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

Pull powerpc updates from Benjamin Herrenschmidt:
 "Notable highlights:

   - iommu improvements from Anton removing the per-iommu global lock in
     favor of dividing the DMA space into pools, each with its own lock,
     and hashed on the CPU number.  Along with making the locking more
     fine grained, this gives significant improvements in multiqueue
     networking scalability.

   - Still from Anton, we know provide a vdso based variant of getcpu
     which makes sched_getcpu with the appropriate glibc patch something
     like 18 times faster.

   - More anton goodness (he's been busy !) in other areas such as a
     faster __clear_user and copy_page on P7, various perf fixes to
     improve sampling quality, etc...

   - One more step toward removing legacy i2c interfaces by using new
     device-tree based probing of platform devices for the AOA audio
     drivers

   - A nice series of patches from Michael Neuling that helps avoiding
     confusion between register numbers and litterals in assembly code,
     trying to enforce the use of "%rN" register names in gas rather
     than plain numbers.

   - A pile of FSL updates

   - The usual bunch of small fixes, cleanups etc...

  You may spot a change to drivers/char/mem.  The patch got no comment
  or ack from outside, it's a trivial patch to allow the architecture to
  skip creating /dev/port, which we use to disable it on ppc64 that
  don't have a legacy brige.  On those, IO ports 0...64K are not mapped
  in kernel space at all, so accesses to /dev/port cause oopses (and
  yes, distros -still- ship userspace that bangs hard coded ports such
  as kbdrate)."

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (106 commits)
  powerpc/mpic: Create a revmap with enough entries for IPIs and timers
  Remove stale .rej file
  powerpc/iommu: Fix iommu pool initialization
  powerpc/eeh: Check handle_eeh_events() return value
  powerpc/85xx: Add phy nodes in SGMII mode for MPC8536/44/72DS & P2020DS
  powerpc/e500: add paravirt QEMU platform
  powerpc/mpc85xx_ds: convert to unified PCI init
  powerpc/fsl-pci: get PCI init out of board files
  powerpc/85xx: Update corenet64_smp_defconfig
  powerpc/85xx: Update corenet32_smp_defconfig
  powerpc/85xx: Rename P1021RDB-PC device trees to be consistent
  powerpc/watchdog: move booke watchdog param related code to setup-common.c
  sound/aoa: Adapt to new i2c probing scheme
  i2c/powermac: Improve detection of devices from device-tree
  powerpc: Disable /dev/port interface on systems without an ISA bridge
  of: Improve prom_update_property() function
  powerpc: Add "memory" attribute for mfmsr()
  powerpc/ftrace: Fix assembly trampoline register usage
  powerpc/hw_breakpoints: Fix incorrect pointer access
  powerpc: Put the gpr save/restore functions in their own section
  ...

19 files changed, 237 insertions, 124 deletions

diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h
index 5d7fbe1950f..6e82f5f9a6f 100644
--- a/arch/powerpc/include/asm/asm-compat.h
+++ b/arch/powerpc/include/asm/asm-compat.h
@@ -29,7 +29,7 @@
 #define PPC_LLARX(t, a, b, eh)	PPC_LDARX(t, a, b, eh)
 #define PPC_STLCX	stringify_in_c(stdcx.)
 #define PPC_CNTLZL	stringify_in_c(cntlzd)
-#define PPC_MTOCRF(FXM, RS) MTOCRF((FXM), (RS))
+#define PPC_MTOCRF(FXM, RS) MTOCRF((FXM), RS)
 #define PPC_LR_STKOFF	16
 #define PPC_MIN_STKFRM	112
 #else /* 32-bit */
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index 37c32aba79b..a6f8c7a5cbb 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -26,8 +26,8 @@ unsigned int create_branch(const unsigned int *addr,
 			   unsigned long target, int flags);
 unsigned int create_cond_branch(const unsigned int *addr,
 				unsigned long target, int flags);
-void patch_branch(unsigned int *addr, unsigned long target, int flags);
-void patch_instruction(unsigned int *addr, unsigned int instr);
+int patch_branch(unsigned int *addr, unsigned long target, int flags);
+int patch_instruction(unsigned int *addr, unsigned int instr);
 
 int instr_is_relative_branch(unsigned int instr);
 int instr_is_branch_to_addr(const unsigned int *instr, unsigned long addr);
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 63d5ca49cec..77e97dd0c15 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -34,6 +34,9 @@ struct dev_archdata {
 #ifdef CONFIG_EEH
 	struct eeh_dev		*edev;
 #endif
+#ifdef CONFIG_FAIL_IOMMU
+	int fail_iommu;
+#endif
 };
 
 struct pdev_archdata {
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index d58fc4e4149..a43c1473915 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -293,7 +293,7 @@ label##_hv:								\
 
