Merge branch 'net-mitigate-kmem_free-slowpath'

Jesper Dangaard Brouer says:

====================
net: mitigating kmem_cache free slowpath

This patchset is the first real use-case for kmem_cache bulk _free_.
The use of bulk _alloc_ is NOT included in this patchset. The full use
have previously been posted here [1].

The bulk free side have the largest benefit for the network stack
use-case, because network stack is hitting the kmem_cache/SLUB
slowpath when freeing SKBs, due to the amount of outstanding SKBs.
This is solved by using the new API kmem_cache_free_bulk().

Introduce new API napi_consume_skb(), that hides/handles bulk freeing
for the caller.  The drivers simply need to use this call when freeing
SKBs in NAPI context, e.g. replacing their calles to dev_kfree_skb() /
dev_consume_skb_any().

Driver ixgbe is the first user of this new API.

[1] http://thread.gmane.org/gmane.linux.network/384302/focus=397373
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -1089,7 +1089,7 @@ static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter)
  * @tx_ring: tx ring to clean
  **/
 static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
-			       struct ixgbe_ring *tx_ring)
+			       struct ixgbe_ring *tx_ring, int napi_budget)
 {
 	struct ixgbe_adapter *adapter = q_vector->adapter;
 	struct ixgbe_tx_buffer *tx_buffer;
@@ -1127,7 +1127,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 		total_packets += tx_buffer->gso_segs;
 
 		/* free the skb */
-		dev_consume_skb_any(tx_buffer->skb);
+		napi_consume_skb(tx_buffer->skb, napi_budget);
 
 		/* unmap skb header data */
 		dma_unmap_single(tx_ring->dev,
@@ -2784,7 +2784,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget)
 #endif
 
 	ixgbe_for_each_ring(ring, q_vector->tx)
-		clean_complete &= !!ixgbe_clean_tx_irq(q_vector, ring);
+		clean_complete &= !!ixgbe_clean_tx_irq(q_vector, ring, budget);
 
 	/* Exit if we are called by netpoll or busy polling is active */
 	if ((budget <= 0) || !ixgbe_qv_lock_napi(q_vector))

include/linux/skbuff.h

@@ -2404,6 +2404,10 @@ static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi,
 {
 	return __napi_alloc_skb(napi, length, GFP_ATOMIC);
 }
+void napi_consume_skb(struct sk_buff *skb, int budget);
+
+void __kfree_skb_flush(void);
+void __kfree_skb_defer(struct sk_buff *skb);
 
 /**
  * __dev_alloc_pages - allocate page for network Rx

net/core/dev.c

@@ -3829,8 +3829,14 @@ static void net_tx_action(struct softirq_action *h)
 				trace_consume_skb(skb);
 			else
 				trace_kfree_skb(skb, net_tx_action);
-			__kfree_skb(skb);
+
+			if (skb->fclone != SKB_FCLONE_UNAVAILABLE)
+				__kfree_skb(skb);
+			else
+				__kfree_skb_defer(skb);
 		}
+
+		__kfree_skb_flush();
 	}
 
 	if (sd->output_queue) {
@@ -5155,6 +5161,7 @@ static void net_rx_action(struct softirq_action *h)
 		}
 	}
 
+	__kfree_skb_flush();
 	local_irq_disable();
 
 	list_splice_tail_init(&sd->poll_list, &list);

net/core/skbuff.c

@@ -347,8 +347,16 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 }
 EXPORT_SYMBOL(build_skb);
 
+#define NAPI_SKB_CACHE_SIZE	64
+
+struct napi_alloc_cache {
+	struct page_frag_cache page;
+	size_t skb_count;
+	void *skb_cache[NAPI_SKB_CACHE_SIZE];
+};
+
 static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache);
-static DEFINE_PER_CPU(struct page_frag_cache, napi_alloc_cache);
+static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache);
 
 static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
 {
@@ -378,9 +386,9 @@ EXPORT_SYMBOL(netdev_alloc_frag);
 
 static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
 {
-	struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
 
-	return __alloc_page_frag(nc, fragsz, gfp_mask);
+	return __alloc_page_frag(&nc->page, fragsz, gfp_mask);
 }
 
 void *napi_alloc_frag(unsigned int fragsz)
@@ -474,7 +482,7 @@ EXPORT_SYMBOL(__netdev_alloc_skb);
 struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
 				 gfp_t gfp_mask)
 {
-	struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
 	struct sk_buff *skb;
 	void *data;
 
@@ -494,7 +502,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
 	if (sk_memalloc_socks())
 		gfp_mask |= __GFP_MEMALLOC;
 
-	data = __alloc_page_frag(nc, len, gfp_mask);
+	data = __alloc_page_frag(&nc->page, len, gfp_mask);
 	if (unlikely(!data))
 		return NULL;
 
@@ -505,7 +513,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
 	}
 
 	/* use OR instead of assignment to avoid clearing of bits in mask */
-	if (nc->pfmemalloc)
+	if (nc->page.pfmemalloc)
 		skb->pfmemalloc = 1;
 	skb->head_frag = 1;
 
@@ -747,6 +755,73 @@ void consume_skb(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(consume_skb);
 
+void __kfree_skb_flush(void)
+{
+	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+
+	/* flush skb_cache if containing objects */
+	if (nc->skb_count) {
+		kmem_cache_free_bulk(skbuff_head_cache, nc->skb_count,
+				     nc->skb_cache);
+		nc->skb_count = 0;
+	}
+}
+
+static inline void _kfree_skb_defer(struct sk_buff *skb)
+{
+	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+
+	/* drop skb->head and call any destructors for packet */
+	skb_release_all(skb);
+
+	/* record skb to CPU local list */
+	nc->skb_cache[nc->skb_count++] = skb;
+
+#ifdef CONFIG_SLUB
+	/* SLUB writes into objects when freeing */
+	prefetchw(skb);
+#endif
+
+	/* flush skb_cache if it is filled */
+	if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) {
+		kmem_cache_free_bulk(skbuff_head_cache, NAPI_SKB_CACHE_SIZE,
+				     nc->skb_cache);
+		nc->skb_count = 0;
+	}
+}
+void __kfree_skb_defer(struct sk_buff *skb)
+{
+	_kfree_skb_defer(skb);
+}
+
+void napi_consume_skb(struct sk_buff *skb, int budget)
+{
+	if (unlikely(!skb))
+		return;
+
+	/* if budget is 0 assume netpoll w/ IRQs disabled */
+	if (unlikely(!budget)) {
+		dev_consume_skb_irq(skb);
+		return;
+	}
+
+	if (likely(atomic_read(&skb->users) == 1))
+		smp_rmb();
+	else if (likely(!atomic_dec_and_test(&skb->users)))
+		return;
+	/* if reaching here SKB is ready to free */
+	trace_consume_skb(skb);
+
+	/* if SKB is a clone, don't handle this case */
+	if (unlikely(skb->fclone != SKB_FCLONE_UNAVAILABLE)) {
+		__kfree_skb(skb);
+		return;
+	}
+
+	_kfree_skb_defer(skb);
+}
+EXPORT_SYMBOL(napi_consume_skb);
+
 /* Make sure a field is enclosed inside headers_start/headers_end section */
 #define CHECK_SKB_FIELD(field) \
 	BUILD_BUG_ON(offsetof(struct sk_buff, field) <		\