freezer: add unsafe versions of freezable helpers for NFS

NFS calls the freezable helpers with locks held, which is unsafe
and will cause lockdep warnings when 6aa9707 "lockdep: check
that no locks held at freeze time" is reapplied (it was reverted
in dbf520a).  NFS shouldn't be doing this, but it has
long-running syscalls that must hold a lock but also shouldn't
block suspend.  Until NFS freeze handling is rewritten to use a
signal to exit out of the critical section, add new *_unsafe
versions of the helpers that will not run the lockdep test when
6aa9707 is reapplied, and call them from NFS.

In practice the likley result of holding the lock while freezing
is that a second task blocked on the lock will never freeze,
aborting suspend, but it is possible to manufacture a case using
the cgroup freezer, the lock, and the suspend freezer to create
a deadlock.  Silencing the lockdep warning here will allow
problems to be found in other drivers that may have a more
serious deadlock risk, and prevent new problems from being added.

Change-Id: Ia17d32cdd013a6517bdd5759da900970a4427170
Signed-off-by: Colin Cross <ccross@android.com>
Acked-by: Pavel Machek <pavel@ucw.cz>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

5 files changed, 46 insertions, 6 deletions

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index c1c7a9d7872..ce727047ee8 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -79,7 +79,7 @@ int nfs_wait_bit_killable(void *word)
 {
 	if (fatal_signal_pending(current))
 		return -ERESTARTSYS;
-	freezable_schedule();
+	freezable_schedule_unsafe();
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nfs_wait_bit_killable);
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 43ea96ced28..ce90eb4775c 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -33,7 +33,7 @@ nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags)
 		res = rpc_call_sync(clnt, msg, flags);
 		if (res != -EJUKEBOX)
 			break;
-		freezable_schedule_timeout_killable(NFS_JUKEBOX_RETRY_TIME);
+		freezable_schedule_timeout_killable_unsafe(NFS_JUKEBOX_RETRY_TIME);
 		res = -ERESTARTSYS;
 	} while (!fatal_signal_pending(current));
 	return res;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d7ba5616989..28241a42f36 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -268,7 +268,7 @@ static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
 		*timeout = NFS4_POLL_RETRY_MIN;
 	if (*timeout > NFS4_POLL_RETRY_MAX)
 		*timeout = NFS4_POLL_RETRY_MAX;
-	freezable_schedule_timeout_killable(*timeout);
+	freezable_schedule_timeout_killable_unsafe(*timeout);
 	if (fatal_signal_pending(current))
 		res = -ERESTARTSYS;
 	*timeout <<= 1;
@@ -4528,7 +4528,7 @@ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4
 static unsigned long
 nfs4_set_lock_task_retry(unsigned long timeout)
 {
-	freezable_schedule_timeout_killable(timeout);
+	freezable_schedule_timeout_killable_unsafe(timeout);
 	timeout <<= 1;
 	if (timeout > NFS4_LOCK_MAXTIMEOUT)
 		return NFS4_LOCK_MAXTIMEOUT;
diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index e70df40d84f..5b31e21c485 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -46,7 +46,11 @@ extern int freeze_kernel_threads(void);
 extern void thaw_processes(void);
 extern void thaw_kernel_threads(void);
 
-static inline bool try_to_freeze(void)
+/*
+ * DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION
+ * If try_to_freeze causes a lockdep warning it means the caller may deadlock
+ */
+static inline bool try_to_freeze_unsafe(void)
 {
 	might_sleep();
 	if (likely(!freezing(current)))
@@ -54,6 +58,11 @@ static inline bool try_to_freeze(void)
 	return __refrigerator(false);
 }
 
+static inline bool try_to_freeze(void)
+{
+	return try_to_freeze_unsafe();
+}
+
 extern bool freeze_task(struct task_struct *p);
 extern bool set_freezable(void);
 
@@ -115,6 +124,14 @@ static inline void freezer_count(void)
 	try_to_freeze();
 }
 
+/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */
+static inline void freezer_count_unsafe(void)
+{
+	current->flags &= ~PF_FREEZER_SKIP;
+	smp_mb();
+	try_to_freeze_unsafe();
+}
+
 /**
  * freezer_should_skip - whether to skip a task when determining frozen
  *			 state is reached
@@ -152,6 +169,14 @@ static inline bool freezer_should_skip(struct task_struct *p)
 	freezer_count();						\
 })
 
+/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */
+#define freezable_schedule_unsafe()					\
+({									\
+	freezer_do_not_count();						\
+	schedule();							\
+	freezer_count_unsafe();						\
+})
+
 /* Like schedule_timeout_killable(), but should not block the freezer. */
 #define freezable_schedule_timeout_killable(timeout)			\
 ({									\
@@ -162,6 +187,16 @@ static inline bool freezer_should_skip(struct task_struct *p)
 	__retval;							\
 })
 
+/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */
+#define freezable_schedule_timeout_killable_unsafe(timeout)		\
+({									\
+	long __retval;							\
+	freezer_do_not_count();						\
+	__retval = schedule_timeout_killable(timeout);			\
+	freezer_count_unsafe();						\
+	__retval;							\
+})
+
 /*
  * Freezer-friendly wrappers around wait_event_interruptible(),
  * wait_event_killable() and wait_event_interruptible_timeout(), originally
@@ -225,9 +260,14 @@ static inline void set_freezable(void) {}
 
 #define freezable_schedule()  schedule()
 
+#define freezable_schedule_unsafe()  schedule()
+
 #define freezable_schedule_timeout_killable(timeout)			\
 	schedule_timeout_killable(timeout)
 
+#define freezable_schedule_timeout_killable_unsafe(timeout)		\
+	schedule_timeout_killable(timeout)
+
 #define wait_event_freezable(wq, condition)				\
 		wait_event_interruptible(wq, condition)
 
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 5356b120dbf..77d251e0259 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -254,7 +254,7 @@ static int rpc_wait_bit_killable(void *word)
 {
 	if (fatal_signal_pending(current))
 		return -ERESTARTSYS;
-	freezable_schedule();
+	freezable_schedule_unsafe();
 	return 0;
 }