diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-03 17:49:17 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-03 17:49:17 -0700 |
commit | aa9d4648c2fbb455df7750ade1b73dd9ad9b3690 (patch) | |
tree | bc4590c27e6f30ec0612b28f3f38a539535b9930 /include | |
parent | 906dde0f355bd97c080c215811ae7db1137c4af8 (diff) | |
parent | 8eb19e8e7c8658226d8b7e75728e6dfa2ef32717 (diff) |
Merge tag 'for-linus-ioctl' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma
Pull rdma updates from Doug Ledford:
"This is a big pull request.
Of note is that I'm sending you the new ioctl API for the rdma
subsystem. We put it up on linux-api@, but didn't get much response.
The API is complex, but it solves two different problems in one go:
1) The bi-directional nature of the RDMA file write calls, which
created the security hole we had to handle (and for which the fix
is now causing problems for systems in production, we were a bit
over zealous in the fix and the ability to open a device, then
fork, then create new queue pairs on the device and use them is
broken).
2) The bloat caused by different vendors implementing extensions to
the base verbs API. Each vendor's hardware is slightly different,
and the hardware might be suitable for one extension but not
another.
By the time we add generic extensions for all the different ways
that the different hardware can offload things, the API becomes
bloated. Things like our completion structs have started to exceed
a cache line in size because of all the elements needed to support
this. That in turn shows up heavily in the performance graphs with
a noticable drop in performance on 100Gigabit links as our
completion structs go from occupying one cache line to 1+.
This API makes things like the completion structs modular in a
very similar way to netlink so that your structs can only include
the items needed for the offloads/features you are actually using
on a given queue pair. In that way we support everything, but only
use what we need, and our structs stay smaller.
The ioctl API is better explained by the posting on linux-api@ than I
can explain it here, so I'll just leave it at that.
The rest of the pull request is typical stuff.
Updates for 4.14 kernel merge window
- Lots of hfi1 driver updates (mixed with a few qib and core updates
as well)
- rxe updates
- various mlx updates
- Set default roce type to RoCEv2
- Several larger fixes for bnxt_re that were too big for -rc
- Several larger fixes for qedr that, likewise, were too big for -rc
- Misc core changes
- Make the hns_roce driver compilable on arches other than aarch64 so
we can more easily debug build issues related to it
- Add rdma-netlink infrastructure updates
- Add automatic IRQ affinity infrastructure
- Add 32bit lid support
- Lots of misc fixes across the subsystem from random people
- Autoloading of RDMA netlink modules
- PCI pool cleanups from Romain Perier
- mlx5 driver feature additions and fixes
- Hardware tag matchine feature
- Fix sleeping in atomic when resolving roce ah
- Add experimental ioctl interface as posted to linux-api@"
* tag 'for-linus-ioctl' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (328 commits)
IB/core: Expose ioctl interface through experimental Kconfig
IB/core: Assign root to all drivers
IB/core: Add completion queue (cq) object actions
IB/core: Add legacy driver's user-data
IB/core: Export ioctl enum types to user-space
IB/core: Explicitly destroy an object while keeping uobject
IB/core: Add macros for declaring methods and attributes
IB/core: Add uverbs merge trees functionality
IB/core: Add DEVICE object and root tree structure
IB/core: Declare an object instead of declaring only type attributes
IB/core: Add new ioctl interface
RDMA/vmw_pvrdma: Fix a signedness
RDMA/vmw_pvrdma: Report network header type in WC
IB/core: Add might_sleep() annotation to ib_init_ah_from_wc()
IB/cm: Fix sleeping in atomic when RoCE is used
IB/core: Add support to finalize objects in one transaction
IB/core: Add a generic way to execute an operation on a uobject
Documentation: Hardware tag matching
IB/mlx5: Support IB_SRQT_TM
net/mlx5: Add XRQ support
...
