diff options
Diffstat (limited to 'include/rdma')
| -rw-r--r-- | include/rdma/ib.h | 89 | ||||
| -rw-r--r-- | include/rdma/ib_addr.h | 312 | ||||
| -rw-r--r-- | include/rdma/ib_cache.h | 31 | ||||
| -rw-r--r-- | include/rdma/ib_cm.h | 69 | ||||
| -rw-r--r-- | include/rdma/ib_fmr_pool.h | 8 | ||||
| -rw-r--r-- | include/rdma/ib_mad.h | 121 | ||||
| -rw-r--r-- | include/rdma/ib_marshall.h | 53 | ||||
| -rw-r--r-- | include/rdma/ib_pack.h | 41 | ||||
| -rw-r--r-- | include/rdma/ib_pma.h | 156 | ||||
| -rw-r--r-- | include/rdma/ib_sa.h | 281 | ||||
| -rw-r--r-- | include/rdma/ib_smi.h | 74 | ||||
| -rw-r--r-- | include/rdma/ib_umem.h | 78 | ||||
| -rw-r--r-- | include/rdma/ib_user_cm.h | 399 | ||||
| -rw-r--r-- | include/rdma/ib_user_mad.h | 137 | ||||
| -rw-r--r-- | include/rdma/ib_user_verbs.h | 574 | ||||
| -rw-r--r-- | include/rdma/ib_verbs.h | 1332 | ||||
| -rw-r--r-- | include/rdma/iw_cm.h | 251 | ||||
| -rw-r--r-- | include/rdma/iw_portmap.h | 199 | ||||
| -rw-r--r-- | include/rdma/rdma_cm.h | 383 | ||||
| -rw-r--r-- | include/rdma/rdma_cm_ib.h | 54 | ||||
| -rw-r--r-- | include/rdma/rdma_netlink.h | 80 |
21 files changed, 3315 insertions, 1407 deletions
diff --git a/include/rdma/ib.h b/include/rdma/ib.h new file mode 100644 index 00000000000..cf8f9e700e4 --- /dev/null +++ b/include/rdma/ib.h @@ -0,0 +1,89 @@ +/* + * Copyright (c) 2010 Intel Corporation. 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. + */ + +#if !defined(_RDMA_IB_H) +#define _RDMA_IB_H + +#include <linux/types.h> + +struct ib_addr { + union { + __u8 uib_addr8[16]; + __be16 uib_addr16[8]; + __be32 uib_addr32[4]; + __be64 uib_addr64[2]; + } ib_u; +#define sib_addr8 ib_u.uib_addr8 +#define sib_addr16 ib_u.uib_addr16 +#define sib_addr32 ib_u.uib_addr32 +#define sib_addr64 ib_u.uib_addr64 +#define sib_raw ib_u.uib_addr8 +#define sib_subnet_prefix ib_u.uib_addr64[0] +#define sib_interface_id ib_u.uib_addr64[1] +}; + +static inline int ib_addr_any(const struct ib_addr *a) +{ + return ((a->sib_addr64[0] | a->sib_addr64[1]) == 0); +} + +static inline int ib_addr_loopback(const struct ib_addr *a) +{ + return ((a->sib_addr32[0] | a->sib_addr32[1] | + a->sib_addr32[2] | (a->sib_addr32[3] ^ htonl(1))) == 0); +} + +static inline void ib_addr_set(struct ib_addr *addr, + __be32 w1, __be32 w2, __be32 w3, __be32 w4) +{ + addr->sib_addr32[0] = w1; + addr->sib_addr32[1] = w2; + addr->sib_addr32[2] = w3; + addr->sib_addr32[3] = w4; +} + +static inline int ib_addr_cmp(const struct ib_addr *a1, const struct ib_addr *a2) +{ + return memcmp(a1, a2, sizeof(struct ib_addr)); +} + +struct sockaddr_ib { + unsigned short int sib_family; /* AF_IB */ + __be16 sib_pkey; + __be32 sib_flowinfo; + struct ib_addr sib_addr; + __be64 sib_sid; + __be64 sib_sid_mask; + __u64 sib_scope_id; +}; + +#endif /* _RDMA_IB_H */ diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h new file mode 100644 index 00000000000..ce55906b54a --- /dev/null +++ b/include/rdma/ib_addr.h @@ -0,0 +1,312 @@ +/* + * Copyright (c) 2005 Voltaire Inc. All rights reserved. + * Copyright (c) 2005 Intel Corporation. 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. + */ + +#if !defined(IB_ADDR_H) +#define IB_ADDR_H + +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/if_arp.h> +#include <linux/netdevice.h> +#include <linux/inetdevice.h> +#include <linux/socket.h> +#include <linux/if_vlan.h> +#include <net/ipv6.h> +#include <net/if_inet6.h> +#include <net/ip.h> +#include <rdma/ib_verbs.h> +#include <rdma/ib_pack.h> +#include <net/ipv6.h> + +struct rdma_addr_client { + atomic_t refcount; + struct completion comp; +}; + +/** + * rdma_addr_register_client - Register an address client. + */ +void rdma_addr_register_client(struct rdma_addr_client *client); + +/** + * rdma_addr_unregister_client - Deregister an address client. + * @client: Client object to deregister. + */ +void rdma_addr_unregister_client(struct rdma_addr_client *client); + +struct rdma_dev_addr { + unsigned char src_dev_addr[MAX_ADDR_LEN]; + unsigned char dst_dev_addr[MAX_ADDR_LEN]; + unsigned char broadcast[MAX_ADDR_LEN]; + unsigned short dev_type; + int bound_dev_if; + enum rdma_transport_type transport; +}; + +/** + * rdma_translate_ip - Translate a local IP address to an RDMA hardware + * address. + */ +int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr, + u16 *vlan_id); + +/** + * rdma_resolve_ip - Resolve source and destination IP addresses to + * RDMA hardware addresses. + * @client: Address client associated with request. + * @src_addr: An optional source address to use in the resolution. If a + * source address is not provided, a usable address will be returned via + * the callback. + * @dst_addr: The destination address to resolve. + * @addr: A reference to a data location that will receive the resolved + * addresses. The data location must remain valid until the callback has + * been invoked. + * @timeout_ms: Amount of time to wait for the address resolution to complete. + * @callback: Call invoked once address resolution has completed, timed out, + * or been canceled. A status of 0 indicates success. + * @context: User-specified context associated with the call. + */ +int rdma_resolve_ip(struct rdma_addr_client *client, + struct sockaddr *src_addr, struct sockaddr *dst_addr, + struct rdma_dev_addr *addr, int timeout_ms, + void (*callback)(int status, struct sockaddr *src_addr, + struct rdma_dev_addr *addr, void *context), + void *context); + +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); + +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_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *smac, + u16 *vlan_id); + +static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr) +{ + return ((u16)dev_addr->broadcast[8] << 8) | (u16)dev_addr->broadcast[9]; +} + +static inline void ib_addr_set_pkey(struct rdma_dev_addr *dev_addr, u16 pkey) +{ + dev_addr->broadcast[8] = pkey >> 8; + dev_addr->broadcast[9] = (unsigned char) pkey; +} + +static inline void ib_addr_get_mgid(struct rdma_dev_addr *dev_addr, + union ib_gid *gid) +{ + memcpy(gid, dev_addr->broadcast + 4, sizeof *gid); +} + +static inline int rdma_addr_gid_offset(struct rdma_dev_addr *dev_addr) +{ + return dev_addr->dev_type == ARPHRD_INFINIBAND ? 4 : 0; +} + +static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev) +{ + return dev->priv_flags & IFF_802_1Q_VLAN ? + vlan_dev_vlan_id(dev) : 0xffff; +} + +static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid) +{ + switch (addr->sa_family) { + case AF_INET: + ipv6_addr_set_v4mapped(((struct sockaddr_in *) + addr)->sin_addr.s_addr, + (struct in6_addr *)gid); + break; + case AF_INET6: + memcpy(gid->raw, &((struct sockaddr_in6 *)addr)->sin6_addr, 16); + break; + default: + return -EINVAL; + } + return 0; +} + +/* Important - sockaddr should be a union of sockaddr_in and sockaddr_in6 */ +static inline int rdma_gid2ip(struct sockaddr *out, union ib_gid *gid) +{ + if (ipv6_addr_v4mapped((struct in6_addr *)gid)) { + struct sockaddr_in *out_in = (struct sockaddr_in *)out; + memset(out_in, 0, sizeof(*out_in)); + out_in->sin_family = AF_INET; + memcpy(&out_in->sin_addr.s_addr, gid->raw + 12, 4); + } else { + struct sockaddr_in6 *out_in = (struct sockaddr_in6 *)out; + memset(out_in, 0, sizeof(*out_in)); + out_in->sin6_family = AF_INET6; + memcpy(&out_in->sin6_addr.s6_addr, gid->raw, 16); + } + return 0; +} + +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 = (struct in_device *)dev->ip_ptr; + if (ip4 && ip4->ifa_list && ip4->ifa_list->ifa_address) + ipv6_addr_set_v4mapped(ip4->ifa_list->ifa_address, + (struct in6_addr *)gid); + dev_put(dev); + } +} + +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); +} + +static inline void rdma_addr_set_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) +{ + memcpy(dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid); +} + +static inline void rdma_addr_get_dgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) +{ + memcpy(gid, dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof *gid); +} + +static inline void rdma_addr_set_dgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) +{ + memcpy(dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid); +} + +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 + */ + mtu = mtu - IB_GRH_BYTES - IB_BTH_BYTES - 28; + + if (mtu >= ib_mtu_enum_to_int(IB_MTU_4096)) + return IB_MTU_4096; + else if (mtu >= ib_mtu_enum_to_int(IB_MTU_2048)) + return IB_MTU_2048; + else if (mtu >= ib_mtu_enum_to_int(IB_MTU_1024)) + return IB_MTU_1024; + else if (mtu >= ib_mtu_enum_to_int(IB_MTU_512)) + return IB_MTU_512; + else if (mtu >= ib_mtu_enum_to_int(IB_MTU_256)) + return IB_MTU_256; + else + return 0; +} + +static inline int iboe_get_rate(struct net_device *dev) +{ + struct ethtool_cmd cmd; + u32 speed; + int err; + + rtnl_lock(); + err = __ethtool_get_settings(dev, &cmd); + rtnl_unlock(); + if (err) + return IB_RATE_PORT_CURRENT; + + speed = ethtool_cmd_speed(&cmd); + if (speed >= 40000) + return IB_RATE_40_GBPS; + else if (speed >= 30000) + return IB_RATE_30_GBPS; + else if (speed >= 20000) + return IB_RATE_20_GBPS; + else if (speed >= 10000) + return IB_RATE_10_GBPS; + else + return IB_RATE_PORT_CURRENT; +} + +static inline int rdma_link_local_addr(struct in6_addr *addr) +{ + if (addr->s6_addr32[0] == htonl(0xfe800000) && + addr->s6_addr32[1] == 0) + return 1; + + return 0; +} + +static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac) +{ + memcpy(mac, &addr->s6_addr[8], 3); + memcpy(mac + 3, &addr->s6_addr[13], 3); + mac[0] ^= 2; +} + +static inline int rdma_is_multicast_addr(struct in6_addr *addr) +{ + return addr->s6_addr[0] == 0xff; +} + +static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac) +{ + int i; + + mac[0] = 0x33; + mac[1] = 0x33; + for (i = 2; i < 6; ++i) + mac[i] = addr->s6_addr[i + 10]; +} + +static inline u16 rdma_get_vlan_id(union ib_gid *dgid) +{ + u16 vid; + + vid = dgid->raw[11] << 8 | dgid->raw[12]; + return vid < 0x1000 ? vid : 0xffff; +} + +static inline struct net_device *rdma_vlan_dev_real_dev(const struct net_device *dev) +{ + return dev->priv_flags & IFF_802_1Q_VLAN ? + vlan_dev_real_dev(dev) : NULL; +} + +#endif /* IB_ADDR_H */ diff --git a/include/rdma/ib_cache.h b/include/rdma/ib_cache.h index 5bf9834f7dc..ad9a3c28094 100644 --- a/include/rdma/ib_cache.h +++ b/include/rdma/ib_cache.h @@ -30,8 +30,6 @@ * 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. - * - * $Id: ib_cache.h 1349 2004-12-16 21:09:43Z roland $ */ #ifndef _IB_CACHE_H @@ -102,4 +100,33 @@ int ib_find_cached_pkey(struct ib_device *device, u16 pkey, u16 *index); +/** + * ib_find_exact_cached_pkey - Returns the PKey table index where a specified + * PKey value occurs. Comparison uses the FULL 16 bits (incl membership bit) + * @device: The device to query. + * @port_num: The port number of the device to search for the PKey. + * @pkey: The PKey value to search for. + * @index: The index into the cached PKey table where the PKey was found. + * + * ib_find_exact_cached_pkey() searches the specified PKey table in + * the local software cache. + */ +int ib_find_exact_cached_pkey(struct ib_device *device, + u8 port_num, + u16 pkey, + u16 *index); + +/** + * ib_get_cached_lmc - Returns a cached lmc table entry + * @device: The device to query. + * @port_num: The port number of the device to query. + * @lmc: The lmc value for the specified port for that device. + * + * ib_get_cached_lmc() fetches the specified lmc table entry stored in + * the local software cache. + */ +int ib_get_cached_lmc(struct ib_device *device, + u8 port_num, + u8 *lmc); + #endif /* _IB_CACHE_H */ diff --git a/include/rdma/ib_cm.h b/include/rdma/ib_cm.h index 0a9fcd59eb4..0e3ff30647d 100644 --- a/include/rdma/ib_cm.h +++ b/include/rdma/ib_cm.h @@ -31,8 +31,6 @@ * 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. - * - * $Id: ib_cm.h 2730 2005-06-28 16:43:03Z sean.hefty $ */ #if !defined(IB_CM_H) #define IB_CM_H @@ -40,6 +38,9 @@ #include <rdma/ib_mad.h> #include <rdma/ib_sa.h> +/* ib_cm and ib_user_cm modules share /sys/class/infiniband_cm */ +extern struct class cm_class; + enum ib_cm_state { IB_CM_IDLE, IB_CM_LISTEN, @@ -60,6 +61,7 @@ enum ib_cm_state { }; enum ib_cm_lap_state { + IB_CM_LAP_UNINIT, IB_CM_LAP_IDLE, IB_CM_LAP_SENT, IB_CM_LAP_RCVD, @@ -102,7 +104,8 @@ enum ib_cm_data_size { IB_CM_APR_INFO_LENGTH = 72, IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE = 216, IB_CM_SIDR_REP_PRIVATE_DATA_SIZE = 136, - IB_CM_SIDR_REP_INFO_LENGTH = 72 + IB_CM_SIDR_REP_INFO_LENGTH = 72, + IB_CM_COMPARE_SIZE = 64 }; struct ib_cm_id; @@ -238,7 +241,6 @@ struct ib_cm_sidr_rep_event_param { u32 qpn; void *info; u8 info_len; - }; struct ib_cm_event { @@ -260,6 +262,18 @@ struct ib_cm_event { void *private_data; }; +#define CM_REQ_ATTR_ID cpu_to_be16(0x0010) +#define CM_MRA_ATTR_ID cpu_to_be16(0x0011) +#define CM_REJ_ATTR_ID cpu_to_be16(0x0012) +#define CM_REP_ATTR_ID cpu_to_be16(0x0013) +#define CM_RTU_ATTR_ID cpu_to_be16(0x0014) +#define CM_DREQ_ATTR_ID cpu_to_be16(0x0015) +#define CM_DREP_ATTR_ID cpu_to_be16(0x0016) +#define CM_SIDR_REQ_ATTR_ID cpu_to_be16(0x0017) +#define CM_SIDR_REP_ATTR_ID cpu_to_be16(0x0018) +#define CM_LAP_ATTR_ID cpu_to_be16(0x0019) +#define CM_APR_ATTR_ID cpu_to_be16(0x001A) + /** * ib_cm_handler - User-defined callback to process communication events. * @cm_id: Communication identifier associated with the reported event. @@ -315,8 +329,17 @@ struct ib_cm_id *ib_create_cm_id(struct ib_device *device, */ void ib_destroy_cm_id(struct ib_cm_id *cm_id); -#define IB_SERVICE_ID_AGN_MASK __constant_cpu_to_be64(0xFF00000000000000ULL) -#define IB_CM_ASSIGN_SERVICE_ID __constant_cpu_to_be64(0x0200000000000000ULL) +#define IB_SERVICE_ID_AGN_MASK cpu_to_be64(0xFF00000000000000ULL) +#define IB_CM_ASSIGN_SERVICE_ID cpu_to_be64(0x0200000000000000ULL) +#define IB_CMA_SERVICE_ID cpu_to_be64(0x0000000001000000ULL) +#define IB_CMA_SERVICE_ID_MASK cpu_to_be64(0xFFFFFFFFFF000000ULL) +#define IB_SDP_SERVICE_ID cpu_to_be64(0x0000000000010000ULL) +#define IB_SDP_SERVICE_ID_MASK cpu_to_be64(0xFFFFFFFFFFFF0000ULL) + +struct ib_cm_compare_data { + u8 data[IB_CM_COMPARE_SIZE]; + u8 mask[IB_CM_COMPARE_SIZE]; +}; /** * ib_cm_listen - Initiates listening on the specified service ID for @@ -330,10 +353,12 @@ void ib_destroy_cm_id(struct ib_cm_id *cm_id); * range of service IDs. If set to 0, the service ID is matched * exactly. This parameter is ignored if %service_id is set to * IB_CM_ASSIGN_SERVICE_ID. + * @compare_data: This parameter is optional. It specifies data that must + * appear in the private data of a connection request for the specified + * listen request. */ -int ib_cm_listen(struct ib_cm_id *cm_id, - __be64 service_id, - __be64 service_mask); +int ib_cm_listen(struct ib_cm_id *cm_id, __be64 service_id, __be64 service_mask, + struct ib_cm_compare_data *compare_data); struct ib_cm_req_param { struct ib_sa_path_rec *primary_path; @@ -373,7 +398,6 @@ struct ib_cm_rep_param { u8 private_data_len; u8 responder_resources; u8 initiator_depth; - u8 target_ack_delay; u8 failover_accepted; u8 flow_control; u8 rnr_retry_count; @@ -432,13 +456,20 @@ int ib_send_cm_drep(struct ib_cm_id *cm_id, u8 private_data_len); /** - * ib_cm_establish - Forces a connection state to established. + * ib_cm_notify - Notifies the CM of an event reported to the consumer. * @cm_id: Connection identifier to transition to established. + * @event: Type of event. + * + * This routine should be invoked by users to notify the CM of relevant + * communication events. Events that should be reported to the CM and + * when to report them are: * - * This routine should be invoked by users who receive messages on a - * connected QP before an RTU has been received. + * IB_EVENT_COMM_EST - Used when a message is received on a connected + * QP before an RTU has been received. + * IB_EVENT_PATH_MIG - Notifies the CM that the connection has failed over + * to the alternate path. */ -int ib_cm_establish(struct ib_cm_id *cm_id); +int ib_cm_notify(struct ib_cm_id *cm_id, enum ib_event_type event); /** * ib_send_cm_rej - Sends a connection rejection message to the @@ -459,12 +490,15 @@ int ib_send_cm_rej(struct ib_cm_id *cm_id, const void *private_data, u8 private_data_len); +#define IB_CM_MRA_FLAG_DELAY 0x80 /* Send MRA only after a duplicate msg */ + /** * ib_send_cm_mra - Sends a message receipt acknowledgement to a connection * message. * @cm_id: Connection identifier associated with the connection message. - * @service_timeout: The maximum time required for the sender to reply to - * to the connection message. + * @service_timeout: The lower 5-bits specify the maximum time required for + * the sender to reply to the connection message. The upper 3-bits + * specify additional control flags. * @private_data: Optional user-defined private data sent with the * message receipt acknowledgement. * @private_data_len: Size of the private data buffer, in bytes. @@ -535,7 +569,6 @@ struct ib_cm_sidr_req_param { const void *private_data; u8 private_data_len; u8 max_cm_retries; - u16 pkey; }; /** @@ -559,7 +592,7 @@ struct ib_cm_sidr_rep_param { }; /** - * ib_send_cm_sidr_rep - Sends a service ID resolution request to the + * ib_send_cm_sidr_rep - Sends a service ID resolution reply to the * remote node. * @cm_id: Communication identifier associated with the received service ID * resolution request. diff --git a/include/rdma/ib_fmr_pool.h b/include/rdma/ib_fmr_pool.h index 86b7e93f198..f62b842e659 100644 --- a/include/rdma/ib_fmr_pool.h +++ b/include/rdma/ib_fmr_pool.h @@ -29,8 +29,6 @@ * 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. - * - * $Id: ib_fmr_pool.h 2730 2005-06-28 16:43:03Z sean.hefty $ */ #if !defined(IB_FMR_POOL_H) @@ -43,6 +41,7 @@ struct ib_fmr_pool; /** * struct ib_fmr_pool_param - Parameters for creating FMR pool * @max_pages_per_fmr:Maximum number of pages per map request. + * @page_shift: Log2 of sizeof "pages" mapped by this fmr * @access:Access flags for FMRs in pool. * @pool_size:Number of FMRs to allocate for pool. * @dirty_watermark:Flush is triggered when @dirty_watermark dirty @@ -55,11 +54,12 @@ struct ib_fmr_pool; */ struct ib_fmr_pool_param { int max_pages_per_fmr; + int page_shift; enum ib_access_flags access; int pool_size; int dirty_watermark; void (*flush_function)(struct ib_fmr_pool *pool, - void * arg); + void *arg); void *flush_arg; unsigned cache:1; }; @@ -86,7 +86,7 @@ int ib_flush_fmr_pool(struct ib_fmr_pool *pool); struct ib_pool_fmr *ib_fmr_pool_map_phys(struct ib_fmr_pool *pool_handle, u64 *page_list, int list_len, - u64 *io_virtual_address); + u64 io_virtual_address); int ib_fmr_pool_unmap(struct ib_pool_fmr *fmr); diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h index 2c133506742..3d81b90cc31 100644 --- a/include/rdma/ib_mad.h +++ b/include/rdma/ib_mad.h @@ -3,7 +3,7 @@ * Copyright (c) 2004 Infinicon Corporation. All rights reserved. * Copyright (c) 2004 Intel Corporation. All rights reserved. * Copyright (c) 2004 Topspin Corporation. All rights reserved. - * Copyright (c) 2004 Voltaire Corporation. All rights reserved. + * Copyright (c) 2004-2006 Voltaire Corporation. 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 @@ -32,14 +32,12 @@ * 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. - * - * $Id: ib_mad.h 2775 2005-07-02 13:42:12Z halr $ */ -#if !defined( IB_MAD_H ) +#if !defined(IB_MAD_H) #define IB_MAD_H -#include <linux/pci.h> +#include <linux/list.h> #include <rdma/ib_verbs.h> @@ -55,6 +53,10 @@ #define IB_MGMT_CLASS_DEVICE_MGMT 0x06 #define IB_MGMT_CLASS_CM 0x07 #define IB_MGMT_CLASS_SNMP 0x08 +#define IB_MGMT_CLASS_DEVICE_ADM 0x10 +#define IB_MGMT_CLASS_BOOT_MGMT 0x11 +#define IB_MGMT_CLASS_BIS 0x12 +#define IB_MGMT_CLASS_CONG_MGMT 0x21 #define IB_MGMT_CLASS_VENDOR_RANGE2_START 0x30 #define IB_MGMT_CLASS_VENDOR_RANGE2_END 0x4F @@ -71,9 +73,19 @@ #define IB_MGMT_METHOD_TRAP_REPRESS 0x07 #define IB_MGMT_METHOD_RESP 0x80 +#define IB_BM_ATTR_MOD_RESP cpu_to_be32(1) #define IB_MGMT_MAX_METHODS 128 +/* MAD Status field bit masks */ +#define IB_MGMT_MAD_STATUS_SUCCESS 0x0000 +#define IB_MGMT_MAD_STATUS_BUSY 0x0001 +#define IB_MGMT_MAD_STATUS_REDIRECT_REQD 0x0002 +#define IB_MGMT_MAD_STATUS_BAD_VERSION 0x0004 +#define IB_MGMT_MAD_STATUS_UNSUPPORTED_METHOD 0x0008 +#define IB_MGMT_MAD_STATUS_UNSUPPORTED_METHOD_ATTRIB 0x000c +#define IB_MGMT_MAD_STATUS_INVALID_ATTRIB_VALUE 0x001c + /* RMPP information */ #define IB_MGMT_RMPP_VERSION 1 @@ -104,10 +116,13 @@ #define IB_MGMT_RMPP_STATUS_ABORT_MAX 127 #define IB_QP0 0 -#define IB_QP1 __constant_htonl(1) +#define IB_QP1 cpu_to_be32(1) #define IB_QP1_QKEY 0x80010000 #define IB_QP_SET_QKEY 0x80000000 +#define IB_DEFAULT_PKEY_PARTIAL 0x7FFF +#define IB_DEFAULT_PKEY_FULL 0xFFFF + enum { IB_MGMT_MAD_HDR = 24, IB_MGMT_MAD_DATA = 232, @@ -117,6 +132,8 @@ enum { IB_MGMT_VENDOR_DATA = 216, IB_MGMT_SA_HDR = 56, IB_MGMT_SA_DATA = 200, + IB_MGMT_DEVICE_HDR = 64, + IB_MGMT_DEVICE_DATA = 192, }; struct ib_mad_hdr { @@ -143,7 +160,7 @@ struct ib_rmpp_hdr { typedef u64 __bitwise ib_sa_comp_mask; -#define IB_SA_COMP_MASK(n) ((__force ib_sa_comp_mask) cpu_to_be64(1ull << n)) +#define IB_SA_COMP_MASK(n) ((__force ib_sa_comp_mask) cpu_to_be64(1ull << (n))) /* * ib_sa_hdr and ib_sa_mad structures must be packed because they have @@ -184,8 +201,7 @@ struct ib_vendor_mad { u8 data[IB_MGMT_VENDOR_DATA]; }; -struct ib_class_port_info -{ +struct ib_class_port_info { u8 base_version; u8 class_version; __be16 capability_mask; @@ -208,15 +224,25 @@ struct ib_class_port_info /** * ib_mad_send_buf - MAD data buffer and work request for sends. * @next: A pointer used to chain together MADs for posting. - * @mad: References an allocated MAD data buffer. + * @mad: References an allocated MAD data buffer for MADs that do not have + * RMPP active. For MADs using RMPP, references the common and management + * class specific headers. * @mad_agent: MAD agent that allocated the buffer. * @ah: The address handle to use when sending the MAD. * @context: User-controlled context fields. + * @hdr_len: Indicates the size of the data header of the MAD. This length + * includes the common MAD, RMPP, and class specific headers. + * @data_len: Indicates the total size of user-transferred data. + * @seg_count: The number of RMPP segments allocated for this send. + * @seg_size: Size of each RMPP segment. * @timeout_ms: Time to wait for a response. - * @retries: Number of times to retry a request for a response. + * @retries: Number of times to retry a request for a response. For MADs + * using RMPP, this applies per window. On completion, returns the number + * of retries needed to complete the transfer. * * Users are responsible for initializing the MAD buffer itself, with the - * exception of specifying the payload length field in any RMPP MAD. + * exception of any RMPP header. Additional segment buffer space allocated + * beyond data_len is padding. */ struct ib_mad_send_buf { struct ib_mad_send_buf *next; @@ -224,11 +250,21 @@ struct ib_mad_send_buf { struct ib_mad_agent *mad_agent; struct ib_ah *ah; void *context[2]; + int hdr_len; + int data_len; + int seg_count; + int seg_size; int timeout_ms; int retries; }; /** + * ib_response_mad - Returns if the specified MAD has been generated in + * response to a sent request or trap. + */ +int ib_response_mad(struct ib_mad *mad); + +/** * ib_get_rmpp_resptime - Returns the RMPP response time. * @rmpp_hdr: An RMPP header. */ @@ -263,7 +299,7 @@ static inline void ib_set_rmpp_resptime(struct ib_rmpp_hdr *rmpp_hdr, u8 rtime) */ static inline void ib_set_rmpp_flags(struct ib_rmpp_hdr *rmpp_hdr, u8 flags) { - rmpp_hdr->rmpp_rtime_flags = (rmpp_hdr->rmpp_rtime_flags & 0xF1) | + rmpp_hdr->rmpp_rtime_flags = (rmpp_hdr->rmpp_rtime_flags & 0xF8) | (flags & 0x7); } @@ -299,7 +335,7 @@ typedef void (*ib_mad_snoop_handler)(struct ib_mad_agent *mad_agent, * @mad_recv_wc: Received work completion information on the received MAD. * * MADs received in response to a send request operation will be handed to - * the user after the send operation completes. All data buffers given + * the user before the send operation completes. All data buffers given * to registered agents through this routine are owned by the receiving * client, except for snooping agents. Clients snooping MADs should not * modify the data referenced by @mad_recv_wc. @@ -485,17 +521,6 @@ int ib_unregister_mad_agent(struct ib_mad_agent *mad_agent); int ib_post_send_mad(struct ib_mad_send_buf *send_buf, struct ib_mad_send_buf **bad_send_buf); -/** - * ib_coalesce_recv_mad - Coalesces received MAD data into a single buffer. - * @mad_recv_wc: Work completion information for a received MAD. - * @buf: User-provided data buffer to receive the coalesced buffers. The - * referenced buffer should be at least the size of the mad_len specified - * by @mad_recv_wc. - * - * This call copies a chain of received MAD segments into a single data buffer, - * removing duplicated headers. - */ -void ib_coalesce_recv_mad(struct ib_mad_recv_wc *mad_recv_wc, void *buf); /** * ib_free_recv_mad - Returns data buffers used to receive a MAD. @@ -590,15 +615,45 @@ int ib_process_mad_wc(struct ib_mad_agent *mad_agent, * with an initialized work request structure. Users may modify the returned * MAD data buffer before posting the send. * - * The returned data buffer will be cleared. Users are responsible for - * initializing the common MAD and any class specific headers. If @rmpp_active - * is set, the RMPP header will be initialized for sending. + * The returned MAD header, class specific headers, and any padding will be + * cleared. Users are responsible for initializing the common MAD header, + * any class specific header, and MAD data area. + * If @rmpp_active is set, the RMPP header will be initialized for sending. + */ +struct ib_mad_send_buf *ib_create_send_mad(struct ib_mad_agent *mad_agent, + u32 remote_qpn, u16 pkey_index, + int rmpp_active, + int hdr_len, int data_len, + gfp_t gfp_mask); + +/** + * ib_is_mad_class_rmpp - returns whether given management class + * supports RMPP. + * @mgmt_class: management class + * + * This routine returns whether the management class supports RMPP. + */ +int ib_is_mad_class_rmpp(u8 mgmt_class); + +/** + * ib_get_mad_data_offset - returns the data offset for a given + * management class. + * @mgmt_class: management class + * + * This routine returns the data offset in the MAD for the management + * class requested. + */ +int ib_get_mad_data_offset(u8 mgmt_class); + +/** + * ib_get_rmpp_segment - returns the data buffer for a given RMPP segment. + * @send_buf: Previously allocated send data buffer. + * @seg_num: number of segment to return + * + * This routine returns a pointer to the data buffer of an RMPP MAD. + * Users must provide synchronization to @send_buf around this call. */ -struct ib_mad_send_buf * ib_create_send_mad(struct ib_mad_agent *mad_agent, - u32 remote_qpn, u16 pkey_index, - int rmpp_active, - int hdr_len, int data_len, - gfp_t gfp_mask); +void *ib_get_rmpp_segment(struct ib_mad_send_buf *send_buf, int seg_num); /** * ib_free_send_mad - Returns data buffers used to send a MAD. diff --git a/include/rdma/ib_marshall.h b/include/rdma/ib_marshall.h new file mode 100644 index 00000000000..db037205c9e --- /dev/null +++ b/include/rdma/ib_marshall.h @@ -0,0 +1,53 @@ +/* + * Copyright (c) 2005-2006 Intel Corporation. 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. + */ + +#if !defined(IB_USER_MARSHALL_H) +#define IB_USER_MARSHALL_H + +#include <rdma/ib_verbs.h> +#include <rdma/ib_sa.h> +#include <rdma/ib_user_verbs.h> +#include <rdma/ib_user_sa.h> + +void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst, + struct ib_qp_attr *src); + +void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst, + struct ib_ah_attr *src); + +void ib_copy_path_rec_to_user(struct ib_user_path_rec *dst, + struct ib_sa_path_rec *src); + +void ib_copy_path_rec_from_user(struct ib_sa_path_rec *dst, + struct ib_user_path_rec *src); + +#endif /* IB_USER_MARSHALL_H */ diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h index f926020d633..b1f7592e02e 100644 --- a/include/rdma/ib_pack.h +++ b/include/rdma/ib_pack.h @@ -28,17 +28,18 @@ * 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. - * - * $Id: ib_pack.h 1349 2004-12-16 21:09:43Z roland $ */ #ifndef IB_PACK_H #define IB_PACK_H #include <rdma/ib_verbs.h> +#include <uapi/linux/if_ether.h> enum { IB_LRH_BYTES = 8, + IB_ETH_BYTES = 14, + IB_VLAN_BYTES = 4, IB_GRH_BYTES = 40, IB_BTH_BYTES = 12, IB_DETH_BYTES = 8 @@ -212,14 +213,32 @@ struct ib_unpacked_deth { __be32 source_qpn; }; +struct ib_unpacked_eth { + u8 dmac_h[4]; + u8 dmac_l[2]; + u8 smac_h[2]; + u8 smac_l[4]; + __be16 type; +}; + +struct ib_unpacked_vlan { + __be16 tag; + __be16 type; +}; + struct ib_ud_header { + int lrh_present; struct ib_unpacked_lrh lrh; - int grh_present; - struct ib_unpacked_grh grh; - struct ib_unpacked_bth bth; + int eth_present; + struct ib_unpacked_eth eth; + int vlan_present; + struct ib_unpacked_vlan vlan; + int grh_present; + struct ib_unpacked_grh grh; + struct ib_unpacked_bth bth; struct ib_unpacked_deth deth; - int immediate_present; - __be32 immediate_data; + int immediate_present; + __be32 immediate_data; }; void ib_pack(const struct ib_field *desc, @@ -232,8 +251,12 @@ void ib_unpack(const struct ib_field *desc, void *buf, void *structure); -void ib_ud_header_init(int payload_bytes, - int grh_present, +void ib_ud_header_init(int payload_bytes, + int lrh_present, + int eth_present, + int vlan_present, + int grh_present, + int immediate_present, struct ib_ud_header *header); int ib_ud_header_pack(struct ib_ud_header *header, diff --git a/include/rdma/ib_pma.h b/include/rdma/ib_pma.h new file mode 100644 index 00000000000..a5889f18807 --- /dev/null +++ b/include/rdma/ib_pma.h @@ -0,0 +1,156 @@ +/* + * Copyright (c) 2006, 2007, 2008, 2009, 2010 QLogic Corporation. + * All rights reserved. + * Copyright (c) 2005, 2006 PathScale, 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. + */ + +#if !defined(IB_PMA_H) +#define IB_PMA_H + +#include <rdma/ib_mad.h> + +/* + * PMA class portinfo capability mask bits + */ +#define IB_PMA_CLASS_CAP_ALLPORTSELECT cpu_to_be16(1 << 8) +#define IB_PMA_CLASS_CAP_EXT_WIDTH cpu_to_be16(1 << 9) +#define IB_PMA_CLASS_CAP_XMIT_WAIT cpu_to_be16(1 << 12) + +#define IB_PMA_CLASS_PORT_INFO cpu_to_be16(0x0001) +#define IB_PMA_PORT_SAMPLES_CONTROL cpu_to_be16(0x0010) +#define IB_PMA_PORT_SAMPLES_RESULT cpu_to_be16(0x0011) +#define IB_PMA_PORT_COUNTERS cpu_to_be16(0x0012) +#define IB_PMA_PORT_COUNTERS_EXT cpu_to_be16(0x001D) +#define IB_PMA_PORT_SAMPLES_RESULT_EXT cpu_to_be16(0x001E) + +struct ib_pma_mad { + struct ib_mad_hdr mad_hdr; + u8 reserved[40]; + u8 data[192]; +} __packed; + +struct ib_pma_portsamplescontrol { + u8 opcode; + u8 port_select; + u8 tick; + u8 counter_width; /* resv: 7:3, counter width: 2:0 */ + __be32 counter_mask0_9; /* 2, 10 3-bit fields */ + __be16 counter_mask10_14; /* 1, 5 3-bit fields */ + u8 sample_mechanisms; + u8 sample_status; /* only lower 2 bits */ + __be64 option_mask; + __be64 vendor_mask; + __be32 sample_start; + __be32 sample_interval; + __be16 tag; + __be16 counter_select[15]; + __be32 reserved1; + __be64 samples_only_option_mask; + __be32 reserved2[28]; +}; + +struct ib_pma_portsamplesresult { + __be16 tag; + __be16 sample_status; /* only lower 2 bits */ + __be32 counter[15]; +}; + +struct ib_pma_portsamplesresult_ext { + __be16 tag; + __be16 sample_status; /* only lower 2 bits */ + __be32 extended_width; /* only upper 2 bits */ + __be64 counter[15]; +}; + +struct ib_pma_portcounters { + u8 reserved; + u8 port_select; + __be16 counter_select; + __be16 symbol_error_counter; + u8 link_error_recovery_counter; + u8 link_downed_counter; + __be16 port_rcv_errors; + __be16 port_rcv_remphys_errors; + __be16 port_rcv_switch_relay_errors; + __be16 port_xmit_discards; + u8 port_xmit_constraint_errors; + u8 port_rcv_constraint_errors; + u8 reserved1; + u8 link_overrun_errors; /* LocalLink: 7:4, BufferOverrun: 3:0 */ + __be16 reserved2; + __be16 vl15_dropped; + __be32 port_xmit_data; + __be32 port_rcv_data; + __be32 port_xmit_packets; + __be32 port_rcv_packets; + __be32 port_xmit_wait; +} __packed; + + +#define IB_PMA_SEL_SYMBOL_ERROR cpu_to_be16(0x0001) +#define IB_PMA_SEL_LINK_ERROR_RECOVERY cpu_to_be16(0x0002) +#define IB_PMA_SEL_LINK_DOWNED cpu_to_be16(0x0004) +#define IB_PMA_SEL_PORT_RCV_ERRORS cpu_to_be16(0x0008) +#define IB_PMA_SEL_PORT_RCV_REMPHYS_ERRORS cpu_to_be16(0x0010) +#define IB_PMA_SEL_PORT_XMIT_DISCARDS cpu_to_be16(0x0040) +#define IB_PMA_SEL_LOCAL_LINK_INTEGRITY_ERRORS cpu_to_be16(0x0200) +#define IB_PMA_SEL_EXCESSIVE_BUFFER_OVERRUNS cpu_to_be16(0x0400) +#define IB_PMA_SEL_PORT_VL15_DROPPED cpu_to_be16(0x0800) +#define IB_PMA_SEL_PORT_XMIT_DATA cpu_to_be16(0x1000) +#define IB_PMA_SEL_PORT_RCV_DATA cpu_to_be16(0x2000) +#define IB_PMA_SEL_PORT_XMIT_PACKETS cpu_to_be16(0x4000) +#define IB_PMA_SEL_PORT_RCV_PACKETS cpu_to_be16(0x8000) + +struct ib_pma_portcounters_ext { + u8 reserved; + u8 port_select; + __be16 counter_select; + __be32 reserved1; + __be64 port_xmit_data; + __be64 port_rcv_data; + __be64 port_xmit_packets; + __be64 port_rcv_packets; + __be64 port_unicast_xmit_packets; + __be64 port_unicast_rcv_packets; + __be64 port_multicast_xmit_packets; + __be64 port_multicast_rcv_packets; +} __packed; + +#define IB_PMA_SELX_PORT_XMIT_DATA cpu_to_be16(0x0001) +#define IB_PMA_SELX_PORT_RCV_DATA cpu_to_be16(0x0002) +#define IB_PMA_SELX_PORT_XMIT_PACKETS cpu_to_be16(0x0004) +#define IB_PMA_SELX_PORT_RCV_PACKETS cpu_to_be16(0x0008) +#define IB_PMA_SELX_PORT_UNI_XMIT_PACKETS cpu_to_be16(0x0010) +#define IB_PMA_SELX_PORT_UNI_RCV_PACKETS cpu_to_be16(0x0020) +#define IB_PMA_SELX_PORT_MULTI_XMIT_PACKETS cpu_to_be16(0x0040) +#define IB_PMA_SELX_PORT_MULTI_RCV_PACKETS cpu_to_be16(0x0080) + +#endif /* IB_PMA_H */ diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h index f404fe21cc2..7e071a6abb3 100644 --- a/include/rdma/ib_sa.h +++ b/include/rdma/ib_sa.h @@ -1,6 +1,7 @@ /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Voltaire, Inc. All rights reserved. + * Copyright (c) 2006 Intel Corporation. 