From patchwork Tue Jun 23 21:39:27 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Lorenzo Bianconi X-Patchwork-Id: 217269 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-10.1 required=3.0 tests=DKIMWL_WL_HIGH, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, INCLUDES_PATCH, MAILING_LIST_MULTI, SIGNED_OFF_BY, SPF_HELO_NONE, SPF_PASS, URIBL_BLOCKED, USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 93713C433E0 for ; Tue, 23 Jun 2020 21:40:09 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 6E0DC20836 for ; Tue, 23 Jun 2020 21:40:09 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1592948409; bh=MAAIjogYPvF6bZtEPj7QH+K5jjnZ8/fLW8FlZpUuk6Q=; h=From:To:Cc:Subject:Date:In-Reply-To:References:List-ID:From; b=OwzEjm+IpB5TuxB72GOtlRx1sbZakxhPh5N+jKKIIm7oUOMUABQUgNnf4SXfICh/h FmQyW0E8l5pa8m2ju3UZuQxz8W9wtnIExQ5GiZAu0L7s4gcd0rct51Ygs/Y07X06Ld T1FQm9wdJrxi2LnOkqvlXvaSkKeL2H9K9mzh9eVo= Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2393904AbgFWVkG (ORCPT ); Tue, 23 Jun 2020 17:40:06 -0400 Received: from mail.kernel.org ([198.145.29.99]:57908 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2393947AbgFWVj7 (ORCPT ); Tue, 23 Jun 2020 17:39:59 -0400 Received: from localhost.localdomain.com (unknown [151.48.138.186]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id 0068B206E2; Tue, 23 Jun 2020 21:39:56 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1592948399; bh=MAAIjogYPvF6bZtEPj7QH+K5jjnZ8/fLW8FlZpUuk6Q=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=ptVXjDv132lxrai9ONruLL7Esb3V3tcu037bRSTreRmOPsIy68ucoWIdjChhHQfl0 +B1cioJkMn0YjHg0fyW5RjOeJ72ZqM82P5K5r9SnUbYWdttuR5D1S7m48eiESyJZuq 0ukwLV8IWc83Ad2+u//grqo8/dEmjJ/2kkwSnOqQ= From: Lorenzo Bianconi To: netdev@vger.kernel.org, bpf@vger.kernel.org Cc: davem@davemloft.net, ast@kernel.org, brouer@redhat.com, daniel@iogearbox.net, toke@redhat.com, lorenzo.bianconi@redhat.com, dsahern@kernel.org, andrii.nakryiko@gmail.com, David Ahern Subject: [PATCH v3 bpf-next 2/9] net: Refactor xdp_convert_buff_to_frame Date: Tue, 23 Jun 2020 23:39:27 +0200 Message-Id: <0f32f3dd1787f050b41ab1d32490b838544fe3e2.1592947694.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.26.2 In-Reply-To: References: MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: David Ahern Move the guts of xdp_convert_buff_to_frame to a new helper, xdp_update_frame_from_buff so it can be reused removing code duplication Suggested-by: Jesper Dangaard Brouer Co-developed-by: Lorenzo Bianconi Signed-off-by: Lorenzo Bianconi Signed-off-by: David Ahern --- include/net/xdp.h | 35 ++++++++++++++++++++++------------- 1 file changed, 22 insertions(+), 13 deletions(-) diff --git a/include/net/xdp.h b/include/net/xdp.h index 609f819ed08b..5b383c450858 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -121,39 +121,48 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) xdp->frame_sz = frame->frame_sz; } -/* Convert xdp_buff to xdp_frame */ static inline -struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) +int xdp_update_frame_from_buff(struct xdp_buff *xdp, + struct xdp_frame *xdp_frame) { - struct xdp_frame *xdp_frame; - int metasize; - int headroom; - - if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) - return xdp_convert_zc_to_xdp_frame(xdp); + int metasize, headroom; /* Assure headroom is available for storing info */ headroom = xdp->data - xdp->data_hard_start; metasize = xdp->data - xdp->data_meta; metasize = metasize > 0 ? metasize : 0; if (unlikely((headroom - metasize) < sizeof(*xdp_frame))) - return NULL; + return -ENOSPC; /* Catch if driver didn't reserve tailroom for skb_shared_info */ if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) { XDP_WARN("Driver BUG: missing reserved tailroom"); - return NULL; + return -ENOSPC; } - /* Store info in top of packet */ - xdp_frame = xdp->data_hard_start; - xdp_frame->data = xdp->data; xdp_frame->len = xdp->data_end - xdp->data; xdp_frame->headroom = headroom - sizeof(*xdp_frame); xdp_frame->metasize = metasize; xdp_frame->frame_sz = xdp->frame_sz; + return 0; +} + +/* Convert xdp_buff to xdp_frame */ +static inline +struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) +{ + struct xdp_frame *xdp_frame; + + if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) + return xdp_convert_zc_to_xdp_frame(xdp); + + /* Store info in top of packet */ + xdp_frame = xdp->data_hard_start; + if (unlikely(xdp_update_frame_from_buff(xdp, xdp_frame) < 0)) + return NULL; + /* rxq only valid until napi_schedule ends, convert to xdp_mem_info */ xdp_frame->mem = xdp->rxq->mem; From patchwork Tue Jun 23 21:39:29 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Lorenzo Bianconi X-Patchwork-Id: 217266 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-10.1 required=3.0 