14 files changed, 1288 insertions, 44 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index b9db46ae545b..e132902e1f14 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_PPC_RTAS)		+= rtas.o rtas-rtc.o $(rtaspci-y-y)
 obj-$(CONFIG_PPC_RTAS_DAEMON)	+= rtasd.o
 obj-$(CONFIG_RTAS_FLASH)	+= rtas_flash.o
 obj-$(CONFIG_RTAS_PROC)		+= rtas-proc.o
+obj-$(CONFIG_PPC_DT_CPU_FTRS)	+= dt_cpu_ftrs.o
 obj-$(CONFIG_EEH)              += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \
 				  eeh_driver.o eeh_event.o eeh_sysfs.o
 obj-$(CONFIG_GENERIC_TBSYNC)	+= smp-tbsync.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 439c257dec4a..709e23425317 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -634,6 +634,8 @@ int main(void)
 	HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu);
 	HSTATE_FIELD(HSTATE_KVM_VCORE, kvm_vcore);
 	HSTATE_FIELD(HSTATE_XICS_PHYS, xics_phys);
+	HSTATE_FIELD(HSTATE_XIVE_TIMA_PHYS, xive_tima_phys);
+	HSTATE_FIELD(HSTATE_XIVE_TIMA_VIRT, xive_tima_virt);
 	HSTATE_FIELD(HSTATE_SAVED_XIRR, saved_xirr);
 	HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi);
 	HSTATE_FIELD(HSTATE_PTID, ptid);
@@ -719,6 +721,14 @@ int main(void)
 	OFFSET(VCPU_HOST_MAS6, kvm_vcpu, arch.host_mas6);
 #endif
 
+#ifdef CONFIG_KVM_XICS
+	DEFINE(VCPU_XIVE_SAVED_STATE, offsetof(struct kvm_vcpu,
+					       arch.xive_saved_state));
+	DEFINE(VCPU_XIVE_CAM_WORD, offsetof(struct kvm_vcpu,
+					    arch.xive_cam_word));
+	DEFINE(VCPU_XIVE_PUSHED, offsetof(struct kvm_vcpu, arch.xive_pushed));
+#endif
+
 #ifdef CONFIG_KVM_EXIT_TIMING
 	OFFSET(VCPU_TIMING_EXIT_TBU, kvm_vcpu, arch.timing_exit.tv32.tbu);
 	OFFSET(VCPU_TIMING_EXIT_TBL, kvm_vcpu, arch.timing_exit.tv32.tbl);
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index e79b9daa873c..6f849832a669 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -23,7 +23,9 @@
 #include <asm/mmu.h>
 #include <asm/setup.h>
 
-struct cpu_spec* cur_cpu_spec = NULL;
+static struct cpu_spec the_cpu_spec __read_mostly;
+
+struct cpu_spec* cur_cpu_spec __read_mostly = NULL;
 EXPORT_SYMBOL(cur_cpu_spec);
 
 /* The platform string corresponding to the real PVR */
@@ -122,7 +124,8 @@ extern void __restore_cpu_e6500(void);
 #define COMMON_USER_POWER9	COMMON_USER_POWER8
 #define COMMON_USER2_POWER9	(COMMON_USER2_POWER8 | \
 				 PPC_FEATURE2_ARCH_3_00 | \
-				 PPC_FEATURE2_HAS_IEEE128)
+				 PPC_FEATURE2_HAS_IEEE128 | \
+				 PPC_FEATURE2_DARN )
 
 #ifdef CONFIG_PPC_BOOK3E_64
 #define COMMON_USER_BOOKE	(COMMON_USER_PPC64 | PPC_FEATURE_BOOKE)
@@ -2179,7 +2182,15 @@ static struct cpu_spec __initdata cpu_specs[] = {
 #endif /* CONFIG_E500 */
 };
 
-static struct cpu_spec the_cpu_spec;
+void __init set_cur_cpu_spec(struct cpu_spec *s)
+{
+	struct cpu_spec *t = &the_cpu_spec;
+
+	t = PTRRELOC(t);
+	*t = *s;
+
+	*PTRRELOC(&cur_cpu_spec) = &the_cpu_spec;
+}
 
 static struct cpu_spec * __init setup_cpu_spec(unsigned long offset,
 					       struct cpu_spec *s)
@@ -2266,6 +2277,29 @@ struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr)
 	return NULL;
 }
 
+/*
+ * Used by cpufeatures to get the name for CPUs with a PVR table.
+ * If they don't hae a PVR table, cpufeatures gets the name from
+ * cpu device-tree node.
+ */
+void __init identify_cpu_name(unsigned int pvr)
+{
+	struct cpu_spec *s = cpu_specs;
+	struct cpu_spec *t = &the_cpu_spec;
+	int i;
+
+	s = PTRRELOC(s);
+	t = PTRRELOC(t);
+
+	for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++) {
+		if ((pvr & s->pvr_mask) == s->pvr_value) {
+			t->cpu_name = s->cpu_name;
+			return;
+		}
+	}
+}
+
+
 #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS
 struct static_key_true cpu_feature_keys[NUM_CPU_FTR_KEYS] = {
 			[0 ... NUM_CPU_FTR_KEYS - 1] = STATIC_KEY_TRUE_INIT
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
new file mode 100644
index 000000000000..4c7656dc4e04
--- /dev/null
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -0,0 +1,1069 @@
+/*
+ * Copyright 2017, Nicholas Piggin, IBM Corporation
+ * Licensed under GPLv2.
+ */
+
+#define pr_fmt(fmt) "dt-cpu-ftrs: " fmt
+
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/jump_label.h>
+#include <linux/libfdt.h>
+#include <linux/memblock.h>
+#include <linux/printk.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/threads.h>
+
+#include <asm/cputable.h>
+#include <asm/dt_cpu_ftrs.h>
+#include <asm/mmu.h>
+#include <asm/oprofile_impl.h>
+#include <asm/prom.h>
+#include <asm/setup.h>
+
+
+/* Device-tree visible constants follow */
+#define ISA_V2_07B      2070
+#define ISA_V3_0B       3000
+
+#define USABLE_PR               (1U << 0)
+#define USABLE_OS               (1U << 1)
+#define USABLE_HV               (1U << 2)
+
+#define HV_SUPPORT_HFSCR        (1U << 0)
+#define OS_SUPPORT_FSCR         (1U << 0)
+
+/* For parsing, we define all bits set as "NONE" case */
+#define HV_SUPPORT_NONE		0xffffffffU
+#define OS_SUPPORT_NONE		0xffffffffU
+
+struct dt_cpu_feature {
+	const char *name;
+	uint32_t isa;
+	uint32_t usable_privilege;
+	uint32_t hv_support;
+	uint32_t os_support;
+	uint32_t hfscr_bit_nr;
+	uint32_t fscr_bit_nr;
+	uint32_t hwcap_bit_nr;
+	/* fdt parsing */
+	unsigned long node;
+	int enabled;
+	int disabled;
+};
+
+#define CPU_FTRS_BASE \
+	   (CPU_FTR_USE_TB | \
+	    CPU_FTR_LWSYNC | \
+	    CPU_FTR_FPU_UNAVAILABLE |\
+	    CPU_FTR_NODSISRALIGN |\
+	    CPU_FTR_NOEXECUTE |\
+	    CPU_FTR_COHERENT_ICACHE | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS |\
+	    CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_DAWR | \
+	    CPU_FTR_ARCH_206 |\
+	    CPU_FTR_ARCH_207S)
+
+#define MMU_FTRS_HASH_BASE (MMU_FTRS_POWER8)
+
+#define COMMON_USER_BASE	(PPC_FEATURE_32 | PPC_FEATURE_64 | \
+				 PPC_FEATURE_ARCH_2_06 |\
+				 PPC_FEATURE_ICACHE_SNOOP)
+#define COMMON_USER2_BASE	(PPC_FEATURE2_ARCH_2_07 | \
+				 PPC_FEATURE2_ISEL)
+/*
+ * Set up the base CPU
+ */
+
+extern void __flush_tlb_power8(unsigned int action);
+extern void __flush_tlb_power9(unsigned int action);
+extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
+extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
+
+static int hv_mode;
+
+static struct {
+	u64	lpcr;
+	u64	hfscr;
+	u64	fscr;
+} system_registers;
+
+static void (*init_pmu_registers)(void);
+
+static void cpufeatures_flush_tlb(void)
+{
+	unsigned long rb;
+	unsigned int i, num_sets;
+
+	/*
+	 * This is a temporary measure to keep equivalent TLB flush as the
+	 * cputable based setup code.
+	 */
+	switch (PVR_VER(mfspr(SPRN_PVR))) {
+	case PVR_POWER8:
+	case PVR_POWER8E:
+	case PVR_POWER8NVL:
+		num_sets = POWER8_TLB_SETS;
+		break;
+	case PVR_POWER9:
+		num_sets = POWER9_TLB_SETS_HASH;
+		break;
+	default:
+		num_sets = 1;
+		pr_err("unknown CPU version for boot TLB flush\n");
+		break;
+	}
+
+	asm volatile("ptesync" : : : "memory");
+	rb = TLBIEL_INVAL_SET;
+	for (i = 0; i < num_sets; i++) {
+		asm volatile("tlbiel %0" : : "r" (rb));
+		rb += 1 << TLBIEL_INVAL_SET_SHIFT;
+	}
+	asm volatile("ptesync" : : : "memory");
+}
+
+static void __restore_cpu_cpufeatures(void)
+{
+	/*
+	 * LPCR is restored by the power on engine already. It can be changed
+	 * after early init e.g., by radix enable, and we have no unified API
+	 * for saving and restoring such SPRs.
+	 *
+	 * This ->restore hook should really be removed from idle and register
+	 * restore moved directly into the idle restore code, because this code
+	 * doesn't know how idle is implemented or what it needs restored here.
+	 *
+	 * The best we can do to accommodate secondary boot and idle restore
+	 * for now is "or" LPCR with existing.
+	 */
+
+	mtspr(SPRN_LPCR, system_registers.lpcr | mfspr(SPRN_LPCR));
+	if (hv_mode) {
+		mtspr(SPRN_LPID, 0);
+		mtspr(SPRN_HFSCR, system_registers.hfscr);
+	}
+	mtspr(SPRN_FSCR, system_registers.fscr);
+
+	if (init_pmu_registers)
+		init_pmu_registers();
+
+	cpufeatures_flush_tlb();
+}
+
+static char dt_cpu_name[64];
+
+static struct cpu_spec __initdata base_cpu_spec = {
+	.cpu_name		= NULL,
+	.cpu_features		= CPU_FTRS_BASE,
+	.cpu_user_features	= COMMON_USER_BASE,
+	.cpu_user_features2	= COMMON_USER2_BASE,
+	.mmu_features		= 0,
+	.icache_bsize		= 32, /* minimum block size, fixed by */
+	.dcache_bsize		= 32, /* cache info init.             */
+	.num_pmcs		= 0,
+	.pmc_type		= PPC_PMC_DEFAULT,
+	.oprofile_cpu_type	= NULL,
+	.oprofile_type		= PPC_OPROFILE_INVALID,
+	.cpu_setup		= NULL,
+	.cpu_restore		= __restore_cpu_cpufeatures,
+	.flush_tlb		= NULL,
+	.machine_check_early	= NULL,
+	.platform		= NULL,
+};
+
+static void __init cpufeatures_setup_cpu(void)
+{
+	set_cur_cpu_spec(&base_cpu_spec);
+
+	cur_cpu_spec->pvr_mask = -1;
+	cur_cpu_spec->pvr_value = mfspr(SPRN_PVR);
+
+	/* Initialize the base environment -- clear FSCR/HFSCR.  */
+	hv_mode = !!(mfmsr() & MSR_HV);
+	if (hv_mode) {
+		/* CPU_FTR_HVMODE is used early in PACA setup */
+		cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE;
+		mtspr(SPRN_HFSCR, 0);
+	}
+	mtspr(SPRN_FSCR, 0);
+
+	/*
+	 * LPCR does not get cleared, to match behaviour with secondaries
+	 * in __restore_cpu_cpufeatures. Once the idle code is fixed, this
+	 * could clear LPCR too.
+	 */
+}
+
+static int __init feat_try_enable_unknown(struct dt_cpu_feature *f)
+{
+	if (f->hv_support == HV_SUPPORT_NONE) {
+	} else if (f->hv_support & HV_SUPPORT_HFSCR) {
+		u64 hfscr = mfspr(SPRN_HFSCR);
+		hfscr |= 1UL << f->hfscr_bit_nr;
+		mtspr(SPRN_HFSCR, hfscr);
+	} else {
+		/* Does not have a known recipe */
+		return 0;
+	}
+
+	if (f->os_support == OS_SUPPORT_NONE) {
+	} else if (f->os_support & OS_SUPPORT_FSCR) {
+		u64 fscr = mfspr(SPRN_FSCR);
+		fscr |= 1UL << f->fscr_bit_nr;
+		mtspr(SPRN_FSCR, fscr);
+	} else {
+		/* Does not have a known recipe */
+		return 0;
+	}
+
+	if ((f->usable_privilege & USABLE_PR) && (f->hwcap_bit_nr != -1)) {
+		uint32_t word = f->hwcap_bit_nr / 32;
+		uint32_t bit = f->hwcap_bit_nr % 32;
+
+		if (word == 0)
+			cur_cpu_spec->cpu_user_features |= 1U << bit;
+		else if (word == 1)
+			cur_cpu_spec->cpu_user_features2 |= 1U << bit;
+		else
+			pr_err("%s could not advertise to user (no hwcap bits)\n", f->name);
+	}
+
+	return 1;
+}
+
+static int __init feat_enable(struct dt_cpu_feature *f)
+{
+	if (f->hv_support != HV_SUPPORT_NONE) {
+		if (f->hfscr_bit_nr != -1) {
+			u64 hfscr = mfspr(SPRN_HFSCR);
+			hfscr |= 1UL << f->hfscr_bit_nr;
+			mtspr(SPRN_HFSCR, hfscr);
+		}
+	}
+
+	if (f->os_support != OS_SUPPORT_NONE) {
+		if (f->fscr_bit_nr != -1) {
+			u64 fscr = mfspr(SPRN_FSCR);
+			fscr |= 1UL << f->fscr_bit_nr;
+			mtspr(SPRN_FSCR, fscr);
+		}
+	}
+
+	if ((f->usable_privilege & USABLE_PR) && (f->hwcap_bit_nr != -1)) {
+		uint32_t word = f->hwcap_bit_nr / 32;
+		uint32_t bit = f->hwcap_bit_nr % 32;
+
+		if (word == 0)
+			cur_cpu_spec->cpu_user_features |= 1U << bit;
+		else if (word == 1)
+			cur_cpu_spec->cpu_user_features2 |= 1U << bit;
+		else
+			pr_err("CPU feature: %s could not advertise to user (no hwcap bits)\n", f->name);
+	}
+
+	return 1;
+}
+
+static int __init feat_disable(struct dt_cpu_feature *f)
+{
+	return 0;
+}
+
+static int __init feat_enable_hv(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	if (!hv_mode) {
+		pr_err("CPU feature hypervisor present in device tree but HV mode not enabled in the CPU. Ignoring.\n");
+		return 0;
+	}
+
+	mtspr(SPRN_LPID, 0);
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr &=  ~LPCR_LPES0; /* HV external interrupts */
+	mtspr(SPRN_LPCR, lpcr);
+
+	cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE;
+
+	return 1;
+}
+
+static int __init feat_enable_le(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_TRUE_LE;
+	return 1;
+}
+
+static int __init feat_enable_smt(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_SMT;
+	return 1;
+}
+
+static int __init feat_enable_idle_nap(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	/* Set PECE wakeup modes for ISA 207 */
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr |=  LPCR_PECE0;
+	lpcr |=  LPCR_PECE1;
+	lpcr |=  LPCR_PECE2;
+	mtspr(SPRN_LPCR, lpcr);
+
+	return 1;
+}
+
+static int __init feat_enable_align_dsisr(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->cpu_features &= ~CPU_FTR_NODSISRALIGN;
+
+	return 1;
+}
+
+static int __init feat_enable_idle_stop(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	/* Set PECE wakeup modes for ISAv3.0B */
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr |=  LPCR_PECE0;
