[dpdk-dev] [PATCH v2 1/3] net/iavf: fix segment fault in AVX512

[Wenzhuo Lu <wenzhuo.lu@intel.com>]

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_avx2.c   | 120 +------------------
 drivers/net/iavf/iavf_rxtx_vec_avx512.c |   5 +-
 drivers/net/iavf/iavf_rxtx_vec_common.h | 201 ++++++++++++++++++++++++++++++++
 3 files changed, 207 insertions(+), 119 deletions(-)

diff --git a/drivers/net/iavf/iavf_rxtx_vec_avx2.c b/drivers/net/iavf/iavf_rxtx_vec_avx2.c
index cdb5139..2c2b139 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_avx2.c
+++ b/drivers/net/iavf/iavf_rxtx_vec_avx2.c
@@ -10,126 +10,10 @@
 #pragma GCC diagnostic ignored "-Wcast-qual"
 #endif
 
-static inline void
+static __rte_always_inline void
 iavf_rxq_rearm(struct iavf_rx_queue *rxq)
 {
-	int i;
-	uint16_t rx_id;
-	volatile union iavf_rx_desc *rxdp;
-	struct rte_mbuf **rxp = &rxq->sw_ring[rxq->rxrearm_start];
-
-	rxdp = rxq->rx_ring + rxq->rxrearm_start;
-
-	/* 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_VPMD_DESCS_PER_LOOP; 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 2 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_iova(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;
-	__m256i dma_addr0_1, dma_addr2_3;
-	__m256i hdr_room = _mm256_set1_epi64x(RTE_PKTMBUF_HEADROOM);
-	/* Initialize the mbufs in vector, process 4 mbufs in one loop */
-	for (i = 0; i < IAVF_RXQ_REARM_THRESH;
-			i += 4, rxp += 4, rxdp += 4) {
-		__m128i vaddr0, vaddr1, vaddr2, vaddr3;
-		__m256i vaddr0_1, vaddr2_3;
-
-		mb0 = rxp[0];
-		mb1 = rxp[1];
-		mb2 = rxp[2];
-		mb3 = rxp[3];
-
-		/* load buf_addr(lo 64bit) and buf_iova(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);
-
-		/**
-		 * 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);
-
-		/* convert pa to dma_addr hdr/data */
-		dma_addr0_1 = _mm256_unpackhi_epi64(vaddr0_1, vaddr0_1);
-		dma_addr2_3 = _mm256_unpackhi_epi64(vaddr2_3, vaddr2_3);
-
-		/* add headroom to pa values */
-		dma_addr0_1 = _mm256_add_epi64(dma_addr0_1, hdr_room);
-		dma_addr2_3 = _mm256_add_epi64(dma_addr2_3, hdr_room);
-
-		/* flush desc with pa dma_addr */
-		_mm256_store_si256((__m256i *)&rxdp->read, dma_addr0_1);
-		_mm256_store_si256((__m256i *)&(rxdp + 2)->read, dma_addr2_3);
-	}
-
-#endif
-
-	rxq->rxrearm_start += IAVF_RXQ_REARM_THRESH;
-	if (rxq->rxrearm_start >= rxq->nb_rx_desc)
-		rxq->rxrearm_start = 0;
-
-	rxq->rxrearm_nb -= IAVF_RXQ_REARM_THRESH;
-
-	rx_id = (uint16_t)((rxq->rxrearm_start == 0) ?
-			     (rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
-
-	/* Update the tail pointer on the NIC */
-	IAVF_PCI_REG_WRITE(rxq->qrx_tail, rx_id);
+	return iavf_rxq_rearm_cmn(rxq, false);
 }
 
 #define PKTLEN_SHIFT     10
diff --git a/drivers/net/iavf/iavf_rxtx_vec_avx512.c b/drivers/net/iavf/iavf_rxtx_vec_avx512.c
index 5cb4c7c..acd5e54 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_avx512.c
+++ b/drivers/net/iavf/iavf_rxtx_vec_avx512.c
@@ -13,7 +13,7 @@
 #define IAVF_DESCS_PER_LOOP_AVX 8
 #define PKTLEN_SHIFT 10
 
