ib_verbs.h 110.0 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6
/*
 * Copyright (c) 2004 Mellanox Technologies Ltd.  All rights reserved.
 * Copyright (c) 2004 Infinicon Corporation.  All rights reserved.
 * Copyright (c) 2004 Intel Corporation.  All rights reserved.
 * Copyright (c) 2004 Topspin Corporation.  All rights reserved.
 * Copyright (c) 2004 Voltaire Corporation.  All rights reserved.
7
 * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
8
 * Copyright (c) 2005, 2006, 2007 Cisco Systems.  All rights reserved.
L
Linus Torvalds 已提交
9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43
 *
 * 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.
 */

#if !defined(IB_VERBS_H)
#define IB_VERBS_H

#include <linux/types.h>
#include <linux/device.h>
44 45
#include <linux/mm.h>
#include <linux/dma-mapping.h>
46
#include <linux/kref.h>
47 48
#include <linux/list.h>
#include <linux/rwsem.h>
A
Adrian Bunk 已提交
49
#include <linux/scatterlist.h>
T
Tejun Heo 已提交
50
#include <linux/workqueue.h>
51
#include <linux/socket.h>
52
#include <linux/irq_poll.h>
53
#include <uapi/linux/if_ether.h>
54 55
#include <net/ipv6.h>
#include <net/ip.h>
M
Matan Barak 已提交
56 57
#include <linux/string.h>
#include <linux/slab.h>
58
#include <linux/netdevice.h>
59

60
#include <linux/if_link.h>
A
Arun Sharma 已提交
61
#include <linux/atomic.h>
62
#include <linux/mmu_notifier.h>
63
#include <linux/uaccess.h>
64
#include <linux/cgroup_rdma.h>
65
#include <uapi/rdma/ib_user_verbs.h>
66
#include <rdma/restrack.h>
67
#include <uapi/rdma/rdma_user_ioctl.h>
L
Linus Torvalds 已提交
68

69 70
#define IB_FW_VERSION_NAME_MAX	ETHTOOL_FWVERS_LEN

T
Tejun Heo 已提交
71
extern struct workqueue_struct *ib_wq;
72
extern struct workqueue_struct *ib_comp_wq;
T
Tejun Heo 已提交
73

L
Linus Torvalds 已提交
74 75 76
union ib_gid {
	u8	raw[16];
	struct {
77 78
		__be64	subnet_prefix;
		__be64	interface_id;
L
Linus Torvalds 已提交
79 80 81
	} global;
};

82 83
extern union ib_gid zgid;

84 85 86 87
enum ib_gid_type {
	/* If link layer is Ethernet, this is RoCE V1 */
	IB_GID_TYPE_IB        = 0,
	IB_GID_TYPE_ROCE      = 0,
88
	IB_GID_TYPE_ROCE_UDP_ENCAP = 1,
89 90 91
	IB_GID_TYPE_SIZE
};

92
#define ROCE_V2_UDP_DPORT      4791
93 94
struct ib_gid_attr {
	struct net_device	*ndev;
95 96 97 98
	struct ib_device	*device;
	enum ib_gid_type	gid_type;
	u16			index;
	u8			port_num;
99 100
};

T
Tom Tucker 已提交
101 102 103 104 105
enum rdma_node_type {
	/* IB values map to NodeInfo:NodeType. */
	RDMA_NODE_IB_CA 	= 1,
	RDMA_NODE_IB_SWITCH,
	RDMA_NODE_IB_ROUTER,
106 107
	RDMA_NODE_RNIC,
	RDMA_NODE_USNIC,
108
	RDMA_NODE_USNIC_UDP,
L
Linus Torvalds 已提交
109 110
};

111 112 113 114 115
enum {
	/* set the local administered indication */
	IB_SA_WELL_KNOWN_GUID	= BIT_ULL(57) | 2,
};

T
Tom Tucker 已提交
116 117
enum rdma_transport_type {
	RDMA_TRANSPORT_IB,
118
	RDMA_TRANSPORT_IWARP,
119 120
	RDMA_TRANSPORT_USNIC,
	RDMA_TRANSPORT_USNIC_UDP
T
Tom Tucker 已提交
121 122
};

123 124 125 126 127 128 129
enum rdma_protocol_type {
	RDMA_PROTOCOL_IB,
	RDMA_PROTOCOL_IBOE,
	RDMA_PROTOCOL_IWARP,
	RDMA_PROTOCOL_USNIC_UDP
};

130 131
__attribute_const__ enum rdma_transport_type
rdma_node_get_transport(enum rdma_node_type node_type);
T
Tom Tucker 已提交
132

133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161
enum rdma_network_type {
	RDMA_NETWORK_IB,
	RDMA_NETWORK_ROCE_V1 = RDMA_NETWORK_IB,
	RDMA_NETWORK_IPV4,
	RDMA_NETWORK_IPV6
};

static inline enum ib_gid_type ib_network_to_gid_type(enum rdma_network_type network_type)
{
	if (network_type == RDMA_NETWORK_IPV4 ||
	    network_type == RDMA_NETWORK_IPV6)
		return IB_GID_TYPE_ROCE_UDP_ENCAP;

	/* IB_GID_TYPE_IB same as RDMA_NETWORK_ROCE_V1 */
	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)
{
	if (gid_type == IB_GID_TYPE_IB)
		return RDMA_NETWORK_IB;

	if (ipv6_addr_v4mapped((struct in6_addr *)gid))
		return RDMA_NETWORK_IPV4;
	else
		return RDMA_NETWORK_IPV6;
}

162 163 164 165 166 167
enum rdma_link_layer {
	IB_LINK_LAYER_UNSPECIFIED,
	IB_LINK_LAYER_INFINIBAND,
	IB_LINK_LAYER_ETHERNET,
};

L
Linus Torvalds 已提交
168
enum ib_device_cap_flags {
169 170 171 172 173 174 175 176 177
	IB_DEVICE_RESIZE_MAX_WR			= (1 << 0),
	IB_DEVICE_BAD_PKEY_CNTR			= (1 << 1),
	IB_DEVICE_BAD_QKEY_CNTR			= (1 << 2),
	IB_DEVICE_RAW_MULTI			= (1 << 3),
	IB_DEVICE_AUTO_PATH_MIG			= (1 << 4),
	IB_DEVICE_CHANGE_PHY_PORT		= (1 << 5),
	IB_DEVICE_UD_AV_PORT_ENFORCE		= (1 << 6),
	IB_DEVICE_CURR_QP_STATE_MOD		= (1 << 7),
	IB_DEVICE_SHUTDOWN_PORT			= (1 << 8),
178
	/* Not in use, former INIT_TYPE		= (1 << 9),*/
179 180 181 182 183
	IB_DEVICE_PORT_ACTIVE_EVENT		= (1 << 10),
	IB_DEVICE_SYS_IMAGE_GUID		= (1 << 11),
	IB_DEVICE_RC_RNR_NAK_GEN		= (1 << 12),
	IB_DEVICE_SRQ_RESIZE			= (1 << 13),
	IB_DEVICE_N_NOTIFY_CQ			= (1 << 14),
184 185 186 187 188 189 190 191

	/*
	 * This device supports a per-device lkey or stag that can be
	 * used without performing a memory registration for the local
	 * memory.  Note that ULPs should never check this flag, but
	 * instead of use the local_dma_lkey flag in the ib_pd structure,
	 * which will always contain a usable lkey.
	 */
192
	IB_DEVICE_LOCAL_DMA_LKEY		= (1 << 15),
193
	/* Reserved, old SEND_W_INV		= (1 << 16),*/
194
	IB_DEVICE_MEM_WINDOW			= (1 << 17),
195 196 197 198 199 200 201
	/*
	 * Devices should set IB_DEVICE_UD_IP_SUM if they support
	 * insertion of UDP and TCP checksum on outgoing UD IPoIB
	 * messages and can verify the validity of checksum for
	 * incoming messages.  Setting this flag implies that the
	 * IPoIB driver may set NETIF_F_IP_CSUM for datagram mode.
	 */
202 203 204
	IB_DEVICE_UD_IP_CSUM			= (1 << 18),
	IB_DEVICE_UD_TSO			= (1 << 19),
	IB_DEVICE_XRC				= (1 << 20),
205 206 207 208 209 210 211 212 213 214

	/*
	 * This device supports the IB "base memory management extension",
	 * which includes support for fast registrations (IB_WR_REG_MR,
	 * IB_WR_LOCAL_INV and IB_WR_SEND_WITH_INV verbs).  This flag should
	 * also be set by any iWarp device which must support FRs to comply
	 * to the iWarp verbs spec.  iWarp devices also support the
	 * IB_WR_RDMA_READ_WITH_INV verb for RDMA READs that invalidate the
	 * stag.
	 */
215 216 217 218 219
	IB_DEVICE_MEM_MGT_EXTENSIONS		= (1 << 21),
	IB_DEVICE_BLOCK_MULTICAST_LOOPBACK	= (1 << 22),
	IB_DEVICE_MEM_WINDOW_TYPE_2A		= (1 << 23),
	IB_DEVICE_MEM_WINDOW_TYPE_2B		= (1 << 24),
	IB_DEVICE_RC_IP_CSUM			= (1 << 25),
220
	/* Deprecated. Please use IB_RAW_PACKET_CAP_IP_CSUM. */
221
	IB_DEVICE_RAW_IP_CSUM			= (1 << 26),
222 223 224 225 226 227
	/*
	 * Devices should set IB_DEVICE_CROSS_CHANNEL if they
	 * support execution of WQEs that involve synchronization
	 * of I/O operations with single completion queue managed
	 * by hardware.
	 */
228
	IB_DEVICE_CROSS_CHANNEL			= (1 << 27),
229 230
	IB_DEVICE_MANAGED_FLOW_STEERING		= (1 << 29),
	IB_DEVICE_SIGNATURE_HANDOVER		= (1 << 30),
231
	IB_DEVICE_ON_DEMAND_PAGING		= (1ULL << 31),
232
	IB_DEVICE_SG_GAPS_REG			= (1ULL << 32),
233
	IB_DEVICE_VIRTUAL_FUNCTION		= (1ULL << 33),
234
	/* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */
235
	IB_DEVICE_RAW_SCATTER_FCS		= (1ULL << 34),
236
	IB_DEVICE_RDMA_NETDEV_OPA_VNIC		= (1ULL << 35),
237 238
	/* The device supports padding incoming writes to cacheline. */
	IB_DEVICE_PCI_WRITE_END_PADDING		= (1ULL << 36),
239 240 241 242 243 244 245 246 247 248 249
};

enum ib_signature_prot_cap {
	IB_PROT_T10DIF_TYPE_1 = 1,
	IB_PROT_T10DIF_TYPE_2 = 1 << 1,
	IB_PROT_T10DIF_TYPE_3 = 1 << 2,
};

enum ib_signature_guard_cap {
	IB_GUARD_T10DIF_CRC	= 1,
	IB_GUARD_T10DIF_CSUM	= 1 << 1,
L
Linus Torvalds 已提交
250 251 252 253 254 255 256 257
};

enum ib_atomic_cap {
	IB_ATOMIC_NONE,
	IB_ATOMIC_HCA,
	IB_ATOMIC_GLOB
};

258
enum ib_odp_general_cap_bits {
A
Artemy Kovalyov 已提交
259 260
	IB_ODP_SUPPORT		= 1 << 0,
	IB_ODP_SUPPORT_IMPLICIT = 1 << 1,
261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279
};

enum ib_odp_transport_cap_bits {
	IB_ODP_SUPPORT_SEND	= 1 << 0,
	IB_ODP_SUPPORT_RECV	= 1 << 1,
	IB_ODP_SUPPORT_WRITE	= 1 << 2,
	IB_ODP_SUPPORT_READ	= 1 << 3,
	IB_ODP_SUPPORT_ATOMIC	= 1 << 4,
};

struct ib_odp_caps {
	uint64_t general_caps;
	struct {
		uint32_t  rc_odp_caps;
		uint32_t  uc_odp_caps;
		uint32_t  ud_odp_caps;
	} per_transport_caps;
};

280 281 282 283 284 285 286 287 288 289
struct ib_rss_caps {
	/* Corresponding bit will be set if qp type from
	 * 'enum ib_qp_type' is supported, e.g.
	 * supported_qpts |= 1 << IB_QPT_UD
	 */
	u32 supported_qpts;
	u32 max_rwq_indirection_tables;
	u32 max_rwq_indirection_table_size;
};

A
Artemy Kovalyov 已提交
290 291 292 293 294
enum ib_tm_cap_flags {
	/*  Support tag matching on RC transport */
	IB_TM_CAP_RC		    = 1 << 0,
};

295
struct ib_tm_caps {
A
Artemy Kovalyov 已提交
296 297 298 299 300 301 302 303 304 305 306 307
	/* 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;
};

308 309 310 311 312 313
struct ib_cq_init_attr {
	unsigned int	cqe;
	int		comp_vector;
	u32		flags;
};

314 315 316 317
enum ib_cq_attr_mask {
	IB_CQ_MODERATE = 1 << 0,
};

318 319 320 321 322
struct ib_cq_caps {
	u16     max_cq_moderation_count;
	u16     max_cq_moderation_period;
};

L
Linus Torvalds 已提交
323 324
struct ib_device_attr {
	u64			fw_ver;
325
	__be64			sys_image_guid;
L
Linus Torvalds 已提交
326 327 328 329 330 331 332
	u64			max_mr_size;
	u64			page_size_cap;
	u32			vendor_id;
	u32			vendor_part_id;
	u32			hw_ver;
	int			max_qp;
	int			max_qp_wr;
333
	u64			device_cap_flags;
L
Linus Torvalds 已提交
334 335 336 337 338 339 340 341 342 343 344 345
	int			max_sge;
	int			max_sge_rd;
	int			max_cq;
	int			max_cqe;
	int			max_mr;
	int			max_pd;
	int			max_qp_rd_atom;
	int			max_ee_rd_atom;
	int			max_res_rd_atom;
	int			max_qp_init_rd_atom;
	int			max_ee_init_rd_atom;
	enum ib_atomic_cap	atomic_cap;
346
	enum ib_atomic_cap	masked_atomic_cap;
L
Linus Torvalds 已提交
347 348 349 350 351 352 353 354 355 356 357 358 359 360
	int			max_ee;
	int			max_rdd;
	int			max_mw;
	int			max_raw_ipv6_qp;
	int			max_raw_ethy_qp;
	int			max_mcast_grp;
	int			max_mcast_qp_attach;
	int			max_total_mcast_qp_attach;
	int			max_ah;
	int			max_fmr;
	int			max_map_per_fmr;
	int			max_srq;
	int			max_srq_wr;
	int			max_srq_sge;
361
	unsigned int		max_fast_reg_page_list_len;
L
Linus Torvalds 已提交
362 363
	u16			max_pkeys;
	u8			local_ca_ack_delay;
364 365
	int			sig_prot_cap;
	int			sig_guard_cap;
366
	struct ib_odp_caps	odp_caps;
367 368
	uint64_t		timestamp_mask;
	uint64_t		hca_core_clock; /* in KHZ */
369 370
	struct ib_rss_caps	rss_caps;
	u32			max_wq_type_rq;
371
	u32			raw_packet_caps; /* Use ib_raw_packet_caps enum */
372
	struct ib_tm_caps	tm_caps;
373
	struct ib_cq_caps       cq_caps;
L
Linus Torvalds 已提交
374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395
};

enum ib_mtu {
	IB_MTU_256  = 1,
	IB_MTU_512  = 2,
	IB_MTU_1024 = 3,
	IB_MTU_2048 = 4,
	IB_MTU_4096 = 5
};

static inline int ib_mtu_enum_to_int(enum ib_mtu mtu)
{
	switch (mtu) {
	case IB_MTU_256:  return  256;
	case IB_MTU_512:  return  512;
	case IB_MTU_1024: return 1024;
	case IB_MTU_2048: return 2048;
	case IB_MTU_4096: return 4096;
	default: 	  return -1;
	}
}

396 397 398 399 400 401 402 403 404 405 406 407 408 409
static inline enum ib_mtu ib_mtu_int_to_enum(int mtu)
{
	if (mtu >= 4096)
		return IB_MTU_4096;
	else if (mtu >= 2048)
		return IB_MTU_2048;
	else if (mtu >= 1024)
		return IB_MTU_1024;
	else if (mtu >= 512)
		return IB_MTU_512;
	else
		return IB_MTU_256;
}

L
Linus Torvalds 已提交
410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431
enum ib_port_state {
	IB_PORT_NOP		= 0,
	IB_PORT_DOWN		= 1,
	IB_PORT_INIT		= 2,
	IB_PORT_ARMED		= 3,
	IB_PORT_ACTIVE		= 4,
	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,
432
	IB_PORT_EXTENDED_SPEEDS_SUP             = 1 << 14,
L
Linus Torvalds 已提交
433 434 435 436 437 438 439 440 441
	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,
442
	IB_PORT_CLIENT_REG_SUP			= 1 << 25,
443
	IB_PORT_IP_BASED_GIDS			= 1 << 26,
L
Linus Torvalds 已提交
444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463
};

enum ib_port_width {
	IB_WIDTH_1X	= 1,
	IB_WIDTH_4X	= 2,
	IB_WIDTH_8X	= 4,
	IB_WIDTH_12X	= 8
};

static inline int ib_width_enum_to_int(enum ib_port_width width)
{
	switch (width) {
	case IB_WIDTH_1X:  return  1;
	case IB_WIDTH_4X:  return  4;
	case IB_WIDTH_8X:  return  8;
	case IB_WIDTH_12X: return 12;
	default: 	  return -1;
	}
}

464 465 466 467 468 469
enum ib_port_speed {
	IB_SPEED_SDR	= 1,
	IB_SPEED_DDR	= 2,
	IB_SPEED_QDR	= 4,
	IB_SPEED_FDR10	= 8,
	IB_SPEED_FDR	= 16,
N
Noa Osherovich 已提交
470 471
	IB_SPEED_EDR	= 32,
	IB_SPEED_HDR	= 64
472 473
};

474 475
/**
 * struct rdma_hw_stats
476 477 478
 * @lock - Mutex to protect parallel write access to lifespan and values
 *    of counters, which are 64bits and not guaranteeed to be written
 *    atomicaly on 32bits systems.
479 480 481 482 483 484 485 486 487 488 489 490 491 492 493
 * @timestamp - Used by the core code to track when the last update was
 * @lifespan - Used by the core code to determine how old the counters
 *   should be before being updated again.  Stored in jiffies, defaults
 *   to 10 milliseconds, drivers can override the default be specifying
 *   their own value during their allocation routine.
 * @name - Array of pointers to static names used for the counters in
 *   directory.
 * @num_counters - How many hardware counters there are.  If name is
 *   shorter than this number, a kernel oops will result.  Driver authors
 *   are encouraged to leave BUILD_BUG_ON(ARRAY_SIZE(@name) < num_counters)
 *   in their code to prevent this.
 * @value - Array of u64 counters that are accessed by the sysfs code and
 *   filled in by the drivers get_stats routine
 */
struct rdma_hw_stats {
494
	struct mutex	lock; /* Protect lifespan and values[] */
495 496 497 498 499
	unsigned long	timestamp;
	unsigned long	lifespan;
	const char * const *names;
	int		num_counters;
	u64		value[];
500 501
};

