Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc: (144 commits)
  powerpc/44x: Support 16K/64K base page sizes on 44x
  powerpc: Force memory size to be a multiple of PAGE_SIZE
  powerpc/32: Wire up the trampoline code for kdump
  powerpc/32: Add the ability for a classic ppc kernel to be loaded at 32M
  powerpc/32: Allow __ioremap on RAM addresses for kdump kernel
  powerpc/32: Setup OF properties for kdump
  powerpc/32/kdump: Implement crash_setup_regs() using ppc_save_regs()
  powerpc: Prepare xmon_save_regs for use with kdump
  powerpc: Remove default kexec/crash_kernel ops assignments
  powerpc: Make default kexec/crash_kernel ops implicit
  powerpc: Setup OF properties for ppc32 kexec
  powerpc/pseries: Fix cpu hotplug
  powerpc: Fix KVM build on ppc440
  powerpc/cell: add QPACE as a separate Cell platform
  powerpc/cell: fix build breakage with CONFIG_SPUFS disabled
  powerpc/mpc5200: fix error paths in PSC UART probe function
  powerpc/mpc5200: add rts/cts handling in PSC UART driver
  powerpc/mpc5200: Make PSC UART driver update serial errors counters
  powerpc/mpc5200: Remove obsolete code from mpc5200 MDIO driver
  powerpc/mpc5200: Add MDMA/UDMA support to MPC5200 ATA driver
  ...

Fix trivial conflict in drivers/char/Makefile as per Paul's directions

arch/powerpc/include/asm/atomic.h

@@ -111,7 +111,7 @@ static __inline__ void atomic_inc(atomic_t *v)
 	bne-	1b"
 	: "=&r" (t), "+m" (v->counter)
 	: "r" (&v->counter)
-	: "cc");
+	: "cc", "xer");
 }
 
 static __inline__ int atomic_inc_return(atomic_t *v)
@@ -128,7 +128,7 @@ static __inline__ int atomic_inc_return(atomic_t *v)
 	ISYNC_ON_SMP
 	: "=&r" (t)
 	: "r" (&v->counter)
-	: "cc", "memory");
+	: "cc", "xer", "memory");
 
 	return t;
 }
@@ -155,7 +155,7 @@ static __inline__ void atomic_dec(atomic_t *v)
 	bne-	1b"
 	: "=&r" (t), "+m" (v->counter)
 	: "r" (&v->counter)
-	: "cc");
+	: "cc", "xer");
 }
 
 static __inline__ int atomic_dec_return(atomic_t *v)
@@ -172,7 +172,7 @@ static __inline__ int atomic_dec_return(atomic_t *v)
 	ISYNC_ON_SMP
 	: "=&r" (t)
 	: "r" (&v->counter)
-	: "cc", "memory");
+	: "cc", "xer", "memory");
 
 	return t;
 }
@@ -346,7 +346,7 @@ static __inline__ void atomic64_inc(atomic64_t *v)
 	bne-	1b"
 	: "=&r" (t), "+m" (v->counter)
 	: "r" (&v->counter)
-	: "cc");
+	: "cc", "xer");
 }
 
 static __inline__ long atomic64_inc_return(atomic64_t *v)
@@ -362,7 +362,7 @@ static __inline__ long atomic64_inc_return(atomic64_t *v)
 	ISYNC_ON_SMP
 	: "=&r" (t)
 	: "r" (&v->counter)
-	: "cc", "memory");
+	: "cc", "xer", "memory");
 
 	return t;
 }
@@ -388,7 +388,7 @@ static __inline__ void atomic64_dec(atomic64_t *v)
 	bne-	1b"
 	: "=&r" (t), "+m" (v->counter)
 	: "r" (&v->counter)
-	: "cc");
+	: "cc", "xer");
 }
 
 static __inline__ long atomic64_dec_return(atomic64_t *v)
@@ -404,7 +404,7 @@ static __inline__ long atomic64_dec_return(atomic64_t *v)
 	ISYNC_ON_SMP
 	: "=&r" (t)
 	: "r" (&v->counter)
-	: "cc", "memory");
+	: "cc", "xer", "memory");
 
 	return t;
 }
@@ -431,7 +431,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 	"\n\
 2:"	: "=&r" (t)
 	: "r" (&v->counter)
-	: "cc", "memory");
+	: "cc", "xer", "memory");
 
 	return t;
 }

arch/powerpc/include/asm/bug.h

@@ -3,6 +3,7 @@
 #ifdef __KERNEL__
 
 #include <asm/asm-compat.h>
+
 /*
  * Define an illegal instr to trap on the bug.
  * We don't use 0 because that marks the end of a function
@@ -14,6 +15,7 @@
 #ifdef CONFIG_BUG
 
 #ifdef __ASSEMBLY__
+#include <asm/asm-offsets.h>
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 .macro EMIT_BUG_ENTRY addr,file,line,flags
 	 .section __bug_table,"a"
@@ -26,7 +28,7 @@
 	 .previous
 .endm
 #else
- .macro EMIT_BUG_ENTRY addr,file,line,flags
+.macro EMIT_BUG_ENTRY addr,file,line,flags
 	 .section __bug_table,"a"
 5001:	 PPC_LONG \addr
 	 .short \flags
@@ -113,6 +115,13 @@
 #define HAVE_ARCH_BUG_ON
 #define HAVE_ARCH_WARN_ON
 #endif /* __ASSEMBLY __ */
+#else
+#ifdef __ASSEMBLY__
+.macro EMIT_BUG_ENTRY addr,file,line,flags
+.endm
+#else /* !__ASSEMBLY__ */
+#define _EMIT_BUG_ENTRY
+#endif
 #endif /* CONFIG_BUG */
 
 #include <asm-generic/bug.h>

arch/powerpc/include/asm/byteorder.h

@@ -11,6 +11,8 @@
 #include <asm/types.h>
 #include <linux/compiler.h>
 
+#define __BIG_ENDIAN
+
 #ifdef __GNUC__
 #ifdef __KERNEL__
 
@@ -21,12 +23,19 @@ static __inline__ __u16 ld_le16(const volatile __u16 *addr)
 	__asm__ __volatile__ ("lhbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr));
 	return val;
 }
+#define __arch_swab16p ld_le16
 
 static __inline__ void st_le16(volatile __u16 *addr, const __u16 val)
 {
 	__asm__ __volatile__ ("sthbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr));
 }
 
+static inline void __arch_swab16s(__u16 *addr)
+{
+	st_le16(addr, *addr);
+}
+#define __arch_swab16s __arch_swab16s
+
 static __inline__ __u32 ld_le32(const volatile __u32 *addr)
 {
 	__u32 val;
@@ -34,13 +43,20 @@ static __inline__ __u32 ld_le32(const volatile __u32 *addr)
 	__asm__ __volatile__ ("lwbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr));
 	return val;
 }
+#define __arch_swab32p ld_le32
 
 static __inline__ void st_le32(volatile __u32 *addr, const __u32 val)
 {
 	__asm__ __volatile__ ("stwbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr));
 }
 
-static __inline__ __attribute_const__ __u16 ___arch__swab16(__u16 value)
+static inline void __arch_swab32s(__u32 *addr)
+{
+	st_le32(addr, *addr);
+}
+#define __arch_swab32s __arch_swab32s
+
+static inline __attribute_const__ __u16 __arch_swab16(__u16 value)
 {
 	__u16 result;
 
@@ -49,8 +65,9 @@ static __inline__ __attribute_const__ __u16 ___arch__swab16(__u16 value)
 	    : "r" (value), "0" (value >> 8));
 	return result;
 }
+#define __arch_swab16 __arch_swab16
 
-static __inline__ __attribute_const__ __u32 ___arch__swab32(__u32 value)
+static inline __attribute_const__ __u32 __arch_swab32(__u32 value)
 {
 	__u32 result;
 
@@ -61,29 +78,16 @@ static __inline__ __attribute_const__ __u32 ___arch__swab32(__u32 value)
 	    : "r" (value), "0" (value >> 24));
 	return result;
 }
-
-#define __arch__swab16(x) ___arch__swab16(x)
-#define __arch__swab32(x) ___arch__swab32(x)
-
-/* The same, but returns converted value from the location pointer by addr. */
-#define __arch__swab16p(addr) ld_le16(addr)
-#define __arch__swab32p(addr) ld_le32(addr)
-
-/* The same, but do the conversion in situ, ie. put the value back to addr. */
-#define __arch__swab16s(addr) st_le16(addr,*addr)
-#define __arch__swab32s(addr) st_le32(addr,*addr)
+#define __arch_swab32 __arch_swab32
 
 #endif /* __KERNEL__ */
 
-#ifndef __STRICT_ANSI__
-#define __BYTEORDER_HAS_U64__
 #ifndef __powerpc64__
 #define __SWAB_64_THRU_32__
 #endif /* __powerpc64__ */
-#endif /* __STRICT_ANSI__ */
 
 #endif /* __GNUC__ */
 
-#include <linux/byteorder/big_endian.h>
+#include <linux/byteorder.h>
 
 #endif /* _ASM_POWERPC_BYTEORDER_H */

arch/powerpc/include/asm/cputable.h

@@ -82,6 +82,7 @@ struct cpu_spec {
 	char		*cpu_name;
 	unsigned long	cpu_features;		/* Kernel features */
 	unsigned int	cpu_user_features;	/* Userland features */
+	unsigned int	mmu_features;		/* MMU features */
 
 	/* cache line sizes */
 	unsigned int	icache_bsize;
@@ -144,17 +145,14 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_USE_TB			ASM_CONST(0x0000000000000040)
 #define CPU_FTR_L2CSR			ASM_CONST(0x0000000000000080)
 #define CPU_FTR_601			ASM_CONST(0x0000000000000100)
-#define CPU_FTR_HPTE_TABLE		ASM_CONST(0x0000000000000200)
 #define CPU_FTR_CAN_NAP			ASM_CONST(0x0000000000000400)
 #define CPU_FTR_L3CR			ASM_CONST(0x0000000000000800)
 #define CPU_FTR_L3_DISABLE_NAP		ASM_CONST(0x0000000000001000)
 #define CPU_FTR_NAP_DISABLE_L2_PR	ASM_CONST(0x0000000000002000)
 #define CPU_FTR_DUAL_PLL_750FX		ASM_CONST(0x0000000000004000)
 #define CPU_FTR_NO_DPM			ASM_CONST(0x0000000000008000)
-#define CPU_FTR_HAS_HIGH_BATS		ASM_CONST(0x0000000000010000)
 #define CPU_FTR_NEED_COHERENT		ASM_CONST(0x0000000000020000)
 #define CPU_FTR_NO_BTIC			ASM_CONST(0x0000000000040000)
-#define CPU_FTR_BIG_PHYS		ASM_CONST(0x0000000000080000)
 #define CPU_FTR_NODSISRALIGN		ASM_CONST(0x0000000000100000)
 #define CPU_FTR_PPC_LE			ASM_CONST(0x0000000000200000)
 #define CPU_FTR_REAL_LE			ASM_CONST(0x0000000000400000)
@@ -163,6 +161,8 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_SPE			ASM_CONST(0x0000000002000000)
 #define CPU_FTR_NEED_PAIRED_STWCX	ASM_CONST(0x0000000004000000)
 #define CPU_FTR_LWSYNC			ASM_CONST(0x0000000008000000)
+#define CPU_FTR_NOEXECUTE		ASM_CONST(0x0000000010000000)
+#define CPU_FTR_INDEXED_DCR		ASM_CONST(0x0000000020000000)
 
 /*
  * Add the 64-bit processor unique features in the top half of the word;
@@ -177,7 +177,6 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_SLB			LONG_ASM_CONST(0x0000000100000000)
 #define CPU_FTR_16M_PAGE		LONG_ASM_CONST(0x0000000200000000)
 #define CPU_FTR_TLBIEL			LONG_ASM_CONST(0x0000000400000000)
-#define CPU_FTR_NOEXECUTE		LONG_ASM_CONST(0x0000000800000000)
 #define CPU_FTR_IABR			LONG_ASM_CONST(0x0000002000000000)
 #define CPU_FTR_MMCRA			LONG_ASM_CONST(0x0000004000000000)
 #define CPU_FTR_CTRL			LONG_ASM_CONST(0x0000008000000000)
@@ -194,6 +193,7 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_VSX			LONG_ASM_CONST(0x0010000000000000)
 #define CPU_FTR_SAO			LONG_ASM_CONST(0x0020000000000000)
 #define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0040000000000000)
+#define CPU_FTR_UNALIGNED_LD_STD	LONG_ASM_CONST(0x0080000000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -264,164 +264,159 @@ extern const char *powerpc_base_platform;
 		     !defined(CONFIG_POWER3) && !defined(CONFIG_POWER4) && \
 		     !defined(CONFIG_BOOKE))
 
-#define CPU_FTRS_PPC601	(CPU_FTR_COMMON | CPU_FTR_601 | CPU_FTR_HPTE_TABLE | \
+#define CPU_FTRS_PPC601	(CPU_FTR_COMMON | CPU_FTR_601 | \
 	CPU_FTR_COHERENT_ICACHE | CPU_FTR_UNIFIED_ID_CACHE)
 #define CPU_FTRS_603	(CPU_FTR_COMMON | \
 	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
 #define CPU_FTRS_604	(CPU_FTR_COMMON | \
-	    CPU_FTR_USE_TB | CPU_FTR_HPTE_TABLE | CPU_FTR_PPC_LE)
+	    CPU_FTR_USE_TB | CPU_FTR_PPC_LE)
 #define CPU_FTRS_740_NOTAU	(CPU_FTR_COMMON | \
 	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \
-	    CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
 #define CPU_FTRS_740	(CPU_FTR_COMMON | \
 	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \
-	    CPU_FTR_TAU | CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP | \
+	    CPU_FTR_TAU | CPU_FTR_MAYBE_CAN_NAP | \
 	    CPU_FTR_PPC_LE)
 #define CPU_FTRS_750	(CPU_FTR_COMMON | \
 	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \
-	    CPU_FTR_TAU | CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP | \
+	    CPU_FTR_TAU | CPU_FTR_MAYBE_CAN_NAP | \
 	    CPU_FTR_PPC_LE)
-#define CPU_FTRS_750CL	(CPU_FTRS_750 | CPU_FTR_HAS_HIGH_BATS)
+#define CPU_FTRS_750CL	(CPU_FTRS_750)
 #define CPU_FTRS_750FX1	(CPU_FTRS_750 | CPU_FTR_DUAL_PLL_750FX | CPU_FTR_NO_DPM)
 #define CPU_FTRS_750FX2	(CPU_FTRS_750 | CPU_FTR_NO_DPM)
-#define CPU_FTRS_750FX	(CPU_FTRS_750 | CPU_FTR_DUAL_PLL_750FX | \
-		CPU_FTR_HAS_HIGH_BATS)
+#define CPU_FTRS_750FX	(CPU_FTRS_750 | CPU_FTR_DUAL_PLL_750FX)
 #define CPU_FTRS_750GX	(CPU_FTRS_750FX)
 #define CPU_FTRS_7400_NOTAU	(CPU_FTR_COMMON | \
 	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \
-	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_HPTE_TABLE | \
+	    CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
 #define CPU_FTRS_7400	(CPU_FTR_COMMON | \
 	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \
-	    CPU_FTR_TAU | CPU_FTR_ALTIVEC_COMP | CPU_FTR_HPTE_TABLE | \
+	    CPU_FTR_TAU | CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
 #define CPU_FTRS_7450_20	(CPU_FTR_COMMON | \
 	    CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-	    CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
+	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
 	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7450_21	(CPU_FTR_COMMON | \
 	    CPU_FTR_USE_TB | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-	    CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
+	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
 	    CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_L3_DISABLE_NAP | \
 	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7450_23	(CPU_FTR_COMMON | \
 	    CPU_FTR_USE_TB | CPU_FTR_NEED_PAIRED_STWCX | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-	    CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
+	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
 	    CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE)
 #define CPU_FTRS_7455_1	(CPU_FTR_COMMON | \
 	    CPU_FTR_USE_TB | CPU_FTR_NEED_PAIRED_STWCX | \
 	    CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | CPU_FTR_L3CR | \
-	    CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | CPU_FTR_HAS_HIGH_BATS | \
-	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE)
+	    CPU_FTR_SPEC7450 | CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE)
 #define CPU_FTRS_7455_20	(CPU_FTR_COMMON | \
 	    CPU_FTR_USE_TB | CPU_FTR_NEED_PAIRED_STWCX | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-	    CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
+	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
 	    CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_L3_DISABLE_NAP | \
-	    CPU_FTR_NEED_COHERENT | CPU_FTR_HAS_HIGH_BATS | CPU_FTR_PPC_LE)
+	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE)
 #define CPU_FTRS_7455	(CPU_FTR_COMMON | \
 	    CPU_FTR_USE_TB | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-	    CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
-	    CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \
+	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
 	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7447_10	(CPU_FTR_COMMON | \
 	    CPU_FTR_USE_TB | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-	    CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
-	    CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \
+	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
 	    CPU_FTR_NEED_COHERENT | CPU_FTR_NO_BTIC | CPU_FTR_PPC_LE | \
 	    CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7447	(CPU_FTR_COMMON | \
 	    CPU_FTR_USE_TB | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-	    CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
-	    CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \
+	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
 	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7447A	(CPU_FTR_COMMON | \
 	    CPU_FTR_USE_TB | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-	    CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
-	    CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \
+	    CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
 	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7448	(CPU_FTR_COMMON | \
 	    CPU_FTR_USE_TB | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-	    CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
-	    CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \
+	    CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
 	    CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_82XX	(CPU_FTR_COMMON | \
 	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB)
 #define CPU_FTRS_G2_LE	(CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \
-	    CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_HAS_HIGH_BATS)
+	    CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP)
 #define CPU_FTRS_E300	(CPU_FTR_MAYBE_CAN_DOZE | \
-	    CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_HAS_HIGH_BATS | \
+	    CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | \
 	    CPU_FTR_COMMON)
 #define CPU_FTRS_E300C2	(CPU_FTR_MAYBE_CAN_DOZE | \
-	    CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_HAS_HIGH_BATS | \
+	    CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | \
 	    CPU_FTR_COMMON | CPU_FTR_FPU_UNAVAILABLE)
-#define CPU_FTRS_CLASSIC32	(CPU_FTR_COMMON | \
-	    CPU_FTR_USE_TB | CPU_FTR_HPTE_TABLE)
+#define CPU_FTRS_CLASSIC32	(CPU_FTR_COMMON | CPU_FTR_USE_TB)
 #define CPU_FTRS_8XX	(CPU_FTR_USE_TB)
-#define CPU_FTRS_40X	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN)
-#define CPU_FTRS_44X	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN)
+#define CPU_FTRS_40X	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_44X	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_440x6	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE | \
+	    CPU_FTR_INDEXED_DCR)
 #define CPU_FTRS_E200	(CPU_FTR_USE_TB | CPU_FTR_SPE_COMP | \
 	    CPU_FTR_NODSISRALIGN | CPU_FTR_COHERENT_ICACHE | \
-	    CPU_FTR_UNIFIED_ID_CACHE)
+	    CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_E500	(CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
-	    CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN)
+	    CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \
+	    CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_E500_2	(CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
-	    CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_BIG_PHYS | \
-	    CPU_FTR_NODSISRALIGN)
+	    CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | \
+	    CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_E500MC	(CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
-	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_BIG_PHYS | CPU_FTR_NODSISRALIGN | \
-	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC)
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \
+	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_GENERIC_32	(CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN)
 
 /* 64-bit CPUs */
 #define CPU_FTRS_POWER3	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-	    CPU_FTR_HPTE_TABLE | CPU_FTR_IABR | CPU_FTR_PPC_LE)
+	    CPU_FTR_IABR | CPU_FTR_PPC_LE)
 #define CPU_FTRS_RS64	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-	    CPU_FTR_HPTE_TABLE | CPU_FTR_IABR | \
+	    CPU_FTR_IABR | \
 	    CPU_FTR_MMCRA | CPU_FTR_CTRL)
 #define CPU_FTRS_POWER4	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-	    CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_CP_USE_DCBTZ)
 #define CPU_FTRS_PPC970	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-	    CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_CAN_NAP | CPU_FTR_MMCRA | \
 	    CPU_FTR_CP_USE_DCBTZ)
 #define CPU_FTRS_POWER5	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-	    CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
 	    CPU_FTR_PURR)
 #define CPU_FTRS_POWER6 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-	    CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR)
+	    CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD)
 #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-	    CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
 	    CPU_FTR_DSCR | CPU_FTR_SAO)
 #define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-	    CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_PAUSE_ZERO | CPU_FTR_CI_LARGE_PAGE | \
-	    CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ)
+	    CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \
+	    CPU_FTR_UNALIGNED_LD_STD)
 #define CPU_FTRS_PA6T (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-	    CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | \
+	    CPU_FTR_PPCAS_ARCH_V2 | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_CI_LARGE_PAGE | \
 	    CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_NO_SLBIE_B)
-#define CPU_FTRS_COMPATIBLE	(CPU_FTR_USE_TB | \
-	    CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2)
+#define CPU_FTRS_COMPATIBLE	(CPU_FTR_USE_TB | CPU_FTR_PPCAS_ARCH_V2)
 
 #ifdef __powerpc64__
 #define CPU_FTRS_POSSIBLE	\
@@ -452,7 +447,7 @@ enum {
 	    CPU_FTRS_40X |
 #endif
 #ifdef CONFIG_44x
-	    CPU_FTRS_44X |
+	    CPU_FTRS_44X | CPU_FTRS_440x6 |
 #endif
 #ifdef CONFIG_E200
 	    CPU_FTRS_E200 |
@@ -492,7 +487,7 @@ enum {
 	    CPU_FTRS_40X &
 #endif
 #ifdef CONFIG_44x
-	    CPU_FTRS_44X &
+	    CPU_FTRS_44X & CPU_FTRS_440x6 &
 #endif
 #ifdef CONFIG_E200
 	    CPU_FTRS_E200 &

arch/powerpc/include/asm/dcr-native.h

@@ -23,6 +23,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/spinlock.h>
+#include <asm/cputable.h>
 
 typedef struct {
 	unsigned int base;
@@ -39,23 +40,45 @@ static inline bool dcr_map_ok_native(dcr_host_native_t host)
 #define dcr_read_native(host, dcr_n)		mfdcr(dcr_n + host.base)
 #define dcr_write_native(host, dcr_n, value)	mtdcr(dcr_n + host.base, value)
 
-/* Device Control Registers */
-void __mtdcr(int reg, unsigned int val);
-unsigned int __mfdcr(int reg);
+/* Table based DCR accessors */
+extern void __mtdcr(unsigned int reg, unsigned int val);
+extern unsigned int __mfdcr(unsigned int reg);
+
+/* mfdcrx/mtdcrx instruction based accessors. We hand code
+ * the opcodes in order not to depend on newer binutils
+ */
+static inline unsigned int mfdcrx(unsigned int reg)
+{
+	unsigned int ret;
+	asm volatile(".long 0x7c000206 | (%0 << 21) | (%1 << 16)"
+		     : "=r" (ret) : "r" (reg));
+	return ret;
+}
+
+static inline void mtdcrx(unsigned int reg, unsigned int val)
+{
+	asm volatile(".long 0x7c000306 | (%0 << 21) | (%1 << 16)"
+		     : : "r" (val), "r" (reg));
+}
+
 #define mfdcr(rn)						\
 	({unsigned int rval;					\
-	if (__builtin_constant_p(rn))				\
+	if (__builtin_constant_p(rn) && rn < 1024)		\
 		asm volatile("mfdcr %0," __stringify(rn)	\
 		              : "=r" (rval));			\
+	else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR)))	\
+		rval = mfdcrx(rn);				\
 	else							\
 		rval = __mfdcr(rn);				\
 	rval;})
 
 #define mtdcr(rn, v)						\
 do {								\
-	if (__builtin_constant_p(rn))				\
+	if (__builtin_constant_p(rn) && rn < 1024)		\
 		asm volatile("mtdcr " __stringify(rn) ",%0"	\
 			      : : "r" (v)); 			\
+	else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR)))	\
+		mtdcrx(rn, v);					\
 	else							\
 		__mtdcr(rn, v);					\
 } while (0)
@@ -69,8 +92,13 @@ static inline unsigned __mfdcri(int base_addr, int base_data, int reg)
 	unsigned int val;
 
 	spin_lock_irqsave(&dcr_ind_lock, flags);
-	__mtdcr(base_addr, reg);
-	val = __mfdcr(base_data);
+	if (cpu_has_feature(CPU_FTR_INDEXED_DCR)) {
+		mtdcrx(base_addr, reg);
+		val = mfdcrx(base_data);
+	} else {
+		__mtdcr(base_addr, reg);
+		val = __mfdcr(base_data);
+	}
 	spin_unlock_irqrestore(&dcr_ind_lock, flags);
 	return val;
 }
@@ -81,8 +109,13 @@ static inline void __mtdcri(int base_addr, int base_data, int reg,
 	unsigned long flags;
 
 	spin_lock_irqsave(&dcr_ind_lock, flags);
-	__mtdcr(base_addr, reg);
-	__mtdcr(base_data, val);
+	if (cpu_has_feature(CPU_FTR_INDEXED_DCR)) {
+		mtdcrx(base_addr, reg);
+		mtdcrx(base_data, val);
+	} else {
+		__mtdcr(base_addr, reg);
+		__mtdcr(base_data, val);
+	}
 	spin_unlock_irqrestore(&dcr_ind_lock, flags);
 }
 
@@ -93,9 +126,15 @@ static inline void __dcri_clrset(int base_addr, int base_data, int reg,
 	unsigned int val;
 
 	spin_lock_irqsave(&dcr_ind_lock, flags);
-	__mtdcr(base_addr, reg);
-	val = (__mfdcr(base_data) & ~clr) | set;
-	__mtdcr(base_data, val);
+	if (cpu_has_feature(CPU_FTR_INDEXED_DCR)) {
+		mtdcrx(base_addr, reg);
+		val = (mfdcrx(base_data) & ~clr) | set;
+		mtdcrx(base_data, val);
+	} else {
+		__mtdcr(base_addr, reg);
+		val = (__mfdcr(base_data) & ~clr) | set;
+		__mtdcr(base_data, val);
+	}
 	spin_unlock_irqrestore(&dcr_ind_lock, flags);
 }
 

arch/powerpc/include/asm/dcr.h

@@ -68,9 +68,9 @@ typedef dcr_host_mmio_t dcr_host_t;
  * additional helpers to read the DCR * base from the device-tree
  */
 struct device_node;
-extern unsigned int dcr_resource_start(struct device_node *np,
+extern unsigned int dcr_resource_start(const struct device_node *np,
 				       unsigned int index);
-extern unsigned int dcr_resource_len(struct device_node *np,
+extern unsigned int dcr_resource_len(const struct device_node *np,
 				     unsigned int index);
 #endif /* CONFIG_PPC_DCR */
 #endif /* __ASSEMBLY__ */

arch/powerpc/include/asm/device.h

@@ -18,4 +18,16 @@ struct dev_archdata {
 	void			*dma_data;
 };
 
