Merge branch 'linus' into locking/core, to fix up conflicts

 Conflicts:
	mm/page_alloc.c

Signed-off-by: Ingo Molnar <mingo@kernel.org>

13 files changed, 871 insertions, 89 deletions

diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index b73a14edc85e..ec5008cf5d51 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -172,7 +172,8 @@ static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid)
 				       (struct in6_addr *)gid);
 		break;
 	case AF_INET6:
-		memcpy(gid->raw, &((struct sockaddr_in6 *)addr)->sin6_addr, 16);
+		*(struct in6_addr *)&gid->raw =
+			((struct sockaddr_in6 *)addr)->sin6_addr;
 		break;
 	default:
 		return -EINVAL;
@@ -304,7 +305,13 @@ static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac)
 
 static inline int rdma_is_multicast_addr(struct in6_addr *addr)
 {
-	return addr->s6_addr[0] == 0xff;
+	u32 ipv4_addr;
+
+	if (addr->s6_addr[0] == 0xff)
+		return 1;
+
+	memcpy(&ipv4_addr, addr->s6_addr + 12, 4);
+	return (ipv6_addr_v4mapped(addr) && ipv4_is_multicast(ipv4_addr));
 }
 
 static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac)
diff --git a/include/rdma/ib_hdrs.h b/include/rdma/ib_hdrs.h
index 5519f31f043a..c124d515f7d5 100644
--- a/include/rdma/ib_hdrs.h
+++ b/include/rdma/ib_hdrs.h
@@ -193,8 +193,12 @@ static inline void put_ib_ateth_compare(u64 val, struct ib_atomic_eth *ateth)
 #define IB_LNH_MASK		3
 #define IB_SC_MASK		0xf
 #define IB_SC_SHIFT		12
+#define IB_SC5_MASK		0x10
 #define IB_SL_MASK		0xf
 #define IB_SL_SHIFT		4
+#define IB_SL_SHIFT		4
+#define IB_LVER_MASK	0xf
+#define IB_LVER_SHIFT	8
 
 static inline u8 ib_get_lnh(struct ib_header *hdr)
 {
@@ -206,6 +210,11 @@ static inline u8 ib_get_sc(struct ib_header *hdr)
 	return ((be16_to_cpu(hdr->lrh[0]) >> IB_SC_SHIFT) & IB_SC_MASK);
 }
 
+static inline bool ib_is_sc5(u16 sc5)
+{
+	return !!(sc5 & IB_SC5_MASK);
+}
+
 static inline u8 ib_get_sl(struct ib_header *hdr)
 {
 	return ((be16_to_cpu(hdr->lrh[0]) >> IB_SL_SHIFT) & IB_SL_MASK);
@@ -221,6 +230,27 @@ static inline u16 ib_get_slid(struct ib_header *hdr)
 	return (be16_to_cpu(hdr->lrh[3]));
 }
 
+static inline u8 ib_get_lver(struct ib_header *hdr)
+{
+	return (u8)((be16_to_cpu(hdr->lrh[0]) >> IB_LVER_SHIFT) &
+		   IB_LVER_MASK);
+}
+
+static inline u16 ib_get_len(struct ib_header *hdr)
+{
+	return (u16)(be16_to_cpu(hdr->lrh[2]));
+}
+
+static inline u32 ib_get_qkey(struct ib_other_headers *ohdr)
+{
+	return be32_to_cpu(ohdr->u.ud.deth[0]);
+}
+
+static inline u32 ib_get_sqpn(struct ib_other_headers *ohdr)
+{
+	return ((be32_to_cpu(ohdr->u.ud.deth[1])) & IB_QPN_MASK);
+}
+
 /*
  * BTH
  */
@@ -229,6 +259,14 @@ static inline u16 ib_get_slid(struct ib_header *hdr)
 #define IB_BTH_PAD_MASK	3
 #define IB_BTH_PKEY_MASK	0xffff
 #define IB_BTH_PAD_SHIFT	20
+#define IB_BTH_A_MASK		1
+#define IB_BTH_A_SHIFT		31
+#define IB_BTH_M_MASK		1
+#define IB_BTH_M_SHIFT		22
+#define IB_BTH_SE_MASK		1
+#define IB_BTH_SE_SHIFT	23
+#define IB_BTH_TVER_MASK	0xf
+#define IB_BTH_TVER_SHIFT	16
 
 static inline u8 ib_bth_get_pad(struct ib_other_headers *ohdr)
 {
@@ -247,4 +285,50 @@ static inline u8 ib_bth_get_opcode(struct ib_other_headers *ohdr)
 		   IB_BTH_OPCODE_MASK);
 }
 
+static inline u8 ib_bth_get_ackreq(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[2]) >> IB_BTH_A_SHIFT) &
+		   IB_BTH_A_MASK);
+}
+
+static inline u8 ib_bth_get_migreq(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[0]) >> IB_BTH_M_SHIFT) &
+		    IB_BTH_M_MASK);
+}
+
+static inline u8 ib_bth_get_se(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[0]) >> IB_BTH_SE_SHIFT) &
+		    IB_BTH_SE_MASK);
+}
+
+static inline u32 ib_bth_get_psn(struct ib_other_headers *ohdr)
+{
+	return (u32)(be32_to_cpu(ohdr->bth[2]));
+}
+
+static inline u32 ib_bth_get_qpn(struct ib_other_headers *ohdr)
+{
+	return (u32)((be32_to_cpu(ohdr->bth[1])) & IB_QPN_MASK);
+}
+
+static inline u8 ib_bth_get_becn(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[1]) >> IB_BECN_SHIFT) &
+		     IB_BECN_MASK);
+}
+
+static inline u8 ib_bth_get_fecn(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[1]) >> IB_FECN_SHIFT) &
+		    IB_FECN_MASK);
+}
+
+static inline u8 ib_bth_get_tver(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[0]) >> IB_BTH_TVER_SHIFT)  &
+		    IB_BTH_TVER_MASK);
+}
+
 #endif                          /* IB_HDRS_H */
diff --git a/include/rdma/ib_marshall.h b/include/rdma/ib_marshall.h
index 68cef3bd50fb..8ebf84ae9ed1 100644
--- a/include/rdma/ib_marshall.h
+++ b/include/rdma/ib_marshall.h
@@ -38,10 +38,12 @@
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_user_sa.h>
 
-void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst,
+void ib_copy_qp_attr_to_user(struct ib_device *device,
+			     struct ib_uverbs_qp_attr *dst,
 			     struct ib_qp_attr *src);
 
-void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst,
+void ib_copy_ah_attr_to_user(struct ib_device *device,
+			     struct ib_uverbs_ah_attr *dst,
 			     struct rdma_ah_attr *src);
 
 void ib_copy_path_rec_to_user(struct ib_user_path_rec *dst,
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 88c32aba32f7..e6df68048517 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -64,6 +64,8 @@
 #include <linux/cgroup_rdma.h>
 #include <uapi/rdma/ib_user_verbs.h>
 
+#define IB_FW_VERSION_NAME_MAX	ETHTOOL_FWVERS_LEN
+
 extern struct workqueue_struct *ib_wq;
 extern struct workqueue_struct *ib_comp_wq;
 
