net: Use nested-BH locking for napi_alloc_cache.

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>
Link: https://patch.msgid.link/20240620132727.660738-5-bigeasy@linutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1b52f69ad05e2bd5f5b1de3f74104500f4d10b2d..eb9a7e65b5c818ab04ff7bcc042f25e2b45fbaa8 100644 (file)
--- 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.
@@ -306,11 +309,16 @@ void napi_get_frags_check(struct napi_struct *napi)
 void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
 {
        struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+       void *data;
 
        fragsz = SKB_DATA_ALIGN(fragsz);
 
-       return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
+       local_lock_nested_bh(&napi_alloc_cache.bh_lock);
+       data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
                                       align_mask);
+       local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
+       return data;
+
 }
 EXPORT_SYMBOL(__napi_alloc_frag_align);
 
@@ -338,16 +346,20 @@ static struct sk_buff *napi_skb_cache_get(void)
        struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
        struct sk_buff *skb;
 
+       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,
                                                      NAPI_SKB_CACHE_BULK,
                                                      nc->skb_cache);
-               if (unlikely(!nc->skb_count))
+               if (unlikely(!nc->skb_count)) {
+                       local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
                        return NULL;
+               }
        }
 
        skb = nc->skb_cache[--nc->skb_count];
+       local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
        kasan_mempool_unpoison_object(skb, kmem_cache_size(net_hotdata.skbuff_cache));
 
        return skb;
@@ -740,9 +752,13 @@ 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 +822,11 @@ 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 +848,7 @@ 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;
@@ -1431,6 +1448,7 @@ static void napi_skb_cache_put(struct sk_buff *skb)
        if (!kasan_mempool_poison_object(skb))
                return;
 
+       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)) {
@@ -1442,6 +1460,7 @@ static void napi_skb_cache_put(struct sk_buff *skb)
                                     nc->skb_cache + NAPI_SKB_CACHE_HALF);
                nc->skb_count = NAPI_SKB_CACHE_HALF;
        }
+       local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
 }
 
 void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason)