[dpdk-dev] [RFC 04/12] lpm: add support for s390x architecture

[Vivian Kong <vivkong@gmail.com>]

Add big endian support for s390x architecture.

Signed-off-by: Vivian Kong <vivkong@ca.ibm.com>
---
 lib/librte_lpm/Makefile        |   2 +
 lib/librte_lpm/meson.build     |   2 +-
 lib/librte_lpm/rte_lpm.h       |   2 +
 lib/librte_lpm/rte_lpm6.c      |  26 ++++++-
 lib/librte_lpm/rte_lpm_s390x.h | 130 +++++++++++++++++++++++++++++++++
 5 files changed, 157 insertions(+), 5 deletions(-)
 create mode 100644 lib/librte_lpm/rte_lpm_s390x.h

diff --git a/lib/librte_lpm/Makefile b/lib/librte_lpm/Makefile
index a7946a1c5..16b868304 100644
--- a/lib/librte_lpm/Makefile
+++ b/lib/librte_lpm/Makefile
@@ -26,6 +26,8 @@ else ifeq ($(CONFIG_RTE_ARCH_X86),y)
 SYMLINK-$(CONFIG_RTE_LIBRTE_LPM)-include += rte_lpm_sse.h
 else ifeq ($(CONFIG_RTE_ARCH_PPC_64),y)
 SYMLINK-$(CONFIG_RTE_LIBRTE_LPM)-include += rte_lpm_altivec.h
+else ifeq ($(CONFIG_RTE_ARCH_S390X),y)
+SYMLINK-$(CONFIG_RTE_LIBRTE_LPM)-include += rte_lpm_s390x.h
 endif
 
 include $(RTE_SDK)/mk/rte.lib.mk
diff --git a/lib/librte_lpm/meson.build b/lib/librte_lpm/meson.build
index a5176d8ae..68317ed52 100644
--- a/lib/librte_lpm/meson.build
+++ b/lib/librte_lpm/meson.build
@@ -6,5 +6,5 @@ sources = files('rte_lpm.c', 'rte_lpm6.c')
 headers = files('rte_lpm.h', 'rte_lpm6.h')
 # since header files have different names, we can install all vector headers
 # without worrying about which architecture we actually need
-headers += files('rte_lpm_altivec.h', 'rte_lpm_neon.h', 'rte_lpm_sse.h')
+headers += files('rte_lpm_s390x.h', 'rte_lpm_altivec.h', 'rte_lpm_neon.h', 'rte_lpm_sse.h')
 deps += ['hash']
diff --git a/lib/librte_lpm/rte_lpm.h b/lib/librte_lpm/rte_lpm.h
index 21550444d..aa8a43968 100644
--- a/lib/librte_lpm/rte_lpm.h
+++ b/lib/librte_lpm/rte_lpm.h
@@ -459,6 +459,8 @@ rte_lpm_lookupx4(const struct rte_lpm *lpm, xmm_t ip, uint32_t hop[4],
 #include "rte_lpm_neon.h"
 #elif defined(RTE_ARCH_PPC_64)
 #include "rte_lpm_altivec.h"
+#elif defined(RTE_ARCH_S390X)
+#include "rte_lpm_s390x.h"
 #else
 #include "rte_lpm_sse.h"
 #endif
diff --git a/lib/librte_lpm/rte_lpm6.c b/lib/librte_lpm/rte_lpm6.c
index a91803113..7aead4035 100644
--- a/lib/librte_lpm/rte_lpm6.c
+++ b/lib/librte_lpm/rte_lpm6.c
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause
  * Copyright(c) 2010-2014 Intel Corporation
  */
+
 #include <string.h>
 #include <stdint.h>
 #include <errno.h>
@@ -24,6 +25,7 @@
 #include <rte_hash.h>
 #include <assert.h>
 #include <rte_jhash.h>
+#include <rte_byteorder.h>
 
 #include "rte_lpm6.h"
 
@@ -58,17 +60,33 @@ static struct rte_tailq_elem rte_lpm6_tailq = {
 };
 EAL_REGISTER_TAILQ(rte_lpm6_tailq)
 
+#if RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
+
 /** Tbl entry structure. It is the same for both tbl24 and tbl8 */
 struct rte_lpm6_tbl_entry {
-	uint32_t next_hop:	21;  /**< Next hop / next table to be checked. */
-	uint32_t depth	:8;      /**< Rule depth. */
+	uint32_t next_hop :21;  /**< Next hop / next table to be checked. */
+	uint32_t depth	  :8;   /**< Rule depth. */
+
+	/* Flags. */
+	uint32_t valid       :1; /**< Validation flag. */
+	uint32_t valid_group :1; /**< Group validation flag. */
+	uint32_t ext_entry   :1; /**< External entry. */
+};
+
+#else
 
+struct rte_lpm6_tbl_entry {
 	/* Flags. */
-	uint32_t valid     :1;   /**< Validation flag. */
+	uint32_t ext_entry   :1; /**< External entry. */
 	uint32_t valid_group :1; /**< Group validation flag. */
-	uint32_t ext_entry :1;   /**< External entry. */
+	uint32_t valid       :1; /**< Validation flag. */
+
+	uint32_t depth    :8;   /**< Rule depth. */
+	uint32_t next_hop :21;  /**< Next hop / next table to be checked. */
 };
 
