[dpdk-dev] [PATCH v3] ipsec: optimize with c11 atomic for sa outbound sqn update

[Phil Yang]

For SA outbound packets, rte_atomic64_add_return is used to generate
SQN atomically. Use c11 atomics with RELAXED ordering for outbound SQN
update instead of rte_atomic ops which enforce unnecessary barriers on
aarch64.

Signed-off-by: Phil Yang <phil.yang at arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang at arm.com>
Reviewed-by: Gavin Hu <gavin.hu at arm.com>
---
v3:
1. since libatomic dependency for 32-bit clang added globally, so remove
the redundant code.
2. collapse union outb to unint64_t outb as the rte_atomic is no needed.

v2:
split from the "generic rte atomic APIs deprecate proposal" patchset.

 lib/librte_ipsec/ipsec_sqn.h | 6 +++---
 lib/librte_ipsec/sa.c        | 2 +-
 lib/librte_ipsec/sa.h        | 5 +----
 3 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/lib/librte_ipsec/ipsec_sqn.h b/lib/librte_ipsec/ipsec_sqn.h
index 0c2f76a..2636cb1 100644
--- a/lib/librte_ipsec/ipsec_sqn.h
+++ b/lib/librte_ipsec/ipsec_sqn.h
@@ -128,10 +128,10 @@ esn_outb_update_sqn(struct rte_ipsec_sa *sa, uint32_t *num)
 
 	n = *num;
 	if (SQN_ATOMIC(sa))
-		sqn = (uint64_t)rte_atomic64_add_return(&sa->sqn.outb.atom, n);
+		sqn = __atomic_add_fetch(&sa->sqn.outb, n, __ATOMIC_RELAXED);
 	else {
-		sqn = sa->sqn.outb.raw + n;
-		sa->sqn.outb.raw = sqn;
+		sqn = sa->sqn.outb + n;
+		sa->sqn.outb = sqn;
 	}
 
 	/* overflow */
diff --git a/lib/librte_ipsec/sa.c b/lib/librte_ipsec/sa.c
index ada195c..e59189d 100644
--- a/lib/librte_ipsec/sa.c
+++ b/lib/librte_ipsec/sa.c
@@ -283,7 +283,7 @@ esp_outb_init(struct rte_ipsec_sa *sa, uint32_t hlen)
 {
 	uint8_t algo_type;
 
-	sa->sqn.outb.raw = 1;
+	sa->sqn.outb = 1;
 
 	algo_type = sa->algo_type;
 
diff --git a/lib/librte_ipsec/sa.h b/lib/librte_ipsec/sa.h
index d22451b..508dd2b 100644
--- a/lib/librte_ipsec/sa.h
+++ b/lib/librte_ipsec/sa.h
@@ -119,10 +119,7 @@ struct rte_ipsec_sa {
 	 * place from other frequently accesed data.
 	 */
 	union {
-		union {
-			rte_atomic64_t atom;
-			uint64_t raw;
-		} outb;
+		uint64_t outb;
 		struct {
 			uint32_t rdidx; /* read index */
 			uint32_t wridx; /* write index */
-- 
2.7.4