64-bit ppc rwsem (was: Re: [GIT] Sparc)

Subsystems: linux for powerpc (32-bit and 64-bit), the rest

19 messages, 5 authors, 2010-08-24 · open the first message on its own page

64-bit ppc rwsem (was: Re: [GIT] Sparc)

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: 2010-08-18 04:39:28

On Tue, 2010-08-17 at 19:14 -0700, David Miller wrote:
quoted
I merged your pull request, but you've got some fixing up to do,
methinks. I also really think you need to make your rwsem's use 64-bit
values on sparc64, because otherwise you can overflow the mmap_sem by
having more than 65536 threads doing page-faults (on 32-bit, having
more than 2**16 threads in one process is unlikely to work for other
reasons, like just pure stack usage, so we don't really care about the
32-bit case)
I have a patch to do this already, just need to test it.

You should bug the powerpc folks too :-)
32K threads :-) you guys are nuts !

Here's an untested patch for the folks on linuxppc-dev to look at, I'll
review my own stuff & test tomorrow.

Cheers,
Ben.

powerpc: Make rwsem use "long" types on 64-bit platforms

This should avoid overflow of the mmap_sem when playing with insane
number of threads.

Not-signed-off-by-yet.
diff --git a/arch/powerpc/include/asm/rwsem.h b/arch/powerpc/include/asm/rwsem.h
index 24cd928..ca64a98 100644
--- a/arch/powerpc/include/asm/rwsem.h
+++ b/arch/powerpc/include/asm/rwsem.h
@@ -21,15 +21,20 @@
 /*
  * the semaphore definition
  */
-struct rw_semaphore {
-	/* XXX this should be able to be an atomic_t  -- paulus */
-	signed int		count;
-#define RWSEM_UNLOCKED_VALUE		0x00000000
-#define RWSEM_ACTIVE_BIAS		0x00000001
-#define RWSEM_ACTIVE_MASK		0x0000ffff
-#define RWSEM_WAITING_BIAS		(-0x00010000)
+#ifdef CONFIG_PPC64
+# define RWSEM_ACTIVE_MASK		0xffffffffL
+#else
+# define RWSEM_ACTIVE_MASK		0x0000ffffL
+#endif
+
+#define RWSEM_UNLOCKED_VALUE		0x00000000L
+#define RWSEM_ACTIVE_BIAS		0x00000001L
+#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)
+
+struct rw_semaphore {
+	atomic_long_t		count;
 	spinlock_t		wait_lock;
 	struct list_head	wait_list;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -43,9 +48,13 @@ struct rw_semaphore {
 # define __RWSEM_DEP_MAP_INIT(lockname)
 #endif
 
-#define __RWSEM_INITIALIZER(name) \
-	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
-	  LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
+#define __RWSEM_INITIALIZER(name)				\
+{								\
+	ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE),			\
+	__SPIN_LOCK_UNLOCKED((name).wait_lock),			\
+	LIST_HEAD_INIT((name).wait_list)			\
+	__RWSEM_DEP_MAP_INIT(name)				\
+}
 
 #define DECLARE_RWSEM(name)		\
 	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
@@ -70,16 +79,16 @@ extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
  */
 static inline void __down_read(struct rw_semaphore *sem)
 {
-	if (unlikely(atomic_inc_return((atomic_t *)(&sem->count)) <= 0))
+	if (unlikely(atomic_long_inc_return(&sem->count) <= 0))
 		rwsem_down_read_failed(sem);
 }
 
 static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
-	int tmp;
+	long tmp;
 
-	while ((tmp = sem->count) >= 0) {
-		if (tmp == cmpxchg(&sem->count, tmp,
+	while ((tmp = atomic_long_read(&sem->count)) >= 0) {
+		if (tmp == cmpxchg((long *)&sem->count, tmp,
 				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
 			return 1;
 		}
@@ -92,10 +101,10 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
  */
 static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
 {
-	int tmp;
+	long tmp;
 
-	tmp = atomic_add_return(RWSEM_ACTIVE_WRITE_BIAS,
-				(atomic_t *)(&sem->count));
+	tmp = atomic_long_add_return(RWSEM_ACTIVE_WRITE_BIAS,
+				     &sem->count);
 	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
 		rwsem_down_write_failed(sem);
 }
@@ -107,9 +116,9 @@ static inline void __down_write(struct rw_semaphore *sem)
 
 static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
-	int tmp;
+	long tmp;
 
-	tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
+	tmp = cmpxchg((long *)&sem->count, RWSEM_UNLOCKED_VALUE,
 		      RWSEM_ACTIVE_WRITE_BIAS);
 	return tmp == RWSEM_UNLOCKED_VALUE;
 }
@@ -119,9 +128,9 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
  */
 static inline void __up_read(struct rw_semaphore *sem)
 {
-	int tmp;
+	long tmp;
 
-	tmp = atomic_dec_return((atomic_t *)(&sem->count));
+	tmp = atomic_long_dec_return(&sem->count);
 	if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
 		rwsem_wake(sem);
 }
@@ -131,17 +140,17 @@ static inline void __up_read(struct rw_semaphore *sem)
  */
 static inline void __up_write(struct rw_semaphore *sem)
 {
-	if (unlikely(atomic_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
-			      (atomic_t *)(&sem->count)) < 0))
+	if (unlikely(atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
+					    &sem->count) < 0))
 		rwsem_wake(sem);
 }
 
 /*
  * implement atomic add functionality
  */
-static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
+static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
 {
-	atomic_add(delta, (atomic_t *)(&sem->count));
+	atomic_long_add(delta, &sem->count);
 }
 
 /*
@@ -149,9 +158,9 @@ static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
  */
 static inline void __downgrade_write(struct rw_semaphore *sem)
 {
-	int tmp;
+	long tmp;
 
