tg3: provide frags as skb head

This patch converts tg3 driver, one of our reference drivers, to use new
build_skb() api in frag mode.

Instead of using kmalloc() to allocate the memory block that will be
used by build_skb() as skb->head, we use a page fragment.

This is a followup of patch "net: allow skb->head to be a page fragment"

This allows GRO, TCP coalescing, and splice() to be more efficient.

Incidentally, this also removes SLUB slow path contention in kfree()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Matt Carlson <mcarlson@broadcom.com>
Cc: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/broadcom/tg3.c

@@ -195,6 +195,15 @@ static inline void _tg3_flag_clear(enum TG3_FLAGS flag, unsigned long *bits)
 #define TG3_RX_OFFSET(tp)	(NET_SKB_PAD)
 #endif
 
+/* This driver uses the new build_skb() API providing a frag as skb->head
+ * This strategy permits better GRO aggregation, better TCP coalescing, and
+ * better splice() implementation (avoids a copy from head to a page), at
+ * minimal memory cost.
+ * In this 2048 bytes block, we have enough room to store the MTU=1500 frame
+ * and the struct skb_shared_info.
+ */
+#define TG3_FRAGSIZE 2048
+
 /* minimum number of free TX descriptors required to wake up TX process */
 #define TG3_TX_WAKEUP_THRESH(tnapi)		((tnapi)->tx_pending / 4)
 #define TG3_TX_BD_DMA_MAX_2K		2048
@@ -5617,17 +5626,48 @@ static void tg3_tx(struct tg3_napi *tnapi)
 	}
 }
 
+static void *tg3_frag_alloc(struct tg3_rx_prodring_set *tpr)
+{
+	void *data;
+
+	if (tpr->rx_page_size < TG3_FRAGSIZE) {
+		struct page *page = alloc_page(GFP_ATOMIC);
+
+		if (!page)
+			return NULL;
+		atomic_add((PAGE_SIZE / TG3_FRAGSIZE) - 1, &page->_count);
+		tpr->rx_page_addr = page_address(page);
+		tpr->rx_page_size = PAGE_SIZE;
+	}
+	data = tpr->rx_page_addr;
+	tpr->rx_page_addr += TG3_FRAGSIZE;
+	tpr->rx_page_size -= TG3_FRAGSIZE;
+	return data;
+}
+
+static void tg3_frag_free(bool is_frag, void *data)
+{
+	if (is_frag)
+		put_page(virt_to_head_page(data));
+	else
+		kfree(data);
+}
+
 static void tg3_rx_data_free(struct tg3 *tp, struct ring_info *ri, u32 map_sz)
 {
+	unsigned int skb_size = SKB_DATA_ALIGN(map_sz + TG3_RX_OFFSET(tp)) +
+		   SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
 	if (!ri->data)
 		return;
 
 	pci_unmap_single(tp->pdev, dma_unmap_addr(ri, mapping),
 			 map_sz, PCI_DMA_FROMDEVICE);
-	kfree(ri->data);
+	tg3_frag_free(skb_size <= TG3_FRAGSIZE, ri->data);
 	ri->data = NULL;
 }
 
+
 /* Returns size of skb allocated or < 0 on error.
  *
  * We only need to fill in the address because the other members
@@ -5640,7 +5680,8 @@ static void tg3_rx_data_free(struct tg3 *tp, struct ring_info *ri, u32 map_sz)
  * (to fetch the error flags, vlan tag, checksum, and opaque cookie).
  */
 static int tg3_alloc_rx_data(struct tg3 *tp, struct tg3_rx_prodring_set *tpr,
-			    u32 opaque_key, u32 dest_idx_unmasked)
+			     u32 opaque_key, u32 dest_idx_unmasked,
+			     unsigned int *frag_size)
 {
 	struct tg3_rx_buffer_desc *desc;
 	struct ring_info *map;
@@ -5675,7 +5716,13 @@ static int tg3_alloc_rx_data(struct tg3 *tp, struct tg3_rx_prodring_set *tpr,
 	 */
 	skb_size = SKB_DATA_ALIGN(data_size + TG3_RX_OFFSET(tp)) +
 		   SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	data = kmalloc(skb_size, GFP_ATOMIC);
+	if (skb_size <= TG3_FRAGSIZE) {
+		data = tg3_frag_alloc(tpr);
+		*frag_size = TG3_FRAGSIZE;
+	} else {
+		data = kmalloc(skb_size, GFP_ATOMIC);
+		*frag_size = 0;
+	}
 	if (!data)
 		return -ENOMEM;
 
