41 files changed, 958 insertions, 493 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 8e5e2c74971e..9ba1bb731fcc 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -18,12 +18,10 @@ CFLAGS_REMOVE_cputable.o = -pg -mno-sched-epilog
 CFLAGS_REMOVE_prom_init.o = -pg -mno-sched-epilog
 CFLAGS_REMOVE_btext.o = -pg -mno-sched-epilog
 CFLAGS_REMOVE_prom.o = -pg -mno-sched-epilog
-
-ifdef CONFIG_DYNAMIC_FTRACE
-# dynamic ftrace setup.
+# do not trace tracer code
 CFLAGS_REMOVE_ftrace.o = -pg -mno-sched-epilog
-endif
-
+# timers used by tracing
+CFLAGS_REMOVE_time.o = -pg -mno-sched-epilog
 endif
 
 obj-y                           := cputable.o ptrace.o syscalls.o \
@@ -61,6 +59,7 @@ obj-$(CONFIG_HIBERNATION)	+= swsusp.o suspend.o \
 obj64-$(CONFIG_HIBERNATION)     += swsusp_asm64.o
 obj-$(CONFIG_MODULES)           += module.o module_$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_44x)               += cpu_setup_44x.o
+obj-$(CONFIG_FSL_BOOKE)         += cpu_setup_fsl_booke.o dbell.o
 
 extra-$(CONFIG_PPC_STD_MMU)     := head_32.o
 extra-$(CONFIG_PPC64)           := head_64.o
@@ -76,7 +75,7 @@ obj-y				+= time.o prom.o traps.o setup-common.o \
 obj-$(CONFIG_PPC32)             += entry_32.o setup_32.o
 obj-$(CONFIG_PPC64)             += dma-iommu.o iommu.o
 obj-$(CONFIG_KGDB)              += kgdb.o
-obj-$(CONFIG_PPC_MULTIPLATFORM) += prom_init.o
+obj-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE)    += prom_init.o
 obj-$(CONFIG_MODULES)           += ppc_ksyms.o
 obj-$(CONFIG_BOOTX_TEXT)        += btext.o
 obj-$(CONFIG_SMP)               += smp.o
@@ -94,6 +93,7 @@ obj-$(CONFIG_AUDIT)		+= audit.o
 obj64-$(CONFIG_AUDIT)           += compat_audit.o
 
 obj-$(CONFIG_DYNAMIC_FTRACE)    += ftrace.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER)     += ftrace.o
 obj-$(CONFIG_PERF_COUNTERS)     += perf_counter.o power4-pmu.o ppc970-pmu.o \
                                    power5-pmu.o power5+-pmu.o power6-pmu.o
 
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 73cb6a3229ae..5ffcfaa77d6a 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -187,7 +187,7 @@ static struct aligninfo aligninfo[128] = {
         { 4, ST+F+S+U },        /* 11 1 1010: stfsux */
         { 8, ST+F+U },          /* 11 1 1011: stfdux */
         INVALID,                /* 11 1 1100 */
-        INVALID,                /* 11 1 1101 */
+        { 4, LD+F },            /* 11 1 1101: lfiwzx */
         INVALID,                /* 11 1 1110 */
         INVALID,                /* 11 1 1111 */
 };
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 3734973f7394..e981d1ce1914 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -49,7 +49,7 @@
 #include <asm/iseries/alpaca.h>
 #endif
 #ifdef CONFIG_KVM
-#include <asm/kvm_44x.h>
+#include <linux/kvm_host.h>
 #endif
 
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
@@ -285,9 +285,6 @@ int main(void)
 #endif /* ! CONFIG_PPC64 */
 
         /* About the CPU features table */
-        DEFINE(CPU_SPEC_ENTRY_SIZE, sizeof(struct cpu_spec));
-        DEFINE(CPU_SPEC_PVR_MASK, offsetof(struct cpu_spec, pvr_mask));
-        DEFINE(CPU_SPEC_PVR_VALUE, offsetof(struct cpu_spec, pvr_value));
         DEFINE(CPU_SPEC_FEATURES, offsetof(struct cpu_spec, cpu_features));
         DEFINE(CPU_SPEC_SETUP, offsetof(struct cpu_spec, cpu_setup));
         DEFINE(CPU_SPEC_RESTORE, offsetof(struct cpu_spec, cpu_restore));
@@ -362,8 +359,6 @@ int main(void)
         DEFINE(PTE_SIZE, sizeof(pte_t));
 
 #ifdef CONFIG_KVM
-        DEFINE(TLBE_BYTES, sizeof(struct kvmppc_44x_tlbe));
-
         DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
         DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
         DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
diff --git a/arch/powerpc/kernel/cpu_setup_44x.S b/arch/powerpc/kernel/cpu_setup_44x.S
index 10b4ab1008af..7d606f89a839 100644
--- a/arch/powerpc/kernel/cpu_setup_44x.S
+++ b/arch/powerpc/kernel/cpu_setup_44x.S
@@ -34,6 +34,7 @@ _GLOBAL(__setup_cpu_440grx)
         blr
 _GLOBAL(__setup_cpu_460ex)
 _GLOBAL(__setup_cpu_460gt)
+_GLOBAL(__setup_cpu_460sx)
         mflr    r4
         bl      __init_fpu_44x
         bl      __fixup_440A_mcheck
diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index 72d1d7395254..54f767e31a1a 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -15,9 +15,14 @@
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/cache.h>
+#include <asm/mmu.h>
 
 _GLOBAL(__setup_cpu_603)
         mflr    r4
+BEGIN_MMU_FTR_SECTION
+        li      r10,0
+        mtspr   SPRN_SPRG4,r10          /* init SW LRU tracking */
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
 BEGIN_FTR_SECTION
         bl      __init_fpu_registers
 END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE)
diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
new file mode 100644
index 000000000000..eb4b9adcedb4
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -0,0 +1,31 @@
+/*
+ * This file contains low level CPU setup functions.
+ * Kumar Gala <galak@kernel.crashing.org>
+ * Copyright 2009 Freescale Semiconductor, Inc.
+ *
+ * Based on cpu_setup_6xx code by
+ * Benjamin Herrenschmidt <benh@kernel.crashing.org>
+ *
+ * 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.
+ *
+ */
+
+#include <asm/processor.h>
+#include <asm/cputable.h>
+#include <asm/ppc_asm.h>
+
+_GLOBAL(__setup_cpu_e200)
+        /* enable dedicated debug exception handling resources (Debug APU) */
+        mfspr   r3,SPRN_HID0
+        ori     r3,r3,HID0_DAPUEN@l
+        mtspr   SPRN_HID0,r3
+        b       __setup_e200_ivors
+_GLOBAL(__setup_cpu_e500v1)
+_GLOBAL(__setup_cpu_e500v2)
+        b       __setup_e500_ivors
+_GLOBAL(__setup_cpu_e500mc)
+        b       __setup_e500mc_ivors
+
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 923f87aff20a..cd1b687544f3 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -35,6 +35,10 @@ const char *powerpc_base_platform;
  * and ppc64
  */
 #ifdef CONFIG_PPC32
+extern void __setup_cpu_e200(unsigned long offset, struct cpu_spec* spec);
+extern void __setup_cpu_e500v1(unsigned long offset, struct cpu_spec* spec);
+extern void __setup_cpu_e500v2(unsigned long offset, struct cpu_spec* spec);
+extern void __setup_cpu_e500mc(unsigned long offset, struct cpu_spec* spec);
 extern void __setup_cpu_440ep(unsigned long offset, struct cpu_spec* spec);
 extern void __setup_cpu_440epx(unsigned long offset, struct cpu_spec* spec);
 extern void __setup_cpu_440gx(unsigned long offset, struct cpu_spec* spec);
@@ -43,6 +47,7 @@ extern void __setup_cpu_440spe(unsigned long offset, struct cpu_spec* spec);
 extern void __setup_cpu_440x5(unsigned long offset, struct cpu_spec* spec);
 extern void __setup_cpu_460ex(unsigned long offset, struct cpu_spec* spec);
 extern void __setup_cpu_460gt(unsigned long offset, struct cpu_spec* spec);
+extern void __setup_cpu_460sx(unsigned long offset, struct cpu_spec *spec);
 extern void __setup_cpu_603(unsigned long offset, struct cpu_spec* spec);
 extern void __setup_cpu_604(unsigned long offset, struct cpu_spec* spec);
 extern void __setup_cpu_750(unsigned long offset, struct cpu_spec* spec);
@@ -726,6 +731,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_setup              = __setup_cpu_750,
                 .machine_check          = machine_check_generic,
                 .platform               = "ppc750",
+                .oprofile_cpu_type      = "ppc/750",
+                .oprofile_type          = PPC_OPROFILE_G4,
         },
         {       /* 750FX rev 2.0 must disable HID0[DPM] */
                 .pvr_mask               = 0xffffffff,
@@ -741,6 +748,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_setup              = __setup_cpu_750,
                 .machine_check          = machine_check_generic,
                 .platform               = "ppc750",
+                .oprofile_cpu_type      = "ppc/750",
+                .oprofile_type          = PPC_OPROFILE_G4,
         },
         {       /* 750FX (All revs except 2.0) */
                 .pvr_mask               = 0xffff0000,
@@ -756,6 +765,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_setup              = __setup_cpu_750fx,
                 .machine_check          = machine_check_generic,
                 .platform               = "ppc750",
+                .oprofile_cpu_type      = "ppc/750",
+                .oprofile_type          = PPC_OPROFILE_G4,
         },
         {       /* 750GX */
                 .pvr_mask               = 0xffff0000,
@@ -771,6 +782,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_setup              = __setup_cpu_750fx,
                 .machine_check          = machine_check_generic,
                 .platform               = "ppc750",
+                .oprofile_cpu_type      = "ppc/750",
+                .oprofile_type          = PPC_OPROFILE_G4,
         },
         {       /* 740/750 (L2CR bit need fixup for 740) */
                 .pvr_mask               = 0xffff0000,
@@ -1077,7 +1090,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "e300c2",
                 .cpu_features           = CPU_FTRS_E300C2,
                 .cpu_user_features      = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
-                .mmu_features           = MMU_FTR_USE_HIGH_BATS,
+                .mmu_features           = MMU_FTR_USE_HIGH_BATS |
+                        MMU_FTR_NEED_DTLB_SW_LRU,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_603,
@@ -1090,7 +1104,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "e300c3",
                 .cpu_features           = CPU_FTRS_E300,
                 .cpu_user_features      = COMMON_USER,
-                .mmu_features           = MMU_FTR_USE_HIGH_BATS,
+                .mmu_features           = MMU_FTR_USE_HIGH_BATS |
+                        MMU_FTR_NEED_DTLB_SW_LRU,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_603,
@@ -1105,7 +1120,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "e300c4",
                 .cpu_features           = CPU_FTRS_E300,
                 .cpu_user_features      = COMMON_USER,
-                .mmu_features           = MMU_FTR_USE_HIGH_BATS,
+                .mmu_features           = MMU_FTR_USE_HIGH_BATS |
+                        MMU_FTR_NEED_DTLB_SW_LRU,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_603,
@@ -1634,6 +1650,19 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .machine_check          = machine_check_440A,
                 .platform               = "ppc440",
         },
+        { /* 460SX */
+                .pvr_mask               = 0xffffff00,
+                .pvr_value              = 0x13541800,
+                .cpu_name               = "460SX",
+                .cpu_features           = CPU_FTRS_44X,
+                .cpu_user_features      = COMMON_USER_BOOKE,
+                .mmu_features           = MMU_FTR_TYPE_44x,
+                .icache_bsize           = 32,
+                .dcache_bsize           = 32,
+                .cpu_setup              = __setup_cpu_460sx,
+                .machine_check          = machine_check_440A,
+                .platform               = "ppc440",
+        },
         {       /* default match */
                 .pvr_mask               = 0x00000000,
                 .pvr_value              = 0x00000000,
@@ -1687,6 +1716,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                         PPC_FEATURE_UNIFIED_CACHE,
                 .mmu_features           = MMU_FTR_TYPE_FSL_E,
                 .dcache_bsize           = 32,
+                .cpu_setup              = __setup_cpu_e200,
                 .machine_check          = machine_check_e200,
                 .platform               = "ppc5554",
         }
@@ -1706,6 +1736,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .num_pmcs               = 4,
                 .oprofile_cpu_type      = "ppc/e500",
                 .oprofile_type          = PPC_OPROFILE_FSL_EMB,
+                .cpu_setup              = __setup_cpu_e500v1,
                 .machine_check          = machine_check_e500,
                 .platform               = "ppc8540",
         },
@@ -1724,6 +1755,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .num_pmcs               = 4,
                 .oprofile_cpu_type      = "ppc/e500",
                 .oprofile_type          = PPC_OPROFILE_FSL_EMB,
+                .cpu_setup              = __setup_cpu_e500v2,
                 .machine_check          = machine_check_e500,
                 .platform               = "ppc8548",
         },
@@ -1733,12 +1765,14 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "e500mc",
                 .cpu_features           = CPU_FTRS_E500MC,
                 .cpu_user_features      = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
-                .mmu_features           = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS,
+                .mmu_features           = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS |
+                        MMU_FTR_USE_TLBILX,
                 .icache_bsize           = 64,
                 .dcache_bsize           = 64,
                 .num_pmcs               = 4,
                 .oprofile_cpu_type      = "ppc/e500", /* xxx - galak, e500mc? */
                 .oprofile_type          = PPC_OPROFILE_FSL_EMB,
+                .cpu_setup              = __setup_cpu_e500mc,
                 .machine_check          = machine_check_e500,
                 .platform               = "ppce500mc",
         },
@@ -1762,74 +1796,84 @@ static struct cpu_spec __initdata cpu_specs[] = {
 
 static struct cpu_spec the_cpu_spec;
 
-struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr)
+static void __init setup_cpu_spec(unsigned long offset, struct cpu_spec *s)
 {
-        struct cpu_spec *s = cpu_specs;
         struct cpu_spec *t = &the_cpu_spec;
-        int i;
+        struct cpu_spec old;
 
-        s = PTRRELOC(s);
         t = PTRRELOC(t);
+        old = *t;
 
-        for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++)
-                if ((pvr & s->pvr_mask) == s->pvr_value) {
-                        /*
-                         * If we are overriding a previous value derived
-                         * from the real PVR with a new value obtained
-                         * using a logical PVR value, don't modify the
-                         * performance monitor fields.
-                         */
-                        if (t->num_pmcs && !s->num_pmcs) {
-                                t->cpu_name = s->cpu_name;
-                                t->cpu_features = s->cpu_features;
-                                t->cpu_user_features = s->cpu_user_features;
-                                t->icache_bsize = s->icache_bsize;
-                                t->dcache_bsize = s->dcache_bsize;
-                                t->cpu_setup = s->cpu_setup;
-                                t->cpu_restore = s->cpu_restore;
-                                t->platform = s->platform;
-                                /*
-                                 * If we have passed through this logic once
-                                 * before and have pulled the default case
-                                 * because the real PVR was not found inside
-                                 * cpu_specs[], then we are possibly running in
-                                 * compatibility mode. In that case, let the
-                                 * oprofiler know which set of compatibility
-                                 * counters to pull from by making sure the
-                                 * oprofile_cpu_type string is set to that of
-                                 * compatibility mode. If the oprofile_cpu_type
-                                 * already has a value, then we are possibly
-                                 * overriding a real PVR with a logical one, and,
-                                 * in that case, keep the current value for
-                                 * oprofile_cpu_type.
-                                 */
-                                if (t->oprofile_cpu_type == NULL)
-                                        t->oprofile_cpu_type = s->oprofile_cpu_type;
-                        } else
-                                *t = *s;
-                        *PTRRELOC(&cur_cpu_spec) = &the_cpu_spec;
+        /* Copy everything, then do fixups */
+        *t = *s;
+
+        /*
+         * If we are overriding a previous value derived from the real
+         * PVR with a new value obtained using a logical PVR value,
+         * don't modify the performance monitor fields.
+         */
+        if (old.num_pmcs && !s->num_pmcs) {
+                t->num_pmcs = old.num_pmcs;
+                t->pmc_type = old.pmc_type;
+                t->oprofile_type = old.oprofile_type;
+                t->oprofile_mmcra_sihv = old.oprofile_mmcra_sihv;
+                t->oprofile_mmcra_sipr = old.oprofile_mmcra_sipr;
+                t->oprofile_mmcra_clear = old.oprofile_mmcra_clear;
+
+                /*
+                 * If we have passed through this logic once before and
+                 * have pulled the default case because the real PVR was
+                 * not found inside cpu_specs[], then we are possibly
+                 * running in compatibility mode. In that case, let the
+                 * oprofiler know which set of compatibility counters to
+                 * pull from by making sure the oprofile_cpu_type string
+                 * is set to that of compatibility mode. If the
+                 * oprofile_cpu_type already has a value, then we are
+                 * possibly overriding a real PVR with a logical one,
+                 * and, in that case, keep the current value for
+                 * oprofile_cpu_type.
+                 */
+                if (old.oprofile_cpu_type == NULL)
+                        t->oprofile_cpu_type = s->oprofile_cpu_type;
+        }
 
-                        /*
-                         * Set the base platform string once; assumes
-                         * we're called with real pvr first.
-                         */
-                        if (*PTRRELOC(&powerpc_base_platform) == NULL)
-                                *PTRRELOC(&powerpc_base_platform) = t->platform;
+        *PTRRELOC(&cur_cpu_spec) = &the_cpu_spec;
+
+        /*
+         * Set the base platform string once; assumes
+         * we're called with real pvr first.
+         */
+        if (*PTRRELOC(&powerpc_base_platform) == NULL)
+                *PTRRELOC(&powerpc_base_platform) = t->platform;
 
 #if defined(CONFIG_PPC64) || defined(CONFIG_BOOKE)
-                        /* ppc64 and booke expect identify_cpu to also call
-                         * setup_cpu for that processor. I will consolidate
-                         * that at a later time, for now, just use #ifdef.
-                         * we also don't need to PTRRELOC the function pointer
-                         * on ppc64 and booke as we are running at 0 in real
-                         * mode on ppc64 and reloc_offset is always 0 on booke.
-                         */
-                        if (s->cpu_setup) {
-                                s->cpu_setup(offset, s);
-                        }
+        /* ppc64 and booke expect identify_cpu to also call setup_cpu for
+         * that processor. I will consolidate that at a later time, for now,
+         * just use #ifdef. We also don't need to PTRRELOC the function
+         * pointer on ppc64 and booke as we are running at 0 in real mode
+         * on ppc64 and reloc_offset is always 0 on booke.
+         */
+        if (s->cpu_setup) {
+                s->cpu_setup(offset, s);
+        }
 #endif /* CONFIG_PPC64 || CONFIG_BOOKE */
+}
+
+struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr)
+{
+        struct cpu_spec *s = cpu_specs;
+        int i;
+
+        s = PTRRELOC(s);
+
+        for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++) {
+                if ((pvr & s->pvr_mask) == s->pvr_value) {
+                        setup_cpu_spec(offset, s);
                         return s;
                 }
+        }
+
         BUG();
+
         return NULL;
 }
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 19671aca6591..5fb667a60894 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -48,7 +48,7 @@ static void __init create_trampoline(unsigned long addr)
          * branch to "addr" we jump to ("addr" + 32 MB). Although it requires
          * two instructions it doesn't require any registers.
          */
-        patch_instruction(p, PPC_NOP_INSTR);
+        patch_instruction(p, PPC_INST_NOP);
         patch_branch(++p, addr + PHYSICAL_START, 0);
 }
 
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
new file mode 100644
index 000000000000..1493734cd871
--- /dev/null
+++ b/arch/powerpc/kernel/dbell.c
@@ -0,0 +1,44 @@
+/*
+ * Author: Kumar Gala <galak@kernel.crashing.org>
+ *
+ * Copyright 2009 Freescale Semiconductor Inc.
+ *
+ * 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.
+ */
+
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <linux/threads.h>
+
+#include <asm/dbell.h>
+
+#ifdef CONFIG_SMP
+unsigned long dbell_smp_message[NR_CPUS];
+
+void smp_dbell_message_pass(int target, int msg)
+{
+        int i;
+
+        if(target < NR_CPUS) {
+                set_bit(msg, &dbell_smp_message[target]);
+                ppc_msgsnd(PPC_DBELL, 0, target);
+        }
+        else if(target == MSG_ALL_BUT_SELF) {
+                for_each_online_cpu(i) {
+                        if (i == smp_processor_id())
+                                continue;
+                        set_bit(msg, &dbell_smp_message[i]);
+                        ppc_msgsnd(PPC_DBELL, 0, i);
+                }
+        }
+        else { /* target == MSG_ALL */
+                for_each_online_cpu(i)
+                        set_bit(msg, &dbell_smp_message[i]);
+                ppc_msgsnd(PPC_DBELL, PPC_DBELL_MSG_BRDCAST, 0);
+        }
+}
+#endif
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 6f7eb7e00c79..4dd38f129153 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -63,7 +63,7 @@ debug_transfer_to_handler:
 
         .globl  crit_transfer_to_handler
 crit_transfer_to_handler:
-#ifdef CONFIG_FSL_BOOKE
+#ifdef CONFIG_PPC_BOOK3E_MMU
         mfspr   r0,SPRN_MAS0
         stw     r0,MAS0(r11)
         mfspr   r0,SPRN_MAS1
@@ -78,7 +78,7 @@ crit_transfer_to_handler:
         mfspr   r0,SPRN_MAS7
         stw     r0,MAS7(r11)
 #endif /* CONFIG_PHYS_64BIT */
-#endif /* CONFIG_FSL_BOOKE */
+#endif /* CONFIG_PPC_BOOK3E_MMU */
 #ifdef CONFIG_44x
         mfspr   r0,SPRN_MMUCR
         stw     r0,MMUCR(r11)
@@ -914,7 +914,7 @@ exc_exit_restart_end:
         mtspr   SPRN_##exc_lvl_srr0,r9;                                 \
         mtspr   SPRN_##exc_lvl_srr1,r10;
 
-#if defined(CONFIG_FSL_BOOKE)
+#if defined(CONFIG_PPC_BOOK3E_MMU)
 #ifdef CONFIG_PHYS_64BIT
 #define RESTORE_MAS7                                                    \
         lwz     r11,MAS7(r1);                                           \
@@ -956,7 +956,7 @@ ret_from_crit_exc:
         lwz     r10,crit_srr1@l(r10);
         mtspr   SPRN_SRR0,r9;
         mtspr   SPRN_SRR1,r10;
-        RET_FROM_EXC_LEVEL(SPRN_CSRR0, SPRN_CSRR1, RFCI)
+        RET_FROM_EXC_LEVEL(SPRN_CSRR0, SPRN_CSRR1, PPC_RFCI)
 #endif /* CONFIG_40x */
 
 #ifdef CONFIG_BOOKE
@@ -967,7 +967,7 @@ ret_from_crit_exc:
         stw     r10,KSP_LIMIT(r9)
         RESTORE_xSRR(SRR0,SRR1);
         RESTORE_MMU_REGS;
-        RET_FROM_EXC_LEVEL(SPRN_CSRR0, SPRN_CSRR1, RFCI)
+        RET_FROM_EXC_LEVEL(SPRN_CSRR0, SPRN_CSRR1, PPC_RFCI)
 
         .globl  ret_from_debug_exc
 ret_from_debug_exc:
@@ -981,7 +981,7 @@ ret_from_debug_exc:
         RESTORE_xSRR(SRR0,SRR1);
         RESTORE_xSRR(CSRR0,CSRR1);
         RESTORE_MMU_REGS;
-        RET_FROM_EXC_LEVEL(SPRN_DSRR0, SPRN_DSRR1, RFDI)
+        RET_FROM_EXC_LEVEL(SPRN_DSRR0, SPRN_DSRR1, PPC_RFDI)
 
         .globl  ret_from_mcheck_exc
 ret_from_mcheck_exc:
@@ -992,7 +992,7 @@ ret_from_mcheck_exc:
         RESTORE_xSRR(CSRR0,CSRR1);
         RESTORE_xSRR(DSRR0,DSRR1);
         RESTORE_MMU_REGS;
-        RET_FROM_EXC_LEVEL(SPRN_MCSRR0, SPRN_MCSRR1, RFMCI)
+        RET_FROM_EXC_LEVEL(SPRN_MCSRR0, SPRN_MCSRR1, PPC_RFMCI)
 #endif /* CONFIG_BOOKE */
 
 /*
@@ -1176,59 +1176,27 @@ _GLOBAL(_mcount)
         bctr
 
 _GLOBAL(ftrace_caller)
-        /* Based off of objdump optput from glibc */
-        stwu    r1,-48(r1)
-        stw     r3, 12(r1)
-        stw     r4, 16(r1)
-        stw     r5, 20(r1)
-        stw     r6, 24(r1)
-        mflr    r3
-        lwz     r4, 52(r1)
-        mfcr    r5
-        stw     r7, 28(r1)
-        stw     r8, 32(r1)
-        stw     r9, 36(r1)
-        stw     r10,40(r1)
-        stw     r3, 44(r1)
-        stw     r5, 8(r1)
+        MCOUNT_SAVE_FRAME
+        /* r3 ends up with link register */
         subi    r3, r3, MCOUNT_INSN_SIZE
 .globl ftrace_call
 ftrace_call:
         bl      ftrace_stub
         nop
-        lwz     r6, 8(r1)
-        lwz     r0, 44(r1)
-        lwz     r3, 12(r1)
-        mtctr   r0
-        lwz     r4, 16(r1)
-        mtcr    r6
-        lwz     r5, 20(r1)
-        lwz     r6, 24(r1)
-        lwz     r0, 52(r1)
-        lwz     r7, 28(r1)
-        lwz     r8, 32(r1)
-        mtlr    r0
-        lwz     r9, 36(r1)
-        lwz     r10,40(r1)
-        addi    r1, r1, 48
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+        b       ftrace_graph_stub
+_GLOBAL(ftrace_graph_stub)
+#endif
+        MCOUNT_RESTORE_FRAME
+        /* old link register ends up in ctr reg */
         bctr
 #else
 _GLOBAL(mcount)
 _GLOBAL(_mcount)
-        stwu    r1,-48(r1)
-        stw     r3, 12(r1)
-        stw     r4, 16(r1)
-        stw     r5, 20(r1)
-        stw     r6, 24(r1)
-        mflr    r3
-        lwz     r4, 52(r1)
-        mfcr    r5
-        stw     r7, 28(r1)
-        stw     r8, 32(r1)
-        stw     r9, 36(r1)
-        stw     r10,40(r1)
-        stw     r3, 44(r1)
-        stw     r5, 8(r1)
+
+        MCOUNT_SAVE_FRAME
 
         subi    r3, r3, MCOUNT_INSN_SIZE
         LOAD_REG_ADDR(r5, ftrace_trace_function)
@@ -1236,28 +1204,55 @@ _GLOBAL(_mcount)
 
         mtctr   r5
         bctrl
-
         nop
 
-        lwz     r6, 8(r1)
-        lwz     r0, 44(r1)
-        lwz     r3, 12(r1)
-        mtctr   r0
-        lwz     r4, 16(r1)
-        mtcr    r6
-        lwz     r5, 20(r1)
-        lwz     r6, 24(r1)
-        lwz     r0, 52(r1)
-        lwz     r7, 28(r1)
-        lwz     r8, 32(r1)
-        mtlr    r0
-        lwz     r9, 36(r1)
-        lwz     r10,40(r1)
-        addi    r1, r1, 48
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+        b       ftrace_graph_caller
+#endif
+        MCOUNT_RESTORE_FRAME
         bctr
 #endif
 
