Merge branch 'locking-rwsem-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull support for killable rwsems from Ingo Molnar:
 "This, by Michal Hocko, implements down_write_killable().

  The main usecase will be to update mm_sem usage sites to use this new
  API, to allow the mm-reaper introduced in commit aac453635549 ("mm,
  oom: introduce oom reaper") to tear down oom victim address spaces
  asynchronously with minimum latencies and without deadlock worries"

[ The vfs will want it too as the inode lock is changed from a mutex to
  a rwsem due to the parallel lookup and readdir updates ]

* 'locking-rwsem-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  locking/rwsem: Fix comment on register clobbering
  locking/rwsem: Fix down_write_killable()
  locking/rwsem, x86: Add frame annotation for call_rwsem_down_write_failed_killable()
  locking/rwsem: Provide down_write_killable()
  locking/rwsem, x86: Provide __down_write_killable()
  locking/rwsem, s390: Provide __down_write_killable()
  locking/rwsem, ia64: Provide __down_write_killable()
  locking/rwsem, alpha: Provide __down_write_killable()
  locking/rwsem: Introduce basis for down_write_killable()
  locking/rwsem, sparc: Drop superfluous arch specific implementation
  locking/rwsem, sh: Drop superfluous arch specific implementation
  locking/rwsem, xtensa: Drop superfluous arch specific implementation
  locking/rwsem: Drop explicit memory barriers
  locking/rwsem: Get rid of __down_write_nested()

11 files changed, 92 insertions, 414 deletions

diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h
index a83bbea62c67..0131a7058778 100644
--- a/arch/alpha/include/asm/rwsem.h
+++ b/arch/alpha/include/asm/rwsem.h
@@ -63,7 +63,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 	return res >= 0 ? 1 : 0;
 }
 
-static inline void __down_write(struct rw_semaphore *sem)
+static inline long ___down_write(struct rw_semaphore *sem)
 {
 	long oldcount;
 #ifndef	CONFIG_SMP
@@ -83,10 +83,24 @@ static inline void __down_write(struct rw_semaphore *sem)
 	:"=&r" (oldcount), "=m" (sem->count), "=&r" (temp)
 	:"Ir" (RWSEM_ACTIVE_WRITE_BIAS), "m" (sem->count) : "memory");
 #endif
-	if (unlikely(oldcount))
+	return oldcount;
+}
+
+static inline void __down_write(struct rw_semaphore *sem)
+{
+	if (unlikely(___down_write(sem)))
 		rwsem_down_write_failed(sem);
 }
 
+static inline int __down_write_killable(struct rw_semaphore *sem)
+{
+	if (unlikely(___down_write(sem)))
+		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
+			return -EINTR;
+
+	return 0;
+}
+
 /*
  * trylock for writing -- returns 1 if successful, 0 if contention
  */
diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
index ce112472bdd6..8b23e070b844 100644
--- a/arch/ia64/include/asm/rwsem.h
+++ b/arch/ia64/include/asm/rwsem.h
@@ -49,8 +49,8 @@ __down_read (struct rw_semaphore *sem)
 /*
  * lock for writing
  */
-static inline void
-__down_write (struct rw_semaphore *sem)
+static inline long
+___down_write (struct rw_semaphore *sem)
 {
 	long old, new;
 
@@ -59,10 +59,26 @@ __down_write (struct rw_semaphore *sem)
 		new = old + RWSEM_ACTIVE_WRITE_BIAS;
 	} while (cmpxchg_acq(&sem->count, old, new) != old);
 
-	if (old != 0)
+	return old;
+}
+
+static inline void
+__down_write (struct rw_semaphore *sem)
+{
+	if (___down_write(sem))
 		rwsem_down_write_failed(sem);
 }
 
+static inline int
+__down_write_killable (struct rw_semaphore *sem)
+{
+	if (___down_write(sem))
+		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
+			return -EINTR;
+
+	return 0;
+}
+
 /*
  * unlock after reading
  */
diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h
index fead491dfc28..c75e4471e618 100644
--- a/arch/s390/include/asm/rwsem.h
+++ b/arch/s390/include/asm/rwsem.h
@@ -90,7 +90,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 /*
  * lock for writing
  */
-static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
+static inline long ___down_write(struct rw_semaphore *sem)
 {
 	signed long old, new, tmp;
 
@@ -104,13 +104,23 @@ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
 		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
 		: "Q" (sem->count), "m" (tmp)
 		: "cc", "memory");
-	if (old != 0)
-		rwsem_down_write_failed(sem);
+
+	return old;
 }
 
 static inline void __down_write(struct rw_semaphore *sem)
 {
-	__down_write_nested(sem, 0);
+	if (___down_write(sem))
+		rwsem_down_write_failed(sem);
+}
+
+static inline int __down_write_killable(struct rw_semaphore *sem)
+{
+	if (___down_write(sem))
+		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
+			return -EINTR;
+
+	return 0;
 }
 
