From patchwork Tue Sep 27 12:45:56 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paul Blakey X-Patchwork-Id: 675560 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from archives.nicira.com (archives.nicira.com [96.126.127.54]) by ozlabs.org (Postfix) with ESMTP id 3sk0vM2b0Cz9s4x for ; Tue, 27 Sep 2016 22:46:23 +1000 (AEST) Received: from archives.nicira.com (localhost [127.0.0.1]) by archives.nicira.com (Postfix) with ESMTP id E947A10296; Tue, 27 Sep 2016 05:46:15 -0700 (PDT) X-Original-To: dev@openvswitch.org Delivered-To: dev@openvswitch.org Received: from mx1e3.cudamail.com (mx1.cudamail.com [69.90.118.67]) by archives.nicira.com (Postfix) with ESMTPS id 656F110244 for ; Tue, 27 Sep 2016 05:46:13 -0700 (PDT) Received: from bar5.cudamail.com (localhost [127.0.0.1]) by mx1e3.cudamail.com (Postfix) with ESMTPS id CEA124203D7 for ; Tue, 27 Sep 2016 06:46:12 -0600 (MDT) X-ASG-Debug-ID: 1474980371-09eadd6290116920001-byXFYA Received: from mx1-pf2.cudamail.com ([192.168.24.2]) by bar5.cudamail.com with ESMTP id gS9wNnH5V2w2Eqjk (version=TLSv1 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO) for ; Tue, 27 Sep 2016 06:46:11 -0600 (MDT) X-Barracuda-Envelope-From: paulb@mellanox.com X-Barracuda-RBL-Trusted-Forwarder: 192.168.24.2 Received: from unknown (HELO mellanox.co.il) (193.47.165.129) by mx1-pf2.cudamail.com with SMTP; 27 Sep 2016 12:46:11 -0000 Received-SPF: pass (mx1-pf2.cudamail.com: SPF record at _mtablock1.salesforce.com designates 193.47.165.129 as permitted sender) X-Barracuda-Apparent-Source-IP: 193.47.165.129 X-Barracuda-RBL-IP: 193.47.165.129 Received: from Internal Mail-Server by MTLPINE1 (envelope-from paulb@mellanox.com) with ESMTPS (AES256-SHA encrypted); 27 Sep 2016 15:46:06 +0300 Received: from r-vnc04.mtr.labs.mlnx (r-vnc04.mtr.labs.mlnx [10.208.0.116]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id u8RCk6Is028432; Tue, 27 Sep 2016 15:46:06 +0300 X-CudaMail-Envelope-Sender: paulb@mellanox.com From: Paul Blakey To: dev@openvswitch.org X-CudaMail-MID: CM-E2-926012581 X-CudaMail-DTE: 092716 X-CudaMail-Originating-IP: 193.47.165.129 Date: Tue, 27 Sep 2016 15:45:56 +0300 X-ASG-Orig-Subj: [##CM-E2-926012581##][PATCH ovs RFC 1/9] dpif-hw-netlink: New dpif provider Message-Id: <1474980364-9291-2-git-send-email-paulb@mellanox.com> X-Mailer: git-send-email 1.7.8.2 In-Reply-To: <1474980364-9291-1-git-send-email-paulb@mellanox.com> References: <1474980364-9291-1-git-send-email-paulb@mellanox.com> X-GBUdb-Analysis: 0, 193.47.165.129, Ugly c=0.271956 p=0 Source Normal X-MessageSniffer-Rules: 0-0-0-32484-c X-Barracuda-Connect: UNKNOWN[192.168.24.2] X-Barracuda-Start-Time: 1474980371 X-Barracuda-Encrypted: DHE-RSA-AES256-SHA X-Barracuda-URL: https://web.cudamail.com:443/cgi-mod/mark.cgi X-Virus-Scanned: by bsmtpd at cudamail.com X-Barracuda-BRTS-Status: 1 X-Barracuda-Spam-Score: 0.60 X-Barracuda-Spam-Status: No, SCORE=0.60 using global scores of TAG_LEVEL=3.5 QUARANTINE_LEVEL=1000.0 KILL_LEVEL=4.0 tests=BSF_SC5_MJ1963, RDNS_NONE, UNPARSEABLE_RELAY X-Barracuda-Spam-Report: Code version 3.2, rules version 3.2.3.33260 Rule breakdown below pts rule name description ---- ---------------------- -------------------------------------------------- 0.00 UNPARSEABLE_RELAY Informational: message has unparseable relay lines 0.10 RDNS_NONE Delivered to