[PATCH v6 0/8] nbd: eliminate queue freeze/unfreeze overhead in connection setup

[PATCH v6 0/8] nbd: eliminate queue freeze/unfreeze overhead in connection setup

[Yang Erkun]

This series eliminates the blk_mq_freeze_queue()/unfreeze_queue()
overhead that currently occurs during nbd connection setup(nbd provide
ondemand and was using in AI sandbox e2b[1] to mount and attach rootfs).
Each freeze cycle will introduce a RCU grace which was significant
with multi-core system.

time nbd-client --name myexport --connections 96 127.0.0.1 1234

After this patchset:
real    0m0.090s
user    0m0.004s
sys     0m0.018s

Without this patchset:
real    0m2.195s
user    0m0.005s
sys     0m0.022s

v5->v6:
1. patch 3, reset stale FEAT*, not only write cache
2. patch 5, using the way Kuai advise to skip freeze
3. patch 6, adopt kuai's suggestion
4. patch 8, rename nr_hw_queues and add some comments

v4->v5:
1. add patch 3 to reset write cache on disconnect
2. fix ("nbd: factor out a nbd_genl_foreach_sock")

v3->v4:
1. factor out nbd_genl_foreach_sock to cleanup duplicated code
2. rewrite some commit message to make what's going more clearly

v2->v3:
1. Stop using xarray, and protect it by rejecting late NBD_SET_SOCKS
2. Eliminate freeze in nbd_set_size when device setup
3. Add module parameter to eliminate freeze for pre-created device

v1->v2:
1. Rewrite cover letter
2. Eliminate freeze call from blk_mq_update_nr_hw_queues in
   nbd_start_device for netlink path


Long Li (1):
  nbd: simplify find_fallback() by removing redundant logic

Yang Erkun (7):
  nbd: disallow NBD_SET_SOCK on an active device
  nbd: clear queue limits on disconnect
  nbd: remove queue freeze in nbd_add_socket
  nbd: skip queue freeze when setting size at device startup
  nbd: factor out a nbd_genl_foreach_sock
  nbd: remove queue freeze for newly created nbd from netlink path
  nbd: add pre_defined_connections module parameter for pre-created
    devices

 drivers/block/nbd.c | 255 +++++++++++++++++++++++---------------------
 1 file changed, 136 insertions(+), 119 deletions(-)

-- 
2.52.0

[PATCH v6 1/8] nbd: simplify find_fallback() by removing redundant logic

[Yang Erkun]

From: Long Li <leo.lilong@huawei.com>

The second conditional checking nsock->fallback_index validity is the
logical inverse of the first, so drop it and let execution fall through
naturally. Consolidate the two identical dev_err_ratelimited() + return
paths into a single no_fallback label to reduce duplication.

Signed-off-by: Long Li <leo.lilong@huawei.com>
Reviewed-by: Yu Kuai <yukuai@fygo.io>
---
 drivers/block/nbd.c | 37 ++++++++++++++-----------------------
 1 file changed, 14 insertions(+), 23 deletions(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 8f10762e90ef..b1a5acd57426 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1061,40 +1061,31 @@ static int find_fallback(struct nbd_device *nbd, int index)
 	int new_index = -1;
 	struct nbd_sock *nsock = config->socks[index];
 	int fallback = nsock->fallback_index;
+	int i;
 
 	if (test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags))
 		return new_index;
 
-	if (config->num_connections <= 1) {
-		dev_err_ratelimited(disk_to_dev(nbd->disk),
-				    "Dead connection, failed to find a fallback\n");
-		return new_index;
-	}
+	if (config->num_connections <= 1)
+		goto no_fallback;
 
 	if (fallback >= 0 && fallback < config->num_connections &&
 	    !config->socks[fallback]->dead)
 		return fallback;
 