@@ -168,7 +170,7 @@ enum ib_device_cap_flags {
 	IB_DEVICE_UD_AV_PORT_ENFORCE		= (1 << 6),
 	IB_DEVICE_CURR_QP_STATE_MOD		= (1 << 7),
 	IB_DEVICE_SHUTDOWN_PORT			= (1 << 8),
-	IB_DEVICE_INIT_TYPE			= (1 << 9),
+	/* Not in use, former INIT_TYPE		= (1 << 9),*/
 	IB_DEVICE_PORT_ACTIVE_EVENT		= (1 << 10),
 	IB_DEVICE_SYS_IMAGE_GUID		= (1 << 11),
 	IB_DEVICE_RC_RNR_NAK_GEN		= (1 << 12),
@@ -183,7 +185,7 @@ enum ib_device_cap_flags {
 	 * which will always contain a usable lkey.
 	 */
 	IB_DEVICE_LOCAL_DMA_LKEY		= (1 << 15),
-	IB_DEVICE_RESERVED /* old SEND_W_INV */	= (1 << 16),
+	/* Reserved, old SEND_W_INV		= (1 << 16),*/
 	IB_DEVICE_MEM_WINDOW			= (1 << 17),
 	/*
 	 * Devices should set IB_DEVICE_UD_IP_SUM if they support
@@ -218,7 +220,7 @@ enum ib_device_cap_flags {
 	 * of I/O operations with single completion queue managed
 	 * by hardware.
 	 */
-	IB_DEVICE_CROSS_CHANNEL		= (1 << 27),
+	IB_DEVICE_CROSS_CHANNEL			= (1 << 27),
 	IB_DEVICE_MANAGED_FLOW_STEERING		= (1 << 29),
 	IB_DEVICE_SIGNATURE_HANDOVER		= (1 << 30),
 	IB_DEVICE_ON_DEMAND_PAGING		= (1ULL << 31),
@@ -278,6 +280,24 @@ struct ib_rss_caps {
 	u32 max_rwq_indirection_table_size;
 };
 
+enum ib_tm_cap_flags {
+	/*  Support tag matching on RC transport */
+	IB_TM_CAP_RC		    = 1 << 0,
+};
+
+struct ib_xrq_caps {
+	/* Max size of RNDV header */
+	u32 max_rndv_hdr_size;
+	/* Max number of entries in tag matching list */
+	u32 max_num_tags;
+	/* From enum ib_tm_cap_flags */
+	u32 flags;
+	/* Max number of outstanding list operations */
+	u32 max_ops;
+	/* Max number of SGE in tag matching entry */
+	u32 max_sge;
+};
+
 enum ib_cq_creation_flags {
 	IB_CQ_FLAGS_TIMESTAMP_COMPLETION   = 1 << 0,
 	IB_CQ_FLAGS_IGNORE_OVERRUN	   = 1 << 1,
@@ -338,6 +358,7 @@ struct ib_device_attr {
 	struct ib_rss_caps	rss_caps;
 	u32			max_wq_type_rq;
 	u32			raw_packet_caps; /* Use ib_raw_packet_caps enum */
+	struct ib_xrq_caps	xrq_caps;
 };
 
 enum ib_mtu {
@@ -549,8 +570,8 @@ struct ib_port_attr {
 	u32			bad_pkey_cntr;
 	u32			qkey_viol_cntr;
 	u16			pkey_tbl_len;
-	u16			lid;
-	u16			sm_lid;
+	u32			sm_lid;
+	u32			lid;
 	u8			lmc;
 	u8			max_vl_num;
 	u8			sm_sl;
@@ -577,7 +598,8 @@ struct ib_device_modify {
 enum ib_port_modify_flags {
 	IB_PORT_SHUTDOWN		= 1,
 	IB_PORT_INIT_TYPE		= (1<<2),
-	IB_PORT_RESET_QKEY_CNTR		= (1<<3)
+	IB_PORT_RESET_QKEY_CNTR		= (1<<3),
+	IB_PORT_OPA_MASK_CHG		= (1<<4)
 };
 
 struct ib_port_modify {
@@ -664,6 +686,8 @@ union rdma_network_hdr {
 	};
 };
 
+#define IB_QPN_MASK		0xFFFFFF
+
 enum {
 	IB_MULTICAST_QPN = 0xffffff
 };
@@ -859,6 +883,7 @@ struct roce_ah_attr {
 struct opa_ah_attr {
 	u32			dlid;
 	u8			src_path_bits;
+	bool			make_grd;
 };
 
 struct rdma_ah_attr {
@@ -948,7 +973,7 @@ struct ib_wc {
 	u32			src_qp;
 	int			wc_flags;
 	u16			pkey_index;
-	u16			slid;
+	u32			slid;
 	u8			sl;
 	u8			dlid_path_bits;
 	u8			port_num;	/* valid only for DR SMPs on switches */
@@ -966,9 +991,16 @@ enum ib_cq_notify_flags {
 
 enum ib_srq_type {
 	IB_SRQT_BASIC,
-	IB_SRQT_XRC
+	IB_SRQT_XRC,
+	IB_SRQT_TM,
 };
 
+static inline bool ib_srq_has_cq(enum ib_srq_type srq_type)
+{
+	return srq_type == IB_SRQT_XRC ||
+	       srq_type == IB_SRQT_TM;
+}
+
 enum ib_srq_attr_mask {
 	IB_SRQ_MAX_WR	= 1 << 0,
 	IB_SRQ_LIMIT	= 1 << 1,
@@ -986,11 +1018,17 @@ struct ib_srq_init_attr {
 	struct ib_srq_attr	attr;
 	enum ib_srq_type	srq_type;
 
-	union {
-		struct {
-			struct ib_xrcd *xrcd;
-			struct ib_cq   *cq;
-		} xrc;
+	struct {
+		struct ib_cq   *cq;
+		union {
+			struct {
+				struct ib_xrcd *xrcd;
+			} xrc;
+
+			struct {
+				u32		max_num_tags;
+			} tag_matching;
+		};
 	} ext;
 };
 
@@ -1059,6 +1097,7 @@ enum ib_qp_create_flags {
 	/* FREE					= 1 << 7, */
 	IB_QP_CREATE_SCATTER_FCS		= 1 << 8,
 	IB_QP_CREATE_CVLAN_STRIPPING		= 1 << 9,
+	IB_QP_CREATE_SOURCE_QPN			= 1 << 10,
 	/* reserve bits 26-31 for low level drivers' internal use */
 	IB_QP_CREATE_RESERVED_START		= 1 << 26,
 	IB_QP_CREATE_RESERVED_END		= 1 << 31,
@@ -1086,6 +1125,7 @@ struct ib_qp_init_attr {
 	 */
 	u8			port_num;
 	struct ib_rwq_ind_table *rwq_ind_tbl;
+	u32			source_qpn;
 };
 
 struct ib_qp_open_attr {
@@ -1527,12 +1567,14 @@ struct ib_srq {
 	enum ib_srq_type	srq_type;
 	atomic_t		usecnt;
 
-	union {
-		struct {
-			struct ib_xrcd *xrcd;
-			struct ib_cq   *cq;
-			u32		srq_num;
-		} xrc;
+	struct {
+		struct ib_cq   *cq;
+		union {
+			struct {
+				struct ib_xrcd *xrcd;
+				u32		srq_num;
+			} xrc;
+		};
 	} ext;
 };
 
