Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull first batch of KVM updates from Paolo Bonzini:
 "The bulk of the changes here is for x86.  And for once it's not for
  silicon that no one owns: these are really new features for everyone.

  Details:

   - ARM:
        several features are in progress but missed the 4.2 deadline.
        So here is just a smattering of bug fixes, plus enabling the
        VFIO integration.

   - s390:
        Some fixes/refactorings/optimizations, plus support for 2GB
        pages.

   - x86:
        * host and guest support for marking kvmclock as a stable
          scheduler clock.
        * support for write combining.
        * support for system management mode, needed for secure boot in
          guests.
        * a bunch of cleanups required for the above
        * support for virtualized performance counters on AMD
        * legacy PCI device assignment is deprecated and defaults to "n"
          in Kconfig; VFIO replaces it

        On top of this there are also bug fixes and eager FPU context
        loading for FPU-heavy guests.

   - Common code:
        Support for multiple address spaces; for now it is used only for
        x86 SMM but the s390 folks also have plans"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (124 commits)
  KVM: s390: clear floating interrupt bitmap and parameters
  KVM: x86/vPMU: Enable PMU handling for AMD PERFCTRn and EVNTSELn MSRs
  KVM: x86/vPMU: Implement AMD vPMU code for KVM
  KVM: x86/vPMU: Define kvm_pmu_ops to support vPMU function dispatch
  KVM: x86/vPMU: introduce kvm_pmu_msr_idx_to_pmc
  KVM: x86/vPMU: reorder PMU functions
  KVM: x86/vPMU: whitespace and stylistic adjustments in PMU code
  KVM: x86/vPMU: use the new macros to go between PMC, PMU and VCPU
  KVM: x86/vPMU: introduce pmu.h header
  KVM: x86/vPMU: rename a few PMU functions
  KVM: MTRR: do not map huge page for non-consistent range
  KVM: MTRR: simplify kvm_mtrr_get_guest_memory_type
  KVM: MTRR: introduce mtrr_for_each_mem_type
  KVM: MTRR: introduce fixed_mtrr_addr_* functions
  KVM: MTRR: sort variable MTRRs
  KVM: MTRR: introduce var_mtrr_range
  KVM: MTRR: introduce fixed_mtrr_segment table
  KVM: MTRR: improve kvm_mtrr_get_guest_memory_type
  KVM: MTRR: do not split 64 bits MSR content
  KVM: MTRR: clean up mtrr default type
  ...

31 files changed, 3305 insertions, 1323 deletions

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 57a9d94fe160..e16466ec473c 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -193,6 +193,8 @@ struct x86_emulate_ops {
 	int (*cpl)(struct x86_emulate_ctxt *ctxt);
 	int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest);
 	int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value);
+	u64 (*get_smbase)(struct x86_emulate_ctxt *ctxt);
+	void (*set_smbase)(struct x86_emulate_ctxt *ctxt, u64 smbase);
 	int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data);
 	int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
 	int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc);
@@ -262,6 +264,11 @@ enum x86emul_mode {
 	X86EMUL_MODE_PROT64,	/* 64-bit (long) mode.    */
 };
 
+/* These match some of the HF_* flags defined in kvm_host.h  */
+#define X86EMUL_GUEST_MASK           (1 << 5) /* VCPU is in guest-mode */
+#define X86EMUL_SMM_MASK             (1 << 6)
+#define X86EMUL_SMM_INSIDE_NMI_MASK  (1 << 7)
+
 struct x86_emulate_ctxt {
 	const struct x86_emulate_ops *ops;
 
@@ -273,8 +280,8 @@ struct x86_emulate_ctxt {
 
 	/* interruptibility state, as a result of execution of STI or MOV SS */
 	int interruptibility;
+	int emul_flags;
 