-	tmp = atomic_add_return(-RWSEM_WAITING_BIAS, (atomic_t *)(&sem->count));
+	tmp = atomic_long_add_return(-RWSEM_WAITING_BIAS, &sem->count);
 	if (tmp < 0)
 		rwsem_downgrade_wake(sem);
 }
@@ -159,14 +168,14 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 /*
  * implement exchange and add functionality
  */
-static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
+static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
 {
-	return atomic_add_return(delta, (atomic_t *)(&sem->count));
+	return atomic_long_add_return(delta, &sem->count);
 }
 
 static inline int rwsem_is_locked(struct rw_semaphore *sem)
 {
-	return (sem->count != 0);
+	return atomic_long_read(&sem->count) != 0;
 }
 
 #endif	/* __KERNEL__ */

Re: 64-bit ppc rwsem (was: Re: [GIT] Sparc)

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: 2010-08-18 05:03:46

On Wed, 2010-08-18 at 14:38 +1000, Benjamin Herrenschmidt wrote:
Here's an untested patch for the folks on linuxppc-dev to look at,
I'll
review my own stuff & test tomorrow. 
Allright, gcc's being a pain, and atomics are a struct so we can't that
easily assign.

I tried various tricks but so far they didn't work. I'll have another
look tomorrow, but I may end up having to keep all the crap typecasts.

Cheers,
Ben.

Re: 64-bit ppc rwsem

From: David Miller <davem@davemloft.net>
Date: 2010-08-18 05:28:03

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Wed, 18 Aug 2010 15:03:23 +1000
I tried various tricks but so far they didn't work. I'll have another
look tomorrow, but I may end up having to keep all the crap typecasts.
The casts are pretty much unavoidable.

Here's what I'm going to end up using on sparc64:

--------------------
sparc64: Make rwsems 64-bit.

Basically tip-off the powerpc code, use a 64-bit type and atomic64_t
interfaces for the implementation.

This gets us off of the by-hand asm code I wrote, which frankly I
think probably ruins I-cache hit rates.

The idea was the keep the call chains less deep, but anything taking
the rw-semaphores probably is also calling other stuff and therefore
already has allocated a stack-frame.  So no real stack frame savings
ever.

Ben H. has posted patches to make powerpc use 64-bit too and with some
abstractions we can probably use a shared header file somewhere.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/include/asm/rwsem-const.h |   12 ---
 arch/sparc/include/asm/rwsem.h       |  120 +++++++++++++++++++++----
 arch/sparc/lib/Makefile              |    2 +-
 arch/sparc/lib/rwsem_64.S            |  163 ----------------------------------
 4 files changed, 104 insertions(+), 193 deletions(-)
 delete mode 100644 arch/sparc/include/asm/rwsem-const.h
 delete mode 100644 arch/sparc/lib/rwsem_64.S
diff --git a/arch/sparc/include/asm/rwsem-const.h b/arch/sparc/include/asm/rwsem-const.h
deleted file mode 100644
index e4c61a1..0000000
--- a/arch/sparc/include/asm/rwsem-const.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* rwsem-const.h: RW semaphore counter constants.  */
-#ifndef _SPARC64_RWSEM_CONST_H
-#define _SPARC64_RWSEM_CONST_H
-
-#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)
-
-#endif /* _SPARC64_RWSEM_CONST_H */
diff --git a/arch/sparc/include/asm/rwsem.h b/arch/sparc/include/asm/rwsem.h
index 6e56210..a2b4302 100644
--- a/arch/sparc/include/asm/rwsem.h
+++ b/arch/sparc/include/asm/rwsem.h
@@ -15,16 +15,21 @@
 
 #include <linux/list.h>
 #include <linux/spinlock.h>
-#include <asm/rwsem-const.h>
 
 struct rwsem_waiter;
 
 struct rw_semaphore {
-	signed int count;
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
+	signed long			count;
+#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)
+	spinlock_t			wait_lock;
+	struct list_head		wait_list;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
+	struct lockdep_map		dep_map;
 #endif
 };
 
@@ -41,6 +46,11 @@ struct rw_semaphore {
 #define DECLARE_RWSEM(name) \
 	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
 
+extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
+
 extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
 			 struct lock_class_key *key);
 
@@ -51,27 +61,103 @@ do {								\
 	__init_rwsem((sem), #sem, &__key);			\
 } while (0)
 
-extern void __down_read(struct rw_semaphore *sem);
-extern int __down_read_trylock(struct rw_semaphore *sem);
-extern void __down_write(struct rw_semaphore *sem);
-extern int __down_write_trylock(struct rw_semaphore *sem);
-extern void __up_read(struct rw_semaphore *sem);
-extern void __up_write(struct rw_semaphore *sem);
-extern void __downgrade_write(struct rw_semaphore *sem);
+/*
+ * 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)
 {
-	__down_write(sem);
+	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 int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
+static inline void __down_write(struct rw_semaphore *sem)
 {
-	return atomic_add_return(delta, (atomic_t *)(&sem->count));
+	__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;
 }
 
-static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
+/*
+ * 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)
 {
-	atomic_add(delta, (atomic_t *)(&sem->count));
+	return atomic64_add_return(delta, (atomic64_t *)(&sem->count));
 }
 
 static inline int rwsem_is_locked(struct rw_semaphore *sem)
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index c4b5e03..fa4c3ea 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -15,7 +15,7 @@ lib-$(CONFIG_SPARC32) += divdi3.o udivdi3.o
 lib-$(CONFIG_SPARC32) += copy_user.o locks.o
 lib-y                 += atomic_$(BITS).o
 lib-$(CONFIG_SPARC32) += lshrdi3.o ashldi3.o
-lib-y                 += rwsem_$(BITS).o
+lib-$(CONFIG_SPARC32) += rwsem_$(BITS).o
 lib-$(CONFIG_SPARC32) += muldi3.o bitext.o cmpdi2.o
 