-	if (nsock->fallback_index < 0 ||
-	    nsock->fallback_index >= config->num_connections ||
-	    config->socks[nsock->fallback_index]->dead) {
-		int i;
-		for (i = 0; i < config->num_connections; i++) {
-			if (i == index)
-				continue;
-			if (!config->socks[i]->dead) {
-				new_index = i;
-				break;
-			}
-		}
-		nsock->fallback_index = new_index;
-		if (new_index < 0) {
-			dev_err_ratelimited(disk_to_dev(nbd->disk),
-					    "Dead connection, failed to find a fallback\n");
-			return new_index;
+	for (i = 0; i < config->num_connections; i++) {
+		if (i != index && !config->socks[i]->dead) {
+			new_index = i;
+			break;
 		}
 	}
-	new_index = nsock->fallback_index;
+	nsock->fallback_index = new_index;
+	if (new_index >= 0)
+		return new_index;
+
+no_fallback:
+	dev_err_ratelimited(disk_to_dev(nbd->disk),
+			    "Dead connection, failed to find a fallback\n");
 	return new_index;
 }
 
-- 
2.52.0

[PATCH v6 2/8] nbd: disallow NBD_SET_SOCK on an active device

[Yang Erkun]

We cannot add a socket to an already running nbd device, the reconfigure
for netlink can only active an inactive socket. But for ioctl path, we can
call NBD_SET_SOCK after NBD_DO_IT, reject this using nbd->pid which has
been setted when NBD_DO_IT. Besides, it is the root cause for commit
b98e762e3d71 ("nbd: freeze the queue while we're adding connections").

Reviewed-by: Yu Kuai <yukuai@fygo.io>
Signed-off-by: Yang Erkun <yangerkun@huawei.com>
---
 drivers/block/nbd.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index b1a5acd57426..7ec85f94f742 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1278,6 +1278,13 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 	/* Arg will be cast to int, check it to avoid overflow */
 	if (arg > INT_MAX)
 		return -EINVAL;
+
+	if (nbd->pid) {
+		dev_err(disk_to_dev(nbd->disk),
+			"Cannot add socket to a running device\n");
+		return -EBUSY;
+	}
+
 	sock = nbd_get_socket(nbd, arg, &err);
 	if (!sock)
 		return err;
-- 
2.52.0

[PATCH v6 3/8] nbd: clear queue limits on disconnect

[Yang Erkun]

An inactive nbd device may refuse any I/O operations. The nbd_config_put
function calls invalidate_disk, which sets the device capacity to zero
to reject all read and write I/O. For zero-sector flush I/O requests
from blkdev_issue_flush, if the write cache is disabled, the zero-sector
flush I/O immediately returns 0 in submit_bio_noacct. However, since
nbd_config_put does not clear the write cache state, an inactive nbd
device might still have the write cache enabled. In this situation,
zero-sector flush I/O will return -EIO because there is no active socket.
Additionally, BLK_FEAT_FUA and BLK_FEAT_ROTATIONAL flags may also remain
stale, resetting all of them ensures consistent behavior.

The limits update uses queue_limits_commit_update() (the non-freezing
variant) because config_refs == 0 here means every fd is closed and recv
threads have drained, so no in-flight I/O can read q->limits concurrently.

Signed-off-by: Yang Erkun <yangerkun@huawei.com>
---
 drivers/block/nbd.c | 43 ++++++++++++++++++++++++++-----------------
 1 file changed, 26 insertions(+), 17 deletions(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 7ec85f94f742..45e58191c5d7 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -331,6 +331,26 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
 	nsock->sent = 0;
 }
 