-static inline void
+static __rte_always_inline void
 iavf_rxq_rearm(struct iavf_rx_queue *rxq)
 {
 	int i;
@@ -25,6 +25,9 @@
 
 	rxdp = rxq->rx_ring + rxq->rxrearm_start;
 
+	if (!cache)
+		return iavf_rxq_rearm_cmn(rxq, true);
+
 	/* 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.
diff --git a/drivers/net/iavf/iavf_rxtx_vec_common.h b/drivers/net/iavf/iavf_rxtx_vec_common.h
index 46a1873..c4cc544 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_common.h
+++ b/drivers/net/iavf/iavf_rxtx_vec_common.h
@@ -11,6 +11,10 @@
 #include "iavf.h"
 #include "iavf_rxtx.h"
 
+#ifndef __INTEL_COMPILER
+#pragma GCC diagnostic ignored "-Wcast-qual"
+#endif
+
 static inline uint16_t
 reassemble_packets(struct iavf_rx_queue *rxq, struct rte_mbuf **rx_bufs,
 		   uint16_t nb_bufs, uint8_t *split_flags)
@@ -276,4 +280,201 @@
 	return 0;
 }
 
+static __rte_always_inline void
+iavf_rxq_rearm_cmn(struct iavf_rx_queue *rxq, __rte_unused bool avx512)
+{
+	int i;
+	uint16_t rx_id;
+	volatile union iavf_rx_desc *rxdp;
+	struct rte_mbuf **rxp = &rxq->sw_ring[rxq->rxrearm_start];
+
+	rxdp = rxq->rx_ring + rxq->rxrearm_start;
+
+	/* 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_VPMD_DESCS_PER_LOOP; 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 2 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_iova(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
+#ifdef CC_AVX512_SUPPORT
+	if (avx512) {
+		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 8 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_iova(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, and so on.
+			 */
+			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);
+		}
+	} else
+#endif
+	{
+		struct rte_mbuf *mb0, *mb1, *mb2, *mb3;
+		__m256i dma_addr0_1, dma_addr2_3;
+		__m256i hdr_room = _mm256_set1_epi64x(RTE_PKTMBUF_HEADROOM);
+		/* Initialize the mbufs in vector, process 4 mbufs in one loop */
+		for (i = 0; i < IAVF_RXQ_REARM_THRESH;
+				i += 4, rxp += 4, rxdp += 4) {
+			__m128i vaddr0, vaddr1, vaddr2, vaddr3;
+			__m256i vaddr0_1, vaddr2_3;
+
+			mb0 = rxp[0];
+			mb1 = rxp[1];
+			mb2 = rxp[2];
+			mb3 = rxp[3];
+
+			/* load buf_addr(lo 64bit) and buf_iova(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);
+
+			/**
+			 * 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);
+
+			/* convert pa to dma_addr hdr/data */
+			dma_addr0_1 = _mm256_unpackhi_epi64(vaddr0_1, vaddr0_1);
+			dma_addr2_3 = _mm256_unpackhi_epi64(vaddr2_3, vaddr2_3);
+
+			/* add headroom to pa values */
+			dma_addr0_1 = _mm256_add_epi64(dma_addr0_1, hdr_room);
+			dma_addr2_3 = _mm256_add_epi64(dma_addr2_3, hdr_room);
+
+			/* flush desc with pa dma_addr */
+			_mm256_store_si256((__m256i *)&rxdp->read, dma_addr0_1);
+			_mm256_store_si256((__m256i *)&(rxdp + 2)->read, dma_addr2_3);
+		}
+	}
+
+#endif
+
+	rxq->rxrearm_start += IAVF_RXQ_REARM_THRESH;
+	if (rxq->rxrearm_start >= rxq->nb_rx_desc)
+		rxq->rxrearm_start = 0;
+
+	rxq->rxrearm_nb -= IAVF_RXQ_REARM_THRESH;
+
+	rx_id = (uint16_t)((rxq->rxrearm_start == 0) ?
+			     (rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
+
+	/* Update the tail pointer on the NIC */
+	IAVF_PCI_REG_WRITE(rxq->qrx_tail, rx_id);
+}
+
 #endif
-- 
1.9.3