1 files changed, 510 insertions, 168 deletions

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 90267f8d64e..5f59f1e3e5b 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -17,7 +17,7 @@
 #include <linux/interrupt.h>
 #include <linux/mutex.h>
 #include <linux/delay.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 
 #define DM_MSG_PREFIX "table"
 
@@ -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 */
@@ -54,7 +40,9 @@ struct dm_table {
 	sector_t *highs;
 	struct dm_target *targets;
 
-	unsigned discards_supported:1;
+	struct target_type *immutable_target_type;
+	unsigned integrity_supported:1;
+	unsigned singleton:1;
 
 	/*
 	 * Indicates the rw permissions for the new logical
@@ -71,6 +59,8 @@ struct dm_table {
 	void *event_context;
 
 	struct dm_md_mempools *mempools;
+
+	struct list_head target_callbacks;
 };
 
 /*
@@ -151,12 +141,11 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size)
 		return NULL;
 
 	size = nmemb * elem_size;
-	addr = vmalloc(size);
-	if (addr)
-		memset(addr, 0, size);
+	addr = vzalloc(size);
 
 	return addr;
 }
+EXPORT_SYMBOL(dm_vcalloc);
 
 /*
  * highs, and targets are managed as dynamic arrays during a
@@ -166,7 +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.
@@ -180,12 +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;
@@ -204,17 +187,20 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&t->devices);
-	atomic_set(&t->holders, 0);
-	t->discards_supported = 1;
+	INIT_LIST_HEAD(&t->target_callbacks);
 
 	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;
 	}
 
@@ -244,10 +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]);
@@ -265,39 +247,13 @@ void dm_table_destroy(struct dm_table *t)
 	vfree(t->highs);
 
 	/* free the device list */
-	if (t->devices.next != &t->devices)
-		free_devices(&t->devices);
+	free_devices(&t->devices);
 
 	dm_free_md_mempools(t->mempools);
 
 	kfree(t);
 }
 
-void dm_table_get(struct dm_table *t)
-{
-	atomic_inc(&t->holders);
-}
-
-void dm_table_put(struct dm_table *t)
-{
-	if (!t)
-		return;
-
-	smp_mb__before_atomic_dec();
-	atomic_dec(&t->holders);
-}
-
-/*
- * 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.
  */
@@ -325,15 +281,18 @@ static int open_dev(struct dm_dev_internal *d, dev_t dev,
 
 	BUG_ON(d->dm_dev.bdev);
 
-	bdev = open_by_devnum(dev, d->dm_dev.mode);
+	bdev = blkdev_get_by_dev(dev, d->dm_dev.mode | FMODE_EXCL, _claim_ptr);
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
-	r = bd_claim_by_disk(bdev, _claim_ptr, dm_disk(md));
-	if (r)
-		blkdev_put(bdev, d->dm_dev.mode);
-	else
-		d->dm_dev.bdev = bdev;
-	return r;
+
+	r = bd_link_disk_holder(bdev, dm_disk(md));
+	if (r) {
+		blkdev_put(bdev, d->dm_dev.mode | FMODE_EXCL);
+		return r;
+	}
+
+	d->dm_dev.bdev = bdev;
+	return 0;
 }
 
 /*
@@ -344,8 +303,8 @@ static void close_dev(struct dm_dev_internal *d, struct mapped_device *md)
 	if (!d->dm_dev.bdev)
 		return;
 
-	bd_release_from_disk(d->dm_dev.bdev, dm_disk(md));
-	blkdev_put(d->dm_dev.bdev, d->dm_dev.mode);
+	bd_unlink_disk_holder(d->dm_dev.bdev, dm_disk(md));
+	blkdev_put(d->dm_dev.bdev, d->dm_dev.mode | FMODE_EXCL);
 	d->dm_dev.bdev = NULL;
 }
 
