Patchwork [DPU] drm/msm/dpu: Fix vblank refcount mismatch

login
register
mail settings
Submitter Jayant Shekhar
Date Dec. 6, 2018, 6:46 a.m.
Message ID <1544078813-10945-1-git-send-email-jshekhar@codeaurora.org>
Download mbox | patch
Permalink /patch/673813/
State New
Headers show

Comments

Jayant Shekhar - Dec. 6, 2018, 6:46 a.m.
_dpu_crtc_vblank_enable_no_lock releases crtc_lock as
its needed for power handle operations. This opens up a
window where in a thread running dpu_crtc_disable and a thread
running dpu_crtc_vblank can race in using dpu_crtc->enabled.

dpu_crtc_disable will change the state, where as dpu_crtc_vblank
use the variable. The fix is to cache the crtc enabled state
while holding the lock and use it as a gate in calling
_dpu_crtc_vblank_enable_no_lock.

This issue was introduced with the commit cf871c48
(drm/msm/dpu: Remove suspend state tracking from crtc).

Below are stack traces of thread 1 and thread 2 in good case
and bad case:

Bad case:
-------------
Thread 1
dpu_encoder_phys_vid_control_vblank_irq+0xd0/0x170
dpu_encoder_register_vblank_callback+0xb8/0x100
_dpu_crtc_vblank_enable_no_lock+0x240/0x288
dpu_crtc_disable+0xc4/0x288
drm_atomic_helper_commit_modeset_disables+0x19c/0x350
msm_atomic_commit_tail+0x48/0x144
commit_tail+0x44/0x70
drm_atomic_helper_commit+0xf0/0xf8
drm_atomic_commit+0x40/0x4c
drm_mode_atomic_ioctl+0x374/0x90c
drm_ioctl_kernel+0xac/0xec
drm_ioctl+0x218/0x384
drm_compat_ioctl+0xd8/0xe8

Thread 2:
dpu_encoder_phys_vid_control_vblank_irq+0x74/0x170
dpu_encoder_register_vblank_callback+0xb8/0x100
_dpu_crtc_vblank_enable_no_lock+0x240/0x288
dpu_crtc_vblank+0xa8/0x118
dpu_kms_disable_vblank+0x20/0x2c
vblank_ctrl_worker+0xa0/0xe0
kthread_worker_fn+0xe4/0x1a4
kthread+0x11c/0x12c
ret_from_fork+0x10/0x18

Good case:
--------------
Thread 1:
dpu_encoder_phys_vid_control_vblank_irq+0xd0/0x170
dpu_encoder_phys_vid_irq_control+0xc8/0x110
_dpu_encoder_irq_control+0x48/0xa0
_dpu_encoder_resource_control_helper+0xb4/0x10c
dpu_encoder_resource_control+0x4e0/0x664
dpu_encoder_virt_enable+0xb8/0x120
dpu_kms_encoder_enable+0x34/0xcc
drm_atomic_helper_commit_modeset_enables+0x120/0x1b8
msm_atomic_commit_tail+0x5c/0x144
commit_tail+0x44/0x70
drm_atomic_helper_commit+0xf0/0xf8
drm_atomic_commit+0x40/0x4c
drm_mode_atomic_ioctl+0x374/0x90c

Thread 2:
dpu_crtc_vblank+0xc8/0x118
dpu_kms_disable_vblank+0x20/0x2c
vblank_ctrl_worker+0xa0/0xe0
kthread_worker_fn+0xe4/0x1a4
kthread+0x11c/0x12c

Signed-off-by: Jayant Shekhar <jshekhar@codeaurora.org>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)
Sean Paul - Dec. 6, 2018, 4:14 p.m.
On Thu, Dec 06, 2018 at 12:16:53PM +0530, Jayant Shekhar wrote:
> _dpu_crtc_vblank_enable_no_lock releases crtc_lock as
> its needed for power handle operations. This opens up a
> window where in a thread running dpu_crtc_disable and a thread
> running dpu_crtc_vblank can race in using dpu_crtc->enabled.

Looks like you're using an old kernel. Both power_handle and
vblank_enable_no_lock were removed.

If you want something more up-to-date for testing, grab the mtp-testing
branch from my dpu-staging tree [1]

