Merge branch 'napi_page_frags'

Alexander Duyck says:

====================
net: Alloc NAPI page frags from their own pool

This patch series implements a means of allocating page fragments without
the need for the local_irq_save/restore in __netdev_alloc_frag.  By doing
this I am able to decrease packet processing time by 11ns per packet in my
test environment.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

13 files changed, 22 insertions, 22 deletions

diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index ffeaf476a120..d86d6baf9681 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -836,7 +836,7 @@ static int b44_rx(struct b44 *bp, int budget)
 			struct sk_buff *copy_skb;
 
 			b44_recycle_rx(bp, cons, bp->rx_prod);
-			copy_skb = netdev_alloc_skb_ip_align(bp->dev, len);
+			copy_skb = napi_alloc_skb(&bp->napi, len);
 			if (copy_skb == NULL)
 				goto drop_it_no_recycle;
 
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 3e8d1a88ed3d..21206d33b638 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -385,7 +385,7 @@ static int bcm_enet_receive_queue(struct net_device *dev, int budget)
 		if (len < copybreak) {
 			struct sk_buff *nskb;
 
-			nskb = netdev_alloc_skb_ip_align(dev, len);
+			nskb = napi_alloc_skb(&priv->napi, len);
 			if (!nskb) {
 				/* forget packet, just rearm desc */
 				dev->stats.rx_dropped++;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index b4d71fd909ee..1d1147c93d59 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1015,7 +1015,7 @@ static int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget)
 		 */
 		if ((bp->dev->mtu > ETH_MAX_PACKET_SIZE) &&
 		    (len <= RX_COPY_THRESH)) {
-			skb = netdev_alloc_skb_ip_align(bp->dev, len);
+			skb = napi_alloc_skb(&fp->napi, len);
 			if (skb == NULL) {
 				DP(NETIF_MSG_RX_ERR | NETIF_MSG_RX_STATUS,
 				   "ERROR  packet dropped because of alloc failure\n");
diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c
index 86222a1bdb12..babe2a915b00 100644
--- a/drivers/net/ethernet/chelsio/cxgb/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb/sge.c
@@ -1025,7 +1025,7 @@ MODULE_PARM_DESC(copybreak, "Receive copy threshold");
 
 /**
  *	get_packet - return the next ingress packet buffer
- *	@pdev: the PCI device that received the packet
+ *	@adapter: the adapter that received the packet
  *	@fl: the SGE free list holding the packet
  *	@len: the actual packet length, excluding any SGE padding
  *
@@ -1037,14 +1037,15 @@ MODULE_PARM_DESC(copybreak, "Receive copy threshold");
  *	threshold and the packet is too big to copy, or (b) the packet should
  *	be copied but there is no memory for the copy.
  */
-static inline struct sk_buff *get_packet(struct pci_dev *pdev,
+static inline struct sk_buff *get_packet(struct adapter *adapter,
 					 struct freelQ *fl, unsigned int len)
 {
-	struct sk_buff *skb;
 	const struct freelQ_ce *ce = &fl->centries[fl->cidx];
+	struct pci_dev *pdev = adapter->pdev;
+	struct sk_buff *skb;
 
 	if (len < copybreak) {
-		skb = netdev_alloc_skb_ip_align(NULL, len);
+		skb = napi_alloc_skb(&adapter->napi, len);
 		if (!skb)
 			goto use_orig_buf;
 
@@ -1357,7 +1358,7 @@ static void sge_rx(struct sge *sge, struct freelQ *fl, unsigned int len)
 	struct sge_port_stats *st;
 	struct net_device *dev;
 
-	skb = get_packet(adapter->pdev, fl, len - sge->rx_pkt_pad);
+	skb = get_packet(adapter, fl, len - sge->rx_pkt_pad);
 	if (unlikely(!skb)) {
 		sge->stats.rx_drops++;
 		return;
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 862d1989ae1c..83140cbb5f01 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -4100,7 +4100,7 @@ static bool e1000_tbi_should_accept(struct e1000_adapter *adapter,
 static struct sk_buff *e1000_alloc_rx_skb(struct e1000_adapter *adapter,
 					  unsigned int bufsz)
 {
-	struct sk_buff *skb = netdev_alloc_skb_ip_align(adapter->netdev, bufsz);
+	struct sk_buff *skb = napi_alloc_skb(&adapter->napi, bufsz);
 
 	if (unlikely(!skb))
 		adapter->alloc_rx_buff_failed++;
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 88936aa0029d..5c82c8065501 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1016,7 +1016,7 @@ static bool e1000_clean_rx_irq(struct e1000_ring *rx_ring, int *work_done,
 		 */
 		if (length < copybreak) {
 			struct sk_buff *new_skb =
-			    netdev_alloc_skb_ip_align(netdev, length);
+				napi_alloc_skb(&adapter->napi, length);
 			if (new_skb) {
 				skb_copy_to_linear_data_offset(new_skb,
 							       -NET_IP_ALIGN,
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 91516aed373e..ee1ecb146df7 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -308,8 +308,8 @@ static struct sk_buff *fm10k_fetch_rx_buffer(struct fm10k_ring *rx_ring,
 #endif
 
 		/* allocate a skb to store the frags */
-		skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
-						FM10K_RX_HDR_LEN);
+		skb = napi_alloc_skb(&rx_ring->q_vector->napi,
+				     FM10K_RX_HDR_LEN);
 		if (unlikely(!skb)) {
 			rx_ring->rx_stats.alloc_failed++;
 			return NULL;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index f04ad13f7159..485d2c609d5d 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -6644,8 +6644,7 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,
 #endif
 
 		/* allocate a skb to store the frags */
-		skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
-						IGB_RX_HDR_LEN);
+		skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN);
 		if (unlikely(!skb)) {
 			rx_ring->rx_stats.alloc_failed++;
 			return NULL;
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
index 055961b0f24b..aa87605b144a 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
@@ -1963,7 +1963,7 @@ ixgb_rx_checksum(struct ixgb_adapter *adapter,
  * this should improve performance for small packets with large amounts
  * of reassembly being done in the stack
  */
-static void ixgb_check_copybreak(struct net_device *netdev,
+static void ixgb_check_copybreak(struct napi_struct *napi,
 				 struct ixgb_buffer *buffer_info,
 				 u32 length, struct sk_buff **skb)
 {
@@ -1972,7 +1972,7 @@ static void ixgb_check_copybreak(struct net_device *netdev,
 	if (length > copybreak)
 		return;
 
-	new_skb = netdev_alloc_skb_ip_align(netdev, length);
+	new_skb = napi_alloc_skb(napi, length);
 	if (!new_skb)
 		return;
 
@@ -2064,7 +2064,7 @@ ixgb_clean_rx_irq(struct ixgb_adapter *adapter, int *work_done, int work_to_do)
 			goto rxdesc_done;
 		}
 
-		ixgb_check_copybreak(netdev, buffer_info, length, &skb);
+		ixgb_check_copybreak(&adapter->napi, buffer_info, length, &skb);
 
 		/* Good Receive */
 		skb_put(skb, length);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index fbd52924ee34..798b05556e1b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1913,8 +1913,8 @@ static struct sk_buff *ixgbe_fetch_rx_buffer(struct ixgbe_ring *rx_ring,
 #endif
 
 		/* allocate a skb to store the frags */
-		skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
-						IXGBE_RX_HDR_SIZE);
+		skb = napi_alloc_skb(&rx_ring->q_vector->napi,
+				     IXGBE_RX_HDR_SIZE);
 		if (unlikely(!skb)) {
 			rx_ring->rx_stats.alloc_rx_buff_failed++;
 			return NULL;
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index 75b1693ec8bf..9c31e46d1eee 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -507,7 +507,7 @@ rx_status_loop:
 		netif_dbg(cp, rx_status, dev, "rx slot %d status 0x%x len %d\n",
 			  rx_tail, status, len);
 
-		new_skb = netdev_alloc_skb_ip_align(dev, buflen);
+		new_skb = napi_alloc_skb(napi, buflen);
 		if (!new_skb) {
 			dev->stats.rx_dropped++;
 			goto rx_next;
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index 63dc0f95d050..6d0b9dfac313 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2037,7 +2037,7 @@ keep_pkt:
 		/* Malloc up new buffer, compatible with net-2e. */
 		/* Omit the four octet CRC from the length. */
 
-		skb = netdev_alloc_skb_ip_align(dev, pkt_size);
+		skb = napi_alloc_skb(&tp->napi, pkt_size);
 		if (likely(skb)) {
 #if RX_BUF_IDX == 3
 			wrap_copy(skb, rx_ring, ring_offset+4, pkt_size);
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index b9c2f33b463d..3dad7e884952 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -7260,7 +7260,7 @@ static struct sk_buff *rtl8169_try_rx_copy(void *data,
 	data = rtl8169_align(data);
 	dma_sync_single_for_cpu(d, addr, pkt_size, DMA_FROM_DEVICE);
 	prefetch(data);
-	skb = netdev_alloc_skb_ip_align(tp->dev, pkt_size);
+	skb = napi_alloc_skb(&tp->napi, pkt_size);
 	if (skb)
 		memcpy(skb->data, data, pkt_size);
 	dma_sync_single_for_device(d, addr, pkt_size, DMA_FROM_DEVICE);