V8 rebase+review changes #11
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add a protocol spec for DPLL. Add code generated from the spec. Signed-off-by: Jakub Kicinski <[email protected]> Signed-off-by: Michal Michalik <[email protected]> Signed-off-by: Arkadiusz Kubalewski <[email protected]> Signed-off-by: Vadim Fedorenko <[email protected]>
DPLL framework is used to represent and configure DPLL devices in systems. Each device that has DPLL and can configure sources and outputs can use this framework. Netlink interface is used to provide configuration data and to receive notification messages about changes in the configuration or status of DPLL device. Inputs and outputs of the DPLL device are represented as special objects which could be dynamically added to and removed from DPLL device. Co-developed-by: Milena Olech <[email protected]> Signed-off-by: Milena Olech <[email protected]> Co-developed-by: Michal Michalik <[email protected]> Signed-off-by: Michal Michalik <[email protected]> Co-developed-by: Arkadiusz Kubalewski <[email protected]> Signed-off-by: Arkadiusz Kubalewski <[email protected]> Signed-off-by: Vadim Fedorenko <[email protected]>
Add documentation explaining common netlink interface to configure DPLL devices and monitoring events. Common way to implement DPLL device in a driver is also covered. Signed-off-by: Vadim Fedorenko <[email protected]> Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Add firmware admin command to access clock generation unit configuration, it is required to enable Extended PTP and SyncE features in the driver. Add definitions of possible hardware variations of input and output pins related to clock generation unit and functions to access the data. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Control over clock generation unit is required for further development of Synchronous Ethernet feature. Interface provides ability to obtain current state of a dpll, its sources and outputs which are pins, and allows their configuration. Co-developed-by: Milena Olech <[email protected]> Signed-off-by: Milena Olech <[email protected]> Co-developed-by: Michal Michalik <[email protected]> Signed-off-by: Michal Michalik <[email protected]> Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Implement basic DPLL operations in ptp_ocp driver as the simplest example of using new subsystem. Signed-off-by: Vadim Fedorenko <[email protected]>
In case netdevice represents a SyncE port, the user needs to understand the connection between netdevice and associated DPLL pin. There might me multiple netdevices pointing to the same pin, in case of VF/SF implementation. Add a IFLA Netlink attribute to nest the DPLL pin handle, similar to how is is implemented for devlink port. Add a struct dpll_pin pointer to netdev and protect access to it by RTNL. Expose netdev_dpll_pin_set() and netdev_dpll_pin_clear() helpers to the drivers so they can set/clear the DPLL pin relationship to netdev. Note that during the lifetime of struct dpll_pin the handle fields do not change. Therefore it is save to access them lockless. It is drivers responsibility to call netdev_dpll_pin_clear() before dpll_pin_put(). Signed-off-by: Jiri Pirko <[email protected]>
Implement SyncE support using newly introduced DPLL support. Make sure that each PFs/VFs/SFs probed with appropriate capability will spawn a dpll auxiliary device and register appropriate dpll device and pin instances. Signed-off-by: Jiri Pirko <[email protected]>
