[PATCH] fib: network byte order IPv4 lookup

[PATCH] fib: network byte order IPv4 lookup

[Vladimir Medvedkin]

Previously when running rte_fib_lookup IPv4 addresses must have been in
host byte order.

This patch adds a new flag RTE_FIB_FLAG_LOOKUP_BE that can be passed on
fib create, which will allow to have IPv4 in network byte order on
lookup.

Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
---
 app/test/test_fib.c      |  2 +-
 lib/fib/dir24_8.c        | 58 +++++++++++++++++-----------
 lib/fib/dir24_8.h        | 44 ++++++++++++++++++++-
 lib/fib/dir24_8_avx512.c | 82 +++++++++++++++++++++++-----------------
 lib/fib/dir24_8_avx512.h | 15 ++++++++
 lib/fib/rte_fib.c        |  7 +++-
 lib/fib/rte_fib.h        |  4 ++
 7 files changed, 152 insertions(+), 60 deletions(-)

diff --git a/app/test/test_fib.c b/app/test/test_fib.c
index 45dccca1f6..b0e53dbe01 100644
--- a/app/test/test_fib.c
+++ b/app/test/test_fib.c
@@ -319,7 +319,7 @@ int32_t
 test_lookup(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 	uint64_t def_nh = 100;
 	int ret;
 
diff --git a/lib/fib/dir24_8.c b/lib/fib/dir24_8.c
index c739e92304..2d2a7db697 100644
--- a/lib/fib/dir24_8.c
+++ b/lib/fib/dir24_8.c
@@ -26,41 +26,49 @@
 #define ROUNDUP(x, y)	 RTE_ALIGN_CEIL(x, (1 << (32 - y)))
 
 static inline rte_fib_lookup_fn_t
-get_scalar_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_scalar_fn(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return dir24_8_lookup_bulk_1b;
+		return (be_addr) ? dir24_8_lookup_bulk_1b_be :
+					dir24_8_lookup_bulk_1b;
 	case RTE_FIB_DIR24_8_2B:
-		return dir24_8_lookup_bulk_2b;
+		return (be_addr) ? dir24_8_lookup_bulk_2b_be :
+					dir24_8_lookup_bulk_2b;
 	case RTE_FIB_DIR24_8_4B:
-		return dir24_8_lookup_bulk_4b;
+		return (be_addr) ? dir24_8_lookup_bulk_4b_be :
+					dir24_8_lookup_bulk_4b;
 	case RTE_FIB_DIR24_8_8B:
-		return dir24_8_lookup_bulk_8b;
+		return (be_addr) ? dir24_8_lookup_bulk_8b_be :
+					dir24_8_lookup_bulk_8b;
 	default:
 		return NULL;
 	}
 }
 
 static inline rte_fib_lookup_fn_t
-get_scalar_fn_inlined(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_scalar_fn_inlined(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return dir24_8_lookup_bulk_0;
+		return (be_addr) ? dir24_8_lookup_bulk_0_be :
+					dir24_8_lookup_bulk_0;
 	case RTE_FIB_DIR24_8_2B:
-		return dir24_8_lookup_bulk_1;
+		return (be_addr) ? dir24_8_lookup_bulk_1_be :
+					dir24_8_lookup_bulk_1;
 	case RTE_FIB_DIR24_8_4B:
-		return dir24_8_lookup_bulk_2;
+		return (be_addr) ? dir24_8_lookup_bulk_2_be :
+					dir24_8_lookup_bulk_2;
 	case RTE_FIB_DIR24_8_8B:
-		return dir24_8_lookup_bulk_3;
+		return (be_addr) ? dir24_8_lookup_bulk_3_be :
+					dir24_8_lookup_bulk_3;
 	default:
 		return NULL;
 	}
 }
 
 static inline rte_fib_lookup_fn_t
-get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 #ifdef CC_DIR24_8_AVX512_SUPPORT
 	if ((rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) <= 0) ||
@@ -69,13 +77,17 @@ get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
 
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return rte_dir24_8_vec_lookup_bulk_1b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_1b_be :
+					rte_dir24_8_vec_lookup_bulk_1b;
 	case RTE_FIB_DIR24_8_2B:
-		return rte_dir24_8_vec_lookup_bulk_2b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_2b_be :
+					rte_dir24_8_vec_lookup_bulk_2b;
 	case RTE_FIB_DIR24_8_4B:
-		return rte_dir24_8_vec_lookup_bulk_4b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_4b_be :
+					rte_dir24_8_vec_lookup_bulk_4b;
 	case RTE_FIB_DIR24_8_8B:
-		return rte_dir24_8_vec_lookup_bulk_8b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_8b_be :
+					rte_dir24_8_vec_lookup_bulk_8b;
 	default:
 		return NULL;
 	}
@@ -86,7 +98,7 @@ get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
 }
 
 rte_fib_lookup_fn_t
-dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type)
+dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type, bool be_addr)
 {
 	enum rte_fib_dir24_8_nh_sz nh_sz;
 	rte_fib_lookup_fn_t ret_fn;
@@ -99,16 +111,18 @@ dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type)
 
 	switch (type) {
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_MACRO:
-		return get_scalar_fn(nh_sz);
+		return get_scalar_fn(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_INLINE:
-		return get_scalar_fn_inlined(nh_sz);
+		return get_scalar_fn_inlined(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_UNI:
-		return dir24_8_lookup_bulk_uni;
+		return (be_addr) ? dir24_8_lookup_bulk_uni_be :
+						dir24_8_lookup_bulk_uni;
 	case RTE_FIB_LOOKUP_DIR24_8_VECTOR_AVX512:
-		return get_vector_fn(nh_sz);
+		return get_vector_fn(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DEFAULT:
-		ret_fn = get_vector_fn(nh_sz);
-		return (ret_fn != NULL) ? ret_fn : get_scalar_fn(nh_sz);
+		ret_fn = get_vector_fn(nh_sz, be_addr);
+		return (ret_fn != NULL) ? ret_fn :
+			get_scalar_fn(nh_sz, be_addr);
 	default:
 		return NULL;
 	}
diff --git a/lib/fib/dir24_8.h b/lib/fib/dir24_8.h
index 7125049f15..2c776e118f 100644
--- a/lib/fib/dir24_8.h
+++ b/lib/fib/dir24_8.h
@@ -7,7 +7,9 @@
 #define _DIR24_8_H_
 
 #include <stdalign.h>
+#include <stdbool.h>
 
+#include <rte_byteorder.h>
 #include <rte_prefetch.h>
 #include <rte_branch_prediction.h>
 
@@ -237,6 +239,46 @@ dir24_8_lookup_bulk_uni(void *p, const uint32_t *ips,
 	}
 }
 
+#define BSWAP_MAX_LENGTH	64
+
+typedef void (*dir24_8_lookup_bulk_be_cb)(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+static inline void
+dir24_8_lookup_bulk_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n,
+	dir24_8_lookup_bulk_be_cb cb)
+{
+	uint32_t le_ips[BSWAP_MAX_LENGTH];
+	unsigned int i;
+
+	for (i = 0; i < n; i += BSWAP_MAX_LENGTH) {
+		int j;
+		for (j = 0; j < BSWAP_MAX_LENGTH && i + j < n; j++)
+			le_ips[j] = rte_be_to_cpu_32(ips[i + j]);
+
+		cb(p, le_ips, next_hops + i, j);
+	}
+}
+
+#define DECLARE_BE_LOOKUP_FN(name)					\
+static inline void							\
+name##_be(void *p, const uint32_t *ips,					\
+	uint64_t *next_hops, const unsigned int n)			\
+{									\
+	dir24_8_lookup_bulk_be(p, ips, next_hops, n, name);		\
+}
+
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_1b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_2b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_4b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_8b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_0)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_1)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_2)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_3)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_uni)
+
 void *
 dir24_8_create(const char *name, int socket_id, struct rte_fib_conf *conf);
 
@@ -244,7 +286,7 @@ void
 dir24_8_free(void *p);
 
 rte_fib_lookup_fn_t
-dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type);
+dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type, bool be_addr);
 
 int
 dir24_8_modify(struct rte_fib *fib, uint32_t ip, uint8_t depth,
diff --git a/lib/fib/dir24_8_avx512.c b/lib/fib/dir24_8_avx512.c
index 43dba28cfb..edd802abe4 100644
--- a/lib/fib/dir24_8_avx512.c
+++ b/lib/fib/dir24_8_avx512.c
@@ -10,7 +10,7 @@
 
 static __rte_always_inline void
 dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
-	uint64_t *next_hops, int size)
+	uint64_t *next_hops, int size, bool be_addr)
 {
 	struct dir24_8_tbl *dp = (struct dir24_8_tbl *)p;
 	__mmask16 msk_ext;
@@ -28,6 +28,16 @@ dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
 		res_msk = _mm512_set1_epi32(UINT16_MAX);
 
 	ip_vec = _mm512_loadu_si512(ips);
+	if (be_addr) {
+		const __m512i bswap32 = _mm512_set_epi8(
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3
+		);
+		ip_vec = _mm512_shuffle_epi8(ip_vec, bswap32);
+	}
+
 	/* mask 24 most significant bits */
 	idxes = _mm512_srli_epi32(ip_vec, 8);
 
@@ -78,7 +88,7 @@ dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
 
 static __rte_always_inline void
 dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
-	uint64_t *next_hops)
+	uint64_t *next_hops, bool be_addr)
 {
 	struct dir24_8_tbl *dp = (struct dir24_8_tbl *)p;
 	const __m512i zero = _mm512_set1_epi32(0);
@@ -89,6 +99,13 @@ dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
 	__mmask8 msk_ext;
 
 	ip_vec = _mm256_loadu_si256((const void *)ips);
+	if (be_addr) {
+		const __m256i bswap32 = _mm256_set_epi8(
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3
+		);
+		ip_vec = _mm256_shuffle_epi8(ip_vec, bswap32);
+	}
 	/* mask 24 most significant bits */
 	idxes_256 = _mm256_srli_epi32(ip_vec, 8);
 
@@ -114,52 +131,49 @@ dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
 	_mm512_storeu_si512(next_hops, res);
 }
 
-void
-rte_dir24_8_vec_lookup_bulk_1b(void *p, const uint32_t *ips,
-	uint64_t *next_hops, const unsigned int n)
-{
-	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint8_t));
-
-	dir24_8_lookup_bulk_1b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
+#define DECLARE_VECTOR_FN(suffix, nh_type, be_addr)			\
+void									\
+rte_dir24_8_vec_lookup_bulk_##suffix(void *p, const uint32_t *ips,	\
+	uint64_t *next_hops, const unsigned int n)			\
+{									\
+	uint32_t i;							\
+									\
+	for (i = 0; i < (n / 16); i++)					\
+		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16, \
+			sizeof(nh_type), be_addr);			\
+									\
+	dir24_8_lookup_bulk_##suffix(p, ips + i * 16, next_hops + i * 16, \
+		n - i * 16);						\
 }
 
-void
-rte_dir24_8_vec_lookup_bulk_2b(void *p, const uint32_t *ips,
-	uint64_t *next_hops, const unsigned int n)
-{
-	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint16_t));
-
-	dir24_8_lookup_bulk_2b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
-}
+DECLARE_VECTOR_FN(1b, uint8_t, false)
+DECLARE_VECTOR_FN(2b, uint16_t, false)
+DECLARE_VECTOR_FN(4b, uint32_t, false)
+DECLARE_VECTOR_FN(1b_be, uint8_t, true)
+DECLARE_VECTOR_FN(2b_be, uint16_t, true)
+DECLARE_VECTOR_FN(4b_be, uint32_t, true)
 
 void
-rte_dir24_8_vec_lookup_bulk_4b(void *p, const uint32_t *ips,
+rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n)
 {
 	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint32_t));
+	for (i = 0; i < (n / 8); i++)
+		dir24_8_vec_lookup_x8_8b(p, ips + i * 8,
+			next_hops + i * 8, false);
 
-	dir24_8_lookup_bulk_4b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
+	dir24_8_lookup_bulk_8b(p, ips + i * 8, next_hops + i * 8, n - i * 8);
 }
 
 void
-rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
+rte_dir24_8_vec_lookup_bulk_8b_be(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n)
 {
 	uint32_t i;
 	for (i = 0; i < (n / 8); i++)
-		dir24_8_vec_lookup_x8_8b(p, ips + i * 8, next_hops + i * 8);
+		dir24_8_vec_lookup_x8_8b(p, ips + i * 8,
+			next_hops + i * 8, true);
 
-	dir24_8_lookup_bulk_8b(p, ips + i * 8, next_hops + i * 8, n - i * 8);
+	dir24_8_lookup_bulk_8b_be(p, ips + i * 8,
+		next_hops + i * 8, n - i * 8);
 }
diff --git a/lib/fib/dir24_8_avx512.h b/lib/fib/dir24_8_avx512.h
index 1d3c2b9317..e9f7b72519 100644
--- a/lib/fib/dir24_8_avx512.h
+++ b/lib/fib/dir24_8_avx512.h
@@ -21,4 +21,19 @@ void
 rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n);
 
+void
+rte_dir24_8_vec_lookup_bulk_1b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_2b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_4b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_8b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
 #endif /* _DIR248_AVX512_H_ */
diff --git a/lib/fib/rte_fib.c b/lib/fib/rte_fib.c
index 4f9fba5a4f..991e48b5ea 100644
--- a/lib/fib/rte_fib.c
+++ b/lib/fib/rte_fib.c
@@ -42,6 +42,7 @@ EAL_REGISTER_TAILQ(rte_fib_tailq)
 struct rte_fib {
 	char			name[RTE_FIB_NAMESIZE];
 	enum rte_fib_type	type;	/**< Type of FIB struct */
+	int flags;					/**< Flags */
 	struct rte_rib		*rib;	/**< RIB helper datastructure */
 	void			*dp;	/**< pointer to the dataplane struct*/
 	rte_fib_lookup_fn_t	lookup;	/**< FIB lookup function */
@@ -110,7 +111,7 @@ init_dataplane(struct rte_fib *fib, __rte_unused int socket_id,
 		if (fib->dp == NULL)
 			return -rte_errno;
 		fib->lookup = dir24_8_get_lookup_fn(fib->dp,
-			RTE_FIB_LOOKUP_DEFAULT);
+			RTE_FIB_LOOKUP_DEFAULT, !!(fib->flags & RTE_FIB_FLAG_LOOKUP_BE));
 		fib->modify = dir24_8_modify;
 		return 0;
 	default:
@@ -214,6 +215,7 @@ rte_fib_create(const char *name, int socket_id, struct rte_fib_conf *conf)
 	rte_strlcpy(fib->name, name, sizeof(fib->name));
 	fib->rib = rib;
 	fib->type = conf->type;
+	fib->flags = conf->flags;
 	fib->def_nh = conf->default_nh;
 	ret = init_dataplane(fib, socket_id, conf);
 	if (ret < 0) {
@@ -329,7 +331,8 @@ rte_fib_select_lookup(struct rte_fib *fib,
 
 	switch (fib->type) {
 	case RTE_FIB_DIR24_8:
-		fn = dir24_8_get_lookup_fn(fib->dp, type);
+		fn = dir24_8_get_lookup_fn(fib->dp, type,
+			!!(fib->flags & RTE_FIB_FLAG_LOOKUP_BE));
 		if (fn == NULL)
 			return -EINVAL;
 		fib->lookup = fn;
diff --git a/lib/fib/rte_fib.h b/lib/fib/rte_fib.h
index d7a5aafe53..1617235e85 100644
--- a/lib/fib/rte_fib.h
+++ b/lib/fib/rte_fib.h
@@ -28,6 +28,9 @@ struct rte_rib;
 /** Maximum depth value possible for IPv4 FIB. */
 #define RTE_FIB_MAXDEPTH	32
 
+/** If set fib lookup is expecting ipv4 in network byte order */
+#define RTE_FIB_FLAG_LOOKUP_BE	1
+
 /** Type of FIB struct */
 enum rte_fib_type {
 	RTE_FIB_DUMMY,		/**< RIB tree based FIB */
@@ -76,6 +79,7 @@ enum rte_fib_lookup_type {
 /** FIB configuration structure */
 struct rte_fib_conf {
 	enum rte_fib_type type; /**< Type of FIB struct */
+	unsigned int flags;
 	/** Default value returned on lookup if there is no route */
 	uint64_t default_nh;
 	int	max_routes;
-- 
2.34.1

Re: [PATCH] fib: network byte order IPv4 lookup

[David Marchand]

On Fri, Sep 6, 2024 at 1:07 PM Vladimir Medvedkin
<vladimir.medvedkin@intel.com> wrote:
>
> Previously when running rte_fib_lookup IPv4 addresses must have been in
> host byte order.
>
> This patch adds a new flag RTE_FIB_FLAG_LOOKUP_BE that can be passed on
> fib create, which will allow to have IPv4 in network byte order on
> lookup.
>
> Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>

_mm512_shuffle_epi8 requires avx512bw, so the dir24_8 AVX512
implementation can only compile when such feature is supported and
enabled.
Like the trie AVX512 implem.

IOW, we are missing an update of the library meson.build.


-- 
David Marchand

Re: [PATCH] fib: network byte order IPv4 lookup

[David Marchand]

On Sat, Sep 28, 2024 at 1:51 AM David Marchand
<david.marchand@redhat.com> wrote:
>
> On Fri, Sep 6, 2024 at 1:07 PM Vladimir Medvedkin
> <vladimir.medvedkin@intel.com> wrote:
> >
> > Previously when running rte_fib_lookup IPv4 addresses must have been in
> > host byte order.
> >
> > This patch adds a new flag RTE_FIB_FLAG_LOOKUP_BE that can be passed on
> > fib create, which will allow to have IPv4 in network byte order on
> > lookup.
> >
> > Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
>
> _mm512_shuffle_epi8 requires avx512bw, so the dir24_8 AVX512
> implementation can only compile when such feature is supported and
> enabled.
> Like the trie AVX512 implem.
>
> IOW, we are missing an update of the library meson.build.

I also suspect that both this added support in the dir24_8
implementation and the existing trie are missing some runtime check on
RTE_CPUFLAG_AVX512BW in get_vector_fn.
Can we get a fix for trie and a respin of this current patch?

Thanks.


-- 
David Marchand

Re: [PATCH] fib: network byte order IPv4 lookup

[Vladimir Medvedkin]

[-- Attachment #1: Type: text/plain, Size: 1308 bytes --]

Hi David,

Thanks for pointing out this problem, I'll send a fix and v2.


пн, 30 сент. 2024 г. в 16:07, David Marchand <david.marchand@redhat.com>:

> On Sat, Sep 28, 2024 at 1:51 AM David Marchand
> <david.marchand@redhat.com> wrote:
> >
> > On Fri, Sep 6, 2024 at 1:07 PM Vladimir Medvedkin
> > <vladimir.medvedkin@intel.com> wrote:
> > >
> > > Previously when running rte_fib_lookup IPv4 addresses must have been in
> > > host byte order.
> > >
> > > This patch adds a new flag RTE_FIB_FLAG_LOOKUP_BE that can be passed on
> > > fib create, which will allow to have IPv4 in network byte order on
> > > lookup.
> > >
> > > Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
> >
> > _mm512_shuffle_epi8 requires avx512bw, so the dir24_8 AVX512
> > implementation can only compile when such feature is supported and
> > enabled.
> > Like the trie AVX512 implem.
> >
> > IOW, we are missing an update of the library meson.build.
>
> I also suspect that both this added support in the dir24_8
> implementation and the existing trie are missing some runtime check on
> RTE_CPUFLAG_AVX512BW in get_vector_fn.
> Can we get a fix for trie and a respin of this current patch?
>
> Thanks.
>
>
> --
> David Marchand
>
>

-- 
Regards,
Vladimir

[-- Attachment #2: Type: text/html, Size: 2223 bytes --]

[PATCH v2] fib: network byte order IPv4 lookup

[Vladimir Medvedkin]

Previously when running rte_fib_lookup IPv4 addresses must have been in
host byte order.

