2017-10-04 19:53 GMT+02:00 Emil Renner Berthing <kernel at esmil.dk>:
> On the Samsung Chromebook Plus I get this error with 4.14-rc3:
>
> BUG: scheduling while atomic: kworker/3:1/50/0x00000002
> Modules linked in:
> CPU: 3 PID: 50 Comm: kworker/3:1 Not tainted 4.14.0-0.rc3-kevin #2
> Hardware name: Google Kevin (DT)
> Workqueue: events analogix_dp_psr_work
> Call trace:
> [<ffffff80080873b0>] dump_backtrace+0x0/0x320
> [<ffffff80080876e4>] show_stack+0x14/0x20
> [<ffffff8008606d38>] dump_stack+0x9c/0xbc
> [<ffffff80080c6b5c>] __schedule_bug+0x4c/0x70
> [<ffffff80086188c0>] __schedule+0x3f0/0x458
> [<ffffff8008618960>] schedule+0x38/0xa0
> [<ffffff800861c20c>] schedule_hrtimeout_range_clock+0x84/0xe8
> [<ffffff800861c2a0>] schedule_hrtimeout_range+0x10/0x18
> [<ffffff800861bcec>] usleep_range+0x64/0x78
> [<ffffff8008415a6c>] analogix_dp_transfer+0x16c/0x340
> [<ffffff8008412550>] analogix_dpaux_transfer+0x10/0x18
> [<ffffff80083ceb14>] drm_dp_dpcd_access+0x4c/0xf0
> [<ffffff80083cf614>] drm_dp_dpcd_write+0x1c/0x28
> [<ffffff8008413b98>] analogix_dp_disable_psr+0x60/0xa8
> [<ffffff800840da3c>] analogix_dp_psr_work+0x4c/0x90
> [<ffffff80080bb09c>] process_one_work+0x1d4/0x348
> [<ffffff80080bb258>] worker_thread+0x48/0x478
> [<ffffff80080c11fc>] kthread+0x12c/0x130
> [<ffffff8008084290>] ret_from_fork+0x10/0x18
>
> Changing rockchip_dp_device::psr_lock to a mutex rather
> than spinlock seems to fix the issue.
>
> Signed-off-by: Emil Renner Berthing <kernel at esmil.dk>
> ---
> drivers/gpu/drm/rockchip/analogix_dp-rockchip.c | 14 ++++++--------
> 1 file changed, 6 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
> index 9606121fa185..d8f72d87ef08 100644
> --- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
> +++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
> @@ -72,7 +72,7 @@ struct rockchip_dp_device {
> struct reset_control *rst;
>
> struct work_struct psr_work;
> - spinlock_t psr_lock;
> + struct mutex psr_lock;
> unsigned int psr_state;
>
> const struct rockchip_dp_chip_data *data;
> @@ -83,21 +83,20 @@ struct rockchip_dp_device {
> static void analogix_dp_psr_set(struct drm_encoder *encoder, bool enabled)
> {
> struct rockchip_dp_device *dp = to_dp(encoder);
> - unsigned long flags;
>
> if (!analogix_dp_psr_supported(dp->dev))
> return;
>
> dev_dbg(dp->dev, "%s PSR...\n", enabled ? "Entry" : "Exit");
>
> - spin_lock_irqsave(&dp->psr_lock, flags);
> + mutex_lock(&dp->psr_lock);
> if (enabled)
> dp->psr_state = EDP_VSC_PSR_STATE_ACTIVE;
> else
> dp->psr_state = ~EDP_VSC_PSR_STATE_ACTIVE;
>
> schedule_work(&dp->psr_work);
> - spin_unlock_irqrestore(&dp->psr_lock, flags);
> + mutex_unlock(&dp->psr_lock);
> }
>
> static void analogix_dp_psr_work(struct work_struct *work)
> @@ -105,7 +104,6 @@ static void analogix_dp_psr_work(struct work_struct *work)
> struct rockchip_dp_device *dp =
> container_of(work, typeof(*dp), psr_work);
> int ret;
> - unsigned long flags;
>
> ret = rockchip_drm_wait_vact_end(dp->encoder.crtc,
> PSR_WAIT_LINE_FLAG_TIMEOUT_MS);
> @@ -114,12 +112,12 @@ static void analogix_dp_psr_work(struct work_struct *work)
> return;
> }
>
> - spin_lock_irqsave(&dp->psr_lock, flags);
> + mutex_lock(&dp->psr_lock);
> if (dp->psr_state == EDP_VSC_PSR_STATE_ACTIVE)
> analogix_dp_enable_psr(dp->dev);
> else
> analogix_dp_disable_psr(dp->dev);
> - spin_unlock_irqrestore(&dp->psr_lock, flags);
> + mutex_unlock(&dp->psr_lock);
> }
>
> static int rockchip_dp_pre_init(struct rockchip_dp_device *dp)
> @@ -381,7 +379,7 @@ static int rockchip_dp_bind(struct device *dev, struct device *master,
> dp->plat_data.power_off = rockchip_dp_powerdown;
> dp->plat_data.get_modes = rockchip_dp_get_modes;
>
> - spin_lock_init(&dp->psr_lock);
> + mutex_init(&dp->psr_lock);
> dp->psr_state = ~EDP_VSC_PSR_STATE_ACTIVE;
> INIT_WORK(&dp->psr_work, analogix_dp_psr_work);
>
> --
> 2.14.2
>
Right this patch fixes the issue for me too.
Tested-by: Enric Balletbo i Serra <enric.balletbo at collabora.com>
