table: improve lookup performance with prefetch offset

This patch modifies rte_prefetch offsets to improve hash/lru
table lookup performance.

Signed-off-by: Fan Zhang <roy.fan.zhang@intel.com>
Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>

diff --git a/lib/librte_table/rte_table_hash_ext.c b/lib/librte_table/rte_table_hash_ext.c
index ebe952b..e283a3d 100644 (file)
--- a/lib/librte_table/rte_table_hash_ext.c
+++ b/lib/librte_table/rte_table_hash_ext.c
@@ -648,6 +648,7 @@ static int rte_table_hash_ext_lookup_unoptimized(
 {                                                                      \
        uint64_t pkt00_mask, pkt01_mask;                                \
        struct rte_mbuf *mbuf00, *mbuf01;                               \
+       uint32_t key_offset = t->key_offset;                    \
                                                                        \
        pkt00_index = __builtin_ctzll(pkts_mask);                       \
        pkt00_mask = 1LLU << pkt00_index;                               \
@@ -659,8 +660,8 @@ static int rte_table_hash_ext_lookup_unoptimized(
        pkts_mask &= ~pkt01_mask;                                       \
        mbuf01 = pkts[pkt01_index];                                     \
                                                                        \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, 0));          \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, 0));          \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, key_offset));\
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, key_offset));\
 }
 
 #define lookup2_stage0_with_odd_support(t, g, pkts, pkts_mask, pkt00_index, \
@@ -668,6 +669,7 @@ static int rte_table_hash_ext_lookup_unoptimized(
 {                                                                      \
        uint64_t pkt00_mask, pkt01_mask;                                \
        struct rte_mbuf *mbuf00, *mbuf01;                               \
+       uint32_t key_offset = t->key_offset;                    \
                                                                        \
        pkt00_index = __builtin_ctzll(pkts_mask);                       \
        pkt00_mask = 1LLU << pkt00_index;                               \
@@ -681,8 +683,8 @@ static int rte_table_hash_ext_lookup_unoptimized(
        pkts_mask &= ~pkt01_mask;                                       \
        mbuf01 = pkts[pkt01_index];                                     \
                                                                        \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, 0));          \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, 0));          \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, key_offset));\
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, key_offset));\
 }
 
 #define lookup2_stage1(t, g, pkts, pkt10_index, pkt11_index)           \

diff --git a/lib/librte_table/rte_table_hash_key16.c b/lib/librte_table/rte_table_hash_key16.c
index a3a5023..b7e000f 100644 (file)
--- a/lib/librte_table/rte_table_hash_key16.c
+++ b/lib/librte_table/rte_table_hash_key16.c
@@ -595,16 +595,17 @@ rte_table_hash_entry_delete_key16_ext(
                pos = 3;                                        \
 }
 
-#define lookup1_stage0(pkt0_index, mbuf0, pkts, pkts_mask)     \
+#define lookup1_stage0(pkt0_index, mbuf0, pkts, pkts_mask, f)  \
 {                                                              \
        uint64_t pkt_mask;                                      \
+       uint32_t key_offset = f->key_offset;\
                                                                \
        pkt0_index = __builtin_ctzll(pkts_mask);                \
        pkt_mask = 1LLU << pkt0_index;                          \
        pkts_mask &= ~pkt_mask;                                 \
                                                                \
        mbuf0 = pkts[pkt0_index];                               \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf0, 0));   \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf0, key_offset));\
 }
 
 #define lookup1_stage1(mbuf1, bucket1, f)                      \
@@ -729,36 +730,38 @@ rte_table_hash_entry_delete_key16_ext(
 }
 
 #define lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01,\
-               pkts, pkts_mask)                                \
+               pkts, pkts_mask, f)                             \
 {                                                              \
        uint64_t pkt00_mask, pkt01_mask;                        \
+       uint32_t key_offset = f->key_offset;            \
                                                                \
        pkt00_index = __builtin_ctzll(pkts_mask);               \
        pkt00_mask = 1LLU << pkt00_index;                       \
        pkts_mask &= ~pkt00_mask;                               \
                                                                \
        mbuf00 = pkts[pkt00_index];                             \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, 0));  \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, key_offset));\
                                                                \
        pkt01_index = __builtin_ctzll(pkts_mask);               \
        pkt01_mask = 1LLU << pkt01_index;                       \
        pkts_mask &= ~pkt01_mask;                               \
                                                                \
        mbuf01 = pkts[pkt01_index];                             \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, 0));  \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, key_offset));\
 }
 
