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

Pull rdma updates from Jason Gunthorpe:
 "This has been a large cycle for RDMA, with several major patch series
  reworking parts of the core code.

   - Rework the so-called 'gid cache' and internal APIs to use a kref'd
     pointer to a struct instead of copying, push this upwards into the
     callers and add more stuff to the struct. The new design avoids
     some ugly races the old one suffered with. This is part of the
     namespace enablement work as the new struct is learning to be
     namespace aware.

   - Various uapi cleanups, moving more stuff to include/uapi and fixing
     some long standing bugs that have recently been discovered.

   - Driver updates for mlx5, mlx4 i40iw, rxe, cxgb4, hfi1, usnic,
     pvrdma, and hns

   - Provide max_send_sge and max_recv_sge attributes to better support
     HW where these values are asymmetric.

   - mlx5 user API 'devx' allows sending commands directly to the device
     FW, instead of trying to cram every wild and niche feature into the
     common API. Sort of like what GPU does.

   - Major write() and ioctl() API rework to cleanly support PCI device
     hot unplug and advance the ioctl conversion work

   - Sparse and compile warning cleanups

   - Add 'const' to the ib_poll_cq() signature, and permit a NULL
     'bad_wr', which is the common use case

   - Various patches to avoid high order allocations across the stack

   - SRQ support for cxgb4, hns and qedr

   - Changes to IPoIB to better follow the netdev model for working with
     struct net_device liftime"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (312 commits)
  Revert "net/smc: Replace ib_query_gid with rdma_get_gid_attr"
  RDMA/hns: Fix usage of bitmap allocation functions return values
  IB/core: Change filter function return type from int to bool
  IB/core: Update GID entries for netdevice whose mac address changes
  IB/core: Add default GIDs of the bond master netdev
  IB/core: Consider adding default GIDs of bond device
  IB/core: Delete lower netdevice default GID entries in bonding scenario
  IB/core: Avoid confusing del_netdev_default_ips
  IB/core: Add comment for change upper netevent handling
  qedr: Add user space support for SRQ
  qedr: Add support for kernel mode SRQ's
  qedr: Add wrapping generic structure for qpidr and adjust idr routines.
  IB/mlx5: Fix leaking stack memory to userspace
  Update the e-mail address of Bart Van Assche
  IB/ucm: Fix compiling ucm.c
  IB/uverbs: Do not check for device disassociation during ioctl
  IB/uverbs: Remove struct uverbs_root_spec and all supporting code
  IB/uverbs: Use uverbs_api to unmarshal ioctl commands
  IB/uverbs: Use uverbs_alloc for allocations
  IB/uverbs: Add a simple allocator to uverbs_attr_bundle
  ...

28 files changed, 1136 insertions, 618 deletions

diff --git a/include/linux/idr.h b/include/linux/idr.h
index e856f4e0ab35..3e8215b2c371 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -98,6 +98,17 @@ static inline void idr_set_cursor(struct idr *idr, unsigned int val)
  * period).
  */
 
+#define idr_lock(idr)		xa_lock(&(idr)->idr_rt)
+#define idr_unlock(idr)		xa_unlock(&(idr)->idr_rt)
+#define idr_lock_bh(idr)	xa_lock_bh(&(idr)->idr_rt)
+#define idr_unlock_bh(idr)	xa_unlock_bh(&(idr)->idr_rt)
+#define idr_lock_irq(idr)	xa_lock_irq(&(idr)->idr_rt)
+#define idr_unlock_irq(idr)	xa_unlock_irq(&(idr)->idr_rt)
+#define idr_lock_irqsave(idr, flags) \
+				xa_lock_irqsave(&(idr)->idr_rt, flags)
+#define idr_unlock_irqrestore(idr, flags) \
+				xa_unlock_irqrestore(&(idr)->idr_rt, flags)
+
 void idr_preload(gfp_t gfp_mask);
 
 int idr_alloc(struct idr *, void *ptr, int start, int end, gfp_t);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 54f385cc8811..7a452716de4b 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1235,14 +1235,11 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
-
-static inline void mlx5_rdma_netdev_free(struct net_device *netdev) {}
 #else
 struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 					  struct ib_device *ibdev,
 					  const char *name,
 					  void (*setup)(struct net_device *));
-void mlx5_rdma_netdev_free(struct net_device *netdev);
 #endif /* CONFIG_MLX5_CORE_IPOIB */
 