Policy defines max as length of enum list, if enum attribute is defined with a value, generated netlink policy max value is wrong. Calculate proper max value of policy for enums that are given a value. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Attributes are not used, remove them and start with a value given. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Remove unspec attributes after removing from dpll netlink spec. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Remove unspec attributes after removing from dpll netlink spec. Fixes: 6348a82 ("ice: add admin commands to access cgu configuration") Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Remove unspec attributes after removing from dpll netlink spec. Fixes: bff85d9 ("ice: implement dpll interface to control cgu") Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Add missing frequencies to the dpll ynl spec, so their defines are properly generated. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
- remove "no holdover available" from freerun mode description - improve description of holdover lock-status - fix temperature typo Signed-off-by: Arkadiusz Kubalewski <[email protected]>
ice_dpll_pin flags field is intended to store flags that were received after getting pin info from firmware, stop using it on set commands, as the flags of set commands can have different meaning and values. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Use ice_dpll_pin's 'state' field to provide state to the caller, as well as to check if state change requested shall be proceeded. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Remove attribute values of subset attributes, they are no longer needed as ynl lib was fixed. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Move device 'nest' to the end of the dpll netlink attributes. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
'device' nested attribute shall be used only for receiving data from pin-get do/dump commands. Use it this way and define list of expected list of attributes for device-get which are not nested. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Previously the docs reffered to DPLL_MODE_FORCED mode, but its name was changed to DPLL_MODE_MANUAL, fix it. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Previously temperature could be supplied with one digit float precision, use divider value of 1000 instead of 10 and allow three digit float precision for users. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Enum in subset attribute definition is redundant and not used for anything in YNL spec, remove it. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Previously it was possible to have different pin-direction returned to the user depending on which dpll was given as argument for pin-get cmd. If pin was registered with multiple dplls each could have reported different direction. I.e. driver exposes chained pins, where one pin is an input for one dpll and an output for second dpll. Fix it by enclosing pin-direction in the 'device' nested attribute. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Previously it was possible to have different pin-direction returned to the user depending on which dpll was given as argument for pin-get cmd. If pin was registered with multiple dplls each could have reported different direction. I.e. driver exposes chained pins, where one pin is an input for one dpll and an output for second dpll. Fix it by enclosing pin-direction in the 'device' nested attribute. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
The header is already included in linux/dpll.h. Remove it. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Caller shall take care of checking if arguments are valid, remove it. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Propagate error return value of netlink callback mutex lock function to the caller, a dpll subsystem. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Replace if statements with enum values to the switch case statements. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
In case of runtime errors the dev_err macro shall be used for printing the traces. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Previously IS_ERR_OR_NULL was used worngly as the function cannot return NULL, use IS_ERR instead. In case of error, return original error value. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
