Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-cpumask into merge-rr-cpumask

Conflicts:
	arch/x86/kernel/io_apic.c
	kernel/rcuclassic.c
	kernel/sched.c
	kernel/time/tick-sched.c

Signed-off-by: Mike Travis <travis@sgi.com>
[ mingo@elte.hu: backmerged typo fix for io_apic.c ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>

28 files changed, 703 insertions, 193 deletions

diff --git a/arch/sh/include/asm/addrspace.h b/arch/sh/include/asm/addrspace.h
index 2702d81bfc0d..36736c7e93db 100644
--- a/arch/sh/include/asm/addrspace.h
+++ b/arch/sh/include/asm/addrspace.h
@@ -49,5 +49,16 @@
 /* Check if an address can be reached in 29 bits */
 #define IS_29BIT(a)	(((unsigned long)(a)) < 0x20000000)
 
+#ifdef CONFIG_SH_STORE_QUEUES
+/*
+ * This is a special case for the SH-4 store queues, as pages for this
+ * space still need to be faulted in before it's possible to flush the
+ * store queue cache for writeout to the remapped region.
+ */
+#define P3_ADDR_MAX		(P4SEG_STORE_QUE + 0x04000000)
+#else
+#define P3_ADDR_MAX		P4SEG
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_SH_ADDRSPACE_H */
diff --git a/arch/sh/include/asm/bitops-grb.h b/arch/sh/include/asm/bitops-grb.h
index a5907b94395b..e73af33acbf4 100644
--- a/arch/sh/include/asm/bitops-grb.h
+++ b/arch/sh/include/asm/bitops-grb.h
@@ -166,4 +166,7 @@ static inline int test_and_change_bit(int nr, volatile void * addr)
 
         return retval;
 }
+
+#include <asm-generic/bitops/non-atomic.h>
+
 #endif /* __ASM_SH_BITOPS_GRB_H */
diff --git a/arch/sh/include/asm/bitops-irq.h b/arch/sh/include/asm/bitops-irq.h
deleted file mode 100644
index 653a12750584..000000000000
--- a/arch/sh/include/asm/bitops-irq.h
+++ /dev/null
@@ -1,91 +0,0 @@
-#ifndef __ASM_SH_BITOPS_IRQ_H
-#define __ASM_SH_BITOPS_IRQ_H
-
-static inline void set_bit(int nr, volatile void *addr)
-{
-	int	mask;
-	volatile unsigned int *a = addr;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	local_irq_save(flags);
-	*a |= mask;
-	local_irq_restore(flags);
-}
-
-static inline void clear_bit(int nr, volatile void *addr)
-{
-	int	mask;
-	volatile unsigned int *a = addr;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	local_irq_save(flags);
-	*a &= ~mask;
-	local_irq_restore(flags);
-}
-
-static inline void change_bit(int nr, volatile void *addr)
-{
-	int	mask;
-	volatile unsigned int *a = addr;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	local_irq_save(flags);
-	*a ^= mask;
-	local_irq_restore(flags);
-}
-
-static inline int test_and_set_bit(int nr, volatile void *addr)
-{
-	int	mask, retval;
-	volatile unsigned int *a = addr;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	local_irq_save(flags);
-	retval = (mask & *a) != 0;
-	*a |= mask;
-	local_irq_restore(flags);
-
-	return retval;
-}
-
-static inline int test_and_clear_bit(int nr, volatile void *addr)
-{
-	int	mask, retval;
-	volatile unsigned int *a = addr;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	local_irq_save(flags);
-	retval = (mask & *a) != 0;
-	*a &= ~mask;
-	local_irq_restore(flags);
-
-	return retval;
-}
-
-static inline int test_and_change_bit(int nr, volatile void *addr)
-{
-	int	mask, retval;
-	volatile unsigned int *a = addr;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	local_irq_save(flags);
-	retval = (mask & *a) != 0;
-	*a ^= mask;
-	local_irq_restore(flags);
-
-	return retval;
-}
-
-#endif /* __ASM_SH_BITOPS_IRQ_H */
diff --git a/arch/sh/include/asm/bitops-llsc.h b/arch/sh/include/asm/bitops-llsc.h
index 43b8e1a8239e..1d2fc0b010ad 100644
--- a/arch/sh/include/asm/bitops-llsc.h
+++ b/arch/sh/include/asm/bitops-llsc.h
@@ -141,4 +141,6 @@ static inline int test_and_change_bit(int nr, volatile void * addr)
 	return retval != 0;
 }
 
