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

Pull networking updates from David Miller:
 "Reasonably busy this cycle, but perhaps not as busy as in the 4.12
  merge window:

   1) Several optimizations for UDP processing under high load from
      Paolo Abeni.

   2) Support pacing internally in TCP when using the sch_fq packet
      scheduler for this is not practical. From Eric Dumazet.

   3) Support mutliple filter chains per qdisc, from Jiri Pirko.

   4) Move to 1ms TCP timestamp clock, from Eric Dumazet.

   5) Add batch dequeueing to vhost_net, from Jason Wang.

   6) Flesh out more completely SCTP checksum offload support, from
      Davide Caratti.

   7) More plumbing of extended netlink ACKs, from David Ahern, Pablo
      Neira Ayuso, and Matthias Schiffer.

   8) Add devlink support to nfp driver, from Simon Horman.

   9) Add RTM_F_FIB_MATCH flag to RTM_GETROUTE queries, from Roopa
      Prabhu.

  10) Add stack depth tracking to BPF verifier and use this information
      in the various eBPF JITs. From Alexei Starovoitov.

  11) Support XDP on qed device VFs, from Yuval Mintz.

  12) Introduce BPF PROG ID for better introspection of installed BPF
      programs. From Martin KaFai Lau.

  13) Add bpf_set_hash helper for TC bpf programs, from Daniel Borkmann.

  14) For loads, allow narrower accesses in bpf verifier checking, from
      Yonghong Song.

  15) Support MIPS in the BPF selftests and samples infrastructure, the
      MIPS eBPF JIT will be merged in via the MIPS GIT tree. From David
      Daney.

  16) Support kernel based TLS, from Dave Watson and others.

  17) Remove completely DST garbage collection, from Wei Wang.

  18) Allow installing TCP MD5 rules using prefixes, from Ivan
      Delalande.

  19) Add XDP support to Intel i40e driver, from Björn Töpel

  20) Add support for TC flower offload in nfp driver, from Simon
      Horman, Pieter Jansen van Vuuren, Benjamin LaHaise, Jakub
      Kicinski, and Bert van Leeuwen.

  21) IPSEC offloading support in mlx5, from Ilan Tayari.

  22) Add HW PTP support to macb driver, from Rafal Ozieblo.

  23) Networking refcount_t conversions, From Elena Reshetova.

  24) Add sock_ops support to BPF, from Lawrence Brako. This is useful
      for tuning the TCP sockopt settings of a group of applications,
      currently via CGROUPs"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1899 commits)
  net: phy: dp83867: add workaround for incorrect RX_CTRL pin strap
  dt-bindings: phy: dp83867: provide a workaround for incorrect RX_CTRL pin strap
  cxgb4: Support for get_ts_info ethtool method
  cxgb4: Add PTP Hardware Clock (PHC) support
  cxgb4: time stamping interface for PTP
  nfp: default to chained metadata prepend format
  nfp: remove legacy MAC address lookup
  nfp: improve order of interfaces in breakout mode
  net: macb: remove extraneous return when MACB_EXT_DESC is defined
  bpf: add missing break in for the TCP_BPF_SNDCWND_CLAMP case
  bpf: fix return in load_bpf_file
  mpls: fix rtm policy in mpls_getroute
  net, ax25: convert ax25_cb.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_route.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_uid_assoc.refcount from atomic_t to refcount_t
  net, sctp: convert sctp_ep_common.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_transport.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_chunk.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_datamsg.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_auth_bytes.refcnt from atomic_t to refcount_t
  ...

1 files changed, 59 insertions, 73 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 9ecc089..dc2f59e 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -60,8 +60,7 @@
 #include "cmd.h"
 
 #define DRIVER_NAME "mlx5_ib"
-#define DRIVER_VERSION "2.2-1"
-#define DRIVER_RELDATE	"Feb 2014"
+#define DRIVER_VERSION "5.0-0"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox Connect-IB HCA IB driver");
@@ -70,7 +69,7 @@ MODULE_VERSION(DRIVER_VERSION);
 
 static char mlx5_version[] =
 	DRIVER_NAME ": Mellanox Connect-IB Infiniband driver v"
-	DRIVER_VERSION " (" DRIVER_RELDATE ")\n";
+	DRIVER_VERSION "\n";
 
 enum {
 	MLX5_ATOMIC_SIZE_QP_8BYTES = 1 << 3,
@@ -224,8 +223,8 @@ static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed,
 	return 0;
 }
 
-static void mlx5_query_port_roce(struct ib_device *device, u8 port_num,
-				 struct ib_port_attr *props)
+static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
+				struct ib_port_attr *props)
 {
 	struct mlx5_ib_dev *dev = to_mdev(device);
 	struct mlx5_core_dev *mdev = dev->mdev;
@@ -233,12 +232,14 @@ static void mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	enum ib_mtu ndev_ib_mtu;
 	u16 qkey_viol_cntr;
 	u32 eth_prot_oper;
+	int err;
 
