Merge tag 'openrisc-for-linus' of git://github.com/openrisc/linux

Pull OpenRISC updates from Stafford Horne:
 "Highlights include:

   - optimized memset and memcpy routines, ~20% boot time saving

   - support for cpu idling

   - adding support for l.swa and l.lwa atomic operations (in spec from
     2014)

   - use atomics to implement: bitops, cmpxchg, futex

   - the atomics are in preparation for SMP support"

* tag 'openrisc-for-linus' of git://github.com/openrisc/linux: (25 commits)
  openrisc: head: Init r0 to 0 on start
  openrisc: Export ioremap symbols used by modules
  arch/openrisc/lib/memcpy.c: use correct OR1200 option
  openrisc: head: Remove unused strings
  openrisc: head: Move init strings to rodata section
  openrisc: entry: Fix delay slot detection
  openrisc: entry: Whitespace and comment cleanups
  scripts/checkstack.pl: Add openrisc support
  MAINTAINERS: Add the openrisc official repository
  openrisc: Add .gitignore
  openrisc: Add optimized memcpy routine
  openrisc: Add optimized memset
  openrisc: Initial support for the idle state
  openrisc: Fix the bitmask for the unit present register
  openrisc: remove unnecessary stddef.h include
  openrisc: add futex_atomic_* implementations
  openrisc: add optimized atomic operations
  openrisc: add cmpxchg and xchg implementations
  openrisc: add atomic bitops
  openrisc: add l.lwa/l.swa emulation
  ...

MAINTAINERS

@@ -9315,6 +9315,7 @@ OPENRISC ARCHITECTURE
 M:	Jonas Bonn <[email protected]>
 M:	Stefan Kristiansson <[email protected]>
 M:	Stafford Horne <[email protected]>
+T:	git git://github.com/openrisc/linux.git
 L:	[email protected]
 W:	http://openrisc.io
 S:	Maintained

arch/openrisc/Kconfig

@@ -12,6 +12,7 @@ config OPENRISC
 	select HAVE_MEMBLOCK
 	select GPIOLIB
         select HAVE_ARCH_TRACEHOOK
+	select SPARSE_IRQ
 	select GENERIC_IRQ_CHIP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW

arch/openrisc/TODO.openrisc

@@ -10,4 +10,3 @@ that are due for investigation shortly, i.e. our TODO list:
    or1k and this change is slowly trickling through the stack.  For the time
    being, or32 is equivalent to or1k.
 
--- Implement optimized version of memcpy and memset

arch/openrisc/include/asm/Kbuild

@@ -1,7 +1,6 @@
 
 header-y += ucontext.h
 
-generic-y += atomic.h
 generic-y += auxvec.h
 generic-y += barrier.h
 generic-y += bitsperlong.h
@@ -10,8 +9,6 @@ generic-y += bugs.h
 generic-y += cacheflush.h
 generic-y += checksum.h
 generic-y += clkdev.h
-generic-y += cmpxchg-local.h
-generic-y += cmpxchg.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
@@ -22,12 +19,12 @@ generic-y += exec.h
 generic-y += fb.h
 generic-y += fcntl.h
 generic-y += ftrace.h
-generic-y += futex.h
 generic-y += hardirq.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
+generic-y += irq.h
 generic-y += irq_regs.h
 generic-y += irq_work.h
 generic-y += kdebug.h

