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

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (62 commits)
  mlx4_core: Deprecate log_num_vlan module param
  IB/mlx4: Don't set VLAN in IBoE WQEs' control segment
  IB/mlx4: Enable 4K mtu for IBoE
  RDMA/cxgb4: Mark QP in error before disabling the queue in firmware
  RDMA/cxgb4: Serialize calls to CQ's comp_handler
  RDMA/cxgb3: Serialize calls to CQ's comp_handler
  IB/qib: Fix issue with link states and QSFP cables
  IB/mlx4: Configure extended active speeds
  mlx4_core: Add extended port capabilities support
  IB/qib: Hold links until tuning data is available
  IB/qib: Clean up checkpatch issue
  IB/qib: Remove s_lock around header validation
  IB/qib: Precompute timeout jiffies to optimize latency
  IB/qib: Use RCU for qpn lookup
  IB/qib: Eliminate divide/mod in converting idx to egr buf pointer
  IB/qib: Decode path MTU optimization
  IB/qib: Optimize RC/UC code by IB operation
  IPoIB: Use the right function to do DMA unmap pages
  RDMA/cxgb4: Use correct QID in insert_recv_cqe()
  RDMA/cxgb4: Make sure flush CQ entries are collected on connection close
  ...

10 files changed, 147 insertions, 30 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 1ad1f6029af8..869a2c220a7b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -484,7 +484,7 @@ static void mlx4_free_eq(struct mlx4_dev *dev,
 
 	mlx4_mtt_cleanup(dev, &eq->mtt);
 	for (i = 0; i < npages; ++i)
-		pci_free_consistent(dev->pdev, PAGE_SIZE,
+		dma_free_coherent(&dev->pdev->dev, PAGE_SIZE,
 				    eq->page_list[i].buf,
 				    eq->page_list[i].map);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index ed452ddfe342..abdfbacab4a6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -205,6 +205,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_MAX_MCG_OFFSET		0x63
 #define QUERY_DEV_CAP_RSVD_PD_OFFSET		0x64
 #define QUERY_DEV_CAP_MAX_PD_OFFSET		0x65
+#define QUERY_DEV_CAP_RSVD_XRC_OFFSET		0x66
+#define QUERY_DEV_CAP_MAX_XRC_OFFSET		0x67
 #define QUERY_DEV_CAP_MAX_COUNTERS_OFFSET	0x68
 #define QUERY_DEV_CAP_RDMARC_ENTRY_SZ_OFFSET	0x80
 #define QUERY_DEV_CAP_QPC_ENTRY_SZ_OFFSET	0x82
@@ -319,6 +321,10 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev_cap->reserved_pds = field >> 4;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_PD_OFFSET);
 	dev_cap->max_pds = 1 << (field & 0x3f);
+	MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_XRC_OFFSET);
+	dev_cap->reserved_xrcds = field >> 4;
+	MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_PD_OFFSET);
+	dev_cap->max_xrcds = 1 << (field & 0x1f);
 
 	MLX4_GET(size, outbox, QUERY_DEV_CAP_RDMARC_ENTRY_SZ_OFFSET);
 	dev_cap->rdmarc_entry_sz = size;
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 1e8ecc3708e2..bf5ec2286528 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -93,6 +93,8 @@ struct mlx4_dev_cap {
 	int max_mcgs;
 	int reserved_pds;
 	int max_pds;
+	int reserved_xrcds;
+	int max_xrcds;
 	int qpc_entry_sz;
 	int rdmarc_entry_sz;
 	int altc_entry_sz;
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index f0ee35df4dd7..94bbc85a532d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -96,6 +96,8 @@ MODULE_PARM_DESC(log_num_mac, "Log2 max number of MACs per ETH port (1-7)");
 static int log_num_vlan;
 module_param_named(log_num_vlan, log_num_vlan, int, 0444);
 MODULE_PARM_DESC(log_num_vlan, "Log2 max number of VLANs per ETH port (0-7)");
+/* Log2 max number of VLANs per ETH port (0-7) */
+#define MLX4_LOG_NUM_VLANS 7
 