Sean

[1]- https://gitlab.freedesktop.org/seanpaul/dpu-staging.git

> 
> dpu_crtc_disable will change the state, where as dpu_crtc_vblank
> use the variable. The fix is to cache the crtc enabled state
> while holding the lock and use it as a gate in calling
> _dpu_crtc_vblank_enable_no_lock.
> 
> This issue was introduced with the commit cf871c48
> (drm/msm/dpu: Remove suspend state tracking from crtc).
> 
> Below are stack traces of thread 1 and thread 2 in good case
> and bad case:
> 
> Bad case:
> -------------
> Thread 1
> dpu_encoder_phys_vid_control_vblank_irq+0xd0/0x170
> dpu_encoder_register_vblank_callback+0xb8/0x100
> _dpu_crtc_vblank_enable_no_lock+0x240/0x288
> dpu_crtc_disable+0xc4/0x288
> drm_atomic_helper_commit_modeset_disables+0x19c/0x350
> msm_atomic_commit_tail+0x48/0x144
> commit_tail+0x44/0x70
> drm_atomic_helper_commit+0xf0/0xf8
> drm_atomic_commit+0x40/0x4c
> drm_mode_atomic_ioctl+0x374/0x90c
> drm_ioctl_kernel+0xac/0xec
> drm_ioctl+0x218/0x384
> drm_compat_ioctl+0xd8/0xe8
> 
> Thread 2:
> dpu_encoder_phys_vid_control_vblank_irq+0x74/0x170
> dpu_encoder_register_vblank_callback+0xb8/0x100
> _dpu_crtc_vblank_enable_no_lock+0x240/0x288
> dpu_crtc_vblank+0xa8/0x118
> dpu_kms_disable_vblank+0x20/0x2c
> vblank_ctrl_worker+0xa0/0xe0
> kthread_worker_fn+0xe4/0x1a4
> kthread+0x11c/0x12c
> ret_from_fork+0x10/0x18
> 
> Good case:
> --------------
> Thread 1:
> dpu_encoder_phys_vid_control_vblank_irq+0xd0/0x170
> dpu_encoder_phys_vid_irq_control+0xc8/0x110
> _dpu_encoder_irq_control+0x48/0xa0
> _dpu_encoder_resource_control_helper+0xb4/0x10c
> dpu_encoder_resource_control+0x4e0/0x664
> dpu_encoder_virt_enable+0xb8/0x120
> dpu_kms_encoder_enable+0x34/0xcc
> drm_atomic_helper_commit_modeset_enables+0x120/0x1b8
> msm_atomic_commit_tail+0x5c/0x144
> commit_tail+0x44/0x70
> drm_atomic_helper_commit+0xf0/0xf8
> drm_atomic_commit+0x40/0x4c
> drm_mode_atomic_ioctl+0x374/0x90c
> 
> Thread 2:
> dpu_crtc_vblank+0xc8/0x118
> dpu_kms_disable_vblank+0x20/0x2c
> vblank_ctrl_worker+0xa0/0xe0
> kthread_worker_fn+0xe4/0x1a4
> kthread+0x11c/0x12c
> 
> Signed-off-by: Jayant Shekhar <jshekhar@codeaurora.org>
> ---
>  drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c | 17 ++++++++++++++---
>  1 file changed, 14 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
> index 630cbaa..e81ad8c 100644
> --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
> +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
> @@ -877,6 +877,7 @@ static void dpu_crtc_disable(struct drm_crtc *crtc)
>  	struct drm_encoder *encoder;
>  	struct msm_drm_private *priv;
>  	unsigned long flags;
> +	bool crtc_en;
>  
>  	if (!crtc || !crtc->dev || !crtc->dev->dev_private || !crtc->state) {
>  		DPU_ERROR("invalid crtc\n");
> @@ -901,11 +902,21 @@ static void dpu_crtc_disable(struct drm_crtc *crtc)
>  				atomic_read(&dpu_crtc->frame_pending));
>  
>  	trace_dpu_crtc_disable(DRMID(crtc), false, dpu_crtc);
> -	if (dpu_crtc->enabled && dpu_crtc->vblank_requested) {
> -		_dpu_crtc_vblank_enable_no_lock(dpu_crtc, false);
> -	}
> +
> +	/*
> +	 * Cache vblank enabled before calling _dpu_crtc_vblank_enable_no_lock,
> +	 * because we release crtc_lock inside and acquire it back. While lock
> +	 * is released, there are cases where dpu_crtc_vblank comes in between
> +	 * while disable is going on. dpu_crtc_vblank further calls
> +	 * _dpu_crtc_vblank_enable_no_lock which tries vblank disable again
> +	 * resulting in refcount mismatch.
> +	 */
> +	crtc_en = dpu_crtc->enabled;
>  	dpu_crtc->enabled = false;
>  
> +	if (crtc_en && dpu_crtc->vblank_requested)
> +		_dpu_crtc_vblank_enable_no_lock(dpu_crtc, false);
> +
>  	if (atomic_read(&dpu_crtc->frame_pending)) {
>  		trace_dpu_crtc_disable_frame_pending(DRMID(crtc),
>  				     atomic_read(&dpu_crtc->frame_pending));
> -- 
> The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
> a Linux Foundation Collaborative Project
>

Patch

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index 630cbaa..e81ad8c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -877,6 +877,7 @@  static void dpu_crtc_disable(struct drm_crtc *crtc)
 	struct drm_encoder *encoder;
 	struct msm_drm_private *priv;
 	unsigned long flags;
+	bool crtc_en;
 
 	if (!crtc || !crtc->dev || !crtc->dev->dev_private || !crtc->state) {
 		DPU_ERROR("invalid crtc\n");
@@ -901,11 +902,21 @@  static void dpu_crtc_disable(struct drm_crtc *crtc)
 				atomic_read(&dpu_crtc->frame_pending));
 
 	trace_dpu_crtc_disable(DRMID(crtc), false, dpu_crtc);
-	if (dpu_crtc->enabled && dpu_crtc->vblank_requested) {
-		_dpu_crtc_vblank_enable_no_lock(dpu_crtc, false);
-	}
+
+	/*
+	 * Cache vblank enabled before calling _dpu_crtc_vblank_enable_no_lock,
+	 * because we release crtc_lock inside and acquire it back. While lock
+	 * is released, there are cases where dpu_crtc_vblank comes in between
+	 * while disable is going on. dpu_crtc_vblank further calls
+	 * _dpu_crtc_vblank_enable_no_lock which tries vblank disable again
+	 * resulting in refcount mismatch.
+	 */
+	crtc_en = dpu_crtc->enabled;
 	dpu_crtc->enabled = false;
 
+	if (crtc_en && dpu_crtc->vblank_requested)
+		_dpu_crtc_vblank_enable_no_lock(dpu_crtc, false);
+
 	if (atomic_read(&dpu_crtc->frame_pending)) {
 		trace_dpu_crtc_disable_frame_pending(DRMID(crtc),
 				     atomic_read(&dpu_crtc->frame_pending));