blob: 975d6e9efbcb441f25eecd630486530cd82107cd [file] [log] [blame]
/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
/*
* Copyright (c) 2004 Mellanox Technologies Ltd. All rights reserved.
* Copyright (c) 2004 Infinicon Corporation. All rights reserved.
* Copyright (c) 2004, 2020 Intel Corporation. All rights reserved.
* Copyright (c) 2004 Topspin Corporation. All rights reserved.
* Copyright (c) 2004 Voltaire Corporation. All rights reserved.
* Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
* Copyright (c) 2005, 2006, 2007 Cisco Systems. All rights reserved.
*/
#ifndef IB_VERBS_H
#define IB_VERBS_H
#include <linux/ethtool.h>
#include <linux/types.h>
#include <linux/device.h>
#include <linux/dma-mapping.h>
#include <linux/kref.h>
#include <linux/list.h>
#include <linux/rwsem.h>
#include <linux/workqueue.h>
#include <linux/irq_poll.h>
#include <uapi/linux/if_ether.h>
#include <net/ipv6.h>
#include <net/ip.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/refcount.h>
#include <linux/if_link.h>
#include <linux/atomic.h>
#include <linux/mmu_notifier.h>
#include <linux/uaccess.h>
#include <linux/cgroup_rdma.h>
#include <linux/irqflags.h>
#include <linux/preempt.h>
#include <linux/dim.h>
#include <uapi/rdma/ib_user_verbs.h>
#include <rdma/rdma_counter.h>
#include <rdma/restrack.h>
#include <rdma/signature.h>
#include <uapi/rdma/rdma_user_ioctl.h>
#include <uapi/rdma/ib_user_ioctl_verbs.h>
#define IB_FW_VERSION_NAME_MAX ETHTOOL_FWVERS_LEN
struct ib_umem_odp;
struct ib_uqp_object;
struct ib_usrq_object;
struct ib_uwq_object;
struct rdma_cm_id;
struct ib_port;
struct hw_stats_device_data;
extern struct workqueue_struct *ib_wq;
extern struct workqueue_struct *ib_comp_wq;
extern struct workqueue_struct *ib_comp_unbound_wq;
struct ib_ucq_object;
__printf(3, 4) __cold
void ibdev_printk(const char *level, const struct ib_device *ibdev,
const char *format, ...);
__printf(2, 3) __cold
void ibdev_emerg(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_alert(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_crit(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_err(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_warn(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_notice(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_info(const struct ib_device *ibdev, const char *format, ...);
#if defined(CONFIG_DYNAMIC_DEBUG) || \
(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
#define ibdev_dbg(__dev, format, args...) \
dynamic_ibdev_dbg(__dev, format, ##args)
#else
__printf(2, 3) __cold
static inline
void ibdev_dbg(const struct ib_device *ibdev, const char *format, ...) {}
#endif
#define ibdev_level_ratelimited(ibdev_level, ibdev, fmt, ...) \
do { \
static DEFINE_RATELIMIT_STATE(_rs, \
DEFAULT_RATELIMIT_INTERVAL, \
DEFAULT_RATELIMIT_BURST); \
if (__ratelimit(&_rs)) \
ibdev_level(ibdev, fmt, ##__VA_ARGS__); \
} while (0)
#define ibdev_emerg_ratelimited(ibdev, fmt, ...) \
ibdev_level_ratelimited(ibdev_emerg, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_alert_ratelimited(ibdev, fmt, ...) \
ibdev_level_ratelimited(ibdev_alert, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_crit_ratelimited(ibdev, fmt, ...) \
ibdev_level_ratelimited(ibdev_crit, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_err_ratelimited(ibdev, fmt, ...) \
ibdev_level_ratelimited(ibdev_err, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_warn_ratelimited(ibdev, fmt, ...) \
ibdev_level_ratelimited(ibdev_warn, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_notice_ratelimited(ibdev, fmt, ...) \
ibdev_level_ratelimited(ibdev_notice, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_info_ratelimited(ibdev, fmt, ...) \
ibdev_level_ratelimited(ibdev_info, ibdev, fmt, ##__VA_ARGS__)
#if defined(CONFIG_DYNAMIC_DEBUG) || \
(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
/* descriptor check is first to prevent flooding with "callbacks suppressed" */
#define ibdev_dbg_ratelimited(ibdev, fmt, ...) \
do { \
static DEFINE_RATELIMIT_STATE(_rs, \
DEFAULT_RATELIMIT_INTERVAL, \
DEFAULT_RATELIMIT_BURST); \
DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \
if (DYNAMIC_DEBUG_BRANCH(descriptor) && __ratelimit(&_rs)) \
__dynamic_ibdev_dbg(&descriptor, ibdev, fmt, \
##__VA_ARGS__); \
} while (0)
#else
__printf(2, 3) __cold
static inline
void ibdev_dbg_ratelimited(const struct ib_device *ibdev, const char *format, ...) {}
#endif
union ib_gid {
u8 raw[16];
struct {
__be64 subnet_prefix;
__be64 interface_id;
} global;
};
extern union ib_gid zgid;
enum ib_gid_type {
IB_GID_TYPE_IB = IB_UVERBS_GID_TYPE_IB,
IB_GID_TYPE_ROCE = IB_UVERBS_GID_TYPE_ROCE_V1,
IB_GID_TYPE_ROCE_UDP_ENCAP = IB_UVERBS_GID_TYPE_ROCE_V2,
IB_GID_TYPE_SIZE
};
#define ROCE_V2_UDP_DPORT 4791
struct ib_gid_attr {
struct net_device __rcu *ndev;
struct ib_device *device;
union ib_gid gid;
enum ib_gid_type gid_type;
u16 index;
u32 port_num;
};
enum {
/* set the local administered indication */
IB_SA_WELL_KNOWN_GUID = BIT_ULL(57) | 2,
};
enum rdma_transport_type {
RDMA_TRANSPORT_IB,
RDMA_TRANSPORT_IWARP,
RDMA_TRANSPORT_USNIC,
RDMA_TRANSPORT_USNIC_UDP,
RDMA_TRANSPORT_UNSPECIFIED,
};
enum rdma_protocol_type {
RDMA_PROTOCOL_IB,
RDMA_PROTOCOL_IBOE,
RDMA_PROTOCOL_IWARP,
RDMA_PROTOCOL_USNIC_UDP
};
__attribute_const__ enum rdma_transport_type
rdma_node_get_transport(unsigned int node_type);
enum rdma_network_type {
RDMA_NETWORK_IB,
RDMA_NETWORK_ROCE_V1,
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;
else if (network_type == RDMA_NETWORK_ROCE_V1)
return IB_GID_TYPE_ROCE;
else
return IB_GID_TYPE_IB;
}
static inline enum rdma_network_type
rdma_gid_attr_network_type(const struct ib_gid_attr *attr)
{
if (attr->gid_type == IB_GID_TYPE_IB)
return RDMA_NETWORK_IB;
if (attr->gid_type == IB_GID_TYPE_ROCE)
return RDMA_NETWORK_ROCE_V1;
if (ipv6_addr_v4mapped((struct in6_addr *)&attr->gid))
return RDMA_NETWORK_IPV4;
else
return RDMA_NETWORK_IPV6;
}
enum rdma_link_layer {
IB_LINK_LAYER_UNSPECIFIED,
IB_LINK_LAYER_INFINIBAND,
IB_LINK_LAYER_ETHERNET,
};
enum ib_device_cap_flags {
IB_DEVICE_RESIZE_MAX_WR = IB_UVERBS_DEVICE_RESIZE_MAX_WR,
IB_DEVICE_BAD_PKEY_CNTR = IB_UVERBS_DEVICE_BAD_PKEY_CNTR,
IB_DEVICE_BAD_QKEY_CNTR = IB_UVERBS_DEVICE_BAD_QKEY_CNTR,
IB_DEVICE_RAW_MULTI = IB_UVERBS_DEVICE_RAW_MULTI,
IB_DEVICE_AUTO_PATH_MIG = IB_UVERBS_DEVICE_AUTO_PATH_MIG,
IB_DEVICE_CHANGE_PHY_PORT = IB_UVERBS_DEVICE_CHANGE_PHY_PORT,
IB_DEVICE_UD_AV_PORT_ENFORCE = IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE,
IB_DEVICE_CURR_QP_STATE_MOD = IB_UVERBS_DEVICE_CURR_QP_STATE_MOD,
IB_DEVICE_SHUTDOWN_PORT = IB_UVERBS_DEVICE_SHUTDOWN_PORT,
/* IB_DEVICE_INIT_TYPE = IB_UVERBS_DEVICE_INIT_TYPE, (not in use) */
IB_DEVICE_PORT_ACTIVE_EVENT = IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT,
IB_DEVICE_SYS_IMAGE_GUID = IB_UVERBS_DEVICE_SYS_IMAGE_GUID,
IB_DEVICE_RC_RNR_NAK_GEN = IB_UVERBS_DEVICE_RC_RNR_NAK_GEN,
IB_DEVICE_SRQ_RESIZE = IB_UVERBS_DEVICE_SRQ_RESIZE,
IB_DEVICE_N_NOTIFY_CQ = IB_UVERBS_DEVICE_N_NOTIFY_CQ,
/* Reserved, old SEND_W_INV = 1 << 16,*/
IB_DEVICE_MEM_WINDOW = IB_UVERBS_DEVICE_MEM_WINDOW,
/*
* 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.
*/
IB_DEVICE_UD_IP_CSUM = IB_UVERBS_DEVICE_UD_IP_CSUM,
IB_DEVICE_XRC = IB_UVERBS_DEVICE_XRC,
/*
* 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.
*/
IB_DEVICE_MEM_MGT_EXTENSIONS = IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS,
IB_DEVICE_MEM_WINDOW_TYPE_2A = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A,
IB_DEVICE_MEM_WINDOW_TYPE_2B = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B,
IB_DEVICE_RC_IP_CSUM = IB_UVERBS_DEVICE_RC_IP_CSUM,
/* Deprecated. Please use IB_RAW_PACKET_CAP_IP_CSUM. */
IB_DEVICE_RAW_IP_CSUM = IB_UVERBS_DEVICE_RAW_IP_CSUM,
IB_DEVICE_MANAGED_FLOW_STEERING =
IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING,
/* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */
IB_DEVICE_RAW_SCATTER_FCS = IB_UVERBS_DEVICE_RAW_SCATTER_FCS,
/* The device supports padding incoming writes to cacheline. */
IB_DEVICE_PCI_WRITE_END_PADDING =
IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING,
};
enum ib_kernel_cap_flags {
/*
* 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.
