diff options
Diffstat (limited to 'include/rdma')
| -rw-r--r-- | include/rdma/ib_addr.h | 63 | ||||
| -rw-r--r-- | include/rdma/ib_cache.h | 29 | ||||
| -rw-r--r-- | include/rdma/ib_hdrs.h | 19 | ||||
| -rw-r--r-- | include/rdma/ib_pack.h | 19 | ||||
| -rw-r--r-- | include/rdma/ib_sa.h | 35 | ||||
| -rw-r--r-- | include/rdma/ib_umem_odp.h | 4 | ||||
| -rw-r--r-- | include/rdma/ib_verbs.h | 327 | ||||
| -rw-r--r-- | include/rdma/opa_addr.h | 22 | ||||
| -rw-r--r-- | include/rdma/rdma_cm.h | 63 | ||||
| -rw-r--r-- | include/rdma/rdma_cm_ib.h | 8 | ||||
| -rw-r--r-- | include/rdma/rdma_netlink.h | 1 | ||||
| -rw-r--r-- | include/rdma/rdma_vt.h | 33 | ||||
| -rw-r--r-- | include/rdma/rdmavt_qp.h | 6 | ||||
| -rw-r--r-- | include/rdma/restrack.h | 177 | ||||
| -rw-r--r-- | include/rdma/uverbs_ioctl.h | 192 | ||||
| -rw-r--r-- | include/rdma/uverbs_named_ioctl.h | 90 | ||||
| -rw-r--r-- | include/rdma/uverbs_std_types.h | 34 |
17 files changed, 844 insertions, 278 deletions
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h index ec5008cf5d51..a08cc7278980 100644 --- a/include/rdma/ib_addr.h +++ b/include/rdma/ib_addr.h @@ -94,7 +94,7 @@ struct rdma_dev_addr { * The dev_addr->net field must be initialized. */ int rdma_translate_ip(const struct sockaddr *addr, - struct rdma_dev_addr *dev_addr, u16 *vlan_id); + struct rdma_dev_addr *dev_addr); /** * rdma_resolve_ip - Resolve source and destination IP addresses to @@ -119,22 +119,15 @@ int rdma_resolve_ip(struct rdma_addr_client *client, struct rdma_dev_addr *addr, void *context), void *context); -int rdma_resolve_ip_route(struct sockaddr *src_addr, - const struct sockaddr *dst_addr, - struct rdma_dev_addr *addr); - void rdma_addr_cancel(struct rdma_dev_addr *addr); -int rdma_copy_addr(struct rdma_dev_addr *dev_addr, struct net_device *dev, - const unsigned char *dst_dev_addr); +void rdma_copy_addr(struct rdma_dev_addr *dev_addr, + const struct net_device *dev, + const unsigned char *dst_dev_addr); int rdma_addr_size(struct sockaddr *addr); - -int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id); -int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid, - const union ib_gid *dgid, - u8 *smac, u16 *vlan_id, int *if_index, - int *hoplimit); +int rdma_addr_size_in6(struct sockaddr_in6 *addr); +int rdma_addr_size_kss(struct __kernel_sockaddr_storage *addr); static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr) { @@ -197,34 +190,15 @@ static inline void rdma_gid2ip(struct sockaddr *out, const union ib_gid *gid) } } -static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr, - union ib_gid *gid) -{ - struct net_device *dev; - struct in_device *ip4; - - dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if); - if (dev) { - ip4 = in_dev_get(dev); - if (ip4 && ip4->ifa_list && ip4->ifa_list->ifa_address) - ipv6_addr_set_v4mapped(ip4->ifa_list->ifa_address, - (struct in6_addr *)gid); - - if (ip4) - in_dev_put(ip4); - - dev_put(dev); - } -} - +/* + * rdma_get/set_sgid/dgid() APIs are applicable to IB, and iWarp. + * They are not applicable to RoCE. + * RoCE GIDs are derived from the IP addresses. + */ static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { - if (dev_addr->transport == RDMA_TRANSPORT_IB && - dev_addr->dev_type != ARPHRD_INFINIBAND) - iboe_addr_get_sgid(dev_addr, gid); - else - memcpy(gid, dev_addr->src_dev_addr + - rdma_addr_gid_offset(dev_addr), sizeof *gid); + memcpy(gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), + sizeof(*gid)); } static inline void rdma_addr_set_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) @@ -245,10 +219,11 @@ static inline void rdma_addr_set_dgid(struct rdma_dev_addr *dev_addr, union ib_g static inline enum ib_mtu iboe_get_mtu(int mtu) { /* - * reduce IB headers from effective IBoE MTU. 28 stands for - * atomic header which is the biggest possible header after BTH + * Reduce IB headers from effective IBoE MTU. */ - mtu = mtu - IB_GRH_BYTES - IB_BTH_BYTES - 28; + mtu = mtu - (IB_GRH_BYTES + IB_UDP_BYTES + IB_BTH_BYTES + + IB_EXT_XRC_BYTES + IB_EXT_ATOMICETH_BYTES + + IB_ICRC_BYTES); if (mtu >= ib_mtu_enum_to_int(IB_MTU_4096)) return IB_MTU_4096; @@ -305,12 +280,12 @@ static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac) static inline int rdma_is_multicast_addr(struct in6_addr *addr) { - u32 ipv4_addr; + __be32 ipv4_addr; if (addr->s6_addr[0] == 0xff) return 1; - memcpy(&ipv4_addr, addr->s6_addr + 12, 4); + ipv4_addr = addr->s6_addr32[3]; return (ipv6_addr_v4mapped(addr) && ipv4_is_multicast(ipv4_addr)); } diff --git a/include/rdma/ib_cache.h b/include/rdma/ib_cache.h index 385ec88ee9e5..eb49cc8d1f95 100644 --- a/include/rdma/ib_cache.h +++ b/include/rdma/ib_cache.h @@ -55,20 +55,6 @@ int ib_get_cached_gid(struct ib_device *device, union ib_gid *gid, struct ib_gid_attr *attr); -/** - * ib_find_cached_gid - Returns the port number and GID table index where - * a specified GID value occurs. - * @device: The device to query. - * @gid: The GID value to search for. - * @gid_type: The GID type to search for. - * @ndev: In RoCE, the net device of the device. NULL means ignore. - * @port_num: The port number of the device where the GID value was found. - * @index: The index into the cached GID table where the GID was found. This - * parameter may be NULL. - * - * ib_find_cached_gid() searches for the specified GID value in - * the local software cache. - */ int ib_find_cached_gid(struct ib_device *device, const union ib_gid *gid, enum ib_gid_type gid_type, @@ -76,21 +62,6 @@ int ib_find_cached_gid(struct ib_device *device, u8 *port_num, u16 *index); -/** - * ib_find_cached_gid_by_port - Returns the GID table index where a specified - * GID value occurs - * @device: The device to query. - * @gid: The GID value to search for. - * @gid_type: The GID type to search for. - * @port_num: The port number of the device where the GID value sould be - * searched. - * @ndev: In RoCE, the net device of the device. Null means ignore. - * @index: The index into the cached GID table where the GID was found. This - * parameter may be NULL. - * - * ib_find_cached_gid() searches for the specified GID value in - * the local software cache. - */ int ib_find_cached_gid_by_port(struct ib_device *device, const union ib_gid *gid, enum ib_gid_type gid_type, diff --git a/include/rdma/ib_hdrs.h b/include/rdma/ib_hdrs.h index c124d515f7d5..6e35416170a3 100644 --- a/include/rdma/ib_hdrs.h +++ b/include/rdma/ib_hdrs.h @@ -313,16 +313,14 @@ static inline u32 ib_bth_get_qpn(struct ib_other_headers *ohdr) return (u32)((be32_to_cpu(ohdr->bth[1])) & IB_QPN_MASK); } -static inline u8 ib_bth_get_becn(struct ib_other_headers *ohdr) +static inline bool ib_bth_get_becn(struct ib_other_headers *ohdr) { - return (u8)((be32_to_cpu(ohdr->bth[1]) >> IB_BECN_SHIFT) & - IB_BECN_MASK); + return (ohdr->bth[1]) & cpu_to_be32(IB_BECN_SMASK); } -static inline u8 ib_bth_get_fecn(struct