 #define RUNLATCH_ON				\
 BEGIN_FTR_SECTION				\
-	clrrdi	r3,r1,THREAD_SHIFT;		\
+	CURRENT_THREAD_INFO(r3, r1);		\
 	ld	r4,TI_LOCAL_FLAGS(r3);		\
 	andi.	r0,r4,_TLF_RUNLATCH;		\
 	beql	ppc64_runlatch_on_trampoline;	\
@@ -332,7 +332,7 @@ label##_common:							\
 #ifdef CONFIG_PPC_970_NAP
 #define FINISH_NAP				\
 BEGIN_FTR_SECTION				\
-	clrrdi	r11,r1,THREAD_SHIFT;		\
+	CURRENT_THREAD_INFO(r11, r1);		\
 	ld	r9,TI_LOCAL_FLAGS(r11);		\
 	andi.	r10,r9,_TLF_NAPPING;		\
 	bnel	power4_fixup_nap;		\
diff --git a/arch/powerpc/include/asm/immap_qe.h b/arch/powerpc/include/asm/immap_qe.h
index 0edb6842b13..61e8490786b 100644
--- a/arch/powerpc/include/asm/immap_qe.h
+++ b/arch/powerpc/include/asm/immap_qe.h
@@ -26,7 +26,9 @@
 struct qe_iram {
 	__be32	iadd;		/* I-RAM Address Register */
 	__be32	idata;		/* I-RAM Data Register */
-	u8	res0[0x78];
+	u8	res0[0x04];
+	__be32	iready;		/* I-RAM Ready Register */
+	u8	res1[0x70];
 } __attribute__ ((packed));
 
 /* QE Interrupt Controller */
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index a3855b81ead..f94ef4213e9 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -20,6 +20,14 @@ extern int check_legacy_ioport(unsigned long base_port);
 #define _PNPWRP		0xa79
 #define PNPBIOS_BASE	0xf000
 
+#if defined(CONFIG_PPC64) && defined(CONFIG_PCI)
+extern struct pci_dev *isa_bridge_pcidev;
+/*
+ * has legacy ISA devices ?
+ */
+#define arch_has_dev_port()	(isa_bridge_pcidev != NULL)
+#endif
+
 #include <linux/device.h>
 #include <linux/io.h>
 
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 957a83f4364..cbfe678e3db 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -53,6 +53,16 @@ static __inline__ __attribute_const__ int get_iommu_order(unsigned long size)
  */
 #define IOMAP_MAX_ORDER		13
 
+#define IOMMU_POOL_HASHBITS	2
+#define IOMMU_NR_POOLS		(1 << IOMMU_POOL_HASHBITS)
+
+struct iommu_pool {
+	unsigned long start;
+	unsigned long end;
+	unsigned long hint;
+	spinlock_t lock;
+} ____cacheline_aligned_in_smp;
+
 struct iommu_table {
 	unsigned long  it_busno;     /* Bus number this table belongs to */
 	unsigned long  it_size;      /* Size of iommu table in entries */
@@ -61,10 +71,10 @@ struct iommu_table {
 	unsigned long  it_index;     /* which iommu table this is */
 	unsigned long  it_type;      /* type: PCI or Virtual Bus */
 	unsigned long  it_blocksize; /* Entries in each block (cacheline) */
-	unsigned long  it_hint;      /* Hint for next alloc */
-	unsigned long  it_largehint; /* Hint for large allocs */
-	unsigned long  it_halfpoint; /* Breaking point for small/large allocs */
-	spinlock_t     it_lock;      /* Protects it_map */
+	unsigned long  poolsize;
+	unsigned long  nr_pools;
+	struct iommu_pool large_pool;
+	struct iommu_pool pools[IOMMU_NR_POOLS];
 	unsigned long *it_map;       /* A simple allocation bitmap for now */
 };
 
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 88609b23b77..bfcd00c1485 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -74,6 +74,7 @@ struct kvmppc_host_state {
 	ulong vmhandler;
 	ulong scratch0;
 	ulong scratch1;
+	ulong sprg3;
 	u8 in_guest;
 	u8 restore_hid5;
 	u8 napping;
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index f0145522cfb..e8a26db2e8f 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -163,12 +163,7 @@ extern u64 ppc64_rma_size;
  * to think about, feedback welcome. --BenH.
  */
 
-/* There are #define as they have to be used in assembly
- *
- * WARNING: If you change this list, make sure to update the array of
- * names currently in arch/powerpc/mm/hugetlbpage.c or bad things will
- * happen
- */
+/* These are #defines as they have to be used in assembly */
 #define MMU_PAGE_4K	0
 #define MMU_PAGE_16K	1
 #define MMU_PAGE_64K	2
diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h
index 5c16b891d50..0bb23725b1e 100644
--- a/arch/powerpc/include/asm/perf_event.h
+++ b/arch/powerpc/include/asm/perf_event.h
@@ -26,8 +26,13 @@
 #include <asm/ptrace.h>
 #include <asm/reg.h>
 
+/*
+ * Overload regs->result to specify whether we should use the MSR (result
+ * is zero) or the SIAR (result is non zero).
+ */
 #define perf_arch_fetch_caller_regs(regs, __ip)			\
 	do {							\
+		(regs)->result = 0;				\
 		(regs)->nip = __ip;				\
 		(regs)->gpr[1] = *(unsigned long *)__get_SP();	\
 		asm volatile("mfmsr %0" : "=r" ((regs)->msr));	\
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index d81f99430fe..4c25319f2fb 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -15,6 +15,72 @@
 #include <linux/stringify.h>
 #include <asm/asm-compat.h>
 
+#define	__REG_R0	0
+#define	__REG_R1	1
+#define	__REG_R2	2
+#define	__REG_R3	3
+#define	__REG_R4	4
+#define	__REG_R5	5
+#define	__REG_R6	6
+#define	__REG_R7	7
+#define	__REG_R8	8
+#define	__REG_R9	9
+#define	__REG_R10	10
+#define	__REG_R11	11
+#define	__REG_R12	12
+#define	__REG_R13	13
+#define	__REG_R14	14
+#define	__REG_R15	15
+#define	__REG_R16	16
+#define	__REG_R17	17
+#define	__REG_R18	18
+#define	__REG_R19	19
+#define	__REG_R20	20
+#define	__REG_R21	21
+#define	__REG_R22	22
+#define	__REG_R23	23
+#define	__REG_R24	24
+#define	__REG_R25	25
+#define	__REG_R26	26
+#define	__REG_R27	27
+#define	__REG_R28	28
+#define	__REG_R29	29
+#define	__REG_R30	30
+#define	__REG_R31	31
+
+#define	__REGA0_0	0
+#define	__REGA0_R1	1
+#define	__REGA0_R2	2
+#define	__REGA0_R3	3
+#define	__REGA0_R4	4
+#define	__REGA0_R5	5
+#define	__REGA0_R6	6
+#define	__REGA0_R7	7
+#define	__REGA0_R8	8
+#define	__REGA0_R9	9
+#define	__REGA0_R10	10
+#define	__REGA0_R11	11
+#define	__REGA0_R12	12
+#define	__REGA0_R13	13
+#define	__REGA0_R14	14
+#define	__REGA0_R15	15
+#define	__REGA0_R16	16
+#define	__REGA0_R17	17
+#define	__REGA0_R18	18
+#define	__REGA0_R19	19
+#define	__REGA0_R20	20
+#define	__REGA0_R21	21
+#define	__REGA0_R22	22
+#define	__REGA0_R23	23
+#define	__REGA0_R24	24
+#define	__REGA0_R25	25
+#define	__REGA0_R26	26
+#define	__REGA0_R27	27
+#define	__REGA0_R28	28
+#define	__REGA0_R29	29
+#define	__REGA0_R30	30
+#define	__REGA0_R31	31
+
 /* sorted alphabetically */
 #define PPC_INST_DCBA			0x7c0005ec
 #define PPC_INST_DCBA_MASK		0xfc0007fe
@@ -107,12 +173,19 @@
 #define PPC_INST_NEG			0x7c0000d0
 #define PPC_INST_BRANCH			0x48000000
 #define PPC_INST_BRANCH_COND		0x40800000
+#define PPC_INST_LBZCIX			0x7c0006aa
+#define PPC_INST_STBCIX			0x7c0007aa
 
