Netdev Archive on lore.kernel.org help / color / mirror / Atom feed
From: Boris Pismenny <borisp@nvidia.com> To: <dsahern@gmail.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>, <smalin@marvell.com> Cc: <boris.pismenny@gmail.com>, <linux-nvme@lists.infradead.org>, <netdev@vger.kernel.org>, <benishay@nvidia.com>, <ogerlitz@nvidia.com>, <yorayz@nvidia.com> Subject: [PATCH v5 net-next 22/36] net: Add ulp_ddp_pdu_info struct Date: Thu, 22 Jul 2021 14:03:11 +0300 [thread overview] Message-ID: <20210722110325.371-23-borisp@nvidia.com> (raw) In-Reply-To: <20210722110325.371-1-borisp@nvidia.com> From: Yoray Zack <yorayz@nvidia.com> This struct is mapping between pdu's pages to TCP sequence number. The use case for this mapping is in tx offload, when the NIC needs to send a retransmitted packet. The NIC, in this case, might need the complete pdu, which is sent before (i.e for computing the CRC for this pdu). Using this mapping, the SW can send the NIC enough context to offload the packet. Signed-off-by: Yoray Zack <yorayz@nvidia.com> --- include/net/ulp_ddp.h | 55 +++++++++++++- net/core/Makefile | 1 + net/core/ulp_ddp.c | 166 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 219 insertions(+), 3 deletions(-) create mode 100644 net/core/ulp_ddp.c diff --git a/include/net/ulp_ddp.h b/include/net/ulp_ddp.h index 1a0b464ff40b..8f48fc121c3a 100644 --- a/include/net/ulp_ddp.h +++ b/include/net/ulp_ddp.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-3.0 * * ulp_ddp.h * Author: Boris Pismenny <borisp@mellanox.com> @@ -10,6 +10,7 @@ #include <linux/netdevice.h> #include <net/inet_connection_sock.h> #include <net/sock.h> +#include <net/tcp.h> /* limits returned by the offload driver, zero means don't care */ struct ulp_ddp_limits { @@ -67,6 +68,26 @@ struct ulp_ddp_io { struct scatterlist first_sgl[SG_CHUNK_SIZE]; }; +/** + * struct ulp_ddp_pdu_info - pdu info for tcp ddp crc Tx offload. + * + * @end_seq: tcp seq of the last byte in the pdu. + * @start_seq: tcp seq of the first byte in the pdu. + * @data_len: pdu data size (in bytes). + * @hdr_len: the size (in bytes) of the pdu header. + * @hdr: pdu header. + * @req: the ulp request for the original pdu. + */ +struct ulp_ddp_pdu_info { + struct list_head list; + u32 end_seq; + u32 start_seq; + u32 data_len; + u32 hdr_len; + void *hdr; + struct request *req; +}; + /* struct ulp_ddp_dev_ops - operations used by an upper layer protocol to configure ddp offload * * @ulp_ddp_limits: limit the number of scatter gather entries per IO. @@ -113,10 +134,25 @@ struct ulp_ddp_ulp_ops { /** * struct ulp_ddp_ctx - Generic ulp ddp context: device driver per queue contexts must * use this as the first member. + * + * @netdev: the coresponding netdev for this tcp ddp. + * @ddgst_len: data digest len in bytes. + * @expected_seq: indicates for next tcp seq. + * @open_info: the current pdu_info. + * @pdu_hint: hint for ulp_ddp_get_pdu_info. + * @info_list: list of the mapped pdu_infos. + * @info_lock: lock for info_list. */ struct ulp_ddp_ctx { - enum ulp_ddp_type type; - unsigned char buf[]; + enum ulp_ddp_type type; + struct net_device *netdev; + int ddgst_len; + u32 expected_seq; + struct ulp_ddp_pdu_info *open_info; + struct ulp_ddp_pdu_info *pdu_hint; + struct list_head info_list; + spinlock_t info_lock; + unsigned char buf[]; }; static inline struct ulp_ddp_ctx *ulp_ddp_get_ctx(const struct sock *sk) @@ -133,4 +169,17 @@ static inline void ulp_ddp_set_ctx(struct sock *sk, void *ctx) rcu_assign_pointer(icsk->icsk_ulp_ddp_data, ctx); } +static inline void ulp_ddp_destroy_info(struct ulp_ddp_pdu_info *info) +{ + kfree(info); +} + +void ulp_ddp_ack_handle(struct sock *sk, u32 acked_seq); +int ulp_ddp_init_tx_offload(struct sock *sk); +void ulp_ddp_release_tx_offload(struct sock *sk); +int ulp_ddp_map_pdu_info(struct sock *sk, u32 start_seq, void *hdr, + u32 hdr_len, u32 data_len, struct request *req); +void ulp_ddp_close_pdu_info(struct sock *sk); +bool ulp_ddp_need_map(struct sock *sk); +struct ulp_ddp_pdu_info *ulp_ddp_get_pdu_info(struct sock *sk, u32 seq); #endif //_ULP_DDP_H diff --git a/net/core/Makefile b/net/core/Makefile index f7f16650fe9e..b7c1618944df 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -14,6 +14,7 @@ obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ fib_notifier.o xdp.o flow_offload.o obj-y += net-sysfs.o +obj-$(CONFIG_ULP_DDP) += ulp_ddp.o obj-$(CONFIG_PAGE_POOL) += page_pool.o obj-$(CONFIG_PROC_FS) += net-procfs.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o diff --git a/net/core/ulp_ddp.c b/net/core/ulp_ddp.c new file mode 100644 index 000000000000..06ed4ad59e88 --- /dev/null +++ b/net/core/ulp_ddp.c @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-3.0 + * + * ulp_ddp.c + * Author: Yoray Zack <yorayz@mellanox.com> + * Copyright (C) 2020 Mellanox Technologies. + */ +#include <net/ulp_ddp.h> + +void ulp_ddp_ack_handle(struct sock *sk, u32 acked_seq) +{ + struct ulp_ddp_ctx *ctx = ulp_ddp_get_ctx(sk); + struct ulp_ddp_pdu_info *info, *temp; + unsigned long flags; + + spin_lock_irqsave(&ctx->info_lock, flags); + info = ctx->pdu_hint; + if (info && !before(acked_seq, info->end_seq)) + ctx->pdu_hint = NULL; + + list_for_each_entry_safe(info, temp, &ctx->info_list, list) { + if (before(acked_seq, info->end_seq - 1)) + break; + + list_del(&info->list); + ulp_ddp_destroy_info(info); + } + + spin_unlock_irqrestore(&ctx->info_lock, flags); +} + +static void ulp_ddp_delete_all_info(struct sock *sk) +{ + struct ulp_ddp_ctx *ctx = ulp_ddp_get_ctx(sk); + struct ulp_ddp_pdu_info *info, *temp; + unsigned long flags; + + spin_lock_irqsave(&ctx->info_lock, flags); + list_for_each_entry_safe(info, temp, &ctx->info_list, list) { + list_del(&info->list); + ulp_ddp_destroy_info(info); + } + + spin_unlock_irqrestore(&ctx->info_lock, flags); + ctx->pdu_hint = NULL; +} + +int ulp_ddp_init_tx_offload(struct sock *sk) +{ + struct ulp_ddp_ctx *ctx = ulp_ddp_get_ctx(sk); + struct ulp_ddp_pdu_info *start_marker_info; + unsigned long flags; + + start_marker_info = kzalloc(sizeof(*start_marker_info), GFP_KERNEL); + if (!start_marker_info) + return -ENOMEM; + + start_marker_info->end_seq = tcp_sk(sk)->write_seq; + start_marker_info->start_seq = tcp_sk(sk)->write_seq; + spin_lock_init(&ctx->info_lock); + INIT_LIST_HEAD(&ctx->info_list); + spin_lock_irqsave(&ctx->info_lock, flags); + list_add_tail(&start_marker_info->list, &ctx->info_list); + spin_unlock_irqrestore(&ctx->info_lock, flags); + ctx->pdu_hint = NULL; + ctx->open_info = NULL; + clean_acked_data_enable(inet_csk(sk), + &ulp_ddp_ack_handle); + return 0; +} EXPORT_SYMBOL(ulp_ddp_init_tx_offload); + +void ulp_ddp_release_tx_offload(struct sock *sk) +{ + clean_acked_data_disable(inet_csk(sk)); + ulp_ddp_delete_all_info(sk); +} EXPORT_SYMBOL(ulp_ddp_release_tx_offload); + +int ulp_ddp_map_pdu_info(struct sock *sk, u32 start_seq, void *hdr, + u32 hdr_len, u32 data_len, struct request *req) +{ + struct ulp_ddp_ctx *ctx = ulp_ddp_get_ctx(sk); + struct ulp_ddp_pdu_info *pdu_info; + u32 ddgst_len; + + pdu_info = kmalloc(sizeof(*pdu_info), GFP_KERNEL); + if (!pdu_info) + return -ENOMEM; + + ddgst_len = data_len ? ctx->ddgst_len : 0; + + pdu_info->end_seq = start_seq + hdr_len + data_len + ddgst_len; + pdu_info->start_seq = start_seq; + pdu_info->data_len = data_len; + pdu_info->hdr_len = hdr_len; + pdu_info->hdr = hdr; + pdu_info->req = req; + pdu_info->ddgst = 0; + + ctx->open_info = pdu_info; + return 0; +} EXPORT_SYMBOL(ulp_ddp_map_pdu_info); + +void ulp_ddp_close_pdu_info(struct sock *sk) +{ + struct ulp_ddp_ctx *ctx = ulp_ddp_get_ctx(sk); + struct ulp_ddp_pdu_info *pdu_info = ctx->open_info; + unsigned long flags; + + if (!pdu_info) + return; + + pdu_info->end_seq = tcp_sk(sk)->write_seq; + + spin_lock_irqsave(&ctx->info_lock, flags); + list_add_tail_rcu(&pdu_info->list, &ctx->info_list); + spin_unlock_irqrestore(&ctx->info_lock, flags); + + ctx->open_info = NULL; +} EXPORT_SYMBOL(ulp_ddp_close_pdu_info); + +bool ulp_ddp_need_map(struct sock *sk) +{ + struct ulp_ddp_ctx *ctx = ulp_ddp_get_ctx(sk); + + return !ctx->open_info; +} EXPORT_SYMBOL(ulp_ddp_need_map); + +struct ulp_ddp_pdu_info *ulp_ddp_get_pdu_info(struct sock *sk, u32 seq) +{ + struct ulp_ddp_ctx *ctx = ulp_ddp_get_ctx(sk); + struct ulp_ddp_pdu_info *info; + u32 open_start = 0; + + if (!ctx) + return NULL; + + if (ctx->open_info) { + open_start = ctx->open_info->start_seq; + if (before(open_start, seq) || seq == open_start) + return ctx->open_info; + } + + info = ctx->pdu_hint; + if (!info || before(seq, info->start_seq)) + info = list_first_entry_or_null(&ctx->info_list, + struct ulp_ddp_pdu_info, list); + + if (!info) + return NULL; + + rcu_read_lock(); + list_for_each_entry_from_rcu(info, &ctx->info_list, list) { + if (!info) + goto out; + + if (between(seq, info->start_seq, info->end_seq - 1)) { + ctx->pdu_hint = info; + goto out; + } + } + + info = NULL; +out: + rcu_read_unlock(); + return info; +} EXPORT_SYMBOL(ulp_ddp_get_pdu_info); + -- 2.24.1
next prev parent reply other threads:[~2021-07-22 11:06 UTC|newest] Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-07-22 11:02 [PATCH v5 net-next 00/36] nvme-tcp receive and tarnsmit offloads Boris Pismenny 2021-07-22 11:02 ` [PATCH v5 net-next 01/36] net: Introduce direct data placement tcp offload Boris Pismenny 2021-07-22 11:26 ` Eric Dumazet 2021-07-22 12:18 ` Boris Pismenny 2021-07-22 13:10 ` Eric Dumazet 2021-07-22 13:33 ` Boris Pismenny 2021-07-22 13:39 ` Eric Dumazet 2021-07-22 14:02 ` Boris Pismenny 2021-07-22 11:02 ` [PATCH v5 net-next 02/36] iov_iter: DDP copy to iter/pages Boris Pismenny 2021-07-22 13:31 ` Christoph Hellwig 2021-07-22 20:23 ` Boris Pismenny 2021-07-23 5:03 ` Christoph Hellwig 2021-07-23 5:21 ` Al Viro 2021-08-04 14:13 ` Or Gerlitz 2021-08-10 13:29 ` Or Gerlitz 2021-07-22 20:55 ` Al Viro 2021-07-22 11:02 ` [PATCH v5 net-next 03/36] net: skb copy(+hash) iterators for DDP offloads Boris Pismenny 2021-07-22 11:02 ` [PATCH v5 net-next 04/36] net/tls: expose get_netdev_for_sock Boris Pismenny 2021-07-23 6:06 ` Christoph Hellwig 2021-08-04 13:26 ` Or Gerlitz [not found] ` <20210804072918.17ba9cff@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com> 2021-08-04 15:07 ` Or Gerlitz 2021-08-10 13:25 ` Or Gerlitz 2021-07-22 11:02 ` [PATCH v5 net-next 05/36] nvme-tcp: Add DDP offload control path Boris Pismenny 2021-07-22 11:02 ` [PATCH v5 net-next 06/36] nvme-tcp: Add DDP data-path Boris Pismenny 2021-07-22 11:02 ` [PATCH v5 net-next 07/36] nvme-tcp: RX DDGST offload Boris Pismenny 2021-07-22 11:02 ` [PATCH v5 net-next 08/36] nvme-tcp: Deal with netdevice DOWN events Boris Pismenny 2021-07-22 11:02 ` [PATCH v5 net-next 09/36] net/mlx5: Header file changes for nvme-tcp offload Boris Pismenny 2021-07-22 11:02 ` [PATCH v5 net-next 10/36] net/mlx5: Add 128B CQE for NVMEoTCP