+#include <asm-generic/bitops/non-atomic.h>
+
 #endif /* __ASM_SH_BITOPS_LLSC_H */
diff --git a/arch/sh/include/asm/bitops-op32.h b/arch/sh/include/asm/bitops-op32.h
new file mode 100644
index 000000000000..f0ae7e9218e0
--- /dev/null
+++ b/arch/sh/include/asm/bitops-op32.h
@@ -0,0 +1,142 @@
+#ifndef __ASM_SH_BITOPS_OP32_H
+#define __ASM_SH_BITOPS_OP32_H
+
+/*
+ * The bit modifying instructions on SH-2A are only capable of working
+ * with a 3-bit immediate, which signifies the shift position for the bit
+ * being worked on.
+ */
+#if defined(__BIG_ENDIAN)
+#define BITOP_LE_SWIZZLE	((BITS_PER_LONG-1) & ~0x7)
+#define BYTE_NUMBER(nr)		((nr ^ BITOP_LE_SWIZZLE) / BITS_PER_BYTE)
+#define BYTE_OFFSET(nr)		((nr ^ BITOP_LE_SWIZZLE) % BITS_PER_BYTE)
+#else
+#define BYTE_NUMBER(nr)		((nr) / BITS_PER_BYTE)
+#define BYTE_OFFSET(nr)		((nr) % BITS_PER_BYTE)
+#endif
+
+#define IS_IMMEDIATE(nr)	(__builtin_constant_p(nr))
+
+static inline void __set_bit(int nr, volatile unsigned long *addr)
+{
+	if (IS_IMMEDIATE(nr)) {
+		__asm__ __volatile__ (
+			"bset.b %1, @(%O2,%0)		! __set_bit\n\t"
+			: "+r" (addr)
+			: "i" (BYTE_OFFSET(nr)), "i" (BYTE_NUMBER(nr))
+			: "t", "memory"
+		);
+	} else {
+		unsigned long mask = BIT_MASK(nr);
+		unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+		*p |= mask;
+	}
+}
+
+static inline void __clear_bit(int nr, volatile unsigned long *addr)
+{
+	if (IS_IMMEDIATE(nr)) {
+		__asm__ __volatile__ (
+			"bclr.b %1, @(%O2,%0)		! __clear_bit\n\t"
+			: "+r" (addr)
+			: "i" (BYTE_OFFSET(nr)),
+			  "i" (BYTE_NUMBER(nr))
+			: "t", "memory"
+		);
+	} else {
+		unsigned long mask = BIT_MASK(nr);
+		unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+		*p &= ~mask;
+	}
+}
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __change_bit(int nr, volatile unsigned long *addr)
+{
+	if (IS_IMMEDIATE(nr)) {
+		__asm__ __volatile__ (
+			"bxor.b %1, @(%O2,%0)		! __change_bit\n\t"
+			: "+r" (addr)
+			: "i" (BYTE_OFFSET(nr)),
+			  "i" (BYTE_NUMBER(nr))
+			: "t", "memory"
+		);
+	} else {
+		unsigned long mask = BIT_MASK(nr);
+		unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+		*p ^= mask;
+	}
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+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 = *p;
+
+	*p = old | mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+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 = *p;
+
+	*p = old & ~mask;
+	return (old & mask) != 0;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+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 = *p;
+
+	*p = old ^ mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline int test_bit(int nr, const volatile unsigned long *addr)
+{
+	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+#endif /* __ASM_SH_BITOPS_OP32_H */
diff --git a/arch/sh/include/asm/bitops.h b/arch/sh/include/asm/bitops.h
index 367930d8e5ae..ebe595b7ab1f 100644
--- a/arch/sh/include/asm/bitops.h
+++ b/arch/sh/include/asm/bitops.h
@@ -13,21 +13,22 @@
 
 #ifdef CONFIG_GUSA_RB
 #include <asm/bitops-grb.h>
+#elif defined(CONFIG_CPU_SH2A)
+#include <asm-generic/bitops/atomic.h>
+#include <asm/bitops-op32.h>
 #elif defined(CONFIG_CPU_SH4A)
 #include <asm/bitops-llsc.h>
 #else
-#include <asm/bitops-irq.h>
+#include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/non-atomic.h>
 #endif
 
-
 /*
  * clear_bit() doesn't provide any barrier for the compiler.
  */
 #define smp_mb__before_clear_bit()	barrier()
 #define smp_mb__after_clear_bit()	barrier()
 
-#include <asm-generic/bitops/non-atomic.h>
-
 #ifdef CONFIG_SUPERH32
 static inline unsigned long ffz(unsigned long word)
 {
diff --git a/arch/sh/include/asm/bugs.h b/arch/sh/include/asm/bugs.h
index 121b2ecddfc3..4924ff6f5439 100644
--- a/arch/sh/include/asm/bugs.h
+++ b/arch/sh/include/asm/bugs.h
@@ -25,7 +25,7 @@ static void __init check_bugs(void)
 	case CPU_SH7619:
 		*p++ = '2';
 		break;
-	case CPU_SH7203 ... CPU_MXG:
+	case CPU_SH7201 ... CPU_MXG:
 		*p++ = '2';
 		*p++ = 'a';
 		break;
diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h
index 9eb9036a1bdc..ccb1d93bb043 100644
--- a/arch/sh/include/asm/elf.h
+++ b/arch/sh/include/asm/elf.h
@@ -108,13 +108,11 @@ typedef struct user_fpu_struct elf_fpregset_t;
 #define elf_check_fdpic(x)		((x)->e_flags & EF_SH_FDPIC)
 #define elf_check_const_displacement(x)	((x)->e_flags & EF_SH_PIC)
 
-#ifdef CONFIG_SUPERH32
 /*
  * Enable dump using regset.
  * This covers all of general/DSP/FPU regs.
  */
 #define CORE_DUMP_USE_REGSET
-#endif
 
 #define USE_ELF_CORE_DUMP
 #define ELF_FDPIC_CORE_EFLAGS	EF_SH_FDPIC
@@ -204,7 +202,7 @@ do {									\
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES
 struct linux_binprm;
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
-				       int executable_stack);
+				       int uses_interp);
 
 extern unsigned int vdso_enabled;
 extern void __kernel_vsyscall;
diff --git a/arch/sh/include/asm/ftrace.h b/arch/sh/include/asm/ftrace.h
index 3aed362c9463..8fea7d8c8258 100644
--- a/arch/sh/include/asm/ftrace.h
+++ b/arch/sh/include/asm/ftrace.h
@@ -1,8 +1,34 @@
 #ifndef __ASM_SH_FTRACE_H
 #define __ASM_SH_FTRACE_H
 
