[PATCH] drm/amdgpu: Fix driver uninstallation problem

[PATCH] drm/amdgpu: Fix driver uninstallation problem

[YiPeng Chai]

The following is the error message:
[  484.495995] task:rmmod           state:D stack:    0 pid: 2195 ppid:  2194 flags:0x00004002
[  484.496000] Call Trace:
[  484.496002]  <TASK>
[  484.496007]  __schedule+0xaf8/0x1870
[  484.496015]  ? update_load_avg+0x74/0x7b0
[  484.496021]  schedule+0x58/0xc0
[  484.496022]  schedule_timeout+0x276/0x480
[  484.496024]  ? ttwu_do_activate+0x9f/0x570
[  484.496028]  wait_for_completion+0x8b/0x130
[  484.496030]  kthread_stop+0x71/0x1a0
[  484.496037]  amdgpu_ras_pre_fini+0x5b/0xe0 [amdgpu]
[  484.496202]  amdgpu_device_fini_hw+0x165/0x4fc [amdgpu]
[  484.496406]  ? blocking_notifier_chain_unregister+0x56/0xb0
[  484.496409]  amdgpu_driver_unload_kms+0x51/0x60 [amdgpu]
[  484.496522]  amdgpu_pci_remove+0x3b/0x70 [amdgpu]
[  484.496627]  pci_device_remove+0x39/0xa0
[  484.496631]  device_remove+0x46/0x70
[  484.496634]  device_release_driver_internal+0xcd/0x140
[  484.496636]  driver_detach+0x4a/0x90
[  484.496638]  bus_remove_driver+0x6c/0xf0
[  484.496641]  driver_unregister+0x31/0x70
[  484.496643]  pci_unregister_driver+0x40/0x90
[  484.496647]  amdgpu_exit+0x15/0x22b [amdgpu]
[  484.496849]  __x64_sys_delete_module+0x14a/0x260
[  484.496853]  ? syscall_exit_to_user_mode+0x26/0x40
[  484.496856]  ? __x64_sys_close+0x12/0x40
[  484.496860]  do_syscall_64+0x5c/0x80
[  484.496861]  ? __x64_sys_read+0x1a/0x20
[  484.496863]  ? do_syscall_64+0x69/0x80
[  484.496864]  ? syscall_exit_to_user_mode+0x26/0x40
[  484.496866]  ? do_syscall_64+0x69/0x80
[  484.496866]  ? exc_page_fault+0x87/0x170
[  484.496868]  ? asm_exc_page_fault+0x8/0x30
[  484.496871]  entry_SYSCALL_64_after_hwframe+0x44/0xae

Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 8c1cb3ec2762..768a98f4bd22 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2674,7 +2674,11 @@ static int amdgpu_ras_page_retirement_thread(void *param)
 	while (!kthread_should_stop()) {
 
 		wait_event_interruptible(con->page_retirement_wq,
-				atomic_read(&con->page_retirement_req_cnt));
+				atomic_read(&con->page_retirement_req_cnt) ||
+				kthread_should_stop());
+
+		if (kthread_should_stop())
+			break;
 
 		dev_info(adev->dev, "Start processing page retirement. request:%d\n",
 			atomic_read(&con->page_retirement_req_cnt));
-- 
2.34.1

Re: [PATCH] drm/amdgpu: Fix driver uninstallation problem

[Lazar, Lijo]

Mukul posted a patch for this already.

	"drm/amdgpu: Fix module unload hang with RAS enabled"

Thanks,
Lijo

On 1/24/2024 9:09 AM, YiPeng Chai wrote:
> The following is the error message:
> [  484.495995] task:rmmod           state:D stack:    0 pid: 2195 ppid:  2194 flags:0x00004002
> [  484.496000] Call Trace:
> [  484.496002]  <TASK>
> [  484.496007]  __schedule+0xaf8/0x1870
> [  484.496015]  ? update_load_avg+0x74/0x7b0
> [  484.496021]  schedule+0x58/0xc0
> [  484.496022]  schedule_timeout+0x276/0x480
> [  484.496024]  ? ttwu_do_activate+0x9f/0x570
> [  484.496028]  wait_for_completion+0x8b/0x130
> [  484.496030]  kthread_stop+0x71/0x1a0
> [  484.496037]  amdgpu_ras_pre_fini+0x5b/0xe0 [amdgpu]
> [  484.496202]  amdgpu_device_fini_hw+0x165/0x4fc [amdgpu]
> [  484.496406]  ? blocking_notifier_chain_unregister+0x56/0xb0
> [  484.496409]  amdgpu_driver_unload_kms+0x51/0x60 [amdgpu]
> [  484.496522]  amdgpu_pci_remove+0x3b/0x70 [amdgpu]
> [  484.496627]  pci_device_remove+0x39/0xa0
> [  484.496631]  device_remove+0x46/0x70
> [  484.496634]  device_release_driver_internal+0xcd/0x140
> [  484.496636]  driver_detach+0x4a/0x90
> [  484.496638]  bus_remove_driver+0x6c/0xf0
> [  484.496641]  driver_unregister+0x31/0x70
> [  484.496643]  pci_unregister_driver+0x40/0x90
> [  484.496647]  amdgpu_exit+0x15/0x22b [amdgpu]
> [  484.496849]  __x64_sys_delete_module+0x14a/0x260
> [  484.496853]  ? syscall_exit_to_user_mode+0x26/0x40
> [  484.496856]  ? __x64_sys_close+0x12/0x40
> [  484.496860]  do_syscall_64+0x5c/0x80
> [  484.496861]  ? __x64_sys_read+0x1a/0x20
> [  484.496863]  ? do_syscall_64+0x69/0x80
> [  484.496864]  ? syscall_exit_to_user_mode+0x26/0x40
> [  484.496866]  ? do_syscall_64+0x69/0x80
> [  484.496866]  ? exc_page_fault+0x87/0x170
> [  484.496868]  ? asm_exc_page_fault+0x8/0x30
> [  484.496871]  entry_SYSCALL_64_after_hwframe+0x44/0xae
> 
> Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 6 +++++-
>  1 file changed, 5 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> index 8c1cb3ec2762..768a98f4bd22 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> @@ -2674,7 +2674,11 @@ static int amdgpu_ras_page_retirement_thread(void *param)
>  	while (!kthread_should_stop()) {
>  
>  		wait_event_interruptible(con->page_retirement_wq,
> -				atomic_read(&con->page_retirement_req_cnt));
> +				atomic_read(&con->page_retirement_req_cnt) ||
> +				kthread_should_stop());
> +
> +		if (kthread_should_stop())
> +			break;
>  
>  		dev_info(adev->dev, "Start processing page retirement. request:%d\n",
>  			atomic_read(&con->page_retirement_req_cnt));