patch 'app/testpmd: fix Tx scheduling interval' has been queued to stable release 20.11.5

[luca.boccassi at gmail.com]

Hi,

FYI, your patch has been queued to stable release 20.11.5

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 02/20/22. 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/bluca/dpdk-stable

This queued commit can be viewed at:
https://github.com/bluca/dpdk-stable/commit/a26506bce105af8f8ebc8f720a3b558d4c208689

Thanks.

Luca Boccassi

---
>From a26506bce105af8f8ebc8f720a3b558d4c208689 Mon Sep 17 00:00:00 2001
From: Viacheslav Ovsiienko <viacheslavo at nvidia.com>
Date: Tue, 23 Nov 2021 18:32:58 +0200
Subject: [PATCH] app/testpmd: fix Tx scheduling interval

[ upstream commit 9fac5ca8edaebd0f6206193277876fdebb6f3eb2 ]

The first "set txtimes" command parameter specifies the time
interval between scheduled send bursts for single queue. This
interval should be the same for all the forwarding ports.
It requires to maintain the timing related variables on per
queue basis instead of per core, as currently implemented.
This resulted in wrong burst intervals if two or more cores
were generating the scheduled traffic for two or more ports
in txonly mode.

This patch moves the timing variable to the fstream structure.
Only txonly forwarding mode with enabled send scheduling is
affected.

Fixes: 4940344dab1d ("app/testpmd: add Tx scheduling command")

Signed-off-by: Viacheslav Ovsiienko <viacheslavo at nvidia.com>
Acked-by: Ferruh Yigit <ferruh.yigit at intel.com>
---
 app/test-pmd/testpmd.h |  1 +
 app/test-pmd/txonly.c  | 20 ++++++--------------
 2 files changed, 7 insertions(+), 14 deletions(-)

diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h
index 43e49a8069..2d4dc05332 100644
--- a/app/test-pmd/testpmd.h
+++ b/app/test-pmd/testpmd.h
@@ -137,6 +137,7 @@ struct fwd_stream {
 	uint64_t rx_bad_l4_csum ; /**< received packets has bad l4 checksum */
 	uint64_t rx_bad_outer_l4_csum;
 	/**< received packets has bad outer l4 checksum */
+	uint64_t ts_skew; /**< TX scheduling timestamp */
 	unsigned int gro_times;	/**< GRO operation times */
 	uint64_t     core_cycles; /**< used for RX and TX processing */
 	struct pkt_burst_stats rx_burst_stats;
diff --git a/app/test-pmd/txonly.c b/app/test-pmd/txonly.c
index 8e242e801b..9f5087d215 100644
--- a/app/test-pmd/txonly.c
+++ b/app/test-pmd/txonly.c
@@ -60,14 +60,10 @@ uint32_t tx_ip_dst_addr = (198U << 24) | (18 << 16) | (0 << 8) | 2;
 static struct rte_ipv4_hdr pkt_ip_hdr; /**< IP header of transmitted packets. */
 RTE_DEFINE_PER_LCORE(uint8_t, _ip_var); /**< IP address variation */
 static struct rte_udp_hdr pkt_udp_hdr; /**< UDP header of tx packets. */
-RTE_DEFINE_PER_LCORE(uint64_t, timestamp_qskew);
-					/**< Timestamp offset per queue */
-RTE_DEFINE_PER_LCORE(uint32_t, timestamp_idone); /**< Timestamp init done. */
 
 static uint64_t timestamp_mask; /**< Timestamp dynamic flag mask */
 static int32_t timestamp_off; /**< Timestamp dynamic field offset */
 static bool timestamp_enable; /**< Timestamp enable */
-static uint32_t timestamp_init_req; /**< Timestamp initialization request. */
 static uint64_t timestamp_initial[RTE_MAX_ETHPORTS];
 
 static void
@@ -195,7 +191,7 @@ static inline bool
 pkt_burst_prepare(struct rte_mbuf *pkt, struct rte_mempool *mbp,
 		struct rte_ether_hdr *eth_hdr, const uint16_t vlan_tci,
 		const uint16_t vlan_tci_outer, const uint64_t ol_flags,
-		const uint16_t idx, const struct fwd_stream *fs)
+		const uint16_t idx, struct fwd_stream *fs)
 {
 	struct rte_mbuf *pkt_segs[RTE_MAX_SEGS_PER_PKT];
 	struct rte_mbuf *pkt_seg;
@@ -263,11 +259,10 @@ pkt_burst_prepare(struct rte_mbuf *pkt, struct rte_mempool *mbp,
 		update_pkt_header(pkt, pkt_len);
 
 	if (unlikely(timestamp_enable)) {
-		uint64_t skew = RTE_PER_LCORE(timestamp_qskew);
+		uint64_t skew = fs->ts_skew;
 		struct tx_timestamp timestamp_mark;
 