 struct mlx5_profile {
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 71fb503b2b52..804516e4f483 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -89,6 +89,7 @@ struct mlx5_flow_destination {
 	enum mlx5_flow_destination_type	type;
 	union {
 		u32			tir_num;
+		u32			ft_num;
 		struct mlx5_flow_table	*ft;
 		struct mlx5_fc		*counter;
 		struct {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6ead9c1a5396..f043d65b9bac 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -82,6 +82,7 @@ enum {
 
 enum {
 	MLX5_OBJ_TYPE_UCTX = 0x0004,
+	MLX5_OBJ_TYPE_UMEM = 0x0005,
 };
 
 enum {
@@ -246,12 +247,15 @@ enum {
 	MLX5_CMD_OP_DEALLOC_ENCAP_HEADER          = 0x93e,
 	MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT   = 0x940,
 	MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT = 0x941,
+	MLX5_CMD_OP_QUERY_MODIFY_HEADER_CONTEXT   = 0x942,
 	MLX5_CMD_OP_FPGA_CREATE_QP                = 0x960,
 	MLX5_CMD_OP_FPGA_MODIFY_QP                = 0x961,
 	MLX5_CMD_OP_FPGA_QUERY_QP                 = 0x962,
 	MLX5_CMD_OP_FPGA_DESTROY_QP               = 0x963,
 	MLX5_CMD_OP_FPGA_QUERY_QP_COUNTERS        = 0x964,
 	MLX5_CMD_OP_CREATE_GENERAL_OBJECT         = 0xa00,
+	MLX5_CMD_OP_MODIFY_GENERAL_OBJECT         = 0xa01,
+	MLX5_CMD_OP_QUERY_GENERAL_OBJECT          = 0xa02,
 	MLX5_CMD_OP_DESTROY_GENERAL_OBJECT        = 0xa03,
 	MLX5_CMD_OP_MAX
 };
@@ -1185,6 +1189,7 @@ enum mlx5_flow_destination_type {
 
 	MLX5_FLOW_DESTINATION_TYPE_PORT         = 0x99,
 	MLX5_FLOW_DESTINATION_TYPE_COUNTER      = 0x100,
+	MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM = 0x101,
 };
 
 struct mlx5_ifc_dest_format_struct_bits {
diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index 8712ff70995f..40b48e2133cb 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -202,6 +202,37 @@
 
 #endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
 
+/** check_shl_overflow() - Calculate a left-shifted value and check overflow
+ *
+ * @a: Value to be shifted
+ * @s: How many bits left to shift
+ * @d: Pointer to where to store the result
+ *
+ * Computes *@d = (@a << @s)
+ *
+ * Returns true if '*d' cannot hold the result or when 'a << s' doesn't
+ * make sense. Example conditions:
+ * - 'a << s' causes bits to be lost when stored in *d.
+ * - 's' is garbage (e.g. negative) or so large that the result of
+ *   'a << s' is guaranteed to be 0.
+ * - 'a' is negative.
+ * - 'a << s' sets the sign bit, if any, in '*d'.
+ *
+ * '*d' will hold the results of the attempted shift, but is not
+ * considered "safe for use" if false is returned.
+ */
+#define check_shl_overflow(a, s, d) ({					\
+	typeof(a) _a = a;						\
+	typeof(s) _s = s;						\
+	typeof(d) _d = d;						\
+	u64 _a_full = _a;						\
+	unsigned int _to_shift =					\
+		_s >= 0 && _s < 8 * sizeof(*d) ? _s : 0;		\
+	*_d = (_a_full << _to_shift);					\
+	(_to_shift != _s || *_d < 0 || _a < 0 ||			\
+		(*_d >> _to_shift) != _a);				\
+})
+
 /**
  * array_size() - Calculate size of 2-dimensional array.
  *
diff --git a/include/rdma/ib.h b/include/rdma/ib.h
index 66dbed0c146d..4f385ec54f80 100644
--- a/include/rdma/ib.h
+++ b/include/rdma/ib.h
@@ -53,12 +53,12 @@ struct ib_addr {
 #define sib_interface_id	ib_u.uib_addr64[1]
 };
 
-static inline int ib_addr_any(const struct ib_addr *a)
+static inline bool ib_addr_any(const struct ib_addr *a)
 {
 	return ((a->sib_addr64[0] | a->sib_addr64[1]) == 0);
 }
 