tests=DKIMWL_WL_HIGH, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, INCLUDES_PATCH, MAILING_LIST_MULTI, SIGNED_OFF_BY, SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 0FE84C433E0 for ; Tue, 23 Jun 2020 21:40:33 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id DE37F206E2 for ; Tue, 23 Jun 2020 21:40:32 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1592948432; bh=hv2b5i3Paqb8BmjecdXjJHnMWbphNIwkGd9HpD5ekOI=; h=From:To:Cc:Subject:Date:In-Reply-To:References:List-ID:From; b=YKmCt3XnmPYbtOtamVKaNX390Vrn5xRLR3ajqZq92TpJcwGaIX2a/RmDTQsHN9qFE xwl5r/i0niEsboh2FL4ac8xOGsbagkxQz94hpI5YBC8L0tQTbQdPYAGhuWdPHuqr5L zuDZRQNYGmqr51eyAhgLscjw4d+Jp6xalPQ5yLXw= Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2394040AbgFWVkO (ORCPT ); Tue, 23 Jun 2020 17:40:14 -0400 Received: from mail.kernel.org ([198.145.29.99]:58048 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2393827AbgFWVkJ (ORCPT ); Tue, 23 Jun 2020 17:40:09 -0400 Received: from localhost.localdomain.com (unknown [151.48.138.186]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id B62582078E; Tue, 23 Jun 2020 21:40:06 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1592948408; bh=hv2b5i3Paqb8BmjecdXjJHnMWbphNIwkGd9HpD5ekOI=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=saoLmcZ99uInmMm1PbHzKx36B3BKqcz3PK58Fsl0mJwwdz+41tByk/4eDtQf0TJh3 wLxkBXE3v2UZCgJAuJ1oROz5lK3J1ZmKkXR4A7CRLnODYmtrJV3X07HXuAfhGMDMDt YjyIu8khE8D9dIBKXsU6E5I7zODgdG95GDAj1B0A= From: Lorenzo Bianconi To: netdev@vger.kernel.org, bpf@vger.kernel.org Cc: davem@davemloft.net, ast@kernel.org, brouer@redhat.com, daniel@iogearbox.net, toke@redhat.com, lorenzo.bianconi@redhat.com, dsahern@kernel.org, andrii.nakryiko@gmail.com Subject: [PATCH v3 bpf-next 4/9] cpumap: formalize map value as a named struct Date: Tue, 23 Jun 2020 23:39:29 +0200 Message-Id: X-Mailer: git-send-email 2.26.2 In-Reply-To: References: MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org As it has been already done for devmap, introduce 'struct bpf_cpumap_val' to formalize the expected values that can be passed in for a CPUMAP. Update cpumap code to use the struct. Signed-off-by: Lorenzo Bianconi --- include/uapi/linux/bpf.h | 9 +++++++++ kernel/bpf/cpumap.c | 25 +++++++++++++------------ tools/include/uapi/linux/bpf.h | 9 +++++++++ 3 files changed, 31 insertions(+), 12 deletions(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 19684813faae..fa3b342985f9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3774,6 +3774,15 @@ struct bpf_devmap_val { } bpf_prog; }; +/* CPUMAP map-value layout + * + * The struct data-layout of map-value is a configuration interface. + * New members can only be added to the end of this structure. + */ +struct bpf_cpumap_val { + __u32 qsize; /* queue size to remote target CPU */ +}; + enum sk_action { SK_DROP = 0, SK_PASS, diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 323c91c4fab0..7e8eec4f7089 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -52,7 +52,6 @@ struct xdp_bulk_queue { struct bpf_cpu_map_entry { u32 cpu; /* kthread CPU and map index */ int map_id; /* Back reference to map */ - u32 qsize; /* Queue size placeholder for map lookup */ /* XDP can run multiple RX-ring queues, need __percpu enqueue store */ struct xdp_bulk_queue __percpu *bulkq; @@ -66,6 +65,8 @@ struct bpf_cpu_map_entry { atomic_t refcnt; /* Control when this struct can be free'ed */ struct rcu_head rcu; + + struct bpf_cpumap_val value; }; struct bpf_cpu_map { @@ -307,8 +308,8 @@ static int cpu_map_kthread_run(void *data) return 0; } -static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, - int map_id) +static struct bpf_cpu_map_entry * +__cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id) { gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; struct bpf_cpu_map_entry *rcpu; @@ -338,13 +339,13 @@ static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, if (!rcpu->queue) goto free_bulkq; - err = ptr_ring_init(rcpu->queue, qsize, gfp); + err = ptr_ring_init(rcpu->queue, value->qsize, gfp); if (err) goto free_queue; rcpu->cpu = cpu; rcpu->map_id = map_id; - rcpu->qsize = qsize; + rcpu->value.qsize = value->qsize; /* Setup kthread */ rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa, @@ -437,12 +438,12 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + struct bpf_cpumap_val cpumap_value = {}; struct bpf_cpu_map_entry *rcpu; - /* Array index key correspond to CPU number */ u32 key_cpu = *(u32 *)key; - /* Value is the queue size */ - u32 qsize = *(u32 *)value; + + memcpy(&cpumap_value, value, map->value_size); if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; @@ -450,18 +451,18 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, return -E2BIG; if (unlikely(map_flags == BPF_NOEXIST)) return -EEXIST; - if (unlikely(qsize > 16384)) /* sanity limit on qsize */ + if (unlikely(cpumap_value.qsize > 16384)) /* sanity limit on qsize */ return -EOVERFLOW; /* Make sure CPU is a valid possible cpu */ if (key_cpu >= nr_cpumask_bits || !cpu_possible(key_cpu)) return -ENODEV; - if (qsize == 0) { + if (cpumap_value.qsize == 0) { rcpu = NULL; /* Same as deleting */ } else { /* Updating qsize cause re-allocation of bpf_cpu_map_entry */ - rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id); + rcpu = __cpu_map_entry_alloc(&cpumap_value, key_cpu, map->id); if (!rcpu) return -ENOMEM; rcpu->cmap = cmap; @@ -523,7 +524,7 @@ static void *cpu_map_lookup_elem(struct bpf_map *map, void *key) struct bpf_cpu_map_entry *rcpu = __cpu_map_lookup_elem(map, *(u32 *)key); - return rcpu ? &rcpu->qsize : NULL; + return rcpu ? &rcpu->value : NULL; } static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 19684813faae..fa3b342985f9 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3774,6 +3774,15 @@ struct bpf_devmap_val { } bpf_prog; }; +/* CPUMAP map-value layout + * + * The struct data-layout of map-value is a configuration interface. + * New members can only be added to the end of this structure. + */ +struct bpf_cpumap_val { + __u32 qsize; /* queue size to remote target CPU */ +}; + enum sk_action { SK_DROP = 0, SK_PASS, From patchwork Tue Jun 23 21:39:30 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Lorenzo Bianconi X-Patchwork-Id: 217268 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-10.1 required=3.0 tests=DKIMWL_WL_HIGH, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, INCLUDES_PATCH, MAILING_LIST_MULTI, SIGNED_OFF_BY, SPF_HELO_NONE, SPF_PASS, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id AC289C433DF for ; Tue, 23 Jun 2020 21:40:19 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 775B02078A for ; Tue, 23 Jun 2020 21:40:19 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1592948419; bh=GkFvgxVWqKOU0Jwgf2uzlNON6UZQ+UK1+twa9d8kmVE=; h=From:To:Cc:Subject:Date:In-Reply-To:References:List-ID:From; b=i3j727Ok2VS90QuD3MY6Mm1UoTotO7nitj9Ozo6aDPnS3t9PzBATCSiMnCuMsXWhB 1KJpA6mVMIH8vvSUXkxDpQqk2oPZ01Ie7fzbEYy/xUSLnY39K9KBE401KGggJF1mSt GFo5k6Acxlm8hoacSI2zqjqdeuaadm0P6vRJw2cs= Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2388502AbgFWVkQ (ORCPT ); Tue, 23 Jun 2020 17:40:16 -0400 Received: from mail.kernel.org ([198.145.29.99]:58084 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2394027AbgFWVkM (ORCPT ); Tue, 23 Jun 2020 17:40:12 -0400 Received: from localhost.localdomain.com (unknown [151.48.138.186]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id 0FBC0206E2; Tue, 23 Jun 2020 21:40:08 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1592948411; bh=GkFvgxVWqKOU0Jwgf2uzlNON6UZQ+UK1+twa9d8kmVE=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=dV9NuLg1hWkrcdaHw2BmRboeuCQaQBdePFe0md5bigRcy0I7kFs/o/o/zVbjUUOi1 SlBUQfrDoAembRP6QOMejp41wPHnfOsJ4Ur6WxKj2SFIpN/E57s27hg1mzeefGeBdP G+R9iE2Hqe1g/Yu6ICFnV2eYTxmZ9JisRbATvlbg= From: Lorenzo Bianconi To: netdev@vger.kernel.org, bpf@vger.kernel.org Cc: davem@davemloft.net, ast@kernel.org, brouer@redhat.com, daniel@iogearbox.net, toke@redhat.com, lorenzo.bianconi@redhat.com, dsahern@kernel.org, andrii.nakryiko@gmail.com Subject: [PATCH v3 bpf-next 5/9] bpf: cpumap: add the possibility to attach an eBPF program to cpumap Date: Tue, 23 Jun 2020 23:39:30 +0200 Message-Id: <7f40456531a507b53e30165afa229b4e2a22e8e7.1592947694.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.26.2 In-Reply-To: References: MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Introduce the capability to attach an eBPF program to cpumap entries. The idea behind this feature is to add the possibility to define on which CPU run the eBPF program if the underlying hw does not support RSS. Current supported verdicts are XDP_DROP and XDP_PASS. This patch has been tested on Marvell ESPRESSObin using xdp_redirect_cpu sample available in the kernel tree to identify possible performance regressions. Results show there are no observable differences in packet-per-second: $./xdp_redirect_cpu --progname xdp_cpu_map0 --dev eth0 --cpu 1 rx: 354.8 Kpps rx: 356.0 Kpps rx: 356.8 Kpps rx: 356.3 Kpps rx: 356.6 Kpps rx: 356.6 Kpps rx: 356.7 Kpps rx: 355.8 Kpps rx: 356.8 Kpps rx: 356.8 Kpps Co-developed-by: Jesper Dangaard Brouer Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi --- include/linux/bpf.h | 6 ++ include/net/xdp.h | 5 ++ include/trace/events/xdp.h | 14 ++-- include/uapi/linux/bpf.h | 5 ++ kernel/bpf/cpumap.c | 122 +++++++++++++++++++++++++++++---- net/core/dev.c | 8 +++ tools/include/uapi/linux/bpf.h | 5 ++ 7 files changed, 148 insertions(+), 17 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1e1501ee53ce..759f280265d0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1265,6 +1265,7 @@ struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); void __cpu_map_flush(void); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx); +bool