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 @@ -29,15 +30,16 @@ * 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. - * - * $Id: ib_sa.h 2811 2005-07-06 18:11:43Z halr $ */ #ifndef IB_SA_H #define IB_SA_H +#include <linux/completion.h> #include <linux/compiler.h> +#include <linux/atomic.h> + #include <rdma/ib_verbs.h> #include <rdma/ib_mad.h> @@ -79,8 +81,8 @@ enum { }; enum ib_sa_selector { - IB_SA_GTE = 0, - IB_SA_LTE = 1, + IB_SA_GT = 0, + IB_SA_LT = 1, IB_SA_EQ = 2, /* * The meaning of "best" depends on the attribute: for @@ -91,34 +93,6 @@ enum ib_sa_selector { IB_SA_BEST = 3 }; -enum ib_sa_rate { - IB_SA_RATE_2_5_GBPS = 2, - IB_SA_RATE_5_GBPS = 5, - IB_SA_RATE_10_GBPS = 3, - IB_SA_RATE_20_GBPS = 6, - IB_SA_RATE_30_GBPS = 4, - IB_SA_RATE_40_GBPS = 7, - IB_SA_RATE_60_GBPS = 8, - IB_SA_RATE_80_GBPS = 9, - IB_SA_RATE_120_GBPS = 10 -}; - -static inline int ib_sa_rate_enum_to_int(enum ib_sa_rate rate) -{ - switch (rate) { - case IB_SA_RATE_2_5_GBPS: return 1; - case IB_SA_RATE_5_GBPS: return 2; - case IB_SA_RATE_10_GBPS: return 4; - case IB_SA_RATE_20_GBPS: return 8; - case IB_SA_RATE_30_GBPS: return 12; - case IB_SA_RATE_40_GBPS: return 16; - case IB_SA_RATE_60_GBPS: return 24; - case IB_SA_RATE_80_GBPS: return 32; - case IB_SA_RATE_120_GBPS: return 48; - default: return -1; - } -} - /* * Structures for SA records are named "struct ib_sa_xxx_rec." No * attempt is made to pack structures to match the physical layout of @@ -133,8 +107,8 @@ static inline int ib_sa_rate_enum_to_int(enum ib_sa_rate rate) * Reserved rows are indicated with comments to help maintainability. */ -/* reserved: 0 */ -/* reserved: 1 */ +#define IB_SA_PATH_REC_SERVICE_ID (IB_SA_COMP_MASK( 0) |\ + IB_SA_COMP_MASK( 1)) #define IB_SA_PATH_REC_DGID IB_SA_COMP_MASK( 2) #define IB_SA_PATH_REC_SGID IB_SA_COMP_MASK( 3) #define IB_SA_PATH_REC_DLID IB_SA_COMP_MASK( 4) @@ -147,7 +121,7 @@ static inline int ib_sa_rate_enum_to_int(enum ib_sa_rate rate) #define IB_SA_PATH_REC_REVERSIBLE IB_SA_COMP_MASK(11) #define IB_SA_PATH_REC_NUMB_PATH IB_SA_COMP_MASK(12) #define IB_SA_PATH_REC_PKEY IB_SA_COMP_MASK(13) -/* reserved: 14 */ +#define IB_SA_PATH_REC_QOS_CLASS IB_SA_COMP_MASK(14) #define IB_SA_PATH_REC_SL IB_SA_COMP_MASK(15) #define IB_SA_PATH_REC_MTU_SELECTOR IB_SA_COMP_MASK(16) #define IB_SA_PATH_REC_MTU IB_SA_COMP_MASK(17) @@ -158,8 +132,7 @@ static inline int ib_sa_rate_enum_to_int(enum ib_sa_rate rate) #define IB_SA_PATH_REC_PREFERENCE IB_SA_COMP_MASK(22) struct ib_sa_path_rec { - /* reserved */ - /* reserved */ + __be64 service_id; union ib_gid dgid; union ib_gid sgid; __be16 dlid; @@ -172,7 +145,7 @@ struct ib_sa_path_rec { int reversible; u8 numb_path; __be16 pkey; - /* reserved */ + __be16 qos_class; u8 sl; u8 mtu_selector; u8 mtu; @@ -181,6 +154,9 @@ struct ib_sa_path_rec { u8 packet_life_time_selector; u8 packet_life_time; u8 preference; + u8 smac[ETH_ALEN]; + u8 dmac[ETH_ALEN]; + u16 vlan_id; }; #define IB_SA_MCMEMBER_REC_MGID IB_SA_COMP_MASK( 0) @@ -278,11 +254,50 @@ struct ib_sa_service_rec { u64 data64[2]; }; +#define IB_SA_GUIDINFO_REC_LID IB_SA_COMP_MASK(0) +#define IB_SA_GUIDINFO_REC_BLOCK_NUM IB_SA_COMP_MASK(1) +#define IB_SA_GUIDINFO_REC_RES1 IB_SA_COMP_MASK(2) +#define IB_SA_GUIDINFO_REC_RES2 IB_SA_COMP_MASK(3) +#define IB_SA_GUIDINFO_REC_GID0 IB_SA_COMP_MASK(4) +#define IB_SA_GUIDINFO_REC_GID1 IB_SA_COMP_MASK(5) +#define IB_SA_GUIDINFO_REC_GID2 IB_SA_COMP_MASK(6) +#define IB_SA_GUIDINFO_REC_GID3 IB_SA_COMP_MASK(7) +#define IB_SA_GUIDINFO_REC_GID4 IB_SA_COMP_MASK(8) +#define IB_SA_GUIDINFO_REC_GID5 IB_SA_COMP_MASK(9) +#define IB_SA_GUIDINFO_REC_GID6 IB_SA_COMP_MASK(10) +#define IB_SA_GUIDINFO_REC_GID7 IB_SA_COMP_MASK(11) + +struct ib_sa_guidinfo_rec { + __be16 lid; + u8 block_num; + /* reserved */ + u8 res1; + __be32 res2; + u8 guid_info_list[64]; +}; + +struct ib_sa_client { + atomic_t users; + struct completion comp; +}; + +/** + * ib_sa_register_client - Register an SA client. + */ +void ib_sa_register_client(struct ib_sa_client *client); + +/** + * ib_sa_unregister_client - Deregister an SA client. + * @client: Client object to deregister. + */ +void ib_sa_unregister_client(struct ib_sa_client *client); + struct ib_sa_query; void ib_sa_cancel_query(int id, struct ib_sa_query *query); -int ib_sa_path_rec_get(struct ib_device *device, u8 port_num, +int ib_sa_path_rec_get(struct ib_sa_client *client, + struct ib_device *device, u8 port_num, struct ib_sa_path_rec *rec, ib_sa_comp_mask comp_mask, int timeout_ms, gfp_t gfp_mask, @@ -292,18 +307,8 @@ int ib_sa_path_rec_get(struct ib_device *device, u8 port_num, void *context, struct ib_sa_query **query); -int ib_sa_mcmember_rec_query(struct ib_device *device, u8 port_num, - u8 method, - struct ib_sa_mcmember_rec *rec, - ib_sa_comp_mask comp_mask, - int timeout_ms, gfp_t gfp_mask, - void (*callback)(int status, - struct ib_sa_mcmember_rec *resp, - void *context), - void *context, - struct ib_sa_query **query); - -int ib_sa_service_rec_query(struct ib_device *device, u8 port_num, +int ib_sa_service_rec_query(struct ib_sa_client *client, + struct ib_device *device, u8 port_num, u8 method, struct ib_sa_service_rec *rec, ib_sa_comp_mask comp_mask, @@ -314,89 +319,113 @@ int ib_sa_service_rec_query(struct ib_device *device, u8 port_num, void *context, struct ib_sa_query **sa_query); +struct ib_sa_multicast { + struct ib_sa_mcmember_rec rec; + ib_sa_comp_mask comp_mask; + int (*callback)(int status, + struct ib_sa_multicast *multicast); + void *context; +}; + /** - * ib_sa_mcmember_rec_set - Start an MCMember set query - * @device:device to send query on - * @port_num: port number to send query on - * @rec:MCMember Record to send in query - * @comp_mask:component mask to send in query - * @timeout_ms:time to wait for response - * @gfp_mask:GFP mask to use for internal allocations - * @callback:function called when query completes, times out or is - * canceled - * @context:opaque user context passed to callback - * @sa_query:query context, used to cancel query + * ib_sa_join_multicast - Initiates a join request to the specified multicast + * group. + * @client: SA client + * @device: Device associated with the multicast group. + * @port_num: Port on the specified device to associate with the multicast + * group. + * @rec: SA multicast member record specifying group attributes. + * @comp_mask: Component mask indicating which group attributes of %rec are + * valid. + * @gfp_mask: GFP mask for memory allocations. + * @callback: User callback invoked once the join operation completes. + * @context: User specified context stored with the ib_sa_multicast structure. * - * Send an MCMember Set query to the SA (eg to join a multicast - * group). The callback function will be called when the query - * completes (or fails); status is 0 for a successful response, -EINTR - * if the query is canceled, -ETIMEDOUT is the query timed out, or - * -EIO if an error occurred sending the query. The resp parameter of - * the callback is only valid if status is 0. + * This call initiates a multicast join request with the SA for the specified + * multicast group. If the join operation is started successfully, it returns + * an ib_sa_multicast structure that is used to track the multicast operation. + * Users must free this structure by calling ib_free_multicast, even if the + * join operation later fails. (The callback status is non-zero.) * - * If the return value of ib_sa_mcmember_rec_set() is negative, it is - * an error code. Otherwise it is a query ID that can be used to - * cancel the query. + * If the join operation fails; status will be non-zero, with the following + * failures possible: + * -ETIMEDOUT: The request timed out. + * -EIO: An error occurred sending the query. + * -EINVAL: The MCMemberRecord values differed from the existing group's. + * -ENETRESET: Indicates that an fatal error has occurred on the multicast + * group, and the user must rejoin the group to continue using it. */ -static inline int -ib_sa_mcmember_rec_set(struct ib_device *device, u8 port_num, - struct ib_sa_mcmember_rec *rec, - ib_sa_comp_mask comp_mask, - int timeout_ms, gfp_t gfp_mask, - void (*callback)(int status, - struct ib_sa_mcmember_rec *resp, - void *context), - void *context, - struct ib_sa_query **query) -{ - return ib_sa_mcmember_rec_query(device, port_num, - IB_MGMT_METHOD_SET, - rec, comp_mask, - timeout_ms, gfp_mask, callback, - context, query); -} +struct ib_sa_multicast *ib_sa_join_multicast(struct ib_sa_client *client, + struct ib_device *device, u8 port_num, + struct ib_sa_mcmember_rec *rec, + ib_sa_comp_mask comp_mask, gfp_t gfp_mask, + int (*callback)(int status, + struct ib_sa_multicast + *multicast), + void *context); /** - * ib_sa_mcmember_rec_delete - Start an MCMember delete query - * @device:device to send query on - * @port_num: port number to send query on - * @rec:MCMember Record to send in query - * @comp_mask:component mask to send in query - * @timeout_ms:time to wait for response - * @gfp_mask:GFP mask to use for internal allocations - * @callback:function called when query completes, times out or is - * canceled - * @context:opaque user context passed to callback - * @sa_query:query context, used to cancel query - * - * Send an MCMember Delete query to the SA (eg to leave a multicast - * group). The callback function will be called when the query - * completes (or fails); status is 0 for a successful response, -EINTR - * if the query is canceled, -ETIMEDOUT is the query timed out, or - * -EIO if an error occurred sending the query. The resp parameter of - * the callback is only valid if status is 0. + * ib_free_multicast - Frees the multicast tracking structure, and releases + * any reference on the multicast group. + * @multicast: Multicast tracking structure allocated by ib_join_multicast. * - * If the return value of ib_sa_mcmember_rec_delete() is negative, it - * is an error code. Otherwise it is a query ID that can be used to - * cancel the query. + * This call blocks until the multicast identifier is destroyed. It may + * not be called from within the multicast callback; however, returning a non- + * zero value from the callback will result in destroying the multicast + * tracking structure. + */ +void ib_sa_free_multicast(struct ib_sa_multicast *multicast); + +/** + * ib_get_mcmember_rec - Looks up a multicast member record by its MGID and + * returns it if found. + * @device: Device associated with the multicast group. + * @port_num: Port on the specified device to associate with the multicast + * group. + * @mgid: MGID of multicast group. + * @rec: Location to copy SA multicast member record. + */ +int ib_sa_get_mcmember_rec(struct ib_device *device, u8 port_num, + union ib_gid *mgid, struct ib_sa_mcmember_rec *rec); + +/** + * ib_init_ah_from_mcmember - Initialize address handle attributes based on + * an SA multicast member record. + */ +int ib_init_ah_from_mcmember(struct ib_device *device, u8 port_num, + struct ib_sa_mcmember_rec *rec, + struct ib_ah_attr *ah_attr); + +/** + * ib_init_ah_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 ib_sa_path_rec *rec, + struct ib_ah_attr *ah_attr); + +/** + * ib_sa_pack_path - Conert a path record from struct ib_sa_path_rec + * to IB MAD wire format. + */ +void ib_sa_pack_path(struct ib_sa_path_rec *rec, void *attribute); + +/** + * ib_sa_unpack_path - Convert a path record from MAD format to struct + * ib_sa_path_rec. */ -static inline int -ib_sa_mcmember_rec_delete(struct ib_device *device, u8 port_num, - struct ib_sa_mcmember_rec *rec, - ib_sa_comp_mask comp_mask, - int timeout_ms, gfp_t gfp_mask, - void (*callback)(int status, - struct ib_sa_mcmember_rec *resp, - void *context), - void *context, - struct ib_sa_query **query) -{ - return ib_sa_mcmember_rec_query(device, port_num, - IB_SA_METHOD_DELETE, - rec, comp_mask, - timeout_ms, gfp_mask, callback, - context, query); -} +void ib_sa_unpack_path(void *attribute, struct ib_sa_path_rec *rec); +/* Support GuidInfoRecord */ +int ib_sa_guid_info_rec_query(struct ib_sa_client *client, + struct ib_device *device, u8 port_num, + struct ib_sa_guidinfo_rec *rec, + ib_sa_comp_mask comp_mask, u8 method, + int timeout_ms, gfp_t gfp_mask, + void (*callback)(int status, + struct ib_sa_guidinfo_rec *resp, + void *context), + void *context, + struct ib_sa_query **sa_query); #endif /* IB_SA_H */ diff --git a/include/rdma/ib_smi.h b/include/rdma/ib_smi.h index 87f60737f69..98b9086d769 100644 --- a/include/rdma/ib_smi.h +++ b/include/rdma/ib_smi.h @@ -32,11 +32,9 @@ * 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. - * - * $Id: ib_smi.h 1389 2004-12-27 22:56:47Z roland $ */ -#if !defined( IB_SMI_H ) +#if !defined(IB_SMI_H) #define IB_SMI_H #include <rdma/ib_mad.h> @@ -65,25 +63,61 @@ struct ib_smp { u8 return_path[IB_SMP_MAX_PATH_HOPS]; } __attribute__ ((packed)); -#define IB_SMP_DIRECTION __constant_htons(0x8000) +#define IB_SMP_DIRECTION cpu_to_be16(0x8000) /* Subnet management attributes */ -#define IB_SMP_ATTR_NOTICE __constant_htons(0x0002) -#define IB_SMP_ATTR_NODE_DESC __constant_htons(0x0010) -#define IB_SMP_ATTR_NODE_INFO __constant_htons(0x0011) -#define IB_SMP_ATTR_SWITCH_INFO __constant_htons(0x0012) -#define IB_SMP_ATTR_GUID_INFO __constant_htons(0x0014) -#define IB_SMP_ATTR_PORT_INFO __constant_htons(0x0015) -#define IB_SMP_ATTR_PKEY_TABLE __constant_htons(0x0016) -#define IB_SMP_ATTR_SL_TO_VL_TABLE __constant_htons(0x0017) -#define IB_SMP_ATTR_VL_ARB_TABLE __constant_htons(0x0018) -#define IB_SMP_ATTR_LINEAR_FORWARD_TABLE __constant_htons(0x0019) -#define IB_SMP_ATTR_RANDOM_FORWARD_TABLE __constant_htons(0x001A) -#define IB_SMP_ATTR_MCAST_FORWARD_TABLE __constant_htons(0x001B) -#define IB_SMP_ATTR_SM_INFO __constant_htons(0x0020) -#define IB_SMP_ATTR_VENDOR_DIAG __constant_htons(0x0030) -#define IB_SMP_ATTR_LED_INFO __constant_htons(0x0031) -#define IB_SMP_ATTR_VENDOR_MASK __constant_htons(0xFF00) +#define IB_SMP_ATTR_NOTICE cpu_to_be16(0x0002) +#define IB_SMP_ATTR_NODE_DESC cpu_to_be16(0x0010) +#define IB_SMP_ATTR_NODE_INFO cpu_to_be16(0x0011) +#define IB_SMP_ATTR_SWITCH_INFO cpu_to_be16(0x0012) +#define IB_SMP_ATTR_GUID_INFO cpu_to_be16(0x0014) +#define IB_SMP_ATTR_PORT_INFO cpu_to_be16(0x0015) +#define IB_SMP_ATTR_PKEY_TABLE cpu_to_be16(0x0016) +#define IB_SMP_ATTR_SL_TO_VL_TABLE cpu_to_be16(0x0017) +#define IB_SMP_ATTR_VL_ARB_TABLE cpu_to_be16(0x0018) +#define IB_SMP_ATTR_LINEAR_FORWARD_TABLE cpu_to_be16(0x0019) +#define IB_SMP_ATTR_RANDOM_FORWARD_TABLE cpu_to_be16(0x001A) +#define IB_SMP_ATTR_MCAST_FORWARD_TABLE cpu_to_be16(0x001B) +#define IB_SMP_ATTR_SM_INFO cpu_to_be16(0x0020) +#define IB_SMP_ATTR_VENDOR_DIAG cpu_to_be16(0x0030) +#define IB_SMP_ATTR_LED_INFO cpu_to_be16(0x0031) +#define IB_SMP_ATTR_VENDOR_MASK cpu_to_be16(0xFF00) + +struct ib_port_info { + __be64 mkey; + __be64 gid_prefix; + __be16 lid; + __be16 sm_lid; + __be32 cap_mask; + __be16 diag_code; + __be16 mkey_lease_period; + u8 local_port_num; + u8 link_width_enabled; + u8 link_width_supported; + u8 link_width_active; + u8 linkspeed_portstate; /* 4 bits, 4 bits */ + u8 portphysstate_linkdown; /* 4 bits, 4 bits */ + u8 mkeyprot_resv_lmc; /* 2 bits, 3, 3 */ + u8 linkspeedactive_enabled; /* 4 bits, 4 bits */ + u8 neighbormtu_mastersmsl; /* 4 bits, 4 bits */ + u8 vlcap_inittype; /* 4 bits, 4 bits */ + u8 vl_high_limit; + u8 vl_arb_high_cap; + u8 vl_arb_low_cap; + u8 inittypereply_mtucap; /* 4 bits, 4 bits */ + u8 vlstallcnt_hoqlife; /* 3 bits, 5 bits */ + u8 operationalvl_pei_peo_fpi_fpo; /* 4 bits, 1, 1, 1, 1 */ + __be16 mkey_violations; + __be16 pkey_violations; + __be16 qkey_violations; + u8 guid_cap; + u8 clientrereg_resv_subnetto; /* 1 bit, 2 bits, 5 */ + u8 resv_resptimevalue; /* 3 bits, 5 bits */ + u8 localphyerrors_overrunerrors; /* 4 bits, 4 bits */ + __be16 max_credit_hint; + u8 resv; + u8 link_roundtrip_latency[3]; +}; static inline u8 ib_get_smp_direction(struct ib_smp *smp) diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h new file mode 100644 index 00000000000..1ea0b65c4cf --- /dev/null +++ b/include/rdma/ib_umem.h @@ -0,0 +1,78 @@ +/* + * Copyright (c) 2007 Cisco Systems. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef IB_UMEM_H +#define IB_UMEM_H + +#include <linux/list.h> +#include <linux/scatterlist.h> +#include <linux/workqueue.h> + +struct ib_ucontext; + +struct ib_umem { + struct ib_ucontext *context; + size_t length; + int offset; + int page_size; + int writable; + int hugetlb; + struct work_struct work; + struct mm_struct *mm; + unsigned long diff; + struct sg_table sg_head; + int nmap; + int npages; +}; + +#ifdef CONFIG_INFINIBAND_USER_MEM + +struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, + size_t size, int access, int dmasync); +void ib_umem_release(struct ib_umem *umem); +int ib_umem_page_count(struct ib_umem *umem); + +#else /* CONFIG_INFINIBAND_USER_MEM */ + +#include <linux/err.h> + +static inline struct ib_umem *ib_umem_get(struct ib_ucontext *context, + unsigned long addr, size_t size, + int access, int dmasync) { + return ERR_PTR(-EINVAL); +} +static inline void ib_umem_release(struct ib_umem *umem) { } +static inline int ib_umem_page_count(struct ib_umem *umem) { return 0; } + +#endif /* CONFIG_INFINIBAND_USER_MEM */ + +#endif /* IB_UMEM_H */ diff --git a/include/rdma/ib_user_cm.h b/include/rdma/ib_user_cm.h deleted file mode 100644 index 19be116047f..00000000000 --- a/include/rdma/ib_user_cm.h +++ /dev/null @@ -1,399 +0,0 @@ -/* - * Copyright (c) 2005 Topspin Communications. All rights reserved. - * Copyright (c) 2005 Intel Corporation. 