@@ -1546,6 +1588,10 @@ enum ib_raw_packet_caps {
 	IB_RAW_PACKET_CAP_SCATTER_FCS		= (1 << 1),
 	/* Checksum offloads are supported (for both send and receive). */
 	IB_RAW_PACKET_CAP_IP_CSUM		= (1 << 2),
+	/* When a packet is received for an RQ with no receive WQEs, the
+	 * packet processing is delayed.
+	 */
+	IB_RAW_PACKET_CAP_DELAY_DROP		= (1 << 3),
 };
 
 enum ib_wq_type {
@@ -1574,6 +1620,7 @@ struct ib_wq {
 enum ib_wq_flags {
 	IB_WQ_FLAGS_CVLAN_STRIPPING	= 1 << 0,
 	IB_WQ_FLAGS_SCATTER_FCS		= 1 << 1,
+	IB_WQ_FLAGS_DELAY_DROP		= 1 << 2,
 };
 
 struct ib_wq_init_attr {
@@ -2289,6 +2336,8 @@ struct ib_device {
 	struct rdmacg_device         cg_device;
 #endif
 
+	u32                          index;
+
 	/**
 	 * The following mandatory functions are used only at device
 	 * registration.  Keep functions such as these at the end of this
@@ -2296,7 +2345,11 @@ struct ib_device {
 	 * in fast paths.
 	 */
 	int (*get_port_immutable)(struct ib_device *, u8, struct ib_port_immutable *);
-	void (*get_dev_fw_str)(struct ib_device *, char *str, size_t str_len);
+	void (*get_dev_fw_str)(struct ib_device *, char *str);
+	const struct cpumask *(*get_vector_affinity)(struct ib_device *ibdev,
+						     int comp_vector);
+
+	struct uverbs_root_spec		*specs_root;
 };
 
 struct ib_client {
@@ -2332,7 +2385,7 @@ struct ib_client {
 struct ib_device *ib_alloc_device(size_t size);
 void ib_dealloc_device(struct ib_device *device);
 
-void ib_get_device_fw_str(struct ib_device *device, char *str, size_t str_len);
+void ib_get_device_fw_str(struct ib_device *device, char *str);
 
 int ib_register_device(struct ib_device *device,
 		       int (*port_callback)(struct ib_device *,
@@ -2396,8 +2449,8 @@ int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
 		       enum ib_qp_type type, enum ib_qp_attr_mask mask,
 		       enum rdma_link_layer ll);
 
-int ib_register_event_handler  (struct ib_event_handler *event_handler);
-int ib_unregister_event_handler(struct ib_event_handler *event_handler);
+void ib_register_event_handler(struct ib_event_handler *event_handler);
+void ib_unregister_event_handler(struct ib_event_handler *event_handler);
 void ib_dispatch_event(struct ib_event *event);
 
 int ib_query_port(struct ib_device *device,
@@ -3556,6 +3609,7 @@ void ib_drain_qp(struct ib_qp *qp);
 
 int ib_resolve_eth_dmac(struct ib_device *device,
 			struct rdma_ah_attr *ah_attr);
+int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width);
 
 static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr)
 {
@@ -3609,6 +3663,20 @@ static inline u8 rdma_ah_get_path_bits(const struct rdma_ah_attr *attr)
 	return 0;
 }
 
+static inline void rdma_ah_set_make_grd(struct rdma_ah_attr *attr,
+					bool make_grd)
+{
+	if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
+		attr->opa.make_grd = make_grd;
+}
+
+static inline bool rdma_ah_get_make_grd(const struct rdma_ah_attr *attr)
+{
+	if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
+		return attr->opa.make_grd;
+	return false;
+}
+
 static inline void rdma_ah_set_port_num(struct rdma_ah_attr *attr, u8 port_num)
 {
 	attr->port_num = port_num;
@@ -3707,4 +3775,52 @@ static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev,
 	else
 		return RDMA_AH_ATTR_TYPE_IB;
 }
+
+/**
+ * ib_lid_cpu16 - Return lid in 16bit CPU encoding.
+ *     In the current implementation the only way to get
+ *     get the 32bit lid is from other sources for OPA.
+ *     For IB, lids will always be 16bits so cast the
+ *     value accordingly.
+ *
+ * @lid: A 32bit LID
+ */
+static inline u16 ib_lid_cpu16(u32 lid)
+{
+	WARN_ON_ONCE(lid & 0xFFFF0000);
+	return (u16)lid;
+}
+
+/**
+ * ib_lid_be16 - Return lid in 16bit BE encoding.
+ *
+ * @lid: A 32bit LID
+ */
+static inline __be16 ib_lid_be16(u32 lid)
+{
+	WARN_ON_ONCE(lid & 0xFFFF0000);
+	return cpu_to_be16((u16)lid);
+}
+
+/**
+ * ib_get_vector_affinity - Get the affinity mappings of a given completion
+ *   vector
+ * @device:         the rdma device
+ * @comp_vector:    index of completion vector
+ *
+ * Returns NULL on failure, otherwise a corresponding cpu map of the
+ * completion vector (returns all-cpus map if the device driver doesn't
+ * implement get_vector_affinity).
+ */
+static inline const struct cpumask *
+ib_get_vector_affinity(struct ib_device *device, int comp_vector)
+{
+	if (comp_vector < 0 || comp_vector >= device->num_comp_vectors ||
+	    !device->get_vector_affinity)
+		return NULL;
+
+	return device->get_vector_affinity(device, comp_vector);
+
+}
+
 #endif /* IB_VERBS_H */
diff --git a/include/rdma/opa_addr.h b/include/rdma/opa_addr.h
index eace28f1555d..e6e90f18e6d5 100644
--- a/include/rdma/opa_addr.h
+++ b/include/rdma/opa_addr.h
@@ -48,8 +48,21 @@
 #ifndef OPA_ADDR_H
 #define OPA_ADDR_H
 
+#include <rdma/opa_smi.h>
+
 #define	OPA_SPECIAL_OUI		(0x00066AULL)
 #define OPA_MAKE_ID(x)          (cpu_to_be64(OPA_SPECIAL_OUI << 40 | (x)))
+#define OPA_TO_IB_UCAST_LID(x) (((x) >= be16_to_cpu(IB_MULTICAST_LID_BASE)) \
+				? 0 : x)
+#define OPA_GID_INDEX		0x1
+/**
+ * 0xF8 - 4 bits of multicast range and 1 bit for collective range
+ * Example: For 24 bit LID space,
+ * Multicast range: 0xF00000 to 0xF7FFFF
+ * Collective range: 0xF80000 to 0xFFFFFE
+ */
+#define OPA_MCAST_NR 0x4 /* Number of top bits set */
+#define OPA_COLLECTIVE_NR 0x1 /* Number of bits after MCAST_NR */
 
