PM / Hibernate: Freeze kernel threads after preallocating memory

There is a problem with the current ordering of hibernate code which
leads to deadlocks in some filesystems' memory shrinkers.  Namely,
some filesystems use freezable kernel threads that are inactive when
the hibernate memory preallocation is carried out.  Those same
filesystems use memory shrinkers that may be triggered by the
hibernate memory preallocation.  If those memory shrinkers wait for
the frozen kernel threads, the hibernate process deadlocks (this
happens with XFS, for one example).

Apparently, it is not technically viable to redesign the filesystems
in question to avoid the situation described above, so the only
possible solution of this issue is to defer the freezing of kernel
threads until the hibernate memory preallocation is done, which is
implemented by this change.

Unfortunately, this requires the memory preallocation to be done
before the "prepare" stage of device freeze, so after this change the
only way drivers can allocate additional memory for their freeze
routines in a clean way is to use PM notifiers.

Reported-by: Christoph <cr2005@u-club.de>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>

5 files changed, 33 insertions, 20 deletions

diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index 29b7a9817f5a..646a89e0c07d 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -281,10 +281,6 @@ When the system goes into the standby or memory sleep state, the phases are:
 	time.)  Unlike the other suspend-related phases, during the prepare
 	phase the device tree is traversed top-down.
 
-	In addition to that, if device drivers need to allocate additional
-	memory to be able to hadle device suspend correctly, that should be
-	done in the prepare phase.
-
 	After the prepare callback method returns, no new children may be
 	registered below the device.  The method may also prepare the device or
 	driver in some way for the upcoming system power transition (for
diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index 1effc8b56b4e..aa56cf31f7ff 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -49,6 +49,7 @@ extern int thaw_process(struct task_struct *p);
 
 extern void refrigerator(void);
 extern int freeze_processes(void);
+extern int freeze_kernel_threads(void);
 extern void thaw_processes(void);
 
 static inline int try_to_freeze(void)
@@ -171,7 +172,8 @@ static inline void clear_freeze_flag(struct task_struct *p) {}
 static inline int thaw_process(struct task_struct *p) { return 1; }
 
 static inline void refrigerator(void) {}
-static inline int freeze_processes(void) { BUG(); return 0; }
+static inline int freeze_processes(void) { return -ENOSYS; }
+static inline int freeze_kernel_threads(void) { return -ENOSYS; }
 static inline void thaw_processes(void) {}
 
 static inline int try_to_freeze(void) { return 0; }
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 8f7b1db1ece1..3a20466015f8 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -334,13 +334,17 @@ int hibernation_snapshot(int platform_mode)
 	if (error)
 		goto Close;
 
-	error = dpm_prepare(PMSG_FREEZE);
-	if (error)
-		goto Complete_devices;
-
 	/* Preallocate image memory before shutting down devices. */
 	error = hibernate_preallocate_memory();
 	if (error)
+		goto Close;
+
+	error = freeze_kernel_threads();
+	if (error)
+		goto Close;
+
+	error = dpm_prepare(PMSG_FREEZE);
+	if (error)
 		goto Complete_devices;
 
 	suspend_console();
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 9a00a0a26280..e6206397ce67 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -228,7 +228,8 @@ extern int pm_test_level;
 #ifdef CONFIG_SUSPEND_FREEZER
 static inline int suspend_freeze_processes(void)
 {
-	return freeze_processes();
+	int error = freeze_processes();
+	return error ? : freeze_kernel_threads();
 }
 
 static inline void suspend_thaw_processes(void)
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 0cf3a27a6c9d..addbbe5531bc 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -135,7 +135,7 @@ static int try_to_freeze_tasks(bool sig_only)
 }
 
 /**
- *	freeze_processes - tell processes to enter the refrigerator
+ * freeze_processes - Signal user space processes to enter the refrigerator.
  */
 int freeze_processes(void)
 {
@@ -143,20 +143,30 @@ int freeze_processes(void)
 
 	printk("Freezing user space processes ... ");
 	error = try_to_freeze_tasks(true);
-	if (error)
-		goto Exit;
-	printk("done.\n");
+	if (!error) {
+		printk("done.");
+		oom_killer_disable();
+	}
+	printk("\n");
+	BUG_ON(in_atomic());
+
+	return error;
+}
+
+/**
+ * freeze_kernel_threads - Make freezable kernel threads go to the refrigerator.
+ */
+int freeze_kernel_threads(void)
+{
+	int error;
 
 	printk("Freezing remaining freezable tasks ... ");
 	error = try_to_freeze_tasks(false);
-	if (error)
-		goto Exit;
-	printk("done.");
+	if (!error)
+		printk("done.");
 
-	oom_killer_disable();
- Exit:
-	BUG_ON(in_atomic());
 	printk("\n");
+	BUG_ON(in_atomic());
 
 	return error;
 }