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

Pull rdma updates from Doug Ledford:
 "This is a big pull request.

  Of note is that I'm sending you the new ioctl API for the rdma
  subsystem. We put it up on linux-api@, but didn't get much response.
  The API is complex, but it solves two different problems in one go:

   1) The bi-directional nature of the RDMA file write calls, which
      created the security hole we had to handle (and for which the fix
      is now causing problems for systems in production, we were a bit
      over zealous in the fix and the ability to open a device, then
      fork, then create new queue pairs on the device and use them is
      broken).

   2) The bloat caused by different vendors implementing extensions to
      the base verbs API. Each vendor's hardware is slightly different,
      and the hardware might be suitable for one extension but not
      another.

      By the time we add generic extensions for all the different ways
      that the different hardware can offload things, the API becomes
      bloated. Things like our completion structs have started to exceed
      a cache line in size because of all the elements needed to support
      this. That in turn shows up heavily in the performance graphs with
      a noticable drop in performance on 100Gigabit links as our
      completion structs go from occupying one cache line to 1+.

      This API makes things like the completion structs modular in a
      very similar way to netlink so that your structs can only include
      the items needed for the offloads/features you are actually using
      on a given queue pair. In that way we support everything, but only
      use what we need, and our structs stay smaller.

  The ioctl API is better explained by the posting on linux-api@ than I
  can explain it here, so I'll just leave it at that.

  The rest of the pull request is typical stuff.

  Updates for 4.14 kernel merge window

   - Lots of hfi1 driver updates (mixed with a few qib and core updates
     as well)

   - rxe updates

   - various mlx updates

   - Set default roce type to RoCEv2

   - Several larger fixes for bnxt_re that were too big for -rc

   - Several larger fixes for qedr that, likewise, were too big for -rc

   - Misc core changes

   - Make the hns_roce driver compilable on arches other than aarch64 so
     we can more easily debug build issues related to it

   - Add rdma-netlink infrastructure updates

   - Add automatic IRQ affinity infrastructure

   - Add 32bit lid support

   - Lots of misc fixes across the subsystem from random people

   - Autoloading of RDMA netlink modules

   - PCI pool cleanups from Romain Perier

   - mlx5 driver feature additions and fixes

   - Hardware tag matchine feature

   - Fix sleeping in atomic when resolving roce ah

   - Add experimental ioctl interface as posted to linux-api@"

* tag 'for-linus-ioctl' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (328 commits)
  IB/core: Expose ioctl interface through experimental Kconfig
  IB/core: Assign root to all drivers
  IB/core: Add completion queue (cq) object actions
  IB/core: Add legacy driver's user-data
  IB/core: Export ioctl enum types to user-space
  IB/core: Explicitly destroy an object while keeping uobject
  IB/core: Add macros for declaring methods and attributes
  IB/core: Add uverbs merge trees functionality
  IB/core: Add DEVICE object and root tree structure
  IB/core: Declare an object instead of declaring only type attributes
  IB/core: Add new ioctl interface
  RDMA/vmw_pvrdma: Fix a signedness
  RDMA/vmw_pvrdma: Report network header type in WC
  IB/core: Add might_sleep() annotation to ib_init_ah_from_wc()
  IB/cm: Fix sleeping in atomic when RoCE is used
  IB/core: Add support to finalize objects in one transaction
  IB/core: Add a generic way to execute an operation on a uobject
  Documentation: Hardware tag matching
  IB/mlx5: Support IB_SRQT_TM
  net/mlx5: Add XRQ support
  ...