+static void nbd_apply_limits(struct queue_limits *lim, u32 flags)
+{
+	lim->features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | BLK_FEAT_ROTATIONAL);
+	lim->max_hw_discard_sectors = 0;
+	lim->max_write_zeroes_sectors = 0;
+
+	if (flags & NBD_FLAG_SEND_TRIM)
+		lim->max_hw_discard_sectors = UINT_MAX << SECTOR_SHIFT;
+	if (flags & NBD_FLAG_SEND_FLUSH) {
+		lim->features |= BLK_FEAT_WRITE_CACHE;
+		if (flags & NBD_FLAG_SEND_FUA)
+			lim->features |= BLK_FEAT_FUA;
+	}
+
+	if (flags & NBD_FLAG_ROTATIONAL)
+		lim->features |= BLK_FEAT_ROTATIONAL;
+	if (flags & NBD_FLAG_SEND_WRITE_ZEROES)
+		lim->max_write_zeroes_sectors = UINT_MAX >> SECTOR_SHIFT;
+}
+
 static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, loff_t blksize)
 {
 	struct queue_limits lim;
@@ -352,23 +372,7 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, loff_t blksize)
 		return 0;
 
 	lim = queue_limits_start_update(nbd->disk->queue);
-	if (nbd->config->flags & NBD_FLAG_SEND_TRIM)
-		lim.max_hw_discard_sectors = UINT_MAX >> SECTOR_SHIFT;
-	else
-		lim.max_hw_discard_sectors = 0;
-	if (!(nbd->config->flags & NBD_FLAG_SEND_FLUSH)) {
-		lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA);
-	} else if (nbd->config->flags & NBD_FLAG_SEND_FUA) {
-		lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA;
-	} else {
-		lim.features |= BLK_FEAT_WRITE_CACHE;
-		lim.features &= ~BLK_FEAT_FUA;
-	}
-	if (nbd->config->flags & NBD_FLAG_ROTATIONAL)
-		lim.features |= BLK_FEAT_ROTATIONAL;
-	if (nbd->config->flags & NBD_FLAG_SEND_WRITE_ZEROES)
-		lim.max_write_zeroes_sectors = UINT_MAX >> SECTOR_SHIFT;
-
+	nbd_apply_limits(&lim, nbd->config->flags);
 	lim.logical_block_size = blksize;
 	lim.physical_block_size = blksize;
 	error = queue_limits_commit_update_frozen(nbd->disk->queue, &lim);
@@ -1469,8 +1473,13 @@ static void nbd_config_put(struct nbd_device *nbd)
 	if (refcount_dec_and_mutex_lock(&nbd->config_refs,
 					&nbd->config_lock)) {
 		struct nbd_config *config = nbd->config;
+		struct queue_limits lim;
 		nbd_dev_dbg_close(nbd);
 		invalidate_disk(nbd->disk);
+		/* reset queue limits to default */
+		lim = queue_limits_start_update(nbd->disk->queue);
+		nbd_apply_limits(&lim, 0);
+		queue_limits_commit_update(nbd->disk->queue, &lim);
 		if (nbd->config->bytesize)
 			kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
 		if (test_and_clear_bit(NBD_RT_HAS_PID_FILE,
-- 
2.52.0

Re: [PATCH v6 3/8] nbd: clear queue limits on disconnect

[yangerkun]

在 2026/8/4 16:39, Yang Erkun 写道:
> An inactive nbd device may refuse any I/O operations. The nbd_config_put
> function calls invalidate_disk, which sets the device capacity to zero
> to reject all read and write I/O. For zero-sector flush I/O requests
> from blkdev_issue_flush, if the write cache is disabled, the zero-sector
> flush I/O immediately returns 0 in submit_bio_noacct. However, since
> nbd_config_put does not clear the write cache state, an inactive nbd
> device might still have the write cache enabled. In this situation,
> zero-sector flush I/O will return -EIO because there is no active socket.
> Additionally, BLK_FEAT_FUA and BLK_FEAT_ROTATIONAL flags may also remain
> stale, resetting all of them ensures consistent behavior.
> 
> The limits update uses queue_limits_commit_update() (the non-freezing
> variant) because config_refs == 0 here means every fd is closed and recv
> threads have drained, so no in-flight I/O can read q->limits concurrently.
> 
> Signed-off-by: Yang Erkun <yangerkun@huawei.com>
> ---
>   drivers/block/nbd.c | 43 ++++++++++++++++++++++++++-----------------
>   1 file changed, 26 insertions(+), 17 deletions(-)
> 
> diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
> index 7ec85f94f742..45e58191c5d7 100644
> --- a/drivers/block/nbd.c
> +++ b/drivers/block/nbd.c
> @@ -331,6 +331,26 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
>   	nsock->sent = 0;
>   }
>   
> +static void nbd_apply_limits(struct queue_limits *lim, u32 flags)
> +{
> +	lim->features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | BLK_FEAT_ROTATIONAL);
> +	lim->max_hw_discard_sectors = 0;
> +	lim->max_write_zeroes_sectors = 0;
> +
> +	if (flags & NBD_FLAG_SEND_TRIM)
> +		lim->max_hw_discard_sectors = UINT_MAX << SECTOR_SHIFT;

