Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc-2.6

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc-2.6:
  sparc64: Get rid of indirect p1275 PROM call buffer.
  sparc64: Fill a missing delay slot.
  sparc64: Make lock backoff really a NOP on UP builds.
  sparc64: simple microoptimizations for atomic functions
  sparc64: Make rwsems 64-bit.
  sparc64: Really fix atomic64_t interface types.

arch/sparc/include/asm/atomic_64.h

@@ -20,14 +20,14 @@
 #define atomic64_set(v, i)	(((v)->counter) = i)
 
 extern void atomic_add(int, atomic_t *);
-extern void atomic64_add(int, atomic64_t *);
+extern void atomic64_add(long, atomic64_t *);
 extern void atomic_sub(int, atomic_t *);
-extern void atomic64_sub(int, atomic64_t *);
+extern void atomic64_sub(long, atomic64_t *);
 
 extern int atomic_add_ret(int, atomic_t *);
-extern long atomic64_add_ret(int, atomic64_t *);
+extern long atomic64_add_ret(long, atomic64_t *);
 extern int atomic_sub_ret(int, atomic_t *);
-extern long atomic64_sub_ret(int, atomic64_t *);
+extern long atomic64_sub_ret(long, atomic64_t *);
 
 #define atomic_dec_return(v) atomic_sub_ret(1, v)
 #define atomic64_dec_return(v) atomic64_sub_ret(1, v)

arch/sparc/include/asm/backoff.h

@@ -8,6 +8,9 @@
 #define BACKOFF_SETUP(reg)	\
 	mov	1, reg
 
+#define BACKOFF_LABEL(spin_label, continue_label) \
+	spin_label
+
 #define BACKOFF_SPIN(reg, tmp, label)	\
 	mov	reg, tmp; \
 88:	brnz,pt	tmp, 88b; \
@@ -22,9 +25,11 @@
 #else
 
 #define BACKOFF_SETUP(reg)
-#define BACKOFF_SPIN(reg, tmp, label) \
-	ba,pt	%xcc, label; \
-	 nop;
+
+#define BACKOFF_LABEL(spin_label, continue_label) \
+	continue_label
+
+#define BACKOFF_SPIN(reg, tmp, label)
 
 #endif
 

arch/sparc/include/asm/oplib_64.h

@@ -185,9 +185,8 @@ extern int prom_getunumber(int syndrome_code,
 			   char *buf, int buflen);
 
 /* Retain physical memory to the caller across soft resets. */
-extern unsigned long prom_retain(const char *name,
-				 unsigned long pa_low, unsigned long pa_high,
-				 long size, long align);
+extern int prom_retain(const char *name, unsigned long size,
+		       unsigned long align, unsigned long *paddr);
 
 /* Load explicit I/D TLB entries into the calling processor. */
 extern long prom_itlb_load(unsigned long index,
@@ -287,26 +286,6 @@ extern void prom_sun4v_guest_soft_state(void);
 extern int prom_ihandle2path(int handle, char *buffer, int bufsize);
 
 /* Client interface level routines. */
-extern long p1275_cmd(const char *, long, ...);
-
-#if 0
-#define P1275_SIZE(x) ((((long)((x) / 32)) << 32) | (x))
-#else
-#define P1275_SIZE(x) x
-#endif
-
-/* We support at most 16 input and 1 output argument */
-#define P1275_ARG_NUMBER		0
-#define P1275_ARG_IN_STRING		1
-#define P1275_ARG_OUT_BUF		2
-#define P1275_ARG_OUT_32B		3
-#define P1275_ARG_IN_FUNCTION		4
-#define P1275_ARG_IN_BUF		5
-#define P1275_ARG_IN_64B		6
-
-#define P1275_IN(x) ((x) & 0xf)
-#define P1275_OUT(x) (((x) << 4) & 0xf0)
-#define P1275_INOUT(i,o) (P1275_IN(i)|P1275_OUT(o))
-#define P1275_ARG(n,x) ((x) << ((n)*3 + 8))
+extern void p1275_cmd_direct(unsigned long *);
 
 #endif /* !(__SPARC64_OPLIB_H) */

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)

arch/sparc/include/asm/system_64.h

@@ -106,6 +106,7 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
  */
 #define write_pic(__p)  					\
 	__asm__ __volatile__("ba,pt	%%xcc, 99f\n\t"		\
+			     " nop\n\t"				\
 			     ".align	64\n"			\
 			  "99:wr	%0, 0x0, %%pic\n\t"	\
 			     "rd	%%pic, %%g0" : : "r" (__p))

