Merge bk://are.twiddle.net/axp-2.5

into home.osdl.org:/home/torvalds/v2.5/linux

arch/alpha/lib/strncpy.S

@@ -16,7 +16,7 @@
 
 	.text
 
-	.align 3
+	.align 4
 	.globl strncpy
 	.ent strncpy
 strncpy:
@@ -24,13 +24,58 @@ strncpy:
 	.prologue 0
 
 	mov	$16, $0		# set return value now
-	beq	$18, 0f
-	mov	$26, $23	# set return address
-	br	__stxncpy	# do the work of the copy
+	beq	$18, $zerolen
+	unop
+	bsr	$23, __stxncpy	# do the work of the copy
+
+	unop
+	bne	$18, $multiword	# do we have full words left?
+	subq	$24, 1, $3	# nope
+	subq	$27, 1, $4
+
+	or	$3, $24, $3	# clear the bits between the last
+	or	$4, $27, $4	# written byte and the last byte in COUNT
+	andnot	$4, $3, $4
+	zap	$1, $4, $1
+
+	stq_u	$1, 0($16)
+	ret
+
+	.align	4
+$multiword:
+	subq	$24, 1, $2	# clear the final bits in the prev word
+	or	$2, $24, $2
+	zapnot	$1, $2, $1
+	subq	$18, 1, $18
+
+	stq_u	$1, 0($16)
+	addq	$16, 8, $16
+	unop
+	beq	$18, 1f
 
-0:	ret
-	nop
 	nop
+	unop
 	nop
+	blbc	$18, 0f
+
+	stq_u	$31, 0($16)	# zero one word
+	subq	$18, 1, $18
+	addq	$16, 8, $16
+	beq	$18, 1f
+
+0:	stq_u	$31, 0($16)	# zero two words
+	subq	$18, 2, $18
+	stq_u	$31, 8($16)
+	addq	$16, 16, $16
+	bne	$18, 0b
+
+1:	ldq_u	$1, 0($16)	# clear the leading bits in the final word
+	subq	$27, 1, $2
+	or	$2, $27, $2
+
+	zap	$1, $2, $1
+	stq_u	$1, 0($16)
+$zerolen:
+	ret
 
 	.end	strncpy

include/asm-alpha/atomic.h

@@ -16,11 +16,16 @@
  * the user gave us, not some alias that contains the same information.
  */
 typedef struct { volatile int counter; } atomic_t;
+typedef struct { volatile long counter; } atomic64_t;
 
 #define ATOMIC_INIT(i)		( (atomic_t) { (i) } )
+#define ATOMIC64_INIT(i)	( (atomic64_t) { (i) } )
+
+#define atomic_read(v)		((v)->counter + 0)
+#define atomic64_read(v)	((v)->counter + 0)
 
-#define atomic_read(v)		((v)->counter)
 #define atomic_set(v,i)		((v)->counter = (i))
+#define atomic64_set(v,i)	((v)->counter = (i))
 
 /*
  * To get proper branch prediction for the main line, we must branch
@@ -43,6 +48,21 @@ static __inline__ void atomic_add(int i, atomic_t * v)
 	:"Ir" (i), "m" (v->counter));
 }
 
+static __inline__ void atomic64_add(long i, atomic64_t * v)
+{
+	unsigned long temp;
+	__asm__ __volatile__(
+	"1:	ldq_l %0,%1\n"
+	"	addq %0,%2,%0\n"
+	"	stq_c %0,%1\n"
+	"	beq %0,2f\n"
+	".subsection 2\n"
+	"2:	br 1b\n"
+	".previous"
+	:"=&r" (temp), "=m" (v->counter)
+	:"Ir" (i), "m" (v->counter));
+}
+
 static __inline__ void atomic_sub(int i, atomic_t * v)
 {
 	unsigned long temp;
@@ -58,6 +78,22 @@ static __inline__ void atomic_sub(int i, atomic_t * v)
 	:"Ir" (i), "m" (v->counter));
 }
 
+static __inline__ void atomic64_sub(long i, atomic64_t * v)
+{
+	unsigned long temp;
+	__asm__ __volatile__(
+	"1:	ldq_l %0,%1\n"
+	"	subq %0,%2,%0\n"
+	"	stq_c %0,%1\n"
+	"	beq %0,2f\n"
+	".subsection 2\n"
+	"2:	br 1b\n"
+	".previous"
+	:"=&r" (temp), "=m" (v->counter)
+	:"Ir" (i), "m" (v->counter));
+}
+
+
 /*
  * Same as above, but return the result value
  */
@@ -79,6 +115,24 @@ static __inline__ long atomic_add_return(int i, atomic_t * v)
 	return result;
 }
 