*/
IBK_LOCAL_DMA_LKEY = 1 << 0,
/* IB_QP_CREATE_INTEGRITY_EN is supported to implement T10-PI */
IBK_INTEGRITY_HANDOVER = 1 << 1,
/* IB_ACCESS_ON_DEMAND is supported during reg_user_mr() */
IBK_ON_DEMAND_PAGING = 1 << 2,
/* IB_MR_TYPE_SG_GAPS is supported */
IBK_SG_GAPS_REG = 1 << 3,
/* Driver supports RDMA_NLDEV_CMD_DELLINK */
IBK_ALLOW_USER_UNREG = 1 << 4,
/* ipoib will use IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK */
IBK_BLOCK_MULTICAST_LOOPBACK = 1 << 5,
/* iopib will use IB_QP_CREATE_IPOIB_UD_LSO for its QPs */
IBK_UD_TSO = 1 << 6,
/* iopib will use the device ops:
* get_vf_config
* get_vf_guid
* get_vf_stats
* set_vf_guid
* set_vf_link_state
*/
IBK_VIRTUAL_FUNCTION = 1 << 7,
/* ipoib will use IB_QP_CREATE_NETDEV_USE for its QPs */
IBK_RDMA_NETDEV_OPA = 1 << 8,
};
enum ib_atomic_cap {
IB_ATOMIC_NONE,
IB_ATOMIC_HCA,
IB_ATOMIC_GLOB
};
enum ib_odp_general_cap_bits {
IB_ODP_SUPPORT = 1 << 0,
IB_ODP_SUPPORT_IMPLICIT = 1 << 1,
};
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,
IB_ODP_SUPPORT_SRQ_RECV = 1 << 5,
};
struct ib_odp_caps {
uint64_t general_caps;
struct {
uint32_t rc_odp_caps;
uint32_t uc_odp_caps;
uint32_t ud_odp_caps;
uint32_t xrc_odp_caps;
} per_transport_caps;
};
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;
};
enum ib_tm_cap_flags {
/* Support tag matching with rendezvous offload for RC transport */
IB_TM_CAP_RNDV_RC = 1 << 0,
};
struct ib_tm_caps {
/* Max size of RNDV header */
u32 max_rndv_hdr_size;
/* Max number of entries in tag matching list */
u32 max_num_tags;
/* From enum ib_tm_cap_flags */
u32 flags;
/* Max number of outstanding list operations */
u32 max_ops;
/* Max number of SGE in tag matching entry */
u32 max_sge;
};
struct ib_cq_init_attr {
unsigned int cqe;
u32 comp_vector;
u32 flags;
};
enum ib_cq_attr_mask {
IB_CQ_MODERATE = 1 << 0,
};
struct ib_cq_caps {
u16 max_cq_moderation_count;
u16 max_cq_moderation_period;
};
struct ib_dm_mr_attr {
u64 length;
u64 offset;
u32 access_flags;
};
struct ib_dm_alloc_attr {
u64 length;
u32 alignment;
u32 flags;
};
struct ib_device_attr {
u64 fw_ver;
__be64 sys_image_guid;
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;
u64 device_cap_flags;
u64 kernel_cap_flags;
int max_send_sge;
int max_recv_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;
enum ib_atomic_cap masked_atomic_cap;
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_srq;
int max_srq_wr;
int max_srq_sge;
unsigned int max_fast_reg_page_list_len;
unsigned int max_pi_fast_reg_page_list_len;
u16 max_pkeys;
u8 local_ca_ack_delay;
int sig_prot_cap;
int sig_guard_cap;
struct ib_odp_caps odp_caps;
uint64_t timestamp_mask;
uint64_t hca_core_clock; /* in KHZ */
struct ib_rss_caps rss_caps;
u32 max_wq_type_rq;
u32 raw_packet_caps; /* Use ib_raw_packet_caps enum */
struct ib_tm_caps tm_caps;
struct ib_cq_caps cq_caps;
u64 max_dm_size;
/* Max entries for sgl for optimized performance per READ */
u32 max_sgl_rd;
};
enum ib_mtu {
IB_MTU_256 = 1,
IB_MTU_512 = 2,
IB_MTU_1024 = 3,
IB_MTU_2048 = 4,
IB_MTU_4096 = 5
};
enum opa_mtu {
OPA_MTU_8192 = 6,
OPA_MTU_10240 = 7
};
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;
}
}
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;
}
static inline int opa_mtu_enum_to_int(enum opa_mtu mtu)
{
switch (mtu) {
case OPA_MTU_8192:
return 8192;
case OPA_MTU_10240:
return 10240;
default:
return(ib_mtu_enum_to_int((enum ib_mtu)mtu));
}
}
static inline enum opa_mtu opa_mtu_int_to_enum(int mtu)
{
if (mtu >= 10240)
return OPA_MTU_10240;
else if (mtu >= 8192)
return OPA_MTU_8192;
else
return ((enum opa_mtu)ib_mtu_int_to_enum(mtu));
}
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_phys_state {
IB_PORT_PHYS_STATE_SLEEP = 1,
IB_PORT_PHYS_STATE_POLLING = 2,
IB_PORT_PHYS_STATE_DISABLED = 3,
IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING = 4,
IB_PORT_PHYS_STATE_LINK_UP = 5,
IB_PORT_PHYS_STATE_LINK_ERROR_RECOVERY = 6,
IB_PORT_PHYS_STATE_PHY_TEST = 7,
};
enum ib_port_width {
IB_WIDTH_1X = 1,
IB_WIDTH_2X = 16,
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_2X: return 2;
case IB_WIDTH_4X: return 4;
case IB_WIDTH_8X: return 8;
case IB_WIDTH_12X: return 12;
default: return -1;
}
}
enum ib_port_speed {
IB_SPEED_SDR = 1,
IB_SPEED_DDR = 2,
IB_SPEED_QDR = 4,
IB_SPEED_FDR10 = 8,
IB_SPEED_FDR = 16,
IB_SPEED_EDR = 32,
IB_SPEED_HDR = 64,
IB_SPEED_NDR = 128,
};
enum ib_stat_flag {
IB_STAT_FLAG_OPTIONAL = 1 << 0,
};
/**
* struct rdma_stat_desc
* @name - The name of the counter
* @flags - Flags of the counter; For example, IB_STAT_FLAG_OPTIONAL
* @priv - Driver private information; Core code should not use
*/
struct rdma_stat_desc {
const char *name;
unsigned int flags;
const void *priv;
};
/**
* struct rdma_hw_stats
* @lock - Mutex to protect parallel write access to lifespan and values
* of counters, which are 64bits and not guaranteed to be written
* atomicaly on 32bits systems.
* @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.
* @descs - Array of pointers to static descriptors used for the counters
* in directory.
* @is_disabled - A bitmap to indicate each counter is currently disabled
* or not.
* @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 {
struct mutex lock; /* Protect lifespan and values[] */
unsigned long timestamp;
unsigned long lifespan;
const struct rdma_stat_desc *descs;
unsigned long *is_disabled;
int num_counters;
u64 value[];
};
#define RDMA_HW_STATS_DEFAULT_LIFESPAN 10
struct rdma_hw_stats *rdma_alloc_hw_stats_struct(
const struct rdma_stat_desc *descs, int num_counters,
unsigned long lifespan);
void rdma_free_hw_stats_struct(struct rdma_hw_stats *stats);
/* 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
#define RDMA_CORE_CAP_OPA_MAD 0x00000020
/* Address format 0x000FF000 */
#define RDMA_CORE_CAP_AF_IB 0x00001000
#define RDMA_CORE_CAP_ETH_AH 0x00002000
#define RDMA_CORE_CAP_OPA_AH 0x00004000
#define RDMA_CORE_CAP_IB_GRH_REQUIRED 0x00008000
/* Protocol 0xFFF00000 */
#define RDMA_CORE_CAP_PROT_IB 0x00100000
#define RDMA_CORE_CAP_PROT_ROCE 0x00200000
#define RDMA_CORE_CAP_PROT_IWARP 0x00400000
#define RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP 0x00800000
#define RDMA_CORE_CAP_PROT_RAW_PACKET 0x01000000
#define RDMA_CORE_CAP_PROT_USNIC 0x02000000
#define RDMA_CORE_PORT_IB_GRH_REQUIRED (RDMA_CORE_CAP_IB_GRH_REQUIRED \
| RDMA_CORE_CAP_PROT_ROCE \
| RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP)
#define RDMA_CORE_PORT_IBA_IB (RDMA_CORE_CAP_PROT_IB \
| RDMA_CORE_CAP_IB_MAD \
| RDMA_CORE_CAP_IB_SMI \
| 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)
#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)
#define RDMA_CORE_PORT_IWARP (RDMA_CORE_CAP_PROT_IWARP \
| RDMA_CORE_CAP_IW_CM)
#define RDMA_CORE_PORT_INTEL_OPA (RDMA_CORE_PORT_IBA_IB \
| RDMA_CORE_CAP_OPA_MAD)
#define RDMA_CORE_PORT_RAW_PACKET (RDMA_CORE_CAP_PROT_RAW_PACKET)
#define RDMA_CORE_PORT_USNIC (RDMA_CORE_CAP_PROT_USNIC)
struct ib_port_attr {
u64 subnet_prefix;
enum ib_port_state state;
enum ib_mtu max_mtu;
enum ib_mtu active_mtu;
u32 phys_mtu;
int gid_tbl_len;
unsigned int ip_gids:1;
/* This is the value from PortInfo CapabilityMask, defined by IBA */
u32 port_cap_flags;
u32 max_msg_sz;
u32 bad_pkey_cntr;
u32 qkey_viol_cntr;
u16 pkey_tbl_len;
u32 sm_lid;
u32 lid;
u8 lmc;
u8 max_vl_num;
u8 sm_sl;
u8 subnet_timeout;
u8 init_type_reply;
u8 active_width;
u16 active_speed;
u8 phys_state;
u16 port_cap_flags2;
};
enum ib_device_modify_flags {
IB_DEVICE_MODIFY_SYS_IMAGE_GUID = 1 << 0,
IB_DEVICE_MODIFY_NODE_DESC = 1 << 1
};
#define IB_DEVICE_NODE_DESC_MAX 64
struct ib_device_modify {
u64 sys_image_guid;
char node_desc[IB_DEVICE_NODE_DESC_MAX];
};
enum ib_port_modify_flags {
IB_PORT_SHUTDOWN = 1,
IB_PORT_INIT_TYPE = (1<<2),
IB_PORT_RESET_QKEY_CNTR = (1<<3),
IB_PORT_OPA_MASK_CHG = (1<<4)
};
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,
IB_EVENT_SM_CHANGE,
IB_EVENT_SRQ_ERR,
IB_EVENT_SRQ_LIMIT_REACHED,
IB_EVENT_QP_LAST_WQE_REACHED,
IB_EVENT_CLIENT_REREGISTER,
IB_EVENT_GID_CHANGE,
IB_EVENT_WQ_FATAL,
};
const char *__attribute_const__ ib_event_msg(enum ib_event_type event);
struct ib_event {
struct ib_device *device;
union {
struct ib_cq *cq;
struct ib_qp *qp;
struct ib_srq *srq;
struct ib_wq *wq;
u32 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 {
const struct ib_gid_attr *sgid_attr;
union ib_gid dgid;
u32 flow_label;
u8 sgid_index;
u8 hop_limit;
u8 traffic_class;
};
struct ib_grh {
__be32 version_tclass_flow;
__be16 paylen;
u8 next_hdr;
u8 hop_limit;
union ib_gid sgid;
union ib_gid dgid;
};
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;
};
};
#define IB_QPN_MASK 0xFFFFFF
enum {
IB_MULTICAST_QPN = 0xffffff
};
#define IB_LID_PERMISSIVE cpu_to_be16(0xFFFF)
#define IB_MULTICAST_LID_BASE cpu_to_be16(0xC000)
enum ib_ah_flags {
IB_AH_GRH = 1
};
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,
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,
IB_RATE_28_GBPS = 19,
IB_RATE_50_GBPS = 20,
IB_RATE_400_GBPS = 21,
IB_RATE_600_GBPS = 22,
};
/**
* 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.
*/
__attribute_const__ int ib_rate_to_mult(enum ib_rate rate);
/**
* 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.
*/
__attribute_const__ int ib_rate_to_mbps(enum ib_rate rate);
/**
* enum ib_mr_type - memory region type
* @IB_MR_TYPE_MEM_REG: memory region that is used for
* normal registration
* @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)
* @IB_MR_TYPE_DM: memory region that is used for device
* memory registration
* @IB_MR_TYPE_USER: memory region that is used for the user-space
* application
* @IB_MR_TYPE_DMA: memory region that is used for DMA operations
* without address translations (VA=PA)
* @IB_MR_TYPE_INTEGRITY: memory region that is used for
* data integrity operations
*/
enum ib_mr_type {
IB_MR_TYPE_MEM_REG,
IB_MR_TYPE_SG_GAPS,
IB_MR_TYPE_DM,
IB_MR_TYPE_USER,
IB_MR_TYPE_DMA,
IB_MR_TYPE_INTEGRITY,
};
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;
};
/**
* mult_to_ib_rate - Convert a multiple of 2.5 Gbit/sec to an IB rate
* enum.
* @mult: multiple to convert.
*/
__attribute_const__ enum ib_rate mult_to_ib_rate(int mult);
struct rdma_ah_init_attr {
struct rdma_ah_attr *ah_attr;
u32 flags;
struct net_device *xmit_slave;
};
enum rdma_ah_attr_type {
RDMA_AH_ATTR_TYPE_UNDEFINED,
RDMA_AH_ATTR_TYPE_IB,
RDMA_AH_ATTR_TYPE_ROCE,
RDMA_AH_ATTR_TYPE_OPA,
};
struct ib_ah_attr {
u16 dlid;
u8 src_path_bits;
};
struct roce_ah_attr {
u8 dmac[ETH_ALEN];
};
struct opa_ah_attr {
u32 dlid;
u8 src_path_bits;
bool make_grd;
};
struct rdma_ah_attr {
struct ib_global_route grh;
u8 sl;
u8 static_rate;
u32 port_num;
u8 ah_flags;
enum rdma_ah_attr_type type;
union {
struct ib_ah_attr ib;
struct roce_ah_attr roce;
struct opa_ah_attr opa;
};
};
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
};
const char *__attribute_const__ ib_wc_status_msg(enum ib_wc_status status);
enum ib_wc_opcode {
IB_WC_SEND = IB_UVERBS_WC_SEND,
IB_WC_RDMA_WRITE = IB_UVERBS_WC_RDMA_WRITE,
IB_WC_RDMA_READ = IB_UVERBS_WC_RDMA_READ,
IB_WC_COMP_SWAP = IB_UVERBS_WC_COMP_SWAP,
IB_WC_FETCH_ADD = IB_UVERBS_WC_FETCH_ADD,
IB_WC_BIND_MW = IB_UVERBS_WC_BIND_MW,
IB_WC_LOCAL_INV = IB_UVERBS_WC_LOCAL_INV,
IB_WC_LSO = IB_UVERBS_WC_TSO,
IB_WC_REG_MR,
IB_WC_MASKED_COMP_SWAP,
IB_WC_MASKED_FETCH_ADD,
/*
* 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,
IB_WC_WITH_IMM = (1<<1),
IB_WC_WITH_INVALIDATE = (1<<2),
IB_WC_IP_CSUM_OK = (1<<3),
IB_WC_WITH_SMAC = (1<<4),
IB_WC_WITH_VLAN = (1<<5),
IB_WC_WITH_NETWORK_HDR_TYPE = (1<<6),
};
struct ib_wc {
union {
u64 wr_id;
struct ib_cqe *wr_cqe;
};
enum ib_wc_status status;
enum ib_wc_opcode opcode;
u32 vendor_err;
u32 byte_len;
struct ib_qp *qp;
union {
__be32 imm_data;
u32 invalidate_rkey;
} ex;
u32 src_qp;
u32 slid;
int wc_flags;
u16 pkey_index;
u8 sl;
u8 dlid_path_bits;
u32 port_num; /* valid only for DR SMPs on switches */
u8 smac[ETH_ALEN];
u16 vlan_id;
u8 network_hdr_type;
};
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,
};
enum ib_srq_type {
IB_SRQT_BASIC = IB_UVERBS_SRQT_BASIC,
IB_SRQT_XRC = IB_UVERBS_SRQT_XRC,
IB_SRQT_TM = IB_UVERBS_SRQT_TM,
};
static inline bool ib_srq_has_cq(enum ib_srq_type srq_type)
{
return srq_type == IB_SRQT_XRC ||
srq_type == IB_SRQT_TM;
}
enum ib_srq_attr_mask {
IB_SRQ_MAX_WR = 1 << 0,
IB_SRQ_LIMIT = 1 << 1,
};
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;
enum ib_srq_type srq_type;
struct {
struct ib_cq *cq;
union {
struct {
struct ib_xrcd *xrcd;
} xrc;
struct {
u32 max_num_tags;
} tag_matching;
};
} ext;
};
struct ib_qp_cap {
u32 max_send_wr;
u32 max_recv_wr;
u32 max_send_sge;
u32 max_recv_sge;
u32 max_inline_data;
/*
* 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;
};
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_UVERBS_QPT_RC,
IB_QPT_UC = IB_UVERBS_QPT_UC,
IB_QPT_UD = IB_UVERBS_QPT_UD,
IB_QPT_RAW_IPV6,
IB_QPT_RAW_ETHERTYPE,
IB_QPT_RAW_PACKET = IB_UVERBS_QPT_RAW_PACKET,
IB_QPT_XRC_INI = IB_UVERBS_QPT_XRC_INI,
IB_QPT_XRC_TGT = IB_UVERBS_QPT_XRC_TGT,
IB_QPT_MAX,
IB_QPT_DRIVER = IB_UVERBS_QPT_DRIVER,
/* 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,
};
enum ib_qp_create_flags {
IB_QP_CREATE_IPOIB_UD_LSO = 1 << 0,
IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK =
IB_UVERBS_QP_CREATE_BLOCK_MULTICAST_LOOPBACK,
IB_QP_CREATE_CROSS_CHANNEL = 1 << 2,
IB_QP_CREATE_MANAGED_SEND = 1 << 3,
IB_QP_CREATE_MANAGED_RECV = 1 << 4,
IB_QP_CREATE_NETIF_QP = 1 << 5,
IB_QP_CREATE_INTEGRITY_EN = 1 << 6,
IB_QP_CREATE_NETDEV_USE = 1 << 7,
IB_QP_CREATE_SCATTER_FCS =
IB_UVERBS_QP_CREATE_SCATTER_FCS,
IB_QP_CREATE_CVLAN_STRIPPING =
IB_UVERBS_QP_CREATE_CVLAN_STRIPPING,
IB_QP_CREATE_SOURCE_QPN = 1 << 10,
IB_QP_CREATE_PCI_WRITE_END_PADDING =
IB_UVERBS_QP_CREATE_PCI_WRITE_END_PADDING,
/* reserve bits 26-31 for low level drivers' internal use */
IB_QP_CREATE_RESERVED_START = 1 << 26,
IB_QP_CREATE_RESERVED_END = 1 << 31,
};
/*
* Note: users may not call ib_close_qp or ib_destroy_qp from the event_handler
* callback to destroy the passed in QP.
*/
struct ib_qp_init_attr {
/* Consumer's event_handler callback must not block */
void (*event_handler)(struct ib_event *, void *);
void *qp_context;
struct ib_cq *send_cq;
struct ib_cq *recv_cq;
struct ib_srq *srq;
struct ib_xrcd *xrcd; /* XRC TGT QPs only */
struct ib_qp_cap cap;
enum ib_sig_type sq_sig_type;
enum ib_qp_type qp_type;
u32 create_flags;
/*
* Only needed for special QP types, or when using the RW API.