This patch adds a new flag RTE_FIB_FLAG_LOOKUP_BE that can be passed on
fib create, which will allow to have IPv4 in network byte order on
lookup.

Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
---
 app/test/test_fib.c      |  2 +-
 lib/fib/dir24_8.c        | 62 +++++++++++++++++++-----------
 lib/fib/dir24_8.h        | 44 ++++++++++++++++++++-
 lib/fib/dir24_8_avx512.c | 82 +++++++++++++++++++++++-----------------
 lib/fib/dir24_8_avx512.h | 15 ++++++++
 lib/fib/meson.build      | 38 +++++++------------
 lib/fib/rte_fib.c        |  7 +++-
 lib/fib/rte_fib.h        |  4 ++
 8 files changed, 169 insertions(+), 85 deletions(-)

diff --git a/app/test/test_fib.c b/app/test/test_fib.c
index 45dccca1f6..b0e53dbe01 100644
--- a/app/test/test_fib.c
+++ b/app/test/test_fib.c
@@ -319,7 +319,7 @@ int32_t
 test_lookup(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 	uint64_t def_nh = 100;
 	int ret;
 
diff --git a/lib/fib/dir24_8.c b/lib/fib/dir24_8.c
index c739e92304..5520f0f519 100644
--- a/lib/fib/dir24_8.c
+++ b/lib/fib/dir24_8.c
@@ -26,56 +26,72 @@
 #define ROUNDUP(x, y)	 RTE_ALIGN_CEIL(x, (1 << (32 - y)))
 
 static inline rte_fib_lookup_fn_t
-get_scalar_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_scalar_fn(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return dir24_8_lookup_bulk_1b;
+		return (be_addr) ? dir24_8_lookup_bulk_1b_be :
+					dir24_8_lookup_bulk_1b;
 	case RTE_FIB_DIR24_8_2B:
-		return dir24_8_lookup_bulk_2b;
+		return (be_addr) ? dir24_8_lookup_bulk_2b_be :
+					dir24_8_lookup_bulk_2b;
 	case RTE_FIB_DIR24_8_4B:
-		return dir24_8_lookup_bulk_4b;
+		return (be_addr) ? dir24_8_lookup_bulk_4b_be :
+					dir24_8_lookup_bulk_4b;
 	case RTE_FIB_DIR24_8_8B:
-		return dir24_8_lookup_bulk_8b;
+		return (be_addr) ? dir24_8_lookup_bulk_8b_be :
+					dir24_8_lookup_bulk_8b;
 	default:
 		return NULL;
 	}
 }
 
 static inline rte_fib_lookup_fn_t
-get_scalar_fn_inlined(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_scalar_fn_inlined(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return dir24_8_lookup_bulk_0;
+		return (be_addr) ? dir24_8_lookup_bulk_0_be :
+					dir24_8_lookup_bulk_0;
 	case RTE_FIB_DIR24_8_2B:
-		return dir24_8_lookup_bulk_1;
+		return (be_addr) ? dir24_8_lookup_bulk_1_be :
+					dir24_8_lookup_bulk_1;
 	case RTE_FIB_DIR24_8_4B:
-		return dir24_8_lookup_bulk_2;
+		return (be_addr) ? dir24_8_lookup_bulk_2_be :
+					dir24_8_lookup_bulk_2;
 	case RTE_FIB_DIR24_8_8B:
-		return dir24_8_lookup_bulk_3;
+		return (be_addr) ? dir24_8_lookup_bulk_3_be :
+					dir24_8_lookup_bulk_3;
 	default:
 		return NULL;
 	}
 }
 
 static inline rte_fib_lookup_fn_t
-get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 #ifdef CC_DIR24_8_AVX512_SUPPORT
 	if ((rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) <= 0) ||
+		(rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512DQ) <= 0) ||
 			(rte_vect_get_max_simd_bitwidth() < RTE_VECT_SIMD_512))
 		return NULL;
 
+	if (be_addr && (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512BW) <= 0))
+		return NULL;
+
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return rte_dir24_8_vec_lookup_bulk_1b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_1b_be :
+					rte_dir24_8_vec_lookup_bulk_1b;
 	case RTE_FIB_DIR24_8_2B:
-		return rte_dir24_8_vec_lookup_bulk_2b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_2b_be :
+					rte_dir24_8_vec_lookup_bulk_2b;
 	case RTE_FIB_DIR24_8_4B:
-		return rte_dir24_8_vec_lookup_bulk_4b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_4b_be :
+					rte_dir24_8_vec_lookup_bulk_4b;
 	case RTE_FIB_DIR24_8_8B:
-		return rte_dir24_8_vec_lookup_bulk_8b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_8b_be :
+					rte_dir24_8_vec_lookup_bulk_8b;
 	default:
 		return NULL;
 	}
@@ -86,7 +102,7 @@ get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
 }
 
 rte_fib_lookup_fn_t
-dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type)
+dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type, bool be_addr)
 {
 	enum rte_fib_dir24_8_nh_sz nh_sz;
 	rte_fib_lookup_fn_t ret_fn;
@@ -99,16 +115,18 @@ dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type)
 
 	switch (type) {
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_MACRO:
-		return get_scalar_fn(nh_sz);
+		return get_scalar_fn(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_INLINE:
-		return get_scalar_fn_inlined(nh_sz);
+		return get_scalar_fn_inlined(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_UNI:
-		return dir24_8_lookup_bulk_uni;
+		return (be_addr) ? dir24_8_lookup_bulk_uni_be :
+						dir24_8_lookup_bulk_uni;
 	case RTE_FIB_LOOKUP_DIR24_8_VECTOR_AVX512:
-		return get_vector_fn(nh_sz);
+		return get_vector_fn(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DEFAULT:
-		ret_fn = get_vector_fn(nh_sz);
-		return (ret_fn != NULL) ? ret_fn : get_scalar_fn(nh_sz);
+		ret_fn = get_vector_fn(nh_sz, be_addr);
+		return (ret_fn != NULL) ? ret_fn :
+			get_scalar_fn(nh_sz, be_addr);
 	default:
 		return NULL;
 	}
diff --git a/lib/fib/dir24_8.h b/lib/fib/dir24_8.h
index 7125049f15..2c776e118f 100644
--- a/lib/fib/dir24_8.h
+++ b/lib/fib/dir24_8.h
@@ -7,7 +7,9 @@
 #define _DIR24_8_H_
 
 #include <stdalign.h>
+#include <stdbool.h>
 
+#include <rte_byteorder.h>
 #include <rte_prefetch.h>
 #include <rte_branch_prediction.h>
 
@@ -237,6 +239,46 @@ dir24_8_lookup_bulk_uni(void *p, const uint32_t *ips,
 	}
 }
 
+#define BSWAP_MAX_LENGTH	64
+
+typedef void (*dir24_8_lookup_bulk_be_cb)(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+static inline void
+dir24_8_lookup_bulk_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n,
+	dir24_8_lookup_bulk_be_cb cb)
+{
+	uint32_t le_ips[BSWAP_MAX_LENGTH];
+	unsigned int i;
+
+	for (i = 0; i < n; i += BSWAP_MAX_LENGTH) {
+		int j;
+		for (j = 0; j < BSWAP_MAX_LENGTH && i + j < n; j++)
+			le_ips[j] = rte_be_to_cpu_32(ips[i + j]);
+
+		cb(p, le_ips, next_hops + i, j);
+	}
+}
+
+#define DECLARE_BE_LOOKUP_FN(name)					\
+static inline void							\
+name##_be(void *p, const uint32_t *ips,					\
+	uint64_t *next_hops, const unsigned int n)			\
+{									\
+	dir24_8_lookup_bulk_be(p, ips, next_hops, n, name);		\
+}
+
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_1b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_2b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_4b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_8b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_0)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_1)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_2)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_3)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_uni)
+
 void *
 dir24_8_create(const char *name, int socket_id, struct rte_fib_conf *conf);
 
@@ -244,7 +286,7 @@ void
 dir24_8_free(void *p);
 
 rte_fib_lookup_fn_t
-dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type);
+dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type, bool be_addr);
 
 int
 dir24_8_modify(struct rte_fib *fib, uint32_t ip, uint8_t depth,
diff --git a/lib/fib/dir24_8_avx512.c b/lib/fib/dir24_8_avx512.c
index 43dba28cfb..edd802abe4 100644
--- a/lib/fib/dir24_8_avx512.c
+++ b/lib/fib/dir24_8_avx512.c
@@ -10,7 +10,7 @@
 
 static __rte_always_inline void
 dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
-	uint64_t *next_hops, int size)
+	uint64_t *next_hops, int size, bool be_addr)
 {
 	struct dir24_8_tbl *dp = (struct dir24_8_tbl *)p;
 	__mmask16 msk_ext;
@@ -28,6 +28,16 @@ dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
 		res_msk = _mm512_set1_epi32(UINT16_MAX);
 
 	ip_vec = _mm512_loadu_si512(ips);
+	if (be_addr) {
+		const __m512i bswap32 = _mm512_set_epi8(
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3
+		);
+		ip_vec = _mm512_shuffle_epi8(ip_vec, bswap32);
+	}
+
 	/* mask 24 most significant bits */
 	idxes = _mm512_srli_epi32(ip_vec, 8);
 
@@ -78,7 +88,7 @@ dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
 
 static __rte_always_inline void
 dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
-	uint64_t *next_hops)
+	uint64_t *next_hops, bool be_addr)
 {
 	struct dir24_8_tbl *dp = (struct dir24_8_tbl *)p;
 	const __m512i zero = _mm512_set1_epi32(0);
@@ -89,6 +99,13 @@ dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
 	__mmask8 msk_ext;
 
 	ip_vec = _mm256_loadu_si256((const void *)ips);
+	if (be_addr) {
+		const __m256i bswap32 = _mm256_set_epi8(
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3
+		);
+		ip_vec = _mm256_shuffle_epi8(ip_vec, bswap32);
+	}
 	/* mask 24 most significant bits */
 	idxes_256 = _mm256_srli_epi32(ip_vec, 8);
 
@@ -114,52 +131,49 @@ dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
 	_mm512_storeu_si512(next_hops, res);
 }
 
-void
-rte_dir24_8_vec_lookup_bulk_1b(void *p, const uint32_t *ips,
-	uint64_t *next_hops, const unsigned int n)
-{
-	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint8_t));
-
-	dir24_8_lookup_bulk_1b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
+#define DECLARE_VECTOR_FN(suffix, nh_type, be_addr)			\
+void									\
+rte_dir24_8_vec_lookup_bulk_##suffix(void *p, const uint32_t *ips,	\
+	uint64_t *next_hops, const unsigned int n)			\
+{									\
+	uint32_t i;							\
+									\
+	for (i = 0; i < (n / 16); i++)					\
+		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16, \
+			sizeof(nh_type), be_addr);			\
+									\
+	dir24_8_lookup_bulk_##suffix(p, ips + i * 16, next_hops + i * 16, \
+		n - i * 16);						\
 }
 
-void
-rte_dir24_8_vec_lookup_bulk_2b(void *p, const uint32_t *ips,
-	uint64_t *next_hops, const unsigned int n)
-{
-	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint16_t));
-
-	dir24_8_lookup_bulk_2b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
-}
+DECLARE_VECTOR_FN(1b, uint8_t, false)
+DECLARE_VECTOR_FN(2b, uint16_t, false)
+DECLARE_VECTOR_FN(4b, uint32_t, false)
+DECLARE_VECTOR_FN(1b_be, uint8_t, true)
+DECLARE_VECTOR_FN(2b_be, uint16_t, true)
+DECLARE_VECTOR_FN(4b_be, uint32_t, true)
 
 void
-rte_dir24_8_vec_lookup_bulk_4b(void *p, const uint32_t *ips,
+rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n)
 {
 	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint32_t));
+	for (i = 0; i < (n / 8); i++)
+		dir24_8_vec_lookup_x8_8b(p, ips + i * 8,
+			next_hops + i * 8, false);
 
-	dir24_8_lookup_bulk_4b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
+	dir24_8_lookup_bulk_8b(p, ips + i * 8, next_hops + i * 8, n - i * 8);
 }
 
 void
-rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
+rte_dir24_8_vec_lookup_bulk_8b_be(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n)
 {
 	uint32_t i;
 	for (i = 0; i < (n / 8); i++)
-		dir24_8_vec_lookup_x8_8b(p, ips + i * 8, next_hops + i * 8);
+		dir24_8_vec_lookup_x8_8b(p, ips + i * 8,
+			next_hops + i * 8, true);
 
-	dir24_8_lookup_bulk_8b(p, ips + i * 8, next_hops + i * 8, n - i * 8);
+	dir24_8_lookup_bulk_8b_be(p, ips + i * 8,
+		next_hops + i * 8, n - i * 8);
 }
diff --git a/lib/fib/dir24_8_avx512.h b/lib/fib/dir24_8_avx512.h
index 1d3c2b9317..e9f7b72519 100644
--- a/lib/fib/dir24_8_avx512.h
+++ b/lib/fib/dir24_8_avx512.h
@@ -21,4 +21,19 @@ void
 rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n);
 
+void
+rte_dir24_8_vec_lookup_bulk_1b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_2b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_4b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_8b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
 #endif /* _DIR248_AVX512_H_ */
diff --git a/lib/fib/meson.build b/lib/fib/meson.build
index 6795f41a0a..8c03496cdc 100644
--- a/lib/fib/meson.build
+++ b/lib/fib/meson.build
@@ -25,40 +25,28 @@ if dpdk_conf.has('RTE_ARCH_X86_64') and binutils_ok
     # linked into main lib.
 
     # check if all required flags already enabled (variant a).
-    acl_avx512_flags = ['__AVX512F__','__AVX512DQ__']
-    acl_avx512_on = true
-    foreach f:acl_avx512_flags
+    fib_avx512_flags = ['__AVX512F__','__AVX512DQ__', '__AVX512BW__']
+    fib_avx512_on = true
+    foreach f:fib_avx512_flags
         if cc.get_define(f, args: machine_args) == ''
-            acl_avx512_on = false
+            fib_avx512_on = false
         endif
     endforeach
 
-    if acl_avx512_on == true
-        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT']
-        sources += files('dir24_8_avx512.c')
-        # TRIE AVX512 implementation uses avx512bw intrinsics along with
-        # avx512f and avx512dq
-        if cc.get_define('__AVX512BW__', args: machine_args) != ''
-            cflags += ['-DCC_TRIE_AVX512_SUPPORT']
-            sources += files('trie_avx512.c')
-        endif
-    elif cc.has_multi_arguments('-mavx512f', '-mavx512dq')
+    if fib_avx512_on == true
+        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT', '-DCC_TRIE_AVX512_SUPPORT']
+        sources += files('dir24_8_avx512.c', 'trie_avx512.c')
+    elif cc.has_multi_arguments('-mavx512f', '-mavx512dq', '-mavx512bw')
         dir24_8_avx512_tmp = static_library('dir24_8_avx512_tmp',
                 'dir24_8_avx512.c',
                 dependencies: static_rte_eal,
-                c_args: cflags + ['-mavx512f', '-mavx512dq'])
+                c_args: cflags + ['-mavx512f', '-mavx512dq', '-mavx512bw'])
         objs += dir24_8_avx512_tmp.extract_objects('dir24_8_avx512.c')
-        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT']
-        # TRIE AVX512 implementation uses avx512bw intrinsics along with
-        # avx512f and avx512dq
-        if cc.has_argument('-mavx512bw')
-            trie_avx512_tmp = static_library('trie_avx512_tmp',
+        trie_avx512_tmp = static_library('trie_avx512_tmp',
                 'trie_avx512.c',
                 dependencies: static_rte_eal,
-                c_args: cflags + ['-mavx512f', \
-                    '-mavx512dq', '-mavx512bw'])
-            objs += trie_avx512_tmp.extract_objects('trie_avx512.c')
-            cflags += ['-DCC_TRIE_AVX512_SUPPORT']
-        endif
+                c_args: cflags + ['-mavx512f', '-mavx512dq', '-mavx512bw'])
+        objs += trie_avx512_tmp.extract_objects('trie_avx512.c')
+        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT', '-DCC_TRIE_AVX512_SUPPORT']
     endif
 endif
diff --git a/lib/fib/rte_fib.c b/lib/fib/rte_fib.c
index 4f9fba5a4f..991e48b5ea 100644
--- a/lib/fib/rte_fib.c
+++ b/lib/fib/rte_fib.c
@@ -42,6 +42,7 @@ EAL_REGISTER_TAILQ(rte_fib_tailq)
 struct rte_fib {
 	char			name[RTE_FIB_NAMESIZE];
 	enum rte_fib_type	type;	/**< Type of FIB struct */
+	int flags;					/**< Flags */
 	struct rte_rib		*rib;	/**< RIB helper datastructure */
 	void			*dp;	/**< pointer to the dataplane struct*/
 	rte_fib_lookup_fn_t	lookup;	/**< FIB lookup function */
@@ -110,7 +111,7 @@ init_dataplane(struct rte_fib *fib, __rte_unused int socket_id,
 		if (fib->dp == NULL)
 			return -rte_errno;
 		fib->lookup = dir24_8_get_lookup_fn(fib->dp,
-			RTE_FIB_LOOKUP_DEFAULT);
+			RTE_FIB_LOOKUP_DEFAULT, !!(fib->flags & RTE_FIB_FLAG_LOOKUP_BE));
 		fib->modify = dir24_8_modify;
 		return 0;
 	default:
@@ -214,6 +215,7 @@ rte_fib_create(const char *name, int socket_id, struct rte_fib_conf *conf)
 	rte_strlcpy(fib->name, name, sizeof(fib->name));
 	fib->rib = rib;
 	fib->type = conf->type;
+	fib->flags = conf->flags;
 	fib->def_nh = conf->default_nh;
 	ret = init_dataplane(fib, socket_id, conf);
 	if (ret < 0) {
@@ -329,7 +331,8 @@ rte_fib_select_lookup(struct rte_fib *fib,
 
 	switch (fib->type) {
 	case RTE_FIB_DIR24_8:
-		fn = dir24_8_get_lookup_fn(fib->dp, type);
+		fn = dir24_8_get_lookup_fn(fib->dp, type,
+			!!(fib->flags & RTE_FIB_FLAG_LOOKUP_BE));
 		if (fn == NULL)
 			return -EINVAL;
 		fib->lookup = fn;
diff --git a/lib/fib/rte_fib.h b/lib/fib/rte_fib.h
index d7a5aafe53..1617235e85 100644
--- a/lib/fib/rte_fib.h
+++ b/lib/fib/rte_fib.h
@@ -28,6 +28,9 @@ struct rte_rib;
 /** Maximum depth value possible for IPv4 FIB. */
 #define RTE_FIB_MAXDEPTH	32
 
+/** If set fib lookup is expecting ipv4 in network byte order */
+#define RTE_FIB_FLAG_LOOKUP_BE	1
+
 /** Type of FIB struct */
 enum rte_fib_type {
 	RTE_FIB_DUMMY,		/**< RIB tree based FIB */
@@ -76,6 +79,7 @@ enum rte_fib_lookup_type {
 /** FIB configuration structure */
 struct rte_fib_conf {
 	enum rte_fib_type type; /**< Type of FIB struct */
+	unsigned int flags;
 	/** Default value returned on lookup if there is no route */
 	uint64_t default_nh;
 	int	max_routes;
-- 
2.34.1

[PATCH v3] fib: network byte order IPv4 lookup

[Vladimir Medvedkin]

Previously when running rte_fib_lookup IPv4 addresses must have been in
host byte order.

This patch adds a new flag RTE_FIB_FLAG_LOOKUP_BE that can be passed on
fib create, which will allow to have IPv4 in network byte order on
lookup.

Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
---
 app/test/test_fib.c      |  2 +-
 lib/fib/dir24_8.c        | 63 +++++++++++++++++++-----------
 lib/fib/dir24_8.h        | 44 ++++++++++++++++++++-
 lib/fib/dir24_8_avx512.c | 82 +++++++++++++++++++++++-----------------
 lib/fib/dir24_8_avx512.h | 15 ++++++++
 lib/fib/meson.build      | 38 +++++++------------
 lib/fib/rte_fib.c        |  7 +++-
 lib/fib/rte_fib.h        |  4 ++
 8 files changed, 170 insertions(+), 85 deletions(-)

diff --git a/app/test/test_fib.c b/app/test/test_fib.c
index 45dccca1f6..b0e53dbe01 100644
--- a/app/test/test_fib.c
+++ b/app/test/test_fib.c
@@ -319,7 +319,7 @@ int32_t
 test_lookup(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 	uint64_t def_nh = 100;
 	int ret;
 
diff --git a/lib/fib/dir24_8.c b/lib/fib/dir24_8.c
index c739e92304..5c856ff6a6 100644
--- a/lib/fib/dir24_8.c
+++ b/lib/fib/dir24_8.c
@@ -26,67 +26,84 @@
 #define ROUNDUP(x, y)	 RTE_ALIGN_CEIL(x, (1 << (32 - y)))
 
 static inline rte_fib_lookup_fn_t
-get_scalar_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_scalar_fn(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return dir24_8_lookup_bulk_1b;
+		return (be_addr) ? dir24_8_lookup_bulk_1b_be :
+					dir24_8_lookup_bulk_1b;
 	case RTE_FIB_DIR24_8_2B:
-		return dir24_8_lookup_bulk_2b;
+		return (be_addr) ? dir24_8_lookup_bulk_2b_be :
+					dir24_8_lookup_bulk_2b;
 	case RTE_FIB_DIR24_8_4B:
-		return dir24_8_lookup_bulk_4b;
+		return (be_addr) ? dir24_8_lookup_bulk_4b_be :
+					dir24_8_lookup_bulk_4b;
 	case RTE_FIB_DIR24_8_8B:
-		return dir24_8_lookup_bulk_8b;
+		return (be_addr) ? dir24_8_lookup_bulk_8b_be :
+					dir24_8_lookup_bulk_8b;
 	default:
 		return NULL;
 	}
 }
 
 static inline rte_fib_lookup_fn_t
-get_scalar_fn_inlined(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_scalar_fn_inlined(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return dir24_8_lookup_bulk_0;
+		return (be_addr) ? dir24_8_lookup_bulk_0_be :
+					dir24_8_lookup_bulk_0;
 	case RTE_FIB_DIR24_8_2B:
-		return dir24_8_lookup_bulk_1;
+		return (be_addr) ? dir24_8_lookup_bulk_1_be :
+					dir24_8_lookup_bulk_1;
 	case RTE_FIB_DIR24_8_4B:
-		return dir24_8_lookup_bulk_2;
+		return (be_addr) ? dir24_8_lookup_bulk_2_be :
+					dir24_8_lookup_bulk_2;
 	case RTE_FIB_DIR24_8_8B:
-		return dir24_8_lookup_bulk_3;
+		return (be_addr) ? dir24_8_lookup_bulk_3_be :
+					dir24_8_lookup_bulk_3;
 	default:
 		return NULL;
 	}
 }
 
 static inline rte_fib_lookup_fn_t
-get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 #ifdef CC_DIR24_8_AVX512_SUPPORT
 	if ((rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) <= 0) ||
+		(rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512DQ) <= 0) ||
 			(rte_vect_get_max_simd_bitwidth() < RTE_VECT_SIMD_512))
 		return NULL;
 
+	if (be_addr && (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512BW) <= 0))
+		return NULL;
+
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return rte_dir24_8_vec_lookup_bulk_1b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_1b_be :
+					rte_dir24_8_vec_lookup_bulk_1b;
 	case RTE_FIB_DIR24_8_2B:
-		return rte_dir24_8_vec_lookup_bulk_2b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_2b_be :
+					rte_dir24_8_vec_lookup_bulk_2b;
 	case RTE_FIB_DIR24_8_4B:
-		return rte_dir24_8_vec_lookup_bulk_4b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_4b_be :
+					rte_dir24_8_vec_lookup_bulk_4b;
 	case RTE_FIB_DIR24_8_8B:
-		return rte_dir24_8_vec_lookup_bulk_8b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_8b_be :
+					rte_dir24_8_vec_lookup_bulk_8b;
 	default:
 		return NULL;
 	}
 #else
 	RTE_SET_USED(nh_sz);
+	RTE_SET_USED(be_addr);
 #endif
 	return NULL;
 }
 
 rte_fib_lookup_fn_t
-dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type)
+dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type, bool be_addr)
 {
 	enum rte_fib_dir24_8_nh_sz nh_sz;
 	rte_fib_lookup_fn_t ret_fn;
@@ -99,16 +116,18 @@ dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type)
 
 	switch (type) {
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_MACRO:
-		return get_scalar_fn(nh_sz);
+		return get_scalar_fn(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_INLINE:
-		return get_scalar_fn_inlined(nh_sz);
+		return get_scalar_fn_inlined(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_UNI:
-		return dir24_8_lookup_bulk_uni;
+		return (be_addr) ? dir24_8_lookup_bulk_uni_be :
+						dir24_8_lookup_bulk_uni;
 	case RTE_FIB_LOOKUP_DIR24_8_VECTOR_AVX512:
-		return get_vector_fn(nh_sz);
+		return get_vector_fn(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DEFAULT:
-		ret_fn = get_vector_fn(nh_sz);
-		return (ret_fn != NULL) ? ret_fn : get_scalar_fn(nh_sz);
+		ret_fn = get_vector_fn(nh_sz, be_addr);
+		return (ret_fn != NULL) ? ret_fn :
+			get_scalar_fn(nh_sz, be_addr);
 	default:
 		return NULL;
 	}
diff --git a/lib/fib/dir24_8.h b/lib/fib/dir24_8.h
index 7125049f15..2c776e118f 100644
--- a/lib/fib/dir24_8.h
+++ b/lib/fib/dir24_8.h
@@ -7,7 +7,9 @@
 #define _DIR24_8_H_
 
 #include <stdalign.h>
+#include <stdbool.h>
 
+#include <rte_byteorder.h>
 #include <rte_prefetch.h>
 #include <rte_branch_prediction.h>
 
@@ -237,6 +239,46 @@ dir24_8_lookup_bulk_uni(void *p, const uint32_t *ips,
 	}
 }
 
+#define BSWAP_MAX_LENGTH	64
+
+typedef void (*dir24_8_lookup_bulk_be_cb)(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+static inline void
+dir24_8_lookup_bulk_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n,
+	dir24_8_lookup_bulk_be_cb cb)
+{
+	uint32_t le_ips[BSWAP_MAX_LENGTH];
+	unsigned int i;
+
+	for (i = 0; i < n; i += BSWAP_MAX_LENGTH) {
+		int j;
+		for (j = 0; j < BSWAP_MAX_LENGTH && i + j < n; j++)
+			le_ips[j] = rte_be_to_cpu_32(ips[i + j]);
+
+		cb(p, le_ips, next_hops + i, j);
+	}
+}
+
+#define DECLARE_BE_LOOKUP_FN(name)					\
+static inline void							\
+name##_be(void *p, const uint32_t *ips,					\
+	uint64_t *next_hops, const unsigned int n)			\
+{									\
+	dir24_8_lookup_bulk_be(p, ips, next_hops, n, name);		\
+}
+
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_1b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_2b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_4b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_8b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_0)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_1)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_2)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_3)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_uni)
+
 void *
 dir24_8_create(const char *name, int socket_id, struct rte_fib_conf *conf);
 
@@ -244,7 +286,7 @@ void
 dir24_8_free(void *p);
 
 rte_fib_lookup_fn_t
-dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type);
+dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type, bool be_addr);
 
 int
 dir24_8_modify(struct rte_fib *fib, uint32_t ip, uint8_t depth,
diff --git a/lib/fib/dir24_8_avx512.c b/lib/fib/dir24_8_avx512.c
index 43dba28cfb..e6fe08ecfe 100644
--- a/lib/fib/dir24_8_avx512.c
+++ b/lib/fib/dir24_8_avx512.c
@@ -10,7 +10,7 @@
 
 static __rte_always_inline void
 dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
-	uint64_t *next_hops, int size)
+	uint64_t *next_hops, int size, bool be_addr)
 {
 	struct dir24_8_tbl *dp = (struct dir24_8_tbl *)p;
 	__mmask16 msk_ext;
@@ -28,6 +28,16 @@ dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
 		res_msk = _mm512_set1_epi32(UINT16_MAX);
 
 	ip_vec = _mm512_loadu_si512(ips);
+	if (be_addr) {
+		const __m512i bswap32 = _mm512_set_epi32(
+			0x0c0d0e0f, 0x08090a0b, 0x04050607, 0x00010203,
+			0x0c0d0e0f, 0x08090a0b, 0x04050607, 0x00010203,
+			0x0c0d0e0f, 0x08090a0b, 0x04050607, 0x00010203,
+			0x0c0d0e0f, 0x08090a0b, 0x04050607, 0x00010203
+		);
+		ip_vec = _mm512_shuffle_epi8(ip_vec, bswap32);
+	}
+
 	/* mask 24 most significant bits */
 	idxes = _mm512_srli_epi32(ip_vec, 8);
 
@@ -78,7 +88,7 @@ dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
 
 static __rte_always_inline void
 dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
-	uint64_t *next_hops)
+	uint64_t *next_hops, bool be_addr)
 {
 	struct dir24_8_tbl *dp = (struct dir24_8_tbl *)p;
 	const __m512i zero = _mm512_set1_epi32(0);
@@ -89,6 +99,13 @@ dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
 	__mmask8 msk_ext;
 
 	ip_vec = _mm256_loadu_si256((const void *)ips);
+	if (be_addr) {
+		const __m256i bswap32 = _mm256_set_epi8(
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3
+		);
+		ip_vec = _mm256_shuffle_epi8(ip_vec, bswap32);
+	}
 	/* mask 24 most significant bits */
 	idxes_256 = _mm256_srli_epi32(ip_vec, 8);
 
@@ -114,52 +131,49 @@ dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
 	_mm512_storeu_si512(next_hops, res);
 }
 
-void
-rte_dir24_8_vec_lookup_bulk_1b(void *p, const uint32_t *ips,
-	uint64_t *next_hops, const unsigned int n)
-{
-	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint8_t));
-
-	dir24_8_lookup_bulk_1b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
+#define DECLARE_VECTOR_FN(suffix, nh_type, be_addr)			\
+void									\
+rte_dir24_8_vec_lookup_bulk_##suffix(void *p, const uint32_t *ips,	\
+	uint64_t *next_hops, const unsigned int n)			\
+{									\
+	uint32_t i;							\
+									\
+	for (i = 0; i < (n / 16); i++)					\
+		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16, \
+			sizeof(nh_type), be_addr);			\
+									\
+	dir24_8_lookup_bulk_##suffix(p, ips + i * 16, next_hops + i * 16, \
+		n - i * 16);						\
 }
 
-void
-rte_dir24_8_vec_lookup_bulk_2b(void *p, const uint32_t *ips,
-	uint64_t *next_hops, const unsigned int n)
-{
-	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint16_t));
-
-	dir24_8_lookup_bulk_2b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
-}
+DECLARE_VECTOR_FN(1b, uint8_t, false)
+DECLARE_VECTOR_FN(2b, uint16_t, false)
+DECLARE_VECTOR_FN(4b, uint32_t, false)
+DECLARE_VECTOR_FN(1b_be, uint8_t, true)
+DECLARE_VECTOR_FN(2b_be, uint16_t, true)
+DECLARE_VECTOR_FN(4b_be, uint32_t, true)
 
 void
-rte_dir24_8_vec_lookup_bulk_4b(void *p, const uint32_t *ips,
+rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n)
 {
 	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint32_t));
+	for (i = 0; i < (n / 8); i++)
+		dir24_8_vec_lookup_x8_8b(p, ips + i * 8,
+			next_hops + i * 8, false);
 
-	dir24_8_lookup_bulk_4b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
+	dir24_8_lookup_bulk_8b(p, ips + i * 8, next_hops + i * 8, n - i * 8);
 }
 
 void
-rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
+rte_dir24_8_vec_lookup_bulk_8b_be(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n)
 {
 	uint32_t i;
 	for (i = 0; i < (n / 8); i++)
-		dir24_8_vec_lookup_x8_8b(p, ips + i * 8, next_hops + i * 8);
+		dir24_8_vec_lookup_x8_8b(p, ips + i * 8,
+			next_hops + i * 8, true);
 
-	dir24_8_lookup_bulk_8b(p, ips + i * 8, next_hops + i * 8, n - i * 8);
+	dir24_8_lookup_bulk_8b_be(p, ips + i * 8,
+		next_hops + i * 8, n - i * 8);
 }
diff --git a/lib/fib/dir24_8_avx512.h b/lib/fib/dir24_8_avx512.h
index 1d3c2b9317..e9f7b72519 100644
--- a/lib/fib/dir24_8_avx512.h
+++ b/lib/fib/dir24_8_avx512.h
@@ -21,4 +21,19 @@ void
 rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n);
 
+void
+rte_dir24_8_vec_lookup_bulk_1b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_2b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_4b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_8b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
 #endif /* _DIR248_AVX512_H_ */
diff --git a/lib/fib/meson.build b/lib/fib/meson.build
index 6795f41a0a..8c03496cdc 100644
--- a/lib/fib/meson.build
+++ b/lib/fib/meson.build
@@ -25,40 +25,28 @@ if dpdk_conf.has('RTE_ARCH_X86_64') and binutils_ok
     # linked into main lib.
 
     # check if all required flags already enabled (variant a).
-    acl_avx512_flags = ['__AVX512F__','__AVX512DQ__']
-    acl_avx512_on = true
-    foreach f:acl_avx512_flags
+    fib_avx512_flags = ['__AVX512F__','__AVX512DQ__', '__AVX512BW__']
+    fib_avx512_on = true
+    foreach f:fib_avx512_flags
         if cc.get_define(f, args: machine_args) == ''
-            acl_avx512_on = false
+            fib_avx512_on = false
         endif
     endforeach
 
-    if acl_avx512_on == true
-        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT']
-        sources += files('dir24_8_avx512.c')
-        # TRIE AVX512 implementation uses avx512bw intrinsics along with
-        # avx512f and avx512dq
-        if cc.get_define('__AVX512BW__', args: machine_args) != ''
-            cflags += ['-DCC_TRIE_AVX512_SUPPORT']
-            sources += files('trie_avx512.c')
-        endif
-    elif cc.has_multi_arguments('-mavx512f', '-mavx512dq')
+    if fib_avx512_on == true
+        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT', '-DCC_TRIE_AVX512_SUPPORT']
+        sources += files('dir24_8_avx512.c', 'trie_avx512.c')
+    elif cc.has_multi_arguments('-mavx512f', '-mavx512dq', '-mavx512bw')
         dir24_8_avx512_tmp = static_library('dir24_8_avx512_tmp',
                 'dir24_8_avx512.c',
                 dependencies: static_rte_eal,
-                c_args: cflags + ['-mavx512f', '-mavx512dq'])
+                c_args: cflags + ['-mavx512f', '-mavx512dq', '-mavx512bw'])
         objs += dir24_8_avx512_tmp.extract_objects('dir24_8_avx512.c')
-        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT']
-        # TRIE AVX512 implementation uses avx512bw intrinsics along with
-        # avx512f and avx512dq
-        if cc.has_argument('-mavx512bw')
-            trie_avx512_tmp = static_library('trie_avx512_tmp',
+        trie_avx512_tmp = static_library('trie_avx512_tmp',
                 'trie_avx512.c',
                 dependencies: static_rte_eal,
-                c_args: cflags + ['-mavx512f', \
-                    '-mavx512dq', '-mavx512bw'])
-            objs += trie_avx512_tmp.extract_objects('trie_avx512.c')
-            cflags += ['-DCC_TRIE_AVX512_SUPPORT']
-        endif
+                c_args: cflags + ['-mavx512f', '-mavx512dq', '-mavx512bw'])
+        objs += trie_avx512_tmp.extract_objects('trie_avx512.c')
+        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT', '-DCC_TRIE_AVX512_SUPPORT']
     endif
 endif
diff --git a/lib/fib/rte_fib.c b/lib/fib/rte_fib.c
index 4f9fba5a4f..991e48b5ea 100644
--- a/lib/fib/rte_fib.c
+++ b/lib/fib/rte_fib.c
@@ -42,6 +42,7 @@ EAL_REGISTER_TAILQ(rte_fib_tailq)
 struct rte_fib {
 	char			name[RTE_FIB_NAMESIZE];
 	enum rte_fib_type	type;	/**< Type of FIB struct */
+	int flags;					/**< Flags */
 	struct rte_rib		*rib;	/**< RIB helper datastructure */
 	void			*dp;	/**< pointer to the dataplane struct*/
 	rte_fib_lookup_fn_t	lookup;	/**< FIB lookup function */
@@ -110,7 +111,7 @@ init_dataplane(struct rte_fib *fib, __rte_unused int socket_id,
 		if (fib->dp == NULL)
 			return -rte_errno;
 		fib->lookup = dir24_8_get_lookup_fn(fib->dp,
-			RTE_FIB_LOOKUP_DEFAULT);
+			RTE_FIB_LOOKUP_DEFAULT, !!(fib->flags & RTE_FIB_FLAG_LOOKUP_BE));
 		fib->modify = dir24_8_modify;
 		return 0;
 	default:
@@ -214,6 +215,7 @@ rte_fib_create(const char *name, int socket_id, struct rte_fib_conf *conf)
 	rte_strlcpy(fib->name, name, sizeof(fib->name));
 	fib->rib = rib;
 	fib->type = conf->type;
+	fib->flags = conf->flags;
 	fib->def_nh = conf->default_nh;
 	ret = init_dataplane(fib, socket_id, conf);
 	if (ret < 0) {
@@ -329,7 +331,8 @@ rte_fib_select_lookup(struct rte_fib *fib,
 
 	switch (fib->type) {
 	case RTE_FIB_DIR24_8:
-		fn = dir24_8_get_lookup_fn(fib->dp, type);
+		fn = dir24_8_get_lookup_fn(fib->dp, type,
+			!!(fib->flags & RTE_FIB_FLAG_LOOKUP_BE));
 		if (fn == NULL)
 			return -EINVAL;
 		fib->lookup = fn;
diff --git a/lib/fib/rte_fib.h b/lib/fib/rte_fib.h
index d7a5aafe53..1617235e85 100644
--- a/lib/fib/rte_fib.h
+++ b/lib/fib/rte_fib.h
@@ -28,6 +28,9 @@ struct rte_rib;
 /** Maximum depth value possible for IPv4 FIB. */
 #define RTE_FIB_MAXDEPTH	32
 
+/** If set fib lookup is expecting ipv4 in network byte order */
+#define RTE_FIB_FLAG_LOOKUP_BE	1
+
 /** Type of FIB struct */
 enum rte_fib_type {
 	RTE_FIB_DUMMY,		/**< RIB tree based FIB */
@@ -76,6 +79,7 @@ enum rte_fib_lookup_type {
 /** FIB configuration structure */
 struct rte_fib_conf {
 	enum rte_fib_type type; /**< Type of FIB struct */
+	unsigned int flags;
 	/** Default value returned on lookup if there is no route */
 	uint64_t default_nh;
 	int	max_routes;
-- 
2.34.1

Re: [PATCH v3] fib: network byte order IPv4 lookup

[Robin Jarry]

Hi Vladimir,

Vladimir Medvedkin, Oct 10, 2024 at 13:26:
> Previously when running rte_fib_lookup IPv4 addresses must have been in
> host byte order.
>
> This patch adds a new flag RTE_FIB_FLAG_LOOKUP_BE that can be passed on
> fib create, which will allow to have IPv4 in network byte order on
> lookup.
>
> Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>

[snip]

> diff --git a/lib/fib/dir24_8.h b/lib/fib/dir24_8.h
> index 7125049f15..2c776e118f 100644
> --- a/lib/fib/dir24_8.h
> +++ b/lib/fib/dir24_8.h
> @@ -7,7 +7,9 @@
>  #define _DIR24_8_H_
>  
>  #include <stdalign.h>
> +#include <stdbool.h>
>  
> +#include <rte_byteorder.h>
>  #include <rte_prefetch.h>
>  #include <rte_branch_prediction.h>
>  
> @@ -237,6 +239,46 @@ dir24_8_lookup_bulk_uni(void *p, const uint32_t *ips,
>  	}
>  }
>  
> +#define BSWAP_MAX_LENGTH	64
> +
> +typedef void (*dir24_8_lookup_bulk_be_cb)(void *p, const uint32_t *ips,
> +	uint64_t *next_hops, const unsigned int n);
> +
> +static inline void
> +dir24_8_lookup_bulk_be(void *p, const uint32_t *ips,
> +	uint64_t *next_hops, const unsigned int n,
> +	dir24_8_lookup_bulk_be_cb cb)
> +{
> +	uint32_t le_ips[BSWAP_MAX_LENGTH];
> +	unsigned int i;
> +
> +	for (i = 0; i < n; i += BSWAP_MAX_LENGTH) {
> +		int j;
> +		for (j = 0; j < BSWAP_MAX_LENGTH && i + j < n; j++)
> +			le_ips[j] = rte_be_to_cpu_32(ips[i + j]);
> +
> +		cb(p, le_ips, next_hops + i, j);
> +	}

This should be a noop for big endian platforms. I'm not sure the 
complier will be smart enough to collapse the nested loops.

