[PATCH] drm/msm/disp/dpu: Use proper define for drm_encoder_init() 'encoder_type'

Sai Prakash Ranjan saiprakash.ranjan at codeaurora.org
Fri Aug 17 09:06:19 UTC 2018


On 8/17/2018 5:06 AM, Stephen Boyd wrote:
> We got a bug report that this function oopses when trying to do a kasprintf().
> 
> PC is at string+0x2c/0x60
> LR is at vsnprintf+0x28c/0x4ec
> pc : [<ffffff80088d35d8>] lr : [<ffffff80088d5fc4>] pstate: a0c00049
> sp : ffffff80095fb540
> x29: ffffff80095fb540 x28: ffffff8008ad42bc
> x27: 00000000ffffffd8 x26: 0000000000000000
> x25: ffffff8008c216c8 x24: 0000000000000000
> x23: 0000000000000000 x22: ffffff80095fb720
> x21: 0000000000000000 x20: ffffff80095fb720
> x19: ffffff80095fb6f0 x18: 000000000000000a
> x17: 00000000b42ba473 x16: ffffff800805bbe8
> x15: 00000000000a157d x14: 000000000000000c
> x13: 0000000000000000 x12: 0000ffff0000000f
> x11: 0000000000000003 x10: 0000000000000001
> x9 : 0000000000000040 x8 : 000000000000001c
> x7 : ffffffffffffffff x6 : 0000000000000000
> x5 : 0000000000000228 x4 : 0000000000000000
> x3 : ffff0a00ffffff04 x2 : 0000000000007961
> x1 : 0000000000000000 x0 : 0000000000000000
> Process kworker/3:1 (pid: 61, stack limit = 0xffffff80095f8000)
> Call trace:
> Exception stack(0xffffff80095fb400 to 0xffffff80095fb540)
> b400: 0000000000000000 0000000000000000 0000000000007961 ffff0a00ffffff04
> b420: 0000000000000000 0000000000000228 0000000000000000 ffffffffffffffff
> b440: 000000000000001c 0000000000000040 0000000000000001 0000000000000003
> b460: 0000ffff0000000f 0000000000000000 000000000000000c 00000000000a157d
> b480: ffffff800805bbe8 00000000b42ba473 000000000000000a ffffff80095fb6f0
> b4a0: ffffff80095fb720 0000000000000000 ffffff80095fb720 0000000000000000
> b4c0: 0000000000000000 ffffff8008c216c8 0000000000000000 00000000ffffffd8
> b4e0: ffffff8008ad42bc ffffff80095fb540 ffffff80088d5fc4 ffffff80095fb540
> b500: ffffff80088d35d8 00000000a0c00049 ffffff80095fb550 ffffff80080d06a4
> b520: ffffffffffffffff ffffff80088d5e0c ffffff80095fb540 ffffff80088d35d8
> [<ffffff80088d35d8>] string+0x2c/0x60
> [<ffffff80088d5fc4>] vsnprintf+0x28c/0x4ec
> [<ffffff80083973b8>] kvasprintf+0x68/0x100
> [<ffffff800839755c>] kasprintf+0x60/0x80
> [<ffffff800849cc24>] drm_encoder_init+0x134/0x164
> [<ffffff80084d9a7c>] dpu_encoder_init+0x60/0x94
> [<ffffff80084eced0>] _dpu_kms_drm_obj_init+0xa0/0x424
> [<ffffff80084ed870>] dpu_kms_hw_init+0x61c/0x6bc
> [<ffffff80084f7614>] msm_drm_bind+0x380/0x67c
> [<ffffff80085114e4>] try_to_bring_up_master+0x228/0x264
> [<ffffff80085116e8>] component_master_add_with_match+0x90/0xc0
> [<ffffff80084f722c>] msm_pdev_probe+0x260/0x2c8
> [<ffffff800851a910>] platform_drv_probe+0x58/0xa8
> [<ffffff80085185c8>] driver_probe_device+0x2d8/0x40c
> [<ffffff8008518928>] __device_attach_driver+0xd4/0x10c
> [<ffffff800851644c>] bus_for_each_drv+0xb4/0xd0
> [<ffffff8008518230>] __device_attach+0xd0/0x160
> [<ffffff8008518984>] device_initial_probe+0x24/0x30
> [<ffffff800851744c>] bus_probe_device+0x38/0x98
> [<ffffff8008517aac>] deferred_probe_work_func+0x144/0x148
> [<ffffff80080c8654>] process_one_work+0x218/0x3bc
> [<ffffff80080c883c>] process_scheduled_works+0x44/0x48
> [<ffffff80080c95bc>] worker_thread+0x288/0x32c
> [<ffffff80080cea30>] kthread+0x134/0x13c
> [<ffffff8008084750>] ret_from_fork+0x10/0x18
> Code: 910003fd 2a0403e6 eb0400ff 54000060 (38646845)
> 
> Looking at the code I see that drm_encoder_init() is called from the DPU
> code with 'DRM_MODE_CONNECTOR_DSI' passed in as the 'encoder_type'
> argument (follow from _dpu_kms_initialize_dsi()). That corresponds to
> the integer 16. That is then indexed into drm_encoder_enum_list in
> drm_encoder_init() to look up the name of the encoder. If you're still
> following along, that's an encoder not a connector! We really want to
> use DRM_MODE_ENCODER_DSI (integer 6) instead of DRM_MODE_CONNECTOR_DSI
> here, or we'll go out of bounds of the encoder array. Pass the right
> thing and everything is fine.
> 
> Cc: Jeykumar Sankaran <jsanka at codeaurora.org>
> Cc: Jordan Crouse <jcrouse at codeaurora.org>
> Cc: Sean Paul <seanpaul at chromium.org>
> Fixes: 25fdd5933e4c ("drm/msm: Add SDM845 DPU support")
> Signed-off-by: Stephen Boyd <swboyd at chromium.org>
> ---
>   drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c | 2 +-
>   1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
> index 7dd6bd2d6d37..74cc204b07e8 100644
> --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
> +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
> @@ -450,7 +450,7 @@ static void _dpu_kms_initialize_dsi(struct drm_device *dev,
>   	int i, rc;
>   
>   	/*TODO: Support two independent DSI connectors */
> -	encoder = dpu_encoder_init(dev, DRM_MODE_CONNECTOR_DSI);
> +	encoder = dpu_encoder_init(dev, DRM_MODE_ENCODER_DSI);
>   	if (IS_ERR_OR_NULL(encoder)) {
>   		DPU_ERROR("encoder init failed for dsi display\n");
>   		return;
> 

I have tested this on sdm845 mtp and it does fix the issue.
Tested-by: Sai Prakash Ranjan <saiprakash.ranjan at codeaurora.org>


More information about the dri-devel mailing list