 /* macros to insert fields into opcodes */
-#define __PPC_RA(a)	(((a) & 0x1f) << 16)
-#define __PPC_RB(b)	(((b) & 0x1f) << 11)
-#define __PPC_RS(s)	(((s) & 0x1f) << 21)
-#define __PPC_RT(s)	__PPC_RS(s)
+#define ___PPC_RA(a)	(((a) & 0x1f) << 16)
+#define ___PPC_RB(b)	(((b) & 0x1f) << 11)
+#define ___PPC_RS(s)	(((s) & 0x1f) << 21)
+#define ___PPC_RT(t)	___PPC_RS(t)
+#define __PPC_RA(a)	___PPC_RA(__REG_##a)
+#define __PPC_RA0(a)	___PPC_RA(__REGA0_##a)
+#define __PPC_RB(b)	___PPC_RB(__REG_##b)
+#define __PPC_RS(s)	___PPC_RS(__REG_##s)
+#define __PPC_RT(t)	___PPC_RT(__REG_##t)
 #define __PPC_XA(a)	((((a) & 0x1f) << 16) | (((a) & 0x20) >> 3))
 #define __PPC_XB(b)	((((b) & 0x1f) << 11) | (((b) & 0x20) >> 4))
 #define __PPC_XS(s)	((((s) & 0x1f) << 21) | (((s) & 0x20) >> 5))
@@ -141,13 +214,13 @@
 #define	PPC_DCBZL(a, b)		stringify_in_c(.long PPC_INST_DCBZL | \
 					__PPC_RA(a) | __PPC_RB(b))
 #define PPC_LDARX(t, a, b, eh)	stringify_in_c(.long PPC_INST_LDARX | \
-					__PPC_RT(t) | __PPC_RA(a) | \
-					__PPC_RB(b) | __PPC_EH(eh))
+					___PPC_RT(t) | ___PPC_RA(a) | \
+					___PPC_RB(b) | __PPC_EH(eh))
 #define PPC_LWARX(t, a, b, eh)	stringify_in_c(.long PPC_INST_LWARX | \
-					__PPC_RT(t) | __PPC_RA(a) | \
-					__PPC_RB(b) | __PPC_EH(eh))
+					___PPC_RT(t) | ___PPC_RA(a) | \
+					___PPC_RB(b) | __PPC_EH(eh))
 #define PPC_MSGSND(b)		stringify_in_c(.long PPC_INST_MSGSND | \
-					__PPC_RB(b))
+					___PPC_RB(b))
 #define PPC_POPCNTB(a, s)	stringify_in_c(.long PPC_INST_POPCNTB | \
 					__PPC_RA(a) | __PPC_RS(s))
 #define PPC_POPCNTD(a, s)	stringify_in_c(.long PPC_INST_POPCNTD | \
@@ -158,34 +231,39 @@
 #define PPC_RFDI		stringify_in_c(.long PPC_INST_RFDI)
 #define PPC_RFMCI		stringify_in_c(.long PPC_INST_RFMCI)
 #define PPC_TLBILX(t, a, b)	stringify_in_c(.long PPC_INST_TLBILX | \
-					__PPC_T_TLB(t) | __PPC_RA(a) | __PPC_RB(b))
+					__PPC_T_TLB(t) | __PPC_RA0(a) | __PPC_RB(b))
 #define PPC_TLBILX_ALL(a, b)	PPC_TLBILX(0, a, b)
 #define PPC_TLBILX_PID(a, b)	PPC_TLBILX(1, a, b)
 #define PPC_TLBILX_VA(a, b)	PPC_TLBILX(3, a, b)
 #define PPC_WAIT(w)		stringify_in_c(.long PPC_INST_WAIT | \
 					__PPC_WC(w))
 #define PPC_TLBIE(lp,a) 	stringify_in_c(.long PPC_INST_TLBIE | \
-					       __PPC_RB(a) | __PPC_RS(lp))
+					       ___PPC_RB(a) | ___PPC_RS(lp))
 #define PPC_TLBSRX_DOT(a,b)	stringify_in_c(.long PPC_INST_TLBSRX_DOT | \
-					__PPC_RA(a) | __PPC_RB(b))
+					__PPC_RA0(a) | __PPC_RB(b))
 #define PPC_TLBIVAX(a,b)	stringify_in_c(.long PPC_INST_TLBIVAX | \
-					__PPC_RA(a) | __PPC_RB(b))
+					__PPC_RA0(a) | __PPC_RB(b))
 
 #define PPC_ERATWE(s, a, w)	stringify_in_c(.long PPC_INST_ERATWE | \
 					__PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w))
 #define PPC_ERATRE(s, a, w)	stringify_in_c(.long PPC_INST_ERATRE | \
 					__PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w))
 #define PPC_ERATILX(t, a, b)	stringify_in_c(.long PPC_INST_ERATILX | \
-					__PPC_T_TLB(t) | __PPC_RA(a) | \
+					__PPC_T_TLB(t) | __PPC_RA0(a) | \
 					__PPC_RB(b))
 #define PPC_ERATIVAX(s, a, b)	stringify_in_c(.long PPC_INST_ERATIVAX | \
-					__PPC_RS(s) | __PPC_RA(a) | __PPC_RB(b))
+					__PPC_RS(s) | __PPC_RA0(a) | __PPC_RB(b))
 #define PPC_ERATSX(t, a, w)	stringify_in_c(.long PPC_INST_ERATSX | \
-					__PPC_RS(t) | __PPC_RA(a) | __PPC_RB(b))
+					__PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b))
 #define PPC_ERATSX_DOT(t, a, w)	stringify_in_c(.long PPC_INST_ERATSX_DOT | \
-					__PPC_RS(t) | __PPC_RA(a) | __PPC_RB(b))
+					__PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b))
 #define PPC_SLBFEE_DOT(t, b)	stringify_in_c(.long PPC_INST_SLBFEE | \
 					__PPC_RT(t) | __PPC_RB(b))
+/* PASemi instructions */
+#define LBZCIX(t,a,b)		stringify_in_c(.long PPC_INST_LBZCIX | \
+				       __PPC_RT(t) | __PPC_RA(a) | __PPC_RB(b))
+#define STBCIX(s,a,b)		stringify_in_c(.long PPC_INST_STBCIX | \
+				       __PPC_RS(s) | __PPC_RA(a) | __PPC_RB(b))
 