I am so sorry there is a mistake here... Should be UINT_MAX >> SECTOR_SHIFT

> +	if (flags & NBD_FLAG_SEND_FLUSH) {
> +		lim->features |= BLK_FEAT_WRITE_CACHE;
> +		if (flags & NBD_FLAG_SEND_FUA)
> +			lim->features |= BLK_FEAT_FUA;
> +	}
> +
> +	if (flags & NBD_FLAG_ROTATIONAL)
> +		lim->features |= BLK_FEAT_ROTATIONAL;
> +	if (flags & NBD_FLAG_SEND_WRITE_ZEROES)
> +		lim->max_write_zeroes_sectors = UINT_MAX >> SECTOR_SHIFT;
> +}
> +
>   static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, loff_t blksize)
>   {
>   	struct queue_limits lim;
> @@ -352,23 +372,7 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, loff_t blksize)
>   		return 0;
>   
>   	lim = queue_limits_start_update(nbd->disk->queue);
> -	if (nbd->config->flags & NBD_FLAG_SEND_TRIM)
> -		lim.max_hw_discard_sectors = UINT_MAX >> SECTOR_SHIFT;
> -	else
> -		lim.max_hw_discard_sectors = 0;
> -	if (!(nbd->config->flags & NBD_FLAG_SEND_FLUSH)) {
> -		lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA);
> -	} else if (nbd->config->flags & NBD_FLAG_SEND_FUA) {
> -		lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA;
> -	} else {
> -		lim.features |= BLK_FEAT_WRITE_CACHE;
> -		lim.features &= ~BLK_FEAT_FUA;
> -	}
> -	if (nbd->config->flags & NBD_FLAG_ROTATIONAL)
> -		lim.features |= BLK_FEAT_ROTATIONAL;
> -	if (nbd->config->flags & NBD_FLAG_SEND_WRITE_ZEROES)
> -		lim.max_write_zeroes_sectors = UINT_MAX >> SECTOR_SHIFT;
> -
> +	nbd_apply_limits(&lim, nbd->config->flags);
>   	lim.logical_block_size = blksize;
>   	lim.physical_block_size = blksize;
>   	error = queue_limits_commit_update_frozen(nbd->disk->queue, &lim);
> @@ -1469,8 +1473,13 @@ static void nbd_config_put(struct nbd_device *nbd)
>   	if (refcount_dec_and_mutex_lock(&nbd->config_refs,
>   					&nbd->config_lock)) {
>   		struct nbd_config *config = nbd->config;
> +		struct queue_limits lim;
>   		nbd_dev_dbg_close(nbd);
>   		invalidate_disk(nbd->disk);
> +		/* reset queue limits to default */
> +		lim = queue_limits_start_update(nbd->disk->queue);
> +		nbd_apply_limits(&lim, 0);
> +		queue_limits_commit_update(nbd->disk->queue, &lim);
>   		if (nbd->config->bytesize)
>   			kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
>   		if (test_and_clear_bit(NBD_RT_HAS_PID_FILE,

[PATCH v6 4/8] nbd: remove queue freeze in nbd_add_socket

[Yang Erkun]

nbd_add_socket() kreallocs config->socks, which a concurrent reader in
nbd_handle_cmd() could UAF; commit b98e762e3d71 ("nbd: freeze the queue
while we're adding connections")froze the queue to block that.  But the
freeze costs an RCU grace period on every socket added, and setup adds
them one by one.

