Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm

Pull ARM updates from Russell King:
 "The major items included in here are:

   - MCPM, multi-cluster power management, part of the infrastructure
     required for ARMs big.LITTLE support.

   - A rework of the ARM KVM code to allow re-use by ARM64.

   - Error handling cleanups of the IS_ERR_OR_NULL() madness and fixes
     of that stuff for arch/arm

   - Preparatory patches for Cortex-M3 support from Uwe Kleine-König.

  There is also a set of three patches in here from Hugh/Catalin to
  address freeing of inappropriate page tables on LPAE.  You already
  have these from akpm, but they were already part of my tree at the
  time he sent them, so unfortunately they'll end up with duplicate
  commits"

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (77 commits)
  ARM: EXYNOS: remove unnecessary use of IS_ERR_VALUE()
  ARM: IMX: remove unnecessary use of IS_ERR_VALUE()
  ARM: OMAP: use consistent error checking
  ARM: cleanup: OMAP hwmod error checking
  ARM: 7709/1: mcpm: Add explicit AFLAGS to support v6/v7 multiplatform kernels
  ARM: 7700/2: Make cpu_init() notrace
  ARM: 7702/1: Set the page table freeing ceiling to TASK_SIZE
  ARM: 7701/1: mm: Allow arch code to control the user page table ceiling
  ARM: 7703/1: Disable preemption in broadcast_tlb*_a15_erratum()
  ARM: mcpm: provide an interface to set the SMP ops at run time
  ARM: mcpm: generic SMP secondary bringup and hotplug support
  ARM: mcpm_head.S: vlock-based first man election
  ARM: mcpm: Add baremetal voting mutexes
  ARM: mcpm: introduce helpers for platform coherency exit/setup
  ARM: mcpm: introduce the CPU/cluster power API
  ARM: multi-cluster PM: secondary kernel entry code
  ARM: cacheflush: add synchronization helpers for mixed cache state accesses
  ARM: cpu hotplug: remove majority of cache flushing from platforms
  ARM: smp: flush L1 cache in cpu_die()
  ARM: tegra: remove tegra specific cpu_disable()
  ...

15 files changed, 594 insertions, 48 deletions

diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index c79f61faa3a5..da1c77d39327 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -243,6 +243,29 @@ typedef struct {
 
 #define ATOMIC64_INIT(i) { (i) }
 
+#ifdef CONFIG_ARM_LPAE
+static inline u64 atomic64_read(const atomic64_t *v)
+{
+	u64 result;
+
+	__asm__ __volatile__("@ atomic64_read\n"
+"	ldrd	%0, %H0, [%1]"
+	: "=&r" (result)
+	: "r" (&v->counter), "Qo" (v->counter)
+	);
+
+	return result;
+}
+
+static inline void atomic64_set(atomic64_t *v, u64 i)
+{
+	__asm__ __volatile__("@ atomic64_set\n"
+"	strd	%2, %H2, [%1]"
+	: "=Qo" (v->counter)
+	: "r" (&v->counter), "r" (i)
+	);
+}
+#else
 static inline u64 atomic64_read(const atomic64_t *v)
 {
 	u64 result;
@@ -269,6 +292,7 @@ static inline void atomic64_set(atomic64_t *v, u64 i)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 }
+#endif
 
 static inline void atomic64_add(u64 i, atomic64_t *v)
 {
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index e1489c54cd12..bff71388e72a 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -363,4 +363,79 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
 		flush_cache_all();
 }
 