Diffstat (limited to 'include')
30 files changed, 1324 insertions, 125 deletions
diff --git a/include/linux/blk-mq-rdma.h b/include/linux/blk-mq-rdma.h new file mode 100644 index 000000000000..b4ade198007d --- /dev/null +++ b/include/linux/blk-mq-rdma.h @@ -0,0 +1,10 @@ +#ifndef _LINUX_BLK_MQ_RDMA_H +#define _LINUX_BLK_MQ_RDMA_H + +struct blk_mq_tag_set; +struct ib_device; + +int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set, + struct ib_device *dev, int first_vec); + +#endif /* _LINUX_BLK_MQ_RDMA_H */ diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index b54517c05e9a..c8a63e148a98 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -428,6 +428,12 @@ enum mlx4_steer_type { MLX4_NUM_STEERS }; +enum mlx4_resource_usage { + MLX4_RES_USAGE_NONE, + MLX4_RES_USAGE_DRIVER, + MLX4_RES_USAGE_USER_VERBS, +}; + enum { MLX4_NUM_FEXCH = 64 * 1024, }; @@ -749,6 +755,7 @@ struct mlx4_cq { } tasklet_ctx; int reset_notify_added; struct list_head reset_notify; + u8 usage; }; struct mlx4_qp { @@ -758,6 +765,7 @@ struct mlx4_qp { atomic_t refcount; struct completion free; + u8 usage; }; struct mlx4_srq { @@ -1121,7 +1129,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt, unsigned vector, int collapsed, int timestamp_en); void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq); int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, - int *base, u8 flags); + int *base, u8 flags, u8 usage); void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt); int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp); @@ -1418,7 +1426,7 @@ int mlx4_get_phys_port_id(struct mlx4_dev *dev); int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port); int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port); -int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx); +int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx, u8 usage); void mlx4_counter_free(struct mlx4_dev *dev, u32 idx); int mlx4_get_default_counter_index(struct mlx4_dev *dev, int port); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f31a0b5377e1..c13d71deaeca 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -290,6 +290,7 @@ enum mlx5_event { MLX5_EVENT_TYPE_GPIO_EVENT = 0x15, MLX5_EVENT_TYPE_PORT_MODULE_EVENT = 0x16, MLX5_EVENT_TYPE_REMOTE_CONFIG = 0x19, + MLX5_EVENT_TYPE_GENERAL_EVENT = 0x22, MLX5_EVENT_TYPE_PPS_EVENT = 0x25, MLX5_EVENT_TYPE_DB_BF_CONGESTION = 0x1a, @@ -305,6 +306,10 @@ enum mlx5_event { }; enum { + MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT = 0x1, +}; + +enum { MLX5_PORT_CHANGE_SUBTYPE_DOWN = 1, MLX5_PORT_CHANGE_SUBTYPE_ACTIVE = 4, MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED = 5, @@ -968,7 +973,7 @@ enum mlx5_cap_type { MLX5_CAP_ATOMIC, MLX5_CAP_ROCE, MLX5_CAP_IPOIB_OFFLOADS, - MLX5_CAP_EOIB_OFFLOADS, + MLX5_CAP_IPOIB_ENHANCED_OFFLOADS, MLX5_CAP_FLOW_TABLE, MLX5_CAP_ESWITCH_FLOW_TABLE, MLX5_CAP_ESWITCH, @@ -1011,6 +1016,10 @@ enum mlx5_mcam_feature_groups { MLX5_GET(per_protocol_networking_offload_caps,\ mdev->caps.hca_max[MLX5_CAP_ETHERNET_OFFLOADS], cap) +#define MLX5_CAP_IPOIB_ENHANCED(mdev, cap) \ + MLX5_GET(per_protocol_networking_offload_caps,\ + mdev->caps.hca_cur[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS], cap) + #define MLX5_CAP_ROCE(mdev, cap) \ MLX5_GET(roce_cap, mdev->caps.hca_cur[MLX5_CAP_ROCE], cap) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 205d82d4c468..b3fc9d586a9f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -162,6 +162,13 @@ enum dbg_rsc_type { MLX5_DBG_RSC_CQ, }; +enum port_state_policy { + MLX5_POLICY_DOWN = 0, + MLX5_POLICY_UP = 1, + MLX5_POLICY_FOLLOW = 2, + MLX5_POLICY_INVALID = 0xffffffff +}; + struct mlx5_field_desc { struct dentry *dent; int i; @@ -185,6 +192,7 @@ enum mlx5_dev_event { MLX5_DEV_EVENT_GUID_CHANGE, MLX5_DEV_EVENT_CLIENT_REREG, MLX5_DEV_EVENT_PPS, + MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT, }; enum mlx5_port_status { @@ -291,7 +299,7 @@ struct mlx5_cmd { struct semaphore pages_sem; int mode; struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS]; - struct pci_pool *pool; + struct dma_pool *pool; struct mlx5_cmd_debug dbg; struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES]; int checksum_disabled; @@ -410,6 +418,7 @@ enum mlx5_res_type { MLX5_RES_SQ = MLX5_EVENT_QUEUE_TYPE_SQ, MLX5_RES_SRQ = 3, MLX5_RES_XSRQ = 4, + MLX5_RES_XRQ = 5, }; struct mlx5_core_rsc_common { @@ -525,6 +534,9 @@ struct mlx5_mkey_table { struct mlx5_vf_context { int enabled; + u64 port_guid; + u64 node_guid; + enum port_state_policy policy; }; struct mlx5_core_sriov { @@ -534,7 +546,6 @@ struct mlx5_core_sriov { }; struct mlx5_irq_info { - cpumask_var_t mask; char name[MLX5_MAX_IRQ_NAME]; }; @@ -597,7 +608,6 @@ struct mlx5_port_module_event_stats { struct mlx5_priv { char name[MLX5_MAX_NAME_LEN]; struct mlx5_eq_table eq_table; - struct msix_entry *msix_arr; struct mlx5_irq_info *irq_info; /* pages stuff */ @@ -840,13 +850,6 @@ struct mlx5_pas { u8 log_sz; }; -enum port_state_policy { - MLX5_POLICY_DOWN = 0, - MLX5_POLICY_UP = 1, - MLX5_POLICY_FOLLOW = 2, - MLX5_POLICY_INVALID = 0xffffffff -}; - enum phy_port_state { MLX5_AAA_111 }; @@ -1089,7 +1092,7 @@ enum { }; enum { - MAX_UMR_CACHE_ENTRY = 20, + MR_CACHE_LAST_STD_ENTRY = 20, MLX5_IMR_MTT_CACHE_ENTRY, MLX5_IMR_KSM_CACHE_ENTRY, MAX_MR_CACHE_ENTRIES @@ -1183,4 +1186,10 @@ enum { MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, }; +static inline const struct cpumask * +mlx5_get_vector_affinity(struct mlx5_core_dev *dev, int vector) +{ + return pci_irq_get_affinity(dev->pdev, MLX5_EQ_VEC_COMP_BASE + vector); +} + #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3030121b4746..b7338a21c780 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -200,6 +200,7 @@ enum { MLX5_CMD_OP_QUERY_SQ = 0x907, MLX5_CMD_OP_CREATE_RQ = 0x908, MLX5_CMD_OP_MODIFY_RQ = 0x909, + MLX5_CMD_OP_SET_DELAY_DROP_PARAMS = 0x910, MLX5_CMD_OP_DESTROY_RQ = 0x90a, MLX5_CMD_OP_QUERY_RQ = 0x90b, MLX5_CMD_OP_CREATE_RMP = 0x90c, @@ -294,8 +295,10 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 inner_tcp_dport[0x1]; u8 inner_tcp_flags[0x1]; u8 reserved_at_37[0x9]; + u8 reserved_at_40[0x1a]; + u8 bth_dst_qp[0x1]; - u8 reserved_at_40[0x40]; + u8 reserved_at_5b[0x25]; }; struct mlx5_ifc_flow_table_prop_layout_bits { @@ -431,7 +434,9 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 reserved_at_100[0xc]; u8 inner_ipv6_flow_label[0x14]; - u8 reserved_at_120[0xe0]; + u8 reserved_at_120[0x28]; + u8 bth_dst_qp[0x18]; + u8 reserved_at_160[0xa0]; }; struct mlx5_ifc_cmd_pas_bits { @@ -599,7 +604,7 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 rss_ind_tbl_cap[0x4]; u8 reg_umr_sq[0x1]; u8 scatter_fcs[0x1]; - u8 reserved_at_1a[0x1]; + u8 enhanced_multi_pkt_send_wqe[0x1]; u8 tunnel_lso_const_out_ip_id[0x1]; u8 reserved_at_1c[0x2]; u8 tunnel_statless_gre[0x1]; @@ -840,7 +845,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 retransmission_q_counters[0x1]; u8 reserved_at_183[0x1]; u8 modify_rq_counter_set_id[0x1]; - u8 reserved_at_185[0x1]; + u8 rq_delay_drop[0x1]; u8 max_qp_cnt[0xa]; u8 pkey_table_size[0x10]; @@ -857,7 +862,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 pcam_reg[0x1]; u8 local_ca_ack_delay[0x5]; u8 port_module_event[0x1]; - u8 reserved_at_1b1[0x1]; + u8 enhanced_error_q_counters[0x1]; u8 ports_check[0x1]; u8 reserved_at_1b3[0x1]; u8 disable_link_up[0x1]; @@ -873,7 +878,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_tc[0x4]; u8 reserved_at_1d0[0x1]; u8 dcbx[0x1]; - u8 reserved_at_1d2[0x3]; + u8 general_notification_event[0x1]; + u8 reserved_at_1d3[0x2]; u8 fpga[0x1]; u8 rol_s[0x1]; u8 rol_g[0x1]; @@ -1016,7 +1022,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_wq_sz[0x5]; u8 nic_vport_change_event[0x1]; - u8 reserved_at_3e1[0xa]; + u8 disable_local_lb[0x1]; + u8 reserved_at_3e2[0x9]; u8 log_max_vlan_list[0x5]; u8 reserved_at_3f0[0x3]; u8 log_max_current_mc_list[0x5]; @@ -1187,7 +1194,8 @@ struct mlx5_ifc_cong_control_r_roce_ecn_np_bits { u8 reserved_at_c0[0x12]; u8 cnp_dscp[0x6]; - u8 reserved_at_d8[0x5]; + u8 reserved_at_d8[0x4]; + u8 cnp_prio_mode[0x1]; u8 cnp_802p_prio[0x3]; u8 reserved_at_e0[0x720]; @@ -2015,6 +2023,10 @@ enum { }; enum { + MLX5_QPC_OFFLOAD_TYPE_RNDV = 0x1, +}; + +enum { MLX5_QPC_END_PADDING_MODE_SCATTER_AS_IS = 0x0, MLX5_QPC_END_PADDING_MODE_PAD_TO_CACHE_LINE_ALIGNMENT = 0x1, }; @@ -2057,7 +2069,8 @@ struct mlx5_ifc_qpc_bits { u8 st[0x8]; u8 reserved_at_10[0x3]; u8 pm_state[0x2]; - u8 reserved_at_15[0x7]; + u8 reserved_at_15[0x3]; + u8 offload_type[0x4]; u8 end_padding_mode[0x2]; u8 reserved_at_1e[0x2]; @@ -2437,7 +2450,7 @@ struct mlx5_ifc_sqc_bits { u8 cd_master[0x1]; u8 fre[0x1]; u8 flush_in_error_en[0x1]; - u8 reserved_at_4[0x1]; + u8 allow_multi_pkt_send_wqe[0x1]; u8 min_wqe_inline_mode[0x3]; u8 state[0x4]; u8 reg_umr[0x1]; @@ -2515,7 +2528,7 @@ enum { struct mlx5_ifc_rqc_bits { u8 rlky[0x1]; - u8 reserved_at_1[0x1]; + u8 