nbd: don't handle response without a corresponding request message

BugLink: https://bugs.launchpad.net/bugs/1896350
While handling a response message from server, nbd_read_stat() will
try to get request by tag, and then complete the request. However,
this is problematic if nbd haven't sent a corresponding request
message:

t1                      t2
                        submit_bio
                         nbd_queue_rq
                          blk_mq_start_request
recv_work
 nbd_read_stat
  blk_mq_tag_to_rq
 blk_mq_complete_request
                          nbd_send_cmd

Thus add a new cmd flag 'NBD_CMD_INFLIGHT', it will be set in
nbd_send_cmd() and checked in nbd_read_stat().

Noted that this patch can't fix that blk_mq_tag_to_rq() might
return a freed request, and this will be fixed in following
patches.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Link: https://lore.kernel.org/r/20210916093350.1410403-2-yukuai3@huawei.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
(cherry picked from 4e6eef5dc25b528e08ac5b5f64f6ca9d9987241d)
Signed-off-by: Matthew Ruffell <matthew.ruffell@canonical.com>
Acked-by: Tim Gardner <tim.gardner@canonical.com>
Acked-by: Bartlomiej Zolnierkiewicz <bartlomiej.zolnierkiewicz@canonical.com>
Signed-off-by: Stefan Bader <stefan.bader@canonical.com>

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 92f5ab1216ed3785fc3bd45f5e92a68439f0ed20..a1d5005ea035890c0c121177abb0fcff2faa82b5 100644 (file)
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -131,6 +131,12 @@ struct nbd_device {
 };
 
 #define NBD_CMD_REQUEUED       1
+/*
+ * This flag will be set if nbd_queue_rq() succeed, and will be checked and
+ * cleared in completion. Both setting and clearing of the flag are protected
+ * by cmd->lock.
+ */
+#define NBD_CMD_INFLIGHT       2
 
 struct nbd_cmd {
        struct nbd_device *nbd;
@@ -405,6 +411,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
        if (!mutex_trylock(&cmd->lock))
                return BLK_EH_RESET_TIMER;
 
+       __clear_bit(NBD_CMD_INFLIGHT, &cmd->flags);
        if (!refcount_inc_not_zero(&nbd->config_refs)) {
                cmd->status = BLK_STS_TIMEOUT;
                mutex_unlock(&cmd->lock);
@@ -734,6 +741,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
        cmd = blk_mq_rq_to_pdu(req);
 
        mutex_lock(&cmd->lock);
+       if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) {
+               dev_err(disk_to_dev(nbd->disk), "Suspicious reply %d (status %u flags %lu)",
+                       tag, cmd->status, cmd->flags);
+               ret = -ENOENT;
+               goto out;
+       }
        if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) {
                dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n",
                        req, cmd->cmd_cookie, nbd_handle_to_cookie(handle));
@@ -833,6 +846,7 @@ static bool nbd_clear_req(struct request *req, void *data, bool reserved)
                return true;
 
        mutex_lock(&cmd->lock);
+       __clear_bit(NBD_CMD_INFLIGHT, &cmd->flags);
        cmd->status = BLK_STS_IOERR;
        mutex_unlock(&cmd->lock);
 
@@ -969,7 +983,13 @@ again:
         * returns EAGAIN can be retried on a different socket.
         */
        ret = nbd_send_cmd(nbd, cmd, index);
-       if (ret == -EAGAIN) {
+       /*
+        * Access to this flag is protected by cmd->lock, thus it's safe to set
+        * the flag after nbd_send_cmd() succeed to send request to server.
+        */
+       if (!ret)
+               __set_bit(NBD_CMD_INFLIGHT, &cmd->flags);
+       else if (ret == -EAGAIN) {
                dev_err_ratelimited(disk_to_dev(nbd->disk),
                                    "Request send failed, requeueing\n");
                nbd_mark_nsock_dead(nbd, nsock, 1);