hash: remove checks for SSE

[dpdk.git] / lib / librte_hash / rte_hash_crc.h

diff --git a/lib/librte_hash/rte_hash_crc.h b/lib/librte_hash/rte_hash_crc.h
index 78a34b7..ea6be52 100644 (file)
--- a/lib/librte_hash/rte_hash_crc.h
+++ b/lib/librte_hash/rte_hash_crc.h
@@ -327,6 +327,28 @@ static const uint32_t crc32c_tables[8][256] = {{
        (crc32c_tables[(n)][(crc) & 0xFF] ^ \
         crc32c_tables[(n)-1][((crc) >> 8) & 0xFF])
 
+static inline uint32_t
+crc32c_1byte(uint8_t data, uint32_t init_val)
+{
+       uint32_t crc;
+       crc = init_val;
+       crc ^= data;
+
+       return crc32c_tables[0][crc & 0xff] ^ (crc >> 8);
+}
+
+static inline uint32_t
+crc32c_2bytes(uint16_t data, uint32_t init_val)
+{
+       uint32_t crc;
+       crc = init_val;
+       crc ^= data;
+
+       crc = CRC32_UPD(crc, 1) ^ (crc >> 16);
+
+       return crc;
+}
+
 static inline uint32_t
 crc32c_1word(uint32_t data, uint32_t init_val)
 {
@@ -365,7 +387,27 @@ crc32c_2words(uint64_t data, uint32_t init_val)
        return crc;
 }
 
-#if defined(RTE_ARCH_I686) || defined(RTE_ARCH_X86_64)
+#if defined(RTE_ARCH_X86)
+static inline uint32_t
+crc32c_sse42_u8(uint8_t data, uint32_t init_val)
+{
+       __asm__ volatile(
+                       "crc32b %[data], %[init_val];"
+                       : [init_val] "+r" (init_val)
+                       : [data] "rm" (data));
+       return init_val;
+}
+
+static inline uint32_t
+crc32c_sse42_u16(uint16_t data, uint32_t init_val)
+{
+       __asm__ volatile(
+                       "crc32w %[data], %[init_val];"
+                       : [init_val] "+r" (init_val)
+                       : [data] "rm" (data));
+       return init_val;
+}
+
 static inline uint32_t
 crc32c_sse42_u32(uint32_t data, uint32_t init_val)
 {
@@ -411,7 +453,7 @@ crc32c_sse42_u64(uint64_t data, uint64_t init_val)
 
 static uint8_t crc32_alg = CRC32_SW;
 
-#if defined(RTE_ARCH_ARM64)
+#if defined(RTE_ARCH_ARM64) && defined(RTE_MACHINE_CPUFLAG_CRC32)
 #include "rte_crc_arm64.h"
 #else
 
@@ -429,20 +471,12 @@ static uint8_t crc32_alg = CRC32_SW;
 static inline void
 rte_hash_crc_set_alg(uint8_t alg)
 {
-       switch (alg) {
-#if defined(RTE_ARCH_I686) || defined(RTE_ARCH_X86_64)
-       case CRC32_SSE42_x64:
-               if (! rte_cpu_get_flag_enabled(RTE_CPUFLAG_EM64T))
-                       alg = CRC32_SSE42;
-       case CRC32_SSE42:
-               if (! rte_cpu_get_flag_enabled(RTE_CPUFLAG_SSE4_2))
-                       alg = CRC32_SW;
+#if defined(RTE_ARCH_X86)
+       if (alg == CRC32_SSE42_x64 &&
+                       !rte_cpu_get_flag_enabled(RTE_CPUFLAG_EM64T))
+               alg = CRC32_SSE42;
 #endif
-       case CRC32_SW:
-               crc32_alg = alg;
-       default:
-               break;
-       }
+       crc32_alg = alg;
 }
 
 /* Setting the best available algorithm */
@@ -452,6 +486,52 @@ rte_hash_crc_init_alg(void)
        rte_hash_crc_set_alg(CRC32_SSE42_x64);
 }
 
