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

Pull infiniband/rdma updates from Roland Dreier:
 - Re-enable flow steering verbs with new improved userspace ABI
 - Fixes for slow connection due to GID lookup scalability
 - IPoIB fixes
 - Many fixes to HW drivers including mlx4, mlx5, ocrdma and qib
 - Further improvements to SRP error handling
 - Add new transport type for Cisco usNIC

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (66 commits)
  IB/core: Re-enable create_flow/destroy_flow uverbs
  IB/core: extended command: an improved infrastructure for uverbs commands
  IB/core: Remove ib_uverbs_flow_spec structure from userspace
  IB/core: Use a common header for uverbs flow_specs
  IB/core: Make uverbs flow structure use names like verbs ones
  IB/core: Rename 'flow' structs to match other uverbs structs
  IB/core: clarify overflow/underflow checks on ib_create/destroy_flow
  IB/ucma: Convert use of typedef ctl_table to struct ctl_table
  IB/cm: Convert to using idr_alloc_cyclic()
  IB/mlx5: Fix page shift in create CQ for userspace
  IB/mlx4: Fix device max capabilities check
  IB/mlx5: Fix list_del of empty list
  IB/mlx5: Remove dead code
  IB/core: Encorce MR access rights rules on kernel consumers
  IB/mlx4: Fix endless loop in resize CQ
  RDMA/cma: Remove unused argument and minor dead code
  RDMA/ucma: Discard events for IDs not yet claimed by user space
  IB/core: Add Cisco usNIC rdma node and transport types
  RDMA/nes: Remove self-assignment from nes_query_qp()
  IB/srp: Report receive errors correctly
  ...

5 files changed, 179 insertions, 50 deletions

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 5eb4e31af22..da78875807f 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -230,6 +230,15 @@ enum {
 	MLX5_MAX_PAGE_SHIFT		= 31
 };
 
+enum {
+	MLX5_ADAPTER_PAGE_SHIFT		= 12
+};
+
+enum {
+	MLX5_CAP_OFF_DCT		= 41,
+	MLX5_CAP_OFF_CMDIF_CSUM		= 46,
+};
+
 struct mlx5_inbox_hdr {
 	__be16		opcode;
 	u8		rsvd[4];
@@ -319,9 +328,9 @@ struct mlx5_hca_cap {
 	u8	rsvd25[42];
 	__be16  log_uar_page_sz;
 	u8	rsvd26[28];
-	u8	log_msx_atomic_size_qp;
+	u8	log_max_atomic_size_qp;
 	u8	rsvd27[2];
-	u8	log_msx_atomic_size_dc;
+	u8	log_max_atomic_size_dc;
 	u8	rsvd28[76];
 };
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 6b8c496572c..554548cd3dd 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -483,6 +483,7 @@ struct mlx5_priv {
 	struct rb_root		page_root;
 	int			fw_pages;
 	int			reg_pages;
+	struct list_head	free_list;
 
 	struct mlx5_core_health health;
 
@@ -557,9 +558,11 @@ typedef void (*mlx5_cmd_cbk_t)(int status, void *context);
 struct mlx5_cmd_work_ent {
 	struct mlx5_cmd_msg    *in;
 	struct mlx5_cmd_msg    *out;
+	void		       *uout;
+	int			uout_size;
 	mlx5_cmd_cbk_t		callback;
 	void		       *context;
-	int idx;
+	int			idx;
 	struct completion	done;
 	struct mlx5_cmd        *cmd;
 	struct work_struct	work;
@@ -570,6 +573,7 @@ struct mlx5_cmd_work_ent {
 	u8			token;
 	struct timespec		ts1;
 	struct timespec		ts2;
+	u16			op;
 };
 
 struct mlx5_pas {
@@ -653,6 +657,9 @@ void mlx5_cmd_use_polling(struct mlx5_core_dev *dev);
 int mlx5_cmd_status_to_err(struct mlx5_outbox_hdr *hdr);
 int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 		  int out_size);
+int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size,
+		     void *out, int out_size, mlx5_cmd_cbk_t callback,
+		     void *context);
 int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn);
 int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn);
 int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari);
@@ -676,7 +683,9 @@ int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 		      u16 lwm, int is_srq);
 int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
-			  struct mlx5_create_mkey_mbox_in *in, int inlen);
+			  struct mlx5_create_mkey_mbox_in *in, int inlen,
+			  mlx5_cmd_cbk_t callback, void *context,
+			  struct mlx5_create_mkey_mbox_out *out);
 int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr);
 int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 			 struct mlx5_query_mkey_mbox_out *out, int outlen);
@@ -745,6 +754,11 @@ static inline u32 mlx5_idx_to_mkey(u32 mkey_idx)
 	return mkey_idx << 8;
 }
 
