diff options
274 files changed, 13778 insertions, 3838 deletions
diff --git a/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml b/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml index 56cbb42b5aea..2735c6a4f336 100644 --- a/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml +++ b/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml @@ -19,6 +19,7 @@ properties: - qcom,qca2066-bt - qcom,qca6174-bt - qcom,qca9377-bt + - qcom,wcn3988-bt - qcom,wcn3990-bt - qcom,wcn3991-bt - qcom,wcn3998-bt @@ -111,6 +112,7 @@ allOf: compatible: contains: enum: + - qcom,wcn3988-bt - qcom,wcn3990-bt - qcom,wcn3991-bt - qcom,wcn3998-bt diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml index 6b0d359367da..9f6a5ccbcefe 100644 --- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml @@ -66,6 +66,7 @@ properties: - mii - gmii - sgmii + - psgmii - qsgmii - qusgmii - tbi diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index f6df0b3fd502..d1ebcd927149 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -6,6 +6,16 @@ protocol: genetlink-legacy doc: Partial family for Devlink. +definitions: + - + type: enum + name: sb-pool-type + entries: + - + name: ingress + - + name: egress + attribute-sets: - name: devlink @@ -25,6 +35,46 @@ attribute-sets: # TODO: fill in the attributes in between - + name: sb-index + type: u32 + value: 11 + + # TODO: fill in the attributes in between + + - + name: sb-pool-index + type: u16 + value: 17 + + - + name: sb-pool-type + type: u8 + enum: sb-pool-type + + # TODO: fill in the attributes in between + + - + name: sb-tc-index + type: u16 + value: 22 + + # TODO: fill in the attributes in between + + - + name: param-name + type: string + value: 81 + + # TODO: fill in the attributes in between + + - + name: region-name + type: string + value: 88 + + # TODO: fill in the attributes in between + + - name: info-driver-name type: string value: 98 @@ -56,9 +106,34 @@ attribute-sets: # TODO: fill in the attributes in between - + name: health-reporter-name + type: string + value: 115 + + # TODO: fill in the attributes in between + + - + name: trap-name + type: string + value: 130 + + # TODO: fill in the attributes in between + + - + name: trap-group-name + type: string + value: 135 + + - name: reload-failed type: u8 - value: 136 + + # TODO: fill in the attributes in between + + - + name: trap-policer-id + type: u32 + value: 142 # TODO: fill in the attributes in between @@ -103,6 +178,21 @@ attribute-sets: type: nest multi-attr: true nested-attributes: dl-reload-act-stats + + # TODO: fill in the attributes in between + + - + name: rate-node-name + type: string + value: 168 + + # TODO: fill in the attributes in between + + - + name: linecard-index + type: u32 + value: 171 + - name: dl-dev-stats subset-of: devlink @@ -188,6 +278,195 @@ operations: dump: reply: *get-reply + - + name: port-get + doc: Get devlink port instances. + attribute-set: devlink + dont-validate: + - strict + + do: + pre: devlink-nl-pre-doit-port + post: devlink-nl-post-doit + request: + value: 5 + attributes: &port-id-attrs + - bus-name + - dev-name + - port-index + reply: + value: 7 + attributes: *port-id-attrs + dump: + request: + attributes: *dev-id-attrs + reply: + value: 3 # due to a bug, port dump returns DEVLINK_CMD_NEW + attributes: *port-id-attrs + + # TODO: fill in the operations in between + + - + name: sb-get + doc: Get shared buffer instances. + attribute-set: devlink + dont-validate: + - strict + + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + value: 11 + attributes: &sb-id-attrs + - bus-name + - dev-name + - sb-index + reply: &sb-get-reply + value: 11 + attributes: *sb-id-attrs + dump: + request: + attributes: *dev-id-attrs + reply: *sb-get-reply + + # TODO: fill in the operations in between + + - + name: sb-pool-get + doc: Get shared buffer pool instances. + attribute-set: devlink + dont-validate: + - strict + + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + value: 15 + attributes: &sb-pool-id-attrs + - bus-name + - dev-name + - sb-index + - sb-pool-index + reply: &sb-pool-get-reply + value: 15 + attributes: *sb-pool-id-attrs + dump: + request: + attributes: *dev-id-attrs + reply: *sb-pool-get-reply + + # TODO: fill in the operations in between + + - + name: sb-port-pool-get + doc: Get shared buffer port-pool combinations and threshold. + attribute-set: devlink + dont-validate: + - strict + + do: + pre: devlink-nl-pre-doit-port + post: devlink-nl-post-doit + request: + value: 19 + attributes: &sb-port-pool-id-attrs + - bus-name + - dev-name + - port-index + - sb-index + - sb-pool-index + reply: &sb-port-pool-get-reply + value: 19 + attributes: *sb-port-pool-id-attrs + dump: + request: + attributes: *dev-id-attrs + reply: *sb-port-pool-get-reply + + # TODO: fill in the operations in between + + - + name: sb-tc-pool-bind-get + doc: Get shared buffer port-TC to pool bindings and threshold. + attribute-set: devlink + dont-validate: + - strict + + do: + pre: devlink-nl-pre-doit-port + post: devlink-nl-post-doit + request: + value: 23 + attributes: &sb-tc-pool-bind-id-attrs + - bus-name + - dev-name + - port-index + - sb-index + - sb-pool-type + - sb-tc-index + reply: &sb-tc-pool-bind-get-reply + value: 23 + attributes: *sb-tc-pool-bind-id-attrs + dump: + request: + attributes: *dev-id-attrs + reply: *sb-tc-pool-bind-get-reply + + # TODO: fill in the operations in between + + - + name: param-get + doc: Get param instances. + attribute-set: devlink + dont-validate: + - strict + + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + value: 38 + attributes: ¶m-id-attrs + - bus-name + - dev-name + - param-name + reply: ¶m-get-reply + value: 38 + attributes: *param-id-attrs + dump: + request: + attributes: *dev-id-attrs + reply: *param-get-reply + + # TODO: fill in the operations in between + + - + name: region-get + doc: Get region instances. + attribute-set: devlink + dont-validate: + - strict + + do: + pre: devlink-nl-pre-doit-port-optional + post: devlink-nl-post-doit + request: + value: 42 + attributes: ®ion-id-attrs + - bus-name + - dev-name + - port-index + - region-name + reply: ®ion-get-reply + value: 42 + attributes: *region-id-attrs + dump: + request: + attributes: *dev-id-attrs + reply: *region-get-reply + # TODO: fill in the operations in between - @@ -216,3 +495,179 @@ operations: - info-version-stored dump: reply: *info-get-reply + + - + name: health-reporter-get + doc: Get health reporter instances. + attribute-set: devlink + dont-validate: + - strict + + do: + pre: devlink-nl-pre-doit-port-optional + post: devlink-nl-post-doit + request: + attributes: &health-reporter-id-attrs + - bus-name + - dev-name + - port-index + - health-reporter-name + reply: &health-reporter-get-reply + attributes: *health-reporter-id-attrs + dump: + request: + attributes: *port-id-attrs + reply: *health-reporter-get-reply + + # TODO: fill in the operations in between + + - + name: trap-get + doc: Get trap instances. + attribute-set: devlink + dont-validate: + - strict + + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + value: 61 + attributes: &trap-id-attrs + - bus-name + - dev-name + - trap-name + reply: &trap-get-reply + value: 61 + attributes: *trap-id-attrs + dump: + request: + attributes: *dev-id-attrs + reply: *trap-get-reply + + # TODO: fill in the operations in between + + - + name: trap-group-get + doc: Get trap group instances. + attribute-set: devlink + dont-validate: + - strict + + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + value: 65 + attributes: &trap-group-id-attrs + - bus-name + - dev-name + - trap-group-name + reply: &trap-group-get-reply + value: 65 + attributes: *trap-group-id-attrs + dump: + request: + attributes: *dev-id-attrs + reply: *trap-group-get-reply + + # TODO: fill in the operations in between + + - + name: trap-policer-get + doc: Get trap policer instances. + attribute-set: devlink + dont-validate: + - strict + + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + value: 69 + attributes: &trap-policer-id-attrs + - bus-name + - dev-name + - trap-policer-id + reply: &trap-policer-get-reply + value: 69 + attributes: *trap-policer-id-attrs + dump: + request: + attributes: *dev-id-attrs + reply: *trap-policer-get-reply + + # TODO: fill in the operations in between + + - + name: rate-get + doc: Get rate instances. + attribute-set: devlink + dont-validate: + - strict + + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + value: 74 + attributes: &rate-id-attrs + - bus-name + - dev-name + - port-index + - rate-node-name + reply: &rate-get-reply + value: 74 + attributes: *rate-id-attrs + dump: + request: + attributes: *dev-id-attrs + reply: *rate-get-reply + + # TODO: fill in the operations in between + + - + name: linecard-get + doc: Get line card instances. + attribute-set: devlink + dont-validate: + - strict + + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + value: 78 + attributes: &linecard-id-attrs + - bus-name + - dev-name + - linecard-index + reply: &linecard-get-reply + value: 78 + attributes: *linecard-id-attrs + dump: + request: + attributes: *dev-id-attrs + reply: *linecard-get-reply + + # TODO: fill in the operations in between + + - + name: selftests-get + doc: Get device selftest instances. + attribute-set: devlink + dont-validate: + - strict + - dump + + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + value: 82 + attributes: *dev-id-attrs + reply: &selftests-get-reply + value: 82 + attributes: *dev-id-attrs + dump: + reply: *selftests-get-reply diff --git a/Documentation/netlink/specs/ovs_vport.yaml b/Documentation/netlink/specs/ovs_vport.yaml index 17336455bec1..ef298b001445 100644 --- a/Documentation/netlink/specs/ovs_vport.yaml +++ b/Documentation/netlink/specs/ovs_vport.yaml @@ -82,6 +82,10 @@ attribute-sets: enum-name: ovs-vport-attr attributes: - + name: unspec + type: unused + value: 0 + - name: port-no type: u32 - @@ -121,6 +125,20 @@ operations: name-prefix: ovs-vport-cmd- list: - + name: new + doc: Create a new OVS vport + attribute-set: vport + fixed-header: ovs-header + do: + request: + attributes: + - name + - type + - upcall-pid + - dp-ifindex + - ifindex + - options + - name: get doc: Get / dump OVS vport configuration and state value: 3 diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst index a395df9c2751..008e560e12b5 100644 --- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst @@ -683,6 +683,12 @@ the software port. time protocol. - Error + * - `ptp_cq[i]_late_cqe` + - Number of times a CQE has been delivered on the PTP timestamping CQ when + the CQE was not expected since a certain amount of time had elapsed where + the device typically ensures not posting the CQE. + - Error + .. [#ring_global] The corresponding ring and global counters do not share the same name (i.e. do not follow the common naming scheme). diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst deleted file mode 100644 index a4edf908b707..000000000000 --- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst +++ /dev/null @@ -1,313 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB -.. include:: <isonum.txt> - -======= -Devlink -======= - -:Copyright: |copy| 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. - -Contents -======== - -- `Info`_ -- `Parameters`_ -- `Health reporters`_ - -Info -==== - -The devlink info reports the running and stored firmware versions on device. -It also prints the device PSID which represents the HCA board type ID. - -User command example:: - - $ devlink dev info pci/0000:00:06.0 - pci/0000:00:06.0: - driver mlx5_core - versions: - fixed: - fw.psid MT_0000000009 - running: - fw.version 16.26.0100 - stored: - fw.version 16.26.0100 - -Parameters -========== - -flow_steering_mode: Device flow steering mode ---------------------------------------------- -The flow steering mode parameter controls the flow steering mode of the driver. -Two modes are supported: - -1. 'dmfs' - Device managed flow steering. -2. 'smfs' - Software/Driver managed flow steering. - -In DMFS mode, the HW steering entities are created and managed through the -Firmware. -In SMFS mode, the HW steering entities are created and managed though by -the driver directly into hardware without firmware intervention. - -SMFS mode is faster and provides better rule insertion rate compared to default DMFS mode. - -User command examples: - -- Set SMFS flow steering mode:: - - $ devlink dev param set pci/0000:06:00.0 name flow_steering_mode value "smfs" cmode runtime - -- Read device flow steering mode:: - - $ devlink dev param show pci/0000:06:00.0 name flow_steering_mode - pci/0000:06:00.0: - name flow_steering_mode type driver-specific - values: - cmode runtime value smfs - -enable_roce: RoCE enablement state ----------------------------------- -If the device supports RoCE disablement, RoCE enablement state controls device -support for RoCE capability. Otherwise, the control occurs in the driver stack. -When RoCE is disabled at the driver level, only raw ethernet QPs are supported. - -To change RoCE enablement state, a user must change the driverinit cmode value -and run devlink reload. - -User command examples: - -- Disable RoCE:: - - $ devlink dev param set pci/0000:06:00.0 name enable_roce value false cmode driverinit - $ devlink dev reload pci/0000:06:00.0 - -- Read RoCE enablement state:: - - $ devlink dev param show pci/0000:06:00.0 name enable_roce - pci/0000:06:00.0: - name enable_roce type generic - values: - cmode driverinit value true - -esw_port_metadata: Eswitch port metadata state ----------------------------------------------- -When applicable, disabling eswitch metadata can increase packet rate -up to 20% depending on the use case and packet sizes. - -Eswitch port metadata state controls whether to internally tag packets with -metadata. Metadata tagging must be enabled for multi-port RoCE, failover -between representors and stacked devices. -By default metadata is enabled on the supported devices in E-switch. -Metadata is applicable only for E-switch in switchdev mode and -users may disable it when NONE of the below use cases will be in use: - -1. HCA is in Dual/multi-port RoCE mode. -2. VF/SF representor bonding (Usually used for Live migration) -3. Stacked devices - -When metadata is disabled, the above use cases will fail to initialize if -users try to enable them. - -- Show eswitch port metadata:: - - $ devlink dev param show pci/0000:06:00.0 name esw_port_metadata - pci/0000:06:00.0: - name esw_port_metadata type driver-specific - values: - cmode runtime value true - -- Disable eswitch port metadata:: - - $ devlink dev param set pci/0000:06:00.0 name esw_port_metadata value false cmode runtime - -- Change eswitch mode to switchdev mode where after choosing the metadata value:: - - $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev - -hairpin_num_queues: Number of hairpin queues --------------------------------------------- -We refer to a TC NIC rule that involves forwarding as "hairpin". - -Hairpin queues are mlx5 hardware specific implementation for hardware -forwarding of such packets. - -- Show the number of hairpin queues:: - - $ devlink dev param show pci/0000:06:00.0 name hairpin_num_queues - pci/0000:06:00.0: - name hairpin_num_queues type driver-specific - values: - cmode driverinit value 2 - -- Change the number of hairpin queues:: - - $ devlink dev param set pci/0000:06:00.0 name hairpin_num_queues value 4 cmode driverinit - -hairpin_queue_size: Size of the hairpin queues ----------------------------------------------- -Control the size of the hairpin queues. - -- Show the size of the hairpin queues:: - - $ devlink dev param show pci/0000:06:00.0 name hairpin_queue_size - pci/0000:06:00.0: - name hairpin_queue_size type driver-specific - values: - cmode driverinit value 1024 - -- Change the size (in packets) of the hairpin queues:: - - $ devlink dev param set pci/0000:06:00.0 name hairpin_queue_size value 512 cmode driverinit - -Health reporters -================ - -tx reporter ------------ -The tx reporter is responsible for reporting and recovering of the following two error scenarios: - -- tx timeout - Report on kernel tx timeout detection. - Recover by searching lost interrupts. -- tx error completion - Report on error tx completion. - Recover by flushing the tx queue and reset it. - -tx reporter also support on demand diagnose callback, on which it provides -real time information of its send queues status. - -User commands examples: - -- Diagnose send queues status:: - - $ devlink health diagnose pci/0000:82:00.0 reporter tx - -.. note:: - This command has valid output only when interface is up, otherwise the command has empty output. - -- Show number of tx errors indicated, number of recover flows ended successfully, - is autorecover enabled and graceful period from last recover:: - - $ devlink health show pci/0000:82:00.0 reporter tx - -rx reporter ------------ -The rx reporter is responsible for reporting and recovering of the following two error scenarios: - -- rx queues' initialization (population) timeout - Population of rx queues' descriptors on ring initialization is done - in napi context via triggering an irq. In case of a failure to get - the minimum amount of descriptors, a timeout would occur, and - descriptors could be recovered by polling the EQ (Event Queue). -- rx completions with errors (reported by HW on interrupt context) - Report on rx completion error. - Recover (if needed) by flushing the related queue and reset it. - -rx reporter also supports on demand diagnose callback, on which it -provides real time information of its receive queues' status. - -- Diagnose rx queues' status and corresponding completion queue:: - - $ devlink health diagnose pci/0000:82:00.0 reporter rx - -NOTE: This command has valid output only when interface is up. Otherwise, the command has empty output. - -- Show number of rx errors indicated, number of recover flows ended successfully, - is autorecover enabled, and graceful period from last recover:: - - $ devlink health show pci/0000:82:00.0 reporter rx - -fw reporter ------------ -The fw reporter implements `diagnose` and `dump` callbacks. -It follows symptoms of fw error such as fw syndrome by triggering -fw core dump and storing it into the dump buffer. -The fw reporter diagnose command can be triggered any time by the user to check -current fw status. - -User commands examples: - -- Check fw heath status:: - - $ devlink health diagnose pci/0000:82:00.0 reporter fw - -- Read FW core dump if already stored or trigger new one:: - - $ devlink health dump show pci/0000:82:00.0 reporter fw - -.. note:: - This command can run only on the PF which has fw tracer ownership, - running it on other PF or any VF will return "Operation not permitted". - -fw fatal reporter ------------------ -The fw fatal reporter implements `dump` and `recover` callbacks. -It follows fatal errors indications by CR-space dump and recover flow. -The CR-space dump uses vsc interface which is valid even if the FW command -interface is not functional, which is the case in most FW fatal errors. -The recover function runs recover flow which reloads the driver and triggers fw -reset if needed. -On firmware error, the health buffer is dumped into the dmesg. The log -level is derived from the error's severity (given in health buffer). - -User commands examples: - -- Run fw recover flow manually:: - - $ devlink health recover pci/0000:82:00.0 reporter fw_fatal - -- Read FW CR-space dump if already stored or trigger new one:: - - $ devlink health dump show pci/0000:82:00.1 reporter fw_fatal - -.. note:: - This command can run only on PF. - -vnic reporter -------------- -The vnic reporter implements only the `diagnose` callback. -It is responsible for querying the vnic diagnostic counters from fw and displaying -them in realtime. - -Description of the vnic counters: - -- total_q_under_processor_handle - number of queues in an error state due to - an async error or errored command. -- send_queue_priority_update_flow - number of QP/SQ priority/SL update events. -- cq_overrun - number of times CQ entered an error state due to an overflow. -- async_eq_overrun - number of times an EQ mapped to async events was overrun. - comp_eq_overrun number of times an EQ mapped to completion events was - overrun. -- quota_exceeded_command - number of commands issued and failed due to quota exceeded. -- invalid_command - number of commands issued and failed dues to any reason other than quota - exceeded. -- nic_receive_steering_discard - number of packets that completed RX flow - steering but were discarded due to a mismatch in flow table. -- generated_pkt_steering_fail - number of packets generated by the VNIC experiencing unexpected steering - failure (at any point in steering flow). -- handled_pkt_steering_fail - number of packets handled by the VNIC experiencing unexpected steering - failure (at any point in steering flow owned by the VNIC, including the FDB - for the eswitch owner). - -User commands examples: - -- Diagnose PF/VF vnic counters:: - - $ devlink health diagnose pci/0000:82:00.1 reporter vnic - -- Diagnose representor vnic counters (performed by supplying devlink port of the - representor, which can be obtained via devlink port command):: - - $ devlink health diagnose pci/0000:82:00.1/65537 reporter vnic - -.. note:: - This command can run over all interfaces such as PF/VF and representor ports. diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/index.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/index.rst index 3fdcd6b61ccf..581a91caa579 100644 --- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/index.rst +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/index.rst @@ -13,7 +13,6 @@ Contents: :maxdepth: 2 kconfig - devlink switchdev tracepoints counters diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst index 202798d6501e..702f204a3dbd 100644 --- a/Documentation/networking/devlink/mlx5.rst +++ b/Documentation/networking/devlink/mlx5.rst @@ -18,6 +18,11 @@ Parameters * - ``enable_roce`` - driverinit - Type: Boolean + + If the device supports RoCE disablement, RoCE enablement state controls + device support for RoCE capability. Otherwise, the control occurs in the + driver stack. When RoCE is disabled at the driver level, only raw + ethernet QPs are supported. * - ``io_eq_size`` - driverinit - The range is between 64 and 4096. @@ -48,6 +53,9 @@ parameters. * ``smfs`` Software managed flow steering. In SMFS mode, the HW steering entities are created and manage through the driver without firmware intervention. + + SMFS mode is faster and provides better rule insertion rate compared to + default DMFS mode. * - ``fdb_large_groups`` - u32 - driverinit @@ -71,7 +79,24 @@ parameters. deprecated. Default: disabled + * - ``esw_port_metadata`` + - Boolean + - runtime + - When applicable, disabling eswitch metadata can increase packet rate up + to 20% depending on the use case and packet sizes. + + Eswitch port metadata state controls whether to internally tag packets + with metadata. Metadata tagging must be enabled for multi-port RoCE, + failover between representors and stacked devices. By default metadata is + enabled on the supported devices in E-switch. Metadata is applicable only + for E-switch in switchdev mode and users may disable it when NONE of the + below use cases will be in use: + 1. HCA is in Dual/multi-port RoCE mode. + 2. VF/SF representor bonding (Usually used for Live migration) + 3. Stacked devices + When metadata is disabled, the above use cases will fail to initialize if + users try to enable them. * - ``hairpin_num_queues`` - u32 - driverinit @@ -104,3 +129,160 @@ The ``mlx5`` driver reports the following versions * - ``fw.version`` - stored, running - Three digit major.minor.subminor firmware version number. + +Health reporters +================ + +tx reporter +----------- +The tx reporter is responsible for reporting and recovering of the following three error scenarios: + +- tx timeout + Report on kernel tx timeout detection. + Recover by searching lost interrupts. +- tx error completion + Report on error tx completion. + Recover by flushing the tx queue and reset it. +- tx PTP port timestamping CQ unhealthy + Report too many CQEs never delivered on port ts CQ. + Recover by flushing and re-creating all PTP channels. + +tx reporter also support on demand diagnose callback, on which it provides +real time information of its send queues status. + +User commands examples: + +- Diagnose send queues status:: + + $ devlink health diagnose pci/0000:82:00.0 reporter tx + +.. note:: + This command has valid output only when interface is up, otherwise the command has empty output. + +- Show number of tx errors indicated, number of recover flows ended successfully, + is autorecover enabled and graceful period from last recover:: + + $ devlink health show pci/0000:82:00.0 reporter tx + +rx reporter +----------- +The rx reporter is responsible for reporting and recovering of the following two error scenarios: + +- rx queues' initialization (population) timeout + Population of rx queues' descriptors on ring initialization is done + in napi context via triggering an irq. In case of a failure to get + the minimum amount of descriptors, a timeout would occur, and + descriptors could be recovered by polling the EQ (Event Queue). +- rx completions with errors (reported by HW on interrupt context) + Report on rx completion error. + Recover (if needed) by flushing the related queue and reset it. + +rx reporter also supports on demand diagnose callback, on which it +provides real time information of its receive queues' status. + +- Diagnose rx queues' status and corresponding completion queue:: + + $ devlink health diagnose pci/0000:82:00.0 reporter rx + +.. note:: + This command has valid output only when interface is up. Otherwise, the command has empty output. + +- Show number of rx errors indicated, number of recover flows ended successfully, + is autorecover enabled, and graceful period from last recover:: + + $ devlink health show pci/0000:82:00.0 reporter rx + +fw reporter +----------- +The fw reporter implements `diagnose` and `dump` callbacks. +It follows symptoms of fw error such as fw syndrome by triggering +fw core dump and storing it into the dump buffer. +The fw reporter diagnose command can be triggered any time by the user to check +current fw status. + +User commands examples: + +- Check fw heath status:: + + $ devlink health diagnose pci/0000:82:00.0 reporter fw + +- Read FW core dump if already stored or trigger new one:: + + $ devlink health dump show pci/0000:82:00.0 reporter fw + +.. note:: + This command can run only on the PF which has fw tracer ownership, + running it on other PF or any VF will return "Operation not permitted". + +fw fatal reporter +----------------- +The fw fatal reporter implements `dump` and `recover` callbacks. +It follows fatal errors indications by CR-space dump and recover flow. +The CR-space dump uses vsc interface which is valid even if the FW command +interface is not functional, which is the case in most FW fatal errors. +The recover function runs recover flow which reloads the driver and triggers fw +reset if needed. +On firmware error, the health buffer is dumped into the dmesg. The log +level is derived from the error's severity (given in health buffer). + +User commands examples: + +- Run fw recover flow manually:: + + $ devlink health recover pci/0000:82:00.0 reporter fw_fatal + +- Read FW CR-space dump if already stored or trigger new one:: + + $ devlink health dump show pci/0000:82:00.1 reporter fw_fatal + +.. note:: + This command can run only on PF. + +vnic reporter +------------- +The vnic reporter implements only the `diagnose` callback. +It is responsible for querying the vnic diagnostic counters from fw and displaying +them in realtime. + +Description of the vnic counters: + +- total_q_under_processor_handle + number of queues in an error state due to + an async error or errored command. +- send_queue_priority_update_flow + number of QP/SQ priority/SL update events. +- cq_overrun + number of times CQ entered an error state due to an overflow. +- async_eq_overrun + number of times an EQ mapped to async events was overrun. + comp_eq_overrun number of times an EQ mapped to completion events was + overrun. +- quota_exceeded_command + number of commands issued and failed due to quota exceeded. +- invalid_command + number of commands issued and failed dues to any reason other than quota + exceeded. +- nic_receive_steering_discard + number of packets that completed RX flow + steering but were discarded due to a mismatch in flow table. +- generated_pkt_steering_fail + number of packets generated by the VNIC experiencing unexpected steering + failure (at any point in steering flow). +- handled_pkt_steering_fail + number of packets handled by the VNIC experiencing unexpected steering + failure (at any point in steering flow owned by the VNIC, including the FDB + for the eswitch owner). + +User commands examples: + +- Diagnose PF/VF vnic counters:: + + $ devlink health diagnose pci/0000:82:00.1 reporter vnic + +- Diagnose representor vnic counters (performed by supplying devlink port of the + representor, which can be obtained via devlink port command):: + + $ devlink health diagnose pci/0000:82:00.1/65537 reporter vnic + +.. note:: + This command can run over all interfaces such as PF/VF and representor ports. diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst index b7ac4c64cf67..1283240d7620 100644 --- a/Documentation/networking/phy.rst +++ b/Documentation/networking/phy.rst @@ -323,6 +323,10 @@ Some of the interface modes are described below: contrast with the 1000BASE-X phy mode used for Clause 38 and 39 PMDs, this interface mode has different autonegotiation and only supports full duplex. +``PHY_INTERFACE_MODE_PSGMII`` + This is the Penta SGMII mode, it is similar to QSGMII but it combines 5 + SGMII lines into a single link compared to 4 on QSGMII. + Pause frames / flow control =========================== diff --git a/MAINTAINERS b/MAINTAINERS index d984c9a7b12c..f150561a396e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14658,7 +14658,7 @@ F: drivers/rtc/rtc-ntxec.c F: include/linux/mfd/ntxec.h NETRONOME ETHERNET DRIVERS -M: Simon Horman <[email protected]> +M: Louis Peens <[email protected]> R: Jakub Kicinski <[email protected]> S: Maintained diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index cddae6f4b00f..d3538bd83fb3 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -159,7 +159,7 @@ static int drbd_msg_sprintf_info(struct sk_buff *skb, const char *fmt, ...) static int drbd_adm_prepare(struct drbd_config_context *adm_ctx, struct sk_buff *skb, struct genl_info *info, unsigned flags) { - struct drbd_genlmsghdr *d_in = info->userhdr; + struct drbd_genlmsghdr *d_in = genl_info_userhdr(info); const u8 cmd = info->genlhdr->cmd; int err; @@ -1396,8 +1396,9 @@ static void drbd_suspend_al(struct drbd_device *device) static bool should_set_defaults(struct genl_info *info) { - unsigned flags = ((struct drbd_genlmsghdr*)info->userhdr)->flags; - return 0 != (flags & DRBD_GENL_F_SET_DEFAULTS); + struct drbd_genlmsghdr *dh = genl_info_userhdr(info); + + return 0 != (dh->flags & DRBD_GENL_F_SET_DEFAULTS); } static unsigned int drbd_al_extents_max(struct drbd_backing_dev *bdev) @@ -4276,7 +4277,7 @@ static void device_to_info(struct device_info *info, int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context adm_ctx; - struct drbd_genlmsghdr *dh = info->userhdr; + struct drbd_genlmsghdr *dh = genl_info_userhdr(info); enum drbd_ret_code retcode; retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE); diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c index de2ea589aa49..0a5445ac5e1b 100644 --- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -24,6 +24,7 @@ #define BDADDR_BCM20702A1 (&(bdaddr_t) {{0x00, 0x00, 0xa0, 0x02, 0x70, 0x20}}) #define BDADDR_BCM2076B1 (&(bdaddr_t) {{0x79, 0x56, 0x00, 0xa0, 0x76, 0x20}}) #define BDADDR_BCM43430A0 (&(bdaddr_t) {{0xac, 0x1f, 0x12, 0xa0, 0x43, 0x43}}) +#define BDADDR_BCM43430A1 (&(bdaddr_t) {{0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa}}) #define BDADDR_BCM4324B3 (&(bdaddr_t) {{0x00, 0x00, 0x00, 0xb3, 0x24, 0x43}}) #define BDADDR_BCM4330B1 (&(bdaddr_t) {{0x00, 0x00, 0x00, 0xb1, 0x30, 0x43}}) #define BDADDR_BCM4334B0 (&(bdaddr_t) {{0x00, 0x00, 0x00, 0xb0, 0x34, 0x43}}) @@ -115,6 +116,9 @@ int btbcm_check_bdaddr(struct hci_dev *hdev) * * The address 43:43:A0:12:1F:AC indicates a BCM43430A0 controller * with no configured address. + * + * The address AA:AA:AA:AA:AA:AA indicates a BCM43430A1 controller + * with no configured address. */ if (!bacmp(&bda->bdaddr, BDADDR_BCM20702A0) || !bacmp(&bda->bdaddr, BDADDR_BCM20702A1) || @@ -124,6 +128,7 @@ int btbcm_check_bdaddr(struct hci_dev *hdev) !bacmp(&bda->bdaddr, BDADDR_BCM4334B0) || !bacmp(&bda->bdaddr, BDADDR_BCM4345C5) || !bacmp(&bda->bdaddr, BDADDR_BCM43430A0) || + !bacmp(&bda->bdaddr, BDADDR_BCM43430A1) || !bacmp(&bda->bdaddr, BDADDR_BCM43341B)) { /* Try falling back to BDADDR EFI variable */ if (btbcm_set_bdaddr_from_efi(hdev) != 0) { diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index d9349ba48281..633e8d9bf58f 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -10,6 +10,7 @@ #include <linux/firmware.h> #include <linux/regmap.h> #include <linux/acpi.h> +#include <acpi/acpi_bus.h> #include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> @@ -27,6 +28,11 @@ #define BTINTEL_PPAG_NAME "PPAG" +enum { + DSM_SET_WDISABLE2_DELAY = 1, + DSM_SET_RESET_METHOD = 3, +}; + /* structure to store the PPAG data read from ACPI table */ struct btintel_ppag { u32 domain; @@ -49,6 +55,10 @@ static struct { u32 fw_build_num; } coredump_info; +static const guid_t btintel_guid_dsm = + GUID_INIT(0xaa10f4e0, 0x81ac, 0x4233, + 0xab, 0xf6, 0x3b, 0x2a, 0xc5, 0x0e, 0x28, 0xd9); + int btintel_check_bdaddr(struct hci_dev *hdev) { struct hci_rp_read_bd_addr *bda; @@ -470,6 +480,7 @@ static int btintel_version_info_tlv(struct hci_dev *hdev, case 0x18: /* Slr */ case 0x19: /* Slr-F */ case 0x1b: /* Mgr */ + case 0x1c: /* Gale Peak (GaP) */ break; default: bt_dev_err(hdev, "Unsupported Intel hardware variant (0x%x)", @@ -2444,6 +2455,116 @@ static void btintel_set_ppag(struct hci_dev *hdev, struct intel_version_tlv *ver kfree_skb(skb); } +static int btintel_acpi_reset_method(struct hci_dev *hdev) +{ + int ret = 0; + acpi_status status; + union acpi_object *p, *ref; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + + status = acpi_evaluate_object(ACPI_HANDLE(GET_HCIDEV_DEV(hdev)), "_PRR", NULL, &buffer); + if (ACPI_FAILURE(status)) { + bt_dev_err(hdev, "Failed to run _PRR method"); + ret = -ENODEV; + return ret; + } + p = buffer.pointer; + + if (p->package.count != 1 || p->type != ACPI_TYPE_PACKAGE) { + bt_dev_err(hdev, "Invalid arguments"); + ret = -EINVAL; + goto exit_on_error; + } + + ref = &p->package.elements[0]; + if (ref->type != ACPI_TYPE_LOCAL_REFERENCE) { + bt_dev_err(hdev, "Invalid object type: 0x%x", ref->type); + ret = -EINVAL; + goto exit_on_error; + } + + status = acpi_evaluate_object(ref->reference.handle, "_RST", NULL, NULL); + if (ACPI_FAILURE(status)) { + bt_dev_err(hdev, "Failed to run_RST method"); + ret = -ENODEV; + goto exit_on_error; + } + +exit_on_error: + kfree(buffer.pointer); + return ret; +} + +static void btintel_set_dsm_reset_method(struct hci_dev *hdev, + struct intel_version_tlv *ver_tlv) +{ + struct btintel_data *data = hci_get_priv(hdev); + acpi_handle handle = ACPI_HANDLE(GET_HCIDEV_DEV(hdev)); + u8 reset_payload[4] = {0x01, 0x00, 0x01, 0x00}; + union acpi_object *obj, argv4; + enum { + RESET_TYPE_WDISABLE2, + RESET_TYPE_VSEC + }; + + handle = ACPI_HANDLE(GET_HCIDEV_DEV(hdev)); + + if (!handle) { + bt_dev_dbg(hdev, "No support for bluetooth device in ACPI firmware"); + return; + } + + if (!acpi_has_method(handle, "_PRR")) { + bt_dev_err(hdev, "No support for _PRR ACPI method"); + return; + } + + switch (ver_tlv->cnvi_top & 0xfff) { + case 0x910: /* GalePeak2 */ + reset_payload[2] = RESET_TYPE_VSEC; + break; + default: + /* WDISABLE2 is the default reset method */ + reset_payload[2] = RESET_TYPE_WDISABLE2; + + if (!acpi_check_dsm(handle, &btintel_guid_dsm, 0, + BIT(DSM_SET_WDISABLE2_DELAY))) { + bt_dev_err(hdev, "No dsm support to set reset delay"); + return; + } + argv4.integer.type = ACPI_TYPE_INTEGER; + /* delay required to toggle BT power */ + argv4.integer.value = 160; + obj = acpi_evaluate_dsm(handle, &btintel_guid_dsm, 0, + DSM_SET_WDISABLE2_DELAY, &argv4); + if (!obj) { + bt_dev_err(hdev, "Failed to call dsm to set reset delay"); + return; + } + ACPI_FREE(obj); + } + + bt_dev_info(hdev, "DSM reset method type: 0x%02x", reset_payload[2]); + + if (!acpi_check_dsm(handle, &btintel_guid_dsm, 0, + DSM_SET_RESET_METHOD)) { + bt_dev_warn(hdev, "No support for dsm to set reset method"); + return; + } + argv4.buffer.type = ACPI_TYPE_BUFFER; + argv4.buffer.length = sizeof(reset_payload); + argv4.buffer.pointer = reset_payload; + + obj = acpi_evaluate_dsm(handle, &btintel_guid_dsm, 0, + DSM_SET_RESET_METHOD, &argv4); + if (!obj) { + bt_dev_err(hdev, "Failed to call dsm to set reset method"); + return; + } + ACPI_FREE(obj); + data->acpi_reset_method = btintel_acpi_reset_method; +} + static int btintel_bootloader_setup_tlv(struct hci_dev *hdev, struct intel_version_tlv *ver) { @@ -2528,6 +2649,7 @@ static void btintel_set_msft_opcode(struct hci_dev *hdev, u8 hw_variant) case 0x18: case 0x19: case 0x1b: + case 0x1c: hci_set_msft_opcode(hdev, 0xFC1E); break; default: @@ -2742,6 +2864,7 @@ static int btintel_setup_combined(struct hci_dev *hdev) case 0x18: case 0x19: case 0x1b: + case 0x1c: /* Display version information of TLV type */ btintel_version_info_tlv(hdev, &ver_tlv); @@ -2757,6 +2880,7 @@ static int btintel_setup_combined(struct hci_dev *hdev) /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, INTEL_HW_VARIANT(ver_tlv.cnvi_bt)); + btintel_set_dsm_reset_method(hdev, &ver_tlv); err = btintel_bootloader_setup_tlv(hdev, &ver_tlv); btintel_register_devcoredump_support(hdev); @@ -2824,6 +2948,80 @@ int btintel_configure_setup(struct hci_dev *hdev, const char *driver_name) } EXPORT_SYMBOL_GPL(btintel_configure_setup); +static int btintel_diagnostics(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct intel_tlv *tlv = (void *)&skb->data[5]; + + /* The first event is always an event type TLV */ + if (tlv->type != INTEL_TLV_TYPE_ID) + goto recv_frame; + + switch (tlv->val[0]) { + case INTEL_TLV_SYSTEM_EXCEPTION: + case INTEL_TLV_FATAL_EXCEPTION: + case INTEL_TLV_DEBUG_EXCEPTION: + case INTEL_TLV_TEST_EXCEPTION: + /* Generate devcoredump from exception */ + if (!hci_devcd_init(hdev, skb->len)) { + hci_devcd_append(hdev, skb); + hci_devcd_complete(hdev); + } else { + bt_dev_err(hdev, "Failed to generate devcoredump"); + kfree_skb(skb); + } + return 0; + default: + bt_dev_err(hdev, "Invalid exception type %02X", tlv->val[0]); + } + +recv_frame: + return hci_recv_frame(hdev, skb); +} + +int btintel_recv_event(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_event_hdr *hdr = (void *)skb->data; + const char diagnostics_hdr[] = { 0x87, 0x80, 0x03 }; + + if (skb->len > HCI_EVENT_HDR_SIZE && hdr->evt == 0xff && + hdr->plen > 0) { + const void *ptr = skb->data + HCI_EVENT_HDR_SIZE + 1; + unsigned int len = skb->len - HCI_EVENT_HDR_SIZE - 1; + + if (btintel_test_flag(hdev, INTEL_BOOTLOADER)) { + switch (skb->data[2]) { + case 0x02: + /* When switching to the operational firmware + * the device sends a vendor specific event + * indicating that the bootup completed. + */ + btintel_bootup(hdev, ptr, len); + break; + case 0x06: + /* When the firmware loading completes the + * device sends out a vendor specific event + * indicating the result of the firmware + * loading. + */ + btintel_secure_send_result(hdev, ptr, len); + break; + } + } + + /* Handle all diagnostics events separately. May still call + * hci_recv_frame. + */ + if (len >= sizeof(diagnostics_hdr) && + memcmp(&skb->data[2], diagnostics_hdr, + sizeof(diagnostics_hdr)) == 0) { + return btintel_diagnostics(hdev, skb); + } + } + + return hci_recv_frame(hdev, skb); +} +EXPORT_SYMBOL_GPL(btintel_recv_event); + void btintel_bootup(struct hci_dev *hdev, const void *ptr, unsigned int len) { const struct intel_bootup *evt = ptr; diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h index d6a1dc8d8a82..2ed646609dee 100644 --- a/drivers/bluetooth/btintel.h +++ b/drivers/bluetooth/btintel.h @@ -166,12 +166,14 @@ enum { INTEL_BROKEN_SHUTDOWN_LED, INTEL_ROM_LEGACY, INTEL_ROM_LEGACY_NO_WBS_SUPPORT, + INTEL_ACPI_RESET_ACTIVE, __INTEL_NUM_FLAGS, }; struct btintel_data { DECLARE_BITMAP(flags, __INTEL_NUM_FLAGS); + int (*acpi_reset_method)(struct hci_dev *hdev); }; #define btintel_set_flag(hdev, nr) \ @@ -220,6 +222,7 @@ int btintel_read_boot_params(struct hci_dev *hdev, int btintel_download_firmware(struct hci_dev *dev, struct intel_version *ver, const struct firmware *fw, u32 *boot_param); int btintel_configure_setup(struct hci_dev *hdev, const char *driver_name); +int btintel_recv_event(struct hci_dev *hdev, struct sk_buff *skb); void btintel_bootup(struct hci_dev *hdev, const void *ptr, unsigned int len); void btintel_secure_send_result(struct hci_dev *hdev, const void *ptr, unsigned int len); diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index 809762d64fc6..aaabb732082c 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -53,10 +53,61 @@ struct btmtk_section_map { }; } __packed; +static void btmtk_coredump(struct hci_dev *hdev) +{ + int err; + + err = __hci_cmd_send(hdev, 0xfd5b, 0, NULL); + if (err < 0) + bt_dev_err(hdev, "Coredump failed (%d)", err); +} + +static void btmtk_coredump_hdr(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct btmediatek_data *data = hci_get_priv(hdev); + char buf[80]; + + snprintf(buf, sizeof(buf), "Controller Name: 0x%X\n", + data->dev_id); + skb_put_data(skb, buf, strlen(buf)); + + snprintf(buf, sizeof(buf), "Firmware Version: 0x%X\n", + data->cd_info.fw_version); + skb_put_data(skb, buf, strlen(buf)); + + snprintf(buf, sizeof(buf), "Driver: %s\n", + data->cd_info.driver_name); + skb_put_data(skb, buf, strlen(buf)); + + snprintf(buf, sizeof(buf), "Vendor: MediaTek\n"); + skb_put_data(skb, buf, strlen(buf)); +} + +static void btmtk_coredump_notify(struct hci_dev *hdev, int state) +{ + struct btmediatek_data *data = hci_get_priv(hdev); + + switch (state) { + case HCI_DEVCOREDUMP_IDLE: + data->cd_info.state = HCI_DEVCOREDUMP_IDLE; + break; + case HCI_DEVCOREDUMP_ACTIVE: + data->cd_info.state = HCI_DEVCOREDUMP_ACTIVE; + break; + case HCI_DEVCOREDUMP_TIMEOUT: + case HCI_DEVCOREDUMP_ABORT: + case HCI_DEVCOREDUMP_DONE: + data->cd_info.state = HCI_DEVCOREDUMP_IDLE; + btmtk_reset_sync(hdev); + break; + } +} + int btmtk_setup_firmware_79xx(struct hci_dev *hdev, const char *fwname, wmt_cmd_sync_func_t wmt_cmd_sync) { struct btmtk_hci_wmt_params wmt_params; + struct btmtk_patch_header *hdr; struct btmtk_global_desc *globaldesc = NULL; struct btmtk_section_map *sectionmap; const struct firmware *fw; @@ -75,9 +126,13 @@ int btmtk_setup_firmware_79xx(struct hci_dev *hdev, const char *fwname, fw_ptr = fw->data; fw_bin_ptr = fw_ptr; + hdr = (struct btmtk_patch_header *)fw_ptr; globaldesc = (struct btmtk_global_desc *)(fw_ptr + MTK_FW_ROM_PATCH_HEADER_SIZE); section_num = le32_to_cpu(globaldesc->section_num); + bt_dev_info(hdev, "HW/SW Version: 0x%04x%04x, Build Time: %s", + le16_to_cpu(hdr->hwver), le16_to_cpu(hdr->swver), hdr->datetime); + for (i = 0; i < section_num; i++) { first_block = 1; fw_ptr = fw_bin_ptr; @@ -280,6 +335,83 @@ int btmtk_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr) } EXPORT_SYMBOL_GPL(btmtk_set_bdaddr); +void btmtk_reset_sync(struct hci_dev *hdev) +{ + struct btmediatek_data *reset_work = hci_get_priv(hdev); + int err; + + hci_dev_lock(hdev); + + err = hci_cmd_sync_queue(hdev, reset_work->reset_sync, NULL, NULL); + if (err) + bt_dev_err(hdev, "failed to reset (%d)", err); + + hci_dev_unlock(hdev); +} +EXPORT_SYMBOL_GPL(btmtk_reset_sync); + +int btmtk_register_coredump(struct hci_dev *hdev, const char *name, + u32 fw_version) +{ + struct btmediatek_data *data = hci_get_priv(hdev); + + if (!IS_ENABLED(CONFIG_DEV_COREDUMP)) + return -EOPNOTSUPP; + + data->cd_info.fw_version = fw_version; + data->cd_info.state = HCI_DEVCOREDUMP_IDLE; + data->cd_info.driver_name = name; + + return hci_devcd_register(hdev, btmtk_coredump, btmtk_coredump_hdr, + btmtk_coredump_notify); +} +EXPORT_SYMBOL_GPL(btmtk_register_coredump); + +int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct btmediatek_data *data = hci_get_priv(hdev); + int err; + + if (!IS_ENABLED(CONFIG_DEV_COREDUMP)) + return 0; + + switch (data->cd_info.state) { + case HCI_DEVCOREDUMP_IDLE: + err = hci_devcd_init(hdev, MTK_COREDUMP_SIZE); + if (err < 0) + break; + data->cd_info.cnt = 0; + + /* It is supposed coredump can be done within 5 seconds */ + schedule_delayed_work(&hdev->dump.dump_timeout, + msecs_to_jiffies(5000)); + fallthrough; + case HCI_DEVCOREDUMP_ACTIVE: + default: + err = hci_devcd_append(hdev, skb); + if (err < 0) + break; + data->cd_info.cnt++; + + /* Mediatek coredump data would be more than MTK_COREDUMP_NUM */ + if (data->cd_info.cnt > MTK_COREDUMP_NUM && + skb->len > MTK_COREDUMP_END_LEN) + if (!memcmp((char *)&skb->data[skb->len - MTK_COREDUMP_END_LEN], + MTK_COREDUMP_END, MTK_COREDUMP_END_LEN - 1)) { + bt_dev_info(hdev, "Mediatek coredump end"); + hci_devcd_complete(hdev); + } + + break; + } + + if (err < 0) + kfree_skb(skb); + + return err; +} +EXPORT_SYMBOL_GPL(btmtk_process_coredump); + MODULE_AUTHOR("Sean Wang <[email protected]>"); MODULE_AUTHOR("Mark Chen <[email protected]>"); MODULE_DESCRIPTION("Bluetooth support for MediaTek devices ver " VERSION); @@ -289,3 +421,4 @@ MODULE_FIRMWARE(FIRMWARE_MT7622); MODULE_FIRMWARE(FIRMWARE_MT7663); MODULE_FIRMWARE(FIRMWARE_MT7668); MODULE_FIRMWARE(FIRMWARE_MT7961); +MODULE_FIRMWARE(FIRMWARE_MT7925); diff --git a/drivers/bluetooth/btmtk.h b/drivers/bluetooth/btmtk.h index 2a88ea8e475e..56f5502baadf 100644 --- a/drivers/bluetooth/btmtk.h +++ b/drivers/bluetooth/btmtk.h @@ -5,6 +5,7 @@ #define FIRMWARE_MT7663 "mediatek/mt7663pr2h.bin" #define FIRMWARE_MT7668 "mediatek/mt7668pr2h.bin" #define FIRMWARE_MT7961 "mediatek/BT_RAM_CODE_MT7961_1_2_hdr.bin" +#define FIRMWARE_MT7925 "mediatek/mt7925/BT_RAM_CODE_MT7925_1_1_hdr.bin" #define HCI_EV_WMT 0xe4 #define HCI_WMT_MAX_EVENT_SIZE 64 @@ -21,6 +22,11 @@ #define MT7921_DLSTATUS 0x7c053c10 #define BT_DL_STATE BIT(1) +#define MTK_COREDUMP_SIZE (1024 * 1000) +#define MTK_COREDUMP_END "coredump end" +#define MTK_COREDUMP_END_LEN (sizeof(MTK_COREDUMP_END)) +#define MTK_COREDUMP_NUM 255 + enum { BTMTK_WMT_PATCH_DWNLD = 0x1, BTMTK_WMT_TEST = 0x2, @@ -119,6 +125,21 @@ struct btmtk_hci_wmt_params { u32 *status; }; +typedef int (*btmtk_reset_sync_func_t)(struct hci_dev *, void *); + +struct btmtk_coredump_info { + const char *driver_name; + u32 fw_version; + u16 cnt; + int state; +}; + +struct btmediatek_data { + u32 dev_id; + btmtk_reset_sync_func_t reset_sync; + struct btmtk_coredump_info cd_info; +}; + typedef int (*wmt_cmd_sync_func_t)(struct hci_dev *, struct btmtk_hci_wmt_params *); @@ -131,6 +152,13 @@ int btmtk_setup_firmware_79xx(struct hci_dev *hdev, const char *fwname, int btmtk_setup_firmware(struct hci_dev *hdev, const char *fwname, wmt_cmd_sync_func_t wmt_cmd_sync); + +void btmtk_reset_sync(struct hci_dev *hdev); + +int btmtk_register_coredump(struct hci_dev *hdev, const char *name, + u32 fw_version); + +int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb); #else static inline int btmtk_set_bdaddr(struct hci_dev *hdev, @@ -151,4 +179,18 @@ static int btmtk_setup_firmware(struct hci_dev *hdev, const char *fwname, return -EOPNOTSUPP; } +static void btmtk_reset_sync(struct hci_dev *hdev) +{ +} + +static int btmtk_register_coredump(struct hci_dev *hdev, const char *name, + u32 fw_version) +{ + return -EOPNOTSUPP; +} + +static int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) +{ + return -EOPNOTSUPP; +} #endif diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c index 7680c67cdb35..935feab815d9 100644 --- a/drivers/bluetooth/btmtkuart.c +++ b/drivers/bluetooth/btmtkuart.c @@ -17,7 +17,6 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/of.h> -#include <linux/of_device.h> #include <linux/pinctrl/consumer.h> #include <linux/pm_runtime.h> #include <linux/regulator/consumer.h> diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index 52ef44688d38..ee6f6c872a34 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -29,16 +29,25 @@ #define BTNXPUART_CHECK_BOOT_SIGNATURE 3 #define BTNXPUART_SERDEV_OPEN 4 -#define FIRMWARE_W8987 "nxp/uartuart8987_bt.bin" -#define FIRMWARE_W8997 "nxp/uartuart8997_bt_v4.bin" -#define FIRMWARE_W9098 "nxp/uartuart9098_bt_v1.bin" -#define FIRMWARE_IW416 "nxp/uartiw416_bt_v0.bin" -#define FIRMWARE_IW612 "nxp/uartspi_n61x_v1.bin.se" -#define FIRMWARE_HELPER "nxp/helper_uart_3000000.bin" +#define FIRMWARE_W8987 "nxp/uartuart8987_bt.bin" +#define FIRMWARE_W8997 "nxp/uartuart8997_bt_v4.bin" +#define FIRMWARE_W9098 "nxp/uartuart9098_bt_v1.bin" +#define FIRMWARE_IW416 "nxp/uartiw416_bt_v0.bin" +#define FIRMWARE_IW612 "nxp/uartspi_n61x_v1.bin.se" +#define FIRMWARE_AW693 "nxp/uartaw693_bt.bin" +#define FIRMWARE_SECURE_AW693 "nxp/uartaw693_bt.bin.se" +#define FIRMWARE_HELPER "nxp/helper_uart_3000000.bin" #define CHIP_ID_W9098 0x5c03 #define CHIP_ID_IW416 0x7201 #define CHIP_ID_IW612 0x7601 +#define CHIP_ID_AW693 0x8200 + +#define FW_SECURE_MASK 0xc0 +#define FW_OPEN 0x00 +#define FW_AUTH_ILLEGAL 0x40 +#define FW_AUTH_PLAIN 0x80 +#define FW_AUTH_ENC 0xc0 #define HCI_NXP_PRI_BAUDRATE 115200 #define HCI_NXP_SEC_BAUDRATE 3000000 @@ -665,6 +674,9 @@ static int nxp_request_firmware(struct hci_dev *hdev, const char *fw_name) struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev); int err = 0; + if (!fw_name) + return -ENOENT; + if (!strlen(nxpdev->fw_name)) { snprintf(nxpdev->fw_name, MAX_FW_FILE_NAME_LEN, "%s", fw_name); @@ -812,7 +824,8 @@ free_skb: return 0; } -static char *nxp_get_fw_name_from_chipid(struct hci_dev *hdev, u16 chipid) +static char *nxp_get_fw_name_from_chipid(struct hci_dev *hdev, u16 chipid, + u8 loader_ver) { char *fw_name = NULL; @@ -826,6 +839,14 @@ static char *nxp_get_fw_name_from_chipid(struct hci_dev *hdev, u16 chipid) case CHIP_ID_IW612: fw_name = FIRMWARE_IW612; break; + case CHIP_ID_AW693: + if ((loader_ver & FW_SECURE_MASK) == FW_OPEN) + fw_name = FIRMWARE_AW693; + else if ((loader_ver & FW_SECURE_MASK) != FW_AUTH_ILLEGAL) + fw_name = FIRMWARE_SECURE_AW693; + else + bt_dev_err(hdev, "Illegal loader version %02x", loader_ver); + break; default: bt_dev_err(hdev, "Unknown chip signature %04x", chipid); break; @@ -838,13 +859,15 @@ static int nxp_recv_chip_ver_v3(struct hci_dev *hdev, struct sk_buff *skb) struct v3_start_ind *req = skb_pull_data(skb, sizeof(*req)); struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev); u16 chip_id; + u8 loader_ver; if (!process_boot_signature(nxpdev)) goto free_skb; chip_id = le16_to_cpu(req->chip_id); + loader_ver = req->loader_ver; if (!nxp_request_firmware(hdev, nxp_get_fw_name_from_chipid(hdev, - chip_id))) + chip_id, loader_ver))) nxp_send_ack(NXP_ACK_V3, hdev); free_skb: diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index e7e58a956d15..6f2187fab55f 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -594,14 +594,20 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, /* Firmware files to download are based on ROM version. * ROM version is derived from last two bytes of soc_ver. */ - rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | (soc_ver & 0x0000000f); + if (soc_type == QCA_WCN3988) + rom_ver = ((soc_ver & 0x00000f00) >> 0x05) | (soc_ver & 0x0000000f); + else + rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | (soc_ver & 0x0000000f); if (soc_type == QCA_WCN6750) qca_send_patch_config_cmd(hdev); /* Download rampatch file */ config.type = TLV_TYPE_PATCH; - if (qca_is_wcn399x(soc_type)) { + if (soc_type == QCA_WCN3988) { + snprintf(config.fwname, sizeof(config.fwname), + "qca/apbtfw%02x.tlv", rom_ver); + } else if (qca_is_wcn399x(soc_type)) { snprintf(config.fwname, sizeof(config.fwname), "qca/crbtfw%02x.tlv", rom_ver); } else if (soc_type == QCA_QCA6390) { @@ -636,6 +642,9 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, if (firmware_name) snprintf(config.fwname, sizeof(config.fwname), "qca/%s", firmware_name); + else if (soc_type == QCA_WCN3988) + snprintf(config.fwname, sizeof(config.fwname), + "qca/apnv%02x.bin", rom_ver); else if (qca_is_wcn399x(soc_type)) { if (le32_to_cpu(ver.soc_id) == QCA_WCN3991_SOC_ID) { snprintf(config.fwname, sizeof(config.fwname), diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h index b884095bcd9d..fc6cf314eb0e 100644 --- a/drivers/bluetooth/btqca.h +++ b/drivers/bluetooth/btqca.h @@ -142,6 +142,7 @@ enum qca_btsoc_type { QCA_INVALID = -1, QCA_AR3002, QCA_ROME, + QCA_WCN3988, QCA_WCN3990, QCA_WCN3998, QCA_WCN3991, @@ -162,8 +163,15 @@ int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr); int qca_send_pre_shutdown_cmd(struct hci_dev *hdev); static inline bool qca_is_wcn399x(enum qca_btsoc_type soc_type) { - return soc_type == QCA_WCN3990 || soc_type == QCA_WCN3991 || - soc_type == QCA_WCN3998; + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + return true; + default: + return false; + } } static inline bool qca_is_wcn6750(enum qca_btsoc_type soc_type) { diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index d978e7cea873..84c2c2e1122f 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -32,6 +32,8 @@ #define RTL_ROM_LMP_8851B 0x8851 #define RTL_CONFIG_MAGIC 0x8723ab55 +#define RTL_VSC_OP_COREDUMP 0xfcff + #define IC_MATCH_FL_LMPSUBV (1 << 0) #define IC_MATCH_FL_HCIREV (1 << 1) #define IC_MATCH_FL_HCIVER (1 << 2) @@ -81,6 +83,7 @@ struct id_table { bool has_msft_ext; char *fw_name; char *cfg_name; + char *hw_info; }; struct btrtl_device_info { @@ -101,22 +104,25 @@ static const struct id_table ic_id_table[] = { { IC_INFO(RTL_ROM_LMP_8723A, 0xb, 0x6, HCI_USB), .config_needed = false, .has_rom_version = false, - .fw_name = "rtl_bt/rtl8723a_fw.bin", - .cfg_name = NULL }, + .fw_name = "rtl_bt/rtl8723a_fw", + .cfg_name = NULL, + .hw_info = "rtl8723au" }, /* 8723BS */ { IC_INFO(RTL_ROM_LMP_8723B, 0xb, 0x6, HCI_UART), .config_needed = true, .has_rom_version = true, - .fw_name = "rtl_bt/rtl8723bs_fw.bin", - .cfg_name = "rtl_bt/rtl8723bs_config" }, + .fw_name = "rtl_bt/rtl8723bs_fw", + .cfg_name = "rtl_bt/rtl8723bs_config", + .hw_info = "rtl8723bs" }, /* 8723B */ { IC_INFO(RTL_ROM_LMP_8723B, 0xb, 0x6, HCI_USB), .config_needed = false, .has_rom_version = true, - .fw_name = "rtl_bt/rtl8723b_fw.bin", - .cfg_name = "rtl_bt/rtl8723b_config" }, + .fw_name = "rtl_bt/rtl8723b_fw", + .cfg_name = "rtl_bt/rtl8723b_config", + .hw_info = "rtl8723bu" }, /* 8723CS-CG */ { .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_CHIP_TYPE | @@ -126,8 +132,9 @@ static const struct id_table ic_id_table[] = { .hci_bus = HCI_UART, .config_needed = true, .has_rom_version = true, - .fw_name = "rtl_bt/rtl8723cs_cg_fw.bin", - .cfg_name = "rtl_bt/rtl8723cs_cg_config" }, + .fw_name = "rtl_bt/rtl8723cs_cg_fw", + .cfg_name = "rtl_bt/rtl8723cs_cg_config", + .hw_info = "rtl8723cs-cg" }, /* 8723CS-VF */ { .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_CHIP_TYPE | @@ -137,8 +144,9 @@ static const struct id_table ic_id_table[] = { .hci_bus = HCI_UART, .config_needed = true, .has_rom_version = true, - .fw_name = "rtl_bt/rtl8723cs_vf_fw.bin", - .cfg_name = "rtl_bt/rtl8723cs_vf_config" }, + .fw_name = "rtl_bt/rtl8723cs_vf_fw", + .cfg_name = "rtl_bt/rtl8723cs_vf_config", + .hw_info = "rtl8723cs-vf" }, /* 8723CS-XX */ { .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_CHIP_TYPE | @@ -148,139 +156,157 @@ static const struct id_table ic_id_table[] = { .hci_bus = HCI_UART, .config_needed = true, .has_rom_version = true, - .fw_name = "rtl_bt/rtl8723cs_xx_fw.bin", - .cfg_name = "rtl_bt/rtl8723cs_xx_config" }, + .fw_name = "rtl_bt/rtl8723cs_xx_fw", + .cfg_name = "rtl_bt/rtl8723cs_xx_config", + .hw_info = "rtl8723cs" }, /* 8723D */ { IC_INFO(RTL_ROM_LMP_8723B, 0xd, 0x8, HCI_USB), .config_needed = true, .has_rom_version = true, - .fw_name = "rtl_bt/rtl8723d_fw.bin", - .cfg_name = "rtl_bt/rtl8723d_config" }, + .fw_name = "rtl_bt/rtl8723d_fw", + .cfg_name = "rtl_bt/rtl8723d_config", + .hw_info = "rtl8723du" }, /* 8723DS */ { IC_INFO(RTL_ROM_LMP_8723B, 0xd, 0x8, HCI_UART), .config_needed = true, .has_rom_version = true, - .fw_name = "rtl_bt/rtl8723ds_fw.bin", - .cfg_name = "rtl_bt/rtl8723ds_config" }, + .fw_name = "rtl_bt/rtl8723ds_fw", + .cfg_name = "rtl_bt/rtl8723ds_config", + .hw_info = "rtl8723ds" }, /* 8821A */ { IC_INFO(RTL_ROM_LMP_8821A, 0xa, 0x6, HCI_USB), .config_needed = false, .has_rom_version = true, - .fw_name = "rtl_bt/rtl8821a_fw.bin", - .cfg_name = "rtl_bt/rtl8821a_config" }, + .fw_name = "rtl_bt/rtl8821a_fw", + .cfg_name = "rtl_bt/rtl8821a_config", + .hw_info = "rtl8821au" }, /* 8821C */ { IC_INFO(RTL_ROM_LMP_8821A, 0xc, 0x8, HCI_USB), .config_needed = false, .has_rom_version = true, .has_msft_ext = true, - .fw_name = "rtl_bt/rtl8821c_fw.bin", - .cfg_name = "rtl_bt/rtl8821c_config" }, + .fw_name = "rtl_bt/rtl8821c_fw", + .cfg_name = "rtl_bt/rtl8821c_config", + .hw_info = "rtl8821cu" }, /* 8821CS */ { IC_INFO(RTL_ROM_LMP_8821A, 0xc, 0x8, HCI_UART), .config_needed = true, .has_rom_version = true, .has_msft_ext = true, - .fw_name = "rtl_bt/rtl8821cs_fw.bin", - .cfg_name = "rtl_bt/rtl8821cs_config" }, + .fw_name = "rtl_bt/rtl8821cs_fw", + .cfg_name = "rtl_bt/rtl8821cs_config", + .hw_info = "rtl8821cs" }, /* 8761A */ { IC_INFO(RTL_ROM_LMP_8761A, 0xa, 0x6, HCI_USB), .config_needed = false, .has_rom_version = true, - .fw_name = "rtl_bt/rtl8761a_fw.bin", - .cfg_name = "rtl_bt/rtl8761a_config" }, + .fw_name = "rtl_bt/rtl8761a_fw", + .cfg_name = "rtl_bt/rtl8761a_config", + .hw_info = "rtl8761au" }, /* 8761B */ { IC_INFO(RTL_ROM_LMP_8761A, 0xb, 0xa, HCI_UART), .config_needed = false, .has_rom_version = true, .has_msft_ext = true, - .fw_name = "rtl_bt/rtl8761b_fw.bin", - .cfg_name = "rtl_bt/rtl8761b_config" }, + .fw_name = "rtl_bt/rtl8761b_fw", + .cfg_name = "rtl_bt/rtl8761b_config", + .hw_info = "rtl8761btv" }, /* 8761BU */ { IC_INFO(RTL_ROM_LMP_8761A, 0xb, 0xa, HCI_USB), .config_needed = false, .has_rom_version = true, - .fw_name = "rtl_bt/rtl8761bu_fw.bin", - .cfg_name = "rtl_bt/rtl8761bu_config" }, + .fw_name = "rtl_bt/rtl8761bu_fw", + .cfg_name = "rtl_bt/rtl8761bu_config", + .hw_info = "rtl8761bu" }, /* 8822C with UART interface */ { IC_INFO(RTL_ROM_LMP_8822B, 0xc, 0x8, HCI_UART), .config_needed = true, .has_rom_version = true, .has_msft_ext = true, - .fw_name = "rtl_bt/rtl8822cs_fw.bin", - .cfg_name = "rtl_bt/rtl8822cs_config" }, + .fw_name = "rtl_bt/rtl8822cs_fw", + .cfg_name = "rtl_bt/rtl8822cs_config", + .hw_info = "rtl8822cs" }, /* 8822C with UART interface */ { IC_INFO(RTL_ROM_LMP_8822B, 0xc, 0xa, HCI_UART), .config_needed = true, .has_rom_version = true, .has_msft_ext = true, - .fw_name = "rtl_bt/rtl8822cs_fw.bin", - .cfg_name = "rtl_bt/rtl8822cs_config" }, + .fw_name = "rtl_bt/rtl8822cs_fw", + .cfg_name = "rtl_bt/rtl8822cs_config", + .hw_info = "rtl8822cs" }, /* 8822C with USB interface */ { IC_INFO(RTL_ROM_LMP_8822B, 0xc, 0xa, HCI_USB), .config_needed = false, .has_rom_version = true, .has_msft_ext = true, - .fw_name = "rtl_bt/rtl8822cu_fw.bin", - .cfg_name = "rtl_bt/rtl8822cu_config" }, + .fw_name = "rtl_bt/rtl8822cu_fw", + .cfg_name = "rtl_bt/rtl8822cu_config", + .hw_info = "rtl8822cu" }, /* 8822B */ { IC_INFO(RTL_ROM_LMP_8822B, 0xb, 0x7, HCI_USB), .config_needed = true, .has_rom_version = true, .has_msft_ext = true, - .fw_name = "rtl_bt/rtl8822b_fw.bin", - .cfg_name = "rtl_bt/rtl8822b_config" }, + .fw_name = "rtl_bt/rtl8822b_fw", + .cfg_name = "rtl_bt/rtl8822b_config", + .hw_info = "rtl8822bu" }, /* 8852A */ { IC_INFO(RTL_ROM_LMP_8852A, 0xa, 0xb, HCI_USB), .config_needed = false, .has_rom_version = true, .has_msft_ext = true, - .fw_name = "rtl_bt/rtl8852au_fw.bin", - .cfg_name = "rtl_bt/rtl8852au_config" }, + .fw_name = "rtl_bt/rtl8852au_fw", + .cfg_name = "rtl_bt/rtl8852au_config", + .hw_info = "rtl8852au" }, /* 8852B with UART interface */ { IC_INFO(RTL_ROM_LMP_8852A, 0xb, 0xb, HCI_UART), .config_needed = true, .has_rom_version = true, .has_msft_ext = true, - .fw_name = "rtl_bt/rtl8852bs_fw.bin", - .cfg_name = "rtl_bt/rtl8852bs_config" }, + .fw_name = "rtl_bt/rtl8852bs_fw", + .cfg_name = "rtl_bt/rtl8852bs_config", + .hw_info = "rtl8852bs" }, /* 8852B */ { IC_INFO(RTL_ROM_LMP_8852A, 0xb, 0xb, HCI_USB), .config_needed = false, .has_rom_version = true, .has_msft_ext = true, - .fw_name = "rtl_bt/rtl8852bu_fw.bin", - .cfg_name = "rtl_bt/rtl8852bu_config" }, + .fw_name = "rtl_bt/rtl8852bu_fw", + .cfg_name = "rtl_bt/rtl8852bu_config", + .hw_info = "rtl8852bu" }, /* 8852C */ { IC_INFO(RTL_ROM_LMP_8852A, 0xc, 0xc, HCI_USB), .config_needed = false, .has_rom_version = true, .has_msft_ext = true, - .fw_name = "rtl_bt/rtl8852cu_fw.bin", - .cfg_name = "rtl_bt/rtl8852cu_config" }, + .fw_name = "rtl_bt/rtl8852cu_fw", + .cfg_name = "rtl_bt/rtl8852cu_config", + .hw_info = "rtl8852cu" }, /* 8851B */ { IC_INFO(RTL_ROM_LMP_8851B, 0xb, 0xc, HCI_USB), .config_needed = false, .has_rom_version = true, .has_msft_ext = false, - .fw_name = "rtl_bt/rtl8851bu_fw.bin", - .cfg_name = "rtl_bt/rtl8851bu_config" }, + .fw_name = "rtl_bt/rtl8851bu_fw", + .cfg_name = "rtl_bt/rtl8851bu_config", + .hw_info = "rtl8851bu" }, }; static const struct id_table *btrtl_match_ic(u16 lmp_subver, u16 hci_rev, @@ -590,6 +616,7 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, unsigned char **_buf) { static const u8 extension_sig[] = { 0x51, 0x04, 0xfd, 0x77 }; + struct btrealtek_data *coredump_info = hci_get_priv(hdev); struct rtl_epatch_header *epatch_info; unsigned char *buf; int i, len; @@ -705,8 +732,10 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, epatch_info = (struct rtl_epatch_header *)btrtl_dev->fw_data; num_patches = le16_to_cpu(epatch_info->num_patches); + BT_DBG("fw_version=%x, num_patches=%d", le32_to_cpu(epatch_info->fw_version), num_patches); + coredump_info->rtl_dump.fw_version = le32_to_cpu(epatch_info->fw_version); /* After the rtl_epatch_header there is a funky patch metadata section. * Assuming 2 patches, the layout is: @@ -903,6 +932,53 @@ out: return ret; } +static void btrtl_coredump(struct hci_dev *hdev) +{ + static const u8 param[] = { 0x00, 0x00 }; + + __hci_cmd_send(hdev, RTL_VSC_OP_COREDUMP, sizeof(param), param); +} + +static void btrtl_dmp_hdr(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct btrealtek_data *coredump_info = hci_get_priv(hdev); + char buf[80]; + + if (coredump_info->rtl_dump.controller) + snprintf(buf, sizeof(buf), "Controller Name: %s\n", + coredump_info->rtl_dump.controller); + else + snprintf(buf, sizeof(buf), "Controller Name: Unknown\n"); + skb_put_data(skb, buf, strlen(buf)); + + snprintf(buf, sizeof(buf), "Firmware Version: 0x%X\n", + coredump_info->rtl_dump.fw_version); + skb_put_data(skb, buf, strlen(buf)); + + snprintf(buf, sizeof(buf), "Driver: %s\n", coredump_info->rtl_dump.driver_name); + skb_put_data(skb, buf, strlen(buf)); + + snprintf(buf, sizeof(buf), "Vendor: Realtek\n"); + skb_put_data(skb, buf, strlen(buf)); +} + +static int btrtl_register_devcoredump_support(struct hci_dev *hdev) +{ + int err; + + err = hci_devcd_register(hdev, btrtl_coredump, btrtl_dmp_hdr, NULL); + + return err; +} + +void btrtl_set_driver_name(struct hci_dev *hdev, const char *driver_name) +{ + struct btrealtek_data *coredump_info = hci_get_priv(hdev); + + coredump_info->rtl_dump.driver_name = driver_name; +} +EXPORT_SYMBOL_GPL(btrtl_set_driver_name); + static bool rtl_has_chip_type(u16 lmp_subver) { switch (lmp_subver) { @@ -964,15 +1040,16 @@ EXPORT_SYMBOL_GPL(btrtl_free); struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev, const char *postfix) { + struct btrealtek_data *coredump_info = hci_get_priv(hdev); struct btrtl_device_info *btrtl_dev; struct sk_buff *skb; struct hci_rp_read_local_version *resp; + struct hci_command_hdr *cmd; + char fw_name[40]; char cfg_name[40]; u16 hci_rev, lmp_subver; u8 hci_ver, lmp_ver, chip_type = 0; int ret; - u16 opcode; - u8 cmd[2]; u8 reg_val[2]; btrtl_dev = kzalloc(sizeof(*btrtl_dev), GFP_KERNEL); @@ -1041,15 +1118,14 @@ next: btrtl_dev->drop_fw = false; if (btrtl_dev->drop_fw) { - opcode = hci_opcode_pack(0x3f, 0x66); - cmd[0] = opcode & 0xff; - cmd[1] = opcode >> 8; - - skb = bt_skb_alloc(sizeof(cmd), GFP_KERNEL); + skb = bt_skb_alloc(sizeof(*cmd), GFP_KERNEL); if (!skb) goto err_free; - skb_put_data(skb, cmd, sizeof(cmd)); + cmd = skb_put(skb, HCI_COMMAND_HDR_SIZE); + cmd->opcode = cpu_to_le16(0xfc66); + cmd->plen = 0; + hci_skb_pkt_type(skb) = HCI_COMMAND_PKT; ret = hdev->send(hdev, skb); @@ -1079,8 +1155,26 @@ next: goto err_free; } - btrtl_dev->fw_len = rtl_load_file(hdev, btrtl_dev->ic_info->fw_name, - &btrtl_dev->fw_data); + if (!btrtl_dev->ic_info->fw_name) { + ret = -ENOMEM; + goto err_free; + } + + btrtl_dev->fw_len = -EIO; + if (lmp_subver == RTL_ROM_LMP_8852A && hci_rev == 0x000c) { + snprintf(fw_name, sizeof(fw_name), "%s_v2.bin", + btrtl_dev->ic_info->fw_name); + btrtl_dev->fw_len = rtl_load_file(hdev, fw_name, + &btrtl_dev->fw_data); + } + + if (btrtl_dev->fw_len < 0) { + snprintf(fw_name, sizeof(fw_name), "%s.bin", + btrtl_dev->ic_info->fw_name); + btrtl_dev->fw_len = rtl_load_file(hdev, fw_name, + &btrtl_dev->fw_data); + } + if (btrtl_dev->fw_len < 0) { rtl_dev_err(hdev, "firmware file %s not found", btrtl_dev->ic_info->fw_name); @@ -1113,6 +1207,9 @@ next: if (btrtl_dev->ic_info->has_msft_ext) hci_set_msft_opcode(hdev, 0xFCF0); + if (btrtl_dev->ic_info) + coredump_info->rtl_dump.controller = btrtl_dev->ic_info->hw_info; + return btrtl_dev; err_free: @@ -1125,6 +1222,8 @@ EXPORT_SYMBOL_GPL(btrtl_initialize); int btrtl_download_firmware(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) { + int err = 0; + /* Match a set of subver values that correspond to stock firmware, * which is not compatible with standard btusb. * If matched, upload an alternative firmware that does conform to @@ -1133,12 +1232,14 @@ int btrtl_download_firmware(struct hci_dev *hdev, */ if (!btrtl_dev->ic_info) { rtl_dev_info(hdev, "assuming no firmware upload needed"); - return 0; + err = 0; + goto done; } switch (btrtl_dev->ic_info->lmp_subver) { case RTL_ROM_LMP_8723A: - return btrtl_setup_rtl8723a(hdev, btrtl_dev); + err = btrtl_setup_rtl8723a(hdev, btrtl_dev); + break; case RTL_ROM_LMP_8723B: case RTL_ROM_LMP_8821A: case RTL_ROM_LMP_8761A: @@ -1146,11 +1247,18 @@ int btrtl_download_firmware(struct hci_dev *hdev, case RTL_ROM_LMP_8852A: case RTL_ROM_LMP_8703B: case RTL_ROM_LMP_8851B: - return btrtl_setup_rtl8723b(hdev, btrtl_dev); + err = btrtl_setup_rtl8723b(hdev, btrtl_dev); + break; default: rtl_dev_info(hdev, "assuming no firmware upload needed"); - return 0; + break; } + +done: + if (!err) + err = btrtl_register_devcoredump_support(hdev); + + return err; } EXPORT_SYMBOL_GPL(btrtl_download_firmware); @@ -1180,6 +1288,10 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) if (btrtl_dev->project_id == CHIP_ID_8852C) btrealtek_set_flag(hdev, REALTEK_ALT6_CONTINUOUS_TX_CHIP); + if (btrtl_dev->project_id == CHIP_ID_8852A || + btrtl_dev->project_id == CHIP_ID_8852C) + set_bit(HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER, &hdev->quirks); + hci_set_aosp_capable(hdev); break; default: @@ -1398,4 +1510,5 @@ MODULE_FIRMWARE("rtl_bt/rtl8852bs_config.bin"); MODULE_FIRMWARE("rtl_bt/rtl8852bu_fw.bin"); MODULE_FIRMWARE("rtl_bt/rtl8852bu_config.bin"); MODULE_FIRMWARE("rtl_bt/rtl8852cu_fw.bin"); +MODULE_FIRMWARE("rtl_bt/rtl8852cu_fw_v2.bin"); MODULE_FIRMWARE("rtl_bt/rtl8852cu_config.bin"); diff --git a/drivers/bluetooth/btrtl.h b/drivers/bluetooth/btrtl.h index adb4c2c9abc5..a2d9d34f9fb0 100644 --- a/drivers/bluetooth/btrtl.h +++ b/drivers/bluetooth/btrtl.h @@ -109,8 +109,16 @@ enum { __REALTEK_NUM_FLAGS, }; +struct rtl_dump_info { + const char *driver_name; + char *controller; + u32 fw_version; +}; + struct btrealtek_data { DECLARE_BITMAP(flags, __REALTEK_NUM_FLAGS); + + struct rtl_dump_info rtl_dump; }; #define btrealtek_set_flag(hdev, nr) \ @@ -139,6 +147,7 @@ int btrtl_get_uart_settings(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev, unsigned int *controller_baudrate, u32 *device_baudrate, bool *flow_control); +void btrtl_set_driver_name(struct hci_dev *hdev, const char *driver_name); #else @@ -182,4 +191,8 @@ static inline int btrtl_get_uart_settings(struct hci_dev *hdev, return -ENOENT; } +static inline void btrtl_set_driver_name(struct hci_dev *hdev, const char *driver_name) +{ +} + #endif diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 764d176e9735..1bb3b09013b0 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -476,6 +476,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x8087, 0x0032), .driver_info = BTUSB_INTEL_COMBINED }, { USB_DEVICE(0x8087, 0x0033), .driver_info = BTUSB_INTEL_COMBINED }, { USB_DEVICE(0x8087, 0x0035), .driver_info = BTUSB_INTEL_COMBINED }, + { USB_DEVICE(0x8087, 0x0036), .driver_info = BTUSB_INTEL_COMBINED }, { USB_DEVICE(0x8087, 0x07da), .driver_info = BTUSB_CSR }, { USB_DEVICE(0x8087, 0x07dc), .driver_info = BTUSB_INTEL_COMBINED | BTUSB_INTEL_NO_WBS_SUPPORT | @@ -625,9 +626,24 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0489, 0xe0e4), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH | BTUSB_VALID_LE_STATES }, + { USB_DEVICE(0x0489, 0xe0f1), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH | + BTUSB_VALID_LE_STATES }, { USB_DEVICE(0x0489, 0xe0f2), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH | BTUSB_VALID_LE_STATES }, + { USB_DEVICE(0x0489, 0xe0f5), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH | + BTUSB_VALID_LE_STATES }, + { USB_DEVICE(0x0489, 0xe0f6), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH | + BTUSB_VALID_LE_STATES }, + { USB_DEVICE(0x0489, 0xe102), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH | + BTUSB_VALID_LE_STATES }, + { USB_DEVICE(0x04ca, 0x3804), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH | + BTUSB_VALID_LE_STATES }, /* Additional Realtek 8723AE Bluetooth devices */ { USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK }, @@ -860,10 +876,26 @@ static void btusb_intel_cmd_timeout(struct hci_dev *hdev) { struct btusb_data *data = hci_get_drvdata(hdev); struct gpio_desc *reset_gpio = data->reset_gpio; + struct btintel_data *intel_data = hci_get_priv(hdev); if (++data->cmd_timeout_cnt < 5) return; + if (intel_data->acpi_reset_method) { + if (test_and_set_bit(INTEL_ACPI_RESET_ACTIVE, intel_data->flags)) { + bt_dev_err(hdev, "acpi: last reset failed ? Not resetting again"); + return; + } + + bt_dev_err(hdev, "Initiating acpi reset method"); + /* If ACPI reset method fails, lets try with legacy GPIO + * toggling + */ + if (!intel_data->acpi_reset_method(hdev)) { + return; + } + } + if (!reset_gpio) { btusb_reset(hdev); return; @@ -887,10 +919,49 @@ static void btusb_intel_cmd_timeout(struct hci_dev *hdev) gpiod_set_value_cansleep(reset_gpio, 0); } +#define RTK_DEVCOREDUMP_CODE_MEMDUMP 0x01 +#define RTK_DEVCOREDUMP_CODE_HW_ERR 0x02 +#define RTK_DEVCOREDUMP_CODE_CMD_TIMEOUT 0x03 + +#define RTK_SUB_EVENT_CODE_COREDUMP 0x34 + +struct rtk_dev_coredump_hdr { + u8 type; + u8 code; + u8 reserved[2]; +} __packed; + +static inline void btusb_rtl_alloc_devcoredump(struct hci_dev *hdev, + struct rtk_dev_coredump_hdr *hdr, u8 *buf, u32 len) +{ + struct sk_buff *skb; + + skb = alloc_skb(len + sizeof(*hdr), GFP_ATOMIC); + if (!skb) + return; + + skb_put_data(skb, hdr, sizeof(*hdr)); + if (len) + skb_put_data(skb, buf, len); + + if (!hci_devcd_init(hdev, skb->len)) { + hci_devcd_append(hdev, skb); + hci_devcd_complete(hdev); + } else { + bt_dev_err(hdev, "RTL: Failed to generate devcoredump"); + kfree_skb(skb); + } +} + static void btusb_rtl_cmd_timeout(struct hci_dev *hdev) { struct btusb_data *data = hci_get_drvdata(hdev); struct gpio_desc *reset_gpio = data->reset_gpio; + struct rtk_dev_coredump_hdr hdr = { + .type = RTK_DEVCOREDUMP_CODE_CMD_TIMEOUT, + }; + + btusb_rtl_alloc_devcoredump(hdev, &hdr, NULL, 0); if (++data->cmd_timeout_cnt < 5) return; @@ -917,6 +988,18 @@ static void btusb_rtl_cmd_timeout(struct hci_dev *hdev) gpiod_set_value_cansleep(reset_gpio, 0); } +static void btusb_rtl_hw_error(struct hci_dev *hdev, u8 code) +{ + struct rtk_dev_coredump_hdr hdr = { + .type = RTK_DEVCOREDUMP_CODE_HW_ERR, + .code = code, + }; + + bt_dev_err(hdev, "RTL: hw err, trigger devcoredump (%d)", code); + + btusb_rtl_alloc_devcoredump(hdev, &hdr, NULL, 0); +} + static void btusb_qca_cmd_timeout(struct hci_dev *hdev) { struct btusb_data *data = hci_get_drvdata(hdev); @@ -2409,79 +2492,6 @@ static int btusb_recv_bulk_intel(struct btusb_data *data, void *buffer, return btusb_recv_bulk(data, buffer, count); } -static int btusb_intel_diagnostics(struct hci_dev *hdev, struct sk_buff *skb) -{ - struct intel_tlv *tlv = (void *)&skb->data[5]; - - /* The first event is always an event type TLV */ - if (tlv->type != INTEL_TLV_TYPE_ID) - goto recv_frame; - - switch (tlv->val[0]) { - case INTEL_TLV_SYSTEM_EXCEPTION: - case INTEL_TLV_FATAL_EXCEPTION: - case INTEL_TLV_DEBUG_EXCEPTION: - case INTEL_TLV_TEST_EXCEPTION: - /* Generate devcoredump from exception */ - if (!hci_devcd_init(hdev, skb->len)) { - hci_devcd_append(hdev, skb); - hci_devcd_complete(hdev); - } else { - bt_dev_err(hdev, "Failed to generate devcoredump"); - kfree_skb(skb); - } - return 0; - default: - bt_dev_err(hdev, "Invalid exception type %02X", tlv->val[0]); - } - -recv_frame: - return hci_recv_frame(hdev, skb); -} - -static int btusb_recv_event_intel(struct hci_dev *hdev, struct sk_buff *skb) -{ - struct hci_event_hdr *hdr = (void *)skb->data; - const char diagnostics_hdr[] = { 0x87, 0x80, 0x03 }; - - if (skb->len > HCI_EVENT_HDR_SIZE && hdr->evt == 0xff && - hdr->plen > 0) { - const void *ptr = skb->data + HCI_EVENT_HDR_SIZE + 1; - unsigned int len = skb->len - HCI_EVENT_HDR_SIZE - 1; - - if (btintel_test_flag(hdev, INTEL_BOOTLOADER)) { - switch (skb->data[2]) { - case 0x02: - /* When switching to the operational firmware - * the device sends a vendor specific event - * indicating that the bootup completed. - */ - btintel_bootup(hdev, ptr, len); - break; - case 0x06: - /* When the firmware loading completes the - * device sends out a vendor specific event - * indicating the result of the firmware - * loading. - */ - btintel_secure_send_result(hdev, ptr, len); - break; - } - } - - /* Handle all diagnostics events separately. May still call - * hci_recv_frame. - */ - if (len >= sizeof(diagnostics_hdr) && - memcmp(&skb->data[2], diagnostics_hdr, - sizeof(diagnostics_hdr)) == 0) { - return btusb_intel_diagnostics(hdev, skb); - } - } - - return hci_recv_frame(hdev, skb); -} - static int btusb_send_frame_intel(struct hci_dev *hdev, struct sk_buff *skb) { struct urb *urb; @@ -2562,6 +2572,25 @@ static int btusb_setup_realtek(struct hci_dev *hdev) return ret; } +static int btusb_recv_event_realtek(struct hci_dev *hdev, struct sk_buff *skb) +{ + if (skb->data[0] == HCI_VENDOR_PKT && skb->data[2] == RTK_SUB_EVENT_CODE_COREDUMP) { + struct rtk_dev_coredump_hdr hdr = { + .code = RTK_DEVCOREDUMP_CODE_MEMDUMP, + }; + + bt_dev_dbg(hdev, "RTL: received coredump vendor evt, len %u", + skb->len); + + btusb_rtl_alloc_devcoredump(hdev, &hdr, skb->data, skb->len); + kfree_skb(skb); + + return 0; + } + + return hci_recv_frame(hdev, skb); +} + /* UHW CR mapping */ #define MTK_BT_MISC 0x70002510 #define MTK_BT_SUBSYS_RST 0x70002610 @@ -2571,8 +2600,9 @@ static int btusb_setup_realtek(struct hci_dev *hdev) #define MTK_EP_RST_OPT 0x74011890 #define MTK_EP_RST_IN_OUT_OPT 0x00010001 #define MTK_BT_RST_DONE 0x00000100 -#define MTK_BT_RESET_WAIT_MS 100 -#define MTK_BT_RESET_NUM_TRIES 10 +#define MTK_BT_RESET_REG_CONNV3 0x70028610 +#define MTK_BT_READ_DEV_ID 0x70010200 + static void btusb_mtk_wmt_recv(struct urb *urb) { @@ -2943,6 +2973,88 @@ static int btusb_mtk_id_get(struct btusb_data *data, u32 reg, u32 *id) return btusb_mtk_reg_read(data, reg, id); } +static u32 btusb_mtk_reset_done(struct hci_dev *hdev) +{ + struct btusb_data *data = hci_get_drvdata(hdev); + u32 val = 0; + + btusb_mtk_uhw_reg_read(data, MTK_BT_MISC, &val); + + return val & MTK_BT_RST_DONE; +} + +static int btusb_mtk_reset(struct hci_dev *hdev, void *rst_data) +{ + struct btusb_data *data = hci_get_drvdata(hdev); + struct btmediatek_data *mediatek; + u32 val; + int err; + + /* It's MediaTek specific bluetooth reset mechanism via USB */ + if (test_and_set_bit(BTUSB_HW_RESET_ACTIVE, &data->flags)) { + bt_dev_err(hdev, "last reset failed? Not resetting again"); + return -EBUSY; + } + + err = usb_autopm_get_interface(data->intf); + if (err < 0) + return err; + + btusb_stop_traffic(data); + usb_kill_anchored_urbs(&data->tx_anchor); + mediatek = hci_get_priv(hdev); + + if (mediatek->dev_id == 0x7925) { + btusb_mtk_uhw_reg_read(data, MTK_BT_RESET_REG_CONNV3, &val); + val |= (1 << 5); + btusb_mtk_uhw_reg_write(data, MTK_BT_RESET_REG_CONNV3, val); + btusb_mtk_uhw_reg_read(data, MTK_BT_RESET_REG_CONNV3, &val); + val &= 0xFFFF00FF; + val |= (1 << 13); + btusb_mtk_uhw_reg_write(data, MTK_BT_RESET_REG_CONNV3, val); + btusb_mtk_uhw_reg_write(data, MTK_EP_RST_OPT, 0x00010001); + btusb_mtk_uhw_reg_read(data, MTK_BT_RESET_REG_CONNV3, &val); + val |= (1 << 0); + btusb_mtk_uhw_reg_write(data, MTK_BT_RESET_REG_CONNV3, val); + btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT, 0x000000FF); + btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT, &val); + btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT1, 0x000000FF); + btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT1, &val); + msleep(100); + } else { + /* It's Device EndPoint Reset Option Register */ + bt_dev_dbg(hdev, "Initiating reset mechanism via uhw"); + btusb_mtk_uhw_reg_write(data, MTK_EP_RST_OPT, MTK_EP_RST_IN_OUT_OPT); + btusb_mtk_uhw_reg_read(data, MTK_BT_WDT_STATUS, &val); + + /* Reset the bluetooth chip via USB interface. */ + btusb_mtk_uhw_reg_write(data, MTK_BT_SUBSYS_RST, 1); + btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT, 0x000000FF); + btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT, &val); + btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT1, 0x000000FF); + btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT1, &val); + /* MT7921 need to delay 20ms between toggle reset bit */ + msleep(20); + btusb_mtk_uhw_reg_write(data, MTK_BT_SUBSYS_RST, 0); + btusb_mtk_uhw_reg_read(data, MTK_BT_SUBSYS_RST, &val); + } + + err = readx_poll_timeout(btusb_mtk_reset_done, hdev, val, + val & MTK_BT_RST_DONE, 20000, 1000000); + if (err < 0) + bt_dev_err(hdev, "Reset timeout"); + + btusb_mtk_id_get(data, 0x70010200, &val); + if (!val) + bt_dev_err(hdev, "Can't get device id, subsys reset fail."); + + usb_queue_reset_device(data->intf); + + clear_bit(BTUSB_HW_RESET_ACTIVE, &data->flags); + + return err; +} + static int btusb_mtk_setup(struct hci_dev *hdev) { struct btusb_data *data = hci_get_drvdata(hdev); @@ -2953,10 +3065,11 @@ static int btusb_mtk_setup(struct hci_dev *hdev) struct sk_buff *skb; const char *fwname; int err, status; - u32 dev_id; + u32 dev_id = 0; char fw_bin_name[64]; u32 fw_version = 0; u8 param; + struct btmediatek_data *mediatek; calltime = ktime_get(); @@ -2966,7 +3079,7 @@ static int btusb_mtk_setup(struct hci_dev *hdev) return err; } - if (!dev_id) { + if (!dev_id || dev_id != 0x7663) { err = btusb_mtk_id_get(data, 0x70010200, &dev_id); if (err < 0) { bt_dev_err(hdev, "Failed to get device id (%d)", err); @@ -2979,6 +3092,14 @@ static int btusb_mtk_setup(struct hci_dev *hdev) } } + mediatek = hci_get_priv(hdev); + mediatek->dev_id = dev_id; + mediatek->reset_sync = btusb_mtk_reset; + + err = btmtk_register_coredump(hdev, btusb_driver.name, fw_version); + if (err < 0) + bt_dev_err(hdev, "Failed to register coredump (%d)", err); + switch (dev_id) { case 0x7663: fwname = FIRMWARE_MT7663; @@ -2988,9 +3109,16 @@ static int btusb_mtk_setup(struct hci_dev *hdev) break; case 0x7922: case 0x7961: - snprintf(fw_bin_name, sizeof(fw_bin_name), - "mediatek/BT_RAM_CODE_MT%04x_1_%x_hdr.bin", - dev_id & 0xffff, (fw_version & 0xff) + 1); + case 0x7925: + if (dev_id == 0x7925) + snprintf(fw_bin_name, sizeof(fw_bin_name), + "mediatek/mt%04x/BT_RAM_CODE_MT%04x_1_%x_hdr.bin", + dev_id & 0xffff, dev_id & 0xffff, (fw_version & 0xff) + 1); + else + snprintf(fw_bin_name, sizeof(fw_bin_name), + "mediatek/BT_RAM_CODE_MT%04x_1_%x_hdr.bin", + dev_id & 0xffff, (fw_version & 0xff) + 1); + err = btmtk_setup_firmware_79xx(hdev, fw_bin_name, btusb_mtk_hci_wmt_sync); if (err < 0) { @@ -3128,67 +3256,11 @@ static int btusb_mtk_shutdown(struct hci_dev *hdev) return 0; } -static void btusb_mtk_cmd_timeout(struct hci_dev *hdev) -{ - struct btusb_data *data = hci_get_drvdata(hdev); - u32 val; - int err, retry = 0; - - /* It's MediaTek specific bluetooth reset mechanism via USB */ - if (test_and_set_bit(BTUSB_HW_RESET_ACTIVE, &data->flags)) { - bt_dev_err(hdev, "last reset failed? Not resetting again"); - return; - } - - err = usb_autopm_get_interface(data->intf); - if (err < 0) - return; - - btusb_stop_traffic(data); - usb_kill_anchored_urbs(&data->tx_anchor); - - /* It's Device EndPoint Reset Option Register */ - bt_dev_dbg(hdev, "Initiating reset mechanism via uhw"); - btusb_mtk_uhw_reg_write(data, MTK_EP_RST_OPT, MTK_EP_RST_IN_OUT_OPT); - btusb_mtk_uhw_reg_read(data, MTK_BT_WDT_STATUS, &val); - - /* Reset the bluetooth chip via USB interface. */ - btusb_mtk_uhw_reg_write(data, MTK_BT_SUBSYS_RST, 1); - btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT, 0x000000FF); - btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT, &val); - btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT1, 0x000000FF); - btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT1, &val); - /* MT7921 need to delay 20ms between toggle reset bit */ - msleep(20); - btusb_mtk_uhw_reg_write(data, MTK_BT_SUBSYS_RST, 0); - btusb_mtk_uhw_reg_read(data, MTK_BT_SUBSYS_RST, &val); - - /* Poll the register until reset is completed */ - do { - btusb_mtk_uhw_reg_read(data, MTK_BT_MISC, &val); - if (val & MTK_BT_RST_DONE) { - bt_dev_dbg(hdev, "Bluetooth Reset Successfully"); - break; - } - - bt_dev_dbg(hdev, "Polling Bluetooth Reset CR"); - retry++; - msleep(MTK_BT_RESET_WAIT_MS); - } while (retry < MTK_BT_RESET_NUM_TRIES); - - btusb_mtk_id_get(data, 0x70010200, &val); - if (!val) - bt_dev_err(hdev, "Can't get device id, subsys reset fail."); - - usb_queue_reset_device(data->intf); - - clear_bit(BTUSB_HW_RESET_ACTIVE, &data->flags); -} - static int btusb_recv_acl_mtk(struct hci_dev *hdev, struct sk_buff *skb) { struct btusb_data *data = hci_get_drvdata(hdev); u16 handle = le16_to_cpu(hci_acl_hdr(skb)->handle); + struct sk_buff *skb_cd; switch (handle) { case 0xfc6f: /* Firmware dump from device */ @@ -3196,6 +3268,15 @@ static int btusb_recv_acl_mtk(struct hci_dev *hdev, struct sk_buff *skb) * suspend and thus disable auto-suspend. */ usb_disable_autosuspend(data->udev); + + /* We need to forward the diagnostic packet to userspace daemon + * for backward compatibility, so we have to clone the packet + * extraly for the in-kernel coredump support. + */ + skb_cd = skb_clone(skb, GFP_ATOMIC); + if (skb_cd) + btmtk_process_coredump(hdev, skb_cd); + fallthrough; case 0x05ff: /* Firmware debug logging 1 */ case 0x05fe: /* Firmware debug logging 2 */ @@ -4196,11 +4277,16 @@ static int btusb_probe(struct usb_interface *intf, priv_size += sizeof(struct btintel_data); /* Override the rx handlers */ - data->recv_event = btusb_recv_event_intel; + data->recv_event = btintel_recv_event; data->recv_bulk = btusb_recv_bulk_intel; } else if (id->driver_info & BTUSB_REALTEK) { /* Allocate extra space for Realtek device */ priv_size += sizeof(struct btrealtek_data); + + data->recv_event = btusb_recv_event_realtek; + } else if (id->driver_info & BTUSB_MEDIATEK) { + /* Allocate extra space for Mediatek device */ + priv_size += sizeof(struct btmediatek_data); } data->recv_acl = hci_recv_frame; @@ -4307,7 +4393,7 @@ static int btusb_probe(struct usb_interface *intf, hdev->setup = btusb_mtk_setup; hdev->shutdown = btusb_mtk_shutdown; hdev->manufacturer = 70; - hdev->cmd_timeout = btusb_mtk_cmd_timeout; + hdev->cmd_timeout = btmtk_reset_sync; hdev->set_bdaddr = btmtk_set_bdaddr; set_bit(HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, &hdev->quirks); set_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks); @@ -4364,9 +4450,11 @@ static int btusb_probe(struct usb_interface *intf, if (IS_ENABLED(CONFIG_BT_HCIBTUSB_RTL) && (id->driver_info & BTUSB_REALTEK)) { + btrtl_set_driver_name(hdev, btusb_driver.name); hdev->setup = btusb_setup_realtek; hdev->shutdown = btrtl_shutdown_realtek; hdev->cmd_timeout = btusb_rtl_cmd_timeout; + hdev->hw_error = btusb_rtl_hw_error; /* Realtek devices need to set remote wakeup on auto-suspend */ set_bit(BTUSB_WAKEUP_AUTOSUSPEND, &data->flags); diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index fefc37b98b4a..71e748a9477e 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -11,7 +11,7 @@ #include <linux/gpio/consumer.h> #include <linux/kernel.h> #include <linux/mod_devicetable.h> -#include <linux/of_device.h> +#include <linux/of.h> #include <linux/pm_runtime.h> #include <linux/serdev.h> #include <linux/skbuff.h> diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index efdda2c3fce8..a76eb98c0047 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -770,7 +770,8 @@ static int hci_uart_tty_ioctl(struct tty_struct *tty, unsigned int cmd, break; case HCIUARTGETPROTO: - if (test_bit(HCI_UART_PROTO_SET, &hu->flags)) + if (test_bit(HCI_UART_PROTO_SET, &hu->flags) && + test_bit(HCI_UART_PROTO_READY, &hu->flags)) err = hu->proto->id; else err = -EUNATCH; diff --git a/drivers/bluetooth/hci_nokia.c b/drivers/bluetooth/hci_nokia.c index 05f7f6de6863..97da0b2bfd17 100644 --- a/drivers/bluetooth/hci_nokia.c +++ b/drivers/bluetooth/hci_nokia.c @@ -734,7 +734,11 @@ static int nokia_bluetooth_serdev_probe(struct serdev_device *serdev) return err; } - clk_prepare_enable(sysclk); + err = clk_prepare_enable(sysclk); + if (err) { + dev_err(dev, "could not enable sysclk: %d", err); + return err; + } btdev->sysclk_speed = clk_get_rate(sysclk); clk_disable_unprepare(sysclk); diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index e30c979535b1..011822519602 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -25,7 +25,7 @@ #include <linux/gpio/consumer.h> #include <linux/mod_devicetable.h> #include <linux/module.h> -#include <linux/of_device.h> +#include <linux/of.h> #include <linux/acpi.h> #include <linux/platform_device.h> #include <linux/regulator/consumer.h> @@ -117,9 +117,7 @@ enum qca_memdump_states { QCA_MEMDUMP_TIMEOUT, }; -struct qca_memdump_data { - char *memdump_buf_head; - char *memdump_buf_tail; +struct qca_memdump_info { u32 current_seq_no; u32 received_dump; u32 ram_dump_size; @@ -160,13 +158,15 @@ struct qca_data { struct work_struct ws_tx_vote_off; struct work_struct ctrl_memdump_evt; struct delayed_work ctrl_memdump_timeout; - struct qca_memdump_data *qca_memdump; + struct qca_memdump_info *qca_memdump; unsigned long flags; struct completion drop_ev_comp; wait_queue_head_t suspend_wait_q; enum qca_memdump_states memdump_state; struct mutex hci_memdump_lock; + u16 fw_version; + u16 controller_id; /* For debugging purpose */ u64 ibs_sent_wacks; u64 ibs_sent_slps; @@ -233,6 +233,7 @@ static void qca_regulator_disable(struct qca_serdev *qcadev); static void qca_power_shutdown(struct hci_uart *hu); static int qca_power_off(struct hci_dev *hdev); static void qca_controller_memdump(struct work_struct *work); +static void qca_dmp_hdr(struct hci_dev *hdev, struct sk_buff *skb); static enum qca_btsoc_type qca_soc_type(struct hci_uart *hu) { @@ -980,6 +981,28 @@ static int qca_recv_acl_data(struct hci_dev *hdev, struct sk_buff *skb) return hci_recv_frame(hdev, skb); } +static void qca_dmp_hdr(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_uart *hu = hci_get_drvdata(hdev); + struct qca_data *qca = hu->priv; + char buf[80]; + + snprintf(buf, sizeof(buf), "Controller Name: 0x%x\n", + qca->controller_id); + skb_put_data(skb, buf, strlen(buf)); + + snprintf(buf, sizeof(buf), "Firmware Version: 0x%x\n", + qca->fw_version); + skb_put_data(skb, buf, strlen(buf)); + + snprintf(buf, sizeof(buf), "Vendor:Qualcomm\n"); + skb_put_data(skb, buf, strlen(buf)); + + snprintf(buf, sizeof(buf), "Driver: %s\n", + hu->serdev->dev.driver->name); + skb_put_data(skb, buf, strlen(buf)); +} + static void qca_controller_memdump(struct work_struct *work) { struct qca_data *qca = container_of(work, struct qca_data, @@ -987,13 +1010,11 @@ static void qca_controller_memdump(struct work_struct *work) struct hci_uart *hu = qca->hu; struct sk_buff *skb; struct qca_memdump_event_hdr *cmd_hdr; - struct qca_memdump_data *qca_memdump = qca->qca_memdump; + struct qca_memdump_info *qca_memdump = qca->qca_memdump; struct qca_dump_size *dump; - char *memdump_buf; - char nullBuff[QCA_DUMP_PACKET_SIZE] = { 0 }; u16 seq_no; - u32 dump_size; u32 rx_size; + int ret = 0; enum qca_btsoc_type soc_type = qca_soc_type(hu); while ((skb = skb_dequeue(&qca->rx_memdump_q))) { @@ -1009,7 +1030,7 @@ static void qca_controller_memdump(struct work_struct *work) } if (!qca_memdump) { - qca_memdump = kzalloc(sizeof(struct qca_memdump_data), + qca_memdump = kzalloc(sizeof(struct qca_memdump_info), GFP_ATOMIC); if (!qca_memdump) { mutex_unlock(&qca->hci_memdump_lock); @@ -1035,44 +1056,49 @@ static void qca_controller_memdump(struct work_struct *work) set_bit(QCA_IBS_DISABLED, &qca->flags); set_bit(QCA_MEMDUMP_COLLECTION, &qca->flags); dump = (void *) skb->data; - dump_size = __le32_to_cpu(dump->dump_size); - if (!(dump_size)) { + qca_memdump->ram_dump_size = __le32_to_cpu(dump->dump_size); + if (!