From patchwork Wed Dec 20 14:44:33 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yuanhan Liu X-Patchwork-Id: 851500 X-Patchwork-Delegate: ian.stokes@intel.com Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (mailfrom) smtp.mailfrom=openvswitch.org (client-ip=140.211.169.12; helo=mail.linuxfoundation.org; envelope-from=ovs-dev-bounces@openvswitch.org; receiver=) Authentication-Results: ozlabs.org; dkim=fail reason="signature verification failed" (2048-bit key; unprotected) header.d=fridaylinux.org header.i=@fridaylinux.org header.b="t9DhqoDo"; dkim=fail reason="signature verification failed" (2048-bit key; unprotected) header.d=messagingengine.com header.i=@messagingengine.com header.b="NSaI7NfX"; dkim-atps=neutral Received: from mail.linuxfoundation.org (mail.linuxfoundation.org [140.211.169.12]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 3z1yHR44tsz9s7F for ; Thu, 21 Dec 2017 01:45:23 +1100 (AEDT) Received: from mail.linux-foundation.org (localhost [127.0.0.1]) by mail.linuxfoundation.org (Postfix) with ESMTP id D17FCC84; Wed, 20 Dec 2017 14:44:59 +0000 (UTC) X-Original-To: dev@openvswitch.org Delivered-To: ovs-dev@mail.linuxfoundation.org Received: from smtp1.linuxfoundation.org (smtp1.linux-foundation.org [172.17.192.35]) by mail.linuxfoundation.org (Postfix) with ESMTPS id 557A7C7D for ; Wed, 20 Dec 2017 14:44:59 +0000 (UTC) X-Greylist: from auto-whitelisted by SQLgrey-1.7.6 Received: from out3-smtp.messagingengine.com (out3-smtp.messagingengine.com [66.111.4.27]) by smtp1.linuxfoundation.org (Postfix) with ESMTPS id 321C73D9 for ; Wed, 20 Dec 2017 14:44:58 +0000 (UTC) Received: from compute1.internal (compute1.nyi.internal [10.202.2.41]) by mailout.nyi.internal (Postfix) with ESMTP id 7BAEB20977; Wed, 20 Dec 2017 09:44:57 -0500 (EST) Received: from frontend1 ([10.202.2.160]) by compute1.internal (MEProxy); Wed, 20 Dec 2017 09:44:57 -0500 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=fridaylinux.org; h=cc:date:from:in-reply-to:message-id:references:subject:to :x-me-sender:x-me-sender:x-sasl-enc; s=fm1; bh=k47hpL2fMQIcQQbb7 ozhgSfIsWoX2DWohE0Pi4LJ0n0=; b=t9DhqoDoZMzZttgZyqKNcj0WB5k/nkKUb nQEv/rUhFHDp5e0dqQ+CWMDqCFZBBNyVVmoRf2vAEKPH8BxZAwS4snq8Q5xus63I WhL2xVPZ0cTuZs3PsVB11+zccThURywIxLjTC/jOviUjPGar4w/HBfTNrdO8ibhK dsO3Q1wi4/8OO9QVit/sjHNza1cOj8gBVVazDLuP9O3f8sD1rXfovCwz9GEMl8ps mxWSVdy7c/p67hkCZ3BBnpQLjC8YTaTY7cnbBm83epQiVZbpk9YCeQS/1WlVSqo4 pxbv6aVCgf+myxhzCljBENKWwsCSeMalPExDqYg0ThMwOLVCFgRqg== DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:date:from:in-reply-to:message-id :references:subject:to:x-me-sender:x-me-sender:x-sasl-enc; s= fm1; bh=k47hpL2fMQIcQQbb7ozhgSfIsWoX2DWohE0Pi4LJ0n0=; b=NSaI7NfX kWOuP93qLwF0Q8rq/3rvYUhhIqtYSTAN849iCgCPFckSnK3kNqgysk3AY3KyI2Ko 5C4PO1ndkPKv0xFJLsUki5EoshrmLsK7GPmIZoC8xxs+mtQdA+W3KyxVC8BCVAbq ZEVwl8C+cWythzLXhGGhIfUywySpSPJLjtwZW9vw3KZDx1wyW7TKKBIJS+L+ebFb cZdmerxy1DP0ZrFKYj+K6eu6oqQiyPlaxeMgotyMp5XXMY/xiudmrJN7bTDCwXbl 3ka59nasu0RnTUjyRdNonqAv5jqHw0yjJYA56JnWCZzXcOU3yu1J5Wn6pbK3his3 7+6S0CjDLepEGA== X-ME-Sender: Received: from yliu-dev.mtl.com (unknown [115.148.91.103]) by mail.messagingengine.com (Postfix) with ESMTPA id 912BE7E3D4; Wed, 20 Dec 2017 09:44:50 -0500 (EST) From: Yuanhan Liu To: dev@openvswitch.org Date: Wed, 20 Dec 2017 22:44:33 +0800 Message-Id: <1513781077-21984-2-git-send-email-yliu@fridaylinux.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1513781077-21984-1-git-send-email-yliu@fridaylinux.org> References: <1513781077-21984-1-git-send-email-yliu@fridaylinux.org> X-Spam-Status: No, score=-2.7 required=5.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, RCVD_IN_DNSWL_LOW autolearn=ham version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on smtp1.linux-foundation.org Cc: Simon Horman Subject: [ovs-dev] [PATCH v5 1/5] dpif-netdev: associate flow with a mark id X-BeenThere: ovs-dev@openvswitch.org X-Mailman-Version: 2.1.12 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Sender: ovs-dev-bounces@openvswitch.org Errors-To: ovs-dev-bounces@openvswitch.org Most modern NICs have the ability to bind a flow with a mark, so that every pkt matches such flow will have that mark present in its desc. The basic idea of doing that is, when we receives pkts later, we could directly get the flow from the mark. That could avoid some very costly CPU operations, including (but not limiting to) miniflow_extract, emc lookup, dpcls lookup, etc. Thus, performance could be greatly improved. Thus, the mojor work of this patch is to associate a flow with a mark id (an uint32_t number). The association in netdev datapatch is done by CMAP, while in hardware it's done by the rte_flow MARK action. One tricky thing in OVS-DPDK is, the flow tables is per-PMD. For the case there is only one phys port but with 2 queues, there could be 2 PMDs. In another word, even for a single mega flow (i.e. udp,tp_src=1000), there could be 2 different dp_netdev flows, one for each PMD. That could results to the same mega flow being offloaded twice in the hardware, worse, we may get 2 different marks and only the last one will work. To avoid that, a megaflow_to_mark CMAP is created. An entry will be added for the first PMD wants to offload a flow. For later PMDs, it will see such megaflow is already offloaded, then the flow will not be offloaded to HW twice. Meanwhile, the mark to flow mapping becomes to 1:N mapping. That is what the mark_to_flow CMAP for. For the first PMD wants to offload a flow, it allocates a new mark and do the flow offload by reusing the ->flow_put method. When it succeeds, a "mark to flow" entry will be added. For later PMDs, it will get the corresponding mark by above megaflow_to_mark CMAP. Then, another "mark to flow" entry will be added. Another thing might worth mentioning is that hte megaflow is created by masking all the bytes from match->flow with match->wc. It works well so far, but I have a feeling that is not the best way. Co-authored-by: Finn Christensen Signed-off-by: Yuanhan Liu Signed-off-by: Finn Christensen --- v5: - fixed check of flow_mark_has_no_ref (renamed from is_last_flow_mark_reference). This fixed an issue that it took too long to finish flow add/removal if we do that repeatdly. - do mark_to_flow disassociation if flow modification failed --- lib/dpif-netdev.c | 263 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ lib/netdev.h | 6 ++ 2 files changed, 269 insertions(+) diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c index 55be632..2fdc8dd 100644 --- a/lib/dpif-netdev.c +++ b/lib/dpif-netdev.c @@ -77,6 +77,7 @@ #include "tnl-ports.h" #include "unixctl.h" #include "util.h" +#include "uuid.h" VLOG_DEFINE_THIS_MODULE(dpif_netdev); @@ -442,7 +443,9 @@ struct dp_netdev_flow { /* Hash table index by unmasked flow. */ const struct cmap_node node; /* In owning dp_netdev_pmd_thread's */ /* 'flow_table'. */ + const struct cmap_node mark_node; /* In owning flow_mark's mark_to_flow */ const ovs_u128 ufid; /* Unique flow identifier. */ + const ovs_u128 mega_ufid; const unsigned pmd_id; /* The 'core_id' of pmd thread owning this */ /* flow. */ @@ -453,6 +456,7 @@ struct dp_netdev_flow { struct ovs_refcount ref_cnt; bool dead; + uint32_t mark; /* Unique flow mark assiged to a flow */ /* Statistics. */ struct dp_netdev_flow_stats stats; @@ -1832,6 +1836,172 @@ dp_netdev_pmd_find_dpcls(struct dp_netdev_pmd_thread *pmd, return cls; } +#define MAX_FLOW_MARK (UINT32_MAX - 1) +#define INVALID_FLOW_MARK (UINT32_MAX) + +struct megaflow_to_mark_data { + const struct cmap_node node; + ovs_u128 mega_ufid; + uint32_t mark; +}; + +struct flow_mark { + struct cmap megaflow_to_mark; + struct cmap mark_to_flow; + struct id_pool *pool; + struct ovs_mutex mutex; +}; + +struct flow_mark flow_mark = { + .megaflow_to_mark = CMAP_INITIALIZER, + .mark_to_flow = CMAP_INITIALIZER, + .mutex = OVS_MUTEX_INITIALIZER, +}; + +static uint32_t +flow_mark_alloc(void) +{ + uint32_t mark; + + if (!flow_mark.pool) { + /* Haven't initiated yet, do it here */ + flow_mark.pool = id_pool_create(0, MAX_FLOW_MARK); + } + + if (id_pool_alloc_id(flow_mark.pool, &mark)) { + return mark; + } + + return INVALID_FLOW_MARK; +} + +static void +flow_mark_free(uint32_t mark) +{ + id_pool_free_id(flow_mark.pool, mark); +} + +/* associate flow with a mark, which is a 1:1 mapping */ +static void +megaflow_to_mark_associate(const ovs_u128 *mega_ufid, uint32_t mark) +{ + size_t hash = dp_netdev_flow_hash(mega_ufid); + struct megaflow_to_mark_data *data = xzalloc(sizeof(*data)); + + data->mega_ufid = *mega_ufid; + data->mark = mark; + + cmap_insert(&flow_mark.megaflow_to_mark, + CONST_CAST(struct cmap_node *, &data->node), hash); +} + +/* disassociate flow with a mark */ +static void +megaflow_to_mark_disassociate(const ovs_u128 *mega_ufid) +{ + size_t hash = dp_netdev_flow_hash(mega_ufid); + struct megaflow_to_mark_data *data; + + CMAP_FOR_EACH_WITH_HASH (data, node, hash, &flow_mark.megaflow_to_mark) { + if (ovs_u128_equals(*mega_ufid, data->mega_ufid)) { + cmap_remove(&flow_mark.megaflow_to_mark, + CONST_CAST(struct cmap_node *, &data->node), hash); + free(data); + return; + } + } + + VLOG_WARN("masked ufid "UUID_FMT" is not associated with a mark?