+static inline u8 mlx5_mkey_variant(u32 mkey)
+{
+	return mkey & 0xff;
+}
+
 enum {
 	MLX5_PROF_MASK_QP_SIZE		= (u64)1 << 0,
 	MLX5_PROF_MASK_MR_CACHE		= (u64)1 << 1,
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index e393171e2fa..979874c627e 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -67,12 +67,14 @@ enum rdma_node_type {
 	RDMA_NODE_IB_CA 	= 1,
 	RDMA_NODE_IB_SWITCH,
 	RDMA_NODE_IB_ROUTER,
-	RDMA_NODE_RNIC
+	RDMA_NODE_RNIC,
+	RDMA_NODE_USNIC,
 };
 
 enum rdma_transport_type {
 	RDMA_TRANSPORT_IB,
-	RDMA_TRANSPORT_IWARP
+	RDMA_TRANSPORT_IWARP,
+	RDMA_TRANSPORT_USNIC
 };
 
 enum rdma_transport_type
@@ -1436,6 +1438,7 @@ struct ib_device {
 
 	int			     uverbs_abi_ver;
 	u64			     uverbs_cmd_mask;
+	u64			     uverbs_ex_cmd_mask;
 
 	char			     node_desc[64];
 	__be64			     node_guid;
@@ -2384,4 +2387,17 @@ struct ib_flow *ib_create_flow(struct ib_qp *qp,
 			       struct ib_flow_attr *flow_attr, int domain);
 int ib_destroy_flow(struct ib_flow *flow_id);
 
+static inline int ib_check_mr_access(int flags)
+{
+	/*
+	 * Local write permission is required if remote write or
+	 * remote atomic permission is also requested.
+	 */
+	if (flags & (IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_REMOTE_WRITE) &&
+	    !(flags & IB_ACCESS_LOCAL_WRITE))
+		return -EINVAL;
+
+	return 0;
+}
+
 #endif /* IB_VERBS_H */
diff --git a/include/scsi/scsi_transport_srp.h b/include/scsi/scsi_transport_srp.h
index ff0f04ac91a..4ebf6913b7b 100644
--- a/include/scsi/scsi_transport_srp.h
+++ b/include/scsi/scsi_transport_srp.h
@@ -13,6 +13,27 @@ struct srp_rport_identifiers {
 	u8 roles;
 };
 
+/**
+ * enum srp_rport_state - SRP transport layer state
+ * @SRP_RPORT_RUNNING:   Transport layer operational.
+ * @SRP_RPORT_BLOCKED:   Transport layer not operational; fast I/O fail timer
+ *                       is running and I/O has been blocked.
+ * @SRP_RPORT_FAIL_FAST: Fast I/O fail timer has expired; fail I/O fast.
+ * @SRP_RPORT_LOST:      Device loss timer has expired; port is being removed.
+ */
+enum srp_rport_state {
+	SRP_RPORT_RUNNING,
+	SRP_RPORT_BLOCKED,
+	SRP_RPORT_FAIL_FAST,
+	SRP_RPORT_LOST,
+};
+
+/**
+ * struct srp_rport
+ * @lld_data: LLD private data.
+ * @mutex:    Protects against concurrent rport reconnect / fast_io_fail /
+ *   dev_loss_tmo activity.
+ */
 struct srp_rport {
 	/* for initiator and target drivers */
 
@@ -23,11 +44,43 @@ struct srp_rport {
 
 	/* for initiator drivers */
 
-	void *lld_data;	/* LLD private data */
+	void			*lld_data;
+
+	struct mutex		mutex;
+	enum srp_rport_state	state;
+	bool			deleted;
+	int			reconnect_delay;
+	int			failed_reconnects;
+	struct delayed_work	reconnect_work;
+	int			fast_io_fail_tmo;
+	int			dev_loss_tmo;
+	struct delayed_work	fast_io_fail_work;
+	struct delayed_work	dev_loss_work;
 };
 