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. - * - * $Id: ib_user_cm.h 2576 2005-06-09 17:00:30Z libor $ - */ - -#ifndef IB_USER_CM_H -#define IB_USER_CM_H - -#include <linux/types.h> - -#define IB_USER_CM_ABI_VERSION 4 - -enum { - IB_USER_CM_CMD_CREATE_ID, - IB_USER_CM_CMD_DESTROY_ID, - IB_USER_CM_CMD_ATTR_ID, - - IB_USER_CM_CMD_LISTEN, - IB_USER_CM_CMD_ESTABLISH, - - IB_USER_CM_CMD_SEND_REQ, - IB_USER_CM_CMD_SEND_REP, - IB_USER_CM_CMD_SEND_RTU, - IB_USER_CM_CMD_SEND_DREQ, - IB_USER_CM_CMD_SEND_DREP, - IB_USER_CM_CMD_SEND_REJ, - IB_USER_CM_CMD_SEND_MRA, - IB_USER_CM_CMD_SEND_LAP, - IB_USER_CM_CMD_SEND_APR, - IB_USER_CM_CMD_SEND_SIDR_REQ, - IB_USER_CM_CMD_SEND_SIDR_REP, - - IB_USER_CM_CMD_EVENT, - IB_USER_CM_CMD_INIT_QP_ATTR, -}; -/* - * command ABI structures. - */ -struct ib_ucm_cmd_hdr { - __u32 cmd; - __u16 in; - __u16 out; -}; - -struct ib_ucm_create_id { - __u64 uid; - __u64 response; -}; - -struct ib_ucm_create_id_resp { - __u32 id; -}; - -struct ib_ucm_destroy_id { - __u64 response; - __u32 id; - __u32 reserved; -}; - -struct ib_ucm_destroy_id_resp { - __u32 events_reported; -}; - -struct ib_ucm_attr_id { - __u64 response; - __u32 id; - __u32 reserved; -}; - -struct ib_ucm_attr_id_resp { - __be64 service_id; - __be64 service_mask; - __be32 local_id; - __be32 remote_id; -}; - -struct ib_ucm_init_qp_attr { - __u64 response; - __u32 id; - __u32 qp_state; -}; - -struct ib_ucm_ah_attr { - __u8 grh_dgid[16]; - __u32 grh_flow_label; - __u16 dlid; - __u16 reserved; - __u8 grh_sgid_index; - __u8 grh_hop_limit; - __u8 grh_traffic_class; - __u8 sl; - __u8 src_path_bits; - __u8 static_rate; - __u8 is_global; - __u8 port_num; -}; - -struct ib_ucm_init_qp_attr_resp { - __u32 qp_attr_mask; - __u32 qp_state; - __u32 cur_qp_state; - __u32 path_mtu; - __u32 path_mig_state; - __u32 qkey; - __u32 rq_psn; - __u32 sq_psn; - __u32 dest_qp_num; - __u32 qp_access_flags; - - struct ib_ucm_ah_attr ah_attr; - struct ib_ucm_ah_attr alt_ah_attr; - - /* ib_qp_cap */ - __u32 max_send_wr; - __u32 max_recv_wr; - __u32 max_send_sge; - __u32 max_recv_sge; - __u32 max_inline_data; - - __u16 pkey_index; - __u16 alt_pkey_index; - __u8 en_sqd_async_notify; - __u8 sq_draining; - __u8 max_rd_atomic; - __u8 max_dest_rd_atomic; - __u8 min_rnr_timer; - __u8 port_num; - __u8 timeout; - __u8 retry_cnt; - __u8 rnr_retry; - __u8 alt_port_num; - __u8 alt_timeout; -}; - -struct ib_ucm_listen { - __be64 service_id; - __be64 service_mask; - __u32 id; - __u32 reserved; -}; - -struct ib_ucm_establish { - __u32 id; -}; - -struct ib_ucm_private_data { - __u64 data; - __u32 id; - __u8 len; - __u8 reserved[3]; -}; - -struct ib_ucm_path_rec { - __u8 dgid[16]; - __u8 sgid[16]; - __be16 dlid; - __be16 slid; - __u32 raw_traffic; - __be32 flow_label; - __u32 reversible; - __u32 mtu; - __be16 pkey; - __u8 hop_limit; - __u8 traffic_class; - __u8 numb_path; - __u8 sl; - __u8 mtu_selector; - __u8 rate_selector; - __u8 rate; - __u8 packet_life_time_selector; - __u8 packet_life_time; - __u8 preference; -}; - -struct ib_ucm_req { - __u32 id; - __u32 qpn; - __u32 qp_type; - __u32 psn; - __be64 sid; - __u64 data; - __u64 primary_path; - __u64 alternate_path; - __u8 len; - __u8 peer_to_peer; - __u8 responder_resources; - __u8 initiator_depth; - __u8 remote_cm_response_timeout; - __u8 flow_control; - __u8 local_cm_response_timeout; - __u8 retry_count; - __u8 rnr_retry_count; - __u8 max_cm_retries; - __u8 srq; - __u8 reserved[5]; -}; - -struct ib_ucm_rep { - __u64 uid; - __u64 data; - __u32 id; - __u32 qpn; - __u32 psn; - __u8 len; - __u8 responder_resources; - __u8 initiator_depth; - __u8 target_ack_delay; - __u8 failover_accepted; - __u8 flow_control; - __u8 rnr_retry_count; - __u8 srq; - __u8 reserved[4]; -}; - -struct ib_ucm_info { - __u32 id; - __u32 status; - __u64 info; - __u64 data; - __u8 info_len; - __u8 data_len; - __u8 reserved[6]; -}; - -struct ib_ucm_mra { - __u64 data; - __u32 id; - __u8 len; - __u8 timeout; - __u8 reserved[2]; -}; - -struct ib_ucm_lap { - __u64 path; - __u64 data; - __u32 id; - __u8 len; - __u8 reserved[3]; -}; - -struct ib_ucm_sidr_req { - __u32 id; - __u32 timeout; - __be64 sid; - __u64 data; - __u64 path; - __u16 pkey; - __u8 len; - __u8 max_cm_retries; - __u8 reserved[4]; -}; - -struct ib_ucm_sidr_rep { - __u32 id; - __u32 qpn; - __u32 qkey; - __u32 status; - __u64 info; - __u64 data; - __u8 info_len; - __u8 data_len; - __u8 reserved[6]; -}; -/* - * event notification ABI structures. - */ -struct ib_ucm_event_get { - __u64 response; - __u64 data; - __u64 info; - __u8 data_len; - __u8 info_len; - __u8 reserved[6]; -}; - -struct ib_ucm_req_event_resp { - struct ib_ucm_path_rec primary_path; - struct ib_ucm_path_rec alternate_path; - __be64 remote_ca_guid; - __u32 remote_qkey; - __u32 remote_qpn; - __u32 qp_type; - __u32 starting_psn; - __u8 responder_resources; - __u8 initiator_depth; - __u8 local_cm_response_timeout; - __u8 flow_control; - __u8 remote_cm_response_timeout; - __u8 retry_count; - __u8 rnr_retry_count; - __u8 srq; - __u8 port; - __u8 reserved[7]; -}; - -struct ib_ucm_rep_event_resp { - __be64 remote_ca_guid; - __u32 remote_qkey; - __u32 remote_qpn; - __u32 starting_psn; - __u8 responder_resources; - __u8 initiator_depth; - __u8 target_ack_delay; - __u8 failover_accepted; - __u8 flow_control; - __u8 rnr_retry_count; - __u8 srq; - __u8 reserved[5]; -}; - -struct ib_ucm_rej_event_resp { - __u32 reason; - /* ari in ib_ucm_event_get info field. */ -}; - -struct ib_ucm_mra_event_resp { - __u8 timeout; - __u8 reserved[3]; -}; - -struct ib_ucm_lap_event_resp { - struct ib_ucm_path_rec path; -}; - -struct ib_ucm_apr_event_resp { - __u32 status; - /* apr info in ib_ucm_event_get info field. */ -}; - -struct ib_ucm_sidr_req_event_resp { - __u16 pkey; - __u8 port; - __u8 reserved; -}; - -struct ib_ucm_sidr_rep_event_resp { - __u32 status; - __u32 qkey; - __u32 qpn; - /* info in ib_ucm_event_get info field. */ -}; - -#define IB_UCM_PRES_DATA 0x01 -#define IB_UCM_PRES_INFO 0x02 -#define IB_UCM_PRES_PRIMARY 0x04 -#define IB_UCM_PRES_ALTERNATE 0x08 - -struct ib_ucm_event_resp { - __u64 uid; - __u32 id; - __u32 event; - __u32 present; - __u32 reserved; - union { - struct ib_ucm_req_event_resp req_resp; - struct ib_ucm_rep_event_resp rep_resp; - struct ib_ucm_rej_event_resp rej_resp; - struct ib_ucm_mra_event_resp mra_resp; - struct ib_ucm_lap_event_resp lap_resp; - struct ib_ucm_apr_event_resp apr_resp; - - struct ib_ucm_sidr_req_event_resp sidr_req_resp; - struct ib_ucm_sidr_rep_event_resp sidr_rep_resp; - - __u32 send_status; - } u; -}; - -#endif /* IB_USER_CM_H */ diff --git a/include/rdma/ib_user_mad.h b/include/rdma/ib_user_mad.h deleted file mode 100644 index 44537aa32e6..00000000000 --- a/include/rdma/ib_user_mad.h +++ /dev/null @@ -1,137 +0,0 @@ -/* - * Copyright (c) 2004 Topspin Communications. All rights reserved. - * Copyright (c) 2005 Voltaire, 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. - * - * $Id: ib_user_mad.h 2814 2005-07-06 19:14:09Z halr $ - */ - -#ifndef IB_USER_MAD_H -#define IB_USER_MAD_H - -#include <linux/types.h> -#include <linux/ioctl.h> - -/* - * Increment this value if any changes that break userspace ABI - * compatibility are made. - */ -#define IB_USER_MAD_ABI_VERSION 5 - -/* - * Make sure that all structs defined in this file remain laid out so - * that they pack the same way on 32-bit and 64-bit architectures (to - * avoid incompatibility between 32-bit userspace and 64-bit kernels). - */ - -/** - * ib_user_mad_hdr - MAD packet header - * @id - ID of agent MAD received with/to be sent with - * @status - 0 on successful receive, ETIMEDOUT if no response - * received (transaction ID in data[] will be set to TID of original - * request) (ignored on send) - * @timeout_ms - Milliseconds to wait for response (unset on receive) - * @retries - Number of automatic retries to attempt - * @qpn - Remote QP number received from/to be sent to - * @qkey - Remote Q_Key to be sent with (unset on receive) - * @lid - Remote lid received from/to be sent to - * @sl - Service level received with/to be sent with - * @path_bits - Local path bits received with/to be sent with - * @grh_present - If set, GRH was received/should be sent - * @gid_index - Local GID index to send with (unset on receive) - * @hop_limit - Hop limit in GRH - * @traffic_class - Traffic class in GRH - * @gid - Remote GID in GRH - * @flow_label - Flow label in GRH - */ -struct ib_user_mad_hdr { - __u32 id; - __u32 status; - __u32 timeout_ms; - __u32 retries; - __u32 length; - __be32 qpn; - __be32 qkey; - __be16 lid; - __u8 sl; - __u8 path_bits; - __u8 grh_present; - __u8 gid_index; - __u8 hop_limit; - __u8 traffic_class; - __u8 gid[16]; - __be32 flow_label; -}; - -/** - * ib_user_mad - MAD packet - * @hdr - MAD packet header - * @data - Contents of MAD - * - */ -struct ib_user_mad { - struct ib_user_mad_hdr hdr; - __u8 data[0]; -}; - -/** - * ib_user_mad_reg_req - MAD registration request - * @id - Set by the kernel; used to identify agent in future requests. - * @qpn - Queue pair number; must be 0 or 1. - * @method_mask - The caller will receive unsolicited MADs for any method - * where @method_mask = 1. - * @mgmt_class - Indicates which management class of MADs should be receive - * by the caller. This field is only required if the user wishes to - * receive unsolicited MADs, otherwise it should be 0. - * @mgmt_class_version - Indicates which version of MADs for the given - * management class to receive. - * @oui: Indicates IEEE OUI when mgmt_class is a vendor class - * in the range from 0x30 to 0x4f. Otherwise not used. - * @rmpp_version: If set, indicates the RMPP version used. - * - */ -struct ib_user_mad_reg_req { - __u32 id; - __u32 method_mask[4]; - __u8 qpn; - __u8 mgmt_class; - __u8 mgmt_class_version; - __u8 oui[3]; - __u8 rmpp_version; -}; - -#define IB_IOCTL_MAGIC 0x1b - -#define IB_USER_MAD_REGISTER_AGENT _IOWR(IB_IOCTL_MAGIC, 1, \ - struct ib_user_mad_reg_req) - -#define IB_USER_MAD_UNREGISTER_AGENT _IOW(IB_IOCTL_MAGIC, 2, __u32) - -#endif /* IB_USER_MAD_H */ diff --git a/include/rdma/ib_user_verbs.h b/include/rdma/ib_user_verbs.h deleted file mode 100644 index 5ff1490c08d..00000000000 --- a/include/rdma/ib_user_verbs.h +++ /dev/null @@ -1,574 +0,0 @@ -/* - * Copyright (c) 2005 Topspin Communications. All rights reserved. - * Copyright (c) 2005 Cisco Systems. All rights reserved. - * Copyright (c) 2005 PathScale, 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. - * - * $Id: ib_user_verbs.h 2708 2005-06-24 17:27:21Z roland $ - */ - -#ifndef IB_USER_VERBS_H -#define IB_USER_VERBS_H - -#include <linux/types.h> - -/* - * Increment this value if any changes that break userspace ABI - * compatibility are made. - */ -#define IB_USER_VERBS_ABI_VERSION 4 - -enum { - IB_USER_VERBS_CMD_GET_CONTEXT, - IB_USER_VERBS_CMD_QUERY_DEVICE, - IB_USER_VERBS_CMD_QUERY_PORT, - IB_USER_VERBS_CMD_ALLOC_PD, - IB_USER_VERBS_CMD_DEALLOC_PD, - IB_USER_VERBS_CMD_CREATE_AH, - IB_USER_VERBS_CMD_MODIFY_AH, - IB_USER_VERBS_CMD_QUERY_AH, - IB_USER_VERBS_CMD_DESTROY_AH, - IB_USER_VERBS_CMD_REG_MR, - IB_USER_VERBS_CMD_REG_SMR, - IB_USER_VERBS_CMD_REREG_MR, - IB_USER_VERBS_CMD_QUERY_MR, - IB_USER_VERBS_CMD_DEREG_MR, - IB_USER_VERBS_CMD_ALLOC_MW, - IB_USER_VERBS_CMD_BIND_MW, - IB_USER_VERBS_CMD_DEALLOC_MW, - IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL, - IB_USER_VERBS_CMD_CREATE_CQ, - IB_USER_VERBS_CMD_RESIZE_CQ, - IB_USER_VERBS_CMD_DESTROY_CQ, - IB_USER_VERBS_CMD_POLL_CQ, - IB_USER_VERBS_CMD_PEEK_CQ, - IB_USER_VERBS_CMD_REQ_NOTIFY_CQ, - IB_USER_VERBS_CMD_CREATE_QP, - IB_USER_VERBS_CMD_QUERY_QP, - IB_USER_VERBS_CMD_MODIFY_QP, - IB_USER_VERBS_CMD_DESTROY_QP, - IB_USER_VERBS_CMD_POST_SEND, - IB_USER_VERBS_CMD_POST_RECV, - IB_USER_VERBS_CMD_ATTACH_MCAST, - IB_USER_VERBS_CMD_DETACH_MCAST, - IB_USER_VERBS_CMD_CREATE_SRQ, - IB_USER_VERBS_CMD_MODIFY_SRQ, - IB_USER_VERBS_CMD_QUERY_SRQ, - IB_USER_VERBS_CMD_DESTROY_SRQ, - IB_USER_VERBS_CMD_POST_SRQ_RECV -}; - -/* - * Make sure that all structs defined in this file remain laid out so - * that they pack the same way on 32-bit and 64-bit architectures (to - * avoid incompatibility between 32-bit userspace and 64-bit kernels). - * Specifically: - * - Do not use pointer types -- pass pointers in __u64 instead. - * - Make sure that any structure larger than 4 bytes is padded to a - * multiple of 8 bytes. Otherwise the structure size will be - * different between 32-bit and 64-bit architectures. - */ - -struct ib_uverbs_async_event_desc { - __u64 element; - __u32 event_type; /* enum ib_event_type */ - __u32 reserved; -}; - -struct ib_uverbs_comp_event_desc { - __u64 cq_handle; -}; - -/* - * All commands from userspace should start with a __u32 command field - * followed by __u16 in_words and out_words fields (which give the - * length of the command block and response buffer if any in 32-bit - * words). The kernel driver will read these fields first and read - * the rest of the command struct based on these value. - */ - -struct ib_uverbs_cmd_hdr { - __u32 command; - __u16 in_words; - __u16 out_words; -}; - -struct ib_uverbs_get_context { - __u64 response; - __u64 driver_data[0]; -}; - -struct ib_uverbs_get_context_resp { - __u32 async_fd; - __u32 num_comp_vectors; -}; - -struct ib_uverbs_query_device { - __u64 response; - __u64 driver_data[0]; -}; - -struct ib_uverbs_query_device_resp { - __u64 fw_ver; - __be64 node_guid; - __be64 sys_image_guid; - __u64 max_mr_size; - __u64 page_size_cap; - __u32 vendor_id; - __u32 vendor_part_id; - __u32 hw_ver; - __u32 max_qp; - __u32 max_qp_wr; - __u32 device_cap_flags; - __u32 max_sge; - __u32 max_sge_rd; - __u32 max_cq; - __u32 max_cqe; - __u32 max_mr; - __u32 max_pd; - __u32 max_qp_rd_atom; - __u32 max_ee_rd_atom; - __u32 max_res_rd_atom; - __u32 max_qp_init_rd_atom; - __u32 max_ee_init_rd_atom; - __u32 atomic_cap; - __u32 max_ee; - __u32 max_rdd; - __u32 max_mw; - __u32 max_raw_ipv6_qp; - __u32 max_raw_ethy_qp; - __u32 max_mcast_grp; - __u32 max_mcast_qp_attach; - __u32 max_total_mcast_qp_attach; - __u32 max_ah; - __u32 max_fmr; - __u32 max_map_per_fmr; - __u32 max_srq; - __u32 max_srq_wr; - __u32 max_srq_sge; - __u16 max_pkeys; - __u8 local_ca_ack_delay; - __u8 phys_port_cnt; - __u8 reserved[4]; -}; - -struct ib_uverbs_query_port { - __u64 response; - __u8 port_num; - __u8 reserved[7]; - __u64 driver_data[0]; -}; - -struct ib_uverbs_query_port_resp { - __u32 port_cap_flags; - __u32 max_msg_sz; - __u32 bad_pkey_cntr; - __u32 qkey_viol_cntr; - __u32 gid_tbl_len; - __u16 pkey_tbl_len; - __u16 lid; - __u16 sm_lid; - __u8 state; - __u8 max_mtu; - __u8 active_mtu; - __u8 lmc; - __u8 max_vl_num; - __u8 sm_sl; - __u8 subnet_timeout; - __u8 init_type_reply; - __u8 active_width; - __u8 active_speed; - __u8 phys_state; - __u8 reserved[3]; -}; - -struct ib_uverbs_alloc_pd { - __u64 response; - __u64 driver_data[0]; -}; - -struct ib_uverbs_alloc_pd_resp { - __u32 pd_handle; -}; - -struct ib_uverbs_dealloc_pd { - __u32 pd_handle; -}; - -struct ib_uverbs_reg_mr { - __u64 response; - __u64 start; - __u64 length; - __u64 hca_va; - __u32 pd_handle; - __u32 access_flags; - __u64 driver_data[0]; -}; - -struct ib_uverbs_reg_mr_resp { - __u32 mr_handle; - __u32 lkey; - __u32 rkey; -}; - -struct ib_uverbs_dereg_mr { - __u32 mr_handle; -}; - -struct ib_uverbs_create_comp_channel { - __u64 response; -}; - -struct ib_uverbs_create_comp_channel_resp { - __u32 fd; -}; - -struct ib_uverbs_create_cq { - __u64 response; - __u64 user_handle; - __u32 cqe; - __u32 comp_vector; - __s32 comp_channel; - __u32 reserved; - __u64 driver_data[0]; -}; - -struct ib_uverbs_create_cq_resp { - __u32 cq_handle; - __u32 cqe; -}; - -struct ib_uverbs_poll_cq { - __u64 response; - __u32 cq_handle; - __u32 ne; -}; - -struct ib_uverbs_wc { - __u64 wr_id; - __u32 status; - __u32 opcode; - __u32 vendor_err; - __u32 byte_len; - __u32 imm_data; - __u32 qp_num; - __u32 src_qp; - __u32 wc_flags; - __u16 pkey_index; - __u16 slid; - __u8 sl; - __u8 dlid_path_bits; - __u8 port_num; - __u8 reserved; -}; - -struct ib_uverbs_poll_cq_resp { - __u32 count; - __u32 reserved; - struct ib_uverbs_wc wc[0]; -}; - -struct ib_uverbs_req_notify_cq { - __u32 cq_handle; - __u32 solicited_only; -}; - -struct ib_uverbs_destroy_cq { - __u64 response; - __u32 cq_handle; - __u32 reserved; -}; - -struct ib_uverbs_destroy_cq_resp { - __u32 comp_events_reported; - __u32 async_events_reported; -}; - -struct ib_uverbs_create_qp { - __u64 response; - __u64 user_handle; - __u32 pd_handle; - __u32 send_cq_handle; - __u32 recv_cq_handle; - __u32 srq_handle; - __u32 max_send_wr; - __u32 max_recv_wr; - __u32 max_send_sge; - __u32 max_recv_sge; - __u32 max_inline_data; - __u8 sq_sig_all; - __u8 qp_type; - __u8 is_srq; - __u8 reserved; - __u64 driver_data[0]; -}; - -struct ib_uverbs_create_qp_resp { - __u32 qp_handle; - __u32 qpn; - __u32 max_send_wr; - __u32 max_recv_wr; - __u32 max_send_sge; - __u32 max_recv_sge; - __u32 max_inline_data; -}; - -/* - * This struct needs to remain a multiple of 8 bytes to keep the - * alignment of the modify QP parameters. - */ -struct ib_uverbs_qp_dest { - __u8 dgid[16]; - __u32 flow_label; - __u16 dlid; - __u16 reserved; - __u8 sgid_index; - __u8 hop_limit; - __u8 traffic_class; - __u8 sl; - __u8 src_path_bits; - __u8 static_rate; - __u8 is_global; - __u8 port_num; -}; - -struct ib_uverbs_modify_qp { - struct ib_uverbs_qp_dest dest; - struct ib_uverbs_qp_dest alt_dest; - __u32 qp_handle; - __u32 attr_mask; - __u32 qkey; - __u32 rq_psn; - __u32 sq_psn; - __u32 dest_qp_num; - __u32 qp_access_flags; - __u16 pkey_index; - __u16 alt_pkey_index; - __u8 qp_state; - __u8 cur_qp_state; - __u8 path_mtu; - __u8 path_mig_state; - __u8 en_sqd_async_notify; - __u8 max_rd_atomic; - __u8 max_dest_rd_atomic; - __u8 min_rnr_timer; - __u8 port_num; - __u8 timeout; - __u8 retry_cnt; - __u8 rnr_retry; - __u8 alt_port_num; - __u8 alt_timeout; - __u8 reserved[2]; - __u64 driver_data[0]; -}; - -struct ib_uverbs_modify_qp_resp { -}; - -struct ib_uverbs_destroy_qp { - __u64 response; - __u32 qp_handle; - __u32 reserved; -}; - -struct ib_uverbs_destroy_qp_resp { - __u32 events_reported; -}; - -/* - * The ib_uverbs_sge structure isn't used anywhere, since we assume - * the ib_sge structure is packed the same way on 32-bit and 64-bit - * architectures in both kernel and user space. It's just here to - * document the ABI. - */ -struct ib_uverbs_sge { - __u64 addr; - __u32 length; - __u32 lkey; -}; - -struct ib_uverbs_send_wr { - __u64 wr_id; - __u32 num_sge; - __u32 opcode; - __u32 send_flags; - __u32 imm_data; - union { - struct { - __u64 remote_addr; - __u32 rkey; - __u32 reserved; - } rdma; - struct { - __u64 remote_addr; - __u64 compare_add; - __u64 swap; - __u32 rkey; - __u32 reserved; - } atomic; - struct { - __u32 ah; - __u32 remote_qpn; - __u32 remote_qkey; - __u32 reserved; - } ud; - } wr; -}; - -struct ib_uverbs_post_send { - __u64 response; - __u32 qp_handle; - __u32 wr_count; - __u32 sge_count; - __u32 wqe_size; - struct ib_uverbs_send_wr send_wr[0]; -}; - -struct ib_uverbs_post_send_resp { - __u32 bad_wr; -}; - -struct ib_uverbs_recv_wr { - __u64 wr_id; - __u32 num_sge; - __u32 reserved; -}; - -struct ib_uverbs_post_recv { - __u64 response; - __u32 qp_handle; - __u32 wr_count; - __u32 sge_count; - __u32 wqe_size; - struct ib_uverbs_recv_wr recv_wr[0]; -}; - -struct ib_uverbs_post_recv_resp { - __u32 bad_wr; -}; - -struct ib_uverbs_post_srq_recv { - __u64 response; - __u32 srq_handle; - __u32 wr_count; - __u32 sge_count; - __u32 wqe_size; - struct ib_uverbs_recv_wr recv[0]; -}; - -struct ib_uverbs_post_srq_recv_resp { - __u32 bad_wr; -}; - -struct ib_uverbs_global_route { - __u8 dgid[16]; - __u32 flow_label; - __u8 sgid_index; - __u8 hop_limit; - __u8 traffic_class; - __u8 reserved; -}; - -struct ib_uverbs_ah_attr { - struct ib_uverbs_global_route grh; - __u16 dlid; - __u8 sl; - __u8 src_path_bits; - __u8 static_rate; - __u8 is_global; - __u8 port_num; - __u8 reserved; -}; - -struct ib_uverbs_create_ah { - __u64 response; - __u64 user_handle; - __u32 pd_handle; - __u32 reserved; - struct ib_uverbs_ah_attr attr; -}; - -struct ib_uverbs_create_ah_resp { - __u32 ah_handle; -}; - -struct ib_uverbs_destroy_ah { - __u32 ah_handle; -}; - -struct ib_uverbs_attach_mcast { - __u8 gid[16]; - __u32 qp_handle; - __u16 mlid; - __u16 reserved; - __u64 driver_data[0]; -}; - -struct ib_uverbs_detach_mcast { - __u8 gid[16]; - __u32 qp_handle; - __u16 mlid; - __u16 reserved; - __u64 driver_data[0]; -}; - -struct ib_uverbs_create_srq { - __u64 response; - __u64 user_handle; - __u32 pd_handle; - __u32 max_wr; - __u32 max_sge; - __u32 srq_limit; - __u64 driver_data[0]; -}; - -struct ib_uverbs_create_srq_resp { - __u32 srq_handle; -}; - -struct ib_uverbs_modify_srq { - __u32 srq_handle; - __u32 attr_mask; - __u32 max_wr; - __u32 srq_limit; - __u64 driver_data[0]; -}; - -struct ib_uverbs_destroy_srq { - __u64 response; - __u32 srq_handle; - __u32 reserved; -}; - -struct ib_uverbs_destroy_srq_resp { - __u32 events_reported; -}; - -#endif /* IB_USER_VERBS_H */ diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 22fc886b969..7ccef342f72 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -5,7 +5,7 @@ * 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 Cisco Systems. All rights reserved. + * Copyright (c) 2005, 2006, 2007 Cisco Systems. 