After the previous patch, nbd_add_socket() is rejected once nbd->pid is
set, so it only runs during setup.  There the capacity is 0 and the
write cache is off (cleared on disconnect by the preceding patch, and
re-enabled only later in nbd_set_size), so submit_bio_noacct() rejects
every bio before it reaches the driver -- non-zero-sector ones via
bio_check_eod(), and flush-only ones via the !bdev_write_cache() branch.
No I/O is in flight, so the freeze is unnecessary.

Signed-off-by: Yang Erkun <yangerkun@huawei.com>
---
 drivers/block/nbd.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 45e58191c5d7..8aeffc0eaaa1 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1276,7 +1276,6 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 	struct socket *sock;
 	struct nbd_sock **socks;
 	struct nbd_sock *nsock;
-	unsigned int memflags;
 	int err;
 
 	/* Arg will be cast to int, check it to avoid overflow */
@@ -1294,12 +1293,6 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 		return err;
 	nbd_reclassify_socket(sock);
 
-	/*
-	 * We need to make sure we don't get any errant requests while we're
-	 * reallocating the ->socks array.
-	 */
-	memflags = blk_mq_freeze_queue(nbd->disk->queue);
-
 	if (!netlink && !nbd->task_setup &&
 	    !test_bit(NBD_RT_BOUND, &config->runtime_flags))
 		nbd->task_setup = current;
@@ -1339,12 +1332,10 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 	INIT_WORK(&nsock->work, nbd_pending_cmd_work);
 	socks[config->num_connections++] = nsock;
 	atomic_inc(&config->live_connections);
-	blk_mq_unfreeze_queue(nbd->disk->queue, memflags);
 
 	return 0;
 
 put_socket:
-	blk_mq_unfreeze_queue(nbd->disk->queue, memflags);
 	sockfd_put(sock);
 	return err;
 }
-- 
2.52.0

[PATCH v6 5/8] nbd: skip queue freeze when setting size at device startup

[Yang Erkun]

Commit 242a49e5c878 ("nbd: freeze the queue for queue limits updates")
added the freeze to keep in-flight commands from seeing
torn queue_limits.  But at startup the capacity is still 0
(invalidate_disk cleared it) and the write cache is off (the previous
patch cleared it on disconnect, and nbd_set_size sets it back only after
the commit), so submit_bio_noacct() rejects any bio before it reaches
the driver and no I/O is in flight.  Drop the freeze by checking
capacity and write cache state in nbd_set_size.

Signed-off-by: Yang Erkun <yangerkun@huawei.com>
---
 drivers/block/nbd.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 8aeffc0eaaa1..66f1b3263b94 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -375,7 +375,11 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, loff_t blksize)
 	nbd_apply_limits(&lim, nbd->config->flags);
 	lim.logical_block_size = blksize;
 	lim.physical_block_size = blksize;
-	error = queue_limits_commit_update_frozen(nbd->disk->queue, &lim);
+	/* No need freeze with 0 capacity and write cache disabled */
+	if (!get_capacity(nbd->disk) && !blk_queue_write_cache(nbd->disk->queue))
+		error = queue_limits_commit_update(nbd->disk->queue, &lim);
+	else
+		error = queue_limits_commit_update_frozen(nbd->disk->queue, &lim);
 	if (error)
 		return error;
 
-- 
2.52.0

[PATCH v6 6/8] nbd: factor out a nbd_genl_foreach_sock

[Yang Erkun]

The NBD_ATTR_SOCKETS walk is duplicated in nbd_genl_connect (add sockets)
and nbd_genl_reconfigure (reconnect).  Factor out a single helper that
walks the list and calls a callback per fd; with a NULL callback it is a
pure counter, used by a later patch to learn nr_hw_queues before the
device exists.  Returns the number of fds walked (>= 0) or a negative
errno; a callback >0 will stops early.