\n", + UUID_ARGS((struct uuid *)mega_ufid)); +} + +static inline uint32_t +megaflow_to_mark_find(const ovs_u128 *mega_ufid) +{ + size_t hash = dp_netdev_flow_hash(mega_ufid); + struct megaflow_to_mark_data *data; + + CMAP_FOR_EACH_WITH_HASH (data, node, hash, &flow_mark.megaflow_to_mark) { + if (ovs_u128_equals(*mega_ufid, data->mega_ufid)) { + return data->mark; + } + } + + return INVALID_FLOW_MARK; +} + +/* associate mark with a flow, which is 1:N mapping */ +static void +mark_to_flow_associate(const uint32_t mark, struct dp_netdev_flow *flow) +{ + dp_netdev_flow_ref(flow); + + cmap_insert(&flow_mark.mark_to_flow, + CONST_CAST(struct cmap_node *, &flow->mark_node), + mark); + flow->mark = mark; + + VLOG_DBG("associated dp_netdev flow %p with mark %u\n", flow, mark); +} + +static bool +flow_mark_has_no_ref(uint32_t mark) +{ + struct dp_netdev_flow *flow; + + CMAP_FOR_EACH_WITH_HASH (flow, mark_node, mark, + &flow_mark.mark_to_flow) { + if (flow->mark == mark) { + return false; + } + } + + return true; +} + +static int +mark_to_flow_disassociate(struct dp_netdev_pmd_thread *pmd, + struct dp_netdev_flow *flow) +{ + int ret = 0; + uint32_t mark = flow->mark; + struct cmap_node *mark_node = CONST_CAST(struct cmap_node *, + &flow->mark_node); + + cmap_remove(&flow_mark.mark_to_flow, mark_node, mark); + flow->mark = INVALID_FLOW_MARK; + + if (flow_mark_has_no_ref(mark)) { + struct dp_netdev_port *port; + odp_port_t in_port = flow->flow.in_port.odp_port; + + port = dp_netdev_lookup_port(pmd->dp, in_port); + if (port) { + ret = netdev_flow_del(port->netdev, &flow->mega_ufid, NULL); + } + + flow_mark_free(mark); + VLOG_DBG("freed flow mark %u\n", mark); + + megaflow_to_mark_disassociate(&flow->mega_ufid); + } + dp_netdev_flow_unref(flow); + + return ret; +} + +static void +flow_mark_flush(struct dp_netdev_pmd_thread *pmd) +{ + struct dp_netdev_flow *flow; + + CMAP_FOR_EACH (flow, mark_node, &flow_mark.mark_to_flow) { + if (flow->pmd_id == pmd->core_id) { + mark_to_flow_disassociate(pmd, flow); + } + } +} + static void dp_netdev_pmd_remove_flow(struct dp_netdev_pmd_thread *pmd, struct dp_netdev_flow *flow) @@ -1845,6 +2015,9 @@ dp_netdev_pmd_remove_flow(struct dp_netdev_pmd_thread *pmd, ovs_assert(cls != NULL); dpcls_remove(cls, &flow->cr); cmap_remove(&pmd->flow_table, node, dp_netdev_flow_hash(&flow->ufid)); + if (flow->mark != INVALID_FLOW_MARK) { + mark_to_flow_disassociate(pmd, flow); + } flow->dead = true; dp_netdev_flow_unref(flow); @@ -2424,6 +2597,87 @@ out: return error; } +static void +try_netdev_flow_put(struct dp_netdev_pmd_thread *pmd, odp_port_t in_port, + struct dp_netdev_flow *flow, struct match *match, + const struct nlattr *actions, size_t actions_len) +{ + struct offload_info info; + struct dp_netdev_port *port; + bool modification = flow->mark != INVALID_FLOW_MARK; + const char *op = modification ? "modify" : "add"; + uint32_t mark; + int ret; + + port = dp_netdev_lookup_port(pmd->dp, in_port); + if (!port) { + return; + } + + ovs_mutex_lock(&flow_mark.mutex); + + if (modification) { + mark = flow->mark; + } else { + if (!netdev_is_flow_api_enabled()) { + goto out; + } + + /* + * If a mega flow has already been offloaded (from other PMD + * instances), do not offload it again. + */ + mark = megaflow_to_mark_find(&flow->mega_ufid); + if (mark != INVALID_FLOW_MARK) { + VLOG_DBG("flow has already been offloaded with mark %u\n", mark); + mark_to_flow_associate(mark, flow); + goto out; + } + + mark = flow_mark_alloc(); + if (mark == INVALID_FLOW_MARK) { + VLOG_ERR("failed to allocate flow mark!\n"); + goto out; + } + } + + info.flow_mark = mark; + ret = netdev_flow_put(port->netdev, match, + CONST_CAST(struct nlattr *, actions), + actions_len, &flow->mega_ufid, &info, NULL); + if (ret) { + VLOG_ERR("failed to %s netdev flow with mark %u\n", op, mark); + if (!modification) { + flow_mark_free(mark); + } else { + mark_to_flow_disassociate(pmd, flow); + } + goto out; + } + + if (!modification) { + megaflow_to_mark_associate(&flow->mega_ufid, mark); + mark_to_flow_associate(mark, flow); + } + VLOG_DBG("succeed to %s netdev flow with mark %u\n", op, mark); + +out: + ovs_mutex_unlock(&flow_mark.mutex); +} + +static void +dp_netdev_get_mega_ufid(const struct match *match, ovs_u128 *mega_ufid) +{ + struct flow masked_flow; + size_t i; + + for (i = 0; i < sizeof(struct flow); i++) { + ((uint8_t *)&masked_flow)[i] = ((uint8_t *)&match->flow)[i] & + ((uint8_t *)&match->wc)[i]; + } + dpif_flow_hash(NULL, &masked_flow, sizeof(struct flow), mega_ufid); +} + static struct dp_netdev_flow * dp_netdev_flow_add(struct dp_netdev_pmd_thread *pmd, struct match *match, const ovs_u128 *ufid, @@ -2459,12 +2713,14 @@ dp_netdev_flow_add(struct dp_netdev_pmd_thread *pmd, memset(&flow->stats, 0, sizeof flow->stats); flow->dead = false; flow->batch = NULL; + flow->mark = INVALID_FLOW_MARK; *CONST_CAST(unsigned *, &flow->pmd_id) = pmd->core_id; *CONST_CAST(struct flow *, &flow->flow) = match->flow; *CONST_CAST(ovs_u128 *, &flow->ufid) = *ufid; ovs_refcount_init(&flow->ref_cnt); ovsrcu_set(&flow->actions, dp_netdev_actions_create(actions, actions_len)); + dp_netdev_get_mega_ufid(match, CONST_CAST(ovs_u128 *, &flow->mega_ufid)); netdev_flow_key_init_masked(&flow->cr.flow, &match->flow, &mask); /* Select dpcls for in_port. Relies on in_port to be exact match. */ @@ -2474,6 +2730,8 @@ dp_netdev_flow_add(struct dp_netdev_pmd_thread *pmd, cmap_insert(&pmd->flow_table, CONST_CAST(struct cmap_node *, &flow->node), dp_netdev_flow_hash(&flow->ufid)); + try_netdev_flow_put(pmd, in_port, flow, match, actions, actions_len); + if (OVS_UNLIKELY(!VLOG_DROP_DBG((&upcall_rl)))) { struct ds ds = DS_EMPTY_INITIALIZER; struct ofpbuf key_buf, mask_buf; @@ -2554,6 +2812,7 @@ flow_put_on_pmd(struct dp_netdev_pmd_thread *pmd, if (put->flags & DPIF_FP_MODIFY) { struct dp_netdev_actions *new_actions; struct dp_netdev_actions *old_actions; + odp_port_t in_port = netdev_flow->flow.in_port.odp_port; new_actions = dp_netdev_actions_create(put->actions, put->actions_len); @@ -2561,6 +2820,9 @@ flow_put_on_pmd(struct dp_netdev_pmd_thread *pmd, old_actions = dp_netdev_flow_get_actions(netdev_flow); ovsrcu_set(&netdev_flow->actions, new_actions); + try_netdev_flow_put(pmd, in_port, netdev_flow, match, + put->actions, put->actions_len); + if (stats) { get_dpif_flow_stats(netdev_flow, stats); } @@ -3570,6 +3832,7 @@ reload_affected_pmds(struct dp_netdev *dp) CMAP_FOR_EACH (pmd, node, &dp->poll_threads) { if (pmd->need_reload) { + flow_mark_flush(pmd); dp_netdev_reload_pmd__(pmd); pmd->need_reload = false; } diff --git a/lib/netdev.h b/lib/netdev.h index 3a545fe..0c1946a 100644 --- a/lib/netdev.h +++ b/lib/netdev.h @@ -188,6 +188,12 @@ void netdev_send_wait(struct netdev *, int qid); struct offload_info { const struct dpif_class *dpif_class; ovs_be16 tp_dst_port; /* Destination port for tunnel in SET action */ + + /* + * The flow mark id assigened to the flow. If any pkts hit the flow, + * it will be in the pkt meta data. + */ + uint32_t flow_mark; }; struct dpif_class; struct netdev_flow_dump; From patchwork Wed Dec 20 14:44:34 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yuanhan Liu X-Patchwork-Id: 851501 X-Patchwork-Delegate: ian.stokes@intel.com Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (mailfrom) smtp.mailfrom=openvswitch.org (client-ip=140.211.169.12; helo=mail.linuxfoundation.org; envelope-from=ovs-dev-bounces@openvswitch.org; receiver=) Authentication-Results: ozlabs.org; dkim=fail reason="signature verification failed" (2048-bit key; unprotected) header.d=fridaylinux.org header.i=@fridaylinux.org header.b="m2IfeWxe"; dkim=fail reason="signature verification failed" (2048-bit key; unprotected) header.d=messagingengine.com header.i=@messagingengine.com header.b="o+4TVQbz"; dkim-atps=neutral Received: from mail.linuxfoundation.org (mail.linuxfoundation.org [140.211.169.12]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 3z1yJF30RJz9s7F for ; Thu, 21 Dec 2017 01:46:05 +1100 (AEDT) Received: from mail.linux-foundation.org (localhost [127.0.0.1]) by mail.linuxfoundation.org (Postfix) with ESMTP id 2680FC9A; Wed, 20 Dec 2017 14:45:10 +0000 (UTC) X-Original-To: dev@openvswitch.org Delivered-To: ovs-dev@mail.linuxfoundation.org Received: from smtp1.linuxfoundation.org (smtp1.linux-foundation.org [172.17.192.35]) by mail.linuxfoundation.org (Postfix) with ESMTPS id 27BA9C8A for ; Wed, 20 Dec 2017 14:45:09 +0000 (UTC) X-Greylist: from auto-whitelisted by SQLgrey-1.7.6 Received: from out3-smtp.messagingengine.com (out3-smtp.messagingengine.com [66.111.4.27]) by smtp1.linuxfoundation.org (Postfix) with ESMTPS id 3B5753D9 for ; Wed, 20 Dec 2017 14:45:08 +0000 (UTC) Received: from compute1.internal (compute1.nyi.internal [10.202.2.41]) by mailout.nyi.internal (Postfix) with ESMTP id 8520F20B56; Wed, 20 Dec 2017 09:45:07 -0500 (EST) Received: from frontend1 ([10.202.2.160]) by compute1.internal (MEProxy); Wed, 20 Dec 2017 09:45:07 -0500 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=fridaylinux.org; h=cc:date:from:in-reply-to:message-id:references:subject:to :x-me-sender:x-me-sender:x-sasl-enc; s=fm1; bh=k6LI+iaO34anmqzq0 jcvM8yqbsdDUQZe+6HMl7JI+XE=; b=m2IfeWxe1L0HofAtqvDLyGX0B0nQjrYOD rMlXDtuVo6mJtu1QpuNzbqydlQZs9edV4zAWr0OU4t5Uml6SduuKiUfuuqsX6X9u HVr/iLboZ9e5EX0Toa+C9OtJSin9tw6Mozd9r4fwsjdMn03HKa4Iekqz7cJitcj2 24hiWP3MxApguk6yFovesz9c37sWibdhpvR91QlqEf/Xaaz/MsTMOcXzQDuSVDoZ 7T+aplA8H2WQylzhYw9OQx1Cl2iiptsR49RdTY5ZbzMotXm8evdiehgg8T7roWDi vPy/a0fu2cVOeA3Jt9mGW9CckpA4XEW1F+wYF3Pd2rvA46Zm5Kl3A== DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:date:from:in-reply-to:message-id :references:subject:to:x-me-sender:x-me-sender:x-sasl-enc; s= fm1; bh=k6LI+iaO34anmqzq0jcvM8yqbsdDUQZe+6HMl7JI+XE=; b=o+4TVQbz nRHf4yxD5kBcYfbgqcj3Bs7KvjZxhv+geJcfDQolJInN1riVDp+MGlkj4cuQEQAZ 6Lm8/yzHGi7WbDAhwgxdOQjs4nPM3s/Z0I+Hu10k2bCGXoRhx9j+q/zMPbQIzz6M K5YXBImJIuKvLZCNvUhsDMF6m3zdOu2DmSG3bBf29mG/s/JoMfG3P/NjxkskcxnL wHbz3L8l/XAqzBT+eVg5UbQemhEDc7wpb9hhzqmSj9423LdVrYld2D9J7ycmQkUK 5r3A41qFqFQDWGLBT7E6/Dajhc/MjL0hyF1I4dqYjDjZUrspSVXdf68dFhwfERwR umBaynsuSO8+OA== X-ME-Sender: Received: from yliu-dev.mtl.com (unknown [115.148.91.103]) by mail.messagingengine.com (Postfix) with ESMTPA id 2AD847E68C; Wed, 20 Dec 2017 09:44:57 -0500 (EST) From: Yuanhan Liu To: dev@openvswitch.org Date: Wed, 20 Dec 2017 22:44:34 +0800 Message-Id: <1513781077-21984-3-git-send-email-yliu@fridaylinux.