502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527
#define RDMA_HW_STATS_DEFAULT_LIFESPAN 10
/**
 * rdma_alloc_hw_stats_struct - Helper function to allocate dynamic struct
 *   for drivers.
 * @names - Array of static const char *
 * @num_counters - How many elements in array
 * @lifespan - How many milliseconds between updates
 */
static inline struct rdma_hw_stats *rdma_alloc_hw_stats_struct(
		const char * const *names, int num_counters,
		unsigned long lifespan)
{
	struct rdma_hw_stats *stats;

	stats = kzalloc(sizeof(*stats) + num_counters * sizeof(u64),
			GFP_KERNEL);
	if (!stats)
		return NULL;
	stats->names = names;
	stats->num_counters = num_counters;
	stats->lifespan = msecs_to_jiffies(lifespan);

	return stats;
}


528 529 530 531 532 533 534 535 536
/* Define bits for the various functionality this port needs to be supported by
 * the core.
 */
/* Management                           0x00000FFF */
#define RDMA_CORE_CAP_IB_MAD            0x00000001
#define RDMA_CORE_CAP_IB_SMI            0x00000002
#define RDMA_CORE_CAP_IB_CM             0x00000004
#define RDMA_CORE_CAP_IW_CM             0x00000008
#define RDMA_CORE_CAP_IB_SA             0x00000010
537
#define RDMA_CORE_CAP_OPA_MAD           0x00000020
538 539 540 541

/* Address format                       0x000FF000 */
#define RDMA_CORE_CAP_AF_IB             0x00001000
#define RDMA_CORE_CAP_ETH_AH            0x00002000
542
#define RDMA_CORE_CAP_OPA_AH            0x00004000
543 544 545 546 547

/* Protocol                             0xFFF00000 */
#define RDMA_CORE_CAP_PROT_IB           0x00100000
#define RDMA_CORE_CAP_PROT_ROCE         0x00200000
#define RDMA_CORE_CAP_PROT_IWARP        0x00400000
548
#define RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP 0x00800000
O
Or Gerlitz 已提交
549
#define RDMA_CORE_CAP_PROT_RAW_PACKET   0x01000000
O
Or Gerlitz 已提交
550
#define RDMA_CORE_CAP_PROT_USNIC        0x02000000
551 552 553 554 555 556 557 558 559 560 561 562

#define RDMA_CORE_PORT_IBA_IB          (RDMA_CORE_CAP_PROT_IB  \
					| RDMA_CORE_CAP_IB_MAD \
					| RDMA_CORE_CAP_IB_SMI \
					| RDMA_CORE_CAP_IB_CM  \
					| RDMA_CORE_CAP_IB_SA  \
					| RDMA_CORE_CAP_AF_IB)
#define RDMA_CORE_PORT_IBA_ROCE        (RDMA_CORE_CAP_PROT_ROCE \
					| RDMA_CORE_CAP_IB_MAD  \
					| RDMA_CORE_CAP_IB_CM   \
					| RDMA_CORE_CAP_AF_IB   \
					| RDMA_CORE_CAP_ETH_AH)
563 564 565 566 567 568
#define RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP			\
					(RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP \
					| RDMA_CORE_CAP_IB_MAD  \
					| RDMA_CORE_CAP_IB_CM   \
					| RDMA_CORE_CAP_AF_IB   \
					| RDMA_CORE_CAP_ETH_AH)
569 570
#define RDMA_CORE_PORT_IWARP           (RDMA_CORE_CAP_PROT_IWARP \
					| RDMA_CORE_CAP_IW_CM)
571 572
#define RDMA_CORE_PORT_INTEL_OPA       (RDMA_CORE_PORT_IBA_IB  \
					| RDMA_CORE_CAP_OPA_MAD)
573

O
Or Gerlitz 已提交
574 575
#define RDMA_CORE_PORT_RAW_PACKET	(RDMA_CORE_CAP_PROT_RAW_PACKET)

O
Or Gerlitz 已提交
576 577
#define RDMA_CORE_PORT_USNIC		(RDMA_CORE_CAP_PROT_USNIC)

L
Linus Torvalds 已提交
578
struct ib_port_attr {
579
	u64			subnet_prefix;
L
Linus Torvalds 已提交
580 581 582 583 584 585 586 587 588
	enum ib_port_state	state;
	enum ib_mtu		max_mtu;
	enum ib_mtu		active_mtu;
	int			gid_tbl_len;
	u32			port_cap_flags;
	u32			max_msg_sz;
	u32			bad_pkey_cntr;
	u32			qkey_viol_cntr;
	u16			pkey_tbl_len;
589
	u32			sm_lid;
590
	u32			lid;
L
Linus Torvalds 已提交
591 592 593 594 595 596 597 598
	u8			lmc;
	u8			max_vl_num;
	u8			sm_sl;
	u8			subnet_timeout;
	u8			init_type_reply;
	u8			active_width;
	u8			active_speed;
	u8                      phys_state;
599
	bool			grh_required;
L
Linus Torvalds 已提交
600 601 602
};

enum ib_device_modify_flags {
603 604
	IB_DEVICE_MODIFY_SYS_IMAGE_GUID	= 1 << 0,
	IB_DEVICE_MODIFY_NODE_DESC	= 1 << 1
L
Linus Torvalds 已提交
605 606
};

607 608
#define IB_DEVICE_NODE_DESC_MAX 64

L
Linus Torvalds 已提交
609 610
struct ib_device_modify {
	u64	sys_image_guid;
611
	char	node_desc[IB_DEVICE_NODE_DESC_MAX];
L
Linus Torvalds 已提交
612 613 614 615 616
};

enum ib_port_modify_flags {
	IB_PORT_SHUTDOWN		= 1,
	IB_PORT_INIT_TYPE		= (1<<2),
617 618
	IB_PORT_RESET_QKEY_CNTR		= (1<<3),
	IB_PORT_OPA_MASK_CHG		= (1<<4)
L
Linus Torvalds 已提交
619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640
};

struct ib_port_modify {
	u32	set_port_cap_mask;
	u32	clr_port_cap_mask;
	u8	init_type;
};

enum ib_event_type {
	IB_EVENT_CQ_ERR,
	IB_EVENT_QP_FATAL,
	IB_EVENT_QP_REQ_ERR,
	IB_EVENT_QP_ACCESS_ERR,
	IB_EVENT_COMM_EST,
	IB_EVENT_SQ_DRAINED,
	IB_EVENT_PATH_MIG,
	IB_EVENT_PATH_MIG_ERR,
	IB_EVENT_DEVICE_FATAL,
	IB_EVENT_PORT_ACTIVE,
	IB_EVENT_PORT_ERR,
	IB_EVENT_LID_CHANGE,
	IB_EVENT_PKEY_CHANGE,
641 642 643
	IB_EVENT_SM_CHANGE,
	IB_EVENT_SRQ_ERR,
	IB_EVENT_SRQ_LIMIT_REACHED,
644
	IB_EVENT_QP_LAST_WQE_REACHED,
O
Or Gerlitz 已提交
645 646
	IB_EVENT_CLIENT_REREGISTER,
	IB_EVENT_GID_CHANGE,
Y
Yishai Hadas 已提交
647
	IB_EVENT_WQ_FATAL,
L
Linus Torvalds 已提交
648 649
};

650
const char *__attribute_const__ ib_event_msg(enum ib_event_type event);
651

L
Linus Torvalds 已提交
652 653 654 655 656
struct ib_event {
	struct ib_device	*device;
	union {
		struct ib_cq	*cq;
		struct ib_qp	*qp;
657
		struct ib_srq	*srq;
Y
Yishai Hadas 已提交
658
		struct ib_wq	*wq;
L
Linus Torvalds 已提交
659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684
		u8		port_num;
	} element;
	enum ib_event_type	event;
};

struct ib_event_handler {
	struct ib_device *device;
	void            (*handler)(struct ib_event_handler *, struct ib_event *);
	struct list_head  list;
};

#define INIT_IB_EVENT_HANDLER(_ptr, _device, _handler)		\
	do {							\
		(_ptr)->device  = _device;			\
		(_ptr)->handler = _handler;			\
		INIT_LIST_HEAD(&(_ptr)->list);			\
	} while (0)

struct ib_global_route {
	union ib_gid	dgid;
	u32		flow_label;
	u8		sgid_index;
	u8		hop_limit;
	u8		traffic_class;
};

685
struct ib_grh {
686 687
	__be32		version_tclass_flow;
	__be16		paylen;
688 689 690 691 692 693
	u8		next_hdr;
	u8		hop_limit;
	union ib_gid	sgid;
	union ib_gid	dgid;
};

694 695 696 697 698 699 700 701 702 703 704
union rdma_network_hdr {
	struct ib_grh ibgrh;
	struct {
		/* The IB spec states that if it's IPv4, the header
		 * is located in the last 20 bytes of the header.
		 */
		u8		reserved[20];
		struct iphdr	roce4grh;
	};
};

705 706
#define IB_QPN_MASK		0xFFFFFF

L
Linus Torvalds 已提交
707 708 709 710
enum {
	IB_MULTICAST_QPN = 0xffffff
};

711
#define IB_LID_PERMISSIVE	cpu_to_be16(0xFFFF)
712
#define IB_MULTICAST_LID_BASE	cpu_to_be16(0xC000)
713

L
Linus Torvalds 已提交
714 715 716 717
enum ib_ah_flags {
	IB_AH_GRH	= 1
};

718 719 720 721 722 723 724 725 726 727
enum ib_rate {
	IB_RATE_PORT_CURRENT = 0,
	IB_RATE_2_5_GBPS = 2,
	IB_RATE_5_GBPS   = 5,
	IB_RATE_10_GBPS  = 3,
	IB_RATE_20_GBPS  = 6,
	IB_RATE_30_GBPS  = 4,
	IB_RATE_40_GBPS  = 7,
	IB_RATE_60_GBPS  = 8,
	IB_RATE_80_GBPS  = 9,
728 729 730 731 732 733 734 735 736
	IB_RATE_120_GBPS = 10,
	IB_RATE_14_GBPS  = 11,
	IB_RATE_56_GBPS  = 12,
	IB_RATE_112_GBPS = 13,
	IB_RATE_168_GBPS = 14,
	IB_RATE_25_GBPS  = 15,
	IB_RATE_100_GBPS = 16,
	IB_RATE_200_GBPS = 17,
	IB_RATE_300_GBPS = 18
737 738 739 740 741 742 743 744
};

/**
 * ib_rate_to_mult - Convert the IB rate enum to a multiple of the
 * base rate of 2.5 Gbit/sec.  For example, IB_RATE_5_GBPS will be
 * converted to 2, since 5 Gbit/sec is 2 * 2.5 Gbit/sec.
 * @rate: rate to convert.
 */
745
__attribute_const__ int ib_rate_to_mult(enum ib_rate rate);
746

747 748 749 750 751
/**
 * ib_rate_to_mbps - Convert the IB rate enum to Mbps.
 * For example, IB_RATE_2_5_GBPS will be converted to 2500.
 * @rate: rate to convert.
 */
752
__attribute_const__ int ib_rate_to_mbps(enum ib_rate rate);
753

754 755

/**
S
Sagi Grimberg 已提交
756 757 758 759 760 761
 * enum ib_mr_type - memory region type
 * @IB_MR_TYPE_MEM_REG:       memory region that is used for
 *                            normal registration
 * @IB_MR_TYPE_SIGNATURE:     memory region that is used for
 *                            signature operations (data-integrity
 *                            capable regions)
762 763 764 765
 * @IB_MR_TYPE_SG_GAPS:       memory region that is capable to
 *                            register any arbitrary sg lists (without
 *                            the normal mr constraints - see
 *                            ib_map_mr_sg)
766
 */
S
Sagi Grimberg 已提交
767 768 769
enum ib_mr_type {
	IB_MR_TYPE_MEM_REG,
	IB_MR_TYPE_SIGNATURE,
770
	IB_MR_TYPE_SG_GAPS,
771 772
};

773
/**
774 775 776
 * Signature types
 * IB_SIG_TYPE_NONE: Unprotected.
 * IB_SIG_TYPE_T10_DIF: Type T10-DIF
777
 */
778 779 780
enum ib_signature_type {
	IB_SIG_TYPE_NONE,
	IB_SIG_TYPE_T10_DIF,
781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800
};

/**
 * Signature T10-DIF block-guard types
 * IB_T10DIF_CRC: Corresponds to T10-PI mandated CRC checksum rules.
 * IB_T10DIF_CSUM: Corresponds to IP checksum rules.
 */
enum ib_t10_dif_bg_type {
	IB_T10DIF_CRC,
	IB_T10DIF_CSUM
};

/**
 * struct ib_t10_dif_domain - Parameters specific for T10-DIF
 *     domain.
 * @bg_type: T10-DIF block guard type (CRC|CSUM)
 * @pi_interval: protection information interval.
 * @bg: seed of guard computation.
 * @app_tag: application tag of guard block
 * @ref_tag: initial guard block reference tag.
801 802 803 804
 * @ref_remap: Indicate wethear the reftag increments each block
 * @app_escape: Indicate to skip block check if apptag=0xffff
 * @ref_escape: Indicate to skip block check if reftag=0xffffffff
 * @apptag_check_mask: check bitmask of application tag.
805 806 807 808 809 810 811
 */
struct ib_t10_dif_domain {
	enum ib_t10_dif_bg_type bg_type;
	u16			pi_interval;
	u16			bg;
	u16			app_tag;
	u32			ref_tag;
812 813 814 815
	bool			ref_remap;
	bool			app_escape;
	bool			ref_escape;
	u16			apptag_check_mask;
816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876
};

/**
 * struct ib_sig_domain - Parameters for signature domain
 * @sig_type: specific signauture type
 * @sig: union of all signature domain attributes that may
 *     be used to set domain layout.
 */
struct ib_sig_domain {
	enum ib_signature_type sig_type;
	union {
		struct ib_t10_dif_domain dif;
	} sig;
};

/**
 * struct ib_sig_attrs - Parameters for signature handover operation
 * @check_mask: bitmask for signature byte check (8 bytes)
 * @mem: memory domain layout desciptor.
 * @wire: wire domain layout desciptor.
 */
struct ib_sig_attrs {
	u8			check_mask;
	struct ib_sig_domain	mem;
	struct ib_sig_domain	wire;
};

enum ib_sig_err_type {
	IB_SIG_BAD_GUARD,
	IB_SIG_BAD_REFTAG,
	IB_SIG_BAD_APPTAG,
};

/**
 * struct ib_sig_err - signature error descriptor
 */
struct ib_sig_err {
	enum ib_sig_err_type	err_type;
	u32			expected;
	u32			actual;
	u64			sig_err_offset;
	u32			key;
};

enum ib_mr_status_check {
	IB_MR_CHECK_SIG_STATUS = 1,
};

/**
 * struct ib_mr_status - Memory region status container
 *
 * @fail_status: Bitmask of MR checks status. For each
 *     failed check a corresponding status bit is set.
 * @sig_err: Additional info for IB_MR_CEHCK_SIG_STATUS
 *     failure.
 */
struct ib_mr_status {
	u32		    fail_status;
	struct ib_sig_err   sig_err;
};

877 878 879 880 881
/**
 * mult_to_ib_rate - Convert a multiple of 2.5 Gbit/sec to an IB rate
 * enum.
 * @mult: multiple to convert.
 */
882
__attribute_const__ enum ib_rate mult_to_ib_rate(int mult);
883

884
enum rdma_ah_attr_type {
885
	RDMA_AH_ATTR_TYPE_UNDEFINED,
886 887
	RDMA_AH_ATTR_TYPE_IB,
	RDMA_AH_ATTR_TYPE_ROCE,
888
	RDMA_AH_ATTR_TYPE_OPA,
889 890 891 892 893 894 895 896 897 898 899
};

struct ib_ah_attr {
	u16			dlid;
	u8			src_path_bits;
};

struct roce_ah_attr {
	u8			dmac[ETH_ALEN];
};

900 901 902
struct opa_ah_attr {
	u32			dlid;
	u8			src_path_bits;
903
	bool			make_grd;
904 905
};

906
struct rdma_ah_attr {
L
Linus Torvalds 已提交
907 908 909 910
	struct ib_global_route	grh;
	u8			sl;
	u8			static_rate;
	u8			port_num;
911 912 913 914 915
	u8			ah_flags;
	enum rdma_ah_attr_type type;
	union {
		struct ib_ah_attr ib;
		struct roce_ah_attr roce;
916
		struct opa_ah_attr opa;
917
	};
L
Linus Torvalds 已提交
918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944
};

enum ib_wc_status {
	IB_WC_SUCCESS,
	IB_WC_LOC_LEN_ERR,
	IB_WC_LOC_QP_OP_ERR,
	IB_WC_LOC_EEC_OP_ERR,
	IB_WC_LOC_PROT_ERR,
	IB_WC_WR_FLUSH_ERR,
	IB_WC_MW_BIND_ERR,
	IB_WC_BAD_RESP_ERR,
	IB_WC_LOC_ACCESS_ERR,
	IB_WC_REM_INV_REQ_ERR,
	IB_WC_REM_ACCESS_ERR,
	IB_WC_REM_OP_ERR,
	IB_WC_RETRY_EXC_ERR,
	IB_WC_RNR_RETRY_EXC_ERR,
	IB_WC_LOC_RDD_VIOL_ERR,
	IB_WC_REM_INV_RD_REQ_ERR,
	IB_WC_REM_ABORT_ERR,
	IB_WC_INV_EECN_ERR,
	IB_WC_INV_EEC_STATE_ERR,
	IB_WC_FATAL_ERR,
	IB_WC_RESP_TIMEOUT_ERR,
	IB_WC_GENERAL_ERR
};

945
const char *__attribute_const__ ib_wc_status_msg(enum ib_wc_status status);
946

L
Linus Torvalds 已提交
947 948 949 950 951 952
enum ib_wc_opcode {
	IB_WC_SEND,
	IB_WC_RDMA_WRITE,
	IB_WC_RDMA_READ,
	IB_WC_COMP_SWAP,
	IB_WC_FETCH_ADD,
E
Eli Cohen 已提交
953
	IB_WC_LSO,
954
	IB_WC_LOCAL_INV,
955
	IB_WC_REG_MR,
956 957
	IB_WC_MASKED_COMP_SWAP,
	IB_WC_MASKED_FETCH_ADD,
L
Linus Torvalds 已提交
958 959 960 961 962 963 964 965 966 967
/*
 * Set value of IB_WC_RECV so consumers can test if a completion is a
 * receive by testing (opcode & IB_WC_RECV).
 */
	IB_WC_RECV			= 1 << 7,
	IB_WC_RECV_RDMA_WITH_IMM
};

enum ib_wc_flags {
	IB_WC_GRH		= 1,
968 969
	IB_WC_WITH_IMM		= (1<<1),
	IB_WC_WITH_INVALIDATE	= (1<<2),
970
	IB_WC_IP_CSUM_OK	= (1<<3),
971 972
	IB_WC_WITH_SMAC		= (1<<4),
	IB_WC_WITH_VLAN		= (1<<5),
973
	IB_WC_WITH_NETWORK_HDR_TYPE	= (1<<6),
L
Linus Torvalds 已提交
974 975 976
};

struct ib_wc {
977 978 979 980
	union {
		u64		wr_id;
		struct ib_cqe	*wr_cqe;
	};
L
Linus Torvalds 已提交
981 982 983 984
	enum ib_wc_status	status;
	enum ib_wc_opcode	opcode;
	u32			vendor_err;
	u32			byte_len;
985
	struct ib_qp	       *qp;
986 987 988 989
	union {
		__be32		imm_data;
		u32		invalidate_rkey;
	} ex;
L
Linus Torvalds 已提交
990
	u32			src_qp;
991
	u32			slid;
L
Linus Torvalds 已提交
992 993 994 995 996
	int			wc_flags;
	u16			pkey_index;
	u8			sl;
	u8			dlid_path_bits;
	u8			port_num;	/* valid only for DR SMPs on switches */
997 998
	u8			smac[ETH_ALEN];
	u16			vlan_id;
999
	u8			network_hdr_type;
L
Linus Torvalds 已提交
1000 1001
};