trusted network by a host with no rDNS 0.50 BSF_SC5_MJ1963 Custom Rule MJ1963 Cc: Shahar Klein , Andy Gospodarek , Rony Efraim , Paul Blakey , Simon Horman , Or Gerlitz Subject: [ovs-dev] [PATCH ovs RFC 1/9] dpif-hw-netlink: New dpif provider X-BeenThere: dev@openvswitch.org X-Mailman-Version: 2.1.16 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Errors-To: dev-bounces@openvswitch.org Sender: "dev" Add infrastructure for a new provider that will be able to send some flows to the HW for offloading. Signed-off-by: Shahar Klein Signed-off-by: Paul Blakey --- lib/automake.mk | 2 + lib/dpif-hw-netlink.c | 463 ++++++++++++++++++++++++++++++++++++++++++++++++++ lib/dpif-hw-netlink.h | 31 ++++ lib/dpif-provider.h | 1 + lib/dpif.c | 1 + 5 files changed, 498 insertions(+) create mode 100644 lib/dpif-hw-netlink.c create mode 100644 lib/dpif-hw-netlink.h diff --git a/lib/automake.mk b/lib/automake.mk index 5387d51..5c517b7 100644 --- a/lib/automake.mk +++ b/lib/automake.mk @@ -341,6 +341,8 @@ if LINUX lib_libopenvswitch_la_SOURCES += \ lib/dpif-netlink.c \ lib/dpif-netlink.h \ + lib/dpif-hw-netlink.c \ + lib/dpif-hw-netlink.h \ lib/if-notifier.c \ lib/if-notifier.h \ lib/netdev-linux.c \ diff --git a/lib/dpif-hw-netlink.c b/lib/dpif-hw-netlink.c new file mode 100644 index 0000000..5281de7 --- /dev/null +++ b/lib/dpif-hw-netlink.c @@ -0,0 +1,463 @@ + +#include + +#include "dpif-netlink.h" + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "bitmap.h" +#include "dpif-provider.h" +#include "dynamic-string.h" +#include "flow.h" +#include "fat-rwlock.h" +#include "netdev.h" +#include "netdev-linux.h" +#include "netdev-vport.h" +#include "netlink-conntrack.h" +#include "netlink-notifier.h" +#include "netlink-socket.h" +#include "netlink.h" +#include "odp-util.h" +#include "ofpbuf.h" +#include "packets.h" +#include "poll-loop.h" +#include "random.h" +#include "shash.h" +#include "sset.h" +#include "timeval.h" +#include "unaligned.h" +#include "util.h" +#include "openvswitch/vlog.h" +#include "dpif-hw-netlink.h" + +VLOG_DEFINE_THIS_MODULE(dpif_hw_netlink); + +static struct dpif_hw_netlink * +dpif_hw_netlink_cast(const struct dpif *dpif) +{ + dpif_assert_class(dpif, &dpif_hw_netlink_class); + return CONTAINER_OF(dpif, struct dpif_hw_netlink, dpif); +} + +static int +dpif_hw_netlink_open(const struct dpif_class *class OVS_UNUSED, + const char *name, bool create, struct dpif **dpifp) +{ + struct dpif_hw_netlink *dpif; + struct dpif *lp_dpif_netlink; + + if (dpif_create_and_open(name, "system", &lp_dpif_netlink)) { + VLOG_WARN("ERROR! %d\n", __LINE__); + } + + dpif = xzalloc(sizeof *dpif); + + *CONST_CAST(const char **, &dpif->name) = xstrdup(name); + uint16_t netflow_id = hash_string(dpif->name, 0); + + dpif->lp_dpif_netlink = lp_dpif_netlink; + + dpif_init(&dpif->dpif, &dpif_hw_netlink_class, dpif->name, netflow_id >> 8, + netflow_id); + + *dpifp = &dpif->dpif; + + return 0; +} + +static void +dpif_hw_netlink_close(struct dpif *dpif_) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class->close(dpif->lp_dpif_netlink); +} + +static int +dpif_hw_netlink_destroy(struct dpif *dpif_) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class->destroy(dpif->lp_dpif_netlink); +} + +static bool +dpif_hw_netlink_run(struct dpif *dpif_) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class->run(dpif->lp_dpif_netlink); +} + +static