cpu_map_prog_allowed(struct bpf_map *map); /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) @@ -1425,6 +1426,11 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, return 0; } +static inline bool cpu_map_prog_allowed(struct bpf_map *map) +{ + return false; +} + static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) { diff --git a/include/net/xdp.h b/include/net/xdp.h index 5b383c450858..83b9e0142b52 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -98,6 +98,11 @@ struct xdp_frame { struct net_device *dev_rx; /* used by cpumap */ }; +struct xdp_cpumap_stats { + unsigned int pass; + unsigned int drop; +}; + /* Clear kernel pointers in xdp_frame */ static inline void xdp_scrub_frame(struct xdp_frame *frame) { diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index b73d3e141323..e2c99f5bee39 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -177,9 +177,9 @@ DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err, TRACE_EVENT(xdp_cpumap_kthread, TP_PROTO(int map_id, unsigned int processed, unsigned int drops, - int sched), + int sched, struct xdp_cpumap_stats *xdp_stats), - TP_ARGS(map_id, processed, drops, sched), + TP_ARGS(map_id, processed, drops, sched, xdp_stats), TP_STRUCT__entry( __field(int, map_id) @@ -188,6 +188,8 @@ TRACE_EVENT(xdp_cpumap_kthread, __field(unsigned int, drops) __field(unsigned int, processed) __field(int, sched) + __field(unsigned int, xdp_pass) + __field(unsigned int, xdp_drop) ), TP_fast_assign( @@ -197,16 +199,20 @@ TRACE_EVENT(xdp_cpumap_kthread, __entry->drops = drops; __entry->processed = processed; __entry->sched = sched; + __entry->xdp_pass = xdp_stats->pass; + __entry->xdp_drop = xdp_stats->drop; ), TP_printk("kthread" " cpu=%d map_id=%d action=%s" " processed=%u drops=%u" - " sched=%d", + " sched=%d" + " xdp_pass=%u xdp_drop=%u", __entry->cpu, __entry->map_id, __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), __entry->processed, __entry->drops, - __entry->sched) + __entry->sched, + __entry->xdp_pass, __entry->xdp_drop) ); TRACE_EVENT(xdp_cpumap_enqueue, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index fa3b342985f9..856c8db22517 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -226,6 +226,7 @@ enum bpf_attach_type { BPF_CGROUP_INET4_GETSOCKNAME, BPF_CGROUP_INET6_GETSOCKNAME, BPF_XDP_DEVMAP, + BPF_XDP_CPUMAP, __MAX_BPF_ATTACH_TYPE }; @@ -3781,6 +3782,10 @@ struct bpf_devmap_val { */ struct bpf_cpumap_val { __u32 qsize; /* queue size to remote target CPU */ + union { + int fd; /* prog fd on map write */ + __u32 id; /* prog id on map read */ + } bpf_prog; }; enum sk_action { diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 7e8eec4f7089..4e4cd240f07b 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -67,6 +67,7 @@ struct bpf_cpu_map_entry { struct rcu_head rcu; struct bpf_cpumap_val value; + struct bpf_prog *prog; }; struct bpf_cpu_map { @@ -81,6 +82,7 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq); static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) { + u32 value_size = attr->value_size; struct bpf_cpu_map *cmap; int err = -ENOMEM; u64 cost; @@ -91,7 +93,9 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + (value_size != offsetofend(struct bpf_cpumap_val, qsize) && + value_size != offsetofend(struct bpf_cpumap_val, bpf_prog.fd)) || + attr->map_flags & ~BPF_F_NUMA_NODE) return ERR_PTR(-EINVAL); cmap = kzalloc(sizeof(*cmap), GFP_USER); @@ -221,6 +225,63 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) } } +static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, + void **frames, int n, + struct xdp_cpumap_stats *stats) +{ + struct xdp_rxq_info rxq; + struct bpf_prog *prog; + struct xdp_buff xdp; + int i, nframes = 0; + + if (!rcpu->prog) + return n; + + xdp_set_return_frame_no_direct(); + xdp.rxq = &rxq; + + rcu_read_lock(); + + prog = READ_ONCE(rcpu->prog); + for (i = 0; i < n; i++) { + struct xdp_frame *xdpf = frames[i]; + u32 act; + int err; + + rxq.dev = xdpf->dev_rx; + rxq.mem = xdpf->mem; + /* TODO: report queue_index to xdp_rxq_info */ + + xdp_convert_frame_to_buff(xdpf, &xdp); + + act = bpf_prog_run_xdp(prog, &xdp); + switch (act) { + case XDP_PASS: + err = xdp_update_frame_from_buff(&xdp, xdpf); + if (err < 0) { + xdp_return_frame(xdpf); + stats->drop++; + } else { + frames[nframes++] = xdpf; + stats->pass++; + } + break; + default: + bpf_warn_invalid_xdp_action(act); + /* fallthrough */ + case XDP_DROP: + xdp_return_frame(xdpf); + stats->drop++; + break; + } + } + + rcu_read_unlock(); + xdp_clear_return_frame_no_direct(); + + return nframes; +} + #define CPUMAP_BATCH 8 static int cpu_map_kthread_run(void *data) @@ -235,11 +296,12 @@ static int cpu_map_kthread_run(void *data) * kthread_stop signal until queue is empty. */ while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) { + struct