patch 'app/compress-perf: fix testing single operation' has been queued to stable release 20.11.8

[luca.boccassi@gmail.com]

Hi,

FYI, your patch has been queued to stable release 20.11.8

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 02/25/23. 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/3cc7c9875b09be70696cd0f5c00ed8c540bb8c44

Thanks.

Luca Boccassi

---
From 3cc7c9875b09be70696cd0f5c00ed8c540bb8c44 Mon Sep 17 00:00:00 2001
From: Michael Baum <michaelba@nvidia.com>
Date: Tue, 14 Feb 2023 19:40:28 +0200
Subject: [PATCH] app/compress-perf: fix testing single operation

[ upstream commit 83cc3b90ad7a63868a43a67d6aa13b55068fbe0c ]

Part of the application options is to test only compress and only
decompress but actually the application ignores this user option and
tries to test always both compress and decompress.

Allow testing only compress and only decompress.

Fixes: e0b6287c035d ("app/compress-perf: add parser")

Signed-off-by: Matan Azrad <matan@nvidia.com>
Signed-off-by: Michael Baum <michaelba@nvidia.com>
---
 app/test-compress-perf/comp_perf_options.h    |   6 +-
 .../comp_perf_options_parse.c                 |   4 +-
 .../comp_perf_test_common.c                   | 126 +++++++++++++-----
 .../comp_perf_test_cyclecount.c               |  69 ++++++----
 .../comp_perf_test_throughput.c               |  66 +++++----
 .../comp_perf_test_verify.c                   |  58 +++++---
 app/test-compress-perf/main.c                 |   8 ++
 7 files changed, 223 insertions(+), 114 deletions(-)

diff --git a/app/test-compress-perf/comp_perf_options.h b/app/test-compress-perf/comp_perf_options.h
index 0b777521c5..cfb00bd1ad 100644
--- a/app/test-compress-perf/comp_perf_options.h
+++ b/app/test-compress-perf/comp_perf_options.h
@@ -30,9 +30,9 @@ enum cperf_test_type {
 };
 
 enum comp_operation {
-	COMPRESS_ONLY,
-	DECOMPRESS_ONLY,
-	COMPRESS_DECOMPRESS
+	COMPRESS = (1 << 0),
+	DECOMPRESS = (1 << 1),
+	COMPRESS_DECOMPRESS = (COMPRESS | DECOMPRESS),
 };
 
 struct range_list {
diff --git a/app/test-compress-perf/comp_perf_options_parse.c b/app/test-compress-perf/comp_perf_options_parse.c
index 9b9d4e6554..303e714cda 100644
--- a/app/test-compress-perf/comp_perf_options_parse.c
+++ b/app/test-compress-perf/comp_perf_options_parse.c
@@ -446,11 +446,11 @@ parse_op_type(struct comp_test_data *test_data, const char *arg)
 	struct name_id_map optype_namemap[] = {
 		{
 			"comp",
-			COMPRESS_ONLY
+			COMPRESS
 		},
 		{
 			"decomp",
-			DECOMPRESS_ONLY
+			DECOMPRESS
 		},
 		{
 			"comp_and_decomp",
diff --git a/app/test-compress-perf/comp_perf_test_common.c b/app/test-compress-perf/comp_perf_test_common.c
index b402a0d839..cd60958944 100644
--- a/app/test-compress-perf/comp_perf_test_common.c
+++ b/app/test-compress-perf/comp_perf_test_common.c
@@ -227,23 +227,43 @@ comp_perf_allocate_memory(struct comp_test_data *test_data,
 {
 	uint16_t comp_mbuf_size;
 	uint16_t decomp_mbuf_size;
+	size_t comp_data_size;
+	size_t decomp_data_size;
+	size_t output_data_sz;
 
 	test_data->out_seg_sz = find_buf_size(test_data->seg_sz);
 