offload Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 11/36] net/mlx5e: TCP flow steering for nvme-tcp Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 12/36] net/mlx5e: NVMEoTCP offload initialization Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 13/36] net/mlx5e: KLM UMR helper macros Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 14/36] net/mlx5e: NVMEoTCP use KLM UMRs Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 15/36] net/mlx5e: NVMEoTCP queue init/teardown Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 16/36] net/mlx5e: NVMEoTCP async ddp invalidation Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 17/36] net/mlx5e: NVMEoTCP ddp setup and resync Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 18/36] net/mlx5e: NVMEoTCP, data-path for DDP+DDGST offload Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 19/36] net/mlx5e: NVMEoTCP statistics Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 20/36] Documentation: add ULP DDP offload documentation Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 21/36] net: drop ULP DDP HW offload feature if no CSUM offload feature Boris Pismenny 2021-07-22 11:03 ` Boris Pismenny [this message] 2021-07-23 19:42 ` [PATCH v5 net-next 22/36] net: Add ulp_ddp_pdu_info struct Sagi Grimberg 2021-07-22 11:03 ` [PATCH v5 net-next 23/36] net: Add to ulp_ddp support for fallback flow Boris Pismenny 2021-07-23 6:09 ` Christoph Hellwig 2021-07-22 11:03 ` [PATCH v5 net-next 24/36] net: Add MSG_DDP_CRC flag Boris Pismenny 2021-07-22 14:23 ` Eric Dumazet 2021-07-22 11:03 ` [PATCH v5 net-next 25/36] nvme-tcp: TX DDGST offload Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 26/36] nvme-tcp: Mapping between Tx NVMEoTCP pdu and TCP sequence Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 27/36] mlx5e: make preparation in TLS code for NVMEoTCP CRC Tx offload Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 28/36] mlx5: Add sq state test bit for nvmeotcp Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 29/36] mlx5: Add support to NETIF_F_HW_TCP_DDP_CRC_TX feature Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 30/36] net/mlx5e: NVMEoTCP DDGST TX offload TIS Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 31/36] net/mlx5e: NVMEoTCP DDGST Tx offload queue init/teardown Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 32/36] net/mlx5e: NVMEoTCP DDGST TX BSF and PSV Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 33/36] net/mlx5e: NVMEoTCP DDGST TX Data path Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 34/36] net/mlx5e: NVMEoTCP DDGST TX handle OOO packets Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 35/36] net/mlx5e: NVMEoTCP DDGST TX offload optimization Boris Pismenny 2021-07-22 11:03 ` [PATCH v5 net-next 36/36] net/mlx5e: NVMEoTCP DDGST TX statistics Boris Pismenny 2021-07-23 5:56 ` [PATCH v5 net-next 00/36] nvme-tcp receive and tarnsmit offloads Christoph Hellwig 2021-07-23 19:58 ` Sagi Grimberg 2021-08-04 13:51 ` Or Gerlitz 2021-08-06 19:46 ` Sagi Grimberg 2021-08-10 13:37 ` Or Gerlitz
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=20210722110325.371-23-borisp@nvidia.com \ --to=borisp@nvidia.com \ --cc=axboe@fb.com \ --cc=benishay@nvidia.com \ --cc=boris.pismenny@gmail.com \ --cc=davem@davemloft.net \ --cc=dsahern@gmail.com \ --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@nvidia.com \ --cc=saeedm@nvidia.com \ --cc=sagi@grimberg.me \ --cc=smalin@marvell.com \ --cc=viro@zeniv.linux.org.uk \ --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: linkBe 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).