+static inline void dev_archdata_set_node(struct dev_archdata *ad,
+					 struct device_node *np)
+{
+	ad->of_node = np;
+}
+
+static inline struct device_node *
+dev_archdata_get_node(const struct dev_archdata *ad)
+{
+	return ad->of_node;
+}
+
 #endif /* _ASM_POWERPC_DEVICE_H */

arch/powerpc/include/asm/dma-mapping.h

@@ -60,12 +60,6 @@ struct dma_mapping_ops {
 				dma_addr_t *dma_handle, gfp_t flag);
 	void		(*free_coherent)(struct device *dev, size_t size,
 				void *vaddr, dma_addr_t dma_handle);
-	dma_addr_t	(*map_single)(struct device *dev, void *ptr,
-				size_t size, enum dma_data_direction direction,
-				struct dma_attrs *attrs);
-	void		(*unmap_single)(struct device *dev, dma_addr_t dma_addr,
-				size_t size, enum dma_data_direction direction,
-				struct dma_attrs *attrs);
 	int		(*map_sg)(struct device *dev, struct scatterlist *sg,
 				int nents, enum dma_data_direction direction,
 				struct dma_attrs *attrs);
@@ -82,6 +76,22 @@ struct dma_mapping_ops {
 				dma_addr_t dma_address, size_t size,
 				enum dma_data_direction direction,
 				struct dma_attrs *attrs);
+#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS
+	void            (*sync_single_range_for_cpu)(struct device *hwdev,
+				dma_addr_t dma_handle, unsigned long offset,
+				size_t size,
+				enum dma_data_direction direction);
+	void            (*sync_single_range_for_device)(struct device *hwdev,
+				dma_addr_t dma_handle, unsigned long offset,
+				size_t size,
+				enum dma_data_direction direction);
+	void            (*sync_sg_for_cpu)(struct device *hwdev,
+				struct scatterlist *sg, int nelems,
+				enum dma_data_direction direction);
+	void            (*sync_sg_for_device)(struct device *hwdev,
+				struct scatterlist *sg, int nelems,
+				enum dma_data_direction direction);
+#endif
 };
 
 /*
@@ -149,10 +159,9 @@ static inline int dma_set_mask(struct device *dev, u64 dma_mask)
 }
 
 /*
- * TODO: map_/unmap_single will ideally go away, to be completely
- * replaced by map/unmap_page.   Until then, we allow dma_ops to have
- * one or the other, or both by checking to see if the specific
- * function requested exists; and if not, falling back on the other set.
+ * map_/unmap_single actually call through to map/unmap_page now that all the
+ * dma_mapping_ops have been converted over. We just have to get the page and
+ * offset to pass through to map_page
  */
 static inline dma_addr_t dma_map_single_attrs(struct device *dev,
 					      void *cpu_addr,
@@ -164,10 +173,6 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev,
 
 	BUG_ON(!dma_ops);
 
-	if (dma_ops->map_single)
-		return dma_ops->map_single(dev, cpu_addr, size, direction,
-					   attrs);
-
 	return dma_ops->map_page(dev, virt_to_page(cpu_addr),
 				 (unsigned long)cpu_addr % PAGE_SIZE, size,
 				 direction, attrs);
@@ -183,11 +188,6 @@ static inline void dma_unmap_single_attrs(struct device *dev,
 
 	BUG_ON(!dma_ops);
 
-	if (dma_ops->unmap_single) {
-		dma_ops->unmap_single(dev, dma_addr, size, direction, attrs);
-		return;
-	}
-
 	dma_ops->unmap_page(dev, dma_addr, size, direction, attrs);
 }
 
@@ -201,12 +201,7 @@ static inline dma_addr_t dma_map_page_attrs(struct device *dev,
 
 	BUG_ON(!dma_ops);
 
-	if (dma_ops->map_page)
-		return dma_ops->map_page(dev, page, offset, size, direction,
-					 attrs);
-
-	return dma_ops->map_single(dev, page_address(page) + offset, size,
-				   direction, attrs);
+	return dma_ops->map_page(dev, page, offset, size, direction, attrs);
 }
 
 static inline void dma_unmap_page_attrs(struct device *dev,
@@ -219,12 +214,7 @@ static inline void dma_unmap_page_attrs(struct device *dev,
 
 	BUG_ON(!dma_ops);
 
-	if (dma_ops->unmap_page) {
-		dma_ops->unmap_page(dev, dma_address, size, direction, attrs);
-		return;
-	}
-
-	dma_ops->unmap_single(dev, dma_address, size, direction, attrs);
+	dma_ops->unmap_page(dev, dma_address, size, direction, attrs);
 }
 
 static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
@@ -308,48 +298,108 @@ static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 	dma_unmap_sg_attrs(dev, sg, nhwentries, direction, NULL);
 }
 
+#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS
 static inline void dma_sync_single_for_cpu(struct device *dev,
 		dma_addr_t dma_handle, size_t size,
 		enum dma_data_direction direction)
 {
-	BUG_ON(direction == DMA_NONE);
-	__dma_sync(bus_to_virt(dma_handle), size, direction);
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	dma_ops->sync_single_range_for_cpu(dev, dma_handle, 0,
+					   size, direction);
 }
 
 static inline void dma_sync_single_for_device(struct device *dev,
 		dma_addr_t dma_handle, size_t size,
 		enum dma_data_direction direction)
 {
-	BUG_ON(direction == DMA_NONE);
-	__dma_sync(bus_to_virt(dma_handle), size, direction);
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	dma_ops->sync_single_range_for_device(dev, dma_handle,
+					      0, size, direction);
 }
 
 static inline void dma_sync_sg_for_cpu(struct device *dev,
 		struct scatterlist *sgl, int nents,
 		enum dma_data_direction direction)
 {
-	struct scatterlist *sg;
-	int i;
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
 
-	BUG_ON(direction == DMA_NONE);
-
-	for_each_sg(sgl, sg, nents, i)
-		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
+	BUG_ON(!dma_ops);
+	dma_ops->sync_sg_for_cpu(dev, sgl, nents, direction);
 }
 
 static inline void dma_sync_sg_for_device(struct device *dev,
 		struct scatterlist *sgl, int nents,
 		enum dma_data_direction direction)
 {
-	struct scatterlist *sg;
-	int i;
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
 
-	BUG_ON(direction == DMA_NONE);
-
-	for_each_sg(sgl, sg, nents, i)
-		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
+	BUG_ON(!dma_ops);
+	dma_ops->sync_sg_for_device(dev, sgl, nents, direction);
 }
 
+static inline void dma_sync_single_range_for_cpu(struct device *dev,
+		dma_addr_t dma_handle, unsigned long offset, size_t size,
+		enum dma_data_direction direction)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	dma_ops->sync_single_range_for_cpu(dev, dma_handle,
+					   offset, size, direction);
+}
+
+static inline void dma_sync_single_range_for_device(struct device *dev,
+		dma_addr_t dma_handle, unsigned long offset, size_t size,
+		enum dma_data_direction direction)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	dma_ops->sync_single_range_for_device(dev, dma_handle, offset,
+					      size, direction);
+}
+#else /* CONFIG_PPC_NEED_DMA_SYNC_OPS */
+static inline void dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t dma_handle, size_t size,
+		enum dma_data_direction direction)
+{
+}
+
+static inline void dma_sync_single_for_device(struct device *dev,
+		dma_addr_t dma_handle, size_t size,
+		enum dma_data_direction direction)
+{
+}
+
+static inline void dma_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents,
+		enum dma_data_direction direction)
+{
+}
+
+static inline void dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nents,
+		enum dma_data_direction direction)
+{
+}
+
+static inline void dma_sync_single_range_for_cpu(struct device *dev,
+		dma_addr_t dma_handle, unsigned long offset, size_t size,
+		enum dma_data_direction direction)
+{
+}
+
+static inline void dma_sync_single_range_for_device(struct device *dev,
+		dma_addr_t dma_handle, unsigned long offset, size_t size,
+		enum dma_data_direction direction)
+{
+}
+#endif
+
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 #ifdef CONFIG_PPC64
@@ -382,22 +432,6 @@ static inline int dma_get_cache_alignment(void)
 #endif
 }
 
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
-{
-	/* just sync everything for now */
-	dma_sync_single_for_cpu(dev, dma_handle, offset + size, direction);
-}
-
-static inline void dma_sync_single_range_for_device(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
-{
-	/* just sync everything for now */
-	dma_sync_single_for_device(dev, dma_handle, offset + size, direction);
-}
-
 static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		enum dma_data_direction direction)
 {

arch/powerpc/include/asm/eeh.h

@@ -17,8 +17,8 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#ifndef _PPC64_EEH_H
-#define _PPC64_EEH_H
+#ifndef _POWERPC_EEH_H
+#define _POWERPC_EEH_H
 #ifdef __KERNEL__
 
 #include <linux/init.h>
@@ -110,6 +110,7 @@ static inline void eeh_remove_bus_device(struct pci_dev *dev) { }
 #define EEH_IO_ERROR_VALUE(size) (-1UL)
 #endif /* CONFIG_EEH */
 
+#ifdef CONFIG_PPC64
 /*
  * MMIO read/write operations with EEH support.
  */
@@ -207,5 +208,6 @@ static inline void eeh_readsl(const volatile void __iomem *addr, void * buf,
 		eeh_check_failure(addr, *(u32*)buf);
 }
 
+#endif /* CONFIG_PPC64 */
 #endif /* __KERNEL__ */
-#endif /* _PPC64_EEH_H */
+#endif /* _POWERPC_EEH_H */

arch/powerpc/include/asm/feature-fixups.h

@@ -81,6 +81,36 @@ label##5:					       	\
 #define ALT_FTR_SECTION_END_IFCLR(msk)	\
 	ALT_FTR_SECTION_END_NESTED_IFCLR(msk, 97)
 
+/* MMU feature dependent sections */
+#define BEGIN_MMU_FTR_SECTION_NESTED(label)	START_FTR_SECTION(label)
+#define BEGIN_MMU_FTR_SECTION			START_FTR_SECTION(97)
+
+#define END_MMU_FTR_SECTION_NESTED(msk, val, label) 		\
+	FTR_SECTION_ELSE_NESTED(label)				\
+	MAKE_FTR_SECTION_ENTRY(msk, val, label, __mmu_ftr_fixup)
+
+#define END_MMU_FTR_SECTION(msk, val)		\
+	END_MMU_FTR_SECTION_NESTED(msk, val, 97)
+
+#define END_MMU_FTR_SECTION_IFSET(msk)	END_MMU_FTR_SECTION((msk), (msk))
+#define END_MMU_FTR_SECTION_IFCLR(msk)	END_MMU_FTR_SECTION((msk), 0)
+
+/* MMU feature sections with alternatives, use BEGIN_FTR_SECTION to start */
+#define MMU_FTR_SECTION_ELSE_NESTED(label)	FTR_SECTION_ELSE_NESTED(label)
+#define MMU_FTR_SECTION_ELSE	MMU_FTR_SECTION_ELSE_NESTED(97)
+#define ALT_MMU_FTR_SECTION_END_NESTED(msk, val, label)	\
+	MAKE_FTR_SECTION_ENTRY(msk, val, label, __mmu_ftr_fixup)
+#define ALT_MMU_FTR_SECTION_END_NESTED_IFSET(msk, label)	\
+	ALT_MMU_FTR_SECTION_END_NESTED(msk, msk, label)
+#define ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(msk, label)	\
+	ALT_MMU_FTR_SECTION_END_NESTED(msk, 0, label)
+#define ALT_MMU_FTR_SECTION_END(msk, val)	\
+	ALT_MMU_FTR_SECTION_END_NESTED(msk, val, 97)
+#define ALT_MMU_FTR_SECTION_END_IFSET(msk)	\
+	ALT_MMU_FTR_SECTION_END_NESTED_IFSET(msk, 97)
+#define ALT_MMU_FTR_SECTION_END_IFCLR(msk)	\
+	ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(msk, 97)
+
 /* Firmware feature dependent sections */
 #define BEGIN_FW_FTR_SECTION_NESTED(label)	START_FTR_SECTION(label)
 #define BEGIN_FW_FTR_SECTION			START_FTR_SECTION(97)

arch/powerpc/include/asm/highmem.h

@@ -38,9 +38,24 @@ extern pte_t *pkmap_page_table;
  * easily, subsequent pte tables have to be allocated in one physical
  * chunk of RAM.
  */
-#define LAST_PKMAP 	(1 << PTE_SHIFT)
-#define LAST_PKMAP_MASK (LAST_PKMAP-1)
+/*
+ * We use one full pte table with 4K pages. And with 16K/64K pages pte
+ * table covers enough memory (32MB and 512MB resp.) that both FIXMAP
+ * and PKMAP can be placed in single pte table. We use 1024 pages for
+ * PKMAP in case of 16K/64K pages.
+ */
+#ifdef CONFIG_PPC_4K_PAGES
+#define PKMAP_ORDER	PTE_SHIFT
+#else
+#define PKMAP_ORDER	10
+#endif
+#define LAST_PKMAP	(1 << PKMAP_ORDER)
+#ifndef CONFIG_PPC_4K_PAGES
+#define PKMAP_BASE	(FIXADDR_START - PAGE_SIZE*(LAST_PKMAP + 1))
+#else
 #define PKMAP_BASE	((FIXADDR_START - PAGE_SIZE*(LAST_PKMAP + 1)) & PMD_MASK)
+#endif
+#define LAST_PKMAP_MASK	(LAST_PKMAP-1)
 #define PKMAP_NR(virt)  ((virt-PKMAP_BASE) >> PAGE_SHIFT)
 #define PKMAP_ADDR(nr)  (PKMAP_BASE + ((nr) << PAGE_SHIFT))
 
