From patchwork Fri Aug 13 11:47:53 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Lorenzo Bianconi X-Patchwork-Id: 12435345 X-Patchwork-Delegate: bpf@iogearbox.net 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=-19.7 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI,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 20DA3C4338F for ; Fri, 13 Aug 2021 11:50:06 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 0B45561038 for ; Fri, 13 Aug 2021 11:50:06 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S240397AbhHMLub (ORCPT ); Fri, 13 Aug 2021 07:50:31 -0400 Received: from mail.kernel.org ([198.145.29.99]:45102 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S240402AbhHMLua (ORCPT ); Fri, 13 Aug 2021 07:50:30 -0400 Received: by mail.kernel.org (Postfix) with ESMTPSA id 5233A6109D; Fri, 13 Aug 2021 11:50:00 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1628855403; bh=uA8e89A9EOUoHsqgL4hRl0K5t1+QUBk1Z8qvo763/zs=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=g4JrNetJNgUngg4YLa+q5v2/J7zw0nt8nbrY4jKuT4M7s4EBO1579hDdLu7PBT4Pl ymtwWqK6vNJQbsogFB3X7GM/DuMbYM7L6csnPXC1+t9u97RKEeTlDvOjtjxZ06Blyb RAcGSPPTw0N7oWI+O2k3+lG9g7U97sYKUkT5L5W4m28N+U9LvrIu/rgQ1qQ+PqS/K/ g0X371q+13AABjrIBqPkSmsC/jocnHlsJdNe/+fdtHI3Wl8SdWNg1BRc+wkd2RmEXW EEAAn2LQgj3lgpDkm2XMr5+YhsCNrDLEe7HhMR12cbXFxIk20DVDgV/4ki4l6wbLLV zl7L+mAmtp0Kw== From: Lorenzo Bianconi To: bpf@vger.kernel.org, netdev@vger.kernel.org Cc: lorenzo.bianconi@redhat.com, davem@davemloft.net, kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net, shayagr@amazon.com, john.fastabend@gmail.com, dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com, jasowang@redhat.com, alexander.duyck@gmail.com, saeed@kernel.org, maciej.fijalkowski@intel.com, magnus.karlsson@intel.com, tirthendu.sarkar@intel.com, toke@redhat.com Subject: [PATCH v11 bpf-next 12/18] bpf: add multi-buffer support to xdp copy helpers Date: Fri, 13 Aug 2021 13:47:53 +0200 Message-Id: <83865a79491e892e43c5e299291d6a2a5757bcf4.1628854454.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.31.1 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net From: Eelco Chaudron This patch adds support for multi-buffer for the following helpers: - bpf_xdp_output() - bpf_perf_event_output() Signed-off-by: Eelco Chaudron Signed-off-by: Lorenzo Bianconi --- kernel/trace/bpf_trace.c | 3 + net/core/filter.c | 68 +++++++- .../selftests/bpf/prog_tests/xdp_bpf2bpf.c | 151 +++++++++++++----- .../selftests/bpf/progs/test_xdp_bpf2bpf.c | 2 +- 4 files changed, 180 insertions(+), 44 deletions(-) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index c5e0b6a64091..054d42b6d080 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1390,6 +1390,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { extern const struct bpf_func_proto bpf_skb_output_proto; extern const struct bpf_func_proto bpf_xdp_output_proto; +extern const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto; BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags) @@ -1487,6 +1488,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sock_from_file_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_ptr_cookie_proto; + case BPF_FUNC_xdp_get_buff_len: + return &bpf_xdp_get_buff_len_trace_proto; #endif case BPF_FUNC_seq_printf: return prog->expected_attach_type == BPF_TRACE_ITER ? diff --git a/net/core/filter.c b/net/core/filter.c index 93ce775eaadf..d67b952730e8 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3805,6 +3805,15 @@ const struct bpf_func_proto bpf_xdp_get_buff_len_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +BTF_ID_LIST_SINGLE(bpf_xdp_get_buff_len_bpf_ids, struct, xdp_buff) + +const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto = { + .func = bpf_xdp_get_buff_len, + .gpl_only = false, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_xdp_get_buff_len_bpf_ids[0], +}; + static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) { return xdp_data_meta_unsupported(xdp) ? 0 : @@ -4619,10 +4628,52 @@ static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = { }; #endif -static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff, +static unsigned long bpf_xdp_copy(void *dst_buff, const void *ctx, unsigned long off, unsigned long len) { - memcpy(dst_buff, src_buff + off, len); + unsigned long base_len, copy_len, frag_off_total; + struct xdp_buff *xdp = (struct xdp_buff *)ctx; + struct skb_shared_info *sinfo; + int i; + + if (likely(!xdp_buff_is_mb(xdp))) { + memcpy(dst_buff, xdp->data + off, len); + return 0; + } + + base_len = xdp->data_end - xdp->data; + frag_off_total = base_len; + sinfo = xdp_get_shared_info_from_buff(xdp); + + /* If we need to copy data from the base buffer do it */ + if (off < base_len) { + copy_len = min(len, base_len - off); + memcpy(dst_buff, xdp->data + off, copy_len); + + off += copy_len; + len -= copy_len; + dst_buff += copy_len; + } + + /* Copy any remaining data from the fragments */ + for (i = 0; len && i < sinfo->nr_frags; i++) { + skb_frag_t *frag = &sinfo->frags[i]; + unsigned long frag_len, frag_off; + + frag_len = skb_frag_size(frag); + frag_off = off - frag_off_total; + if (frag_off < frag_len) { + copy_len = min(len, frag_len - frag_off); + memcpy(dst_buff, + skb_frag_address(frag) + frag_off, copy_len); + + off += copy_len; + len -= copy_len; + dst_buff += copy_len; + } + frag_off_total += frag_len; + } + return 0; } @@ -4634,10 +4685,19 @@ BPF_CALL_5(bpf_xdp_event_output, struct xdp_buff *, xdp, struct bpf_map *, map, if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; if (unlikely(!xdp || - xdp_size > (unsigned long)(xdp->data_end - xdp->data))) + (likely(!xdp_buff_is_mb(xdp)) && + xdp_size > (unsigned long)(xdp->data_end - xdp->data)))) return -EFAULT; + if (unlikely(xdp_buff_is_mb(xdp))) { + struct skb_shared_info *sinfo; + + sinfo = xdp_get_shared_info_from_buff(xdp); + if (unlikely(xdp_size > ((int)(xdp->data_end - xdp->data) + + sinfo->xdp_frags_size))) + return -EFAULT; + } - return bpf_event_output(map, flags, meta, meta_size, xdp->data, + return bpf_event_output(map, flags, meta, meta_size, xdp, xdp_size, bpf_xdp_copy); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c index 3bd5904b4db5..fe279c1c0e48 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c @@ -10,11 +10,20 @@ struct meta { int pkt_len; }; +struct test_ctx_s { + bool passed; + int pkt_size; +}; + +struct test_ctx_s test_ctx; + static void on_sample(void *ctx, int cpu, void *data, __u32 size) { - int duration = 0; struct meta *meta = (struct meta *)data; struct ipv4_packet *trace_pkt_v4 = data + sizeof(*meta); + unsigned char *raw_pkt = data + sizeof(*meta); + struct test_ctx_s *tst_ctx = ctx; + int duration = 0; if (CHECK(size < sizeof(pkt_v4) + sizeof(*meta), "check_size", "size %u < %zu\n", @@ -25,25 +34,114 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size) "meta->ifindex = %d\n", meta->ifindex)) return; - if (CHECK(meta->pkt_len != sizeof(pkt_v4), "check_meta_pkt_len", - "meta->pkt_len = %zd\n", sizeof(pkt_v4))) + if (CHECK(meta->pkt_len != tst_ctx->pkt_size, "check_meta_pkt_len", + "meta->pkt_len = %d\n", tst_ctx->pkt_size)) return; if (CHECK(memcmp(trace_pkt_v4, &pkt_v4, sizeof(pkt_v4)), "check_packet_content", "content not the same\n")) return; - *(bool *)ctx = true; + if (meta->pkt_len > sizeof(pkt_v4)) { + for (int i = 0; i < (meta->pkt_len - sizeof(pkt_v4)); i++) { + if (raw_pkt[i + sizeof(pkt_v4)] != (unsigned char)i) { + CHECK(true, "check_packet_content", + "byte %zu does not match %u != %u\n", + i + sizeof(pkt_v4), + raw_pkt[i + sizeof(pkt_v4)], + (unsigned char)i); + break; + } + } + } + + tst_ctx->passed = true; } -void test_xdp_bpf2bpf(void) +#define BUF_SZ 9000 + +static int run_xdp_bpf2bpf_pkt_size(int pkt_fd, struct perf_buffer *pb, + struct test_xdp_bpf2bpf *ftrace_skel, + int pkt_size) { __u32 duration = 