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1513781077-21984-1-git-send-email-yliu@fridaylinux.org> References: <1513781077-21984-1-git-send-email-yliu@fridaylinux.org> X-Spam-Status: No, score=-2.7 required=5.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, RCVD_IN_DNSWL_LOW autolearn=ham version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on smtp1.linux-foundation.org Cc: Simon Horman Subject: [ovs-dev] [PATCH v5 2/5] dpif-netdev: retrieve flow directly from the flow mark X-BeenThere: ovs-dev@openvswitch.org X-Mailman-Version: 2.1.12 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Sender: ovs-dev-bounces@openvswitch.org Errors-To: ovs-dev-bounces@openvswitch.org So that we could skip some very costly CPU operations, including but not limiting to miniflow_extract, emc lookup, dpcls lookup, etc. Thus, performance could be greatly improved. A PHY-PHY forwarding with 1000 mega flows (udp,tp_src=1000-1999) and 1 million streams (tp_src=1000-1999, tp_dst=2000-2999) show more that 260% performance boost. Note that though the heavy miniflow_extract is skipped, we still have to do per packet checking, due to we have to check the tcp_flags. Co-authored-by: Finn Christensen Signed-off-by: Yuanhan Liu Signed-off-by: Finn Christensen --- v5: - do not fetch the flow if the flow has been dead --- lib/dp-packet.h | 13 +++++ lib/dpif-netdev.c | 43 ++++++++++++--- lib/flow.c | 155 +++++++++++++++++++++++++++++++++++++++++++----------- lib/flow.h | 1 + 4 files changed, 174 insertions(+), 38 deletions(-) diff --git a/lib/dp-packet.h b/lib/dp-packet.h index b4b721c..ea1194c 100644 --- a/lib/dp-packet.h +++ b/lib/dp-packet.h @@ -691,6 +691,19 @@ reset_dp_packet_checksum_ol_flags(struct dp_packet *p) #define reset_dp_packet_checksum_ol_flags(arg) #endif +static inline bool +dp_packet_has_flow_mark(struct dp_packet *p OVS_UNUSED, + uint32_t *mark OVS_UNUSED) +{ +#ifdef DPDK_NETDEV + if (p->mbuf.ol_flags & PKT_RX_FDIR_ID) { + *mark = p->mbuf.hash.fdir.hi; + return true; + } +#endif + return false; +} + enum { NETDEV_MAX_BURST = 32 }; /* Maximum number packets in a batch. */ struct dp_packet_batch { diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c index 2fdc8dd..b8e03db 100644 --- a/lib/dpif-netdev.c +++ b/lib/dpif-netdev.c @@ -2002,6 +2002,22 @@ flow_mark_flush(struct dp_netdev_pmd_thread *pmd) } } +static struct dp_netdev_flow * +mark_to_flow_find(const struct dp_netdev_pmd_thread *pmd, + const uint32_t mark) +{ + struct dp_netdev_flow *flow; + + CMAP_FOR_EACH_WITH_HASH (flow, mark_node, mark, &flow_mark.mark_to_flow) { + if (flow->mark == mark && flow->pmd_id == pmd->core_id && + flow->dead == false) { + return flow; + } + } + + return NULL; +} + static void dp_netdev_pmd_remove_flow(struct dp_netdev_pmd_thread *pmd, struct dp_netdev_flow *flow) @@ -5101,10 +5117,10 @@ struct packet_batch_per_flow { static inline void packet_batch_per_flow_update(struct packet_batch_per_flow *batch, struct dp_packet *packet, - const struct miniflow *mf) + uint16_t tcp_flags) { batch->byte_count += dp_packet_size(packet); - batch->tcp_flags |= miniflow_get_tcp_flags(mf); + batch->tcp_flags |= tcp_flags; batch->array.packets[batch->array.count++] = packet; } @@ -5139,7 +5155,7 @@ packet_batch_per_flow_execute(struct packet_batch_per_flow *batch, static inline void dp_netdev_queue_batches(struct dp_packet *pkt, - struct dp_netdev_flow *flow, const struct miniflow *mf, + struct dp_netdev_flow *flow, uint16_t tcp_flags, struct packet_batch_per_flow *batches, size_t *n_batches) { @@ -5150,7 +5166,7 @@ dp_netdev_queue_batches(struct dp_packet *pkt, packet_batch_per_flow_init(batch, flow); } - packet_batch_per_flow_update(batch, pkt, mf); + packet_batch_per_flow_update(batch, pkt, tcp_flags); } /* Try to process all ('cnt') the 'packets' using only the exact match cache @@ -5181,11 +5197,13 @@ emc_processing(struct dp_netdev_pmd_thread *pmd, const size_t cnt = dp_packet_batch_size(packets_); uint32_t cur_min; int i; + uint16_t tcp_flags; atomic_read_relaxed(&pmd->dp->emc_insert_min, &cur_min); DP_PACKET_BATCH_REFILL_FOR_EACH (i, cnt, packet, packets_) { struct dp_netdev_flow *flow; + uint32_t flow_mark; if (OVS_UNLIKELY(dp_packet_size(packet) < ETH_HEADER_LEN)) { dp_packet_delete(packet); @@ -5193,6 +5211,16 @@ emc_processing(struct dp_netdev_pmd_thread *pmd, continue; } + if (dp_packet_has_flow_mark(packet, &flow_mark)) { + flow = mark_to_flow_find(pmd, flow_mark); + if (flow) { + tcp_flags = parse_tcp_flags(packet); + dp_netdev_queue_batches(packet, flow, tcp_flags, batches, + n_batches); + continue; + } + } + if (i != cnt - 1) { struct dp_packet **packets = packets_->packets; /* Prefetch next packet data and metadata. */ @@ -5218,7 +5246,8 @@ emc_processing(struct dp_netdev_pmd_thread *pmd, flow = NULL; } if (OVS_LIKELY(flow)) { - dp_netdev_queue_batches(packet, flow, &key->mf, batches, + tcp_flags = miniflow_get_tcp_flags(&key->mf); + dp_netdev_queue_batches(packet, flow, tcp_flags, batches, n_batches); } else { /* Exact match cache missed. Group missed packets together at @@ -5394,7 +5423,9 @@ fast_path_processing(struct dp_netdev_pmd_thread *pmd, flow = dp_netdev_flow_cast(rules[i]); emc_probabilistic_insert(pmd, &keys[i], flow); - dp_netdev_queue_batches(packet, flow, &keys[i].mf, batches, n_batches); + dp_netdev_queue_batches(packet, flow, + miniflow_get_tcp_flags(&keys[i].mf), + batches, n_batches); } dp_netdev_count_packet(pmd, DP_STAT_MASKED_HIT, cnt - miss_cnt); diff --git a/lib/flow.c b/lib/flow.c index bc24fe7..224e8fb 100644 --- a/lib/flow.c +++ b/lib/flow.c @@ -625,6 +625,70 @@ flow_extract(struct dp_packet *packet, struct flow *flow) miniflow_expand(&m.mf, flow); } +static inline bool +ipv4_sanity_check(const struct ip_header *nh, size_t size, + int *ip_lenp, uint16_t *tot_lenp) +{ + int ip_len; + uint16_t tot_len; + + if (OVS_UNLIKELY(size < IP_HEADER_LEN)) { + return false; + } + ip_len = IP_IHL(nh->ip_ihl_ver) * 4; + + if (OVS_UNLIKELY(ip_len < IP_HEADER_LEN || size < ip_len)) { + return false; + } + + tot_len = ntohs(nh->ip_tot_len); + if (OVS_UNLIKELY(tot_len > size || ip_len > tot_len || + size - tot_len > UINT8_MAX)) { + return false; + } + + *ip_lenp = ip_len; + *tot_lenp = tot_len; + + return true; +} + +static inline uint8_t +ipv4_get_nw_frag(const struct ip_header *nh) +{ + uint8_t nw_frag = 0; + + if (OVS_UNLIKELY(IP_IS_FRAGMENT(nh->ip_frag_off))) { + nw_frag = FLOW_NW_FRAG_ANY; + if (nh->ip_frag_off & htons(IP_FRAG_OFF_MASK)) { + nw_frag |= FLOW_NW_FRAG_LATER; + } + } + + return nw_frag; +} + +static inline bool +ipv6_sanity_check(const struct ovs_16aligned_ip6_hdr *nh, size_t size) +{ + uint16_t plen; + + if (OVS_UNLIKELY(size < sizeof *nh)) { + return false; + } + + plen = ntohs(nh->ip6_plen); + if (OVS_UNLIKELY(plen > size)) { + return false; + } + /* Jumbo Payload option not supported yet. */ + if (OVS_UNLIKELY(size - plen > UINT8_MAX)) { + return false; + } + + return true; +} + /* Caller is responsible for initializing 'dst' with enough storage for * FLOW_U64S * 8 bytes. */ void @@ -749,22 +813,7 @@ miniflow_extract(struct dp_packet *packet, struct miniflow *dst) int ip_len; uint16_t tot_len; - if (OVS_UNLIKELY(size < IP_HEADER_LEN)) { - goto out; - } - ip_len = IP_IHL(nh->ip_ihl_ver) * 4; - - if (OVS_UNLIKELY(ip_len < IP_HEADER_LEN)) { - goto out; - } - if (OVS_UNLIKELY(size < ip_len)) { - goto out; - } - tot_len = ntohs(nh->ip_tot_len); - if (OVS_UNLIKELY(tot_len > size || ip_len > tot_len)) { - goto out; - } - if (OVS_UNLIKELY(size - tot_len > UINT8_MAX)) { + if (OVS_UNLIKELY(!ipv4_sanity_check(nh, size, &ip_len, &tot_len))) { goto out; } dp_packet_set_l2_pad_size(packet, size - tot_len); @@ -787,31 +836,19 @@ miniflow_extract(struct dp_packet *packet, struct miniflow *dst) nw_tos = nh->ip_tos; nw_ttl = nh->ip_ttl; nw_proto = nh->ip_proto; - if (OVS_UNLIKELY(IP_IS_FRAGMENT(nh->ip_frag_off))) { - nw_frag = FLOW_NW_FRAG_ANY; - if (nh->ip_frag_off & htons(IP_FRAG_OFF_MASK)) { - nw_frag |= FLOW_NW_FRAG_LATER; - } - } + nw_frag = ipv4_get_nw_frag(nh); data_pull(&data, &size, ip_len); } else if (dl_type == htons(ETH_TYPE_IPV6)) { - const struct ovs_16aligned_ip6_hdr *nh; + const struct ovs_16aligned_ip6_hdr *nh = data; ovs_be32 tc_flow; uint16_t plen; - if (OVS_UNLIKELY(size < sizeof *nh)) { + if (OVS_UNLIKELY(!ipv6_sanity_check(nh, size))) { goto out; } - nh = data_pull(&data, &size, sizeof *nh); + data_pull(&data, &size, sizeof *nh); plen = ntohs(nh->ip6_plen); - if (OVS_UNLIKELY(plen > size)) { - goto out; - } - /* Jumbo Payload option not supported yet. */ - if (OVS_UNLIKELY(size - plen > UINT8_MAX)) { - goto out; - } dp_packet_set_l2_pad_size(packet, size - plen); size = plen; /* Never pull padding. */ @@ -990,6 +1027,60 @@ parse_dl_type(const struct eth_header *data_, size_t size) return parse_ethertype(&data, &size); } +uint16_t +parse_tcp_flags(struct dp_packet *packet) +{ + const void *data = dp_packet_data(packet); + size_t size = dp_packet_size(packet); + ovs_be16 dl_type; + uint8_t nw_frag = 0, nw_proto = 0; + + if (packet->packet_type != htonl(PT_ETH)) { + return 0; + } + + data_pull(&data, &size, ETH_ADDR_LEN * 2); + dl_type = parse_ethertype(&data, &size); + if (OVS_LIKELY(dl_type == htons(ETH_TYPE_IP))) { + const struct ip_header *nh = data; + int ip_len; + uint16_t tot_len; + + if (OVS_UNLIKELY(!ipv4_sanity_check(nh, size, &ip_len, &tot_len))) { + return 0; + } + nw_proto = nh->ip_proto; + nw_frag = ipv4_get_nw_frag(nh); + + size = tot_len; /* Never pull padding. */ + data_pull(&data, &size, ip_len); + } else if (dl_type == htons(ETH_TYPE_IPV6)) { + const struct ovs_16aligned_ip6_hdr *nh = data; + + if (OVS_UNLIKELY(!ipv6_sanity_check(nh, size))) { + return 0; + } + data_pull(&data, &size, sizeof *nh); + + size = ntohs(nh->ip6_plen); /* Never pull padding. */ + if (!parse_ipv6_ext_hdrs__(&data, &size, &nw_proto, &nw_frag)) { + return 0; + } + nw_proto = nh->ip6_nxt; + } else { + return 0; + } + + if (!