 _GLOBAL(ftrace_stub)
         blr
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(ftrace_graph_caller)
+        /* load r4 with local address */
+        lwz     r4, 44(r1)
+        subi    r4, r4, MCOUNT_INSN_SIZE
+
+        /* get the parent address */
+        addi    r3, r1, 52
+
+        bl      prepare_ftrace_return
+        nop
+
+        MCOUNT_RESTORE_FRAME
+        /* old link register ends up in ctr reg */
+        bctr
+
+_GLOBAL(return_to_handler)
+        /* need to save return values */
+        stwu    r1, -32(r1)
+        stw     r3, 20(r1)
+        stw     r4, 16(r1)
+        stw     r31, 12(r1)
+        mr      r31, r1
+
+        bl      ftrace_return_to_handler
+        nop
+
+        /* return value has real return address */
+        mtlr    r3
+
+        lwz     r3, 20(r1)
+        lwz     r4, 16(r1)
+        lwz     r31,12(r1)
+        lwz     r1, 0(r1)
+
+        /* Jump back to real return address */
+        blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
 #endif /* CONFIG_MCOUNT */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index f30b4e553c53..43e073477c34 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -917,6 +917,12 @@ _GLOBAL(ftrace_caller)
 ftrace_call:
         bl      ftrace_stub
         nop
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+        b       ftrace_graph_stub
+_GLOBAL(ftrace_graph_stub)
+#endif
         ld      r0, 128(r1)
         mtlr    r0
         addi    r1, r1, 112
@@ -940,13 +946,90 @@ _GLOBAL(_mcount)
         ld      r5,0(r5)
         mtctr   r5
         bctrl
-
         nop
+
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+        b       ftrace_graph_caller
+#endif
         ld      r0, 128(r1)
         mtlr    r0
         addi    r1, r1, 112
 _GLOBAL(ftrace_stub)
         blr
 
-#endif
-#endif
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(ftrace_graph_caller)
+        /* load r4 with local address */
+        ld      r4, 128(r1)
+        subi    r4, r4, MCOUNT_INSN_SIZE
+
+        /* get the parent address */
+        ld      r11, 112(r1)
+        addi    r3, r11, 16
+
+        bl      .prepare_ftrace_return
+        nop
+
+        ld      r0, 128(r1)
+        mtlr    r0
+        addi    r1, r1, 112
+        blr
+
+_GLOBAL(return_to_handler)
+        /* need to save return values */
+        std     r4,  -24(r1)
+        std     r3,  -16(r1)
+        std     r31, -8(r1)
+        mr      r31, r1
+        stdu    r1, -112(r1)
+
+        bl      .ftrace_return_to_handler
+        nop
+
+        /* return value has real return address */
+        mtlr    r3
+
+        ld      r1, 0(r1)
+        ld      r4,  -24(r1)
+        ld      r3,  -16(r1)
+        ld      r31, -8(r1)
+
+        /* Jump back to real return address */
+        blr
+
+_GLOBAL(mod_return_to_handler)
+        /* need to save return values */
+        std     r4,  -32(r1)
+        std     r3,  -24(r1)
+        /* save TOC */
+        std     r2,  -16(r1)
+        std     r31, -8(r1)
+        mr      r31, r1
+        stdu    r1, -112(r1)
+
+        /*
+         * We are in a module using the module's TOC.
+         * Switch to our TOC to run inside the core kernel.
+         */
+        LOAD_REG_IMMEDIATE(r4,ftrace_return_to_handler)
+        ld      r2, 8(r4)
+
+        bl      .ftrace_return_to_handler
+        nop
+
+        /* return value has real return address */
+        mtlr    r3
+
+        ld      r1, 0(r1)
+        ld      r4,  -32(r1)
+        ld      r3,  -24(r1)
+        ld      r2,  -16(r1)
+        ld      r31, -8(r1)
+
+        /* Jump back to real return address */
+        blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+#endif /* CONFIG_FUNCTION_TRACER */
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 60c60ccf5e3c..5455943f16aa 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -5,6 +5,9 @@
  *
  * Thanks goes out to P.A. Semi, Inc for supplying me with a PPC64 box.
  *
+ * Added function graph tracer code, taken from x86 that was written
+ * by Frederic Weisbecker, and ported to PPC by Steven Rostedt.
+ *
  */
 
 #include <linux/spinlock.h>
@@ -20,14 +23,6 @@
 #include <asm/code-patching.h>
 #include <asm/ftrace.h>
 
-#if 0
-#define DEBUGP printk
-#else
-#define DEBUGP(fmt , ...)       do { } while (0)
-#endif
-
-static unsigned int ftrace_nop = PPC_NOP_INSTR;
-
 #ifdef CONFIG_PPC32
 # define GET_ADDR(addr) addr
 #else
@@ -35,37 +30,23 @@ static unsigned int ftrace_nop = PPC_NOP_INSTR;
 # define GET_ADDR(addr) (*(unsigned long *)addr)
 #endif
 
-
-static unsigned int ftrace_calc_offset(long ip, long addr)
+#ifdef CONFIG_DYNAMIC_FTRACE
+static unsigned int ftrace_nop_replace(void)
 {
-        return (int)(addr - ip);
+        return PPC_INST_NOP;
 }
 
-static unsigned char *ftrace_nop_replace(void)
+static unsigned int
+ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
 {
-        return (char *)&ftrace_nop;
-}
-
-static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
-{
-        static unsigned int op;
+        unsigned int op;
 
-        /*
-         * It would be nice to just use create_function_call, but that will
-         * update the code itself. Here we need to just return the
-         * instruction that is going to be modified, without modifying the
-         * code.
-         */
         addr = GET_ADDR(addr);
 
-        /* Set to "bl addr" */
-        op = 0x48000001 | (ftrace_calc_offset(ip, addr) & 0x03fffffc);
+        /* if (link) set op to 'bl' else 'b' */
+        op = create_branch((unsigned int *)ip, addr, link ? 1 : 0);
 
-        /*
-         * No locking needed, this must be called via kstop_machine
-         * which in essence is like running on a uniprocessor machine.
-         */
-        return (unsigned char *)&op;
+        return op;
 }
 
 #ifdef CONFIG_PPC64
@@ -77,10 +58,9 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 #endif
 
 static int
-ftrace_modify_code(unsigned long ip, unsigned char *old_code,
-                   unsigned char *new_code)
+ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)
 {
-        unsigned char replaced[MCOUNT_INSN_SIZE];
+        unsigned int replaced;
 
         /*
          * Note: Due to modules and __init, code can
@@ -93,15 +73,15 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
          */
 
         /* read the text we want to modify */
-        if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+        if (probe_kernel_read(&replaced, (void *)ip, MCOUNT_INSN_SIZE))
                 return -EFAULT;
 
         /* Make sure it is what we expect it to be */
-        if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
+        if (replaced != old)
                 return -EINVAL;
 
         /* replace the text with the new text */
-        if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
+        if (probe_kernel_write((void *)ip, &new, MCOUNT_INSN_SIZE))
                 return -EPERM;
 
         flush_icache_range(ip, ip + 8);
@@ -119,6 +99,8 @@ static int test_24bit_addr(unsigned long ip, unsigned long addr)
         return create_branch((unsigned int *)ip, addr, 0);
 }
 
+#ifdef CONFIG_MODULES
+
 static int is_bl_op(unsigned int op)
 {
         return (op & 0xfc000003) == 0x48000001;
@@ -175,7 +157,7 @@ __ftrace_make_nop(struct module *mod,
          * 0xe8, 0x4c, 0x00, 0x28,    ld      r2,40(r12)
          */
 
-        DEBUGP("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc);
+        pr_debug("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc);
 
         /* Find where the trampoline jumps to */
         if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) {
@@ -183,7 +165,7 @@ __ftrace_make_nop(struct module *mod,
                 return -EFAULT;
         }
 
-        DEBUGP(" %08x %08x", jmp[0], jmp[1]);
+        pr_debug(" %08x %08x", jmp[0], jmp[1]);
 
         /* verify that this is what we expect it to be */
         if (((jmp[0] & 0xffff0000) != 0x3d820000) ||
@@ -199,18 +181,18 @@ __ftrace_make_nop(struct module *mod,
         offset = ((unsigned)((unsigned short)jmp[0]) << 16) +
                 (int)((short)jmp[1]);
 
-        DEBUGP(" %x ", offset);
+        pr_debug(" %x ", offset);
 
         /* get the address this jumps too */
         tramp = mod->arch.toc + offset + 32;
-        DEBUGP("toc: %lx", tramp);
+        pr_debug("toc: %lx", tramp);
 
         if (probe_kernel_read(jmp, (void *)tramp, 8)) {
                 printk(KERN_ERR "Failed to read %lx\n", tramp);
                 return -EFAULT;
         }
 
-        DEBUGP(" %08x %08x\n", jmp[0], jmp[1]);
+        pr_debug(" %08x %08x\n", jmp[0], jmp[1]);
 
         ptr = ((unsigned long)jmp[0] << 32) + jmp[1];
 
@@ -287,7 +269,7 @@ __ftrace_make_nop(struct module *mod,
          *  0x4e, 0x80, 0x04, 0x20  bctr
          */
 
-        DEBUGP("ip:%lx jumps to %lx", ip, tramp);
+        pr_debug("ip:%lx jumps to %lx", ip, tramp);
 
         /* Find where the trampoline jumps to */
         if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) {
@@ -295,7 +277,7 @@ __ftrace_make_nop(struct module *mod,
                 return -EFAULT;
         }
 
-        DEBUGP(" %08x %08x ", jmp[0], jmp[1]);
+        pr_debug(" %08x %08x ", jmp[0], jmp[1]);
 
         /* verify that this is what we expect it to be */
         if (((jmp[0] & 0xffff0000) != 0x3d600000) ||
@@ -311,7 +293,7 @@ __ftrace_make_nop(struct module *mod,
         if (tramp & 0x8000)
                 tramp -= 0x10000;
 
-        DEBUGP(" %x ", tramp);
+        pr_debug(" %x ", tramp);
 
         if (tramp != addr) {
                 printk(KERN_ERR
@@ -320,7 +302,7 @@ __ftrace_make_nop(struct module *mod,
                 return -EINVAL;
         }
 
-        op = PPC_NOP_INSTR;
+        op = PPC_INST_NOP;
 
         if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE))
                 return -EPERM;
@@ -330,12 +312,13 @@ __ftrace_make_nop(struct module *mod,
         return 0;
 }
 #endif /* PPC64 */
+#endif /* CONFIG_MODULES */
 
 int ftrace_make_nop(struct module *mod,
                     struct dyn_ftrace *rec, unsigned long addr)
 {
-        unsigned char *old, *new;
         unsigned long ip = rec->ip;
+        unsigned int old, new;
 
         /*
          * If the calling address is more that 24 bits away,
@@ -344,11 +327,12 @@ int ftrace_make_nop(struct module *mod,
          */
         if (test_24bit_addr(ip, addr)) {
                 /* within range */
-                old = ftrace_call_replace(ip, addr);
+                old = ftrace_call_replace(ip, addr, 1);
                 new = ftrace_nop_replace();
                 return ftrace_modify_code(ip, old, new);
         }
 
+#ifdef CONFIG_MODULES
         /*
          * Out of range jumps are called from modules.
          * We should either already have a pointer to the module
@@ -373,9 +357,13 @@ int ftrace_make_nop(struct module *mod,
                 mod = rec->arch.mod;
 
         return __ftrace_make_nop(mod, rec, addr);
-
+#else
+        /* We should not get here without modules */
+        return -EINVAL;
+#endif /* CONFIG_MODULES */
 }
 
+#ifdef CONFIG_MODULES
 #ifdef CONFIG_PPC64
 static int
 __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
@@ -392,7 +380,7 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
          *  b +8; ld r2,40(r1)
          */
         if (((op[0] != 0x48000008) || (op[1] != 0xe8410028)) &&
-            ((op[0] != PPC_NOP_INSTR) || (op[1] != PPC_NOP_INSTR))) {
+            ((op[0] != PPC_INST_NOP) || (op[1] != PPC_INST_NOP))) {
                 printk(KERN_ERR "Expected NOPs but have %x %x\n", op[0], op[1]);
                 return -EINVAL;
         }
@@ -414,7 +402,7 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
         /* ld r2,40(r1) */
         op[1] = 0xe8410028;
 
-        DEBUGP("write to %lx\n", rec->ip);
+        pr_debug("write to %lx\n", rec->ip);
 
         if (probe_kernel_write((void *)ip, op, MCOUNT_INSN_SIZE * 2))
                 return -EPERM;
@@ -435,7 +423,7 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
                 return -EFAULT;
 
         /* It should be pointing to a nop */
-        if (op != PPC_NOP_INSTR) {
+        if (op != PPC_INST_NOP) {
                 printk(KERN_ERR "Expected NOP but have %x\n", op);
                 return -EINVAL;
         }
@@ -454,7 +442,7 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
                 return -EINVAL;
         }
 
-        DEBUGP("write to %lx\n", rec->ip);
+        pr_debug("write to %lx\n", rec->ip);
 
         if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE))
                 return -EPERM;
@@ -464,11 +452,12 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
         return 0;
 }
 #endif /* CONFIG_PPC64 */
+#endif /* CONFIG_MODULES */
 
 int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
-        unsigned char *old, *new;
         unsigned long ip = rec->ip;
+        unsigned int old, new;
 