When source pin changes previous source state notification shall be also requested, request it. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Simplify code by locking dpll subsystem once and releasing all the resources, instead of locking per each resource release. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Use proper way of setting bits for capabilities field. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Align function name with dpll counterpart (rename from ice_dpll_register_pins to ice_dpll_init_pins), similarly old ice_dpll_init_pins function renamed to ice_dpll_init_pins_info. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Change the clock_id function to return clock ID on the stack instead of using an output variable, in order to simplify the function. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Remove the mode as it is not used by any of the in-kernel drivers implementing the dpll subsystem. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Remove the mode as it is not used by any of the in-kernel drivers implementing the dpll subsystem. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
DPLL_LOCK_STATUS_CALIBRATING is removed, when dpll is locked with a source signal it shall return DPLL_LOCK_STATUS_LOCKED, if it is capable of holdover with that signal it shall return it's state as: DPLL_LOCK_STATUS_LOCKED_HO_ACQ Signed-off-by: Arkadiusz Kubalewski <[email protected]>
DPLL_LOCK_STATUS_CALIBRATING is removed, when dpll is locked with a source signal it shall return DPLL_LOCK_STATUS_LOCKED, if it is capable of holdover with that signal it shall return it's state as: DPLL_LOCK_STATUS_LOCKED_HO_ACQ Signed-off-by: Arkadiusz Kubalewski <[email protected]>
DPLL_LOCK_STATUS_CALIBRATING was removed, return: DPLL_LOCK_STATUS_LOCKED - if dpll was locked DPLL_LOCK_STATUS_LOCKED_HO_ACQ - if dpll was locked and holdover is acquired. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Propagate and use dpll_priv to obtain pf pointer in corresponding functions. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Pointer is given back from dpll subsystem, it cannot null unless dpll subsystem is broken. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Define notifications as commands as expected by yaml spec. Add separated notification for pin events. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Align with new notification names. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Use separated notifications for dpll pins and devices. Format the messages as corresponding get netlink commands. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Align with fixed notification scheme in dpll subsystem. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Align with fixed notification scheme in dpll subsystem. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Register a recoered clock pin of a pf in its netdevice struct. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Use full names of commands, attributes and values of dpll subsystem in the documentation. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Rename enum attributes name from dplla to dpll_a. Add name for dpll commands enum: dpll_cmd. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
The argument of notify functions shall be of 'enum dpll_cmd' type. Fix it. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Fix implementation of error paths in ice_dpll_init. Previously the implementation worked but error paths were not clear for the developers. Fix by providing separated functions for each error encountered during initialization. Fix function descriptions. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
Rename 'source' to 'input' as it is opposite of 'output', previous naming 'source' shall have 'sink' counterpart, but 'input'/'output' seems a better fit for explaining the pins existence reason. Fix function definition alignment. Signed-off-by: Arkadiusz Kubalewski <[email protected]>
