patches for DPDK stable branches
 help / color / mirror / Atom feed
* [dpdk-stable] [PATCH 1/3] net/iavf: fix segment fault in AVX512
@ 2021-03-12  1:26 Wenzhuo Lu
  2021-03-15 17:07 ` [dpdk-stable] [dpdk-dev] " Coyle, David
  0 siblings, 1 reply; 3+ messages in thread
From: Wenzhuo Lu @ 2021-03-12  1:26 UTC (permalink / raw)
  To: dev; +Cc: Wenzhuo Lu, stable

Fix segment fault when failing to get the memory from the pool.

Fixes: 31737f2b66fb ("net/iavf: enable AVX512 for legacy Rx")
Cc: stable@dpdk.org

Reported-by: David Coyle <David.Coyle@intel.com>
Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
---
 drivers/net/iavf/iavf_rxtx_vec_avx512.c | 130 ++++++++++++++++++++++++++++++++
 1 file changed, 130 insertions(+)

diff --git a/drivers/net/iavf/iavf_rxtx_vec_avx512.c b/drivers/net/iavf/iavf_rxtx_vec_avx512.c
index 5cb4c7c..6134520 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_avx512.c
+++ b/drivers/net/iavf/iavf_rxtx_vec_avx512.c
@@ -25,6 +25,9 @@
 
 	rxdp = rxq->rx_ring + rxq->rxrearm_start;
 
+	if (!cache)
+		goto normal;
+
 	/* We need to pull 'n' more MBUFs into the software ring from mempool
 	 * We inline the mempool function here, so we can vectorize the copy
 	 * from the cache into the shadow ring.
@@ -127,6 +130,133 @@
 		cache->len -= IAVF_DESCS_PER_LOOP_AVX;
 	}
 