-	bool guest_mode; /* guest running a nested guest */
 	bool perm_ok; /* do not check permissions if true */
 	bool ud;	/* inject an #UD if host doesn't support insn */
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f8c0ec3a4a97..c7fa57b529d2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -184,23 +184,12 @@ struct kvm_mmu_memory_cache {
 	void *objects[KVM_NR_MEM_OBJS];
 };
 
-/*
- * kvm_mmu_page_role, below, is defined as:
- *
- *   bits 0:3 - total guest paging levels (2-4, or zero for real mode)
- *   bits 4:7 - page table level for this shadow (1-4)
- *   bits 8:9 - page table quadrant for 2-level guests
- *   bit   16 - direct mapping of virtual to physical mapping at gfn
- *              used for real mode and two-dimensional paging
- *   bits 17:19 - common access permissions for all ptes in this shadow page
- */
 union kvm_mmu_page_role {
 	unsigned word;
 	struct {
 		unsigned level:4;
 		unsigned cr4_pae:1;
 		unsigned quadrant:2;
-		unsigned pad_for_nice_hex_output:6;
 		unsigned direct:1;
 		unsigned access:3;
 		unsigned invalid:1;
@@ -208,6 +197,15 @@ union kvm_mmu_page_role {
 		unsigned cr0_wp:1;
 		unsigned smep_andnot_wp:1;
 		unsigned smap_andnot_wp:1;
+		unsigned :8;
+
+		/*
+		 * This is left at the top of the word so that
+		 * kvm_memslots_for_spte_role can extract it with a
+		 * simple shift.  While there is room, give it a whole
+		 * byte so it is also faster to load it from memory.
+		 */
+		unsigned smm:8;
 	};
 };
 
@@ -338,12 +336,28 @@ struct kvm_pmu {
 	u64 reprogram_pmi;
 };
 
+struct kvm_pmu_ops;
+
 enum {
 	KVM_DEBUGREG_BP_ENABLED = 1,
 	KVM_DEBUGREG_WONT_EXIT = 2,
 	KVM_DEBUGREG_RELOAD = 4,
 };
 
+struct kvm_mtrr_range {
+	u64 base;
+	u64 mask;
+	struct list_head node;
+};
+
+struct kvm_mtrr {
+	struct kvm_mtrr_range var_ranges[KVM_NR_VAR_MTRR];
+	mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION];
+	u64 deftype;
+
+	struct list_head head;
+};
+
 struct kvm_vcpu_arch {
 	/*
 	 * rip and regs accesses must go through
@@ -368,6 +382,7 @@ struct kvm_vcpu_arch {
 	int32_t apic_arb_prio;
 	int mp_state;
 	u64 ia32_misc_enable_msr;
+	u64 smbase;
 	bool tpr_access_reporting;
 	u64 ia32_xss;
 
@@ -471,8 +486,9 @@ struct kvm_vcpu_arch {
 	atomic_t nmi_queued;  /* unprocessed asynchronous NMIs */
 	unsigned nmi_pending; /* NMI queued after currently running handler */
 	bool nmi_injected;    /* Trying to inject an NMI this entry */
+	bool smi_pending;    /* SMI queued after currently running handler */
 
-	struct mtrr_state_type mtrr_state;
+	struct kvm_mtrr mtrr_state;
 	u64 pat;
 
 	unsigned switch_db_regs;
@@ -637,6 +653,8 @@ struct kvm_arch {
 	#endif
 
 	bool boot_vcpu_runs_old_kvmclock;
+
+	u64 disabled_quirks;
 };
 
 struct kvm_vm_stat {
@@ -689,12 +707,13 @@ struct msr_data {
 
 struct kvm_lapic_irq {
 	u32 vector;
-	u32 delivery_mode;
-	u32 dest_mode;
-	u32 level;
-	u32 trig_mode;
+	u16 delivery_mode;
+	u16 dest_mode;
+	bool level;
+	u16 trig_mode;
 	u32 shorthand;
 	u32 dest_id;
+	bool msi_redir_hint;
 };
 
 struct kvm_x86_ops {
@@ -706,19 +725,20 @@ struct kvm_x86_ops {
 	int (*hardware_setup)(void);               /* __init */
 	void (*hardware_unsetup)(void);            /* __exit */
 	bool (*cpu_has_accelerated_tpr)(void);
+	bool (*cpu_has_high_real_mode_segbase)(void);
 	void (*cpuid_update)(struct kvm_vcpu *vcpu);
 
