linux/drivers/base/dd.c
Grant Likely 58b116bce1 drivercore: deferral race condition fix
When the kernel is built with CONFIG_PREEMPT it is possible to reach a state
when all modules loaded but some driver still stuck in the deferred list
and there is a need for external event to kick the deferred queue to probe
these drivers.

The issue has been observed on embedded systems with CONFIG_PREEMPT enabled,
audio support built as modules and using nfsroot for root filesystem.

The following log fragment shows such sequence when all audio modules
were loaded but the sound card is not present since the machine driver has
failed to probe due to missing dependency during it's probe.
The board is am335x-evmsk (McASP<->tlv320aic3106 codec) with davinci-evm
machine driver:

...
[   12.615118] davinci-mcasp 4803c000.mcasp: davinci_mcasp_probe: ENTER
[   12.719969] davinci_evm sound.3: davinci_evm_probe: ENTER
[   12.725753] davinci_evm sound.3: davinci_evm_probe: snd_soc_register_card
[   12.753846] davinci-mcasp 4803c000.mcasp: davinci_mcasp_probe: snd_soc_register_component
[   12.922051] davinci-mcasp 4803c000.mcasp: davinci_mcasp_probe: snd_soc_register_component DONE
[   12.950839] davinci_evm sound.3: ASoC: platform (null) not registered
[   12.957898] davinci_evm sound.3: davinci_evm_probe: snd_soc_register_card DONE (-517)
[   13.099026] davinci-mcasp 4803c000.mcasp: Kicking the deferred list
[   13.177838] davinci-mcasp 4803c000.mcasp: really_probe: probe_count = 2
[   13.194130] davinci_evm sound.3: snd_soc_register_card failed (-517)
[   13.346755] davinci_mcasp_driver_init: LEAVE
[   13.377446] platform sound.3: Driver davinci_evm requests probe deferral
[   13.592527] platform sound.3: really_probe: probe_count = 0

In the log the machine driver enters it's probe at 12.719969 (this point it
has been removed from the deferred lists). McASP driver already executing
it's probing (since 12.615118).
The machine driver tries to construct the sound card (12.950839) but did
not found one of the components so it fails. After this McASP driver
registers all the ASoC components (the machine driver still in it's probe
function after it failed to construct the card) and the deferred work is
prepared at 13.099026 (note that this time the machine driver is not in the
lists so it is not going to be handled when the work is executing).
Lastly the machine driver exit from it's probe and the core places it to
the deferred list but there will be no other driver going to load and the
deferred queue is not going to be kicked again - till we have external event
like connecting USB stick, etc.

The proposed solution is to try the deferred queue once more when the last
driver is asking for deferring and we had drivers loaded while this last
driver was probing.

This way we can avoid drivers stuck in the deferred queue.

Signed-off-by: Grant Likely <grant.likely@linaro.org>
Reviewed-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Tested-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Stable <stable@vger.kernel.org> # v3.4+
2014-04-29 15:44:05 +01:00

616 lines
17 KiB
C

/*
* drivers/base/dd.c - The core device/driver interactions.
*
* This file contains the (sometimes tricky) code that controls the
* interactions between devices and drivers, which primarily includes
* driver binding and unbinding.
*
* All of this code used to exist in drivers/base/bus.c, but was
* relocated to here in the name of compartmentalization (since it wasn't
* strictly code just for the 'struct bus_type'.
*
* Copyright (c) 2002-5 Patrick Mochel
* Copyright (c) 2002-3 Open Source Development Labs
* Copyright (c) 2007-2009 Greg Kroah-Hartman <gregkh@suse.de>
* Copyright (c) 2007-2009 Novell Inc.
*
* This file is released under the GPLv2
*/
#include <linux/device.h>
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/kthread.h>
#include <linux/wait.h>
#include <linux/async.h>
#include <linux/pm_runtime.h>
#include <linux/pinctrl/devinfo.h>
#include "base.h"
#include "power/power.h"
/*
* Deferred Probe infrastructure.
*
* Sometimes driver probe order matters, but the kernel doesn't always have
* dependency information which means some drivers will get probed before a
* resource it depends on is available. For example, an SDHCI driver may
* first need a GPIO line from an i2c GPIO controller before it can be
* initialized. If a required resource is not available yet, a driver can
* request probing to be deferred by returning -EPROBE_DEFER from its probe hook
*
* Deferred probe maintains two lists of devices, a pending list and an active
* list. A driver returning -EPROBE_DEFER causes the device to be added to the
* pending list. A successful driver probe will trigger moving all devices
* from the pending to the active list so that the workqueue will eventually
* retry them.
*
* The deferred_probe_mutex must be held any time the deferred_probe_*_list
* of the (struct device*)->p->deferred_probe pointers are manipulated
*/
static DEFINE_MUTEX(deferred_probe_mutex);
static LIST_HEAD(deferred_probe_pending_list);
static LIST_HEAD(deferred_probe_active_list);
static struct workqueue_struct *deferred_wq;
static atomic_t deferred_trigger_count = ATOMIC_INIT(0);
/**
* deferred_probe_work_func() - Retry probing devices in the active list.
*/
static void deferred_probe_work_func(struct work_struct *work)
{
struct device *dev;
struct device_private *private;
/*
* This block processes every device in the deferred 'active' list.
* Each device is removed from the active list and passed to
* bus_probe_device() to re-attempt the probe. The loop continues
* until every device in the active list is removed and retried.
*
* Note: Once the device is removed from the list and the mutex is
* released, it is possible for the device get freed by another thread
* and cause a illegal pointer dereference. This code uses
* get/put_device() to ensure the device structure cannot disappear
* from under our feet.
*/
mutex_lock(&deferred_probe_mutex);
while (!list_empty(&deferred_probe_active_list)) {
private = list_first_entry(&deferred_probe_active_list,
typeof(*dev->p), deferred_probe);
dev = private->device;
list_del_init(&private->deferred_probe);
get_device(dev);
/*
* Drop the mutex while probing each device; the probe path may
* manipulate the deferred list
*/
mutex_unlock(&deferred_probe_mutex);
/*
* Force the device to the end of the dpm_list since
* the PM code assumes that the order we add things to
* the list is a good order for suspend but deferred
* probe makes that very unsafe.
*/
device_pm_lock();
device_pm_move_last(dev);
device_pm_unlock();
dev_dbg(dev, "Retrying from deferred list\n");
bus_probe_device(dev);
mutex_lock(&deferred_probe_mutex);
put_device(dev);
}
mutex_unlock(&deferred_probe_mutex);
}
static DECLARE_WORK(deferred_probe_work, deferred_probe_work_func);
static void driver_deferred_probe_add(struct device *dev)
{
mutex_lock(&deferred_probe_mutex);
if (list_empty(&dev->p->deferred_probe)) {
dev_dbg(dev, "Added to deferred list\n");
list_add_tail(&dev->p->deferred_probe, &deferred_probe_pending_list);
}
mutex_unlock(&deferred_probe_mutex);
}
void driver_deferred_probe_del(struct device *dev)
