linux.git/include/linux/mlx5, branch v6.18-rc2 Linux kernel source tree Merge tag 'mlx5-next-lag' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux 2025-09-30T01:49:59+00:00 Jakub Kicinski kuba@kernel.org 2025-09-30T01:49:58+00:00 377ea331281f2c63dc281a6ea2dc318e4e1fc2d1 Tariq Toukan says: ==================== mlx5-next updates 2025-09-28 * tag 'mlx5-next-lag' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux: net/mlx5: IFC add balance ID and LAG per MP group bits net/mlx5: Add IFC bit for TIR/SQ order capability ==================== Link: https://patch.msgid.link/1759093989-841873-1-git-send-email-tariqt@nvidia.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
Tariq Toukan says:

====================
mlx5-next updates 2025-09-28

* tag 'mlx5-next-lag' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux:
  net/mlx5: IFC add balance ID and LAG per MP group bits
  net/mlx5: Add IFC bit for TIR/SQ order capability
====================

Link: https://patch.msgid.link/1759093989-841873-1-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net/mlx5: IFC add balance ID and LAG per MP group bits 2025-09-28T07:36:36+00:00 Mark Bloch mbloch@nvidia.com 2025-09-22T06:06:31+00:00 137d1a6355131457723b51a34192320d93d15654 Add interface definitions for load balance ID and LAG per multiplane group functionality. This patch introduces the hardware capability bits needed to support balance ID in multiplane LAG configurations. The new fields include: - load_balance_id: 4-bit field for balance identifier. - lag_per_mp_group: capability bit for LAG per multiplane group support. These interface additions are prerequisites for implementing balance ID support in the MLX5 driver. Signed-off-by: Mark Bloch <mbloch@nvidia.com> Reviewed-by: Shay Drori <shayd@nvidia.com> Signed-off-by: Tariq Toukan <tariqt@nvidia.com> Link: https://patch.msgid.link/1758521191-814350-3-git-send-email-tariqt@nvidia.com Signed-off-by: Leon Romanovsky <leon@kernel.org> 
Add interface definitions for load balance ID and LAG per multiplane group
functionality. This patch introduces the hardware capability bits needed
to support balance ID in multiplane LAG configurations.

The new fields include:
- load_balance_id: 4-bit field for balance identifier.
- lag_per_mp_group: capability bit for LAG per multiplane group support.

These interface additions are prerequisites for implementing balance ID
support in the MLX5 driver.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Shay Drori <shayd@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1758521191-814350-3-git-send-email-tariqt@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
net/mlx5: Add IFC bit for TIR/SQ order capability 2025-09-28T07:36:36+00:00 Tariq Toukan tariqt@nvidia.com 2025-09-22T06:06:30+00:00 1ddf1636e0e058adf2231486da0419243eb49539 Before this cap, firmware requested a certain creation order between TIR objects and SQs of the same transport domain to properly support the self loopback prevention feature. If order is not preserved, explicit modify_tir operations are necessary after the opening of the SQs. When set, this cap bit indicates that this firmware requirement / limitation no longer holds. Signed-off-by: Tariq Toukan <tariqt@nvidia.com> Link: https://patch.msgid.link/1758521191-814350-2-git-send-email-tariqt@nvidia.com Reviewed-by: Carolina Jubran <cjubran@nvidia.com> Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> 
Before this cap, firmware requested a certain creation order between TIR
objects and SQs of the same transport domain to properly support the
self loopback prevention feature. If order is not preserved, explicit
modify_tir operations are necessary after the opening of the SQs.