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_32.o
 lib-$(CONFIG_SPARC32) += muldi3.o bitext.o cmpdi2.o
 
 lib-$(CONFIG_SPARC64) += copy_page.o clear_page.o bzero.o

arch/sparc/lib/atomic_64.S

@@ -21,7 +21,7 @@ atomic_add: /* %o0 = increment, %o1 = atomic_ptr */
 	add	%g1, %o0, %g7
 	cas	[%o1], %g1, %g7
 	cmp	%g1, %g7
-	bne,pn	%icc, 2f
+	bne,pn	%icc, BACKOFF_LABEL(2f, 1b)
 	 nop
 	retl
 	 nop
@@ -36,7 +36,7 @@ atomic_sub: /* %o0 = decrement, %o1 = atomic_ptr */
 	sub	%g1, %o0, %g7
 	cas	[%o1], %g1, %g7
 	cmp	%g1, %g7
-	bne,pn	%icc, 2f
+	bne,pn	%icc, BACKOFF_LABEL(2f, 1b)
 	 nop
 	retl
 	 nop
@@ -51,11 +51,10 @@ atomic_add_ret: /* %o0 = increment, %o1 = atomic_ptr */
 	add	%g1, %o0, %g7
 	cas	[%o1], %g1, %g7
 	cmp	%g1, %g7
-	bne,pn	%icc, 2f
-	 add	%g7, %o0, %g7
-	sra	%g7, 0, %o0
+	bne,pn	%icc, BACKOFF_LABEL(2f, 1b)
+	 add	%g1, %o0, %g1
 	retl
-	 nop
+	 sra	%g1, 0, %o0
 2:	BACKOFF_SPIN(%o2, %o3, 1b)
 	.size	atomic_add_ret, .-atomic_add_ret
 
@@ -67,11 +66,10 @@ atomic_sub_ret: /* %o0 = decrement, %o1 = atomic_ptr */
 	sub	%g1, %o0, %g7
 	cas	[%o1], %g1, %g7
 	cmp	%g1, %g7
-	bne,pn	%icc, 2f
-	 sub	%g7, %o0, %g7
-	sra	%g7, 0, %o0
+	bne,pn	%icc, BACKOFF_LABEL(2f, 1b)
+	 sub	%g1, %o0, %g1
 	retl
-	 nop
+	 sra	%g1, 0, %o0
 2:	BACKOFF_SPIN(%o2, %o3, 1b)
 	.size	atomic_sub_ret, .-atomic_sub_ret
 
@@ -83,7 +81,7 @@ atomic64_add: /* %o0 = increment, %o1 = atomic_ptr */
 	add	%g1, %o0, %g7
 	casx	[%o1], %g1, %g7
 	cmp	%g1, %g7
-	bne,pn	%xcc, 2f
+	bne,pn	%xcc, BACKOFF_LABEL(2f, 1b)
 	 nop
 	retl
 	 nop
@@ -98,7 +96,7 @@ atomic64_sub: /* %o0 = decrement, %o1 = atomic_ptr */
 	sub	%g1, %o0, %g7
 	casx	[%o1], %g1, %g7
 	cmp	%g1, %g7
-	bne,pn	%xcc, 2f
+	bne,pn	%xcc, BACKOFF_LABEL(2f, 1b)
 	 nop
 	retl
 	 nop
@@ -113,11 +111,10 @@ atomic64_add_ret: /* %o0 = increment, %o1 = atomic_ptr */
 	add	%g1, %o0, %g7
 	casx	[%o1], %g1, %g7
 	cmp	%g1, %g7
-	bne,pn	%xcc, 2f
-	 add	%g7, %o0, %g7
-	mov	%g7, %o0
-	retl
+	bne,pn	%xcc, BACKOFF_LABEL(2f, 1b)
 	 nop
+	retl
+	 add	%g1, %o0, %o0
 2:	BACKOFF_SPIN(%o2, %o3, 1b)
 	.size	atomic64_add_ret, .-atomic64_add_ret
 
@@ -129,10 +126,9 @@ atomic64_sub_ret: /* %o0 = decrement, %o1 = atomic_ptr */
 	sub	%g1, %o0, %g7
 	casx	[%o1], %g1, %g7
 	cmp	%g1, %g7
-	bne,pn	%xcc, 2f
-	 sub	%g7, %o0, %g7
-	mov	%g7, %o0
-	retl
+	bne,pn	%xcc, BACKOFF_LABEL(2f, 1b)
 	 nop
+	retl
+	 sub	%g1, %o0, %o0
 2:	BACKOFF_SPIN(%o2, %o3, 1b)
 	.size	atomic64_sub_ret, .-atomic64_sub_ret