Merge tag 'kvm-5.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "This is the first batch of KVM changes.

  ARM:
   - cleanups and corner case fixes.

  PPC:
   - Bugfixes

  x86:
   - Support for mapping DAX areas with large nested page table entries.

   - Cleanups and bugfixes here too. A particularly important one is a
     fix for FPU load when the thread has TIF_NEED_FPU_LOAD. There is
     also a race condition which could be used in guest userspace to
     exploit the guest kernel, for which the embargo expired today.

   - Fast path for IPI delivery vmexits, shaving about 200 clock cycles
     from IPI latency.

   - Protect against "Spectre-v1/L1TF" (bring data in the cache via
     speculative out of bound accesses, use L1TF on the sibling
     hyperthread to read it), which unfortunately is an even bigger
     whack-a-mole game than SpectreV1.

  Sean continues his mission to rewrite KVM. In addition to a sizable
  number of x86 patches, this time he contributed a pretty large
  refactoring of vCPU creation that affects all architectures but should
  not have any visible effect.

  s390 will come next week together with some more x86 patches"

* tag 'kvm-5.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (204 commits)
  x86/KVM: Clean up host's steal time structure
  x86/KVM: Make sure KVM_VCPU_FLUSH_TLB flag is not missed
  x86/kvm: Cache gfn to pfn translation
  x86/kvm: Introduce kvm_(un)map_gfn()
  x86/kvm: Be careful not to clear KVM_VCPU_FLUSH_TLB bit
  KVM: PPC: Book3S PR: Fix -Werror=return-type build failure
  KVM: PPC: Book3S HV: Release lock on page-out failure path
  KVM: arm64: Treat emulated TVAL TimerValue as a signed 32-bit integer
  KVM: arm64: pmu: Only handle supported event counters
  KVM: arm64: pmu: Fix chained SW_INCR counters
  KVM: arm64: pmu: Don't mark a counter as chained if the odd one is disabled
  KVM: arm64: pmu: Don't increment SW_INCR if PMCR.E is unset
  KVM: x86: Use a typedef for fastop functions
  KVM: X86: Add 'else' to unify fastop and execute call path
  KVM: x86: inline memslot_valid_for_gpte
  KVM: x86/mmu: Use huge pages for DAX-backed files
  KVM: x86/mmu: Remove lpage_is_disallowed() check from set_spte()
  KVM: x86/mmu: Fold max_mapping_level() into kvm_mmu_hugepage_adjust()
  KVM: x86/mmu: Zap any compound page when collapsing sptes
  KVM: x86/mmu: Remove obsolete gfn restoration in FNAME(fetch)
  ...

5 files changed, 36 insertions, 16 deletions

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 77cf6c11f66b..03946eb3e2b9 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -222,6 +222,10 @@ struct x86_emulate_ops {
 
 	bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt, u32 *eax, u32 *ebx,
 			  u32 *ecx, u32 *edx, bool check_limit);
+	bool (*guest_has_long_mode)(struct x86_emulate_ctxt *ctxt);
+	bool (*guest_has_movbe)(struct x86_emulate_ctxt *ctxt);
+	bool (*guest_has_fxsr)(struct x86_emulate_ctxt *ctxt);
+
 	void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
 
 	unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b79cd6aa4075..329d01c689b7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -175,6 +175,11 @@ enum {
 	VCPU_SREG_LDTR,
 };
 
+enum exit_fastpath_completion {
+	EXIT_FASTPATH_NONE,
+	EXIT_FASTPATH_SKIP_EMUL_INS,
+};
+
 #include <asm/kvm_emulate.h>
 
 #define KVM_NR_MEM_OBJS 40
@@ -378,12 +383,12 @@ struct kvm_mmu {
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
 	unsigned long (*get_cr3)(struct kvm_vcpu *vcpu);
 	u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index);
-	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err,
+	int (*page_fault)(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 err,
 			  bool prefault);
 	void (*inject_page_fault)(struct kvm_vcpu *vcpu,
 				  struct x86_exception *fault);
-	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
-			    struct x86_exception *exception);
+	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa,
+			    u32 access, struct x86_exception *exception);
 	gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
 			       struct x86_exception *exception);
 	int (*sync_page)(struct kvm_vcpu *vcpu,
@@ -606,7 +611,7 @@ struct kvm_vcpu_arch {
 	 * Paging state of an L2 guest (used for nested npt)
 	 *
 	 * This context will save all necessary information to walk page tables
-	 * of the an L2 guest. This context is only initialized for page table
+	 * of an L2 guest. This context is only initialized for page table
 	 * walking and not for faulting since we never handle l2 page faults on
 	 * the host.
 	 */
@@ -685,10 +690,10 @@ struct kvm_vcpu_arch {
 	bool pvclock_set_guest_stopped_request;
 
 	struct {
+		u8 preempted;
 		u64 msr_val;
 		u64 last_steal;
-		struct gfn_to_hva_cache stime;
-		struct kvm_steal_time steal;
+		struct gfn_to_pfn_cache cache;
 	} st;
 
 	u64 tsc_offset;
@@ -1022,6 +1027,11 @@ struct kvm_lapic_irq {
 	bool msi_redir_hint;
 };
 
+static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical)
+{
+	return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL;
+}
+
 struct kvm_x86_ops {
 	int (*cpu_has_kvm_support)(void);          /* __init */
 	int (*disabled_by_bios)(void);             /* __init */
@@ -1040,7 +1050,7 @@ struct kvm_x86_ops {
 	void (*vm_destroy)(struct kvm *kvm);
 