1002 1003 1004 1005 1006
enum ib_cq_notify_flags {
	IB_CQ_SOLICITED			= 1 << 0,
	IB_CQ_NEXT_COMP			= 1 << 1,
	IB_CQ_SOLICITED_MASK		= IB_CQ_SOLICITED | IB_CQ_NEXT_COMP,
	IB_CQ_REPORT_MISSED_EVENTS	= 1 << 2,
L
Linus Torvalds 已提交
1007 1008
};

S
Sean Hefty 已提交
1009
enum ib_srq_type {
S
Sean Hefty 已提交
1010
	IB_SRQT_BASIC,
1011 1012
	IB_SRQT_XRC,
	IB_SRQT_TM,
S
Sean Hefty 已提交
1013 1014
};

1015 1016
static inline bool ib_srq_has_cq(enum ib_srq_type srq_type)
{
1017 1018
	return srq_type == IB_SRQT_XRC ||
	       srq_type == IB_SRQT_TM;
1019 1020
}

1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035
enum ib_srq_attr_mask {
	IB_SRQ_MAX_WR	= 1 << 0,
	IB_SRQ_LIMIT	= 1 << 1,
};

struct ib_srq_attr {
	u32	max_wr;
	u32	max_sge;
	u32	srq_limit;
};

struct ib_srq_init_attr {
	void		      (*event_handler)(struct ib_event *, void *);
	void		       *srq_context;
	struct ib_srq_attr	attr;
S
Sean Hefty 已提交
1036
	enum ib_srq_type	srq_type;
S
Sean Hefty 已提交
1037

1038 1039 1040 1041 1042 1043
	struct {
		struct ib_cq   *cq;
		union {
			struct {
				struct ib_xrcd *xrcd;
			} xrc;
1044 1045 1046 1047

			struct {
				u32		max_num_tags;
			} tag_matching;
1048
		};
S
Sean Hefty 已提交
1049
	} ext;
1050 1051
};

L
Linus Torvalds 已提交
1052 1053 1054 1055 1056 1057
struct ib_qp_cap {
	u32	max_send_wr;
	u32	max_recv_wr;
	u32	max_send_sge;
	u32	max_recv_sge;
	u32	max_inline_data;
1058 1059 1060 1061 1062 1063 1064

	/*
	 * Maximum number of rdma_rw_ctx structures in flight at a time.
	 * ib_create_qp() will calculate the right amount of neededed WRs
	 * and MRs based on this.
	 */
	u32	max_rdma_ctxs;
L
Linus Torvalds 已提交
1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084
};

enum ib_sig_type {
	IB_SIGNAL_ALL_WR,
	IB_SIGNAL_REQ_WR
};

enum ib_qp_type {
	/*
	 * IB_QPT_SMI and IB_QPT_GSI have to be the first two entries
	 * here (and in that order) since the MAD layer uses them as
	 * indices into a 2-entry table.
	 */
	IB_QPT_SMI,
	IB_QPT_GSI,

	IB_QPT_RC,
	IB_QPT_UC,
	IB_QPT_UD,
	IB_QPT_RAW_IPV6,
S
Sean Hefty 已提交
1085
	IB_QPT_RAW_ETHERTYPE,
O
Or Gerlitz 已提交
1086
	IB_QPT_RAW_PACKET = 8,
S
Sean Hefty 已提交
1087 1088
	IB_QPT_XRC_INI = 9,
	IB_QPT_XRC_TGT,
1089
	IB_QPT_MAX,
M
Moni Shoua 已提交
1090
	IB_QPT_DRIVER = 0xFF,
1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104
	/* Reserve a range for qp types internal to the low level driver.
	 * These qp types will not be visible at the IB core layer, so the
	 * IB_QPT_MAX usages should not be affected in the core layer
	 */
	IB_QPT_RESERVED1 = 0x1000,
	IB_QPT_RESERVED2,
	IB_QPT_RESERVED3,
	IB_QPT_RESERVED4,
	IB_QPT_RESERVED5,
	IB_QPT_RESERVED6,
	IB_QPT_RESERVED7,
	IB_QPT_RESERVED8,
	IB_QPT_RESERVED9,
	IB_QPT_RESERVED10,
L
Linus Torvalds 已提交
1105 1106
};

1107
enum ib_qp_create_flags {
1108 1109
	IB_QP_CREATE_IPOIB_UD_LSO		= 1 << 0,
	IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK	= 1 << 1,
1110 1111 1112
	IB_QP_CREATE_CROSS_CHANNEL              = 1 << 2,
	IB_QP_CREATE_MANAGED_SEND               = 1 << 3,
	IB_QP_CREATE_MANAGED_RECV               = 1 << 4,
1113
	IB_QP_CREATE_NETIF_QP			= 1 << 5,
1114
	IB_QP_CREATE_SIGNATURE_EN		= 1 << 6,
1115
	/* FREE					= 1 << 7, */
1116
	IB_QP_CREATE_SCATTER_FCS		= 1 << 8,
1117
	IB_QP_CREATE_CVLAN_STRIPPING		= 1 << 9,
1118
	IB_QP_CREATE_SOURCE_QPN			= 1 << 10,
1119
	IB_QP_CREATE_PCI_WRITE_END_PADDING	= 1 << 11,
1120 1121 1122
	/* reserve bits 26-31 for low level drivers' internal use */
	IB_QP_CREATE_RESERVED_START		= 1 << 26,
	IB_QP_CREATE_RESERVED_END		= 1 << 31,
1123 1124
};

1125 1126 1127 1128 1129
/*
 * Note: users may not call ib_close_qp or ib_destroy_qp from the event_handler
 * callback to destroy the passed in QP.
 */

L
Linus Torvalds 已提交
1130 1131 1132 1133 1134 1135
struct ib_qp_init_attr {
	void                  (*event_handler)(struct ib_event *, void *);
	void		       *qp_context;
	struct ib_cq	       *send_cq;
	struct ib_cq	       *recv_cq;
	struct ib_srq	       *srq;
S
Sean Hefty 已提交
1136
	struct ib_xrcd	       *xrcd;     /* XRC TGT QPs only */
L
Linus Torvalds 已提交
1137 1138 1139
	struct ib_qp_cap	cap;
	enum ib_sig_type	sq_sig_type;
	enum ib_qp_type		qp_type;
1140
	enum ib_qp_create_flags	create_flags;
1141 1142 1143 1144 1145

	/*
	 * Only needed for special QP types, or when using the RW API.
	 */
	u8			port_num;
1146
	struct ib_rwq_ind_table *rwq_ind_tbl;
1147
	u32			source_qpn;
L
Linus Torvalds 已提交
1148 1149
};

1150 1151 1152 1153 1154 1155 1156
struct ib_qp_open_attr {
	void                  (*event_handler)(struct ib_event *, void *);
	void		       *qp_context;
	u32			qp_num;
	enum ib_qp_type		qp_type;
};

L
Linus Torvalds 已提交
1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212
enum ib_rnr_timeout {
	IB_RNR_TIMER_655_36 =  0,
	IB_RNR_TIMER_000_01 =  1,
	IB_RNR_TIMER_000_02 =  2,
	IB_RNR_TIMER_000_03 =  3,
	IB_RNR_TIMER_000_04 =  4,
	IB_RNR_TIMER_000_06 =  5,
	IB_RNR_TIMER_000_08 =  6,
	IB_RNR_TIMER_000_12 =  7,
	IB_RNR_TIMER_000_16 =  8,
	IB_RNR_TIMER_000_24 =  9,
	IB_RNR_TIMER_000_32 = 10,
	IB_RNR_TIMER_000_48 = 11,
	IB_RNR_TIMER_000_64 = 12,
	IB_RNR_TIMER_000_96 = 13,
	IB_RNR_TIMER_001_28 = 14,
	IB_RNR_TIMER_001_92 = 15,
	IB_RNR_TIMER_002_56 = 16,
	IB_RNR_TIMER_003_84 = 17,
	IB_RNR_TIMER_005_12 = 18,
	IB_RNR_TIMER_007_68 = 19,
	IB_RNR_TIMER_010_24 = 20,
	IB_RNR_TIMER_015_36 = 21,
	IB_RNR_TIMER_020_48 = 22,
	IB_RNR_TIMER_030_72 = 23,
	IB_RNR_TIMER_040_96 = 24,
	IB_RNR_TIMER_061_44 = 25,
	IB_RNR_TIMER_081_92 = 26,
	IB_RNR_TIMER_122_88 = 27,
	IB_RNR_TIMER_163_84 = 28,
	IB_RNR_TIMER_245_76 = 29,
	IB_RNR_TIMER_327_68 = 30,
	IB_RNR_TIMER_491_52 = 31
};

enum ib_qp_attr_mask {
	IB_QP_STATE			= 1,
	IB_QP_CUR_STATE			= (1<<1),
	IB_QP_EN_SQD_ASYNC_NOTIFY	= (1<<2),
	IB_QP_ACCESS_FLAGS		= (1<<3),
	IB_QP_PKEY_INDEX		= (1<<4),
	IB_QP_PORT			= (1<<5),
	IB_QP_QKEY			= (1<<6),
	IB_QP_AV			= (1<<7),
	IB_QP_PATH_MTU			= (1<<8),
	IB_QP_TIMEOUT			= (1<<9),
	IB_QP_RETRY_CNT			= (1<<10),
	IB_QP_RNR_RETRY			= (1<<11),
	IB_QP_RQ_PSN			= (1<<12),
	IB_QP_MAX_QP_RD_ATOMIC		= (1<<13),
	IB_QP_ALT_PATH			= (1<<14),
	IB_QP_MIN_RNR_TIMER		= (1<<15),
	IB_QP_SQ_PSN			= (1<<16),
	IB_QP_MAX_DEST_RD_ATOMIC	= (1<<17),
	IB_QP_PATH_MIG_STATE		= (1<<18),
	IB_QP_CAP			= (1<<19),
1213
	IB_QP_DEST_QPN			= (1<<20),
1214 1215 1216 1217
	IB_QP_RESERVED1			= (1<<21),
	IB_QP_RESERVED2			= (1<<22),
	IB_QP_RESERVED3			= (1<<23),
	IB_QP_RESERVED4			= (1<<24),
1218
	IB_QP_RATE_LIMIT		= (1<<25),
L
Linus Torvalds 已提交
1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236
};

enum ib_qp_state {
	IB_QPS_RESET,
	IB_QPS_INIT,
	IB_QPS_RTR,
	IB_QPS_RTS,
	IB_QPS_SQD,
	IB_QPS_SQE,
	IB_QPS_ERR
};

enum ib_mig_state {
	IB_MIG_MIGRATED,
	IB_MIG_REARM,
	IB_MIG_ARMED
};

1237 1238 1239 1240 1241
enum ib_mw_type {
	IB_MW_TYPE_1 = 1,
	IB_MW_TYPE_2 = 2
};

L
Linus Torvalds 已提交
1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252
struct ib_qp_attr {
	enum ib_qp_state	qp_state;
	enum ib_qp_state	cur_qp_state;
	enum ib_mtu		path_mtu;
	enum ib_mig_state	path_mig_state;
	u32			qkey;
	u32			rq_psn;
	u32			sq_psn;
	u32			dest_qp_num;
	int			qp_access_flags;
	struct ib_qp_cap	cap;
1253 1254
	struct rdma_ah_attr	ah_attr;
	struct rdma_ah_attr	alt_ah_attr;
L
Linus Torvalds 已提交
1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267
	u16			pkey_index;
	u16			alt_pkey_index;
	u8			en_sqd_async_notify;
	u8			sq_draining;
	u8			max_rd_atomic;
	u8			max_dest_rd_atomic;
	u8			min_rnr_timer;
	u8			port_num;
	u8			timeout;
	u8			retry_cnt;
	u8			rnr_retry;
	u8			alt_port_num;
	u8			alt_timeout;
1268
	u32			rate_limit;
L
Linus Torvalds 已提交
1269 1270 1271 1272 1273 1274 1275 1276 1277
};

enum ib_wr_opcode {
	IB_WR_RDMA_WRITE,
	IB_WR_RDMA_WRITE_WITH_IMM,
	IB_WR_SEND,
	IB_WR_SEND_WITH_IMM,
	IB_WR_RDMA_READ,
	IB_WR_ATOMIC_CMP_AND_SWP,
E
Eli Cohen 已提交
1278
	IB_WR_ATOMIC_FETCH_AND_ADD,
1279 1280
	IB_WR_LSO,
	IB_WR_SEND_WITH_INV,
1281 1282
	IB_WR_RDMA_READ_WITH_INV,
	IB_WR_LOCAL_INV,
1283
	IB_WR_REG_MR,
1284 1285
	IB_WR_MASKED_ATOMIC_CMP_AND_SWP,
	IB_WR_MASKED_ATOMIC_FETCH_AND_ADD,
1286
	IB_WR_REG_SIG_MR,
1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299
	/* reserve values for low level drivers' internal use.
	 * These values will not be used at all in the ib core layer.
	 */
	IB_WR_RESERVED1 = 0xf0,
	IB_WR_RESERVED2,
	IB_WR_RESERVED3,
	IB_WR_RESERVED4,
	IB_WR_RESERVED5,
	IB_WR_RESERVED6,
	IB_WR_RESERVED7,
	IB_WR_RESERVED8,
	IB_WR_RESERVED9,
	IB_WR_RESERVED10,
L
Linus Torvalds 已提交
1300 1301 1302 1303 1304 1305
};

enum ib_send_flags {
	IB_SEND_FENCE		= 1,
	IB_SEND_SIGNALED	= (1<<1),
	IB_SEND_SOLICITED	= (1<<2),
1306
	IB_SEND_INLINE		= (1<<3),
1307 1308 1309 1310 1311
	IB_SEND_IP_CSUM		= (1<<4),

	/* reserve bits 26-31 for low level drivers' internal use */
	IB_SEND_RESERVED_START	= (1 << 26),
	IB_SEND_RESERVED_END	= (1 << 31),
L
Linus Torvalds 已提交
1312 1313 1314 1315 1316 1317 1318 1319
};

struct ib_sge {
	u64	addr;
	u32	length;
	u32	lkey;
};

1320 1321 1322 1323
struct ib_cqe {
	void (*done)(struct ib_cq *cq, struct ib_wc *wc);
};

L
Linus Torvalds 已提交
1324 1325
struct ib_send_wr {
	struct ib_send_wr      *next;
1326 1327 1328 1329
	union {
		u64		wr_id;
		struct ib_cqe	*wr_cqe;
	};
L
Linus Torvalds 已提交
1330 1331 1332 1333
	struct ib_sge	       *sg_list;
	int			num_sge;
	enum ib_wr_opcode	opcode;
	int			send_flags;
1334 1335 1336 1337
	union {
		__be32		imm_data;
		u32		invalidate_rkey;
	} ex;
L
Linus Torvalds 已提交
1338 1339
};

C
Christoph Hellwig 已提交
1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382
struct ib_rdma_wr {
	struct ib_send_wr	wr;
	u64			remote_addr;
	u32			rkey;
};

static inline struct ib_rdma_wr *rdma_wr(struct ib_send_wr *wr)
{
	return container_of(wr, struct ib_rdma_wr, wr);
}

struct ib_atomic_wr {
	struct ib_send_wr	wr;
	u64			remote_addr;
	u64			compare_add;
	u64			swap;
	u64			compare_add_mask;
	u64			swap_mask;
	u32			rkey;
};

static inline struct ib_atomic_wr *atomic_wr(struct ib_send_wr *wr)
{
	return container_of(wr, struct ib_atomic_wr, wr);
}

struct ib_ud_wr {
	struct ib_send_wr	wr;
	struct ib_ah		*ah;
	void			*header;
	int			hlen;
	int			mss;
	u32			remote_qpn;
	u32			remote_qkey;
	u16			pkey_index; /* valid for GSI only */
	u8			port_num;   /* valid for DR SMPs on switch only */
};

static inline struct ib_ud_wr *ud_wr(struct ib_send_wr *wr)
{
	return container_of(wr, struct ib_ud_wr, wr);
}

1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394
struct ib_reg_wr {
	struct ib_send_wr	wr;
	struct ib_mr		*mr;
	u32			key;
	int			access;
};

static inline struct ib_reg_wr *reg_wr(struct ib_send_wr *wr)
{
	return container_of(wr, struct ib_reg_wr, wr);
}

C
Christoph Hellwig 已提交
1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407
struct ib_sig_handover_wr {
	struct ib_send_wr	wr;
	struct ib_sig_attrs    *sig_attrs;
	struct ib_mr	       *sig_mr;
	int			access_flags;
	struct ib_sge	       *prot;
};

static inline struct ib_sig_handover_wr *sig_handover_wr(struct ib_send_wr *wr)
{
	return container_of(wr, struct ib_sig_handover_wr, wr);
}

L
Linus Torvalds 已提交
1408 1409
struct ib_recv_wr {
	struct ib_recv_wr      *next;
1410 1411 1412 1413
	union {
		u64		wr_id;
		struct ib_cqe	*wr_cqe;
	};
L
Linus Torvalds 已提交
1414 1415 1416 1417 1418 1419 1420 1421 1422
	struct ib_sge	       *sg_list;
	int			num_sge;
};

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),
1423
	IB_ACCESS_MW_BIND	= (1<<4),
1424 1425
	IB_ZERO_BASED		= (1<<5),
	IB_ACCESS_ON_DEMAND     = (1<<6),
1426
	IB_ACCESS_HUGETLB	= (1<<7),
L
Linus Torvalds 已提交
1427 1428
};

1429 1430 1431 1432
/*
 * XXX: these are apparently used for ->rereg_user_mr, no idea why they
 * are hidden here instead of a uapi header!
 */
L
Linus Torvalds 已提交
1433 1434 1435
enum ib_mr_rereg_flags {
	IB_MR_REREG_TRANS	= 1,
	IB_MR_REREG_PD		= (1<<1),
1436 1437
	IB_MR_REREG_ACCESS	= (1<<2),
	IB_MR_REREG_SUPPORTED	= ((IB_MR_REREG_ACCESS << 1) - 1)
L
Linus Torvalds 已提交
1438 1439 1440 1441 1442
};

struct ib_fmr_attr {
	int	max_pages;
	int	max_maps;
1443
	u8	page_shift;
L
Linus Torvalds 已提交
1444 1445
};

1446 1447
struct ib_umem;

M
Matan Barak 已提交
1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458
enum rdma_remove_reason {
	/* Userspace requested uobject deletion. 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,
};

1459 1460 1461 1462 1463 1464
struct ib_rdmacg_object {
#ifdef CONFIG_CGROUP_RDMA
	struct rdma_cgroup	*cg;		/* owner rdma cgroup */
#endif
};

1465 1466
struct ib_ucontext {
	struct ib_device       *device;
1467
	struct ib_uverbs_file  *ufile;
1468
	int			closing;
1469

M
Matan Barak 已提交
1470 1471 1472 1473 1474 1475 1476
	/* 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;

1477
	struct pid             *tgid;
1478
#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
1479
	struct rb_root_cached   umem_tree;
1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493
	/*
	 * Protects .umem_rbroot and tree, as well as odp_mrs_count and
	 * mmu notifiers registration.
	 */
	struct rw_semaphore	umem_rwsem;
	void (*invalidate_range)(struct ib_umem *umem,
				 unsigned long start, unsigned long end);

	struct mmu_notifier	mn;
	atomic_t		notifier_count;
	/* A list of umems that don't have private mmu notifier counters yet. */
	struct list_head	no_private_counters;
	int                     odp_mrs_count;
#endif
1494 1495

	struct ib_rdmacg_object	cg_obj;
1496 1497 1498 1499 1500
};

struct ib_uobject {
	u64			user_handle;	/* handle given to us by userspace */
	struct ib_ucontext     *context;	/* associated user context */
1501
	void		       *object;		/* containing object */
1502
	struct list_head	list;		/* link to context's list */
1503
	struct ib_rdmacg_object	cg_obj;		/* rdmacg object */
1504
	int			id;		/* index into kernel idr */
1505
	struct kref		ref;
M
Matan Barak 已提交
1506
	atomic_t		usecnt;		/* protects exclusive access */
1507
	struct rcu_head		rcu;		/* kfree_rcu() overhead */
M
Matan Barak 已提交
1508 1509

	const struct uverbs_obj_type *type;
1510 1511
};

1512 1513 1514 1515
struct ib_uobject_file {
	struct ib_uobject	uobj;
	/* ufile contains the lock between context release and file close */
	struct ib_uverbs_file	*ufile;
1516 1517 1518
};

struct ib_udata {
1519
	const void __user *inbuf;
1520 1521 1522 1523 1524
	void __user *outbuf;
	size_t       inlen;
	size_t       outlen;
};

L
Linus Torvalds 已提交
1525
struct ib_pd {
1526
	u32			local_dma_lkey;
1527
	u32			flags;
1528 1529 1530
	struct ib_device       *device;
	struct ib_uobject      *uobject;
	atomic_t          	usecnt; /* count all resources */
1531

1532 1533
	u32			unsafe_global_rkey;

1534 1535 1536 1537
	/*
	 * Implementation details of the RDMA core, don't use in drivers:
	 */
	struct ib_mr	       *__internal_mr;
1538
	struct rdma_restrack_entry res;
L
Linus Torvalds 已提交
1539 1540
};

S
Sean Hefty 已提交
1541 1542
struct ib_xrcd {
	struct ib_device       *device;
1543
	atomic_t		usecnt; /* count all exposed resources */
1544
	struct inode	       *inode;
1545 1546 1547

	struct mutex		tgt_qp_mutex;
	struct list_head	tgt_qp_list;
1548 1549 1550 1551
	/*
	 * Implementation details of the RDMA core, don't use in drivers:
	 */
	struct rdma_restrack_entry res;
S
Sean Hefty 已提交
1552 1553
};

L
Linus Torvalds 已提交
1554 1555 1556
struct ib_ah {
	struct ib_device	*device;
	struct ib_pd		*pd;
1557
	struct ib_uobject	*uobject;
1558
	enum rdma_ah_attr_type	type;
L
Linus Torvalds 已提交
1559 1560 1561 1562
};

typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context);

1563 1564 1565 1566 1567 1568
enum ib_poll_context {
	IB_POLL_DIRECT,		/* caller context, no hw completions */
	IB_POLL_SOFTIRQ,	/* poll from softirq context */
	IB_POLL_WORKQUEUE,	/* poll from workqueue */
};

L
Linus Torvalds 已提交
1569
struct ib_cq {
1570 1571 1572 1573
	struct ib_device       *device;
	struct ib_uobject      *uobject;
	ib_comp_handler   	comp_handler;
	void                  (*event_handler)(struct ib_event *, void *);
1574
	void                   *cq_context;
1575 1576
	int               	cqe;
	atomic_t          	usecnt; /* count number of work queues */
1577 1578 1579 1580 1581 1582
	enum ib_poll_context	poll_ctx;
	struct ib_wc		*wc;
	union {
		struct irq_poll		iop;
		struct work_struct	work;
	};
1583 1584 1585 1586
	/*
	 * Implementation details of the RDMA core, don't use in drivers:
	 */
	struct rdma_restrack_entry res;
L
Linus Torvalds 已提交
1587 1588 1589
};

struct ib_srq {
1590 1591 1592 1593 1594
	struct ib_device       *device;
	struct ib_pd	       *pd;
	struct ib_uobject      *uobject;
	void		      (*event_handler)(struct ib_event *, void *);
	void		       *srq_context;
S
Sean Hefty 已提交
1595
	enum ib_srq_type	srq_type;
L
Linus Torvalds 已提交
1596
	atomic_t		usecnt;
S
Sean Hefty 已提交
1597

1598 1599 1600 1601 1602 1603 1604 1605
	struct {
		struct ib_cq   *cq;
		union {
			struct {
				struct ib_xrcd *xrcd;
				u32		srq_num;
			} xrc;
		};
S
Sean Hefty 已提交
1606
	} ext;
L
Linus Torvalds 已提交
1607 1608
};

1609 1610 1611 1612 1613 1614 1615 1616 1617 1618
enum ib_raw_packet_caps {
	/* Strip cvlan from incoming packet and report it in the matching work
	 * completion is supported.
	 */
	IB_RAW_PACKET_CAP_CVLAN_STRIPPING	= (1 << 0),
	/* Scatter FCS field of an incoming packet to host memory is supported.
	 */
	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),
1619 1620 1621 1622
	/* 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),
1623 1624
};

1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647
enum ib_wq_type {
	IB_WQT_RQ
};

enum ib_wq_state {
	IB_WQS_RESET,
	IB_WQS_RDY,
	IB_WQS_ERR
};

struct ib_wq {
	struct ib_device       *device;
	struct ib_uobject      *uobject;
	void		    *wq_context;
	void		    (*event_handler)(struct ib_event *, void *);
	struct ib_pd	       *pd;
	struct ib_cq	       *cq;
	u32		wq_num;
	enum ib_wq_state       state;
	enum ib_wq_type	wq_type;
	atomic_t		usecnt;
};

1648 1649
enum ib_wq_flags {
	IB_WQ_FLAGS_CVLAN_STRIPPING	= 1 << 0,
1650
	IB_WQ_FLAGS_SCATTER_FCS		= 1 << 1,
1651
	IB_WQ_FLAGS_DELAY_DROP		= 1 << 2,
1652
	IB_WQ_FLAGS_PCI_WRITE_END_PADDING = 1 << 3,
1653 1654
};

1655 1656 1657 1658 1659 1660 1661
struct ib_wq_init_attr {
	void		       *wq_context;
	enum ib_wq_type	wq_type;
	u32		max_wr;
	u32		max_sge;
	struct	ib_cq	       *cq;
	void		    (*event_handler)(struct ib_event *, void *);
1662
	u32		create_flags; /* Use enum ib_wq_flags */
1663 1664 1665
};

enum ib_wq_attr_mask {
1666 1667 1668
	IB_WQ_STATE		= 1 << 0,
	IB_WQ_CUR_STATE		= 1 << 1,
	IB_WQ_FLAGS		= 1 << 2,
1669 1670 1671 1672 1673
};

struct ib_wq_attr {
	enum	ib_wq_state	wq_state;
	enum	ib_wq_state	curr_wq_state;
1674 1675
	u32			flags; /* Use enum ib_wq_flags */
	u32			flags_mask; /* Use enum ib_wq_flags */
1676 1677
};

1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692
struct ib_rwq_ind_table {
	struct ib_device	*device;
	struct ib_uobject      *uobject;
	atomic_t		usecnt;
	u32		ind_tbl_num;
	u32		log_ind_tbl_size;
	struct ib_wq	**ind_tbl;
};

struct ib_rwq_ind_table_init_attr {
	u32		log_ind_tbl_size;
	/* Each entry is a pointer to Receive Work Queue */
	struct ib_wq	**ind_tbl;
};

1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731
enum port_pkey_state {
	IB_PORT_PKEY_NOT_VALID = 0,
	IB_PORT_PKEY_VALID = 1,
	IB_PORT_PKEY_LISTED = 2,
};

struct ib_qp_security;

struct ib_port_pkey {
	enum port_pkey_state	state;
	u16			pkey_index;
	u8			port_num;
	struct list_head	qp_list;
	struct list_head	to_error_list;
	struct ib_qp_security  *sec;
};

struct ib_ports_pkeys {
	struct ib_port_pkey	main;
	struct ib_port_pkey	alt;
};

struct ib_qp_security {
	struct ib_qp	       *qp;
	struct ib_device       *dev;
	/* Hold this mutex when changing port and pkey settings. */
	struct mutex		mutex;
	struct ib_ports_pkeys  *ports_pkeys;
	/* A list of all open shared QP handles.  Required to enforce security
	 * properly for all users of a shared QP.
	 */
	struct list_head        shared_qp_list;
	void                   *security;
	bool			destroying;
	atomic_t		error_list_count;
	struct completion	error_complete;
	int			error_comps_pending;
};

1732 1733 1734 1735
/*
 * @max_write_sge: Maximum SGE elements per RDMA WRITE request.
 * @max_read_sge:  Maximum SGE elements per RDMA READ request.
 */
L
Linus Torvalds 已提交
1736 1737 1738 1739 1740
struct ib_qp {
	struct ib_device       *device;
	struct ib_pd	       *pd;
	struct ib_cq	       *send_cq;
	struct ib_cq	       *recv_cq;
1741 1742
	spinlock_t		mr_lock;
	int			mrs_used;
1743
	struct list_head	rdma_mrs;
1744
	struct list_head	sig_mrs;
L
Linus Torvalds 已提交
1745
	struct ib_srq	       *srq;
S
Sean Hefty 已提交
1746
	struct ib_xrcd	       *xrcd; /* XRC TGT QPs only */
1747
	struct list_head	xrcd_list;
1748

1749 1750
	/* count times opened, mcast attaches, flow attaches */
	atomic_t		usecnt;
1751 1752
	struct list_head	open_list;
	struct ib_qp           *real_qp;
1753
	struct ib_uobject      *uobject;
L
Linus Torvalds 已提交
1754 1755 1756
	void                  (*event_handler)(struct ib_event *, void *);
	void		       *qp_context;
	u32			qp_num;
1757 1758
	u32			max_write_sge;
	u32			max_read_sge;
L
Linus Torvalds 已提交
1759
	enum ib_qp_type		qp_type;
1760
	struct ib_rwq_ind_table *rwq_ind_tbl;
1761
	struct ib_qp_security  *qp_sec;
1762
	u8			port;
1763 1764 1765 1766 1767

	/*
	 * Implementation details of the RDMA core, don't use in drivers:
	 */
	struct rdma_restrack_entry     res;
L
Linus Torvalds 已提交
1768 1769 1770
};

struct ib_mr {
1771 1772 1773 1774
	struct ib_device  *device;
	struct ib_pd	  *pd;
	u32		   lkey;
	u32		   rkey;
1775
	u64		   iova;
1776
	u64		   length;
1777
	unsigned int	   page_size;
1778
	bool		   need_inval;
1779 1780 1781 1782
	union {
		struct ib_uobject	*uobject;	/* user */
		struct list_head	qp_entry;	/* FR */
	};
1783 1784 1785 1786 1787

	/*
	 * Implementation details of the RDMA core, don't use in drivers:
	 */
	struct rdma_restrack_entry res;
L
Linus Torvalds 已提交
1788 1789 1790 1791 1792
};

struct ib_mw {
	struct ib_device	*device;
	struct ib_pd		*pd;
1793
	struct ib_uobject	*uobject;
L
Linus Torvalds 已提交
1794
	u32			rkey;
1795
	enum ib_mw_type         type;
L
Linus Torvalds 已提交
1796 1797 1798 1799 1800 1801 1802 1803 1804 1805
};

struct ib_fmr {
	struct ib_device	*device;
	struct ib_pd		*pd;
	struct list_head	list;
	u32			lkey;
	u32			rkey;
};

1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824
/* Supported steering options */
enum ib_flow_attr_type {
	/* steering according to rule specifications */
	IB_FLOW_ATTR_NORMAL		= 0x0,
	/* default unicast and multicast rule -
	 * receive all Eth traffic which isn't steered to any QP
	 */
	IB_FLOW_ATTR_ALL_DEFAULT	= 0x1,
	/* default multicast rule -
	 * receive all Eth multicast traffic which isn't steered to any QP
	 */
	IB_FLOW_ATTR_MC_DEFAULT		= 0x2,
	/* sniffer rule - receive all port traffic */
	IB_FLOW_ATTR_SNIFFER		= 0x3
};

/* Supported steering header types */
enum ib_flow_spec_type {
	/* L2 headers*/
1825 1826
	IB_FLOW_SPEC_ETH		= 0x20,
	IB_FLOW_SPEC_IB			= 0x22,
1827
	/* L3 header*/
1828 1829
	IB_FLOW_SPEC_IPV4		= 0x30,
	IB_FLOW_SPEC_IPV6		= 0x31,
1830
	/* L4 headers*/
1831 1832
	IB_FLOW_SPEC_TCP		= 0x40,
	IB_FLOW_SPEC_UDP		= 0x41,
1833
	IB_FLOW_SPEC_VXLAN_TUNNEL	= 0x50,
1834
	IB_FLOW_SPEC_INNER		= 0x100,
1835 1836
	/* Actions */
	IB_FLOW_SPEC_ACTION_TAG         = 0x1000,
1837
	IB_FLOW_SPEC_ACTION_DROP        = 0x1001,
1838
};
1839
#define IB_FLOW_SPEC_LAYER_MASK	0xF0
1840
#define IB_FLOW_SPEC_SUPPORT_LAYERS 8
1841

1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852
/* Flow steering rule priority is set according to it's domain.
 * Lower domain value means higher priority.
 */
enum ib_flow_domain {
	IB_FLOW_DOMAIN_USER,
	IB_FLOW_DOMAIN_ETHTOOL,
	IB_FLOW_DOMAIN_RFS,
	IB_FLOW_DOMAIN_NIC,
	IB_FLOW_DOMAIN_NUM /* Must be last */
};

1853 1854 1855 1856 1857
enum ib_flow_flags {
	IB_FLOW_ATTR_FLAGS_DONT_TRAP = 1UL << 1, /* Continue match, no steal */
	IB_FLOW_ATTR_FLAGS_RESERVED  = 1UL << 2  /* Must be last */
};

1858 1859 1860 1861 1862
struct ib_flow_eth_filter {
	u8	dst_mac[6];
	u8	src_mac[6];
	__be16	ether_type;
	__be16	vlan_tag;
1863 1864
	/* Must be last */
	u8	real_sz[0];
1865 1866 1867
};

struct ib_flow_spec_eth {
1868
	u32			  type;
1869 1870 1871 1872 1873
	u16			  size;
	struct ib_flow_eth_filter val;
	struct ib_flow_eth_filter mask;
};

1874 1875 1876
struct ib_flow_ib_filter {
	__be16 dlid;
	__u8   sl;
1877 1878
	/* Must be last */
	u8	real_sz[0];
1879 1880 1881
};

struct ib_flow_spec_ib {
1882
	u32			 type;
1883 1884 1885 1886 1887
	u16			 size;
	struct ib_flow_ib_filter val;
	struct ib_flow_ib_filter mask;
};

1888 1889 1890 1891 1892 1893 1894
/* IPv4 header flags */
enum ib_ipv4_flags {
	IB_IPV4_DONT_FRAG = 0x2, /* Don't enable packet fragmentation */
	IB_IPV4_MORE_FRAG = 0X4  /* For All fragmented packets except the
				    last have this flag set */
};

1895 1896 1897
struct ib_flow_ipv4_filter {
	__be32	src_ip;
	__be32	dst_ip;
1898 1899 1900 1901
	u8	proto;
	u8	tos;
	u8	ttl;
	u8	flags;
1902 1903
	/* Must be last */
	u8	real_sz[0];
1904 1905 1906
};

struct ib_flow_spec_ipv4 {
1907
	u32			   type;
1908 1909 1910 1911 1912
	u16			   size;
	struct ib_flow_ipv4_filter val;
	struct ib_flow_ipv4_filter mask;
};

1913 1914 1915
struct ib_flow_ipv6_filter {
	u8	src_ip[16];
	u8	dst_ip[16];
1916 1917 1918 1919
	__be32	flow_label;
	u8	next_hdr;
	u8	traffic_class;
	u8	hop_limit;
1920 1921
	/* Must be last */
	u8	real_sz[0];
1922 1923 1924
};

struct ib_flow_spec_ipv6 {
1925
	u32			   type;
1926 1927 1928 1929 1930
	u16			   size;
	struct ib_flow_ipv6_filter val;
	struct ib_flow_ipv6_filter mask;
};

1931 1932 1933
struct ib_flow_tcp_udp_filter {
	__be16	dst_port;
	__be16	src_port;
1934 1935
	/* Must be last */
	u8	real_sz[0];
1936 1937 1938
};

struct ib_flow_spec_tcp_udp {
1939
	u32			      type;
1940 1941 1942 1943 1944
	u16			      size;
	struct ib_flow_tcp_udp_filter val;
	struct ib_flow_tcp_udp_filter mask;
};

1945 1946 1947 1948 1949 1950 1951 1952 1953
struct ib_flow_tunnel_filter {
	__be32	tunnel_id;
	u8	real_sz[0];
};

/* ib_flow_spec_tunnel describes the Vxlan tunnel
 * the tunnel_id from val has the vni value
 */
struct ib_flow_spec_tunnel {
1954
	u32			      type;
1955 1956 1957 1958 1959
	u16			      size;
	struct ib_flow_tunnel_filter  val;
	struct ib_flow_tunnel_filter  mask;
};

1960 1961 1962 1963 1964 1965
struct ib_flow_spec_action_tag {
	enum ib_flow_spec_type	      type;
	u16			      size;
	u32                           tag_id;
};

1966 1967 1968 1969 1970
struct ib_flow_spec_action_drop {
	enum ib_flow_spec_type	      type;
	u16			      size;
};