> +}
> +
> +#define DECLARE_BE_LOOKUP_FN(name)					\
> +static inline void							\
> +name##_be(void *p, const uint32_t *ips,					\
> +	uint64_t *next_hops, const unsigned int n)			\
> +{									\
> +	dir24_8_lookup_bulk_be(p, ips, next_hops, n, name);		\
> +}
> +
> +DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_1b)
> +DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_2b)
> +DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_4b)
> +DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_8b)
> +DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_0)
> +DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_1)
> +DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_2)
> +DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_3)
> +DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_uni)
> +
>  void *
>  dir24_8_create(const char *name, int socket_id, struct rte_fib_conf *conf);
>  
> @@ -244,7 +286,7 @@ void
>  dir24_8_free(void *p);
>  
>  rte_fib_lookup_fn_t
> -dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type);
> +dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type, bool be_addr);
>  
>  int
>  dir24_8_modify(struct rte_fib *fib, uint32_t ip, uint8_t depth,

[snip]

> diff --git a/lib/fib/rte_fib.h b/lib/fib/rte_fib.h
> index d7a5aafe53..1617235e85 100644
> --- a/lib/fib/rte_fib.h
> +++ b/lib/fib/rte_fib.h
> @@ -28,6 +28,9 @@ struct rte_rib;
>  /** Maximum depth value possible for IPv4 FIB. */
>  #define RTE_FIB_MAXDEPTH	32
>  
> +/** If set fib lookup is expecting ipv4 in network byte order */
> +#define RTE_FIB_FLAG_LOOKUP_BE	1

I think RTE_FIB_F_NETWORK_ORDER would be more appropriate.

> +
>  /** Type of FIB struct */
>  enum rte_fib_type {
>  	RTE_FIB_DUMMY,		/**< RIB tree based FIB */
> @@ -76,6 +79,7 @@ enum rte_fib_lookup_type {
>  /** FIB configuration structure */
>  struct rte_fib_conf {
>  	enum rte_fib_type type; /**< Type of FIB struct */
> +	unsigned int flags;

Maybe use an explicit int size for flags like uint32_t? I doubt we'll 
ever need more than 32 flags.

Also, maybe it would be better to add this field at the end to avoid 
breaking the API?

You forgot to add a doc string for that field:

    uint32_t flags; /**< Optional feature flags from RTE_FIB_F_* **/

Thanks!

Re: [PATCH v3] fib: network byte order IPv4 lookup

[David Marchand]

On Thu, Oct 10, 2024 at 1:26 PM Vladimir Medvedkin
<vladimir.medvedkin@intel.com> wrote:
> diff --git a/lib/fib/meson.build b/lib/fib/meson.build
> index 6795f41a0a..8c03496cdc 100644
> --- a/lib/fib/meson.build
> +++ b/lib/fib/meson.build
> @@ -25,40 +25,28 @@ if dpdk_conf.has('RTE_ARCH_X86_64') and binutils_ok
>      # linked into main lib.
>
>      # check if all required flags already enabled (variant a).
> -    acl_avx512_flags = ['__AVX512F__','__AVX512DQ__']
> -    acl_avx512_on = true
> -    foreach f:acl_avx512_flags
> +    fib_avx512_flags = ['__AVX512F__','__AVX512DQ__', '__AVX512BW__']
> +    fib_avx512_on = true
> +    foreach f:fib_avx512_flags
>          if cc.get_define(f, args: machine_args) == ''
> -            acl_avx512_on = false
> +            fib_avx512_on = false
>          endif
>      endforeach

Repeating comment on v2 that was lost because of duplicate submission (?):

Please reuse the common checks recently merged, see for example:
https://git.dpdk.org/dpdk/diff/drivers/event/dlb2/meson.build?id=ef7a4025cd714189dc333bb19ea60c2abdeffb7d

>
> -    if acl_avx512_on == true
> -        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT']
> -        sources += files('dir24_8_avx512.c')
> -        # TRIE AVX512 implementation uses avx512bw intrinsics along with
> -        # avx512f and avx512dq
> -        if cc.get_define('__AVX512BW__', args: machine_args) != ''
> -            cflags += ['-DCC_TRIE_AVX512_SUPPORT']
> -            sources += files('trie_avx512.c')
> -        endif
> -    elif cc.has_multi_arguments('-mavx512f', '-mavx512dq')
> +    if fib_avx512_on == true
> +        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT', '-DCC_TRIE_AVX512_SUPPORT']

Nit: now that both dir24_8 and trie share the same requirement, can we
go with a simple CC_AVX512_SUPPORT?
This is really a nit, I am ok if you prefer to separate both.


> +        sources += files('dir24_8_avx512.c', 'trie_avx512.c')
> +    elif cc.has_multi_arguments('-mavx512f', '-mavx512dq', '-mavx512bw')
>          dir24_8_avx512_tmp = static_library('dir24_8_avx512_tmp',
>                  'dir24_8_avx512.c',
>                  dependencies: static_rte_eal,
> -                c_args: cflags + ['-mavx512f', '-mavx512dq'])
> +                c_args: cflags + ['-mavx512f', '-mavx512dq', '-mavx512bw'])
>          objs += dir24_8_avx512_tmp.extract_objects('dir24_8_avx512.c')
> -        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT']
> -        # TRIE AVX512 implementation uses avx512bw intrinsics along with
> -        # avx512f and avx512dq
> -        if cc.has_argument('-mavx512bw')
> -            trie_avx512_tmp = static_library('trie_avx512_tmp',
> +        trie_avx512_tmp = static_library('trie_avx512_tmp',
>                  'trie_avx512.c',
>                  dependencies: static_rte_eal,
> -                c_args: cflags + ['-mavx512f', \
> -                    '-mavx512dq', '-mavx512bw'])
> -            objs += trie_avx512_tmp.extract_objects('trie_avx512.c')
> -            cflags += ['-DCC_TRIE_AVX512_SUPPORT']
> -        endif
> +                c_args: cflags + ['-mavx512f', '-mavx512dq', '-mavx512bw'])
> +        objs += trie_avx512_tmp.extract_objects('trie_avx512.c')
> +        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT', '-DCC_TRIE_AVX512_SUPPORT']
>      endif
>  endif
> diff --git a/lib/fib/rte_fib.c b/lib/fib/rte_fib.c
> index 4f9fba5a4f..991e48b5ea 100644
> --- a/lib/fib/rte_fib.c
> +++ b/lib/fib/rte_fib.c
> @@ -42,6 +42,7 @@ EAL_REGISTER_TAILQ(rte_fib_tailq)
>  struct rte_fib {
>         char                    name[RTE_FIB_NAMESIZE];
>         enum rte_fib_type       type;   /**< Type of FIB struct */
> +       int flags;                                      /**< Flags */
>         struct rte_rib          *rib;   /**< RIB helper datastructure */
>         void                    *dp;    /**< pointer to the dataplane struct*/
>         rte_fib_lookup_fn_t     lookup; /**< FIB lookup function */
> @@ -110,7 +111,7 @@ init_dataplane(struct rte_fib *fib, __rte_unused int socket_id,
>                 if (fib->dp == NULL)
>                         return -rte_errno;
>                 fib->lookup = dir24_8_get_lookup_fn(fib->dp,
> -                       RTE_FIB_LOOKUP_DEFAULT);
> +                       RTE_FIB_LOOKUP_DEFAULT, !!(fib->flags & RTE_FIB_FLAG_LOOKUP_BE));
>                 fib->modify = dir24_8_modify;
>                 return 0;
>         default:
> @@ -214,6 +215,7 @@ rte_fib_create(const char *name, int socket_id, struct rte_fib_conf *conf)
>         rte_strlcpy(fib->name, name, sizeof(fib->name));
>         fib->rib = rib;
>         fib->type = conf->type;
> +       fib->flags = conf->flags;

In addition to Robin comments, I also have a concern on the
extensibility aspect.

conf->flags must be validated against known flags.
Otherwise existing applications may pass wrong stuff and "work fine",
until the day we had one more flag.


>         fib->def_nh = conf->default_nh;
>         ret = init_dataplane(fib, socket_id, conf);
>         if (ret < 0) {


-- 
David Marchand

Re: [PATCH v3] fib: network byte order IPv4 lookup

[David Marchand]

On Fri, Oct 11, 2024 at 1:29 PM David Marchand
<david.marchand@redhat.com> wrote:
> > @@ -214,6 +215,7 @@ rte_fib_create(const char *name, int socket_id, struct rte_fib_conf *conf)
> >         rte_strlcpy(fib->name, name, sizeof(fib->name));
> >         fib->rib = rib;
> >         fib->type = conf->type;
> > +       fib->flags = conf->flags;
>
> In addition to Robin comments, I also have a concern on the
> extensibility aspect.
>
> conf->flags must be validated against known flags.
> Otherwise existing applications may pass wrong stuff and "work fine",
> until the day we had one more flag.
>

And about this flag field, please update release notes and remove the
associated deprecation notice.
Thank you.


-- 
David Marchand

[PATCH v4] fib: network byte order IPv4 lookup

[Vladimir Medvedkin]

Previously when running rte_fib_lookup IPv4 addresses must have been in
host byte order.

This patch adds a new flag RTE_FIB_FLAG_LOOKUP_BE that can be passed on
fib create, which will allow to have IPv4 in network byte order on
lookup.

Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
---
 app/test/test_fib.c                    | 10 ++--
 app/test/test_fib_perf.c               |  2 +-
 doc/guides/rel_notes/deprecation.rst   |  3 -
 doc/guides/rel_notes/release_24_11.rst |  5 ++
 examples/l3fwd/l3fwd_fib.c             |  2 +-
 lib/fib/dir24_8.c                      | 63 +++++++++++++-------
 lib/fib/dir24_8.h                      | 48 ++++++++++++++-
 lib/fib/dir24_8_avx512.c               | 82 +++++++++++++++-----------
 lib/fib/dir24_8_avx512.h               | 15 +++++
 lib/fib/meson.build                    | 63 +++++---------------
 lib/fib/rte_fib.c                      |  8 ++-
 lib/fib/rte_fib.h                      |  5 ++
 12 files changed, 189 insertions(+), 117 deletions(-)

diff --git a/app/test/test_fib.c b/app/test/test_fib.c
index 45dccca1f6..69c439a3a8 100644
--- a/app/test/test_fib.c
+++ b/app/test/test_fib.c
@@ -33,7 +33,7 @@ int32_t
 test_create_invalid(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 
 	config.max_routes = MAX_ROUTES;
 	config.rib_ext_sz = 0;
@@ -92,7 +92,7 @@ int32_t
 test_multiple_create(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 	int32_t i;
 
 	config.rib_ext_sz = 0;
@@ -119,7 +119,7 @@ int32_t
 test_free_null(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 
 	config.max_routes = MAX_ROUTES;
 	config.rib_ext_sz = 0;
@@ -142,7 +142,7 @@ int32_t
 test_add_del_invalid(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 	uint64_t nh = 100;
 	uint32_t ip = RTE_IPV4(0, 0, 0, 0);
 	int ret;
@@ -319,7 +319,7 @@ int32_t
 test_lookup(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 	uint64_t def_nh = 100;
 	int ret;
 
diff --git a/app/test/test_fib_perf.c b/app/test/test_fib_perf.c
index d3cd986d2e..1b2ad04854 100644
--- a/app/test/test_fib_perf.c
+++ b/app/test/test_fib_perf.c
@@ -320,7 +320,7 @@ static int
 test_fib_perf(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 
 	config.max_routes = 2000000;
 	config.rib_ext_sz = 0;
diff --git a/doc/guides/rel_notes/deprecation.rst b/doc/guides/rel_notes/deprecation.rst
index 1535ea7abf..7bc2310bc4 100644
--- a/doc/guides/rel_notes/deprecation.rst
+++ b/doc/guides/rel_notes/deprecation.rst
@@ -166,9 +166,6 @@ Deprecation Notices
   The legacy actions should be removed
   once ``MODIFY_FIELD`` alternative is implemented in drivers.
 
-* fib: A new flag field will be introduced in ``rte_fib_conf`` structure
-  in DPDK 24.11. This field will be used to pass extra configuration settings.
-
 * cryptodev: The Intel IPsec Multi-Buffer version will be bumped
   to a minimum version of v1.4.
   This will effect the KASUMI, SNOW3G, ZUC, AESNI GCM, AESNI MB and CHACHAPOLY
diff --git a/doc/guides/rel_notes/release_24_11.rst b/doc/guides/rel_notes/release_24_11.rst
index 22c4084d83..bfef2cd99e 100644
--- a/doc/guides/rel_notes/release_24_11.rst
+++ b/doc/guides/rel_notes/release_24_11.rst
@@ -154,6 +154,11 @@ New Features
 
   * Added independent enqueue feature.
 
+* **Updated FIB configuration structure.**
+
+  A new flag field introduced in ``rte_fib_conf`` structure.
+  This field is used to pass an extra configuration settings such as ability
+  to lookup IPv4 addresses in network byte order.
 
 Removed Items
 -------------
diff --git a/examples/l3fwd/l3fwd_fib.c b/examples/l3fwd/l3fwd_fib.c
index f38b19af3f..993e36cec2 100644
--- a/examples/l3fwd/l3fwd_fib.c
+++ b/examples/l3fwd/l3fwd_fib.c
@@ -644,7 +644,7 @@ setup_fib(const int socketid)
 {
 	struct rte_eth_dev_info dev_info;
 	struct rte_fib6_conf config;
-	struct rte_fib_conf config_ipv4;
+	struct rte_fib_conf config_ipv4 = { 0 };
 	int i;
 	int ret;
 	char s[64];
diff --git a/lib/fib/dir24_8.c b/lib/fib/dir24_8.c
index c739e92304..5c856ff6a6 100644
--- a/lib/fib/dir24_8.c
+++ b/lib/fib/dir24_8.c
@@ -26,67 +26,84 @@
 #define ROUNDUP(x, y)	 RTE_ALIGN_CEIL(x, (1 << (32 - y)))
 
 static inline rte_fib_lookup_fn_t
-get_scalar_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_scalar_fn(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return dir24_8_lookup_bulk_1b;
+		return (be_addr) ? dir24_8_lookup_bulk_1b_be :
+					dir24_8_lookup_bulk_1b;
 	case RTE_FIB_DIR24_8_2B:
-		return dir24_8_lookup_bulk_2b;
+		return (be_addr) ? dir24_8_lookup_bulk_2b_be :
+					dir24_8_lookup_bulk_2b;
 	case RTE_FIB_DIR24_8_4B:
-		return dir24_8_lookup_bulk_4b;
+		return (be_addr) ? dir24_8_lookup_bulk_4b_be :
+					dir24_8_lookup_bulk_4b;
 	case RTE_FIB_DIR24_8_8B:
-		return dir24_8_lookup_bulk_8b;
+		return (be_addr) ? dir24_8_lookup_bulk_8b_be :
+					dir24_8_lookup_bulk_8b;
 	default:
 		return NULL;
 	}
 }
 
 static inline rte_fib_lookup_fn_t
-get_scalar_fn_inlined(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_scalar_fn_inlined(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return dir24_8_lookup_bulk_0;
+		return (be_addr) ? dir24_8_lookup_bulk_0_be :
+					dir24_8_lookup_bulk_0;
 	case RTE_FIB_DIR24_8_2B:
-		return dir24_8_lookup_bulk_1;
+		return (be_addr) ? dir24_8_lookup_bulk_1_be :
+					dir24_8_lookup_bulk_1;
 	case RTE_FIB_DIR24_8_4B:
-		return dir24_8_lookup_bulk_2;
+		return (be_addr) ? dir24_8_lookup_bulk_2_be :
+					dir24_8_lookup_bulk_2;
 	case RTE_FIB_DIR24_8_8B:
-		return dir24_8_lookup_bulk_3;
+		return (be_addr) ? dir24_8_lookup_bulk_3_be :
+					dir24_8_lookup_bulk_3;
 	default:
 		return NULL;
 	}
 }
 
 static inline rte_fib_lookup_fn_t
-get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 #ifdef CC_DIR24_8_AVX512_SUPPORT
 	if ((rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) <= 0) ||
+		(rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512DQ) <= 0) ||
 			(rte_vect_get_max_simd_bitwidth() < RTE_VECT_SIMD_512))
 		return NULL;
 
