From: Aurelien Aptel <aaptel@nvidia.com>
To: netdev@vger.kernel.org, davem@davemloft.net, kuba@kernel.org,
edumazet@google.com, pabeni@redhat.com, saeedm@nvidia.com,
tariqt@nvidia.com, linux-nvme@lists.infradead.org,
sagi@grimberg.me, hch@lst.de, kbusch@kernel.org, axboe@fb.com,
chaitanyak@nvidia.com
Cc: smalin@nvidia.com, aaptel@nvidia.com, ogerlitz@nvidia.com,
yorayz@nvidia.com, borisp@nvidia.com, aurelien.aptel@gmail.com,
malin1024@gmail.com
Subject: [PATCH v6 07/23] nvme-tcp: RX DDGST offload
Date: Thu, 20 Oct 2022 13:18:22 +0300 [thread overview]
Message-ID: <20221020101838.2712846-8-aaptel@nvidia.com> (raw)
In-Reply-To: <20221020101838.2712846-1-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 | 113 ++++++++++++++++++++++++++++++++++++----
1 file changed, 104 insertions(+), 9 deletions(-)
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 0fe4ff9e098b..76aed532186c 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -115,6 +115,7 @@ 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 {
@@ -142,6 +143,9 @@ struct nvme_tcp_queue {
size_t ddgst_remaining;
unsigned int nr_cqe;
+#ifdef CONFIG_ULP_DDP
+ bool ddp_ddgst_valid;
+
/*
* HW can request a tcp seq num to continue
* offload in case of resync.
@@ -150,6 +154,7 @@ struct nvme_tcp_queue {
* is pending (ULP_DDP_RESYNC_PENDING).
*/
atomic64_t resync_req;
+#endif
/* send state */
struct nvme_tcp_request *request;
@@ -308,6 +313,18 @@ static bool nvme_tcp_ddp_query_limits(struct net_device *netdev,
return true;
}
+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 = IS_ULP_CRC(skb);
+}
+
static int nvme_tcp_req_map_sg(struct nvme_tcp_request *req, struct request *rq)
{
int ret;
@@ -322,6 +339,38 @@ static int nvme_tcp_req_map_sg(struct nvme_tcp_request *req, struct request *rq)
return 0;
}
+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);
+
+ if (!req->offloaded) {
+ /* if we have DDGST_RX offload without DDP the request
+ * wasn't mapped, so we need to map it here
+ */
+ if (nvme_tcp_req_map_sg(req, rq))
+ return;
+ }
+
+ req->ddp.sg_table.sgl = req->ddp.first_sgl;
+ ahash_request_set_crypt(hash, req->ddp.sg_table.sgl, (u8 *)ddgst,
+ req->data_len);
+ crypto_ahash_digest(hash);
+
+ if (!req->offloaded) {
+ /* without DDP, ddp_teardown() won't be called, so
+ * free the table here
+ */
+ sg_free_table_chained(&req->ddp.sg_table, SG_CHUNK_SIZE);
+ }
+}
+
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 = {
@@ -389,7 +438,8 @@ static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
if (!nvme_tcp_ddp_query_limits(netdev, &limits))
return 0;
- if (!(limits.lmt.offload_capabilities & ULP_DDP_C_NVME_TCP))
+ if (!(limits.lmt.offload_capabilities &
+ (ULP_DDP_C_NVME_TCP|ULP_DDP_C_NVME_TCP_DDGST_RX)))
return 0;
config.cfg.type = ULP_DDP_NVME;
@@ -417,7 +467,10 @@ static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
}
inet_csk(queue->sock->sk)->icsk_ulp_ddp_ops = &nvme_tcp_ddp_ulp_ops;
- set_bit(NVME_TCP_Q_OFF_DDP, &queue->flags);
+ if (limits.lmt.offload_capabilities & ULP_DDP_C_NVME_TCP)
+ set_bit(NVME_TCP_Q_OFF_DDP, &queue->flags);
+ if (limits.lmt.offload_capabilities & ULP_DDP_C_NVME_TCP_DDGST_RX)
+ set_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags);
return 0;
}
@@ -431,6 +484,7 @@ 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);
netdev->ulp_ddp_ops->ulp_ddp_sk_del(netdev, queue->sock->sk);
@@ -518,6 +572,20 @@ static bool nvme_tcp_resync_request(struct sock *sk, u32 seq, u32 flags)
#else
+static inline bool nvme_tcp_ddp_ddgst_ok(struct nvme_tcp_queue *queue)
+{
+ return true;
+}
+
+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)
+{}
+
static int nvme_tcp_setup_ddp(struct nvme_tcp_queue *queue, u16 command_id,
struct request *rq)
{
@@ -801,6 +869,9 @@ 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)
@@ -1003,7 +1074,8 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
size_t rcv_len = min_t(size_t, *len, queue->pdu_remaining);
int ret;
- if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags))
+ if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags) ||
+ test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags))
nvme_tcp_resync_response(queue, skb, *offset);
