Re: [PATCH v3 01/12] drm/mediatek: add refcount for DPI power on/off

[CK Hu]

Hi, Bibby:

On Fri, 2018-09-21 at 11:28 +0800, Bibby Hsieh wrote:
> From: chunhui dai <chunhui.dai@xxxxxxxxxxxx>
> 
> After the kernel 4.4, the DRM disable flow was changed, if DPI was
> disableed before CRTC, it will cause warning message as following:
> 
> ------------[ cut here ]------------
> WARNING: CPU: 0 PID: 1339 at ../../linux/linux-4.4.24-mtk/drivers/gpu/drm/drm_irq.c:1326 drm_wait_one_vblank+0x188/0x18c()
> vblank wait timed out on crtc 0
> Modules linked in: bridge mt8521p_ir_shim(O) i2c_eeprom(O) mtk_m4(O) fuse_ctrl(O) virtual_block(O) caamkeys(PO) chk(PO) amperctl(O) ledctl(O) apple_auth(PO) micctl(O) sensors(PO) lla(O) sdd(PO) ice40_fpga(O) psmon(O) event_queue(PO) utils(O) blackbox(O)
> CPU: 0 PID: 1339 Comm: kworker/0:1 Tainted: P        W  O    4.4.24 #1
> Hardware name: Mediatek Cortex-A7 (Device Tree)
> Workqueue: events drm_mode_rmfb_work_fn
> [<c001a710>] (unwind_backtrace) from [<c00151e4>] (show_stack+0x20/0x24)
> [<c00151e4>] (show_stack) from [<c027961c>] (dump_stack+0x98/0xac)
> [<c027961c>] (dump_stack) from [<c002ac54>] (warn_slowpath_common+0x94/0xc4)
> [<c002ac54>] (warn_slowpath_common) from [<c002acc4>] (warn_slowpath_fmt+0x40/0x48)
> [<c002acc4>] (warn_slowpath_fmt) from [<c03307ac>] (drm_wait_one_vblank+0x188/0x18c)
> [<c03307ac>] (drm_wait_one_vblank) from [<c03307d8>] (drm_crtc_wait_one_vblank+0x28/0x2c)
> [<c03307d8>] (drm_crtc_wait_one_vblank) from [<c034f48c>] (mtk_drm_crtc_disable+0x78/0x240)
> [<c034f48c>] (mtk_drm_crtc_disable) from [<c03240d4>] (drm_atomic_helper_commit_modeset_disables+0x128/0x3b8)
> [<c03240d4>] (drm_atomic_helper_commit_modeset_disables) from [<c0350a7c>] (mtk_atomic_complete+0x74/0xb4)
> [<c0350a7c>] (mtk_atomic_complete) from [<c0350b24>] (mtk_atomic_commit+0x68/0x98)
> [<c0350b24>] (mtk_atomic_commit) from [<c034ab48>] (drm_atomic_commit+0x54/0x74)
> [<c034ab48>] (drm_atomic_commit) from [<c0325c4c>] (drm_atomic_helper_set_config+0x7c/0xa0)
> [<c0325c4c>] (drm_atomic_helper_set_config) from [<c0338594>] (drm_mode_set_config_internal+0x68/0xe4)
> [<c0338594>] (drm_mode_set_config_internal) from [<c033967c>] (drm_framebuffer_remove+0xe4/0x120)
> [<c033967c>] (drm_framebuffer_remove) from [<c0339700>] (drm_mode_rmfb_work_fn+0x48/0x58)
> [<c0339700>] (drm_mode_rmfb_work_fn) from [<c0043a38>] (process_one_work+0x154/0x50c)
> [<c0043a38>] (process_one_work) from [<c0044074>] (worker_thread+0x284/0x568)
> [<c0044074>] (worker_thread) from [<c0049dc4>] (kthread+0xec/0x104)
> [<c0049dc4>] (kthread) from [<c0010678>] (ret_from_fork+0x14/0x3c)
> ---[ end trace 12ae5358e992abd5 ]---
> 
> so, we add refcount for DPI power on/off to protect the flow.
> 
> Signed-off-by: Bibby Hsieh <bibby.hsieh@xxxxxxxxxxxx>
> Signed-off-by: chunhui dai <chunhui.dai@xxxxxxxxxxxx>
> ---
>  drivers/gpu/drm/mediatek/mtk_dpi.c | 16 ++++++++++++++--
>  1 file changed, 14 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c
> index 6c0ea39d5739..d9373e67d328 100644
> --- a/drivers/gpu/drm/mediatek/mtk_dpi.c
> +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c
> @@ -77,6 +77,7 @@ struct mtk_dpi {
>  	enum mtk_dpi_out_bit_num bit_num;
>  	enum mtk_dpi_out_channel_swap channel_swap;
>  	bool power_sta;
> +	int refcount;
>  	u8 power_ctl;
>  };
>  
> @@ -369,6 +370,12 @@ static void mtk_dpi_config_color_format(struct mtk_dpi *dpi,
>  
>  static void mtk_dpi_power_off(struct mtk_dpi *dpi, enum mtk_dpi_power_ctl pctl)
>  {
> +	if (WARN_ON(dpi->refcount == 0))
> +		return;
> +
> +	if (--dpi->refcount != 0)
> +		return;
> +
>  	dpi->power_ctl &= ~pctl;
>  
>  	if ((dpi->power_ctl & DPI_POWER_START) ||
> @@ -388,14 +395,17 @@ static int mtk_dpi_power_on(struct mtk_dpi *dpi, enum mtk_dpi_power_ctl pctl)
>  {
>  	int ret;
>  
> +	if (++dpi->refcount != 1)
> +		return 0;
> +
>  	dpi->power_ctl |= pctl;
>  
>  	if (!(dpi->power_ctl & DPI_POWER_START) &&
>  	    !(dpi->power_ctl & DPI_POWER_ENABLE))
> -		return 0;
> +		goto err_refcount;
>  
>  	if (dpi->power_sta)
> -		return 0;
> +		goto err_refcount;

I think dpi->power_ctl and dpi->power_sta is something like reference
count. mtk_dpi_start() and mtk_dpi_stop() is called by crtc. If the
error message happen without this patch, I think there is a bug in
dpi->power_ctl and dpi->power_sta. I think you should fix the bug of
dpi->power_ctl and dpi->power_sta, or just replace it with your
reference count mechanism.

Regards,
CK

>  
>  	ret = clk_prepare_enable(dpi->engine_clk);
>  	if (ret) {
> @@ -417,6 +427,8 @@ static int mtk_dpi_power_on(struct mtk_dpi *dpi, enum mtk_dpi_power_ctl pctl)
>  	clk_disable_unprepare(dpi->engine_clk);
>  err_eng:
>  	dpi->power_ctl &= ~pctl;
> +err_refcount:
> +	dpi->refcount--;
>  	return ret;
>  }
>