From bded747bb432bc5f7ad6d84ea747368b70ed9df2 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Tue, 30 May 2017 09:42:53 +0300 Subject: net/mlx5: Add raw ethernet local loopback firmware command Add support for raw ethernet local loopback firmware command. Signed-off-by: Huy Nguyen Reviewed-by: Daniel Jurgens Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 11 ++++++++--- include/linux/mlx5/vport.h | 3 ++- 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 87869c04849a..57c75e8b3c19 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1016,7 +1016,8 @@ 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]; @@ -2562,7 +2563,9 @@ 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]; @@ -5229,7 +5232,9 @@ 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]; 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__ */ -- cgit v1.2.3 From 4a2da0b8c0782816f3ae6846ae7942fcbb0f8172 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 30 May 2017 10:05:15 +0300 Subject: IB/mlx5: Add debug control parameters for congestion control This patch adds debug control parameters for congestion control which can be read or written through debugfs. They are for reaction point and notification point nodes. These control parameters are as below: +------------------------------+-----------------------------------------+ | Name | Description | |------------------------------+-----------------------------------------| |rp_clamp_tgt_rate | When set target rate is updated to | | | current rate | |------------------------------+-----------------------------------------| |rp_clamp_tgt_rate_ati | When set update target rate based on | | | timer as well | |------------------------------+-----------------------------------------| |rp_time_reset | time between rate increase if no | | | CNP is received unit in usec | |------------------------------+-----------------------------------------| |rp_byte_reset | Number of bytes between rate inease if | | | no CNP is received | |------------------------------+-----------------------------------------| |rp_threshold | Threshold for reaction point rate | | | control | |------------------------------+-----------------------------------------| |rp_ai_rate | Rate for target rate, unit in Mbps | |------------------------------+-----------------------------------------| |rp_hai_rate | Rate for hyper increase state | | | unit in Mbps | |------------------------------+-----------------------------------------| |rp_min_dec_fac | Minimum factor by which the current | | | transmit rate can be changed when | | | processing a CNP, unit is percerntage | |------------------------------+-----------------------------------------| |rp_min_rate | Minimum value for rate limit, | | | unit in Mbps | |------------------------------+-----------------------------------------| |rp_rate_to_set_on_first_cnp | Rate that is set when first CNP is | | | received, unit is Mbps | |------------------------------+-----------------------------------------| |rp_dce_tcp_g | Used to calculate alpha | |------------------------------+-----------------------------------------| |rp_dce_tcp_rtt | Time between updates of alpha value, | | | unit is usec | |------------------------------+-----------------------------------------| |rp_rate_reduce_monitor_period | Minimum time between consecutive rate | | | reductions | |------------------------------+-----------------------------------------| |rp_initial_alpha_value | Initial value of alpha | |------------------------------+-----------------------------------------| |rp_gd | When CNP is received, flow rate is | | | reduced based on gd, rp_gd is given as | | | log2(rp_gd) | |------------------------------+-----------------------------------------| |np_cnp_dscp | dscp code point for generated cnp | |------------------------------+-----------------------------------------| |np_cnp_prio_mode | 802.1p priority for generated cnp | |------------------------------+-----------------------------------------| |np_cnp_prio | cnp priority mode | +------------------------------+-----------------------------------------+ Signed-off-by: Parav Pandit Reviewed-by: Daniel Jurgens Reviewed-by: Eli Cohen Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 57c75e8b3c19..3e697f672de5 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1188,7 +1188,8 @@ 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]; -- cgit v1.2.3 From 7ecf6d8ff154e6f7471ee537a400d43a5f3b1c57 Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Tue, 30 May 2017 10:18:24 +0300 Subject: IB/mlx5: Restore IB guid/policy for virtual functions When a user sets