ib_other_headers *ohdr) +static inline bool ib_bth_get_fecn(struct ib_other_headers *ohdr) { - return (u8)((be32_to_cpu(ohdr->bth[1]) >> IB_FECN_SHIFT) & - IB_FECN_MASK); + return (ohdr->bth[1]) & cpu_to_be32(IB_FECN_SMASK); } static inline u8 ib_bth_get_tver(struct ib_other_headers *ohdr) @@ -331,4 +329,13 @@ static inline u8 ib_bth_get_tver(struct ib_other_headers *ohdr) IB_BTH_TVER_MASK); } +static inline bool ib_bth_is_solicited(struct ib_other_headers *ohdr) +{ + return ohdr->bth[0] & cpu_to_be32(IB_BTH_SOLICITED); +} + +static inline bool ib_bth_is_migration(struct ib_other_headers *ohdr) +{ + return ohdr->bth[0] & cpu_to_be32(IB_BTH_MIG_REQ); +} #endif /* IB_HDRS_H */ diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h index 36655899ee02..7ea1382ad0e5 100644 --- a/include/rdma/ib_pack.h +++ b/include/rdma/ib_pack.h @@ -37,14 +37,17 @@ #include <uapi/linux/if_ether.h> enum { - IB_LRH_BYTES = 8, - IB_ETH_BYTES = 14, - IB_VLAN_BYTES = 4, - IB_GRH_BYTES = 40, - IB_IP4_BYTES = 20, - IB_UDP_BYTES = 8, - IB_BTH_BYTES = 12, - IB_DETH_BYTES = 8 + IB_LRH_BYTES = 8, + IB_ETH_BYTES = 14, + IB_VLAN_BYTES = 4, + IB_GRH_BYTES = 40, + IB_IP4_BYTES = 20, + IB_UDP_BYTES = 8, + IB_BTH_BYTES = 12, + IB_DETH_BYTES = 8, + IB_EXT_ATOMICETH_BYTES = 28, + IB_EXT_XRC_BYTES = 4, + IB_ICRC_BYTES = 4 }; struct ib_field { diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h index 355b81f4242d..bacb144f7780 100644 --- a/include/rdma/ib_sa.h +++ b/include/rdma/ib_sa.h @@ -163,7 +163,15 @@ struct sa_path_rec_ib { u8 raw_traffic; }; +/** + * struct sa_path_rec_roce - RoCE specific portion of the path record entry + * @route_resolved: When set, it indicates that this route is already + * resolved for this path record entry. + * @dmac: Destination mac address for the given DGID entry + * of the path record entry. + */ struct sa_path_rec_roce { + bool route_resolved; u8 dmac[ETH_ALEN]; /* ignored in IB */ int ifindex; @@ -549,12 +557,12 @@ int ib_init_ah_from_mcmember(struct ib_device *device, u8 port_num, struct rdma_ah_attr *ah_attr); /** - * ib_init_ah_from_path - Initialize address handle attributes based on an SA - * path record. + * ib_init_ah_attr_from_path - Initialize address handle attributes based on + * an SA path record. */ -int ib_init_ah_from_path(struct ib_device *device, u8 port_num, - struct sa_path_rec *rec, - struct rdma_ah_attr *ah_attr); +int ib_init_ah_attr_from_path(struct ib_device *device, u8 port_num, + struct sa_path_rec *rec, + struct rdma_ah_attr *ah_attr); /** * ib_sa_pack_path - Conert a path record from struct ib_sa_path_rec @@ -590,20 +598,25 @@ static inline bool sa_path_is_roce(struct sa_path_rec *rec) (rec->rec_type == SA_PATH_REC_TYPE_ROCE_V2)); } -static inline void sa_path_set_slid(struct sa_path_rec *rec, __be32 slid) +static inline bool sa_path_is_opa(struct sa_path_rec *rec) +{ + return (rec->rec_type == SA_PATH_REC_TYPE_OPA); +} + +static inline void sa_path_set_slid(struct sa_path_rec *rec, u32 slid) { if (rec->rec_type == SA_PATH_REC_TYPE_IB) - rec->ib.slid = htons(ntohl(slid)); + rec->ib.slid = cpu_to_be16(slid); else if (rec->rec_type == SA_PATH_REC_TYPE_OPA) - rec->opa.slid = slid; + rec->opa.slid = cpu_to_be32(slid); } -static inline void sa_path_set_dlid(struct sa_path_rec *rec, __be32 dlid) +static inline void sa_path_set_dlid(struct sa_path_rec *rec, u32 dlid) { if (rec->rec_type == SA_PATH_REC_TYPE_IB) - rec->ib.dlid = htons(ntohl(dlid)); + rec->ib.dlid = cpu_to_be16(dlid); else if (rec->rec_type == SA_PATH_REC_TYPE_OPA) - rec->opa.dlid = dlid; + rec->opa.dlid = cpu_to_be32(dlid); } static inline void sa_path_set_raw_traffic(struct sa_path_rec *rec, diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h index 5eb7f5bc8248..6a17f856f841 100644 --- a/include/rdma/ib_umem_odp.h +++ b/include/rdma/ib_umem_odp.h @@ -111,10 +111,6 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 start_offset, u64 bcnt, void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 start_offset, u64 bound); -void rbt_ib_umem_insert(struct umem_odp_node *node, - struct rb_root_cached *root); -void rbt_ib_umem_remove(struct umem_odp_node *node, - struct rb_root_cached *root); typedef int (*umem_call_back)(struct ib_umem *item, u64 start, u64 end, void *cookie); /* diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index e8608b2dc844..9fc8a825aa28 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -63,6 +63,9 @@ #include <linux/uaccess.h> #include <linux/cgroup_rdma.h> #include <uapi/rdma/ib_user_verbs.h> +#include <rdma/restrack.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 @@ -89,8 +92,11 @@ enum ib_gid_type { #define ROCE_V2_UDP_DPORT 4791 struct ib_gid_attr { - enum ib_gid_type gid_type; struct net_device *ndev; + struct ib_device *device; + enum ib_gid_type gid_type; + u16 index; + u8 port_num; }; enum rdma_node_type { @@ -229,6 +235,8 @@ enum ib_device_cap_flags { /* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */ IB_DEVICE_RAW_SCATTER_FCS = (1ULL << 34), IB_DEVICE_RDMA_NETDEV_OPA_VNIC = (1ULL << 35), + /* The device supports padding incoming writes to cacheline. */ + IB_DEVICE_PCI_WRITE_END_PADDING = (1ULL << 36), }; enum ib_signature_prot_cap { @@ -298,17 +306,33 @@ struct ib_tm_caps { u32 max_sge; }; -enum ib_cq_creation_flags { - IB_CQ_FLAGS_TIMESTAMP_COMPLETION = 1 << 0, - IB_CQ_FLAGS_IGNORE_OVERRUN = 1 << 1, -}; - struct ib_cq_init_attr { unsigned int cqe; int 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; @@ -359,6 +383,8 @@ struct ib_device_attr { 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; }; enum ib_mtu { @@ -461,6 +487,9 @@ enum ib_port_speed { /** * struct rdma_hw_stats + * @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. * @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 @@ -476,6 +505,7 @@ enum ib_port_speed { * 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 char * const *names; @@ -866,6 +896,7 @@ struct ib_mr_status { __attribute_const__ enum ib_rate mult_to_ib_rate(int mult); 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, @@ -971,9 +1002,9 @@ struct ib_wc { u32 invalidate_rkey; } ex; u32 src_qp; + u32 slid; int wc_flags; u16 pkey_index; - u32 slid; u8 sl; u8 dlid_path_bits; u8 port_num; /* valid only for DR SMPs on switches */ @@ -1070,6 +1101,7 @@ enum ib_qp_type { IB_QPT_XRC_INI = 9, IB_QPT_XRC_TGT, IB_QPT_MAX, + IB_QPT_DRIVER = 0xFF, /* 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 @@ -1098,6 +1130,7 @@ enum ib_qp_create_flags { IB_QP_CREATE_SCATTER_FCS = 1 << 8, IB_QP_CREATE_CVLAN_STRIPPING = 1 << 9, IB_QP_CREATE_SOURCE_QPN = 1 << 10, + IB_QP_CREATE_PCI_WRITE_END_PADDING = 1 << 11, /* reserve bits 26-31 for low level drivers' internal use */ IB_QP_CREATE_RESERVED_START = 1 << 26, IB_QP_CREATE_RESERVED_END = 1 << 31, @@ -1516,6 +1549,7 @@ struct ib_pd { * Implementation details of the RDMA core, don't use in drivers: */ struct ib_mr *__internal_mr; + struct rdma_restrack_entry res; }; struct ib_xrcd { @@ -1556,6 +1590,10 @@ struct ib_cq { struct irq_poll iop; struct work_struct work; }; + /* + * Implementation details of the RDMA core, don't use in drivers: + */ + struct rdma_restrack_entry res; }; struct ib_srq { @@ -1621,6 +1659,7 @@ enum ib_wq_flags { IB_WQ_FLAGS_CVLAN_STRIPPING = 1 << 0, IB_WQ_FLAGS_SCATTER_FCS = 1 << 1, IB_WQ_FLAGS_DELAY_DROP = 1 << 2, + IB_WQ_FLAGS_PCI_WRITE_END_PADDING = 1 << 3, }; struct ib_wq_init_attr { @@ -1731,6 +1770,19 @@ struct ib_qp { struct ib_rwq_ind_table *rwq_ind_tbl; struct ib_qp_security *qp_sec; u8 port; + + /* + * Implementation details of the RDMA core, don't use in drivers: + */ + struct rdma_restrack_entry res; +}; + +struct ib_dm { + struct ib_device *device; + u32 length; + u32 flags; + struct ib_uobject *uobject; + atomic_t usecnt; }; struct ib_mr { @@ -1746,6 +1798,13 @@ struct ib_mr { struct ib_uobject *uobject; /* user */ struct list_head qp_entry; /* FR */ }; + + struct ib_dm *dm; + + /* + * Implementation details of the RDMA core, don't use in drivers: + */ + struct rdma_restrack_entry res; }; struct ib_mw { @@ -1788,6 +1847,7 @@ enum ib_flow_spec_type { /* 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, @@ -1796,6 +1856,7 @@ enum ib_flow_spec_type { /* Actions */ IB_FLOW_SPEC_ACTION_TAG = 0x1000, IB_FLOW_SPEC_ACTION_DROP = 0x1001, + IB_FLOW_SPEC_ACTION_HANDLE = 0x1002, }; #define IB_FLOW_SPEC_LAYER_MASK 0xF0 #define IB_FLOW_SPEC_SUPPORT_LAYERS 8 @@ -1813,7 +1874,8 @@ enum ib_flow_domain { 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 */ + IB_FLOW_ATTR_FLAGS_EGRESS = 1UL << 2, /* Egress flow */ + IB_FLOW_ATTR_FLAGS_RESERVED = 1UL << 3 /* Must be last */ }; struct ib_flow_eth_filter { @@ -1918,6 +1980,20 @@ struct ib_flow_spec_tunnel { struct ib_flow_tunnel_filter mask; }; +struct ib_flow_esp_filter { + __be32 spi; + __be32 seq; + /* Must be last */ + u8 real_sz[0]; +}; + +struct ib_flow_spec_esp { + u32 type; + u16 size; + struct ib_flow_esp_filter val; + struct ib_flow_esp_filter mask; +}; + struct ib_flow_spec_action_tag { enum ib_flow_spec_type type; u16 size; @@ -1929,6 +2005,12 @@ struct ib_flow_spec_action_drop { u16 size; }; +struct ib_flow_spec_action_handle { + enum ib_flow_spec_type type; + u16 size; + struct ib_flow_action *act; +}; + union ib_flow_spec { struct { u32 type; @@ -1940,8 +2022,10 @@ union ib_flow_spec { 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_action_tag flow_tag; struct ib_flow_spec_action_drop drop; + struct ib_flow_spec_action_handle action; }; struct ib_flow_attr { @@ -1962,6 +2046,64 @@ struct ib_flow { 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_hdr; struct ib_grh; @@ -2038,6 +2180,8 @@ struct ib_port_pkey_list { struct list_head pkey_list; }; +struct uverbs_attr_bundle; + struct ib_device { /* Do not access @dma_device directly from ULP nor from HW drivers. */ struct device *dma_device; @@ -2100,42 +2244,41 @@ struct ib_device { * 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. + * that this function returns NULL before the net device has finished + * NETDEV_UNREGISTER state. */ struct net_device *(*get_netdev)(struct ib_device *device, u8 port_num); + /* 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, u8 port_num, int index, union ib_gid *gid); - /* When calling add_gid, the HW vendor's driver should - * add the gid of device @device at gid index @index of - * port @port_num to be @gid. 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 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 + /* 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. + * concurrently for different ports. This function is only called when + * roce_gid_table is used. */ - int (*add_gid)(struct ib_device *device, - u8 port_num, - unsigned int index, - const union ib_gid *gid, + int (*add_gid)(const union ib_gid *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 @index of port @port_num. + * 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)(struct ib_device *device, - u8 port_num, - unsigned int index, + int (*del_gid)(const struct ib_gid_attr *attr, void **context); int (*query_pkey)(struct ib_device *device, u8 port_num, u16 index, u16 *pkey); @@ -2293,6 +2436,21 @@ struct ib_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); + struct ib_flow_action * (*create_flow_action_esp)(struct ib_device *device, + const struct ib_flow_action_attrs_esp *attr, + struct uverbs_attr_bundle *attrs); + int (*destroy_flow_action)(struct ib_flow_action *action); + int (*modify_flow_action_esp)(struct ib_flow_action *action, + const struct ib_flow_action_attrs_esp *attr, + struct uverbs_attr_bundle *attrs); + 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 ib_mr * (*reg_dm_mr)(struct ib_pd *pd, struct ib_dm *dm, + struct ib_dm_mr_attr *attr, + struct uverbs_attr_bundle *attrs); /** * rdma netdev operation * @@ -2337,6 +2495,10 @@ struct ib_device { #endif u32 index; + /* + * Implementation details of the RDMA core, don't use in drivers + */ + struct rdma_restrack_root res; /** * The following mandatory functions are used only at device @@ -2350,6 +2512,7 @@ struct ib_device { int comp_vector); struct uverbs_root_spec *specs_root; + enum rdma_driver_id driver_id; }; struct ib_client { @@ -2409,11 +2572,9 @@ 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_udata_cleared(struct ib_udata *udata, - size_t offset, - size_t len) +static inline bool ib_is_buffer_cleared(const void __user *p, + size_t len) { - const void __user *p = udata->inbuf + offset; bool ret; u8 *buf; @@ -2429,6 +2590,13 @@ static inline bool ib_is_udata_cleared(struct ib_udata *udata, 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 @@ -2445,9 +2613,9 @@ static inline bool ib_is_udata_cleared(struct ib_udata *udata, * transition from cur_state to next_state is allowed by the IB spec, * and that the attribute mask supplied is allowed for the transition. */ -int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state, - enum ib_qp_type type, enum ib_qp_attr_mask mask, - enum rdma_link_layer ll); +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); void ib_register_event_handler(struct ib_event_handler *event_handler); void ib_unregister_event_handler(struct ib_event_handler *event_handler); @@ -2822,7 +2990,6 @@ int ib_modify_port(struct ib_device *device, struct ib_port_modify *port_modify); int ib_find_gid(struct ib_device *device, union ib_gid *gid, - enum ib_gid_type gid_type, struct net_device *ndev, u8 *port_num, u16 *index); int ib_find_pkey(struct ib_device *device, @@ -2844,7 +3011,7 @@ enum ib_pd_flags { struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags, const char *caller); #define ib_alloc_pd(device, flags) \ - __ib_alloc_pd((device), (flags), __func__) + __ib_alloc_pd((device), (flags), KBUILD_MODNAME) void ib_dealloc_pd(struct ib_pd *pd); /** @@ -2858,6 +3025,21 @@ void ib_dealloc_pd(struct ib_pd *pd); struct ib_ah *rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr); /** + * 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); +/** * ib_get_gids_from_rdma_hdr - Get sgid and dgid from GRH or IPv4 header * work completion. * @hdr: the L3 header to parse @@ -2876,7 +3058,7 @@ int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr, int ib_get_rdma_header_version(const union rdma_network_hdr *hdr); /** - * ib_init_ah_from_wc - Initializes address handle attributes from a + * ib_init_ah_attr_from_wc - Initializes address handle attributes from a * work completion. * @device: Device on which the received message arrived. * @port_num: Port on which the received message arrived. @@ -2886,9 +3068,9 @@ int ib_get_rdma_header_version(const union rdma_network_hdr *hdr); * @ah_attr: Returned attributes that can be used when creating an address * handle for replying to the message. */ -int ib_init_ah_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); +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); /** * ib_create_ah_from_wc - Creates an address handle associated with the @@ -3106,8 +3288,12 @@ static inline int ib_post_recv(struct ib_qp *qp, return qp->device->post_recv(qp, recv_wr, bad_recv_wr); } -struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private, - int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx); +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) + void ib_free_cq(struct ib_cq *cq); int ib_process_cq_direct(struct ib_cq *cq, int budget); @@ -3140,13 +3326,13 @@ struct ib_cq *ib_create_cq(struct ib_device *device, int ib_resize_cq(struct ib_cq *cq, int cqe); /** - * ib_modify_cq - Modifies moderation params of the CQ + * rdma_set_cq_moderation - Modifies moderation params of the CQ * @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 * */ -int ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period); +int rdma_set_cq_moderation(struct ib_cq *cq, u16 cq_count, u16 cq_period); /** * ib_destroy_cq - Destroys the specified CQ. @@ -3173,18 +3359,6 @@ static inline int ib_poll_cq(struct ib_cq *cq, int num_entries, } /** - * ib_peek_cq - Returns the number of unreaped completions currently - * on the specified CQ. - * @cq: The CQ to peek. - * @wc_cnt: A minimum number of unreaped completions to check for. - * - * If the number of unreaped completions is greater than or equal to wc_cnt, - * this function returns wc_cnt, otherwise, it returns the actual number of - * unreaped completions. - */ -int ib_peek_cq(struct ib_cq *cq, int wc_cnt); - -/** * ib_req_notify_cq - Request completion notification on a CQ. * @cq: The CQ to generate an event for. * @flags: @@ -3531,8 +3705,11 @@ int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid); /** * ib_alloc_xrcd - Allocates an XRC domain. * @device: The device on which to allocate the XRC domain. + * @caller: Module name for kernel consumers */ -struct ib_xrcd *ib_alloc_xrcd(struct ib_device *device); +struct ib_xrcd *__ib_alloc_xrcd(struct ib_device *device, const char *caller); +#define ib_alloc_xrcd(device) \ + __ib_alloc_xrcd((device), KBUILD_MODNAME) /** * ib_dealloc_xrcd - Deallocates an XRC domain. @@ -3607,8 +3784,6 @@ void ib_drain_rq(struct ib_qp *qp); void ib_drain_sq(struct ib_qp *qp); void ib_drain_qp(struct ib_qp *qp); -int ib_resolve_eth_dmac(struct ib_device *device, - struct rdma_ah_attr *ah_attr); int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width); static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr) @@ -3762,18 +3937,24 @@ static inline void rdma_ah_set_grh(struct rdma_ah_attr *attr, grh->traffic_class = traffic_class; } -/*Get AH type */ +/** + * rdma_ah_find_type - Return address handle type. + * + * @dev: Device to be checked + * @port_num: Port number + */ static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev, - u32 port_num) + u8 port_num) { - if ((rdma_protocol_roce(dev, port_num)) || - (rdma_protocol_iwarp(dev, port_num))) + if (rdma_protocol_roce(dev, port_num)) return RDMA_AH_ATTR_TYPE_ROCE; - else if ((rdma_protocol_ib(dev, port_num)) && - (rdma_cap_opa_ah(dev, port_num))) - return RDMA_AH_ATTR_TYPE_OPA; - else + if (rdma_protocol_ib(dev, port_num)) { + if (rdma_cap_opa_ah(dev, port_num)) + return RDMA_AH_ATTR_TYPE_OPA; return RDMA_AH_ATTR_TYPE_IB; + } + + return RDMA_AH_ATTR_TYPE_UNDEFINED; } /** @@ -3823,4 +4004,12 @@ ib_get_vector_affinity(struct ib_device *device, int comp_vector) } +/** + * 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); + #endif /* IB_VERBS_H */ diff --git a/include/rdma/opa_addr.h b/include/rdma/opa_addr.h index e6e90f18e6d5..2bbb7a67e643 100644 --- a/include/rdma/opa_addr.h +++ b/include/rdma/opa_addr.h @@ -97,15 +97,15 @@ static inline u32 opa_get_lid_from_gid(const union ib_gid *gid) * @dlid: The DLID * @slid: The SLID */ -static inline bool opa_is_extended_lid(u32 dlid, u32 slid) +static inline bool opa_is_extended_lid(__be32 dlid, __be32 slid) { if ((be32_to_cpu(dlid) >= be16_to_cpu(IB_MULTICAST_LID_BASE)) || (be32_to_cpu(slid) >= be16_to_cpu(IB_MULTICAST_LID_BASE))) return true; - else - return false; + + return false; } /* Get multicast lid base */ @@ -114,4 +114,20 @@ static inline u32 opa_get_mcast_base(u32 nr_top_bits) return (be32_to_cpu(OPA_LID_PERMISSIVE) << (32 - nr_top_bits)); } +/* Check for a valid unicast LID for non-SM traffic types */ +static inline bool rdma_is_valid_unicast_lid(struct rdma_ah_attr *attr) +{ + if (attr->type == RDMA_AH_ATTR_TYPE_IB) { + if (!rdma_ah_get_dlid(attr) || + rdma_ah_get_dlid(attr) >= + be32_to_cpu(IB_MULTICAST_LID_BASE)) + return false; + } else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) { + if (!rdma_ah_get_dlid(attr) || + rdma_ah_get_dlid(attr) >= + opa_get_mcast_base(OPA_MCAST_NR)) + return false; + } + return true; +} #endif /* OPA_ADDR_H */ diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h index 3d2eed3c4e75..690934733ba7 100644 --- a/include/rdma/rdma_cm.h +++ b/include/rdma/rdma_cm.h @@ -38,6 +38,7 @@ #include <linux/in6.h> #include <rdma/ib_addr.h> #include <rdma/ib_sa.h> +#include <uapi/rdma/rdma_user_cm.h> /* * Upon receiving a device removal event, users must destroy the associated @@ -64,14 +65,6 @@ enum rdma_cm_event_type { const char *__attribute_const__ rdma_event_msg(enum rdma_cm_event_type event); -enum rdma_port_space { - RDMA_PS_SDP = 0x0001, - RDMA_PS_IPOIB = 0x0002, - RDMA_PS_IB = 0x013F, - RDMA_PS_TCP = 0x0106, - RDMA_PS_UDP = 0x0111, -}; - #define RDMA_IB_IP_PS_MASK 0xFFFFFFFFFFFF0000ULL #define RDMA_IB_IP_PS_TCP 0x0000000001060000ULL #define RDMA_IB_IP_PS_UDP 0x0000000001110000ULL @@ -120,20 +113,6 @@ struct rdma_cm_event { } param; }; -enum rdma_cm_state { - RDMA_CM_IDLE, - RDMA_CM_ADDR_QUERY, - RDMA_CM_ADDR_RESOLVED, - RDMA_CM_ROUTE_QUERY, - RDMA_CM_ROUTE_RESOLVED, - RDMA_CM_CONNECT, - RDMA_CM_DISCONNECT, - RDMA_CM_ADDR_BOUND, - RDMA_CM_LISTEN, - RDMA_CM_DEVICE_REMOVAL, - RDMA_CM_DESTROYING -}; - struct rdma_cm_id; /** @@ -152,11 +131,17 @@ struct rdma_cm_id { struct ib_qp *qp; rdma_cm_event_handler event_handler; struct rdma_route route; - enum rdma_port_space ps; + enum rdma_ucm_port_space ps; enum ib_qp_type qp_type; u8 port_num; }; +struct rdma_cm_id *__rdma_create_id(struct net *net, + rdma_cm_event_handler event_handler, + void *context, enum rdma_ucm_port_space ps, + enum ib_qp_type qp_type, + const char *caller); + /** * rdma_create_id - Create an RDMA identifier. * @@ -169,10 +154,9 @@ struct rdma_cm_id { * * The id holds a reference on the network namespace until it is destroyed. */ -struct rdma_cm_id *rdma_create_id(struct net *net, - rdma_cm_event_handler event_handler, - void *context, enum rdma_port_space ps, - enum ib_qp_type qp_type); +#define rdma_create_id(net, event_handler, context, ps, qp_type) \ + __rdma_create_id((net), (event_handler), (context), (ps), (qp_type), \ + KBUILD_MODNAME) /** * rdma_destroy_id - Destroys an RDMA identifier. @@ -284,6 +268,9 @@ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param); */ int rdma_listen(struct rdma_cm_id *id, int backlog); +int __rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, + const char *caller); + /** * rdma_accept - Called to accept a connection request or response. * @id: Connection identifier associated with the request. @@ -299,7 +286,8 @@ int rdma_listen(struct rdma_cm_id *id, int backlog); * state of the qp associated with the id is modified to error, such that any * previously posted receive buffers would be flushed. */ -int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param); +#define rdma_accept(id, conn_param) \ + __rdma_accept((id), (conn_param), KBUILD_MODNAME) /** * rdma_notify - Notifies the RDMA CM of an asynchronous event that has @@ -413,4 +401,23 @@ bool rdma_is_consumer_reject(struct rdma_cm_id *id, int reason); const void *rdma_consumer_reject_data(struct rdma_cm_id *id, struct rdma_cm_event *ev, u8 *data_len); +/** + * rdma_read_gids - Return the SGID and DGID used for establishing + * connection. This can be used after rdma_resolve_addr() + * on client side. This can be use on new connection + * on server side. This is applicable to IB, RoCE, iWarp. + * If cm_id is not bound yet to the RDMA device, it doesn't + * copy and SGID or DGID to the given pointers. + * @id: Communication identifier whose GIDs are queried. + * @sgid: Pointer to SGID where SGID will be returned. It is optional. + * @dgid: Pointer to DGID where DGID will be returned. It is optional. + * Note: This API should not be used by any new ULPs or new code. + * Instead, users interested in querying GIDs should refer to path record + * of the rdma_cm_id to query the GIDs. + * This API is provided for compatibility for existing users. + */ + +void rdma_read_gids(struct rdma_cm_id *cm_id, union ib_gid *sgid, + union ib_gid *dgid); + #endif /* RDMA_CM_H */ diff --git a/include/rdma/rdma_cm_ib.h b/include/rdma/rdma_cm_ib.h index 6947a6ba2557..6a69d71a21a5 100644 --- a/include/rdma/rdma_cm_ib.h +++ b/include/rdma/rdma_cm_ib.h @@ -36,17 +36,17 @@ #include <rdma/rdma_cm.h> /** - * rdma_set_ib_paths - Manually sets the path records used to establish a + * rdma_set_ib_path - Manually sets the path record used to establish a * connection. * @id: Connection identifier associated with the request. * @path_rec: Reference to the path record * * This call permits a user to specify routing information for rdma_cm_id's - * bound to Infiniband devices. It is called on the client side of a + * bound to InfiniBand devices. It is called on the client side of a * connection and replaces the call to rdma_resolve_route. */ -int rdma_set_ib_paths(struct rdma_cm_id *id, - struct sa_path_rec *path_rec, int num_paths); +int rdma_set_ib_path(struct rdma_cm_id *id, + struct sa_path_rec *path_rec); /* Global qkey for UDP QPs and multicast groups. */ #define RDMA_UDP_QKEY 0x01234567 diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h index 2d878596b1e0..c369703fcd69 100644 --- a/include/rdma/rdma_netlink.h +++ b/include/rdma/rdma_netlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _RDMA_NETLINK_H #define _RDMA_NETLINK_H diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h index 1ba84a78f1c5..3f4c187e435d 100644 --- a/include/rdma/rdma_vt.h +++ b/include/rdma/rdma_vt.h @@ -228,13 +228,6 @@ struct rvt_driver_provided { int (*port_callback)(struct ib_device *, u8, struct kobject *); /* - * Returns a string to represent the device for which is being - * registered. This is primarily used for error and debug messages on - * the console. - */ - const char * (*get_card_name)(struct rvt_dev_info *rdi); - - /* * Returns a pointer to the undelying hardware's PCI device. This is * used to display information as to what hardware is being referenced * in an output message @@ -419,6 +412,30 @@ struct rvt_dev_info { }; +/** + * rvt_set_ibdev_name - Craft an IB device name from client info + * @rdi: pointer to the client rvt_dev_info structure + * @name: client specific name + * @unit: client specific unit number. + */ +static inline void rvt_set_ibdev_name(struct rvt_dev_info *rdi, + const char *fmt, const char *name, + const int unit) +{ + snprintf(rdi->ibdev.name, sizeof(rdi->ibdev.name), fmt, name, unit); +} + +/** + * rvt_get_ibdev_name - return the IB name + * @rdi: rdmavt device + * + * Return the registered name of the device. + */ +static inline const char *rvt_get_ibdev_name(const struct rvt_dev_info *rdi) +{ + return rdi->ibdev.name; +} + static inline struct rvt_pd *ibpd_to_rvtpd(struct ib_pd *ibpd) { return container_of(ibpd, struct rvt_pd, ibpd); @@ -521,7 +538,7 @@ static inline void rvt_mod_retry_timer(struct rvt_qp *qp) struct rvt_dev_info *rvt_alloc_device(size_t size, int nports); void rvt_dealloc_device(struct rvt_dev_info *rdi); -int rvt_register_device(struct rvt_dev_info *rvd); +int rvt_register_device(struct rvt_dev_info *rvd, u32 driver_id); void rvt_unregister_device(struct rvt_dev_info *rvd); int rvt_check_ah(struct ib_device *ibdev, struct rdma_ah_attr *ah_attr); int rvt_init_port(struct rvt_dev_info *rdi, struct rvt_ibport *port, diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index 0eed3d8752fa..89ab88c342b6 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -282,7 +282,6 @@ struct rvt_qp { u32 remote_qpn; u32 qkey; /* QKEY for this QP (for UD or RD) */ u32 s_size; /* send work queue size */ - u32 s_ahgpsn; /* set to the psn in the copy of the header */ u16 pmtu; /* decoded from path_mtu */ u8 log_pmtu; /* shift for pmtu */ @@ -344,7 +343,6 @@ struct rvt_qp { struct rvt_swqe *s_wqe; struct rvt_sge_state s_sge; /* current send request data */ struct rvt_mregion *s_rdma_mr; - u32 s_cur_size; /* size of send packet in bytes */ u32 s_len; /* total length of s_sge */ u32 s_rdma_read_len; /* total