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

Pull networking updates from David Miller:
 "Most notable changes in here:

   1) By far the biggest accomplishment, thanks to a large range of
      contributors, is the addition of multi-send for transmit.  This is
      the result of discussions back in Chicago, and the hard work of
      several individuals.

      Now, when the ->ndo_start_xmit() method of a driver sees
      skb->xmit_more as true, it can choose to defer the doorbell
      telling the driver to start processing the new TX queue entires.

      skb->xmit_more means that the generic networking is guaranteed to
      call the driver immediately with another SKB to send.

      There is logic added to the qdisc layer to dequeue multiple
      packets at a time, and the handling mis-predicted offloads in
      software is now done with no locks held.

      Finally, pktgen is extended to have a "burst" parameter that can
      be used to test a multi-send implementation.

      Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
      virtio_net

      Adding support is almost trivial, so export more drivers to
      support this optimization soon.

      I want to thank, in no particular or implied order, Jesper
      Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
      Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
      David Tat, Hannes Frederic Sowa, and Rusty Russell.

   2) PTP and timestamping support in bnx2x, from Michal Kalderon.

   3) Allow adjusting the rx_copybreak threshold for a driver via
      ethtool, and add rx_copybreak support to enic driver.  From
      Govindarajulu Varadarajan.

   4) Significant enhancements to the generic PHY layer and the bcm7xxx
      driver in particular (EEE support, auto power down, etc.) from
      Florian Fainelli.

   5) Allow raw buffers to be used for flow dissection, allowing drivers
      to determine the optimal "linear pull" size for devices that DMA
      into pools of pages.  The objective is to get exactly the
      necessary amount of headers into the linear SKB area pre-pulled,
      but no more.  The new interface drivers use is eth_get_headlen().
      From WANG Cong, with driver conversions (several had their own
      by-hand duplicated implementations) by Alexander Duyck and Eric
      Dumazet.

   6) Support checksumming more smoothly and efficiently for
      encapsulations, and add "foo over UDP" facility.  From Tom
      Herbert.

   7) Add Broadcom SF2 switch driver to DSA layer, from Florian
      Fainelli.

   8) eBPF now can load programs via a system call and has an extensive
      testsuite.  Alexei Starovoitov and Daniel Borkmann.

   9) Major overhaul of the packet scheduler to use RCU in several major
      areas such as the classifiers and rate estimators.  From John
      Fastabend.

  10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
      Duyck.

  11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
      Dumazet.

  12) Add Datacenter TCP congestion control algorithm support, From
      Florian Westphal.

  13) Reorganize sk_buff so that __copy_skb_header() is significantly
      faster.  From Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
  netlabel: directly return netlbl_unlabel_genl_init()
  net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
  net: description of dma_cookie cause make xmldocs warning
  cxgb4: clean up a type issue
  cxgb4: potential shift wrapping bug
  i40e: skb->xmit_more support
  net: fs_enet: Add NAPI TX
  net: fs_enet: Remove non NAPI RX
  r8169:add support for RTL8168EP
  net_sched: copy exts->type in tcf_exts_change()
  wimax: convert printk to pr_foo()
  af_unix: remove 0 assignment on static
  ipv6: Do not warn for informational ICMP messages, regardless of type.
  Update Intel Ethernet Driver maintainers list
  bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
  tipc: fix bug in multicast congestion handling
  net: better IFF_XMIT_DST_RELEASE support
  net/mlx4_en: remove NETDEV_TX_BUSY
  3c59x: fix bad split of cpu_to_le32(pci_map_single())
  net: bcmgenet: fix Tx ring priority programming
  ...

1 files changed, 66 insertions, 120 deletions

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 4d08f45a9c29..3b1f89b6e743 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -99,36 +99,10 @@ struct vring_virtqueue
 
 #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
 
-static inline struct scatterlist *sg_next_chained(struct scatterlist *sg,
-						  unsigned int *count)
-{
-	return sg_next(sg);
-}
-
-static inline struct scatterlist *sg_next_arr(struct scatterlist *sg,
-					      unsigned int *count)
-{
-	if (--(*count) == 0)
-		return NULL;
-	return sg + 1;
-}
-
-/* Set up an indirect table of descriptors and add it to the queue. */
-static inline int vring_add_indirect(struct vring_virtqueue *vq,
-				     struct scatterlist *sgs[],
-				     struct scatterlist *(*next)
-				       (struct scatterlist *, unsigned int *),
-				     unsigned int total_sg,
-				     unsigned int total_out,
-				     unsigned int total_in,
-				     unsigned int out_sgs,
-				     unsigned int in_sgs,
-				     gfp_t gfp)
+static struct vring_desc *alloc_indirect(unsigned int total_sg, gfp_t gfp)
 {
 	struct vring_desc *desc;
-	unsigned head;
-	struct scatterlist *sg;
-	int i, n;
+	unsigned int i;
 