-	/* Number of segments for input and output
-	 * (compression and decompression)
-	 */
-	test_data->total_segs = DIV_CEIL(test_data->input_data_sz,
-			test_data->seg_sz);
+	if (test_data->test_op & COMPRESS) {
+		/*
+		 * Number of segments for input and output
+		 * (compression and decompression)
+		 */
+		test_data->total_segs = DIV_CEIL(test_data->input_data_sz,
+						 test_data->seg_sz);
+	} else {
+		/*
+		 * When application does decompression only, input data is
+		 * compressed and smaller than the output. The expected size of
+		 * uncompressed data given by the user in segment size argument.
+		 */
+		test_data->total_segs = test_data->max_sgl_segs;
+	}
+
+	output_data_sz = (size_t) test_data->out_seg_sz * test_data->total_segs;
+	output_data_sz =
+		RTE_MAX(output_data_sz, (size_t) MIN_COMPRESSED_BUF_SIZE);
 
 	if (test_data->use_external_mbufs != 0) {
 		if (comp_perf_allocate_external_mbufs(test_data, mem) < 0)
 			return -1;
 		comp_mbuf_size = 0;
 		decomp_mbuf_size = 0;
-	} else {
+	} else if (test_data->test_op & COMPRESS) {
 		comp_mbuf_size = test_data->out_seg_sz + RTE_PKTMBUF_HEADROOM;
 		decomp_mbuf_size = test_data->seg_sz + RTE_PKTMBUF_HEADROOM;
+	} else {
+		comp_mbuf_size = test_data->seg_sz + RTE_PKTMBUF_HEADROOM;
+		decomp_mbuf_size = test_data->out_seg_sz + RTE_PKTMBUF_HEADROOM;
 	}
 
 	char pool_name[32] = "";
@@ -287,26 +307,28 @@ comp_perf_allocate_memory(struct comp_test_data *test_data,
 		return -1;
 	}
 
-	/*
-	 * Compressed data might be a bit larger than input data,
-	 * if data cannot be compressed
-	 */
-	mem->compressed_data = rte_zmalloc_socket(NULL,
-				RTE_MAX(
-				    (size_t) test_data->out_seg_sz *
-							  test_data->total_segs,
-				    (size_t) MIN_COMPRESSED_BUF_SIZE),
-				0,
-				rte_socket_id());
+	if (test_data->test_op & COMPRESS) {
+		/*
+		 * Compressed data might be a bit larger than input data,
+		 * if data cannot be compressed
+		 */
+		comp_data_size = output_data_sz;
+		decomp_data_size = test_data->input_data_sz;
+	} else {
+		comp_data_size = test_data->input_data_sz;
+		decomp_data_size = output_data_sz;
+	}
+
+	mem->compressed_data = rte_zmalloc_socket(NULL, comp_data_size, 0,
+						  rte_socket_id());
 	if (mem->compressed_data == NULL) {
 		RTE_LOG(ERR, USER1, "Memory to hold the data from the input "
 				"file could not be allocated\n");
 		return -1;
 	}
 
-	mem->decompressed_data = rte_zmalloc_socket(NULL,
-				test_data->input_data_sz, 0,
-				rte_socket_id());
+	mem->decompressed_data = rte_zmalloc_socket(NULL, decomp_data_size, 0,
+						    rte_socket_id());
 	if (mem->decompressed_data == NULL) {
 		RTE_LOG(ERR, USER1, "Memory to hold the data from the input "
 				"file could not be allocated\n");
@@ -351,6 +373,7 @@ prepare_bufs(struct comp_test_data *test_data, struct cperf_mem_resources *mem)
 	uint16_t segs_per_mbuf = 0;
 	uint32_t cmz = 0;
 	uint32_t dmz = 0;
+	bool decompress_only = !!(test_data->test_op == DECOMPRESS);
 
 	for (i = 0; i < mem->total_bufs; i++) {
 		/* Allocate data in input mbuf and copy data from input file */
@@ -361,8 +384,6 @@ prepare_bufs(struct comp_test_data *test_data, struct cperf_mem_resources *mem)
 			return -1;
 		}
 
-		data_sz = RTE_MIN(remaining_data, test_data->seg_sz);
-
 		if (test_data->use_external_mbufs != 0) {
 			rte_pktmbuf_attach_extbuf(mem->decomp_bufs[i],
 					mem->decomp_memzones[dmz]->addr,
@@ -372,16 +393,23 @@ prepare_bufs(struct comp_test_data *test_data, struct cperf_mem_resources *mem)
 			dmz++;
 		}
 