 /*
  * Define what the VSX XX1 form instructions will look like, then add
@@ -194,11 +272,11 @@
 #define VSX_XX1(s, a, b)	(__PPC_XS(s) | __PPC_RA(a) | __PPC_RB(b))
 #define VSX_XX3(t, a, b)	(__PPC_XT(t) | __PPC_XA(a) | __PPC_XB(b))
 #define STXVD2X(s, a, b)	stringify_in_c(.long PPC_INST_STXVD2X | \
-					       VSX_XX1((s), (a), (b)))
+					       VSX_XX1((s), a, b))
 #define LXVD2X(s, a, b)		stringify_in_c(.long PPC_INST_LXVD2X | \
-					       VSX_XX1((s), (a), (b)))
+					       VSX_XX1((s), a, b))
 #define XXLOR(t, a, b)		stringify_in_c(.long PPC_INST_XXLOR | \
-					       VSX_XX3((t), (a), (b)))
+					       VSX_XX3((t), a, b))
 
 #define PPC_NAP			stringify_in_c(.long PPC_INST_NAP)
 #define PPC_SLEEP		stringify_in_c(.long PPC_INST_SLEEP)
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 15444204a3a..ea2a86e8ff9 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -126,26 +126,26 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #define REST_32VRS(n,b,base)	REST_16VRS(n,b,base); REST_16VRS(n+16,b,base)
 
 /* Save the lower 32 VSRs in the thread VSR region */
-#define SAVE_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n));  STXVD2X(n,base,b)
+#define SAVE_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n));  STXVD2X(n,R##base,R##b)
 #define SAVE_2VSRS(n,b,base)	SAVE_VSR(n,b,base); SAVE_VSR(n+1,b,base)
 #define SAVE_4VSRS(n,b,base)	SAVE_2VSRS(n,b,base); SAVE_2VSRS(n+2,b,base)
 #define SAVE_8VSRS(n,b,base)	SAVE_4VSRS(n,b,base); SAVE_4VSRS(n+4,b,base)
 #define SAVE_16VSRS(n,b,base)	SAVE_8VSRS(n,b,base); SAVE_8VSRS(n+8,b,base)
 #define SAVE_32VSRS(n,b,base)	SAVE_16VSRS(n,b,base); SAVE_16VSRS(n+16,b,base)
-#define REST_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n)); LXVD2X(n,base,b)
+#define REST_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n)); LXVD2X(n,R##base,R##b)
 #define REST_2VSRS(n,b,base)	REST_VSR(n,b,base); REST_VSR(n+1,b,base)
 #define REST_4VSRS(n,b,base)	REST_2VSRS(n,b,base); REST_2VSRS(n+2,b,base)
 #define REST_8VSRS(n,b,base)	REST_4VSRS(n,b,base); REST_4VSRS(n+4,b,base)
 #define REST_16VSRS(n,b,base)	REST_8VSRS(n,b,base); REST_8VSRS(n+8,b,base)
 #define REST_32VSRS(n,b,base)	REST_16VSRS(n,b,base); REST_16VSRS(n+16,b,base)
 /* Save the upper 32 VSRs (32-63) in the thread VSX region (0-31) */
-#define SAVE_VSRU(n,b,base)	li b,THREAD_VR0+(16*(n));  STXVD2X(n+32,base,b)
+#define SAVE_VSRU(n,b,base)	li b,THREAD_VR0+(16*(n));  STXVD2X(n+32,R##base,R##b)
 #define SAVE_2VSRSU(n,b,base)	SAVE_VSRU(n,b,base); SAVE_VSRU(n+1,b,base)
 #define SAVE_4VSRSU(n,b,base)	SAVE_2VSRSU(n,b,base); SAVE_2VSRSU(n+2,b,base)
 #define SAVE_8VSRSU(n,b,base)	SAVE_4VSRSU(n,b,base); SAVE_4VSRSU(n+4,b,base)
 #define SAVE_16VSRSU(n,b,base)	SAVE_8VSRSU(n,b,base); SAVE_8VSRSU(n+8,b,base)
 #define SAVE_32VSRSU(n,b,base)	SAVE_16VSRSU(n,b,base); SAVE_16VSRSU(n+16,b,base)
-#define REST_VSRU(n,b,base)	li b,THREAD_VR0+(16*(n)); LXVD2X(n+32,base,b)
+#define REST_VSRU(n,b,base)	li b,THREAD_VR0+(16*(n)); LXVD2X(n+32,R##base,R##b)
 #define REST_2VSRSU(n,b,base)	REST_VSRU(n,b,base); REST_VSRU(n+1,b,base)
 #define REST_4VSRSU(n,b,base)	REST_2VSRSU(n,b,base); REST_2VSRSU(n+2,b,base)
 #define REST_8VSRSU(n,b,base)	REST_4VSRSU(n,b,base); REST_4VSRSU(n+4,b,base)
@@ -178,9 +178,24 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #define HMT_HIGH	or	3,3,3
 #define HMT_EXTRA_HIGH	or	7,7,7		# power7 only
 
