From patchwork Tue Feb 28 16:38:08 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "D. Wythe" X-Patchwork-Id: 13155065 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id C2983C6FA8E for ; Tue, 28 Feb 2023 16:38:44 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229754AbjB1Qin (ORCPT ); Tue, 28 Feb 2023 11:38:43 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:58950 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229451AbjB1Qim (ORCPT ); Tue, 28 Feb 2023 11:38:42 -0500 Received: from out30-113.freemail.mail.aliyun.com (out30-113.freemail.mail.aliyun.com [115.124.30.113]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 200A1EC7C; Tue, 28 Feb 2023 08:38:19 -0800 (PST) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R391e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=ay29a033018046051;MF=alibuda@linux.alibaba.com;NM=1;PH=DS;RN=12;SR=0;TI=SMTPD_---0Vck8984_1677602296; Received: from j66a10360.sqa.eu95.tbsite.net(mailfrom:alibuda@linux.alibaba.com fp:SMTPD_---0Vck8984_1677602296) by smtp.aliyun-inc.com; Wed, 01 Mar 2023 00:38:16 +0800 From: "D. Wythe" To: kgraul@linux.ibm.com, wenjia@linux.ibm.com, jaka@linux.ibm.com, ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org Cc: kuba@kernel.org, davem@davemloft.net, netdev@vger.kernel.org, linux-s390@vger.kernel.org, linux-rdma@vger.kernel.org, bpf@vger.kernel.org Subject: [PATCH bpf-next v4 1/4] net/smc: move smc_sock related structure definition Date: Wed, 1 Mar 2023 00:38:08 +0800 Message-Id: <1677602291-1666-2-git-send-email-alibuda@linux.alibaba.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1677602291-1666-1-git-send-email-alibuda@linux.alibaba.com> References: <1677602291-1666-1-git-send-email-alibuda@linux.alibaba.com> Precedence: bulk List-ID: X-Mailing-List: linux-rdma@vger.kernel.org From: "D. Wythe" This patch only try to move the definition of smc_sock and its related structure, from et/smc/smc.h to include/net/smc/smc.h. In that way can ebpf generate the BTF ID corresponding to our structure. Of course, we can also choose to hide the structure and only to expose an intermediate structure, but it requires an additional transformation. If we need to obtain some information frequently, this may cause some performance problems. Signed-off-by: D. Wythe --- include/net/smc.h | 225 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ net/smc/smc.h | 224 ----------------------------------------------------- 2 files changed, 225 insertions(+), 224 deletions(-) diff --git a/include/net/smc.h b/include/net/smc.h index 597cb93..eccbd37 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -11,12 +11,17 @@ #ifndef _SMC_H #define _SMC_H +#include #include #include #include #include #include "linux/ism.h" +#ifdef ATOMIC64_INIT +#define KERNEL_HAS_ATOMIC64 +#endif + struct sock; #define SMC_MAX_PNETID_LEN 16 /* Max. length of PNET id */ @@ -90,4 +95,224 @@ struct smcd_dev { u8 going_away : 1; }; +struct smc_wr_rx_hdr { /* common prefix part of LLC and CDC to demultiplex */ + union { + u8 type; +#if defined(__BIG_ENDIAN_BITFIELD) + struct { + u8 llc_version:4, + llc_type:4; + }; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + struct { + u8 llc_type:4, + llc_version:4; + }; +#endif + }; +} __aligned(1); + +struct smc_cdc_conn_state_flags { +#if defined(__BIG_ENDIAN_BITFIELD) + u8 peer_done_writing : 1; /* Sending done indicator */ + u8 peer_conn_closed : 1; /* Peer connection closed indicator */ + u8 peer_conn_abort : 1; /* Abnormal close indicator */ + u8 reserved : 5; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u8 reserved : 5; + u8 peer_conn_abort : 1; + u8 peer_conn_closed : 1; + u8 peer_done_writing : 1; +#endif +}; + +struct smc_cdc_producer_flags { +#if defined(__BIG_ENDIAN_BITFIELD) + u8 write_blocked : 1; /* Writing Blocked, no rx buf space */ + u8 urg_data_pending : 1; /* Urgent Data Pending */ + u8 urg_data_present : 1; /* Urgent Data Present */ + u8 cons_curs_upd_req : 1; /* cursor update requested */ + u8 failover_validation : 1;/* message replay due to failover */ + u8 reserved : 3; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u8 reserved : 3; + u8 failover_validation : 1; + u8 cons_curs_upd_req : 1; + u8 urg_data_present : 1; + u8 urg_data_pending : 1; + u8 write_blocked : 1; +#endif +}; + +/* in host byte order */ +union smc_host_cursor { /* SMC cursor - an offset in an RMBE */ + struct { + u16 reserved; + u16 wrap; /* window wrap sequence number */ + u32 count; /* cursor (= offset) part */ + }; +#ifdef KERNEL_HAS_ATOMIC64 + atomic64_t acurs; /* for atomic processing */ +#else + u64 acurs; /* for atomic processing */ +#endif +} __aligned(8); + +/* in host byte order, except for flag bitfields in network byte order */ +struct smc_host_cdc_msg { /* Connection Data Control message */ + struct smc_wr_rx_hdr common; /* .type = 0xFE */ + u8 len; /* length = 44 */ + u16 seqno; /* connection seq # */ + u32 token; /* alert_token */ + union smc_host_cursor prod; /* producer cursor */ + union smc_host_cursor cons; /* consumer cursor, + * piggy backed "ack" + */ + struct smc_cdc_producer_flags prod_flags; /* conn. tx/rx status */ + struct smc_cdc_conn_state_flags conn_state_flags; /* peer conn. status*/ + u8 reserved[18]; +} __aligned(8); + +enum smc_urg_state { + SMC_URG_VALID = 1, /* data present */ + SMC_URG_NOTYET = 2, /* data pending */ + SMC_URG_READ = 3, /* data was already read */ +}; + +struct