kubalewski
pushed a commit
that referenced
this pull request
Jun 5, 2023
Commit 349d03f ("crypto: s390 - add crypto library interface for ChaCha20") added a library interface to the s390 specific ChaCha20 implementation. However no check was added to verify if the required facilities are installed before branching into the assembler code. If compiled into the kernel, this will lead to the following crash, if vector instructions are not available: data exception: 0007 ilc:3 [#1] SMP Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.3.0-rc7+ #11 Hardware name: IBM 3931 A01 704 (KVM/Linux) Krnl PSW : 0704e00180000000 000000001857277a (chacha20_vx+0x32/0x818) R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:2 PM:0 RI:0 EA:3 Krnl GPRS: 0000037f0000000a ffffffffffffff60 000000008184b000 0000000019f5c8e6 0000000000000109 0000037fffb13c58 0000037fffb13c78 0000000019bb1780 0000037fffb13c58 0000000019f5c8e6 000000008184b000 0000000000000109 00000000802d8000 0000000000000109 0000000018571ebc 0000037fffb13718 Krnl Code: 000000001857276a: c07000b1f80b larl %r7,0000000019bb1780 0000000018572770: a708000a lhi %r0,10 #0000000018572774: e78950000c36 vlm %v24,%v25,0(%r5),0 >000000001857277a: e7a060000806 vl %v26,0(%r6),0 0000000018572780: e7bf70004c36 vlm %v27,%v31,0(%r7),4 0000000018572786: e70b00000456 vlr %v0,%v27 000000001857278c: e71800000456 vlr %v1,%v24 0000000018572792: e74b00000456 vlr %v4,%v27 Call Trace: [<000000001857277a>] chacha20_vx+0x32/0x818 Last Breaking-Event-Address: [<0000000018571eb6>] chacha20_crypt_s390.constprop.0+0x6e/0xd8 ---[ end trace 0000000000000000 ]--- Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b Fix this by adding a missing MACHINE_HAS_VX check. Fixes: 349d03f ("crypto: s390 - add crypto library interface for ChaCha20") Reported-by: Marc Hartmayer <[email protected]> Cc: <[email protected]> # 5.19+ Reviewed-by: Harald Freudenberger <[email protected]> [[email protected]: remove duplicates in commit message] Signed-off-by: Heiko Carstens <[email protected]> Signed-off-by: Alexander Gordeev <[email protected]>
kubalewski
pushed a commit
that referenced
this pull request
Jun 5, 2023
The cited commit adds a compeletion to remove dependency on rtnl lock. But it causes a deadlock for multiple encapsulations: crash> bt ffff8aece8a64000 PID: 1514557 TASK: ffff8aece8a64000 CPU: 3 COMMAND: "tc" #0 [ffffa6d14183f368] __schedule at ffffffffb8ba7f45 #1 [ffffa6d14183f3f8] schedule at ffffffffb8ba8418 #2 [ffffa6d14183f418] schedule_preempt_disabled at ffffffffb8ba8898 #3 [ffffa6d14183f428] __mutex_lock at ffffffffb8baa7f8 #4 [ffffa6d14183f4d0] mutex_lock_nested at ffffffffb8baabeb #5 [ffffa6d14183f4e0] mlx5e_attach_encap at ffffffffc0f48c17 [mlx5_core] #6 [ffffa6d14183f628] mlx5e_tc_add_fdb_flow at ffffffffc0f39680 [mlx5_core] #7 [ffffa6d14183f688] __mlx5e_add_fdb_flow at ffffffffc0f3b636 [mlx5_core] #8 [ffffa6d14183f6f0] mlx5e_tc_add_flow at ffffffffc0f3bcdf [mlx5_core] #9 [ffffa6d14183f728] mlx5e_configure_flower at ffffffffc0f3c1d1 [mlx5_core] #10 [ffffa6d14183f790] mlx5e_rep_setup_tc_cls_flower at ffffffffc0f3d529 [mlx5_core] #11 [ffffa6d14183f7a0] mlx5e_rep_setup_tc_cb at ffffffffc0f3d714 [mlx5_core] #12 [ffffa6d14183f7b0] tc_setup_cb_add at ffffffffb8931bb8 #13 [ffffa6d14183f810] fl_hw_replace_filter at ffffffffc0dae901 [cls_flower] #14 [ffffa6d14183f8d8] fl_change at ffffffffc0db5c57 [cls_flower] #15 [ffffa6d14183f970] tc_new_tfilter at ffffffffb8936047 #16 [ffffa6d14183fac8] rtnetlink_rcv_msg at ffffffffb88c7c31 #17 [ffffa6d14183fb50] netlink_rcv_skb at ffffffffb8942853 #18 [ffffa6d14183fbc0] rtnetlink_rcv at ffffffffb88c1835 #19 [ffffa6d14183fbd0] netlink_unicast at ffffffffb8941f27 #20 [ffffa6d14183fc18] netlink_sendmsg at ffffffffb8942245 #21 [ffffa6d14183fc98] sock_sendmsg at ffffffffb887d482 #22 [ffffa6d14183fcb8] ____sys_sendmsg