From: David Ahern <dsahern@gmail.com>
To: Boris Pismenny <borisp@mellanox.com>,
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: Re: [PATCH v1 net-next 02/15] net: Introduce direct data placement tcp offload
Date: Tue, 8 Dec 2020 17:57:46 -0700 [thread overview]
Message-ID: <824e3bea-60d2-5a4d-e8ce-770d70f0ba37@gmail.com> (raw)
In-Reply-To: <20201207210649.19194-3-borisp@mellanox.com>
On 12/7/20 2:06 PM, Boris Pismenny wrote:
> diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
> index 934de56644e7..fb35dcac03d2 100644
> --- a/include/linux/netdev_features.h
> +++ b/include/linux/netdev_features.h
> @@ -84,6 +84,7 @@ enum {
> NETIF_F_GRO_FRAGLIST_BIT, /* Fraglist GRO */
>
> NETIF_F_HW_MACSEC_BIT, /* Offload MACsec operations */
> + NETIF_F_HW_TCP_DDP_BIT, /* TCP direct data placement offload */
>
> /*
> * Add your fresh new feature above and remember to update
> @@ -157,6 +158,7 @@ enum {
> #define NETIF_F_GRO_FRAGLIST __NETIF_F(GRO_FRAGLIST)
> #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)
All of the DDP naming seems wrong to me. I realize the specific use case
is targeted payloads of a ULP, but it is still S/W handing H/W specific
buffers for a payload of a flow.
>
> /* Finds the next feature with the highest number of the range of start till 0.
> */
> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
> index a07c8e431f45..755766976408 100644
> --- a/include/linux/netdevice.h
> +++ b/include/linux/netdevice.h
> @@ -934,6 +934,7 @@ struct dev_ifalias {
>
> struct devlink;
> struct tlsdev_ops;
> +struct tcp_ddp_dev_ops;
>
> struct netdev_name_node {
> struct hlist_node hlist;
> @@ -1930,6 +1931,10 @@ struct net_device {
> const struct tlsdev_ops *tlsdev_ops;
> #endif
>
> +#ifdef CONFIG_TCP_DDP
> + const struct tcp_ddp_dev_ops *tcp_ddp_ops;
> +#endif
> +
> const struct header_ops *header_ops;
>
> unsigned int flags;
> diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
> index 7338b3865a2a..a08b85b53aa8 100644
> --- a/include/net/inet_connection_sock.h
> +++ b/include/net/inet_connection_sock.h
> @@ -66,6 +66,8 @@ struct inet_connection_sock_af_ops {
> * @icsk_ulp_ops Pluggable ULP control hook
> * @icsk_ulp_data ULP private data
> * @icsk_clean_acked Clean acked data hook
> + * @icsk_ulp_ddp_ops Pluggable ULP direct data placement control hook
> + * @icsk_ulp_ddp_data ULP direct data placement private data
Neither of these socket layer intrusions are needed. All references but
1 -- the skbuff check -- are in the mlx5 driver. Any skb check that is
needed can be handled with a different setting.
> * @icsk_listen_portaddr_node hash to the portaddr listener hashtable
> * @icsk_ca_state: Congestion control state
> * @icsk_retransmits: Number of unrecovered [RTO] timeouts
> @@ -94,6 +96,8 @@ struct inet_connection_sock {
> const struct tcp_ulp_ops *icsk_ulp_ops;
> void __rcu *icsk_ulp_data;
> void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq);
> + const struct tcp_ddp_ulp_ops *icsk_ulp_ddp_ops;
> + void __rcu *icsk_ulp_ddp_data;
> struct hlist_node icsk_listen_portaddr_node;
> unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
> __u8 icsk_ca_state:5,
> diff --git a/include/net/tcp_ddp.h b/include/net/tcp_ddp.h
> new file mode 100644
> index 000000000000..df3264be4600
> --- /dev/null
> +++ b/include/net/tcp_ddp.h
> @@ -0,0 +1,129 @@
> +/* SPDX-License-Identifier: GPL-2.0
> + *
> + * tcp_ddp.h
> + * Author: Boris Pismenny <borisp@mellanox.com>
> + * Copyright (C) 2020 Mellanox Technologies.
> + */
> +#ifndef _TCP_DDP_H
> +#define _TCP_DDP_H
> +
> +#include <linux/netdevice.h>
> +#include <net/inet_connection_sock.h>
> +#include <net/sock.h>
> +
> +/* limits returned by the offload driver, zero means don't care */
> +struct tcp_ddp_limits {
> + int max_ddp_sgl_len;
> +};
> +
> +enum tcp_ddp_type {
> + TCP_DDP_NVME = 1,
> +};
> +
> +/**
> + * struct tcp_ddp_config - Generic tcp ddp configuration: tcp ddp IO queue
> + * config implementations must use this as the first member.