+#ifdef CONFIG_FUNCTION_TRACER
+
+#define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
+
 #ifndef __ASSEMBLY__
 extern void mcount(void);
-#endif
+
+#define MCOUNT_ADDR		((long)(mcount))
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+#define CALLER_ADDR		((long)(ftrace_caller))
+#define STUB_ADDR		((long)(ftrace_stub))
+
+#define MCOUNT_INSN_OFFSET	((STUB_ADDR - CALLER_ADDR) >> 1)
+
+struct dyn_arch_ftrace {
+	/* No extra data needed on sh */
+};
+
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	/* 'addr' is the memory table address. */
+	return addr;
+}
+
+#endif /* __ASSEMBLY__ */
+#endif /* CONFIG_FUNCTION_TRACER */
 
 #endif /* __ASM_SH_FTRACE_H */
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index 65eaae34e753..61f6dae40534 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -260,6 +260,10 @@ __ioremap_mode(unsigned long offset, unsigned long size, unsigned long flags)
 
 		return (void __iomem *)P2SEGADDR(offset);
 	}
+
+	/* P4 above the store queues are always mapped. */
+	if (unlikely(offset >= P3_ADDR_MAX))
+		return (void __iomem *)P4SEGADDR(offset);
 #endif
 
 	return __ioremap(offset, size, flags);
diff --git a/arch/sh/include/asm/kgdb.h b/arch/sh/include/asm/kgdb.h
index 24e42078f36f..72704ed725e5 100644
--- a/arch/sh/include/asm/kgdb.h
+++ b/arch/sh/include/asm/kgdb.h
@@ -1,21 +1,7 @@
-/*
- * May be copied or modified under the terms of the GNU General Public
- * License.  See linux/COPYING for more information.
- *
- * Based on original code by Glenn Engel, Jim Kingdon,
- * David Grothe <dave@gcom.com>, Tigran Aivazian, <tigran@sco.com> and
- * Amit S. Kale <akale@veritas.com>
- * 
- * Super-H port based on sh-stub.c (Ben Lee and Steve Chamberlain) by
- * Henry Bell <henry.bell@st.com>
- * 
- * Header file for low-level support for remote debug using GDB. 
- *
- */
-
-#ifndef __KGDB_H
-#define __KGDB_H
+#ifndef __ASM_SH_KGDB_H
+#define __ASM_SH_KGDB_H
 
+#include <asm/cacheflush.h>
 #include <asm/ptrace.h>
 
 /* Same as pt_regs but has vbr in place of syscall_nr */
@@ -30,40 +16,26 @@ struct kgdb_regs {
         unsigned long vbr;
 };
 
-/* State info */
-extern char kgdb_in_gdb_mode;
-extern int kgdb_nofault;	/* Ignore bus errors (in gdb mem access) */
-extern char in_nmi;		/* Debounce flag to prevent NMI reentry*/
+enum regnames {
+	GDB_R0, GDB_R1, GDB_R2, GDB_R3, GDB_R4, GDB_R5, GDB_R6, GDB_R7,
+	GDB_R8, GDB_R9, GDB_R10, GDB_R11, GDB_R12, GDB_R13, GDB_R14, GDB_R15,
 
-/* SCI */
-extern int kgdb_portnum;
-extern int kgdb_baud;
-extern char kgdb_parity;
-extern char kgdb_bits;
+	GDB_PC, GDB_PR, GDB_SR, GDB_GBR, GDB_MACH, GDB_MACL, GDB_VBR,
+};
 
-/* Init and interface stuff */
-extern int kgdb_init(void);
-extern int (*kgdb_getchar)(void);
-extern void (*kgdb_putchar)(int);
+#define NUMREGBYTES    ((GDB_VBR + 1) * 4)
 
-/* Trap functions */
-typedef void (kgdb_debug_hook_t)(struct pt_regs *regs);
-typedef void (kgdb_bus_error_hook_t)(void);
-extern kgdb_debug_hook_t  *kgdb_debug_hook;
-extern kgdb_bus_error_hook_t *kgdb_bus_err_hook;
+static inline void arch_kgdb_breakpoint(void)
+{
+	__asm__ __volatile__ ("trapa #0x3c\n");
+}
 
-/* Console */
-struct console;
-void kgdb_console_write(struct console *co, const char *s, unsigned count);
-extern int kgdb_console_setup(struct console *, char *);
+/* State info */
+extern char in_nmi;		/* Debounce flag to prevent NMI reentry*/
 
-/* Prototypes for jmp fns */
-#define _JBLEN 9
-typedef        int jmp_buf[_JBLEN];
-extern void    longjmp(jmp_buf __jmpb, int __retval);
-extern int     setjmp(jmp_buf __jmpb);
+#define BUFMAX                 2048
 
-/* Forced breakpoint */
-#define breakpoint()	__asm__ __volatile__("trapa   #0x3c")
+#define CACHE_FLUSH_IS_SAFE	1
+#define BREAK_INSTR_SIZE	2
 
-#endif
+#endif /* __ASM_SH_KGDB_H */
diff --git a/arch/sh/include/asm/machvec.h b/arch/sh/include/asm/machvec.h
index f1bae02ef7b6..64b1c16a0f03 100644
--- a/arch/sh/include/asm/machvec.h
+++ b/arch/sh/include/asm/machvec.h
@@ -14,8 +14,6 @@
 #include <linux/time.h>
 #include <asm/machtypes.h>
 
-struct device;
-
 struct sh_machine_vector {
 	void (*mv_setup)(char **cmdline_p);
 	const char *mv_name;
@@ -45,9 +43,6 @@ struct sh_machine_vector {
 	int (*mv_irq_demux)(int irq);
 
 	void (*mv_init_irq)(void);
-	void (*mv_init_pci)(void);
-
-	void (*mv_heartbeat)(void);
 
 	void __iomem *(*mv_ioport_map)(unsigned long port, unsigned int size);
 	void (*mv_ioport_unmap)(void __iomem *);
diff --git a/arch/sh/include/asm/mmu_context.h b/arch/sh/include/asm/mmu_context.h
index 04c0c9733ad6..5d9157bd474d 100644
--- a/arch/sh/include/asm/mmu_context.h
+++ b/arch/sh/include/asm/mmu_context.h
@@ -22,7 +22,7 @@
 #define MMU_CONTEXT_ASID_MASK		0x000000ff
 #define MMU_CONTEXT_VERSION_MASK	0xffffff00
 #define MMU_CONTEXT_FIRST_VERSION	0x00000100
-#define NO_CONTEXT			0
+#define NO_CONTEXT			0UL
 
 /* ASID is 8-bit value, so it can't be 0x100 */
 #define MMU_NO_ASID			0x100
@@ -130,7 +130,7 @@ static inline void switch_mm(struct mm_struct *prev,
 #define destroy_context(mm)		do { } while (0)
 #define set_asid(asid)			do { } while (0)
 #define get_asid()			(0)
-#define cpu_asid(cpu, mm)		({ (void)cpu; 0; })
+#define cpu_asid(cpu, mm)		({ (void)cpu; NO_CONTEXT; })
 #define switch_and_save_asid(asid)	(0)
 #define set_TTB(pgd)			do { } while (0)
 #define get_TTB()			(0)
diff --git a/arch/sh/include/asm/mutex-llsc.h b/arch/sh/include/asm/mutex-llsc.h
new file mode 100644
index 000000000000..ee839ee58ac8
--- /dev/null
+++ b/arch/sh/include/asm/mutex-llsc.h
@@ -0,0 +1,112 @@
+/*
+ * arch/sh/include/asm/mutex-llsc.h
+ *
+ * SH-4A optimized mutex locking primitives
+ *
+ * Please look into asm-generic/mutex-xchg.h for a formal definition.
+ */
+#ifndef __ASM_SH_MUTEX_LLSC_H
+#define __ASM_SH_MUTEX_LLSC_H
+
+/*
+ * Attempting to lock a mutex on SH4A is done like in ARMv6+ architecure.
+ * with a bastardized atomic decrement (it is not a reliable atomic decrement
+ * but it satisfies the defined semantics for our purpose, while being
+ * smaller and faster than a real atomic decrement or atomic swap.
+ * The idea is to attempt  decrementing the lock value only once. If once
+ * decremented it isn't zero, or if its store-back fails due to a dispute
+ * on the exclusive store, we simply bail out immediately through the slow
+ * path where the lock will be reattempted until it succeeds.
+ */
+static inline void
+__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+	int __ex_flag, __res;
+
+	__asm__ __volatile__ (
+		"movli.l	@%2, %0	\n"
+		"add		#-1, %0	\n"
+		"movco.l	%0, @%2	\n"
+		"movt		%1	\n"
+		: "=&z" (__res), "=&r" (__ex_flag)
+		: "r" (&(count)->counter)
+		: "t");
+
+	__res |= !__ex_flag;
+	if (unlikely(__res != 0))
+		fail_fn(count);
+}
+
+static inline int
+__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+	int __ex_flag, __res;
+
+	__asm__ __volatile__ (
+		"movli.l	@%2, %0	\n"
+		"add		#-1, %0	\n"
+		"movco.l	%0, @%2	\n"
+		"movt		%1	\n"
+		: "=&z" (__res), "=&r" (__ex_flag)
+		: "r" (&(count)->counter)
+		: "t");
+
+	__res |= !__ex_flag;
+	if (unlikely(__res != 0))
+		__res = fail_fn(count);
+
+	return __res;
+}
+
+static inline void
+__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+	int __ex_flag, __res;
+
+	__asm__ __volatile__ (
+		"movli.l	@%2, %0	\n\t"
+		"add		#1, %0	\n\t"
+		"movco.l	%0, @%2 \n\t"
+		"movt		%1	\n\t"
+		: "=&z" (__res), "=&r" (__ex_flag)
+		: "r" (&(count)->counter)
+		: "t");
+
+	__res |= !__ex_flag;
+	if (unlikely(__res <= 0))
+		fail_fn(count);
+}
+
+/*
+ * If the unlock was done on a contended lock, or if the unlock simply fails
+ * then the mutex remains locked.
+ */
+#define __mutex_slowpath_needs_to_unlock()	1
+
+/*
+ * For __mutex_fastpath_trylock we do an atomic decrement and check the
+ * result and put it in the __res variable.
+ */
+static inline int
+__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+	int __res, __orig;
+
+	__asm__ __volatile__ (
+		"1: movli.l	@%2, %0		\n\t"
+		"dt		%0		\n\t"
+		"movco.l	%0,@%2		\n\t"
+		"bf		1b		\n\t"
+		"cmp/eq		#0,%0		\n\t"
+		"bt		2f		\n\t"
+		"mov		#0, %1		\n\t"
+		"bf		3f		\n\t"
+		"2: mov		#1, %1		\n\t"
+		"3:				"
+		: "=&z" (__orig), "=&r" (__res)
+		: "r" (&count->counter)
+		: "t");
+
+	return __res;
+}
+#endif /* __ASM_SH_MUTEX_LLSC_H */
diff --git a/arch/sh/include/asm/mutex.h b/arch/sh/include/asm/mutex.h
index 458c1f7fbc18..d8e37716a4a0 100644
--- a/arch/sh/include/asm/mutex.h
+++ b/arch/sh/include/asm/mutex.h
@@ -5,5 +5,8 @@
  * implementation in place, or pick the atomic_xchg() based generic
  * implementation. (see asm-generic/mutex-xchg.h for details)
  */
-
+#if defined(CONFIG_CPU_SH4A)
+#include <asm/mutex-llsc.h>
+#else
 #include <asm-generic/mutex-dec.h>
+#endif
diff --git a/arch/sh/include/asm/pm.h b/arch/sh/include/asm/pm.h
deleted file mode 100644
index 56fdbd6b1c94..000000000000
--- a/arch/sh/include/asm/pm.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright 2006 (c) Andriy Skulysh <askulysh@gmail.com>
- *
- */
-#ifndef __ASM_SH_PM_H
-#define __ASM_SH_PM_H
-
-extern u8 wakeup_start;
-extern u8 wakeup_end;
-
-void pm_enter(void);
-
-#endif
diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h
index 693364a20ad7..1ef4b24d7619 100644
--- a/arch/sh/include/asm/processor.h
+++ b/arch/sh/include/asm/processor.h
@@ -18,7 +18,7 @@ enum cpu_type {
 	CPU_SH7619,
 