         /*
          * If the calling address is more that 24 bits away,
@@ -478,10 +467,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
         if (test_24bit_addr(ip, addr)) {
                 /* within range */
                 old = ftrace_nop_replace();
-                new = ftrace_call_replace(ip, addr);
+                new = ftrace_call_replace(ip, addr, 1);
                 return ftrace_modify_code(ip, old, new);
         }
 
+#ifdef CONFIG_MODULES
         /*
          * Out of range jumps are called from modules.
          * Being that we are converting from nop, it had better
@@ -493,16 +483,20 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
         }
 
         return __ftrace_make_call(rec, addr);
+#else
+        /* We should not get here without modules */
+        return -EINVAL;
+#endif /* CONFIG_MODULES */
 }
 
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
         unsigned long ip = (unsigned long)(&ftrace_call);
-        unsigned char old[MCOUNT_INSN_SIZE], *new;
+        unsigned int old, new;
         int ret;
 
-        memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
-        new = ftrace_call_replace(ip, (unsigned long)func);
+        old = *(unsigned int *)&ftrace_call;
+        new = ftrace_call_replace(ip, (unsigned long)func, 1);
         ret = ftrace_modify_code(ip, old, new);
 
         return ret;
@@ -517,3 +511,111 @@ int __init ftrace_dyn_arch_init(void *data)
 
         return 0;
 }
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void ftrace_graph_call(void);
+extern void ftrace_graph_stub(void);
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+        unsigned long ip = (unsigned long)(&ftrace_graph_call);
+        unsigned long addr = (unsigned long)(&ftrace_graph_caller);
+        unsigned long stub = (unsigned long)(&ftrace_graph_stub);
+        unsigned int old, new;
+
+        old = ftrace_call_replace(ip, stub, 0);
+        new = ftrace_call_replace(ip, addr, 0);
+
+        return ftrace_modify_code(ip, old, new);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+        unsigned long ip = (unsigned long)(&ftrace_graph_call);
+        unsigned long addr = (unsigned long)(&ftrace_graph_caller);
+        unsigned long stub = (unsigned long)(&ftrace_graph_stub);
+        unsigned int old, new;
+
+        old = ftrace_call_replace(ip, addr, 0);
+        new = ftrace_call_replace(ip, stub, 0);
+
+        return ftrace_modify_code(ip, old, new);
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_PPC64
+extern void mod_return_to_handler(void);
+#endif
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
+{
+        unsigned long old;
+        int faulted;
+        struct ftrace_graph_ent trace;
+        unsigned long return_hooker = (unsigned long)&return_to_handler;
+
+        if (unlikely(atomic_read(&current->tracing_graph_pause)))
+                return;
+
+#if CONFIG_PPC64
+        /* non core kernel code needs to save and restore the TOC */
+        if (REGION_ID(self_addr) != KERNEL_REGION_ID)
+                return_hooker = (unsigned long)&mod_return_to_handler;
+#endif
+
+        return_hooker = GET_ADDR(return_hooker);
+
+        /*
+         * Protect against fault, even if it shouldn't
+         * happen. This tool is too much intrusive to
+         * ignore such a protection.
+         */
+        asm volatile(
+                "1: " PPC_LL "%[old], 0(%[parent])\n"
+                "2: " PPC_STL "%[return_hooker], 0(%[parent])\n"
+                "   li %[faulted], 0\n"
+                "3:\n"
+
+                ".section .fixup, \"ax\"\n"
+                "4: li %[faulted], 1\n"
+                "   b 3b\n"
+                ".previous\n"
+
+                ".section __ex_table,\"a\"\n"
+                        PPC_LONG_ALIGN "\n"
+                        PPC_LONG "1b,4b\n"
+                        PPC_LONG "2b,4b\n"
+                ".previous"
+
+                : [old] "=r" (old), [faulted] "=r" (faulted)
+                : [parent] "r" (parent), [return_hooker] "r" (return_hooker)
+                : "memory"
+        );
+
+        if (unlikely(faulted)) {
+                ftrace_graph_stop();
+                WARN_ON(1);
+                return;
+        }
+
+        if (ftrace_push_return_trace(old, self_addr, &trace.depth) == -EBUSY) {
+                *parent = old;
+                return;
+        }
+
+        trace.func = self_addr;
+
+        /* Only trace if the calling function expects to */
+        if (!ftrace_graph_entry(&trace)) {
+                current->curr_ret_stack--;
+                *parent = old;
+        }
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index a1c4cfd25ded..54e68c11ae15 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -108,18 +108,21 @@ __start:
  * because OF may have I/O devices mapped into that area
  * (particularly on CHRP).
  */
-#ifdef CONFIG_PPC_MULTIPLATFORM
         cmpwi   0,r5,0
         beq     1f
 
+#ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE
         /* find out where we are now */
         bcl     20,31,$+4
 0:      mflr    r8                      /* r8 = runtime addr here */
         addis   r8,r8,(_stext - 0b)@ha
         addi    r8,r8,(_stext - 0b)@l   /* current runtime base addr */
         bl      prom_init
+#endif /* CONFIG_PPC_OF_BOOT_TRAMPOLINE */
+
+        /* We never return. We also hit that trap if trying to boot
+         * from OF while CONFIG_PPC_OF_BOOT_TRAMPOLINE isn't selected */
         trap
-#endif
 
 /*
  * Check for BootX signature when supporting PowerMac and branch to
@@ -472,12 +475,11 @@ SystemCall:
         . = 0x1000
 InstructionTLBMiss:
 /*
- * r0:  stored ctr
+ * r0:  scratch
  * r1:  linux style pte ( later becomes ppc hardware pte )
  * r2:  ptr to linux-style pte
  * r3:  scratch
  */
-        mfctr   r0
         /* Get PTE (linux-style) and check access */
         mfspr   r3,SPRN_IMISS
         lis     r1,PAGE_OFFSET@h                /* check if kernel address */
@@ -496,25 +498,27 @@ InstructionTLBMiss:
         rlwinm. r2,r2,0,0,19            /* extract address of pte page */
         beq-    InstructionAddressInvalid       /* return if no mapping */
         rlwimi  r2,r3,22,20,29          /* insert next 10 bits of address */
-        lwz     r3,0(r2)                /* get linux-style pte */
-        andc.   r1,r1,r3                /* check access & ~permission */
+        lwz     r0,0(r2)                /* get linux-style pte */
+        andc.   r1,r1,r0                /* check access & ~permission */
         bne-    InstructionAddressInvalid /* return if access not permitted */
-        ori     r3,r3,_PAGE_ACCESSED    /* set _PAGE_ACCESSED in pte */
+        ori     r0,r0,_PAGE_ACCESSED    /* set _PAGE_ACCESSED in pte */
         /*
          * NOTE! We are assuming this is not an SMP system, otherwise
          * we would need to update the pte atomically with lwarx/stwcx.
          */
-        stw     r3,0(r2)                /* update PTE (accessed bit) */
+        stw     r0,0(r2)                /* update PTE (accessed bit) */
         /* Convert linux-style PTE to low word of PPC-style PTE */
-        rlwinm  r1,r3,32-10,31,31       /* _PAGE_RW -> PP lsb */
-        rlwinm  r2,r3,32-7,31,31        /* _PAGE_DIRTY -> PP lsb */
+        rlwinm  r1,r0,32-10,31,31       /* _PAGE_RW -> PP lsb */
+        rlwinm  r2,r0,32-7,31,31        /* _PAGE_DIRTY -> PP lsb */
         and     r1,r1,r2                /* writable if _RW and _DIRTY */
-        rlwimi  r3,r3,32-1,30,30        /* _PAGE_USER -> PP msb */
-        rlwimi  r3,r3,32-1,31,31        /* _PAGE_USER -> PP lsb */
-        ori     r1,r1,0xe14             /* clear out reserved bits and M */
-        andc    r1,r3,r1                /* PP = user? (rw&dirty? 2: 3): 0 */
+        rlwimi  r0,r0,32-1,30,30        /* _PAGE_USER -> PP msb */
+        rlwimi  r0,r0,32-1,31,31        /* _PAGE_USER -> PP lsb */
+        ori     r1,r1,0xe04             /* clear out reserved bits */
+        andc    r1,r0,r1                /* PP = user? (rw&dirty? 2: 3): 0 */
+BEGIN_FTR_SECTION
+        rlwinm  r1,r1,0,~_PAGE_COHERENT /* clear M (coherence not required) */
+END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
         mtspr   SPRN_RPA,r1
-        mfspr   r3,SPRN_IMISS
         tlbli   r3
         mfspr   r3,SPRN_SRR1            /* Need to restore CR0 */
         mtcrf   0x80,r3
@@ -525,7 +529,6 @@ InstructionAddressInvalid:
 
         addis   r1,r1,0x2000
         mtspr   SPRN_DSISR,r1   /* (shouldn't be needed) */
-        mtctr   r0              /* Restore CTR */
         andi.   r2,r3,0xFFFF    /* Clear upper bits of SRR1 */
         or      r2,r2,r1
         mtspr   SPRN_SRR1,r2
@@ -546,12 +549,11 @@ InstructionAddressInvalid:
         . = 0x1100
 DataLoadTLBMiss:
 /*
- * r0:  stored ctr
+ * r0:  scratch
  * r1:  linux style pte ( later becomes ppc hardware pte )
  * r2:  ptr to linux-style pte
  * r3:  scratch
  */
-        mfctr   r0
         /* Get PTE (linux-style) and check access */
         mfspr   r3,SPRN_DMISS
         lis     r1,PAGE_OFFSET@h                /* check if kernel address */
@@ -570,35 +572,48 @@ DataLoadTLBMiss:
         rlwinm. r2,r2,0,0,19            /* extract address of pte page */
         beq-    DataAddressInvalid      /* return if no mapping */
         rlwimi  r2,r3,22,20,29          /* insert next 10 bits of address */
-        lwz     r3,0(r2)                /* get linux-style pte */
-        andc.   r1,r1,r3                /* check access & ~permission */
+        lwz     r0,0(r2)                /* get linux-style pte */
+        andc.   r1,r1,r0                /* check access & ~permission */
         bne-    DataAddressInvalid      /* return if access not permitted */
-        ori     r3,r3,_PAGE_ACCESSED    /* set _PAGE_ACCESSED in pte */
+        ori     r0,r0,_PAGE_ACCESSED    /* set _PAGE_ACCESSED in pte */
         /*
          * NOTE! We are assuming this is not an SMP system, otherwise
          * we would need to update the pte atomically with lwarx/stwcx.
          */
-        stw     r3,0(r2)                /* update PTE (accessed bit) */
+        stw     r0,0(r2)                /* update PTE (accessed bit) */
         /* Convert linux-style PTE to low word of PPC-style PTE */
-        rlwinm  r1,r3,32-10,31,31       /* _PAGE_RW -> PP lsb */
-        rlwinm  r2,r3,32-7,31,31        /* _PAGE_DIRTY -> PP lsb */
+        rlwinm  r1,r0,32-10,31,31       /* _PAGE_RW -> PP lsb */
+        rlwinm  r2,r0,32-7,31,31        /* _PAGE_DIRTY -> PP lsb */
         and     r1,r1,r2                /* writable if _RW and _DIRTY */
-        rlwimi  r3,r3,32-1,30,30        /* _PAGE_USER -> PP msb */
-        rlwimi  r3,r3,32-1,31,31        /* _PAGE_USER -> PP lsb */
-        ori     r1,r1,0xe14             /* clear out reserved bits and M */
-        andc    r1,r3,r1                /* PP = user? (rw&dirty? 2: 3): 0 */
+        rlwimi  r0,r0,32-1,30,30        /* _PAGE_USER -> PP msb */
+        rlwimi  r0,r0,32-1,31,31        /* _PAGE_USER -> PP lsb */
+        ori     r1,r1,0xe04             /* clear out reserved bits */
+        andc    r1,r0,r1                /* PP = user? (rw&dirty? 2: 3): 0 */
+BEGIN_FTR_SECTION
+        rlwinm  r1,r1,0,~_PAGE_COHERENT /* clear M (coherence not required) */
+END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
         mtspr   SPRN_RPA,r1
-        mfspr   r3,SPRN_DMISS
+        mfspr   r2,SPRN_SRR1            /* Need to restore CR0 */
+        mtcrf   0x80,r2
+BEGIN_MMU_FTR_SECTION
+        li      r0,1
+        mfspr   r1,SPRN_SPRG4
+        rlwinm  r2,r3,20,27,31          /* Get Address bits 15:19 */
+        slw     r0,r0,r2
+        xor     r1,r0,r1
+        srw     r0,r1,r2
+        mtspr   SPRN_SPRG4,r1
+        mfspr   r2,SPRN_SRR1
+        rlwimi  r2,r0,31-14,14,14
+        mtspr   SPRN_SRR1,r2
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
         tlbld   r3
-        mfspr   r3,SPRN_SRR1            /* Need to restore CR0 */
-        mtcrf   0x80,r3
         rfi
 DataAddressInvalid:
         mfspr   r3,SPRN_SRR1
         rlwinm  r1,r3,9,6,6     /* Get load/store bit */
         addis   r1,r1,0x2000
         mtspr   SPRN_DSISR,r1
-        mtctr   r0              /* Restore CTR */
         andi.   r2,r3,0xFFFF    /* Clear upper bits of SRR1 */
         mtspr   SPRN_SRR1,r2
         mfspr   r1,SPRN_DMISS   /* Get failing address */
@@ -618,12 +633,11 @@ DataAddressInvalid:
         . = 0x1200
 DataStoreTLBMiss:
 /*
- * r0:  stored ctr
+ * r0:  scratch
  * r1:  linux style pte ( later becomes ppc hardware pte )
  * r2:  ptr to linux-style pte
  * r3:  scratch
  */
-        mfctr   r0
         /* Get PTE (linux-style) and check access */
         mfspr   r3,SPRN_DMISS
         lis     r1,PAGE_OFFSET@h                /* check if kernel address */
@@ -642,24 +656,38 @@ DataStoreTLBMiss:
         rlwinm. r2,r2,0,0,19            /* extract address of pte page */
         beq-    DataAddressInvalid      /* return if no mapping */
         rlwimi  r2,r3,22,20,29          /* insert next 10 bits of address */
-        lwz     r3,0(r2)                /* get linux-style pte */
-        andc.   r1,r1,r3                /* check access & ~permission */
+        lwz     r0,0(r2)                /* get linux-style pte */
+        andc.   r1,r1,r0                /* check access & ~permission */
         bne-    DataAddressInvalid      /* return if access not permitted */
-        ori     r3,r3,_PAGE_ACCESSED|_PAGE_DIRTY
+        ori     r0,r0,_PAGE_ACCESSED|_PAGE_DIRTY
         /*
          * NOTE! We are assuming this is not an SMP system, otherwise
          * we would need to update the pte atomically with lwarx/stwcx.
          */
-        stw     r3,0(r2)                /* update PTE (accessed/dirty bits) */
+        stw     r0,0(r2)                /* update PTE (accessed/dirty bits) */
         /* Convert linux-style PTE to low word of PPC-style PTE */
-        rlwimi  r3,r3,32-1,30,30        /* _PAGE_USER -> PP msb */
-        li      r1,0xe15                /* clear out reserved bits and M */
-        andc    r1,r3,r1                /* PP = user? 2: 0 */
+        rlwimi  r0,r0,32-1,30,30        /* _PAGE_USER -> PP msb */
+        li      r1,0xe05                /* clear out reserved bits & PP lsb */
+        andc    r1,r0,r1                /* PP = user? 2: 0 */
+BEGIN_FTR_SECTION
+        rlwinm  r1,r1,0,~_PAGE_COHERENT /* clear M (coherence not required) */
+END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
         mtspr   SPRN_RPA,r1
-        mfspr   r3,SPRN_DMISS
+        mfspr   r2,SPRN_SRR1            /* Need to restore CR0 */
+        mtcrf   0x80,r2
+BEGIN_MMU_FTR_SECTION
+        li      r0,1
+        mfspr   r1,SPRN_SPRG4
+        rlwinm  r2,r3,20,27,31          /* Get Address bits 15:19 */
+        slw     r0,r0,r2
+        xor     r1,r0,r1
+        srw     r0,r1,r2
+        mtspr   SPRN_SPRG4,r1
+        mfspr   r2,SPRN_SRR1
+        rlwimi  r2,r0,31-14,14,14
+        mtspr   SPRN_SRR1,r2
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
         tlbld   r3
-        mfspr   r3,SPRN_SRR1            /* Need to restore CR0 */
-        mtcrf   0x80,r3
         rfi
 