Signed-off-by: Yang Erkun <yangerkun@huawei.com>
---
 drivers/block/nbd.c | 131 ++++++++++++++++++++++----------------------
 1 file changed, 66 insertions(+), 65 deletions(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 66f1b3263b94..c080bb95653b 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1399,11 +1399,12 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
 
 		atomic_inc(&config->live_connections);
 		wake_up(&config->conn_wait);
+		dev_info(nbd_to_dev(nbd), "reconnected socket\n");
 		return 0;
 	}
 	sockfd_put(sock);
 	kfree(args);
-	return -ENOSPC;
+	return 1;
 }
 
 static void nbd_bdev_reset(struct nbd_device *nbd)
@@ -2109,6 +2110,58 @@ static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd)
 	return 0;
 }
 
+/*
+ * Walk the NBD_ATTR_SOCKETS nested list can call @cb for each socket fd.
+ *
+ * Return the number of fds walked, or a negative errno.
+ */
+static int nbd_genl_foreach_sock(struct genl_info *info,
+		int (*cb)(struct nbd_device *nbd, int fd),
+		struct nbd_device *nbd)
+{
+	struct nlattr *attr;
+	int rem, count = 0;
+
+	if (!info->attrs[NBD_ATTR_SOCKETS])
+		return 0;
+
+	nla_for_each_nested(attr, info->attrs[NBD_ATTR_SOCKETS], rem) {
+		struct nlattr *socks[NBD_SOCK_MAX + 1];
+		int ret;
+
+		if (nla_type(attr) != NBD_SOCK_ITEM) {
+			pr_err("socks must be embedded in a SOCK_ITEM attr\n");
+			return -EINVAL;
+		}
+
+		if (nla_parse_nested_deprecated(socks, NBD_SOCK_MAX,
+						attr,
+						nbd_sock_policy,
+						info->extack)) {
+			pr_err("error processing sock list\n");
+			return -EINVAL;
+		}
+
+		if (!socks[NBD_SOCK_FD])
+			continue;
+
+		count++;
+		if (cb) {
+			ret = cb(nbd, (int)nla_get_u32(socks[NBD_SOCK_FD]));
+			if (ret > 0)
+				return count;
+			if (ret < 0)
+				return ret;
+		}
+	}
+	return count;
+}
+
+static int nbd_genl_connect_sock_cb(struct nbd_device *nbd, int fd)
+{
+	return nbd_add_socket(nbd, fd, true);
+}
+
 static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nbd_device *nbd;
@@ -2228,36 +2281,9 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	if (info->attrs[NBD_ATTR_SOCKETS]) {
-		struct nlattr *attr;
-		int rem, fd;
-
-		nla_for_each_nested(attr, info->attrs[NBD_ATTR_SOCKETS],
-				    rem) {
-			struct nlattr *socks[NBD_SOCK_MAX+1];
-
-			if (nla_type(attr) != NBD_SOCK_ITEM) {
-				pr_err("socks must be embedded in a SOCK_ITEM attr\n");
-				ret = -EINVAL;
-				goto out;
-			}
-			ret = nla_parse_nested_deprecated(socks, NBD_SOCK_MAX,
-							  attr,
-							  nbd_sock_policy,
-							  info->extack);
-			if (ret != 0) {
-				pr_err("error processing sock list\n");
-				ret = -EINVAL;
-				goto out;
-			}
-			if (!socks[NBD_SOCK_FD])
-				continue;
-			fd = (int)nla_get_u32(socks[NBD_SOCK_FD]);
-			ret = nbd_add_socket(nbd, fd, true);
-			if (ret)
-				goto out;
-		}
-	}
+	ret = nbd_genl_foreach_sock(info, nbd_genl_connect_sock_cb, nbd);
+	if (ret < 0)
+		goto out;
 