 static int use_prio;
 module_param_named(use_prio, use_prio, bool, 0444);
@@ -220,6 +222,10 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.reserved_mrws	     = dev_cap->reserved_mrws;
 	dev->caps.reserved_uars	     = dev_cap->reserved_uars;
 	dev->caps.reserved_pds	     = dev_cap->reserved_pds;
+	dev->caps.reserved_xrcds     = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ?
+					dev_cap->reserved_xrcds : 0;
+	dev->caps.max_xrcds          = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ?
+					dev_cap->max_xrcds : 0;
 	dev->caps.mtt_entry_sz	     = dev->caps.mtts_per_seg * dev_cap->mtt_entry_sz;
 	dev->caps.max_msg_sz         = dev_cap->max_msg_sz;
 	dev->caps.page_size_cap	     = ~(u32) (dev_cap->min_page_sz - 1);
@@ -230,7 +236,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
 
 	dev->caps.log_num_macs  = log_num_mac;
-	dev->caps.log_num_vlans = log_num_vlan;
+	dev->caps.log_num_vlans = MLX4_LOG_NUM_VLANS;
 	dev->caps.log_num_prios = use_prio ? 3 : 0;
 
 	for (i = 1; i <= dev->caps.num_ports; ++i) {
@@ -912,11 +918,18 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 		goto err_kar_unmap;
 	}
 
+	err = mlx4_init_xrcd_table(dev);
+	if (err) {
+		mlx4_err(dev, "Failed to initialize "
+			 "reliable connection domain table, aborting.\n");
+		goto err_pd_table_free;
+	}
+
 	err = mlx4_init_mr_table(dev);
 	if (err) {
 		mlx4_err(dev, "Failed to initialize "
 			 "memory region table, aborting.\n");
-		goto err_pd_table_free;
+		goto err_xrcd_table_free;
 	}
 
 	err = mlx4_init_eq_table(dev);
@@ -998,6 +1011,13 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 				  "ib capabilities (%d). Continuing 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);
+
 		err = mlx4_SET_PORT(dev, port);
 		if (err) {
 			mlx4_err(dev, "Failed to set port %d, aborting\n",
@@ -1033,6 +1053,9 @@ err_eq_table_free:
 err_mr_table_free:
 	mlx4_cleanup_mr_table(dev);
 
+err_xrcd_table_free:
+	mlx4_cleanup_xrcd_table(dev);
+
 err_pd_table_free:
 	mlx4_cleanup_pd_table(dev);
 
@@ -1355,6 +1378,7 @@ err_port:
 	mlx4_cmd_use_polling(dev);
 	mlx4_cleanup_eq_table(dev);
 	mlx4_cleanup_mr_table(dev);
+	mlx4_cleanup_xrcd_table(dev);
 	mlx4_cleanup_pd_table(dev);
 	mlx4_cleanup_uar_table(dev);
 
@@ -1416,6 +1440,7 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 		mlx4_cmd_use_polling(dev);
 		mlx4_cleanup_eq_table(dev);
 		mlx4_cleanup_mr_table(dev);
+		mlx4_cleanup_xrcd_table(dev);
 		mlx4_cleanup_pd_table(dev);
 
 		iounmap(priv->kar);
@@ -1489,10 +1514,9 @@ static int __init mlx4_verify_params(void)
 		return -1;
 	}
 
-	if ((log_num_vlan < 0) || (log_num_vlan > 7)) {
-		pr_warning("mlx4_core: bad num_vlan: %d\n", log_num_vlan);
-		return -1;
-	}
+	if (log_num_vlan != 0)
+		pr_warning("mlx4_core: log_num_vlan - obsolete module param, using %d\n",
+			   MLX4_LOG_NUM_VLANS);
 
 	if ((log_mtts_per_seg < 1) || (log_mtts_per_seg > 7)) {
 		pr_warning("mlx4_core: bad log_mtts_per_seg: %d\n", log_mtts_per_seg);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index a2fcd8402d37..5dfa68ffc11c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -335,6 +335,7 @@ struct mlx4_priv {
 	struct mlx4_cmd		cmd;
 