delay_drop_en[0x1]; u8 scatter_fcs[0x1]; u8 vsd[0x1]; u8 mem_rq_type[0x4]; @@ -2562,7 +2575,9 @@ struct mlx5_ifc_rmpc_bits { struct mlx5_ifc_nic_vport_context_bits { u8 reserved_at_0[0x5]; u8 min_wqe_inline_mode[0x3]; - u8 reserved_at_8[0x17]; + u8 reserved_at_8[0x15]; + u8 disable_mc_local_lb[0x1]; + u8 disable_uc_local_lb[0x1]; u8 roce_en[0x1]; u8 arm_change_event[0x1]; @@ -3000,7 +3015,7 @@ struct mlx5_ifc_xrqc_bits { struct mlx5_ifc_tag_matching_topology_context_bits tag_matching_topology_context; - u8 reserved_at_180[0x880]; + u8 reserved_at_180[0x280]; struct mlx5_ifc_wq_bits wq; }; @@ -3947,7 +3962,47 @@ struct mlx5_ifc_query_q_counter_out_bits { u8 local_ack_timeout_err[0x20]; - u8 reserved_at_320[0x4e0]; + u8 reserved_at_320[0xa0]; + + u8 resp_local_length_error[0x20]; + + u8 req_local_length_error[0x20]; + + u8 resp_local_qp_error[0x20]; + + u8 local_operation_error[0x20]; + + u8 resp_local_protection[0x20]; + + u8 req_local_protection[0x20]; + + u8 resp_cqe_error[0x20]; + + u8 req_cqe_error[0x20]; + + u8 req_mw_binding[0x20]; + + u8 req_bad_response[0x20]; + + u8 req_remote_invalid_request[0x20]; + + u8 resp_remote_invalid_request[0x20]; + + u8 req_remote_access_errors[0x20]; + + u8 resp_remote_access_errors[0x20]; + + u8 req_remote_operation_errors[0x20]; + + u8 req_transport_retries_exceeded[0x20]; + + u8 cq_overflow[0x20]; + + u8 resp_cqe_flush_error[0x20]; + + u8 req_cqe_flush_error[0x20]; + + u8 reserved_at_620[0x1e0]; }; struct mlx5_ifc_query_q_counter_in_bits { @@ -5229,7 +5284,9 @@ struct mlx5_ifc_modify_nic_vport_context_out_bits { }; struct mlx5_ifc_modify_nic_vport_field_select_bits { - u8 reserved_at_0[0x16]; + u8 reserved_at_0[0x14]; + u8 disable_uc_local_lb[0x1]; + u8 disable_mc_local_lb[0x1]; u8 node_guid[0x1]; u8 port_guid[0x1]; u8 min_inline[0x1]; @@ -5847,6 +5904,28 @@ struct mlx5_ifc_destroy_rq_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_set_delay_drop_params_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x10]; + u8 delay_drop_timeout[0x10]; +}; + +struct mlx5_ifc_set_delay_drop_params_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_destroy_rmp_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index f378dc0e7eaf..66d19b611fe4 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -560,6 +560,9 @@ int mlx5_core_destroy_qp(struct mlx5_core_dev *dev, int mlx5_core_qp_query(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp, u32 *out, int outlen); +int mlx5_core_set_delay_drop(struct mlx5_core_dev *dev, + u32 timeout_usec); + int mlx5_core_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn); int mlx5_core_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn); void mlx5_init_qp_table(struct mlx5_core_dev *dev); diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h index 1cde0fd53f90..24ff23e27c8a 100644 --- a/include/linux/mlx5/srq.h +++ b/include/linux/mlx5/srq.h @@ -38,6 +38,7 @@ enum { MLX5_SRQ_FLAG_ERR = (1 << 0), MLX5_SRQ_FLAG_WQ_SIG = (1 << 1), + MLX5_SRQ_FLAG_RNDV = (1 << 2), }; struct mlx5_srq_attr { @@ -56,6 +57,10 @@ struct mlx5_srq_attr { u32 user_index; u64 db_record; __be64 *pas; + u32 tm_log_list_size; + u32 tm_next_tag; + u32 tm_hw_phase_cnt; + u32 tm_sw_phase_cnt; }; struct mlx5_core_dev; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 656c70b65dd2..aaa0bb9e7655 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -114,5 +114,6 @@ int mlx5_core_modify_hca_vport_context(struct mlx5_core_dev *dev, u8 other_vport, u8 port_num, int vf, struct mlx5_hca_vport_context *req); - +int mlx5_nic_vport_update_local_lb(struct mlx5_core_dev *mdev, bool enable); +int mlx5_nic_vport_query_local_lb(struct mlx5_core_dev *mdev, bool *status); #endif /* __MLX5_VPORT_H__ */ diff --git a/include/linux/pci.h b/include/linux/pci.h index f958d0732af6..da05e5db06ac 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -731,6 +731,7 @@ struct pci_driver { void (*shutdown) (struct pci_dev *dev); int (*sriov_configure) (struct pci_dev *dev, int num_vfs); /* PF pdev */ const struct pci_error_handlers *err_handler; + const struct attribute_group **groups; struct device_driver driver; struct pci_dynids dynids; }; diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h index b73a14edc85e..ec5008cf5d51 100644 --- a/include/rdma/ib_addr.h +++ b/include/rdma/ib_addr.h @@ -172,7 +172,8 @@ static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid) (struct in6_addr *)gid); break; case AF_INET6: - memcpy(gid->raw, &((struct sockaddr_in6 *)addr)->sin6_addr, 16); + *(struct in6_addr *)&gid->raw = + ((struct sockaddr_in6 *)addr)->sin6_addr; break; default: return -EINVAL; @@ -304,7 +305,13 @@ static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac) static inline int rdma_is_multicast_addr(struct in6_addr *addr) { - return addr->s6_addr[0] == 0xff; + u32 ipv4_addr; + + if (addr->s6_addr[0] == 0xff) + return 1; + + memcpy(&ipv4_addr, addr->s6_addr + 12, 4); + return (ipv6_addr_v4mapped(addr) && ipv4_is_multicast(ipv4_addr)); } static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac) diff --git a/include/rdma/ib_hdrs.h b/include/rdma/ib_hdrs.h index 5519f31f043a..c124d515f7d5 100644 --- a/include/rdma/ib_hdrs.h +++ b/include/rdma/ib_hdrs.h @@ -193,8 +193,12 @@ static inline void put_ib_ateth_compare(u64 val, struct ib_atomic_eth *ateth) #define IB_LNH_MASK 3 #define IB_SC_MASK 0xf #define IB_SC_SHIFT 12 +#define IB_SC5_MASK 0x10 #define IB_SL_MASK 0xf #define IB_SL_SHIFT 4 +#define IB_SL_SHIFT 4 +#define IB_LVER_MASK 0xf +#define IB_LVER_SHIFT 8 static inline u8 ib_get_lnh(struct ib_header *hdr) { @@ -206,6 +210,11 @@ static inline u8 ib_get_sc(struct ib_header *hdr) return ((be16_to_cpu(hdr->lrh[0]) >> IB_SC_SHIFT) & IB_SC_MASK); } +static inline bool ib_is_sc5(u16 sc5) +{ + return !!