When set, this cap bit indicates that this firmware requirement /
limitation no longer holds.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1758521191-814350-2-git-send-email-tariqt@nvidia.com
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net 2025-09-25T18:00:59+00:00 Jakub Kicinski kuba@kernel.org 2025-09-12T00:37:09+00:00 203e3beb73e53584ca90bc2a6d8240b9b12b9bcf Cross-merge networking fixes after downstream PR (net-6.17-rc8). Conflicts: drivers/net/can/spi/hi311x.c 6b6968084721 ("can: hi311x: fix null pointer dereference when resuming from sleep before interface was enabled") 27ce71e1ce81 ("net: WQ_PERCPU added to alloc_workqueue users") https://lore.kernel.org/72ce7599-1b5b-464a-a5de-228ff9724701@kernel.org net/smc/smc_loopback.c drivers/dibs/dibs_loopback.c a35c04de2565 ("net/smc: fix warning in smc_rx_splice() when calling get_page()") cc21191b584c ("dibs: Move data path to dibs layer") https://lore.kernel.org/74368a5c-48ac-4f8e-a198-40ec1ed3cf5f@kernel.org Adjacent changes: drivers/net/dsa/lantiq/lantiq_gswip.c c0054b25e2f1 ("net: dsa: lantiq_gswip: move gswip_add_single_port_br() call to port_setup()") 7a1eaef0a791 ("net: dsa: lantiq_gswip: support model-specific mac_select_pcs()") Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
Cross-merge networking fixes after downstream PR (net-6.17-rc8).

Conflicts:

drivers/net/can/spi/hi311x.c
  6b6968084721 ("can: hi311x: fix null pointer dereference when resuming from sleep before interface was enabled")
  27ce71e1ce81 ("net: WQ_PERCPU added to alloc_workqueue users")
https://lore.kernel.org/72ce7599-1b5b-464a-a5de-228ff9724701@kernel.org

net/smc/smc_loopback.c
drivers/dibs/dibs_loopback.c
  a35c04de2565 ("net/smc: fix warning in smc_rx_splice() when calling get_page()")
  cc21191b584c ("dibs: Move data path to dibs layer")
https://lore.kernel.org/74368a5c-48ac-4f8e-a198-40ec1ed3cf5f@kernel.org

Adjacent changes:

drivers/net/dsa/lantiq/lantiq_gswip.c
  c0054b25e2f1 ("net: dsa: lantiq_gswip: move gswip_add_single_port_br() call to port_setup()")
  7a1eaef0a791 ("net: dsa: lantiq_gswip: support model-specific mac_select_pcs()")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net/mlx5: fs, fix UAF in flow counter release 2025-09-24T00:17:30+00:00 Moshe Shemesh moshe@nvidia.com 2025-09-22T07:11:32+00:00 6043819e707cefb1c9e59d6e431dcfa735c4f975 Fix a kernel trace [1] caused by releasing an HWS action of a local flow counter in mlx5_cmd_hws_delete_fte(), where the HWS action refcount and mutex were not initialized and the counter struct could already be freed when deleting the rule. Fix it by adding the missing initializations and adding refcount for the local flow counter struct. [1] Kernel log: Call Trace: <TASK> dump_stack_lvl+0x34/0x48 mlx5_fs_put_hws_action.part.0.cold+0x21/0x94 [mlx5_core] mlx5_fc_put_hws_action+0x96/0xad [mlx5_core] mlx5_fs_destroy_fs_actions+0x8b/0x152 [mlx5_core] mlx5_cmd_hws_delete_fte+0x5a/0xa0 [mlx5_core] del_hw_fte+0x1ce/0x260 [mlx5_core] mlx5_del_flow_rules+0x12d/0x240 [mlx5_core] ? ttwu_queue_wakelist+0xf4/0x110 mlx5_ib_destroy_flow+0x103/0x1b0 [mlx5_ib] uverbs_free_flow+0x20/0x50 [ib_uverbs] destroy_hw_idr_uobject+0x1b/0x50 [ib_uverbs] uverbs_destroy_uobject+0x34/0x1a0 [ib_uverbs] uobj_destroy+0x3c/0x80 [ib_uverbs] ib_uverbs_run_method+0x23e/0x360 [ib_uverbs] ? uverbs_finalize_object+0x60/0x60 [ib_uverbs] ib_uverbs_cmd_verbs+0x14f/0x2c0 [ib_uverbs] ? do_tty_write+0x1a9/0x270 ? file_tty_write.constprop.0+0x98/0xc0 ? new_sync_write+0xfc/0x190 ib_uverbs_ioctl+0xd7/0x160 [ib_uverbs] __x64_sys_ioctl+0x87/0xc0 do_syscall_64+0x59/0x90 Fixes: b581f4266928 ("net/mlx5: fs, manage flow counters HWS action sharing by refcount") Signed-off-by: Moshe Shemesh <moshe@nvidia.com> Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com> Reviewed-by: Mark Bloch <mbloch@nvidia.com> Signed-off-by: Tariq Toukan <tariqt@nvidia.com> Link: https://patch.msgid.link/1758525094-816583-2-git-send-email-tariqt@nvidia.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
Fix a kernel trace [1] caused by releasing an HWS action of a local flow
counter in mlx5_cmd_hws_delete_fte(), where the HWS action refcount and
mutex were not initialized and the counter struct could already be freed
when deleting the rule.

