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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 70 insertions, 23 deletions

diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 62dcdf082349..f2084e3f7aa4 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -14,14 +14,14 @@
 #include <net/sock.h>
 #include <net/af_vsock.h>
 
-/* The host side's design of the feature requires 6 exact 4KB pages for
- * recv/send rings respectively -- this is suboptimal considering memory
- * consumption, however unluckily we have to live with it, before the
- * host comes up with a better design in the future.
+/* Older (VMBUS version 'VERSION_WIN10' or before) Windows hosts have some
+ * stricter requirements on the hv_sock ring buffer size of six 4K pages. Newer
+ * hosts don't have this limitation; but, keep the defaults the same for compat.
  */
 #define PAGE_SIZE_4K		4096
 #define RINGBUFFER_HVS_RCV_SIZE (PAGE_SIZE_4K * 6)
 #define RINGBUFFER_HVS_SND_SIZE (PAGE_SIZE_4K * 6)
+#define RINGBUFFER_HVS_MAX_SIZE (PAGE_SIZE_4K * 64)
 
 /* The MTU is 16KB per the host side's design */
 #define HVS_MTU_SIZE		(1024 * 16)
@@ -46,8 +46,9 @@ struct hvs_recv_buf {
 };
 
 /* We can send up to HVS_MTU_SIZE bytes of payload to the host, but let's use
- * a small size, i.e. HVS_SEND_BUF_SIZE, to minimize the dynamically-allocated
- * buffer, because tests show there is no significant performance difference.
+ * a smaller size, i.e. HVS_SEND_BUF_SIZE, to maximize concurrency between the
+ * guest and the host processing as one VMBUS packet is the smallest processing
+ * unit.
  *
  * Note: the buffer can be eliminated in the future when we add new VMBus
  * ringbuffer APIs that allow us to directly copy data from userspace buffer
@@ -321,8 +322,11 @@ static void hvs_open_connection(struct vmbus_channel *chan)
 	struct sockaddr_vm addr;
 	struct sock *sk, *new = NULL;
 	struct vsock_sock *vnew = NULL;
-	struct hvsock *hvs, *hvs_new = NULL;
+	struct hvsock *hvs = NULL;
+	struct hvsock *hvs_new = NULL;
+	int rcvbuf;
 	int ret;
+	int sndbuf;
 
 	if_type = &chan->offermsg.offer.if_type;
 	if_instance = &chan->offermsg.offer.if_instance;
@@ -364,9 +368,34 @@ static void hvs_open_connection(struct vmbus_channel *chan)
 	}
 
 	set_channel_read_mode(chan, HV_CALL_DIRECT);
-	ret = vmbus_open(chan, RINGBUFFER_HVS_SND_SIZE,
-			 RINGBUFFER_HVS_RCV_SIZE, NULL, 0,
-			 hvs_channel_cb, conn_from_host ? new : sk);
+
+	/* Use the socket buffer sizes as hints for the VMBUS ring size. For
+	 * server side sockets, 'sk' is the parent socket and thus, this will
+	 * allow the child sockets to inherit the size from the parent. Keep
+	 * the mins to the default value and align to page size as per VMBUS
+	 * requirements.
+	 * For the max, the socket core library will limit the socket buffer
+	 * size that can be set by the user, but, since currently, the hv_sock
+	 * VMBUS ring buffer is physically contiguous allocation, restrict it
+	 * further.
+	 * Older versions of hv_sock host side code cannot handle bigger VMBUS
+	 * ring buffer size. Use the version number to limit the change to newer
+	 * versions.
+	 */
+	if (vmbus_proto_version < VERSION_WIN10_V5) {
+		sndbuf = RINGBUFFER_HVS_SND_SIZE;
+		rcvbuf = RINGBUFFER_HVS_RCV_SIZE;
+	} else {
+		sndbuf = max_t(int, sk->sk_sndbuf, RINGBUFFER_HVS_SND_SIZE);
+		sndbuf = min_t(int, sndbuf, RINGBUFFER_HVS_MAX_SIZE);
+		sndbuf = ALIGN(sndbuf, PAGE_SIZE);
+		rcvbuf = max_t(int, sk->sk_rcvbuf, RINGBUFFER_HVS_RCV_SIZE);
+		rcvbuf = min_t(int, rcvbuf, RINGBUFFER_HVS_MAX_SIZE);
+		rcvbuf = ALIGN(rcvbuf, PAGE_SIZE);
+	}
+
+	ret = vmbus_open(chan, sndbuf, rcvbuf, NULL, 0, hvs_channel_cb,
+			 conn_from_host ? new : sk);
 	if (ret != 0) {
 		if (conn_from_host) {
 			hvs_new->chan = NULL;
@@ -424,6 +453,7 @@ static u32 hvs_get_local_cid(void)
 static int hvs_sock_init(struct vsock_sock *vsk, struct vsock_sock *psk)
 {
 	struct hvsock *hvs;
+	struct sock *sk = sk_vsock(vsk);
 
 	hvs = kzalloc(sizeof(*hvs), GFP_KERNEL);
 	if (!hvs)
@@ -431,7 +461,8 @@ static int hvs_sock_init(struct vsock_sock *vsk, struct vsock_sock *psk)
 
 	vsk->trans = hvs;
 	hvs->vsk = vsk;
-
+	sk->sk_sndbuf = RINGBUFFER_HVS_SND_SIZE;
+	sk->sk_rcvbuf = RINGBUFFER_HVS_RCV_SIZE;
 	return 0;
 }
 
@@ -627,7 +658,9 @@ static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg,
 	struct hvsock *hvs = vsk->trans;
 	struct vmbus_channel *chan = hvs->chan;
 	struct hvs_send_buf *send_buf;
-	ssize_t to_write, max_writable, ret;
+	ssize_t to_write, max_writable;
+	ssize_t ret = 0;
+	ssize_t bytes_written = 0;
 
 	BUILD_BUG_ON(sizeof(*send_buf) != PAGE_SIZE_4K);
 
@@ -635,20 +668,34 @@ static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg,
 	if (!send_buf)
 		return -ENOMEM;
 
-	max_writable = hvs_channel_writable_bytes(chan);
-	to_write = min_t(ssize_t, len, max_writable);
-	to_write = min_t(ssize_t, to_write, HVS_SEND_BUF_SIZE);
-
-	ret = memcpy_from_msg(send_buf->data, msg, to_write);
-	if (ret < 0)
-		goto out;
+	/* Reader(s) could be draining data from the channel as we write.
+	 * Maximize bandwidth, by iterating until the channel is found to be
+	 * full.
+	 */
+	while (len) {
+		max_writable = hvs_channel_writable_bytes(chan);
+		if (!max_writable)
+			break;
+		to_write = min_t(ssize_t, len, max_writable);
+		to_write = min_t(ssize_t, to_write, HVS_SEND_BUF_SIZE);
+		/* memcpy_from_msg is safe for loop as it advances the offsets
+		 * within the message iterator.
+		 */
+		ret = memcpy_from_msg(send_buf->data, msg, to_write);
+		if (ret < 0)
+			goto out;
 
-	ret = hvs_send_data(hvs->chan, send_buf, to_write);
-	if (ret < 0)
-		goto out;
+		ret = hvs_send_data(hvs->chan, send_buf, to_write);
+		if (ret < 0)
+			goto out;
 
-	ret = to_write;
+		bytes_written += to_write;
+		len -= to_write;
+	}
 out:
+	/* If any data has been sent, return that */
+	if (bytes_written)
+		ret = bytes_written;
 	kfree(send_buf);
 	return ret;
 }