+	lpcr |=  LPCR_PECE1;
+	lpcr |=  LPCR_PECE2;
+	mtspr(SPRN_LPCR, lpcr);
+
+	return 1;
+}
+
+static int __init feat_enable_mmu_hash(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr &= ~LPCR_ISL;
+
+	/* VRMASD */
+	lpcr |= LPCR_VPM0;
+	lpcr &= ~LPCR_VPM1;
+	lpcr |= 0x10UL << LPCR_VRMASD_SH; /* L=1 LP=00 */
+	mtspr(SPRN_LPCR, lpcr);
+
+	cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU;
+
+	return 1;
+}
+
+static int __init feat_enable_mmu_hash_v3(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr &= ~LPCR_ISL;
+	mtspr(SPRN_LPCR, lpcr);
+
+	cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU;
+
+	return 1;
+}
+
+
+static int __init feat_enable_mmu_radix(struct dt_cpu_feature *f)
+{
+#ifdef CONFIG_PPC_RADIX_MMU
+	cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX;
+	cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU;
+
+	return 1;
+#endif
+	return 0;
+}
+
+static int __init feat_enable_dscr(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	feat_enable(f);
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr &= ~LPCR_DPFD;
+	lpcr |=  (4UL << LPCR_DPFD_SH);
+	mtspr(SPRN_LPCR, lpcr);
+
+	return 1;
+}
+
+static void hfscr_pmu_enable(void)
+{
+	u64 hfscr = mfspr(SPRN_HFSCR);
+	hfscr |= PPC_BIT(60);
+	mtspr(SPRN_HFSCR, hfscr);
+}
+
+static void init_pmu_power8(void)
+{
+	if (hv_mode) {
+		mtspr(SPRN_MMCRC, 0);
+		mtspr(SPRN_MMCRH, 0);
+	}
+
+	mtspr(SPRN_MMCRA, 0);
+	mtspr(SPRN_MMCR0, 0);
+	mtspr(SPRN_MMCR1, 0);
+	mtspr(SPRN_MMCR2, 0);
+	mtspr(SPRN_MMCRS, 0);
+}
+
+static int __init feat_enable_mce_power8(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->platform = "power8";
+	cur_cpu_spec->flush_tlb = __flush_tlb_power8;
+	cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p8;
+
+	return 1;
+}
+
+static int __init feat_enable_pmu_power8(struct dt_cpu_feature *f)
+{
+	hfscr_pmu_enable();
+
+	init_pmu_power8();
+	init_pmu_registers = init_pmu_power8;
+
+	cur_cpu_spec->cpu_features |= CPU_FTR_MMCRA;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_PSERIES_PERFMON_COMPAT;
+	if (pvr_version_is(PVR_POWER8E))
+		cur_cpu_spec->cpu_features |= CPU_FTR_PMAO_BUG;
+
+	cur_cpu_spec->num_pmcs		= 6;
+	cur_cpu_spec->pmc_type		= PPC_PMC_IBM;
+	cur_cpu_spec->oprofile_cpu_type	= "ppc64/power8";
+
+	return 1;
+}
+
+static void init_pmu_power9(void)
+{
+	if (hv_mode)
+		mtspr(SPRN_MMCRC, 0);
+
+	mtspr(SPRN_MMCRA, 0);
+	mtspr(SPRN_MMCR0, 0);
+	mtspr(SPRN_MMCR1, 0);
+	mtspr(SPRN_MMCR2, 0);
+}
+
+static int __init feat_enable_mce_power9(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->platform = "power9";
+	cur_cpu_spec->flush_tlb = __flush_tlb_power9;
+	cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p9;
+
+	return 1;
+}
+
+static int __init feat_enable_pmu_power9(struct dt_cpu_feature *f)
+{
+	hfscr_pmu_enable();
+
+	init_pmu_power9();
+	init_pmu_registers = init_pmu_power9;
+
+	cur_cpu_spec->cpu_features |= CPU_FTR_MMCRA;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_PSERIES_PERFMON_COMPAT;
+
+	cur_cpu_spec->num_pmcs		= 6;
+	cur_cpu_spec->pmc_type		= PPC_PMC_IBM;
+	cur_cpu_spec->oprofile_cpu_type	= "ppc64/power9";
+
+	return 1;
+}
+
+static int __init feat_enable_tm(struct dt_cpu_feature *f)
+{
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	feat_enable(f);
+	cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_HTM_NOSC;
+	return 1;
+#endif
+	return 0;
+}
+
+static int __init feat_enable_fp(struct dt_cpu_feature *f)
+{
+	feat_enable(f);
+	cur_cpu_spec->cpu_features &= ~CPU_FTR_FPU_UNAVAILABLE;
+
+	return 1;
+}
+
+static int __init feat_enable_vector(struct dt_cpu_feature *f)
+{
+#ifdef CONFIG_ALTIVEC
+	feat_enable(f);
+	cur_cpu_spec->cpu_features |= CPU_FTR_ALTIVEC;
+	cur_cpu_spec->cpu_features |= CPU_FTR_VMX_COPY;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_ALTIVEC;
+
+	return 1;
+#endif
+	return 0;
+}
+
+static int __init feat_enable_vsx(struct dt_cpu_feature *f)
+{
+#ifdef CONFIG_VSX
+	feat_enable(f);
+	cur_cpu_spec->cpu_features |= CPU_FTR_VSX;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_VSX;
+
+	return 1;
+#endif
+	return 0;
+}
+
+static int __init feat_enable_purr(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->cpu_features |= CPU_FTR_PURR | CPU_FTR_SPURR;
+
+	return 1;
+}
+
+static int __init feat_enable_ebb(struct dt_cpu_feature *f)
+{
+	/*
+	 * PPC_FEATURE2_EBB is enabled in PMU init code because it has
+	 * historically been related to the PMU facility. This may have
+	 * to be decoupled if EBB becomes more generic. For now, follow
+	 * existing convention.
+	 */
+	f->hwcap_bit_nr = -1;
+	feat_enable(f);
+
+	return 1;
+}
+
+static int __init feat_enable_dbell(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	/* P9 has an HFSCR for privileged state */
+	feat_enable(f);
+
+	cur_cpu_spec->cpu_features |= CPU_FTR_DBELL;
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr |=  LPCR_PECEDH; /* hyp doorbell wakeup */
+	mtspr(SPRN_LPCR, lpcr);
+
+	return 1;
+}
+
+static int __init feat_enable_hvi(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	/*
+	 * POWER9 XIVE interrupts including in OPAL XICS compatibility
+	 * are always delivered as hypervisor virtualization interrupts (HVI)
+	 * rather than EE.
+	 *
+	 * However LPES0 is not set here, in the chance that an EE does get
+	 * delivered to the host somehow, the EE handler would not expect it
+	 * to be delivered in LPES0 mode (e.g., using SRR[01]). This could
+	 * happen if there is a bug in interrupt controller code, or IC is
+	 * misconfigured in systemsim.
+	 */
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr |= LPCR_HVICE;	/* enable hvi interrupts */
+	lpcr |= LPCR_HEIC;	/* disable ee interrupts when MSR_HV */
+	lpcr |= LPCR_PECE_HVEE; /* hvi can wake from stop */
+	mtspr(SPRN_LPCR, lpcr);
+
+	return 1;
+}
+
+static int __init feat_enable_large_ci(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->mmu_features |= MMU_FTR_CI_LARGE_PAGE;
+
+	return 1;
+}
+
+struct dt_cpu_feature_match {
+	const char *name;
+	int (*enable)(struct dt_cpu_feature *f);
+	u64 cpu_ftr_bit_mask;
+};
+
+static struct dt_cpu_feature_match __initdata
+		dt_cpu_feature_match_table[] = {
+	{"hypervisor", feat_enable_hv, 0},
+	{"big-endian", feat_enable, 0},
+	{"little-endian", feat_enable_le, CPU_FTR_REAL_LE},
+	{"smt", feat_enable_smt, 0},
+	{"interrupt-facilities", feat_enable, 0},
+	{"timer-facilities", feat_enable, 0},
+	{"timer-facilities-v3", feat_enable, 0},
+	{"debug-facilities", feat_enable, 0},
+	{"come-from-address-register", feat_enable, CPU_FTR_CFAR},
+	{"branch-tracing", feat_enable, 0},
+	{"floating-point", feat_enable_fp, 0},
+	{"vector", feat_enable_vector, 0},
+	{"vector-scalar", feat_enable_vsx, 0},
+	{"vector-scalar-v3", feat_enable, 0},
+	{"decimal-floating-point", feat_enable, 0},
+	{"decimal-integer", feat_enable, 0},
+	{"quadword-load-store", feat_enable, 0},
+	{"vector-crypto", feat_enable, 0},
+	{"mmu-hash", feat_enable_mmu_hash, 0},
+	{"mmu-radix", feat_enable_mmu_radix, 0},
+	{"mmu-hash-v3", feat_enable_mmu_hash_v3, 0},
+	{"virtual-page-class-key-protection", feat_enable, 0},
+	{"transactional-memory", feat_enable_tm, CPU_FTR_TM},
+	{"transactional-memory-v3", feat_enable_tm, 0},
+	{"idle-nap", feat_enable_idle_nap, 0},
+	{"alignment-interrupt-dsisr", feat_enable_align_dsisr, 0},
+	{"idle-stop", feat_enable_idle_stop, 0},
+	{"machine-check-power8", feat_enable_mce_power8, 0},
+	{"performance-monitor-power8", feat_enable_pmu_power8, 0},
+	{"data-stream-control-register", feat_enable_dscr, CPU_FTR_DSCR},
+	{"event-based-branch", feat_enable_ebb, 0},
+	{"target-address-register", feat_enable, 0},
+	{"branch-history-rolling-buffer", feat_enable, 0},
+	{"control-register", feat_enable, CPU_FTR_CTRL},
+	{"processor-control-facility", feat_enable_dbell, CPU_FTR_DBELL},
+	{"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL},
+	{"processor-utilization-of-resources-register", feat_enable_purr, 0},
+	{"no-execute", feat_enable, 0},
+	{"strong-access-ordering", feat_enable, CPU_FTR_SAO},
+	{"cache-inhibited-large-page", feat_enable_large_ci, 0},
+	{"coprocessor-icswx", feat_enable, CPU_FTR_ICSWX},
+	{"hypervisor-virtualization-interrupt", feat_enable_hvi, 0},
+	{"program-priority-register", feat_enable, CPU_FTR_HAS_PPR},
+	{"wait", feat_enable, 0},
+	{"atomic-memory-operations", feat_enable, 0},
+	{"branch-v3", feat_enable, 0},
+	{"copy-paste", feat_enable, 0},
+	{"decimal-floating-point-v3", feat_enable, 0},
+	{"decimal-integer-v3", feat_enable, 0},
+	{"fixed-point-v3", feat_enable, 0},
+	{"floating-point-v3", feat_enable, 0},
+	{"group-start-register", feat_enable, 0},
+	{"pc-relative-addressing", feat_enable, 0},
+	{"machine-check-power9", feat_enable_mce_power9, 0},
+	{"performance-monitor-power9", feat_enable_pmu_power9, 0},
+	{"event-based-branch-v3", feat_enable, 0},
+	{"random-number-generator", feat_enable, 0},
+	{"system-call-vectored", feat_disable, 0},
+	{"trace-interrupt-v3", feat_enable, 0},
+	{"vector-v3", feat_enable, 0},
+	{"vector-binary128", feat_enable, 0},
+	{"vector-binary16", feat_enable, 0},
+	{"wait-v3", feat_enable, 0},
+};
+
+static bool __initdata using_dt_cpu_ftrs;
+static bool __initdata enable_unknown = true;
+
+static int __init dt_cpu_ftrs_parse(char *str)
+{
+	if (!str)
+		return 0;
+
+	if (!strcmp(str, "off"))
+		using_dt_cpu_ftrs = false;
+	else if (!strcmp(str, "known"))
+		enable_unknown = false;
+	else
+		return 1;
+
+	return 0;
+}
+early_param("dt_cpu_ftrs", dt_cpu_ftrs_parse);
+
+static void __init cpufeatures_setup_start(u32 isa)
+{
+	pr_info("setup for ISA %d\n", isa);
+
+	if (isa >= 3000) {
+		cur_cpu_spec->cpu_features |= CPU_FTR_ARCH_300;
+		cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_ARCH_3_00;
+	}
+}
+
+static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f)
+{
+	const struct dt_cpu_feature_match *m;
+	bool known = false;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dt_cpu_feature_match_table); i++) {
+		m = &dt_cpu_feature_match_table[i];
+		if (!strcmp(f->name, m->name)) {
+			known = true;
+			if (m->enable(f))
+				break;
+
+			pr_info("not enabling: %s (disabled or unsupported by kernel)\n",
+				f->name);
+			return false;
+		}
+	}
+
+	if (!known && enable_unknown) {
+		if (!feat_try_enable_unknown(f)) {
+			pr_info("not enabling: %s (unknown and unsupported by kernel)\n",
+				f->name);
+			return false;
+		}
+	}
+
+	if (m->cpu_ftr_bit_mask)
+		cur_cpu_spec->cpu_features |= m->cpu_ftr_bit_mask;
+
+	if (known)
+		pr_debug("enabling: %s\n", f->name);
+	else
+		pr_debug("enabling: %s (unknown)\n", f->name);
+
+	return true;
+}
+
+static __init void cpufeatures_cpu_quirks(void)
+{
+	int version = mfspr(SPRN_PVR);
+
+	/*
+	 * Not all quirks can be derived from the cpufeatures device tree.
+	 */
+	if ((version & 0xffffff00) == 0x004e0100)
+		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD1;
+}
+
+static void __init cpufeatures_setup_finished(void)
+{
+	cpufeatures_cpu_quirks();
+
+	if (hv_mode && !(cur_cpu_spec->cpu_features & CPU_FTR_HVMODE)) {
+		pr_err("hypervisor not present in device tree but HV mode is enabled in the CPU. Enabling.\n");
+		cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE;
+	}
+
+	system_registers.lpcr = mfspr(SPRN_LPCR);
+	system_registers.hfscr = mfspr(SPRN_HFSCR);
+	system_registers.fscr = mfspr(SPRN_FSCR);
+
+	cpufeatures_flush_tlb();
+
+	pr_info("final cpu/mmu features = 0x%016lx 0x%08x\n",
+		cur_cpu_spec->cpu_features, cur_cpu_spec->mmu_features);
+}
+
+static int __init disabled_on_cmdline(void)
+{
+	unsigned long root, chosen;
+	const char *p;
+
+	root = of_get_flat_dt_root();
+	chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
+	if (chosen == -FDT_ERR_NOTFOUND)
+		return false;
+
+	p = of_get_flat_dt_prop(chosen, "bootargs", NULL);
+	if (!p)
+		return false;
+
+	if (strstr(p, "dt_cpu_ftrs=off"))
+		return true;
+
+	return false;
+}
+
+static int __init fdt_find_cpu_features(unsigned long node, const char *uname,
+					int depth, void *data)
+{
+	if (of_flat_dt_is_compatible(node, "ibm,powerpc-cpu-features")
+	    && of_get_flat_dt_prop(node, "isa", NULL))
+		return 1;
+
+	return 0;
+}
+
+bool __init dt_cpu_ftrs_in_use(void)
+{
+	return using_dt_cpu_ftrs;
+}
+
+bool __init dt_cpu_ftrs_init(void *fdt)
+{
+	using_dt_cpu_ftrs = false;
+
+	/* Setup and verify the FDT, if it fails we just bail */
+	if (!early_init_dt_verify(fdt))
+		return false;
+
+	if (!of_scan_flat_dt(fdt_find_cpu_features, NULL))
+		return false;
+
+	if (disabled_on_cmdline())
+		return false;
+
+	cpufeatures_setup_cpu();
+
+	using_dt_cpu_ftrs = true;
+	return true;
+}
+
+static int nr_dt_cpu_features;
+static struct dt_cpu_feature *dt_cpu_features;
+
+static int __init process_cpufeatures_node(unsigned long node,
+					  const char *uname, int i)
+{
+	const __be32 *prop;
+	struct dt_cpu_feature *f;
+	int len;
+
+	f = &dt_cpu_features[i];
+	memset(f, 0, sizeof(struct dt_cpu_feature));
+
+	f->node = node;
+
+	f->name = uname;
+
+	prop = of_get_flat_dt_prop(node, "isa", &len);
+	if (!prop) {
+		pr_warn("%s: missing isa property\n", uname);
+		return 0;
+	}
+	f->isa = be32_to_cpup(prop);
+
+	prop = of_get_flat_dt_prop(node, "usable-privilege", &len);
+	if (!prop) {
+		pr_warn("%s: missing usable-privilege property", uname);
+		return 0;
+	}
+	f->usable_privilege = be32_to_cpup(prop);
+
+	prop = of_get_flat_dt_prop(node, "hv-support", &len);
+	if (prop)
+		f->hv_support = be32_to_cpup(prop);
+	else
+		f->hv_support = HV_SUPPORT_NONE;
+
+	prop = of_get_flat_dt_prop(node, "os-support", &len);
+	if (prop)
+		f->os_support = be32_to_cpup(prop);
+	else
+		f->os_support = OS_SUPPORT_NONE;
+
+	prop = of_get_flat_dt_prop(node, "hfscr-bit-nr", &len);
+	if (prop)
+		f->hfscr_bit_nr = be32_to_cpup(prop);
+	else
+		f->hfscr_bit_nr = -1;
+	prop = of_get_flat_dt_prop(node, "fscr-bit-nr", &len);
+	if (prop)
+		f->fscr_bit_nr = be32_to_cpup(prop);
+	else
+		f->fscr_bit_nr = -1;
+	prop = of_get_flat_dt_prop(node, "hwcap-bit-nr", &len);
+	if (prop)
+		f->hwcap_bit_nr = be32_to_cpup(prop);
+	else
+		f->hwcap_bit_nr = -1;
+
+	if (f->usable_privilege & USABLE_HV) {
+		if (!(mfmsr() & MSR_HV)) {
+			pr_warn("%s: HV feature passed to guest\n", uname);
+			return 0;
+		}
+
+		if (f->hv_support == HV_SUPPORT_NONE && f->hfscr_bit_nr != -1) {
+			pr_warn("%s: unwanted hfscr_bit_nr\n", uname);
+			return 0;
+		}
+
+		if (f->hv_support == HV_SUPPORT_HFSCR) {
+			if (f->hfscr_bit_nr == -1) {
+				pr_warn("%s: missing hfscr_bit_nr\n", uname);
+				return 0;
+			}
+		}
+	} else {
+		if (f->hv_support != HV_SUPPORT_NONE || f->hfscr_bit_nr != -1) {
+			pr_warn("%s: unwanted hv_support/hfscr_bit_nr\n", uname);
+			return 0;
+		}
+	}
+
+	if (f->usable_privilege & USABLE_OS) {
+		if (f->os_support == OS_SUPPORT_NONE && f->fscr_bit_nr != -1) {
+			pr_warn("%s: unwanted fscr_bit_nr\n", uname);
+			return 0;
+		}
+
+		if (f->os_support == OS_SUPPORT_FSCR) {
+			if (f->fscr_bit_nr == -1) {
+				pr_warn("%s: missing fscr_bit_nr\n", uname);
+				return 0;
+			}
+		}
+	} else {
+		if (f->os_support != OS_SUPPORT_NONE || f->fscr_bit_nr != -1) {
+			pr_warn("%s: unwanted os_support/fscr_bit_nr\n", uname);
+			return 0;
+		}
+	}
+
+	if (!(f->usable_privilege & USABLE_PR)) {
+		if (f->hwcap_bit_nr != -1) {
+			pr_warn("%s: unwanted hwcap_bit_nr\n", uname);
+			return 0;
+		}
+	}
+
+	/* Do all the independent features in the first pass */
+	if (!of_get_flat_dt_prop(node, "dependencies", &len)) {
+		if (cpufeatures_process_feature(f))
+			f->enabled = 1;
+		else
+			f->disabled = 1;
+	}
+
+	return 0;
+}
+
+static void __init cpufeatures_deps_enable(struct dt_cpu_feature *f)
+{
+	const __be32 *prop;
+	int len;
+	int nr_deps;
+	int i;
+
+	if (f->enabled || f->disabled)
+		return;
+
+	prop = of_get_flat_dt_prop(f->node, "dependencies", &len);
+	if (!prop) {
+		pr_warn("%s: missing dependencies property", f->name);
+		return;
+	}
+
+	nr_deps = len / sizeof(int);
+
+	for (i = 0; i < nr_deps; i++) {
+		unsigned long phandle = be32_to_cpu(prop[i]);
+		int j;
+
+		for (j = 0; j < nr_dt_cpu_features; j++) {
+			struct dt_cpu_feature *d = &dt_cpu_features[j];
+
+			if (of_get_flat_dt_phandle(d->node) == phandle) {
+				cpufeatures_deps_enable(d);
+				if (d->disabled) {
+					f->disabled = 1;
+					return;
+				}
+			}
+		}
+	}
+
+	if (cpufeatures_process_feature(f))
+		f->enabled = 1;
+	else
+		f->disabled = 1;
+}
+
+static int __init scan_cpufeatures_subnodes(unsigned long node,
+					  const char *uname,
+					  void *data)
+{
+	int *count = data;
+
+	process_cpufeatures_node(node, uname, *count);
+
+	(*count)++;
+
+	return 0;
+}
+
+static int __init count_cpufeatures_subnodes(unsigned long node,
+					  const char *uname,
+					  void *data)
+{
+	int *count = data;
+
+	(*count)++;
+
+	return 0;
+}
+
+static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char
+					    *uname, int depth, void *data)
+{
+	const __be32 *prop;
+	int count, i;
+	u32 isa;
+
+	/* We are scanning "ibm,powerpc-cpu-features" nodes only */
+	if (!of_flat_dt_is_compatible(node, "ibm,powerpc-cpu-features"))
+		return 0;
+
+	prop = of_get_flat_dt_prop(node, "isa", NULL);
+	if (!prop)
+		/* We checked before, "can't happen" */
+		return 0;
+
+	isa = be32_to_cpup(prop);
+
+	/* Count and allocate space for cpu features */
+	of_scan_flat_dt_subnodes(node, count_cpufeatures_subnodes,
+						&nr_dt_cpu_features);
+	dt_cpu_features = __va(
+		memblock_alloc(sizeof(struct dt_cpu_feature)*
+				nr_dt_cpu_features, PAGE_SIZE));
+
+	cpufeatures_setup_start(isa);
+
+	/* Scan nodes into dt_cpu_features and enable those without deps  */
+	count = 0;
+	of_scan_flat_dt_subnodes(node, scan_cpufeatures_subnodes, &count);
+
+	/* Recursive enable remaining features with dependencies */
+	for (i = 0; i < nr_dt_cpu_features; i++) {
+		struct dt_cpu_feature *f = &dt_cpu_features[i];
+
+		cpufeatures_deps_enable(f);
+	}
+
+	prop = of_get_flat_dt_prop(node, "display-name", NULL);
+	if (prop && strlen((char *)prop) != 0) {
+		strlcpy(dt_cpu_name, (char *)prop, sizeof(dt_cpu_name));
+		cur_cpu_spec->cpu_name = dt_cpu_name;
+	}
+
+	cpufeatures_setup_finished();
+
+	memblock_free(__pa(dt_cpu_features),
+			sizeof(struct dt_cpu_feature)*nr_dt_cpu_features);
+
+	return 0;
+}
+
+void __init dt_cpu_ftrs_scan(void)
+{
+	if (!using_dt_cpu_ftrs)
+		return;
+
+	of_scan_flat_dt(dt_cpu_ftrs_scan_callback, NULL);
+}
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 45b453e4d0c8..acd8ca76233e 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -735,8 +735,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	andis.	r15,r14,(DBSR_IC|DBSR_BT)@h
 	beq+	1f
 
+#ifdef CONFIG_RELOCATABLE
+	ld	r15,PACATOC(r13)
+	ld	r14,interrupt_base_book3e@got(r15)
+	ld	r15,__end_interrupts@got(r15)
+#else
 	LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
 	LOAD_REG_IMMEDIATE(r15,__end_interrupts)
+#endif
 	cmpld	cr0,r10,r14
 	cmpld	cr1,r10,r15
 	blt+	cr0,1f
@@ -799,8 +805,14 @@ kernel_dbg_exc:
 	andis.	r15,r14,(DBSR_IC|DBSR_BT)@h
 	beq+	1f
 
+#ifdef CONFIG_RELOCATABLE
+	ld	r15,PACATOC(r13)
+	ld	r14,interrupt_base_book3e@got(r15)
+	ld	r15,__end_interrupts@got(r15)
+#else
 	LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
 	LOAD_REG_IMMEDIATE(r15,__end_interrupts)
+#endif
 	cmpld	cr0,r10,r14
 	cmpld	cr1,r10,r15
 	blt+	cr0,1f
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index a9312b52fe6f..b886795060fd 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -391,9 +391,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
 	 */
 	BEGIN_FTR_SECTION
 	rlwinm.	r11,r12,47-31,30,31
-	beq-	4f
-	BRANCH_TO_COMMON(r10, machine_check_idle_common)
-4:
+	bne	machine_check_idle_common
 	END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
 #endif
 
@@ -1413,10 +1411,8 @@ USE_TEXT_SECTION()
 	.balign	IFETCH_ALIGN_BYTES
 do_hash_page:
 #ifdef CONFIG_PPC_STD_MMU_64
-	andis.	r0,r4,0xa410		/* weird error? */
+	andis.	r0,r4,0xa450		/* weird error? */
 	bne-	handle_page_fault	/* if not, try to insert a HPTE */
-	andis.  r0,r4,DSISR_DABRMATCH@h
-	bne-    handle_dabr_fault
 	CURRENT_THREAD_INFO(r11, r1)
 	lwz	r0,TI_PREEMPT(r11)	/* If we're in an "NMI" */
 	andis.	r0,r0,NMI_MASK@h	/* (i.e. an irq when soft-disabled) */
@@ -1440,11 +1436,16 @@ do_hash_page:
 
 	/* Error */
 	blt-	13f
+
+	/* Reload DSISR into r4 for the DABR check below */
+	ld      r4,_DSISR(r1)
 #endif /* CONFIG_PPC_STD_MMU_64 */
 
 /* Here we have a page fault that hash_page can't handle. */
 handle_page_fault:
-11:	ld	r4,_DAR(r1)
+11:	andis.  r0,r4,DSISR_DABRMATCH@h
+	bne-    handle_dabr_fault
+	ld	r4,_DAR(r1)
 	ld	r5,_DSISR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_page_fault
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 07d4e0ad60db..4898d676dcae 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -416,7 +416,7 @@ power9_dd1_recover_paca:
 	 * which needs to be restored from the stack.
 	 */
 	li	r3, 1
-	stb	r0,PACA_NAPSTATELOST(r13)
+	stb	r3,PACA_NAPSTATELOST(r13)
 	blr
 
 /*
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 160ae0fa7d0d..01addfb0ed0a 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -43,6 +43,12 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
 struct kretprobe_blackpoint kretprobe_blacklist[] = {{NULL, NULL}};
 
+int is_current_kprobe_addr(unsigned long addr)
+{
+	struct kprobe *p = kprobe_running();
+	return (p && (unsigned long)p->addr == addr) ? 1 : 0;
+}
+
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
 	return  (addr >= (unsigned long)__kprobes_text_start &&
@@ -305,16 +311,17 @@ int kprobe_handler(struct pt_regs *regs)
 			save_previous_kprobe(kcb);
 			set_current_kprobe(p, regs, kcb);
 			kprobes_inc_nmissed_count(p);
-			prepare_singlestep(p, regs);
 			kcb->kprobe_status = KPROBE_REENTER;
 			if (p->ainsn.boostable >= 0) {
 				ret = try_to_emulate(p, regs);
 
 				if (ret > 0) {
 					restore_previous_kprobe(kcb);
+					preempt_enable_no_resched();
 					return 1;
 				}
 			}
+			prepare_singlestep(p, regs);
 			return 1;
 		} else {
 			if (*addr != BREAKPOINT_INSTRUCTION) {
@@ -616,6 +623,15 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
 #endif
 
+	/*
+	 * jprobes use jprobe_return() which skips the normal return
+	 * path of the function, and this messes up the accounting of the
+	 * function graph tracer.
+	 *
+	 * Pause function graph tracing while performing the jprobe function.
+	 */
+	pause_graph_tracing();
+
 	return 1;
 }
 NOKPROBE_SYMBOL(setjmp_pre_handler);
@@ -641,6 +657,8 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	 * saved regs...
 	 */
 	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
+	/* It's OK to start function graph tracing again */
+	unpause_graph_tracing();
 	preempt_enable_no_resched();
 	return 1;
 }
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index d645da302bf2..2ad725ef4368 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -864,6 +864,25 @@ static void tm_reclaim_thread(struct thread_struct *thr,
 	if (!MSR_TM_SUSPENDED(mfmsr()))
 		return;
 
+	/*
+	 * If we are in a transaction and FP is off then we can't have
+	 * used FP inside that transaction. Hence the checkpointed
+	 * state is the same as the live state. We need to copy the
+	 * live state to the checkpointed state so that when the
+	 * transaction is restored, the checkpointed state is correct
+	 * and the aborted transaction sees the correct state. We use
+	 * ckpt_regs.msr here as that's what tm_reclaim will use to
+	 * determine if it's going to write the checkpointed state or
+	 * not. So either this will write the checkpointed registers,
+	 * or reclaim will. Similarly for VMX.
+	 */
+	if ((thr->ckpt_regs.msr & MSR_FP) == 0)
+		memcpy(&thr->ckfp_state, &thr->fp_state,
+		       sizeof(struct thread_fp_state));
+	if ((thr->ckpt_regs.msr & MSR_VEC) == 0)
+		memcpy(&thr->ckvr_state, &thr->vr_state,
+		       sizeof(struct thread_vr_state));
+
 	giveup_all(container_of(thr, struct task_struct, thread));
 
 	tm_reclaim(thr, thr->ckpt_regs.msr, cause);
@@ -1647,6 +1666,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 #ifdef CONFIG_VSX
 	current->thread.used_vsr = 0;
 #endif
+	current->thread.load_fp = 0;
 	memset(&current->thread.fp_state, 0, sizeof(current->thread.fp_state));
 	current->thread.fp_save_area = NULL;
 #ifdef CONFIG_ALTIVEC
@@ -1655,6 +1675,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 	current->thread.vr_save_area = NULL;
 	current->thread.vrsave = 0;
 	current->thread.used_vr = 0;
+	current->thread.load_vec = 0;
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_SPE
 	memset(current->thread.evr, 0, sizeof(current->thread.evr));
@@ -1666,6 +1687,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 	current->thread.tm_tfhar = 0;
 	current->thread.tm_texasr = 0;
 	current->thread.tm_tfiar = 0;
+	current->thread.load_tm = 0;
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 }
 EXPORT_SYMBOL(start_thread);
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index d2f0afeae5a0..f83056297441 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -57,6 +57,7 @@
 #include <asm/fadump.h>
 #include <asm/epapr_hcalls.h>
 #include <asm/firmware.h>
+#include <asm/dt_cpu_ftrs.h>
 
 #include <mm/mmu_decl.h>
 
@@ -160,7 +161,9 @@ static struct ibm_pa_feature {
 	{ .pabyte = 0,  .pabit = 3, .cpu_features  = CPU_FTR_CTRL },
 	{ .pabyte = 0,  .pabit = 6, .cpu_features  = CPU_FTR_NOEXECUTE },
 	{ .pabyte = 1,  .pabit = 2, .mmu_features  = MMU_FTR_CI_LARGE_PAGE },
+#ifdef CONFIG_PPC_RADIX_MMU
 	{ .pabyte = 40, .pabit = 0, .mmu_features  = MMU_FTR_TYPE_RADIX },
+#endif
 	{ .pabyte = 1,  .pabit = 1, .invert = 1, .cpu_features = CPU_FTR_NODSISRALIGN },
 	{ .pabyte = 5,  .pabit = 0, .cpu_features  = CPU_FTR_REAL_LE,
 				    .cpu_user_ftrs = PPC_FEATURE_TRUE_LE },
@@ -375,23 +378,31 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 	 * A POWER6 partition in "POWER6 architected" mode
 	 * uses the 0x0f000002 PVR value; in POWER5+ mode
 	 * it uses 0x0f000001.
+	 *
+	 * If we're using device tree CPU feature discovery then we don't
+	 * support the cpu-version property, and it's the responsibility of the
+	 * firmware/hypervisor to provide the correct feature set for the
+	 * architecture level via the ibm,powerpc-cpu-features binding.
 	 */
-	prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
-	if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000)
-		identify_cpu(0, be32_to_cpup(prop));
+	if (!dt_cpu_ftrs_in_use()) {
+		prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
+		if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000)
+			identify_cpu(0, be32_to_cpup(prop));
 
-	identical_pvr_fixup(node);
+		check_cpu_feature_properties(node);
+		check_cpu_pa_features(node);
+	}
 
-	check_cpu_feature_properties(node);
-	check_cpu_pa_features(node);
+	identical_pvr_fixup(node);
 	init_mmu_slb_size(node);
 
 #ifdef CONFIG_PPC64
-	if (nthreads > 1)
-		cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
-	else
+	if (nthreads == 1)
 		cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT;
+	else if (!dt_cpu_ftrs_in_use())
+		cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
 #endif
+
 	return 0;
 }
 
@@ -721,6 +732,8 @@ void __init early_init_devtree(void *params)
 
 	DBG("Scanning CPUs ...\n");
 
+	dt_cpu_ftrs_scan();
+
 	/* Retrieve CPU related informations from the flat tree
 	 * (altivec support, boot CPU ID, ...)
 	 */
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 69e077180db6..857129acf960 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -261,7 +261,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	seq_printf(m, "processor\t: %lu\n", cpu_id);
 	seq_printf(m, "cpu\t\t: ");
 
-	if (cur_cpu_spec->pvr_mask)
+	if (cur_cpu_spec->pvr_mask && cur_cpu_spec->cpu_name)
 		seq_printf(m, "%s", cur_cpu_spec->cpu_name);
 	else
 		seq_printf(m, "unknown (%08x)", pvr);
@@ -928,7 +928,7 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_PPC_MM_SLICES
 #ifdef CONFIG_PPC64
-	init_mm.context.addr_limit = TASK_SIZE_128TB;
+	init_mm.context.addr_limit = DEFAULT_MAP_WINDOW_USER64;
 #else
 #error	"context.addr_limit not initialized."
 #endif
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 0d4dcaeaafcb..4640f6d64f8b 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -49,6 +49,7 @@
 #include <asm/paca.h>
 #include <asm/time.h>
 #include <asm/cputable.h>
+#include <asm/dt_cpu_ftrs.h>
 #include <asm/sections.h>
 #include <asm/btext.h>
 #include <asm/nvram.h>
@@ -274,8 +275,10 @@ void __init early_setup(unsigned long dt_ptr)
 
 	/* -------- printk is _NOT_ safe to use here ! ------- */
 
-	/* Identify CPU type */
-	identify_cpu(0, mfspr(SPRN_PVR));
+	/* Try new device tree based feature discovery ... */
+	if (!dt_cpu_ftrs_init(__va(dt_ptr)))
+		/* Otherwise use the old style CPU table */
+		identify_cpu(0, mfspr(SPRN_PVR));
 
