Merge branch 'xsk-minor-optimizations-around-locks'

Jason Xing says:

====================
xsk: minor optimizations around locks

Two optimizations regarding xsk_tx_list_lock and cq_lock can yield a
performance increase because of avoiding disabling and enabling
interrupts frequently.
====================

Link: https://patch.msgid.link/20251030000646.18859-1-kerneljasonxing@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

3 files changed, 21 insertions, 22 deletions

diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index cac56e6b0869..92a2358c6ce3 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -85,11 +85,16 @@ struct xsk_buff_pool {
 	bool unaligned;
 	bool tx_sw_csum;
 	void *addrs;
-	/* Mutual exclusion of the completion ring in the SKB mode. Two cases to protect:
-	 * NAPI TX thread and sendmsg error paths in the SKB destructor callback and when
-	 * sockets share a single cq when the same netdev and queue id is shared.
+	/* Mutual exclusion of the completion ring in the SKB mode.
+	 * Protect: NAPI TX thread and sendmsg error paths in the SKB
+	 * destructor callback.
 	 */
-	spinlock_t cq_lock;
+	spinlock_t cq_prod_lock;
+	/* Mutual exclusion of the completion ring in the SKB mode.
+	 * Protect: when sockets share a single cq when the same netdev
+	 * and queue id is shared.
+	 */
+	spinlock_t cq_cached_prod_lock;
 	struct xdp_buff_xsk *free_heads[];
 };
 
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 7b0c68a70888..2f26c918d448 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -548,12 +548,11 @@ static int xsk_wakeup(struct xdp_sock *xs, u8 flags)
 
 static int xsk_cq_reserve_locked(struct xsk_buff_pool *pool)
 {
-	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(&pool->cq_lock, flags);
+	spin_lock(&pool->cq_cached_prod_lock);
 	ret = xskq_prod_reserve(pool->cq);
-	spin_unlock_irqrestore(&pool->cq_lock, flags);
+	spin_unlock(&pool->cq_cached_prod_lock);
 
 	return ret;
 }
@@ -566,7 +565,7 @@ static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool,
 	unsigned long flags;
 	u32 idx;
 
-	spin_lock_irqsave(&pool->cq_lock, flags);
+	spin_lock_irqsave(&pool->cq_prod_lock, flags);
 	idx = xskq_get_prod(pool->cq);
 
 	xskq_prod_write_addr(pool->cq, idx,
@@ -583,16 +582,14 @@ static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool,
 		}
 	}
 	xskq_prod_submit_n(pool->cq, descs_processed);
-	spin_unlock_irqrestore(&pool->cq_lock, flags);
+	spin_unlock_irqrestore(&pool->cq_prod_lock, flags);
 }
 
 static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&pool->cq_lock, flags);
+	spin_lock(&pool->cq_cached_prod_lock);
 	xskq_prod_cancel_n(pool->cq, n);
-	spin_unlock_irqrestore(&pool->cq_lock, flags);
+	spin_unlock(&pool->cq_cached_prod_lock);
 }
 
 static void xsk_inc_num_desc(struct sk_buff *skb)
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index aa9788f20d0d..00a4eddaa0cd 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -12,26 +12,22 @@
 
 void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
 {
-	unsigned long flags;
-
 	if (!xs->tx)
 		return;
 
-	spin_lock_irqsave(&pool->xsk_tx_list_lock, flags);
+	spin_lock(&pool->xsk_tx_list_lock);
 	list_add_rcu(&xs->tx_list, &pool->xsk_tx_list);
-	spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags);
+	spin_unlock(&pool->xsk_tx_list_lock);
 }
 
 void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
 {
-	unsigned long flags;
-
 	if (!xs->tx)
 		return;
 
-	spin_lock_irqsave(&pool->xsk_tx_list_lock, flags);
+	spin_lock(&pool->xsk_tx_list_lock);
 	list_del_rcu(&xs->tx_list);
-	spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags);
+	spin_unlock(&pool->xsk_tx_list_lock);
 }
 
 void xp_destroy(struct xsk_buff_pool *pool)
@@ -94,7 +90,8 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 	INIT_LIST_HEAD(&pool->xskb_list);
 	INIT_LIST_HEAD(&pool->xsk_tx_list);
 	spin_lock_init(&pool->xsk_tx_list_lock);
-	spin_lock_init(&pool->cq_lock);
+	spin_lock_init(&pool->cq_prod_lock);
+	spin_lock_init(&pool->cq_cached_prod_lock);
 	refcount_set(&pool->users, 1);
 
 	pool->fq = xs->fq_tmp;