(nw_frag & FLOW_NW_FRAG_LATER) && nw_proto == IPPROTO_TCP && + size >= TCP_HEADER_LEN) { + const struct tcp_header *tcp = data; + + return TCP_FLAGS_BE32(tcp->tcp_ctl); + } + + return 0; +} + /* For every bit of a field that is wildcarded in 'wildcards', sets the * corresponding bit in 'flow' to zero. */ void diff --git a/lib/flow.h b/lib/flow.h index b3128da..6537094 100644 --- a/lib/flow.h +++ b/lib/flow.h @@ -130,6 +130,7 @@ bool parse_ipv6_ext_hdrs(const void **datap, size_t *sizep, uint8_t *nw_proto, uint8_t *nw_frag); ovs_be16 parse_dl_type(const struct eth_header *data_, size_t size); bool parse_nsh(const void **datap, size_t *sizep, struct flow_nsh *key); +uint16_t parse_tcp_flags(struct dp_packet *packet); static inline uint64_t flow_get_xreg(const struct flow *flow, int idx) From patchwork Wed Dec 20 14:44:35 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yuanhan Liu X-Patchwork-Id: 851502 X-Patchwork-Delegate: ian.stokes@intel.com Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (mailfrom) smtp.mailfrom=openvswitch.org (client-ip=140.211.169.12; helo=mail.linuxfoundation.org; envelope-from=ovs-dev-bounces@openvswitch.org; receiver=) Authentication-Results: ozlabs.org; dkim=fail reason="signature verification failed" (2048-bit key; unprotected) header.d=fridaylinux.org header.i=@fridaylinux.org header.b="QEPAcE7v"; dkim=fail reason="signature verification failed" (2048-bit key; unprotected) header.d=messagingengine.com header.i=@messagingengine.com header.b="gbrx3NDX"; dkim-atps=neutral Received: from mail.linuxfoundation.org (mail.linuxfoundation.org [140.211.169.12]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 3z1yJs2PGcz9s7F for ; Thu, 21 Dec 2017 01:46:37 +1100 (AEDT) Received: from mail.linux-foundation.org (localhost [127.0.0.1]) by mail.linuxfoundation.org (Postfix) with ESMTP id 3FBBDC83; Wed, 20 Dec 2017 14:45:23 +0000 (UTC) X-Original-To: dev@openvswitch.org Delivered-To: ovs-dev@mail.linuxfoundation.org Received: from smtp1.linuxfoundation.org (smtp1.linux-foundation.org [172.17.192.35]) by mail.linuxfoundation.org (Postfix) with ESMTPS id B2F01C46 for ; Wed, 20 Dec 2017 14:45:21 +0000 (UTC) X-Greylist: from auto-whitelisted by SQLgrey-1.7.6 Received: from out3-smtp.messagingengine.com (out3-smtp.messagingengine.com [66.111.4.27]) by smtp1.linuxfoundation.org (Postfix) with ESMTPS id 0B84A456 for ; Wed, 20 Dec 2017 14:45:20 +0000 (UTC) Received: from compute1.internal (compute1.nyi.internal [10.202.2.41]) by mailout.nyi.internal (Postfix) with ESMTP id 6239120BB1; Wed, 20 Dec 2017 09:45:19 -0500 (EST) Received: from frontend1 ([10.202.2.160]) by compute1.internal (MEProxy); Wed, 20 Dec 2017 09:45:19 -0500 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=fridaylinux.org; h=cc:date:from:in-reply-to:message-id:references:subject:to :x-me-sender:x-me-sender:x-sasl-enc; s=fm1; bh=4q3sHQgtYRlsF/SNf sGPeISpKcjVar1d8YUcS8IhSvs=; b=QEPAcE7vBnQweQ0Og26ez+72wHIkZOGv+ f4+c3gLB9VqKqWMrRUXsvjQTxvDtwX+zTpb7xquXZK3df9GXeZHDzLvbqrA62+4g /1XKr0Q4Jn5f+PdBg7xNvUsCX4IUSdubWhhh3NAbxIbZ9/nj/aszyzDrXIsmo8rX jYbtkEJFxt7Ohs3it6c7cMzh0i8yfU/Bv80mzxIM9xRSTFl49ksl0NugZa89LJsh o0aMIcUp0CqpgfAFlm3OT81G8hpGq+lEaN5qIH5uSLo0m4ewWOjAHSN7sayXiRPp omfGoODie3NqYRhKxET9K1P7mEAOynA2OJ/YSzNPRizZInDiosvtQ== DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:date:from:in-reply-to:message-id :references:subject:to:x-me-sender:x-me-sender:x-sasl-enc; s= fm1; bh=4q3sHQgtYRlsF/SNfsGPeISpKcjVar1d8YUcS8IhSvs=; b=gbrx3NDX XkmLrYSELqbJNaQFtB29Ax9/ElEd3PXw9AuL/oeJCG0G1Jfq2c1RHfKXImY2NPn9 PK1VZH2K8zTsNqkvksYsrSi6Z+5dJNk4CE0hf0qzuJIheFdER2Nov6UmfcEZhBe2 SRvcqueqUQ6vxlCNSEsN4QwktThL57wO/qV+hXQkuoZTjjpWEDch1lDnzU2fH/Sa 8lDqTGEUB08wdHXJAHzgGIodmJjTQTg2kDpIRzuOyj0576T/OwY6L14GylM+b0Xj H3OPZbwAKQUqcWjsW72RcCBkSrmDOpeKPHGAVysz7/Sg/mAxWXV5W/RKGIM+V0Jn jG9iCDnNuB74Ow== X-ME-Sender: Received: from yliu-dev.mtl.com (unknown [115.148.91.103]) by mail.messagingengine.com (Postfix) with ESMTPA id E4C4E7E17D; Wed, 20 Dec 2017 09:45:07 -0500 (EST) From: Yuanhan Liu To: dev@openvswitch.org Date: Wed, 20 Dec 2017 22:44:35 +0800 Message-Id: <1513781077-21984-4-git-send-email-yliu@fridaylinux.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1513781077-21984-1-git-send-email-yliu@fridaylinux.org> References: <1513781077-21984-1-git-send-email-yliu@fridaylinux.org> X-Spam-Status: No, score=-2.7 required=5.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, RCVD_IN_DNSWL_LOW autolearn=ham version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on smtp1.linux-foundation.org Cc: Simon Horman Subject: [ovs-dev] [PATCH v5 3/5] netdev-dpdk: implement flow offload with rte flow X-BeenThere: ovs-dev@openvswitch.org X-Mailman-Version: 2.1.12 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Sender: ovs-dev-bounces@openvswitch.org Errors-To: ovs-dev-bounces@openvswitch.org From: Finn Christensen The basic yet the major part of this patch is to translate the "match" to rte flow patterns. And then, we create a rte flow with MARK + RSS actions. Afterwards, all pkts match the flow will have the mark id in the mbuf. The reason RSS is needed is, for most NICs, a MARK only action is not allowed. It has to be used together with some other actions, such as QUEUE, RSS, etc. However, QUEUE action can specify one queue only, which may break the rss. Likely, RSS action is currently the best we could now. Thus, RSS action is choosen. For any unsupported flows, such as MPLS, -1 is returned, meaning the flow offload is failed and then skipped. Co-authored-by: Yuanhan Liu Signed-off-by: Finn Christensen Signed-off-by: Yuanhan Liu --- lib/netdev-dpdk.c | 555 +++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 554 insertions(+), 1 deletion(-) diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c index 8f22264..2a329e6 100644 --- a/lib/netdev-dpdk.c +++ b/lib/netdev-dpdk.c @@ -38,7 +38,9 @@ #include #include #include +#include +#include "cmap.h" #include "dirs.h" #include "dp-packet.h" #include "dpdk.h" @@ -60,6 +62,7 @@ #include "sset.h" #include "unaligned.h" #include "timeval.h" +#include "uuid.h" #include "unixctl.h" enum {VIRTIO_RXQ, VIRTIO_TXQ, VIRTIO_QNUM}; @@ -3343,6 +3346,556 @@ unlock: return err; } +/* + * A mapping from ufid to dpdk rte_flow. + */ +static struct cmap ufid_to_rte_flow = CMAP_INITIALIZER; + +struct ufid_to_rte_flow_data { + struct cmap_node node; + ovs_u128 ufid; + struct rte_flow *rte_flow; +}; + +/* Find rte_flow with @ufid */ +static struct rte_flow * +ufid_to_rte_flow_find(const ovs_u128 *ufid) +{ + size_t hash = hash_bytes(ufid, sizeof(*ufid), 0); + struct ufid_to_rte_flow_data *data; + + CMAP_FOR_EACH_WITH_HASH (data, node, hash, &ufid_to_rte_flow) { + if (ovs_u128_equals(*ufid, data->ufid)) { + return data->rte_flow; + } + } + + return NULL; +} + +static inline void +ufid_to_rte_flow_associate(const ovs_u128 *ufid, struct rte_flow *rte_flow) +{ + size_t hash = hash_bytes(ufid, sizeof(*ufid), 0); + struct ufid_to_rte_flow_data *data = xzalloc(sizeof(*data)); + + /* + * We should not simply overwrite an existing rte flow. + * We should have deleted it first before re-adding it. + * Thus, if following assert triggers, something is wrong: + * the rte_flow is not destroyed. + */ + ovs_assert(ufid_to_rte_flow_find(ufid) == NULL); + + data->ufid = *ufid; + data->rte_flow = rte_flow; + + cmap_insert(&ufid_to_rte_flow, + CONST_CAST(struct cmap_node *, &data->node), hash); +} + +static inline void +ufid_to_rte_flow_disassociate(const ovs_u128 *ufid) +{ + size_t hash = hash_bytes(ufid, sizeof(*ufid), 0); + struct ufid_to_rte_flow_data *data; + + CMAP_FOR_EACH_WITH_HASH (data, node, hash, &ufid_to_rte_flow) { + if (ovs_u128_equals(*ufid, data->ufid)) { + cmap_remove(&ufid_to_rte_flow, + CONST_CAST(struct cmap_node *, &data->node), hash); + free(data); + return; + } + } + + VLOG_WARN("ufid "UUID_FMT" is not associated with an rte flow\n", + UUID_ARGS((struct uuid *)ufid)); +} + +struct flow_patterns { + struct rte_flow_item *items; + int cnt; + int max; +}; + +struct flow_actions { + struct rte_flow_action *actions; + int cnt; + int max; +}; + +static void +add_flow_pattern(struct flow_patterns *patterns, enum rte_flow_item_type type, + const void *spec, const void *mask) +{ + int cnt = patterns->cnt; + + if (cnt == 0) { + patterns->max = 8; + patterns->items = xcalloc(patterns->max, sizeof(struct rte_flow_item)); + } else if (cnt == patterns->max) { + patterns->max *= 2; + patterns->items = xrealloc(patterns->items, patterns->max * + sizeof(struct rte_flow_item)); + } + + patterns->items[cnt].type = type; + patterns->items[cnt].spec = spec; + patterns->items[cnt].mask = mask; + patterns->items[cnt].last = NULL; + patterns->cnt++; +} + +static void +add_flow_action(struct flow_actions *actions, enum rte_flow_action_type type, + const void *conf) +{ + int cnt = actions->cnt; + + if (cnt == 0) { + actions->max = 8; + actions->actions = xcalloc(actions->max, + sizeof(struct rte_flow_action)); + } else if (cnt == actions->max) { + actions->max *= 2; + actions->actions = xrealloc(actions->actions, actions->max * + sizeof(struct rte_flow_action)); + } + + actions->actions[cnt].type = type; + actions->actions[cnt].conf = conf; + actions->cnt++; +} + +static struct rte_flow_action_rss * +add_flow_rss_action(struct flow_actions *actions, struct netdev *netdev) +{ + int i; + struct rte_flow_action_rss *rss; + + rss = xmalloc(sizeof(*rss) + sizeof(uint16_t) * netdev->n_rxq); + rss->rss_conf = &port_conf.rx_adv_conf.rss_conf; + rss->num = netdev->n_rxq; + + for (i = 0; i < rss->num; i++) { + rss->queue[i] = i; + } + + add_flow_action(actions, RTE_FLOW_ACTION_TYPE_RSS, rss); + + return rss; +} + +static int +netdev_dpdk_add_rte_flow_offload(struct netdev *netdev, + const struct match *match, + struct nlattr *nl_actions OVS_UNUSED, + size_t actions_len OVS_UNUSED, + const ovs_u128 *ufid, + struct offload_info *info) +{ + struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); + const struct rte_flow_attr flow_attr = { + .group = 0, + .priority = 0, + .ingress = 1, + .egress = 0 + }; + struct flow_patterns patterns = { .items = NULL, .cnt = 0 }; + struct flow_actions actions = { .actions = NULL, .cnt = 0 }; + struct rte_flow *flow; + struct rte_flow_error error; + uint8_t *ipv4_next_proto_mask = NULL; + int ret = 0; + + /* Eth */ + struct rte_flow_item_eth eth_spec; + struct rte_flow_item_eth eth_mask; + memset(ð_spec, 0, sizeof(eth_spec)); + memset(ð_mask, 0, sizeof(eth_mask)); + if (!eth_addr_is_zero(match->wc.masks.dl_src) || + !eth_addr_is_zero(match->wc.masks.dl_dst)) { + rte_memcpy(ð_spec.dst, &match->flow.dl_dst, sizeof(eth_spec.dst)); + rte_memcpy(ð_spec.src, &match->flow.dl_src, sizeof(eth_spec.src)); + eth_spec.type = match->flow.dl_type; + + rte_memcpy(ð_mask.dst, &match->wc.masks.dl_dst, + sizeof(eth_mask.dst)); + rte_memcpy(ð_mask.src, &match->wc.masks.dl_src, + sizeof(eth_mask.src)); + eth_mask.type = match->wc.masks.dl_type; + + add_flow_pattern(&patterns, RTE_FLOW_ITEM_TYPE_ETH, + ð_spec, ð_mask); + } else { + /* + * If user specifies a flow (like UDP flow) without L2 patterns, + * OVS will at least set the dl_type. Normally, it's enough to + * create an eth pattern just with it. Unluckily, some Intel's + * NIC (such as XL710) doesn't support that. Below is a workaround, + * which simply matches any L2 pkts. + */ + add_flow_pattern(&patterns, RTE_FLOW_ITEM_TYPE_ETH, NULL, NULL); + } + + /* VLAN */ + struct rte_flow_item_vlan vlan_spec; + struct rte_flow_item_vlan vlan_mask; + memset(&vlan_spec, 0, sizeof(vlan_spec)); + memset(&vlan_mask, 0, sizeof(vlan_mask)); + if (match->wc.masks.vlans[0].tci && match->flow.vlans[0].tci) { + vlan_spec.tci = match->flow.vlans[0].tci; + vlan_mask.tci = match->wc.masks.vlans[0].tci; + + /* match any protocols */ + vlan_mask.tpid = 0; + + add_flow_pattern(&patterns, RTE_FLOW_ITEM_TYPE_VLAN, + &vlan_spec, &vlan_mask); + } + + /* IP v4 */ + uint8_t proto = 0; + struct rte_flow_item_ipv4 ipv4_spec; + struct rte_flow_item_ipv4 ipv4_mask; + memset(&ipv4_spec, 0, sizeof(ipv4_spec)); + memset(&ipv4_mask, 0, sizeof(ipv4_mask)); + if (match->flow.dl_type == ntohs(ETH_TYPE_IP) && + (match->wc.masks.nw_src || match->wc.masks.nw_dst || + match->wc.masks.nw_tos || match->wc.masks.nw_ttl || + match->wc.masks.nw_proto)) { + ipv4_spec.hdr.type_of_service = match->flow.nw_tos; + ipv4_spec.hdr.time_to_live = match->flow.nw_ttl; + ipv4_spec.hdr.next_proto_id = match->flow.nw_proto; + ipv4_spec.hdr.src_addr = match->flow.nw_src; + ipv4_spec.hdr.dst_addr = match->flow.nw_dst; + + ipv4_mask.hdr.type_of_service = match->wc.masks.nw_tos; + ipv4_mask.hdr.time_to_live = match->wc.masks.nw_ttl; + ipv4_mask.hdr.next_proto_id = match->wc.masks.nw_proto; + ipv4_mask.hdr.src_addr = match->wc.masks.nw_src; + ipv4_mask.hdr.dst_addr = match->wc.masks.nw_dst; + + add_flow_pattern(&patterns, RTE_FLOW_ITEM_TYPE_IPV4, + &ipv4_spec, &ipv4_mask); + + /* Save proto for L4 protocol setup */ + proto = ipv4_spec.hdr.next_proto_id & ipv4_mask.hdr.next_proto_id; + + /* Remember proto mask address for later modification */ + ipv4_next_proto_mask = &ipv4_mask.hdr.next_proto_id; + } + + if (proto != IPPROTO_ICMP && proto != IPPROTO_UDP && + proto != IPPROTO_SCTP && proto != IPPROTO_TCP && + (match->wc.masks.tp_src || + match->wc.masks.tp_dst || + match->wc.masks.tcp_flags)) { + VLOG_DBG("L4 Protocol (%u) not supported", proto); + ret = -1; + goto out; + } + + if ((match->wc.masks.tp_src && match->wc.masks.tp_src != 0xffff) || + (match->wc.masks.tp_dst && match->wc.masks.tp_dst != 0xffff)) { + ret = -1; + goto out; + } + + struct rte_flow_item_udp udp_spec; + struct rte_flow_item_udp udp_mask; + memset(&udp_spec, 0, sizeof(udp_spec)); + memset(&udp_mask, 0, sizeof(udp_mask)); + if (proto == IPPROTO_UDP && + (match->wc.masks.tp_src || match->wc.masks.tp_dst)) { + udp_spec.hdr.src_port = match->flow.tp_src; + udp_spec.hdr.dst_port = match->flow.tp_dst; + + udp_mask.hdr.src_port = match->wc.masks.tp_src; + udp_mask.hdr.dst_port = match->wc.masks.tp_dst; + + add_flow_pattern(&patterns, RTE_FLOW_ITEM_TYPE_UDP, + &udp_spec, &udp_mask); + + /* proto == UDP and ITEM_TYPE_UDP, thus no need for proto match */ + if (ipv4_next_proto_mask) { + *ipv4_next_proto_mask = 0; + } + } + + struct rte_flow_item_sctp sctp_spec; + struct rte_flow_item_sctp sctp_mask; + memset(&sctp_spec, 0, sizeof(sctp_spec)); + memset(&sctp_mask, 0, sizeof(sctp_mask)); + if (proto == IPPROTO_SCTP && + (match->wc.masks.tp_src || match->wc.masks.tp_dst)) { + sctp_spec.hdr.src_port = match->flow.tp_src; + sctp_spec.hdr.dst_port = match->flow.tp_dst; + + sctp_mask.hdr.src_port = match->wc.masks.tp_src; + sctp_mask.hdr.dst_port = match->wc.masks.tp_dst; + + add_flow_pattern(&patterns, RTE_FLOW_ITEM_TYPE_SCTP, + &sctp_spec, &sctp_mask); + + /* proto == SCTP and ITEM_TYPE_SCTP, thus no need for proto match */ + if (ipv4_next_proto_mask) { + *ipv4_next_proto_mask = 0; + } + } + + struct rte_flow_item_icmp icmp_spec; + struct rte_flow_item_icmp icmp_mask; + memset(&icmp_spec, 0, sizeof(icmp_spec)); + memset(&icmp_mask, 0, sizeof(icmp_mask)); + if (proto == IPPROTO_ICMP && + (match->wc.masks.tp_src || match->wc.masks.tp_dst)) { + icmp_spec.hdr.icmp_type = (uint8_t)ntohs(match->flow.tp_src); + icmp_spec.hdr.icmp_code = (uint8_t)ntohs(match->flow.tp_dst); + + icmp_mask.hdr.icmp_type = (uint8_t)ntohs(match->wc.masks.tp_src); + icmp_mask.hdr.icmp_code = (uint8_t)ntohs(match->wc.masks.tp_dst); + + add_flow_pattern(&patterns, RTE_FLOW_ITEM_TYPE_ICMP, + &icmp_spec, &icmp_mask); + + /* proto == ICMP and ITEM_TYPE_ICMP, thus no need for proto match */ + if (ipv4_next_proto_mask) { + *ipv4_next_proto_mask = 0; + } + } + + struct rte_flow_item_tcp tcp_spec; + struct rte_flow_item_tcp tcp_mask; + memset(&tcp_spec, 0, sizeof(tcp_spec)); + memset(&tcp_mask, 0, sizeof(tcp_mask)); + if (proto == IPPROTO_TCP && + (match->wc.masks.tp_src || + match->wc.masks.tp_dst || + match->wc.masks.tcp_flags)) { + tcp_spec.hdr.src_port = match->flow.tp_src; + tcp_spec.hdr.dst_port = match->flow.tp_dst; + tcp_spec.hdr.data_off = ntohs(match->flow.tcp_flags) >> 8; + tcp_spec.hdr.tcp_flags = ntohs(match->flow.tcp_flags) & 0xff; + + tcp_mask.hdr.src_port = match->wc.masks.tp_src; + tcp_mask.hdr.dst_port = match->wc.masks.tp_dst; + tcp_mask.hdr.data_off = ntohs(match->wc.masks.tcp_flags) >> 8; + tcp_mask.hdr.tcp_flags = ntohs(match->wc.masks.tcp_flags) & 0xff; + + add_flow_pattern(&patterns, RTE_FLOW_ITEM_TYPE_TCP, + &tcp_spec, &tcp_mask); + + /* proto == TCP and ITEM_TYPE_TCP, thus no need for proto match */ + if (ipv4_next_proto_mask) { + *ipv4_next_proto_mask = 0; + } + } + add_flow_pattern(&patterns, RTE_FLOW_ITEM_TYPE_END, NULL, NULL); + + struct rte_flow_action_mark mark; + mark.id = info->flow_mark; + add_flow_action(&actions, RTE_FLOW_ACTION_TYPE_MARK, &mark); + + struct rte_flow_action_rss *rss; + rss = add_flow_rss_action(&actions, netdev); + add_flow_action(&actions, RTE_FLOW_ACTION_TYPE_END, NULL); + + flow = rte_flow_create(dev->port_id, &flow_attr, patterns.items, + actions.actions, &error); + free(rss); + if (!flow) { + VLOG_ERR("rte flow creat error: %u : message : %s\n", + error.type, error.message); + ret = -1; + goto out; + } + ufid_to_rte_flow_associate(ufid, flow); + VLOG_DBG("installed flow %p by ufid "UUID_FMT"\n", + flow, UUID_ARGS((struct uuid *)ufid)); + +out: + free(patterns.items); + free(actions.actions); + return ret; +} + +static bool +is_all_zero(const void *addr, size_t n) +{ + size_t i = 0; + const uint8_t *p = (uint8_t *)addr; + + for (i = 0; i < n; i++) { + if (p[i] != 0) { + return false; + } + } + + return true; +} + +/* + * Check if any unsupported flow patterns are specified. + */ +static int +netdev_dpdk_validate_flow(const struct match *match) +{ + struct match match_zero_wc; + + /* Create a wc-zeroed version of flow */ + match_init(&match_zero_wc, &match->flow, &match->wc); + + if (!is_all_zero(&match_zero_wc.flow.tunnel, + sizeof(match_zero_wc.flow.tunnel))) { + goto err; + } + + if (match->wc.masks.metadata || + match->wc.masks.skb_priority || + match->wc.masks.pkt_mark || + match->wc.masks.dp_hash) { + goto err; + } + + /* recirc id must be zero */ + if (match_zero_wc.flow.recirc_id) { + goto err; + } + + if (match->wc.masks.ct_state || + match->wc.masks.ct_nw_proto || + match->wc.masks.ct_zone || + match->wc.masks.ct_mark || + match->wc.masks.ct_label.u64.hi || + match->wc.masks.ct_label.u64.lo) { + goto err; + } + + if (match->wc.masks.conj_id || + match->wc.masks.actset_output) { + goto err; + } + + /* unsupported L2 */ + if (!is_all_zero(&match->wc.masks.mpls_lse, + sizeof(match_zero_wc.flow.mpls_lse))) { + goto err; + } + + /* unsupported L3 */ + if (match->wc.masks.ipv6_label || + match->wc.masks.ct_nw_src || + match->wc.masks.ct_nw_dst || + !is_all_zero(&match->wc.masks.ipv6_src, sizeof(struct in6_addr)) || + !is_all_zero(&match->wc.masks.ipv6_dst, sizeof(struct in6_addr)) || + !is_all_zero(&match->wc.masks.ct_ipv6_src, sizeof(struct in6_addr)) || + !is_all_zero(&match->wc.masks.ct_ipv6_dst, sizeof(struct in6_addr)) || + !is_all_zero(&match->wc.masks.nd_target, sizeof(struct in6_addr)) || + !is_all_zero(&match->wc.masks.nsh, sizeof(struct flow_nsh)) || + !is_all_zero(&match->wc.masks.arp_sha, sizeof(struct eth_addr)) || + !is_all_zero(&match->wc.masks.arp_tha, sizeof(struct eth_addr))) { + goto err; + } + + /* If fragmented, then don't HW accelerate - for now */ + if (match_zero_wc.flow.nw_frag) { + goto err; + } + + /* unsupported L4 */ + if (match->wc.masks.igmp_group_ip4 || + match->wc.masks.ct_tp_src || + match->wc.masks.ct_tp_dst) { + goto err; + } + + return 0; + +err: + VLOG_ERR("cannot HW accelerate this flow due to unsupported protocols"); + return -1; +} + +static int +netdev_dpdk_destroy_rte_flow(struct netdev_dpdk *dev, + const ovs_u128 *ufid, + struct rte_flow *rte_flow) +{ + struct rte_flow_error error; + int ret; + + ret = rte_flow_destroy(dev->port_id, rte_flow, &error); + if (ret == 0) { + ufid_to_rte_flow_disassociate(ufid); + VLOG_DBG("removed rte flow %p associated with ufid " UUID_FMT "\n", + rte_flow, UUID_ARGS((struct uuid *)ufid)); + } else { + VLOG_ERR("rte flow destroy error: %u : message : %s\n", + error.type, error.message); + } + + return ret; +} + +static int +netdev_dpdk_flow_put(struct netdev *netdev, struct match *match, + struct nlattr *actions, size_t actions_len, + const ovs_u128 *ufid, struct offload_info *info, + struct dpif_flow_stats *stats OVS_UNUSED) +{ + struct rte_flow *rte_flow; + int ret; + + /* + * If an old rte_flow exists, it means it's a flow modification. + * Here destroy the old rte flow first before adding a new one. + */ + rte_flow = ufid_to_rte_flow_find(ufid); + if (rte_flow) { + ret = netdev_dpdk_destroy_rte_flow(netdev_dpdk_cast(netdev), + ufid, rte_flow); + if (ret < 0) { + return ret; + } + } + + ret = netdev_dpdk_validate_flow(match); + if (ret < 0) { + return ret; + } + + return netdev_dpdk_add_rte_flow_offload(netdev, match, actions, + actions_len, ufid, info); +} + +static int +netdev_dpdk_flow_del(struct netdev *netdev, const ovs_u128 *ufid, + struct dpif_flow_stats *stats OVS_UNUSED) +{ + + struct rte_flow *rte_flow = ufid_to_rte_flow_find(ufid); + + if (!rte_flow) { + return -1; + } + + return netdev_dpdk_destroy_rte_flow(netdev_dpdk_cast(netdev), + ufid, rte_flow); +} + +#define DPDK_FLOW_OFFLOAD_API \ + NULL, /* flow_flush */ \ + NULL, /* flow_dump_create */ \ + NULL, /* flow_dump_destroy */ \ + NULL, /* flow_dump_next */ \ + netdev_dpdk_flow_put, \ + NULL, /* flow_get */ \ + netdev_dpdk_flow_del, \ + NULL /* init_flow_api */ + + #define NETDEV_DPDK_CLASS(NAME, INIT, CONSTRUCT, DESTRUCT, \ SET_CONFIG, SET_TX_MULTIQ, SEND, \ GET_CARRIER, GET_STATS, \ @@ -3415,7 +3968,7 @@ unlock: RXQ_RECV, \ NULL, /* rx_wait */ \ NULL, /* rxq_drain */ \ - NO_OFFLOAD_API \ + DPDK_FLOW_OFFLOAD_API \ } static const struct netdev_class dpdk_class = From patchwork Wed Dec 20 14:44:36 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yuanhan Liu X-Patchwork-Id: 851503 X-Patchwork-Delegate: ian.stokes@intel.com Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (mailfrom) smtp.mailfrom=openvswitch.org (client-ip=140.211.169.12; helo=mail.linuxfoundation.org; envelope-from=ovs-dev-bounces@openvswitch.org; receiver=) Authentication-Results: ozlabs.org; dkim=fail reason="signature verification failed" (2048-bit key; unprotected) header.d=fridaylinux.org header.i=@fridaylinux.org header.b="f3OXUt7O"; dkim=fail reason="signature verification failed" (2048-bit key; unprotected) header.d=messagingengine.com header.i=@messagingengine.com header.b="m8JGYgM9"; dkim-atps=neutral Received: from mail.linuxfoundation.org (mail.linuxfoundation.org [140.211.169.12]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 3z1yL45Bbdz9s7F for ; Thu, 21 Dec 2017 01:47:40 +1100 (AEDT) Received: from mail.linux-foundation.org (localhost [127.0.0.1]) by mail.linuxfoundation.org (Postfix) with ESMTP id C4E6ACB2; Wed, 20 Dec 2017 14:45:32 +0000 (UTC) X-Original-To: dev@openvswitch.org Delivered-To: ovs-dev@mail.linuxfoundation.org Received: from smtp1.linuxfoundation.org (smtp1.linux-foundation.org [172.17.192.35]) by mail.linuxfoundation.org (Postfix) with ESMTPS id D915ACB9 for ; Wed, 20 Dec 2017 14:45:30 +0000 (UTC) X-Greylist: from auto-whitelisted by SQLgrey-1.7.6 Received: from out3-smtp.messagingengine.com (out3-smtp.messagingengine.com [66.111.4.27]) by smtp1.linuxfoundation.org (Postfix) with ESMTPS id 09842463 for ; Wed, 20 Dec 2017 14:45:29 +0000 (UTC) Received: from compute1.internal (compute1.nyi.internal [10.202.2.41]) by mailout.nyi.internal (Postfix) with ESMTP id 53C8D20AE7; Wed, 20 Dec 2017 09:45:29 -0500 (EST) Received: from frontend1 ([10.202.2.160]) by compute1.internal (MEProxy); Wed, 20 Dec 2017 09:45:29 -0500 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=fridaylinux.org; h=cc:date:from:in-reply-to:message-id:references:subject:to :x-me-sender:x-me-sender:x-sasl-enc; s=fm1; bh=cUSCn7PuFSsPSFL4u gkaQLy6CwS5ttRDRB7I5W4O4Qg=; b=f3OXUt7O1xBDUsIZjsIanJ3NGqgkDO8rx ikQTxSbPIG+uqJ0Dn3C+D8sVVaUZtCXNNw19WhAtovE/LYVjamXGdP+qVogkBaM8 ICW0YJGY91BZfXNMvR3iRax/2Zi173a1CWJKRHygOzunM/7PNPN5vhGl23tH0HD4 or0SJ7SZntukIlfuwb5i8rOGDPXG/PNWwsWv1X5iGJYBZ0nXne3ZKawQ0sCBD1BS skf47KDSscryCCNN2gZhUB0DvEv2RivdkX/NOKNGqCsamJyUX8JOlmKRzzS1F+uk q5bBTJtE4ZdYbTbmm7+V6v2VcDAh82zg7apm3VHwB47fClmuiejcQ== DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:date:from:in-reply-to:message-id :references:subject:to:x-me-sender:x-me-sender:x-sasl-enc; s= fm1; bh=cUSCn7PuFSsPSFL4ugkaQLy6CwS5ttRDRB7I5W4O4Qg=; b=m8JGYgM9 ZPWv5fQNOnIsk+IkvgvWWKBQJPTokgqqfSw/LIaj30O/sWQaQmx7K5Ft4n2zZIh7 NbLrTi0Iu8MVYA0KCxfL9hUZ83O1KfpjF+anv60mIweDRUcML/VLowegMXeTVno9 mSfOoQbIPikAd0bftSmKb858NbyLJnEGgtZfg03E2dbzS/bznSvHs6Ucrd/xIncG qkyKMCG93KWEBvvGaPdo5qe+aQddKjsW4pPmOn5rWjj1RKDMxu7I0HS92SAzbnw+ FYyWQDTOHdRzyafwptI6Q+H07M1CyA4tU2n83Ej31lcyIuEmxD1ek2gfOblwpaXk EygFsaglpY9e6w== X-ME-Sender: Received: from yliu-dev.mtl.com (unknown [115.148.91.103]) by mail.messagingengine.com (Postfix) with ESMTPA id 232507E34D; Wed, 20 Dec 2017 09:45:19 -0500 (EST) From: Yuanhan Liu To: dev@openvswitch.org Date: Wed, 20 Dec 2017 22:44:36 +0800 Message-Id: <1513781077-21984-5-git-send-email-yliu@fridaylinux.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1513781077-21984-1-git-send-email-yliu@fridaylinux.org> References: <1513781077-21984-1-git-send-email-yliu@fridaylinux.org> X-Spam-Status: No, score=-2.7 required=5.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, RCVD_IN_DNSWL_LOW autolearn=ham version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on smtp1.linux-foundation.org Cc: Simon Horman Subject: [ovs-dev] [PATCH v5 4/5] netdev-dpdk: add debug for rte flow patterns X-BeenThere: ovs-dev@openvswitch.org X-Mailman-Version: 2.1.12 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Sender: ovs-dev-bounces@openvswitch.org Errors-To: ovs-dev-bounces@openvswitch.org For debug purpose. Co-authored-by: Finn Christensen Signed-off-by: Yuanhan Liu Signed-off-by: Finn Christensen ---- v5: - turned log to DBG level --- lib/netdev-dpdk.c | 177 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 177 insertions(+) diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c index 2a329e6..45fcc74 100644 --- a/lib/netdev-dpdk.c +++ b/lib/netdev-dpdk.c @@ -3426,6 +3426,182 @@ struct flow_actions { }; static void +dump_flow_pattern(struct rte_flow_item *item) +{ + if (item->type == RTE_FLOW_ITEM_TYPE_ETH) { + const struct rte_flow_item_eth *eth_spec = item->spec; + const struct rte_flow_item_eth *eth_mask = item->mask; + + VLOG_DBG("rte flow eth pattern:\n"); + if (eth_spec) { + VLOG_DBG(" spec: src="ETH_ADDR_FMT", dst="ETH_ADDR_FMT", " + "type=0x%04" PRIx16"\n", + eth_spec->src.addr_bytes[0], eth_spec->src.addr_bytes[1], + eth_spec->src.addr_bytes[2], eth_spec->src.addr_bytes[3], + eth_spec->src.addr_bytes[4], eth_spec->src.addr_bytes[5], + eth_spec->dst.addr_bytes[0], eth_spec->dst.addr_bytes[1], + eth_spec->dst.addr_bytes[2], eth_spec->dst.addr_bytes[3], + eth_spec->dst.addr_bytes[4], eth_spec->dst.addr_bytes[5], + ntohs(eth_spec->type)); + } else { + VLOG_DBG(" spec = null\n"); + } + if (eth_mask) { + VLOG_DBG(" mask: src="ETH_ADDR_FMT", dst="ETH_ADDR_FMT", " + "type=0x%04"PRIx16"\n", + eth_mask->src.addr_bytes[0], eth_mask->src.addr_bytes[1], + eth_mask->src.addr_bytes[2], eth_mask->src.addr_bytes[3], + eth_mask->src.addr_bytes[4], eth_mask->src.addr_bytes[5], + eth_mask->dst.addr_bytes[0], eth_mask->dst.addr_bytes[1], + eth_mask->dst.addr_bytes[2], eth_mask->dst.addr_bytes[3], + eth_mask->dst.addr_bytes[4], eth_mask->dst.addr_bytes[5], + eth_mask->type); + } else { + VLOG_DBG(" mask = null\n"); + } + } + + if (item->type == RTE_FLOW_ITEM_TYPE_VLAN) { + const struct rte_flow_item_vlan *vlan_spec = item->spec; + const struct rte_flow_item_vlan *vlan_mask = item->mask; + + VLOG_DBG("rte flow