 	/* Possible bad flows are checked before filling out props so in case
 	 * of an error it will still be zeroed out.
 	 */
-	if (mlx5_query_port_eth_proto_oper(mdev, &eth_prot_oper, port_num))
-		return;
+	err = mlx5_query_port_eth_proto_oper(mdev, &eth_prot_oper, port_num);
+	if (err)
+		return err;
 
 	translate_eth_proto_oper(eth_prot_oper, &props->active_speed,
 				 &props->active_width);
@@ -259,7 +260,7 @@ static void mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 
 	ndev = mlx5_ib_get_netdev(device, port_num);
 	if (!ndev)
-		return;
+		return 0;
 
 	if (mlx5_lag_is_active(dev->mdev)) {
 		rcu_read_lock();
@@ -282,75 +283,49 @@ static void mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	dev_put(ndev);
 
 	props->active_mtu	= min(props->max_mtu, ndev_ib_mtu);
+	return 0;
 }
 
-static void ib_gid_to_mlx5_roce_addr(const union ib_gid *gid,
-				     const struct ib_gid_attr *attr,
-				     void *mlx5_addr)
+static int set_roce_addr(struct mlx5_ib_dev *dev, u8 port_num,
+			 unsigned int index, const union ib_gid *gid,
+			 const struct ib_gid_attr *attr)
 {
-#define MLX5_SET_RA(p, f, v) MLX5_SET(roce_addr_layout, p, f, v)
-	char *mlx5_addr_l3_addr	= MLX5_ADDR_OF(roce_addr_layout, mlx5_addr,
-					       source_l3_address);
-	void *mlx5_addr_mac	= MLX5_ADDR_OF(roce_addr_layout, mlx5_addr,
-					       source_mac_47_32);
-
-	if (!gid)
-		return;
+	enum ib_gid_type gid_type = IB_GID_TYPE_IB;
+	u8 roce_version = 0;
+	u8 roce_l3_type = 0;
+	bool vlan = false;
+	u8 mac[ETH_ALEN];
+	u16 vlan_id = 0;
 
-	ether_addr_copy(mlx5_addr_mac, attr->ndev->dev_addr);
+	if (gid) {
+		gid_type = attr->gid_type;
+		ether_addr_copy(mac, attr->ndev->dev_addr);
 
-	if (is_vlan_dev(attr->ndev)) {
-		MLX5_SET_RA(mlx5_addr, vlan_valid, 1);
-		MLX5_SET_RA(mlx5_addr, vlan_id, vlan_dev_vlan_id(attr->ndev));
+		if (is_vlan_dev(attr->ndev)) {
+			vlan = true;
+			vlan_id = vlan_dev_vlan_id(attr->ndev);
+		}
 	}
 
-	switch (attr->gid_type) {
+	switch (gid_type) {
 	case IB_GID_TYPE_IB:
-		MLX5_SET_RA(mlx5_addr, roce_version, MLX5_ROCE_VERSION_1);
+		roce_version = MLX5_ROCE_VERSION_1;
 		break;
 	case IB_GID_TYPE_ROCE_UDP_ENCAP:
-		MLX5_SET_RA(mlx5_addr, roce_version, MLX5_ROCE_VERSION_2);
+		roce_version = MLX5_ROCE_VERSION_2;
+		if (ipv6_addr_v4mapped((void *)gid))
+			roce_l3_type = MLX5_ROCE_L3_TYPE_IPV4;
+		else
+			roce_l3_type = MLX5_ROCE_L3_TYPE_IPV6;
 		break;
 
 	default:
-		WARN_ON(true);
+		mlx5_ib_warn(dev, "Unexpected GID type %u\n", gid_type);
 	}
 
-	if (attr->gid_type != IB_GID_TYPE_IB) {
-		if (ipv6_addr_v4mapped((void *)gid))
-			MLX5_SET_RA(mlx5_addr, roce_l3_type,
-				    MLX5_ROCE_L3_TYPE_IPV4);
-		else
-			MLX5_SET_RA(mlx5_addr, roce_l3_type,
-				    MLX5_ROCE_L3_TYPE_IPV6);
-	}
-
-	if ((attr->gid_type == IB_GID_TYPE_IB) ||
-	    !ipv6_addr_v4mapped((void *)gid))
-		memcpy(mlx5_addr_l3_addr, gid, sizeof(*gid));
-	else
-		memcpy(&mlx5_addr_l3_addr[12], &gid->raw[12], 4);
-}
-
-static int set_roce_addr(struct ib_device *device, u8 port_num,
-			 unsigned int index,
-			 const union ib_gid *gid,
-			 const struct ib_gid_attr *attr)
-{
-	struct mlx5_ib_dev *dev = to_mdev(device);
-	u32  in[MLX5_ST_SZ_DW(set_roce_address_in)]  = {0};
-	u32 out[MLX5_ST_SZ_DW(set_roce_address_out)] = {0};
-	void *in_addr = MLX5_ADDR_OF(set_roce_address_in, in, roce_address);
-	enum rdma_link_layer ll = mlx5_ib_port_link_layer(device, port_num);
-
-	if (ll != IB_LINK_LAYER_ETHERNET)
-		return -EINVAL;
-
-	ib_gid_to_mlx5_roce_addr(gid, attr, in_addr);
-
-	MLX5_SET(set_roce_address_in, in, roce_address_index, index);
-	MLX5_SET(set_roce_address_in, in, opcode, MLX5_CMD_OP_SET_ROCE_ADDRESS);
-	return mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, sizeof(out));
+	return mlx5_core_roce_gid_set(dev->mdev, index, roce_version,
+				      roce_l3_type, gid->raw, mac, vlan,
+				      vlan_id);
 }
 
