From: Boris Pismenny <borisp@mellanox.com>
To: kuba@kernel.org, davem@davemloft.net, saeedm@nvidia.com,
hch@lst.de, sagi@grimberg.me, axboe@fb.com, kbusch@kernel.org,
viro@zeniv.linux.org.uk, edumazet@google.com
Cc: boris.pismenny@gmail.com, linux-nvme@lists.infradead.org,
netdev@vger.kernel.org, benishay@nvidia.com, ogerlitz@nvidia.com,
yorayz@nvidia.com, Ben Ben-Ishay <benishay@mellanox.com>,
Or Gerlitz <ogerlitz@mellanox.com>,
Yoray Zack <yorayz@mellanox.com>
Subject: [PATCH v1 net-next 03/15] net: Introduce crc offload for tcp ddp ulp
Date: Mon, 7 Dec 2020 23:06:37 +0200 [thread overview]
Message-ID: <20201207210649.19194-4-borisp@mellanox.com> (raw)
In-Reply-To: <20201207210649.19194-1-borisp@mellanox.com>
This commit introduces support for CRC offload to direct data placement
ULP on the receive side. Both DDP and CRC share a common API to
initialize the offload for a TCP socket. But otherwise, both can
be executed independently.
On the receive side, CRC offload requires a new SKB bit that
indicates that no CRC error was encountered while processing this packet.
If all packets of a ULP message have this bit set, then the CRC
verification for the message can be skipped, as hardware already checked
it.
The following patches will set and use this bit to perform NVME-TCP
CRC offload.
A subsequent series, will add NVMe-TCP transmit side CRC support.
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Ben Ben-Ishay <benishay@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Yoray Zack <yorayz@mellanox.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
---
include/linux/netdev_features.h | 2 ++
include/linux/skbuff.h | 5 +++++
net/Kconfig | 8 ++++++++
net/ethtool/common.c | 1 +
net/ipv4/tcp_input.c | 7 +++++++
net/ipv4/tcp_ipv4.c | 3 +++
net/ipv4/tcp_offload.c | 3 +++
7 files changed, 29 insertions(+)
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index fb35dcac03d2..dc79709586cd 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -85,6 +85,7 @@ enum {
NETIF_F_HW_MACSEC_BIT, /* Offload MACsec operations */
NETIF_F_HW_TCP_DDP_BIT, /* TCP direct data placement offload */
+ NETIF_F_HW_TCP_DDP_CRC_RX_BIT, /* TCP DDP CRC RX offload */
/*
* Add your fresh new feature above and remember to update
@@ -159,6 +160,7 @@ enum {
#define NETIF_F_GSO_FRAGLIST __NETIF_F(GSO_FRAGLIST)
#define NETIF_F_HW_MACSEC __NETIF_F(HW_MACSEC)
#define NETIF_F_HW_TCP_DDP __NETIF_F(HW_TCP_DDP)
+#define NETIF_F_HW_TCP_DDP_CRC_RX __NETIF_F(HW_TCP_DDP_CRC_RX)
/* Finds the next feature with the highest number of the range of start till 0.
*/
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 0a1239819fd2..c7daf93788e8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -683,6 +683,7 @@ typedef unsigned char *sk_buff_data_t;
* CHECKSUM_UNNECESSARY (max 3)
* @dst_pending_confirm: need to confirm neighbour
* @decrypted: Decrypted SKB
+ * @ddp_crc: NIC is responsible for PDU's CRC computation and verification
* @napi_id: id of the NAPI struct this skb came from
* @sender_cpu: (aka @napi_id) source CPU in XPS
* @secmark: security marking
@@ -858,6 +859,10 @@ struct sk_buff {
#ifdef CONFIG_TLS_DEVICE
__u8 decrypted:1;
#endif
+#ifdef CONFIG_TCP_DDP_CRC
+ __u8 ddp_crc:1;
+#endif
+
#ifdef CONFIG_NET_SCHED
__u16 tc_index; /* traffic control index */
diff --git a/net/Kconfig b/net/Kconfig
index 3876861cdc90..80ed9f038968 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -465,6 +465,14 @@ config TCP_DDP
NVMe-TCP/iSCSI, to request the NIC to place TCP payload data
of a command response directly into kernel pages.
+config TCP_DDP_CRC
+ bool "TCP direct data placement CRC offload"
+ default n
+ help
+ Direct Data Placement (DDP) CRC32C offload for TCP enables ULP, such as
+ NVMe-TCP/iSCSI, to request the NIC to calculate/verify the data digest
+ of commands as they go through the NIC. Thus avoiding the costly
+ per-byte overhead.