at ffffffffb887d81a #23 [ffffa6d14183fd38] ___sys_sendmsg at ffffffffb88806e2 vvfedorenko#24 [ffffa6d14183fe90] __sys_sendmsg at ffffffffb88807a2 vvfedorenko#25 [ffffa6d14183ff28] __x64_sys_sendmsg at ffffffffb888080f vvfedorenko#26 [ffffa6d14183ff38] do_syscall_64 at ffffffffb8b9b6a8 vvfedorenko#27 [ffffa6d14183ff50] entry_SYSCALL_64_after_hwframe at ffffffffb8c0007c crash> bt 0xffff8aeb07544000 PID: 1110766 TASK: ffff8aeb07544000 CPU: 0 COMMAND: "kworker/u20:9" #0 [ffffa6d14e6b7bd8] __schedule at ffffffffb8ba7f45 #1 [ffffa6d14e6b7c68] schedule at ffffffffb8ba8418 #2 [ffffa6d14e6b7c88] schedule_timeout at ffffffffb8baef88 #3 [ffffa6d14e6b7d10] wait_for_completion at ffffffffb8ba968b #4 [ffffa6d14e6b7d60] mlx5e_take_all_encap_flows at ffffffffc0f47ec4 [mlx5_core] #5 [ffffa6d14e6b7da0] mlx5e_rep_update_flows at ffffffffc0f3e734 [mlx5_core] #6 [ffffa6d14e6b7df8] mlx5e_rep_neigh_update at ffffffffc0f400bb [mlx5_core] #7 [ffffa6d14e6b7e50] process_one_work at ffffffffb80acc9c #8 [ffffa6d14e6b7ed0] worker_thread at ffffffffb80ad012 #9 [ffffa6d14e6b7f10] kthread at ffffffffb80b615d #10 [ffffa6d14e6b7f50] ret_from_fork at ffffffffb8001b2f After the first encap is attached, flow will be added to encap entry's flows list. If neigh update is running at this time, the following encaps of the flow can't hold the encap_tbl_lock and sleep. If neigh update thread is waiting for that flow's init_done, deadlock happens. Fix it by holding lock outside of the for loop. If neigh update is running, prevent encap flows from offloading. Since the lock is held outside of the for loop, concurrent creation of encap entries is not allowed. So remove unnecessary wait_for_completion call for res_ready. Fixes: 95435ad ("net/mlx5e: Only access fully initialized flows in neigh update") Signed-off-by: Chris Mi <[email protected]> Reviewed-by: Roi Dayan <[email protected]> Reviewed-by: Vlad Buslov <[email protected]> Signed-off-by: Saeed Mahameed <[email protected]>
kubalewski
pushed a commit
that referenced
this pull request
Jun 19, 2023
Currently, the per cpu upcall counters are allocated after the vport is created and inserted into the system. This could lead to the datapath accessing the counters before they are allocated resulting in a kernel Oops. Here is an example: PID: 59693 TASK: ffff0005f4f51500 CPU: 0 COMMAND: "ovs-vswitchd" #0 [ffff80000a39b5b0] __switch_to at ffffb70f0629f2f4 #1 [ffff80000a39b5d0] __schedule at ffffb70f0629f5cc #2 [ffff80000a39b650] preempt_schedule_common at ffffb70f0629fa60 #3 [ffff80000a39b670] dynamic_might_resched at ffffb70f0629fb58 #4 [ffff80000a39b680] mutex_lock_killable at ffffb70f062a1388 #5 [ffff80000a39b6a0] pcpu_alloc at ffffb70f0594460c #6 [ffff80000a39b750] __alloc_percpu_gfp at ffffb70f05944e68 #7 [ffff80000a39b760] ovs_vport_cmd_new at ffffb70ee6961b90 [openvswitch] ... PID: 58682 TASK: ffff0005b2f0bf00 CPU: 0 COMMAND: "kworker/0:3" #0 [ffff80000a5d2f40] machine_kexec at ffffb70f056a0758 #1 [ffff80000a5d2f70] __crash_kexec at ffffb70f057e2994 #2 [ffff80000a5d3100] crash_kexec at ffffb70f057e2ad8 #3 [ffff80000a5d3120] die at ffffb70f0628234c #4 [ffff80000a5d31e0] die_kernel_fault at ffffb70f062828a8 #5 [ffff80000a5d3210] __do_kernel_fault at ffffb70f056a31f4 #6 [ffff80000a5d3240] do_bad_area at ffffb70f056a32a4 #7 [ffff80000a5d3260] do_translation_fault at ffffb70f062a9710 #8 [ffff80000a5d3270] do_mem_abort at ffffb70f056a2f74 #9 [ffff80000a5d32a0] el1_abort at ffffb70f06297dac #10 [ffff80000a5d32d0] el1h_64_sync_handler at ffffb70f06299b24 #11 [ffff80000a5d3410] el1h_64_sync at ffffb70f056812dc #12 [ffff80000a5d3430] ovs_dp_upcall at ffffb70ee6963c84 [openvswitch] #13 [ffff80000a5d3470] ovs_dp_process_packet at ffffb70ee6963fdc [openvswitch] #14 [ffff80000a5d34f0] ovs_vport_receive at ffffb70ee6972c78 [openvswitch] #15 [ffff80000a5d36f0] netdev_port_receive at ffffb70ee6973948 [openvswitch] #16 [ffff80000a5d3720] netdev_frame_hook at ffffb70ee6973a28 [openvswitch] #17 [ffff80000a5d3730] __netif_receive_skb_core.constprop.0 at ffffb70f06079f90 We moved the per cpu upcall counter allocation to the existing vport alloc and free functions to solve this. Fixes: 95637d9 ("net: openvswitch: release vport resources on failure") Fixes: 1933ea3 ("net: openvswitch: Add support to count upcall packets") Signed-off-by: Eelco Chaudron <[email protected]> Reviewed-by: Simon Horman <[email protected]> Acked-by: Aaron Conole <[email protected]> Signed-off-by: David S. Miller <[email protected]>