 static int mlx5_ib_add_gid(struct ib_device *device, u8 port_num,
@@ -358,13 +333,13 @@ static int mlx5_ib_add_gid(struct ib_device *device, u8 port_num,
 			   const struct ib_gid_attr *attr,
 			   __always_unused void **context)
 {
-	return set_roce_addr(device, port_num, index, gid, attr);
+	return set_roce_addr(to_mdev(device), port_num, index, gid, attr);
 }
 
 static int mlx5_ib_del_gid(struct ib_device *device, u8 port_num,
 			   unsigned int index, __always_unused void **context)
 {
-	return set_roce_addr(device, port_num, index, NULL, NULL);
+	return set_roce_addr(to_mdev(device), port_num, index, NULL, NULL);
 }
 
 __be16 mlx5_get_roce_udp_sport(struct mlx5_ib_dev *dev, u8 port_num,
@@ -440,7 +415,7 @@ static void get_atomic_caps(struct mlx5_ib_dev *dev,
 	u8 atomic_operations = MLX5_CAP_ATOMIC(dev->mdev, atomic_operations);
 	u8 atomic_size_qp = MLX5_CAP_ATOMIC(dev->mdev, atomic_size_qp);
 	u8 atomic_req_8B_endianness_mode =
-		MLX5_CAP_ATOMIC(dev->mdev, atomic_req_8B_endianess_mode);
+		MLX5_CAP_ATOMIC(dev->mdev, atomic_req_8B_endianness_mode);
 
 	/* Check if HW supports 8 bytes standard atomic operations and capable
 	 * of host endianness respond
@@ -979,20 +954,31 @@ out:
 int mlx5_ib_query_port(struct ib_device *ibdev, u8 port,
 		       struct ib_port_attr *props)
 {
+	unsigned int count;
+	int ret;
+
 	switch (mlx5_get_vport_access_method(ibdev)) {
 	case MLX5_VPORT_ACCESS_METHOD_MAD:
-		return mlx5_query_mad_ifc_port(ibdev, port, props);
+		ret = mlx5_query_mad_ifc_port(ibdev, port, props);
+		break;
 
 	case MLX5_VPORT_ACCESS_METHOD_HCA:
-		return mlx5_query_hca_port(ibdev, port, props);
+		ret = mlx5_query_hca_port(ibdev, port, props);
+		break;
 
 	case MLX5_VPORT_ACCESS_METHOD_NIC:
-		mlx5_query_port_roce(ibdev, port, props);
-		return 0;
+		ret = mlx5_query_port_roce(ibdev, port, props);
+		break;
 
 	default:
-		return -EINVAL;
+		ret = -EINVAL;
+	}
+
+	if (!ret && props) {
+		count = mlx5_core_reserved_gids_count(to_mdev(ibdev)->mdev);
+		props->gid_tbl_len -= count;
 	}
+	return ret;
 }
 
 static int mlx5_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
@@ -2263,7 +2249,7 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 	if (!is_valid_attr(dev->mdev, flow_attr))
 		return ERR_PTR(-EINVAL);
 
-	spec = mlx5_vzalloc(sizeof(*spec));
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	handler = kzalloc(sizeof(*handler), GFP_KERNEL);
 	if (!handler || !spec) {
 		err = -ENOMEM;
@@ -3468,7 +3454,7 @@ static int mlx5_ib_query_q_counters(struct mlx5_ib_dev *dev,
 	__be32 val;
 	int ret, i;
 
-	out = mlx5_vzalloc(outlen);
+	out = kvzalloc(outlen, GFP_KERNEL);
 	if (!out)
 		return -ENOMEM;
 
@@ -3497,7 +3483,7 @@ static int mlx5_ib_query_cong_counters(struct mlx5_ib_dev *dev,
 	int ret, i;
 	int offset = port->cnts.num_q_counters;
 
-	out = mlx5_vzalloc(outlen);
+	out = kvzalloc(outlen, GFP_KERNEL);
 	if (!out)
 		return -ENOMEM;