[dpdk-dev] [PATCH v3 16/17] lpm/arm: implement rte_lpm_lookupx4 using rte_lpm_lookup_bulk for non-x86

[Jan Viktorin]

From: Vlastimil Kosar <kosar at rehivetech.com>

LPM function rte_lpm_lookupx4() uses i686/x86_64 SIMD intrinsics. Therefore,
the function is reimplemented using non-vector operations for non-x86
architectures.

LPM now builds for ARM.

Signed-off-by: Vlastimil Kosar <kosar at rehivetech.com>
Signed-off-by: Jan Viktorin <viktorin at rehivetech.com>
---
v2 -> v3: as SIMD operations have been moved to rte_vect.h,
          this patch is now quite clear and just defines the
          non-x86 version of rte_lpm_lookupx4
---
 config/defconfig_arm-armv7-a-linuxapp-gcc |  1 -
 lib/librte_lpm/rte_lpm.h                  | 24 +++++++++++++++++++++---
 2 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/config/defconfig_arm-armv7-a-linuxapp-gcc b/config/defconfig_arm-armv7-a-linuxapp-gcc
index 5a778cf..a2c8b95 100644
--- a/config/defconfig_arm-armv7-a-linuxapp-gcc
+++ b/config/defconfig_arm-armv7-a-linuxapp-gcc
@@ -55,7 +55,6 @@ CONFIG_RTE_EAL_IGB_UIO=n
 
 # fails to compile on ARM
 CONFIG_RTE_LIBRTE_ACL=n
-CONFIG_RTE_LIBRTE_LPM=n
 
 # cannot use those on ARM
 CONFIG_RTE_KNI_KMOD=n
diff --git a/lib/librte_lpm/rte_lpm.h b/lib/librte_lpm/rte_lpm.h
index c299ce2..c02b355 100644
--- a/lib/librte_lpm/rte_lpm.h
+++ b/lib/librte_lpm/rte_lpm.h
@@ -358,9 +358,6 @@ 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.
  *
@@ -382,6 +379,14 @@ rte_lpm_lookup_bulk_func(const struct rte_lpm *lpm, const uint32_t * ips,
  */
 static inline void
 rte_lpm_lookupx4(const struct rte_lpm *lpm, __m128i ip, uint16_t hop[4],
+	uint16_t defv);
+
+#if defined(RTE_ARCH_X86_64) || defined(RTE_ARCH_I686)
+/* Mask four results. */
+#define	 RTE_LPM_MASKX4_RES	UINT64_C(0x00ff00ff00ff00ff)
+
+static inline void
+rte_lpm_lookupx4(const struct rte_lpm *lpm, __m128i ip, uint16_t hop[4],
 	uint16_t defv)
 {
 	__m128i i24;
@@ -472,6 +477,19 @@ rte_lpm_lookupx4(const struct rte_lpm *lpm, __m128i ip, uint16_t hop[4],
 	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;
 }
+#else
+static inline void
+rte_lpm_lookupx4(const struct rte_lpm *lpm, __m128i ip, uint16_t hop[4],
+	uint16_t defv)
+{
+	rte_lpm_lookup_bulk(lpm, ip.val.uint32, hop, 4);
+
+	hop[0] = (hop[0] & RTE_LPM_LOOKUP_SUCCESS) ? (uint8_t)hop[0] : defv;
+	hop[1] = (hop[1] & RTE_LPM_LOOKUP_SUCCESS) ? (uint8_t)hop[1] : defv;
+	hop[2] = (hop[2] & RTE_LPM_LOOKUP_SUCCESS) ? (uint8_t)hop[2] : defv;
+	hop[3] = (hop[3] & RTE_LPM_LOOKUP_SUCCESS) ? (uint8_t)hop[3] : defv;
+}
+#endif
 
 #ifdef __cplusplus
 }
-- 
2.6.1