(qca_memdump->ram_dump_size)) { bt_dev_err(hu->hdev, "Rx invalid memdump size"); kfree(qca_memdump); kfree_skb(skb); - qca->qca_memdump = NULL; mutex_unlock(&qca->hci_memdump_lock); return; } - bt_dev_info(hu->hdev, "QCA collecting dump of size:%u", - dump_size); queue_delayed_work(qca->workqueue, &qca->ctrl_memdump_timeout, - msecs_to_jiffies(MEMDUMP_TIMEOUT_MS) - ); - - skb_pull(skb, sizeof(dump_size)); - memdump_buf = vmalloc(dump_size); - qca_memdump->ram_dump_size = dump_size; - qca_memdump->memdump_buf_head = memdump_buf; - qca_memdump->memdump_buf_tail = memdump_buf; - } + msecs_to_jiffies(MEMDUMP_TIMEOUT_MS)); + skb_pull(skb, sizeof(qca_memdump->ram_dump_size)); + qca_memdump->current_seq_no = 0; + qca_memdump->received_dump = 0; + ret = hci_devcd_init(hu->hdev, qca_memdump->ram_dump_size); + bt_dev_info(hu->hdev, "hci_devcd_init Return:%d", + ret); + if (ret < 0) { + kfree(qca->qca_memdump); + qca->qca_memdump = NULL; + qca->memdump_state = QCA_MEMDUMP_COLLECTED; + cancel_delayed_work(&qca->ctrl_memdump_timeout); + clear_bit(QCA_MEMDUMP_COLLECTION, &qca->flags); + mutex_unlock(&qca->hci_memdump_lock); + return; + } + + bt_dev_info(hu->hdev, "QCA collecting dump of size:%u", + qca_memdump->ram_dump_size); - memdump_buf = qca_memdump->memdump_buf_tail; + } /* If sequence no 0 is missed then there is no point in * accepting the other sequences. */ - if (!memdump_buf) { + if (!test_bit(QCA_MEMDUMP_COLLECTION, &qca->flags)) { bt_dev_err(hu->hdev, "QCA: Discarding other packets"); kfree(qca_memdump); kfree_skb(skb); - qca->qca_memdump = NULL; mutex_unlock(&qca->hci_memdump_lock); return; } - /* There could be chance of missing some packets from * the controller. In such cases let us store the dummy * packets in the buffer. @@ -1082,8 +1108,8 @@ static void qca_controller_memdump(struct work_struct *work) * bits, so skip this checking for missing packet. */ while ((seq_no > qca_memdump->current_seq_no + 1) && - (soc_type != QCA_QCA6390) && - seq_no != QCA_LAST_SEQUENCE_NUM) { + (soc_type != QCA_QCA6390) && + seq_no != QCA_LAST_SEQUENCE_NUM) { bt_dev_err(hu->hdev, "QCA controller missed packet:%d", qca_memdump->current_seq_no); rx_size = qca_memdump->received_dump; @@ -1094,43 +1120,38 @@ static void qca_controller_memdump(struct work_struct *work) qca_memdump->received_dump); break; } - memcpy(memdump_buf, nullBuff, QCA_DUMP_PACKET_SIZE); - memdump_buf = memdump_buf + QCA_DUMP_PACKET_SIZE; + hci_devcd_append_pattern(hu->hdev, 0x00, + QCA_DUMP_PACKET_SIZE); qca_memdump->received_dump += QCA_DUMP_PACKET_SIZE; qca_memdump->current_seq_no++; } - rx_size = qca_memdump->received_dump + skb->len; + rx_size = qca_memdump->received_dump + skb->len; if (rx_size <= qca_memdump->ram_dump_size) { if ((seq_no != QCA_LAST_SEQUENCE_NUM) && - (seq_no != qca_memdump->current_seq_no)) + (seq_no != qca_memdump->current_seq_no)) { bt_dev_err(hu->hdev, "QCA memdump unexpected packet %d", seq_no); + } bt_dev_dbg(hu->hdev, "QCA memdump packet %d with length %d", seq_no, skb->len); - memcpy(memdump_buf, (unsigned char *)skb->data, - skb->len); - memdump_buf = memdump_buf + skb->len; - qca_memdump->memdump_buf_tail = memdump_buf; - qca_memdump->current_seq_no = seq_no + 1; - qca_memdump->received_dump += skb->len; + hci_devcd_append(hu->hdev, skb); + qca_memdump->current_seq_no += 1; + qca_memdump->received_dump = rx_size; } else { bt_dev_err(hu->hdev, - "QCA memdump received %d, no space for packet %d", - qca_memdump->received_dump, seq_no); + "QCA memdump received no space for packet %d", + qca_memdump->current_seq_no); } - qca->qca_memdump = qca_memdump; - kfree_skb(skb); + if (seq_no == QCA_LAST_SEQUENCE_NUM) { bt_dev_info(hu->hdev, - "QCA memdump Done, received %d, total %d", - qca_memdump->received_dump, - qca_memdump->ram_dump_size); - memdump_buf = qca_memdump->memdump_buf_head; - dev_coredumpv(&hu->serdev->dev, memdump_buf, - qca_memdump->received_dump, GFP_KERNEL); + "QCA memdump Done, received %d, total %d", + qca_memdump->received_dump, + qca_memdump->ram_dump_size); + hci_devcd_complete(hu->hdev); cancel_delayed_work(&qca->ctrl_memdump_timeout); kfree(qca->qca_memdump); qca->qca_memdump = NULL; @@ -1541,8 +1562,8 @@ static void qca_hw_error(struct hci_dev *hdev, u8 code) mutex_lock(&qca->hci_memdump_lock); if (qca->memdump_state != QCA_MEMDUMP_COLLECTED) { bt_dev_err(hu->hdev, "clearing allocated memory due to memdump timeout"); + hci_devcd_abort(hu->hdev); if (qca->qca_memdump) { - vfree(qca->qca_memdump->memdump_buf_head); kfree(qca->qca_memdump); qca->qca_memdump = NULL; } @@ -1706,6 +1727,17 @@ static int qca_power_on(struct hci_dev *hdev) return ret; } +static void hci_coredump_qca(struct hci_dev *hdev) +{ + static const u8 param[] = { 0x26 }; + struct sk_buff *skb; + + skb = __hci_cmd_sync(hdev, 0xfc0c, 1, param, HCI_CMD_TIMEOUT); + if (IS_ERR(skb)) + bt_dev_err(hdev, "%s: trigger crash failed (%ld)", __func__, PTR_ERR(skb)); + kfree_skb(skb); +} + static int qca_setup(struct hci_uart *hu) { struct hci_dev *hdev = hu->hdev; @@ -1820,6 +1852,9 @@ out: hu->hdev->set_bdaddr = qca_set_bdaddr_rome; else hu->hdev->set_bdaddr = qca_set_bdaddr; + qca->fw_version = le16_to_cpu(ver.patch_ver); + qca->controller_id = le16_to_cpu(ver.rom_ver); + hci_devcd_register(hdev, hci_coredump_qca, qca_dmp_hdr, NULL); return ret; } @@ -1839,6 +1874,17 @@ static const struct hci_uart_proto qca_proto = { .dequeue = qca_dequeue, }; +static const struct qca_device_data qca_soc_data_wcn3988 __maybe_unused = { + .soc_type = QCA_WCN3988, + .vregs = (struct qca_vreg []) { + { "vddio", 15000 }, + { "vddxo", 80000 }, + { "vddrf", 300000 }, + { "vddch0", 450000 }, + }, + .num_vregs = 4, +}; + static const struct qca_device_data qca_soc_data_wcn3990 __maybe_unused = { .soc_type = QCA_WCN3990, .vregs = (struct qca_vreg []) { @@ -2363,6 +2409,7 @@ static const struct of_device_id qca_bluetooth_of_match[] = { { .compatible = "qcom,qca6174-bt" }, { .compatible = "qcom,qca6390-bt", .data = &qca_soc_data_qca6390}, { .compatible = "qcom,qca9377-bt" }, + { .compatible = "qcom,wcn3988-bt", .data = &qca_soc_data_wcn3988}, { .compatible = "qcom,wcn3990-bt", .data = &qca_soc_data_wcn3990}, { .compatible = "qcom,wcn3991-bt", .data = &qca_soc_data_wcn3991}, { .compatible = "qcom,wcn3998-bt", .data = &qca_soc_data_wcn3998}, @@ -2384,6 +2431,18 @@ static const struct acpi_device_id qca_bluetooth_acpi_match[] = { MODULE_DEVICE_TABLE(acpi, qca_bluetooth_acpi_match); #endif +#ifdef CONFIG_DEV_COREDUMP +static void hciqca_coredump(struct device *dev) +{ + struct serdev_device *serdev = to_serdev_device(dev); + struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev); + struct hci_uart *hu = &qcadev->serdev_hu; + struct hci_dev *hdev = hu->hdev; + + if (hdev->dump.coredump) + hdev->dump.coredump(hdev); +} +#endif static struct serdev_device_driver qca_serdev_driver = { .probe = qca_serdev_probe, @@ -2394,6 +2453,9 @@ static struct serdev_device_driver qca_serdev_driver = { .acpi_match_table = ACPI_PTR(qca_bluetooth_acpi_match), .shutdown = qca_serdev_shutdown, .pm = &qca_pm_ops, +#ifdef CONFIG_DEV_COREDUMP + .coredump = hciqca_coredump, +#endif }, }; diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 4953c1494723..be43cd08027b 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -571,6 +571,7 @@ config VMXNET3 tristate "VMware VMXNET3 ethernet driver" depends on PCI && INET depends on PAGE_SIZE_LESS_THAN_64KB + select PAGE_POOL help This driver supports VMware's vmxnet3 virtual ethernet NIC. To compile this driver as a module, choose M here: the diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index 594094526648..b19492a7f6ad 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -49,9 +49,6 @@ DEFINE_SHOW_ATTRIBUTE(bond_debug_rlb_hash); void bond_debug_register(struct bonding *bond) { - if (!bonding_debug_root) - return; - bond->debug_dir = debugfs_create_dir(bond->dev->name, bonding_debug_root); @@ -61,9 +58,6 @@ void bond_debug_register(struct bonding *bond) void bond_debug_unregister(struct bonding *bond) { - if (!bonding_debug_root) - return; - debugfs_remove_recursive(bond->debug_dir); } @@ -71,9 +65,6 @@ void bond_debug_reregister(struct bonding *bond) { struct dentry *d; - if (!bonding_debug_root) - return; - d = debugfs_rename(bonding_debug_root, bond->debug_dir, bonding_debug_root, bond->dev->name); if (!IS_ERR(d)) { @@ -84,11 +75,11 @@ void bond_debug_reregister(struct bonding *bond) } } -void bond_create_debugfs(void) +void __init bond_create_debugfs(void) { bonding_debug_root = debugfs_create_dir("bonding", NULL); - if (!bonding_debug_root) + if (IS_ERR(bonding_debug_root)) pr_warn("Warning: Cannot create bonding directory in debugfs\n"); } @@ -113,7 +104,7 @@ void bond_debug_reregister(struct bonding *bond) { } -void bond_create_debugfs(void) +void __init bond_create_debugfs(void) { } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index d26c69d84c1e..f398bec78457 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -5046,19 +5046,7 @@ static void bond_set_slave_arr(struct bonding *bond, static void bond_reset_slave_arr(struct bonding *bond) { - struct bond_up_slave *usable, *all; - - usable = rtnl_dereference(bond->usable_slaves); - if (usable) { - RCU_INIT_POINTER(bond->usable_slaves, NULL); - kfree_rcu(usable, rcu); - } - - all = rtnl_dereference(bond->all_slaves); - if (all) { - RCU_INIT_POINTER(bond->all_slaves, NULL); - kfree_rcu(all, rcu); - } + bond_set_slave_arr(bond, NULL, NULL); } /* Build the usable slaves array in control path for modes that use xmit-hash @@ -5875,8 +5863,7 @@ static void bond_destructor(struct net_device *bond_dev) if (bond->wq) destroy_workqueue(bond->wq); - if (bond->rr_tx_counter) - free_percpu(bond->rr_tx_counter); + free_percpu(bond->rr_tx_counter); } void bond_setup(struct net_device *bond_dev) @@ -5951,7 +5938,6 @@ void bond_setup(struct net_device *bond_dev) static void bond_uninit(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct bond_up_slave *usable, *all; struct list_head *iter; struct slave *slave; @@ -5962,17 +5948,7 @@ static void bond_uninit(struct net_device *bond_dev) __bond_release_one(bond_dev, slave->dev, true, true); netdev_info(bond_dev, "Released all slaves\n"); - usable = rtnl_dereference(bond->usable_slaves); - if (usable) { - RCU_INIT_POINTER(bond->usable_slaves, NULL); - kfree_rcu(usable, rcu); - } - - all = rtnl_dereference(bond->all_slaves); - if (all) { - RCU_INIT_POINTER(bond->all_slaves, NULL); - kfree_rcu(all, rcu); - } + bond_set_slave_arr(bond, NULL, NULL); list_del(&bond->bond_list); @@ -5981,7 +5957,7 @@ static void bond_uninit(struct net_device *bond_dev) /*------------------------- Module initialization ---------------------------*/ -static int bond_check_params(struct bond_params *params) +static int __init bond_check_params(struct bond_params *params) { int arp_validate_value, fail_over_mac_value, primary_reselect_value, i; struct bond_opt_value newval; diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 0bb59da24922..2805135a7205 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -803,7 +803,7 @@ static const struct attribute_group bonding_group = { /* Initialize sysfs. This sets up the bonding_masters file in * /sys/class/net. */ -int bond_create_sysfs(struct bond_net *bn) +int __net_init bond_create_sysfs(struct bond_net *bn) { int ret; @@ -836,7 +836,7 @@ int bond_create_sysfs(struct bond_net *bn) } /* Remove /sys/class/net/bonding_masters. */ -void bond_destroy_sysfs(struct bond_net *bn) +void __net_exit bond_destroy_sysfs(struct bond_net *bn) { netdev_class_remove_file_ns(&bn->class_attr_bonding_masters, bn->net); } diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c index fdda62d6eb16..294312b58e4f 100644 --- a/drivers/net/dsa/mv88e6060.c +++ b/drivers/net/dsa/mv88e6060.c @@ -247,11 +247,56 @@ mv88e6060_phy_write(struct dsa_switch *ds, int port, int regnum, u16 val) return reg_write(priv, addr, regnum, val); } +static void mv88e6060_phylink_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) +{ + unsigned long *interfaces = config->supported_interfaces; + struct mv88e6060_priv *priv = ds->priv; + int addr = REG_PORT(port); + int ret; + + ret = reg_read(priv, addr, PORT_STATUS); + if (ret < 0) { + dev_err(ds->dev, + "port %d: unable to read status register: %pe\n", + port, ERR_PTR(ret)); + return; + } + + /* If the port is configured in SNI mode (acts as a 10Mbps PHY), + * it should have phy-mode = "sni", but that doesn't yet exist, so + * forcibly fail validation until the need arises to introduce it. + */ + if (!(ret & PORT_STATUS_PORTMODE)) { + dev_warn(ds->dev, "port %d: SNI mode not supported\n", port); + return; + } + + config->mac_capabilities = MAC_100 | MAC_10 | MAC_SYM_PAUSE; + + if (port >= 4) { + /* Ports 4 and 5 can support MII, REVMII and REVRMII modes */ + __set_bit(PHY_INTERFACE_MODE_MII, interfaces); + __set_bit(PHY_INTERFACE_MODE_REVMII, interfaces); + __set_bit(PHY_INTERFACE_MODE_REVRMII, interfaces); + } + if (port <= 4) { + /* Ports 0 to 3 have internal PHYs, and port 4 can optionally + * use an internal PHY. + */ + /* Internal PHY */ + __set_bit(PHY_INTERFACE_MODE_INTERNAL, interfaces); + /* Default phylib interface mode */ + __set_bit(PHY_INTERFACE_MODE_GMII, interfaces); + } +} + static const struct dsa_switch_ops mv88e6060_switch_ops = { .get_tag_protocol = mv88e6060_get_tag_protocol, .setup = mv88e6060_setup, .phy_read = mv88e6060_phy_read, .phy_write = mv88e6060_phy_write, + .phylink_get_caps = mv88e6060_phylink_get_caps, }; static int mv88e6060_probe(struct mdio_device *mdiodev) diff --git a/drivers/net/dsa/realtek/realtek-mdio.c b/drivers/net/dsa/realtek/realtek-mdio.c index 4310e7793e58..292e6d087e8b 100644 --- a/drivers/net/dsa/realtek/realtek-mdio.c +++ b/drivers/net/dsa/realtek/realtek-mdio.c @@ -276,7 +276,7 @@ MODULE_DEVICE_TABLE(of, realtek_mdio_of_match); static struct mdio_driver realtek_mdio_driver = { .mdiodrv.driver = { .name = "realtek-mdio", - .of_match_table = of_match_ptr(realtek_mdio_of_match), + .of_match_table = realtek_mdio_of_match, }, .probe = realtek_mdio_probe, .remove = realtek_mdio_remove, diff --git a/drivers/net/dsa/realtek/realtek-smi.c b/drivers/net/dsa/realtek/realtek-smi.c index c2bd8bb6c9c2..ff13563059c5 100644 --- a/drivers/net/dsa/realtek/realtek-smi.c +++ b/drivers/net/dsa/realtek/realtek-smi.c @@ -556,7 +556,7 @@ MODULE_DEVICE_TABLE(of, realtek_smi_of_match); static struct platform_driver realtek_smi_driver = { .driver = { .name = "realtek-smi", - .of_match_table = of_match_ptr(realtek_smi_of_match), + .of_match_table = realtek_smi_of_match, }, .probe = realtek_smi_probe, .remove = realtek_smi_remove, diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c index c37d2e537230..9167e83fbceb 100644 --- a/drivers/net/dsa/rzn1_a5psw.c +++ b/drivers/net/dsa/rzn1_a5psw.c @@ -331,13 +331,9 @@ static void a5psw_flooding_set_resolution(struct a5psw *a5psw, int port, A5PSW_MCAST_DEF_MASK}; int i; - if (set) - a5psw->bridged_ports |= BIT(port); - else - a5psw->bridged_ports &= ~BIT(port); - for (i = 0; i < ARRAY_SIZE(offsets); i++) - a5psw_reg_writel(a5psw, offsets[i], a5psw->bridged_ports); + a5psw_reg_rmw(a5psw, offsets[i], BIT(port), + set ? BIT(port) : 0); } static void a5psw_port_set_standalone(struct a5psw *a5psw, int port, @@ -365,6 +361,8 @@ static int a5psw_port_bridge_join(struct dsa_switch *ds, int port, a5psw->br_dev = bridge.dev; a5psw_port_set_standalone(a5psw, port, false); + a5psw->bridged_ports |= BIT(port); + return 0; } @@ -373,6 +371,8 @@ static void a5psw_port_bridge_leave(struct dsa_switch *ds, int port, { struct a5psw *a5psw = ds->priv; + a5psw->bridged_ports &= ~BIT(port); + a5psw_port_set_standalone(a5psw, port, true); /* No more ports bridged */ @@ -380,9 +380,63 @@ static void a5psw_port_bridge_leave(struct dsa_switch *ds, int port, a5psw->br_dev = NULL; } +static int a5psw_port_pre_bridge_flags(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) +{ + if (flags.mask & ~(BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD | + BR_BCAST_FLOOD)) + return -EINVAL; + + return 0; +} + +static int +a5psw_port_bridge_flags(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) +{ + struct a5psw *a5psw = ds->priv; + u32 val; + + /* If a port is set as standalone, we do not want to be able to + * configure flooding nor learning which would result in joining the + * unique bridge. This can happen when a port leaves the bridge, in + * which case the DSA core will try to "clear" all flags for the + * standalone port (ie enable flooding, disable learning). In that case + * do not fail but do not apply the flags. + */ + if (!(a5psw->bridged_ports & BIT(port))) + return 0; + + if (flags.mask & BR_LEARNING) { + val = flags.val & BR_LEARNING ? 0 : A5PSW_INPUT_LEARN_DIS(port); + a5psw_reg_rmw(a5psw, A5PSW_INPUT_LEARN, + A5PSW_INPUT_LEARN_DIS(port), val); + } + + if (flags.mask & BR_FLOOD) { + val = flags.val & BR_FLOOD ? BIT(port) : 0; + a5psw_reg_rmw(a5psw, A5PSW_UCAST_DEF_MASK, BIT(port), val); + } + + if (flags.mask & BR_MCAST_FLOOD) { + val = flags.val & BR_MCAST_FLOOD ? BIT(port) : 0; + a5psw_reg_rmw(a5psw, A5PSW_MCAST_DEF_MASK, BIT(port), val); + } + + if (flags.mask & BR_BCAST_FLOOD) { + val = flags.val & BR_BCAST_FLOOD ? BIT(port) : 0; + a5psw_reg_rmw(a5psw, A5PSW_BCAST_DEF_MASK, BIT(port), val); + } + + return 0; +} + static void a5psw_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) { bool learning_enabled, rx_enabled, tx_enabled; + struct dsa_port *dp = dsa_to_port(ds, port); struct a5psw *a5psw = ds->priv; switch (state) { @@ -396,12 +450,12 @@ static void a5psw_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) case BR_STATE_LEARNING: rx_enabled = false; tx_enabled = false; - learning_enabled = true; + learning_enabled = dp->learning; break; case BR_STATE_FORWARDING: rx_enabled = true; tx_enabled = true; - learning_enabled = true; + learning_enabled = dp->learning; break; default: dev_err(ds->dev, "invalid STP state: %d\n", state); @@ -585,6 +639,146 @@ out_unlock: return ret; } +static int a5psw_port_vlan_filtering(struct dsa_switch *ds, int port, + bool vlan_filtering, + struct netlink_ext_ack *extack) +{ + u32 mask = BIT(port + A5PSW_VLAN_VERI_SHIFT) | + BIT(port + A5PSW_VLAN_DISC_SHIFT); + u32 val = vlan_filtering ? mask : 0; + struct a5psw *a5psw = ds->priv; + + /* Disable/enable vlan tagging */ + a5psw_reg_rmw(a5psw, A5PSW_VLAN_IN_MODE_ENA, BIT(port), + vlan_filtering ? BIT(port) : 0); + + /* Disable/enable vlan input filtering */ + a5psw_reg_rmw(a5psw, A5PSW_VLAN_VERIFY, mask, val); + + return 0; +} + +static int a5psw_find_vlan_entry(struct a5psw *a5psw, u16 vid) +{ + u32 vlan_res; + int i; + + /* Find vlan for this port */ + for (i = 0; i < A5PSW_VLAN_COUNT; i++) { + vlan_res = a5psw_reg_readl(a5psw, A5PSW_VLAN_RES(i)); + if (FIELD_GET(A5PSW_VLAN_RES_VLANID, vlan_res) == vid) + return i; + } + + return -1; +} + +static int a5psw_new_vlan_res_entry(struct a5psw *a5psw, u16 newvid) +{ + u32 vlan_res; + int i; + + /* Find a free VLAN entry */ + for (i = 0; i < A5PSW_VLAN_COUNT; i++) { + vlan_res = a5psw_reg_readl(a5psw, A5PSW_VLAN_RES(i)); + if (!(FIELD_GET(A5PSW_VLAN_RES_PORTMASK, vlan_res))) { + vlan_res = FIELD_PREP(A5PSW_VLAN_RES_VLANID, newvid); + a5psw_reg_writel(a5psw, A5PSW_VLAN_RES(i), vlan_res); + return i; + } + } + + return -1; +} + +static void a5psw_port_vlan_tagged_cfg(struct a5psw *a5psw, + unsigned int vlan_res_id, int port, + bool set) +{ + u32 mask = A5PSW_VLAN_RES_WR_PORTMASK | A5PSW_VLAN_RES_RD_TAGMASK | + BIT(port); + u32 vlan_res_off = A5PSW_VLAN_RES(vlan_res_id); + u32 val = A5PSW_VLAN_RES_WR_TAGMASK, reg; + + if (set) + val |= BIT(port); + + /* Toggle tag mask read */ + a5psw_reg_writel(a5psw, vlan_res_off, A5PSW_VLAN_RES_RD_TAGMASK); + reg = a5psw_reg_readl(a5psw, vlan_res_off); + a5psw_reg_writel(a5psw, vlan_res_off, A5PSW_VLAN_RES_RD_TAGMASK); + + reg &= ~mask; + reg |= val; + a5psw_reg_writel(a5psw, vlan_res_off, reg); +} + +static void a5psw_port_vlan_cfg(struct a5psw *a5psw, unsigned int vlan_res_id, + int port, bool set) +{ + u32 mask = A5PSW_VLAN_RES_WR_TAGMASK | BIT(port); + u32 reg = A5PSW_VLAN_RES_WR_PORTMASK; + + if (set) + reg |= BIT(port); + + a5psw_reg_rmw(a5psw, A5PSW_VLAN_RES(vlan_res_id), mask, reg); +} + +static int a5psw_port_vlan_add(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan, + struct netlink_ext_ack *extack) +{ + bool tagged = !(vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED); + bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; + struct a5psw *a5psw = ds->priv; + u16 vid = vlan->vid; + int vlan_res_id; + + dev_dbg(a5psw->dev, "Add VLAN %d on port %d, %s, %s\n", + vid, port, tagged ? "tagged" : "untagged", + pvid ? "PVID" : "no PVID"); + + vlan_res_id = a5psw_find_vlan_entry(a5psw, vid); + if (vlan_res_id < 0) { + vlan_res_id = a5psw_new_vlan_res_entry(a5psw, vid); + if (vlan_res_id < 0) + return -ENOSPC; + } + + a5psw_port_vlan_cfg(a5psw, vlan_res_id, port, true); + if (tagged) + a5psw_port_vlan_tagged_cfg(a5psw, vlan_res_id, port, true); + + /* Configure port to tag with corresponding VID, but do not enable it + * yet: wait for vlan filtering to be enabled to enable vlan port + * tagging + */ + if (pvid) + a5psw_reg_writel(a5psw, A5PSW_SYSTEM_TAGINFO(port), vid); + + return 0; +} + +static int a5psw_port_vlan_del(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan) +{ + struct a5psw *a5psw = ds->priv; + u16 vid = vlan->vid; + int vlan_res_id; + + dev_dbg(a5psw->dev, "Removing VLAN %d on port %d\n", vid, port); + + vlan_res_id = a5psw_find_vlan_entry(a5psw, vid); + if (vlan_res_id < 0) + return -EINVAL; + + a5psw_port_vlan_cfg(a5psw, vlan_res_id, port, false); + a5psw_port_vlan_tagged_cfg(a5psw, vlan_res_id, port, false); + + return 0; +} + static u64 a5psw_read_stat(struct a5psw *a5psw, u32 offset, int port) { u32 reg_lo, reg_hi; @@ -702,6 +896,27 @@ static void a5psw_get_eth_ctrl_stats(struct dsa_switch *ds, int port, ctrl_stats->MACControlFramesReceived = stat; } +static void a5psw_vlan_setup(struct a5psw *a5psw, int port) +{ + u32 reg; + + /* Enable TAG always mode for the port, this is actually controlled + * by VLAN_IN_MODE_ENA field which will be used for PVID insertion + */ + reg = A5PSW_VLAN_IN_MODE_TAG_ALWAYS; + reg <<= A5PSW_VLAN_IN_MODE_PORT_SHIFT(port); + a5psw_reg_rmw(a5psw, A5PSW_VLAN_IN_MODE, A5PSW_VLAN_IN_MODE_PORT(port), + reg); + + /* Set transparent mode for output frame manipulation, this will depend + * on the VLAN_RES configuration mode + */ + reg = A5PSW_VLAN_OUT_MODE_TRANSPARENT; + reg <<= A5PSW_VLAN_OUT_MODE_PORT_SHIFT(port); + a5psw_reg_rmw(a5psw, A5PSW_VLAN_OUT_MODE, + A5PSW_VLAN_OUT_MODE_PORT(port), reg); +} + static int a5psw_setup(struct dsa_switch *ds) { struct a5psw *a5psw = ds->priv; @@ -776,6 +991,8 @@ static int a5psw_setup(struct dsa_switch *ds) /* Enable standalone mode for user ports */ if (dsa_port_is_user(dp)) a5psw_port_set_standalone(a5psw, port, true); + + a5psw_vlan_setup(a5psw, port); } return 0; @@ -801,8 +1018,13 @@ static const struct dsa_switch_ops a5psw_switch_ops = { .set_ageing_time = a5psw_set_ageing_time, .port_bridge_join = a5psw_port_bridge_join, .port_bridge_leave = a5psw_port_bridge_leave, + .port_pre_bridge_flags = a5psw_port_pre_bridge_flags, + .port_bridge_flags = a5psw_port_bridge_flags, .port_stp_state_set = a5psw_port_stp_state_set, .port_fast_age = a5psw_port_fast_age, + .port_vlan_filtering = a5psw_port_vlan_filtering, + .port_vlan_add = a5psw_port_vlan_add, + .port_vlan_del = a5psw_port_vlan_del, .port_fdb_add = a5psw_port_fdb_add, .port_fdb_del = a5psw_port_fdb_del, .port_fdb_dump = a5psw_port_fdb_dump, @@ -992,6 +1214,8 @@ static int a5psw_probe(struct platform_device *pdev) if (IS_ERR(a5psw->base)) return PTR_ERR(a5psw->base); + a5psw->bridged_ports = BIT(A5PSW_CPU_PORT); + ret = a5psw_pcs_get(a5psw); if (ret) return ret; @@ -1090,7 +1314,7 @@ MODULE_DEVICE_TABLE(of, a5psw_of_mtable); static struct platform_driver a5psw_driver = { .driver = { .name = "rzn1_a5psw", - .of_match_table = of_match_ptr(a5psw_of_mtable), + .of_match_table = a5psw_of_mtable, }, .probe = a5psw_probe, .remove = a5psw_remove, diff --git a/drivers/net/dsa/rzn1_a5psw.h b/drivers/net/dsa/rzn1_a5psw.h index b869192eef3f..d54acedac194 100644 --- a/drivers/net/dsa/rzn1_a5psw.h +++ b/drivers/net/dsa/rzn1_a5psw.h @@ -51,7 +51,9 @@ #define A5PSW_VLAN_IN_MODE_TAG_ALWAYS 0x2 #define A5PSW_VLAN_OUT_MODE 0x2C -#define A5PSW_VLAN_OUT_MODE_PORT(port) (GENMASK(1, 0) << ((port) * 2)) +#define A5PSW_VLAN_OUT_MODE_PORT_SHIFT(port) ((port) * 2) +#define A5PSW_VLAN_OUT_MODE_PORT(port) (GENMASK(1, 0) << \ + A5PSW_VLAN_OUT_MODE_PORT_SHIFT(port)) #define A5PSW_VLAN_OUT_MODE_DIS 0x0 #define A5PSW_VLAN_OUT_MODE_STRIP 0x1 #define A5PSW_VLAN_OUT_MODE_TAG_THROUGH 0x2 @@ -60,7 +62,7 @@ #define A5PSW_VLAN_IN_MODE_ENA 0x30 #define A5PSW_VLAN_TAG_ID 0x34 -#define A5PSW_SYSTEM_TAGINFO(port) (0x200 + A5PSW_PORT_OFFSET(port)) +#define A5PSW_SYSTEM_TAGINFO(port) (0x200 + 4 * (port)) #define A5PSW_AUTH_PORT(port) (0x240 + 4 * (port)) #define A5PSW_AUTH_PORT_AUTHORIZED BIT(0) @@ -69,7 +71,7 @@ #define A5PSW_VLAN_RES_WR_PORTMASK BIT(30) #define A5PSW_VLAN_RES_WR_TAGMASK BIT(29) #define A5PSW_VLAN_RES_RD_TAGMASK BIT(28) -#define A5PSW_VLAN_RES_ID GENMASK(16, 5) +#define A5PSW_VLAN_RES_VLANID GENMASK(16, 5) #define A5PSW_VLAN_RES_PORTMASK GENMASK(4, 0) #define A5PSW_RXMATCH_CONFIG(port) (0x3e80 + 4 * (port)) diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index 5fab589b3ddf..3d9220f9c9fe 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -3982,8 +3982,7 @@ static int et131x_pci_setup(struct pci_dev *pdev, } adapter->mii_bus->name = "et131x_eth_mii"; - snprintf(adapter->mii_bus->id, MII_BUS_ID_SIZE, "%x", - (adapter->pdev->bus->number << 8) | adapter->pdev->devfn); + snprintf(adapter->mii_bus->id, MII_BUS_ID_SIZE, "%x", pci_dev_id(adapter->pdev)); adapter->mii_bus->priv = netdev; adapter->mii_bus->read = et131x_mdio_read; adapter->mii_bus->write = et131x_mdio_write; diff --git a/drivers/net/ethernet/amd/atarilance.c b/drivers/net/ethernet/amd/atarilance.c index ec704222925d..751454d305c6 100644 --- a/drivers/net/ethernet/amd/atarilance.c +++ b/drivers/net/ethernet/amd/atarilance.c @@ -367,7 +367,7 @@ static void *slow_memcpy( void *dst, const void *src, size_t len ) } -struct net_device * __init atarilance_probe(void) +static struct net_device * __init atarilance_probe(void) { int i; static int found; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 41d96f4b23d8..4d4140b7c450 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -2041,7 +2041,7 @@ static int xgene_enet_probe(struct platform_device *pdev) of_id = of_match_device(xgene_enet_of_match, &pdev->dev); if (of_id) { - pdata->enet_id = (enum xgene_enet_id)of_id->data; + pdata->enet_id = (uintptr_t)of_id->data; } #ifdef CONFIG_ACPI else { diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 5ef073a79ce9..7f956cf36337 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -1539,8 +1539,7 @@ static int tg3_mdio_init(struct tg3 *tp) return -ENOMEM; tp->mdio_bus->name = "tg3 mdio bus"; - snprintf(tp->mdio_bus->id, MII_BUS_ID_SIZE, "%x", - (tp->pdev->bus->number << 8) | tp->pdev->devfn); + snprintf(tp->mdio_bus->id, MII_BUS_ID_SIZE, "%x", pci_dev_id(tp->pdev)); tp->mdio_bus->priv = tp; tp->mdio_bus->parent = &tp->pdev->dev; tp->mdio_bus->read = &tg3_mdio_read; diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 692cb2d04c1c..a8b9d1a3e4d5 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2538,7 +2538,7 @@ MODULE_DEVICE_TABLE(of, gemini_ethernet_port_of_match); static struct platform_driver gemini_ethernet_port_driver = { .driver = { .name = "gemini-ethernet-port", - .of_match_table = of_match_ptr(gemini_ethernet_port_of_match), + .of_match_table = gemini_ethernet_port_of_match, }, .probe = gemini_ethernet_port_probe, .remove = gemini_ethernet_port_remove, @@ -2604,7 +2604,7 @@ MODULE_DEVICE_TABLE(of, gemini_ethernet_of_match); static struct platform_driver gemini_ethernet_driver = { .driver = { .name = DRV_NAME, - .of_match_table = of_match_ptr(gemini_ethernet_of_match), + .of_match_table = gemini_ethernet_of_match, }, .probe = gemini_ethernet_probe, .remove = gemini_ethernet_remove, diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c index 139fe66f8bcd..183069581bc0 100644 --- a/drivers/net/ethernet/faraday/ftmac100.c +++ b/drivers/net/ethernet/faraday/ftmac100.c @@ -149,6 +149,40 @@ static void ftmac100_set_mac(struct ftmac100 *priv, const unsigned char *mac) iowrite32(laddr, priv->base + FTMAC100_OFFSET_MAC_LADR); } +static void ftmac100_setup_mc_ht(struct ftmac100 *priv) +{ + struct netdev_hw_addr *ha; + u64 maht = 0; /* Multicast Address Hash Table */ + + netdev_for_each_mc_addr(ha, priv->netdev) { + u32 hash = ether_crc(ETH_ALEN, ha->addr) >> 26; + + maht |= BIT_ULL(hash); + } + + iowrite32(lower_32_bits(maht), priv->base + FTMAC100_OFFSET_MAHT0); + iowrite32(upper_32_bits(maht), priv->base + FTMAC100_OFFSET_MAHT1); +} + +static void ftmac100_set_rx_bits(struct ftmac100 *priv, unsigned int *maccr) +{ + struct net_device *netdev = priv->netdev; + + /* Clear all */ + *maccr &= ~(FTMAC100_MACCR_RCV_ALL | FTMAC100_MACCR_RX_MULTIPKT | + FTMAC100_MACCR_HT_MULTI_EN); + + /* Set the requested bits */ + if (netdev->flags & IFF_PROMISC) + *maccr |= FTMAC100_MACCR_RCV_ALL; + if (netdev->flags & IFF_ALLMULTI) + *maccr |= FTMAC100_MACCR_RX_MULTIPKT; + else if (netdev_mc_count(netdev)) { + *maccr |= FTMAC100_MACCR_HT_MULTI_EN; + ftmac100_setup_mc_ht(priv); + } +} + #define MACCR_ENABLE_ALL (FTMAC100_MACCR_XMT_EN | \ FTMAC100_MACCR_RCV_EN | \ FTMAC100_MACCR_XDMA_EN | \ @@ -182,11 +216,7 @@ static int ftmac100_start_hw(struct ftmac100 *priv) if (netdev->mtu > ETH_DATA_LEN) maccr |= FTMAC100_MACCR_RX_FTL; - /* Add other bits as needed */ - if (netdev->flags & IFF_PROMISC) - maccr |= FTMAC100_MACCR_RCV_ALL; - if (netdev->flags & IFF_ALLMULTI) - maccr |= FTMAC100_MACCR_RX_MULTIPKT; + ftmac100_set_rx_bits(priv, &maccr); iowrite32(maccr, priv->base + FTMAC100_OFFSET_MACCR); return 0; @@ -1067,6 +1097,15 @@ static int ftmac100_change_mtu(struct net_device *netdev, int mtu) return 0; } +static void ftmac100_set_rx_mode(struct net_device *netdev) +{ + struct ftmac100 *priv = netdev_priv(netdev); + unsigned int maccr = ioread32(priv->base + FTMAC100_OFFSET_MACCR); + + ftmac100_set_rx_bits(priv, &maccr); + iowrite32(maccr, priv->base + FTMAC100_OFFSET_MACCR); +} + static const struct net_device_ops ftmac100_netdev_ops = { .ndo_open = ftmac100_open, .ndo_stop = ftmac100_stop, @@ -1075,6 +1114,7 @@ static const struct net_device_ops ftmac100_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_eth_ioctl = ftmac100_do_ioctl, .ndo_change_mtu = ftmac100_change_mtu, + .ndo_set_rx_mode = ftmac100_set_rx_mode, }; /****************************************************************************** diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 5ca9906d7c6a..a8fbcada6b01 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -548,13 +548,11 @@ enum { enum fec_txbuf_type { FEC_TXBUF_T_SKB, FEC_TXBUF_T_XDP_NDO, + FEC_TXBUF_T_XDP_TX, }; struct fec_tx_buffer { - union { - struct sk_buff *skb; - struct xdp_frame *xdp; - }; + void *buf_p; enum fec_txbuf_type type; }; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 3bd0bf03aedb..f77105f017c1 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -69,6 +69,7 @@ #include <soc/imx/cpuidle.h> #include <linux/filter.h> #include <linux/bpf.h> +#include <linux/bpf_trace.h> #include <asm/cacheflush.h> @@ -76,6 +77,9 @@ static void set_multicast_list(struct net_device *ndev); static void fec_enet_itr_coal_set(struct net_device *ndev); +static int fec_enet_xdp_tx_xmit(struct fec_enet_private *fep, + int cpu, struct xdp_buff *xdp, + u32 dma_sync_len); #define DRIVER_NAME "fec" @@ -396,7 +400,7 @@ static void fec_dump(struct net_device *ndev) fec16_to_cpu(bdp->cbd_sc), fec32_to_cpu(bdp->cbd_bufaddr), fec16_to_cpu(bdp->cbd_datlen), - txq->tx_buf[index].skb); + txq->tx_buf[index].buf_p); bdp = fec_enet_get_nextdesc(bdp, &txq->bd); index++; } while (bdp != txq->bd.base); @@ -653,7 +657,7 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq, index = fec_enet_get_bd_index(last_bdp, &txq->bd); /* Save skb pointer */ - txq->tx_buf[index].skb = skb; + txq->tx_buf[index].buf_p = skb; /* Make sure the updates to rest of the descriptor are performed before * transferring ownership. @@ -859,7 +863,7 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq, } /* Save skb pointer */ - txq->tx_buf[index].skb = skb; + txq->tx_buf[index].buf_p = skb; skb_tx_timestamp(skb); txq->bd.cur = bdp; @@ -956,26 +960,27 @@ static void fec_enet_bd_init(struct net_device *dev) fec32_to_cpu(bdp->cbd_bufaddr), fec16_to_cpu(bdp->cbd_datlen), DMA_TO_DEVICE); - if (txq->tx_buf[i].skb) { - dev_kfree_skb_any(txq->tx_buf[i].skb); - txq->tx_buf[i].skb = NULL; - } - } else { + if (txq->tx_buf[i].buf_p) + dev_kfree_skb_any(txq->tx_buf[i].buf_p); + } else if (txq->tx_buf[i].type == FEC_TXBUF_T_XDP_NDO) { if (bdp->cbd_bufaddr) dma_unmap_single(&fep->pdev->dev, fec32_to_cpu(bdp->cbd_bufaddr), fec16_to_cpu(bdp->cbd_datlen), DMA_TO_DEVICE); - if (txq->tx_buf[i].xdp) { - xdp_return_frame(txq->tx_buf[i].xdp); - txq->tx_buf[i].xdp = NULL; - } + if (txq->tx_buf[i].buf_p) + xdp_return_frame(txq->tx_buf[i].buf_p); + } else { + struct page *page = txq->tx_buf[i].buf_p; - /* restore default tx buffer type: FEC_TXBUF_T_SKB */ - txq->tx_buf[i].type = FEC_TXBUF_T_SKB; + if (page) + page_pool_put_page(page->pp, page, 0, false); } + txq->tx_buf[i].buf_p = NULL; + /* restore default tx buffer type: FEC_TXBUF_T_SKB */ + txq->tx_buf[i].type = FEC_TXBUF_T_SKB; bdp->cbd_bufaddr = cpu_to_fec32(0); bdp = fec_enet_get_nextdesc(bdp, &txq->bd); } @@ -1382,6 +1387,8 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget) struct netdev_queue *nq; int index = 0; int entries_free; + struct page *page; + int frame_len; fep = netdev_priv(ndev); @@ -1403,8 +1410,7 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget) index = fec_enet_get_bd_index(bdp, &txq->bd); if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB) { - skb = txq->tx_buf[index].skb; - txq->tx_buf[index].skb = NULL; + skb = txq->tx_buf[index].buf_p; if (bdp->cbd_bufaddr && !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr))) dma_unmap_single(&fep->pdev->dev, @@ -1423,17 +1429,24 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget) if (unlikely(!budget)) break; - xdpf = txq->tx_buf[index].xdp; - if (bdp->cbd_bufaddr) - dma_unmap_single(&fep->pdev->dev, - fec32_to_cpu(bdp->cbd_bufaddr), - fec16_to_cpu(bdp->cbd_datlen), - DMA_TO_DEVICE); + if (txq->tx_buf[index].type == FEC_TXBUF_T_XDP_NDO) { + xdpf = txq->tx_buf[index].buf_p; + if (bdp->cbd_bufaddr) + dma_unmap_single(&fep->pdev->dev, + fec32_to_cpu(bdp->cbd_bufaddr), + fec16_to_cpu(bdp->cbd_datlen), + DMA_TO_DEVICE); + } else { + page = txq->tx_buf[index].buf_p; + } + bdp->cbd_bufaddr = cpu_to_fec32(0); - if (!xdpf) { + if (unlikely(!txq->tx_buf[index].buf_p)) { txq->tx_buf[index].type = FEC_TXBUF_T_SKB; goto tx_buf_done; } + + frame_len = fec16_to_cpu(bdp->cbd_datlen); } /* Check for errors. */ @@ -1457,7 +1470,7 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget) if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB) ndev->stats.tx_bytes += skb->len; else - ndev->stats.tx_bytes += xdpf->len; + ndev->stats.tx_bytes += frame_len; } /* Deferred means some collisions occurred during transmit, @@ -1482,14 +1495,17 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget) /* Free the sk buffer associated with this last transmit */ dev_kfree_skb_any(skb); - } else { - xdp_return_frame(xdpf); - - txq->tx_buf[index].xdp = NULL; - /* restore default tx buffer type: FEC_TXBUF_T_SKB */ - txq->tx_buf[index].type = FEC_TXBUF_T_SKB; + } else if (txq->tx_buf[index].type == FEC_TXBUF_T_XDP_NDO) { + xdp_return_frame_rx_napi(xdpf); + } else { /* recycle pages of XDP_TX frames */ + /* The dma_sync_size = 0 as XDP_TX has already synced DMA for_device */ + page_pool_put_page(page->pp, page, 0, true); } + txq->tx_buf[index].buf_p = NULL; + /* restore default tx buffer type: FEC_TXBUF_T_SKB */ + txq->tx_buf[index].type = FEC_TXBUF_T_SKB; + tx_buf_done: /* Make sure the update to bdp and tx_buf are performed * before dirty_tx @@ -1542,7 +1558,7 @@ static void fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq, static u32 fec_enet_run_xdp(struct fec_enet_private *fep, struct bpf_prog *prog, - struct xdp_buff *xdp, struct fec_enet_priv_rx_q *rxq, int index) + struct xdp_buff *xdp, struct fec_enet_priv_rx_q *rxq, int cpu) { unsigned int sync, len = xdp->data_end - xdp->data; u32 ret = FEC_ENET_XDP_PASS; @@ -1552,8 +1568,10 @@ fec_enet_run_xdp(struct fec_enet_private *fep, struct bpf_prog *prog, act = bpf_prog_run_xdp(prog, xdp); - /* Due xdp_adjust_tail: DMA sync for_device cover max len CPU touch */ - sync = xdp->data_end - xdp->data_hard_start - FEC_ENET_XDP_HEADROOM; + /* Due xdp_adjust_tail and xdp_adjust_head: DMA sync for_device cover + * max len CPU touch + */ + sync = xdp->data_end - xdp->data; sync = max(sync, len); switch (act) { @@ -1574,11 +1592,19 @@ fec_enet_run_xdp(struct fec_enet_private *fep, struct bpf_prog *prog, } break; - default: - bpf_warn_invalid_xdp_action(fep->netdev, prog, act); - fallthrough; - case XDP_TX: + err = fec_enet_xdp_tx_xmit(fep, cpu, xdp, sync); + if (unlikely(err)) { + ret = FEC_ENET_XDP_CONSUMED; + page = virt_to_head_page(xdp->data); + page_pool_put_page(rxq->page_pool, page, sync, true); + trace_xdp_exception(fep->netdev, prog, act); + } else { + ret = FEC_ENET_XDP_TX; + } + break; + + default: bpf_warn_invalid_xdp_action(fep->netdev, prog, act); fallthrough; @@ -1620,6 +1646,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) struct bpf_prog *xdp_prog = READ_ONCE(fep->xdp_prog); u32 ret, xdp_result = FEC_ENET_XDP_PASS; u32 data_start = FEC_ENET_XDP_HEADROOM; + int cpu = smp_processor_id(); struct xdp_buff xdp; struct page *page; u32 sub_len = 4; @@ -1698,7 +1725,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) /* subtract 16bit shift and FCS */ xdp_prepare_buff(&xdp, page_address(page), data_start, pkt_len - sub_len, false); - ret = fec_enet_run_xdp(fep, xdp_prog, &xdp, rxq, index); + ret = fec_enet_run_xdp(fep, xdp_prog, &xdp, rxq, cpu); xdp_result |= ret; if (ret != FEC_ENET_XDP_PASS) goto rx_processing_done; @@ -3208,7 +3235,6 @@ static void fec_enet_free_buffers(struct net_device *ndev) { struct fec_enet_private *fep = netdev_priv(ndev); unsigned int i; - struct sk_buff *skb; struct fec_enet_priv_tx_q *txq; struct fec_enet_priv_rx_q *rxq; unsigned int q; @@ -3233,18 +3259,23 @@ static void fec_enet_free_buffers(struct net_device *ndev) kfree(txq->tx_bounce[i]); txq->tx_bounce[i] = NULL; + if (!txq->tx_buf[i].buf_p) { + txq->tx_buf[i].type = FEC_TXBUF_T_SKB; + continue; + } + if (txq->tx_buf[i].type == FEC_TXBUF_T_SKB) { - skb = txq->tx_buf[i].skb; - txq->tx_buf[i].skb = NULL; - dev_kfree_skb(skb); + dev_kfree_skb(txq->tx_buf[i].buf_p); + } else if (txq->tx_buf[i].type == FEC_TXBUF_T_XDP_NDO) { + xdp_return_frame(txq->tx_buf[i].buf_p); } else { - if (txq->tx_buf[i].xdp) { - xdp_return_frame(txq->tx_buf[i].xdp); - txq->tx_buf[i].xdp = NULL; - } + struct page *page = txq->tx_buf[i].buf_p; - txq->tx_buf[i].type = FEC_TXBUF_T_SKB; + page_pool_put_page(page->pp, page, 0, false); } + + txq->tx_buf[i].buf_p = NULL; + txq->tx_buf[i].type = FEC_TXBUF_T_SKB; } } } @@ -3767,12 +3798,14 @@ fec_enet_xdp_get_tx_queue(struct fec_enet_private *fep, int index) static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, struct fec_enet_priv_tx_q *txq, - struct xdp_frame *frame) + void *frame, u32 dma_sync_len, + bool ndo_xmit) { unsigned int index, status, estatus; struct bufdesc *bdp; dma_addr_t dma_addr; int entries_free; + u16 frame_len; entries_free = fec_enet_get_free_txdesc_num(txq); if (entries_free < MAX_SKB_FRAGS + 1) { @@ -3787,17 +3820,37 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, index = fec_enet_get_bd_index(bdp, &txq->bd); - dma_addr = dma_map_single(&fep->pdev->dev, frame->data, - frame->len, DMA_TO_DEVICE); - if (dma_mapping_error(&fep->pdev->dev, dma_addr)) - return -ENOMEM; + if (ndo_xmit) { + struct xdp_frame *xdpf = frame; + + dma_addr = dma_map_single(&fep->pdev->dev, xdpf->data, + xdpf->len, DMA_TO_DEVICE); + if (dma_mapping_error(&fep->pdev->dev, dma_addr)) + return -ENOMEM; + + frame_len = xdpf->len; + txq->tx_buf[index].buf_p = xdpf; + txq->tx_buf[index].type = FEC_TXBUF_T_XDP_NDO; + } else { + struct xdp_buff *xdpb = frame; + struct page *page; + + page = virt_to_page(xdpb->data); + dma_addr = page_pool_get_dma_addr(page) + + (xdpb->data - xdpb->data_hard_start); + dma_sync_single_for_device(&fep->pdev->dev, dma_addr, + dma_sync_len, DMA_BIDIRECTIONAL); + frame_len = xdpb->data_end - xdpb->data; + txq->tx_buf[index].buf_p = page; + txq->tx_buf[index].type = FEC_TXBUF_T_XDP_TX; + } status |= (BD_ENET_TX_INTR | BD_ENET_TX_LAST); if (fep->bufdesc_ex) estatus = BD_ENET_TX_INT; bdp->cbd_bufaddr = cpu_to_fec32(dma_addr); - bdp->cbd_datlen = cpu_to_fec16(frame->len); + bdp->cbd_datlen = cpu_to_fec16(frame_len); if (fep->bufdesc_ex) { struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp; @@ -3809,9 +3862,6 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, ebdp->cbd_esc = cpu_to_fec32(estatus); } - txq->tx_buf[index].type = FEC_TXBUF_T_XDP_NDO; - txq->tx_buf[index].xdp = frame; - /* Make sure the updates to rest of the descriptor are performed before * transferring ownership. */ @@ -3837,6 +3887,29 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, return 0; } +static int fec_enet_xdp_tx_xmit(struct fec_enet_private *fep, + int cpu, struct xdp_buff *xdp, + u32 dma_sync_len) +{ + struct fec_enet_priv_tx_q *txq; + struct netdev_queue *nq; + int queue, ret; + + queue = fec_enet_xdp_get_tx_queue(fep, cpu); + txq = fep->tx_queue[queue]; + nq = netdev_get_tx_queue(fep->netdev, queue); + + __netif_tx_lock(nq, cpu); + + /* Avoid tx timeout as XDP shares the queue with kernel stack */ + txq_trans_cond_update(nq); + ret = fec_enet_txq_xmit_frame(fep, txq, xdp, dma_sync_len, false); + + __netif_tx_unlock(nq); + + return ret; +} + static int fec_enet_xdp_xmit(struct net_device *dev, int num_frames, struct xdp_frame **frames, @@ -3859,7 +3932,7 @@ static int fec_enet_xdp_xmit(struct net_device *dev, /* Avoid tx timeout as XDP shares the queue with kernel stack */ txq_trans_cond_update(nq); for (i = 0; i < num_frames; i++) { - if (fec_enet_txq_xmit_frame(fep, txq, frames[i]) < 0) + if (fec_enet_txq_xmit_frame(fep, txq, frames[i], 0, true) < 0) break; sent_frames++; } diff --git a/drivers/net/ethernet/hisilicon/hns3/Makefile b/drivers/net/ethernet/hisilicon/hns3/Makefile index 6efea4662858..e214bfaece1f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/Makefile +++ b/drivers/net/ethernet/hisilicon/hns3/Makefile @@ -17,11 +17,11 @@ hns3-$(CONFIG_HNS3_DCB) += hns3_dcbnl.o obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o -hclgevf-objs = hns3vf/hclgevf_main.o hns3vf/hclgevf_mbx.o hns3vf/hclgevf_devlink.o \ +hclgevf-objs = hns3vf/hclgevf_main.o hns3vf/hclgevf_mbx.o hns3vf/hclgevf_devlink.o hns3vf/hclgevf_regs.o \ hns3_common/hclge_comm_cmd.o hns3_common/hclge_comm_rss.o hns3_common/hclge_comm_tqp_stats.o obj-$(CONFIG_HNS3_HCLGE) += hclge.o -hclge-objs = hns3pf/hclge_main.o hns3pf/hclge_mdio.o hns3pf/hclge_tm.o \ +hclge-objs = hns3pf/hclge_main.o hns3pf/hclge_mdio.o hns3pf/hclge_tm.o hns3pf/hclge_regs.o \ hns3pf/hclge_mbx.o hns3pf/hclge_err.o hns3pf/hclge_debugfs.o hns3pf/hclge_ptp.o hns3pf/hclge_devlink.o \ hns3_common/hclge_comm_cmd.o hns3_common/hclge_comm_rss.o hns3_common/hclge_comm_tqp_stats.o diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 514a20bce4f4..a4b43bcd2f0c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -382,6 +382,7 @@ struct hnae3_dev_specs { u16 umv_size; u16 mc_mac_size; u32 mac_stats_num; + u8 tnl_num; }; struct hnae3_client_ops { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 0bd858620f27..4d15eb73b972 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -826,7 +826,9 @@ struct hclge_dev_specs_1_cmd { u8 rsv0[2]; __le16 umv_size; __le16 mc_mac_size; - u8 rsv1[12]; + u8 rsv1[6]; + u8 tnl_num; + u8 rsv2[5]; }; /* mac speed type defined in firmware command */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 0fb2eaee3e8a..f01a7a9ee02c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -7,6 +7,7 @@ #include "hclge_debugfs.h" #include "hclge_err.h" #include "hclge_main.h" +#include "hclge_regs.h" #include "hclge_tm.h" #include "hnae3.h" diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 437b510f2b80..0f50dba6cc47 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -20,6 +20,7 @@ #include "hclge_main.h" #include "hclge_mbx.h" #include "hclge_mdio.h" +#include "hclge_regs.h" #include "hclge_tm.h" #include "hclge_err.h" #include "hnae3.h" @@ -40,20 +41,6 @@ #define HCLGE_PF_RESET_SYNC_TIME 20 #define HCLGE_PF_RESET_SYNC_CNT 1500 -/* Get DFX BD number offset */ -#define HCLGE_DFX_BIOS_BD_OFFSET 1 -#define HCLGE_DFX_SSU_0_BD_OFFSET 2 -#define HCLGE_DFX_SSU_1_BD_OFFSET 3 -#define HCLGE_DFX_IGU_BD_OFFSET 4 -#define HCLGE_DFX_RPU_0_BD_OFFSET 5 -#define HCLGE_DFX_RPU_1_BD_OFFSET 6 -#define HCLGE_DFX_NCSI_BD_OFFSET 7 -#define HCLGE_DFX_RTC_BD_OFFSET 8 -#define HCLGE_DFX_PPP_BD_OFFSET 9 -#define HCLGE_DFX_RCB_BD_OFFSET 10 -#define HCLGE_DFX_TQP_BD_OFFSET 11 -#define HCLGE_DFX_SSU_2_BD_OFFSET 12 - #define HCLGE_LINK_STATUS_MS 10 static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps); @@ -94,62 +81,6 @@ static const struct pci_device_id ae_algo_pci_tbl[] = { MODULE_DEVICE_TABLE(pci, ae_algo_pci_tbl); -static const u32 cmdq_reg_addr_list[] = {HCLGE_COMM_NIC_CSQ_BASEADDR_L_REG, - HCLGE_COMM_NIC_CSQ_BASEADDR_H_REG, - HCLGE_COMM_NIC_CSQ_DEPTH_REG, - HCLGE_COMM_NIC_CSQ_TAIL_REG, - HCLGE_COMM_NIC_CSQ_HEAD_REG, - HCLGE_COMM_NIC_CRQ_BASEADDR_L_REG, - HCLGE_COMM_NIC_CRQ_BASEADDR_H_REG, - HCLGE_COMM_NIC_CRQ_DEPTH_REG, - HCLGE_COMM_NIC_CRQ_TAIL_REG, - HCLGE_COMM_NIC_CRQ_HEAD_REG, - HCLGE_COMM_VECTOR0_CMDQ_SRC_REG, - HCLGE_COMM_CMDQ_INTR_STS_REG, - HCLGE_COMM_CMDQ_INTR_EN_REG, - HCLGE_COMM_CMDQ_INTR_GEN_REG}; - -static const u32 common_reg_addr_list[] = {HCLGE_MISC_VECTOR_REG_BASE, - HCLGE_PF_OTHER_INT_REG, - HCLGE_MISC_RESET_STS_REG, - HCLGE_MISC_VECTOR_INT_STS, - HCLGE_GLOBAL_RESET_REG, - HCLGE_FUN_RST_ING, - HCLGE_GRO_EN_REG}; - -static const u32 ring_reg_addr_list[] = {HCLGE_RING_RX_ADDR_L_REG, - HCLGE_RING_RX_ADDR_H_REG, - HCLGE_RING_RX_BD_NUM_REG, - HCLGE_RING_RX_BD_LENGTH_REG, - HCLGE_RING_RX_MERGE_EN_REG, - HCLGE_RING_RX_TAIL_REG, - HCLGE_RING_RX_HEAD_REG, - HCLGE_RING_RX_FBD_NUM_REG, - HCLGE_RING_RX_OFFSET_REG, - HCLGE_RING_RX_FBD_OFFSET_REG, - HCLGE_RING_RX_STASH_REG, - HCLGE_RING_RX_BD_ERR_REG, - HCLGE_RING_TX_ADDR_L_REG, - HCLGE_RING_TX_ADDR_H_REG, - HCLGE_RING_TX_BD_NUM_REG, - HCLGE_RING_TX_PRIORITY_REG, - HCLGE_RING_TX_TC_REG, - HCLGE_RING_TX_MERGE_EN_REG, - HCLGE_RING_TX_TAIL_REG, - HCLGE_RING_TX_HEAD_REG, - HCLGE_RING_TX_FBD_NUM_REG, - HCLGE_RING_TX_OFFSET_REG, - HCLGE_RING_TX_EBD_NUM_REG, - HCLGE_RING_TX_EBD_OFFSET_REG, - HCLGE_RING_TX_BD_ERR_REG, - HCLGE_RING_EN_REG}; - -static const u32 tqp_intr_reg_addr_list[] = {HCLGE_TQP_INTR_CTRL_REG, - HCLGE_TQP_INTR_GL0_REG, - HCLGE_TQP_INTR_GL1_REG, - HCLGE_TQP_INTR_GL2_REG, - HCLGE_TQP_INTR_RL_REG}; - static const char hns3_nic_test_strs[][ETH_GSTRING_LEN] = { "External Loopback test", "App Loopback test", @@ -375,36 +306,6 @@ static const struct hclge_mac_mgr_tbl_entry_cmd hclge_mgr_table[] = { }, }; -static const u32 hclge_dfx_bd_offset_list[] = { - HCLGE_DFX_BIOS_BD_OFFSET, - HCLGE_DFX_SSU_0_BD_OFFSET, - HCLGE_DFX_SSU_1_BD_OFFSET, - HCLGE_DFX_IGU_BD_OFFSET, - HCLGE_DFX_RPU_0_BD_OFFSET, - HCLGE_DFX_RPU_1_BD_OFFSET, - HCLGE_DFX_NCSI_BD_OFFSET, - HCLGE_DFX_RTC_BD_OFFSET, - HCLGE_DFX_PPP_BD_OFFSET, - HCLGE_DFX_RCB_BD_OFFSET, - HCLGE_DFX_TQP_BD_OFFSET, - HCLGE_DFX_SSU_2_BD_OFFSET -}; - -static const enum hclge_opcode_type hclge_dfx_reg_opcode_list[] = { - HCLGE_OPC_DFX_BIOS_COMMON_REG, - HCLGE_OPC_DFX_SSU_REG_0, - HCLGE_OPC_DFX_SSU_REG_1, - HCLGE_OPC_DFX_IGU_EGU_REG, - HCLGE_OPC_DFX_RPU_REG_0, - HCLGE_OPC_DFX_RPU_REG_1, - HCLGE_OPC_DFX_NCSI_REG, - HCLGE_OPC_DFX_RTC_REG, - HCLGE_OPC_DFX_PPP_REG, - HCLGE_OPC_DFX_RCB_REG, - HCLGE_OPC_DFX_TQP_REG, - HCLGE_OPC_DFX_SSU_REG_2 -}; - static const struct key_info meta_data_key_info[] = { { PACKET_TYPE_ID, 6 }, { IP_FRAGEMENT, 1 }, @@ -1425,6 +1326,7 @@ static void hclge_set_default_dev_specs(struct hclge_dev *hdev) ae_dev->dev_specs.max_frm_size = HCLGE_MAC_MAX_FRAME; ae_dev->dev_specs.max_qset_num = HCLGE_MAX_QSET_NUM; ae_dev->dev_specs.umv_size = HCLGE_DEFAULT_UMV_SPACE_PER_PF; + ae_dev->dev_specs.tnl_num = 0; } static void hclge_parse_dev_specs(struct hclge_dev *hdev, @@ -1448,6 +1350,7 @@ static void hclge_parse_dev_specs(struct hclge_dev *hdev, ae_dev->dev_specs.max_frm_size = le16_to_cpu(req1->max_frm_size); ae_dev->dev_specs.umv_size = le16_to_cpu(req1->umv_size); ae_dev->dev_specs.mc_mac_size = le16_to_cpu(req1->mc_mac_size); + ae_dev->dev_specs.tnl_num = req1->tnl_num; } static void hclge_check_dev_specs(struct hclge_dev *hdev) @@ -12383,463 +12286,6 @@ out: return ret; } -static int hclge_get_regs_num(struct hclge_dev *hdev, u32 *regs_num_32_bit, - u32 *regs_num_64_bit) -{ - struct hclge_desc desc; - u32 total_num; - int ret; - - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_REG_NUM, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) { - dev_err(&hdev->pdev->dev, - "Query register number cmd failed, ret = %d.\n", ret); - return ret; - } - - *regs_num_32_bit = le32_to_cpu(desc.data[0]); - *regs_num_64_bit = le32_to_cpu(desc.data[1]); - - total_num = *regs_num_32_bit + *regs_num_64_bit; - if (!total_num) - return -EINVAL; - - return 0; -} - -static int hclge_get_32_bit_regs(struct hclge_dev *hdev, u32 regs_num, - void *data) -{ -#define HCLGE_32_BIT_REG_RTN_DATANUM 8 -#define HCLGE_32_BIT_DESC_NODATA_LEN 2 - - struct hclge_desc *desc; - u32 *reg_val = data; - __le32 *desc_data; - int nodata_num; - int cmd_num; - int i, k, n; - int ret; - - if (regs_num == 0) - return 0; - - nodata_num = HCLGE_32_BIT_DESC_NODATA_LEN; - cmd_num = DIV_ROUND_UP(regs_num + nodata_num, - HCLGE_32_BIT_REG_RTN_DATANUM); - desc = kcalloc(cmd_num, sizeof(struct hclge_desc), GFP_KERNEL); - if (!desc) - return -ENOMEM; - - hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_32_BIT_REG, true); - ret = hclge_cmd_send(&hdev->hw, desc, cmd_num); - if (ret) { - dev_err(&hdev->pdev->dev, - "Query 32 bit register cmd failed, ret = %d.\n", ret); - kfree(desc); - return ret; - } - - for (i = 0; i < cmd_num; i++) { - if (i == 0) { - desc_data = (__le32 *)(&desc[i].data[0]); - n = HCLGE_32_BIT_REG_RTN_DATANUM - nodata_num; - } else { - desc_data = (__le32 *)(&desc[i]); - n = HCLGE_32_BIT_REG_RTN_DATANUM; - } - for (k = 0; k < n; k++) { - *reg_val++ = le32_to_cpu(*desc_data++); - - regs_num--; - if (!regs_num) - break; - } - } - - kfree(desc); - return 0; -} - -static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num, - void *data) -{ -#define HCLGE_64_BIT_REG_RTN_DATANUM 4 -#define HCLGE_64_BIT_DESC_NODATA_LEN 1 - - struct hclge_desc *desc; - u64 *reg_val = data; - __le64 *desc_data; - int nodata_len; - int cmd_num; - int i, k, n; - int ret; - - if (regs_num == 0) - return 0; - - nodata_len = HCLGE_64_BIT_DESC_NODATA_LEN; - cmd_num = DIV_ROUND_UP(regs_num + nodata_len, - HCLGE_64_BIT_REG_RTN_DATANUM); - desc = kcalloc(cmd_num, sizeof(struct hclge_desc), GFP_KERNEL); - if (!desc) - return -ENOMEM; - - hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_64_BIT_REG, true); - ret = hclge_cmd_send(&hdev->hw, desc, cmd_num); - if (ret) { - dev_err(&hdev->pdev->dev, - "Query 64 bit register cmd failed, ret = %d.\n", ret); - kfree(desc); - return ret; - } - - for (i = 0; i < cmd_num; i++) { - if (i == 0) { - desc_data = (__le64 *)(&desc[i].data[0]); - n = HCLGE_64_BIT_REG_RTN_DATANUM - nodata_len; - } else { - desc_data = (__le64 *)(&desc[i]); - n = HCLGE_64_BIT_REG_RTN_DATANUM; - } - for (k = 0; k < n; k++) { - *reg_val++ = le64_to_cpu(*desc_data++); - - regs_num--; - if (!regs_num) - break; - } - } - - kfree(desc); - return 0; -} - -#define MAX_SEPARATE_NUM 4 -#define SEPARATOR_VALUE 0xFDFCFBFA -#define REG_NUM_PER_LINE 4 -#define REG_LEN_PER_LINE (REG_NUM_PER_LINE * sizeof(u32)) -#define REG_SEPARATOR_LINE 1 -#define REG_NUM_REMAIN_MASK 3 - -int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc) -{ - int i; - - /* initialize command BD except the last one */ - for (i = 0; i < HCLGE_GET_DFX_REG_TYPE_CNT - 1; i++) { - hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_DFX_BD_NUM, - true); - desc[i].flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_NEXT); - } - - /* initialize the last command BD */ - hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_DFX_BD_NUM, true); - - return hclge_cmd_send(&hdev->hw, desc, HCLGE_GET_DFX_REG_TYPE_CNT); -} - -static int hclge_get_dfx_reg_bd_num(struct hclge_dev *hdev, - int *bd_num_list, - u32 type_num) -{ - u32 entries_per_desc, desc_index, index, offset, i; - struct hclge_desc desc[HCLGE_GET_DFX_REG_TYPE_CNT]; - int ret; - - ret = hclge_query_bd_num_cmd_send(hdev, desc); - if (ret) { - dev_err(&hdev->pdev->dev, - "Get dfx bd num fail, status is %d.\n", ret); - return ret; - } - - entries_per_desc = ARRAY_SIZE(desc[0].data); - for (i = 0; i < type_num; i++) { - offset = hclge_dfx_bd_offset_list[i]; - index = offset % entries_per_desc; - desc_index = offset / entries_per_desc; - bd_num_list[i] = le32_to_cpu(desc[desc_index].data[index]); - } - - return ret; -} - -static int hclge_dfx_reg_cmd_send(struct hclge_dev *hdev, - struct hclge_desc *desc_src, int bd_num, - enum hclge_opcode_type cmd) -{ - struct hclge_desc *desc = desc_src; - int i, ret; - - hclge_cmd_setup_basic_desc(desc, cmd, true); - for (i = 0; i < bd_num - 1; i++) { - desc->flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_NEXT); - desc++; - hclge_cmd_setup_basic_desc(desc, cmd, true); - } - - desc = desc_src; - ret = hclge_cmd_send(&hdev->hw, desc, bd_num); - if (ret) - dev_err(&hdev->pdev->dev, - "Query dfx reg cmd(0x%x) send fail, status is %d.\n", - cmd, ret); - - return ret; -} - -static int hclge_dfx_reg_fetch_data(struct hclge_desc *desc_src, int bd_num, - void *data) -{ - int entries_per_desc, reg_num, separator_num, desc_index, index, i; - struct hclge_desc *desc = desc_src; - u32 *reg = data; - - entries_per_desc = ARRAY_SIZE(desc->data); - reg_num = entries_per_desc * bd_num; - separator_num = REG_NUM_PER_LINE - (reg_num & REG_NUM_REMAIN_MASK); - for (i = 0; i < reg_num; i++) { - index = i % entries_per_desc; - desc_index = i / entries_per_desc; - *reg++ = le32_to_cpu(desc[desc_index].data[index]); - } - for (i = 0; i < separator_num; i++) - *reg++ = SEPARATOR_VALUE; - - return reg_num + separator_num; -} - -static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len) -{ - u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list); - int data_len_per_desc, bd_num, i; - int *bd_num_list; - u32 data_len; - int ret; - - bd_num_list = kcalloc(dfx_reg_type_num, sizeof(int), GFP_KERNEL); - if (!bd_num_list) - return -ENOMEM; - - ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num); - if (ret) { - dev_err(&hdev->pdev->dev, - "Get dfx reg bd num fail, status is %d.\n", ret); - goto out; - } - - data_len_per_desc = sizeof_field(struct hclge_desc, data); - *len = 0; - for (i = 0; i < dfx_reg_type_num; i++) { - bd_num = bd_num_list[i]; - data_len = data_len_per_desc * bd_num; - *len += (data_len / REG_LEN_PER_LINE + 1) * REG_LEN_PER_LINE; - } - -out: - kfree(bd_num_list); - return ret; -} - -static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data) -{ - u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list); - int bd_num, bd_num_max, buf_len, i; - struct hclge_desc *desc_src; - int *bd_num_list; - u32 *reg = data; - int ret; - - bd_num_list = kcalloc(dfx_reg_type_num, sizeof(int), GFP_KERNEL); - if (!bd_num_list) - return -ENOMEM; - - ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num); - if (ret) { - dev_err(&hdev->pdev->dev, - "Get dfx reg bd num fail, status is %d.\n", ret); - goto out; - } - - bd_num_max = bd_num_list[0]; - for (i = 1; i < dfx_reg_type_num; i++) - bd_num_max = max_t(int, bd_num_max, bd_num_list[i]); - - buf_len = sizeof(*desc_src) * bd_num_max; - desc_src = kzalloc(buf_len, GFP_KERNEL); - if (!desc_src) { - ret = -ENOMEM; - goto out; - } - - for (i = 0; i < dfx_reg_type_num; i++) { - bd_num = bd_num_list[i]; - ret = hclge_dfx_reg_cmd_send(hdev, desc_src, bd_num, - hclge_dfx_reg_opcode_list[i]); - if (ret) { - dev_err(&hdev->pdev->dev, - "Get dfx reg fail, status is %d.\n", ret); - break; - } - - reg += hclge_dfx_reg_fetch_data(desc_src, bd_num, reg); - } - - kfree(desc_src); -out: - kfree(bd_num_list); - return ret; -} - -static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data, - struct hnae3_knic_private_info *kinfo) -{ -#define HCLGE_RING_REG_OFFSET 0x200 -#define HCLGE_RING_INT_REG_OFFSET 0x4 - - int i, j, reg_num, separator_num; - int data_num_sum; - u32 *reg = data; - - /* fetching per-PF registers valus from PF PCIe register space */ - reg_num = ARRAY_SIZE(cmdq_reg_addr_list); - separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); - for (i = 0; i < reg_num; i++) - *reg++ = hclge_read_dev(&hdev->hw, cmdq_reg_addr_list[i]); - for (i = 0; i < separator_num; i++) - *reg++ = SEPARATOR_VALUE; - data_num_sum = reg_num + separator_num; - - reg_num = ARRAY_SIZE(common_reg_addr_list); - separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); - for (i = 0; i < reg_num; i++) - *reg++ = hclge_read_dev(&hdev->hw, common_reg_addr_list[i]); - for (i = 0; i < separator_num; i++) - *reg++ = SEPARATOR_VALUE; - data_num_sum += reg_num + separator_num; - - reg_num = ARRAY_SIZE(ring_reg_addr_list); - separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); - for (j = 0; j < kinfo->num_tqps; j++) { - for (i = 0; i < reg_num; i++) - *reg++ = hclge_read_dev(&hdev->hw, - ring_reg_addr_list[i] + - HCLGE_RING_REG_OFFSET * j); - for (i = 0; i < separator_num; i++) - *reg++ = SEPARATOR_VALUE; - } - data_num_sum += (reg_num + separator_num) * kinfo->num_tqps; - - reg_num = ARRAY_SIZE(tqp_intr_reg_addr_list); - separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); - for (j = 0; j < hdev->num_msi_used - 1; j++) { - for (i = 0; i < reg_num; i++) - *reg++ = hclge_read_dev(&hdev->hw, - tqp_intr_reg_addr_list[i] + - HCLGE_RING_INT_REG_OFFSET * j); - for (i = 0; i < separator_num; i++) - *reg++ = SEPARATOR_VALUE; - } - data_num_sum += (reg_num + separator_num) * (hdev->num_msi_used - 1); - - return data_num_sum; -} - -static int hclge_get_regs_len(struct hnae3_handle *handle) -{ - int cmdq_lines, common_lines, ring_lines, tqp_intr_lines; - struct hnae3_knic_private_info *kinfo = &handle->kinfo; - struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_dev *hdev = vport->back; - int regs_num_32_bit, regs_num_64_bit, dfx_regs_len; - int regs_lines_32_bit, regs_lines_64_bit; - int ret; - - ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); - if (ret) { - dev_err(&hdev->pdev->dev, - "Get register number failed, ret = %d.\n", ret); - return ret; - } - - ret = hclge_get_dfx_reg_len(hdev, &dfx_regs_len); - if (ret) { - dev_err(&hdev->pdev->dev, - "Get dfx reg len failed, ret = %d.\n", ret); - return ret; - } - - cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + - REG_SEPARATOR_LINE; - common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + - REG_SEPARATOR_LINE; - ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + - REG_SEPARATOR_LINE; - tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + - REG_SEPARATOR_LINE; - regs_lines_32_bit = regs_num_32_bit * sizeof(u32) / REG_LEN_PER_LINE + - REG_SEPARATOR_LINE; - regs_lines_64_bit = regs_num_64_bit * sizeof(u64) / REG_LEN_PER_LINE + - REG_SEPARATOR_LINE; - - return (cmdq_lines + common_lines + ring_lines * kinfo->num_tqps + - tqp_intr_lines * (hdev->num_msi_used - 1) + regs_lines_32_bit + - regs_lines_64_bit) * REG_LEN_PER_LINE + dfx_regs_len; -} - -static void hclge_get_regs(struct hnae3_handle *handle, u32 *version, - void *data) -{ - struct hnae3_knic_private_info *kinfo = &handle->kinfo; - struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_dev *hdev = vport->back; - u32 regs_num_32_bit, regs_num_64_bit; - int i, reg_num, separator_num, ret; - u32 *reg = data; - - *version = hdev->fw_version; - - ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); - if (ret) { - dev_err(&hdev->pdev->dev, - "Get register number failed, ret = %d.\n", ret); - return; - } - - reg += hclge_fetch_pf_reg(hdev, reg, kinfo); - - ret = hclge_get_32_bit_regs(hdev, regs_num_32_bit, reg); - if (ret) { - dev_err(&hdev->pdev->dev, - "Get 32 bit register failed, ret = %d.\n", ret); - return; - } - reg_num = regs_num_32_bit; - reg += reg_num; - separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); - for (i = 0; i < separator_num; i++) - *reg++ = SEPARATOR_VALUE; - - ret = hclge_get_64_bit_regs(hdev, regs_num_64_bit, reg); - if (ret) { - dev_err(&hdev->pdev->dev, - "Get 64 bit register failed, ret = %d.\n", ret); - return; - } - reg_num = regs_num_64_bit * 2; - reg += reg_num; - separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); - for (i = 0; i < separator_num; i++) - *reg++ = SEPARATOR_VALUE; - - ret = hclge_get_dfx_reg(hdev, reg); - if (ret) - dev_err(&hdev->pdev->dev, - "Get dfx register failed, ret = %d.\n", ret); -} - static int hclge_set_led_status(struct hclge_dev *hdev, u8 locate_led_status) { struct hclge_set_led_state_cmd *req; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 70b059e6d35f..ec233ec57222 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -1142,8 +1142,6 @@ int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid, u16 state, struct hclge_vlan_info *vlan_info); void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time); -int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, - struct hclge_desc *desc); void hclge_report_hw_error(struct hclge_dev *hdev, enum hnae3_hw_error_type type); int hclge_dbg_dump_rst_info(struct hclge_dev *hdev, char *buf, int len); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c new file mode 100644 index 000000000000..43c1c18fa81f --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c @@ -0,0 +1,668 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright (c) 2023 Hisilicon Limited. + +#include "hclge_cmd.h" +#include "hclge_main.h" +#include "hclge_regs.h" +#include "hnae3.h" + +static const u32 cmdq_reg_addr_list[] = {HCLGE_COMM_NIC_CSQ_BASEADDR_L_REG, + HCLGE_COMM_NIC_CSQ_BASEADDR_H_REG, + HCLGE_COMM_NIC_CSQ_DEPTH_REG, + HCLGE_COMM_NIC_CSQ_TAIL_REG, + HCLGE_COMM_NIC_CSQ_HEAD_REG, + HCLGE_COMM_NIC_CRQ_BASEADDR_L_REG, + HCLGE_COMM_NIC_CRQ_BASEADDR_H_REG, + HCLGE_COMM_NIC_CRQ_DEPTH_REG, + HCLGE_COMM_NIC_CRQ_TAIL_REG, + HCLGE_COMM_NIC_CRQ_HEAD_REG, + HCLGE_COMM_VECTOR0_CMDQ_SRC_REG, + HCLGE_COMM_CMDQ_INTR_STS_REG, + HCLGE_COMM_CMDQ_INTR_EN_REG, + HCLGE_COMM_CMDQ_INTR_GEN_REG}; + +static const u32 common_reg_addr_list[] = {HCLGE_MISC_VECTOR_REG_BASE, + HCLGE_PF_OTHER_INT_REG, + HCLGE_MISC_RESET_STS_REG, + HCLGE_MISC_VECTOR_INT_STS, + HCLGE_GLOBAL_RESET_REG, + HCLGE_FUN_RST_ING, + HCLGE_GRO_EN_REG}; + +static const u32 ring_reg_addr_list[] = {HCLGE_RING_RX_ADDR_L_REG, + HCLGE_RING_RX_ADDR_H_REG, + HCLGE_RING_RX_BD_NUM_REG, + HCLGE_RING_RX_BD_LENGTH_REG, + HCLGE_RING_RX_MERGE_EN_REG, + HCLGE_RING_RX_TAIL_REG, + HCLGE_RING_RX_HEAD_REG, + HCLGE_RING_RX_FBD_NUM_REG, + HCLGE_RING_RX_OFFSET_REG, + HCLGE_RING_RX_FBD_OFFSET_REG, + HCLGE_RING_RX_STASH_REG, + HCLGE_RING_RX_BD_ERR_REG, + HCLGE_RING_TX_ADDR_L_REG, + HCLGE_RING_TX_ADDR_H_REG, + HCLGE_RING_TX_BD_NUM_REG, + HCLGE_RING_TX_PRIORITY_REG, + HCLGE_RING_TX_TC_REG, + HCLGE_RING_TX_MERGE_EN_REG, + HCLGE_RING_TX_TAIL_REG, + HCLGE_RING_TX_HEAD_REG, + HCLGE_RING_TX_FBD_NUM_REG, + HCLGE_RING_TX_OFFSET_REG, + HCLGE_RING_TX_EBD_NUM_REG, + HCLGE_RING_TX_EBD_OFFSET_REG, + HCLGE_RING_TX_BD_ERR_REG, + HCLGE_RING_EN_REG}; + +static const u32 tqp_intr_reg_addr_list[] = {HCLGE_TQP_INTR_CTRL_REG, + HCLGE_TQP_INTR_GL0_REG, + HCLGE_TQP_INTR_GL1_REG, + HCLGE_TQP_INTR_GL2_REG, + HCLGE_TQP_INTR_RL_REG}; + +/* Get DFX BD number offset */ +#define HCLGE_DFX_BIOS_BD_OFFSET 1 +#define HCLGE_DFX_SSU_0_BD_OFFSET 2 +#define HCLGE_DFX_SSU_1_BD_OFFSET 3 +#define HCLGE_DFX_IGU_BD_OFFSET 4 +#define HCLGE_DFX_RPU_0_BD_OFFSET 5 +#define HCLGE_DFX_RPU_1_BD_OFFSET 6 +#define HCLGE_DFX_NCSI_BD_OFFSET 7 +#define HCLGE_DFX_RTC_BD_OFFSET 8 +#define HCLGE_DFX_PPP_BD_OFFSET 9 +#define HCLGE_DFX_RCB_BD_OFFSET 10 +#define HCLGE_DFX_TQP_BD_OFFSET 11 +#define HCLGE_DFX_SSU_2_BD_OFFSET 12 + +static const u32 hclge_dfx_bd_offset_list[] = { + HCLGE_DFX_BIOS_BD_OFFSET, + HCLGE_DFX_SSU_0_BD_OFFSET, + HCLGE_DFX_SSU_1_BD_OFFSET, + HCLGE_DFX_IGU_BD_OFFSET, + HCLGE_DFX_RPU_0_BD_OFFSET, + HCLGE_DFX_RPU_1_BD_OFFSET, + HCLGE_DFX_NCSI_BD_OFFSET, + HCLGE_DFX_RTC_BD_OFFSET, + HCLGE_DFX_PPP_BD_OFFSET, + HCLGE_DFX_RCB_BD_OFFSET, + HCLGE_DFX_TQP_BD_OFFSET, + HCLGE_DFX_SSU_2_BD_OFFSET +}; + +static const enum hclge_opcode_type hclge_dfx_reg_opcode_list[] = { + HCLGE_OPC_DFX_BIOS_COMMON_REG, + HCLGE_OPC_DFX_SSU_REG_0, + HCLGE_OPC_DFX_SSU_REG_1, + HCLGE_OPC_DFX_IGU_EGU_REG, + HCLGE_OPC_DFX_RPU_REG_0, + HCLGE_OPC_DFX_RPU_REG_1, + HCLGE_OPC_DFX_NCSI_REG, + HCLGE_OPC_DFX_RTC_REG, + HCLGE_OPC_DFX_PPP_REG, + HCLGE_OPC_DFX_RCB_REG, + HCLGE_OPC_DFX_TQP_REG, + HCLGE_OPC_DFX_SSU_REG_2 +}; + +enum hclge_reg_tag { + HCLGE_REG_TAG_CMDQ = 0, + HCLGE_REG_TAG_COMMON, + HCLGE_REG_TAG_RING, + HCLGE_REG_TAG_TQP_INTR, + HCLGE_REG_TAG_QUERY_32_BIT, + HCLGE_REG_TAG_QUERY_64_BIT, + HCLGE_REG_TAG_DFX_BIOS_COMMON, + HCLGE_REG_TAG_DFX_SSU_0, + HCLGE_REG_TAG_DFX_SSU_1, + HCLGE_REG_TAG_DFX_IGU_EGU, + HCLGE_REG_TAG_DFX_RPU_0, + HCLGE_REG_TAG_DFX_RPU_1, + HCLGE_REG_TAG_DFX_NCSI, + HCLGE_REG_TAG_DFX_RTC, + HCLGE_REG_TAG_DFX_PPP, + HCLGE_REG_TAG_DFX_RCB, + HCLGE_REG_TAG_DFX_TQP, + HCLGE_REG_TAG_DFX_SSU_2, + HCLGE_REG_TAG_RPU_TNL, +}; + +#pragma pack(4) +struct hclge_reg_tlv { + u16 tag; + u16 len; +}; + +struct hclge_reg_header { + u64 magic_number; + u8 is_vf; + u8 rsv[7]; +}; + +#pragma pack() + +#define HCLGE_REG_TLV_SIZE sizeof(struct hclge_reg_tlv) +#define HCLGE_REG_HEADER_SIZE sizeof(struct hclge_reg_header) +#define HCLGE_REG_TLV_SPACE (sizeof(struct hclge_reg_tlv) / sizeof(u32)) +#define HCLGE_REG_HEADER_SPACE (sizeof(struct hclge_reg_header) / sizeof(u32)) +#define HCLGE_REG_MAGIC_NUMBER 0x686e733372656773 /* meaning is hns3regs */ + +#define HCLGE_REG_RPU_TNL_ID_0 1 + +static u32 hclge_reg_get_header(void *data) +{ + struct hclge_reg_header *header = data; + + header->magic_number = HCLGE_REG_MAGIC_NUMBER; + header->is_vf = 0x0; + + return HCLGE_REG_HEADER_SPACE; +} + +static u32 hclge_reg_get_tlv(u32 tag, u32 regs_num, void *data) +{ + struct hclge_reg_tlv *tlv = data; + + tlv->tag = tag; + tlv->len = regs_num * sizeof(u32) + HCLGE_REG_TLV_SIZE; + + return HCLGE_REG_TLV_SPACE; +} + +static int hclge_get_32_bit_regs(struct hclge_dev *hdev, u32 regs_num, + void *data) +{ +#define HCLGE_32_BIT_REG_RTN_DATANUM 8 +#define HCLGE_32_BIT_DESC_NODATA_LEN 2 + + struct hclge_desc *desc; + u32 *reg_val = data; + __le32 *desc_data; + int nodata_num; + int cmd_num; + int i, k, n; + int ret; + + if (regs_num == 0) + return 0; + + nodata_num = HCLGE_32_BIT_DESC_NODATA_LEN; + cmd_num = DIV_ROUND_UP(regs_num + nodata_num, + HCLGE_32_BIT_REG_RTN_DATANUM); + desc = kcalloc(cmd_num, sizeof(struct hclge_desc), GFP_KERNEL); + if (!desc) + return -ENOMEM; + + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_32_BIT_REG, true); + ret = hclge_cmd_send(&hdev->hw, desc, cmd_num); + if (ret) { + dev_err(&hdev->pdev->dev, + "Query 32 bit register cmd failed, ret = %d.\n", ret); + kfree(desc); + return ret; + } + + for (i = 0; i < cmd_num; i++) { + if (i == 0) { + desc_data = (__le32 *)(&desc[i].data[0]); + n = HCLGE_32_BIT_REG_RTN_DATANUM - nodata_num; + } else { + desc_data = (__le32 *)(&desc[i]); + n = HCLGE_32_BIT_REG_RTN_DATANUM; + } + for (k = 0; k < n; k++) { + *reg_val++ = le32_to_cpu(*desc_data++); + + regs_num--; + if (!regs_num) + break; + } + } + + kfree(desc); + return 0; +} + +static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num, + void *data) +{ +#define HCLGE_64_BIT_REG_RTN_DATANUM 4 +#define HCLGE_64_BIT_DESC_NODATA_LEN 1 + + struct hclge_desc *desc; + u64 *reg_val = data; + __le64 *desc_data; + int nodata_len; + int cmd_num; + int i, k, n; + int ret; + + if (regs_num == 0) + return 0; + + nodata_len = HCLGE_64_BIT_DESC_NODATA_LEN; + cmd_num = DIV_ROUND_UP(regs_num + nodata_len, + HCLGE_64_BIT_REG_RTN_DATANUM); + desc = kcalloc(cmd_num, sizeof(struct hclge_desc), GFP_KERNEL); + if (!desc) + return -ENOMEM; + + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_64_BIT_REG, true); + ret = hclge_cmd_send(&hdev->hw, desc, cmd_num); + if (ret) { + dev_err(&hdev->pdev->dev, + "Query 64 bit register cmd failed, ret = %d.\n", ret); + kfree(desc); + return ret; + } + + for (i = 0; i < cmd_num; i++) { + if (i == 0) { + desc_data = (__le64 *)(&desc[i].data[0]); + n = HCLGE_64_BIT_REG_RTN_DATANUM - nodata_len; + } else { + desc_data = (__le64 *)(&desc[i]); + n = HCLGE_64_BIT_REG_RTN_DATANUM; + } + for (k = 0; k < n; k++) { + *reg_val++ = le64_to_cpu(*desc_data++); + + regs_num--; + if (!regs_num) + break; + } + } + + kfree(desc); + return 0; +} + +int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc) +{ + int i; + + /* initialize command BD except the last one */ + for (i = 0; i < HCLGE_GET_DFX_REG_TYPE_CNT - 1; i++) { + hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_DFX_BD_NUM, + true); + desc[i].flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_NEXT); + } + + /* initialize the last command BD */ + hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_DFX_BD_NUM, true); + + return hclge_cmd_send(&hdev->hw, desc, HCLGE_GET_DFX_REG_TYPE_CNT); +} + +static int hclge_get_dfx_reg_bd_num(struct hclge_dev *hdev, + int *bd_num_list, + u32 type_num) +{ + u32 entries_per_desc, desc_index, index, offset, i; + struct hclge_desc desc[HCLGE_GET_DFX_REG_TYPE_CNT]; + int ret; + + ret = hclge_query_bd_num_cmd_send(hdev, desc); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get dfx bd num fail, status is %d.\n", ret); + return ret; + } + + entries_per_desc = ARRAY_SIZE(desc[0].data); + for (i = 0; i < type_num; i++) { + offset = hclge_dfx_bd_offset_list[i]; + index = offset % entries_per_desc; + desc_index = offset / entries_per_desc; + bd_num_list[i] = le32_to_cpu(desc[desc_index].data[index]); + } + + return ret; +} + +static int hclge_dfx_reg_cmd_send(struct hclge_dev *hdev, + struct hclge_desc *desc_src, int bd_num, + enum hclge_opcode_type cmd) +{ + struct hclge_desc *desc = desc_src; + int i, ret; + + hclge_cmd_setup_basic_desc(desc, cmd, true); + for (i = 0; i < bd_num - 1; i++) { + desc->flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_NEXT); + desc++; + hclge_cmd_setup_basic_desc(desc, cmd, true); + } + + desc = desc_src; + ret = hclge_cmd_send(&hdev->hw, desc, bd_num); + if (ret) + dev_err(&hdev->pdev->dev, + "Query dfx reg cmd(0x%x) send fail, status is %d.\n", + cmd, ret); + + return ret; +} + +/* tnl_id = 0 means get sum of all tnl reg's value */ +static int hclge_dfx_reg_rpu_tnl_cmd_send(struct hclge_dev *hdev, u32 tnl_id, + struct hclge_desc *desc, int bd_num) +{ + int i, ret; + + for (i = 0; i < bd_num; i++) { + hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_DFX_RPU_REG_0, + true); + if (i != bd_num - 1) + desc[i].flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_NEXT); + } + + desc[0].data[0] = cpu_to_le32(tnl_id); + ret = hclge_cmd_send(&hdev->hw, desc, bd_num); + if (ret) + dev_err(&hdev->pdev->dev, + "failed to query dfx rpu tnl reg, ret = %d\n", + ret); + return ret; +} + +static int hclge_dfx_reg_fetch_data(struct hclge_desc *desc_src, int bd_num, + void *data) +{ + int entries_per_desc, reg_num, desc_index, index, i; + struct hclge_desc *desc = desc_src; + u32 *reg = data; + + entries_per_desc = ARRAY_SIZE(desc->data); + reg_num = entries_per_desc * bd_num; + for (i = 0; i < reg_num; i++) { + index = i % entries_per_desc; + desc_index = i / entries_per_desc; + *reg++ = le32_to_cpu(desc[desc_index].data[index]); + } + + return reg_num; +} + +static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len) +{ + u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list); + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); + int data_len_per_desc; + int *bd_num_list; + int ret; + u32 i; + + bd_num_list = kcalloc(dfx_reg_type_num, sizeof(int), GFP_KERNEL); + if (!bd_num_list) + return -ENOMEM; + + ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get dfx reg bd num fail, status is %d.\n", ret); + goto out; + } + + data_len_per_desc = sizeof_field(struct hclge_desc, data); + *len = 0; + for (i = 0; i < dfx_reg_type_num; i++) + *len += bd_num_list[i] * data_len_per_desc + HCLGE_REG_TLV_SIZE; + + /** + * the num of dfx_rpu_0 is reused by each dfx_rpu_tnl + * HCLGE_DFX_BD_OFFSET is starting at 1, but the array subscript is + * starting at 0, so offset need '- 1'. + */ + *len += (bd_num_list[HCLGE_DFX_RPU_0_BD_OFFSET - 1] * data_len_per_desc + + HCLGE_REG_TLV_SIZE) * ae_dev->dev_specs.tnl_num; + +out: + kfree(bd_num_list); + return ret; +} + +static int hclge_get_dfx_rpu_tnl_reg(struct hclge_dev *hdev, u32 *reg, + struct hclge_desc *desc_src, + int bd_num) +{ + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); + int ret = 0; + u8 i; + + for (i = HCLGE_REG_RPU_TNL_ID_0; i <= ae_dev->dev_specs.tnl_num; i++) { + ret = hclge_dfx_reg_rpu_tnl_cmd_send(hdev, i, desc_src, bd_num); + if (ret) + break; + + reg += hclge_reg_get_tlv(HCLGE_REG_TAG_RPU_TNL, + ARRAY_SIZE(desc_src->data) * bd_num, + reg); + reg += hclge_dfx_reg_fetch_data(desc_src, bd_num, reg); + } + + return ret; +} + +static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data) +{ + u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list); + int bd_num, bd_num_max, buf_len; + struct hclge_desc *desc_src; + int *bd_num_list; + u32 *reg = data; + int ret; + u32 i; + + bd_num_list = kcalloc(dfx_reg_type_num, sizeof(int), GFP_KERNEL); + if (!bd_num_list) + return -ENOMEM; + + ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get dfx reg bd num fail, status is %d.\n", ret); + goto out; + } + + bd_num_max = bd_num_list[0]; + for (i = 1; i < dfx_reg_type_num; i++) + bd_num_max = max_t(int, bd_num_max, bd_num_list[i]); + + buf_len = sizeof(*desc_src) * bd_num_max; + desc_src = kzalloc(buf_len, GFP_KERNEL); + if (!desc_src) { + ret = -ENOMEM; + goto out; + } + + for (i = 0; i < dfx_reg_type_num; i++) { + bd_num = bd_num_list[i]; + ret = hclge_dfx_reg_cmd_send(hdev, desc_src, bd_num, + hclge_dfx_reg_opcode_list[i]); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get dfx reg fail, status is %d.\n", ret); + goto free; + } + + reg += hclge_reg_get_tlv(HCLGE_REG_TAG_DFX_BIOS_COMMON + i, + ARRAY_SIZE(desc_src->data) * bd_num, + reg); + reg += hclge_dfx_reg_fetch_data(desc_src, bd_num, reg); + } + + /** + * HCLGE_DFX_BD_OFFSET is starting at 1, but the array subscript is + * starting at 0, so offset need '- 1'. + */ + bd_num = bd_num_list[HCLGE_DFX_RPU_0_BD_OFFSET - 1]; + ret = hclge_get_dfx_rpu_tnl_reg(hdev, reg, desc_src, bd_num); + +free: + kfree(desc_src); +out: + kfree(bd_num_list); + return ret; +} + +static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data, + struct hnae3_knic_private_info *kinfo) +{ +#define HCLGE_RING_REG_OFFSET 0x200 +#define HCLGE_RING_INT_REG_OFFSET 0x4 + + int i, j, reg_num; + int data_num_sum; + u32 *reg = data; + + /* fetching per-PF registers valus from PF PCIe register space */ + reg_num = ARRAY_SIZE(cmdq_reg_addr_list); + reg += hclge_reg_get_tlv(HCLGE_REG_TAG_CMDQ, reg_num, reg); + for (i = 0; i < reg_num; i++) + *reg++ = hclge_read_dev(&hdev->hw, cmdq_reg_addr_list[i]); + data_num_sum = reg_num + HCLGE_REG_TLV_SPACE; + + reg_num = ARRAY_SIZE(common_reg_addr_list); + reg += hclge_reg_get_tlv(HCLGE_REG_TAG_COMMON, reg_num, reg); + for (i = 0; i < reg_num; i++) + *reg++ = hclge_read_dev(&hdev->hw, common_reg_addr_list[i]); + data_num_sum += reg_num + HCLGE_REG_TLV_SPACE; + + reg_num = ARRAY_SIZE(ring_reg_addr_list); + for (j = 0; j < kinfo->num_tqps; j++) { + reg += hclge_reg_get_tlv(HCLGE_REG_TAG_RING, reg_num, reg); + for (i = 0; i < reg_num; i++) + *reg++ = hclge_read_dev(&hdev->hw, + ring_reg_addr_list[i] + + HCLGE_RING_REG_OFFSET * j); + } + data_num_sum += (reg_num + HCLGE_REG_TLV_SPACE) * kinfo->num_tqps; + + reg_num = ARRAY_SIZE(tqp_intr_reg_addr_list); + for (j = 0; j < hdev->num_msi_used - 1; j++) { + reg += hclge_reg_get_tlv(HCLGE_REG_TAG_TQP_INTR, reg_num, reg); + for (i = 0; i < reg_num; i++) + *reg++ = hclge_read_dev(&hdev->hw, + tqp_intr_reg_addr_list[i] + + HCLGE_RING_INT_REG_OFFSET * j); + } + data_num_sum += (reg_num + HCLGE_REG_TLV_SPACE) * + (hdev->num_msi_used - 1); + + return data_num_sum; +} + +static int hclge_get_regs_num(struct hclge_dev *hdev, u32 *regs_num_32_bit, + u32 *regs_num_64_bit) +{ + struct hclge_desc desc; + u32 total_num; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_REG_NUM, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Query register number cmd failed, ret = %d.\n", ret); + return ret; + } + + *regs_num_32_bit = le32_to_cpu(desc.data[0]); + *regs_num_64_bit = le32_to_cpu(desc.data[1]); + + total_num = *regs_num_32_bit + *regs_num_64_bit; + if (!total_num) + return -EINVAL; + + return 0; +} + +int hclge_get_regs_len(struct hnae3_handle *handle) +{ + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + struct hclge_vport *vport = hclge_get_vport(handle); + int regs_num_32_bit, regs_num_64_bit, dfx_regs_len; + int cmdq_len, common_len, ring_len, tqp_intr_len; + int regs_len_32_bit, regs_len_64_bit; + struct hclge_dev *hdev = vport->back; + int ret; + + ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get register number failed, ret = %d.\n", ret); + return ret; + } + + ret = hclge_get_dfx_reg_len(hdev, &dfx_regs_len); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get dfx reg len failed, ret = %d.\n", ret); + return ret; + } + + cmdq_len = HCLGE_REG_TLV_SIZE + sizeof(cmdq_reg_addr_list); + common_len = HCLGE_REG_TLV_SIZE + sizeof(common_reg_addr_list); + ring_len = HCLGE_REG_TLV_SIZE + sizeof(ring_reg_addr_list); + tqp_intr_len = HCLGE_REG_TLV_SIZE + sizeof(tqp_intr_reg_addr_list); + regs_len_32_bit = HCLGE_REG_TLV_SIZE + regs_num_32_bit * sizeof(u32); + regs_len_64_bit = HCLGE_REG_TLV_SIZE + regs_num_64_bit * sizeof(u64); + + /* return the total length of all register values */ + return HCLGE_REG_HEADER_SIZE + cmdq_len + common_len + ring_len * + kinfo->num_tqps + tqp_intr_len * (hdev->num_msi_used - 1) + + regs_len_32_bit + regs_len_64_bit + dfx_regs_len; +} + +void hclge_get_regs(struct hnae3_handle *handle, u32 *version, + void *data) +{ +#define HCLGE_REG_64_BIT_SPACE_MULTIPLE 2 + + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + u32 regs_num_32_bit, regs_num_64_bit; + u32 *reg = data; + int ret; + + *version = hdev->fw_version; + + ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get register number failed, ret = %d.\n", ret); + return; + } + + reg += hclge_reg_get_header(reg); + reg += hclge_fetch_pf_reg(hdev, reg, kinfo); + + reg += hclge_reg_get_tlv(HCLGE_REG_TAG_QUERY_32_BIT, + regs_num_32_bit, reg); + ret = hclge_get_32_bit_regs(hdev, regs_num_32_bit, reg); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get 32 bit register failed, ret = %d.\n", ret); + return; + } + reg += regs_num_32_bit; + + reg += hclge_reg_get_tlv(HCLGE_REG_TAG_QUERY_64_BIT, + regs_num_64_bit * + HCLGE_REG_64_BIT_SPACE_MULTIPLE, reg); + ret = hclge_get_64_bit_regs(hdev, regs_num_64_bit, reg); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get 64 bit register failed, ret = %d.\n", ret); + return; + } + reg += regs_num_64_bit * HCLGE_REG_64_BIT_SPACE_MULTIPLE; + + ret = hclge_get_dfx_reg(hdev, reg); + if (ret) + dev_err(&hdev->pdev->dev, + "Get dfx register failed, ret = %d.\n", ret); +} diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.h new file mode 100644 index 000000000000..b6bc1ecb8054 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +// Copyright (c) 2023 Hisilicon Limited. + +#ifndef __HCLGE_REGS_H +#define __HCLGE_REGS_H +#include <linux/types.h> +#include "hclge_comm_cmd.h" + +struct hnae3_handle; +struct hclge_dev; + +int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, + struct hclge_desc *desc); +int hclge_get_regs_len(struct hnae3_handle *handle); +void hclge_get_regs(struct hnae3_handle *handle, u32 *version, + void *data); +#endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 34f02ca8d1d2..7a2f9233d695 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -6,6 +6,7 @@ #include <net/rtnetlink.h> #include "hclgevf_cmd.h" #include "hclgevf_main.h" +#include "hclgevf_regs.h" #include "hclge_mbx.h" #include "hnae3.h" #include "hclgevf_devlink.h" @@ -33,58 +34,6 @@ static const struct pci_device_id ae_algovf_pci_tbl[] = { MODULE_DEVICE_TABLE(pci, ae_algovf_pci_tbl); -static const u32 cmdq_reg_addr_list[] = {HCLGE_COMM_NIC_CSQ_BASEADDR_L_REG, - HCLGE_COMM_NIC_CSQ_BASEADDR_H_REG, - HCLGE_COMM_NIC_CSQ_DEPTH_REG, - HCLGE_COMM_NIC_CSQ_TAIL_REG, - HCLGE_COMM_NIC_CSQ_HEAD_REG, - HCLGE_COMM_NIC_CRQ_BASEADDR_L_REG, - HCLGE_COMM_NIC_CRQ_BASEADDR_H_REG, - HCLGE_COMM_NIC_CRQ_DEPTH_REG, - HCLGE_COMM_NIC_CRQ_TAIL_REG, - HCLGE_COMM_NIC_CRQ_HEAD_REG, - HCLGE_COMM_VECTOR0_CMDQ_SRC_REG, - HCLGE_COMM_VECTOR0_CMDQ_STATE_REG, - HCLGE_COMM_CMDQ_INTR_EN_REG, - HCLGE_COMM_CMDQ_INTR_GEN_REG}; - -static const u32 common_reg_addr_list[] = {HCLGEVF_MISC_VECTOR_REG_BASE, - HCLGEVF_RST_ING, - HCLGEVF_GRO_EN_REG}; - -static const u32 ring_reg_addr_list[] = {HCLGEVF_RING_RX_ADDR_L_REG, - HCLGEVF_RING_RX_ADDR_H_REG, - HCLGEVF_RING_RX_BD_NUM_REG, - HCLGEVF_RING_RX_BD_LENGTH_REG, - HCLGEVF_RING_RX_MERGE_EN_REG, - HCLGEVF_RING_RX_TAIL_REG, - HCLGEVF_RING_RX_HEAD_REG, - HCLGEVF_RING_RX_FBD_NUM_REG, - HCLGEVF_RING_RX_OFFSET_REG, - HCLGEVF_RING_RX_FBD_OFFSET_REG, - HCLGEVF_RING_RX_STASH_REG, - HCLGEVF_RING_RX_BD_ERR_REG, - HCLGEVF_RING_TX_ADDR_L_REG, - HCLGEVF_RING_TX_ADDR_H_REG, - HCLGEVF_RING_TX_BD_NUM_REG, - HCLGEVF_RING_TX_PRIORITY_REG, - HCLGEVF_RING_TX_TC_REG, - HCLGEVF_RING_TX_MERGE_EN_REG, - HCLGEVF_RING_TX_TAIL_REG, - HCLGEVF_RING_TX_HEAD_REG, - HCLGEVF_RING_TX_FBD_NUM_REG, - HCLGEVF_RING_TX_OFFSET_REG, - HCLGEVF_RING_TX_EBD_NUM_REG, - HCLGEVF_RING_TX_EBD_OFFSET_REG, - HCLGEVF_RING_TX_BD_ERR_REG, - HCLGEVF_RING_EN_REG}; - -static const u32 tqp_intr_reg_addr_list[] = {HCLGEVF_TQP_INTR_CTRL_REG, - HCLGEVF_TQP_INTR_GL0_REG, - HCLGEVF_TQP_INTR_GL1_REG, - HCLGEVF_TQP_INTR_GL2_REG, - HCLGEVF_TQP_INTR_RL_REG}; - /* hclgevf_cmd_send - send command to command queue * @hw: pointer to the hw struct * @desc: prefilled descriptor for describing the command @@ -111,7 +60,7 @@ void hclgevf_arq_init(struct hclgevf_dev *hdev) spin_unlock(&cmdq->crq.lock); } -static struct hclgevf_dev *hclgevf_ae_get_hdev(struct hnae3_handle *handle) +struct hclgevf_dev *hclgevf_ae_get_hdev(struct hnae3_handle *handle) { if (!handle->client) return container_of(handle, struct hclgevf_dev, nic); @@ -3258,72 +3207,6 @@ static void hclgevf_get_link_mode(struct hnae3_handle *handle, *advertising = hdev->hw.mac.advertising; } -#define MAX_SEPARATE_NUM 4 -#define SEPARATOR_VALUE 0xFDFCFBFA -#define REG_NUM_PER_LINE 4 -#define REG_LEN_PER_LINE (REG_NUM_PER_LINE * sizeof(u32)) - -static int hclgevf_get_regs_len(struct hnae3_handle *handle) -{ - int cmdq_lines, common_lines, ring_lines, tqp_intr_lines; - struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); - - cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + 1; - common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + 1; - ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + 1; - tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + 1; - - return (cmdq_lines + common_lines + ring_lines * hdev->num_tqps + - tqp_intr_lines * (hdev->num_msi_used - 1)) * REG_LEN_PER_LINE; -} - -static void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version, - void *data) -{ - struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); - int i, j, reg_um, separator_num; - u32 *reg = data; - - *version = hdev->fw_version; - - /* fetching per-VF registers values from VF PCIe register space */ - reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; - for (i = 0; i < reg_um; i++) - *reg++ = hclgevf_read_dev(&hdev->hw, cmdq_reg_addr_list[i]); - for (i = 0; i < separator_num; i++) - *reg++ = SEPARATOR_VALUE; - - reg_um = sizeof(common_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; - for (i = 0; i < reg_um; i++) - *reg++ = hclgevf_read_dev(&hdev->hw, common_reg_addr_list[i]); - for (i = 0; i < separator_num; i++) - *reg++ = SEPARATOR_VALUE; - - reg_um = sizeof(ring_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; - for (j = 0; j < hdev->num_tqps; j++) { - for (i = 0; i < reg_um; i++) - *reg++ = hclgevf_read_dev(&hdev->hw, - ring_reg_addr_list[i] + - HCLGEVF_TQP_REG_SIZE * j); - for (i = 0; i < separator_num; i++) - *reg++ = SEPARATOR_VALUE; - } - - reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; - for (j = 0; j < hdev->num_msi_used - 1; j++) { - for (i = 0; i < reg_um; i++) - *reg++ = hclgevf_read_dev(&hdev->hw, - tqp_intr_reg_addr_list[i] + - 4 * j); - for (i = 0; i < separator_num; i++) - *reg++ = SEPARATOR_VALUE; - } -} - void hclgevf_update_port_base_vlan_info(struct hclgevf_dev *hdev, u16 state, struct hclge_mbx_port_base_vlan *port_base_vlan) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 59ca6c794d6d..81c16b8c8da2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -294,4 +294,5 @@ void hclgevf_reset_task_schedule(struct hclgevf_dev *hdev); void hclgevf_mbx_task_schedule(struct hclgevf_dev *hdev); void hclgevf_update_port_base_vlan_info(struct hclgevf_dev *hdev, u16 state, struct hclge_mbx_port_base_vlan *port_base_vlan); +struct hclgevf_dev *hclgevf_ae_get_hdev(struct hnae3_handle *handle); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c new file mode 100644 index 000000000000..65b9dcd38137 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright (c) 2023 Hisilicon Limited. + +#include "hclgevf_main.h" +#include "hclgevf_regs.h" +#include "hnae3.h" + +static const u32 cmdq_reg_addr_list[] = {HCLGE_COMM_NIC_CSQ_BASEADDR_L_REG, + HCLGE_COMM_NIC_CSQ_BASEADDR_H_REG, + HCLGE_COMM_NIC_CSQ_DEPTH_REG, + HCLGE_COMM_NIC_CSQ_TAIL_REG, + HCLGE_COMM_NIC_CSQ_HEAD_REG, + HCLGE_COMM_NIC_CRQ_BASEADDR_L_REG, + HCLGE_COMM_NIC_CRQ_BASEADDR_H_REG, + HCLGE_COMM_NIC_CRQ_DEPTH_REG, + HCLGE_COMM_NIC_CRQ_TAIL_REG, + HCLGE_COMM_NIC_CRQ_HEAD_REG, + HCLGE_COMM_VECTOR0_CMDQ_SRC_REG, + HCLGE_COMM_VECTOR0_CMDQ_STATE_REG, + HCLGE_COMM_CMDQ_INTR_EN_REG, + HCLGE_COMM_CMDQ_INTR_GEN_REG}; + +static const u32 common_reg_addr_list[] = {HCLGEVF_MISC_VECTOR_REG_BASE, + HCLGEVF_RST_ING, + HCLGEVF_GRO_EN_REG}; + +static const u32 ring_reg_addr_list[] = {HCLGEVF_RING_RX_ADDR_L_REG, + HCLGEVF_RING_RX_ADDR_H_REG, + HCLGEVF_RING_RX_BD_NUM_REG, + HCLGEVF_RING_RX_BD_LENGTH_REG, + HCLGEVF_RING_RX_MERGE_EN_REG, + HCLGEVF_RING_RX_TAIL_REG, + HCLGEVF_RING_RX_HEAD_REG, + HCLGEVF_RING_RX_FBD_NUM_REG, + HCLGEVF_RING_RX_OFFSET_REG, + HCLGEVF_RING_RX_FBD_OFFSET_REG, + HCLGEVF_RING_RX_STASH_REG, + HCLGEVF_RING_RX_BD_ERR_REG, + HCLGEVF_RING_TX_ADDR_L_REG, + HCLGEVF_RING_TX_ADDR_H_REG, + HCLGEVF_RING_TX_BD_NUM_REG, + HCLGEVF_RING_TX_PRIORITY_REG, + HCLGEVF_RING_TX_TC_REG, + HCLGEVF_RING_TX_MERGE_EN_REG, + HCLGEVF_RING_TX_TAIL_REG, + HCLGEVF_RING_TX_HEAD_REG, + HCLGEVF_RING_TX_FBD_NUM_REG, + HCLGEVF_RING_TX_OFFSET_REG, + HCLGEVF_RING_TX_EBD_NUM_REG, + HCLGEVF_RING_TX_EBD_OFFSET_REG, + HCLGEVF_RING_TX_BD_ERR_REG, + HCLGEVF_RING_EN_REG}; + +static const u32 tqp_intr_reg_addr_list[] = {HCLGEVF_TQP_INTR_CTRL_REG, + HCLGEVF_TQP_INTR_GL0_REG, + HCLGEVF_TQP_INTR_GL1_REG, + HCLGEVF_TQP_INTR_GL2_REG, + HCLGEVF_TQP_INTR_RL_REG}; + +enum hclgevf_reg_tag { + HCLGEVF_REG_TAG_CMDQ = 0, + HCLGEVF_REG_TAG_COMMON, + HCLGEVF_REG_TAG_RING, + HCLGEVF_REG_TAG_TQP_INTR, +}; + +#pragma pack(4) +struct hclgevf_reg_tlv { + u16 tag; + u16 len; +}; + +struct hclgevf_reg_header { + u64 magic_number; + u8 is_vf; + u8 rsv[7]; +}; + +#pragma pack() + +#define HCLGEVF_REG_TLV_SIZE sizeof(struct hclgevf_reg_tlv) +#define HCLGEVF_REG_HEADER_SIZE sizeof(struct hclgevf_reg_header) +#define HCLGEVF_REG_TLV_SPACE (sizeof(struct hclgevf_reg_tlv) / sizeof(u32)) +#define HCLGEVF_REG_HEADER_SPACE (sizeof(struct hclgevf_reg_header) / sizeof(u32)) +#define HCLGEVF_REG_MAGIC_NUMBER 0x686e733372656773 /* meaning is hns3regs */ + +static u32 hclgevf_reg_get_header(void *data) +{ + struct hclgevf_reg_header *header = data; + + header->magic_number = HCLGEVF_REG_MAGIC_NUMBER; + header->is_vf = 0x1; + + return HCLGEVF_REG_HEADER_SPACE; +} + +static u32 hclgevf_reg_get_tlv(u32 tag, u32 regs_num, void *data) +{ + struct hclgevf_reg_tlv *tlv = data; + + tlv->tag = tag; + tlv->len = regs_num * sizeof(u32) + HCLGEVF_REG_TLV_SIZE; + + return HCLGEVF_REG_TLV_SPACE; +} + +int hclgevf_get_regs_len(struct hnae3_handle *handle) +{ + struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + int cmdq_len, common_len, ring_len, tqp_intr_len; + + cmdq_len = HCLGEVF_REG_TLV_SIZE + sizeof(cmdq_reg_addr_list); + common_len = HCLGEVF_REG_TLV_SIZE + sizeof(common_reg_addr_list); + ring_len = HCLGEVF_REG_TLV_SIZE + sizeof(ring_reg_addr_list); + tqp_intr_len = HCLGEVF_REG_TLV_SIZE + sizeof(tqp_intr_reg_addr_list); + + /* return the total length of all register values */ + return HCLGEVF_REG_HEADER_SIZE + cmdq_len + common_len + + tqp_intr_len * (hdev->num_msi_used - 1) + + ring_len * hdev->num_tqps; +} + +void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version, + void *data) +{ +#define HCLGEVF_RING_REG_OFFSET 0x200 +#define HCLGEVF_RING_INT_REG_OFFSET 0x4 + + struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + int i, j, reg_um; + u32 *reg = data; + + *version = hdev->fw_version; + reg += hclgevf_reg_get_header(reg); + + /* fetching per-VF registers values from VF PCIe register space */ + reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32); + reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_CMDQ, reg_um, reg); + for (i = 0; i < reg_um; i++) + *reg++ = hclgevf_read_dev(&hdev->hw, cmdq_reg_addr_list[i]); + + reg_um = sizeof(common_reg_addr_list) / sizeof(u32); + reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_COMMON, reg_um, reg); + for (i = 0; i < reg_um; i++) + *reg++ = hclgevf_read_dev(&hdev->hw, common_reg_addr_list[i]); + + reg_um = sizeof(ring_reg_addr_list) / sizeof(u32); + for (j = 0; j < hdev->num_tqps; j++) { + reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_RING, reg_um, reg); + for (i = 0; i < reg_um; i++) + *reg++ = hclgevf_read_dev(&hdev->hw, + ring_reg_addr_list[i] + + HCLGEVF_RING_REG_OFFSET * j); + } + + reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32); + for (j = 0; j < hdev->num_msi_used - 1; j++) { + reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_TQP_INTR, reg_um, reg); + for (i = 0; i < reg_um; i++) + *reg++ = hclgevf_read_dev(&hdev->hw, + tqp_intr_reg_addr_list[i] + + HCLGEVF_RING_INT_REG_OFFSET * j); + } +} diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.h new file mode 100644 index 000000000000..77bdcf60a1af --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2023 Hisilicon Limited. */ + +#ifndef __HCLGEVF_REGS_H +#define __HCLGEVF_REGS_H +#include <linux/types.h> + +struct hnae3_handle; + +int hclgevf_get_regs_len(struct hnae3_handle *handle); +void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version, + void *data); +#endif diff --git a/drivers/net/ethernet/intel/e1000/e1000.h b/drivers/net/ethernet/intel/e1000/e1000.h index 4817eb13ca6f..75f3fd1d8d6e 100644 --- a/drivers/net/ethernet/intel/e1000/e1000.h +++ b/drivers/net/ethernet/intel/e1000/e1000.h @@ -347,6 +347,5 @@ bool e1000_has_link(struct e1000_adapter *adapter); void e1000_power_up_phy(struct e1000_adapter *); void e1000_set_ethtool_ops(struct net_device *netdev); void e1000_check_options(struct e1000_adapter *adapter); -char *e1000_get_hw_dev_name(struct e1000_hw *hw); #endif /* _E1000_H_ */ diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.h b/drivers/net/ethernet/intel/e1000/e1000_hw.h index b57a04954ccf..95cdd17134e5 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_hw.h +++ b/drivers/net/ethernet/intel/e1000/e1000_hw.h @@ -343,7 +343,6 @@ struct e1000_host_mng_dhcp_cookie { }; #endif -bool e1000_check_mng_mode(struct e1000_hw *hw); s32 e1000_read_eeprom(struct e1000_hw *hw, u16 reg, u16 words, u16 * data); s32 e1000_validate_eeprom_checksum(struct e1000_hw *hw); s32 e1000_update_eeprom_checksum(struct e1000_hw *hw); @@ -352,7 +351,6 @@ s32 e1000_read_mac_addr(struct e1000_hw *hw); /* Filters (multicast, vlan, receive) */ u32 e1000_hash_mc_addr(struct e1000_hw *hw, u8 * mc_addr); -void e1000_mta_set(struct e1000_hw *hw, u32 hash_value); void e1000_rar_set(struct e1000_hw *hw, u8 * mc_addr, u32 rar_index); void e1000_write_vfta(struct e1000_hw *hw, u32 offset, u32 value); @@ -361,7 +359,6 @@ s32 e1000_setup_led(struct e1000_hw *hw); s32 e1000_cleanup_led(struct e1000_hw *hw); s32 e1000_led_on(struct e1000_hw *hw); s32 e1000_led_off(struct e1000_hw *hw); -s32 e1000_blink_led_start(struct e1000_hw *hw); /* Adaptive IFS Functions */ diff --git a/drivers/net/ethernet/intel/e1000e/mac.h b/drivers/net/ethernet/intel/e1000e/mac.h index 6ab261119801..563176fd436e 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.h +++ b/drivers/net/ethernet/intel/e1000e/mac.h @@ -29,8 +29,6 @@ s32 e1000e_set_fc_watermarks(struct e1000_hw *hw); s32 e1000e_setup_fiber_serdes_link(struct e1000_hw *hw); s32 e1000e_setup_led_generic(struct e1000_hw *hw); s32 e1000e_setup_link_generic(struct e1000_hw *hw); -s32 e1000e_validate_mdi_setting_generic(struct e1000_hw *hw); -s32 e1000e_validate_mdi_setting_crossover_generic(struct e1000_hw *hw); void e1000e_clear_hw_cntrs_base(struct e1000_hw *hw); void e1000_clear_vfta_generic(struct e1000_hw *hw); diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 771a3c909c45..18a5e73b8680 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -7021,6 +7021,8 @@ static __maybe_unused int e1000e_pm_runtime_resume(struct device *dev) struct e1000_adapter *adapter = netdev_priv(netdev); int rc; + pdev->pme_poll = true; + rc = __e1000_resume(pdev); if (rc) return rc; @@ -7682,7 +7684,7 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_SMART_PREPARE); - if (pci_dev_run_wake(pdev) && hw->mac.type != e1000_pch_cnp) + if (pci_dev_run_wake(pdev)) pm_runtime_put_noidle(&pdev->dev); return 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ddp.c b/drivers/net/ethernet/intel/i40e/i40e_ddp.c index 969120587cad..0e72abd178ae 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ddp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ddp.c @@ -220,7 +220,7 @@ static bool i40e_ddp_is_pkg_hdr_valid(struct net_device *netdev, netdev_err(netdev, "Invalid DDP profile - size is bigger than 4G"); return false; } - if (size < (sizeof(struct i40e_package_header) + + if (size < (sizeof(struct i40e_package_header) + sizeof(u32) + sizeof(struct i40e_metadata_segment) + sizeof(u32) * 2)) { netdev_err(netdev, "Invalid DDP profile - size is too small."); return false; @@ -281,7 +281,7 @@ int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size, if (!i40e_ddp_is_pkg_hdr_valid(netdev, pkg_hdr, size)) return -EINVAL; - if (size < (sizeof(struct i40e_package_header) + + if (size < (sizeof(struct i40e_package_header) + sizeof(u32) + sizeof(struct i40e_metadata_segment) + sizeof(u32) * 2)) { netdev_err(netdev, "Invalid DDP recipe size."); return -EINVAL; diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 5f61546f50d8..232131bedc3e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -1455,7 +1455,7 @@ struct i40e_ddp_version { struct i40e_package_header { struct i40e_ddp_version version; u32 segment_count; - u32 segment_offset[1]; + u32 segment_offset[]; }; /* Generic segment header */ @@ -1486,12 +1486,12 @@ struct i40e_profile_segment { struct i40e_ddp_version version; char name[I40E_DDP_NAME_SIZE]; u32 device_table_count; - struct i40e_device_id_entry device_table[1]; + struct i40e_device_id_entry device_table[]; }; struct i40e_section_table { u32 section_count; - u32 section_offset[1]; + u32 section_offset[]; }; struct i40e_profile_section_header { @@ -1523,7 +1523,7 @@ struct i40e_profile_aq_section { u16 flags; u8 param[16]; u16 datalen; - u8 data[1]; + u8 data[]; }; struct i40e_profile_info { diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c index a1a80f13b1e8..674913184ebf 100644 --- a/drivers/net/ethernet/marvell/mvmdio.c +++ b/drivers/net/ethernet/marvell/mvmdio.c @@ -269,7 +269,7 @@ static int orion_mdio_probe(struct platform_device *pdev) struct orion_mdio_dev *dev; int i, ret; - type = (enum orion_mdio_bus_type)device_get_match_data(&pdev->dev); + type = (uintptr_t)device_get_match_data(&pdev->dev); r = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!r) { diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_cp_version.h b/drivers/net/ethernet/marvell/octeon_ep/octep_cp_version.h new file mode 100644 index 000000000000..0c741e752db6 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_cp_version.