+		if (!decompress_only)
+			data_sz = RTE_MIN(remaining_data, test_data->seg_sz);
+		else
+			data_sz = test_data->out_seg_sz;
+
 		data_addr = (uint8_t *) rte_pktmbuf_append(
 					mem->decomp_bufs[i], data_sz);
 		if (data_addr == NULL) {
 			RTE_LOG(ERR, USER1, "Could not append data\n");
 			return -1;
 		}
-		rte_memcpy(data_addr, input_data_ptr, data_sz);
 
-		input_data_ptr += data_sz;
-		remaining_data -= data_sz;
+		if (!decompress_only) {
+			rte_memcpy(data_addr, input_data_ptr, data_sz);
+			input_data_ptr += data_sz;
+			remaining_data -= data_sz;
+		}
 
 		/* Already one segment in the mbuf */
 		segs_per_mbuf = 1;
@@ -398,8 +426,6 @@ prepare_bufs(struct comp_test_data *test_data, struct cperf_mem_resources *mem)
 				return -1;
 			}
 
-			data_sz = RTE_MIN(remaining_data, test_data->seg_sz);
-
 			if (test_data->use_external_mbufs != 0) {
 				rte_pktmbuf_attach_extbuf(
 					next_seg,
@@ -410,6 +436,12 @@ prepare_bufs(struct comp_test_data *test_data, struct cperf_mem_resources *mem)
 				dmz++;
 			}
 
+			if (!decompress_only)
+				data_sz = RTE_MIN(remaining_data,
+						  test_data->seg_sz);
+			else
+				data_sz = test_data->out_seg_sz;
+
 			data_addr = (uint8_t *)rte_pktmbuf_append(next_seg,
 				data_sz);
 
@@ -418,9 +450,11 @@ prepare_bufs(struct comp_test_data *test_data, struct cperf_mem_resources *mem)
 				return -1;
 			}
 
-			rte_memcpy(data_addr, input_data_ptr, data_sz);
-			input_data_ptr += data_sz;
-			remaining_data -= data_sz;
+			if (!decompress_only) {
+				rte_memcpy(data_addr, input_data_ptr, data_sz);
+				input_data_ptr += data_sz;
+				remaining_data -= data_sz;
+			}
 
 			if (rte_pktmbuf_chain(mem->decomp_bufs[i],
 					next_seg) < 0) {
@@ -447,16 +481,26 @@ prepare_bufs(struct comp_test_data *test_data, struct cperf_mem_resources *mem)
 			cmz++;
 		}
 
-		data_addr = (uint8_t *) rte_pktmbuf_append(
-					mem->comp_bufs[i],
-					test_data->out_seg_sz);
+		if (decompress_only)
+			data_sz = RTE_MIN(remaining_data, test_data->seg_sz);
+		else
+			data_sz = test_data->out_seg_sz;
+
+		data_addr = (uint8_t *) rte_pktmbuf_append(mem->comp_bufs[i],
+							   data_sz);
 		if (data_addr == NULL) {
 			RTE_LOG(ERR, USER1, "Could not append data\n");
 			return -1;
 		}
 
+		if (decompress_only) {
+			rte_memcpy(data_addr, input_data_ptr, data_sz);
+			input_data_ptr += data_sz;
+			remaining_data -= data_sz;
+		}
+
 		/* Chain mbufs if needed for output mbufs */
-		for (j = 1; j < segs_per_mbuf; j++) {
+		for (j = 1; j < segs_per_mbuf && remaining_data > 0; j++) {
 			struct rte_mbuf *next_seg =
 				rte_pktmbuf_alloc(mem->comp_buf_pool);
 
@@ -476,13 +520,25 @@ prepare_bufs(struct comp_test_data *test_data, struct cperf_mem_resources *mem)
 				cmz++;
 			}
 
