Re: [PATCH] power: genpd: fix lockdep issue for all subdomains

[Marek Szyprowski]

Hello,

On 2016-01-04 11:39, Marek Szyprowski wrote:
> During genpd_poweron, genpd->lock is acquired recursively for each
> parent (master) domain, which are separate obejcts. This confuses
> lockdep, which considers every operation on genpd->lock as being done on
> the same lock class. This leads to the following false positive warning:
>
> =============================================
> [ INFO: possible recursive locking detected ]
> 4.4.0-rc4-xu3s #32 Not tainted
> ---------------------------------------------
> swapper/0/1 is trying to acquire lock:
>   (&genpd->lock){+.+...}, at: [<c0361550>] __genpd_poweron+0x64/0x108
>
> but task is already holding lock:
>   (&genpd->lock){+.+...}, at: [<c0361af8>] genpd_dev_pm_attach+0x168/0x1b8
>
> other info that might help us debug this:
>   Possible unsafe locking scenario:
>
>         CPU0
>         ----
>    lock(&genpd->lock);
>    lock(&genpd->lock);
>
>   *** DEADLOCK ***
>
>   May be due to missing lock nesting notation
>
> 3 locks held by swapper/0/1:
>   #0:  (&dev->mutex){......}, at: [<c0350910>] __driver_attach+0x48/0x98
>   #1:  (&dev->mutex){......}, at: [<c0350920>] __driver_attach+0x58/0x98
>   #2:  (&genpd->lock){+.+...}, at: [<c0361af8>] genpd_dev_pm_attach+0x168/0x1b8
>
> stack backtrace:
> CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.4.0-rc4-xu3s #32
> Hardware name: SAMSUNG EXYNOS (Flattened Device Tree)
> [<c0016c98>] (unwind_backtrace) from [<c00139c4>] (show_stack+0x10/0x14)
> [<c00139c4>] (show_stack) from [<c0270df0>] (dump_stack+0x84/0xc4)
> [<c0270df0>] (dump_stack) from [<c00780b8>] (__lock_acquire+0x1f88/0x215c)
> [<c00780b8>] (__lock_acquire) from [<c007886c>] (lock_acquire+0xa4/0xd0)
> [<c007886c>] (lock_acquire) from [<c0641f2c>] (mutex_lock_nested+0x70/0x4d4)
> [<c0641f2c>] (mutex_lock_nested) from [<c0361550>] (__genpd_poweron+0x64/0x108)
> [<c0361550>] (__genpd_poweron) from [<c0361b00>] (genpd_dev_pm_attach+0x170/0x1b8)
> [<c0361b00>] (genpd_dev_pm_attach) from [<c03520a8>] (platform_drv_probe+0x2c/0xac)
> [<c03520a8>] (platform_drv_probe) from [<c03507d4>] (driver_probe_device+0x208/0x2fc)
> [<c03507d4>] (driver_probe_device) from [<c035095c>] (__driver_attach+0x94/0x98)
> [<c035095c>] (__driver_attach) from [<c034ec14>] (bus_for_each_dev+0x68/0x9c)
> [<c034ec14>] (bus_for_each_dev) from [<c034fec8>] (bus_add_driver+0x1a0/0x218)
> [<c034fec8>] (bus_add_driver) from [<c035115c>] (driver_register+0x78/0xf8)
> [<c035115c>] (driver_register) from [<c0338488>] (exynos_drm_register_drivers+0x28/0x74)
> [<c0338488>] (exynos_drm_register_drivers) from [<c0338594>] (exynos_drm_init+0x6c/0xc4)
> [<c0338594>] (exynos_drm_init) from [<c00097f4>] (do_one_initcall+0x90/0x1dc)
> [<c00097f4>] (do_one_initcall) from [<c0895e08>] (kernel_init_freeable+0x158/0x1f8)
> [<c0895e08>] (kernel_init_freeable) from [<c063ecac>] (kernel_init+0x8/0xe8)
> [<c063ecac>] (kernel_init) from [<c000f7d0>] (ret_from_fork+0x14/0x24)
>
> This patch replaces mutex_lock with mutex_lock_nested() and uses
> recursion depth to annotate each genpd->lock operation with separate
> lockdep subclass.
>
> Reported-by: Anand Moon <linux.amoon@xxxxxxxxx>
> Signed-off-by: Marek Szyprowski <m.szyprowski@xxxxxxxxxxx>

Ulf: could you comment on this patch?

> ---
>   drivers/base/power/domain.c | 21 +++++++++++++--------
>   1 file changed, 13 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
> index b803790..e02ddf6 100644
> --- a/drivers/base/power/domain.c
> +++ b/drivers/base/power/domain.c
> @@ -170,16 +170,15 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
>   	queue_work(pm_wq, &genpd->power_off_work);
>   }
>   
> -static int genpd_poweron(struct generic_pm_domain *genpd);
> -
>   /**
>    * __genpd_poweron - Restore power to a given PM domain and its masters.
>    * @genpd: PM domain to power up.
> + * @depth: nesting count for lockdep.
>    *
>    * Restore power to @genpd and all of its masters so that it is possible to
>    * resume a device belonging to it.
>    */
> -static int __genpd_poweron(struct generic_pm_domain *genpd)
> +static int __genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth)
>   {
>   	struct gpd_link *link;
>   	int ret = 0;
> @@ -194,11 +193,16 @@ static int __genpd_poweron(struct generic_pm_domain *genpd)
>   	 * with it.
>   	 */
>   	list_for_each_entry(link, &genpd->slave_links, slave_node) {
> -		genpd_sd_counter_inc(link->master);
> +		struct generic_pm_domain *master = link->master;
> +
> +		genpd_sd_counter_inc(master);
> +
> +		mutex_lock_nested(&master->lock, depth + 1);
> +		ret = __genpd_poweron(master, depth + 1);
> +		mutex_unlock(&master->lock);
>   
> -		ret = genpd_poweron(link->master);
>   		if (ret) {
> -			genpd_sd_counter_dec(link->master);
> +			genpd_sd_counter_dec(master);
>   			goto err;
>   		}
>   	}
> @@ -230,11 +234,12 @@ static int genpd_poweron(struct generic_pm_domain *genpd)
>   	int ret;
>   
>   	mutex_lock(&genpd->lock);
> -	ret = __genpd_poweron(genpd);
> +	ret = __genpd_poweron(genpd, 0);
>   	mutex_unlock(&genpd->lock);
>   	return ret;
>   }
>   
> +
>   static int genpd_save_dev(struct generic_pm_domain *genpd, struct device *dev)
>   {
>   	return GENPD_DEV_CALLBACK(genpd, int, save_state, dev);
> @@ -482,7 +487,7 @@ static int pm_genpd_runtime_resume(struct device *dev)
>   	}
>   
>   	mutex_lock(&genpd->lock);
> -	ret = __genpd_poweron(genpd);
> +	ret = __genpd_poweron(genpd, 0);
>   	mutex_unlock(&genpd->lock);
>   
>   	if (ret)

Best regards
--
Marek Szyprowski, PhD
Samsung R&D Institute Poland