 	/* Create, but do not attach this VCPU */
 	struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id);
 	void (*vcpu_free)(struct kvm_vcpu *vcpu);
-	void (*vcpu_reset)(struct kvm_vcpu *vcpu);
+	void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event);
 
 	void (*prepare_guest_switch)(struct kvm_vcpu *vcpu);
 	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
 
 	void (*update_db_bp_intercept)(struct kvm_vcpu *vcpu);
-	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
+	int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
 	int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
 	u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
 	void (*get_segment)(struct kvm_vcpu *vcpu,
@@ -836,6 +856,8 @@ struct kvm_x86_ops {
 	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
 					   struct kvm_memory_slot *slot,
 					   gfn_t offset, unsigned long mask);
+	/* pmu operations of sub-arch */
+	const struct kvm_pmu_ops *pmu_ops;
 };
 
 struct kvm_arch_async_pf {
@@ -871,7 +893,7 @@ void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
 				      struct kvm_memory_slot *memslot);
 void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
-					struct kvm_memory_slot *memslot);
+				   const struct kvm_memory_slot *memslot);
 void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot);
 void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
@@ -882,7 +904,7 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 				   struct kvm_memory_slot *slot,
 				   gfn_t gfn_offset, unsigned long mask);
 void kvm_mmu_zap_all(struct kvm *kvm);
-void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm);
+void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots);
 unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
 
@@ -890,7 +912,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
 
 int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 			  const void *val, int bytes);
-u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 struct kvm_irq_mask_notifier {
 	void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked);
@@ -938,7 +959,7 @@ static inline int emulate_instruction(struct kvm_vcpu *vcpu,
 
 void kvm_enable_efer_bits(u64);
 bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer);
-int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data);
+int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
 int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
 
 struct x86_emulate_ctxt;
@@ -967,7 +988,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
 void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
 int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr);
 
-int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
+int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr);
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr);
 
 unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu);
@@ -1110,6 +1131,14 @@ enum {
 #define HF_NMI_MASK		(1 << 3)
 #define HF_IRET_MASK		(1 << 4)
 #define HF_GUEST_MASK		(1 << 5) /* VCPU is in guest-mode */
+#define HF_SMM_MASK		(1 << 6)
+#define HF_SMM_INSIDE_NMI_MASK	(1 << 7)
+
+#define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
+#define KVM_ADDRESS_SPACE_NUM 2
+
+#define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
+#define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
 
 /*
  * Hardware virtualization extension instructions may fault if a
@@ -1144,7 +1173,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
-void kvm_vcpu_reset(struct kvm_vcpu *vcpu);
+void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);
 void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
 					   unsigned long address);
@@ -1168,16 +1197,9 @@ void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
 
 int kvm_is_in_guest(void);
 
-void kvm_pmu_init(struct kvm_vcpu *vcpu);
-void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
-void kvm_pmu_reset(struct kvm_vcpu *vcpu);
-void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu);
-bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr);
-int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
-int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
-int kvm_pmu_check_pmc(struct kvm_vcpu *vcpu, unsigned pmc);
-int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
-void kvm_handle_pmu_event(struct kvm_vcpu *vcpu);
-void kvm_deliver_pmi(struct kvm_vcpu *vcpu);
+int __x86_set_memory_region(struct kvm *kvm,
+			    const struct kvm_userspace_memory_region *mem);
+int x86_set_memory_region(struct kvm *kvm,
+			  const struct kvm_userspace_memory_region *mem);
 
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
index 6167fd798188..655e07a48f6c 100644
--- a/arch/x86/include/asm/pvclock-abi.h
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -41,5 +41,6 @@ struct pvclock_wall_clock {
 
 #define PVCLOCK_TSC_STABLE_BIT	(1 << 0)
 #define PVCLOCK_GUEST_STOPPED	(1 << 1)
+#define PVCLOCK_COUNTS_FROM_ZERO (1 << 2)
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index d6b078e9fa28..628954ceede1 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -86,7 +86,6 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
 	offset = pvclock_get_nsec_offset(src);
 	ret = src->system_time + offset;
 	ret_flags = src->flags;
-	rdtsc_barrier();
 
 	*cycles = ret;
 	*flags = ret_flags;
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index d7dcef58aefa..a4ae82eb82aa 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -106,6 +106,8 @@ struct kvm_ioapic_state {
 #define KVM_IRQCHIP_IOAPIC       2
 #define KVM_NR_IRQCHIPS          3
 
+#define KVM_RUN_X86_SMM		 (1 << 0)
+
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
 	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
@@ -281,6 +283,7 @@ struct kvm_reinject_control {
 #define KVM_VCPUEVENT_VALID_NMI_PENDING	0x00000001
 #define KVM_VCPUEVENT_VALID_SIPI_VECTOR	0x00000002
 #define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
+#define KVM_VCPUEVENT_VALID_SMM		0x00000008
 
 /* Interrupt shadow states */
 #define KVM_X86_SHADOW_INT_MOV_SS	0x01
@@ -309,7 +312,13 @@ struct kvm_vcpu_events {
 	} nmi;
 	__u32 sipi_vector;
 	__u32 flags;
-	__u32 reserved[10];
+	struct {
+		__u8 smm;
+		__u8 pending;
+		__u8 smm_inside_nmi;
+		__u8 latched_init;
+	} smi;
+	__u32 reserved[9];
 };
 
 /* for KVM_GET/SET_DEBUGREGS */
@@ -345,4 +354,7 @@ struct kvm_xcrs {
 struct kvm_sync_regs {
 };
 
+#define KVM_QUIRK_LINT0_REENABLED	(1 << 0)
+#define KVM_QUIRK_CD_NW_CLEARED		(1 << 1)
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 1681504e44a4..47190bd399e7 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -331,7 +331,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val)
 	apic_write(APIC_EOI, APIC_EOI_ACK);
 }
 
-void kvm_guest_cpu_init(void)
+static void kvm_guest_cpu_init(void)
 {
 	if (!kvm_para_available())
 		return;
@@ -688,7 +688,7 @@ static inline void spin_time_accum_blocked(u64 start)
 static struct dentry *d_spin_debug;
 static struct dentry *d_kvm_debug;
 
-struct dentry *kvm_init_debugfs(void)
+static struct dentry *kvm_init_debugfs(void)
 {
 	d_kvm_debug = debugfs_create_dir("kvm-guest", NULL);
 	if (!d_kvm_debug)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 42caaef897c8..49487b488061 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -24,6 +24,7 @@
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
 #include <linux/memblock.h>
+#include <linux/sched.h>
 
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
@@ -217,8 +218,10 @@ static void kvm_shutdown(void)
 
 void __init kvmclock_init(void)
 {
+	struct pvclock_vcpu_time_info *vcpu_time;
 	unsigned long mem;
-	int size;
+	int size, cpu;
+	u8 flags;
 
 	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
 
@@ -264,7 +267,14 @@ void __init kvmclock_init(void)
 	pv_info.name = "KVM";
 
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
-		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
+		pvclock_set_flags(~0);
+
+	cpu = get_cpu();
+	vcpu_time = &hv_clock[cpu].pvti;
+	flags = pvclock_read_flags(vcpu_time);
+	if (flags & PVCLOCK_COUNTS_FROM_ZERO)
+		set_sched_clock_stable();
+	put_cpu();
 }
 
 int __init kvm_setup_vsyscall_timeinfo(void)
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 413a7bf9efbb..d8a1d56276e1 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -86,15 +86,16 @@ config KVM_MMU_AUDIT
 	 auditing of KVM MMU events at runtime.
 
 config KVM_DEVICE_ASSIGNMENT
-	bool "KVM legacy PCI device assignment support"
+	bool "KVM legacy PCI device assignment support (DEPRECATED)"
 	depends on KVM && PCI && IOMMU_API
-	default y
+	default n
 	---help---
 	  Provide support for legacy PCI device assignment through KVM.  The
 	  kernel now also supports a full featured userspace device driver
-	  framework through VFIO, which supersedes much of this support.
+	  framework through VFIO, which supersedes this support and provides
+	  better security.
 
-	  If unsure, say Y.
+	  If unsure, say N.
 
 # OK, it's a little counter-intuitive to do this, but it puts it neatly under
 # the virtualization menu.
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 16e8f962eaad..67d215cb8953 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -12,10 +12,10 @@ kvm-y			+= $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
-			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o
+			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o
 kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT)	+= assigned-dev.o iommu.o
-kvm-intel-y		+= vmx.o
-kvm-amd-y		+= svm.o
+kvm-intel-y		+= vmx.o pmu_intel.o
+kvm-amd-y		+= svm.o pmu_amd.o
 
 obj-$(CONFIG_KVM)	+= kvm.o
 obj-$(CONFIG_KVM_INTEL)	+= kvm-intel.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 9f705e618af5..64dd46793099 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -16,12 +16,14 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
+#include <asm/fpu/internal.h> /* For use_eager_fpu.  Ugh! */
 #include <asm/user.h>
 #include <asm/fpu/xstate.h>
 #include "cpuid.h"
 #include "lapic.h"
 #include "mmu.h"
 #include "trace.h"
+#include "pmu.h"
 
 static u32 xstate_required_size(u64 xstate_bv, bool compacted)
 {
@@ -95,7 +97,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 	if (best && (best->eax & (F(XSAVES) | F(XSAVEC))))
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
 
-	vcpu->arch.eager_fpu = guest_cpuid_has_mpx(vcpu);
+	vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu);
 
 	/*
 	 * The existing code assumes virtual address is 48-bit in the canonical
@@ -109,7 +111,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 	/* Update physical-address width */
 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
 
-	kvm_pmu_cpuid_update(vcpu);
+	kvm_pmu_refresh(vcpu);
 	return 0;
 }
 
@@ -413,6 +415,12 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		}
 		break;
 	}
+	case 6: /* Thermal management */
+		entry->eax = 0x4; /* allow ARAT */
+		entry->ebx = 0;
+		entry->ecx = 0;
+		entry->edx = 0;
+		break;
 	case 7: {
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
 		/* Mask ebx against host capability word 9 */
@@ -589,7 +597,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		break;
 	case 3: /* Processor serial number */
 	case 5: /* MONITOR/MWAIT */
-	case 6: /* Thermal management */
 	case 0xC0000002:
 	case 0xC0000003:
 	case 0xC0000004:
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 496b3695d3d3..dd05b9cef6ae 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -70,6 +70,14 @@ static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu)
 	return best && (best->ebx & bit(X86_FEATURE_FSGSBASE));
 }
 
+static inline bool guest_cpuid_has_longmode(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
+	return best && (best->edx & bit(X86_FEATURE_LM));
+}
+
 static inline bool guest_cpuid_has_osvw(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 630bcb0d7a04..e7a4fde5d631 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <asm/kvm_emulate.h>
 #include <linux/stringify.h>
+#include <asm/debugreg.h>
 
 #include "x86.h"
 #include "tss.h"
@@ -523,13 +524,9 @@ static void masked_increment(ulong *reg, ulong mask, int inc)
 static inline void
 register_address_increment(struct x86_emulate_ctxt *ctxt, int reg, int inc)
 {
-	ulong mask;
+	ulong *preg = reg_rmw(ctxt, reg);
 
-	if (ctxt->ad_bytes == sizeof(unsigned long))
-		mask = ~0UL;
-	else
-		mask = ad_mask(ctxt);
-	masked_increment(reg_rmw(ctxt, reg), mask, inc);
+	assign_register(preg, *preg + inc, ctxt->ad_bytes);
 }
 
 static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
@@ -2262,6 +2259,260 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt)
 	return rc;
 }
 
+static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
+{
+	u32 eax, ebx, ecx, edx;
+
+	eax = 0x80000001;
+	ecx = 0;
+	ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+	return edx & bit(X86_FEATURE_LM);
+}
+
+#define GET_SMSTATE(type, smbase, offset)				  \
+	({								  \
+	 type __val;							  \
+	 int r = ctxt->ops->read_std(ctxt, smbase + offset, &__val,       \
+				     sizeof(__val), NULL);		  \
+	 if (r != X86EMUL_CONTINUE)					  \
+		 return X86EMUL_UNHANDLEABLE;				  \
+	 __val;								  \
+	})
+
+static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
+{
+	desc->g    = (flags >> 23) & 1;
+	desc->d    = (flags >> 22) & 1;
+	desc->l    = (flags >> 21) & 1;
+	desc->avl  = (flags >> 20) & 1;
+	desc->p    = (flags >> 15) & 1;
+	desc->dpl  = (flags >> 13) & 3;
+	desc->s    = (flags >> 12) & 1;
+	desc->type = (flags >>  8) & 15;
+}
+
+static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+{
+	struct desc_struct desc;
+	int offset;
+	u16 selector;
+
+	selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4);
+
+	if (n < 3)
+		offset = 0x7f84 + n * 12;
+	else
+		offset = 0x7f2c + (n - 3) * 12;
+
+	set_desc_base(&desc,      GET_SMSTATE(u32, smbase, offset + 8));
+	set_desc_limit(&desc,     GET_SMSTATE(u32, smbase, offset + 4));
+	rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset));
+	ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
+	return X86EMUL_CONTINUE;
+}
+
+static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+{
+	struct desc_struct desc;
+	int offset;
+	u16 selector;
+	u32 base3;
+
+	offset = 0x7e00 + n * 16;
+
+	selector =                GET_SMSTATE(u16, smbase, offset);
+	rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8);
+	set_desc_limit(&desc,     GET_SMSTATE(u32, smbase, offset + 4));
+	set_desc_base(&desc,      GET_SMSTATE(u32, smbase, offset + 8));
+	base3 =                   GET_SMSTATE(u32, smbase, offset + 12);
+
+	ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
+	return X86EMUL_CONTINUE;
+}
+
+static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
+				     u64 cr0, u64 cr4)
+{
+	int bad;
+
+	/*
+	 * First enable PAE, long mode needs it before CR0.PG = 1 is set.
+	 * Then enable protected mode.	However, PCID cannot be enabled
+	 * if EFER.LMA=0, so set it separately.
+	 */
+	bad = ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
+	if (bad)
+		return X86EMUL_UNHANDLEABLE;
+
+	bad = ctxt->ops->set_cr(ctxt, 0, cr0);
+	if (bad)
+		return X86EMUL_UNHANDLEABLE;
+
+	if (cr4 & X86_CR4_PCIDE) {
+		bad = ctxt->ops->set_cr(ctxt, 4, cr4);
+		if (bad)
+			return X86EMUL_UNHANDLEABLE;
+	}
+
+	return X86EMUL_CONTINUE;
+}
+
+static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
+{
+	struct desc_struct desc;
+	struct desc_ptr dt;
+	u16 selector;
+	u32 val, cr0, cr4;
+	int i;
+
+	cr0 =                      GET_SMSTATE(u32, smbase, 0x7ffc);
+	ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u32, smbase, 0x7ff8));
+	ctxt->eflags =             GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
+	ctxt->_eip =               GET_SMSTATE(u32, smbase, 0x7ff0);
+
+	for (i = 0; i < 8; i++)
+		*reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4);
+
+	val = GET_SMSTATE(u32, smbase, 0x7fcc);
+	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+	val = GET_SMSTATE(u32, smbase, 0x7fc8);
+	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+	selector =                 GET_SMSTATE(u32, smbase, 0x7fc4);
+	set_desc_base(&desc,       GET_SMSTATE(u32, smbase, 0x7f64));
+	set_desc_limit(&desc,      GET_SMSTATE(u32, smbase, 0x7f60));
+	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smbase, 0x7f5c));
+	ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
+
+	selector =                 GET_SMSTATE(u32, smbase, 0x7fc0);
+	set_desc_base(&desc,       GET_SMSTATE(u32, smbase, 0x7f80));
+	set_desc_limit(&desc,      GET_SMSTATE(u32, smbase, 0x7f7c));
+	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smbase, 0x7f78));
+	ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
+
+	dt.address =               GET_SMSTATE(u32, smbase, 0x7f74);
+	dt.size =                  GET_SMSTATE(u32, smbase, 0x7f70);
+	ctxt->ops->set_gdt(ctxt, &dt);
+
+	dt.address =               GET_SMSTATE(u32, smbase, 0x7f58);
+	dt.size =                  GET_SMSTATE(u32, smbase, 0x7f54);
+	ctxt->ops->set_idt(ctxt, &dt);
+
+	for (i = 0; i < 6; i++) {
+		int r = rsm_load_seg_32(ctxt, smbase, i);
+		if (r != X86EMUL_CONTINUE)
+			return r;
+	}
+
+	cr4 = GET_SMSTATE(u32, smbase, 0x7f14);
+
+	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
+
+	return rsm_enter_protected_mode(ctxt, cr0, cr4);
+}
+
+static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
+{
+	struct desc_struct desc;
+	struct desc_ptr dt;
+	u64 val, cr0, cr4;
+	u32 base3;
+	u16 selector;
+	int i;
+
+	for (i = 0; i < 16; i++)
+		*reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8);
+
+	ctxt->_eip   = GET_SMSTATE(u64, smbase, 0x7f78);
+	ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED;
+
+	val = GET_SMSTATE(u32, smbase, 0x7f68);
+	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+	val = GET_SMSTATE(u32, smbase, 0x7f60);
+	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+	cr0 =                       GET_SMSTATE(u64, smbase, 0x7f58);
+	ctxt->ops->set_cr(ctxt, 3,  GET_SMSTATE(u64, smbase, 0x7f50));
+	cr4 =                       GET_SMSTATE(u64, smbase, 0x7f48);
+	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
+	val =                       GET_SMSTATE(u64, smbase, 0x7ed0);
+	ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
+
+	selector =                  GET_SMSTATE(u32, smbase, 0x7e90);
+	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smbase, 0x7e92) << 8);
+	set_desc_limit(&desc,       GET_SMSTATE(u32, smbase, 0x7e94));
+	set_desc_base(&desc,        GET_SMSTATE(u32, smbase, 0x7e98));
+	base3 =                     GET_SMSTATE(u32, smbase, 0x7e9c);
+	ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
+
+	dt.size =                   GET_SMSTATE(u32, smbase, 0x7e84);
+	dt.address =                GET_SMSTATE(u64, smbase, 0x7e88);
+	ctxt->ops->set_idt(ctxt, &dt);
+
+	selector =                  GET_SMSTATE(u32, smbase, 0x7e70);
+	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smbase, 0x7e72) << 8);
+	set_desc_limit(&desc,       GET_SMSTATE(u32, smbase, 0x7e74));
+	set_desc_base(&desc,        GET_SMSTATE(u32, smbase, 0x7e78));
+	base3 =                     GET_SMSTATE(u32, smbase, 0x7e7c);
+	ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
+
+	dt.size =