 	/*
 	 * We require lowmem mappings for the descriptors because
@@ -139,57 +113,16 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq,
 
 	desc = kmalloc(total_sg * sizeof(struct vring_desc), gfp);
 	if (!desc)
-		return -ENOMEM;
-
-	/* Transfer entries from the sg lists into the indirect page */
-	i = 0;
-	for (n = 0; n < out_sgs; n++) {
-		for (sg = sgs[n]; sg; sg = next(sg, &total_out)) {
-			desc[i].flags = VRING_DESC_F_NEXT;
-			desc[i].addr = sg_phys(sg);
-			desc[i].len = sg->length;
-			desc[i].next = i+1;
-			i++;
-		}
-	}
-	for (; n < (out_sgs + in_sgs); n++) {
-		for (sg = sgs[n]; sg; sg = next(sg, &total_in)) {
-			desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
-			desc[i].addr = sg_phys(sg);
-			desc[i].len = sg->length;
-			desc[i].next = i+1;
-			i++;
-		}
-	}
-	BUG_ON(i != total_sg);
-
-	/* Last one doesn't continue. */
-	desc[i-1].flags &= ~VRING_DESC_F_NEXT;
-	desc[i-1].next = 0;
-
-	/* We're about to use a buffer */
-	vq->vq.num_free--;
-
-	/* Use a single buffer which doesn't continue */
-	head = vq->free_head;
-	vq->vring.desc[head].flags = VRING_DESC_F_INDIRECT;
-	vq->vring.desc[head].addr = virt_to_phys(desc);
-	/* kmemleak gives a false positive, as it's hidden by virt_to_phys */
-	kmemleak_ignore(desc);
-	vq->vring.desc[head].len = i * sizeof(struct vring_desc);
-
-	/* Update free pointer */
-	vq->free_head = vq->vring.desc[head].next;
+		return NULL;
 
-	return head;
+	for (i = 0; i < total_sg; i++)
+		desc[i].next = i+1;
+	return desc;
 }
 
 static inline int virtqueue_add(struct virtqueue *_vq,
 				struct scatterlist *sgs[],
-				struct scatterlist *(*next)
-				  (struct scatterlist *, unsigned int *),
-				unsigned int total_out,
-				unsigned int total_in,
+				unsigned int total_sg,
 				unsigned int out_sgs,
 				unsigned int in_sgs,
 				void *data,
@@ -197,8 +130,10 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	struct scatterlist *sg;
-	unsigned int i, n, avail, uninitialized_var(prev), total_sg;
+	struct vring_desc *desc;
+	unsigned int i, n, avail, descs_used, uninitialized_var(prev);
 	int head;
+	bool indirect;
 
 	START_USE(vq);
 
@@ -222,24 +157,40 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 	}
 #endif
 
-	total_sg = total_in + total_out;
+	BUG_ON(total_sg > vq->vring.num);
+	BUG_ON(total_sg == 0);
+
+	head = vq->free_head;
 
 	/* If the host supports indirect descriptor tables, and we have multiple
 	 * buffers, then go indirect. FIXME: tune this threshold */
-	if (vq->indirect && total_sg > 1 && vq->vq.num_free) {
-		head = vring_add_indirect(vq, sgs, next, total_sg, total_out,
-					  total_in,
-					  out_sgs, in_sgs, gfp);
-		if (likely(head >= 0))
-			goto add_head;
+	if (vq->indirect && total_sg > 1 && vq->vq.num_free)
+		desc = alloc_indirect(total_sg, gfp);
+	else
+		desc = NULL;
+
+	if (desc) {
+		/* Use a single buffer which doesn't continue */
+		vq->vring.desc[head].flags = VRING_DESC_F_INDIRECT;
+		vq->vring.desc[head].addr = virt_to_phys(desc);
+		/* avoid kmemleak false positive (hidden by virt_to_phys) */
+		kmemleak_ignore(desc);
+		vq->vring.desc[head].len = total_sg * sizeof(struct vring_desc);
+
+		/* Set up rest to use this indirect table. */
+		i = 0;
+		descs_used = 1;
+		indirect = true;
+	} else {
+		desc = vq->vring.desc;
+		i = head;
+		descs_used = total_sg;
+		indirect = false;
 	}
 
-	BUG_ON(total_sg > vq->vring.num);
-	BUG_ON(total_sg == 0);
-
-	if (vq->vq.num_free < total_sg) {
+	if (vq->vq.num_free < descs_used) {
 		pr_debug("Can't add buf len %i - avail = %i\n",
-			 total_sg, vq->vq.num_free);
+			 descs_used, vq->vq.num_free);
 		/* FIXME: for historical reasons, we force a notify here if
 		 * there are outgoing parts to the buffer.  Presumably the
 		 * host should service the ring ASAP. */
@@ -250,34 +201,35 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 	}
 
 	/* We're about to use some buffers from the free list. */
-	vq->vq.num_free -= total_sg;
+	vq->vq.num_free -= descs_used;
 
