nvmet-tcp: fix possible memory leak when tearing down a controller

[ Upstream commit 6825bdde44 ]

When we teardown the controller, we wait for pending I/Os to complete
(sq->ref on all queues to drop to zero) and then we go over the commands,
and free their command buffers in case they are still fetching data from
the host (e.g. processing nvme writes) and have yet to take a reference
on the sq.

However, we may miss the case where commands have failed before executing
and are queued for sending a response, but will never occur because the
queue socket is already down. In this case we may miss deallocating command
buffers.

Solve this by freeing all commands buffers as nvmet_tcp_free_cmd_buffers is
idempotent anyways.

Reported-by: Yi Zhang <yi.zhang@redhat.com>
Tested-by: Yi Zhang <yi.zhang@redhat.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
Sagi Grimberg 2024-04-28 11:49:49 +03:00 committed by Greg Kroah-Hartman
parent b6eaa53f95
commit ae451994ba

View file

@ -324,6 +324,7 @@ static int nvmet_tcp_check_ddgst(struct nvmet_tcp_queue *queue, void *pdu)
return 0;
}
/* If cmd buffers are NULL, no operation is performed */
static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd)
{
kfree(cmd->iov);
@ -1476,13 +1477,9 @@ static void nvmet_tcp_free_cmd_data_in_buffers(struct nvmet_tcp_queue *queue)
struct nvmet_tcp_cmd *cmd = queue->cmds;
int i;
for (i = 0; i < queue->nr_cmds; i++, cmd++) {
if (nvmet_tcp_need_data_in(cmd))
nvmet_tcp_free_cmd_buffers(cmd);
}
if (!queue->nr_cmds && nvmet_tcp_need_data_in(&queue->connect))
nvmet_tcp_free_cmd_buffers(&queue->connect);
for (i = 0; i < queue->nr_cmds; i++, cmd++)
nvmet_tcp_free_cmd_buffers(cmd);
nvmet_tcp_free_cmd_buffers(&queue->connect);
}
static void nvmet_tcp_release_queue_work(struct work_struct *w)