{
mutex_lock(&deferred_probe_mutex);
if (!list_empty(&dev->p->deferred_probe)) {
dev_dbg(dev, "Removed from deferred list\n");
list_del_init(&dev->p->deferred_probe);
}
mutex_unlock(&deferred_probe_mutex);
}
static bool driver_deferred_probe_enable = false;
/**
* driver_deferred_probe_trigger() - Kick off re-probing deferred devices
*
* This functions moves all devices from the pending list to the active
* list and schedules the deferred probe workqueue to process them. It
* should be called anytime a driver is successfully bound to a device.
*
* Note, there is a race condition in multi-threaded probe. In the case where
* more than one device is probing at the same time, it is possible for one
* probe to complete successfully while another is about to defer. If the second
* depends on the first, then it will get put on the pending list after the
* trigger event has already occured and will be stuck there.
*
* The atomic 'deferred_trigger_count' is used to determine if a successful
* trigger has occurred in the midst of probing a driver. If the trigger count
* changes in the midst of a probe, then deferred processing should be triggered
* again.
*/
static void driver_deferred_probe_trigger(void)
{
if (!driver_deferred_probe_enable)
return;
/*
* A successful probe means that all the devices in the pending list
* should be triggered to be reprobed. Move all the deferred devices
* into the active list so they can be retried by the workqueue
*/
mutex_lock(&deferred_probe_mutex);
atomic_inc(&deferred_trigger_count);
list_splice_tail_init(&deferred_probe_pending_list,
&deferred_probe_active_list);
mutex_unlock(&deferred_probe_mutex);
/*
* Kick the re-probe thread. It may already be scheduled, but it is
* safe to kick it again.
*/
queue_work(deferred_wq, &deferred_probe_work);
}
/**
* deferred_probe_initcall() - Enable probing of deferred devices
*
* We don't want to get in the way when the bulk of drivers are getting probed.
* Instead, this initcall makes sure that deferred probing is delayed until
* late_initcall time.
*/
static int deferred_probe_initcall(void)
{
deferred_wq = create_singlethread_workqueue("deferwq");
if (WARN_ON(!deferred_wq))
return -ENOMEM;
driver_deferred_probe_enable = true;
driver_deferred_probe_trigger();
/* Sort as many dependencies as possible before exiting initcalls */
flush_workqueue(deferred_wq);
return 0;
}
late_initcall(deferred_probe_initcall);
static void driver_bound(struct device *dev)
{
if (klist_node_attached(&dev->p->knode_driver)) {
printk(KERN_WARNING "%s: device %s already bound\n",
__func__, kobject_name(&dev->kobj));
return;
}
pr_debug("driver: '%s': %s: bound to device '%s'\n", dev->driver->name,
__func__, dev_name(dev));
klist_add_tail(&dev->p->knode_driver, &dev->driver->p->klist_devices);
/*
* Make sure the device is no longer in one of the deferred lists and
* kick off retrying all pending devices
*/
driver_deferred_probe_del(dev);
driver_deferred_probe_trigger();
if (dev->bus)
blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
BUS_NOTIFY_BOUND_DRIVER, dev);
}
static int driver_sysfs_add(struct device *dev)
{
int ret;
if (dev->bus)
blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
BUS_NOTIFY_BIND_DRIVER, dev);
ret = sysfs_create_link(&dev->driver->p->kobj, &dev->kobj,
kobject_name(&dev->kobj));
if (ret == 0) {
ret = sysfs_create_link(&dev->kobj, &dev->driver->p->kobj,
"driver");
if (ret)
sysfs_remove_link(&dev->driver->p->kobj,
kobject_name(&dev->kobj));
}
return ret;
}
static void driver_sysfs_remove(struct device *dev)
{
struct device_driver *drv = dev->driver;
if (drv) {
sysfs_remove_link(&drv->p->kobj, kobject_name(&dev->kobj));
sysfs_remove_link(&dev->kobj, "driver");
}
}
/**
* device_bind_driver - bind a driver to one device.
* @dev: device.
*
* Allow manual attachment of a driver to a device.
* Caller must have already set @dev->driver.
*
* Note that this does not modify the bus reference count
* nor take the bus's rwsem. Please verify those are accounted
* for before calling this. (It is ok to call with no other effort
* from a driver's probe() method.)
*
* This function must be called with the device lock held.
*/
int device_bind_driver(struct device *dev)
{
int ret;
ret = driver_sysfs_add(dev);
if (!ret)
driver_bound(dev);
return ret;
}
EXPORT_SYMBOL_GPL(device_bind_driver);
static atomic_t probe_count = ATOMIC_INIT(0);
static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue);
static int really_probe(struct device *dev, struct device_driver *drv)
{
int ret = 0;
int local_trigger_count = atomic_read(&deferred_trigger_count);
atomic_inc(&probe_count);
pr_debug("bus: '%s': %s: probing driver %s with device %s\n",
drv->bus->name, __func__, drv->name, dev_name(dev));
WARN_ON(!list_empty(&dev->devres_head));
dev->driver = drv;
/* If using pinctrl, bind pins now before probing */
ret = pinctrl_bind_pins(dev);
if (ret)
goto probe_failed;
if (driver_sysfs_add(dev)) {
printk(KERN_ERR "%s: driver_sysfs_add(%s) failed\n",
__func__, dev_name(dev));
goto probe_failed;
}
if (dev->bus->probe) {
ret = dev->bus->probe(dev);
if (ret)
goto probe_failed;
} else if (drv->probe) {
ret = drv->probe(dev);
if (ret)
goto probe_failed;
}
driver_bound(dev);
ret = 1;
pr_debug("bus: '%s': %s: bound device %s to driver %s\n",
drv->bus->name, __func__, dev_name(dev), drv->name);
goto done;
probe_failed:
devres_release_all(dev);
driver_sysfs_remove(dev);
dev->driver = NULL;
dev_set_drvdata(dev, NULL);
if (ret == -EPROBE_DEFER) {
/* Driver requested deferred probing */
dev_info(dev, "Driver %s requests probe deferral\n", drv->name);
driver_deferred_probe_add(dev);
/* Did a trigger occur while probing? Need to re-trigger if yes */
if (local_trigger_count != atomic_read(&deferred_trigger_count))
driver_deferred_probe_trigger();
} else if (ret != -ENODEV && ret != -ENXIO) {
/* driver matched but the probe failed */
printk(KERN_WARNING
"%s: probe of %s failed with error %d\n",
drv->name, dev_name(dev), ret);
} else {
pr_debug("%s: probe of %s rejects match %d\n",
drv->name, dev_name(dev), ret);
}
/*
* Ignore errors returned by ->probe so that the next driver can try
* its luck.
*/
ret = 0;
done:
atomic_dec(&probe_count);
wake_up(&probe_waitqueue);
return ret;
}
/**
* driver_probe_done
* Determine if the probe sequence is finished or not.
*
* Should somehow figure out how to use a semaphore, not an atomic variable...
*/
int driver_probe_done(void)
{
pr_debug("%s: probe_count = %d\n", __func__,
atomic_read(&probe_count));
if (atomic_read(&probe_count))
return -EBUSY;
return 0;
}
/**
* wait_for_device_probe
* Wait for device probing to be completed.
*/
void wait_for_device_probe(void)
{
/* wait for the known devices to complete their probing */
wait_event(probe_waitqueue, atomic_read(&probe_count) == 0);
async_synchronize_full();
}
EXPORT_SYMBOL_GPL(wait_for_device_probe);
/**
* driver_probe_device - attempt to bind device & driver together
* @drv: driver to bind a device to
* @dev: device to try to bind to the driver
*
* This function returns -ENODEV if the device is not registered,
* 1 if the device is bound successfully and 0 otherwise.
*
* This function must be called with @dev lock held. When called for a
* USB interface, @dev->parent lock must be held as well.
*/
int driver_probe_device(struct device_driver *drv, struct device *dev)
{
int ret = 0;
if (!device_is_registered(dev))
return -ENODEV;
pr_debug("bus: '%s': %s: matched device %s with driver %s\n",
drv->bus->name, __func__, dev_name(dev), drv->name);
pm_runtime_barrier(dev);
ret = really_probe(dev, drv);
pm_request_idle(dev);
return ret;
}
static int __device_attach(struct device_driver *drv, void *data)
{
struct device *dev = data;
if (!driver_match_device(drv, dev))
return 0;
return driver_probe_device(drv, dev);
}
/**
* device_attach - try to attach device to a driver.
* @dev: device.
*
* Walk the list of drivers that the bus has and call
* driver_probe_device() for each pair. If a compatible
* pair is found, break out and return.
*
* Returns 1 if the device was bound to a driver;
* 0 if no matching driver was found;
* -ENODEV if the device is not registered.
*
* When called for a USB interface, @dev->parent lock must be held.
*/
int device_attach(struct device *dev)
{
int ret = 0;
device_lock(dev);
if (dev->driver) {
if (klist_node_attached(&dev->p->knode_driver)) {
ret = 1;
goto out_unlock;
}
ret = device_bind_driver(dev);
if (ret == 0)
ret = 1;
else {
dev->driver = NULL;
ret = 0;
}
} else {
ret = bus_for_each_drv(dev->bus, NULL, dev, __device_attach);
pm_request_idle(dev);
}
out_unlock:
device_unlock(dev);
return ret;
}
EXPORT_SYMBOL_GPL(device_attach);
static int __driver_attach(struct device *dev, void *data)
{
struct device_driver *drv = data;
/*
* Lock device and try to bind to it. We drop the error
* here and always return 0, because we need to keep trying
* to bind to devices and some drivers will return an error
* simply if it didn't support the device.
*
* driver_probe_device() will spit a warning if there
* is an error.
*/
if (!driver_match_device(drv, dev))
return 0;
if (dev->parent) /* Needed for USB */
device_lock(dev->parent);
device_lock(dev);
if (!dev->driver)
driver_probe_device(drv, dev);
device_unlock(dev);
if (dev->parent)
device_unlock(dev->parent);
return 0;
}
/**
* driver_attach - try to bind driver to devices.
* @drv: driver.
*
* Walk the list of devices that the bus has on it and try to
* match the driver with each one. If driver_probe_device()
* returns 0 and the @dev->driver is set, we've found a
* compatible pair.
*/
int driver_attach(struct device_driver *drv)
{
return bus_for_each_dev(drv->bus, NULL, drv, __driver_attach);
}
EXPORT_SYMBOL_GPL(driver_attach);
/*
* __device_release_driver() must be called with @dev lock held.
* When called for a USB interface, @dev->parent lock must be held as well.
*/
static void __device_release_driver(struct device *dev)
{
struct device_driver *drv;
drv = dev->driver;
if (drv) {
pm_runtime_get_sync(dev);
driver_sysfs_remove(dev);
if (dev->bus)
blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
BUS_NOTIFY_UNBIND_DRIVER,
dev);
pm_runtime_put_sync(dev);
if (dev->bus && dev->bus->remove)
dev->bus->remove(dev);
else if (drv->remove)
drv->remove(dev);
devres_release_all(dev);
dev->driver = NULL;
dev_set_drvdata(dev, NULL);
klist_remove(&dev->p->knode_driver);
if (dev->bus)
blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
BUS_NOTIFY_UNBOUND_DRIVER,
dev);
}
}
/**
* device_release_driver - manually detach device from driver.
* @dev: device.
*
* Manually detach device from driver.
* When called for a USB interface, @dev->parent lock must be held.
*/
void device_release_driver(struct device *dev)
{
/*
* If anyone calls device_release_driver() recursively from
* within their ->remove callback for the same device, they
* will deadlock right here.
*/
device_lock(dev);
__device_release_driver(dev);
device_unlock(dev);
}
EXPORT_SYMBOL_GPL(device_release_driver);
/**
* driver_detach - detach driver from all devices it controls.
* @drv: driver.
*/
void driver_detach(struct device_driver *drv)
{
struct device_private *dev_prv;
struct device *dev;
for (;;) {
spin_lock(&drv->p->klist_devices.k_lock);
if (list_empty(&drv->p->klist_devices.k_list)) {
spin_unlock(&drv->p->klist_devices.k_lock);
break;
}
dev_prv = list_entry(drv->p->klist_devices.k_list.prev,
struct device_private,
knode_driver.n_node);
dev = dev_prv->device;
get_device(dev);
spin_unlock(&drv->p->klist_devices.k_lock);
if (dev->parent) /* Needed for USB */
device_lock(dev->parent);
device_lock(dev);
if (dev->driver == drv)
__device_release_driver(dev);
device_unlock(dev);
if (dev->parent)
device_unlock(dev->parent);
put_device(dev);
}
}
/*
* These exports can't be _GPL due to .h files using this within them, and it
* might break something that was previously working...
*/
void *dev_get_drvdata(const struct device *dev)
{
if (dev && dev->p)
return dev->p->driver_data;
return NULL;
}
EXPORT_SYMBOL(dev_get_drvdata);
int dev_set_drvdata(struct device *dev, void *data)
{
int error;
if (!dev->p) {
error = device_private_init(dev);
if (error)
return error;
}
dev->p->driver_data = data;
return 0;
}
EXPORT_SYMBOL(dev_set_drvdata);