enic: replace use of printf with log

[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 4da7ca4..d28bb2a 100644 (file)
--- a/lib/librte_hash/rte_hash_crc.h
+++ b/lib/librte_hash/rte_hash_crc.h
@@ -45,7 +45,8 @@ extern "C" {
 #endif
 
 #include <stdint.h>
-#include <nmmintrin.h>
+#include <rte_cpuflags.h>
+#include <rte_branch_prediction.h>
 
 /* Lookup tables for software implementation of CRC32C */
 static const uint32_t crc32c_tables[8][256] = {{
@@ -363,8 +364,86 @@ crc32c_2words(uint64_t data, uint32_t init_val)
        return crc;
 }
 
+static inline uint32_t
+crc32c_sse42_u32(uint32_t data, uint32_t init_val)
+{
+       __asm__ volatile(
+                       "crc32l %[data], %[init_val];"
+                       : [init_val] "+r" (init_val)
+                       : [data] "rm" (data));
+       return init_val;
+}
+
+static inline uint32_t
+crc32c_sse42_u64(uint64_t data, uint64_t init_val)
+{
+       __asm__ volatile(
+                       "crc32q %[data], %[init_val];"
+                       : [init_val] "+r" (init_val)
+                       : [data] "rm" (data));
+       return init_val;
+}
+
+static inline uint32_t
+crc32c_sse42_u64_mimic(uint64_t data, uint64_t init_val)
+{
+       union {
+               uint32_t u32[2];
+               uint64_t u64;
+       } d;
+
+       d.u64 = data;
+       init_val = crc32c_sse42_u32(d.u32[0], init_val);
+       init_val = crc32c_sse42_u32(d.u32[1], init_val);
+       return init_val;
+}
+
+#define CRC32_SW            (1U << 0)
+#define CRC32_SSE42         (1U << 1)
+#define CRC32_x64           (1U << 2)
+#define CRC32_SSE42_x64     (CRC32_x64|CRC32_SSE42)
+
+static uint8_t crc32_alg = CRC32_SW;
+
+/**
+ * Allow or disallow use of SSE4.2 instrinsics for CRC32 hash
+ * calculation.
+ *
+ * @param alg
+ *   An OR of following flags:
+ *   - (CRC32_SW) Don't use SSE4.2 intrinsics
+ *   - (CRC32_SSE42) Use SSE4.2 intrinsics if available
+ *   - (CRC32_SSE42_x64) Use 64-bit SSE4.2 intrinsic if available (default)
+ *
+ */
+static inline void
+rte_hash_crc_set_alg(uint8_t alg)
+{
+       switch (alg) {
+       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;
+       case CRC32_SW:
+               crc32_alg = alg;
+       default:
+               break;
+       }
+}
+
+/* Setting the best available algorithm */
+static inline void __attribute__((constructor))
+rte_hash_crc_init_alg(void)
+{
+       rte_hash_crc_set_alg(CRC32_SSE42_x64);
+}
+
 /**
  * Use single crc32 instruction to perform a hash on a 4 byte value.
+ * Fall back to software crc32 implementation in case SSE4.2 is
+ * not supported
  *
  * @param data
  *   Data to perform hash on.
@@ -376,11 +455,38 @@ crc32c_2words(uint64_t data, uint32_t init_val)
 static inline uint32_t
 rte_hash_crc_4byte(uint32_t data, uint32_t init_val)
 {
-       return _mm_crc32_u32(init_val, data);
+       if (likely(crc32_alg & CRC32_SSE42))
+               return crc32c_sse42_u32(data, init_val);
+
+       return crc32c_1word(data, init_val);
+}
+
+/**
+ * Use single crc32 instruction to perform a hash on a 8 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_8byte(uint64_t data, uint32_t init_val)
+{
+       if (likely(crc32_alg == CRC32_SSE42_x64))
+               return crc32c_sse42_u64(data, init_val);
+
+       if (likely(crc32_alg & CRC32_SSE42))
+               return crc32c_sse42_u64_mimic(data, init_val);
+
+       return crc32c_2words(data, init_val);
 }
 
 /**
- * Use crc32 instruction to perform a hash.
+ * Calculate CRC32 hash on user-supplied byte array.
  *
  * @param data
  *   Data to perform hash on.
@@ -395,23 +501,38 @@ static inline uint32_t
 rte_hash_crc(const void *data, uint32_t data_len, uint32_t init_val)
 {
        unsigned i;
-       uint32_t temp = 0;
-       const uint32_t *p32 = (const uint32_t *)data;
+       uint64_t temp = 0;
+       const uint64_t *p64 = (const uint64_t *)data;
 
-       for (i = 0; i < data_len / 4; i++) {
-               init_val = rte_hash_crc_4byte(*p32++, init_val);
+       for (i = 0; i < data_len / 8; i++) {
+               init_val = rte_hash_crc_8byte(*p64++, init_val);
        }
 
-       switch (3 - (data_len & 0x03)) {
+       switch (7 - (data_len & 0x07)) {
        case 0:
-               temp |= *((const uint8_t *)p32 + 2) << 16;
+               temp |= (uint64_t) *((const uint8_t *)p64 + 6) << 48;
                /* Fallthrough */
        case 1:
-               temp |= *((const uint8_t *)p32 + 1) << 8;
+               temp |= (uint64_t) *((const uint8_t *)p64 + 5) << 40;
                /* Fallthrough */
        case 2:
-               temp |= *((const uint8_t *)p32);
+               temp |= (uint64_t) *((const uint8_t *)p64 + 4) << 32;
+               temp |= *((const uint32_t *)p64);
+               init_val = rte_hash_crc_8byte(temp, init_val);
+               break;
+       case 3:
+               init_val = rte_hash_crc_4byte(*(const uint32_t *)p64, init_val);
+               break;
+       case 4:
+               temp |= *((const uint8_t *)p64 + 2) << 16;
+               /* Fallthrough */
+       case 5:
+               temp |= *((const uint8_t *)p64 + 1) << 8;
+               /* Fallthrough */
+       case 6:
+               temp |= *((const uint8_t *)p64);
                init_val = rte_hash_crc_4byte(temp, init_val);
+               /* Fallthrough */
        default:
                break;
        }