 /*
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index a319745a7b63..751c3373a92c 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -26,6 +26,7 @@ generic-y += percpu.h
 generic-y += poll.h
 generic-y += preempt.h
 generic-y += resource.h
+generic-y += rwsem.h
 generic-y += sembuf.h
 generic-y += serial.h
 generic-y += shmbuf.h
diff --git a/arch/sh/include/asm/rwsem.h b/arch/sh/include/asm/rwsem.h
deleted file mode 100644
index edab57265293..000000000000
--- a/arch/sh/include/asm/rwsem.h
+++ /dev/null
@@ -1,132 +0,0 @@
-/*
- * include/asm-sh/rwsem.h: R/W semaphores for SH using the stuff
- * in lib/rwsem.c.
- */
-
-#ifndef _ASM_SH_RWSEM_H
-#define _ASM_SH_RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
-#endif
-
-#ifdef __KERNEL__
-
-#define RWSEM_UNLOCKED_VALUE		0x00000000
-#define RWSEM_ACTIVE_BIAS		0x00000001
-#define RWSEM_ACTIVE_MASK		0x0000ffff
-#define RWSEM_WAITING_BIAS		(-0x00010000)
-#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-/*
- * lock for reading
- */
-static inline void __down_read(struct rw_semaphore *sem)
-{
-	if (atomic_inc_return((atomic_t *)(&sem->count)) > 0)
-		smp_wmb();
-	else
-		rwsem_down_read_failed(sem);
-}
-
-static inline int __down_read_trylock(struct rw_semaphore *sem)
-{
-	int tmp;
-
-	while ((tmp = sem->count) >= 0) {
-		if (tmp == cmpxchg(&sem->count, tmp,
-				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
-			smp_wmb();
-			return 1;
-		}
-	}
-	return 0;
-}
-
-/*
- * lock for writing
- */
-static inline void __down_write(struct rw_semaphore *sem)
-{
-	int tmp;
-
-	tmp = atomic_add_return(RWSEM_ACTIVE_WRITE_BIAS,
-				(atomic_t *)(&sem->count));
-	if (tmp == RWSEM_ACTIVE_WRITE_BIAS)
-		smp_wmb();
-	else
-		rwsem_down_write_failed(sem);
-}
-
-static inline int __down_write_trylock(struct rw_semaphore *sem)
-{
-	int tmp;
-
-	tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
-		      RWSEM_ACTIVE_WRITE_BIAS);
-	smp_wmb();
-	return tmp == RWSEM_UNLOCKED_VALUE;
-}
-
-/*
- * unlock after reading
- */
-static inline void __up_read(struct rw_semaphore *sem)
-{
-	int tmp;
-
-	smp_wmb();
-	tmp = atomic_dec_return((atomic_t *)(&sem->count));
-	if (tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0)
-		rwsem_wake(sem);
-}
-
-/*
- * unlock after writing
- */
-static inline void __up_write(struct rw_semaphore *sem)
-{
-	smp_wmb();
-	if (atomic_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
-			      (atomic_t *)(&sem->count)) < 0)
-		rwsem_wake(sem);
-}
-
-/*
- * implement atomic add functionality
- */
-static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
-{
-	atomic_add(delta, (atomic_t *)(&sem->count));
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
-	int tmp;
-
-	smp_wmb();
-	tmp = atomic_add_return(-RWSEM_WAITING_BIAS, (atomic_t *)(&sem->count));
-	if (tmp < 0)
-		rwsem_downgrade_wake(sem);
-}
-
-static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
-{
-	__down_write(sem);
-}
-
-/*
- * implement exchange and add functionality
- */
-static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
-{
-	smp_mb();
-	return atomic_add_return(delta, (atomic_t *)(&sem->count));
-}
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_SH_RWSEM_H */
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index e928618838bc..6024c26c0585 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -16,6 +16,7 @@ generic-y += mm-arch-hooks.h
 generic-y += module.h
 generic-y += mutex.h
 generic-y += preempt.h
+generic-y += rwsem.h
 generic-y += serial.h
 generic-y += trace_clock.h
 generic-y += types.h
diff --git a/arch/sparc/include/asm/rwsem.h b/arch/sparc/include/asm/rwsem.h
deleted file mode 100644
index 069bf4d663a1..000000000000
--- a/arch/sparc/include/asm/rwsem.h
+++ /dev/null
@@ -1,124 +0,0 @@
-/*
- * rwsem.h: R/W semaphores implemented using CAS
- *
- * Written by David S. Miller (davem@redhat.com), 2001.
- * Derived from asm-i386/rwsem.h
- */
-#ifndef _SPARC64_RWSEM_H
-#define _SPARC64_RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
