On Fri, Feb 2, 2024 at 1:18 PM Nuno Sa via B4 Relay
<devnull+nuno.sa.analog.com@xxxxxxxxxx> wrote:
>
> From: Nuno Sa <nuno.sa@xxxxxxxxxx>
>
> Let's use a dedicated queue for devlinks since releasing a link happens
> asynchronously but some code paths, like DT overlays, have some
> expectations regarding the of_node when being removed (the refcount must
> be 1). Given how devlinks are released that cannot be assured. Hence, add a
> dedicated queue so that it's easy to sync against devlinks removal.
Thanks for following my suggestion!
> While at it, make sure to explicitly include <linux/workqueue.h>.
>
> Signed-off-by: Nuno Sa <nuno.sa@xxxxxxxxxx>
> ---
> drivers/base/core.c | 33 +++++++++++++++++++++++++++++----
> include/linux/fwnode.h | 1 +
> 2 files changed, 30 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/base/core.c b/drivers/base/core.c
> index 14d46af40f9a..06e7766b5227 100644
> --- a/drivers/base/core.c
> +++ b/drivers/base/core.c
> @@ -31,6 +31,7 @@
> #include <linux/swiotlb.h>
> #include <linux/sysfs.h>
> #include <linux/dma-map-ops.h> /* for dma_default_coherent */
> +#include <linux/workqueue.h>
>
> #include "base.h"
> #include "physical_location.h"
> @@ -44,6 +45,7 @@ static bool fw_devlink_is_permissive(void);
> static void __fw_devlink_link_to_consumers(struct device *dev);
> static bool fw_devlink_drv_reg_done;
> static bool fw_devlink_best_effort;
> +static struct workqueue_struct *devlink_release_queue __ro_after_init;
>
> /**
> * __fwnode_link_add - Create a link between two fwnode_handles.
> @@ -235,6 +237,11 @@ static void __fw_devlink_pickup_dangling_consumers(struct fwnode_handle *fwnode,
> __fw_devlink_pickup_dangling_consumers(child, new_sup);
> }
>
> +void fwnode_links_flush_queue(void)
> +{
> + flush_workqueue(devlink_release_queue);
> +}
> +
> static DEFINE_MUTEX(device_links_lock);
> DEFINE_STATIC_SRCU(device_links_srcu);
>
> @@ -531,9 +538,10 @@ static void devlink_dev_release(struct device *dev)
> * It may take a while to complete this work because of the SRCU
> * synchronization in device_link_release_fn() and if the consumer or
> * supplier devices get deleted when it runs, so put it into the "long"
> - * workqueue.
> + * devlink workqueue.
> + *
> */
> - queue_work(system_long_wq, &link->rm_work);
> + queue_work(devlink_release_queue, &link->rm_work);
> }
>
> static struct class devlink_class = {
> @@ -636,10 +644,27 @@ static int __init devlink_class_init(void)
> return ret;
>
> ret = class_interface_register(&devlink_class_intf);
> - if (ret)
> + if (ret) {
> + class_unregister(&devlink_class);
> + return ret;
> + }
> +
> + /*
> + * Using a dedicated queue for devlinks since releasing a link happens
> + * asynchronously but some code paths, like DT overlays, have some
> + * expectations regarding the of_node when being removed (the refcount
> + * must be 1). Given how devlinks are released that cannot be assured.
> + * Hence, add a dedicated queue so that it's easy to sync against
> + * devlinks removal.
> + */
> + devlink_release_queue = alloc_workqueue("devlink_release", 0, 0);
> + if (!devlink_release_queue) {
> + class_interface_unregister(&devlink_class_intf);
> class_unregister(&devlink_class);
This is a bit drastic.
I think that device links can still work if devlink_release_queue is
NULL, just devlink_dev_release() needs to check it and release
synchronously if it is NULL.
Apart from this LGTM.
> + return -ENODEV;
> + }
>
> - return ret;
> + return 0;
> }
> postcore_initcall(devlink_class_init);
>
> diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
> index 2a72f55d26eb..017b170e9903 100644
> --- a/include/linux/fwnode.h
> +++ b/include/linux/fwnode.h
> @@ -213,5 +213,6 @@ extern bool fw_devlink_is_strict(void);
> int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup);
> void fwnode_links_purge(struct fwnode_handle *fwnode);
> void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode);
> +void fwnode_links_flush_queue(void);
>
> #endif
>
> --