+			if (decompress_only)
+				data_sz = RTE_MIN(remaining_data,
+						  test_data->seg_sz);
+			else
+				data_sz = test_data->out_seg_sz;
+
 			data_addr = (uint8_t *)rte_pktmbuf_append(next_seg,
-				test_data->out_seg_sz);
+								  data_sz);
 			if (data_addr == NULL) {
 				RTE_LOG(ERR, USER1, "Could not append data\n");
 				return -1;
 			}
 
+			if (decompress_only) {
+				rte_memcpy(data_addr, input_data_ptr, data_sz);
+				input_data_ptr += data_sz;
+				remaining_data -= data_sz;
+			}
+
 			if (rte_pktmbuf_chain(mem->comp_bufs[i],
 					next_seg) < 0) {
 				RTE_LOG(ERR, USER1, "Could not chain mbufs\n");
diff --git a/app/test-compress-perf/comp_perf_test_cyclecount.c b/app/test-compress-perf/comp_perf_test_cyclecount.c
index ea62fcf52e..8474e59f17 100644
--- a/app/test-compress-perf/comp_perf_test_cyclecount.c
+++ b/app/test-compress-perf/comp_perf_test_cyclecount.c
@@ -510,38 +510,55 @@ cperf_cyclecount_test_runner(void *test_ctx)
 	if (cperf_verify_test_runner(&ctx->ver))
 		return EXIT_FAILURE;
 
-	/*
-	 * Run the tests twice, discarding the first performance
-	 * results, before the cache is warmed up
-	 */
+	if (test_data->test_op & COMPRESS) {
+		/*
+		 * Run the test twice, discarding the first performance
+		 * results, before the cache is warmed up
+		 */
+		for (i = 0; i < 2; i++) {
+			if (main_loop(ctx, RTE_COMP_COMPRESS) < 0)
+				return EXIT_FAILURE;
+		}
 
-	/* C O M P R E S S */
-	for (i = 0; i < 2; i++) {
-		if (main_loop(ctx, RTE_COMP_COMPRESS) < 0)
-			return EXIT_FAILURE;
-	}
-
-	ops_enq_retries_comp = ctx->ops_enq_retries;
-	ops_deq_retries_comp = ctx->ops_deq_retries;
+		ops_enq_retries_comp = ctx->ops_enq_retries;
+		ops_deq_retries_comp = ctx->ops_deq_retries;
 
-	duration_enq_per_op_comp = ctx->duration_enq /
-			(ctx->ver.mem.total_bufs * test_data->num_iter);
-	duration_deq_per_op_comp = ctx->duration_deq /
-			(ctx->ver.mem.total_bufs * test_data->num_iter);
+		duration_enq_per_op_comp = ctx->duration_enq /
+				(ctx->ver.mem.total_bufs * test_data->num_iter);
+		duration_deq_per_op_comp = ctx->duration_deq /
+				(ctx->ver.mem.total_bufs * test_data->num_iter);
+	} else {
+		ops_enq_retries_comp = 0;
+		ops_deq_retries_comp = 0;
 
-	/* D E C O M P R E S S */
-	for (i = 0; i < 2; i++) {
-		if (main_loop(ctx, RTE_COMP_DECOMPRESS) < 0)
-			return EXIT_FAILURE;
+		duration_enq_per_op_comp = 0;
+		duration_deq_per_op_comp = 0;
 	}
 
-	ops_enq_retries_decomp = ctx->ops_enq_retries;
-	ops_deq_retries_decomp = ctx->ops_deq_retries;
+	if (test_data->test_op & DECOMPRESS) {
+		/*
+		 * Run the test twice, discarding the first performance
+		 * results, before the cache is warmed up
+		 */
+		for (i = 0; i < 2; i++) {
+			if (main_loop(ctx, RTE_COMP_DECOMPRESS) < 0)
+				return EXIT_FAILURE;
+		}
+
+		ops_enq_retries_decomp = ctx->ops_enq_retries;
+		ops_deq_retries_decomp = ctx->ops_deq_retries;
 
