kernel/Documentation/networking/devlink/mlx5.rst, branch linux-rolling-stable

net/mlx5: implement swp_l4_csum_mode via devlink params

2025-11-21T03:01:22Z

swp_l4_csum_mode controls how L4 transmit checksums are computed when using Software Parser (SWP) hints for header locations. Supported values: 1. default: device will choose between full_csum or l4_only. Driver will discover the device's choice during initialization. 2. full_csum: calculate L4 checksum with the pseudo-header. 3. l4_only: calculate L4 checksum without the pseudo-header. Only available when swp_l4_csum_mode_l4_only is set in mlx5_ifc_nv_sw_offload_cap_bits. Note that 'default' might be returned from the device and passed to userspace, and it might also be set during a devlink_param::reset_default() call, but attempts to set a value of default directly with param-set will be rejected. The l4_only setting is a dependency for PSP initialization in mlx5e_psp_init(). Reviewed-by: Aleksandr Loktionov Signed-off-by: Daniel Zahka Link: https://patch.msgid.link/20251119025038.651131-5-daniel.zahka@gmail.com Signed-off-by: Jakub Kicinski

net/mlx5: Expose uar access and odp page fault counters

2025-09-27T15:53:50Z

Add three counters to vnic health reporter: bar_uar_access, odp_local_triggered_page_fault, and odp_remote_triggered_page_fault. - bar_uar_access number of WRITE or READ access operations to the UAR on the PCIe BAR. - odp_local_triggered_page_fault number of locally-triggered page-faults due to ODP. - odp_remote_triggered_page_fault number of remotly-triggered page-faults due to ODP. Example access: $ devlink health diagnose pci/0000:08:00.0 reporter vnic vNIC env counters: total_error_queues: 0 send_queue_priority_update_flow: 0 comp_eq_overrun: 0 async_eq_overrun: 0 cq_overrun: 0 invalid_command: 0 quota_exceeded_command: 0 nic_receive_steering_discard: 0 icm_consumption: 1032 bar_uar_access: 1279 odp_local_triggered_page_fault: 20 odp_remote_triggered_page_fault: 34 Signed-off-by: Akiva Goldberger Reviewed-by: Moshe Shemesh Signed-off-by: Tariq Toukan Reviewed-by: Simon Horman Link: https://patch.msgid.link/1758797130-829564-1-git-send-email-tariqt@nvidia.com Signed-off-by: Jakub Kicinski

net/mlx5e: Use the 'num_doorbells' devlink param

2025-09-18T01:30:54Z

Use the new devlink param to control how many doorbells mlx5e devices allocate and use. The maximum number of doorbells configurable is capped to the maximum number of channels. This only applies to the Ethernet part, the RDMA devices using mlx5 manage their own doorbells. Signed-off-by: Cosmin Ratiu Reviewed-by: Dragos Tatulea Signed-off-by: Tariq Toukan Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski

net/mlx5e: Make PCIe congestion event thresholds configurable

2025-09-10T02:21:30Z

Add devlink driverinit parameters for configuring the thresholds for PCIe congestion events. These parameters are registered only when the firmware supports this feature. Update the mlx5 devlink docs as well on these new params. Signed-off-by: Dragos Tatulea Signed-off-by: Tariq Toukan Reviewed-by: Simon Horman Link: https://patch.msgid.link/1757237976-531416-2-git-send-email-tariqt@nvidia.com Signed-off-by: Jakub Kicinski

net/mlx5: Implement devlink total_vfs parameter

2025-09-10T02:14:24Z

Some devices support both symmetric (same value for all PFs) and asymmetric, while others only support symmetric configuration. This implementation prefers asymmetric, since it is closer to the devlink model (per function settings), but falls back to symmetric when needed. Example usage: devlink dev param set pci/0000:01:00.0 name total_vfs value cmode permanent devlink dev reload pci/0000:01:00.0 action fw_activate echo 1 >/sys/bus/pci/devices/0000:01:00.0/remove echo 1 >/sys/bus/pci/rescan cat /sys/bus/pci/devices/0000:01:00.0/sriov_totalvfs Signed-off-by: Vlad Dumitrescu Reviewed-by: Jiri Pirko Tested-by: Kamal Heib Signed-off-by: Saeed Mahameed Reviewed-by: Simon Horman Link: https://patch.msgid.link/20250907012953.301746-5-saeed@kernel.org Signed-off-by: Jakub Kicinski

