pm / runtime: introduce pm_runtime_set_memalloc_noio()

Introduce the flag memalloc_noio in 'struct dev_pm_info' to help PM core
to teach mm not allocating memory with GFP_KERNEL flag for avoiding
probable deadlock.

As explained in the comment, any GFP_KERNEL allocation inside
runtime_resume() or runtime_suspend() 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 in the path recursively.

Signed-off-by: Ming Lei <ming.lei@canonical.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Oliver Neukum <oneukum@suse.de>
Cc: Jiri Kosina <jiri.kosina@suse.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Greg KH <greg@kroah.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: David Decotigny <david.decotigny@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 3148b10..cd92e1c 100644 (file)
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -124,6 +124,76 @@ unsigned long pm_runtime_autosuspend_expiration(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration);
 
+static int dev_memalloc_noio(struct device *dev, void *data)
+{
+       return dev->power.memalloc_noio;
+}
+
+/*
+ * 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 whose siblings 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/suspend:
+ *
+ *     If memory allocation with GFP_KERNEL is called inside runtime
+ *     resume/suspend 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().
+ *
+ * The function should be called between device_add() and device_del()
+ * on the affected device(block/network device).
+ */
+void pm_runtime_set_memalloc_noio(struct device *dev, bool enable)
+{
+       static DEFINE_MUTEX(dev_hotplug_mutex);
+
+       mutex_lock(&dev_hotplug_mutex);
+       for (;;) {
+               bool enabled;
+
+               /* hold power lock since bitfield is not SMP-safe. */
+               spin_lock_irq(&dev->power.lock);
+               enabled = dev->power.memalloc_noio;
+               dev->power.memalloc_noio = enable;
+               spin_unlock_irq(&dev->power.lock);
+
+               /*
+                * not need to enable ancestors any more if the device
+                * has been enabled.
+                */
+               if (enabled && enable)
+                       break;
+
+               dev = dev->parent;
+
+               /*
+                * clear flag of the parent device only if all the
+                * children don't set the flag because ancestor's
+                * flag was set by any one of the descendants.
+                */
+               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 97bcf23..e5d7230 100644 (file)
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -537,6 +537,7 @@ struct dev_pm_info {
        unsigned int            irq_safe:1;
        unsigned int            use_autosuspend:1;
        unsigned int            timer_autosuspends:1;
+       unsigned int            memalloc_noio: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 c785c21..7d7e09e 100644 (file)
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -47,6 +47,7 @@ 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 void pm_runtime_set_memalloc_noio(struct device *dev, bool enable);
 
 static inline bool pm_children_suspended(struct device *dev)
 {
@@ -156,6 +157,8 @@ 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 void pm_runtime_set_memalloc_noio(struct device *dev,
+                                               bool enable){}
 
 #endif /* !CONFIG_PM_RUNTIME */