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright (c) 2022 Marvell. + */ +#ifndef __OCTEP_CP_VERSION_H__ +#define __OCTEP_CP_VERSION_H__ + +#define OCTEP_CP_VERSION(a, b, c) ((((a) & 0xff) << 16) + \ + (((b) & 0xff) << 8) + \ + ((c) & 0xff)) + +#endif /* __OCTEP_CP_VERSION_H__ */ diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.c b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.c index dab61cc1acb5..9d53c1402cb4 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.c @@ -37,7 +37,9 @@ #define OCTEP_CTRL_MBOX_INFO_MAGIC_NUM(m) (m) #define OCTEP_CTRL_MBOX_INFO_BARMEM_SZ(m) ((m) + 8) +#define OCTEP_CTRL_MBOX_INFO_HOST_VERSION(m) ((m) + 16) #define OCTEP_CTRL_MBOX_INFO_HOST_STATUS(m) ((m) + 24) +#define OCTEP_CTRL_MBOX_INFO_FW_VERSION(m) ((m) + 136) #define OCTEP_CTRL_MBOX_INFO_FW_STATUS(m) ((m) + 144) #define OCTEP_CTRL_MBOX_H2FQ_INFO(m) ((m) + OCTEP_CTRL_MBOX_INFO_SZ) @@ -71,7 +73,7 @@ static u32 octep_ctrl_mbox_circq_depth(u32 pi, u32 ci, u32 sz) int octep_ctrl_mbox_init(struct octep_ctrl_mbox *mbox) { - u64 magic_num, status; + u64 magic_num, status, fw_versions; if (!mbox) return -EINVAL; @@ -93,6 +95,9 @@ int octep_ctrl_mbox_init(struct octep_ctrl_mbox *mbox) return -EINVAL; } + fw_versions = readq(OCTEP_CTRL_MBOX_INFO_FW_VERSION(mbox->barmem)); + mbox->min_fw_version = ((fw_versions & 0xffffffff00000000ull) >> 32); + mbox->max_fw_version = (fw_versions & 0xffffffff); mbox->barmem_sz = readl(OCTEP_CTRL_MBOX_INFO_BARMEM_SZ(mbox->barmem)); writeq(OCTEP_CTRL_MBOX_STATUS_INIT, @@ -113,6 +118,7 @@ int octep_ctrl_mbox_init(struct octep_ctrl_mbox *mbox) OCTEP_CTRL_MBOX_TOTAL_INFO_SZ + mbox->h2fq.sz; + writeq(mbox->version, OCTEP_CTRL_MBOX_INFO_HOST_VERSION(mbox->barmem)); /* ensure ready state is seen after everything is initialized */ wmb(); writeq(OCTEP_CTRL_MBOX_STATUS_READY, @@ -258,6 +264,7 @@ int octep_ctrl_mbox_uninit(struct octep_ctrl_mbox *mbox) if (!mbox->barmem) return -EINVAL; + writeq(0, OCTEP_CTRL_MBOX_INFO_HOST_VERSION(mbox->barmem)); writeq(OCTEP_CTRL_MBOX_STATUS_INVALID, OCTEP_CTRL_MBOX_INFO_HOST_STATUS(mbox->barmem)); /* ensure uninit state is written before uninitialization */ diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.h b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.h index 9c4ff0fba6a0..7f8135788efc 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.h @@ -121,6 +121,8 @@ struct octep_ctrl_mbox_q { }; struct octep_ctrl_mbox { + /* control plane version */ + u64 version; /* size of bar memory */ u32 barmem_sz; /* pointer to BAR memory */ @@ -133,6 +135,10 @@ struct octep_ctrl_mbox { struct mutex h2fq_lock; /* lock for f2hq */ struct mutex f2hq_lock; + /* Min control plane version supported by firmware */ + u32 min_fw_version; + /* Max control plane version supported by firmware */ + u32 max_fw_version; }; /* Initialize control mbox. diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.c b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.c index 1cc6af2feb38..4c6d91a8c83e 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.c @@ -14,6 +14,9 @@ #include "octep_main.h" #include "octep_ctrl_net.h" +/* Control plane version */ +#define OCTEP_CP_VERSION_CURRENT OCTEP_CP_VERSION(1, 0, 0) + static const u32 req_hdr_sz = sizeof(union octep_ctrl_net_req_hdr); static const u32 mtu_sz = sizeof(struct octep_ctrl_net_h2f_req_cmd_mtu); static const u32 mac_sz = sizeof(struct octep_ctrl_net_h2f_req_cmd_mac); @@ -21,6 +24,18 @@ static const u32 state_sz = sizeof(struct octep_ctrl_net_h2f_req_cmd_state); static const u32 link_info_sz = sizeof(struct octep_ctrl_net_link_info); static atomic_t ctrl_net_msg_id; +/* Control plane version in which OCTEP_CTRL_NET_H2F_CMD was added */ +static const u32 octep_ctrl_net_h2f_cmd_versions[OCTEP_CTRL_NET_H2F_CMD_MAX] = { + [OCTEP_CTRL_NET_H2F_CMD_INVALID ... OCTEP_CTRL_NET_H2F_CMD_LINK_INFO] = + OCTEP_CP_VERSION(1, 0, 0) +}; + +/* Control plane version in which OCTEP_CTRL_NET_F2H_CMD was added */ +static const u32 octep_ctrl_net_f2h_cmd_versions[OCTEP_CTRL_NET_F2H_CMD_MAX] = { + [OCTEP_CTRL_NET_F2H_CMD_INVALID ... OCTEP_CTRL_NET_F2H_CMD_LINK_STATUS] = + OCTEP_CP_VERSION(1, 0, 0) +}; + static void init_send_req(struct octep_ctrl_mbox_msg *msg, void *buf, u16 sz, int vfid) { @@ -41,7 +56,13 @@ static int octep_send_mbox_req(struct octep_device *oct, struct octep_ctrl_net_wait_data *d, bool wait_for_response) { - int err, ret; + int err, ret, cmd; + + /* check if firmware is compatible for this request */ + cmd = d->data.req.hdr.s.cmd; + if (octep_ctrl_net_h2f_cmd_versions[cmd] > oct->ctrl_mbox.max_fw_version || + octep_ctrl_net_h2f_cmd_versions[cmd] < oct->ctrl_mbox.min_fw_version) + return -EOPNOTSUPP; err = octep_ctrl_mbox_send(&oct->ctrl_mbox, &d->msg); if (err < 0) @@ -84,12 +105,16 @@ int octep_ctrl_net_init(struct octep_device *oct) /* Initialize control mbox */ ctrl_mbox = &oct->ctrl_mbox; + ctrl_mbox->version = OCTEP_CP_VERSION_CURRENT; ctrl_mbox->barmem = CFG_GET_CTRL_MBOX_MEM_ADDR(oct->conf); ret = octep_ctrl_mbox_init(ctrl_mbox); if (ret) { dev_err(&pdev->dev, "Failed to initialize control mbox\n"); return ret; } + dev_info(&pdev->dev, "Control plane versions host: %llx, firmware: %x:%x\n", + ctrl_mbox->version, ctrl_mbox->min_fw_version, + ctrl_mbox->max_fw_version); oct->ctrl_mbox_ifstats_offset = ctrl_mbox->barmem_sz; return 0; @@ -273,9 +298,17 @@ static int process_mbox_notify(struct octep_device *oct, { struct net_device *netdev = oct->netdev; struct octep_ctrl_net_f2h_req *req; + int cmd; req = (struct octep_ctrl_net_f2h_req *)msg->sg_list[0].msg; - switch (req->hdr.s.cmd) { + cmd = req->hdr.s.cmd; + + /* check if we support this command */ + if (octep_ctrl_net_f2h_cmd_versions[cmd] > OCTEP_CP_VERSION_CURRENT || + octep_ctrl_net_f2h_cmd_versions[cmd] < OCTEP_CP_VERSION_CURRENT) + return -EOPNOTSUPP; + + switch (cmd) { case OCTEP_CTRL_NET_F2H_CMD_LINK_STATUS: if (netif_running(netdev)) { if (req->link.state) { diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.h b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.h index 37880dd79116..1c2ef4ee31d9 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.h @@ -7,6 +7,8 @@ #ifndef __OCTEP_CTRL_NET_H__ #define __OCTEP_CTRL_NET_H__ +#include "octep_cp_version.h" + #define OCTEP_CTRL_NET_INVALID_VFID (-1) /* Supported commands */ @@ -39,12 +41,14 @@ enum octep_ctrl_net_h2f_cmd { OCTEP_CTRL_NET_H2F_CMD_LINK_STATUS, OCTEP_CTRL_NET_H2F_CMD_RX_STATE, OCTEP_CTRL_NET_H2F_CMD_LINK_INFO, + OCTEP_CTRL_NET_H2F_CMD_MAX }; /* Supported fw to host commands */ enum octep_ctrl_net_f2h_cmd { OCTEP_CTRL_NET_F2H_CMD_INVALID = 0, OCTEP_CTRL_NET_F2H_CMD_LINK_STATUS, + OCTEP_CTRL_NET_F2H_CMD_MAX }; union octep_ctrl_net_req_hdr { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index 5c8f9fc15ff8..237f82082ebe 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -580,7 +580,9 @@ static void npc_set_features(struct rvu *rvu, int blkaddr, u8 intf) if (!npc_check_field(rvu, blkaddr, NPC_LB, intf)) *features &= ~BIT_ULL(NPC_OUTER_VID); - if (*features & (BIT_ULL(NPC_IPPROTO_AH) | BIT_ULL(NPC_IPPROTO_ESP))) + /* Set SPI flag only if AH/ESP and IPSEC_SPI are in the key */ + if (npc_check_field(rvu, blkaddr, NPC_IPSEC_SPI, intf) && + (*features & (BIT_ULL(NPC_IPPROTO_ESP) | BIT_ULL(NPC_IPPROTO_AH)))) *features |= BIT_ULL(NPC_IPSEC_SPI); /* for vlan ethertypes corresponding layer type should be in the key */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 8336cea16aff..dce3cea00032 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1905,31 +1905,16 @@ int otx2_handle_ntuple_tc_features(struct net_device *netdev, netdev_features_t } } - if ((changed & NETIF_F_HW_TC) && tc) { - if (!pfvf->flow_cfg->max_flows) { - netdev_err(netdev, - "Can't enable TC, MCAM entries not allocated\n"); - return -EINVAL; - } - } - if ((changed & NETIF_F_HW_TC) && !tc && - pfvf->flow_cfg && pfvf->flow_cfg->nr_flows) { + otx2_tc_flower_rule_cnt(pfvf)) { netdev_err(netdev, "Can't disable TC hardware offload while flows are active\n"); return -EBUSY; } if ((changed & NETIF_F_NTUPLE) && ntuple && - (netdev->features & NETIF_F_HW_TC) && !(changed & NETIF_F_HW_TC)) { - netdev_err(netdev, - "Can't enable NTUPLE when TC is active, disable TC and retry\n"); - return -EINVAL; - } - - if ((changed & NETIF_F_HW_TC) && tc && - (netdev->features & NETIF_F_NTUPLE) && !(changed & NETIF_F_NTUPLE)) { + otx2_tc_flower_rule_cnt(pfvf) && !(changed & NETIF_F_HW_TC)) { netdev_err(netdev, - "Can't enable TC when NTUPLE is active, disable NTUPLE and retry\n"); + "Can't enable NTUPLE when TC flower offload is active, disable TC rules and retry\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 25e99fd2e3fd..5fd05d94de7c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -940,6 +940,15 @@ static inline u64 otx2_convert_rate(u64 rate) return converted_rate; } +static inline int otx2_tc_flower_rule_cnt(struct otx2_nic *pfvf) +{ + /* return here if MCAM entries not allocated */ + if (!pfvf->flow_cfg) + return 0; + + return pfvf->flow_cfg->nr_flows; +} + /* MSI-X APIs */ void otx2_free_cints(struct otx2_nic *pfvf, int n); void otx2_set_cints_affinity(struct otx2_nic *pfvf); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 3d82ec890666..af8460bb257b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -212,6 +212,9 @@ static int mlx5_devlink_reload_up(struct devlink *devlink, enum devlink_reload_a /* On fw_activate action, also driver is reloaded and reinit performed */ *actions_performed |= BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT); ret = mlx5_load_one_devl_locked(dev, true); + if (ret) + return ret; + ret = mlx5_fw_reset_verify_fw_complete(dev, extack); break; default: /* Unsupported action should not get to this function */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h index defba5bd91d9..961f75da6227 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h @@ -6,6 +6,14 @@ #include <net/devlink.h> +enum mlx5_devlink_resource_id { + MLX5_DL_RES_MAX_LOCAL_SFS = 1, + MLX5_DL_RES_MAX_EXTERNAL_SFS, + + __MLX5_ID_RES_MAX, + MLX5_ID_RES_MAX = __MLX5_ID_RES_MAX - 1, +}; + enum mlx5_devlink_param_id { MLX5_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, MLX5_DEVLINK_PARAM_ID_FLOW_STEERING_MODE, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h index 0107e4e73bb0..415840c3ef84 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h @@ -18,6 +18,7 @@ void mlx5e_reporter_tx_create(struct mlx5e_priv *priv); void mlx5e_reporter_tx_destroy(struct mlx5e_priv *priv); void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq); int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq); +void mlx5e_reporter_tx_ptpsq_unhealthy(struct mlx5e_ptpsq *ptpsq); int mlx5e_health_cq_diag_fmsg(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg); int mlx5e_health_cq_common_diag_fmsg(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index b0b429a0321e..bb11e644d24f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -2,9 +2,12 @@ // Copyright (c) 2020 Mellanox Technologies #include "en/ptp.h" +#include "en/health.h" #include "en/txrx.h" #include "en/params.h" #include "en/fs_tt_redirect.h" +#include <linux/list.h> +#include <linux/spinlock.h> struct mlx5e_ptp_fs { struct mlx5_flow_handle *l2_rule; @@ -19,6 +22,48 @@ struct mlx5e_ptp_params { struct mlx5e_rq_param rq_param; }; +struct mlx5e_ptp_port_ts_cqe_tracker { + u8 metadata_id; + bool inuse : 1; + struct list_head entry; +}; + +struct mlx5e_ptp_port_ts_cqe_list { + struct mlx5e_ptp_port_ts_cqe_tracker *nodes; + struct list_head tracker_list_head; + /* Sync list operations in xmit and napi_poll contexts */ + spinlock_t tracker_list_lock; +}; + +static inline void +mlx5e_ptp_port_ts_cqe_list_add(struct mlx5e_ptp_port_ts_cqe_list *list, u8 metadata) +{ + struct mlx5e_ptp_port_ts_cqe_tracker *tracker = &list->nodes[metadata]; + + WARN_ON_ONCE(tracker->inuse); + tracker->inuse = true; + spin_lock(&list->tracker_list_lock); + list_add_tail(&tracker->entry, &list->tracker_list_head); + spin_unlock(&list->tracker_list_lock); +} + +static void +mlx5e_ptp_port_ts_cqe_list_remove(struct mlx5e_ptp_port_ts_cqe_list *list, u8 metadata) +{ + struct mlx5e_ptp_port_ts_cqe_tracker *tracker = &list->nodes[metadata]; + + WARN_ON_ONCE(!tracker->inuse); + tracker->inuse = false; + spin_lock(&list->tracker_list_lock); + list_del(&tracker->entry); + spin_unlock(&list->tracker_list_lock); +} + +void mlx5e_ptpsq_track_metadata(struct mlx5e_ptpsq *ptpsq, u8 metadata) +{ + mlx5e_ptp_port_ts_cqe_list_add(ptpsq->ts_cqe_pending_list, metadata); +} + struct mlx5e_skb_cb_hwtstamp { ktime_t cqe_hwtstamp; ktime_t port_hwtstamp; @@ -79,75 +124,97 @@ void mlx5e_skb_cb_hwtstamp_handler(struct sk_buff *skb, int hwtstamp_type, memset(skb->cb, 0, sizeof(struct mlx5e_skb_cb_hwtstamp)); } -#define PTP_WQE_CTR2IDX(val) ((val) & ptpsq->ts_cqe_ctr_mask) - -static bool mlx5e_ptp_ts_cqe_drop(struct mlx5e_ptpsq *ptpsq, u16 skb_ci, u16 skb_id) +static struct sk_buff * +mlx5e_ptp_metadata_map_lookup(struct mlx5e_ptp_metadata_map *map, u16 metadata) { - return (ptpsq->ts_cqe_ctr_mask && (skb_ci != skb_id)); + return map->data[metadata]; } -static bool mlx5e_ptp_ts_cqe_ooo(struct mlx5e_ptpsq *ptpsq, u16 skb_id) +static struct sk_buff * +mlx5e_ptp_metadata_map_remove(struct mlx5e_ptp_metadata_map *map, u16 metadata) { - u16 skb_ci = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_cc); - u16 skb_pi = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_pc); + struct sk_buff *skb; - if (PTP_WQE_CTR2IDX(skb_id - skb_ci) >= PTP_WQE_CTR2IDX(skb_pi - skb_ci)) - return true; + skb = map->data[metadata]; + map->data[metadata] = NULL; - return false; + return skb; } -static void mlx5e_ptp_skb_fifo_ts_cqe_resync(struct mlx5e_ptpsq *ptpsq, u16 skb_ci, - u16 skb_id, int budget) +static bool mlx5e_ptp_metadata_map_unhealthy(struct mlx5e_ptp_metadata_map *map) { - struct skb_shared_hwtstamps hwts = {}; - struct sk_buff *skb; + /* Considered beginning unhealthy state if size * 15 / 2^4 cannot be reclaimed. */ + return map->undelivered_counter > (map->capacity >> 4) * 15; +} - ptpsq->cq_stats->resync_event++; +static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq, + ktime_t port_tstamp) +{ + struct mlx5e_ptp_port_ts_cqe_list *cqe_list = ptpsq->ts_cqe_pending_list; + ktime_t timeout = ns_to_ktime(MLX5E_PTP_TS_CQE_UNDELIVERED_TIMEOUT); + struct mlx5e_ptp_metadata_map *metadata_map = &ptpsq->metadata_map; + struct mlx5e_ptp_port_ts_cqe_tracker *pos, *n; + + spin_lock(&cqe_list->tracker_list_lock); + list_for_each_entry_safe(pos, n, &cqe_list->tracker_list_head, entry) { + struct sk_buff *skb = + mlx5e_ptp_metadata_map_lookup(metadata_map, pos->metadata_id); + ktime_t dma_tstamp = mlx5e_skb_cb_get_hwts(skb)->cqe_hwtstamp; + + if (!dma_tstamp || + ktime_after(ktime_add(dma_tstamp, timeout), port_tstamp)) + break; - while (skb_ci != skb_id) { - skb = mlx5e_skb_fifo_pop(&ptpsq->skb_fifo); - hwts.hwtstamp = mlx5e_skb_cb_get_hwts(skb)->cqe_hwtstamp; - skb_tstamp_tx(skb, &hwts); - ptpsq->cq_stats->resync_cqe++; - napi_consume_skb(skb, budget); - skb_ci = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_cc); + metadata_map->undelivered_counter++; + WARN_ON_ONCE(!pos->inuse); + pos->inuse = false; + list_del(&pos->entry); } + spin_unlock(&cqe_list->tracker_list_lock); } +#define PTP_WQE_CTR2IDX(val) ((val) & ptpsq->ts_cqe_ctr_mask) + static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq, struct mlx5_cqe64 *cqe, int budget) { - u16 skb_id = PTP_WQE_CTR2IDX(be16_to_cpu(cqe->wqe_counter)); - u16 skb_ci = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_cc); + struct mlx5e_ptp_port_ts_cqe_list *pending_cqe_list = ptpsq->ts_cqe_pending_list; + u8 metadata_id = PTP_WQE_CTR2IDX(be16_to_cpu(cqe->wqe_counter)); + bool is_err_cqe = !!MLX5E_RX_ERR_CQE(cqe); struct mlx5e_txqsq *sq = &ptpsq->txqsq; struct sk_buff *skb; ktime_t hwtstamp; - if (unlikely(MLX5E_RX_ERR_CQE(cqe))) { - skb = mlx5e_skb_fifo_pop(&ptpsq->skb_fifo); - ptpsq->cq_stats->err_cqe++; - goto out; + if (likely(pending_cqe_list->nodes[metadata_id].inuse)) { + mlx5e_ptp_port_ts_cqe_list_remove(pending_cqe_list, metadata_id); + } else { + /* Reclaim space in the unlikely event CQE was delivered after + * marking it late. + */ + ptpsq->metadata_map.undelivered_counter--; + ptpsq->cq_stats->late_cqe++; } - if (mlx5e_ptp_ts_cqe_drop(ptpsq, skb_ci, skb_id)) { - if (mlx5e_ptp_ts_cqe_ooo(ptpsq, skb_id)) { - /* already handled by a previous resync */ - ptpsq->cq_stats->ooo_cqe_drop++; - return; - } - mlx5e_ptp_skb_fifo_ts_cqe_resync(ptpsq, skb_ci, skb_id, budget); + skb = mlx5e_ptp_metadata_map_remove(&ptpsq->metadata_map, metadata_id); + + if (unlikely(is_err_cqe)) { + ptpsq->cq_stats->err_cqe++; + goto out; } - skb = mlx5e_skb_fifo_pop(&ptpsq->skb_fifo); hwtstamp = mlx5e_cqe_ts_to_ns(sq->ptp_cyc2time, sq->clock, get_cqe_ts(cqe)); mlx5e_skb_cb_hwtstamp_handler(skb, MLX5E_SKB_CB_PORT_HWTSTAMP, hwtstamp, ptpsq->cq_stats); ptpsq->cq_stats->cqe++; + mlx5e_ptpsq_mark_ts_cqes_undelivered(ptpsq, hwtstamp); out: napi_consume_skb(skb, budget); + mlx5e_ptp_metadata_fifo_push(&ptpsq->metadata_freelist, metadata_id); + if (unlikely(mlx5e_ptp_metadata_map_unhealthy(&ptpsq->metadata_map)) && + !test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) + queue_work(ptpsq->txqsq.priv->wq, &ptpsq->report_unhealthy_work); } static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget) @@ -291,36 +358,86 @@ static void mlx5e_ptp_destroy_sq(struct mlx5_core_dev *mdev, u32 sqn) static int mlx5e_ptp_alloc_traffic_db(struct mlx5e_ptpsq *ptpsq, int numa) { - int wq_sz = mlx5_wq_cyc_get_size(&ptpsq->txqsq.wq); - struct mlx5_core_dev *mdev = ptpsq->txqsq.mdev; + struct mlx5e_ptp_metadata_fifo *metadata_freelist = &ptpsq->metadata_freelist; + struct mlx5e_ptp_metadata_map *metadata_map = &ptpsq->metadata_map; + struct mlx5e_ptp_port_ts_cqe_list *cqe_list; + int db_sz; + int md; - ptpsq->skb_fifo.fifo = kvzalloc_node(array_size(wq_sz, sizeof(*ptpsq->skb_fifo.fifo)), - GFP_KERNEL, numa); - if (!ptpsq->skb_fifo.fifo) + cqe_list = kvzalloc_node(sizeof(*ptpsq->ts_cqe_pending_list), GFP_KERNEL, numa); + if (!cqe_list) return -ENOMEM; + ptpsq->ts_cqe_pending_list = cqe_list; + + db_sz = min_t(u32, mlx5_wq_cyc_get_size(&ptpsq->txqsq.wq), + 1 << MLX5_CAP_GEN_2(ptpsq->txqsq.mdev, + ts_cqe_metadata_size2wqe_counter)); + ptpsq->ts_cqe_ctr_mask = db_sz - 1; + + cqe_list->nodes = kvzalloc_node(array_size(db_sz, sizeof(*cqe_list->nodes)), + GFP_KERNEL, numa); + if (!cqe_list->nodes) + goto free_cqe_list; + INIT_LIST_HEAD(&cqe_list->tracker_list_head); + spin_lock_init(&cqe_list->tracker_list_lock); + + metadata_freelist->data = + kvzalloc_node(array_size(db_sz, sizeof(*metadata_freelist->data)), + GFP_KERNEL, numa); + if (!metadata_freelist->data) + goto free_cqe_list_nodes; + metadata_freelist->mask = ptpsq->ts_cqe_ctr_mask; + + for (md = 0; md < db_sz; ++md) { + cqe_list->nodes[md].metadata_id = md; + metadata_freelist->data[md] = md; + } + metadata_freelist->pc = db_sz; + + metadata_map->data = + kvzalloc_node(array_size(db_sz, sizeof(*metadata_map->data)), + GFP_KERNEL, numa); + if (!metadata_map->data) + goto free_metadata_freelist; + metadata_map->capacity = db_sz; - ptpsq->skb_fifo.pc = &ptpsq->skb_fifo_pc; - ptpsq->skb_fifo.cc = &ptpsq->skb_fifo_cc; - ptpsq->skb_fifo.mask = wq_sz - 1; - if (MLX5_CAP_GEN_2(mdev, ts_cqe_metadata_size2wqe_counter)) - ptpsq->ts_cqe_ctr_mask = - (1 << MLX5_CAP_GEN_2(mdev, ts_cqe_metadata_size2wqe_counter)) - 1; return 0; + +free_metadata_freelist: + kvfree(metadata_freelist->data); +free_cqe_list_nodes: + kvfree(cqe_list->nodes); +free_cqe_list: + kvfree(cqe_list); + return -ENOMEM; } -static void mlx5e_ptp_drain_skb_fifo(struct mlx5e_skb_fifo *skb_fifo) +static void mlx5e_ptp_drain_metadata_map(struct mlx5e_ptp_metadata_map *map) { - while (*skb_fifo->pc != *skb_fifo->cc) { - struct sk_buff *skb = mlx5e_skb_fifo_pop(skb_fifo); + int idx; + + for (idx = 0; idx < map->capacity; ++idx) { + struct sk_buff *skb = map->data[idx]; dev_kfree_skb_any(skb); } } -static void mlx5e_ptp_free_traffic_db(struct mlx5e_skb_fifo *skb_fifo) +static void mlx5e_ptp_free_traffic_db(struct mlx5e_ptpsq *ptpsq) { - mlx5e_ptp_drain_skb_fifo(skb_fifo); - kvfree(skb_fifo->fifo); + mlx5e_ptp_drain_metadata_map(&ptpsq->metadata_map); + kvfree(ptpsq->metadata_map.data); + kvfree(ptpsq->metadata_freelist.data); + kvfree(ptpsq->ts_cqe_pending_list->nodes); + kvfree(ptpsq->ts_cqe_pending_list); +} + +static void mlx5e_ptpsq_unhealthy_work(struct work_struct *work) +{ + struct mlx5e_ptpsq *ptpsq = + container_of(work, struct mlx5e_ptpsq, report_unhealthy_work); + + mlx5e_reporter_tx_ptpsq_unhealthy(ptpsq); } static int mlx5e_ptp_open_txqsq(struct mlx5e_ptp *c, u32 tisn, @@ -348,11 +465,12 @@ static int mlx5e_ptp_open_txqsq(struct mlx5e_ptp *c, u32 tisn, if (err) goto err_free_txqsq; - err = mlx5e_ptp_alloc_traffic_db(ptpsq, - dev_to_node(mlx5_core_dma_dev(c->mdev))); + err = mlx5e_ptp_alloc_traffic_db(ptpsq, dev_to_node(mlx5_core_dma_dev(c->mdev))); if (err) goto err_free_txqsq; + INIT_WORK(&ptpsq->report_unhealthy_work, mlx5e_ptpsq_unhealthy_work); + return 0; err_free_txqsq: @@ -366,7 +484,9 @@ static void mlx5e_ptp_close_txqsq(struct mlx5e_ptpsq *ptpsq) struct mlx5e_txqsq *sq = &ptpsq->txqsq; struct mlx5_core_dev *mdev = sq->mdev; - mlx5e_ptp_free_traffic_db(&ptpsq->skb_fifo); + if (current_work() != &ptpsq->report_unhealthy_work) + cancel_work_sync(&ptpsq->report_unhealthy_work); + mlx5e_ptp_free_traffic_db(ptpsq); cancel_work_sync(&sq->recover_work); mlx5e_ptp_destroy_sq(mdev, sq->sqn); mlx5e_free_txqsq_descs(sq); @@ -534,7 +654,10 @@ static void mlx5e_ptp_build_params(struct mlx5e_ptp *c, /* SQ */ if (test_bit(MLX5E_PTP_STATE_TX, c->state)) { - params->log_sq_size = orig->log_sq_size; + params->log_sq_size = + min(MLX5_CAP_GEN_2(c->mdev, ts_cqe_metadata_size2wqe_counter), + MLX5E_PTP_MAX_LOG_SQ_SIZE); + params->log_sq_size = min(params->log_sq_size, orig->log_sq_size); mlx5e_ptp_build_sq_param(c->mdev, params, &cparams->txq_sq_param); } /* RQ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h index cc7efde88ac3..7b700d0f956a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h @@ -7,18 +7,38 @@ #include "en.h" #include "en_stats.h" #include "en/txrx.h" +#include <linux/ktime.h> #include <linux/ptp_classify.h> +#include <linux/time64.h> +#include <linux/workqueue.h> #define MLX5E_PTP_CHANNEL_IX 0 +#define MLX5E_PTP_MAX_LOG_SQ_SIZE (8U) +#define MLX5E_PTP_TS_CQE_UNDELIVERED_TIMEOUT (1 * NSEC_PER_SEC) + +struct mlx5e_ptp_metadata_fifo { + u8 cc; + u8 pc; + u8 mask; + u8 *data; +}; + +struct mlx5e_ptp_metadata_map { + u16 undelivered_counter; + u16 capacity; + struct sk_buff **data; +}; struct mlx5e_ptpsq { struct mlx5e_txqsq txqsq; struct mlx5e_cq ts_cq; - u16 skb_fifo_cc; - u16 skb_fifo_pc; - struct mlx5e_skb_fifo skb_fifo; struct mlx5e_ptp_cq_stats *cq_stats; u16 ts_cqe_ctr_mask; + + struct work_struct report_unhealthy_work; + struct mlx5e_ptp_port_ts_cqe_list *ts_cqe_pending_list; + struct mlx5e_ptp_metadata_fifo metadata_freelist; + struct mlx5e_ptp_metadata_map metadata_map; }; enum { @@ -69,12 +89,35 @@ static inline bool mlx5e_use_ptpsq(struct sk_buff *skb) fk.ports.dst == htons(PTP_EV_PORT)); } -static inline bool mlx5e_ptpsq_fifo_has_room(struct mlx5e_txqsq *sq) +static inline void mlx5e_ptp_metadata_fifo_push(struct mlx5e_ptp_metadata_fifo *fifo, u8 metadata) { - if (!sq->ptpsq) - return true; + fifo->data[fifo->mask & fifo->pc++] = metadata; +} + +static inline u8 +mlx5e_ptp_metadata_fifo_pop(struct mlx5e_ptp_metadata_fifo *fifo) +{ + return fifo->data[fifo->mask & fifo->cc++]; +} - return mlx5e_skb_fifo_has_room(&sq->ptpsq->skb_fifo); +static inline void +mlx5e_ptp_metadata_map_put(struct mlx5e_ptp_metadata_map *map, + struct sk_buff *skb, u8 metadata) +{ + WARN_ON_ONCE(map->data[metadata]); + map->data[metadata] = skb; +} + +static inline bool mlx5e_ptpsq_metadata_freelist_empty(struct mlx5e_ptpsq *ptpsq) +{ + struct mlx5e_ptp_metadata_fifo *freelist; + + if (likely(!ptpsq)) + return false; + + freelist = &ptpsq->metadata_freelist; + + return freelist->pc == freelist->cc; } int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params, @@ -89,6 +132,8 @@ void mlx5e_ptp_free_rx_fs(struct mlx5e_flow_steering *fs, const struct mlx5e_profile *profile); int mlx5e_ptp_rx_manage_fs(struct mlx5e_priv *priv, bool set); +void mlx5e_ptpsq_track_metadata(struct mlx5e_ptpsq *ptpsq, u8 metadata); + enum { MLX5E_SKB_CB_CQE_HWTSTAMP = BIT(0), MLX5E_SKB_CB_PORT_HWTSTAMP = BIT(1), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index b35ff289af49..ff8242f67c54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -164,6 +164,43 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx) return err; } +static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx) +{ + struct mlx5e_ptpsq *ptpsq = ctx; + struct mlx5e_channels *chs; + struct net_device *netdev; + struct mlx5e_priv *priv; + int carrier_ok; + int err; + + if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &ptpsq->txqsq.state)) + return 0; + + priv = ptpsq->txqsq.priv; + + mutex_lock(&priv->state_lock); + chs = &priv->channels; + netdev = priv->netdev; + + carrier_ok = netif_carrier_ok(netdev); + netif_carrier_off(netdev); + + mlx5e_deactivate_priv_channels(priv); + + mlx5e_ptp_close(chs->ptp); + err = mlx5e_ptp_open(priv, &chs->params, chs->c[0]->lag_port, &chs->ptp); + + mlx5e_activate_priv_channels(priv); + + /* return carrier back if needed */ + if (carrier_ok) + netif_carrier_on(netdev); + + mutex_unlock(&priv->state_lock); + + return err; +} + /* state lock cannot be grabbed within this function. * It can cause a dead lock or a read-after-free. */ @@ -516,6 +553,15 @@ static int mlx5e_tx_reporter_timeout_dump(struct mlx5e_priv *priv, struct devlin return mlx5e_tx_reporter_dump_sq(priv, fmsg, to_ctx->sq); } +static int mlx5e_tx_reporter_ptpsq_unhealthy_dump(struct mlx5e_priv *priv, + struct devlink_fmsg *fmsg, + void *ctx) +{ + struct mlx5e_ptpsq *ptpsq = ctx; + + return mlx5e_tx_reporter_dump_sq(priv, fmsg, &ptpsq->txqsq); +} + static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg) { @@ -621,6 +667,25 @@ int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq) return to_ctx.status; } +void mlx5e_reporter_tx_ptpsq_unhealthy(struct mlx5e_ptpsq *ptpsq) +{ + struct mlx5e_ptp_metadata_map *map = &ptpsq->metadata_map; + char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; + struct mlx5e_txqsq *txqsq = &ptpsq->txqsq; + struct mlx5e_cq *ts_cq = &ptpsq->ts_cq; + struct mlx5e_priv *priv = txqsq->priv; + struct mlx5e_err_ctx err_ctx = {}; + + err_ctx.ctx = ptpsq; + err_ctx.recover = mlx5e_tx_reporter_ptpsq_unhealthy_recover; + err_ctx.dump = mlx5e_tx_reporter_ptpsq_unhealthy_dump; + snprintf(err_str, sizeof(err_str), + "Unhealthy TX port TS queue: %d, SQ: 0x%x, CQ: 0x%x, Undelivered CQEs: %u Map Capacity: %u", + txqsq->ch_ix, txqsq->sqn, ts_cq->mcq.cqn, map->undelivered_counter, map->capacity); + + mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx); +} + static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = { .name = "tx", .recover = mlx5e_tx_reporter_recover, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 04195a673a6b..dff02434ff45 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -2061,7 +2061,8 @@ static int set_pflag_tx_port_ts(struct net_device *netdev, bool enable) struct mlx5e_params new_params; int err; - if (!MLX5_CAP_GEN(mdev, ts_cqe_to_dest_cqn)) + if (!MLX5_CAP_GEN(mdev, ts_cqe_to_dest_cqn) || + !MLX5_CAP_GEN_2(mdev, ts_cqe_metadata_size2wqe_counter)) return -EOPNOTSUPP; /* Don't allow changing the PTP state if HTB offload is active, because diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 07b84d668fcc..52141729444e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -2142,9 +2142,7 @@ static const struct counter_desc ptp_cq_stats_desc[] = { { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, err_cqe) }, { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, abort) }, { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, abort_abs_diff_ns) }, - { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, resync_cqe) }, - { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, resync_event) }, - { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, ooo_cqe_drop) }, + { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, late_cqe) }, }; static const struct counter_desc ptp_rq_stats_desc[] = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 1ff8a06027dc..409e9a47e433 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -449,9 +449,7 @@ struct mlx5e_ptp_cq_stats { u64 err_cqe; u64 abort; u64 abort_abs_diff_ns; - u64 resync_cqe; - u64 resync_event; - u64 ooo_cqe_drop; + u64 late_cqe; }; struct mlx5e_rep_stats { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index c7eb6b238c2b..d41435c22ce5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -372,7 +372,7 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, const struct mlx5e_tx_attr *attr, const struct mlx5e_tx_wqe_attr *wqe_attr, u8 num_dma, struct mlx5e_tx_wqe_info *wi, struct mlx5_wqe_ctrl_seg *cseg, - bool xmit_more) + struct mlx5_wqe_eth_seg *eseg, bool xmit_more) { struct mlx5_wq_cyc *wq = &sq->wq; bool send_doorbell; @@ -394,11 +394,16 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, mlx5e_tx_check_stop(sq); - if (unlikely(sq->ptpsq)) { + if (unlikely(sq->ptpsq && + (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) { + u8 metadata_index = be32_to_cpu(eseg->flow_table_metadata); + mlx5e_skb_cb_hwtstamp_init(skb); - mlx5e_skb_fifo_push(&sq->ptpsq->skb_fifo, skb); + mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index); + mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb, + metadata_index); if (!netif_tx_queue_stopped(sq->txq) && - !mlx5e_skb_fifo_has_room(&sq->ptpsq->skb_fifo)) { + mlx5e_ptpsq_metadata_freelist_empty(sq->ptpsq)) { netif_tx_stop_queue(sq->txq); sq->stats->stopped++; } @@ -483,13 +488,16 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb, if (unlikely(num_dma < 0)) goto err_drop; - mlx5e_txwqe_complete(sq, skb, attr, wqe_attr, num_dma, wi, cseg, xmit_more); + mlx5e_txwqe_complete(sq, skb, attr, wqe_attr, num_dma, wi, cseg, eseg, xmit_more); return; err_drop: stats->dropped++; dev_kfree_skb_any(skb); + if (unlikely(sq->ptpsq && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) + mlx5e_ptp_metadata_fifo_push(&sq->ptpsq->metadata_freelist, + be32_to_cpu(eseg->flow_table_metadata)); mlx5e_tx_flush(sq); } @@ -645,9 +653,9 @@ void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq) static void mlx5e_cqe_ts_id_eseg(struct mlx5e_ptpsq *ptpsq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) { - if (ptpsq->ts_cqe_ctr_mask && unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) - eseg->flow_table_metadata = cpu_to_be32(ptpsq->skb_fifo_pc & - ptpsq->ts_cqe_ctr_mask); + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) + eseg->flow_table_metadata = + cpu_to_be32(mlx5e_ptp_metadata_fifo_pop(&ptpsq->metadata_freelist)); } static void mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq, @@ -766,7 +774,7 @@ void mlx5e_txqsq_wake(struct mlx5e_txqsq *sq) { if (netif_tx_queue_stopped(sq->txq) && mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, sq->stop_room) && - mlx5e_ptpsq_fifo_has_room(sq) && + !mlx5e_ptpsq_metadata_freelist_empty(sq->ptpsq) && !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) { netif_tx_wake_queue(sq->txq); sq->stats->wake++; @@ -1031,7 +1039,7 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, if (unlikely(num_dma < 0)) goto err_drop; - mlx5e_txwqe_complete(sq, skb, &attr, &wqe_attr, num_dma, wi, cseg, xmit_more); + mlx5e_txwqe_complete(sq, skb, &attr, &wqe_attr, num_dma, wi, cseg, eseg, xmit_more); return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index e391535e1ab1..46b8c60ac39a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -535,6 +535,28 @@ esw_src_port_rewrite_supported(struct mlx5_eswitch *esw) MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level); } +static bool +esw_dests_to_vf_pf_vports(struct mlx5_flow_destination *dests, int max_dest) +{ + bool vf_dest = false, pf_dest = false; + int i; + + for (i = 0; i < max_dest; i++) { + if (dests[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT) + continue; + + if (dests[i].vport.num == MLX5_VPORT_UPLINK) + pf_dest = true; + else + vf_dest = true; + + if (vf_dest && pf_dest) + return true; + } + + return false; +} + static int esw_setup_dests(struct mlx5_flow_destination *dest, struct mlx5_flow_act *flow_act, @@ -671,6 +693,15 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, rule = ERR_PTR(err); goto err_create_goto_table; } + + /* Header rewrite with combined wire+loopback in FDB is not allowed */ + if ((flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) && + esw_dests_to_vf_pf_vports(dest, i)) { + esw_warn(esw->dev, + "FDB: Header rewrite with forwarding to both PF and VF is not allowed\n"); + rule = ERR_PTR(-EINVAL); + goto err_esw_get; + } } if (esw_attr->decap_pkt_reformat) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index fb2035a5ec99..58f4c0d0fafa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -143,90 +143,86 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) { int err; - err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_GENERAL, HCA_CAP_OPMOD_GET_CUR); if (err) return err; if (MLX5_CAP_GEN(dev, port_selection_cap)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_PORT_SELECTION); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_PORT_SELECTION, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, hca_cap_2)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL_2); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_GENERAL_2, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, eth_net_offloads)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_ETHERNET_OFFLOADS); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ETHERNET_OFFLOADS, + HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, ipoib_enhanced_offloads)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_IPOIB_ENHANCED_OFFLOADS); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_IPOIB_ENHANCED_OFFLOADS, + HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, pg)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_ODP); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ODP, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, atomic)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_ATOMIC); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ATOMIC, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, roce)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_ROCE); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ROCE, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, nic_flow_table) || MLX5_CAP_GEN(dev, ipoib_enhanced_offloads)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_FLOW_TABLE); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_FLOW_TABLE, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_ESWITCH_MANAGER(dev)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ESWITCH_FLOW_TABLE, + HCA_CAP_OPMOD_GET_CUR); if (err) return err; - err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH); - if (err) - return err; - } - - if (MLX5_CAP_GEN(dev, vector_calc)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_VECTOR_CALC); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ESWITCH, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, qos)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_QOS); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_QOS, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, debug)) - mlx5_core_get_caps(dev, MLX5_CAP_DEBUG); + mlx5_core_get_caps_mode(dev, MLX5_CAP_DEBUG, HCA_CAP_OPMOD_GET_CUR); if (MLX5_CAP_GEN(dev, pcam_reg)) mlx5_get_pcam_reg(dev); if (MLX5_CAP_GEN(dev, mcam_reg)) { mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_FIRST_128); - mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9080_0x90FF); mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9100_0x917F); } @@ -234,57 +230,52 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) mlx5_get_qcam_reg(dev); if (MLX5_CAP_GEN(dev, device_memory)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_DEV_MEM); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_DEV_MEM, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, event_cap)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_DEV_EVENT); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_DEV_EVENT, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, tls_tx) || MLX5_CAP_GEN(dev, tls_rx)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_TLS); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_TLS, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN_64(dev, general_obj_types) & MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q) { - err = mlx5_core_get_caps(dev, MLX5_CAP_VDPA_EMULATION); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_VDPA_EMULATION, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, ipsec_offload)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_IPSEC); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_IPSEC, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, crypto)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_CRYPTO); - if (err) - return err; - } - - if (MLX5_CAP_GEN(dev, shampo)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_DEV_SHAMPO); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_CRYPTO, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN_64(dev, general_obj_types) & MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD) { - err = mlx5_core_get_caps(dev, MLX5_CAP_MACSEC); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_MACSEC, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, adv_virtualization)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_ADV_VIRTUALIZATION); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ADV_VIRTUALIZATION, + HCA_CAP_OPMOD_GET_CUR); if (err) return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 4804990b7f22..e87766f91150 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -127,17 +127,23 @@ static int mlx5_fw_reset_get_reset_state_err(struct mlx5_core_dev *dev, if (mlx5_reg_mfrl_query(dev, NULL, NULL, &reset_state)) goto out; + if (!reset_state) + return 0; + switch (reset_state) { case MLX5_MFRL_REG_RESET_STATE_IN_NEGOTIATION: case MLX5_MFRL_REG_RESET_STATE_RESET_IN_PROGRESS: - NL_SET_ERR_MSG_MOD(extack, "Sync reset was already triggered"); + NL_SET_ERR_MSG_MOD(extack, "Sync reset still in progress"); return -EBUSY; - case MLX5_MFRL_REG_RESET_STATE_TIMEOUT: - NL_SET_ERR_MSG_MOD(extack, "Sync reset got timeout"); + case MLX5_MFRL_REG_RESET_STATE_NEG_TIMEOUT: + NL_SET_ERR_MSG_MOD(extack, "Sync reset negotiation timeout"); return -ETIMEDOUT; case MLX5_MFRL_REG_RESET_STATE_NACK: NL_SET_ERR_MSG_MOD(extack, "One of the hosts disabled reset"); return -EPERM; + case MLX5_MFRL_REG_RESET_STATE_UNLOAD_TIMEOUT: + NL_SET_ERR_MSG_MOD(extack, "Sync reset unload timeout"); + return -ETIMEDOUT; } out: @@ -151,7 +157,7 @@ int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel, struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; u32 out[MLX5_ST_SZ_DW(mfrl_reg)] = {}; u32 in[MLX5_ST_SZ_DW(mfrl_reg)] = {}; - int err; + int err, rst_res; set_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags); @@ -164,13 +170,34 @@ int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel, return 0; clear_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags); - if (err == -EREMOTEIO && MLX5_CAP_MCAM_FEATURE(dev, reset_state)) - return mlx5_fw_reset_get_reset_state_err(dev, extack); + if (err == -EREMOTEIO && MLX5_CAP_MCAM_FEATURE(dev, reset_state)) { + rst_res = mlx5_fw_reset_get_reset_state_err(dev, extack); + return rst_res ? rst_res : err; + } NL_SET_ERR_MSG_MOD(extack, "Sync reset command failed"); return mlx5_cmd_check(dev, err, in, out); } +int mlx5_fw_reset_verify_fw_complete(struct mlx5_core_dev *dev, + struct netlink_ext_ack *extack) +{ + u8 rst_state; + int err; + + err = mlx5_fw_reset_get_reset_state_err(dev, extack); + if (err) + return err; + + rst_state = mlx5_get_fw_rst_state(dev); + if (!rst_state) + return 0; + + mlx5_core_err(dev, "Sync reset did not complete, state=%d\n", rst_state); + NL_SET_ERR_MSG_MOD(extack, "Sync reset did not complete successfully"); + return rst_state; +} + int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev) { return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL0, 0, 0, false); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h index c57465595f7c..ea527d06a85f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h @@ -12,6 +12,8 @@ int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel, int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev); int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev); +int mlx5_fw_reset_verify_fw_complete(struct mlx5_core_dev *dev, + struct netlink_ext_ack *extack); void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev); void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev); void mlx5_drain_fw_reset(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index f4fe06a5042e..15561965d2af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -361,9 +361,8 @@ void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_core_uplink_netdev_event_replay); -static int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, - enum mlx5_cap_type cap_type, - enum mlx5_cap_mode cap_mode) +int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type, + enum mlx5_cap_mode cap_mode) { u8 in[MLX5_ST_SZ_BYTES(query_hca_cap_in)]; int out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out); @@ -1620,21 +1619,24 @@ static int mlx5_query_hca_caps_light(struct mlx5_core_dev *dev) return err; if (MLX5_CAP_GEN(dev, eth_net_offloads)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_ETHERNET_OFFLOADS); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ETHERNET_OFFLOADS, + HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, nic_flow_table) || MLX5_CAP_GEN(dev, ipoib_enhanced_offloads)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_FLOW_TABLE); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_FLOW_TABLE, + HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN_64(dev, general_obj_types) & MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q) { - err = mlx5_core_get_caps(dev, MLX5_CAP_VDPA_EMULATION); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_VDPA_EMULATION, + HCA_CAP_OPMOD_GET_CUR); if (err) return err; } @@ -1714,7 +1716,6 @@ static const int types[] = { MLX5_CAP_FLOW_TABLE, MLX5_CAP_ESWITCH_FLOW_TABLE, MLX5_CAP_ESWITCH, - MLX5_CAP_VECTOR_CALC, MLX5_CAP_QOS, MLX5_CAP_DEBUG, MLX5_CAP_DEV_MEM, @@ -1723,7 +1724,6 @@ static const int types[] = { MLX5_CAP_VDPA_EMULATION, MLX5_CAP_IPSEC, MLX5_CAP_PORT_SELECTION, - MLX5_CAP_DEV_SHAMPO, MLX5_CAP_MACSEC, MLX5_CAP_ADV_VIRTUALIZATION, MLX5_CAP_CRYPTO, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 8e2028d20a9e..124352459c23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -174,6 +174,9 @@ static inline int mlx5_flexible_inlen(struct mlx5_core_dev *dev, size_t fixed, #define MLX5_FLEXIBLE_INLEN(dev, fixed, item_size, num_items) \ mlx5_flexible_inlen(dev, fixed, item_size, num_items, __func__, __LINE__) +int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); +int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type, + enum mlx5_cap_mode cap_mode); int mlx5_query_hca_caps(struct mlx5_core_dev *dev); int mlx5_query_board_id(struct mlx5_core_dev *dev); int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c index 8e2abbab05f0..05e148db9889 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c @@ -129,7 +129,7 @@ static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u16 fn_id, err = auxiliary_device_add(&sf_dev->adev); if (err) { - put_device(&sf_dev->adev.dev); + auxiliary_device_uninit(&sf_dev->adev); goto add_err; } @@ -167,7 +167,7 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_ if (!max_functions) return 0; - base_id = MLX5_CAP_GEN(table->dev, sf_base_id); + base_id = mlx5_sf_start_function_id(table->dev); if (event->function_id < base_id || event->function_id >= (base_id + max_functions)) return 0; @@ -185,7 +185,7 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_ mlx5_sf_dev_del(table->dev, sf_dev, sf_index); else mlx5_core_err(table->dev, - "SF DEV: teardown state for invalid dev index=%d fn_id=0x%x\n", + "SF DEV: teardown state for invalid dev index=%d sfnum=0x%x\n", sf_index, event->sw_function_id); break; case MLX5_VHCA_STATE_ACTIVE: @@ -209,7 +209,7 @@ static int mlx5_sf_dev_vhca_arm_all(struct mlx5_sf_dev_table *table) int i; max_functions = mlx5_sf_max_functions(dev); - function_id = MLX5_CAP_GEN(dev, sf_base_id); + function_id = mlx5_sf_start_function_id(dev); /* Arm the vhca context as the vhca event notifier */ for (i = 0; i < max_functions; i++) { err = mlx5_vhca_event_arm(dev, function_id); @@ -234,7 +234,7 @@ static void mlx5_sf_dev_add_active_work(struct work_struct *work) int i; max_functions = mlx5_sf_max_functions(dev); - function_id = MLX5_CAP_GEN(dev, sf_base_id); + function_id = mlx5_sf_start_function_id(dev); for (i = 0; i < max_functions; i++, function_id++) { if (table->stop_active_wq) return; @@ -299,7 +299,7 @@ void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) unsigned int max_sfs; int err; - if (!mlx5_sf_dev_supported(dev) || !mlx5_vhca_event_supported(dev)) + if (!mlx5_sf_dev_supported(dev)) return; table = kzalloc(sizeof(*table), GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c index 17aa348989cb..1f613320fe07 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c @@ -9,6 +9,7 @@ #include "mlx5_core.h" #include "eswitch.h" #include "diag/sf_tracepoint.h" +#include "devlink.h" struct mlx5_sf_hw { u32 usr_sfnum; @@ -243,31 +244,61 @@ static void mlx5_sf_hw_table_hwc_cleanup(struct mlx5_sf_hwc_table *hwc) kfree(hwc->sfs); } +static void mlx5_sf_hw_table_res_unregister(struct mlx5_core_dev *dev) +{ + devl_resources_unregister(priv_to_devlink(dev)); +} + +static int mlx5_sf_hw_table_res_register(struct mlx5_core_dev *dev, u16 max_fn, + u16 max_ext_fn) +{ + struct devlink_resource_size_params size_params; + struct devlink *devlink = priv_to_devlink(dev); + int err; + + devlink_resource_size_params_init(&size_params, max_fn, max_fn, 1, + DEVLINK_RESOURCE_UNIT_ENTRY); + err = devl_resource_register(devlink, "max_local_SFs", max_fn, MLX5_DL_RES_MAX_LOCAL_SFS, + DEVLINK_RESOURCE_ID_PARENT_TOP, &size_params); + if (err) + return err; + + devlink_resource_size_params_init(&size_params, max_ext_fn, max_ext_fn, 1, + DEVLINK_RESOURCE_UNIT_ENTRY); + return devl_resource_register(devlink, "max_external_SFs", max_ext_fn, + MLX5_DL_RES_MAX_EXTERNAL_SFS, DEVLINK_RESOURCE_ID_PARENT_TOP, + &size_params); +} + int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev) { struct mlx5_sf_hw_table *table; u16 max_ext_fn = 0; u16 ext_base_id = 0; - u16 max_fn = 0; u16 base_id; + u16 max_fn; int err; if (!mlx5_vhca_event_supported(dev)) return 0; - if (mlx5_sf_supported(dev)) - max_fn = mlx5_sf_max_functions(dev); + max_fn = mlx5_sf_max_functions(dev); err = mlx5_esw_sf_max_hpf_functions(dev, &max_ext_fn, &ext_base_id); if (err) return err; + if (mlx5_sf_hw_table_res_register(dev, max_fn, max_ext_fn)) + mlx5_core_dbg(dev, "failed to register max SFs resources"); + if (!max_fn && !max_ext_fn) return 0; table = kzalloc(sizeof(*table), GFP_KERNEL); - if (!table) - return -ENOMEM; + if (!table) { + err = -ENOMEM; + goto alloc_err; + } mutex_init(&table->table_lock); table->dev = dev; @@ -291,6 +322,8 @@ ext_err: table_err: mutex_destroy(&table->table_lock); kfree(table); +alloc_err: + mlx5_sf_hw_table_res_unregister(dev); return err; } @@ -299,12 +332,14 @@ void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev) struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table; if (!table) - return; + goto res_unregister; - mutex_destroy(&table->table_lock); mlx5_sf_hw_table_hwc_cleanup(&table->hwc[MLX5_SF_HWC_EXTERNAL]); mlx5_sf_hw_table_hwc_cleanup(&table->hwc[MLX5_SF_HWC_LOCAL]); + mutex_destroy(&table->table_lock); kfree(table); +res_unregister: + mlx5_sf_hw_table_res_unregister(dev); } static int mlx5_sf_hw_vhca_event(struct notifier_block *nb, unsigned long opcode, void *data) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index 9dfe7148199f..faa63ea9b83e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -1887,6 +1887,46 @@ int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid, } EXPORT_SYMBOL(mlxsw_afa_block_append_fid_set); +/* Ignore Action + * ------------- + * The ignore action is used to ignore basic switching functions such as + * learning on a per-packet basis. + */ + +#define MLXSW_AFA_IGNORE_CODE 0x0F +#define MLXSW_AFA_IGNORE_SIZE 1 + +/* afa_ignore_disable_learning + * Disable learning on ingress. + */ +MLXSW_ITEM32(afa, ignore, disable_learning, 0x00, 29, 1); + +/* afa_ignore_disable_security + * Disable security lookup on ingress. + * Reserved when Spectrum-1. + */ +MLXSW_ITEM32(afa, ignore, disable_security, 0x00, 28, 1); + +static void mlxsw_afa_ignore_pack(char *payload, bool disable_learning, + bool disable_security) +{ + mlxsw_afa_ignore_disable_learning_set(payload, disable_learning); + mlxsw_afa_ignore_disable_security_set(payload, disable_security); +} + +int mlxsw_afa_block_append_ignore(struct mlxsw_afa_block *block, + bool disable_learning, bool disable_security) +{ + char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_IGNORE_CODE, + MLXSW_AFA_IGNORE_SIZE); + + if (IS_ERR(act)) + return PTR_ERR(act); + mlxsw_afa_ignore_pack(act, disable_learning, disable_security); + return 0; +} +EXPORT_SYMBOL(mlxsw_afa_block_append_ignore); + /* MC Routing Action * ----------------- * The Multicast router action. Can be used by RMFT_V2 - Router Multicast diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h index db58037be46e..0ead3a212de8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h @@ -89,6 +89,8 @@ int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block, struct netlink_ext_ack *extack); int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid, struct netlink_ext_ack *extack); +int mlxsw_afa_block_append_ignore(struct mlxsw_afa_block *block, + bool disable_learning, bool disable_security); int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block, u16 expected_irif, u16 min_mtu, bool rmid_valid, u32 kvdl_index); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 8da7bb04fc3a..02ca2871b6f9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -1050,6 +1050,9 @@ int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp, int mlxsw_sp_acl_rulei_act_fid_set(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, u16 fid, struct netlink_ext_ack *extack); +int mlxsw_sp_acl_rulei_act_ignore(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei, + bool disable_learning, bool disable_security); int mlxsw_sp_acl_rulei_act_sample(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, struct mlxsw_sp_flow_block *block, @@ -1268,7 +1271,6 @@ int mlxsw_sp_setup_tc_block_qevent_mark(struct mlxsw_sp_port *mlxsw_sp_port, struct flow_block_offload *f); /* spectrum_fid.c */ -bool mlxsw_sp_fid_is_dummy(struct mlxsw_sp *mlxsw_sp, u16 fid_index); struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_index(struct mlxsw_sp *mlxsw_sp, u16 fid_index); int mlxsw_sp_fid_nve_ifindex(const struct mlxsw_sp_fid *fid, int *nve_ifindex); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 186161a3459d..7c59c8a13584 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -775,6 +775,15 @@ int mlxsw_sp_acl_rulei_act_fid_set(struct mlxsw_sp *mlxsw_sp, return mlxsw_afa_block_append_fid_set(rulei->act_block, fid, extack); } +int mlxsw_sp_acl_rulei_act_ignore(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei, + bool disable_learning, bool disable_security) +{ + return mlxsw_afa_block_append_ignore(rulei->act_block, + disable_learning, + disable_security); +} + int mlxsw_sp_acl_rulei_act_sample(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, struct mlxsw_sp_flow_block *block, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c index b6ee2d658b0c..9df098474743 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c @@ -137,16 +137,6 @@ static const int *mlxsw_sp_packet_type_sfgc_types[] = { [MLXSW_SP_FLOOD_TYPE_MC] = mlxsw_sp_sfgc_mc_packet_types, }; -bool mlxsw_sp_fid_is_dummy(struct mlxsw_sp *mlxsw_sp, u16 fid_index) -{ - enum mlxsw_sp_fid_type fid_type = MLXSW_SP_FID_TYPE_DUMMY; - struct mlxsw_sp_fid_family *fid_family; - - fid_family = mlxsw_sp->fid_core->fid_family_arr[fid_type]; - - return fid_family->start_index == fid_index; -} - struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_index(struct mlxsw_sp *mlxsw_sp, u16 fid_index) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index af3f57d017ec..9fd1ca079258 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -160,6 +160,16 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, */ rulei->egress_bind_blocker = 1; + /* Ignore learning and security lookup as redirection + * using ingress filters happens before the bridge. + */ + err = mlxsw_sp_acl_rulei_act_ignore(mlxsw_sp, rulei, + true, true); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Cannot append ignore action"); + return err; + } + fid = mlxsw_sp_acl_dummy_fid(mlxsw_sp); fid_index = mlxsw_sp_fid_index(fid); err = mlxsw_sp_acl_rulei_act_fid_set(mlxsw_sp, rulei, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 3662b9da5489..6c749c148148 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -3066,9 +3066,6 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, goto just_remove; } - if (mlxsw_sp_fid_is_dummy(mlxsw_sp, fid)) - goto just_remove; - mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_fid(mlxsw_sp_port, fid); if (!mlxsw_sp_port_vlan) { netdev_err(mlxsw_sp_port->dev, "Failed to find a matching {Port, VID} following FDB notification\n"); @@ -3136,9 +3133,6 @@ static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp, goto just_remove; } - if (mlxsw_sp_fid_is_dummy(mlxsw_sp, fid)) - goto just_remove; - mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_fid(mlxsw_sp_port, fid); if (!mlxsw_sp_port_vlan) { netdev_err(mlxsw_sp_port->dev, "Failed to find a matching {Port, VID} following FDB notification\n"); diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 48f330d59284..4a16ebff3d1d 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -2295,6 +2295,46 @@ int mana_config_rss(struct mana_port_context *apc, enum TRI_STATE rx, return 0; } +void mana_query_gf_stats(struct mana_port_context *apc) +{ + struct mana_query_gf_stat_resp resp = {}; + struct mana_query_gf_stat_req req = {}; + struct net_device *ndev = apc->ndev; + int err; + + mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_GF_STAT, + sizeof(req), sizeof(resp)); + req.req_stats = STATISTICS_FLAGS_HC_TX_BYTES | + STATISTICS_FLAGS_HC_TX_UCAST_PACKETS | + STATISTICS_FLAGS_HC_TX_UCAST_BYTES | + STATISTICS_FLAGS_HC_TX_MCAST_PACKETS | + STATISTICS_FLAGS_HC_TX_MCAST_BYTES | + STATISTICS_FLAGS_HC_TX_BCAST_PACKETS | + STATISTICS_FLAGS_HC_TX_BCAST_BYTES; + + err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + sizeof(resp)); + if (err) { + netdev_err(ndev, "Failed to query GF stats: %d\n", err); + return; + } + err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_GF_STAT, + sizeof(resp)); + if (err || resp.hdr.status) { + netdev_err(ndev, "Failed to query GF stats: %d, 0x%x\n", err, + resp.hdr.status); + return; + } + + apc->eth_stats.hc_tx_bytes = resp.hc_tx_bytes; + apc->eth_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts; + apc->eth_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes; + apc->eth_stats.hc_tx_bcast_pkts = resp.hc_tx_bcast_pkts; + apc->eth_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes; + apc->eth_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts; + apc->eth_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes; +} + static int mana_init_port(struct net_device *ndev) { struct mana_port_context *apc = netdev_priv(ndev); diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index 0dc78679f620..607150165ab4 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -13,6 +13,19 @@ static const struct { } mana_eth_stats[] = { {"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)}, {"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)}, + {"hc_tx_bytes", offsetof(struct mana_ethtool_stats, hc_tx_bytes)}, + {"hc_tx_ucast_pkts", offsetof(struct mana_ethtool_stats, + hc_tx_ucast_pkts)}, + {"hc_tx_ucast_bytes", offsetof(struct mana_ethtool_stats, + hc_tx_ucast_bytes)}, + {"hc_tx_bcast_pkts", offsetof(struct mana_ethtool_stats, + hc_tx_bcast_pkts)}, + {"hc_tx_bcast_bytes", offsetof(struct mana_ethtool_stats, + hc_tx_bcast_bytes)}, + {"hc_tx_mcast_pkts", offsetof(struct mana_ethtool_stats, + hc_tx_mcast_pkts)}, + {"hc_tx_mcast_bytes", offsetof(struct mana_ethtool_stats, + hc_tx_mcast_bytes)}, {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, tx_cqe_unknown_type)}, @@ -114,6 +127,8 @@ static void mana_get_ethtool_stats(struct net_device *ndev, if (!apc->port_is_up) return; + /* we call mana function to update stats from GDMA */ + mana_query_gf_stats(apc); for (q = 0; q < ARRAY_SIZE(mana_eth_stats); q++) data[i++] = *(u64 *)(eth_stats + mana_eth_stats[q].offset); diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 7b0e390c0b07..0e265ed1f501 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -60,7 +60,7 @@ static void qed_vf_pf_req_end(struct qed_hwfn *p_hwfn, int req_status) #define QED_VF_CHANNEL_MSLEEP_ITERATIONS 10 #define QED_VF_CHANNEL_MSLEEP_DELAY 25 -static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size) +static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done) { union vfpf_tlvs *p_req = p_hwfn->vf_iov_info->vf2pf_request; struct ustorm_trigger_vf_zone trigger; @@ -72,9 +72,6 @@ static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size) /* output tlvs list */ qed_dp_tlv_list(p_hwfn, p_req); - /* need to add the END TLV to the message size */ - resp_size += sizeof(struct channel_list_end_tlv); - /* Send TLVs over HW channel */ memset(&trigger, 0, sizeof(struct ustorm_trigger_vf_zone)); trigger.vf_pf_msg_valid = 1; @@ -172,7 +169,7 @@ static int _qed_vf_pf_release(struct qed_hwfn *p_hwfn, bool b_final) CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv)); resp = &p_iov->pf2vf_reply->default_resp; - rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status); if (!rc && resp->hdr.status != PFVF_STATUS_SUCCESS) rc = -EAGAIN; @@ -301,7 +298,7 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn) memset(p_iov->pf2vf_reply, 0, sizeof(union pfvf_tlvs)); /* send acquire request */ - rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status); /* Re-try acquire in case of vf-pf hw channel timeout */ if (retry_cnt && rc == -EBUSY) { @@ -705,7 +702,7 @@ int qed_vf_pf_tunnel_param_update(struct qed_hwfn *p_hwfn, sizeof(struct channel_list_end_tlv)); p_resp = &p_iov->pf2vf_reply->tunn_param_resp; - rc = qed_send_msg2pf(p_hwfn, &p_resp->hdr.status, sizeof(*p_resp)); + rc = qed_send_msg2pf(p_hwfn, &p_resp->hdr.status); if (rc) goto exit; @@ -772,7 +769,7 @@ qed_vf_pf_rxq_start(struct qed_hwfn *p_hwfn, CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv)); resp = &p_iov->pf2vf_reply->queue_start; - rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status); if (rc) goto exit; @@ -822,7 +819,7 @@ int qed_vf_pf_rxq_stop(struct qed_hwfn *p_hwfn, CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv)); resp = &p_iov->pf2vf_reply->default_resp; - rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status); if (rc) goto exit; @@ -867,7 +864,7 @@ qed_vf_pf_txq_start(struct qed_hwfn *p_hwfn, CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv)); resp = &p_iov->pf2vf_reply->queue_start; - rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status); if (rc) goto exit; @@ -918,7 +915,7 @@ int qed_vf_pf_txq_stop(struct qed_hwfn *p_hwfn, struct qed_queue_cid *p_cid) CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv)); resp = &p_iov->pf2vf_reply->default_resp; - rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status); if (rc) goto exit; @@ -968,7 +965,7 @@ int qed_vf_pf_vport_start(struct qed_hwfn *p_hwfn, CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv)); resp = &p_iov->pf2vf_reply->default_resp; - rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status); if (rc) goto exit; @@ -997,7 +994,7 @@ int qed_vf_pf_vport_stop(struct qed_hwfn *p_hwfn) qed_add_tlv(p_hwfn, &p_iov->offset, CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv)); - rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status); if (rc) goto exit; @@ -1075,12 +1072,10 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn, struct vfpf_vport_update_tlv *req; struct pfvf_def_resp_tlv *resp; u8 update_rx, update_tx; - u32 resp_size = 0; u16 size, tlv; int rc; resp = &p_iov->pf2vf_reply->default_resp; - resp_size = sizeof(*resp); update_rx = p_params->update_vport_active_rx_flg; update_tx = p_params->update_vport_active_tx_flg; @@ -1096,7 +1091,6 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn, p_act_tlv = qed_add_tlv(p_hwfn, &p_iov->offset, CHANNEL_TLV_VPORT_UPDATE_ACTIVATE, size); - resp_size += sizeof(struct pfvf_def_resp_tlv); if (update_rx) { p_act_tlv->update_rx = update_rx; @@ -1116,7 +1110,6 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn, tlv = CHANNEL_TLV_VPORT_UPDATE_TX_SWITCH; p_tx_switch_tlv = qed_add_tlv(p_hwfn, &p_iov->offset, tlv, size); - resp_size += sizeof(struct pfvf_def_resp_tlv); p_tx_switch_tlv->tx_switching = p_params->tx_switching_flg; } @@ -1127,7 +1120,6 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn, size = sizeof(struct vfpf_vport_update_mcast_bin_tlv); p_mcast_tlv = qed_add_tlv(p_hwfn, &p_iov->offset, CHANNEL_TLV_VPORT_UPDATE_MCAST, size); - resp_size += sizeof(struct pfvf_def_resp_tlv); memcpy(p_mcast_tlv->bins, p_params->bins, sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS); @@ -1142,7 +1134,6 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn, tlv = CHANNEL_TLV_VPORT_UPDATE_ACCEPT_PARAM; size = sizeof(struct vfpf_vport_update_accept_param_tlv); p_accept_tlv = qed_add_tlv(p_hwfn, &p_iov->offset, tlv, size); - resp_size += sizeof(struct pfvf_def_resp_tlv); if (update_rx) { p_accept_tlv->update_rx_mode = update_rx; @@ -1166,7 +1157,6 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn, p_rss_tlv = qed_add_tlv(p_hwfn, &p_iov->offset, CHANNEL_TLV_VPORT_UPDATE_RSS, size); - resp_size += sizeof(struct pfvf_def_resp_tlv); if (rss_params->update_rss_config) p_rss_tlv->update_rss_flags |= @@ -1203,7 +1193,6 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn, tlv = CHANNEL_TLV_VPORT_UPDATE_ACCEPT_ANY_VLAN; p_any_vlan_tlv = qed_add_tlv(p_hwfn, &p_iov->offset, tlv, size); - resp_size += sizeof(struct pfvf_def_resp_tlv); p_any_vlan_tlv->accept_any_vlan = p_params->accept_any_vlan; p_any_vlan_tlv->update_accept_any_vlan_flg = p_params->update_accept_any_vlan_flg; @@ -1213,7 +1202,7 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn, qed_add_tlv(p_hwfn, &p_iov->offset, CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv)); - rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, resp_size); + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status); if (rc) goto exit; @@ -1245,7 +1234,7 @@ int qed_vf_pf_reset(struct qed_hwfn *p_hwfn) CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv)); resp = &p_iov->pf2vf_reply->default_resp; - rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status); if (rc) goto exit; @@ -1303,7 +1292,7 @@ int qed_vf_pf_filter_ucast(struct qed_hwfn *p_hwfn, CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv)); resp = &p_iov->pf2vf_reply->default_resp; - rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status); if (rc) goto exit; @@ -1332,7 +1321,7 @@ int qed_vf_pf_int_cleanup(struct qed_hwfn *p_hwfn) qed_add_tlv(p_hwfn, &p_iov->offset, CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv)); - rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status); if (rc) goto exit; @@ -1364,7 +1353,7 @@ int qed_vf_pf_get_coalesce(struct qed_hwfn *p_hwfn, sizeof(struct channel_list_end_tlv)); resp = &p_iov->pf2vf_reply->read_coal_resp; - rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status); if (rc) goto exit; @@ -1402,7 +1391,7 @@ qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, sizeof(struct channel_list_end_tlv)); p_resp = &p_iov->pf2vf_reply->default_resp; - rc = qed_send_msg2pf(p_hwfn, &p_resp->hdr.status, sizeof(*p_resp)); + rc = qed_send_msg2pf(p_hwfn, &p_resp->hdr.status); qed_vf_pf_req_end(p_hwfn, rc); return rc; } @@ -1433,7 +1422,7 @@ qed_vf_pf_set_coalesce(struct qed_hwfn *p_hwfn, sizeof(struct channel_list_end_tlv)); resp = &p_iov->pf2vf_reply->default_resp; - rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status); if (rc) goto exit; diff --git a/drivers/net/ethernet/qualcomm/qca_uart.c b/drivers/net/ethernet/qualcomm/qca_uart.c index ace99c62d03a..9adec91f35e9 100644 --- a/drivers/net/ethernet/qualcomm/qca_uart.c +++ b/drivers/net/ethernet/qualcomm/qca_uart.c @@ -403,7 +403,7 @@ static struct serdev_device_driver qca_uart_driver = { .remove = qca_uart_remove, .driver = { .name = QCAUART_DRV_NAME, - .of_match_table = of_match_ptr(qca_uart_of_match), + .of_match_table = qca_uart_of_match, }, }; diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c index 3b26f1d86beb..e1c4a11c1f18 100644 --- a/drivers/net/ethernet/smsc/smsc9420.c +++ b/drivers/net/ethernet/smsc/smsc9420.c @@ -1144,8 +1144,7 @@ static int smsc9420_mii_init(struct net_device *dev) goto err_out_1; } pd->mii_bus->name = DRV_MDIONAME; - snprintf(pd->mii_bus->id, MII_BUS_ID_SIZE, "%x", - (pd->pdev->bus->number << 8) | pd->pdev->devfn); + snprintf(pd->mii_bus->id, MII_BUS_ID_SIZE, "%x", pci_dev_id(pd->pdev)); pd->mii_bus->priv = pd; pd->mii_bus->read = smsc9420_mii_read; pd->mii_bus->write = smsc9420_mii_write; diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index c67171975d5c..1f5293c8cc04 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -438,6 +438,8 @@ struct dma_features { unsigned int tbssel; /* Numbers of Auxiliary Snapshot Inputs */ unsigned int aux_snapshot_n; + /* Timestamp System Time Source */ + unsigned int tssrc; }; /* RX Buffer size must be multiple of 4/8/16 bytes */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index ce67b178c2d5..7f68bef456b7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -123,6 +123,8 @@ #define XGMAC_LPI_TIMER_CTRL 0x000000d4 #define XGMAC_HW_FEATURE0 0x0000011c #define XGMAC_HWFEAT_SAVLANINS BIT(27) +#define XGMAC_HWFEAT_TSSTSSEL GENMASK(26, 25) +#define XGMAC_HWFEAT_ADDMACADRSEL GENMASK(22, 18) #define XGMAC_HWFEAT_RXCOESEL BIT(16) #define XGMAC_HWFEAT_TXCOESEL BIT(14) #define XGMAC_HWFEAT_EEESEL BIT(13) @@ -133,7 +135,9 @@ #define XGMAC_HWFEAT_MMCSEL BIT(8) #define XGMAC_HWFEAT_MGKSEL BIT(7) #define XGMAC_HWFEAT_RWKSEL BIT(6) +#define XGMAC_HWFEAT_SMASEL BIT(5) #define XGMAC_HWFEAT_VLHASH BIT(4) +#define XGMAC_HWFEAT_HDSEL BIT(3) #define XGMAC_HWFEAT_GMIISEL BIT(1) #define XGMAC_HW_FEATURE1 0x00000120 #define XGMAC_HWFEAT_L3L4FNUM GENMASK(30, 27) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index b09395f5edcb..3aacf791efeb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -391,9 +391,11 @@ static int dwxgmac2_get_hw_feature(void __iomem *ioaddr, { u32 hw_cap; - /* MAC HW feature 0 */ + /* MAC HW feature 0 */ hw_cap = readl(ioaddr + XGMAC_HW_FEATURE0); dma_cap->vlins = (hw_cap & XGMAC_HWFEAT_SAVLANINS) >> 27; + dma_cap->tssrc = (hw_cap & XGMAC_HWFEAT_TSSTSSEL) >> 25; + dma_cap->multi_addr = (hw_cap & XGMAC_HWFEAT_ADDMACADRSEL) >> 18; dma_cap->rx_coe = (hw_cap & XGMAC_HWFEAT_RXCOESEL) >> 16; dma_cap->tx_coe = (hw_cap & XGMAC_HWFEAT_TXCOESEL) >> 14; dma_cap->eee = (hw_cap & XGMAC_HWFEAT_EEESEL) >> 13; @@ -404,7 +406,9 @@ static int dwxgmac2_get_hw_feature(void __iomem *ioaddr, dma_cap->rmon = (hw_cap & XGMAC_HWFEAT_MMCSEL) >> 8; dma_cap->pmt_magic_frame = (hw_cap & XGMAC_HWFEAT_MGKSEL) >> 7; dma_cap->pmt_remote_wake_up = (hw_cap & XGMAC_HWFEAT_RWKSEL) >> 6; + dma_cap->sma_mdio = (hw_cap & XGMAC_HWFEAT_SMASEL) >> 5; dma_cap->vlhash = (hw_cap & XGMAC_HWFEAT_VLHASH) >> 4; + dma_cap->half_duplex = (hw_cap & XGMAC_HWFEAT_HDSEL) >> 3; dma_cap->mbps_1000 = (hw_cap & XGMAC_HWFEAT_GMIISEL) >> 1; /* MAC HW feature 1 */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 351eca6109e0..733b5e900817 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -6237,6 +6237,12 @@ DEFINE_SHOW_ATTRIBUTE(stmmac_rings_status); static int stmmac_dma_cap_show(struct seq_file *seq, void *v) { + static const char * const dwxgmac_timestamp_source[] = { + "None", + "Internal", + "External", + "Both", + }; struct net_device *dev = seq->private; struct stmmac_priv *priv = netdev_priv(dev); @@ -6257,8 +6263,13 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v) (priv->dma_cap.half_duplex) ? "Y" : "N"); seq_printf(seq, "\tHash Filter: %s\n", (priv->dma_cap.hash_filter) ? "Y" : "N"); - seq_printf(seq, "\tMultiple MAC address registers: %s\n", - (priv->dma_cap.multi_addr) ? "Y" : "N"); + if (priv->plat->has_xgmac) + seq_printf(seq, + "\tNumber of Additional MAC address registers: %d\n", + priv->dma_cap.multi_addr); + else + seq_printf(seq, "\tMultiple MAC address registers: %s\n", + (priv->dma_cap.multi_addr) ? "Y" : "N"); seq_printf(seq, "\tPCS (TBI/SGMII/RTBI PHY interfaces): %s\n", (priv->dma_cap.pcs) ? "Y" : "N"); seq_printf(seq, "\tSMA (MDIO) Interface: %s\n", @@ -6273,12 +6284,16 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v) (priv->dma_cap.time_stamp) ? "Y" : "N"); seq_printf(seq, "\tIEEE 1588-2008 Advanced Time Stamp: %s\n", (priv->dma_cap.atime_stamp) ? "Y" : "N"); + if (priv->plat->has_xgmac) + seq_printf(seq, "\tTimestamp System Time Source: %s\n", + dwxgmac_timestamp_source[priv->dma_cap.tssrc]); seq_printf(seq, "\t802.3az - Energy-Efficient Ethernet (EEE): %s\n", (priv->dma_cap.eee) ? "Y" : "N"); seq_printf(seq, "\tAV features: %s\n", (priv->dma_cap.av) ? "Y" : "N"); seq_printf(seq, "\tChecksum Offload in TX: %s\n", (priv->dma_cap.tx_coe) ? "Y" : "N"); - if (priv->synopsys_id >= DWMAC_CORE_4_00) { + if (priv->synopsys_id >= DWMAC_CORE_4_00 || + priv->plat->has_xgmac) { seq_printf(seq, "\tIP Checksum Offload in RX: %s\n", (priv->dma_cap.rx_coe) ? "Y" : "N"); } else { @@ -6286,9 +6301,9 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v) (priv->dma_cap.rx_coe_type1) ? "Y" : "N"); seq_printf(seq, "\tIP Checksum Offload (type2) in RX: %s\n", (priv->dma_cap.rx_coe_type2) ? "Y" : "N"); + seq_printf(seq, "\tRXFIFO > 2048bytes: %s\n", + (priv->dma_cap.rxfifo_over_2048) ? "Y" : "N"); } - seq_printf(seq, "\tRXFIFO > 2048bytes: %s\n", - (priv->dma_cap.rxfifo_over_2048) ? "Y" : "N"); seq_printf(seq, "\tNumber of Additional RX channel: %d\n", priv->dma_cap.number_rx_channel); seq_printf(seq, "\tNumber of Additional TX channel: %d\n", diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index 734a817d3c94..a9a6670b5ff1 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -124,7 +124,7 @@ static void vsw_set_rx_mode(struct net_device *dev) return sunvnet_set_rx_mode_common(dev, port->vp); } -int ldmvsw_open(struct net_device *dev) +static int ldmvsw_open(struct net_device *dev) { struct vnet_port *port = netdev_priv(dev); struct vio_driver_state *vio = &port->vio; @@ -136,7 +136,6 @@ int ldmvsw_open(struct net_device *dev) return 0; } -EXPORT_SYMBOL_GPL(ldmvsw_open); #ifdef CONFIG_NET_POLL_CONTROLLER static void vsw_poll_controller(struct net_device *dev) diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index b50be67b398b..14cf6ecf6d0d 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -667,8 +667,7 @@ static int tc_mii_init(struct net_device *dev) lp->mii_bus->name = "tc35815_mii_bus"; lp->mii_bus->read = tc_mdio_read; lp->mii_bus->write = tc_mdio_write; - snprintf(lp->mii_bus->id, MII_BUS_ID_SIZE, "%x", - (lp->pci_dev->bus->number << 8) | lp->pci_dev->devfn); + snprintf(lp->mii_bus->id, MII_BUS_ID_SIZE, "%x", pci_dev_id(lp->pci_dev)); lp->mii_bus->priv = dev; lp->mii_bus->parent = &lp->pci_dev->dev; err = mdiobus_register(lp->mii_bus); diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c index cc2f325a52f7..fe20f02ecb3a 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c @@ -266,8 +266,7 @@ int ngbe_mdio_init(struct wx *wx) mii_bus->write_c45 = ngbe_phy_write_reg_mdi_c45; } - snprintf(mii_bus->id, MII_BUS_ID_SIZE, "ngbe-%x", - (pdev->bus->number << 8) | pdev->devfn); + snprintf(mii_bus->id, MII_BUS_ID_SIZE, "ngbe-%x", pci_dev_id(pdev)); ret = devm_mdiobus_register(&pdev->dev, mii_bus); if (ret) return ret; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 144ec756c796..ae60817ec5c2 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -518,14 +518,8 @@ static void macsec_count_tx(struct sk_buff *skb, struct macsec_tx_sc *tx_sc, static void count_tx(struct net_device *dev, int ret, int len) { - if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { - struct pcpu_sw_netstats *stats = this_cpu_ptr(dev->tstats); - - u64_stats_update_begin(&stats->syncp); - u64_stats_inc(&stats->tx_packets); - u64_stats_add(&stats->tx_bytes, len); - u64_stats_update_end(&stats->syncp); - } + if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) + dev_sw_netstats_tx_add(dev, 1, len); } static void macsec_encrypt_done(void *data, int err) @@ -827,12 +821,7 @@ static void macsec_finalize_skb(struct sk_buff *skb, u8 icv_len, u8 hdr_len) static void count_rx(struct net_device *dev, int len) { - struct pcpu_sw_netstats *stats = this_cpu_ptr(dev->tstats); - - u64_stats_update_begin(&stats->syncp); - u64_stats_inc(&stats->rx_packets); - u64_stats_add(&stats->rx_bytes, len); - u64_stats_update_end(&stats->syncp); + dev_sw_netstats_rx_add(dev, len); } static void macsec_decrypt_done(void *data, int err) diff --git a/drivers/net/pcs/pcs-lynx.c b/drivers/net/pcs/pcs-lynx.c index 9021b96d4f9d..dc3962b2aa6b 100644 --- a/drivers/net/pcs/pcs-lynx.c +++ b/drivers/net/pcs/pcs-lynx.c @@ -216,7 +216,7 @@ static void lynx_pcs_link_up_sgmii(struct mdio_device *pcs, /* The PCS needs to be configured manually only * when not operating on in-band mode */ - if (neg_mode != PHYLINK_PCS_NEG_INBAND_ENABLED) + if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED) return; if (duplex == DUPLEX_HALF) diff --git a/drivers/net/phy/mediatek-ge-soc.c b/drivers/net/phy/mediatek-ge-soc.c index da512fab0eb0..8a20d9889f10 100644 --- a/drivers/net/phy/mediatek-ge-soc.c +++ b/drivers/net/phy/mediatek-ge-soc.c @@ -1,9 +1,12 @@ // SPDX-License-Identifier: GPL-2.0+ #include <linux/bitfield.h> +#include <linux/bitmap.h> +#include <linux/mfd/syscon.h> #include <linux/module.h> #include <linux/nvmem-consumer.h> #include <linux/pinctrl/consumer.h> #include <linux/phy.h> +#include <linux/regmap.h> #define MTK_GPHY_ID_MT7981 0x03a29461 #define MTK_GPHY_ID_MT7988 0x03a29481 @@ -206,9 +209,42 @@ #define MTK_PHY_DA_TX_R50_PAIR_C 0x53f #define MTK_PHY_DA_TX_R50_PAIR_D 0x540 +/* Registers on MDIO_MMD_VEND2 */ +#define MTK_PHY_LED0_ON_CTRL 0x24 +#define MTK_PHY_LED1_ON_CTRL 0x26 +#define MTK_PHY_LED_ON_MASK GENMASK(6, 0) +#define MTK_PHY_LED_ON_LINK1000 BIT(0) +#define MTK_PHY_LED_ON_LINK100 BIT(1) +#define MTK_PHY_LED_ON_LINK10 BIT(2) +#define MTK_PHY_LED_ON_LINKDOWN BIT(3) +#define MTK_PHY_LED_ON_FDX BIT(4) /* Full duplex */ +#define MTK_PHY_LED_ON_HDX BIT(5) /* Half duplex */ +#define MTK_PHY_LED_ON_FORCE_ON BIT(6) +#define MTK_PHY_LED_ON_POLARITY BIT(14) +#define MTK_PHY_LED_ON_ENABLE BIT(15) + +#define MTK_PHY_LED0_BLINK_CTRL 0x25 +#define MTK_PHY_LED1_BLINK_CTRL 0x27 +#define MTK_PHY_LED_BLINK_1000TX BIT(0) +#define MTK_PHY_LED_BLINK_1000RX BIT(1) +#define MTK_PHY_LED_BLINK_100TX BIT(2) +#define MTK_PHY_LED_BLINK_100RX BIT(3) +#define MTK_PHY_LED_BLINK_10TX BIT(4) +#define MTK_PHY_LED_BLINK_10RX BIT(5) +#define MTK_PHY_LED_BLINK_COLLISION BIT(6) +#define MTK_PHY_LED_BLINK_RX_CRC_ERR BIT(7) +#define MTK_PHY_LED_BLINK_RX_IDLE_ERR BIT(8) +#define MTK_PHY_LED_BLINK_FORCE_BLINK BIT(9) + +#define MTK_PHY_LED1_DEFAULT_POLARITIES BIT(1) + #define MTK_PHY_RG_BG_RASEL 0x115 #define MTK_PHY_RG_BG_RASEL_MASK GENMASK(2, 0) +/* 'boottrap' register reflecting the configuration of the 4 PHY LEDs */ +#define RG_GPIO_MISC_TPBANK0 0x6f0 +#define RG_GPIO_MISC_TPBANK0_BOOTMODE GENMASK(11, 8) + /* These macro privides efuse parsing for internal phy. */ #define EFS_DA_TX_I2MPB_A(x) (((x) >> 0) & GENMASK(5, 0)) #define EFS_DA_TX_I2MPB_B(x) (((x) >> 6) & GENMASK(5, 0)) @@ -236,13 +272,6 @@ enum { PAIR_D, }; -enum { - GPHY_PORT0, - GPHY_PORT1, - GPHY_PORT2, - GPHY_PORT3, -}; - enum calibration_mode { EFUSE_K, SW_K @@ -261,6 +290,19 @@ enum CAL_MODE { SW_M }; +#define MTK_PHY_LED_STATE_FORCE_ON 0 +#define MTK_PHY_LED_STATE_FORCE_BLINK 1 +#define MTK_PHY_LED_STATE_NETDEV 2 + +struct mtk_socphy_priv { + unsigned long led_state; +}; + +struct mtk_socphy_shared { + u32 boottrap; + struct mtk_socphy_priv priv[4]; +}; + static int mtk_socphy_read_page(struct phy_device *phydev) { return __phy_read(phydev, MTK_EXT_PAGE_ACCESS); @@ -1071,6 +1113,371 @@ static int mt798x_phy_config_init(struct phy_device *phydev) return mt798x_phy_calibration(phydev); } +static int mt798x_phy_hw_led_on_set(struct phy_device *phydev, u8 index, + bool on) +{ + unsigned int bit_on = MTK_PHY_LED_STATE_FORCE_ON + (index ? 16 : 0); + struct mtk_socphy_priv *priv = phydev->priv; + bool changed; + + if (on) + changed = !test_and_set_bit(bit_on, &priv->led_state); + else + changed = !!test_and_clear_bit(bit_on, &priv->led_state); + + changed |= !!test_and_clear_bit(MTK_PHY_LED_STATE_NETDEV + + (index ? 16 : 0), &priv->led_state); + if (changed) + return phy_modify_mmd(phydev, MDIO_MMD_VEND2, index ? + MTK_PHY_LED1_ON_CTRL : MTK_PHY_LED0_ON_CTRL, + MTK_PHY_LED_ON_MASK, + on ? MTK_PHY_LED_ON_FORCE_ON : 0); + else + return 0; +} + +static int mt798x_phy_hw_led_blink_set(struct phy_device *phydev, u8 index, + bool blinking) +{ + unsigned int bit_blink = MTK_PHY_LED_STATE_FORCE_BLINK + (index ? 16 : 0); + struct mtk_socphy_priv *priv = phydev->priv; + bool changed; + + if (blinking) + changed = !test_and_set_bit(bit_blink, &priv->led_state); + else + changed = !!test_and_clear_bit(bit_blink, &priv->led_state); + + changed |= !!test_bit(MTK_PHY_LED_STATE_NETDEV + + (index ? 16 : 0), &priv->led_state); + if (changed) + return phy_write_mmd(phydev, MDIO_MMD_VEND2, index ? + MTK_PHY_LED1_BLINK_CTRL : MTK_PHY_LED0_BLINK_CTRL, + blinking ? MTK_PHY_LED_BLINK_FORCE_BLINK : 0); + else + return 0; +} + +static int mt798x_phy_led_blink_set(struct phy_device *phydev, u8 index, + unsigned long *delay_on, + unsigned long *delay_off) +{ + bool blinking = false; + int err = 0; + + if (index > 1) + return -EINVAL; + + if (delay_on && delay_off && (*delay_on > 0) && (*delay_off > 0)) { + blinking = true; + *delay_on = 50; + *delay_off = 50; + } + + err = mt798x_phy_hw_led_blink_set(phydev, index, blinking); + if (err) + return err; + + return mt798x_phy_hw_led_on_set(phydev, index, false); +} + +static int mt798x_phy_led_brightness_set(struct phy_device *phydev, + u8 index, enum led_brightness value) +{ + int err; + + err = mt798x_phy_hw_led_blink_set(phydev, index, false); + if (err) + return err; + + return mt798x_phy_hw_led_on_set(phydev, index, (value != LED_OFF)); +} + +static const unsigned long supported_triggers = (BIT(TRIGGER_NETDEV_FULL_DUPLEX) | + BIT(TRIGGER_NETDEV_HALF_DUPLEX) | + BIT(TRIGGER_NETDEV_LINK) | + BIT(TRIGGER_NETDEV_LINK_10) | + BIT(TRIGGER_NETDEV_LINK_100) | + BIT(TRIGGER_NETDEV_LINK_1000) | + BIT(TRIGGER_NETDEV_RX) | + BIT(TRIGGER_NETDEV_TX)); + +static int mt798x_phy_led_hw_is_supported(struct phy_device *phydev, u8 index, + unsigned long rules) +{ + if (index > 1) + return -EINVAL; + + /* All combinations of the supported triggers are allowed */ + if (rules & ~supported_triggers) + return -EOPNOTSUPP; + + return 0; +}; + +static int mt798x_phy_led_hw_control_get(struct phy_device *phydev, u8 index, + unsigned long *rules) +{ + unsigned int bit_blink = MTK_PHY_LED_STATE_FORCE_BLINK + (index ? 16 : 0); + unsigned int bit_netdev = MTK_PHY_LED_STATE_NETDEV + (index ? 16 : 0); + unsigned int bit_on = MTK_PHY_LED_STATE_FORCE_ON + (index ? 16 : 0); + struct mtk_socphy_priv *priv = phydev->priv; + int on, blink; + + if (index > 1) + return -EINVAL; + + on = phy_read_mmd(phydev, MDIO_MMD_VEND2, + index ? MTK_PHY_LED1_ON_CTRL : MTK_PHY_LED0_ON_CTRL); + + if (on < 0) + return -EIO; + + blink = phy_read_mmd(phydev, MDIO_MMD_VEND2, + index ? MTK_PHY_LED1_BLINK_CTRL : + MTK_PHY_LED0_BLINK_CTRL); + if (blink < 0) + return -EIO; + + if ((on & (MTK_PHY_LED_ON_LINK1000 | MTK_PHY_LED_ON_LINK100 | + MTK_PHY_LED_ON_LINK10)) || + (blink & (MTK_PHY_LED_BLINK_1000RX | MTK_PHY_LED_BLINK_100RX | + MTK_PHY_LED_BLINK_10RX | MTK_PHY_LED_BLINK_1000TX | + MTK_PHY_LED_BLINK_100TX | MTK_PHY_LED_BLINK_10TX))) + set_bit(bit_netdev, &priv->led_state); + else + clear_bit(bit_netdev, &priv->led_state); + + if (on & MTK_PHY_LED_ON_FORCE_ON) + set_bit(bit_on, &priv->led_state); + else + clear_bit(bit_on, &priv->led_state); + + if (blink & MTK_PHY_LED_BLINK_FORCE_BLINK) + set_bit(bit_blink, &priv->led_state); + else + clear_bit(bit_blink, &priv->led_state); + + if (!rules) + return 0; + + if (on & (MTK_PHY_LED_ON_LINK1000 | MTK_PHY_LED_ON_LINK100 | MTK_PHY_LED_ON_LINK10)) + *rules |= BIT(TRIGGER_NETDEV_LINK); + + if (on & MTK_PHY_LED_ON_LINK10) + *rules |= BIT(TRIGGER_NETDEV_LINK_10); + + if (on & MTK_PHY_LED_ON_LINK100) + *rules |= BIT(TRIGGER_NETDEV_LINK_100); + + if (on & MTK_PHY_LED_ON_LINK1000) + *rules |= BIT(TRIGGER_NETDEV_LINK_1000); + + if (on & MTK_PHY_LED_ON_FDX) + *rules |= BIT(TRIGGER_NETDEV_FULL_DUPLEX); + + if (on & MTK_PHY_LED_ON_HDX) + *rules |= BIT(TRIGGER_NETDEV_HALF_DUPLEX); + + if (blink & (MTK_PHY_LED_BLINK_1000RX | MTK_PHY_LED_BLINK_100RX | MTK_PHY_LED_BLINK_10RX)) + *rules |= BIT(TRIGGER_NETDEV_RX); + + if (blink & (MTK_PHY_LED_BLINK_1000TX | MTK_PHY_LED_BLINK_100TX | MTK_PHY_LED_BLINK_10TX)) + *rules |= BIT(TRIGGER_NETDEV_TX); + + return 0; +}; + +static int mt798x_phy_led_hw_control_set(struct phy_device *phydev, u8 index, + unsigned long rules) +{ + unsigned int bit_netdev = MTK_PHY_LED_STATE_NETDEV + (index ? 16 : 0); + struct mtk_socphy_priv *priv = phydev->priv; + u16 on = 0, blink = 0; + int ret; + + if (index > 1) + return -EINVAL; + + if (rules & BIT(TRIGGER_NETDEV_FULL_DUPLEX)) + on |= MTK_PHY_LED_ON_FDX; + + if (rules & BIT(TRIGGER_NETDEV_HALF_DUPLEX)) + on |= MTK_PHY_LED_ON_HDX; + + if (rules & (BIT(TRIGGER_NETDEV_LINK_10) | BIT(TRIGGER_NETDEV_LINK))) + on |= MTK_PHY_LED_ON_LINK10; + + if (rules & (BIT(TRIGGER_NETDEV_LINK_100) | BIT(TRIGGER_NETDEV_LINK))) + on |= MTK_PHY_LED_ON_LINK100; + + if (rules & (BIT(TRIGGER_NETDEV_LINK_1000) | BIT(TRIGGER_NETDEV_LINK))) + on |= MTK_PHY_LED_ON_LINK1000; + + if (rules & BIT(TRIGGER_NETDEV_RX)) { + blink |= MTK_PHY_LED_BLINK_10RX | + MTK_PHY_LED_BLINK_100RX | + MTK_PHY_LED_BLINK_1000RX; + } + + if (rules & BIT(TRIGGER_NETDEV_TX)) { + blink |= MTK_PHY_LED_BLINK_10TX | + MTK_PHY_LED_BLINK_100TX | + MTK_PHY_LED_BLINK_1000TX; + } + + if (blink || on) + set_bit(bit_netdev, &priv->led_state); + else + clear_bit(bit_netdev, &priv->led_state); + + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, index ? + MTK_PHY_LED1_ON_CTRL : + MTK_PHY_LED0_ON_CTRL, + MTK_PHY_LED_ON_FDX | + MTK_PHY_LED_ON_HDX | + MTK_PHY_LED_ON_LINK10 | + MTK_PHY_LED_ON_LINK100 | + MTK_PHY_LED_ON_LINK1000, + on); + + if (ret) + return ret; + + return phy_write_mmd(phydev, MDIO_MMD_VEND2, index ? + MTK_PHY_LED1_BLINK_CTRL : + MTK_PHY_LED0_BLINK_CTRL, blink); +}; + +static bool mt7988_phy_led_get_polarity(struct phy_device *phydev, int led_num) +{ + struct mtk_socphy_shared *priv = phydev->shared->priv; + u32 polarities; + + if (led_num == 0) + polarities = ~(priv->boottrap); + else + polarities = MTK_PHY_LED1_DEFAULT_POLARITIES; + + if (polarities & BIT(phydev->mdio.addr)) + return true; + + return false; +} + +static int mt7988_phy_fix_leds_polarities(struct phy_device *phydev) +{ + struct pinctrl *pinctrl; + int index; + + /* Setup LED polarity according to bootstrap use of LED pins */ + for (index = 0; index < 2; ++index) + phy_modify_mmd(phydev, MDIO_MMD_VEND2, index ? + MTK_PHY_LED1_ON_CTRL : MTK_PHY_LED0_ON_CTRL, + MTK_PHY_LED_ON_POLARITY, + mt7988_phy_led_get_polarity(phydev, index) ? + MTK_PHY_LED_ON_POLARITY : 0); + + /* Only now setup pinctrl to avoid bogus blinking */ + pinctrl = devm_pinctrl_get_select(&phydev->mdio.dev, "gbe-led"); + if (IS_ERR(pinctrl)) + dev_err(&phydev->mdio.bus->dev, "Failed to setup PHY LED pinctrl\n"); + + return 0; +} + +static int mt7988_phy_probe_shared(struct phy_device *phydev) +{ + struct device_node *np = dev_of_node(&phydev->mdio.bus->dev); + struct mtk_socphy_shared *shared = phydev->shared->priv; + struct regmap *regmap; + u32 reg; + int ret; + + /* The LED0 of the 4 PHYs in MT7988 are wired to SoC pins LED_A, LED_B, + * LED_C and LED_D respectively. At the same time those pins are used to + * bootstrap configuration of the reference clock source (LED_A), + * DRAM DDRx16b x2/x1 (LED_B) and boot device (LED_C, LED_D). + * In practise this is done using a LED and a resistor pulling the pin + * either to GND or to VIO. + * The detected value at boot time is accessible at run-time using the + * TPBANK0 register located in the gpio base of the pinctrl, in order + * to read it here it needs to be referenced by a phandle called + * 'mediatek,pio' in the MDIO bus hosting the PHY. + * The 4 bits in TPBANK0 are kept as package shared data and are used to + * set LED polarity for each of the LED0. + */ + regmap = syscon_regmap_lookup_by_phandle(np, "mediatek,pio"); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + ret = regmap_read(regmap, RG_GPIO_MISC_TPBANK0, ®); + if (ret) + return ret; + + shared->boottrap = FIELD_GET(RG_GPIO_MISC_TPBANK0_BOOTMODE, reg); + + return 0; +} + +static void mt798x_phy_leds_state_init(struct phy_device *phydev) +{ + int i; + + for (i = 0; i < 2; ++i) + mt798x_phy_led_hw_control_get(phydev, i, NULL); +} + +static int mt7988_phy_probe(struct phy_device *phydev) +{ + struct mtk_socphy_shared *shared; + struct mtk_socphy_priv *priv; + int err; + + if (phydev->mdio.addr > 3) + return -EINVAL; + + err = devm_phy_package_join(&phydev->mdio.dev, phydev, 0, + sizeof(struct mtk_socphy_shared)); + if (err) + return err; + + if (phy_package_probe_once(phydev)) { + err = mt7988_phy_probe_shared(phydev); + if (err) + return err; + } + + shared = phydev->shared->priv; + priv = &shared->priv[phydev->mdio.addr]; + + phydev->priv = priv; + + mt798x_phy_leds_state_init(phydev); + + err = mt7988_phy_fix_leds_polarities(phydev); + if (err) + return err; + + return mt798x_phy_calibration(phydev); +} + +static int mt7981_phy_probe(struct phy_device *phydev) +{ + struct mtk_socphy_priv *priv; + + priv = devm_kzalloc(&phydev->mdio.dev, sizeof(struct mtk_socphy_priv), + GFP_KERNEL); + if (!priv) + return -ENOMEM; + + phydev->priv = priv; + + mt798x_phy_leds_state_init(phydev); + + return mt798x_phy_calibration(phydev); +} + static struct phy_driver mtk_socphy_driver[] = { { PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7981), @@ -1078,11 +1485,16 @@ static struct phy_driver mtk_socphy_driver[] = { .config_init = mt798x_phy_config_init, .config_intr = genphy_no_config_intr, .handle_interrupt = genphy_handle_interrupt_no_ack, - .probe = mt798x_phy_calibration, + .probe = mt7981_phy_probe, .suspend = genphy_suspend, .resume = genphy_resume, .read_page = mtk_socphy_read_page, .write_page = mtk_socphy_write_page, + .led_blink_set = mt798x_phy_led_blink_set, + .led_brightness_set = mt798x_phy_led_brightness_set, + .led_hw_is_supported = mt798x_phy_led_hw_is_supported, + .led_hw_control_set = mt798x_phy_led_hw_control_set, + .led_hw_control_get = mt798x_phy_led_hw_control_get, }, { PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7988), @@ -1090,11 +1502,16 @@ static struct phy_driver mtk_socphy_driver[] = { .config_init = mt798x_phy_config_init, .config_intr = genphy_no_config_intr, .handle_interrupt = genphy_handle_interrupt_no_ack, - .probe = mt798x_phy_calibration, + .probe = mt7988_phy_probe, .suspend = genphy_suspend, .resume = genphy_resume, .read_page = mtk_socphy_read_page, .write_page = mtk_socphy_write_page, + .led_blink_set = mt798x_phy_led_blink_set, + .led_brightness_set = mt798x_phy_led_brightness_set, + .led_hw_is_supported = mt798x_phy_led_hw_is_supported, + .led_hw_control_set = mt798x_phy_led_hw_control_set, + .led_hw_control_get = mt798x_phy_led_hw_control_get, }, }; diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index a64186dc53f8..966c93cbe616 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -142,6 +142,8 @@ int phy_interface_num_ports(phy_interface_t interface) case PHY_INTERFACE_MODE_QSGMII: case PHY_INTERFACE_MODE_QUSGMII: return 4; + case PHY_INTERFACE_MODE_PSGMII: + return 5; case PHY_INTERFACE_MODE_MAX: WARN_ONCE(1, "PHY_INTERFACE_MODE_MAX isn't a valid interface mode"); return 0; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 4f1c8bb199e9..160bce608c34 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -210,6 +210,7 @@ static int phylink_interface_max_speed(phy_interface_t interface) case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_PSGMII: case PHY_INTERFACE_MODE_QSGMII: case PHY_INTERFACE_MODE_QUSGMII: case PHY_INTERFACE_MODE_SGMII: @@ -475,6 +476,7 @@ unsigned long phylink_get_capabilities(phy_interface_t interface, case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_PSGMII: case PHY_INTERFACE_MODE_QSGMII: case PHY_INTERFACE_MODE_QUSGMII: case PHY_INTERFACE_MODE_SGMII: @@ -868,6 +870,7 @@ static int phylink_parse_mode(struct phylink *pl, switch (pl->link_config.interface) { case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_PSGMII: case PHY_INTERFACE_MODE_QSGMII: case PHY_INTERFACE_MODE_QUSGMII: case PHY_INTERFACE_MODE_RGMII: diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index db9897e825b4..bb234cf0cea0 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -9760,8 +9760,7 @@ static int rtl8152_probe(struct usb_interface *intf, usb_set_intfdata(intf, tp); - netif_napi_add_weight(netdev, &tp->napi, r8152_poll, - tp->support_2500full ? 256 : 64); + netif_napi_add(netdev, &tp->napi, r8152_poll); ret = register_netdev(netdev); if (ret != 0) { diff --git a/drivers/net/vmxnet3/Makefile b/drivers/net/vmxnet3/Makefile index a666a88ac1ff..f82870c10205 100644 --- a/drivers/net/vmxnet3/Makefile +++ b/drivers/net/vmxnet3/Makefile @@ -32,4 +32,4 @@ obj-$(CONFIG_VMXNET3) += vmxnet3.o -vmxnet3-objs := vmxnet3_drv.o vmxnet3_ethtool.o +vmxnet3-objs := vmxnet3_drv.o vmxnet3_ethtool.o vmxnet3_xdp.o diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 7fa74b8b2100..0578864792b6 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -28,6 +28,7 @@ #include <net/ip6_checksum.h> #include "vmxnet3_int.h" +#include "vmxnet3_xdp.h" char vmxnet3_driver_name[] = "vmxnet3"; #define VMXNET3_DRIVER_DESC "VMware vmxnet3 virtual NIC driver" @@ -338,14 +339,16 @@ static void vmxnet3_unmap_tx_buf(struct vmxnet3_tx_buf_info *tbi, struct pci_dev *pdev) { - if (tbi->map_type == VMXNET3_MAP_SINGLE) + u32 map_type = tbi->map_type; + + if (map_type & VMXNET3_MAP_SINGLE) dma_unmap_single(&pdev->dev, tbi->dma_addr, tbi->len, DMA_TO_DEVICE); - else if (tbi->map_type == VMXNET3_MAP_PAGE) + else if (map_type & VMXNET3_MAP_PAGE) dma_unmap_page(&pdev->dev, tbi->dma_addr, tbi->len, DMA_TO_DEVICE); else - BUG_ON(tbi->map_type != VMXNET3_MAP_NONE); + BUG_ON(map_type & ~VMXNET3_MAP_XDP); tbi->map_type = VMXNET3_MAP_NONE; /* to help debugging */ } @@ -353,19 +356,20 @@ vmxnet3_unmap_tx_buf(struct vmxnet3_tx_buf_info *tbi, static int vmxnet3_unmap_pkt(u32 eop_idx, struct vmxnet3_tx_queue *tq, - struct pci_dev *pdev, struct vmxnet3_adapter *adapter) + struct pci_dev *pdev, struct vmxnet3_adapter *adapter, + struct xdp_frame_bulk *bq) { - struct sk_buff *skb; + struct vmxnet3_tx_buf_info *tbi; int entries = 0; + u32 map_type; /* no out of order completion */ BUG_ON(tq->buf_info[eop_idx].sop_idx != tq->tx_ring.next2comp); BUG_ON(VMXNET3_TXDESC_GET_EOP(&(tq->tx_ring.base[eop_idx].txd)) != 1); - skb = tq->buf_info[eop_idx].skb; - BUG_ON(skb == NULL); - tq->buf_info[eop_idx].skb = NULL; - + tbi = &tq->buf_info[eop_idx]; + BUG_ON(!tbi->skb); + map_type = tbi->map_type; VMXNET3_INC_RING_IDX_ONLY(eop_idx, tq->tx_ring.size); while (tq->tx_ring.next2comp != eop_idx) { @@ -381,7 +385,14 @@ vmxnet3_unmap_pkt(u32 eop_idx, struct vmxnet3_tx_queue *tq, entries++; } - dev_kfree_skb_any(skb); + if (map_type & VMXNET3_MAP_XDP) + xdp_return_frame_bulk(tbi->xdpf, bq); + else + dev_kfree_skb_any(tbi->skb); + + /* xdpf and skb are in an anonymous union. */ + tbi->skb = NULL; + return entries; } @@ -390,8 +401,12 @@ static int vmxnet3_tq_tx_complete(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) { - int completed = 0; union Vmxnet3_GenericDesc *gdesc; + struct xdp_frame_bulk bq; + int completed = 0; + + xdp_frame_bulk_init(&bq); + rcu_read_lock(); gdesc = tq->comp_ring.base + tq->comp_ring.next2proc; while (VMXNET3_TCD_GET_GEN(&gdesc->tcd) == tq->comp_ring.gen) { @@ -402,11 +417,13 @@ vmxnet3_tq_tx_complete(struct vmxnet3_tx_queue *tq, completed += vmxnet3_unmap_pkt(VMXNET3_TCD_GET_TXIDX( &gdesc->tcd), tq, adapter->pdev, - adapter); + adapter, &bq); vmxnet3_comp_ring_adv_next2proc(&tq->comp_ring); gdesc = tq->comp_ring.base + tq->comp_ring.next2proc; } + xdp_flush_frame_bulk(&bq); + rcu_read_unlock(); if (completed) { spin_lock(&tq->tx_lock); @@ -426,26 +443,36 @@ static void vmxnet3_tq_cleanup(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) { + struct xdp_frame_bulk bq; + u32 map_type; int i; + xdp_frame_bulk_init(&bq); + rcu_read_lock(); + while (tq->tx_ring.next2comp != tq->tx_ring.next2fill) { struct vmxnet3_tx_buf_info *tbi; tbi = tq->buf_info + tq->tx_ring.next2comp; + map_type = tbi->map_type; vmxnet3_unmap_tx_buf(tbi, adapter->pdev); if (tbi->skb) { - dev_kfree_skb_any(tbi->skb); + if (map_type & VMXNET3_MAP_XDP) + xdp_return_frame_bulk(tbi->xdpf, &bq); + else + dev_kfree_skb_any(tbi->skb); tbi->skb = NULL; } vmxnet3_cmd_ring_adv_next2comp(&tq->tx_ring); } - /* sanity check, verify all buffers are indeed unmapped and freed */ - for (i = 0; i < tq->tx_ring.size; i++) { - BUG_ON(tq->buf_info[i].skb != NULL || - tq->buf_info[i].map_type != VMXNET3_MAP_NONE); - } + xdp_flush_frame_bulk(&bq); + rcu_read_unlock(); + + /* sanity check, verify all buffers are indeed unmapped */ + for (i = 0; i < tq->tx_ring.size; i++) + BUG_ON(tq->buf_info[i].map_type != VMXNET3_MAP_NONE); tq->tx_ring.gen = VMXNET3_INIT_GEN; tq->tx_ring.next2fill = tq->tx_ring.next2comp = 0; @@ -599,7 +626,17 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, gd = ring->base + ring->next2fill; rbi->comp_state = VMXNET3_RXD_COMP_PENDING; - if (rbi->buf_type == VMXNET3_RX_BUF_SKB) { + if (rbi->buf_type == VMXNET3_RX_BUF_XDP) { + void *data = vmxnet3_pp_get_buff(rq->page_pool, + &rbi->dma_addr, + GFP_KERNEL); + if (!data) { + rq->stats.rx_buf_alloc_failure++; + break; + } + rbi->page = virt_to_page(data); + val = VMXNET3_RXD_BTYPE_HEAD << VMXNET3_RXD_BTYPE_SHIFT; + } else if (rbi->buf_type == VMXNET3_RX_BUF_SKB) { if (rbi->skb == NULL) { rbi->skb = __netdev_alloc_skb_ip_align(adapter->netdev, rbi->len, @@ -1263,6 +1300,63 @@ drop_pkt: return NETDEV_TX_OK; } +static int +vmxnet3_create_pp(struct vmxnet3_adapter *adapter, + struct vmxnet3_rx_queue *rq, int size) +{ + bool xdp_prog = vmxnet3_xdp_enabled(adapter); + const struct page_pool_params pp_params = { + .order = 0, + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .pool_size = size, + .nid = NUMA_NO_NODE, + .dev = &adapter->pdev->dev, + .offset = VMXNET3_XDP_RX_OFFSET, + .max_len = VMXNET3_XDP_MAX_FRSIZE, + .dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE, + }; + struct page_pool *pp; + int err; + + pp = page_pool_create(&pp_params); + if (IS_ERR(pp)) + return PTR_ERR(pp); + + err = xdp_rxq_info_reg(&rq->xdp_rxq, adapter->netdev, rq->qid, + rq->napi.napi_id); + if (err < 0) + goto err_free_pp; + + err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_PAGE_POOL, pp); + if (err) + goto err_unregister_rxq; + + rq->page_pool = pp; + + return 0; + +err_unregister_rxq: + xdp_rxq_info_unreg(&rq->xdp_rxq); +err_free_pp: + page_pool_destroy(pp); + + return err; +} + +void * +vmxnet3_pp_get_buff(struct page_pool *pp, dma_addr_t *dma_addr, + gfp_t gfp_mask) +{ + struct page *page; + + page = page_pool_alloc_pages(pp, gfp_mask | __GFP_NOWARN); + if (unlikely(!page)) + return NULL; + + *dma_addr = page_pool_get_dma_addr(page) + pp->p.offset; + + return page_address(page); +} static netdev_tx_t vmxnet3_xmit_frame(struct sk_buff *skb, struct net_device *netdev) @@ -1423,6 +1517,8 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, struct Vmxnet3_RxDesc rxCmdDesc; struct Vmxnet3_RxCompDesc rxComp; #endif + bool need_flush = false; + vmxnet3_getRxComp(rcd, &rq->comp_ring.base[rq->comp_ring.next2proc].rcd, &rxComp); while (rcd->gen == rq->comp_ring.gen) { @@ -1463,6 +1559,31 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, goto rcd_done; } + if (rcd->sop && rcd->eop && vmxnet3_xdp_enabled(adapter)) { + struct sk_buff *skb_xdp_pass; + int act; + + if (VMXNET3_RX_DATA_RING(adapter, rcd->rqID)) { + ctx->skb = NULL; + goto skip_xdp; /* Handle it later. */ + } + + if (rbi->buf_type != VMXNET3_RX_BUF_XDP) + goto rcd_done; + + act = vmxnet3_process_xdp(adapter, rq, rcd, rbi, rxd, + &skb_xdp_pass); + if (act == XDP_PASS) { + ctx->skb = skb_xdp_pass; + goto sop_done; + } + ctx->skb = NULL; + need_flush |= act == XDP_REDIRECT; + + goto rcd_done; + } +skip_xdp: + if (rcd->sop) { /* first buf of the pkt */ bool rxDataRingUsed; u16 len; @@ -1471,7 +1592,8 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, (rcd->rqID != rq->qid && rcd->rqID != rq->dataRingQid)); - BUG_ON(rbi->buf_type != VMXNET3_RX_BUF_SKB); + BUG_ON(rbi->buf_type != VMXNET3_RX_BUF_SKB && + rbi->buf_type != VMXNET3_RX_BUF_XDP); BUG_ON(ctx->skb != NULL || rbi->skb == NULL); if (unlikely(rcd->len == 0)) { @@ -1489,6 +1611,25 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, rxDataRingUsed = VMXNET3_RX_DATA_RING(adapter, rcd->rqID); len = rxDataRingUsed ? rcd->len : rbi->len; + + if (rxDataRingUsed && vmxnet3_xdp_enabled(adapter)) { + struct sk_buff *skb_xdp_pass; + size_t sz; + int act; + + sz = rcd->rxdIdx * rq->data_ring.desc_size; + act = vmxnet3_process_xdp_small(adapter, rq, + &rq->data_ring.base[sz], + rcd->len, + &skb_xdp_pass); + if (act == XDP_PASS) { + ctx->skb = skb_xdp_pass; + goto sop_done; + } + need_flush |= act == XDP_REDIRECT; + + goto rcd_done; + } new_skb = netdev_alloc_skb_ip_align(adapter->netdev, len); if (new_skb == NULL) { @@ -1621,6 +1762,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, } +sop_done: skb = ctx->skb; if (rcd->eop) { u32 mtu = adapter->netdev->mtu; @@ -1757,6 +1899,8 @@ refill_buf: vmxnet3_getRxComp(rcd, &rq->comp_ring.base[rq->comp_ring.next2proc].rcd, &rxComp); } + if (need_flush) + xdp_do_flush(); return num_pkts; } @@ -1775,24 +1919,32 @@ vmxnet3_rq_cleanup(struct vmxnet3_rx_queue *rq, for (ring_idx = 0; ring_idx < 2; ring_idx++) { for (i = 0; i < rq->rx_ring[ring_idx].size; i++) { + struct vmxnet3_rx_buf_info *rbi; #ifdef __BIG_ENDIAN_BITFIELD struct Vmxnet3_RxDesc rxDesc; #endif + + rbi = &rq->buf_info[ring_idx][i]; vmxnet3_getRxDesc(rxd, &rq->rx_ring[ring_idx].base[i].rxd, &rxDesc); if (rxd->btype == VMXNET3_RXD_BTYPE_HEAD && - rq->buf_info[ring_idx][i].skb) { + rbi->page && rbi->buf_type == VMXNET3_RX_BUF_XDP) { + page_pool_recycle_direct(rq->page_pool, + rbi->page); + rbi->page = NULL; + } else if (rxd->btype == VMXNET3_RXD_BTYPE_HEAD && + rbi->skb) { dma_unmap_single(&adapter->pdev->dev, rxd->addr, rxd->len, DMA_FROM_DEVICE); - dev_kfree_skb(rq->buf_info[ring_idx][i].skb); - rq->buf_info[ring_idx][i].skb = NULL; + dev_kfree_skb(rbi->skb); + rbi->skb = NULL; } else if (rxd->btype == VMXNET3_RXD_BTYPE_BODY && - rq->buf_info[ring_idx][i].page) { + rbi->page) { dma_unmap_page(&adapter->pdev->dev, rxd->addr, rxd->len, DMA_FROM_DEVICE); - put_page(rq->buf_info[ring_idx][i].page); - rq->buf_info[ring_idx][i].page = NULL; + put_page(rbi->page); + rbi->page = NULL; } } @@ -1813,6 +1965,7 @@ vmxnet3_rq_cleanup_all(struct vmxnet3_adapter *adapter) for (i = 0; i < adapter->num_rx_queues; i++) vmxnet3_rq_cleanup(&adapter->rx_queue[i], adapter); + rcu_assign_pointer(adapter->xdp_bpf_prog, NULL); } @@ -1842,6 +1995,11 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq, } } + if (xdp_rxq_info_is_reg(&rq->xdp_rxq)) + xdp_rxq_info_unreg(&rq->xdp_rxq); + page_pool_destroy(rq->page_pool); + rq->page_pool = NULL; + if (rq->data_ring.base) { dma_free_coherent(&adapter->pdev->dev, rq->rx_ring[0].size * rq->data_ring.desc_size, @@ -1885,14 +2043,16 @@ static int vmxnet3_rq_init(struct vmxnet3_rx_queue *rq, struct vmxnet3_adapter *adapter) { - int i; + int i, err; /* initialize buf_info */ for (i = 0; i < rq->rx_ring[0].size; i++) { - /* 1st buf for a pkt is skbuff */ + /* 1st buf for a pkt is skbuff or xdp page */ if (i % adapter->rx_buf_per_pkt == 0) { - rq->buf_info[0][i].buf_type = VMXNET3_RX_BUF_SKB; + rq->buf_info[0][i].buf_type = vmxnet3_xdp_enabled(adapter) ? + VMXNET3_RX_BUF_XDP : + VMXNET3_RX_BUF_SKB; rq->buf_info[0][i].len = adapter->skb_buf_size; } else { /* subsequent bufs for a pkt is frag */ rq->buf_info[0][i].buf_type = VMXNET3_RX_BUF_PAGE; @@ -1913,8 +2073,18 @@ vmxnet3_rq_init(struct vmxnet3_rx_queue *rq, rq->rx_ring[i].gen = VMXNET3_INIT_GEN; rq->rx_ring[i].isOutOfOrder = 0; } + + err = vmxnet3_create_pp(adapter, rq, + rq->rx_ring[0].size + rq->rx_ring[1].size); + if (err) + return err; + if (vmxnet3_rq_alloc_rx_buf(rq, 0, rq->rx_ring[0].size - 1, adapter) == 0) { + xdp_rxq_info_unreg(&rq->xdp_rxq); + page_pool_destroy(rq->page_pool); + rq->page_pool = NULL; + /* at least has 1 rx buffer for the 1st ring */ return -ENOMEM; } @@ -2016,7 +2186,7 @@ err: } -static int +int vmxnet3_rq_create_all(struct vmxnet3_adapter *adapter) { int i, err = 0; @@ -3053,7 +3223,7 @@ vmxnet3_free_pci_resources(struct vmxnet3_adapter *adapter) } -static void +void vmxnet3_adjust_rx_ring_size(struct vmxnet3_adapter *adapter) { size_t sz, i, ring0_size, ring1_size, comp_size; @@ -3612,6 +3782,8 @@ vmxnet3_probe_device(struct pci_dev *pdev, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = vmxnet3_netpoll, #endif + .ndo_bpf = vmxnet3_xdp, + .ndo_xdp_xmit = vmxnet3_xdp_xmit, }; int err; u32 ver; @@ -3864,6 +4036,8 @@ vmxnet3_probe_device(struct pci_dev *pdev, SET_NETDEV_DEV(netdev, &pdev->dev); vmxnet3_declare_features(adapter); + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; adapter->rxdata_desc_size = VMXNET3_VERSION_GE_3(adapter) ? VMXNET3_DEF_RXDATA_DESC_SIZE : 0; diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c index 18cf7c723201..98c22d7d87a2 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -28,6 +28,7 @@ #include "vmxnet3_int.h" #include <net/vxlan.h> #include <net/geneve.h> +#include "vmxnet3_xdp.h" #define VXLAN_UDP_PORT 8472 @@ -76,6 +77,10 @@ vmxnet3_tq_driver_stats[] = { copy_skb_header) }, { " giant hdr", offsetof(struct vmxnet3_tq_driver_stats, oversized_hdr) }, + { " xdp xmit", offsetof(struct vmxnet3_tq_driver_stats, + xdp_xmit) }, + { " xdp xmit err", offsetof(struct vmxnet3_tq_driver_stats, + xdp_xmit_err) }, }; /* per rq stats maintained by the device */ @@ -106,6 +111,16 @@ vmxnet3_rq_driver_stats[] = { drop_fcs) }, { " rx buf alloc fail", offsetof(struct vmxnet3_rq_driver_stats, rx_buf_alloc_failure) }, + { " xdp packets", offsetof(struct vmxnet3_rq_driver_stats, + xdp_packets) }, + { " xdp tx", offsetof(struct vmxnet3_rq_driver_stats, + xdp_tx) }, + { " xdp redirects", offsetof(struct vmxnet3_rq_driver_stats, + xdp_redirects) }, + { " xdp drops", offsetof(struct vmxnet3_rq_driver_stats, + xdp_drops) }, + { " xdp aborted", offsetof(struct vmxnet3_rq_driver_stats, + xdp_aborted) }, }; /* global stats maintained by the driver */ @@ -249,10 +264,18 @@ vmxnet3_get_strings(struct net_device *netdev, u32 stringset, u8 *buf) netdev_features_t vmxnet3_fix_features(struct net_device *netdev, netdev_features_t features) { + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + /* If Rx checksum is disabled, then LRO should also be disabled */ if (!(features & NETIF_F_RXCSUM)) features &= ~NETIF_F_LRO; + /* If XDP is enabled, then LRO should not be enabled */ + if (vmxnet3_xdp_enabled(adapter) && (features & NETIF_F_LRO)) { + netdev_err(netdev, "LRO is not supported with XDP"); + features &= ~NETIF_F_LRO; + } + return features; } diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index 3367db23aa13..915aaf18c409 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -56,6 +56,9 @@ #include <linux/if_arp.h> #include <linux/inetdevice.h> #include <linux/log2.h> +#include <linux/bpf.h> +#include <net/page_pool/helpers.h> +#include <net/xdp.h> #include "vmxnet3_defs.h" @@ -188,19 +191,20 @@ struct vmxnet3_tx_data_ring { dma_addr_t basePA; }; -enum vmxnet3_buf_map_type { - VMXNET3_MAP_INVALID = 0, - VMXNET3_MAP_NONE, - VMXNET3_MAP_SINGLE, - VMXNET3_MAP_PAGE, -}; +#define VMXNET3_MAP_NONE 0 +#define VMXNET3_MAP_SINGLE BIT(0) +#define VMXNET3_MAP_PAGE BIT(1) +#define VMXNET3_MAP_XDP BIT(2) struct vmxnet3_tx_buf_info { u32 map_type; u16 len; u16 sop_idx; dma_addr_t dma_addr; - struct sk_buff *skb; + union { + struct sk_buff *skb; + struct xdp_frame *xdpf; + }; }; struct vmxnet3_tq_driver_stats { @@ -217,6 +221,9 @@ struct vmxnet3_tq_driver_stats { u64 linearized; /* # of pkts linearized */ u64 copy_skb_header; /* # of times we have to copy skb header */ u64 oversized_hdr; + + u64 xdp_xmit; + u64 xdp_xmit_err; }; struct vmxnet3_tx_ctx { @@ -253,12 +260,13 @@ struct vmxnet3_tx_queue { * stopped */ int qid; u16 txdata_desc_size; -} __attribute__((__aligned__(SMP_CACHE_BYTES))); +} ____cacheline_aligned; enum vmxnet3_rx_buf_type { VMXNET3_RX_BUF_NONE = 0, VMXNET3_RX_BUF_SKB = 1, - VMXNET3_RX_BUF_PAGE = 2 + VMXNET3_RX_BUF_PAGE = 2, + VMXNET3_RX_BUF_XDP = 3, }; #define VMXNET3_RXD_COMP_PENDING 0 @@ -285,6 +293,12 @@ struct vmxnet3_rq_driver_stats { u64 drop_err; u64 drop_fcs; u64 rx_buf_alloc_failure; + + u64 xdp_packets; /* Total packets processed by XDP. */ + u64 xdp_tx; + u64 xdp_redirects; + u64 xdp_drops; + u64 xdp_aborted; }; struct vmxnet3_rx_data_ring { @@ -307,7 +321,9 @@ struct vmxnet3_rx_queue { struct vmxnet3_rx_buf_info *buf_info[2]; struct Vmxnet3_RxQueueCtrl *shared; struct vmxnet3_rq_driver_stats stats; -} __attribute__((__aligned__(SMP_CACHE_BYTES))); + struct page_pool *page_pool; + struct xdp_rxq_info xdp_rxq; +} ____cacheline_aligned; #define VMXNET3_DEVICE_MAX_TX_QUEUES 32 #define VMXNET3_DEVICE_MAX_RX_QUEUES 32 /* Keep this value as a power of 2 */ @@ -415,6 +431,7 @@ struct vmxnet3_adapter { u16 tx_prod_offset; u16 rx_prod_offset; u16 rx_prod2_offset; + struct bpf_prog __rcu *xdp_bpf_prog; }; #define VMXNET3_WRITE_BAR0_REG(adapter, reg, val) \ @@ -490,6 +507,12 @@ vmxnet3_tq_destroy_all(struct vmxnet3_adapter *adapter); void vmxnet3_rq_destroy_all(struct vmxnet3_adapter *adapter); +int +vmxnet3_rq_create_all(struct vmxnet3_adapter *adapter); + +void +vmxnet3_adjust_rx_ring_size(struct vmxnet3_adapter *adapter); + netdev_features_t vmxnet3_fix_features(struct net_device *netdev, netdev_features_t features); diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.c b/drivers/net/vmxnet3/vmxnet3_xdp.c new file mode 100644 index 000000000000..80ddaff759d4 --- /dev/null +++ b/drivers/net/vmxnet3/vmxnet3_xdp.c @@ -0,0 +1,419 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Linux driver for VMware's vmxnet3 ethernet NIC. + * Copyright (C) 2008-2023, VMware, Inc. All Rights Reserved. + * Maintained by: [email protected] + * + */ + +#include "vmxnet3_int.h" +#include "vmxnet3_xdp.h" + +static void +vmxnet3_xdp_exchange_program(struct vmxnet3_adapter *adapter, + struct bpf_prog *prog) +{ + rcu_assign_pointer(adapter->xdp_bpf_prog, prog); +} + +static inline struct vmxnet3_tx_queue * +vmxnet3_xdp_get_tq(struct vmxnet3_adapter *adapter) +{ + struct vmxnet3_tx_queue *tq; + int tq_number; + int cpu; + + tq_number = adapter->num_tx_queues; + cpu = smp_processor_id(); + if (likely(cpu < tq_number)) + tq = &adapter->tx_queue[cpu]; + else + tq = &adapter->tx_queue[reciprocal_scale(cpu, tq_number)]; + + return tq; +} + +static int +vmxnet3_xdp_set(struct net_device *netdev, struct netdev_bpf *bpf, + struct netlink_ext_ack *extack) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + struct bpf_prog *new_bpf_prog = bpf->prog; + struct bpf_prog *old_bpf_prog; + bool need_update; + bool running; + int err; + + if (new_bpf_prog && netdev->mtu > VMXNET3_XDP_MAX_MTU) { + NL_SET_ERR_MSG_FMT_MOD(extack, "MTU %u too large for XDP", + netdev->mtu); + return -EOPNOTSUPP; + } + + if (adapter->netdev->features & NETIF_F_LRO) { + NL_SET_ERR_MSG_MOD(extack, "LRO is not supported with XDP"); + adapter->netdev->features &= ~NETIF_F_LRO; + } + + old_bpf_prog = rcu_dereference(adapter->xdp_bpf_prog); + if (!new_bpf_prog && !old_bpf_prog) + return 0; + + running = netif_running(netdev); + need_update = !!old_bpf_prog != !!new_bpf_prog; + + if (running && need_update) + vmxnet3_quiesce_dev(adapter); + + vmxnet3_xdp_exchange_program(adapter, new_bpf_prog); + if (old_bpf_prog) + bpf_prog_put(old_bpf_prog); + + if (!running || !need_update) + return 0; + + if (new_bpf_prog) + xdp_features_set_redirect_target(netdev, false); + else + xdp_features_clear_redirect_target(netdev); + + vmxnet3_reset_dev(adapter); + vmxnet3_rq_destroy_all(adapter); + vmxnet3_adjust_rx_ring_size(adapter); + err = vmxnet3_rq_create_all(adapter); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "failed to re-create rx queues for XDP."); + return -EOPNOTSUPP; + } + err = vmxnet3_activate_dev(adapter); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "failed to activate device for XDP."); + return -EOPNOTSUPP; + } + clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state); + + return 0; +} + +/* This is the main xdp call used by kernel to set/unset eBPF program. */ +int +vmxnet3_xdp(struct net_device *netdev, struct netdev_bpf *bpf) +{ + switch (bpf->command) { + case XDP_SETUP_PROG: + return vmxnet3_xdp_set(netdev, bpf, bpf->extack); + default: + return -EINVAL; + } + + return 0; +} + +static int +vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter, + struct xdp_frame *xdpf, + struct vmxnet3_tx_queue *tq, bool dma_map) +{ + struct vmxnet3_tx_buf_info *tbi = NULL; + union Vmxnet3_GenericDesc *gdesc; + struct vmxnet3_tx_ctx ctx; + int tx_num_deferred; + struct page *page; + u32 buf_size; + u32 dw2; + + dw2 = (tq->tx_ring.gen ^ 0x1) << VMXNET3_TXD_GEN_SHIFT; + dw2 |= xdpf->len; + ctx.sop_txd = tq->tx_ring.base + tq->tx_ring.next2fill; + gdesc = ctx.sop_txd; + + buf_size = xdpf->len; + tbi = tq->buf_info + tq->tx_ring.next2fill; + + if (vmxnet3_cmd_ring_desc_avail(&tq->tx_ring) == 0) { + tq->stats.tx_ring_full++; + return -ENOSPC; + } + + tbi->map_type = VMXNET3_MAP_XDP; + if (dma_map) { /* ndo_xdp_xmit */ + tbi->dma_addr = dma_map_single(&adapter->pdev->dev, + xdpf->data, buf_size, + DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr)) + return -EFAULT; + tbi->map_type |= VMXNET3_MAP_SINGLE; + } else { /* XDP buffer from page pool */ + page = virt_to_page(xdpf->data); + tbi->dma_addr = page_pool_get_dma_addr(page) + + VMXNET3_XDP_HEADROOM; + dma_sync_single_for_device(&adapter->pdev->dev, + tbi->dma_addr, buf_size, + DMA_TO_DEVICE); + } + tbi->xdpf = xdpf; + tbi->len = buf_size; + + gdesc = tq->tx_ring.base + tq->tx_ring.next2fill; + WARN_ON_ONCE(gdesc->txd.gen == tq->tx_ring.gen); + + gdesc->txd.addr = cpu_to_le64(tbi->dma_addr); + gdesc->dword[2] = cpu_to_le32(dw2); + + /* Setup the EOP desc */ + gdesc->dword[3] = cpu_to_le32(VMXNET3_TXD_CQ | VMXNET3_TXD_EOP); + + gdesc->txd.om = 0; + gdesc->txd.msscof = 0; + gdesc->txd.hlen = 0; + gdesc->txd.ti = 0; + + tx_num_deferred = le32_to_cpu(tq->shared->txNumDeferred); + le32_add_cpu(&tq->shared->txNumDeferred, 1); + tx_num_deferred++; + + vmxnet3_cmd_ring_adv_next2fill(&tq->tx_ring); + + /* set the last buf_info for the pkt */ + tbi->sop_idx = ctx.sop_txd - tq->tx_ring.base; + + dma_wmb(); + gdesc->dword[2] = cpu_to_le32(le32_to_cpu(gdesc->dword[2]) ^ + VMXNET3_TXD_GEN); + + /* No need to handle the case when tx_num_deferred doesn't reach + * threshold. Backend driver at hypervisor side will poll and reset + * tq->shared->txNumDeferred to 0. + */ + if (tx_num_deferred >= le32_to_cpu(tq->shared->txThreshold)) { + tq->shared->txNumDeferred = 0; + VMXNET3_WRITE_BAR0_REG(adapter, + VMXNET3_REG_TXPROD + tq->qid * 8, + tq->tx_ring.next2fill); + } + + return 0; +} + +static int +vmxnet3_xdp_xmit_back(struct vmxnet3_adapter *adapter, + struct xdp_frame *xdpf) +{ + struct vmxnet3_tx_queue *tq; + struct netdev_queue *nq; + int err; + + tq = vmxnet3_xdp_get_tq(adapter); + if (tq->stopped) + return -ENETDOWN; + + nq = netdev_get_tx_queue(adapter->netdev, tq->qid); + + __netif_tx_lock(nq, smp_processor_id()); + err = vmxnet3_xdp_xmit_frame(adapter, xdpf, tq, false); + __netif_tx_unlock(nq); + + return err; +} + +/* ndo_xdp_xmit */ +int +vmxnet3_xdp_xmit(struct net_device *dev, + int n, struct xdp_frame **frames, u32 flags) +{ + struct vmxnet3_adapter *adapter = netdev_priv(dev); + struct vmxnet3_tx_queue *tq; + int i; + + if (unlikely(test_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state))) + return -ENETDOWN; + if (unlikely(test_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state))) + return -EINVAL; + + tq = vmxnet3_xdp_get_tq(adapter); + if (tq->stopped) + return -ENETDOWN; + + for (i = 0; i < n; i++) { + if (vmxnet3_xdp_xmit_frame(adapter, frames[i], tq, true)) { + tq->stats.xdp_xmit_err++; + break; + } + } + tq->stats.xdp_xmit += i; + + return i; +} + +static int +vmxnet3_run_xdp(struct vmxnet3_rx_queue *rq, struct xdp_buff *xdp, + struct bpf_prog *prog) +{ + struct xdp_frame *xdpf; + struct page *page; + int err; + u32 act; + + rq->stats.xdp_packets++; + act = bpf_prog_run_xdp(prog, xdp); + page = virt_to_page(xdp->data_hard_start); + + switch (act) { + case XDP_PASS: + return act; + case XDP_REDIRECT: + err = xdp_do_redirect(rq->adapter->netdev, xdp, prog); + if (!err) { + rq->stats.xdp_redirects++; + } else { + rq->stats.xdp_drops++; + page_pool_recycle_direct(rq->page_pool, page); + } + return act; + case XDP_TX: + xdpf = xdp_convert_buff_to_frame(xdp); + if (unlikely(!xdpf || + vmxnet3_xdp_xmit_back(rq->adapter, xdpf))) { + rq->stats.xdp_drops++; + page_pool_recycle_direct(rq->page_pool, page); + } else { + rq->stats.xdp_tx++; + } + return act; + default: + bpf_warn_invalid_xdp_action(rq->adapter->netdev, prog, act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(rq->adapter->netdev, prog, act); + rq->stats.xdp_aborted++; + break; + case XDP_DROP: + rq->stats.xdp_drops++; + break; + } + + page_pool_recycle_direct(rq->page_pool, page); + + return act; +} + +static struct sk_buff * +vmxnet3_build_skb(struct vmxnet3_rx_queue *rq, struct page *page, + const struct xdp_buff *xdp) +{ + struct sk_buff *skb; + + skb = build_skb(page_address(page), PAGE_SIZE); + if (unlikely(!skb)) { + page_pool_recycle_direct(rq->page_pool, page); + rq->stats.rx_buf_alloc_failure++; + return NULL; + } + + /* bpf prog might change len and data position. */ + skb_reserve(skb, xdp->data - xdp->data_hard_start); + skb_put(skb, xdp->data_end - xdp->data); + skb_mark_for_recycle(skb); + + return skb; +} + +/* Handle packets from DataRing. */ +int +vmxnet3_process_xdp_small(struct vmxnet3_adapter *adapter, + struct vmxnet3_rx_queue *rq, + void *data, int len, + struct sk_buff **skb_xdp_pass) +{ + struct bpf_prog *xdp_prog; + struct xdp_buff xdp; + struct page *page; + int act; + + page = page_pool_alloc_pages(rq->page_pool, GFP_ATOMIC); + if (unlikely(!page)) { + rq->stats.rx_buf_alloc_failure++; + return XDP_DROP; + } + + xdp_init_buff(&xdp, PAGE_SIZE, &rq->xdp_rxq); + xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset, + len, false); + xdp_buff_clear_frags_flag(&xdp); + + /* Must copy the data because it's at dataring. */ + memcpy(xdp.data, data, len); + + xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog); + if (!xdp_prog) { + act = XDP_PASS; + goto out_skb; + } + act = vmxnet3_run_xdp(rq, &xdp, xdp_prog); + if (act != XDP_PASS) + return act; + +out_skb: + *skb_xdp_pass = vmxnet3_build_skb(rq, page, &xdp); + if (!*skb_xdp_pass) + return XDP_DROP; + + /* No need to refill. */ + return likely(*skb_xdp_pass) ? act : XDP_DROP; +} + +int +vmxnet3_process_xdp(struct vmxnet3_adapter *adapter, + struct vmxnet3_rx_queue *rq, + struct Vmxnet3_RxCompDesc *rcd, + struct vmxnet3_rx_buf_info *rbi, + struct Vmxnet3_RxDesc *rxd, + struct sk_buff **skb_xdp_pass) +{ + struct bpf_prog *xdp_prog; + dma_addr_t new_dma_addr; + struct xdp_buff xdp; + struct page *page; + void *new_data; + int act; + + page = rbi->page; + dma_sync_single_for_cpu(&adapter->pdev->dev, + page_pool_get_dma_addr(page) + + rq->page_pool->p.offset, rcd->len, + page_pool_get_dma_dir(rq->page_pool)); + + xdp_init_buff(&xdp, rbi->len, &rq->xdp_rxq); + xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset, + rcd->len, false); + xdp_buff_clear_frags_flag(&xdp); + + xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog); + if (!xdp_prog) { + act = XDP_PASS; + goto out_skb; + } + act = vmxnet3_run_xdp(rq, &xdp, xdp_prog); + + if (act == XDP_PASS) { +out_skb: + *skb_xdp_pass = vmxnet3_build_skb(rq, page, &xdp); + if (!*skb_xdp_pass) + act = XDP_DROP; + } + + new_data = vmxnet3_pp_get_buff(rq->page_pool, &new_dma_addr, + GFP_ATOMIC); + if (!new_data) { + rq->stats.rx_buf_alloc_failure++; + return XDP_DROP; + } + rbi->page = virt_to_page(new_data); + rbi->dma_addr = new_dma_addr; + rxd->addr = cpu_to_le64(rbi->dma_addr); + rxd->len = rbi->len; + + return act; +} diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.h b/drivers/net/vmxnet3/vmxnet3_xdp.h new file mode 100644 index 000000000000..f9d843e060a3 --- /dev/null +++ b/drivers/net/vmxnet3/vmxnet3_xdp.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later + * + * Linux driver for VMware's vmxnet3 ethernet NIC. + * Copyright (C) 2008-2023, VMware, Inc. All Rights Reserved. + * Maintained by: [email protected] + * + */ + +#ifndef _VMXNET3_XDP_H +#define _VMXNET3_XDP_H + +#include <linux/filter.h> +#include <linux/bpf_trace.h> +#include <linux/netlink.h> + +#include "vmxnet3_int.h" + +#define VMXNET3_XDP_HEADROOM (XDP_PACKET_HEADROOM + NET_IP_ALIGN) +#define VMXNET3_XDP_RX_TAILROOM SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +#define VMXNET3_XDP_RX_OFFSET VMXNET3_XDP_HEADROOM +#define VMXNET3_XDP_MAX_FRSIZE (PAGE_SIZE - VMXNET3_XDP_HEADROOM - \ + VMXNET3_XDP_RX_TAILROOM) +#define VMXNET3_XDP_MAX_MTU (VMXNET3_XDP_MAX_FRSIZE - ETH_HLEN - \ + 2 * VLAN_HLEN - ETH_FCS_LEN) + +int vmxnet3_xdp(struct net_device *netdev, struct netdev_bpf *bpf); +int vmxnet3_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, + u32 flags); +int vmxnet3_process_xdp(struct vmxnet3_adapter *adapter, + struct vmxnet3_rx_queue *rq, + struct Vmxnet3_RxCompDesc *rcd, + struct vmxnet3_rx_buf_info *rbi, + struct Vmxnet3_RxDesc *rxd, + struct sk_buff **skb_xdp_pass); +int vmxnet3_process_xdp_small(struct vmxnet3_adapter *adapter, + struct vmxnet3_rx_queue *rq, + void *data, int len, + struct sk_buff **skb_xdp_pass); +void *vmxnet3_pp_get_buff(struct page_pool *pp, dma_addr_t *dma_addr, + gfp_t gfp_mask); + +static inline bool vmxnet3_xdp_enabled(struct vmxnet3_adapter *adapter) +{ + return !!rcu_access_pointer(adapter->xdp_bpf_prog); +} + +#endif diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 2bddcdf482a7..e463f59e95c2 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -2328,14 +2328,11 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct vxlan_dev *dst_vxlan, __be32 vni, bool snoop) { - struct pcpu_sw_netstats *tx_stats, *rx_stats; union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; struct net_device *dev; int len = skb->len; - tx_stats = this_cpu_ptr(src_vxlan->dev->tstats); - rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats); skb->pkt_type = PACKET_HOST; skb->encapsulation = 0; skb->dev = dst_vxlan->dev; @@ -2361,17 +2358,11 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, if ((dst_vxlan->cfg.flags & VXLAN_F_LEARN) && snoop) vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni); - u64_stats_update_begin(&tx_stats->syncp); - u64_stats_inc(&tx_stats->tx_packets); - u64_stats_add(&tx_stats->tx_bytes, len); - u64_stats_update_end(&tx_stats->syncp); + dev_sw_netstats_tx_add(src_vxlan->dev, 1, len); vxlan_vnifilter_count(src_vxlan, vni, NULL, VXLAN_VNI_STATS_TX, len); if (__netif_rx(skb) == NET_RX_SUCCESS) { - u64_stats_update_begin(&rx_stats->syncp); - u64_stats_inc(&rx_stats->rx_packets); - u64_stats_add(&rx_stats->rx_bytes, len); - u64_stats_update_end(&rx_stats->syncp); + dev_sw_netstats_rx_add(dst_vxlan->dev, len); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX, len); } else { diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index 6d1bd9f52d02..dc09b75a3248 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -200,7 +200,7 @@ static int wg_get_device_start(struct netlink_callback *cb) { struct wg_device *wg; - wg = lookup_interface(genl_dumpit_info(cb)->attrs, cb->skb); + wg = lookup_interface(genl_info_dump(cb)->attrs, cb->skb); if (IS_ERR(wg)) return PTR_ERR(wg); DUMP_CTX(cb)->wg = wg; diff --git a/drivers/net/wireless/ti/wlcore/spi.c b/drivers/net/wireless/ti/wlcore/spi.c index 3f88e6a0a510..7d9a139db59e 100644 --- a/drivers/net/wireless/ti/wlcore/spi.c +++ b/drivers/net/wireless/ti/wlcore/spi.c @@ -554,7 +554,7 @@ static void wl1271_remove(struct spi_device *spi) static struct spi_driver wl1271_spi_driver = { .driver = { .name = "wl1271_spi", - .of_match_table = of_match_ptr(wlcore_spi_of_match_table), + .of_match_table = wlcore_spi_of_match_table, }, .probe = wl1271_probe, diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c index bb76c7c7cc82..b027be0b0b6f 100644 --- a/drivers/nfc/virtual_ncidev.c +++ b/drivers/nfc/virtual_ncidev.c @@ -200,18 +200,7 @@ static struct miscdevice miscdev = { .mode = 0600, }; -static int __init virtual_ncidev_init(void) -{ - return misc_register(&miscdev); -} - -static void __exit virtual_ncidev_exit(void) -{ - misc_deregister(&miscdev); -} - -module_init(virtual_ncidev_init); -module_exit(virtual_ncidev_exit); +module_misc_device(miscdev); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Virtual NCI device simulation driver"); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5818af8eca5a..dbf26bc89dd4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -284,6 +284,11 @@ struct mem_cgroup { atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS]; + /* + * Hint of reclaim pressure for socket memroy management. Note + * that this indicator should NOT be used in legacy cgroup mode + * where socket memory is accounted/charged separately. + */ unsigned long socket_pressure; /* Legacy tcp memory accounting */ @@ -1727,8 +1732,8 @@ void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) - return true; + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return !!memcg->tcpmem_pressure; do { if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 80cc12a9a531..93399802ba77 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1208,9 +1208,7 @@ enum mlx5_cap_type { MLX5_CAP_FLOW_TABLE, MLX5_CAP_ESWITCH_FLOW_TABLE, MLX5_CAP_ESWITCH, - MLX5_CAP_RESERVED, - MLX5_CAP_VECTOR_CALC, - MLX5_CAP_QOS, + MLX5_CAP_QOS = 0xc, MLX5_CAP_DEBUG, MLX5_CAP_RESERVED_14, MLX5_CAP_DEV_MEM, @@ -1220,7 +1218,6 @@ enum mlx5_cap_type { MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, MLX5_CAP_CRYPTO = 0x1a, - MLX5_CAP_DEV_SHAMPO = 0x1d, MLX5_CAP_MACSEC = 0x1f, MLX5_CAP_GENERAL_2 = 0x20, MLX5_CAP_PORT_SELECTION = 0x25, @@ -1239,7 +1236,6 @@ enum mlx5_pcam_feature_groups { enum mlx5_mcam_reg_groups { MLX5_MCAM_REGS_FIRST_128 = 0x0, - MLX5_MCAM_REGS_0x9080_0x90FF = 0x1, MLX5_MCAM_REGS_0x9100_0x917F = 0x2, MLX5_MCAM_REGS_NUM = 0x3, }; @@ -1279,10 +1275,6 @@ enum mlx5_qcam_feature_groups { MLX5_GET(per_protocol_networking_offload_caps,\ mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS]->cur, cap) -#define MLX5_CAP_ETH_MAX(mdev, cap) \ - MLX5_GET(per_protocol_networking_offload_caps,\ - mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS]->max, cap) - #define MLX5_CAP_IPOIB_ENHANCED(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ mdev->caps.hca[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS]->cur, cap) @@ -1305,77 +1297,40 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP64_FLOWTABLE(mdev, cap) \ MLX5_GET64(flow_table_nic_cap, (mdev)->caps.hca[MLX5_CAP_FLOW_TABLE]->cur, cap) -#define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \ - MLX5_GET(flow_table_nic_cap, mdev->caps.hca[MLX5_CAP_FLOW_TABLE]->max, cap) - #define MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.cap) -#define MLX5_CAP_FLOWTABLE_NIC_RX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive.cap) - #define MLX5_CAP_FLOWTABLE_NIC_TX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit.cap) -#define MLX5_CAP_FLOWTABLE_NIC_TX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit.cap) - #define MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_sniffer.cap) -#define MLX5_CAP_FLOWTABLE_SNIFFER_RX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive_sniffer.cap) - #define MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit_sniffer.cap) -#define MLX5_CAP_FLOWTABLE_SNIFFER_TX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit_sniffer.cap) - #define MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_rdma.cap) -#define MLX5_CAP_FLOWTABLE_RDMA_RX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive_rdma.cap) - #define MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit_rdma.cap) -#define MLX5_CAP_FLOWTABLE_RDMA_TX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit_rdma.cap) - #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \ MLX5_GET(flow_table_eswitch_cap, \ mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap) -#define MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, cap) \ - MLX5_GET(flow_table_eswitch_cap, \ - mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->max, cap) - #define MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_nic_esw_fdb.cap) -#define MLX5_CAP_ESW_FLOWTABLE_FDB_MAX(mdev, cap) \ - MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_nic_esw_fdb.cap) - #define MLX5_CAP_ESW_EGRESS_ACL(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_esw_acl_egress.cap) -#define MLX5_CAP_ESW_EGRESS_ACL_MAX(mdev, cap) \ - MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_egress.cap) - #define MLX5_CAP_ESW_INGRESS_ACL(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_esw_acl_ingress.cap) -#define MLX5_CAP_ESW_INGRESS_ACL_MAX(mdev, cap) \ - MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_ingress.cap) - #define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, ft_field_support_2_esw_fdb.cap) -#define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2_MAX(mdev, cap) \ - MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, ft_field_support_2_esw_fdb.cap) - #define MLX5_CAP_ESW(mdev, cap) \ MLX5_GET(e_switch_cap, \ mdev->caps.hca[MLX5_CAP_ESWITCH]->cur, cap) @@ -1384,10 +1339,6 @@ enum mlx5_qcam_feature_groups { MLX5_GET64(flow_table_eswitch_cap, \ (mdev)->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap) -#define MLX5_CAP_ESW_MAX(mdev, cap) \ - MLX5_GET(e_switch_cap, \ - mdev->caps.hca[MLX5_CAP_ESWITCH]->max, cap) - #define MLX5_CAP_PORT_SELECTION(mdev, cap) \ MLX5_GET(port_selection_cap, \ mdev->caps.hca[MLX5_CAP_PORT_SELECTION]->cur, cap) @@ -1400,26 +1351,15 @@ enum mlx5_qcam_feature_groups { MLX5_GET(adv_virtualization_cap, \ mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->cur, cap) -#define MLX5_CAP_ADV_VIRTUALIZATION_MAX(mdev, cap) \ - MLX5_GET(adv_virtualization_cap, \ - mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->max, cap) - #define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \ MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap) -#define MLX5_CAP_FLOWTABLE_PORT_SELECTION_MAX(mdev, cap) \ - MLX5_CAP_PORT_SELECTION_MAX(mdev, flow_table_properties_port_selection.cap) - #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap) #define MLX5_CAP_ODP_MAX(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->max, cap) -#define MLX5_CAP_VECTOR_CALC(mdev, cap) \ - MLX5_GET(vector_calc_cap, \ - mdev->caps.hca[MLX5_CAP_VECTOR_CALC]->cur, cap) - #define MLX5_CAP_QOS(mdev, cap)\ MLX5_GET(qos_cap, mdev->caps.hca[MLX5_CAP_QOS]->cur, cap) @@ -1436,10 +1376,6 @@ enum mlx5_qcam_feature_groups { MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_FIRST_128], \ mng_access_reg_cap_mask.access_regs.reg) -#define MLX5_CAP_MCAM_REG1(mdev, reg) \ - MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9080_0x90FF], \ - mng_access_reg_cap_mask.access_regs1.reg) - #define MLX5_CAP_MCAM_REG2(mdev, reg) \ MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9100_0x917F], \ mng_access_reg_cap_mask.access_regs2.reg) @@ -1485,9 +1421,6 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_CRYPTO(mdev, cap)\ MLX5_GET(crypto_cap, (mdev)->caps.hca[MLX5_CAP_CRYPTO]->cur, cap) -#define MLX5_CAP_DEV_SHAMPO(mdev, cap)\ - MLX5_GET(shampo_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_SHAMPO], cap) - #define MLX5_CAP_MACSEC(mdev, cap)\ MLX5_GET(macsec_cap, (mdev)->caps.hca[MLX5_CAP_MACSEC]->cur, cap) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index e1c7e502a4fc..c9d82e74daaa 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1022,7 +1022,6 @@ bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev); void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *mdev); -int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 87fd6f9ed82c..08dcb1f43be7 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1314,33 +1314,6 @@ struct mlx5_ifc_odp_cap_bits { u8 reserved_at_120[0x6E0]; }; -struct mlx5_ifc_calc_op { - u8 reserved_at_0[0x10]; - u8 reserved_at_10[0x9]; - u8 op_swap_endianness[0x1]; - u8 op_min[0x1]; - u8 op_xor[0x1]; - u8 op_or[0x1]; - u8 op_and[0x1]; - u8 op_max[0x1]; - u8 op_add[0x1]; -}; - -struct mlx5_ifc_vector_calc_cap_bits { - u8 calc_matrix[0x1]; - u8 reserved_at_1[0x1f]; - u8 reserved_at_20[0x8]; - u8 max_vec_count[0x8]; - u8 reserved_at_30[0xd]; - u8 max_chunk_size[0x3]; - struct mlx5_ifc_calc_op calc0; - struct mlx5_ifc_calc_op calc1; - struct mlx5_ifc_calc_op calc2; - struct mlx5_ifc_calc_op calc3; - - u8 reserved_at_c0[0x720]; -}; - struct mlx5_ifc_tls_cap_bits { u8 tls_1_2_aes_gcm_128[0x1]; u8 tls_1_3_aes_gcm_128[0x1]; @@ -3435,20 +3408,6 @@ struct mlx5_ifc_roce_addr_layout_bits { u8 reserved_at_e0[0x20]; }; -struct mlx5_ifc_shampo_cap_bits { - u8 reserved_at_0[0x3]; - u8 shampo_log_max_reservation_size[0x5]; - u8 reserved_at_8[0x3]; - u8 shampo_log_min_reservation_size[0x5]; - u8 shampo_min_mss_size[0x10]; - - u8 reserved_at_20[0x3]; - u8 shampo_max_log_headers_entry_size[0x5]; - u8 reserved_at_28[0x18]; - - u8 reserved_at_40[0x7c0]; -}; - struct mlx5_ifc_crypto_cap_bits { u8 reserved_at_0[0x3]; u8 synchronize_dek[0x1]; @@ -3484,14 +3443,12 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap; struct mlx5_ifc_e_switch_cap_bits e_switch_cap; struct mlx5_ifc_port_selection_cap_bits port_selection_cap; - struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap; struct mlx5_ifc_qos_cap_bits qos_cap; struct mlx5_ifc_debug_cap_bits debug_cap; struct mlx5_ifc_fpga_cap_bits fpga_cap; struct mlx5_ifc_tls_cap_bits tls_cap; struct mlx5_ifc_device_mem_cap_bits device_mem_cap; struct mlx5_ifc_virtio_emulation_cap_bits virtio_emulation_cap; - struct mlx5_ifc_shampo_cap_bits shampo_cap; struct mlx5_ifc_macsec_cap_bits macsec_cap; struct mlx5_ifc_crypto_cap_bits crypto_cap; u8 reserved_at_0[0x8000]; @@ -10858,8 +10815,9 @@ enum { MLX5_MFRL_REG_RESET_STATE_IDLE = 0, MLX5_MFRL_REG_RESET_STATE_IN_NEGOTIATION = 1, MLX5_MFRL_REG_RESET_STATE_RESET_IN_PROGRESS = 2, - MLX5_MFRL_REG_RESET_STATE_TIMEOUT = 3, + MLX5_MFRL_REG_RESET_STATE_NEG_TIMEOUT = 3, MLX5_MFRL_REG_RESET_STATE_NACK = 4, + MLX5_MFRL_REG_RESET_STATE_UNLOAD_TIMEOUT = 5, }; enum { diff --git a/include/linux/phy.h b/include/linux/phy.h index 3c1ceedd1b77..1351b802ffcf 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -110,6 +110,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface * @PHY_INTERFACE_MODE_XLGMII:40 gigabit media-independent interface * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax + * @PHY_INTERFACE_MODE_PSGMII: Penta SGMII * @PHY_INTERFACE_MODE_QSGMII: Quad SGMII * @PHY_INTERFACE_MODE_TRGMII: Turbo RGMII * @PHY_INTERFACE_MODE_100BASEX: 100 BaseX @@ -147,6 +148,7 @@ typedef enum { PHY_INTERFACE_MODE_XGMII, PHY_INTERFACE_MODE_XLGMII, PHY_INTERFACE_MODE_MOCA, + PHY_INTERFACE_MODE_PSGMII, PHY_INTERFACE_MODE_QSGMII, PHY_INTERFACE_MODE_TRGMII, PHY_INTERFACE_MODE_100BASEX, @@ -254,6 +256,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "xlgmii"; case PHY_INTERFACE_MODE_MOCA: return "moca"; + case PHY_INTERFACE_MODE_PSGMII: + return "psgmii"; case PHY_INTERFACE_MODE_QSGMII: return "qsgmii"; case PHY_INTERFACE_MODE_TRGMII: diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index af729859385e..aa90adc3b2a4 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -386,6 +386,7 @@ struct bt_sock { enum { BT_SK_DEFER_SETUP, BT_SK_SUSPEND, + BT_SK_PKT_STATUS }; struct bt_sock_list { @@ -400,6 +401,8 @@ int bt_sock_register(int proto, const struct net_proto_family *ops); void bt_sock_unregister(int proto); void bt_sock_link(struct bt_sock_list *l, struct sock *s); void bt_sock_unlink(struct bt_sock_list *l, struct sock *s); +struct sock *bt_sock_alloc(struct net *net, struct socket *sock, + struct proto *prot, int proto, gfp_t prio, int kern); int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg, @@ -430,10 +433,6 @@ struct l2cap_ctrl { struct l2cap_chan *chan; }; -struct sco_ctrl { - u8 pkt_status; -}; - struct hci_dev; typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode); @@ -464,16 +463,18 @@ struct bt_skb_cb { u8 force_active; u16 expect; u8 incoming:1; + u8 pkt_status:2; union { struct l2cap_ctrl l2cap; - struct sco_ctrl sco; struct hci_ctrl hci; struct mgmt_ctrl mgmt; + struct scm_creds creds; }; }; #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb)) #define hci_skb_pkt_type(skb) bt_cb((skb))->pkt_type +#define hci_skb_pkt_status(skb) bt_cb((skb))->pkt_status #define hci_skb_expect(skb) bt_cb((skb))->expect #define hci_skb_opcode(skb) bt_cb((skb))->hci.opcode #define hci_skb_event(skb) bt_cb((skb))->hci.req_event diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 872dcb91a540..5723405b833e 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -309,6 +309,16 @@ enum { * to support it. */ HCI_QUIRK_BROKEN_SET_RPA_TIMEOUT, + + /* When this quirk is set, MSFT extension monitor tracking by + * address filter is supported. Since tracking quantity of each + * pattern is limited, this feature supports tracking multiple + * devices concurrently if controller supports multiple + * address filters. + * + * This quirk must be set before hci_register_dev is called. + */ + HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER, }; /* HCI device flags */ @@ -577,6 +587,7 @@ enum { #define HCI_LE_CIS_CENTRAL 0x10 #define HCI_LE_CIS_PERIPHERAL 0x20 #define HCI_LE_ISO_BROADCASTER 0x40 +#define HCI_LE_ISO_SYNC_RECEIVER 0x80 /* Connection modes */ #define HCI_CM_ACTIVE 0x0000 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index e01d52cb668c..c53d74236e3a 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -321,8 +321,8 @@ struct adv_monitor { #define HCI_MAX_SHORT_NAME_LENGTH 10 -#define HCI_CONN_HANDLE_UNSET 0xffff #define HCI_CONN_HANDLE_MAX 0x0eff +#define HCI_CONN_HANDLE_UNSET(_handle) (_handle > HCI_CONN_HANDLE_MAX) /* Min encryption key size to match with SMP */ #define HCI_MIN_ENC_KEY_SIZE 7 @@ -739,6 +739,7 @@ struct hci_conn { unsigned long flags; enum conn_reasons conn_reason; + __u8 abort_reason; __u32 clock; __u16 clock_accuracy; @@ -758,7 +759,6 @@ struct hci_conn { struct delayed_work auto_accept_work; struct delayed_work idle_work; struct delayed_work le_conn_timeout; - struct work_struct le_scan_cleanup; struct device dev; struct dentry *debugfs; @@ -974,6 +974,10 @@ enum { HCI_CONN_SCANNING, HCI_CONN_AUTH_FAILURE, HCI_CONN_PER_ADV, + HCI_CONN_BIG_CREATED, + HCI_CONN_CREATE_CIS, + HCI_CONN_BIG_SYNC, + HCI_CONN_BIG_SYNC_FAILED, }; static inline bool hci_conn_ssp_enabled(struct hci_conn *conn) @@ -1093,8 +1097,7 @@ static inline __u8 hci_conn_lookup_type(struct hci_dev *hdev, __u16 handle) } static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev, - bdaddr_t *ba, - __u8 big, __u8 bis) + bdaddr_t *ba, __u8 bis) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; @@ -1105,7 +1108,33 @@ static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev, if (bacmp(&c->dst, ba) || c->type != ISO_LINK) continue; - if (c->iso_qos.bcast.big == big && c->iso_qos.bcast.bis == bis) { + if (c->iso_qos.bcast.bis == bis) { + rcu_read_unlock(); + return c; + } + } + rcu_read_unlock(); + + return NULL; +} + +static inline struct hci_conn * +hci_conn_hash_lookup_per_adv_bis(struct hci_dev *hdev, + bdaddr_t *ba, + __u8 big, __u8 bis) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (bacmp(&c->dst, ba) || c->type != ISO_LINK || + !test_bit(HCI_CONN_PER_ADV, &c->flags)) + continue; + + if (c->iso_qos.bcast.big == big && + c->iso_qos.bcast.bis == bis) { rcu_read_unlock(); return c; } @@ -1190,7 +1219,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev, rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (c->type != ISO_LINK) + if (c->type != ISO_LINK || !bacmp(&c->dst, BDADDR_ANY)) continue; /* Match CIG ID if set */ @@ -1222,7 +1251,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_cig(struct hci_dev *hdev, rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (c->type != ISO_LINK) + if (c->type != ISO_LINK || !bacmp(&c->dst, BDADDR_ANY)) continue; if (handle == c->iso_qos.ucast.cig) { @@ -1259,6 +1288,29 @@ static inline struct hci_conn *hci_conn_hash_lookup_big(struct hci_dev *hdev, return NULL; } +static inline struct hci_conn *hci_conn_hash_lookup_big_any_dst(struct hci_dev *hdev, + __u8 handle) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (c->type != ISO_LINK) + continue; + + if (handle == c->iso_qos.bcast.big) { + rcu_read_unlock(); + return c; + } + } + + rcu_read_unlock(); + + return NULL; +} + static inline struct hci_conn *hci_conn_hash_lookup_state(struct hci_dev *hdev, __u8 type, __u16 state) { @@ -1320,11 +1372,33 @@ static inline struct hci_conn *hci_lookup_le_connect(struct hci_dev *hdev) return NULL; } +/* Returns true if an le connection is in the scanning state */ +static inline bool hci_is_le_conn_scanning(struct hci_dev *hdev) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (c->type == LE_LINK && c->state == BT_CONNECT && + test_bit(HCI_CONN_SCANNING, &c->flags)) { + rcu_read_unlock(); + return true; + } + } + + rcu_read_unlock(); + + return false; +} + int hci_disconnect(struct hci_conn *conn, __u8 reason); bool hci_setup_sync(struct hci_conn *conn, __u16 handle); void hci_sco_setup(struct hci_conn *conn, __u8 status); bool hci_iso_setup_path(struct hci_conn *conn); -int hci_le_create_cis(struct hci_conn *conn); +int hci_le_create_cis_pending(struct hci_dev *hdev); +int hci_conn_check_create_cis(struct hci_conn *conn); struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role); @@ -1351,6 +1425,9 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, __u16 setting, struct bt_codec *codec); struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos); +struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, + struct bt_iso_qos *qos, + __u8 base_len, __u8 *base); struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos); struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, @@ -1369,6 +1446,7 @@ int hci_conn_switch_role(struct hci_conn *conn, __u8 role); void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active); void hci_conn_failed(struct hci_conn *conn, u8 status); +u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle); /* * hci_conn_get() and hci_conn_put() are used to control the life-time of an @@ -1745,6 +1823,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn); /* Extended advertising support */ #define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV)) +/* Maximum advertising length */ +#define max_adv_len(dev) \ + (ext_adv_capable(dev) ? HCI_MAX_EXT_AD_LENGTH : HCI_MAX_AD_LENGTH) + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E page 1789: * * C24: Mandatory if the LE Controller supports Connection State and either @@ -1765,6 +1847,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define cis_peripheral_capable(dev) \ ((dev)->le_features[3] & HCI_LE_CIS_PERIPHERAL) #define bis_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_BROADCASTER) +#define sync_recv_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER) #define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \ (!test_bit(HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG, &(dev)->quirks))) diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index 2495be4d8b82..57eeb07aeb25 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -5,6 +5,9 @@ * Copyright (C) 2021 Intel Corporation */ +#define UINT_PTR(_handle) ((void *)((uintptr_t)_handle)) +#define PTR_UINT(_ptr) ((uintptr_t)((void *)_ptr)) + typedef int (*hci_cmd_sync_work_func_t)(struct hci_dev *hdev, void *data); typedef void (*hci_cmd_sync_work_destroy_t)(struct hci_dev *hdev, void *data, int err); @@ -124,7 +127,7 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason); int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn); -int hci_le_create_cis_sync(struct hci_dev *hdev, struct hci_conn *conn); +int hci_le_create_cis_sync(struct hci_dev *hdev); int hci_le_remove_cig_sync(struct hci_dev *hdev, u8 handle); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 5e68b3dd4422..d382679efd2b 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -111,6 +111,8 @@ struct mgmt_rp_read_index_list { #define MGMT_SETTING_WIDEBAND_SPEECH BIT(17) #define MGMT_SETTING_CIS_CENTRAL BIT(18) #define MGMT_SETTING_CIS_PERIPHERAL BIT(19) +#define MGMT_SETTING_ISO_BROADCASTER BIT(20) +#define MGMT_SETTING_ISO_SYNC_RECEIVER BIT(21) #define MGMT_OP_READ_INFO 0x0004 #define MGMT_READ_INFO_SIZE 0 diff --git a/include/net/bluetooth/sco.h b/include/net/bluetooth/sco.h index 1aa2e14b6c94..f40ddb4264fc 100644 --- a/include/net/bluetooth/sco.h +++ b/include/net/bluetooth/sco.h @@ -46,6 +46,4 @@ struct sco_conninfo { __u8 dev_class[3]; }; -#define SCO_CMSG_PKT_STATUS 0x01 - #endif /* __SCO_H */ diff --git a/include/net/dropreason.h b/include/net/dropreason.h index 685fb37df8e8..56cb7be92244 100644 --- a/include/net/dropreason.h +++ b/include/net/dropreason.h @@ -23,6 +23,12 @@ enum skb_drop_reason_subsys { */ SKB_DROP_REASON_SUBSYS_MAC80211_MONITOR, + /** + * @SKB_DROP_REASON_SUBSYS_OPENVSWITCH: openvswitch drop reasons, + * see net/openvswitch/drop.h + */ + SKB_DROP_REASON_SUBSYS_OPENVSWITCH, + /** @SKB_DROP_REASON_SUBSYS_NUM: number of subsystems defined */ SKB_DROP_REASON_SUBSYS_NUM }; diff --git a/include/net/genetlink.h b/include/net/genetlink.h index ed4622dd4828..e18a4c0d69ee 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -93,9 +93,9 @@ struct genl_family { * struct genl_info - receiving information * @snd_seq: sending sequence number * @snd_portid: netlink portid of sender + * @family: generic netlink family * @nlhdr: netlink message header * @genlhdr: generic netlink message header - * @userhdr: user specific header * @attrs: netlink attributes * @_net: network namespace * @user_ptr: user pointers @@ -104,16 +104,16 @@ struct genl_family { struct genl_info { u32 snd_seq; u32 snd_portid; - struct nlmsghdr * nlhdr; + const struct genl_family *family; + const struct nlmsghdr * nlhdr; struct genlmsghdr * genlhdr; - void * userhdr; struct nlattr ** attrs; possible_net_t _net; void * user_ptr[2]; struct netlink_ext_ack *extack; }; -static inline struct net *genl_info_net(struct genl_info *info) +static inline struct net *genl_info_net(const struct genl_info *info) { return read_pnet(&info->_net); } @@ -123,6 +123,11 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net) write_pnet(&info->_net, net); } +static inline void *genl_info_userhdr(const struct genl_info *info) +{ + return (u8 *)info->genlhdr + GENL_HDRLEN; +} + #define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg) #define GENL_SET_ERR_MSG_FMT(info, msg, args...) \ @@ -244,14 +249,13 @@ struct genl_split_ops { /** * struct genl_dumpit_info - info that is available during dumpit op call - * @family: generic netlink family - for internal genl code usage * @op: generic netlink ops - for internal genl code usage * @attrs: netlink attributes + * @info: struct genl_info describing the request */ struct genl_dumpit_info { - const struct genl_family *family; struct genl_split_ops op; - struct nlattr **attrs; + struct genl_info info; }; static inline const struct genl_dumpit_info * @@ -260,6 +264,38 @@ genl_dumpit_info(struct netlink_callback *cb) return cb->data; } +static inline const struct genl_info * +genl_info_dump(struct netlink_callback *cb) +{ + return &genl_dumpit_info(cb)->info; +} + +/** + * genl_info_init_ntf() - initialize genl_info for notifications + * @info: genl_info struct to set up + * @family: pointer to the genetlink family + * @cmd: command to be used in the notification + * + * Initialize a locally declared struct genl_info to pass to various APIs. + * Intended to be used when creating notifications. + */ +static inline void +genl_info_init_ntf(struct genl_info *info, const struct genl_family *family, + u8 cmd) +{ + struct genlmsghdr *hdr = (void *) &info->user_ptr[0]; + + memset(info, 0, sizeof(*info)); + info->family = family; + info->genlhdr = hdr; + hdr->cmd = cmd; +} + +static inline bool genl_info_is_ntf(const struct genl_info *info) +{ + return !info->nlhdr; +} + int genl_register_family(struct genl_family *family); int genl_unregister_family(const struct genl_family *family); void genl_notify(const struct genl_family *family, struct sk_buff *skb, @@ -268,6 +304,32 @@ void genl_notify(const struct genl_family *family, struct sk_buff *skb, void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, const struct genl_family *family, int flags, u8 cmd); +static inline void * +__genlmsg_iput(struct sk_buff *skb, const struct genl_info *info, int flags) +{ + return genlmsg_put(skb, info->snd_portid, info->snd_seq, info->family, + flags, info->genlhdr->cmd); +} + +/** + * genlmsg_iput - start genetlink message based on genl_info + * @skb: skb in which message header will be placed + * @info: genl_info as provided to do/dump handlers + * + * Convenience wrapper which starts a genetlink message based on + * information in user request. @info should be either the struct passed + * by genetlink core to do/dump handlers (when constructing replies to + * such requests) or a struct initialized by genl_info_init_ntf() + * when constructing notifications. + * + * Returns pointer to new genetlink header. + */ +static inline void * +genlmsg_iput(struct sk_buff *skb, const struct genl_info *info) +{ + return __genlmsg_iput(skb, info, 0); +} + /** * genlmsg_nlhdr - Obtain netlink header from user specified header * @user_hdr: user header as returned from genlmsg_put() diff --git a/include/net/inet_common.h b/include/net/inet_common.h index b86b8e21de7f..f50a644d87a9 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -40,8 +40,10 @@ int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); int inet_shutdown(struct socket *sock, int how); int inet_listen(struct socket *sock, int backlog); +int __inet_listen_sk(struct sock *sk, int backlog); void inet_sock_destruct(struct sock *sk); int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); +int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len); /* Don't allocate port at this moment, defer to connect. */ #define BIND_FORCE_ADDRESS_NO_PORT (1 << 0) /* Grab and release socket lock. */ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index c2b15f7e5516..5d2fcc137b88 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -164,7 +164,8 @@ enum inet_csk_ack_state_t { ICSK_ACK_TIMER = 2, ICSK_ACK_PUSHED = 4, ICSK_ACK_PUSHED2 = 8, - ICSK_ACK_NOW = 16 /* Send the next ACK immediately (once) */ + ICSK_ACK_NOW = 16, /* Send the next ACK immediately (once) */ + ICSK_ACK_NOMEM = 32, }; void inet_csk_init_xmit_timers(struct sock *sk, @@ -341,9 +342,9 @@ static inline bool inet_csk_in_pingpong_mode(struct sock *sk) return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH; } -static inline bool inet_csk_has_ulp(struct sock *sk) +static inline bool inet_csk_has_ulp(const struct sock *sk) { - return inet_sk(sk)->is_icsk && !!inet_csk(sk)->icsk_ulp_ops; + return inet_test_bit(IS_ICSK, sk) && !!inet_csk(sk)->icsk_ulp_ops; } #endif /* _INET_CONNECTION_SOCK_H */ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 0bb32bfc6183..acbb93d7607a 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -194,13 +194,13 @@ struct rtable; * @inet_rcv_saddr - Bound local IPv4 addr * @inet_dport - Destination port * @inet_num - Local port + * @inet_flags - various atomic flags * @inet_saddr - Sending source * @uc_ttl - Unicast TTL * @inet_sport - Source port * @inet_id - ID counter for DF pkts * @tos - TOS * @mc_ttl - Multicasting TTL - * @is_icsk - is this an inet_connection_sock? * @uc_index - Unicast outgoing device index * @mc_index - Multicast device index * @mc_list - Group array @@ -218,57 +218,88 @@ struct inet_sock { #define inet_dport sk.__sk_common.skc_dport #define inet_num sk.__sk_common.skc_num + unsigned long inet_flags; __be32 inet_saddr; __s16 uc_ttl; - __u16 cmsg_flags; - struct ip_options_rcu __rcu *inet_opt; __be16 inet_sport; + struct ip_options_rcu __rcu *inet_opt; __u16 inet_id; __u8 tos; __u8 min_ttl; __u8 mc_ttl; __u8 pmtudisc; - __u8 recverr:1, - is_icsk:1, - freebind:1, - hdrincl:1, - mc_loop:1, - transparent:1, - mc_all:1, - nodefrag:1; - __u8 bind_address_no_port:1, - recverr_rfc4884:1, - defer_connect:1; /* Indicates that fastopen_connect is set - * and cookie exists so we defer connect - * until first data frame is written - */ __u8 rcv_tos; __u8 convert_csum; int uc_index; int mc_index; __be32 mc_addr; - struct ip_mc_socklist __rcu *mc_list; - struct inet_cork_full cork; struct { __u16 lo; __u16 hi; } local_port_range; + + struct ip_mc_socklist __rcu *mc_list; + struct inet_cork_full cork; }; #define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ #define IPCORK_ALLFRAG 2 /* always fragment (for ipv6 for now) */ +enum { + INET_FLAGS_PKTINFO = 0, + INET_FLAGS_TTL = 1, + INET_FLAGS_TOS = 2, + INET_FLAGS_RECVOPTS = 3, + INET_FLAGS_RETOPTS = 4, + INET_FLAGS_PASSSEC = 5, + INET_FLAGS_ORIGDSTADDR = 6, + INET_FLAGS_CHECKSUM = 7, + INET_FLAGS_RECVFRAGSIZE = 8, + + INET_FLAGS_RECVERR = 9, + INET_FLAGS_RECVERR_RFC4884 = 10, + INET_FLAGS_FREEBIND = 11, + INET_FLAGS_HDRINCL = 12, + INET_FLAGS_MC_LOOP = 13, + INET_FLAGS_MC_ALL = 14, + INET_FLAGS_TRANSPARENT = 15, + INET_FLAGS_IS_ICSK = 16, + INET_FLAGS_NODEFRAG = 17, + INET_FLAGS_BIND_ADDRESS_NO_PORT = 18, + INET_FLAGS_DEFER_CONNECT = 19, +}; + /* cmsg flags for inet */ -#define IP_CMSG_PKTINFO BIT(0) -#define IP_CMSG_TTL BIT(1) -#define IP_CMSG_TOS BIT(2) -#define IP_CMSG_RECVOPTS BIT(3) -#define IP_CMSG_RETOPTS BIT(4) -#define IP_CMSG_PASSSEC BIT(5) -#define IP_CMSG_ORIGDSTADDR BIT(6) -#define IP_CMSG_CHECKSUM BIT(7) -#define IP_CMSG_RECVFRAGSIZE BIT(8) +#define IP_CMSG_PKTINFO BIT(INET_FLAGS_PKTINFO) +#define IP_CMSG_TTL BIT(INET_FLAGS_TTL) +#define IP_CMSG_TOS BIT(INET_FLAGS_TOS) +#define IP_CMSG_RECVOPTS BIT(INET_FLAGS_RECVOPTS) +#define IP_CMSG_RETOPTS BIT(INET_FLAGS_RETOPTS) +#define IP_CMSG_PASSSEC BIT(INET_FLAGS_PASSSEC) +#define IP_CMSG_ORIGDSTADDR BIT(INET_FLAGS_ORIGDSTADDR) +#define IP_CMSG_CHECKSUM BIT(INET_FLAGS_CHECKSUM) +#define IP_CMSG_RECVFRAGSIZE BIT(INET_FLAGS_RECVFRAGSIZE) + +#define IP_CMSG_ALL (IP_CMSG_PKTINFO | IP_CMSG_TTL | \ + IP_CMSG_TOS | IP_CMSG_RECVOPTS | \ + IP_CMSG_RETOPTS | IP_CMSG_PASSSEC | \ + IP_CMSG_ORIGDSTADDR | IP_CMSG_CHECKSUM | \ + IP_CMSG_RECVFRAGSIZE) + +static inline unsigned long inet_cmsg_flags(const struct inet_sock *inet) +{ + return READ_ONCE(inet->inet_flags) & IP_CMSG_ALL; +} + +#define inet_test_bit(nr, sk) \ + test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) +#define inet_set_bit(nr, sk) \ + set_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) +#define inet_clear_bit(nr, sk) \ + clear_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) +#define inet_assign_bit(nr, sk, val) \ + assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val) static inline bool sk_is_inet(struct sock *sk) { @@ -363,7 +394,7 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { __u8 flags = 0; - if (inet_sk(sk)->transparent || inet_sk(sk)->hdrincl) + if (inet_test_bit(TRANSPARENT, sk) || inet_test_bit(HDRINCL, sk)) flags |= FLOWI_FLAG_ANYSRC; return flags; } @@ -389,7 +420,8 @@ static inline bool inet_can_nonlocal_bind(struct net *net, struct inet_sock *inet) { return READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind) || - inet->freebind || inet->transparent; + test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) || + test_bit(INET_FLAGS_TRANSPARENT, &inet->inet_flags); } static inline bool inet_addr_valid_or_nonlocal(struct net *net, diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 05e6f756feaf..c9ff23cf313e 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -179,6 +179,9 @@ struct fib6_info { refcount_t fib6_ref; unsigned long expires; + + struct hlist_node gc_link; + struct dst_metrics *fib6_metrics; #define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1] @@ -247,19 +250,6 @@ static inline bool fib6_requires_src(const struct fib6_info *rt) return rt->fib6_src.plen > 0; } -static inline void fib6_clean_expires(struct fib6_info *f6i) -{ - f6i->fib6_flags &= ~RTF_EXPIRES; - f6i->expires = 0; -} - -static inline void fib6_set_expires(struct fib6_info *f6i, - unsigned long expires) -{ - f6i->expires = expires; - f6i->fib6_flags |= RTF_EXPIRES; -} - static inline bool fib6_check_expired(const struct fib6_info *f6i) { if (f6i->fib6_flags & RTF_EXPIRES) @@ -267,6 +257,11 @@ static inline bool fib6_check_expired(const struct fib6_info *f6i) return false; } +static inline bool fib6_has_expires(const struct fib6_info *f6i) +{ + return f6i->fib6_flags & RTF_EXPIRES; +} + /* Function to safely get fn->fn_sernum for passed in rt * and store result in passed in cookie. * Return true if we can get cookie safely @@ -388,6 +383,7 @@ struct fib6_table { struct inet_peer_base tb6_peers; unsigned int flags; unsigned int fib_seq; + struct hlist_head tb6_gc_hlist; /* GC candidates */ #define RT6_TABLE_HAS_DFLT_ROUTER BIT(0) }; @@ -504,6 +500,48 @@ void fib6_gc_cleanup(void); int fib6_init(void); +/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be + * NULL. + */ +static inline void fib6_set_expires_locked(struct fib6_info *f6i, + unsigned long expires) +{ + struct fib6_table *tb6; + + tb6 = f6i->fib6_table; + f6i->expires = expires; + if (tb6 && !fib6_has_expires(f6i)) + hlist_add_head(&f6i->gc_link, &tb6->tb6_gc_hlist); + f6i->fib6_flags |= RTF_EXPIRES; +} + +/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be + * NULL. If fib6_table is NULL, the fib6_info will no be inserted into the + * list of GC candidates until it is inserted into a table. + */ +static inline void fib6_set_expires(struct fib6_info *f6i, + unsigned long expires) +{ + spin_lock_bh(&f6i->fib6_table->tb6_lock); + fib6_set_expires_locked(f6i, expires); + spin_unlock_bh(&f6i->fib6_table->tb6_lock); +} + +static inline void fib6_clean_expires_locked(struct fib6_info *f6i) +{ + if (fib6_has_expires(f6i)) + hlist_del_init(&f6i->gc_link); + f6i->fib6_flags &= ~RTF_EXPIRES; + f6i->expires = 0; +} + +static inline void fib6_clean_expires(struct fib6_info *f6i) +{ + spin_lock_bh(&f6i->fib6_table->tb6_lock); + fib6_clean_expires_locked(f6i); + spin_unlock_bh(&f6i->fib6_table->tb6_lock); +} + struct ipv6_route_iter { struct seq_net_private p; struct fib6_walker w; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 2acc4c808d45..d40d8238d4c2 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -937,7 +937,8 @@ static inline bool ipv6_can_nonlocal_bind(struct net *net, struct inet_sock *inet) { return net->ipv6.sysctl.ip_nonlocal_bind || - inet->freebind || inet->transparent; + test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) || + test_bit(INET_FLAGS_TRANSPARENT, &inet->inet_flags); } /* Sysctl settings for net ipv6.auto_flowlabels */ @@ -1216,6 +1217,7 @@ void inet6_cleanup_sock(struct sock *sk); void inet6_sock_destruct(struct sock *sk); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); +int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 879990101c9f..9f70b4332238 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -352,6 +352,13 @@ struct mana_tx_qp { struct mana_ethtool_stats { u64 stop_queue; u64 wake_queue; + u64 hc_tx_bytes; + u64 hc_tx_ucast_pkts; + u64 hc_tx_ucast_bytes; + u64 hc_tx_bcast_pkts; + u64 hc_tx_bcast_bytes; + u64 hc_tx_mcast_pkts; + u64 hc_tx_mcast_bytes; u64 tx_cqe_err; u64 tx_cqe_unknown_type; u64 rx_coalesced_err; @@ -442,6 +449,7 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); +void mana_query_gf_stats(struct mana_port_context *apc); extern const struct ethtool_ops mana_ethtool_ops; @@ -583,6 +591,49 @@ struct mana_fence_rq_resp { struct gdma_resp_hdr hdr; }; /* HW DATA */ +/* Query stats RQ */ +struct mana_query_gf_stat_req { + struct gdma_req_hdr hdr; + u64 req_stats; +}; /* HW DATA */ + +struct mana_query_gf_stat_resp { + struct gdma_resp_hdr hdr; + u64 reported_stats; + /* rx errors/discards */ + u64 discard_rx_nowqe; + u64 err_rx_vport_disabled; + /* rx bytes/packets */ + u64 hc_rx_bytes; + u64 hc_rx_ucast_pkts; + u64 hc_rx_ucast_bytes; + u64 hc_rx_bcast_pkts; + u64 hc_rx_bcast_bytes; + u64 hc_rx_mcast_pkts; + u64 hc_rx_mcast_bytes; + /* tx errors */ + u64 err_tx_gf_disabled; + u64 err_tx_vport_disabled; + u64 err_tx_inval_vport_offset_pkt; + u64 err_tx_vlan_enforcement; + u64 err_tx_ethtype_enforcement; + u64 err_tx_SA_enforecement; + u64 err_tx_SQPDID_enforcement; + u64 err_tx_CQPDID_enforcement; + u64 err_tx_mtu_violation; + u64 err_tx_inval_oob; + /* tx bytes/packets */ + u64 hc_tx_bytes; + u64 hc_tx_ucast_pkts; + u64 hc_tx_ucast_bytes; + u64 hc_tx_bcast_pkts; + u64 hc_tx_bcast_bytes; + u64 hc_tx_mcast_pkts; + u64 hc_tx_mcast_bytes; + /* tx error */ + u64 err_tx_gdma; +}; /* HW DATA */ + /* Configure vPort Rx Steering */ struct mana_cfg_rx_steer_req_v2 { struct gdma_req_hdr hdr; @@ -662,6 +713,42 @@ struct mana_deregister_filter_resp { struct gdma_resp_hdr hdr; }; /* HW DATA */ +/* Requested GF stats Flags */ +/* Rx discards/Errors */ +#define STATISTICS_FLAGS_RX_DISCARDS_NO_WQE 0x0000000000000001 +#define STATISTICS_FLAGS_RX_ERRORS_VPORT_DISABLED 0x0000000000000002 +/* Rx bytes/pkts */ +#define STATISTICS_FLAGS_HC_RX_BYTES 0x0000000000000004 +#define STATISTICS_FLAGS_HC_RX_UCAST_PACKETS 0x0000000000000008 +#define STATISTICS_FLAGS_HC_RX_UCAST_BYTES 0x0000000000000010 +#define STATISTICS_FLAGS_HC_RX_MCAST_PACKETS 0x0000000000000020 +#define STATISTICS_FLAGS_HC_RX_MCAST_BYTES 0x0000000000000040 +#define STATISTICS_FLAGS_HC_RX_BCAST_PACKETS 0x0000000000000080 +#define STATISTICS_FLAGS_HC_RX_BCAST_BYTES 0x0000000000000100 +/* Tx errors */ +#define STATISTICS_FLAGS_TX_ERRORS_GF_DISABLED 0x0000000000000200 +#define STATISTICS_FLAGS_TX_ERRORS_VPORT_DISABLED 0x0000000000000400 +#define STATISTICS_FLAGS_TX_ERRORS_INVAL_VPORT_OFFSET_PACKETS \ + 0x0000000000000800 +#define STATISTICS_FLAGS_TX_ERRORS_VLAN_ENFORCEMENT 0x0000000000001000 +#define STATISTICS_FLAGS_TX_ERRORS_ETH_TYPE_ENFORCEMENT \ + 0x0000000000002000 +#define STATISTICS_FLAGS_TX_ERRORS_SA_ENFORCEMENT 0x0000000000004000 +#define STATISTICS_FLAGS_TX_ERRORS_SQPDID_ENFORCEMENT 0x0000000000008000 +#define STATISTICS_FLAGS_TX_ERRORS_CQPDID_ENFORCEMENT 0x0000000000010000 +#define STATISTICS_FLAGS_TX_ERRORS_MTU_VIOLATION 0x0000000000020000 +#define STATISTICS_FLAGS_TX_ERRORS_INVALID_OOB 0x0000000000040000 +/* Tx bytes/pkts */ +#define STATISTICS_FLAGS_HC_TX_BYTES 0x0000000000080000 +#define STATISTICS_FLAGS_HC_TX_UCAST_PACKETS 0x0000000000100000 +#define STATISTICS_FLAGS_HC_TX_UCAST_BYTES 0x0000000000200000 +#define STATISTICS_FLAGS_HC_TX_MCAST_PACKETS 0x0000000000400000 +#define STATISTICS_FLAGS_HC_TX_MCAST_BYTES 0x0000000000800000 +#define STATISTICS_FLAGS_HC_TX_BCAST_PACKETS 0x0000000001000000 +#define STATISTICS_FLAGS_HC_TX_BCAST_BYTES 0x0000000002000000 +/* Tx error */ +#define STATISTICS_FLAGS_TX_ERRORS_GDMA_ERROR 0x0000000004000000 + #define MANA_MAX_NUM_QUEUES 64 #define MANA_SHORT_VPORT_OFFSET_MAX ((1U << 8) - 1) diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index 8c77832d0240..cc8060c017d5 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -2,8 +2,6 @@ #ifndef _NETNS_NFTABLES_H_ #define _NETNS_NFTABLES_H_ -#include <linux/list.h> - struct netns_nftables { u8 gencursor; }; diff --git a/include/net/route.h b/include/net/route.h index d9ca98d2366f..51a45b1887b5 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -298,7 +298,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, { __u8 flow_flags = 0; - if (inet_sk(sk)->transparent) + if (inet_test_bit(TRANSPARENT, sk)) flow_flags |= FLOWI_FLAG_ANYSRC; flowi4_init_output(fl4, oif, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk), diff --git a/include/net/tcp.h b/include/net/tcp.h index 6d77c08d83b7..07b21d9a9620 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2031,7 +2031,7 @@ static inline bool inet_sk_transparent(const struct sock *sk) case TCP_NEW_SYN_RECV: return inet_rsk(inet_reqsk(sk))->no_srccheck; } - return inet_sk(sk)->transparent; + return inet_test_bit(TRANSPARENT, sk); } /* Determines whether this is a thin stream (which may suffer from diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index e94870e77ee9..efc82c318fa2 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -965,6 +965,7 @@ struct check_pkt_len_arg { * start of the packet or at the start of the l3 header depending on the value * of l3 tunnel flag in the tun_flags field of OVS_ACTION_ATTR_ADD_MPLS * argument. + * @OVS_ACTION_ATTR_DROP: Explicit drop action. * * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all * fields within a header are modifiable, e.g. the IPv4 protocol and fragment @@ -1002,6 +1003,7 @@ enum ovs_action_attr { OVS_ACTION_ATTR_CHECK_PKT_LEN, /* Nested OVS_CHECK_PKT_LEN_ATTR_*. */ OVS_ACTION_ATTR_ADD_MPLS, /* struct ovs_action_add_mpls. */ OVS_ACTION_ATTR_DEC_TTL, /* Nested OVS_DEC_TTL_ATTR_*. */ + OVS_ACTION_ATTR_DROP, /* u32 error code. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/mm/vmpressure.c b/mm/vmpressure.c index b52644771cc4..22c6689d9302 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -244,6 +244,14 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, if (mem_cgroup_disabled()) return; + /* + * The in-kernel users only care about the reclaim efficiency + * for this @memcg rather than the whole subtree, and there + * isn't and won't be any in-kernel user in a legacy cgroup. + */ + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !tree) + return; + vmpr = memcg_to_vmpressure(memcg); /* diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 1c3c7ff5c3c6..336a76165454 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -140,6 +140,35 @@ static int bt_sock_create(struct net *net, struct socket *sock, int proto, return err; } +struct sock *bt_sock_alloc(struct net *net, struct socket *sock, + struct proto *prot, int proto, gfp_t prio, int kern) +{ + struct sock *sk; + + sk = sk_alloc(net, PF_BLUETOOTH, prio, prot, kern); + if (!sk) + return NULL; + + sock_init_data(sock, sk); + INIT_LIST_HEAD(&bt_sk(sk)->accept_q); + + sock_reset_flag(sk, SOCK_ZAPPED); + + sk->sk_protocol = proto; + sk->sk_state = BT_OPEN; + + /* Init peer information so it can be properly monitored */ + if (!kern) { + spin_lock(&sk->sk_peer_lock); + sk->sk_peer_pid = get_pid(task_tgid(current)); + sk->sk_peer_cred = get_current_cred(); + spin_unlock(&sk->sk_peer_lock); + } + + return sk; +} +EXPORT_SYMBOL(bt_sock_alloc); + void bt_sock_link(struct bt_sock_list *l, struct sock *sk) { write_lock(&l->lock); @@ -158,6 +187,9 @@ EXPORT_SYMBOL(bt_sock_unlink); void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh) { + const struct cred *old_cred; + struct pid *old_pid; + BT_DBG("parent %p, sk %p", parent, sk); sock_hold(sk); @@ -170,6 +202,19 @@ void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh) list_add_tail(&bt_sk(sk)->accept_q, &bt_sk(parent)->accept_q); bt_sk(sk)->parent = parent; + /* Copy credentials from parent since for incoming connections the + * socket is allocated by the kernel. + */ + spin_lock(&sk->sk_peer_lock); + old_pid = sk->sk_peer_pid; + old_cred = sk->sk_peer_cred; + sk->sk_peer_pid = get_pid(parent->sk_peer_pid); + sk->sk_peer_cred = get_cred(parent->sk_peer_cred); + spin_unlock(&sk->sk_peer_lock); + + put_pid(old_pid); + put_cred(old_cred); + if (bh) bh_unlock_sock(sk); else @@ -288,8 +333,12 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, bt_sk(sk)->skb_msg_name(skb, msg->msg_name, &msg->msg_namelen); - if (bt_sk(sk)->skb_put_cmsg) - bt_sk(sk)->skb_put_cmsg(skb, msg, sk); + if (test_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags)) { + u8 pkt_status = hci_skb_pkt_status(skb); + + put_cmsg(msg, SOL_BLUETOOTH, BT_SCM_PKT_STATUS, + sizeof(pkt_status), &pkt_status); + } } skb_free_datagram(sk, skb); diff --git a/net/bluetooth/amp.h b/net/bluetooth/amp.h index 832764dfbfb3..97c87abd129f 100644 --- a/net/bluetooth/amp.h +++ b/net/bluetooth/amp.h @@ -28,7 +28,6 @@ struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr, int phylink_gen_key(struct hci_conn *hcon, u8 *data, u8 *len, u8 *type); -void amp_read_loc_info(struct hci_dev *hdev, struct amp_mgr *mgr); void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle); void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr); void amp_read_loc_assoc_final_data(struct hci_dev *hdev, diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c index 57d509d77cb4..00d47bcf4d7d 100644 --- a/net/bluetooth/bnep/sock.c +++ b/net/bluetooth/bnep/sock.c @@ -205,21 +205,13 @@ static int bnep_sock_create(struct net *net, struct socket *sock, int protocol, if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; - sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &bnep_proto, kern); + sk = bt_sock_alloc(net, sock, &bnep_proto, protocol, GFP_ATOMIC, kern); if (!sk) return -ENOMEM; - sock_init_data(sock, sk); - sock->ops = &bnep_sock_ops; - sock->state = SS_UNCONNECTED; - sock_reset_flag(sk, SOCK_ZAPPED); - - sk->sk_protocol = protocol; - sk->sk_state = BT_OPEN; - bt_sock_link(&bnep_sk_list, sk); return 0; } diff --git a/net/bluetooth/coredump.c b/net/bluetooth/coredump.c index d2d2624ec708..ec97a4bab1c9 100644 --- a/net/bluetooth/coredump.c +++ b/net/bluetooth/coredump.c @@ -100,8 +100,7 @@ void hci_devcd_reset(struct hci_dev *hdev) /* Call with hci_dev_lock only. */ static void hci_devcd_free(struct hci_dev *hdev) { - if (hdev->dump.head) - vfree(hdev->dump.head); + vfree(hdev->dump.head); hci_devcd_reset(hdev); } diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 76222565e2df..234746721047 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -178,57 +178,6 @@ static void hci_conn_cleanup(struct hci_conn *conn) hci_conn_put(conn); } -static void le_scan_cleanup(struct work_struct *work) -{ - struct hci_conn *conn = container_of(work, struct hci_conn, - le_scan_cleanup); - struct hci_dev *hdev = conn->hdev; - struct hci_conn *c = NULL; - - BT_DBG("%s hcon %p", hdev->name, conn); - - hci_dev_lock(hdev); - - /* Check that the hci_conn is still around */ - rcu_read_lock(); - list_for_each_entry_rcu(c, &hdev->conn_hash.list, list) { - if (c == conn) - break; - } - rcu_read_unlock(); - - if (c == conn) { - hci_connect_le_scan_cleanup(conn, 0x00); - hci_conn_cleanup(conn); - } - - hci_dev_unlock(hdev); - hci_dev_put(hdev); - hci_conn_put(conn); -} - -static void hci_connect_le_scan_remove(struct hci_conn *conn) -{ - BT_DBG("%s hcon %p", conn->hdev->name, conn); - - /* We can't call hci_conn_del/hci_conn_cleanup here since that - * could deadlock with another hci_conn_del() call that's holding - * hci_dev_lock and doing cancel_delayed_work_sync(&conn->disc_work). - * Instead, grab temporary extra references to the hci_dev and - * hci_conn and perform the necessary cleanup in a separate work - * callback. - */ - - hci_dev_hold(conn->hdev); - hci_conn_get(conn); - - /* Even though we hold a reference to the hdev, many other - * things might get cleaned up meanwhile, including the hdev's - * own workqueue, so we can't use that for scheduling. - */ - schedule_work(&conn->le_scan_cleanup); -} - static void hci_acl_create_connection(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; @@ -679,13 +628,6 @@ static void hci_conn_timeout(struct work_struct *work) if (refcnt > 0) return; - /* LE connections in scanning state need special handling */ - if (conn->state == BT_CONNECT && conn->type == LE_LINK && - test_bit(HCI_CONN_SCANNING, &conn->flags)) { - hci_connect_le_scan_remove(conn); - return; - } - hci_abort_conn(conn, hci_proto_disconn_ind(conn)); } @@ -791,7 +733,8 @@ struct iso_list_data { u16 sync_handle; }; int count; - struct iso_cig_params pdu; + bool big_term; + bool big_sync_term; }; static void bis_list(struct hci_conn *conn, void *data) @@ -809,17 +752,6 @@ static void bis_list(struct hci_conn *conn, void *data) d->count++; } -static void find_bis(struct hci_conn *conn, void *data) -{ - struct iso_list_data *d = data; - - /* Ignore unicast */ - if (bacmp(&conn->dst, BDADDR_ANY)) - return; - - d->count++; -} - static int terminate_big_sync(struct hci_dev *hdev, void *data) { struct iso_list_data *d = data; @@ -828,11 +760,8 @@ static int terminate_big_sync(struct hci_dev *hdev, void *data) hci_remove_ext_adv_instance_sync(hdev, d->bis, NULL); - /* Check if ISO connection is a BIS and terminate BIG if there are - * no other connections using it. - */ - hci_conn_hash_list_state(hdev, find_bis, ISO_LINK, BT_CONNECTED, d); - if (d->count) + /* Only terminate BIG if it has been created */ + if (!d->big_term) return 0; return hci_le_terminate_big_sync(hdev, d->big, @@ -844,19 +773,21 @@ static void terminate_big_destroy(struct hci_dev *hdev, void *data, int err) kfree(data); } -static int hci_le_terminate_big(struct hci_dev *hdev, u8 big, u8 bis) +static int hci_le_terminate_big(struct hci_dev *hdev, struct hci_conn *conn) { struct iso_list_data *d; int ret; - bt_dev_dbg(hdev, "big 0x%2.2x bis 0x%2.2x", big, bis); + bt_dev_dbg(hdev, "big 0x%2.2x bis 0x%2.2x", conn->iso_qos.bcast.big, + conn->iso_qos.bcast.bis); d = kzalloc(sizeof(*d), GFP_KERNEL); if (!d) return -ENOMEM; - d->big = big; - d->bis = bis; + d->big = conn->iso_qos.bcast.big; + d->bis = conn->iso_qos.bcast.bis; + d->big_term = test_and_clear_bit(HCI_CONN_BIG_CREATED, &conn->flags); ret = hci_cmd_sync_queue(hdev, terminate_big_sync, d, terminate_big_destroy); @@ -873,31 +804,26 @@ static int big_terminate_sync(struct hci_dev *hdev, void *data) bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", d->big, d->sync_handle); - /* Check if ISO connection is a BIS and terminate BIG if there are - * no other connections using it. - */ - hci_conn_hash_list_state(hdev, find_bis, ISO_LINK, BT_CONNECTED, d); - if (d->count) - return 0; - - hci_le_big_terminate_sync(hdev, d->big); + if (d->big_sync_term) + hci_le_big_terminate_sync(hdev, d->big); return hci_le_pa_terminate_sync(hdev, d->sync_handle); } -static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, u16 sync_handle) +static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *conn) { struct iso_list_data *d; int ret; - bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", big, sync_handle); + bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", big, conn->sync_handle); d = kzalloc(sizeof(*d), GFP_KERNEL); if (!d) return -ENOMEM; d->big = big; - d->sync_handle = sync_handle; + d->sync_handle = conn->sync_handle; + d->big_sync_term = test_and_clear_bit(HCI_CONN_BIG_SYNC, &conn->flags); ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d, terminate_big_destroy); @@ -916,6 +842,7 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, u16 sync_handle) static void bis_cleanup(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; + struct hci_conn *bis; bt_dev_dbg(hdev, "conn %p", conn); @@ -923,17 +850,29 @@ static void bis_cleanup(struct hci_conn *conn) if (!test_and_clear_bit(HCI_CONN_PER_ADV, &conn->flags)) return; - hci_le_terminate_big(hdev, conn->iso_qos.bcast.big, - conn->iso_qos.bcast.bis); + /* Check if ISO connection is a BIS and terminate advertising + * set and BIG if there are no other connections using it. + */ + bis = hci_conn_hash_lookup_big(hdev, conn->iso_qos.bcast.big); + if (bis) + return; + + hci_le_terminate_big(hdev, conn); } else { + bis = hci_conn_hash_lookup_big_any_dst(hdev, + conn->iso_qos.bcast.big); + + if (bis) + return; + hci_le_big_terminate(hdev, conn->iso_qos.bcast.big, - conn->sync_handle); + conn); } } static int remove_cig_sync(struct hci_dev *hdev, void *data) { - u8 handle = PTR_ERR(data); + u8 handle = PTR_UINT(data); return hci_le_remove_cig_sync(hdev, handle); } @@ -942,7 +881,8 @@ static int hci_le_remove_cig(struct hci_dev *hdev, u8 handle) { bt_dev_dbg(hdev, "handle 0x%2.2x", handle); - return hci_cmd_sync_queue(hdev, remove_cig_sync, ERR_PTR(handle), NULL); + return hci_cmd_sync_queue(hdev, remove_cig_sync, UINT_PTR(handle), + NULL); } static void find_cis(struct hci_conn *conn, void *data) @@ -983,6 +923,25 @@ static void cis_cleanup(struct hci_conn *conn) hci_le_remove_cig(hdev, conn->iso_qos.ucast.cig); } +static u16 hci_conn_hash_alloc_unset(struct hci_dev *hdev) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + u16 handle = HCI_CONN_HANDLE_MAX + 1; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + /* Find the first unused handle */ + if (handle == 0xffff || c->handle != handle) + break; + handle++; + } + rcu_read_unlock(); + + return handle; +} + struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role) { @@ -996,7 +955,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, bacpy(&conn->dst, dst); bacpy(&conn->src, &hdev->bdaddr); - conn->handle = HCI_CONN_HANDLE_UNSET; + conn->handle = hci_conn_hash_alloc_unset(hdev); conn->hdev = hdev; conn->type = type; conn->role = role; @@ -1059,7 +1018,6 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, INIT_DELAYED_WORK(&conn->auto_accept_work, hci_conn_auto_accept); INIT_DELAYED_WORK(&conn->idle_work, hci_conn_idle); INIT_DELAYED_WORK(&conn->le_conn_timeout, le_conn_timeout); - INIT_WORK(&conn->le_scan_cleanup, le_scan_cleanup); atomic_set(&conn->refcnt, 0); @@ -1109,7 +1067,7 @@ static void hci_conn_unlink(struct hci_conn *conn) */ if ((child->type == SCO_LINK || child->type == ESCO_LINK) && - child->handle == HCI_CONN_HANDLE_UNSET) + HCI_CONN_HANDLE_UNSET(child->handle)) hci_conn_del(child); } @@ -1273,9 +1231,41 @@ void hci_conn_failed(struct hci_conn *conn, u8 status) hci_conn_del(conn); } +/* This function requires the caller holds hdev->lock */ +u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle) +{ + struct hci_dev *hdev = conn->hdev; + + bt_dev_dbg(hdev, "hcon %p handle 0x%4.4x", conn, handle); + + if (conn->handle == handle) + return 0; + + if (handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", + handle, HCI_CONN_HANDLE_MAX); + return HCI_ERROR_INVALID_PARAMETERS; + } + + /* If abort_reason has been sent it means the connection is being + * aborted and the handle shall not be changed. + */ + if (conn->abort_reason) + return conn->abort_reason; + + conn->handle = handle; + + return 0; +} + static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) { - struct hci_conn *conn = data; + struct hci_conn *conn; + u16 handle = PTR_UINT(data); + + conn = hci_conn_hash_lookup_handle(hdev, handle); + if (!conn) + return; bt_dev_dbg(hdev, "err %d", err); @@ -1300,10 +1290,17 @@ done: static int hci_connect_le_sync(struct hci_dev *hdev, void *data) { - struct hci_conn *conn = data; + struct hci_conn *conn; + u16 handle = PTR_UINT(data); + + conn = hci_conn_hash_lookup_handle(hdev, handle); + if (!conn) + return 0; bt_dev_dbg(hdev, "conn %p", conn); + conn->state = BT_CONNECT; + return hci_le_create_conn_sync(hdev, conn); } @@ -1373,10 +1370,10 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, conn->sec_level = BT_SECURITY_LOW; conn->conn_timeout = conn_timeout; - conn->state = BT_CONNECT; clear_bit(HCI_CONN_SCANNING, &conn->flags); - err = hci_cmd_sync_queue(hdev, hci_connect_le_sync, conn, + err = hci_cmd_sync_queue(hdev, hci_connect_le_sync, + UINT_PTR(conn->handle), create_le_conn_complete); if (err) { hci_conn_del(conn); @@ -1440,25 +1437,23 @@ static int hci_explicit_conn_params_set(struct hci_dev *hdev, static int qos_set_big(struct hci_dev *hdev, struct bt_iso_qos *qos) { - struct iso_list_data data; + struct hci_conn *conn; + u8 big; /* Allocate a BIG if not set */ if (qos->bcast.big == BT_ISO_QOS_BIG_UNSET) { - for (data.big = 0x00; data.big < 0xef; data.big++) { - data.count = 0; - data.bis = 0xff; + for (big = 0x00; big < 0xef; big++) { - hci_conn_hash_list_state(hdev, bis_list, ISO_LINK, - BT_BOUND, &data); - if (!data.count) + conn = hci_conn_hash_lookup_big(hdev, big); + if (!conn) break; } - if (data.big == 0xef) + if (big == 0xef) return -EADDRNOTAVAIL; /* Update BIG */ - qos->bcast.big = data.big; + qos->bcast.big = big; } return 0; @@ -1466,28 +1461,27 @@ static int qos_set_big(struct hci_dev *hdev, struct bt_iso_qos *qos) static int qos_set_bis(struct hci_dev *hdev, struct bt_iso_qos *qos) { - struct iso_list_data data; + struct hci_conn *conn; + u8 bis; /* Allocate BIS if not set */ if (qos->bcast.bis == BT_ISO_QOS_BIS_UNSET) { /* Find an unused adv set to advertise BIS, skip instance 0x00 * since it is reserved as general purpose set. */ - for (data.bis = 0x01; data.bis < hdev->le_num_of_adv_sets; - data.bis++) { - data.count = 0; + for (bis = 0x01; bis < hdev->le_num_of_adv_sets; + bis++) { - hci_conn_hash_list_state(hdev, bis_list, ISO_LINK, - BT_BOUND, &data); - if (!data.count) + conn = hci_conn_hash_lookup_bis(hdev, BDADDR_ANY, bis); + if (!conn) break; } - if (data.bis == hdev->le_num_of_adv_sets) + if (bis == hdev->le_num_of_adv_sets) return -EADDRNOTAVAIL; /* Update BIS */ - qos->bcast.bis = data.bis; + qos->bcast.bis = bis; } return 0; @@ -1495,10 +1489,10 @@ static int qos_set_bis(struct hci_dev *hdev, struct bt_iso_qos *qos) /* This function requires the caller holds hdev->lock */ static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst, - struct bt_iso_qos *qos) + struct bt_iso_qos *qos, __u8 base_len, + __u8 *base) { struct hci_conn *conn; - struct iso_list_data data; int err; /* Let's make sure that le is enabled.*/ @@ -1516,24 +1510,26 @@ static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst, if (err) return ERR_PTR(err); - data.big = qos->bcast.big; - data.bis = qos->bcast.bis; - data.count = 0; - - /* Check if there is already a matching BIG/BIS */ - hci_conn_hash_list_state(hdev, bis_list, ISO_LINK, BT_BOUND, &data); - if (data.count) + /* Check if the LE Create BIG command has already been sent */ + conn = hci_conn_hash_lookup_per_adv_bis(hdev, dst, qos->bcast.big, + qos->bcast.big); + if (conn) return ERR_PTR(-EADDRINUSE); - conn = hci_conn_hash_lookup_bis(hdev, dst, qos->bcast.big, qos->bcast.bis); - if (conn) + /* Check BIS settings against other bound BISes, since all + * BISes in a BIG must have the same value for all parameters + */ + conn = hci_conn_hash_lookup_big(hdev, qos->bcast.big); + + if (conn && (memcmp(qos, &conn->iso_qos, sizeof(*qos)) || + base_len != conn->le_per_adv_data_len || + memcmp(conn->le_per_adv_data, base, base_len))) return ERR_PTR(-EADDRINUSE); conn = hci_conn_add(hdev, ISO_LINK, dst, HCI_ROLE_MASTER); if (!conn) return ERR_PTR(-ENOMEM); - set_bit(HCI_CONN_PER_ADV, &conn->flags); conn->state = BT_CONNECT; hci_conn_hold(conn); @@ -1707,52 +1703,25 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, return sco; } -static void cis_add(struct iso_list_data *d, struct bt_iso_qos *qos) -{ - struct hci_cis_params *cis = &d->pdu.cis[d->pdu.cp.num_cis]; - - cis->cis_id = qos->ucast.cis; - cis->c_sdu = cpu_to_le16(qos->ucast.out.sdu); - cis->p_sdu = cpu_to_le16(qos->ucast.in.sdu); - cis->c_phy = qos->ucast.out.phy ? qos->ucast.out.phy : qos->ucast.in.phy; - cis->p_phy = qos->ucast.in.phy ? qos->ucast.in.phy : qos->ucast.out.phy; - cis->c_rtn = qos->ucast.out.rtn; - cis->p_rtn = qos->ucast.in.rtn; - - d->pdu.cp.num_cis++; -} - -static void cis_list(struct hci_conn *conn, void *data) -{ - struct iso_list_data *d = data; - - /* Skip if broadcast/ANY address */ - if (!bacmp(&conn->dst, BDADDR_ANY)) - return; - - if (d->cig != conn->iso_qos.ucast.cig || d->cis == BT_ISO_QOS_CIS_UNSET || - d->cis != conn->iso_qos.ucast.cis) - return; - - d->count++; - - if (d->pdu.cp.cig_id == BT_ISO_QOS_CIG_UNSET || - d->count >= ARRAY_SIZE(d->pdu.cis)) - return; - - cis_add(d, &conn->iso_qos); -} - static int hci_le_create_big(struct hci_conn *conn, struct bt_iso_qos *qos) { struct hci_dev *hdev = conn->hdev; struct hci_cp_le_create_big cp; + struct iso_list_data data; memset(&cp, 0, sizeof(cp)); + data.big = qos->bcast.big; + data.bis = qos->bcast.bis; + data.count = 0; + + /* Create a BIS for each bound connection */ + hci_conn_hash_list_state(hdev, bis_list, ISO_LINK, + BT_BOUND, &data); + cp.handle = qos->bcast.big; cp.adv_handle = qos->bcast.bis; - cp.num_bis = 0x01; + cp.num_bis = data.count; hci_cpu_to_le24(qos->bcast.out.interval, cp.bis.sdu_interval); cp.bis.sdu = cpu_to_le16(qos->bcast.out.sdu); cp.bis.latency = cpu_to_le16(qos->bcast.out.latency); @@ -1766,25 +1735,62 @@ static int hci_le_create_big(struct hci_conn *conn, struct bt_iso_qos *qos) return hci_send_cmd(hdev, HCI_OP_LE_CREATE_BIG, sizeof(cp), &cp); } -static void set_cig_params_complete(struct hci_dev *hdev, void *data, int err) +static int set_cig_params_sync(struct hci_dev *hdev, void *data) { - struct iso_cig_params *pdu = data; + u8 cig_id = PTR_UINT(data); + struct hci_conn *conn; + struct bt_iso_qos *qos; + struct iso_cig_params pdu; + u8 cis_id; - bt_dev_dbg(hdev, ""); + conn = hci_conn_hash_lookup_cig(hdev, cig_id); + if (!conn) + return 0; - if (err) - bt_dev_err(hdev, "Unable to set CIG parameters: %d", err); + memset(&pdu, 0, sizeof(pdu)); - kfree(pdu); -} + qos = &conn->iso_qos; + pdu.cp.cig_id = cig_id; + hci_cpu_to_le24(qos->ucast.out.interval, pdu.cp.c_interval); + hci_cpu_to_le24(qos->ucast.in.interval, pdu.cp.p_interval); + pdu.cp.sca = qos->ucast.sca; + pdu.cp.packing = qos->ucast.packing; + pdu.cp.framing = qos->ucast.framing; + pdu.cp.c_latency = cpu_to_le16(qos->ucast.out.latency); + pdu.cp.p_latency = cpu_to_le16(qos->ucast.in.latency); + + /* Reprogram all CIS(s) with the same CIG, valid range are: + * num_cis: 0x00 to 0x1F + * cis_id: 0x00 to 0xEF + */ + for (cis_id = 0x00; cis_id < 0xf0 && + pdu.cp.num_cis < ARRAY_SIZE(pdu.cis); cis_id++) { + struct hci_cis_params *cis; -static int set_cig_params_sync(struct hci_dev *hdev, void *data) -{ - struct iso_cig_params *pdu = data; - u32 plen; + conn = hci_conn_hash_lookup_cis(hdev, NULL, 0, cig_id, cis_id); + if (!conn) + continue; + + qos = &conn->iso_qos; + + cis = &pdu.cis[pdu.cp.num_cis++]; + cis->cis_id = cis_id; + cis->c_sdu = cpu_to_le16(conn->iso_qos.ucast.out.sdu); + cis->p_sdu = cpu_to_le16(conn->iso_qos.ucast.in.sdu); + cis->c_phy = qos->ucast.out.phy ? qos->ucast.out.phy : + qos->ucast.in.phy; + cis->p_phy = qos->ucast.in.phy ? qos->ucast.in.phy : + qos->ucast.out.phy; + cis->c_rtn = qos->ucast.out.rtn; + cis->p_rtn = qos->ucast.in.rtn; + } + + if (!pdu.cp.num_cis) + return 0; - plen = sizeof(pdu->cp) + pdu->cp.num_cis * sizeof(pdu->cis[0]); - return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_CIG_PARAMS, plen, pdu, + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_CIG_PARAMS, + sizeof(pdu.cp) + + pdu.cp.num_cis * sizeof(pdu.cis[0]), &pdu, HCI_CMD_TIMEOUT); } @@ -1792,7 +1798,6 @@ static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos) { struct hci_dev *hdev = conn->hdev; struct iso_list_data data; - struct iso_cig_params *pdu; memset(&data, 0, sizeof(data)); @@ -1819,58 +1824,31 @@ static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos) qos->ucast.cig = data.cig; } - data.pdu.cp.cig_id = qos->ucast.cig; - hci_cpu_to_le24(qos->ucast.out.interval, data.pdu.cp.c_interval); - hci_cpu_to_le24(qos->ucast.in.interval, data.pdu.cp.p_interval); - data.pdu.cp.sca = qos->ucast.sca; - data.pdu.cp.packing = qos->ucast.packing; - data.pdu.cp.framing = qos->ucast.framing; - data.pdu.cp.c_latency = cpu_to_le16(qos->ucast.out.latency); - data.pdu.cp.p_latency = cpu_to_le16(qos->ucast.in.latency); - if (qos->ucast.cis != BT_ISO_QOS_CIS_UNSET) { - data.count = 0; - data.cig = qos->ucast.cig; - data.cis = qos->ucast.cis; - - hci_conn_hash_list_state(hdev, cis_list, ISO_LINK, BT_BOUND, - &data); - if (data.count) + if (hci_conn_hash_lookup_cis(hdev, NULL, 0, qos->ucast.cig, + qos->ucast.cis)) return false; - - cis_add(&data, qos); + goto done; } - /* Reprogram all CIS(s) with the same CIG */ - for (data.cig = qos->ucast.cig, data.cis = 0x00; data.cis < 0x11; + /* Allocate first available CIS if not set */ + for (data.cig = qos->ucast.cig, data.cis = 0x00; data.cis < 0xf0; data.cis++) { - data.count = 0; - - hci_conn_hash_list_state(hdev, cis_list, ISO_LINK, BT_BOUND, - &data); - if (data.count) - continue; - - /* Allocate a CIS if not set */ - if (qos->ucast.cis == BT_ISO_QOS_CIS_UNSET) { + if (!hci_conn_hash_lookup_cis(hdev, NULL, 0, data.cig, + data.cis)) { /* Update CIS */ qos->ucast.cis = data.cis; - cis_add(&data, qos); + break; } } - if (qos->ucast.cis == BT_ISO_QOS_CIS_UNSET || !data.pdu.cp.num_cis) + if (qos->ucast.cis == BT_ISO_QOS_CIS_UNSET) return false; - pdu = kmemdup(&data.pdu, sizeof(*pdu), GFP_KERNEL); - if (!pdu) - return false; - - if (hci_cmd_sync_queue(hdev, set_cig_params_sync, pdu, - set_cig_params_complete) < 0) { - kfree(pdu); +done: + if (hci_cmd_sync_queue(hdev, set_cig_params_sync, + UINT_PTR(qos->ucast.cig), NULL) < 0) return false; - } return true; } @@ -1888,6 +1866,8 @@ struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, return ERR_PTR(-ENOMEM); cis->cleanup = cis_cleanup; cis->dst_type = dst_type; + cis->iso_qos.ucast.cig = BT_ISO_QOS_CIG_UNSET; + cis->iso_qos.ucast.cis = BT_ISO_QOS_CIS_UNSET; } if (cis->state == BT_CONNECTED) @@ -1931,6 +1911,8 @@ struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, return ERR_PTR(-EINVAL); } + hci_conn_hold(cis); + cis->iso_qos = *qos; cis->state = BT_BOUND; @@ -1969,59 +1951,47 @@ bool hci_iso_setup_path(struct hci_conn *conn) return true; } -static int hci_create_cis_sync(struct hci_dev *hdev, void *data) +int hci_conn_check_create_cis(struct hci_conn *conn) { - return hci_le_create_cis_sync(hdev, data); -} + if (conn->type != ISO_LINK || !bacmp(&conn->dst, BDADDR_ANY)) + return -EINVAL; -int hci_le_create_cis(struct hci_conn *conn) -{ - struct hci_conn *cis; - struct hci_link *link, *t; - struct hci_dev *hdev = conn->hdev; - int err; + if (!conn->parent || conn->parent->state != BT_CONNECTED || + conn->state != BT_CONNECT || HCI_CONN_HANDLE_UNSET(conn->handle)) + return 1; - bt_dev_dbg(hdev, "hcon %p", conn); + return 0; +} - switch (conn->type) { - case LE_LINK: - if (conn->state != BT_CONNECTED || list_empty(&conn->link_list)) - return -EINVAL; +static int hci_create_cis_sync(struct hci_dev *hdev, void *data) +{ + return hci_le_create_cis_sync(hdev); +} - cis = NULL; +int hci_le_create_cis_pending(struct hci_dev *hdev) +{ + struct hci_conn *conn; + bool pending = false; - /* hci_conn_link uses list_add_tail_rcu so the list is in - * the same order as the connections are requested. - */ - list_for_each_entry_safe(link, t, &conn->link_list, list) { - if (link->conn->state == BT_BOUND) { - err = hci_le_create_cis(link->conn); - if (err) - return err; + rcu_read_lock(); - cis = link->conn; - } + list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { + if (test_bit(HCI_CONN_CREATE_CIS, &conn->flags)) { + rcu_read_unlock(); + return -EBUSY; } - return cis ? 