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

[Stephen Hemminger]

On Mon, 25 Jul 2022 17:28:11 +0200
Mário Kuka <kuka at cesnet.cz> wrote:

> The rte_pcapng_write_packets() function fails when we try to write more
> packets than the IOV_MAX limit. The error is caused by the writev()
> system call, which 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 split the iovec buffer into smaller
> chunks with a maximum size of IOV_MAX and write them sequentially by
> calling the writev() repeatedly.
> 
> Fixes: 8d23ce8f5ee9 ("pcapng: add new library for writing pcapng files")
> Cc: stephen at networkplumber.org
> 
> Signed-off-by: Mário Kuka <kuka at cesnet.cz>
> ---

Something like this (compile tested only).

diff --git a/lib/pcapng/rte_pcapng.c b/lib/pcapng/rte_pcapng.c
index 06ad712bd1eb..e41cf909e120 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 */