@@ -355,6 +314,7 @@ static void close_dev(struct dm_dev_internal *d, struct mapped_device *md)
 static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
 				  sector_t start, sector_t len, void *data)
 {
+	struct request_queue *q;
 	struct queue_limits *limits = data;
 	struct block_device *bdev = dev->bdev;
 	sector_t dev_size =
@@ -363,6 +323,22 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
 		limits->logical_block_size >> SECTOR_SHIFT;
 	char b[BDEVNAME_SIZE];
 
+	/*
+	 * Some devices exist without request functions,
+	 * such as loop devices not yet bound to backing files.
+	 * Forbid the use of such devices.
+	 */
+	q = bdev_get_queue(bdev);
+	if (!q || !q->make_request_fn) {
+		DMWARN("%s: %s is not yet initialised: "
+		       "start=%llu, len=%llu, dev_size=%llu",
+		       dm_device_name(ti->table->md), bdevname(bdev, b),
+		       (unsigned long long)start,
+		       (unsigned long long)len,
+		       (unsigned long long)dev_size);
+		return 1;
+	}
+
 	if (!dev_size)
 		return 0;
 
@@ -431,17 +407,19 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
  * Add a device to the list, or just increment the usage count if
  * it's already present.
  */
-static int __table_get_device(struct dm_table *t, struct dm_target *ti,
-		      const char *path, fmode_t mode, struct dm_dev **result)
+int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
+		  struct dm_dev **result)
 {
 	int r;
 	dev_t uninitialized_var(dev);
 	struct dm_dev_internal *dd;
 	unsigned int major, minor;
+	struct dm_table *t = ti->table;
+	char dummy;
 
 	BUG_ON(!t);
 
-	if (sscanf(path, "%u:%u", &major, &minor) == 2) {
+	if (sscanf(path, "%u:%u%c", &major, &minor, &dummy) == 2) {
 		/* Extract the major/minor numbers */
 		dev = MKDEV(major, minor);
 		if (MAJOR(dev) != major || MINOR(dev) != minor)
@@ -485,9 +463,10 @@ static int __table_get_device(struct dm_table *t, struct dm_target *ti,
 	*result = &dd->dm_dev;
 	return 0;
 }
+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;
@@ -515,24 +494,14 @@ int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 	 * If not we'll force DM to use PAGE_SIZE or
 	 * smaller I/O, just to be safe.
 	 */
-
-	if (q->merge_bvec_fn && !ti->type->merge)
-		limits->max_sectors =
-			min_not_zero(limits->max_sectors,
-				     (unsigned int) (PAGE_SIZE >> 9));
+	if (dm_queue_merge_is_compulsory(q) && !ti->type->merge)
+		blk_limits_max_hw_sectors(limits,
+					  (unsigned int) (PAGE_SIZE >> 9));
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dm_set_device_limits);
-
-int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
-		  struct dm_dev **result)
-{
-	return __table_get_device(ti->table, ti, path, mode, result);
-}
-
 
 /*
- * Decrement a devices use count and remove it if necessary.
+ * Decrement a device's use count and remove it if necessary.
  */
 void dm_put_device(struct dm_target *ti, struct dm_dev *d)
 {
@@ -545,6 +514,7 @@ void dm_put_device(struct dm_target *ti, struct dm_dev *d)
 		kfree(dd);
 	}
 }
+EXPORT_SYMBOL(dm_put_device);
 
 /*
  * Checks to see if the target joins onto the end of the table.
@@ -562,14 +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;
@@ -680,7 +664,7 @@ static int validate_hardware_logical_block_alignment(struct dm_table *table,
 	while (i < dm_table_get_num_targets(table)) {
 		ti = dm_table_get_target(table, i++);
 
-		blk_set_default_limits(&ti_limits);
+		blk_set_stacking_limits(&ti_limits);
 
 		/* combine all target devices' limits */
 		if (ti->type->iterate_devices)
@@ -723,8 +707,13 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 	char **argv;
 	struct dm_target *tgt;
 
-	if ((r = check_space(t)))
-		return r;
+	if (t->singleton) {
+		DMERR("%s: target type %s must appear alone in table",
+		      dm_device_name(t->md), t->targets->type->name);
+		return -EINVAL;
+	}
+
+	BUG_ON(t->num_targets >= t->num_allocated);
 
 	tgt = t->targets + t->num_targets;
 	memset(tgt, 0, sizeof(*tgt));
@@ -741,6 +730,36 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 		return -EINVAL;
 	}
 
+	if (dm_target_needs_singleton(tgt->type)) {
+		if (t->num_targets) {
+			DMERR("%s: target type %s must appear alone in table",
+			      dm_device_name(t->md), type);
+			return -EINVAL;
+		}
+		t->singleton = 1;
+	}
+
+	if (dm_target_always_writeable(tgt->type) && !(t->mode & FMODE_WRITE)) {
+		DMERR("%s: target type %s may not be included in read-only tables",
+		      dm_device_name(t->md), type);
+		return -EINVAL;
+	}
+
+	if (t->immutable_target_type) {
+		if (t->immutable_target_type != tgt->type) {
+			DMERR("%s: immutable target type %s cannot be mixed with other target types",
+			      dm_device_name(t->md), t->immutable_target_type->name);
+			return -EINVAL;
+		}
+	} else if (dm_target_is_immutable(tgt->type)) {
+		if (t->num_targets) {
+			DMERR("%s: immutable target type %s cannot be mixed with other target types",
+			      dm_device_name(t->md), tgt->type->name);
+			return -EINVAL;
+		}
+		t->immutable_target_type = tgt->type;
+	}
+
 	tgt->table = t;
 	tgt->begin = start;
 	tgt->len = len;
@@ -768,8 +787,9 @@ 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)
-		t->discards_supported = 0;
+	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;
 
@@ -779,17 +799,78 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 	return r;
 }
 
+/*
+ * Target argument parsing helpers.
+ */
+static int validate_next_arg(struct dm_arg *arg, struct dm_arg_set *arg_set,
+			     unsigned *value, char **error, unsigned grouped)
+{
+	const char *arg_str = dm_shift_arg(arg_set);
+	char dummy;
+
+	if (!arg_str ||
+	    (sscanf(arg_str, "%u%c", value, &dummy) != 1) ||
+	    (*value < arg->min) ||
+	    (*value > arg->max) ||
+	    (grouped && arg_set->argc < *value)) {
+		*error = arg->error;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int dm_read_arg(struct dm_arg *arg, struct dm_arg_set *arg_set,
+		unsigned *value, char **error)
+{
+	return validate_next_arg(arg, arg_set, value, error, 0);
+}
+EXPORT_SYMBOL(dm_read_arg);
+
+int dm_read_arg_group(struct dm_arg *arg, struct dm_arg_set *arg_set,
+		      unsigned *value, char **error)
+{
+	return validate_next_arg(arg, arg_set, value, error, 1);
+}
+EXPORT_SYMBOL(dm_read_arg_group);
+
+const char *dm_shift_arg(struct dm_arg_set *as)
+{
+	char *r;
+
+	if (as->argc) {
+		as->argc--;
+		r = *as->argv;
+		as->argv++;
+		return r;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(dm_shift_arg);
+
+void dm_consume_args(struct dm_arg_set *as, unsigned num_args)
+{
+	BUG_ON(as->argc < num_args);
+	as->argc -= num_args;
+	as->argv += num_args;
+}
+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;
@@ -801,6 +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;
@@ -840,21 +934,35 @@ unsigned dm_table_get_type(struct dm_table *t)
 	return t->type;
 }
 
+struct target_type *dm_table_get_immutable_target_type(struct dm_table *t)
+{
+	return t->immutable_target_type;
+}
+
 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);
+	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;
 
