This is a note to let you know that I've just added the patch titled
nvme-tcp: fix incorrect h2cdata pdu offset accounting
to the 5.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
nvme-tcp-fix-incorrect-h2cdata-pdu-offset-accounting.patch
and it can be found in the queue-5.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit a8d9e71abf1064d4b62f1cf22f35e27845220c67
Author: Sagi Grimberg <sagi@xxxxxxxxxxx>
Date: Tue Sep 14 18:38:55 2021 +0300
nvme-tcp: fix incorrect h2cdata pdu offset accounting
[ Upstream commit e371af033c560b9dd1e861f8f0b503142bf0a06c ]
When the controller sends us multiple r2t PDUs in a single
request we need to account for it correctly as our send/recv
context run concurrently (i.e. we get a new r2t with r2t_offset
before we updated our iterator and req->data_sent marker). This
can cause wrong offsets to be sent to the controller.
To fix that, we will first know that this may happen only in
the send sequence of the last page, hence we will take
the r2t_offset to the h2c PDU data_offset, and in
nvme_tcp_try_send_data loop, we make sure to increment
the request markers also when we completed a PDU but
we are expecting more r2t PDUs as we still did not send
the entire data of the request.
Fixes: 825619b09ad3 ("nvme-tcp: fix possible use-after-completion")
Reported-by: Nowak, Lukasz <Lukasz.Nowak@xxxxxxxx>
Tested-by: Nowak, Lukasz <Lukasz.Nowak@xxxxxxxx>
Signed-off-by: Sagi Grimberg <sagi@xxxxxxxxxxx>
Reviewed-by: Keith Busch <kbusch@xxxxxxxxxx>
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index a6b3b0762763..05ad6bee085c 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -611,7 +611,7 @@ static int nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req,
cpu_to_le32(data->hdr.hlen + hdgst + req->pdu_len + ddgst);
data->ttag = pdu->ttag;
data->command_id = nvme_cid(rq);
- data->data_offset = cpu_to_le32(req->data_sent);
+ data->data_offset = pdu->r2t_offset;
data->data_length = cpu_to_le32(req->pdu_len);
return 0;
}
@@ -937,7 +937,15 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
nvme_tcp_ddgst_update(queue->snd_hash, page,
offset, ret);
- /* fully successful last write*/
+ /*
+ * update the request iterator except for the last payload send
+ * in the request where we don't want to modify it as we may
+ * compete with the RX path completing the request.
+ */
+ if (req->data_sent + ret < req->data_len)
+ nvme_tcp_advance_req(req, ret);
+
+ /* fully successful last send in current PDU */
if (last && ret == len) {
if (queue->data_digest) {
nvme_tcp_ddgst_final(queue->snd_hash,
@@ -949,7 +957,6 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
}
return 1;
}
- nvme_tcp_advance_req(req, ret);
}
return -EAGAIN;
}