 	/* SH-2A types */
-	CPU_SH7203, CPU_SH7206, CPU_SH7263, CPU_MXG,
+	CPU_SH7201, CPU_SH7203, CPU_SH7206, CPU_SH7263, CPU_MXG,
 
 	/* SH-3 types */
 	CPU_SH7705, CPU_SH7706, CPU_SH7707,
@@ -82,6 +82,9 @@ extern struct sh_cpuinfo cpu_data[];
 #define current_cpu_data cpu_data[smp_processor_id()]
 #define raw_current_cpu_data cpu_data[raw_smp_processor_id()]
 
+#define cpu_sleep()	__asm__ __volatile__ ("sleep" : : : "memory")
+#define cpu_relax()	barrier()
+
 /* Forward decl */
 struct seq_operations;
 
diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h
index a46a0207e977..d79063c5eb9c 100644
--- a/arch/sh/include/asm/processor_32.h
+++ b/arch/sh/include/asm/processor_32.h
@@ -175,6 +175,15 @@ static __inline__ void enable_fpu(void)
 
 void show_trace(struct task_struct *tsk, unsigned long *sp,
 		struct pt_regs *regs);
+
+#ifdef CONFIG_DUMP_CODE
+void show_code(struct pt_regs *regs);
+#else
+static inline void show_code(struct pt_regs *regs)
+{
+}
+#endif
+
 extern unsigned long get_wchan(struct task_struct *p);
 
 #define KSTK_EIP(tsk)  (task_pt_regs(tsk)->pc)
@@ -182,9 +191,6 @@ extern unsigned long get_wchan(struct task_struct *p);
 
 #define user_stack_pointer(regs)	((regs)->regs[15])
 
-#define cpu_sleep()	__asm__ __volatile__ ("sleep" : : : "memory")
-#define cpu_relax()	barrier()
-
 #if defined(CONFIG_CPU_SH2A) || defined(CONFIG_CPU_SH3) || \
     defined(CONFIG_CPU_SH4)
 #define PREFETCH_STRIDE		L1_CACHE_BYTES
diff --git a/arch/sh/include/asm/processor_64.h b/arch/sh/include/asm/processor_64.h
index b0b4824dfc4c..803177fcf086 100644
--- a/arch/sh/include/asm/processor_64.h
+++ b/arch/sh/include/asm/processor_64.h
@@ -226,9 +226,7 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define KSTK_EIP(tsk)  ((tsk)->thread.pc)
 #define KSTK_ESP(tsk)  ((tsk)->thread.sp)
 
-#define user_stack_pointer(regs)	((regs)->sp)
-
-#define cpu_relax()	barrier()
+#define user_stack_pointer(regs)	((regs)->regs[15])
 
 #endif	/* __ASSEMBLY__ */
 #endif /* __ASM_SH_PROCESSOR_64_H */
diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h
index 3ad18e91bca6..12912ab80c15 100644
--- a/arch/sh/include/asm/ptrace.h
+++ b/arch/sh/include/asm/ptrace.h
@@ -86,6 +86,7 @@ struct pt_dspregs {
 	unsigned long	re;
 	unsigned long	mod;
 };
+#endif
 
 #define PTRACE_GETREGS		12	/* General registers */
 #define PTRACE_SETREGS		13
@@ -100,7 +101,6 @@ struct pt_dspregs {
 
 #define	PTRACE_GETDSPREGS	55	/* DSP registers */
 #define	PTRACE_SETDSPREGS	56
-#endif
 
