[dpdk-stable] [PATCH v5] mbuf: fix reset on mbuf free

Olivier Matz olivier.matz at 6wind.com
Wed Sep 29 23:37:07 CEST 2021


m->nb_seg must be reset on mbuf free whatever the value of m->next,
because it can happen that m->nb_seg is != 1. For instance in this
case:

  m1 = rte_pktmbuf_alloc(mp);
  rte_pktmbuf_append(m1, 500);
  m2 = rte_pktmbuf_alloc(mp);
  rte_pktmbuf_append(m2, 500);
  rte_pktmbuf_chain(m1, m2);
  m0 = rte_pktmbuf_alloc(mp);
  rte_pktmbuf_append(m0, 500);
  rte_pktmbuf_chain(m0, m1);

As rte_pktmbuf_chain() does not reset nb_seg in the initial m1
segment (this is not required), after this code the mbuf chain
have 3 segments:
  - m0: next=m1, nb_seg=3
  - m1: next=m2, nb_seg=2
  - m2: next=NULL, nb_seg=1

Then split this chain between m1 and m2, it would result in 2 packets:
  - first packet
    - m0: next=m1, nb_seg=2
    - m1: next=NULL, nb_seg=2
  - second packet
    - m2: next=NULL, nb_seg=1

Freeing the first packet will not restore nb_seg=1 in the second
segment. This is an issue because it is expected that mbufs stored
in pool have their nb_seg field set to 1.

Fixes: 8f094a9ac5d7 ("mbuf: set mbuf fields while in pool")
Cc: stable at dpdk.org

Signed-off-by: Olivier Matz <olivier.matz at 6wind.com>
Acked-by: Morten Brørup <mb at smartsharesystems.com>
Acked-by: Ajit Khaparde <ajit.khaparde at broadcom.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev at intel.com>
---
 app/test/test_mbuf.c     | 69 ++++++++++++++++++++++++++++++++++++++++
 lib/mbuf/rte_mbuf.c      |  4 +--
 lib/mbuf/rte_mbuf.h      |  8 ++---
 lib/mbuf/rte_mbuf_core.h | 13 ++++++--
 4 files changed, 86 insertions(+), 8 deletions(-)

diff --git a/app/test/test_mbuf.c b/app/test/test_mbuf.c
index 9a248dfaea..a4e32e933a 100644
--- a/app/test/test_mbuf.c
+++ b/app/test/test_mbuf.c
@@ -2684,6 +2684,70 @@ test_mbuf_dyn(struct rte_mempool *pktmbuf_pool)
 	return -1;
 }
 
+/* check that m->nb_segs and m->next are reset on mbuf free */
+static int
+test_nb_segs_and_next_reset(void)
+{
+	struct rte_mbuf *m0 = NULL, *m1 = NULL, *m2 = NULL;
+	struct rte_mempool *pool = NULL;
+
+	pool = rte_pktmbuf_pool_create("test_mbuf_reset",
+			3, 0, 0, MBUF_DATA_SIZE, SOCKET_ID_ANY);
+	if (pool == NULL)
+		GOTO_FAIL("Failed to create mbuf pool");
+
+	/* alloc mbufs */
+	m0 = rte_pktmbuf_alloc(pool);
+	m1 = rte_pktmbuf_alloc(pool);
+	m2 = rte_pktmbuf_alloc(pool);
+	if (m0 == NULL || m1 == NULL || m2 == NULL)
+		GOTO_FAIL("Failed to allocate mbuf");
+
+	/* append data in all of them */
+	if (rte_pktmbuf_append(m0, 500) == NULL ||
+			rte_pktmbuf_append(m1, 500) == NULL ||
+			rte_pktmbuf_append(m2, 500) == NULL)
+		GOTO_FAIL("Failed to append data in mbuf");
+
+	/* chain them in one mbuf m0 */
+	rte_pktmbuf_chain(m1, m2);
+	rte_pktmbuf_chain(m0, m1);
+	if (m0->nb_segs != 3 || m0->next != m1 || m1->next != m2 ||
+			m2->next != NULL) {
+		m1 = m2 = NULL;
+		GOTO_FAIL("Failed to chain mbufs");
+	}
+
+	/* split m0 chain in two, between m1 and m2 */
+	m0->nb_segs = 2;
+	m1->next = NULL;
+	m2->nb_segs = 1;
+
+	/* free the 2 mbuf chains m0 and m2  */
+	rte_pktmbuf_free(m0);
+	rte_pktmbuf_free(m2);
+
+	/* realloc the 3 mbufs */
+	m0 = rte_mbuf_raw_alloc(pool);
+	m1 = rte_mbuf_raw_alloc(pool);
+	m2 = rte_mbuf_raw_alloc(pool);
+	if (m0 == NULL || m1 == NULL || m2 == NULL)
+		GOTO_FAIL("Failed to reallocate mbuf");
+
+	/* ensure that m->next and m->nb_segs are reset allocated mbufs */
+	if (m0->nb_segs != 1 || m0->next != NULL ||
+			m1->nb_segs != 1 || m1->next != NULL ||
+			m2->nb_segs != 1 || m2->next != NULL)
+		GOTO_FAIL("nb_segs or next was not reset properly");
+
+	return 0;
+
+fail:
+	if (pool != NULL)
+		rte_mempool_free(pool);
+	return -1;
+}
+
 static int
 test_mbuf(void)
 {
@@ -2874,6 +2938,11 @@ test_mbuf(void)
 		goto err;
 	}
 
