Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband

Pull InfiniBand/RDMA changes for the 3.4 merge window from Roland Dreier:
 "Nothing big really stands out; by patch count lots of fixes to the
  mlx4 driver plus some cleanups and fixes to the core and other
  drivers."

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (28 commits)
  mlx4_core: Scale size of MTT table with system RAM
  mlx4_core: Allow dynamic MTU configuration for IB ports
  IB/mlx4: Fix info returned when querying IBoE ports
  IB/mlx4: Fix possible missed completion event
  mlx4_core: Report thermal error events
  mlx4_core: Fix one more static exported function
  IB: Change CQE "csum_ok" field to a bit flag
  RDMA/iwcm: Reject connect requests if cmid is not in LISTEN state
  RDMA/cxgb3: Don't pass irq flags to flush_qp()
  mlx4_core: Get rid of redundant ext_port_cap flags
  RDMA/ucma: Fix AB-BA deadlock
  IB/ehca: Fix ilog2() compile failure
  IB: Use central enum for speed instead of hard-coded values
  IB/iser: Post initial receive buffers before sending the final login request
  IB/iser: Free IB connection resources in the proper place
  IB/srp: Consolidate repetitive sysfs code
  IB/srp: Use pr_fmt() and pr_err()/pr_warn()
  IB/core: Fix SDR rates in sysfs
  mlx4: Enforce device max FMR maps in FMR alloc
  IB/mlx4: Set bad_wr for invalid send opcode
  ...

6 files changed, 201 insertions, 56 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 9129ace02560..3b6f8efbf141 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -79,7 +79,8 @@ enum {
 			       (1ull << MLX4_EVENT_TYPE_SRQ_LIMIT)	    | \
 			       (1ull << MLX4_EVENT_TYPE_CMD)		    | \
 			       (1ull << MLX4_EVENT_TYPE_COMM_CHANNEL)       | \
-			       (1ull << MLX4_EVENT_TYPE_FLR_EVENT))
+			       (1ull << MLX4_EVENT_TYPE_FLR_EVENT)	    | \
+			       (1ull << MLX4_EVENT_TYPE_FATAL_WARNING))
 
 static void eq_set_ci(struct mlx4_eq *eq, int req_not)
 {
@@ -443,6 +444,35 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 			queue_work(priv->mfunc.master.comm_wq,
 				   &priv->mfunc.master.slave_flr_event_work);
 			break;
+
+		case MLX4_EVENT_TYPE_FATAL_WARNING:
+			if (eqe->subtype == MLX4_FATAL_WARNING_SUBTYPE_WARMING) {
+				if (mlx4_is_master(dev))
+					for (i = 0; i < dev->num_slaves; i++) {
+						mlx4_dbg(dev, "%s: Sending "
+							"MLX4_FATAL_WARNING_SUBTYPE_WARMING"
+							" to slave: %d\n", __func__, i);
+						if (i == dev->caps.function)
+							continue;
+						mlx4_slave_event(dev, i, eqe);
+					}
+				mlx4_err(dev, "Temperature Threshold was reached! "
+					"Threshold: %d celsius degrees; "
+					"Current Temperature: %d\n",
+					be16_to_cpu(eqe->event.warming.warning_threshold),
+					be16_to_cpu(eqe->event.warming.current_temperature));
+			} else
+				mlx4_warn(dev, "Unhandled event FATAL WARNING (%02x), "
+					  "subtype %02x on EQ %d at index %u. owner=%x, "
+					  "nent=0x%x, slave=%x, ownership=%s\n",
+					  eqe->type, eqe->subtype, eq->eqn,
+					  eq->cons_index, eqe->owner, eq->nent,
+					  eqe->slave_id,
+					  !!(eqe->owner & 0x80) ^
+					  !!(eq->cons_index & eq->nent) ? "HW" : "SW");
+
+			break;
+
 		case MLX4_EVENT_TYPE_EEC_CATAS_ERROR:
 		case MLX4_EVENT_TYPE_ECC_DETECT:
 		default:
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 5f15014713bc..8bb05b46db86 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -394,7 +394,7 @@ static int mlx4_how_many_lives_vf(struct mlx4_dev *dev)
 	return ret;
 }
 
-static int mlx4_is_slave_active(struct mlx4_dev *dev, int slave)
+int mlx4_is_slave_active(struct mlx4_dev *dev, int slave)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_slave_state *s_slave;
@@ -646,6 +646,99 @@ out:
 	return err ? err : count;
 }
 