-		if (unlikely(timestamp_init_req !=
-				RTE_PER_LCORE(timestamp_idone))) {
+		if (!skew) {
 			struct rte_eth_dev *dev = &rte_eth_devices[fs->tx_port];
 			unsigned int txqs_n = dev->data->nb_tx_queues;
 			uint64_t phase = tx_pkt_times_inter * fs->tx_queue /
@@ -278,8 +273,7 @@ pkt_burst_prepare(struct rte_mbuf *pkt, struct rte_mempool *mbp,
 			 */
 			skew = timestamp_initial[fs->tx_port] +
 			       tx_pkt_times_inter + phase;
-			RTE_PER_LCORE(timestamp_qskew) = skew;
-			RTE_PER_LCORE(timestamp_idone) = timestamp_init_req;
+			fs->ts_skew = skew;
 		}
 		timestamp_mark.pkt_idx = rte_cpu_to_be_16(idx);
 		timestamp_mark.queue_idx = rte_cpu_to_be_16(fs->tx_queue);
@@ -289,14 +283,14 @@ pkt_burst_prepare(struct rte_mbuf *pkt, struct rte_mempool *mbp,
 			pkt->ol_flags |= timestamp_mask;
 			*RTE_MBUF_DYNFIELD
 				(pkt, timestamp_off, uint64_t *) = skew;
-			RTE_PER_LCORE(timestamp_qskew) = skew;
+			fs->ts_skew = skew;
 			timestamp_mark.ts = rte_cpu_to_be_64(skew);
 		} else if (tx_pkt_times_intra) {
 			skew +=	tx_pkt_times_intra;
 			pkt->ol_flags |= timestamp_mask;
 			*RTE_MBUF_DYNFIELD
 				(pkt, timestamp_off, uint64_t *) = skew;
-			RTE_PER_LCORE(timestamp_qskew) = skew;
+			fs->ts_skew = skew;
 			timestamp_mark.ts = rte_cpu_to_be_64(skew);
 		} else {
 			timestamp_mark.ts = RTE_BE64(0);
@@ -450,7 +444,6 @@ tx_only_begin(portid_t pi)
 	timestamp_enable = false;
 	timestamp_mask = 0;
 	timestamp_off = -1;
-	RTE_PER_LCORE(timestamp_qskew) = 0;
 	dynf = rte_mbuf_dynflag_lookup
 				(RTE_MBUF_DYNFLAG_TX_TIMESTAMP_NAME, NULL);
 	if (dynf >= 0)
@@ -493,7 +486,6 @@ tx_only_begin(portid_t pi)
 				return -EINVAL;
 			}
 		}
-		timestamp_init_req++;
 	}
 
 	/* Make sure all settings are visible on forwarding cores.*/
-- 
2.30.2

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2022-02-18 12:37:39.501766816 +0000
+++ 0036-app-testpmd-fix-Tx-scheduling-interval.patch	2022-02-18 12:37:37.626790491 +0000
@@ -1 +1 @@
-From 9fac5ca8edaebd0f6206193277876fdebb6f3eb2 Mon Sep 17 00:00:00 2001
+From a26506bce105af8f8ebc8f720a3b558d4c208689 Mon Sep 17 00:00:00 2001
@@ -5,0 +6,2 @@
+[ upstream commit 9fac5ca8edaebd0f6206193277876fdebb6f3eb2 ]
+
@@ -20 +21,0 @@
-Cc: stable at dpdk.org
@@ -30 +31 @@
-index 2149ecd93a..9967825044 100644
+index 43e49a8069..2d4dc05332 100644
@@ -33 +34,3 @@
-@@ -147,6 +147,7 @@ struct fwd_stream {
+@@ -137,6 +137,7 @@ struct fwd_stream {
+ 	uint64_t rx_bad_l4_csum ; /**< received packets has bad l4 checksum */
+ 	uint64_t rx_bad_outer_l4_csum;
@@ -35,2 +37,0 @@
- 	uint64_t rx_bad_outer_ip_csum;
- 	/**< received packets having bad outer ip checksum */
@@ -38 +38,0 @@
- #ifdef RTE_LIB_GRO
@@ -40 +40,2 @@
- #endif
+ 	uint64_t     core_cycles; /**< used for RX and TX processing */
+ 	struct pkt_burst_stats rx_burst_stats;
@@ -42 +43 @@
-index e8c0c7b926..fc039a622c 100644
+index 8e242e801b..9f5087d215 100644
@@ -45 +46 @@
-@@ -59,14 +59,10 @@ uint32_t tx_ip_dst_addr = (198U << 24) | (18 << 16) | (0 << 8) | 2;
+@@ -60,14 +60,10 @@ uint32_t tx_ip_dst_addr = (198U << 24) | (18 << 16) | (0 << 8) | 2;
@@ -60 +61 @@
-@@ -194,7 +190,7 @@ static inline bool
+@@ -195,7 +191,7 @@ static inline bool
@@ -69 +70 @@
-@@ -262,11 +258,10 @@ pkt_burst_prepare(struct rte_mbuf *pkt, struct rte_mempool *mbp,
+@@ -263,11 +259,10 @@ pkt_burst_prepare(struct rte_mbuf *pkt, struct rte_mempool *mbp,
@@ -79,5 +80,5 @@
-+		if (unlikely(!skew)) {
- 			struct rte_eth_dev_info dev_info;
- 			unsigned int txqs_n;
- 			uint64_t phase;
-@@ -289,8 +284,7 @@ pkt_burst_prepare(struct rte_mbuf *pkt, struct rte_mempool *mbp,
++		if (!skew) {
+ 			struct rte_eth_dev *dev = &rte_eth_devices[fs->tx_port];
+ 			unsigned int txqs_n = dev->data->nb_tx_queues;
+ 			uint64_t phase = tx_pkt_times_inter * fs->tx_queue /
+@@ -278,8 +273,7 @@ pkt_burst_prepare(struct rte_mbuf *pkt, struct rte_mempool *mbp,
@@ -93 +94 @@
-@@ -300,14 +294,14 @@ pkt_burst_prepare(struct rte_mbuf *pkt, struct rte_mempool *mbp,
+@@ -289,14 +283,14 @@ pkt_burst_prepare(struct rte_mbuf *pkt, struct rte_mempool *mbp,
@@ -110 +111 @@
-@@ -461,7 +455,6 @@ tx_only_begin(portid_t pi)
+@@ -450,7 +444,6 @@ tx_only_begin(portid_t pi)
@@ -118 +119 @@
-@@ -504,7 +497,6 @@ tx_only_begin(portid_t pi)
+@@ -493,7 +486,6 @@ tx_only_begin(portid_t pi)