 #define lookup2_stage0_with_odd_support(pkt00_index, pkt01_index,\
-               mbuf00, mbuf01, pkts, pkts_mask)                \
+               mbuf00, mbuf01, pkts, pkts_mask, f)             \
 {                                                              \
        uint64_t pkt00_mask, pkt01_mask;                        \
+       uint32_t key_offset = f->key_offset;            \
                                                                \
        pkt00_index = __builtin_ctzll(pkts_mask);               \
        pkt00_mask = 1LLU << pkt00_index;                       \
        pkts_mask &= ~pkt00_mask;                               \
                                                                \
        mbuf00 = pkts[pkt00_index];                             \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, 0));  \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, key_offset)); \
                                                                \
        pkt01_index = __builtin_ctzll(pkts_mask);               \
        if (pkts_mask == 0)                                     \
@@ -767,7 +770,7 @@ rte_table_hash_entry_delete_key16_ext(
        pkts_mask &= ~pkt01_mask;                               \
                                                                \
        mbuf01 = pkts[pkt01_index];                             \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, 0));  \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, key_offset)); \
 }
 
 #define lookup2_stage1(mbuf10, mbuf11, bucket10, bucket11, f)  \
@@ -922,7 +925,7 @@ rte_table_hash_lookup_key16_lru(
                        struct rte_mbuf *mbuf;
                        uint32_t pkt_index;
 
-                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask);
+                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask, f);
                        lookup1_stage1(mbuf, bucket, f);
                        lookup1_stage2_lru(pkt_index, mbuf, bucket,
                                pkts_mask_out, entries, f);
@@ -940,7 +943,7 @@ rte_table_hash_lookup_key16_lru(
         */
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline feed */
        mbuf10 = mbuf00;
@@ -950,7 +953,7 @@ rte_table_hash_lookup_key16_lru(
 
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline stage 1 */
        lookup2_stage1(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -974,7 +977,7 @@ rte_table_hash_lookup_key16_lru(
 
                /* Pipeline stage 0 */
                lookup2_stage0_with_odd_support(pkt00_index, pkt01_index,
-                       mbuf00, mbuf01, pkts, pkts_mask);
+                       mbuf00, mbuf01, pkts, pkts_mask, f);
 
                /* Pipeline stage 1 */
                lookup2_stage1(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -1051,7 +1054,7 @@ rte_table_hash_lookup_key16_lru_dosig(
                        struct rte_mbuf *mbuf;
                        uint32_t pkt_index;
 
-                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask);
+                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask, f);
                        lookup1_stage1_dosig(mbuf, bucket, f);
                        lookup1_stage2_lru(pkt_index, mbuf, bucket,
                                pkts_mask_out, entries, f);
@@ -1069,7 +1072,7 @@ rte_table_hash_lookup_key16_lru_dosig(
         */
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline feed */
        mbuf10 = mbuf00;
@@ -1079,7 +1082,7 @@ rte_table_hash_lookup_key16_lru_dosig(
 
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline stage 1 */
        lookup2_stage1_dosig(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -1103,7 +1106,7 @@ rte_table_hash_lookup_key16_lru_dosig(
 
                /* Pipeline stage 0 */
                lookup2_stage0_with_odd_support(pkt00_index, pkt01_index,
-                       mbuf00, mbuf01, pkts, pkts_mask);
+                       mbuf00, mbuf01, pkts, pkts_mask, f);
 
                /* Pipeline stage 1 */
                lookup2_stage1_dosig(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -1181,7 +1184,7 @@ rte_table_hash_lookup_key16_ext(
                        struct rte_mbuf *mbuf;
                        uint32_t pkt_index;
 
-                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask);
+                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask, f);
                        lookup1_stage1(mbuf, bucket, f);
                        lookup1_stage2_ext(pkt_index, mbuf, bucket,
                                pkts_mask_out, entries, buckets_mask,
@@ -1197,7 +1200,7 @@ rte_table_hash_lookup_key16_ext(
         */
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline feed */
        mbuf10 = mbuf00;
@@ -1207,7 +1210,7 @@ rte_table_hash_lookup_key16_ext(
 
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline stage 1 */
        lookup2_stage1(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -1231,7 +1234,7 @@ rte_table_hash_lookup_key16_ext(
 