 #ifndef CONFIG_ALTIVEC
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index ebaedafc8e67..50ef505b8fb6 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -1360,6 +1360,7 @@ _GLOBAL(__start_initialization_multiplatform)
         b       .__after_prom_start
 
 _INIT_STATIC(__boot_from_prom)
+#ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE
         /* Save parameters */
         mr      r31,r3
         mr      r30,r4
@@ -1390,7 +1391,10 @@ _INIT_STATIC(__boot_from_prom)
         /* Do all of the interaction with OF client interface */
         mr      r8,r26
         bl      .prom_init
-        /* We never return */
+#endif /* #CONFIG_PPC_OF_BOOT_TRAMPOLINE */
+
+        /* We never return. We also hit that trap if trying to boot
+         * from OF while CONFIG_PPC_OF_BOOT_TRAMPOLINE isn't selected */
         trap
 
 _STATIC(__after_prom_start)
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index fce2df988504..95f39f1e68d4 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -10,6 +10,15 @@
                 mtspr   SPRN_IVOR##vector_number,r26;   \
                 sync
 
+#if (THREAD_SHIFT < 15)
+#define ALLOC_STACK_FRAME(reg, val)                     \
+        addi reg,reg,val
+#else
+#define ALLOC_STACK_FRAME(reg, val)                     \
+        addis   reg,reg,val@ha;                         \
+        addi    reg,reg,val@l
+#endif
+
 #define NORMAL_EXCEPTION_PROLOG                                              \
         mtspr   SPRN_SPRG0,r10;         /* save two registers to work with */\
         mtspr   SPRN_SPRG1,r11;                                              \
@@ -20,7 +29,7 @@
         beq     1f;                                                          \
         mfspr   r1,SPRN_SPRG3;          /* if from user, start at top of   */\
         lwz     r1,THREAD_INFO-THREAD(r1); /* this thread's kernel stack   */\
-        addi    r1,r1,THREAD_SIZE;                                           \
+        ALLOC_STACK_FRAME(r1, THREAD_SIZE);                                  \
 1:      subi    r1,r1,INT_FRAME_SIZE;   /* Allocate an exception frame     */\
         mr      r11,r1;                                                      \
         stw     r10,_CCR(r11);          /* save various registers          */\
@@ -70,10 +79,10 @@
 
 /* only on e500mc/e200 */
 #define DEBUG_STACK_BASE        dbgirq_ctx
-#ifdef CONFIG_PPC_E500MC
-#define DEBUG_SPRG              SPRN_SPRG9
-#else
+#ifdef CONFIG_E200
 #define DEBUG_SPRG              SPRN_SPRG6W
+#else
+#define DEBUG_SPRG              SPRN_SPRG9
 #endif
 
 #define EXC_LVL_FRAME_OVERHEAD  (THREAD_SIZE - INT_FRAME_SIZE - EXC_LVL_SIZE)
@@ -279,7 +288,7 @@ label:
         lwz     r11,GPR11(r8);                                                \
         mfspr   r8,DEBUG_SPRG;                                                \
                                                                               \
-        RFDI;                                                                 \
+        PPC_RFDI;                                                                     \
         b       .;                                                            \
                                                                               \
         /* continue normal handling for a debug exception... */               \
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 36ffb3504a4f..4c22620d009b 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -103,10 +103,15 @@ invstr:	mflr	r6				/* Make it accessible */
         or      r7,r7,r4
         mtspr   SPRN_MAS6,r7
         tlbsx   0,r6                            /* search MSR[IS], SPID=PID0 */
-#ifndef CONFIG_E200
         mfspr   r7,SPRN_MAS1
         andis.  r7,r7,MAS1_VALID@h
         bne     match_TLB
+
+        mfspr   r7,SPRN_MMUCFG
+        rlwinm  r7,r7,21,28,31                  /* extract MMUCFG[NPIDS] */
+        cmpwi   r7,3
+        bne     match_TLB                       /* skip if NPIDS != 3 */
+
         mfspr   r7,SPRN_PID1
         slwi    r7,r7,16
         or      r7,r7,r4
@@ -120,7 +125,7 @@ invstr:	mflr	r6				/* Make it accessible */
         or      r7,r7,r4
         mtspr   SPRN_MAS6,r7
         tlbsx   0,r6                            /* Fall through, we had to match */
-#endif
+
 match_TLB:
         mfspr   r7,SPRN_MAS0
         rlwinm  r3,r7,16,20,31                  /* Extract MAS0(Entry) */
@@ -168,7 +173,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 
         /* grab and fixup the RPN */
         mfspr   r6,SPRN_MAS1    /* extract MAS1[SIZE] */
-        rlwinm  r6,r6,25,27,30
+        rlwinm  r6,r6,25,27,31
         li      r8,-1
         addi    r6,r6,10
         slw     r6,r8,r6        /* convert to mask */
@@ -194,7 +199,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
         xori    r6,r4,1         /* Setup TMP mapping in the other Address space */
         slwi    r6,r6,12
         oris    r6,r6,(MAS1_VALID|MAS1_IPROT)@h
-        ori     r6,r6,(MAS1_TSIZE(BOOKE_PAGESZ_4K))@l
+        ori     r6,r6,(MAS1_TSIZE(BOOK3E_PAGESZ_4K))@l
         mtspr   SPRN_MAS1,r6
         mfspr   r6,SPRN_MAS2
         li      r7,0            /* temp EPN = 0 */
@@ -215,14 +220,19 @@ skpinv:	addi	r6,r6,1				/* Increment */
 
 /* 4. Clear out PIDs & Search info */
         li      r6,0
+        mtspr   SPRN_MAS6,r6
         mtspr   SPRN_PID0,r6
-#ifndef CONFIG_E200
+
+        mfspr   r7,SPRN_MMUCFG
+        rlwinm  r7,r7,21,28,31                  /* extract MMUCFG[NPIDS] */
+        cmpwi   r7,3
+        bne     2f                              /* skip if NPIDS != 3 */
+
         mtspr   SPRN_PID1,r6
         mtspr   SPRN_PID2,r6
-#endif
-        mtspr   SPRN_MAS6,r6
 
 /* 5. Invalidate mapping we started in */
+2:
         lis     r7,0x1000       /* Set MAS0(TLBSEL) = 1 */
         rlwimi  r7,r3,16,4,15   /* Setup MAS0 = TLBSEL | ESEL(r3) */
         mtspr   SPRN_MAS0,r7
@@ -247,10 +257,10 @@ skpinv:	addi	r6,r6,1				/* Increment */
         lis     r6,0x1000               /* Set MAS0(TLBSEL) = TLB1(1), ESEL = 0 */
         mtspr   SPRN_MAS0,r6
         lis     r6,(MAS1_VALID|MAS1_IPROT)@h
-        ori     r6,r6,(MAS1_TSIZE(BOOKE_PAGESZ_64M))@l
+        ori     r6,r6,(MAS1_TSIZE(BOOK3E_PAGESZ_64M))@l
         mtspr   SPRN_MAS1,r6
-        lis     r6,MAS2_VAL(PAGE_OFFSET, BOOKE_PAGESZ_64M, M_IF_SMP)@h
-        ori     r6,r6,MAS2_VAL(PAGE_OFFSET, BOOKE_PAGESZ_64M, M_IF_SMP)@l
+        lis     r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_SMP)@h
+        ori     r6,r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_SMP)@l
         mtspr   SPRN_MAS2,r6
         mtspr   SPRN_MAS3,r8
         tlbwe
@@ -298,26 +308,14 @@ skpinv:	addi	r6,r6,1				/* Increment */
         SET_IVOR(12, WatchdogTimer);
         SET_IVOR(13, DataTLBError);
         SET_IVOR(14, InstructionTLBError);
-        SET_IVOR(15, DebugDebug);
-#if defined(CONFIG_E500) && !defined(CONFIG_PPC_E500MC)
         SET_IVOR(15, DebugCrit);
-#endif
-        SET_IVOR(32, SPEUnavailable);
-        SET_IVOR(33, SPEFloatingPointData);
-        SET_IVOR(34, SPEFloatingPointRound);
-#ifndef CONFIG_E200
-        SET_IVOR(35, PerformanceMonitor);
-#endif
-#ifdef CONFIG_PPC_E500MC
-        SET_IVOR(36, Doorbell);
-#endif
 
         /* Establish the interrupt vector base */
         lis     r4,interrupt_base@h     /* IVPR only uses the high 16-bits */
         mtspr   SPRN_IVPR,r4
 
         /* Setup the defaults for TLB entries */
-        li      r2,(MAS4_TSIZED(BOOKE_PAGESZ_4K))@l
+        li      r2,(MAS4_TSIZED(BOOK3E_PAGESZ_4K))@l
 #ifdef CONFIG_E200
         oris    r2,r2,MAS4_TLBSELD(1)@h
 #endif
@@ -329,12 +327,6 @@ skpinv:	addi	r6,r6,1				/* Increment */
         oris    r2,r2,HID0_DOZE@h
         mtspr   SPRN_HID0, r2
 #endif
-#ifdef CONFIG_E200
-        /* enable dedicated debug exception handling resources (Debug APU) */
-        mfspr   r2,SPRN_HID0
-        ori     r2,r2,HID0_DAPUEN@l
-        mtspr   SPRN_HID0,r2
-#endif
 
 #if !defined(CONFIG_BDI_SWITCH)
         /*
@@ -706,15 +698,13 @@ interrupt_base:
         /* Performance Monitor */
         EXCEPTION(0x2060, PerformanceMonitor, performance_monitor_exception, EXC_XFER_STD)
 
-#ifdef CONFIG_PPC_E500MC
-        EXCEPTION(0x2070, Doorbell, unknown_exception, EXC_XFER_STD)
-#endif
+        EXCEPTION(0x2070, Doorbell, doorbell_exception, EXC_XFER_STD)
+
+        CRITICAL_EXCEPTION(0x2080, CriticalDoorbell, unknown_exception)
 
         /* Debug Interrupt */
         DEBUG_DEBUG_EXCEPTION
-#if defined(CONFIG_E500) && !defined(CONFIG_PPC_E500MC)
         DEBUG_CRIT_EXCEPTION
-#endif
 