@@ -5683,8 +5730,8 @@ static int tg3_alloc_rx_data(struct tg3 *tp, struct tg3_rx_prodring_set *tpr,
 				 data + TG3_RX_OFFSET(tp),
 				 data_size,
 				 PCI_DMA_FROMDEVICE);
-	if (pci_dma_mapping_error(tp->pdev, mapping)) {
-		kfree(data);
+	if (unlikely(pci_dma_mapping_error(tp->pdev, mapping))) {
+		tg3_frag_free(skb_size <= TG3_FRAGSIZE, data);
 		return -EIO;
 	}
 
@@ -5835,18 +5882,19 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 
 		if (len > TG3_RX_COPY_THRESH(tp)) {
 			int skb_size;
+			unsigned int frag_size;
 
 			skb_size = tg3_alloc_rx_data(tp, tpr, opaque_key,
-						    *post_ptr);
+						    *post_ptr, &frag_size);
 			if (skb_size < 0)
 				goto drop_it;
 
 			pci_unmap_single(tp->pdev, dma_addr, skb_size,
 					 PCI_DMA_FROMDEVICE);
 
-			skb = build_skb(data, 0);
+			skb = build_skb(data, frag_size);
 			if (!skb) {
-				kfree(data);
+				tg3_frag_free(frag_size != 0, data);
 				goto drop_it_no_recycle;
 			}
 			skb_reserve(skb, TG3_RX_OFFSET(tp));
@@ -7279,7 +7327,10 @@ static int tg3_rx_prodring_alloc(struct tg3 *tp,
 
 	/* Now allocate fresh SKBs for each rx ring. */
 	for (i = 0; i < tp->rx_pending; i++) {
-		if (tg3_alloc_rx_data(tp, tpr, RXD_OPAQUE_RING_STD, i) < 0) {
+		unsigned int frag_size;
+
+		if (tg3_alloc_rx_data(tp, tpr, RXD_OPAQUE_RING_STD, i,
+				      &frag_size) < 0) {
 			netdev_warn(tp->dev,
 				    "Using a smaller RX standard ring. Only "
 				    "%d out of %d buffers were allocated "
@@ -7311,7 +7362,10 @@ static int tg3_rx_prodring_alloc(struct tg3 *tp,
 	}
 
 	for (i = 0; i < tp->rx_jumbo_pending; i++) {
-		if (tg3_alloc_rx_data(tp, tpr, RXD_OPAQUE_RING_JUMBO, i) < 0) {
+		unsigned int frag_size;
+
+		if (tg3_alloc_rx_data(tp, tpr, RXD_OPAQUE_RING_JUMBO, i,
+				      &frag_size) < 0) {
 			netdev_warn(tp->dev,
 				    "Using a smaller RX jumbo ring. Only %d "
 				    "out of %d buffers were allocated "

drivers/net/ethernet/broadcom/tg3.h

@@ -2815,6 +2815,8 @@ struct tg3_rx_prodring_set {
 	struct ring_info		*rx_jmb_buffers;
 	dma_addr_t			rx_std_mapping;
 	dma_addr_t			rx_jmb_mapping;
+	void				*rx_page_addr;
+	unsigned int			rx_page_size;
 };
 
 #define TG3_IRQ_MAX_VECS_RSS		5