 /**
  * ib_is_opa_gid: Returns true if the top 24 bits of the gid
@@ -59,7 +72,7 @@
  *
  * @gid: The Global identifier
  */
-static inline bool ib_is_opa_gid(union ib_gid *gid)
+static inline bool ib_is_opa_gid(const union ib_gid *gid)
 {
 	return ((be64_to_cpu(gid->global.interface_id) >> 40) ==
 		OPA_SPECIAL_OUI);
@@ -72,8 +85,33 @@ static inline bool ib_is_opa_gid(union ib_gid *gid)
  *
  * @gid: The Global identifier
  */
-static inline u32 opa_get_lid_from_gid(union ib_gid *gid)
+static inline u32 opa_get_lid_from_gid(const union ib_gid *gid)
 {
 	return be64_to_cpu(gid->global.interface_id) & 0xFFFFFFFF;
 }
+
+/**
+ * opa_is_extended_lid: Returns true if dlid or slid are
+ * extended.
+ *
+ * @dlid: The DLID
+ * @slid: The SLID
+ */
+static inline bool opa_is_extended_lid(u32 dlid, u32 slid)
+{
+	if ((be32_to_cpu(dlid) >=
+	     be16_to_cpu(IB_MULTICAST_LID_BASE)) ||
+	    (be32_to_cpu(slid) >=
+	     be16_to_cpu(IB_MULTICAST_LID_BASE)))
+		return true;
+	else
+		return false;
+}
+
+/* Get multicast lid base */
+static inline u32 opa_get_mcast_base(u32 nr_top_bits)
+{
+	return (be32_to_cpu(OPA_LID_PERMISSIVE) << (32 - nr_top_bits));
+}
+
 #endif /* OPA_ADDR_H */
diff --git a/include/rdma/opa_vnic.h b/include/rdma/opa_vnic.h
index 39d6890616a6..0c07a70bd7f6 100644
--- a/include/rdma/opa_vnic.h
+++ b/include/rdma/opa_vnic.h
@@ -54,9 +54,6 @@
 
 #include <rdma/ib_verbs.h>
 
-/* VNIC uses 16B header format */
-#define OPA_VNIC_L2_TYPE    0x2
-
 /* 16 header bytes + 2 reserved bytes */
 #define OPA_VNIC_L2_HDR_LEN   (16 + 2)
 
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 348c102cb5f6..2d878596b1e0 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -5,29 +5,43 @@
 #include <linux/netlink.h>
 #include <uapi/rdma/rdma_netlink.h>
 
-struct ibnl_client_cbs {
+struct rdma_nl_cbs {
+	int (*doit)(struct sk_buff *skb, struct nlmsghdr *nlh,
+		    struct netlink_ext_ack *extack);
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
-	struct module *module;
+	u8 flags;
 };
 
+enum rdma_nl_flags {
+	/* Require CAP_NET_ADMIN */
+	RDMA_NL_ADMIN_PERM	= 1 << 0,
+};
+
+/* Define this module as providing netlink services for NETLINK_RDMA, with
+ * index _index.  Since the client indexes were setup in a uapi header as an
+ * enum and we do no want to change that, the user must supply the expanded
+ * constant as well and the compiler checks they are the same.
+ */
+#define MODULE_ALIAS_RDMA_NETLINK(_index, _val)                                \
+	static inline void __chk_##_index(void)                                \
+	{                                                                      \
+		BUILD_BUG_ON(_index != _val);                                  \
+	}                                                                      \
+	MODULE_ALIAS("rdma-netlink-subsys-" __stringify(_val))
+
 /**
- * Add a a client to the list of IB netlink exporters.
+ * Register client in RDMA netlink.
  * @index: Index of the added client
- * @nops: Number of supported ops by the added client.
  * @cb_table: A table for op->callback
- *
- * Returns 0 on success or a negative error code.
  */
-int ibnl_add_client(int index, int nops,
-		    const struct ibnl_client_cbs cb_table[]);
+void rdma_nl_register(unsigned int index,
+		      const struct rdma_nl_cbs cb_table[]);
 
 /**
  * Remove a client from IB netlink.
  * @index: Index of the removed IB client.
- *
- * Returns 0 on success or a negative error code.
  */
-int ibnl_remove_client(int index);
+void rdma_nl_unregister(unsigned int index);
 
 /**
  * Put a new message in a supplied skb.
@@ -56,22 +70,32 @@ int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 /**
  * Send the supplied skb to a specific userspace PID.
  * @skb: The netlink skb
- * @nlh: Header of the netlink message to send
  * @pid: Userspace netlink process ID
  * Returns 0 on success or a negative error code.
  */
-int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			__u32 pid);
+int rdma_nl_unicast(struct sk_buff *skb, u32 pid);
+
+/**
+ * Send, with wait/1 retry, the supplied skb to a specific userspace PID.
+ * @skb: The netlink skb
+ * @pid: Userspace netlink process ID
+ * Returns 0 on success or a negative error code.
+ */
+int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid);
 
 /**
  * Send the supplied skb to a netlink group.
  * @skb: The netlink skb
- * @nlh: Header of the netlink message to send
  * @group: Netlink group ID
  * @flags: allocation flags
  * Returns 0 on success or a negative error code.
  */
-int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			unsigned int group, gfp_t flags);
+int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags);
 
+/**
+ * Check if there are any listeners to the netlink group
+ * @group: the netlink group ID
+ * Returns 0 on success or a negative for no listeners.
+ */
+int rdma_nl_chk_listeners(unsigned int group);
 #endif /* _RDMA_NETLINK_H */
diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index 55af69271053..1ba84a78f1c5 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -57,11 +57,21 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 #include <rdma/ib_verbs.h>
+#include <rdma/ib_mad.h>
 #include <rdma/rdmavt_mr.h>
 #include <rdma/rdmavt_qp.h>
 
 #define RVT_MAX_PKEY_VALUES 16
 
+#define RVT_MAX_TRAP_LEN 100 /* Limit pending trap list */
+#define RVT_MAX_TRAP_LISTS 5 /*((IB_NOTICE_TYPE_INFO & 0x0F) + 1)*/
+#define RVT_TRAP_TIMEOUT 4096 /* 4.096 usec */
+
+struct trap_list {
+	u32 list_len;
+	struct list_head list;
+};
+
 struct rvt_ibport {
 	struct rvt_qp __rcu *qp[2];
 	struct ib_mad_agent *send_agent;	/* agent for SMI (traps) */
@@ -75,12 +85,13 @@ struct rvt_ibport {
 	__be64 mkey;
 	u64 tid;
 	u32 port_cap_flags;
+	u16 port_cap3_flags;
 	u32 pma_sample_start;
 	u32 pma_sample_interval;
 	__be16 pma_counter_select[5];
 	u16 pma_tag;
 	u16 mkey_lease_period;
-	u16 sm_lid;
+	u32 sm_lid;
 	u8 sm_sl;
 	u8 mkeyprot;
 	u8 subnet_timeout;
@@ -127,6 +138,13 @@ struct rvt_ibport {
 	u16 *pkey_table;
 
 	struct rvt_ah *sm_ah;
+
+	/*
+	 * Keep a list of traps that have not been repressed.  They will be
+	 * resent based on trap_timer.
+	 */
+	struct trap_list trap_lists[RVT_MAX_TRAP_LISTS];
+	struct timer_list trap_timer;
 };
 
