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
  ...

9 files changed, 483 insertions, 7 deletions

diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index ef8d1ccc3e45..fb241757f7f0 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/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
diff --git a/arch/openrisc/include/asm/atomic.h b/arch/openrisc/include/asm/atomic.h
new file mode 100644
index 000000000000..146e1660f00e
--- /dev/null
+++ b/arch/openrisc/include/asm/atomic.h
@@ -0,0 +1,126 @@
+/*
+ * Copyright (C) 2014 Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
+ *
+ * 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 */
diff --git a/arch/openrisc/include/asm/bitops.h b/arch/openrisc/include/asm/bitops.h
index 3003cdad561b..689f56819d53 100644
--- a/arch/openrisc/include/asm/bitops.h
+++ b/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>
diff --git a/arch/openrisc/include/asm/bitops/atomic.h b/arch/openrisc/include/asm/bitops/atomic.h
new file mode 100644
index 000000000000..35fb85f61b4a
--- /dev/null
+++ b/arch/openrisc/include/asm/bitops/atomic.h
@@ -0,0 +1,123 @@
+/*
+ * Copyright (C) 2014 Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
+ *
+ * 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 */
diff --git a/arch/openrisc/include/asm/cmpxchg.h b/arch/openrisc/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..5fcb9ac72693
--- /dev/null
+++ b/arch/openrisc/include/asm/cmpxchg.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2014 Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
+ *
+ * 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 */
diff --git a/arch/openrisc/include/asm/cpuinfo.h b/arch/openrisc/include/asm/cpuinfo.h
index 917318b6a970..ec10679d6429 100644
--- a/arch/openrisc/include/asm/cpuinfo.h
+++ b/arch/openrisc/include/asm/cpuinfo.h
@@ -24,9 +24,11 @@ struct cpuinfo {
 
 	u32 icache_size;
 	u32 icache_block_size;
+	u32 icache_ways;
 
 	u32 dcache_size;
 	u32 dcache_block_size;
+	u32 dcache_ways;
 };
 