@@ -85,7 +100,7 @@ static inline void *kmap_atomic_prot(struct page *page, enum km_type type, pgpro
 	BUG_ON(!pte_none(*(kmap_pte-idx)));
 #endif
 	__set_pte_at(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot));
-	flush_tlb_page(NULL, vaddr);
+	local_flush_tlb_page(NULL, vaddr);
 
 	return (void*) vaddr;
 }
@@ -113,7 +128,7 @@ static inline void kunmap_atomic(void *kvaddr, enum km_type type)
 	 * this pte without first remap it
 	 */
 	pte_clear(&init_mm, vaddr, kmap_pte-idx);
-	flush_tlb_page(NULL, vaddr);
+	local_flush_tlb_page(NULL, vaddr);
 #endif
 	pagefault_enable();
 }

arch/powerpc/include/asm/io.h

@@ -713,13 +713,6 @@ static inline void * phys_to_virt(unsigned long address)
  */
 #define page_to_phys(page)	((phys_addr_t)page_to_pfn(page) << PAGE_SHIFT)
 
-/* We do NOT want virtual merging, it would put too much pressure on
- * our iommu allocator. Instead, we want drivers to be smart enough
- * to coalesce sglists that happen to have been mapped in a contiguous
- * way by the iommu
- */
-#define BIO_VMERGE_BOUNDARY	0
-
 /*
  * 32 bits still uses virt_to_bus() for it's implementation of DMA
  * mappings se we have to keep it defined here. We also have some old

arch/powerpc/include/asm/kdump.h

@@ -1,6 +1,8 @@
 #ifndef _PPC64_KDUMP_H
 #define _PPC64_KDUMP_H
 
+#include <asm/page.h>
+
 /* Kdump kernel runs at 32 MB, change at your peril. */
 #define KDUMP_KERNELBASE	0x2000000
 
@@ -11,8 +13,19 @@
 
 #ifdef CONFIG_CRASH_DUMP
 
+/*
+ * On PPC64 translation is disabled during trampoline setup, so we use
+ * physical addresses. Though on PPC32 translation is already enabled,
+ * so we can't do the same. Luckily create_trampoline() creates relative
+ * branches, so we can just add the PAGE_OFFSET and don't worry about it.
+ */
+#ifdef __powerpc64__
 #define KDUMP_TRAMPOLINE_START	0x0100
 #define KDUMP_TRAMPOLINE_END	0x3000
+#else
+#define KDUMP_TRAMPOLINE_START	(0x0100 + PAGE_OFFSET)
+#define KDUMP_TRAMPOLINE_END	(0x3000 + PAGE_OFFSET)
+#endif /* __powerpc64__ */
 
 #define KDUMP_MIN_TCE_ENTRIES	2048
 

arch/powerpc/include/asm/kexec.h

@@ -33,12 +33,12 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
+#include <asm/reg.h>
 
 typedef void (*crash_shutdown_t)(void);
 
 #ifdef CONFIG_KEXEC
 
-#ifdef __powerpc64__
 /*
  * This function is responsible for capturing register states if coming
  * via panic or invoking dump using sysrq-trigger.
@@ -48,6 +48,7 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 {
 	if (oldregs)
 		memcpy(newregs, oldregs, sizeof(*newregs));
+#ifdef __powerpc64__
 	else {
 		/* FIXME Merge this with xmon_save_regs ?? */
 		unsigned long tmp1, tmp2;
@@ -100,15 +101,11 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 			: "b" (newregs)
 			: "memory");
 	}
-}
 #else
-/*
- * Provide a dummy definition to avoid build failures. Will remain
- * empty till crash dump support is enabled.
- */
-static inline void crash_setup_regs(struct pt_regs *newregs,
-					struct pt_regs *oldregs) { }
-#endif /* !__powerpc64 __ */
+	else
+		ppc_save_regs(newregs);
+#endif /* __powerpc64__ */
+}
 
 extern void kexec_smp_wait(void);	/* get and clear naca physid, wait for
 					  master to copy new code to 0 */

arch/powerpc/include/asm/local.h

@@ -67,7 +67,7 @@ static __inline__ long local_inc_return(local_t *l)
 	bne-	1b"
 	: "=&r" (t)
 	: "r" (&(l->a.counter))
-	: "cc", "memory");
+	: "cc", "xer", "memory");
 
 	return t;
 }
@@ -94,7 +94,7 @@ static __inline__ long local_dec_return(local_t *l)
 	bne-	1b"
 	: "=&r" (t)
 	: "r" (&(l->a.counter))
-	: "cc", "memory");
+	: "cc", "xer", "memory");
 
 	return t;
 }

arch/powerpc/include/asm/lppaca.h

@@ -133,7 +133,8 @@ struct lppaca {
 //=============================================================================
 // CACHE_LINE_4-5 0x0180 - 0x027F Contains PMC interrupt data
 //=============================================================================
-	u8	pmc_save_area[256];	// PMC interrupt Area           x00-xFF
+	u32	page_ins;			// CMO Hint - # page ins by OS  x00-x04
+	u8	pmc_save_area[252];	// PMC interrupt Area           x04-xFF
 } __attribute__((__aligned__(0x400)));
 
 extern struct lppaca lppaca[];

arch/powerpc/include/asm/mmu-40x.h

@@ -54,8 +54,9 @@
 #ifndef __ASSEMBLY__
 
 typedef struct {
-	unsigned long id;
-	unsigned long vdso_base;
+	unsigned int	id;
+	unsigned int	active;
+	unsigned long	vdso_base;
 } mm_context_t;
 
 #endif /* !__ASSEMBLY__ */

arch/powerpc/include/asm/mmu-44x.h

@@ -4,6 +4,8 @@
  * PPC440 support
  */
 
+#include <asm/page.h>
+
 #define PPC44x_MMUCR_TID	0x000000ff
 #define PPC44x_MMUCR_STS	0x00010000
 
@@ -56,8 +58,9 @@
 extern unsigned int tlb_44x_hwater;
 
 typedef struct {
-	unsigned long id;
-	unsigned long vdso_base;
+	unsigned int	id;
+	unsigned int	active;
+	unsigned long	vdso_base;
 } mm_context_t;
 
 #endif /* !__ASSEMBLY__ */
@@ -73,4 +76,19 @@ typedef struct {
 /* Size of the TLBs used for pinning in lowmem */
 #define PPC_PIN_SIZE	(1 << 28)	/* 256M */
 
+#if (PAGE_SHIFT == 12)
+#define PPC44x_TLBE_SIZE	PPC44x_TLB_4K
+#elif (PAGE_SHIFT == 14)
+#define PPC44x_TLBE_SIZE	PPC44x_TLB_16K
+#elif (PAGE_SHIFT == 16)
+#define PPC44x_TLBE_SIZE	PPC44x_TLB_64K
+#else
+#error "Unsupported PAGE_SIZE"
+#endif
+
+#define PPC44x_PGD_OFF_SHIFT	(32 - PGDIR_SHIFT + PGD_T_LOG2)
+#define PPC44x_PGD_OFF_MASK_BIT	(PGDIR_SHIFT - PGD_T_LOG2)
+#define PPC44x_PTE_ADD_SHIFT	(32 - PGDIR_SHIFT + PTE_SHIFT + PTE_T_LOG2)
+#define PPC44x_PTE_ADD_MASK_BIT	(32 - PTE_T_LOG2 - PTE_SHIFT)
+
 #endif /* _ASM_POWERPC_MMU_44X_H_ */

arch/powerpc/include/asm/mmu-8xx.h

@@ -137,7 +137,8 @@
 
 #ifndef __ASSEMBLY__
 typedef struct {
-	unsigned long id;
+	unsigned int id;
+	unsigned int active;
 	unsigned long vdso_base;
 } mm_context_t;
 #endif /* !__ASSEMBLY__ */

arch/powerpc/include/asm/mmu-fsl-booke.h

@@ -40,6 +40,8 @@
 #define MAS2_M		0x00000004
 #define MAS2_G		0x00000002
 #define MAS2_E		0x00000001
+#define MAS2_EPN_MASK(size)		(~0 << (2*(size) + 10))
+#define MAS2_VAL(addr, size, flags)	((addr) & MAS2_EPN_MASK(size) | (flags))
 
 #define MAS3_RPN	0xFFFFF000
 #define MAS3_U0		0x00000200
@@ -74,8 +76,9 @@
 #ifndef __ASSEMBLY__
 
 typedef struct {
-	unsigned long id;
-	unsigned long vdso_base;
+	unsigned int	id;
+	unsigned int	active;
+	unsigned long	vdso_base;
 } mm_context_t;
 #endif /* !__ASSEMBLY__ */
 

arch/powerpc/include/asm/mmu.h

@@ -2,6 +2,63 @@
 #define _ASM_POWERPC_MMU_H_
 #ifdef __KERNEL__
 
+#include <asm/asm-compat.h>
+#include <asm/feature-fixups.h>
+
+/*
+ * MMU features bit definitions
+ */
+
+/*
+ * First half is MMU families
+ */
+#define MMU_FTR_HPTE_TABLE		ASM_CONST(0x00000001)
+#define MMU_FTR_TYPE_8xx		ASM_CONST(0x00000002)
+#define MMU_FTR_TYPE_40x		ASM_CONST(0x00000004)
+#define MMU_FTR_TYPE_44x		ASM_CONST(0x00000008)
+#define MMU_FTR_TYPE_FSL_E		ASM_CONST(0x00000010)
+
+/*
+ * This is individual features
+ */
+
+/* Enable use of high BAT registers */
+#define MMU_FTR_USE_HIGH_BATS		ASM_CONST(0x00010000)
+
+/* Enable >32-bit physical addresses on 32-bit processor, only used
+ * by CONFIG_6xx currently as BookE supports that from day 1
+ */
+#define MMU_FTR_BIG_PHYS		ASM_CONST(0x00020000)
+
+/* Enable use of broadcast TLB invalidations. We don't always set it
+ * on processors that support it due to other constraints with the
+ * use of such invalidations
+ */
+#define MMU_FTR_USE_TLBIVAX_BCAST	ASM_CONST(0x00040000)
+
+/* Enable use of tlbilx invalidate-by-PID variant.
+ */
+#define MMU_FTR_USE_TLBILX_PID		ASM_CONST(0x00080000)
+
+/* This indicates that the processor cannot handle multiple outstanding
+ * broadcast tlbivax or tlbsync. This makes the code use a spinlock
+ * around such invalidate forms.
+ */
+#define MMU_FTR_LOCK_BCAST_INVAL	ASM_CONST(0x00100000)
+
+#ifndef __ASSEMBLY__
+#include <asm/cputable.h>
+
+static inline int mmu_has_feature(unsigned long feature)
+{
+	return (cur_cpu_spec->mmu_features & feature);
+}
+
+extern unsigned int __start___mmu_ftr_fixup, __stop___mmu_ftr_fixup;
+
+#endif /* !__ASSEMBLY__ */
+
+
 #ifdef CONFIG_PPC64
 /* 64-bit classic hash table MMU */
 #  include <asm/mmu-hash64.h>

arch/powerpc/include/asm/mmu_context.h

@@ -2,237 +2,26 @@
 #define __ASM_POWERPC_MMU_CONTEXT_H
 #ifdef __KERNEL__
 
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
 #include <asm/mmu.h>	
 #include <asm/cputable.h>
 #include <asm-generic/mm_hooks.h>
-
-#ifndef CONFIG_PPC64
-#include <asm/atomic.h>
-#include <linux/bitops.h>
+#include <asm/cputhreads.h>
 