+/*
+ * Memory synchronization helpers for mixed cached vs non cached accesses.
+ *
+ * Some synchronization algorithms have to set states in memory with the
+ * cache enabled or disabled depending on the code path.  It is crucial
+ * to always ensure proper cache maintenance to update main memory right
+ * away in that case.
+ *
+ * Any cached write must be followed by a cache clean operation.
+ * Any cached read must be preceded by a cache invalidate operation.
+ * Yet, in the read case, a cache flush i.e. atomic clean+invalidate
+ * operation is needed to avoid discarding possible concurrent writes to the
+ * accessed memory.
+ *
+ * Also, in order to prevent a cached writer from interfering with an
+ * adjacent non-cached writer, each state variable must be located to
+ * a separate cache line.
+ */
+
+/*
+ * This needs to be >= the max cache writeback size of all
+ * supported platforms included in the current kernel configuration.
+ * This is used to align state variables to their own cache lines.
+ */
+#define __CACHE_WRITEBACK_ORDER 6  /* guessed from existing platforms */
+#define __CACHE_WRITEBACK_GRANULE (1 << __CACHE_WRITEBACK_ORDER)
+
+/*
+ * There is no __cpuc_clean_dcache_area but we use it anyway for
+ * code intent clarity, and alias it to __cpuc_flush_dcache_area.
+ */
+#define __cpuc_clean_dcache_area __cpuc_flush_dcache_area
+
+/*
+ * Ensure preceding writes to *p by this CPU are visible to
+ * subsequent reads by other CPUs:
+ */
+static inline void __sync_cache_range_w(volatile void *p, size_t size)
+{
+	char *_p = (char *)p;
+
+	__cpuc_clean_dcache_area(_p, size);
+	outer_clean_range(__pa(_p), __pa(_p + size));
+}
+
+/*
+ * Ensure preceding writes to *p by other CPUs are visible to
+ * subsequent reads by this CPU.  We must be careful not to
+ * discard data simultaneously written by another CPU, hence the
+ * usage of flush rather than invalidate operations.
+ */
+static inline void __sync_cache_range_r(volatile void *p, size_t size)
+{
+	char *_p = (char *)p;
+
+#ifdef CONFIG_OUTER_CACHE
+	if (outer_cache.flush_range) {
+		/*
+		 * Ensure dirty data migrated from other CPUs into our cache
+		 * are cleaned out safely before the outer cache is cleaned:
+		 */
+		__cpuc_clean_dcache_area(_p, size);
+
+		/* Clean and invalidate stale data for *p from outer ... */
+		outer_flush_range(__pa(_p), __pa(_p + size));
+	}
+#endif
+
+	/* ... and inner cache: */
+	__cpuc_flush_dcache_area(_p, size);
+}
+
+#define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr))
+#define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr))
+
 #endif
diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
index 5ef4d8015a60..1f3262e99d81 100644
--- a/arch/arm/include/asm/cp15.h
+++ b/arch/arm/include/asm/cp15.h
@@ -42,6 +42,8 @@
 #define vectors_high()	(0)
 #endif
 
+#ifdef CONFIG_CPU_CP15
+
 extern unsigned long cr_no_alignment;	/* defined in entry-armv.S */
 extern unsigned long cr_alignment;	/* defined in entry-armv.S */
 
@@ -82,6 +84,18 @@ static inline void set_copro_access(unsigned int val)
 	isb();
 }
 
-#endif
+#else /* ifdef CONFIG_CPU_CP15 */
+
+/*
+ * cr_alignment and cr_no_alignment are tightly coupled to cp15 (at least in the
+ * minds of the developers). Yielding 0 for machines without a cp15 (and making
+ * it read-only) is fine for most cases and saves quite some #ifdeffery.
+ */
+#define cr_no_alignment	UL(0)
+#define cr_alignment	UL(0)
+
+#endif /* ifdef CONFIG_CPU_CP15 / else */
+
+#endif /* ifndef __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index ad41ec2471e8..7652712d1d14 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -38,6 +38,24 @@
 #define MPIDR_AFFINITY_LEVEL(mpidr, level) \
 	((mpidr >> (MPIDR_LEVEL_BITS * level)) & MPIDR_LEVEL_MASK)
 
+#define ARM_CPU_IMP_ARM			0x41
+#define ARM_CPU_IMP_INTEL		0x69
+
+#define ARM_CPU_PART_ARM1136		0xB360
+#define ARM_CPU_PART_ARM1156		0xB560
+#define ARM_CPU_PART_ARM1176		0xB760
+#define ARM_CPU_PART_ARM11MPCORE	0xB020
+#define ARM_CPU_PART_CORTEX_A8		0xC080
+#define ARM_CPU_PART_CORTEX_A9		0xC090
+#define ARM_CPU_PART_CORTEX_A5		0xC050
+#define ARM_CPU_PART_CORTEX_A15		0xC0F0
+#define ARM_CPU_PART_CORTEX_A7		0xC070
+
+#define ARM_CPU_XSCALE_ARCH_MASK	0xe000
+#define ARM_CPU_XSCALE_ARCH_V1		0x2000
+#define ARM_CPU_XSCALE_ARCH_V2		0x4000
+#define ARM_CPU_XSCALE_ARCH_V3		0x6000
+
 extern unsigned int processor_id;
 
