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
  ...

5 files changed, 79 insertions, 38 deletions

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 57a9d94..e16466e 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 f8c0ec3..c7fa57b 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 6167fd7..655e07a 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 d6b078e..628954c 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 d7dcef5..a4ae82e 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 */