-	duration_enq_per_op_decomp = ctx->duration_enq /
-			(ctx->ver.mem.total_bufs * test_data->num_iter);
-	duration_deq_per_op_decomp = ctx->duration_deq /
-			(ctx->ver.mem.total_bufs * test_data->num_iter);
+		duration_enq_per_op_decomp = ctx->duration_enq /
+				(ctx->ver.mem.total_bufs * test_data->num_iter);
+		duration_deq_per_op_decomp = ctx->duration_deq /
+				(ctx->ver.mem.total_bufs * test_data->num_iter);
+	} else {
+		ops_enq_retries_decomp = 0;
+		ops_deq_retries_decomp = 0;
+
+		duration_enq_per_op_decomp = 0;
+		duration_deq_per_op_decomp = 0;
+	}
 
 	duration_setup_per_op = ctx->duration_op /
 			(ctx->ver.mem.total_bufs * test_data->num_iter);
diff --git a/app/test-compress-perf/comp_perf_test_throughput.c b/app/test-compress-perf/comp_perf_test_throughput.c
index 7574e33ac7..5ea56e366a 100644
--- a/app/test-compress-perf/comp_perf_test_throughput.c
+++ b/app/test-compress-perf/comp_perf_test_throughput.c
@@ -355,41 +355,53 @@ cperf_throughput_test_runner(void *test_ctx)
 	 * First the verification part is needed
 	 */
 	if (cperf_verify_test_runner(&ctx->ver)) {
-		ret =  EXIT_FAILURE;
+		ret = EXIT_FAILURE;
 		goto end;
 	}
 
-	/*
-	 * Run the tests twice, discarding the first performance
-	 * results, before the cache is warmed up
-	 */
-	for (i = 0; i < 2; i++) {
-		if (main_loop(ctx, RTE_COMP_COMPRESS) < 0) {
-			ret = EXIT_FAILURE;
-			goto end;
+	if (test_data->test_op & COMPRESS) {
+		/*
+		 * Run the test twice, discarding the first performance
+		 * results, before the cache is warmed up
+		 */
+		for (i = 0; i < 2; i++) {
+			if (main_loop(ctx, RTE_COMP_COMPRESS) < 0) {
+				ret = EXIT_FAILURE;
+				goto end;
+			}
 		}
-	}
 
-	for (i = 0; i < 2; i++) {
-		if (main_loop(ctx, RTE_COMP_DECOMPRESS) < 0) {
-			ret = EXIT_FAILURE;
-			goto end;
-		}
-	}
-
-	ctx->comp_tsc_byte =
+		ctx->comp_tsc_byte =
 			(double)(ctx->comp_tsc_duration[test_data->level]) /
-					test_data->input_data_sz;
+						       test_data->input_data_sz;
+		ctx->comp_gbps = rte_get_tsc_hz() / ctx->comp_tsc_byte * 8 /
+								     1000000000;
+	} else {
+		ctx->comp_tsc_byte = 0;
+		ctx->comp_gbps = 0;
+	}
 
-	ctx->decomp_tsc_byte =
+	if (test_data->test_op & DECOMPRESS) {
+		/*
+		 * Run the test twice, discarding the first performance
+		 * results, before the cache is warmed up
+		 */
+		for (i = 0; i < 2; i++) {
+			if (main_loop(ctx, RTE_COMP_DECOMPRESS) < 0) {
+				ret = EXIT_FAILURE;
+				goto end;
+			}
+		}
+
+		ctx->decomp_tsc_byte =
 			(double)(ctx->decomp_tsc_duration[test_data->level]) /
-					test_data->input_data_sz;
-
-	ctx->comp_gbps = rte_get_tsc_hz() / ctx->comp_tsc_byte * 8 /
-			1000000000;
-
-	ctx->decomp_gbps = rte_get_tsc_hz() / ctx->decomp_tsc_byte * 8 /
-			1000000000;
+						       test_data->input_data_sz;
+		ctx->decomp_gbps = rte_get_tsc_hz() / ctx->decomp_tsc_byte * 8 /
+								     1000000000;
+	} else {
+		ctx->decomp_tsc_byte = 0;
+		ctx->decomp_gbps = 0;
+	}
 