length of s_rdma_read_sge */ u32 s_last_psn; /* last response PSN processed */ @@ -358,8 +356,10 @@ struct rvt_qp { u32 s_acked; /* last un-ACK'ed entry */ u32 s_last; /* last completed entry */ u32 s_lsn; /* limit sequence number (credit) */ - u16 s_hdrwords; /* size of s_hdr in 32 bit words */ + u32 s_ahgpsn; /* set to the psn in the copy of the header */ + u16 s_cur_size; /* size of send packet in bytes */ u16 s_rdma_ack_cnt; + u8 s_hdrwords; /* size of s_hdr in 32 bit words */ s8 s_ahgidx; u8 s_state; /* opcode of last packet sent */ u8 s_ack_state; /* opcode of packet to ACK */ diff --git a/include/rdma/restrack.h b/include/rdma/restrack.h new file mode 100644 index 000000000000..f3b3e3576f6a --- /dev/null +++ b/include/rdma/restrack.h @@ -0,0 +1,177 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* + * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved. + */ + +#ifndef _RDMA_RESTRACK_H_ +#define _RDMA_RESTRACK_H_ + +#include <linux/typecheck.h> +#include <linux/rwsem.h> +#include <linux/sched.h> +#include <linux/kref.h> +#include <linux/completion.h> +#include <linux/sched/task.h> + +/** + * enum rdma_restrack_type - HW objects to track + */ +enum rdma_restrack_type { + /** + * @RDMA_RESTRACK_PD: Protection domain (PD) + */ + RDMA_RESTRACK_PD, + /** + * @RDMA_RESTRACK_CQ: Completion queue (CQ) + */ + RDMA_RESTRACK_CQ, + /** + * @RDMA_RESTRACK_QP: Queue pair (QP) + */ + RDMA_RESTRACK_QP, + /** + * @RDMA_RESTRACK_CM_ID: Connection Manager ID (CM_ID) + */ + RDMA_RESTRACK_CM_ID, + /** + * @RDMA_RESTRACK_MR: Memory Region (MR) + */ + RDMA_RESTRACK_MR, + /** + * @RDMA_RESTRACK_MAX: Last entry, used for array dclarations + */ + RDMA_RESTRACK_MAX +}; + +#define RDMA_RESTRACK_HASH_BITS 8 +/** + * struct rdma_restrack_root - main resource tracking management + * entity, per-device + */ +struct rdma_restrack_root { + /* + * @rwsem: Read/write lock to protect lists + */ + struct rw_semaphore rwsem; + /** + * @hash: global database for all resources per-device + */ + DECLARE_HASHTABLE(hash, RDMA_RESTRACK_HASH_BITS); +}; + +/** + * struct rdma_restrack_entry - metadata per-entry + */ +struct rdma_restrack_entry { + /** + * @valid: validity indicator + * + * The entries are filled during rdma_restrack_add, + * can be attempted to be free during rdma_restrack_del. + * + * As an example for that, see mlx5 QPs with type MLX5_IB_QPT_HW_GSI + */ + bool valid; + /* + * @kref: Protect destroy of the resource + */ + struct kref kref; + /* + * @comp: Signal that all consumers of resource are completed their work + */ + struct completion comp; + /** + * @task: owner of resource tracking entity + * + * There are two types of entities: created by user and created + * by kernel. + * + * This is relevant for the entities created by users. + * For the entities created by kernel, this pointer will be NULL. + */ + struct task_struct *task; + /** + * @kern_name: name of owner for the kernel created entities. + */ + const char *kern_name; + /** + * @node: hash table entry + */ + struct hlist_node node; + /** + * @type: various objects in restrack database + */ + enum rdma_restrack_type type; +}; + +/** + * rdma_restrack_init() - initialize resource tracking + * @res: resource tracking root + */ +void rdma_restrack_init(struct rdma_restrack_root *res); + +/** + * rdma_restrack_clean() - clean resource tracking + * @res: resource tracking root + */ +void rdma_restrack_clean(struct rdma_restrack_root *res); + +/** + * rdma_restrack_count() - the current usage of specific object + * @res: resource entry + * @type: actual type of object to operate + * @ns: PID namespace + */ +int rdma_restrack_count(struct rdma_restrack_root *res, + enum rdma_restrack_type type, + struct pid_namespace *ns); + +/** + * rdma_restrack_add() - add object to the reource tracking database + * @res: resource entry + */ +void rdma_restrack_add(struct rdma_restrack_entry *res); + +/** + * rdma_restrack_del() - delete object from the reource tracking database + * @res: resource entry + * @type: actual type of object to operate + */ +void rdma_restrack_del(struct rdma_restrack_entry *res); + +/** + * rdma_is_kernel_res() - check the owner of resource + * @res: resource entry + */ +static inline bool rdma_is_kernel_res(struct rdma_restrack_entry *res) +{ + return !res->task; +} + +/** + * rdma_restrack_get() - grab to protect resource from release + * @res: resource entry + */ +int __must_check rdma_restrack_get(struct rdma_restrack_entry *res); + +/** + * rdma_restrack_put() - release resource + * @res: resource entry + */ +int rdma_restrack_put(struct rdma_restrack_entry *res); + +/** + * rdma_restrack_set_task() - set the task for this resource + * @res: resource entry + * @task: task struct + */ +static inline void rdma_restrack_set_task(struct rdma_restrack_entry *res, + struct task_struct *task) +{ + if (res->task) + put_task_struct(res->task); + get_task_struct(task); + res->task = task; +} + +#endif /* _RDMA_RESTRACK_H_ */ diff --git a/include/rdma/uverbs_ioctl.h b/include/rdma/uverbs_ioctl.h index 6da44079aa58..4a4201d997a7 100644 --- a/include/rdma/uverbs_ioctl.h +++ b/include/rdma/uverbs_ioctl.h @@ -37,6 +37,7 @@ #include <linux/uaccess.h> #include <rdma/rdma_user_ioctl.h> #include <rdma/ib_user_ioctl_verbs.h> +#include <rdma/ib_user_ioctl_cmds.h> /* * ======================================= @@ -50,6 +51,7 @@ enum uverbs_attr_type { UVERBS_ATTR_TYPE_PTR_OUT, UVERBS_ATTR_TYPE_IDR, UVERBS_ATTR_TYPE_FD, + UVERBS_ATTR_TYPE_ENUM_IN, }; enum uverbs_obj_access { @@ -61,15 +63,32 @@ enum uverbs_obj_access { enum { UVERBS_ATTR_SPEC_F_MANDATORY = 1U << 0, - /* Support extending attributes by length */ - UVERBS_ATTR_SPEC_F_MIN_SZ = 1U << 1, + /* Support extending attributes by length, validate all unknown size == zero */ + UVERBS_ATTR_SPEC_F_MIN_SZ_OR_ZERO = 1U << 1, }; +/* Specification of a single attribute inside the ioctl message */ struct uverbs_attr_spec { - enum uverbs_attr_type type; union { - u16 len; + /* Header shared by all following union members - to reduce space. */ struct { + enum uverbs_attr_type type; + /* Combination of bits from enum UVERBS_ATTR_SPEC_F_XXXX */ + u8 flags; + }; + struct { + enum uverbs_attr_type type; + /* Combination of bits from enum UVERBS_ATTR_SPEC_F_XXXX */ + u8 flags; + /* Current known size to kernel */ + u16 len; + /* User isn't allowed to provide something < min_len */ + u16 min_len; + } ptr; + struct { + enum uverbs_attr_type type; + /* Combination of bits from enum UVERBS_ATTR_SPEC_F_XXXX */ + u8 flags; /* * higher bits mean the namespace and lower bits mean * the type id within the namespace. @@ -77,9 +96,19 @@ struct uverbs_attr_spec { u16 obj_type; u8 access; } obj; + struct { + enum uverbs_attr_type type; + /* Combination of bits from enum UVERBS_ATTR_SPEC_F_XXXX */ + u8 flags; + u8 num_elems; + /* + * The enum attribute can select