The patch introduces the flag of memalloc_noio_resume in
'struct dev_pm_info' to help PM core to teach mm not allocating
memory with GFP_KERNEL flag for avoiding probable deadlock
problem.
As explained in the comment, any GFP_KERNEL allocation inside
runtime_resume on any one of device in the path from one block
or network device to the root device in the device tree may cause
deadlock, the introduced pm_runtime_set_memalloc_noio() sets or
clears the flag on device of the path recursively.
This patch also introduces pm_runtime_get_memalloc_noio() because
the flag may be accessed in block device's error handling path
(for example, usb device reset)
Cc: Alan Stern <stern@xxxxxxxxxxxxxxxxxxx>
Cc: "Rafael J. Wysocki" <rjw@xxxxxxx>
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxxxxx>
---
v3:
- introduce pm_runtime_get_memalloc_noio()
- hold one global lock on pm_runtime_set_memalloc_noio
- hold device power lock when accessing memalloc_noio_resume
flag suggested by Alan Stern
- implement pm_runtime_set_memalloc_noio without recursion
suggested by Alan Stern
v2:
- introduce pm_runtime_set_memalloc_noio()
---
drivers/base/power/runtime.c | 72 ++++++++++++++++++++++++++++++++++++++++++
include/linux/pm.h | 1 +
include/linux/pm_runtime.h | 5 +++
3 files changed, 78 insertions(+)
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 3148b10..9fa6ea7 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -124,6 +124,78 @@ unsigned long pm_runtime_autosuspend_expiration(struct device *dev)
}
EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration);
+/*
+ * pm_runtime_get_memalloc_noio - Get a device's memalloc_noio flag.
+ * @dev: Device to handle.
+ *
+ * Return the device's memalloc_noio flag.
+ *
+ * The device power lock is held because bitfield is not SMP-safe.
+ */
+bool pm_runtime_get_memalloc_noio(struct device *dev)
+{
+ bool ret;
+ spin_lock_irq(&dev->power.lock);
+ ret = dev->power.memalloc_noio_resume;
+ spin_unlock_irq(&dev->power.lock);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_get_memalloc_noio);
+
+static int dev_memalloc_noio(struct device *dev, void *data)
+{
+ return pm_runtime_get_memalloc_noio(dev);
+}
+
+/*
+ * pm_runtime_set_memalloc_noio - Set a device's memalloc_noio flag.
+ * @dev: Device to handle.
+ * @enable: True for setting the flag and False for clearing the flag.
+ *
+ * Set the flag for all devices in the path from the device to the
+ * root device in the device tree if @enable is true, otherwise clear
+ * the flag for devices in the path which sibliings don't set the flag.
+ *
+ * The function should only be called by block device, or network
+ * device driver for solving the deadlock problem during runtime
+ * resume:
+ * if memory allocation with GFP_KERNEL is called inside runtime
+ * resume callback of any one of its ancestors(or the block device
+ * itself), the deadlock may be triggered inside the memory
+ * allocation since it might not complete until the block device
+ * becomes active and the involed page I/O finishes. The situation
+ * is pointed out first by Alan Stern. Network device are involved
+ * in iSCSI kind of situation.
+ *
+ * The lock of dev_hotplug_mutex is held in the function for handling
+ * hotplug race because pm_runtime_set_memalloc_noio() may be called
+ * in async probe().
+ */
+void pm_runtime_set_memalloc_noio(struct device *dev, bool enable)
+{
+ static DEFINE_MUTEX(dev_hotplug_mutex);
+
+ mutex_lock(&dev_hotplug_mutex);
+ while (dev) {
+ /* hold power lock since bitfield is not SMP-safe. */
+ spin_lock_irq(&dev->power.lock);
+ dev->power.memalloc_noio_resume = enable;
+ spin_unlock_irq(&dev->power.lock);
+
+ dev = dev->parent;
+
+ /* only clear the flag for one device if all
+ * children of the device don't set the flag.
+ */
+ if (!dev || (!enable &&
+ device_for_each_child(dev, NULL,
+ dev_memalloc_noio)))
+ break;
+ }
+ mutex_unlock(&dev_hotplug_mutex);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_set_memalloc_noio);
+
/**
* rpm_check_suspend_allowed - Test whether a device may be suspended.
* @dev: Device to test.
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 03d7bb1..d104579 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -538,6 +538,7 @@ struct dev_pm_info {
unsigned int irq_safe:1;
unsigned int use_autosuspend:1;
unsigned int timer_autosuspends:1;
+ unsigned int memalloc_noio_resume:1;
enum rpm_request request;
enum rpm_status runtime_status;
int runtime_error;
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index f271860..b522b09 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -47,6 +47,8 @@ extern void pm_runtime_set_autosuspend_delay(struct device *dev, int delay);
extern unsigned long pm_runtime_autosuspend_expiration(struct device *dev);
extern void pm_runtime_update_max_time_suspended(struct device *dev,
s64 delta_ns);
+extern bool pm_runtime_get_memalloc_noio(struct device *dev);
+extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable);
static inline bool pm_children_suspended(struct device *dev)
{
@@ -149,6 +151,9 @@ static inline void pm_runtime_set_autosuspend_delay(struct device *dev,
int delay) {}
static inline unsigned long pm_runtime_autosuspend_expiration(
struct device *dev) { return 0; }
+static inline bool pm_runtime_get_memalloc_noio(struct device *dev) { return false; }
+static inline void pm_runtime_set_memalloc_noio(struct device *dev,
+ bool enable){}
#endif /* !CONFIG_PM_RUNTIME */
--
1.7.9.5
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>