0 : -EINVAL; - case ISO_LINK: - cis = conn; - break; - default: - return -EINVAL; + if (!hci_conn_check_create_cis(conn)) + pending = true; } - if (cis->state == BT_CONNECT) + rcu_read_unlock(); + + if (!pending) return 0; /* Queue Create CIS */ - err = hci_cmd_sync_queue(hdev, hci_create_cis_sync, cis, NULL); - if (err) - return err; - - cis->state = BT_CONNECT; - - return 0; + return hci_cmd_sync_queue(hdev, hci_create_cis_sync, NULL, NULL); } static void hci_iso_qos_setup(struct hci_dev *hdev, struct hci_conn *conn, @@ -2051,16 +2021,6 @@ static void hci_iso_qos_setup(struct hci_dev *hdev, struct hci_conn *conn, qos->latency = conn->le_conn_latency; } -static void hci_bind_bis(struct hci_conn *conn, - struct bt_iso_qos *qos) -{ - /* Update LINK PHYs according to QoS preference */ - conn->le_tx_phy = qos->bcast.out.phy; - conn->le_tx_phy = qos->bcast.out.phy; - conn->iso_qos = *qos; - conn->state = BT_BOUND; -} - static int create_big_sync(struct hci_dev *hdev, void *data) { struct hci_conn *conn = data; @@ -2183,27 +2143,80 @@ static void create_big_complete(struct hci_dev *hdev, void *data, int err) } } -struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, - __u8 dst_type, struct bt_iso_qos *qos, - __u8 base_len, __u8 *base) +struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, + struct bt_iso_qos *qos, + __u8 base_len, __u8 *base) { struct hci_conn *conn; - int err; + __u8 eir[HCI_MAX_PER_AD_LENGTH]; + + if (base_len && base) + base_len = eir_append_service_data(eir, 0, 0x1851, + base, base_len); /* We need hci_conn object using the BDADDR_ANY as dst */ - conn = hci_add_bis(hdev, dst, qos); + conn = hci_add_bis(hdev, dst, qos, base_len, eir); if (IS_ERR(conn)) return conn; - hci_bind_bis(conn, qos); + /* Update LINK PHYs according to QoS preference */ + conn->le_tx_phy = qos->bcast.out.phy; + conn->le_tx_phy = qos->bcast.out.phy; /* Add Basic Announcement into Peridic Adv Data if BASE is set */ if (base_len && base) { - base_len = eir_append_service_data(conn->le_per_adv_data, 0, - 0x1851, base, base_len); + memcpy(conn->le_per_adv_data, eir, sizeof(eir)); conn->le_per_adv_data_len = base_len; } + hci_iso_qos_setup(hdev, conn, &qos->bcast.out, + conn->le_tx_phy ? conn->le_tx_phy : + hdev->le_tx_def_phys); + + conn->iso_qos = *qos; + conn->state = BT_BOUND; + + return conn; +} + +static void bis_mark_per_adv(struct hci_conn *conn, void *data) +{ + struct iso_list_data *d = data; + + /* Skip if not broadcast/ANY address */ + if (bacmp(&conn->dst, BDADDR_ANY)) + return; + + if (d->big != conn->iso_qos.bcast.big || + d->bis == BT_ISO_QOS_BIS_UNSET || + d->bis != conn->iso_qos.bcast.bis) + return; + + set_bit(HCI_CONN_PER_ADV, &conn->flags); +} + +struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, + __u8 dst_type, struct bt_iso_qos *qos, + __u8 base_len, __u8 *base) +{ + struct hci_conn *conn; + int err; + struct iso_list_data data; + + conn = hci_bind_bis(hdev, dst, qos, base_len, base); + if (IS_ERR(conn)) + return conn; + + data.big = qos->bcast.big; + data.bis = qos->bcast.bis; + + /* Set HCI_CONN_PER_ADV for all bound connections, to mark that + * the start periodic advertising and create BIG commands have + * been queued + */ + hci_conn_hash_list_state(hdev, bis_mark_per_adv, ISO_LINK, + BT_BOUND, &data); + /* Queue start periodic advertising and create BIG */ err = hci_cmd_sync_queue(hdev, create_big_sync, conn, create_big_complete); @@ -2212,10 +2225,6 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, return ERR_PTR(err); } - hci_iso_qos_setup(hdev, conn, &qos->bcast.out, - conn->le_tx_phy ? conn->le_tx_phy : - hdev->le_tx_def_phys); - return conn; } @@ -2257,11 +2266,12 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, return ERR_PTR(-ENOLINK); } - /* If LE is already connected and CIS handle is already set proceed to - * Create CIS immediately. - */ - if (le->state == BT_CONNECTED && cis->handle != HCI_CONN_HANDLE_UNSET) - hci_le_create_cis(cis); + /* Link takes the refcount */ + hci_conn_drop(cis); + + cis->state = BT_CONNECT; + + hci_le_create_cis_pending(hdev); return cis; } @@ -2848,81 +2858,49 @@ u32 hci_conn_get_phy(struct hci_conn *conn) return phys; } -int hci_abort_conn(struct hci_conn *conn, u8 reason) +static int abort_conn_sync(struct hci_dev *hdev, void *data) { - int r = 0; + struct hci_conn *conn; + u16 handle = PTR_UINT(data); - if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + conn = hci_conn_hash_lookup_handle(hdev, handle); + if (!conn) return 0; - switch (conn->state) { - case BT_CONNECTED: - case BT_CONFIG: - if (conn->type == AMP_LINK) { - struct hci_cp_disconn_phy_link cp; + return hci_abort_conn_sync(hdev, conn, conn->abort_reason); +} - cp.phy_handle = HCI_PHY_HANDLE(conn->handle); - cp.reason = reason; - r = hci_send_cmd(conn->hdev, HCI_OP_DISCONN_PHY_LINK, - sizeof(cp), &cp); - } else { - struct hci_cp_disconnect dc; +int hci_abort_conn(struct hci_conn *conn, u8 reason) +{ + struct hci_dev *hdev = conn->hdev; - dc.handle = cpu_to_le16(conn->handle); - dc.reason = reason; - r = hci_send_cmd(conn->hdev, HCI_OP_DISCONNECT, - sizeof(dc), &dc); - } + /* If abort_reason has already been set it means the connection is + * already being aborted so don't attempt to overwrite it. + */ + if (conn->abort_reason) + return 0; - conn->state = BT_DISCONN; + bt_dev_dbg(hdev, "handle 0x%2.2x reason 0x%2.2x", conn->handle, reason); - break; - case BT_CONNECT: - if (conn->type == LE_LINK) { - if (test_bit(HCI_CONN_SCANNING, &conn->flags)) - break; - r = hci_send_cmd(conn->hdev, - HCI_OP_LE_CREATE_CONN_CANCEL, 0, NULL); - } else if (conn->type == ACL_LINK) { - if (conn->hdev->hci_ver < BLUETOOTH_VER_1_2) - break; - r = hci_send_cmd(conn->hdev, - HCI_OP_CREATE_CONN_CANCEL, - 6, &conn->dst); - } - break; - case BT_CONNECT2: - if (conn->type == ACL_LINK) { - struct hci_cp_reject_conn_req rej; - - bacpy(&rej.bdaddr, &conn->dst); - rej.reason = reason; - - r = hci_send_cmd(conn->hdev, - HCI_OP_REJECT_CONN_REQ, - sizeof(rej), &rej); - } else if (conn->type == SCO_LINK || conn->type == ESCO_LINK) { - struct hci_cp_reject_sync_conn_req rej; - - bacpy(&rej.bdaddr, &conn->dst); - - /* SCO rejection has its own limited set of - * allowed error values (0x0D-0x0F) which isn't - * compatible with most values passed to this - * function. To be safe hard-code one of the - * values that's suitable for SCO. - */ - rej.reason = HCI_ERROR_REJ_LIMITED_RESOURCES; + conn->abort_reason = reason; - r = hci_send_cmd(conn->hdev, - HCI_OP_REJECT_SYNC_CONN_REQ, - sizeof(rej), &rej); + /* If the connection is pending check the command opcode since that + * might be blocking on hci_cmd_sync_work while waiting its respective + * event so we need to hci_cmd_sync_cancel to cancel it. + * + * hci_connect_le serializes the connection attempts so only one + * connection can be in BT_CONNECT at time. + */ + if (conn->state == BT_CONNECT && hdev->req_status == HCI_REQ_PEND) { + switch (hci_skb_event(hdev->sent_cmd)) { + case HCI_EV_LE_CONN_COMPLETE: + case HCI_EV_LE_ENHANCED_CONN_COMPLETE: + case HCI_EVT_LE_CIS_ESTABLISHED: + hci_cmd_sync_cancel(hdev, -ECANCELED); + break; } - break; - default: - conn->state = BT_CLOSED; - break; } - return r; + return hci_cmd_sync_queue(hdev, abort_conn_sync, UINT_PTR(conn->handle), + NULL); } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 1ec83985f1ab..a5992f1b3c9b 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1074,9 +1074,9 @@ void hci_uuids_clear(struct hci_dev *hdev) void hci_link_keys_clear(struct hci_dev *hdev) { - struct link_key *key; + struct link_key *key, *tmp; - list_for_each_entry(key, &hdev->link_keys, list) { + list_for_each_entry_safe(key, tmp, &hdev->link_keys, list) { list_del_rcu(&key->list); kfree_rcu(key, rcu); } @@ -1084,9 +1084,9 @@ void hci_link_keys_clear(struct hci_dev *hdev) void hci_smp_ltks_clear(struct hci_dev *hdev) { - struct smp_ltk *k; + struct smp_ltk *k, *tmp; - list_for_each_entry(k, &hdev->long_term_keys, list) { + list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) { list_del_rcu(&k->list); kfree_rcu(k, rcu); } @@ -1094,9 +1094,9 @@ void hci_smp_ltks_clear(struct hci_dev *hdev) void hci_smp_irks_clear(struct hci_dev *hdev) { - struct smp_irk *k; + struct smp_irk *k, *tmp; - list_for_each_entry(k, &hdev->identity_resolving_keys, list) { + list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) { list_del_rcu(&k->list); kfree_rcu(k, rcu); } @@ -1104,9 +1104,9 @@ void hci_smp_irks_clear(struct hci_dev *hdev) void hci_blocked_keys_clear(struct hci_dev *hdev) { - struct blocked_key *b; + struct blocked_key *b, *tmp; - list_for_each_entry(b, &hdev->blocked_keys, list) { + list_for_each_entry_safe(b, tmp, &hdev->blocked_keys, list) { list_del_rcu(&b->list); kfree_rcu(b, rcu); } @@ -1949,15 +1949,15 @@ int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) switch (hci_get_adv_monitor_offload_ext(hdev)) { case HCI_ADV_MONITOR_EXT_NONE: - bt_dev_dbg(hdev, "%s add monitor %d status %d", hdev->name, + bt_dev_dbg(hdev, "add monitor %d status %d", monitor->handle, status); /* Message was not forwarded to controller - not an error */ break; case HCI_ADV_MONITOR_EXT_MSFT: status = msft_add_monitor_pattern(hdev, monitor); - bt_dev_dbg(hdev, "%s add monitor %d msft status %d", hdev->name, - monitor->handle, status); + bt_dev_dbg(hdev, "add monitor %d msft status %d", + handle, status); break; } @@ -1976,15 +1976,15 @@ static int hci_remove_adv_monitor(struct hci_dev *hdev, switch (hci_get_adv_monitor_offload_ext(hdev)) { case HCI_ADV_MONITOR_EXT_NONE: /* also goes here when powered off */ - bt_dev_dbg(hdev, "%s remove monitor %d status %d", hdev->name, + bt_dev_dbg(hdev, "remove monitor %d status %d", monitor->handle, status); goto free_monitor; case HCI_ADV_MONITOR_EXT_MSFT: handle = monitor->handle; status = msft_remove_monitor(hdev, monitor); - bt_dev_dbg(hdev, "%s remove monitor %d msft status %d", - hdev->name, handle, status); + bt_dev_dbg(hdev, "remove monitor %d msft status %d", + handle, status); break; } @@ -2436,6 +2436,9 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return NOTIFY_DONE; + /* To avoid a potential race with hci_unregister_dev. */ + hci_dev_hold(hdev); + if (action == PM_SUSPEND_PREPARE) ret = hci_suspend_dev(hdev); else if (action == PM_POST_SUSPEND) @@ -2445,6 +2448,7 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, bt_dev_err(hdev, "Suspend notifier action (%lu) failed: %d", action, ret); + hci_dev_put(hdev); return NOTIFY_DONE; } @@ -3891,7 +3895,7 @@ static void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb) if (conn) { /* Send to upper protocol */ - bt_cb(skb)->sco.pkt_status = flags & 0x03; + hci_skb_pkt_status(skb) = flags & 0x03; sco_recv_scodata(conn, skb); return; } else { diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index ec0df2f9188e..6b7741f6e95b 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -22,6 +22,7 @@ */ #include <linux/debugfs.h> +#include <linux/kstrtox.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -1152,7 +1153,7 @@ static ssize_t force_no_mitm_write(struct file *file, return -EFAULT; buf[buf_size] = '\0'; - if (strtobool(buf, &enable)) + if (kstrtobool(buf, &enable)) return -EINVAL; if (enable == hci_dev_test_flag(hdev, HCI_FORCE_NO_MITM)) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 31ca320ce38d..559b6080706c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1639,7 +1639,7 @@ static u8 hci_cc_le_set_ext_adv_enable(struct hci_dev *hdev, void *data, hci_dev_set_flag(hdev, HCI_LE_ADV); - if (adv) + if (adv && !adv->periodic) adv->enabled = true; conn = hci_lookup_le_connect(hdev); @@ -1747,7 +1747,7 @@ static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr, { struct discovery_state *d = &hdev->discovery; - if (len > HCI_MAX_AD_LENGTH) + if (len > max_adv_len(hdev)) return; bacpy(&d->last_adv_addr, bdaddr); @@ -3173,19 +3173,15 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, * As the connection handle is set here for the first time, it indicates * whether the connection is already set up. */ - if (conn->handle != HCI_CONN_HANDLE_UNSET) { + if (!HCI_CONN_HANDLE_UNSET(conn->handle)) { bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection"); goto unlock; } if (!status) { - conn->handle = __le16_to_cpu(ev->handle); - if (conn->handle > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", - conn->handle, HCI_CONN_HANDLE_MAX); - status = HCI_ERROR_INVALID_PARAMETERS; + status = hci_conn_set_handle(conn, __le16_to_cpu(ev->handle)); + if (status) goto done; - } if (conn->type == ACL_LINK) { conn->state = BT_CONFIG; @@ -3803,6 +3799,22 @@ static u8 hci_cc_le_read_buffer_size_v2(struct hci_dev *hdev, void *data, return rp->status; } +static void hci_unbound_cis_failed(struct hci_dev *hdev, u8 cig, u8 status) +{ + struct hci_conn *conn, *tmp; + + lockdep_assert_held(&hdev->lock); + + list_for_each_entry_safe(conn, tmp, &hdev->conn_hash.list, list) { + if (conn->type != ISO_LINK || !bacmp(&conn->dst, BDADDR_ANY) || + conn->state == BT_OPEN || conn->iso_qos.ucast.cig != cig) + continue; + + if (HCI_CONN_HANDLE_UNSET(conn->handle)) + hci_conn_failed(conn, status); + } +} + static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -3810,6 +3822,7 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data, struct hci_cp_le_set_cig_params *cp; struct hci_conn *conn; u8 status = rp->status; + bool pending = false; int i; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); @@ -3823,12 +3836,15 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data, hci_dev_lock(hdev); + /* BLUETOOTH CORE SPECIFICATION Version 5.4 | Vol 4, Part E page 2554 + * + * If the Status return parameter is non-zero, then the state of the CIG + * and its CIS configurations shall not be changed by the command. If + * the CIG did not already exist, it shall not be created. + */ if (status) { - while ((conn = hci_conn_hash_lookup_cig(hdev, rp->cig_id))) { - conn->state = BT_CLOSED; - hci_connect_cfm(conn, status); - hci_conn_del(conn); - } + /* Keep current configuration, fail only the unbound CIS */ + hci_unbound_cis_failed(hdev, rp->cig_id, status); goto unlock; } @@ -3848,17 +3864,17 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data, if (conn->state != BT_BOUND && conn->state != BT_CONNECT) continue; - conn->handle = __le16_to_cpu(rp->handle[i]); - - bt_dev_dbg(hdev, "%p handle 0x%4.4x parent %p", conn, - conn->handle, conn->parent); + if (hci_conn_set_handle(conn, __le16_to_cpu(rp->handle[i]))) + continue; - /* Create CIS if LE is already connected */ - if (conn->parent && conn->parent->state == BT_CONNECTED) - hci_le_create_cis(conn); + if (conn->state == BT_CONNECT) + pending = true; } unlock: + if (pending) + hci_le_create_cis_pending(hdev); + hci_dev_unlock(hdev); return rp->status; @@ -3938,24 +3954,47 @@ static u8 hci_cc_le_set_per_adv_enable(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; - __u8 *sent; + struct hci_cp_le_set_per_adv_enable *cp; + struct adv_info *adv = NULL, *n; + u8 per_adv_cnt = 0; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; - sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_PER_ADV_ENABLE); - if (!sent) + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_PER_ADV_ENABLE); + if (!cp) return rp->status; hci_dev_lock(hdev); - if (*sent) + adv = hci_find_adv_instance(hdev, cp->handle); + + if (cp->enable) { hci_dev_set_flag(hdev, HCI_LE_PER_ADV); - else + + if (adv) + adv->enabled = true; + } else { + /* If just one instance was disabled check if there are + * any other instance enabled before clearing HCI_LE_PER_ADV. + * The current periodic adv instance will be marked as + * disabled once extended advertising is also disabled. + */ + list_for_each_entry_safe(adv, n, &hdev->adv_instances, + list) { + if (adv->periodic && adv->enabled) + per_adv_cnt++; + } + + if (per_adv_cnt > 1) + goto unlock; + hci_dev_clear_flag(hdev, HCI_LE_PER_ADV); + } +unlock: hci_dev_unlock(hdev); return rp->status; @@ -4224,6 +4263,7 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, void *data, static void hci_cs_le_create_cis(struct hci_dev *hdev, u8 status) { struct hci_cp_le_create_cis *cp; + bool pending = false; int i; bt_dev_dbg(hdev, "status 0x%2.2x", status); @@ -4246,12 +4286,18 @@ static void hci_cs_le_create_cis(struct hci_dev *hdev, u8 status) conn = hci_conn_hash_lookup_handle(hdev, handle); if (conn) { + if (test_and_clear_bit(HCI_CONN_CREATE_CIS, + &conn->flags)) + pending = true; conn->state = BT_CLOSED; hci_connect_cfm(conn, status); hci_conn_del(conn); } } + if (pending) + hci_le_create_cis_pending(hdev); + hci_dev_unlock(hdev); } @@ -4999,18 +5045,15 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, * As the connection handle is set here for the first time, it indicates * whether the connection is already set up. */ - if (conn->handle != HCI_CONN_HANDLE_UNSET) { + if (!HCI_CONN_HANDLE_UNSET(conn->handle)) { bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete event for existing connection"); goto unlock; } switch (status) { case 0x00: - conn->handle = __le16_to_cpu(ev->handle); - if (conn->handle > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", - conn->handle, HCI_CONN_HANDLE_MAX); - status = HCI_ERROR_INVALID_PARAMETERS; + status = hci_conn_set_handle(conn, __le16_to_cpu(ev->handle)); + if (status) { conn->state = BT_CLOSED; break; } @@ -5863,7 +5906,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, * As the connection handle is set here for the first time, it indicates * whether the connection is already set up. */ - if (conn->handle != HCI_CONN_HANDLE_UNSET) { + if (!HCI_CONN_HANDLE_UNSET(conn->handle)) { bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection"); goto unlock; } @@ -6216,8 +6259,9 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, return; } - if (!ext_adv && len > HCI_MAX_AD_LENGTH) { - bt_dev_err_ratelimited(hdev, "legacy adv larger than 31 bytes"); + if (len > max_adv_len(hdev)) { + bt_dev_err_ratelimited(hdev, + "adv larger than maximum supported"); return; } @@ -6282,7 +6326,8 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, */ conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, bdaddr_resolved, type); - if (!ext_adv && conn && type == LE_ADV_IND && len <= HCI_MAX_AD_LENGTH) { + if (!ext_adv && conn && type == LE_ADV_IND && + len <= max_adv_len(hdev)) { /* Store report for later inclusion by * mgmt_device_connected */ @@ -6423,7 +6468,7 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, void *data, info->length + 1)) break; - if (info->length <= HCI_MAX_AD_LENGTH) { + if (info->length <= max_adv_len(hdev)) { rssi = info->data[info->length]; process_adv_report(hdev, info->type, &info->bdaddr, info->bdaddr_type, NULL, 0, rssi, @@ -6790,6 +6835,7 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, struct hci_evt_le_cis_established *ev = data; struct hci_conn *conn; struct bt_iso_qos *qos; + bool pending = false; u16 handle = __le16_to_cpu(ev->handle); bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); @@ -6813,6 +6859,8 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, qos = &conn->iso_qos; + pending = test_and_clear_bit(HCI_CONN_CREATE_CIS, &conn->flags); + /* Convert ISO Interval (1.25 ms slots) to SDU Interval (us) */ qos->ucast.in.interval = le16_to_cpu(ev->interval) * 1250; qos->ucast.out.interval = qos->ucast.in.interval; @@ -6854,10 +6902,14 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, goto unlock; } + conn->state = BT_CLOSED; hci_connect_cfm(conn, ev->status); hci_conn_del(conn); unlock: + if (pending) + hci_le_create_cis_pending(hdev); + hci_dev_unlock(hdev); } @@ -6936,6 +6988,7 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, { struct hci_evt_le_create_big_complete *ev = data; struct hci_conn *conn; + __u8 i = 0; BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); @@ -6944,33 +6997,46 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, return; hci_dev_lock(hdev); + rcu_read_lock(); - conn = hci_conn_hash_lookup_big(hdev, ev->handle); - if (!conn) - goto unlock; + /* Connect all BISes that are bound to the BIG */ + list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { + if (bacmp(&conn->dst, BDADDR_ANY) || + conn->type != ISO_LINK || + conn->iso_qos.bcast.big != ev->handle) + continue; - if (conn->type != ISO_LINK) { - bt_dev_err(hdev, - "Invalid connection link type handle 0x%2.2x", - ev->handle); - goto unlock; - } + if (hci_conn_set_handle(conn, + __le16_to_cpu(ev->bis_handle[i++]))) + continue; - if (ev->num_bis) - conn->handle = __le16_to_cpu(ev->bis_handle[0]); + if (!ev->status) { + conn->state = BT_CONNECTED; + set_bit(HCI_CONN_BIG_CREATED, &conn->flags); + rcu_read_unlock(); + hci_debugfs_create_conn(conn); + hci_conn_add_sysfs(conn); + hci_iso_setup_path(conn); + rcu_read_lock(); + continue; + } - if (!ev->status) { - conn->state = BT_CONNECTED; - hci_debugfs_create_conn(conn); - hci_conn_add_sysfs(conn); - hci_iso_setup_path(conn); - goto unlock; + hci_connect_cfm(conn, ev->status); + rcu_read_unlock(); + hci_conn_del(conn); + rcu_read_lock(); } - hci_connect_cfm(conn, ev->status); - hci_conn_del(conn); + if (!ev->status && !i) + /* If no BISes have been connected for the BIG, + * terminate. This is in case all bound connections + * have been closed before the BIG creation + * has completed. + */ + hci_le_terminate_big_sync(hdev, ev->handle, + HCI_ERROR_LOCAL_HOST_TERM); -unlock: + rcu_read_unlock(); hci_dev_unlock(hdev); } @@ -6987,9 +7053,6 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, flex_array_size(ev, bis, ev->num_bis))) return; - if (ev->status) - return; - hci_dev_lock(hdev); for (i = 0; i < ev->num_bis; i++) { @@ -7013,9 +7076,25 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, bis->iso_qos.bcast.in.latency = le16_to_cpu(ev->interval) * 125 / 100; bis->iso_qos.bcast.in.sdu = le16_to_cpu(ev->max_pdu); - hci_iso_setup_path(bis); + if (!ev->status) { + set_bit(HCI_CONN_BIG_SYNC, &bis->flags); + hci_iso_setup_path(bis); + } } + /* In case BIG sync failed, notify each failed connection to + * the user after all hci connections have been added + */ + if (ev->status) + for (i = 0; i < ev->num_bis; i++) { + u16 handle = le16_to_cpu(ev->bis[i]); + + bis = hci_conn_hash_lookup_handle(hdev, handle); + + set_bit(HCI_CONN_BIG_SYNC_FAILED, &bis->flags); + hci_connect_cfm(bis, ev->status); + } + hci_dev_unlock(hdev); } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index f7e006a36382..6e023b0104b0 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -629,27 +629,6 @@ static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval, } } -/* Returns true if an le connection is in the scanning state */ -static inline bool hci_is_le_conn_scanning(struct hci_dev *hdev) -{ - struct hci_conn_hash *h = &hdev->conn_hash; - struct hci_conn *c; - - rcu_read_lock(); - - list_for_each_entry_rcu(c, &h->list, list) { - if (c->type == LE_LINK && c->state == BT_CONNECT && - test_bit(HCI_CONN_SCANNING, &c->flags)) { - rcu_read_unlock(); - return true; - } - } - - rcu_read_unlock(); - - return false; -} - static void set_random_addr(struct hci_request *req, bdaddr_t *rpa); static int hci_update_random_address(struct hci_request *req, bool require_privacy, bool use_rpa, diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 1d249d839819..5e4f718073b7 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -264,6 +264,53 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb) kfree_skb(skb_copy); } +static void hci_sock_copy_creds(struct sock *sk, struct sk_buff *skb) +{ + struct scm_creds *creds; + + if (!sk || WARN_ON(!skb)) + return; + + creds = &bt_cb(skb)->creds; + + /* Check if peer credentials is set */ + if (!sk->sk_peer_pid) { + /* Check if parent peer credentials is set */ + if (bt_sk(sk)->parent && bt_sk(sk)->parent->sk_peer_pid) + sk = bt_sk(sk)->parent; + else + return; + } + + /* Check if scm_creds already set */ + if (creds->pid == pid_vnr(sk->sk_peer_pid)) + return; + + memset(creds, 0, sizeof(*creds)); + + creds->pid = pid_vnr(sk->sk_peer_pid); + if (sk->sk_peer_cred) { + creds->uid = sk->sk_peer_cred->uid; + creds->gid = sk->sk_peer_cred->gid; + } +} + +static struct sk_buff *hci_skb_clone(struct sk_buff *skb) +{ + struct sk_buff *nskb; + + if (!skb) + return NULL; + + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return NULL; + + hci_sock_copy_creds(skb->sk, nskb); + + return nskb; +} + /* Send frame to sockets with specific channel */ static void __hci_send_to_channel(unsigned short channel, struct sk_buff *skb, int flag, struct sock *skip_sk) @@ -289,7 +336,7 @@ static void __hci_send_to_channel(unsigned short channel, struct sk_buff *skb, if (hci_pi(sk)->channel != channel) continue; - nskb = skb_clone(skb, GFP_ATOMIC); + nskb = hci_skb_clone(skb); if (!nskb) continue; @@ -356,6 +403,8 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) if (!skb_copy) return; + hci_sock_copy_creds(skb->sk, skb_copy); + /* Put header before the data */ hdr = skb_push(skb_copy, HCI_MON_HDR_SIZE); hdr->opcode = opcode; @@ -531,10 +580,12 @@ static struct sk_buff *create_monitor_ctrl_open(struct sock *sk) return NULL; } - skb = bt_skb_alloc(14 + TASK_COMM_LEN , GFP_ATOMIC); + skb = bt_skb_alloc(14 + TASK_COMM_LEN, GFP_ATOMIC); if (!skb) return NULL; + hci_sock_copy_creds(sk, skb); + flags = hci_sock_test_flag(sk, HCI_SOCK_TRUSTED) ? 0x1 : 0x0; put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4)); @@ -580,6 +631,8 @@ static struct sk_buff *create_monitor_ctrl_close(struct sock *sk) if (!skb) return NULL; + hci_sock_copy_creds(sk, skb); + put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4)); __net_timestamp(skb); @@ -606,6 +659,8 @@ static struct sk_buff *create_monitor_ctrl_command(struct sock *sk, u16 index, if (!skb) return NULL; + hci_sock_copy_creds(sk, skb); + put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4)); put_unaligned_le16(opcode, skb_put(skb, 2)); @@ -638,6 +693,8 @@ send_monitor_note(struct sock *sk, const char *fmt, ...) if (!skb) return; + hci_sock_copy_creds(sk, skb); + va_start(args, fmt); vsprintf(skb_put(skb, len), fmt, args); *(u8 *)skb_put(skb, 1) = 0; @@ -1494,6 +1551,7 @@ static void hci_sock_cmsg(struct sock *sk, struct msghdr *msg, static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { + struct scm_cookie scm; struct sock *sk = sock->sk; struct sk_buff *skb; int copied, err; @@ -1538,11 +1596,16 @@ static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg, break; } + memset(&scm, 0, sizeof(scm)); + scm.creds = bt_cb(skb)->creds; + skb_free_datagram(sk, skb); if (flags & MSG_TRUNC) copied = skblen; + scm_recv(sock, msg, &scm, flags); + return err ? : copied; } @@ -2143,18 +2206,12 @@ static int hci_sock_create(struct net *net, struct socket *sock, int protocol, sock->ops = &hci_sock_ops; - sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &hci_sk_proto, kern); + sk = bt_sock_alloc(net, sock, &hci_sk_proto, protocol, GFP_ATOMIC, + kern); if (!sk) return -ENOMEM; - sock_init_data(sock, sk); - - sock_reset_flag(sk, SOCK_ZAPPED); - - sk->sk_protocol = protocol; - sock->state = SS_UNCONNECTED; - sk->sk_state = BT_OPEN; sk->sk_destruct = hci_sock_destruct; bt_sock_link(&hci_sk_list, sk); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 4d1e32bb6a9c..5eb30ba21370 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -3,6 +3,7 @@ * BlueZ - Bluetooth protocol stack for Linux * * Copyright (C) 2021 Intel Corporation + * Copyright 2023 NXP */ #include <linux/property.h> @@ -1319,9 +1320,11 @@ int hci_start_ext_adv_sync(struct hci_dev *hdev, u8 instance) static int hci_disable_per_advertising_sync(struct hci_dev *hdev, u8 instance) { struct hci_cp_le_set_per_adv_enable cp; + struct adv_info *adv = NULL; /* If periodic advertising already disabled there is nothing to do. */ - if (!hci_dev_test_flag(hdev, HCI_LE_PER_ADV)) + adv = hci_find_adv_instance(hdev, instance); + if (!adv || !adv->periodic || !adv->enabled) return 0; memset(&cp, 0, sizeof(cp)); @@ -1386,9 +1389,11 @@ static int hci_set_per_adv_data_sync(struct hci_dev *hdev, u8 instance) static int hci_enable_per_advertising_sync(struct hci_dev *hdev, u8 instance) { struct hci_cp_le_set_per_adv_enable cp; + struct adv_info *adv = NULL; /* If periodic advertising already enabled there is nothing to do. */ - if (hci_dev_test_flag(hdev, HCI_LE_PER_ADV)) + adv = hci_find_adv_instance(hdev, instance); + if (adv && adv->periodic && adv->enabled) return 0; memset(&cp, 0, sizeof(cp)); @@ -1458,22 +1463,19 @@ int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 data_len, sync_interval); if (IS_ERR(adv)) return PTR_ERR(adv); + adv->pending = false; added = true; } } - /* Only start advertising if instance 0 or if a dedicated instance has - * been added. - */ - if (!adv || added) { - err = hci_start_ext_adv_sync(hdev, instance); - if (err < 0) - goto fail; + /* Start advertising */ + err = hci_start_ext_adv_sync(hdev, instance); + if (err < 0) + goto fail; - err = hci_adv_bcast_annoucement(hdev, adv); - if (err < 0) - goto fail; - } + err = hci_adv_bcast_annoucement(hdev, adv); + if (err < 0) + goto fail; err = hci_set_per_adv_params_sync(hdev, instance, min_interval, max_interval); @@ -2670,27 +2672,6 @@ done: return filter_policy; } -/* Returns true if an le connection is in the scanning state */ -static inline bool hci_is_le_conn_scanning(struct hci_dev *hdev) -{ - struct hci_conn_hash *h = &hdev->conn_hash; - struct hci_conn *c; - - rcu_read_lock(); - - list_for_each_entry_rcu(c, &h->list, list) { - if (c->type == LE_LINK && c->state == BT_CONNECT && - test_bit(HCI_CONN_SCANNING, &c->flags)) { - rcu_read_unlock(); - return true; - } - } - - rcu_read_unlock(); - - return false; -} - static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type, u16 interval, u16 window, u8 own_addr_type, u8 filter_policy) @@ -4133,10 +4114,13 @@ static int hci_le_set_event_mask_sync(struct hci_dev *hdev) } if (bis_capable(hdev)) { + events[1] |= 0x20; /* LE PA Report */ + events[1] |= 0x40; /* LE PA Sync Established */ events[3] |= 0x04; /* LE Create BIG Complete */ events[3] |= 0x08; /* LE Terminate BIG Complete */ events[3] |= 0x10; /* LE BIG Sync Established */ events[3] |= 0x20; /* LE BIG Sync Loss */ + events[4] |= 0x02; /* LE BIG Info Advertising Report */ } return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EVENT_MASK, @@ -5269,26 +5253,64 @@ static int hci_disconnect_sync(struct hci_dev *hdev, struct hci_conn *conn, } static int hci_le_connect_cancel_sync(struct hci_dev *hdev, - struct hci_conn *conn) + struct hci_conn *conn, u8 reason) { + /* Return reason if scanning since the connection shall probably be + * cleanup directly. + */ if (test_bit(HCI_CONN_SCANNING, &conn->flags)) - return 0; + return reason; - if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + if (conn->role == HCI_ROLE_SLAVE || + test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) return 0; return __hci_cmd_sync_status(hdev, HCI_OP_LE_CREATE_CONN_CANCEL, 0, NULL, HCI_CMD_TIMEOUT); } -static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn) +static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn, + u8 reason) { if (conn->type == LE_LINK) - return hci_le_connect_cancel_sync(hdev, conn); + return hci_le_connect_cancel_sync(hdev, conn, reason); + + if (conn->type == ISO_LINK) { + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E + * page 1857: + * + * If this command is issued for a CIS on the Central and the + * CIS is successfully terminated before being established, + * then an HCI_LE_CIS_Established event shall also be sent for + * this CIS with the Status Operation Cancelled by Host (0x44). + */ + if (test_bit(HCI_CONN_CREATE_CIS, &conn->flags)) + return hci_disconnect_sync(hdev, conn, reason); + + /* CIS with no Create CIS sent have nothing to cancel */ + if (bacmp(&conn->dst, BDADDR_ANY)) + return HCI_ERROR_LOCAL_HOST_TERM; + + /* There is no way to cancel a BIS without terminating the BIG + * which is done later on connection cleanup. + */ + return 0; + } if (hdev->hci_ver < BLUETOOTH_VER_1_2) return 0; + /* Wait for HCI_EV_CONN_COMPLETE, not HCI_EV_CMD_STATUS, when the + * reason is anything but HCI_ERROR_REMOTE_POWER_OFF. This reason is + * used when suspending or powering off, where we don't want to wait + * for the peer's response. + */ + if (reason != HCI_ERROR_REMOTE_POWER_OFF) + return __hci_cmd_sync_status_sk(hdev, HCI_OP_CREATE_CONN_CANCEL, + 6, &conn->dst, + HCI_EV_CONN_COMPLETE, + HCI_CMD_TIMEOUT, NULL); + return __hci_cmd_sync_status(hdev, HCI_OP_CREATE_CONN_CANCEL, 6, &conn->dst, HCI_CMD_TIMEOUT); } @@ -5312,11 +5334,27 @@ static int hci_reject_sco_sync(struct hci_dev *hdev, struct hci_conn *conn, sizeof(cp), &cp, HCI_CMD_TIMEOUT); } +static int hci_le_reject_cis_sync(struct hci_dev *hdev, struct hci_conn *conn, + u8 reason) +{ + struct hci_cp_le_reject_cis cp; + + memset(&cp, 0, sizeof(cp)); + cp.handle = cpu_to_le16(conn->handle); + cp.reason = reason; + + return __hci_cmd_sync_status(hdev, HCI_OP_LE_REJECT_CIS, + sizeof(cp), &cp, HCI_CMD_TIMEOUT); +} + static int hci_reject_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) { struct hci_cp_reject_conn_req cp; + if (conn->type == ISO_LINK) + return hci_le_reject_cis_sync(hdev, conn, reason); + if (conn->type == SCO_LINK || conn->type == ESCO_LINK) return hci_reject_sco_sync(hdev, conn, reason); @@ -5330,31 +5368,52 @@ static int hci_reject_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) { - int err; + int err = 0; + u16 handle = conn->handle; switch (conn->state) { case BT_CONNECTED: case BT_CONFIG: - return hci_disconnect_sync(hdev, conn, reason); + err = hci_disconnect_sync(hdev, conn, reason); + break; case BT_CONNECT: - err = hci_connect_cancel_sync(hdev, conn); - /* Cleanup hci_conn object if it cannot be cancelled as it - * likelly means the controller and host stack are out of sync. - */ - if (err) { - hci_dev_lock(hdev); - hci_conn_failed(conn, err); - hci_dev_unlock(hdev); - } - return err; + err = hci_connect_cancel_sync(hdev, conn, reason); + break; case BT_CONNECT2: - return hci_reject_conn_sync(hdev, conn, reason); + err = hci_reject_conn_sync(hdev, conn, reason); + break; + case BT_OPEN: + case BT_BOUND: + hci_dev_lock(hdev); + hci_conn_failed(conn, reason); + hci_dev_unlock(hdev); + return 0; default: conn->state = BT_CLOSED; - break; + return 0; } - return 0; + /* Cleanup hci_conn object if it cannot be cancelled as it + * likelly means the controller and host stack are out of sync + * or in case of LE it was still scanning so it can be cleanup + * safely. + */ + if (err) { + struct hci_conn *c; + + /* Check if the connection hasn't been cleanup while waiting + * commands to complete. + */ + c = hci_conn_hash_lookup_handle(hdev, handle); + if (!c || c != conn) + return 0; + + hci_dev_lock(hdev); + hci_conn_failed(conn, err); + hci_dev_unlock(hdev); + } + + return err; } static int hci_disconnect_all_sync(struct hci_dev *hdev, u8 reason) @@ -6253,63 +6312,99 @@ int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) done: if (err == -ETIMEDOUT) - hci_le_connect_cancel_sync(hdev, conn); + hci_le_connect_cancel_sync(hdev, conn, 0x00); /* Re-enable advertising after the connection attempt is finished. */ hci_resume_advertising_sync(hdev); return err; } -int hci_le_create_cis_sync(struct hci_dev *hdev, struct hci_conn *conn) +int hci_le_create_cis_sync(struct hci_dev *hdev) { struct { struct hci_cp_le_create_cis cp; struct hci_cis cis[0x1f]; } cmd; - u8 cig; - struct hci_conn *hcon = conn; + struct hci_conn *conn; + u8 cig = BT_ISO_QOS_CIG_UNSET; + + /* The spec allows only one pending LE Create CIS command at a time. If + * the command is pending now, don't do anything. We check for pending + * connections after each CIS Established event. + * + * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E + * page 2566: + * + * If the Host issues this command before all the + * HCI_LE_CIS_Established events from the previous use of the + * command have been generated, the Controller shall return the + * error code Command Disallowed (0x0C). + * + * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E + * page 2567: + * + * When the Controller receives the HCI_LE_Create_CIS command, the + * Controller sends the HCI_Command_Status event to the Host. An + * HCI_LE_CIS_Established event will be generated for each CIS when it + * is established or if it is disconnected or considered lost before + * being established; until all the events are generated, the command + * remains pending. + */ memset(&cmd, 0, sizeof(cmd)); - cmd.cis[0].acl_handle = cpu_to_le16(conn->parent->handle); - cmd.cis[0].cis_handle = cpu_to_le16(conn->handle); - cmd.cp.num_cis++; - cig = conn->iso_qos.ucast.cig; hci_dev_lock(hdev); rcu_read_lock(); + /* Wait until previous Create CIS has completed */ list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { - struct hci_cis *cis = &cmd.cis[cmd.cp.num_cis]; + if (test_bit(HCI_CONN_CREATE_CIS, &conn->flags)) + goto done; + } - if (conn == hcon || conn->type != ISO_LINK || - conn->state == BT_CONNECTED || - conn->iso_qos.ucast.cig != cig) + /* Find CIG with all CIS ready */ + list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { + struct hci_conn *link; + + if (hci_conn_check_create_cis(conn)) continue; - /* Check if all CIS(s) belonging to a CIG are ready */ - if (!conn->parent || conn->parent->state != BT_CONNECTED || - conn->state != BT_CONNECT) { - cmd.cp.num_cis = 0; - break; + cig = conn->iso_qos.ucast.cig; + + list_for_each_entry_rcu(link, &hdev->conn_hash.list, list) { + if (hci_conn_check_create_cis(link) > 0 && + link->iso_qos.ucast.cig == cig && + link->state != BT_CONNECTED) { + cig = BT_ISO_QOS_CIG_UNSET; + break; + } } - /* Group all CIS with state BT_CONNECT since the spec don't - * allow to send them individually: - * - * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E - * page 2566: - * - * If the Host issues this command before all the - * HCI_LE_CIS_Established events from the previous use of the - * command have been generated, the Controller shall return the - * error code Command Disallowed (0x0C). - */ + if (cig != BT_ISO_QOS_CIG_UNSET) + break; + } + + if (cig == BT_ISO_QOS_CIG_UNSET) + goto done; + + list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { + struct hci_cis *cis = &cmd.cis[cmd.cp.num_cis]; + + if (hci_conn_check_create_cis(conn) || + conn->iso_qos.ucast.cig != cig) + continue; + + set_bit(HCI_CONN_CREATE_CIS, &conn->flags); cis->acl_handle = cpu_to_le16(conn->parent->handle); cis->cis_handle = cpu_to_le16(conn->handle); cmd.cp.num_cis++; + + if (cmd.cp.num_cis >= ARRAY_SIZE(cmd.cis)) + break; } +done: rcu_read_unlock(); hci_dev_unlock(hdev); @@ -6433,7 +6528,7 @@ int hci_get_random_address(struct hci_dev *hdev, bool require_privacy, static int _update_adv_data_sync(struct hci_dev *hdev, void *data) { - u8 instance = PTR_ERR(data); + u8 instance = PTR_UINT(data); return hci_update_adv_data_sync(hdev, instance); } @@ -6441,5 +6536,5 @@ static int _update_adv_data_sync(struct hci_dev *hdev, void *data) int hci_update_adv_data(struct hci_dev *hdev, u8 instance) { return hci_cmd_sync_queue(hdev, _update_adv_data_sync, - ERR_PTR(instance), NULL); + UINT_PTR(instance), NULL); } diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c index 369ed92dac99..c93aaeb3a3fa 100644 --- a/net/bluetooth/hidp/sock.c +++ b/net/bluetooth/hidp/sock.c @@ -256,21 +256,13 @@ static int hidp_sock_create(struct net *net, struct socket *sock, int protocol, if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; - sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &hidp_proto, kern); + sk = bt_sock_alloc(net, sock, &hidp_proto, protocol, GFP_ATOMIC, kern); if (!sk) return -ENOMEM; - sock_init_data(sock, sk); - sock->ops = &hidp_sock_ops; - sock->state = SS_UNCONNECTED; - sock_reset_flag(sk, SOCK_ZAPPED); - - sk->sk_protocol = protocol; - sk->sk_state = BT_OPEN; - bt_sock_link(&hidp_sk_list, sk); return 0; diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 505d62247268..6b66d6a88b9a 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -48,6 +48,11 @@ static void iso_sock_kill(struct sock *sk); #define EIR_SERVICE_DATA_LENGTH 4 #define BASE_MAX_LENGTH (HCI_MAX_PER_AD_LENGTH - EIR_SERVICE_DATA_LENGTH) +/* iso_pinfo flags values */ +enum { + BT_SK_BIG_SYNC, +}; + struct iso_pinfo { struct bt_sock bt; bdaddr_t src; @@ -58,7 +63,7 @@ struct iso_pinfo { __u8 bc_num_bis; __u8 bc_bis[ISO_MAX_NUM_BIS]; __u16 sync_handle; - __u32 flags; + unsigned long flags; struct bt_iso_qos qos; bool qos_user_set; __u8 base_len; @@ -287,13 +292,24 @@ static int iso_connect_bis(struct sock *sk) goto unlock; } - hcon = hci_connect_bis(hdev, &iso_pi(sk)->dst, - le_addr_type(iso_pi(sk)->dst_type), - &iso_pi(sk)->qos, iso_pi(sk)->base_len, - iso_pi(sk)->base); - if (IS_ERR(hcon)) { - err = PTR_ERR(hcon); - goto unlock; + /* Just bind if DEFER_SETUP has been set */ + if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { + hcon = hci_bind_bis(hdev, &iso_pi(sk)->dst, + &iso_pi(sk)->qos, iso_pi(sk)->base_len, + iso_pi(sk)->base); + if (IS_ERR(hcon)) { + err = PTR_ERR(hcon); + goto unlock; + } + } else { + hcon = hci_connect_bis(hdev, &iso_pi(sk)->dst, + le_addr_type(iso_pi(sk)->dst_type), + &iso_pi(sk)->qos, iso_pi(sk)->base_len, + iso_pi(sk)->base); + if (IS_ERR(hcon)) { + err = PTR_ERR(hcon); + goto unlock; + } } conn = iso_conn_add(hcon); @@ -317,6 +333,9 @@ static int iso_connect_bis(struct sock *sk) if (hcon->state == BT_CONNECTED) { iso_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; + } else if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { + iso_sock_clear_timer(sk); + sk->sk_state = BT_CONNECT; } else { sk->sk_state = BT_CONNECT; iso_sock_set_timer(sk, sk->sk_sndtimeo); @@ -600,18 +619,6 @@ static void iso_sock_kill(struct sock *sk) sock_put(sk); } -static void iso_conn_defer_reject(struct hci_conn *conn) -{ - struct hci_cp_le_reject_cis cp; - - BT_DBG("conn %p", conn); - - memset(&cp, 0, sizeof(cp)); - cp.handle = cpu_to_le16(conn->handle); - cp.reason = HCI_ERROR_REJ_BAD_ADDR; - hci_send_cmd(conn->hdev, HCI_OP_LE_REJECT_CIS, sizeof(cp), &cp); -} - static void __iso_sock_close(struct sock *sk) { BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket); @@ -621,6 +628,7 @@ static void __iso_sock_close(struct sock *sk) iso_sock_cleanup_listen(sk); break; + case BT_CONNECT: case BT_CONNECTED: case BT_CONFIG: if (iso_pi(sk)->conn->hcon) { @@ -636,21 +644,6 @@ static void __iso_sock_close(struct sock *sk) break; case BT_CONNECT2: - if (iso_pi(sk)->conn->hcon) - iso_conn_defer_reject(iso_pi(sk)->conn->hcon); - iso_chan_del(sk, ECONNRESET); - break; - case BT_CONNECT: - /* In case of DEFER_SETUP the hcon would be bound to CIG which - * needs to be removed so just call hci_conn_del so the cleanup - * callback do what is needed. - */ - if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags) && - iso_pi(sk)->conn->hcon) { - hci_conn_del(iso_pi(sk)->conn->hcon); - iso_pi(sk)->conn->hcon = NULL; - } - iso_chan_del(sk, ECONNRESET); break; case BT_DISCONN: @@ -724,21 +717,13 @@ static struct sock *iso_sock_alloc(struct net *net, struct socket *sock, { struct sock *sk; - sk = sk_alloc(net, PF_BLUETOOTH, prio, &iso_proto, kern); + sk = bt_sock_alloc(net, sock, &iso_proto, proto, prio, kern); if (!sk) return NULL; - sock_init_data(sock, sk); - INIT_LIST_HEAD(&bt_sk(sk)->accept_q); - sk->sk_destruct = iso_sock_destruct; sk->sk_sndtimeo = ISO_CONN_TIMEOUT; - sock_reset_flag(sk, SOCK_ZAPPED); - - sk->sk_protocol = proto; - sk->sk_state = BT_OPEN; - /* Set address type as public as default src address is BDADDR_ANY */ iso_pi(sk)->src_type = BDADDR_LE_PUBLIC; @@ -1202,6 +1187,12 @@ static bool check_io_qos(struct bt_iso_io_qos *qos) static bool check_ucast_qos(struct bt_iso_qos *qos) { + if (qos->ucast.cig > 0xef && qos->ucast.cig != BT_ISO_QOS_CIG_UNSET) + return false; + + if (qos->ucast.cis > 0xef && qos->ucast.cis != BT_ISO_QOS_CIS_UNSET) + return false; + if (qos->ucast.sca > 0x07) return false; @@ -1291,6 +1282,18 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); break; + case BT_PKT_STATUS: + if (copy_from_sockptr(&opt, optval, sizeof(u32))) { + err = -EFAULT; + break; + } + + if (opt) + set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); + else + clear_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); + break; + case BT_ISO_QOS: if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND && sk->sk_state != BT_CONNECT2) { @@ -1376,6 +1379,12 @@ static int iso_sock_getsockopt(struct socket *sock, int level, int optname, break; + case BT_PKT_STATUS: + if (put_user(test_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags), + (int __user *)optval)) + err = -EFAULT; + break; + case BT_ISO_QOS: qos = iso_sock_get_qos(sk); @@ -1563,6 +1572,12 @@ static void iso_conn_ready(struct iso_conn *conn) hci_conn_hold(hcon); iso_chan_add(conn, sk, parent); + if (ev && ((struct hci_evt_le_big_sync_estabilished *)ev)->status) { + /* Trigger error signal on child socket */ + sk->sk_err = ECONNREFUSED; + sk->sk_error_report(sk); + } + if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) sk->sk_state = BT_CONNECT2; else @@ -1631,15 +1646,17 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) if (ev2->num_bis < iso_pi(sk)->bc_num_bis) iso_pi(sk)->bc_num_bis = ev2->num_bis; - err = hci_le_big_create_sync(hdev, - &iso_pi(sk)->qos, - iso_pi(sk)->sync_handle, - iso_pi(sk)->bc_num_bis, - iso_pi(sk)->bc_bis); - if (err) { - bt_dev_err(hdev, "hci_le_big_create_sync: %d", - err); - sk = NULL; + if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) { + err = hci_le_big_create_sync(hdev, + &iso_pi(sk)->qos, + iso_pi(sk)->sync_handle, + iso_pi(sk)->bc_num_bis, + iso_pi(sk)->bc_bis); + if (err) { + bt_dev_err(hdev, "hci_le_big_create_sync: %d", + err); + sk = NULL; + } } } } else { @@ -1676,13 +1693,18 @@ static void iso_connect_cfm(struct hci_conn *hcon, __u8 status) } /* Create CIS if pending */ - hci_le_create_cis(hcon); + hci_le_create_cis_pending(hcon->hdev); return; } BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status); - if (!status) { + /* Similar to the success case, if HCI_CONN_BIG_SYNC_FAILED is set, + * queue the failed bis connection into the accept queue of the + * listening socket and wake up userspace, to inform the user about + * the BIG sync failed event. + */ + if (!status || test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags)) { struct iso_conn *conn; conn = iso_conn_add(hcon); @@ -1757,6 +1779,7 @@ void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) if (len == skb->len) { /* Complete frame received */ + hci_skb_pkt_status(skb) = flags & 0x03; iso_recv_frame(conn, skb); return; } @@ -1778,6 +1801,7 @@ void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) if (!conn->rx_skb) goto drop; + hci_skb_pkt_status(conn->rx_skb) = flags & 0x03; skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), skb->len); conn->rx_len = len - skb->len; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 947ca580bb9a..3bdfc3f1e73d 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -178,21 +178,6 @@ done: return err; } -static void l2cap_sock_init_pid(struct sock *sk) -{ - struct l2cap_chan *chan = l2cap_pi(sk)->chan; - - /* Only L2CAP_MODE_EXT_FLOWCTL ever need to access the PID in order to - * group the channels being requested. - */ - if (chan->mode != L2CAP_MODE_EXT_FLOWCTL) - return; - - spin_lock(&sk->sk_peer_lock); - sk->sk_peer_pid = get_pid(task_tgid(current)); - spin_unlock(&sk->sk_peer_lock); -} - static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) { @@ -268,8 +253,6 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, chan->mode != L2CAP_MODE_EXT_FLOWCTL) chan->mode = L2CAP_MODE_LE_FLOWCTL; - l2cap_sock_init_pid(sk); - err = l2cap_chan_connect(chan, la.l2_psm, __le16_to_cpu(la.l2_cid), &la.l2_bdaddr, la.l2_bdaddr_type); if (err) @@ -325,8 +308,6 @@ static int l2cap_sock_listen(struct socket *sock, int backlog) goto done; } - l2cap_sock_init_pid(sk); - sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; @@ -1858,21 +1839,13 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, struct sock *sk; struct l2cap_chan *chan; - sk = sk_alloc(net, PF_BLUETOOTH, prio, &l2cap_proto, kern); + sk = bt_sock_alloc(net, sock, &l2cap_proto, proto, prio, kern); if (!sk) return NULL; - sock_init_data(sock, sk); - INIT_LIST_HEAD(&bt_sk(sk)->accept_q); - sk->sk_destruct = l2cap_sock_destruct; sk->sk_sndtimeo = L2CAP_CONN_TIMEOUT; - sock_reset_flag(sk, SOCK_ZAPPED); - - sk->sk_protocol = proto; - sk->sk_state = BT_OPEN; - chan = l2cap_chan_create(); if (!chan) { sk_free(sk); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index d4498037fadc..d6c9b7bc8592 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -944,6 +944,12 @@ static u32 get_current_settings(struct hci_dev *hdev) if (cis_peripheral_capable(hdev)) settings |= MGMT_SETTING_CIS_PERIPHERAL; + if (bis_capable(hdev)) + settings |= MGMT_SETTING_ISO_BROADCASTER; + + if (sync_recv_capable(hdev)) + settings |= MGMT_SETTING_ISO_SYNC_RECEIVER; + return settings; } @@ -3580,18 +3586,6 @@ unlock: return err; } -static int abort_conn_sync(struct hci_dev *hdev, void *data) -{ - struct hci_conn *conn; - u16 handle = PTR_ERR(data); - - conn = hci_conn_hash_lookup_handle(hdev, handle); - if (!conn) - return 0; - - return hci_abort_conn_sync(hdev, conn, HCI_ERROR_REMOTE_USER_TERM); -} - static int cancel_pair_device(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { @@ -3642,8 +3636,7 @@ static int cancel_pair_device(struct sock *sk, struct hci_dev *hdev, void *data, le_addr_type(addr->type)); if (conn->conn_reason == CONN_REASON_PAIR_DEVICE) - hci_cmd_sync_queue(hdev, abort_conn_sync, ERR_PTR(conn->handle), - NULL); + hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); unlock: hci_dev_unlock(hdev); @@ -8435,8 +8428,8 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev, supported_flags = get_supported_adv_flags(hdev); rp->supported_flags = cpu_to_le32(supported_flags); - rp->max_adv_data_len = HCI_MAX_AD_LENGTH; - rp->max_scan_rsp_len = HCI_MAX_AD_LENGTH; + rp->max_adv_data_len = max_adv_len(hdev); + rp->max_scan_rsp_len = max_adv_len(hdev); rp->max_instances = hdev->le_num_of_adv_sets; rp->num_instances = hdev->adv_instance_cnt; @@ -8472,7 +8465,7 @@ static u8 calculate_name_len(struct hci_dev *hdev) static u8 tlv_data_max_len(struct hci_dev *hdev, u32 adv_flags, bool is_adv_data) { - u8 max_len = HCI_MAX_AD_LENGTH; + u8 max_len = max_adv_len(hdev); if (is_adv_data) { if (adv_flags & (MGMT_ADV_FLAG_DISCOV | diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index bf5cee48916c..abbafa6194ca 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -91,6 +91,33 @@ struct msft_ev_le_monitor_device { struct msft_monitor_advertisement_handle_data { __u8 msft_handle; __u16 mgmt_handle; + __s8 rssi_high; + __s8 rssi_low; + __u8 rssi_low_interval; + __u8 rssi_sampling_period; + __u8 cond_type; + struct list_head list; +}; + +enum monitor_addr_filter_state { + AF_STATE_IDLE, + AF_STATE_ADDING, + AF_STATE_ADDED, + AF_STATE_REMOVING, +}; + +#define MSFT_MONITOR_ADVERTISEMENT_TYPE_ADDR 0x04 +struct msft_monitor_addr_filter_data { + __u8 msft_handle; + __u8 pattern_handle; /* address filters pertain to */ + __u16 mgmt_handle; + int state; + __s8 rssi_high; + __s8 rssi_low; + __u8 rssi_low_interval; + __u8 rssi_sampling_period; + __u8 addr_type; + bdaddr_t bdaddr; struct list_head list; }; @@ -99,9 +126,12 @@ struct msft_data { __u8 evt_prefix_len; __u8 *evt_prefix; struct list_head handle_map; + struct list_head address_filters; __u8 resuming; __u8 suspending; __u8 filter_enabled; + /* To synchronize add/remove address filter and monitor device event.*/ + struct mutex filter_lock; }; bool msft_monitor_supported(struct hci_dev *hdev) @@ -180,6 +210,24 @@ static struct msft_monitor_advertisement_handle_data *msft_find_handle_data return NULL; } +/* This function requires the caller holds msft->filter_lock */ +static struct msft_monitor_addr_filter_data *msft_find_address_data + (struct hci_dev *hdev, u8 addr_type, bdaddr_t *addr, + u8 pattern_handle) +{ + struct msft_monitor_addr_filter_data *entry; + struct msft_data *msft = hdev->msft_data; + + list_for_each_entry(entry, &msft->address_filters, list) { + if (entry->pattern_handle == pattern_handle && + addr_type == entry->addr_type && + !bacmp(addr, &entry->bdaddr)) + return entry; + } + + return NULL; +} + /* This function requires the caller holds hdev->lock */ static int msft_monitor_device_del(struct hci_dev *hdev, __u16 mgmt_handle, bdaddr_t *bdaddr, __u8 addr_type, @@ -240,6 +288,7 @@ static int msft_le_monitor_advertisement_cb(struct hci_dev *hdev, u16 opcode, handle_data->mgmt_handle = monitor->handle; handle_data->msft_handle = rp->handle; + handle_data->cond_type = MSFT_MONITOR_ADVERTISEMENT_TYPE_PATTERN; INIT_LIST_HEAD(&handle_data->list); list_add(&handle_data->list, &msft->handle_map); @@ -254,6 +303,70 @@ unlock: return status; } +/* This function requires the caller holds hci_req_sync_lock */ +static void msft_remove_addr_filters_sync(struct hci_dev *hdev, u8 handle) +{ + struct msft_monitor_addr_filter_data *address_filter, *n; + struct msft_cp_le_cancel_monitor_advertisement cp; + struct msft_data *msft = hdev->msft_data; + struct list_head head; + struct sk_buff *skb; + + INIT_LIST_HEAD(&head); + + /* Cancel all corresponding address monitors */ + mutex_lock(&msft->filter_lock); + + list_for_each_entry_safe(address_filter, n, &msft->address_filters, + list) { + if (address_filter->pattern_handle != handle) + continue; + + list_del(&address_filter->list); + + /* Keep the address filter and let + * msft_add_address_filter_sync() remove and free the address + * filter. + */ + if (address_filter->state == AF_STATE_ADDING) { + address_filter->state = AF_STATE_REMOVING; + continue; + } + + /* Keep the address filter and let + * msft_cancel_address_filter_sync() remove and free the address + * filter + */ + if (address_filter->state == AF_STATE_REMOVING) + continue; + + list_add_tail(&address_filter->list, &head); + } + + mutex_unlock(&msft->filter_lock); + + list_for_each_entry_safe(address_filter, n, &head, list) { + list_del(&address_filter->list); + + cp.sub_opcode = MSFT_OP_LE_CANCEL_MONITOR_ADVERTISEMENT; + cp.handle = address_filter->msft_handle; + + skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp, + HCI_CMD_TIMEOUT); + if (IS_ERR_OR_NULL(skb)) { + kfree(address_filter); + continue; + } + + kfree_skb(skb); + + bt_dev_dbg(hdev, "MSFT: Canceled device %pMR address filter", + &address_filter->bdaddr); + + kfree(address_filter); + } +} + static int msft_le_cancel_monitor_advertisement_cb(struct hci_dev *hdev, u16 opcode, struct adv_monitor *monitor, @@ -263,6 +376,7 @@ static int msft_le_cancel_monitor_advertisement_cb(struct hci_dev *hdev, struct msft_monitor_advertisement_handle_data *handle_data; struct msft_data *msft = hdev->msft_data; int status = 0; + u8 msft_handle; rp = (struct msft_rp_le_cancel_monitor_advertisement *)skb->data; if (skb->len < sizeof(*rp)) { @@ -293,11 +407,17 @@ static int msft_le_cancel_monitor_advertisement_cb(struct hci_dev *hdev, NULL, 0, false); } + msft_handle = handle_data->msft_handle; + list_del(&handle_data->list); kfree(handle_data); - } - hci_dev_unlock(hdev); + hci_dev_unlock(hdev); + + msft_remove_addr_filters_sync(hdev, msft_handle); + } else { + hci_dev_unlock(hdev); + } done: return status; @@ -394,12 +514,14 @@ static int msft_add_monitor_sync(struct hci_dev *hdev, { struct msft_cp_le_monitor_advertisement *cp; struct msft_le_monitor_advertisement_pattern_data *pattern_data; + struct msft_monitor_advertisement_handle_data *handle_data; struct msft_le_monitor_advertisement_pattern *pattern; struct adv_pattern *entry; size_t total_size = sizeof(*cp) + sizeof(*pattern_data); ptrdiff_t offset = 0; u8 pattern_count = 0; struct sk_buff *skb; + int err; if (!msft_monitor_pattern_valid(monitor)) return -EINVAL; @@ -436,16 +558,31 @@ static int msft_add_monitor_sync(struct hci_dev *hdev, skb = __hci_cmd_sync(hdev, hdev->msft_opcode, total_size, cp, HCI_CMD_TIMEOUT); - kfree(cp); if (IS_ERR_OR_NULL(skb)) { - if (!skb) - return -EIO; - return PTR_ERR(skb); + err = PTR_ERR(skb); + goto out_free; } - return msft_le_monitor_advertisement_cb(hdev, hdev->msft_opcode, - monitor, skb); + err = msft_le_monitor_advertisement_cb(hdev, hdev->msft_opcode, + monitor, skb); + if (err) + goto out_free; + + handle_data = msft_find_handle_data(hdev, monitor->handle, true); + if (!handle_data) { + err = -ENODATA; + goto out_free; + } + + handle_data->rssi_high = cp->rssi_high; + handle_data->rssi_low = cp->rssi_low; + handle_data->rssi_low_interval = cp->rssi_low_interval; + handle_data->rssi_sampling_period = cp->rssi_sampling_period; + +out_free: + kfree(cp); + return err; } /* This function requires the caller holds hci_req_sync_lock */ @@ -538,6 +675,7 @@ void msft_do_close(struct hci_dev *hdev) { struct msft_data *msft = hdev->msft_data; struct msft_monitor_advertisement_handle_data *handle_data, *tmp; + struct msft_monitor_addr_filter_data *address_filter, *n; struct adv_monitor *monitor; if (!msft) @@ -559,6 +697,14 @@ void msft_do_close(struct hci_dev *hdev) kfree(handle_data); } + mutex_lock(&msft->filter_lock); + list_for_each_entry_safe(address_filter, n, &msft->address_filters, + list) { + list_del(&address_filter->list); + kfree(address_filter); + } + mutex_unlock(&msft->filter_lock); + hci_dev_lock(hdev); /* Clear any devices that are being monitored and notify device lost */ @@ -568,6 +714,49 @@ void msft_do_close(struct hci_dev *hdev) hci_dev_unlock(hdev); } +static int msft_cancel_address_filter_sync(struct hci_dev *hdev, void *data) +{ + struct msft_monitor_addr_filter_data *address_filter = data; + struct msft_cp_le_cancel_monitor_advertisement cp; + struct msft_data *msft = hdev->msft_data; + struct sk_buff *skb; + int err = 0; + + if (!msft) { + bt_dev_err(hdev, "MSFT: msft data is freed"); + return -EINVAL; + } + + /* The address filter has been removed by hci dev close */ + if (!test_bit(HCI_UP, &hdev->flags)) + return 0; + + mutex_lock(&msft->filter_lock); + list_del(&address_filter->list); + mutex_unlock(&msft->filter_lock); + + cp.sub_opcode = MSFT_OP_LE_CANCEL_MONITOR_ADVERTISEMENT; + cp.handle = address_filter->msft_handle; + + skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp, + HCI_CMD_TIMEOUT); + if (IS_ERR_OR_NULL(skb)) { + bt_dev_err(hdev, "MSFT: Failed to cancel address (%pMR) filter", + &address_filter->bdaddr); + err = -EIO; + goto done; + } + kfree_skb(skb); + + bt_dev_dbg(hdev, "MSFT: Canceled device %pMR address filter", + &address_filter->bdaddr); + +done: + kfree(address_filter); + + return err; +} + void msft_register(struct hci_dev *hdev) { struct msft_data *msft = NULL; @@ -581,7 +770,9 @@ void msft_register(struct hci_dev *hdev) } INIT_LIST_HEAD(&msft->handle_map); + INIT_LIST_HEAD(&msft->address_filters); hdev->msft_data = msft; + mutex_init(&msft->filter_lock); } void msft_unregister(struct hci_dev *hdev) @@ -596,6 +787,7 @@ void msft_unregister(struct hci_dev *hdev) hdev->msft_data = NULL; kfree(msft->evt_prefix); + mutex_destroy(&msft->filter_lock); kfree(msft); } @@ -645,11 +837,149 @@ static void *msft_skb_pull(struct hci_dev *hdev, struct sk_buff *skb, return data; } +static int msft_add_address_filter_sync(struct hci_dev *hdev, void *data) +{ + struct msft_monitor_addr_filter_data *address_filter = data; + struct msft_rp_le_monitor_advertisement *rp; + struct msft_cp_le_monitor_advertisement *cp; + struct msft_data *msft = hdev->msft_data; + struct sk_buff *skb = NULL; + bool remove = false; + size_t size; + + if (!msft) { + bt_dev_err(hdev, "MSFT: msft data is freed"); + return -EINVAL; + } + + /* The address filter has been removed by hci dev close */ + if (!test_bit(HCI_UP, &hdev->flags)) + return -ENODEV; + + /* We are safe to use the address filter from now on. + * msft_monitor_device_evt() wouldn't delete this filter because it's + * not been added by now. + * And all other functions that requiring hci_req_sync_lock wouldn't + * touch this filter before this func completes because it's protected + * by hci_req_sync_lock. + */ + + if (address_filter->state == AF_STATE_REMOVING) { + mutex_lock(&msft->filter_lock); + list_del(&address_filter->list); + mutex_unlock(&msft->filter_lock); + kfree(address_filter); + return 0; + } + + size = sizeof(*cp) + + sizeof(address_filter->addr_type) + + sizeof(address_filter->bdaddr); + cp = kzalloc(size, GFP_KERNEL); + if (!cp) { + bt_dev_err(hdev, "MSFT: Alloc cmd param err"); + remove = true; + goto done; + } + cp->sub_opcode = MSFT_OP_LE_MONITOR_ADVERTISEMENT; + cp->rssi_high = address_filter->rssi_high; + cp->rssi_low = address_filter->rssi_low; + cp->rssi_low_interval = address_filter->rssi_low_interval; + cp->rssi_sampling_period = address_filter->rssi_sampling_period; + cp->cond_type = MSFT_MONITOR_ADVERTISEMENT_TYPE_ADDR; + cp->data[0] = address_filter->addr_type; + memcpy(&cp->data[1], &address_filter->bdaddr, + sizeof(address_filter->bdaddr)); + + skb = __hci_cmd_sync(hdev, hdev->msft_opcode, size, cp, + HCI_CMD_TIMEOUT); + if (IS_ERR_OR_NULL(skb)) { + bt_dev_err(hdev, "Failed to enable address %pMR filter", + &address_filter->bdaddr); + skb = NULL; + remove = true; + goto done; + } + + rp = skb_pull_data(skb, sizeof(*rp)); + if (!rp || rp->sub_opcode != MSFT_OP_LE_MONITOR_ADVERTISEMENT || + rp->status) + remove = true; + +done: + mutex_lock(&msft->filter_lock); + + if (remove) { + bt_dev_warn(hdev, "MSFT: Remove address (%pMR) filter", + &address_filter->bdaddr); + list_del(&address_filter->list); + kfree(address_filter); + } else { + address_filter->state = AF_STATE_ADDED; + address_filter->msft_handle = rp->handle; + bt_dev_dbg(hdev, "MSFT: Address %pMR filter enabled", + &address_filter->bdaddr); + } + mutex_unlock(&msft->filter_lock); + + kfree_skb(skb); + + return 0; +} + +/* This function requires the caller holds msft->filter_lock */ +static struct msft_monitor_addr_filter_data *msft_add_address_filter + (struct hci_dev *hdev, u8 addr_type, bdaddr_t *bdaddr, + struct msft_monitor_advertisement_handle_data *handle_data) +{ + struct msft_monitor_addr_filter_data *address_filter = NULL; + struct msft_data *msft = hdev->msft_data; + int err; + + address_filter = kzalloc(sizeof(*address_filter), GFP_KERNEL); + if (!address_filter) + return NULL; + + address_filter->state = AF_STATE_ADDING; + address_filter->msft_handle = 0xff; + address_filter->pattern_handle = handle_data->msft_handle; + address_filter->mgmt_handle = handle_data->mgmt_handle; + address_filter->rssi_high = handle_data->rssi_high; + address_filter->rssi_low = handle_data->rssi_low; + address_filter->rssi_low_interval = handle_data->rssi_low_interval; + address_filter->rssi_sampling_period = handle_data->rssi_sampling_period; + address_filter->addr_type = addr_type; + bacpy(&address_filter->bdaddr, bdaddr); + + /* With the above AF_STATE_ADDING, duplicated address filter can be + * avoided when receiving monitor device event (found/lost) frequently + * for the same device. + */ + list_add_tail(&address_filter->list, &msft->address_filters); + + err = hci_cmd_sync_queue(hdev, msft_add_address_filter_sync, + address_filter, NULL); + if (err < 0) { + bt_dev_err(hdev, "MSFT: Add address %pMR filter err", bdaddr); + list_del(&address_filter->list); + kfree(address_filter); + return NULL; + } + + bt_dev_dbg(hdev, "MSFT: Add device %pMR address filter", + &address_filter->bdaddr); + + return address_filter; +} + /* This function requires the caller holds hdev->lock */ static void msft_monitor_device_evt(struct hci_dev *hdev, struct sk_buff *skb) { + struct msft_monitor_addr_filter_data *n, *address_filter = NULL; struct msft_ev_le_monitor_device *ev; struct msft_monitor_advertisement_handle_data *handle_data; + struct msft_data *msft = hdev->msft_data; + u16 mgmt_handle = 0xffff; u8 addr_type; ev = msft_skb_pull(hdev, skb, MSFT_EV_LE_MONITOR_DEVICE, sizeof(*ev)); @@ -662,9 +992,53 @@ static void msft_monitor_device_evt(struct hci_dev *hdev, struct sk_buff *skb) ev->monitor_state, &ev->bdaddr); handle_data = msft_find_handle_data(hdev, ev->monitor_handle, false); - if (!handle_data) + + if (!test_bit(HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER, &hdev->quirks)) { + if (!handle_data) + return; + mgmt_handle = handle_data->mgmt_handle; + goto report_state; + } + + if (handle_data) { + /* Don't report any device found/lost event from pattern + * monitors. Pattern monitor always has its address filters for + * tracking devices. + */ + + address_filter = msft_find_address_data(hdev, ev->addr_type, + &ev->bdaddr, + handle_data->msft_handle); + if (address_filter) + return; + + if (ev->monitor_state && handle_data->cond_type == + MSFT_MONITOR_ADVERTISEMENT_TYPE_PATTERN) + msft_add_address_filter(hdev, ev->addr_type, + &ev->bdaddr, handle_data); + return; + } + /* This device event is not from pattern monitor. + * Report it if there is a corresponding address_filter for it. + */ + list_for_each_entry(n, &msft->address_filters, list) { + if (n->state == AF_STATE_ADDED && + n->msft_handle == ev->monitor_handle) { + mgmt_handle = n->mgmt_handle; + address_filter = n; + break; + } + } + + if (!address_filter) { + bt_dev_warn(hdev, "MSFT: Unexpected device event %pMR, %u, %u", + &ev->bdaddr, ev->monitor_handle, ev->monitor_state); + return; + } + +report_state: switch (ev->addr_type) { case ADDR_LE_DEV_PUBLIC: addr_type = BDADDR_LE_PUBLIC; @@ -681,12 +1055,18 @@ static void msft_monitor_device_evt(struct hci_dev *hdev, struct sk_buff *skb) return; } - if (ev->monitor_state) - msft_device_found(hdev, &ev->bdaddr, addr_type, - handle_data->mgmt_handle); - else - msft_device_lost(hdev, &ev->bdaddr, addr_type, - handle_data->mgmt_handle); + if (ev->monitor_state) { + msft_device_found(hdev, &ev->bdaddr, addr_type, mgmt_handle); + } else { + if (address_filter && address_filter->state == AF_STATE_ADDED) { + address_filter->state = AF_STATE_REMOVING; + hci_cmd_sync_queue(hdev, + msft_cancel_address_filter_sync, + address_filter, + NULL); + } + msft_device_lost(hdev, &ev->bdaddr, addr_type, mgmt_handle); + } } void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) @@ -724,7 +1104,9 @@ void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) switch (*evt) { case MSFT_EV_LE_MONITOR_DEVICE: + mutex_lock(&msft->filter_lock); msft_monitor_device_evt(hdev, skb); + mutex_unlock(&msft->filter_lock); break; default: diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 4397e14ff560..b54e8a530f55 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -268,18 +268,16 @@ static struct proto rfcomm_proto = { .obj_size = sizeof(struct rfcomm_pinfo) }; -static struct sock *rfcomm_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern) +static struct sock *rfcomm_sock_alloc(struct net *net, struct socket *sock, + int proto, gfp_t prio, int kern) { struct rfcomm_dlc *d; struct sock *sk; - sk = sk_alloc(net, PF_BLUETOOTH, prio, &rfcomm_proto, kern); + sk = bt_sock_alloc(net, sock, &rfcomm_proto, proto, prio, kern); if (!sk) return NULL; - sock_init_data(sock, sk); - INIT_LIST_HEAD(&bt_sk(sk)->accept_q); - d = rfcomm_dlc_alloc(prio); if (!d) { sk_free(sk); @@ -298,11 +296,6 @@ static struct sock *rfcomm_sock_alloc(struct net *net, struct socket *sock, int sk->sk_sndbuf = RFCOMM_MAX_CREDITS * RFCOMM_DEFAULT_MTU * 10; sk->sk_rcvbuf = RFCOMM_MAX_CREDITS * RFCOMM_DEFAULT_MTU * 10; - sock_reset_flag(sk, SOCK_ZAPPED); - - sk->sk_protocol = proto; - sk->sk_state = BT_OPEN; - bt_sock_link(&rfcomm_sk_list, sk); BT_DBG("sk %p", sk); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 7762604ddfc0..50ad5935ae47 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -68,7 +68,6 @@ struct sco_pinfo { bdaddr_t dst; __u32 flags; __u16 setting; - __u8 cmsg_mask; struct bt_codec codec; struct sco_conn *conn; }; @@ -471,15 +470,6 @@ static void sco_sock_close(struct sock *sk) release_sock(sk); } -static void sco_skb_put_cmsg(struct sk_buff *skb, struct msghdr *msg, - struct sock *sk) -{ - if (sco_pi(sk)->cmsg_mask & SCO_CMSG_PKT_STATUS) - put_cmsg(msg, SOL_BLUETOOTH, BT_SCM_PKT_STATUS, - sizeof(bt_cb(skb)->sco.pkt_status), - &bt_cb(skb)->sco.pkt_status); -} - static void sco_sock_init(struct sock *sk, struct sock *parent) { BT_DBG("sk %p", sk); @@ -488,8 +478,6 @@ static void sco_sock_init(struct sock *sk, struct sock *parent) sk->sk_type = parent->sk_type; bt_sk(sk)->flags = bt_sk(parent)->flags; security_sk_clone(parent, sk); - } else { - bt_sk(sk)->skb_put_cmsg = sco_skb_put_cmsg; } } @@ -504,21 +492,13 @@ static struct sock *sco_sock_alloc(struct net *net, struct socket *sock, { struct sock *sk; - sk = sk_alloc(net, PF_BLUETOOTH, prio, &sco_proto, kern); + sk = bt_sock_alloc(net, sock, &sco_proto, proto, prio, kern); if (!sk) return NULL; - sock_init_data(sock, sk); - INIT_LIST_HEAD(&bt_sk(sk)->accept_q); - sk->sk_destruct = sco_sock_destruct; sk->sk_sndtimeo = SCO_CONN_TIMEOUT; - sock_reset_flag(sk, SOCK_ZAPPED); - - sk->sk_protocol = proto; - sk->sk_state = BT_OPEN; - sco_pi(sk)->setting = BT_VOICE_CVSD_16BIT; sco_pi(sk)->codec.id = BT_CODEC_CVSD; sco_pi(sk)->codec.cid = 0xffff; @@ -915,9 +895,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, } if (opt) - sco_pi(sk)->cmsg_mask |= SCO_CMSG_PKT_STATUS; + set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); else - sco_pi(sk)->cmsg_mask &= SCO_CMSG_PKT_STATUS; + clear_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); break; case BT_CODEC: @@ -1048,7 +1028,6 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, int len, err = 0; struct bt_voice voice; u32 phys; - int pkt_status; int buf_len; struct codec_list *c; u8 num_codecs, i, __user *ptr; @@ -1102,9 +1081,8 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, break; case BT_PKT_STATUS: - pkt_status = (sco_pi(sk)->cmsg_mask & SCO_CMSG_PKT_STATUS); - - if (put_user(pkt_status, (int __user *)optval)) + if (put_user(test_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags), + (int __user *)optval)) err = -EFAULT; break; diff --git a/net/core/dev.c b/net/core/dev.c index 636b41f0b32d..17e6281e408c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9589,6 +9589,11 @@ static int dev_index_reserve(struct net *net, u32 ifindex) { int err; + if (ifindex > INT_MAX) { + DEBUG_NET_WARN_ON_ONCE(1); + return -EINVAL; + } + if (!ifindex) err = xa_alloc_cyclic(&net->dev_by_index, &ifindex, NULL, xa_limit_31b, &net->ifindex, GFP_KERNEL); diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 797c813c7c77..c1aea8b756b6 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -10,11 +10,11 @@ static int netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp, - u32 portid, u32 seq, int flags, u32 cmd) + const struct genl_info *info) { void *hdr; - hdr = genlmsg_put(rsp, portid, seq, &netdev_nl_family, flags, cmd); + hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; @@ -41,17 +41,20 @@ netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp, static void netdev_genl_dev_notify(struct net_device *netdev, int cmd) { + struct genl_info info; struct sk_buff *ntf; if (!genl_has_listeners(&netdev_nl_family, dev_net(netdev), NETDEV_NLGRP_MGMT)) return; + genl_info_init_ntf(&info, &netdev_nl_family, cmd); + ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!ntf) return; - if (netdev_nl_dev_fill(netdev, ntf, 0, 0, 0, cmd)) { + if (netdev_nl_dev_fill(netdev, ntf, &info)) { nlmsg_free(ntf); return; } @@ -80,8 +83,7 @@ int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info) netdev = __dev_get_by_index(genl_info_net(info), ifindex); if (netdev) - err = netdev_nl_dev_fill(netdev, rsp, info->snd_portid, - info->snd_seq, 0, info->genlhdr->cmd); + err = netdev_nl_dev_fill(netdev, rsp, info); else err = -ENODEV; @@ -105,10 +107,7 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) rtnl_lock(); for_each_netdev_dump(net, netdev, cb->args[0]) { - err = netdev_nl_dev_fill(netdev, skb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, 0, - NETDEV_CMD_DEV_GET); + err = netdev_nl_dev_fill(netdev, skb, genl_info_dump(cb)); if (err < 0) break; } diff --git a/net/core/sock.c b/net/core/sock.c index 525619776c6f..22d94394335f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -767,7 +767,7 @@ bool sk_mc_loop(struct sock *sk) return true; switch (sk->sk_family) { case AF_INET: - return inet_sk(sk)->mc_loop; + return inet_test_bit(MC_LOOP, sk); #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return inet6_sk(sk)->mc_loop; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 8e919cfe6e23..8dd6837c476a 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -247,7 +247,6 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) const u8 offset = iph->ihl << 2; const struct dccp_hdr *dh; struct dccp_sock *dp; - struct inet_sock *inet; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct sock *sk; @@ -361,8 +360,7 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) * --ANK (980905) */ - inet = inet_sk(sk); - if (!sock_owned_by_user(sk) && inet->recverr) { + if (!sock_owned_by_user(sk) && inet_test_bit(RECVERR, sk)) { sk->sk_err = err; sk_error_report(sk); } else { /* Only an error on timeout */ diff --git a/net/devlink/dev.c b/net/devlink/dev.c index 5dfba2248b90..abf3393a7a17 100644 --- a/net/devlink/dev.c +++ b/net/devlink/dev.c @@ -218,11 +218,11 @@ int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info) static int devlink_nl_get_dump_one(struct sk_buff *msg, struct devlink *devlink, - struct netlink_callback *cb) + struct netlink_callback *cb, int flags) { return devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI); + cb->nlh->nlmsg_seq, flags); } int devlink_nl_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) @@ -828,13 +828,13 @@ int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info) static int devlink_nl_info_get_dump_one(struct sk_buff *msg, struct devlink *devlink, - struct netlink_callback *cb) + struct netlink_callback *cb, int flags) { int err; err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->nlh->nlmsg_seq, flags, cb->extack); if (err == -EOPNOTSUPP) err = 0; @@ -1206,8 +1206,7 @@ err_cancel_msg: return err; } -int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct sk_buff *msg; @@ -1230,23 +1229,25 @@ int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } -static int -devlink_nl_cmd_selftests_get_dump_one(struct sk_buff *msg, - struct devlink *devlink, - struct netlink_callback *cb) +static int devlink_nl_selftests_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb, + int flags) { if (!devlink->ops->selftest_check) return 0; return devlink_nl_selftests_fill(msg, devlink, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->nlh->nlmsg_seq, flags, cb->extack); } -const struct devlink_cmd devl_cmd_selftests_get = { - .dump_one = devlink_nl_cmd_selftests_get_dump_one, -}; +int devlink_nl_selftests_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return devlink_nl_dumpit(skb, cb, devlink_nl_selftests_get_dump_one); +} static int devlink_selftest_result_put(struct sk_buff *skb, unsigned int id, enum devlink_selftest_status test_status) diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h index 7fdd956ff992..eb1d5066c73f 100644 --- a/net/devlink/devl_internal.h +++ b/net/devlink/devl_internal.h @@ -92,9 +92,6 @@ static inline bool devl_is_registered(struct devlink *devlink) /* Netlink */ #define DEVLINK_NL_FLAG_NEED_PORT BIT(0) #define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT BIT(1) -#define DEVLINK_NL_FLAG_NEED_RATE BIT(2) -#define DEVLINK_NL_FLAG_NEED_RATE_NODE BIT(3) -#define DEVLINK_NL_FLAG_NEED_LINECARD BIT(4) enum devlink_multicast_groups { DEVLINK_MCGRP_CONFIG, @@ -118,13 +115,10 @@ struct devlink_nl_dump_state { typedef int devlink_nl_dump_one_func_t(struct sk_buff *msg, struct devlink *devlink, - struct netlink_callback *cb); + struct netlink_callback *cb, + int flags); -struct devlink_cmd { - devlink_nl_dump_one_func_t *dump_one; -}; - -extern const struct genl_small_ops devlink_nl_small_ops[54]; +extern const struct genl_small_ops devlink_nl_small_ops[40]; struct devlink * devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs); @@ -134,7 +128,6 @@ void devlink_notify_register(struct devlink *devlink); int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb, devlink_nl_dump_one_func_t *dump_one); -int devlink_nl_instance_iter_dumpit(struct sk_buff *msg, struct netlink_callback *cb); static inline struct devlink_nl_dump_state * devlink_dump_state(struct netlink_callback *cb) @@ -154,22 +147,6 @@ devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) return 0; } -/* Commands */ -extern const struct devlink_cmd devl_cmd_port_get; -extern const struct devlink_cmd devl_cmd_sb_get; -extern const struct devlink_cmd devl_cmd_sb_pool_get; -extern const struct devlink_cmd devl_cmd_sb_port_pool_get; -extern const struct devlink_cmd devl_cmd_sb_tc_pool_bind_get; -extern const struct devlink_cmd devl_cmd_param_get; -extern const struct devlink_cmd devl_cmd_region_get; -extern const struct devlink_cmd devl_cmd_health_reporter_get; -extern const struct devlink_cmd devl_cmd_trap_get; -extern const struct devlink_cmd devl_cmd_trap_group_get; -extern const struct devlink_cmd devl_cmd_trap_policer_get; -extern const struct devlink_cmd devl_cmd_rate_get; -extern const struct devlink_cmd devl_cmd_linecard_get; -extern const struct devlink_cmd devl_cmd_selftests_get; - /* Notify */ void devlink_notify(struct devlink *devlink, enum devlink_command cmd); @@ -203,29 +180,16 @@ int devlink_resources_validate(struct devlink *devlink, struct devlink_resource *resource, struct genl_info *info); -/* Line cards */ -struct devlink_linecard; - -struct devlink_linecard * -devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info); - /* Rates */ int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, struct netlink_ext_ack *extack); -struct devlink_rate * -devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info); -struct devlink_rate * -devlink_rate_node_get_from_info(struct devlink *devlink, - struct genl_info *info); + /* Devlink nl cmds */ int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info); int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb, - struct genl_info *info); int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, diff --git a/net/devlink/health.c b/net/devlink/health.c index 194340a8bb86..638cad8d5c65 100644 --- a/net/devlink/health.c +++ b/net/devlink/health.c @@ -356,8 +356,8 @@ devlink_health_reporter_get_from_info(struct devlink *devlink, return devlink_health_reporter_get_from_attrs(devlink, info->attrs); } -int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_health_reporter_get_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; @@ -384,18 +384,29 @@ int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } -static int -devlink_nl_cmd_health_reporter_get_dump_one(struct sk_buff *msg, - struct devlink *devlink, - struct netlink_callback *cb) +static int devlink_nl_health_reporter_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb, + int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); + const struct genl_info *info = genl_info_dump(cb); struct devlink_health_reporter *reporter; + unsigned long port_index_end = ULONG_MAX; + struct nlattr **attrs = info->attrs; + unsigned long port_index_start = 0; struct devlink_port *port; unsigned long port_index; int idx = 0; int err; + if (attrs && attrs[DEVLINK_ATTR_PORT_INDEX]) { + port_index_start = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); + port_index_end = port_index_start; + flags |= NLM_F_DUMP_FILTERED; + goto per_port_dump; + } + list_for_each_entry(reporter, &devlink->reporter_list, list) { if (idx < state->idx) { idx++; @@ -405,14 +416,16 @@ devlink_nl_cmd_health_reporter_get_dump_one(struct sk_buff *msg, DEVLINK_CMD_HEALTH_REPORTER_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - NLM_F_MULTI); + flags); if (err) { state->idx = idx; return err; } idx++; } - xa_for_each(&devlink->ports, port_index, port) { +per_port_dump: + xa_for_each_range(&devlink->ports, port_index, port, + port_index_start, port_index_end) { list_for_each_entry(reporter, &port->reporter_list, list) { if (idx < state->idx) { idx++; @@ -422,7 +435,7 @@ devlink_nl_cmd_health_reporter_get_dump_one(struct sk_buff *msg, DEVLINK_CMD_HEALTH_REPORTER_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - NLM_F_MULTI); + flags); if (err) { state->idx = idx; return err; @@ -434,9 +447,12 @@ devlink_nl_cmd_health_reporter_get_dump_one(struct sk_buff *msg, return 0; } -const struct devlink_cmd devl_cmd_health_reporter_get = { - .dump_one = devlink_nl_cmd_health_reporter_get_dump_one, -}; +int devlink_nl_health_reporter_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return devlink_nl_dumpit(skb, cb, + devlink_nl_health_reporter_get_dump_one); +} int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, struct genl_info *info) @@ -1248,7 +1264,7 @@ out: static struct devlink_health_reporter * devlink_health_reporter_get_from_cb(struct netlink_callback *cb) { - const struct genl_dumpit_info *info = genl_dumpit_info(cb); + const struct genl_info *info = genl_info_dump(cb); struct devlink_health_reporter *reporter; struct nlattr **attrs = info->attrs; struct devlink *devlink; diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c index e7900d9fa205..72ba8a716525 100644 --- a/net/devlink/leftover.c +++ b/net/devlink/leftover.c @@ -232,13 +232,13 @@ devlink_rate_node_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) return devlink_rate_node_get_by_name(devlink, rate_node_name); } -struct devlink_rate * +static struct devlink_rate * devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info) { return devlink_rate_node_get_from_attrs(devlink, info->attrs); } -struct devlink_rate * +static struct devlink_rate * devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info) { struct nlattr **attrs = info->attrs; @@ -285,7 +285,7 @@ devlink_linecard_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) return ERR_PTR(-EINVAL); } -struct devlink_linecard * +static struct devlink_linecard * devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info) { return devlink_linecard_get_from_attrs(devlink, info->attrs); @@ -1005,8 +1005,8 @@ static void devlink_rate_notify(struct devlink_rate *devlink_rate, } static int -devlink_nl_cmd_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink, - struct netlink_callback *cb) +devlink_nl_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_rate *devlink_rate; @@ -1022,8 +1022,7 @@ devlink_nl_cmd_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink, continue; } err = devlink_nl_rate_fill(msg, devlink_rate, cmd, id, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, NULL); + cb->nlh->nlmsg_seq, flags, NULL); if (err) { state->idx = idx; break; @@ -1034,17 +1033,22 @@ devlink_nl_cmd_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink, return err; } -const struct devlink_cmd devl_cmd_rate_get = { - .dump_one = devlink_nl_cmd_rate_get_dump_one, -}; +int devlink_nl_rate_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + return devlink_nl_dumpit(skb, cb, devlink_nl_rate_get_dump_one); +} -static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info) { - struct devlink_rate *devlink_rate = info->user_ptr[1]; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_rate *devlink_rate; struct sk_buff *msg; int err; + devlink_rate = devlink_rate_get_from_info(devlink, info); + if (IS_ERR(devlink_rate)) + return PTR_ERR(devlink_rate); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; @@ -1072,8 +1076,7 @@ devlink_rate_is_parent_node(struct devlink_rate *devlink_rate, return false; } -static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct sk_buff *msg; @@ -1095,8 +1098,8 @@ static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, } static int -devlink_nl_cmd_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink, - struct netlink_callback *cb) +devlink_nl_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_port *devlink_port; @@ -1107,8 +1110,8 @@ devlink_nl_cmd_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink, err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, cb->extack); + cb->nlh->nlmsg_seq, flags, + cb->extack); if (err) { state->idx = port_index; break; @@ -1118,9 +1121,10 @@ devlink_nl_cmd_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink, return err; } -const struct devlink_cmd devl_cmd_port_get = { - .dump_one = devlink_nl_cmd_port_get_dump_one, -}; +int devlink_nl_port_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + return devlink_nl_dumpit(skb, cb, devlink_nl_port_get_dump_one); +} static int devlink_port_type_set(struct devlink_port *devlink_port, enum devlink_port_type port_type) @@ -1629,11 +1633,16 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, static int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb, struct genl_info *info) { - struct devlink_rate *devlink_rate = info->user_ptr[1]; - struct devlink *devlink = devlink_rate->devlink; - const struct devlink_ops *ops = devlink->ops; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_rate *devlink_rate; + const struct devlink_ops *ops; int err; + devlink_rate = devlink_rate_get_from_info(devlink, info); + if (IS_ERR(devlink_rate)) + return PTR_ERR(devlink_rate); + + ops = devlink->ops; if (!ops || !devlink_rate_set_ops_supported(ops, info, devlink_rate->type)) return -EOPNOTSUPP; @@ -1704,18 +1713,22 @@ err_strdup: static int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb, struct genl_info *info) { - struct devlink_rate *rate_node = info->user_ptr[1]; - struct devlink *devlink = rate_node->devlink; - const struct devlink_ops *ops = devlink->ops; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_rate *rate_node; int err; + rate_node = devlink_rate_node_get_from_info(devlink, info); + if (IS_ERR(rate_node)) + return PTR_ERR(rate_node); + if (refcount_read(&rate_node->refcnt) > 1) { NL_SET_ERR_MSG(info->extack, "Node has children. Cannot delete node."); return -EBUSY; } devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL); - err = ops->rate_node_del(rate_node, rate_node->priv, info->extack); + err = devlink->ops->rate_node_del(rate_node, rate_node->priv, + info->extack); if (rate_node->parent) refcount_dec(&rate_node->parent->refcnt); list_del(&rate_node->list); @@ -1811,14 +1824,17 @@ static void devlink_linecard_notify(struct devlink_linecard *linecard, msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } -static int devlink_nl_cmd_linecard_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info) { - struct devlink_linecard *linecard = info->user_ptr[1]; - struct devlink *devlink = linecard->devlink; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_linecard *linecard; struct sk_buff *msg; int err; + linecard = devlink_linecard_get_from_info(devlink, info); + if (IS_ERR(linecard)) + return PTR_ERR(linecard); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; @@ -1837,9 +1853,10 @@ static int devlink_nl_cmd_linecard_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } -static int devlink_nl_cmd_linecard_get_dump_one(struct sk_buff *msg, - struct devlink *devlink, - struct netlink_callback *cb) +static int devlink_nl_linecard_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb, + int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_linecard *linecard; @@ -1855,8 +1872,7 @@ static int devlink_nl_cmd_linecard_get_dump_one(struct sk_buff *msg, err = devlink_nl_linecard_fill(msg, devlink, linecard, DEVLINK_CMD_LINECARD_NEW, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, + cb->nlh->nlmsg_seq, flags, cb->extack); mutex_unlock(&linecard->state_lock); if (err) { @@ -1869,9 +1885,11 @@ static int devlink_nl_cmd_linecard_get_dump_one(struct sk_buff *msg, return err; } -const struct devlink_cmd devl_cmd_linecard_get = { - .dump_one = devlink_nl_cmd_linecard_get_dump_one, -}; +int devlink_nl_linecard_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return devlink_nl_dumpit(skb, cb, devlink_nl_linecard_get_dump_one); +} static struct devlink_linecard_type * devlink_linecard_type_lookup(struct devlink_linecard *linecard, @@ -2008,10 +2026,15 @@ out: static int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb, struct genl_info *info) { - struct devlink_linecard *linecard = info->user_ptr[1]; struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_linecard *linecard; int err; + linecard = devlink_linecard_get_from_info(devlink, info); + if (IS_ERR(linecard)) + return PTR_ERR(linecard); + if (info->attrs[DEVLINK_ATTR_LINECARD_TYPE]) { const char *type; @@ -2068,8 +2091,7 @@ nla_put_failure: return -EMSGSIZE; } -static int devlink_nl_cmd_sb_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_sb *devlink_sb; @@ -2096,8 +2118,8 @@ static int devlink_nl_cmd_sb_get_doit(struct sk_buff *skb, } static int -devlink_nl_cmd_sb_get_dump_one(struct sk_buff *msg, struct devlink *devlink, - struct netlink_callback *cb) +devlink_nl_sb_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_sb *devlink_sb; @@ -2112,8 +2134,7 @@ devlink_nl_cmd_sb_get_dump_one(struct sk_buff *msg, struct devlink *devlink, err = devlink_nl_sb_fill(msg, devlink, devlink_sb, DEVLINK_CMD_SB_NEW, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); + cb->nlh->nlmsg_seq, flags); if (err) { state->idx = idx; break; @@ -2124,9 +2145,10 @@ devlink_nl_cmd_sb_get_dump_one(struct sk_buff *msg, struct devlink *devlink, return err; } -const struct devlink_cmd devl_cmd_sb_get = { - .dump_one = devlink_nl_cmd_sb_get_dump_one, -}; +int devlink_nl_sb_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + return devlink_nl_dumpit(skb, cb, devlink_nl_sb_get_dump_one); +} static int devlink_nl_sb_pool_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_sb *devlink_sb, @@ -2171,8 +2193,7 @@ nla_put_failure: return -EMSGSIZE; } -static int devlink_nl_cmd_sb_pool_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_sb *devlink_sb; @@ -2210,7 +2231,7 @@ static int devlink_nl_cmd_sb_pool_get_doit(struct sk_buff *skb, static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, struct devlink *devlink, struct devlink_sb *devlink_sb, - u32 portid, u32 seq) + u32 portid, u32 seq, int flags) { u16 pool_count = devlink_sb_pool_count(devlink_sb); u16 pool_index; @@ -2225,7 +2246,7 @@ static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, devlink_sb, pool_index, DEVLINK_CMD_SB_POOL_NEW, - portid, seq, NLM_F_MULTI); + portid, seq, flags); if (err) return err; (*p_idx)++; @@ -2234,9 +2255,8 @@ static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, } static int -devlink_nl_cmd_sb_pool_get_dump_one(struct sk_buff *msg, - struct devlink *devlink, - struct netlink_callback *cb) +devlink_nl_sb_pool_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_sb *devlink_sb; @@ -2250,7 +2270,7 @@ devlink_nl_cmd_sb_pool_get_dump_one(struct sk_buff *msg, err = __sb_pool_get_dumpit(msg, state->idx, &idx, devlink, devlink_sb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq); + cb->nlh->nlmsg_seq, flags); if (err == -EOPNOTSUPP) { err = 0; } else if (err) { @@ -2262,9 +2282,11 @@ devlink_nl_cmd_sb_pool_get_dump_one(struct sk_buff *msg, return err; } -const struct devlink_cmd devl_cmd_sb_pool_get = { - .dump_one = devlink_nl_cmd_sb_pool_get_dump_one, -}; +int devlink_nl_sb_pool_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return devlink_nl_dumpit(skb, cb, devlink_nl_sb_pool_get_dump_one); +} static int devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index, u16 pool_index, u32 size, @@ -2371,8 +2393,8 @@ sb_occ_get_failure: return err; } -static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = devlink_port->devlink; @@ -2412,7 +2434,7 @@ static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb, static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, struct devlink *devlink, struct devlink_sb *devlink_sb, - u32 portid, u32 seq) + u32 portid, u32 seq, int flags) { struct devlink_port *devlink_port; u16 pool_count = devlink_sb_pool_count(devlink_sb); @@ -2431,8 +2453,7 @@ static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, devlink_sb, pool_index, DEVLINK_CMD_SB_PORT_POOL_NEW, - portid, seq, - NLM_F_MULTI); + portid, seq, flags); if (err) return err; (*p_idx)++; @@ -2442,9 +2463,9 @@ static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, } static int -devlink_nl_cmd_sb_port_pool_get_dump_one(struct sk_buff *msg, - struct devlink *devlink, - struct netlink_callback *cb) +devlink_nl_sb_port_pool_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_sb *devlink_sb; @@ -2458,7 +2479,7 @@ devlink_nl_cmd_sb_port_pool_get_dump_one(struct sk_buff *msg, err = __sb_port_pool_get_dumpit(msg, state->idx, &idx, devlink, devlink_sb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq); + cb->nlh->nlmsg_seq, flags); if (err == -EOPNOTSUPP) { err = 0; } else if (err) { @@ -2470,9 +2491,11 @@ devlink_nl_cmd_sb_port_pool_get_dump_one(struct sk_buff *msg, return err; } -const struct devlink_cmd devl_cmd_sb_port_pool_get = { - .dump_one = devlink_nl_cmd_sb_port_pool_get_dump_one, -}; +int devlink_nl_sb_port_pool_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return devlink_nl_dumpit(skb, cb, devlink_nl_sb_port_pool_get_dump_one); +} static int devlink_sb_port_pool_set(struct devlink_port *devlink_port, unsigned int sb_index, u16 pool_index, @@ -2580,8 +2603,8 @@ nla_put_failure: return -EMSGSIZE; } -static int devlink_nl_cmd_sb_tc_pool_bind_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = devlink_port->devlink; @@ -2628,7 +2651,7 @@ static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, int start, int *p_idx, struct devlink *devlink, struct devlink_sb *devlink_sb, - u32 portid, u32 seq) + u32 portid, u32 seq, int flags) { struct devlink_port *devlink_port; unsigned long port_index; @@ -2649,7 +2672,7 @@ static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, DEVLINK_SB_POOL_TYPE_INGRESS, DEVLINK_CMD_SB_TC_POOL_BIND_NEW, portid, seq, - NLM_F_MULTI); + flags); if (err) return err; (*p_idx)++; @@ -2667,7 +2690,7 @@ static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, DEVLINK_SB_POOL_TYPE_EGRESS, DEVLINK_CMD_SB_TC_POOL_BIND_NEW, portid, seq, - NLM_F_MULTI); + flags); if (err) return err; (*p_idx)++; @@ -2676,10 +2699,10 @@ static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, return 0; } -static int -devlink_nl_cmd_sb_tc_pool_bind_get_dump_one(struct sk_buff *msg, - struct devlink *devlink, - struct netlink_callback *cb) +static int devlink_nl_sb_tc_pool_bind_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb, + int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_sb *devlink_sb; @@ -2693,7 +2716,7 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dump_one(struct sk_buff *msg, err = __sb_tc_pool_bind_get_dumpit(msg, state->idx, &idx, devlink, devlink_sb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq); + cb->nlh->nlmsg_seq, flags); if (err == -EOPNOTSUPP) { err = 0; } else if (err) { @@ -2705,9 +2728,12 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dump_one(struct sk_buff *msg, return err; } -const struct devlink_cmd devl_cmd_sb_tc_pool_bind_get = { - .dump_one = devlink_nl_cmd_sb_tc_pool_bind_get_dump_one, -}; +int devlink_nl_sb_tc_pool_bind_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return devlink_nl_dumpit(skb, cb, + devlink_nl_sb_tc_pool_bind_get_dump_one); +} static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port, unsigned int sb_index, u16 tc_index, @@ -4155,9 +4181,10 @@ static void devlink_param_notify(struct devlink *devlink, msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } -static int -devlink_nl_cmd_param_get_dump_one(struct sk_buff *msg, struct devlink *devlink, - struct netlink_callback *cb) +static int devlink_nl_param_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb, + int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_param_item *param_item; @@ -4168,8 +4195,7 @@ devlink_nl_cmd_param_get_dump_one(struct sk_buff *msg, struct devlink *devlink, err = devlink_nl_param_fill(msg, devlink, 0, param_item, DEVLINK_CMD_PARAM_GET, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); + cb->nlh->nlmsg_seq, flags); if (err == -EOPNOTSUPP) { err = 0; } else if (err) { @@ -4181,9 +4207,11 @@ devlink_nl_cmd_param_get_dump_one(struct sk_buff *msg, struct devlink *devlink, return err; } -const struct devlink_cmd devl_cmd_param_get = { - .dump_one = devlink_nl_cmd_param_get_dump_one, -}; +int devlink_nl_param_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return devlink_nl_dumpit(skb, cb, devlink_nl_param_get_dump_one); +} static int devlink_param_type_get_from_info(struct genl_info *info, @@ -4272,8 +4300,8 @@ devlink_param_get_from_info(struct xarray *params, struct genl_info *info) return devlink_param_find_by_name(params, param_name); } -static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_param_get_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_param_item *param_item; @@ -4770,8 +4798,7 @@ static void devlink_region_snapshot_del(struct devlink_region *region, kfree(snapshot); } -static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_port *port = NULL; @@ -4819,8 +4846,7 @@ static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb, static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg, struct netlink_callback *cb, struct devlink_port *port, - int *idx, - int start) + int *idx, int start, int flags) { struct devlink_region *region; int err = 0; @@ -4834,7 +4860,7 @@ static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg, DEVLINK_CMD_REGION_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - NLM_F_MULTI, region); + flags, region); if (err) goto out; (*idx)++; @@ -4844,9 +4870,10 @@ out: return err; } -static int -devlink_nl_cmd_region_get_dump_one(struct sk_buff *msg, struct devlink *devlink, - struct netlink_callback *cb) +static int devlink_nl_region_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb, + int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_region *region; @@ -4863,8 +4890,8 @@ devlink_nl_cmd_region_get_dump_one(struct sk_buff *msg, struct devlink *devlink, err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, region); + cb->nlh->nlmsg_seq, flags, + region); if (err) { state->idx = idx; return err; @@ -4874,7 +4901,7 @@ devlink_nl_cmd_region_get_dump_one(struct sk_buff *msg, struct devlink *devlink, xa_for_each(&devlink->ports, port_index, port) { err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, &idx, - state->idx); + state->idx, flags); if (err) { state->idx = idx; return err; @@ -4884,9 +4911,11 @@ devlink_nl_cmd_region_get_dump_one(struct sk_buff *msg, struct devlink *devlink, return 0; } -const struct devlink_cmd devl_cmd_region_get = { - .dump_one = devlink_nl_cmd_region_get_dump_one, -}; +int devlink_nl_region_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return devlink_nl_dumpit(skb, cb, devlink_nl_region_get_dump_one); +} static int devlink_nl_cmd_region_del(struct sk_buff *skb, struct genl_info *info) @@ -5172,7 +5201,7 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct nlattr *chunks_attr, *region_attr, *snapshot_attr; u64 ret_offset, start_offset, end_offset = U64_MAX; - struct nlattr **attrs = info->attrs; + struct nlattr **attrs = info->info.attrs; struct devlink_port *port = NULL; devlink_chunk_fill_t *region_cb; struct devlink_region *region; @@ -5195,8 +5224,8 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, goto out_unlock; } - if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { - index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + if (attrs[DEVLINK_ATTR_PORT_INDEX]) { + index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) { @@ -5632,8 +5661,7 @@ nla_put_failure: return -EMSGSIZE; } -static int devlink_nl_cmd_trap_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_trap_get_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; @@ -5667,9 +5695,9 @@ err_trap_fill: return err; } -static int -devlink_nl_cmd_trap_get_dump_one(struct sk_buff *msg, struct devlink *devlink, - struct netlink_callback *cb) +static int devlink_nl_trap_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_trap_item *trap_item; @@ -5684,8 +5712,7 @@ devlink_nl_cmd_trap_get_dump_one(struct sk_buff *msg, struct devlink *devlink, err = devlink_nl_trap_fill(msg, devlink, trap_item, DEVLINK_CMD_TRAP_NEW, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); + cb->nlh->nlmsg_seq, flags); if (err) { state->idx = idx; break; @@ -5696,9 +5723,10 @@ devlink_nl_cmd_trap_get_dump_one(struct sk_buff *msg, struct devlink *devlink, return err; } -const struct devlink_cmd devl_cmd_trap_get = { - .dump_one = devlink_nl_cmd_trap_get_dump_one, -}; +int devlink_nl_trap_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + return devlink_nl_dumpit(skb, cb, devlink_nl_trap_get_dump_one); +} static int __devlink_trap_action_set(struct devlink *devlink, struct devlink_trap_item *trap_item, @@ -5843,8 +5871,7 @@ nla_put_failure: return -EMSGSIZE; } -static int devlink_nl_cmd_trap_group_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_trap_group_get_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; @@ -5878,10 +5905,10 @@ err_trap_group_fill: return err; } -static int -devlink_nl_cmd_trap_group_get_dump_one(struct sk_buff *msg, - struct devlink *devlink, - struct netlink_callback *cb) +static int devlink_nl_trap_group_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb, + int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_trap_group_item *group_item; @@ -5897,8 +5924,7 @@ devlink_nl_cmd_trap_group_get_dump_one(struct sk_buff *msg, err = devlink_nl_trap_group_fill(msg, devlink, group_item, DEVLINK_CMD_TRAP_GROUP_NEW, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); + cb->nlh->nlmsg_seq, flags); if (err) { state->idx = idx; break; @@ -5909,9 +5935,11 @@ devlink_nl_cmd_trap_group_get_dump_one(struct sk_buff *msg, return err; } -const struct devlink_cmd devl_cmd_trap_group_get = { - .dump_one = devlink_nl_cmd_trap_group_get_dump_one, -}; +int devlink_nl_trap_group_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return devlink_nl_dumpit(skb, cb, devlink_nl_trap_group_get_dump_one); +} static int __devlink_trap_group_action_set(struct devlink *devlink, @@ -6137,8 +6165,8 @@ nla_put_failure: return -EMSGSIZE; } -static int devlink_nl_cmd_trap_policer_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_trap_policer_get_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink_trap_policer_item *policer_item; struct netlink_ext_ack *extack = info->extack; @@ -6172,10 +6200,10 @@ err_trap_policer_fill: return err; } -static int -devlink_nl_cmd_trap_policer_get_dump_one(struct sk_buff *msg, - struct devlink *devlink, - struct netlink_callback *cb) +static int devlink_nl_trap_policer_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb, + int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_trap_policer_item *policer_item; @@ -6190,8 +6218,7 @@ devlink_nl_cmd_trap_policer_get_dump_one(struct sk_buff *msg, err = devlink_nl_trap_policer_fill(msg, devlink, policer_item, DEVLINK_CMD_TRAP_POLICER_NEW, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); + cb->nlh->nlmsg_seq, flags); if (err) { state->idx = idx; break; @@ -6202,9 +6229,11 @@ devlink_nl_cmd_trap_policer_get_dump_one(struct sk_buff *msg, return err; } -const struct devlink_cmd devl_cmd_trap_policer_get = { - .dump_one = devlink_nl_cmd_trap_policer_get_dump_one, -}; +int devlink_nl_trap_policer_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return devlink_nl_dumpit(skb, cb, devlink_nl_trap_policer_get_dump_one); +} static int devlink_trap_policer_set(struct devlink *devlink, @@ -6278,15 +6307,7 @@ static int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb, return devlink_trap_policer_set(devlink, policer_item, info); } -const struct genl_small_ops devlink_nl_small_ops[54] = { - { - .cmd = DEVLINK_CMD_PORT_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_get_doit, - .dumpit = devlink_nl_instance_iter_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - /* can be retrieved by unprivileged users */ - }, +const struct genl_small_ops devlink_nl_small_ops[40] = { { .cmd = DEVLINK_CMD_PORT_SET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -6295,17 +6316,9 @@ const struct genl_small_ops devlink_nl_small_ops[54] = { .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, }, { - .cmd = DEVLINK_CMD_RATE_GET, - .doit = devlink_nl_cmd_rate_get_doit, - .dumpit = devlink_nl_instance_iter_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_RATE, - /* can be retrieved by unprivileged users */ - }, - { .cmd = DEVLINK_CMD_RATE_SET, .doit = devlink_nl_cmd_rate_set_doit, .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_RATE, }, { .cmd = DEVLINK_CMD_RATE_NEW, @@ -6316,7 +6329,6 @@ const struct genl_small_ops devlink_nl_small_ops[54] = { .cmd = DEVLINK_CMD_RATE_DEL, .doit = devlink_nl_cmd_rate_del_doit, .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_RATE_NODE, }, { .cmd = DEVLINK_CMD_PORT_SPLIT, @@ -6343,32 +6355,11 @@ const struct genl_small_ops devlink_nl_small_ops[54] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, }, - { - .cmd = DEVLINK_CMD_LINECARD_GET, - .doit = devlink_nl_cmd_linecard_get_doit, - .dumpit = devlink_nl_instance_iter_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_LINECARD, - /* can be retrieved by unprivileged users */ - }, + { .cmd = DEVLINK_CMD_LINECARD_SET, .doit = devlink_nl_cmd_linecard_set_doit, .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_LINECARD, - }, - { - .cmd = DEVLINK_CMD_SB_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_get_doit, - .dumpit = devlink_nl_instance_iter_dumpit, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_SB_POOL_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_pool_get_doit, - .dumpit = devlink_nl_instance_iter_dumpit, - /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_SB_POOL_SET, @@ -6377,14 +6368,6 @@ const struct genl_small_ops devlink_nl_small_ops[54] = { .flags = GENL_ADMIN_PERM, }, { - .cmd = DEVLINK_CMD_SB_PORT_POOL_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_port_pool_get_doit, - .dumpit = devlink_nl_instance_iter_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - /* can be retrieved by unprivileged users */ - }, - { .cmd = DEVLINK_CMD_SB_PORT_POOL_SET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_sb_port_pool_set_doit, @@ -6392,14 +6375,6 @@ const struct genl_small_ops devlink_nl_small_ops[54] = { .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, }, { - .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_tc_pool_bind_get_doit, - .dumpit = devlink_nl_instance_iter_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - /* can be retrieved by unprivileged users */ - }, - { .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_sb_tc_pool_bind_set_doit, @@ -6473,13 +6448,6 @@ const struct genl_small_ops devlink_nl_small_ops[54] = { .flags = GENL_ADMIN_PERM, }, { - .cmd = DEVLINK_CMD_PARAM_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_param_get_doit, - .dumpit = devlink_nl_instance_iter_dumpit, - /* can be retrieved by unprivileged users */ - }, - { .cmd = DEVLINK_CMD_PARAM_SET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_param_set_doit, @@ -6501,13 +6469,6 @@ const struct genl_small_ops devlink_nl_small_ops[54] = { .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, }, { - .cmd = DEVLINK_CMD_REGION_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_region_get_doit, - .dumpit = devlink_nl_instance_iter_dumpit, - .flags = GENL_ADMIN_PERM, - }, - { .cmd = DEVLINK_CMD_REGION_NEW, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_region_new, @@ -6527,14 +6488,6 @@ const struct genl_small_ops devlink_nl_small_ops[54] = { .flags = GENL_ADMIN_PERM, }, { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_get_doit, - .dumpit = devlink_nl_instance_iter_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - /* can be retrieved by unprivileged users */ - }, - { .cmd = DEVLINK_CMD_HEALTH_REPORTER_SET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_health_reporter_set_doit, @@ -6583,45 +6536,21 @@ const struct genl_small_ops devlink_nl_small_ops[54] = { .flags = GENL_ADMIN_PERM, }, { - .cmd = DEVLINK_CMD_TRAP_GET, - .doit = devlink_nl_cmd_trap_get_doit, - .dumpit = devlink_nl_instance_iter_dumpit, - /* can be retrieved by unprivileged users */ - }, - { .cmd = DEVLINK_CMD_TRAP_SET, .doit = devlink_nl_cmd_trap_set_doit, .flags = GENL_ADMIN_PERM, }, { - .cmd = DEVLINK_CMD_TRAP_GROUP_GET, - .doit = devlink_nl_cmd_trap_group_get_doit, - .dumpit = devlink_nl_instance_iter_dumpit, - /* can be retrieved by unprivileged users */ - }, - { .cmd = DEVLINK_CMD_TRAP_GROUP_SET, .doit = devlink_nl_cmd_trap_group_set_doit, .flags = GENL_ADMIN_PERM, }, { - .cmd = DEVLINK_CMD_TRAP_POLICER_GET, - .doit = devlink_nl_cmd_trap_policer_get_doit, - .dumpit = devlink_nl_instance_iter_dumpit, - /* can be retrieved by unprivileged users */ - }, - { .cmd = DEVLINK_CMD_TRAP_POLICER_SET, .doit = devlink_nl_cmd_trap_policer_set_doit, .flags = GENL_ADMIN_PERM, }, { - .cmd = DEVLINK_CMD_SELFTESTS_GET, - .doit = devlink_nl_cmd_selftests_get_doit, - .dumpit = devlink_nl_instance_iter_dumpit, - /* can be retrieved by unprivileged users */ - }, - { .cmd = DEVLINK_CMD_SELFTESTS_RUN, .doit = devlink_nl_cmd_selftests_run, .flags = GENL_ADMIN_PERM, diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c index bada2819827b..72a5005a64cd 100644 --- a/net/devlink/netlink.c +++ b/net/devlink/netlink.c @@ -109,10 +109,9 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs) return ERR_PTR(-ENODEV); } -int devlink_nl_pre_doit(const struct genl_split_ops *ops, - struct sk_buff *skb, struct genl_info *info) +static int __devlink_nl_pre_doit(struct sk_buff *skb, struct genl_info *info, + u8 flags) { - struct devlink_linecard *linecard; struct devlink_port *devlink_port; struct devlink *devlink; int err; @@ -122,42 +121,17 @@ int devlink_nl_pre_doit(const struct genl_split_ops *ops, return PTR_ERR(devlink); info->user_ptr[0] = devlink; - if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) { + if (flags & DEVLINK_NL_FLAG_NEED_PORT) { devlink_port = devlink_port_get_from_info(devlink, info); if (IS_ERR(devlink_port)) { err = PTR_ERR(devlink_port); goto unlock; } info->user_ptr[1] = devlink_port; - } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT) { + } else if (flags & DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT) { devlink_port = devlink_port_get_from_info(devlink, info); if (!IS_ERR(devlink_port)) info->user_ptr[1] = devlink_port; - } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE) { - struct devlink_rate *devlink_rate; - - devlink_rate = devlink_rate_get_from_info(devlink, info); - if (IS_ERR(devlink_rate)) { - err = PTR_ERR(devlink_rate); - goto unlock; - } - info->user_ptr[1] = devlink_rate; - } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE_NODE) { - struct devlink_rate *rate_node; - - rate_node = devlink_rate_node_get_from_info(devlink, info); - if (IS_ERR(rate_node)) { - err = PTR_ERR(rate_node); - goto unlock; - } - info->user_ptr[1] = rate_node; - } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_LINECARD) { - linecard = devlink_linecard_get_from_info(devlink, info); - if (IS_ERR(linecard)) { - err = PTR_ERR(linecard); - goto unlock; - } - info->user_ptr[1] = linecard; } return 0; @@ -167,6 +141,25 @@ unlock: return err; } +int devlink_nl_pre_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + return __devlink_nl_pre_doit(skb, info, ops->internal_flags); +} + +int devlink_nl_pre_doit_port(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_PORT); +} + +int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops, + struct sk_buff *skb, + struct genl_info *info) +{ + return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT); +} + void devlink_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { @@ -177,25 +170,30 @@ void devlink_nl_post_doit(const struct genl_split_ops *ops, devlink_put(devlink); } -static const struct devlink_cmd *devl_cmds[] = { - [DEVLINK_CMD_PORT_GET] = &devl_cmd_port_get, - [DEVLINK_CMD_SB_GET] = &devl_cmd_sb_get, - [DEVLINK_CMD_SB_POOL_GET] = &devl_cmd_sb_pool_get, - [DEVLINK_CMD_SB_PORT_POOL_GET] = &devl_cmd_sb_port_pool_get, - [DEVLINK_CMD_SB_TC_POOL_BIND_GET] = &devl_cmd_sb_tc_pool_bind_get, - [DEVLINK_CMD_PARAM_GET] = &devl_cmd_param_get, - [DEVLINK_CMD_REGION_GET] = &devl_cmd_region_get, - [DEVLINK_CMD_HEALTH_REPORTER_GET] = &devl_cmd_health_reporter_get, - [DEVLINK_CMD_TRAP_GET] = &devl_cmd_trap_get, - [DEVLINK_CMD_TRAP_GROUP_GET] = &devl_cmd_trap_group_get, - [DEVLINK_CMD_TRAP_POLICER_GET] = &devl_cmd_trap_policer_get, - [DEVLINK_CMD_RATE_GET] = &devl_cmd_rate_get, - [DEVLINK_CMD_LINECARD_GET] = &devl_cmd_linecard_get, - [DEVLINK_CMD_SELFTESTS_GET] = &devl_cmd_selftests_get, -}; +static int devlink_nl_inst_single_dumpit(struct sk_buff *msg, + struct netlink_callback *cb, int flags, + devlink_nl_dump_one_func_t *dump_one, + struct nlattr **attrs) +{ + struct devlink *devlink; + int err; -int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb, - devlink_nl_dump_one_func_t *dump_one) + devlink = devlink_get_from_attrs_lock(sock_net(msg->sk), attrs); + if (IS_ERR(devlink)) + return PTR_ERR(devlink); + err = dump_one(msg, devlink, cb, flags | NLM_F_DUMP_FILTERED); + + devl_unlock(devlink); + devlink_put(devlink); + + if (err != -EMSGSIZE) + return err; + return msg->len; +} + +static int devlink_nl_inst_iter_dumpit(struct sk_buff *msg, + struct netlink_callback *cb, int flags, + devlink_nl_dump_one_func_t *dump_one) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink *devlink; @@ -206,7 +204,7 @@ int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb, devl_lock(devlink); if (devl_is_registered(devlink)) - err = dump_one(msg, devlink, cb); + err = dump_one(msg, devlink, cb, flags); else err = 0; @@ -227,13 +225,19 @@ int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb, return msg->len; } -int devlink_nl_instance_iter_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb, + devlink_nl_dump_one_func_t *dump_one) { - const struct genl_dumpit_info *info = genl_dumpit_info(cb); - const struct devlink_cmd *cmd = devl_cmds[info->op.cmd]; + const struct genl_info *info = genl_info_dump(cb); + struct nlattr **attrs = info->attrs; + int flags = NLM_F_MULTI; - return devlink_nl_dumpit(msg, cb, cmd->dump_one); + if (attrs && + (attrs[DEVLINK_ATTR_BUS_NAME] || attrs[DEVLINK_ATTR_DEV_NAME])) + return devlink_nl_inst_single_dumpit(msg, cb, flags, dump_one, + attrs); + else + return devlink_nl_inst_iter_dumpit(msg, cb, flags, dump_one); } struct genl_family devlink_nl_family __ro_after_init = { diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c index 32d8cbed0c30..467b7a431de1 100644 --- a/net/devlink/netlink_gen.c +++ b/net/devlink/netlink_gen.c @@ -16,14 +16,199 @@ static const struct nla_policy devlink_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_PORT_GET - do */ +static const struct nla_policy devlink_port_get_do_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_PORT_GET - dump */ +static const struct nla_policy devlink_port_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_SB_GET - do */ +static const struct nla_policy devlink_sb_get_do_nl_policy[DEVLINK_ATTR_SB_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_SB_GET - dump */ +static const struct nla_policy devlink_sb_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_SB_POOL_GET - do */ +static const struct nla_policy devlink_sb_pool_get_do_nl_policy[DEVLINK_ATTR_SB_POOL_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16, }, +}; + +/* DEVLINK_CMD_SB_POOL_GET - dump */ +static const struct nla_policy devlink_sb_pool_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_SB_PORT_POOL_GET - do */ +static const struct nla_policy devlink_sb_port_pool_get_do_nl_policy[DEVLINK_ATTR_SB_POOL_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16, }, +}; + +/* DEVLINK_CMD_SB_PORT_POOL_GET - dump */ +static const struct nla_policy devlink_sb_port_pool_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */ +static const struct nla_policy devlink_sb_tc_pool_bind_get_do_nl_policy[DEVLINK_ATTR_SB_TC_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_SB_POOL_TYPE] = NLA_POLICY_MAX(NLA_U8, 1), + [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16, }, +}; + +/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - dump */ +static const struct nla_policy devlink_sb_tc_pool_bind_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_PARAM_GET - do */ +static const struct nla_policy devlink_param_get_do_nl_policy[DEVLINK_ATTR_PARAM_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_PARAM_GET - dump */ +static const struct nla_policy devlink_param_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_REGION_GET - do */ +static const struct nla_policy devlink_region_get_do_nl_policy[DEVLINK_ATTR_REGION_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_REGION_GET - dump */ +static const struct nla_policy devlink_region_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + /* DEVLINK_CMD_INFO_GET - do */ static const struct nla_policy devlink_info_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_HEALTH_REPORTER_GET - do */ +static const struct nla_policy devlink_health_reporter_get_do_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_HEALTH_REPORTER_GET - dump */ +static const struct nla_policy devlink_health_reporter_get_dump_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_TRAP_GET - do */ +static const struct nla_policy devlink_trap_get_do_nl_policy[DEVLINK_ATTR_TRAP_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_TRAP_GET - dump */ +static const struct nla_policy devlink_trap_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_TRAP_GROUP_GET - do */ +static const struct nla_policy devlink_trap_group_get_do_nl_policy[DEVLINK_ATTR_TRAP_GROUP_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_TRAP_GROUP_GET - dump */ +static const struct nla_policy devlink_trap_group_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_TRAP_POLICER_GET - do */ +static const struct nla_policy devlink_trap_policer_get_do_nl_policy[DEVLINK_ATTR_TRAP_POLICER_ID + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_TRAP_POLICER_GET - dump */ +static const struct nla_policy devlink_trap_policer_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_RATE_GET - do */ +static const struct nla_policy devlink_rate_get_do_nl_policy[DEVLINK_ATTR_RATE_NODE_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_RATE_GET - dump */ +static const struct nla_policy devlink_rate_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_LINECARD_GET - do */ +static const struct nla_policy devlink_linecard_get_do_nl_policy[DEVLINK_ATTR_LINECARD_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_LINECARD_GET - dump */ +static const struct nla_policy devlink_linecard_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_SELFTESTS_GET - do */ +static const struct nla_policy devlink_selftests_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + /* Ops table for devlink */ -const struct genl_split_ops devlink_nl_ops[4] = { +const struct genl_split_ops devlink_nl_ops[32] = { { .cmd = DEVLINK_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT, @@ -41,6 +226,125 @@ const struct genl_split_ops devlink_nl_ops[4] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_PORT_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_port_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_port_get_do_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_INDEX, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_PORT_GET, + .dumpit = devlink_nl_port_get_dumpit, + .policy = devlink_port_get_dump_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_SB_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_sb_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_sb_get_do_nl_policy, + .maxattr = DEVLINK_ATTR_SB_INDEX, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_SB_GET, + .dumpit = devlink_nl_sb_get_dumpit, + .policy = devlink_sb_get_dump_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_SB_POOL_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_sb_pool_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_sb_pool_get_do_nl_policy, + .maxattr = DEVLINK_ATTR_SB_POOL_INDEX, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_SB_POOL_GET, + .dumpit = devlink_nl_sb_pool_get_dumpit, + .policy = devlink_sb_pool_get_dump_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_SB_PORT_POOL_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_sb_port_pool_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_sb_port_pool_get_do_nl_policy, + .maxattr = DEVLINK_ATTR_SB_POOL_INDEX, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_SB_PORT_POOL_GET, + .dumpit = devlink_nl_sb_port_pool_get_dumpit, + .policy = devlink_sb_port_pool_get_dump_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_sb_tc_pool_bind_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_sb_tc_pool_bind_get_do_nl_policy, + .maxattr = DEVLINK_ATTR_SB_TC_INDEX, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET, + .dumpit = devlink_nl_sb_tc_pool_bind_get_dumpit, + .policy = devlink_sb_tc_pool_bind_get_dump_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_PARAM_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_param_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_param_get_do_nl_policy, + .maxattr = DEVLINK_ATTR_PARAM_NAME, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_PARAM_GET, + .dumpit = devlink_nl_param_get_dumpit, + .policy = devlink_param_get_dump_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_REGION_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_region_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_region_get_do_nl_policy, + .maxattr = DEVLINK_ATTR_REGION_NAME, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_REGION_GET, + .dumpit = devlink_nl_region_get_dumpit, + .policy = devlink_region_get_dump_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DUMP, + }, + { .cmd = DEVLINK_CMD_INFO_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -56,4 +360,122 @@ const struct genl_split_ops devlink_nl_ops[4] = { .dumpit = devlink_nl_info_get_dumpit, .flags = GENL_CMD_CAP_DUMP, }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_health_reporter_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_health_reporter_get_do_nl_policy, + .maxattr = DEVLINK_ATTR_HEALTH_REPORTER_NAME, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_GET, + .dumpit = devlink_nl_health_reporter_get_dumpit, + .policy = devlink_health_reporter_get_dump_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_INDEX, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_TRAP_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_trap_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_trap_get_do_nl_policy, + .maxattr = DEVLINK_ATTR_TRAP_NAME, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_TRAP_GET, + .dumpit = devlink_nl_trap_get_dumpit, + .policy = devlink_trap_get_dump_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_TRAP_GROUP_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_trap_group_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_trap_group_get_do_nl_policy, + .maxattr = DEVLINK_ATTR_TRAP_GROUP_NAME, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_TRAP_GROUP_GET, + .dumpit = devlink_nl_trap_group_get_dumpit, + .policy = devlink_trap_group_get_dump_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_TRAP_POLICER_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_trap_policer_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_trap_policer_get_do_nl_policy, + .maxattr = DEVLINK_ATTR_TRAP_POLICER_ID, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_TRAP_POLICER_GET, + .dumpit = devlink_nl_trap_policer_get_dumpit, + .policy = devlink_trap_policer_get_dump_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_RATE_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_rate_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_rate_get_do_nl_policy, + .maxattr = DEVLINK_ATTR_RATE_NODE_NAME, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_RATE_GET, + .dumpit = devlink_nl_rate_get_dumpit, + .policy = devlink_rate_get_dump_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_LINECARD_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_linecard_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_linecard_get_do_nl_policy, + .maxattr = DEVLINK_ATTR_LINECARD_INDEX, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_LINECARD_GET, + .dumpit = devlink_nl_linecard_get_dumpit, + .policy = devlink_linecard_get_dump_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_SELFTESTS_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_selftests_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_selftests_get_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_SELFTESTS_GET, + .validate = GENL_DONT_VALIDATE_DUMP, + .dumpit = devlink_nl_selftests_get_dumpit, + .flags = GENL_CMD_CAP_DUMP, + }, }; diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h index 11980e04a718..f8bbc93e39be 100644 --- a/net/devlink/netlink_gen.h +++ b/net/devlink/netlink_gen.h @@ -12,18 +12,68 @@ #include <uapi/linux/devlink.h> /* Ops table for devlink */ -extern const struct genl_split_ops devlink_nl_ops[4]; +extern const struct genl_split_ops devlink_nl_ops[32]; int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); +int devlink_nl_pre_doit_port(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info); +int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops, + struct sk_buff *skb, + struct genl_info *info); void devlink_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_port_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_sb_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_sb_pool_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_sb_port_pool_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_sb_tc_pool_bind_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_param_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_param_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_region_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_info_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_health_reporter_get_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_health_reporter_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_trap_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_trap_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_trap_group_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_trap_group_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_trap_policer_get_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_trap_policer_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_rate_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_linecard_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_selftests_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); #endif /* _LINUX_DEVLINK_GEN_H */ diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c index 61c40e889a4d..7b4bbd674bae 100644 --- a/net/ethtool/channels.c +++ b/net/ethtool/channels.c @@ -24,7 +24,7 @@ const struct nla_policy ethnl_channels_get_policy[] = { static int channels_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct channels_reply_data *data = CHANNELS_REPDATA(reply_base); struct net_device *dev = reply_base->dev; diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c index 01a59ce211c8..83112c1a71ae 100644 --- a/net/ethtool/coalesce.c +++ b/net/ethtool/coalesce.c @@ -59,10 +59,9 @@ const struct nla_policy ethnl_coalesce_get_policy[] = { static int coalesce_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); - struct netlink_ext_ack *extack = info ? info->extack : NULL; struct net_device *dev = reply_base->dev; int ret; @@ -73,7 +72,8 @@ static int coalesce_prepare_data(const struct ethnl_req_info *req_base, if (ret < 0) return ret; ret = dev->ethtool_ops->get_coalesce(dev, &data->coalesce, - &data->kernel_coalesce, extack); + &data->kernel_coalesce, + info->extack); ethnl_ops_complete(dev); return ret; diff --git a/net/ethtool/debug.c b/net/ethtool/debug.c index e4369769817e..0b2dea56d461 100644 --- a/net/ethtool/debug.c +++ b/net/ethtool/debug.c @@ -23,7 +23,7 @@ const struct nla_policy ethnl_debug_get_policy[] = { static int debug_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct debug_reply_data *data = DEBUG_REPDATA(reply_base); struct net_device *dev = reply_base->dev; diff --git a/net/ethtool/eee.c b/net/ethtool/eee.c index 42104bcb0e47..2853394d06a8 100644 --- a/net/ethtool/eee.c +++ b/net/ethtool/eee.c @@ -26,7 +26,7 @@ const struct nla_policy ethnl_eee_get_policy[] = { static int eee_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct eee_reply_data *data = EEE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; diff --git a/net/ethtool/eeprom.c b/net/ethtool/eeprom.c index 49c0a2a77f02..6209c3a9c8f7 100644 --- a/net/ethtool/eeprom.c +++ b/net/ethtool/eeprom.c @@ -51,8 +51,7 @@ static int fallback_set_params(struct eeprom_req_info *request, } static int eeprom_fallback(struct eeprom_req_info *request, - struct eeprom_reply_data *reply, - struct genl_info *info) + struct eeprom_reply_data *reply) { struct net_device *dev = reply->base.dev; struct ethtool_modinfo modinfo = {0}; @@ -103,7 +102,7 @@ static int get_module_eeprom_by_page(struct net_device *dev, static int eeprom_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct eeprom_reply_data *reply = MODULE_EEPROM_REPDATA(reply_base); struct eeprom_req_info *request = MODULE_EEPROM_REQINFO(req_base); @@ -124,7 +123,7 @@ static int eeprom_prepare_data(const struct ethnl_req_info *req_base, if (ret) goto err_free; - ret = get_module_eeprom_by_page(dev, &page_data, info ? info->extack : NULL); + ret = get_module_eeprom_by_page(dev, &page_data, info->extack); if (ret < 0) goto err_ops; @@ -140,7 +139,7 @@ err_free: kfree(page_data.data); if (ret == -EOPNOTSUPP) - return eeprom_fallback(request, reply, info); + return eeprom_fallback(request, reply); return ret; } diff --git a/net/ethtool/features.c b/net/ethtool/features.c index 55d449a2d3fc..a79af8c25a07 100644 --- a/net/ethtool/features.c +++ b/net/ethtool/features.c @@ -35,7 +35,7 @@ static void ethnl_features_to_bitmap32(u32 *dest, netdev_features_t src) static int features_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct features_reply_data *data = FEATURES_REPDATA(reply_base); struct net_device *dev = reply_base->dev; diff --git a/net/ethtool/fec.c b/net/ethtool/fec.c index 0d9a3d153170..e7d3f2c352a3 100644 --- a/net/ethtool/fec.c +++ b/net/ethtool/fec.c @@ -92,7 +92,7 @@ fec_stats_recalc(struct fec_stat_grp *grp, struct ethtool_fec_stat *stats) static int fec_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { __ETHTOOL_DECLARE_LINK_MODE_MASK(active_fec_modes) = {}; struct fec_reply_data *data = FEC_REPDATA(reply_base); diff --git a/net/ethtool/linkinfo.c b/net/ethtool/linkinfo.c index 310dfe63292a..5c317d23787b 100644 --- a/net/ethtool/linkinfo.c +++ b/net/ethtool/linkinfo.c @@ -23,7 +23,7 @@ const struct nla_policy ethnl_linkinfo_get_policy[] = { static int linkinfo_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct linkinfo_reply_data *data = LINKINFO_REPDATA(reply_base); struct net_device *dev = reply_base->dev; diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index 20165e07ef90..b2591db49f7d 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -27,7 +27,7 @@ const struct nla_policy ethnl_linkmodes_get_policy[] = { static int linkmodes_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct linkmodes_reply_data *data = LINKMODES_REPDATA(reply_base); struct net_device *dev = reply_base->dev; diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c index 2158c17a0b32..b2de2108b356 100644 --- a/net/ethtool/linkstate.c +++ b/net/ethtool/linkstate.c @@ -81,7 +81,7 @@ static int linkstate_get_link_ext_state(struct net_device *dev, static int linkstate_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct linkstate_reply_data *data = LINKSTATE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; diff --git a/net/ethtool/mm.c b/net/ethtool/mm.c index 4058a557b5a4..2816bb23c3ad 100644 --- a/net/ethtool/mm.c +++ b/net/ethtool/mm.c @@ -27,7 +27,7 @@ const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1] = { static int mm_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct mm_reply_data *data = MM_REPDATA(reply_base); struct net_device *dev = reply_base->dev; diff --git a/net/ethtool/module.c b/net/ethtool/module.c index e0d539b21423..ceb575efc290 100644 --- a/net/ethtool/module.c +++ b/net/ethtool/module.c @@ -38,10 +38,9 @@ static int module_get_power_mode(struct net_device *dev, static int module_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct module_reply_data *data = MODULE_REPDATA(reply_base); - struct netlink_ext_ack *extack = info ? info->extack : NULL; struct net_device *dev = reply_base->dev; int ret; @@ -49,7 +48,7 @@ static int module_prepare_data(const struct ethnl_req_info *req_base, if (ret < 0) return ret; - ret = module_get_power_mode(dev, data, extack); + ret = module_get_power_mode(dev, data, info->extack); if (ret < 0) goto out_complete; diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index ae344f1b0bbd..3bbd5afb7b31 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -316,10 +316,8 @@ static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) /** * ethnl_default_parse() - Parse request message * @req_info: pointer to structure to put data into - * @tb: parsed attributes - * @net: request netns + * @info: genl_info from the request * @request_ops: struct request_ops for request type - * @extack: netlink extack for error reporting * @require_dev: fail if no device identified in header * * Parse universal request header and call request specific ->parse_request() @@ -328,19 +326,21 @@ static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) * Return: 0 on success or negative error code */ static int ethnl_default_parse(struct ethnl_req_info *req_info, - struct nlattr **tb, struct net *net, + const struct genl_info *info, const struct ethnl_request_ops *request_ops, - struct netlink_ext_ack *extack, bool require_dev) + bool require_dev) { + struct nlattr **tb = info->attrs; int ret; ret = ethnl_parse_header_dev_get(req_info, tb[request_ops->hdr_attr], - net, extack, require_dev); + genl_info_net(info), info->extack, + require_dev); if (ret < 0) return ret; if (request_ops->parse_request) { - ret = request_ops->parse_request(req_info, tb, extack); + ret = request_ops->parse_request(req_info, tb, info->extack); if (ret < 0) return ret; } @@ -393,8 +393,7 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; } - ret = ethnl_default_parse(req_info, info->attrs, genl_info_net(info), - ops, info->extack, !ops->allow_nodev_do); + ret = ethnl_default_parse(req_info, info, ops, !ops->allow_nodev_do); if (ret < 0) goto err_dev; ethnl_init_reply_data(reply_data, ops, req_info->dev); @@ -445,12 +444,12 @@ err_dev: static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev, const struct ethnl_dump_ctx *ctx, - struct netlink_callback *cb) + const struct genl_info *info) { void *ehdr; int ret; - ehdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + ehdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, ðtool_genl_family, NLM_F_MULTI, ctx->ops->reply_cmd); if (!ehdr) @@ -458,7 +457,7 @@ static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev, ethnl_init_reply_data(ctx->reply_data, ctx->ops, dev); rtnl_lock(); - ret = ctx->ops->prepare_data(ctx->req_info, ctx->reply_data, NULL); + ret = ctx->ops->prepare_data(ctx->req_info, ctx->reply_data, info); rtnl_unlock(); if (ret < 0) goto out; @@ -496,7 +495,7 @@ static int ethnl_default_dumpit(struct sk_buff *skb, dev_hold(dev); rtnl_unlock(); - ret = ethnl_default_dump_one(skb, dev, ctx, cb); + ret = ethnl_default_dump_one(skb, dev, ctx, genl_info_dump(cb)); rtnl_lock(); dev_put(dev); @@ -538,8 +537,7 @@ static int ethnl_default_start(struct netlink_callback *cb) goto free_req_info; } - ret = ethnl_default_parse(req_info, info->attrs, sock_net(cb->skb->sk), - ops, cb->extack, false); + ret = ethnl_default_parse(req_info, &info->info, ops, false); if (req_info->dev) { /* We ignore device specification in dump requests but as the * same parser as for non-dump (doit) requests is used, it @@ -649,11 +647,14 @@ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd, struct ethnl_reply_data *reply_data; const struct ethnl_request_ops *ops; struct ethnl_req_info *req_info; + struct genl_info info; struct sk_buff *skb; void *reply_payload; int reply_len; int ret; + genl_info_init_ntf(&info, ðtool_genl_family, cmd); + if (WARN_ONCE(cmd > ETHTOOL_MSG_KERNEL_MAX || !ethnl_default_notify_ops[cmd], "unexpected notification type %u\n", cmd)) @@ -672,7 +673,7 @@ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd, req_info->flags |= ETHTOOL_FLAG_COMPACT_BITSETS; ethnl_init_reply_data(reply_data, ops, dev); - ret = ops->prepare_data(req_info, reply_data, NULL); + ret = ops->prepare_data(req_info, reply_data, &info); if (ret < 0) goto err_cleanup; ret = ops->reply_size(req_info, reply_data); diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 79424b34b553..9a333a8d04c1 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -355,7 +355,7 @@ struct ethnl_request_ops { struct netlink_ext_ack *extack); int (*prepare_data)(const struct ethnl_req_info *req_info, struct ethnl_reply_data *reply_data, - struct genl_info *info); + const struct genl_info *info); int (*reply_size)(const struct ethnl_req_info *req_info, const struct ethnl_reply_data *reply_data); int (*fill_reply)(struct sk_buff *skb, diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c index 6657d0b888d8..f7c847aeb1a2 100644 --- a/net/ethtool/pause.c +++ b/net/ethtool/pause.c @@ -51,10 +51,9 @@ static int pause_parse_request(struct ethnl_req_info *req_base, static int pause_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { const struct pause_req_info *req_info = PAUSE_REQINFO(req_base); - struct netlink_ext_ack *extack = info ? info->extack : NULL; struct pause_reply_data *data = PAUSE_REPDATA(reply_base); enum ethtool_mac_stats_src src = req_info->src; struct net_device *dev = reply_base->dev; @@ -74,7 +73,7 @@ static int pause_prepare_data(const struct ethnl_req_info *req_base, if ((src == ETHTOOL_MAC_STATS_SRC_EMAC || src == ETHTOOL_MAC_STATS_SRC_PMAC) && !__ethtool_dev_mm_supported(dev)) { - NL_SET_ERR_MSG_MOD(extack, + NL_SET_ERR_MSG_MOD(info->extack, "Device does not support MAC merge layer"); ethnl_ops_complete(dev); return -EOPNOTSUPP; diff --git a/net/ethtool/phc_vclocks.c b/net/ethtool/phc_vclocks.c index 637b2f5297d5..cadaabed60bd 100644 --- a/net/ethtool/phc_vclocks.c +++ b/net/ethtool/phc_vclocks.c @@ -24,7 +24,7 @@ const struct nla_policy ethnl_phc_vclocks_get_policy[] = { static int phc_vclocks_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base); struct net_device *dev = reply_base->dev; diff --git a/net/ethtool/plca.c b/net/ethtool/plca.c index 5a8cab4df0c9..b238a1afe9ae 100644 --- a/net/ethtool/plca.c +++ b/net/ethtool/plca.c @@ -40,7 +40,7 @@ const struct nla_policy ethnl_plca_get_cfg_policy[] = { static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct plca_reply_data *data = PLCA_REPDATA(reply_base); struct net_device *dev = reply_base->dev; @@ -183,7 +183,7 @@ const struct nla_policy ethnl_plca_get_status_policy[] = { static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct plca_reply_data *data = PLCA_REPDATA(reply_base); struct net_device *dev = reply_base->dev; diff --git a/net/ethtool/privflags.c b/net/ethtool/privflags.c index 23264a1ebf12..297be6a13ab9 100644 --- a/net/ethtool/privflags.c +++ b/net/ethtool/privflags.c @@ -57,7 +57,7 @@ static int ethnl_get_priv_flags_info(struct net_device *dev, static int privflags_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct privflags_reply_data *data = PRIVFLAGS_REPDATA(reply_base); struct net_device *dev = reply_base->dev; diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c index 530b8b99e6df..cc478af77111 100644 --- a/net/ethtool/pse-pd.c +++ b/net/ethtool/pse-pd.c @@ -53,8 +53,8 @@ static int pse_get_pse_attributes(struct net_device *dev, } static int pse_prepare_data(const struct ethnl_req_info *req_base, - struct ethnl_reply_data *reply_base, - struct genl_info *info) + struct ethnl_reply_data *reply_base, + const struct genl_info *info) { struct pse_reply_data *data = PSE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; @@ -64,7 +64,7 @@ static int pse_prepare_data(const struct ethnl_req_info *req_base, if (ret < 0) return ret; - ret = pse_get_pse_attributes(dev, info ? info->extack : NULL, data); + ret = pse_get_pse_attributes(dev, info->extack, data); ethnl_ops_complete(dev); diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c index 1c4972526142..fb09f774ea01 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -24,10 +24,9 @@ const struct nla_policy ethnl_rings_get_policy[] = { static int rings_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct rings_reply_data *data = RINGS_REPDATA(reply_base); - struct netlink_ext_ack *extack = info ? info->extack : NULL; struct net_device *dev = reply_base->dev; int ret; @@ -39,7 +38,7 @@ static int rings_prepare_data(const struct ethnl_req_info *req_base, if (ret < 0) return ret; dev->ethtool_ops->get_ringparam(dev, &data->ringparam, - &data->kernel_ringparam, extack); + &data->kernel_ringparam, info->extack); ethnl_ops_complete(dev); return 0; diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index be260ab34e58..5764202e6cb6 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -42,7 +42,8 @@ rss_parse_request(struct ethnl_req_info *req_info, struct nlattr **tb, static int rss_prepare_data(const struct ethnl_req_info *req_base, - struct ethnl_reply_data *reply_base, struct genl_info *info) + struct ethnl_reply_data *reply_base, + const struct genl_info *info) { struct rss_reply_data *data = RSS_REPDATA(reply_base); struct rss_req_info *request = RSS_REQINFO(req_base); diff --git a/net/ethtool/stats.c b/net/ethtool/stats.c index 010ed19ccc99..912f0c4fff2f 100644 --- a/net/ethtool/stats.c +++ b/net/ethtool/stats.c @@ -114,10 +114,9 @@ static int stats_parse_request(struct ethnl_req_info *req_base, static int stats_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { const struct stats_req_info *req_info = STATS_REQINFO(req_base); - struct netlink_ext_ack *extack = info ? info->extack : NULL; struct stats_reply_data *data = STATS_REPDATA(reply_base); enum ethtool_mac_stats_src src = req_info->src; struct net_device *dev = reply_base->dev; @@ -130,7 +129,7 @@ static int stats_prepare_data(const struct ethnl_req_info *req_base, if ((src == ETHTOOL_MAC_STATS_SRC_EMAC || src == ETHTOOL_MAC_STATS_SRC_PMAC) && !__ethtool_dev_mm_supported(dev)) { - NL_SET_ERR_MSG_MOD(extack, + NL_SET_ERR_MSG_MOD(info->extack, "Device does not support MAC merge layer"); ethnl_ops_complete(dev); return -EOPNOTSUPP; diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index 3f7de54d85fb..c678b484a079 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -274,7 +274,7 @@ static int strset_prepare_set(struct strset_info *info, struct net_device *dev, static int strset_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { const struct strset_req_info *req_info = STRSET_REQINFO(req_base); struct strset_reply_data *data = STRSET_REPDATA(reply_base); diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c index 63b5814bd460..9daed0aab162 100644 --- a/net/ethtool/tsinfo.c +++ b/net/ethtool/tsinfo.c @@ -25,7 +25,7 @@ const struct nla_policy ethnl_tsinfo_get_policy[] = { static int tsinfo_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct tsinfo_reply_data *data = TSINFO_REPDATA(reply_base); struct net_device *dev = reply_base->dev; diff --git a/net/ethtool/tunnels.c b/net/ethtool/tunnels.c index 05f752557b5e..b4ce47dd2aa6 100644 --- a/net/ethtool/tunnels.c +++ b/net/ethtool/tunnels.c @@ -219,7 +219,7 @@ int ethnl_tunnel_info_start(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ethnl_tunnel_info_dump_ctx *ctx = (void *)cb->ctx; - struct nlattr **tb = info->attrs; + struct nlattr **tb = info->info.attrs; int ret; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); diff --git a/net/ethtool/wol.c b/net/ethtool/wol.c index a4a43d9e6e9d..0ed56c9ac1bc 100644 --- a/net/ethtool/wol.c +++ b/net/ethtool/wol.c @@ -24,7 +24,7 @@ const struct nla_policy ethnl_wol_get_policy[] = { static int wol_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, - struct genl_info *info) + const struct genl_info *info) { struct wol_reply_data *data = WOL_REPDATA(reply_base); struct net_device *dev = reply_base->dev; @@ -39,7 +39,8 @@ static int wol_prepare_data(const struct ethnl_req_info *req_base, dev->ethtool_ops->get_wol(dev, &data->wol); ethnl_ops_complete(dev); /* do not include password in notifications */ - data->show_sopass = info && (data->wol.supported & WAKE_MAGICSECURE); + data->show_sopass = !genl_info_is_ntf(info) && + (data->wol.supported & WAKE_MAGICSECURE); return 0; } diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index d610c1886160..1a265a421308 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -262,7 +262,7 @@ nl802154_prepare_wpan_dev_dump(struct sk_buff *skb, if (!cb->args[0]) { *wpan_dev = __cfg802154_wpan_dev_from_attrs(sock_net(skb->sk), - info->attrs); + info->info.attrs); if (IS_ERR(*wpan_dev)) { err = PTR_ERR(*wpan_dev); goto out_unlock; @@ -570,7 +570,7 @@ static int nl802154_dump_wpan_phy_parse(struct sk_buff *skb, struct nl802154_dump_wpan_phy_state *state) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); - struct nlattr **tb = info->attrs; + struct nlattr **tb = info->info.attrs; if (tb[NL802154_ATTR_WPAN_PHY]) state->filter_wpan_phy = nla_get_u32(tb[NL802154_ATTR_WPAN_PHY]); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9b2ca2fcc5a1..e07ee60625d9 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -187,24 +187,13 @@ static int inet_autobind(struct sock *sk) return 0; } -/* - * Move a socket into listening state. - */ -int inet_listen(struct socket *sock, int backlog) +int __inet_listen_sk(struct sock *sk, int backlog) { - struct sock *sk = sock->sk; - unsigned char old_state; + unsigned char old_state = sk->sk_state; int err, tcp_fastopen; - lock_sock(sk); - - err = -EINVAL; - if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) - goto out; - - old_state = sk->sk_state; if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN))) - goto out; + return -EINVAL; WRITE_ONCE(sk->sk_max_ack_backlog, backlog); /* Really, if the socket is already in listen state @@ -227,10 +216,27 @@ int inet_listen(struct socket *sock, int backlog) err = inet_csk_listen_start(sk); if (err) - goto out; + return err; + tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL); } - err = 0; + return 0; +} + +/* + * Move a socket into listening state. + */ +int inet_listen(struct socket *sock, int backlog) +{ + struct sock *sk = sock->sk; + int err = -EINVAL; + + lock_sock(sk); + + if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) + goto out; + + err = __inet_listen_sk(sk, backlog); out: release_sock(sk); @@ -325,14 +331,14 @@ lookup_protocol: sk->sk_reuse = SK_CAN_REUSE; inet = inet_sk(sk); - inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; + inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags); - inet->nodefrag = 0; + inet_clear_bit(NODEFRAG, sk); if (SOCK_RAW == sock->type) { inet->inet_num = protocol; if (IPPROTO_RAW == protocol) - inet->hdrincl = 1; + inet_set_bit(HDRINCL, sk); } if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) @@ -350,9 +356,9 @@ lookup_protocol: sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); inet->uc_ttl = -1; - inet->mc_loop = 1; + inet_set_bit(MC_LOOP, sk); inet->mc_ttl = 1; - inet->mc_all = 1; + inet_set_bit(MC_ALL, sk); inet->mc_index = 0; inet->mc_list = NULL; inet->rcv_tos = 0; @@ -431,9 +437,8 @@ int inet_release(struct socket *sock) } EXPORT_SYMBOL(inet_release); -int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) { - struct sock *sk = sock->sk; u32 flags = BIND_WITH_LOCK; int err; @@ -454,6 +459,11 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) return __inet_bind(sk, uaddr, addr_len, flags); } + +int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +{ + return inet_bind_sk(sock->sk, uaddr, addr_len); +} EXPORT_SYMBOL(inet_bind); int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, @@ -519,7 +529,7 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, inet->inet_saddr = 0; /* Use device */ /* Make sure we are allowed to bind here. */ - if (snum || !(inet->bind_address_no_port || + if (snum || !(inet_test_bit(BIND_ADDRESS_NO_PORT, sk) || (flags & BIND_FORCE_ADDRESS_NO_PORT))) { err = sk->sk_prot->get_port(sk, snum); if (err) { @@ -646,7 +656,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, err = -EISCONN; goto out; case SS_CONNECTING: - if (inet_sk(sk)->defer_connect) + if (inet_test_bit(DEFER_CONNECT, sk)) err = is_sendmsg ? -EINPROGRESS : -EISCONN; else err = -EALREADY; @@ -669,7 +679,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, sock->state = SS_CONNECTING; - if (!err && inet_sk(sk)->defer_connect) + if (!err && inet_test_bit(DEFER_CONNECT, sk)) goto out; /* Just entered SS_CONNECTING state; the only diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 79ae7204e8ed..d048aa833293 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1881,7 +1881,7 @@ int cipso_v4_sock_setattr(struct sock *sk, old = rcu_dereference_protected(sk_inet->inet_opt, lockdep_sock_is_held(sk)); - if (sk_inet->is_icsk) { + if (inet_test_bit(IS_ICSK, sk)) { sk_conn = inet_csk(sk); if (old) sk_conn->icsk_ext_hdr_len -= old->opt.optlen; @@ -2051,7 +2051,7 @@ void cipso_v4_sock_delattr(struct sock *sk) sk_inet = inet_sk(sk); hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt); - if (sk_inet->is_icsk && hdr_delta > 0) { + if (inet_test_bit(IS_ICSK, sk) && hdr_delta > 0) { struct inet_connection_sock *sk_conn = inet_csk(sk); sk_conn->icsk_ext_hdr_len -= hdr_delta; sk_conn->icsk_sync_mss(sk, sk_conn->icsk_pmtu_cookie); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 48ff5f13e797..0c9e768e5628 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2658,7 +2658,7 @@ int ip_mc_sf_allow(const struct sock *sk, __be32 loc_addr, __be32 rmt_addr, (sdif && pmc->multi.imr_ifindex == sdif))) break; } - ret = inet->mc_all; + ret = inet_test_bit(MC_ALL, sk); if (!pmc) goto unlock; psl = rcu_dereference(pmc->sflist); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index f7426926a104..e13a84433413 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -182,17 +182,17 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, r->idiag_inode = sock_i_ino(sk); memset(&inet_sockopt, 0, sizeof(inet_sockopt)); - inet_sockopt.recverr = inet->recverr; - inet_sockopt.is_icsk = inet->is_icsk; - inet_sockopt.freebind = inet->freebind; - inet_sockopt.hdrincl = inet->hdrincl; - inet_sockopt.mc_loop = inet->mc_loop; - inet_sockopt.transparent = inet->transparent; - inet_sockopt.mc_all = inet->mc_all; - inet_sockopt.nodefrag = inet->nodefrag; - inet_sockopt.bind_address_no_port = inet->bind_address_no_port; - inet_sockopt.recverr_rfc4884 = inet->recverr_rfc4884; - inet_sockopt.defer_connect = inet->defer_connect; + inet_sockopt.recverr = inet_test_bit(RECVERR, sk); + inet_sockopt.is_icsk = inet_test_bit(IS_ICSK, sk); + inet_sockopt.freebind = inet_test_bit(FREEBIND, sk); + inet_sockopt.hdrincl = inet_test_bit(HDRINCL, sk); + inet_sockopt.mc_loop = inet_test_bit(MC_LOOP, sk); + inet_sockopt.transparent = inet_test_bit(TRANSPARENT, sk); + inet_sockopt.mc_all = inet_test_bit(MC_ALL, sk); + inet_sockopt.nodefrag = inet_test_bit(NODEFRAG, sk); + inet_sockopt.bind_address_no_port = inet_test_bit(BIND_ADDRESS_NO_PORT, sk); + inet_sockopt.recverr_rfc4884 = inet_test_bit(RECVERR_RFC4884, sk); + inet_sockopt.defer_connect = inet_test_bit(DEFER_CONNECT, sk); if (nla_put(skb, INET_DIAG_SOCKOPT, sizeof(inet_sockopt), &inet_sockopt)) goto errout; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 2c1b245dba8e..dd37a5bf6881 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -203,7 +203,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, tw->tw_reuseport = sk->sk_reuseport; tw->tw_hash = sk->sk_hash; tw->tw_ipv6only = 0; - tw->tw_transparent = inet->transparent; + tw->tw_transparent = inet_test_bit(TRANSPARENT, sk); tw->tw_prot = sk->sk_prot_creator; atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie)); twsk_net_set(tw, sock_net(sk)); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index f28c87533a46..ce6257860a40 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -133,7 +133,7 @@ EXPORT_SYMBOL_GPL(ip_local_out); static inline int ip_select_ttl(const struct inet_sock *inet, const struct dst_entry *dst) { - int ttl = inet->uc_ttl; + int ttl = READ_ONCE(inet->uc_ttl); if (ttl < 0) ttl = ip4_dst_hoplimit(dst); @@ -1039,7 +1039,7 @@ static int __ip_append_data(struct sock *sk, } } } else if ((flags & MSG_SPLICE_PAGES) && length) { - if (inet->hdrincl) + if (inet_test_bit(HDRINCL, sk)) return -EPERM; if (rt->dst.dev->features & NETIF_F_SG && getfrag == ip_generic_getfrag) @@ -1467,7 +1467,8 @@ struct sk_buff *__ip_make_skb(struct sock *sk, * so icmphdr does not in skb linear region and can not get icmp_type * by icmp_hdr(skb)->type. */ - if (sk->sk_type == SOCK_RAW && !inet_sk(sk)->hdrincl) + if (sk->sk_type == SOCK_RAW && + !inet_test_bit(HDRINCL, sk)) icmp_type = fl4->fl4_icmp_type; else icmp_type = icmp_hdr(skb)->type; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index d41bce8927b2..61b2e7bc7031 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -171,8 +171,10 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, int tlen, int offset) { - struct inet_sock *inet = inet_sk(sk); - unsigned int flags = inet->cmsg_flags; + unsigned long flags = inet_cmsg_flags(inet_sk(sk)); + + if (!flags) + return; /* Ordered by supposed usage frequency */ if (flags & IP_CMSG_PKTINFO) { @@ -431,7 +433,7 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, serr->port = port; if (skb_pull(skb, payload - skb->data)) { - if (inet_sk(sk)->recverr_rfc4884) + if (inet_test_bit(RECVERR_RFC4884, sk)) ipv4_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884); skb_reset_transport_header(skb); @@ -444,12 +446,11 @@ EXPORT_SYMBOL_GPL(ip_icmp_error); void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 info) { - struct inet_sock *inet = inet_sk(sk); struct sock_exterr_skb *serr; struct iphdr *iph; struct sk_buff *skb; - if (!inet->recverr) + if (!inet_test_bit(RECVERR, sk)) return; skb = alloc_skb(sizeof(struct iphdr), GFP_ATOMIC); @@ -568,7 +569,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) if (ipv4_datagram_support_cmsg(sk, skb, serr->ee.ee_origin)) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; - if (inet_sk(sk)->cmsg_flags) + if (inet_cmsg_flags(inet_sk(sk))) ip_cmsg_recv(msg, skb); } @@ -607,17 +608,13 @@ EXPORT_SYMBOL(ip_sock_set_tos); void ip_sock_set_freebind(struct sock *sk) { - lock_sock(sk); - inet_sk(sk)->freebind = true; - release_sock(sk); + inet_set_bit(FREEBIND, sk); } EXPORT_SYMBOL(ip_sock_set_freebind); void ip_sock_set_recverr(struct sock *sk) { - lock_sock(sk); - inet_sk(sk)->recverr = true; - release_sock(sk); + inet_set_bit(RECVERR, sk); } EXPORT_SYMBOL(ip_sock_set_recverr); @@ -634,9 +631,7 @@ EXPORT_SYMBOL(ip_sock_set_mtu_discover); void ip_sock_set_pktinfo(struct sock *sk) { - lock_sock(sk); - inet_sk(sk)->cmsg_flags |= IP_CMSG_PKTINFO; - release_sock(sk); + inet_set_bit(PKTINFO, sk); } EXPORT_SYMBOL(ip_sock_set_pktinfo); @@ -950,6 +945,104 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, if (ip_mroute_opt(optname)) return ip_mroute_setsockopt(sk, optname, optval, optlen); + /* Handle options that can be set without locking the socket. */ + switch (optname) { + case IP_PKTINFO: + inet_assign_bit(PKTINFO, sk, val); + return 0; + case IP_RECVTTL: + inet_assign_bit(TTL, sk, val); + return 0; + case IP_RECVTOS: + inet_assign_bit(TOS, sk, val); + return 0; + case IP_RECVOPTS: + inet_assign_bit(RECVOPTS, sk, val); + return 0; + case IP_RETOPTS: + inet_assign_bit(RETOPTS, sk, val); + return 0; + case IP_PASSSEC: + inet_assign_bit(PASSSEC, sk, val); + return 0; + case IP_RECVORIGDSTADDR: + inet_assign_bit(ORIGDSTADDR, sk, val); + return 0; + case IP_RECVFRAGSIZE: + if (sk->sk_type != SOCK_RAW && sk->sk_type != SOCK_DGRAM) + return -EINVAL; + inet_assign_bit(RECVFRAGSIZE, sk, val); + return 0; + case IP_RECVERR: + inet_assign_bit(RECVERR, sk, val); + if (!val) + skb_queue_purge(&sk->sk_error_queue); + return 0; + case IP_RECVERR_RFC4884: + if (val < 0 || val > 1) + return -EINVAL; + inet_assign_bit(RECVERR_RFC4884, sk, val); + return 0; + case IP_FREEBIND: + if (optlen < 1) + return -EINVAL; + inet_assign_bit(FREEBIND, sk, val); + return 0; + case IP_HDRINCL: + if (sk->sk_type != SOCK_RAW) + return -ENOPROTOOPT; + inet_assign_bit(HDRINCL, sk, val); + return 0; + case IP_MULTICAST_LOOP: + if (optlen < 1) + return -EINVAL; + inet_assign_bit(MC_LOOP, sk, val); + return 0; + case IP_MULTICAST_ALL: + if (optlen < 1) + return -EINVAL; + if (val != 0 && val != 1) + return -EINVAL; + inet_assign_bit(MC_ALL, sk, val); + return 0; + case IP_TRANSPARENT: + if (!!val && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && + !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { + err = -EPERM; + break; + } + if (optlen < 1) + goto e_inval; + inet_assign_bit(TRANSPARENT, sk, val); + return 0; + case IP_NODEFRAG: + if (sk->sk_type != SOCK_RAW) + return -ENOPROTOOPT; + inet_assign_bit(NODEFRAG, sk, val); + return 0; + case IP_BIND_ADDRESS_NO_PORT: + inet_assign_bit(BIND_ADDRESS_NO_PORT, sk, val); + return 0; + case IP_TTL: + if (optlen < 1) + return -EINVAL; + if (val != -1 && (val < 1 || val > 255)) + return -EINVAL; + WRITE_ONCE(inet->uc_ttl, val); + return 0; + case IP_MINTTL: + if (optlen < 1) + return -EINVAL; + if (val < 0 || val > 255) + return -EINVAL; + + if (val) + static_branch_enable(&ip4_min_ttl); + + WRITE_ONCE(inet->min_ttl, val); + return 0; + } + err = 0; if (needs_rtnl) rtnl_lock(); @@ -967,7 +1060,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, break; old = rcu_dereference_protected(inet->inet_opt, lockdep_sock_is_held(sk)); - if (inet->is_icsk) { + if (inet_test_bit(IS_ICSK, sk)) { struct inet_connection_sock *icsk = inet_csk(sk); #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET || @@ -989,111 +1082,27 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, kfree_rcu(old, rcu); break; } - case IP_PKTINFO: - if (val) - inet->cmsg_flags |= IP_CMSG_PKTINFO; - else - inet->cmsg_flags &= ~IP_CMSG_PKTINFO; - break; - case IP_RECVTTL: - if (val) - inet->cmsg_flags |= IP_CMSG_TTL; - else - inet->cmsg_flags &= ~IP_CMSG_TTL; - break; - case IP_RECVTOS: - if (val) - inet->cmsg_flags |= IP_CMSG_TOS; - else - inet->cmsg_flags &= ~IP_CMSG_TOS; - break; - case IP_RECVOPTS: - if (val) - inet->cmsg_flags |= IP_CMSG_RECVOPTS; - else - inet->cmsg_flags &= ~IP_CMSG_RECVOPTS; - break; - case IP_RETOPTS: - if (val) - inet->cmsg_flags |= IP_CMSG_RETOPTS; - else - inet->cmsg_flags &= ~IP_CMSG_RETOPTS; - break; - case IP_PASSSEC: - if (val) - inet->cmsg_flags |= IP_CMSG_PASSSEC; - else - inet->cmsg_flags &= ~IP_CMSG_PASSSEC; - break; - case IP_RECVORIGDSTADDR: - if (val) - inet->cmsg_flags |= IP_CMSG_ORIGDSTADDR; - else - inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR; - break; case IP_CHECKSUM: if (val) { - if (!(inet->cmsg_flags & IP_CMSG_CHECKSUM)) { + if (!(inet_test_bit(CHECKSUM, sk))) { inet_inc_convert_csum(sk); - inet->cmsg_flags |= IP_CMSG_CHECKSUM; + inet_set_bit(CHECKSUM, sk); } } else { - if (inet->cmsg_flags & IP_CMSG_CHECKSUM) { + if (inet_test_bit(CHECKSUM, sk)) { inet_dec_convert_csum(sk); - inet->cmsg_flags &= ~IP_CMSG_CHECKSUM; + inet_clear_bit(CHECKSUM, sk); } } break; - case IP_RECVFRAGSIZE: - if (sk->sk_type != SOCK_RAW && sk->sk_type != SOCK_DGRAM) - goto e_inval; - if (val) - inet->cmsg_flags |= IP_CMSG_RECVFRAGSIZE; - else - inet->cmsg_flags &= ~IP_CMSG_RECVFRAGSIZE; - break; case IP_TOS: /* This sets both TOS and Precedence */ __ip_sock_set_tos(sk, val); break; - case IP_TTL: - if (optlen < 1) - goto e_inval; - if (val != -1 && (val < 1 || val > 255)) - goto e_inval; - inet->uc_ttl = val; - break; - case IP_HDRINCL: - if (sk->sk_type != SOCK_RAW) { - err = -ENOPROTOOPT; - break; - } - inet->hdrincl = val ? 1 : 0; - break; - case IP_NODEFRAG: - if (sk->sk_type != SOCK_RAW) { - err = -ENOPROTOOPT; - break; - } - inet->nodefrag = val ? 1 : 0; - break; - case IP_BIND_ADDRESS_NO_PORT: - inet->bind_address_no_port = val ? 1 : 0; - break; case IP_MTU_DISCOVER: if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT) goto e_inval; inet->pmtudisc = val; break; - case IP_RECVERR: - inet->recverr = !!val; - if (!val) - skb_queue_purge(&sk->sk_error_queue); - break; - case IP_RECVERR_RFC4884: - if (val < 0 || val > 1) - goto e_inval; - inet->recverr_rfc4884 = !!val; - break; case IP_MULTICAST_TTL: if (sk->sk_type == SOCK_STREAM) goto e_inval; @@ -1105,11 +1114,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, goto e_inval; inet->mc_ttl = val; break; - case IP_MULTICAST_LOOP: - if (optlen < 1) - goto e_inval; - inet->mc_loop = !!val; - break; case IP_UNICAST_IF: { struct net_device *dev = NULL; @@ -1214,7 +1218,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, struct ip_mreqn mreq; err = -EPROTO; - if (inet_sk(sk)->is_icsk) + if (inet_test_bit(IS_ICSK, sk)) break; if (optlen < sizeof(struct ip_mreq)) @@ -1325,20 +1329,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, else err = ip_set_mcast_msfilter(sk, optval, optlen); break; - case IP_MULTICAST_ALL: - if (optlen < 1) - goto e_inval; - if (val != 0 && val != 1) - goto e_inval; - inet->mc_all = val; - break; - - case IP_FREEBIND: - if (optlen < 1) - goto e_inval; - inet->freebind = !!val; - break; - case IP_IPSEC_POLICY: case IP_XFRM_POLICY: err = -EPERM; @@ -1347,32 +1337,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, err = xfrm_user_policy(sk, optname, optval, optlen); break; - case IP_TRANSPARENT: - if (!!val && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && - !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { - err = -EPERM; - break; - } - if (optlen < 1) - goto e_inval; - inet->transparent = !!val; - break; - - case IP_MINTTL: - if (optlen < 1) - goto e_inval; - if (val < 0 || val > 255) - goto e_inval; - - if (val) - static_branch_enable(&ip4_min_ttl); - - /* tcp_v4_err() and tcp_v4_rcv() might read min_ttl - * while we are changint it. - */ - WRITE_ONCE(inet->min_ttl, val); - break; - case IP_LOCAL_PORT_RANGE: { const __u16 lo = val; @@ -1415,7 +1379,7 @@ e_inval: void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) { struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); - bool prepare = (inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) || + bool prepare = inet_test_bit(PKTINFO, sk) || ipv6_sk_rxinfo(sk); if (prepare && skb_rtable(skb)) { @@ -1566,6 +1530,72 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, if (len < 0) return -EINVAL; + /* Handle options that can be read without locking the socket. */ + switch (optname) { + case IP_PKTINFO: + val = inet_test_bit(PKTINFO, sk); + goto copyval; + case IP_RECVTTL: + val = inet_test_bit(TTL, sk); + goto copyval; + case IP_RECVTOS: + val = inet_test_bit(TOS, sk); + goto copyval; + case IP_RECVOPTS: + val = inet_test_bit(RECVOPTS, sk); + goto copyval; + case IP_RETOPTS: + val = inet_test_bit(RETOPTS, sk); + goto copyval; + case IP_PASSSEC: + val = inet_test_bit(PASSSEC, sk); + goto copyval; + case IP_RECVORIGDSTADDR: + val = inet_test_bit(ORIGDSTADDR, sk); + goto copyval; + case IP_CHECKSUM: + val = inet_test_bit(CHECKSUM, sk); + goto copyval; + case IP_RECVFRAGSIZE: + val = inet_test_bit(RECVFRAGSIZE, sk); + goto copyval; + case IP_RECVERR: + val = inet_test_bit(RECVERR, sk); + goto copyval; + case IP_RECVERR_RFC4884: + val = inet_test_bit(RECVERR_RFC4884, sk); + goto copyval; + case IP_FREEBIND: + val = inet_test_bit(FREEBIND, sk); + goto copyval; + case IP_HDRINCL: + val = inet_test_bit(HDRINCL, sk); + goto copyval; + case IP_MULTICAST_LOOP: + val = inet_test_bit(MC_LOOP, sk); + goto copyval; + case IP_MULTICAST_ALL: + val = inet_test_bit(MC_ALL, sk); + goto copyval; + case IP_TRANSPARENT: + val = inet_test_bit(TRANSPARENT, sk); + goto copyval; + case IP_NODEFRAG: + val = inet_test_bit(NODEFRAG, sk); + goto copyval; + case IP_BIND_ADDRESS_NO_PORT: + val = inet_test_bit(BIND_ADDRESS_NO_PORT, sk); + goto copyval; + case IP_TTL: + val = READ_ONCE(inet->uc_ttl); + if (val < 0) + val = READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_default_ttl); + goto copyval; + case IP_MINTTL: + val = READ_ONCE(inet->min_ttl); + goto copyval; + } + if (needs_rtnl) rtnl_lock(); sockopt_lock_sock(sk); @@ -1600,53 +1630,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, return -EFAULT; return 0; } - case IP_PKTINFO: - val = (inet->cmsg_flags & IP_CMSG_PKTINFO) != 0; - break; - case IP_RECVTTL: - val = (inet->cmsg_flags & IP_CMSG_TTL) != 0; - break; - case IP_RECVTOS: - val = (inet->cmsg_flags & IP_CMSG_TOS) != 0; - break; - case IP_RECVOPTS: - val = (inet->cmsg_flags & IP_CMSG_RECVOPTS) != 0; - break; - case IP_RETOPTS: - val = (inet->cmsg_flags & IP_CMSG_RETOPTS) != 0; - break; - case IP_PASSSEC: - val = (inet->cmsg_flags & IP_CMSG_PASSSEC) != 0; - break; - case IP_RECVORIGDSTADDR: - val = (inet->cmsg_flags & IP_CMSG_ORIGDSTADDR) != 0; - break; - case IP_CHECKSUM: - val = (inet->cmsg_flags & IP_CMSG_CHECKSUM) != 0; - break; - case IP_RECVFRAGSIZE: - val = (inet->cmsg_flags & IP_CMSG_RECVFRAGSIZE) != 0; - break; case IP_TOS: val = inet->tos; break; - case IP_TTL: - { - struct net *net = sock_net(sk); - val = (inet->uc_ttl == -1 ? - READ_ONCE(net->ipv4.sysctl_ip_default_ttl) : - inet->uc_ttl); - break; - } - case IP_HDRINCL: - val = inet->hdrincl; - break; - case IP_NODEFRAG: - val = inet->nodefrag; - break; - case IP_BIND_ADDRESS_NO_PORT: - val = inet->bind_address_no_port; - break; case IP_MTU_DISCOVER: val = inet->pmtudisc; break; @@ -1665,18 +1651,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, } break; } - case IP_RECVERR: - val = inet->recverr; - break; - case IP_RECVERR_RFC4884: - val = inet->recverr_rfc4884; - break; case IP_MULTICAST_TTL: val = inet->mc_ttl; break; - case IP_MULTICAST_LOOP: - val = inet->mc_loop; - break; case IP_UNICAST_IF: val = (__force int)htonl((__u32) inet->uc_index); break; @@ -1715,9 +1692,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, else err = ip_get_mcast_msfilter(sk, optval, optlen, len); goto out; - case IP_MULTICAST_ALL: - val = inet->mc_all; - break; case IP_PKTOPTIONS: { struct msghdr msg; @@ -1737,7 +1711,7 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, msg.msg_controllen = len; msg.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0; - if (inet->cmsg_flags & IP_CMSG_PKTINFO) { + if (inet_test_bit(PKTINFO, sk)) { struct in_pktinfo info; info.ipi_addr.s_addr = inet->inet_rcv_saddr; @@ -1745,26 +1719,17 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, info.ipi_ifindex = inet->mc_index; put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info); } - if (inet->cmsg_flags & IP_CMSG_TTL) { + if (inet_test_bit(TTL, sk)) { int hlim = inet->mc_ttl; put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim); } - if (inet->cmsg_flags & IP_CMSG_TOS) { + if (inet_test_bit(TOS, sk)) { int tos = inet->rcv_tos; put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos); } len -= msg.msg_controllen; return copy_to_sockptr(optlen, &len, sizeof(int)); } - case IP_FREEBIND: - val = inet->freebind; - break; - case IP_TRANSPARENT: - val = inet->transparent; - break; - case IP_MINTTL: - val = inet->min_ttl; - break; case IP_LOCAL_PORT_RANGE: val = inet->local_port_range.hi << 16 | inet->local_port_range.lo; break; @@ -1776,7 +1741,7 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, return -ENOPROTOOPT; } sockopt_release_sock(sk); - +copyval: if (len < sizeof(int) && len > 0 && val >= 0 && val <= 255) { unsigned char ucval = (unsigned char)val; len = 1; diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index a9ba7de092c4..265b39bc435b 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -66,7 +66,7 @@ static unsigned int ipv4_conntrack_defrag(void *priv, struct sock *sk = skb->sk; if (sk && sk_fullsock(sk) && (sk->sk_family == PF_INET) && - inet_sk(sk)->nodefrag) + inet_test_bit(NODEFRAG, sk)) return NF_ACCEPT; #if IS_ENABLED(CONFIG_NF_CONNTRACK) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 09d36bcbd7d4..bbff68b5b5d4 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3209,7 +3209,6 @@ static int rtm_dump_walk_nexthops(struct sk_buff *skb, return err; } - ctx->idx++; return 0; } @@ -3337,7 +3336,6 @@ static int nh_valid_dump_bucket_req(const struct nlmsghdr *nlh, struct rtm_dump_res_bucket_ctx { struct rtm_dump_nh_ctx nh; u16 bucket_index; - u32 done_nh_idx; /* 1 + the index of the last fully processed NH. */ }; static struct rtm_dump_res_bucket_ctx * @@ -3366,9 +3364,6 @@ static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb, u16 bucket_index; int err; - if (dd->ctx->nh.idx < dd->ctx->done_nh_idx) - return 0; - nhg = rtnl_dereference(nh->nh_grp); res_table = rtnl_dereference(nhg->res_table); for (bucket_index = dd->ctx->bucket_index; @@ -3395,7 +3390,6 @@ static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb, return err; } - dd->ctx->done_nh_idx = dd->ctx->nh.idx + 1; dd->ctx->bucket_index = 0; return 0; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 25dd78cee179..75e0aee35eb7 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -580,7 +580,7 @@ void ping_err(struct sk_buff *skb, int offset, u32 info) * RFC1122: OK. Passes ICMP errors back to application, as per * 4.1.3.3. */ - if ((family == AF_INET && !inet_sock->recverr) || + if ((family == AF_INET && !inet_test_bit(RECVERR, sk)) || (family == AF_INET6 && !inet6_sk(sk)->recverr)) { if (!harderr || sk->sk_state != TCP_ESTABLISHED) goto out; @@ -894,7 +894,7 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, *addr_len = sizeof(*sin); } - if (isk->cmsg_flags) + if (inet_cmsg_flags(isk)) ip_cmsg_recv(msg, skb); #if IS_ENABLED(CONFIG_IPV6) @@ -921,7 +921,8 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, if (skb->protocol == htons(ETH_P_IPV6) && inet6_sk(sk)->rxopt.all) pingv6_ops.ip6_datagram_recv_specific_ctl(sk, msg, skb); - else if (skb->protocol == htons(ETH_P_IP) && isk->cmsg_flags) + else if (skb->protocol == htons(ETH_P_IP) && + inet_cmsg_flags(isk)) ip_cmsg_recv(msg, skb); #endif } else { diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index cb381f5aa464..4b5db5d1edc2 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -203,8 +203,9 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) struct inet_sock *inet = inet_sk(sk); const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; - int err = 0; int harderr = 0; + bool recverr; + int err = 0; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) ipv4_sk_update_pmtu(skb, sk, info); @@ -218,7 +219,8 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) 2. Socket is connected (otherwise the error indication is useless without ip_recverr and error is hard. */ - if (!inet->recverr && sk->sk_state != TCP_ESTABLISHED) + recverr = inet_test_bit(RECVERR, sk); + if (!recverr && sk->sk_state != TCP_ESTABLISHED) return; switch (type) { @@ -245,16 +247,16 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) } } - if (inet->recverr) { + if (recverr) { const struct iphdr *iph = (const struct iphdr *)skb->data; u8 *payload = skb->data + (iph->ihl << 2); - if (inet->hdrincl) + if (inet_test_bit(HDRINCL, sk)) payload = skb->data; ip_icmp_error(sk, skb, err, 0, info, payload); } - if (inet->recverr || harderr) { + if (recverr || harderr) { sk->sk_err = err; sk_error_report(sk); } @@ -413,7 +415,7 @@ error_free: kfree_skb(skb); error: IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); - if (err == -ENOBUFS && !inet->recverr) + if (err == -ENOBUFS && !inet_test_bit(RECVERR, sk)) err = 0; return err; } @@ -489,12 +491,8 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (len > 0xFFFF) goto out; - /* hdrincl should be READ_ONCE(inet->hdrincl) - * but READ_ONCE() doesn't work with bit fields. - * Doing this indirectly yields the same result. - */ - hdrincl = inet->hdrincl; - hdrincl = READ_ONCE(hdrincl); + hdrincl = inet_test_bit(HDRINCL, sk); + /* * Check the flags. */ @@ -645,7 +643,7 @@ back_from_confirm: ip_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) { err = ip_push_pending_frames(sk, &fl4); - if (err == -ENOBUFS && !inet->recverr) + if (err == -ENOBUFS && !inet_test_bit(RECVERR, sk)) err = 0; } release_sock(sk); @@ -767,7 +765,7 @@ static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); } - if (inet->cmsg_flags) + if (inet_cmsg_flags(inet)) ip_cmsg_recv(msg, skb); if (flags & MSG_TRUNC) copied = skb->len; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 92fede388d52..a4e153dd615b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -515,13 +515,12 @@ static void __build_flow_key(const struct net *net, struct flowi4 *fl4, __u8 scope = RT_SCOPE_UNIVERSE; if (sk) { - const struct inet_sock *inet = inet_sk(sk); - oif = sk->sk_bound_dev_if; mark = READ_ONCE(sk->sk_mark); tos = ip_sock_rt_tos(sk); scope = ip_sock_rt_scope(sk); - prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol; + prot = inet_test_bit(HDRINCL, sk) ? IPPROTO_RAW : + sk->sk_protocol; } flowi4_init_output(fl4, oif, mark, tos & IPTOS_RT_MASK, scope, @@ -555,7 +554,8 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk) & IPTOS_RT_MASK, ip_sock_rt_scope(sk), - inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, + inet_test_bit(HDRINCL, sk) ? + IPPROTO_RAW : sk->sk_protocol, inet_sk_flowi_flags(sk), daddr, inet->inet_saddr, 0, 0, sk->sk_uid); rcu_read_unlock(); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4fbc7ff8c53c..cee1e548660c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -583,7 +583,8 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (urg_data & TCP_URG_VALID) mask |= EPOLLPRI; - } else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) { + } else if (state == TCP_SYN_SENT && + inet_test_bit(DEFER_CONNECT, sk)) { /* Active TCP fastopen socket with defer_connect * Return EPOLLOUT so application can call write() * in order for kernel to generate SYN+data @@ -1007,7 +1008,7 @@ int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, tp->fastopen_req->size = size; tp->fastopen_req->uarg = uarg; - if (inet->defer_connect) { + if (inet_test_bit(DEFER_CONNECT, sk)) { err = tcp_connect(sk); /* Same failure procedure as in tcp_v4/6_connect */ if (err) { @@ -1025,7 +1026,7 @@ int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, if (tp->fastopen_req) { *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); - inet->defer_connect = 0; + inet_clear_bit(DEFER_CONNECT, sk); } return err; } @@ -1066,7 +1067,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) zc = MSG_SPLICE_PAGES; } - if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) && + if (unlikely(flags & MSG_FASTOPEN || + inet_test_bit(DEFER_CONNECT, sk)) && !tp->repair) { err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size, uarg); if (err == -EINPROGRESS && copied_syn > 0) @@ -3088,7 +3090,7 @@ int tcp_disconnect(struct sock *sk, int flags) /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); - inet->defer_connect = 0; + inet_clear_bit(DEFER_CONNECT, sk); tp->fastopen_client_fail = 0; WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 85e4953f1182..8ed54e7334a9 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -451,7 +451,7 @@ bool tcp_fastopen_defer_connect(struct sock *sk, int *err) if (tp->fastopen_connect && !tp->fastopen_req) { if (tcp_fastopen_cookie_check(sk, &mss, &cookie)) { - inet_sk(sk)->defer_connect = 1; + inet_set_bit(DEFER_CONNECT, sk); return true; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8e96ebe373d7..06fe1cf645d5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3525,7 +3525,7 @@ static inline bool tcp_may_update_window(const struct tcp_sock *tp, { return after(ack, tp->snd_una) || after(ack_seq, tp->snd_wl1) || - (ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd); + (ack_seq == tp->snd_wl1 && (nwin > tp->snd_wnd || !nwin)); } /* If we update tp->snd_una, also update tp->bytes_acked */ @@ -5059,13 +5059,19 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) /* Ok. In sequence. In window. */ queue_and_out: - if (skb_queue_len(&sk->sk_receive_queue) == 0) - sk_forced_mem_schedule(sk, skb->truesize); - else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { - reason = SKB_DROP_REASON_PROTO_MEM; - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); + if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { + /* TODO: maybe ratelimit these WIN 0 ACK ? */ + inet_csk(sk)->icsk_ack.pending |= + (ICSK_ACK_NOMEM | ICSK_ACK_NOW); + inet_csk_schedule_ack(sk); sk->sk_data_ready(sk); - goto drop; + + if (skb_queue_len(&sk->sk_receive_queue)) { + reason = SKB_DROP_REASON_PROTO_MEM; + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); + goto drop; + } + sk_forced_mem_schedule(sk, skb->truesize); } eaten = tcp_queue_rcv(sk, skb, &fragstolen); @@ -6994,7 +7000,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb, sk); - inet_rsk(req)->no_srccheck = inet_sk(sk)->transparent; + inet_rsk(req)->no_srccheck = inet_test_bit(TRANSPARENT, sk); /* Note: tcp_v6_init_req() might override ir_iif for link locals */ inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5b18a048f613..2a662d5f3072 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -477,7 +477,6 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) const struct iphdr *iph = (const struct iphdr *)skb->data; struct tcphdr *th = (struct tcphdr *)(skb->data + (iph->ihl << 2)); struct tcp_sock *tp; - struct inet_sock *inet; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct sock *sk; @@ -625,8 +624,8 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) * --ANK (980905) */ - inet = inet_sk(sk); - if (!sock_owned_by_user(sk) && inet->recverr) { + if (!sock_owned_by_user(sk) && + inet_test_bit(RECVERR, sk)) { WRITE_ONCE(sk->sk_err, err); sk_error_report(sk); } else { /* Only an error on timeout */ diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 13ee12983c42..b98d476f1594 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -289,9 +289,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) if (tw) { struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); - struct inet_sock *inet = inet_sk(sk); - tw->tw_transparent = inet->transparent; + tw->tw_transparent = inet_test_bit(TRANSPARENT, sk); tw->tw_mark = sk->sk_mark; tw->tw_priority = sk->sk_priority; tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index c5412ee77fc8..769a558159ee 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -257,11 +257,19 @@ EXPORT_SYMBOL(tcp_select_initial_window); static u16 tcp_select_window(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - u32 old_win = tp->rcv_wnd; - u32 cur_win = tcp_receive_window(tp); - u32 new_win = __tcp_select_window(sk); struct net *net = sock_net(sk); + u32 old_win = tp->rcv_wnd; + u32 cur_win, new_win; + + /* Make the window 0 if we failed to queue the data because we + * are out of memory. The window is temporary, so we don't store + * it on the socket. + */ + if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM)) + return 0; + cur_win = tcp_receive_window(tp); + new_win = __tcp_select_window(sk); if (new_win < cur_win) { /* Danger Will Robinson! * Don't update rcv_wup/rcv_wnd here or else diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index d45c96c7f5a4..74c70fc1003c 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -454,6 +454,22 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) req->timeout << req->num_timeout, TCP_RTO_MAX); } +static bool tcp_rtx_probe0_timed_out(const struct sock *sk, + const struct sk_buff *skb) +{ + const struct tcp_sock *tp = tcp_sk(sk); + const int timeout = TCP_RTO_MAX * 2; + u32 rcv_delta, rtx_delta; + + rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp; + if (rcv_delta <= timeout) + return false; + + rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) - + (tp->retrans_stamp ?: tcp_skb_timestamp(skb))); + + return rtx_delta > timeout; +} /** * tcp_retransmit_timer() - The TCP retransmit timeout handler @@ -503,23 +519,26 @@ void tcp_retransmit_timer(struct sock *sk) * we cannot allow such beasts to hang infinitely. */ struct inet_sock *inet = inet_sk(sk); + u32 rtx_delta; + + rtx_delta = tcp_time_stamp(tp) - (tp->retrans_stamp ?: tcp_skb_timestamp(skb)); if (sk->sk_family == AF_INET) { - net_dbg_ratelimited("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", - &inet->inet_daddr, - ntohs(inet->inet_dport), - inet->inet_num, - tp->snd_una, tp->snd_nxt); + net_dbg_ratelimited("Probing zero-window on %pI4:%u/%u, seq=%u:%u, recv %ums ago, lasting %ums\n", + &inet->inet_daddr, ntohs(inet->inet_dport), + inet->inet_num, tp->snd_una, tp->snd_nxt, + jiffies_to_msecs(jiffies - tp->rcv_tstamp), + rtx_delta); } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { - net_dbg_ratelimited("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", - &sk->sk_v6_daddr, - ntohs(inet->inet_dport), - inet->inet_num, - tp->snd_una, tp->snd_nxt); + net_dbg_ratelimited("Probing zero-window on %pI6:%u/%u, seq=%u:%u, recv %ums ago, lasting %ums\n", + &sk->sk_v6_daddr, ntohs(inet->inet_dport), + inet->inet_num, tp->snd_una, tp->snd_nxt, + jiffies_to_msecs(jiffies - tp->rcv_tstamp), + rtx_delta); } #endif - if (tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX) { + if (tcp_rtx_probe0_timed_out(sk, skb)) { tcp_write_err(sk); goto out; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 3e2f29c14fa8..0794a2c46a56 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -779,7 +779,7 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) (u8 *)(uh+1)); goto out; } - if (!inet->recverr) { + if (!inet_test_bit(RECVERR, sk)) { if (!harderr || sk->sk_state != TCP_ESTABLISHED) goto out; } else @@ -962,7 +962,8 @@ csum_partial: send: err = ip_send_skb(sock_net(sk), skb); if (err) { - if (err == -ENOBUFS && !inet->recverr) { + if (err == -ENOBUFS && + !inet_test_bit(RECVERR, sk)) { UDP_INC_STATS(sock_net(sk), UDP_MIB_SNDBUFERRORS, is_udplite); err = 0; @@ -1870,7 +1871,7 @@ try_again: if (udp_sk(sk)->gro_enabled) udp_cmsg_recv(msg, sk, skb); - if (inet->cmsg_flags) + if (inet_cmsg_flags(inet)) ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off); err = copied; diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 5f8104cf082d..9b18f371af0d 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -63,7 +63,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct sock *sk = sock->sk; /* Disable multicast loopback */ - inet_sk(sk)->mc_loop = 0; + inet_clear_bit(MC_LOOP, sk); /* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */ inet_inc_convert_csum(sk); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 9f9c4b838664..368824fe9719 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -200,12 +200,12 @@ lookup_protocol: sk->sk_reuse = SK_CAN_REUSE; inet = inet_sk(sk); - inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; + inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags); if (SOCK_RAW == sock->type) { inet->inet_num = protocol; if (IPPROTO_RAW == protocol) - inet->hdrincl = 1; + inet_set_bit(HDRINCL, sk); } sk->sk_destruct = inet6_sock_destruct; @@ -229,7 +229,7 @@ lookup_protocol: */ inet->uc_ttl = -1; - inet->mc_loop = 1; + inet_set_bit(MC_LOOP, sk); inet->mc_ttl = 1; inet->mc_index = 0; RCU_INIT_POINTER(inet->mc_list, NULL); @@ -399,7 +399,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, sk->sk_ipv6only = 1; /* Make sure we are allowed to bind here. */ - if (snum || !