 /*
  * Local functions
@@ -897,6 +887,47 @@ KernelSPE:
  * Global functions
  */
 
+/* Adjust or setup IVORs for e200 */
+_GLOBAL(__setup_e200_ivors)
+        li      r3,DebugDebug@l
+        mtspr   SPRN_IVOR15,r3
+        li      r3,SPEUnavailable@l
+        mtspr   SPRN_IVOR32,r3
+        li      r3,SPEFloatingPointData@l
+        mtspr   SPRN_IVOR33,r3
+        li      r3,SPEFloatingPointRound@l
+        mtspr   SPRN_IVOR34,r3
+        sync
+        blr
+
+/* Adjust or setup IVORs for e500v1/v2 */
+_GLOBAL(__setup_e500_ivors)
+        li      r3,DebugCrit@l
+        mtspr   SPRN_IVOR15,r3
+        li      r3,SPEUnavailable@l
+        mtspr   SPRN_IVOR32,r3
+        li      r3,SPEFloatingPointData@l
+        mtspr   SPRN_IVOR33,r3
+        li      r3,SPEFloatingPointRound@l
+        mtspr   SPRN_IVOR34,r3
+        li      r3,PerformanceMonitor@l
+        mtspr   SPRN_IVOR35,r3
+        sync
+        blr
+
+/* Adjust or setup IVORs for e500mc */
+_GLOBAL(__setup_e500mc_ivors)
+        li      r3,DebugDebug@l
+        mtspr   SPRN_IVOR15,r3
+        li      r3,PerformanceMonitor@l
+        mtspr   SPRN_IVOR35,r3
+        li      r3,Doorbell@l
+        mtspr   SPRN_IVOR36,r3
+        li      r3,CriticalDoorbell@l
+        mtspr   SPRN_IVOR37,r3
+        sync
+        blr
+
 /*
  * extern void loadcam_entry(unsigned int index)
  *
@@ -1089,7 +1120,7 @@ __secondary_start:
         mtspr   SPRN_SPRG3,r4
 
         /* Setup the defaults for TLB entries */
-        li      r4,(MAS4_TSIZED(BOOKE_PAGESZ_4K))@l
+        li      r4,(MAS4_TSIZED(BOOK3E_PAGESZ_4K))@l
         mtspr   SPRN_MAS4,r4
 
         /* Jump to start_secondary */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 7f8e6a92c5a1..0d2e37c57738 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -181,7 +181,7 @@ int show_interrupts(struct seq_file *p, void *v)
 {
         int i = *(loff_t *)v, j;
         struct irqaction *action;
-        irq_desc_t *desc;
+        struct irq_desc *desc;
         unsigned long flags;
 
         if (i == 0) {
@@ -200,7 +200,7 @@ int show_interrupts(struct seq_file *p, void *v)
                 seq_printf(p, "%3d: ", i);
 #ifdef CONFIG_SMP
                 for_each_online_cpu(j)
-                        seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+                        seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #else
                 seq_printf(p, "%10u ", kstat_irqs(i));
 #endif /* CONFIG_SMP */
@@ -1048,7 +1048,7 @@ arch_initcall(irq_late_init);
 static int virq_debug_show(struct seq_file *m, void *private)
 {
         unsigned long flags;
-        irq_desc_t *desc;
+        struct irq_desc *desc;
         const char *p;
         char none[] = "none";
         int i;
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 8992b031a7b6..8fbb12508bf3 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -329,7 +329,7 @@ static unsigned long stub_for_addr(Elf64_Shdr *sechdrs,
    restore r2. */
 static int restore_r2(u32 *instruction, struct module *me)
 {
-        if (*instruction != PPC_NOP_INSTR) {
+        if (*instruction != PPC_INST_NOP) {
                 printk("%s: Expect noop after relocate, got %08x\n",
                        me->name, *instruction);
                 return 0;
diff --git a/arch/powerpc/kernel/msi.c b/arch/powerpc/kernel/msi.c
index 3bb7d3dd28be..8bbc12d20f5c 100644
--- a/arch/powerpc/kernel/msi.c
+++ b/arch/powerpc/kernel/msi.c
@@ -9,6 +9,7 @@
 
 #include <linux/kernel.h>
 #include <linux/msi.h>
+#include <linux/pci.h>
 
 #include <asm/machdep.h>
 
@@ -19,6 +20,10 @@ int arch_msi_check_device(struct pci_dev* dev, int nvec, int type)
                 return -ENOSYS;
         }
 
+        /* PowerPC doesn't support multiple MSI yet */
+        if (type == PCI_CAP_ID_MSI && nvec > 1)
+                return 1;
+
         if (ppc_md.msi_check_device) {
                 pr_debug("msi: Using platform check routine.\n");
                 return ppc_md.msi_check_device(dev, nvec, type);
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 0f4181272311..9c69e7e145c5 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -38,6 +38,7 @@
 #include <asm/eeh.h>
 
 static DEFINE_SPINLOCK(hose_spinlock);
+LIST_HEAD(hose_list);
 
 /* XXX kill that some day ... */
 static int global_phb_number;           /* Global phb counter */
@@ -49,7 +50,7 @@ resource_size_t isa_mem_base;
 unsigned int ppc_pci_flags = 0;
 
 
-static struct dma_mapping_ops *pci_dma_ops;
+static struct dma_mapping_ops *pci_dma_ops = &dma_direct_ops;
 
 void set_pci_dma_ops(struct dma_mapping_ops *dma_ops)
 {
@@ -113,19 +114,24 @@ void pcibios_free_controller(struct pci_controller *phb)
                 kfree(phb);
 }
 
+static resource_size_t pcibios_io_size(const struct pci_controller *hose)
+{
+#ifdef CONFIG_PPC64
+        return hose->pci_io_size;
+#else
+        return hose->io_resource.end - hose->io_resource.start + 1;
+#endif
+}
+
 int pcibios_vaddr_is_ioport(void __iomem *address)
 {
         int ret = 0;
         struct pci_controller *hose;
-        unsigned long size;
+        resource_size_t size;
 
         spin_lock(&hose_spinlock);
         list_for_each_entry(hose, &hose_list, list_node) {
-#ifdef CONFIG_PPC64
-                size = hose->pci_io_size;
-#else
-                size = hose->io_resource.end - hose->io_resource.start + 1;
-#endif
+                size = pcibios_io_size(hose);
                 if (address >= hose->io_base_virt &&
                     address < (hose->io_base_virt + size)) {
                         ret = 1;
@@ -136,6 +142,29 @@ int pcibios_vaddr_is_ioport(void __iomem *address)
         return ret;
 }
 
+unsigned long pci_address_to_pio(phys_addr_t address)
+{
+        struct pci_controller *hose;
+        resource_size_t size;
+        unsigned long ret = ~0;
+
+        spin_lock(&hose_spinlock);
+        list_for_each_entry(hose, &hose_list, list_node) {
+                size = pcibios_io_size(hose);
+                if (address >= hose->io_base_phys &&
+                    address < (hose->io_base_phys + size)) {
+                        unsigned long base =
+                                (unsigned long)hose->io_base_virt - _IO_BASE;
+                        ret = base + (address - hose->io_base_phys);
+                        break;
+                }
+        }
+        spin_unlock(&hose_spinlock);
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(pci_address_to_pio);
+
 /*
  * Return the domain number for this bus.
  */
@@ -1453,7 +1482,7 @@ void __init pcibios_resource_survey(void)
          * we proceed to assigning things that were left unassigned
          */
         if (!(ppc_pci_flags & PPC_PCI_PROBE_ONLY)) {
-                pr_debug("PCI: Assigning unassigned resouces...\n");
+                pr_debug("PCI: Assigning unassigned resources...\n");
                 pci_assign_unassigned_resources();
         }
 
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 132cd80afa21..d473634e39e3 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -20,6 +20,7 @@
 #include <asm/prom.h>
 #include <asm/sections.h>
 #include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
 #include <asm/byteorder.h>
 #include <asm/uaccess.h>
 #include <asm/machdep.h>
@@ -43,8 +44,6 @@ static u8* pci_to_OF_bus_map;
  */
 static int pci_assign_all_buses;
 
-LIST_HEAD(hose_list);
-
 static int pci_bus_count;
 
 /* This will remain NULL for now, until isa-bridge.c is made common
@@ -219,16 +218,23 @@ scan_OF_pci_childs(struct device_node *parent, pci_OF_scan_iterator filter, void
 static struct device_node *scan_OF_for_pci_dev(struct device_node *parent,
                                                unsigned int devfn)
 {
-        struct device_node *np;
+        struct device_node *np, *cnp;
         const u32 *reg;
         unsigned int psize;
 
         for_each_child_of_node(parent, np) {
                 reg = of_get_property(np, "reg", &psize);
-                if (reg == NULL || psize < 4)
-                        continue;
-                if (((reg[0] >> 8) & 0xff) == devfn)
+                if (reg && psize >= 4 && ((reg[0] >> 8) & 0xff) == devfn)
                         return np;
+
+                /* Note: some OFs create a parent node "multifunc-device" as
+                 * a fake root for all functions of a multi-function device,
+                 * we go down them as well. */
+                if (!strcmp(np->name, "multifunc-device")) {
+                        cnp = scan_OF_for_pci_dev(np, devfn);
+                        if (cnp)
+                                return cnp;
+                }
         }
         return NULL;
 }
@@ -491,24 +497,6 @@ long sys_pciconfig_iobase(long which, unsigned long bus, unsigned long devfn)
         return result;
 }
 
-unsigned long pci_address_to_pio(phys_addr_t address)
-{
-        struct pci_controller *hose, *tmp;
-
-        list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
-                unsigned int size = hose->io_resource.end -
-                        hose->io_resource.start + 1;
-                if (address >= hose->io_base_phys &&
-                    address < (hose->io_base_phys + size)) {
-                        unsigned long base =
-                                (unsigned long)hose->io_base_virt - _IO_BASE;
-                        return base + (address - hose->io_base_phys);
-                }
-        }
-        return (unsigned int)-1;
-}
-EXPORT_SYMBOL(pci_address_to_pio);
-
 /*
  * Null PCI config access functions, for the case when we can't
  * find a hose.
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index ea8eda8c87cf..be574fc0d92f 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -43,8 +43,6 @@ unsigned long pci_probe_only = 1;
 unsigned long pci_io_base = ISA_IO_BASE;
 EXPORT_SYMBOL(pci_io_base);
 
-LIST_HEAD(hose_list);
-
 static void fixup_broken_pcnet32(struct pci_dev* dev)
 {
         if ((dev->class>>8 == PCI_CLASS_NETWORK_ETHERNET)) {
@@ -524,23 +522,6 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus)
 }
 EXPORT_SYMBOL_GPL(pcibios_map_io_space);
 
-unsigned long pci_address_to_pio(phys_addr_t address)
-{
-        struct pci_controller *hose, *tmp;
-
-        list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
-                if (address >= hose->io_base_phys &&
-                    address < (hose->io_base_phys + hose->pci_io_size)) {
-                        unsigned long base =
-                                (unsigned long)hose->io_base_virt - _IO_BASE;
-                        return base + (address - hose->io_base_phys);
-                }
-        }
-        return (unsigned int)-1;
-}
-EXPORT_SYMBOL_GPL(pci_address_to_pio);
-
-
 #define IOBASE_BRIDGE_NUMBER    0
 #define IOBASE_MEMORY           1
 #define IOBASE_IO               2
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index fb7049c054c0..7b44a33f03c2 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -33,7 +33,10 @@
 #include <linux/mqueue.h>
 #include <linux/hardirq.h>
 #include <linux/utsname.h>
+#include <linux/ftrace.h>
 #include <linux/kernel_stat.h>
+#include <linux/personality.h>
+#include <linux/random.h>
 
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
@@ -595,7 +598,7 @@ void prepare_to_copy(struct task_struct *tsk)
 /*
  * Copy a thread..
  */
-int copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
+int copy_thread(unsigned long clone_flags, unsigned long usp,
                 unsigned long unused, struct task_struct *p,
                 struct pt_regs *regs)
 {
@@ -1008,6 +1011,14 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
         unsigned long sp, ip, lr, newsp;
         int count = 0;
         int firstframe = 1;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+        int curr_frame = current->curr_ret_stack;
+        extern void return_to_handler(void);
+        unsigned long addr = (unsigned long)return_to_handler;
+#ifdef CONFIG_PPC64
+        addr = *(unsigned long*)addr;
+#endif
+#endif
 
         sp = (unsigned long) stack;
         if (tsk == NULL)
@@ -1030,6 +1041,13 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
                 ip = stack[STACK_FRAME_LR_SAVE];
                 if (!firstframe || ip != lr) {
                         printk("["REG"] ["REG"] %pS", sp, ip, (void *)ip);
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+                        if (ip == addr && curr_frame >= 0) {
+                                printk(" (%pS)",
+                                       (void *)current->ret_stack[curr_frame].ret);
+                                curr_frame--;
+                        }
+#endif
                         if (firstframe)
                                 printk(" (unreliable)");
                         printk("\n");
@@ -1122,3 +1140,43 @@ void thread_info_cache_init(void)
 }
 
 #endif /* THREAD_SHIFT < PAGE_SHIFT */
+
+unsigned long arch_align_stack(unsigned long sp)
+{
+        if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
+                sp -= get_random_int() & ~PAGE_MASK;
+        return sp & ~0xf;
+}
+
+static inline unsigned long brk_rnd(void)
+{
+        unsigned long rnd = 0;
+
+        /* 8MB for 32bit, 1GB for 64bit */
+        if (is_32bit_task())
+                rnd = (long)(get_random_int() % (1<<(23-PAGE_SHIFT)));
+        else
+                rnd = (long)(get_random_int() % (1<<(30-PAGE_SHIFT)));
+
+        return rnd << PAGE_SHIFT;
+}
+
+unsigned long arch_randomize_brk(struct mm_struct *mm)
+{
+        unsigned long ret = PAGE_ALIGN(mm->brk + brk_rnd());
+
+        if (ret < mm->brk)
+                return mm->brk;
+
+        return ret;
+}
+
+unsigned long randomize_et_dyn(unsigned long base)
+{
+        unsigned long ret = PAGE_ALIGN(base + brk_rnd());
+
+        if (ret < base)
+                return base;
+
+        return ret;
+}
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index f00f83109ab3..5ec6a9e23933 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -1075,11 +1075,6 @@ static void __init early_reserve_mem(void)
                 DBG("reserving: %llx -> %llx\n", base, size);
                 lmb_reserve(base, size);
         }
-
-#if 0
-        DBG("memory reserved, lmbs :\n");
-        lmb_dump_all();
-#endif
 }
 
 #ifdef CONFIG_PHYP_DUMP
@@ -1221,6 +1216,7 @@ void __init early_init_devtree(void *params)
         lmb_enforce_memory_limit(limit);
 
         lmb_analyze();
+        lmb_dump_all();
 
         DBG("Phys. mem: %lx\n", lmb_phys_mem_size());
 
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 7f1b33d5e30d..2e026c0407d4 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -2283,6 +2283,8 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
          */
         prom_init_stdout();
 
+        prom_printf("Preparing to boot %s", RELOC(linux_banner));
+
         /*
          * Get default machine type. At this point, we do not differentiate
          * between pSeries SMP and pSeries LPAR
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index ea3a2ec03ffa..1ac136b128f0 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -20,7 +20,7 @@ WHITELIST="add_reloc_offset __bss_start __bss_stop copy_and_flush
 _end enter_prom memcpy memset reloc_offset __secondary_hold
 __secondary_hold_acknowledge __secondary_hold_spinloop __start
 strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224
-reloc_got2 kernstart_addr memstart_addr"
+reloc_got2 kernstart_addr memstart_addr linux_banner"
 
 NM="$1"
 OBJ="$2"
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index fdfe14c4bdef..ee4c7609b649 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -46,6 +46,7 @@ EXPORT_SYMBOL(rtas);
 
 struct rtas_suspend_me_data {
         atomic_t working; /* number of cpus accessing this struct */
+        atomic_t done;
         int token; /* ibm,suspend-me */
         int error;
         struct completion *complete; /* wait on this until working == 0 */
@@ -689,7 +690,7 @@ static int ibm_suspend_me_token = RTAS_UNKNOWN_SERVICE;
 #ifdef CONFIG_PPC_PSERIES
 static void rtas_percpu_suspend_me(void *info)
 {
-        long rc;
+        long rc = H_SUCCESS;
         unsigned long msr_save;
         int cpu;
         struct rtas_suspend_me_data *data =
@@ -701,7 +702,8 @@ static void rtas_percpu_suspend_me(void *info)
         msr_save = mfmsr();
         mtmsr(msr_save & ~(MSR_EE));
 
-        rc = plpar_hcall_norets(H_JOIN);
+        while (rc == H_SUCCESS && !atomic_read(&data->done))
+                rc = plpar_hcall_norets(H_JOIN);
 
         mtmsr(msr_save);
 
@@ -724,6 +726,9 @@ static void rtas_percpu_suspend_me(void *info)
                        smp_processor_id(), rc);
                 data->error = rc;
         }
+
+        atomic_set(&data->done, 1);
+
         /* This cpu did the suspend or got an error; in either case,
          * we need to prod all other other cpus out of join state.
          * Extra prods are harmless.
@@ -766,6 +771,7 @@ static int rtas_ibm_suspend_me(struct rtas_args *args)
         }
 
         atomic_set(&data.working, 0);
+        atomic_set(&data.done, 0);
         data.token = rtas_token("ibm,suspend-me");
         data.error = 0;
         data.complete = &done;
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 149cb112cd1a..13011a96a977 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -669,7 +669,6 @@ static void remove_flash_pde(struct proc_dir_entry *dp)
 {
         if (dp) {
                 kfree(dp->data);
-                dp->owner = NULL;
                 remove_proc_entry(dp->name, dp->parent);
         }
 }
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 705fc4bf3800..9774f9fed96e 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -35,6 +35,8 @@
 #include <linux/debugfs.h>
 #include <linux/percpu.h>
 #include <linux/lmb.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/processor.h>
@@ -669,3 +671,37 @@ static int powerpc_debugfs_init(void)
 }
 arch_initcall(powerpc_debugfs_init);
 #endif
+
+static int ppc_dflt_bus_notify(struct notifier_block *nb,
+                                unsigned long action, void *data)
+{
+        struct device *dev = data;
+
+        /* We are only intereted in device addition */
+        if (action != BUS_NOTIFY_ADD_DEVICE)
+                return 0;
+
+        set_dma_ops(dev, &dma_direct_ops);
+
+        return NOTIFY_DONE;
+}
+
+static struct notifier_block ppc_dflt_plat_bus_notifier = {
+        .notifier_call = ppc_dflt_bus_notify,
+        .priority = INT_MAX,
+};
+
+static struct notifier_block ppc_dflt_of_bus_notifier = {
+        .notifier_call = ppc_dflt_bus_notify,
+        .priority = INT_MAX,
+};
+
+static int __init setup_bus_notifier(void)
+{
+        bus_register_notifier(&platform_bus_type, &ppc_dflt_plat_bus_notifier);
+        bus_register_notifier(&of_platform_bus_type, &ppc_dflt_of_bus_notifier);
+
+        return 0;
+}
+
+arch_initcall(setup_bus_notifier);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 2d34196bba8c..c410c606955d 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -202,8 +202,6 @@ void __init early_setup(unsigned long dt_ptr)
 
         /* Fix up paca fields required for the boot cpu */
         get_paca()->cpu_start = 1;
-        get_paca()->stab_real = __pa((u64)&initial_stab);
-        get_paca()->stab_addr = (u64)&initial_stab;
 
         /* Probe the machine type */
         probe_machine();
@@ -212,20 +210,8 @@ void __init early_setup(unsigned long dt_ptr)
 
         DBG("Found, Initializing memory management...\n");
 
-        /*
-         * Initialize the MMU Hash table and create the linear mapping
-         * of memory. Has to be done before stab/slb initialization as
-         * this is currently where the page size encoding is obtained
-         */
-        htab_initialize();
-
-        /*
-         * Initialize stab / SLB management except on iSeries
-         */
-        if (cpu_has_feature(CPU_FTR_SLB))
-                slb_initialize();
-        else if (!firmware_has_feature(FW_FEATURE_ISERIES))
-                stab_initialize(get_paca()->stab_real);
+        /* Initialize the hash table or TLB handling */
+        early_init_mmu();
 
         DBG(" <- early_setup()\n");
 }
@@ -233,22 +219,11 @@ void __init early_setup(unsigned long dt_ptr)
 #ifdef CONFIG_SMP
 void early_setup_secondary(void)
 {
-        struct paca_struct *lpaca = get_paca();
-
         /* Mark interrupts enabled in PACA */
-        lpaca->soft_enabled = 0;
+        get_paca()->soft_enabled = 0;
 
-        /* Initialize hash table for that CPU */
-        htab_initialize_secondary();
-
-        /* Initialize STAB/SLB. We use a virtual address as it works
-         * in real mode on pSeries and we want a virutal address on
-         * iSeries anyway
-         */
-        if (cpu_has_feature(CPU_FTR_SLB))
-                slb_initialize();
-        else
-                stab_initialize(lpaca->stab_addr);
+        /* Initialize the hash table or TLB handling */
+        early_init_mmu_secondary();
 }
 
 #endif /* CONFIG_SMP */
@@ -578,13 +553,6 @@ void ppc64_boot_msg(unsigned int src, const char *msg)
         printk("[boot]%04x %s\n", src, msg);
 }
 
-/* Print a termination message (print only -- does not stop the kernel) */
-void ppc64_terminate_msg(unsigned int src, const char *msg)
-{
-        ppc64_do_msg(PPC64_LINUX_FUNCTION|PPC64_TERM_MESSAGE|src, msg);
-        printk("[terminate]%04x %s\n", src, msg);
-}
-
 void cpu_die(void)
 {
         if (ppc_md.cpu_die)
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index a54405ebd7b0..00b5078da9a3 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -26,12 +26,12 @@ int show_unhandled_signals = 0;
  * Allocate space for the signal frame
  */
 void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
-                           size_t frame_size)
+                           size_t frame_size, int is_32)
 {
         unsigned long oldsp, newsp;
 
         /* Default to using normal stack */
-        oldsp = regs->gpr[1];
+        oldsp = get_clean_sp(regs, is_32);
 
         /* Check for alt stack */
         if ((ka->sa.sa_flags & SA_ONSTACK) &&
diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h
index b427bf8e1d8f..6c0ddfc0603e 100644
--- a/arch/powerpc/kernel/signal.h
+++ b/arch/powerpc/kernel/signal.h
@@ -15,7 +15,7 @@
 extern void do_signal(struct pt_regs *regs, unsigned long thread_info_flags);
 
 extern void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
-                                  size_t frame_size);
+                                  size_t frame_size, int is_32);
 extern void restore_sigmask(sigset_t *set);
 
 extern int handle_signal32(unsigned long sig, struct k_sigaction *ka,
@@ -39,22 +39,12 @@ extern unsigned long copy_vsx_from_user(struct task_struct *task,
 
 #ifdef CONFIG_PPC64
 
-static inline int is_32bit_task(void)
-{
-        return test_thread_flag(TIF_32BIT);
-}
-
 extern int handle_rt_signal64(int signr, struct k_sigaction *ka,
                               siginfo_t *info, sigset_t *set,
                               struct pt_regs *regs);
 
 #else /* CONFIG_PPC64 */
 
-static inline int is_32bit_task(void)
-{
-        return 1;
-}
-
 static inline int handle_rt_signal64(int signr, struct k_sigaction *ka,
                                      siginfo_t *info, sigset_t *set,
                                      struct pt_regs *regs)
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index b13abf305996..d670429a1608 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -836,7 +836,7 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka,
 
         /* Set up Signal Frame */
         /* Put a Real Time Context onto stack */
-        rt_sf = get_sigframe(ka, regs, sizeof(*rt_sf));
+        rt_sf = get_sigframe(ka, regs, sizeof(*rt_sf), 1);
         addr = rt_sf;
         if (unlikely(rt_sf == NULL))
                 goto badframe;
@@ -1182,7 +1182,7 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka,
         unsigned long newsp = 0;
 
         /* Set up Signal Frame */
-        frame = get_sigframe(ka, regs, sizeof(*frame));
+        frame = get_sigframe(ka, regs, sizeof(*frame), 1);
         if (unlikely(frame == NULL))
                 goto badframe;
         sc = (struct sigcontext __user *) &frame->sctx;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index e132891d3cea..2fe6fc64b614 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -402,7 +402,7 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info,
         unsigned long newsp = 0;
         long err = 0;
 
-        frame = get_sigframe(ka, regs, sizeof(*frame));
+        frame = get_sigframe(ka, regs, sizeof(*frame), 0);
         if (unlikely(frame == NULL))
                 goto badframe;
 
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 4a2ee08af6a7..f41aec85aa49 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -134,44 +134,23 @@ void ppc_enable_pmcs(void)
 }
 EXPORT_SYMBOL(ppc_enable_pmcs);
 
-#if defined(CONFIG_6xx) || defined(CONFIG_PPC64)
-/* XXX convert to rusty's on_one_cpu */
-static unsigned long run_on_cpu(unsigned long cpu,
-                                unsigned long (*func)(unsigned long),
-                                unsigned long arg)
-{
-        cpumask_t old_affinity = current->cpus_allowed;
-        unsigned long ret;
-
-        /* should return -EINVAL to userspace */
-        if (set_cpus_allowed(current, cpumask_of_cpu(cpu)))
-                return 0;
-
-        ret = func(arg);
-
-        set_cpus_allowed(current, old_affinity);
-
-        return ret;
-}
-#endif
-
 #define SYSFS_PMCSETUP(NAME, ADDRESS) \
-static unsigned long read_##NAME(unsigned long junk) \
+static void read_##NAME(void *val) \
 { \
-        return mfspr(ADDRESS); \
+        *(unsigned long *)val = mfspr(ADDRESS); \
 } \
-static unsigned long write_##NAME(unsigned long val) \
+static void write_##NAME(void *val) \
 { \
         ppc_enable_pmcs(); \
-        mtspr(ADDRESS, val); \
-        return 0; \
+        mtspr(ADDRESS, *(unsigned long *)val);  \
 } \
 static ssize_t show_##NAME(struct sys_device *dev, \
                         struct sysdev_attribute *attr, \
                         char *buf) \
 { \
         struct cpu *cpu = container_of(dev, struct cpu, sysdev); \
-        unsigned long val = run_on_cpu(cpu->sysdev.id, read_##NAME, 0); \
+        unsigned long val; \
+        smp_call_function_single(cpu->sysdev.id, read_##NAME, &val, 1); \
         return sprintf(buf, "%lx\n", val); \
 } \
 static ssize_t __used \
@@ -183,7 +162,7 @@ static ssize_t __used \
         int ret = sscanf(buf, "%lx", &val); \
         if (ret != 1) \
                 return -EINVAL; \
-        run_on_cpu(cpu->sysdev.id, write_##NAME, val); \
+        smp_call_function_single(cpu->sysdev.id, write_##NAME, &val, 1); \
         return count; \
 }
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index c9564031a2a9..926ea864e34f 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -1127,3 +1127,19 @@ void div128_by_32(u64 dividend_high, u64 dividend_low,
         dr->result_low  = ((u64)y << 32) + z;
 
 }
+
+static int __init rtc_init(void)
+{
+        struct platform_device *pdev;
+
+        if (!ppc_md.get_rtc_time)
+                return -ENODEV;
+
+        pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0);
+        if (IS_ERR(pdev))
+                return PTR_ERR(pdev);
+
+        return 0;
+}
+
+module_init(rtc_init);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 5457e9575685..678fbff0d206 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -52,6 +52,10 @@
 #include <asm/processor.h>
 #endif
 #include <asm/kexec.h>
+#include <asm/ppc-opcode.h>
+#ifdef CONFIG_FSL_BOOKE
+#include <asm/dbell.h>
+#endif
 
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
 int (*__debugger)(struct pt_regs *regs);
@@ -637,29 +641,6 @@ static void parse_fpe(struct pt_regs *regs)
  * bits is faster and easier.
  *
  */
-#define INST_MFSPR_PVR          0x7c1f42a6
-#define INST_MFSPR_PVR_MASK     0xfc1fffff
-
-#define INST_DCBA               0x7c0005ec
-#define INST_DCBA_MASK          0xfc0007fe
-
-#define INST_MCRXR              0x7c000400
-#define INST_MCRXR_MASK         0xfc0007fe
-
-#define INST_STRING             0x7c00042a
-#define INST_STRING_MASK        0xfc0007fe
-#define INST_STRING_GEN_MASK    0xfc00067e
-#define INST_LSWI               0x7c0004aa
-#define INST_LSWX               0x7c00042a
-#define INST_STSWI              0x7c0005aa
-#define INST_STSWX              0x7c00052a
-
-#define INST_POPCNTB            0x7c0000f4
-#define INST_POPCNTB_MASK       0xfc0007fe
-
-#define INST_ISEL               0x7c00001e
-#define INST_ISEL_MASK          0xfc00003e
-
 static int emulate_string_inst(struct pt_regs *regs, u32 instword)
 {
         u8 rT = (instword >> 21) & 0x1f;
@@ -670,20 +651,20 @@ static int emulate_string_inst(struct pt_regs *regs, u32 instword)
         int pos = 0;
 
         /* Early out if we are an invalid form of lswx */
-        if ((instword & INST_STRING_MASK) == INST_LSWX)
+        if ((instword & PPC_INST_STRING_MASK) == PPC_INST_LSWX)
                 if ((rT == rA) || (rT == NB_RB))
                         return -EINVAL;
 
         EA = (rA == 0) ? 0 : regs->gpr[rA];
 
-        switch (instword & INST_STRING_MASK) {
-                case INST_LSWX:
-                case INST_STSWX:
+        switch (instword & PPC_INST_STRING_MASK) {
+                case PPC_INST_LSWX:
+                case PPC_INST_STSWX:
                         EA += NB_RB;
                         num_bytes = regs->xer & 0x7f;
                         break;
-                case INST_LSWI:
-                case INST_STSWI:
+                case PPC_INST_LSWI:
+                case PPC_INST_STSWI:
                         num_bytes = (NB_RB == 0) ? 32 : NB_RB;
                         break;
                 default:
@@ -695,9 +676,9 @@ static int emulate_string_inst(struct pt_regs *regs, u32 instword)
                 u8 val;
                 u32 shift = 8 * (3 - (pos & 0x3));
 
-                switch ((instword & INST_STRING_MASK)) {
-                        case INST_LSWX:
-                        case INST_LSWI:
+                switch ((instword & PPC_INST_STRING_MASK)) {
+                        case PPC_INST_LSWX:
+                        case PPC_INST_LSWI:
                                 if (get_user(val, (u8 __user *)EA))
                                         return -EFAULT;
                                 /* first time updating this reg,
@@ -706,8 +687,8 @@ static int emulate_string_inst(struct pt_regs *regs, u32 instword)
                                         regs->gpr[rT] = 0;
                                 regs->gpr[rT] |= val << shift;
                                 break;
-                        case INST_STSWI:
-                        case INST_STSWX:
+                        case PPC_INST_STSWI:
+                        case PPC_INST_STSWX:
                                 val = regs->gpr[rT] >> shift;
                                 if (put_user(val, (u8 __user *)EA))
                                         return -EFAULT;
@@ -775,18 +756,18 @@ static int emulate_instruction(struct pt_regs *regs)
                 return -EFAULT;
 
         /* Emulate the mfspr rD, PVR. */
-        if ((instword & INST_MFSPR_PVR_MASK) == INST_MFSPR_PVR) {
+        if ((instword & PPC_INST_MFSPR_PVR_MASK) == PPC_INST_MFSPR_PVR) {
                 rd = (instword >> 21) & 0x1f;
                 regs->gpr[rd] = mfspr(SPRN_PVR);
                 return 0;
         }
 
         /* Emulating the dcba insn is just a no-op.  */
-        if ((instword & INST_DCBA_MASK) == INST_DCBA)
+        if ((instword & PPC_INST_DCBA_MASK) == PPC_INST_DCBA)
                 return 0;
 
         /* Emulate the mcrxr insn.  */
-        if ((instword & INST_MCRXR_MASK) == INST_MCRXR) {
+        if ((instword & PPC_INST_MCRXR_MASK) == PPC_INST_MCRXR) {
                 int shift = (instword >> 21) & 0x1c;
                 unsigned long msk = 0xf0000000UL >> shift;
 
@@ -796,16 +777,16 @@ static int emulate_instruction(struct pt_regs *regs)
         }
 
         /* Emulate load/store string insn. */
-        if ((instword & INST_STRING_GEN_MASK) == INST_STRING)
+        if ((instword & PPC_INST_STRING_GEN_MASK) == PPC_INST_STRING)
                 return emulate_string_inst(regs, instword);
 
         /* Emulate the popcntb (Population Count Bytes) instruction. */
-        if ((instword & INST_POPCNTB_MASK) == INST_POPCNTB) {
+        if ((instword & PPC_INST_POPCNTB_MASK) == PPC_INST_POPCNTB) {
                 return emulate_popcntb_inst(regs, instword);
         }
 
         /* Emulate isel (Integer Select) instruction */
-        if ((instword & INST_ISEL_MASK) == INST_ISEL) {
+        if ((instword & PPC_INST_ISEL_MASK) == PPC_INST_ISEL) {
                 return emulate_isel(regs, instword);
         }
 
@@ -1144,6 +1125,24 @@ void vsx_assist_exception(struct pt_regs *regs)
 #endif /* CONFIG_VSX */
 
 #ifdef CONFIG_FSL_BOOKE
+
+void doorbell_exception(struct pt_regs *regs)
+{
+#ifdef CONFIG_SMP
+        int cpu = smp_processor_id();
+        int msg;
+
+        if (num_online_cpus() < 2)
+                return;
+
+        for (msg = 0; msg < 4; msg++)
+                if (test_and_clear_bit(msg, &dbell_smp_message[cpu]))
+                        smp_message_recv(msg);
+#else
+        printk(KERN_WARNING "Received doorbell on non-smp system\n");
+#endif
+}
+
 void CacheLockingException(struct pt_regs *regs, unsigned long address,
                            unsigned long error_code)
 {
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index 7d6c9bb8c77f..fc9af47e2128 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -18,6 +18,7 @@
 #include <asm/udbg.h>
 
 void (*udbg_putc)(char c);
+void (*udbg_flush)(void);
 int (*udbg_getc)(void);
 int (*udbg_getc_poll)(void);
 
@@ -76,6 +77,9 @@ void udbg_puts(const char *s)
                         while ((c = *s++) != '\0')
                                 udbg_putc(c);
                 }
+
+                if (udbg_flush)
+                        udbg_flush();
         }
 #if 0
         else {
@@ -98,6 +102,9 @@ int udbg_write(const char *s, int n)
                 }
         }
 
+        if (udbg_flush)
+                udbg_flush();
+
         return n - remain;
 }
 
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 7b7da8cfd5e8..0362a891e54e 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -48,14 +48,21 @@ struct NS16550 {
 
 static struct NS16550 __iomem *udbg_comport;
 
-static void udbg_550_putc(char c)
+static void udbg_550_flush(void)
 {
         if (udbg_comport) {
                 while ((in_8(&udbg_comport->lsr) & LSR_THRE) == 0)
                         /* wait for idle */;
-                out_8(&udbg_comport->thr, c);
+        }
+}
+
+static void udbg_550_putc(char c)
+{
+        if (udbg_comport) {
                 if (c == '\n')
                         udbg_550_putc('\r');
+                udbg_550_flush();
+                out_8(&udbg_comport->thr, c);
         }
 }
 
@@ -108,6 +115,7 @@ void udbg_init_uart(void __iomem *comport, unsigned int speed,
                 /* Clear & enable FIFOs */
                 out_8(&udbg_comport->fcr ,0x07);
                 udbg_putc = udbg_550_putc;
+                udbg_flush = udbg_550_flush;
                 udbg_getc = udbg_550_getc;
                 udbg_getc_poll = udbg_550_getc_poll;
         }
@@ -149,14 +157,21 @@ unsigned int udbg_probe_uart_speed(void __iomem *comport, unsigned int clock)
 }
 
 #ifdef CONFIG_PPC_MAPLE
-void udbg_maple_real_putc(char c)
+void udbg_maple_real_flush(void)
 {
         if (udbg_comport) {
                 while ((real_readb(&udbg_comport->lsr) & LSR_THRE) == 0)
                         /* wait for idle */;
-                real_writeb(c, &udbg_comport->thr); eieio();
+        }
+}
+
+void udbg_maple_real_putc(char c)
+{
+        if (udbg_comport) {
                 if (c == '\n')
                         udbg_maple_real_putc('\r');
+                udbg_maple_real_flush();
+                real_writeb(c, &udbg_comport->thr); eieio();
         }
 }
 
@@ -165,20 +180,28 @@ void __init udbg_init_maple_realmode(void)
         udbg_comport = (struct NS16550 __iomem *)0xf40003f8;
 
         udbg_putc = udbg_maple_real_putc;
+        udbg_flush = udbg_maple_real_flush;
         udbg_getc = NULL;
         udbg_getc_poll = NULL;
 }
 #endif /* CONFIG_PPC_MAPLE */
 
 #ifdef CONFIG_PPC_PASEMI
-void udbg_pas_real_putc(char c)
+void udbg_pas_real_flush(void)
 {
         if (udbg_comport) {
                 while ((real_205_readb(&udbg_comport->lsr) & LSR_THRE) == 0)
                         /* wait for idle */;
-                real_205_writeb(c, &udbg_comport->thr); eieio();
+        }
+}
+
+void udbg_pas_real_putc(char c)
+{
+        if (udbg_comport) {
                 if (c == '\n')
                         udbg_pas_real_putc('\r');
+                udbg_pas_real_flush();
+                real_205_writeb(c, &udbg_comport->thr); eieio();
         }
 }
 
@@ -187,6 +210,7 @@ void udbg_init_pas_realmode(void)
         udbg_comport = (struct NS16550 __iomem *)0xfcff03f8UL;
 
         udbg_putc = udbg_pas_real_putc;
+        udbg_flush = udbg_pas_real_flush;
         udbg_getc = NULL;
         udbg_getc_poll = NULL;
 }
@@ -195,14 +219,21 @@ void udbg_init_pas_realmode(void)
 #ifdef CONFIG_PPC_EARLY_DEBUG_44x
 #include <platforms/44x/44x.h>
 
-static void udbg_44x_as1_putc(char c)
+static int udbg_44x_as1_flush(void)
 {
         if (udbg_comport) {
                 while ((as1_readb(&udbg_comport->lsr) & LSR_THRE) == 0)
                         /* wait for idle */;
-                as1_writeb(c, &udbg_comport->thr); eieio();
+        }
+}
+
+static void udbg_44x_as1_putc(char c)
+{
+        if (udbg_comport) {
                 if (c == '\n')
                         udbg_44x_as1_putc('\r');
+                udbg_44x_as1_flush();
+                as1_writeb(c, &udbg_comport->thr); eieio();
         }
 }
 
@@ -222,19 +253,27 @@ void __init udbg_init_44x_as1(void)
                 (struct NS16550 __iomem *)PPC44x_EARLY_DEBUG_VIRTADDR;
 
         udbg_putc = udbg_44x_as1_putc;
+        udbg_flush = udbg_44x_as1_flush;
         udbg_getc = udbg_44x_as1_getc;
 }
 #endif /* CONFIG_PPC_EARLY_DEBUG_44x */
 
 #ifdef CONFIG_PPC_EARLY_DEBUG_40x
-static void udbg_40x_real_putc(char c)
+static void udbg_40x_real_flush(void)
 {
         if (udbg_comport) {
                 while ((real_readb(&udbg_comport->lsr) & LSR_THRE) == 0)
                         /* wait for idle */;
-                real_writeb(c, &udbg_comport->thr); eieio();
+        }
+}
+
+static void udbg_40x_real_putc(char c)
+{
+        if (udbg_comport) {
                 if (c == '\n')
                         udbg_40x_real_putc('\r');
+                udbg_40x_real_flush();
+                real_writeb(c, &udbg_comport->thr); eieio();
         }
 }
 
@@ -254,6 +293,7 @@ void __init udbg_init_40x_realmode(void)
                 CONFIG_PPC_EARLY_DEBUG_40x_PHYSADDR;
 
         udbg_putc = udbg_40x_real_putc;
+        udbg_flush = udbg_40x_real_flush;
         udbg_getc = udbg_40x_real_getc;
         udbg_getc_poll = NULL;
 }
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index d3694498f3af..819e59f6f7c7 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -482,7 +482,7 @@ static void vio_cmo_balance(struct work_struct *work)
         cmo->excess.size = cmo->entitled - cmo->reserve.size;
         cmo->excess.free = cmo->excess.size - need;
 
-        cancel_delayed_work(container_of(work, struct delayed_work, work));
+        cancel_delayed_work(to_delayed_work(work));
         spin_unlock_irqrestore(&vio_cmo.lock, flags);
 }
 
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 295ccc5e86b1..b9ef1644a722 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -58,6 +58,7 @@ SECTIONS
                 SCHED_TEXT
                 LOCK_TEXT
                 KPROBES_TEXT
+                IRQENTRY_TEXT
 
 #ifdef CONFIG_PPC32
                 *(.got1)
@@ -181,14 +182,7 @@ SECTIONS
                 __initramfs_end = .;
         }
 #endif
-        . = ALIGN(PAGE_SIZE);
-        .data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {
-                __per_cpu_start = .;
-                *(.data.percpu.page_aligned)
-                *(.data.percpu)
-                *(.data.percpu.shared_aligned)
-                __per_cpu_end = .;
-        }
+        PERCPU(PAGE_SIZE)
 
         . = ALIGN(8);
         .machine.desc : AT(ADDR(.machine.desc) - LOAD_OFFSET) {