+/**
+ * struct srp_function_template
+ * @has_rport_state: Whether or not to create the state, fast_io_fail_tmo and
+ *     dev_loss_tmo sysfs attribute for an rport.
+ * @reset_timer_if_blocked: Whether or srp_timed_out() should reset the command
+ *     timer if the device on which it has been queued is blocked.
+ * @reconnect_delay: If not NULL, points to the default reconnect_delay value.
+ * @fast_io_fail_tmo: If not NULL, points to the default fast_io_fail_tmo value.
+ * @dev_loss_tmo: If not NULL, points to the default dev_loss_tmo value.
+ * @reconnect: Callback function for reconnecting to the target. See also
+ *     srp_reconnect_rport().
+ * @terminate_rport_io: Callback function for terminating all outstanding I/O
+ *     requests for an rport.
+ */
 struct srp_function_template {
 	/* for initiator drivers */
+	bool has_rport_state;
+	bool reset_timer_if_blocked;
+	int *reconnect_delay;
+	int *fast_io_fail_tmo;
+	int *dev_loss_tmo;
+	int (*reconnect)(struct srp_rport *rport);
+	void (*terminate_rport_io)(struct srp_rport *rport);
 	void (*rport_delete)(struct srp_rport *rport);
 	/* for target drivers */
 	int (* tsk_mgmt_response)(struct Scsi_Host *, u64, u64, int);
@@ -38,10 +91,36 @@ extern struct scsi_transport_template *
 srp_attach_transport(struct srp_function_template *);
 extern void srp_release_transport(struct scsi_transport_template *);
 
+extern void srp_rport_get(struct srp_rport *rport);
+extern void srp_rport_put(struct srp_rport *rport);
 extern struct srp_rport *srp_rport_add(struct Scsi_Host *,
 				       struct srp_rport_identifiers *);
 extern void srp_rport_del(struct srp_rport *);
-
+extern int srp_tmo_valid(int reconnect_delay, int fast_io_fail_tmo,
+			 int dev_loss_tmo);
+extern int srp_reconnect_rport(struct srp_rport *rport);
+extern void srp_start_tl_fail_timers(struct srp_rport *rport);
 extern void srp_remove_host(struct Scsi_Host *);
 
+/**
+ * srp_chkready() - evaluate the transport layer state before I/O
+ *
+ * Returns a SCSI result code that can be returned by the LLD queuecommand()
+ * implementation. The role of this function is similar to that of
+ * fc_remote_port_chkready().
+ */
+static inline int srp_chkready(struct srp_rport *rport)
+{
+	switch (rport->state) {
+	case SRP_RPORT_RUNNING:
+	case SRP_RPORT_BLOCKED:
+	default:
+		return 0;
+	case SRP_RPORT_FAIL_FAST:
+		return DID_TRANSPORT_FAILFAST << 16;
+	case SRP_RPORT_LOST:
+		return DID_NO_CONNECT << 16;
+	}
+}
+
 #endif
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index e3ddd86c90a..cbfdd4ca951 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -87,10 +87,11 @@ enum {
 	IB_USER_VERBS_CMD_CLOSE_XRCD,
 	IB_USER_VERBS_CMD_CREATE_XSRQ,
 	IB_USER_VERBS_CMD_OPEN_QP,
-#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-	IB_USER_VERBS_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD,
-	IB_USER_VERBS_CMD_DESTROY_FLOW
-#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
+};
+
+enum {
+	IB_USER_VERBS_EX_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD,
+	IB_USER_VERBS_EX_CMD_DESTROY_FLOW
 };
 
 /*
@@ -122,22 +123,24 @@ struct ib_uverbs_comp_event_desc {
  * the rest of the command struct based on these value.
  */
 
+#define IB_USER_VERBS_CMD_COMMAND_MASK 0xff
+#define IB_USER_VERBS_CMD_FLAGS_MASK 0xff000000u
+#define IB_USER_VERBS_CMD_FLAGS_SHIFT 24
+
+#define IB_USER_VERBS_CMD_FLAG_EXTENDED 0x80
+
 struct ib_uverbs_cmd_hdr {
 	__u32 command;
 	__u16 in_words;
 	__u16 out_words;
 };
 