@@ -921,18 +1029,80 @@ static int dm_table_build_index(struct dm_table *t)
 }
 
 /*
+ * Get a disk whose integrity profile reflects the table's profile.
+ * If %match_all is true, all devices' profiles must match.
+ * If %match_all is false, all devices must at least have an
+ * allocated integrity profile; but uninitialized is ok.
+ * Returns NULL if integrity support was inconsistent or unavailable.
+ */
+static struct gendisk * dm_table_get_integrity_disk(struct dm_table *t,
+						    bool match_all)
+{
+	struct list_head *devices = dm_table_get_devices(t);
+	struct dm_dev_internal *dd = NULL;
+	struct gendisk *prev_disk = NULL, *template_disk = NULL;
+
+	list_for_each_entry(dd, devices, list) {
+		template_disk = dd->dm_dev.bdev->bd_disk;
+		if (!blk_get_integrity(template_disk))
+			goto no_integrity;
+		if (!match_all && !blk_integrity_is_initialized(template_disk))
+			continue; /* skip uninitialized profiles */
+		else if (prev_disk &&
+			 blk_integrity_compare(prev_disk, template_disk) < 0)
+			goto no_integrity;
+		prev_disk = template_disk;
+	}
+
+	return template_disk;
+
+no_integrity:
+	if (prev_disk)
+		DMWARN("%s: integrity not set: %s and %s profile mismatch",
+		       dm_device_name(t->md),
+		       prev_disk->disk_name,
+		       template_disk->disk_name);
+	return NULL;
+}
+
+/*
  * Register the mapped device for blk_integrity support if
- * the underlying devices support it.
+ * the underlying devices have an integrity profile.  But all devices
+ * may not have matching profiles (checking all devices isn't reliable
+ * during table load because this table may use other DM device(s) which
+ * must be resumed before they will have an initialized integity profile).
+ * Stacked DM devices force a 2 stage integrity profile validation:
+ * 1 - during load, validate all initialized integrity profiles match
+ * 2 - during resume, validate all integrity profiles match
  */
 static int dm_table_prealloc_integrity(struct dm_table *t, struct mapped_device *md)
 {
-	struct list_head *devices = dm_table_get_devices(t);
-	struct dm_dev_internal *dd;
+	struct gendisk *template_disk = NULL;
+
+	template_disk = dm_table_get_integrity_disk(t, false);
+	if (!template_disk)
+		return 0;
 
-	list_for_each_entry(dd, devices, list)
-		if (bdev_get_integrity(dd->dm_dev.bdev))
-			return blk_integrity_register(dm_disk(md), NULL);
+	if (!blk_integrity_is_initialized(dm_disk(md))) {
+		t->integrity_supported = 1;
+		return blk_integrity_register(dm_disk(md), NULL);
+	}
 
+	/*
+	 * If DM device already has an initalized integrity
+	 * profile the new profile should not conflict.
+	 */
+	if (blk_integrity_is_initialized(template_disk) &&
+	    blk_integrity_compare(dm_disk(md), template_disk) < 0) {
+		DMWARN("%s: conflict with existing integrity profile: "
+		       "%s profile mismatch",
+		       dm_device_name(t->md),
+		       template_disk->disk_name);
+		return 1;
+	}
+
+	/* Preserve existing initialized integrity profile */
+	t->integrity_supported = 1;
 	return 0;
 }
 
@@ -992,11 +1162,13 @@ void dm_table_event(struct dm_table *t)
 		t->event_fn(t->event_context);
 	mutex_unlock(&_event_lock);
 }
+EXPORT_SYMBOL(dm_table_event);
 
 sector_t dm_table_get_size(struct dm_table *t)
 {
 	return t->num_targets ? (t->highs[t->num_targets - 1] + 1) : 0;
 }
+EXPORT_SYMBOL(dm_table_get_size);
 
 struct dm_target *dm_table_get_target(struct dm_table *t, unsigned int index)
 {
@@ -1029,6 +1201,41 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector)
 	return &t->targets[(KEYS_PER_NODE * n) + k];
 }
 