 #ifdef CONFIG_CPU_CP15
@@ -50,6 +68,7 @@ extern unsigned int processor_id;
 		    : "cc");						\
 		__val;							\
 	})
+
 #define read_cpuid_ext(ext_reg)						\
 	({								\
 		unsigned int __val;					\
@@ -59,29 +78,24 @@ extern unsigned int processor_id;
 		    : "cc");						\
 		__val;							\
 	})
-#else
-#define read_cpuid(reg) (processor_id)
-#define read_cpuid_ext(reg) 0
-#endif
 
-#define ARM_CPU_IMP_ARM			0x41
-#define ARM_CPU_IMP_INTEL		0x69
+#else /* ifdef CONFIG_CPU_CP15 */
 
-#define ARM_CPU_PART_ARM1136		0xB360
-#define ARM_CPU_PART_ARM1156		0xB560
-#define ARM_CPU_PART_ARM1176		0xB760
-#define ARM_CPU_PART_ARM11MPCORE	0xB020
-#define ARM_CPU_PART_CORTEX_A8		0xC080
-#define ARM_CPU_PART_CORTEX_A9		0xC090
-#define ARM_CPU_PART_CORTEX_A5		0xC050
-#define ARM_CPU_PART_CORTEX_A15		0xC0F0
-#define ARM_CPU_PART_CORTEX_A7		0xC070
+/*
+ * read_cpuid and read_cpuid_ext should only ever be called on machines that
+ * have cp15 so warn on other usages.
+ */
+#define read_cpuid(reg)							\
+	({								\
+		WARN_ON_ONCE(1);					\
+		0;							\
+	})
 
-#define ARM_CPU_XSCALE_ARCH_MASK	0xe000
-#define ARM_CPU_XSCALE_ARCH_V1		0x2000
-#define ARM_CPU_XSCALE_ARCH_V2		0x4000
-#define ARM_CPU_XSCALE_ARCH_V3		0x6000
+#define read_cpuid_ext(reg) read_cpuid(reg)
+
+#endif /* ifdef CONFIG_CPU_CP15 / else */
 
+#ifdef CONFIG_CPU_CP15
 /*
  * The CPU ID never changes at run time, so we might as well tell the
  * compiler that it's constant.  Use this function to read the CPU ID
@@ -92,6 +106,15 @@ static inline unsigned int __attribute_const__ read_cpuid_id(void)
 	return read_cpuid(CPUID_ID);
 }
 
+#else /* ifdef CONFIG_CPU_CP15 */
+
+static inline unsigned int __attribute_const__ read_cpuid_id(void)
+{
+	return processor_id;
+}
+
+#endif /* ifdef CONFIG_CPU_CP15 / else */
+
 static inline unsigned int __attribute_const__ read_cpuid_implementor(void)
 {
 	return (read_cpuid_id() & 0xFF000000) >> 24;
diff --git a/arch/arm/include/asm/glue-df.h b/arch/arm/include/asm/glue-df.h
index 8cacbcda76da..b6e9f2c108b5 100644
--- a/arch/arm/include/asm/glue-df.h
+++ b/arch/arm/include/asm/glue-df.h
@@ -18,12 +18,12 @@
  *	================
  *
  *	We have the following to choose from:
- *	  arm6          - ARM6 style
  *	  arm7		- ARM7 style
  *	  v4_early	- ARMv4 without Thumb early abort handler
  *	  v4t_late	- ARMv4 with Thumb late abort handler
  *	  v4t_early	- ARMv4 with Thumb early abort handler
- *	  v5tej_early	- ARMv5 with Thumb and Java early abort handler
+ *	  v5t_early	- ARMv5 with Thumb early abort handler
+ *	  v5tj_early	- ARMv5 with Thumb and Java early abort handler
  *	  xscale	- ARMv5 with Thumb with Xscale extensions
  *	  v6_early	- ARMv6 generic early abort handler
  *	  v7_early	- ARMv7 generic early abort handler
@@ -39,19 +39,19 @@
 # endif
 #endif
 
-#ifdef CONFIG_CPU_ABRT_LV4T
+#ifdef CONFIG_CPU_ABRT_EV4
 # ifdef CPU_DABORT_HANDLER
 #  define MULTI_DABORT 1
 # else
-#  define CPU_DABORT_HANDLER v4t_late_abort
+#  define CPU_DABORT_HANDLER v4_early_abort
 # endif
 #endif
 
