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

Pull networking updates from David Miller:

 1) More iov_iter conversion work from Al Viro.

    [ The "crypto: switch af_alg_make_sg() to iov_iter" commit was
      wrong, and this pull actually adds an extra commit on top of the
      branch I'm pulling to fix that up, so that the pre-merge state is
      ok.   - Linus ]

 2) Various optimizations to the ipv4 forwarding information base trie
    lookup implementation.  From Alexander Duyck.

 3) Remove sock_iocb altogether, from CHristoph Hellwig.

 4) Allow congestion control algorithm selection via routing metrics.
    From Daniel Borkmann.

 5) Make ipv4 uncached route list per-cpu, from Eric Dumazet.

 6) Handle rfs hash collisions more gracefully, also from Eric Dumazet.

 7) Add xmit_more support to r8169, e1000, and e1000e drivers.  From
    Florian Westphal.

 8) Transparent Ethernet Bridging support for GRO, from Jesse Gross.

 9) Add BPF packet actions to packet scheduler, from Jiri Pirko.

10) Add support for uniqu flow IDs to openvswitch, from Joe Stringer.

11) New NetCP ethernet driver, from Muralidharan Karicheri and Wingman
    Kwok.

12) More sanely handle out-of-window dupacks, which can result in
    serious ACK storms.  From Neal Cardwell.

13) Various rhashtable bug fixes and enhancements, from Herbert Xu,
    Patrick McHardy, and Thomas Graf.

14) Support xmit_more in be2net, from Sathya Perla.

15) Group Policy extensions for vxlan, from Thomas Graf.

16) Remove Checksum Offload support for vxlan, from Tom Herbert.

17) Like ipv4, support lockless transmit over ipv6 UDP sockets.  From
    Vlad Yasevich.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1494+1 commits)
  crypto: fix af_alg_make_sg() conversion to iov_iter
  ipv4: Namespecify TCP PMTU mechanism
  i40e: Fix for stats init function call in Rx setup
  tcp: don't include Fast Open option in SYN-ACK on pure SYN-data
  openvswitch: Only set TUNNEL_VXLAN_OPT if VXLAN-GBP metadata is set
  ipv6: Make __ipv6_select_ident static
  ipv6: Fix fragment id assignment on LE arches.
  bridge: Fix inability to add non-vlan fdb entry
  net: Mellanox: Delete unnecessary checks before the function call "vunmap"
  cxgb4: Add support in cxgb4 to get expansion rom version via ethtool
  ethtool: rename reserved1 memeber in ethtool_drvinfo for expansion ROM version
  net: dsa: Remove redundant phy_attach()
  IB/mlx4: Reset flow support for IB kernel ULPs
  IB/mlx4: Always use the correct port for mirrored multicast attachments
  net/bonding: Fix potential bad memory access during bonding events
  tipc: remove tipc_snprintf
  tipc: nl compat add noop and remove legacy nl framework
  tipc: convert legacy nl stats show to nl compat
  tipc: convert legacy nl net id get to nl compat
  tipc: convert legacy nl net id set to nl compat
  ...

1 files changed, 89 insertions, 169 deletions

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index d8c10764f130..e9b960f0ff32 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -142,10 +142,6 @@ struct netfront_queue {
 	struct sk_buff *rx_skbs[NET_RX_RING_SIZE];
 	grant_ref_t gref_rx_head;
 	grant_ref_t grant_rx_ref[NET_RX_RING_SIZE];
-
-	unsigned long rx_pfn_array[NET_RX_RING_SIZE];
-	struct multicall_entry rx_mcl[NET_RX_RING_SIZE+1];
-	struct mmu_update rx_mmu[NET_RX_RING_SIZE];
 };
 
 struct netfront_info {
@@ -223,11 +219,7 @@ static grant_ref_t xennet_get_rx_ref(struct netfront_queue *queue,
 }
 
 #ifdef CONFIG_SYSFS
-static int xennet_sysfs_addif(struct net_device *netdev);
-static void xennet_sysfs_delif(struct net_device *netdev);
-#else /* !CONFIG_SYSFS */
-#define xennet_sysfs_addif(dev) (0)
-#define xennet_sysfs_delif(dev) do { } while (0)
+static const struct attribute_group xennet_dev_group;
 #endif
 
 static bool xennet_can_sg(struct net_device *dev)
@@ -424,109 +416,68 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue)
 	xennet_maybe_wake_tx(queue);
 }
 