8 files changed, 298 insertions, 6 deletions

diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h
new file mode 100644
index 000000000000..842792eae383
--- /dev/null
+++ b/include/uapi/rdma/ib_user_ioctl_verbs.h
@@ -0,0 +1,84 @@
+/*
+ * 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 IB_USER_IOCTL_VERBS_H
+#define IB_USER_IOCTL_VERBS_H
+
+#include <rdma/rdma_user_ioctl.h>
+
+#define UVERBS_UDATA_DRIVER_DATA_NS	1
+#define UVERBS_UDATA_DRIVER_DATA_FLAG	(1UL << UVERBS_ID_NS_SHIFT)
+
+enum uverbs_default_objects {
+	UVERBS_OBJECT_DEVICE, /* No instances of DEVICE are allowed */
+	UVERBS_OBJECT_PD,
+	UVERBS_OBJECT_COMP_CHANNEL,
+	UVERBS_OBJECT_CQ,
+	UVERBS_OBJECT_QP,
+	UVERBS_OBJECT_SRQ,
+	UVERBS_OBJECT_AH,
+	UVERBS_OBJECT_MR,
+	UVERBS_OBJECT_MW,
+	UVERBS_OBJECT_FLOW,
+	UVERBS_OBJECT_XRCD,
+	UVERBS_OBJECT_RWQ_IND_TBL,
+	UVERBS_OBJECT_WQ,
+	UVERBS_OBJECT_LAST,
+};
+
+enum {
+	UVERBS_UHW_IN = UVERBS_UDATA_DRIVER_DATA_FLAG,
+	UVERBS_UHW_OUT,
+};
+
+enum uverbs_create_cq_cmd_attr_ids {
+	CREATE_CQ_HANDLE,
+	CREATE_CQ_CQE,
+	CREATE_CQ_USER_HANDLE,
+	CREATE_CQ_COMP_CHANNEL,
+	CREATE_CQ_COMP_VECTOR,
+	CREATE_CQ_FLAGS,
+	CREATE_CQ_RESP_CQE,
+};
+
+enum uverbs_destroy_cq_cmd_attr_ids {
+	DESTROY_CQ_HANDLE,
+	DESTROY_CQ_RESP,
+};
+
+enum uverbs_actions_cq_ops {
+	UVERBS_CQ_CREATE,
+	UVERBS_CQ_DESTROY,
+};
+
+#endif
+
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 270c350bedc6..9a0b6479fe0c 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -236,6 +236,20 @@ struct ib_uverbs_rss_caps {
 	__u32 reserved;
 };
 
+struct ib_uverbs_tm_caps {
+	/* Max size of rendezvous request message */
+	__u32 max_rndv_hdr_size;
+	/* Max number of entries in tag matching list */
+	__u32 max_num_tags;
+	/* TM flags */
+	__u32 flags;
+	/* Max number of outstanding list operations */
+	__u32 max_ops;
+	/* Max number of SGE in tag matching entry */
+	__u32 max_sge;
+	__u32 reserved;
+};
+
 struct ib_uverbs_ex_query_device_resp {
 	struct ib_uverbs_query_device_resp base;
 	__u32 comp_mask;
@@ -247,6 +261,7 @@ struct ib_uverbs_ex_query_device_resp {
 	struct ib_uverbs_rss_caps rss_caps;
 	__u32  max_wq_type_rq;
 	__u32 raw_packet_caps;
+	struct ib_uverbs_tm_caps xrq_caps;
 };
 
 struct ib_uverbs_query_port {
@@ -578,7 +593,7 @@ struct ib_uverbs_ex_create_qp {
 	__u32 comp_mask;
 	__u32 create_flags;
 	__u32 rwq_ind_tbl_handle;
-	__u32  reserved1;
+	__u32  source_qpn;
 };
 
 struct ib_uverbs_open_qp {
@@ -1024,7 +1039,7 @@ struct ib_uverbs_create_xsrq {
 	__u32 max_wr;
 	__u32 max_sge;
 	__u32 srq_limit;
-	__u32 reserved;
+	__u32 max_num_tags;
 	__u32 xrcd_handle;
 	__u32 cq_handle;
 	__u64 driver_data[0];
diff --git a/include/uapi/rdma/mlx4-abi.h b/include/uapi/rdma/mlx4-abi.h
index af431752655c..c55f60e05f86 100644
--- a/include/uapi/rdma/mlx4-abi.h
+++ b/include/uapi/rdma/mlx4-abi.h
@@ -95,13 +95,63 @@ struct mlx4_ib_create_srq_resp {
 	__u32	reserved;
 };
 
