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, 72 insertions, 0 deletions

diff --git a/arch/sparc/include/asm/switch_to_64.h b/arch/sparc/include/asm/switch_to_64.h
new file mode 100644
index 000000000000..7923c4a2be38
--- /dev/null
+++ b/arch/sparc/include/asm/switch_to_64.h
@@ -0,0 +1,72 @@
+#ifndef __SPARC64_SWITCH_TO_64_H
+#define __SPARC64_SWITCH_TO_64_H
+
+#include <asm/visasm.h>
+
+#define prepare_arch_switch(next)		\
+do {						\
+	flushw_all();				\
+} while (0)
+
+	/* See what happens when you design the chip correctly?
+	 *
+	 * We tell gcc we clobber all non-fixed-usage registers except
+	 * for l0/l1.  It will use one for 'next' and the other to hold
+	 * the output value of 'last'.  'next' is not referenced again
+	 * past the invocation of switch_to in the scheduler, so we need
+	 * not preserve it's value.  Hairy, but it lets us remove 2 loads
+	 * and 2 stores in this critical code path.  -DaveM
+	 */
+#define switch_to(prev, next, last)					\
+do {	flush_tlb_pending();						\
+	save_and_clear_fpu();						\
+	/* If you are tempted to conditionalize the following */	\
+	/* so that ASI is only written if it changes, think again. */	\
+	__asm__ __volatile__("wr %%g0, %0, %%asi"			\
+	: : "r" (__thread_flag_byte_ptr(task_thread_info(next))[TI_FLAG_BYTE_CURRENT_DS]));\
+	trap_block[current_thread_info()->cpu].thread =			\
+		task_thread_info(next);					\
+	__asm__ __volatile__(						\
+	"mov	%%g4, %%g7\n\t"						\
+	"stx	%%i6, [%%sp + 2047 + 0x70]\n\t"				\
+	"stx	%%i7, [%%sp + 2047 + 0x78]\n\t"				\
+	"rdpr	%%wstate, %%o5\n\t"					\
+	"stx	%%o6, [%%g6 + %6]\n\t"					\
+	"stb	%%o5, [%%g6 + %5]\n\t"					\
+	"rdpr	%%cwp, %%o5\n\t"					\
+	"stb	%%o5, [%%g6 + %8]\n\t"					\
+	"wrpr	%%g0, 15, %%pil\n\t"					\
+	"mov	%4, %%g6\n\t"						\
+	"ldub	[%4 + %8], %%g1\n\t"					\
+	"wrpr	%%g1, %%cwp\n\t"					\
+	"ldx	[%%g6 + %6], %%o6\n\t"					\
+	"ldub	[%%g6 + %5], %%o5\n\t"					\
+	"ldub	[%%g6 + %7], %%o7\n\t"					\
+	"wrpr	%%o5, 0x0, %%wstate\n\t"				\
+	"ldx	[%%sp + 2047 + 0x70], %%i6\n\t"				\
+	"ldx	[%%sp + 2047 + 0x78], %%i7\n\t"				\
+	"ldx	[%%g6 + %9], %%g4\n\t"					\
+	"wrpr	%%g0, 14, %%pil\n\t"					\
+	"brz,pt %%o7, switch_to_pc\n\t"					\
+	" mov	%%g7, %0\n\t"						\
+	"sethi	%%hi(ret_from_syscall), %%g1\n\t"			\
+	"jmpl	%%g1 + %%lo(ret_from_syscall), %%g0\n\t"		\
+	" nop\n\t"							\
+	".globl switch_to_pc\n\t"					\
+	"switch_to_pc:\n\t"						\
+	: "=&r" (last), "=r" (current), "=r" (current_thread_info_reg),	\
+	  "=r" (__local_per_cpu_offset)					\
+	: "0" (task_thread_info(next)),					\
+	  "i" (TI_WSTATE), "i" (TI_KSP), "i" (TI_NEW_CHILD),            \
+	  "i" (TI_CWP), "i" (TI_TASK)					\
+	: "cc",								\
+	        "g1", "g2", "g3",                   "g7",		\
+	        "l1", "l2", "l3", "l4", "l5", "l6", "l7",		\
+	  "i0", "i1", "i2", "i3", "i4", "i5",				\
+	  "o0", "o1", "o2", "o3", "o4", "o5",       "o7");		\
+} while(0)
+
+extern void synchronize_user_stack(void);
+extern void fault_in_user_windows(void);
+
+#endif /* __SPARC64_SWITCH_TO_64_H */