diff mbox series

[v4,net-next,03/14] net: Use nested-BH locking for napi_alloc_cache.

Message ID 20240604154425.878636-4-bigeasy@linutronix.de (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series locking: Introduce nested-BH locking. | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net-next, async
netdev/apply fail Patch does not apply to net-next-1

Commit Message

Sebastian Andrzej Siewior June 4, 2024, 3:24 p.m. UTC 
napi_alloc_cache is a per-CPU variable and relies on disabled BH for its
locking. Without per-CPU locking in local_bh_disable() on PREEMPT_RT
this data structure requires explicit locking.

Add a local_lock_t to the data structure and use local_lock_nested_bh()
for locking. This change adds only lockdep coverage and does not alter
the functional behaviour for !PREEMPT_RT.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 net/core/skbuff.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

Comments

Jakub Kicinski June 6, 2024, 2:54 a.m. UTC | #1 
On Tue,  4 Jun 2024 17:24:10 +0200 Sebastian Andrzej Siewior wrote:
> @@ -308,6 +311,7 @@ void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
>  	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
>  
>  	fragsz = SKB_DATA_ALIGN(fragsz);
> +	guard(local_lock_nested_bh)(&napi_alloc_cache.bh_lock);
>  
>  	return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
>  				       align_mask);

We have decided to advise against the use of guard() in networking, 
at least for now.

Andrew, wasn't it on your TODO list to send the update to the docs? :)
Sebastian Andrzej Siewior June 6, 2024, 6:22 a.m. UTC | #2 
On 2024-06-05 19:54:20 [-0700], Jakub Kicinski wrote:
> On Tue,  4 Jun 2024 17:24:10 +0200 Sebastian Andrzej Siewior wrote:
> > @@ -308,6 +311,7 @@ void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
> >  	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
> >  
> >  	fragsz = SKB_DATA_ALIGN(fragsz);
> > +	guard(local_lock_nested_bh)(&napi_alloc_cache.bh_lock);
> >  
> >  	return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
> >  				       align_mask);
> 
> We have decided to advise against the use of guard() in networking, 
> at least for now.

Understood.

> Andrew, wasn't it on your TODO list to send the update to the docs? :)
I can add it to
	Documentation/process/maintainer-netdev.rst

Yes, no, Andrew?

Sebastian
diff mbox series

Patch

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index dda13fdffb697..b33bae4ba78b6 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -277,6 +277,7 @@  static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp_mask)
 #endif
 
 struct napi_alloc_cache {
+	local_lock_t bh_lock;
 	struct page_frag_cache page;
 	struct page_frag_1k page_small;
 	unsigned int skb_count;
@@ -284,7 +285,9 @@  struct napi_alloc_cache {
 };
 
 static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache);
-static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache);
+static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 
 /* Double check that napi_get_frags() allocates skbs with
  * skb->head being backed by slab, not a page fragment.
@@ -308,6 +311,7 @@  void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
 	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
 
 	fragsz = SKB_DATA_ALIGN(fragsz);
+	guard(local_lock_nested_bh)(&napi_alloc_cache.bh_lock);
 
 	return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
 				       align_mask);
@@ -338,6 +342,7 @@  static struct sk_buff *napi_skb_cache_get(void)
 	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
 	struct sk_buff *skb;
 
+	guard(local_lock_nested_bh)(&napi_alloc_cache.bh_lock);
 	if (unlikely(!nc->skb_count)) {
 		nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache,
 						      GFP_ATOMIC,
@@ -740,9 +745,13 @@  struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len,
 		pfmemalloc = nc->pfmemalloc;
 	} else {
 		local_bh_disable();
+		local_lock_nested_bh(&napi_alloc_cache.bh_lock);
+
 		nc = this_cpu_ptr(&napi_alloc_cache.page);
 		data = page_frag_alloc(nc, len, gfp_mask);
 		pfmemalloc = nc->pfmemalloc;
+
+		local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
 		local_bh_enable();
 	}
 
@@ -806,11 +815,11 @@  struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len)
 		goto skb_success;
 	}
 
-	nc = this_cpu_ptr(&napi_alloc_cache);
-
 	if (sk_memalloc_socks())
 		gfp_mask |= __GFP_MEMALLOC;
 
+	local_lock_nested_bh(&napi_alloc_cache.bh_lock);
+	nc = this_cpu_ptr(&napi_alloc_cache);
 	if (NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) {
 		/* we are artificially inflating the allocation size, but
 		 * that is not as bad as it may look like, as:
@@ -832,6 +841,7 @@  struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len)
 		data = page_frag_alloc(&nc->page, len, gfp_mask);
 		pfmemalloc = nc->page.pfmemalloc;
 	}
+	local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
 
 	if (unlikely(!data))
 		return NULL;
@@ -1429,6 +1439,7 @@  static void napi_skb_cache_put(struct sk_buff *skb)
 	if (!kasan_mempool_poison_object(skb))
 		return;
 
+	guard(local_lock_nested_bh)(&napi_alloc_cache.bh_lock);
 	nc->skb_cache[nc->skb_count++] = skb;
 
 	if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) {