int +dpif_hw_netlink_get_stats(const struct dpif *dpif_, + struct dpif_dp_stats *stats) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class->get_stats(dpif->lp_dpif_netlink, + stats); +} + +static int +dpif_hw_netlink_port_add(struct dpif *dpif_, struct netdev *netdev, + odp_port_t * port_nop) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class->port_add(dpif->lp_dpif_netlink, + netdev, port_nop); +} + +static int +dpif_hw_netlink_port_del(struct dpif *dpif_, odp_port_t port_no) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class->port_del(dpif->lp_dpif_netlink, + port_no); +} + +static int +dpif_hw_netlink_port_query_by_number(const struct dpif *dpif_, + odp_port_t port_no, + struct dpif_port *dpif_port) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class-> + port_query_by_number(dpif->lp_dpif_netlink, port_no, dpif_port); +} + +static int +dpif_hw_netlink_port_query_by_name(const struct dpif *dpif_, + const char *devname, + struct dpif_port *dpif_port) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class-> + port_query_by_name(dpif->lp_dpif_netlink, devname, dpif_port); +} + +static uint32_t +dpif_hw_netlink_port_get_pid(const struct dpif *dpif_, odp_port_t port_no, + uint32_t hash) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class-> + port_get_pid(dpif->lp_dpif_netlink, port_no, hash); +} + +static int +dpif_hw_netlink_port_dump_start(const struct dpif *dpif_, void **statep) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class-> + port_dump_start(dpif->lp_dpif_netlink, statep); +} + +static int +dpif_hw_netlink_port_dump_next(const struct dpif *dpif_, void *state_, + struct dpif_port *dpif_port) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class-> + port_dump_next(dpif->lp_dpif_netlink, state_, dpif_port); +} + +static int +dpif_hw_netlink_port_dump_done(const struct dpif *dpif_ OVS_UNUSED, + void *state_) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class-> + port_dump_done(dpif->lp_dpif_netlink, state_); +} + +static int +dpif_hw_netlink_port_poll(const struct dpif *dpif_, char **devnamep) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class->port_poll(dpif->lp_dpif_netlink, + devnamep); +} + +static void +dpif_hw_netlink_port_poll_wait(const struct dpif *dpif_) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class-> + port_poll_wait(dpif->lp_dpif_netlink); +} + +static int +dpif_hw_netlink_flow_flush(struct dpif *dpif_) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class-> + flow_flush(dpif->lp_dpif_netlink); +} + +static struct dpif_flow_dump * +dpif_hw_netlink_flow_dump_create(const struct dpif *dpif_, bool terse) +{ + struct dpif_flow_dump *dump; + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + dump = + dpif->lp_dpif_netlink->dpif_class-> + flow_dump_create(dpif->lp_dpif_netlink, terse); + dump->dpif = CONST_CAST(struct dpif *, dpif_); + + return dump; + +} + +static int +dpif_hw_netlink_flow_dump_destroy(struct dpif_flow_dump *dump_) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dump_->dpif); + + dump_->dpif = dpif->lp_dpif_netlink; + return dpif->lp_dpif_netlink->dpif_class->flow_dump_destroy(dump_); +} + +static struct dpif_flow_dump_thread * +dpif_hw_netlink_flow_dump_thread_create(struct dpif_flow_dump *dump_) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dump_->dpif); + + return dpif->lp_dpif_netlink->dpif_class->flow_dump_thread_create(dump_); + +} + +static void +dpif_hw_netlink_flow_dump_thread_destroy(struct dpif_flow_dump_thread *thread_) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(thread_->dpif); + + thread_->dpif = dpif->lp_dpif_netlink; + return dpif->lp_dpif_netlink-> + dpif_class->flow_dump_thread_destroy(thread_); +} + +static int +dpif_hw_netlink_flow_dump_next(struct dpif_flow_dump_thread *thread_, + struct dpif_flow *flows, int max_flows) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(thread_->dpif); + + thread_->dpif = dpif->lp_dpif_netlink; + return dpif->lp_dpif_netlink->dpif_class->flow_dump_next(thread_, flows, + max_flows); +} + +static void +dpif_hw_netlink_operate(struct dpif *dpif_, struct dpif_op **ops, size_t n_ops) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class->operate(dpif->lp_dpif_netlink, + ops, n_ops); +} + +static int +dpif_hw_netlink_recv_set(struct dpif *dpif_, bool enable) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class->recv_set(dpif->lp_dpif_netlink, + enable); +} + +static int +dpif_hw_netlink_handlers_set(struct dpif *dpif_, uint32_t n_handlers) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class-> + handlers_set(dpif->lp_dpif_netlink, n_handlers); +} + +static int +dpif_hw_netlink_queue_to_priority(const struct dpif *dpif_, + uint32_t queue_id, uint32_t * priority) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class-> + queue_to_priority(dpif->lp_dpif_netlink, queue_id, priority); +} + +static int +dpif_hw_netlink_recv(struct dpif *dpif_, uint32_t handler_id, + struct dpif_upcall *upcall, struct ofpbuf *buf) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class->recv(dpif->lp_dpif_netlink, + handler_id, upcall, buf); + +} + +static void +dpif_hw_netlink_recv_wait(struct dpif *dpif_, uint32_t handler_id) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class->recv_wait(dpif->lp_dpif_netlink, + handler_id); +} + +static void +dpif_hw_netlink_recv_purge(struct dpif *dpif_) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class-> + recv_purge(dpif->lp_dpif_netlink); +} + +static char * +dpif_hw_netlink_get_datapath_version(void) +{ + char *version_str = NULL; + +#ifdef __linux__ + +#define MAX_VERSION_STR_SIZE 80 +#define LINUX_DATAPATH_VERSION_FILE "/sys/module/openvswitch/version" + FILE *f; + + f = fopen(LINUX_DATAPATH_VERSION_FILE, "r"); + if (f) { + char *newline; + char version[MAX_VERSION_STR_SIZE]; + + if (fgets(version, MAX_VERSION_STR_SIZE, f)) { + newline = strchr(version, '\n'); + if (newline) { + *newline = '\0'; + } + version_str = xstrdup(version); + } + fclose(f); + } +#endif + + return version_str; +} + +static int +dpif_hw_netlink_ct_dump_start(struct dpif *dpif_, + struct ct_dpif_dump_state **dump_, + const uint16_t * zone) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class-> + ct_dump_start(dpif->lp_dpif_netlink, dump_, zone); +} + +static int +dpif_hw_netlink_ct_dump_next(struct dpif *dpif_, + struct ct_dpif_dump_state *dump_, + struct ct_dpif_entry *entry) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class-> + ct_dump_next(dpif->lp_dpif_netlink, dump_, entry); +} + +static int +dpif_hw_netlink_ct_dump_done(struct dpif *dpif_, + struct ct_dpif_dump_state *dump_) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class-> + ct_dump_done(dpif->lp_dpif_netlink, dump_); +} + +static int +dpif_hw_netlink_ct_flush(struct dpif *dpif_, const uint16_t * zone) +{ + struct dpif_hw_netlink *dpif = dpif_hw_netlink_cast(dpif_); + + return dpif->lp_dpif_netlink->dpif_class->ct_flush(dpif->lp_dpif_netlink, + zone); +} + +const struct dpif_class dpif_hw_netlink_class = { + "hw_netlink", + NULL, /* init */ + NULL, + NULL, + dpif_hw_netlink_open, + dpif_hw_netlink_close, + dpif_hw_netlink_destroy, + dpif_hw_netlink_run, + NULL, /* wait */ + dpif_hw_netlink_get_stats, + dpif_hw_netlink_port_add, + dpif_hw_netlink_port_del, + dpif_hw_netlink_port_query_by_number, + dpif_hw_netlink_port_query_by_name, + dpif_hw_netlink_port_get_pid, + dpif_hw_netlink_port_dump_start, + dpif_hw_netlink_port_dump_next, + dpif_hw_netlink_port_dump_done, + dpif_hw_netlink_port_poll, + dpif_hw_netlink_port_poll_wait, + dpif_hw_netlink_flow_flush, + dpif_hw_netlink_flow_dump_create, + dpif_hw_netlink_flow_dump_destroy, + dpif_hw_netlink_flow_dump_thread_create, + dpif_hw_netlink_flow_dump_thread_destroy, + dpif_hw_netlink_flow_dump_next, + dpif_hw_netlink_operate, + dpif_hw_netlink_recv_set, + dpif_hw_netlink_handlers_set, + NULL, /* poll_thread_set */ + dpif_hw_netlink_queue_to_priority, + dpif_hw_netlink_recv, + dpif_hw_netlink_recv_wait, + dpif_hw_netlink_recv_purge, + NULL, /* register_dp_purge_cb */ + NULL, /* register_upcall_cb */ + NULL, /* enable_upcall */ + NULL, /* disable_upcall */ + dpif_hw_netlink_get_datapath_version, /* get_datapath_version */ +#ifdef __linux__ + dpif_hw_netlink_ct_dump_start, + dpif_hw_netlink_ct_dump_next, + dpif_hw_netlink_ct_dump_done, + dpif_hw_netlink_ct_flush, +#else + NULL, /* ct_dump_start */ + NULL, /* ct_dump_next */ + NULL, /* ct_dump_done */ + NULL, /* ct_flush */ +#endif +}; diff --git a/lib/dpif-hw-netlink.h b/lib/dpif-hw-netlink.h new file mode 100644 index 0000000..42f203e --- /dev/null +++ b/lib/dpif-hw-netlink.h @@ -0,0 +1,31 @@ +#ifndef DPIF_HW_NETLINK_H +#define DPIF_HW_NETLINK_H 1 + +#include "ovs-thread.h" +#include "hmap.h" +#include "dpif-provider.h" + +/* Datapath interface for the openvswitch Linux kernel module. */ +struct dpif_hw_netlink { + struct dpif dpif; + struct dpif *lp_dpif_netlink; + const char *const name; +}; + +struct port_netdev_hash_data { + struct hmap_node node; + struct netdev *netdev; + odp_port_t port; +}; + +struct ufid_handle_hash_data { + struct hmap_node node_ufid; + struct hmap_node node_handle; + ovs_u128 ovs_ufid; + int handle; + int protocol; + struct netdev *netdev; + odp_port_t port; +}; + +#endif diff --git a/lib/dpif-provider.h b/lib/dpif-provider.h index a9844be..ccd016c 100644 --- a/lib/dpif-provider.h +++ b/lib/dpif-provider.h @@ -423,6 +423,7 @@ struct dpif_class { extern const struct dpif_class dpif_netlink_class; extern const struct dpif_class dpif_netdev_class; +extern const struct dpif_class dpif_hw_netlink_class; #ifdef __cplusplus } diff --git a/lib/dpif.c b/lib/dpif.c index 38e40ba..e9399f3 100644 --- a/lib/dpif.c +++ b/lib/dpif.c @@ -67,6 +67,7 @@ COVERAGE_DEFINE(dpif_execute_with_help); static const struct dpif_class *base_dpif_classes[] = { #if defined(__linux__) || defined(_WIN32) &dpif_netlink_class, + &dpif_hw_netlink_class, #endif &dpif_netdev_class, };