+static int count_device(struct dm_target *ti, struct dm_dev *dev,
+			sector_t start, sector_t len, void *data)
+{
+	unsigned *num_devices = data;
+
+	(*num_devices)++;
+
+	return 0;
+}
+
+/*
+ * Check whether a table has no data devices attached using each
+ * target's iterate_devices method.
+ * Returns false if the result is unknown because a target doesn't
+ * support iterate_devices.
+ */
+bool dm_table_has_no_data_devices(struct dm_table *table)
+{
+	struct dm_target *uninitialized_var(ti);
+	unsigned i = 0, num_devices = 0;
+
+	while (i < dm_table_get_num_targets(table)) {
+		ti = dm_table_get_target(table, i++);
+
+		if (!ti->type->iterate_devices)
+			return false;
+
+		ti->type->iterate_devices(ti, count_device, &num_devices);
+		if (num_devices)
+			return false;
+	}
+
+	return true;
+}
+
 /*
  * Establish the new table's queue_limits and validate them.
  */
@@ -1039,10 +1246,10 @@ int dm_calculate_queue_limits(struct dm_table *table,
 	struct queue_limits ti_limits;
 	unsigned i = 0;
 
-	blk_set_default_limits(limits);
+	blk_set_stacking_limits(limits);
 
 	while (i < dm_table_get_num_targets(table)) {
-		blk_set_default_limits(&ti_limits);
+		blk_set_stacking_limits(&ti_limits);
 
 		ti = dm_table_get_target(table, i++);
 
@@ -1086,64 +1293,189 @@ combine_limits:
 
 /*
  * Set the integrity profile for this device if all devices used have
- * matching profiles.
+ * matching profiles.  We're quite deep in the resume path but still
+ * don't know if all devices (particularly DM devices this device
+ * may be stacked on) have matching profiles.  Even if the profiles
+ * don't match we have no way to fail (to resume) at this point.
  */
 static void dm_table_set_integrity(struct dm_table *t)
 {
-	struct list_head *devices = dm_table_get_devices(t);
-	struct dm_dev_internal *prev = NULL, *dd = NULL;
+	struct gendisk *template_disk = NULL;
 
 	if (!blk_get_integrity(dm_disk(t->md)))
 		return;
 
-	list_for_each_entry(dd, devices, list) {
-		if (prev &&
-		    blk_integrity_compare(prev->dm_dev.bdev->bd_disk,
-					  dd->dm_dev.bdev->bd_disk) < 0) {
-			DMWARN("%s: integrity not set: %s and %s mismatch",
-			       dm_device_name(t->md),
-			       prev->dm_dev.bdev->bd_disk->disk_name,
-			       dd->dm_dev.bdev->bd_disk->disk_name);
-			goto no_integrity;
-		}
-		prev = dd;
+	template_disk = dm_table_get_integrity_disk(t, true);
+	if (template_disk)
+		blk_integrity_register(dm_disk(t->md),
+				       blk_get_integrity(template_disk));
+	else if (blk_integrity_is_initialized(dm_disk(t->md)))
+		DMWARN("%s: device no longer has a valid integrity profile",
+		       dm_device_name(t->md));
+	else
+		DMWARN("%s: unable to establish an integrity profile",
+		       dm_device_name(t->md));
+}
+
+static int device_flush_capable(struct dm_target *ti, struct dm_dev *dev,
+				sector_t start, sector_t len, void *data)
+{
+	unsigned flush = (*(unsigned *)data);
+	struct request_queue *q = bdev_get_queue(dev->bdev);
+
+	return q && (q->flush_flags & flush);
+}
+
+static bool dm_table_supports_flush(struct dm_table *t, unsigned flush)
+{
+	struct dm_target *ti;
+	unsigned i = 0;
+
+	/*
+	 * Require at least one underlying device to support flushes.
+	 * t->devices includes internal dm devices such as mirror logs
+	 * so we need to use iterate_devices here, which targets
+	 * supporting flushes must provide.
+	 */
+	while (i < dm_table_get_num_targets(t)) {
+		ti = dm_table_get_target(t, i++);
+
+		if (!ti->num_flush_bios)
+			continue;
+
+		if (ti->flush_supported)
+			return 1;
+
+		if (ti->type->iterate_devices &&
+		    ti->type->iterate_devices(ti, device_flush_capable, &flush))
+			return 1;
 	}
 