port_guid, node_guid or policy of an IB virtual function, save this information in "struct mlx5_vf_context". This information will be restored later when pci_resume is called. To make sure this works, one can use aer-inject to generate PCI errors on mlx5 devices and verify if relevant fields are restored after PCI resume. Signed-off-by: Bodong Wang Reviewed-by: Eli Cohen Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index df6ce59a1f95..54221be5f69e 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; @@ -525,6 +532,9 @@ 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 { @@ -842,13 +852,6 @@ 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 }; -- cgit v1.2.3 From c1e0bfc1312d0e06bdb24e6e4e7e10b0b4313ec6 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 30 May 2017 10:29:11 +0300 Subject: net/mlx5: Introduce set delay drop command Add support to SET_DELAY_DROP command. This command will be used in downstream patches for delay packet drop. The timeout value should be indicated by delay_drop_timeout field. Packet processing will be delayed till timeout value passed or until more WQEs are posted. Setting this value to 0 disables the feature. Signed-off-by: Maor Gottlieb Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 25 ++++++++++++++++++++++++- include/linux/mlx5/qp.h | 3 +++ 2 files changed, 27 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3e697f672de5..40c05d29d5bb 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, @@ -840,7 +841,7 @@ 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]; @@ -5853,6 +5854,28 @@ 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 6f41270d80c0..fff4ec13f620 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -561,6 +561,9 @@ 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); -- cgit v1.2.3 From 246ac9814c5b2c0e9916dca5fbf8d6a40245fad1 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 30 May 2017 10:29:12 +0300 Subject: net/mlx5: Introduce general notification event When delay drop timeout is expired, the firmware raises general notification event of DELAY_DROP_TIMEOUT subtype. In addition the feature is disable so the driver have to reactivate the timeout. Signed-off-by: Maor Gottlieb Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/device.h | 5 +++++ include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 3 ++- 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f31a0b5377e1..a47b9ab9f2c9 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, @@ -304,6 +305,10 @@ enum mlx5_event { MLX5_EVENT_TYPE_FPGA_ERROR = 0x20, }; +enum { + MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT = 0x1, +}; + enum { MLX5_PORT_CHANGE_SUBTYPE_DOWN = 1, MLX5_PORT_CHANGE_SUBTYPE_ACTIVE = 4, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 54221be5f69e..758ef40f9316 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -192,6 +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 { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 40c05d29d5bb..4bc57647fad8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -874,7 +874,8 @@ 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]; -- cgit v1.2.3 From 03404e8ae652e02a5e3388224836cef53d7a0988 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 30 May 2017 10:29:13 +0300 Subject: IB/mlx5: Add support to dropless RQ RQs that were configured for "delay drop" will prevent packet drops when their WQEs are depleted. Marking an RQ to be drop-less is done by setting delay_drop_en in RQ context using CREATE_RQ command. Since this feature is globally activated/deactivated by using the SET_DELAY_DROP command on all the marked RQs, we activated/deactivated it according to the number of RQs with 'delay_drop' enabled. When timeout is expired, then the feature is deactivated. Therefore the driver handles the delay drop timeout event and reactivate it. Signed-off-by: Maor Gottlieb Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4bc57647fad8..f350688a12fa 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2519,7 +2519,7 @@ 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]; -- cgit v1.2.3 From 4ce749bd94f697772ac2be4fb7e7a92726e94bfb Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 8 Jun 2017 16:15:10 +0300 Subject: net/mlx5: Report enhanced capabilities for IPoIB Report 'ipoib_enhanced_offloads' capabilities from the core layer, it will be used in the next patch from this series. Signed-off-by: Yishai Hadas Reviewed-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/device.