+#ifdef CONFIG_PPC64
+#define ULONG_SIZE 	8
+#else
+#define ULONG_SIZE	4
+#endif
+#define __VCPU_GPR(n)	(VCPU_GPRS + (n * ULONG_SIZE))
+#define VCPU_GPR(n)	__VCPU_GPR(__REG_##n)
+
 #ifdef __KERNEL__
 #ifdef CONFIG_PPC64
 
+#define STACKFRAMESIZE 256
+#define __STK_REG(i)   (112 + ((i)-14)*8)
+#define STK_REG(i)     __STK_REG(__REG_##i)
+
+#define __STK_PARAM(i)	(48 + ((i)-3)*8)
+#define STK_PARAM(i)	__STK_PARAM(__REG_##i)
+
 #define XGLUE(a,b) a##b
 #define GLUE(a,b) XGLUE(a,b)
 
@@ -295,14 +310,14 @@ n:
  */
 #ifdef __powerpc64__
 #define LOAD_REG_IMMEDIATE(reg,expr)		\
-	lis     (reg),(expr)@highest;		\
-	ori     (reg),(reg),(expr)@higher;	\
-	rldicr  (reg),(reg),32,31;		\
-	oris    (reg),(reg),(expr)@h;		\
-	ori     (reg),(reg),(expr)@l;
+	lis     reg,(expr)@highest;		\
+	ori     reg,reg,(expr)@higher;	\
+	rldicr  reg,reg,32,31;		\
+	oris    reg,reg,(expr)@h;		\
+	ori     reg,reg,(expr)@l;
 
 #define LOAD_REG_ADDR(reg,name)			\
-	ld	(reg),name@got(r2)
+	ld	reg,name@got(r2)
 
 #define LOAD_REG_ADDRBASE(reg,name)	LOAD_REG_ADDR(reg,name)
 #define ADDROFF(name)			0
@@ -313,12 +328,12 @@ n:
 #else /* 32-bit */
 
 #define LOAD_REG_IMMEDIATE(reg,expr)		\
-	lis	(reg),(expr)@ha;		\
-	addi	(reg),(reg),(expr)@l;
+	lis	reg,(expr)@ha;		\
+	addi	reg,reg,(expr)@l;
 
 #define LOAD_REG_ADDR(reg,name)		LOAD_REG_IMMEDIATE(reg, name)
 
-#define LOAD_REG_ADDRBASE(reg, name)	lis	(reg),name@ha
+#define LOAD_REG_ADDRBASE(reg, name)	lis	reg,name@ha
 #define ADDROFF(name)			name@l
 
 /* offsets for stack frame layout */
@@ -372,9 +387,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 #ifdef CONFIG_PPC64
 #define MTOCRF(FXM, RS)			\
 	BEGIN_FTR_SECTION_NESTED(848);	\
-	mtcrf	(FXM), (RS);		\
+	mtcrf	(FXM), RS;		\
 	FTR_SECTION_ELSE_NESTED(848);	\
-	mtocrf (FXM), (RS);		\
+	mtocrf (FXM), RS;		\
 	ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_NOEXECUTE, 848)
 #endif
 
@@ -463,6 +478,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 #ifdef CONFIG_PPC_BOOK3S_64
 #define RFI		rfid
 #define MTMSRD(r)	mtmsrd	r
+#define MTMSR_EERI(reg)	mtmsrd	reg,1
 #else
 #define FIX_SRR1(ra, rb)
 #ifndef CONFIG_40x
@@ -471,6 +487,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 #define RFI		rfi; b .	/* Prevent prefetch past rfi */
 #endif
 #define MTMSRD(r)	mtmsr	r
+#define MTMSR_EERI(reg)	mtmsr	reg
 #define CLR_TOP32(r)
 #endif
 