 #define RVT_CQN_MAX 16 /* maximum length of cq name */
@@ -514,7 +532,8 @@ int rvt_invalidate_rkey(struct rvt_qp *qp, u32 rkey);
 int rvt_rkey_ok(struct rvt_qp *qp, struct rvt_sge *sge,
 		u32 len, u64 vaddr, u32 rkey, int acc);
 int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
-		struct rvt_sge *isge, struct ib_sge *sge, int acc);
+		struct rvt_sge *isge, struct rvt_sge *last_sge,
+		struct ib_sge *sge, int acc);
 struct rvt_mcast *rvt_mcast_find(struct rvt_ibport *ibp, union ib_gid *mgid,
 				 u16 lid);
 
diff --git a/include/rdma/rdmavt_mr.h b/include/rdma/rdmavt_mr.h
index f418bd5571a5..72a3856d4057 100644
--- a/include/rdma/rdmavt_mr.h
+++ b/include/rdma/rdmavt_mr.h
@@ -191,4 +191,7 @@ static inline void rvt_skip_sge(struct rvt_sge_state *ss, u32 length,
 	}
 }
 
+bool rvt_ss_has_lkey(struct rvt_sge_state *ss, u32 lkey);
+bool rvt_mr_has_lkey(struct rvt_mregion *mr, u32 lkey);
+
 #endif          /* DEF_RDMAVT_INCMRH */
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index d664d2e76280..0eed3d8752fa 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -277,7 +277,6 @@ struct rvt_qp {
 
 	unsigned long timeout_jiffies;  /* computed from timeout */
 
-	enum ib_mtu path_mtu;
 	int srate_mbps;		/* s_srate (below) converted to Mbit/s */
 	pid_t pid;		/* pid for user mode QPs */
 	u32 remote_qpn;
@@ -396,7 +395,7 @@ struct rvt_srq {
 #define RVT_QPNMAP_ENTRIES          (RVT_QPN_MAX / PAGE_SIZE / BITS_PER_BYTE)
 #define RVT_BITS_PER_PAGE           (PAGE_SIZE * BITS_PER_BYTE)
 #define RVT_BITS_PER_PAGE_MASK      (RVT_BITS_PER_PAGE - 1)
-#define RVT_QPN_MASK		    0xFFFFFF
+#define RVT_QPN_MASK		    IB_QPN_MASK
 
 /*
  * QPN-map pages start out as NULL, they get allocated upon
@@ -674,4 +673,34 @@ void rvt_del_timers_sync(struct rvt_qp *qp);
 void rvt_stop_rc_timers(struct rvt_qp *qp);
 void rvt_add_retry_timer(struct rvt_qp *qp);
 