-#endif
-
-#ifdef __KERNEL__
-
-#define RWSEM_UNLOCKED_VALUE		0x00000000L
-#define RWSEM_ACTIVE_BIAS		0x00000001L
-#define RWSEM_ACTIVE_MASK		0xffffffffL
-#define RWSEM_WAITING_BIAS		(-RWSEM_ACTIVE_MASK-1)
-#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-/*
- * lock for reading
- */
-static inline void __down_read(struct rw_semaphore *sem)
-{
-	if (unlikely(atomic64_inc_return((atomic64_t *)(&sem->count)) <= 0L))
-		rwsem_down_read_failed(sem);
-}
-
-static inline int __down_read_trylock(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	while ((tmp = sem->count) >= 0L) {
-		if (tmp == cmpxchg(&sem->count, tmp,
-				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
-			return 1;
-		}
-	}
-	return 0;
-}
-
-/*
- * lock for writing
- */
-static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
-{
-	long tmp;
-
-	tmp = atomic64_add_return(RWSEM_ACTIVE_WRITE_BIAS,
-				  (atomic64_t *)(&sem->count));
-	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
-		rwsem_down_write_failed(sem);
-}
-
-static inline void __down_write(struct rw_semaphore *sem)
-{
-	__down_write_nested(sem, 0);
-}
-
-static inline int __down_write_trylock(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
-		      RWSEM_ACTIVE_WRITE_BIAS);
-	return tmp == RWSEM_UNLOCKED_VALUE;
-}
-
-/*
- * unlock after reading
- */
-static inline void __up_read(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = atomic64_dec_return((atomic64_t *)(&sem->count));
-	if (unlikely(tmp < -1L && (tmp & RWSEM_ACTIVE_MASK) == 0L))
-		rwsem_wake(sem);
-}
-
-/*
- * unlock after writing
- */
-static inline void __up_write(struct rw_semaphore *sem)
-{
-	if (unlikely(atomic64_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
-					 (atomic64_t *)(&sem->count)) < 0L))
-		rwsem_wake(sem);
-}
-
-/*
- * implement atomic add functionality
- */
-static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
-{
-	atomic64_add(delta, (atomic64_t *)(&sem->count));
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = atomic64_add_return(-RWSEM_WAITING_BIAS, (atomic64_t *)(&sem->count));
-	if (tmp < 0L)
-		rwsem_downgrade_wake(sem);
-}
-
-/*
- * implement exchange and add functionality
- */
-static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
-{
-	return atomic64_add_return(delta, (atomic64_t *)(&sem->count));
-}
-
-#endif /* __KERNEL__ */
-
-#endif /* _SPARC64_RWSEM_H */
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index ceec86eb68e9..453744c1d347 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -99,26 +99,36 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 /*
  * lock for writing
  */
-static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
+#define ____down_write(sem, slow_path)			\
+({							\
+	long tmp;					\
+	struct rw_semaphore* ret;			\
+	asm volatile("# beginning down_write\n\t"	\
+		     LOCK_PREFIX "  xadd      %1,(%3)\n\t"	\
+		     /* adds 0xffff0001, returns the old value */ \
+		     "  test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \
+		     /* was the active mask 0 before? */\
+		     "  jz        1f\n"			\
+		     "  call " slow_path "\n"		\
+		     "1:\n"				\
+		     "# ending down_write"		\
+		     : "+m" (sem->count), "=d" (tmp), "=a" (ret)	\
+		     : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \
+		     : "memory", "cc");			\
+	ret;						\
+})
+
+static inline void __down_write(struct rw_semaphore *sem)
 {
-	long tmp;
-	asm volatile("# beginning down_write\n\t"
-		     LOCK_PREFIX "  xadd      %1,(%2)\n\t"
-		     /* adds 0xffff0001, returns the old value */
-		     "  test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t"
-		     /* was the active mask 0 before? */
-		     "  jz        1f\n"
-		     "  call call_rwsem_down_write_failed\n"
-		     "1:\n"
-		     "# ending down_write"
-		     : "+m" (sem->count), "=d" (tmp)
-		     : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS)
-		     : "memory", "cc");
+	____down_write(sem, "call_rwsem_down_write_failed");
 }
 