 extern struct cpuinfo cpuinfo;
diff --git a/arch/openrisc/include/asm/futex.h b/arch/openrisc/include/asm/futex.h
new file mode 100644
index 000000000000..778087341977
--- /dev/null
+++ b/arch/openrisc/include/asm/futex.h
@@ -0,0 +1,135 @@
+#ifndef __ASM_OPENRISC_FUTEX_H
+#define __ASM_OPENRISC_FUTEX_H
+
+#ifdef __KERNEL__
+
+#include <linux/futex.h>
+#include <linux/uaccess.h>
+#include <asm/errno.h>
+
+#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \
+({								\
+	__asm__ __volatile__ (					\
+		"1:	l.lwa	%0, %2			\n"	\
+			insn				"\n"	\
+		"2:	l.swa	%2, %1			\n"	\
+		"	l.bnf	1b			\n"	\
+		"	 l.ori	%1, r0, 0		\n"	\
+		"3:					\n"	\
+		".section .fixup,\"ax\"			\n"	\
+		"4:	l.j	3b			\n"	\
+		"	 l.addi	%1, r0, %3		\n"	\
+		".previous				\n"	\
+		".section __ex_table,\"a\"		\n"	\
+		".word	1b,4b,2b,4b			\n"	\
+		".previous				\n"	\
+		: "=&r" (oldval), "=&r" (ret), "+m" (*uaddr)	\
+		: "i" (-EFAULT), "r" (oparg)			\
+		: "cc", "memory"				\
+		);						\
+})
+
+static inline int
+futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+{
+	int op = (encoded_op >> 28) & 7;
+	int cmp = (encoded_op >> 24) & 15;
+	int oparg = (encoded_op << 8) >> 20;
+	int cmparg = (encoded_op << 20) >> 20;
+	int oldval = 0, ret;
+
+	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
+		oparg = 1 << oparg;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	pagefault_disable();
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		__futex_atomic_op("l.or %1,%4,%4", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ADD:
+		__futex_atomic_op("l.add %1,%0,%4", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_OR:
+		__futex_atomic_op("l.or %1,%0,%4", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ANDN:
+		__futex_atomic_op("l.and %1,%0,%4", ret, oldval, uaddr, ~oparg);
+		break;
+	case FUTEX_OP_XOR:
+		__futex_atomic_op("l.xor %1,%0,%4", ret, oldval, uaddr, oparg);
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	pagefault_enable();
+
+	if (!ret) {
+		switch (cmp) {
+		case FUTEX_OP_CMP_EQ:
+			ret = (oldval == cmparg);
+			break;
+		case FUTEX_OP_CMP_NE:
+			ret = (oldval != cmparg);
+			break;
+		case FUTEX_OP_CMP_LT:
+			ret = (oldval < cmparg);
+			break;
+		case FUTEX_OP_CMP_GE:
+			ret = (oldval >= cmparg);
+			break;
+		case FUTEX_OP_CMP_LE:
+			ret = (oldval <= cmparg);
+			break;
+		case FUTEX_OP_CMP_GT:
+			ret = (oldval > cmparg);
+			break;
+		default:
+			ret = -ENOSYS;
+		}
+	}
+	return ret;
+}
+
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	int ret = 0;
+	u32 prev;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	__asm__ __volatile__ (				\
+		"1:	l.lwa	%1, %2		\n"	\
+		"	l.sfeq	%1, %3		\n"	\
+		"	l.bnf	3f		\n"	\
+		"	 l.nop			\n"	\
+		"2:	l.swa	%2, %4		\n"	\
+		"	l.bnf	1b		\n"	\
+		"	 l.nop			\n"	\
+		"3:				\n"	\
+		".section .fixup,\"ax\"		\n"	\
+		"4:	l.j	3b		\n"	\
+		"	 l.addi	%0, r0, %5	\n"	\
+		".previous			\n"	\
+		".section __ex_table,\"a\"	\n"	\
+		".word	1b,4b,2b,4b		\n"	\
+		".previous			\n"	\
+		: "+r" (ret), "=&r" (prev), "+m" (*uaddr) \
+		: "r" (oldval), "r" (newval), "i" (-EFAULT) \
+		: "cc",	"memory"			\
+		);
+
+	*uval = prev;
+	return ret;
+}
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASM_OPENRISC_FUTEX_H */
diff --git a/arch/openrisc/include/asm/spr_defs.h b/arch/openrisc/include/asm/spr_defs.h
index 5dbc668865c4..367dac70326a 100644
--- a/arch/openrisc/include/asm/spr_defs.h
+++ b/arch/openrisc/include/asm/spr_defs.h
@@ -152,8 +152,8 @@
 #define SPR_UPR_MP	   0x00000020  /* MAC present */
 #define SPR_UPR_DUP	   0x00000040  /* Debug unit present */
 #define SPR_UPR_PCUP	   0x00000080  /* Performance counters unit present */
-#define SPR_UPR_PMP	   0x00000100  /* Power management present */
-#define SPR_UPR_PICP	   0x00000200  /* PIC present */
+#define SPR_UPR_PICP	   0x00000100  /* PIC present */
+#define SPR_UPR_PMP	   0x00000200  /* Power management present */
 #define SPR_UPR_TTP	   0x00000400  /* Tick timer present */
 #define SPR_UPR_RES	   0x00fe0000  /* Reserved */
 #define SPR_UPR_CUP	   0xff000000  /* Context units present */
diff --git a/arch/openrisc/include/asm/string.h b/arch/openrisc/include/asm/string.h
new file mode 100644
index 000000000000..64939ccd7531
--- /dev/null
+++ b/arch/openrisc/include/asm/string.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_OPENRISC_STRING_H
+#define __ASM_OPENRISC_STRING_H
+
+#define __HAVE_ARCH_MEMSET
+extern void *memset(void *s, int c, __kernel_size_t n);
+
+#define __HAVE_ARCH_MEMCPY
+extern void *memcpy(void *dest, __const void *src, __kernel_size_t n);
+
+#endif /* __ASM_OPENRISC_STRING_H */