+	if (be_addr && (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512BW) <= 0))
+		return NULL;
+
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return rte_dir24_8_vec_lookup_bulk_1b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_1b_be :
+					rte_dir24_8_vec_lookup_bulk_1b;
 	case RTE_FIB_DIR24_8_2B:
-		return rte_dir24_8_vec_lookup_bulk_2b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_2b_be :
+					rte_dir24_8_vec_lookup_bulk_2b;
 	case RTE_FIB_DIR24_8_4B:
-		return rte_dir24_8_vec_lookup_bulk_4b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_4b_be :
+					rte_dir24_8_vec_lookup_bulk_4b;
 	case RTE_FIB_DIR24_8_8B:
-		return rte_dir24_8_vec_lookup_bulk_8b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_8b_be :
+					rte_dir24_8_vec_lookup_bulk_8b;
 	default:
 		return NULL;
 	}
 #else
 	RTE_SET_USED(nh_sz);
+	RTE_SET_USED(be_addr);
 #endif
 	return NULL;
 }
 
 rte_fib_lookup_fn_t
-dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type)
+dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type, bool be_addr)
 {
 	enum rte_fib_dir24_8_nh_sz nh_sz;
 	rte_fib_lookup_fn_t ret_fn;
@@ -99,16 +116,18 @@ dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type)
 
 	switch (type) {
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_MACRO:
-		return get_scalar_fn(nh_sz);
+		return get_scalar_fn(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_INLINE:
-		return get_scalar_fn_inlined(nh_sz);
+		return get_scalar_fn_inlined(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_UNI:
-		return dir24_8_lookup_bulk_uni;
+		return (be_addr) ? dir24_8_lookup_bulk_uni_be :
+						dir24_8_lookup_bulk_uni;
 	case RTE_FIB_LOOKUP_DIR24_8_VECTOR_AVX512:
-		return get_vector_fn(nh_sz);
+		return get_vector_fn(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DEFAULT:
-		ret_fn = get_vector_fn(nh_sz);
-		return (ret_fn != NULL) ? ret_fn : get_scalar_fn(nh_sz);
+		ret_fn = get_vector_fn(nh_sz, be_addr);
+		return (ret_fn != NULL) ? ret_fn :
+			get_scalar_fn(nh_sz, be_addr);
 	default:
 		return NULL;
 	}
diff --git a/lib/fib/dir24_8.h b/lib/fib/dir24_8.h
index 7125049f15..dee5275673 100644
--- a/lib/fib/dir24_8.h
+++ b/lib/fib/dir24_8.h
@@ -7,7 +7,9 @@
 #define _DIR24_8_H_
 
 #include <stdalign.h>
+#include <stdbool.h>
 
+#include <rte_byteorder.h>
 #include <rte_prefetch.h>
 #include <rte_branch_prediction.h>
 
@@ -237,6 +239,50 @@ dir24_8_lookup_bulk_uni(void *p, const uint32_t *ips,
 	}
 }
 
+#define BSWAP_MAX_LENGTH	64
+
+typedef void (*dir24_8_lookup_bulk_be_cb)(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+static inline void
+dir24_8_lookup_bulk_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n,
+	dir24_8_lookup_bulk_be_cb cb)
+{
+	uint32_t le_ips[BSWAP_MAX_LENGTH];
+	unsigned int i;
+
+#if RTE_BYTE_ORDER == RTE_BIG_ENDIAN
+	cb(p, ips, next_hops, n);
+#else
+	for (i = 0; i < n; i += BSWAP_MAX_LENGTH) {
+		int j;
+		for (j = 0; j < BSWAP_MAX_LENGTH && i + j < n; j++)
+			le_ips[j] = rte_be_to_cpu_32(ips[i + j]);
+
+		cb(p, le_ips, next_hops + i, j);
+	}
+#endif
+}
+
+#define DECLARE_BE_LOOKUP_FN(name)					\
+static inline void							\
+name##_be(void *p, const uint32_t *ips,					\
+	uint64_t *next_hops, const unsigned int n)			\
+{									\
+	dir24_8_lookup_bulk_be(p, ips, next_hops, n, name);		\
+}
+
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_1b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_2b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_4b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_8b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_0)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_1)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_2)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_3)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_uni)
+
 void *
 dir24_8_create(const char *name, int socket_id, struct rte_fib_conf *conf);
 
@@ -244,7 +290,7 @@ void
 dir24_8_free(void *p);
 
 rte_fib_lookup_fn_t
-dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type);
+dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type, bool be_addr);
 
 int
 dir24_8_modify(struct rte_fib *fib, uint32_t ip, uint8_t depth,
diff --git a/lib/fib/dir24_8_avx512.c b/lib/fib/dir24_8_avx512.c
index 43dba28cfb..e6fe08ecfe 100644
--- a/lib/fib/dir24_8_avx512.c
+++ b/lib/fib/dir24_8_avx512.c
@@ -10,7 +10,7 @@
 
 static __rte_always_inline void
 dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
-	uint64_t *next_hops, int size)
+	uint64_t *next_hops, int size, bool be_addr)
 {
 	struct dir24_8_tbl *dp = (struct dir24_8_tbl *)p;
 	__mmask16 msk_ext;
@@ -28,6 +28,16 @@ dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
 		res_msk = _mm512_set1_epi32(UINT16_MAX);
 
 	ip_vec = _mm512_loadu_si512(ips);
+	if (be_addr) {
+		const __m512i bswap32 = _mm512_set_epi32(
+			0x0c0d0e0f, 0x08090a0b, 0x04050607, 0x00010203,
+			0x0c0d0e0f, 0x08090a0b, 0x04050607, 0x00010203,
+			0x0c0d0e0f, 0x08090a0b, 0x04050607, 0x00010203,
+			0x0c0d0e0f, 0x08090a0b, 0x04050607, 0x00010203
+		);
+		ip_vec = _mm512_shuffle_epi8(ip_vec, bswap32);
+	}
+
 	/* mask 24 most significant bits */
 	idxes = _mm512_srli_epi32(ip_vec, 8);
 
@@ -78,7 +88,7 @@ dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
 
 static __rte_always_inline void
 dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
-	uint64_t *next_hops)
+	uint64_t *next_hops, bool be_addr)
 {
 	struct dir24_8_tbl *dp = (struct dir24_8_tbl *)p;
 	const __m512i zero = _mm512_set1_epi32(0);
@@ -89,6 +99,13 @@ dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
 	__mmask8 msk_ext;
 
 	ip_vec = _mm256_loadu_si256((const void *)ips);
+	if (be_addr) {
+		const __m256i bswap32 = _mm256_set_epi8(
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3
+		);
+		ip_vec = _mm256_shuffle_epi8(ip_vec, bswap32);
+	}
 	/* mask 24 most significant bits */
 	idxes_256 = _mm256_srli_epi32(ip_vec, 8);
 
@@ -114,52 +131,49 @@ dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
 	_mm512_storeu_si512(next_hops, res);
 }
 
-void
-rte_dir24_8_vec_lookup_bulk_1b(void *p, const uint32_t *ips,
-	uint64_t *next_hops, const unsigned int n)
-{
-	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint8_t));
-
-	dir24_8_lookup_bulk_1b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
+#define DECLARE_VECTOR_FN(suffix, nh_type, be_addr)			\
+void									\
+rte_dir24_8_vec_lookup_bulk_##suffix(void *p, const uint32_t *ips,	\
+	uint64_t *next_hops, const unsigned int n)			\
+{									\
+	uint32_t i;							\
+									\
+	for (i = 0; i < (n / 16); i++)					\
+		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16, \
+			sizeof(nh_type), be_addr);			\
+									\
+	dir24_8_lookup_bulk_##suffix(p, ips + i * 16, next_hops + i * 16, \
+		n - i * 16);						\
 }
 
-void
-rte_dir24_8_vec_lookup_bulk_2b(void *p, const uint32_t *ips,
-	uint64_t *next_hops, const unsigned int n)
-{
-	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint16_t));
-
-	dir24_8_lookup_bulk_2b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
-}
+DECLARE_VECTOR_FN(1b, uint8_t, false)
+DECLARE_VECTOR_FN(2b, uint16_t, false)
+DECLARE_VECTOR_FN(4b, uint32_t, false)
+DECLARE_VECTOR_FN(1b_be, uint8_t, true)
+DECLARE_VECTOR_FN(2b_be, uint16_t, true)
+DECLARE_VECTOR_FN(4b_be, uint32_t, true)
 
 void
-rte_dir24_8_vec_lookup_bulk_4b(void *p, const uint32_t *ips,
+rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n)
 {
 	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint32_t));
+	for (i = 0; i < (n / 8); i++)
+		dir24_8_vec_lookup_x8_8b(p, ips + i * 8,
+			next_hops + i * 8, false);
 
-	dir24_8_lookup_bulk_4b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
+	dir24_8_lookup_bulk_8b(p, ips + i * 8, next_hops + i * 8, n - i * 8);
 }
 
 void
-rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
+rte_dir24_8_vec_lookup_bulk_8b_be(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n)
 {
 	uint32_t i;
 	for (i = 0; i < (n / 8); i++)
-		dir24_8_vec_lookup_x8_8b(p, ips + i * 8, next_hops + i * 8);
+		dir24_8_vec_lookup_x8_8b(p, ips + i * 8,
+			next_hops + i * 8, true);
 
-	dir24_8_lookup_bulk_8b(p, ips + i * 8, next_hops + i * 8, n - i * 8);
+	dir24_8_lookup_bulk_8b_be(p, ips + i * 8,
+		next_hops + i * 8, n - i * 8);
 }
diff --git a/lib/fib/dir24_8_avx512.h b/lib/fib/dir24_8_avx512.h
index 1d3c2b9317..e9f7b72519 100644
--- a/lib/fib/dir24_8_avx512.h
+++ b/lib/fib/dir24_8_avx512.h
@@ -21,4 +21,19 @@ void
 rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n);
 
+void
+rte_dir24_8_vec_lookup_bulk_1b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_2b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_4b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_8b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
 #endif /* _DIR248_AVX512_H_ */
diff --git a/lib/fib/meson.build b/lib/fib/meson.build
index 6795f41a0a..07f207bd41 100644
--- a/lib/fib/meson.build
+++ b/lib/fib/meson.build
@@ -12,53 +12,20 @@ sources = files('rte_fib.c', 'rte_fib6.c', 'dir24_8.c', 'trie.c')
 headers = files('rte_fib.h', 'rte_fib6.h')
 deps += ['rib']
 
-# compile AVX512 version if:
-# we are building 64-bit binary AND binutils can generate proper code
-if dpdk_conf.has('RTE_ARCH_X86_64') and binutils_ok
-    # compile AVX512 version if either:
-    # a. we have AVX512F supported in minimum instruction set baseline
-    # b. it's not minimum instruction set, but supported by compiler
-    #
-    # in former case, just add avx512 C file to files list
-    # in latter case, compile c file to static lib, using correct
-    # compiler flags, and then have the .o file from static lib
-    # linked into main lib.
+if target_has_avx512
+    cflags += ['-DCC_DIR24_8_AVX512_SUPPORT', '-DCC_TRIE_AVX512_SUPPORT']
+    sources += files('dir24_8_avx512.c', 'trie_avx512.c')
 
-    # check if all required flags already enabled (variant a).
-    acl_avx512_flags = ['__AVX512F__','__AVX512DQ__']
-    acl_avx512_on = true
-    foreach f:acl_avx512_flags
-        if cc.get_define(f, args: machine_args) == ''
-            acl_avx512_on = false
-        endif
-    endforeach
-
-    if acl_avx512_on == true
-        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT']
-        sources += files('dir24_8_avx512.c')
-        # TRIE AVX512 implementation uses avx512bw intrinsics along with
-        # avx512f and avx512dq
-        if cc.get_define('__AVX512BW__', args: machine_args) != ''
-            cflags += ['-DCC_TRIE_AVX512_SUPPORT']
-            sources += files('trie_avx512.c')
-        endif
-    elif cc.has_multi_arguments('-mavx512f', '-mavx512dq')
-        dir24_8_avx512_tmp = static_library('dir24_8_avx512_tmp',
-                'dir24_8_avx512.c',
-                dependencies: static_rte_eal,
-                c_args: cflags + ['-mavx512f', '-mavx512dq'])
-        objs += dir24_8_avx512_tmp.extract_objects('dir24_8_avx512.c')
-        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT']
-        # TRIE AVX512 implementation uses avx512bw intrinsics along with
-        # avx512f and avx512dq
-        if cc.has_argument('-mavx512bw')
-            trie_avx512_tmp = static_library('trie_avx512_tmp',
-                'trie_avx512.c',
-                dependencies: static_rte_eal,
-                c_args: cflags + ['-mavx512f', \
-                    '-mavx512dq', '-mavx512bw'])
-            objs += trie_avx512_tmp.extract_objects('trie_avx512.c')
-            cflags += ['-DCC_TRIE_AVX512_SUPPORT']
-        endif
-    endif
+elif cc_has_avx512
+    dir24_8_avx512_tmp = static_library('dir24_8_avx512_tmp',
+            'dir24_8_avx512.c',
+            dependencies: static_rte_eal,
+            c_args: cflags + ['-mavx512f', '-mavx512dq', '-mavx512bw'])
+    objs += dir24_8_avx512_tmp.extract_objects('dir24_8_avx512.c')
+    trie_avx512_tmp = static_library('trie_avx512_tmp',
+            'trie_avx512.c',
+            dependencies: static_rte_eal,
+            c_args: cflags + ['-mavx512f', '-mavx512dq', '-mavx512bw'])
+    objs += trie_avx512_tmp.extract_objects('trie_avx512.c')
+    cflags += ['-DCC_DIR24_8_AVX512_SUPPORT', '-DCC_TRIE_AVX512_SUPPORT']
 endif
diff --git a/lib/fib/rte_fib.c b/lib/fib/rte_fib.c
index 4f9fba5a4f..30a55489ad 100644
--- a/lib/fib/rte_fib.c
+++ b/lib/fib/rte_fib.c
@@ -42,6 +42,7 @@ EAL_REGISTER_TAILQ(rte_fib_tailq)
 struct rte_fib {
 	char			name[RTE_FIB_NAMESIZE];
 	enum rte_fib_type	type;	/**< Type of FIB struct */
+	int flags;					/**< Flags */
 	struct rte_rib		*rib;	/**< RIB helper datastructure */
 	void			*dp;	/**< pointer to the dataplane struct*/
 	rte_fib_lookup_fn_t	lookup;	/**< FIB lookup function */
@@ -110,7 +111,7 @@ init_dataplane(struct rte_fib *fib, __rte_unused int socket_id,
 		if (fib->dp == NULL)
 			return -rte_errno;
 		fib->lookup = dir24_8_get_lookup_fn(fib->dp,
-			RTE_FIB_LOOKUP_DEFAULT);
+			RTE_FIB_LOOKUP_DEFAULT, !!(fib->flags & RTE_FIB_F_NETWORK_ORDER));
 		fib->modify = dir24_8_modify;
 		return 0;
 	default:
@@ -161,6 +162,7 @@ rte_fib_create(const char *name, int socket_id, struct rte_fib_conf *conf)
 
 	/* Check user arguments. */
 	if ((name == NULL) || (conf == NULL) ||	(conf->max_routes < 0) ||
+			(conf->flags & ~RTE_FIB_ALLOWED_FLAGS) ||
 			(conf->type > RTE_FIB_DIR24_8)) {
 		rte_errno = EINVAL;
 		return NULL;
@@ -214,6 +216,7 @@ rte_fib_create(const char *name, int socket_id, struct rte_fib_conf *conf)
 	rte_strlcpy(fib->name, name, sizeof(fib->name));
 	fib->rib = rib;
 	fib->type = conf->type;
+	fib->flags = conf->flags;
 	fib->def_nh = conf->default_nh;
 	ret = init_dataplane(fib, socket_id, conf);
 	if (ret < 0) {
@@ -329,7 +332,8 @@ rte_fib_select_lookup(struct rte_fib *fib,
 
 	switch (fib->type) {
 	case RTE_FIB_DIR24_8:
-		fn = dir24_8_get_lookup_fn(fib->dp, type);
+		fn = dir24_8_get_lookup_fn(fib->dp, type,
+			!!(fib->flags & RTE_FIB_F_NETWORK_ORDER));
 		if (fn == NULL)
 			return -EINVAL;
 		fib->lookup = fn;
diff --git a/lib/fib/rte_fib.h b/lib/fib/rte_fib.h
index d7a5aafe53..0c3e3e574e 100644
--- a/lib/fib/rte_fib.h
+++ b/lib/fib/rte_fib.h
@@ -28,6 +28,10 @@ struct rte_rib;
 /** Maximum depth value possible for IPv4 FIB. */
 #define RTE_FIB_MAXDEPTH	32
 
+/** If set fib lookup is expecting ipv4 in network byte order */
+#define RTE_FIB_F_NETWORK_ORDER	1
+#define RTE_FIB_ALLOWED_FLAGS	(RTE_FIB_F_NETWORK_ORDER)
+
 /** Type of FIB struct */
 enum rte_fib_type {
 	RTE_FIB_DUMMY,		/**< RIB tree based FIB */
@@ -87,6 +91,7 @@ struct rte_fib_conf {
 			uint32_t	num_tbl8;
 		} dir24_8;
 	};
+	unsigned int flags;	/**< Optional feature flags from RTE_FIB_F_* **/
 };
 
 /**
-- 
2.43.0

[PATCH v5] fib: network byte order IPv4 lookup

[Vladimir Medvedkin]

Previously when running rte_fib_lookup IPv4 addresses must have been in
host byte order.

This patch adds a new flag RTE_FIB_FLAG_LOOKUP_BE that can be passed on
fib create, which will allow to have IPv4 in network byte order on
lookup.

Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
---
 app/test/test_fib.c                    | 10 ++--
 app/test/test_fib_perf.c               |  2 +-
 doc/guides/rel_notes/deprecation.rst   |  3 -
 doc/guides/rel_notes/release_24_11.rst |  5 ++
 examples/l3fwd/l3fwd_fib.c             |  2 +-
 lib/fib/dir24_8.c                      | 63 +++++++++++++-------
 lib/fib/dir24_8.h                      | 48 ++++++++++++++-
 lib/fib/dir24_8_avx512.c               | 82 +++++++++++++++-----------
 lib/fib/dir24_8_avx512.h               | 15 +++++
 lib/fib/meson.build                    | 53 ++++-------------
 lib/fib/rte_fib.c                      |  8 ++-
 lib/fib/rte_fib.h                      |  5 ++
 12 files changed, 185 insertions(+), 111 deletions(-)

diff --git a/app/test/test_fib.c b/app/test/test_fib.c
index 45dccca1f6..69c439a3a8 100644
--- a/app/test/test_fib.c
+++ b/app/test/test_fib.c
@@ -33,7 +33,7 @@ int32_t
 test_create_invalid(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 
 	config.max_routes = MAX_ROUTES;
 	config.rib_ext_sz = 0;
@@ -92,7 +92,7 @@ int32_t
 test_multiple_create(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 	int32_t i;
 
 	config.rib_ext_sz = 0;
@@ -119,7 +119,7 @@ int32_t
 test_free_null(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 
 	config.max_routes = MAX_ROUTES;
 	config.rib_ext_sz = 0;
@@ -142,7 +142,7 @@ int32_t
 test_add_del_invalid(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 	uint64_t nh = 100;
 	uint32_t ip = RTE_IPV4(0, 0, 0, 0);
 	int ret;
@@ -319,7 +319,7 @@ int32_t
 test_lookup(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 	uint64_t def_nh = 100;
 	int ret;
 
diff --git a/app/test/test_fib_perf.c b/app/test/test_fib_perf.c
index d3cd986d2e..1b2ad04854 100644
--- a/app/test/test_fib_perf.c
+++ b/app/test/test_fib_perf.c
@@ -320,7 +320,7 @@ static int
 test_fib_perf(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 
 	config.max_routes = 2000000;
 	config.rib_ext_sz = 0;
diff --git a/doc/guides/rel_notes/deprecation.rst b/doc/guides/rel_notes/deprecation.rst
index 1535ea7abf..7bc2310bc4 100644
--- a/doc/guides/rel_notes/deprecation.rst
+++ b/doc/guides/rel_notes/deprecation.rst
@@ -166,9 +166,6 @@ Deprecation Notices
   The legacy actions should be removed
   once ``MODIFY_FIELD`` alternative is implemented in drivers.
 