*/
u32 port_num;
struct ib_rwq_ind_table *rwq_ind_tbl;
u32 source_qpn;
};
struct ib_qp_open_attr {
void (*event_handler)(struct ib_event *, void *);
void *qp_context;
u32 qp_num;
enum ib_qp_type qp_type;
};
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),
IB_QP_DEST_QPN = (1<<20),
IB_QP_RESERVED1 = (1<<21),
IB_QP_RESERVED2 = (1<<22),
IB_QP_RESERVED3 = (1<<23),
IB_QP_RESERVED4 = (1<<24),
IB_QP_RATE_LIMIT = (1<<25),
IB_QP_ATTR_STANDARD_BITS = GENMASK(20, 0),
};
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
};
enum ib_mw_type {
IB_MW_TYPE_1 = 1,
IB_MW_TYPE_2 = 2
};
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;
struct rdma_ah_attr ah_attr;
struct rdma_ah_attr alt_ah_attr;
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;
u32 port_num;
u8 timeout;
u8 retry_cnt;
u8 rnr_retry;
u32 alt_port_num;
u8 alt_timeout;
u32 rate_limit;
struct net_device *xmit_slave;
};
enum ib_wr_opcode {
/* These are shared with userspace */
IB_WR_RDMA_WRITE = IB_UVERBS_WR_RDMA_WRITE,
IB_WR_RDMA_WRITE_WITH_IMM = IB_UVERBS_WR_RDMA_WRITE_WITH_IMM,
IB_WR_SEND = IB_UVERBS_WR_SEND,
IB_WR_SEND_WITH_IMM = IB_UVERBS_WR_SEND_WITH_IMM,
IB_WR_RDMA_READ = IB_UVERBS_WR_RDMA_READ,
IB_WR_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_ATOMIC_CMP_AND_SWP,
IB_WR_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD,
IB_WR_BIND_MW = IB_UVERBS_WR_BIND_MW,
IB_WR_LSO = IB_UVERBS_WR_TSO,
IB_WR_SEND_WITH_INV = IB_UVERBS_WR_SEND_WITH_INV,
IB_WR_RDMA_READ_WITH_INV = IB_UVERBS_WR_RDMA_READ_WITH_INV,
IB_WR_LOCAL_INV = IB_UVERBS_WR_LOCAL_INV,
IB_WR_MASKED_ATOMIC_CMP_AND_SWP =
IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP,
IB_WR_MASKED_ATOMIC_FETCH_AND_ADD =
IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD,
/* These are kernel only and can not be issued by userspace */
IB_WR_REG_MR = 0x20,
IB_WR_REG_MR_INTEGRITY,
/* 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,
};
enum ib_send_flags {
IB_SEND_FENCE = 1,
IB_SEND_SIGNALED = (1<<1),
IB_SEND_SOLICITED = (1<<2),
IB_SEND_INLINE = (1<<3),
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),
};
struct ib_sge {
u64 addr;
u32 length;
u32 lkey;
};
struct ib_cqe {
void (*done)(struct ib_cq *cq, struct ib_wc *wc);
};
struct ib_send_wr {
struct ib_send_wr *next;
union {
u64 wr_id;
struct ib_cqe *wr_cqe;
};
struct ib_sge *sg_list;
int num_sge;
enum ib_wr_opcode opcode;
int send_flags;
union {
__be32 imm_data;
u32 invalidate_rkey;
} ex;
};
struct ib_rdma_wr {
struct ib_send_wr wr;
u64 remote_addr;
u32 rkey;
};
static inline const struct ib_rdma_wr *rdma_wr(const 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 const struct ib_atomic_wr *atomic_wr(const 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 */
u32 port_num; /* valid for DR SMPs on switch only */
};
static inline const struct ib_ud_wr *ud_wr(const struct ib_send_wr *wr)
{
return container_of(wr, struct ib_ud_wr, wr);
}
struct ib_reg_wr {
struct ib_send_wr wr;
struct ib_mr *mr;
u32 key;
int access;
};
static inline const struct ib_reg_wr *reg_wr(const struct ib_send_wr *wr)
{
return container_of(wr, struct ib_reg_wr, wr);
}
struct ib_recv_wr {
struct ib_recv_wr *next;
union {
u64 wr_id;
struct ib_cqe *wr_cqe;
};
struct ib_sge *sg_list;
int num_sge;
};
enum ib_access_flags {
IB_ACCESS_LOCAL_WRITE = IB_UVERBS_ACCESS_LOCAL_WRITE,
IB_ACCESS_REMOTE_WRITE = IB_UVERBS_ACCESS_REMOTE_WRITE,
IB_ACCESS_REMOTE_READ = IB_UVERBS_ACCESS_REMOTE_READ,
IB_ACCESS_REMOTE_ATOMIC = IB_UVERBS_ACCESS_REMOTE_ATOMIC,
IB_ACCESS_MW_BIND = IB_UVERBS_ACCESS_MW_BIND,
IB_ZERO_BASED = IB_UVERBS_ACCESS_ZERO_BASED,
IB_ACCESS_ON_DEMAND = IB_UVERBS_ACCESS_ON_DEMAND,
IB_ACCESS_HUGETLB = IB_UVERBS_ACCESS_HUGETLB,
IB_ACCESS_RELAXED_ORDERING = IB_UVERBS_ACCESS_RELAXED_ORDERING,
IB_ACCESS_OPTIONAL = IB_UVERBS_ACCESS_OPTIONAL_RANGE,
IB_ACCESS_SUPPORTED =
((IB_ACCESS_HUGETLB << 1) - 1) | IB_ACCESS_OPTIONAL,
};
/*
* XXX: these are apparently used for ->rereg_user_mr, no idea why they
* are hidden here instead of a uapi header!
*/
enum ib_mr_rereg_flags {
IB_MR_REREG_TRANS = 1,
IB_MR_REREG_PD = (1<<1),
IB_MR_REREG_ACCESS = (1<<2),
IB_MR_REREG_SUPPORTED = ((IB_MR_REREG_ACCESS << 1) - 1)
};
struct ib_umem;
enum rdma_remove_reason {
/*
* Userspace requested uobject deletion or initial try
* to remove uobject via cleanup. Call could fail
*/
RDMA_REMOVE_DESTROY,
/* Context deletion. This call should delete the actual object itself */
RDMA_REMOVE_CLOSE,
/* Driver is being hot-unplugged. This call should delete the actual object itself */
RDMA_REMOVE_DRIVER_REMOVE,
/* uobj is being cleaned-up before being committed */
RDMA_REMOVE_ABORT,
/* The driver failed to destroy the uobject and is being disconnected */
RDMA_REMOVE_DRIVER_FAILURE,
};
struct ib_rdmacg_object {
#ifdef CONFIG_CGROUP_RDMA
struct rdma_cgroup *cg; /* owner rdma cgroup */
#endif
};
struct ib_ucontext {
struct ib_device *device;
struct ib_uverbs_file *ufile;
struct ib_rdmacg_object cg_obj;
/*
* Implementation details of the RDMA core, don't use in drivers:
*/
struct rdma_restrack_entry res;
struct xarray mmap_xa;
};
struct ib_uobject {
u64 user_handle; /* handle given to us by userspace */
/* ufile & ucontext owning this object */
struct ib_uverbs_file *ufile;
/* FIXME, save memory: ufile->context == context */
struct ib_ucontext *context; /* associated user context */
void *object; /* containing object */
struct list_head list; /* link to context's list */
struct ib_rdmacg_object cg_obj; /* rdmacg object */
int id; /* index into kernel idr */
struct kref ref;
atomic_t usecnt; /* protects exclusive access */
struct rcu_head rcu; /* kfree_rcu() overhead */
const struct uverbs_api_object *uapi_object;
};
struct ib_udata {
const void __user *inbuf;
void __user *outbuf;
size_t inlen;
size_t outlen;
};
struct ib_pd {
u32 local_dma_lkey;
u32 flags;
struct ib_device *device;
struct ib_uobject *uobject;
atomic_t usecnt; /* count all resources */
u32 unsafe_global_rkey;
/*
* Implementation details of the RDMA core, don't use in drivers:
*/
struct ib_mr *__internal_mr;
struct rdma_restrack_entry res;
};
struct ib_xrcd {
struct ib_device *device;
atomic_t usecnt; /* count all exposed resources */
struct inode *inode;
struct rw_semaphore tgt_qps_rwsem;
struct xarray tgt_qps;
};
struct ib_ah {
struct ib_device *device;
struct ib_pd *pd;
struct ib_uobject *uobject;
const struct ib_gid_attr *sgid_attr;
enum rdma_ah_attr_type type;
};
typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context);
enum ib_poll_context {
IB_POLL_SOFTIRQ, /* poll from softirq context */
IB_POLL_WORKQUEUE, /* poll from workqueue */
IB_POLL_UNBOUND_WORKQUEUE, /* poll from unbound workqueue */
IB_POLL_LAST_POOL_TYPE = IB_POLL_UNBOUND_WORKQUEUE,
IB_POLL_DIRECT, /* caller context, no hw completions */
};
struct ib_cq {
struct ib_device *device;
struct ib_ucq_object *uobject;
ib_comp_handler comp_handler;
void (*event_handler)(struct ib_event *, void *);
void *cq_context;
int cqe;
unsigned int cqe_used;
atomic_t usecnt; /* count number of work queues */
enum ib_poll_context poll_ctx;
struct ib_wc *wc;
struct list_head pool_entry;
union {
struct irq_poll iop;
struct work_struct work;
};
struct workqueue_struct *comp_wq;
struct dim *dim;
/* updated only by trace points */
ktime_t timestamp;
u8 interrupt:1;
u8 shared:1;
unsigned int comp_vector;
/*
* Implementation details of the RDMA core, don't use in drivers:
*/
struct rdma_restrack_entry res;
};
struct ib_srq {
struct ib_device *device;
struct ib_pd *pd;
struct ib_usrq_object *uobject;
void (*event_handler)(struct ib_event *, void *);
void *srq_context;
enum ib_srq_type srq_type;
atomic_t usecnt;
struct {
struct ib_cq *cq;
union {
struct {
struct ib_xrcd *xrcd;
u32 srq_num;
} xrc;
};
} ext;
/*
* Implementation details of the RDMA core, don't use in drivers:
*/
struct rdma_restrack_entry res;
};
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 =
IB_UVERBS_RAW_PACKET_CAP_CVLAN_STRIPPING,
/*
* Scatter FCS field of an incoming packet to host memory is supported.
*/
IB_RAW_PACKET_CAP_SCATTER_FCS = IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS,
/* Checksum offloads are supported (for both send and receive). */
IB_RAW_PACKET_CAP_IP_CSUM = IB_UVERBS_RAW_PACKET_CAP_IP_CSUM,
/*
* When a packet is received for an RQ with no receive WQEs, the
* packet processing is delayed.