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 @@ -34,8 +34,6 @@ * 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. - * - * $Id: ib_verbs.h 1349 2004-12-16 21:09:43Z roland $ */ #if !defined(IB_VERBS_H) @@ -43,11 +41,20 @@ #include <linux/types.h> #include <linux/device.h> - -#include <asm/atomic.h> -#include <asm/scatterlist.h> +#include <linux/mm.h> +#include <linux/dma-mapping.h> +#include <linux/kref.h> +#include <linux/list.h> +#include <linux/rwsem.h> +#include <linux/scatterlist.h> +#include <linux/workqueue.h> +#include <uapi/linux/if_ether.h> + +#include <linux/atomic.h> #include <asm/uaccess.h> +extern struct workqueue_struct *ib_wq; + union ib_gid { u8 raw[16]; struct { @@ -56,10 +63,30 @@ union ib_gid { } global; }; -enum ib_node_type { - IB_NODE_CA = 1, - IB_NODE_SWITCH, - IB_NODE_ROUTER +enum rdma_node_type { + /* IB values map to NodeInfo:NodeType. */ + RDMA_NODE_IB_CA = 1, + RDMA_NODE_IB_SWITCH, + RDMA_NODE_IB_ROUTER, + RDMA_NODE_RNIC, + RDMA_NODE_USNIC, + RDMA_NODE_USNIC_UDP, +}; + +enum rdma_transport_type { + RDMA_TRANSPORT_IB, + RDMA_TRANSPORT_IWARP, + RDMA_TRANSPORT_USNIC, + RDMA_TRANSPORT_USNIC_UDP +}; + +__attribute_const__ enum rdma_transport_type +rdma_node_get_transport(enum rdma_node_type node_type); + +enum rdma_link_layer { + IB_LINK_LAYER_UNSPECIFIED, + IB_LINK_LAYER_INFINIBAND, + IB_LINK_LAYER_ETHERNET, }; enum ib_device_cap_flags { @@ -78,6 +105,36 @@ enum ib_device_cap_flags { IB_DEVICE_RC_RNR_NAK_GEN = (1<<12), IB_DEVICE_SRQ_RESIZE = (1<<13), IB_DEVICE_N_NOTIFY_CQ = (1<<14), + IB_DEVICE_LOCAL_DMA_LKEY = (1<<15), + IB_DEVICE_RESERVED = (1<<16), /* old SEND_W_INV */ + IB_DEVICE_MEM_WINDOW = (1<<17), + /* + * 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 = (1<<18), + IB_DEVICE_UD_TSO = (1<<19), + IB_DEVICE_XRC = (1<<20), + IB_DEVICE_MEM_MGT_EXTENSIONS = (1<<21), + IB_DEVICE_BLOCK_MULTICAST_LOOPBACK = (1<<22), + IB_DEVICE_MEM_WINDOW_TYPE_2A = (1<<23), + IB_DEVICE_MEM_WINDOW_TYPE_2B = (1<<24), + IB_DEVICE_MANAGED_FLOW_STEERING = (1<<29), + IB_DEVICE_SIGNATURE_HANDOVER = (1<<30) +}; + +enum ib_signature_prot_cap { + IB_PROT_T10DIF_TYPE_1 = 1, + IB_PROT_T10DIF_TYPE_2 = 1 << 1, + IB_PROT_T10DIF_TYPE_3 = 1 << 2, +}; + +enum ib_signature_guard_cap { + IB_GUARD_T10DIF_CRC = 1, + IB_GUARD_T10DIF_CSUM = 1 << 1, }; enum ib_atomic_cap { @@ -109,6 +166,7 @@ struct ib_device_attr { 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; @@ -123,8 +181,11 @@ struct ib_device_attr { int max_srq; int max_srq_wr; int max_srq_sge; + unsigned int max_fast_reg_page_list_len; u16 max_pkeys; u8 local_ca_ack_delay; + int sig_prot_cap; + int sig_guard_cap; }; enum ib_mtu { @@ -169,6 +230,7 @@ enum ib_port_cap_flags { IB_PORT_SM_DISABLED = 1 << 10, IB_PORT_SYS_IMAGE_GUID_SUP = 1 << 11, IB_PORT_PKEY_SW_EXT_PORT_TRAP_SUP = 1 << 12, + IB_PORT_EXTENDED_SPEEDS_SUP = 1 << 14, IB_PORT_CM_SUP = 1 << 16, IB_PORT_SNMP_TUNNEL_SUP = 1 << 17, IB_PORT_REINIT_SUP = 1 << 18, @@ -178,7 +240,8 @@ enum ib_port_cap_flags { IB_PORT_CAP_MASK_NOTICE_SUP = 1 << 22, IB_PORT_BOOT_MGMT_SUP = 1 << 23, IB_PORT_LINK_LATENCY_SUP = 1 << 24, - IB_PORT_CLIENT_REG_SUP = 1 << 25 + IB_PORT_CLIENT_REG_SUP = 1 << 25, + IB_PORT_IP_BASED_GIDS = 1 << 26 }; enum ib_port_width { @@ -199,6 +262,66 @@ static inline int ib_width_enum_to_int(enum ib_port_width width) } } +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 +}; + +struct ib_protocol_stats { + /* TBD... */ +}; + +struct iw_protocol_stats { + u64 ipInReceives; + u64 ipInHdrErrors; + u64 ipInTooBigErrors; + u64 ipInNoRoutes; + u64 ipInAddrErrors; + u64 ipInUnknownProtos; + u64 ipInTruncatedPkts; + u64 ipInDiscards; + u64 ipInDelivers; + u64 ipOutForwDatagrams; + u64 ipOutRequests; + u64 ipOutDiscards; + u64 ipOutNoRoutes; + u64 ipReasmTimeout; + u64 ipReasmReqds; + u64 ipReasmOKs; + u64 ipReasmFails; + u64 ipFragOKs; + u64 ipFragFails; + u64 ipFragCreates; + u64 ipInMcastPkts; + u64 ipOutMcastPkts; + u64 ipInBcastPkts; + u64 ipOutBcastPkts; + + u64 tcpRtoAlgorithm; + u64 tcpRtoMin; + u64 tcpRtoMax; + u64 tcpMaxConn; + u64 tcpActiveOpens; + u64 tcpPassiveOpens; + u64 tcpAttemptFails; + u64 tcpEstabResets; + u64 tcpCurrEstab; + u64 tcpInSegs; + u64 tcpOutSegs; + u64 tcpRetransSegs; + u64 tcpInErrs; + u64 tcpOutRsts; +}; + +union rdma_protocol_stats { + struct ib_protocol_stats ib; + struct iw_protocol_stats iw; +}; + struct ib_port_attr { enum ib_port_state state; enum ib_mtu max_mtu; @@ -222,11 +345,13 @@ struct ib_port_attr { }; enum ib_device_modify_flags { - IB_DEVICE_MODIFY_SYS_IMAGE_GUID = 1 + IB_DEVICE_MODIFY_SYS_IMAGE_GUID = 1 << 0, + IB_DEVICE_MODIFY_NODE_DESC = 1 << 1 }; struct ib_device_modify { u64 sys_image_guid; + char node_desc[64]; }; enum ib_port_modify_flags { @@ -258,7 +383,9 @@ enum ib_event_type { IB_EVENT_SM_CHANGE, IB_EVENT_SRQ_ERR, IB_EVENT_SRQ_LIMIT_REACHED, - IB_EVENT_QP_LAST_WQE_REACHED + IB_EVENT_QP_LAST_WQE_REACHED, + IB_EVENT_CLIENT_REREGISTER, + IB_EVENT_GID_CHANGE, }; struct ib_event { @@ -306,12 +433,179 @@ enum { IB_MULTICAST_QPN = 0xffffff }; -#define IB_LID_PERMISSIVE __constant_htons(0xFFFF) +#define IB_LID_PERMISSIVE cpu_to_be16(0xFFFF) 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_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_create_flags { + IB_MR_SIGNATURE_EN = 1, +}; + +/** + * ib_mr_init_attr - Memory region init attributes passed to routine + * ib_create_mr. + * @max_reg_descriptors: max number of registration descriptors that + * may be used with registration work requests. + * @flags: MR creation flags bit mask. + */ +struct ib_mr_init_attr { + int max_reg_descriptors; + u32 flags; +}; + +enum ib_signature_type { + IB_SIG_TYPE_T10_DIF, +}; + +/** + * T10-DIF Signature types + * T10-DIF types are defined by SCSI + * specifications. + */ +enum ib_t10_dif_type { + IB_T10DIF_NONE, + IB_T10DIF_TYPE1, + IB_T10DIF_TYPE2, + IB_T10DIF_TYPE3 +}; + +/** + * Signature T10-DIF block-guard types + * IB_T10DIF_CRC: Corresponds to T10-PI mandated CRC checksum rules. + * IB_T10DIF_CSUM: Corresponds to IP checksum rules. + */ +enum ib_t10_dif_bg_type { + IB_T10DIF_CRC, + IB_T10DIF_CSUM +}; + +/** + * struct ib_t10_dif_domain - Parameters specific for T10-DIF + * domain. + * @type: T10-DIF type (0|1|2|3) + * @bg_type: T10-DIF block guard type (CRC|CSUM) + * @pi_interval: protection information interval. + * @bg: seed of guard computation. + * @app_tag: application tag of guard block + * @ref_tag: initial guard block reference tag. + * @type3_inc_reftag: T10-DIF type 3 does not state + * about the reference tag, it is the user + * choice to increment it or not. + */ +struct ib_t10_dif_domain { + enum ib_t10_dif_type type; + enum ib_t10_dif_bg_type bg_type; + u16 pi_interval; + u16 bg; + u16 app_tag; + u32 ref_tag; + bool type3_inc_reftag; +}; + +/** + * struct ib_sig_domain - Parameters for signature domain + * @sig_type: specific signauture type + * @sig: union of all signature domain attributes that may + * be used to set domain layout. + */ +struct ib_sig_domain { + enum ib_signature_type sig_type; + union { + struct ib_t10_dif_domain dif; + } sig; +}; + +/** + * struct ib_sig_attrs - Parameters for signature handover operation + * @check_mask: bitmask for signature byte check (8 bytes) + * @mem: memory domain layout desciptor. + * @wire: wire domain layout desciptor. + */ +struct ib_sig_attrs { + u8 check_mask; + struct ib_sig_domain mem; + struct ib_sig_domain wire; +}; + +enum ib_sig_err_type { + IB_SIG_BAD_GUARD, + IB_SIG_BAD_REFTAG, + IB_SIG_BAD_APPTAG, +}; + +/** + * struct ib_sig_err - signature error descriptor + */ +struct ib_sig_err { + enum ib_sig_err_type err_type; + u32 expected; + u32 actual; + u64 sig_err_offset; + u32 key; +}; + +enum ib_mr_status_check { + IB_MR_CHECK_SIG_STATUS = 1, +}; + +/** + * struct ib_mr_status - Memory region status container + * + * @fail_status: Bitmask of MR checks status. For each + * failed check a corresponding status bit is set. + * @sig_err: Additional info for IB_MR_CEHCK_SIG_STATUS + * failure. + */ +struct ib_mr_status { + u32 fail_status; + struct ib_sig_err sig_err; +}; + +/** + * 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 ib_ah_attr { struct ib_global_route grh; u16 dlid; @@ -320,6 +614,8 @@ struct ib_ah_attr { u8 static_rate; u8 ah_flags; u8 port_num; + u8 dmac[ETH_ALEN]; + u16 vlan_id; }; enum ib_wc_status { @@ -354,6 +650,11 @@ enum ib_wc_opcode { IB_WC_COMP_SWAP, IB_WC_FETCH_ADD, IB_WC_BIND_MW, + IB_WC_LSO, + IB_WC_LOCAL_INV, + IB_WC_FAST_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). @@ -364,7 +665,11 @@ enum ib_wc_opcode { enum ib_wc_flags { IB_WC_GRH = 1, - IB_WC_WITH_IMM = (1<<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), }; struct ib_wc { @@ -373,8 +678,11 @@ struct ib_wc { enum ib_wc_opcode opcode; u32 vendor_err; u32 byte_len; - __be32 imm_data; - u32 qp_num; + struct ib_qp *qp; + union { + __be32 imm_data; + u32 invalidate_rkey; + } ex; u32 src_qp; int wc_flags; u16 pkey_index; @@ -382,11 +690,20 @@ struct ib_wc { u8 sl; u8 dlid_path_bits; u8 port_num; /* valid only for DR SMPs on switches */ + u8 smac[ETH_ALEN]; + u16 vlan_id; +}; + +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_cq_notify { - IB_CQ_SOLICITED, - IB_CQ_NEXT_COMP +enum ib_srq_type { + IB_SRQT_BASIC, + IB_SRQT_XRC }; enum ib_srq_attr_mask { @@ -404,6 +721,14 @@ 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; + + union { + struct { + struct ib_xrcd *xrcd; + struct ib_cq *cq; + } xrc; + } ext; }; struct ib_qp_cap { @@ -432,21 +757,65 @@ enum ib_qp_type { IB_QPT_UC, IB_QPT_UD, IB_QPT_RAW_IPV6, - IB_QPT_RAW_ETY + IB_QPT_RAW_ETHERTYPE, + IB_QPT_RAW_PACKET = 8, + IB_QPT_XRC_INI = 9, + IB_QPT_XRC_TGT, + IB_QPT_MAX, + /* 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 = 1 << 1, + IB_QP_CREATE_NETIF_QP = 1 << 5, + IB_QP_CREATE_SIGNATURE_EN = 1 << 6, + IB_QP_CREATE_USE_GFP_NOIO = 1 << 7, + /* 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 { 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; + enum ib_qp_create_flags create_flags; u8 port_num; /* special QP types only */ }; +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, @@ -503,7 +872,11 @@ enum ib_qp_attr_mask { 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_DEST_QPN = (1<<20), + IB_QP_SMAC = (1<<21), + IB_QP_ALT_SMAC = (1<<22), + IB_QP_VID = (1<<23), + IB_QP_ALT_VID = (1<<24), }; enum ib_qp_state { @@ -522,6 +895,11 @@ enum ib_mig_state { 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; @@ -548,6 +926,10 @@ struct ib_qp_attr { u8 rnr_retry; u8 alt_port_num; u8 alt_timeout; + u8 smac[ETH_ALEN]; + u8 alt_smac[ETH_ALEN]; + u16 vlan_id; + u16 alt_vlan_id; }; enum ib_wr_opcode { @@ -557,14 +939,41 @@ enum ib_wr_opcode { IB_WR_SEND_WITH_IMM, IB_WR_RDMA_READ, IB_WR_ATOMIC_CMP_AND_SWP, - IB_WR_ATOMIC_FETCH_AND_ADD + IB_WR_ATOMIC_FETCH_AND_ADD, + IB_WR_LSO, + IB_WR_SEND_WITH_INV, + IB_WR_RDMA_READ_WITH_INV, + IB_WR_LOCAL_INV, + IB_WR_FAST_REG_MR, + IB_WR_MASKED_ATOMIC_CMP_AND_SWP, + IB_WR_MASKED_ATOMIC_FETCH_AND_ADD, + IB_WR_BIND_MW, + IB_WR_REG_SIG_MR, + /* 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_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 { @@ -573,6 +982,29 @@ struct ib_sge { u32 lkey; }; +struct ib_fast_reg_page_list { + struct ib_device *device; + u64 *page_list; + unsigned int max_page_list_len; +}; + +/** + * struct ib_mw_bind_info - Parameters for a memory window bind operation. + * @mr: A memory region to bind the memory window to. + * @addr: The address where the memory window should begin. + * @length: The length of the memory window, in bytes. + * @mw_access_flags: Access flags from enum ib_access_flags for the window. + * + * This struct contains the shared parameters for type 1 and type 2 + * memory window bind operations. + */ +struct ib_mw_bind_info { + struct ib_mr *mr; + u64 addr; + u64 length; + int mw_access_flags; +}; + struct ib_send_wr { struct ib_send_wr *next; u64 wr_id; @@ -580,7 +1012,10 @@ struct ib_send_wr { int num_sge; enum ib_wr_opcode opcode; int send_flags; - __be32 imm_data; + union { + __be32 imm_data; + u32 invalidate_rkey; + } ex; union { struct { u64 remote_addr; @@ -590,16 +1025,43 @@ struct ib_send_wr { u64 remote_addr; u64 compare_add; u64 swap; + u64 compare_add_mask; + u64 swap_mask; u32 rkey; } atomic; struct { struct ib_ah *ah; + void *header; + int hlen; + int mss; u32 remote_qpn; u32 remote_qkey; u16 pkey_index; /* valid for GSI only */ u8 port_num; /* valid for DR SMPs on switch only */ } ud; + struct { + u64 iova_start; + struct ib_fast_reg_page_list *page_list; + unsigned int page_shift; + unsigned int page_list_len; + u32 length; + int access_flags; + u32 rkey; + } fast_reg; + struct { + struct ib_mw *mw; + /* The new rkey for the memory window. */ + u32 rkey; + struct ib_mw_bind_info bind_info; + } bind_mw; + struct { + struct ib_sig_attrs *sig_attrs; + struct ib_mr *sig_mr; + int access_flags; + struct ib_sge *prot; + } sig_handover; } wr; + u32 xrc_remote_srq_num; /* XRC TGT QPs only */ }; struct ib_recv_wr { @@ -614,7 +1076,8 @@ enum ib_access_flags { IB_ACCESS_REMOTE_WRITE = (1<<1), IB_ACCESS_REMOTE_READ = (1<<2), IB_ACCESS_REMOTE_ATOMIC = (1<<3), - IB_ACCESS_MW_BIND = (1<<4) + IB_ACCESS_MW_BIND = (1<<4), + IB_ZERO_BASED = (1<<5) }; struct ib_phys_buf { @@ -637,19 +1100,22 @@ enum ib_mr_rereg_flags { IB_MR_REREG_ACCESS = (1<<2) }; +/** + * struct ib_mw_bind - Parameters for a type 1 memory window bind operation. + * @wr_id: Work request id. + * @send_flags: Flags from ib_send_flags enum. + * @bind_info: More parameters of the bind operation. + */ struct ib_mw_bind { - struct ib_mr *mr; - u64 wr_id; - u64 addr; - u32 length; - int send_flags; - int mw_access_flags; + u64 wr_id; + int send_flags; + struct ib_mw_bind_info bind_info; }; struct ib_fmr_attr { int max_pages; int max_maps; - u8 page_size; + u8 page_shift; }; struct ib_ucontext { @@ -661,55 +1127,44 @@ struct ib_ucontext { struct list_head qp_list; struct list_head srq_list; struct list_head ah_list; + struct list_head xrcd_list; + struct list_head rule_list; + int closing; }; struct ib_uobject { u64 user_handle; /* handle given to us by userspace */ struct ib_ucontext *context; /* associated user context */ + void *object; /* containing object */ struct list_head list; /* link to context's list */ - u32 id; /* index into kernel idr */ -}; - -struct ib_umem { - unsigned long user_base; - unsigned long virt_base; - size_t length; - int offset; - int page_size; - int writable; - struct list_head chunk_list; -}; - -struct ib_umem_chunk { - struct list_head list; - int nents; - int nmap; - struct scatterlist page_list[0]; + int id; /* index into kernel idr */ + struct kref ref; + struct rw_semaphore mutex; /* protects .live */ + int live; }; struct ib_udata { - void __user *inbuf; + const void __user *inbuf; void __user *outbuf; size_t inlen; size_t outlen; }; -#define IB_UMEM_MAX_PAGE_CHUNK \ - ((PAGE_SIZE - offsetof(struct ib_umem_chunk, page_list)) / \ - ((void *) &((struct ib_umem_chunk *) 0)->page_list[1] - \ - (void *) &((struct ib_umem_chunk *) 0)->page_list[0])) - -struct ib_umem_object { - struct ib_uobject uobject; - struct ib_umem umem; -}; - struct ib_pd { struct ib_device *device; struct ib_uobject *uobject; atomic_t usecnt; /* count all resources */ }; +struct ib_xrcd { + struct ib_device *device; + atomic_t usecnt; /* count all exposed resources */ + struct inode *inode; + + struct mutex tgt_qp_mutex; + struct list_head tgt_qp_list; +}; + struct ib_ah { struct ib_device *device; struct ib_pd *pd; @@ -723,7 +1178,7 @@ struct ib_cq { struct ib_uobject *uobject; ib_comp_handler comp_handler; void (*event_handler)(struct ib_event *, void *); - void * cq_context; + void *cq_context; int cqe; atomic_t usecnt; /* count number of work queues */ }; @@ -734,7 +1189,16 @@ struct ib_srq { struct ib_uobject *uobject; void (*event_handler)(struct ib_event *, void *); void *srq_context; + enum ib_srq_type srq_type; atomic_t usecnt; + + union { + struct { + struct ib_xrcd *xrcd; + struct ib_cq *cq; + u32 srq_num; + } xrc; + } ext; }; struct ib_qp { @@ -743,6 +1207,12 @@ struct ib_qp { struct ib_cq *send_cq; struct ib_cq *recv_cq; 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_uobject *uobject; void (*event_handler)(struct ib_event *, void *); void *qp_context; @@ -764,6 +1234,7 @@ struct ib_mw { struct ib_pd *pd; struct ib_uobject *uobject; u32 rkey; + enum ib_mw_type type; }; struct ib_fmr { @@ -774,6 +1245,126 @@ struct ib_fmr { u32 rkey; }; +/* 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, + /* L4 headers*/ + IB_FLOW_SPEC_TCP = 0x40, + IB_FLOW_SPEC_UDP = 0x41 +}; +#define IB_FLOW_SPEC_LAYER_MASK 0xF0 +#define IB_FLOW_SPEC_SUPPORT_LAYERS 4 + +/* Flow steering rule priority is set according to it's domain. + * Lower domain value means higher priority. + */ +enum ib_flow_domain { + IB_FLOW_DOMAIN_USER, + IB_FLOW_DOMAIN_ETHTOOL, + IB_FLOW_DOMAIN_RFS, + IB_FLOW_DOMAIN_NIC, + IB_FLOW_DOMAIN_NUM /* Must be last */ +}; + +struct ib_flow_eth_filter { + u8 dst_mac[6]; + u8 src_mac[6]; + __be16 ether_type; + __be16 vlan_tag; +}; + +struct ib_flow_spec_eth { + enum ib_flow_spec_type type; + u16 size; + struct ib_flow_eth_filter val; + struct ib_flow_eth_filter mask; +}; + +struct ib_flow_ib_filter { + __be16 dlid; + __u8 sl; +}; + +struct ib_flow_spec_ib { + enum ib_flow_spec_type type; + u16 size; + struct ib_flow_ib_filter val; + struct ib_flow_ib_filter mask; +}; + +struct ib_flow_ipv4_filter { + __be32 src_ip; + __be32 dst_ip; +}; + +struct ib_flow_spec_ipv4 { + enum ib_flow_spec_type type; + u16 size; + struct ib_flow_ipv4_filter val; + struct ib_flow_ipv4_filter mask; +}; + +struct ib_flow_tcp_udp_filter { + __be16 dst_port; + __be16 src_port; +}; + +struct ib_flow_spec_tcp_udp { + enum ib_flow_spec_type type; + u16 size; + struct ib_flow_tcp_udp_filter val; + struct ib_flow_tcp_udp_filter mask; +}; + +union ib_flow_spec { + struct { + enum ib_flow_spec_type 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_attr { + enum ib_flow_attr_type type; + u16 size; + u16 priority; + u32 flags; + u8 num_of_specs; + u8 port; + /* Following are the optional layers according to user request + * struct ib_flow_spec_xxx + * struct ib_flow_spec_yyy + */ +}; + +struct ib_flow { + struct ib_qp *qp; + struct ib_uobject *uobject; +}; + struct ib_mad; struct ib_grh; @@ -797,7 +1388,49 @@ struct ib_cache { struct ib_event_handler event_handler; struct ib_pkey_cache **pkey_cache; struct ib_gid_cache **gid_cache; -}; + u8 *lmc_cache; +}; + +struct ib_dma_mapping_ops { + int (*mapping_error)(struct ib_device *dev, + u64 dma_addr); + u64 (*map_single)(struct ib_device *dev, + void *ptr, size_t size, + enum dma_data_direction direction); + void (*unmap_single)(struct ib_device *dev, + u64 addr, size_t size, + enum dma_data_direction direction); + u64 (*map_page)(struct ib_device *dev, + struct page *page, unsigned long offset, + size_t size, + enum dma_data_direction direction); + void (*unmap_page)(struct ib_device *dev, + u64 addr, size_t size, + enum dma_data_direction direction); + int (*map_sg)(struct ib_device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction direction); + void (*unmap_sg)(struct ib_device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction direction); + void (*sync_single_for_cpu)(struct ib_device *dev, + u64 dma_handle, + size_t size, + enum dma_data_direction dir); + void (*sync_single_for_device)(struct ib_device *dev, + u64 dma_handle, + size_t size, + enum dma_data_direction dir); + void *(*alloc_coherent)(struct ib_device *dev, + size_t size, + u64 *dma_handle, + gfp_t flag); + void (*free_coherent)(struct ib_device *dev, + size_t size, void *cpu_addr, + u64 dma_handle); +}; + +struct iw_cm_verbs; struct ib_device { struct device *dma_device; @@ -807,19 +1440,27 @@ struct ib_device { struct list_head event_handler_list; spinlock_t event_handler_lock; + spinlock_t client_data_lock; struct list_head core_list; struct list_head client_data_list; - spinlock_t client_data_lock; struct ib_cache cache; + int *pkey_tbl_len; + int *gid_tbl_len; - u32 flags; + int num_comp_vectors; + struct iw_cm_verbs *iwcm; + + int (*get_protocol_stats)(struct ib_device *device, + union rdma_protocol_stats *stats); int (*query_device)(struct ib_device *device, struct ib_device_attr *device_attr); int (*query_port)(struct ib_device *device, u8 port_num, struct ib_port_attr *port_attr); + enum rdma_link_layer (*get_link_layer)(struct ib_device *device, + u8 port_num); int (*query_gid)(struct ib_device *device, u8 port_num, int index, union ib_gid *gid); @@ -852,7 +1493,8 @@ struct ib_device { 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); + 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); @@ -864,7 +1506,8 @@ struct ib_device { struct ib_udata *udata); int (*modify_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr, - int qp_attr_mask); + 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, @@ -877,15 +1520,19 @@ struct ib_device { struct ib_recv_wr *recv_wr, struct ib_recv_wr **bad_recv_wr); struct ib_cq * (*create_cq)(struct ib_device *device, int cqe, + int comp_vector, struct ib_ucontext *context, struct ib_udata *udata); + int (*modify_cq)(struct ib_cq *cq, u16 cq_count, + u16 cq_period); int (*destroy_cq)(struct ib_cq *cq); - int (*resize_cq)(struct ib_cq *cq, int cqe); + int (*resize_cq)(struct ib_cq *cq, int cqe, + struct ib_udata *udata); 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 cq_notify); + enum ib_cq_notify_flags flags); int (*req_ncomp_notif)(struct ib_cq *cq, int wc_cnt); struct ib_mr * (*get_dma_mr)(struct ib_pd *pd, @@ -896,12 +1543,21 @@ struct ib_device { int mr_access_flags, u64 *iova_start); struct ib_mr * (*reg_user_mr)(struct ib_pd *pd, - struct ib_umem *region, + u64 start, u64 length, + u64 virt_addr, int mr_access_flags, struct ib_udata *udata); int (*query_mr)(struct ib_mr *mr, struct ib_mr_attr *mr_attr); int (*dereg_mr)(struct ib_mr *mr); + int (*destroy_mr)(struct ib_mr *mr); + struct ib_mr * (*create_mr)(struct ib_pd *pd, + struct ib_mr_init_attr *mr_init_attr); + struct ib_mr * (*alloc_fast_reg_mr)(struct ib_pd *pd, + int max_page_list_len); + struct ib_fast_reg_page_list * (*alloc_fast_reg_page_list)(struct ib_device *device, + int page_list_len); + void (*free_fast_reg_page_list)(struct ib_fast_reg_page_list *page_list); int (*rereg_phys_mr)(struct ib_mr *mr, int mr_rereg_mask, struct ib_pd *pd, @@ -909,7 +1565,8 @@ struct ib_device { int num_phys_buf, int mr_access_flags, u64 *iova_start); - struct ib_mw * (*alloc_mw)(struct ib_pd *pd); + struct ib_mw * (*alloc_mw)(struct ib_pd *pd, + enum ib_mw_type type); int (*bind_mw)(struct ib_qp *qp, struct ib_mw *mw, struct ib_mw_bind *mw_bind); @@ -935,10 +1592,23 @@ struct ib_device { struct ib_grh *in_grh, struct ib_mad *in_mad, struct ib_mad *out_mad); + struct ib_xrcd * (*alloc_xrcd)(struct ib_device *device, + struct ib_ucontext *ucontext, + struct ib_udata *udata); + int (*dealloc_xrcd)(struct ib_xrcd *xrcd); + struct ib_flow * (*create_flow)(struct ib_qp *qp, + struct ib_flow_attr + *flow_attr, + int domain); + int (*destroy_flow)(struct ib_flow *flow_id); + int (*check_mr_status)(struct ib_mr *mr, u32 check_mask, + struct ib_mr_status *mr_status); + + struct ib_dma_mapping_ops *dma_ops; struct module *owner; - struct class_device class_dev; - struct kobject ports_parent; + struct device dev; + struct kobject *ports_parent; struct list_head port_list; enum { @@ -947,10 +1617,13 @@ struct ib_device { IB_DEV_UNREGISTERED } reg_state; - u64 uverbs_cmd_mask; int uverbs_abi_ver; + u64 uverbs_cmd_mask; + u64 uverbs_ex_cmd_mask; + char node_desc[64]; __be64 node_guid; + u32 local_dma_lkey; u8 node_type; u8 phys_port_cnt; }; @@ -966,7 +1639,9 @@ struct ib_client { struct ib_device *ib_alloc_device(size_t size); void ib_dealloc_device(struct ib_device *device); -int ib_register_device (struct ib_device *device); +int ib_register_device(struct ib_device *device, + int (*port_callback)(struct ib_device *, + u8, struct kobject *)); void ib_unregister_device(struct ib_device *device); int ib_register_client (struct ib_client *client); @@ -986,6 +1661,26 @@ 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; } +/** + * 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 + * @ll : link layer of port + * + * 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. + */ +int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state, + enum ib_qp_type type, enum ib_qp_attr_mask mask, + enum rdma_link_layer ll); + int ib_register_event_handler (struct ib_event_handler *event_handler); int ib_unregister_event_handler(struct ib_event_handler *event_handler); void ib_dispatch_event(struct ib_event *event); @@ -996,6 +1691,9 @@ int ib_query_device(struct ib_device *device, int ib_query_port(struct ib_device *device, u8 port_num, struct ib_port_attr *port_attr); +enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, + u8 port_num); + int ib_query_gid(struct ib_device *device, u8 port_num, int index, union ib_gid *gid); @@ -1010,6 +1708,12 @@ int ib_modify_port(struct ib_device *device, u8 port_num, int port_modify_mask, struct ib_port_modify *port_modify); +int ib_find_gid(struct ib_device *device, union ib_gid *gid, + u8 *port_num, u16 *index); + +int ib_find_pkey(struct ib_device *device, + u8 port_num, u16 pkey, u16 *index); + /** * ib_alloc_pd - Allocates an unused protection domain. * @device: The device on which to allocate the protection domain. @@ -1036,6 +1740,20 @@ int ib_dealloc_pd(struct ib_pd *pd); struct ib_ah *ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr); /** + * ib_init_ah_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. + * @wc: Work completion associated with the received message. + * @grh: References the received global route header. This parameter is + * ignored unless the work completion indicates that the GRH is valid. + * @ah_attr: Returned attributes that can be used when creating an address + * handle for replying to the message. + */ +int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc, + struct ib_grh *grh, struct ib_ah_attr *ah_attr); + +/** * ib_create_ah_from_wc - Creates an address handle associated with the * sender of the specified work completion. * @pd: The protection domain associated with the address handle. @@ -1078,7 +1796,9 @@ int ib_destroy_ah(struct ib_ah *ah); * ib_create_srq - Creates a SRQ associated with the specified protection * domain. * @pd: The protection domain associated with the SRQ. - * @srq_init_attr: A list of initial attributes required to create the SRQ. + * @srq_init_attr: A list of initial attributes required to create the + * SRQ. If SRQ creation succeeds, then the attributes are updated to + * the actual capabilities of the created SRQ. * * srq_attr->max_wr and srq_attr->max_sge are read the determine the * requested size of the SRQ, and set to the actual values allocated @@ -1137,7 +1857,9 @@ static inline int ib_post_srq_recv(struct ib_srq *srq, * ib_create_qp - Creates a QP associated with the specified protection * domain. * @pd: The protection domain associated with the QP. - * @qp_init_attr: A list of initial attributes required to create the QP. + * @qp_init_attr: A list of initial attributes required to create the + * QP. If QP creation succeeds, then the attributes are updated to + * the actual capabilities of the created QP. */ struct ib_qp *ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr); @@ -1178,12 +1900,36 @@ int ib_query_qp(struct ib_qp *qp, int ib_destroy_qp(struct ib_qp *qp); /** + * ib_open_qp - Obtain a reference to an existing sharable QP. + * @xrcd - XRC domain + * @qp_open_attr: Attributes identifying the QP to open. + * + * Returns a reference to a sharable QP. + */ +struct ib_qp *ib_open_qp(struct ib_xrcd *xrcd, + struct ib_qp_open_attr *qp_open_attr); + +/** + * ib_close_qp - Release an external reference to a QP. + * @qp: The QP handle to release + * + * The opened QP handle is released by the caller. The underlying + * shared QP is not destroyed until all internal references are released. + */ +int ib_close_qp(struct ib_qp *qp); + +/** * ib_post_send - Posts a list of work requests to the send queue of * the specified QP. * @qp: The QP to post the work request on. * @send_wr: A list of work requests to post on the send queue. * @bad_send_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. + * + * While IBA Vol. 1 section 11.4.1.1 specifies that if an immediate + * error is returned, the QP state shall not be affected, + * ib_post_send() will return an immediate error after queueing any + * earlier work requests in the list. */ static inline int ib_post_send(struct ib_qp *qp, struct ib_send_wr *send_wr, @@ -1217,13 +1963,15 @@ static inline int ib_post_recv(struct ib_qp *qp, * @cq_context: Context associated with the CQ returned to the user via * the associated completion and event handlers. * @cqe: The minimum size of the CQ. + * @comp_vector - Completion vector used to signal completion events. + * Must be >= 0 and < context->num_comp_vectors. * * Users can examine the cq structure to determine the actual CQ size. */ struct ib_cq *ib_create_cq(struct ib_device *device, ib_comp_handler comp_handler, void (*event_handler)(struct ib_event *, void *), - void *cq_context, int cqe); + void *cq_context, int cqe, int comp_vector); /** * ib_resize_cq - Modifies the capacity of the CQ. @@ -1235,6 +1983,15 @@ 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 + * @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); + +/** * ib_destroy_cq - Destroys the specified CQ. * @cq: The CQ to destroy. */ @@ -1273,14 +2030,34 @@ 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. - * @cq_notify: If set to %IB_CQ_SOLICITED, completion notification will - * occur on the next solicited event. If set to %IB_CQ_NEXT_COMP, - * notification will occur on the next completion. + * @flags: + * Must contain exactly one of %IB_CQ_SOLICITED or %IB_CQ_NEXT_COMP + * to request an event on the next solicited event or next work + * completion at any type, respectively. %IB_CQ_REPORT_MISSED_EVENTS + * may also be |ed in to request a hint about missed events, as + * described below. + * + * Return Value: + * < 0 means an error occurred while requesting notification + * == 0 means notification was requested successfully, and if + * IB_CQ_REPORT_MISSED_EVENTS was passed in, then no events + * were missed and it is safe to wait for another event. In + * this case is it guaranteed that any work completions added + * to the CQ since the last CQ poll will trigger a completion + * notification event. + * > 0 is only returned if IB_CQ_REPORT_MISSED_EVENTS was passed + * in. It means that the consumer must poll the CQ again to + * make sure it is empty to avoid missing an event because of a + * race between requesting notification and an entry being + * added to the CQ. This return value means it is possible + * (but not guaranteed) that a work completion has been added + * to the CQ since the last poll without triggering a + * completion notification event. */ static inline int ib_req_notify_cq(struct ib_cq *cq, - enum ib_cq_notify cq_notify) + enum ib_cq_notify_flags flags) { - return cq->device->req_notify_cq(cq, cq_notify); + return cq->device->req_notify_cq(cq, flags); } /** @@ -1302,10 +2079,266 @@ static inline int ib_req_ncomp_notif(struct ib_cq *cq, int wc_cnt) * usable for DMA. * @pd: The protection domain associated with the memory region. * @mr_access_flags: Specifies the memory access rights. + * + * Note that the ib_dma_*() functions defined below must be used + * to create/destroy addresses used with the Lkey or Rkey returned + * by ib_get_dma_mr(). */ struct ib_mr *ib_get_dma_mr(struct ib_pd *pd, int mr_access_flags); /** + * ib_dma_mapping_error - check a DMA addr for error + * @dev: The device for which the dma_addr was created + * @dma_addr: The DMA address to check + */ +static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr) +{ + if (dev->dma_ops) + return dev->dma_ops->mapping_error(dev, dma_addr); + return dma_mapping_error(dev->dma_device, dma_addr); +} + +/** + * ib_dma_map_single - Map a kernel virtual address to DMA address + * @dev: The device for which the dma_addr is to be created + * @cpu_addr: The kernel virtual address + * @size: The size of the region in bytes + * @direction: The direction of the DMA + */ +static inline u64 ib_dma_map_single(struct ib_device *dev, + void *cpu_addr, size_t size, + enum dma_data_direction direction) +{ + if (dev->dma_ops) + return dev->dma_ops->map_single(dev, cpu_addr, size, direction); + return dma_map_single(dev->dma_device, cpu_addr, size, direction); +} + +/** + * ib_dma_unmap_single - Destroy a mapping created by ib_dma_map_single() + * @dev: The device for which the DMA address was created + * @addr: The DMA address + * @size: The size of the region in bytes + * @direction: The direction of the DMA + */ +static inline void ib_dma_unmap_single(struct ib_device *dev, + u64 addr, size_t size, + enum dma_data_direction direction) +{ + if (dev->dma_ops) + dev->dma_ops->unmap_single(dev, addr, size, direction); + else + dma_unmap_single(dev->dma_device, addr, size, direction); +} + +static inline u64 ib_dma_map_single_attrs(struct ib_device *dev, + void *cpu_addr, size_t size, + enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + return dma_map_single_attrs(dev->dma_device, cpu_addr, size, + direction, attrs); +} + +static inline void ib_dma_unmap_single_attrs(struct ib_device *dev, + u64 addr, size_t size, + enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + return dma_unmap_single_attrs(dev->dma_device, addr, size, + direction, attrs); +} + +/** + * ib_dma_map_page - Map a physical page to DMA address + * @dev: The device for which the dma_addr is to be created + * @page: The page to be mapped + * @offset: The offset within the page + * @size: The size of the region in bytes + * @direction: The direction of the DMA + */ +static inline u64 ib_dma_map_page(struct ib_device *dev, + struct page *page, + unsigned long offset, + size_t size, + enum dma_data_direction direction) +{ + if (dev->dma_ops) + return dev->dma_ops->map_page(dev, page, offset, size, direction); + return dma_map_page(dev->dma_device, page, offset, size, direction); +} + +/** + * ib_dma_unmap_page - Destroy a mapping created by ib_dma_map_page() + * @dev: The device for which the DMA address was created + * @addr: The DMA address + * @size: The size of the region in bytes + * @direction: The direction of the DMA + */ +static inline void ib_dma_unmap_page(struct ib_device *dev, + u64 addr, size_t size, + enum dma_data_direction direction) +{ + if (dev->dma_ops) + dev->dma_ops->unmap_page(dev, addr, size, direction); + else + dma_unmap_page(dev->dma_device, addr, size, direction); +} + +/** + * ib_dma_map_sg - Map a scatter/gather list to DMA addresses + * @dev: The device for which the DMA addresses are to be created + * @sg: The array of scatter/gather entries + * @nents: The number of scatter/gather entries + * @direction: The direction of the DMA + */ +static inline int ib_dma_map_sg(struct ib_device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction direction) +{ + if (dev->dma_ops) + return dev->dma_ops->map_sg(dev, sg, nents, direction); + return dma_map_sg(dev->dma_device, sg, nents, direction); +} + +/** + * ib_dma_unmap_sg - Unmap a scatter/gather list of DMA addresses + * @dev: The device for which the DMA addresses were created + * @sg: The array of scatter/gather entries + * @nents: The number of scatter/gather entries + * @direction: The direction of the DMA + */ +static inline void ib_dma_unmap_sg(struct ib_device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction direction) +{ + if (dev->dma_ops) + dev->dma_ops->unmap_sg(dev, sg, nents, direction); + else + dma_unmap_sg(dev->dma_device, sg, nents, direction); +} + +static