 	if (info->attrs[NBD_ATTR_BACKEND_IDENTIFIER]) {
 		nbd->backend = nla_strdup(info->attrs[NBD_ATTR_BACKEND_IDENTIFIER],
@@ -2346,6 +2372,11 @@ static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
+static int nbd_genl_reconnect_sock_cb(struct nbd_device *nbd, int fd)
+{
+	return nbd_reconnect_socket(nbd, fd);
+}
+
 static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nbd_device *nbd = NULL;
@@ -2442,40 +2473,10 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	if (info->attrs[NBD_ATTR_SOCKETS]) {
-		struct nlattr *attr;
-		int rem, fd;
-
-		nla_for_each_nested(attr, info->attrs[NBD_ATTR_SOCKETS],
-				    rem) {
-			struct nlattr *socks[NBD_SOCK_MAX+1];
-
-			if (nla_type(attr) != NBD_SOCK_ITEM) {
-				pr_err("socks must be embedded in a SOCK_ITEM attr\n");
-				ret = -EINVAL;
-				goto out;
-			}
-			ret = nla_parse_nested_deprecated(socks, NBD_SOCK_MAX,
-							  attr,
-							  nbd_sock_policy,
-							  info->extack);
-			if (ret != 0) {
-				pr_err("error processing sock list\n");
-				ret = -EINVAL;
-				goto out;
-			}
-			if (!socks[NBD_SOCK_FD])
-				continue;
-			fd = (int)nla_get_u32(socks[NBD_SOCK_FD]);
-			ret = nbd_reconnect_socket(nbd, fd);
-			if (ret) {
-				if (ret == -ENOSPC)
-					ret = 0;
-				goto out;
-			}
-			dev_info(nbd_to_dev(nbd), "reconnected socket\n");
-		}
-	}
+	ret = nbd_genl_foreach_sock(info, nbd_genl_reconnect_sock_cb, nbd);
+	/* foreach_sock returns a positive count on success; doit must return 0 */
+	if (ret >= 0)
+		ret = 0;
 out:
 	mutex_unlock(&nbd->config_lock);
 	nbd_config_put(nbd);
-- 
2.52.0

[PATCH v6 7/8] nbd: remove queue freeze for newly created nbd from netlink path

[Yang Erkun]

Previous commits has removed the queue freeze in nbd_add_socket and
nbd_set_size during nbd device setup. However, a queue freeze can still
occur when nbd_start_device calls blk_mq_update_nr_hw_queues if the
socket connection count does not match nbd->tag_set->nr_hw_queues.

The nbd_start_device function can be invoked through either the ioctl or
netlink paths. The ioctl path only allows reusing an existing inactivate
nbd device, there is nothing more we can do to prevent the queue freeze
since the old nbd->tag_set->nr_hw_queues may not match the new socket
connection count. Similarly, the netlink path can reuse a preferred
inactivate nbd device, and again, we cannot do more in this scenario.
However, the netlink path can also add a new nbd device using
nbd_dev_add. In this case, we can obtain the new number of socket
connections, and by adding a new argument representing the expected
nr_hw_queues in nbd_dev_add, we can ensure the queue freeze is avoided
for this situation.

Reviewed-by: Yu Kuai <yukuai@fygo.io>
Signed-off-by: Yang Erkun <yangerkun@huawei.com>
---
 drivers/block/nbd.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index c080bb95653b..481911c5ac50 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1944,7 +1944,8 @@ static const struct blk_mq_ops nbd_mq_ops = {
 	.timeout	= nbd_xmit_timeout,
 };
 
-static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
+static struct nbd_device *nbd_dev_add(int index, unsigned int refs,
+				       int nr_hw_queues)
 {
 	struct queue_limits lim = {
 		.max_hw_sectors		= 65536,
@@ -1961,7 +1962,7 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 		goto out;
 
 	nbd->tag_set.ops = &nbd_mq_ops;
-	nbd->tag_set.nr_hw_queues = 1;
+	nbd->tag_set.nr_hw_queues = nr_hw_queues;
 	nbd->tag_set.queue_depth = 128;
 	nbd->tag_set.numa_node = NUMA_NO_NODE;
 	nbd->tag_set.cmd_size = sizeof(struct nbd_cmd);
@@ -2214,7 +2215,11 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 	mutex_unlock(&nbd_index_mutex);
 
 	if (!nbd) {
-		nbd = nbd_dev_add(index, 2);
+		ret = nbd_genl_foreach_sock(info, NULL, NULL);
+		if (ret < 0)
+			return ret;
+
+		nbd = nbd_dev_add(index, 2, ret > 0 ? ret : 1);
 		if (IS_ERR(nbd)) {
 			pr_err("failed to add new device\n");
 			return PTR_ERR(nbd);
@@ -2729,7 +2734,7 @@ static int __init nbd_init(void)
 	nbd_dbg_init();
 
 	for (i = 0; i < nbds_max; i++)
-		nbd_dev_add(i, 1);
+		nbd_dev_add(i, 1, 1);
 	return 0;
 }
 
-- 
2.52.0

[PATCH v6 8/8] nbd: add pre_defined_connections module parameter for pre-created devices

[Yang Erkun]

blk_mq_update_nr_hw_queues() in nbd_start_device() may cause a queue
freeze.  The previous commit addressed this for newly created nbd
devices by setting the expected nr_hw_queues in nbd_dev_add().  However,
when reusing an old inactive nbd device, the queue freeze can still
occur if the old nbd->tag_set->nr_hw_queues does not match the new
socket connection count.  Inactive nbd devices can originate from two
sources: loading the nbd module with nbds_max, which sets the default
nr_hw_queues to 1, and the netlink method, which sets nr_hw_queues
according to the expected number of socket connections.  For the first
case, add a module parameter so the default nr_hw_queues can be
changed.  Users who know their expected number of connections can then
prevent queue freezes on pre-created devices via nbds_max.

Before this patchset:
real    0m2.195s
user    0m0.005s
sys     0m0.022s

After this patchset:
real    0m0.090s
user    0m0.004s
sys     0m0.018s

Signed-off-by: Yang Erkun <yangerkun@huawei.com>
---
 drivers/block/nbd.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 481911c5ac50..eec14617fa15 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -166,6 +166,7 @@ static struct dentry *nbd_dbg_dir;
 
 static unsigned int nbds_max = 16;
 static int max_part = 16;
+static int pre_defined_connections = 1;
 static int part_shift;
 
 static int nbd_dev_dbg_init(struct nbd_device *nbd);
@@ -2733,8 +2734,13 @@ static int __init nbd_init(void)
 	}
 	nbd_dbg_init();
 
+	if (pre_defined_connections < 1)
+		pre_defined_connections = 1;
+	/* Set to the intended connection count so nbd_start_device() can skip
+	 * the queue-freezing blk_mq_update_nr_hw_queues() call.
+	 */
 	for (i = 0; i < nbds_max; i++)
-		nbd_dev_add(i, 1, 1);
+		nbd_dev_add(i, 1, pre_defined_connections);
 	return 0;
 }
 
@@ -2795,3 +2801,6 @@ module_param(nbds_max, int, 0444);
 MODULE_PARM_DESC(nbds_max, "number of network block devices to initialize (default: 16)");
 module_param(max_part, int, 0444);
 MODULE_PARM_DESC(max_part, "number of partitions per device (default: 16)");
+module_param(pre_defined_connections, int, 0444);
+MODULE_PARM_DESC(pre_defined_connections,
+"number of connections for devices pre-created at module load (default: 1)");
-- 
2.52.0