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

Pull kvm updates from Paolo Bonzini:
 "S390:

   - ultravisor communication device driver

   - fix TEID on terminating storage key ops

  RISC-V:

   - Added Sv57x4 support for G-stage page table

   - Added range based local HFENCE functions

   - Added remote HFENCE functions based on VCPU requests

   - Added ISA extension registers in ONE_REG interface

   - Updated KVM RISC-V maintainers entry to cover selftests support

  ARM:

   - Add support for the ARMv8.6 WFxT extension

   - Guard pages for the EL2 stacks

   - Trap and emulate AArch32 ID registers to hide unsupported features

   - Ability to select and save/restore the set of hypercalls exposed to
     the guest

   - Support for PSCI-initiated suspend in collaboration with userspace

   - GICv3 register-based LPI invalidation support

   - Move host PMU event merging into the vcpu data structure

   - GICv3 ITS save/restore fixes

   - The usual set of small-scale cleanups and fixes

  x86:

   - New ioctls to get/set TSC frequency for a whole VM

   - Allow userspace to opt out of hypercall patching

   - Only do MSR filtering for MSRs accessed by rdmsr/wrmsr

  AMD SEV improvements:

   - Add KVM_EXIT_SHUTDOWN metadata for SEV-ES

   - V_TSC_AUX support

  Nested virtualization improvements for AMD:

   - Support for "nested nested" optimizations (nested vVMLOAD/VMSAVE,
     nested vGIF)

   - Allow AVIC to co-exist with a nested guest running

   - Fixes for LBR virtualizations when a nested guest is running, and
     nested LBR virtualization support

   - PAUSE filtering for nested hypervisors

  Guest support:

   - Decoupling of vcpu_is_preempted from PV spinlocks"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (199 commits)
  KVM: x86: Fix the intel_pt PMI handling wrongly considered from guest
  KVM: selftests: x86: Sync the new name of the test case to .gitignore
  Documentation: kvm: reorder ARM-specific section about KVM_SYSTEM_EVENT_SUSPEND
  x86, kvm: use correct GFP flags for preemption disabled
  KVM: LAPIC: Drop pending LAPIC timer injection when canceling the timer
  x86/kvm: Alloc dummy async #PF token outside of raw spinlock
  KVM: x86: avoid calling x86 emulator without a decoded instruction
  KVM: SVM: Use kzalloc for sev ioctl interfaces to prevent kernel data leak
  x86/fpu: KVM: Set the base guest FPU uABI size to sizeof(struct kvm_xsave)
  s390/uv_uapi: depend on CONFIG_S390
  KVM: selftests: x86: Fix test failure on arch lbr capable platforms
  KVM: LAPIC: Trace LAPIC timer expiration on every vmentry
  KVM: s390: selftest: Test suppression indication on key prot exception
  KVM: s390: Don't indicate suppression on dirtying, failing memop
  selftests: drivers/s390x: Add uvdevice tests
  drivers/s390/char: Add Ultravisor io device
  MAINTAINERS: Update KVM RISC-V entry to cover selftests support
  RISC-V: KVM: Introduce ISA extension register
  RISC-V: KVM: Cleanup stale TLB entries when host CPU changes
  RISC-V: KVM: Add remote HFENCE functions based on VCPU requests
  ...

1 files changed, 49 insertions, 44 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4ff36610af6a..959d66b9be94 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -281,11 +281,11 @@ struct kvm_kernel_irq_routing_entry;
 /*
  * kvm_mmu_page_role tracks the properties of a shadow page (where shadow page
  * also includes TDP pages) to determine whether or not a page can be used in
- * the given MMU context.  This is a subset of the overall kvm_mmu_role to
+ * the given MMU context.  This is a subset of the overall kvm_cpu_role to
  * minimize the size of kvm_memory_slot.arch.gfn_track, i.e. allows allocating
  * 2 bytes per gfn instead of 4 bytes per gfn.
  *
- * Indirect upper-level shadow pages are tracked for write-protection via
+ * Upper-level shadow pages having gptes are tracked for write-protection via
  * gfn_track.  As above, gfn_track is a 16 bit counter, so KVM must not create
  * more than 2^16-1 upper-level shadow pages at a single gfn, otherwise
  * gfn_track will overflow and explosions will ensure.
@@ -331,7 +331,8 @@ union kvm_mmu_page_role {
 		unsigned smap_andnot_wp:1;
 		unsigned ad_disabled:1;
 		unsigned guest_mode:1;
-		unsigned :6;
+		unsigned passthrough:1;
+		unsigned :5;
 