*/
IB_RAW_PACKET_CAP_DELAY_DROP = IB_UVERBS_RAW_PACKET_CAP_DELAY_DROP,
};
enum ib_wq_type {
IB_WQT_RQ = IB_UVERBS_WQT_RQ,
};
enum ib_wq_state {
IB_WQS_RESET,
IB_WQS_RDY,
IB_WQS_ERR
};
struct ib_wq {
struct ib_device *device;
struct ib_uwq_object *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;
};
enum ib_wq_flags {
IB_WQ_FLAGS_CVLAN_STRIPPING = IB_UVERBS_WQ_FLAGS_CVLAN_STRIPPING,
IB_WQ_FLAGS_SCATTER_FCS = IB_UVERBS_WQ_FLAGS_SCATTER_FCS,
IB_WQ_FLAGS_DELAY_DROP = IB_UVERBS_WQ_FLAGS_DELAY_DROP,
IB_WQ_FLAGS_PCI_WRITE_END_PADDING =
IB_UVERBS_WQ_FLAGS_PCI_WRITE_END_PADDING,
};
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 *);
u32 create_flags; /* Use enum ib_wq_flags */
};
enum ib_wq_attr_mask {
IB_WQ_STATE = 1 << 0,
IB_WQ_CUR_STATE = 1 << 1,
IB_WQ_FLAGS = 1 << 2,
};
struct ib_wq_attr {
enum ib_wq_state wq_state;
enum ib_wq_state curr_wq_state;
u32 flags; /* Use enum ib_wq_flags */
u32 flags_mask; /* Use enum ib_wq_flags */
};
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;
};
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;
u32 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;
};
/*
* @max_write_sge: Maximum SGE elements per RDMA WRITE request.
* @max_read_sge: Maximum SGE elements per RDMA READ request.
*/
struct ib_qp {
struct ib_device *device;
struct ib_pd *pd;
struct ib_cq *send_cq;
struct ib_cq *recv_cq;
spinlock_t mr_lock;
int mrs_used;
struct list_head rdma_mrs;
struct list_head sig_mrs;
struct ib_srq *srq;
struct ib_xrcd *xrcd; /* XRC TGT QPs only */
struct list_head xrcd_list;
/* count times opened, mcast attaches, flow attaches */
atomic_t usecnt;
struct list_head open_list;
struct ib_qp *real_qp;
struct ib_uqp_object *uobject;
void (*event_handler)(struct ib_event *, void *);
void *qp_context;
/* sgid_attrs associated with the AV's */
const struct ib_gid_attr *av_sgid_attr;
const struct ib_gid_attr *alt_path_sgid_attr;
u32 qp_num;
u32 max_write_sge;
u32 max_read_sge;
enum ib_qp_type qp_type;
struct ib_rwq_ind_table *rwq_ind_tbl;
struct ib_qp_security *qp_sec;
u32 port;
bool integrity_en;
/*
* Implementation details of the RDMA core, don't use in drivers:
*/
struct rdma_restrack_entry res;
/* The counter the qp is bind to */
struct rdma_counter *counter;
};
struct ib_dm {
struct ib_device *device;
u32 length;
u32 flags;
struct ib_uobject *uobject;
atomic_t usecnt;
};
struct ib_mr {
struct ib_device *device;
struct ib_pd *pd;
u32 lkey;
u32 rkey;
u64 iova;
u64 length;
unsigned int page_size;
enum ib_mr_type type;
bool need_inval;
union {
struct ib_uobject *uobject; /* user */
struct list_head qp_entry; /* FR */
};
struct ib_dm *dm;
struct ib_sig_attrs *sig_attrs; /* only for IB_MR_TYPE_INTEGRITY MRs */
/*
* Implementation details of the RDMA core, don't use in drivers:
*/
struct rdma_restrack_entry res;
};
struct ib_mw {
struct ib_device *device;
struct ib_pd *pd;
struct ib_uobject *uobject;
u32 rkey;
enum ib_mw_type type;
};
/* 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*/
IB_FLOW_SPEC_ETH = 0x20,
IB_FLOW_SPEC_IB = 0x22,
/* L3 header*/
IB_FLOW_SPEC_IPV4 = 0x30,
IB_FLOW_SPEC_IPV6 = 0x31,
IB_FLOW_SPEC_ESP = 0x34,
/* L4 headers*/
IB_FLOW_SPEC_TCP = 0x40,
IB_FLOW_SPEC_UDP = 0x41,
IB_FLOW_SPEC_VXLAN_TUNNEL = 0x50,
IB_FLOW_SPEC_GRE = 0x51,
IB_FLOW_SPEC_MPLS = 0x60,
IB_FLOW_SPEC_INNER = 0x100,
/* Actions */
IB_FLOW_SPEC_ACTION_TAG = 0x1000,
IB_FLOW_SPEC_ACTION_DROP = 0x1001,
IB_FLOW_SPEC_ACTION_HANDLE = 0x1002,
IB_FLOW_SPEC_ACTION_COUNT = 0x1003,
};
#define IB_FLOW_SPEC_LAYER_MASK 0xF0
#define IB_FLOW_SPEC_SUPPORT_LAYERS 10
enum ib_flow_flags {
IB_FLOW_ATTR_FLAGS_DONT_TRAP = 1UL << 1, /* Continue match, no steal */
IB_FLOW_ATTR_FLAGS_EGRESS = 1UL << 2, /* Egress flow */
IB_FLOW_ATTR_FLAGS_RESERVED = 1UL << 3 /* Must be last */
};
struct ib_flow_eth_filter {
u8 dst_mac[6];
u8 src_mac[6];
__be16 ether_type;
__be16 vlan_tag;
/* Must be last */
u8 real_sz[];
};
struct ib_flow_spec_eth {
u32 type;
u16 size;
struct ib_flow_eth_filter val;
struct ib_flow_eth_filter mask;
};
struct ib_flow_ib_filter {
__be16 dlid;
__u8 sl;
/* Must be last */
u8 real_sz[];
};
struct ib_flow_spec_ib {
u32 type;
u16 size;
struct ib_flow_ib_filter val;
struct ib_flow_ib_filter mask;
};
/* 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 */
};
struct ib_flow_ipv4_filter {
__be32 src_ip;
__be32 dst_ip;
u8 proto;
u8 tos;
u8 ttl;
u8 flags;
/* Must be last */
u8 real_sz[];
};
struct ib_flow_spec_ipv4 {
u32 type;
u16 size;
struct ib_flow_ipv4_filter val;
struct ib_flow_ipv4_filter mask;
};
struct ib_flow_ipv6_filter {
u8 src_ip[16];
u8 dst_ip[16];
__be32 flow_label;
u8 next_hdr;
u8 traffic_class;
u8 hop_limit;
/* Must be last */
u8 real_sz[];
};
struct ib_flow_spec_ipv6 {
u32 type;
u16 size;
struct ib_flow_ipv6_filter val;
struct ib_flow_ipv6_filter mask;
};
struct ib_flow_tcp_udp_filter {
__be16 dst_port;
__be16 src_port;
/* Must be last */
u8 real_sz[];
};
struct ib_flow_spec_tcp_udp {
u32 type;
u16 size;
struct ib_flow_tcp_udp_filter val;
struct ib_flow_tcp_udp_filter mask;
};
struct ib_flow_tunnel_filter {
__be32 tunnel_id;
u8 real_sz[];
};
/* ib_flow_spec_tunnel describes the Vxlan tunnel
* the tunnel_id from val has the vni value
*/
struct ib_flow_spec_tunnel {
u32 type;
u16 size;
struct ib_flow_tunnel_filter val;
struct ib_flow_tunnel_filter mask;
};
struct ib_flow_esp_filter {
__be32 spi;
__be32 seq;
/* Must be last */
u8 real_sz[];
};
struct ib_flow_spec_esp {
u32 type;
u16 size;
struct ib_flow_esp_filter val;
struct ib_flow_esp_filter mask;
};
struct ib_flow_gre_filter {
__be16 c_ks_res0_ver;
__be16 protocol;
__be32 key;
/* Must be last */
u8 real_sz[];
};
struct ib_flow_spec_gre {
u32 type;
u16 size;
struct ib_flow_gre_filter val;
struct ib_flow_gre_filter mask;
};
struct ib_flow_mpls_filter {
__be32 tag;
/* Must be last */
u8 real_sz[];
};
struct ib_flow_spec_mpls {
u32 type;
u16 size;
struct ib_flow_mpls_filter val;
struct ib_flow_mpls_filter mask;
};
struct ib_flow_spec_action_tag {
enum ib_flow_spec_type type;
u16 size;
u32 tag_id;
};
struct ib_flow_spec_action_drop {
enum ib_flow_spec_type type;
u16 size;
};
struct ib_flow_spec_action_handle {
enum ib_flow_spec_type type;
u16 size;
struct ib_flow_action *act;
};
enum ib_counters_description {
IB_COUNTER_PACKETS,
IB_COUNTER_BYTES,
};
struct ib_flow_spec_action_count {
enum ib_flow_spec_type type;
u16 size;
struct ib_counters *counters;
};
union ib_flow_spec {
struct {
u32 type;
u16 size;
};
struct ib_flow_spec_eth eth;
struct ib_flow_spec_ib ib;
struct ib_flow_spec_ipv4 ipv4;
struct ib_flow_spec_tcp_udp tcp_udp;
struct ib_flow_spec_ipv6 ipv6;
struct ib_flow_spec_tunnel tunnel;
struct ib_flow_spec_esp esp;
struct ib_flow_spec_gre gre;
struct ib_flow_spec_mpls mpls;
struct ib_flow_spec_action_tag flow_tag;
struct ib_flow_spec_action_drop drop;
struct ib_flow_spec_action_handle action;
struct ib_flow_spec_action_count flow_count;
};
struct ib_flow_attr {
enum ib_flow_attr_type type;
u16 size;
u16 priority;
u32 flags;
u8 num_of_specs;
u32 port;
union ib_flow_spec flows[];
};
struct ib_flow {
struct ib_qp *qp;
struct ib_device *device;
struct ib_uobject *uobject;
};
enum ib_flow_action_type {
IB_FLOW_ACTION_UNSPECIFIED,
IB_FLOW_ACTION_ESP = 1,
};
struct ib_flow_action_attrs_esp_keymats {
enum ib_uverbs_flow_action_esp_keymat protocol;
union {
struct ib_uverbs_flow_action_esp_keymat_aes_gcm aes_gcm;
} keymat;
};
struct ib_flow_action_attrs_esp_replays {
enum ib_uverbs_flow_action_esp_replay protocol;
union {
struct ib_uverbs_flow_action_esp_replay_bmp bmp;
} replay;
};
enum ib_flow_action_attrs_esp_flags {
/* All user-space flags at the top: Use enum ib_uverbs_flow_action_esp_flags
* This is done in order to share the same flags between user-space and
* kernel and spare an unnecessary translation.
*/
/* Kernel flags */
IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED = 1ULL << 32,
IB_FLOW_ACTION_ESP_FLAGS_MOD_ESP_ATTRS = 1ULL << 33,
};
struct ib_flow_spec_list {
struct ib_flow_spec_list *next;
union ib_flow_spec spec;
};
struct ib_flow_action_attrs_esp {
struct ib_flow_action_attrs_esp_keymats *keymat;
struct ib_flow_action_attrs_esp_replays *replay;
struct ib_flow_spec_list *encap;
/* Used only if IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED is enabled.
* Value of 0 is a valid value.
*/
u32 esn;
u32 spi;
u32 seq;
u32 tfc_pad;
/* Use enum ib_flow_action_attrs_esp_flags */
u64 flags;
u64 hard_limit_pkts;
};
struct ib_flow_action {
struct ib_device *device;
struct ib_uobject *uobject;
enum ib_flow_action_type type;
atomic_t usecnt;
};
struct ib_mad;
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 */
};
struct ib_port_cache {
u64 subnet_prefix;
struct ib_pkey_cache *pkey;
struct ib_gid_table *gid;
u8 lmc;
enum ib_port_state port_state;
};
struct ib_port_immutable {
int pkey_tbl_len;
int gid_tbl_len;
u32 core_cap_flags;
u32 max_mad_size;
};
struct ib_port_data {
struct ib_device *ib_dev;
struct ib_port_immutable immutable;
spinlock_t pkey_list_lock;
spinlock_t netdev_lock;
struct list_head pkey_list;
struct ib_port_cache cache;
struct net_device __rcu *netdev;
struct hlist_node ndev_hash_link;
struct rdma_port_counter port_counter;
struct ib_port *sysfs;
};
/* rdma netdev type - specifies protocol type */
enum rdma_netdev_t {
RDMA_NETDEV_OPA_VNIC,
RDMA_NETDEV_IPOIB,
};
/**
* struct rdma_netdev - rdma netdev
* For cases where netstack interfacing is required.
*/
struct rdma_netdev {
void *clnt_priv;
struct ib_device *hca;
u32 port_num;
int mtu;
/*
* cleanup function must be specified.
* FIXME: This is only used for OPA_VNIC and that usage should be
* removed too.
*/
void (*free_rdma_netdev)(struct net_device *netdev);
/* control functions */
void (*set_id)(struct net_device *netdev, int id);
/* 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);
/* timeout */
void (*tx_timeout)(struct net_device *dev, unsigned int txqueue);
};
struct rdma_netdev_alloc_params {
size_t sizeof_priv;
unsigned int txqs;
unsigned int rxqs;
void *param;
int (*initialize_rdma_netdev)(struct ib_device *device, u32 port_num,
struct net_device *netdev, void *param);
};
struct ib_odp_counters {
atomic64_t faults;
atomic64_t invalidations;
atomic64_t prefetch;
};
struct ib_counters {
struct ib_device *device;
struct ib_uobject *uobject;
/* num of objects attached */
atomic_t usecnt;
};
struct ib_counters_read_attr {
u64 *counters_buff;
u32 ncounters;
u32 flags; /* use enum ib_read_counters_flags */
};
struct uverbs_attr_bundle;
struct iw_cm_id;
struct iw_cm_conn_param;
#define INIT_RDMA_OBJ_SIZE(ib_struct, drv_struct, member) \
.size_##ib_struct = \
(sizeof(struct drv_struct) + \
BUILD_BUG_ON_ZERO(offsetof(struct drv_struct, member)) + \
BUILD_BUG_ON_ZERO( \
!__same_type(((struct drv_struct *)NULL)->member, \
struct ib_struct)))
#define rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, gfp) \
((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \
gfp, false))
#define rdma_zalloc_drv_obj_numa(ib_dev, ib_type) \
((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \
GFP_KERNEL, true))
#define rdma_zalloc_drv_obj(ib_dev, ib_type) \
rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, GFP_KERNEL)
#define DECLARE_RDMA_OBJ_SIZE(ib_struct) size_t size_##ib_struct
struct rdma_user_mmap_entry {
struct kref ref;
struct ib_ucontext *ucontext;
unsigned long start_pgoff;
size_t npages;
bool driver_removed;
};
/* Return the offset (in bytes) the user should pass to libc's mmap() */
static inline u64
rdma_user_mmap_get_offset(const struct rdma_user_mmap_entry *entry)
{
return (u64)entry->start_pgoff << PAGE_SHIFT;
}
/**
* struct ib_device_ops - InfiniBand device operations
* This structure defines all the InfiniBand device operations, providers will
* need to define the supported operations, otherwise they will be set to null.
*/
struct ib_device_ops {
struct module *owner;
enum rdma_driver_id driver_id;
u32 uverbs_abi_ver;
unsigned int uverbs_no_driver_id_binding:1;
/*
* NOTE: New drivers should not make use of device_group; instead new
* device parameter should be exposed via netlink command. This
* mechanism exists only for existing drivers.
*/
const struct attribute_group *device_group;
const struct attribute_group **port_groups;
int (*post_send)(struct ib_qp *qp, const struct ib_send_wr *send_wr,
const struct ib_send_wr **bad_send_wr);
int (*post_recv)(struct ib_qp *qp, const struct ib_recv_wr *recv_wr,
const struct ib_recv_wr **bad_recv_wr);
void (*drain_rq)(struct ib_qp *qp);
void (*drain_sq)(struct ib_qp *qp);
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, enum ib_cq_notify_flags flags);
int (*post_srq_recv)(struct ib_srq *srq,
const struct ib_recv_wr *recv_wr,
const struct ib_recv_wr **bad_recv_wr);
int (*process_mad)(struct ib_device *device, int process_mad_flags,
u32 port_num, const struct ib_wc *in_wc,
const struct ib_grh *in_grh,
const struct ib_mad *in_mad, struct ib_mad *out_mad,
size_t *out_mad_size, u16 *out_mad_pkey_index);
int (*query_device)(struct ib_device *device,
struct ib_device_attr *device_attr,
struct ib_udata *udata);
int (*modify_device)(struct ib_device *device, int device_modify_mask,
struct ib_device_modify *device_modify);
void (*get_dev_fw_str)(struct ib_device *device, char *str);
const struct cpumask *(*get_vector_affinity)(struct ib_device *ibdev,
int comp_vector);
int (*query_port)(struct ib_device *device, u32 port_num,
struct ib_port_attr *port_attr);
int (*modify_port)(struct ib_device *device, u32 port_num,
int port_modify_mask,
struct ib_port_modify *port_modify);
/**
* 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 *device, u32 port_num,
struct ib_port_immutable *immutable);
enum rdma_link_layer (*get_link_layer)(struct ib_device *device,
u32 port_num);
/**
* 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 has finished
* NETDEV_UNREGISTER state.
*/
struct net_device *(*get_netdev)(struct ib_device *device,
u32 port_num);
/**
* rdma netdev operation
*
* Driver implementing alloc_rdma_netdev or rdma_netdev_get_params
* must return -EOPNOTSUPP if it doesn't support the specified type.
*/
struct net_device *(*alloc_rdma_netdev)(
struct ib_device *device, u32 port_num, enum rdma_netdev_t type,
const char *name, unsigned char name_assign_type,
void (*setup)(struct net_device *));
int (*rdma_netdev_get_params)(struct ib_device *device, u32 port_num,
enum rdma_netdev_t type,
struct rdma_netdev_alloc_params *params);
/**
* 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.
*/
int (*query_gid)(struct ib_device *device, u32 port_num, int index,
union ib_gid *gid);
/**
* 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
* success or error otherwise. The function could be called
* concurrently for different ports. This function is only called when
* roce_gid_table is used.
*/
int (*add_gid)(const struct ib_gid_attr *attr, void **context);
/**
* When calling del_gid, the HW vendor's driver should delete the
* gid of device @device at gid index gid_index of port port_num
* available in @attr.
* 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.
*/
int (*del_gid)(const struct ib_gid_attr *attr, void **context);
int (*query_pkey)(struct ib_device *device, u32 port_num, u16 index,
u16 *pkey);
int (*alloc_ucontext)(struct ib_ucontext *context,
struct ib_udata *udata);
void (*dealloc_ucontext)(struct ib_ucontext *context);
int (*mmap)(struct ib_ucontext *context, struct vm_area_struct *vma);
/**
* This will be called once refcount of an entry in mmap_xa reaches
* zero. The type of the memory that was mapped may differ between
* entries and is opaque to the rdma_user_mmap interface.
* Therefore needs to be implemented by the driver in mmap_free.
*/
void (*mmap_free)(struct rdma_user_mmap_entry *entry);
void (*disassociate_ucontext)(struct ib_ucontext *ibcontext);
int (*alloc_pd)(struct ib_pd *pd, struct ib_udata *udata);
int (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata);
int (*create_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr,
struct ib_udata *udata);
int (*create_user_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr,
struct ib_udata *udata);
int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
int (*query_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
int (*destroy_ah)(struct ib_ah *ah, u32 flags);
int (*create_srq)(struct ib_srq *srq,
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,
enum ib_srq_attr_mask srq_attr_mask,
struct ib_udata *udata);
int (*query_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr);
int (*destroy_srq)(struct ib_srq *srq, struct ib_udata *udata);
int (*create_qp)(struct ib_qp *qp, struct ib_qp_init_attr *qp_init_attr,
struct ib_udata *udata);
int (*modify_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
int qp_attr_mask, struct ib_udata *udata);
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, struct ib_udata *udata);
int (*create_cq)(struct ib_cq *cq, const struct ib_cq_init_attr *attr,
struct ib_udata *udata);
int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period);
int (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata);
int (*resize_cq)(struct ib_cq *cq, int cqe, struct ib_udata *udata);
struct ib_mr *(*get_dma_mr)(struct ib_pd *pd, int mr_access_flags);
struct ib_mr *(*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length,
u64 virt_addr, int mr_access_flags,
struct ib_udata *udata);
struct ib_mr *(*reg_user_mr_dmabuf)(struct ib_pd *pd, u64 offset,
u64 length, u64 virt_addr, int fd,
int mr_access_flags,
struct ib_udata *udata);
struct ib_mr *(*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);
int (*dereg_mr)(struct ib_mr *mr, struct ib_udata *udata);
struct ib_mr *(*alloc_mr)(struct ib_pd *pd, enum ib_mr_type mr_type,
u32 max_num_sg);
struct ib_mr *(*alloc_mr_integrity)(struct ib_pd *pd,
u32 max_num_data_sg,
u32 max_num_meta_sg);
int (*advise_mr)(struct ib_pd *pd,
enum ib_uverbs_advise_mr_advice advice, u32 flags,
struct ib_sge *sg_list, u32 num_sge,
struct uverbs_attr_bundle *attrs);
/*
* Kernel users should universally support relaxed ordering (RO), as
* they are designed to read data only after observing the CQE and use
* the DMA API correctly.