                /* Pipeline stage 0 */
                lookup2_stage0_with_odd_support(pkt00_index, pkt01_index,
-                       mbuf00, mbuf01, pkts, pkts_mask);
+                       mbuf00, mbuf01, pkts, pkts_mask, f);
 
                /* Pipeline stage 1 */
                lookup2_stage1(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -1333,7 +1336,7 @@ rte_table_hash_lookup_key16_ext_dosig(
                        struct rte_mbuf *mbuf;
                        uint32_t pkt_index;
 
-                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask);
+                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask, f);
                        lookup1_stage1_dosig(mbuf, bucket, f);
                        lookup1_stage2_ext(pkt_index, mbuf, bucket,
                                pkts_mask_out, entries, buckets_mask,
@@ -1349,7 +1352,7 @@ rte_table_hash_lookup_key16_ext_dosig(
         */
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline feed */
        mbuf10 = mbuf00;
@@ -1359,7 +1362,7 @@ rte_table_hash_lookup_key16_ext_dosig(
 
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline stage 1 */
        lookup2_stage1_dosig(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -1383,7 +1386,7 @@ rte_table_hash_lookup_key16_ext_dosig(
 
                /* Pipeline stage 0 */
                lookup2_stage0_with_odd_support(pkt00_index, pkt01_index,
-                       mbuf00, mbuf01, pkts, pkts_mask);
+                       mbuf00, mbuf01, pkts, pkts_mask, f);
 
                /* Pipeline stage 1 */
                lookup2_stage1_dosig(mbuf10, mbuf11, bucket10, bucket11, f);

diff --git a/lib/librte_table/rte_table_hash_key32.c b/lib/librte_table/rte_table_hash_key32.c
index b3ae73e..a7aba49 100644 (file)
--- a/lib/librte_table/rte_table_hash_key32.c
+++ b/lib/librte_table/rte_table_hash_key32.c
@@ -591,16 +591,17 @@ rte_table_hash_entry_delete_key32_ext(
                pos = 3;                                        \
 }
 
-#define lookup1_stage0(pkt0_index, mbuf0, pkts, pkts_mask)     \
+#define lookup1_stage0(pkt0_index, mbuf0, pkts, pkts_mask, f)  \
 {                                                              \
        uint64_t pkt_mask;                                      \
+       uint32_t key_offset = f->key_offset;    \
                                                                \
        pkt0_index = __builtin_ctzll(pkts_mask);                \
        pkt_mask = 1LLU << pkt0_index;                          \
        pkts_mask &= ~pkt_mask;                                 \
                                                                \
        mbuf0 = pkts[pkt0_index];                               \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf0, 0));   \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf0, key_offset));\
 }
 
 #define lookup1_stage1(mbuf1, bucket1, f)                      \
@@ -698,36 +699,38 @@ rte_table_hash_entry_delete_key32_ext(
 }
 
 #define lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01,\
-       pkts, pkts_mask)                                        \
+       pkts, pkts_mask, f)                                     \
 {                                                              \
        uint64_t pkt00_mask, pkt01_mask;                        \
+       uint32_t key_offset = f->key_offset;            \
                                                                \
        pkt00_index = __builtin_ctzll(pkts_mask);               \
        pkt00_mask = 1LLU << pkt00_index;                       \
        pkts_mask &= ~pkt00_mask;                               \
                                                                \
        mbuf00 = pkts[pkt00_index];                             \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, 0));  \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, key_offset));\
                                                                \
        pkt01_index = __builtin_ctzll(pkts_mask);               \
        pkt01_mask = 1LLU << pkt01_index;                       \
        pkts_mask &= ~pkt01_mask;                               \
                                                                \
        mbuf01 = pkts[pkt01_index];                             \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, 0));  \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, key_offset));\
 }
 
 #define lookup2_stage0_with_odd_support(pkt00_index, pkt01_index,\
-       mbuf00, mbuf01, pkts, pkts_mask)                        \
+       mbuf00, mbuf01, pkts, pkts_mask, f)                     \
 {                                                              \
        uint64_t pkt00_mask, pkt01_mask;                        \
+       uint32_t key_offset = f->key_offset;            \
                                                                \
        pkt00_index = __builtin_ctzll(pkts_mask);               \
        pkt00_mask = 1LLU << pkt00_index;                       \
        pkts_mask &= ~pkt00_mask;                               \
                                                                \
        mbuf00 = pkts[pkt00_index];                             \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, 0));  \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, key_offset)); \
                                                                \
        pkt01_index = __builtin_ctzll(pkts_mask);               \
        if (pkts_mask == 0)                                     \
@@ -737,7 +740,7 @@ rte_table_hash_entry_delete_key32_ext(
        pkts_mask &= ~pkt01_mask;                               \
                                                                \
        mbuf01 = pkts[pkt01_index];                             \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, 0));  \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, key_offset)); \
 }
 