> + * Add new instances of tcp_ddp_config below (nvme-tcp, etc.).
> + */
> +struct tcp_ddp_config {
> + enum tcp_ddp_type type;
> + unsigned char buf[];
you have this variable length buf, but it is not used (as far as I can
tell). But then ...
> +};
> +
> +/**
> + * struct nvme_tcp_ddp_config - nvme tcp ddp configuration for an IO queue
> + *
> + * @pfv: pdu version (e.g., NVME_TCP_PFV_1_0)
> + * @cpda: controller pdu data alignmend (dwords, 0's based)
> + * @dgst: digest types enabled.
> + * The netdev will offload crc if ddp_crc is supported.
> + * @queue_size: number of nvme-tcp IO queue elements
> + * @queue_id: queue identifier
> + * @cpu_io: cpu core running the IO thread for this queue
> + */
> +struct nvme_tcp_ddp_config {
> + struct tcp_ddp_config cfg;
... how would you use it within another struct like this?
> +
> + u16 pfv;
> + u8 cpda;
> + u8 dgst;
> + int queue_size;
> + int queue_id;
> + int io_cpu;
> +};
> +
> +/**
> + * struct tcp_ddp_io - tcp ddp configuration for an IO request.
> + *
> + * @command_id: identifier on the wire associated with these buffers
> + * @nents: number of entries in the sg_table
> + * @sg_table: describing the buffers for this IO request
> + * @first_sgl: first SGL in sg_table
> + */
> +struct tcp_ddp_io {
> + u32 command_id;
> + int nents;
> + struct sg_table sg_table;
> + struct scatterlist first_sgl[SG_CHUNK_SIZE];
> +};
> +
> +/* struct tcp_ddp_dev_ops - operations used by an upper layer protocol to configure ddp offload
> + *
> + * @tcp_ddp_limits: limit the number of scatter gather entries per IO.
> + * the device driver can use this to limit the resources allocated per queue.
> + * @tcp_ddp_sk_add: add offload for the queue represennted by the socket+config pair.
> + * this function is used to configure either copy, crc or both offloads.
> + * @tcp_ddp_sk_del: remove offload from the socket, and release any device related resources.
> + * @tcp_ddp_setup: request copy offload for buffers associated with a command_id in tcp_ddp_io.
> + * @tcp_ddp_teardown: release offload resources association between buffers and command_id in
> + * tcp_ddp_io.
> + * @tcp_ddp_resync: respond to the driver's resync_request. Called only if resync is successful.
> + */
> +struct tcp_ddp_dev_ops {
> + int (*tcp_ddp_limits)(struct net_device *netdev,
> + struct tcp_ddp_limits *limits);
> + int (*tcp_ddp_sk_add)(struct net_device *netdev,
> + struct sock *sk,
> + struct tcp_ddp_config *config);
> + void (*tcp_ddp_sk_del)(struct net_device *netdev,
> + struct sock *sk);
> + int (*tcp_ddp_setup)(struct net_device *netdev,
> + struct sock *sk,
> + struct tcp_ddp_io *io);
> + int (*tcp_ddp_teardown)(struct net_device *netdev,
> + struct sock *sk,
> + struct tcp_ddp_io *io,
> + void *ddp_ctx);
> + void (*tcp_ddp_resync)(struct net_device *netdev,
> + struct sock *sk, u32 seq);
> +};
> +
> +#define TCP_DDP_RESYNC_REQ (1 << 0)
> +
> +/**
> + * struct tcp_ddp_ulp_ops - Interface to register uppper layer Direct Data Placement (DDP) TCP offload
> + */
> +struct tcp_ddp_ulp_ops {
> + /* NIC requests ulp to indicate if @seq is the start of a message */
> + bool (*resync_request)(struct sock *sk, u32 seq, u32 flags);
> + /* NIC driver informs the ulp that ddp teardown is done - used for async completions*/
> + void (*ddp_teardown_done)(void *ddp_ctx);
> +};
> +
> +/**
> + * struct tcp_ddp_ctx - Generic tcp ddp context: device driver per queue contexts must
> + * use this as the first member.
> + */
> +struct tcp_ddp_ctx {
> + enum tcp_ddp_type type;
> + unsigned char buf[];
similar to my comment above, I did not see any uses of the buf element.
next prev parent reply other threads:[~2020-12-09 0:58 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 [this message]
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 ` [PATCH v1 net-next 03/15] net: Introduce crc offload for tcp ddp ulp Boris Pismenny
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=824e3bea-60d2-5a4d-e8ce-770d70f0ba37@gmail.com \
--to=dsahern@gmail.com \
--cc=axboe@fb.com \
--cc=benishay@mellanox.com \
--cc=benishay@nvidia.com \
--cc=boris.pismenny@gmail.com \
--cc=borisp@mellanox.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).