vlan pattern:\n"); + if (vlan_spec) { + VLOG_DBG(" spec: tpid=0x%"PRIx16", tci=0x%"PRIx16"\n", + ntohs(vlan_spec->tpid), ntohs(vlan_spec->tci)); + } else { + VLOG_DBG(" spec = null\n"); + } + + if (vlan_mask) { + VLOG_DBG(" mask: tpid=0x%"PRIx16", tci=0x%"PRIx16"\n", + vlan_mask->tpid, vlan_mask->tci); + } else { + VLOG_DBG(" mask = null\n"); + } + } + + if (item->type == RTE_FLOW_ITEM_TYPE_IPV4) { + const struct rte_flow_item_ipv4 *ipv4_spec = item->spec; + const struct rte_flow_item_ipv4 *ipv4_mask = item->mask; + + VLOG_DBG("rte flow ipv4 pattern:\n"); + if (ipv4_spec) { + VLOG_DBG(" spec: tos=0x%"PRIx8", ttl=%"PRIx8", proto=0x%"PRIx8 + ", src="IP_FMT", dst="IP_FMT"\n", + ipv4_spec->hdr.type_of_service, + ipv4_spec->hdr.time_to_live, + ipv4_spec->hdr.next_proto_id, + IP_ARGS(ipv4_spec->hdr.src_addr), + IP_ARGS(ipv4_spec->hdr.dst_addr)); + } else { + VLOG_DBG(" spec = null\n"); + } + if (ipv4_mask) { + VLOG_DBG(" mask: tos=0x%"PRIx8", ttl=%"PRIx8", proto=0x%"PRIx8 + ", src="IP_FMT", dst="IP_FMT"\n", + ipv4_mask->hdr.type_of_service, + ipv4_mask->hdr.time_to_live, + ipv4_mask->hdr.next_proto_id, + IP_ARGS(ipv4_mask->hdr.src_addr), + IP_ARGS(ipv4_mask->hdr.dst_addr)); + } else { + VLOG_DBG(" mask = null\n"); + } + } + + if (item->type == RTE_FLOW_ITEM_TYPE_UDP) { + const struct rte_flow_item_udp *udp_spec = item->spec; + const struct rte_flow_item_udp *udp_mask = item->mask; + + VLOG_DBG("rte flow udp pattern:\n"); + if (udp_spec) { + VLOG_DBG(" spec: src_port=%"PRIu16", dst_port=%"PRIu16"\n", + ntohs(udp_spec->hdr.src_port), + ntohs(udp_spec->hdr.dst_port)); + } else { + VLOG_DBG(" spec = null\n"); + } + if (udp_mask) { + VLOG_DBG(" mask: src_port=0x%"PRIx16", dst_port=0x%"PRIx16"\n", + udp_mask->hdr.src_port, + udp_mask->hdr.dst_port); + } else { + VLOG_DBG(" mask = null\n"); + } + } + + if (item->type == RTE_FLOW_ITEM_TYPE_SCTP) { + const struct rte_flow_item_sctp *sctp_spec = item->spec; + const struct rte_flow_item_sctp *sctp_mask = item->mask; + + VLOG_DBG("rte flow sctp pattern:\n"); + if (sctp_spec) { + VLOG_DBG(" spec: src_port=%"PRIu16", dst_port=%"PRIu16"\n", + ntohs(sctp_spec->hdr.src_port), + ntohs(sctp_spec->hdr.dst_port)); + } else { + VLOG_DBG(" spec = null\n"); + } + if (sctp_mask) { + VLOG_DBG(" mask: src_port=0x%"PRIx16", dst_port=0x%"PRIx16"\n", + sctp_mask->hdr.src_port, + sctp_mask->hdr.dst_port); + } else { + VLOG_DBG(" mask = null\n"); + } + } + + if (item->type == RTE_FLOW_ITEM_TYPE_ICMP) { + const struct rte_flow_item_icmp *icmp_spec = item->spec; + const struct rte_flow_item_icmp *icmp_mask = item->mask; + + VLOG_DBG("rte flow icmp pattern:\n"); + if (icmp_spec) { + VLOG_DBG(" spec: icmp_type=%"PRIu8", icmp_code=%"PRIu8"\n", + ntohs(icmp_spec->hdr.icmp_type), + ntohs(icmp_spec->hdr.icmp_code)); + } else { + VLOG_DBG(" spec = null\n"); + } + if (icmp_mask) { + VLOG_DBG(" mask: icmp_type=0x%"PRIx8", icmp_code=0x%"PRIx8"\n", + icmp_spec->hdr.icmp_type, + icmp_spec->hdr.icmp_code); + } else { + VLOG_DBG(" mask = null\n"); + } + } + + if (item->type == RTE_FLOW_ITEM_TYPE_TCP) { + const struct rte_flow_item_tcp *tcp_spec = item->spec; + const struct rte_flow_item_tcp *tcp_mask = item->mask; + + VLOG_DBG("rte flow tcp pattern:\n"); + if (tcp_spec) { + VLOG_DBG(" spec: src_port=%"PRIu16", dst_port=%"PRIu16 + ", data_off=0x%"PRIx8", tcp_flags=0x%"PRIx8"\n", + ntohs(tcp_spec->hdr.src_port), + ntohs(tcp_spec->hdr.dst_port), + tcp_spec->hdr.data_off, + tcp_spec->hdr.tcp_flags); + } else { + VLOG_DBG(" spec = null\n"); + } + if (tcp_mask) { + VLOG_DBG(" mask: src_port=%"PRIx16", dst_port=%"PRIx16 + ", data_off=0x%"PRIx8", tcp_flags=0x%"PRIx8"\n", + tcp_mask->hdr.src_port, + tcp_mask->hdr.dst_port, + tcp_mask->hdr.data_off, + tcp_mask->hdr.tcp_flags); + } else { + VLOG_DBG(" mask = null\n"); + } + } +} + +static void add_flow_pattern(struct flow_patterns *patterns, enum rte_flow_item_type type, const void *spec, const void *mask) { @@ -3444,6 +3620,7 @@ add_flow_pattern(struct flow_patterns *patterns, enum rte_flow_item_type type, patterns->items[cnt].spec = spec; patterns->items[cnt].mask = mask; patterns->items[cnt].last = NULL; + dump_flow_pattern(&patterns->items[cnt]); patterns->cnt++; } From patchwork Wed Dec 20 14:44:37 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yuanhan Liu X-Patchwork-Id: 851504 X-Patchwork-Delegate: ian.stokes@intel.com Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (mailfrom) smtp.mailfrom=openvswitch.org (client-ip=140.211.169.12; helo=mail.linuxfoundation.org; envelope-from=ovs-dev-bounces@openvswitch.org; receiver=) Authentication-Results: ozlabs.org; dkim=fail reason="signature verification failed" (2048-bit key; unprotected) header.d=fridaylinux.org header.i=@fridaylinux.org header.b="QejJrURS"; dkim=fail reason="signature verification failed" (2048-bit key; unprotected) header.d=messagingengine.com header.i=@messagingengine.com header.b="mkDLT3Ub"; dkim-atps=neutral Received: from mail.linuxfoundation.org (mail.linuxfoundation.org [140.211.169.12]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 3z1yLf2Hf0z9s7F for ; Thu, 21 Dec 2017 01:48:10 +1100 (AEDT) Received: from mail.linux-foundation.org (localhost [127.0.0.1]) by mail.linuxfoundation.org (Postfix) with ESMTP id C1CEDCBF; Wed, 20 Dec 2017 14:45:45 +0000 (UTC) X-Original-To: dev@openvswitch.org Delivered-To: ovs-dev@mail.linuxfoundation.org Received: from smtp1.linuxfoundation.org (smtp1.linux-foundation.org [172.17.192.35]) by mail.linuxfoundation.org (Postfix) with ESMTPS id 9B8BDC96 for ; Wed, 20 Dec 2017 14:45:44 +0000 (UTC) X-Greylist: from auto-whitelisted by SQLgrey-1.7.6 Received: from out3-smtp.messagingengine.com (out3-smtp.messagingengine.com [66.111.4.27]) by smtp1.linuxfoundation.org (Postfix) with ESMTPS id B41A83D9 for ; Wed, 20 Dec 2017 14:45:43 +0000 (UTC) Received: from compute1.internal (compute1.nyi.internal [10.202.2.41]) by mailout.nyi.internal (Postfix) with ESMTP id 1D8AD20BBE; Wed, 20 Dec 2017 09:45:43 -0500 (EST) Received: from frontend1 ([10.202.2.160]) by compute1.internal (MEProxy); Wed, 20 Dec 2017 09:45:43 -0500 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=fridaylinux.org; h=cc:date:from:in-reply-to:message-id:references:subject:to :x-me-sender:x-me-sender:x-sasl-enc; s=fm1; bh=+LBYA9/FJBcWCZjcm hSOcuG06IW4RsmGPJRuS6jgiTg=; b=QejJrURSZZNGcNRFABAxVYqeT2ear3Hqi PesGmbc6RYq4Lv78AGD1QR13WG+QCvr+tysl51Qo+fwk/x8d3ri9z/36dwOCJjli bM+AD4HsUx+xiOel2ceWWW/gqDMmigRL9ekpxrfykdE/LRzl4SHYK1SjQRHTTA8i TSq3u4EmgamOWzr6lnnLONfND6TcEM96ix1ZE2nZ2e0C5Tk/ukWx8BiPD3ULiS4z fgp/Og+OehaIhOgfiqyoQ0tghrsFDHRC8Pe/98RP897AU33CzN77wVtAnyATc+Bm SAGtwtrFteKg/dkpw+51PFtRj4EQDxvfZ1T3H4OAujBCRnZKgaR3A== DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:date:from:in-reply-to:message-id :references:subject:to:x-me-sender:x-me-sender:x-sasl-enc; s= fm1; bh=+LBYA9/FJBcWCZjcmhSOcuG06IW4RsmGPJRuS6jgiTg=; b=mkDLT3Ub yM+mFDZBgO/DVE2kiN4pAeaSJTdWLSTs6x4rESGMB/sUsZx80Bq9+oOELT+qE7At aTRhxnmW4xi9a4IdDyY1qDFbfB0IAgr+808apj0l7tp/9rmM0TYXhj3zbtHwWaTV 4ilGVpUxVgUqBxHzOrnBCAxwWFOViyCexSNF75oWFMSd8bRHUozJeEPuObELwP4B 3S7Ohz+w3OsNWiPoprU2Kz0VDxV4F01d36JxEXTl+X/I2urVhH9J6LuvktmWDy26 X64BJgX6Nc7EeNKHkYstL2QwfLuGF2g912kogmoeOE6zeiOGroHRAvsxJXHxh45A bob2d7l13paBFw== X-ME-Sender: Received: from yliu-dev.mtl.com (unknown [115.148.91.103]) by mail.messagingengine.com (Postfix) with ESMTPA id B26ED7E4FA; Wed, 20 Dec 2017 09:45:29 -0500 (EST) From: Yuanhan Liu To: dev@openvswitch.org Date: Wed, 20 Dec 2017 22:44:37 +0800 Message-Id: <1513781077-21984-6-git-send-email-yliu@fridaylinux.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1513781077-21984-1-git-send-email-yliu@fridaylinux.org> References: <1513781077-21984-1-git-send-email-yliu@fridaylinux.org> X-Spam-Status: No, score=-2.7 required=5.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, RCVD_IN_DNSWL_LOW autolearn=ham version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on smtp1.linux-foundation.org Cc: Simon Horman Subject: [ovs-dev] [PATCH v5 5/5] dpif-netdev: do hw flow offload in a thread X-BeenThere: ovs-dev@openvswitch.org X-Mailman-Version: 2.1.12 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Sender: ovs-dev-bounces@openvswitch.org Errors-To: ovs-dev-bounces@openvswitch.org Currently, the major trigger for hw flow offload is at upcall handling, which is actually in the datapath. Moreover, the hw offload installation and modification is not that lightweight. Meaning, if there are so many flows being added or modified frequently, it could stall the datapath, which could result to packet loss. To diminish that, all those flow operations will be recorded and appended to a list. A thread is then introduced to process this list (to do the real flow offloading put/del operations). This could leave the datapath as lightweight as possible. Signed-off-by: Yuanhan Liu --- v5: - removed an not-used mutex lock --- lib/dpif-netdev.c | 319 +++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 243 insertions(+), 76 deletions(-) diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c index b8e03db..e4dda07 100644 --- a/lib/dpif-netdev.c +++ b/lib/dpif-netdev.c @@ -1849,13 +1849,11 @@ struct flow_mark { struct cmap megaflow_to_mark; struct cmap mark_to_flow; struct id_pool *pool; - struct ovs_mutex mutex; }; struct flow_mark flow_mark = { .megaflow_to_mark = CMAP_INITIALIZER, .mark_to_flow = CMAP_INITIALIZER, - .mutex = OVS_MUTEX_INITIALIZER, }; static uint32_t @@ -1990,6 +1988,8 @@ mark_to_flow_disassociate(struct dp_netdev_pmd_thread *pmd, return ret; } +static void queue_netdev_flow_del(struct