 #define lookup2_stage1(mbuf10, mbuf11, bucket10, bucket11, f)  \
@@ -852,7 +855,7 @@ rte_table_hash_lookup_key32_lru(
                        struct rte_mbuf *mbuf;
                        uint32_t pkt_index;
 
-                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask);
+                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask, f);
                        lookup1_stage1(mbuf, bucket, f);
                        lookup1_stage2_lru(pkt_index, mbuf, bucket,
                                        pkts_mask_out, entries, f);
@@ -869,7 +872,7 @@ rte_table_hash_lookup_key32_lru(
         */
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline feed */
        mbuf10 = mbuf00;
@@ -879,7 +882,7 @@ rte_table_hash_lookup_key32_lru(
 
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline stage 1 */
        lookup2_stage1(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -903,7 +906,7 @@ rte_table_hash_lookup_key32_lru(
 
                /* Pipeline stage 0 */
                lookup2_stage0_with_odd_support(pkt00_index, pkt01_index,
-                       mbuf00, mbuf01, pkts, pkts_mask);
+                       mbuf00, mbuf01, pkts, pkts_mask, f);
 
                /* Pipeline stage 1 */
                lookup2_stage1(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -981,7 +984,7 @@ rte_table_hash_lookup_key32_ext(
                        struct rte_mbuf *mbuf;
                        uint32_t pkt_index;
 
-                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask);
+                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask, f);
                        lookup1_stage1(mbuf, bucket, f);
                        lookup1_stage2_ext(pkt_index, mbuf, bucket,
                                pkts_mask_out, entries, buckets_mask, buckets,
@@ -997,7 +1000,7 @@ rte_table_hash_lookup_key32_ext(
         */
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline feed */
        mbuf10 = mbuf00;
@@ -1007,7 +1010,7 @@ rte_table_hash_lookup_key32_ext(
 
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline stage 1 */
        lookup2_stage1(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -1031,7 +1034,7 @@ rte_table_hash_lookup_key32_ext(
 
                /* Pipeline stage 0 */
                lookup2_stage0_with_odd_support(pkt00_index, pkt01_index,
-                       mbuf00, mbuf01, pkts, pkts_mask);
+                       mbuf00, mbuf01, pkts, pkts_mask, f);
 
                /* Pipeline stage 1 */
                lookup2_stage1(mbuf10, mbuf11, bucket10, bucket11, f);

diff --git a/lib/librte_table/rte_table_hash_key8.c b/lib/librte_table/rte_table_hash_key8.c
index 5f05903..e2e2bdc 100644 (file)
--- a/lib/librte_table/rte_table_hash_key8.c
+++ b/lib/librte_table/rte_table_hash_key8.c
@@ -568,16 +568,17 @@ rte_table_hash_entry_delete_key8_ext(
                pos = 3;                                        \
 }
 
-#define lookup1_stage0(pkt0_index, mbuf0, pkts, pkts_mask)     \
+#define lookup1_stage0(pkt0_index, mbuf0, pkts, pkts_mask, f)  \
 {                                                              \
        uint64_t pkt_mask;                                      \
+       uint32_t key_offset = f->key_offset;\
                                                                \
        pkt0_index = __builtin_ctzll(pkts_mask);                \
        pkt_mask = 1LLU << pkt0_index;                          \
        pkts_mask &= ~pkt_mask;                                 \
                                                                \
        mbuf0 = pkts[pkt0_index];                               \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf0, 0));   \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf0, key_offset));  \
 }
 
 #define lookup1_stage1(mbuf1, bucket1, f)                      \
@@ -693,36 +694,38 @@ rte_table_hash_entry_delete_key8_ext(
 }
 