xdp_cpumap_stats stats = {}; /* zero stats */ + gfp_t gfp = __GFP_ZERO | GFP_ATOMIC; unsigned int drops = 0, sched = 0; void *frames[CPUMAP_BATCH]; void *skbs[CPUMAP_BATCH]; - gfp_t gfp = __GFP_ZERO | GFP_ATOMIC; - int i, n, m; + int i, n, m, nframes; /* Release CPU reschedule checks */ if (__ptr_ring_empty(rcpu->queue)) { @@ -260,8 +322,8 @@ static int cpu_map_kthread_run(void *data) * kthread CPU pinned. Lockless access to ptr_ring * consume side valid as no-resize allowed of queue. */ - n = __ptr_ring_consume_batched(rcpu->queue, frames, CPUMAP_BATCH); - + n = __ptr_ring_consume_batched(rcpu->queue, frames, + CPUMAP_BATCH); for (i = 0; i < n; i++) { void *f = frames[i]; struct page *page = virt_to_page(f); @@ -273,15 +335,19 @@ static int cpu_map_kthread_run(void *data) prefetchw(page); } - m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, n, skbs); - if (unlikely(m == 0)) { - for (i = 0; i < n; i++) - skbs[i] = NULL; /* effect: xdp_return_frame */ - drops = n; + /* Support running another XDP prog on this CPU */ + nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, n, &stats); + if (nframes) { + m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, skbs); + if (unlikely(m == 0)) { + for (i = 0; i < nframes; i++) + skbs[i] = NULL; /* effect: xdp_return_frame */ + drops += nframes; + } } local_bh_disable(); - for (i = 0; i < n; i++) { + for (i = 0; i < nframes; i++) { struct xdp_frame *xdpf = frames[i]; struct sk_buff *skb = skbs[i]; int ret; @@ -298,7 +364,7 @@ static int cpu_map_kthread_run(void *data) drops++; } /* Feedback loop via tracepoint */ - trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched); + trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched, &stats); local_bh_enable(); /* resched point, may call do_softirq() */ } @@ -308,13 +374,38 @@ static int cpu_map_kthread_run(void *data) return 0; } +bool cpu_map_prog_allowed(struct bpf_map *map) +{ + return map->map_type == BPF_MAP_TYPE_CPUMAP && + map->value_size != offsetofend(struct bpf_cpumap_val, qsize); +} + +static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd) +{ + struct bpf_prog *prog; + + prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, false); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + if (prog->expected_attach_type != BPF_XDP_CPUMAP) { + bpf_prog_put(prog); + return -EINVAL; + } + + rcpu->value.bpf_prog.id = prog->aux->id; + rcpu->prog = prog; + + return 0; +} + static struct bpf_cpu_map_entry * __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id) { + int numa, err, i, fd = value->bpf_prog.fd; gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; struct bpf_cpu_map_entry *rcpu; struct xdp_bulk_queue *bq; - int numa, err, i; /* Have map->numa_node, but choose node of redirect target CPU */ numa = cpu_to_node(cpu); @@ -356,6 +447,9 @@ __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id) get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */ get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */ + if (fd > 0 && __cpu_map_load_bpf_program(rcpu, fd)) + goto free_ptr_ring; + /* Make sure kthread runs on a single CPU */ kthread_bind(rcpu->kthread, cpu); wake_up_process(rcpu->kthread); @@ -415,6 +509,8 @@ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu); if (old_rcpu) { + if (old_rcpu->prog) + bpf_prog_put(old_rcpu->prog); call_rcu(&old_rcpu->rcu, __cpu_map_entry_free); INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop); schedule_work(&old_rcpu->kthread_stop_wq); diff --git a/net/core/dev.c b/net/core/dev.c index 6bc2388141f6..2867df05cf82 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5440,6 +5440,8 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) for (i = 0; i < new->aux->used_map_cnt; i++) { if (dev_map_can_have_prog(new->aux->used_maps[i])) return -EINVAL; + if (cpu_map_prog_allowed(new->aux->used_maps[i])) + return -EINVAL; } } @@ -8864,6 +8866,12 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, return -EINVAL; } + if (prog->expected_attach_type == BPF_XDP_CPUMAP) { + NL_SET_ERR_MSG(extack, "BPF_XDP_CPUMAP programs can not be attached to a device"); + bpf_prog_put(prog); + return -EINVAL; + } + /* prog->aux->id may be 0 for orphaned device-bound progs */ if (prog->aux->id && prog->aux->id == prog_id) { bpf_prog_put(prog); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index fa3b342985f9..856c8db22517 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -226,6 +226,7 @@ enum bpf_attach_type { BPF_CGROUP_INET4_GETSOCKNAME, BPF_CGROUP_INET6_GETSOCKNAME, BPF_XDP_DEVMAP, + BPF_XDP_CPUMAP, __MAX_BPF_ATTACH_TYPE }; @@ -3781,6 +3782,10 @@ struct bpf_devmap_val { */ struct bpf_cpumap_val { __u32 qsize; /* queue size to remote target CPU */ + union { + int fd; /* prog fd on map write */ + __u32 id; /* prog id on map read */ + } bpf_prog; }; enum sk_action { From patchwork Tue Jun 23 21:39:33 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Lorenzo Bianconi X-Patchwork-Id: 217267 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-10.1 required=3.0 tests=DKIMWL_WL_HIGH, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, INCLUDES_PATCH, MAILING_LIST_MULTI, SIGNED_OFF_BY, SPF_HELO_NONE, SPF_PASS, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 9806FC433E0 for ; Tue, 23 Jun 2020 21:40:24 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 6DB33206E2 for ; Tue, 23 Jun 2020 21:40:24 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1592948424; bh=5FNcKNx4n/XdZZiHXIVql9Al04c7hPk3B5QDRdWbxOs=; h=From:To:Cc:Subject:Date:In-Reply-To:References:List-ID:From; b=ouP5Kv7A2MAoRsbqZwbwIqQpbQD3PQtjRRHdtQ90dwySpZMOVKpwEM3Xf72OKHDw1 fwvCEAnDJwmWEIT+87MY4FziSv7ZQPuE2O2bjB7p1+dfGMl0R6g/6CEwWdI0zyfaYE pakcDboZADLaGuXszw1JuNmNRfe2jn7azzc9Qnho= Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2394056AbgFWVkW (ORCPT ); Tue, 23 Jun 2020 17:40:22 -0400 Received: from mail.kernel.org ([198.145.29.99]:58178 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2394049AbgFWVkU (ORCPT ); Tue, 23 Jun 2020 17:40:20 -0400 Received: from localhost.localdomain.com (unknown [151.48.138.186]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id 6E38420780; Tue, 23 Jun 2020 21:40:16 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1592948418; bh=5FNcKNx4n/XdZZiHXIVql9Al04c7hPk3B5QDRdWbxOs=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=I6e6SeI3pGUFSSCFQn4yq0gkEoHZ/iH6NxXHMRZn52qL5u93jN9nXYsKmbH7nMsNF az0WllP8C/O4E1L3LlZNzQfZscaIVpypqB0uXae4Iz9ZaXmP5g4UeQjOL+pfmn95fO 61R9EdFD6ih7Guf0tfZeCd5ZG8OSC+feupnrX+M8= From: Lorenzo Bianconi To: netdev@vger.kernel.org, bpf@vger.kernel.org Cc: davem@davemloft.net, ast@kernel.org, brouer@redhat.com, daniel@iogearbox.net, toke@redhat.com, lorenzo.bianconi@redhat.com, dsahern@kernel.org, andrii.nakryiko@gmail.com Subject: [PATCH v3 bpf-next 8/9] samples/bpf: xdp_redirect_cpu: load a eBPF program on cpumap Date: Tue, 23 Jun 2020 23:39:33 +0200 Message-Id: X-Mailer: git-send-email 2.26.2 In-Reply-To: References: MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Extend xdp_redirect_cpu_{usr,kern}.c adding the possibility to load a XDP program on cpumap entries. The following options have been added: - mprog-name: cpumap entry program name - mprog-filename: cpumap entry program filename - redirect-device: output interface if the cpumap program performs a XDP_REDIRECT to an egress interface - redirect-map: bpf map used to perform XDP_REDIRECT to an egress interface - mprog-disable: disable loading XDP program on cpumap entries Add xdp_pass, xdp_drop, xdp_redirect stats accounting Co-developed-by: Jesper Dangaard Brouer Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi --- samples/bpf/xdp_redirect_cpu_kern.c | 25 ++-- samples/bpf/xdp_redirect_cpu_user.c | 174 +++++++++++++++++++++++++--- 2 files changed, 177 insertions(+), 22 deletions(-) diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c index 2baf8db1f7e7..8255025dea97 100644 --- a/samples/bpf/xdp_redirect_cpu_kern.c +++ b/samples/bpf/xdp_redirect_cpu_kern.c @@ -21,7 +21,7 @@ struct { __uint(type, BPF_MAP_TYPE_CPUMAP); __uint(key_size, sizeof(u32)); - __uint(value_size, sizeof(u32)); + __uint(value_size, sizeof(struct bpf_cpumap_val)); __uint(max_entries, MAX_CPUS); } cpu_map SEC(".maps"); @@ -30,6 +30,9 @@ struct datarec { __u64 processed; __u64 dropped; __u64 issue; + __u64 xdp_pass; + __u64 xdp_drop; + __u64 xdp_redirect; }; /* Count RX packets, as XDP bpf_prog doesn't get direct TX-success @@ -692,13 +695,16 @@ int trace_xdp_cpumap_enqueue(struct cpumap_enqueue_ctx *ctx) * Code in: kernel/include/trace/events/xdp.h */ struct cpumap_kthread_ctx { - u64 __pad; // First 8 bytes are not accessible by bpf code - int map_id; // offset:8; size:4; signed:1; - u32 act; // offset:12; size:4; signed:0; - int cpu; // offset:16; size:4; signed:1; - unsigned int drops; // offset:20; size:4; signed:0; - unsigned int processed; // offset:24; size:4; signed:0; - int sched; // offset:28; size:4; signed:1; + u64 __pad; // First 8 bytes are not accessible + int map_id; // offset:8; size:4; signed:1; + u32 act; // offset:12; size:4; signed:0; + int cpu; // offset:16; size:4; signed:1; + unsigned int drops; // offset:20; size:4; signed:0; + unsigned int processed; // offset:24; size:4; signed:0; + int sched; // offset:28; size:4; signed:1; + unsigned int xdp_pass; // offset:32; size:4; signed:0; + unsigned int xdp_drop; // offset:36; size:4; signed:0; + unsigned int xdp_redirect; // offset:40; size:4; signed:0; }; SEC("tracepoint/xdp/xdp_cpumap_kthread") @@ -712,6 +718,9 @@ int trace_xdp_cpumap_kthread(struct cpumap_kthread_ctx *ctx) return 0; rec->processed += ctx->processed; rec->dropped += ctx->drops; + rec->xdp_pass += ctx->xdp_pass; + rec->xdp_drop += ctx->xdp_drop; + rec->xdp_redirect += ctx->xdp_redirect; /* Count times kthread yielded CPU via schedule call */ if (ctx->sched) diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index 1a054737c35a..4b1264ca7ab7 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -70,6 +70,11 @@ static const struct option long_options[] = { {"stress-mode", no_argument, NULL, 'x' }, {"no-separators", no_argument, NULL, 'z' }, {"force", no_argument, NULL, 'F' }, + {"mprog-disable", no_argument, NULL, 'n' }, + {"mprog-name", required_argument, NULL, 'e' }, + {"mprog-filename", required_argument, NULL, 'f' }, + {"redirect-device", required_argument, NULL, 'r' }, + {"redirect-map", required_argument, NULL, 'm' }, {0, 0, NULL, 0 } }; @@ -156,6 +161,9 @@ struct datarec { __u64 processed; __u64 dropped; __u64 issue; + __u64 xdp_pass; + __u64 xdp_drop; + __u64 xdp_redirect; }; struct record { __u64 timestamp; @@ -175,6 +183,9 @@ static bool map_collect_percpu(int fd, __u32 key, struct record *rec) /* For percpu maps, userspace gets a value per possible CPU */ unsigned int nr_cpus = bpf_num_possible_cpus(); struct datarec values[nr_cpus]; + __u64 sum_xdp_redirect = 0; + __u64 sum_xdp_pass = 0; + __u64 sum_xdp_drop = 0; __u64 sum_processed = 0; __u64 sum_dropped = 0; __u64 sum_issue = 0; @@ -196,10 +207,19 @@ static bool map_collect_percpu(int fd, __u32 key, struct record *rec) sum_dropped += values[i].dropped; rec->cpu[i].issue = values[i].issue; sum_issue += values[i].issue; + rec->cpu[i].xdp_pass = values[i].xdp_pass; + sum_xdp_pass += values[i].xdp_pass; + rec->cpu[i].xdp_drop = values[i].xdp_drop; + sum_xdp_drop += values[i].xdp_drop; + rec->cpu[i].xdp_redirect = values[i].xdp_redirect; + sum_xdp_redirect += values[i].xdp_redirect; } rec->total.processed = sum_processed; rec->total.dropped = sum_dropped; rec->total.issue = sum_issue; + rec->total.xdp_pass = sum_xdp_pass; + rec->total.xdp_drop = sum_xdp_drop; + rec->total.xdp_redirect = sum_xdp_redirect; return true; } @@ -303,17 +323,33 @@ static __u64 calc_errs_pps(struct datarec *r, return pps; } +static void calc_xdp_pps(struct datarec *r, struct datarec *p, + double *xdp_pass, double *xdp_drop, + double *xdp_redirect, double period_) +{ + *xdp_pass = 0, *xdp_drop = 0, *xdp_redirect = 0; + if (period_ > 0) { + *xdp_redirect = (r->xdp_redirect - p->xdp_redirect) / period_; + *xdp_pass = (r->xdp_pass - p->xdp_pass) / period_; + *xdp_drop = (r->xdp_drop - p->xdp_drop) / period_; + } +} + static void stats_print(struct stats_record *stats_rec, struct stats_record *stats_prev, - char *prog_name) + char *prog_name, char *mprog_name, int mprog_fd) { unsigned int nr_cpus = bpf_num_possible_cpus(); double pps = 0, drop = 0, err = 0; + bool mprog_enabled = false; struct record *rec, *prev; int to_cpu; double t; int i; + if (mprog_fd > 0) + mprog_enabled = true; + /* Header */ printf("Running XDP/eBPF prog_name:%s\n", prog_name); printf("%-15s %-7s %-14s %-11s %-9s\n", @@ -458,6 +494,33 @@ static void stats_print(struct stats_record *stats_rec, printf(fm2_err, "xdp_exception", "total", pps, drop); } + /* CPUMAP attached XDP program that runs on remote/destination CPU */ + if (mprog_enabled) { + char *fmt_k = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f\n"; + char *fm2_k = "%-15s %-7s %'-14.0f %'-11.0f %'-10.0f\n"; + double xdp_pass, xdp_drop, xdp_redirect; + + printf("\n2nd remote XDP/eBPF prog_name: %s\n", mprog_name); + printf("%-15s %-7s %-14s %-11s %-9s\n", + "XDP-cpumap", "CPU:to", "xdp-pass", "xdp-drop", "xdp-redir"); + + rec = &stats_rec->kthread; + prev = &stats_prev->kthread; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + calc_xdp_pps(r, p, &xdp_pass, &xdp_drop, + &xdp_redirect, t); + if (xdp_pass > 0 || xdp_drop > 0 || xdp_redirect > 0) + printf(fmt_k, "xdp-in-kthread", i, xdp_pass, xdp_drop, xdp_redirect); + } + calc_xdp_pps(&rec->total, &prev->total, &xdp_pass, &xdp_drop, + &xdp_redirect, t); + printf(fm2_k, "xdp-in-kthread", "total", xdp_pass, xdp_drop, xdp_redirect); + } + printf("\n"); fflush(stdout); } @@ -494,7 +557,7 @@ static inline void swap(struct stats_record **a, struct stats_record **b) *b = tmp; } -static int create_cpu_entry(__u32 cpu, __u32 queue_size, +static int create_cpu_entry(__u32 cpu, struct bpf_cpumap_val *value, __u32 avail_idx, bool new) { __u32 curr_cpus_count = 0; @@ -504,7 +567,7 @@ static int create_cpu_entry(__u32 cpu, __u32 queue_size, /* Add a CPU entry to cpumap, as this allocate a cpu entry in * the kernel for the cpu. */ - ret = bpf_map_update_elem(cpu_map_fd, &cpu, &queue_size, 0); + ret = bpf_map_update_elem(cpu_map_fd, &cpu, value, 0); if (ret) { fprintf(stderr, "Create CPU entry failed (err:%d)\n", ret); exit(EXIT_FAIL_BPF); @@ -535,9 +598,9 @@ static int create_cpu_entry(__u32 cpu, __u32 queue_size, } } /* map_fd[7] = cpus_iterator */ - printf("%s CPU:%u as idx:%u queue_size:%d (total cpus_count:%u)\n", + printf("%s CPU:%u as idx:%u qsize:%d prog_fd: %d (cpus_count:%u)\n", new ? "Add-new":"Replace", cpu, avail_idx, - queue_size, curr_cpus_count); + value->qsize, value->bpf_prog.fd, curr_cpus_count); return 0; } @@ -561,21 +624,26 @@ static void mark_cpus_unavailable(void) } /* Stress cpumap management code by concurrently changing underlying cpumap */ -static void stress_cpumap(void) +static void stress_cpumap(struct bpf_cpumap_val *value) { /* Changing qsize will cause kernel to free and alloc a new * bpf_cpu_map_entry, with an associated/complicated tear-down * procedure. */ - create_cpu_entry(1, 1024, 0, false); - create_cpu_entry(1, 8, 0, false); - create_cpu_entry(1, 16000, 0, false); + value->qsize = 1024; + create_cpu_entry(1, value, 0, false); + value->qsize = 8; + create_cpu_entry(1, value, 0, false); + value->qsize = 16000; + create_cpu_entry(1, value, 0, false); } static void stats_poll(int interval, bool use_separators, char *prog_name, + char *mprog_name, struct bpf_cpumap_val *value, bool stress_mode) { struct stats_record *record, *prev; + int mprog_fd; record = alloc_stats_record(); prev = alloc_stats_record(); @@ -587,11 +655,12 @@ static void stats_poll(int interval, bool use_separators, char *prog_name, while (1) { swap(&prev, &record); + mprog_fd = value->bpf_prog.fd; stats_collect(record); - stats_print(record, prev, prog_name); + stats_print(record, prev, prog_name, mprog_name, mprog_fd); sleep(interval); if (stress_mode) - stress_cpumap(); + stress_cpumap(value); } free_stats_record(record); @@ -664,15 +733,66 @@ static int init_map_fds(struct bpf_object *obj) return 0; } +static int load_cpumap_prog(char *file_name, char *prog_name, + char *redir_interface, char *redir_map) +{ + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + .expected_attach_type = BPF_XDP_CPUMAP, + .file = file_name, + }; + struct bpf_program *prog; + struct bpf_object *obj; + int fd; + + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &fd)) + return -1; + + if (fd < 0) { + fprintf(stderr, "ERR: bpf_prog_load_xattr: %s\n", + strerror(errno)); + return fd; + } + + if (redir_interface && redir_map) { + int err, map_fd, ifindex_out, key = 0; + + map_fd = bpf_object__find_map_fd_by_name(obj, redir_map); + if (map_fd < 0) + return map_fd; + + ifindex_out = if_nametoindex(redir_interface); + if (!ifindex_out) + return -1; + + err = bpf_map_update_elem(map_fd, &key, &ifindex_out, 0); + if (err < 0) + return err; + } + + prog = bpf_object__find_program_by_title(obj, prog_name); + if (!prog) { + fprintf(stderr, "bpf_object__find_program_by_title failed\n"); + return EXIT_FAIL; + } + + return bpf_program__fd(prog); +} + int main(int argc, char **argv) { struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; char *prog_name = "xdp_cpu_map5_lb_hash_ip_pairs"; + char *mprog_filename = "xdp_redirect_kern.o"; + char *redir_interface = NULL, *redir_map = NULL; + char *mprog_name = "xdp_redirect_dummy"; + bool mprog_disable = false; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_UNSPEC, }; struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); + struct bpf_cpumap_val value; bool use_separators = true; bool stress_mode = false; struct bpf_program *prog; @@ -728,7 +848,7 @@ int main(int argc, char **argv) memset(cpu, 0, n_cpus * sizeof(int)); /* Parse commands line args */ - while ((opt = getopt_long(argc, argv, "hSd:s:p:q:c:xzF", + while ((opt = getopt_long(argc, argv, "hSd:s:p:q:c:xzFf:e:r:m:", long_options, &longindex)) != -1) { switch (opt) { case 'd': @@ -762,6 +882,21 @@ int main(int argc, char **argv) /* Selecting eBPF prog to load */ prog_name = optarg; break; + case 'n': + mprog_disable = true; + break; + case 'f': + mprog_filename = optarg; + break; + case 'e': + mprog_name = optarg; + break; + case 'r': + redir_interface = optarg; + break; + case 'm': + redir_map = optarg; + break; case 'c': /* Add multiple CPUs */ add_cpu = strtoul(optarg, NULL, 0); @@ -807,8 +942,18 @@ int main(int argc, char **argv) goto out; } + value.bpf_prog.fd = 0; + if (!mprog_disable) + value.bpf_prog.fd = load_cpumap_prog(mprog_filename, mprog_name, + redir_interface, redir_map); + if (value.bpf_prog.fd < 0) { + err = value.bpf_prog.fd; + goto out; + } + value.qsize = qsize; + for (i = 0; i < added_cpus; i++) - create_cpu_entry(cpu[i], qsize, i, true); + create_cpu_entry(cpu[i], &value, i, true); /* Remove XDP program when program is interrupted or killed */ signal(SIGINT, int_exit); @@ -841,7 +986,8 @@ int main(int argc, char **argv) } prog_id = info.id; - stats_poll(interval, use_separators, prog_name, stress_mode); + stats_poll(interval, use_separators, prog_name, mprog_name, + &value, stress_mode); out: free(cpu); return err;