X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_lpm%2Frte_lpm.h;h=d35565df7cf79ed924037c86217f364b2841c436;hb=3440438c5d4749371be8c9c2abace4793af495b9;hp=047738cf9b23d132efc6b194dd3b4cb9f6340b02;hpb=cc333208d5658fea642098b665cd429e6cda54a9;p=dpdk.git

diff --git a/lib/librte_lpm/rte_lpm.h b/lib/librte_lpm/rte_lpm.h
index 047738cf9b..d35565df7c 100644
--- a/lib/librte_lpm/rte_lpm.h
+++ b/lib/librte_lpm/rte_lpm.h
@@ -45,6 +45,8 @@
 #include <stdlib.h>
 #include <rte_branch_prediction.h>
 #include <rte_memory.h>
+#include <rte_common.h>
+#include <rte_common_vect.h>
 
 #ifdef __cplusplus
 extern "C" {
@@ -331,6 +333,121 @@ rte_lpm_lookup_bulk_func(const struct rte_lpm *lpm, const uint32_t * ips,
 	return 0;
 }
 
+/* Mask four results. */
+#define	 RTE_LPM_MASKX4_RES	UINT64_C(0x00ff00ff00ff00ff)
+
+/**
+ * Lookup four IP addresses in an LPM table.
+ *
+ * @param lpm
+ *   LPM object handle
+ * @param ip
+ *   Four IPs to be looked up in the LPM table
+ * @param hop
+ *   Next hop of the most specific rule found for IP (valid on lookup hit only).
+ *   This is an 4 elements array of two byte values.
+ *   If the lookup was succesfull for the given IP, then least significant byte
+ *   of the corresponding element is the  actual next hop and the most
+ *   significant byte is zero.
+ *   If the lookup for the given IP failed, then corresponding element would
+ *   contain default value, see description of then next parameter.
+ * @param defv
+ *   Default value to populate into corresponding element of hop[] array,
+ *   if lookup would fail.
+ */
+static inline void
+rte_lpm_lookupx4(const struct rte_lpm *lpm, __m128i ip, uint16_t hop[4],
+	uint16_t defv)
+{
+	__m128i i24;
+	rte_xmm_t i8;
+	uint16_t tbl[4];
+	uint64_t idx, pt;
+
+	const __m128i mask8 =
+		_mm_set_epi32(UINT8_MAX, UINT8_MAX, UINT8_MAX, UINT8_MAX);
+
+	/*
+	 * RTE_LPM_VALID_EXT_ENTRY_BITMASK for 4 LPM entries
+	 * as one 64-bit value (0x0300030003000300).
+	 */
+	const uint64_t mask_xv =
+		((uint64_t)RTE_LPM_VALID_EXT_ENTRY_BITMASK |
+		(uint64_t)RTE_LPM_VALID_EXT_ENTRY_BITMASK << 16 |
+		(uint64_t)RTE_LPM_VALID_EXT_ENTRY_BITMASK << 32 |
+		(uint64_t)RTE_LPM_VALID_EXT_ENTRY_BITMASK << 48);
+
+	/*
+	 * RTE_LPM_LOOKUP_SUCCESS for 4 LPM entries
+	 * as one 64-bit value (0x0100010001000100).
+	 */
+	const uint64_t mask_v =
+		((uint64_t)RTE_LPM_LOOKUP_SUCCESS |
+		(uint64_t)RTE_LPM_LOOKUP_SUCCESS << 16 |
+		(uint64_t)RTE_LPM_LOOKUP_SUCCESS << 32 |
+		(uint64_t)RTE_LPM_LOOKUP_SUCCESS << 48);
+
+	/* get 4 indexes for tbl24[]. */
+	i24 = _mm_srli_epi32(ip, CHAR_BIT);
+
+	/* extract values from tbl24[] */
+	idx = _mm_cvtsi128_si64(i24);
+	i24 = _mm_srli_si128(i24, sizeof(uint64_t));
+
+	tbl[0] = *(const uint16_t *)&lpm->tbl24[(uint32_t)idx];
+	tbl[1] = *(const uint16_t *)&lpm->tbl24[idx >> 32];
+
+	idx = _mm_cvtsi128_si64(i24);
+
+	tbl[2] = *(const uint16_t *)&lpm->tbl24[(uint32_t)idx];
+	tbl[3] = *(const uint16_t *)&lpm->tbl24[idx >> 32];
+
+	/* get 4 indexes for tbl8[]. */
+	i8.m = _mm_and_si128(ip, mask8);
+
+	pt = (uint64_t)tbl[0] |
+		(uint64_t)tbl[1] << 16 |
+		(uint64_t)tbl[2] << 32 |
+		(uint64_t)tbl[3] << 48;
+
+	/* search successfully finished for all 4 IP addresses. */
+	if (likely((pt & mask_xv) == mask_v)) {
+		uintptr_t ph = (uintptr_t)hop;
+		*(uint64_t *)ph = pt & RTE_LPM_MASKX4_RES;
+		return;
+	}
+
+	if (unlikely((pt & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
+			RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
+		i8.u32[0] = i8.u32[0] +
+			(uint8_t)tbl[0] * RTE_LPM_TBL8_GROUP_NUM_ENTRIES;
+		tbl[0] = *(const uint16_t *)&lpm->tbl8[i8.u32[0]];
+	}
+	if (unlikely((pt >> 16 & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
+			RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
+		i8.u32[1] = i8.u32[1] +
+			(uint8_t)tbl[1] * RTE_LPM_TBL8_GROUP_NUM_ENTRIES;
+		tbl[1] = *(const uint16_t *)&lpm->tbl8[i8.u32[1]];
+	}
+	if (unlikely((pt >> 32 & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
+			RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
+		i8.u32[2] = i8.u32[2] +
+			(uint8_t)tbl[2] * RTE_LPM_TBL8_GROUP_NUM_ENTRIES;
+		tbl[2] = *(const uint16_t *)&lpm->tbl8[i8.u32[2]];
+	}
+	if (unlikely((pt >> 48 & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
+			RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
+		i8.u32[3] = i8.u32[3] +
+			(uint8_t)tbl[3] * RTE_LPM_TBL8_GROUP_NUM_ENTRIES;
+		tbl[3] = *(const uint16_t *)&lpm->tbl8[i8.u32[3]];
+	}
+
+	hop[0] = (tbl[0] & RTE_LPM_LOOKUP_SUCCESS) ? (uint8_t)tbl[0] : defv;
+	hop[1] = (tbl[1] & RTE_LPM_LOOKUP_SUCCESS) ? (uint8_t)tbl[1] : defv;
+	hop[2] = (tbl[2] & RTE_LPM_LOOKUP_SUCCESS) ? (uint8_t)tbl[2] : defv;
+	hop[3] = (tbl[3] & RTE_LPM_LOOKUP_SUCCESS) ? (uint8_t)tbl[3] : defv;
+}
+
 #ifdef __cplusplus
 }
 #endif