 #define lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01,\
-       pkts, pkts_mask)                                        \
+       pkts, pkts_mask, f)                                     \
 {                                                              \
        uint64_t pkt00_mask, pkt01_mask;                        \
+       uint32_t key_offset = f->key_offset;            \
                                                                \
        pkt00_index = __builtin_ctzll(pkts_mask);               \
        pkt00_mask = 1LLU << pkt00_index;                       \
        pkts_mask &= ~pkt00_mask;                               \
                                                                \
        mbuf00 = pkts[pkt00_index];                             \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, 0));  \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, key_offset));\
                                                                \
        pkt01_index = __builtin_ctzll(pkts_mask);               \
        pkt01_mask = 1LLU << pkt01_index;                       \
        pkts_mask &= ~pkt01_mask;                               \
                                                                \
        mbuf01 = pkts[pkt01_index];                             \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, 0));  \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, key_offset));\
 }
 
 #define lookup2_stage0_with_odd_support(pkt00_index, pkt01_index,\
-       mbuf00, mbuf01, pkts, pkts_mask)                        \
+       mbuf00, mbuf01, pkts, pkts_mask, f)                     \
 {                                                              \
        uint64_t pkt00_mask, pkt01_mask;                        \
+       uint32_t key_offset = f->key_offset;            \
                                                                \
        pkt00_index = __builtin_ctzll(pkts_mask);               \
        pkt00_mask = 1LLU << pkt00_index;                       \
        pkts_mask &= ~pkt00_mask;                               \
                                                                \
        mbuf00 = pkts[pkt00_index];                             \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, 0));  \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, key_offset));\
                                                                \
        pkt01_index = __builtin_ctzll(pkts_mask);               \
        if (pkts_mask == 0)                                     \
@@ -732,7 +735,7 @@ rte_table_hash_entry_delete_key8_ext(
        pkts_mask &= ~pkt01_mask;                               \
                                                                \
        mbuf01 = pkts[pkt01_index];                             \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, 0));  \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, key_offset));\
 }
 
 #define lookup2_stage1(mbuf10, mbuf11, bucket10, bucket11, f)  \
@@ -882,7 +885,7 @@ rte_table_hash_lookup_key8_lru(
                        struct rte_mbuf *mbuf;
                        uint32_t pkt_index;
 
-                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask);
+                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask, f);
                        lookup1_stage1(mbuf, bucket, f);
                        lookup1_stage2_lru(pkt_index, mbuf, bucket,
                                        pkts_mask_out, entries, f);
@@ -899,7 +902,7 @@ rte_table_hash_lookup_key8_lru(
         */
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline feed */
        mbuf10 = mbuf00;
@@ -909,7 +912,7 @@ rte_table_hash_lookup_key8_lru(
 
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline stage 1 */
        lookup2_stage1(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -933,7 +936,7 @@ rte_table_hash_lookup_key8_lru(
 
                /* Pipeline stage 0 */
                lookup2_stage0_with_odd_support(pkt00_index, pkt01_index,
-                       mbuf00, mbuf01, pkts, pkts_mask);
+                       mbuf00, mbuf01, pkts, pkts_mask, f);
 
                /* Pipeline stage 1 */
                lookup2_stage1(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -1008,7 +1011,7 @@ rte_table_hash_lookup_key8_lru_dosig(
                        struct rte_mbuf *mbuf;
                        uint32_t pkt_index;
 
-                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask);
+                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask, f);
                        lookup1_stage1_dosig(mbuf, bucket, f);
                        lookup1_stage2_lru(pkt_index, mbuf, bucket,
                                pkts_mask_out, entries, f);
@@ -1025,7 +1028,7 @@ rte_table_hash_lookup_key8_lru_dosig(
         */
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline feed */
        mbuf10 = mbuf00;
@@ -1035,7 +1038,7 @@ rte_table_hash_lookup_key8_lru_dosig(
 
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline stage 1 */
        lookup2_stage1_dosig(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -1059,7 +1062,7 @@ rte_table_hash_lookup_key8_lru_dosig(
 
                /* Pipeline stage 0 */
                lookup2_stage0_with_odd_support(pkt00_index, pkt01_index,
-                       mbuf00, mbuf01, pkts, pkts_mask);
+                       mbuf00, mbuf01, pkts, pkts_mask, f);
 
                /* Pipeline stage 1 */
                lookup2_stage1_dosig(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -1136,7 +1139,7 @@ rte_table_hash_lookup_key8_ext(
                        struct rte_mbuf *mbuf;
                        uint32_t pkt_index;
 
-                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask);
+                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask, f);
                        lookup1_stage1(mbuf, bucket, f);
                        lookup1_stage2_ext(pkt_index, mbuf, bucket,
                                pkts_mask_out, entries, buckets_mask, buckets,
@@ -1152,7 +1155,7 @@ rte_table_hash_lookup_key8_ext(
         */
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline feed */
        mbuf10 = mbuf00;
@@ -1162,7 +1165,7 @@ rte_table_hash_lookup_key8_ext(
 