-* fib: A new flag field will be introduced in ``rte_fib_conf`` structure
-  in DPDK 24.11. This field will be used to pass extra configuration settings.
-
 * cryptodev: The Intel IPsec Multi-Buffer version will be bumped
   to a minimum version of v1.4.
   This will effect the KASUMI, SNOW3G, ZUC, AESNI GCM, AESNI MB and CHACHAPOLY
diff --git a/doc/guides/rel_notes/release_24_11.rst b/doc/guides/rel_notes/release_24_11.rst
index 22c4084d83..bfef2cd99e 100644
--- a/doc/guides/rel_notes/release_24_11.rst
+++ b/doc/guides/rel_notes/release_24_11.rst
@@ -154,6 +154,11 @@ New Features
 
   * Added independent enqueue feature.
 
+* **Updated FIB configuration structure.**
+
+  A new flag field introduced in ``rte_fib_conf`` structure.
+  This field is used to pass an extra configuration settings such as ability
+  to lookup IPv4 addresses in network byte order.
 
 Removed Items
 -------------
diff --git a/examples/l3fwd/l3fwd_fib.c b/examples/l3fwd/l3fwd_fib.c
index f38b19af3f..993e36cec2 100644
--- a/examples/l3fwd/l3fwd_fib.c
+++ b/examples/l3fwd/l3fwd_fib.c
@@ -644,7 +644,7 @@ setup_fib(const int socketid)
 {
 	struct rte_eth_dev_info dev_info;
 	struct rte_fib6_conf config;
-	struct rte_fib_conf config_ipv4;
+	struct rte_fib_conf config_ipv4 = { 0 };
 	int i;
 	int ret;
 	char s[64];
diff --git a/lib/fib/dir24_8.c b/lib/fib/dir24_8.c
index c739e92304..5c856ff6a6 100644
--- a/lib/fib/dir24_8.c
+++ b/lib/fib/dir24_8.c
@@ -26,67 +26,84 @@
 #define ROUNDUP(x, y)	 RTE_ALIGN_CEIL(x, (1 << (32 - y)))
 
 static inline rte_fib_lookup_fn_t
-get_scalar_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_scalar_fn(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return dir24_8_lookup_bulk_1b;
+		return (be_addr) ? dir24_8_lookup_bulk_1b_be :
+					dir24_8_lookup_bulk_1b;
 	case RTE_FIB_DIR24_8_2B:
-		return dir24_8_lookup_bulk_2b;
+		return (be_addr) ? dir24_8_lookup_bulk_2b_be :
+					dir24_8_lookup_bulk_2b;
 	case RTE_FIB_DIR24_8_4B:
-		return dir24_8_lookup_bulk_4b;
+		return (be_addr) ? dir24_8_lookup_bulk_4b_be :
+					dir24_8_lookup_bulk_4b;
 	case RTE_FIB_DIR24_8_8B:
-		return dir24_8_lookup_bulk_8b;
+		return (be_addr) ? dir24_8_lookup_bulk_8b_be :
+					dir24_8_lookup_bulk_8b;
 	default:
 		return NULL;
 	}
 }
 
 static inline rte_fib_lookup_fn_t
-get_scalar_fn_inlined(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_scalar_fn_inlined(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return dir24_8_lookup_bulk_0;
+		return (be_addr) ? dir24_8_lookup_bulk_0_be :
+					dir24_8_lookup_bulk_0;
 	case RTE_FIB_DIR24_8_2B:
-		return dir24_8_lookup_bulk_1;
+		return (be_addr) ? dir24_8_lookup_bulk_1_be :
+					dir24_8_lookup_bulk_1;
 	case RTE_FIB_DIR24_8_4B:
-		return dir24_8_lookup_bulk_2;
+		return (be_addr) ? dir24_8_lookup_bulk_2_be :
+					dir24_8_lookup_bulk_2;
 	case RTE_FIB_DIR24_8_8B:
-		return dir24_8_lookup_bulk_3;
+		return (be_addr) ? dir24_8_lookup_bulk_3_be :
+					dir24_8_lookup_bulk_3;
 	default:
 		return NULL;
 	}
 }
 
 static inline rte_fib_lookup_fn_t
-get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 #ifdef CC_DIR24_8_AVX512_SUPPORT
 	if ((rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) <= 0) ||
+		(rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512DQ) <= 0) ||
 			(rte_vect_get_max_simd_bitwidth() < RTE_VECT_SIMD_512))
 		return NULL;
 
+	if (be_addr && (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512BW) <= 0))
+		return NULL;
+
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return rte_dir24_8_vec_lookup_bulk_1b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_1b_be :
+					rte_dir24_8_vec_lookup_bulk_1b;
 	case RTE_FIB_DIR24_8_2B:
-		return rte_dir24_8_vec_lookup_bulk_2b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_2b_be :
+					rte_dir24_8_vec_lookup_bulk_2b;
 	case RTE_FIB_DIR24_8_4B:
-		return rte_dir24_8_vec_lookup_bulk_4b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_4b_be :
+					rte_dir24_8_vec_lookup_bulk_4b;
 	case RTE_FIB_DIR24_8_8B:
-		return rte_dir24_8_vec_lookup_bulk_8b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_8b_be :
+					rte_dir24_8_vec_lookup_bulk_8b;
 	default:
 		return NULL;
 	}
 #else
 	RTE_SET_USED(nh_sz);
+	RTE_SET_USED(be_addr);
 #endif
 	return NULL;
 }
 
 rte_fib_lookup_fn_t
-dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type)
+dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type, bool be_addr)
 {
 	enum rte_fib_dir24_8_nh_sz nh_sz;
 	rte_fib_lookup_fn_t ret_fn;
@@ -99,16 +116,18 @@ dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type)
 
 	switch (type) {
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_MACRO:
-		return get_scalar_fn(nh_sz);
+		return get_scalar_fn(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_INLINE:
-		return get_scalar_fn_inlined(nh_sz);
+		return get_scalar_fn_inlined(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_UNI:
-		return dir24_8_lookup_bulk_uni;
+		return (be_addr) ? dir24_8_lookup_bulk_uni_be :
+						dir24_8_lookup_bulk_uni;
 	case RTE_FIB_LOOKUP_DIR24_8_VECTOR_AVX512:
-		return get_vector_fn(nh_sz);
+		return get_vector_fn(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DEFAULT:
-		ret_fn = get_vector_fn(nh_sz);
-		return (ret_fn != NULL) ? ret_fn : get_scalar_fn(nh_sz);
+		ret_fn = get_vector_fn(nh_sz, be_addr);
+		return (ret_fn != NULL) ? ret_fn :
+			get_scalar_fn(nh_sz, be_addr);
 	default:
 		return NULL;
 	}
diff --git a/lib/fib/dir24_8.h b/lib/fib/dir24_8.h
index 7125049f15..dee5275673 100644
--- a/lib/fib/dir24_8.h
+++ b/lib/fib/dir24_8.h
@@ -7,7 +7,9 @@
 #define _DIR24_8_H_
 
 #include <stdalign.h>
+#include <stdbool.h>
 
+#include <rte_byteorder.h>
 #include <rte_prefetch.h>
 #include <rte_branch_prediction.h>
 
@@ -237,6 +239,50 @@ dir24_8_lookup_bulk_uni(void *p, const uint32_t *ips,
 	}
 }
 
+#define BSWAP_MAX_LENGTH	64
+
+typedef void (*dir24_8_lookup_bulk_be_cb)(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+static inline void
+dir24_8_lookup_bulk_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n,
+	dir24_8_lookup_bulk_be_cb cb)
+{
+	uint32_t le_ips[BSWAP_MAX_LENGTH];
+	unsigned int i;
+
+#if RTE_BYTE_ORDER == RTE_BIG_ENDIAN
+	cb(p, ips, next_hops, n);
+#else
+	for (i = 0; i < n; i += BSWAP_MAX_LENGTH) {
+		int j;
+		for (j = 0; j < BSWAP_MAX_LENGTH && i + j < n; j++)
+			le_ips[j] = rte_be_to_cpu_32(ips[i + j]);
+
+		cb(p, le_ips, next_hops + i, j);
+	}
+#endif
+}
+
+#define DECLARE_BE_LOOKUP_FN(name)					\
+static inline void							\
+name##_be(void *p, const uint32_t *ips,					\
+	uint64_t *next_hops, const unsigned int n)			\
+{									\
+	dir24_8_lookup_bulk_be(p, ips, next_hops, n, name);		\
+}
+
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_1b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_2b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_4b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_8b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_0)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_1)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_2)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_3)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_uni)
+
 void *
 dir24_8_create(const char *name, int socket_id, struct rte_fib_conf *conf);
 
@@ -244,7 +290,7 @@ void
 dir24_8_free(void *p);
 
 rte_fib_lookup_fn_t
-dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type);
+dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type, bool be_addr);
 
 int
 dir24_8_modify(struct rte_fib *fib, uint32_t ip, uint8_t depth,
diff --git a/lib/fib/dir24_8_avx512.c b/lib/fib/dir24_8_avx512.c
index 43dba28cfb..e6fe08ecfe 100644
--- a/lib/fib/dir24_8_avx512.c
+++ b/lib/fib/dir24_8_avx512.c
@@ -10,7 +10,7 @@
 
 static __rte_always_inline void
 dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
-	uint64_t *next_hops, int size)
+	uint64_t *next_hops, int size, bool be_addr)
 {
 	struct dir24_8_tbl *dp = (struct dir24_8_tbl *)p;
 	__mmask16 msk_ext;
@@ -28,6 +28,16 @@ dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
 		res_msk = _mm512_set1_epi32(UINT16_MAX);
 
 	ip_vec = _mm512_loadu_si512(ips);
+	if (be_addr) {
+		const __m512i bswap32 = _mm512_set_epi32(
+			0x0c0d0e0f, 0x08090a0b, 0x04050607, 0x00010203,
+			0x0c0d0e0f, 0x08090a0b, 0x04050607, 0x00010203,
+			0x0c0d0e0f, 0x08090a0b, 0x04050607, 0x00010203,
+			0x0c0d0e0f, 0x08090a0b, 0x04050607, 0x00010203
+		);
+		ip_vec = _mm512_shuffle_epi8(ip_vec, bswap32);
+	}
+
 	/* mask 24 most significant bits */
 	idxes = _mm512_srli_epi32(ip_vec, 8);
 
@@ -78,7 +88,7 @@ dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
 
 static __rte_always_inline void
 dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
-	uint64_t *next_hops)
+	uint64_t *next_hops, bool be_addr)
 {
 	struct dir24_8_tbl *dp = (struct dir24_8_tbl *)p;
 	const __m512i zero = _mm512_set1_epi32(0);
@@ -89,6 +99,13 @@ dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
 	__mmask8 msk_ext;
 
 	ip_vec = _mm256_loadu_si256((const void *)ips);
+	if (be_addr) {
+		const __m256i bswap32 = _mm256_set_epi8(
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3
+		);
+		ip_vec = _mm256_shuffle_epi8(ip_vec, bswap32);
+	}
 	/* mask 24 most significant bits */
 	idxes_256 = _mm256_srli_epi32(ip_vec, 8);
 
@@ -114,52 +131,49 @@ dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
 	_mm512_storeu_si512(next_hops, res);
 }
 
-void
-rte_dir24_8_vec_lookup_bulk_1b(void *p, const uint32_t *ips,
-	uint64_t *next_hops, const unsigned int n)
-{
-	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint8_t));
-
-	dir24_8_lookup_bulk_1b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
+#define DECLARE_VECTOR_FN(suffix, nh_type, be_addr)			\
+void									\
+rte_dir24_8_vec_lookup_bulk_##suffix(void *p, const uint32_t *ips,	\
+	uint64_t *next_hops, const unsigned int n)			\
+{									\
+	uint32_t i;							\
+									\
+	for (i = 0; i < (n / 16); i++)					\
+		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16, \
+			sizeof(nh_type), be_addr);			\
+									\
+	dir24_8_lookup_bulk_##suffix(p, ips + i * 16, next_hops + i * 16, \
+		n - i * 16);						\
 }
 
-void
-rte_dir24_8_vec_lookup_bulk_2b(void *p, const uint32_t *ips,
-	uint64_t *next_hops, const unsigned int n)
-{
-	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint16_t));
-
-	dir24_8_lookup_bulk_2b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
-}
+DECLARE_VECTOR_FN(1b, uint8_t, false)
+DECLARE_VECTOR_FN(2b, uint16_t, false)
+DECLARE_VECTOR_FN(4b, uint32_t, false)
+DECLARE_VECTOR_FN(1b_be, uint8_t, true)
+DECLARE_VECTOR_FN(2b_be, uint16_t, true)
+DECLARE_VECTOR_FN(4b_be, uint32_t, true)
 
 void
-rte_dir24_8_vec_lookup_bulk_4b(void *p, const uint32_t *ips,
+rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n)
 {
 	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint32_t));
+	for (i = 0; i < (n / 8); i++)
+		dir24_8_vec_lookup_x8_8b(p, ips + i * 8,
+			next_hops + i * 8, false);
 
-	dir24_8_lookup_bulk_4b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
+	dir24_8_lookup_bulk_8b(p, ips + i * 8, next_hops + i * 8, n - i * 8);
 }
 
 void
-rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
+rte_dir24_8_vec_lookup_bulk_8b_be(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n)
 {
 	uint32_t i;
 	for (i = 0; i < (n / 8); i++)
-		dir24_8_vec_lookup_x8_8b(p, ips + i * 8, next_hops + i * 8);
+		dir24_8_vec_lookup_x8_8b(p, ips + i * 8,
+			next_hops + i * 8, true);
 
-	dir24_8_lookup_bulk_8b(p, ips + i * 8, next_hops + i * 8, n - i * 8);
+	dir24_8_lookup_bulk_8b_be(p, ips + i * 8,
+		next_hops + i * 8, n - i * 8);
 }
diff --git a/lib/fib/dir24_8_avx512.h b/lib/fib/dir24_8_avx512.h
index 1d3c2b9317..e9f7b72519 100644
--- a/lib/fib/dir24_8_avx512.h
+++ b/lib/fib/dir24_8_avx512.h
@@ -21,4 +21,19 @@ void
 rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n);
 
+void
+rte_dir24_8_vec_lookup_bulk_1b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_2b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_4b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_8b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
 #endif /* _DIR248_AVX512_H_ */
diff --git a/lib/fib/meson.build b/lib/fib/meson.build
index 6795f41a0a..394e93b53a 100644
--- a/lib/fib/meson.build
+++ b/lib/fib/meson.build
@@ -12,53 +12,22 @@ sources = files('rte_fib.c', 'rte_fib6.c', 'dir24_8.c', 'trie.c')
 headers = files('rte_fib.h', 'rte_fib6.h')
 deps += ['rib']
 
-# compile AVX512 version if:
-# we are building 64-bit binary AND binutils can generate proper code
-if dpdk_conf.has('RTE_ARCH_X86_64') and binutils_ok
-    # compile AVX512 version if either:
-    # a. we have AVX512F supported in minimum instruction set baseline
-    # b. it's not minimum instruction set, but supported by compiler
-    #
-    # in former case, just add avx512 C file to files list
-    # in latter case, compile c file to static lib, using correct
-    # compiler flags, and then have the .o file from static lib
-    # linked into main lib.
+if dpdk_conf.has('RTE_ARCH_X86_64')
+    if target_has_avx512
+        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT', '-DCC_TRIE_AVX512_SUPPORT']
+        sources += files('dir24_8_avx512.c', 'trie_avx512.c')
 
-    # check if all required flags already enabled (variant a).
-    acl_avx512_flags = ['__AVX512F__','__AVX512DQ__']
-    acl_avx512_on = true
-    foreach f:acl_avx512_flags
-        if cc.get_define(f, args: machine_args) == ''
-            acl_avx512_on = false
-        endif
-    endforeach
-
-    if acl_avx512_on == true
-        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT']
-        sources += files('dir24_8_avx512.c')
-        # TRIE AVX512 implementation uses avx512bw intrinsics along with
-        # avx512f and avx512dq
-        if cc.get_define('__AVX512BW__', args: machine_args) != ''
-            cflags += ['-DCC_TRIE_AVX512_SUPPORT']
-            sources += files('trie_avx512.c')
-        endif
-    elif cc.has_multi_arguments('-mavx512f', '-mavx512dq')
+    elif cc_has_avx512
         dir24_8_avx512_tmp = static_library('dir24_8_avx512_tmp',
                 'dir24_8_avx512.c',
                 dependencies: static_rte_eal,
-                c_args: cflags + ['-mavx512f', '-mavx512dq'])
+                c_args: cflags + ['-mavx512f', '-mavx512dq', '-mavx512bw'])
         objs += dir24_8_avx512_tmp.extract_objects('dir24_8_avx512.c')
-        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT']
-        # TRIE AVX512 implementation uses avx512bw intrinsics along with
-        # avx512f and avx512dq
-        if cc.has_argument('-mavx512bw')
-            trie_avx512_tmp = static_library('trie_avx512_tmp',
+        trie_avx512_tmp = static_library('trie_avx512_tmp',
                 'trie_avx512.c',
                 dependencies: static_rte_eal,
-                c_args: cflags + ['-mavx512f', \
-                    '-mavx512dq', '-mavx512bw'])
-            objs += trie_avx512_tmp.extract_objects('trie_avx512.c')
-            cflags += ['-DCC_TRIE_AVX512_SUPPORT']
-        endif
+                c_args: cflags + ['-mavx512f', '-mavx512dq', '-mavx512bw'])
+        objs += trie_avx512_tmp.extract_objects('trie_avx512.c')
+        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT', '-DCC_TRIE_AVX512_SUPPORT']
     endif
-endif
+endif
\ No newline at end of file
diff --git a/lib/fib/rte_fib.c b/lib/fib/rte_fib.c
index 4f9fba5a4f..30a55489ad 100644
--- a/lib/fib/rte_fib.c
+++ b/lib/fib/rte_fib.c
@@ -42,6 +42,7 @@ EAL_REGISTER_TAILQ(rte_fib_tailq)
 struct rte_fib {
 	char			name[RTE_FIB_NAMESIZE];
 	enum rte_fib_type	type;	/**< Type of FIB struct */
+	int flags;					/**< Flags */
 	struct rte_rib		*rib;	/**< RIB helper datastructure */
 	void			*dp;	/**< pointer to the dataplane struct*/
 	rte_fib_lookup_fn_t	lookup;	/**< FIB lookup function */
@@ -110,7 +111,7 @@ init_dataplane(struct rte_fib *fib, __rte_unused int socket_id,
 		if (fib->dp == NULL)
 			return -rte_errno;
 		fib->lookup = dir24_8_get_lookup_fn(fib->dp,
-			RTE_FIB_LOOKUP_DEFAULT);
+			RTE_FIB_LOOKUP_DEFAULT, !!(fib->flags & RTE_FIB_F_NETWORK_ORDER));
 		fib->modify = dir24_8_modify;
 		return 0;
 	default:
@@ -161,6 +162,7 @@ rte_fib_create(const char *name, int socket_id, struct rte_fib_conf *conf)
 
 	/* Check user arguments. */
 	if ((name == NULL) || (conf == NULL) ||	(conf->max_routes < 0) ||
+			(conf->flags & ~RTE_FIB_ALLOWED_FLAGS) ||
 			(conf->type > RTE_FIB_DIR24_8)) {
 		rte_errno = EINVAL;
 		return NULL;
@@ -214,6 +216,7 @@ rte_fib_create(const char *name, int socket_id, struct rte_fib_conf *conf)
 	rte_strlcpy(fib->name, name, sizeof(fib->name));
 	fib->rib = rib;
 	fib->type = conf->type;
+	fib->flags = conf->flags;
 	fib->def_nh = conf->default_nh;
 	ret = init_dataplane(fib, socket_id, conf);
 	if (ret < 0) {
@@ -329,7 +332,8 @@ rte_fib_select_lookup(struct rte_fib *fib,
 
 	switch (fib->type) {
 	case RTE_FIB_DIR24_8:
-		fn = dir24_8_get_lookup_fn(fib->dp, type);
+		fn = dir24_8_get_lookup_fn(fib->dp, type,
+			!!(fib->flags & RTE_FIB_F_NETWORK_ORDER));
 		if (fn == NULL)
 			return -EINVAL;
 		fib->lookup = fn;
diff --git a/lib/fib/rte_fib.h b/lib/fib/rte_fib.h
index d7a5aafe53..0c3e3e574e 100644
--- a/lib/fib/rte_fib.h
+++ b/lib/fib/rte_fib.h
@@ -28,6 +28,10 @@ struct rte_rib;
 /** Maximum depth value possible for IPv4 FIB. */
 #define RTE_FIB_MAXDEPTH	32
 
+/** If set fib lookup is expecting ipv4 in network byte order */
+#define RTE_FIB_F_NETWORK_ORDER	1
+#define RTE_FIB_ALLOWED_FLAGS	(RTE_FIB_F_NETWORK_ORDER)
+
 /** Type of FIB struct */
 enum rte_fib_type {
 	RTE_FIB_DUMMY,		/**< RIB tree based FIB */
@@ -87,6 +91,7 @@ struct rte_fib_conf {
 			uint32_t	num_tbl8;
 		} dir24_8;
 	};
+	unsigned int flags;	/**< Optional feature flags from RTE_FIB_F_* **/
 };
 
 /**
-- 
2.43.0

Re: [PATCH v5] fib: network byte order IPv4 lookup

[Stephen Hemminger]

On Mon, 14 Oct 2024 13:37:07 +0000
Vladimir Medvedkin <vladimir.medvedkin@intel.com> wrote:

> Previously when running rte_fib_lookup IPv4 addresses must have been in
> host byte order.
> 
> This patch adds a new flag RTE_FIB_FLAG_LOOKUP_BE that can be passed on
> fib create, which will allow to have IPv4 in network byte order on
> lookup.
> 
> Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
> ---

Acked-by: Stephen Hemminger <stephent@networkplumber.org>

Re: [PATCH v5] fib: network byte order IPv4 lookup

[David Marchand]

On Mon, Oct 14, 2024 at 5:22 PM Stephen Hemminger
<stephen@networkplumber.org> wrote:
> On Mon, 14 Oct 2024 13:37:07 +0000
> Vladimir Medvedkin <vladimir.medvedkin@intel.com> wrote:
>
> > Previously when running rte_fib_lookup IPv4 addresses must have been in
> > host byte order.
> >
> > This patch adds a new flag RTE_FIB_FLAG_LOOKUP_BE that can be passed on
> > fib create, which will allow to have IPv4 in network byte order on
> > lookup.
> >
> > Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
> Acked-by: Stephen Hemminger <stephent@networkplumber.org>

I aligned the meson bits to other libraries (passing cc_avx512_flags),
and changed internal flags field into an unsigned int (like the field
coming from the configuration structure).
Applied, thanks Vladimir.


-- 
David Marchand

[PATCH v2] fib: network byte order IPv4 lookup

[Vladimir Medvedkin]

Previously when running rte_fib_lookup IPv4 addresses must have been in
host byte order.

This patch adds a new flag RTE_FIB_FLAG_LOOKUP_BE that can be passed on
fib create, which will allow to have IPv4 in network byte order on
lookup.

Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
---
 app/test/test_fib.c      |  2 +-
 lib/fib/dir24_8.c        | 62 +++++++++++++++++++-----------
 lib/fib/dir24_8.h        | 44 ++++++++++++++++++++-
 lib/fib/dir24_8_avx512.c | 82 +++++++++++++++++++++++-----------------
 lib/fib/dir24_8_avx512.h | 15 ++++++++
 lib/fib/meson.build      | 38 +++++++------------
 lib/fib/rte_fib.c        |  7 +++-
 lib/fib/rte_fib.h        |  4 ++
 8 files changed, 169 insertions(+), 85 deletions(-)

diff --git a/app/test/test_fib.c b/app/test/test_fib.c
index 45dccca1f6..b0e53dbe01 100644
--- a/app/test/test_fib.c
+++ b/app/test/test_fib.c
@@ -319,7 +319,7 @@ int32_t
 test_lookup(void)
 {
 	struct rte_fib *fib = NULL;
-	struct rte_fib_conf config;
+	struct rte_fib_conf config = { 0 };
 	uint64_t def_nh = 100;
 	int ret;
 
diff --git a/lib/fib/dir24_8.c b/lib/fib/dir24_8.c
index c739e92304..5520f0f519 100644
--- a/lib/fib/dir24_8.c
+++ b/lib/fib/dir24_8.c
@@ -26,56 +26,72 @@
 #define ROUNDUP(x, y)	 RTE_ALIGN_CEIL(x, (1 << (32 - y)))
 
 static inline rte_fib_lookup_fn_t
-get_scalar_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_scalar_fn(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return dir24_8_lookup_bulk_1b;
+		return (be_addr) ? dir24_8_lookup_bulk_1b_be :
+					dir24_8_lookup_bulk_1b;
 	case RTE_FIB_DIR24_8_2B:
-		return dir24_8_lookup_bulk_2b;
+		return (be_addr) ? dir24_8_lookup_bulk_2b_be :
+					dir24_8_lookup_bulk_2b;
 	case RTE_FIB_DIR24_8_4B:
-		return dir24_8_lookup_bulk_4b;
+		return (be_addr) ? dir24_8_lookup_bulk_4b_be :
+					dir24_8_lookup_bulk_4b;
 	case RTE_FIB_DIR24_8_8B:
-		return dir24_8_lookup_bulk_8b;
+		return (be_addr) ? dir24_8_lookup_bulk_8b_be :
+					dir24_8_lookup_bulk_8b;
 	default:
 		return NULL;
 	}
 }
 
 static inline rte_fib_lookup_fn_t
-get_scalar_fn_inlined(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_scalar_fn_inlined(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return dir24_8_lookup_bulk_0;
+		return (be_addr) ? dir24_8_lookup_bulk_0_be :
+					dir24_8_lookup_bulk_0;
 	case RTE_FIB_DIR24_8_2B:
-		return dir24_8_lookup_bulk_1;
+		return (be_addr) ? dir24_8_lookup_bulk_1_be :
+					dir24_8_lookup_bulk_1;
 	case RTE_FIB_DIR24_8_4B:
-		return dir24_8_lookup_bulk_2;
+		return (be_addr) ? dir24_8_lookup_bulk_2_be :
+					dir24_8_lookup_bulk_2;
 	case RTE_FIB_DIR24_8_8B:
-		return dir24_8_lookup_bulk_3;
+		return (be_addr) ? dir24_8_lookup_bulk_3_be :
+					dir24_8_lookup_bulk_3;
 	default:
 		return NULL;
 	}
 }
 
 static inline rte_fib_lookup_fn_t
-get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
+get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
 {
 #ifdef CC_DIR24_8_AVX512_SUPPORT
 	if ((rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) <= 0) ||
+		(rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512DQ) <= 0) ||
 			(rte_vect_get_max_simd_bitwidth() < RTE_VECT_SIMD_512))
 		return NULL;
 
+	if (be_addr && (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512BW) <= 0))
+		return NULL;
+
 	switch (nh_sz) {
 	case RTE_FIB_DIR24_8_1B:
-		return rte_dir24_8_vec_lookup_bulk_1b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_1b_be :
+					rte_dir24_8_vec_lookup_bulk_1b;
 	case RTE_FIB_DIR24_8_2B:
-		return rte_dir24_8_vec_lookup_bulk_2b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_2b_be :
+					rte_dir24_8_vec_lookup_bulk_2b;
 	case RTE_FIB_DIR24_8_4B:
-		return rte_dir24_8_vec_lookup_bulk_4b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_4b_be :
+					rte_dir24_8_vec_lookup_bulk_4b;
 	case RTE_FIB_DIR24_8_8B:
-		return rte_dir24_8_vec_lookup_bulk_8b;
+		return (be_addr) ? rte_dir24_8_vec_lookup_bulk_8b_be :
+					rte_dir24_8_vec_lookup_bulk_8b;
 	default:
 		return NULL;
 	}
@@ -86,7 +102,7 @@ get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz)
 }
 
 rte_fib_lookup_fn_t
-dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type)
+dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type, bool be_addr)
 {
 	enum rte_fib_dir24_8_nh_sz nh_sz;
 	rte_fib_lookup_fn_t ret_fn;
@@ -99,16 +115,18 @@ dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type)
 
 	switch (type) {
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_MACRO:
-		return get_scalar_fn(nh_sz);
+		return get_scalar_fn(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_INLINE:
-		return get_scalar_fn_inlined(nh_sz);
+		return get_scalar_fn_inlined(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DIR24_8_SCALAR_UNI:
-		return dir24_8_lookup_bulk_uni;
+		return (be_addr) ? dir24_8_lookup_bulk_uni_be :
+						dir24_8_lookup_bulk_uni;
 	case RTE_FIB_LOOKUP_DIR24_8_VECTOR_AVX512:
-		return get_vector_fn(nh_sz);
+		return get_vector_fn(nh_sz, be_addr);
 	case RTE_FIB_LOOKUP_DEFAULT:
-		ret_fn = get_vector_fn(nh_sz);
-		return (ret_fn != NULL) ? ret_fn : get_scalar_fn(nh_sz);
+		ret_fn = get_vector_fn(nh_sz, be_addr);
+		return (ret_fn != NULL) ? ret_fn :
+			get_scalar_fn(nh_sz, be_addr);
 	default:
 		return NULL;
 	}
diff --git a/lib/fib/dir24_8.h b/lib/fib/dir24_8.h
index 7125049f15..2c776e118f 100644
--- a/lib/fib/dir24_8.h
+++ b/lib/fib/dir24_8.h
@@ -7,7 +7,9 @@
 #define _DIR24_8_H_
 
 #include <stdalign.h>
+#include <stdbool.h>
 
+#include <rte_byteorder.h>
 #include <rte_prefetch.h>
 #include <rte_branch_prediction.h>
 
@@ -237,6 +239,46 @@ dir24_8_lookup_bulk_uni(void *p, const uint32_t *ips,
 	}
 }
 
+#define BSWAP_MAX_LENGTH	64
+
+typedef void (*dir24_8_lookup_bulk_be_cb)(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+static inline void
+dir24_8_lookup_bulk_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n,
+	dir24_8_lookup_bulk_be_cb cb)
+{
+	uint32_t le_ips[BSWAP_MAX_LENGTH];
+	unsigned int i;
+
+	for (i = 0; i < n; i += BSWAP_MAX_LENGTH) {
+		int j;
+		for (j = 0; j < BSWAP_MAX_LENGTH && i + j < n; j++)
+			le_ips[j] = rte_be_to_cpu_32(ips[i + j]);
+
+		cb(p, le_ips, next_hops + i, j);
+	}
+}
+
+#define DECLARE_BE_LOOKUP_FN(name)					\
+static inline void							\
+name##_be(void *p, const uint32_t *ips,					\
+	uint64_t *next_hops, const unsigned int n)			\
+{									\
+	dir24_8_lookup_bulk_be(p, ips, next_hops, n, name);		\
+}
+
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_1b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_2b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_4b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_8b)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_0)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_1)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_2)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_3)
+DECLARE_BE_LOOKUP_FN(dir24_8_lookup_bulk_uni)
+
 void *
 dir24_8_create(const char *name, int socket_id, struct rte_fib_conf *conf);
 
@@ -244,7 +286,7 @@ void
 dir24_8_free(void *p);
 
 rte_fib_lookup_fn_t
-dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type);
+dir24_8_get_lookup_fn(void *p, enum rte_fib_lookup_type type, bool be_addr);
 
 int
 dir24_8_modify(struct rte_fib *fib, uint32_t ip, uint8_t depth,
diff --git a/lib/fib/dir24_8_avx512.c b/lib/fib/dir24_8_avx512.c
index 43dba28cfb..edd802abe4 100644
--- a/lib/fib/dir24_8_avx512.c
+++ b/lib/fib/dir24_8_avx512.c
@@ -10,7 +10,7 @@
 
 static __rte_always_inline void
 dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
-	uint64_t *next_hops, int size)
+	uint64_t *next_hops, int size, bool be_addr)
 {
 	struct dir24_8_tbl *dp = (struct dir24_8_tbl *)p;
 	__mmask16 msk_ext;
@@ -28,6 +28,16 @@ dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
 		res_msk = _mm512_set1_epi32(UINT16_MAX);
 
 	ip_vec = _mm512_loadu_si512(ips);
+	if (be_addr) {
+		const __m512i bswap32 = _mm512_set_epi8(
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3
+		);
+		ip_vec = _mm512_shuffle_epi8(ip_vec, bswap32);
+	}
+
 	/* mask 24 most significant bits */
 	idxes = _mm512_srli_epi32(ip_vec, 8);
 
@@ -78,7 +88,7 @@ dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
 
 static __rte_always_inline void
 dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
-	uint64_t *next_hops)
+	uint64_t *next_hops, bool be_addr)
 {
 	struct dir24_8_tbl *dp = (struct dir24_8_tbl *)p;
 	const __m512i zero = _mm512_set1_epi32(0);
@@ -89,6 +99,13 @@ dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
 	__mmask8 msk_ext;
 
 	ip_vec = _mm256_loadu_si256((const void *)ips);
+	if (be_addr) {
+		const __m256i bswap32 = _mm256_set_epi8(
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
+			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3
+		);
+		ip_vec = _mm256_shuffle_epi8(ip_vec, bswap32);
+	}
 	/* mask 24 most significant bits */
 	idxes_256 = _mm256_srli_epi32(ip_vec, 8);
 
@@ -114,52 +131,49 @@ dir24_8_vec_lookup_x8_8b(void *p, const uint32_t *ips,
 	_mm512_storeu_si512(next_hops, res);
 }
 
-void
-rte_dir24_8_vec_lookup_bulk_1b(void *p, const uint32_t *ips,
-	uint64_t *next_hops, const unsigned int n)
-{
-	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint8_t));
-
-	dir24_8_lookup_bulk_1b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
+#define DECLARE_VECTOR_FN(suffix, nh_type, be_addr)			\
+void									\
+rte_dir24_8_vec_lookup_bulk_##suffix(void *p, const uint32_t *ips,	\
+	uint64_t *next_hops, const unsigned int n)			\
+{									\
+	uint32_t i;							\
+									\
+	for (i = 0; i < (n / 16); i++)					\
+		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16, \
+			sizeof(nh_type), be_addr);			\
+									\
+	dir24_8_lookup_bulk_##suffix(p, ips + i * 16, next_hops + i * 16, \
+		n - i * 16);						\
 }
 
-void
-rte_dir24_8_vec_lookup_bulk_2b(void *p, const uint32_t *ips,
-	uint64_t *next_hops, const unsigned int n)
-{
-	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint16_t));
-
-	dir24_8_lookup_bulk_2b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
-}
+DECLARE_VECTOR_FN(1b, uint8_t, false)
+DECLARE_VECTOR_FN(2b, uint16_t, false)
+DECLARE_VECTOR_FN(4b, uint32_t, false)
+DECLARE_VECTOR_FN(1b_be, uint8_t, true)
+DECLARE_VECTOR_FN(2b_be, uint16_t, true)
+DECLARE_VECTOR_FN(4b_be, uint32_t, true)
 
 void
-rte_dir24_8_vec_lookup_bulk_4b(void *p, const uint32_t *ips,
+rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n)
 {
 	uint32_t i;
-	for (i = 0; i < (n / 16); i++)
-		dir24_8_vec_lookup_x16(p, ips + i * 16, next_hops + i * 16,
-			sizeof(uint32_t));
+	for (i = 0; i < (n / 8); i++)
+		dir24_8_vec_lookup_x8_8b(p, ips + i * 8,
+			next_hops + i * 8, false);
 
-	dir24_8_lookup_bulk_4b(p, ips + i * 16, next_hops + i * 16,
-		n - i * 16);
+	dir24_8_lookup_bulk_8b(p, ips + i * 8, next_hops + i * 8, n - i * 8);
 }
 
 void
-rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
+rte_dir24_8_vec_lookup_bulk_8b_be(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n)
 {
 	uint32_t i;
 	for (i = 0; i < (n / 8); i++)
-		dir24_8_vec_lookup_x8_8b(p, ips + i * 8, next_hops + i * 8);
+		dir24_8_vec_lookup_x8_8b(p, ips + i * 8,
+			next_hops + i * 8, true);
 
-	dir24_8_lookup_bulk_8b(p, ips + i * 8, next_hops + i * 8, n - i * 8);
+	dir24_8_lookup_bulk_8b_be(p, ips + i * 8,
+		next_hops + i * 8, n - i * 8);
 }
diff --git a/lib/fib/dir24_8_avx512.h b/lib/fib/dir24_8_avx512.h
index 1d3c2b9317..e9f7b72519 100644
--- a/lib/fib/dir24_8_avx512.h
+++ b/lib/fib/dir24_8_avx512.h
@@ -21,4 +21,19 @@ void
 rte_dir24_8_vec_lookup_bulk_8b(void *p, const uint32_t *ips,
 	uint64_t *next_hops, const unsigned int n);
 
+void
+rte_dir24_8_vec_lookup_bulk_1b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_2b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_4b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
+
+void
+rte_dir24_8_vec_lookup_bulk_8b_be(void *p, const uint32_t *ips,
+	uint64_t *next_hops, const unsigned int n);
 #endif /* _DIR248_AVX512_H_ */
diff --git a/lib/fib/meson.build b/lib/fib/meson.build
index 6795f41a0a..8c03496cdc 100644
--- a/lib/fib/meson.build
+++ b/lib/fib/meson.build
@@ -25,40 +25,28 @@ if dpdk_conf.has('RTE_ARCH_X86_64') and binutils_ok
     # linked into main lib.
 
