6.6-stable patches

added patches:
	net-mlx5e-don-t-call-cleanup-on-profile-rollback-failure.patch

diff --git a/queue-6.6/net-mlx5e-don-t-call-cleanup-on-profile-rollback-failure.patch b/queue-6.6/net-mlx5e-don-t-call-cleanup-on-profile-rollback-failure.patch
new file mode 100644 (file)
index 0000000..2d51852
--- /dev/null
+++ b/queue-6.6/net-mlx5e-don-t-call-cleanup-on-profile-rollback-failure.patch
@@ -0,0 +1,83 @@
+From 4dbc1d1a9f39c3711ad2a40addca04d07d9ab5d0 Mon Sep 17 00:00:00 2001
+From: Cosmin Ratiu <cratiu@nvidia.com>
+Date: Tue, 15 Oct 2024 12:32:08 +0300
+Subject: net/mlx5e: Don't call cleanup on profile rollback failure
+
+From: Cosmin Ratiu <cratiu@nvidia.com>
+
+commit 4dbc1d1a9f39c3711ad2a40addca04d07d9ab5d0 upstream.
+
+When profile rollback fails in mlx5e_netdev_change_profile, the netdev
+profile var is left set to NULL. Avoid a crash when unloading the driver
+by not calling profile->cleanup in such a case.
+
+This was encountered while testing, with the original trigger that
+the wq rescuer thread creation got interrupted (presumably due to
+Ctrl+C-ing modprobe), which gets converted to ENOMEM (-12) by
+mlx5e_priv_init, the profile rollback also fails for the same reason
+(signal still active) so the profile is left as NULL, leading to a crash
+later in _mlx5e_remove.
+
+ [  732.473932] mlx5_core 0000:08:00.1: E-Switch: Unload vfs: mode(OFFLOADS), nvfs(2), necvfs(0), active vports(2)
+ [  734.525513] workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR
+ [  734.557372] mlx5_core 0000:08:00.1: mlx5e_netdev_init_profile:6235:(pid 6086): mlx5e_priv_init failed, err=-12
+ [  734.559187] mlx5_core 0000:08:00.1 eth3: mlx5e_netdev_change_profile: new profile init failed, -12
+ [  734.560153] workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR
+ [  734.589378] mlx5_core 0000:08:00.1: mlx5e_netdev_init_profile:6235:(pid 6086): mlx5e_priv_init failed, err=-12
+ [  734.591136] mlx5_core 0000:08:00.1 eth3: mlx5e_netdev_change_profile: failed to rollback to orig profile, -12
+ [  745.537492] BUG: kernel NULL pointer dereference, address: 0000000000000008
+ [  745.538222] #PF: supervisor read access in kernel mode
+<snipped>
+ [  745.551290] Call Trace:
+ [  745.551590]  <TASK>
+ [  745.551866]  ? __die+0x20/0x60
+ [  745.552218]  ? page_fault_oops+0x150/0x400
+ [  745.555307]  ? exc_page_fault+0x79/0x240
+ [  745.555729]  ? asm_exc_page_fault+0x22/0x30
+ [  745.556166]  ? mlx5e_remove+0x6b/0xb0 [mlx5_core]
+ [  745.556698]  auxiliary_bus_remove+0x18/0x30
+ [  745.557134]  device_release_driver_internal+0x1df/0x240
+ [  745.557654]  bus_remove_device+0xd7/0x140
+ [  745.558075]  device_del+0x15b/0x3c0
+ [  745.558456]  mlx5_rescan_drivers_locked.part.0+0xb1/0x2f0 [mlx5_core]
+ [  745.559112]  mlx5_unregister_device+0x34/0x50 [mlx5_core]
+ [  745.559686]  mlx5_uninit_one+0x46/0xf0 [mlx5_core]
+ [  745.560203]  remove_one+0x4e/0xd0 [mlx5_core]
+ [  745.560694]  pci_device_remove+0x39/0xa0
+ [  745.561112]  device_release_driver_internal+0x1df/0x240
+ [  745.561631]  driver_detach+0x47/0x90
+ [  745.562022]  bus_remove_driver+0x84/0x100
+ [  745.562444]  pci_unregister_driver+0x3b/0x90
+ [  745.562890]  mlx5_cleanup+0xc/0x1b [mlx5_core]
+ [  745.563415]  __x64_sys_delete_module+0x14d/0x2f0
+ [  745.563886]  ? kmem_cache_free+0x1b0/0x460
+ [  745.564313]  ? lockdep_hardirqs_on_prepare+0xe2/0x190
+ [  745.564825]  do_syscall_64+0x6d/0x140
+ [  745.565223]  entry_SYSCALL_64_after_hwframe+0x4b/0x53
+ [  745.565725] RIP: 0033:0x7f1579b1288b
+
+Fixes: 3ef14e463f6e ("net/mlx5e: Separate between netdev objects and mlx5e profiles initialization")
+Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
+Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
+Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Signed-off-by: Jianqi Ren <jianqi.ren.cn@windriver.com>
+Signed-off-by: He Zhe <zhe.he@windriver.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/net/ethernet/mellanox/mlx5/core/en_main.c |    4 +++-
+ 1 file changed, 3 insertions(+), 1 deletion(-)
+
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+@@ -6110,7 +6110,9 @@ static void mlx5e_remove(struct auxiliar
+       mlx5e_dcbnl_delete_app(priv);
+       unregister_netdev(priv->netdev);
+       mlx5e_suspend(adev, state);
+-      priv->profile->cleanup(priv);
++      /* Avoid cleanup if profile rollback failed. */
++      if (priv->profile)
++              priv->profile->cleanup(priv);
+       mlx5e_destroy_netdev(priv);
+       mlx5e_devlink_port_unregister(mlx5e_dev);
+       mlx5e_destroy_devlink(mlx5e_dev);

diff --git a/queue-6.6/series b/queue-6.6/series
index 328eb16a3eca023392429908addba67e1e2ff690..6df724f859830c253ec884bb5fe784c1dea54a31 100644 (file)
--- a/queue-6.6/series
+++ b/queue-6.6/series
@@ -129,3 +129,4 @@ smb-client-add-check-for-next_buffer-in-receive_encrypted_standard.patch
 edac-qcom-correct-interrupt-enable-register-configuration.patch
 ftrace-correct-preemption-accounting-for-function-tracing.patch
 ftrace-do-not-add-duplicate-entries-in-subops-manager-ops.patch
+net-mlx5e-don-t-call-cleanup-on-profile-rollback-failure.patch