dp_netdev_pmd_thread *pmd, + struct dp_netdev_flow *flow); static void flow_mark_flush(struct dp_netdev_pmd_thread *pmd) { @@ -1997,7 +1997,7 @@ flow_mark_flush(struct dp_netdev_pmd_thread *pmd) CMAP_FOR_EACH (flow, mark_node, &flow_mark.mark_to_flow) { if (flow->pmd_id == pmd->core_id) { - mark_to_flow_disassociate(pmd, flow); + queue_netdev_flow_del(pmd, flow); } } } @@ -2018,6 +2018,242 @@ mark_to_flow_find(const struct dp_netdev_pmd_thread *pmd, return NULL; } +enum { + DP_NETDEV_FLOW_OFFLOAD_OP_ADD, + DP_NETDEV_FLOW_OFFLOAD_OP_MOD, + DP_NETDEV_FLOW_OFFLOAD_OP_DEL, +}; + +struct dp_flow_offload_item { + struct dp_netdev_pmd_thread *pmd; + struct dp_netdev_flow *flow; + int op; + struct match match; + struct nlattr *actions; + size_t actions_len; + + struct ovs_list node; +}; + +struct dp_flow_offload { + struct ovs_mutex mutex; + struct ovs_list list; + pthread_cond_t cond; +}; + +static struct dp_flow_offload dp_flow_offload = { + .mutex = OVS_MUTEX_INITIALIZER, + .list = OVS_LIST_INITIALIZER(&dp_flow_offload.list), +}; + +static struct ovsthread_once offload_thread_once + = OVSTHREAD_ONCE_INITIALIZER; + +static struct dp_flow_offload_item * +dp_netdev_alloc_flow_offload(struct dp_netdev_pmd_thread *pmd, + struct dp_netdev_flow *flow, + int op) +{ + struct dp_flow_offload_item *offload; + + offload = xzalloc(sizeof(*offload)); + offload->pmd = pmd; + offload->flow = flow; + offload->op = op; + + dp_netdev_flow_ref(flow); + dp_netdev_pmd_try_ref(pmd); + + return offload; +} + +static void +dp_netdev_free_flow_offload(struct dp_flow_offload_item *offload) +{ + dp_netdev_pmd_unref(offload->pmd); + dp_netdev_flow_unref(offload->flow); + + free(offload->actions); + free(offload); +} + +static void +dp_netdev_append_flow_offload(struct dp_flow_offload_item *offload) +{ + ovs_mutex_lock(&dp_flow_offload.mutex); + ovs_list_push_back(&dp_flow_offload.list, &offload->node); + xpthread_cond_signal(&dp_flow_offload.cond); + ovs_mutex_unlock(&dp_flow_offload.mutex); +} + +static int +dp_netdev_flow_offload_del(struct dp_flow_offload_item *offload) +{ + return mark_to_flow_disassociate(offload->pmd, offload->flow); +} + +static int +dp_netdev_flow_offload_put(struct dp_flow_offload_item *offload) +{ + struct dp_netdev_port *port; + struct dp_netdev_flow *flow = offload->flow; + odp_port_t in_port = flow->flow.in_port.odp_port; + bool modification = offload->op == DP_NETDEV_FLOW_OFFLOAD_OP_MOD; + struct offload_info info; + uint32_t mark; + int ret; + + if (flow->dead) { + return -1; + } + + port = dp_netdev_lookup_port(offload->pmd->dp, in_port); + if (!port) { + return -1; + } + + if (modification) { + mark = flow->mark; + ovs_assert(mark != INVALID_FLOW_MARK); + } else { + /* + * If a mega flow has already been offloaded (from other PMD + * instances), do not offload it again. + */ + mark = megaflow_to_mark_find(&flow->mega_ufid); + if (mark != INVALID_FLOW_MARK) { + VLOG_DBG("flow has already been offloaded with mark %u\n", mark); + if (flow->mark != INVALID_FLOW_MARK) { + ovs_assert(flow->mark == mark); + } else { + mark_to_flow_associate(mark, flow); + } + return 0; + } + + mark = flow_mark_alloc(); + if (mark == INVALID_FLOW_MARK) { + VLOG_ERR("failed to allocate flow mark!\n"); + } + } + + info.flow_mark = mark; + ret = netdev_flow_put(port->netdev, &offload->match, + CONST_CAST(struct nlattr *, offload->actions), + offload->actions_len, &flow->mega_ufid, &info, + NULL); + if (ret) { + if (!modification) { + flow_mark_free(mark); + } else { + mark_to_flow_disassociate(offload->pmd, flow); + } + return -1; + } + + if (!modification) { + megaflow_to_mark_associate(&flow->mega_ufid, mark); + mark_to_flow_associate(mark, flow); + } + + return 0; +} + +static void * +dp_netdev_flow_offload_main(void *data OVS_UNUSED) +{ + struct dp_flow_offload_item *offload; + struct ovs_list *list; + const char *op; + int ret; + + for (;;) { + ovs_mutex_lock(&dp_flow_offload.mutex); + if (ovs_list_is_empty(&dp_flow_offload.list)) { + ovsrcu_quiesce_start(); + ovs_mutex_cond_wait(&dp_flow_offload.cond, + &dp_flow_offload.mutex); + } + list = ovs_list_pop_front(&dp_flow_offload.list); + offload = CONTAINER_OF(list, struct dp_flow_offload_item, node); + ovs_mutex_unlock(&dp_flow_offload.mutex); + + switch (offload->op) { + case DP_NETDEV_FLOW_OFFLOAD_OP_ADD: + op = "add"; + ret = dp_netdev_flow_offload_put(offload); + break; + case DP_NETDEV_FLOW_OFFLOAD_OP_MOD: + op = "modify"; + ret = dp_netdev_flow_offload_put(offload); + break; + case DP_NETDEV_FLOW_OFFLOAD_OP_DEL: + op = "delete"; + ret = dp_netdev_flow_offload_del(offload); + break; + default: + OVS_NOT_REACHED(); + } + + VLOG_DBG("%s to %s netdev flow\n", + ret == 0 ? "succeed" : "failed", op); + dp_netdev_free_flow_offload(offload); + } + + return NULL; +} + +static void +queue_netdev_flow_del(struct dp_netdev_pmd_thread *pmd, + struct dp_netdev_flow *flow) +{ + struct dp_flow_offload_item *offload; + + if (ovsthread_once_start(&offload_thread_once)) { + xpthread_cond_init(&dp_flow_offload.cond, NULL); + ovs_thread_create("dp_netdev_flow_offload", + dp_netdev_flow_offload_main, NULL); + ovsthread_once_done(&offload_thread_once); + } + + offload = dp_netdev_alloc_flow_offload(pmd, flow, + DP_NETDEV_FLOW_OFFLOAD_OP_DEL); + dp_netdev_append_flow_offload(offload); +} + +static void +queue_netdev_flow_put(struct dp_netdev_pmd_thread *pmd, + struct dp_netdev_flow *flow, struct match *match, + const struct nlattr *actions, size_t actions_len) +{ + struct dp_flow_offload_item *offload; + int op; + + if (!netdev_is_flow_api_enabled()) { + return; + } + + if (ovsthread_once_start(&offload_thread_once)) { + xpthread_cond_init(&dp_flow_offload.cond, NULL); + ovs_thread_create("dp_netdev_flow_offload", + dp_netdev_flow_offload_main, NULL); + ovsthread_once_done(&offload_thread_once); + } + + if (flow->mark != INVALID_FLOW_MARK) { + op = DP_NETDEV_FLOW_OFFLOAD_OP_MOD; + } else { + op = DP_NETDEV_FLOW_OFFLOAD_OP_ADD; + } + offload = dp_netdev_alloc_flow_offload(pmd, flow, op); + offload->match = *match; + offload->actions = xmalloc(actions_len); + memcpy(offload->actions, actions, actions_len); + offload->actions_len = actions_len; + + dp_netdev_append_flow_offload(offload); +} + static void dp_netdev_pmd_remove_flow(struct dp_netdev_pmd_thread *pmd, struct dp_netdev_flow *flow) @@ -2032,7 +2268,7 @@ dp_netdev_pmd_remove_flow(struct dp_netdev_pmd_thread *pmd, dpcls_remove(cls, &flow->cr); cmap_remove(&pmd->flow_table, node, dp_netdev_flow_hash(&flow->ufid)); if (flow->mark != INVALID_FLOW_MARK) { - mark_to_flow_disassociate(pmd, flow); + queue_netdev_flow_del(pmd, flow); } flow->dead = true; @@ -2614,74 +2850,6 @@ out: } static void -try_netdev_flow_put(struct dp_netdev_pmd_thread *pmd, odp_port_t in_port, - struct dp_netdev_flow *flow, struct match *match, - const struct nlattr *actions, size_t actions_len) -{ - struct offload_info info; - struct dp_netdev_port *port; - bool modification = flow->mark != INVALID_FLOW_MARK; - const char *op = modification ? "modify" : "add"; - uint32_t mark; - int ret; - - port = dp_netdev_lookup_port(pmd->dp, in_port); - if (!port) { - return; - } - - ovs_mutex_lock(&flow_mark.mutex); - - if (modification) { - mark = flow->mark; - } else { - if (!netdev_is_flow_api_enabled()) { - goto out; - } - - /* - * If a mega flow has already been offloaded (from other PMD - * instances), do not offload it again. - */ - mark = megaflow_to_mark_find(&flow->mega_ufid); - if (mark != INVALID_FLOW_MARK) { - VLOG_DBG("flow has already been offloaded with mark %u\n", mark); - mark_to_flow_associate(mark, flow); - goto out; - } - - mark = flow_mark_alloc(); - if (mark == INVALID_FLOW_MARK) { - VLOG_ERR("failed to allocate flow mark!\n"); - goto out; - } - } - - info.flow_mark = mark; - ret = netdev_flow_put(port->netdev, match, - CONST_CAST(struct nlattr *, actions), - actions_len, &flow->mega_ufid, &info, NULL); - if (ret) { - VLOG_ERR("failed to %s netdev flow with mark %u\n", op, mark); - if (!modification) { - flow_mark_free(mark); - } else { - mark_to_flow_disassociate(pmd, flow); - } - goto out; - } - - if (!modification) { - megaflow_to_mark_associate(&flow->mega_ufid, mark); - mark_to_flow_associate(mark, flow); - } - VLOG_DBG("succeed to %s netdev flow with mark %u\n", op, mark); - -out: - ovs_mutex_unlock(&flow_mark.mutex); -} - -static void dp_netdev_get_mega_ufid(const struct match *match, ovs_u128 *mega_ufid) { struct flow masked_flow; @@ -2746,7 +2914,7 @@ dp_netdev_flow_add(struct dp_netdev_pmd_thread *pmd, cmap_insert(&pmd->flow_table, CONST_CAST(struct cmap_node *, &flow->node), dp_netdev_flow_hash(&flow->ufid)); - try_netdev_flow_put(pmd, in_port, flow, match, actions, actions_len); + queue_netdev_flow_put(pmd, flow, match, actions, actions_len); if (OVS_UNLIKELY(!VLOG_DROP_DBG((&upcall_rl)))) { struct ds ds = DS_EMPTY_INITIALIZER; @@ -2828,7 +2996,6 @@ flow_put_on_pmd(struct dp_netdev_pmd_thread *pmd, if (put->flags & DPIF_FP_MODIFY) { struct dp_netdev_actions *new_actions; struct dp_netdev_actions *old_actions; - odp_port_t in_port = netdev_flow->flow.in_port.odp_port; new_actions = dp_netdev_actions_create(put->actions, put->actions_len); @@ -2836,8 +3003,8 @@ flow_put_on_pmd(struct dp_netdev_pmd_thread *pmd, old_actions = dp_netdev_flow_get_actions(netdev_flow); ovsrcu_set(&netdev_flow->actions, new_actions); - try_netdev_flow_put(pmd, in_port, netdev_flow, match, - put->actions, put->actions_len); + queue_netdev_flow_put(pmd, netdev_flow, match, + put->actions, put->actions_len); if (stats) { get_dpif_flow_stats(netdev_flow, stats);