kubalewski
pushed a commit
that referenced
this pull request
Jul 28, 2023
Petr Machata says: ==================== mlxsw: Permit enslavement to netdevices with uppers The mlxsw driver currently makes the assumption that the user applies configuration in a bottom-up manner. Thus netdevices need to be added to the bridge before IP addresses are configured on that bridge or SVI added on top of it. Enslaving a netdevice to another netdevice that already has uppers is in fact forbidden by mlxsw for this reason. Despite this safety, it is rather easy to get into situations where the offloaded configuration is just plain wrong. As an example, take a front panel port, configure an IP address: it gets a RIF. Now enslave the port to the bridge, and the RIF is gone. Remove the port from the bridge again, but the RIF never comes back. There is a number of similar situations, where changing the configuration there and back utterly breaks the offload. Similarly, detaching a front panel port from a configured topology means unoffloading of this whole topology -- VLAN uppers, next hops, etc. Attaching the port back is then not permitted at all. If it were, it would not result in a working configuration, because much of mlxsw is written to react to changes in immediate configuration. There is nothing that would go visit netdevices in the attached-to topology and offload existing routes and VLAN memberships, for example. In this patchset, introduce a number of replays to be invoked so that this sort of post-hoc offload is supported. Then remove the vetoes that disallowed enslavement of front panel ports to other netdevices with uppers. The patchset progresses as follows: - In patch #1, fix an issue in the bridge driver. To my knowledge, the issue could not have resulted in a buggy behavior previously, and thus is packaged with this patchset instead of being sent separately to net. - In patch #2, add a new helper to the switchdev code. - In patch #3, drop mlxsw selftests that will not be relevant after this patchset anymore. - Patches #4, #5, #6, #7 and #8 prepare the codebase for smoother introduction of the rest of the code. - Patches #9, #10, #11, #12, #13 and #14 replay various aspects of upper configuration when a front panel port is introduced into a topology. Individual patches take care of bridge and LAG RIF memberships, switchdev replay, nexthop and neighbors replay, and MACVLAN offload. - Patches #15 and #16 introduce RIFs for newly-relevant netdevices when a front panel port is enslaved (in which case all uppers are newly relevant), or, respectively, deslaved (in which case the newly-relevant netdevice is the one being deslaved). - Up until this point, the introduced scaffolding was not really used, because mlxsw still forbids enslavement of mlxsw netdevices to uppers with uppers. In patch #17, this condition is finally relaxed. A sizable selftest suite is available to test all this new code. That will be sent in a separate patchset. ==================== Signed-off-by: David S. Miller <[email protected]>
kubalewski
pushed a commit
that referenced
this pull request
Aug 4, 2023