1971 1972
union ib_flow_spec {
	struct {
1973
		u32			type;
1974 1975 1976
		u16			size;
	};
	struct ib_flow_spec_eth		eth;
1977
	struct ib_flow_spec_ib		ib;
1978 1979
	struct ib_flow_spec_ipv4        ipv4;
	struct ib_flow_spec_tcp_udp	tcp_udp;
1980
	struct ib_flow_spec_ipv6        ipv6;
1981
	struct ib_flow_spec_tunnel      tunnel;
1982
	struct ib_flow_spec_action_tag  flow_tag;
1983
	struct ib_flow_spec_action_drop drop;
1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003
};

struct ib_flow_attr {
	enum ib_flow_attr_type type;
	u16	     size;
	u16	     priority;
	u32	     flags;
	u8	     num_of_specs;
	u8	     port;
	/* Following are the optional layers according to user request
	 * struct ib_flow_spec_xxx
	 * struct ib_flow_spec_yyy
	 */
};

struct ib_flow {
	struct ib_qp		*qp;
	struct ib_uobject	*uobject;
};

2004
struct ib_mad_hdr;
L
Linus Torvalds 已提交
2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019
struct ib_grh;

enum ib_process_mad_flags {
	IB_MAD_IGNORE_MKEY	= 1,
	IB_MAD_IGNORE_BKEY	= 2,
	IB_MAD_IGNORE_ALL	= IB_MAD_IGNORE_MKEY | IB_MAD_IGNORE_BKEY
};

enum ib_mad_result {
	IB_MAD_RESULT_FAILURE  = 0,      /* (!SUCCESS is the important flag) */
	IB_MAD_RESULT_SUCCESS  = 1 << 0, /* MAD was successfully processed   */
	IB_MAD_RESULT_REPLY    = 1 << 1, /* Reply packet needs to be sent    */
	IB_MAD_RESULT_CONSUMED = 1 << 2  /* Packet consumed: stop processing */
};

2020
struct ib_port_cache {
2021
	u64		      subnet_prefix;
2022 2023 2024 2025 2026 2027
	struct ib_pkey_cache  *pkey;
	struct ib_gid_table   *gid;
	u8                     lmc;
	enum ib_port_state     port_state;
};

L
Linus Torvalds 已提交
2028 2029 2030
struct ib_cache {
	rwlock_t                lock;
	struct ib_event_handler event_handler;
2031
	struct ib_port_cache   *ports;
L
Linus Torvalds 已提交
2032 2033
};

T
Tom Tucker 已提交
2034 2035
struct iw_cm_verbs;

2036 2037 2038
struct ib_port_immutable {
	int                           pkey_tbl_len;
	int                           gid_tbl_len;
2039
	u32                           core_cap_flags;
2040
	u32                           max_mad_size;
2041 2042
};

2043 2044
/* rdma netdev type - specifies protocol type */
enum rdma_netdev_t {
2045 2046
	RDMA_NETDEV_OPA_VNIC,
	RDMA_NETDEV_IPOIB,
2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057
};

/**
 * struct rdma_netdev - rdma netdev
 * For cases where netstack interfacing is required.
 */
struct rdma_netdev {
	void              *clnt_priv;
	struct ib_device  *hca;
	u8                 port_num;

2058 2059 2060
	/* cleanup function must be specified */
	void (*free_rdma_netdev)(struct net_device *netdev);

2061 2062
	/* control functions */
	void (*set_id)(struct net_device *netdev, int id);
2063 2064 2065 2066 2067 2068 2069 2070 2071
	/* send packet */
	int (*send)(struct net_device *dev, struct sk_buff *skb,
		    struct ib_ah *address, u32 dqpn);
	/* multicast */
	int (*attach_mcast)(struct net_device *dev, struct ib_device *hca,
			    union ib_gid *gid, u16 mlid,
			    int set_qkey, u32 qkey);
	int (*detach_mcast)(struct net_device *dev, struct ib_device *hca,
			    union ib_gid *gid, u16 mlid);
2072 2073
};

2074 2075 2076 2077 2078 2079
struct ib_port_pkey_list {
	/* Lock to hold while modifying the list. */
	spinlock_t                    list_lock;
	struct list_head              pkey_list;
};

L
Linus Torvalds 已提交
2080
struct ib_device {
2081 2082 2083
	/* Do not access @dma_device directly from ULP nor from HW drivers. */
	struct device                *dma_device;

L
Linus Torvalds 已提交
2084 2085 2086 2087 2088
	char                          name[IB_DEVICE_NAME_MAX];

	struct list_head              event_handler_list;
	spinlock_t                    event_handler_lock;

2089
	spinlock_t                    client_data_lock;
L
Linus Torvalds 已提交
2090
	struct list_head              core_list;
2091 2092
	/* Access to the client_data_list is protected by the client_data_lock
	 * spinlock and the lists_rwsem read-write semaphore */
L
Linus Torvalds 已提交
2093 2094 2095
	struct list_head              client_data_list;

	struct ib_cache               cache;
2096 2097 2098 2099
	/**
	 * port_immutable is indexed by port number
	 */
	struct ib_port_immutable     *port_immutable;
L
Linus Torvalds 已提交
2100

2101 2102
	int			      num_comp_vectors;

2103 2104
	struct ib_port_pkey_list     *port_pkey_list;

T
Tom Tucker 已提交
2105 2106
	struct iw_cm_verbs	     *iwcm;

2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129
	/**
	 * alloc_hw_stats - Allocate a struct rdma_hw_stats and fill in the
	 *   driver initialized data.  The struct is kfree()'ed by the sysfs
	 *   core when the device is removed.  A lifespan of -1 in the return
	 *   struct tells the core to set a default lifespan.
	 */
	struct rdma_hw_stats      *(*alloc_hw_stats)(struct ib_device *device,
						     u8 port_num);
	/**
	 * get_hw_stats - Fill in the counter value(s) in the stats struct.
	 * @index - The index in the value array we wish to have updated, or
	 *   num_counters if we want all stats updated
	 * Return codes -
	 *   < 0 - Error, no counters updated
	 *   index - Updated the single counter pointed to by index
	 *   num_counters - Updated all counters (will reset the timestamp
	 *     and prevent further calls for lifespan milliseconds)
	 * Drivers are allowed to update all counters in leiu of just the
	 *   one given in index at their option
	 */
	int		           (*get_hw_stats)(struct ib_device *device,
						   struct rdma_hw_stats *stats,
						   u8 port, int index);
L
Linus Torvalds 已提交
2130
	int		           (*query_device)(struct ib_device *device,
2131 2132
						   struct ib_device_attr *device_attr,
						   struct ib_udata *udata);
L
Linus Torvalds 已提交
2133 2134 2135
	int		           (*query_port)(struct ib_device *device,
						 u8 port_num,
						 struct ib_port_attr *port_attr);
2136 2137
	enum rdma_link_layer	   (*get_link_layer)(struct ib_device *device,
						     u8 port_num);
2138 2139 2140 2141 2142 2143 2144 2145 2146
	/* When calling get_netdev, the HW vendor's driver should return the
	 * net device of device @device at port @port_num or NULL if such
	 * a net device doesn't exist. The vendor driver should call dev_hold
	 * on this net device. The HW vendor's device driver must guarantee
	 * that this function returns NULL before the net device reaches
	 * NETDEV_UNREGISTER_FINAL state.
	 */
	struct net_device	  *(*get_netdev)(struct ib_device *device,
						 u8 port_num);
2147 2148 2149 2150
	/* query_gid should be return GID value for @device, when @port_num
	 * link layer is either IB or iWarp. It is no-op if @port_num port
	 * is RoCE link layer.
	 */
L
Linus Torvalds 已提交
2151 2152 2153
	int		           (*query_gid)(struct ib_device *device,
						u8 port_num, int index,
						union ib_gid *gid);
2154 2155 2156 2157 2158 2159 2160 2161
	/* When calling add_gid, the HW vendor's driver should add the gid
	 * of device of port at gid index available at @attr. Meta-info of
	 * that gid (for example, the network device related to this gid) is
	 * available at @attr. @context allows the HW vendor driver to store
	 * extra information together with a GID entry. The HW vendor driver may
	 * allocate memory to contain this information and store it in @context
	 * when a new GID entry is written to. Params are consistent until the
	 * next call of add_gid or delete_gid. The function should return 0 on
2162
	 * success or error otherwise. The function could be called
2163 2164
	 * concurrently for different ports. This function is only called when
	 * roce_gid_table is used.
2165
	 */
2166
	int		           (*add_gid)(const union ib_gid *gid,
2167 2168 2169
					      const struct ib_gid_attr *attr,
					      void **context);
	/* When calling del_gid, the HW vendor's driver should delete the
2170 2171
	 * gid of device @device at gid index gid_index of port port_num
	 * available in @attr.
2172 2173 2174 2175
	 * Upon the deletion of a GID entry, the HW vendor must free any
	 * allocated memory. The caller will clear @context afterwards.
	 * This function is only called when roce_gid_table is used.
	 */
2176
	int		           (*del_gid)(const struct ib_gid_attr *attr,
2177
					      void **context);
L
Linus Torvalds 已提交
2178 2179 2180 2181 2182 2183 2184 2185
	int		           (*query_pkey)(struct ib_device *device,
						 u8 port_num, u16 index, u16 *pkey);
	int		           (*modify_device)(struct ib_device *device,
						    int device_modify_mask,
						    struct ib_device_modify *device_modify);
	int		           (*modify_port)(struct ib_device *device,
						  u8 port_num, int port_modify_mask,
						  struct ib_port_modify *port_modify);
2186 2187 2188 2189 2190 2191 2192 2193
	struct ib_ucontext *       (*alloc_ucontext)(struct ib_device *device,
						     struct ib_udata *udata);
	int                        (*dealloc_ucontext)(struct ib_ucontext *context);
	int                        (*mmap)(struct ib_ucontext *context,
					   struct vm_area_struct *vma);
	struct ib_pd *             (*alloc_pd)(struct ib_device *device,
					       struct ib_ucontext *context,
					       struct ib_udata *udata);
L
Linus Torvalds 已提交
2194 2195
	int                        (*dealloc_pd)(struct ib_pd *pd);
	struct ib_ah *             (*create_ah)(struct ib_pd *pd,
2196
						struct rdma_ah_attr *ah_attr,
2197
						struct ib_udata *udata);
L
Linus Torvalds 已提交
2198
	int                        (*modify_ah)(struct ib_ah *ah,
2199
						struct rdma_ah_attr *ah_attr);
L
Linus Torvalds 已提交
2200
	int                        (*query_ah)(struct ib_ah *ah,
2201
					       struct rdma_ah_attr *ah_attr);
L
Linus Torvalds 已提交
2202
	int                        (*destroy_ah)(struct ib_ah *ah);
2203 2204 2205 2206 2207
	struct ib_srq *            (*create_srq)(struct ib_pd *pd,
						 struct ib_srq_init_attr *srq_init_attr,
						 struct ib_udata *udata);
	int                        (*modify_srq)(struct ib_srq *srq,
						 struct ib_srq_attr *srq_attr,
2208 2209
						 enum ib_srq_attr_mask srq_attr_mask,
						 struct ib_udata *udata);
2210 2211 2212 2213 2214 2215
	int                        (*query_srq)(struct ib_srq *srq,
						struct ib_srq_attr *srq_attr);
	int                        (*destroy_srq)(struct ib_srq *srq);
	int                        (*post_srq_recv)(struct ib_srq *srq,
						    struct ib_recv_wr *recv_wr,
						    struct ib_recv_wr **bad_recv_wr);
L
Linus Torvalds 已提交
2216
	struct ib_qp *             (*create_qp)(struct ib_pd *pd,
2217 2218
						struct ib_qp_init_attr *qp_init_attr,
						struct ib_udata *udata);
L
Linus Torvalds 已提交
2219 2220
	int                        (*modify_qp)(struct ib_qp *qp,
						struct ib_qp_attr *qp_attr,
2221 2222
						int qp_attr_mask,
						struct ib_udata *udata);
L
Linus Torvalds 已提交
2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233
	int                        (*query_qp)(struct ib_qp *qp,
					       struct ib_qp_attr *qp_attr,
					       int qp_attr_mask,
					       struct ib_qp_init_attr *qp_init_attr);
	int                        (*destroy_qp)(struct ib_qp *qp);
	int                        (*post_send)(struct ib_qp *qp,
						struct ib_send_wr *send_wr,
						struct ib_send_wr **bad_send_wr);
	int                        (*post_recv)(struct ib_qp *qp,
						struct ib_recv_wr *recv_wr,
						struct ib_recv_wr **bad_recv_wr);
2234 2235
	struct ib_cq *             (*create_cq)(struct ib_device *device,
						const struct ib_cq_init_attr *attr,
2236 2237
						struct ib_ucontext *context,
						struct ib_udata *udata);
E
Eli Cohen 已提交
2238 2239
	int                        (*modify_cq)(struct ib_cq *cq, u16 cq_count,
						u16 cq_period);
L
Linus Torvalds 已提交
2240
	int                        (*destroy_cq)(struct ib_cq *cq);
2241 2242
	int                        (*resize_cq)(struct ib_cq *cq, int cqe,
						struct ib_udata *udata);
L
Linus Torvalds 已提交
2243 2244 2245 2246
	int                        (*poll_cq)(struct ib_cq *cq, int num_entries,
					      struct ib_wc *wc);
	int                        (*peek_cq)(struct ib_cq *cq, int wc_cnt);
	int                        (*req_notify_cq)(struct ib_cq *cq,
2247
						    enum ib_cq_notify_flags flags);
L
Linus Torvalds 已提交
2248 2249 2250 2251
	int                        (*req_ncomp_notif)(struct ib_cq *cq,
						      int wc_cnt);
	struct ib_mr *             (*get_dma_mr)(struct ib_pd *pd,
						 int mr_access_flags);
2252
	struct ib_mr *             (*reg_user_mr)(struct ib_pd *pd,
2253 2254
						  u64 start, u64 length,
						  u64 virt_addr,
2255 2256
						  int mr_access_flags,
						  struct ib_udata *udata);
2257 2258 2259 2260 2261 2262 2263
	int			   (*rereg_user_mr)(struct ib_mr *mr,
						    int flags,
						    u64 start, u64 length,
						    u64 virt_addr,
						    int mr_access_flags,
						    struct ib_pd *pd,
						    struct ib_udata *udata);
L
Linus Torvalds 已提交
2264
	int                        (*dereg_mr)(struct ib_mr *mr);
S
Sagi Grimberg 已提交
2265 2266 2267
	struct ib_mr *		   (*alloc_mr)(struct ib_pd *pd,
					       enum ib_mr_type mr_type,
					       u32 max_num_sg);
2268 2269
	int                        (*map_mr_sg)(struct ib_mr *mr,
						struct scatterlist *sg,
2270
						int sg_nents,
2271
						unsigned int *sg_offset);
2272
	struct ib_mw *             (*alloc_mw)(struct ib_pd *pd,
2273 2274
					       enum ib_mw_type type,
					       struct ib_udata *udata);
L
Linus Torvalds 已提交
2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292
	int                        (*dealloc_mw)(struct ib_mw *mw);
	struct ib_fmr *	           (*alloc_fmr)(struct ib_pd *pd,
						int mr_access_flags,
						struct ib_fmr_attr *fmr_attr);
	int		           (*map_phys_fmr)(struct ib_fmr *fmr,
						   u64 *page_list, int list_len,
						   u64 iova);
	int		           (*unmap_fmr)(struct list_head *fmr_list);
	int		           (*dealloc_fmr)(struct ib_fmr *fmr);
	int                        (*attach_mcast)(struct ib_qp *qp,
						   union ib_gid *gid,
						   u16 lid);
	int                        (*detach_mcast)(struct ib_qp *qp,
						   union ib_gid *gid,
						   u16 lid);
	int                        (*process_mad)(struct ib_device *device,
						  int process_mad_flags,
						  u8 port_num,
2293 2294
						  const struct ib_wc *in_wc,
						  const struct ib_grh *in_grh,
2295 2296 2297 2298 2299
						  const struct ib_mad_hdr *in_mad,
						  size_t in_mad_size,
						  struct ib_mad_hdr *out_mad,
						  size_t *out_mad_size,
						  u16 *out_mad_pkey_index);
S
Sean Hefty 已提交
2300 2301 2302 2303
	struct ib_xrcd *	   (*alloc_xrcd)(struct ib_device *device,
						 struct ib_ucontext *ucontext,
						 struct ib_udata *udata);
	int			   (*dealloc_xrcd)(struct ib_xrcd *xrcd);
2304 2305 2306 2307 2308
	struct ib_flow *	   (*create_flow)(struct ib_qp *qp,
						  struct ib_flow_attr
						  *flow_attr,
						  int domain);
	int			   (*destroy_flow)(struct ib_flow *flow_id);
2309 2310
	int			   (*check_mr_status)(struct ib_mr *mr, u32 check_mask,
						      struct ib_mr_status *mr_status);
2311
	void			   (*disassociate_ucontext)(struct ib_ucontext *ibcontext);
2312 2313
	void			   (*drain_rq)(struct ib_qp *qp);
	void			   (*drain_sq)(struct ib_qp *qp);
2314 2315 2316 2317 2318 2319 2320 2321
	int			   (*set_vf_link_state)(struct ib_device *device, int vf, u8 port,
							int state);
	int			   (*get_vf_config)(struct ib_device *device, int vf, u8 port,
						   struct ifla_vf_info *ivf);
	int			   (*get_vf_stats)(struct ib_device *device, int vf, u8 port,
						   struct ifla_vf_stats *stats);
	int			   (*set_vf_guid)(struct ib_device *device, int vf, u8 port, u64 guid,
						  int type);
2322 2323 2324 2325 2326 2327 2328 2329
	struct ib_wq *		   (*create_wq)(struct ib_pd *pd,
						struct ib_wq_init_attr *init_attr,
						struct ib_udata *udata);
	int			   (*destroy_wq)(struct ib_wq *wq);
	int			   (*modify_wq)(struct ib_wq *wq,
						struct ib_wq_attr *attr,
						u32 wq_attr_mask,
						struct ib_udata *udata);
2330 2331 2332 2333
	struct ib_rwq_ind_table *  (*create_rwq_ind_table)(struct ib_device *device,
							   struct ib_rwq_ind_table_init_attr *init_attr,
							   struct ib_udata *udata);
	int                        (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table);
2334
	/**
2335
	 * rdma netdev operation
2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346
	 *
	 * Driver implementing alloc_rdma_netdev must return -EOPNOTSUPP if it
	 * doesn't support the specified rdma netdev type.
	 */
	struct net_device *(*alloc_rdma_netdev)(
					struct ib_device *device,
					u8 port_num,
					enum rdma_netdev_t type,
					const char *name,
					unsigned char name_assign_type,
					void (*setup)(struct net_device *));
2347

2348
	struct module               *owner;
2349
	struct device                dev;
2350
	struct kobject               *ports_parent;
L
Linus Torvalds 已提交
2351 2352 2353 2354 2355 2356 2357 2358
	struct list_head             port_list;

	enum {
		IB_DEV_UNINITIALIZED,
		IB_DEV_REGISTERED,
		IB_DEV_UNREGISTERED
	}                            reg_state;

