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
  ...

79 files changed, 670 insertions, 671 deletions

diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 9dd0a769fa1..905832aa9e9 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -13,9 +13,9 @@
 
 #include <linux/types.h>
 
+#include <asm/cmpxchg.h>
 #include <asm-generic/atomic64.h>
 
-#include <asm/system.h>
 
 #define ATOMIC_INIT(i)  { (i) }
 
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 9f421df46ae..ce35a1cf1a2 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -8,7 +8,7 @@
 #define __ARCH_SPARC64_ATOMIC__
 
 #include <linux/types.h>
-#include <asm/system.h>
+#include <asm/cmpxchg.h>
 
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
@@ -85,7 +85,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
-
 #define atomic64_cmpxchg(v, o, n) \
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
diff --git a/arch/sparc/include/asm/auxio_32.h b/arch/sparc/include/asm/auxio_32.h
index e03e088be95..3a319775ae3 100644
--- a/arch/sparc/include/asm/auxio_32.h
+++ b/arch/sparc/include/asm/auxio_32.h
@@ -6,7 +6,6 @@
 #ifndef _SPARC_AUXIO_H
 #define _SPARC_AUXIO_H
 
-#include <asm/system.h>
 #include <asm/vaddrs.h>
 
 /* This register is an unsigned char in IO space.  It does two things.
diff --git a/arch/sparc/include/asm/barrier.h b/arch/sparc/include/asm/barrier.h
new file mode 100644
index 00000000000..b25f02a029e
--- /dev/null
+++ b/arch/sparc/include/asm/barrier.h
@@ -0,0 +1,8 @@
+#ifndef ___ASM_SPARC_BARRIER_H
+#define ___ASM_SPARC_BARRIER_H
+#if defined(__sparc__) && defined(__arch64__)
+#include <asm/barrier_64.h>
+#else
+#include <asm/barrier_32.h>
+#endif
+#endif
diff --git a/arch/sparc/include/asm/barrier_32.h b/arch/sparc/include/asm/barrier_32.h
new file mode 100644
index 00000000000..c1b76654ee7
--- /dev/null
+++ b/arch/sparc/include/asm/barrier_32.h
@@ -0,0 +1,15 @@
+#ifndef __SPARC_BARRIER_H
+#define __SPARC_BARRIER_H
+
+/* XXX Change this if we ever use a PSO mode kernel. */
+#define mb()	__asm__ __volatile__ ("" : : : "memory")
+#define rmb()	mb()
+#define wmb()	mb()
+#define read_barrier_depends()	do { } while(0)
+#define set_mb(__var, __value)  do { __var = __value; mb(); } while(0)
+#define smp_mb()	__asm__ __volatile__("":::"memory")
+#define smp_rmb()	__asm__ __volatile__("":::"memory")
+#define smp_wmb()	__asm__ __volatile__("":::"memory")
+#define smp_read_barrier_depends()	do { } while(0)
+
+#endif /* !(__SPARC_BARRIER_H) */
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
new file mode 100644
index 00000000000..95d45986f90
--- /dev/null
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -0,0 +1,56 @@
+#ifndef __SPARC64_BARRIER_H
+#define __SPARC64_BARRIER_H
+
+/* These are here in an effort to more fully work around Spitfire Errata
+ * #51.  Essentially, if a memory barrier occurs soon after a mispredicted
+ * branch, the chip can stop executing instructions until a trap occurs.
+ * Therefore, if interrupts are disabled, the chip can hang forever.
+ *
+ * It used to be believed that the memory barrier had to be right in the
+ * delay slot, but a case has been traced recently wherein the memory barrier
+ * was one instruction after the branch delay slot and the chip still hung.
+ * The offending sequence was the following in sym_wakeup_done() of the
+ * sym53c8xx_2 driver:
+ *
+ *	call	sym_ccb_from_dsa, 0
+ *	 movge	%icc, 0, %l0
+ *	brz,pn	%o0, .LL1303
+ *	 mov	%o0, %l2
+ *	membar	#LoadLoad
+ *
+ * The branch has to be mispredicted for the bug to occur.  Therefore, we put
+ * the memory barrier explicitly into a "branch always, predicted taken"
+ * delay slot to avoid the problem case.
+ */
+#define membar_safe(type) \
+do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
+			     " membar	" type "\n" \
+			     "1:\n" \
+			     : : : "memory"); \
+} while (0)
+
+/* The kernel always executes in TSO memory model these days,
+ * and furthermore most sparc64 chips implement more stringent
+ * memory ordering than required by the specifications.
+ */
+#define mb()	membar_safe("#StoreLoad")
+#define rmb()	__asm__ __volatile__("":::"memory")
+#define wmb()	__asm__ __volatile__("":::"memory")
+
+#define read_barrier_depends()		do { } while(0)
+#define set_mb(__var, __value) \
+	do { __var = __value; membar_safe("#StoreLoad"); } while(0)
+
+#ifdef CONFIG_SMP
+#define smp_mb()	mb()
+#define smp_rmb()	rmb()
+#define smp_wmb()	wmb()
+#else
+#define smp_mb()	__asm__ __volatile__("":::"memory")
+#define smp_rmb()	__asm__ __volatile__("":::"memory")
+#define smp_wmb()	__asm__ __volatile__("":::"memory")
+#endif
+
+#define smp_read_barrier_depends()	do { } while(0)
+
+#endif /* !(__SPARC64_BARRIER_H) */
diff --git a/arch/sparc/include/asm/bug.h b/arch/sparc/include/asm/bug.h
index 8a59e5a8c21..6bd9f43cb5a 100644
--- a/arch/sparc/include/asm/bug.h
+++ b/arch/sparc/include/asm/bug.h
@@ -19,4 +19,7 @@ extern void do_BUG(const char *file, int line);
 
 #include <asm-generic/bug.h>
 
+struct pt_regs;
+extern void die_if_kernel(char *str, struct pt_regs *regs) __attribute__ ((noreturn));
+
 #endif
diff --git a/arch/sparc/include/asm/cacheflush_32.h b/arch/sparc/include/asm/cacheflush_32.h
index 2e468773f25..68431b47a22 100644
--- a/arch/sparc/include/asm/cacheflush_32.h
+++ b/arch/sparc/include/asm/cacheflush_32.h
@@ -83,4 +83,13 @@ extern void sparc_flush_page_to_ram(struct page *page);
 #define flush_cache_vmap(start, end)		flush_cache_all()
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
+/* When a context switch happens we must flush all user windows so that
+ * the windows of the current process are flushed onto its stack. This
+ * way the windows are all clean for the next process and the stack
+ * frames are up to date.
+ */
+extern void flush_user_windows(void);
+extern void kill_user_windows(void);
+extern void flushw_all(void);
+
 #endif /* _SPARC_CACHEFLUSH_H */
diff --git a/arch/sparc/include/asm/cacheflush_64.h b/arch/sparc/include/asm/cacheflush_64.h
index b95384033e8..2efea2ff88b 100644
--- a/arch/sparc/include/asm/cacheflush_64.h
+++ b/arch/sparc/include/asm/cacheflush_64.h
@@ -9,6 +9,16 @@
 