*
* Some drivers implicitly enable RO if platform supports it.
*/
int (*map_mr_sg)(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
unsigned int *sg_offset);
int (*check_mr_status)(struct ib_mr *mr, u32 check_mask,
struct ib_mr_status *mr_status);
int (*alloc_mw)(struct ib_mw *mw, struct ib_udata *udata);
int (*dealloc_mw)(struct ib_mw *mw);
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 (*alloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata);
int (*dealloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata);
struct ib_flow *(*create_flow)(struct ib_qp *qp,
struct ib_flow_attr *flow_attr,
struct ib_udata *udata);
int (*destroy_flow)(struct ib_flow *flow_id);
int (*destroy_flow_action)(struct ib_flow_action *action);
int (*set_vf_link_state)(struct ib_device *device, int vf, u32 port,
int state);
int (*get_vf_config)(struct ib_device *device, int vf, u32 port,
struct ifla_vf_info *ivf);
int (*get_vf_stats)(struct ib_device *device, int vf, u32 port,
struct ifla_vf_stats *stats);
int (*get_vf_guid)(struct ib_device *device, int vf, u32 port,
struct ifla_vf_guid *node_guid,
struct ifla_vf_guid *port_guid);
int (*set_vf_guid)(struct ib_device *device, int vf, u32 port, u64 guid,
int type);
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, struct ib_udata *udata);
int (*modify_wq)(struct ib_wq *wq, struct ib_wq_attr *attr,
u32 wq_attr_mask, struct ib_udata *udata);
int (*create_rwq_ind_table)(struct ib_rwq_ind_table *ib_rwq_ind_table,
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);
struct ib_dm *(*alloc_dm)(struct ib_device *device,
struct ib_ucontext *context,
struct ib_dm_alloc_attr *attr,
struct uverbs_attr_bundle *attrs);
int (*dealloc_dm)(struct ib_dm *dm, struct uverbs_attr_bundle *attrs);
struct ib_mr *(*reg_dm_mr)(struct ib_pd *pd, struct ib_dm *dm,
struct ib_dm_mr_attr *attr,
struct uverbs_attr_bundle *attrs);
int (*create_counters)(struct ib_counters *counters,
struct uverbs_attr_bundle *attrs);
int (*destroy_counters)(struct ib_counters *counters);
int (*read_counters)(struct ib_counters *counters,
struct ib_counters_read_attr *counters_read_attr,
struct uverbs_attr_bundle *attrs);
int (*map_mr_sg_pi)(struct ib_mr *mr, struct scatterlist *data_sg,
int data_sg_nents, unsigned int *data_sg_offset,
struct scatterlist *meta_sg, int meta_sg_nents,
unsigned int *meta_sg_offset);
/**
* alloc_hw_[device,port]_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_device_stats)(struct ib_device *device);
struct rdma_hw_stats *(*alloc_hw_port_stats)(struct ib_device *device,
u32 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, u32 port, int index);
/**
* modify_hw_stat - Modify the counter configuration
* @enable: true/false when enable/disable a counter
* Return codes - 0 on success or error code otherwise.
*/
int (*modify_hw_stat)(struct ib_device *device, u32 port,
unsigned int counter_index, bool enable);
/**
* Allows rdma drivers to add their own restrack attributes.
*/
int (*fill_res_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr);
int (*fill_res_mr_entry_raw)(struct sk_buff *msg, struct ib_mr *ibmr);
int (*fill_res_cq_entry)(struct sk_buff *msg, struct ib_cq *ibcq);
int (*fill_res_cq_entry_raw)(struct sk_buff *msg, struct ib_cq *ibcq);
int (*fill_res_qp_entry)(struct sk_buff *msg, struct ib_qp *ibqp);
int (*fill_res_qp_entry_raw)(struct sk_buff *msg, struct ib_qp *ibqp);
int (*fill_res_cm_id_entry)(struct sk_buff *msg, struct rdma_cm_id *id);
/* Device lifecycle callbacks */
/*
* Called after the device becomes registered, before clients are
* attached
*/
int (*enable_driver)(struct ib_device *dev);
/*
* This is called as part of ib_dealloc_device().
*/
void (*dealloc_driver)(struct ib_device *dev);
/* iWarp CM callbacks */
void (*iw_add_ref)(struct ib_qp *qp);
void (*iw_rem_ref)(struct ib_qp *qp);
struct ib_qp *(*iw_get_qp)(struct ib_device *device, int qpn);
int (*iw_connect)(struct iw_cm_id *cm_id,
struct iw_cm_conn_param *conn_param);
int (*iw_accept)(struct iw_cm_id *cm_id,
struct iw_cm_conn_param *conn_param);
int (*iw_reject)(struct iw_cm_id *cm_id, const void *pdata,
u8 pdata_len);
int (*iw_create_listen)(struct iw_cm_id *cm_id, int backlog);
int (*iw_destroy_listen)(struct iw_cm_id *cm_id);
/**
* counter_bind_qp - Bind a QP to a counter.
* @counter - The counter to be bound. If counter->id is zero then
* the driver needs to allocate a new counter and set counter->id
*/
int (*counter_bind_qp)(struct rdma_counter *counter, struct ib_qp *qp);
/**
* counter_unbind_qp - Unbind the qp from the dynamically-allocated
* counter and bind it onto the default one
*/
int (*counter_unbind_qp)(struct ib_qp *qp);
/**
* counter_dealloc -De-allocate the hw counter
*/
int (*counter_dealloc)(struct rdma_counter *counter);
/**
* counter_alloc_stats - Allocate a struct rdma_hw_stats and fill in
* the driver initialized data.
*/
struct rdma_hw_stats *(*counter_alloc_stats)(
struct rdma_counter *counter);
/**
* counter_update_stats - Query the stats value of this counter
*/
int (*counter_update_stats)(struct rdma_counter *counter);
/**
* Allows rdma drivers to add their own restrack attributes
* dumped via 'rdma stat' iproute2 command.
*/
int (*fill_stat_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr);
/* query driver for its ucontext properties */
int (*query_ucontext)(struct ib_ucontext *context,
struct uverbs_attr_bundle *attrs);
/*
* Provide NUMA node. This API exists for rdmavt/hfi1 only.
* Everyone else relies on Linux memory management model.
*/
int (*get_numa_node)(struct ib_device *dev);
DECLARE_RDMA_OBJ_SIZE(ib_ah);
DECLARE_RDMA_OBJ_SIZE(ib_counters);
DECLARE_RDMA_OBJ_SIZE(ib_cq);
DECLARE_RDMA_OBJ_SIZE(ib_mw);
DECLARE_RDMA_OBJ_SIZE(ib_pd);
DECLARE_RDMA_OBJ_SIZE(ib_qp);
DECLARE_RDMA_OBJ_SIZE(ib_rwq_ind_table);
DECLARE_RDMA_OBJ_SIZE(ib_srq);
DECLARE_RDMA_OBJ_SIZE(ib_ucontext);
DECLARE_RDMA_OBJ_SIZE(ib_xrcd);
};
struct ib_core_device {
/* device must be the first element in structure until,
* union of ib_core_device and device exists in ib_device.
*/
struct device dev;
possible_net_t rdma_net;
struct kobject *ports_kobj;
struct list_head port_list;
struct ib_device *owner; /* reach back to owner ib_device */
};
struct rdma_restrack_root;
struct ib_device {
/* Do not access @dma_device directly from ULP nor from HW drivers. */
struct device *dma_device;
struct ib_device_ops ops;
char name[IB_DEVICE_NAME_MAX];
struct rcu_head rcu_head;
struct list_head event_handler_list;
/* Protects event_handler_list */
struct rw_semaphore event_handler_rwsem;
/* Protects QP's event_handler calls and open_qp list */
spinlock_t qp_open_list_lock;
struct rw_semaphore client_data_rwsem;
struct xarray client_data;
struct mutex unregistration_lock;
/* Synchronize GID, Pkey cache entries, subnet prefix, LMC */
rwlock_t cache_lock;
/**
* port_data is indexed by port number
*/
struct ib_port_data *port_data;
int num_comp_vectors;
union {
struct device dev;
struct ib_core_device coredev;
};
/* First group is for device attributes,
* Second group is for driver provided attributes (optional).
* Third group is for the hw_stats
* It is a NULL terminated array.
*/
const struct attribute_group *groups[4];
u64 uverbs_cmd_mask;
char node_desc[IB_DEVICE_NODE_DESC_MAX];
__be64 node_guid;
u32 local_dma_lkey;
u16 is_switch:1;
/* Indicates kernel verbs support, should not be used in drivers */
u16 kverbs_provider:1;
/* CQ adaptive moderation (RDMA DIM) */
u16 use_cq_dim:1;
u8 node_type;
u32 phys_port_cnt;
struct ib_device_attr attrs;
struct hw_stats_device_data *hw_stats_data;
#ifdef CONFIG_CGROUP_RDMA
struct rdmacg_device cg_device;
#endif
u32 index;
spinlock_t cq_pools_lock;
struct list_head cq_pools[IB_POLL_LAST_POOL_TYPE + 1];
struct rdma_restrack_root *res;
const struct uapi_definition *driver_def;
/*
* Positive refcount indicates that the device is currently
* registered and cannot be unregistered.
*/
refcount_t refcount;
struct completion unreg_completion;
struct work_struct unregistration_work;
const struct rdma_link_ops *link_ops;
/* Protects compat_devs xarray modifications */
struct mutex compat_devs_mutex;
/* Maintains compat devices for each net namespace */
struct xarray compat_devs;
/* Used by iWarp CM */
char iw_ifname[IFNAMSIZ];
u32 iw_driver_flags;
u32 lag_flags;
};
static inline void *rdma_zalloc_obj(struct ib_device *dev, size_t size,
gfp_t gfp, bool is_numa_aware)
{
if (is_numa_aware && dev->ops.get_numa_node)
return kzalloc_node(size, gfp, dev->ops.get_numa_node(dev));
return kzalloc(size, gfp);
}
struct ib_client_nl_info;
struct ib_client {
const char *name;
int (*add)(struct ib_device *ibdev);
void (*remove)(struct ib_device *, void *client_data);
void (*rename)(struct ib_device *dev, void *client_data);
int (*get_nl_info)(struct ib_device *ibdev, void *client_data,
struct ib_client_nl_info *res);
int (*get_global_nl_info)(struct ib_client_nl_info *res);
/* 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,
u32 port,
u16 pkey,
const union ib_gid *gid,
const struct sockaddr *addr,
void *client_data);
refcount_t uses;
struct completion uses_zero;
u32 client_id;
/* kverbs are not required by the client */
u8 no_kverbs_req:1;
};
/*
* IB block DMA iterator
*
* Iterates the DMA-mapped SGL in contiguous memory blocks aligned
* to a HW supported page size.