 lib-$(CONFIG_SPARC64) += copy_page.o clear_page.o bzero.o
diff --git a/arch/sparc/lib/rwsem_64.S b/arch/sparc/lib/rwsem_64.S
deleted file mode 100644
index 91a7d29..0000000
--- a/arch/sparc/lib/rwsem_64.S
+++ /dev/null
@@ -1,163 +0,0 @@
-/* rwsem.S: RW semaphore assembler.
- *
- * Written by David S. Miller (davem@redhat.com), 2001.
- * Derived from asm-i386/rwsem.h
- */
-
-#include <asm/rwsem-const.h>
-
-	.section	.sched.text, "ax"
-
-	.globl		__down_read
-__down_read:
-1:	lduw		[%o0], %g1
-	add		%g1, 1, %g7
-	cas		[%o0], %g1, %g7
-	cmp		%g1, %g7
-	bne,pn		%icc, 1b
-	 add		%g7, 1, %g7
-	cmp		%g7, 0
-	bl,pn		%icc, 3f
-	 nop
-2:
-	retl
-	 nop
-3:
-	save		%sp, -192, %sp
-	call		rwsem_down_read_failed
-	 mov		%i0, %o0
-	ret
-	 restore
-	.size		__down_read, .-__down_read
-
-	.globl		__down_read_trylock
-__down_read_trylock:
-1:	lduw		[%o0], %g1
-	add		%g1, 1, %g7
-	cmp		%g7, 0
-	bl,pn		%icc, 2f
-	 mov		0, %o1
-	cas		[%o0], %g1, %g7
-	cmp		%g1, %g7
-	bne,pn		%icc, 1b
-	 mov		1, %o1
-2:	retl
-	 mov		%o1, %o0
-	.size		__down_read_trylock, .-__down_read_trylock
-
-	.globl		__down_write
-__down_write:
-	sethi		%hi(RWSEM_ACTIVE_WRITE_BIAS), %g1
-	or		%g1, %lo(RWSEM_ACTIVE_WRITE_BIAS), %g1
-1:
-	lduw		[%o0], %g3
-	add		%g3, %g1, %g7
-	cas		[%o0], %g3, %g7
-	cmp		%g3, %g7
-	bne,pn		%icc, 1b
-	 cmp		%g7, 0
-	bne,pn		%icc, 3f
-	 nop
-2:	retl
-	 nop
-3:
-	save		%sp, -192, %sp
-	call		rwsem_down_write_failed
-	 mov		%i0, %o0
-	ret
-	 restore
-	.size		__down_write, .-__down_write
-
-	.globl		__down_write_trylock
-__down_write_trylock:
-	sethi		%hi(RWSEM_ACTIVE_WRITE_BIAS), %g1
-	or		%g1, %lo(RWSEM_ACTIVE_WRITE_BIAS), %g1
-1:
-	lduw		[%o0], %g3
-	cmp		%g3, 0
-	bne,pn		%icc, 2f
-	 mov		0, %o1
-	add		%g3, %g1, %g7
-	cas		[%o0], %g3, %g7
-	cmp		%g3, %g7
-	bne,pn		%icc, 1b
-	 mov		1, %o1
-2:	retl
-	 mov		%o1, %o0
-	.size		__down_write_trylock, .-__down_write_trylock
-
-	.globl		__up_read
-__up_read:
-1:
-	lduw		[%o0], %g1
-	sub		%g1, 1, %g7
-	cas		[%o0], %g1, %g7
-	cmp		%g1, %g7
-	bne,pn		%icc, 1b
-	 cmp		%g7, 0
-	bl,pn		%icc, 3f
-	 nop
-2:	retl
-	 nop
-3:	sethi		%hi(RWSEM_ACTIVE_MASK), %g1
-	sub		%g7, 1, %g7
-	or		%g1, %lo(RWSEM_ACTIVE_MASK), %g1
-	andcc		%g7, %g1, %g0
-	bne,pn		%icc, 2b
-	 nop
-	save		%sp, -192, %sp
-	call		rwsem_wake
-	 mov		%i0, %o0
-	ret
-	 restore
-	.size		__up_read, .-__up_read
-
-	.globl		__up_write
-__up_write:
-	sethi		%hi(RWSEM_ACTIVE_WRITE_BIAS), %g1
-	or		%g1, %lo(RWSEM_ACTIVE_WRITE_BIAS), %g1
-1:
-	lduw		[%o0], %g3
-	sub		%g3, %g1, %g7
-	cas		[%o0], %g3, %g7
-	cmp		%g3, %g7
-	bne,pn		%icc, 1b
-	 sub		%g7, %g1, %g7
-	cmp		%g7, 0
-	bl,pn		%icc, 3f
-	 nop
-2:
-	retl
-	 nop
-3:
-	save		%sp, -192, %sp
-	call		rwsem_wake
-	 mov		%i0, %o0
-	ret
-	 restore
-	.size		__up_write, .-__up_write
-
-	.globl		__downgrade_write
-__downgrade_write:
-	sethi		%hi(RWSEM_WAITING_BIAS), %g1
-	or		%g1, %lo(RWSEM_WAITING_BIAS), %g1
-1:
-	lduw		[%o0], %g3
-	sub		%g3, %g1, %g7
-	cas		[%o0], %g3, %g7
-	cmp		%g3, %g7
-	bne,pn		%icc, 1b
-	 sub		%g7, %g1, %g7
-	cmp		%g7, 0
-	bl,pn		%icc, 3f
-	 nop
-2:
-	retl
-	 nop
-3:
-	save		%sp, -192, %sp
-	call		rwsem_downgrade_wake
-	 mov		%i0, %o0
-	ret
-	 restore
-	.size		__downgrade_write, .-__downgrade_write
-- 
1.7.2.1

Re: 64-bit ppc rwsem

From: Sam Ravnborg <hidden>
Date: 2010-08-18 05:40:04

quoted hunk
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index c4b5e03..fa4c3ea 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -15,7 +15,7 @@ lib-$(CONFIG_SPARC32) += divdi3.o udivdi3.o
 lib-$(CONFIG_SPARC32) += copy_user.o locks.o
 lib-y                 += atomic_$(BITS).o
 lib-$(CONFIG_SPARC32) += lshrdi3.o ashldi3.o
-lib-y                 += rwsem_$(BITS).o
+lib-$(CONFIG_SPARC32) += rwsem_$(BITS).o
You could write this explicit as:
+lib-$(CONFIG_SPARC32) += rwsem_32.o
As rwsem_64 is gone now.