smc_connection { + struct rb_node alert_node; + struct smc_link_group *lgr; /* link group of connection */ + struct smc_link *lnk; /* assigned SMC-R link */ + u32 alert_token_local; /* unique conn. id */ + u8 peer_rmbe_idx; /* from tcp handshake */ + int peer_rmbe_size; /* size of peer rx buffer */ + atomic_t peer_rmbe_space;/* remaining free bytes in peer + * rmbe + */ + int rtoken_idx; /* idx to peer RMB rkey/addr */ + + struct smc_buf_desc *sndbuf_desc; /* send buffer descriptor */ + struct smc_buf_desc *rmb_desc; /* RMBE descriptor */ + int rmbe_size_short;/* compressed notation */ + int rmbe_update_limit; + /* lower limit for consumer + * cursor update + */ + + struct smc_host_cdc_msg local_tx_ctrl; /* host byte order staging + * buffer for CDC msg send + * .prod cf. TCP snd_nxt + * .cons cf. TCP sends ack + */ + union smc_host_cursor local_tx_ctrl_fin; + /* prod crsr - confirmed by peer + */ + union smc_host_cursor tx_curs_prep; /* tx - prepared data + * snd_max..wmem_alloc + */ + union smc_host_cursor tx_curs_sent; /* tx - sent data + * snd_nxt ? + */ + union smc_host_cursor tx_curs_fin; /* tx - confirmed by peer + * snd-wnd-begin ? + */ + atomic_t sndbuf_space; /* remaining space in sndbuf */ + u16 tx_cdc_seq; /* sequence # for CDC send */ + u16 tx_cdc_seq_fin; /* sequence # - tx completed */ + spinlock_t send_lock; /* protect wr_sends */ + atomic_t cdc_pend_tx_wr; /* number of pending tx CDC wqe + * - inc when post wqe, + * - dec on polled tx cqe + */ + wait_queue_head_t cdc_pend_tx_wq; /* wakeup on no cdc_pend_tx_wr*/ + atomic_t tx_pushing; /* nr_threads trying tx push */ + struct delayed_work tx_work; /* retry of smc_cdc_msg_send */ + u32 tx_off; /* base offset in peer rmb */ + + struct smc_host_cdc_msg local_rx_ctrl; /* filled during event_handl. + * .prod cf. TCP rcv_nxt + * .cons cf. TCP snd_una + */ + union smc_host_cursor rx_curs_confirmed; /* confirmed to peer + * source of snd_una ? + */ + union smc_host_cursor urg_curs; /* points at urgent byte */ + enum smc_urg_state urg_state; + bool urg_tx_pend; /* urgent data staged */ + bool urg_rx_skip_pend; + /* indicate urgent oob data + * read, but previous regular + * data still pending + */ + char urg_rx_byte; /* urgent byte */ + bool tx_in_release_sock; + /* flush pending tx data in + * sock release_cb() + */ + atomic_t bytes_to_rcv; /* arrived data, + * not yet received + */ + atomic_t splice_pending; /* number of spliced bytes + * pending processing + */ +#ifndef KERNEL_HAS_ATOMIC64 + spinlock_t acurs_lock; /* protect cursors */ +#endif + struct work_struct close_work; /* peer sent some closing */ + struct work_struct abort_work; /* abort the connection */ + struct tasklet_struct rx_tsklet; /* Receiver tasklet for SMC-D */ + u8 rx_off; /* receive offset: + * 0 for SMC-R, 32 for SMC-D + */ + u64 peer_token; /* SMC-D token of peer */ + u8 killed : 1; /* abnormal termination */ + u8 freed : 1; /* normal termiation */ + u8 out_of_sync : 1; /* out of sync with peer */ +}; + +struct smc_sock { /* smc sock container */ + struct sock sk; + struct socket *clcsock; /* internal tcp socket */ + void (*clcsk_state_change)(struct sock *sk); + /* original stat_change fct. */ + void (*clcsk_data_ready)(struct sock *sk); + /* original data_ready fct. */ + void (*clcsk_write_space)(struct sock *sk); + /* original write_space fct. */ + void (*clcsk_error_report)(struct sock *sk); + /* original error_report fct. */ + struct smc_connection conn; /* smc connection */ + struct smc_sock *listen_smc; /* listen parent */ + struct work_struct connect_work; /* handle non-blocking connect*/ + struct work_struct tcp_listen_work;/* handle tcp socket accepts */ + struct work_struct smc_listen_work;/* prepare new accept socket */ + struct list_head accept_q; /* sockets to be accepted */ + spinlock_t accept_q_lock; /* protects accept_q */ + bool limit_smc_hs; /* put constraint on handshake */ + bool use_fallback; /* fallback to tcp */ + int fallback_rsn; /* reason for fallback */ + u32 peer_diagnosis; /* decline reason from peer */ + atomic_t queued_smc_hs; /* queued smc handshakes */ + struct inet_connection_sock_af_ops af_ops; + const struct inet_connection_sock_af_ops *ori_af_ops; + /* original af ops */ + int sockopt_defer_accept; + /* sockopt TCP_DEFER_ACCEPT + * value + */ + u8 wait_close_tx_prepared : 1; + /* shutdown wr or close + * started, waiting for unsent + * data to be sent + */ + u8 connect_nonblock : 1; + /* non-blocking connect in + * flight + */ + struct mutex clcsock_release_lock; + /* protects clcsock of a listen + * socket + */ +}; + #endif /* _SMC_H */ diff --git a/net/smc/smc.h b/net/smc/smc.h index 5ed765e..6f27f40 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -34,10 +34,6 @@ extern struct proto smc_proto; extern struct proto smc_proto6; -#ifdef ATOMIC64_INIT -#define KERNEL_HAS_ATOMIC64 -#endif - enum smc_state { /* possible states of an SMC socket */ SMC_ACTIVE = 1, SMC_INIT = 2, @@ -57,232 +53,12 @@ enum smc_state { /* possible states of an SMC socket */ struct smc_link_group; -struct smc_wr_rx_hdr { /* common prefix part of LLC and CDC to demultiplex */ - union { - u8 type; -#if defined(__BIG_ENDIAN_BITFIELD) - struct { - u8 llc_version:4, - llc_type:4; - }; -#elif defined(__LITTLE_ENDIAN_BITFIELD) - struct { - u8 llc_type:4, - llc_version:4; - }; -#endif - }; -} __aligned(1); - -struct smc_cdc_conn_state_flags { -#if defined(__BIG_ENDIAN_BITFIELD) - u8 