_discard_capable(struct dm_target *ti, struct dm_dev *dev,
 				  sector_t start, sector_t len, void *data)
 {
@@ -1618,7 +1659,7 @@ bool dm_table_supports_discards(struct dm_table *t)
 	while (i < dm_table_get_num_targets(t)) {
 		ti = dm_table_get_target(t, i++);
 
-		if (!ti->num_discard_requests)
+		if (!ti->num_discard_bios)
 			continue;
 
 		if (ti->discards_supported)