one of the attributes + * contained in the ids array. Currently only PTR_IN + * attributes are supported in the ids array. + */ + const struct uverbs_attr_spec *ids; + } enum_def; }; - /* Combination of bits from enum UVERBS_ATTR_SPEC_F_XXXX */ - u8 flags; }; struct uverbs_attr_spec_hash { @@ -164,30 +193,45 @@ struct uverbs_object_tree_def { }; #define UA_FLAGS(_flags) .flags = _flags -#define __UVERBS_ATTR0(_id, _len, _type, ...) \ +#define __UVERBS_ATTR0(_id, _type, _fld, _attr, ...) \ + ((const struct uverbs_attr_def) \ + {.id = _id, .attr = {{._fld = {.type = _type, _attr, .flags = 0, } }, } }) +#define __UVERBS_ATTR1(_id, _type, _fld, _attr, _extra1, ...) \ ((const struct uverbs_attr_def) \ - {.id = _id, .attr = {.type = _type, {.len = _len}, .flags = 0, } }) -#define __UVERBS_ATTR1(_id, _len, _type, _flags) \ + {.id = _id, .attr = {{._fld = {.type = _type, _attr, _extra1 } },} }) +#define __UVERBS_ATTR2(_id, _type, _fld, _attr, _extra1, _extra2) \ ((const struct uverbs_attr_def) \ - {.id = _id, .attr = {.type = _type, {.len = _len}, _flags, } }) -#define __UVERBS_ATTR(_id, _len, _type, _flags, _n, ...) \ - __UVERBS_ATTR##_n(_id, _len, _type, _flags) + {.id = _id, .attr = {{._fld = {.type = _type, _attr, _extra1, _extra2 } },} }) +#define __UVERBS_ATTR(_id, _type, _fld, _attr, _extra1, _extra2, _n, ...) \ + __UVERBS_ATTR##_n(_id, _type, _fld, _attr, _extra1, _extra2) + +#define UVERBS_ATTR_TYPE(_type) \ + .min_len = sizeof(_type), .len = sizeof(_type) +#define UVERBS_ATTR_STRUCT(_type, _last) \ + .min_len = ((uintptr_t)(&((_type *)0)->_last + 1)), .len = sizeof(_type) +#define UVERBS_ATTR_SIZE(_min_len, _len) \ + .min_len = _min_len, .len = _len + /* * In new compiler, UVERBS_ATTR could be simplified by declaring it as * [_id] = {.type = _type, .len = _len, ##__VA_ARGS__} * But since we support older compilers too, we need the more complex code. */ -#define UVERBS_ATTR(_id, _len, _type, ...) \ - __UVERBS_ATTR(_id, _len, _type, ##__VA_ARGS__, 1, 0) +#define UVERBS_ATTR(_id, _type, _fld, _attr, ...) \ + __UVERBS_ATTR(_id, _type, _fld, _attr, ##__VA_ARGS__, 2, 1, 0) #define UVERBS_ATTR_PTR_IN_SZ(_id, _len, ...) \ - UVERBS_ATTR(_id, _len, UVERBS_ATTR_TYPE_PTR_IN, ##__VA_ARGS__) + UVERBS_ATTR(_id, UVERBS_ATTR_TYPE_PTR_IN, ptr, _len, ##__VA_ARGS__) /* If sizeof(_type) <= sizeof(u64), this will be inlined rather than a pointer */ #define UVERBS_ATTR_PTR_IN(_id, _type, ...) \ - UVERBS_ATTR_PTR_IN_SZ(_id, sizeof(_type), ##__VA_ARGS__) + UVERBS_ATTR_PTR_IN_SZ(_id, _type, ##__VA_ARGS__) #define UVERBS_ATTR_PTR_OUT_SZ(_id, _len, ...) \ - UVERBS_ATTR(_id, _len, UVERBS_ATTR_TYPE_PTR_OUT, ##__VA_ARGS__) + UVERBS_ATTR(_id, UVERBS_ATTR_TYPE_PTR_OUT, ptr, _len, ##__VA_ARGS__) #define UVERBS_ATTR_PTR_OUT(_id, _type, ...) \ - UVERBS_ATTR_PTR_OUT_SZ(_id, sizeof(_type), ##__VA_ARGS__) + UVERBS_ATTR_PTR_OUT_SZ(_id, _type, ##__VA_ARGS__) +#define UVERBS_ATTR_ENUM_IN(_id, _enum_arr, ...) \ + UVERBS_ATTR(_id, UVERBS_ATTR_TYPE_ENUM_IN, enum_def, \ + .ids = (_enum_arr), \ + .num_elems = ARRAY_SIZE(_enum_arr), ##__VA_ARGS__) /* * In new compiler, UVERBS_ATTR_IDR (and FD) could be simplified by declaring @@ -202,15 +246,13 @@ struct uverbs_object_tree_def { #define ___UVERBS_ATTR_OBJ0(_id, _obj_class, _obj_type, _access, ...)\ ((const struct uverbs_attr_def) \ {.id = _id, \ - .attr = {.type = _obj_class, \ - {.obj = {.obj_type = _obj_type, .access = _access } },\ - .flags = 0} }) + .attr = { {.obj = {.type = _obj_class, .obj_type = _obj_type, \ + .access = _access, .flags = 0 } }, } }) #define ___UVERBS_ATTR_OBJ1(_id, _obj_class, _obj_type, _access, _flags)\ ((const struct uverbs_attr_def) \ {.id = _id, \ - .attr = {.type = _obj_class, \ - {.obj = {.obj_type = _obj_type, .access = _access} }, \ - _flags} }) + .attr = { {.obj = {.type = _obj_class, .obj_type = _obj_type, \ + .access = _access, _flags} }, } }) #define ___UVERBS_ATTR_OBJ(_id, _obj_class, _obj_type, _access, _flags, \ _n, ...) \ ___UVERBS_ATTR_OBJ##_n(_id, _obj_class, _obj_type, _access, _flags) @@ -229,6 +271,11 @@ struct uverbs_object_tree_def { #define DECLARE_UVERBS_ATTR_SPEC(_name, ...) \ const struct uverbs_attr_def _name = __VA_ARGS__ +#define DECLARE_UVERBS_ENUM(_name, ...) \ + const struct uverbs_enum_spec _name = { \ + .len = ARRAY_SIZE(((struct uverbs_attr_spec[]){__VA_ARGS__})),\ + .ids = {__VA_ARGS__}, \ + } #define _UVERBS_METHOD_ATTRS_SZ(...) \ (sizeof((const struct uverbs_attr_def * const []){__VA_ARGS__}) /\ sizeof(const struct uverbs_attr_def *)) @@ -276,13 +323,11 @@ struct uverbs_object_tree_def { */ struct uverbs_ptr_attr { - union { - u64 data; - void __user *ptr; - }; + u64 data; u16 len; /* Combination of bits from enum UVERBS_ATTR_F_XXXX */ u16 flags; + u8 enum_id; }; struct uverbs_obj_attr { @@ -339,6 +384,8 @@ static inline bool uverbs_attr_is_valid(const struct uverbs_attr_bundle *attrs_b idx & ~UVERBS_ID_NS_MASK); } +#define IS_UVERBS_COPY_ERR(_ret) ((_ret) && (_ret) != -ENOENT) + static inline const struct uverbs_attr *uverbs_attr_get(const struct uverbs_attr_bundle *attrs_bundle, u16 idx) { @@ -350,39 +397,112 @@ static inline const struct uverbs_attr *uverbs_attr_get(const struct uverbs_attr return &attrs_bundle->hash[idx_bucket].attrs[idx & ~UVERBS_ID_NS_MASK]; } +static inline int uverbs_attr_get_enum_id(const struct uverbs_attr_bundle *attrs_bundle, + u16 idx) +{ + const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx); + + if (IS_ERR(attr)) + return PTR_ERR(attr); + + return attr->ptr_attr.enum_id; +} + +static inline void *uverbs_attr_get_obj(const struct uverbs_attr_bundle *attrs_bundle, + u16 idx) +{ + struct ib_uobject *uobj = + uverbs_attr_get(attrs_bundle, idx)->obj_attr.uobject; + + if (IS_ERR(uobj)) + return uobj; + + return uobj->object; +} + static inline int uverbs_copy_to(const struct uverbs_attr_bundle *attrs_bundle, - size_t idx, const void *from) + size_t idx, const void *from, size_t size) { const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx); u16 flags; + size_t min_size; if (IS_ERR(attr)) return PTR_ERR(attr); + min_size = min_t(size_t, attr->ptr_attr.len, size); + if (copy_to_user(u64_to_user_ptr(attr->ptr_attr.data), from, min_size)) + return -EFAULT; + flags = attr->ptr_attr.flags | UVERBS_ATTR_F_VALID_OUTPUT; - return (!copy_to_user(attr->ptr_attr.ptr, from, attr->ptr_attr.len) && - !put_user(flags, &attr->uattr->flags)) ? 