-static void xennet_make_frags(struct sk_buff *skb, struct netfront_queue *queue,
-			      struct xen_netif_tx_request *tx)
+static struct xen_netif_tx_request *xennet_make_one_txreq(
+	struct netfront_queue *queue, struct sk_buff *skb,
+	struct page *page, unsigned int offset, unsigned int len)
 {
-	char *data = skb->data;
-	unsigned long mfn;
-	RING_IDX prod = queue->tx.req_prod_pvt;
-	int frags = skb_shinfo(skb)->nr_frags;
-	unsigned int offset = offset_in_page(data);
-	unsigned int len = skb_headlen(skb);
 	unsigned int id;
+	struct xen_netif_tx_request *tx;
 	grant_ref_t ref;
-	int i;
 
-	/* While the header overlaps a page boundary (including being
-	   larger than a page), split it it into page-sized chunks. */
-	while (len > PAGE_SIZE - offset) {
-		tx->size = PAGE_SIZE - offset;
-		tx->flags |= XEN_NETTXF_more_data;
-		len -= tx->size;
-		data += tx->size;
-		offset = 0;
+	len = min_t(unsigned int, PAGE_SIZE - offset, len);
 
-		id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs);
-		queue->tx_skbs[id].skb = skb_get(skb);
-		tx = RING_GET_REQUEST(&queue->tx, prod++);
-		tx->id = id;
-		ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
-		BUG_ON((signed short)ref < 0);
+	id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs);
+	tx = RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++);
+	ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
+	BUG_ON((signed short)ref < 0);
 
-		mfn = virt_to_mfn(data);
-		gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id,
-						mfn, GNTMAP_readonly);
+	gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id,
+					page_to_mfn(page), GNTMAP_readonly);
 
-		queue->grant_tx_page[id] = virt_to_page(data);
-		tx->gref = queue->grant_tx_ref[id] = ref;
-		tx->offset = offset;
-		tx->size = len;
-		tx->flags = 0;
-	}
+	queue->tx_skbs[id].skb = skb;
+	queue->grant_tx_page[id] = page;
+	queue->grant_tx_ref[id] = ref;
 
-	/* Grant backend access to each skb fragment page. */
-	for (i = 0; i < frags; i++) {
-		skb_frag_t *frag = skb_shinfo(skb)->frags + i;
-		struct page *page = skb_frag_page(frag);
+	tx->id = id;
+	tx->gref = ref;
+	tx->offset = offset;
+	tx->size = len;
+	tx->flags = 0;
 
-		len = skb_frag_size(frag);
-		offset = frag->page_offset;
+	return tx;
+}
 
-		/* Skip unused frames from start of page */
-		page += offset >> PAGE_SHIFT;
-		offset &= ~PAGE_MASK;
+static struct xen_netif_tx_request *xennet_make_txreqs(
+	struct netfront_queue *queue, struct xen_netif_tx_request *tx,
+	struct sk_buff *skb, struct page *page,
+	unsigned int offset, unsigned int len)
+{
+	/* Skip unused frames from start of page */
+	page += offset >> PAGE_SHIFT;
+	offset &= ~PAGE_MASK;
 
-		while (len > 0) {
-			unsigned long bytes;
-
-			bytes = PAGE_SIZE - offset;
-			if (bytes > len)
-				bytes = len;
-
-			tx->flags |= XEN_NETTXF_more_data;
-
-			id = get_id_from_freelist(&queue->tx_skb_freelist,
-						  queue->tx_skbs);
-			queue->tx_skbs[id].skb = skb_get(skb);
-			tx = RING_GET_REQUEST(&queue->tx, prod++);
-			tx->id = id;
-			ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
-			BUG_ON((signed short)ref < 0);
-
-			mfn = pfn_to_mfn(page_to_pfn(page));
-			gnttab_grant_foreign_access_ref(ref,
-							queue->info->xbdev->otherend_id,
-							mfn, GNTMAP_readonly);
-
-			queue->grant_tx_page[id] = page;
-			tx->gref = queue->grant_tx_ref[id] = ref;
-			tx->offset = offset;
-			tx->size = bytes;
-			tx->flags = 0;
-
-			offset += bytes;
-			len -= bytes;
-
-			/* Next frame */
-			if (offset == PAGE_SIZE && len) {
-				BUG_ON(!PageCompound(page));
-				page++;
-				offset = 0;
-			}
-		}
+	while (len) {
+		tx->flags |= XEN_NETTXF_more_data;
+		tx = xennet_make_one_txreq(queue, skb_get(skb),
+					   page, offset, len);
+		page++;
+		offset = 0;
+		len -= tx->size;
 	}
 