0, retval, size; - char buf[128]; + __u8 *buf, *buf_in; + int err, ret = 0; + + if (pkt_size > BUF_SZ || pkt_size < sizeof(pkt_v4)) + return -EINVAL; + + buf_in = malloc(BUF_SZ); + if (CHECK(!buf_in, "buf_in malloc()", "error:%s\n", strerror(errno))) + return -ENOMEM; + + buf = malloc(BUF_SZ); + if (CHECK(!buf, "buf malloc()", "error:%s\n", strerror(errno))) { + ret = -ENOMEM; + goto free_buf_in; + } + + test_ctx.passed = false; + test_ctx.pkt_size = pkt_size; + + memcpy(buf_in, &pkt_v4, sizeof(pkt_v4)); + if (pkt_size > sizeof(pkt_v4)) { + for (int i = 0; i < (pkt_size - sizeof(pkt_v4)); i++) + buf_in[i + sizeof(pkt_v4)] = i; + } + + /* Run test program */ + err = bpf_prog_test_run(pkt_fd, 1, buf_in, pkt_size, + buf, &size, &retval, &duration); + + if (CHECK(err || retval != XDP_PASS || size != pkt_size, + "ipv4", "err %d errno %d retval %d size %d\n", + err, errno, retval, size)) { + ret = err ? err : -EINVAL; + goto free_buf; + } + + /* Make sure bpf_xdp_output() was triggered and it sent the expected + * data to the perf ring buffer. + */ + err = perf_buffer__poll(pb, 100); + if (CHECK(err <= 0, "perf_buffer__poll", "err %d\n", err)) { + ret = -EINVAL; + goto free_buf; + } + + if (CHECK_FAIL(!test_ctx.passed)) { + ret = -EINVAL; + goto free_buf; + } + + /* Verify test results */ + if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"), + "result", "fentry failed err %llu\n", + ftrace_skel->bss->test_result_fentry)) { + ret = -EINVAL; + goto free_buf; + } + + if (CHECK(ftrace_skel->bss->test_result_fexit != XDP_PASS, "result", + "fexit failed err %llu\n", + ftrace_skel->bss->test_result_fexit)) + ret = -EINVAL; + +free_buf: + free(buf); +free_buf_in: + free(buf_in); + + return ret; +} + +void test_xdp_bpf2bpf(void) +{ int err, pkt_fd, map_fd; - bool passed = false; - struct iphdr *iph = (void *)buf + sizeof(struct ethhdr); - struct iptnl_info value4 = {.family = AF_INET}; + __u32 duration = 0; + int pkt_sizes[] = {sizeof(pkt_v4), 1024, 4100, 8200}; + struct iptnl_info value4 = {.family = AF_INET6}; struct test_xdp *pkt_skel = NULL; struct test_xdp_bpf2bpf *ftrace_skel = NULL; struct vip key4 = {.protocol = 6, .family = AF_INET}; @@ -87,40 +185,15 @@ void test_xdp_bpf2bpf(void) /* Set up perf buffer */ pb_opts.sample_cb = on_sample; - pb_opts.ctx = &passed; + pb_opts.ctx = &test_ctx; pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map), - 1, &pb_opts); + 8, &pb_opts); if (!ASSERT_OK_PTR(pb, "perf_buf__new")) goto out; - /* Run test program */ - err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - - if (CHECK(err || retval != XDP_TX || size != 74 || - iph->protocol != IPPROTO_IPIP, "ipv4", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size)) - goto out; - - /* Make sure bpf_xdp_output() was triggered and it sent the expected - * data to the perf ring buffer. - */ - err = perf_buffer__poll(pb, 100); - if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err)) - goto out; - - CHECK_FAIL(!passed); - - /* Verify test results */ - if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"), - "result", "fentry failed err %llu\n", - ftrace_skel->bss->test_result_fentry)) - goto out; - - CHECK(ftrace_skel->bss->test_result_fexit != XDP_TX, "result", - "fexit failed err %llu\n", ftrace_skel->bss->test_result_fexit); - + for (int i = 0; i < ARRAY_SIZE(pkt_sizes); i++) + run_xdp_bpf2bpf_pkt_size(pkt_fd, pb, ftrace_skel, + pkt_sizes[i]); out: if (pb) perf_buffer__free(pb); diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c index a038e827f850..902b54190377 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c @@ -49,7 +49,7 @@ int BPF_PROG(trace_on_entry, struct xdp_buff *xdp) void *data = (void *)(long)xdp->data; meta.ifindex = xdp->rxq->dev->ifindex; - meta.pkt_len = data_end - data; + meta.pkt_len = bpf_xdp_get_buff_len((struct xdp_md *)xdp); bpf_xdp_output(xdp, &perf_buf_map, ((__u64) meta.pkt_len << 32) | BPF_F_CURRENT_CPU,