patch 'drivers/net: fix vector Rx comments' has been queued to stable release 19.11.11

[christian.ehrhardt at canonical.com]

Hi,

FYI, your patch has been queued to stable release 19.11.11

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before December 10th 2021. So please
shout if anyone has objections.

Also note that after the patch there's a diff of the upstream commit vs the
patch applied to the branch. This will indicate if there was any rebasing
needed to apply to the stable branch. If there were code changes for rebasing
(ie: not only metadata diffs), please double check that the rebase was
correctly done.

Queued patches are on a temporary branch at:
https://github.com/cpaelzer/dpdk-stable-queue

This queued commit can be viewed at:
https://github.com/cpaelzer/dpdk-stable-queue/commit/b83e5a9c5caa2fd047d6b215ff9e90b2643f274f

Thanks.

Christian Ehrhardt <christian.ehrhardt at canonical.com>

---
>From b83e5a9c5caa2fd047d6b215ff9e90b2643f274f Mon Sep 17 00:00:00 2001
From: Feifei Wang <feifei.wang2 at arm.com>
Date: Fri, 23 Jul 2021 11:10:47 +0800
Subject: [PATCH] drivers/net: fix vector Rx comments

[ upstream commit 4f76ac98b787dbc893d9aaae487f79e69cb962c4 ]

For the loop to process packets in Rx vector path, some notes for the
code are wrong, fix these errors.

Fixes: 7092be8437bd ("fm10k: add vector Rx")
Fixes: c3def6a8724c ("net/i40e: implement vector PMD for altivec")
Fixes: ae0eb310f253 ("net/i40e: implement vector PMD for ARM")
Fixes: 9ed94e5bb04e ("i40e: add vector Rx")
Fixes: 319c421f3890 ("net/avf: enable SSE Rx Tx")
Fixes: 1162f5a0ef31 ("net/iavf: support flexible Rx descriptor in SSE path")
Fixes: c68a52b8b38c ("net/ice: support vector SSE in Rx")
Fixes: cf4b4708a88a ("ixgbe: improve slow-path perf with vector scattered Rx")

Suggested-by: Ruifeng Wang <ruifeng.wang at arm.com>
Signed-off-by: Feifei Wang <feifei.wang2 at arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang at arm.com>
---
 drivers/net/fm10k/fm10k_rxtx_vec.c       | 4 ++--
 drivers/net/i40e/i40e_rxtx_vec_altivec.c | 8 ++++----
 drivers/net/i40e/i40e_rxtx_vec_neon.c    | 8 ++++----
 drivers/net/i40e/i40e_rxtx_vec_sse.c     | 4 ++--
 drivers/net/iavf/iavf_rxtx_vec_sse.c     | 4 ++--
 drivers/net/ice/ice_rxtx_vec_sse.c       | 4 ++--
 drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c   | 4 ++--
 7 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/drivers/net/fm10k/fm10k_rxtx_vec.c b/drivers/net/fm10k/fm10k_rxtx_vec.c
index ab7c515e9c..a441d33980 100644
--- a/drivers/net/fm10k/fm10k_rxtx_vec.c
+++ b/drivers/net/fm10k/fm10k_rxtx_vec.c
@@ -472,7 +472,7 @@ fm10k_recv_raw_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 		mbp1 = _mm_loadu_si128((__m128i *)&mbufp[pos]);
 
 		/* Read desc statuses backwards to avoid race condition */
-		/* A.1 load 4 pkts desc */
+		/* A.1 load desc[3] */
 		descs0[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
 		rte_compiler_barrier();
 
@@ -484,9 +484,9 @@ fm10k_recv_raw_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 		mbp2 = _mm_loadu_si128((__m128i *)&mbufp[pos+2]);
 #endif
 
+		/* A.1 load desc[2-0] */
 		descs0[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
 		rte_compiler_barrier();
-		/* B.1 load 2 mbuf point */
 		descs0[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
 		rte_compiler_barrier();
 		descs0[0] = _mm_loadu_si128((__m128i *)(rxdp));
diff --git a/drivers/net/i40e/i40e_rxtx_vec_altivec.c b/drivers/net/i40e/i40e_rxtx_vec_altivec.c
index e912ab02bc..12dacc31a4 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_altivec.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_altivec.c
@@ -281,22 +281,22 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 						  * in one XMM reg.
 						  */
 
-		/* B.1 load 1 mbuf point */
+		/* B.1 load 2 mbuf point */
 		mbp1 = *(vector unsigned long *)&sw_ring[pos];
 		/* Read desc statuses backwards to avoid race condition */
-		/* A.1 load 4 pkts desc */
+		/* A.1 load desc[3] */
 		descs[3] = *(vector unsigned long *)(rxdp + 3);
 		rte_compiler_barrier();
 
 		/* B.2 copy 2 mbuf point into rx_pkts  */
 		*(vector unsigned long *)&rx_pkts[pos] = mbp1;
 
-		/* B.1 load 1 mbuf point */
+		/* B.1 load 2 mbuf point */
 		mbp2 = *(vector unsigned long *)&sw_ring[pos + 2];
 
+		/* A.1 load desc[2-0] */
 		descs[2] = *(vector unsigned long *)(rxdp + 2);
 		rte_compiler_barrier();
-		/* B.1 load 2 mbuf point */
 		descs[1] = *(vector unsigned long *)(rxdp + 1);
 		rte_compiler_barrier();
 		descs[0] = *(vector unsigned long *)(rxdp);
diff --git a/drivers/net/i40e/i40e_rxtx_vec_neon.c b/drivers/net/i40e/i40e_rxtx_vec_neon.c
index d279cd3a9b..bd1e0490da 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_neon.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_neon.c
@@ -279,20 +279,20 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 
 		int32x4_t len_shl = {0, 0, 0, PKTLEN_SHIFT};
 
-		/* B.1 load 1 mbuf point */
+		/* B.1 load 2 mbuf point */
 		mbp1 = vld1q_u64((uint64_t *)&sw_ring[pos]);
 		/* Read desc statuses backwards to avoid race condition */
-		/* A.1 load 4 pkts desc */
+		/* A.1 load desc[3] */
 		descs[3] =  vld1q_u64((uint64_t *)(rxdp + 3));
 
 		/* B.2 copy 2 mbuf point into rx_pkts  */
 		vst1q_u64((uint64_t *)&rx_pkts[pos], mbp1);
 
-		/* B.1 load 1 mbuf point */
+		/* B.1 load 2 mbuf point */
 		mbp2 = vld1q_u64((uint64_t *)&sw_ring[pos + 2]);
 
+		/* A.1 load desc[2-0] */
 		descs[2] =  vld1q_u64((uint64_t *)(rxdp + 2));
-		/* B.1 load 2 mbuf point */
 		descs[1] =  vld1q_u64((uint64_t *)(rxdp + 1));
 		descs[0] =  vld1q_u64((uint64_t *)(rxdp));
 
diff --git a/drivers/net/i40e/i40e_rxtx_vec_sse.c b/drivers/net/i40e/i40e_rxtx_vec_sse.c
index 8c17f2d27f..65202a5277 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_sse.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_sse.c
@@ -462,7 +462,7 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		/* B.1 load 2 (64 bit) or 4 (32 bit) mbuf points */
 		mbp1 = _mm_loadu_si128((__m128i *)&sw_ring[pos]);
 		/* Read desc statuses backwards to avoid race condition */
-		/* A.1 load 4 pkts desc */
+		/* A.1 load desc[3] */
 		descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
 		rte_compiler_barrier();
 
@@ -474,9 +474,9 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		mbp2 = _mm_loadu_si128((__m128i *)&sw_ring[pos+2]);
 #endif
 