Fix it by adding the missing initializations and adding refcount for the
local flow counter struct.

[1] Kernel log:
 Call Trace:
  <TASK>
  dump_stack_lvl+0x34/0x48
  mlx5_fs_put_hws_action.part.0.cold+0x21/0x94 [mlx5_core]
  mlx5_fc_put_hws_action+0x96/0xad [mlx5_core]
  mlx5_fs_destroy_fs_actions+0x8b/0x152 [mlx5_core]
  mlx5_cmd_hws_delete_fte+0x5a/0xa0 [mlx5_core]
  del_hw_fte+0x1ce/0x260 [mlx5_core]
  mlx5_del_flow_rules+0x12d/0x240 [mlx5_core]
  ? ttwu_queue_wakelist+0xf4/0x110
  mlx5_ib_destroy_flow+0x103/0x1b0 [mlx5_ib]
  uverbs_free_flow+0x20/0x50 [ib_uverbs]
  destroy_hw_idr_uobject+0x1b/0x50 [ib_uverbs]
  uverbs_destroy_uobject+0x34/0x1a0 [ib_uverbs]
  uobj_destroy+0x3c/0x80 [ib_uverbs]
  ib_uverbs_run_method+0x23e/0x360 [ib_uverbs]
  ? uverbs_finalize_object+0x60/0x60 [ib_uverbs]
  ib_uverbs_cmd_verbs+0x14f/0x2c0 [ib_uverbs]
  ? do_tty_write+0x1a9/0x270
  ? file_tty_write.constprop.0+0x98/0xc0
  ? new_sync_write+0xfc/0x190
  ib_uverbs_ioctl+0xd7/0x160 [ib_uverbs]
  __x64_sys_ioctl+0x87/0xc0
  do_syscall_64+0x59/0x90

Fixes: b581f4266928 ("net/mlx5: fs, manage flow counters HWS action sharing by refcount")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1758525094-816583-2-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Merge tag 'mlx5-next-counters' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux 2025-09-22T23:30:18+00:00 Jakub Kicinski kuba@kernel.org 2025-09-22T23:30:17+00:00 1bcce9ec189b2a28a5b9ee7b0c9ea9158bfd95ae Tariq Toukan says: ==================== mlx5-next updates 2025-09-21 * tag 'mlx5-next-counters' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux: net/mlx5: Add uar access and odp page fault counters ==================== Link: https://patch.msgid.link/1758443940-708689-1-git-send-email-tariqt@nvidia.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
Tariq Toukan says:

====================
mlx5-next updates 2025-09-21

* tag 'mlx5-next-counters' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux:
  net/mlx5: Add uar access and odp page fault counters
====================

Link: https://patch.msgid.link/1758443940-708689-1-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Merge tag 'mlx5-next-09-11' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux 2025-09-18T22:47:35+00:00 Jakub Kicinski kuba@kernel.org 2025-09-18T22:47:34+00:00 38c5b9c38be8303b536d0c15a5f955715bfba534 Tariq Toukan says: ==================== mlx5-next updates 2025-09-17 This series by Carolina contains cleanups significantly touching shared mlx5 net and rdma headers. * tag 'mlx5-next-09-11' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux: net/mlx5e: Prevent WQE metadata conflicts between timestamping and offloads net/mlx5: Refactor MACsec WQE metadata shifts net/mlx5: Remove VLAN insertion fields from WQE Ether segment ==================== Link: https://patch.msgid.link/1757574619-604874-1-git-send-email-tariqt@nvidia.com Link: https://patch.msgid.link/1758104780-642426-1-git-send-email-tariqt@nvidia.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
Tariq Toukan says:

====================
mlx5-next updates 2025-09-17

This series by Carolina contains cleanups significantly touching shared
mlx5 net and rdma headers.

