Re: [PATCH] examples/l3fwd: em path hash offload to machine
From: Hemant Agrawal <hidden>
Date: 2016-10-07 07:06:20
Hi Jerin, Thanks for the review, I will send a v2 with the suggestions made Regards, Hemant
-----Original Message----- From: Jerin Jacob [mailto:jerin.jacob@caviumnetworks.com] Sent: Wednesday, October 05, 2016 5:23 PM To: Hemant Agrawal <redacted> Cc: dev@dpdk.org Subject: Re: [dpdk-dev] [PATCH] examples/l3fwd: em path hash offload to machine On Tue, Aug 23, 2016 at 08:24:39PM +0530, Hemant Agrawal wrote: Maybe you can change the subject line to: examples/l3fwd: em: use hw accelerated crc hash function for arm64 instead of: examples/l3fwd: em path hash offload to machinequoted
if machine level CRC extension are available, offload the hash to machine provided functions e.g. armv8-a CRC extensions support it Signed-off-by: Hemant Agrawal <redacted> --- examples/l3fwd/l3fwd_em.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-)diff --git a/examples/l3fwd/l3fwd_em.c b/examples/l3fwd/l3fwd_em.c index def5a02..a889c67 100644 --- a/examples/l3fwd/l3fwd_em.c +++ b/examples/l3fwd/l3fwd_em.c@@ -58,13 +58,13 @@ #include "l3fwd.h" -#ifdef RTE_MACHINE_CPUFLAG_SSE4_2 +#if defined(RTE_MACHINE_CPUFLAG_SSE4_2) || +defined(RTE_MACHINE_CPUFLAG_CRC32)Rather than adding new compilation flag everywhere, Maybe you can add #if defined(RTE_MACHINE_CPUFLAG_SSE4_2) && defined(RTE_MACHINE_CPUFLAG_CRC32) #define EM_HASH_CRC 1 #endif something like above to reduce the change for future platforms with crc support. Other than that, you can add: Reviewed-by: Jerin Jacob <redacted>quoted
#include <rte_hash_crc.h> #define DEFAULT_HASH_FUNC rte_hash_crc #else #include <rte_jhash.h> #define DEFAULT_HASH_FUNC rte_jhash -#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */ +#endif #define IPV6_ADDR_LEN 16@@ -169,17 +169,17 @@ ipv4_hash_crc(const void *data, __rte_unuseduint32_t data_len,quoted
t = k->proto; p = (const uint32_t *)&k->port_src; -#ifdef RTE_MACHINE_CPUFLAG_SSE4_2 +#if defined(RTE_MACHINE_CPUFLAG_SSE4_2) || +defined(RTE_MACHINE_CPUFLAG_CRC32) init_val = rte_hash_crc_4byte(t, init_val); init_val = rte_hash_crc_4byte(k->ip_src, init_val); init_val = rte_hash_crc_4byte(k->ip_dst, init_val); init_val = rte_hash_crc_4byte(*p, init_val); -#else /* RTE_MACHINE_CPUFLAG_SSE4_2 */ +#else init_val = rte_jhash_1word(t, init_val); init_val = rte_jhash_1word(k->ip_src, init_val); init_val = rte_jhash_1word(k->ip_dst, init_val); init_val = rte_jhash_1word(*p, init_val); -#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */ +#endif return init_val; }@@ -191,16 +191,16 @@ ipv6_hash_crc(const void *data, __rte_unuseduint32_t data_len,quoted
const union ipv6_5tuple_host *k; uint32_t t; const uint32_t *p; -#ifdef RTE_MACHINE_CPUFLAG_SSE4_2 +#if defined(RTE_MACHINE_CPUFLAG_SSE4_2) || +defined(RTE_MACHINE_CPUFLAG_CRC32) const uint32_t *ip_src0, *ip_src1, *ip_src2, *ip_src3; const uint32_t *ip_dst0, *ip_dst1, *ip_dst2, *ip_dst3; -#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */ +#endif k = data; t = k->proto; p = (const uint32_t *)&k->port_src; -#ifdef RTE_MACHINE_CPUFLAG_SSE4_2 +#if defined(RTE_MACHINE_CPUFLAG_SSE4_2) || +defined(RTE_MACHINE_CPUFLAG_CRC32) ip_src0 = (const uint32_t *) k->ip_src; ip_src1 = (const uint32_t *)(k->ip_src+4); ip_src2 = (const uint32_t *)(k->ip_src+8); @@ -219,14 +219,14 @@ ipv6_hash_crc(const void *data, __rte_unused uint32_t data_len, init_val = rte_hash_crc_4byte(*ip_dst2, init_val); init_val = rte_hash_crc_4byte(*ip_dst3, init_val); init_val = rte_hash_crc_4byte(*p, init_val); -#else /* RTE_MACHINE_CPUFLAG_SSE4_2 */ +#else init_val = rte_jhash_1word(t, init_val); init_val = rte_jhash(k->ip_src, sizeof(uint8_t) * IPV6_ADDR_LEN, init_val); init_val = rte_jhash(k->ip_dst, sizeof(uint8_t) * IPV6_ADDR_LEN, init_val); init_val = rte_jhash_1word(*p, init_val); -#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */ +#endif return init_val; } -- 1.9.1