 	struct mlx4_bitmap	pd_bitmap;
+	struct mlx4_bitmap	xrcd_bitmap;
 	struct mlx4_uar_table	uar_table;
 	struct mlx4_mr_table	mr_table;
 	struct mlx4_cq_table	cq_table;
@@ -384,6 +385,7 @@ int mlx4_alloc_eq_table(struct mlx4_dev *dev);
 void mlx4_free_eq_table(struct mlx4_dev *dev);
 
 int mlx4_init_pd_table(struct mlx4_dev *dev);
+int mlx4_init_xrcd_table(struct mlx4_dev *dev);
 int mlx4_init_uar_table(struct mlx4_dev *dev);
 int mlx4_init_mr_table(struct mlx4_dev *dev);
 int mlx4_init_eq_table(struct mlx4_dev *dev);
@@ -393,6 +395,7 @@ int mlx4_init_srq_table(struct mlx4_dev *dev);
 int mlx4_init_mcg_table(struct mlx4_dev *dev);
 
 void mlx4_cleanup_pd_table(struct mlx4_dev *dev);
+void mlx4_cleanup_xrcd_table(struct mlx4_dev *dev);
 void mlx4_cleanup_uar_table(struct mlx4_dev *dev);
 void mlx4_cleanup_mr_table(struct mlx4_dev *dev);
 void mlx4_cleanup_eq_table(struct mlx4_dev *dev);
@@ -450,6 +453,7 @@ void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table);
 
 int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port);
 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_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 			  enum mlx4_protocol prot, enum mlx4_steer_type steer);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index 9c188bdd7f4f..ab639cfef78e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -139,7 +139,7 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order)
 
 	buddy->bits = kzalloc((buddy->max_order + 1) * sizeof (long *),
 			      GFP_KERNEL);
-	buddy->num_free = kzalloc((buddy->max_order + 1) * sizeof (int *),
+	buddy->num_free = kcalloc((buddy->max_order + 1), sizeof *buddy->num_free,
 				  GFP_KERNEL);
 	if (!buddy->bits || !buddy->num_free)
 		goto err_out;
diff --git a/drivers/net/ethernet/mellanox/mlx4/pd.c b/drivers/net/ethernet/mellanox/mlx4/pd.c
index 1286b886dcea..3736163e30e9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/pd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/pd.c
@@ -61,6 +61,24 @@ void mlx4_pd_free(struct mlx4_dev *dev, u32 pdn)
 }
 EXPORT_SYMBOL_GPL(mlx4_pd_free);
 
+int mlx4_xrcd_alloc(struct mlx4_dev *dev, u32 *xrcdn)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	*xrcdn = mlx4_bitmap_alloc(&priv->xrcd_bitmap);
+	if (*xrcdn == -1)
+		return -ENOMEM;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx4_xrcd_alloc);
+
+void mlx4_xrcd_free(struct mlx4_dev *dev, u32 xrcdn)
+{
+	mlx4_bitmap_free(&mlx4_priv(dev)->xrcd_bitmap, xrcdn);
+}
+EXPORT_SYMBOL_GPL(mlx4_xrcd_free);
+
 int mlx4_init_pd_table(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -74,6 +92,18 @@ void mlx4_cleanup_pd_table(struct mlx4_dev *dev)
 	mlx4_bitmap_cleanup(&mlx4_priv(dev)->pd_bitmap);
 }
 
+int mlx4_init_xrcd_table(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	return mlx4_bitmap_init(&priv->xrcd_bitmap, (1 << 16),
+				(1 << 16) - 1, dev->caps.reserved_xrcds + 1, 0);
+}
+
+void mlx4_cleanup_xrcd_table(struct mlx4_dev *dev)
+{
+	mlx4_bitmap_cleanup(&mlx4_priv(dev)->xrcd_bitmap);
+}
 
 int mlx4_uar_alloc(struct mlx4_dev *dev, struct mlx4_uar *uar)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 163a314c148f..a44f080fdfe5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -148,22 +148,26 @@ int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn, u8 wrap)
 