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline stage 1 */
        lookup2_stage1(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -1186,7 +1189,7 @@ rte_table_hash_lookup_key8_ext(
 
                /* Pipeline stage 0 */
                lookup2_stage0_with_odd_support(pkt00_index, pkt01_index,
-                       mbuf00, mbuf01, pkts, pkts_mask);
+                       mbuf00, mbuf01, pkts, pkts_mask, f);
 
                /* Pipeline stage 1 */
                lookup2_stage1(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -1286,7 +1289,7 @@ rte_table_hash_lookup_key8_ext_dosig(
                        struct rte_mbuf *mbuf;
                        uint32_t pkt_index;
 
-                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask);
+                       lookup1_stage0(pkt_index, mbuf, pkts, pkts_mask, f);
                        lookup1_stage1_dosig(mbuf, bucket, f);
                        lookup1_stage2_ext(pkt_index, mbuf, bucket,
                                pkts_mask_out, entries, buckets_mask,
@@ -1302,7 +1305,7 @@ rte_table_hash_lookup_key8_ext_dosig(
         */
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline feed */
        mbuf10 = mbuf00;
@@ -1312,7 +1315,7 @@ rte_table_hash_lookup_key8_ext_dosig(
 
        /* Pipeline stage 0 */
        lookup2_stage0(pkt00_index, pkt01_index, mbuf00, mbuf01, pkts,
-               pkts_mask);
+               pkts_mask, f);
 
        /* Pipeline stage 1 */
        lookup2_stage1_dosig(mbuf10, mbuf11, bucket10, bucket11, f);
@@ -1336,7 +1339,7 @@ rte_table_hash_lookup_key8_ext_dosig(
 
                /* Pipeline stage 0 */
                lookup2_stage0_with_odd_support(pkt00_index, pkt01_index,
-                       mbuf00, mbuf01, pkts, pkts_mask);
+                       mbuf00, mbuf01, pkts, pkts_mask, f);
 
                /* Pipeline stage 1 */
                lookup2_stage1_dosig(mbuf10, mbuf11, bucket10, bucket11, f);

diff --git a/lib/librte_table/rte_table_hash_lru.c b/lib/librte_table/rte_table_hash_lru.c
index 14e9072..407c62a 100644 (file)
--- a/lib/librte_table/rte_table_hash_lru.c
+++ b/lib/librte_table/rte_table_hash_lru.c
@@ -576,6 +576,7 @@ static int rte_table_hash_lru_lookup_unoptimized(
 {                                                              \
        uint64_t pkt00_mask, pkt01_mask;                        \
        struct rte_mbuf *mbuf00, *mbuf01;                       \
+       uint32_t key_offset = t->key_offset;            \
                                                                \
        pkt00_index = __builtin_ctzll(pkts_mask);               \
        pkt00_mask = 1LLU << pkt00_index;                       \
@@ -587,8 +588,8 @@ static int rte_table_hash_lru_lookup_unoptimized(
        pkts_mask &= ~pkt01_mask;                               \
        mbuf01 = pkts[pkt01_index];                             \
                                                                \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, 0));  \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, 0));  \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, key_offset));\
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, key_offset));\
 }
 
 #define lookup2_stage0_with_odd_support(t, g, pkts, pkts_mask, pkt00_index, \
@@ -596,6 +597,7 @@ static int rte_table_hash_lru_lookup_unoptimized(
 {                                                              \
        uint64_t pkt00_mask, pkt01_mask;                        \
        struct rte_mbuf *mbuf00, *mbuf01;                       \
+       uint32_t key_offset = t->key_offset;            \
                                                                \
        pkt00_index = __builtin_ctzll(pkts_mask);               \
        pkt00_mask = 1LLU << pkt00_index;                       \
@@ -610,8 +612,8 @@ static int rte_table_hash_lru_lookup_unoptimized(
        pkts_mask &= ~pkt01_mask;                               \
        mbuf01 = pkts[pkt01_index];                             \
                                                                \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, 0));  \
-       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, 0));  \
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf00, key_offset));\
+       rte_prefetch0(RTE_MBUF_METADATA_UINT8_PTR(mbuf01, key_offset));\
 }
 
 #define lookup2_stage1(t, g, pkts, pkt10_index, pkt11_index)   \