-	if (!prev || !bdev_get_integrity(prev->dm_dev.bdev))
-		goto no_integrity;
+	return 0;
+}
 
-	blk_integrity_register(dm_disk(t->md),
-			       bdev_get_integrity(prev->dm_dev.bdev));
+static bool dm_table_discard_zeroes_data(struct dm_table *t)
+{
+	struct dm_target *ti;
+	unsigned i = 0;
 
-	return;
+	/* Ensure that all targets supports discard_zeroes_data. */
+	while (i < dm_table_get_num_targets(t)) {
+		ti = dm_table_get_target(t, i++);
 
-no_integrity:
-	blk_integrity_register(dm_disk(t->md), NULL);
+		if (ti->discard_zeroes_data_unsupported)
+			return 0;
+	}
+
+	return 1;
+}
+
+static int device_is_nonrot(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 && blk_queue_nonrot(q);
+}
+
+static int device_is_not_random(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 && !blk_queue_add_random(q);
+}
+
+static bool dm_table_all_devices_attribute(struct dm_table *t,
+					   iterate_devices_callout_fn func)
+{
+	struct dm_target *ti;
+	unsigned i = 0;
+
+	while (i < dm_table_get_num_targets(t)) {
+		ti = dm_table_get_target(t, i++);
+
+		if (!ti->type->iterate_devices ||
+		    !ti->type->iterate_devices(ti, func, NULL))
+			return 0;
+	}
+
+	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;
+	return true;
 }
 
 void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			       struct queue_limits *limits)
 {
+	unsigned flush = 0;
+
 	/*
 	 * Copy table's limits to the DM device's request_queue
 	 */
 	q->limits = *limits;
 
-	if (limits->no_cluster)
-		queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q);
-	else
-		queue_flag_set_unlocked(QUEUE_FLAG_CLUSTER, q);
-
 	if (!dm_table_supports_discards(t))
 		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
 	else
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 
+	if (dm_table_supports_flush(t, REQ_FLUSH)) {
+		flush |= REQ_FLUSH;
+		if (dm_table_supports_flush(t, REQ_FUA))
+			flush |= REQ_FUA;
+	}
+	blk_queue_flush(q, flush);
+
+	if (!dm_table_discard_zeroes_data(t))
+		q->limits.discard_zeroes_data = 0;
+
+	/* Ensure that all underlying devices are non-rotational. */
+	if (dm_table_all_devices_attribute(t, device_is_nonrot))
+		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, 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);
 
 	/*
+	 * Determine whether or not this queue's I/O timings contribute
+	 * to the entropy pool, Only request-based targets use this.
+	 * Clear QUEUE_FLAG_ADD_RANDOM if any underlying device does not
+	 * have it set.
+	 */
+	if (blk_queue_add_random(q) && dm_table_all_devices_attribute(t, device_is_not_random))
+		queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, q);
+
+	/*
 	 * QUEUE_FLAG_STACKABLE must be set after all queue settings are
 	 * visible to other CPUs because, once the flag is set, incoming bios
 	 * are processed by request-based dm, which refers to the queue
@@ -1171,6 +1503,7 @@ fmode_t dm_table_get_mode(struct dm_table *t)
 {
 	return t->mode;
 }
+EXPORT_SYMBOL(dm_table_get_mode);
 
 static void suspend_targets(struct dm_table *t, unsigned postsuspend)
 {
@@ -1215,8 +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++) {
@@ -1229,10 +1565,17 @@ int dm_table_resume_targets(struct dm_table *t)
 	return 0;
 }
 