-static inline void __down_write(struct rw_semaphore *sem)
+static inline int __down_write_killable(struct rw_semaphore *sem)
 {
-	__down_write_nested(sem, 0);
+	if (IS_ERR(____down_write(sem, "call_rwsem_down_write_failed_killable")))
+		return -EINTR;
+
+	return 0;
 }
 
 /*
diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S
index be110efa0096..bf2c6074efd2 100644
--- a/arch/x86/lib/rwsem.S
+++ b/arch/x86/lib/rwsem.S
@@ -29,8 +29,10 @@
  * there is contention on the semaphore.
  *
  * %eax contains the semaphore pointer on entry. Save the C-clobbered
- * registers (%eax, %edx and %ecx) except %eax whish is either a return
- * value or just clobbered..
+ * registers (%eax, %edx and %ecx) except %eax which is either a return
+ * value or just gets clobbered. Same is true for %edx so make sure GCC
+ * reloads it after the slow path, by making it hold a temporary, for
+ * example see ____down_write().
  */
 
 #define save_common_regs \
@@ -106,6 +108,16 @@ ENTRY(call_rwsem_down_write_failed)
 	ret
 ENDPROC(call_rwsem_down_write_failed)
 
+ENTRY(call_rwsem_down_write_failed_killable)
+	FRAME_BEGIN
+	save_common_regs
+	movq %rax,%rdi
+	call rwsem_down_write_failed_killable
+	restore_common_regs
+	FRAME_END
+	ret
+ENDPROC(call_rwsem_down_write_failed_killable)
+
 ENTRY(call_rwsem_wake)
 	FRAME_BEGIN
 	/* do nothing if still outstanding active readers */
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index b56855a1382a..28cf4c5d65ef 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -22,6 +22,7 @@ generic-y += mm-arch-hooks.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += resource.h
+generic-y += rwsem.h
 generic-y += sections.h
 generic-y += siginfo.h
 generic-y += statfs.h
diff --git a/arch/xtensa/include/asm/rwsem.h b/arch/xtensa/include/asm/rwsem.h
deleted file mode 100644
index 249619e7e7f2..000000000000
--- a/arch/xtensa/include/asm/rwsem.h
+++ /dev/null
@@ -1,131 +0,0 @@
-/*
- * include/asm-xtensa/rwsem.h
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Largely copied from include/asm-ppc/rwsem.h
- *
- * Copyright (C) 2001 - 2005 Tensilica Inc.
- */
-
-#ifndef _XTENSA_RWSEM_H
-#define _XTENSA_RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
-#endif
-
-#define RWSEM_UNLOCKED_VALUE		0x00000000
-#define RWSEM_ACTIVE_BIAS		0x00000001
-#define RWSEM_ACTIVE_MASK		0x0000ffff
-#define RWSEM_WAITING_BIAS		(-0x00010000)
-#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-/*
- * lock for reading
- */
-static inline void __down_read(struct rw_semaphore *sem)
-{
-	if (atomic_add_return(1,(atomic_t *)(&sem->count)) > 0)
-		smp_wmb();
-	else
-		rwsem_down_read_failed(sem);
-}
-
-static inline int __down_read_trylock(struct rw_semaphore *sem)
-{
-	int tmp;
-
-	while ((tmp = sem->count) >= 0) {
-		if (tmp == cmpxchg(&sem->count, tmp,
-				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
-			smp_wmb();
-			return 1;
-		}
-	}
-	return 0;
-}
-
-/*
- * lock for writing
- */
-static inline void __down_write(struct rw_semaphore *sem)
-{
-	int tmp;
-
-	tmp = atomic_add_return(RWSEM_ACTIVE_WRITE_BIAS,
-				(atomic_t *)(&sem->count));
-	if (tmp == RWSEM_ACTIVE_WRITE_BIAS)
-		smp_wmb();
-	else
-		rwsem_down_write_failed(sem);
-}
-
-static inline int __down_write_trylock(struct rw_semaphore *sem)
-{
-	int tmp;
-
-	tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
-		      RWSEM_ACTIVE_WRITE_BIAS);
-	smp_wmb();
-	return tmp == RWSEM_UNLOCKED_VALUE;
-}
-
-/*
- * unlock after reading
- */
-static inline void __up_read(struct rw_semaphore *sem)
-{
-	int tmp;
-
-	smp_wmb();
-	tmp = atomic_sub_return(1,(atomic_t *)(&sem->count));
-	if (tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0)
-		rwsem_wake(sem);
-}
-
-/*
- * unlock after writing
- */
-static inline void __up_write(struct rw_semaphore *sem)
-{
-	smp_wmb();
-	if (atomic_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
-			      (atomic_t *)(&sem->count)) < 0)
-		rwsem_wake(sem);
-}
-
-/*
- * implement atomic add functionality
- */
-static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
-{
-	atomic_add(delta, (atomic_t *)(&sem->count));
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
-	int tmp;
-
-	smp_wmb();
-	tmp = atomic_add_return(-RWSEM_WAITING_BIAS, (atomic_t *)(&sem->count));
-	if (tmp < 0)
-		rwsem_downgrade_wake(sem);
-}
-
-/*
- * implement exchange and add functionality
- */
-static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
-{
-	smp_mb();
-	return atomic_add_return(delta, (atomic_t *)(&sem->count));
-}
-
-#endif	/* _XTENSA_RWSEM_H */