-	queue->tx.req_prod_pvt = prod;
+	return tx;
 }
 
 /*
- * Count how many ring slots are required to send the frags of this
- * skb. Each frag might be a compound page.
+ * Count how many ring slots are required to send this skb. Each frag
+ * might be a compound page.
  */
-static int xennet_count_skb_frag_slots(struct sk_buff *skb)
+static int xennet_count_skb_slots(struct sk_buff *skb)
 {
 	int i, frags = skb_shinfo(skb)->nr_frags;
-	int pages = 0;
+	int pages;
+
+	pages = PFN_UP(offset_in_page(skb->data) + skb_headlen(skb));
 
 	for (i = 0; i < frags; i++) {
 		skb_frag_t *frag = skb_shinfo(skb)->frags + i;
@@ -562,18 +513,15 @@ static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb,
 
 static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	unsigned short id;
 	struct netfront_info *np = netdev_priv(dev);
 	struct netfront_stats *tx_stats = this_cpu_ptr(np->tx_stats);
-	struct xen_netif_tx_request *tx;
-	char *data = skb->data;
-	RING_IDX i;
-	grant_ref_t ref;
-	unsigned long mfn;
+	struct xen_netif_tx_request *tx, *first_tx;
+	unsigned int i;
 	int notify;
 	int slots;
-	unsigned int offset = offset_in_page(data);
-	unsigned int len = skb_headlen(skb);
+	struct page *page;
+	unsigned int offset;
+	unsigned int len;
 	unsigned long flags;
 	struct netfront_queue *queue = NULL;
 	unsigned int num_queues = dev->real_num_tx_queues;
@@ -596,18 +544,18 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto drop;
 	}
 
-	slots = DIV_ROUND_UP(offset + len, PAGE_SIZE) +
-		xennet_count_skb_frag_slots(skb);
+	slots = xennet_count_skb_slots(skb);
 	if (unlikely(slots > MAX_SKB_FRAGS + 1)) {
 		net_dbg_ratelimited("xennet: skb rides the rocket: %d slots, %d bytes\n",
 				    slots, skb->len);
 		if (skb_linearize(skb))
 			goto drop;
-		data = skb->data;
-		offset = offset_in_page(data);
-		len = skb_headlen(skb);
 	}
 
+	page = virt_to_page(skb->data);
+	offset = offset_in_page(skb->data);
+	len = skb_headlen(skb);
+
 	spin_lock_irqsave(&queue->tx_lock, flags);
 
 	if (unlikely(!netif_carrier_ok(dev) ||
@@ -617,25 +565,13 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto drop;
 	}
 
-	i = queue->tx.req_prod_pvt;
-
-	id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs);
-	queue->tx_skbs[id].skb = skb;
-
-	tx = RING_GET_REQUEST(&queue->tx, i);
+	/* First request for the linear area. */
+	first_tx = tx = xennet_make_one_txreq(queue, skb,
+					      page, offset, len);
+	page++;
+	offset = 0;
+	len -= tx->size;
 
-	tx->id   = id;
-	ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
-	BUG_ON((signed short)ref < 0);
-	mfn = virt_to_mfn(data);
-	gnttab_grant_foreign_access_ref(
-		ref, queue->info->xbdev->otherend_id, mfn, GNTMAP_readonly);
-	queue->grant_tx_page[id] = virt_to_page(data);
-	tx->gref = queue->grant_tx_ref[id] = ref;
-	tx->offset = offset;
-	tx->size = len;
-
-	tx->flags = 0;
 	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		/* local packet? */
 		tx->flags |= XEN_NETTXF_csum_blank | XEN_NETTXF_data_validated;
@@ -643,11 +579,12 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		/* remote but checksummed. */
 		tx->flags |= XEN_NETTXF_data_validated;
 
+	/* Optional extra info after the first request. */
 	if (skb_shinfo(skb)->gso_size) {
 		struct xen_netif_extra_info *gso;
 
 		gso = (struct xen_netif_extra_info *)
-			RING_GET_REQUEST(&queue->tx, ++i);
+			RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++);
 
 		tx->flags |= XEN_NETTXF_extra_info;
 
@@ -662,10 +599,19 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		gso->flags = 0;
 	}
 
-	queue->tx.req_prod_pvt = i + 1;
+	/* Requests for the rest of the linear area. */
+	tx = xennet_make_txreqs(queue, tx, skb, page, offset, len);
+
+	/* Requests for all the frags. */
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+		tx = xennet_make_txreqs(queue, tx, skb,
+					skb_frag_page(frag), frag->page_offset,
+					skb_frag_size(frag));
+	}
 
-	xennet_make_frags(skb, queue, tx);
-	tx->size = skb->len;
+	/* First request has the packet length. */
+	first_tx->size = skb->len;
 
 	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->tx, notify);
 	if (notify)
@@ -1367,20 +1313,15 @@ static int netfront_probe(struct xenbus_device *dev,
 
 	info = netdev_priv(netdev);
 	dev_set_drvdata(&dev->dev, info);
-
+#ifdef CONFIG_SYSFS
+	info->netdev->sysfs_groups[0] = &xennet_dev_group;
+#endif
 	err = register_netdev(info->netdev);
 	if (err) {
 		pr_warn("%s: register_netdev err=%d\n", __func__, err);
 		goto fail;
 	}
 
-	err = xennet_sysfs_addif(info->netdev);
-	if (err) {
-		unregister_netdev(info->netdev);
-		pr_warn("%s: add sysfs failed err=%d\n", __func__, err);
-		goto fail;
-	}
-
 	return 0;
 
  fail:
@@ -2144,39 +2085,20 @@ static ssize_t store_rxbuf(struct device *dev,
 	return len;
 }
 
-static struct device_attribute xennet_attrs[] = {
-	__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)
-{
-	int i;
-	int err;
-
-	for (i = 0; i < ARRAY_SIZE(xennet_attrs); i++) {
-		err = device_create_file(&netdev->dev,
-					   &xennet_attrs[i]);
-		if (err)
-			goto fail;
-	}
-	return 0;
-
- fail:
-	while (--i >= 0)
-		device_remove_file(&netdev->dev, &xennet_attrs[i]);
-	return err;
-}
-
-static void xennet_sysfs_delif(struct net_device *netdev)
-{
-	int i;
+static DEVICE_ATTR(rxbuf_min, S_IRUGO|S_IWUSR, show_rxbuf, store_rxbuf);
+static DEVICE_ATTR(rxbuf_max, S_IRUGO|S_IWUSR, show_rxbuf, store_rxbuf);
+static DEVICE_ATTR(rxbuf_cur, S_IRUGO, show_rxbuf, NULL);
 
-	for (i = 0; i < ARRAY_SIZE(xennet_attrs); i++)
-		device_remove_file(&netdev->dev, &xennet_attrs[i]);
-}
+static struct attribute *xennet_dev_attrs[] = {
+	&dev_attr_rxbuf_min.attr,
+	&dev_attr_rxbuf_max.attr,
+	&dev_attr_rxbuf_cur.attr,
+	NULL
+};
 
+static const struct attribute_group xennet_dev_group = {
+	.attrs = xennet_dev_attrs
+};
 #endif /* CONFIG_SYSFS */
 
 static int xennet_remove(struct xenbus_device *dev)
@@ -2190,8 +2112,6 @@ static int xennet_remove(struct xenbus_device *dev)
 
 	xennet_disconnect_backend(info);
 
-	xennet_sysfs_delif(info->netdev);
-
 	unregister_netdev(info->netdev);
 
 	for (i = 0; i < num_queues; ++i) {