@@ -490,40 +507,46 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 #define	cr7	7
 
 
-/* General Purpose Registers (GPRs) */
-
-#define	r0	0
-#define	r1	1
-#define	r2	2
-#define	r3	3
-#define	r4	4
-#define	r5	5
-#define	r6	6
-#define	r7	7
-#define	r8	8
-#define	r9	9
-#define	r10	10
-#define	r11	11
-#define	r12	12
-#define	r13	13
-#define	r14	14
-#define	r15	15
-#define	r16	16
-#define	r17	17
-#define	r18	18
-#define	r19	19
-#define	r20	20
-#define	r21	21
-#define	r22	22
-#define	r23	23
-#define	r24	24
-#define	r25	25
-#define	r26	26
-#define	r27	27
-#define	r28	28
-#define	r29	29
-#define	r30	30
-#define	r31	31
+/*
+ * General Purpose Registers (GPRs)
+ *
+ * The lower case r0-r31 should be used in preference to the upper
+ * case R0-R31 as they provide more error checking in the assembler.
+ * Use R0-31 only when really nessesary.
+ */
+
+#define	r0	%r0
+#define	r1	%r1
+#define	r2	%r2
+#define	r3	%r3
+#define	r4	%r4
+#define	r5	%r5
+#define	r6	%r6
+#define	r7	%r7
+#define	r8	%r8
+#define	r9	%r9
+#define	r10	%r10
+#define	r11	%r11
+#define	r12	%r12
+#define	r13	%r13
+#define	r14	%r14
+#define	r15	%r15
+#define	r16	%r16
+#define	r17	%r17
+#define	r18	%r18
+#define	r19	%r19
+#define	r20	%r20
+#define	r21	%r21
+#define	r22	%r22
+#define	r23	%r23
+#define	r24	%r24
+#define	r25	%r25
+#define	r26	%r26
+#define	r27	%r27
+#define	r28	%r28
+#define	r29	%r29
+#define	r30	%r30
+#define	r31	%r31
 
 
 /* Floating Point Registers (FPRs) */
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 413a5eaef56..53b6dfa8334 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -389,10 +389,8 @@ extern int powersave_nap;	/* set if nap mode can be used in idle loop */
 
 #ifdef CONFIG_PSERIES_IDLE
 extern void update_smt_snooze_delay(int snooze);
-extern int pseries_notify_cpuidle_add_cpu(int cpu);
 #else
 static inline void update_smt_snooze_delay(int snooze) {}
-static inline int pseries_notify_cpuidle_add_cpu(int cpu) { return 0; }
 #endif
 
 extern void flush_instruction_cache(void);
diff --git a/arch/powerpc/include/asm/qe.h b/arch/powerpc/include/asm/qe.h
index 5e0b6d511e1..229571a4939 100644
--- a/arch/powerpc/include/asm/qe.h
+++ b/arch/powerpc/include/asm/qe.h
@@ -499,6 +499,7 @@ enum comm_dir {
 /* I-RAM */
 #define QE_IRAM_IADD_AIE	0x80000000	/* Auto Increment Enable */
 #define QE_IRAM_IADD_BADDR	0x00080000	/* Base Address */
+#define QE_IRAM_READY           0x80000000      /* Ready */
 
 /* UPC */
 #define UPGCR_PROTOCOL	0x80000000	/* protocol ul2 or pl2 */
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index f0cb7f461b9..638608677e2 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -491,6 +491,7 @@
 #define SPRN_SPRG1	0x111	/* Special Purpose Register General 1 */
 #define SPRN_SPRG2	0x112	/* Special Purpose Register General 2 */
 #define SPRN_SPRG3	0x113	/* Special Purpose Register General 3 */
+#define SPRN_USPRG3	0x103	/* SPRG3 userspace read */
 #define SPRN_SPRG4	0x114	/* Special Purpose Register General 4 */
 #define SPRN_SPRG5	0x115	/* Special Purpose Register General 5 */
 #define SPRN_SPRG6	0x116	/* Special Purpose Register General 6 */
@@ -753,14 +754,14 @@
  * 64-bit server:
  *	- SPRG0 unused (reserved for HV on Power4)
  *	- SPRG2 scratch for exception vectors
- *	- SPRG3 unused (user visible)
+ *	- SPRG3 CPU and NUMA node for VDSO getcpu (user visible)
  *      - HSPRG0 stores PACA in HV mode
  *      - HSPRG1 scratch for "HV" exceptions
  *
  * 64-bit embedded
  *	- SPRG0 generic exception scratch
  *	- SPRG2 TLB exception stack
- *	- SPRG3 unused (user visible)
+ *	- SPRG3 CPU and NUMA node for VDSO getcpu (user visible)
  *	- SPRG4 unused (user visible)
  *	- SPRG6 TLB miss scratch (user visible, sorry !)
  *	- SPRG7 critical exception scratch
@@ -1024,7 +1025,8 @@
 /* Macros for setting and retrieving special purpose registers */
 #ifndef __ASSEMBLY__
 #define mfmsr()		({unsigned long rval; \
-			asm volatile("mfmsr %0" : "=r" (rval)); rval;})
+			asm volatile("mfmsr %0" : "=r" (rval) : \
+						: "memory"); rval;})
 #ifdef CONFIG_PPC_BOOK3S_64
 #define __mtmsrd(v, l)	asm volatile("mtmsrd %0," __stringify(l) \
 				     : : "r" (v) : "memory")
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 68831e9cf82..faf93529cbf 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -22,6 +22,12 @@
 
