Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) New offloading infrastructure and example 'rocker' driver for
    offloading of switching and routing to hardware.

    This work was done by a large group of dedicated individuals, not
    limited to: Scott Feldman, Jiri Pirko, Thomas Graf, John Fastabend,
    Jamal Hadi Salim, Andy Gospodarek, Florian Fainelli, Roopa Prabhu

 2) Start making the networking operate on IOV iterators instead of
    modifying iov objects in-situ during transfers.  Thanks to Al Viro
    and Herbert Xu.

 3) A set of new netlink interfaces for the TIPC stack, from Richard
    Alpe.

 4) Remove unnecessary looping during ipv6 routing lookups, from Martin
    KaFai Lau.

 5) Add PAUSE frame generation support to gianfar driver, from Matei
    Pavaluca.

 6) Allow for larger reordering levels in TCP, which are easily
    achievable in the real world right now, from Eric Dumazet.

 7) Add a variable of napi_schedule that doesn't need to disable cpu
    interrupts, from Eric Dumazet.

 8) Use a doubly linked list to optimize neigh_parms_release(), from
    Nicolas Dichtel.

 9) Various enhancements to the kernel BPF verifier, and allow eBPF
    programs to actually be attached to sockets.  From Alexei
    Starovoitov.

10) Support TSO/LSO in sunvnet driver, from David L Stevens.

11) Allow controlling ECN usage via routing metrics, from Florian
    Westphal.

12) Remote checksum offload, from Tom Herbert.

13) Add split-header receive, BQL, and xmit_more support to amd-xgbe
    driver, from Thomas Lendacky.

14) Add MPLS support to openvswitch, from Simon Horman.

15) Support wildcard tunnel endpoints in ipv6 tunnels, from Steffen
    Klassert.

16) Do gro flushes on a per-device basis using a timer, from Eric
    Dumazet.  This tries to resolve the conflicting goals between the
    desired handling of bulk vs.  RPC-like traffic.

17) Allow userspace to ask for the CPU upon what a packet was
    received/steered, via SO_INCOMING_CPU.  From Eric Dumazet.

18) Limit GSO packets to half the current congestion window, from Eric
    Dumazet.

19) Add a generic helper so that all drivers set their RSS keys in a
    consistent way, from Eric Dumazet.

20) Add xmit_more support to enic driver, from Govindarajulu
    Varadarajan.

21) Add VLAN packet scheduler action, from Jiri Pirko.

22) Support configurable RSS hash functions via ethtool, from Eyal
    Perry.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1820 commits)
  Fix race condition between vxlan_sock_add and vxlan_sock_release
  net/macb: fix compilation warning for print_hex_dump() called with skb->mac_header
  net/mlx4: Add support for A0 steering
  net/mlx4: Refactor QUERY_PORT
  net/mlx4_core: Add explicit error message when rule doesn't meet configuration
  net/mlx4: Add A0 hybrid steering
  net/mlx4: Add mlx4_bitmap zone allocator
  net/mlx4: Add a check if there are too many reserved QPs
  net/mlx4: Change QP allocation scheme
  net/mlx4_core: Use tasklet for user-space CQ completion events
  net/mlx4_core: Mask out host side virtualization features for guests
  net/mlx4_en: Set csum level for encapsulated packets
  be2net: Export tunnel offloads only when a VxLAN tunnel is created
  gianfar: Fix dma check map error when DMA_API_DEBUG is enabled
  cxgb4/csiostor: Don't use MASTER_MUST for fw_hello call
  net: fec: only enable mdio interrupt before phy device link up
  net: fec: clear all interrupt events to support i.MX6SX
  net: fec: reset fep link status in suspend function
  net: sock: fix access via invalid file descriptor
  net: introduce helper macro for_each_cmsghdr
  ...

1 files changed, 65 insertions, 191 deletions

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index ece8d1804d13..2f0a9ce9ff73 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -77,7 +77,9 @@ struct netfront_cb {
 
 #define NET_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE)
 #define NET_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE)
-#define TX_MAX_TARGET min_t(int, NET_TX_RING_SIZE, 256)
+
+/* Minimum number of Rx slots (includes slot for GSO metadata). */
+#define NET_RX_SLOTS_MIN (XEN_NETIF_NR_SLOTS_MIN + 1)
 
 /* Queue name is interface name with "-qNNN" appended */
 #define QUEUE_NAME_SIZE (IFNAMSIZ + 6)
@@ -137,13 +139,6 @@ struct netfront_queue {
 	struct xen_netif_rx_front_ring rx;
 	int rx_ring_ref;
 
-	/* Receive-ring batched refills. */
-#define RX_MIN_TARGET 8
-#define RX_DFL_MIN_TARGET 64
-#define RX_MAX_TARGET min_t(int, NET_RX_RING_SIZE, 256)
-	unsigned rx_min_target, rx_max_target, rx_target;
-	struct sk_buff_head rx_batch;
-
 	struct timer_list rx_refill_timer;
 
 	struct sk_buff *rx_skbs[NET_RX_RING_SIZE];
@@ -251,7 +246,7 @@ static void rx_refill_timeout(unsigned long data)
 static int netfront_tx_slot_available(struct netfront_queue *queue)
 {
 	return (queue->tx.req_prod_pvt - queue->tx.rsp_cons) <
-		(TX_MAX_TARGET - MAX_SKB_FRAGS - 2);
+		(NET_TX_RING_SIZE - MAX_SKB_FRAGS - 2);
 }
 
 static void xennet_maybe_wake_tx(struct netfront_queue *queue)
@@ -265,77 +260,55 @@ static void xennet_maybe_wake_tx(struct netfront_queue *queue)
 		netif_tx_wake_queue(netdev_get_tx_queue(dev, queue->id));
 }
 
-static void xennet_alloc_rx_buffers(struct netfront_queue *queue)
+
+static struct sk_buff *xennet_alloc_one_rx_buffer(struct netfront_queue *queue)
 {
-	unsigned short id;
 	struct sk_buff *skb;
 	struct page *page;
-	int i, batch_target, notify;
-	RING_IDX req_prod = queue->rx.req_prod_pvt;
-	grant_ref_t ref;
-	unsigned long pfn;
-	void *vaddr;
-	struct xen_netif_rx_request *req;
 
-	if (unlikely(!netif_carrier_ok(queue->info->netdev)))
-		return;
+	skb = __netdev_alloc_skb(queue->info->netdev,
+				 RX_COPY_THRESHOLD + NET_IP_ALIGN,
+				 GFP_ATOMIC | __GFP_NOWARN);
+	if (unlikely(!skb))
+		return NULL;
 
-	/*
-	 * Allocate skbuffs greedily, even though we batch updates to the
-	 * receive ring. This creates a less bursty demand on the memory
-	 * allocator, so should reduce the chance of failed allocation requests
-	 * both for ourself and for other kernel subsystems.
-	 */
-	batch_target = queue->rx_target - (req_prod - queue->rx.rsp_cons);
-	for (i = skb_queue_len(&queue->rx_batch); i < batch_target; i++) {
-		skb = __netdev_alloc_skb(queue->info->netdev,
-					 RX_COPY_THRESHOLD + NET_IP_ALIGN,
-					 GFP_ATOMIC | __GFP_NOWARN);
-		if (unlikely(!skb))
-			goto no_skb;
-
-		/* Align ip header to a 16 bytes boundary */
-		skb_reserve(skb, NET_IP_ALIGN);
-
-		page = alloc_page(GFP_ATOMIC | __GFP_NOWARN);
-		if (!page) {
-			kfree_skb(skb);
-no_skb:
-			/* Could not allocate any skbuffs. Try again later. */
-			mod_timer(&queue->rx_refill_timer,
-				  jiffies + (HZ/10));
-
-			/* Any skbuffs queued for refill? Force them out. */
-			if (i != 0)
-				goto refill;
-			break;
-		}
-
-		skb_add_rx_frag(skb, 0, page, 0, 0, PAGE_SIZE);
-		__skb_queue_tail(&queue->rx_batch, skb);
+	page = alloc_page(GFP_ATOMIC | __GFP_NOWARN);
+	if (!page) {
+		kfree_skb(skb);
+		return NULL;
 	}
+	skb_add_rx_frag(skb, 0, page, 0, 0, PAGE_SIZE);
+
+	/* Align ip header to a 16 bytes boundary */
+	skb_reserve(skb, NET_IP_ALIGN);
+	skb->dev = queue->info->netdev;
+
+	return skb;
+}
+
 
-	/* Is the batch large enough to be worthwhile? */
-	if (i < (queue->rx_target/2)) {
-		if (req_prod > queue->rx.sring->req_prod)
-			goto push;
+static void xennet_alloc_rx_buffers(struct netfront_queue *queue)
+{
+	RING_IDX req_prod = queue->rx.req_prod_pvt;
+	int notify;
+
+	if (unlikely(!netif_carrier_ok(queue->info->netdev)))
 		return;
-	}
 
-	/* Adjust our fill target if we risked running out of buffers. */
-	if (((req_prod - queue->rx.sring->rsp_prod) < (queue->rx_target / 4)) &&
-	    ((queue->rx_target *= 2) > queue->rx_max_target))
-		queue->rx_target = queue->rx_max_target;
+	for (req_prod = queue->rx.req_prod_pvt;
+	     req_prod - queue->rx.rsp_cons < NET_RX_RING_SIZE;
+	     req_prod++) {
+		struct sk_buff *skb;
+		unsigned short id;
+		grant_ref_t ref;
+		unsigned long pfn;
+		struct xen_netif_rx_request *req;
 
- refill:
-	for (i = 0; ; i++) {
-		skb = __skb_dequeue(&queue->rx_batch);
-		if (skb == NULL)
+		skb = xennet_alloc_one_rx_buffer(queue);
+		if (!skb)
 			break;
 
-		skb->dev = queue->info->netdev;
-
-		id = xennet_rxidx(req_prod + i);
+		id = xennet_rxidx(req_prod);
 
 		BUG_ON(queue->rx_skbs[id]);
 		queue->rx_skbs[id] = skb;
@@ -345,9 +318,8 @@ no_skb:
 		queue->grant_rx_ref[id] = ref;
 
 		pfn = page_to_pfn(skb_frag_page(&skb_shinfo(skb)->frags[0]));
-		vaddr = page_address(skb_frag_page(&skb_shinfo(skb)->frags[0]));
 
-		req = RING_GET_REQUEST(&queue->rx, req_prod + i);
+		req = RING_GET_REQUEST(&queue->rx, req_prod);
 		gnttab_grant_foreign_access_ref(ref,
 						queue->info->xbdev->otherend_id,
 						pfn_to_mfn(pfn),
@@ -357,11 +329,16 @@ no_skb:
 		req->gref = ref;
 	}
 
+	queue->rx.req_prod_pvt = req_prod;
+
+	/* Not enough requests? Try again later. */
+	if (req_prod - queue->rx.rsp_cons < NET_RX_SLOTS_MIN) {
+		mod_timer(&queue->rx_refill_timer, jiffies + (HZ/10));
+		return;
+	}
+
 	wmb();		/* barrier so backend seens requests */
 
-	/* Above is a suitable barrier to ensure backend will see requests. */
-	queue->rx.req_prod_pvt = req_prod + i;
- push:
 	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->rx, notify);
 	if (notify)
 		notify_remote_via_irq(queue->rx_irq);
@@ -627,6 +604,9 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 				    slots, skb->len);
 		if (skb_linearize(skb))
 			goto drop;
+		data = skb->data;
+		offset = offset_in_page(data);
+		len = skb_headlen(skb);
 	}
 
 	spin_lock_irqsave(&queue->tx_lock, flags);
@@ -1065,13 +1045,6 @@ err:
 
 	work_done -= handle_incoming_queue(queue, &rxq);
 
-	/* If we get a callback with very few responses, reduce fill target. */
-	/* NB. Note exponential increase, linear decrease. */
-	if (((queue->rx.req_prod_pvt - queue->rx.sring->rsp_prod) >
-	     ((3*queue->rx_target) / 4)) &&
-	    (--queue->rx_target < queue->rx_min_target))
-		queue->rx_target = queue->rx_min_target;
-
 	xennet_alloc_rx_buffers(queue);
 
 	if (work_done < budget) {
@@ -1638,11 +1611,6 @@ static int xennet_init_queue(struct netfront_queue *queue)
 	spin_lock_init(&queue->tx_lock);
 	spin_lock_init(&queue->rx_lock);
 
-	skb_queue_head_init(&queue->rx_batch);
-	queue->rx_target     = RX_DFL_MIN_TARGET;
-	queue->rx_min_target = RX_DFL_MIN_TARGET;
-	queue->rx_max_target = RX_MAX_TARGET;
-
 	init_timer(&queue->rx_refill_timer);
 	queue->rx_refill_timer.data = (unsigned long)queue;
 	queue->rx_refill_timer.function = rx_refill_timeout;
@@ -1665,7 +1633,7 @@ static int xennet_init_queue(struct netfront_queue *queue)
 	}
 
 	/* A grant for every tx ring slot */
-	if (gnttab_alloc_grant_references(TX_MAX_TARGET,
+	if (gnttab_alloc_grant_references(NET_TX_RING_SIZE,
 					  &queue->gref_tx_head) < 0) {
 		pr_alert("can't alloc tx grant refs\n");
 		err = -ENOMEM;
@@ -1673,7 +1641,7 @@ static int xennet_init_queue(struct netfront_queue *queue)
 	}
 
 	/* A grant for every rx ring slot */
-	if (gnttab_alloc_grant_references(RX_MAX_TARGET,
+	if (gnttab_alloc_grant_references(NET_RX_RING_SIZE,
 					  &queue->gref_rx_head) < 0) {
 		pr_alert("can't alloc rx grant refs\n");
 		err = -ENOMEM;
@@ -2141,83 +2109,18 @@ static const struct ethtool_ops xennet_ethtool_ops =
 };
 
 #ifdef CONFIG_SYSFS
-static ssize_t show_rxbuf_min(struct device *dev,
-			      struct device_attribute *attr, char *buf)
-{
-	struct net_device *netdev = to_net_dev(dev);
-	struct netfront_info *info = netdev_priv(netdev);
-	unsigned int num_queues = netdev->real_num_tx_queues;
-
-	if (num_queues)
-		return sprintf(buf, "%u\n", info->queues[0].rx_min_target);
-	else
-		return sprintf(buf, "%u\n", RX_MIN_TARGET);
-}
-
-static ssize_t store_rxbuf_min(struct device *dev,
-			       struct device_attribute *attr,
-			       const char *buf, size_t len)
+static ssize_t show_rxbuf(struct device *dev,
+			  struct device_attribute *attr, char *buf)
 {
-	struct net_device *netdev = to_net_dev(dev);
-	struct netfront_info *np = netdev_priv(netdev);
-	unsigned int num_queues = netdev->real_num_tx_queues;
-	char *endp;
-	unsigned long target;
-	unsigned int i;
-	struct netfront_queue *queue;
-
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
-	target = simple_strtoul(buf, &endp, 0);
-	if (endp == buf)
-		return -EBADMSG;
-
-	if (target < RX_MIN_TARGET)
-		target = RX_MIN_TARGET;
-	if (target > RX_MAX_TARGET)
-		target = RX_MAX_TARGET;
-
-	for (i = 0; i < num_queues; ++i) {
-		queue = &np->queues[i];
-		spin_lock_bh(&queue->rx_lock);
-		if (target > queue->rx_max_target)
-			queue->rx_max_target = target;
-		queue->rx_min_target = target;
-		if (target > queue->rx_target)
-			queue->rx_target = target;
-
-		xennet_alloc_rx_buffers(queue);
-
-		spin_unlock_bh(&queue->rx_lock);
-	}
-	return len;
-}
-
-static ssize_t show_rxbuf_max(struct device *dev,
-			      struct device_attribute *attr, char *buf)
-{
-	struct net_device *netdev = to_net_dev(dev);
-	struct netfront_info *info = netdev_priv(netdev);
-	unsigned int num_queues = netdev->real_num_tx_queues;
-
-	if (num_queues)
-		return sprintf(buf, "%u\n", info->queues[0].rx_max_target);
-	else
-		return sprintf(buf, "%u\n", RX_MAX_TARGET);
+	return sprintf(buf, "%lu\n", NET_RX_RING_SIZE);
 }
 