 /*
- * On 32-bit PowerPC 6xx/7xx/7xxx CPUs, we use a set of 16 VSIDs
- * (virtual segment identifiers) for each context.  Although the
- * hardware supports 24-bit VSIDs, and thus >1 million contexts,
- * we only use 32,768 of them.  That is ample, since there can be
- * at most around 30,000 tasks in the system anyway, and it means
- * that we can use a bitmap to indicate which contexts are in use.
- * Using a bitmap means that we entirely avoid all of the problems
- * that we used to have when the context number overflowed,
- * particularly on SMP systems.
- *  -- paulus.
+ * Most if the context management is out of line
  */
-
-/*
- * This function defines the mapping from contexts to VSIDs (virtual
- * segment IDs).  We use a skew on both the context and the high 4 bits
- * of the 32-bit virtual address (the "effective segment ID") in order
- * to spread out the entries in the MMU hash table.  Note, if this
- * function is changed then arch/ppc/mm/hashtable.S will have to be
- * changed to correspond.
- */
-#define CTX_TO_VSID(ctx, va)	(((ctx) * (897 * 16) + ((va) >> 28) * 0x111) \
-				 & 0xffffff)
-
-/*
-   The MPC8xx has only 16 contexts.  We rotate through them on each
-   task switch.  A better way would be to keep track of tasks that
-   own contexts, and implement an LRU usage.  That way very active
-   tasks don't always have to pay the TLB reload overhead.  The
-   kernel pages are mapped shared, so the kernel can run on behalf
-   of any task that makes a kernel entry.  Shared does not mean they
-   are not protected, just that the ASID comparison is not performed.
-        -- Dan
-
-   The IBM4xx has 256 contexts, so we can just rotate through these
-   as a way of "switching" contexts.  If the TID of the TLB is zero,
-   the PID/TID comparison is disabled, so we can use a TID of zero
-   to represent all kernel pages as shared among all contexts.
-   	-- Dan
- */
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-}
-
-#ifdef CONFIG_8xx
-#define NO_CONTEXT      	16
-#define LAST_CONTEXT    	15
-#define FIRST_CONTEXT    	0
-
-#elif defined(CONFIG_4xx)
-#define NO_CONTEXT      	256
-#define LAST_CONTEXT    	255
-#define FIRST_CONTEXT    	1
-
-#elif defined(CONFIG_E200) || defined(CONFIG_E500)
-#define NO_CONTEXT      	256
-#define LAST_CONTEXT    	255
-#define FIRST_CONTEXT    	1
-
-#else
-
-/* PPC 6xx, 7xx CPUs */
-#define NO_CONTEXT      	((unsigned long) -1)
-#define LAST_CONTEXT    	32767
-#define FIRST_CONTEXT    	1
-#endif
-
-/*
- * Set the current MMU context.
- * On 32-bit PowerPCs (other than the 8xx embedded chips), this is done by
- * loading up the segment registers for the user part of the address space.
- *
- * Since the PGD is immediately available, it is much faster to simply
- * pass this along as a second parameter, which is required for 8xx and
- * can be used for debugging on all processors (if you happen to have
- * an Abatron).
- */
-extern void set_context(unsigned long contextid, pgd_t *pgd);
-
-/*
- * Bitmap of contexts in use.
- * The size of this bitmap is LAST_CONTEXT + 1 bits.
- */
-extern unsigned long context_map[];
-
-/*
- * This caches the next context number that we expect to be free.
- * Its use is an optimization only, we can't rely on this context
- * number to be free, but it usually will be.
- */
-extern unsigned long next_mmu_context;
-
-/*
- * If we don't have sufficient contexts to give one to every task
- * that could be in the system, we need to be able to steal contexts.
- * These variables support that.
- */
-#if LAST_CONTEXT < 30000
-#define FEW_CONTEXTS	1
-extern atomic_t nr_free_contexts;
-extern struct mm_struct *context_mm[LAST_CONTEXT+1];
-extern void steal_context(void);
-#endif
-
-/*
- * Get a new mmu context for the address space described by `mm'.
- */
-static inline void get_mmu_context(struct mm_struct *mm)
-{
-	unsigned long ctx;
-
-	if (mm->context.id != NO_CONTEXT)
-		return;
-#ifdef FEW_CONTEXTS
-	while (atomic_dec_if_positive(&nr_free_contexts) < 0)
-		steal_context();
-#endif
-	ctx = next_mmu_context;
-	while (test_and_set_bit(ctx, context_map)) {
-		ctx = find_next_zero_bit(context_map, LAST_CONTEXT+1, ctx);
-		if (ctx > LAST_CONTEXT)
-			ctx = 0;
-	}
-	next_mmu_context = (ctx + 1) & LAST_CONTEXT;
-	mm->context.id = ctx;
-#ifdef FEW_CONTEXTS
-	context_mm[ctx] = mm;
-#endif
-}
-
-/*
- * Set up the context for a new address space.
- */
-static inline int init_new_context(struct task_struct *t, struct mm_struct *mm)
-{
-	mm->context.id = NO_CONTEXT;
-	return 0;
-}
-
-/*
- * We're finished using the context for an address space.
- */
-static inline void destroy_context(struct mm_struct *mm)
-{
-	preempt_disable();
-	if (mm->context.id != NO_CONTEXT) {
-		clear_bit(mm->context.id, context_map);
-		mm->context.id = NO_CONTEXT;
-#ifdef FEW_CONTEXTS
-		atomic_inc(&nr_free_contexts);
-#endif
-	}
-	preempt_enable();
-}
-
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
-			     struct task_struct *tsk)
-{
-#ifdef CONFIG_ALTIVEC
-	if (cpu_has_feature(CPU_FTR_ALTIVEC))
-	asm volatile ("dssall;\n"
-#ifndef CONFIG_POWER4
-	 "sync;\n" /* G4 needs a sync here, G5 apparently not */
-#endif
-	 : : );
-#endif /* CONFIG_ALTIVEC */
-
-	tsk->thread.pgdir = next->pgd;
-
-	/* No need to flush userspace segments if the mm doesnt change */
-	if (prev == next)
-		return;
-
-	/* Setup new userspace context */
-	get_mmu_context(next);
-	set_context(next->context.id, next->pgd);
-}
-
-#define deactivate_mm(tsk,mm)	do { } while (0)
-
-/*
- * After we have set current->mm to a new value, this activates
- * the context for the new mm so we see the new mappings.
- */
-#define activate_mm(active_mm, mm)   switch_mm(active_mm, mm, current)
-
 extern void mmu_context_init(void);
-
-
-#else
-
-#include <linux/kernel.h>	
-#include <linux/mm.h>	
-#include <linux/sched.h>
-
-/*
- * Copyright (C) 2001 PPC 64 Team, IBM Corp
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-static inline void enter_lazy_tlb(struct mm_struct *mm,
-				  struct task_struct *tsk)
-{
-}
-
-/*
- * The proto-VSID space has 2^35 - 1 segments available for user mappings.
- * Each segment contains 2^28 bytes.  Each context maps 2^44 bytes,
- * so we can support 2^19-1 contexts (19 == 35 + 28 - 44).
- */
-#define NO_CONTEXT	0
-#define MAX_CONTEXT	((1UL << 19) - 1)
-
 extern int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 extern void destroy_context(struct mm_struct *mm);
 
+extern void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next);
 extern void switch_stab(struct task_struct *tsk, struct mm_struct *mm);
 extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm);
+extern void set_context(unsigned long id, pgd_t *pgd);
 
 /*
  * switch_mm is the entry point called from the architecture independent
@@ -241,22 +30,39 @@ extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm);
 static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 			     struct task_struct *tsk)
 {
-	if (!cpu_isset(smp_processor_id(), next->cpu_vm_mask))
-		cpu_set(smp_processor_id(), next->cpu_vm_mask);
+	/* Mark this context has been used on the new CPU */
+	cpu_set(smp_processor_id(), next->cpu_vm_mask);
 
-	/* No need to flush userspace segments if the mm doesnt change */
+	/* 32-bit keeps track of the current PGDIR in the thread struct */
+#ifdef CONFIG_PPC32
+	tsk->thread.pgdir = next->pgd;
+#endif /* CONFIG_PPC32 */
+
+	/* Nothing else to do if we aren't actually switching */
 	if (prev == next)
 		return;
 
+	/* We must stop all altivec streams before changing the HW
+	 * context
+	 */
 #ifdef CONFIG_ALTIVEC
 	if (cpu_has_feature(CPU_FTR_ALTIVEC))
 		asm volatile ("dssall");
 #endif /* CONFIG_ALTIVEC */
 
+	/* The actual HW switching method differs between the various
+	 * sub architectures.
+	 */
+#ifdef CONFIG_PPC_STD_MMU_64
 	if (cpu_has_feature(CPU_FTR_SLB))
 		switch_slb(tsk, next);
 	else
 		switch_stab(tsk, next);
+#else
+	/* Out of line for now */
+	switch_mmu_context(prev, next);
+#endif
+
 }
 
 #define deactivate_mm(tsk,mm)	do { } while (0)
@@ -274,6 +80,11 @@ static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next)
 	local_irq_restore(flags);
 }
 
-#endif /* CONFIG_PPC64 */
+/* We don't currently use enter_lazy_tlb() for anything */
+static inline void enter_lazy_tlb(struct mm_struct *mm,
+				  struct task_struct *tsk)
+{
+}
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_POWERPC_MMU_CONTEXT_H */

arch/powerpc/include/asm/mpc52xx.h

@@ -239,6 +239,25 @@ struct mpc52xx_cdm {
 	u16 mclken_div_psc6;	/* CDM + 0x36  reg13 byte2,3 */
 };
 
+/* Interrupt controller Register set */
+struct mpc52xx_intr {
+	u32 per_mask;		/* INTR + 0x00 */
+	u32 per_pri1;		/* INTR + 0x04 */
+	u32 per_pri2;		/* INTR + 0x08 */
+	u32 per_pri3;		/* INTR + 0x0c */
+	u32 ctrl;		/* INTR + 0x10 */
+	u32 main_mask;		/* INTR + 0x14 */
+	u32 main_pri1;		/* INTR + 0x18 */
+	u32 main_pri2;		/* INTR + 0x1c */
+	u32 reserved1;		/* INTR + 0x20 */
+	u32 enc_status;		/* INTR + 0x24 */
+	u32 crit_status;	/* INTR + 0x28 */
+	u32 main_status;	/* INTR + 0x2c */
+	u32 per_status;		/* INTR + 0x30 */
+	u32 reserved2;		/* INTR + 0x34 */
+	u32 per_error;		/* INTR + 0x38 */
+};
+
 #endif /* __ASSEMBLY__ */
 
 

arch/powerpc/include/asm/mpc52xx_psc.h

@@ -68,12 +68,20 @@
 #define MPC52xx_PSC_IMR_ORERR		0x1000
 #define MPC52xx_PSC_IMR_IPC		0x8000
 
-/* PSC input port change bit */
+/* PSC input port change bits */
 #define MPC52xx_PSC_CTS			0x01
 #define MPC52xx_PSC_DCD			0x02
 #define MPC52xx_PSC_D_CTS		0x10
 #define MPC52xx_PSC_D_DCD		0x20
 
+/* PSC acr bits */
+#define MPC52xx_PSC_IEC_CTS		0x01
+#define MPC52xx_PSC_IEC_DCD		0x02
+
+/* PSC output port bits */
+#define MPC52xx_PSC_OP_RTS		0x01
+#define MPC52xx_PSC_OP_RES		0x02
+
 /* PSC mode fields */
 #define MPC52xx_PSC_MODE_5_BITS			0x00
 #define MPC52xx_PSC_MODE_6_BITS			0x01
@@ -91,6 +99,7 @@
 #define MPC52xx_PSC_MODE_ONE_STOP_5_BITS	0x00
 #define MPC52xx_PSC_MODE_ONE_STOP		0x07
 #define MPC52xx_PSC_MODE_TWO_STOP		0x0f
+#define MPC52xx_PSC_MODE_TXCTS			0x10
 
 #define MPC52xx_PSC_RFNUM_MASK	0x01ff
 

arch/powerpc/include/asm/mutex.h

@@ -1,9 +1,134 @@
 /*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
+ * Optimised mutex implementation of include/asm-generic/mutex-dec.h algorithm
  */
+#ifndef _ASM_POWERPC_MUTEX_H
+#define _ASM_POWERPC_MUTEX_H
 
-#include <asm-generic/mutex-dec.h>
+static inline int __mutex_cmpxchg_lock(atomic_t *v, int old, int new)
+{
+	int t;
+
+	__asm__ __volatile__ (
+"1:	lwarx	%0,0,%1		# mutex trylock\n\
+	cmpw	0,%0,%2\n\
+	bne-	2f\n"
+	PPC405_ERR77(0,%1)
+"	stwcx.	%3,0,%1\n\
+	bne-	1b"
+	ISYNC_ON_SMP
+	"\n\
+2:"
+	: "=&r" (t)
+	: "r" (&v->counter), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return t;
+}
+
+static inline int __mutex_dec_return_lock(atomic_t *v)
+{
+	int t;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%1		# mutex lock\n\
+	addic	%0,%0,-1\n"
+	PPC405_ERR77(0,%1)
+"	stwcx.	%0,0,%1\n\
+	bne-	1b"
+	ISYNC_ON_SMP
+	: "=&r" (t)
+	: "r" (&v->counter)
+	: "cc", "memory");
+
+	return t;
+}
+
+static inline int __mutex_inc_return_unlock(atomic_t *v)
+{
+	int t;
+
+	__asm__ __volatile__(
+	LWSYNC_ON_SMP
+"1:	lwarx	%0,0,%1		# mutex unlock\n\
+	addic	%0,%0,1\n"
+	PPC405_ERR77(0,%1)
+"	stwcx.	%0,0,%1 \n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (&v->counter)
+	: "cc", "memory");
+
+	return t;
+}
+
+/**
+ *  __mutex_fastpath_lock - try to take the lock by moving the count
+ *                          from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if
+ * it wasn't 1 originally. This function MUST leave the value lower than
+ * 1 even when the "1" assertion wasn't true.
+ */
+static inline void
+__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+	if (unlikely(__mutex_dec_return_lock(count) < 0))
+		fail_fn(count);
+}
+
+/**
+ *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
+ *                                 from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if
+ * it wasn't 1 originally. This function returns 0 if the fastpath succeeds,
+ * or anything the slow path function returns.
+ */
+static inline int
+__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+	if (unlikely(__mutex_dec_return_lock(count) < 0))
+		return fail_fn(count);
+	return 0;
+}
+
+/**
+ *  __mutex_fastpath_unlock - try to promote the count from 0 to 1
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 0
+ *
+ * Try to promote the count from 0 to 1. If it wasn't 0, call <fail_fn>.
+ * In the failure case, this function is allowed to either set the value to
+ * 1, or to set it to a value lower than 1.
+ */
+static inline void
+__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+	if (unlikely(__mutex_inc_return_unlock(count) <= 0))
+		fail_fn(count);
+}
+
+#define __mutex_slowpath_needs_to_unlock()		1
+
+/**
+ * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
+ *
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: fallback function
+ *
+ * Change the count from 1 to 0, and return 1 (success), or if the count
+ * was not 1, then return 0 (failure).
+ */
+static inline int
+__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+	if (likely(__mutex_cmpxchg_lock(count, 1, 0) == 1))
+		return 1;
+	return 0;
+}
+
+#endif