+		/* A.1 load desc[2-0] */
 		descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
 		rte_compiler_barrier();
-		/* B.1 load 2 mbuf point */
 		descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
 		rte_compiler_barrier();
 		descs[0] = _mm_loadu_si128((__m128i *)(rxdp));
diff --git a/drivers/net/iavf/iavf_rxtx_vec_sse.c b/drivers/net/iavf/iavf_rxtx_vec_sse.c
index 8237a8180a..aefa81ecd3 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_sse.c
+++ b/drivers/net/iavf/iavf_rxtx_vec_sse.c
@@ -341,7 +341,7 @@ _recv_raw_pkts_vec(struct iavf_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		/* B.1 load 2 (64 bit) or 4 (32 bit) mbuf points */
 		mbp1 = _mm_loadu_si128((__m128i *)&sw_ring[pos]);
 		/* Read desc statuses backwards to avoid race condition */
-		/* A.1 load 4 pkts desc */
+		/* A.1 load desc[3] */
 		descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
 		rte_compiler_barrier();
 
@@ -353,9 +353,9 @@ _recv_raw_pkts_vec(struct iavf_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		mbp2 = _mm_loadu_si128((__m128i *)&sw_ring[pos + 2]);
 #endif
 
+		/* A.1 load desc[2-0] */
 		descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
 		rte_compiler_barrier();
-		/* B.1 load 2 mbuf point */
 		descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
 		rte_compiler_barrier();
 		descs[0] = _mm_loadu_si128((__m128i *)(rxdp));
diff --git a/drivers/net/ice/ice_rxtx_vec_sse.c b/drivers/net/ice/ice_rxtx_vec_sse.c
index b6bcca6d19..71320d82aa 100644
--- a/drivers/net/ice/ice_rxtx_vec_sse.c
+++ b/drivers/net/ice/ice_rxtx_vec_sse.c
@@ -366,7 +366,7 @@ _ice_recv_raw_pkts_vec(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		/* B.1 load 2 (64 bit) or 4 (32 bit) mbuf points */
 		mbp1 = _mm_loadu_si128((__m128i *)&sw_ring[pos]);
 		/* Read desc statuses backwards to avoid race condition */
-		/* A.1 load 4 pkts desc */
+		/* A.1 load desc[3] */
 		descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
 		rte_compiler_barrier();
 
@@ -378,9 +378,9 @@ _ice_recv_raw_pkts_vec(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		mbp2 = _mm_loadu_si128((__m128i *)&sw_ring[pos + 2]);
 #endif
 
+		/* A.1 load desc[2-0] */
 		descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
 		rte_compiler_barrier();
-		/* B.1 load 2 mbuf point */
 		descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
 		rte_compiler_barrier();
 		descs[0] = _mm_loadu_si128((__m128i *)(rxdp));
diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
index e9b101a486..414845f2d7 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
@@ -454,7 +454,7 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		mbp1 = _mm_loadu_si128((__m128i *)&sw_ring[pos]);
 
 		/* Read desc statuses backwards to avoid race condition */
-		/* A.1 load 4 pkts desc */
+		/* A.1 load desc[3] */
 		descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
 		rte_compiler_barrier();
 
@@ -466,9 +466,9 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		mbp2 = _mm_loadu_si128((__m128i *)&sw_ring[pos+2]);
 #endif
 
+		/* A.1 load desc[2-0] */
 		descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
 		rte_compiler_barrier();
-		/* B.1 load 2 mbuf point */
 		descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
 		rte_compiler_barrier();
 		descs[0] = _mm_loadu_si128((__m128i *)(rxdp));
-- 
2.34.0

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2021-11-30 16:50:06.485449708 +0100
+++ 0005-drivers-net-fix-vector-Rx-comments.patch	2021-11-30 16:50:05.506871446 +0100
@@ -1 +1 @@
-From 4f76ac98b787dbc893d9aaae487f79e69cb962c4 Mon Sep 17 00:00:00 2001
+From b83e5a9c5caa2fd047d6b215ff9e90b2643f274f Mon Sep 17 00:00:00 2001
@@ -5,0 +6,2 @@
+[ upstream commit 4f76ac98b787dbc893d9aaae487f79e69cb962c4 ]
+
@@ -17 +18,0 @@
-Cc: stable at dpdk.org
@@ -27 +28 @@
- drivers/net/iavf/iavf_rxtx_vec_sse.c     | 8 ++++----
+ drivers/net/iavf/iavf_rxtx_vec_sse.c     | 4 ++--
@@ -30 +31 @@
- 7 files changed, 20 insertions(+), 20 deletions(-)
+ 7 files changed, 18 insertions(+), 18 deletions(-)
@@ -33 +34 @@
-index cae5322d48..83af01dc2d 100644
+index ab7c515e9c..a441d33980 100644
@@ -57 +58 @@
-index edaa462ac8..b99323992f 100644
+index e912ab02bc..12dacc31a4 100644
@@ -88 +89 @@
-index 32336fdb80..fb624a4882 100644
+index d279cd3a9b..bd1e0490da 100644
@@ -91 +92 @@
-@@ -280,20 +280,20 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *__rte_restrict rxq,
+@@ -279,20 +279,20 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
@@ -117 +118 @@
-index 03a0320353..b235502db5 100644
+index 8c17f2d27f..65202a5277 100644
@@ -141 +142 @@
-index b813d96ef4..ee1e905525 100644
+index 8237a8180a..aefa81ecd3 100644
@@ -144,21 +145 @@
-@@ -494,7 +494,7 @@ _recv_raw_pkts_vec(struct iavf_rx_queue *rxq, struct rte_mbuf **rx_pkts,
- 		/* B.1 load 2 (64 bit) or 4 (32 bit) mbuf points */
- 		mbp1 = _mm_loadu_si128((__m128i *)&sw_ring[pos]);
- 		/* Read desc statuses backwards to avoid race condition */
--		/* A.1 load 4 pkts desc */
-+		/* A.1 load desc[3] */
- 		descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
- 		rte_compiler_barrier();
- 
-@@ -506,9 +506,9 @@ _recv_raw_pkts_vec(struct iavf_rx_queue *rxq, struct rte_mbuf **rx_pkts,
- 		mbp2 = _mm_loadu_si128((__m128i *)&sw_ring[pos + 2]);
- #endif
- 
-+		/* A.1 load desc[2-0] */
- 		descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
- 		rte_compiler_barrier();
--		/* B.1 load 2 mbuf point */
- 		descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
- 		rte_compiler_barrier();
- 		descs[0] = _mm_loadu_si128((__m128i *)(rxdp));
-@@ -755,7 +755,7 @@ _recv_raw_pkts_vec_flex_rxd(struct iavf_rx_queue *rxq,
+@@ -341,7 +341,7 @@ _recv_raw_pkts_vec(struct iavf_rx_queue *rxq, struct rte_mbuf **rx_pkts,
@@ -173 +154 @@
-@@ -767,9 +767,9 @@ _recv_raw_pkts_vec_flex_rxd(struct iavf_rx_queue *rxq,
+@@ -353,9 +353,9 @@ _recv_raw_pkts_vec(struct iavf_rx_queue *rxq, struct rte_mbuf **rx_pkts,
@@ -185 +166 @@
-index 5f7e13ee39..653bd28b41 100644
+index b6bcca6d19..71320d82aa 100644
@@ -188 +169 @@
-@@ -416,7 +416,7 @@ _ice_recv_raw_pkts_vec(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
+@@ -366,7 +366,7 @@ _ice_recv_raw_pkts_vec(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
@@ -197 +178 @@
-@@ -428,9 +428,9 @@ _ice_recv_raw_pkts_vec(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
+@@ -378,9 +378,9 @@ _ice_recv_raw_pkts_vec(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
@@ -209 +190 @@
-index 3a3ef51172..1dea95e73b 100644
+index e9b101a486..414845f2d7 100644