*/
struct ib_block_iter {
/* internal states */
struct scatterlist *__sg; /* sg holding the current aligned block */
dma_addr_t __dma_addr; /* unaligned DMA address of this block */
unsigned int __sg_nents; /* number of SG entries */
unsigned int __sg_advance; /* number of bytes to advance in sg in next step */
unsigned int __pg_bit; /* alignment of current block */
};
struct ib_device *_ib_alloc_device(size_t size);
#define ib_alloc_device(drv_struct, member) \
container_of(_ib_alloc_device(sizeof(struct drv_struct) + \
BUILD_BUG_ON_ZERO(offsetof( \
struct drv_struct, member))), \
struct drv_struct, member)
void ib_dealloc_device(struct ib_device *device);
void ib_get_device_fw_str(struct ib_device *device, char *str);
int ib_register_device(struct ib_device *device, const char *name,
struct device *dma_device);
void ib_unregister_device(struct ib_device *device);
void ib_unregister_driver(enum rdma_driver_id driver_id);
void ib_unregister_device_and_put(struct ib_device *device);
void ib_unregister_device_queued(struct ib_device *ib_dev);
int ib_register_client (struct ib_client *client);
void ib_unregister_client(struct ib_client *client);
void __rdma_block_iter_start(struct ib_block_iter *biter,
struct scatterlist *sglist,
unsigned int nents,
unsigned long pgsz);
bool __rdma_block_iter_next(struct ib_block_iter *biter);
/**
* rdma_block_iter_dma_address - get the aligned dma address of the current
* block held by the block iterator.
* @biter: block iterator holding the memory block
*/
static inline dma_addr_t
rdma_block_iter_dma_address(struct ib_block_iter *biter)
{
return biter->__dma_addr & ~(BIT_ULL(biter->__pg_bit) - 1);
}
/**
* rdma_for_each_block - iterate over contiguous memory blocks of the sg list
* @sglist: sglist to iterate over
* @biter: block iterator holding the memory block
* @nents: maximum number of sg entries to iterate over
* @pgsz: best HW supported page size to use
*
* Callers may use rdma_block_iter_dma_address() to get each
* blocks aligned DMA address.
*/
#define rdma_for_each_block(sglist, biter, nents, pgsz) \
for (__rdma_block_iter_start(biter, sglist, nents, \
pgsz); \
__rdma_block_iter_next(biter);)
/**
* ib_get_client_data - Get IB client context
* @device:Device to get context for
* @client:Client to get context for
*
* ib_get_client_data() returns the client context data set with
* ib_set_client_data(). This can only be called while the client is
* registered to the device, once the ib_client remove() callback returns this
* cannot be called.
*/
static inline void *ib_get_client_data(struct ib_device *device,
struct ib_client *client)
{
return xa_load(&device->client_data, client->client_id);
}
void ib_set_client_data(struct ib_device *device, struct ib_client *client,
void *data);
void ib_set_device_ops(struct ib_device *device,
const struct ib_device_ops *ops);
int rdma_user_mmap_io(struct ib_ucontext *ucontext, struct vm_area_struct *vma,
unsigned long pfn, unsigned long size, pgprot_t prot,
struct rdma_user_mmap_entry *entry);
int rdma_user_mmap_entry_insert(struct ib_ucontext *ucontext,
struct rdma_user_mmap_entry *entry,
size_t length);
int rdma_user_mmap_entry_insert_range(struct ib_ucontext *ucontext,
struct rdma_user_mmap_entry *entry,
size_t length, u32 min_pgoff,
u32 max_pgoff);
static inline int
rdma_user_mmap_entry_insert_exact(struct ib_ucontext *ucontext,
struct rdma_user_mmap_entry *entry,
size_t length, u32 pgoff)
{
return rdma_user_mmap_entry_insert_range(ucontext, entry, length, pgoff,
pgoff);
}
struct rdma_user_mmap_entry *
rdma_user_mmap_entry_get_pgoff(struct ib_ucontext *ucontext,
unsigned long pgoff);
struct rdma_user_mmap_entry *
rdma_user_mmap_entry_get(struct ib_ucontext *ucontext,
struct vm_area_struct *vma);
void rdma_user_mmap_entry_put(struct rdma_user_mmap_entry *entry);
void rdma_user_mmap_entry_remove(struct rdma_user_mmap_entry *entry);
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)
{
return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0;
}
static inline bool ib_is_buffer_cleared(const void __user *p,
size_t len)
{
bool ret;
u8 *buf;
if (len > USHRT_MAX)
return false;
buf = memdup_user(p, len);
if (IS_ERR(buf))
return false;
ret = !memchr_inv(buf, 0, len);
kfree(buf);
return ret;
}
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);
}
/**
* 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
*
* 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.
*/
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);
void ib_register_event_handler(struct ib_event_handler *event_handler);
void ib_unregister_event_handler(struct ib_event_handler *event_handler);
void ib_dispatch_event(const struct ib_event *event);
int ib_query_port(struct ib_device *device,
u32 port_num, struct ib_port_attr *port_attr);
enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device,
u32 port_num);
/**
* 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;
}
/**
* rdma_start_port - Return the first valid port number for the device
* specified
*
* @device: Device to be checked
*
* Return start port number
*/
static inline u32 rdma_start_port(const struct ib_device *device)
{
return rdma_cap_ib_switch(device) ? 0 : 1;
}
/**
* rdma_for_each_port - Iterate over all valid port numbers of the IB device
* @device - The struct ib_device * to iterate over
* @iter - The unsigned int to store the port number
*/
#define rdma_for_each_port(device, iter) \
for (iter = rdma_start_port(device + \
BUILD_BUG_ON_ZERO(!__same_type(u32, \
iter))); \
iter <= rdma_end_port(device); iter++)
/**
* rdma_end_port - Return the last valid port number for the device
* specified
*
* @device: Device to be checked
*
* Return last port number
*/
static inline u32 rdma_end_port(const struct ib_device *device)
{
return rdma_cap_ib_switch(device) ? 0 : device->phys_port_cnt;
}
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));
}
static inline bool rdma_is_grh_required(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_PORT_IB_GRH_REQUIRED;
}
static inline bool rdma_protocol_ib(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_PROT_IB;
}
static inline bool rdma_protocol_roce(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.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,
u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP;
}
static inline bool rdma_protocol_roce_eth_encap(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_PROT_ROCE;
}
static inline bool rdma_protocol_iwarp(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_PROT_IWARP;
}
static inline bool rdma_ib_or_roce(const struct ib_device *device,
u32 port_num)
{
return rdma_protocol_ib(device, port_num) ||
rdma_protocol_roce(device, port_num);
}
static inline bool rdma_protocol_raw_packet(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_PROT_RAW_PACKET;
}
static inline bool rdma_protocol_usnic(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_PROT_USNIC;
}
/**
* rdma_cap_ib_mad - Check if the port of a device supports Infiniband
* Management Datagrams.
* @device: Device to check
* @port_num: Port number to check
*
* 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.
*
* Return: true if the port supports sending/receiving of MAD packets.
*/
static inline bool rdma_cap_ib_mad(const struct ib_device *device, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_IB_MAD;
}
/**
* 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, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_OPA_MAD;
}
/**
* 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
*
* 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.
*
* Return: true if the port provides an SMI.
*/
static inline bool rdma_cap_ib_smi(const struct ib_device *device, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_IB_SMI;
}
/**
* rdma_cap_ib_cm - Check if the port of device has the capability Infiniband
* Communication Manager.
* @device: Device to check
* @port_num: Port number to check
*
* 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.
*
* Return: true if the port supports an IB CM (this does not guarantee that
* a CM is actually running however).
*/
static inline bool rdma_cap_ib_cm(const struct ib_device *device, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_IB_CM;
}
/**
* rdma_cap_iw_cm - Check if the port of device has the capability IWARP
* Communication Manager.
* @device: Device to check
* @port_num: Port number to check
*
* Similar to above, but specific to iWARP connections which have a different
* managment protocol than InfiniBand.
*
* Return: true if the port supports an iWARP CM (this does not guarantee that
* a CM is actually running however).
*/
static inline bool rdma_cap_iw_cm(const struct ib_device *device, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_IW_CM;
}
/**
* rdma_cap_ib_sa - Check if the port of device has the capability Infiniband
* Subnet Administration.
* @device: Device to check
* @port_num: Port number to check
*
* 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.
*
* 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.
*/
static inline bool rdma_cap_ib_sa(const struct ib_device *device, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_IB_SA;
}
/**
* rdma_cap_ib_mcast - Check if the port of device has the capability Infiniband
* Multicast.
* @device: Device to check
* @port_num: Port number to check
*
* 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.
*
* 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.
*/
static inline bool rdma_cap_ib_mcast(const struct ib_device *device,
u32 port_num)
{
return rdma_cap_ib_sa(device, port_num);
}
/**
* rdma_cap_af_ib - Check if the port of device has the capability
* Native Infiniband Address.
* @device: Device to check
* @port_num: Port number to check
*
* 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.
*
* Return: true if the port uses a GID address to identify devices on the
* network.
*/
static inline bool rdma_cap_af_ib(const struct ib_device *device, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_AF_IB;
}
/**
* rdma_cap_eth_ah - Check if the port of device has the capability
* Ethernet Address Handle.
* @device: Device to check
* @port_num: Port number to check
*
* 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.
*
* 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.
*/
static inline bool rdma_cap_eth_ah(const struct ib_device *device, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_ETH_AH;
}
/**
* 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, u32 port_num)
{
return (device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_OPA_AH) == RDMA_CORE_CAP_OPA_AH;
}
/**
* 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,
u32 port_num)
{
return device->port_data[port_num].immutable.max_mad_size;
}
/**
* 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,
u32 port_num)
{
return rdma_protocol_roce(device, port_num) &&
device->ops.add_gid && device->ops.del_gid;
}
/*
* Check if the device supports READ W/ INVALIDATE.
*/
static inline bool rdma_cap_read_inv(struct ib_device *dev, u32 port_num)