+struct mlx4_ib_create_qp_rss {
+	__u64   rx_hash_fields_mask;
+	__u8    rx_hash_function;
+	__u8    reserved[7];
+	__u8    rx_hash_key[40];
+	__u32   comp_mask;
+	__u32   reserved1;
+};
+
 struct mlx4_ib_create_qp {
 	__u64	buf_addr;
 	__u64	db_addr;
 	__u8	log_sq_bb_count;
 	__u8	log_sq_stride;
 	__u8	sq_no_prefetch;
-	__u8	reserved[5];
+	__u8	reserved;
+	__u32	inl_recv_sz;
+};
+
+struct mlx4_ib_create_wq {
+	__u64	buf_addr;
+	__u64	db_addr;
+	__u8	log_range_size;
+	__u8	reserved[3];
+	__u32   comp_mask;
+};
+
+struct mlx4_ib_modify_wq {
+	__u32	comp_mask;
+	__u32	reserved;
+};
+
+struct mlx4_ib_create_rwq_ind_tbl_resp {
+	__u32	response_length;
+	__u32	reserved;
+};
+
+/* RX Hash function flags */
+enum mlx4_ib_rx_hash_function_flags {
+	MLX4_IB_RX_HASH_FUNC_TOEPLITZ	= 1 << 0,
+};
+
+/*
+ * RX Hash flags, these flags allows to set which incoming packet's field should
+ * participates in RX Hash. Each flag represent certain packet's field,
+ * when the flag is set the field that is represented by the flag will
+ * participate in RX Hash calculation.
+ */
+enum mlx4_ib_rx_hash_fields {
+	MLX4_IB_RX_HASH_SRC_IPV4	= 1 << 0,
+	MLX4_IB_RX_HASH_DST_IPV4	= 1 << 1,
+	MLX4_IB_RX_HASH_SRC_IPV6	= 1 << 2,
+	MLX4_IB_RX_HASH_DST_IPV6	= 1 << 3,
+	MLX4_IB_RX_HASH_SRC_PORT_TCP	= 1 << 4,
+	MLX4_IB_RX_HASH_DST_PORT_TCP	= 1 << 5,
+	MLX4_IB_RX_HASH_SRC_PORT_UDP	= 1 << 6,
+	MLX4_IB_RX_HASH_DST_PORT_UDP	= 1 << 7
 };
 
 #endif /* MLX4_ABI_USER_H */
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index 0b3d30837a9f..1791bf123ba9 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -168,6 +168,28 @@ struct mlx5_packet_pacing_caps {
 	__u32 reserved;
 };
 
+enum mlx5_ib_mpw_caps {
+	MPW_RESERVED		= 1 << 0,
+	MLX5_IB_ALLOW_MPW	= 1 << 1,
+	MLX5_IB_SUPPORT_EMPW	= 1 << 2,
+};
+
+enum mlx5_ib_sw_parsing_offloads {
+	MLX5_IB_SW_PARSING = 1 << 0,
+	MLX5_IB_SW_PARSING_CSUM = 1 << 1,
+	MLX5_IB_SW_PARSING_LSO = 1 << 2,
+};
+
+struct mlx5_ib_sw_parsing_caps {
+	__u32 sw_parsing_offloads; /* enum mlx5_ib_sw_parsing_offloads */
+
+	/* Corresponding bit will be set if qp type from
+	 * 'enum ib_qp_type' is supported, e.g.
+	 * supported_qpts |= 1 << IB_QPT_RAW_PACKET
+	 */
+	__u32 supported_qpts;
+};
+
 struct mlx5_ib_query_device_resp {
 	__u32	comp_mask;
 	__u32	response_length;
@@ -177,6 +199,7 @@ struct mlx5_ib_query_device_resp {
 	struct	mlx5_packet_pacing_caps packet_pacing_caps;
 	__u32	mlx5_ib_support_multi_pkt_send_wqes;
 	__u32	reserved;
+	struct mlx5_ib_sw_parsing_caps sw_parsing_caps;
 };
 