+/**
+ * Use single crc32 instruction to perform a hash on a byte value.
+ * Fall back to software crc32 implementation in case SSE4.2 is
+ * not supported
+ *
+ * @param data
+ *   Data to perform hash on.
+ * @param init_val
+ *   Value to initialise hash generator.
+ * @return
+ *   32bit calculated hash value.
+ */
+static inline uint32_t
+rte_hash_crc_1byte(uint8_t data, uint32_t init_val)
+{
+#if defined RTE_ARCH_X86
+       if (likely(crc32_alg & CRC32_SSE42))
+               return crc32c_sse42_u8(data, init_val);
+#endif
+
+       return crc32c_1byte(data, init_val);
+}
+
+/**
+ * Use single crc32 instruction to perform a hash on a 2 bytes value.
+ * Fall back to software crc32 implementation in case SSE4.2 is
+ * not supported
+ *
+ * @param data
+ *   Data to perform hash on.
+ * @param init_val
+ *   Value to initialise hash generator.
+ * @return
+ *   32bit calculated hash value.
+ */
+static inline uint32_t
+rte_hash_crc_2byte(uint16_t data, uint32_t init_val)
+{
+#if defined RTE_ARCH_X86
+       if (likely(crc32_alg & CRC32_SSE42))
+               return crc32c_sse42_u16(data, init_val);
+#endif
+
+       return crc32c_2bytes(data, init_val);
+}
+
 /**
  * Use single crc32 instruction to perform a hash on a 4 byte value.
  * Fall back to software crc32 implementation in case SSE4.2 is
@@ -467,7 +547,7 @@ rte_hash_crc_init_alg(void)
 static inline uint32_t
 rte_hash_crc_4byte(uint32_t data, uint32_t init_val)
 {
-#if defined RTE_ARCH_I686 || defined RTE_ARCH_X86_64
+#if defined RTE_ARCH_X86
        if (likely(crc32_alg & CRC32_SSE42))
                return crc32c_sse42_u32(data, init_val);
 #endif
@@ -495,7 +575,7 @@ rte_hash_crc_8byte(uint64_t data, uint32_t init_val)
                return crc32c_sse42_u64(data, init_val);
 #endif
 
-#if defined RTE_ARCH_I686 || defined RTE_ARCH_X86_64
+#if defined RTE_ARCH_X86
        if (likely(crc32_alg & CRC32_SSE42))
                return crc32c_sse42_u64_mimic(data, init_val);
 #endif
@@ -521,7 +601,6 @@ static inline uint32_t
 rte_hash_crc(const void *data, uint32_t data_len, uint32_t init_val)
 {
        unsigned i;
-       uint64_t temp = 0;
        uintptr_t pd = (uintptr_t) data;
 
        for (i = 0; i < data_len / 8; i++) {
@@ -529,35 +608,19 @@ rte_hash_crc(const void *data, uint32_t data_len, uint32_t init_val)
                pd += 8;
        }
 
-       switch (7 - (data_len & 0x07)) {
-       case 0:
-               temp |= (uint64_t) *((const uint8_t *)pd + 6) << 48;
-               /* Fallthrough */
-       case 1:
-               temp |= (uint64_t) *((const uint8_t *)pd + 5) << 40;
-               /* Fallthrough */
-       case 2:
-               temp |= (uint64_t) *((const uint8_t *)pd + 4) << 32;
-               temp |= *(const uint32_t *)pd;
-               init_val = rte_hash_crc_8byte(temp, init_val);
-               break;
-       case 3:
+       if (data_len & 0x4) {
                init_val = rte_hash_crc_4byte(*(const uint32_t *)pd, init_val);
-               break;
-       case 4:
-               temp |= *((const uint8_t *)pd + 2) << 16;
-               /* Fallthrough */
-       case 5:
-               temp |= *((const uint8_t *)pd + 1) << 8;
-               /* Fallthrough */
-       case 6:
-               temp |= *(const uint8_t *)pd;
-               init_val = rte_hash_crc_4byte(temp, init_val);
-               /* Fallthrough */
-       default:
-               break;
+               pd += 4;
+       }
+
+       if (data_len & 0x2) {
+               init_val = rte_hash_crc_2byte(*(const uint16_t *)pd, init_val);
+               pd += 2;
        }
 
+       if (data_len & 0x1)
+               init_val = rte_hash_crc_1byte(*(const uint8_t *)pd, init_val);
+
        return init_val;
 }