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index a47b9ab9f2c9..c13d71deaeca 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -973,7 +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, @@ -1016,6 +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) -- cgit v1.2.3 From 3fffc82ad6c78fcc9d5d4eca089f00db14ab0358 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 12 Jun 2017 10:36:16 +0300 Subject: IB/mlx5: Fix existence check for extended address vector The extended address vector is the highest bit in be32 variable, but it was compared with the lowest. This patch fixes the endianness of that check and removes already declared define. Fixes: 17d2f88f92ce ("IB/mlx5: Add ODP atomics support") Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/qp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index fff4ec13f620..66d19b611fe4 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -212,7 +212,6 @@ struct mlx5_wqe_ctrl_seg { #define MLX5_WQE_CTRL_OPCODE_MASK 0xff #define MLX5_WQE_CTRL_WQE_INDEX_MASK 0x00ffff00 #define MLX5_WQE_CTRL_WQE_INDEX_SHIFT 8 -#define MLX5_WQE_AV_EXT 0x80000000 enum { MLX5_ETH_WQE_L3_INNER_CSUM = 1 << 4, -- cgit v1.2.3 From 58dcb60a226ee48cc66c96c27b751f06ec2bc5a9 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 19 Jun 2017 07:19:37 +0300 Subject: IB/mlx5: Expose extended error counters This patch adds below requester and responder side error counters, which will be exposed by hardware counters interface and are supported as part of query Q counters command extension. +---------------------------+-------------------------------------+ | Name | Description | |---------------------------+-------------------------------------| |resp_local_length_error | Number of times responder detected | | | local length errors | |---------------------------+-------------------------------------| |resp_cqe_error | Number of CQEs completed with error | | | at responder | |---------------------------+-------------------------------------| |req_cqe_error | Number of CQEs completed with error | | | at requester | |---------------------------+-------------------------------------| |req_remote_invalid_request | Number of times requester detected | | | remote invalid request error | |---------------------------+-------------------------------------| |req_remote_access_error | Number of times requester detected | | | remote access error | |---------------------------+-------------------------------------| |resp_remote_access_error | Number of times responder detected | | | remote access error | |---------------------------+-------------------------------------| |resp_cqe_flush_error | Number of CQEs completed with | | | flushed with error at responder | |---------------------------+-------------------------------------| |req_cqe_flush_error | Number of CQEs completed with | | | flushed with error at requester | +---------------------------+-------------------------------------+ Signed-off-by: Parav Pandit Reviewed-by: Daniel Jurgens Reviewed-by: Eli Cohen Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 44 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 42 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f350688a12fa..5bae70eb25af 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -858,7 +858,7 @@ 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]; @@ -3953,7 +3953,47 @@ 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 { -- cgit v1.2.3 From f3301870161ca293cd14b20a802c5646da02407f Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 21 Jun 2017 09:29:36 +0300 Subject: (IB, net)/mlx4: Add resource utilization support Adding visibility of resource usage of QPs, CQs and counters used by virtual functions. This feature will be used to give the PF administrator more data while debugging VF status. Usage info was added to ALLOC_RES command, to notify the PF if the resource which is being reserved or allocated for the VF will be used by kernel driver or by user verbs. Updated reservation and allocation functions of QP, CQ and counter with additional usage parameter. Signed-off-by: Moshe Shemesh Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx4/device.