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

Pull networking updates from David Miller:

 1) New ipset extensions for matching on destination MAC addresses, from
    Stefano Brivio.

 2) Add ipv4 ttl and tos, plus ipv6 flow label and hop limit offloads to
    nfp driver. From Stefano Brivio.

 3) Implement GRO for plain UDP sockets, from Paolo Abeni.

 4) Lots of work from Michał Mirosław to eliminate the VLAN_TAG_PRESENT
    bit so that we could support the entire vlan_tci value.

 5) Rework the IPSEC policy lookups to better optimize more usecases,
    from Florian Westphal.

 6) Infrastructure changes eliminating direct manipulation of SKB lists
    wherever possible, and to always use the appropriate SKB list
    helpers. This work is still ongoing...

 7) Lots of PHY driver and state machine improvements and
    simplifications, from Heiner Kallweit.

 8) Various TSO deferral refinements, from Eric Dumazet.

 9) Add ntuple filter support to aquantia driver, from Dmitry Bogdanov.

10) Batch dropping of XDP packets in tuntap, from Jason Wang.

11) Lots of cleanups and improvements to the r8169 driver from Heiner
    Kallweit, including support for ->xmit_more. This driver has been
    getting some much needed love since he started working on it.

12) Lots of new forwarding selftests from Petr Machata.

13) Enable VXLAN learning in mlxsw driver, from Ido Schimmel.

14) Packed ring support for virtio, from Tiwei Bie.

15) Add new Aquantia AQtion USB driver, from Dmitry Bezrukov.

16) Add XDP support to dpaa2-eth driver, from Ioana Ciocoi Radulescu.

17) Implement coalescing on TCP backlog queue, from Eric Dumazet.

18) Implement carrier change in tun driver, from Nicolas Dichtel.

19) Support msg_zerocopy in UDP, from Willem de Bruijn.

20) Significantly improve garbage collection of neighbor objects when
    the table has many PERMANENT entries, from David Ahern.

21) Remove egdev usage from nfp and mlx5, and remove the facility
    completely from the tree as it no longer has any users. From Oz
    Shlomo and others.

22) Add a NETDEV_PRE_CHANGEADDR so that drivers can veto the change and
    therefore abort the operation before the commit phase (which is the
    NETDEV_CHANGEADDR event). From Petr Machata.

23) Add indirect call wrappers to avoid retpoline overhead, and use them
    in the GRO code paths. From Paolo Abeni.

24) Add support for netlink FDB get operations, from Roopa Prabhu.

25) Support bloom filter in mlxsw driver, from Nir Dotan.

26) Add SKB extension infrastructure. This consolidates the handling of
    the auxiliary SKB data used by IPSEC and bridge netfilter, and is
    designed to support the needs to MPTCP which could be integrated in
    the future.

27) Lots of XDP TX optimizations in mlx5 from Tariq Toukan.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1845 commits)
  net: dccp: fix kernel crash on module load
  drivers/net: appletalk/cops: remove redundant if statement and mask
  bnx2x: Fix NULL pointer dereference in bnx2x_del_all_vlans() on some hw
  net/net_namespace: Check the return value of register_pernet_subsys()
  net/netlink_compat: Fix a missing check of nla_parse_nested
  ieee802154: lowpan_header_create check must check daddr
  net/mlx4_core: drop useless LIST_HEAD
  mlxsw: spectrum: drop useless LIST_HEAD
  net/mlx5e: drop useless LIST_HEAD
  iptunnel: Set tun_flags in the iptunnel_metadata_reply from src
  net/mlx5e: fix semicolon.cocci warnings
  staging: octeon: fix build failure with XFRM enabled
  net: Revert recent Spectre-v1 patches.
  can: af_can: Fix Spectre v1 vulnerability
  packet: validate address length if non-zero
  nfc: af_nfc: Fix Spectre v1 vulnerability
  phonet: af_phonet: Fix Spectre v1 vulnerability
  net: core: Fix Spectre v1 vulnerability
  net: minor cleanup in skb_ext_add()
  net: drop the unused helper skb_ext_get()
  ...