+enum ibta_mtu {
+	IB_MTU_256  = 1,
+	IB_MTU_512  = 2,
+	IB_MTU_1024 = 3,
+	IB_MTU_2048 = 4,
+	IB_MTU_4096 = 5
+};
+
+static inline int int_to_ibta_mtu(int mtu)
+{
+	switch (mtu) {
+	case 256:  return IB_MTU_256;
+	case 512:  return IB_MTU_512;
+	case 1024: return IB_MTU_1024;
+	case 2048: return IB_MTU_2048;
+	case 4096: return IB_MTU_4096;
+	default: return -1;
+	}
+}
+
+static inline int ibta_mtu_to_int(enum ibta_mtu mtu)
+{
+	switch (mtu) {
+	case IB_MTU_256:  return  256;
+	case IB_MTU_512:  return  512;
+	case IB_MTU_1024: return 1024;
+	case IB_MTU_2048: return 2048;
+	case IB_MTU_4096: return 4096;
+	default: return -1;
+	}
+}
+
+static ssize_t show_port_ib_mtu(struct device *dev,
+			     struct device_attribute *attr,
+			     char *buf)
+{
+	struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info,
+						   port_mtu_attr);
+	struct mlx4_dev *mdev = info->dev;
+
+	if (mdev->caps.port_type[info->port] == MLX4_PORT_TYPE_ETH)
+		mlx4_warn(mdev, "port level mtu is only used for IB ports\n");
+
+	sprintf(buf, "%d\n",
+			ibta_mtu_to_int(mdev->caps.port_ib_mtu[info->port]));
+	return strlen(buf);
+}
+
+static ssize_t set_port_ib_mtu(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info,
+						   port_mtu_attr);
+	struct mlx4_dev *mdev = info->dev;
+	struct mlx4_priv *priv = mlx4_priv(mdev);
+	int err, port, mtu, ibta_mtu = -1;
+
+	if (mdev->caps.port_type[info->port] == MLX4_PORT_TYPE_ETH) {
+		mlx4_warn(mdev, "port level mtu is only used for IB ports\n");
+		return -EINVAL;
+	}
+
+	err = sscanf(buf, "%d", &mtu);
+	if (err > 0)
+		ibta_mtu = int_to_ibta_mtu(mtu);
+
+	if (err <= 0 || ibta_mtu < 0) {
+		mlx4_err(mdev, "%s is invalid IBTA mtu\n", buf);
+		return -EINVAL;
+	}
+
+	mdev->caps.port_ib_mtu[info->port] = ibta_mtu;
+
+	mlx4_stop_sense(mdev);
+	mutex_lock(&priv->port_mutex);
+	mlx4_unregister_device(mdev);
+	for (port = 1; port <= mdev->caps.num_ports; port++) {
+		mlx4_CLOSE_PORT(mdev, port);
+		err = mlx4_SET_PORT(mdev, port);
+		if (err) {
+			mlx4_err(mdev, "Failed to set port %d, "
+				      "aborting\n", port);
+			goto err_set_port;
+		}
+	}
+	err = mlx4_register_device(mdev);
+err_set_port:
+	mutex_unlock(&priv->port_mutex);
+	mlx4_start_sense(mdev);
+	return err ? err : count;
+}
+
 static int mlx4_load_fw(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -1133,6 +1226,8 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 			goto err_stop_fw;
 		}
 
+		dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1;
+
 		init_hca.log_uar_sz = ilog2(dev->caps.num_uars);
 		init_hca.uar_page_sz = PAGE_SHIFT - 12;
 
@@ -1363,12 +1458,10 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 					  "with caps = 0\n", port, err);
 			dev->caps.ib_port_def_cap[port] = ib_port_default_caps;
 
-			err = mlx4_check_ext_port_caps(dev, port);
-			if (err)
-				mlx4_warn(dev, "failed to get port %d extended "
-					  "port capabilities support info (%d)."
-					  " Assuming not supported\n",
-					  port, err);
+			if (mlx4_is_mfunc(dev))
+				dev->caps.port_ib_mtu[port] = IB_MTU_2048;
+			else
+				dev->caps.port_ib_mtu[port] = IB_MTU_4096;
 
 			err = mlx4_SET_PORT(dev, port);
 			if (err) {
@@ -1524,6 +1617,24 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
 		info->port = -1;
 	}
 
+	sprintf(info->dev_mtu_name, "mlx4_port%d_mtu", port);
+	info->port_mtu_attr.attr.name = info->dev_mtu_name;
+	if (mlx4_is_mfunc(dev))
+		info->port_mtu_attr.attr.mode = S_IRUGO;
+	else {
+		info->port_mtu_attr.attr.mode = S_IRUGO | S_IWUSR;
+		info->port_mtu_attr.store     = set_port_ib_mtu;
+	}
+	info->port_mtu_attr.show      = show_port_ib_mtu;
+	sysfs_attr_init(&info->port_mtu_attr.attr);
+
+	err = device_create_file(&dev->pdev->dev, &info->port_mtu_attr);
+	if (err) {
+		mlx4_err(dev, "Failed to create mtu file for port %d\n", port);
+		device_remove_file(&info->dev->pdev->dev, &info->port_attr);
+		info->port = -1;
+	}
+
 	return err;
 }
 
@@ -1533,6 +1644,7 @@ static void mlx4_cleanup_port_info(struct mlx4_port_info *info)
 		return;
 
 	device_remove_file(&info->dev->pdev->dev, &info->port_attr);
+	device_remove_file(&info->dev->pdev->dev, &info->port_mtu_attr);
 }
 
 static int mlx4_init_steering(struct mlx4_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 5da51b99dbb8..2a0ff2cc7182 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -363,6 +363,10 @@ struct mlx4_eqe {
 		struct {
 			__be32	slave_id;
 		} __packed flr_event;
+		struct {
+			__be16  current_temperature;
+			__be16  warning_threshold;
+		} __packed warming;
 	}			event;
 	u8			slave_id;
 	u8			reserved3[2];
@@ -399,7 +403,7 @@ struct mlx4_profile {
 	int			num_cq;
 	int			num_mcg;
 	int			num_mpt;
-	int			num_mtt;
+	unsigned		num_mtt;
 };
 
 struct mlx4_fw {
@@ -682,6 +686,8 @@ struct mlx4_port_info {
 	char			dev_name[16];
 	struct device_attribute port_attr;
 	enum mlx4_port_type	tmp_type;
+	char			dev_mtu_name[16];
+	struct device_attribute port_mtu_attr;
 	struct mlx4_mac_table	mac_table;
 	struct radix_tree_root	mac_tree;
 	struct mlx4_vlan_table	vlan_table;
@@ -1024,7 +1030,6 @@ int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave,
 			    struct mlx4_cmd_mailbox *outbox,
 			    struct mlx4_cmd_info *cmd);
 int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps);
-int mlx4_check_ext_port_caps(struct mlx4_dev *dev, u8 port);
 
 
 int mlx4_QP_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index 32e2b6616f3d..fe2ac8449c19 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -791,6 +791,9 @@ int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages,
 	u64 mtt_offset;
 	int err = -ENOMEM;
 
+	if (max_maps > dev->caps.max_fmr_maps)
+		return -EINVAL;
+
 	if (page_shift < (ffs(dev->caps.page_size_cap) - 1) || page_shift >= 32)
 		return -EINVAL;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 98e776261ead..77535ff18f1b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -590,49 +590,6 @@ int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps)
 	return err;
 }
 
-int mlx4_check_ext_port_caps(struct mlx4_dev *dev, u8 port)
-{
-	struct mlx4_cmd_mailbox *inmailbox, *outmailbox;
-	u8 *inbuf, *outbuf;
-	int err, packet_error;
-
-	inmailbox = mlx4_alloc_cmd_mailbox(dev);
-	if (IS_ERR(inmailbox))
-		return PTR_ERR(inmailbox);
-
-	outmailbox = mlx4_alloc_cmd_mailbox(dev);
-	if (IS_ERR(outmailbox)) {
-		mlx4_free_cmd_mailbox(dev, inmailbox);
-		return PTR_ERR(outmailbox);
-	}
-
-	inbuf = inmailbox->buf;
-	outbuf = outmailbox->buf;
-	memset(inbuf, 0, 256);
-	memset(outbuf, 0, 256);
-	inbuf[0] = 1;
-	inbuf[1] = 1;
-	inbuf[2] = 1;
-	inbuf[3] = 1;
-
-	*(__be16 *) (&inbuf[16]) = MLX4_ATTR_EXTENDED_PORT_INFO;
-	*(__be32 *) (&inbuf[20]) = cpu_to_be32(port);
-
-	err = mlx4_cmd_box(dev, inmailbox->dma, outmailbox->dma, port, 3,
-			   MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C,
-			   MLX4_CMD_NATIVE);
-
-	packet_error = be16_to_cpu(*(__be16 *) (outbuf + 4));
-
-	dev->caps.ext_port_cap[port] = (!err && !packet_error) ?
-				       MLX_EXT_PORT_CAP_FLAG_EXTENDED_PORT_INFO
-				       : 0;
-
-	mlx4_free_cmd_mailbox(dev, inmailbox);
-	mlx4_free_cmd_mailbox(dev, outmailbox);
-	return err;
-}
-
 static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
 				u8 op_mod, struct mlx4_cmd_mailbox *inbox)
 {
@@ -766,10 +723,18 @@ int mlx4_SET_PORT_wrapper(struct mlx4_dev *dev, int slave,
 				    vhcr->op_modifier, inbox);
 }
 