 		/*
 		 * This is left at the top of the word so that
@@ -367,8 +368,6 @@ union kvm_mmu_extended_role {
 	struct {
 		unsigned int valid:1;
 		unsigned int execonly:1;
-		unsigned int cr0_pg:1;
-		unsigned int cr4_pae:1;
 		unsigned int cr4_pse:1;
 		unsigned int cr4_pke:1;
 		unsigned int cr4_smap:1;
@@ -378,7 +377,7 @@ union kvm_mmu_extended_role {
 	};
 };
 
-union kvm_mmu_role {
+union kvm_cpu_role {
 	u64 as_u64;
 	struct {
 		union kvm_mmu_page_role base;
@@ -438,19 +437,8 @@ struct kvm_mmu {
 			 struct kvm_mmu_page *sp);
 	void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa);
 	struct kvm_mmu_root_info root;
-	union kvm_mmu_role mmu_role;
-	u8 root_level;
-	u8 shadow_root_level;
-	u8 ept_ad;
-	bool direct_map;
-	struct kvm_mmu_root_info prev_roots[KVM_MMU_NUM_PREV_ROOTS];
-
-	/*
-	 * Bitmap; bit set = permission fault
-	 * Byte index: page fault error code [4:1]
-	 * Bit index: pte permissions in ACC_* format
-	 */
-	u8 permissions[16];
+	union kvm_cpu_role cpu_role;
+	union kvm_mmu_page_role root_role;
 
 	/*
 	* The pkru_mask indicates if protection key checks are needed.  It
@@ -460,6 +448,15 @@ struct kvm_mmu {
 	*/
 	u32 pkru_mask;
 
+	struct kvm_mmu_root_info prev_roots[KVM_MMU_NUM_PREV_ROOTS];
+
+	/*
+	 * Bitmap; bit set = permission fault
+	 * Byte index: page fault error code [4:1]
+	 * Bit index: pte permissions in ACC_* format
+	 */
+	u8 permissions[16];
+
 	u64 *pae_root;
 	u64 *pml4_root;
 	u64 *pml5_root;
@@ -607,16 +604,21 @@ struct kvm_vcpu_hv {
 struct kvm_vcpu_xen {
 	u64 hypercall_rip;
 	u32 current_runstate;
-	bool vcpu_info_set;
-	bool vcpu_time_info_set;
-	bool runstate_set;
-	struct gfn_to_hva_cache vcpu_info_cache;
-	struct gfn_to_hva_cache vcpu_time_info_cache;
-	struct gfn_to_hva_cache runstate_cache;
+	u8 upcall_vector;
+	struct gfn_to_pfn_cache vcpu_info_cache;
+	struct gfn_to_pfn_cache vcpu_time_info_cache;
+	struct gfn_to_pfn_cache runstate_cache;
 	u64 last_steal;
 	u64 runstate_entry_time;
 	u64 runstate_times[4];
 	unsigned long evtchn_pending_sel;
+	u32 vcpu_id; /* The Xen / ACPI vCPU ID */
+	u32 timer_virq;
+	u64 timer_expires; /* In guest epoch */
+	atomic_t timer_pending;
+	struct hrtimer timer;
+	int poll_evtchn;
+	struct timer_list poll_timer;
 };
 
 struct kvm_vcpu_arch {
@@ -753,8 +755,7 @@ struct kvm_vcpu_arch {
 	gpa_t time;
 	struct pvclock_vcpu_time_info hv_clock;
 	unsigned int hw_tsc_khz;
-	struct gfn_to_hva_cache pv_time;
-	bool pv_time_enabled;
+	struct gfn_to_pfn_cache pv_time;
 	/* set guest stopped flag in pvclock flags field */
 	bool pvclock_set_guest_stopped_request;
 