peer_done_writing : 1; /* Sending done indicator */ - u8 peer_conn_closed : 1; /* Peer connection closed indicator */ - u8 peer_conn_abort : 1; /* Abnormal close indicator */ - u8 reserved : 5; -#elif defined(__LITTLE_ENDIAN_BITFIELD) - u8 reserved : 5; - u8 peer_conn_abort : 1; - u8 peer_conn_closed : 1; - u8 peer_done_writing : 1; -#endif -}; - -struct smc_cdc_producer_flags { -#if defined(__BIG_ENDIAN_BITFIELD) - u8 write_blocked : 1; /* Writing Blocked, no rx buf space */ - u8 urg_data_pending : 1; /* Urgent Data Pending */ - u8 urg_data_present : 1; /* Urgent Data Present */ - u8 cons_curs_upd_req : 1; /* cursor update requested */ - u8 failover_validation : 1;/* message replay due to failover */ - u8 reserved : 3; -#elif defined(__LITTLE_ENDIAN_BITFIELD) - u8 reserved : 3; - u8 failover_validation : 1; - u8 cons_curs_upd_req : 1; - u8 urg_data_present : 1; - u8 urg_data_pending : 1; - u8 write_blocked : 1; -#endif -}; - -/* in host byte order */ -union smc_host_cursor { /* SMC cursor - an offset in an RMBE */ - struct { - u16 reserved; - u16 wrap; /* window wrap sequence number */ - u32 count; /* cursor (= offset) part */ - }; -#ifdef KERNEL_HAS_ATOMIC64 - atomic64_t acurs; /* for atomic processing */ -#else - u64 acurs; /* for atomic processing */ -#endif -} __aligned(8); - -/* in host byte order, except for flag bitfields in network byte order */ -struct smc_host_cdc_msg { /* Connection Data Control message */ - struct smc_wr_rx_hdr common; /* .type = 0xFE */ - u8 len; /* length = 44 */ - u16 seqno; /* connection seq # */ - u32 token; /* alert_token */ - union smc_host_cursor prod; /* producer cursor */ - union smc_host_cursor cons; /* consumer cursor, - * piggy backed "ack" - */ - struct smc_cdc_producer_flags prod_flags; /* conn. tx/rx status */ - struct smc_cdc_conn_state_flags conn_state_flags; /* peer conn. status*/ - u8 reserved[18]; -} __aligned(8); - -enum smc_urg_state { - SMC_URG_VALID = 1, /* data present */ - SMC_URG_NOTYET = 2, /* data pending */ - SMC_URG_READ = 3, /* data was already read */ -}; - struct smc_mark_woken { bool woken; void *key; wait_queue_entry_t wait_entry; }; -struct smc_connection { - struct rb_node alert_node; - struct smc_link_group *lgr; /* link group of connection */ - struct smc_link *lnk; /* assigned SMC-R link */ - u32 alert_token_local; /* unique conn. id */ - u8 peer_rmbe_idx; /* from tcp handshake */ - int peer_rmbe_size; /* size of peer rx buffer */ - atomic_t peer_rmbe_space;/* remaining free bytes in peer - * rmbe - */ - int rtoken_idx; /* idx to peer RMB rkey/addr */ - - struct smc_buf_desc *sndbuf_desc; /* send buffer descriptor */ - struct smc_buf_desc *rmb_desc; /* RMBE descriptor */ - int rmbe_size_short;/* compressed notation */ - int rmbe_update_limit; - /* lower limit for consumer - * cursor update - */ - - struct smc_host_cdc_msg local_tx_ctrl; /* host byte order staging - * buffer for CDC msg send - * .prod cf. TCP snd_nxt - * .cons cf. TCP sends ack - */ - union smc_host_cursor local_tx_ctrl_fin; - /* prod crsr - confirmed by peer - */ - union smc_host_cursor tx_curs_prep; /* tx - prepared data - * snd_max..wmem_alloc - */ - union smc_host_cursor tx_curs_sent; /* tx - sent data - * snd_nxt ? - */ - union smc_host_cursor tx_curs_fin; /* tx - confirmed by peer - * snd-wnd-begin ? - */ - atomic_t sndbuf_space; /* remaining space in sndbuf */ - u16 tx_cdc_seq; /* sequence # for CDC send */ - u16 tx_cdc_seq_fin; /* sequence # - tx completed */ - spinlock_t send_lock; /* protect wr_sends */ - atomic_t cdc_pend_tx_wr; /* number of pending tx CDC wqe - * - inc when post wqe, - * - dec on polled tx cqe - */ - wait_queue_head_t cdc_pend_tx_wq; /* wakeup on no cdc_pend_tx_wr*/ - atomic_t tx_pushing; /* nr_threads trying tx push */ - struct delayed_work tx_work; /* retry of smc_cdc_msg_send */ - u32 tx_off; /* base offset in peer rmb */ - - struct smc_host_cdc_msg local_rx_ctrl; /* filled during event_handl. - * .prod cf. TCP rcv_nxt - * .cons cf. TCP snd_una - */ - union smc_host_cursor rx_curs_confirmed; /* confirmed to peer - * source of snd_una ? - */ - union smc_host_cursor urg_curs; /* points at urgent byte */ - enum smc_urg_state urg_state; - bool urg_tx_pend; /* urgent data staged */ - bool urg_rx_skip_pend; - /* indicate urgent oob data - * read, but previous regular - * data still pending - */ - char urg_rx_byte; /* urgent byte */ - bool tx_in_release_sock; - /* flush pending tx data in - * sock release_cb() - */ - atomic_t bytes_to_rcv; /* arrived data, - * not yet received - */ - atomic_t splice_pending; /* number of spliced bytes - * pending processing - */ -#ifndef KERNEL_HAS_ATOMIC64 - spinlock_t acurs_lock; /* protect cursors */ -#endif - struct work_struct close_work; /* peer sent some closing */ - struct work_struct abort_work; /* abort the connection */ - struct tasklet_struct rx_tsklet; /* Receiver tasklet for SMC-D */ - u8 rx_off; /* receive offset: - * 0 for SMC-R, 32 for SMC-D - */ - u64 peer_token; /* SMC-D token of peer */ - u8 killed : 1; /* abnormal termination */ - u8 freed : 1; /* normal termiation */ - u8 out_of_sync : 1; /* out of sync with peer */ -}; - -struct smc_sock { /* smc sock container */ - struct sock sk; - struct socket *clcsock; /* internal tcp socket */ - void (*clcsk_state_change)(struct sock *sk); - /* original stat_change fct. */ - void (*clcsk_data_ready)(struct sock *sk); - /* original data_ready fct. */ - void (*clcsk_write_space)(struct sock *sk); - /* original write_space fct. */ - void (*clcsk_error_report)(struct sock *sk); - /* original error_report fct. */ - struct smc_connection conn; /* smc connection */ - struct smc_sock *listen_smc; /* listen parent */ - struct work_struct connect_work; /* handle non-blocking connect*/ - struct work_struct tcp_listen_work;/* handle tcp socket accepts */ - struct work_struct smc_listen_work;/* prepare new accept socket */ - struct list_head accept_q; /* sockets to be accepted */ - spinlock_t accept_q_lock; /* protects accept_q */ - bool limit_smc_hs; /* put constraint on handshake */ - bool use_fallback; /* fallback to tcp */ - int fallback_rsn; /* reason for fallback */ - u32 peer_diagnosis; /* decline reason from peer */ - atomic_t queued_smc_hs; /* queued smc handshakes */ - struct inet_connection_sock_af_ops af_ops; - const struct inet_connection_sock_af_ops *ori_af_ops; - /* original af ops */ - int sockopt_defer_accept; - /* sockopt TCP_DEFER_ACCEPT - * value - */ - u8 wait_close_tx_prepared : 1; - /* shutdown wr or close - * started, waiting for unsent - * data to be sent - */ - u8 connect_nonblock : 1; - /* non-blocking connect in - * flight - */ - struct mutex clcsock_release_lock; - /* protects clcsock of a listen - * socket - * */ -}; - static inline struct smc_sock *smc_sk(const struct sock *sk) { return (struct smc_sock *)sk; From patchwork Tue Feb 28 16:38:09 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "D. Wythe" X-Patchwork-Id: 13155067 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 69210C7EE43 for ; Tue, 28 Feb 2023 16:38:48 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229775AbjB1Qiq (ORCPT ); Tue, 28 Feb 2023 11:38:46 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:58996 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229765AbjB1Qio (ORCPT ); Tue, 28 Feb 2023 11:38:44 -0500 Received: from out30-113.freemail.mail.aliyun.com (out30-113.freemail.mail.aliyun.com [115.124.30.113]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 2EB283A84; Tue, 28 Feb 2023 08:38:21 -0800 (PST) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R581e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=ay29a033018046051;MF=alibuda@linux.alibaba.com;NM=1;PH=DS;RN=12;SR=0;TI=SMTPD_---0Vck898W_1677602296; Received: from j66a10360.sqa.eu95.tbsite.net(mailfrom:alibuda@linux.alibaba.com fp:SMTPD_---0Vck898W_1677602296) by smtp.aliyun-inc.com; Wed, 01 Mar 2023 00:38:17 +0800 From: "D. Wythe" To: kgraul@linux.ibm.com, wenjia@linux.ibm.com, jaka@linux.ibm.com, ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org Cc: kuba@kernel.org, davem@davemloft.net, netdev@vger.kernel.org, linux-s390@vger.kernel.org, linux-rdma@vger.kernel.org, bpf@vger.kernel.org Subject: [PATCH bpf-next v4 2/4] bpf: add SMC support in BPF struct_ops Date: Wed, 1 Mar 2023 00:38:09 +0800 Message-Id: <1677602291-1666-3-git-send-email-alibuda@linux.alibaba.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1677602291-1666-1-git-send-email-alibuda@linux.alibaba.com> References: <1677602291-1666-1-git-send-email-alibuda@linux.alibaba.com> Precedence: bulk List-ID: X-Mailing-List: linux-rdma@vger.kernel.org From: "D. Wythe" This PATCH attempts to introduce BPF injection capability for SMC. Considering that the SMC protocol is not suitable for all scenarios, especially for short-lived. However, for most applications, they cannot guarantee that there are no such scenarios at all. Therefore, apps may need some specific strategies to decide shall we need to use SMC or not, for example, apps can limit the scope of the SMC to a specific IP address or port. Based on the consideration of transparent replacement, we hope that apps can remain transparent even if they need to formulate some specific strategies for SMC using. That is, do not need to recompile their code. On the other hand, we need to ensure the scalability of strategies implementation. Although it is simple to use socket options or sysctl, it will bring more complexity to subsequent expansion. Fortunately, BPF can solve these concerns very well, users can write thire own strategies in eBPF to choose whether to use SMC or not. And it's quite easy for them to modify their strategies in the future. This PATCH implement injection capability for SMC via struct_ops. In that way, we can add new injection scenarios in the future. Signed-off-by: D. Wythe --- include/linux/btf_ids.h | 12 ++++ include/net/smc.h | 38 ++++++++++ kernel/bpf/bpf_struct_ops_types.h | 4 ++ net/Makefile | 5 ++ net/smc/bpf_smc_struct_ops.c | 148 ++++++++++++++++++++++++++++++++++++++ 5 files changed, 207 insertions(+) create mode 100644 net/smc/bpf_smc_struct_ops.c diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 3a4f7cd..d4cf0a9 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -264,6 +264,18 @@ enum { MAX_BTF_TRACING_TYPE, }; +#if IS_ENABLED(CONFIG_SMC) +enum { +#define BTF_SMC_TYPE(name, type) name, +BTF_SMC_TYPE(BTF_SMC_TYPE_SOCK, smc_sock) +BTF_SMC_TYPE(BTF_SMC_TYPE_CONNECTION, smc_connection) +BTF_SMC_TYPE(BTF_SMC_TYPE_HOST_CURSOR, smc_host_cursor) +#undef BTF_SMC_TYPE +MAX_BTF_SMC_TYPE, +}; +extern u32 btf_smc_ids[]; +#endif + extern u32 btf_tracing_ids[]; extern u32 bpf_cgroup_btf_id[]; extern u32 bpf_local_storage_map_btf_id[]; diff --git a/include/net/smc.h b/include/net/smc.h index eccbd37..1891f49 