-	head = i = vq->free_head;
 	for (n = 0; n < out_sgs; n++) {
-		for (sg = sgs[n]; sg; sg = next(sg, &total_out)) {
-			vq->vring.desc[i].flags = VRING_DESC_F_NEXT;
-			vq->vring.desc[i].addr = sg_phys(sg);
-			vq->vring.desc[i].len = sg->length;
+		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
+			desc[i].flags = VRING_DESC_F_NEXT;
+			desc[i].addr = sg_phys(sg);
+			desc[i].len = sg->length;
 			prev = i;
-			i = vq->vring.desc[i].next;
+			i = desc[i].next;
 		}
 	}
 	for (; n < (out_sgs + in_sgs); n++) {
-		for (sg = sgs[n]; sg; sg = next(sg, &total_in)) {
-			vq->vring.desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
-			vq->vring.desc[i].addr = sg_phys(sg);
-			vq->vring.desc[i].len = sg->length;
+		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
+			desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
+			desc[i].addr = sg_phys(sg);
+			desc[i].len = sg->length;
 			prev = i;
-			i = vq->vring.desc[i].next;
+			i = desc[i].next;
 		}
 	}
 	/* Last one doesn't continue. */
-	vq->vring.desc[prev].flags &= ~VRING_DESC_F_NEXT;
+	desc[prev].flags &= ~VRING_DESC_F_NEXT;
 
 	/* Update free pointer */
-	vq->free_head = i;
+	if (indirect)
+		vq->free_head = vq->vring.desc[head].next;
+	else
+		vq->free_head = i;
 
-add_head:
 	/* Set token. */
 	vq->data[head] = data;
 
@@ -324,29 +276,23 @@ int virtqueue_add_sgs(struct virtqueue *_vq,
 		      void *data,
 		      gfp_t gfp)
 {
-	unsigned int i, total_out, total_in;
+	unsigned int i, total_sg = 0;
 
 	/* Count them first. */
-	for (i = total_out = total_in = 0; i < out_sgs; i++) {
-		struct scatterlist *sg;
-		for (sg = sgs[i]; sg; sg = sg_next(sg))
-			total_out++;
-	}
-	for (; i < out_sgs + in_sgs; i++) {
+	for (i = 0; i < out_sgs + in_sgs; i++) {
 		struct scatterlist *sg;
 		for (sg = sgs[i]; sg; sg = sg_next(sg))
-			total_in++;
+			total_sg++;
 	}
-	return virtqueue_add(_vq, sgs, sg_next_chained,
-			     total_out, total_in, out_sgs, in_sgs, data, gfp);
+	return virtqueue_add(_vq, sgs, total_sg, out_sgs, in_sgs, data, gfp);
 }
 EXPORT_SYMBOL_GPL(virtqueue_add_sgs);
 
 /**
  * virtqueue_add_outbuf - expose output buffers to other end
  * @vq: the struct virtqueue we're talking about.
- * @sgs: array of scatterlists (need not be terminated!)
- * @num: the number of scatterlists readable by other side
+ * @sg: scatterlist (must be well-formed and terminated!)
+ * @num: the number of entries in @sg readable by other side
  * @data: the token identifying the buffer.
  * @gfp: how to do memory allocations (if necessary).
  *
@@ -356,19 +302,19 @@ EXPORT_SYMBOL_GPL(virtqueue_add_sgs);
  * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
  */
 int virtqueue_add_outbuf(struct virtqueue *vq,
-			 struct scatterlist sg[], unsigned int num,
+			 struct scatterlist *sg, unsigned int num,
 			 void *data,
 			 gfp_t gfp)
 {
-	return virtqueue_add(vq, &sg, sg_next_arr, num, 0, 1, 0, data, gfp);
+	return virtqueue_add(vq, &sg, num, 1, 0, data, gfp);
 }
 EXPORT_SYMBOL_GPL(virtqueue_add_outbuf);
 
 /**
  * virtqueue_add_inbuf - expose input buffers to other end
  * @vq: the struct virtqueue we're talking about.
- * @sgs: array of scatterlists (need not be terminated!)
- * @num: the number of scatterlists writable by other side
+ * @sg: scatterlist (must be well-formed and terminated!)
+ * @num: the number of entries in @sg writable by other side
  * @data: the token identifying the buffer.
  * @gfp: how to do memory allocations (if necessary).
  *
@@ -378,11 +324,11 @@ EXPORT_SYMBOL_GPL(virtqueue_add_outbuf);
  * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
  */
 int virtqueue_add_inbuf(struct virtqueue *vq,
-			struct scatterlist sg[], unsigned int num,
+			struct scatterlist *sg, unsigned int num,
 			void *data,
 			gfp_t gfp)
 {
-	return virtqueue_add(vq, &sg, sg_next_arr, 0, num, 0, 1, data, gfp);
+	return virtqueue_add(vq, &sg, num, 0, 1, data, gfp);
 }
 EXPORT_SYMBOL_GPL(virtqueue_add_inbuf);