 #ifdef __KERNEL__
 #include <asm/addrspace.h>
diff --git a/arch/sh/include/asm/sh_bios.h b/arch/sh/include/asm/sh_bios.h
index 0ca261956e3d..d9c96d7cf6c7 100644
--- a/arch/sh/include/asm/sh_bios.h
+++ b/arch/sh/include/asm/sh_bios.h
@@ -10,7 +10,6 @@
 
 extern void sh_bios_console_write(const char *buf, unsigned int len);
 extern void sh_bios_char_out(char ch);
-extern int sh_bios_in_gdb_mode(void);
 extern void sh_bios_gdb_detach(void);
 
 extern void sh_bios_get_node_addr(unsigned char *node_addr);
diff --git a/arch/sh/include/asm/string_64.h b/arch/sh/include/asm/string_64.h
index aa1fef229c78..742007172624 100644
--- a/arch/sh/include/asm/string_64.h
+++ b/arch/sh/include/asm/string_64.h
@@ -1,17 +1,20 @@
 #ifndef __ASM_SH_STRING_64_H
 #define __ASM_SH_STRING_64_H
 
-/*
- * include/asm-sh/string_64.h
- *
- * Copyright (C) 2000, 2001  Paolo Alberelli
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
+#ifdef __KERNEL__
+
+#define __HAVE_ARCH_MEMSET
+extern void *memset(void *__s, int __c, size_t __count);
 
 #define __HAVE_ARCH_MEMCPY
 extern void *memcpy(void *dest, const void *src, size_t count);
 
+#define __HAVE_ARCH_STRLEN
+extern size_t strlen(const char *);
+
+#define __HAVE_ARCH_STRCPY
+extern char *strcpy(char *__dest, const char *__src);
+
+#endif /* __KERNEL__ */
+
 #endif /* __ASM_SH_STRING_64_H */
diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h
index 54773f26cd44..05a868a71ef5 100644
--- a/arch/sh/include/asm/syscall_32.h
+++ b/arch/sh/include/asm/syscall_32.h
@@ -5,7 +5,7 @@
 #include <linux/sched.h>
 #include <asm/ptrace.h>
 
-/* The system call number is given by the user in %g1 */
+/* The system call number is given by the user in R3 */
 static inline long syscall_get_nr(struct task_struct *task,
 				  struct pt_regs *regs)
 {
diff --git a/arch/sh/include/asm/syscall_64.h b/arch/sh/include/asm/syscall_64.h
index bcaaa8ca4d70..e1143b9784d6 100644
--- a/arch/sh/include/asm/syscall_64.h
+++ b/arch/sh/include/asm/syscall_64.h
@@ -1,6 +1,80 @@
 #ifndef __ASM_SH_SYSCALL_64_H
 #define __ASM_SH_SYSCALL_64_H
 
-#include <asm-generic/syscall.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <asm/ptrace.h>
+
+/* The system call number is given by the user in R9 */
+static inline long syscall_get_nr(struct task_struct *task,
+				  struct pt_regs *regs)
+{
+	return (regs->syscall_nr >= 0) ? regs->regs[9] : -1L;
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+				    struct pt_regs *regs)
+{
+	/*
+	 * XXX: This needs some thought. On SH we don't
+	 * save away the original R9 value anywhere.
+	 */
+}
+
+static inline bool syscall_has_error(struct pt_regs *regs)
+{
+	return (regs->sr & 0x1) ? true : false;
+}
+static inline void syscall_set_error(struct pt_regs *regs)
+{
+	regs->sr |= 0x1;
+}
+static inline void syscall_clear_error(struct pt_regs *regs)
+{
+	regs->sr &= ~0x1;
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	return syscall_has_error(regs) ? regs->regs[9] : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	return regs->regs[9];
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+					    struct pt_regs *regs,
+					    int error, long val)
+{
+	if (error) {
+		syscall_set_error(regs);
+		regs->regs[9] = -error;
+	} else {
+		syscall_clear_error(regs);
+		regs->regs[9] = val;
+	}
+}
+
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 unsigned long *args)
+{
+	BUG_ON(i + n > 6);
+	memcpy(args, &regs->regs[2 + i], n * sizeof(args[0]));
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 const unsigned long *args)
+{
+	BUG_ON(i + n > 6);
+	memcpy(&regs->regs[2 + i], args, n * sizeof(args[0]));
+}
 
 #endif /* __ASM_SH_SYSCALL_64_H */
diff --git a/arch/sh/include/asm/system.h b/arch/sh/include/asm/system.h
index 6160fe445161..c9ec6af8e745 100644
--- a/arch/sh/include/asm/system.h
+++ b/arch/sh/include/asm/system.h
@@ -175,6 +175,8 @@ asmlinkage void name##_trap_handler(unsigned int vec, struct pt_regs *regs)
 BUILD_TRAP_HANDLER(address_error);
 BUILD_TRAP_HANDLER(debug);
 BUILD_TRAP_HANDLER(bug);
+BUILD_TRAP_HANDLER(breakpoint);
+BUILD_TRAP_HANDLER(singlestep);
 BUILD_TRAP_HANDLER(fpu_error);
 BUILD_TRAP_HANDLER(fpu_state_restore);
 
diff --git a/arch/sh/include/asm/topology.h b/arch/sh/include/asm/topology.h
index 279d9cc4a007..066f0fba590e 100644
--- a/arch/sh/include/asm/topology.h
+++ b/arch/sh/include/asm/topology.h
@@ -32,6 +32,7 @@
 #define parent_node(node)	((void)(node),0)
 