+/* bit locations for set port command with zero op modifier */
+enum {
+	MLX4_SET_PORT_VL_CAP	 = 4, /* bits 7:4 */
+	MLX4_SET_PORT_MTU_CAP	 = 12, /* bits 15:12 */
+	MLX4_CHANGE_PORT_VL_CAP	 = 21,
+	MLX4_CHANGE_PORT_MTU_CAP = 22,
+};
+
 int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port)
 {
 	struct mlx4_cmd_mailbox *mailbox;
-	int err;
+	int err, vl_cap;
 
 	if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH)
 		return 0;
@@ -781,8 +746,19 @@ int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port)
 	memset(mailbox->buf, 0, 256);
 
 	((__be32 *) mailbox->buf)[1] = dev->caps.ib_port_def_cap[port];
-	err = mlx4_cmd(dev, mailbox->dma, port, 0, MLX4_CMD_SET_PORT,
-		       MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
+
+	/* IB VL CAP enum isn't used by the firmware, just numerical values */
+	for (vl_cap = 8; vl_cap >= 1; vl_cap >>= 1) {
+		((__be32 *) mailbox->buf)[0] = cpu_to_be32(
+			(1 << MLX4_CHANGE_PORT_MTU_CAP) |
+			(1 << MLX4_CHANGE_PORT_VL_CAP)  |
+			(dev->caps.port_ib_mtu[port] << MLX4_SET_PORT_MTU_CAP) |
+			(vl_cap << MLX4_SET_PORT_VL_CAP));
+		err = mlx4_cmd(dev, mailbox->dma, port, 0, MLX4_CMD_SET_PORT,
+				MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
+		if (err != -ENOMEM)
+			break;
+	}
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/profile.c b/drivers/net/ethernet/mellanox/mlx4/profile.c
index 1129677daa62..06e5adeb76f7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/profile.c
+++ b/drivers/net/ethernet/mellanox/mlx4/profile.c
@@ -83,12 +83,31 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 	u64 total_size = 0;
 	struct mlx4_resource *profile;
 	struct mlx4_resource tmp;
+	struct sysinfo si;
 	int i, j;
 
 	profile = kcalloc(MLX4_RES_NUM, sizeof(*profile), GFP_KERNEL);
 	if (!profile)
 		return -ENOMEM;
 
+	/*
+	 * We want to scale the number of MTTs with the size of the
+	 * system memory, since it makes sense to register a lot of
+	 * memory on a system with a lot of memory.  As a heuristic,
+	 * make sure we have enough MTTs to cover twice the system
+	 * memory (with PAGE_SIZE entries).
+	 *
+	 * This number has to be a power of two and fit into 32 bits
+	 * due to device limitations, so cap this at 2^31 as well.
+	 * That limits us to 8TB of memory registration per HCA with
+	 * 4KB pages, which is probably OK for the next few months.
+	 */
+	si_meminfo(&si);
+	request->num_mtt =
+		roundup_pow_of_two(max_t(unsigned, request->num_mtt,
+					 min(1UL << 31,
+					     si.totalram >> (log_mtts_per_seg - 1))));
+
 	profile[MLX4_RES_QP].size     = dev_cap->qpc_entry_sz;
 	profile[MLX4_RES_RDMARC].size = dev_cap->rdmarc_entry_sz;
 	profile[MLX4_RES_ALTC].size   = dev_cap->altc_entry_sz;