driver core / ACPI: Avoid device hot remove locking issues

device_hotplug_lock is held around the acpi_bus_trim() call in
acpi_scan_hot_remove() which generally removes devices (it removes
ACPI device objects at least, but it may also remove "physical"
device objects through .detach() callbacks of ACPI scan handlers).
Thus, potentially, device sysfs attributes are removed under that
lock and to remove those attributes it is necessary to hold the
s_active references of their directory entries for writing.

On the other hand, the execution of a .show() or .store() callback
from a sysfs attribute is carried out with that attribute's s_active
reference held for reading.  Consequently, if any device sysfs
attribute that may be removed from within acpi_scan_hot_remove()
through acpi_bus_trim() has a .store() or .show() callback which
acquires device_hotplug_lock, the execution of that callback may
deadlock with the removal of the attribute.  [Unfortunately, the
"online" device attribute of CPUs and memory blocks is one of them.]

To avoid such deadlocks, make all of the sysfs attribute callbacks
that need to lock device hotplug, for example store_online(), use
a special function, lock_device_hotplug_sysfs(), to lock device
hotplug and return the result of that function immediately if it is
not zero.  This will cause the s_active reference of the directory
entry in question to be released and the syscall to be restarted
if device_hotplug_lock cannot be acquired.

[show_online() actually doesn't need to lock device hotplug, but
it is useful to serialize it with respect to device_offline() and
device_online() for the same device (in case user space attempts to
run them concurrently) which can be done with the help of
device_lock().]

Reported-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Reported-and-tested-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Toshi Kani <toshi.kani@hp.com>

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 8856d74545d988271986f9152380ba3f615f9f8a..ac419a15fcd459b3ac94bfb7bb4c5da68916a1ae 100644 (file)
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -49,6 +49,28 @@ static struct kobject *dev_kobj;
 struct kobject *sysfs_dev_char_kobj;
 struct kobject *sysfs_dev_block_kobj;
 
+static DEFINE_MUTEX(device_hotplug_lock);
+
+void lock_device_hotplug(void)
+{
+       mutex_lock(&device_hotplug_lock);
+}
+
+void unlock_device_hotplug(void)
+{
+       mutex_unlock(&device_hotplug_lock);
+}
+
+int lock_device_hotplug_sysfs(void)
+{
+       if (mutex_trylock(&device_hotplug_lock))
+               return 0;
+
+       /* Avoid busy looping (5 ms of sleep should do). */
+       msleep(5);
+       return restart_syscall();
+}
+
 #ifdef CONFIG_BLOCK
 static inline int device_is_not_partition(struct device *dev)
 {
@@ -408,9 +430,9 @@ static ssize_t show_online(struct device *dev, struct device_attribute *attr,
 {
        bool val;
 
-       lock_device_hotplug();
+       device_lock(dev);
        val = !dev->offline;
-       unlock_device_hotplug();
+       device_unlock(dev);
        return sprintf(buf, "%u\n", val);
 }
 
@@ -424,7 +446,10 @@ static ssize_t store_online(struct device *dev, struct device_attribute *attr,
        if (ret < 0)
                return ret;
 
-       lock_device_hotplug();
+       ret = lock_device_hotplug_sysfs();
+       if (ret)
+               return ret;
+
        ret = val ? device_online(dev) : device_offline(dev);
        unlock_device_hotplug();
        return ret < 0 ? ret : count;
@@ -1479,18 +1504,6 @@ EXPORT_SYMBOL_GPL(put_device);
 EXPORT_SYMBOL_GPL(device_create_file);
 EXPORT_SYMBOL_GPL(device_remove_file);
 
-static DEFINE_MUTEX(device_hotplug_lock);
-
-void lock_device_hotplug(void)
-{
-       mutex_lock(&device_hotplug_lock);
-}
-
-void unlock_device_hotplug(void)
-{
-       mutex_unlock(&device_hotplug_lock);
-}
-
 static int device_check_offline(struct device *dev, void *not_used)
 {
        int ret;

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 2b7813ec6d02f31e842d181b61b01fa6be6f4b9d..6f4c99ff1ce75a83adf6212db2f83e8fbcd3516a 100644 (file)
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -351,7 +351,9 @@ store_mem_state(struct device *dev,
 
        mem = container_of(dev, struct memory_block, dev);
 
-       lock_device_hotplug();
+       ret = lock_device_hotplug_sysfs();
+       if (ret)
+               return ret;
 
        if (!strncmp(buf, "online_kernel", min_t(int, count, 13))) {
                offline = false;

diff --git a/include/linux/device.h b/include/linux/device.h
index 22b546a585916b2c8b5754c3f321130c7231d1fe..545a04285120449b9566f2860f11e44b76d54561 100644 (file)
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -895,6 +895,7 @@ static inline bool device_supports_offline(struct device *dev)
 
 extern void lock_device_hotplug(void);
 extern void unlock_device_hotplug(void);
+extern int lock_device_hotplug_sysfs(void);
 extern int device_offline(struct device *dev);
 extern int device_online(struct device *dev);
 /*