The cited commit holds encap tbl lock unconditionally when setting up dests. But it may cause the following deadlock: PID: 1063722 TASK: ffffa062ca5d0000 CPU: 13 COMMAND: "handler8" #0 [ffffb14de05b7368] __schedule at ffffffffa1d5aa91 #1 [ffffb14de05b7410] schedule at ffffffffa1d5afdb #2 [ffffb14de05b7430] schedule_preempt_disabled at ffffffffa1d5b528 #3 [ffffb14de05b7440] __mutex_lock at ffffffffa1d5d6cb #4 [ffffb14de05b74e8] mutex_lock_nested at ffffffffa1d5ddeb #5 [ffffb14de05b74f8] mlx5e_tc_tun_encap_dests_set at ffffffffc12f2096 [mlx5_core] #6 [ffffb14de05b7568] post_process_attr at ffffffffc12d9fc5 [mlx5_core] #7 [ffffb14de05b75a0] mlx5e_tc_add_fdb_flow at ffffffffc12de877 [mlx5_core] #8 [ffffb14de05b75f0] __mlx5e_add_fdb_flow at ffffffffc12e0eef [mlx5_core] #9 [ffffb14de05b7660] mlx5e_tc_add_flow at ffffffffc12e12f7 [mlx5_core] #10 [ffffb14de05b76b8] mlx5e_configure_flower at ffffffffc12e1686 [mlx5_core] #11 [ffffb14de05b7720] mlx5e_rep_indr_offload at ffffffffc12e3817 [mlx5_core] #12 [ffffb14de05b7730] mlx5e_rep_indr_setup_tc_cb at ffffffffc12e388a [mlx5_core] #13 [ffffb14de05b7740] tc_setup_cb_add at ffffffffa1ab2ba8 #14 [ffffb14de05b77a0] fl_hw_replace_filter at ffffffffc0bdec2f [cls_flower] #15 [ffffb14de05b7868] fl_change at ffffffffc0be6caa [cls_flower] #16 [ffffb14de05b7908] tc_new_tfilter at ffffffffa1ab71f0 [1031218.028143] wait_for_completion+0x24/0x30 [1031218.028589] mlx5e_update_route_decap_flows+0x9a/0x1e0 [mlx5_core] [1031218.029256] mlx5e_tc_fib_event_work+0x1ad/0x300 [mlx5_core] [1031218.029885] process_one_work+0x24e/0x510 Actually no need to hold encap tbl lock if there is no encap action. Fix it by checking if encap action exists or not before holding encap tbl lock. Fixes: 37c3b9f ("net/mlx5e: Prevent encap offload when neigh update is running") Signed-off-by: Chris Mi <[email protected]> Reviewed-by: Vlad Buslov <[email protected]> Signed-off-by: Saeed Mahameed <[email protected]>
kubalewski
pushed a commit
that referenced
this pull request
Aug 11, 2023
…inux/kernel/git/saeed/linux Saeed Mahameed says: ==================== mlx5-updates-2023-08-07 1) Few cleanups 2) Dynamic completion EQs The driver creates completion EQs for all vectors directly on driver load, even if those EQs will not be utilized later on. To allow more flexibility in managing completion EQs and to reduce the memory overhead of driver load, this series will adjust completion EQs creation to be dynamic. Meaning, completion EQs will be created only when needed. Patch #1 introduces a counter for tracking the current number of completion EQs. Patches #2-6 refactor the existing infrastructure of managing completion EQs and completion IRQs to be compatible with per-vector allocation/release requests. Patches #7-8 modify the CPU-to-IRQ affinity calculation to be resilient in case the affinity is requested but completion IRQ is not allocated yet. Patch #9 function rename. Patch #10 handles the corner case of SF performing an IRQ request when no SF IRQ pool is found, and no PF IRQ exists for the same vector. Patch #11 modify driver to use dynamically allocate completion EQs. * tag 'mlx5-updates-2023-08-07' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux: net/mlx5: Bridge, Only handle registered netdev bridge events net/mlx5: E-Switch, Remove redundant arg ignore_flow_lvl net/mlx5: Fix typo reminder -> remainder net/mlx5: remove many unnecessary NULL values net/mlx5: Allocate completion EQs dynamically net/mlx5: Handle SF IRQ request in the absence of SF IRQ pool net/mlx5: Rename mlx5_comp_vectors_count() to mlx5_comp_vectors_max() net/mlx5: Add IRQ vector to CPU lookup function net/mlx5: Introduce mlx5_cpumask_default_spread net/mlx5: Implement single completion EQ create/destroy methods net/mlx5: Use xarray to store and manage completion EQs net/mlx5: Refactor completion IRQ request/release handlers in EQ layer net/mlx5: Use xarray to store and manage completion IRQs net/mlx5: Refactor completion IRQ request/release API net/mlx5: Track the current number of completion EQs ==================== Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jakub Kicinski <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.