From: Andrzej Ostruszka <amo@semihalf.com>
Date: Tue, 11 Jan 2022 11:37:39 +0000 (+0100)
Subject: ring: optimize corner case for enqueue/dequeue
X-Git-Url: http://git.droids-corp.org/?a=commitdiff_plain;h=97ed4cb6fb324f4277ee754d4b6f3c7a0d96400b;p=dpdk.git

ring: optimize corner case for enqueue/dequeue

When enqueueing/dequeueing to/from the ring we try to optimize by manual
loop unrolling.  The check for this optimization looks like:

	if (likely(idx + n < size)) {

where 'idx' points to the first usable element (empty slot for enqueue,
data for dequeue).  The correct comparison here should be '<=' instead
of '<'.

This is not a functional error since we fall back to the loop with
correct checks on indexes.  Just a minor suboptimal behaviour for the
case when we want to enqueue/dequeue exactly the number of elements that
we have in the ring before wrapping to its beginning.

Fixes: cc4b218790f6 ("ring: support configurable element size")
Fixes: 286bd05bf70d ("ring: optimisations")

Signed-off-by: Andrzej Ostruszka <amo@semihalf.com>
Reviewed-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Reviewed-by: Morten Brørup <mb@smartsharesystems.com>
---

diff --git a/lib/ring/rte_ring_elem_pvt.h b/lib/ring/rte_ring_elem_pvt.h
index 275ec55393..83788c56e6 100644
--- a/lib/ring/rte_ring_elem_pvt.h
+++ b/lib/ring/rte_ring_elem_pvt.h
@@ -17,7 +17,7 @@ __rte_ring_enqueue_elems_32(struct rte_ring *r, const uint32_t size,
 	unsigned int i;
 	uint32_t *ring = (uint32_t *)&r[1];
 	const uint32_t *obj = (const uint32_t *)obj_table;
-	if (likely(idx + n < size)) {
+	if (likely(idx + n <= size)) {
 		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
 			ring[idx] = obj[i];
 			ring[idx + 1] = obj[i + 1];
@@ -62,7 +62,7 @@ __rte_ring_enqueue_elems_64(struct rte_ring *r, uint32_t prod_head,
 	uint32_t idx = prod_head & r->mask;
 	uint64_t *ring = (uint64_t *)&r[1];
 	const unaligned_uint64_t *obj = (const unaligned_uint64_t *)obj_table;
-	if (likely(idx + n < size)) {
+	if (likely(idx + n <= size)) {
 		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
 			ring[idx] = obj[i];
 			ring[idx + 1] = obj[i + 1];
@@ -95,7 +95,7 @@ __rte_ring_enqueue_elems_128(struct rte_ring *r, uint32_t prod_head,
 	uint32_t idx = prod_head & r->mask;
 	rte_int128_t *ring = (rte_int128_t *)&r[1];
 	const rte_int128_t *obj = (const rte_int128_t *)obj_table;
-	if (likely(idx + n < size)) {
+	if (likely(idx + n <= size)) {
 		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
 			memcpy((void *)(ring + idx),
 				(const void *)(obj + i), 32);
@@ -151,7 +151,7 @@ __rte_ring_dequeue_elems_32(struct rte_ring *r, const uint32_t size,
 	unsigned int i;
 	uint32_t *ring = (uint32_t *)&r[1];
 	uint32_t *obj = (uint32_t *)obj_table;
-	if (likely(idx + n < size)) {
+	if (likely(idx + n <= size)) {
 		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
 			obj[i] = ring[idx];
 			obj[i + 1] = ring[idx + 1];
@@ -196,7 +196,7 @@ __rte_ring_dequeue_elems_64(struct rte_ring *r, uint32_t prod_head,
 	uint32_t idx = prod_head & r->mask;
 	uint64_t *ring = (uint64_t *)&r[1];
 	unaligned_uint64_t *obj = (unaligned_uint64_t *)obj_table;
-	if (likely(idx + n < size)) {
+	if (likely(idx + n <= size)) {
 		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
 			obj[i] = ring[idx];
 			obj[i + 1] = ring[idx + 1];
@@ -229,7 +229,7 @@ __rte_ring_dequeue_elems_128(struct rte_ring *r, uint32_t prod_head,
 	uint32_t idx = prod_head & r->mask;
 	rte_int128_t *ring = (rte_int128_t *)&r[1];
 	rte_int128_t *obj = (rte_int128_t *)obj_table;
-	if (likely(idx + n < size)) {
+	if (likely(idx + n <= size)) {
 		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
 			memcpy((void *)(obj + i), (void *)(ring + idx), 32);
 		switch (n & 0x1) {