	Sam

Re: 64-bit ppc rwsem

From: David Miller <davem@davemloft.net>
Date: 2010-08-18 05:47:58

From: Sam Ravnborg <redacted>
Date: Wed, 18 Aug 2010 07:39:55 +0200
quoted
@@ -15,7 +15,7 @@ lib-$(CONFIG_SPARC32) += divdi3.o udivdi3.o
 lib-$(CONFIG_SPARC32) += copy_user.o locks.o
 lib-y                 += atomic_$(BITS).o
 lib-$(CONFIG_SPARC32) += lshrdi3.o ashldi3.o
-lib-y                 += rwsem_$(BITS).o
+lib-$(CONFIG_SPARC32) += rwsem_$(BITS).o
You could write this explicit as:
quoted
+lib-$(CONFIG_SPARC32) += rwsem_32.o
As rwsem_64 is gone now.
Sure, I'll make that change, thanks Sam.

Re: 64-bit ppc rwsem

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: 2010-08-19 05:23:48

On Tue, 2010-08-17 at 22:28 -0700, David Miller wrote:
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Wed, 18 Aug 2010 15:03:23 +1000
quoted
I tried various tricks but so far they didn't work. I'll have another
look tomorrow, but I may end up having to keep all the crap typecasts.
The casts are pretty much unavoidable.

Here's what I'm going to end up using on sparc64:
Similar here, but using atomic_long_t instead so it works for 32-bit too
for me. I suppose we could make that part common indeed.

What about asm-generic/rwsem-atomic.h  or rwsem-cmpxchg.h ?

Below is my current patch, seems to boot fine here so far.

Cheers,
Ben

Subject: [PATCH] powerpc: Make rwsem use "long" type

This makes the 64-bit kernel use 64-bit signed integers for the counter
(effectively supporting 32-bit of active count in the semaphore), thus
avoiding things like overflow of the mmap_sem if you use a really crazy
number of threads

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/rwsem.h |   64 ++++++++++++++++++++++----------------
 1 files changed, 37 insertions(+), 27 deletions(-)
diff --git a/arch/powerpc/include/asm/rwsem.h b/arch/powerpc/include/asm/rwsem.h
index 24cd928..8447d89 100644
--- a/arch/powerpc/include/asm/rwsem.h
+++ b/arch/powerpc/include/asm/rwsem.h
@@ -21,15 +21,20 @@
 /*
  * the semaphore definition
  */
-struct rw_semaphore {
-	/* XXX this should be able to be an atomic_t  -- paulus */
-	signed int		count;
-#define RWSEM_UNLOCKED_VALUE		0x00000000
-#define RWSEM_ACTIVE_BIAS		0x00000001
-#define RWSEM_ACTIVE_MASK		0x0000ffff
-#define RWSEM_WAITING_BIAS		(-0x00010000)
+#ifdef CONFIG_PPC64
+# define RWSEM_ACTIVE_MASK		0xffffffffL
+#else
+# define RWSEM_ACTIVE_MASK		0x0000ffffL
+#endif
+
+#define RWSEM_UNLOCKED_VALUE		0x00000000L
+#define RWSEM_ACTIVE_BIAS		0x00000001L
+#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)
+
+struct rw_semaphore {
+	long			count;
 	spinlock_t		wait_lock;
 	struct list_head	wait_list;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -43,9 +48,13 @@ struct rw_semaphore {
 # define __RWSEM_DEP_MAP_INIT(lockname)
 #endif
 
-#define __RWSEM_INITIALIZER(name) \
-	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
-	  LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
+#define __RWSEM_INITIALIZER(name)				\
+{								\
+	RWSEM_UNLOCKED_VALUE,					\
+	__SPIN_LOCK_UNLOCKED((name).wait_lock),			\
+	LIST_HEAD_INIT((name).wait_list)			\
+	__RWSEM_DEP_MAP_INIT(name)				\
+}
 
 #define DECLARE_RWSEM(name)		\
 	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
@@ -70,13 +79,13 @@ extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
  */
 static inline void __down_read(struct rw_semaphore *sem)
 {
-	if (unlikely(atomic_inc_return((atomic_t *)(&sem->count)) <= 0))
+	if (unlikely(atomic_long_inc_return((atomic_long_t *)&sem->count) <= 0))
 		rwsem_down_read_failed(sem);
 }
 
 static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
-	int tmp;
+	long tmp;
 
 	while ((tmp = sem->count) >= 0) {
 		if (tmp == cmpxchg(&sem->count, tmp,
@@ -92,10 +101,10 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
  */
 static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
 {
-	int tmp;
+	long tmp;
 
-	tmp = atomic_add_return(RWSEM_ACTIVE_WRITE_BIAS,
-				(atomic_t *)(&sem->count));
+	tmp = atomic_long_add_return(RWSEM_ACTIVE_WRITE_BIAS,
+				     (atomic_long_t *)&sem->count);
 	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
 		rwsem_down_write_failed(sem);
 }
@@ -107,7 +116,7 @@ static inline void __down_write(struct rw_semaphore *sem)
 
 static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
-	int tmp;
+	long tmp;
 
 	tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
 		      RWSEM_ACTIVE_WRITE_BIAS);
@@ -119,9 +128,9 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
  */
 static inline void __up_read(struct rw_semaphore *sem)
 {
-	int tmp;
+	long tmp;
 
-	tmp = atomic_dec_return((atomic_t *)(&sem->count));
+	tmp = atomic_long_dec_return((atomic_long_t *)&sem->count);
 	if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
 		rwsem_wake(sem);
 }
@@ -131,17 +140,17 @@ static inline void __up_read(struct rw_semaphore *sem)
  */
 static inline void __up_write(struct rw_semaphore *sem)
 {
-	if (unlikely(atomic_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
-			      (atomic_t *)(&sem->count)) < 0))
+	if (unlikely(atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
+				 (atomic_long_t *)&sem->count) < 0))
 		rwsem_wake(sem);
 }
 