arch/openrisc/include/asm/atomic.h

@@ -0,0 +1,126 @@
+/*
+ * Copyright (C) 2014 Stefan Kristiansson <[email protected]>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#ifndef __ASM_OPENRISC_ATOMIC_H
+#define __ASM_OPENRISC_ATOMIC_H
+
+#include <linux/types.h>
+
+/* Atomically perform op with v->counter and i */
+#define ATOMIC_OP(op)							\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	int tmp;							\
+									\
+	__asm__ __volatile__(						\
+		"1:	l.lwa	%0,0(%1)	\n"			\
+		"	l." #op " %0,%0,%2	\n"			\
+		"	l.swa	0(%1),%0	\n"			\
+		"	l.bnf	1b		\n"			\
+		"	 l.nop			\n"			\
+		: "=&r"(tmp)						\
+		: "r"(&v->counter), "r"(i)				\
+		: "cc", "memory");					\
+}
+
+/* Atomically perform op with v->counter and i, return the result */
+#define ATOMIC_OP_RETURN(op)						\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	int tmp;							\
+									\
+	__asm__ __volatile__(						\
+		"1:	l.lwa	%0,0(%1)	\n"			\
+		"	l." #op " %0,%0,%2	\n"			\
+		"	l.swa	0(%1),%0	\n"			\
+		"	l.bnf	1b		\n"			\
+		"	 l.nop			\n"			\
+		: "=&r"(tmp)						\
+		: "r"(&v->counter), "r"(i)				\
+		: "cc", "memory");					\
+									\
+	return tmp;							\
+}
+
+/* Atomically perform op with v->counter and i, return orig v->counter */
+#define ATOMIC_FETCH_OP(op)						\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int tmp, old;							\
+									\
+	__asm__ __volatile__(						\
+		"1:	l.lwa	%0,0(%2)	\n"			\
+		"	l." #op " %1,%0,%3	\n"			\
+		"	l.swa	0(%2),%1	\n"			\
+		"	l.bnf	1b		\n"			\
+		"	 l.nop			\n"			\
+		: "=&r"(old), "=&r"(tmp)				\
+		: "r"(&v->counter), "r"(i)				\
+		: "cc", "memory");					\
+									\
+	return old;							\
+}
+
+ATOMIC_OP_RETURN(add)
+ATOMIC_OP_RETURN(sub)
+
+ATOMIC_FETCH_OP(add)
+ATOMIC_FETCH_OP(sub)
+ATOMIC_FETCH_OP(and)
+ATOMIC_FETCH_OP(or)
+ATOMIC_FETCH_OP(xor)
+
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
+#define atomic_add_return	atomic_add_return
+#define atomic_sub_return	atomic_sub_return
+#define atomic_fetch_add	atomic_fetch_add
+#define atomic_fetch_sub	atomic_fetch_sub
+#define atomic_fetch_and	atomic_fetch_and
+#define atomic_fetch_or		atomic_fetch_or
+#define atomic_fetch_xor	atomic_fetch_xor
+#define atomic_and	atomic_and
+#define atomic_or	atomic_or
+#define atomic_xor	atomic_xor
+
+/*
+ * Atomically add a to v->counter as long as v is not already u.
+ * Returns the original value at v->counter.
+ *
+ * This is often used through atomic_inc_not_zero()
+ */
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int old, tmp;
+
+	__asm__ __volatile__(
+		"1:	l.lwa %0, 0(%2)		\n"
+		"	l.sfeq %0, %4		\n"
+		"	l.bf 2f			\n"
+		"	 l.add %1, %0, %3	\n"
+		"	l.swa 0(%2), %1		\n"
+		"	l.bnf 1b		\n"
+		"	 l.nop			\n"
+		"2:				\n"
+		: "=&r"(old), "=&r" (tmp)
+		: "r"(&v->counter), "r"(a), "r"(u)
+		: "cc", "memory");
+
+	return old;
+}
+#define __atomic_add_unless	__atomic_add_unless
+
+#include <asm-generic/atomic.h>
+
+#endif /* __ASM_OPENRISC_ATOMIC_H */

arch/openrisc/include/asm/bitops.h

@@ -45,7 +45,7 @@
 #include <asm-generic/bitops/hweight.h>
 #include <asm-generic/bitops/lock.h>
 
-#include <asm-generic/bitops/atomic.h>
+#include <asm/bitops/atomic.h>
 #include <asm-generic/bitops/non-atomic.h>
 #include <asm-generic/bitops/le.h>
 #include <asm-generic/bitops/ext2-atomic.h>