 /* Cache flush operations. */
 
+
+#define flushi(addr)	__asm__ __volatile__ ("flush %0" : : "r" (addr) : "memory")
+#define flushw_all()	__asm__ __volatile__("flushw")
+
+extern void __flushw_user(void);
+#define flushw_user() __flushw_user()
+
+#define flush_user_windows flushw_user
+#define flush_register_windows flushw_all
+
 /* These are the same regardless of whether this is an SMP kernel or not. */
 #define flush_cache_mm(__mm) \
 	do { if ((__mm) == current->mm) flushw_user(); } while(0)
diff --git a/arch/sparc/include/asm/cmpxchg.h b/arch/sparc/include/asm/cmpxchg.h
new file mode 100644
index 00000000000..9355893efa5
--- /dev/null
+++ b/arch/sparc/include/asm/cmpxchg.h
@@ -0,0 +1,8 @@
+#ifndef ___ASM_SPARC_CMPXCHG_H
+#define ___ASM_SPARC_CMPXCHG_H
+#if defined(__sparc__) && defined(__arch64__)
+#include <asm/cmpxchg_64.h>
+#else
+#include <asm/cmpxchg_32.h>
+#endif
+#endif
diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
new file mode 100644
index 00000000000..c786b0a92b5
--- /dev/null
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -0,0 +1,112 @@
+/* 32-bit atomic xchg() and cmpxchg() definitions.
+ *
+ * Copyright (C) 1996 David S. Miller (davem@davemloft.net)
+ * Copyright (C) 2000 Anton Blanchard (anton@linuxcare.com.au)
+ * Copyright (C) 2007 Kyle McMartin (kyle@parisc-linux.org)
+ *
+ * Additions by Keith M Wesolowski (wesolows@foobazco.org) based
+ * on asm-parisc/atomic.h Copyright (C) 2000 Philipp Rumpf <prumpf@tux.org>.
+ */
+
+#ifndef __ARCH_SPARC_CMPXCHG__
+#define __ARCH_SPARC_CMPXCHG__
+
+#include <asm/btfixup.h>
+
+/* This has special calling conventions */
+#ifndef CONFIG_SMP
+BTFIXUPDEF_CALL(void, ___xchg32, void)
+#endif
+
+static inline unsigned long xchg_u32(__volatile__ unsigned long *m, unsigned long val)
+{
+#ifdef CONFIG_SMP
+	__asm__ __volatile__("swap [%2], %0"
+			     : "=&r" (val)
+			     : "0" (val), "r" (m)
+			     : "memory");
+	return val;
+#else
+	register unsigned long *ptr asm("g1");
+	register unsigned long ret asm("g2");
+
+	ptr = (unsigned long *) m;
+	ret = val;
+
+	/* Note: this is magic and the nop there is
+	   really needed. */
+	__asm__ __volatile__(
+	"mov	%%o7, %%g4\n\t"
+	"call	___f____xchg32\n\t"
+	" nop\n\t"
+	: "=&r" (ret)
+	: "0" (ret), "r" (ptr)
+	: "g3", "g4", "g7", "memory", "cc");
+
+	return ret;
+#endif
+}
+
+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;
+}
+
+#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+
+/* Emulate cmpxchg() the same way we emulate atomics,
+ * by hashing the object address and indexing into an array
+ * of spinlocks to get a bit of performance...
+ *
+ * See arch/sparc/lib/atomic32.c for implementation.
+ *
+ * Cribbed from <asm-parisc/atomic.h>
+ */
+#define __HAVE_ARCH_CMPXCHG	1
+
+/* bug catcher for when unsupported size is used - won't link */
+extern void __cmpxchg_called_with_bad_pointer(void);
+/* we only need to support cmpxchg of a u32 on sparc */
+extern unsigned long __cmpxchg_u32(volatile u32 *m, u32 old, u32 new_);
+
+/* don't worry...optimizer will get rid of most of this */
+static inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32((u32 *)ptr, (u32)old, (u32)new_);
+	default:
+		__cmpxchg_called_with_bad_pointer();
+		break;
+	}
+	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>
+
+/*
+ * 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))
+
+#endif /* __ARCH_SPARC_CMPXCHG__ */
diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h
new file mode 100644
index 00000000000..b30eb37294c
--- /dev/null
+++ b/arch/sparc/include/asm/cmpxchg_64.h
@@ -0,0 +1,145 @@
+/* 64-bit atomic xchg() and cmpxchg() definitions.
+ *
+ * Copyright (C) 1996, 1997, 2000 David S. Miller (davem@redhat.com)
+ */
+
+#ifndef __ARCH_SPARC64_CMPXCHG__
+#define __ARCH_SPARC64_CMPXCHG__
+
+static inline unsigned long xchg32(__volatile__ unsigned int *m, unsigned int val)
+{
+	unsigned long tmp1, tmp2;
+
+	__asm__ __volatile__(
+"	mov		%0, %1\n"
+"1:	lduw		[%4], %2\n"
+"	cas		[%4], %2, %0\n"
+"	cmp		%2, %0\n"
+"	bne,a,pn	%%icc, 1b\n"
+"	 mov		%1, %0\n"
+	: "=&r" (val), "=&r" (tmp1), "=&r" (tmp2)
+	: "0" (val), "r" (m)
+	: "cc", "memory");
+	return val;
+}
+
+static inline unsigned long xchg64(__volatile__ unsigned long *m, unsigned long val)
+{
+	unsigned long tmp1, tmp2;
+
+	__asm__ __volatile__(
+"	mov		%0, %1\n"
+"1:	ldx		[%4], %2\n"
+"	casx		[%4], %2, %0\n"
+"	cmp		%2, %0\n"
+"	bne,a,pn	%%xcc, 1b\n"
+"	 mov		%1, %0\n"
+	: "=&r" (val), "=&r" (tmp1), "=&r" (tmp2)
+	: "0" (val), "r" (m)
+	: "cc", "memory");
+	return val;
+}
+
+#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+
+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