[dpdk-stable] [PATCH v5 3/3] net/i40e: fix segment fault in AVX512

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

Fix segment fault when failing to get the memory from the pool.
If there's no memory in the default cache, fall back to the
previous process.

The previous AVX2 rearm function is changed to add some AVX512
intructions and changed to a callee of the AVX2 and AVX512
rearm functions.

Fixes: e6a6a138919f ("net/i40e: add AVX512 vector path")
Cc: stable@dpdk.org

Reported-by: David Coyle <david.coyle@intel.com>
Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
---
 drivers/net/i40e/i40e_rxtx_vec_avx2.c   | 117 +------------------
 drivers/net/i40e/i40e_rxtx_vec_avx512.c |   5 +-
 drivers/net/i40e/i40e_rxtx_vec_common.h | 201 ++++++++++++++++++++++++++++++++
 3 files changed, 207 insertions(+), 116 deletions(-)

diff --git a/drivers/net/i40e/i40e_rxtx_vec_avx2.c b/drivers/net/i40e/i40e_rxtx_vec_avx2.c
index 15abd9d..3b9eef9 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_avx2.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_avx2.c
@@ -18,123 +18,10 @@
 #pragma GCC diagnostic ignored "-Wcast-qual"
 #endif
 
-static inline void
+static __rte_always_inline void
 i40e_rxq_rearm(struct i40e_rx_queue *rxq)
 {
-	int i;
-	uint16_t rx_id;
-	volatile union i40e_rx_desc *rxdp;
-	struct i40e_rx_entry *rxep = &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 *)rxep,
-				 RTE_I40E_RXQ_REARM_THRESH) < 0) {
-		if (rxq->rxrearm_nb + RTE_I40E_RXQ_REARM_THRESH >=
-		    rxq->nb_rx_desc) {
-			__m128i dma_addr0;
-			dma_addr0 = _mm_setzero_si128();
-			for (i = 0; i < RTE_I40E_DESCS_PER_LOOP; i++) {
-				rxep[i].mbuf = &rxq->fake_mbuf;
-				_mm_store_si128((__m128i *)&rxdp[i].read,
-						dma_addr0);
-			}
-		}
-		rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
-			RTE_I40E_RXQ_REARM_THRESH;
-		return;
-	}
-
-#ifndef RTE_LIBRTE_I40E_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 < RTE_I40E_RXQ_REARM_THRESH; i += 2, rxep += 2) {
-		__m128i vaddr0, vaddr1;
-
-		mb0 = rxep[0].mbuf;
-		mb1 = rxep[1].mbuf;
-
-		/* 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 < RTE_I40E_RXQ_REARM_THRESH;
-			i += 4, rxep += 4, rxdp += 4) {
-		__m128i vaddr0, vaddr1, vaddr2, vaddr3;
-		__m256i vaddr0_1, vaddr2_3;
-
-		mb0 = rxep[0].mbuf;
-		mb1 = rxep[1].mbuf;
-		mb2 = rxep[2].mbuf;
-		mb3 = rxep[3].mbuf;
-
-		/* 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 += RTE_I40E_RXQ_REARM_THRESH;
-	if (rxq->rxrearm_start >= rxq->nb_rx_desc)
-		rxq->rxrearm_start = 0;
-
-	rxq->rxrearm_nb -= RTE_I40E_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 */
-	I40E_PCI_REG_WC_WRITE(rxq->qrx_tail, rx_id);
+	return i40e_rxq_rearm_common(rxq, false);
 }
 
 #ifndef RTE_LIBRTE_I40E_16BYTE_RX_DESC
diff --git a/drivers/net/i40e/i40e_rxtx_vec_avx512.c b/drivers/net/i40e/i40e_rxtx_vec_avx512.c
index 862c916..bd21d64 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_avx512.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_avx512.c
@@ -20,7 +20,7 @@
 