+	/* test reset of m->nb_segs and m->next on mbuf free */
+	if (test_nb_segs_and_next_reset() < 0) {
+		printf("test_nb_segs_and_next_reset() failed\n");
+		goto err;
+	}
 
 	ret = 0;
 err:
diff --git a/lib/mbuf/rte_mbuf.c b/lib/mbuf/rte_mbuf.c
index f7e3c1a187..f145cd800a 100644
--- a/lib/mbuf/rte_mbuf.c
+++ b/lib/mbuf/rte_mbuf.c
@@ -134,10 +134,10 @@ rte_pktmbuf_free_pinned_extmem(void *addr, void *opaque)
 
 	rte_mbuf_ext_refcnt_set(m->shinfo, 1);
 	m->ol_flags = EXT_ATTACHED_MBUF;
-	if (m->next != NULL) {
+	if (m->next != NULL)
 		m->next = NULL;
+	if (m->nb_segs != 1)
 		m->nb_segs = 1;
-	}
 	rte_mbuf_raw_free(m);
 }
 
diff --git a/lib/mbuf/rte_mbuf.h b/lib/mbuf/rte_mbuf.h
index a555f216ae..dded3dd70c 100644
--- a/lib/mbuf/rte_mbuf.h
+++ b/lib/mbuf/rte_mbuf.h
@@ -1346,10 +1346,10 @@ rte_pktmbuf_prefree_seg(struct rte_mbuf *m)
 				return NULL;
 		}
 
-		if (m->next != NULL) {
+		if (m->next != NULL)
 			m->next = NULL;
+		if (m->nb_segs != 1)
 			m->nb_segs = 1;
-		}
 
 		return m;
 
@@ -1363,10 +1363,10 @@ rte_pktmbuf_prefree_seg(struct rte_mbuf *m)
 				return NULL;
 		}
 
-		if (m->next != NULL) {
+		if (m->next != NULL)
 			m->next = NULL;
+		if (m->nb_segs != 1)
 			m->nb_segs = 1;
-		}
 		rte_mbuf_refcnt_set(m, 1);
 
 		return m;
diff --git a/lib/mbuf/rte_mbuf_core.h b/lib/mbuf/rte_mbuf_core.h
index 9d8e3ddc86..9ef807daaa 100644
--- a/lib/mbuf/rte_mbuf_core.h
+++ b/lib/mbuf/rte_mbuf_core.h
@@ -508,7 +508,12 @@ struct rte_mbuf {
 	 * or non-atomic) is controlled by the RTE_MBUF_REFCNT_ATOMIC flag.
 	 */
 	uint16_t refcnt;
-	uint16_t nb_segs;         /**< Number of segments. */
+
+	/**
+	 * Number of segments. Only valid for the first segment of an mbuf
+	 * chain.
+	 */
+	uint16_t nb_segs;
 
 	/** Input port (16 bits to support more than 256 virtual ports).
 	 * The event eth Tx adapter uses this field to specify the output port.
@@ -604,7 +609,11 @@ struct rte_mbuf {
 	/* second cache line - fields only used in slow path or on TX */
 	RTE_MARKER cacheline1 __rte_cache_min_aligned;
 
-	struct rte_mbuf *next;    /**< Next segment of scattered packet. */
+	/**
+	 * Next segment of scattered packet. Must be NULL in the last segment or
+	 * in case of non-segmented packet.
+	 */
+	struct rte_mbuf *next;
 
 	/* fields to support TX offloads */
 	RTE_STD_C11
-- 
2.30.2



More information about the stable mailing list