@@ -1024,9 +1025,12 @@ struct msr_bitmap_range {
 
 /* Xen emulation context */
 struct kvm_xen {
+	u32 xen_version;
 	bool long_mode;
 	u8 upcall_vector;
 	struct gfn_to_pfn_cache shinfo_cache;
+	struct idr evtchn_ports;
+	unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
 };
 
 enum kvm_irqchip_mode {
@@ -1119,6 +1123,8 @@ struct kvm_arch {
 	u64 cur_tsc_generation;
 	int nr_vcpus_matched_tsc;
 
+	u32 default_tsc_khz;
+
 	seqcount_raw_spinlock_t pvclock_sc;
 	bool use_master_clock;
 	u64 master_kernel_ns;
@@ -1263,7 +1269,12 @@ struct kvm_vm_stat {
 
 struct kvm_vcpu_stat {
 	struct kvm_vcpu_stat_generic generic;
+	u64 pf_taken;
 	u64 pf_fixed;
+	u64 pf_emulate;
+	u64 pf_spurious;
+	u64 pf_fast;
+	u64 pf_mmio_spte_created;
 	u64 pf_guest;
 	u64 tlb_flush;
 	u64 invlpg;
@@ -1455,8 +1466,6 @@ struct kvm_x86_ops {
 	int cpu_dirty_log_size;
 	void (*update_cpu_dirty_logging)(struct kvm_vcpu *vcpu);
 
-	/* pmu operations of sub-arch */
-	const struct kvm_pmu_ops *pmu_ops;
 	const struct kvm_x86_nested_ops *nested_ops;
 
 	void (*vcpu_blocking)(struct kvm_vcpu *vcpu);
@@ -1499,11 +1508,18 @@ struct kvm_x86_ops {
 	int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err);
 
 	void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
+
+	/*
+	 * Returns vCPU specific APICv inhibit reasons
+	 */
+	unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_x86_nested_ops {
 	void (*leave_nested)(struct kvm_vcpu *vcpu);
 	int (*check_events)(struct kvm_vcpu *vcpu);
+	bool (*handle_page_fault_workaround)(struct kvm_vcpu *vcpu,
+					     struct x86_exception *fault);
 	bool (*hv_timer_pending)(struct kvm_vcpu *vcpu);
 	void (*triple_fault)(struct kvm_vcpu *vcpu);
 	int (*get_state)(struct kvm_vcpu *vcpu,
@@ -1528,6 +1544,7 @@ struct kvm_x86_init_ops {
 	unsigned int (*handle_intel_pt_intr)(void);
 
 	struct kvm_x86_ops *runtime_ops;
+	struct kvm_pmu_ops *pmu_ops;
 };
 
 struct kvm_arch_async_pf {
@@ -1549,20 +1566,6 @@ extern struct kvm_x86_ops kvm_x86_ops;
 #define KVM_X86_OP_OPTIONAL_RET0 KVM_X86_OP
 #include <asm/kvm-x86-ops.h>
 
-static inline void kvm_ops_static_call_update(void)
-{
-#define __KVM_X86_OP(func) \
-	static_call_update(kvm_x86_##func, kvm_x86_ops.func);
-#define KVM_X86_OP(func) \
-	WARN_ON(!kvm_x86_ops.func); __KVM_X86_OP(func)
-#define KVM_X86_OP_OPTIONAL __KVM_X86_OP
-#define KVM_X86_OP_OPTIONAL_RET0(func) \
-	static_call_update(kvm_x86_##func, (void *)kvm_x86_ops.func ? : \
-					   (void *)__static_call_return0);
-#include <asm/kvm-x86-ops.h>
-#undef __KVM_X86_OP
-}
-
 #define __KVM_HAVE_ARCH_VM_ALLOC
 static inline struct kvm *kvm_arch_alloc_vm(void)
 {
@@ -1800,6 +1803,7 @@ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
 				struct x86_exception *exception);
 
 bool kvm_apicv_activated(struct kvm *kvm);
+bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu);
 void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu);
 void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
 				      enum kvm_apicv_inhibit reason, bool set);
@@ -1989,6 +1993,7 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
 	 KVM_X86_QUIRK_CD_NW_CLEARED |		\
 	 KVM_X86_QUIRK_LAPIC_MMIO_HOLE |	\
 	 KVM_X86_QUIRK_OUT_7E_INC_RIP |		\
-	 KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)
+	 KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT |	\
+	 KVM_X86_QUIRK_FIX_HYPERCALL_INSN)
 
 #endif /* _ASM_X86_KVM_HOST_H */