Re: [PATCH net-next v3 05/18] xdp: Use nested-BH locking for system_page_pool

On 2025-05-01 12:13:24 [+0200], Toke Høiland-Jørgensen wrote:

quoted

--- a/net/core/dev.c
+++ b/net/core/dev.c

@@ -462,7 +462,9 @@ EXPORT_PER_CPU_SYMBOL(softnet_data);
  * PP consumers must pay attention to run APIs in the appropriate context
  * (e.g. NAPI context).
  */
-DEFINE_PER_CPU(struct page_pool *, system_page_pool);
+DEFINE_PER_CPU(struct page_pool_bh, system_page_pool) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};

I'm a little fuzzy on how DEFINE_PER_CPU() works, but does this
initialisation automatically do the right thing with the multiple
per-CPU instances?

It sets the "first" per-CPU data which is then copied to all
"possible-CPUs" during early boot when the per-CPU data is made
available. You can initialize almost everything like that. Pointer based
structures (such as LIST_HEAD_INIT()) is something that obviously won't
work.

quoted

 #ifdef CONFIG_LOCKDEP
 /*

--- a/net/core/xdp.c
+++ b/net/core/xdp.c

@@ -737,10 +737,10 @@ static noinline bool xdp_copy_frags_from_zc(struct sk_buff *skb,
  */
 struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp)
 {
-	struct page_pool *pp = this_cpu_read(system_page_pool);
 	const struct xdp_rxq_info *rxq = xdp->rxq;
 	u32 len = xdp->data_end - xdp->data_meta;
 	u32 truesize = xdp->frame_sz;
+	struct page_pool *pp;
 	struct sk_buff *skb;
 	int metalen;
 	void *data;

@@ -748,13 +748,18 @@ struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp)
 	if (!IS_ENABLED(CONFIG_PAGE_POOL))
 		return NULL;
 
+	local_lock_nested_bh(&system_page_pool.bh_lock);
+	pp = this_cpu_read(system_page_pool.pool);
 	data = page_pool_dev_alloc_va(pp, &truesize);
-	if (unlikely(!data))
+	if (unlikely(!data)) {
+		local_unlock_nested_bh(&system_page_pool.bh_lock);
 		return NULL;
+	}
 
 	skb = napi_build_skb(data, truesize);
 	if (unlikely(!skb)) {
 		page_pool_free_va(pp, data, true);
+		local_unlock_nested_bh(&system_page_pool.bh_lock);
 		return NULL;
 	}
 

@@ -773,9 +778,11 @@ struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp)
 
 	if (unlikely(xdp_buff_has_frags(xdp)) &&
 	    unlikely(!xdp_copy_frags_from_zc(skb, xdp, pp))) {
+		local_unlock_nested_bh(&system_page_pool.bh_lock);
 		napi_consume_skb(skb, true);
 		return NULL;
 	}
+	local_unlock_nested_bh(&system_page_pool.bh_lock);

Hmm, instead of having four separate unlock calls in this function, how
about initialising skb = NULL, and having the unlock call just above
'return skb' with an out: label?

Then the three topmost 'return NULL' can just straight-forwardly be
replaced with 'goto out', while the last one becomes 'skb = NULL; goto
out;'. I think that would be more readable than this repetition.

Something like the following maybe? We would keep the lock during
napi_consume_skb() which should work.

diff --git a/net/core/xdp.c b/net/core/xdp.c
index b2a5c934fe7b7..1ff0bc328305d 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c

@@ -740,8 +740,8 @@ struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp)
 	const struct xdp_rxq_info *rxq = xdp->rxq;
 	u32 len = xdp->data_end - xdp->data_meta;
 	u32 truesize = xdp->frame_sz;
+	struct sk_buff *skb = NULL;
 	struct page_pool *pp;
-	struct sk_buff *skb;
 	int metalen;
 	void *data;
 

@@ -751,16 +751,13 @@ struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp)
 	local_lock_nested_bh(&system_page_pool.bh_lock);
 	pp = this_cpu_read(system_page_pool.pool);
 	data = page_pool_dev_alloc_va(pp, &truesize);
-	if (unlikely(!data)) {
-		local_unlock_nested_bh(&system_page_pool.bh_lock);
-		return NULL;
-	}
+	if (unlikely(!data))
+		goto out;
 
 	skb = napi_build_skb(data, truesize);
 	if (unlikely(!skb)) {
 		page_pool_free_va(pp, data, true);
-		local_unlock_nested_bh(&system_page_pool.bh_lock);
-		return NULL;
+		goto out;
 	}
 
 	skb_mark_for_recycle(skb);

@@ -778,15 +775,16 @@ struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp)
 
 	if (unlikely(xdp_buff_has_frags(xdp)) &&
 	    unlikely(!xdp_copy_frags_from_zc(skb, xdp, pp))) {
-		local_unlock_nested_bh(&system_page_pool.bh_lock);
 		napi_consume_skb(skb, true);
-		return NULL;
+		skb = NULL;
 	}
+
+out:
 	local_unlock_nested_bh(&system_page_pool.bh_lock);
-
-	xsk_buff_free(xdp);
-
-	skb->protocol = eth_type_trans(skb, rxq->dev);
+	if (skb) {
+		xsk_buff_free(xdp);
+		skb->protocol = eth_type_trans(skb, rxq->dev);
+	}
 
 	return skb;
 }

-Toke

Sebastian