 /*
  * implement atomic add functionality
  */
-static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
+static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
 {
-	atomic_add(delta, (atomic_t *)(&sem->count));
+	atomic_long_add(delta, (atomic_long_t *)&sem->count);
 }
 
 /*
@@ -149,9 +158,10 @@ static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
  */
 static inline void __downgrade_write(struct rw_semaphore *sem)
 {
-	int tmp;
+	long tmp;
 
-	tmp = atomic_add_return(-RWSEM_WAITING_BIAS, (atomic_t *)(&sem->count));
+	tmp = atomic_long_add_return(-RWSEM_WAITING_BIAS,
+				     (atomic_long_t *)&sem->count);
 	if (tmp < 0)
 		rwsem_downgrade_wake(sem);
 }
@@ -159,14 +169,14 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 /*
  * implement exchange and add functionality
  */
-static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
+static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
 {
-	return atomic_add_return(delta, (atomic_t *)(&sem->count));
+	return atomic_long_add_return(delta, (atomic_long_t *)&sem->count);
 }
 
 static inline int rwsem_is_locked(struct rw_semaphore *sem)
 {
-	return (sem->count != 0);
+	return sem->count != 0;
 }
 
 #endif	/* __KERNEL__ */

Re: 64-bit ppc rwsem

From: David Miller <davem@davemloft.net>
Date: 2010-08-19 05:29:10

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 19 Aug 2010 15:23:23 +1000
Similar here, but using atomic_long_t instead so it works for 32-bit too
for me. I suppose we could make that part common indeed.

What about asm-generic/rwsem-atomic.h  or rwsem-cmpxchg.h ?
Using rwsem-cmpxchg.h sounds best I guess.

Re: 64-bit ppc rwsem

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: 2010-08-19 10:24:46

On Wed, 2010-08-18 at 22:29 -0700, David Miller wrote:
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 19 Aug 2010 15:23:23 +1000
quoted
Similar here, but using atomic_long_t instead so it works for 32-bit too
for me. I suppose we could make that part common indeed.

What about asm-generic/rwsem-atomic.h  or rwsem-cmpxchg.h ?
Using rwsem-cmpxchg.h sounds best I guess.
Ok, I'll send a new patch tomorrow that does that.

Cheers,
Ben.

[PATCH 1/2] powerpc: Make rwsem use "long" type

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: 2010-08-20 05:15:22

This makes the 64-bit kernel use 64-bit signed integers for the counter
(effectively supporting 32-bit of active count in the semaphore), thus
avoiding things like overflow of the mmap_sem if you use a really crazy
number of threads

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/rwsem.h |   64 ++++++++++++++++++++++----------------
 1 files changed, 37 insertions(+), 27 deletions(-)
diff --git a/arch/powerpc/include/asm/rwsem.h b/arch/powerpc/include/asm/rwsem.h
index 24cd928..8447d89 100644
--- a/arch/powerpc/include/asm/rwsem.h
+++ b/arch/powerpc/include/asm/rwsem.h
@@ -21,15 +21,20 @@
 /*
  * the semaphore definition
  */
-struct rw_semaphore {
-	/* XXX this should be able to be an atomic_t  -- paulus */
-	signed int		count;
-#define RWSEM_UNLOCKED_VALUE		0x00000000
-#define RWSEM_ACTIVE_BIAS		0x00000001
-#define RWSEM_ACTIVE_MASK		0x0000ffff
-#define RWSEM_WAITING_BIAS		(-0x00010000)
+#ifdef CONFIG_PPC64
+# define RWSEM_ACTIVE_MASK		0xffffffffL
+#else
+# define RWSEM_ACTIVE_MASK		0x0000ffffL
+#endif
+
+#define RWSEM_UNLOCKED_VALUE		0x00000000L
+#define RWSEM_ACTIVE_BIAS		0x00000001L
+#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)
+
+struct rw_semaphore {
+	long			count;
 	spinlock_t		wait_lock;
 	struct list_head	wait_list;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -43,9 +48,13 @@ struct rw_semaphore {
 # define __RWSEM_DEP_MAP_INIT(lockname)
 #endif
 
-#define __RWSEM_INITIALIZER(name) \
-	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
-	  LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
+#define __RWSEM_INITIALIZER(name)				\
+{								\
+	RWSEM_UNLOCKED_VALUE,					\
+	__SPIN_LOCK_UNLOCKED((name).wait_lock),			\
+	LIST_HEAD_INIT((name).wait_list)			\
+	__RWSEM_DEP_MAP_INIT(name)				\
+}
 
 #define DECLARE_RWSEM(name)		\
 	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
@@ -70,13 +79,13 @@ extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
  */
 static inline void __down_read(struct rw_semaphore *sem)
 {
-	if (unlikely(atomic_inc_return((atomic_t *)(&sem->count)) <= 0))
+	if (unlikely(atomic_long_inc_return((atomic_long_t *)&sem->count) <= 0))
 		rwsem_down_read_failed(sem);
 }
 
 static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
-	int tmp;
+	long tmp;
 
 	while ((tmp = sem->count) >= 0) {
 		if (tmp == cmpxchg(&sem->count, tmp,
@@ -92,10 +101,10 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
  */
 static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
 {
-	int tmp;
+	long tmp;
 
-	tmp = atomic_add_return(RWSEM_ACTIVE_WRITE_BIAS,
-				(atomic_t *)(&sem->count));
+	tmp = atomic_long_add_return(RWSEM_ACTIVE_WRITE_BIAS,
+				     (atomic_long_t *)&sem->count);
 	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
 		rwsem_down_write_failed(sem);
 }
@@ -107,7 +116,7 @@ static inline void __down_write(struct rw_semaphore *sem)
 
 static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
-	int tmp;
+	long tmp;
 
 	tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
 		      RWSEM_ACTIVE_WRITE_BIAS);
@@ -119,9 +128,9 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
  */
 static inline void __up_read(struct rw_semaphore *sem)
 {
-	int tmp;
+	long tmp;
 
