[dpdk-dev] [PATCH v2 10/12] acl: for AVX512 classify use 4B load whenever possible

[Konstantin Ananyev <konstantin.ananyev@intel.com>]

With current ACL implementation first field in the rule definition
has always to be one byte long. Though for optimising classify
implementation it might be useful to be able to use 4B reads
(as we do for rest of the fields).
So at build phase, check user provided field definitions to determine
is it safe to do 4B loads for first ACL field.
Then at run-time this information can be used to choose classify
behavior.

Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
---
 lib/librte_acl/acl.h               |  1 +
 lib/librte_acl/acl_bld.c           | 34 ++++++++++++++++++++++++++++++
 lib/librte_acl/acl_run_avx512.c    |  7 ++++++
 lib/librte_acl/acl_run_avx512x16.h |  8 +++----
 lib/librte_acl/acl_run_avx512x8.h  |  8 +++----
 lib/librte_acl/rte_acl.c           |  1 +
 6 files changed, 51 insertions(+), 8 deletions(-)

diff --git a/lib/librte_acl/acl.h b/lib/librte_acl/acl.h
index 3f0719f33..493dec2a2 100644
--- a/lib/librte_acl/acl.h
+++ b/lib/librte_acl/acl.h
@@ -169,6 +169,7 @@ struct rte_acl_ctx {
 	int32_t             socket_id;
 	/** Socket ID to allocate memory from. */
 	enum rte_acl_classify_alg alg;
+	uint32_t           first_load_sz;
 	void               *rules;
 	uint32_t            max_rules;
 	uint32_t            rule_sz;
diff --git a/lib/librte_acl/acl_bld.c b/lib/librte_acl/acl_bld.c
index d1f920b09..da10864cd 100644
--- a/lib/librte_acl/acl_bld.c
+++ b/lib/librte_acl/acl_bld.c
@@ -1581,6 +1581,37 @@ acl_check_bld_param(struct rte_acl_ctx *ctx, const struct rte_acl_config *cfg)
 	return 0;
 }
 
+/*
+ * With current ACL implementation first field in the rule definition
+ * has always to be one byte long. Though for optimising *classify*
+ * implementation it might be useful to be able to use 4B reads
+ * (as we do for rest of the fields).
+ * This function checks input config to determine is it safe to do 4B
+ * loads for first ACL field. For that we need to make sure that
+ * first field in our rule definition doesn't have the biggest offset,
+ * i.e. we still do have other fields located after the first one.
+ * Contrary if first field has the largest offset, then it means
+ * first field can occupy the very last byte in the input data buffer,
+ * and we have to do single byte load for it.
+ */
+static uint32_t
+get_first_load_size(const struct rte_acl_config *cfg)
+{
+	uint32_t i, max_ofs, ofs;
+
+	ofs = 0;
+	max_ofs = 0;
+
+	for (i = 0; i != cfg->num_fields; i++) {
+		if (cfg->defs[i].field_index == 0)
+			ofs = cfg->defs[i].offset;
+		else if (max_ofs < cfg->defs[i].offset)
+			max_ofs = cfg->defs[i].offset;
+	}
+
+	return (ofs < max_ofs) ? sizeof(uint32_t) : sizeof(uint8_t);
+}
+
 int
 rte_acl_build(struct rte_acl_ctx *ctx, const struct rte_acl_config *cfg)
 {
@@ -1618,6 +1649,9 @@ rte_acl_build(struct rte_acl_ctx *ctx, const struct rte_acl_config *cfg)
 				/* set data indexes. */
 				acl_set_data_indexes(ctx);
 
+				/* determine can we always do 4B load */
+				ctx->first_load_sz = get_first_load_size(cfg);
+
 				/* copy in build config. */
 				ctx->config = *cfg;
 			}
diff --git a/lib/librte_acl/acl_run_avx512.c b/lib/librte_acl/acl_run_avx512.c
index 60762b7d6..51bfa6a3b 100644
--- a/lib/librte_acl/acl_run_avx512.c
+++ b/lib/librte_acl/acl_run_avx512.c
@@ -16,6 +16,7 @@ struct acl_flow_avx512 {
 	uint32_t num_packets;       /* number of packets processed */
 	uint32_t total_packets;     /* max number of packets to process */
 	uint32_t root_index;        /* current root index */
+	uint32_t first_load_sz;     /* first load size for new packet */
 	const uint64_t *trans;      /* transition table */
 	const uint32_t *data_index; /* input data indexes */
 	const uint8_t **idata;      /* input data */
@@ -29,6 +30,7 @@ acl_set_flow_avx512(struct acl_flow_avx512 *flow, const struct rte_acl_ctx *ctx,
 {
 	flow->num_packets = 0;
 	flow->total_packets = total_packets;
+	flow->first_load_sz = ctx->first_load_sz;
 	flow->root_index = ctx->trie[trie].root_index;
 	flow->trans = ctx->trans_table;
 	flow->data_index = ctx->trie[trie].data_index;
@@ -155,6 +157,11 @@ resolve_mcgt8_avx512x1(uint32_t result[],
 	}
 }
 
+/*
+ * unfortunately current AVX512 ISA doesn't provide ability for
+ * gather load on a byte quantity. So we have to mimic it in SW,
+ * by doing 8x1B scalar loads.
+ */
 static inline ymm_t
 _m512_mask_gather_epi8x8(__m512i pdata, __mmask8 mask)
 {
diff --git a/lib/librte_acl/acl_run_avx512x16.h b/lib/librte_acl/acl_run_avx512x16.h
index 45b0b4db6..df5f6135f 100644
--- a/lib/librte_acl/acl_run_avx512x16.h
+++ b/lib/librte_acl/acl_run_avx512x16.h
@@ -413,7 +413,7 @@ match_check_process_avx512x16x2(struct acl_flow_avx512 *flow, uint32_t fm[2],
 
 		if (n[0] != 0) {
 			inp[0] = get_next_bytes_avx512x16(flow, &pdata[0],
-				rm[0], &di[0], sizeof(uint8_t));
+				rm[0], &di[0], flow->first_load_sz);
 			first_trans16(flow, inp[0], rm[0], &tr_lo[0],
 				&tr_hi[0]);
 			rm[0] = _mm512_test_epi32_mask(tr_lo[0],
@@ -422,7 +422,7 @@ match_check_process_avx512x16x2(struct acl_flow_avx512 *flow, uint32_t fm[2],
 
 		if (n[1] != 0) {
 			inp[1] = get_next_bytes_avx512x16(flow, &pdata[2],
-				rm[1], &di[1], sizeof(uint8_t));
+				rm[1], &di[1], flow->first_load_sz);
 			first_trans16(flow, inp[1], rm[1], &tr_lo[1],
 				&tr_hi[1]);
 			rm[1] = _mm512_test_epi32_mask(tr_lo[1],
@@ -447,9 +447,9 @@ search_trie_avx512x16x2(struct acl_flow_avx512 *flow)
 	start_flow16(flow, MASK16_BIT, UINT16_MAX, &pdata[2], &idx[1], &di[1]);
 
 	in[0] = get_next_bytes_avx512x16(flow, &pdata[0], UINT16_MAX, &di[0],
-		sizeof(uint8_t));
+			flow->first_load_sz);
 	in[1] = get_next_bytes_avx512x16(flow, &pdata[2], UINT16_MAX, &di[1],
-		sizeof(uint8_t));
+			flow->first_load_sz);
 
 	first_trans16(flow, in[0], UINT16_MAX, &tr_lo[0], &tr_hi[0]);
 	first_trans16(flow, in[1], UINT16_MAX, &tr_lo[1], &tr_hi[1]);
diff --git a/lib/librte_acl/acl_run_avx512x8.h b/lib/librte_acl/acl_run_avx512x8.h
index 82171e8e0..777451973 100644
--- a/lib/librte_acl/acl_run_avx512x8.h
+++ b/lib/librte_acl/acl_run_avx512x8.h
@@ -325,7 +325,7 @@ match_check_process_avx512x8x2(struct acl_flow_avx512 *flow, uint32_t fm[2],
 
 		if (n[0] != 0) {
 			inp[0] = get_next_bytes_avx512x8(flow, pdata[0], rm[0],
-				&di[0], sizeof(uint8_t));
+				&di[0], flow->first_load_sz);
 			first_trans8(flow, inp[0], rm[0], &tr_lo[0], &tr_hi[0]);
 
 			rm[0] = _mm256_test_epi32_mask(tr_lo[0],
@@ -334,7 +334,7 @@ match_check_process_avx512x8x2(struct acl_flow_avx512 *flow, uint32_t fm[2],
 
 		if (n[1] != 0) {
 			inp[1] = get_next_bytes_avx512x8(flow, pdata[1], rm[1],
-				&di[1], sizeof(uint8_t));
+				&di[1], flow->first_load_sz);
 			first_trans8(flow, inp[1], rm[1], &tr_lo[1], &tr_hi[1]);
 
 			rm[1] = _mm256_test_epi32_mask(tr_lo[1],
@@ -360,9 +360,9 @@ search_trie_avx512x8x2(struct acl_flow_avx512 *flow)
 	start_flow8(flow, CHAR_BIT, UINT8_MAX, &pdata[1], &idx[1], &di[1]);
 
 	inp[0] = get_next_bytes_avx512x8(flow, pdata[0], UINT8_MAX, &di[0],
-		sizeof(uint8_t));
+			flow->first_load_sz);
 	inp[1] = get_next_bytes_avx512x8(flow, pdata[1], UINT8_MAX, &di[1],
-		sizeof(uint8_t));
+			flow->first_load_sz);
 
 	first_trans8(flow, inp[0], UINT8_MAX, &tr_lo[0], &tr_hi[0]);
 	first_trans8(flow, inp[1], UINT8_MAX, &tr_lo[1], &tr_hi[1]);
diff --git a/lib/librte_acl/rte_acl.c b/lib/librte_acl/rte_acl.c
index fdcb7a798..9f16d28ea 100644
--- a/lib/librte_acl/rte_acl.c
+++ b/lib/librte_acl/rte_acl.c
@@ -486,6 +486,7 @@ rte_acl_dump(const struct rte_acl_ctx *ctx)
 	printf("acl context <%s>@%p\n", ctx->name, ctx);
 	printf("  socket_id=%"PRId32"\n", ctx->socket_id);
 	printf("  alg=%"PRId32"\n", ctx->alg);
+	printf("  first_load_sz=%"PRIu32"\n", ctx->first_load_sz);
 	printf("  max_rules=%"PRIu32"\n", ctx->max_rules);
 	printf("  rule_size=%"PRIu32"\n", ctx->rule_sz);
 	printf("  num_rules=%"PRIu32"\n", ctx->num_rules);
-- 
2.17.1