2359
	int			     uverbs_abi_ver;
2360
	u64			     uverbs_cmd_mask;
2361
	u64			     uverbs_ex_cmd_mask;
2362

2363
	char			     node_desc[IB_DEVICE_NODE_DESC_MAX];
2364
	__be64			     node_guid;
2365
	u32			     local_dma_lkey;
2366
	u16                          is_switch:1;
L
Linus Torvalds 已提交
2367 2368
	u8                           node_type;
	u8                           phys_port_cnt;
2369
	struct ib_device_attr        attrs;
2370 2371
	struct attribute_group	     *hw_stats_ag;
	struct rdma_hw_stats         *hw_stats;
2372

2373 2374 2375 2376
#ifdef CONFIG_CGROUP_RDMA
	struct rdmacg_device         cg_device;
#endif

2377
	u32                          index;
2378 2379 2380 2381
	/*
	 * Implementation details of the RDMA core, don't use in drivers
	 */
	struct rdma_restrack_root     res;
2382

2383 2384 2385 2386 2387 2388 2389
	/**
	 * The following mandatory functions are used only at device
	 * registration.  Keep functions such as these at the end of this
	 * structure to avoid cache line misses when accessing struct ib_device
	 * in fast paths.
	 */
	int (*get_port_immutable)(struct ib_device *, u8, struct ib_port_immutable *);
2390
	void (*get_dev_fw_str)(struct ib_device *, char *str);
2391 2392
	const struct cpumask *(*get_vector_affinity)(struct ib_device *ibdev,
						     int comp_vector);
M
Matan Barak 已提交
2393 2394

	struct uverbs_root_spec		*specs_root;
2395
	enum rdma_driver_id		driver_id;
L
Linus Torvalds 已提交
2396 2397 2398 2399 2400
};

struct ib_client {
	char  *name;
	void (*add)   (struct ib_device *);
2401
	void (*remove)(struct ib_device *, void *client_data);
L
Linus Torvalds 已提交
2402

2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424
	/* Returns the net_dev belonging to this ib_client and matching the
	 * given parameters.
	 * @dev:	 An RDMA device that the net_dev use for communication.
	 * @port:	 A physical port number on the RDMA device.
	 * @pkey:	 P_Key that the net_dev uses if applicable.
	 * @gid:	 A GID that the net_dev uses to communicate.
	 * @addr:	 An IP address the net_dev is configured with.
	 * @client_data: The device's client data set by ib_set_client_data().
	 *
	 * An ib_client that implements a net_dev on top of RDMA devices
	 * (such as IP over IB) should implement this callback, allowing the
	 * rdma_cm module to find the right net_dev for a given request.
	 *
	 * The caller is responsible for calling dev_put on the returned
	 * netdev. */
	struct net_device *(*get_net_dev_by_params)(
			struct ib_device *dev,
			u8 port,
			u16 pkey,
			const union ib_gid *gid,
			const struct sockaddr *addr,
			void *client_data);
L
Linus Torvalds 已提交
2425 2426 2427 2428 2429 2430
	struct list_head list;
};

struct ib_device *ib_alloc_device(size_t size);
void ib_dealloc_device(struct ib_device *device);

2431
void ib_get_device_fw_str(struct ib_device *device, char *str);
2432

2433 2434 2435
int ib_register_device(struct ib_device *device,
		       int (*port_callback)(struct ib_device *,
					    u8, struct kobject *));
L
Linus Torvalds 已提交
2436 2437 2438 2439 2440 2441 2442 2443 2444
void ib_unregister_device(struct ib_device *device);

int ib_register_client   (struct ib_client *client);
void ib_unregister_client(struct ib_client *client);

void *ib_get_client_data(struct ib_device *device, struct ib_client *client);
void  ib_set_client_data(struct ib_device *device, struct ib_client *client,
			 void *data);

2445 2446 2447 2448 2449 2450 2451
static inline int ib_copy_from_udata(void *dest, struct ib_udata *udata, size_t len)
{
	return copy_from_user(dest, udata->inbuf, len) ? -EFAULT : 0;
}

static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len)
{
2452
	return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0;
2453 2454
}

2455 2456
static inline bool ib_is_buffer_cleared(const void __user *p,
					size_t len)
M
Matan Barak 已提交
2457
{
2458
	bool ret;
M
Matan Barak 已提交
2459 2460 2461 2462 2463
	u8 *buf;

	if (len > USHRT_MAX)
		return false;

2464 2465
	buf = memdup_user(p, len);
	if (IS_ERR(buf))
M
Matan Barak 已提交
2466 2467 2468 2469 2470 2471 2472
		return false;

	ret = !memchr_inv(buf, 0, len);
	kfree(buf);
	return ret;
}

2473 2474 2475 2476 2477 2478 2479
static inline bool ib_is_udata_cleared(struct ib_udata *udata,
				       size_t offset,
				       size_t len)
{
	return ib_is_buffer_cleared(udata->inbuf + offset, len);
}

2480 2481 2482 2483 2484 2485 2486 2487
/**
 * ib_modify_qp_is_ok - Check that the supplied attribute mask
 * contains all required attributes and no attributes not allowed for
 * the given QP state transition.
 * @cur_state: Current QP state
 * @next_state: Next QP state
 * @type: QP type
 * @mask: Mask of supplied QP attributes
2488
 * @ll : link layer of port
2489 2490 2491 2492 2493 2494 2495
 *
 * This function is a helper function that a low-level driver's
 * modify_qp method can use to validate the consumer's input.  It
 * checks that cur_state and next_state are valid QP states, that a
 * transition from cur_state to next_state is allowed by the IB spec,
 * and that the attribute mask supplied is allowed for the transition.
 */
2496 2497 2498
bool 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);
2499

2500 2501
void ib_register_event_handler(struct ib_event_handler *event_handler);
void ib_unregister_event_handler(struct ib_event_handler *event_handler);
L
Linus Torvalds 已提交
2502 2503 2504 2505 2506
void ib_dispatch_event(struct ib_event *event);

int ib_query_port(struct ib_device *device,
		  u8 port_num, struct ib_port_attr *port_attr);

2507 2508 2509
enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device,
					       u8 port_num);

2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523
/**
 * rdma_cap_ib_switch - Check if the device is IB switch
 * @device: Device to check
 *
 * Device driver is responsible for setting is_switch bit on
 * in ib_device structure at init time.
 *
 * Return: true if the device is IB switch.
 */
static inline bool rdma_cap_ib_switch(const struct ib_device *device)
{
	return device->is_switch;
}

2524 2525 2526 2527 2528 2529 2530 2531 2532 2533
/**
 * rdma_start_port - Return the first valid port number for the device
 * specified
 *
 * @device: Device to be checked
 *
 * Return start port number
 */
static inline u8 rdma_start_port(const struct ib_device *device)
{
2534
	return rdma_cap_ib_switch(device) ? 0 : 1;
2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546
}

/**
 * rdma_end_port - Return the last valid port number for the device
 * specified
 *
 * @device: Device to be checked
 *
 * Return last port number
 */
static inline u8 rdma_end_port(const struct ib_device *device)
{
2547
	return rdma_cap_ib_switch(device) ? 0 : device->phys_port_cnt;
2548 2549
}

2550 2551 2552 2553 2554 2555 2556
static inline int rdma_is_port_valid(const struct ib_device *device,
				     unsigned int port)
{
	return (port >= rdma_start_port(device) &&
		port <= rdma_end_port(device));
}

2557
static inline bool rdma_protocol_ib(const struct ib_device *device, u8 port_num)
2558
{
2559
	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_IB;
2560 2561
}

2562
static inline bool rdma_protocol_roce(const struct ib_device *device, u8 port_num)
2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573
{
	return device->port_immutable[port_num].core_cap_flags &
		(RDMA_CORE_CAP_PROT_ROCE | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP);
}

static inline bool rdma_protocol_roce_udp_encap(const struct ib_device *device, u8 port_num)
{
	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP;
}

static inline bool rdma_protocol_roce_eth_encap(const struct ib_device *device, u8 port_num)
2574
{
2575
	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_ROCE;
2576 2577
}

2578
static inline bool rdma_protocol_iwarp(const struct ib_device *device, u8 port_num)
2579
{
2580
	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_IWARP;
2581 2582
}

2583
static inline bool rdma_ib_or_roce(const struct ib_device *device, u8 port_num)
2584
{
2585 2586
	return rdma_protocol_ib(device, port_num) ||
		rdma_protocol_roce(device, port_num);
2587 2588
}

O
Or Gerlitz 已提交
2589 2590 2591 2592 2593
static inline bool rdma_protocol_raw_packet(const struct ib_device *device, u8 port_num)
{
	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_RAW_PACKET;
}

O
Or Gerlitz 已提交
2594 2595 2596 2597 2598
static inline bool rdma_protocol_usnic(const struct ib_device *device, u8 port_num)
{
	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_USNIC;
}

2599
/**
2600
 * rdma_cap_ib_mad - Check if the port of a device supports Infiniband
2601
 * Management Datagrams.
2602 2603
 * @device: Device to check
 * @port_num: Port number to check
2604
 *
2605 2606 2607
 * Management Datagrams (MAD) are a required part of the InfiniBand
 * specification and are supported on all InfiniBand devices.  A slightly
 * extended version are also supported on OPA interfaces.
2608
 *
2609
 * Return: true if the port supports sending/receiving of MAD packets.
2610
 */
2611
static inline bool rdma_cap_ib_mad(const struct ib_device *device, u8 port_num)
2612
{
2613
	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_MAD;
2614 2615
}

2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640
/**
 * rdma_cap_opa_mad - Check if the port of device provides support for OPA
 * Management Datagrams.
 * @device: Device to check
 * @port_num: Port number to check
 *
 * Intel OmniPath devices extend and/or replace the InfiniBand Management
 * datagrams with their own versions.  These OPA MADs share many but not all of
 * the characteristics of InfiniBand MADs.
 *
 * OPA MADs differ in the following ways:
 *
 *    1) MADs are variable size up to 2K
 *       IBTA defined MADs remain fixed at 256 bytes
 *    2) OPA SMPs must carry valid PKeys
 *    3) OPA SMP packets are a different format
 *
 * Return: true if the port supports OPA MAD packet formats.
 */
static inline bool rdma_cap_opa_mad(struct ib_device *device, u8 port_num)
{
	return (device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_OPA_MAD)
		== RDMA_CORE_CAP_OPA_MAD;
}

2641
/**
2642 2643 2644 2645
 * rdma_cap_ib_smi - Check if the port of a device provides an Infiniband
 * Subnet Management Agent (SMA) on the Subnet Management Interface (SMI).
 * @device: Device to check
 * @port_num: Port number to check
2646
 *
2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657
 * Each InfiniBand node is required to provide a Subnet Management Agent
 * that the subnet manager can access.  Prior to the fabric being fully
 * configured by the subnet manager, the SMA is accessed via a well known
 * interface called the Subnet Management Interface (SMI).  This interface
 * uses directed route packets to communicate with the SM to get around the
 * chicken and egg problem of the SM needing to know what's on the fabric
 * in order to configure the fabric, and needing to configure the fabric in
 * order to send packets to the devices on the fabric.  These directed
 * route packets do not need the fabric fully configured in order to reach
 * their destination.  The SMI is the only method allowed to send
 * directed route packets on an InfiniBand fabric.
2658
 *
2659
 * Return: true if the port provides an SMI.
2660
 */
2661
static inline bool rdma_cap_ib_smi(const struct ib_device *device, u8 port_num)
2662
{
2663
	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_SMI;
2664 2665
}

2666 2667 2668
/**
 * rdma_cap_ib_cm - Check if the port of device has the capability Infiniband
 * Communication Manager.
2669 2670
 * @device: Device to check
 * @port_num: Port number to check
2671
 *
2672 2673 2674 2675 2676
 * The InfiniBand Communication Manager is one of many pre-defined General
 * Service Agents (GSA) that are accessed via the General Service
 * Interface (GSI).  It's role is to facilitate establishment of connections
 * between nodes as well as other management related tasks for established
 * connections.
2677
 *
2678 2679
 * Return: true if the port supports an IB CM (this does not guarantee that
 * a CM is actually running however).
2680
 */
2681
static inline bool rdma_cap_ib_cm(const struct ib_device *device, u8 port_num)
2682
{
2683
	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_CM;
2684 2685
}

2686 2687 2688
/**
 * rdma_cap_iw_cm - Check if the port of device has the capability IWARP
 * Communication Manager.
2689 2690
 * @device: Device to check
 * @port_num: Port number to check
2691
 *
2692 2693
 * Similar to above, but specific to iWARP connections which have a different
 * managment protocol than InfiniBand.
2694
 *
2695 2696
 * Return: true if the port supports an iWARP CM (this does not guarantee that
 * a CM is actually running however).
2697
 */
2698
static inline bool rdma_cap_iw_cm(const struct ib_device *device, u8 port_num)
2699
{
2700
	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IW_CM;
2701 2702
}

2703 2704 2705
/**
 * rdma_cap_ib_sa - Check if the port of device has the capability Infiniband
 * Subnet Administration.
2706 2707
 * @device: Device to check
 * @port_num: Port number to check
2708
 *
2709 2710 2711 2712
 * An InfiniBand Subnet Administration (SA) service is a pre-defined General
 * Service Agent (GSA) provided by the Subnet Manager (SM).  On InfiniBand
 * fabrics, devices should resolve routes to other hosts by contacting the
 * SA to query the proper route.
2713
 *
2714 2715 2716
 * Return: true if the port should act as a client to the fabric Subnet
 * Administration interface.  This does not imply that the SA service is
 * running locally.
2717
 */
2718
static inline bool rdma_cap_ib_sa(const struct ib_device *device, u8 port_num)
2719
{
2720
	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_SA;
2721 2722
}

2723 2724 2725
/**
 * rdma_cap_ib_mcast - Check if the port of device has the capability Infiniband
 * Multicast.
2726 2727
 * @device: Device to check
 * @port_num: Port number to check
2728
 *
2729 2730 2731 2732 2733 2734
 * InfiniBand multicast registration is more complex than normal IPv4 or
 * IPv6 multicast registration.  Each Host Channel Adapter must register
 * with the Subnet Manager when it wishes to join a multicast group.  It
 * should do so only once regardless of how many queue pairs it subscribes
 * to this group.  And it should leave the group only after all queue pairs
 * attached to the group have been detached.
2735
 *
2736 2737 2738
 * Return: true if the port must undertake the additional adminstrative
 * overhead of registering/unregistering with the SM and tracking of the
 * total number of queue pairs attached to the multicast group.
2739
 */
2740
static inline bool rdma_cap_ib_mcast(const struct ib_device *device, u8 port_num)
2741 2742 2743 2744
{
	return rdma_cap_ib_sa(device, port_num);
}

2745 2746 2747
/**
 * rdma_cap_af_ib - Check if the port of device has the capability
 * Native Infiniband Address.
2748 2749
 * @device: Device to check
 * @port_num: Port number to check
2750
 *
2751 2752 2753
 * InfiniBand addressing uses a port's GUID + Subnet Prefix to make a default
 * GID.  RoCE uses a different mechanism, but still generates a GID via
 * a prescribed mechanism and port specific data.
2754
 *
2755 2756
 * Return: true if the port uses a GID address to identify devices on the
 * network.
2757
 */
2758
static inline bool rdma_cap_af_ib(const struct ib_device *device, u8 port_num)
2759
{
2760
	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_AF_IB;
2761 2762
}

2763 2764
/**
 * rdma_cap_eth_ah - Check if the port of device has the capability
2765 2766 2767
 * Ethernet Address Handle.
 * @device: Device to check
 * @port_num: Port number to check
2768
 *
2769 2770 2771 2772 2773
 * RoCE is InfiniBand over Ethernet, and it uses a well defined technique
 * to fabricate GIDs over Ethernet/IP specific addresses native to the
 * port.  Normally, packet headers are generated by the sending host
 * adapter, but when sending connectionless datagrams, we must manually
 * inject the proper headers for the fabric we are communicating over.
2774
 *
2775 2776 2777
 * Return: true if we are running as a RoCE port and must force the
 * addition of a Global Route Header built from our Ethernet Address
 * Handle into our header list for connectionless packets.
2778
 */
2779
static inline bool rdma_cap_eth_ah(const struct ib_device *device, u8 port_num)
2780
{
2781
	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_ETH_AH;
2782 2783
}

2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798
/**
 * rdma_cap_opa_ah - Check if the port of device supports
 * OPA Address handles
 * @device: Device to check
 * @port_num: Port number to check
 *
 * Return: true if we are running on an OPA device which supports
 * the extended OPA addressing.
 */
static inline bool rdma_cap_opa_ah(struct ib_device *device, u8 port_num)
{
	return (device->port_immutable[port_num].core_cap_flags &
		RDMA_CORE_CAP_OPA_AH) == RDMA_CORE_CAP_OPA_AH;
}

2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815
/**
 * rdma_max_mad_size - Return the max MAD size required by this RDMA Port.
 *
 * @device: Device
 * @port_num: Port number
 *
 * This MAD size includes the MAD headers and MAD payload.  No other headers
 * are included.
 *
 * Return the max MAD size required by the Port.  Will return 0 if the port
 * does not support MADs
 */
static inline size_t rdma_max_mad_size(const struct ib_device *device, u8 port_num)
{
	return device->port_immutable[port_num].max_mad_size;
}

2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835
/**
 * rdma_cap_roce_gid_table - Check if the port of device uses roce_gid_table
 * @device: Device to check
 * @port_num: Port number to check
 *
 * RoCE GID table mechanism manages the various GIDs for a device.
 *
 * NOTE: if allocating the port's GID table has failed, this call will still
 * return true, but any RoCE GID table API will fail.
 *
 * Return: true if the port uses RoCE GID table mechanism in order to manage
 * its GIDs.
 */
static inline bool rdma_cap_roce_gid_table(const struct ib_device *device,
					   u8 port_num)
{
	return rdma_protocol_roce(device, port_num) &&
		device->add_gid && device->del_gid;
}

2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847
/*
 * Check if the device supports READ W/ INVALIDATE.
 */
static inline bool rdma_cap_read_inv(struct ib_device *dev, u32 port_num)
{
	/*
	 * iWarp drivers must support READ W/ INVALIDATE.  No other protocol
	 * has support for it yet.
	 */
	return rdma_protocol_iwarp(dev, port_num);
}

L
Linus Torvalds 已提交
2848
int ib_query_gid(struct ib_device *device,
2849 2850
		 u8 port_num, int index, union ib_gid *gid,
		 struct ib_gid_attr *attr);
L
Linus Torvalds 已提交
2851

2852 2853 2854 2855 2856 2857 2858 2859 2860
int ib_set_vf_link_state(struct ib_device *device, int vf, u8 port,
			 int state);
int ib_get_vf_config(struct ib_device *device, int vf, u8 port,
		     struct ifla_vf_info *info);
int ib_get_vf_stats(struct ib_device *device, int vf, u8 port,
		    struct ifla_vf_stats *stats);
int ib_set_vf_guid(struct ib_device *device, int vf, u8 port, u64 guid,
		   int type);

L
Linus Torvalds 已提交
2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871
int ib_query_pkey(struct ib_device *device,
		  u8 port_num, u16 index, u16 *pkey);

int ib_modify_device(struct ib_device *device,
		     int device_modify_mask,
		     struct ib_device_modify *device_modify);

int ib_modify_port(struct ib_device *device,
		   u8 port_num, int port_modify_mask,
		   struct ib_port_modify *port_modify);

2872
int ib_find_gid(struct ib_device *device, union ib_gid *gid,
2873
		u8 *port_num, u16 *index);
2874 2875 2876 2877

int ib_find_pkey(struct ib_device *device,
		 u8 port_num, u16 pkey, u16 *index);

2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889
enum ib_pd_flags {
	/*
	 * Create a memory registration for all memory in the system and place
	 * the rkey for it into pd->unsafe_global_rkey.  This can be used by
	 * ULPs to avoid the overhead of dynamic MRs.
	 *
	 * This flag is generally considered unsafe and must only be used in
	 * extremly trusted environments.  Every use of it will log a warning
	 * in the kernel log.
	 */
	IB_PD_UNSAFE_GLOBAL_RKEY	= 0x01,
};
L
Linus Torvalds 已提交
2890

2891 2892 2893
struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags,
		const char *caller);
#define ib_alloc_pd(device, flags) \
2894
	__ib_alloc_pd((device), (flags), KBUILD_MODNAME)
2895
void ib_dealloc_pd(struct ib_pd *pd);
L
Linus Torvalds 已提交
2896 2897

/**
2898
 * rdma_create_ah - Creates an address handle for the given address vector.
L
Linus Torvalds 已提交
2899 2900 2901 2902 2903 2904
 * @pd: The protection domain associated with the address handle.
 * @ah_attr: The attributes of the address vector.
 *
 * The address handle is used to reference a local or global destination
 * in all UD QP post sends.
 */
2905
struct ib_ah *rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr);
L
Linus Torvalds 已提交
2906

2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921
/**
 * rdma_create_user_ah - Creates an address handle for the given address vector.
 * It resolves destination mac address for ah attribute of RoCE type.
 * @pd: The protection domain associated with the address handle.
 * @ah_attr: The attributes of the address vector.
 * @udata: pointer to user's input output buffer information need by
 *         provider driver.
 *
 * It returns 0 on success and returns appropriate error code on error.
 * The address handle is used to reference a local or global destination
 * in all UD QP post sends.
 */
struct ib_ah *rdma_create_user_ah(struct ib_pd *pd,
				  struct rdma_ah_attr *ah_attr,
				  struct ib_udata *udata);
2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939
/**
 * ib_get_gids_from_rdma_hdr - Get sgid and dgid from GRH or IPv4 header
 *   work completion.
 * @hdr: the L3 header to parse
 * @net_type: type of header to parse
 * @sgid: place to store source gid
 * @dgid: place to store destination gid
 */
int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr,
			      enum rdma_network_type net_type,
			      union ib_gid *sgid, union ib_gid *dgid);

/**
 * ib_get_rdma_header_version - Get the header version
 * @hdr: the L3 header to parse
 */
int ib_get_rdma_header_version(const union rdma_network_hdr *hdr);

S
Sean Hefty 已提交
2940
/**
2941
 * ib_init_ah_attr_from_wc - Initializes address handle attributes from a
S
Sean Hefty 已提交
2942 2943 2944 2945 2946 2947 2948 2949 2950
 *   work completion.
 * @device: Device on which the received message arrived.
 * @port_num: Port on which the received message arrived.
 * @wc: Work completion associated with the received message.
 * @grh: References the received global route header.  This parameter is
 *   ignored unless the work completion indicates that the GRH is valid.
 * @ah_attr: Returned attributes that can be used when creating an address
 *   handle for replying to the message.
 */
2951 2952 2953
int ib_init_ah_attr_from_wc(struct ib_device *device, u8 port_num,
			    const struct ib_wc *wc, const struct ib_grh *grh,
			    struct rdma_ah_attr *ah_attr);
S
Sean Hefty 已提交
2954

2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966
/**
 * ib_create_ah_from_wc - Creates an address handle associated with the
 *   sender of the specified work completion.
 * @pd: The protection domain associated with the address handle.
 * @wc: Work completion information associated with a received message.
 * @grh: References the received global route header.  This parameter is
 *   ignored unless the work completion indicates that the GRH is valid.
 * @port_num: The outbound port number to associate with the address.
 *
 * The address handle is used to reference a local or global destination
 * in all UD QP post sends.
 */
2967 2968
struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, const struct ib_wc *wc,
				   const struct ib_grh *grh, u8 port_num);
2969

L
Linus Torvalds 已提交
2970
/**
2971
 * rdma_modify_ah - Modifies the address vector associated with an address
L
Linus Torvalds 已提交
2972 2973 2974 2975 2976
 *   handle.
 * @ah: The address handle to modify.
 * @ah_attr: The new address vector attributes to associate with the
 *   address handle.
 */
2977
int rdma_modify_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
L
Linus Torvalds 已提交
2978 2979

/**
2980
 * rdma_query_ah - Queries the address vector associated with an address
L
Linus Torvalds 已提交
2981 2982 2983 2984 2985
 *   handle.
 * @ah: The address handle to query.
 * @ah_attr: The address vector attributes associated with the address
 *   handle.
 */
2986
int rdma_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
L
Linus Torvalds 已提交
2987 2988

/**
2989
 * rdma_destroy_ah - Destroys an address handle.
L
Linus Torvalds 已提交
2990 2991
 * @ah: The address handle to destroy.
 */
2992
int rdma_destroy_ah(struct ib_ah *ah);
L
Linus Torvalds 已提交
2993

2994 2995 2996 2997
/**
 * ib_create_srq - Creates a SRQ associated with the specified protection
 *   domain.
 * @pd: The protection domain associated with the SRQ.
2998 2999 3000
 * @srq_init_attr: A list of initial attributes required to create the
 *   SRQ.  If SRQ creation succeeds, then the attributes are updated to
 *   the actual capabilities of the created SRQ.
3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054
 *
 * srq_attr->max_wr and srq_attr->max_sge are read the determine the
 * requested size of the SRQ, and set to the actual values allocated
 * on return.  If ib_create_srq() succeeds, then max_wr and max_sge
 * will always be at least as large as the requested values.
 */
struct ib_srq *ib_create_srq(struct ib_pd *pd,
			     struct ib_srq_init_attr *srq_init_attr);

/**
 * ib_modify_srq - Modifies the attributes for the specified SRQ.
 * @srq: The SRQ to modify.
 * @srq_attr: On input, specifies the SRQ attributes to modify.  On output,
 *   the current values of selected SRQ attributes are returned.
 * @srq_attr_mask: A bit-mask used to specify which attributes of the SRQ
 *   are being modified.
 *
 * The mask may contain IB_SRQ_MAX_WR to resize the SRQ and/or
 * IB_SRQ_LIMIT to set the SRQ's limit and request notification when
 * the number of receives queued drops below the limit.
 */
int ib_modify_srq(struct ib_srq *srq,
		  struct ib_srq_attr *srq_attr,
		  enum ib_srq_attr_mask srq_attr_mask);

/**
 * ib_query_srq - Returns the attribute list and current values for the
 *   specified SRQ.
 * @srq: The SRQ to query.
 * @srq_attr: The attributes of the specified SRQ.
 */
int ib_query_srq(struct ib_srq *srq,
		 struct ib_srq_attr *srq_attr);

/**
 * ib_destroy_srq - Destroys the specified SRQ.
 * @srq: The SRQ to destroy.
 */
int ib_destroy_srq(struct ib_srq *srq);

/**
 * ib_post_srq_recv - Posts a list of work requests to the specified SRQ.
 * @srq: The SRQ to post the work request on.
 * @recv_wr: A list of work requests to post on the receive queue.
 * @bad_recv_wr: On an immediate failure, this parameter will reference
 *   the work request that failed to be posted on the QP.
 */
static inline int ib_post_srq_recv(struct ib_srq *srq,
				   struct ib_recv_wr *recv_wr,
				   struct ib_recv_wr **bad_recv_wr)
{
	return srq->device->post_srq_recv(srq, recv_wr, bad_recv_wr);
}

L
Linus Torvalds 已提交
3055 3056 3057 3058
/**
 * ib_create_qp - Creates a QP associated with the specified protection
 *   domain.
 * @pd: The protection domain associated with the QP.
3059 3060 3061
 * @qp_init_attr: A list of initial attributes required to create the
 *   QP.  If QP creation succeeds, then the attributes are updated to
 *   the actual capabilities of the created QP.
L
Linus Torvalds 已提交
3062 3063 3064 3065
 */
struct ib_qp *ib_create_qp(struct ib_pd *pd,
			   struct ib_qp_init_attr *qp_init_attr);

3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081
/**
 * ib_modify_qp_with_udata - Modifies the attributes for the specified QP.
 * @qp: The QP to modify.
 * @attr: On input, specifies the QP attributes to modify.  On output,
 *   the current values of selected QP attributes are returned.
 * @attr_mask: A bit-mask used to specify which attributes of the QP
 *   are being modified.
 * @udata: pointer to user's input output buffer information
 *   are being modified.
 * It returns 0 on success and returns appropriate error code on error.
 */
int ib_modify_qp_with_udata(struct ib_qp *qp,
			    struct ib_qp_attr *attr,
			    int attr_mask,
			    struct ib_udata *udata);

L
Linus Torvalds 已提交
3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116
/**
 * ib_modify_qp - Modifies the attributes for the specified QP and then
 *   transitions the QP to the given state.
 * @qp: The QP to modify.
 * @qp_attr: On input, specifies the QP attributes to modify.  On output,
 *   the current values of selected QP attributes are returned.
 * @qp_attr_mask: A bit-mask used to specify which attributes of the QP
 *   are being modified.
 */
int ib_modify_qp(struct ib_qp *qp,
		 struct ib_qp_attr *qp_attr,
		 int qp_attr_mask);

/**
 * ib_query_qp - Returns the attribute list and current values for the
 *   specified QP.
 * @qp: The QP to query.
 * @qp_attr: The attributes of the specified QP.
 * @qp_attr_mask: A bit-mask used to select specific attributes to query.
 * @qp_init_attr: Additional attributes of the selected QP.
 *
 * The qp_attr_mask may be used to limit the query to gathering only the
 * selected attributes.
 */
int ib_query_qp(struct ib_qp *qp,
		struct ib_qp_attr *qp_attr,
		int qp_attr_mask,
		struct ib_qp_init_attr *qp_init_attr);

/**
 * ib_destroy_qp - Destroys the specified QP.
 * @qp: The QP to destroy.
 */
int ib_destroy_qp(struct ib_qp *qp);

3117
/**
3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128
 * ib_open_qp - Obtain a reference to an existing sharable QP.
 * @xrcd - XRC domain
 * @qp_open_attr: Attributes identifying the QP to open.
 *
 * Returns a reference to a sharable QP.
 */
struct ib_qp *ib_open_qp(struct ib_xrcd *xrcd,
			 struct ib_qp_open_attr *qp_open_attr);

/**
 * ib_close_qp - Release an external reference to a QP.
3129 3130
 * @qp: The QP handle to release
 *
3131 3132
 * The opened QP handle is released by the caller.  The underlying
 * shared QP is not destroyed until all internal references are released.
3133
 */
3134
int ib_close_qp(struct ib_qp *qp);
3135

L
Linus Torvalds 已提交
3136 3137 3138 3139 3140 3141 3142
/**
 * ib_post_send - Posts a list of work requests to the send queue of
 *   the specified QP.
 * @qp: The QP to post the work request on.
 * @send_wr: A list of work requests to post on the send queue.
 * @bad_send_wr: On an immediate failure, this parameter will reference
 *   the work request that failed to be posted on the QP.
3143 3144 3145 3146 3147
 *
 * While IBA Vol. 1 section 11.4.1.1 specifies that if an immediate
 * error is returned, the QP state shall not be affected,
 * ib_post_send() will return an immediate error after queueing any
 * earlier work requests in the list.
L
Linus Torvalds 已提交
3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170
 */
static inline int ib_post_send(struct ib_qp *qp,
			       struct ib_send_wr *send_wr,
			       struct ib_send_wr **bad_send_wr)
{
	return qp->device->post_send(qp, send_wr, bad_send_wr);
}

/**
 * ib_post_recv - Posts a list of work requests to the receive queue of
 *   the specified QP.
 * @qp: The QP to post the work request on.
 * @recv_wr: A list of work requests to post on the receive queue.
 * @bad_recv_wr: On an immediate failure, this parameter will reference
 *   the work request that failed to be posted on the QP.
 */
static inline int ib_post_recv(struct ib_qp *qp,
			       struct ib_recv_wr *recv_wr,
			       struct ib_recv_wr **bad_recv_wr)
{
	return qp->device->post_recv(qp, recv_wr, bad_recv_wr);
}

3171 3172 3173 3174 3175 3176
struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private,
			    int nr_cqe, int comp_vector,
			    enum ib_poll_context poll_ctx, const char *caller);
#define ib_alloc_cq(device, priv, nr_cqe, comp_vect, poll_ctx) \
	__ib_alloc_cq((device), (priv), (nr_cqe), (comp_vect), (poll_ctx), KBUILD_MODNAME)

3177 3178 3179
void ib_free_cq(struct ib_cq *cq);
int ib_process_cq_direct(struct ib_cq *cq, int budget);

L
Linus Torvalds 已提交
3180 3181 3182 3183 3184 3185 3186 3187 3188
/**
 * ib_create_cq - Creates a CQ on the specified device.
 * @device: The device on which to create the CQ.
 * @comp_handler: A user-specified callback that is invoked when a
 *   completion event occurs on the CQ.
 * @event_handler: A user-specified callback that is invoked when an
 *   asynchronous event not associated with a completion occurs on the CQ.
 * @cq_context: Context associated with the CQ returned to the user via
 *   the associated completion and event handlers.
3189
 * @cq_attr: The attributes the CQ should be created upon.
L
Linus Torvalds 已提交
3190 3191 3192 3193 3194 3195
 *
 * Users can examine the cq structure to determine the actual CQ size.
 */
struct ib_cq *ib_create_cq(struct ib_device *device,
			   ib_comp_handler comp_handler,
			   void (*event_handler)(struct ib_event *, void *),
3196 3197
			   void *cq_context,
			   const struct ib_cq_init_attr *cq_attr);
L
Linus Torvalds 已提交
3198 3199 3200 3201 3202 3203 3204 3205 3206 3207

/**
 * ib_resize_cq - Modifies the capacity of the CQ.
 * @cq: The CQ to resize.
 * @cqe: The minimum size of the CQ.
 *
 * Users can examine the cq structure to determine the actual CQ size.
 */
int ib_resize_cq(struct ib_cq *cq, int cqe);

E
Eli Cohen 已提交
3208
/**
3209
 * rdma_set_cq_moderation - Modifies moderation params of the CQ
E
Eli Cohen 已提交
3210 3211 3212 3213 3214
 * @cq: The CQ to modify.
 * @cq_count: number of CQEs that will trigger an event
 * @cq_period: max period of time in usec before triggering an event
 *
 */
3215
int rdma_set_cq_moderation(struct ib_cq *cq, u16 cq_count, u16 cq_period);
E
Eli Cohen 已提交
3216

L
Linus Torvalds 已提交
3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243
/**
 * ib_destroy_cq - Destroys the specified CQ.
 * @cq: The CQ to destroy.
 */
int ib_destroy_cq(struct ib_cq *cq);

/**
 * ib_poll_cq - poll a CQ for completion(s)
 * @cq:the CQ being polled
 * @num_entries:maximum number of completions to return
 * @wc:array of at least @num_entries &struct ib_wc where completions
 *   will be returned
 *
 * Poll a CQ for (possibly multiple) completions.  If the return value
 * is < 0, an error occurred.  If the return value is >= 0, it is the
 * number of completions returned.  If the return value is
 * non-negative and < num_entries, then the CQ was emptied.
 */
static inline int ib_poll_cq(struct ib_cq *cq, int num_entries,
			     struct ib_wc *wc)
{
	return cq->device->poll_cq(cq, num_entries, wc);
}

/**
 * ib_req_notify_cq - Request completion notification on a CQ.
 * @cq: The CQ to generate an event for.
3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266
 * @flags:
 *   Must contain exactly one of %IB_CQ_SOLICITED or %IB_CQ_NEXT_COMP
 *   to request an event on the next solicited event or next work
 *   completion at any type, respectively. %IB_CQ_REPORT_MISSED_EVENTS
 *   may also be |ed in to request a hint about missed events, as
 *   described below.
 *
 * Return Value:
 *    < 0 means an error occurred while requesting notification
 *   == 0 means notification was requested successfully, and if
 *        IB_CQ_REPORT_MISSED_EVENTS was passed in, then no events
 *        were missed and it is safe to wait for another event.  In
 *        this case is it guaranteed that any work completions added
 *        to the CQ since the last CQ poll will trigger a completion
 *        notification event.
 *    > 0 is only returned if IB_CQ_REPORT_MISSED_EVENTS was passed
 *        in.  It means that the consumer must poll the CQ again to
 *        make sure it is empty to avoid missing an event because of a
 *        race between requesting notification and an entry being
 *        added to the CQ.  This return value means it is possible
 *        (but not guaranteed) that a work completion has been added
 *        to the CQ since the last poll without triggering a
 *        completion notification event.
L
Linus Torvalds 已提交
3267 3268
 */
static inline int ib_req_notify_cq(struct ib_cq *cq,
3269
				   enum ib_cq_notify_flags flags)
L
Linus Torvalds 已提交
3270
{
3271
	return cq->device->req_notify_cq(cq, flags);
L
Linus Torvalds 已提交
3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287
}

/**
 * ib_req_ncomp_notif - Request completion notification when there are
 *   at least the specified number of unreaped completions on the CQ.
 * @cq: The CQ to generate an event for.
 * @wc_cnt: The number of unreaped completions that should be on the
 *   CQ before an event is generated.
 */
static inline int ib_req_ncomp_notif(struct ib_cq *cq, int wc_cnt)
{
	return cq->device->req_ncomp_notif ?
		cq->device->req_ncomp_notif(cq, wc_cnt) :
		-ENOSYS;
}

3288 3289 3290 3291 3292 3293 3294
/**
 * ib_dma_mapping_error - check a DMA addr for error
 * @dev: The device for which the dma_addr was created
 * @dma_addr: The DMA address to check
 */
static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr)
{
3295
	return dma_mapping_error(dev->dma_device, dma_addr);
3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308
}

/**
 * ib_dma_map_single - Map a kernel virtual address to DMA address
 * @dev: The device for which the dma_addr is to be created
 * @cpu_addr: The kernel virtual address
 * @size: The size of the region in bytes
 * @direction: The direction of the DMA
 */
static inline u64 ib_dma_map_single(struct ib_device *dev,
				    void *cpu_addr, size_t size,
				    enum dma_data_direction direction)
{
3309
	return dma_map_single(dev->dma_device, cpu_addr, size, direction);
3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322
}