-	tmp = atomic_dec_return((atomic_t *)(&sem->count));
+	tmp = atomic_long_dec_return((atomic_long_t *)&sem->count);
 	if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
 		rwsem_wake(sem);
 }
@@ -131,17 +140,17 @@ static inline void __up_read(struct rw_semaphore *sem)
  */
 static inline void __up_write(struct rw_semaphore *sem)
 {
-	if (unlikely(atomic_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
-			      (atomic_t *)(&sem->count)) < 0))
+	if (unlikely(atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
+				 (atomic_long_t *)&sem->count) < 0))
 		rwsem_wake(sem);
 }
 
 /*
  * implement atomic add functionality
  */
-static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
+static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
 {
-	atomic_add(delta, (atomic_t *)(&sem->count));
+	atomic_long_add(delta, (atomic_long_t *)&sem->count);
 }
 
 /*
@@ -149,9 +158,10 @@ static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
  */
 static inline void __downgrade_write(struct rw_semaphore *sem)
 {
-	int tmp;
+	long tmp;
 
-	tmp = atomic_add_return(-RWSEM_WAITING_BIAS, (atomic_t *)(&sem->count));
+	tmp = atomic_long_add_return(-RWSEM_WAITING_BIAS,
+				     (atomic_long_t *)&sem->count);
 	if (tmp < 0)
 		rwsem_downgrade_wake(sem);
 }
@@ -159,14 +169,14 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 /*
  * implement exchange and add functionality
  */
-static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
+static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
 {
-	return atomic_add_return(delta, (atomic_t *)(&sem->count));
+	return atomic_long_add_return(delta, (atomic_long_t *)&sem->count);
 }
 
 static inline int rwsem_is_locked(struct rw_semaphore *sem)
 {
-	return (sem->count != 0);
+	return sem->count != 0;
 }
 
 #endif	/* __KERNEL__ */

[PATCH 2/2] rwsem: Move powerpc atomic-long based implementation to asm-generic

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: 2010-08-20 05:15:37

Other architectures who support cmpxchg and atomic_long can
use that directly.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/rwsem.h    |  184 +----------------------------------
 include/asm-generic/rwsem-cmpxchg.h |  183 ++++++++++++++++++++++++++++++++++
 2 files changed, 184 insertions(+), 183 deletions(-)
 create mode 100644 include/asm-generic/rwsem-cmpxchg.h
diff --git a/arch/powerpc/include/asm/rwsem.h b/arch/powerpc/include/asm/rwsem.h
index 8447d89..1237ad6 100644
--- a/arch/powerpc/include/asm/rwsem.h
+++ b/arch/powerpc/include/asm/rwsem.h
@@ -1,183 +1 @@
-#ifndef _ASM_POWERPC_RWSEM_H
-#define _ASM_POWERPC_RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
-#endif
-
-#ifdef __KERNEL__
-
-/*
- * R/W semaphores for PPC using the stuff in lib/rwsem.c.
- * Adapted largely from include/asm-i386/rwsem.h
- * by Paul Mackerras <paulus@samba.org>.
- */
-
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <asm/atomic.h>
-#include <asm/system.h>
-
-/*
- * the semaphore definition
- */
-#ifdef CONFIG_PPC64
-# define RWSEM_ACTIVE_MASK		0xffffffffL
-#else
-# define RWSEM_ACTIVE_MASK		0x0000ffffL
-#endif
-
-#define RWSEM_UNLOCKED_VALUE		0x00000000L
-#define RWSEM_ACTIVE_BIAS		0x00000001L
-#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)
-
-struct rw_semaphore {
-	long			count;
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-};
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name)				\
-{								\
-	RWSEM_UNLOCKED_VALUE,					\
-	__SPIN_LOCK_UNLOCKED((name).wait_lock),			\
-	LIST_HEAD_INIT((name).wait_list)			\
-	__RWSEM_DEP_MAP_INIT(name)				\
-}
-
-#define DECLARE_RWSEM(name)		\
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)					\
-	do {						\
-		static struct lock_class_key __key;	\
-							\
-		__init_rwsem((sem), #sem, &__key);	\
-	} while (0)
-
-/*
- * lock for reading
- */
-static inline void __down_read(struct rw_semaphore *sem)
-{
-	if (unlikely(atomic_long_inc_return((atomic_long_t *)&sem->count) <= 0))
-		rwsem_down_read_failed(sem);
-}
-
-static inline int __down_read_trylock(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	while ((tmp = sem->count) >= 0) {
-		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 = atomic_long_add_return(RWSEM_ACTIVE_WRITE_BIAS,
-				     (atomic_long_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 = atomic_long_dec_return((atomic_long_t *)&sem->count);
-	if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
-		rwsem_wake(sem);
-}
-
-/*
- * unlock after writing
- */
-static inline void __up_write(struct rw_semaphore *sem)
-{
-	if (unlikely(atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
-				 (atomic_long_t *)&sem->count) < 0))
-		rwsem_wake(sem);
-}
-
-/*
- * implement atomic add functionality
- */
-static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
-{
-	atomic_long_add(delta, (atomic_long_t *)&sem->count);
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = atomic_long_add_return(-RWSEM_WAITING_BIAS,
-				     (atomic_long_t *)&sem->count);
-	if (tmp < 0)
-		rwsem_downgrade_wake(sem);
-}
-
-/*
- * implement exchange and add functionality
- */
-static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
-{
-	return atomic_long_add_return(delta, (atomic_long_t *)&sem->count);
-}
-
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return sem->count != 0;
-}
-
-#endif	/* __KERNEL__ */
-#endif	/* _ASM_POWERPC_RWSEM_H */
+#include <asm-generic/rwsem-cmpxchg.h>
diff --git a/include/asm-generic/rwsem-cmpxchg.h b/include/asm-generic/rwsem-cmpxchg.h
new file mode 100644
index 0000000..2b1c859
--- /dev/null
+++ b/include/asm-generic/rwsem-cmpxchg.h
@@ -0,0 +1,183 @@
+#ifndef _RWSEM_CMPXCHG_H
+#define _RWSEM_CMPXCHG_H
+
+#ifndef _LINUX_RWSEM_H
+#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
+#endif
+
+#ifdef __KERNEL__
+
+/*
+ * Generic R/W semaphores the stuff in lib/rwsem.c.
+ * Adapted largely from include/asm-i386/rwsem.h
+ * by Paul Mackerras <paulus@samba.org>.
+ */
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <asm/atomic.h>
+#include <asm/system.h>
+
+/*
+ * the semaphore definition
+ */
+#if BITS_PER_LONG == 64
+# define RWSEM_ACTIVE_MASK		0xffffffffL
+#else
+# define RWSEM_ACTIVE_MASK		0x0000ffffL
+#endif
+
+#define RWSEM_UNLOCKED_VALUE		0x00000000L
+#define RWSEM_ACTIVE_BIAS		0x00000001L
+#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)
+
+struct rw_semaphore {
+	long			count;
+	spinlock_t		wait_lock;
+	struct list_head	wait_list;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
+#else
+# define __RWSEM_DEP_MAP_INIT(lockname)
+#endif
+
+#define __RWSEM_INITIALIZER(name)				\
+{								\
+	RWSEM_UNLOCKED_VALUE,					\
+	__SPIN_LOCK_UNLOCKED((name).wait_lock),			\
+	LIST_HEAD_INIT((name).wait_list)			\
+	__RWSEM_DEP_MAP_INIT(name)				\
+}
+
+#define DECLARE_RWSEM(name)		\
+	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
+
+extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
+
+extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
+			 struct lock_class_key *key);
+
+#define init_rwsem(sem)					\
+	do {						\
+		static struct lock_class_key __key;	\
+							\
+		__init_rwsem((sem), #sem, &__key);	\
+	} while (0)
+
+/*
+ * lock for reading
+ */
+static inline void __down_read(struct rw_semaphore *sem)
+{
+	if (unlikely(atomic_long_inc_return((atomic_long_t *)&sem->count) <= 0))
+		rwsem_down_read_failed(sem);
+}
+
+static inline int __down_read_trylock(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	while ((tmp = sem->count) >= 0) {
+		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 = atomic_long_add_return(RWSEM_ACTIVE_WRITE_BIAS,
+				     (atomic_long_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 = atomic_long_dec_return((atomic_long_t *)&sem->count);
+	if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
+		rwsem_wake(sem);
+}
+
+/*
+ * unlock after writing
+ */
+static inline void __up_write(struct rw_semaphore *sem)
+{
+	if (unlikely(atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
+				 (atomic_long_t *)&sem->count) < 0))
+		rwsem_wake(sem);
+}
+
+/*
+ * implement atomic add functionality
+ */
+static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
+{
+	atomic_long_add(delta, (atomic_long_t *)&sem->count);
+}
+
+/*
+ * downgrade write lock to read lock
+ */
+static inline void __downgrade_write(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	tmp = atomic_long_add_return(-RWSEM_WAITING_BIAS,
+				     (atomic_long_t *)&sem->count);
+	if (tmp < 0)
+		rwsem_downgrade_wake(sem);
+}
+
+/*
+ * implement exchange and add functionality
+ */
+static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
+{
+	return atomic_long_add_return(delta, (atomic_long_t *)&sem->count);
+}
+
+static inline int rwsem_is_locked(struct rw_semaphore *sem)
+{
+	return sem->count != 0;
+}
+
+#endif	/* __KERNEL__ */
+#endif	/* _RWSEM_CMPXCHG_H */