     # check if all required flags already enabled (variant a).
-    acl_avx512_flags = ['__AVX512F__','__AVX512DQ__']
-    acl_avx512_on = true
-    foreach f:acl_avx512_flags
+    fib_avx512_flags = ['__AVX512F__','__AVX512DQ__', '__AVX512BW__']
+    fib_avx512_on = true
+    foreach f:fib_avx512_flags
         if cc.get_define(f, args: machine_args) == ''
-            acl_avx512_on = false
+            fib_avx512_on = false
         endif
     endforeach
 
-    if acl_avx512_on == true
-        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT']
-        sources += files('dir24_8_avx512.c')
-        # TRIE AVX512 implementation uses avx512bw intrinsics along with
-        # avx512f and avx512dq
-        if cc.get_define('__AVX512BW__', args: machine_args) != ''
-            cflags += ['-DCC_TRIE_AVX512_SUPPORT']
-            sources += files('trie_avx512.c')
-        endif
-    elif cc.has_multi_arguments('-mavx512f', '-mavx512dq')
+    if fib_avx512_on == true
+        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT', '-DCC_TRIE_AVX512_SUPPORT']
+        sources += files('dir24_8_avx512.c', 'trie_avx512.c')
+    elif cc.has_multi_arguments('-mavx512f', '-mavx512dq', '-mavx512bw')
         dir24_8_avx512_tmp = static_library('dir24_8_avx512_tmp',
                 'dir24_8_avx512.c',
                 dependencies: static_rte_eal,
-                c_args: cflags + ['-mavx512f', '-mavx512dq'])
+                c_args: cflags + ['-mavx512f', '-mavx512dq', '-mavx512bw'])
         objs += dir24_8_avx512_tmp.extract_objects('dir24_8_avx512.c')
-        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT']
-        # TRIE AVX512 implementation uses avx512bw intrinsics along with
-        # avx512f and avx512dq
-        if cc.has_argument('-mavx512bw')
-            trie_avx512_tmp = static_library('trie_avx512_tmp',
+        trie_avx512_tmp = static_library('trie_avx512_tmp',
                 'trie_avx512.c',
                 dependencies: static_rte_eal,
-                c_args: cflags + ['-mavx512f', \
-                    '-mavx512dq', '-mavx512bw'])
-            objs += trie_avx512_tmp.extract_objects('trie_avx512.c')
-            cflags += ['-DCC_TRIE_AVX512_SUPPORT']
-        endif
+                c_args: cflags + ['-mavx512f', '-mavx512dq', '-mavx512bw'])
+        objs += trie_avx512_tmp.extract_objects('trie_avx512.c')
+        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT', '-DCC_TRIE_AVX512_SUPPORT']
     endif
 endif
diff --git a/lib/fib/rte_fib.c b/lib/fib/rte_fib.c
index 4f9fba5a4f..991e48b5ea 100644
--- a/lib/fib/rte_fib.c
+++ b/lib/fib/rte_fib.c
@@ -42,6 +42,7 @@ EAL_REGISTER_TAILQ(rte_fib_tailq)
 struct rte_fib {
 	char			name[RTE_FIB_NAMESIZE];
 	enum rte_fib_type	type;	/**< Type of FIB struct */
+	int flags;					/**< Flags */
 	struct rte_rib		*rib;	/**< RIB helper datastructure */
 	void			*dp;	/**< pointer to the dataplane struct*/
 	rte_fib_lookup_fn_t	lookup;	/**< FIB lookup function */
@@ -110,7 +111,7 @@ init_dataplane(struct rte_fib *fib, __rte_unused int socket_id,
 		if (fib->dp == NULL)
 			return -rte_errno;
 		fib->lookup = dir24_8_get_lookup_fn(fib->dp,
-			RTE_FIB_LOOKUP_DEFAULT);
+			RTE_FIB_LOOKUP_DEFAULT, !!(fib->flags & RTE_FIB_FLAG_LOOKUP_BE));
 		fib->modify = dir24_8_modify;
 		return 0;
 	default:
@@ -214,6 +215,7 @@ rte_fib_create(const char *name, int socket_id, struct rte_fib_conf *conf)
 	rte_strlcpy(fib->name, name, sizeof(fib->name));
 	fib->rib = rib;
 	fib->type = conf->type;
+	fib->flags = conf->flags;
 	fib->def_nh = conf->default_nh;
 	ret = init_dataplane(fib, socket_id, conf);
 	if (ret < 0) {
@@ -329,7 +331,8 @@ rte_fib_select_lookup(struct rte_fib *fib,
 
 	switch (fib->type) {
 	case RTE_FIB_DIR24_8:
-		fn = dir24_8_get_lookup_fn(fib->dp, type);
+		fn = dir24_8_get_lookup_fn(fib->dp, type,
+			!!(fib->flags & RTE_FIB_FLAG_LOOKUP_BE));
 		if (fn == NULL)
 			return -EINVAL;
 		fib->lookup = fn;
diff --git a/lib/fib/rte_fib.h b/lib/fib/rte_fib.h
index d7a5aafe53..1617235e85 100644
--- a/lib/fib/rte_fib.h
+++ b/lib/fib/rte_fib.h
@@ -28,6 +28,9 @@ struct rte_rib;
 /** Maximum depth value possible for IPv4 FIB. */
 #define RTE_FIB_MAXDEPTH	32
 
+/** If set fib lookup is expecting ipv4 in network byte order */
+#define RTE_FIB_FLAG_LOOKUP_BE	1
+
 /** Type of FIB struct */
 enum rte_fib_type {
 	RTE_FIB_DUMMY,		/**< RIB tree based FIB */
@@ -76,6 +79,7 @@ enum rte_fib_lookup_type {
 /** FIB configuration structure */
 struct rte_fib_conf {
 	enum rte_fib_type type; /**< Type of FIB struct */
+	unsigned int flags;
 	/** Default value returned on lookup if there is no route */
 	uint64_t default_nh;
 	int	max_routes;
-- 
2.34.1

Re: [PATCH v2] fib: network byte order IPv4 lookup

[Stephen Hemminger]

On Tue,  8 Oct 2024 17:16:05 +0000
Vladimir Medvedkin <vladimir.medvedkin@intel.com> wrote:

> Previously when running rte_fib_lookup IPv4 addresses must have been in
> host byte order.
> 
> This patch adds a new flag RTE_FIB_FLAG_LOOKUP_BE that can be passed on
> fib create, which will allow to have IPv4 in network byte order on
> lookup.
> 
> Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
> ---

github build failed with this.

FAILED: lib/76b5a35@@rte_fib at sta/fib_dir24_8.c.o 
ccache gcc -Ilib/76b5a35@@rte_fib at sta -Ilib -I../lib -Ilib/fib -I../lib/fib -I. -I../ -Iconfig -I../config -Ilib/eal/include -I../lib/eal/include -Ilib/eal/linux/include -I../lib/eal/linux/include -Ilib/eal/x86/include -I../lib/eal/x86/include -Ilib/eal/common -I../lib/eal/common -Ilib/eal -I../lib/eal -Ilib/kvargs -I../lib/kvargs -Ilib/log -I../lib/log -Ilib/telemetry/../metrics -I../lib/telemetry/../metrics -Ilib/telemetry -I../lib/telemetry -Ilib/rib -I../lib/rib -Ilib/mempool -I../lib/mempool -Ilib/ring -I../lib/ring -fdiagnostics-color=always -pipe -D_FILE_OFFSET_BITS=64 -Wall -Winvalid-pch -Wextra -Werror -std=c11 -O2 -g -include rte_config.h -Wcast-qual -Wdeprecated -Wformat -Wformat-nonliteral -Wformat-security -Wmissing-declarations -Wmissing-prototypes -Wnested-externs -Wold-style-definition -Wpointer-arith -Wsign-compare -Wstrict-prototypes -Wundef -Wwrite-strings -Wno-address-of-packed-member -Wno-packed-not-aligned -Wno-missing-field-initializers -Wno-zero-length-bounds -Wno-pointer-to-int-cast -D_GNU_SOURCE -m32 -fPIC -march=corei7 -mrtm -DALLOW_EXPERIMENTAL_API -DALLOW_INTERNAL_API -Wno-format-truncation -DRTE_LOG_DEFAULT_LOGTYPE=lib.fib -MD -MQ 'lib/76b5a35@@rte_fib at sta/fib_dir24_8.c.o' -MF 'lib/76b5a35@@rte_fib at sta/fib_dir24_8.c.o.d' -o 'lib/76b5a35@@rte_fib at sta/fib_dir24_8.c.o' -c ../lib/fib/dir24_8.c
../lib/fib/dir24_8.c: In function ‘get_vector_fn’:
../lib/fib/dir24_8.c:71:54: error: unused parameter ‘be_addr’ [-Werror=unused-parameter]
   71 | get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
      |    

Re: [PATCH v2] fib: network byte order IPv4 lookup

[David Marchand]

Hi Vladimir,

On Tue, Oct 8, 2024 at 7:16 PM Vladimir Medvedkin
<vladimir.medvedkin@intel.com> wrote:
> diff --git a/lib/fib/dir24_8_avx512.c b/lib/fib/dir24_8_avx512.c
> index 43dba28cfb..edd802abe4 100644
> --- a/lib/fib/dir24_8_avx512.c
> +++ b/lib/fib/dir24_8_avx512.c
> @@ -10,7 +10,7 @@
>
>  static __rte_always_inline void
>  dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
> -       uint64_t *next_hops, int size)
> +       uint64_t *next_hops, int size, bool be_addr)
>  {
>         struct dir24_8_tbl *dp = (struct dir24_8_tbl *)p;
>         __mmask16 msk_ext;
> @@ -28,6 +28,16 @@ dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
>                 res_msk = _mm512_set1_epi32(UINT16_MAX);
>
>         ip_vec = _mm512_loadu_si512(ips);
> +       if (be_addr) {
> +               const __m512i bswap32 = _mm512_set_epi8(

Some toolchains do not like _mm512_set_epi8 (reported by the CI).


> +                       12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
> +                       12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
> +                       12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
> +                       12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3
> +               );
> +               ip_vec = _mm512_shuffle_epi8(ip_vec, bswap32);
> +       }
> +
>         /* mask 24 most significant bits */
>         idxes = _mm512_srli_epi32(ip_vec, 8);
>

[snip]

> diff --git a/lib/fib/meson.build b/lib/fib/meson.build
> index 6795f41a0a..8c03496cdc 100644
> --- a/lib/fib/meson.build
> +++ b/lib/fib/meson.build
> @@ -25,40 +25,28 @@ if dpdk_conf.has('RTE_ARCH_X86_64') and binutils_ok
>      # linked into main lib.
>
>      # check if all required flags already enabled (variant a).
> -    acl_avx512_flags = ['__AVX512F__','__AVX512DQ__']
> -    acl_avx512_on = true
> -    foreach f:acl_avx512_flags
> +    fib_avx512_flags = ['__AVX512F__','__AVX512DQ__', '__AVX512BW__']
> +    fib_avx512_on = true
> +    foreach f:fib_avx512_flags
>          if cc.get_define(f, args: machine_args) == ''
> -            acl_avx512_on = false
> +            fib_avx512_on = false
>          endif
>      endforeach

Please reuse the common checks recently merged, see for example:
https://git.dpdk.org/dpdk/diff/drivers/event/dlb2/meson.build?id=ef7a4025cd714189dc333bb19ea60c2abdeffb7d


>
> -    if acl_avx512_on == true
> -        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT']
> -        sources += files('dir24_8_avx512.c')
> -        # TRIE AVX512 implementation uses avx512bw intrinsics along with
> -        # avx512f and avx512dq
> -        if cc.get_define('__AVX512BW__', args: machine_args) != ''
> -            cflags += ['-DCC_TRIE_AVX512_SUPPORT']
> -            sources += files('trie_avx512.c')
> -        endif
> -    elif cc.has_multi_arguments('-mavx512f', '-mavx512dq')
> +    if fib_avx512_on == true
> +        cflags += ['-DCC_DIR24_8_AVX512_SUPPORT', '-DCC_TRIE_AVX512_SUPPORT']

Nit: now that both dir24_8 and trie share the same requirement, can we
go with a simple CC_AVX512_SUPPORT?


-- 
David Marchand

Re: [PATCH v2] fib: network byte order IPv4 lookup

[David Marchand]

On Wed, Oct 9, 2024 at 11:51 AM David Marchand
<david.marchand@redhat.com> wrote:
>
> Hi Vladimir,
>
> On Tue, Oct 8, 2024 at 7:16 PM Vladimir Medvedkin
> <vladimir.medvedkin@intel.com> wrote:
> > diff --git a/lib/fib/dir24_8_avx512.c b/lib/fib/dir24_8_avx512.c
> > index 43dba28cfb..edd802abe4 100644
> > --- a/lib/fib/dir24_8_avx512.c
> > +++ b/lib/fib/dir24_8_avx512.c
> > @@ -10,7 +10,7 @@
> >
> >  static __rte_always_inline void
> >  dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
> > -       uint64_t *next_hops, int size)
> > +       uint64_t *next_hops, int size, bool be_addr)
> >  {
> >         struct dir24_8_tbl *dp = (struct dir24_8_tbl *)p;
> >         __mmask16 msk_ext;
> > @@ -28,6 +28,16 @@ dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
> >                 res_msk = _mm512_set1_epi32(UINT16_MAX);
> >
> >         ip_vec = _mm512_loadu_si512(ips);
> > +       if (be_addr) {
> > +               const __m512i bswap32 = _mm512_set_epi8(
>
> Some toolchains do not like _mm512_set_epi8 (reported by the CI).

Probably related to gcc commit 4e6a811fad69 ("avx512fintrin.h
(_mm512_set_epi16, [...]): New intrinsics.") introduced in gcc 9.
Some distributions in the CI come with a gcc < 9.

We had a similar situation in the hash library in the past,
fba335b4b204 ("hash: fix Toeplitz hash implementation").


-- 
David Marchand

Re: [PATCH v2] fib: network byte order IPv4 lookup

[Medvedkin, Vladimir]

Hi David,

On 09/10/2024 11:56, David Marchand wrote:
> On Wed, Oct 9, 2024 at 11:51 AM David Marchand
> <david.marchand@redhat.com> wrote:
>> Hi Vladimir,
>>
>> On Tue, Oct 8, 2024 at 7:16 PM Vladimir Medvedkin
>> <vladimir.medvedkin@intel.com> wrote:
>>> diff --git a/lib/fib/dir24_8_avx512.c b/lib/fib/dir24_8_avx512.c
>>> index 43dba28cfb..edd802abe4 100644
>>> --- a/lib/fib/dir24_8_avx512.c
>>> +++ b/lib/fib/dir24_8_avx512.c
>>> @@ -10,7 +10,7 @@
>>>
>>>   static __rte_always_inline void
>>>   dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
>>> -       uint64_t *next_hops, int size)
>>> +       uint64_t *next_hops, int size, bool be_addr)
>>>   {
>>>          struct dir24_8_tbl *dp = (struct dir24_8_tbl *)p;
>>>          __mmask16 msk_ext;
>>> @@ -28,6 +28,16 @@ dir24_8_vec_lookup_x16(void *p, const uint32_t *ips,
>>>                  res_msk = _mm512_set1_epi32(UINT16_MAX);
>>>
>>>          ip_vec = _mm512_loadu_si512(ips);
>>> +       if (be_addr) {
>>> +               const __m512i bswap32 = _mm512_set_epi8(
>> Some toolchains do not like _mm512_set_epi8 (reported by the CI).
> Probably related to gcc commit 4e6a811fad69 ("avx512fintrin.h
> (_mm512_set_epi16, [...]): New intrinsics.") introduced in gcc 9.
> Some distributions in the CI come with a gcc < 9.
>
> We had a similar situation in the hash library in the past,
> fba335b4b204 ("hash: fix Toeplitz hash implementation").
>
Thanks, I'll change it with _mm512_set_epi32(), afaik it should be 
supported by an old gcc

-- 
Regards,
Vladimir

Re: [PATCH v2] fib: network byte order IPv4 lookup

[Stephen Hemminger]

On Tue,  8 Oct 2024 17:16:05 +0000
Vladimir Medvedkin <vladimir.medvedkin@intel.com> wrote:

> Previously when running rte_fib_lookup IPv4 addresses must have been in
> host byte order.
> 
> This patch adds a new flag RTE_FIB_FLAG_LOOKUP_BE that can be passed on
> fib create, which will allow to have IPv4 in network byte order on
> lookup.
> 
> Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>

Need to address David's comment see the build failures.

Build URL: https://github.com/ovsrobot/dpdk/actions/runs/11240928255
Build Logs:
-----------------------Summary of failed steps-----------------------
"ubuntu-22.04-gcc-static-i386" failed at step Build and test
"ubuntu-22.04-gcc-shared-aarch64" failed at step Build and test
"ubuntu-22.04-gcc-ppc64le" failed at step Build and test
"ubuntu-22.04-gcc-riscv64" failed at step Build and test
----------------------End summary of failed steps--------------------

-------------------------------BEGIN LOGS----------------------------
####################################################################################
#### [Begin job log] "ubuntu-22.04-gcc-static-i386" at step Build and test
####################################################################################
[423/3186] Compiling C object 'lib/76b5a35@@rte_fib at sta/fib_rte_fib.c.o'.
[424/3186] Compiling C object 'lib/76b5a35@@rte_pdcp at sta/pdcp_pdcp_ctrl_pdu.c.o'.
[425/3186] Compiling C object 'lib/76b5a35@@rte_pdcp at sta/pdcp_pdcp_reorder.c.o'.
[426/3186] Generating ipsec.sym_chk with a meson_exe.py custom command.
[427/3186] Linking target lib/librte_ipsec.so.25.0.
[428/3186] Compiling C object 'lib/76b5a35@@rte_pdcp at sta/pdcp_rte_pdcp.c.o'.
[429/3186] Generating symbol file 'lib/76b5a35@@rte_ipsec at sha/librte_ipsec.so.25.0.symbols'.
[430/3186] Compiling C object 'lib/76b5a35@@rte_fib at sta/fib_rte_fib6.c.o'.
[431/3186] Compiling C object 'lib/76b5a35@@rte_port at sta/port_port_log.c.o'.
[432/3186] Compiling C object 'lib/76b5a35@@rte_fib at sta/fib_trie.c.o'.
[433/3186] Compiling C object 'lib/76b5a35@@rte_fib at sta/fib_dir24_8.c.o'.
FAILED: lib/76b5a35@@rte_fib at sta/fib_dir24_8.c.o 
ccache gcc -Ilib/76b5a35@@rte_fib at sta -Ilib -I../lib -Ilib/fib -I../lib/fib -I. -I../ -Iconfig -I../config -Ilib/eal/include -I../lib/eal/include -Ilib/eal/linux/include -I../lib/eal/linux/include -Ilib/eal/x86/include -I../lib/eal/x86/include -Ilib/eal/common -I../lib/eal/common -Ilib/eal -I../lib/eal -Ilib/kvargs -I../lib/kvargs -Ilib/log -I../lib/log -Ilib/telemetry/../metrics -I../lib/telemetry/../metrics -Ilib/telemetry -I../lib/telemetry -Ilib/rib -I../lib/rib -Ilib/mempool -I../lib/mempool -Ilib/ring -I../lib/ring -fdiagnostics-color=always -pipe -D_FILE_OFFSET_BITS=64 -Wall -Winvalid-pch -Wextra -Werror -std=c11 -O2 -g -include rte_config.h -Wcast-qual -Wdeprecated -Wformat -Wformat-nonliteral -Wformat-security -Wmissing-declarations -Wmissing-prototypes -Wnested-externs -Wold-style-definition -Wpointer-arith -Wsign-compare -Wstrict-prototypes -Wundef -Wwrite-strings -Wno-address-of-packed-member -Wno-packed-not-aligned -Wno-missing-field-initializers -Wno-zero-length-bounds -Wno-pointer-to-int-cast -D_GNU_SOURCE -m32 -fPIC -march=corei7 -mrtm -DALLOW_EXPERIMENTAL_API -DALLOW_INTERNAL_API -Wno-format-truncation -DRTE_LOG_DEFAULT_LOGTYPE=lib.fib -MD -MQ 'lib/76b5a35@@rte_fib at sta/fib_dir24_8.c.o' -MF 'lib/76b5a35@@rte_fib at sta/fib_dir24_8.c.o.d' -o 'lib/76b5a35@@rte_fib at sta/fib_dir24_8.c.o' -c ../lib/fib/dir24_8.c
../lib/fib/dir24_8.c: In function ‘get_vector_fn’:
../lib/fib/dir24_8.c:71:54: error: unused parameter ‘be_addr’ [-Werror=unused-parameter]
   71 | get_vector_fn(enum rte_fib_dir24_8_nh_sz nh_sz, bool be_addr)
      |                                                      ^
cc1: all warnings being treated as errors
[434/3186] Compiling C object 'lib/76b5a35@@rte_port at sta/port_rte_port_ethdev.c.o'.
[435/3186] Compiling C object 'lib/76b5a35@@rte_port at sta/port_rte_port_fd.c.o'.
[436/3186] Compiling C object 'lib/76b5a35@@rte_pdcp at sta/pdcp_pdcp_process.c.o'.
[437/3186] Compiling C object 'lib/76b5a35@@rte_vhost at sta/vhost_vhost_crypto.c.o'.
[438/3186] Compiling C object 'lib/76b5a35@@rte_vhost at sta/vhost_virtio_net.c.o'.
ninja: build stopped: subcommand failed.
##[error]Process completed with exit code 1.
####################################################################################
#### [End job log] "ubuntu-22.04-gcc-static-i386" at step Build and test
####################################################################################