[PATCH 1/2] ACPI: scan: Use async schedule function for acpi_scan_clear_dep_fn

[Rafael J. Wysocki]

On Thu, Jan 22, 2026 at 8:35 AM Yicong Yang <yang.yicong at picoheart.com> wrote:
>
> The device object rescan in acpi_scan_clear_dep_fn is scheduled
> in the system workqueue which is not guaranteed to be finished
> before entering userspace. This will cause the problem that
> some key devices are missed when the init task try to find them,
> e.g. console devices and root devices (PCIe nvme, etc).
> This issues is more possbile to happen on RISCV since these
> devices using GSI interrupt may depend on APLIC and will be
> scanned in acpi_scan_clear_dep_queue() after APLIC initialized.
>
> Fix this by scheduling the acpi_scan_clear_dep_queue() using async
> schedule function rather than the system workqueue. The deferred
> works will be synchronized by async_synchronize_full() before
> entering init task.
>
> Update the comment as well.
>
> Signed-off-by: Yicong Yang <yang.yicong at picoheart.com>
> ---
>  drivers/acpi/scan.c | 35 ++++++++++++++++-------------------
>  1 file changed, 16 insertions(+), 19 deletions(-)
>
> diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
> index 416d87f9bd10..bf0d8ba9ba19 100644
> --- a/drivers/acpi/scan.c
> +++ b/drivers/acpi/scan.c
> @@ -5,6 +5,7 @@
>
>  #define pr_fmt(fmt) "ACPI: " fmt
>
> +#include <linux/async.h>
>  #include <linux/module.h>
>  #include <linux/init.h>
>  #include <linux/slab.h>
> @@ -2365,39 +2366,35 @@ struct acpi_scan_clear_dep_work {
>         struct acpi_device *adev;
>  };
>
> -static void acpi_scan_clear_dep_fn(struct work_struct *work)
> +static void acpi_scan_clear_dep_fn(void *dev, async_cookie_t cookie)
>  {
> -       struct acpi_scan_clear_dep_work *cdw;
> -
> -       cdw = container_of(work, struct acpi_scan_clear_dep_work, work);
> +       struct acpi_device *adev = to_acpi_device(dev);
>
>         acpi_scan_lock_acquire();
> -       acpi_bus_attach(cdw->adev, (void *)true);
> +       acpi_bus_attach(adev, (void *)true);
>         acpi_scan_lock_release();
>
> -       acpi_dev_put(cdw->adev);
> -       kfree(cdw);
> +       acpi_dev_put(adev);
>  }
>
>  static bool acpi_scan_clear_dep_queue(struct acpi_device *adev)
>  {
> -       struct acpi_scan_clear_dep_work *cdw;
> -
>         if (adev->dep_unmet)
>                 return false;
>
> -       cdw = kmalloc(sizeof(*cdw), GFP_KERNEL);
> -       if (!cdw)
> -               return false;
> -
> -       cdw->adev = adev;
> -       INIT_WORK(&cdw->work, acpi_scan_clear_dep_fn);
>         /*
> -        * Since the work function may block on the lock until the entire
> -        * initial enumeration of devices is complete, put it into the unbound
> -        * workqueue.
> +        * Async schedule the deferred acpi_scan_clear_dep_fn() since:
> +        * - acpi_bus_attach() needs to hold acpi_scan_lock which cannot
> +        *   be acquired under acpi_dep_list_lock (held here)
> +        * - the deferred work at boot stage is ensured to be finished
> +        *   before entering init task by the async_synchronize_full()
> +        *   barrier
> +        *
> +        * Use _nocall variant since it'll return on failure instead of
> +        * run the function synchronously.
>          */
> -       queue_work(system_dfl_wq, &cdw->work);
> +       if (!async_schedule_dev_nocall(acpi_scan_clear_dep_fn, &adev->dev))

If the problem is that system_dfl_wq is too slow, why don't you just
try a dedicated workqueue for this?

There's no need to modify all of this code.

> +               return false;
>
>         return true;
>  }
> --