 struct mlx5_ib_create_cq {
diff --git a/include/uapi/rdma/qedr-abi.h b/include/uapi/rdma/qedr-abi.h
index 75c270d839c8..54b64357ab24 100644
--- a/include/uapi/rdma/qedr-abi.h
+++ b/include/uapi/rdma/qedr-abi.h
@@ -49,6 +49,9 @@ struct qedr_alloc_ucontext_resp {
 	__u32 sges_per_recv_wr;
 	__u32 sges_per_srq_wr;
 	__u32 max_cqes;
+	__u8 dpm_enabled;
+	__u8 wids_enabled;
+	__u16 wid_count;
 };
 
 struct qedr_alloc_pd_ureq {
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 02fe8390c18f..861440a87e7c 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -8,7 +8,7 @@ enum {
 	RDMA_NL_IWCM,
 	RDMA_NL_RSVD,
 	RDMA_NL_LS,	/* RDMA Local Services */
-	RDMA_NL_I40IW,
+	RDMA_NL_NLDEV,	/* RDMA device interface */
 	RDMA_NL_NUM_CLIENTS
 };
 
@@ -222,4 +222,86 @@ struct rdma_nla_ls_gid {
 	__u8		gid[16];
 };
 
+enum rdma_nldev_command {
+	RDMA_NLDEV_CMD_UNSPEC,
+
+	RDMA_NLDEV_CMD_GET, /* can dump */
+	RDMA_NLDEV_CMD_SET,
+	RDMA_NLDEV_CMD_NEW,
+	RDMA_NLDEV_CMD_DEL,
+
+	RDMA_NLDEV_CMD_PORT_GET, /* can dump */
+	RDMA_NLDEV_CMD_PORT_SET,
+	RDMA_NLDEV_CMD_PORT_NEW,
+	RDMA_NLDEV_CMD_PORT_DEL,
+
+	RDMA_NLDEV_NUM_OPS
+};
+
+enum rdma_nldev_attr {
+	/* don't change the order or add anything between, this is ABI! */
+	RDMA_NLDEV_ATTR_UNSPEC,
+
+	/* Identifier for ib_device */
+	RDMA_NLDEV_ATTR_DEV_INDEX,		/* u32 */
+
+	RDMA_NLDEV_ATTR_DEV_NAME,		/* string */
+	/*
+	 * Device index together with port index are identifiers
+	 * for port/link properties.
+	 *
+	 * For RDMA_NLDEV_CMD_GET commamnd, port index will return number
+	 * of available ports in ib_device, while for port specific operations,
+	 * it will be real port index as it appears in sysfs. Port index follows
+	 * sysfs notation and starts from 1 for the first port.
+	 */
+	RDMA_NLDEV_ATTR_PORT_INDEX,		/* u32 */
+
+	/*
+	 * Device and port capabilities
+	 */
+	RDMA_NLDEV_ATTR_CAP_FLAGS,		/* u64 */
+
+	/*
+	 * FW version
+	 */
+	RDMA_NLDEV_ATTR_FW_VERSION,		/* string */
+
+	/*
+	 * Node GUID (in host byte order) associated with the RDMA device.
+	 */
+	RDMA_NLDEV_ATTR_NODE_GUID,			/* u64 */
+
+	/*
+	 * System image GUID (in host byte order) associated with
+	 * this RDMA device and other devices which are part of a
+	 * single system.
+	 */
+	RDMA_NLDEV_ATTR_SYS_IMAGE_GUID,		/* u64 */
+
+	/*
+	 * Subnet prefix (in host byte order)
+	 */
+	RDMA_NLDEV_ATTR_SUBNET_PREFIX,		/* u64 */
+
+	/*
+	 * Local Identifier (LID),
+	 * According to IB specification, It is 16-bit address assigned
+	 * by the Subnet Manager. Extended to be 32-bit for OmniPath users.
+	 */
+	RDMA_NLDEV_ATTR_LID,			/* u32 */
+	RDMA_NLDEV_ATTR_SM_LID,			/* u32 */
+
+	/*
+	 * LID mask control (LMC)
+	 */
+	RDMA_NLDEV_ATTR_LMC,			/* u8 */
+
+	RDMA_NLDEV_ATTR_PORT_STATE,		/* u8 */
+	RDMA_NLDEV_ATTR_PORT_PHYS_STATE,	/* u8 */
+
+	RDMA_NLDEV_ATTR_DEV_NODE_TYPE,		/* u8 */
+
+	RDMA_NLDEV_ATTR_MAX
+};
 #endif /* _UAPI_RDMA_NETLINK_H */
diff --git a/include/uapi/rdma/rdma_user_ioctl.h b/include/uapi/rdma/rdma_user_ioctl.h
index 9388125ad51b..165a27e969d5 100644
--- a/include/uapi/rdma/rdma_user_ioctl.h
+++ b/include/uapi/rdma/rdma_user_ioctl.h
@@ -43,6 +43,39 @@
 /* Legacy name, for user space application which already use it */
 #define IB_IOCTL_MAGIC		RDMA_IOCTL_MAGIC
 
+#define RDMA_VERBS_IOCTL \
+	_IOWR(RDMA_IOCTL_MAGIC, 1, struct ib_uverbs_ioctl_hdr)
+
+#define UVERBS_ID_NS_MASK 0xF000
+#define UVERBS_ID_NS_SHIFT 12
+
+enum {
+	/* User input */
+	UVERBS_ATTR_F_MANDATORY = 1U << 0,
+	/*
+	 * Valid output bit should be ignored and considered set in
+	 * mandatory fields. This bit is kernel output.
+	 */
+	UVERBS_ATTR_F_VALID_OUTPUT = 1U << 1,
+};
+
+struct ib_uverbs_attr {
+	__u16 attr_id;		/* command specific type attribute */
+	__u16 len;		/* only for pointers */
+	__u16 flags;		/* combination of UVERBS_ATTR_F_XXXX */
+	__u16 reserved;
+	__u64 data;		/* ptr to command, inline data or idr/fd */
+};
+
+struct ib_uverbs_ioctl_hdr {
+	__u16 length;
+	__u16 object_id;
+	__u16 method_id;
+	__u16 num_attrs;
+	__u64 reserved;
+	struct ib_uverbs_attr  attrs[0];
+};
+
 /*
  * General blocks assignments
  * It is closed on purpose do not expose it it user space
diff --git a/include/uapi/rdma/vmw_pvrdma-abi.h b/include/uapi/rdma/vmw_pvrdma-abi.h
index c8c1d2d6df4d..c6569b0032ec 100644
--- a/include/uapi/rdma/vmw_pvrdma-abi.h
+++ b/include/uapi/rdma/vmw_pvrdma-abi.h
@@ -125,7 +125,8 @@ enum pvrdma_wc_flags {
 	PVRDMA_WC_IP_CSUM_OK		= 1 << 3,
 	PVRDMA_WC_WITH_SMAC		= 1 << 4,
 	PVRDMA_WC_WITH_VLAN		= 1 << 5,
-	PVRDMA_WC_FLAGS_MAX		= PVRDMA_WC_WITH_VLAN,
+	PVRDMA_WC_WITH_NETWORK_HDR_TYPE	= 1 << 6,
+	PVRDMA_WC_FLAGS_MAX		= PVRDMA_WC_WITH_NETWORK_HDR_TYPE,
 };
 
 struct pvrdma_alloc_ucontext_resp {
@@ -283,7 +284,8 @@ struct pvrdma_cqe {
 	__u8 dlid_path_bits;
 	__u8 port_num;
 	__u8 smac[6];
-	__u8 reserved2[7]; /* Pad to next power of 2 (64). */
+	__u8 network_hdr_type;
+	__u8 reserved2[6]; /* Pad to next power of 2 (64). */
 };
 
 #endif /* __VMW_PVRDMA_ABI_H__ */