Merge tag 'for-6.6/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:

 - Fix DM core retrieve_deps() UAF race due to missing locking of a DM
   table's list of devices that is managed using dm_{get,put}_device.

 - Revert DM core's half-baked RCU optimization if IO submitter has set
   REQ_NOWAIT. Can be revisited, and properly justified, after
   comprehensively auditing all of DM to also pass GFP_NOWAIT for any
   allocations if REQ_NOWAIT used.

* tag 'for-6.6/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm: don't attempt to queue IO under RCU protection
  dm: fix a race condition in retrieve_deps

Author: torvalds

drivers/md/dm-core.h

@@ -214,6 +214,7 @@ struct dm_table {
 
 	/* a list of devices used by this table */
 	struct list_head devices;
+	struct rw_semaphore devices_lock;
 
 	/* events get handed up using this callback */
 	void (*event_fn)(void *data);

drivers/md/dm-ioctl.c

@@ -1630,6 +1630,8 @@ static void retrieve_deps(struct dm_table *table,
 	struct dm_dev_internal *dd;
 	struct dm_target_deps *deps;
 
+	down_read(&table->devices_lock);
+
 	deps = get_result_buffer(param, param_size, &len);
 
 	/*
@@ -1644,7 +1646,7 @@ static void retrieve_deps(struct dm_table *table,
 	needed = struct_size(deps, dev, count);
 	if (len < needed) {
 		param->flags |= DM_BUFFER_FULL_FLAG;
-		return;
+		goto out;
 	}
 
 	/*
@@ -1656,6 +1658,9 @@ static void retrieve_deps(struct dm_table *table,
 		deps->dev[count++] = huge_encode_dev(dd->dm_dev->bdev->bd_dev);
 
 	param->data_size = param->data_start + needed;
+
+out:
+	up_read(&table->devices_lock);
 }
 
 static int table_deps(struct file *filp, struct dm_ioctl *param, size_t param_size)

drivers/md/dm-table.c

@@ -135,6 +135,7 @@ int dm_table_create(struct dm_table **result, blk_mode_t mode,
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&t->devices);
+	init_rwsem(&t->devices_lock);
 
 	if (!num_targets)
 		num_targets = KEYS_PER_NODE;
@@ -359,16 +360,20 @@ int __ref dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode,
 	if (dev == disk_devt(t->md->disk))
 		return -EINVAL;
 
+	down_write(&t->devices_lock);
+
 	dd = find_device(&t->devices, dev);
 	if (!dd) {
 		dd = kmalloc(sizeof(*dd), GFP_KERNEL);
-		if (!dd)
-			return -ENOMEM;
+		if (!dd) {
+			r = -ENOMEM;
+			goto unlock_ret_r;
+		}
 
 		r = dm_get_table_device(t->md, dev, mode, &dd->dm_dev);
 		if (r) {
 			kfree(dd);
-			return r;
+			goto unlock_ret_r;
 		}
 
 		refcount_set(&dd->count, 1);
@@ -378,12 +383,17 @@ int __ref dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode,
 	} else if (dd->dm_dev->mode != (mode | dd->dm_dev->mode)) {
 		r = upgrade_mode(dd, mode, t->md);
 		if (r)
-			return r;
+			goto unlock_ret_r;
 	}
 	refcount_inc(&dd->count);
 out:
+	up_write(&t->devices_lock);
 	*result = dd->dm_dev;
 	return 0;
+
+unlock_ret_r:
+	up_write(&t->devices_lock);
+	return r;
 }
 EXPORT_SYMBOL(dm_get_device);
 
@@ -419,9 +429,12 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 void dm_put_device(struct dm_target *ti, struct dm_dev *d)
 {
 	int found = 0;
-	struct list_head *devices = &ti->table->devices;
+	struct dm_table *t = ti->table;
+	struct list_head *devices = &t->devices;
 	struct dm_dev_internal *dd;
 
+	down_write(&t->devices_lock);
+
 	list_for_each_entry(dd, devices, list) {
 		if (dd->dm_dev == d) {
 			found = 1;
@@ -430,14 +443,17 @@ void dm_put_device(struct dm_target *ti, struct dm_dev *d)
 	}
 	if (!found) {
 		DMERR("%s: device %s not in table devices list",
-		      dm_device_name(ti->table->md), d->name);
-		return;
+		      dm_device_name(t->md), d->name);
+		goto unlock_ret;
 	}
 	if (refcount_dec_and_test(&dd->count)) {
-		dm_put_table_device(ti->table->md, d);
+		dm_put_table_device(t->md, d);
 		list_del(&dd->list);
 		kfree(dd);
 	}
+
+unlock_ret:
+	up_write(&t->devices_lock);
 }
 EXPORT_SYMBOL(dm_put_device);
 

drivers/md/dm.c

@@ -715,24 +715,6 @@ static void dm_put_live_table_fast(struct mapped_device *md) __releases(RCU)
 	rcu_read_unlock();
 }
 
-static inline struct dm_table *dm_get_live_table_bio(struct mapped_device *md,
-					int *srcu_idx, blk_opf_t bio_opf)
-{
-	if (bio_opf & REQ_NOWAIT)
-		return dm_get_live_table_fast(md);
-	else
-		return dm_get_live_table(md, srcu_idx);
-}
-
-static inline void dm_put_live_table_bio(struct mapped_device *md, int srcu_idx,
-					 blk_opf_t bio_opf)
-{
-	if (bio_opf & REQ_NOWAIT)
-		dm_put_live_table_fast(md);
-	else
-		dm_put_live_table(md, srcu_idx);
-}
-
 static char *_dm_claim_ptr = "I belong to device-mapper";
 
 /*
@@ -1833,9 +1815,8 @@ static void dm_submit_bio(struct bio *bio)
 	struct mapped_device *md = bio->bi_bdev->bd_disk->private_data;
 	int srcu_idx;
 	struct dm_table *map;
-	blk_opf_t bio_opf = bio->bi_opf;
 
-	map = dm_get_live_table_bio(md, &srcu_idx, bio_opf);
+	map = dm_get_live_table(md, &srcu_idx);
 
 	/* If suspended, or map not yet available, queue this IO for later */
 	if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) ||
@@ -1851,7 +1832,7 @@ static void dm_submit_bio(struct bio *bio)
 
 	dm_split_and_process_bio(md, map, bio);
 out:
-	dm_put_live_table_bio(md, srcu_idx, bio_opf);
+	dm_put_live_table(md, srcu_idx);
 }
 
 static bool dm_poll_dm_io(struct dm_io *io, struct io_comp_batch *iob,