+#endif
+
 /** Rules tbl entry structure. */
 struct rte_lpm6_rule {
 	uint8_t ip[RTE_LPM6_IPV6_ADDR_SIZE]; /**< Rule IP address. */
diff --git a/lib/librte_lpm/rte_lpm_s390x.h b/lib/librte_lpm/rte_lpm_s390x.h
new file mode 100644
index 000000000..eb1fdd450
--- /dev/null
+++ b/lib/librte_lpm/rte_lpm_s390x.h
@@ -0,0 +1,130 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * (c) Copyright IBM Corp. 2016, 2018
+ */
+
+#ifndef _RTE_LPM_S390X_H_
+#define _RTE_LPM_S390X_H_
+
+#include <rte_branch_prediction.h>
+#include <rte_byteorder.h>
+#include <rte_common.h>
+#include <rte_vect.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+static inline void
+rte_lpm_lookupx4(const struct rte_lpm *lpm, xmm_t ip, uint32_t hop[4],
+	uint32_t defv)
+{
+	typedef int vector_signed_int
+		__attribute__((vector_size(4*sizeof(int))));
+	vector_signed_int i24;
+	rte_xmm_t i8;
+	uint32_t tbl[4];
+	uint64_t idx, pt, pt2;
+	const uint32_t *ptbl;
+
+	const uint32_t mask = UINT8_MAX;
+	const vector_signed_int mask8 = (xmm_t){mask, mask, mask, mask};
+
+	/*
+	 * RTE_LPM_VALID_EXT_ENTRY_BITMASK for 2 LPM entries
+	 * as one 64-bit value (0x0300000003000000).
+	 */
+	const uint64_t mask_xv =
+		((uint64_t)RTE_LPM_VALID_EXT_ENTRY_BITMASK |
+		(uint64_t)RTE_LPM_VALID_EXT_ENTRY_BITMASK << 32);
+
+	/*
+	 * RTE_LPM_LOOKUP_SUCCESS for 2 LPM entries
+	 * as one 64-bit value (0x0100000001000000).
+	 */
+	const uint64_t mask_v =
+		((uint64_t)RTE_LPM_LOOKUP_SUCCESS |
+		(uint64_t)RTE_LPM_LOOKUP_SUCCESS << 32);
+
+	/* get 4 indexes for tbl24[]. */
+	i24[0] = (uint32_t)ip[0] >> 8;
+	i24[1] = (uint32_t)ip[1] >> 8;
+	i24[2] = (uint32_t)ip[2] >> 8;
+	i24[3] = (uint32_t)ip[3] >> 8;
+
+	/* extract values from tbl24[] */
+	idx = (uint32_t)i24[0];
+	idx = idx < (1<<24) ? idx : (1<<24)-1;
+	ptbl = (const uint32_t *)&lpm->tbl24[idx];
+	tbl[0] = *ptbl;
+
+	idx = (uint32_t) i24[1];
+	idx = idx < (1<<24) ? idx : (1<<24)-1;
+	ptbl = (const uint32_t *)&lpm->tbl24[idx];
+	tbl[1] = *ptbl;
+
+	idx = (uint32_t) i24[2];
+	idx = idx < (1<<24) ? idx : (1<<24)-1;
+	ptbl = (const uint32_t *)&lpm->tbl24[idx];
+	tbl[2] = *ptbl;
+
+	idx = (uint32_t) i24[3];
+	idx = idx < (1<<24) ? idx : (1<<24)-1;
+	ptbl = (const uint32_t *)&lpm->tbl24[idx];
+	tbl[3] = *ptbl;
+
+	/* get 4 indexes for tbl8[]. */
+	i8.x = vec_and(ip, mask8);
+
+	pt = (uint64_t)tbl[0] |
+		(uint64_t)tbl[1] << 32;
+	pt2 = (uint64_t)tbl[2] |
+		(uint64_t)tbl[3] << 32;
+
+	/* search successfully finished for all 4 IP addresses. */
+	if (likely((pt & mask_xv) == mask_v) &&
+			likely((pt2 & mask_xv) == mask_v)) {
+		*(uint64_t *)hop = pt & RTE_LPM_MASKX4_RES;
+		*(uint64_t *)(hop + 2) = pt2 & 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;
+		ptbl = (const uint32_t *)&lpm->tbl8[i8.u32[0]];
+		tbl[0] = *ptbl;
+	}
+	if (unlikely((pt >> 32 & 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;
+		ptbl = (const uint32_t *)&lpm->tbl8[i8.u32[1]];
+		tbl[1] = *ptbl;
+	}
+	if (unlikely((pt2 & 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;
+		ptbl = (const uint32_t *)&lpm->tbl8[i8.u32[2]];
+		tbl[2] = *ptbl;
+	}
+	if (unlikely((pt2 >> 32 & 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;
+		ptbl = (const uint32_t *)&lpm->tbl8[i8.u32[3]];
+		tbl[3] = *ptbl;
+	}
+
+	hop[0] = (tbl[0] & RTE_LPM_LOOKUP_SUCCESS) ? tbl[0] & 0x00FFFFFF : defv;
+	hop[1] = (tbl[1] & RTE_LPM_LOOKUP_SUCCESS) ? tbl[1] & 0x00FFFFFF : defv;
+	hop[2] = (tbl[2] & RTE_LPM_LOOKUP_SUCCESS) ? tbl[2] & 0x00FFFFFF : defv;
+	hop[3] = (tbl[3] & RTE_LPM_LOOKUP_SUCCESS) ? tbl[3] & 0x00FFFFFF : defv;
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_LPM_S390X_H_ */
-- 
2.17.1