-#ifdef CONFIG_CPU_ABRT_EV4
+#ifdef CONFIG_CPU_ABRT_LV4T
 # ifdef CPU_DABORT_HANDLER
 #  define MULTI_DABORT 1
 # else
-#  define CPU_DABORT_HANDLER v4_early_abort
+#  define CPU_DABORT_HANDLER v4t_late_abort
 # endif
 #endif
 
@@ -63,19 +63,19 @@
 # endif
 #endif
 
-#ifdef CONFIG_CPU_ABRT_EV5TJ
+#ifdef CONFIG_CPU_ABRT_EV5T
 # ifdef CPU_DABORT_HANDLER
 #  define MULTI_DABORT 1
 # else
-#  define CPU_DABORT_HANDLER v5tj_early_abort
+#  define CPU_DABORT_HANDLER v5t_early_abort
 # endif
 #endif
 
-#ifdef CONFIG_CPU_ABRT_EV5T
+#ifdef CONFIG_CPU_ABRT_EV5TJ
 # ifdef CPU_DABORT_HANDLER
 #  define MULTI_DABORT 1
 # else
-#  define CPU_DABORT_HANDLER v5t_early_abort
+#  define CPU_DABORT_HANDLER v5tj_early_abort
 # endif
 #endif
 
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index 7c3d813e15df..124623e5ef14 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -211,4 +211,8 @@
 
 #define HSR_HVC_IMM_MASK	((1UL << 16) - 1)
 
+#define HSR_DABT_S1PTW		(1U << 7)
+#define HSR_DABT_CM		(1U << 8)
+#define HSR_DABT_EA		(1U << 9)
+
 #endif /* __ARM_KVM_ARM_H__ */
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index e4956f4e23e1..18d50322a9e2 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -75,7 +75,7 @@ extern char __kvm_hyp_code_end[];
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
 
 extern void __kvm_flush_vm_context(void);
-extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
+extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 #endif
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index fd611996bfb5..82b4babead2c 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -22,11 +22,12 @@
 #include <linux/kvm_host.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
+#include <asm/kvm_arm.h>
 
-u32 *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
-u32 *vcpu_spsr(struct kvm_vcpu *vcpu);
+unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
+unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu);
 
-int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run);
+bool kvm_condition_valid(struct kvm_vcpu *vcpu);
 void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr);
 void kvm_inject_undefined(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
@@ -37,14 +38,14 @@ static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static inline u32 *vcpu_pc(struct kvm_vcpu *vcpu)
+static inline unsigned long *vcpu_pc(struct kvm_vcpu *vcpu)
 {
-	return (u32 *)&vcpu->arch.regs.usr_regs.ARM_pc;
+	return &vcpu->arch.regs.usr_regs.ARM_pc;
 }
 
-static inline u32 *vcpu_cpsr(struct kvm_vcpu *vcpu)
+static inline unsigned long *vcpu_cpsr(struct kvm_vcpu *vcpu)
 {
-	return (u32 *)&vcpu->arch.regs.usr_regs.ARM_cpsr;
+	return &vcpu->arch.regs.usr_regs.ARM_cpsr;
 }
 
 static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
@@ -69,4 +70,96 @@ static inline bool kvm_vcpu_reg_is_pc(struct kvm_vcpu *vcpu, int reg)
 	return reg == 15;
 }
 
+static inline u32 kvm_vcpu_get_hsr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.fault.hsr;
+}
+
+static inline unsigned long kvm_vcpu_get_hfar(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.fault.hxfar;
+}
+
+static inline phys_addr_t kvm_vcpu_get_fault_ipa(struct kvm_vcpu *vcpu)
+{
+	return ((phys_addr_t)vcpu->arch.fault.hpfar & HPFAR_MASK) << 8;
+}
+
+static inline unsigned long kvm_vcpu_get_hyp_pc(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.fault.hyp_pc;
+}
+
+static inline bool kvm_vcpu_dabt_isvalid(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_ISV;
+}
+
+static inline bool kvm_vcpu_dabt_iswrite(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_WNR;
+}
+
+static inline bool kvm_vcpu_dabt_issext(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_SSE;
+}
+
+static inline int kvm_vcpu_dabt_get_rd(struct kvm_vcpu *vcpu)
+{
+	return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT;
+}
+
+static inline bool kvm_vcpu_dabt_isextabt(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_EA;
+}
+
+static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW;
+}
+
+/* Get Access Size from a data abort */
+static inline int kvm_vcpu_dabt_get_as(struct kvm_vcpu *vcpu)
+{
+	switch ((kvm_vcpu_get_hsr(vcpu) >> 22) & 0x3) {
+	case 0:
+		return 1;
+	case 1:
+		return 2;
+	case 2:
+		return 4;
+	default:
+		kvm_err("Hardware is weird: SAS 0b11 is reserved\n");
+		return -EFAULT;
+	}
+}
+
+/* This one is not specific to Data Abort */
+static inline bool kvm_vcpu_trap_il_is32bit(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_IL;
+}
+
+static inline u8 kvm_vcpu_trap_get_class(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) >> HSR_EC_SHIFT;
+}
+
+static inline bool kvm_vcpu_trap_is_iabt(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_trap_get_class(vcpu) == HSR_EC_IABT;
+}
+
+static inline u8 kvm_vcpu_trap_get_fault(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_FSC_TYPE;
+}
+
+static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK;
+}
+
 #endif /* __ARM_KVM_EMULATE_H__ */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index d1736a53b12d..0c4e643d939e 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -80,6 +80,15 @@ struct kvm_mmu_memory_cache {
 	void *objects[KVM_NR_MEM_OBJS];
 };
 
+struct kvm_vcpu_fault_info {
+	u32 hsr;		/* Hyp Syndrome Register */
+	u32 hxfar;		/* Hyp Data/Inst. Fault Address Register */
+	u32 hpfar;		/* Hyp IPA Fault Address Register */
+	u32 hyp_pc;		/* PC when exception was taken from Hyp mode */
+};
+
+typedef struct vfp_hard_struct kvm_kernel_vfp_t;
+
 struct kvm_vcpu_arch {
 	struct kvm_regs regs;
 
@@ -93,13 +102,11 @@ struct kvm_vcpu_arch {
 	u32 midr;
 
 	/* Exception Information */
-	u32 hsr;		/* Hyp Syndrome Register */
-	u32 hxfar;		/* Hyp Data/Inst Fault Address Register */
-	u32 hpfar;		/* Hyp IPA Fault Address Register */
+	struct kvm_vcpu_fault_info fault;
 
 	/* Floating point registers (VFP and Advanced SIMD/NEON) */
-	struct vfp_hard_struct vfp_guest;
-	struct vfp_hard_struct *vfp_host;
+	kvm_kernel_vfp_t vfp_guest;
+	kvm_kernel_vfp_t *vfp_host;
 
 	/* VGIC state */
 	struct vgic_cpu vgic_cpu;
@@ -122,9 +129,6 @@ struct kvm_vcpu_arch {
 	/* Interrupt related fields */
 	u32 irq_lines;		/* IRQ and FIQ levels */
 
-	/* Hyp exception information */
-	u32 hyp_pc;		/* PC when exception was taken from Hyp mode */
-
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
@@ -181,4 +185,26 @@ struct kvm_one_reg;
 int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
 int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
 
+int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		int exception_index);
+
+static inline void __cpu_init_hyp_mode(unsigned long long pgd_ptr,
+				       unsigned long hyp_stack_ptr,
+				       unsigned long vector_ptr)
+{
+	unsigned long pgd_low, pgd_high;
+
+	pgd_low = (pgd_ptr & ((1ULL << 32) - 1));
+	pgd_high = (pgd_ptr >> 32ULL);
+
+	/*
+	 * Call initialization code, and switch to the full blown
+	 * HYP code. The init code doesn't need to preserve these registers as
+	 * r1-r3 and r12 are already callee save according to the AAPCS.
+	 * Note that we slightly misuse the prototype by casing the pgd_low to
+	 * a void *.
+	 */
+	kvm_call_hyp((void *)pgd_low, pgd_high, hyp_stack_ptr, vector_ptr);
+}
+
 #endif /* __ARM_KVM_HOST_H__ */
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 421a20b34874..970f3b5fa109 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -19,6 +19,18 @@
 #ifndef __ARM_KVM_MMU_H__
 #define __ARM_KVM_MMU_H__
 
+#include <asm/cacheflush.h>
+#include <asm/pgalloc.h>
+#include <asm/idmap.h>
+
+/*
+ * We directly use the kernel VA for the HYP, as we can directly share
+ * the mapping (HTTBR "covers" TTBR1).
+ */
+#define HYP_PAGE_OFFSET_MASK	(~0UL)
+#define HYP_PAGE_OFFSET		PAGE_OFFSET
+#define KERN_TO_HYP(kva)	(kva)
+
 int create_hyp_mappings(void *from, void *to);
 int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
 void free_hyp_pmds(void);
@@ -36,6 +48,16 @@ phys_addr_t kvm_mmu_get_httbr(void);
 int kvm_mmu_init(void);
 void kvm_clear_hyp_idmap(void);
 
+static inline void kvm_set_pte(pte_t *pte, pte_t new_pte)
+{
+	pte_val(*pte) = new_pte;
+	/*
+	 * flush_pmd_entry just takes a void pointer and cleans the necessary
+	 * cache entries, so we can reuse the function for ptes.
+	 */
+	flush_pmd_entry(pte);
+}
+
 static inline bool kvm_is_write_fault(unsigned long hsr)
 {
 	unsigned long hsr_ec = hsr >> HSR_EC_SHIFT;
@@ -47,4 +69,49 @@ static inline bool kvm_is_write_fault(unsigned long hsr)
 		return true;
 }
 
+static inline void kvm_clean_pgd(pgd_t *pgd)
+{
+	clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t));
+}
+
+static inline void kvm_clean_pmd_entry(pmd_t *pmd)
+{
+	clean_pmd_entry(pmd);
+}
+
+static inline void kvm_clean_pte(pte_t *pte)
+{
+	clean_pte_table(pte);
+}
+
+static inline void kvm_set_s2pte_writable(pte_t *pte)
+{
+	pte_val(*pte) |= L_PTE_S2_RDWR;
+}
+
+struct kvm;
+
+static inline void coherent_icache_guest_page(struct kvm *kvm, gfn_t gfn)
+{
+	/*
+	 * If we are going to insert an instruction page and the icache is
+	 * either VIPT or PIPT, there is a potential problem where the host
+	 * (or another VM) may have used the same page as this guest, and we
+	 * read incorrect data from the icache.  If we're using a PIPT cache,
+	 * we can invalidate just that page, but if we are using a VIPT cache
+	 * we need to invalidate the entire icache - damn shame - as written
+	 * in the ARM ARM (DDI 0406C.b - Page B3-1393).
+	 *
+	 * VIVT caches are tagged using both the ASID and the VMID and doesn't
+	 * need any kind of flushing (DDI 0406C.b - Page B3-1392).
+	 */
+	if (icache_is_pipt()) {
+		unsigned long hva = gfn_to_hva(kvm, gfn);
+		__cpuc_coherent_user_range(hva, hva + PAGE_SIZE);
+	} else if (!icache_is_vivt_asid_tagged()) {
+		/* any kind of VIPT cache */
+		__flush_icache_all();
+	}
+}
+
 #endif /* __ARM_KVM_MMU_H__ */
diff --git a/arch/arm/include/asm/kvm_vgic.h b/arch/arm/include/asm/kvm_vgic.h
index ab97207d9cd3..343744e4809c 100644
--- a/arch/arm/include/asm/kvm_vgic.h
+++ b/arch/arm/include/asm/kvm_vgic.h
@@ -21,7 +21,6 @@
 
 #include <linux/kernel.h>
 #include <linux/kvm.h>
-#include <linux/kvm_host.h>
 #include <linux/irqreturn.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
diff --git a/arch/arm/include/asm/mach/pci.h b/arch/arm/include/asm/mach/pci.h
index 5cf2e979b4be..7d2c3c843801 100644
--- a/arch/arm/include/asm/mach/pci.h
+++ b/arch/arm/include/asm/mach/pci.h
@@ -30,6 +30,11 @@ struct hw_pci {
 	void		(*postinit)(void);
 	u8		(*swizzle)(struct pci_dev *dev, u8 *pin);
 	int		(*map_irq)(const struct pci_dev *dev, u8 slot, u8 pin);
+	resource_size_t (*align_resource)(struct pci_dev *dev,
+					  const struct resource *res,
+					  resource_size_t start,
+					  resource_size_t size,
+					  resource_size_t align);
 };
 
 /*
@@ -51,6 +56,12 @@ struct pci_sys_data {
 	u8		(*swizzle)(struct pci_dev *, u8 *);
 					/* IRQ mapping				*/
 	int		(*map_irq)(const struct pci_dev *, u8, u8);
+					/* Resource alignement requirements	*/
+	resource_size_t (*align_resource)(struct pci_dev *dev,
+					  const struct resource *res,
+					  resource_size_t start,
+					  resource_size_t size,
+					  resource_size_t align);
 	void		*private_data;	/* platform controller private data	*/
 };
 
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
new file mode 100644
index 000000000000..0f7b7620e9a5
--- /dev/null
+++ b/arch/arm/include/asm/mcpm.h
@@ -0,0 +1,209 @@
+/*
+ * arch/arm/include/asm/mcpm.h
+ *
+ * Created by:  Nicolas Pitre, April 2012
+ * Copyright:   (C) 2012-2013  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef MCPM_H
+#define MCPM_H
+
+/*
+ * Maximum number of possible clusters / CPUs per cluster.
+ *
+ * This should be sufficient for quite a while, while keeping the
+ * (assembly) code simpler.  When this starts to grow then we'll have
+ * to consider dynamic allocation.
+ */
+#define MAX_CPUS_PER_CLUSTER	4
+#define MAX_NR_CLUSTERS		2
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <asm/cacheflush.h>
+
+/*
+ * Platform specific code should use this symbol to set up secondary
+ * entry location for processors to use when released from reset.
+ */
+extern void mcpm_entry_point(void);
+
+/*
+ * This is used to indicate where the given CPU from given cluster should
+ * branch once it is ready to re-enter the kernel using ptr, or NULL if it
+ * should be gated.  A gated CPU is held in a WFE loop until its vector
+ * becomes non NULL.
+ */
+void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr);
+
+/*
+ * CPU/cluster power operations API for higher subsystems to use.
+ */
+
+/**
+ * mcpm_cpu_power_up - make given CPU in given cluster runable
+ *
+ * @cpu: CPU number within given cluster
+ * @cluster: cluster number for the CPU
+ *
+ * The identified CPU is brought out of reset.  If the cluster was powered
+ * down then it is brought up as well, taking care not to let the other CPUs
+ * in the cluster run, and ensuring appropriate cluster setup.
+ *
+ * Caller must ensure the appropriate entry vector is initialized with
+ * mcpm_set_entry_vector() prior to calling this.
+ *
+ * This must be called in a sleepable context.  However, the implementation
+ * is strongly encouraged to return early and let the operation happen
+ * asynchronously, especially when significant delays are expected.
+ *
+ * If the operation cannot be performed then an error code is returned.
+ */
+int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster);
+
+/**
+ * mcpm_cpu_power_down - power the calling CPU down
+ *
+ * The calling CPU is powered down.
+ *
+ * If this CPU is found to be the "last man standing" in the cluster
+ * then the cluster is prepared for power-down too.
+ *
+ * This must be called with interrupts disabled.
+ *
+ * This does not return.  Re-entry in the kernel is expected via
+ * mcpm_entry_point.
+ */
+void mcpm_cpu_power_down(void);
+
+/**
+ * mcpm_cpu_suspend - bring the calling CPU in a suspended state
+ *
+ * @expected_residency: duration in microseconds the CPU is expected
+ *			to remain suspended, or 0 if unknown/infinity.
+ *
+ * The calling CPU is suspended.  The expected residency argument is used
+ * as a hint by the platform specific backend to implement the appropriate
+ * sleep state level according to the knowledge it has on wake-up latency
+ * for the given hardware.
+ *
+ * If this CPU is found to be the "last man standing" in the cluster
+ * then the cluster may be prepared for power-down too, if the expected
+ * residency makes it worthwhile.
+ *
+ * This must be called with interrupts disabled.
+ *
+ * This does not return.  Re-entry in the kernel is expected via
+ * mcpm_entry_point.
+ */
+void mcpm_cpu_suspend(u64 expected_residency);
+
+/**
+ * mcpm_cpu_powered_up - housekeeping workafter a CPU has been powered up
+ *
+ * This lets the platform specific backend code perform needed housekeeping
+ * work.  This must be called by the newly activated CPU as soon as it is
+ * fully operational in kernel space, before it enables interrupts.
+ *
+ * If the operation cannot be performed then an error code is returned.
+ */
+int mcpm_cpu_powered_up(void);
+
+/*
+ * Platform specific methods used in the implementation of the above API.
+ */
+struct mcpm_platform_ops {
+	int (*power_up)(unsigned int cpu, unsigned int cluster);
+	void (*power_down)(void);
+	void (*suspend)(u64);
+	void (*powered_up)(void);
+};
+
+/**
+ * mcpm_platform_register - register platform specific power methods
+ *
+ * @ops: mcpm_platform_ops structure to register
+ *
+ * An error is returned if the registration has been done previously.
+ */
+int __init mcpm_platform_register(const struct mcpm_platform_ops *ops);
+
+/* Synchronisation structures for coordinating safe cluster setup/teardown: */
+
+/*
+ * When modifying this structure, make sure you update the MCPM_SYNC_ defines
+ * to match.
+ */
+struct mcpm_sync_struct {
+	/* individual CPU states */
+	struct {
+		s8 cpu __aligned(__CACHE_WRITEBACK_GRANULE);
+	} cpus[MAX_CPUS_PER_CLUSTER];
+
+	/* cluster state */
+	s8 cluster __aligned(__CACHE_WRITEBACK_GRANULE);
+
+	/* inbound-side state */
+	s8 inbound __aligned(__CACHE_WRITEBACK_GRANULE);
+};
+
+struct sync_struct {
+	struct mcpm_sync_struct clusters[MAX_NR_CLUSTERS];
+};
+
+extern unsigned long sync_phys;	/* physical address of *mcpm_sync */
+
+void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster);
+void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster);
+void __mcpm_outbound_leave_critical(unsigned int cluster, int state);
+bool __mcpm_outbound_enter_critical(unsigned int this_cpu, unsigned int cluster);
+int __mcpm_cluster_state(unsigned int cluster);
+
+int __init mcpm_sync_init(
+	void (*power_up_setup)(unsigned int affinity_level));
+
+void __init mcpm_smp_set_ops(void);
+
+#else
+
+/* 
+ * asm-offsets.h causes trouble when included in .c files, and cacheflush.h
+ * cannot be included in asm files.  Let's work around the conflict like this.
+ */
+#include <asm/asm-offsets.h>
+#define __CACHE_WRITEBACK_GRANULE CACHE_WRITEBACK_GRANULE
+
+#endif /* ! __ASSEMBLY__ */
+
+/* Definitions for mcpm_sync_struct */
+#define CPU_DOWN		0x11
+#define CPU_COMING_UP		0x12
+#define CPU_UP			0x13
+#define CPU_GOING_DOWN		0x14
+
+#define CLUSTER_DOWN		0x21
+#define CLUSTER_UP		0x22
+#define CLUSTER_GOING_DOWN	0x23
+
+#define INBOUND_NOT_COMING_UP	0x31
+#define INBOUND_COMING_UP	0x32
+
+/*
+ * Offsets for the mcpm_sync_struct members, for use in asm.
+ * We don't want to make them global to the kernel via asm-offsets.c.
+ */
+#define MCPM_SYNC_CLUSTER_CPUS	0
+#define MCPM_SYNC_CPU_SIZE	__CACHE_WRITEBACK_GRANULE
+#define MCPM_SYNC_CLUSTER_CLUSTER \
+	(MCPM_SYNC_CLUSTER_CPUS + MCPM_SYNC_CPU_SIZE * MAX_CPUS_PER_CLUSTER)
+#define MCPM_SYNC_CLUSTER_INBOUND \
+	(MCPM_SYNC_CLUSTER_CLUSTER + __CACHE_WRITEBACK_GRANULE)
+#define MCPM_SYNC_CLUSTER_SIZE \
+	(MCPM_SYNC_CLUSTER_INBOUND + __CACHE_WRITEBACK_GRANULE)
+
+#endif
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index cddda1f41f0f..1995d1a84060 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -152,6 +152,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
 #define TIF_SYSCALL_AUDIT	9
 #define TIF_SYSCALL_TRACEPOINT	10
 #define TIF_SECCOMP		11	/* seccomp syscall filtering active */
+#define TIF_NOHZ		12	/* in adaptive nohz mode */
 #define TIF_USING_IWMMXT	17
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	20
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index ab865e65a84c..a3625d141c1d 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -166,7 +166,7 @@
 # define v6wbi_always_flags	(-1UL)
 #endif
 
-#define v7wbi_tlb_flags_smp	(TLB_WB | TLB_DCLEAN | TLB_BARRIER | \
+#define v7wbi_tlb_flags_smp	(TLB_WB | TLB_BARRIER | \
 				 TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | \
 				 TLB_V7_UIS_ASID | TLB_V7_UIS_BP)
 #define v7wbi_tlb_flags_up	(TLB_WB | TLB_DCLEAN | TLB_BARRIER | \