net/mlx5: Implement devlink enable_sriov parameter

2025-09-10T02:14:24Z

Example usage: devlink dev param set pci/0000:01:00.0 name enable_sriov value {true, false} cmode permanent devlink dev reload pci/0000:01:00.0 action fw_activate echo 1 >/sys/bus/pci/devices/0000:01:00.0/remove echo 1 >/sys/bus/pci/rescan grep ^ /sys/bus/pci/devices/0000:01:00.0/sriov_* Signed-off-by: Vlad Dumitrescu Tested-by: Kamal Heib Reviewed-by: Jiri Pirko Signed-off-by: Saeed Mahameed Reviewed-by: Simon Horman Link: https://patch.msgid.link/20250907012953.301746-4-saeed@kernel.org Signed-off-by: Jakub Kicinski

net/mlx5: Implement cqe_compress_type via devlink params

2025-09-10T02:14:23Z

Selects which algorithm should be used by the NIC in order to decide rate of CQE compression dependeng on PCIe bus conditions. Supported values: 1) balanced, merges fewer CQEs, resulting in a moderate compression ratio but maintaining a balance between bandwidth savings and performance 2) aggressive, merges more CQEs into a single entry, achieving a higher compression rate and maximizing performance, particularly under high traffic loads. Signed-off-by: Saeed Mahameed Reviewed-by: Jiri Pirko Reviewed-by: Simon Horman Link: https://patch.msgid.link/20250907012953.301746-3-saeed@kernel.org Signed-off-by: Jakub Kicinski

net/mlx5: Expose ICM consumption per function

2025-02-12T18:46:17Z

ICM is a portion of the host's memory assigned to a function by the OS through requests made by the NIC's firmware. PF ICM consumption can be accessed directly, while VF/SF ICM consumption can be accessed through their representors in switchdev mode. The value is exposed to the user in granularity of 4KB through the vnic health reporter as follows: $ devlink health diagnose pci/0000:08:00.0 reporter vnic vNIC env counters: total_error_queues: 0 send_queue_priority_update_flow: 0 comp_eq_overrun: 0 async_eq_overrun: 0 cq_overrun: 0 invalid_command: 0 quota_exceeded_command: 0 nic_receive_steering_discard: 0 icm_consumption: 1032 Signed-off-by: Akiva Goldberger Reviewed-by: Moshe Shemesh Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20250209101716.112774-11-tariqt@nvidia.com Signed-off-by: Jakub Kicinski

net/mlx5: fs, add HWS to steering mode options

2025-01-14T03:21:09Z

Add HW Steering mode to mlx5 devlink param of steering mode options. Signed-off-by: Moshe Shemesh Reviewed-by: Yevgeny Kliteynik Reviewed-by: Mark Bloch Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20250109160546.1733647-14-tariqt@nvidia.com Signed-off-by: Jakub Kicinski

Documentation: Fix counter name of mlx5 vnic reporter

2024-02-06T00:45:50Z

Fix counter name in documentation of mlx5 vnic health reporter diagnose output: total_error_queues. While here fix alignment in the documentation file of another counter, comp_eq_overrun, as it should have its own line and not be part of another counter's description. Example: $ devlink health diagnose pci/0000:00:04.0 reporter vnic vNIC env counters: total_error_queues: 0 send_queue_priority_update_flow: 0 comp_eq_overrun: 0 async_eq_overrun: 0 cq_overrun: 0 invalid_command: 0 quota_exceeded_command: 0 nic_receive_steering_discard: 0 Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed