From: Aurelien Aptel <aaptel@nvidia.com>
To: linux-nvme@lists.infradead.org, netdev@vger.kernel.org,
sagi@grimberg.me, hch@lst.de, kbusch@kernel.org, axboe@fb.com,
chaitanyak@nvidia.com, davem@davemloft.net, kuba@kernel.org
Cc: Yoray Zack <yorayz@nvidia.com>,
aaptel@nvidia.com, aurelien.aptel@gmail.com, smalin@nvidia.com,
malin1024@gmail.com, ogerlitz@nvidia.com, borisp@nvidia.com,
galshalom@nvidia.com, mgurtovoy@nvidia.com
Subject: [PATCH v18 07/20] nvme-tcp: RX DDGST offload
Date: Fri, 27 Oct 2023 12:27:42 +0000 [thread overview]
Message-ID: <20231027122755.205334-8-aaptel@nvidia.com> (raw)
In-Reply-To: <20231027122755.205334-1-aaptel@nvidia.com>
From: Yoray Zack <yorayz@nvidia.com>
Enable rx side of DDGST offload when supported.
At the end of the capsule, check if all the skb bits are on, and if not
recalculate the DDGST in SW and check it.
Signed-off-by: Yoray Zack <yorayz@nvidia.com>
Signed-off-by: Boris Pismenny <borisp@nvidia.com>
Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Signed-off-by: Or Gerlitz <ogerlitz@nvidia.com>
Signed-off-by: Shai Malin <smalin@nvidia.com>
Signed-off-by: Aurelien Aptel <aaptel@nvidia.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
---
drivers/nvme/host/tcp.c | 84 ++++++++++++++++++++++++++++++++++++++---
1 file changed, 79 insertions(+), 5 deletions(-)
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 5c80ee089ee1..5c20f53b8002 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -126,6 +126,7 @@ enum nvme_tcp_queue_flags {
NVME_TCP_Q_LIVE = 1,
NVME_TCP_Q_POLLING = 2,
NVME_TCP_Q_OFF_DDP = 3,
+ NVME_TCP_Q_OFF_DDGST_RX = 4,
};
enum nvme_tcp_recv_state {
@@ -163,6 +164,7 @@ struct nvme_tcp_queue {
* is pending (ULP_DDP_RESYNC_PENDING).
*/
atomic64_t resync_tcp_seq;
+ bool ddp_ddgst_valid;
#endif
/* send state */
@@ -342,6 +344,33 @@ nvme_tcp_get_ddp_netdev_with_limits(struct nvme_tcp_ctrl *ctrl)
return netdev;
}
+static inline bool nvme_tcp_ddp_ddgst_ok(struct nvme_tcp_queue *queue)
+{
+ return queue->ddp_ddgst_valid;
+}
+
+static inline void nvme_tcp_ddp_ddgst_update(struct nvme_tcp_queue *queue,
+ struct sk_buff *skb)
+{
+ if (queue->ddp_ddgst_valid)
+ queue->ddp_ddgst_valid = skb_is_ulp_crc(skb);
+}
+
+static void nvme_tcp_ddp_ddgst_recalc(struct ahash_request *hash,
+ struct request *rq,
+ __le32 *ddgst)
+{
+ struct nvme_tcp_request *req;
+
+ if (!rq)
+ return;
+
+ req = blk_mq_rq_to_pdu(rq);
+ ahash_request_set_crypt(hash, req->ddp.sg_table.sgl, (u8 *)ddgst,
+ req->data_len);
+ crypto_ahash_digest(hash);
+}
+
static bool nvme_tcp_resync_request(struct sock *sk, u32 seq, u32 flags);
static void nvme_tcp_ddp_teardown_done(void *ddp_ctx);
static const struct ulp_ddp_ulp_ops nvme_tcp_ddp_ulp_ops = {
@@ -412,6 +441,8 @@ static void nvme_tcp_setup_ddp(struct nvme_tcp_queue *queue,
static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
{
struct ulp_ddp_config config = {.type = ULP_DDP_NVME};
+ bool offload_ddgst_rx = ulp_ddp_is_cap_active(queue->ctrl->ddp_netdev,
+ ULP_DDP_CAP_NVME_TCP_DDGST_RX);
int ret;
config.nvmeotcp.pfv = NVME_TCP_PFV_1_0;
@@ -431,6 +462,8 @@ static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
return ret;
set_bit(NVME_TCP_Q_OFF_DDP, &queue->flags);
+ if (queue->data_digest && offload_ddgst_rx)
+ set_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags);
return 0;
}
@@ -438,6 +471,7 @@ static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
static void nvme_tcp_unoffload_socket(struct nvme_tcp_queue *queue)
{
clear_bit(NVME_TCP_Q_OFF_DDP, &queue->flags);
+ clear_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags);
ulp_ddp_sk_del(queue->ctrl->ddp_netdev, queue->sock->sk);
}
@@ -537,6 +571,20 @@ static void nvme_tcp_resync_response(struct nvme_tcp_queue *queue,
struct sk_buff *skb, unsigned int offset)
{}
+static inline bool nvme_tcp_ddp_ddgst_ok(struct nvme_tcp_queue *queue)
+{
+ return false;
+}
+
+static inline void nvme_tcp_ddp_ddgst_update(struct nvme_tcp_queue *queue,
+ struct sk_buff *skb)
+{}
+
+static void nvme_tcp_ddp_ddgst_recalc(struct ahash_request *hash,
+ struct request *rq,
+ __le32 *ddgst)
+{}
+
#endif
static void nvme_tcp_init_iter(struct nvme_tcp_request *req,
@@ -797,6 +845,9 @@ static void nvme_tcp_init_recv_ctx(struct nvme_tcp_queue *queue)
queue->pdu_offset = 0;
queue->data_remaining = -1;
queue->ddgst_remaining = 0;
+#ifdef CONFIG_ULP_DDP
+ queue->ddp_ddgst_valid = true;
+#endif
}
static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl)
@@ -1064,6 +1115,10 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
nvme_cid_to_rq(nvme_tcp_tagset(queue), pdu->command_id);
struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
+ if (queue->data_digest &&
+ test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags))
+ nvme_tcp_ddp_ddgst_update(queue, skb);
+
while (true) {
int recv_len, ret;
@@ -1092,7 +1147,8 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
recv_len = min_t(size_t, recv_len,
iov_iter_count(&req->iter));
- if (queue->data_digest)
+ if (queue->data_digest &&
+ !test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags))
ret = skb_copy_and_hash_datagram_iter(skb, *offset,
&req->iter, recv_len, queue->rcv_hash);
else
@@ -1134,8 +1190,11 @@ static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue,
char *ddgst = (char *)&queue->recv_ddgst;
size_t recv_len = min_t(size_t, *len, queue->ddgst_remaining);
off_t off = NVME_TCP_DIGEST_LENGTH - queue->ddgst_remaining;
+ struct request *rq;
int ret;
+ if (test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags))
+ nvme_tcp_ddp_ddgst_update(queue, skb);
ret = skb_copy_bits(skb, *offset, &ddgst[off], recv_len);
if (unlikely(ret))
return ret;
@@ -1146,9 +1205,25 @@ static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue,
if (queue->ddgst_remaining)
return 0;
+ rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
+ pdu->command_id);
+
+ if (test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags)) {
+ /*
+ * If HW successfully offloaded the digest
+ * verification, we can skip it
+ */
+ if (nvme_tcp_ddp_ddgst_ok(queue))
+ goto out;
+ /*
+ * Otherwise we have to recalculate and verify the
+ * digest with the software-fallback
+ */
+ nvme_tcp_ddp_ddgst_recalc(queue->rcv_hash, rq,
+ &queue->exp_ddgst);
+ }
+
if (queue->recv_ddgst != queue->exp_ddgst) {