 #define THREAD_SIZE		(1 << THREAD_SHIFT)
 
+#ifdef CONFIG_PPC64
+#define CURRENT_THREAD_INFO(dest, sp)	clrrdi dest, sp, THREAD_SHIFT
+#else
+#define CURRENT_THREAD_INFO(dest, sp)	rlwinm dest, sp, 0, 0, 31-THREAD_SHIFT
+#endif
+
 #ifndef __ASSEMBLY__
 #include <linux/cache.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h
index cbe2297d68b..5712f06905a 100644
--- a/arch/powerpc/include/asm/trace.h
+++ b/arch/powerpc/include/asm/trace.h
@@ -8,7 +8,7 @@
 
 struct pt_regs;
 
-TRACE_EVENT(irq_entry,
+DECLARE_EVENT_CLASS(ppc64_interrupt_class,
 
 	TP_PROTO(struct pt_regs *regs),
 
@@ -25,55 +25,32 @@ TRACE_EVENT(irq_entry,
 	TP_printk("pt_regs=%p", __entry->regs)
 );
 
-TRACE_EVENT(irq_exit,
+DEFINE_EVENT(ppc64_interrupt_class, irq_entry,
 
 	TP_PROTO(struct pt_regs *regs),
 
-	TP_ARGS(regs),
-
-	TP_STRUCT__entry(
-		__field(struct pt_regs *, regs)
-	),
-
-	TP_fast_assign(
-		__entry->regs = regs;
-	),
-
-	TP_printk("pt_regs=%p", __entry->regs)
+	TP_ARGS(regs)
 );
 
-TRACE_EVENT(timer_interrupt_entry,
+DEFINE_EVENT(ppc64_interrupt_class, irq_exit,
 
 	TP_PROTO(struct pt_regs *regs),
 
-	TP_ARGS(regs),
-
-	TP_STRUCT__entry(
-		__field(struct pt_regs *, regs)
-	),
-
-	TP_fast_assign(
-		__entry->regs = regs;
-	),
-
-	TP_printk("pt_regs=%p", __entry->regs)
+	TP_ARGS(regs)
 );
 
-TRACE_EVENT(timer_interrupt_exit,
+DEFINE_EVENT(ppc64_interrupt_class, timer_interrupt_entry,
 
 	TP_PROTO(struct pt_regs *regs),
 
-	TP_ARGS(regs),
+	TP_ARGS(regs)
+);
 
-	TP_STRUCT__entry(
-		__field(struct pt_regs *, regs)
-	),
+DEFINE_EVENT(ppc64_interrupt_class, timer_interrupt_exit,
 
-	TP_fast_assign(
-		__entry->regs = regs;
-	),
+	TP_PROTO(struct pt_regs *regs),
 
-	TP_printk("pt_regs=%p", __entry->regs)
+	TP_ARGS(regs)
 );
 
 #ifdef CONFIG_PPC_PSERIES
diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h
index dc0419b66f1..50f261bc3e9 100644
--- a/arch/powerpc/include/asm/vdso.h
+++ b/arch/powerpc/include/asm/vdso.h
@@ -22,6 +22,8 @@ extern unsigned long vdso64_rt_sigtramp;
 extern unsigned long vdso32_sigtramp;
 extern unsigned long vdso32_rt_sigtramp;
 
+int __cpuinit vdso_getcpu_init(void);
+
 #else /* __ASSEMBLY__ */
 
 #ifdef __VDSO64__
diff --git a/arch/powerpc/include/asm/vio.h b/arch/powerpc/include/asm/vio.h
index b19adf751dd..df81cb72d1e 100644
--- a/arch/powerpc/include/asm/vio.h
+++ b/arch/powerpc/include/asm/vio.h
@@ -44,6 +44,8 @@
  */
 #define VIO_CMO_MIN_ENT 1562624
 
+extern struct bus_type vio_bus_type;
+
 struct iommu_table;
 
 /*