 	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER) {
 		err = mlx4_uc_steer_add(dev, port, mac, qpn, 1);
-		if (!err) {
-			entry = kmalloc(sizeof *entry, GFP_KERNEL);
-			if (!entry) {
-				mlx4_uc_steer_release(dev, port, mac, *qpn, 1);
-				return -ENOMEM;
-			}
-			entry->mac = mac;
-			err = radix_tree_insert(&info->mac_tree, *qpn, entry);
-			if (err) {
-				mlx4_uc_steer_release(dev, port, mac, *qpn, 1);
-				return err;
-			}
-		} else
+		if (err)
 			return err;
+
+		entry = kmalloc(sizeof *entry, GFP_KERNEL);
+		if (!entry) {
+			mlx4_uc_steer_release(dev, port, mac, *qpn, 1);
+			return -ENOMEM;
+		}
+
+		entry->mac = mac;
+		err = radix_tree_insert(&info->mac_tree, *qpn, entry);
+		if (err) {
+			kfree(entry);
+			mlx4_uc_steer_release(dev, port, mac, *qpn, 1);
+			return err;
+		}
 	}
+
 	mlx4_dbg(dev, "Registering MAC: 0x%llx\n", (unsigned long long) mac);
+
 	mutex_lock(&table->mutex);
 	for (i = 0; i < MLX4_MAX_MAC_NUM - 1; i++) {
 		if (free < 0 && !table->refs[i]) {
@@ -465,6 +469,48 @@ 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);
+
+	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;
+}
+
 int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port)
 {
 	struct mlx4_cmd_mailbox *mailbox;
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index ec9350e5f21a..51c53898c35f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -280,6 +280,9 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 	 * We reserve 2 extra QPs per port for the special QPs.  The
 	 * block of special QPs must be aligned to a multiple of 8, so
 	 * round up.
+	 *
+	 * We also reserve the MSB of the 24-bit QP number to indicate
+	 * that a QP is an XRC QP.
 	 */
 	dev->caps.sqp_start =
 		ALIGN(dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW], 8);
diff --git a/drivers/net/ethernet/mellanox/mlx4/srq.c b/drivers/net/ethernet/mellanox/mlx4/srq.c
index 3b07b80a0456..a20b141dbb5c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/srq.c
@@ -40,20 +40,20 @@
 struct mlx4_srq_context {
 	__be32			state_logsize_srqn;
 	u8			logstride;
-	u8			reserved1[3];
-	u8			pg_offset;
-	u8			reserved2[3];
-	u32			reserved3;
+	u8			reserved1;
+	__be16			xrcd;
+	__be32			pg_offset_cqn;
+	u32			reserved2;
 	u8			log_page_size;
-	u8			reserved4[2];
+	u8			reserved3[2];
 	u8			mtt_base_addr_h;
 	__be32			mtt_base_addr_l;
 	__be32			pd;
 	__be16			limit_watermark;
 	__be16			wqe_cnt;
-	u16			reserved5;
+	u16			reserved4;
 	__be16			wqe_counter;
-	u32			reserved6;
+	u32			reserved5;
 	__be64			db_rec_addr;
 };
 
@@ -109,8 +109,8 @@ static int mlx4_QUERY_SRQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox
 			    MLX4_CMD_TIME_CLASS_A);
 }
 
-int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, struct mlx4_mtt *mtt,
-		   u64 db_rec, struct mlx4_srq *srq)
+int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, u32 cqn, u16 xrcd,
+		   struct mlx4_mtt *mtt, u64 db_rec, struct mlx4_srq *srq)
 {
 	struct mlx4_srq_table *srq_table = &mlx4_priv(dev)->srq_table;
 	struct mlx4_cmd_mailbox *mailbox;
@@ -148,6 +148,8 @@ int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, struct mlx4_mtt *mtt,
 	srq_context->state_logsize_srqn = cpu_to_be32((ilog2(srq->max) << 24) |
 						      srq->srqn);
 	srq_context->logstride          = srq->wqe_shift - 4;
+	srq_context->xrcd		= cpu_to_be16(xrcd);
+	srq_context->pg_offset_cqn	= cpu_to_be32(cqn & 0xffffff);
 	srq_context->log_page_size      = mtt->page_shift - MLX4_ICM_PAGE_SHIFT;
 
 	mtt_addr = mlx4_mtt_addr(dev, mtt);