 #define node_to_cpumask(node)	((void)node, cpu_online_map)
+#define cpumask_of_node(node)	((void)node, cpu_online_mask)
 #define node_to_first_cpu(node)	((void)(node),0)
 
 #define pcibus_to_node(bus)	((void)(bus), -1)
diff --git a/arch/sh/include/asm/unaligned-sh4a.h b/arch/sh/include/asm/unaligned-sh4a.h
new file mode 100644
index 000000000000..d8f89770275b
--- /dev/null
+++ b/arch/sh/include/asm/unaligned-sh4a.h
@@ -0,0 +1,258 @@
+#ifndef __ASM_SH_UNALIGNED_SH4A_H
+#define __ASM_SH_UNALIGNED_SH4A_H
+
+/*
+ * SH-4A has support for unaligned 32-bit loads, and 32-bit loads only.
+ * Support for 16 and 64-bit accesses are done through shifting and
+ * masking relative to the endianness. Unaligned stores are not supported
+ * by the instruction encoding, so these continue to use the packed
+ * struct.
+ *
+ * The same note as with the movli.l/movco.l pair applies here, as long
+ * as the load is gauranteed to be inlined, nothing else will hook in to
+ * r0 and we get the return value for free.
+ *
+ * NOTE: Due to the fact we require r0 encoding, care should be taken to
+ * avoid mixing these heavily with other r0 consumers, such as the atomic
+ * ops. Failure to adhere to this can result in the compiler running out
+ * of spill registers and blowing up when building at low optimization
+ * levels. See http://gcc.gnu.org/bugzilla/show_bug.cgi?id=34777.
+ */
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+static __always_inline u32 __get_unaligned_cpu32(const u8 *p)
+{
+	unsigned long unaligned;
+
+	__asm__ __volatile__ (
+		"movua.l	@%1, %0\n\t"
+		 : "=z" (unaligned)
+		 : "r" (p)
+	);
+
+	return unaligned;
+}
+
+struct __una_u16 { u16 x __attribute__((packed)); };
+struct __una_u32 { u32 x __attribute__((packed)); };
+struct __una_u64 { u64 x __attribute__((packed)); };
+
+static inline u16 __get_unaligned_cpu16(const u8 *p)
+{
+#ifdef __LITTLE_ENDIAN
+	return __get_unaligned_cpu32(p) & 0xffff;
+#else
+	return __get_unaligned_cpu32(p) >> 16;
+#endif
+}
+
+/*
+ * Even though movua.l supports auto-increment on the read side, it can
+ * only store to r0 due to instruction encoding constraints, so just let
+ * the compiler sort it out on its own.
+ */
+static inline u64 __get_unaligned_cpu64(const u8 *p)
+{
+#ifdef __LITTLE_ENDIAN
+	return (u64)__get_unaligned_cpu32(p + 4) << 32 |
+		    __get_unaligned_cpu32(p);
+#else
+	return (u64)__get_unaligned_cpu32(p) << 32 |
+		    __get_unaligned_cpu32(p + 4);
+#endif
+}
+
+static inline u16 get_unaligned_le16(const void *p)
+{
+	return le16_to_cpu(__get_unaligned_cpu16(p));
+}
+
+static inline u32 get_unaligned_le32(const void *p)
+{
+	return le32_to_cpu(__get_unaligned_cpu32(p));
+}
+
+static inline u64 get_unaligned_le64(const void *p)
+{
+	return le64_to_cpu(__get_unaligned_cpu64(p));
+}
+
+static inline u16 get_unaligned_be16(const void *p)
+{
+	return be16_to_cpu(__get_unaligned_cpu16(p));
+}
+
+static inline u32 get_unaligned_be32(const void *p)
+{
+	return be32_to_cpu(__get_unaligned_cpu32(p));
+}
+
+static inline u64 get_unaligned_be64(const void *p)
+{
+	return be64_to_cpu(__get_unaligned_cpu64(p));
+}
+
+static inline void __put_le16_noalign(u8 *p, u16 val)
+{
+	*p++ = val;
+	*p++ = val >> 8;
+}
+
+static inline void __put_le32_noalign(u8 *p, u32 val)
+{
+	__put_le16_noalign(p, val);
+	__put_le16_noalign(p + 2, val >> 16);
+}
+
+static inline void __put_le64_noalign(u8 *p, u64 val)
+{
+	__put_le32_noalign(p, val);
+	__put_le32_noalign(p + 4, val >> 32);
+}
+
+static inline void __put_be16_noalign(u8 *p, u16 val)
+{
+	*p++ = val >> 8;
+	*p++ = val;
+}
+
+static inline void __put_be32_noalign(u8 *p, u32 val)
+{
+	__put_be16_noalign(p, val >> 16);
+	__put_be16_noalign(p + 2, val);
+}
+
+static inline void __put_be64_noalign(u8 *p, u64 val)
+{
+	__put_be32_noalign(p, val >> 32);
+	__put_be32_noalign(p + 4, val);
+}
+
+static inline void put_unaligned_le16(u16 val, void *p)
+{
+#ifdef __LITTLE_ENDIAN
+	((struct __una_u16 *)p)->x = val;
+#else