 	if (rte_atomic16_test_and_set(&display_once)) {
 		printf("\n%12s%6s%12s%17s%15s%16s\n",
diff --git a/app/test-compress-perf/comp_perf_test_verify.c b/app/test-compress-perf/comp_perf_test_verify.c
index 98704a9548..aaf50657c0 100644
--- a/app/test-compress-perf/comp_perf_test_verify.c
+++ b/app/test-compress-perf/comp_perf_test_verify.c
@@ -112,7 +112,8 @@ main_loop(struct cperf_verify_ctx *ctx, enum rte_comp_xform_type type)
 		output_data_sz = &ctx->decomp_data_sz;
 		input_bufs = mem->comp_bufs;
 		output_bufs = mem->decomp_bufs;
-		out_seg_sz = test_data->seg_sz;
+		out_seg_sz = (test_data->test_op & COMPRESS) ?
+			     test_data->seg_sz : test_data->out_seg_sz;
 	}
 
 	/* Create private xform */
@@ -395,32 +396,47 @@ cperf_verify_test_runner(void *test_ctx)
 
 	test_data->ratio = 0;
 
-	if (main_loop(ctx, RTE_COMP_COMPRESS) < 0) {
-		ret = EXIT_FAILURE;
-		goto end;
+	if (test_data->test_op & COMPRESS) {
+		if (main_loop(ctx, RTE_COMP_COMPRESS) < 0) {
+			ret = EXIT_FAILURE;
+			goto end;
+		}
 	}
 
-	if (main_loop(ctx, RTE_COMP_DECOMPRESS) < 0) {
-		ret = EXIT_FAILURE;
-		goto end;
-	}
+	if (test_data->test_op & DECOMPRESS) {
+		if (main_loop(ctx, RTE_COMP_DECOMPRESS) < 0) {
+			ret = EXIT_FAILURE;
+			goto end;
+		}
+
+		if (!(test_data->test_op & COMPRESS)) {
+			/*
+			 * For DECOMPRESS_ONLY mode there is no more
+			 * verifications, reset the 'ratio' and 'comp_data_sz'
+			 * fields for other tests report.
+			 */
+			ctx->comp_data_sz = 0;
+			ctx->ratio = 0;
+			goto end;
+		}
 
-	if (ctx->decomp_data_sz != test_data->input_data_sz) {
-		RTE_LOG(ERR, USER1,
-	   "Decompressed data length not equal to input data length\n");
-		RTE_LOG(ERR, USER1,
-			"Decompressed size = %zu, expected = %zu\n",
-			ctx->decomp_data_sz, test_data->input_data_sz);
-		ret = EXIT_FAILURE;
-		goto end;
-	} else {
-		if (memcmp(ctx->mem.decompressed_data,
-				test_data->input_data,
-				test_data->input_data_sz) != 0) {
+		if (ctx->decomp_data_sz != test_data->input_data_sz) {
+			RTE_LOG(ERR, USER1,
+				"Decompressed data length not equal to input data length\n");
 			RTE_LOG(ERR, USER1,
-		    "Decompressed data is not the same as file data\n");
+				"Decompressed size = %zu, expected = %zu\n",
+				ctx->decomp_data_sz, test_data->input_data_sz);
 			ret = EXIT_FAILURE;
 			goto end;
+		} else {
+			if (memcmp(ctx->mem.decompressed_data,
+					test_data->input_data,
+					test_data->input_data_sz) != 0) {
+				RTE_LOG(ERR, USER1,
+					"Decompressed data is not the same as file data\n");
+				ret = EXIT_FAILURE;
+				goto end;
+			}
 		}
 	}
 
diff --git a/app/test-compress-perf/main.c b/app/test-compress-perf/main.c
index ce9e80bedc..832140f814 100644
--- a/app/test-compress-perf/main.c
+++ b/app/test-compress-perf/main.c
@@ -253,6 +253,14 @@ comp_perf_dump_input_data(struct comp_test_data *test_data)
 		goto end;
 	}
 
+	if (!(test_data->test_op & COMPRESS) &&
+	    test_data->input_data_sz >
+	    (size_t) test_data->seg_sz * (size_t) test_data->max_sgl_segs) {
+		RTE_LOG(ERR, USER1,
+			"Size of input must be less than total segments\n");
+		goto end;
+	}
+
 	test_data->input_data = rte_zmalloc_socket(NULL,
 				test_data->input_data_sz, 0, rte_socket_id());
 
