[dpdk-dev] [PATCH ] examples/l3fwd: fix aliasing in port grouping

Guduri Prathyusha gprathyusha at caviumnetworks.com
Thu Nov 2 15:31:14 CET 2017


With -f-strict-aliasing enabled by default from -O2, gcc > 5.x gives
undefined behavior in port_groupx4. 'pn' and 'pnum' are two different
pointers pointing to same chunk of memory and with -f-strict-aliasing the
pointers are assumed to be pointing to different memory and compiler
reorders instructions that depend on pnum and pn. This breaks port
grouping algorithm.

This patch eliminates the usage of union and uses memcpy for copying
gptbl[v].pnum to pn. memcpy when applied on built_in constant size does
not call its library implementation but uses appropriate LD and ST
instructions directly and hence no performance overhead.

Fixes: 569b290cdb36 ("examples/l3fwd: add NEON implementation")
Fixes: af1694d94bf1 ("examples/l3fwd: fix crash with gcc 5")
Signed-off-by: Guduri Prathyusha <gprathyusha at caviumnetworks.com>
---
 examples/l3fwd/l3fwd_neon.h | 11 +++--------
 examples/l3fwd/l3fwd_sse.h  | 11 +++--------
 2 files changed, 6 insertions(+), 16 deletions(-)

diff --git a/examples/l3fwd/l3fwd_neon.h b/examples/l3fwd/l3fwd_neon.h
index 4bc161394..10a602a04 100644
--- a/examples/l3fwd/l3fwd_neon.h
+++ b/examples/l3fwd/l3fwd_neon.h
@@ -100,11 +100,6 @@ static inline uint16_t *
 port_groupx4(uint16_t pn[FWDSTEP + 1], uint16_t *lp, uint16x8_t dp1,
 	     uint16x8_t dp2)
 {
-	union {
-		uint16_t u16[FWDSTEP + 1];
-		uint64_t u64;
-	} *pnum = (void *)pn;
-
 	int32_t v;
 	uint16x8_t mask = {1, 2, 4, 8, 0, 0, 0, 0};

@@ -117,9 +112,9 @@ port_groupx4(uint16_t pn[FWDSTEP + 1], uint16_t *lp, uint16x8_t dp1,

 	/* if dest port value has changed. */
 	if (v != GRPMSK) {
-		pnum->u64 = gptbl[v].pnum;
-		pnum->u16[FWDSTEP] = 1;
-		lp = pnum->u16 + gptbl[v].idx;
+		rte_memcpy(pn, &gptbl[v].pnum, sizeof(gptbl[v].pnum));
+		pn[FWDSTEP] = 1;
+		lp = pn + gptbl[v].idx;
 	}

 	return lp;
diff --git a/examples/l3fwd/l3fwd_sse.h b/examples/l3fwd/l3fwd_sse.h
index 831760f02..79a71d77e 100644
--- a/examples/l3fwd/l3fwd_sse.h
+++ b/examples/l3fwd/l3fwd_sse.h
@@ -98,11 +98,6 @@ processx4_step3(struct rte_mbuf *pkt[FWDSTEP], uint16_t dst_port[FWDSTEP])
 static inline uint16_t *
 port_groupx4(uint16_t pn[FWDSTEP + 1], uint16_t *lp, __m128i dp1, __m128i dp2)
 {
-	union {
-		uint16_t u16[FWDSTEP + 1];
-		uint64_t u64;
-	} *pnum = (void *)pn;
-
 	int32_t v;

 	dp1 = _mm_cmpeq_epi16(dp1, dp2);
@@ -114,9 +109,9 @@ port_groupx4(uint16_t pn[FWDSTEP + 1], uint16_t *lp, __m128i dp1, __m128i dp2)

 	/* if dest port value has changed. */
 	if (v != GRPMSK) {
-		pnum->u64 = gptbl[v].pnum;
-		pnum->u16[FWDSTEP] = 1;
-		lp = pnum->u16 + gptbl[v].idx;
+		rte_memcpy(pn, &gptbl[v].pnum, sizeof(gptbl[v].pnum));
+		pn[FWDSTEP] = 1;
+		lp = pn + gptbl[v].idx;
 	}

 	return lp;
--
2.14.1



More information about the dev mailing list