arch/powerpc/include/asm/page.h

@@ -19,12 +19,15 @@
 #include <asm/kdump.h>
 
 /*
- * On PPC32 page size is 4K. For PPC64 we support either 4K or 64K software
+ * On regular PPC32 page size is 4K (but we support 4K/16K/64K pages
+ * on PPC44x). For PPC64 we support either 4K or 64K software
  * page size. When using 64K pages however, whether we are really supporting
  * 64K pages in HW or not is irrelevant to those definitions.
  */
-#ifdef CONFIG_PPC_64K_PAGES
+#if defined(CONFIG_PPC_64K_PAGES)
 #define PAGE_SHIFT		16
+#elif defined(CONFIG_PPC_16K_PAGES)
+#define PAGE_SHIFT		14
 #else
 #define PAGE_SHIFT		12
 #endif
@@ -151,7 +154,7 @@ typedef struct { pte_basic_t pte; } pte_t;
 /* 64k pages additionally define a bigger "real PTE" type that gathers
  * the "second half" part of the PTE for pseudo 64k pages
  */
-#ifdef CONFIG_PPC_64K_PAGES
+#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64)
 typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
 #else
 typedef struct { pte_t pte; } real_pte_t;
@@ -191,10 +194,10 @@ typedef pte_basic_t pte_t;
 #define pte_val(x)	(x)
 #define __pte(x)	(x)
 
-#ifdef CONFIG_PPC_64K_PAGES
+#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64)
 typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
 #else
-typedef unsigned long real_pte_t;
+typedef pte_t real_pte_t;
 #endif
 
 

arch/powerpc/include/asm/page_32.h

@@ -19,6 +19,8 @@
 #define PTE_FLAGS_OFFSET	0
 #endif
 
+#define PTE_SHIFT	(PAGE_SHIFT - PTE_T_LOG2)	/* full page */
+
 #ifndef __ASSEMBLY__
 /*
  * The basic type of a PTE - 64 bits for those CPUs with > 32 bit
@@ -26,10 +28,8 @@
  */
 #ifdef CONFIG_PTE_64BIT
 typedef unsigned long long pte_basic_t;
-#define PTE_SHIFT	(PAGE_SHIFT - 3)	/* 512 ptes per page */
 #else
 typedef unsigned long pte_basic_t;
-#define PTE_SHIFT	(PAGE_SHIFT - 2)	/* 1024 ptes per page */
 #endif
 
 struct page;
@@ -39,6 +39,9 @@ extern void copy_page(void *to, void *from);
 
 #include <asm-generic/page.h>
 
+#define PGD_T_LOG2	(__builtin_ffs(sizeof(pgd_t)) - 1)
+#define PTE_T_LOG2	(__builtin_ffs(sizeof(pte_t)) - 1)
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_PAGE_32_H */

arch/powerpc/include/asm/pci-bridge.h

@@ -13,7 +13,6 @@
 
 struct device_node;
 
-extern unsigned int ppc_pci_flags;
 enum {
 	/* Force re-assigning all resources (ignore firmware
 	 * setup completely)
@@ -36,6 +35,31 @@ enum {
 	/* ... except for domain 0 */
 	PPC_PCI_COMPAT_DOMAIN_0		= 0x00000020,
 };
+#ifdef CONFIG_PCI
+extern unsigned int ppc_pci_flags;
+
+static inline void ppc_pci_set_flags(int flags)
+{
+	ppc_pci_flags = flags;
+}
+
+static inline void ppc_pci_add_flags(int flags)
+{
+	ppc_pci_flags |= flags;
+}
+
+static inline int ppc_pci_has_flag(int flag)
+{
+	return (ppc_pci_flags & flag);
+}
+#else
+static inline void ppc_pci_set_flags(int flags) { }
+static inline void ppc_pci_add_flags(int flags) { }
+static inline int ppc_pci_has_flag(int flag)
+{
+	return 0;
+}
+#endif
 
 
 /*
@@ -241,9 +265,6 @@ extern void pcibios_remove_pci_devices(struct pci_bus *bus);
 
 /** Discover new pci devices under this bus, and add them */
 extern void pcibios_add_pci_devices(struct pci_bus *bus);
-extern void pcibios_fixup_new_pci_devices(struct pci_bus *bus);
-
-extern int pcibios_remove_root_bus(struct pci_controller *phb);
 
 static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus)
 {
@@ -290,6 +311,7 @@ extern void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 /* Allocate & free a PCI host bridge structure */
 extern struct pci_controller *pcibios_alloc_controller(struct device_node *dev);
 extern void pcibios_free_controller(struct pci_controller *phb);
+extern void pcibios_setup_phb_resources(struct pci_controller *hose);
 
 #ifdef CONFIG_PCI
 extern unsigned long pci_address_to_pio(phys_addr_t address);

arch/powerpc/include/asm/pci.h

@@ -38,8 +38,8 @@ struct pci_dev;
  * Set this to 1 if you want the kernel to re-assign all PCI
  * bus numbers (don't do that on ppc64 yet !)
  */
-#define pcibios_assign_all_busses()    	(ppc_pci_flags & \
-					 PPC_PCI_REASSIGN_ALL_BUS)
+#define pcibios_assign_all_busses() \
+	(ppc_pci_has_flag(PPC_PCI_REASSIGN_ALL_BUS))
 #define pcibios_scan_all_fns(a, b)	0
 
 static inline void pcibios_set_master(struct pci_dev *dev)
@@ -204,15 +204,14 @@ static inline struct resource *pcibios_select_root(struct pci_dev *pdev,
 	return root;
 }
 
-extern void pcibios_setup_new_device(struct pci_dev *dev);
-
 extern void pcibios_claim_one_bus(struct pci_bus *b);
 
-extern void pcibios_allocate_bus_resources(struct pci_bus *bus);
+extern void pcibios_finish_adding_to_bus(struct pci_bus *bus);
 
 extern void pcibios_resource_survey(void);
 
 extern struct pci_controller *init_phb_dynamic(struct device_node *dn);
+extern int remove_phb_dynamic(struct pci_controller *phb);
 
 extern struct pci_dev *of_create_pci_dev(struct device_node *node,
 					struct pci_bus *bus, int devfn);
@@ -221,6 +220,7 @@ extern void of_scan_pci_bridge(struct device_node *node,
 				struct pci_dev *dev);
 
 extern void of_scan_bus(struct device_node *node, struct pci_bus *bus);
+extern void of_rescan_bus(struct device_node *node, struct pci_bus *bus);
 
 extern int pci_read_irq_line(struct pci_dev *dev);
 
@@ -235,9 +235,8 @@ extern void pci_resource_to_user(const struct pci_dev *dev, int bar,
 				 const struct resource *rsrc,
 				 resource_size_t *start, resource_size_t *end);
 
-extern void pcibios_do_bus_setup(struct pci_bus *bus);
-extern void pcibios_fixup_of_probed_bus(struct pci_bus *bus);
-
+extern void pcibios_setup_bus_devices(struct pci_bus *bus);
+extern void pcibios_setup_bus_self(struct pci_bus *bus);
 
 #endif	/* __KERNEL__ */
 #endif /* __ASM_POWERPC_PCI_H */

arch/powerpc/include/asm/pgalloc-32.h

@@ -3,6 +3,8 @@
 
 #include <linux/threads.h>
 
+#define PTE_NONCACHE_NUM	0  /* dummy for now to share code w/ppc64 */
+
 extern void __bad_pte(pmd_t *pmd);
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
@@ -33,10 +35,13 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
 extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr);
-extern void pte_free_kernel(struct mm_struct *mm, pte_t *pte);
-extern void pte_free(struct mm_struct *mm, pgtable_t pte);
 
-#define __pte_free_tlb(tlb, pte)	pte_free((tlb)->mm, (pte))
+static inline void pgtable_free(pgtable_free_t pgf)
+{
+	void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
+
+	free_page((unsigned long)p);
+}
 
 #define check_pgt_cache()	do { } while (0)
 

arch/powerpc/include/asm/pgalloc-64.h

@@ -7,7 +7,6 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
@@ -108,31 +107,6 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 	return page;
 }
 
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
-{
-	pgtable_page_dtor(ptepage);
-	__free_page(ptepage);
-}
-
-#define PGF_CACHENUM_MASK	0x7
-
-typedef struct pgtable_free {
-	unsigned long val;
-} pgtable_free_t;
-
-static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
-						unsigned long mask)
-{
-	BUG_ON(cachenum > PGF_CACHENUM_MASK);
-
-	return (pgtable_free_t){.val = ((unsigned long) p & ~mask) | cachenum};
-}
-
 static inline void pgtable_free(pgtable_free_t pgf)
 {
 	void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
@@ -144,14 +118,6 @@ static inline void pgtable_free(pgtable_free_t pgf)
 		kmem_cache_free(pgtable_cache[cachenum], p);
 }
 
-extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
-
-#define __pte_free_tlb(tlb,ptepage)	\
-do { \
-	pgtable_page_dtor(ptepage); \
-	pgtable_free_tlb(tlb, pgtable_free_cache(page_address(ptepage), \
-		PTE_NONCACHE_NUM, PTE_TABLE_SIZE-1)); \
-} while (0)
 #define __pmd_free_tlb(tlb, pmd) 	\
 	pgtable_free_tlb(tlb, pgtable_free_cache(pmd, \
 		PMD_CACHE_NUM, PMD_TABLE_SIZE-1))

arch/powerpc/include/asm/pgalloc.h

@@ -2,11 +2,52 @@
 #define _ASM_POWERPC_PGALLOC_H
 #ifdef __KERNEL__
 
+#include <linux/mm.h>
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
+{
+	pgtable_page_dtor(ptepage);
+	__free_page(ptepage);
+}
+
+typedef struct pgtable_free {
+	unsigned long val;
+} pgtable_free_t;
+
+#define PGF_CACHENUM_MASK	0x7
+
+static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
+						unsigned long mask)
+{
+	BUG_ON(cachenum > PGF_CACHENUM_MASK);
+
+	return (pgtable_free_t){.val = ((unsigned long) p & ~mask) | cachenum};
+}
+
 #ifdef CONFIG_PPC64
 #include <asm/pgalloc-64.h>
 #else
 #include <asm/pgalloc-32.h>
 #endif
 
+extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
+
+#ifdef CONFIG_SMP
+#define __pte_free_tlb(tlb,ptepage)	\
+do { \
+	pgtable_page_dtor(ptepage); \
+	pgtable_free_tlb(tlb, pgtable_free_cache(page_address(ptepage), \
+		PTE_NONCACHE_NUM, PTE_TABLE_SIZE-1)); \
+} while (0)
+#else
+#define __pte_free_tlb(tlb, pte)	pte_free((tlb)->mm, (pte))
+#endif
+
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_PGALLOC_H */

arch/powerpc/include/asm/pgtable-ppc32.h

@@ -228,9 +228,10 @@ extern int icache_44x_need_flush;
  *   - FILE *must* be in the bottom three bits because swap cache
  *     entries use the top 29 bits for TLB2.
  *
- *   - CACHE COHERENT bit (M) has no effect on PPC440 core, because it
- *     doesn't support SMP. So we can use this as software bit, like
- *     DIRTY.
+ *   - CACHE COHERENT bit (M) has no effect on original PPC440 cores,
+ *     because it doesn't support SMP. However, some later 460 variants
+ *     have -some- form of SMP support and so I keep the bit there for
+ *     future use
  *
  * With the PPC 44x Linux implementation, the 0-11th LSBs of the PTE are used
  * for memory protection related functions (see PTE structure in
@@ -436,20 +437,23 @@ extern int icache_44x_need_flush;
 			 _PAGE_USER | _PAGE_ACCESSED | \
 			 _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | \
 			 _PAGE_EXEC | _PAGE_HWEXEC)
-/*
- * Note: the _PAGE_COHERENT bit automatically gets set in the hardware
- * PTE if CONFIG_SMP is defined (hash_page does this); there is no need
- * to have it in the Linux PTE, and in fact the bit could be reused for
- * another purpose.  -- paulus.
- */
 
-#ifdef CONFIG_44x
-#define _PAGE_BASE	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_GUARDED)
+/*
+ * We define 2 sets of base prot bits, one for basic pages (ie,
+ * cacheable kernel and user pages) and one for non cacheable
+ * pages. We always set _PAGE_COHERENT when SMP is enabled or
+ * the processor might need it for DMA coherency.
+ */
+#if defined(CONFIG_SMP) || defined(CONFIG_PPC_STD_MMU)
+#define _PAGE_BASE	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_COHERENT)
 #else
 #define _PAGE_BASE	(_PAGE_PRESENT | _PAGE_ACCESSED)
 #endif
+#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_NO_CACHE)
+
 #define _PAGE_WRENABLE	(_PAGE_RW | _PAGE_DIRTY | _PAGE_HWWRITE)
 #define _PAGE_KERNEL	(_PAGE_BASE | _PAGE_SHARED | _PAGE_WRENABLE)
+#define _PAGE_KERNEL_NC	(_PAGE_BASE_NC | _PAGE_SHARED | _PAGE_WRENABLE)
 