ret = skb_copy_bits(skb, *offset,
@@ -1066,6 +1138,10 @@ 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;
@@ -1094,7 +1170,8 @@ 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
@@ -1136,8 +1213,11 @@ 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;
@@ -1148,9 +1228,24 @@ 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);
@@ -1161,9 +1256,8 @@ 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));
@@ -1962,7 +2056,8 @@ static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue)
kernel_sock_shutdown(queue->sock, SHUT_RDWR);
nvme_tcp_restore_sock_calls(queue);
cancel_work_sync(&queue->io_work);
- if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags))
+ if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags) ||
+ test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags))
nvme_tcp_unoffload_socket(queue);
}
--
2.31.1
next prev parent reply other threads:[~2022-10-20 10:44 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-20 10:18 [PATCH v6 00/23] nvme-tcp receive offloads Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 01/23] net: Introduce direct data placement tcp offload Aurelien Aptel
2022-10-21 5:05 ` Jakub Kicinski
2022-10-21 11:19 ` Aurelien Aptel
2022-10-24 11:22 ` Leon Romanovsky
2022-10-24 13:09 ` Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 02/23] iov_iter: DDP copy to iter/pages Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 03/23] net/tls: export get_netdev_for_sock Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 04/23] Revert "nvme-tcp: remove the unused queue_size member in nvme_tcp_queue" Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 05/23] nvme-tcp: Add DDP offload control path Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 06/23] nvme-tcp: Add DDP data-path Aurelien Aptel
2022-10-20 10:18 ` Aurelien Aptel [this message]
2022-10-20 10:18 ` [PATCH v6 08/23] nvme-tcp: Deal with netdevice DOWN events Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 09/23] nvme-tcp: Add ulp_offload modparam to control enablement of ULP offload Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 10/23] Documentation: add ULP DDP offload documentation Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 11/23] net/mlx5e: Rename from tls to transport static params Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 12/23] net/mlx5e: Refactor ico sq polling to get budget Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 13/23] net/mlx5e: Have mdev pointer directly on the icosq structure Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 14/23] net/mlx5e: Refactor doorbell function to allow avoiding a completion Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 15/23] net/mlx5: Add NVMEoTCP caps, HW bits, 128B CQE and enumerations Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 16/23] net/mlx5e: NVMEoTCP, offload initialization Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 17/23] net/mlx5e: TCP flow steering for nvme-tcp acceleration Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 18/23] net/mlx5e: NVMEoTCP, use KLM UMRs for buffer registration Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 19/23] net/mlx5e: NVMEoTCP, queue init/teardown Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 20/23] net/mlx5e: NVMEoTCP, ddp setup and resync Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 21/23] net/mlx5e: NVMEoTCP, async ddp invalidation Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 22/23] net/mlx5e: NVMEoTCP, data-path for DDP+DDGST offload Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 23/23] net/mlx5e: NVMEoTCP, statistics Aurelien Aptel
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=20221020101838.2712846-8-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=edumazet@google.com \
--cc=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=kuba@kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=malin1024@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=ogerlitz@nvidia.com \
--cc=pabeni@redhat.com \
--cc=saeedm@nvidia.com \
--cc=sagi@grimberg.me \
--cc=smalin@nvidia.com \
--cc=tariqt@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