 	/* Create, but do not attach this VCPU */
-	struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id);
+	int (*vcpu_create)(struct kvm_vcpu *vcpu);
 	void (*vcpu_free)(struct kvm_vcpu *vcpu);
 	void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event);
 
@@ -1090,7 +1100,8 @@ struct kvm_x86_ops {
 	void (*tlb_flush_gva)(struct kvm_vcpu *vcpu, gva_t addr);
 
 	void (*run)(struct kvm_vcpu *vcpu);
-	int (*handle_exit)(struct kvm_vcpu *vcpu);
+	int (*handle_exit)(struct kvm_vcpu *vcpu,
+		enum exit_fastpath_completion exit_fastpath);
 	int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
 	void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
 	u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu);
@@ -1140,11 +1151,13 @@ struct kvm_x86_ops {
 	int (*check_intercept)(struct kvm_vcpu *vcpu,
 			       struct x86_instruction_info *info,
 			       enum x86_intercept_stage stage);
-	void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
+	void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu,
+		enum exit_fastpath_completion *exit_fastpath);
 	bool (*mpx_supported)(void);
 	bool (*xsaves_supported)(void);
 	bool (*umip_emulated)(void);
 	bool (*pt_supported)(void);
+	bool (*pku_supported)(void);
 
 	int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
 	void (*request_immediate_exit)(struct kvm_vcpu *vcpu);
@@ -1468,7 +1481,7 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu);
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code,
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 		       void *insn, int insn_len);
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
 void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid);
@@ -1614,7 +1627,6 @@ void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);
 int kvm_is_in_guest(void);
 
 int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
-int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
 bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
 bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index ea7400726d7a..0239998d8cdc 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -566,6 +566,10 @@ static inline void update_page_count(int level, unsigned long pages) { }
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
 extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
 				    unsigned int *level);
+
+struct mm_struct;
+extern pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address,
+				   unsigned int *level);
 extern pmd_t *lookup_pmd_address(unsigned long address);
 extern phys_addr_t slow_virt_to_phys(void *__address);
 extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn,
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 9fbba31be825..d380b3b7ddd9 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -22,8 +22,8 @@
 /*
  * Definitions of Primary Processor-Based VM-Execution Controls.
  */
-#define CPU_BASED_VIRTUAL_INTR_PENDING          VMCS_CONTROL_BIT(VIRTUAL_INTR_PENDING)
-#define CPU_BASED_USE_TSC_OFFSETING             VMCS_CONTROL_BIT(TSC_OFFSETTING)
+#define CPU_BASED_INTR_WINDOW_EXITING           VMCS_CONTROL_BIT(VIRTUAL_INTR_PENDING)
+#define CPU_BASED_USE_TSC_OFFSETTING            VMCS_CONTROL_BIT(TSC_OFFSETTING)
 #define CPU_BASED_HLT_EXITING                   VMCS_CONTROL_BIT(HLT_EXITING)
 #define CPU_BASED_INVLPG_EXITING                VMCS_CONTROL_BIT(INVLPG_EXITING)
 #define CPU_BASED_MWAIT_EXITING                 VMCS_CONTROL_BIT(MWAIT_EXITING)
@@ -34,7 +34,7 @@
 #define CPU_BASED_CR8_LOAD_EXITING              VMCS_CONTROL_BIT(CR8_LOAD_EXITING)
 #define CPU_BASED_CR8_STORE_EXITING             VMCS_CONTROL_BIT(CR8_STORE_EXITING)
 #define CPU_BASED_TPR_SHADOW                    VMCS_CONTROL_BIT(VIRTUAL_TPR)
-#define CPU_BASED_VIRTUAL_NMI_PENDING		VMCS_CONTROL_BIT(VIRTUAL_NMI_PENDING)
+#define CPU_BASED_NMI_WINDOW_EXITING		VMCS_CONTROL_BIT(VIRTUAL_NMI_PENDING)
 #define CPU_BASED_MOV_DR_EXITING                VMCS_CONTROL_BIT(MOV_DR_EXITING)
 #define CPU_BASED_UNCOND_IO_EXITING             VMCS_CONTROL_BIT(UNCOND_IO_EXITING)
 #define CPU_BASED_USE_IO_BITMAPS                VMCS_CONTROL_BIT(USE_IO_BITMAPS)
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 3eb8411ab60e..e95b72ec19bc 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -33,7 +33,7 @@
 #define EXIT_REASON_TRIPLE_FAULT        2
 #define EXIT_REASON_INIT_SIGNAL			3
 
-#define EXIT_REASON_PENDING_INTERRUPT   7
+#define EXIT_REASON_INTERRUPT_WINDOW    7
 #define EXIT_REASON_NMI_WINDOW          8
 #define EXIT_REASON_TASK_SWITCH         9
 #define EXIT_REASON_CPUID               10
@@ -94,7 +94,7 @@
 	{ EXIT_REASON_EXTERNAL_INTERRUPT,    "EXTERNAL_INTERRUPT" }, \
 	{ EXIT_REASON_TRIPLE_FAULT,          "TRIPLE_FAULT" }, \
 	{ EXIT_REASON_INIT_SIGNAL,           "INIT_SIGNAL" }, \
-	{ EXIT_REASON_PENDING_INTERRUPT,     "PENDING_INTERRUPT" }, \
+	{ EXIT_REASON_INTERRUPT_WINDOW,      "INTERRUPT_WINDOW" }, \
 	{ EXIT_REASON_NMI_WINDOW,            "NMI_WINDOW" }, \
 	{ EXIT_REASON_TASK_SWITCH,           "TASK_SWITCH" }, \
 	{ EXIT_REASON_CPUID,                 "CPUID" }, \