1 files changed, 51 insertions, 3 deletions

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index e87ef969a0fd..36f3d0f49e60 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -141,6 +141,10 @@ struct vhost_net {
 	unsigned tx_zcopy_err;
 	/* Flush in progress. Protected by tx vq lock. */
 	bool tx_flush;
+	/* Private page frag */
+	struct page_frag page_frag;
+	/* Refcount bias of page frag */
+	int refcnt_bias;
 };
 
 static unsigned vhost_net_zcopy_mask __read_mostly;
@@ -643,14 +647,53 @@ static bool tx_can_batch(struct vhost_virtqueue *vq, size_t total_len)
 	       !vhost_vq_avail_empty(vq->dev, vq);
 }
 
+#define SKB_FRAG_PAGE_ORDER     get_order(32768)
+
+static bool vhost_net_page_frag_refill(struct vhost_net *net, unsigned int sz,
+				       struct page_frag *pfrag, gfp_t gfp)
+{
+	if (pfrag->page) {
+		if (pfrag->offset + sz <= pfrag->size)
+			return true;
+		__page_frag_cache_drain(pfrag->page, net->refcnt_bias);
+	}
+
+	pfrag->offset = 0;
+	net->refcnt_bias = 0;
+	if (SKB_FRAG_PAGE_ORDER) {
+		/* Avoid direct reclaim but allow kswapd to wake */
+		pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) |
+					  __GFP_COMP | __GFP_NOWARN |
+					  __GFP_NORETRY,
+					  SKB_FRAG_PAGE_ORDER);
+		if (likely(pfrag->page)) {
+			pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER;
+			goto done;
+		}
+	}
+	pfrag->page = alloc_page(gfp);
+	if (likely(pfrag->page)) {
+		pfrag->size = PAGE_SIZE;
+		goto done;
+	}
+	return false;
+
+done:
+	net->refcnt_bias = USHRT_MAX;
+	page_ref_add(pfrag->page, USHRT_MAX - 1);
+	return true;
+}
+
 #define VHOST_NET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD)
 
 static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
 			       struct iov_iter *from)
 {
 	struct vhost_virtqueue *vq = &nvq->vq;
+	struct vhost_net *net = container_of(vq->dev, struct vhost_net,
+					     dev);
 	struct socket *sock = vq->private_data;
-	struct page_frag *alloc_frag = &current->task_frag;
+	struct page_frag *alloc_frag = &net->page_frag;
 	struct virtio_net_hdr *gso;
 	struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp];
 	struct tun_xdp_hdr *hdr;
@@ -671,7 +714,8 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
 
 	buflen += SKB_DATA_ALIGN(len + pad);
 	alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES);
-	if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL)))
+	if (unlikely(!vhost_net_page_frag_refill(net, buflen,
+						 alloc_frag, GFP_KERNEL)))
 		return -ENOMEM;
 
 	buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
@@ -709,7 +753,7 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
 	xdp->data_end = xdp->data + len;
 	hdr->buflen = buflen;
 
-	get_page(alloc_frag->page);
+	--net->refcnt_bias;
 	alloc_frag->offset += buflen;
 
 	++nvq->batched_xdp;
@@ -1298,6 +1342,8 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev);
 
 	f->private_data = n;
+	n->page_frag.page = NULL;
+	n->refcnt_bias = 0;
 
 	return 0;
 }
@@ -1372,6 +1418,8 @@ static int vhost_net_release(struct inode *inode, struct file *f)
 	kfree(n->vqs[VHOST_NET_VQ_RX].rxq.queue);
 	kfree(n->vqs[VHOST_NET_VQ_TX].xdp);
 	kfree(n->dev.vqs);
+	if (n->page_frag.page)
+		__page_frag_cache_drain(n->page_frag.page, n->refcnt_bias);
 	kvfree(n);
 	return 0;
 }