+void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb)
+{
+	list_add(&cb->list, &t->target_callbacks);
+}
+EXPORT_SYMBOL_GPL(dm_table_add_target_callbacks);
+
 int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 {
 	struct dm_dev_internal *dd;
 	struct list_head *devices = dm_table_get_devices(t);
+	struct dm_target_callbacks *cb;
 	int r = 0;
 
 	list_for_each_entry(dd, devices, list) {
@@ -1247,6 +1590,10 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 				     bdevname(dd->dm_dev.bdev, b));
 	}
 
+	list_for_each_entry(cb, &t->target_callbacks, list)
+		if (cb->congested_fn)
+			r |= cb->congested_fn(cb, bdi_bits);
+
 	return r;
 }
 
@@ -1264,28 +1611,30 @@ int dm_table_any_busy_target(struct dm_table *t)
 	return 0;
 }
 
-void dm_table_unplug_all(struct dm_table *t)
+struct mapped_device *dm_table_get_md(struct dm_table *t)
 {
-	struct dm_dev_internal *dd;
-	struct list_head *devices = dm_table_get_devices(t);
-
-	list_for_each_entry(dd, devices, list) {
-		struct request_queue *q = bdev_get_queue(dd->dm_dev.bdev);
-		char b[BDEVNAME_SIZE];
-
-		if (likely(q))
-			blk_unplug(q);
-		else
-			DMWARN_LIMIT("%s: Cannot unplug nonexistent device %s",
-				     dm_device_name(t->md),
-				     bdevname(dd->dm_dev.bdev, b));
-	}
+	return t->md;
 }
+EXPORT_SYMBOL(dm_table_get_md);
 
-struct mapped_device *dm_table_get_md(struct dm_table *t)
+void dm_table_run_md_queue_async(struct dm_table *t)
 {
-	return t->md;
+	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)
@@ -1300,18 +1649,22 @@ bool dm_table_supports_discards(struct dm_table *t)
 	struct dm_target *ti;
 	unsigned i = 0;
 
-	if (!t->discards_supported)
-		return 0;
-
 	/*
-	 * Ensure that at least one underlying device supports discards.
+	 * Unless any target used by the table set discards_supported,
+	 * require at least one underlying device to support discards.
 	 * t->devices includes internal dm devices such as mirror logs
 	 * so we need to use iterate_devices here, which targets
-	 * supporting discard must provide.
+	 * supporting discard selectively must provide.
 	 */
 	while (i < dm_table_get_num_targets(t)) {
 		ti = dm_table_get_target(t, i++);
 
+		if (!ti->num_discard_bios)
+			continue;
+
+		if (ti->discards_supported)
+			return 1;
+
 		if (ti->type->iterate_devices &&
 		    ti->type->iterate_devices(ti, device_discard_capable, NULL))
 			return 1;
@@ -1319,14 +1672,3 @@ bool dm_table_supports_discards(struct dm_table *t)
 
 	return 0;
 }
-
-EXPORT_SYMBOL(dm_vcalloc);
-EXPORT_SYMBOL(dm_get_device);
-EXPORT_SYMBOL(dm_put_device);
-EXPORT_SYMBOL(dm_table_event);
-EXPORT_SYMBOL(dm_table_get_size);
-EXPORT_SYMBOL(dm_table_get_mode);
-EXPORT_SYMBOL(dm_table_get_md);
-EXPORT_SYMBOL(dm_table_put);
-EXPORT_SYMBOL(dm_table_get);
-EXPORT_SYMBOL(dm_table_unplug_all);