+static __inline__ long atomic64_add_return(long i, atomic64_t * v)
+{
+	long temp, result;
+	__asm__ __volatile__(
+	"1:	ldq_l %0,%1\n"
+	"	addq %0,%3,%2\n"
+	"	addq %0,%3,%0\n"
+	"	stq_c %0,%1\n"
+	"	beq %0,2f\n"
+	"	mb\n"
+	".subsection 2\n"
+	"2:	br 1b\n"
+	".previous"
+	:"=&r" (temp), "=m" (v->counter), "=&r" (result)
+	:"Ir" (i), "m" (v->counter) : "memory");
+	return result;
+}
+
 static __inline__ long atomic_sub_return(int i, atomic_t * v)
 {
 	long temp, result;
@@ -97,14 +151,41 @@ static __inline__ long atomic_sub_return(int i, atomic_t * v)
 	return result;
 }
 
+static __inline__ long atomic64_sub_return(long i, atomic64_t * v)
+{
+	long temp, result;
+	__asm__ __volatile__(
+	"1:	ldq_l %0,%1\n"
+	"	subq %0,%3,%2\n"
+	"	subq %0,%3,%0\n"
+	"	stq_c %0,%1\n"
+	"	beq %0,2f\n"
+	"	mb\n"
+	".subsection 2\n"
+	"2:	br 1b\n"
+	".previous"
+	:"=&r" (temp), "=m" (v->counter), "=&r" (result)
+	:"Ir" (i), "m" (v->counter) : "memory");
+	return result;
+}
+
 #define atomic_dec_return(v) atomic_sub_return(1,(v))
+#define atomic64_dec_return(v) atomic64_sub_return(1,(v))
+
 #define atomic_inc_return(v) atomic_add_return(1,(v))
+#define atomic64_inc_return(v) atomic64_add_return(1,(v))
 
 #define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0)
+#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0)
+
 #define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
+#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0)
 
 #define atomic_inc(v) atomic_add(1,(v))
+#define atomic64_inc(v) atomic64_add(1,(v))
+
 #define atomic_dec(v) atomic_sub(1,(v))
+#define atomic64_dec(v) atomic64_sub(1,(v))
 
 #define smp_mb__before_atomic_dec()	smp_mb()
 #define smp_mb__after_atomic_dec()	smp_mb()

include/asm-alpha/local.h

+#ifndef _ALPHA_LOCAL_H
+#define _ALPHA_LOCAL_H
+
+#include <linux/percpu.h>
+#include <asm/atomic.h>
+
+typedef atomic64_t local_t;
+
+#define LOCAL_INIT(i)	ATOMIC64_INIT(i)
+#define local_read(v)	atomic64_read(v)
+#define local_set(v,i)	atomic64_set(v,i)
+
+#define local_inc(v)	atomic64_inc(v)
+#define local_dec(v)	atomic64_inc(v)
+#define local_add(i, v)	atomic64_add(i, v)
+#define local_sub(i, v)	atomic64_sub(i, v)
+
+#define __local_inc(v)		((v)->counter++)
+#define __local_dec(v)		((v)->counter++)
+#define __local_add(i,v)	((v)->counter+=(i))
+#define __local_sub(i,v)	((v)->counter-=(i))
+
+/* Use these for per-cpu local_t variables: on some archs they are
+ * much more efficient than these naive implementations.  Note they take
+ * a variable, not an address.
+ */
+#define cpu_local_read(v)	local_read(&__get_cpu_var(v))
+#define cpu_local_set(v, i)	local_set(&__get_cpu_var(v), (i))
+
+#define cpu_local_inc(v)	local_inc(&__get_cpu_var(v))
+#define cpu_local_dec(v)	local_dec(&__get_cpu_var(v))
+#define cpu_local_add(i, v)	local_add((i), &__get_cpu_var(v))
+#define cpu_local_sub(i, v)	local_sub((i), &__get_cpu_var(v))
+
+#define __cpu_local_inc(v)	__local_inc(&__get_cpu_var(v))
+#define __cpu_local_dec(v)	__local_dec(&__get_cpu_var(v))
+#define __cpu_local_add(i, v)	__local_add((i), &__get_cpu_var(v))
+#define __cpu_local_sub(i, v)	__local_sub((i), &__get_cpu_var(v))
+
+#endif /* _ALPHA_LOCAL_H */

include/asm-alpha/sections.h

+#ifndef _ALPHA_SECTIONS_H
+#define _ALPHA_SECTIONS_H
+
+/* nothing to see, move along */
+#include <asm-generic/sections.h>
+
+#endif