(sc5 & IB_SC5_MASK); +} + static inline u8 ib_get_sl(struct ib_header *hdr) { return ((be16_to_cpu(hdr->lrh[0]) >> IB_SL_SHIFT) & IB_SL_MASK); @@ -221,6 +230,27 @@ static inline u16 ib_get_slid(struct ib_header *hdr) return (be16_to_cpu(hdr->lrh[3])); } +static inline u8 ib_get_lver(struct ib_header *hdr) +{ + return (u8)((be16_to_cpu(hdr->lrh[0]) >> IB_LVER_SHIFT) & + IB_LVER_MASK); +} + +static inline u16 ib_get_len(struct ib_header *hdr) +{ + return (u16)(be16_to_cpu(hdr->lrh[2])); +} + +static inline u32 ib_get_qkey(struct ib_other_headers *ohdr) +{ + return be32_to_cpu(ohdr->u.ud.deth[0]); +} + +static inline u32 ib_get_sqpn(struct ib_other_headers *ohdr) +{ + return ((be32_to_cpu(ohdr->u.ud.deth[1])) & IB_QPN_MASK); +} + /* * BTH */ @@ -229,6 +259,14 @@ static inline u16 ib_get_slid(struct ib_header *hdr) #define IB_BTH_PAD_MASK 3 #define IB_BTH_PKEY_MASK 0xffff #define IB_BTH_PAD_SHIFT 20 +#define IB_BTH_A_MASK 1 +#define IB_BTH_A_SHIFT 31 +#define IB_BTH_M_MASK 1 +#define IB_BTH_M_SHIFT 22 +#define IB_BTH_SE_MASK 1 +#define IB_BTH_SE_SHIFT 23 +#define IB_BTH_TVER_MASK 0xf +#define IB_BTH_TVER_SHIFT 16 static inline u8 ib_bth_get_pad(struct ib_other_headers *ohdr) { @@ -247,4 +285,50 @@ static inline u8 ib_bth_get_opcode(struct ib_other_headers *ohdr) IB_BTH_OPCODE_MASK); } +static inline u8 ib_bth_get_ackreq(struct ib_other_headers *ohdr) +{ + return (u8)((be32_to_cpu(ohdr->bth[2]) >> IB_BTH_A_SHIFT) & + IB_BTH_A_MASK); +} + +static inline u8 ib_bth_get_migreq(struct ib_other_headers *ohdr) +{ + return (u8)((be32_to_cpu(ohdr->bth[0]) >> IB_BTH_M_SHIFT) & + IB_BTH_M_MASK); +} + +static inline u8 ib_bth_get_se(struct ib_other_headers *ohdr) +{ + return (u8)((be32_to_cpu(ohdr->bth[0]) >> IB_BTH_SE_SHIFT) & + IB_BTH_SE_MASK); +} + +static inline u32 ib_bth_get_psn(struct ib_other_headers *ohdr) +{ + return (u32)(be32_to_cpu(ohdr->bth[2])); +} + +static inline u32 ib_bth_get_qpn(struct ib_other_headers *ohdr) +{ + return (u32)((be32_to_cpu(ohdr->bth[1])) & IB_QPN_MASK); +} + +static inline u8 ib_bth_get_becn(struct ib_other_headers *ohdr) +{ + return (u8)((be32_to_cpu(ohdr->bth[1]) >> IB_BECN_SHIFT) & + IB_BECN_MASK); +} + +static inline u8 ib_bth_get_fecn(struct ib_other_headers *ohdr) +{ + return (u8)((be32_to_cpu(ohdr->bth[1]) >> IB_FECN_SHIFT) & + IB_FECN_MASK); +} + +static inline u8 ib_bth_get_tver(struct ib_other_headers *ohdr) +{ + return (u8)((be32_to_cpu(ohdr->bth[0]) >> IB_BTH_TVER_SHIFT) & + IB_BTH_TVER_MASK); +} + #endif /* IB_HDRS_H */ diff --git a/include/rdma/ib_marshall.h b/include/rdma/ib_marshall.h index 68cef3bd50fb..8ebf84ae9ed1 100644 --- a/include/rdma/ib_marshall.h +++ b/include/rdma/ib_marshall.h @@ -38,10 +38,12 @@ #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, +void ib_copy_qp_attr_to_user(struct ib_device *device, + struct ib_uverbs_qp_attr *dst, struct ib_qp_attr *src); -void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst, +void ib_copy_ah_attr_to_user(struct ib_device *device, + struct ib_uverbs_ah_attr *dst, struct rdma_ah_attr *src); void ib_copy_path_rec_to_user(struct ib_user_path_rec *dst, diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 88c32aba32f7..e6df68048517 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -64,6 +64,8 @@ #include <linux/cgroup_rdma.h> #include <uapi/rdma/ib_user_verbs.h> +#define IB_FW_VERSION_NAME_MAX ETHTOOL_FWVERS_LEN + extern struct workqueue_struct *ib_wq; extern struct workqueue_struct *ib_comp_wq; @@ -168,7 +170,7 @@ enum ib_device_cap_flags { IB_DEVICE_UD_AV_PORT_ENFORCE = (1 << 6), IB_DEVICE_CURR_QP_STATE_MOD = (1 << 7), IB_DEVICE_SHUTDOWN_PORT = (1 << 8), - IB_DEVICE_INIT_TYPE = (1 << 9), + /* Not in use, former INIT_TYPE = (1 << 9),*/ IB_DEVICE_PORT_ACTIVE_EVENT = (1 << 10), IB_DEVICE_SYS_IMAGE_GUID = (1 << 11), IB_DEVICE_RC_RNR_NAK_GEN = (1 << 12), @@ -183,7 +185,7 @@ enum ib_device_cap_flags { * which will always contain a usable lkey. */ IB_DEVICE_LOCAL_DMA_LKEY = (1 << 15), - IB_DEVICE_RESERVED /* old SEND_W_INV */ = (1 << 16), + /* Reserved, old SEND_W_INV = (1 << 16),*/ IB_DEVICE_MEM_WINDOW = (1 << 17), /* * Devices should set IB_DEVICE_UD_IP_SUM if they support @@ -218,7 +220,7 @@ enum ib_device_cap_flags { * of I/O operations with single completion queue managed * by hardware. */ - IB_DEVICE_CROSS_CHANNEL = (1 << 27), + IB_DEVICE_CROSS_CHANNEL = (1 << 27), IB_DEVICE_MANAGED_FLOW_STEERING = (1 << 29), IB_DEVICE_SIGNATURE_HANDOVER = (1 << 30), IB_DEVICE_ON_DEMAND_PAGING = (1ULL << 31), @@ -278,6 +280,24 @@ struct ib_rss_caps { u32 max_rwq_indirection_table_size; }; +enum ib_tm_cap_flags { + /* Support tag matching on RC transport */ + IB_TM_CAP_RC = 1 << 0, +}; + +struct ib_xrq_caps { + /* Max size of RNDV header */ + u32 max_rndv_hdr_size; + /* Max number of entries in tag matching list */ + u32 max_num_tags; + /* From enum ib_tm_cap_flags */ + u32 flags; + /* Max number of outstanding list operations */ + u32 max_ops; + /* Max number of SGE in tag matching entry */ + u32 max_sge; +}; + enum ib_cq_creation_flags { IB_CQ_FLAGS_TIMESTAMP_COMPLETION = 1 << 0, IB_CQ_FLAGS_IGNORE_OVERRUN = 1 << 1, @@ -338,6 +358,7 @@ struct ib_device_attr { struct ib_rss_caps rss_caps; u32 max_wq_type_rq; u32 raw_packet_caps; /* Use ib_raw_packet_caps enum */ + struct ib_xrq_caps xrq_caps; }; enum ib_mtu { @@ -549,8 +570,8 @@ struct ib_port_attr { u32 bad_pkey_cntr; u32 qkey_viol_cntr; u16 pkey_tbl_len; - u16 lid; - u16 sm_lid; + u32 sm_lid; + u32 lid; u8 lmc; u8 max_vl_num; u8 sm_sl; @@ -577,7 +598,8 @@ struct ib_device_modify { enum ib_port_modify_flags { IB_PORT_SHUTDOWN = 1, IB_PORT_INIT_TYPE = (1<<2), - IB_PORT_RESET_QKEY_CNTR = (1<<3) + IB_PORT_RESET_QKEY_CNTR = (1<<3), + IB_PORT_OPA_MASK_CHG = (1<<4) }; struct ib_port_modify { @@ -664,6 +686,8 @@ union rdma_network_hdr { }; }; +#define IB_QPN_MASK 0xFFFFFF + enum { IB_MULTICAST_QPN = 0xffffff }; @@ -859,6 +883,7 @@ struct roce_ah_attr { struct opa_ah_attr { u32 dlid; u8 src_path_bits; + bool make_grd; }; struct rdma_ah_attr { @@ -948,7 +973,7 @@ struct ib_wc { u32 src_qp; int wc_flags; u16 pkey_index; - u16 slid; + u32 |