arch/openrisc/include/asm/bitops/atomic.h

@@ -0,0 +1,123 @@
+/*
+ * Copyright (C) 2014 Stefan Kristiansson <[email protected]>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#ifndef __ASM_OPENRISC_BITOPS_ATOMIC_H
+#define __ASM_OPENRISC_BITOPS_ATOMIC_H
+
+static inline void set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long tmp;
+
+	__asm__ __volatile__(
+		"1:	l.lwa	%0,0(%1)	\n"
+		"	l.or	%0,%0,%2	\n"
+		"	l.swa	0(%1),%0	\n"
+		"	l.bnf	1b		\n"
+		"	 l.nop			\n"
+		: "=&r"(tmp)
+		: "r"(p), "r"(mask)
+		: "cc", "memory");
+}
+
+static inline void clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long tmp;
+
+	__asm__ __volatile__(
+		"1:	l.lwa	%0,0(%1)	\n"
+		"	l.and	%0,%0,%2	\n"
+		"	l.swa	0(%1),%0	\n"
+		"	l.bnf	1b		\n"
+		"	 l.nop			\n"
+		: "=&r"(tmp)
+		: "r"(p), "r"(~mask)
+		: "cc", "memory");
+}
+
+static inline void change_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long tmp;
+
+	__asm__ __volatile__(
+		"1:	l.lwa	%0,0(%1)	\n"
+		"	l.xor	%0,%0,%2	\n"
+		"	l.swa	0(%1),%0	\n"
+		"	l.bnf	1b		\n"
+		"	 l.nop			\n"
+		: "=&r"(tmp)
+		: "r"(p), "r"(mask)
+		: "cc", "memory");
+}
+
+static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old;
+	unsigned long tmp;
+
+	__asm__ __volatile__(
+		"1:	l.lwa	%0,0(%2)	\n"
+		"	l.or	%1,%0,%3	\n"
+		"	l.swa	0(%2),%1	\n"
+		"	l.bnf	1b		\n"
+		"	 l.nop			\n"
+		: "=&r"(old), "=&r"(tmp)
+		: "r"(p), "r"(mask)
+		: "cc", "memory");
+
+	return (old & mask) != 0;
+}
+
+static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old;
+	unsigned long tmp;
+
+	__asm__ __volatile__(
+		"1:	l.lwa	%0,0(%2)	\n"
+		"	l.and	%1,%0,%3	\n"
+		"	l.swa	0(%2),%1	\n"
+		"	l.bnf	1b		\n"
+		"	 l.nop			\n"
+		: "=&r"(old), "=&r"(tmp)
+		: "r"(p), "r"(~mask)
+		: "cc", "memory");
+
+	return (old & mask) != 0;
+}
+
+static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old;
+	unsigned long tmp;
+
+	__asm__ __volatile__(
+		"1:	l.lwa	%0,0(%2)	\n"
+		"	l.xor	%1,%0,%3	\n"
+		"	l.swa	0(%2),%1	\n"
+		"	l.bnf	1b		\n"
+		"	 l.nop			\n"
+		: "=&r"(old), "=&r"(tmp)
+		: "r"(p), "r"(mask)
+		: "cc", "memory");
+
+	return (old & mask) != 0;
+}
+
+#endif /* __ASM_OPENRISC_BITOPS_ATOMIC_H */

arch/openrisc/include/asm/cmpxchg.h

@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2014 Stefan Kristiansson <[email protected]>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#ifndef __ASM_OPENRISC_CMPXCHG_H
+#define __ASM_OPENRISC_CMPXCHG_H
+
+#include  <linux/types.h>
+
+/*
+ * This function doesn't exist, so you'll get a linker error
+ * if something tries to do an invalid cmpxchg().
+ */
+extern void __cmpxchg_called_with_bad_pointer(void);
+
+#define __HAVE_ARCH_CMPXCHG 1
+
+static inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
+{
+	if (size != 4) {
+		__cmpxchg_called_with_bad_pointer();
+		return old;
+	}
+
+	__asm__ __volatile__(
+		"1:	l.lwa %0, 0(%1)		\n"
+		"	l.sfeq %0, %2		\n"
+		"	l.bnf 2f		\n"
+		"	 l.nop			\n"
+		"	l.swa 0(%1), %3		\n"
+		"	l.bnf 1b		\n"
+		"	 l.nop			\n"
+		"2:				\n"
+		: "=&r"(old)
+		: "r"(ptr), "r"(old), "r"(new)
+		: "cc", "memory");
+
+	return old;
+}
+
+#define cmpxchg(ptr, o, n)						\
+	({								\
+		(__typeof__(*(ptr))) __cmpxchg((ptr),			\
+					       (unsigned long)(o),	\
+					       (unsigned long)(n),	\
+					       sizeof(*(ptr)));		\
+	})
+
+/*
+ * This function doesn't exist, so you'll get a linker error if
+ * something tries to do an invalidly-sized xchg().
+ */
+extern void __xchg_called_with_bad_pointer(void);
+
+static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
+				   int size)
+{
+	if (size != 4) {
+		__xchg_called_with_bad_pointer();
+		return val;
+	}
+
+	__asm__ __volatile__(
+		"1:	l.lwa %0, 0(%1)		\n"
+		"	l.swa 0(%1), %2		\n"
+		"	l.bnf 1b		\n"
+		"	 l.nop			\n"
+		: "=&r"(val)
+		: "r"(ptr), "r"(val)
+		: "cc", "memory");
+
+	return val;
+}
+
+#define xchg(ptr, with) \
+	((typeof(*(ptr)))__xchg((unsigned long)(with), (ptr), sizeof(*(ptr))))
+
+#endif /* __ASM_OPENRISC_CMPXCHG_H */