Merge tag 'split-asm_system_h-for-linus-20120328' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-asm_system

Pull "Disintegrate and delete asm/system.h" from David Howells:
 "Here are a bunch of patches to disintegrate asm/system.h into a set of
  separate bits to relieve the problem of circular inclusion
  dependencies.

  I've built all the working defconfigs from all the arches that I can
  and made sure that they don't break.

  The reason for these patches is that I recently encountered a circular
  dependency problem that came about when I produced some patches to
  optimise get_order() by rewriting it to use ilog2().

  This uses bitops - and on the SH arch asm/bitops.h drags in
  asm-generic/get_order.h by a circuituous route involving asm/system.h.

  The main difficulty seems to be asm/system.h.  It holds a number of
  low level bits with no/few dependencies that are commonly used (eg.
  memory barriers) and a number of bits with more dependencies that
  aren't used in many places (eg.  switch_to()).

  These patches break asm/system.h up into the following core pieces:

    (1) asm/barrier.h

        Move memory barriers here.  This already done for MIPS and Alpha.

    (2) asm/switch_to.h

        Move switch_to() and related stuff here.

    (3) asm/exec.h

        Move arch_align_stack() here.  Other process execution related bits
        could perhaps go here from asm/processor.h.

    (4) asm/cmpxchg.h

        Move xchg() and cmpxchg() here as they're full word atomic ops and
        frequently used by atomic_xchg() and atomic_cmpxchg().

    (5) asm/bug.h

        Move die() and related bits.

    (6) asm/auxvec.h

        Move AT_VECTOR_SIZE_ARCH here.

  Other arch headers are created as needed on a per-arch basis."

Fixed up some conflicts from other header file cleanups and moving code
around that has happened in the meantime, so David's testing is somewhat
weakened by that.  We'll find out anything that got broken and fix it..

* tag 'split-asm_system_h-for-linus-20120328' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-asm_system: (38 commits)
  Delete all instances of asm/system.h
  Remove all #inclusions of asm/system.h
  Add #includes needed to permit the removal of asm/system.h
  Move all declarations of free_initmem() to linux/mm.h
  Disintegrate asm/system.h for OpenRISC
  Split arch_align_stack() out from asm-generic/system.h
  Split the switch_to() wrapper out of asm-generic/system.h
  Move the asm-generic/system.h xchg() implementation to asm-generic/cmpxchg.h
  Create asm-generic/barrier.h
  Make asm-generic/cmpxchg.h #include asm-generic/cmpxchg-local.h
  Disintegrate asm/system.h for Xtensa
  Disintegrate asm/system.h for Unicore32 [based on ver #3, changed by gxt]
  Disintegrate asm/system.h for Tile
  Disintegrate asm/system.h for Sparc
  Disintegrate asm/system.h for SH
  Disintegrate asm/system.h for Score
  Disintegrate asm/system.h for S390
  Disintegrate asm/system.h for PowerPC
  Disintegrate asm/system.h for PA-RISC
  Disintegrate asm/system.h for MN10300
  ...

1 files changed, 131 insertions, 0 deletions

diff --git a/arch/xtensa/include/asm/cmpxchg.h b/arch/xtensa/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..e32149063d83
--- /dev/null
+++ b/arch/xtensa/include/asm/cmpxchg.h
@@ -0,0 +1,131 @@
+/*
+ * Atomic xchg and cmpxchg operations.
+ *
+ * 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 (C) 2001 - 2005 Tensilica Inc.
+ */
+
+#ifndef _XTENSA_CMPXCHG_H
+#define _XTENSA_CMPXCHG_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/stringify.h>
+
+/*
+ * cmpxchg
+ */
+
+static inline unsigned long
+__cmpxchg_u32(volatile int *p, int old, int new)
+{
+  __asm__ __volatile__("rsil    a15, "__stringify(LOCKLEVEL)"\n\t"
+		       "l32i    %0, %1, 0              \n\t"
+		       "bne	%0, %2, 1f             \n\t"
+		       "s32i    %3, %1, 0              \n\t"
+		       "1:                             \n\t"
+		       "wsr     a15, "__stringify(PS)" \n\t"
+		       "rsync                          \n\t"
+		       : "=&a" (old)
+		       : "a" (p), "a" (old), "r" (new)
+		       : "a15", "memory");
+  return old;
+}
+/* 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);
+
+static __inline__ unsigned long
+__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
+{
+	switch (size) {
+	case 4:  return __cmpxchg_u32(ptr, old, new);
+	default: __cmpxchg_called_with_bad_pointer();
+		 return old;
+	}
+}
+
+#define cmpxchg(ptr,o,n)						      \
+	({ __typeof__(*(ptr)) _o_ = (o);				      \
+	   __typeof__(*(ptr)) _n_ = (n);				      \
+	   (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,	      \
+	   			        (unsigned long)_n_, sizeof (*(ptr))); \
+	})
+
+#include <asm-generic/cmpxchg-local.h>
+
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+				      unsigned long old,
+				      unsigned long new, int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32(ptr, old, new);
+	default:
+		return __cmpxchg_local_generic(ptr, old, new, size);
+	}
+
+	return old;
+}
+
+/*
+ * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
+ * them available.
+ */
+#define cmpxchg_local(ptr, o, n)				  	       \
+	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
+			(unsigned long)(n), sizeof(*(ptr))))
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+
+/*
+ * xchg_u32
+ *
+ * Note that a15 is used here because the register allocation
+ * done by the compiler is not guaranteed and a window overflow
+ * may not occur between the rsil and wsr instructions. By using
+ * a15 in the rsil, the machine is guaranteed to be in a state
+ * where no register reference will cause an overflow.
+ */
+
+static inline unsigned long xchg_u32(volatile int * m, unsigned long val)
+{
+  unsigned long tmp;
+  __asm__ __volatile__("rsil    a15, "__stringify(LOCKLEVEL)"\n\t"
+		       "l32i    %0, %1, 0              \n\t"
+		       "s32i    %2, %1, 0              \n\t"
+		       "wsr     a15, "__stringify(PS)" \n\t"
+		       "rsync                          \n\t"
+		       : "=&a" (tmp)
+		       : "a" (m), "a" (val)
+		       : "a15", "memory");
+  return tmp;
+}
+
+#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+
+/*
+ * This only works if the compiler isn't horribly bad at optimizing.
+ * gcc-2.5.8 reportedly can't handle this, but I define that one to
+ * be dead anyway.
+ */
+
+extern void __xchg_called_with_bad_pointer(void);
+
+static __inline__ unsigned long
+__xchg(unsigned long x, volatile void * ptr, int size)
+{
+	switch (size) {
+		case 4:
+			return xchg_u32(ptr, x);
+	}
+	__xchg_called_with_bad_pointer();
+	return x;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _XTENSA_CMPXCHG_H */