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -16,6 +16,7 @@ #include #include #include +#include #include "linux/ism.h" #ifdef ATOMIC64_INIT @@ -315,4 +316,41 @@ struct smc_sock { /* smc sock container */ */ }; +#define SMC_SOCK_CLOSED_TIMING (0) + +#ifdef CONFIG_BPF_SYSCALL + +/* BPF struct ops for smc protocol negotiator */ +struct smc_sock_negotiator_ops { + /* ret for negotiate */ + int (*negotiate)(struct smc_sock *sk); + + /* info gathering timing */ + void (*collect_info)(struct sock *sk, int timing); +}; + +/* Query if current sock should go with SMC protocol + * SK_PASS for yes, otherwise for no. + */ +int smc_sock_should_select_smc(const struct smc_sock *smc); + +/* At some specific points in time, + * let negotiator can perform info gathering + * on target sock. + */ +void smc_sock_perform_collecting_info(const struct sock *sk, int timing); + +#else + +static inline int smc_sock_should_select_smc(const struct smc_sock *smc) +{ + return SK_PASS; +} + +static inline void smc_sock_perform_collecting_info(const struct sock *sk, int timing) +{ +} + +#endif /* CONFIG_BPF_SYSCALL */ + #endif /* _SMC_H */ diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h index 5678a9d..35cdd15 100644 --- a/kernel/bpf/bpf_struct_ops_types.h +++ b/kernel/bpf/bpf_struct_ops_types.h @@ -9,4 +9,8 @@ #include BPF_STRUCT_OPS_TYPE(tcp_congestion_ops) #endif +#if IS_ENABLED(CONFIG_SMC) +#include +BPF_STRUCT_OPS_TYPE(smc_sock_negotiator_ops) +#endif #endif diff --git a/net/Makefile b/net/Makefile index 0914bea..47a4c00 100644 --- a/net/Makefile +++ b/net/Makefile @@ -52,6 +52,11 @@ obj-$(CONFIG_TIPC) += tipc/ obj-$(CONFIG_NETLABEL) += netlabel/ obj-$(CONFIG_IUCV) += iucv/ obj-$(CONFIG_SMC) += smc/ +ifneq ($(CONFIG_SMC),) +ifeq ($(CONFIG_BPF_SYSCALL),y) +obj-y += smc/bpf_smc_struct_ops.o +endif +endif obj-$(CONFIG_RFKILL) += rfkill/ obj-$(CONFIG_NET_9P) += 9p/ obj-$(CONFIG_CAIF) += caif/ diff --git a/net/smc/bpf_smc_struct_ops.c b/net/smc/bpf_smc_struct_ops.c new file mode 100644 index 0000000..5772a42 --- /dev/null +++ b/net/smc/bpf_smc_struct_ops.c @@ -0,0 +1,148 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include +#include +#include +#include + +extern struct bpf_struct_ops smc_sock_negotiator_ops; + +DEFINE_RWLOCK(smc_sock_negotiator_ops_rwlock); +struct smc_sock_negotiator_ops *negotiator; + +/* convert sk to smc_sock */ +static inline struct smc_sock *smc_sk(const struct sock *sk) +{ + return (struct smc_sock *)sk; +} + +/* register ops */ +static inline void smc_reg_passive_sk_ops(struct smc_sock_negotiator_ops *ops) +{ + write_lock_bh(&smc_sock_negotiator_ops_rwlock); + negotiator = ops; + write_unlock_bh(&smc_sock_negotiator_ops_rwlock); +} + +/* unregister ops */ +static inline void smc_unreg_passive_sk_ops(struct smc_sock_negotiator_ops *ops) +{ + write_lock_bh(&smc_sock_negotiator_ops_rwlock); + if (negotiator == ops) + negotiator = NULL; + write_unlock_bh(&smc_sock_negotiator_ops_rwlock); +} + +int smc_sock_should_select_smc(const struct smc_sock *smc) +{ + int ret = SK_PASS; + + read_lock_bh(&smc_sock_negotiator_ops_rwlock); + if (negotiator && negotiator->negotiate) + ret = negotiator->negotiate((struct smc_sock *)smc); + read_unlock_bh(&smc_sock_negotiator_ops_rwlock); + return ret; +} +EXPORT_SYMBOL_GPL(smc_sock_should_select_smc); + +void smc_sock_perform_collecting_info(const struct sock *sk, int timing) +{ + read_lock_bh(&smc_sock_negotiator_ops_rwlock); + if (negotiator && negotiator->collect_info) + negotiator->collect_info((struct sock *)sk, timing); + read_unlock_bh(&smc_sock_negotiator_ops_rwlock); +} +EXPORT_SYMBOL_GPL(smc_sock_perform_collecting_info); + +/* define global smc ID for smc_struct_ops */ +BTF_ID_LIST_GLOBAL(btf_smc_ids, MAX_BTF_SMC_TYPE) +#define BTF_SMC_TYPE(name, type) BTF_ID(struct, type) +BTF_SMC_TYPE(BTF_SMC_TYPE_SOCK, smc_sock) +BTF_SMC_TYPE(BTF_SMC_TYPE_CONNECTION, smc_connection) +BTF_SMC_TYPE(BTF_SMC_TYPE_HOST_CURSOR, smc_host_cursor) +#undef BTF_SMC_TYPE + +static int bpf_smc_passive_sk_init(struct btf *btf) +{ + return 0; +} + +/* register ops by BPF */ +static int bpf_smc_passive_sk_ops_reg(void *kdata) +{ + struct smc_sock_negotiator_ops *ops = kdata; + + /* at least one ops need implement */ + if (!ops->negotiate || !ops->collect_info) { + pr_err("At least one ops need implement.\n"); + return -EINVAL; + } + + smc_reg_passive_sk_ops(ops); + /* always success now */ + return 0; +} + +/* unregister ops by BPF */ +static void bpf_smc_passive_sk_ops_unreg(void *kdata) +{ + smc_unreg_passive_sk_ops(kdata); +} + +static int bpf_smc_passive_sk_ops_check_member(const struct btf_type *t, + const struct btf_member *member, + const struct bpf_prog *prog) +{ + return 0; +} + +static int bpf_smc_passive_sk_ops_init_member(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata) +{ + return 0; +} + +static const struct bpf_func_proto * +smc_passive_sk_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + return bpf_base_func_proto(func_id); +} + +static bool smc_passive_sk_ops_prog_is_valid_access(int off, int size, enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + return bpf_tracing_btf_ctx_access(off, size, type, prog, info); +} + +static int smc_passive_sk_ops_prog_struct_access(struct bpf_verifier_log *log, + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag) +{ + /* only allow read now*/ + if (atype == BPF_READ) + return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); + + return -EACCES; +} + +static const struct bpf_verifier_ops bpf_smc_passive_sk_verifier_ops = { + .get_func_proto = smc_passive_sk_prog_func_proto, + .is_valid_access = smc_passive_sk_ops_prog_is_valid_access, + .btf_struct_access = smc_passive_sk_ops_prog_struct_access +}; + +struct bpf_struct_ops bpf_smc_sock_negotiator_ops = { + .verifier_ops = &bpf_smc_passive_sk_verifier_ops, + .init = bpf_smc_passive_sk_init, + .check_member = bpf_smc_passive_sk_ops_check_member, + .init_member = bpf_smc_passive_sk_ops_init_member, + .reg = bpf_smc_passive_sk_ops_reg, + .unreg = bpf_smc_passive_sk_ops_unreg, + .name = "smc_sock_negotiator_ops", +}; From patchwork Tue Feb 28 16:38:10 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "D. Wythe" X-Patchwork-Id: 13155066 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5B409C7EE39 for ; Tue, 28 Feb 2023 16:38:47 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229769AbjB1Qip (ORCPT ); Tue, 28 Feb 2023 11:38:45 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:58992 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229451AbjB1Qin (ORCPT ); Tue, 28 Feb 2023 11:38:43 -0500 Received: from out30-99.freemail.mail.aliyun.com (out30-99.freemail.mail.aliyun.com [115.124.30.99]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 8FCC11FFE; Tue, 28 Feb 2023 08:38:21 -0800 (PST) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R621e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=ay29a033018046060;MF=alibuda@linux.alibaba.com;NM=1;PH=DS;RN=12;SR=0;TI=SMTPD_---0Vck898u_1677602297; Received: from j66a10360.sqa.eu95.tbsite.net(mailfrom:alibuda@linux.alibaba.com fp:SMTPD_---0Vck898u_1677602297) by smtp.aliyun-inc.com; Wed, 01 Mar 2023 00:38:17 +0800 From: "D. Wythe" To: kgraul@linux.ibm.com, wenjia@linux.ibm.com, jaka@linux.ibm.com, ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org Cc: kuba@kernel.org, davem@davemloft.net, netdev@vger.kernel.org, linux-s390@vger.kernel.org, linux-rdma@vger.kernel.org, bpf@vger.kernel.org Subject: [PATCH bpf-next v4 3/4] net/smc: add BPF injection on smc negotiation Date: Wed, 1 Mar 2023 00:38:10 +0800 Message-Id: <1677602291-1666-4-git-send-email-alibuda@linux.alibaba.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1677602291-1666-1-git-send-email-alibuda@linux.alibaba.com> References: <1677602291-1666-1-git-send-email-alibuda@linux.alibaba.com> Precedence: bulk List-ID: X-Mailing-List: linux-rdma@vger.kernel.org From: "D. Wythe" This patch try add BPF injection on smc negotiation, so that the application can decided whether to use smc or not through eBPF progs. In particular, some applications may need global dynamic information to make decision. Therefore, we also inject a information collect point into smc_release. Note that, in order to make negotiation can be decided by application, sockets must have SMC_LIMIT_HS set. Signed-off-by: D. Wythe --- net/smc/af_smc.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index a4cccdf..7ebe5e8 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -166,6 +166,9 @@ static bool smc_hs_congested(const struct sock *sk) if (workqueue_congested(WORK_CPU_UNBOUND, smc_hs_wq)) return true; + if (!smc_sock_should_select_smc(smc)) + return true; + return false; } @@ -320,6 +323,9 @@ static int smc_release(struct socket *sock) sock_hold(sk); /* sock_put below */ smc = smc_sk(sk); + /* trigger info gathering if needed.*/ + smc_sock_perform_collecting_info(sk, SMC_SOCK_CLOSED_TIMING); + old_state = sk->sk_state; /* cleanup for a dangling non-blocking connect */ @@ -1627,7 +1633,14 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, } smc_copy_sock_settings_to_clc(smc); - tcp_sk(smc->clcsock->sk)->syn_smc = 1; + /* accept out connection as SMC connection */ + if (smc_sock_should_select_smc(smc) == SK_PASS) { + tcp_sk(smc->clcsock->sk)->syn_smc = 1; + } else { + tcp_sk(smc->clcsock->sk)->syn_smc = 0; + smc_switch_to_fallback(smc, /* just a chooice */ 0); + } + if (smc->connect_nonblock) { rc = -EALREADY; goto out; From patchwork Tue Feb 28 16:38:11 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "D. Wythe" X-Patchwork-Id: 13155068 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id A5B7BC6FA8E for ; Tue, 28 Feb 2023 16:38:58 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229799AbjB1Qi5 (ORCPT ); Tue, 28 Feb 2023 11:38:57 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:59030 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229783AbjB1Qiq (ORCPT ); Tue, 28 Feb 2023 11:38:46 -0500 Received: from out30-133.freemail.mail.aliyun.com (out30-133.freemail.mail.aliyun.com [115.124.30.133]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 9D8512411A; Tue, 28 Feb 2023 08:38:23 -0800 (PST) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R181e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=ay29a033018046060;MF=alibuda@linux.alibaba.com;NM=1;PH=DS;RN=12;SR=0;TI=SMTPD_---0Vck899Q_1677602298; Received: from j66a10360.sqa.eu95.tbsite.net(mailfrom:alibuda@linux.alibaba.com fp:SMTPD_---0Vck899Q_1677602298) by smtp.aliyun-inc.com; Wed, 01 Mar 2023 00:38:18 +0800 From: "D. Wythe" To: kgraul@linux.ibm.com, wenjia@linux.ibm.com, jaka@linux.ibm.com, ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org Cc: kuba@kernel.org, davem@davemloft.net, netdev@vger.kernel.org, linux-s390@vger.kernel.org, linux-rdma@vger.kernel.org, bpf@vger.kernel.org Subject: [PATCH bpf-next v4 4/4] bpf/selftests: add selftest for SMC bpf capability Date: Wed, 1 Mar 2023 00:38:11 +0800 Message-Id: <1677602291-1666-5-git-send-email-alibuda@linux.alibaba.