-#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-struct ib_uverbs_cmd_hdr_ex {
-	__u32 command;
-	__u16 in_words;
-	__u16 out_words;
+struct ib_uverbs_ex_cmd_hdr {
+	__u64 response;
 	__u16 provider_in_words;
 	__u16 provider_out_words;
 	__u32 cmd_hdr_reserved;
 };
-#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 
 struct ib_uverbs_get_context {
 	__u64 response;
@@ -700,62 +703,71 @@ struct ib_uverbs_detach_mcast {
 	__u64 driver_data[0];
 };
 
-#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-struct ib_kern_eth_filter {
+struct ib_uverbs_flow_spec_hdr {
+	__u32 type;
+	__u16 size;
+	__u16 reserved;
+	/* followed by flow_spec */
+	__u64 flow_spec_data[0];
+};
+
+struct ib_uverbs_flow_eth_filter {
 	__u8  dst_mac[6];
 	__u8  src_mac[6];
 	__be16 ether_type;
 	__be16 vlan_tag;
 };
 
-struct ib_kern_spec_eth {
-	__u32  type;
-	__u16  size;
-	__u16  reserved;
-	struct ib_kern_eth_filter val;
-	struct ib_kern_eth_filter mask;
+struct ib_uverbs_flow_spec_eth {
+	union {
+		struct ib_uverbs_flow_spec_hdr hdr;
+		struct {
+			__u32 type;
+			__u16 size;
+			__u16 reserved;
+		};
+	};
+	struct ib_uverbs_flow_eth_filter val;
+	struct ib_uverbs_flow_eth_filter mask;
 };
 
-struct ib_kern_ipv4_filter {
+struct ib_uverbs_flow_ipv4_filter {
 	__be32 src_ip;
 	__be32 dst_ip;
 };
 
-struct ib_kern_spec_ipv4 {
-	__u32  type;
-	__u16  size;
-	__u16  reserved;
-	struct ib_kern_ipv4_filter val;
-	struct ib_kern_ipv4_filter mask;
+struct ib_uverbs_flow_spec_ipv4 {
+	union {
+		struct ib_uverbs_flow_spec_hdr hdr;
+		struct {
+			__u32 type;
+			__u16 size;
+			__u16 reserved;
+		};
+	};
+	struct ib_uverbs_flow_ipv4_filter val;
+	struct ib_uverbs_flow_ipv4_filter mask;
 };
 
-struct ib_kern_tcp_udp_filter {
+struct ib_uverbs_flow_tcp_udp_filter {
 	__be16 dst_port;
 	__be16 src_port;
 };
 
-struct ib_kern_spec_tcp_udp {
-	__u32  type;
-	__u16  size;
-	__u16  reserved;
-	struct ib_kern_tcp_udp_filter val;
-	struct ib_kern_tcp_udp_filter mask;
-};
-
-struct ib_kern_spec {
+struct ib_uverbs_flow_spec_tcp_udp {
 	union {
+		struct ib_uverbs_flow_spec_hdr hdr;
 		struct {
 			__u32 type;
 			__u16 size;
 			__u16 reserved;
 		};
-		struct ib_kern_spec_eth	    eth;
-		struct ib_kern_spec_ipv4    ipv4;
-		struct ib_kern_spec_tcp_udp tcp_udp;
 	};
+	struct ib_uverbs_flow_tcp_udp_filter val;
+	struct ib_uverbs_flow_tcp_udp_filter mask;
 };
 
-struct ib_kern_flow_attr {
+struct ib_uverbs_flow_attr {
 	__u32 type;
 	__u16 size;
 	__u16 priority;
@@ -767,13 +779,13 @@ struct ib_kern_flow_attr {
 	 * struct ib_flow_spec_xxx
 	 * struct ib_flow_spec_yyy
 	 */
+	struct ib_uverbs_flow_spec_hdr flow_specs[0];
 };
 
 struct ib_uverbs_create_flow  {
 	__u32 comp_mask;
-	__u64 response;
 	__u32 qp_handle;
-	struct ib_kern_flow_attr flow_attr;
+	struct ib_uverbs_flow_attr flow_attr;
 };
 
 struct ib_uverbs_create_flow_resp {
@@ -785,7 +797,6 @@ struct ib_uverbs_destroy_flow  {
 	__u32 comp_mask;
 	__u32 flow_handle;
 };
-#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 
 struct ib_uverbs_create_srq {
 	__u64 response;