 #define RTE_I40E_DESCS_PER_LOOP_AVX 8
 
-static inline void
+static __rte_always_inline void
 i40e_rxq_rearm(struct i40e_rx_queue *rxq)
 {
 	int i;
@@ -32,6 +32,9 @@
 
 	rxdp = rxq->rx_ring + rxq->rxrearm_start;
 
+	if (unlikely(!cache))
+		return i40e_rxq_rearm_common(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/i40e/i40e_rxtx_vec_common.h b/drivers/net/i40e/i40e_rxtx_vec_common.h
index 33cebbe..16fcf0a 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_common.h
+++ b/drivers/net/i40e/i40e_rxtx_vec_common.h
@@ -11,6 +11,10 @@
 #include "i40e_ethdev.h"
 #include "i40e_rxtx.h"
 
+#ifndef __INTEL_COMPILER
+#pragma GCC diagnostic ignored "-Wcast-qual"
+#endif
+
 static inline uint16_t
 reassemble_packets(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_bufs,
 		   uint16_t nb_bufs, uint8_t *split_flags)
@@ -252,4 +256,201 @@
 	return -1;
 #endif
 }
+
+#ifdef CC_AVX2_SUPPORT
+static __rte_always_inline void
+i40e_rxq_rearm_common(struct i40e_rx_queue *rxq, __rte_unused bool avx512)
+{
+	int i;
+	uint16_t rx_id;
+	volatile union i40e_rx_desc *rxdp;
+	struct i40e_rx_entry *rxep = &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 *)rxep,
+				 RTE_I40E_RXQ_REARM_THRESH) < 0) {
+		if (rxq->rxrearm_nb + RTE_I40E_RXQ_REARM_THRESH >=
+		    rxq->nb_rx_desc) {
+			__m128i dma_addr0;
+			dma_addr0 = _mm_setzero_si128();
+			for (i = 0; i < RTE_I40E_DESCS_PER_LOOP; i++) {
+				rxep[i].mbuf = &rxq->fake_mbuf;
+				_mm_store_si128((__m128i *)&rxdp[i].read,
+						dma_addr0);
+			}
+		}
+		rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
+			RTE_I40E_RXQ_REARM_THRESH;
+		return;
+	}
+
+#ifndef RTE_LIBRTE_I40E_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 < RTE_I40E_RXQ_REARM_THRESH; i += 2, rxep += 2) {
+		__m128i vaddr0, vaddr1;
+
+		mb0 = rxep[0].mbuf;
+		mb1 = rxep[1].mbuf;
+
+		/* 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 < RTE_I40E_RXQ_REARM_THRESH;
+				i += 8, rxep += 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 = rxep[0].mbuf;
+			mb1 = rxep[1].mbuf;
+			mb2 = rxep[2].mbuf;
+			mb3 = rxep[3].mbuf;
+			mb4 = rxep[4].mbuf;
+			mb5 = rxep[5].mbuf;
+			mb6 = rxep[6].mbuf;
+			mb7 = rxep[7].mbuf;
+
+			/* 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 < RTE_I40E_RXQ_REARM_THRESH;
+				i += 4, rxep += 4, rxdp += 4) {
+			__m128i vaddr0, vaddr1, vaddr2, vaddr3;
+			__m256i vaddr0_1, vaddr2_3;
+
+			mb0 = rxep[0].mbuf;
+			mb1 = rxep[1].mbuf;
+			mb2 = rxep[2].mbuf;
+			mb3 = rxep[3].mbuf;
+
+			/* 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 += RTE_I40E_RXQ_REARM_THRESH;
+	if (rxq->rxrearm_start >= rxq->nb_rx_desc)
+		rxq->rxrearm_start = 0;
+
+	rxq->rxrearm_nb -= RTE_I40E_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 */
+	I40E_PCI_REG_WC_WRITE(rxq->qrx_tail, rx_id);
+}
+#endif
+
 #endif
-- 
1.9.3