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1677602291-1666-1-git-send-email-alibuda@linux.alibaba.com> References: <1677602291-1666-1-git-send-email-alibuda@linux.alibaba.com> Precedence: bulk List-ID: X-Mailing-List: linux-rdma@vger.kernel.org From: "D. Wythe" This PATCH adds a tiny selftest for SMC bpf capability, making decisions on whether to use SMC by collecting certain information from kernel smc sock. Follow the steps below to run this test. make -C tools/testing/selftests/bpf cd tools/testing/selftests/bpf sudo ./test_progs -t bpf_smc Results shows: 18 bpf_smc:OK Summary: 1/0 PASSED, 0 SKIPPED, 0 FAILED Signed-off-by: D. Wythe --- tools/testing/selftests/bpf/prog_tests/bpf_smc.c | 37 +++ tools/testing/selftests/bpf/progs/bpf_smc.c | 320 +++++++++++++++++++++++ 2 files changed, 357 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/bpf_smc.c create mode 100644 tools/testing/selftests/bpf/progs/bpf_smc.c diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_smc.c b/tools/testing/selftests/bpf/prog_tests/bpf_smc.c new file mode 100644 index 0000000..b57326c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_smc.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include "bpf_smc.skel.h" + +void test_bpf_smc(void) +{ + struct bpf_smc *smc_skel; + struct bpf_link *link; + int err; + + smc_skel = bpf_smc__open(); + if (!ASSERT_OK_PTR(smc_skel, "skel_open")) + return; + + err = bpf_map__set_type(smc_skel->maps.negotiator_map, BPF_MAP_TYPE_HASH); + if (!ASSERT_OK(err, "bpf_map__set_type")) + goto error; + + err = bpf_map__set_max_entries(smc_skel->maps.negotiator_map, 1); + if (!ASSERT_OK(err, "bpf_map__set_type")) + goto error; + + err = bpf_smc__load(smc_skel); + if (!ASSERT_OK(err, "skel_load")) + goto error; + + link = bpf_map__attach_struct_ops(smc_skel->maps.ops); + if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops")) + goto error; + + bpf_link__destroy(link); +error: + bpf_smc__destroy(smc_skel); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_smc.c b/tools/testing/selftests/bpf/progs/bpf_smc.c new file mode 100644 index 0000000..4f4a541 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_smc.c @@ -0,0 +1,320 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include +#include +#include +#include +#include + +#define AF_SMC (43) +#define SMC_LISTEN (10) +#define SMC_SOCK_CLOSED_TIMING (0) +extern unsigned long CONFIG_HZ __kconfig; +#define HZ CONFIG_HZ + +char _license[] SEC("license") = "GPL"; +#define max(a, b) ((a) > (b) ? (a) : (b)) + +struct sock_common { + unsigned char skc_state; + unsigned short skc_family; + __u16 skc_num; +} __attribute__((preserve_access_index)); + +struct sock { + struct sock_common __sk_common; + int sk_sndbuf; +} __attribute__((preserve_access_index)); + +struct inet_sock { + struct sock sk; +} __attribute__((preserve_access_index)); + +struct inet_connection_sock { + struct inet_sock icsk_inet; +} __attribute__((preserve_access_index)); + +struct tcp_sock { + struct inet_connection_sock inet_conn; + __u32 rcv_nxt; + __u32 snd_nxt; + __u32 snd_una; + __u32 delivered; + __u8 syn_data:1, /* SYN includes data */ + syn_fastopen:1, /* SYN includes Fast Open option */ + syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */ + syn_fastopen_ch:1, /* Active TFO re-enabling probe */ + syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ + save_syn:1, /* Save headers of SYN packet */ + is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ + syn_smc:1; /* SYN includes SMC */ +} __attribute__((preserve_access_index)); + +struct socket { + struct sock *sk; +} __attribute__((preserve_access_index)); + +union smc_host_cursor { + struct { + __u16 reserved; + __u16 wrap; + __u32 count; + }; +} __attribute__((preserve_access_index)); + +struct smc_connection { + union smc_host_cursor tx_curs_sent; + union smc_host_cursor rx_curs_confirmed; +} __attribute__((preserve_access_index)); + +struct smc_sock { + struct sock sk; + struct socket *clcsock; /* internal tcp socket */ + struct smc_connection conn; + int use_fallback; +} __attribute__((preserve_access_index)); + +static __always_inline struct tcp_sock *tcp_sk(const struct sock *sk) +{ + return (struct tcp_sock *)sk; +} + +static __always_inline struct smc_sock *smc_sk(struct sock *sk) +{ + return (struct smc_sock *)sk; +} + +struct smc_prediction { + /* protection for smc_prediction */ + struct bpf_spin_lock lock; + /* start of time slice */ + __u64 start_tstamp; + /* delta of pacing */ + __u64 pacing_delta; + /* N of closed connections determined as long connections + * in current time slice + */ + __u32 closed_long_cc; + /* N of closed connections in this time slice */ + __u32 closed_total_cc; + /* N of incoming connections determined as long connections + * in current time slice + */ + __u32 incoming_long_cc; + /* last splice rate of long cc */ + __u32 last_rate_of_lcc; +}; + +#define SMC_PREDICTION_MIN_PACING_DELTA (1llu) +#define SMC_PREDICTION_MAX_PACING_DELTA (HZ << 3) +#define SMC_PREDICTION_MAX_LONGCC_PER_SPLICE (8) +#define SMC_PREDICTION_MAX_PORT (64) +#define SMC_PREDICTION_MAX_SPLICE_GAP (1) +#define SMC_PREDICTION_LONGCC_RATE_THRESHOLD (13189) +#define SMC_PREDICTION_LONGCC_PACKETS_THRESHOLD (100) +#define SMC_PREDICTION_LONGCC_BYTES_THRESHOLD \ + (SMC_PREDICTION_LONGCC_PACKETS_THRESHOLD * 1024) + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, SMC_PREDICTION_MAX_PORT); + __type(key, __u16); + __type(value, struct smc_prediction); +} negotiator_map SEC(".maps"); + + +static inline __u32 smc_prediction_calt_rate(struct smc_prediction *smc_predictor) +{ + if (!smc_predictor->closed_total_cc) + return smc_predictor->last_rate_of_lcc; + + return (smc_predictor->closed_long_cc << 14) / smc_predictor->closed_total_cc; +} + +static inline struct smc_prediction *smc_prediction_get(__u16 key, __u64 tstamp) +{ + struct smc_prediction zero = {}, *smc_predictor; + __u32 gap; + int err; + + smc_predictor = bpf_map_lookup_elem(&negotiator_map, &key); + if (!smc_predictor) { + zero.start_tstamp = bpf_jiffies64(); + zero.pacing_delta = SMC_PREDICTION_MIN_PACING_DELTA; + err = bpf_map_update_elem(&negotiator_map, &key, &zero, 0); + if (err) + return NULL; + smc_predictor = bpf_map_lookup_elem(&negotiator_map, &key); + if (!smc_predictor) + return NULL; + } + + if (tstamp) { + bpf_spin_lock(&smc_predictor->lock); + gap = (tstamp - smc_predictor->start_tstamp) / smc_predictor->pacing_delta; + /* new splice */ + if (gap > 0) { + smc_predictor->start_tstamp = tstamp; + smc_predictor->last_rate_of_lcc = + (smc_prediction_calt_rate(smc_predictor) * 7) >> (2 + gap); + smc_predictor->closed_long_cc = 0; + smc_predictor->closed_total_cc = 0; + smc_predictor->incoming_long_cc = 0; + } + bpf_spin_unlock(&smc_predictor->lock); + } + return smc_predictor; +} + +/* BPF struct ops for smc protocol negotiator */ +struct smc_sock_negotiator_ops { + /* ret for negotiate */ + int (*negotiate)(struct smc_sock *smc); + + /* info gathering timing */ + void (*collect_info)(struct smc_sock *smc, int timing); +}; + +int SEC("struct_ops/bpf_smc_negotiate") +BPF_PROG(bpf_smc_negotiate, struct smc_sock *smc) +{ + struct smc_prediction *smc_predictor; + int err, ret = SK_DROP; + struct tcp_sock *tp; + struct sock *clcsk; + __u32 rate = 0; + __u16 key; + + /* client side */ + if (smc == NULL || smc->sk.__sk_common.skc_state != SMC_LISTEN) { + /* use Global smc_predictor */ + key = 0; + } else { /* server side */ + clcsk = BPF_CORE_READ(smc, clcsock, sk); + if (!clcsk) + goto error; + tp = tcp_sk(clcsk); + err = bpf_core_read(&key, sizeof(__u16), + &tp->inet_conn.icsk_inet.sk.__sk_common.skc_num); + if (err) + goto error; + } + + smc_predictor = smc_prediction_get(key, bpf_jiffies64()); + if (!smc_predictor) + return SK_PASS; + + bpf_spin_lock(&smc_predictor->lock); + + if (smc_predictor->incoming_long_cc == 0) + goto out_locked_pass; + + if (smc_predictor->incoming_long_cc > SMC_PREDICTION_MAX_LONGCC_PER_SPLICE) + goto out_locked_drop; + + rate = smc_prediction_calt_rate(smc_predictor); + if (rate < SMC_PREDICTION_LONGCC_RATE_THRESHOLD) + goto out_locked_drop; + +out_locked_pass: + smc_predictor->incoming_long_cc++; + bpf_spin_unlock(&smc_predictor->lock); + return SK_PASS; +out_locked_drop: + bpf_spin_unlock(&smc_predictor->lock); +error: + return SK_DROP; +} + +void SEC("struct_ops/bpf_smc_collect_info") +BPF_PROG(bpf_smc_collect_info, struct sock *sk, int timing) +{ + struct smc_prediction *smc_predictor; + int use_fallback, sndbuf, err; + struct smc_sock *smc; + struct tcp_sock *tp; + struct sock *clcsk; + bool match = false; + __u16 wrap, count; + __u32 delivered; + __u16 key; + + /* no info can collect */ + if (sk == NULL) + return; + + /* only fouces on closed */ + if (timing != SMC_SOCK_CLOSED_TIMING) + return; + + /* first check the sk type */ + if (sk->__sk_common.skc_family == AF_SMC) { + smc = smc_sk(sk); + clcsk = BPF_CORE_READ(smc, clcsock, sk); + if (!clcsk) + goto error; + tp = tcp_sk(clcsk); + /* check if it's fallback */ + err = bpf_core_read(&use_fallback, sizeof(use_fallback), &smc->use_fallback); + if (err) + goto error; + if (use_fallback) + goto fallback; + err = bpf_core_read(&wrap, sizeof(__u16), &smc->conn.tx_curs_sent.wrap); + if (err) + goto error; + err = bpf_core_read(&count, sizeof(__u16), &smc->conn.tx_curs_sent.count); + if (err) + goto error; + err = bpf_core_read(&sndbuf, sizeof(int), &clcsk->sk_sndbuf); + if (err) + goto error; + match = (count + wrap * sndbuf) > SMC_PREDICTION_LONGCC_BYTES_THRESHOLD; + } else { + smc = NULL; + tp = tcp_sk(sk); + use_fallback = 1; +fallback: + err = bpf_core_read(&delivered, sizeof(delivered), &tp->delivered); + if (err) + goto error; + match = (delivered > SMC_PREDICTION_LONGCC_PACKETS_THRESHOLD); + } + + /* whatever, tp is never NULL */ + err = bpf_core_read(&key, sizeof(__u16), &tp->inet_conn.icsk_inet.sk.__sk_common.skc_num); + if (err) + goto error; + + smc_predictor = smc_prediction_get(key, 0); + if (!smc_predictor) + goto error; + + bpf_spin_lock(&smc_predictor->lock); + smc_predictor->closed_total_cc++; + if (match) { + /* increase stats */ + smc_predictor->closed_long_cc++; + /* try more aggressive */ + if (smc_predictor->pacing_delta > SMC_PREDICTION_MIN_PACING_DELTA) { + if (use_fallback) { + smc_predictor->pacing_delta = max(SMC_PREDICTION_MIN_PACING_DELTA, + (smc_predictor->pacing_delta * 3) >> 2); + } + } + } else if (!use_fallback) { + smc_predictor->pacing_delta <<= 1; + } + bpf_spin_unlock(&smc_predictor->lock); +error: + return; +} + +SEC(".struct_ops") +struct smc_sock_negotiator_ops ops = { + .negotiate = (void *)bpf_smc_negotiate, + .collect_info = (void *)bpf_smc_collect_info, +};