+	goto done;
+
+normal:
+	/* Pull 'n' more MBUFs into the software ring */
+	if (rte_mempool_get_bulk(rxq->mp,
+				 (void *)rxp,
+				 IAVF_RXQ_REARM_THRESH) < 0) {
+		if (rxq->rxrearm_nb + IAVF_RXQ_REARM_THRESH >=
+		    rxq->nb_rx_desc) {
+			__m128i dma_addr0;
+
+			dma_addr0 = _mm_setzero_si128();
+			for (i = 0; i < IAVF_DESCS_PER_LOOP_AVX; i++) {
+				rxp[i] = &rxq->fake_mbuf;
+				_mm_store_si128((__m128i *)&rxdp[i].read,
+						dma_addr0);
+			}
+		}
+		rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
+			IAVF_RXQ_REARM_THRESH;
+		return;
+	}
+
+#ifndef RTE_LIBRTE_IAVF_16BYTE_RX_DESC
+	struct rte_mbuf *mb0, *mb1;
+	__m128i dma_addr0, dma_addr1;
+	__m128i hdr_room = _mm_set_epi64x(RTE_PKTMBUF_HEADROOM,
+			RTE_PKTMBUF_HEADROOM);
+	/* Initialize the mbufs in vector, process 4 mbufs in one loop */
+	for (i = 0; i < IAVF_RXQ_REARM_THRESH; i += 2, rxp += 2) {
+		__m128i vaddr0, vaddr1;
+
+		mb0 = rxp[0];
+		mb1 = rxp[1];
+
+		/* load buf_addr(lo 64bit) and buf_physaddr(hi 64bit) */
+		RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) !=
+				offsetof(struct rte_mbuf, buf_addr) + 8);
+		vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr);
+		vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr);
+
+		/* convert pa to dma_addr hdr/data */
+		dma_addr0 = _mm_unpackhi_epi64(vaddr0, vaddr0);
+		dma_addr1 = _mm_unpackhi_epi64(vaddr1, vaddr1);
+
+		/* add headroom to pa values */
+		dma_addr0 = _mm_add_epi64(dma_addr0, hdr_room);
+		dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room);
+
+		/* flush desc with pa dma_addr */
+		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr0);
+		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr1);
+	}
+#else
+	struct rte_mbuf *mb0, *mb1, *mb2, *mb3;
+	struct rte_mbuf *mb4, *mb5, *mb6, *mb7;
+	__m512i dma_addr0_3, dma_addr4_7;
+	__m512i hdr_room = _mm512_set1_epi64(RTE_PKTMBUF_HEADROOM);
+	/* Initialize the mbufs in vector, process 4 mbufs in one loop */
+	for (i = 0; i < IAVF_RXQ_REARM_THRESH;
+			i += 8, rxp += 8, rxdp += 8) {
+		__m128i vaddr0, vaddr1, vaddr2, vaddr3;
+		__m128i vaddr4, vaddr5, vaddr6, vaddr7;
+		__m256i vaddr0_1, vaddr2_3;
+		__m256i vaddr4_5, vaddr6_7;
+		__m512i vaddr0_3, vaddr4_7;
+
+		mb0 = rxp[0];
+		mb1 = rxp[1];
+		mb2 = rxp[2];
+		mb3 = rxp[3];
+		mb4 = rxp[4];
+		mb5 = rxp[5];
+		mb6 = rxp[6];
+		mb7 = rxp[7];
+
+		/* load buf_addr(lo 64bit) and buf_physaddr(hi 64bit) */
+		RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) !=
+				offsetof(struct rte_mbuf, buf_addr) + 8);
+		vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr);
+		vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr);
+		vaddr2 = _mm_loadu_si128((__m128i *)&mb2->buf_addr);
+		vaddr3 = _mm_loadu_si128((__m128i *)&mb3->buf_addr);
+		vaddr4 = _mm_loadu_si128((__m128i *)&mb4->buf_addr);
+		vaddr5 = _mm_loadu_si128((__m128i *)&mb5->buf_addr);
+		vaddr6 = _mm_loadu_si128((__m128i *)&mb6->buf_addr);
+		vaddr7 = _mm_loadu_si128((__m128i *)&mb7->buf_addr);
+
+		/**
+		 * merge 0 & 1, by casting 0 to 256-bit and inserting 1
+		 * into the high lanes. Similarly for 2 & 3
+		 */
+		vaddr0_1 =
+			_mm256_inserti128_si256(_mm256_castsi128_si256(vaddr0),
+						vaddr1, 1);
+		vaddr2_3 =
+			_mm256_inserti128_si256(_mm256_castsi128_si256(vaddr2),
+						vaddr3, 1);
+		vaddr4_5 =
+			_mm256_inserti128_si256(_mm256_castsi128_si256(vaddr4),
+						vaddr5, 1);
+		vaddr6_7 =
+			_mm256_inserti128_si256(_mm256_castsi128_si256(vaddr6),
+						vaddr7, 1);
+		vaddr0_3 =
+			_mm512_inserti64x4(_mm512_castsi256_si512(vaddr0_1),
+						vaddr2_3, 1);
+		vaddr4_7 =
+			_mm512_inserti64x4(_mm512_castsi256_si512(vaddr4_5),
+						vaddr6_7, 1);
+
+		/* convert pa to dma_addr hdr/data */
+		dma_addr0_3 = _mm512_unpackhi_epi64(vaddr0_3, vaddr0_3);
+		dma_addr4_7 = _mm512_unpackhi_epi64(vaddr4_7, vaddr4_7);
+
+		/* add headroom to pa values */
+		dma_addr0_3 = _mm512_add_epi64(dma_addr0_3, hdr_room);
+		dma_addr4_7 = _mm512_add_epi64(dma_addr4_7, hdr_room);
+
+		/* flush desc with pa dma_addr */
+		_mm512_store_si512((__m512i *)&rxdp->read, dma_addr0_3);
+		_mm512_store_si512((__m512i *)&(rxdp + 4)->read, dma_addr4_7);
+	}
+
+#endif
+
+done:
 	rxq->rxrearm_start += IAVF_RXQ_REARM_THRESH;
 	if (rxq->rxrearm_start >= rxq->nb_rx_desc)
 		rxq->rxrearm_start = 0;
-- 
1.9.3


^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2021-03-26  1:52 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-03-12  1:26 [dpdk-stable] [PATCH 1/3] net/iavf: fix segment fault in AVX512 Wenzhuo Lu
2021-03-15 17:07 ` [dpdk-stable] [dpdk-dev] " Coyle, David
2021-03-26  1:52   ` Lu, Wenzhuo

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).