(inet->bind_address_no_port || + if (snum || !(inet_test_bit(BIND_ADDRESS_NO_PORT, sk) || (flags & BIND_FORCE_ADDRESS_NO_PORT))) { err = sk->sk_prot->get_port(sk, snum); if (err) { @@ -435,10 +435,8 @@ out_unlock: goto out; } -/* bind for INET6 API */ -int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) { - struct sock *sk = sock->sk; u32 flags = BIND_WITH_LOCK; const struct proto *prot; int err = 0; @@ -462,6 +460,12 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) return __inet6_bind(sk, uaddr, addr_len, flags); } + +/* bind for INET6 API */ +int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +{ + return inet6_bind_sk(sock->sk, uaddr, addr_len); +} EXPORT_SYMBOL(inet6_bind); int inet6_release(struct socket *sock) diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index d80d6024cafa..41ebc4e57473 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -524,7 +524,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) } else { ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &sin->sin6_addr); - if (inet_sk(sk)->cmsg_flags) + if (inet_cmsg_flags(inet_sk(sk))) ip_cmsg_recv(msg, skb); } } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index bac768d36cc1..28b01a068412 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -160,6 +160,8 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh) INIT_LIST_HEAD(&f6i->fib6_siblings); refcount_set(&f6i->fib6_ref, 1); + INIT_HLIST_NODE(&f6i->gc_link); + return f6i; } @@ -246,6 +248,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) net->ipv6.fib6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); + INIT_HLIST_HEAD(&table->tb6_gc_hlist); } return table; @@ -1057,6 +1060,8 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, lockdep_is_held(&table->tb6_lock)); } } + + fib6_clean_expires_locked(rt); } /* @@ -1118,9 +1123,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, if (!(iter->fib6_flags & RTF_EXPIRES)) return -EEXIST; if (!(rt->fib6_flags & RTF_EXPIRES)) - fib6_clean_expires(iter); + fib6_clean_expires_locked(iter); else - fib6_set_expires(iter, rt->expires); + fib6_set_expires_locked(iter, + rt->expires); if (rt->fib6_pmtu) fib6_metric_set(iter, RTAX_MTU, @@ -1479,6 +1485,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, if (rt->nh) list_add(&rt->nh_list, &rt->nh->f6i_list); __fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net)); + + if (fib6_has_expires(rt)) + hlist_add_head(&rt->gc_link, &table->tb6_gc_hlist); + fib6_start_gc(info->nl_net, rt); } @@ -2285,9 +2295,8 @@ static void fib6_flush_trees(struct net *net) * Garbage collection */ -static int fib6_age(struct fib6_info *rt, void *arg) +static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) { - struct fib6_gc_args *gc_args = arg; unsigned long now = jiffies; /* @@ -2295,7 +2304,7 @@ static int fib6_age(struct fib6_info *rt, void *arg) * Routes are expired even if they are in use. */ - if (rt->fib6_flags & RTF_EXPIRES && rt->expires) { + if (fib6_has_expires(rt) && rt->expires) { if (time_after(now, rt->expires)) { RT6_TRACE("expiring %p\n", rt); return -1; @@ -2312,6 +2321,40 @@ static int fib6_age(struct fib6_info *rt, void *arg) return 0; } +static void fib6_gc_table(struct net *net, + struct fib6_table *tb6, + struct fib6_gc_args *gc_args) +{ + struct fib6_info *rt; + struct hlist_node *n; + struct nl_info info = { + .nl_net = net, + .skip_notify = false, + }; + + hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link) + if (fib6_age(rt, gc_args) == -1) + fib6_del(rt, &info); +} + +static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args) +{ + struct fib6_table *table; + struct hlist_head *head; + unsigned int h; + + rcu_read_lock(); + for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { + head = &net->ipv6.fib_table_hash[h]; + hlist_for_each_entry_rcu(table, head, tb6_hlist) { + spin_lock_bh(&table->tb6_lock); + fib6_gc_table(net, table, gc_args); + spin_unlock_bh(&table->tb6_lock); + } + } + rcu_read_unlock(); +} + void fib6_run_gc(unsigned long expires, struct net *net, bool force) { struct fib6_gc_args gc_args; @@ -2327,7 +2370,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force) net->ipv6.sysctl.ip6_rt_gc_interval; gc_args.more = 0; - fib6_clean_all(net, fib6_age, &gc_args); + fib6_gc_all(net, &gc_args); now = jiffies; net->ipv6.ip6_rt_last_gc = now; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index bc96559bbf0f..f8a1f6bb3f87 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1591,7 +1591,7 @@ emsgsize: } } } else if ((flags & MSG_SPLICE_PAGES) && length) { - if (inet_sk(sk)->hdrincl) + if (inet_test_bit(HDRINCL, sk)) return -EPERM; if (rt->dst.dev->features & NETIF_F_SG && getfrag == ip_generic_getfrag) @@ -1995,7 +1995,8 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); u8 icmp6_type; - if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl) + if (sk->sk_socket->type == SOCK_RAW && + !inet_test_bit(HDRINCL, sk)) icmp6_type = fl6->fl6_icmp_type; else icmp6_type = icmp6_hdr(skb)->icmp6_type; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index ca377159967c..d19577a94bcc 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -102,7 +102,7 @@ int ip6_ra_control(struct sock *sk, int sel) struct ipv6_txoptions *ipv6_update_options(struct sock *sk, struct ipv6_txoptions *opt) { - if (inet_sk(sk)->is_icsk) { + if (inet_test_bit(IS_ICSK, sk)) { if (opt && !((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) && inet_sk(sk)->inet_daddr != LOOPBACK4_IPV6) { @@ -633,7 +633,7 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (optlen < sizeof(int)) goto e_inval; /* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */ - inet_sk(sk)->transparent = valbool; + inet_assign_bit(TRANSPARENT, sk, valbool); retv = 0; break; @@ -641,7 +641,7 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (optlen < sizeof(int)) goto e_inval; /* we also don't have a separate freebind bit for IPV6 */ - inet_sk(sk)->freebind = valbool; + inet_assign_bit(FREEBIND, sk, valbool); retv = 0; break; @@ -831,7 +831,7 @@ done: goto e_inval; retv = -EPROTO; - if (inet_sk(sk)->is_icsk) + if (inet_test_bit(IS_ICSK, sk)) break; retv = -EFAULT; @@ -1330,11 +1330,11 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname, } case IPV6_TRANSPARENT: - val = inet_sk(sk)->transparent; + val = inet_test_bit(TRANSPARENT, sk); break; case IPV6_FREEBIND: - val = inet_sk(sk)->freebind; + val = inet_test_bit(FREEBIND, sk); break; case IPV6_RECVORIGDSTADDR: diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ea16734f5e1f..0eae7661a85c 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -291,7 +291,6 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { - struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); int err; int harderr; @@ -315,7 +314,7 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, } if (np->recverr) { u8 *payload = skb->data; - if (!inet->hdrincl) + if (!inet_test_bit(HDRINCL, sk)) payload += offset; ipv6_icmp_error(sk, skb, err, 0, ntohl(info), payload); } @@ -406,7 +405,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) skb->len, inet->inet_num, 0)); - if (inet->hdrincl) { + if (inet_test_bit(HDRINCL, sk)) { if (skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb_reason(skb, SKB_DROP_REASON_SKB_CSUM); @@ -762,12 +761,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; - /* hdrincl should be READ_ONCE(inet->hdrincl) - * but READ_ONCE() doesn't work with bit fields. - * Doing this indirectly yields the same result. - */ - hdrincl = inet->hdrincl; - hdrincl = READ_ONCE(hdrincl); + hdrincl = inet_test_bit(HDRINCL, sk); /* * Get and verify the address. @@ -1000,7 +994,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, case IPV6_HDRINCL: if (sk->sk_type != SOCK_RAW) return -EINVAL; - inet_sk(sk)->hdrincl = !!val; + inet_assign_bit(HDRINCL, sk, val); return 0; case IPV6_CHECKSUM: if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && @@ -1068,7 +1062,7 @@ static int do_rawv6_getsockopt(struct sock *sk, int level, int optname, switch (optname) { case IPV6_HDRINCL: - val = inet_sk(sk)->hdrincl; + val = inet_test_bit(HDRINCL, sk); break; case IPV6_CHECKSUM: /* diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 10751df16dab..db10c36f34bb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3761,10 +3761,10 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, rt->dst_nocount = true; if (cfg->fc_flags & RTF_EXPIRES) - fib6_set_expires(rt, jiffies + - clock_t_to_jiffies(cfg->fc_expires)); + fib6_set_expires_locked(rt, jiffies + + clock_t_to_jiffies(cfg->fc_expires)); else - fib6_clean_expires(rt); + fib6_clean_expires_locked(rt); if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index dd433cc265c8..24e2b4b494cb 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -109,15 +109,19 @@ struct bpf_lwt_prog { #define next_csid_chk_lcnode_fn_bits(flen) \ next_csid_chk_lcblock_bits(flen) +/* flag indicating that flavors are set up for a given End* behavior */ +#define SEG6_F_LOCAL_FLAVORS SEG6_F_ATTR(SEG6_LOCAL_FLAVORS) + #define SEG6_F_LOCAL_FLV_OP(flvname) BIT(SEG6_LOCAL_FLV_OP_##flvname) +#define SEG6_F_LOCAL_FLV_NEXT_CSID SEG6_F_LOCAL_FLV_OP(NEXT_CSID) #define SEG6_F_LOCAL_FLV_PSP SEG6_F_LOCAL_FLV_OP(PSP) /* Supported RFC8986 Flavor operations are reported in this bitmask */ #define SEG6_LOCAL_FLV8986_SUPP_OPS SEG6_F_LOCAL_FLV_PSP -/* Supported Flavor operations are reported in this bitmask */ -#define SEG6_LOCAL_FLV_SUPP_OPS (SEG6_F_LOCAL_FLV_OP(NEXT_CSID) | \ +#define SEG6_LOCAL_END_FLV_SUPP_OPS (SEG6_F_LOCAL_FLV_NEXT_CSID | \ SEG6_LOCAL_FLV8986_SUPP_OPS) +#define SEG6_LOCAL_END_X_FLV_SUPP_OPS SEG6_F_LOCAL_FLV_NEXT_CSID struct seg6_flavors_info { /* Flavor operations */ @@ -411,9 +415,72 @@ static int end_next_csid_core(struct sk_buff *skb, struct seg6_local_lwt *slwt) return input_action_end_finish(skb, slwt); } +static int input_action_end_x_finish(struct sk_buff *skb, + struct seg6_local_lwt *slwt) +{ + seg6_lookup_nexthop(skb, &slwt->nh6, 0); + + return dst_input(skb); +} + +static int input_action_end_x_core(struct sk_buff *skb, + struct seg6_local_lwt *slwt) +{ + struct ipv6_sr_hdr *srh; + + srh = get_and_validate_srh(skb); + if (!srh) + goto drop; + + advance_nextseg(srh, &ipv6_hdr(skb)->daddr); + + return input_action_end_x_finish(skb, slwt); + +drop: + kfree_skb(skb); + return -EINVAL; +} + +static int end_x_next_csid_core(struct sk_buff *skb, + struct seg6_local_lwt *slwt) +{ + const struct seg6_flavors_info *finfo = &slwt->flv_info; + struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; + + if (seg6_next_csid_is_arg_zero(daddr, finfo)) + return input_action_end_x_core(skb, slwt); + + /* update DA */ + seg6_next_csid_advance_arg(daddr, finfo); + + return input_action_end_x_finish(skb, slwt); +} + static bool seg6_next_csid_enabled(__u32 fops) { - return fops & BIT(SEG6_LOCAL_FLV_OP_NEXT_CSID); + return fops & SEG6_F_LOCAL_FLV_NEXT_CSID; +} + +/* Processing of SRv6 End, End.X, and End.T behaviors can be extended through + * the flavors framework. These behaviors must report the subset of (flavor) + * operations they currently implement. In this way, if a user specifies a + * flavor combination that is not supported by a given End* behavior, the + * kernel refuses to instantiate the tunnel reporting the error. + */ +static int seg6_flv_supp_ops_by_action(int action, __u32 *fops) +{ + switch (action) { + case SEG6_LOCAL_ACTION_END: + *fops = SEG6_LOCAL_END_FLV_SUPP_OPS; + break; + case SEG6_LOCAL_ACTION_END_X: + *fops = SEG6_LOCAL_END_X_FLV_SUPP_OPS; + break; + default: + return -EOPNOTSUPP; + } + + return 0; } /* We describe the packet state in relation to the absence/presence of the SRH @@ -746,21 +813,14 @@ static int input_action_end(struct sk_buff *skb, struct seg6_local_lwt *slwt) /* regular endpoint, and forward to specified nexthop */ static int input_action_end_x(struct sk_buff *skb, struct seg6_local_lwt *slwt) { - struct ipv6_sr_hdr *srh; - - srh = get_and_validate_srh(skb); - if (!srh) - goto drop; - - advance_nextseg(srh, &ipv6_hdr(skb)->daddr); - - seg6_lookup_nexthop(skb, &slwt->nh6, 0); + const struct seg6_flavors_info *finfo = &slwt->flv_info; + __u32 fops = finfo->flv_ops; - return dst_input(skb); + /* check for the presence of NEXT-C-SID since it applies first */ + if (seg6_next_csid_enabled(fops)) + return end_x_next_csid_core(skb, slwt); -drop: - kfree_skb(skb); - return -EINVAL; + return input_action_end_x_core(skb, slwt); } static int input_action_end_t(struct sk_buff *skb, struct seg6_local_lwt *slwt) @@ -1404,13 +1464,14 @@ static struct seg6_action_desc seg6_action_table[] = { .action = SEG6_LOCAL_ACTION_END, .attrs = 0, .optattrs = SEG6_F_LOCAL_COUNTERS | - SEG6_F_ATTR(SEG6_LOCAL_FLAVORS), + SEG6_F_LOCAL_FLAVORS, .input = input_action_end, }, { .action = SEG6_LOCAL_ACTION_END_X, .attrs = SEG6_F_ATTR(SEG6_LOCAL_NH6), - .optattrs = SEG6_F_LOCAL_COUNTERS, + .optattrs = SEG6_F_LOCAL_COUNTERS | + SEG6_F_LOCAL_FLAVORS, .input = input_action_end_x, }, { @@ -2070,7 +2131,8 @@ static int parse_nla_flavors(struct nlattr **attrs, struct seg6_local_lwt *slwt, { struct seg6_flavors_info *finfo = &slwt->flv_info; struct nlattr *tb[SEG6_LOCAL_FLV_MAX + 1]; - unsigned long fops; + int action = slwt->action; + __u32 fops, supp_fops; int rc; rc = nla_parse_nested_deprecated(tb, SEG6_LOCAL_FLV_MAX, @@ -2086,7 +2148,8 @@ static int parse_nla_flavors(struct nlattr **attrs, struct seg6_local_lwt *slwt, return -EINVAL; fops = nla_get_u32(tb[SEG6_LOCAL_FLV_OPERATION]); - if (fops & ~SEG6_LOCAL_FLV_SUPP_OPS) { + rc = seg6_flv_supp_ops_by_action(action, &supp_fops); + if (rc < 0 || (fops & ~supp_fops)) { NL_SET_ERR_MSG(extack, "Unsupported Flavor operation(s)"); return -EOPNOTSUPP; } @@ -2618,6 +2681,11 @@ int __init seg6_local_init(void) */ BUILD_BUG_ON(SEG6_LOCAL_MAX + 1 > BITS_PER_TYPE(unsigned long)); + /* Check whether the number of defined flavors exceeds the maximum + * allowed value. + */ + BUILD_BUG_ON(SEG6_LOCAL_FLV_OP_MAX + 1 > BITS_PER_TYPE(__u32)); + /* If the default NEXT-C-SID Locator-Block/Node Function lengths (in * bits) have been changed with invalid values, kernel build stops * here. diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1ea01b0d9be3..ebc6ae47cfea 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -420,7 +420,7 @@ try_again: ip6_datagram_recv_common_ctl(sk, msg, skb); if (is_udp4) { - if (inet->cmsg_flags) + if (inet_cmsg_flags(inet)) ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off); } else { diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index f9073bc7281f..9a2a9ed3ba47 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -552,7 +552,7 @@ static int l2tp_ip_recvmsg(struct sock *sk, struct msghdr *msg, memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); } - if (inet->cmsg_flags) + if (inet_cmsg_flags(inet)) ip_cmsg_recv(msg, skb); if (flags & MSG_TRUNC) copied = skb->len; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 5692daf57a4d..c75d9d88a053 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -9,6 +9,7 @@ #include <linux/inet.h> #include <linux/kernel.h> #include <net/tcp.h> +#include <net/inet_common.h> #include <net/netns/generic.h> #include <net/mptcp.h> #include <net/genetlink.h> @@ -1005,8 +1006,7 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, bool is_ipv6 = sk->sk_family == AF_INET6; int addrlen = sizeof(struct sockaddr_in); struct sockaddr_storage addr; - struct socket *ssock; - struct sock *newsk; + struct sock *newsk, *ssk; int backlog = 1024; int err; @@ -1032,28 +1032,32 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, &mptcp_keys[is_ipv6]); lock_sock(newsk); - ssock = __mptcp_nmpc_socket(mptcp_sk(newsk)); + ssk = __mptcp_nmpc_sk(mptcp_sk(newsk)); release_sock(newsk); - if (IS_ERR(ssock)) - return PTR_ERR(ssock); + if (IS_ERR(ssk)) + return PTR_ERR(ssk); mptcp_info2sockaddr(&entry->addr, &addr, entry->addr.family); #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (entry->addr.family == AF_INET6) addrlen = sizeof(struct sockaddr_in6); #endif - err = kernel_bind(ssock, (struct sockaddr *)&addr, addrlen); + if (ssk->sk_family == AF_INET) + err = inet_bind_sk(ssk, (struct sockaddr *)&addr, addrlen); +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + else if (ssk->sk_family == AF_INET6) + err = inet6_bind_sk(ssk, (struct sockaddr *)&addr, addrlen); +#endif if (err) return err; inet_sk_state_store(newsk, TCP_LISTEN); - err = kernel_listen(ssock, backlog); - if (err) - return err; - - mptcp_event_pm_listener(ssock->sk, MPTCP_EVENT_LISTENER_CREATED); - - return 0; + lock_sock(ssk); + err = __inet_listen_sk(ssk, backlog); + if (!err) + mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED); + release_sock(ssk); + return err; } int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 48e649fe2360..6019a3cf1625 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -92,7 +92,6 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) msk->scaling_ratio = tcp_sk(ssock->sk)->scaling_ratio; WRITE_ONCE(msk->first, ssock->sk); - WRITE_ONCE(msk->subflow, ssock); subflow = mptcp_subflow_ctx(ssock->sk); list_add(&subflow->node, &msk->conn_list); sock_hold(ssock->sk); @@ -102,6 +101,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) /* This is the first subflow, always with id 0 */ subflow->local_id_valid = 1; mptcp_sock_graft(msk->first, sk->sk_socket); + iput(SOCK_INODE(ssock)); return 0; } @@ -109,7 +109,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) /* If the MPC handshake is not started, returns the first subflow, * eventually allocating it. */ -struct socket *__mptcp_nmpc_socket(struct mptcp_sock *msk) +struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; int ret; @@ -117,10 +117,7 @@ struct socket *__mptcp_nmpc_socket(struct mptcp_sock *msk) if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) return ERR_PTR(-EINVAL); - if (!msk->subflow) { - if (msk->first) - return ERR_PTR(-EINVAL); - + if (!msk->first) { ret = __mptcp_socket_create(msk); if (ret) return ERR_PTR(ret); @@ -128,7 +125,7 @@ struct socket *__mptcp_nmpc_socket(struct mptcp_sock *msk) mptcp_sockopt_sync(msk, msk->first); } - return msk->subflow; + return msk->first; } static void mptcp_drop(struct sock *sk, struct sk_buff *skb) @@ -1643,7 +1640,6 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, { unsigned int saved_flags = msg->msg_flags; struct mptcp_sock *msk = mptcp_sk(sk); - struct socket *ssock; struct sock *ssk; int ret; @@ -1654,9 +1650,9 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, * fastopen attempt, no need to check for additional subflow status. */ if (msg->msg_flags & MSG_FASTOPEN) { - ssock = __mptcp_nmpc_socket(msk); - if (IS_ERR(ssock)) - return PTR_ERR(ssock); + ssk = __mptcp_nmpc_sk(msk); + if (IS_ERR(ssk)) + return PTR_ERR(ssk); } if (!msk->first) return -EINVAL; @@ -1690,7 +1686,7 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, if (!mptcp_disconnect(sk, 0)) sk->sk_socket->state = SS_UNCONNECTED; } - inet_sk(sk)->defer_connect = 0; + inet_clear_bit(DEFER_CONNECT, sk); return ret; } @@ -1708,7 +1704,8 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) lock_sock(sk); - if (unlikely(inet_sk(sk)->defer_connect || msg->msg_flags & MSG_FASTOPEN)) { + if (unlikely(inet_test_bit(DEFER_CONNECT, sk) || + msg->msg_flags & MSG_FASTOPEN)) { int copied_syn = 0; ret = mptcp_sendmsg_fastopen(sk, msg, len, &copied_syn); @@ -2242,14 +2239,6 @@ static struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk) return min_stale_count > 1 ? backup : NULL; } -static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk) -{ - if (msk->subflow) { - iput(SOCK_INODE(msk->subflow)); - WRITE_ONCE(msk->subflow, NULL); - } -} - bool __mptcp_retransmit_pending_data(struct sock *sk) { struct mptcp_data_frag *cur, *rtx_head; @@ -2328,7 +2317,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, goto out_release; } - dispose_it = !msk->subflow || ssk != msk->subflow->sk; + dispose_it = msk->free_first || ssk != msk->first; if (dispose_it) list_del(&subflow->node); @@ -2349,7 +2338,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, * disconnect should never fail */ WARN_ON_ONCE(tcp_disconnect(ssk, 0)); - msk->subflow->state = SS_UNCONNECTED; mptcp_subflow_ctx_reset(subflow); release_sock(ssk); @@ -2662,7 +2650,7 @@ unlock: sock_put(sk); } -static int __mptcp_init_sock(struct sock *sk) +static void __mptcp_init_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -2689,8 +2677,6 @@ static int __mptcp_init_sock(struct sock *sk) /* re-use the csk retrans timer for MPTCP-level retrans */ timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0); timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0); - - return 0; } static void mptcp_ca_reset(struct sock *sk) @@ -2708,11 +2694,8 @@ static void mptcp_ca_reset(struct sock *sk) static int mptcp_init_sock(struct sock *sk) { struct net *net = sock_net(sk); - int ret; - ret = __mptcp_init_sock(sk); - if (ret) - return ret; + __mptcp_init_sock(sk); if (!mptcp_is_enabled(net)) return -ENOPROTOOPT; @@ -3110,7 +3093,6 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, msk = mptcp_sk(nsk); msk->local_key = subflow_req->local_key; msk->token = subflow_req->token; - WRITE_ONCE(msk->subflow, NULL); msk->in_accept_queue = 1; WRITE_ONCE(msk->fully_established, false); if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD) @@ -3174,25 +3156,17 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); } -static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, +static struct sock *mptcp_accept(struct sock *ssk, int flags, int *err, bool kern) { - struct mptcp_sock *msk = mptcp_sk(sk); - struct socket *listener; struct sock *newsk; - listener = READ_ONCE(msk->subflow); - if (WARN_ON_ONCE(!listener)) { - *err = -EINVAL; - return NULL; - } - - pr_debug("msk=%p, listener=%p", msk, mptcp_subflow_ctx(listener->sk)); - newsk = inet_csk_accept(listener->sk, flags, err, kern); + pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk)); + newsk = inet_csk_accept(ssk, flags, err, kern); if (!newsk) return NULL; - pr_debug("msk=%p, subflow is mptcp=%d", msk, sk_is_mptcp(newsk)); + pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk)); if (sk_is_mptcp(newsk)) { struct mptcp_subflow_context *subflow; struct sock *new_mptcp_sock; @@ -3209,9 +3183,9 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, } newsk = new_mptcp_sock; - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK); + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK); } else { - MPTCP_INC_STATS(sock_net(sk), + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); } @@ -3252,10 +3226,8 @@ static void mptcp_destroy(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - /* clears msk->subflow, allowing the following to close - * even the initial subflow - */ - mptcp_dispose_initial_subflow(msk); + /* allow the following to close even the initial subflow */ + msk->free_first = 1; mptcp_destroy_common(msk, 0); sk_sockets_allocated_dec(sk); } @@ -3405,14 +3377,12 @@ static void mptcp_unhash(struct sock *sk) static int mptcp_get_port(struct sock *sk, unsigned short snum) { struct mptcp_sock *msk = mptcp_sk(sk); - struct socket *ssock; - ssock = msk->subflow; - pr_debug("msk=%p, subflow=%p", msk, ssock); - if (WARN_ON_ONCE(!ssock)) + pr_debug("msk=%p, ssk=%p", msk, msk->first); + if (WARN_ON_ONCE(!msk->first)) return -EINVAL; - return inet_csk_get_port(ssock->sk, snum); + return inet_csk_get_port(msk->first, snum); } void mptcp_finish_connect(struct sock *ssk) @@ -3587,25 +3557,24 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); - struct socket *ssock; int err = -EINVAL; + struct sock *ssk; - ssock = __mptcp_nmpc_socket(msk); - if (IS_ERR(ssock)) - return PTR_ERR(ssock); + ssk = __mptcp_nmpc_sk(msk); + if (IS_ERR(ssk)) + return PTR_ERR(ssk); - mptcp_token_destroy(msk); inet_sk_state_store(sk, TCP_SYN_SENT); - subflow = mptcp_subflow_ctx(ssock->sk); + subflow = mptcp_subflow_ctx(ssk); #ifdef CONFIG_TCP_MD5SIG /* no MPTCP if MD5SIG is enabled on this socket or we may run out of * TCP option space. */ - if (rcu_access_pointer(tcp_sk(ssock->sk)->md5sig_info)) + if (rcu_access_pointer(tcp_sk(ssk)->md5sig_info)) mptcp_subflow_early_fallback(msk, subflow); #endif - if (subflow->request_mptcp && mptcp_token_new_connect(ssock->sk)) { - MPTCP_INC_STATS(sock_net(ssock->sk), MPTCP_MIB_TOKENFALLBACKINIT); + if (subflow->request_mptcp && mptcp_token_new_connect(ssk)) { + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_TOKENFALLBACKINIT); mptcp_subflow_early_fallback(msk, subflow); } if (likely(!__mptcp_check_fallback(msk))) @@ -3614,25 +3583,42 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* if reaching here via the fastopen/sendmsg path, the caller already * acquired the subflow socket lock, too. */ - if (msk->fastopening) - err = __inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK, 1); - else - err = inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK); - inet_sk(sk)->defer_connect = inet_sk(ssock->sk)->defer_connect; + if (!msk->fastopening) + lock_sock(ssk); + + /* the following mirrors closely a very small chunk of code from + * __inet_stream_connect() + */ + if (ssk->sk_state != TCP_CLOSE) + goto out; + + if (BPF_CGROUP_PRE_CONNECT_ENABLED(ssk)) { + err = ssk->sk_prot->pre_connect(ssk, uaddr, addr_len); + if (err) + goto out; + } + + err = ssk->sk_prot->connect(ssk, uaddr, addr_len); + if (err < 0) + goto out; + + inet_assign_bit(DEFER_CONNECT, sk, inet_test_bit(DEFER_CONNECT, ssk)); + +out: + if (!msk->fastopening) + release_sock(ssk); /* on successful connect, the msk state will be moved to established by * subflow_finish_connect() */ - if (unlikely(err && err != -EINPROGRESS)) { - inet_sk_state_store(sk, inet_sk_state_load(ssock->sk)); + if (unlikely(err)) { + /* avoid leaving a dangling token in an unconnected socket */ + mptcp_token_destroy(msk); + inet_sk_state_store(sk, TCP_CLOSE); return err; } - mptcp_copy_inaddrs(sk, ssock->sk); - - /* silence EINPROGRESS and let the caller inet_stream_connect - * handle the connection in progress - */ + mptcp_copy_inaddrs(sk, ssk); return 0; } @@ -3673,22 +3659,27 @@ static struct proto mptcp_prot = { static int mptcp_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct mptcp_sock *msk = mptcp_sk(sock->sk); - struct socket *ssock; - int err; + struct sock *ssk, *sk = sock->sk; + int err = -EINVAL; - lock_sock(sock->sk); - ssock = __mptcp_nmpc_socket(msk); - if (IS_ERR(ssock)) { - err = PTR_ERR(ssock); + lock_sock(sk); + ssk = __mptcp_nmpc_sk(msk); + if (IS_ERR(ssk)) { + err = PTR_ERR(ssk); goto unlock; } - err = READ_ONCE(ssock->ops)->bind(ssock, uaddr, addr_len); + if (sk->sk_family == AF_INET) + err = inet_bind_sk(ssk, uaddr, addr_len); +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + else if (sk->sk_family == AF_INET6) + err = inet6_bind_sk(ssk, uaddr, addr_len); +#endif if (!err) - mptcp_copy_inaddrs(sock->sk, ssock->sk); + mptcp_copy_inaddrs(sk, ssk); unlock: - release_sock(sock->sk); + release_sock(sk); return err; } @@ -3696,7 +3687,7 @@ static int mptcp_listen(struct socket *sock, int backlog) { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct sock *sk = sock->sk; - struct socket *ssock; + struct sock *ssk; int err; pr_debug("msk=%p", msk); @@ -3707,22 +3698,24 @@ static int mptcp_listen(struct socket *sock, int backlog) if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) goto unlock; - ssock = __mptcp_nmpc_socket(msk); - if (IS_ERR(ssock)) { - err = PTR_ERR(ssock); + ssk = __mptcp_nmpc_sk(msk); + if (IS_ERR(ssk)) { + err = PTR_ERR(ssk); goto unlock; } - mptcp_token_destroy(msk); inet_sk_state_store(sk, TCP_LISTEN); sock_set_flag(sk, SOCK_RCU_FREE); - err = READ_ONCE(ssock->ops)->listen(ssock, backlog); - inet_sk_state_store(sk, inet_sk_state_load(ssock->sk)); + lock_sock(ssk); + err = __inet_listen_sk(ssk, backlog); + release_sock(ssk); + inet_sk_state_store(sk, inet_sk_state_load(ssk)); + if (!err) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - mptcp_copy_inaddrs(sk, ssock->sk); - mptcp_event_pm_listener(ssock->sk, MPTCP_EVENT_LISTENER_CREATED); + mptcp_copy_inaddrs(sk, ssk); + mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED); } unlock: @@ -3734,8 +3727,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { struct mptcp_sock *msk = mptcp_sk(sock->sk); - struct socket *ssock; - struct sock *newsk; + struct sock *ssk, *newsk; int err; pr_debug("msk=%p", msk); @@ -3743,11 +3735,11 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, /* Buggy applications can call accept on socket states other then LISTEN * but no need to allocate the first subflow just to error out. */ - ssock = READ_ONCE(msk->subflow); - if (!ssock) + ssk = READ_ONCE(msk->first); + if (!ssk) return -EINVAL; - newsk = mptcp_accept(sock->sk, flags, &err, kern); + newsk = mptcp_accept(ssk, flags, &err, kern); if (!newsk) return err; @@ -3774,11 +3766,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, /* Do late cleanup for the first subflow as necessary. Also * deal with bad peers not doing a complete shutdown. */ - if (msk->first && - unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) { + if (unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) { __mptcp_close_ssk(newsk, msk->first, mptcp_subflow_ctx(msk->first), 0); - if (unlikely(list_empty(&msk->conn_list))) + if (unlikely(list_is_singular(&msk->conn_list))) inet_sk_state_store(newsk, TCP_CLOSE); } } @@ -3817,12 +3808,12 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, state = inet_sk_state_load(sk); pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags); if (state == TCP_LISTEN) { - struct socket *ssock = READ_ONCE(msk->subflow); + struct sock *ssk = READ_ONCE(msk->first); - if (WARN_ON_ONCE(!ssock || !ssock->sk)) + if (WARN_ON_ONCE(!ssk)) return 0; - return inet_csk_listen_poll(ssock->sk); + return inet_csk_listen_poll(ssk); } shutdown = READ_ONCE(sk->sk_shutdown); @@ -3837,7 +3828,8 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, mask |= EPOLLOUT | EPOLLWRNORM; else mask |= mptcp_check_writeable(msk); - } else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) { + } else if (state == TCP_SYN_SENT && + inet_test_bit(DEFER_CONNECT, sk)) { /* cf tcp_poll() note about TFO */ mask |= EPOLLOUT | EPOLLWRNORM; } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 79fc5cdb67bc..38c7ea013361 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -299,7 +299,8 @@ struct mptcp_sock { cork:1, nodelay:1, fastopening:1, - in_accept_queue:1; + in_accept_queue:1, + free_first:1; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -308,12 +309,10 @@ struct mptcp_sock { struct list_head rtx_queue; struct mptcp_data_frag *first_pending; struct list_head join_list; - struct socket *subflow; /* outgoing connect/listener/!mp_capable - * The mptcp ops can safely dereference, using suitable - * ONCE annotation, the subflow outside the socket - * lock as such sock is freed after close(). - */ - struct sock *first; + struct sock *first; /* The mptcp ops can safely dereference, using suitable + * ONCE annotation, the subflow outside the socket + * lock as such sock is freed after close(). + */ struct mptcp_pm_data pm; struct { u32 space; /* bytes copied in last measurement window */ @@ -640,7 +639,7 @@ void __mptcp_subflow_send_ack(struct sock *ssk); void mptcp_subflow_reset(struct sock *ssk); void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk); void mptcp_sock_graft(struct sock *sk, struct socket *parent); -struct socket *__mptcp_nmpc_socket(struct mptcp_sock *msk); +struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk); bool __mptcp_close(struct sock *sk, long timeout); void mptcp_cancel_work(struct sock *sk); void __mptcp_unaccepted_force_close(struct sock *sk); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index a3f1fe810cc9..8260202c0066 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -292,7 +292,7 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = (struct sock *)msk; - struct socket *ssock; + struct sock *ssk; int ret; switch (optname) { @@ -301,22 +301,22 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname, case SO_BINDTODEVICE: case SO_BINDTOIFINDEX: lock_sock(sk); - ssock = __mptcp_nmpc_socket(msk); - if (IS_ERR(ssock)) { + ssk = __mptcp_nmpc_sk(msk); + if (IS_ERR(ssk)) { release_sock(sk); - return PTR_ERR(ssock); + return PTR_ERR(ssk); } - ret = sock_setsockopt(ssock, SOL_SOCKET, optname, optval, optlen); + ret = sk_setsockopt(ssk, SOL_SOCKET, optname, optval, optlen); if (ret == 0) { if (optname == SO_REUSEPORT) - sk->sk_reuseport = ssock->sk->sk_reuseport; + sk->sk_reuseport = ssk->sk_reuseport; else if (optname == SO_REUSEADDR) - sk->sk_reuse = ssock->sk->sk_reuse; + sk->sk_reuse = ssk->sk_reuse; else if (optname == SO_BINDTODEVICE) - sk->sk_bound_dev_if = ssock->sk->sk_bound_dev_if; + sk->sk_bound_dev_if = ssk->sk_bound_dev_if; else if (optname == SO_BINDTOIFINDEX) - sk->sk_bound_dev_if = ssock->sk->sk_bound_dev_if; + sk->sk_bound_dev_if = ssk->sk_bound_dev_if; } release_sock(sk); return ret; @@ -390,20 +390,20 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname, { struct sock *sk = (struct sock *)msk; int ret = -EOPNOTSUPP; - struct socket *ssock; + struct sock *ssk; switch (optname) { case IPV6_V6ONLY: case IPV6_TRANSPARENT: case IPV6_FREEBIND: lock_sock(sk); - ssock = __mptcp_nmpc_socket(msk); - if (IS_ERR(ssock)) { + ssk = __mptcp_nmpc_sk(msk); + if (IS_ERR(ssk)) { release_sock(sk); - return PTR_ERR(ssock); + return PTR_ERR(ssk); } - ret = tcp_setsockopt(ssock->sk, SOL_IPV6, optname, optval, optlen); + ret = tcp_setsockopt(ssk, SOL_IPV6, optname, optval, optlen); if (ret != 0) { release_sock(sk); return ret; @@ -413,13 +413,15 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname, switch (optname) { case IPV6_V6ONLY: - sk->sk_ipv6only = ssock->sk->sk_ipv6only; + sk->sk_ipv6only = ssk->sk_ipv6only; break; case IPV6_TRANSPARENT: - inet_sk(sk)->transparent = inet_sk(ssock->sk)->transparent; + inet_assign_bit(TRANSPARENT, sk, + inet_test_bit(TRANSPARENT, ssk)); break; case IPV6_FREEBIND: - inet_sk(sk)->freebind = inet_sk(ssock->sk)->freebind; + inet_assign_bit(FREEBIND, sk, + inet_test_bit(FREEBIND, ssk)); break; } @@ -684,8 +686,7 @@ static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int o sockptr_t optval, unsigned int optlen) { struct sock *sk = (struct sock *)msk; - struct inet_sock *issk; - struct socket *ssock; + struct sock *ssk; int err; err = ip_setsockopt(sk, SOL_IP, optname, optval, optlen); @@ -694,20 +695,19 @@ static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int o lock_sock(sk); - ssock = __mptcp_nmpc_socket(msk); - if (IS_ERR(ssock)) { + ssk = __mptcp_nmpc_sk(msk); + if (IS_ERR(ssk)) { release_sock(sk); - return PTR_ERR(ssock); + return PTR_ERR(ssk); } - issk = inet_sk(ssock->sk); - switch (optname) { case IP_FREEBIND: - issk->freebind = inet_sk(sk)->freebind; + inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk)); break; case IP_TRANSPARENT: - issk->transparent = inet_sk(sk)->transparent; + inet_assign_bit(TRANSPARENT, ssk, + inet_test_bit(TRANSPARENT, sk)); break; default: release_sock(sk); @@ -763,18 +763,18 @@ static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int sockptr_t optval, unsigned int optlen) { struct sock *sk = (struct sock *)msk; - struct socket *sock; + struct sock *ssk; int ret; /* Limit to first subflow, before the connection establishment */ lock_sock(sk); - sock = __mptcp_nmpc_socket(msk); - if (IS_ERR(sock)) { - ret = PTR_ERR(sock); + ssk = __mptcp_nmpc_sk(msk); + if (IS_ERR(ssk)) { + ret = PTR_ERR(ssk); goto unlock; } - ret = tcp_setsockopt(sock->sk, level, optname, optval, optlen); + ret = tcp_setsockopt(ssk, level, optname, optval, optlen); unlock: release_sock(sk); @@ -864,9 +864,8 @@ static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int char __user *optval, int __user *optlen) { struct sock *sk = (struct sock *)msk; - struct socket *ssock; - int ret; struct sock *ssk; + int ret; lock_sock(sk); ssk = msk->first; @@ -875,13 +874,13 @@ static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int goto out; } - ssock = __mptcp_nmpc_socket(msk); - if (IS_ERR(ssock)) { - ret = PTR_ERR(ssock); + ssk = __mptcp_nmpc_sk(msk); + if (IS_ERR(ssk)) { + ret = PTR_ERR(ssk); goto out; } - ret = tcp_getsockopt(ssock->sk, level, optname, optval, optlen); + ret = tcp_getsockopt(ssk, level, optname, optval, optlen); out: release_sock(sk); @@ -1441,8 +1440,8 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) __tcp_sock_set_cork(ssk, !!msk->cork); __tcp_sock_set_nodelay(ssk, !!msk->nodelay); - inet_sk(ssk)->transparent = inet_sk(sk)->transparent; - inet_sk(ssk)->freebind = inet_sk(sk)->freebind; + inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk)); + inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk)); } static void __mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk) diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index d27f4eccce6d..a3a6753a1db7 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -563,7 +563,7 @@ int ncsi_send_netlink_timeout(struct ncsi_request *nr, int ncsi_send_netlink_err(struct net_device *dev, u32 snd_seq, u32 snd_portid, - struct nlmsghdr *nlhdr, + const struct nlmsghdr *nlhdr, int err) { struct nlmsghdr *nlh; diff --git a/net/ncsi/ncsi-netlink.h b/net/ncsi/ncsi-netlink.h index 39a1a9d7bf77..747767ea0aae 100644 --- a/net/ncsi/ncsi-netlink.h +++ b/net/ncsi/ncsi-netlink.h @@ -19,7 +19,7 @@ int ncsi_send_netlink_timeout(struct ncsi_request *nr, int ncsi_send_netlink_err(struct net_device *dev, u32 snd_seq, u32 snd_portid, - struct nlmsghdr *nlhdr, + const struct nlmsghdr *nlhdr, int err); #endif /* __NCSI_NETLINK_H__ */ diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index cb83ca506c5c..3230506ae3ff 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1346,7 +1346,7 @@ ip_vs_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *stat if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { - if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag) + if (sk->sk_family == PF_INET && inet_test_bit(NODEFRAG, sk)) return NF_ACCEPT; } @@ -1946,7 +1946,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { - if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag) + if (sk->sk_family == PF_INET && inet_test_bit(NODEFRAG, sk)) return NF_ACCEPT; } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 264f2f87a437..da5af28ff57b 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1297,11 +1297,9 @@ static void set_sock_size(struct sock *sk, int mode, int val) */ static void set_mcast_loop(struct sock *sk, u_char loop) { - struct inet_sock *inet = inet_sk(sk); - /* setsockopt(sock, SOL_IP, IP_MULTICAST_LOOP, &loop, sizeof(loop)); */ lock_sock(sk); - inet->mc_loop = loop ? 1 : 0; + inet_assign_bit(MC_LOOP, sk, loop); #ifdef CONFIG_IP_VS_IPV6 if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 96c605e45235..642b9d382fb4 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -84,7 +84,7 @@ struct listeners { static inline int netlink_is_kernel(struct sock *sk) { - return nlk_sk(sk)->flags & NETLINK_F_KERNEL_SOCKET; + return nlk_test_bit(KERNEL_SOCKET, sk); } struct netlink_table *nl_table __read_mostly; @@ -349,9 +349,7 @@ static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src, static void netlink_overrun(struct sock *sk) { - struct netlink_sock *nlk = nlk_sk(sk); - - if (!(nlk->flags & NETLINK_F_RECV_NO_ENOBUFS)) { + if (!nlk_test_bit(RECV_NO_ENOBUFS, sk)) { if (!test_and_set_bit(NETLINK_S_CONGESTED, &nlk_sk(sk)->state)) { sk->sk_err = ENOBUFS; @@ -1407,9 +1405,7 @@ EXPORT_SYMBOL_GPL(netlink_has_listeners); bool netlink_strict_get_check(struct sk_buff *skb) { - const struct netlink_sock *nlk = nlk_sk(NETLINK_CB(skb).sk); - - return nlk->flags & NETLINK_F_STRICT_CHK; + return nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); } EXPORT_SYMBOL_GPL(netlink_strict_get_check); @@ -1455,7 +1451,7 @@ static void do_one_broadcast(struct sock *sk, return; if (!net_eq(sock_net(sk), p->net)) { - if (!(nlk->flags & NETLINK_F_LISTEN_ALL_NSID)) + if (!nlk_test_bit(LISTEN_ALL_NSID, sk)) return; if (!peernet_has_id(sock_net(sk), p->net)) @@ -1488,7 +1484,7 @@ static void do_one_broadcast(struct sock *sk, netlink_overrun(sk); /* Clone failed. Notify ALL listeners. */ p->failure = 1; - if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR) + if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) p->delivery_failure = 1; goto out; } @@ -1510,7 +1506,7 @@ static void do_one_broadcast(struct sock *sk, val = netlink_broadcast_deliver(sk, p->skb2); if (val < 0) { netlink_overrun(sk); - if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR) + if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) p->delivery_failure = 1; } else { p->congested |= val; @@ -1604,7 +1600,7 @@ static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) !test_bit(p->group - 1, nlk->groups)) goto out; - if (p->code == ENOBUFS && nlk->flags & NETLINK_F_RECV_NO_ENOBUFS) { + if (p->code == ENOBUFS && nlk_test_bit(RECV_NO_ENOBUFS, sk)) { ret = 1; goto out; } @@ -1668,7 +1664,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); unsigned int val = 0; - int err; + int nr = -1; if (level != SOL_NETLINK) return -ENOPROTOOPT; @@ -1679,14 +1675,12 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, switch (optname) { case NETLINK_PKTINFO: - if (val) - nlk->flags |= NETLINK_F_RECV_PKTINFO; - else - nlk->flags &= ~NETLINK_F_RECV_PKTINFO; - err = 0; + nr = NETLINK_F_RECV_PKTINFO; break; case NETLINK_ADD_MEMBERSHIP: case NETLINK_DROP_MEMBERSHIP: { + int err; + if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); @@ -1706,61 +1700,38 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind) nlk->netlink_unbind(sock_net(sk), val); - err = 0; break; } case NETLINK_BROADCAST_ERROR: - if (val) - nlk->flags |= NETLINK_F_BROADCAST_SEND_ERROR; - else - nlk->flags &= ~NETLINK_F_BROADCAST_SEND_ERROR; - err = 0; + nr = NETLINK_F_BROADCAST_SEND_ERROR; break; case NETLINK_NO_ENOBUFS: + assign_bit(NETLINK_F_RECV_NO_ENOBUFS, &nlk->flags, val); if (val) { - nlk->flags |= NETLINK_F_RECV_NO_ENOBUFS; clear_bit(NETLINK_S_CONGESTED, &nlk->state); wake_up_interruptible(&nlk->wait); - } else { - nlk->flags &= ~NETLINK_F_RECV_NO_ENOBUFS; } - err = 0; break; case NETLINK_LISTEN_ALL_NSID: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST)) return -EPERM; - - if (val) - nlk->flags |= NETLINK_F_LISTEN_ALL_NSID; - else - nlk->flags &= ~NETLINK_F_LISTEN_ALL_NSID; - err = 0; + nr = NETLINK_F_LISTEN_ALL_NSID; break; case NETLINK_CAP_ACK: - if (val) - nlk->flags |= NETLINK_F_CAP_ACK; - else - nlk->flags &= ~NETLINK_F_CAP_ACK; - err = 0; + nr = NETLINK_F_CAP_ACK; break; case NETLINK_EXT_ACK: - if (val) - nlk->flags |= NETLINK_F_EXT_ACK; - else - nlk->flags &= ~NETLINK_F_EXT_ACK; - err = 0; + nr = NETLINK_F_EXT_ACK; break; case NETLINK_GET_STRICT_CHK: - if (val) - nlk->flags |= NETLINK_F_STRICT_CHK; - else - nlk->flags &= ~NETLINK_F_STRICT_CHK; - err = 0; + nr = NETLINK_F_STRICT_CHK; break; default: - err = -ENOPROTOOPT; + return -ENOPROTOOPT; } - return err; + if (nr >= 0) + assign_bit(nr, &nlk->flags, val); + return 0; } static int netlink_getsockopt(struct socket *sock, int level, int optname, @@ -1827,7 +1798,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, return -EINVAL; len = sizeof(int); - val = nlk->flags & flag ? 1 : 0; + val = test_bit(flag, &nlk->flags); if (put_user(len, optlen) || copy_to_user(optval, &val, len)) @@ -2004,9 +1975,9 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, msg->msg_namelen = sizeof(*addr); } - if (nlk->flags & NETLINK_F_RECV_PKTINFO) + if (nlk_test_bit(RECV_PKTINFO, sk)) netlink_cmsg_recv_pktinfo(msg, skb); - if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID) + if (nlk_test_bit(LISTEN_ALL_NSID, sk)) netlink_cmsg_listen_all_nsid(sk, msg, skb); memset(&scm, 0, sizeof(scm)); @@ -2083,7 +2054,7 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module, goto out_sock_release; nlk = nlk_sk(sk); - nlk->flags |= NETLINK_F_KERNEL_SOCKET; + set_bit(NETLINK_F_KERNEL_SOCKET, &nlk->flags); netlink_table_grab(); if (!nl_table[unit].registered) { @@ -2218,7 +2189,7 @@ static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb, nl_dump_check_consistent(cb, nlh); memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, sizeof(nlk->dump_done_errno)); - if (extack->_msg && nlk->flags & NETLINK_F_EXT_ACK) { + if (extack->_msg && test_bit(NETLINK_F_EXT_ACK, &nlk->flags)) { nlh->nlmsg_flags |= NLM_F_ACK_TLVS; if (!nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg)) nlmsg_end(skb, nlh); @@ -2347,8 +2318,8 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *control) { - struct netlink_sock *nlk, *nlk2; struct netlink_callback *cb; + struct netlink_sock *nlk; struct sock *sk; int ret; @@ -2383,8 +2354,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, cb->min_dump_alloc = control->min_dump_alloc; cb->skb = skb; - nlk2 = nlk_sk(NETLINK_CB(skb).sk); - cb->strict_check = !!(nlk2->flags & NETLINK_F_STRICT_CHK); + cb->strict_check = nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); if (control->start) { cb->extack = control->extack; @@ -2428,7 +2398,7 @@ netlink_ack_tlv_len(struct netlink_sock *nlk, int err, { size_t tlvlen; - if (!extack || !(nlk->flags & NETLINK_F_EXT_ACK)) + if (!extack || !test_bit(NETLINK_F_EXT_ACK, &nlk->flags)) return 0; tlvlen = 0; @@ -2500,7 +2470,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, * requests to cap the error message, and get extra error data if * requested. */ - if (err && !(nlk->flags & NETLINK_F_CAP_ACK)) + if (err && !test_bit(NETLINK_F_CAP_ACK, &nlk->flags)) payload += nlmsg_len(nlh); else flags |= NLM_F_CAPPED; diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index fd424cd63f31..2145979b9986 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -8,14 +8,16 @@ #include <net/sock.h> /* flags */ -#define NETLINK_F_KERNEL_SOCKET 0x1 -#define NETLINK_F_RECV_PKTINFO 0x2 -#define NETLINK_F_BROADCAST_SEND_ERROR 0x4 -#define NETLINK_F_RECV_NO_ENOBUFS 0x8 -#define NETLINK_F_LISTEN_ALL_NSID 0x10 -#define NETLINK_F_CAP_ACK 0x20 -#define NETLINK_F_EXT_ACK 0x40 -#define NETLINK_F_STRICT_CHK 0x80 +enum { + NETLINK_F_KERNEL_SOCKET, + NETLINK_F_RECV_PKTINFO, + NETLINK_F_BROADCAST_SEND_ERROR, + NETLINK_F_RECV_NO_ENOBUFS, + NETLINK_F_LISTEN_ALL_NSID, + NETLINK_F_CAP_ACK, + NETLINK_F_EXT_ACK, + NETLINK_F_STRICT_CHK, +}; #define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8) #define NLGRPLONGS(x) (NLGRPSZ(x)/sizeof(unsigned long)) @@ -23,10 +25,10 @@ struct netlink_sock { /* struct sock has to be the first member of netlink_sock */ struct sock sk; + unsigned long flags; u32 portid; u32 dst_portid; u32 dst_group; - u32 flags; u32 subscriptions; u32 ngroups; unsigned long *groups; @@ -56,6 +58,8 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk) return container_of(sk, struct netlink_sock, sk); } +#define nlk_test_bit(nr, sk) test_bit(NETLINK_F_##nr, &nlk_sk(sk)->flags) + struct netlink_table { struct rhashtable hash; struct hlist_head mc_list; diff --git a/net/netlink/diag.c b/net/netlink/diag.c index e4f21b1067bc..9c4f231be275 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -27,15 +27,15 @@ static int sk_diag_put_flags(struct sock *sk, struct sk_buff *skb) if (nlk->cb_running) flags |= NDIAG_FLAG_CB_RUNNING; - if (nlk->flags & NETLINK_F_RECV_PKTINFO) + if (nlk_test_bit(RECV_PKTINFO, sk)) flags |= NDIAG_FLAG_PKTINFO; - if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR) + if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) flags |= NDIAG_FLAG_BROADCAST_ERROR; - if (nlk->flags & NETLINK_F_RECV_NO_ENOBUFS) + if (nlk_test_bit(RECV_NO_ENOBUFS, sk)) flags |= NDIAG_FLAG_NO_ENOBUFS; - if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID) + if (nlk_test_bit(LISTEN_ALL_NSID, sk)) flags |= NDIAG_FLAG_LISTEN_ALL_NSID; - if (nlk->flags & NETLINK_F_CAP_ACK) + if (nlk_test_bit(CAP_ACK, sk)) flags |= NDIAG_FLAG_CAP_ACK; return nla_put_u32(skb, NETLINK_DIAG_FLAGS, flags); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 6bd2ce51271f..8315d31b53db 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -52,6 +52,18 @@ static void genl_unlock_all(void) up_write(&cb_lock); } +static void genl_op_lock(const struct genl_family *family) +{ + if (!family->parallel_ops) + genl_lock(); +} + +static void genl_op_unlock(const struct genl_family *family) +{ + if (!family->parallel_ops) + genl_unlock(); +} + static DEFINE_IDR(genl_fam_idr); /* @@ -832,64 +844,63 @@ static int genl_start(struct netlink_callback *cb) genl_family_rcv_msg_attrs_free(attrs); return -ENOMEM; } - info->family = ctx->family; info->op = *ops; - info->attrs = attrs; + info->info.family = ctx->family; + info->info.snd_seq = cb->nlh->nlmsg_seq; + info->info.snd_portid = NETLINK_CB(cb->skb).portid; + info->info.nlhdr = cb->nlh; + info->info.genlhdr = nlmsg_data(cb->nlh); + info->info.attrs = attrs; + genl_info_net_set(&info->info, sock_net(cb->skb->sk)); + info->info.extack = cb->extack; + memset(&info->info.user_ptr, 0, sizeof(info->info.user_ptr)); cb->data = info; if (ops->start) { - if (!ctx->family->parallel_ops) - genl_lock(); + genl_op_lock(ctx->family); rc = ops->start(cb); - if (!ctx->family->parallel_ops) - genl_unlock(); + genl_op_unlock(ctx->family); } if (rc) { - genl_family_rcv_msg_attrs_free(info->attrs); + genl_family_rcv_msg_attrs_free(info->info.attrs); genl_dumpit_info_free(info); cb->data = NULL; } return rc; } -static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +static int genl_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { - const struct genl_split_ops *ops = &genl_dumpit_info(cb)->op; + struct genl_dumpit_info *dump_info = cb->data; + const struct genl_split_ops *ops = &dump_info->op; + struct genl_info *info = &dump_info->info; int rc; - genl_lock(); + info->extack = cb->extack; + + genl_op_lock(info->family); rc = ops->dumpit(skb, cb); - genl_unlock(); + genl_op_unlock(info->family); return rc; } -static int genl_lock_done(struct netlink_callback *cb) +static int genl_done(struct netlink_callback *cb) { - const struct genl_dumpit_info *info = genl_dumpit_info(cb); - const struct genl_split_ops *ops = &info->op; + struct genl_dumpit_info *dump_info = cb->data; + const struct genl_split_ops *ops = &dump_info->op; + struct genl_info *info = &dump_info->info; int rc = 0; + info->extack = cb->extack; + if (ops->done) { - genl_lock(); + genl_op_lock(info->family); rc = ops->done(cb); - genl_unlock(); + genl_op_unlock(info->family); } genl_family_rcv_msg_attrs_free(info->attrs); - genl_dumpit_info_free(info); - return rc; -} - -static int genl_parallel_done(struct netlink_callback *cb) -{ - const struct genl_dumpit_info *info = genl_dumpit_info(cb); - const struct genl_split_ops *ops = &info->op; - int rc = 0; - - if (ops->done) - rc = ops->done(cb); - genl_family_rcv_msg_attrs_free(info->attrs); - genl_dumpit_info_free(info); + genl_dumpit_info_free(dump_info); return rc; } @@ -901,6 +912,14 @@ static int genl_family_rcv_msg_dumpit(const struct genl_family *family, int hdrlen, struct net *net) { struct genl_start_context ctx; + struct netlink_dump_control c = { + .module = family->module, + .data = &ctx, + .start = genl_start, + .dump = genl_dumpit, + .done = genl_done, + .extack = extack, + }; int err; ctx.family = family; @@ -909,31 +928,9 @@ static int genl_family_rcv_msg_dumpit(const struct genl_family *family, ctx.ops = ops; ctx.hdrlen = hdrlen; - if (!family->parallel_ops) { - struct netlink_dump_control c = { - .module = family->module, - .data = &ctx, - .start = genl_start, - .dump = genl_lock_dumpit, - .done = genl_lock_done, - .extack = extack, - }; - - genl_unlock(); - err = __netlink_dump_start(net->genl_sock, skb, nlh, &c); - genl_lock(); - } else { - struct netlink_dump_control c = { - .module = family->module, - .data = &ctx, - .start = genl_start, - .dump = ops->dumpit, - .done = genl_parallel_done, - .extack = extack, - }; - - err = __netlink_dump_start(net->genl_sock, skb, nlh, &c); - } + genl_op_unlock(family); + err = __netlink_dump_start(net->genl_sock, skb, nlh, &c); + genl_op_lock(family); return err; } @@ -957,9 +954,9 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family, info.snd_seq = nlh->nlmsg_seq; info.snd_portid = NETLINK_CB(skb).portid; + info.family = family; info.nlhdr = nlh; info.genlhdr = nlmsg_data(nlh); - info.userhdr = nlmsg_data(nlh) + GENL_HDRLEN; info.attrs = attrbuf; info.extack = extack; genl_info_net_set(&info, net); @@ -1065,13 +1062,9 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, if (family == NULL) return -ENOENT; - if (!family->parallel_ops) - genl_lock(); - + genl_op_lock(family); err = genl_family_rcv_msg(family, skb, nlh, extack); - - if (!family->parallel_ops) - genl_unlock(); + genl_op_unlock(family); return err; } @@ -1396,7 +1389,7 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; - struct nlattr **tb = info->attrs; + struct nlattr **tb = info->info.attrs; const struct genl_family *rt; struct genl_op_iter i; int err; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index e9ac6a6f934e..aa1dbf654c3e 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -110,10 +110,10 @@ static struct nfc_dev *__get_device_from_cb(struct netlink_callback *cb) struct nfc_dev *dev; u32 idx; - if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + if (!info->info.attrs[NFC_ATTR_DEVICE_INDEX]) return ERR_PTR(-EINVAL); - idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); + idx = nla_get_u32(info->info.attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index cab1e02b63e0..fd66014d8a76 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -27,6 +27,7 @@ #include <net/sctp/checksum.h> #include "datapath.h" +#include "drop.h" #include "flow.h" #include "conntrack.h" #include "vport.h" @@ -781,7 +782,7 @@ static int ovs_vport_output(struct net *net, struct sock *sk, struct vport *vport = data->vport; if (skb_cow_head(skb, data->l2_len) < 0) { - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_NOMEM); return -ENOMEM; } @@ -852,6 +853,7 @@ static void ovs_fragment(struct net *net, struct vport *vport, struct sk_buff *skb, u16 mru, struct sw_flow_key *key) { + enum ovs_drop_reason reason; u16 orig_network_offset = 0; if (eth_p_mpls(skb->protocol)) { @@ -861,6 +863,7 @@ static void ovs_fragment(struct net *net, struct vport *vport, if (skb_network_offset(skb) > MAX_L2_LEN) { OVS_NLERR(1, "L2 header too long to fragment"); + reason = OVS_DROP_FRAG_L2_TOO_LONG; goto err; } @@ -901,12 +904,13 @@ static void ovs_fragment(struct net *net, struct vport *vport, WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.", ovs_vport_name(vport), ntohs(key->eth.type), mru, vport->dev->mtu); + reason = OVS_DROP_FRAG_INVALID_PROTO; goto err; } return; err: - kfree_skb(skb); + ovs_kfree_skb_reason(skb, reason); } static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, @@ -933,10 +937,10 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, ovs_fragment(net, vport, skb, mru, key); } else { - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG); } } else { - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_DEV_READY); } } @@ -1010,7 +1014,7 @@ static int dec_ttl_exception_handler(struct datapath *dp, struct sk_buff *skb, return clone_execute(dp, skb, key, 0, nla_data(actions), nla_len(actions), true, false); - consume_skb(skb); + ovs_kfree_skb_reason(skb, OVS_DROP_IP_TTL); return 0; } @@ -1036,7 +1040,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb, if ((arg->probability != U32_MAX) && (!arg->probability || get_random_u32() > arg->probability)) { if (last) - consume_skb(skb); + ovs_kfree_skb_reason(skb, OVS_DROP_LAST_ACTION); return 0; } @@ -1297,6 +1301,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, if (trace_ovs_do_execute_action_enabled()) trace_ovs_do_execute_action(dp, skb, key, a, rem); + /* Actions that rightfully have to consume the skb should do it + * and return directly. + */ switch (nla_type(a)) { case OVS_ACTION_ATTR_OUTPUT: { int port = nla_get_u32(a); @@ -1332,6 +1339,10 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, output_userspace(dp, skb, key, a, attr, len, OVS_CB(skb)->cutlen); OVS_CB(skb)->cutlen = 0; + if (nla_is_last(a, rem)) { + consume_skb(skb); + return 0; + } break; case OVS_ACTION_ATTR_HASH: @@ -1446,7 +1457,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, case OVS_ACTION_ATTR_METER: if (ovs_meter_execute(dp, skb, key, nla_get_u32(a))) { - consume_skb(skb); + ovs_kfree_skb_reason(skb, OVS_DROP_METER); return 0; } break; @@ -1477,15 +1488,24 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, return dec_ttl_exception_handler(dp, skb, key, a); break; + + case OVS_ACTION_ATTR_DROP: { + enum ovs_drop_reason reason = nla_get_u32(a) + ? OVS_DROP_EXPLICIT_WITH_ERROR + : OVS_DROP_EXPLICIT; + + ovs_kfree_skb_reason(skb, reason); + return 0; + } } if (unlikely(err)) { - kfree_skb(skb); + ovs_kfree_skb_reason(skb, OVS_DROP_ACTION_ERROR); return err; } } - consume_skb(skb); + ovs_kfree_skb_reason(skb, OVS_DROP_LAST_ACTION); return 0; } @@ -1547,7 +1567,7 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb, /* Out of per CPU action FIFO space. Drop the 'skb' and * log an error. */ - kfree_skb(skb); + ovs_kfree_skb_reason(skb, OVS_DROP_DEFERRED_LIMIT); if (net_ratelimit()) { if (actions) { /* Sample action */ @@ -1599,7 +1619,7 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb, if (unlikely(level > OVS_RECURSION_LIMIT)) { net_crit_ratelimited("ovs: recursion limit reached on datapath %s, probable configuration error\n", ovs_dp_name(dp)); - kfree_skb(skb); + ovs_kfree_skb_reason(skb, OVS_DROP_RECURSION_LIMIT); err = -ENETDOWN; goto out; } diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index fa955e892210..0b9a785dea45 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -29,6 +29,7 @@ #include <net/netfilter/nf_conntrack_act_ct.h> #include "datapath.h" +#include "drop.h" #include "conntrack.h" #include "flow.h" #include "flow_netlink.h" @@ -1035,7 +1036,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, skb_push_rcsum(skb, nh_ofs); if (err) - kfree_skb(skb); + ovs_kfree_skb_reason(skb, OVS_DROP_CONNTRACK); return err; } @@ -1604,7 +1605,7 @@ static struct sk_buff * ovs_ct_limit_cmd_reply_start(struct genl_info *info, u8 cmd, struct ovs_header **ovs_reply_header) { - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct sk_buff *skb; skb = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index a6d2a0b1aa21..0a974eeef76e 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -41,6 +41,7 @@ #include <net/pkt_cls.h> #include "datapath.h" +#include "drop.h" #include "flow.h" #include "flow_table.h" #include "flow_netlink.h" @@ -589,7 +590,7 @@ out: static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) { - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct net *net = sock_net(skb->sk); struct nlattr **a = info->attrs; struct sw_flow_actions *acts; @@ -966,7 +967,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); struct nlattr **a = info->attrs; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct sw_flow *flow = NULL, *new_flow; struct sw_flow_mask mask; struct sk_buff *reply; @@ -1213,7 +1214,7 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); struct nlattr **a = info->attrs; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct sw_flow_key key; struct sw_flow *flow; struct sk_buff *reply = NULL; @@ -1314,7 +1315,7 @@ error: static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct net *net = sock_net(skb->sk); struct sw_flow_key key; struct sk_buff *reply; @@ -1373,7 +1374,7 @@ unlock: static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct net *net = sock_net(skb->sk); struct sw_flow_key key; struct sk_buff *reply; @@ -1641,7 +1642,7 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, { struct datapath *dp; - dp = lookup_datapath(sock_net(skb->sk), info->userhdr, + dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info), info->attrs); if (IS_ERR(dp)) return; @@ -1934,7 +1935,8 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; ovs_lock(); - dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); + dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info), + info->attrs); err = PTR_ERR(dp); if (IS_ERR(dp)) goto err_unlock_free; @@ -1967,7 +1969,8 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; ovs_lock(); - dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); + dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info), + info->attrs); err = PTR_ERR(dp); if (IS_ERR(dp)) goto err_unlock_free; @@ -2002,7 +2005,8 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; ovs_lock(); - dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); + dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info), + info->attrs); if (IS_ERR(dp)) { err = PTR_ERR(dp); goto err_unlock_free; @@ -2245,7 +2249,7 @@ static void ovs_update_headroom(struct datapath *dp, unsigned int new_headroom) static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct vport_parms parms; struct sk_buff *reply; struct vport *vport; @@ -2347,7 +2351,7 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; ovs_lock(); - vport = lookup_vport(sock_net(skb->sk), info->userhdr, a); + vport = lookup_vport(sock_net(skb->sk), genl_info_userhdr(info), a); err = PTR_ERR(vport); if (IS_ERR(vport)) goto exit_unlock_free; @@ -2403,7 +2407,7 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; ovs_lock(); - vport = lookup_vport(sock_net(skb->sk), info->userhdr, a); + vport = lookup_vport(sock_net(skb->sk), genl_info_userhdr(info), a); err = PTR_ERR(vport); if (IS_ERR(vport)) goto exit_unlock_free; @@ -2446,7 +2450,7 @@ exit_unlock_free: static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct sk_buff *reply; struct vport *vport; int err; @@ -2702,6 +2706,17 @@ static struct pernet_operations ovs_net_ops = { .size = sizeof(struct ovs_net), }; +static const char * const ovs_drop_reasons[] = { +#define S(x) (#x), + OVS_DROP_REASONS(S) +#undef S +}; + +static struct drop_reason_list drop_reason_list_ovs = { + .reasons = ovs_drop_reasons, + .n_reasons = ARRAY_SIZE(ovs_drop_reasons), +}; + static int __init dp_init(void) { int err; @@ -2743,6 +2758,9 @@ static int __init dp_init(void) if (err < 0) goto error_unreg_netdev; + drop_reasons_register_subsys(SKB_DROP_REASON_SUBSYS_OPENVSWITCH, + &drop_reason_list_ovs); + return 0; error_unreg_netdev: @@ -2769,6 +2787,7 @@ static void dp_cleanup(void) ovs_netdev_exit(); unregister_netdevice_notifier(&ovs_dp_device_notifier); unregister_pernet_device(&ovs_net_ops); + drop_reasons_unregister_subsys(SKB_DROP_REASON_SUBSYS_OPENVSWITCH); rcu_barrier(); ovs_vport_exit(); ovs_flow_exit(); diff --git a/net/openvswitch/drop.h b/net/openvswitch/drop.h new file mode 100644 index 000000000000..cedf9b7b5796 --- /dev/null +++ b/net/openvswitch/drop.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * OpenvSwitch drop reason list. + */ + +#ifndef OPENVSWITCH_DROP_H +#define OPENVSWITCH_DROP_H +#include <linux/skbuff.h> +#include <net/dropreason.h> + +#define OVS_DROP_REASONS(R) \ + R(OVS_DROP_LAST_ACTION) \ + R(OVS_DROP_ACTION_ERROR) \ + R(OVS_DROP_EXPLICIT) \ + R(OVS_DROP_EXPLICIT_WITH_ERROR) \ + R(OVS_DROP_METER) \ + R(OVS_DROP_RECURSION_LIMIT) \ + R(OVS_DROP_DEFERRED_LIMIT) \ + R(OVS_DROP_FRAG_L2_TOO_LONG) \ + R(OVS_DROP_FRAG_INVALID_PROTO) \ + R(OVS_DROP_CONNTRACK) \ + R(OVS_DROP_IP_TTL) \ + /* deliberate comment for trailing \ */ + +enum ovs_drop_reason { + __OVS_DROP_REASON = SKB_DROP_REASON_SUBSYS_OPENVSWITCH << + SKB_DROP_REASON_SUBSYS_SHIFT, +#define ENUM(x) x, + OVS_DROP_REASONS(ENUM) +#undef ENUM + + OVS_DROP_MAX, +}; + +static inline void +ovs_kfree_skb_reason(struct sk_buff *skb, enum ovs_drop_reason reason) +{ + kfree_skb_reason(skb, (u32)reason); +} + +#endif /* OPENVSWITCH_DROP_H */ diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 41116361433d..88965e2068ac 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -38,6 +38,7 @@ #include <net/tun_proto.h> #include <net/erspan.h> +#include "drop.h" #include "flow_netlink.h" struct ovs_len_tbl { @@ -61,6 +62,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) case OVS_ACTION_ATTR_RECIRC: case OVS_ACTION_ATTR_TRUNC: case OVS_ACTION_ATTR_USERSPACE: + case OVS_ACTION_ATTR_DROP: break; case OVS_ACTION_ATTR_CT: @@ -2394,7 +2396,7 @@ static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len) /* Whenever new actions are added, the need to update this * function should be considered. */ - BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 23); + BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 24); if (!actions) return; @@ -3182,6 +3184,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_CHECK_PKT_LEN] = (u32)-1, [OVS_ACTION_ATTR_ADD_MPLS] = sizeof(struct ovs_action_add_mpls), [OVS_ACTION_ATTR_DEC_TTL] = (u32)-1, + [OVS_ACTION_ATTR_DROP] = sizeof(u32), }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -3453,6 +3456,11 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, skip_copy = true; break; + case OVS_ACTION_ATTR_DROP: + if (!nla_is_last(a, rem)) + return -EINVAL; + break; + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index c4ebf810e4b1..cc08e0403909 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -211,7 +211,7 @@ ovs_meter_cmd_reply_start(struct genl_info *info, u8 cmd, struct ovs_header **ovs_reply_header) { struct sk_buff *skb; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) @@ -272,7 +272,7 @@ error: static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info) { - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct ovs_header *ovs_reply_header; struct nlattr *nla, *band_nla; struct sk_buff *reply; @@ -409,7 +409,7 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) struct dp_meter *meter, *old_meter; struct sk_buff *reply; struct ovs_header *ovs_reply_header; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct dp_meter_table *meter_tbl; struct datapath *dp; int err; @@ -482,7 +482,7 @@ exit_free_meter: static int ovs_meter_cmd_get(struct sk_buff *skb, struct genl_info *info) { - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct ovs_header *ovs_reply_header; struct nlattr **a = info->attrs; struct dp_meter *meter; @@ -535,7 +535,7 @@ exit_unlock: static int ovs_meter_cmd_del(struct sk_buff *skb, struct genl_info *info) { - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct ovs_header *ovs_reply_header; struct nlattr **a = info->attrs; struct dp_meter *old_meter; diff --git a/net/rds/rdma_transport.h b/net/rds/rdma_transport.h index ca4c3a667091..d2fdb1529585 100644 --- a/net/rds/rdma_transport.h +++ b/net/rds/rdma_transport.h @@ -17,7 +17,6 @@ */ #define RDS_RDMA_REJ_INCOMPAT 1 -int rds_rdma_conn_connect(struct rds_connection *conn); int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event); int rds6_rdma_cm_event_handler(struct rdma_cm_id *cm_id, diff --git a/net/rds/rds.h b/net/rds/rds.h index d35d1fc39807..dc360252c515 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -863,7 +863,6 @@ int rds_message_next_extension(struct rds_header *hdr, unsigned int *pos, void *buf, unsigned int *buflen); int rds_message_add_rdma_dest_extension(struct rds_header *hdr, u32 r_key, u32 offset); int rds_message_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to); -void rds_message_inc_free(struct rds_incoming *inc); void rds_message_addref(struct rds_message *rm); void rds_message_put(struct rds_message *rm); void rds_message_wait(struct rds_message *rm); @@ -1013,7 +1012,5 @@ void rds_trans_put(struct rds_transport *trans); unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter, unsigned int avail); struct rds_transport *rds_trans_get(int t_type); -int rds_trans_init(void); -void rds_trans_exit(void); #endif diff --git a/net/rds/tcp.h b/net/rds/tcp.h index f8b5930d7b34..053aa7da87ef 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -56,7 +56,6 @@ void rds_tcp_restore_callbacks(struct socket *sock, struct rds_tcp_connection *tc); u32 rds_tcp_write_seq(struct rds_tcp_connection *tc); u32 rds_tcp_snd_una(struct rds_tcp_connection *tc); -u64 rds_tcp_map_seq(struct rds_tcp_connection *tc, u32 seq); extern struct rds_transport rds_tcp_transport; void rds_tcp_accept_work(struct sock *sk); int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, diff --git a/net/sctp/input.c b/net/sctp/input.c index 2613c4d74b16..17fcaa9b0df9 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -581,7 +581,7 @@ static void sctp_v4_err_handle(struct sctp_transport *t, struct sk_buff *skb, default: return; } - if (!sock_owned_by_user(sk) && inet_sk(sk)->recverr) { + if (!sock_owned_by_user(sk) && inet_test_bit(RECVERR, sk)) { sk->sk_err = err; sk_error_report(sk); } else { /* Only an error on timeout */ diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 33c0895e101c..2185f44198de 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -360,7 +360,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) ret = inet_addr_type_table(net, addr->v4.sin_addr.s_addr, tb_id); if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) && ret != RTN_LOCAL && - !sp->inet.freebind && + !inet_test_bit(FREEBIND, sk) && !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind)) return 0; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6e3d28aa587c..04b390892827 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -9482,7 +9482,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->inet_id = get_random_u16(); newinet->uc_ttl = inet->uc_ttl; - newinet->mc_loop = 1; + inet_set_bit(MC_LOOP, newsk); newinet->mc_ttl = 1; newinet->mc_index = 0; newinet->mc_list = NULL; diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 9b47c8409231..5bc076f2fa74 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -208,7 +208,7 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, goto err_out; } - info.attrs = attrbuf; + info.info.attrs = attrbuf; if (nlmsg_len(cb.nlh) > 0) { err = nlmsg_parse_deprecated(cb.nlh, GENL_HDRLEN, attrbuf, @@ -1294,7 +1294,7 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info) struct tipc_nl_compat_msg msg; struct nlmsghdr *req_nlh; struct nlmsghdr *rep_nlh; - struct tipc_genlmsghdr *req_userhdr = info->userhdr; + struct tipc_genlmsghdr *req_userhdr = genl_info_userhdr(info); memset(&msg, 0, sizeof(msg)); diff --git a/net/tipc/node.c b/net/tipc/node.c index a9c5b6594889..3105abe97bb9 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2662,7 +2662,7 @@ static int __tipc_nl_add_node_links(struct net *net, struct tipc_nl_msg *msg, int tipc_nl_node_dump_link(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - struct nlattr **attrs = genl_dumpit_info(cb)->attrs; + struct nlattr **attrs = genl_dumpit_info(cb)->info.attrs; struct nlattr *link[TIPC_NLA_LINK_MAX + 1]; struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_node *node; @@ -2870,7 +2870,7 @@ int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb, int err; if (!prev_node) { - struct nlattr **attrs = genl_dumpit_info(cb)->attrs; + struct nlattr **attrs = genl_dumpit_info(cb)->info.attrs; struct nlattr *mon[TIPC_NLA_MON_MAX + 1]; if (!attrs[TIPC_NLA_MON]) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index ef8e5139a873..bb1118d02f95 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -3791,7 +3791,7 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb) struct tipc_sock *tsk; if (!tsk_portid) { - struct nlattr **attrs = genl_dumpit_info(cb)->attrs; + struct nlattr **attrs = genl_dumpit_info(cb)->info.attrs; struct nlattr *sock[TIPC_NLA_SOCK_MAX + 1]; if (!attrs[TIPC_NLA_SOCK]) diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 926232557e77..f892b0903dba 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -465,7 +465,7 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb) int i; if (!bid && !skip_cnt) { - struct nlattr **attrs = genl_dumpit_info(cb)->attrs; + struct nlattr **attrs = genl_dumpit_info(cb)->info.attrs; struct net *net = sock_net(skb->sk); struct nlattr *battrs[TIPC_NLA_BEARER_MAX + 1]; char *bname; diff --git a/tools/net/ynl/generated/devlink-user.c b/tools/net/ynl/generated/devlink-user.c index 8492789433b9..3a8d8499fab6 100644 --- a/tools/net/ynl/generated/devlink-user.c +++ b/tools/net/ynl/generated/devlink-user.c @@ -15,7 +15,21 @@ /* Enums */ static const char * const devlink_op_strmap[] = { [3] = "get", + [7] = "port-get", + [DEVLINK_CMD_SB_GET] = "sb-get", + [DEVLINK_CMD_SB_POOL_GET] = "sb-pool-get", + [DEVLINK_CMD_SB_PORT_POOL_GET] = "sb-port-pool-get", + [DEVLINK_CMD_SB_TC_POOL_BIND_GET] = "sb-tc-pool-bind-get", + [DEVLINK_CMD_PARAM_GET] = "param-get", + [DEVLINK_CMD_REGION_GET] = "region-get", [DEVLINK_CMD_INFO_GET] = "info-get", + [DEVLINK_CMD_HEALTH_REPORTER_GET] = "health-reporter-get", + [DEVLINK_CMD_TRAP_GET] = "trap-get", + [DEVLINK_CMD_TRAP_GROUP_GET] = "trap-group-get", + [DEVLINK_CMD_TRAP_POLICER_GET] = "trap-policer-get", + [DEVLINK_CMD_RATE_GET] = "rate-get", + [DEVLINK_CMD_LINECARD_GET] = "linecard-get", + [DEVLINK_CMD_SELFTESTS_GET] = "selftests-get", }; const char *devlink_op_str(int op) @@ -25,6 +39,18 @@ const char *devlink_op_str(int op) return devlink_op_strmap[op]; } +static const char * const devlink_sb_pool_type_strmap[] = { + [0] = "ingress", + [1] = "egress", +}; + +const char *devlink_sb_pool_type_str(enum devlink_sb_pool_type value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_sb_pool_type_strmap)) + return NULL; + return devlink_sb_pool_type_strmap[value]; +} + /* Policies */ struct ynl_policy_attr devlink_dl_info_version_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, }, @@ -88,6 +114,12 @@ struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .name = "bus-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_DEV_NAME] = { .name = "dev-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_PORT_INDEX] = { .name = "port-index", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_SB_INDEX] = { .name = "sb-index", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_SB_POOL_INDEX] = { .name = "sb-pool-index", .type = YNL_PT_U16, }, + [DEVLINK_ATTR_SB_POOL_TYPE] = { .name = "sb-pool-type", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_SB_TC_INDEX] = { .name = "sb-tc-index", .type = YNL_PT_U16, }, + [DEVLINK_ATTR_PARAM_NAME] = { .name = "param-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_REGION_NAME] = { .name = "region-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_INFO_DRIVER_NAME] = { .name = "info-driver-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_INFO_SERIAL_NUMBER] = { .name = "info-serial-number", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_INFO_VERSION_FIXED] = { .name = "info-version-fixed", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, }, @@ -95,7 +127,11 @@ struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_INFO_VERSION_STORED] = { .name = "info-version-stored", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, }, [DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_INFO_VERSION_VALUE] = { .name = "info-version-value", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .name = "health-reporter-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_TRAP_NAME] = { .name = "trap-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .name = "trap-group-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_RELOAD_FAILED] = { .name = "reload-failed", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_TRAP_POLICER_ID] = { .name = "trap-policer-id", .type = YNL_PT_U32, }, [DEVLINK_ATTR_RELOAD_ACTION] = { .name = "reload-action", .type = YNL_PT_U8, }, [DEVLINK_ATTR_DEV_STATS] = { .name = "dev-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_dev_stats_nest, }, [DEVLINK_ATTR_RELOAD_STATS] = { .name = "reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, @@ -105,6 +141,8 @@ struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_REMOTE_RELOAD_STATS] = { .name = "remote-reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, [DEVLINK_ATTR_RELOAD_ACTION_INFO] = { .name = "reload-action-info", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_info_nest, }, [DEVLINK_ATTR_RELOAD_ACTION_STATS] = { .name = "reload-action-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_stats_nest, }, + [DEVLINK_ATTR_RATE_NODE_NAME] = { .name = "rate-node-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_LINECARD_INDEX] = { .name = "linecard-index", .type = YNL_PT_U32, }, }; struct ynl_policy_nest devlink_nest = { @@ -531,6 +569,1126 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_PORT_GET ============== */ +/* DEVLINK_CMD_PORT_GET - do */ +void devlink_port_get_req_free(struct devlink_port_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_port_get_rsp_free(struct devlink_port_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_port_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct devlink_port_get_rsp *dst; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_port_get_rsp * +devlink_port_get(struct ynl_sock *ys, struct devlink_port_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_port_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_port_get_rsp_parse; + yrs.rsp_cmd = 7; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_port_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_PORT_GET - dump */ +int devlink_port_get_rsp_dump_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_port_get_rsp_dump *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +void devlink_port_get_rsp_list_free(struct devlink_port_get_rsp_list *rsp) +{ + struct devlink_port_get_rsp_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_port_get_rsp_list * +devlink_port_get_dump(struct ynl_sock *ys, + struct devlink_port_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_port_get_rsp_list); + yds.cb = devlink_port_get_rsp_dump_parse; + yds.rsp_cmd = 7; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PORT_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_port_get_rsp_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_SB_GET ============== */ +/* DEVLINK_CMD_SB_GET - do */ +void devlink_sb_get_req_free(struct devlink_sb_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_sb_get_rsp_free(struct devlink_sb_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_sb_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct devlink_sb_get_rsp *dst; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_SB_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_index = 1; + dst->sb_index = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_sb_get_rsp * +devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_sb_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.sb_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_sb_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_SB_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_sb_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_SB_GET - dump */ +void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp) +{ + struct devlink_sb_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_sb_get_list * +devlink_sb_get_dump(struct ynl_sock *ys, struct devlink_sb_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_sb_get_list); + yds.cb = devlink_sb_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_SB_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_sb_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_SB_POOL_GET ============== */ +/* DEVLINK_CMD_SB_POOL_GET - do */ +void devlink_sb_pool_get_req_free(struct devlink_sb_pool_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_sb_pool_get_rsp_free(struct devlink_sb_pool_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_sb_pool_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_sb_pool_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_SB_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_index = 1; + dst->sb_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_SB_POOL_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_pool_index = 1; + dst->sb_pool_index = mnl_attr_get_u16(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_sb_pool_get_rsp * +devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_sb_pool_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_POOL_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.sb_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index); + if (req->_present.sb_pool_index) + mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_sb_pool_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_SB_POOL_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_sb_pool_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_SB_POOL_GET - dump */ +void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp) +{ + struct devlink_sb_pool_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_sb_pool_get_list * +devlink_sb_pool_get_dump(struct ynl_sock *ys, + struct devlink_sb_pool_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_sb_pool_get_list); + yds.cb = devlink_sb_pool_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_SB_POOL_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_POOL_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_sb_pool_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_SB_PORT_POOL_GET ============== */ +/* DEVLINK_CMD_SB_PORT_POOL_GET - do */ +void +devlink_sb_port_pool_get_req_free(struct devlink_sb_port_pool_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void +devlink_sb_port_pool_get_rsp_free(struct devlink_sb_port_pool_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_sb_port_pool_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_sb_port_pool_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_SB_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_index = 1; + dst->sb_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_SB_POOL_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_pool_index = 1; + dst->sb_pool_index = mnl_attr_get_u16(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_sb_port_pool_get_rsp * +devlink_sb_port_pool_get(struct ynl_sock *ys, + struct devlink_sb_port_pool_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_sb_port_pool_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.sb_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index); + if (req->_present.sb_pool_index) + mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_sb_port_pool_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_SB_PORT_POOL_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_sb_port_pool_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_SB_PORT_POOL_GET - dump */ +void +devlink_sb_port_pool_get_list_free(struct devlink_sb_port_pool_get_list *rsp) +{ + struct devlink_sb_port_pool_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_sb_port_pool_get_list * +devlink_sb_port_pool_get_dump(struct ynl_sock *ys, + struct devlink_sb_port_pool_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_sb_port_pool_get_list); + yds.cb = devlink_sb_port_pool_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_SB_PORT_POOL_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_sb_port_pool_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_GET ============== */ +/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */ +void +devlink_sb_tc_pool_bind_get_req_free(struct devlink_sb_tc_pool_bind_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void +devlink_sb_tc_pool_bind_get_rsp_free(struct devlink_sb_tc_pool_bind_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_sb_tc_pool_bind_get_rsp_parse(const struct nlmsghdr *nlh, + void *data) +{ + struct devlink_sb_tc_pool_bind_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_SB_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_index = 1; + dst->sb_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_SB_POOL_TYPE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_pool_type = 1; + dst->sb_pool_type = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_SB_TC_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_tc_index = 1; + dst->sb_tc_index = mnl_attr_get_u16(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_sb_tc_pool_bind_get_rsp * +devlink_sb_tc_pool_bind_get(struct ynl_sock *ys, + struct devlink_sb_tc_pool_bind_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_sb_tc_pool_bind_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.sb_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index); + if (req->_present.sb_pool_type) + mnl_attr_put_u8(nlh, DEVLINK_ATTR_SB_POOL_TYPE, req->sb_pool_type); + if (req->_present.sb_tc_index) + mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_TC_INDEX, req->sb_tc_index); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_sb_tc_pool_bind_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_sb_tc_pool_bind_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - dump */ +void +devlink_sb_tc_pool_bind_get_list_free(struct devlink_sb_tc_pool_bind_get_list *rsp) +{ + struct devlink_sb_tc_pool_bind_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_sb_tc_pool_bind_get_list * +devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys, + struct devlink_sb_tc_pool_bind_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_sb_tc_pool_bind_get_list); + yds.cb = devlink_sb_tc_pool_bind_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_sb_tc_pool_bind_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_PARAM_GET ============== */ +/* DEVLINK_CMD_PARAM_GET - do */ +void devlink_param_get_req_free(struct devlink_param_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->param_name); + free(req); +} + +void devlink_param_get_rsp_free(struct devlink_param_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp->param_name); + free(rsp); +} + +int devlink_param_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_param_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PARAM_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.param_name_len = len; + dst->param_name = malloc(len + 1); + memcpy(dst->param_name, mnl_attr_get_str(attr), len); + dst->param_name[len] = 0; + } + } + + return MNL_CB_OK; +} + +struct devlink_param_get_rsp * +devlink_param_get(struct ynl_sock *ys, struct devlink_param_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_param_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PARAM_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.param_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_PARAM_NAME, req->param_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_param_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_PARAM_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_param_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_PARAM_GET - dump */ +void devlink_param_get_list_free(struct devlink_param_get_list *rsp) +{ + struct devlink_param_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp->obj.param_name); + free(rsp); + } +} + +struct devlink_param_get_list * +devlink_param_get_dump(struct ynl_sock *ys, + struct devlink_param_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_param_get_list); + yds.cb = devlink_param_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_PARAM_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PARAM_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_param_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_REGION_GET ============== */ +/* DEVLINK_CMD_REGION_GET - do */ +void devlink_region_get_req_free(struct devlink_region_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->region_name); + free(req); +} + +void devlink_region_get_rsp_free(struct devlink_region_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp->region_name); + free(rsp); +} + +int devlink_region_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_region_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_REGION_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.region_name_len = len; + dst->region_name = malloc(len + 1); + memcpy(dst->region_name, mnl_attr_get_str(attr), len); + dst->region_name[len] = 0; + } + } + + return MNL_CB_OK; +} + +struct devlink_region_get_rsp * +devlink_region_get(struct ynl_sock *ys, struct devlink_region_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_region_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_REGION_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.region_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME, req->region_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_region_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_REGION_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_region_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_REGION_GET - dump */ +void devlink_region_get_list_free(struct devlink_region_get_list *rsp) +{ + struct devlink_region_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp->obj.region_name); + free(rsp); + } +} + +struct devlink_region_get_list * +devlink_region_get_dump(struct ynl_sock *ys, + struct devlink_region_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_region_get_list); + yds.cb = devlink_region_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_REGION_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_REGION_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_region_get_list_free(yds.first); + return NULL; +} + /* ============== DEVLINK_CMD_INFO_GET ============== */ /* DEVLINK_CMD_INFO_GET - do */ void devlink_info_get_req_free(struct devlink_info_get_req *req) @@ -769,6 +1927,1056 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_HEALTH_REPORTER_GET ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_GET - do */ +void +devlink_health_reporter_get_req_free(struct devlink_health_reporter_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->health_reporter_name); + free(req); +} + +void +devlink_health_reporter_get_rsp_free(struct devlink_health_reporter_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp->health_reporter_name); + free(rsp); +} + +int devlink_health_reporter_get_rsp_parse(const struct nlmsghdr *nlh, + void *data) +{ + struct devlink_health_reporter_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_HEALTH_REPORTER_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.health_reporter_name_len = len; + dst->health_reporter_name = malloc(len + 1); + memcpy(dst->health_reporter_name, mnl_attr_get_str(attr), len); + dst->health_reporter_name[len] = 0; + } + } + + return MNL_CB_OK; +} + +struct devlink_health_reporter_get_rsp * +devlink_health_reporter_get(struct ynl_sock *ys, + struct