+	__put_le16_noalign(p, val);
+#endif
+}
+
+static inline void put_unaligned_le32(u32 val, void *p)
+{
+#ifdef __LITTLE_ENDIAN
+	((struct __una_u32 *)p)->x = val;
+#else
+	__put_le32_noalign(p, val);
+#endif
+}
+
+static inline void put_unaligned_le64(u64 val, void *p)
+{
+#ifdef __LITTLE_ENDIAN
+	((struct __una_u64 *)p)->x = val;
+#else
+	__put_le64_noalign(p, val);
+#endif
+}
+
+static inline void put_unaligned_be16(u16 val, void *p)
+{
+#ifdef __BIG_ENDIAN
+	((struct __una_u16 *)p)->x = val;
+#else
+	__put_be16_noalign(p, val);
+#endif
+}
+
+static inline void put_unaligned_be32(u32 val, void *p)
+{
+#ifdef __BIG_ENDIAN
+	((struct __una_u32 *)p)->x = val;
+#else
+	__put_be32_noalign(p, val);
+#endif
+}
+
+static inline void put_unaligned_be64(u64 val, void *p)
+{
+#ifdef __BIG_ENDIAN
+	((struct __una_u64 *)p)->x = val;
+#else
+	__put_be64_noalign(p, val);
+#endif
+}
+
+/*
+ * Cause a link-time error if we try an unaligned access other than
+ * 1,2,4 or 8 bytes long
+ */
+extern void __bad_unaligned_access_size(void);
+
+#define __get_unaligned_le(ptr) ((__force typeof(*(ptr)))({			\
+	__builtin_choose_expr(sizeof(*(ptr)) == 1, *(ptr),			\
+	__builtin_choose_expr(sizeof(*(ptr)) == 2, get_unaligned_le16((ptr)),	\
+	__builtin_choose_expr(sizeof(*(ptr)) == 4, get_unaligned_le32((ptr)),	\
+	__builtin_choose_expr(sizeof(*(ptr)) == 8, get_unaligned_le64((ptr)),	\
+	__bad_unaligned_access_size()))));					\
+	}))
+
+#define __get_unaligned_be(ptr) ((__force typeof(*(ptr)))({			\
+	__builtin_choose_expr(sizeof(*(ptr)) == 1, *(ptr),			\
+	__builtin_choose_expr(sizeof(*(ptr)) == 2, get_unaligned_be16((ptr)),	\
+	__builtin_choose_expr(sizeof(*(ptr)) == 4, get_unaligned_be32((ptr)),	\
+	__builtin_choose_expr(sizeof(*(ptr)) == 8, get_unaligned_be64((ptr)),	\
+	__bad_unaligned_access_size()))));					\
+	}))
+
+#define __put_unaligned_le(val, ptr) ({					\
+	void *__gu_p = (ptr);						\
+	switch (sizeof(*(ptr))) {					\
+	case 1:								\
+		*(u8 *)__gu_p = (__force u8)(val);			\
+		break;							\
+	case 2:								\
+		put_unaligned_le16((__force u16)(val), __gu_p);		\
+		break;							\
+	case 4:								\
+		put_unaligned_le32((__force u32)(val), __gu_p);		\
+		break;							\
+	case 8:								\
+		put_unaligned_le64((__force u64)(val), __gu_p);		\
+		break;							\
+	default:							\
+		__bad_unaligned_access_size();				\
+		break;							\
+	}								\
+	(void)0; })
+
+#define __put_unaligned_be(val, ptr) ({					\
+	void *__gu_p = (ptr);						\
+	switch (sizeof(*(ptr))) {					\
+	case 1:								\
+		*(u8 *)__gu_p = (__force u8)(val);			\
+		break;							\
+	case 2:								\
+		put_unaligned_be16((__force u16)(val), __gu_p);		\
+		break;							\
+	case 4:								\
+		put_unaligned_be32((__force u32)(val), __gu_p);		\
+		break;							\
+	case 8:								\
+		put_unaligned_be64((__force u64)(val), __gu_p);		\
+		break;							\
+	default:							\
+		__bad_unaligned_access_size();				\
+		break;							\
+	}								\
+	(void)0; })
+
+#ifdef __LITTLE_ENDIAN
+# define get_unaligned __get_unaligned_le
+# define put_unaligned __put_unaligned_le
+#else
+# define get_unaligned __get_unaligned_be
+# define put_unaligned __put_unaligned_be
+#endif
+
+#endif /* __ASM_SH_UNALIGNED_SH4A_H */
diff --git a/arch/sh/include/asm/unaligned.h b/arch/sh/include/asm/unaligned.h
index c1641a01d50f..8c0ad5e4487a 100644
--- a/arch/sh/include/asm/unaligned.h
+++ b/arch/sh/include/asm/unaligned.h
@@ -1,7 +1,11 @@
 #ifndef _ASM_SH_UNALIGNED_H
 #define _ASM_SH_UNALIGNED_H
 
-/* SH can't handle unaligned accesses. */
+#ifdef CONFIG_CPU_SH4A
+/* SH-4A can handle unaligned loads in a relatively neutered fashion. */
+#include <asm/unaligned-sh4a.h>
+#else
+/* Otherwise, SH can't handle unaligned accesses. */
 #ifdef __LITTLE_ENDIAN__
 # include <linux/unaligned/le_struct.h>
 # include <linux/unaligned/be_byteshift.h>
@@ -15,5 +19,6 @@
 # define get_unaligned	__get_unaligned_be
 # define put_unaligned	__put_unaligned_be
 #endif
+#endif
 
 #endif /* _ASM_SH_UNALIGNED_H */