- struct request *rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
- pdu->command_id);
struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
req->status = cpu_to_le16(NVME_SC_DATA_XFER_ERROR);
@@ -1159,9 +1234,8 @@ static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue,
le32_to_cpu(queue->exp_ddgst));
}
+out:
if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
- struct request *rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
- pdu->command_id);
struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
nvme_tcp_end_request(rq, le16_to_cpu(req->status));
--
2.34.1
next prev parent reply other threads:[~2023-10-27 12:28 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-27 12:27 [PATCH v18 00/20] nvme-tcp receive offloads Aurelien Aptel
2023-10-27 12:27 ` [PATCH v18 01/20] net: Introduce direct data placement tcp offload Aurelien Aptel
2023-10-27 12:27 ` [PATCH v18 02/20] netlink: add new family to manage ULP_DDP enablement and stats Aurelien Aptel
2023-10-27 12:27 ` [PATCH v18 03/20] iov_iter: skip copy if src == dst for direct data placement Aurelien Aptel
2023-10-27 12:27 ` [PATCH v18 04/20] net/tls,core: export get_netdev_for_sock Aurelien Aptel
2023-10-27 12:27 ` [PATCH v18 05/20] nvme-tcp: Add DDP offload control path Aurelien Aptel
2023-10-27 12:27 ` [PATCH v18 06/20] nvme-tcp: Add DDP data-path Aurelien Aptel
2023-10-27 12:27 ` Aurelien Aptel [this message]
2023-10-27 12:27 ` [PATCH v18 08/20] nvme-tcp: Deal with netdevice DOWN events Aurelien Aptel
2023-10-27 12:27 ` [PATCH v18 09/20] Documentation: add ULP DDP offload documentation Aurelien Aptel
2023-10-27 12:27 ` [PATCH v18 10/20] net/mlx5e: Rename from tls to transport static params Aurelien Aptel
2023-10-27 12:27 ` [PATCH v18 11/20] net/mlx5e: Refactor ico sq polling to get budget Aurelien Aptel
2023-10-27 12:27 ` [PATCH v18 12/20] net/mlx5: Add NVMEoTCP caps, HW bits, 128B CQE and enumerations Aurelien Aptel
2023-10-27 12:27 ` [PATCH v18 13/20] net/mlx5e: NVMEoTCP, offload initialization Aurelien Aptel
2023-10-27 12:27 ` [PATCH v18 14/20] net/mlx5e: TCP flow steering for nvme-tcp acceleration Aurelien Aptel
2023-10-27 12:27 ` [PATCH v18 18/20] net/mlx5e: NVMEoTCP, async ddp invalidation Aurelien Aptel
2023-10-27 12:27 ` [PATCH v18 19/20] net/mlx5e: NVMEoTCP, data-path for DDP+DDGST offload Aurelien Aptel
2023-10-27 12:27 ` [PATCH v18 20/20] net/mlx5e: NVMEoTCP, statistics Aurelien Aptel
2023-10-30 6:15 ` [PATCH v18 00/20] nvme-tcp receive offloads Jakub Kicinski
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20231027122755.205334-8-aaptel@nvidia.com \
--to=aaptel@nvidia.com \
--cc=aurelien.aptel@gmail.com \
--cc=axboe@fb.com \
--cc=borisp@nvidia.com \
--cc=chaitanyak@nvidia.com \
--cc=davem@davemloft.net \
--cc=galshalom@nvidia.com \
--cc=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=kuba@kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=malin1024@gmail.com \
--cc=mgurtovoy@nvidia.com \
--cc=netdev@vger.kernel.org \
--cc=ogerlitz@nvidia.com \
--cc=sagi@grimberg.me \
--cc=smalin@nvidia.com \
--cc=yorayz@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).