 	/* Assume we're on cpu 0 for now. Don't write to the paca yet! */
 	initialise_paca(&boot_paca, 0);
@@ -541,6 +544,9 @@ void __init initialize_cache_info(void)
 	dcache_bsize = ppc64_caches.l1d.block_size;
 	icache_bsize = ppc64_caches.l1i.block_size;
 
+	cur_cpu_spec->dcache_bsize = dcache_bsize;
+	cur_cpu_spec->icache_bsize = icache_bsize;
+
 	DBG(" <- initialize_cache_info()\n");
 }
 
@@ -610,6 +616,24 @@ void __init exc_lvl_early_init(void)
 #endif
 
 /*
+ * Emergency stacks are used for a range of things, from asynchronous
+ * NMIs (system reset, machine check) to synchronous, process context.
+ * We set preempt_count to zero, even though that isn't necessarily correct. To
+ * get the right value we'd need to copy it from the previous thread_info, but
+ * doing that might fault causing more problems.
+ * TODO: what to do with accounting?
+ */
+static void emerg_stack_init_thread_info(struct thread_info *ti, int cpu)
+{
+	ti->task = NULL;
+	ti->cpu = cpu;
+	ti->preempt_count = 0;
+	ti->local_flags = 0;
+	ti->flags = 0;
+	klp_init_thread_info(ti);
+}
+
+/*
  * Stack space used when we detect a bad kernel stack pointer, and
  * early in SMP boots before relocation is enabled. Exclusive emergency
  * stack for machine checks.
@@ -627,24 +651,31 @@ void __init emergency_stack_init(void)
 	 * Since we use these as temporary stacks during secondary CPU
 	 * bringup, we need to get at them in real mode. This means they
 	 * must also be within the RMO region.
+	 *
+	 * The IRQ stacks allocated elsewhere in this file are zeroed and
+	 * initialized in kernel/irq.c. These are initialized here in order
+	 * to have emergency stacks available as early as possible.
 	 */
 	limit = min(safe_stack_limit(), ppc64_rma_size);
 
 	for_each_possible_cpu(i) {
 		struct thread_info *ti;
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
-		klp_init_thread_info(ti);
+		memset(ti, 0, THREAD_SIZE);
+		emerg_stack_init_thread_info(ti, i);
 		paca[i].emergency_sp = (void *)ti + THREAD_SIZE;
 
 #ifdef CONFIG_PPC_BOOK3S_64
 		/* emergency stack for NMI exception handling. */
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
-		klp_init_thread_info(ti);
+		memset(ti, 0, THREAD_SIZE);
+		emerg_stack_init_thread_info(ti, i);
 		paca[i].nmi_emergency_sp = (void *)ti + THREAD_SIZE;
 
 		/* emergency stack for machine check exception handling. */
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
-		klp_init_thread_info(ti);
+		memset(ti, 0, THREAD_SIZE);
+		emerg_stack_init_thread_info(ti, i);
 		paca[i].mc_emergency_sp = (void *)ti + THREAD_SIZE;
 #endif
 	}
@@ -655,7 +686,7 @@ void __init emergency_stack_init(void)
 
 static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 {
-	return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align,
+	return __alloc_bootmem_node(NODE_DATA(early_cpu_to_node(cpu)), size, align,
 				    __pa(MAX_DMA_ADDRESS));
 }
 
@@ -666,7 +697,7 @@ static void __init pcpu_fc_free(void *ptr, size_t size)
 
 static int pcpu_cpu_distance(unsigned int from, unsigned int to)
 {
-	if (cpu_to_node(from) == cpu_to_node(to))
+	if (early_cpu_to_node(from) == early_cpu_to_node(to))
 		return LOCAL_DISTANCE;
 	else
 		return REMOTE_DISTANCE;
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index df2a41647d8e..1069f74fca47 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -97,7 +97,7 @@ int smp_generic_cpu_bootable(unsigned int nr)
 	/* Special case - we inhibit secondary thread startup
 	 * during boot if the user requests it.
 	 */
-	if (system_state == SYSTEM_BOOTING && cpu_has_feature(CPU_FTR_SMT)) {
+	if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) {
 		if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
 			return 0;
 		if (smt_enabled_at_boot
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index 7c933a99f5d5..c98e90b4ea7b 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -45,10 +45,14 @@ _GLOBAL(ftrace_caller)
 	stdu	r1,-SWITCH_FRAME_SIZE(r1)
 
 	/* Save all gprs to pt_regs */
-	SAVE_8GPRS(0,r1)
-	SAVE_8GPRS(8,r1)
-	SAVE_8GPRS(16,r1)
-	SAVE_8GPRS(24,r1)
+	SAVE_GPR(0, r1)
+	SAVE_10GPRS(2, r1)
+	SAVE_10GPRS(12, r1)
+	SAVE_10GPRS(22, r1)
+
+	/* Save previous stack pointer (r1) */
+	addi	r8, r1, SWITCH_FRAME_SIZE
+	std	r8, GPR1(r1)
 
 	/* Load special regs for save below */
 	mfmsr   r8
@@ -95,18 +99,44 @@ ftrace_call:
 	bl	ftrace_stub
 	nop
 
-	/* Load ctr with the possibly modified NIP */
-	ld	r3, _NIP(r1)
-	mtctr	r3
+	/* Load the possibly modified NIP */
+	ld	r15, _NIP(r1)
+
 #ifdef CONFIG_LIVEPATCH
-	cmpd	r14,r3		/* has NIP been altered? */
+	cmpd	r14, r15	/* has NIP been altered? */
+#endif
+
+#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE)
+	/* NIP has not been altered, skip over further checks */
+	beq	1f
+
+	/* Check if there is an active kprobe on us */
+	subi	r3, r14, 4
+	bl	is_current_kprobe_addr
+	nop
+
+	/*
+	 * If r3 == 1, then this is a kprobe/jprobe.
+	 * else, this is livepatched function.
+	 *
+	 * The conditional branch for livepatch_handler below will use the
+	 * result of this comparison. For kprobe/jprobe, we just need to branch to
+	 * the new NIP, not call livepatch_handler. The branch below is bne, so we
+	 * want CR0[EQ] to be true if this is a kprobe/jprobe. Which means we want
+	 * CR0[EQ] = (r3 == 1).
+	 */
+	cmpdi	r3, 1
+1:
 #endif
 
+	/* Load CTR with the possibly modified NIP */
+	mtctr	r15
+
 	/* Restore gprs */
-	REST_8GPRS(0,r1)
-	REST_8GPRS(8,r1)
-	REST_8GPRS(16,r1)
-	REST_8GPRS(24,r1)
+	REST_GPR(0,r1)
+	REST_10GPRS(2,r1)
+	REST_10GPRS(12,r1)
+	REST_10GPRS(22,r1)
 
 	/* Restore possibly modified LR */
 	ld	r0, _LINK(r1)
@@ -119,7 +149,10 @@ ftrace_call:
 	addi r1, r1, SWITCH_FRAME_SIZE
 
 #ifdef CONFIG_LIVEPATCH
-        /* Based on the cmpd above, if the NIP was altered handle livepatch */
+        /*
+	 * Based on the cmpd or cmpdi above, if the NIP was altered and we're
+	 * not on a kprobe/jprobe, then handle livepatch.
+	 */
 	bne-	livepatch_handler
 #endif