endif # if NET
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index a2ff7a4a6bbf..cc6858105449 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -69,6 +69,7 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = {
[NETIF_F_GRO_FRAGLIST_BIT] = "rx-gro-list",
[NETIF_F_HW_MACSEC_BIT] = "macsec-hw-offload",
[NETIF_F_HW_TCP_DDP_BIT] = "tcp-ddp-offload",
+ [NETIF_F_HW_TCP_DDP_CRC_RX_BIT] = "tcp-ddp-crc-rx-offload",
};
const char
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fb3a7750f623..daa0680b2bc1 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5128,6 +5128,9 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
#ifdef CONFIG_TLS_DEVICE
nskb->decrypted = skb->decrypted;
+#endif
+#ifdef CONFIG_TCP_DDP_CRC
+ nskb->ddp_crc = skb->ddp_crc;
#endif
TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start;
if (list)
@@ -5161,6 +5164,10 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
#ifdef CONFIG_TLS_DEVICE
if (skb->decrypted != nskb->decrypted)
goto end;
+#endif
+#ifdef CONFIG_TCP_DDP_CRC
+ if (skb->ddp_crc != nskb->ddp_crc)
+ goto end;
#endif
}
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index e4b31e70bd30..a12d016ce6c9 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1807,6 +1807,9 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) ||
#ifdef CONFIG_TLS_DEVICE
tail->decrypted != skb->decrypted ||
+#endif
+#ifdef CONFIG_TCP_DDP_CRC
+ tail->ddp_crc != skb->ddp_crc ||
#endif
thtail->doff != th->doff ||
memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th)))
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index e09147ac9a99..39f5f0bcf181 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -262,6 +262,9 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
#ifdef CONFIG_TLS_DEVICE
flush |= p->decrypted ^ skb->decrypted;
#endif
+#ifdef CONFIG_TCP_DDP_CRC
+ flush |= p->ddp_crc ^ skb->ddp_crc;
+#endif
if (flush || skb_gro_receive(p, skb)) {
mss = 1;
--
2.24.1
next prev parent reply other threads:[~2020-12-07 21:08 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-07 21:06 [PATCH v1 net-next 00/15] nvme-tcp receive offloads Boris Pismenny
2020-12-07 21:06 ` [PATCH v1 net-next 01/15] iov_iter: Skip copy in memcpy_to_page if src==dst Boris Pismenny
2020-12-08 0:39 ` David Ahern
2020-12-08 14:30 ` Boris Pismenny
2020-12-07 21:06 ` [PATCH v1 net-next 02/15] net: Introduce direct data placement tcp offload Boris Pismenny
2020-12-08 0:42 ` David Ahern
2020-12-08 14:36 ` Boris Pismenny
2020-12-09 0:38 ` David Ahern
2020-12-09 8:15 ` Boris Pismenny
2020-12-10 4:26 ` David Ahern
2020-12-11 2:01 ` Jakub Kicinski
2020-12-11 2:43 ` David Ahern
2020-12-11 18:45 ` Jakub Kicinski
2020-12-11 18:58 ` Eric Dumazet
2020-12-11 19:59 ` David Ahern
2020-12-11 23:05 ` Jonathan Lemon
2020-12-13 18:34 ` Boris Pismenny
2020-12-13 18:21 ` Boris Pismenny
2020-12-15 5:19 ` David Ahern
2020-12-17 19:06 ` Boris Pismenny
2020-12-18 0:44 ` David Ahern
2020-12-09 0:57 ` David Ahern
2020-12-09 1:11 ` David Ahern
2020-12-09 8:28 ` Boris Pismenny
2020-12-09 8:25 ` Boris Pismenny
2020-12-07 21:06 ` Boris Pismenny [this message]
2020-12-07 21:06 ` [PATCH v1 net-next 04/15] net/tls: expose get_netdev_for_sock Boris Pismenny
2020-12-09 1:06 ` David Ahern
2020-12-09 7:41 ` Boris Pismenny
2020-12-10 3:39 ` David Ahern
2020-12-11 18:43 ` Boris Pismenny
2020-12-07 21:06 ` [PATCH v1 net-next 05/15] nvme-tcp: Add DDP offload control path Boris Pismenny
2020-12-10 17:15 ` Shai Malin
2020-12-14 6:38 ` Boris Pismenny
2020-12-15 13:33 ` Shai Malin
2020-12-17 18:51 ` Boris Pismenny
2020-12-07 21:06 ` [PATCH v1 net-next 06/15] nvme-tcp: Add DDP data-path Boris Pismenny
2020-12-07 21:06 ` [PATCH v1 net-next 07/15] nvme-tcp : Recalculate crc in the end of the capsule Boris Pismenny
2020-12-15 14:07 ` Shai Malin
2020-12-07 21:06 ` [PATCH v1 net-next 08/15] nvme-tcp: Deal with netdevice DOWN events Boris Pismenny
2020-12-07 21:06 ` [PATCH v1 net-next 09/15] net/mlx5: Header file changes for nvme-tcp offload Boris Pismenny
2020-12-07 21:06 ` [PATCH v1 net-next 10/15] net/mlx5: Add 128B CQE for NVMEoTCP offload Boris Pismenny
2020-12-07 21:06 ` [PATCH v1 net-next 11/15] net/mlx5e: TCP flow steering for nvme-tcp Boris Pismenny
2020-12-07 21:06 ` [PATCH v1 net-next 12/15] net/mlx5e: NVMEoTCP DDP offload control path Boris Pismenny
2020-12-07 21:06 ` [PATCH v1 net-next 13/15] net/mlx5e: NVMEoTCP, data-path for DDP offload Boris Pismenny
2020-12-18 0:57 ` David Ahern
2020-12-07 21:06 ` [PATCH v1 net-next 14/15] net/mlx5e: NVMEoTCP statistics Boris Pismenny
2020-12-07 21:06 ` [PATCH v1 net-next 15/15] net/mlx5e: NVMEoTCP workaround CRC after resync Boris Pismenny
2021-01-14 1:27 ` [PATCH v1 net-next 00/15] nvme-tcp receive offloads Sagi Grimberg
2021-01-14 4:47 ` David Ahern
2021-01-14 19:21 ` Boris Pismenny
2021-01-14 19:17 ` Boris Pismenny
2021-01-14 21:07 ` Sagi Grimberg
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=20201207210649.19194-4-borisp@mellanox.com \
--to=borisp@mellanox.com \
--cc=axboe@fb.com \
--cc=benishay@mellanox.com \
--cc=benishay@nvidia.com \
--cc=boris.pismenny@gmail.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=netdev@vger.kernel.org \
--cc=ogerlitz@mellanox.com \
--cc=ogerlitz@nvidia.com \
--cc=saeedm@nvidia.com \
--cc=sagi@grimberg.me \
--cc=viro@zeniv.linux.org.uk \
--cc=yorayz@mellanox.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).