 #ifdef CONFIG_PPC_STD_MMU
 /* On standard PPC MMU, no user access implies kernel read/write access,
@@ -459,7 +463,7 @@ extern int icache_44x_need_flush;
 #define _PAGE_KERNEL_RO	(_PAGE_BASE | _PAGE_SHARED)
 #endif
 
-#define _PAGE_IO	(_PAGE_KERNEL | _PAGE_NO_CACHE | _PAGE_GUARDED)
+#define _PAGE_IO	(_PAGE_KERNEL_NC | _PAGE_GUARDED)
 #define _PAGE_RAM	(_PAGE_KERNEL | _PAGE_HWEXEC)
 
 #if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\
@@ -552,9 +556,6 @@ static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED;
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
 static inline int pte_special(pte_t pte)	{ return pte_val(pte) & _PAGE_SPECIAL; }
 
-static inline void pte_uncache(pte_t pte)       { pte_val(pte) |= _PAGE_NO_CACHE; }
-static inline void pte_cache(pte_t pte)         { pte_val(pte) &= ~_PAGE_NO_CACHE; }
-
 static inline pte_t pte_wrprotect(pte_t pte) {
 	pte_val(pte) &= ~(_PAGE_RW | _PAGE_HWWRITE); return pte; }
 static inline pte_t pte_mkclean(pte_t pte) {
@@ -693,10 +694,11 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 #endif
 }
 
+
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pte)
 {
-#if defined(CONFIG_PTE_64BIT) && defined(CONFIG_SMP)
+#if defined(CONFIG_PTE_64BIT) && defined(CONFIG_SMP) && defined(CONFIG_DEBUG_VM)
 	WARN_ON(pte_present(*ptep));
 #endif
 	__set_pte_at(mm, addr, ptep, pte);
@@ -760,16 +762,6 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry, int dirty)
 	__changed;							   \
 })
 
-/*
- * Macro to mark a page protection value as "uncacheable".
- */
-#define pgprot_noncached(prot)	(__pgprot(pgprot_val(prot) | _PAGE_NO_CACHE | _PAGE_GUARDED))
-
-struct file;
-extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-				     unsigned long size, pgprot_t vma_prot);
-#define __HAVE_PHYS_MEM_ACCESS_PROT
-
 #define __HAVE_ARCH_PTE_SAME
 #define pte_same(A,B)	(((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0)
 

arch/powerpc/include/asm/pgtable-ppc64.h

@@ -100,7 +100,7 @@
 
 #define _PAGE_WRENABLE	(_PAGE_RW | _PAGE_DIRTY)
 
-/* __pgprot defined in arch/powerpc/incliude/asm/page.h */
+/* __pgprot defined in arch/powerpc/include/asm/page.h */
 #define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_ACCESSED)
 
 #define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_RW | _PAGE_USER)
@@ -245,9 +245,6 @@ static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED;}
 static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE;}
 static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; }
 
-static inline void pte_uncache(pte_t pte) { pte_val(pte) |= _PAGE_NO_CACHE; }
-static inline void pte_cache(pte_t pte)   { pte_val(pte) &= ~_PAGE_NO_CACHE; }
-
 static inline pte_t pte_wrprotect(pte_t pte) {
 	pte_val(pte) &= ~(_PAGE_RW); return pte; }
 static inline pte_t pte_mkclean(pte_t pte) {
@@ -405,16 +402,6 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry, int dirty)
 	__changed;							   \
 })
 
-/*
- * Macro to mark a page protection value as "uncacheable".
- */
-#define pgprot_noncached(prot)	(__pgprot(pgprot_val(prot) | _PAGE_NO_CACHE | _PAGE_GUARDED))
-
-struct file;
-extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-				     unsigned long size, pgprot_t vma_prot);
-#define __HAVE_PHYS_MEM_ACCESS_PROT
-
 #define __HAVE_ARCH_PTE_SAME
 #define pte_same(A,B)	(((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0)
 

arch/powerpc/include/asm/pgtable.h

@@ -16,6 +16,32 @@ struct mm_struct;
 #endif
 
 #ifndef __ASSEMBLY__
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ */
+
+#define _PAGE_CACHE_CTL	(_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \
+			 _PAGE_WRITETHRU)
+
+#define pgprot_noncached(prot)	  (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+				            _PAGE_NO_CACHE | _PAGE_GUARDED))
+
+#define pgprot_noncached_wc(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+				            _PAGE_NO_CACHE))
+
+#define pgprot_cached(prot)       (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+				            _PAGE_COHERENT))
+
+#define pgprot_cached_wthru(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+				            _PAGE_COHERENT | _PAGE_WRITETHRU))
+
+
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..

arch/powerpc/include/asm/ppc_asm.h

@@ -425,14 +425,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 #define fromreal(rd)	tovirt(rd,rd)
 
 #define tophys(rd,rs)				\
-0:	addis	rd,rs,-KERNELBASE@h;		\
+0:	addis	rd,rs,-PAGE_OFFSET@h;		\
 	.section ".vtop_fixup","aw";		\
 	.align  1;				\
 	.long   0b;				\
 	.previous
 
 #define tovirt(rd,rs)				\
-0:	addis	rd,rs,KERNELBASE@h;		\
+0:	addis	rd,rs,PAGE_OFFSET@h;		\
 	.section ".ptov_fixup","aw";		\
 	.align  1;				\
 	.long   0b;				\

arch/powerpc/include/asm/processor.h

@@ -69,8 +69,6 @@ extern int _prep_type;
 
 #ifdef __KERNEL__
 
-extern int have_of;
-
 struct task_struct;
 void start_thread(struct pt_regs *regs, unsigned long fdptr, unsigned long sp);
 void release_thread(struct task_struct *);
@@ -207,6 +205,11 @@ struct thread_struct {
 #define INIT_SP_LIMIT \
 	(_ALIGN_UP(sizeof(init_thread_info), 16) + (unsigned long) &init_stack)
 
+#ifdef CONFIG_SPE
+#define SPEFSCR_INIT .spefscr = SPEFSCR_FINVE | SPEFSCR_FDBZE | SPEFSCR_FUNFE | SPEFSCR_FOVFE,
+#else
+#define SPEFSCR_INIT
+#endif
 
 #ifdef CONFIG_PPC32
 #define INIT_THREAD { \
@@ -215,6 +218,7 @@ struct thread_struct {
 	.fs = KERNEL_DS, \
 	.pgdir = swapper_pg_dir, \
 	.fpexc_mode = MSR_FE0 | MSR_FE1, \
+	SPEFSCR_INIT \
 }
 #else
 #define INIT_THREAD  { \

arch/powerpc/include/asm/prom.h

@@ -253,6 +253,9 @@ extern void kdump_move_device_tree(void);
 /* CPU OF node matching */
 struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
 
+/* cache lookup */
+struct device_node *of_find_next_cache_node(struct device_node *np);
+
 /* Get the MAC address */
 extern const void *of_get_mac_address(struct device_node *np);
 

arch/powerpc/include/asm/ps3.h

@@ -305,30 +305,34 @@ static inline const char* ps3_result(int result)
 /* system bus routines */
 
 enum ps3_match_id {
-	PS3_MATCH_ID_EHCI           = 1,
-	PS3_MATCH_ID_OHCI           = 2,
-	PS3_MATCH_ID_GELIC          = 3,
-	PS3_MATCH_ID_AV_SETTINGS    = 4,
-	PS3_MATCH_ID_SYSTEM_MANAGER = 5,
-	PS3_MATCH_ID_STOR_DISK      = 6,
-	PS3_MATCH_ID_STOR_ROM       = 7,
-	PS3_MATCH_ID_STOR_FLASH     = 8,
-	PS3_MATCH_ID_SOUND          = 9,
-	PS3_MATCH_ID_GRAPHICS       = 10,
-	PS3_MATCH_ID_LPM            = 11,
+	PS3_MATCH_ID_EHCI		= 1,
+	PS3_MATCH_ID_OHCI		= 2,
+	PS3_MATCH_ID_GELIC		= 3,
+	PS3_MATCH_ID_AV_SETTINGS	= 4,
+	PS3_MATCH_ID_SYSTEM_MANAGER	= 5,
+	PS3_MATCH_ID_STOR_DISK		= 6,
+	PS3_MATCH_ID_STOR_ROM		= 7,
+	PS3_MATCH_ID_STOR_FLASH		= 8,
+	PS3_MATCH_ID_SOUND		= 9,
+	PS3_MATCH_ID_GPU		= 10,
+	PS3_MATCH_ID_LPM		= 11,
 };
 
-#define PS3_MODULE_ALIAS_EHCI           "ps3:1"
-#define PS3_MODULE_ALIAS_OHCI           "ps3:2"
-#define PS3_MODULE_ALIAS_GELIC          "ps3:3"
-#define PS3_MODULE_ALIAS_AV_SETTINGS    "ps3:4"
-#define PS3_MODULE_ALIAS_SYSTEM_MANAGER "ps3:5"
-#define PS3_MODULE_ALIAS_STOR_DISK      "ps3:6"
-#define PS3_MODULE_ALIAS_STOR_ROM       "ps3:7"
-#define PS3_MODULE_ALIAS_STOR_FLASH     "ps3:8"
-#define PS3_MODULE_ALIAS_SOUND          "ps3:9"
-#define PS3_MODULE_ALIAS_GRAPHICS       "ps3:10"
-#define PS3_MODULE_ALIAS_LPM            "ps3:11"
+enum ps3_match_sub_id {
+	PS3_MATCH_SUB_ID_GPU_FB		= 1,
+};
+
+#define PS3_MODULE_ALIAS_EHCI		"ps3:1:0"
+#define PS3_MODULE_ALIAS_OHCI		"ps3:2:0"
+#define PS3_MODULE_ALIAS_GELIC		"ps3:3:0"
+#define PS3_MODULE_ALIAS_AV_SETTINGS	"ps3:4:0"
+#define PS3_MODULE_ALIAS_SYSTEM_MANAGER	"ps3:5:0"
+#define PS3_MODULE_ALIAS_STOR_DISK	"ps3:6:0"
+#define PS3_MODULE_ALIAS_STOR_ROM	"ps3:7:0"
+#define PS3_MODULE_ALIAS_STOR_FLASH	"ps3:8:0"
+#define PS3_MODULE_ALIAS_SOUND		"ps3:9:0"
+#define PS3_MODULE_ALIAS_GPU_FB		"ps3:10:1"
+#define PS3_MODULE_ALIAS_LPM		"ps3:11:0"
 
 enum ps3_system_bus_device_type {
 	PS3_DEVICE_TYPE_IOC0 = 1,
@@ -337,11 +341,6 @@ enum ps3_system_bus_device_type {
 	PS3_DEVICE_TYPE_LPM,
 };
 
-enum ps3_match_sub_id {
-	/* for PS3_MATCH_ID_GRAPHICS */
-	PS3_MATCH_SUB_ID_FB		= 1,
-};
-
 /**
  * struct ps3_system_bus_device - a device on the system bus
  */
@@ -516,4 +515,7 @@ void ps3_sync_irq(int node);
 u32 ps3_get_hw_thread_id(int cpu);
 u64 ps3_get_spe_id(void *arg);
 
+/* mutex synchronizing GPU accesses and video mode changes */
+extern struct mutex ps3_gpu_mutex;
+
 #endif

arch/powerpc/include/asm/ps3av.h

@@ -740,8 +740,4 @@ extern int ps3av_audio_mute(int);
 extern int ps3av_audio_mute_analog(int);
 extern int ps3av_dev_open(void);
 extern int ps3av_dev_close(void);
-extern void ps3av_register_flip_ctl(void (*flip_ctl)(int on, void *data),
-				    void *flip_data);
-extern void ps3av_flip_ctl(int on);
-
 #endif	/* _ASM_POWERPC_PS3AV_H_ */

arch/powerpc/include/asm/reg.h

@@ -783,6 +783,10 @@ extern void scom970_write(unsigned int address, unsigned long value);
 #define __get_SP()	({unsigned long sp; \
 			asm volatile("mr %0,1": "=r" (sp)); sp;})
 
+struct pt_regs;
+
+extern void ppc_save_regs(struct pt_regs *regs);
+
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_REG_H */

arch/powerpc/include/asm/rtas.h

@@ -168,6 +168,7 @@ extern void rtas_os_term(char *str);
 extern int rtas_get_sensor(int sensor, int index, int *state);
 extern int rtas_get_power_level(int powerdomain, int *level);
 extern int rtas_set_power_level(int powerdomain, int level, int *setlevel);
+extern bool rtas_indicator_present(int token, int *maxindex);
 extern int rtas_set_indicator(int indicator, int index, int new_value);
 extern int rtas_set_indicator_fast(int indicator, int index, int new_value);
 extern void rtas_progress(char *s, unsigned short hex);

arch/powerpc/include/asm/sfp-machine.h

@@ -82,7 +82,7 @@
 #define _FP_MUL_MEAT_S(R,X,Y)   _FP_MUL_MEAT_1_wide(_FP_WFRACBITS_S,R,X,Y,umul_ppmm)
 #define _FP_MUL_MEAT_D(R,X,Y)   _FP_MUL_MEAT_2_wide(_FP_WFRACBITS_D,R,X,Y,umul_ppmm)
 
-#define _FP_DIV_MEAT_S(R,X,Y)	_FP_DIV_MEAT_1_udiv(S,R,X,Y)
+#define _FP_DIV_MEAT_S(R,X,Y)	_FP_DIV_MEAT_1_udiv_norm(S,R,X,Y)
 #define _FP_DIV_MEAT_D(R,X,Y)	_FP_DIV_MEAT_2_udiv(D,R,X,Y)
 
 /* These macros define what NaN looks like. They're supposed to expand to
@@ -97,6 +97,20 @@
 
 #define _FP_KEEPNANFRACP 1
 
+#ifdef FP_EX_BOOKE_E500_SPE
+#define FP_EX_INEXACT		(1 << 21)
+#define FP_EX_INVALID		(1 << 20)
+#define FP_EX_DIVZERO		(1 << 19)
+#define FP_EX_UNDERFLOW		(1 << 18)
+#define FP_EX_OVERFLOW		(1 << 17)
+#define FP_INHIBIT_RESULTS	0
+
+#define __FPU_FPSCR	(current->thread.spefscr)
+#define __FPU_ENABLED_EXC		\
+({					\
+	(__FPU_FPSCR >> 2) & 0x1f;	\
+})
+#else
 /* Exception flags.  We use the bit positions of the appropriate bits
    in the FPSCR, which also correspond to the FE_* bits.  This makes
    everything easier ;-).  */
@@ -111,22 +125,6 @@
 #define FP_EX_DIVZERO         (1 << (31 - 5))
 #define FP_EX_INEXACT         (1 << (31 - 6))
 
-/* This macro appears to be called when both X and Y are NaNs, and
- * has to choose one and copy it to R. i386 goes for the larger of the
- * two, sparc64 just picks Y. I don't understand this at all so I'll
- * go with sparc64 because it's shorter :->   -- PMM
- */
-#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP)		\
-  do {							\
-    R##_s = Y##_s;					\
-    _FP_FRAC_COPY_##wc(R,Y);				\
-    R##_c = FP_CLS_NAN;					\
-  } while (0)
-
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-
 #define __FPU_FPSCR	(current->thread.fpscr.val)
 
 /* We only actually write to the destination register
@@ -137,6 +135,32 @@
 	(__FPU_FPSCR >> 3) & 0x1f;	\
 })
 
+#endif
+
+/*
+ * If one NaN is signaling and the other is not,
+ * we choose that one, otherwise we choose X.
+ */
+#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP)			\
+  do {								\
+    if ((_FP_FRAC_HIGH_RAW_##fs(Y) & _FP_QNANBIT_##fs)		\
+	&& !(_FP_FRAC_HIGH_RAW_##fs(X) & _FP_QNANBIT_##fs))	\
+      {								\
+	R##_s = X##_s;						\
+	_FP_FRAC_COPY_##wc(R,X);				\
+      }								\
+    else							\
+      {								\
+	R##_s = Y##_s;						\
+	_FP_FRAC_COPY_##wc(R,Y);				\
+      }								\
+    R##_c = FP_CLS_NAN;						\
+  } while (0)
+
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+
 #define __FPU_TRAP_P(bits) \
 	((__FPU_ENABLED_EXC & (bits)) != 0)
 

arch/powerpc/include/asm/smp.h

@@ -81,6 +81,13 @@ extern int cpu_to_core_id(int cpu);
 #define PPC_MSG_CALL_FUNC_SINGLE	2
 #define PPC_MSG_DEBUGGER_BREAK  3
 
+/*
+ * irq controllers that have dedicated ipis per message and don't
+ * need additional code in the action handler may use this
+ */
+extern int smp_request_message_ipi(int virq, int message);
+extern const char *smp_ipi_name[];
+
 void smp_init_iSeries(void);
 void smp_init_pSeries(void);
 void smp_init_cell(void);

arch/powerpc/include/asm/spinlock.h

@@ -277,7 +277,7 @@ static inline void __raw_read_unlock(raw_rwlock_t *rw)
 	bne-		1b"
 	: "=&r"(tmp)
 	: "r"(&rw->lock)
-	: "cr0", "memory");
+	: "cr0", "xer", "memory");
 }
 
 static inline void __raw_write_unlock(raw_rwlock_t *rw)

arch/powerpc/include/asm/synch.h

@@ -5,6 +5,10 @@
 #include <linux/stringify.h>
 #include <asm/feature-fixups.h>
 
+#if defined(__powerpc64__) || defined(CONFIG_PPC_E500MC)
+#define __SUBARCH_HAS_LWSYNC
+#endif
+
 #ifndef __ASSEMBLY__
 extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup;
 extern void do_lwsync_fixups(unsigned long value, void *fixup_start,

arch/powerpc/include/asm/system.h

@@ -23,15 +23,17 @@
  * read_barrier_depends() prevents data-dependent loads being reordered
  *	across this point (nop on PPC).
  *
- * We have to use the sync instructions for mb(), since lwsync doesn't
- * order loads with respect to previous stores.  Lwsync is fine for
- * rmb(), though. Note that rmb() actually uses a sync on 32-bit
- * architectures.
+ * *mb() variants without smp_ prefix must order all types of memory
+ * operations with one another. sync is the only instruction sufficient
+ * to do this.
  *
- * For wmb(), we use sync since wmb is used in drivers to order
- * stores to system memory with respect to writes to the device.
- * However, smp_wmb() can be a lighter-weight lwsync or eieio barrier
- * on SMP since it is only used to order updates to system memory.
+ * For the smp_ barriers, ordering is for cacheable memory operations
+ * only. We have to use the sync instruction for smp_mb(), since lwsync
+ * doesn't order loads with respect to previous stores.  Lwsync can be
+ * used for smp_rmb() and smp_wmb().
+ *
+ * However, on CPUs that don't support lwsync, lwsync actually maps to a
+ * heavy-weight sync, so smp_wmb() can be a lighter-weight eieio.
  */
 #define mb()   __asm__ __volatile__ ("sync" : : : "memory")
 #define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
@@ -45,14 +47,14 @@
 #ifdef CONFIG_SMP
 
 #ifdef __SUBARCH_HAS_LWSYNC
-#    define SMPWMB      lwsync
+#    define SMPWMB      LWSYNC
 #else
 #    define SMPWMB      eieio
 #endif
 
 #define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	__asm__ __volatile__ (__stringify(SMPWMB) : : :"memory")
+#define smp_rmb()	__asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+#define smp_wmb()	__asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
 #define smp_read_barrier_depends()	read_barrier_depends()
 #else
 #define smp_mb()	barrier()

arch/powerpc/include/asm/time.h

@@ -48,26 +48,6 @@ extern unsigned long ppc_proc_freq;
 extern unsigned long ppc_tb_freq;
 #define DEFAULT_TB_FREQ		125000000UL
 
-/*
- * By putting all of this stuff into a single struct we 
- * reduce the number of cache lines touched by do_gettimeofday.
- * Both by collecting all of the data in one cache line and
- * by touching only one TOC entry on ppc64.
- */
-struct gettimeofday_vars {
-	u64 tb_to_xs;
-	u64 stamp_xsec;
-	u64 tb_orig_stamp;
-};
-
-struct gettimeofday_struct {
-	unsigned long tb_ticks_per_sec;
-	struct gettimeofday_vars vars[2];
-	struct gettimeofday_vars * volatile varp;
-	unsigned      var_idx;
-	unsigned      tb_to_us;
-};
-
 struct div_result {
 	u64 result_high;
 	u64 result_low;

arch/powerpc/include/asm/tlbflush.h

@@ -6,6 +6,9 @@
  *
  *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
  *  - flush_tlb_page(vma, vmaddr) flushes one page
+ *  - local_flush_tlb_mm(mm) flushes the specified mm context on
+ *                           the local processor
+ *  - local_flush_tlb_page(vma, vmaddr) flushes one page on the local processor
  *  - flush_tlb_page_nohash(vma, vmaddr) flushes one page if SW loaded TLB
  *  - flush_tlb_range(vma, start, end) flushes a range of pages
  *  - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
@@ -17,7 +20,7 @@
  */
 #ifdef __KERNEL__
 
-#if defined(CONFIG_4xx) || defined(CONFIG_8xx) || defined(CONFIG_FSL_BOOKE)
+#ifdef CONFIG_PPC_MMU_NOHASH
 /*
  * TLB flushing for software loaded TLB chips
  *
@@ -28,63 +31,49 @@
 
 #include <linux/mm.h>
 
-extern void _tlbie(unsigned long address, unsigned int pid);
-extern void _tlbil_all(void);
-extern void _tlbil_pid(unsigned int pid);
-extern void _tlbil_va(unsigned long address, unsigned int pid);
+#define MMU_NO_CONTEXT      	((unsigned int)-1)
 
-#if defined(CONFIG_40x) || defined(CONFIG_8xx)
-#define _tlbia()	asm volatile ("tlbia; sync" : : : "memory")
-#else /* CONFIG_44x || CONFIG_FSL_BOOKE */
-extern void _tlbia(void);
+extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			    unsigned long end);
+extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+
+extern void local_flush_tlb_mm(struct mm_struct *mm);
+extern void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
+
+#ifdef CONFIG_SMP
+extern void flush_tlb_mm(struct mm_struct *mm);
+extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
+#else
+#define flush_tlb_mm(mm)		local_flush_tlb_mm(mm)
+#define flush_tlb_page(vma,addr)	local_flush_tlb_page(vma,addr)
 #endif
+#define flush_tlb_page_nohash(vma,addr)	flush_tlb_page(vma,addr)
 
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
-	_tlbil_pid(mm->context.id);
-}
+#elif defined(CONFIG_PPC_STD_MMU_32)
 
-static inline void flush_tlb_page(struct vm_area_struct *vma,
-				  unsigned long vmaddr)
-{
-	_tlbil_va(vmaddr, vma ? vma->vm_mm->context.id : 0);
-}
-
-static inline void flush_tlb_page_nohash(struct vm_area_struct *vma,
-					 unsigned long vmaddr)
-{
-	flush_tlb_page(vma, vmaddr);
-}
-
-static inline void flush_tlb_range(struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end)
-{
-	_tlbil_pid(vma->vm_mm->context.id);
-}
-
-static inline void flush_tlb_kernel_range(unsigned long start,
-					  unsigned long end)
-{
-	_tlbil_pid(0);
-}
-
-#elif defined(CONFIG_PPC32)
 /*
- * TLB flushing for "classic" hash-MMMU 32-bit CPUs, 6xx, 7xx, 7xxx
+ * TLB flushing for "classic" hash-MMU 32-bit CPUs, 6xx, 7xx, 7xxx
  */
-extern void _tlbie(unsigned long address);
-extern void _tlbia(void);
-
 extern void flush_tlb_mm(struct mm_struct *mm);
 extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 extern void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr);
 extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			    unsigned long end);
 extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+static inline void local_flush_tlb_page(struct vm_area_struct *vma,
+					unsigned long vmaddr)
+{
+	flush_tlb_page(vma, vmaddr);
+}
+static inline void local_flush_tlb_mm(struct mm_struct *mm)
+{
+	flush_tlb_mm(mm);
+}
+
+#elif defined(CONFIG_PPC_STD_MMU_64)
 
-#else
 /*
- * TLB flushing for 64-bit has-MMU CPUs
+ * TLB flushing for 64-bit hash-MMU CPUs
  */
 
 #include <linux/percpu.h>
@@ -134,10 +123,19 @@ extern void flush_hash_page(unsigned long va, real_pte_t pte, int psize,
 extern void flush_hash_range(unsigned long number, int local);
 
 
+static inline void local_flush_tlb_mm(struct mm_struct *mm)
+{
+}
+
 static inline void flush_tlb_mm(struct mm_struct *mm)
 {
 }
 
+static inline void local_flush_tlb_page(struct vm_area_struct *vma,
+					unsigned long vmaddr)
+{
+}
+
 static inline void flush_tlb_page(struct vm_area_struct *vma,
 				  unsigned long vmaddr)
 {
@@ -162,7 +160,8 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 extern void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
 				     unsigned long end);
 
-
+#else
+#error Unsupported MMU type
 #endif
 
 #endif /*__KERNEL__ */

arch/powerpc/include/asm/vdso_datapage.h

@@ -39,6 +39,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/unistd.h>
+#include <linux/time.h>
 
 #define SYSCALL_MAP_SIZE      ((__NR_syscalls + 31) / 32)
 
@@ -83,6 +84,7 @@ struct vdso_data {
 	__u32 icache_log_block_size;		/* L1 i-cache log block size */
 	__s32 wtom_clock_sec;			/* Wall to monotonic clock */
 	__s32 wtom_clock_nsec;
+	struct timespec stamp_xtime;	/* xtime as at tb_orig_stamp */
    	__u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls  */
    	__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
 };
@@ -102,6 +104,7 @@ struct vdso_data {
 	__u32 tz_dsttime;		/* Type of dst correction	0x5C */
 	__s32 wtom_clock_sec;			/* Wall to monotonic clock */
 	__s32 wtom_clock_nsec;
+	struct timespec stamp_xtime;	/* xtime as at tb_orig_stamp */
    	__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
 	__u32 dcache_block_size;	/* L1 d-cache block size     */
 	__u32 icache_block_size;	/* L1 i-cache block size     */