/**
 * ib_dma_unmap_single - Destroy a mapping created by ib_dma_map_single()
 * @dev: The device for which the DMA address was created
 * @addr: The DMA address
 * @size: The size of the region in bytes
 * @direction: The direction of the DMA
 */
static inline void ib_dma_unmap_single(struct ib_device *dev,
				       u64 addr, size_t size,
				       enum dma_data_direction direction)
{
3323
	dma_unmap_single(dev->dma_device, addr, size, direction);
3324 3325
}

3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339
/**
 * ib_dma_map_page - Map a physical page to DMA address
 * @dev: The device for which the dma_addr is to be created
 * @page: The page to be mapped
 * @offset: The offset within the page
 * @size: The size of the region in bytes
 * @direction: The direction of the DMA
 */
static inline u64 ib_dma_map_page(struct ib_device *dev,
				  struct page *page,
				  unsigned long offset,
				  size_t size,
					 enum dma_data_direction direction)
{
3340
	return dma_map_page(dev->dma_device, page, offset, size, direction);
3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353
}

/**
 * ib_dma_unmap_page - Destroy a mapping created by ib_dma_map_page()
 * @dev: The device for which the DMA address was created
 * @addr: The DMA address
 * @size: The size of the region in bytes
 * @direction: The direction of the DMA
 */
static inline void ib_dma_unmap_page(struct ib_device *dev,
				     u64 addr, size_t size,
				     enum dma_data_direction direction)
{
3354
	dma_unmap_page(dev->dma_device, addr, size, direction);
3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367
}

/**
 * ib_dma_map_sg - Map a scatter/gather list to DMA addresses
 * @dev: The device for which the DMA addresses are to be created
 * @sg: The array of scatter/gather entries
 * @nents: The number of scatter/gather entries
 * @direction: The direction of the DMA
 */
static inline int ib_dma_map_sg(struct ib_device *dev,
				struct scatterlist *sg, int nents,
				enum dma_data_direction direction)
{
3368
	return dma_map_sg(dev->dma_device, sg, nents, direction);
3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381
}

/**
 * ib_dma_unmap_sg - Unmap a scatter/gather list of DMA addresses
 * @dev: The device for which the DMA addresses were created
 * @sg: The array of scatter/gather entries
 * @nents: The number of scatter/gather entries
 * @direction: The direction of the DMA
 */
static inline void ib_dma_unmap_sg(struct ib_device *dev,
				   struct scatterlist *sg, int nents,
				   enum dma_data_direction direction)
{
3382
	dma_unmap_sg(dev->dma_device, sg, nents, direction);
3383 3384
}

3385 3386 3387
static inline int ib_dma_map_sg_attrs(struct ib_device *dev,
				      struct scatterlist *sg, int nents,
				      enum dma_data_direction direction,
3388
				      unsigned long dma_attrs)
3389
{
3390 3391
	return dma_map_sg_attrs(dev->dma_device, sg, nents, direction,
				dma_attrs);
3392 3393 3394 3395 3396
}

static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev,
					 struct scatterlist *sg, int nents,
					 enum dma_data_direction direction,
3397
					 unsigned long dma_attrs)
3398
{
3399
	dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs);
3400
}
3401 3402 3403 3404
/**
 * ib_sg_dma_address - Return the DMA address from a scatter/gather entry
 * @dev: The device for which the DMA addresses were created
 * @sg: The scatter/gather entry
3405 3406 3407
 *
 * Note: this function is obsolete. To do: change all occurrences of
 * ib_sg_dma_address() into sg_dma_address().
3408 3409 3410 3411
 */
static inline u64 ib_sg_dma_address(struct ib_device *dev,
				    struct scatterlist *sg)
{
3412
	return sg_dma_address(sg);
3413 3414 3415 3416 3417 3418
}

/**
 * ib_sg_dma_len - Return the DMA length from a scatter/gather entry
 * @dev: The device for which the DMA addresses were created
 * @sg: The scatter/gather entry
3419 3420 3421
 *
 * Note: this function is obsolete. To do: change all occurrences of
 * ib_sg_dma_len() into sg_dma_len().
3422 3423 3424 3425
 */
static inline unsigned int ib_sg_dma_len(struct ib_device *dev,
					 struct scatterlist *sg)
{
3426
	return sg_dma_len(sg);
3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440
}

/**
 * ib_dma_sync_single_for_cpu - Prepare DMA region to be accessed by CPU
 * @dev: The device for which the DMA address was created
 * @addr: The DMA address
 * @size: The size of the region in bytes
 * @dir: The direction of the DMA
 */
static inline void ib_dma_sync_single_for_cpu(struct ib_device *dev,
					      u64 addr,
					      size_t size,
					      enum dma_data_direction dir)
{
3441
	dma_sync_single_for_cpu(dev->dma_device, addr, size, dir);
3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455
}

/**
 * ib_dma_sync_single_for_device - Prepare DMA region to be accessed by device
 * @dev: The device for which the DMA address was created
 * @addr: The DMA address
 * @size: The size of the region in bytes
 * @dir: The direction of the DMA
 */
static inline void ib_dma_sync_single_for_device(struct ib_device *dev,
						 u64 addr,
						 size_t size,
						 enum dma_data_direction dir)
{
3456
	dma_sync_single_for_device(dev->dma_device, addr, size, dir);
3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467
}

/**
 * ib_dma_alloc_coherent - Allocate memory and map it for DMA
 * @dev: The device for which the DMA address is requested
 * @size: The size of the region to allocate in bytes
 * @dma_handle: A pointer for returning the DMA address of the region
 * @flag: memory allocator flags
 */
static inline void *ib_dma_alloc_coherent(struct ib_device *dev,
					   size_t size,
3468
					   dma_addr_t *dma_handle,
3469 3470
					   gfp_t flag)
{
3471
	return dma_alloc_coherent(dev->dma_device, size, dma_handle, flag);
3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482
}

/**
 * ib_dma_free_coherent - Free memory allocated by ib_dma_alloc_coherent()
 * @dev: The device for which the DMA addresses were allocated
 * @size: The size of the region
 * @cpu_addr: the address returned by ib_dma_alloc_coherent()
 * @dma_handle: the DMA address returned by ib_dma_alloc_coherent()
 */
static inline void ib_dma_free_coherent(struct ib_device *dev,
					size_t size, void *cpu_addr,
3483
					dma_addr_t dma_handle)
3484
{
3485
	dma_free_coherent(dev->dma_device, size, cpu_addr, dma_handle);
3486 3487
}

L
Linus Torvalds 已提交
3488 3489 3490 3491
/**
 * ib_dereg_mr - Deregisters a memory region and removes it from the
 *   HCA translation table.
 * @mr: The memory region to deregister.
3492 3493
 *
 * This function can fail, if the memory region has memory windows bound to it.
L
Linus Torvalds 已提交
3494 3495 3496
 */
int ib_dereg_mr(struct ib_mr *mr);

S
Sagi Grimberg 已提交
3497 3498 3499
struct ib_mr *ib_alloc_mr(struct ib_pd *pd,
			  enum ib_mr_type mr_type,
			  u32 max_num_sg);
3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512

/**
 * ib_update_fast_reg_key - updates the key portion of the fast_reg MR
 *   R_Key and L_Key.
 * @mr - struct ib_mr pointer to be updated.
 * @newkey - new key to be used.
 */
static inline void ib_update_fast_reg_key(struct ib_mr *mr, u8 newkey)
{
	mr->lkey = (mr->lkey & 0xffffff00) | newkey;
	mr->rkey = (mr->rkey & 0xffffff00) | newkey;
}

3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523
/**
 * ib_inc_rkey - increments the key portion of the given rkey. Can be used
 * for calculating a new rkey for type 2 memory windows.
 * @rkey - the rkey to increment.
 */
static inline u32 ib_inc_rkey(u32 rkey)
{
	const u32 mask = 0x000000ff;
	return ((rkey + 1) & mask) | (rkey & ~mask);
}

L
Linus Torvalds 已提交
3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584
/**
 * ib_alloc_fmr - Allocates a unmapped fast memory region.
 * @pd: The protection domain associated with the unmapped region.
 * @mr_access_flags: Specifies the memory access rights.
 * @fmr_attr: Attributes of the unmapped region.
 *
 * A fast memory region must be mapped before it can be used as part of
 * a work request.
 */
struct ib_fmr *ib_alloc_fmr(struct ib_pd *pd,
			    int mr_access_flags,
			    struct ib_fmr_attr *fmr_attr);

/**
 * ib_map_phys_fmr - Maps a list of physical pages to a fast memory region.
 * @fmr: The fast memory region to associate with the pages.
 * @page_list: An array of physical pages to map to the fast memory region.
 * @list_len: The number of pages in page_list.
 * @iova: The I/O virtual address to use with the mapped region.
 */
static inline int ib_map_phys_fmr(struct ib_fmr *fmr,
				  u64 *page_list, int list_len,
				  u64 iova)
{
	return fmr->device->map_phys_fmr(fmr, page_list, list_len, iova);
}

/**
 * ib_unmap_fmr - Removes the mapping from a list of fast memory regions.
 * @fmr_list: A linked list of fast memory regions to unmap.
 */
int ib_unmap_fmr(struct list_head *fmr_list);

/**
 * ib_dealloc_fmr - Deallocates a fast memory region.
 * @fmr: The fast memory region to deallocate.
 */
int ib_dealloc_fmr(struct ib_fmr *fmr);

/**
 * ib_attach_mcast - Attaches the specified QP to a multicast group.
 * @qp: QP to attach to the multicast group.  The QP must be type
 *   IB_QPT_UD.
 * @gid: Multicast group GID.
 * @lid: Multicast group LID in host byte order.
 *
 * In order to send and receive multicast packets, subnet
 * administration must have created the multicast group and configured
 * the fabric appropriately.  The port associated with the specified
 * QP must also be a member of the multicast group.
 */
int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid);

/**
 * ib_detach_mcast - Detaches the specified QP from a multicast group.
 * @qp: QP to detach from the multicast group.
 * @gid: Multicast group GID.
 * @lid: Multicast group LID in host byte order.
 */
int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid);

S
Sean Hefty 已提交
3585 3586 3587
/**
 * ib_alloc_xrcd - Allocates an XRC domain.
 * @device: The device on which to allocate the XRC domain.
3588
 * @caller: Module name for kernel consumers
S
Sean Hefty 已提交
3589
 */
3590 3591 3592
struct ib_xrcd *__ib_alloc_xrcd(struct ib_device *device, const char *caller);
#define ib_alloc_xrcd(device) \
	__ib_alloc_xrcd((device), KBUILD_MODNAME)
S
Sean Hefty 已提交
3593 3594 3595 3596 3597 3598 3599

/**
 * ib_dealloc_xrcd - Deallocates an XRC domain.
 * @xrcd: The XRC domain to deallocate.
 */
int ib_dealloc_xrcd(struct ib_xrcd *xrcd);

3600 3601 3602 3603
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);

3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616
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;
}

3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631
/**
 * ib_check_mr_status: lightweight check of MR status.
 *     This routine may provide status checks on a selected
 *     ib_mr. first use is for signature status check.
 *
 * @mr: A memory region.
 * @check_mask: Bitmask of which checks to perform from
 *     ib_mr_status_check enumeration.
 * @mr_status: The container of relevant status checks.
 *     failed checks will be indicated in the status bitmask
 *     and the relevant info shall be in the error item.
 */
int ib_check_mr_status(struct ib_mr *mr, u32 check_mask,
		       struct ib_mr_status *mr_status);

3632 3633 3634
struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u8 port,
					    u16 pkey, const union ib_gid *gid,
					    const struct sockaddr *addr);
3635 3636 3637 3638 3639
struct ib_wq *ib_create_wq(struct ib_pd *pd,
			   struct ib_wq_init_attr *init_attr);
int ib_destroy_wq(struct ib_wq *wq);
int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *attr,
		 u32 wq_attr_mask);
3640 3641 3642 3643
struct ib_rwq_ind_table *ib_create_rwq_ind_table(struct ib_device *device,
						 struct ib_rwq_ind_table_init_attr*
						 wq_ind_table_init_attr);
int ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table);
3644

3645
int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
3646
		 unsigned int *sg_offset, unsigned int page_size);
3647 3648

static inline int
3649
ib_map_mr_sg_zbva(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
3650
		  unsigned int *sg_offset, unsigned int page_size)
3651 3652 3653
{
	int n;

3654
	n = ib_map_mr_sg(mr, sg, sg_nents, sg_offset, page_size);
3655 3656 3657 3658 3659
	mr->iova = 0;

	return n;
}

3660
int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents,
3661
		unsigned int *sg_offset, int (*set_page)(struct ib_mr *, u64));
3662

3663 3664 3665
void ib_drain_rq(struct ib_qp *qp);
void ib_drain_sq(struct ib_qp *qp);
void ib_drain_qp(struct ib_qp *qp);
3666

3667
int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width);
3668 3669 3670

static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr)
{
3671 3672 3673
	if (attr->type == RDMA_AH_ATTR_TYPE_ROCE)
		return attr->roce.dmac;
	return NULL;
3674 3675
}

3676
static inline void rdma_ah_set_dlid(struct rdma_ah_attr *attr, u32 dlid)
3677
{
3678
	if (attr->type == RDMA_AH_ATTR_TYPE_IB)
3679 3680 3681
		attr->ib.dlid = (u16)dlid;
	else if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
		attr->opa.dlid = dlid;
3682 3683
}

3684
static inline u32 rdma_ah_get_dlid(const struct rdma_ah_attr *attr)
3685
{
3686 3687
	if (attr->type == RDMA_AH_ATTR_TYPE_IB)
		return attr->ib.dlid;
3688 3689
	else if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
		return attr->opa.dlid;
3690
	return 0;
3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705
}

static inline void rdma_ah_set_sl(struct rdma_ah_attr *attr, u8 sl)
{
	attr->sl = sl;
}

static inline u8 rdma_ah_get_sl(const struct rdma_ah_attr *attr)
{
	return attr->sl;
}

static inline void rdma_ah_set_path_bits(struct rdma_ah_attr *attr,
					 u8 src_path_bits)
{
3706 3707
	if (attr->type == RDMA_AH_ATTR_TYPE_IB)
		attr->ib.src_path_bits = src_path_bits;
3708 3709
	else if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
		attr->opa.src_path_bits = src_path_bits;
3710 3711 3712 3713
}

static inline u8 rdma_ah_get_path_bits(const struct rdma_ah_attr *attr)
{
3714 3715
	if (attr->type == RDMA_AH_ATTR_TYPE_IB)
		return attr->ib.src_path_bits;
3716 3717
	else if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
		return attr->opa.src_path_bits;
3718
	return 0;
3719 3720
}

3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734
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;
}

3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818
static inline void rdma_ah_set_port_num(struct rdma_ah_attr *attr, u8 port_num)
{
	attr->port_num = port_num;
}

static inline u8 rdma_ah_get_port_num(const struct rdma_ah_attr *attr)
{
	return attr->port_num;
}

static inline void rdma_ah_set_static_rate(struct rdma_ah_attr *attr,
					   u8 static_rate)
{
	attr->static_rate = static_rate;
}

static inline u8 rdma_ah_get_static_rate(const struct rdma_ah_attr *attr)
{
	return attr->static_rate;
}

static inline void rdma_ah_set_ah_flags(struct rdma_ah_attr *attr,
					enum ib_ah_flags flag)
{
	attr->ah_flags = flag;
}

static inline enum ib_ah_flags
		rdma_ah_get_ah_flags(const struct rdma_ah_attr *attr)
{
	return attr->ah_flags;
}

static inline const struct ib_global_route
		*rdma_ah_read_grh(const struct rdma_ah_attr *attr)
{
	return &attr->grh;
}

/*To retrieve and modify the grh */
static inline struct ib_global_route
		*rdma_ah_retrieve_grh(struct rdma_ah_attr *attr)
{
	return &attr->grh;
}

static inline void rdma_ah_set_dgid_raw(struct rdma_ah_attr *attr, void *dgid)
{
	struct ib_global_route *grh = rdma_ah_retrieve_grh(attr);

	memcpy(grh->dgid.raw, dgid, sizeof(grh->dgid));
}

static inline void rdma_ah_set_subnet_prefix(struct rdma_ah_attr *attr,
					     __be64 prefix)
{
	struct ib_global_route *grh = rdma_ah_retrieve_grh(attr);

	grh->dgid.global.subnet_prefix = prefix;
}

static inline void rdma_ah_set_interface_id(struct rdma_ah_attr *attr,
					    __be64 if_id)
{
	struct ib_global_route *grh = rdma_ah_retrieve_grh(attr);

	grh->dgid.global.interface_id = if_id;
}

static inline void rdma_ah_set_grh(struct rdma_ah_attr *attr,
				   union ib_gid *dgid, u32 flow_label,
				   u8 sgid_index, u8 hop_limit,
				   u8 traffic_class)
{
	struct ib_global_route *grh = rdma_ah_retrieve_grh(attr);

	attr->ah_flags = IB_AH_GRH;
	if (dgid)
		grh->dgid = *dgid;
	grh->flow_label = flow_label;
	grh->sgid_index = sgid_index;
	grh->hop_limit = hop_limit;
	grh->traffic_class = traffic_class;
}
3819

3820 3821 3822 3823 3824 3825
/**
 * rdma_ah_find_type - Return address handle type.
 *
 * @dev: Device to be checked
 * @port_num: Port number
 */
3826
static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev,
3827
						       u8 port_num)
3828
{
3829
	if (rdma_protocol_roce(dev, port_num))
3830
		return RDMA_AH_ATTR_TYPE_ROCE;
3831 3832 3833
	if (rdma_protocol_ib(dev, port_num)) {
		if (rdma_cap_opa_ah(dev, port_num))
			return RDMA_AH_ATTR_TYPE_OPA;
3834
		return RDMA_AH_ATTR_TYPE_IB;
3835 3836 3837
	}

	return RDMA_AH_ATTR_TYPE_UNDEFINED;
3838
}
3839

H
Hiatt, Don 已提交
3840 3841 3842 3843 3844 3845 3846 3847 3848 3849
/**
 * 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)
3850
{
H
Hiatt, Don 已提交
3851 3852
	WARN_ON_ONCE(lid & 0xFFFF0000);
	return (u16)lid;
3853 3854
}

H
Hiatt, Don 已提交
3855 3856 3857 3858 3859 3860
/**
 * ib_lid_be16 - Return lid in 16bit BE encoding.
 *
 * @lid: A 32bit LID
 */
static inline __be16 ib_lid_be16(u32 lid)
3861
{
H
Hiatt, Don 已提交
3862 3863
	WARN_ON_ONCE(lid & 0xFFFF0000);
	return cpu_to_be16((u16)lid);
3864
}
3865

3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886
/**
 * 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);

}

3887 3888 3889 3890 3891 3892 3893 3894
/**
 * rdma_roce_rescan_device - Rescan all of the network devices in the system
 * and add their gids, as needed, to the relevant RoCE devices.
 *
 * @device:         the rdma device
 */
void rdma_roce_rescan_device(struct ib_device *ibdev);

L
Linus Torvalds 已提交
3895
#endif /* IB_VERBS_H */