-static ssize_t store_rxbuf_max(struct device *dev,
-			       struct device_attribute *attr,
-			       const char *buf, size_t len)
+static ssize_t store_rxbuf(struct device *dev,
+			   struct device_attribute *attr,
+			   const char *buf, size_t len)
 {
-	struct net_device *netdev = to_net_dev(dev);
-	struct netfront_info *np = netdev_priv(netdev);
-	unsigned int num_queues = netdev->real_num_tx_queues;
 	char *endp;
 	unsigned long target;
-	unsigned int i = 0;
-	struct netfront_queue *queue = NULL;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -2226,44 +2129,15 @@ static ssize_t store_rxbuf_max(struct device *dev,
 	if (endp == buf)
 		return -EBADMSG;
 
-	if (target < RX_MIN_TARGET)
-		target = RX_MIN_TARGET;
-	if (target > RX_MAX_TARGET)
-		target = RX_MAX_TARGET;
-
-	for (i = 0; i < num_queues; ++i) {
-		queue = &np->queues[i];
-		spin_lock_bh(&queue->rx_lock);
-		if (target < queue->rx_min_target)
-			queue->rx_min_target = target;
-		queue->rx_max_target = target;
-		if (target < queue->rx_target)
-			queue->rx_target = target;
-
-		xennet_alloc_rx_buffers(queue);
+	/* rxbuf_min and rxbuf_max are no longer configurable. */
 
-		spin_unlock_bh(&queue->rx_lock);
-	}
 	return len;
 }
 
-static ssize_t show_rxbuf_cur(struct device *dev,
-			      struct device_attribute *attr, char *buf)
-{
-	struct net_device *netdev = to_net_dev(dev);
-	struct netfront_info *info = netdev_priv(netdev);
-	unsigned int num_queues = netdev->real_num_tx_queues;
-
-	if (num_queues)
-		return sprintf(buf, "%u\n", info->queues[0].rx_target);
-	else
-		return sprintf(buf, "0\n");
-}
-
 static struct device_attribute xennet_attrs[] = {
-	__ATTR(rxbuf_min, S_IRUGO|S_IWUSR, show_rxbuf_min, store_rxbuf_min),
-	__ATTR(rxbuf_max, S_IRUGO|S_IWUSR, show_rxbuf_max, store_rxbuf_max),
-	__ATTR(rxbuf_cur, S_IRUGO, show_rxbuf_cur, NULL),
+	__ATTR(rxbuf_min, S_IRUGO|S_IWUSR, show_rxbuf, store_rxbuf),
+	__ATTR(rxbuf_max, S_IRUGO|S_IWUSR, show_rxbuf, store_rxbuf),
+	__ATTR(rxbuf_cur, S_IRUGO, show_rxbuf, NULL),
 };
 
 static int xennet_sysfs_addif(struct net_device *netdev)