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
  ...

3 files changed, 4 insertions, 106 deletions

diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 5f1fda44882b..589fa256256b 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -251,7 +251,6 @@ struct xenvif {
 struct xenvif_rx_cb {
         unsigned long expires;
         int meta_slots_used;
-        bool full_coalesce;
 };
 
 #define XENVIF_RX_CB(skb) ((struct xenvif_rx_cb *)(skb)->cb)
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 12f9e2708afb..f38227afe099 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -80,7 +80,7 @@ static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id)
         return IRQ_HANDLED;
 }
 
-int xenvif_poll(struct napi_struct *napi, int budget)
+static int xenvif_poll(struct napi_struct *napi, int budget)
 {
         struct xenvif_queue *queue =
                 container_of(napi, struct xenvif_queue, napi);
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 7dc2d64db3cb..f7a31d2cb3f1 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -233,51 +233,6 @@ static void xenvif_rx_queue_drop_expired(struct xenvif_queue *queue)
         }
 }
 
-/*
- * Returns true if we should start a new receive buffer instead of
- * adding 'size' bytes to a buffer which currently contains 'offset'
- * bytes.
- */
-static bool start_new_rx_buffer(int offset, unsigned long size, int head,
-                                bool full_coalesce)
-{
-        /* simple case: we have completely filled the current buffer. */
-        if (offset == MAX_BUFFER_OFFSET)
-                return true;
-
-        /*
-         * complex case: start a fresh buffer if the current frag
-         * would overflow the current buffer but only if:
-         *     (i)   this frag would fit completely in the next buffer
-         * and (ii)  there is already some data in the current buffer
-         * and (iii) this is not the head buffer.
-         * and (iv)  there is no need to fully utilize the buffers
-         *
-         * Where:
-         * - (i) stops us splitting a frag into two copies
-         *   unless the frag is too large for a single buffer.
-         * - (ii) stops us from leaving a buffer pointlessly empty.
-         * - (iii) stops us leaving the first buffer
-         *   empty. Strictly speaking this is already covered
-         *   by (ii) but is explicitly checked because
-         *   netfront relies on the first buffer being
-         *   non-empty and can crash otherwise.
-         * - (iv) is needed for skbs which can use up more than MAX_SKB_FRAGS
-         *   slot
-         *
-         * This means we will effectively linearise small
-         * frags but do not needlessly split large buffers
-         * into multiple copies tend to give large frags their
-         * own buffers as before.
-         */
-        BUG_ON(size > MAX_BUFFER_OFFSET);
-        if ((offset + size > MAX_BUFFER_OFFSET) && offset && !head &&
-            !full_coalesce)
-                return true;
-
-        return false;
-}
-
 struct netrx_pending_operations {
         unsigned copy_prod, copy_cons;
         unsigned meta_prod, meta_cons;
@@ -336,24 +291,13 @@ static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb
                 BUG_ON(offset >= PAGE_SIZE);
                 BUG_ON(npo->copy_off > MAX_BUFFER_OFFSET);
 
-                bytes = PAGE_SIZE - offset;
+                if (npo->copy_off == MAX_BUFFER_OFFSET)
+                        meta = get_next_rx_buffer(queue, npo);
 
+                bytes = PAGE_SIZE - offset;
                 if (bytes > size)
                         bytes = size;
 
-                if (start_new_rx_buffer(npo->copy_off,
-                                        bytes,
-                                        *head,
-                                        XENVIF_RX_CB(skb)->full_coalesce)) {
-                        /*
-                         * Netfront requires there to be some data in the head
-                         * buffer.
-                         */
-                        BUG_ON(*head);
-
-                        meta = get_next_rx_buffer(queue, npo);
-                }
-
                 if (npo->copy_off + bytes > MAX_BUFFER_OFFSET)
                         bytes = MAX_BUFFER_OFFSET - npo->copy_off;
 
@@ -570,60 +514,15 @@ static void xenvif_rx_action(struct xenvif_queue *queue)
 
         while (xenvif_rx_ring_slots_available(queue, XEN_NETBK_RX_SLOTS_MAX)
                && (skb = xenvif_rx_dequeue(queue)) != NULL) {
-                RING_IDX max_slots_needed;
                 RING_IDX old_req_cons;
                 RING_IDX ring_slots_used;
-                int i;
 
                 queue->last_rx_time = jiffies;
 
-                /* We need a cheap worse case estimate for the number of
-                 * slots we'll use.
-                 */
-
-                max_slots_needed = DIV_ROUND_UP(offset_in_page(skb->data) +
-                                                skb_headlen(skb),
-                                                PAGE_SIZE);
-                for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-                        unsigned int size;
-                        unsigned int offset;
-
-                        size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
-                        offset = skb_shinfo(skb)->frags[i].page_offset;
-
-                        /* For a worse-case estimate we need to factor in
-                         * the fragment page offset as this will affect the
-                         * number of times xenvif_gop_frag_copy() will
-                         * call start_new_rx_buffer().
-                         */
-                        max_slots_needed += DIV_ROUND_UP(offset + size,
-                                                         PAGE_SIZE);
-                }
-
-                /* To avoid the estimate becoming too pessimal for some
-                 * frontends that limit posted rx requests, cap the estimate
-                 * at MAX_SKB_FRAGS. In this case netback will fully coalesce
-                 * the skb into the provided slots.
-                 */
-                if (max_slots_needed > MAX_SKB_FRAGS) {
-                        max_slots_needed = MAX_SKB_FRAGS;
-                        XENVIF_RX_CB(skb)->full_coalesce = true;
-                } else {
-                        XENVIF_RX_CB(skb)->full_coalesce = false;
-                }
-
-                /* We may need one more slot for GSO metadata */
-                if (skb_is_gso(skb) &&
-                   (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 ||
-                    skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6))
-                        max_slots_needed++;
-
                 old_req_cons = queue->rx.req_cons;
                 XENVIF_RX_CB(skb)->meta_slots_used = xenvif_gop_skb(skb, &npo, queue);
                 ring_slots_used = queue->rx.req_cons - old_req_cons;
 
-                BUG_ON(ring_slots_used > max_slots_needed);
-
                 __skb_queue_tail(&rxq, skb);
         }