+/**
+ * struct rvt_qp_iter - the iterator for QPs
+ * @qp - the current QP
+ *
+ * This structure defines the current iterator
+ * state for sequenced access to all QPs relative
+ * to an rvt_dev_info.
+ */
+struct rvt_qp_iter {
+	struct rvt_qp *qp;
+	/* private: backpointer */
+	struct rvt_dev_info *rdi;
+	/* private: callback routine */
+	void (*cb)(struct rvt_qp *qp, u64 v);
+	/* private: for arg to callback routine */
+	u64 v;
+	/* private: number of SMI,GSI QPs for device */
+	int specials;
+	/* private: current iterator index */
+	int n;
+};
+
+struct rvt_qp_iter *rvt_qp_iter_init(struct rvt_dev_info *rdi,
+				     u64 v,
+				     void (*cb)(struct rvt_qp *qp, u64 v));
+int rvt_qp_iter_next(struct rvt_qp_iter *iter);
+void rvt_qp_iter(struct rvt_dev_info *rdi,
+		 u64 v,
+		 void (*cb)(struct rvt_qp *qp, u64 v));
+void rvt_qp_mr_clean(struct rvt_qp *qp, u32 lkey);
 #endif          /* DEF_RDMAVT_INCQP_H */
diff --git a/include/rdma/uverbs_ioctl.h b/include/rdma/uverbs_ioctl.h
new file mode 100644
index 000000000000..6da44079aa58
--- /dev/null
+++ b/include/rdma/uverbs_ioctl.h
@@ -0,0 +1,438 @@
+/*
+ * Copyright (c) 2017, Mellanox Technologies inc.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _UVERBS_IOCTL_
+#define _UVERBS_IOCTL_
+
+#include <rdma/uverbs_types.h>
+#include <linux/uaccess.h>
+#include <rdma/rdma_user_ioctl.h>
+#include <rdma/ib_user_ioctl_verbs.h>
+
+/*
+ * =======================================
+ *	Verbs action specifications
+ * =======================================
+ */
+
+enum uverbs_attr_type {
+	UVERBS_ATTR_TYPE_NA,
+	UVERBS_ATTR_TYPE_PTR_IN,
+	UVERBS_ATTR_TYPE_PTR_OUT,
+	UVERBS_ATTR_TYPE_IDR,
+	UVERBS_ATTR_TYPE_FD,
+};
+
+enum uverbs_obj_access {
+	UVERBS_ACCESS_READ,
+	UVERBS_ACCESS_WRITE,
+	UVERBS_ACCESS_NEW,
+	UVERBS_ACCESS_DESTROY
+};
+
+enum {
+	UVERBS_ATTR_SPEC_F_MANDATORY	= 1U << 0,
+	/* Support extending attributes by length */
+	UVERBS_ATTR_SPEC_F_MIN_SZ	= 1U << 1,
+};
+
+struct uverbs_attr_spec {
+	enum uverbs_attr_type		type;
+	union {
+		u16				len;
+		struct {
+			/*
+			 * higher bits mean the namespace and lower bits mean
+			 * the type id within the namespace.
+			 */
+			u16			obj_type;
+			u8			access;
+		} obj;
+	};
+	/* Combination of bits from enum UVERBS_ATTR_SPEC_F_XXXX */
+	u8				flags;
+};
+
+struct uverbs_attr_spec_hash {
+	size_t				num_attrs;
+	unsigned long			*mandatory_attrs_bitmask;
+	struct uverbs_attr_spec		attrs[0];
+};
+
+struct uverbs_attr_bundle;
+struct ib_uverbs_file;
+
+enum {
+	/*
+	 * Action marked with this flag creates a context (or root for all
+	 * objects).
+	 */
+	UVERBS_ACTION_FLAG_CREATE_ROOT = 1U << 0,
+};
+
+struct uverbs_method_spec {
+	/* Combination of bits from enum UVERBS_ACTION_FLAG_XXXX */
+	u32						flags;
+	size_t						num_buckets;
+	size_t						num_child_attrs;
+	int (*handler)(struct ib_device *ib_dev, struct ib_uverbs_file *ufile,
+		       struct uverbs_attr_bundle *ctx);
+	struct uverbs_attr_spec_hash		*attr_buckets[0];
+};
+
+struct uverbs_method_spec_hash {
+	size_t					num_methods;
+	struct uverbs_method_spec		*methods[0];
+};
+
+struct uverbs_object_spec {
+	const struct uverbs_obj_type		*type_attrs;
+	size_t					num_buckets;
+	struct uverbs_method_spec_hash		*method_buckets[0];
+};
+
+struct uverbs_object_spec_hash {
+	size_t					num_objects;
+	struct uverbs_object_spec		*objects[0];
+};
+
+struct uverbs_root_spec {
+	size_t					num_buckets;
+	struct uverbs_object_spec_hash		*object_buckets[0];
+};
+
+/*
+ * =======================================
+ *	Verbs definitions
+ * =======================================
+ */
+
+struct uverbs_attr_def {
+	u16                           id;
+	struct uverbs_attr_spec       attr;
+};
+
+struct uverbs_method_def {
+	u16                                  id;
+	/* Combination of bits from enum UVERBS_ACTION_FLAG_XXXX */
+	u32				     flags;
+	size_t				     num_attrs;
+	const struct uverbs_attr_def * const (*attrs)[];
+	int (*handler)(struct ib_device *ib_dev, struct ib_uverbs_file *ufile,
+		       struct uverbs_attr_bundle *ctx);
+};
+
+struct uverbs_object_def {
+	u16					 id;
+	const struct uverbs_obj_type	        *type_attrs;
+	size_t				         num_methods;
+	const struct uverbs_method_def * const (*methods)[];
+};
+
+struct uverbs_object_tree_def {
+	size_t					 num_objects;
+	const struct uverbs_object_def * const (*objects)[];
+};
+
+#define UA_FLAGS(_flags)  .flags = _flags
+#define __UVERBS_ATTR0(_id, _len, _type, ...)                           \
+	((const struct uverbs_attr_def)				  \
+	 {.id = _id, .attr = {.type = _type, {.len = _len}, .flags = 0, } })
+#define __UVERBS_ATTR1(_id, _len, _type, _flags)                        \
+	((const struct uverbs_attr_def)				  \
+	 {.id = _id, .attr = {.type = _type, {.len = _len}, _flags, } })
+#define __UVERBS_ATTR(_id, _len, _type, _flags, _n, ...)		\
+	__UVERBS_ATTR##_n(_id, _len, _type, _flags)
+/*
+ * In new compiler, UVERBS_ATTR could be simplified by declaring it as
+ * [_id] = {.type = _type, .len = _len, ##__VA_ARGS__}
+ * But since we support older compilers too, we need the more complex code.
+ */
+#define UVERBS_ATTR(_id, _len, _type, ...)				\
+	__UVERBS_ATTR(_id, _len, _type, ##__VA_ARGS__, 1, 0)
+#define UVERBS_ATTR_PTR_IN_SZ(_id, _len, ...)				\
+	UVERBS_ATTR(_id, _len, UVERBS_ATTR_TYPE_PTR_IN, ##__VA_ARGS__)
+/* If sizeof(_type) <= sizeof(u64), this will be inlined rather than a pointer */
+#define UVERBS_ATTR_PTR_IN(_id, _type, ...)				\
+	UVERBS_ATTR_PTR_IN_SZ(_id, sizeof(_type), ##__VA_ARGS__)
+#define UVERBS_ATTR_PTR_OUT_SZ(_id, _len, ...)				\
+	UVERBS_ATTR(_id, _len, UVERBS_ATTR_TYPE_PTR_OUT, ##__VA_ARGS__)
+#define UVERBS_ATTR_PTR_OUT(_id, _type, ...)				\
+	UVERBS_ATTR_PTR_OUT_SZ(_id, sizeof(_type), ##__VA_ARGS__)
+
+/*
+ * In new compiler, UVERBS_ATTR_IDR (and FD) could be simplified by declaring
+ * it as
+ * {.id = _id,								\
+ *  .attr {.type = __obj_class,						\
+ *         .obj = {.obj_type = _idr_type,				\
+ *                       .access = _access                              \
+ *                }, ##__VA_ARGS__ } }
+ * But since we support older compilers too, we need the more complex code.
+ */
+#define ___UVERBS_ATTR_OBJ0(_id, _obj_class, _obj_type, _access, ...)\
+	((const struct uverbs_attr_def)					\
+	{.id = _id,							\
+	 .attr = {.type = _obj_class,					\
+		  {.obj = {.obj_type = _obj_type, .access = _access } },\
+		  .flags = 0} })
+#define ___UVERBS_ATTR_OBJ1(_id, _obj_class, _obj_type, _access, _flags)\
+	((const struct uverbs_attr_def)					\
+	{.id = _id,							\
+	.attr = {.type = _obj_class,					\
+		 {.obj = {.obj_type = _obj_type, .access = _access} },	\
+		  _flags} })
+#define ___UVERBS_ATTR_OBJ(_id, _obj_class, _obj_type, _access, _flags, \
+			   _n, ...)					\
+	___UVERBS_ATTR_OBJ##_n(_id, _obj_class, _obj_type, _access, _flags)
+#define __UVERBS_ATTR_OBJ(_id, _obj_class, _obj_type, _access, ...)	\
+	___UVERBS_ATTR_OBJ(_id, _obj_class, _obj_type, _access,		\
+			   ##__VA_ARGS__, 1, 0)
+#define UVERBS_ATTR_IDR(_id, _idr_type, _access, ...)			 \
+	__UVERBS_ATTR_OBJ(_id, UVERBS_ATTR_TYPE_IDR, _idr_type, _access,\
+			  ##__VA_ARGS__)
+#define UVERBS_ATTR_FD(_id, _fd_type, _access, ...)			\
+	__UVERBS_ATTR_OBJ(_id, UVERBS_ATTR_TYPE_FD, _fd_type,		\
+			  (_access) + BUILD_BUG_ON_ZERO(		\
+				(_access) != UVERBS_ACCESS_NEW &&	\
+				(_access) != UVERBS_ACCESS_READ),	\
+			  ##__VA_ARGS__)
+#define DECLARE_UVERBS_ATTR_SPEC(_name, ...)				\
+	const struct uverbs_attr_def _name = __VA_ARGS__
+
+#define _UVERBS_METHOD_ATTRS_SZ(...)					\
+	(sizeof((const struct uverbs_attr_def * const []){__VA_ARGS__}) /\
+	 sizeof(const struct uverbs_attr_def *))
+#define _UVERBS_METHOD(_id, _handler, _flags, ...)			\
+	((const struct uverbs_method_def) {				\
+	 .id = _id,							\
+	 .flags = _flags,						\
+	 .handler = _handler,						\
+	 .num_attrs = _UVERBS_METHOD_ATTRS_SZ(__VA_ARGS__),		\
+	 .attrs = &(const struct uverbs_attr_def * const []){__VA_ARGS__} })
+#define DECLARE_UVERBS_METHOD(_name, _id, _handler, ...)		\
+	const struct uverbs_method_def _name =				\
+		_UVERBS_METHOD(_id, _handler, 0, ##__VA_ARGS__)
+#define DECLARE_UVERBS_CTX_METHOD(_name, _id, _handler, _flags, ...)	\
+	const struct uverbs_method_def _name =				\
+		_UVERBS_METHOD(_id, _handler,				\
+			       UVERBS_ACTION_FLAG_CREATE_ROOT,		\
+			       ##__VA_ARGS__)
+#define _UVERBS_OBJECT_METHODS_SZ(...)					\
+	(sizeof((const struct uverbs_method_def * const []){__VA_ARGS__}) / \
+	 sizeof(const struct uverbs_method_def *))
+#define _UVERBS_OBJECT(_id, _type_attrs, ...)				\
+	((const struct uverbs_object_def) {				\
+	 .id = _id,							\
+	 .type_attrs = _type_attrs,					\
+	 .num_methods = _UVERBS_OBJECT_METHODS_SZ(__VA_ARGS__),		\
+	 .methods = &(const struct uverbs_method_def * const []){__VA_ARGS__} })
+#define DECLARE_UVERBS_OBJECT(_name, _id, _type_attrs, ...)		\
+	const struct uverbs_object_def _name =				\
+		_UVERBS_OBJECT(_id, _type_attrs, ##__VA_ARGS__)
+#define _UVERBS_TREE_OBJECTS_SZ(...)					\
+	(sizeof((const struct uverbs_object_def * const []){__VA_ARGS__}) / \
+	 sizeof(const struct uverbs_object_def *))
+#define _UVERBS_OBJECT_TREE(...)					\
+	((const struct uverbs_object_tree_def) {			\
+	 .num_objects = _UVERBS_TREE_OBJECTS_SZ(__VA_ARGS__),		\
+	 .objects = &(const struct uverbs_object_def * const []){__VA_ARGS__} })
+#define DECLARE_UVERBS_OBJECT_TREE(_name, ...)				\
+	const struct uverbs_object_tree_def _name =			\
+		_UVERBS_OBJECT_TREE(__VA_ARGS__)
+
+/* =================================================
+ *              Parsing infrastructure
+ * =================================================
+ */
+
+struct uverbs_ptr_attr {
+	union {
+		u64		data;
+		void	__user *ptr;
+	};
+	u16		len;
+	/* Combination of bits from enum UVERBS_ATTR_F_XXXX */
+	u16		flags;
+};
+
+struct uverbs_obj_attr {
+	/* pointer to the kernel descriptor -> type, access, etc */
+	const struct uverbs_obj_type	*type;
+	struct ib_uobject		*uobject;
+	/* fd or id in idr of this object */
+	int				id;
+};
+
+struct uverbs_attr {
+	/*
+	 * pointer to the user-space given attribute, in order to write the
+	 * new uobject's id or update flags.
+	 */
+	struct ib_uverbs_attr __user	*uattr;
+	union {
+		struct uverbs_ptr_attr	ptr_attr;
+		struct uverbs_obj_attr	obj_attr;
+	};
+};
+
+struct uverbs_attr_bundle_hash {
+	/* if bit i is set, it means attrs[i] contains valid information */
+	unsigned long *valid_bitmap;
+	size_t num_attrs;
+	/*
+	 * arrays of attributes, each element corresponds to the specification
+	 * of the attribute in the same index.
+	 */
+	struct uverbs_attr *attrs;
+};
+
+struct uverbs_attr_bundle {
+	size_t				num_buckets;
+	struct uverbs_attr_bundle_hash  hash[];
+};
+
+static inline bool uverbs_attr_is_valid_in_hash(const struct uverbs_attr_bundle_hash *attrs_hash,
+						unsigned int idx)
+{
+	return test_bit(idx, attrs_hash->valid_bitmap);
+}
+
+static inline bool uverbs_attr_is_valid(const struct uverbs_attr_bundle *attrs_bundle,
+					unsigned int idx)
+{
+	u16 idx_bucket = idx >>	UVERBS_ID_NS_SHIFT;
+
+	if (attrs_bundle->num_buckets <= idx_bucket)
+		return false;
+
+	return uverbs_attr_is_valid_in_hash(&attrs_bundle->hash[idx_bucket],
+					    idx & ~UVERBS_ID_NS_MASK);
+}
+
+static inline const struct uverbs_attr *uverbs_attr_get(const struct uverbs_attr_bundle *attrs_bundle,
+							u16 idx)
+{
+	u16 idx_bucket = idx >>	UVERBS_ID_NS_SHIFT;
+
+	if (!uverbs_attr_is_valid(attrs_bundle, idx))
+		return ERR_PTR(-ENOENT);
+
+	return &attrs_bundle->hash[idx_bucket].attrs[idx & ~UVERBS_ID_NS_MASK];
+}
+
+static inline int uverbs_copy_to(const struct uverbs_attr_bundle *attrs_bundle,
+				 size_t idx, const void *from)
+{
+	const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx);
+	u16 flags;
+
+	if (IS_ERR(attr))
+		return PTR_ERR(attr);
+
+	flags = attr->ptr_attr.flags | UVERBS_ATTR_F_VALID_OUTPUT;
+	return (!copy_to_user(attr->ptr_attr.ptr, from, attr->ptr_attr.len) &&
+		!put_user(flags, &attr->uattr->flags)) ? 0 : -EFAULT;
+}
+
+static inline int _uverbs_copy_from(void *to, size_t to_size,
+				    const struct uverbs_attr_bundle *attrs_bundle,
+				    size_t idx)
+{
+	const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx);
+
+	if (IS_ERR(attr))
+		return PTR_ERR(attr);
+
+	if (to_size <= sizeof(((struct ib_uverbs_attr *)0)->data))
+		memcpy(to, &attr->ptr_attr.data, attr->ptr_attr.len);
+	else if (copy_from_user(to, attr->ptr_attr.ptr, attr->ptr_attr.len))
+		return -EFAULT;
+
+	return 0;
+}
+
+#define uverbs_copy_from(to, attrs_bundle, idx)				      \
+	_uverbs_copy_from(to, sizeof(*(to)), attrs_bundle, idx)
+
+/* =================================================
+ *	 Definitions -> Specs infrastructure
+ * =================================================
+ */
+
+/*
+ * uverbs_alloc_spec_tree - Merges different common and driver specific feature
+ *	into one parsing tree that every uverbs command will be parsed upon.
+ *
+ * @num_trees: Number of trees in the array @trees.
+ * @trees: Array of pointers to tree root definitions to merge. Each such tree
+ *	   possibly contains objects, methods and attributes definitions.
+ *
+ * Returns:
+ *	uverbs_root_spec *: The root of the merged parsing tree.
+ *	On error, we return an error code. Error is checked via IS_ERR.
+ *
+ * The following merges could take place:
+ * a. Two trees representing the same method with different handler
+ *	-> We take the handler of the tree that its handler != NULL
+ *	   and its index in the trees array is greater. The incentive for that
+ *	   is that developers are expected to first merge common trees and then
+ *	   merge trees that gives specialized the behaviour.
+ * b. Two trees representing the same object with different
+ *    type_attrs (struct uverbs_obj_type):
+ *	-> We take the type_attrs of the tree that its type_attr != NULL
+ *	   and its index in the trees array is greater. This could be used
+ *	   in order to override the free function, allocation size, etc.
+ * c. Two trees representing the same method attribute (same id but possibly
+ *    different attributes):
+ *	-> ERROR (-ENOENT), we believe that's not the programmer's intent.
+ *
+ * An object without any methods is considered invalid and will abort the
+ * function with -ENOENT error.
+ */
+#if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
+struct uverbs_root_spec *uverbs_alloc_spec_tree(unsigned int num_trees,
+						const struct uverbs_object_tree_def **trees);
+void uverbs_free_spec_tree(struct uverbs_root_spec *root);
+#else
+static inline struct uverbs_root_spec *uverbs_alloc_spec_tree(unsigned int num_trees,
+							      const struct uverbs_object_tree_def **trees)
+{
+	return NULL;
+}
+
+static inline void uverbs_free_spec_tree(struct uverbs_root_spec *root)
+{
+}
+#endif
+
+#endif
diff --git a/include/rdma/uverbs_std_types.h b/include/rdma/uverbs_std_types.h
index 7771ce966952..5f8e20bbd67c 100644
--- a/include/rdma/uverbs_std_types.h
+++ b/include/rdma/uverbs_std_types.h
@@ -34,19 +34,35 @@
 #define _UVERBS_STD_TYPES__
 
