[PATCH] drm/amdgpu: lock and unlock console only for amdgpu_fbdev_set_suspend [V5]

[PATCH] drm/amdgpu: lock and unlock console only for amdgpu_fbdev_set_suspend [V5]

[Shirish S]

[Why]
While the console_lock is held, console output will be buffered, till
its unlocked it wont be emitted, hence its ideal to unlock sooner to enable
debugging/detecting/fixing of any issue in the remaining sequence of events
in resume path.
The concern here is about consoles other than fbcon on the device,
e.g. a serial console

[How]
This patch restructures the console_lock, console_unlock around
amdgpu_fbdev_set_suspend() and moves this new block appropriately.

V2: Kept amdgpu_fbdev_set_suspend after pci_set_power_state
V3: Updated the commit message to clarify the real concern that this patch
    addresses.
V4: code clean-up.
V5: fixed return value

Signed-off-by: Shirish S <shirish.s@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 22 +++++++---------------
 1 file changed, 7 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 709e4a3..cf9af28 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2720,15 +2720,12 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
-	if (fbcon)
-		console_lock();
-
 	if (resume) {
 		pci_set_power_state(dev->pdev, PCI_D0);
 		pci_restore_state(dev->pdev);
 		r = pci_enable_device(dev->pdev);
 		if (r)
-			goto unlock;
+			return r;
 	}
 
 	/* post card */
@@ -2741,7 +2738,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	r = amdgpu_device_ip_resume(adev);
 	if (r) {
 		DRM_ERROR("amdgpu_device_ip_resume failed (%d).\n", r);
-		goto unlock;
+		return r;
 	}
 
 	amdgpu_fence_driver_resume(adev);
@@ -2749,7 +2746,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 
 	r = amdgpu_device_ip_late_init(adev);
 	if (r)
-		goto unlock;
+		return r;
 
 	/* pin cursors */
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
@@ -2784,6 +2781,9 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 			}
 			drm_modeset_unlock_all(dev);
 		}
+		console_lock();
+		amdgpu_fbdev_set_suspend(adev, 0);
+		console_unlock();
 	}
 
 	drm_kms_helper_poll_enable(dev);
@@ -2807,15 +2807,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 #ifdef CONFIG_PM
 	dev->dev->power.disable_depth--;
 #endif
-
-	if (fbcon)
-		amdgpu_fbdev_set_suspend(adev, 0);
-
-unlock:
-	if (fbcon)
-		console_unlock();
-
-	return r;
+	return 0;
 }
 
 /**
-- 
2.7.4

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH] drm/amdgpu: lock and unlock console only for amdgpu_fbdev_set_suspend [V5]

[Michel Dänzer]

On 2018-07-19 12:02 PM, Shirish S wrote:
> [Why]
> While the console_lock is held, console output will be buffered, till
> its unlocked it wont be emitted, hence its ideal to unlock sooner to enable
> debugging/detecting/fixing of any issue in the remaining sequence of events
> in resume path.
> The concern here is about consoles other than fbcon on the device,
> e.g. a serial console
> 
> [How]
> This patch restructures the console_lock, console_unlock around
> amdgpu_fbdev_set_suspend() and moves this new block appropriately.
> 
> V2: Kept amdgpu_fbdev_set_suspend after pci_set_power_state
> V3: Updated the commit message to clarify the real concern that this patch
>     addresses.
> V4: code clean-up.
> V5: fixed return value
> 
> Signed-off-by: Shirish S <shirish.s@amd.com>
> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>

In the future, please mark which revision a review was given for when
making significant changes in later revisions.

However, v5 looks good, so in this case, you can leave it as is. :)

(BTW, this is also a bug fix: we would leave the console locked if
amdgpu_amdkfd_resume returned an error)


-- 
Earthling Michel Dänzer               |               http://www.amd.com
Libre software enthusiast             |             Mesa and X developer
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx