Netdev Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Lorenzo Bianconi <lorenzo@kernel.org>
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 v10 bpf-next 12/18] bpf: add multi-buffer support to xdp copy helpers
Date: Wed, 28 Jul 2021 11:38:17 +0200	[thread overview]
Message-ID: <749f6d146902f7067343169162e91caca83ecef2.1627463617.git.lorenzo@kernel.org> (raw)
In-Reply-To: <cover.1627463617.git.lorenzo@kernel.org>

From: Eelco Chaudron <echaudro@redhat.com>

This patch adds support for multi-buffer for the following helpers:
  - bpf_xdp_output()
  - bpf_perf_event_output()

Signed-off-by: Eelco Chaudron <echaudro@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 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 e3d34da19ef2..8f1a3b48cc6f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3822,6 +3822,15 @@ 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 :
@@ -4611,10 +4620,52 @@ 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;
 }
 
@@ -4626,10 +4677,19 @@ 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,
-- 
2.31.1


  parent reply	other threads:[~2021-07-28  9:39 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-28  9:33 [PATCH v10 bpf-next 00/18] mvneta: introduce XDP multi-buffer support Lorenzo Bianconi
2021-07-28  9:38 ` Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 01/18] net: skbuff: add size metadata to skb_shared_info for xdp Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 02/18] xdp: introduce flags field in xdp_buff/xdp_frame Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 03/18] net: mvneta: update mb bit before passing the xdp buffer to eBPF layer Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 04/18] net: mvneta: simplify mvneta_swbm_add_rx_fragment management Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 05/18] net: xdp: add xdp_update_skb_shared_info utility routine Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 06/18] net: marvell: rely on " Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 07/18] xdp: add multi-buff support to xdp_return_{buff/frame} Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 08/18] net: mvneta: add multi buffer support to XDP_TX Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 09/18] net: mvneta: enable jumbo frames for XDP Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 10/18] bpf: add multi-buff support to the bpf_xdp_adjust_tail() API Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 11/18] bpf: introduce bpf_xdp_get_buff_len helper Lorenzo Bianconi
2021-07-28  9:38 ` Lorenzo Bianconi [this message]
2021-07-28  9:38 ` [PATCH v10 bpf-next 13/18] bpf: move user_size out of bpf_test_init Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 14/18] bpf: introduce multibuff support to bpf_prog_test_run_xdp() Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 15/18] bpf: test_run: add xdp_shared_info pointer in bpf_test_finish signature Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 16/18] bpf: update xdp_adjust_tail selftest to include multi-buffer Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 17/18] net: xdp: introduce bpf_xdp_adjust_data helper Lorenzo Bianconi
2021-07-28  9:38 ` [PATCH v10 bpf-next 18/18] bpf: add bpf_xdp_adjust_data selftest Lorenzo Bianconi
2021-07-28  9:47 ` [PATCH v10 bpf-next 00/18] mvneta: introduce XDP multi-buffer support Lorenzo Bianconi
2021-07-30 23:00   ` Andrii Nakryiko
2021-08-02 14:42     ` Lorenzo Bianconi

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=749f6d146902f7067343169162e91caca83ecef2.1627463617.git.lorenzo@kernel.org \
    --to=lorenzo@kernel.org \
    --cc=alexander.duyck@gmail.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=brouer@redhat.com \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=dsahern@kernel.org \
    --cc=echaudro@redhat.com \
    --cc=jasowang@redhat.com \
    --cc=john.fastabend@gmail.com \
    --cc=kuba@kernel.org \
    --cc=lorenzo.bianconi@redhat.com \
    --cc=maciej.fijalkowski@intel.com \
    --cc=magnus.karlsson@intel.com \
    --cc=netdev@vger.kernel.org \
    --cc=saeed@kernel.org \
    --cc=shayagr@amazon.com \
    --cc=tirthendu.sarkar@intel.com \
    --cc=toke@redhat.com \
    --subject='Re: [PATCH v10 bpf-next 12/18] bpf: add multi-buffer support to xdp copy helpers' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).