 #include <rdma/uverbs_types.h>
-
-extern const struct uverbs_obj_fd_type uverbs_type_attrs_comp_channel;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_cq;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_qp;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_rwq_ind_table;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_wq;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_srq;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_ah;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_flow;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_mr;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_mw;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_pd;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_xrcd;
+#include <rdma/uverbs_ioctl.h>
+#include <rdma/ib_user_ioctl_verbs.h>
+
+#if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
+extern const struct uverbs_object_def uverbs_object_comp_channel;
+extern const struct uverbs_object_def uverbs_object_cq;
+extern const struct uverbs_object_def uverbs_object_qp;
+extern const struct uverbs_object_def uverbs_object_rwq_ind_table;
+extern const struct uverbs_object_def uverbs_object_wq;
+extern const struct uverbs_object_def uverbs_object_srq;
+extern const struct uverbs_object_def uverbs_object_ah;
+extern const struct uverbs_object_def uverbs_object_flow;
+extern const struct uverbs_object_def uverbs_object_mr;
+extern const struct uverbs_object_def uverbs_object_mw;
+extern const struct uverbs_object_def uverbs_object_pd;
+extern const struct uverbs_object_def uverbs_object_xrcd;
+extern const struct uverbs_object_def uverbs_object_device;
+
+extern const struct uverbs_object_tree_def uverbs_default_objects;
+static inline const struct uverbs_object_tree_def *uverbs_default_get_objects(void)
+{
+	return &uverbs_default_objects;
+}
+#else
+static inline const struct uverbs_object_tree_def *uverbs_default_get_objects(void)
+{
+	return NULL;
+}
+#endif
 
 static inline struct ib_uobject *__uobj_get(const struct uverbs_obj_type *type,
 					    bool write,
@@ -56,22 +72,22 @@ static inline struct ib_uobject *__uobj_get(const struct uverbs_obj_type *type,
 	return rdma_lookup_get_uobject(type, ucontext, id, write);
 }
 
-#define uobj_get_type(_type) uverbs_type_attrs_##_type.type
+#define uobj_get_type(_object) uverbs_object_##_object.type_attrs
 
 #define uobj_get_read(_type, _id, _ucontext)				\
-	 __uobj_get(&(_type), false, _ucontext, _id)
+	 __uobj_get(_type, false, _ucontext, _id)
 
-#define uobj_get_obj_read(_type, _id, _ucontext)			\
+#define uobj_get_obj_read(_object, _id, _ucontext)			\
 ({									\
-	struct ib_uobject *uobj =					\
-		__uobj_get(&uobj_get_type(_type),			\
+	struct ib_uobject *__uobj =					\
+		__uobj_get(uverbs_object_##_object.type_attrs,		\
 			   false, _ucontext, _id);			\
 									\
-	(struct ib_##_type *)(IS_ERR(uobj) ? NULL : uobj->object);	\
+	(struct ib_##_object *)(IS_ERR(__uobj) ? NULL : __uobj->object);\
 })
 
 #define uobj_get_write(_type, _id, _ucontext)				\
-	 __uobj_get(&(_type), true, _ucontext, _id)
+	 __uobj_get(_type, true, _ucontext, _id)
 
 static inline void uobj_put_read(struct ib_uobject *uobj)
 {
@@ -108,7 +124,7 @@ static inline struct ib_uobject *__uobj_alloc(const struct uverbs_obj_type *type
 }
 
 #define uobj_alloc(_type, ucontext)	\
-	__uobj_alloc(&(_type), ucontext)
+	__uobj_alloc(_type, ucontext)
 
 #endif
 
diff --git a/include/rdma/uverbs_types.h b/include/rdma/uverbs_types.h
index 351ea185df44..cc04ec65588d 100644
--- a/include/rdma/uverbs_types.h
+++ b/include/rdma/uverbs_types.h
@@ -129,6 +129,7 @@ struct ib_uobject *rdma_alloc_begin_uobject(const struct uverbs_obj_type *type,
 void rdma_alloc_abort_uobject(struct ib_uobject *uobj);
 int __must_check rdma_remove_commit_uobject(struct ib_uobject *uobj);
 int rdma_alloc_commit_uobject(struct ib_uobject *uobj);
+int rdma_explicit_destroy(struct ib_uobject *uobject);
 
 struct uverbs_obj_fd_type {
 	/*
@@ -151,22 +152,30 @@ extern const struct uverbs_obj_type_class uverbs_fd_class;
 
 #define UVERBS_BUILD_BUG_ON(cond) (sizeof(char[1 - 2 * !!(cond)]) -	\
 				   sizeof(char))
-#define UVERBS_TYPE_ALLOC_FD(_size, _order)				 \
-	{								 \
-		.destroy_order = _order,				 \
-		.type_class = &uverbs_fd_class,				 \
-		.obj_size = (_size) +					 \
-			  UVERBS_BUILD_BUG_ON((_size) <			 \
-					      sizeof(struct ib_uobject_file)),\
-	}
-#define UVERBS_TYPE_ALLOC_IDR_SZ(_size, _order)				\
-	{								\
+#define UVERBS_TYPE_ALLOC_FD(_order, _obj_size, _context_closed, _fops, _name, _flags)\
+	((&((const struct uverbs_obj_fd_type)				\
+	 {.type = {							\
+		.destroy_order = _order,				\
+		.type_class = &uverbs_fd_class,				\
+		.obj_size = (_obj_size) +				\
+			UVERBS_BUILD_BUG_ON((_obj_size) < sizeof(struct ib_uobject_file)), \
+	 },								\
+	 .context_closed = _context_closed,				\
+	 .fops = _fops,							\
+	 .name = _name,							\
+	 .flags = _flags}))->type)
+#define UVERBS_TYPE_ALLOC_IDR_SZ(_size, _order, _destroy_object)	\
+	((&((const struct uverbs_obj_idr_type)				\
+	 {.type = {							\
 		.destroy_order = _order,				\
 		.type_class = &uverbs_idr_class,			\
 		.obj_size = (_size) +					\
-			  UVERBS_BUILD_BUG_ON((_size) <			\
-					      sizeof(struct ib_uobject)), \
-	}
-#define UVERBS_TYPE_ALLOC_IDR(_order)					\
-	 UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uobject), _order)
+			UVERBS_BUILD_BUG_ON((_size) <			\
+					    sizeof(struct ib_uobject))	\
+	 },								\
+	 .destroy_object = _destroy_object,}))->type)
+#define UVERBS_TYPE_ALLOC_IDR(_order, _destroy_object)			\
+	 UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uobject), _order,	\
+				  _destroy_object)
+
 #endif