inline int ib_dma_map_sg_attrs(struct ib_device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + return dma_map_sg_attrs(dev->dma_device, sg, nents, direction, attrs); +} + +static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, attrs); +} +/** + * ib_sg_dma_address - Return the DMA address from a scatter/gather entry + * @dev: The device for which the DMA addresses were created + * @sg: The scatter/gather entry + * + * Note: this function is obsolete. To do: change all occurrences of + * ib_sg_dma_address() into sg_dma_address(). + */ +static inline u64 ib_sg_dma_address(struct ib_device *dev, + struct scatterlist *sg) +{ + return sg_dma_address(sg); +} + +/** + * ib_sg_dma_len - Return the DMA length from a scatter/gather entry + * @dev: The device for which the DMA addresses were created + * @sg: The scatter/gather entry + * + * Note: this function is obsolete. To do: change all occurrences of + * ib_sg_dma_len() into sg_dma_len(). + */ +static inline unsigned int ib_sg_dma_len(struct ib_device *dev, + struct scatterlist *sg) +{ + return sg_dma_len(sg); +} + +/** + * ib_dma_sync_single_for_cpu - Prepare DMA region to be accessed by CPU + * @dev: The device for which the DMA address was created + * @addr: The DMA address + * @size: The size of the region in bytes + * @dir: The direction of the DMA + */ +static inline void ib_dma_sync_single_for_cpu(struct ib_device *dev, + u64 addr, + size_t size, + enum dma_data_direction dir) +{ + if (dev->dma_ops) + dev->dma_ops->sync_single_for_cpu(dev, addr, size, dir); + else + dma_sync_single_for_cpu(dev->dma_device, addr, size, dir); +} + +/** + * ib_dma_sync_single_for_device - Prepare DMA region to be accessed by device + * @dev: The device for which the DMA address was created + * @addr: The DMA address + * @size: The size of the region in bytes + * @dir: The direction of the DMA + */ +static inline void ib_dma_sync_single_for_device(struct ib_device *dev, + u64 addr, + size_t size, + enum dma_data_direction dir) +{ + if (dev->dma_ops) + dev->dma_ops->sync_single_for_device(dev, addr, size, dir); + else + dma_sync_single_for_device(dev->dma_device, addr, size, dir); +} + +/** + * ib_dma_alloc_coherent - Allocate memory and map it for DMA + * @dev: The device for which the DMA address is requested + * @size: The size of the region to allocate in bytes + * @dma_handle: A pointer for returning the DMA address of the region + * @flag: memory allocator flags + */ +static inline void *ib_dma_alloc_coherent(struct ib_device *dev, + size_t size, + u64 *dma_handle, + gfp_t flag) +{ + if (dev->dma_ops) + return dev->dma_ops->alloc_coherent(dev, size, dma_handle, flag); + else { + dma_addr_t handle; + void *ret; + + ret = dma_alloc_coherent(dev->dma_device, size, &handle, flag); + *dma_handle = handle; + return ret; + } +} + +/** + * ib_dma_free_coherent - Free memory allocated by ib_dma_alloc_coherent() + * @dev: The device for which the DMA addresses were allocated + * @size: The size of the region + * @cpu_addr: the address returned by ib_dma_alloc_coherent() + * @dma_handle: the DMA address returned by ib_dma_alloc_coherent() + */ +static inline void ib_dma_free_coherent(struct ib_device *dev, + size_t size, void *cpu_addr, + u64 dma_handle) +{ + if (dev->dma_ops) + dev->dma_ops->free_coherent(dev, size, cpu_addr, dma_handle); + else + dma_free_coherent(dev->dma_device, size, cpu_addr, dma_handle); +} + +/** * ib_reg_phys_mr - Prepares a virtually addressed memory region for use * by an HCA. * @pd: The protection domain associated assigned to the registered region. @@ -1362,14 +2395,95 @@ int ib_query_mr(struct ib_mr *mr, struct ib_mr_attr *mr_attr); * ib_dereg_mr - Deregisters a memory region and removes it from the * HCA translation table. * @mr: The memory region to deregister. + * + * This function can fail, if the memory region has memory windows bound to it. */ int ib_dereg_mr(struct ib_mr *mr); + +/** + * ib_create_mr - Allocates a memory region that may be used for + * signature handover operations. + * @pd: The protection domain associated with the region. + * @mr_init_attr: memory region init attributes. + */ +struct ib_mr *ib_create_mr(struct ib_pd *pd, + struct ib_mr_init_attr *mr_init_attr); + +/** + * ib_destroy_mr - Destroys a memory region that was created using + * ib_create_mr and removes it from HW translation tables. + * @mr: The memory region to destroy. + * + * This function can fail, if the memory region has memory windows bound to it. + */ +int ib_destroy_mr(struct ib_mr *mr); + +/** + * ib_alloc_fast_reg_mr - Allocates memory region usable with the + * IB_WR_FAST_REG_MR send work request. + * @pd: The protection domain associated with the region. + * @max_page_list_len: requested max physical buffer list length to be + * used with fast register work requests for this MR. + */ +struct ib_mr *ib_alloc_fast_reg_mr(struct ib_pd *pd, int max_page_list_len); + +/** + * ib_alloc_fast_reg_page_list - Allocates a page list array + * @device - ib device pointer. + * @page_list_len - size of the page list array to be allocated. + * + * This allocates and returns a struct ib_fast_reg_page_list * and a + * page_list array that is at least page_list_len in size. The actual + * size is returned in max_page_list_len. The caller is responsible + * for initializing the contents of the page_list array before posting + * a send work request with the IB_WC_FAST_REG_MR opcode. + * + * The page_list array entries must be translated using one of the + * ib_dma_*() functions just like the addresses passed to + * ib_map_phys_fmr(). Once the ib_post_send() is issued, the struct + * ib_fast_reg_page_list must not be modified by the caller until the + * IB_WC_FAST_REG_MR work request completes. + */ +struct ib_fast_reg_page_list *ib_alloc_fast_reg_page_list( + struct ib_device *device, int page_list_len); + +/** + * ib_free_fast_reg_page_list - Deallocates a previously allocated + * page list array. + * @page_list - struct ib_fast_reg_page_list pointer to be deallocated. + */ +void ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list); + +/** + * ib_update_fast_reg_key - updates the key portion of the fast_reg MR + * R_Key and L_Key. + * @mr - struct ib_mr pointer to be updated. + * @newkey - new key to be used. + */ +static inline void ib_update_fast_reg_key(struct ib_mr *mr, u8 newkey) +{ + mr->lkey = (mr->lkey & 0xffffff00) | newkey; + mr->rkey = (mr->rkey & 0xffffff00) | newkey; +} + +/** + * ib_inc_rkey - increments the key portion of the given rkey. Can be used + * for calculating a new rkey for type 2 memory windows. + * @rkey - the rkey to increment. + */ +static inline u32 ib_inc_rkey(u32 rkey) +{ + const u32 mask = 0x000000ff; + return ((rkey + 1) & mask) | (rkey & ~mask); +} + /** * ib_alloc_mw - Allocates a memory window. * @pd: The protection domain associated with the memory window. + * @type: The type of the memory window (1 or 2). */ -struct ib_mw *ib_alloc_mw(struct ib_pd *pd); +struct ib_mw *ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type); /** * ib_bind_mw - Posts a work request to the send queue of the specified @@ -1379,6 +2493,10 @@ struct ib_mw *ib_alloc_mw(struct ib_pd *pd); * @mw: The memory window to bind. * @mw_bind: Specifies information about the memory window, including * its address range, remote access rights, and associated memory region. + * + * If there is no immediate error, the function will update the rkey member + * of the mw parameter to its new value. The bind operation can still fail + * asynchronously. */ static inline int ib_bind_mw(struct ib_qp *qp, struct ib_mw *mw, @@ -1457,4 +2575,48 @@ int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid); */ 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. + */ +struct ib_xrcd *ib_alloc_xrcd(struct ib_device *device); + +/** + * ib_dealloc_xrcd - Deallocates an XRC domain. + * @xrcd: The XRC domain to deallocate. + */ +int ib_dealloc_xrcd(struct ib_xrcd *xrcd); + +struct ib_flow *ib_create_flow(struct ib_qp *qp, + struct ib_flow_attr *flow_attr, int domain); +int ib_destroy_flow(struct ib_flow *flow_id); + +static inline int ib_check_mr_access(int flags) +{ + /* + * Local write permission is required if remote write or + * remote atomic permission is also requested. + */ + if (flags & (IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_REMOTE_WRITE) && + !(flags & IB_ACCESS_LOCAL_WRITE)) + return -EINVAL; + + return 0; +} + +/** + * ib_check_mr_status: lightweight check of MR status. + * This routine may provide status checks on a selected + * ib_mr. first use is for signature status check. + * + * @mr: A memory region. + * @check_mask: Bitmask of which checks to perform from + * ib_mr_status_check enumeration. + * @mr_status: The container of relevant status checks. + * failed checks will be indicated in the status bitmask + * and the relevant info shall be in the error item. + */ +int ib_check_mr_status(struct ib_mr *mr, u32 check_mask, + struct ib_mr_status *mr_status); + #endif /* IB_VERBS_H */ diff --git a/include/rdma/iw_cm.h b/include/rdma/iw_cm.h new file mode 100644 index 00000000000..1017e0bdf8b --- /dev/null +++ b/include/rdma/iw_cm.h @@ -0,0 +1,251 @@ +/* + * Copyright (c) 2005 Network Appliance, Inc. All rights reserved. + * Copyright (c) 2005 Open Grid Computing, 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 IW_CM_H +#define IW_CM_H + +#include <linux/in.h> +#include <rdma/ib_cm.h> + +struct iw_cm_id; + +enum iw_cm_event_type { + IW_CM_EVENT_CONNECT_REQUEST = 1, /* connect request received */ + IW_CM_EVENT_CONNECT_REPLY, /* reply from active connect request */ + IW_CM_EVENT_ESTABLISHED, /* passive side accept successful */ + IW_CM_EVENT_DISCONNECT, /* orderly shutdown */ + IW_CM_EVENT_CLOSE /* close complete */ +}; + +struct iw_cm_event { + enum iw_cm_event_type event; + int status; + struct sockaddr_storage local_addr; + struct sockaddr_storage remote_addr; + void *private_data; + void *provider_data; + u8 private_data_len; + u8 ord; + u8 ird; +}; + +/** + * iw_cm_handler - Function to be called by the IW CM when delivering events + * to the client. + * + * @cm_id: The IW CM identifier associated with the event. + * @event: Pointer to the event structure. + */ +typedef int (*iw_cm_handler)(struct iw_cm_id *cm_id, + struct iw_cm_event *event); + +/** + * iw_event_handler - Function called by the provider when delivering provider + * events to the IW CM. Returns either 0 indicating the event was processed + * or -errno if the event could not be processed. + * + * @cm_id: The IW CM identifier associated with the event. + * @event: Pointer to the event structure. + */ +typedef int (*iw_event_handler)(struct iw_cm_id *cm_id, + struct iw_cm_event *event); + +struct iw_cm_id { + iw_cm_handler cm_handler; /* client callback function */ + void *context; /* client cb context */ + struct ib_device *device; + struct sockaddr_storage local_addr; + struct sockaddr_storage remote_addr; + void *provider_data; /* provider private data */ + iw_event_handler event_handler; /* cb for provider + events */ + /* Used by provider to add and remove refs on IW cm_id */ + void (*add_ref)(struct iw_cm_id *); + void (*rem_ref)(struct iw_cm_id *); +}; + +struct iw_cm_conn_param { + const void *private_data; + u16 private_data_len; + u32 ord; + u32 ird; + u32 qpn; +}; + +struct iw_cm_verbs { + void (*add_ref)(struct ib_qp *qp); + + void (*rem_ref)(struct ib_qp *qp); + + struct ib_qp * (*get_qp)(struct ib_device *device, + int qpn); + + int (*connect)(struct iw_cm_id *cm_id, + struct iw_cm_conn_param *conn_param); + + int (*accept)(struct iw_cm_id *cm_id, + struct iw_cm_conn_param *conn_param); + + int (*reject)(struct iw_cm_id *cm_id, + const void *pdata, u8 pdata_len); + + int (*create_listen)(struct iw_cm_id *cm_id, + int backlog); + + int (*destroy_listen)(struct iw_cm_id *cm_id); +}; + +/** + * iw_create_cm_id - Create an IW CM identifier. + * + * @device: The IB device on which to create the IW CM identier. + * @event_handler: User callback invoked to report events associated with the + * returned IW CM identifier. + * @context: User specified context associated with the id. + */ +struct iw_cm_id *iw_create_cm_id(struct ib_device *device, + iw_cm_handler cm_handler, void *context); + +/** + * iw_destroy_cm_id - Destroy an IW CM identifier. + * + * @cm_id: The previously created IW CM identifier to destroy. + * + * The client can assume that no events will be delivered for the CM ID after + * this function returns. + */ +void iw_destroy_cm_id(struct iw_cm_id *cm_id); + +/** + * iw_cm_bind_qp - Unbind the specified IW CM identifier and QP + * + * @cm_id: The IW CM idenfier to unbind from the QP. + * @qp: The QP + * + * This is called by the provider when destroying the QP to ensure + * that any references held by the IWCM are released. It may also + * be called by the IWCM when destroying a CM_ID to that any + * references held by the provider are released. + */ +void iw_cm_unbind_qp(struct iw_cm_id *cm_id, struct ib_qp *qp); + +/** + * iw_cm_get_qp - Return the ib_qp associated with a QPN + * + * @ib_device: The IB device + * @qpn: The queue pair number + */ +struct ib_qp *iw_cm_get_qp(struct ib_device *device, int qpn); + +/** + * iw_cm_listen - Listen for incoming connection requests on the + * specified IW CM id. + * + * @cm_id: The IW CM identifier. + * @backlog: The maximum number of outstanding un-accepted inbound listen + * requests to queue. + * + * The source address and port number are specified in the IW CM identifier + * structure. + */ +int iw_cm_listen(struct iw_cm_id *cm_id, int backlog); + +/** + * iw_cm_accept - Called to accept an incoming connect request. + * + * @cm_id: The IW CM identifier associated with the connection request. + * @iw_param: Pointer to a structure containing connection establishment + * parameters. + * + * The specified cm_id will have been provided in the event data for a + * CONNECT_REQUEST event. Subsequent events related to this connection will be + * delivered to the specified IW CM identifier prior and may occur prior to + * the return of this function. If this function returns a non-zero value, the + * client can assume that no events will be delivered to the specified IW CM + * identifier. + */ +int iw_cm_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *iw_param); + +/** + * iw_cm_reject - Reject an incoming connection request. + * + * @cm_id: Connection identifier associated with the request. + * @private_daa: Pointer to data to deliver to the remote peer as part of the + * reject message. + * @private_data_len: The number of bytes in the private_data parameter. + * + * The client can assume that no events will be delivered to the specified IW + * CM identifier following the return of this function. The private_data + * buffer is available for reuse when this function returns. + */ +int iw_cm_reject(struct iw_cm_id *cm_id, const void *private_data, + u8 private_data_len); + +/** + * iw_cm_connect - Called to request a connection to a remote peer. + * + * @cm_id: The IW CM identifier for the connection. + * @iw_param: Pointer to a structure containing connection establishment + * parameters. + * + * Events may be delivered to the specified IW CM identifier prior to the + * return of this function. If this function returns a non-zero value, the + * client can assume that no events will be delivered to the specified IW CM + * identifier. + */ +int iw_cm_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *iw_param); + +/** + * iw_cm_disconnect - Close the specified connection. + * + * @cm_id: The IW CM identifier to close. + * @abrupt: If 0, the connection will be closed gracefully, otherwise, the + * connection will be reset. + * + * The IW CM identifier is still active until the IW_CM_EVENT_CLOSE event is + * delivered. + */ +int iw_cm_disconnect(struct iw_cm_id *cm_id, int abrupt); + +/** + * iw_cm_init_qp_attr - Called to initialize the attributes of the QP + * associated with a IW CM identifier. + * + * @cm_id: The IW CM identifier associated with the QP + * @qp_attr: Pointer to the QP attributes structure. + * @qp_attr_mask: Pointer to a bit vector specifying which QP attributes are + * valid. + */ +int iw_cm_init_qp_attr(struct iw_cm_id *cm_id, struct ib_qp_attr *qp_attr, + int *qp_attr_mask); + +#endif /* IW_CM_H */ diff --git a/include/rdma/iw_portmap.h b/include/rdma/iw_portmap.h new file mode 100644 index 00000000000..928b2775e99 --- /dev/null +++ b/include/rdma/iw_portmap.h @@ -0,0 +1,199 @@ +/* + * Copyright (c) 2014 Intel Corporation. All rights reserved. + * Copyright (c) 2014 Chelsio, 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 _IW_PORTMAP_H +#define _IW_PORTMAP_H + +#define IWPM_ULIBNAME_SIZE 32 +#define IWPM_DEVNAME_SIZE 32 +#define IWPM_IFNAME_SIZE 16 +#define IWPM_IPADDR_SIZE 16 + +enum { + IWPM_INVALID_NLMSG_ERR = 10, + IWPM_CREATE_MAPPING_ERR, + IWPM_DUPLICATE_MAPPING_ERR, + IWPM_UNKNOWN_MAPPING_ERR, + IWPM_CLIENT_DEV_INFO_ERR, + IWPM_USER_LIB_INFO_ERR, + IWPM_REMOTE_QUERY_REJECT +}; + +struct iwpm_dev_data { + char dev_name[IWPM_DEVNAME_SIZE]; + char if_name[IWPM_IFNAME_SIZE]; +}; + +struct iwpm_sa_data { + struct sockaddr_storage loc_addr; + struct sockaddr_storage mapped_loc_addr; + struct sockaddr_storage rem_addr; + struct sockaddr_storage mapped_rem_addr; +}; + +/** + * iwpm_init - Allocate resources for the iwarp port mapper + * + * Should be called when network interface goes up. + */ +int iwpm_init(u8); + +/** + * iwpm_exit - Deallocate resources for the iwarp port mapper + * + * Should be called when network interface goes down. + */ +int iwpm_exit(u8); + +/** + * iwpm_valid_pid - Check if the userspace iwarp port mapper pid is valid + * + * Returns true if the pid is greater than zero, otherwise returns false + */ +int iwpm_valid_pid(void); + +/** + * iwpm_register_pid - Send a netlink query to userspace + * to get the iwarp port mapper pid + * @pm_msg: Contains driver info to send to the userspace port mapper + * @nl_client: The index of the netlink client + */ +int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client); + +/** + * iwpm_add_mapping - Send a netlink add mapping request to + * the userspace port mapper + * @pm_msg: Contains the local ip/tcp address info to send + * @nl_client: The index of the netlink client + * + * If the request is successful, the pm_msg stores + * the port mapper response (mapped address info) + */ +int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client); + +/** + * iwpm_add_and_query_mapping - Send a netlink add and query mapping request + * to the userspace port mapper + * @pm_msg: Contains the local and remote ip/tcp address info to send + * @nl_client: The index of the netlink client + * + * If the request is successful, the pm_msg stores the + * port mapper response (mapped local and remote address info) + */ +int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client); + +/** + * iwpm_remove_mapping - Send a netlink remove mapping request + * to the userspace port mapper + * + * @local_addr: Local ip/tcp address to remove + * @nl_client: The index of the netlink client + */ +int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client); + +/** + * iwpm_register_pid_cb - Process the port mapper response to + * iwpm_register_pid query + * @skb: + * @cb: Contains the received message (payload and netlink header) + * + * If successful, the function receives the userspace port mapper pid + * which is used in future communication with the port mapper + */ +int iwpm_register_pid_cb(struct sk_buff *, struct netlink_callback *); + +/** + * iwpm_add_mapping_cb - Process the port mapper response to + * iwpm_add_mapping request + * @skb: + * @cb: Contains the received message (payload and netlink header) + */ +int iwpm_add_mapping_cb(struct sk_buff *, struct netlink_callback *); + +/** + * iwpm_add_and_query_mapping_cb - Process the port mapper response to + * iwpm_add_and_query_mapping request + * @skb: + * @cb: Contains the received message (payload and netlink header) + */ +int iwpm_add_and_query_mapping_cb(struct sk_buff *, struct netlink_callback *); + +/** + * iwpm_mapping_error_cb - Process port mapper notification for error + * + * @skb: + * @cb: Contains the received message (payload and netlink header) + */ +int iwpm_mapping_error_cb(struct sk_buff *, struct netlink_callback *); + +/** + * iwpm_mapping_info_cb - Process a notification that the userspace + * port mapper daemon is started + * @skb: + * @cb: Contains the received message (payload and netlink header) + * + * Using the received port mapper pid, send all the local mapping + * info records to the userspace port mapper + */ +int iwpm_mapping_info_cb(struct sk_buff *, struct netlink_callback *); + +/** + * iwpm_ack_mapping_info_cb - Process the port mapper ack for + * the provided local mapping info records + * @skb: + * @cb: Contains the received message (payload and netlink header) + */ +int iwpm_ack_mapping_info_cb(struct sk_buff *, struct netlink_callback *); + +/** + * iwpm_create_mapinfo - Store local and mapped IPv4/IPv6 address + * info in a hash table + * @local_addr: Local ip/tcp address + * @mapped_addr: Mapped local ip/tcp address + * @nl_client: The index of the netlink client + */ +int iwpm_create_mapinfo(struct sockaddr_storage *local_addr, + struct sockaddr_storage *mapped_addr, u8 nl_client); + +/** + * iwpm_remove_mapinfo - Remove local and mapped IPv4/IPv6 address + * info from the hash table + * @local_addr: Local ip/tcp address + * @mapped_addr: Mapped local ip/tcp address + * + * Returns err code if mapping info is not found in the hash table, + * otherwise returns 0 + */ +int iwpm_remove_mapinfo(struct sockaddr_storage *local_addr, + struct sockaddr_storage *mapped_addr); + +#endif /* _IW_PORTMAP_H */ diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h new file mode 100644 index 00000000000..1ed2088dc9f --- /dev/null +++ b/include/rdma/rdma_cm.h @@ -0,0 +1,383 @@ +/* + * Copyright (c) 2005 Voltaire Inc. All rights reserved. + * Copyright (c) 2005 Intel Corporation. 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. + */ + +#if !defined(RDMA_CM_H) +#define RDMA_CM_H + +#include <linux/socket.h> +#include <linux/in6.h> +#include <rdma/ib_addr.h> +#include <rdma/ib_sa.h> + +/* + * Upon receiving a device removal event, users must destroy the associated + * RDMA identifier and release all resources allocated with the device. + */ +enum rdma_cm_event_type { + RDMA_CM_EVENT_ADDR_RESOLVED, + RDMA_CM_EVENT_ADDR_ERROR, + RDMA_CM_EVENT_ROUTE_RESOLVED, + RDMA_CM_EVENT_ROUTE_ERROR, + RDMA_CM_EVENT_CONNECT_REQUEST, + RDMA_CM_EVENT_CONNECT_RESPONSE, + RDMA_CM_EVENT_CONNECT_ERROR, + RDMA_CM_EVENT_UNREACHABLE, + RDMA_CM_EVENT_REJECTED, + RDMA_CM_EVENT_ESTABLISHED, + RDMA_CM_EVENT_DISCONNECTED, + RDMA_CM_EVENT_DEVICE_REMOVAL, + RDMA_CM_EVENT_MULTICAST_JOIN, + RDMA_CM_EVENT_MULTICAST_ERROR, + RDMA_CM_EVENT_ADDR_CHANGE, + RDMA_CM_EVENT_TIMEWAIT_EXIT +}; + +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 +#define RDMA_IB_IP_PS_IB 0x00000000013F0000ULL + +struct rdma_addr { + struct sockaddr_storage src_addr; + struct sockaddr_storage dst_addr; + struct rdma_dev_addr dev_addr; +}; + +struct rdma_route { + struct rdma_addr addr; + struct ib_sa_path_rec *path_rec; + int num_paths; +}; + +struct rdma_conn_param { + const void *private_data; + u8 private_data_len; + u8 responder_resources; + u8 initiator_depth; + u8 flow_control; + u8 retry_count; /* ignored when accepting */ + u8 rnr_retry_count; + /* Fields below ignored if a QP is created on the rdma_cm_id. */ + u8 srq; + u32 qp_num; + u32 qkey; +}; + +struct rdma_ud_param { + const void *private_data; + u8 private_data_len; + struct ib_ah_attr ah_attr; + u32 qp_num; + u32 qkey; +}; + +struct rdma_cm_event { + enum rdma_cm_event_type event; + int status; + union { + struct rdma_conn_param conn; + struct rdma_ud_param ud; + } 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; + +/** + * rdma_cm_event_handler - Callback used to report user events. + * + * Notes: Users may not call rdma_destroy_id from this callback to destroy + * the passed in id, or a corresponding listen id. Returning a + * non-zero value from the callback will destroy the passed in id. + */ +typedef int (*rdma_cm_event_handler)(struct rdma_cm_id *id, + struct rdma_cm_event *event); + +struct rdma_cm_id { + struct ib_device *device; + void *context; + struct ib_qp *qp; + rdma_cm_event_handler event_handler; + struct rdma_route route; + enum rdma_port_space ps; + enum ib_qp_type qp_type; + u8 port_num; +}; + +/** + * rdma_create_id - Create an RDMA identifier. + * + * @event_handler: User callback invoked to report events associated with the + * returned rdma_id. + * @context: User specified context associated with the id. + * @ps: RDMA port space. + * @qp_type: type of queue pair associated with the id. + */ +struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler event_handler, + void *context, enum rdma_port_space ps, + enum ib_qp_type qp_type); + +/** + * rdma_destroy_id - Destroys an RDMA identifier. + * + * @id: RDMA identifier. + * + * Note: calling this function has the effect of canceling in-flight + * asynchronous operations associated with the id. + */ +void rdma_destroy_id(struct rdma_cm_id *id); + +/** + * rdma_bind_addr - Bind an RDMA identifier to a source address and + * associated RDMA device, if needed. + * + * @id: RDMA identifier. + * @addr: Local address information. Wildcard values are permitted. + * + * This associates a source address with the RDMA identifier before calling + * rdma_listen. If a specific local address is given, the RDMA identifier will + * be bound to a local RDMA device. + */ +int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr); + +/** + * rdma_resolve_addr - Resolve destination and optional source addresses + * from IP addresses to an RDMA address. If successful, the specified + * rdma_cm_id will be bound to a local device. + * + * @id: RDMA identifier. + * @src_addr: Source address information. This parameter may be NULL. + * @dst_addr: Destination address information. + * @timeout_ms: Time to wait for resolution to complete. + */ +int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, + struct sockaddr *dst_addr, int timeout_ms); + +/** + * rdma_resolve_route - Resolve the RDMA address bound to the RDMA identifier + * into route information needed to establish a connection. + * + * This is called on the client side of a connection. + * Users must have first called rdma_resolve_addr to resolve a dst_addr + * into an RDMA address before calling this routine. + */ +int rdma_resolve_route(struct rdma_cm_id *id, int timeout_ms); + +/** + * rdma_create_qp - Allocate a QP and associate it with the specified RDMA + * identifier. + * + * QPs allocated to an rdma_cm_id will automatically be transitioned by the CMA + * through their states. + */ +int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd, + struct ib_qp_init_attr *qp_init_attr); + +/** + * rdma_destroy_qp - Deallocate the QP associated with the specified RDMA + * identifier. + * + * Users must destroy any QP associated with an RDMA identifier before + * destroying the RDMA ID. + */ +void rdma_destroy_qp(struct rdma_cm_id *id); + +/** + * rdma_init_qp_attr - Initializes the QP attributes for use in transitioning + * to a specified QP state. + * @id: Communication identifier associated with the QP attributes to + * initialize. + * @qp_attr: On input, specifies the desired QP state. On output, the + * mandatory and desired optional attributes will be set in order to + * modify the QP to the specified state. + * @qp_attr_mask: The QP attribute mask that may be used to transition the + * QP to the specified state. + * + * Users must set the @qp_attr->qp_state to the desired QP state. This call + * will set all required attributes for the given transition, along with + * known optional attributes. Users may override the attributes returned from + * this call before calling ib_modify_qp. + * + * Users that wish to have their QP automatically transitioned through its + * states can associate a QP with the rdma_cm_id by calling rdma_create_qp(). + */ +int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr, + int *qp_attr_mask); + +/** + * rdma_connect - Initiate an active connection request. + * @id: Connection identifier to connect. + * @conn_param: Connection information used for connected QPs. + * + * Users must have resolved a route for the rdma_cm_id to connect with + * by having called rdma_resolve_route before calling this routine. + * + * This call will either connect to a remote QP or obtain remote QP + * information for unconnected rdma_cm_id's. The actual operation is + * based on the rdma_cm_id's port space. + */ +int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param); + +/** + * rdma_listen - This function is called by the passive side to + * listen for incoming connection requests. + * + * Users must have bound the rdma_cm_id to a local address by calling + * rdma_bind_addr before calling this routine. + */ +int rdma_listen(struct rdma_cm_id *id, int backlog); + +/** + * rdma_accept - Called to accept a connection request or response. + * @id: Connection identifier associated with the request. + * @conn_param: Information needed to establish the connection. This must be + * provided if accepting a connection request. If accepting a connection + * response, this parameter must be NULL. + * + * Typically, this routine is only called by the listener to accept a connection + * request. It must also be called on the active side of a connection if the + * user is performing their own QP transitions. + * + * In the case of error, a reject message is sent to the remote side and the + * 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); + +/** + * rdma_notify - Notifies the RDMA CM of an asynchronous event that has + * occurred on the connection. + * @id: Connection identifier to transition to established. + * @event: Asynchronous event. + * + * This routine should be invoked by users to notify the CM of relevant + * communication events. Events that should be reported to the CM and + * when to report them are: + * + * IB_EVENT_COMM_EST - Used when a message is received on a connected + * QP before an RTU has been received. + */ +int rdma_notify(struct rdma_cm_id *id, enum ib_event_type event); + +/** + * rdma_reject - Called to reject a connection request or response. + */ +int rdma_reject(struct rdma_cm_id *id, const void *private_data, + u8 private_data_len); + +/** + * rdma_disconnect - This function disconnects the associated QP and + * transitions it into the error state. + */ +int rdma_disconnect(struct rdma_cm_id *id); + +/** + * rdma_join_multicast - Join the multicast group specified by the given + * address. + * @id: Communication identifier associated with the request. + * @addr: Multicast address identifying the group to join. + * @context: User-defined context associated with the join request, returned + * to the user through the private_data pointer in multicast events. + */ +int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, + void *context); + +/** + * rdma_leave_multicast - Leave the multicast group specified by the given + * address. + */ +void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr); + +/** + * rdma_set_service_type - Set the type of service associated with a + * connection identifier. + * @id: Communication identifier to associated with service type. + * @tos: Type of service. + * + * The type of service is interpretted as a differentiated service + * field (RFC 2474). The service type should be specified before + * performing route resolution, as existing communication on the + * connection identifier may be unaffected. The type of service + * requested may not be supported by the network to all destinations. + */ +void rdma_set_service_type(struct rdma_cm_id *id, int tos); + +/** + * rdma_set_reuseaddr - Allow the reuse of local addresses when binding + * the rdma_cm_id. + * @id: Communication identifier to configure. + * @reuse: Value indicating if the bound address is reusable. + * + * Reuse must be set before an address is bound to the id. + */ +int rdma_set_reuseaddr(struct rdma_cm_id *id, int reuse); + +/** + * rdma_set_afonly - Specify that listens are restricted to the + * bound address family only. + * @id: Communication identifer to configure. + * @afonly: Value indicating if listens are restricted. + * + * Must be set before identifier is in the listening state. + */ +int rdma_set_afonly(struct rdma_cm_id *id, int afonly); + + /** + * rdma_get_service_id - Return the IB service ID for a specified address. + * @id: Communication identifier associated with the address. + * @addr: Address for the service ID. + */ +__be64 rdma_get_service_id(struct rdma_cm_id *id, struct sockaddr *addr); + +#endif /* RDMA_CM_H */ diff --git a/include/rdma/rdma_cm_ib.h b/include/rdma/rdma_cm_ib.h new file mode 100644 index 00000000000..2389c3b4540 --- /dev/null +++ b/include/rdma/rdma_cm_ib.h @@ -0,0 +1,54 @@ +/* + * Copyright (c) 2006 Intel Corporation. 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. + */ + +#if !defined(RDMA_CM_IB_H) +#define RDMA_CM_IB_H + +#include <rdma/rdma_cm.h> + +/** + * rdma_set_ib_paths - Manually sets the path records 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 + * connection and replaces the call to rdma_resolve_route. + */ +int rdma_set_ib_paths(struct rdma_cm_id *id, + struct ib_sa_path_rec *path_rec, int num_paths); + +/* Global qkey for UDP QPs and multicast groups. */ +#define RDMA_UDP_QKEY 0x01234567 + +#endif /* RDMA_CM_IB_H */ diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h new file mode 100644 index 00000000000..0790882e0c9 --- /dev/null +++ b/include/rdma/rdma_netlink.h @@ -0,0 +1,80 @@ +#ifndef _RDMA_NETLINK_H +#define _RDMA_NETLINK_H + + +#include <linux/netlink.h> +#include <uapi/rdma/rdma_netlink.h> + +struct ibnl_client_cbs { + int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb); + struct module *module; +}; + +int ibnl_init(void); +void ibnl_cleanup(void); + +/** + * Add a a client to the list of IB netlink exporters. + * @index: Index of the added client + * @nops: Number of supported ops by the added client. + * @cb_table: A table for op->callback + * + * Returns 0 on success or a negative error code. + */ +int ibnl_add_client(int index, int nops, + const struct ibnl_client_cbs cb_table[]); + +/** + * Remove a client from IB netlink. + * @index: Index of the removed IB client. + * + * Returns 0 on success or a negative error code. + */ +int ibnl_remove_client(int index); + +/** + * Put a new message in a supplied skb. + * @skb: The netlink skb. + * @nlh: Pointer to put the header of the new netlink message. + * @seq: The message sequence number. + * @len: The requested message length to allocate. + * @client: Calling IB netlink client. + * @op: message content op. + * Returns the allocated buffer on success and NULL on failure. + */ +void *ibnl_put_msg(struct sk_buff *skb, struct nlmsghdr **nlh, int seq, + int len, int client, int op, int flags); +/** + * Put a new attribute in a supplied skb. + * @skb: The netlink skb. + * @nlh: Header of the netlink message to append the attribute to. + * @len: The length of the attribute data. + * @data: The attribute data to put. + * @type: The attribute type. + * Returns the 0 and a negative error code on failure. + */ +int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh, + int len, void *data, int type); + +/** + * Send the supplied skb to a specific userspace PID. + * @skb: The netlink skb + * @nlh: Header of the netlink message to send + * @pid: Userspace netlink process ID + * Returns 0 on success or a negative error code. + */ +int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh, + __u32 pid); + +/** + * Send the supplied skb to a netlink group. + * @skb: The netlink skb + * @nlh: Header of the netlink message to send + * @group: Netlink group ID + * @flags: allocation flags + * Returns 0 on success or a negative error code. + */ +int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh, + unsigned int group, gfp_t flags); + +#endif /* _RDMA_NETLINK_H */ |