Re: [PATCH 2/2] rwsem: Move powerpc atomic-long based implementation to asm-generic

From: Sam Ravnborg <hidden>
Date: 2010-08-20 06:43:54

quoted hunk
diff --git a/include/asm-generic/rwsem-cmpxchg.h b/include/asm-generic/rwsem-cmpxchg.h
new file mode 100644
index 0000000..2b1c859
--- /dev/null
+++ b/include/asm-generic/rwsem-cmpxchg.h
@@ -0,0 +1,183 @@
+#ifndef _RWSEM_CMPXCHG_H
+#define _RWSEM_CMPXCHG_H
+
+#ifndef _LINUX_RWSEM_H
+#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
+#endif
+
+#ifdef __KERNEL__
#ifdef __KERNEL__ is only relevant for exported headers.
For kernel only headers like this is does not make sense,
but it does not harm.

	Sam

Re: [PATCH 2/2] rwsem: Move powerpc atomic-long based implementation to asm-generic

From: David Miller <davem@davemloft.net>
Date: 2010-08-23 04:39:29

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Fri, 20 Aug 2010 15:14:55 +1000
Other architectures who support cmpxchg and atomic_long can
use that directly.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: David S. Miller <davem@davemloft.net>

I'll move sparc64 over to this once it hits Linus's tree.

Re: 64-bit ppc rwsem

From: Arnd Bergmann <arnd@arndb.de>
Date: 2010-08-23 13:44:26

On Thursday 19 August 2010, David Miller wrote:
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 19 Aug 2010 15:23:23 +1000
quoted
Similar here, but using atomic_long_t instead so it works for 32-bit too
for me. I suppose we could make that part common indeed.

What about asm-generic/rwsem-atomic.h  or rwsem-cmpxchg.h ?
Using rwsem-cmpxchg.h sounds best I guess.
The implementation looks good for asm-generic, but there is now an asymmetry
between the spinlock and the atomic_long_t based version.

Maybe we can make them both do the same thing, either of

1. create include/linux/rwsem-cmpxchg.h and add an
   #elif defined(CONFIG_RWSEM_GENERIC_ATOMIC) to include/linux/rwsem.h

2. move include/linux/rwsem-spinlock.h to include/asm-generic/ and
   include that from all architectures that want the spinlock based version.

Further comments:

* Alpha has an optimization for the uniprocessor case, where the atomic
instructions get turned into nonatomic additions. The spinlock based
version uses no locks on UP but disables interrupts for reasons I don't
understand (nothing running at interrupt time should try to access an rwsem).
Should the generic version do the same as Alpha?

* Is there any architecture that would still benefit from having a separate
rwsem implementation? AFAICT all the remaining ones are just variations of
the same concept of using cmpxchg (or xadd in case of x86), which is what
atomics typically end up doing anyway.

	Arnd

Re: 64-bit ppc rwsem

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: 2010-08-23 22:02:19

On Mon, 2010-08-23 at 15:44 +0200, Arnd Bergmann wrote:
* Alpha has an optimization for the uniprocessor case, where the atomic
instructions get turned into nonatomic additions. The spinlock based
version uses no locks on UP but disables interrupts for reasons I don't
understand (nothing running at interrupt time should try to access an rwsem).
Should the generic version do the same as Alpha?
I've seen drivers in the past do trylocks at interrupt time ... tho I
agree it sucks.
* Is there any architecture that would still benefit from having a separate
rwsem implementation? AFAICT all the remaining ones are just variations of
the same concept of using cmpxchg (or xadd in case of x86), which is what
atomics typically end up doing anyway.
It depends how sensitive rwsems are. 

The "generic" variant based on atomic's and cmpxchg on powerpc is
sub-optimal in the sense that it has stronger memory barriers that would
be necessary (atomic_inc_return for example has both acquire and
release).

But that vs. one more pile of inline asm, we decided it wasn't hot
enough a spot for us to care back then.

Cheers,
Ben.

Re: 64-bit ppc rwsem

From: David Miller <davem@davemloft.net>
Date: 2010-08-23 22:18:36

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 24 Aug 2010 08:01:25 +1000
On Mon, 2010-08-23 at 15:44 +0200, Arnd Bergmann wrote:
quoted
* Alpha has an optimization for the uniprocessor case, where the atomic
instructions get turned into nonatomic additions. The spinlock based
version uses no locks on UP but disables interrupts for reasons I don't
understand (nothing running at interrupt time should try to access an rwsem).
Should the generic version do the same as Alpha?
I've seen drivers in the past do trylocks at interrupt time ... tho I
agree it sucks.
Recently there was a thread where this was declared absolutely illegal.

Maybe it was allowed, or sort-of worked before, and that's why it's
accounted for with IRQ disables in some implementations.  I don't
know.

Re: 64-bit ppc rwsem

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: 2010-08-24 01:31:45

On Mon, 2010-08-23 at 15:18 -0700, David Miller wrote:
quoted
I've seen drivers in the past do trylocks at interrupt time ... tho
I
quoted
agree it sucks.
Recently there was a thread where this was declared absolutely
illegal.

Maybe it was allowed, or sort-of worked before, and that's why it's
accounted for with IRQ disables in some implementations.  I don't
know. 
Ok, I'm happy to say it's a big no-no then.

Arnd, do you want to take over the moving to asm-generic and take care
of the spinlock case as well ? I can send Linus the first patch that
changes powerpc to use atomic_long now along with a few other things I
have pending, then you can pickup from there. Or do you want me to
continue pushing my patch as-is and we can look at cleaning up the
spinlock case separately ?

Cheers,
Ben.

Re: [PATCH 1/2] powerpc: Make rwsem use "long" type

From: Timur Tabi <hidden>
Date: 2010-08-24 01:37:31

On Fri, Aug 20, 2010 at 12:14 AM, Benjamin Herrenschmidt
[off-list ref] wrote:
=A0static inline int rwsem_is_locked(struct rw_semaphore *sem)
=A0{
- =A0 =A0 =A0 return (sem->count !=3D 0);
+ =A0 =A0 =A0 return sem->count !=3D 0;
=A0}
Does this change make the code do anything different?

--=20
Timur Tabi
Linux kernel developer at Freescale

Re: [PATCH 2/2] rwsem: Move powerpc atomic-long based implementation to asm-generic

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: 2010-08-24 02:08:02

On Fri, 2010-08-20 at 08:43 +0200, Sam Ravnborg wrote:
quoted
diff --git a/include/asm-generic/rwsem-cmpxchg.h b/include/asm-generic/rwsem-cmpxchg.h
new file mode 100644
index 0000000..2b1c859
--- /dev/null
+++ b/include/asm-generic/rwsem-cmpxchg.h
@@ -0,0 +1,183 @@
+#ifndef _RWSEM_CMPXCHG_H
+#define _RWSEM_CMPXCHG_H
+
+#ifndef _LINUX_RWSEM_H
+#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
+#endif
+
+#ifdef __KERNEL__
#ifdef __KERNEL__ is only relevant for exported headers.
For kernel only headers like this is does not make sense,
but it does not harm.
Well, it was there in the first place, I think we've carried around
forever, but as you say, it doesn't really harm.

Ben.

Re: 64-bit ppc rwsem

From: Arnd Bergmann <arnd@arndb.de>
Date: 2010-08-24 12:06:59

On Tuesday 24 August 2010, Benjamin Herrenschmidt wrote:
On Mon, 2010-08-23 at 15:18 -0700, David Miller wrote:
quoted
quoted
I've seen drivers in the past do trylocks at interrupt time ... tho
I
quoted
agree it sucks.
Recently there was a thread where this was declared absolutely
illegal.

Maybe it was allowed, or sort-of worked before, and that's why it's
accounted for with IRQ disables in some implementations.  I don't
know. 
Ok, I'm happy to say it's a big no-no then.

Arnd, do you want to take over the moving to asm-generic and take care
of the spinlock case as well ? I can send Linus the first patch that
changes powerpc to use atomic_long now along with a few other things I
have pending, then you can pickup from there. Or do you want me to
continue pushing my patch as-is and we can look at cleaning up the
spinlock case separately ?
I'm currently doing too many things at once, please push in your existing
patch for now, we can continue from there.

For the asm-generic patch:
Acked-by: Arnd Bergmann <arnd@arndb.de>
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help