0 : -EFAULT; + if (put_user(flags, &attr->uattr->flags)) + return -EFAULT; + + return 0; +} + +static inline bool uverbs_attr_ptr_is_inline(const struct uverbs_attr *attr) +{ + return attr->ptr_attr.len <= sizeof(attr->ptr_attr.data); } -static inline int _uverbs_copy_from(void *to, size_t to_size, +static inline int _uverbs_copy_from(void *to, const struct uverbs_attr_bundle *attrs_bundle, - size_t idx) + size_t idx, + size_t size) { const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx); if (IS_ERR(attr)) return PTR_ERR(attr); - if (to_size <= sizeof(((struct ib_uverbs_attr *)0)->data)) + /* + * Validation ensures attr->ptr_attr.len >= size. If the caller is + * using UVERBS_ATTR_SPEC_F_MIN_SZ_OR_ZERO then it must call + * uverbs_copy_from_or_zero. + */ + if (unlikely(size < attr->ptr_attr.len)) + return -EINVAL; + + if (uverbs_attr_ptr_is_inline(attr)) memcpy(to, &attr->ptr_attr.data, attr->ptr_attr.len); - else if (copy_from_user(to, attr->ptr_attr.ptr, attr->ptr_attr.len)) + else if (copy_from_user(to, u64_to_user_ptr(attr->ptr_attr.data), + attr->ptr_attr.len)) + return -EFAULT; + + return 0; +} + +static inline int _uverbs_copy_from_or_zero(void *to, + const struct uverbs_attr_bundle *attrs_bundle, + size_t idx, + size_t size) +{ + const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx); + size_t min_size; + + if (IS_ERR(attr)) + return PTR_ERR(attr); + + min_size = min_t(size_t, size, attr->ptr_attr.len); + + if (uverbs_attr_ptr_is_inline(attr)) + memcpy(to, &attr->ptr_attr.data, min_size); + else if (copy_from_user(to, u64_to_user_ptr(attr->ptr_attr.data), + min_size)) return -EFAULT; + if (size > min_size) + memset(to + min_size, 0, size - min_size); + return 0; } #define uverbs_copy_from(to, attrs_bundle, idx) \ - _uverbs_copy_from(to, sizeof(*(to)), attrs_bundle, idx) + _uverbs_copy_from(to, attrs_bundle, idx, sizeof(*to)) + +#define uverbs_copy_from_or_zero(to, attrs_bundle, idx) \ + _uverbs_copy_from_or_zero(to, attrs_bundle, idx, sizeof(*to)) /* ================================================= * Definitions -> Specs infrastructure diff --git a/include/rdma/uverbs_named_ioctl.h b/include/rdma/uverbs_named_ioctl.h new file mode 100644 index 000000000000..c5bb4ebdb0b0 --- /dev/null +++ b/include/rdma/uverbs_named_ioctl.h @@ -0,0 +1,90 @@ +/* + * Copyright (c) 2018, Mellanox Technologies inc. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef _UVERBS_NAMED_IOCTL_ +#define _UVERBS_NAMED_IOCTL_ + +#include <rdma/uverbs_ioctl.h> + +#ifndef UVERBS_MODULE_NAME +#error "Please #define UVERBS_MODULE_NAME before including rdma/uverbs_named_ioctl.h" +#endif + +#define _UVERBS_PASTE(x, y) x ## y +#define _UVERBS_NAME(x, y) _UVERBS_PASTE(x, y) +#define UVERBS_METHOD(id) _UVERBS_NAME(UVERBS_MODULE_NAME, _method_##id) +#define UVERBS_HANDLER(id) _UVERBS_NAME(UVERBS_MODULE_NAME, _handler_##id) + +#define DECLARE_UVERBS_NAMED_METHOD(id, ...) \ + DECLARE_UVERBS_METHOD(UVERBS_METHOD(id), id, UVERBS_HANDLER(id), ##__VA_ARGS__) + +#define DECLARE_UVERBS_NAMED_METHOD_WITH_HANDLER(id, handler, ...) \ + DECLARE_UVERBS_METHOD(UVERBS_METHOD(id), id, handler, ##__VA_ARGS__) + +#define DECLARE_UVERBS_NAMED_METHOD_NO_OVERRIDE(id, handler, ...) \ + DECLARE_UVERBS_METHOD(UVERBS_METHOD(id), id, NULL, ##__VA_ARGS__) + +#define DECLARE_UVERBS_NAMED_OBJECT(id, ...) \ + DECLARE_UVERBS_OBJECT(UVERBS_OBJECT(id), id, ##__VA_ARGS__) + +#define _UVERBS_COMP_NAME(x, y, z) _UVERBS_NAME(_UVERBS_NAME(x, y), z) + +#define UVERBS_NO_OVERRIDE NULL + +/* This declares a parsing tree with one object and one method. This is usually + * used for merging driver attributes to the common attributes. The driver has + * a chance to override the handler and type attrs of the original object. + * The __VA_ARGS__ just contains a list of attributes. + */ +#define ADD_UVERBS_ATTRIBUTES(_name, _object, _method, _type_attrs, _handler, ...) \ +static DECLARE_UVERBS_METHOD(_UVERBS_COMP_NAME(UVERBS_MODULE_NAME, \ + _method_, _name), \ + _method, _handler, ##__VA_ARGS__); \ + \ +static DECLARE_UVERBS_OBJECT(_UVERBS_COMP_NAME(UVERBS_MODULE_NAME, \ + _object_, _name), \ + _object, _type_attrs, \ + &_UVERBS_COMP_NAME(UVERBS_MODULE_NAME, \ + _method_, _name)); \ + \ +static DECLARE_UVERBS_OBJECT_TREE(_name, \ + &_UVERBS_COMP_NAME(UVERBS_MODULE_NAME, \ + _object_, _name)) + +/* A very common use case is that the driver doesn't override the handler and + * type_attrs. Therefore, we provide a simplified macro for this common case. + */ +#define ADD_UVERBS_ATTRIBUTES_SIMPLE(_name, _object, _method, ...) \ + ADD_UVERBS_ATTRIBUTES(_name, _object, _method, UVERBS_NO_OVERRIDE, \ + UVERBS_NO_OVERRIDE, ##__VA_ARGS__) + +#endif diff --git a/include/rdma/uverbs_std_types.h b/include/rdma/uverbs_std_types.h index 5f8e20bbd67c..9d56cdb84655 100644 --- a/include/rdma/uverbs_std_types.h +++ b/include/rdma/uverbs_std_types.h @@ -37,26 +37,10 @@ #include <rdma/uverbs_ioctl.h> #include <rdma/ib_user_ioctl_verbs.h> +#define UVERBS_OBJECT(id) uverbs_object_##id + #if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS) -extern const struct uverbs_object_def uverbs_object_comp_channel; -extern const struct uverbs_object_def uverbs_object_cq; -extern const struct uverbs_object_def uverbs_object_qp; -extern const struct uverbs_object_def uverbs_object_rwq_ind_table; -extern const struct uverbs_object_def uverbs_object_wq; -extern const struct uverbs_object_def uverbs_object_srq; -extern const struct uverbs_object_def uverbs_object_ah; -extern const struct uverbs_object_def uverbs_object_flow; -extern const struct uverbs_object_def uverbs_object_mr; -extern const struct uverbs_object_def uverbs_object_mw; -extern const struct uverbs_object_def uverbs_object_pd; -extern const struct uverbs_object_def uverbs_object_xrcd; -extern const struct uverbs_object_def uverbs_object_device; - -extern const struct uverbs_object_tree_def uverbs_default_objects; -static inline const struct uverbs_object_tree_def *uverbs_default_get_objects(void) -{ - return &uverbs_default_objects; -} +const struct uverbs_object_tree_def *uverbs_default_get_objects(void); #else static inline const struct uverbs_object_tree_def *uverbs_default_get_objects(void) { @@ -72,22 +56,22 @@ static inline struct ib_uobject *__uobj_get(const struct uverbs_obj_type *type, return rdma_lookup_get_uobject(type, ucontext, id, write); } -#define uobj_get_type(_object) uverbs_object_##_object.type_attrs +#define uobj_get_type(_object) UVERBS_OBJECT(_object).type_attrs #define uobj_get_read(_type, _id, _ucontext) \ - __uobj_get(_type, false, _ucontext, _id) + __uobj_get(uobj_get_type(_type), false, _ucontext, _id) -#define uobj_get_obj_read(_object, _id, _ucontext) \ +#define uobj_get_obj_read(_object, _type, _id, _ucontext) \ ({ \ struct ib_uobject *__uobj = \ - __uobj_get(uverbs_object_##_object.type_attrs, \ + __uobj_get(uobj_get_type(_type), \ false, _ucontext, _id); \ \ (struct ib_##_object *)(IS_ERR(__uobj) ? NULL : __uobj->object);\ }) #define uobj_get_write(_type, _id, _ucontext) \ - __uobj_get(_type, true, _ucontext, _id) + __uobj_get(uobj_get_type(_type), true, _ucontext, _id) static inline void uobj_put_read(struct ib_uobject *uobj) { @@ -124,7 +108,7 @@ static inline struct ib_uobject *__uobj_alloc(const struct uverbs_obj_type *type } #define uobj_alloc(_type, ucontext) \ - __uobj_alloc(_type, ucontext) + __uobj_alloc(uobj_get_type(_type), ucontext) #endif |