devlink_health_reporter_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_health_reporter_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.health_reporter_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_health_reporter_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_HEALTH_REPORTER_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_health_reporter_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_HEALTH_REPORTER_GET - dump */ +void +devlink_health_reporter_get_list_free(struct devlink_health_reporter_get_list *rsp) +{ + struct devlink_health_reporter_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp->obj.health_reporter_name); + free(rsp); + } +} + +struct devlink_health_reporter_get_list * +devlink_health_reporter_get_dump(struct ynl_sock *ys, + struct devlink_health_reporter_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_health_reporter_get_list); + yds.cb = devlink_health_reporter_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_HEALTH_REPORTER_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_health_reporter_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_TRAP_GET ============== */ +/* DEVLINK_CMD_TRAP_GET - do */ +void devlink_trap_get_req_free(struct devlink_trap_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->trap_name); + free(req); +} + +void devlink_trap_get_rsp_free(struct devlink_trap_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp->trap_name); + free(rsp); +} + +int devlink_trap_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct devlink_trap_get_rsp *dst; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_TRAP_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.trap_name_len = len; + dst->trap_name = malloc(len + 1); + memcpy(dst->trap_name, mnl_attr_get_str(attr), len); + dst->trap_name[len] = 0; + } + } + + return MNL_CB_OK; +} + +struct devlink_trap_get_rsp * +devlink_trap_get(struct ynl_sock *ys, struct devlink_trap_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_trap_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.trap_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_NAME, req->trap_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_trap_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_TRAP_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_trap_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_TRAP_GET - dump */ +void devlink_trap_get_list_free(struct devlink_trap_get_list *rsp) +{ + struct devlink_trap_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp->obj.trap_name); + free(rsp); + } +} + +struct devlink_trap_get_list * +devlink_trap_get_dump(struct ynl_sock *ys, + struct devlink_trap_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_trap_get_list); + yds.cb = devlink_trap_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_TRAP_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_trap_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_TRAP_GROUP_GET ============== */ +/* DEVLINK_CMD_TRAP_GROUP_GET - do */ +void devlink_trap_group_get_req_free(struct devlink_trap_group_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->trap_group_name); + free(req); +} + +void devlink_trap_group_get_rsp_free(struct devlink_trap_group_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp->trap_group_name); + free(rsp); +} + +int devlink_trap_group_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_trap_group_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_TRAP_GROUP_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.trap_group_name_len = len; + dst->trap_group_name = malloc(len + 1); + memcpy(dst->trap_group_name, mnl_attr_get_str(attr), len); + dst->trap_group_name[len] = 0; + } + } + + return MNL_CB_OK; +} + +struct devlink_trap_group_get_rsp * +devlink_trap_group_get(struct ynl_sock *ys, + struct devlink_trap_group_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_trap_group_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_GROUP_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.trap_group_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_GROUP_NAME, req->trap_group_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_trap_group_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_TRAP_GROUP_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_trap_group_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_TRAP_GROUP_GET - dump */ +void devlink_trap_group_get_list_free(struct devlink_trap_group_get_list *rsp) +{ + struct devlink_trap_group_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp->obj.trap_group_name); + free(rsp); + } +} + +struct devlink_trap_group_get_list * +devlink_trap_group_get_dump(struct ynl_sock *ys, + struct devlink_trap_group_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_trap_group_get_list); + yds.cb = devlink_trap_group_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_TRAP_GROUP_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_GROUP_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_trap_group_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_TRAP_POLICER_GET ============== */ +/* DEVLINK_CMD_TRAP_POLICER_GET - do */ +void +devlink_trap_policer_get_req_free(struct devlink_trap_policer_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void +devlink_trap_policer_get_rsp_free(struct devlink_trap_policer_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_trap_policer_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_trap_policer_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_TRAP_POLICER_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.trap_policer_id = 1; + dst->trap_policer_id = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_trap_policer_get_rsp * +devlink_trap_policer_get(struct ynl_sock *ys, + struct devlink_trap_policer_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_trap_policer_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_POLICER_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.trap_policer_id) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_TRAP_POLICER_ID, req->trap_policer_id); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_trap_policer_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_TRAP_POLICER_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_trap_policer_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_TRAP_POLICER_GET - dump */ +void +devlink_trap_policer_get_list_free(struct devlink_trap_policer_get_list *rsp) +{ + struct devlink_trap_policer_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_trap_policer_get_list * +devlink_trap_policer_get_dump(struct ynl_sock *ys, + struct devlink_trap_policer_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_trap_policer_get_list); + yds.cb = devlink_trap_policer_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_TRAP_POLICER_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_POLICER_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_trap_policer_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_RATE_GET ============== */ +/* DEVLINK_CMD_RATE_GET - do */ +void devlink_rate_get_req_free(struct devlink_rate_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->rate_node_name); + free(req); +} + +void devlink_rate_get_rsp_free(struct devlink_rate_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp->rate_node_name); + free(rsp); +} + +int devlink_rate_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct devlink_rate_get_rsp *dst; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_RATE_NODE_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.rate_node_name_len = len; + dst->rate_node_name = malloc(len + 1); + memcpy(dst->rate_node_name, mnl_attr_get_str(attr), len); + dst->rate_node_name[len] = 0; + } + } + + return MNL_CB_OK; +} + +struct devlink_rate_get_rsp * +devlink_rate_get(struct ynl_sock *ys, struct devlink_rate_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_rate_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RATE_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.rate_node_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_NODE_NAME, req->rate_node_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_rate_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_RATE_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_rate_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_RATE_GET - dump */ +void devlink_rate_get_list_free(struct devlink_rate_get_list *rsp) +{ + struct devlink_rate_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp->obj.rate_node_name); + free(rsp); + } +} + +struct devlink_rate_get_list * +devlink_rate_get_dump(struct ynl_sock *ys, + struct devlink_rate_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_rate_get_list); + yds.cb = devlink_rate_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_RATE_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_RATE_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_rate_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_LINECARD_GET ============== */ +/* DEVLINK_CMD_LINECARD_GET - do */ +void devlink_linecard_get_req_free(struct devlink_linecard_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_linecard_get_rsp_free(struct devlink_linecard_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_linecard_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_linecard_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_LINECARD_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.linecard_index = 1; + dst->linecard_index = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_linecard_get_rsp * +devlink_linecard_get(struct ynl_sock *ys, struct devlink_linecard_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_linecard_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_LINECARD_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.linecard_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_LINECARD_INDEX, req->linecard_index); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_linecard_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_LINECARD_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_linecard_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_LINECARD_GET - dump */ +void devlink_linecard_get_list_free(struct devlink_linecard_get_list *rsp) +{ + struct devlink_linecard_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_linecard_get_list * +devlink_linecard_get_dump(struct ynl_sock *ys, + struct devlink_linecard_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_linecard_get_list); + yds.cb = devlink_linecard_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_LINECARD_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_LINECARD_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_linecard_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_SELFTESTS_GET ============== */ +/* DEVLINK_CMD_SELFTESTS_GET - do */ +void devlink_selftests_get_req_free(struct devlink_selftests_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_selftests_get_rsp_free(struct devlink_selftests_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_selftests_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_selftests_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } + } + + return MNL_CB_OK; +} + +struct devlink_selftests_get_rsp * +devlink_selftests_get(struct ynl_sock *ys, + struct devlink_selftests_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_selftests_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SELFTESTS_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_selftests_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_SELFTESTS_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_selftests_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_SELFTESTS_GET - dump */ +void devlink_selftests_get_list_free(struct devlink_selftests_get_list *rsp) +{ + struct devlink_selftests_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_selftests_get_list * +devlink_selftests_get_dump(struct ynl_sock *ys) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_selftests_get_list); + yds.cb = devlink_selftests_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_SELFTESTS_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SELFTESTS_GET, 1); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_selftests_get_list_free(yds.first); + return NULL; +} + const struct ynl_family ynl_devlink_family = { .name = "devlink", }; diff --git a/tools/net/ynl/generated/devlink-user.h b/tools/net/ynl/generated/devlink-user.h index af65e2f2f529..4b686d147613 100644 --- a/tools/net/ynl/generated/devlink-user.h +++ b/tools/net/ynl/generated/devlink-user.h @@ -17,6 +17,7 @@ extern const struct ynl_family ynl_devlink_family; /* Enums */ const char *devlink_op_str(int op); +const char *devlink_sb_pool_type_str(enum devlink_sb_pool_type value); /* Common nested types */ struct devlink_dl_info_version { @@ -140,6 +141,939 @@ void devlink_get_list_free(struct devlink_get_list *rsp); struct devlink_get_list *devlink_get_dump(struct ynl_sock *ys); +/* ============== DEVLINK_CMD_PORT_GET ============== */ +/* DEVLINK_CMD_PORT_GET - do */ +struct devlink_port_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; +}; + +static inline struct devlink_port_get_req *devlink_port_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_port_get_req)); +} +void devlink_port_get_req_free(struct devlink_port_get_req *req); + +static inline void +devlink_port_get_req_set_bus_name(struct devlink_port_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_port_get_req_set_dev_name(struct devlink_port_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_port_get_req_set_port_index(struct devlink_port_get_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} + +struct devlink_port_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; +}; + +void devlink_port_get_rsp_free(struct devlink_port_get_rsp *rsp); + +/* + * Get devlink port instances. + */ +struct devlink_port_get_rsp * +devlink_port_get(struct ynl_sock *ys, struct devlink_port_get_req *req); + +/* DEVLINK_CMD_PORT_GET - dump */ +struct devlink_port_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_port_get_req_dump * +devlink_port_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_port_get_req_dump)); +} +void devlink_port_get_req_dump_free(struct devlink_port_get_req_dump *req); + +static inline void +devlink_port_get_req_dump_set_bus_name(struct devlink_port_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_port_get_req_dump_set_dev_name(struct devlink_port_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_port_get_rsp_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; +}; + +struct devlink_port_get_rsp_list { + struct devlink_port_get_rsp_list *next; + struct devlink_port_get_rsp_dump obj __attribute__ ((aligned (8))); +}; + +void devlink_port_get_rsp_list_free(struct devlink_port_get_rsp_list *rsp); + +struct devlink_port_get_rsp_list * +devlink_port_get_dump(struct ynl_sock *ys, + struct devlink_port_get_req_dump *req); + +/* ============== DEVLINK_CMD_SB_GET ============== */ +/* DEVLINK_CMD_SB_GET - do */ +struct devlink_sb_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 sb_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 sb_index; +}; + +static inline struct devlink_sb_get_req *devlink_sb_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_get_req)); +} +void devlink_sb_get_req_free(struct devlink_sb_get_req *req); + +static inline void +devlink_sb_get_req_set_bus_name(struct devlink_sb_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_get_req_set_dev_name(struct devlink_sb_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_sb_get_req_set_sb_index(struct devlink_sb_get_req *req, __u32 sb_index) +{ + req->_present.sb_index = 1; + req->sb_index = sb_index; +} + +struct devlink_sb_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 sb_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 sb_index; +}; + +void devlink_sb_get_rsp_free(struct devlink_sb_get_rsp *rsp); + +/* + * Get shared buffer instances. + */ +struct devlink_sb_get_rsp * +devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req); + +/* DEVLINK_CMD_SB_GET - dump */ +struct devlink_sb_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_sb_get_req_dump * +devlink_sb_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_get_req_dump)); +} +void devlink_sb_get_req_dump_free(struct devlink_sb_get_req_dump *req); + +static inline void +devlink_sb_get_req_dump_set_bus_name(struct devlink_sb_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_get_req_dump_set_dev_name(struct devlink_sb_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_sb_get_list { + struct devlink_sb_get_list *next; + struct devlink_sb_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp); + +struct devlink_sb_get_list * +devlink_sb_get_dump(struct ynl_sock *ys, struct devlink_sb_get_req_dump *req); + +/* ============== DEVLINK_CMD_SB_POOL_GET ============== */ +/* DEVLINK_CMD_SB_POOL_GET - do */ +struct devlink_sb_pool_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 sb_index:1; + __u32 sb_pool_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 sb_index; + __u16 sb_pool_index; +}; + +static inline struct devlink_sb_pool_get_req * +devlink_sb_pool_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_pool_get_req)); +} +void devlink_sb_pool_get_req_free(struct devlink_sb_pool_get_req *req); + +static inline void +devlink_sb_pool_get_req_set_bus_name(struct devlink_sb_pool_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_pool_get_req_set_dev_name(struct devlink_sb_pool_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_sb_pool_get_req_set_sb_index(struct devlink_sb_pool_get_req *req, + __u32 sb_index) +{ + req->_present.sb_index = 1; + req->sb_index = sb_index; +} +static inline void +devlink_sb_pool_get_req_set_sb_pool_index(struct devlink_sb_pool_get_req *req, + __u16 sb_pool_index) +{ + req->_present.sb_pool_index = 1; + req->sb_pool_index = sb_pool_index; +} + +struct devlink_sb_pool_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 sb_index:1; + __u32 sb_pool_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 sb_index; + __u16 sb_pool_index; +}; + +void devlink_sb_pool_get_rsp_free(struct devlink_sb_pool_get_rsp *rsp); + +/* + * Get shared buffer pool instances. + */ +struct devlink_sb_pool_get_rsp * +devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req); + +/* DEVLINK_CMD_SB_POOL_GET - dump */ +struct devlink_sb_pool_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_sb_pool_get_req_dump * +devlink_sb_pool_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_pool_get_req_dump)); +} +void +devlink_sb_pool_get_req_dump_free(struct devlink_sb_pool_get_req_dump *req); + +static inline void +devlink_sb_pool_get_req_dump_set_bus_name(struct devlink_sb_pool_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_pool_get_req_dump_set_dev_name(struct devlink_sb_pool_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_sb_pool_get_list { + struct devlink_sb_pool_get_list *next; + struct devlink_sb_pool_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp); + +struct devlink_sb_pool_get_list * +devlink_sb_pool_get_dump(struct ynl_sock *ys, + struct devlink_sb_pool_get_req_dump *req); + +/* ============== DEVLINK_CMD_SB_PORT_POOL_GET ============== */ +/* DEVLINK_CMD_SB_PORT_POOL_GET - do */ +struct devlink_sb_port_pool_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 sb_index:1; + __u32 sb_pool_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + __u32 sb_index; + __u16 sb_pool_index; +}; + +static inline struct devlink_sb_port_pool_get_req * +devlink_sb_port_pool_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_port_pool_get_req)); +} +void +devlink_sb_port_pool_get_req_free(struct devlink_sb_port_pool_get_req *req); + +static inline void +devlink_sb_port_pool_get_req_set_bus_name(struct devlink_sb_port_pool_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_port_pool_get_req_set_dev_name(struct devlink_sb_port_pool_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_sb_port_pool_get_req_set_port_index(struct devlink_sb_port_pool_get_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_sb_port_pool_get_req_set_sb_index(struct devlink_sb_port_pool_get_req *req, + __u32 sb_index) +{ + req->_present.sb_index = 1; + req->sb_index = sb_index; +} +static inline void +devlink_sb_port_pool_get_req_set_sb_pool_index(struct devlink_sb_port_pool_get_req *req, + __u16 sb_pool_index) +{ + req->_present.sb_pool_index = 1; + req->sb_pool_index = sb_pool_index; +} + +struct devlink_sb_port_pool_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 sb_index:1; + __u32 sb_pool_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + __u32 sb_index; + __u16 sb_pool_index; +}; + +void +devlink_sb_port_pool_get_rsp_free(struct devlink_sb_port_pool_get_rsp *rsp); + +/* + * Get shared buffer port-pool combinations and threshold. + */ +struct devlink_sb_port_pool_get_rsp * +devlink_sb_port_pool_get(struct ynl_sock *ys, + struct devlink_sb_port_pool_get_req *req); + +/* DEVLINK_CMD_SB_PORT_POOL_GET - dump */ +struct devlink_sb_port_pool_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_sb_port_pool_get_req_dump * +devlink_sb_port_pool_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_port_pool_get_req_dump)); +} +void +devlink_sb_port_pool_get_req_dump_free(struct devlink_sb_port_pool_get_req_dump *req); + +static inline void +devlink_sb_port_pool_get_req_dump_set_bus_name(struct devlink_sb_port_pool_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_port_pool_get_req_dump_set_dev_name(struct devlink_sb_port_pool_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_sb_port_pool_get_list { + struct devlink_sb_port_pool_get_list *next; + struct devlink_sb_port_pool_get_rsp obj __attribute__ ((aligned (8))); +}; + +void +devlink_sb_port_pool_get_list_free(struct devlink_sb_port_pool_get_list *rsp); + +struct devlink_sb_port_pool_get_list * +devlink_sb_port_pool_get_dump(struct ynl_sock *ys, + struct devlink_sb_port_pool_get_req_dump *req); + +/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_GET ============== */ +/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */ +struct devlink_sb_tc_pool_bind_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 sb_index:1; + __u32 sb_pool_type:1; + __u32 sb_tc_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + __u32 sb_index; + enum devlink_sb_pool_type sb_pool_type; + __u16 sb_tc_index; +}; + +static inline struct devlink_sb_tc_pool_bind_get_req * +devlink_sb_tc_pool_bind_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_tc_pool_bind_get_req)); +} +void +devlink_sb_tc_pool_bind_get_req_free(struct devlink_sb_tc_pool_bind_get_req *req); + +static inline void +devlink_sb_tc_pool_bind_get_req_set_bus_name(struct devlink_sb_tc_pool_bind_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_tc_pool_bind_get_req_set_dev_name(struct devlink_sb_tc_pool_bind_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_sb_tc_pool_bind_get_req_set_port_index(struct devlink_sb_tc_pool_bind_get_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_sb_tc_pool_bind_get_req_set_sb_index(struct devlink_sb_tc_pool_bind_get_req *req, + __u32 sb_index) +{ + req->_present.sb_index = 1; + req->sb_index = sb_index; +} +static inline void +devlink_sb_tc_pool_bind_get_req_set_sb_pool_type(struct devlink_sb_tc_pool_bind_get_req *req, + enum devlink_sb_pool_type sb_pool_type) +{ + req->_present.sb_pool_type = 1; + req->sb_pool_type = sb_pool_type; +} +static inline void +devlink_sb_tc_pool_bind_get_req_set_sb_tc_index(struct devlink_sb_tc_pool_bind_get_req *req, + __u16 sb_tc_index) +{ + req->_present.sb_tc_index = 1; + req->sb_tc_index = sb_tc_index; +} + +struct devlink_sb_tc_pool_bind_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 sb_index:1; + __u32 sb_pool_type:1; + __u32 sb_tc_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + __u32 sb_index; + enum devlink_sb_pool_type sb_pool_type; + __u16 sb_tc_index; +}; + +void +devlink_sb_tc_pool_bind_get_rsp_free(struct devlink_sb_tc_pool_bind_get_rsp *rsp); + +/* + * Get shared buffer port-TC to pool bindings and threshold. + */ +struct devlink_sb_tc_pool_bind_get_rsp * +devlink_sb_tc_pool_bind_get(struct ynl_sock *ys, + struct devlink_sb_tc_pool_bind_get_req *req); + +/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - dump */ +struct devlink_sb_tc_pool_bind_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_sb_tc_pool_bind_get_req_dump * +devlink_sb_tc_pool_bind_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_tc_pool_bind_get_req_dump)); +} +void +devlink_sb_tc_pool_bind_get_req_dump_free(struct devlink_sb_tc_pool_bind_get_req_dump *req); + +static inline void +devlink_sb_tc_pool_bind_get_req_dump_set_bus_name(struct devlink_sb_tc_pool_bind_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_tc_pool_bind_get_req_dump_set_dev_name(struct devlink_sb_tc_pool_bind_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_sb_tc_pool_bind_get_list { + struct devlink_sb_tc_pool_bind_get_list *next; + struct devlink_sb_tc_pool_bind_get_rsp obj __attribute__ ((aligned (8))); +}; + +void +devlink_sb_tc_pool_bind_get_list_free(struct devlink_sb_tc_pool_bind_get_list *rsp); + +struct devlink_sb_tc_pool_bind_get_list * +devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys, + struct devlink_sb_tc_pool_bind_get_req_dump *req); + +/* ============== DEVLINK_CMD_PARAM_GET ============== */ +/* DEVLINK_CMD_PARAM_GET - do */ +struct devlink_param_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 param_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *param_name; +}; + +static inline struct devlink_param_get_req *devlink_param_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_param_get_req)); +} +void devlink_param_get_req_free(struct devlink_param_get_req *req); + +static inline void +devlink_param_get_req_set_bus_name(struct devlink_param_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_param_get_req_set_dev_name(struct devlink_param_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_param_get_req_set_param_name(struct devlink_param_get_req *req, + const char *param_name) +{ + free(req->param_name); + req->_present.param_name_len = strlen(param_name); + req->param_name = malloc(req->_present.param_name_len + 1); + memcpy(req->param_name, param_name, req->_present.param_name_len); + req->param_name[req->_present.param_name_len] = 0; +} + +struct devlink_param_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 param_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *param_name; +}; + +void devlink_param_get_rsp_free(struct devlink_param_get_rsp *rsp); + +/* + * Get param instances. + */ +struct devlink_param_get_rsp * +devlink_param_get(struct ynl_sock *ys, struct devlink_param_get_req *req); + +/* DEVLINK_CMD_PARAM_GET - dump */ +struct devlink_param_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_param_get_req_dump * +devlink_param_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_param_get_req_dump)); +} +void devlink_param_get_req_dump_free(struct devlink_param_get_req_dump *req); + +static inline void +devlink_param_get_req_dump_set_bus_name(struct devlink_param_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_param_get_req_dump_set_dev_name(struct devlink_param_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_param_get_list { + struct devlink_param_get_list *next; + struct devlink_param_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_param_get_list_free(struct devlink_param_get_list *rsp); + +struct devlink_param_get_list * +devlink_param_get_dump(struct ynl_sock *ys, + struct devlink_param_get_req_dump *req); + +/* ============== DEVLINK_CMD_REGION_GET ============== */ +/* DEVLINK_CMD_REGION_GET - do */ +struct devlink_region_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 region_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *region_name; +}; + +static inline struct devlink_region_get_req *devlink_region_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_region_get_req)); +} +void devlink_region_get_req_free(struct devlink_region_get_req *req); + +static inline void +devlink_region_get_req_set_bus_name(struct devlink_region_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_region_get_req_set_dev_name(struct devlink_region_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_region_get_req_set_port_index(struct devlink_region_get_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_region_get_req_set_region_name(struct devlink_region_get_req *req, + const char *region_name) +{ + free(req->region_name); + req->_present.region_name_len = strlen(region_name); + req->region_name = malloc(req->_present.region_name_len + 1); + memcpy(req->region_name, region_name, req->_present.region_name_len); + req->region_name[req->_present.region_name_len] = 0; +} + +struct devlink_region_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 region_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *region_name; +}; + +void devlink_region_get_rsp_free(struct devlink_region_get_rsp *rsp); + +/* + * Get region instances. + */ +struct devlink_region_get_rsp * +devlink_region_get(struct ynl_sock *ys, struct devlink_region_get_req *req); + +/* DEVLINK_CMD_REGION_GET - dump */ +struct devlink_region_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_region_get_req_dump * +devlink_region_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_region_get_req_dump)); +} +void devlink_region_get_req_dump_free(struct devlink_region_get_req_dump *req); + +static inline void +devlink_region_get_req_dump_set_bus_name(struct devlink_region_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_region_get_req_dump_set_dev_name(struct devlink_region_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_region_get_list { + struct devlink_region_get_list *next; + struct devlink_region_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_region_get_list_free(struct devlink_region_get_list *rsp); + +struct devlink_region_get_list * +devlink_region_get_dump(struct ynl_sock *ys, + struct devlink_region_get_req_dump *req); + /* ============== DEVLINK_CMD_INFO_GET ============== */ /* DEVLINK_CMD_INFO_GET - do */ struct devlink_info_get_req { @@ -217,4 +1151,842 @@ void devlink_info_get_list_free(struct devlink_info_get_list *rsp); struct devlink_info_get_list *devlink_info_get_dump(struct ynl_sock *ys); +/* ============== DEVLINK_CMD_HEALTH_REPORTER_GET ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_GET - do */ +struct devlink_health_reporter_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 health_reporter_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *health_reporter_name; +}; + +static inline struct devlink_health_reporter_get_req * +devlink_health_reporter_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_health_reporter_get_req)); +} +void +devlink_health_reporter_get_req_free(struct devlink_health_reporter_get_req *req); + +static inline void +devlink_health_reporter_get_req_set_bus_name(struct devlink_health_reporter_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_health_reporter_get_req_set_dev_name(struct devlink_health_reporter_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_health_reporter_get_req_set_port_index(struct devlink_health_reporter_get_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_health_reporter_get_req_set_health_reporter_name(struct devlink_health_reporter_get_req *req, + const char *health_reporter_name) +{ + free(req->health_reporter_name); + req->_present.health_reporter_name_len = strlen(health_reporter_name); + req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1); + memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len); + req->health_reporter_name[req->_present.health_reporter_name_len] = 0; +} + +struct devlink_health_reporter_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 health_reporter_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *health_reporter_name; +}; + +void +devlink_health_reporter_get_rsp_free(struct devlink_health_reporter_get_rsp *rsp); + +/* + * Get health reporter instances. + */ +struct devlink_health_reporter_get_rsp * +devlink_health_reporter_get(struct ynl_sock *ys, + struct devlink_health_reporter_get_req *req); + +/* DEVLINK_CMD_HEALTH_REPORTER_GET - dump */ +struct devlink_health_reporter_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; +}; + +static inline struct devlink_health_reporter_get_req_dump * +devlink_health_reporter_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_health_reporter_get_req_dump)); +} +void +devlink_health_reporter_get_req_dump_free(struct devlink_health_reporter_get_req_dump *req); + +static inline void +devlink_health_reporter_get_req_dump_set_bus_name(struct devlink_health_reporter_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_health_reporter_get_req_dump_set_dev_name(struct devlink_health_reporter_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_health_reporter_get_req_dump_set_port_index(struct devlink_health_reporter_get_req_dump *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} + +struct devlink_health_reporter_get_list { + struct devlink_health_reporter_get_list *next; + struct devlink_health_reporter_get_rsp obj __attribute__ ((aligned (8))); +}; + +void +devlink_health_reporter_get_list_free(struct devlink_health_reporter_get_list *rsp); + +struct devlink_health_reporter_get_list * +devlink_health_reporter_get_dump(struct ynl_sock *ys, + struct devlink_health_reporter_get_req_dump *req); + +/* ============== DEVLINK_CMD_TRAP_GET ============== */ +/* DEVLINK_CMD_TRAP_GET - do */ +struct devlink_trap_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 trap_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *trap_name; +}; + +static inline struct devlink_trap_get_req *devlink_trap_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_trap_get_req)); +} +void devlink_trap_get_req_free(struct devlink_trap_get_req *req); + +static inline void +devlink_trap_get_req_set_bus_name(struct devlink_trap_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_trap_get_req_set_dev_name(struct devlink_trap_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_trap_get_req_set_trap_name(struct devlink_trap_get_req *req, + const char *trap_name) +{ + free(req->trap_name); + req->_present.trap_name_len = strlen(trap_name); + req->trap_name = malloc(req->_present.trap_name_len + 1); + memcpy(req->trap_name, trap_name, req->_present.trap_name_len); + req->trap_name[req->_present.trap_name_len] = 0; +} + +struct devlink_trap_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 trap_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *trap_name; +}; + +void devlink_trap_get_rsp_free(struct devlink_trap_get_rsp *rsp); + +/* + * Get trap instances. + */ +struct devlink_trap_get_rsp * +devlink_trap_get(struct ynl_sock *ys, struct devlink_trap_get_req *req); + +/* DEVLINK_CMD_TRAP_GET - dump */ +struct devlink_trap_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_trap_get_req_dump * +devlink_trap_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_trap_get_req_dump)); +} +void devlink_trap_get_req_dump_free(struct devlink_trap_get_req_dump *req); + +static inline void +devlink_trap_get_req_dump_set_bus_name(struct devlink_trap_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_trap_get_req_dump_set_dev_name(struct devlink_trap_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_trap_get_list { + struct devlink_trap_get_list *next; + struct devlink_trap_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_trap_get_list_free(struct devlink_trap_get_list *rsp); + +struct devlink_trap_get_list * +devlink_trap_get_dump(struct ynl_sock *ys, + struct devlink_trap_get_req_dump *req); + +/* ============== DEVLINK_CMD_TRAP_GROUP_GET ============== */ +/* DEVLINK_CMD_TRAP_GROUP_GET - do */ +struct devlink_trap_group_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 trap_group_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *trap_group_name; +}; + +static inline struct devlink_trap_group_get_req * +devlink_trap_group_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_trap_group_get_req)); +} +void devlink_trap_group_get_req_free(struct devlink_trap_group_get_req *req); + +static inline void +devlink_trap_group_get_req_set_bus_name(struct devlink_trap_group_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_trap_group_get_req_set_dev_name(struct devlink_trap_group_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_trap_group_get_req_set_trap_group_name(struct devlink_trap_group_get_req *req, + const char *trap_group_name) +{ + free(req->trap_group_name); + req->_present.trap_group_name_len = strlen(trap_group_name); + req->trap_group_name = malloc(req->_present.trap_group_name_len + 1); + memcpy(req->trap_group_name, trap_group_name, req->_present.trap_group_name_len); + req->trap_group_name[req->_present.trap_group_name_len] = 0; +} + +struct devlink_trap_group_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 trap_group_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *trap_group_name; +}; + +void devlink_trap_group_get_rsp_free(struct devlink_trap_group_get_rsp *rsp); + +/* + * Get trap group instances. + */ +struct devlink_trap_group_get_rsp * +devlink_trap_group_get(struct ynl_sock *ys, + struct devlink_trap_group_get_req *req); + +/* DEVLINK_CMD_TRAP_GROUP_GET - dump */ +struct devlink_trap_group_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_trap_group_get_req_dump * +devlink_trap_group_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_trap_group_get_req_dump)); +} +void +devlink_trap_group_get_req_dump_free(struct devlink_trap_group_get_req_dump *req); + +static inline void +devlink_trap_group_get_req_dump_set_bus_name(struct devlink_trap_group_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_trap_group_get_req_dump_set_dev_name(struct devlink_trap_group_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_trap_group_get_list { + struct devlink_trap_group_get_list *next; + struct devlink_trap_group_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_trap_group_get_list_free(struct devlink_trap_group_get_list *rsp); + +struct devlink_trap_group_get_list * +devlink_trap_group_get_dump(struct ynl_sock *ys, + struct devlink_trap_group_get_req_dump *req); + +/* ============== DEVLINK_CMD_TRAP_POLICER_GET ============== */ +/* DEVLINK_CMD_TRAP_POLICER_GET - do */ +struct devlink_trap_policer_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 trap_policer_id:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 trap_policer_id; +}; + +static inline struct devlink_trap_policer_get_req * +devlink_trap_policer_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_trap_policer_get_req)); +} +void +devlink_trap_policer_get_req_free(struct devlink_trap_policer_get_req *req); + +static inline void +devlink_trap_policer_get_req_set_bus_name(struct devlink_trap_policer_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_trap_policer_get_req_set_dev_name(struct devlink_trap_policer_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_trap_policer_get_req_set_trap_policer_id(struct devlink_trap_policer_get_req *req, + __u32 trap_policer_id) +{ + req->_present.trap_policer_id = 1; + req->trap_policer_id = trap_policer_id; +} + +struct devlink_trap_policer_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 trap_policer_id:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 trap_policer_id; +}; + +void +devlink_trap_policer_get_rsp_free(struct devlink_trap_policer_get_rsp *rsp); + +/* + * Get trap policer instances. + */ +struct devlink_trap_policer_get_rsp * +devlink_trap_policer_get(struct ynl_sock *ys, + struct devlink_trap_policer_get_req *req); + +/* DEVLINK_CMD_TRAP_POLICER_GET - dump */ +struct devlink_trap_policer_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_trap_policer_get_req_dump * +devlink_trap_policer_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_trap_policer_get_req_dump)); +} +void +devlink_trap_policer_get_req_dump_free(struct devlink_trap_policer_get_req_dump *req); + +static inline void +devlink_trap_policer_get_req_dump_set_bus_name(struct devlink_trap_policer_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_trap_policer_get_req_dump_set_dev_name(struct devlink_trap_policer_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_trap_policer_get_list { + struct devlink_trap_policer_get_list *next; + struct devlink_trap_policer_get_rsp obj __attribute__ ((aligned (8))); +}; + +void +devlink_trap_policer_get_list_free(struct devlink_trap_policer_get_list *rsp); + +struct devlink_trap_policer_get_list * +devlink_trap_policer_get_dump(struct ynl_sock *ys, + struct devlink_trap_policer_get_req_dump *req); + +/* ============== DEVLINK_CMD_RATE_GET ============== */ +/* DEVLINK_CMD_RATE_GET - do */ +struct devlink_rate_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 rate_node_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *rate_node_name; +}; + +static inline struct devlink_rate_get_req *devlink_rate_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_rate_get_req)); +} +void devlink_rate_get_req_free(struct devlink_rate_get_req *req); + +static inline void +devlink_rate_get_req_set_bus_name(struct devlink_rate_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_rate_get_req_set_dev_name(struct devlink_rate_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_rate_get_req_set_port_index(struct devlink_rate_get_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_rate_get_req_set_rate_node_name(struct devlink_rate_get_req *req, + const char *rate_node_name) +{ + free(req->rate_node_name); + req->_present.rate_node_name_len = strlen(rate_node_name); + req->rate_node_name = malloc(req->_present.rate_node_name_len + 1); + memcpy(req->rate_node_name, rate_node_name, req->_present.rate_node_name_len); + req->rate_node_name[req->_present.rate_node_name_len] = 0; +} + +struct devlink_rate_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 rate_node_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *rate_node_name; +}; + +void devlink_rate_get_rsp_free(struct devlink_rate_get_rsp *rsp); + +/* + * Get rate instances. + */ +struct devlink_rate_get_rsp * +devlink_rate_get(struct ynl_sock *ys, struct devlink_rate_get_req *req); + +/* DEVLINK_CMD_RATE_GET - dump */ +struct devlink_rate_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_rate_get_req_dump * +devlink_rate_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_rate_get_req_dump)); +} +void devlink_rate_get_req_dump_free(struct devlink_rate_get_req_dump *req); + +static inline void +devlink_rate_get_req_dump_set_bus_name(struct devlink_rate_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_rate_get_req_dump_set_dev_name(struct devlink_rate_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_rate_get_list { + struct devlink_rate_get_list *next; + struct devlink_rate_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_rate_get_list_free(struct devlink_rate_get_list *rsp); + +struct devlink_rate_get_list * +devlink_rate_get_dump(struct ynl_sock *ys, + struct devlink_rate_get_req_dump *req); + +/* ============== DEVLINK_CMD_LINECARD_GET ============== */ +/* DEVLINK_CMD_LINECARD_GET - do */ +struct devlink_linecard_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 linecard_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 linecard_index; +}; + +static inline struct devlink_linecard_get_req * +devlink_linecard_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_linecard_get_req)); +} +void devlink_linecard_get_req_free(struct devlink_linecard_get_req *req); + +static inline void +devlink_linecard_get_req_set_bus_name(struct devlink_linecard_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_linecard_get_req_set_dev_name(struct devlink_linecard_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_linecard_get_req_set_linecard_index(struct devlink_linecard_get_req *req, + __u32 linecard_index) +{ + req->_present.linecard_index = 1; + req->linecard_index = linecard_index; +} + +struct devlink_linecard_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 linecard_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 linecard_index; +}; + +void devlink_linecard_get_rsp_free(struct devlink_linecard_get_rsp *rsp); + +/* + * Get line card instances. + */ +struct devlink_linecard_get_rsp * +devlink_linecard_get(struct ynl_sock *ys, struct devlink_linecard_get_req *req); + +/* DEVLINK_CMD_LINECARD_GET - dump */ +struct devlink_linecard_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_linecard_get_req_dump * +devlink_linecard_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_linecard_get_req_dump)); +} +void +devlink_linecard_get_req_dump_free(struct devlink_linecard_get_req_dump *req); + +static inline void +devlink_linecard_get_req_dump_set_bus_name(struct devlink_linecard_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_linecard_get_req_dump_set_dev_name(struct devlink_linecard_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_linecard_get_list { + struct devlink_linecard_get_list *next; + struct devlink_linecard_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_linecard_get_list_free(struct devlink_linecard_get_list *rsp); + +struct devlink_linecard_get_list * +devlink_linecard_get_dump(struct ynl_sock *ys, + struct devlink_linecard_get_req_dump *req); + +/* ============== DEVLINK_CMD_SELFTESTS_GET ============== */ +/* DEVLINK_CMD_SELFTESTS_GET - do */ +struct devlink_selftests_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_selftests_get_req * +devlink_selftests_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_selftests_get_req)); +} +void devlink_selftests_get_req_free(struct devlink_selftests_get_req *req); + +static inline void +devlink_selftests_get_req_set_bus_name(struct devlink_selftests_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_selftests_get_req_set_dev_name(struct devlink_selftests_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_selftests_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +void devlink_selftests_get_rsp_free(struct devlink_selftests_get_rsp *rsp); + +/* + * Get device selftest instances. + */ +struct devlink_selftests_get_rsp * +devlink_selftests_get(struct ynl_sock *ys, + struct devlink_selftests_get_req *req); + +/* DEVLINK_CMD_SELFTESTS_GET - dump */ +struct devlink_selftests_get_list { + struct devlink_selftests_get_list *next; + struct devlink_selftests_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_selftests_get_list_free(struct devlink_selftests_get_list *rsp); + +struct devlink_selftests_get_list * +devlink_selftests_get_dump(struct ynl_sock *ys); + #endif /* _LINUX_DEVLINK_GEN_H */ diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index 3ca28d4bcb18..6951bcc7efdc 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -395,7 +395,10 @@ class YnlFamily(SpecFamily): self.family.genl_family['mcast'][mcast_name]) def _add_attr(self, space, name, value): - attr = self.attr_sets[space][name] + try: + attr = self.attr_sets[space][name] + except KeyError: + raise Exception(f"Space '{space}' has no attribute '{name}'") nl_type = attr.value if attr["type"] == 'nest': nl_type |= Netlink.NLA_F_NESTED @@ -450,7 +453,10 @@ class YnlFamily(SpecFamily): attr_space = self.attr_sets[space] rsp = dict() for attr in attrs: - attr_spec = attr_space.attrs_by_val[attr.type] + try: + attr_spec = attr_space.attrs_by_val[attr.type] + except KeyError: + raise Exception(f"Space '{space}' has no attribute with value '{attr.type}'") if attr_spec["type"] == 'nest': subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes']) decoded = subdict @@ -479,7 +485,10 @@ class YnlFamily(SpecFamily): def _decode_extack_path(self, attrs, attr_set, offset, target): for attr in attrs: - attr_spec = attr_set.attrs_by_val[attr.type] + try: + attr_spec = attr_set.attrs_by_val[attr.type] + except KeyError: + raise Exception(f"Space '{attr_set.name}' has no attribute with value '{attr.type}'") if offset > target: break if offset == target: diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh index 71c00bfafbc9..7b2d421f09cf 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh @@ -11,7 +11,6 @@ finish() { ip netns delete server || true ip netns delete client || true - ip link del link1_1 || true } trap finish EXIT diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 04341e1b38f0..8b017070960d 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -40,6 +40,7 @@ TEST_PROGS += srv6_end_dt6_l3vpn_test.sh TEST_PROGS += srv6_hencap_red_l3vpn_test.sh TEST_PROGS += srv6_hl2encap_red_l2vpn_test.sh TEST_PROGS += srv6_end_next_csid_l3vpn_test.sh +TEST_PROGS += srv6_end_x_next_csid_l3vpn_test.sh TEST_PROGS += srv6_end_flavors_test.sh TEST_PROGS += vrf_strict_mode_test.sh TEST_PROGS += arp_ndisc_evict_nocarrier.sh diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 35d89dfa6f11..c14ad6e75c1e 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -9,13 +9,16 @@ ret=0 ksft_skip=4 # all tests in this script. Can be overridden with -t option -TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh" +TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \ + ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics \ + ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr \ + ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test" VERBOSE=0 PAUSE_ON_FAIL=no PAUSE=no -IP="ip -netns ns1" -NS_EXEC="ip netns exec ns1" +IP="$(which ip) -netns ns1" +NS_EXEC="$(which ip) netns exec ns1" which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) @@ -747,6 +750,68 @@ fib_notify_test() cleanup &> /dev/null } +fib6_gc_test() +{ + setup + + echo + echo "Fib6 garbage collection test" + set -e + + EXPIRE=3 + + # Check expiration of routes every $EXPIRE seconds (GC) + $NS_EXEC sysctl -wq net.ipv6.route.gc_interval=$EXPIRE + + $IP link add dummy_10 type dummy + $IP link set dev dummy_10 up + $IP -6 address add 2001:10::1/64 dev dummy_10 + + $NS_EXEC sysctl -wq net.ipv6.route.flush=1 + + # Temporary routes + for i in $(seq 1 1000); do + # Expire route after $EXPIRE seconds + $IP -6 route add 2001:20::$i \ + via 2001:10::2 dev dummy_10 expires $EXPIRE + done + sleep $(($EXPIRE * 2)) + N_EXP_SLEEP=$($IP -6 route list |grep expires|wc -l) + if [ $N_EXP_SLEEP -ne 0 ]; then + echo "FAIL: expected 0 routes with expires, got $N_EXP_SLEEP" + ret=1 + else + ret=0 + fi + + # Permanent routes + for i in $(seq 1 5000); do + $IP -6 route add 2001:30::$i \ + via 2001:10::2 dev dummy_10 + done + # Temporary routes + for i in $(seq 1 1000); do + # Expire route after $EXPIRE seconds + $IP -6 route add 2001:20::$i \ + via 2001:10::2 dev dummy_10 expires $EXPIRE + done + sleep $(($EXPIRE * 2)) + N_EXP_SLEEP=$($IP -6 route list |grep expires|wc -l) + if [ $N_EXP_SLEEP -ne 0 ]; then + echo "FAIL: expected 0 routes with expires," \ + "got $N_EXP_SLEEP (5000 permanent routes)" + ret=1 + else + ret=0 + fi + + set +e + + log_test $ret 0 "ipv6 route garbage collection" + + cleanup &> /dev/null +} + fib_suppress_test() { echo @@ -2217,6 +2282,7 @@ do ipv4_mangle) ipv4_mangle_test;; ipv6_mangle) ipv6_mangle_test;; ipv4_bcast_neigh) ipv4_bcast_neigh_test;; + fib6_gc_test|ipv6_gc) fib6_gc_test;; help) echo "Test names: $TESTS"; exit 0;; esac diff --git a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh index dc92d32464f6..9af9f6964808 100755 --- a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh +++ b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh @@ -9,6 +9,7 @@ ALL_TESTS=" locked_port_mab_roam locked_port_mab_config locked_port_mab_flush + locked_port_mab_redirect " NUM_NETIFS=4 @@ -319,6 +320,41 @@ locked_port_mab_flush() log_test "Locked port MAB FDB flush" } +# Check that traffic can be redirected from a locked bridge port and that it +# does not create locked FDB entries. +locked_port_mab_redirect() +{ + RET=0 + check_port_mab_support || return 0 + + bridge link set dev $swp1 learning on locked on mab on + tc qdisc add dev $swp1 clsact + tc filter add dev $swp1 ingress protocol all pref 1 handle 101 flower \ + action mirred egress redirect dev $swp2 + + ping_do $h1 192.0.2.2 + check_err $? "Ping did not work with redirection" + + bridge fdb get `mac_get $h1` br br0 vlan 1 2> /dev/null | \ + grep "dev $swp1" | grep -q "locked" + check_fail $? "Locked entry created for redirected traffic" + + tc filter del dev $swp1 ingress protocol all pref 1 handle 101 flower + + ping_do $h1 192.0.2.2 + check_fail $? "Ping worked without redirection" + + bridge fdb get `mac_get $h1` br br0 vlan 1 2> /dev/null | \ + grep "dev $swp1" | grep -q "locked" + check_err $? "Locked entry not created after deleting filter" + + bridge fdb del `mac_get $h1` vlan 1 dev $swp1 master + tc qdisc del dev $swp1 clsact + bridge link set dev $swp1 learning off locked off mab off + + log_test "Locked port MAB redirect" +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index dced4f612a78..9c2012d70b08 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -16,7 +16,8 @@ tests=" connect_v4 ip4-xon: Basic ipv4 ping between two NS nat_connect_v4 ip4-nat-xon: Basic ipv4 tcp connection via NAT netlink_checks ovsnl: validate netlink attrs and settings - upcall_interfaces ovs: test the upcall interfaces" + upcall_interfaces ovs: test the upcall interfaces + drop_reason drop: test drop reasons are emitted" info() { [ $VERBOSE = 0 ] || echo $* @@ -141,6 +142,25 @@ ovs_add_flow () { return 0 } +ovs_drop_record_and_run () { + local sbx=$1 + shift + + perf record -a -q -e skb:kfree_skb -o ${ovs_dir}/perf.data $* \ + >> ${ovs_dir}/stdout 2>> ${ovs_dir}/stderr + return $? +} + +ovs_drop_reason_count() +{ + local reason=$1 + + local perf_output=`perf script -i ${ovs_dir}/perf.data -F trace:event,trace` + local pattern="skb:kfree_skb:.*reason: $reason" + + return `echo "$perf_output" | grep "$pattern" | wc -l` +} + usage() { echo echo "$0 [OPTIONS] [TEST]..." @@ -155,6 +175,76 @@ usage() { exit 1 } +# drop_reason test +# - drop packets and verify the right drop reason is reported +test_drop_reason() { + which perf >/dev/null 2>&1 || return $ksft_skip + + sbx_add "test_drop_reason" || return $? + + ovs_add_dp "test_drop_reason" dropreason || return 1 + + info "create namespaces" + for ns in client server; do + ovs_add_netns_and_veths "test_drop_reason" "dropreason" "$ns" \ + "${ns:0:1}0" "${ns:0:1}1" || return 1 + done + + # Setup client namespace + ip netns exec client ip addr add 172.31.110.10/24 dev c1 + ip netns exec client ip link set c1 up + + # Setup server namespace + ip netns exec server ip addr add 172.31.110.20/24 dev s1 + ip netns exec server ip link set s1 up + + # Allow ARP + ovs_add_flow "test_drop_reason" dropreason \ + 'in_port(1),eth(),eth_type(0x0806),arp()' '2' || return 1 + ovs_add_flow "test_drop_reason" dropreason \ + 'in_port(2),eth(),eth_type(0x0806),arp()' '1' || return 1 + + # Allow client ICMP traffic but drop return path + ovs_add_flow "test_drop_reason" dropreason \ + "in_port(1),eth(),eth_type(0x0800),ipv4(src=172.31.110.10,proto=1),icmp()" '2' + ovs_add_flow "test_drop_reason" dropreason \ + "in_port(2),eth(),eth_type(0x0800),ipv4(src=172.31.110.20,proto=1),icmp()" 'drop' + + ovs_drop_record_and_run "test_drop_reason" ip netns exec client ping -c 2 172.31.110.20 + ovs_drop_reason_count 0x30001 # OVS_DROP_FLOW_ACTION + if [[ "$?" -ne "2" ]]; then + info "Did not detect expected drops: $?" + return 1 + fi + + # Drop UDP 6000 traffic with an explicit action and an error code. + ovs_add_flow "test_drop_reason" dropreason \ + "in_port(1),eth(),eth_type(0x0800),ipv4(src=172.31.110.10,proto=17),udp(dst=6000)" \ + 'drop(42)' + # Drop UDP 7000 traffic with an explicit action with no error code. + ovs_add_flow "test_drop_reason" dropreason \ + "in_port(1),eth(),eth_type(0x0800),ipv4(src=172.31.110.10,proto=17),udp(dst=7000)" \ + 'drop(0)' + + ovs_drop_record_and_run \ + "test_drop_reason" ip netns exec client nc -i 1 -zuv 172.31.110.20 6000 + ovs_drop_reason_count 0x30004 # OVS_DROP_EXPLICIT_ACTION_ERROR + if [[ "$?" -ne "1" ]]; then + info "Did not detect expected explicit error drops: $?" + return 1 + fi + + ovs_drop_record_and_run \ + "test_drop_reason" ip netns exec client nc -i 1 -zuv 172.31.110.20 7000 + ovs_drop_reason_count 0x30003 # OVS_DROP_EXPLICIT_ACTION + if [[ "$?" -ne "1" ]]; then + info "Did not detect expected explicit drops: $?" + return 1 + fi + + return 0 +} + # arp_ping test # - client has 1500 byte MTU # - server has 1500 byte MTU @@ -393,6 +483,16 @@ test_netlink_checks () { wc -l) == 2 ] || \ return 1 + ERR_MSG="Flow actions may not be safe on all matching packets" + PRE_TEST=$(dmesg | grep -c "${ERR_MSG}") + ovs_add_flow "test_netlink_checks" nv0 \ + 'in_port(1),eth(),eth_type(0x0806),arp()' 'drop(0),2' \ + &> /dev/null && return 1 + POST_TEST=$(dmesg | grep -c "${ERR_MSG}") + if [ "$PRE_TEST" == "$POST_TEST" ]; then + info "failed - error not generated" + return 1 + fi return 0 } diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index fbdac15e3134..912dc8c49085 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -301,6 +301,7 @@ class ovsactions(nla): ("OVS_ACTION_ATTR_CHECK_PKT_LEN", "none"), ("OVS_ACTION_ATTR_ADD_MPLS", "none"), ("OVS_ACTION_ATTR_DEC_TTL", "none"), + ("OVS_ACTION_ATTR_DROP", "uint32"), ) class ctact(nla): @@ -447,6 +448,8 @@ class ovsactions(nla): print_str += "recirc(0x%x)" % int(self.get_attr(field[0])) elif field[0] == "OVS_ACTION_ATTR_TRUNC": print_str += "trunc(%d)" % int(self.get_attr(field[0])) + elif field[0] == "OVS_ACTION_ATTR_DROP": + print_str += "drop(%d)" % int(self.get_attr(field[0])) elif field[1] == "flag": if field[0] == "OVS_ACTION_ATTR_CT_CLEAR": print_str += "ct_clear" @@ -468,10 +471,21 @@ class ovsactions(nla): while len(actstr) != 0: parsed = False if actstr.startswith("drop"): - # for now, drops have no explicit action, so we - # don't need to set any attributes. The final - # act of the processing chain will just drop the packet - return + # If no reason is provided, the implicit drop is used (i.e no + # action). If some reason is given, an explicit action is used. + actstr, reason = parse_extract_field( + actstr, + "drop(", + "([0-9]+)", + lambda x: int(x, 0), + False, + None, + ) + if reason is not None: + self["attrs"].append(["OVS_ACTION_ATTR_DROP", reason]) + parsed = True + else: + return elif parse_starts_block(actstr, "^(\d+)", False, True): actstr, output = parse_extract_field( diff --git a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh new file mode 100755 index 000000000000..c79cb8ede17f --- /dev/null +++ b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh @@ -0,0 +1,1213 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# author: Andrea Mayer <[email protected]> +# author: Paolo Lungaroni <[email protected]> +# +# This script is designed for testing the support of NEXT-C-SID flavor for SRv6 +# End.X behavior. +# A basic knowledge of SRv6 architecture [1] and of the compressed SID approach +# [2] is assumed for the reader. +# +# The network topology used in the selftest is depicted hereafter, composed of +# two hosts and four routers. Hosts hs-1 and hs-2 are connected through an +# IPv4/IPv6 L3 VPN service, offered by routers rt-1, rt-2, rt-3 and rt-4 using +# the NEXT-C-SID flavor. The key components for such VPNs are: +# +# i) The SRv6 H.Encaps/H.Encaps.Red behaviors [1] apply SRv6 Policies on +# traffic received by connected hosts, initiating the VPN tunnel; +# +# ii) The SRv6 End.X behavior [1] (Endpoint with L3 cross connect) is a +# variant of SRv6 End behavior. It advances the active SID in the SID +# List carried by the SRH and forwards the packet to an L3 adjacency; +# +# iii) The NEXT-C-SID mechanism [2] offers the possibility of encoding several +# SRv6 segments within a single 128-bit SID address, referred to as a +# Compressed SID (C-SID) container. In this way, the length of the SID +# List can be drastically reduced. +# The NEXT-C-SID is provided as a "flavor" of the SRv6 End.X behavior +# which advances the current C-SID (i.e. the Locator-Node Function defined +# in [2]) with the next one carried in the Argument, if available. +# When no more C-SIDs are available in the Argument, the SRv6 End.X +# behavior will apply the End.X function selecting the next SID in the SID +# List; +# +# iv) The SRv6 End.DT46 behavior [1] is used for removing the SRv6 Policy and, +# thus, it terminates the VPN tunnel. Such a behavior is capable of +# handling, at the same time, both tunneled IPv4 and IPv6 traffic. +# +# [1] https://datatracker.ietf.org/doc/html/rfc8986 +# [2] https://datatracker.ietf.org/doc/html/draft-ietf-spring-srv6-srh-compression +# +# +# cafe::1 cafe::2 +# 10.0.0.1 10.0.0.2 +# +--------+ +--------+ +# | | | | +# | hs-1 | | hs-2 | +# | | | | +# +---+----+ +----+---+ +# cafe::/64 | | cafe::/64 +# 10.0.0.0/24 | | 10.0.0.0/24 +# +---+----+ +----+---+ +# | | fcf0:0:1:2::/64 | | +# | rt-1 +-------------------+ rt-2 | +# | | | | +# +---+----+ +----+---+ +# | . . | +# | fcf0:0:1:3::/64 . | +# | . . | +# | . . | +# fcf0:0:1:4::/64 | . | fcf0:0:2:3::/64 +# | . . | +# | . . | +# | fcf0:0:2:4::/64 . | +# | . . | +# +---+----+ +----+---+ +# | | | | +# | rt-4 +-------------------+ rt-3 | +# | | fcf0:0:3:4::/64 | | +# +---+----+ +----+---+ +# +# Every fcf0:0:x:y::/64 network interconnects the SRv6 routers rt-x with rt-y in +# the selftest network. +# +# Local SID/C-SID table +# ===================== +# +# Each SRv6 router is configured with a Local SID/C-SID table in which +# SIDs/C-SIDs are stored. Considering an SRv6 router rt-x, SIDs/C-SIDs are +# configured in the Local SID/C-SIDs table as follows: +# +# Local SID/C-SID table for SRv6 router rt-x +# +-----------------------------------------------------------+ +# |fcff:x::d46 is associated with the non-compressed SRv6 | +# | End.DT46 behavior | +# +-----------------------------------------------------------+ +# |fcbb:0:0x00::/48 is associated with the NEXT-C-SID flavor | +# | of SRv6 End.X behavior | +# +-----------------------------------------------------------+ +# |fcbb:0:0x00:d46::/64 is associated with the SRv6 End.DT46 | +# | behavior when NEXT-C-SID compression is turned on | +# +-----------------------------------------------------------+ +# +# The fcff::/16 prefix is reserved for implementing SRv6 services with regular +# (non compressed) SIDs. Reachability of SIDs is ensured by proper configuration +# of the IPv6 routing tables in the routers. +# Similarly, the fcbb:0::/32 prefix is reserved for implementing SRv6 VPN +# services leveraging the NEXT-C-SID compression mechanism. Indeed, the +# fcbb:0::/32 is used for encoding the Locator-Block while the Locator-Node +# Function is encoded with 16 bits. +# +# Incoming traffic classification and application of SRv6 Policies +# ================================================================ +# +# An SRv6 ingress router applies different SRv6 Policies to the traffic received +# from a connected host, considering the IPv4 or IPv6 destination address. +# SRv6 policy enforcement consists of encapsulating the received traffic into a +# new IPv6 packet with a given SID List contained in the SRH. +# When the SID List contains only one SID, the SRH could be omitted completely +# and that SID is stored directly in the IPv6 Destination Address (DA) (this is +# called "reduced" encapsulation). +# +# Test cases for NEXT-C-SID +# ========================= +# +# We consider two test cases for NEXT-C-SID: i) single SID and ii) double SID. +# +# In the single SID test case we have a number of segments that are all +# contained in a single Compressed SID (C-SID) container. Therefore the +# resulting SID List has only one SID. Using the reduced encapsulation format +# this will result in a packet with no SRH. +# +# In the double SID test case we have one segment carried in a Compressed SID +# (C-SID) container, followed by a regular (non compressed) SID. The resulting +# SID List has two segments and it is possible to test the advance to the next +# SID when all the C-SIDs in a C-SID container have been processed. Using the +# reduced encapsulation format this will result in a packet with an SRH +# containing 1 segment. +# +# For the single SID test case, we use the IPv6 addresses of hs-1 and hs-2, for +# the double SID test case, we use their IPv4 addresses. This is only done to +# simplify the test setup and avoid adding other hosts or multiple addresses on +# the same interface of a host. +# +# Traffic from hs-1 to hs-2 +# ------------------------- +# +# Packets generated from hs-1 and directed towards hs-2 are handled by rt-1 +# which applies the SRv6 Policies as follows: +# +# i) IPv6 DA=cafe::2, H.Encaps.Red with SID List=fcbb:0:0300:0200:d46:: +# ii) IPv4 DA=10.0.0.2, H.Encaps.Red with SID List=fcbb:0:0300::,fcff:2::d46 +# +# ### i) single SID +# +# The router rt-1 is configured to enforce the given Policy through the SRv6 +# H.Encaps.Red behavior which avoids the presence of the SRH at all, since it +# pushes the single SID directly in the IPv6 DA. Such a SID encodes a whole +# C-SID container carrying several C-SIDs (e.g. 0300, 0200, etc). +# +# As the packet reaches the router rt-3, the enabled NEXT-C-SID SRv6 End.X +# behavior (associated with fcbb:0:0300::/48) is triggered. This behavior +# analyzes the IPv6 DA and checks whether the Argument of the C-SID container +# is zero or not. In this case, the Argument is *NOT* zero and the IPv6 DA is +# updated as follows: +# +# +-----------------------------------------------------------------+ +# | Before applying the rt-3 enabled NEXT-C-SID SRv6 End.X behavior | +# +-----------------------------------------------------------------+ +# | +---------- Argument | +# | vvvvvvvvvv | +# | IPv6 DA fcbb:0:0300:0200:d46:: | +# | ^^^^ <-- shifting | +# | | | +# | Locator-Node Function | +# +-----------------------------------------------------------------+ +# | After applying the rt-3 enabled NEXT-C-SID SRv6 End.X behavior | +# +-----------------------------------------------------------------+ +# | +---------- Argument | +# | vvvvvv | +# | IPv6 DA fcbb:0:0200:d46:: | +# | ^^^^ | +# | | | +# | Locator-Node Function | +# +-----------------------------------------------------------------+ +# +# After having applied the enabled NEXT-C-SID SRv6 End.X behavior, the packet +# is sent to rt-4 node using the L3 adjacency address fcf0:0:3:4::4. +# +# The node rt-4 performs a plain IPv6 forward to the rt-2 router according to +# its Local SID table and using the IPv6 DA fcbb:0:0200:d46:: . +# +# The router rt-2 is configured for decapsulating the inner IPv6 packet and, +# for this reason, it applies the SRv6 End.DT46 behavior on the received +# packet. It is worth noting that the SRv6 End.DT46 behavior does not require +# the presence of the SRH: it is fully capable to operate properly on +# IPv4/IPv6-in-IPv6 encapsulations. +# At the end of the decap operation, the packet is sent to the host hs-2. +# +# ### ii) double SID +# +# The router rt-1 is configured to enforce the given Policy through the SRv6 +# H.Encaps.Red. As a result, the first SID fcbb:0:0300:: is stored into the +# IPv6 DA, while the SRH pushed into the packet is made of only one SID, i.e. +# fcff:2::d46. Hence, the packet sent by hs-1 to hs-2 is encapsulated in an +# outer IPv6 header plus the SRH. +# +# As the packet reaches the node rt-3, the router applies the enabled NEXT-C-SID +# SRv6 End.X behavior. +# +# +-----------------------------------------------------------------+ +# | Before applying the rt-3 enabled NEXT-C-SID SRv6 End.X behavior | +# +-----------------------------------------------------------------+ +# | +---------- Argument | +# | vvvv (Argument is all filled with zeros) | +# | IPv6 DA fcbb:0:0300:: | +# | ^^^^ | +# | | | +# | Locator-Node Function | +# +-----------------------------------------------------------------+ +# | After applying the rt-3 enabled NEXT-C-SID SRv6 End.X behavior | +# +-----------------------------------------------------------------+ +# | | +# | IPv6 DA fcff:2::d46 | +# | ^^^^^^^^^^^ | +# | | | +# | SID copied from the SID List contained in the SRH | +# +-----------------------------------------------------------------+ +# +# Since the Argument of the C-SID container is zero, the behavior can not +# update the Locator-Node function with the next C-SID carried in the Argument +# itself. Thus, the enabled NEXT-C-SID SRv6 End.X behavior operates as the +# traditional End.X behavior: it updates the IPv6 DA by copying the next +# available SID in the SID List carried by the SRH. Next, the packet is +# forwarded to the rt-4 node using the L3 adjacency fcf0:3:4::4 previously +# configured for this behavior. +# +# The node rt-4 performs a plain IPv6 forward to the rt-2 router according to +# its Local SID table and using the IPv6 DA fcff:2::d46. +# +# Once the packet is received by rt-2, the router decapsulates the inner IPv4 +# packet using the SRv6 End.DT46 behavior (associated with the SID fcff:2::d46) +# and sends it to the host hs-2. +# +# Traffic from hs-2 to hs-1 +# ------------------------- +# +# Packets generated from hs-2 and directed towards hs-1 are handled by rt-2 +# which applies the SRv6 Policies as follows: +# +# i) IPv6 DA=cafe::1, SID List=fcbb:0:0400:0100:d46:: +# ii) IPv4 DA=10.0.0.1, SID List=fcbb:0:0300::,fcff:1::d46 +# +# ### i) single SID +# +# The node hs-2 sends an IPv6 packet directed to node hs-1. The router rt-2 is +# directly connected to hs-2 and receives the packet. Rt-2 applies the +# H.Encap.Red behavior with policy i) described above. Since there is only one +# SID, the SRH header is omitted and the policy is inserted directly into the DA +# of IPv6 packet. +# +# The packet reaches the router rt-4 and the enabled NEXT-C-SID SRv6 End.X +# behavior (associated with fcbb:0:0400::/48) is triggered. This behavior +# analyzes the IPv6 DA and checks whether the Argument of the C-SID container +# is zero or not. The Argument is *NOT* zero and the C-SID in the IPv6 DA is +# advanced. At this point, the current IPv6 DA is fcbb:0:0100:d46:: . +# The enabled NEXT-C-SID SRv6 End.X behavior is configured with the L3 adjacency +# fcf0:0:1:4::1, used to route traffic to the rt-1 node. +# +# The router rt-1 is configured for decapsulating the inner packet. It applies +# the SRv6 End.DT46 behavior on the received packet. Decapsulation does not +# require the presence of the SRH. At the end of the decap operation, the packet +# is sent to the host hs-1. +# +# ### ii) double SID +# +# The router rt-2 is configured to enforce the given Policy through the SRv6 +# H.Encaps.Red. As a result, the first SID fcbb:0:0300:: is stored into the +# IPv6 DA, while the SRH pushed into the packet is made of only one SID, i.e. +# fcff:1::d46. Hence, the packet sent by hs-2 to hs-1 is encapsulated in an +# outer IPv6 header plus the SRH. +# +# As the packet reaches the node rt-3, the enabled NEXT-C-SID SRv6 End.X +# behavior bound to the SID fcbb:0:0300::/48 is triggered. +# Since the Argument of the C-SID container is zero, the behavior can not +# update the Locator-Node function with the next C-SID carried in the Argument +# itself. Thus, the enabled NEXT-C-SID SRv6 End-X behavior operates as the +# traditional End.X behavior: it updates the IPv6 DA by copying the next +# available SID in the SID List carried by the SRH. After that, the packet is +# forwarded to the rt-4 node using the L3 adjacency (fcf0:3:4::4) previously +# configured for this behavior. +# +# The node rt-4 performs a plain IPv6 forward to the rt-1 router according to +# its Local SID table, considering the IPv6 DA fcff:1::d46. +# +# Once the packet is received by rt-1, the router decapsulates the inner IPv4 +# packet using the SRv6 End.DT46 behavior (associated with the SID fcff:1::d46) +# and sends it to the host hs-1. + +# Kselftest framework requirement - SKIP code is 4. +readonly ksft_skip=4 + +readonly RDMSUFF="$(mktemp -u XXXXXXXX)" +readonly DUMMY_DEVNAME="dum0" +readonly VRF_TID=100 +readonly VRF_DEVNAME="vrf-${VRF_TID}" +readonly RT2HS_DEVNAME="veth-t${VRF_TID}" +readonly LOCALSID_TABLE_ID=90 +readonly IPv6_RT_NETWORK=fcf0:0 +readonly IPv6_HS_NETWORK=cafe +readonly IPv4_HS_NETWORK=10.0.0 +readonly VPN_LOCATOR_SERVICE=fcff +readonly DT46_FUNC=0d46 +readonly HEADEND_ENCAP="encap.red" + +# do not add ':' as separator +readonly LCBLOCK_ADDR=fcbb0000 +readonly LCBLOCK_BLEN=32 +# do not add ':' as separator +readonly LCNODEFUNC_FMT="0%d00" +readonly LCNODEFUNC_BLEN=16 + +readonly LCBLOCK_NODEFUNC_BLEN=$((LCBLOCK_BLEN + LCNODEFUNC_BLEN)) + +readonly CSID_CNTR_PREFIX="dead:beaf::/32" +# ID of the router used for testing the C-SID container cfgs +readonly CSID_CNTR_RT_ID_TEST=1 +# Routing table used for testing the C-SID container cfgs +readonly CSID_CNTR_RT_TABLE=91 + +# C-SID container configurations to be tested +# +# An entry of the array is defined as "a,b,c" where: +# - 'a' and 'b' elements represent respectively the Locator-Block length +# (lblen) in bits and the Locator-Node Function length (nflen) in bits. +# 'a' and 'b' can be set to default values using the placeholder "d" which +# indicates the default kernel values (32 for lblen and 16 for nflen); +# otherwise, any numeric value is accepted; +# - 'c' indicates whether the C-SID configuration provided by the values 'a' +# and 'b' should be considered valid ("y") or invalid ("n"). +declare -ra CSID_CONTAINER_CFGS=( + "d,d,y" + "d,16,y" + "16,d,y" + "16,32,y" + "32,16,y" + "48,8,y" + "8,48,y" + "d,0,n" + "0,d,n" + "32,0,n" + "0,32,n" + "17,d,n" + "d,17,n" + "120,16,n" + "16,120,n" + "0,128,n" + "128,0,n" + "130,0,n" + "0,130,n" + "0,0,n" +) + +PING_TIMEOUT_SEC=4 +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} + +# IDs of routers and hosts are initialized during the setup of the testing +# network +ROUTERS='' +HOSTS='' + +SETUP_ERR=1 + +ret=${ksft_skip} +nsuccess=0 +nfail=0 + +log_test() +{ + local rc="$1" + local expected="$2" + local msg="$3" + + if [ "${rc}" -eq "${expected}" ]; then + nsuccess=$((nsuccess+1)) + printf "\n TEST: %-60s [ OK ]\n" "${msg}" + else + ret=1 + nfail=$((nfail+1)) + printf "\n TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +print_log_test_results() +{ + printf "\nTests passed: %3d\n" "${nsuccess}" + printf "Tests failed: %3d\n" "${nfail}" + + # when a test fails, the value of 'ret' is set to 1 (error code). + # Conversely, when all tests are passed successfully, the 'ret' value + # is set to 0 (success code). + if [ "${ret}" -ne 1 ]; then + ret=0 + fi +} + +log_section() +{ + echo + echo "################################################################################" + echo "TEST SECTION: $*" + echo "################################################################################" +} + +test_command_or_ksft_skip() +{ + local cmd="$1" + + if [ ! -x "$(command -v "${cmd}")" ]; then + echo "SKIP: Could not run test without \"${cmd}\" tool"; + exit "${ksft_skip}" + fi +} + +get_nodename() +{ + local name="$1" + + echo "${name}-${RDMSUFF}" +} + +get_rtname() +{ + local rtid="$1" + + get_nodename "rt-${rtid}" +} + +get_hsname() +{ + local hsid="$1" + + get_nodename "hs-${hsid}" +} + +__create_namespace() +{ + local name="$1" + + ip netns add "${name}" +} + +create_router() +{ + local rtid="$1" + local nsname + + nsname="$(get_rtname "${rtid}")" + + __create_namespace "${nsname}" + + ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1 + + ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip netns exec "${nsname}" sysctl -wq net.ipv4.ip_forward=1 +} + +create_host() +{ + local hsid="$1" + local nsname + + nsname="$(get_hsname "${hsid}")" + + __create_namespace "${nsname}" +} + +cleanup() +{ + local nsname + local i + + # destroy routers + for i in ${ROUTERS}; do + nsname="$(get_rtname "${i}")" + + ip netns del "${nsname}" &>/dev/null || true + done + + # destroy hosts + for i in ${HOSTS}; do + nsname="$(get_hsname "${i}")" + + ip netns del "${nsname}" &>/dev/null || true + done + + # check whether the setup phase was completed successfully or not. In + # case of an error during the setup phase of the testing environment, + # the selftest is considered as "skipped". + if [ "${SETUP_ERR}" -ne 0 ]; then + echo "SKIP: Setting up the testing environment failed" + exit "${ksft_skip}" + fi + + exit "${ret}" +} + +add_link_rt_pairs() +{ + local rt="$1" + local rt_neighs="$2" + local neigh + local nsname + local neigh_nsname + + nsname="$(get_rtname "${rt}")" + + for neigh in ${rt_neighs}; do + neigh_nsname="$(get_rtname "${neigh}")" + + ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \ + type veth peer name "veth-rt-${neigh}-${rt}" \ + netns "${neigh_nsname}" + done +} + +get_network_prefix() +{ + local rt="$1" + local neigh="$2" + local p="${rt}" + local q="${neigh}" + + if [ "${p}" -gt "${q}" ]; then + p="${q}"; q="${rt}" + fi + + echo "${IPv6_RT_NETWORK}:${p}:${q}" +} + +# Setup the basic networking for the routers +setup_rt_networking() +{ + local rt="$1" + local rt_neighs="$2" + local nsname + local net_prefix + local devname + local neigh + + nsname="$(get_rtname "${rt}")" + + for neigh in ${rt_neighs}; do + devname="veth-rt-${rt}-${neigh}" + + net_prefix="$(get_network_prefix "${rt}" "${neigh}")" + + ip -netns "${nsname}" addr \ + add "${net_prefix}::${rt}/64" dev "${devname}" nodad + + ip -netns "${nsname}" link set "${devname}" up + done + + ip -netns "${nsname}" link add "${DUMMY_DEVNAME}" type dummy + + ip -netns "${nsname}" link set "${DUMMY_DEVNAME}" up + ip -netns "${nsname}" link set lo up +} + +# build an ipv6 prefix/address based on the input string +# Note that the input string does not contain ':' and '::' which are considered +# to be implicit. +# e.g.: +# - input: fbcc00000400300 +# - output: fbcc:0000:0400:0300:0000:0000:0000:0000 +# ^^^^^^^^^^^^^^^^^^^ +# fill the address with 0s +build_ipv6_addr() +{ + local addr="$1" + local out="" + local strlen="${#addr}" + local padn + local i + + # add ":" every 4 digits (16 bits) + for (( i = 0; i < strlen; i++ )); do + if (( i > 0 && i < 32 && (i % 4) == 0 )); then + out="${out}:" + fi + + out="${out}${addr:$i:1}" + done + + # fill the remaining bits of the address with 0s + padn=$((32 - strlen)) + for (( i = padn; i > 0; i-- )); do + if (( i > 0 && i < 32 && (i % 4) == 0 )); then + out="${out}:" + fi + + out="${out}0" + done + + printf "${out}" +} + +build_csid() +{ + local nodeid="$1" + + printf "${LCNODEFUNC_FMT}" "${nodeid}" +} + +build_lcnode_func_prefix() +{ + local nodeid="$1" + local lcnodefunc + local prefix + local out + + lcnodefunc="$(build_csid "${nodeid}")" + prefix="$(build_ipv6_addr "${LCBLOCK_ADDR}${lcnodefunc}")" + + out="${prefix}/${LCBLOCK_NODEFUNC_BLEN}" + + echo "${out}" +} + +set_end_x_nextcsid() +{ + local rt="$1" + local adj="$2" + + nsname="$(get_rtname "${rt}")" + net_prefix="$(get_network_prefix "${rt}" "${adj}")" + lcnode_func_prefix="$(build_lcnode_func_prefix "${rt}")" + + # enabled NEXT-C-SID SRv6 End.X behavior (note that "dev" is the dummy + # dum0 device chosen for the sake of simplicity). + ip -netns "${nsname}" -6 route \ + replace "${lcnode_func_prefix}" \ + table "${LOCALSID_TABLE_ID}" \ + encap seg6local action End.X nh6 "${net_prefix}::${adj}" \ + flavors next-csid lblen "${LCBLOCK_BLEN}" \ + nflen "${LCNODEFUNC_BLEN}" dev "${DUMMY_DEVNAME}" +} + +set_underlay_sids_reachability() +{ + local rt="$1" + local rt_neighs="$2" + + nsname="$(get_rtname "${rt}")" + + for neigh in ${rt_neighs}; do + devname="veth-rt-${rt}-${neigh}" + + net_prefix="$(get_network_prefix "${rt}" "${neigh}")" + + # set underlay network routes for SIDs reachability + ip -netns "${nsname}" -6 route \ + replace "${VPN_LOCATOR_SERVICE}:${neigh}::/32" \ + table "${LOCALSID_TABLE_ID}" \ + via "${net_prefix}::${neigh}" dev "${devname}" + + # set the underlay network for C-SIDs reachability + lcnode_func_prefix="$(build_lcnode_func_prefix "${neigh}")" + + ip -netns "${nsname}" -6 route \ + replace "${lcnode_func_prefix}" \ + table "${LOCALSID_TABLE_ID}" \ + via "${net_prefix}::${neigh}" dev "${devname}" + done +} + +# Setup local SIDs for an SRv6 router +setup_rt_local_sids() +{ + local rt="$1" + local rt_neighs="$2" + local net_prefix + local devname + local nsname + local neigh + local lcnode_func_prefix + local lcblock_prefix + + nsname="$(get_rtname "${rt}")" + + set_underlay_sids_reachability "${rt}" "${rt_neighs}" + + # all SIDs for VPNs start with a common locator. Routes and SRv6 + # Endpoint behavior instaces are grouped together in the 'localsid' + # table. + ip -netns "${nsname}" -6 rule \ + add to "${VPN_LOCATOR_SERVICE}::/16" \ + lookup "${LOCALSID_TABLE_ID}" prio 999 + + # common locator block for NEXT-C-SIDS compression mechanism. + lcblock_prefix="$(build_ipv6_addr "${LCBLOCK_ADDR}")" + ip -netns "${nsname}" -6 rule \ + add to "${lcblock_prefix}/${LCBLOCK_BLEN}" \ + lookup "${LOCALSID_TABLE_ID}" prio 999 +} + +# build and install the SRv6 policy into the ingress SRv6 router as well as the +# decap SID in the egress one. +# args: +# $1 - src host (evaluate automatically the ingress router) +# $2 - dst host (evaluate automatically the egress router) +# $3 - SRv6 routers configured for steering traffic (End.X behaviors) +# $4 - single SID or double SID +# $5 - traffic type (IPv6 or IPv4) +__setup_l3vpn() +{ + local src="$1" + local dst="$2" + local end_rts="$3" + local mode="$4" + local traffic="$5" + local nsname + local policy + local container + local decapsid + local lcnfunc + local dt + local n + local rtsrc_nsname + local rtdst_nsname + + rtsrc_nsname="$(get_rtname "${src}")" + rtdst_nsname="$(get_rtname "${dst}")" + + container="${LCBLOCK_ADDR}" + + # build first SID (C-SID container) + for n in ${end_rts}; do + lcnfunc="$(build_csid "${n}")" + + container="${container}${lcnfunc}" + done + + if [ "${mode}" -eq 1 ]; then + # single SID policy + dt="$(build_csid "${dst}")${DT46_FUNC}" + container="${container}${dt}" + # build the full ipv6 address for the container + policy="$(build_ipv6_addr "${container}")" + + # build the decap SID used in the decap node + container="${LCBLOCK_ADDR}${dt}" + decapsid="$(build_ipv6_addr "${container}")" + else + # double SID policy + decapsid="${VPN_LOCATOR_SERVICE}:${dst}::${DT46_FUNC}" + + policy="$(build_ipv6_addr "${container}"),${decapsid}" + fi + + # apply encap policy + if [ "${traffic}" -eq 6 ]; then + ip -netns "${rtsrc_nsname}" -6 route \ + add "${IPv6_HS_NETWORK}::${dst}" vrf "${VRF_DEVNAME}" \ + encap seg6 mode "${HEADEND_ENCAP}" segs "${policy}" \ + dev "${VRF_DEVNAME}" + + ip -netns "${rtsrc_nsname}" -6 neigh \ + add proxy "${IPv6_HS_NETWORK}::${dst}" \ + dev "${RT2HS_DEVNAME}" + else + # "dev" must be different from the one where the packet is + # received, otherwise the proxy arp does not work. + ip -netns "${rtsrc_nsname}" -4 route \ + add "${IPv4_HS_NETWORK}.${dst}" vrf "${VRF_DEVNAME}" \ + encap seg6 mode "${HEADEND_ENCAP}" segs "${policy}" \ + dev "${VRF_DEVNAME}" + fi + + # apply decap + # Local End.DT46 behavior (decap) + ip -netns "${rtdst_nsname}" -6 route \ + add "${decapsid}" \ + table "${LOCALSID_TABLE_ID}" \ + encap seg6local action End.DT46 vrftable "${VRF_TID}" \ + dev "${VRF_DEVNAME}" +} + +# see __setup_l3vpn() +setup_ipv4_vpn_2sids() +{ + __setup_l3vpn "$1" "$2" "$3" 2 4 +} + +# see __setup_l3vpn() +setup_ipv6_vpn_1sid() +{ + __setup_l3vpn "$1" "$2" "$3" 1 6 +} + +setup_hs() +{ + local hs="$1" + local rt="$2" + local hsname + local rtname + + hsname="$(get_hsname "${hs}")" + rtname="$(get_rtname "${rt}")" + + ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0 + + ip -netns "${hsname}" link add veth0 type veth \ + peer name "${RT2HS_DEVNAME}" netns "${rtname}" + + ip -netns "${hsname}" addr \ + add "${IPv6_HS_NETWORK}::${hs}/64" dev veth0 nodad + ip -netns "${hsname}" addr add "${IPv4_HS_NETWORK}.${hs}/24" dev veth0 + + ip -netns "${hsname}" link set veth0 up + ip -netns "${hsname}" link set lo up + + # configure the VRF on the router which is directly connected to the + # source host. + ip -netns "${rtname}" link \ + add "${VRF_DEVNAME}" type vrf table "${VRF_TID}" + ip -netns "${rtname}" link set "${VRF_DEVNAME}" up + + # enslave the veth interface connecting the router with the host to the + # VRF in the access router + ip -netns "${rtname}" link \ + set "${RT2HS_DEVNAME}" master "${VRF_DEVNAME}" + + # set default routes to unreachable for both ipv6 and ipv4 + ip -netns "${rtname}" -6 route \ + add unreachable default metric 4278198272 \ + vrf "${VRF_DEVNAME}" + ip -netns "${rtname}" -4 route \ + add unreachable default metric 4278198272 \ + vrf "${VRF_DEVNAME}" + + ip -netns "${rtname}" addr \ + add "${IPv6_HS_NETWORK}::254/64" dev "${RT2HS_DEVNAME}" nodad + ip -netns "${rtname}" addr \ + add "${IPv4_HS_NETWORK}.254/24" dev "${RT2HS_DEVNAME}" + + ip -netns "${rtname}" link set "${RT2HS_DEVNAME}" up + + ip netns exec "${rtname}" \ + sysctl -wq net.ipv6.conf."${RT2HS_DEVNAME}".proxy_ndp=1 + ip netns exec "${rtname}" \ + sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".proxy_arp=1 + + # disable the rp_filter otherwise the kernel gets confused about how + # to route decap ipv4 packets. + ip netns exec "${rtname}" \ + sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".rp_filter=0 + + ip netns exec "${rtname}" sh -c "echo 1 > /proc/sys/net/vrf/strict_mode" +} + +setup() +{ + local i + + # create routers + ROUTERS="1 2 3 4"; readonly ROUTERS + for i in ${ROUTERS}; do + create_router "${i}" + done + + # create hosts + HOSTS="1 2"; readonly HOSTS + for i in ${HOSTS}; do + create_host "${i}" + done + + # set up the links for connecting routers + add_link_rt_pairs 1 "2 3 4" + add_link_rt_pairs 2 "3 4" + add_link_rt_pairs 3 "4" + + # set up the basic connectivity of routers and routes required for + # reachability of SIDs. + setup_rt_networking 1 "2 3 4" + setup_rt_networking 2 "1 3 4" + setup_rt_networking 3 "1 2 4" + setup_rt_networking 4 "1 2 3" + + # set up the hosts connected to routers + setup_hs 1 1 + setup_hs 2 2 + + # set up default SRv6 Endpoints (i.e. SRv6 End and SRv6 End.DT46) + setup_rt_local_sids 1 "2 3 4" + setup_rt_local_sids 2 "1 3 4" + setup_rt_local_sids 3 "1 2 4" + setup_rt_local_sids 4 "1 2 3" + + # set up SRv6 Policies + + # create an IPv6 VPN between hosts hs-1 and hs-2. + # + # Direction hs-1 -> hs-2 + # - rt-1 encap (H.Encaps.Red) + # - rt-3 SRv6 End.X behavior adj rt-4 (NEXT-C-SID flavor) + # - rt-4 Plain IPv6 Forwarding to rt-2 + # - rt-2 SRv6 End.DT46 behavior + setup_ipv6_vpn_1sid 1 2 "3" + + # Direction hs2 -> hs-1 + # - rt-2 encap (H.Encaps.Red) + # - rt-4 SRv6 End.X behavior adj rt-1 (NEXT-C-SID flavor) + # - rt-1 SRv6 End.DT46 behavior + setup_ipv6_vpn_1sid 2 1 "4" + + # create an IPv4 VPN between hosts hs-1 and hs-2 + # + # Direction hs-1 -> hs-2 + # - rt-1 encap (H.Encaps.Red) + # - rt-3 SRv6 End.X behavior adj rt-4 (NEXT-C-SID flavor) + # - rt-4 Plain IPv6 Forwarding to rt-2 + # - rt-2 SRv6 End.DT46 behavior + setup_ipv4_vpn_2sids 1 2 "3" + + # Direction hs-2 -> hs-1 + # - rt-2 encap (H.Encaps.Red) + # - rt-3 SRv6 End.X behavior adj rt-4 (NEXT-C-SID flavor) + # - rt-4 Plain IPv6 Forwarding to rt-1 + # - rt-1 SRv6 End.DT46 behavior + setup_ipv4_vpn_2sids 2 1 "3" + + # Setup the adjacencies in the SRv6 aware routers + # - rt-3 SRv6 End.X adjacency with rt-4 + # - rt-4 SRv6 End.X adjacency with rt-1 + set_end_x_nextcsid 3 4 + set_end_x_nextcsid 4 1 + + # testing environment was set up successfully + SETUP_ERR=0 +} + +check_rt_connectivity() +{ + local rtsrc="$1" + local rtdst="$2" + local prefix + local rtsrc_nsname + + rtsrc_nsname="$(get_rtname "${rtsrc}")" + + prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")" + + ip netns exec "${rtsrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \ + "${prefix}::${rtdst}" >/dev/null 2>&1 +} + +check_and_log_rt_connectivity() +{ + local rtsrc="$1" + local rtdst="$2" + + check_rt_connectivity "${rtsrc}" "${rtdst}" + log_test $? 0 "Routers connectivity: rt-${rtsrc} -> rt-${rtdst}" +} + +check_hs_ipv6_connectivity() +{ + local hssrc="$1" + local hsdst="$2" + local hssrc_nsname + + hssrc_nsname="$(get_hsname "${hssrc}")" + + ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \ + "${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1 +} + +check_hs_ipv4_connectivity() +{ + local hssrc="$1" + local hsdst="$2" + local hssrc_nsname + + hssrc_nsname="$(get_hsname "${hssrc}")" + + ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \ + "${IPv4_HS_NETWORK}.${hsdst}" >/dev/null 2>&1 +} + +check_and_log_hs2gw_connectivity() +{ + local hssrc="$1" + + check_hs_ipv6_connectivity "${hssrc}" 254 + log_test $? 0 "IPv6 Hosts connectivity: hs-${hssrc} -> gw" + + check_hs_ipv4_connectivity "${hssrc}" 254 + log_test $? 0 "IPv4 Hosts connectivity: hs-${hssrc} -> gw" +} + +check_and_log_hs_ipv6_connectivity() +{ + local hssrc="$1" + local hsdst="$2" + + check_hs_ipv6_connectivity "${hssrc}" "${hsdst}" + log_test $? 0 "IPv6 Hosts connectivity: hs-${hssrc} -> hs-${hsdst}" +} + +check_and_log_hs_ipv4_connectivity() +{ + local hssrc="$1" + local hsdst="$2" + + check_hs_ipv4_connectivity "${hssrc}" "${hsdst}" + log_test $? 0 "IPv4 Hosts connectivity: hs-${hssrc} -> hs-${hsdst}" +} + +router_tests() +{ + local i + local j + + log_section "IPv6 routers connectivity test" + + for i in ${ROUTERS}; do + for j in ${ROUTERS}; do + if [ "${i}" -eq "${j}" ]; then + continue + fi + + check_and_log_rt_connectivity "${i}" "${j}" + done + done +} + +host2gateway_tests() +{ + local hs + + log_section "IPv4/IPv6 connectivity test among hosts and gateways" + + for hs in ${HOSTS}; do + check_and_log_hs2gw_connectivity "${hs}" + done +} + +host_vpn_tests() +{ + log_section "SRv6 VPN connectivity test hosts (h1 <-> h2, IPv6)" + + check_and_log_hs_ipv6_connectivity 1 2 + check_and_log_hs_ipv6_connectivity 2 1 + + log_section "SRv6 VPN connectivity test hosts (h1 <-> h2, IPv4)" + + check_and_log_hs_ipv4_connectivity 1 2 + check_and_log_hs_ipv4_connectivity 2 1 +} + +__nextcsid_end_x_behavior_test() +{ + local nsname="$1" + local cmd="$2" + local blen="$3" + local flen="$4" + local layout="" + + if [ "${blen}" != "d" ]; then + layout="${layout} lblen ${blen}" + fi + + if [ "${flen}" != "d" ]; then + layout="${layout} nflen ${flen}" + fi + + ip -netns "${nsname}" -6 route \ + "${cmd}" "${CSID_CNTR_PREFIX}" \ + table "${CSID_CNTR_RT_TABLE}" \ + encap seg6local action End.X nh6 :: \ + flavors next-csid ${layout} \ + dev "${DUMMY_DEVNAME}" &>/dev/null + + return "$?" +} + +rt_x_nextcsid_end_x_behavior_test() +{ + local rt="$1" + local blen="$2" + local flen="$3" + local nsname + local ret + + nsname="$(get_rtname "${rt}")" + + __nextcsid_end_x_behavior_test "${nsname}" "add" "${blen}" "${flen}" + ret="$?" + __nextcsid_end_x_behavior_test "${nsname}" "del" "${blen}" "${flen}" + + return "${ret}" +} + +__parse_csid_container_cfg() +{ + local cfg="$1" + local index="$2" + local out + + echo "${cfg}" | cut -d',' -f"${index}" +} + +csid_container_cfg_tests() +{ + local valid + local blen + local flen + local cfg + local ret + + log_section "C-SID Container config tests (legend: d='kernel default')" + + for cfg in "${CSID_CONTAINER_CFGS[@]}"; do + blen="$(__parse_csid_container_cfg "${cfg}" 1)" + flen="$(__parse_csid_container_cfg "${cfg}" 2)" + valid="$(__parse_csid_container_cfg "${cfg}" 3)" + + rt_x_nextcsid_end_x_behavior_test \ + "${CSID_CNTR_RT_ID_TEST}" \ + "${blen}" \ + "${flen}" + ret="$?" + + if [ "${valid}" == "y" ]; then + log_test "${ret}" 0 \ + "Accept valid C-SID container cfg (lblen=${blen}, nflen=${flen})" + else + log_test "${ret}" 2 \ + "Reject invalid C-SID container cfg (lblen=${blen}, nflen=${flen})" + fi + done +} + +test_iproute2_supp_or_ksft_skip() +{ + if ! ip route help 2>&1 | grep -qo "next-csid"; then + echo "SKIP: Missing SRv6 NEXT-C-SID flavor support in iproute2" + exit "${ksft_skip}" + fi +} + +test_dummy_dev_or_ksft_skip() +{ + local test_netns + + test_netns="dummy-$(mktemp -u XXXXXXXX)" + + if ! ip netns add "${test_netns}"; then + echo "SKIP: Cannot set up netns for testing dummy dev support" + exit "${ksft_skip}" + fi + + modprobe dummy &>/dev/null || true + if ! ip -netns "${test_netns}" link \ + add "${DUMMY_DEVNAME}" type dummy; then + echo "SKIP: dummy dev not supported" + + ip netns del "${test_netns}" + exit "${ksft_skip}" + fi + + ip netns del "${test_netns}" +} + +test_vrf_or_ksft_skip() +{ + modprobe vrf &>/dev/null || true + if [ ! -e /proc/sys/net/vrf/strict_mode ]; then + echo "SKIP: vrf sysctl does not exist" + exit "${ksft_skip}" + fi +} + +if [ "$(id -u)" -ne 0 ]; then + echo "SKIP: Need root privileges" + exit "${ksft_skip}" +fi + +# required programs to carry out this selftest +test_command_or_ksft_skip ip +test_command_or_ksft_skip ping +test_command_or_ksft_skip sysctl +test_command_or_ksft_skip grep +test_command_or_ksft_skip cut + +test_iproute2_supp_or_ksft_skip +test_dummy_dev_or_ksft_skip +test_vrf_or_ksft_skip + +set -e +trap cleanup EXIT + +setup +set +e + +csid_container_cfg_tests + +router_tests +host2gateway_tests +host_vpn_tests + +print_log_test_results |