* tag 'mlx5-next-09-11' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux:
  net/mlx5e: Prevent WQE metadata conflicts between timestamping and offloads
  net/mlx5: Refactor MACsec WQE metadata shifts
  net/mlx5: Remove VLAN insertion fields from WQE Ether segment
====================

Link: https://patch.msgid.link/1757574619-604874-1-git-send-email-tariqt@nvidia.com
Link: https://patch.msgid.link/1758104780-642426-1-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net 2025-09-18T18:26:06+00:00 Jakub Kicinski kuba@kernel.org 2025-09-18T18:23:29+00:00 f2cdc4c22bca57ab4cdb28ef4a02c53837d26fe0 Cross-merge networking fixes after downstream PR (net-6.17-rc7). No conflicts. Adjacent changes: drivers/net/ethernet/mellanox/mlx5/core/en/fs.h 9536fbe10c9d ("net/mlx5e: Add PSP steering in local NIC RX") 7601a0a46216 ("net/mlx5e: Add a miss level for ipsec crypto offload") Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
Cross-merge networking fixes after downstream PR (net-6.17-rc7).

No conflicts.

Adjacent changes:

drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
  9536fbe10c9d ("net/mlx5e: Add PSP steering in local NIC RX")
  7601a0a46216 ("net/mlx5e: Add a miss level for ipsec crypto offload")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net/mlx5: Add uar access and odp page fault counters 2025-09-18T09:32:22+00:00 Akiva Goldberger agoldberger@nvidia.com 2025-09-17T13:27:58+00:00 a3d076b0567e729d5f21a95525c4d096b1f59e79 Add bar_uar_access, odp_local_triggered_page_fault, and odp_remote_triggered_page_fault counters to the query_vnic_env command. Additionally, add corresponding capabilities bits to the HCA CAP. Signed-off-by: Akiva Goldberger <agoldberger@nvidia.com> Reviewed-by: Moshe Shemesh <moshe@nvidia.com> Signed-off-by: Tariq Toukan <tariqt@nvidia.com> Link: https://patch.msgid.link/1758115678-643464-1-git-send-email-tariqt@nvidia.com Signed-off-by: Leon Romanovsky <leon@kernel.org> 
Add bar_uar_access, odp_local_triggered_page_fault, and
odp_remote_triggered_page_fault counters to the query_vnic_env command.
Additionally, add corresponding capabilities bits to the HCA CAP.

Signed-off-by: Akiva Goldberger <agoldberger@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1758115678-643464-1-git-send-email-tariqt@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
net/mlx5e: Use multiple TX doorbells 2025-09-18T01:30:44+00:00 Cosmin Ratiu cratiu@nvidia.com 2025-09-16T14:11:41+00:00 71fb4832d50b01f0af2d257360c239879ce93a8e First, allocate more doorbells in mlx5e_create_mdev_resources: - one doorbell remains 'global' and will be used by all non-channel associated SQs (e.g. ASO, HWS, PTP, ...). - allocate additional 'num_doorbells' doorbells. This defaults to minimum between 8 and max number of channels. mlx5e_channel_pick_doorbell() now spreads out channel SQs across available doorbells. Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com> Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com> Signed-off-by: Tariq Toukan <tariqt@nvidia.com> Reviewed-by: Simon Horman <horms@kernel.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
First, allocate more doorbells in mlx5e_create_mdev_resources:
- one doorbell remains 'global' and will be used by all non-channel
  associated SQs (e.g. ASO, HWS, PTP, ...).
- allocate additional 'num_doorbells' doorbells. This defaults to
  minimum between 8 and max number of channels.

mlx5e_channel_pick_doorbell() now spreads out channel SQs across
available doorbells.

Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>