-static inline int ib_addr_loopback(const struct ib_addr *a)
+static inline bool ib_addr_loopback(const struct ib_addr *a)
 {
 	return ((a->sib_addr32[0] | a->sib_addr32[1] |
 		 a->sib_addr32[2] | (a->sib_addr32[3] ^ htonl(1))) == 0);
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index c2c8b1fdeead..77c7908b7d73 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -58,6 +58,7 @@
  * @bound_dev_if:	An optional device interface index.
  * @transport:		The transport type used.
  * @net:		Network namespace containing the bound_dev_if net_dev.
+ * @sgid_attr:		GID attribute to use for identified SGID
  */
 struct rdma_dev_addr {
 	unsigned char src_dev_addr[MAX_ADDR_LEN];
@@ -67,6 +68,7 @@ struct rdma_dev_addr {
 	int bound_dev_if;
 	enum rdma_transport_type transport;
 	struct net *net;
+	const struct ib_gid_attr *sgid_attr;
 	enum rdma_network_type network;
 	int hoplimit;
 };
@@ -95,7 +97,7 @@ int rdma_translate_ip(const struct sockaddr *addr,
  *   or been canceled.  A status of 0 indicates success.
  * @context: User-specified context associated with the call.
  */
-int rdma_resolve_ip(struct sockaddr *src_addr, struct sockaddr *dst_addr,
+int rdma_resolve_ip(struct sockaddr *src_addr, const struct sockaddr *dst_addr,
 		    struct rdma_dev_addr *addr, int timeout_ms,
 		    void (*callback)(int status, struct sockaddr *src_addr,
 				     struct rdma_dev_addr *addr, void *context),
@@ -107,7 +109,7 @@ void rdma_copy_addr(struct rdma_dev_addr *dev_addr,
 		    const struct net_device *dev,
 		    const unsigned char *dst_dev_addr);
 
-int rdma_addr_size(struct sockaddr *addr);
+int rdma_addr_size(const struct sockaddr *addr);
 int rdma_addr_size_in6(struct sockaddr_in6 *addr);
 int rdma_addr_size_kss(struct __kernel_sockaddr_storage *addr);
 
diff --git a/include/rdma/ib_cache.h b/include/rdma/ib_cache.h
index a5f249828115..3e11e7cc60b7 100644
--- a/include/rdma/ib_cache.h
+++ b/include/rdma/ib_cache.h
@@ -37,45 +37,23 @@
 
 #include <rdma/ib_verbs.h>
 
-/**
- * ib_get_cached_gid - Returns a cached GID table entry
- * @device: The device to query.
- * @port_num: The port number of the device to query.
- * @index: The index into the cached GID table to query.
- * @gid: The GID value found at the specified index.
- * @attr: The GID attribute found at the specified index (only in RoCE).
- *   NULL means ignore (output parameter).
- *
- * ib_get_cached_gid() fetches the specified GID table entry stored in
- * the local software cache.
- */
-int ib_get_cached_gid(struct ib_device    *device,
-		      u8                   port_num,
-		      int                  index,
-		      union ib_gid        *gid,
-		      struct ib_gid_attr  *attr);
-
-int ib_find_cached_gid(struct ib_device *device,
-		       const union ib_gid *gid,
-		       enum ib_gid_type gid_type,
-		       struct net_device *ndev,
-		       u8               *port_num,
-		       u16              *index);
-
-int ib_find_cached_gid_by_port(struct ib_device *device,
-			       const union ib_gid *gid,
-			       enum ib_gid_type gid_type,
-			       u8               port_num,
-			       struct net_device *ndev,
-			       u16              *index);
+int rdma_query_gid(struct ib_device *device, u8 port_num, int index,
+		   union ib_gid *gid);
+const struct ib_gid_attr *rdma_find_gid(struct ib_device *device,
+					const union ib_gid *gid,
+					enum ib_gid_type gid_type,
+					struct net_device *ndev);
+const struct ib_gid_attr *rdma_find_gid_by_port(struct ib_device *ib_dev,
+						const union ib_gid *gid,
+						enum ib_gid_type gid_type,
+						u8 port,
+						struct net_device *ndev);
+const struct ib_gid_attr *rdma_find_gid_by_filter(
+	struct ib_device *device, const union ib_gid *gid, u8 port_num,
+	bool (*filter)(const union ib_gid *gid, const struct ib_gid_attr *,
+		       void *),
+	void *context);
 
-int ib_find_gid_by_filter(struct ib_device *device,
-			  const union ib_gid *gid,
-			  u8 port_num,
-			  bool (*filter)(const union ib_gid *gid,
-					 const struct ib_gid_attr *,
-					 void *),
-			  void *context, u16 *index);
 /**
  * ib_get_cached_pkey - Returns a cached PKey table entry
  * @device: The device to query.
@@ -150,4 +128,33 @@ int ib_get_cached_port_state(struct ib_device *device,
 			      enum ib_port_state *port_active);
 
 bool rdma_is_zero_gid(const union ib_gid *gid);
+const struct ib_gid_attr *rdma_get_gid_attr(struct ib_device *device,
+					    u8 port_num, int index);
+void rdma_put_gid_attr(const struct ib_gid_attr *attr);
+void rdma_hold_gid_attr(const struct ib_gid_attr *attr);
+
+/*
+ * This is to be removed. It only exists to make merging rdma and smc simpler.
+ */
+static inline __deprecated int ib_query_gid(struct ib_device *device,
+					    u8 port_num, int index,
+					    union ib_gid *gid,
+					    struct ib_gid_attr *attr_out)
+{
+	const struct ib_gid_attr *attr;
+
+	memset(attr_out, 0, sizeof(*attr_out));
+	attr = rdma_get_gid_attr(device, port_num, index);
+	if (IS_ERR(attr))
+		return PTR_ERR(attr);
+
+	if (attr->ndev)
+		dev_hold(attr->ndev);
+	*attr_out = *attr;
+
+	rdma_put_gid_attr(attr);
+
+	return 0;
+}
+
 #endif /* _IB_CACHE_H */
diff --git a/include/rdma/ib_cm.h b/include/rdma/ib_cm.h
index 7979cb04f529..c10f4b5ea8ab 100644
--- a/include/rdma/ib_cm.h
+++ b/include/rdma/ib_cm.h
@@ -120,6 +120,13 @@ struct ib_cm_req_event_param {
 	struct sa_path_rec	*primary_path;
 	struct sa_path_rec	*alternate_path;
 
+	/*
+	 * SGID attribute of the primary path. Currently only
+	 * useful for RoCE. Alternate path GID attributes
+	 * are not yet supported.
+	 */
+	const struct ib_gid_attr *ppath_sgid_attr;
+
 	__be64			remote_ca_guid;
 	u32			remote_qkey;
 	u32			remote_qpn;
@@ -226,6 +233,12 @@ struct ib_cm_apr_event_param {
 struct ib_cm_sidr_req_event_param {
 	struct ib_cm_id		*listen_id;
 	__be64			service_id;
+
+	/*
+	 * SGID attribute of the request. Currently only
+	 * useful for RoCE.
+	 */
+	const struct ib_gid_attr *sgid_attr;
 	/* P_Key that was used by the GMP's BTH header */
 	u16			bth_pkey;
 	u8			port;
@@ -246,6 +259,7 @@ struct ib_cm_sidr_rep_event_param {
 	u32			qkey;
 	u32			qpn;
 	void			*info;
+	const struct ib_gid_attr *sgid_attr;
 	u8			info_len;
 };
 
@@ -297,7 +311,7 @@ struct ib_cm_event {
  * destroy the @cm_id after the callback completes.
  */
 typedef int (*ib_cm_handler)(struct ib_cm_id *cm_id,
-			     struct ib_cm_event *event);
+			     const struct ib_cm_event *event);
 
 struct ib_cm_id {
 	ib_cm_handler		cm_handler;
@@ -365,6 +379,7 @@ struct ib_cm_id *ib_cm_insert_listen(struct ib_device *device,
 struct ib_cm_req_param {
 	struct sa_path_rec	*primary_path;
 	struct sa_path_rec	*alternate_path;
+	const struct ib_gid_attr *ppath_sgid_attr;
 	__be64			service_id;
 	u32			qp_num;
 	enum ib_qp_type		qp_type;
@@ -566,6 +581,7 @@ int ib_send_cm_apr(struct ib_cm_id *cm_id,
 
 struct ib_cm_sidr_req_param {
 	struct sa_path_rec	*path;
+	const struct ib_gid_attr *sgid_attr;
 	__be64			service_id;
 	int			timeout_ms;
 	const void		*private_data;
diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h
index 2f4f1768ded4..f6ba366051c7 100644
--- a/include/rdma/ib_mad.h
+++ b/include/rdma/ib_mad.h
@@ -262,6 +262,39 @@ struct ib_class_port_info {
 	__be32			trap_qkey;
 };
 
+/* PortInfo CapabilityMask */
+enum ib_port_capability_mask_bits {
+	IB_PORT_SM = 1 << 1,
+	IB_PORT_NOTICE_SUP = 1 << 2,
+	IB_PORT_TRAP_SUP = 1 << 3,
+	IB_PORT_OPT_IPD_SUP = 1 << 4,
+	IB_PORT_AUTO_MIGR_SUP = 1 << 5,
+	IB_PORT_SL_MAP_SUP = 1 << 6,
+	IB_PORT_MKEY_NVRAM = 1 << 7,
+	IB_PORT_PKEY_NVRAM = 1 << 8,
+	IB_PORT_LED_INFO_SUP = 1 << 9,
+	IB_PORT_SM_DISABLED = 1 << 10,
+	IB_PORT_SYS_IMAGE_GUID_SUP = 1 << 11,
+	IB_PORT_PKEY_SW_EXT_PORT_TRAP_SUP = 1 << 12,
+	IB_PORT_EXTENDED_SPEEDS_SUP = 1 << 14,
+	IB_PORT_CM_SUP = 1 << 16,
+	IB_PORT_SNMP_TUNNEL_SUP = 1 << 17,
+	IB_PORT_REINIT_SUP = 1 << 18,
+	IB_PORT_DEVICE_MGMT_SUP = 1 << 19,
+	IB_PORT_VENDOR_CLASS_SUP = 1 << 20,
+	IB_PORT_DR_NOTICE_SUP = 1 << 21,
+	IB_PORT_CAP_MASK_NOTICE_SUP = 1 << 22,
+	IB_PORT_BOOT_MGMT_SUP = 1 << 23,
+	IB_PORT_LINK_LATENCY_SUP = 1 << 24,
+	IB_PORT_CLIENT_REG_SUP = 1 << 25,
+	IB_PORT_OTHER_LOCAL_CHANGES_SUP = 1 << 26,
+	IB_PORT_LINK_SPEED_WIDTH_TABLE_SUP = 1 << 27,
+	IB_PORT_VENDOR_SPECIFIC_MADS_TABLE_SUP = 1 << 28,
+	IB_PORT_MCAST_PKEY_TRAP_SUPPRESSION_SUP = 1 << 29,
+	IB_PORT_MCAST_FDB_TOP_SUP = 1 << 30,
+	IB_PORT_HIERARCHY_INFO_SUP = 1ULL << 31,
+};
+
 #define OPA_CLASS_PORT_INFO_PR_SUPPORT BIT(26)
 
 struct opa_class_port_info {
diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h
index bacb144f7780..b6ddf2a1b9d8 100644
--- a/include/rdma/ib_sa.h
+++ b/include/rdma/ib_sa.h
@@ -172,12 +172,7 @@ struct sa_path_rec_ib {
  */
 struct sa_path_rec_roce {
 	bool	route_resolved;
-	u8           dmac[ETH_ALEN];
-	/* ignored in IB */
-	int	     ifindex;
-	/* ignored in IB */
-	struct net  *net;
-
+	u8	dmac[ETH_ALEN];
 };
 
 struct sa_path_rec_opa {
@@ -556,13 +551,10 @@ int ib_init_ah_from_mcmember(struct ib_device *device, u8 port_num,
 			     enum ib_gid_type gid_type,
 			     struct rdma_ah_attr *ah_attr);
 
-/**
- * ib_init_ah_attr_from_path - Initialize address handle attributes based on
- *   an SA path record.
- */
 int ib_init_ah_attr_from_path(struct ib_device *device, u8 port_num,
 			      struct sa_path_rec *rec,
-			      struct rdma_ah_attr *ah_attr);
+			      struct rdma_ah_attr *ah_attr,
+			      const struct ib_gid_attr *sgid_attr);
 
 /**
  * ib_sa_pack_path - Conert a path record from struct ib_sa_path_rec
@@ -667,45 +659,10 @@ static inline void sa_path_set_dmac_zero(struct sa_path_rec *rec)
 		eth_zero_addr(rec->roce.dmac);
 }
 
-static inline void sa_path_set_ifindex(struct sa_path_rec *rec, int ifindex)
-{
-	if (sa_path_is_roce(rec))
-		rec->roce.ifindex = ifindex;
-}
-
-static inline void sa_path_set_ndev(struct sa_path_rec *rec, struct net *net)
-{
-	if (sa_path_is_roce(rec))
-		rec->roce.net = net;
-}
-
 static inline u8 *sa_path_get_dmac(struct sa_path_rec *rec)
 {
 	if (sa_path_is_roce(rec))
 		return rec->roce.dmac;
 	return NULL;
 }
-
-static inline int sa_path_get_ifindex(struct sa_path_rec *rec)
-{
-	if (sa_path_is_roce(rec))
-		return rec->roce.ifindex;
-	return 0;
-}
-
-static inline struct net *sa_path_get_ndev(struct sa_path_rec *rec)
-{
-	if (sa_path_is_roce(rec))
-		return rec->roce.net;
-	return NULL;
-}
-
-static inline struct net_device *ib_get_ndev_from_path(struct sa_path_rec *rec)
-{
-	return sa_path_get_ndev(rec) ?
-		dev_get_by_index(sa_path_get_ndev(rec),
-				 sa_path_get_ifindex(rec))
-		: NULL;
-}
-
 #endif /* IB_SA_H */
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 6c003995347a..e950c2a68f06 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -94,6 +94,7 @@ enum ib_gid_type {
 struct ib_gid_attr {
 	struct net_device	*ndev;
 	struct ib_device	*device;
+	union ib_gid		gid;
 	enum ib_gid_type	gid_type;
 	u16			index;
 	u8			port_num;
@@ -148,13 +149,13 @@ static inline enum ib_gid_type ib_network_to_gid_type(enum rdma_network_type net
 	return IB_GID_TYPE_IB;
 }
 
-static inline enum rdma_network_type ib_gid_to_network_type(enum ib_gid_type gid_type,
-							    union ib_gid *gid)
+static inline enum rdma_network_type
+rdma_gid_attr_network_type(const struct ib_gid_attr *attr)
 {
-	if (gid_type == IB_GID_TYPE_IB)
+	if (attr->gid_type == IB_GID_TYPE_IB)
 		return RDMA_NETWORK_IB;
 
-	if (ipv6_addr_v4mapped((struct in6_addr *)gid))
+	if (ipv6_addr_v4mapped((struct in6_addr *)&attr->gid))
 		return RDMA_NETWORK_IPV4;
 	else
 		return RDMA_NETWORK_IPV6;
@@ -344,7 +345,8 @@ struct ib_device_attr {
 	int			max_qp;
 	int			max_qp_wr;
 	u64			device_cap_flags;
-	int			max_sge;
+	int			max_send_sge;
+	int			max_recv_sge;
 	int			max_sge_rd;
 	int			max_cq;
 	int			max_cqe;
@@ -430,33 +432,6 @@ enum ib_port_state {
 	IB_PORT_ACTIVE_DEFER	= 5
 };
 
-enum ib_port_cap_flags {
-	IB_PORT_SM				= 1 <<  1,
-	IB_PORT_NOTICE_SUP			= 1 <<  2,
-	IB_PORT_TRAP_SUP			= 1 <<  3,
-	IB_PORT_OPT_IPD_SUP                     = 1 <<  4,
-	IB_PORT_AUTO_MIGR_SUP			= 1 <<  5,
-	IB_PORT_SL_MAP_SUP			= 1 <<  6,
-	IB_PORT_MKEY_NVRAM			= 1 <<  7,
-	IB_PORT_PKEY_NVRAM			= 1 <<  8,
-	IB_PORT_LED_INFO_SUP			= 1 <<  9,
-	IB_PORT_SM_DISABLED			= 1 << 10,
-	IB_PORT_SYS_IMAGE_GUID_SUP		= 1 << 11,
-	IB_PORT_PKEY_SW_EXT_PORT_TRAP_SUP	= 1 << 12,
-	IB_PORT_EXTENDED_SPEEDS_SUP             = 1 << 14,
-	IB_PORT_CM_SUP				= 1 << 16,
-	IB_PORT_SNMP_TUNNEL_SUP			= 1 << 17,
-	IB_PORT_REINIT_SUP			= 1 << 18,
-	IB_PORT_DEVICE_MGMT_SUP			= 1 << 19,
-	IB_PORT_VENDOR_CLASS_SUP		= 1 << 20,
-	IB_PORT_DR_NOTICE_SUP			= 1 << 21,
-	IB_PORT_CAP_MASK_NOTICE_SUP		= 1 << 22,
-	IB_PORT_BOOT_MGMT_SUP			= 1 << 23,
-	IB_PORT_LINK_LATENCY_SUP		= 1 << 24,
-	IB_PORT_CLIENT_REG_SUP			= 1 << 25,
-	IB_PORT_IP_BASED_GIDS			= 1 << 26,
-};
-
 enum ib_port_width {
 	IB_WIDTH_1X	= 1,
 	IB_WIDTH_4X	= 2,
@@ -554,6 +529,7 @@ static inline struct rdma_hw_stats *rdma_alloc_hw_stats_struct(
 #define RDMA_CORE_CAP_AF_IB             0x00001000
 #define RDMA_CORE_CAP_ETH_AH            0x00002000
 #define RDMA_CORE_CAP_OPA_AH            0x00004000
+#define RDMA_CORE_CAP_IB_GRH_REQUIRED   0x00008000
 
 /* Protocol                             0xFFF00000 */
 #define RDMA_CORE_CAP_PROT_IB           0x00100000
@@ -563,6 +539,10 @@ static inline struct rdma_hw_stats *rdma_alloc_hw_stats_struct(
 #define RDMA_CORE_CAP_PROT_RAW_PACKET   0x01000000
 #define RDMA_CORE_CAP_PROT_USNIC        0x02000000
 
+#define RDMA_CORE_PORT_IB_GRH_REQUIRED (RDMA_CORE_CAP_IB_GRH_REQUIRED \
+					| RDMA_CORE_CAP_PROT_ROCE     \
+					| RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP)
+
 #define RDMA_CORE_PORT_IBA_IB          (RDMA_CORE_CAP_PROT_IB  \
 					| RDMA_CORE_CAP_IB_MAD \
 					| RDMA_CORE_CAP_IB_SMI \
@@ -595,6 +575,8 @@ struct ib_port_attr {
 	enum ib_mtu		max_mtu;
 	enum ib_mtu		active_mtu;
 	int			gid_tbl_len;
+	unsigned int		ip_gids:1;
+	/* This is the value from PortInfo CapabilityMask, defined by IBA */
 	u32			port_cap_flags;
 	u32			max_msg_sz;
 	u32			bad_pkey_cntr;
@@ -610,7 +592,6 @@ struct ib_port_attr {
 	u8			active_width;
 	u8			active_speed;
 	u8                      phys_state;
-	bool			grh_required;
 };
 
 enum ib_device_modify_flags {
@@ -689,6 +670,7 @@ struct ib_event_handler {
 	} while (0)
 
 struct ib_global_route {
+	const struct ib_gid_attr *sgid_attr;
 	union ib_gid	dgid;
 	u32		flow_label;
 	u8		sgid_index;
@@ -1370,7 +1352,7 @@ struct ib_rdma_wr {
 	u32			rkey;
 };
 
-static inline struct ib_rdma_wr *rdma_wr(struct ib_send_wr *wr)
+static inline const struct ib_rdma_wr *rdma_wr(const struct ib_send_wr *wr)
 {
 	return container_of(wr, struct ib_rdma_wr, wr);
 }
@@ -1385,7 +1367,7 @@ struct ib_atomic_wr {
 	u32			rkey;
 };
 
-static inline struct ib_atomic_wr *atomic_wr(struct ib_send_wr *wr)
+static inline const struct ib_atomic_wr *atomic_wr(const struct ib_send_wr *wr)
 {
 	return container_of(wr, struct ib_atomic_wr, wr);
 }
@@ -1402,7 +1384,7 @@ struct ib_ud_wr {
 	u8			port_num;   /* valid for DR SMPs on switch only */
 };
 
-static inline struct ib_ud_wr *ud_wr(struct ib_send_wr *wr)
+static inline const struct ib_ud_wr *ud_wr(const struct ib_send_wr *wr)
 {
 	return container_of(wr, struct ib_ud_wr, wr);
 }
@@ -1414,7 +1396,7 @@ struct ib_reg_wr {
 	int			access;
 };
 
-static inline struct ib_reg_wr *reg_wr(struct ib_send_wr *wr)
+static inline const struct ib_reg_wr *reg_wr(const struct ib_send_wr *wr)
 {
 	return container_of(wr, struct ib_reg_wr, wr);
 }
@@ -1427,7 +1409,8 @@ struct ib_sig_handover_wr {
 	struct ib_sge	       *prot;
 };
 
-static inline struct ib_sig_handover_wr *sig_handover_wr(struct ib_send_wr *wr)
+static inline const struct ib_sig_handover_wr *
+sig_handover_wr(const struct ib_send_wr *wr)
 {
 	return container_of(wr, struct ib_sig_handover_wr, wr);
 }
@@ -1443,14 +1426,16 @@ struct ib_recv_wr {
 };
 
 enum ib_access_flags {
-	IB_ACCESS_LOCAL_WRITE	= 1,
-	IB_ACCESS_REMOTE_WRITE	= (1<<1),
-	IB_ACCESS_REMOTE_READ	= (1<<2),
-	IB_ACCESS_REMOTE_ATOMIC	= (1<<3),
-	IB_ACCESS_MW_BIND	= (1<<4),
-	IB_ZERO_BASED		= (1<<5),
-	IB_ACCESS_ON_DEMAND     = (1<<6),
-	IB_ACCESS_HUGETLB	= (1<<7),
+	IB_ACCESS_LOCAL_WRITE = IB_UVERBS_ACCESS_LOCAL_WRITE,
+	IB_ACCESS_REMOTE_WRITE = IB_UVERBS_ACCESS_REMOTE_WRITE,
+	IB_ACCESS_REMOTE_READ = IB_UVERBS_ACCESS_REMOTE_READ,
+	IB_ACCESS_REMOTE_ATOMIC = IB_UVERBS_ACCESS_REMOTE_ATOMIC,
+	IB_ACCESS_MW_BIND = IB_UVERBS_ACCESS_MW_BIND,
+	IB_ZERO_BASED = IB_UVERBS_ACCESS_ZERO_BASED,
+	IB_ACCESS_ON_DEMAND = IB_UVERBS_ACCESS_ON_DEMAND,
+	IB_ACCESS_HUGETLB = IB_UVERBS_ACCESS_HUGETLB,
+
+	IB_ACCESS_SUPPORTED = ((IB_ACCESS_HUGETLB << 1) - 1)
 };
 
 /*
@@ -1473,14 +1458,17 @@ struct ib_fmr_attr {
 struct ib_umem;
 
 enum rdma_remove_reason {
-	/* Userspace requested uobject deletion. Call could fail */
+	/*
+	 * Userspace requested uobject deletion or initial try
+	 * to remove uobject via cleanup. Call could fail
+	 */
 	RDMA_REMOVE_DESTROY,
 	/* Context deletion. This call should delete the actual object itself */
 	RDMA_REMOVE_CLOSE,
 	/* Driver is being hot-unplugged. This call should delete the actual object itself */
 	RDMA_REMOVE_DRIVER_REMOVE,
-	/* Context is being cleaned-up, but commit was just completed */
-	RDMA_REMOVE_DURING_CLEANUP,
+	/* uobj is being cleaned-up before being committed */
+	RDMA_REMOVE_ABORT,
 };
 
 struct ib_rdmacg_object {
@@ -1492,14 +1480,14 @@ struct ib_rdmacg_object {
 struct ib_ucontext {
 	struct ib_device       *device;
 	struct ib_uverbs_file  *ufile;
+	/*
+	 * 'closing' can be read by the driver only during a destroy callback,
+	 * it is set when we are closing the file descriptor and indicates
+	 * that mm_sem may be locked.
+	 */
 	int			closing;
 
-	/* locking the uobjects_list */
-	struct mutex		uobjects_lock;
-	struct list_head	uobjects;
-	/* protects cleanup process from other actions */
-	struct rw_semaphore	cleanup_rwsem;
-	enum rdma_remove_reason cleanup_reason;
+	bool cleanup_retryable;
 
 	struct pid             *tgid;
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
@@ -1524,6 +1512,9 @@ struct ib_ucontext {
 
 struct ib_uobject {
 	u64			user_handle;	/* handle given to us by userspace */
+	/* ufile & ucontext owning this object */
+	struct ib_uverbs_file  *ufile;
+	/* FIXME, save memory: ufile->context == context */
 	struct ib_ucontext     *context;	/* associated user context */
 	void		       *object;		/* containing object */
 	struct list_head	list;		/* link to context's list */
@@ -1533,13 +1524,7 @@ struct ib_uobject {
 	atomic_t		usecnt;		/* protects exclusive access */
 	struct rcu_head		rcu;		/* kfree_rcu() overhead */
 
-	const struct uverbs_obj_type *type;
-};
-
-struct ib_uobject_file {
-	struct ib_uobject	uobj;
-	/* ufile contains the lock between context release and file close */
-	struct ib_uverbs_file	*ufile;
+	const struct uverbs_api_object *uapi_object;
 };
 
 struct ib_udata {
@@ -1578,6 +1563,7 @@ struct ib_ah {
 	struct ib_device	*device;
 	struct ib_pd		*pd;
 	struct ib_uobject	*uobject;
+	const struct ib_gid_attr *sgid_attr;
 	enum rdma_ah_attr_type	type;
 };
 
@@ -1776,6 +1762,9 @@ struct ib_qp {
 	struct ib_uobject      *uobject;
 	void                  (*event_handler)(struct ib_event *, void *);
 	void		       *qp_context;
+	/* sgid_attrs associated with the AV's */
+	const struct ib_gid_attr *av_sgid_attr;
+	const struct ib_gid_attr *alt_path_sgid_attr;