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index aad5d81dfb44..3607da001ad3 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, }; @@ -748,6 +754,7 @@ struct mlx4_cq { } tasklet_ctx; int reset_notify_added; struct list_head reset_notify; + u8 usage; }; struct mlx4_qp { @@ -757,6 +764,7 @@ struct mlx4_qp { atomic_t refcount; struct completion free; + u8 usage; }; struct mlx4_srq { @@ -1120,7 +1128,7 @@ 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); @@ -1417,7 +1425,7 @@ 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); -- cgit v1.2.3 From 78249c4215840edb95447ec6867b69a7ac1d7a0d Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 13 Jul 2017 11:09:38 +0300 Subject: mlx5: convert to generic pci_alloc_irq_vectors Now that we have a generic code to allocate an array of irq vectors and even correctly spread their affinity, correctly handle cpu hotplug events and more, were much better off using it. Reviewed-by: Christoph Hellwig Acked-by: Leon Romanovsky Signed-off-by: Sagi Grimberg Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index df6ce59a1f95..5bac7f53b4f9 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -597,7 +597,6 @@ 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 */ -- cgit v1.2.3 From a435393acafbf0ecff4deb3e3cb554b34f0d0664 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 13 Jul 2017 11:09:40 +0300 Subject: mlx5: move affinity hints assignments to generic code generic api takes care of spreading affinity similar to what mlx5 open coded (and even handles better asymmetric configurations). Ask the generic API to spread affinity for us, and feed him pre_vectors that do not participate in affinity settings (which is an improvement to what we had before). The affinity assignments should match what mlx5 tried to do earlier but now we do not set affinity to async, cmd and pages dedicated vectors. Also, remove mlx5e_get_cpu and introduce mlx5e_get_node (used for allocation purposes) and mlx5_get_vector_affinity (for indirection table construction) as they provide the needed information. Luckily, we have generic helpers to get cpumask and node given a irq vector. mlx5_get_vector_affinity will be used by mlx5_ib in a subsequent patch. Reviewed-by: Christoph Hellwig Acked-by: Leon Romanovsky Signed-off-by: Sagi Grimberg Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5bac7f53b4f9..579731842c94 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -534,7 +534,6 @@ struct mlx5_core_sriov { }; struct mlx5_irq_info { - cpumask_var_t mask; char name[MLX5_MAX_IRQ_NAME]; }; @@ -1184,4 +1183,10 @@ 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 */ -- cgit v1.2.3 From 24c5dc6610e8a3764fcb885cc3284c12ff1513de Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 13 Jul 2017 11:09:43 +0300 Subject: block: Add rdma affinity based queue mapping helper Like pci and virtio, we add a rdma helper for affinity spreading. This achieves optimal mq affinity assignments according to the underlying rdma device affinity maps. Reviewed-by: Jens Axboe Reviewed-by: Christoph Hellwig Reviewed-by: Max Gurtovoy Signed-off-by: Sagi Grimberg Signed-off-by: Doug Ledford --- include/linux/blk-mq-rdma.h | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 include/linux/blk-mq-rdma.h (limited to 'include/linux') 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 */ -- cgit v1.2.3 From 92d50fc1602ecef44babe411c475344e55e1cdd9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 19 Jul 2017 15:01:06 +0200 Subject: PCI/IB: add support for pci driver attribute groups Some drivers (specifically the nes IB driver), want to create a lot of sysfs driver attributes. Instead of open-coding the creation and removal of these files (and getting it wrong btw), it's a better idea to let the driver core handle all of this logic for us. So add a new field to the pci driver structure, **groups, that allows pci drivers to specify an attribute group list it wishes to have created when it is registered with the driver core. Big bonus is now the driver doesn't race with userspace when the sysfs files are created vs. when the kobject is announced, so any script/tool that actually wanted to use these files will not have to poll waiting for them to show up. Cc: Faisal Latif Cc: Doug Ledford Cc: Sean Hefty Cc: Hal Rosenstock Cc: Bjorn Helgaas Signed-off-by: Greg Kroah-Hartman Acked-by: Bjorn Helgaas Signed-off-by: Doug Ledford --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 4869e66dd659..c421af60f2df 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -729,6 +729,7 @@ 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; }; -- cgit v1.2.3 From 18c90df9f2c00cb35ab8ba747aa0f742ee6bbf6a Mon Sep 17 00:00:00 2001 From: Romain Perier Date: Tue, 22 Aug 2017 13:46:59 +0200 Subject: mlx5: Replace PCI pool old API The PCI pool API is deprecated. This commit replaces the PCI pool old API by the appropriate function with the DMA pool API. Signed-off-by: Romain Perier Reviewed-by: Peter Senna Tschudin Acked-by: Doug Ledford Tested-by: Doug Ledford Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 099fe311f272..db40bc4055c7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -299,7 +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; -- cgit v1.2.3 From 8b7ff7f3b301de52924cb2cf3fed47b181893116 Mon Sep 17 00:00:00 2001 From: Ilya Lesokhin Date: Thu, 17 Aug 2017 15:52:29 +0300 Subject: IB/mlx5: Enable UMR for MRs created with reg_create This patch is the first step in decoupling UMR usage and allocation from the MR cache. The only functional change in this patch is to enables UMR for MRs created with reg_create. This change fixes a bug where ODP memory regions that were not allocated from the MR cache did not have UMR enabled. Signed-off-by: Ilya Lesokhin Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index db40bc4055c7..99d88624ad07 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1093,7 +1093,7 @@ 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 -- cgit v1.2.3 From a550ddfc543e250798048cf4eabe721cd85ac724 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 17 Aug 2017 15:52:33 +0300 Subject: IB/mlx5: Add support for multi underlay QP Set underlay QPN as part of flow rule when it's applicable. There is one root flow table in the NIC RX namespace and all the underlay QPs steer the traffic to this flow table. In order to prevent QP to get traffic which is not target to its underlay QP, we need to set the underlay QP number as part of the steering matching. Note: When multicast traffic is sent the QPN filtering is done by the firmware as some early step. Adding the QPN match on the flow table entry is wrong as by that time the target QPN holds the multicast address (e.g. FF(s)) and it won't match. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 5bae70eb25af..6563500c85de 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -295,8 +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 { @@ -432,7 +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 { -- cgit v1.2.3 From 795b609c8b59f8f20fa9d72bf8b4ae3b8aa5582c Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Thu, 17 Aug 2017 15:52:34 +0300 Subject: IB/mlx5: Allow posting multi packet send WQEs if hardware supports Set the field to allow posting multi packet send WQEs if hardware supports this feature. This doesn't mean the send WQEs will be for multi packet unless the send WQE was prepared according to multi packet send WQE format. User space shall use flag MLX5_IB_ALLOW_MPW to check if hardware supports MPW and allows MPW in SQ context. Signed-off-by: Bodong Wang Reviewed-by: Daniel Jurgens Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6563500c85de..6865e60ba473 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2445,7 +2445,7 @@ 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]; -- cgit v1.2.3 From 050da902adde8faf6b1bef15ac4876ae145358f4 Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Thu, 17 Aug 2017 15:52:35 +0300 Subject: IB/mlx5: Report mlx5 enhanced multi packet WQE capability Expose enhanced multi packet WQE capability to user space through query_device by uhw. Signed-off-by: Bodong Wang Reviewed-by: Daniel Jurgens Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6865e60ba473..4eff0b8a1482 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -604,7 +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]; -- cgit v1.2.3 From 6e44636aeab19259f804c8abca57a95ddc01df66 Mon Sep 17 00:00:00 2001 From: Artemy Kovalyov Date: Tue, 15 Aug 2017 11:59:02 +0300 Subject: net/mlx5: Update HW layout definitions * add offload_type field to mlx5_ifc_qpc_bits * update mlx5_ifc_xrqc_bits layout Signed-off-by: Artemy Kovalyov Reviewed-by: Yossi Itigin Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4eff0b8a1482..e27283ab3667 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2022,6 +2022,10 @@ enum { MLX5_QPC_PM_STATE_MIGRATED = 0x3, }; +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, @@ -2065,7 +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]; @@ -3010,7 +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; }; -- cgit v1.2.3 From 5b3ec3fcb6bbe081279c73fb574af8c72f14cea0 Mon Sep 17 00:00:00 2001 From: Artemy Kovalyov Date: Thu, 17 Aug 2017 15:52:10 +0300 Subject: net/mlx5: Add XRQ support Add support to new XRQ(eXtended shared Receive Queue) hardware object. It supports SRQ semantics with addition of extended receive buffers topologies and offloads. Currently supports tag matching topology and rendezvouz offload. Signed-off-by: Artemy Kovalyov Reviewed-by: Yossi Itigin Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/srq.h | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 99d88624ad07..c33e6f7a1afb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -418,6 +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 { 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; -- cgit v1.2.3