-- 
2.39.1

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2023-02-23 09:36:30.718322882 +0000
+++ 0062-app-compress-perf-fix-testing-single-operation.patch	2023-02-23 09:36:28.342172076 +0000
@@ -1 +1 @@
-From 83cc3b90ad7a63868a43a67d6aa13b55068fbe0c Mon Sep 17 00:00:00 2001
+From 3cc7c9875b09be70696cd0f5c00ed8c540bb8c44 Mon Sep 17 00:00:00 2001
@@ -5,0 +6,2 @@
+[ upstream commit 83cc3b90ad7a63868a43a67d6aa13b55068fbe0c ]
+
@@ -13 +14,0 @@
-Cc: stable@dpdk.org
@@ -23 +24 @@
- .../comp_perf_test_verify.c                   |  60 ++++++---
+ .../comp_perf_test_verify.c                   |  58 +++++---
@@ -25 +26 @@
- 7 files changed, 224 insertions(+), 115 deletions(-)
+ 7 files changed, 223 insertions(+), 114 deletions(-)
@@ -28 +29 @@
-index 57dd146330..d00b299247 100644
+index 0b777521c5..cfb00bd1ad 100644
@@ -31 +32 @@
-@@ -32,9 +32,9 @@ enum cperf_test_type {
+@@ -30,9 +30,9 @@ enum cperf_test_type {
@@ -299 +300 @@
-index ce457fefbb..ce6c4d7605 100644
+index ea62fcf52e..8474e59f17 100644
@@ -302 +303 @@
-@@ -514,38 +514,55 @@ cperf_cyclecount_test_runner(void *test_ctx)
+@@ -510,38 +510,55 @@ cperf_cyclecount_test_runner(void *test_ctx)
@@ -385 +386 @@
-index 79cd2b2bf2..c9f8237626 100644
+index 7574e33ac7..5ea56e366a 100644
@@ -388 +389 @@
-@@ -359,41 +359,53 @@ cperf_throughput_test_runner(void *test_ctx)
+@@ -355,41 +355,53 @@ cperf_throughput_test_runner(void *test_ctx)
@@ -467,2 +468,2 @@
- 	exp = 0;
- 	if (__atomic_compare_exchange_n(&display_once, &exp, 1, 0,
+ 	if (rte_atomic16_test_and_set(&display_once)) {
+ 		printf("\n%12s%6s%12s%17s%15s%16s\n",
@@ -470 +471 @@
-index 6b61a9194f..7d6b6abecd 100644
+index 98704a9548..aaf50657c0 100644
@@ -473 +474 @@
-@@ -114,7 +114,8 @@ main_loop(struct cperf_verify_ctx *ctx, enum rte_comp_xform_type type)
+@@ -112,7 +112,8 @@ main_loop(struct cperf_verify_ctx *ctx, enum rte_comp_xform_type type)
@@ -483,7 +484 @@
-@@ -392,44 +393,59 @@ cperf_verify_test_runner(void *test_ctx)
- 	int ret = EXIT_SUCCESS;
- 	static uint16_t display_once;
- 	uint32_t lcore = rte_lcore_id();
-+	uint16_t exp = 0;
- 
- 	ctx->mem.lcore_id = lcore;
+@@ -395,32 +396,47 @@ cperf_verify_test_runner(void *test_ctx)
@@ -557,7 +551,0 @@
- 	ctx->ratio = (double) ctx->comp_data_sz /
- 			test_data->input_data_sz * 100;
- 
--	uint16_t exp = 0;
- 	if (!ctx->silent) {
- 		if (__atomic_compare_exchange_n(&display_once, &exp, 1, 0,
- 				__ATOMIC_RELAXED, __ATOMIC_RELAXED)) {
@@ -565 +553 @@
-index 41b8edc2bd..bbb4c7917b 100644
+index ce9e80bedc..832140f814 100644
@@ -568 +556 @@
-@@ -254,6 +254,14 @@ comp_perf_dump_input_data(struct comp_test_data *test_data)
+@@ -253,6 +253,14 @@ comp_perf_dump_input_data(struct comp_test_data *test_data)