[PATCH v3] pcapng: fix write more packets than IOV_MAX limit

[Mário Kuka]

The rte_pcapng_write_packets() function fails when we try to write more
packets than the IOV_MAX limit. writev() system call is limited by the
IOV_MAX limit. The iovcnt argument is valid if it is greater than 0 and
less than or equal to IOV_MAX as defined in <limits.h>.

To avoid this problem, we can check that all segments of the next
packet will fit into the iovec buffer, whose capacity will be limited
by the IOV_MAX limit. If not, we flush the current iovec buffer to the
file by calling writev() and, if successful, fit the current packet at
the beginning of the flushed iovec buffer.

Fixes: 8d23ce8f5ee9 ("pcapng: add new library for writing pcapng files")
Cc: stephen at networkplumber.org

Signed-off-by: Mário Kuka <kuka at cesnet.cz>
---
v3:
* Remove unwanted changes to check for partial writes from the writev().

 app/test/test_pcapng.c  | 42 +++++++++++++++++++++++++++++++++++-
 lib/pcapng/rte_pcapng.c | 47 ++++++++++++++++++++---------------------
 2 files changed, 64 insertions(+), 25 deletions(-)

diff --git a/app/test/test_pcapng.c b/app/test/test_pcapng.c
index 320dacea34..7f51946fff 100644
--- a/app/test/test_pcapng.c
+++ b/app/test/test_pcapng.c
@@ -110,7 +110,7 @@ test_setup(void)
 	}
 
 	/* Make a pool for cloned packets */
-	mp = rte_pktmbuf_pool_create_by_ops("pcapng_test_pool", NUM_PACKETS,
+	mp = rte_pktmbuf_pool_create_by_ops("pcapng_test_pool", IOV_MAX + NUM_PACKETS,
 					    0, 0,
 					    rte_pcapng_mbuf_size(pkt_len),
 					    SOCKET_ID_ANY, "ring_mp_sc");
@@ -237,6 +237,45 @@ test_validate(void)
 	return ret;
 }
 
+static int
+test_write_over_limit_iov_max(void)
+{
+	struct rte_mbuf *orig;
+	struct rte_mbuf *clones[IOV_MAX + NUM_PACKETS] = { };
+	struct dummy_mbuf mbfs;
+	unsigned int i;
+	ssize_t len;
+
+	/* make a dummy packet */
+	mbuf1_prepare(&mbfs, pkt_len);
+
+	/* clone them */
+	orig  = &mbfs.mb[0];
+	for (i = 0; i < IOV_MAX + NUM_PACKETS; i++) {
+		struct rte_mbuf *mc;
+
+		mc = rte_pcapng_copy(port_id, 0, orig, mp, pkt_len,
+				rte_get_tsc_cycles(), 0);
+		if (mc == NULL) {
+			fprintf(stderr, "Cannot copy packet\n");
+			return -1;
+		}
+		clones[i] = mc;
+	}
+
+	/* write it to capture file */
+	len = rte_pcapng_write_packets(pcapng, clones, IOV_MAX + NUM_PACKETS);
+
+	rte_pktmbuf_free_bulk(clones, IOV_MAX + NUM_PACKETS);
+
+	if (len <= 0) {
+		fprintf(stderr, "Write of packets failed\n");
+		return -1;
+	}
+
+	return 0;
+}
+
 static void
 test_cleanup(void)
 {
@@ -256,6 +295,7 @@ unit_test_suite test_pcapng_suite  = {
 		TEST_CASE(test_write_packets),
 		TEST_CASE(test_write_stats),
 		TEST_CASE(test_validate),
+		TEST_CASE(test_write_over_limit_iov_max),
 		TEST_CASES_END()
 	}
 };
diff --git a/lib/pcapng/rte_pcapng.c b/lib/pcapng/rte_pcapng.c
index 06ad712bd1..e41cf909e1 100644
--- a/lib/pcapng/rte_pcapng.c
+++ b/lib/pcapng/rte_pcapng.c
@@ -551,33 +551,16 @@ rte_pcapng_copy(uint16_t port_id, uint32_t queue,
 	return NULL;
 }
 
-/* Count how many segments are in this array of mbufs */
-static unsigned int
-mbuf_burst_segs(struct rte_mbuf *pkts[], unsigned int n)
-{
-	unsigned int i, iovcnt;
-
-	for (iovcnt = 0, i = 0; i < n; i++) {
-		const struct rte_mbuf *m = pkts[i];
-
-		__rte_mbuf_sanity_check(m, 1);
-
-		iovcnt += m->nb_segs;
-	}
-	return iovcnt;
-}
-
 /* Write pre-formatted packets to file. */
 ssize_t
 rte_pcapng_write_packets(rte_pcapng_t *self,
 			 struct rte_mbuf *pkts[], uint16_t nb_pkts)
 {
-	int iovcnt = mbuf_burst_segs(pkts, nb_pkts);
-	struct iovec iov[iovcnt];
-	unsigned int i, cnt;
-	ssize_t ret;
+	struct iovec iov[IOV_MAX];
+	unsigned int i, cnt = 0;
+	ssize_t ret, total = 0;
 
-	for (i = cnt = 0; i < nb_pkts; i++) {
+	for (i = 0; i < nb_pkts; i++) {
 		struct rte_mbuf *m = pkts[i];
 		struct pcapng_enhance_packet_block *epb;
 
@@ -589,6 +572,20 @@ rte_pcapng_write_packets(rte_pcapng_t *self,
 			return -1;
 		}
 
+		/*
+		 * Handle case of highly fragmented and large burst size
+		 * Note: this assumes that max segments per mbuf < IOV_MAX
+		 */
+		if (unlikely(cnt + m->nb_segs >= IOV_MAX)) {
+			ret = writev(self->outfd, iov, cnt);
+			if (unlikely(ret < 0)) {
+				rte_errno = errno;
+				return -1;
+			}
+			total += ret;
+			cnt = 0;
+		}
+
 		/*
 		 * The DPDK port is recorded during pcapng_copy.
 		 * Map that to PCAPNG interface in file.
@@ -601,10 +598,12 @@ rte_pcapng_write_packets(rte_pcapng_t *self,
 		} while ((m = m->next));
 	}
 
-	ret = writev(self->outfd, iov, iovcnt);
-	if (unlikely(ret < 0))
+	ret = writev(self->outfd, iov, cnt);
+	if (unlikely(ret < 0)) {
 		rte_errno = errno;
-	return ret;
+		return -1;
+	}
+	return total + ret;
 }
 
 /* Create new pcapng writer handle */
-- 
2.31.1