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

Pull kvm updates from Paolo Bonzini:
 "This covers all architectures (except MIPS) so I don't expect any
  other feature pull requests this merge window.

  ARM:

   - Add MTE support in guests, complete with tag save/restore interface

   - Reduce the impact of CMOs by moving them in the page-table code

   - Allow device block mappings at stage-2

   - Reduce the footprint of the vmemmap in protected mode

   - Support the vGIC on dumb systems such as the Apple M1

   - Add selftest infrastructure to support multiple configuration and
     apply that to PMU/non-PMU setups

   - Add selftests for the debug architecture

   - The usual crop of PMU fixes

  PPC:

   - Support for the H_RPT_INVALIDATE hypercall

   - Conversion of Book3S entry/exit to C

   - Bug fixes

  S390:

   - new HW facilities for guests

   - make inline assembly more robust with KASAN and co

  x86:

   - Allow userspace to handle emulation errors (unknown instructions)

   - Lazy allocation of the rmap (host physical -> guest physical
     address)

   - Support for virtualizing TSC scaling on VMX machines

   - Optimizations to avoid shattering huge pages at the beginning of
     live migration

   - Support for initializing the PDPTRs without loading them from
     memory

   - Many TLB flushing cleanups

   - Refuse to load if two-stage paging is available but NX is not (this
     has been a requirement in practice for over a year)

   - A large series that separates the MMU mode (WP/SMAP/SMEP etc.) from
     CR0/CR4/EFER, using the MMU mode everywhere once it is computed
     from the CPU registers

   - Use PM notifier to notify the guest about host suspend or hibernate

   - Support for passing arguments to Hyper-V hypercalls using XMM
     registers

   - Support for Hyper-V TLB flush hypercalls and enlightened MSR bitmap
     on AMD processors

   - Hide Hyper-V hypercalls that are not included in the guest CPUID

   - Fixes for live migration of virtual machines that use the Hyper-V
     "enlightened VMCS" optimization of nested virtualization

   - Bugfixes (not many)

  Generic:

   - Support for retrieving statistics without debugfs

   - Cleanups for the KVM selftests API"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (314 commits)
  KVM: x86: rename apic_access_page_done to apic_access_memslot_enabled
  kvm: x86: disable the narrow guest module parameter on unload
  selftests: kvm: Allows userspace to handle emulation errors.
  kvm: x86: Allow userspace to handle emulation errors
  KVM: x86/mmu: Let guest use GBPAGES if supported in hardware and TDP is on
  KVM: x86/mmu: Get CR4.SMEP from MMU, not vCPU, in shadow page fault
  KVM: x86/mmu: Get CR0.WP from MMU, not vCPU, in shadow page fault
  KVM: x86/mmu: Drop redundant rsvd bits reset for nested NPT
  KVM: x86/mmu: Optimize and clean up so called "last nonleaf level" logic
  KVM: x86: Enhance comments for MMU roles and nested transition trickiness
  KVM: x86/mmu: WARN on any reserved SPTE value when making a valid SPTE
  KVM: x86/mmu: Add helpers to do full reserved SPTE checks w/ generic MMU
  KVM: x86/mmu: Use MMU's role to determine PTTYPE
  KVM: x86/mmu: Collapse 32-bit PAE and 64-bit statements for helpers
  KVM: x86/mmu: Add a helper to calculate root from role_regs
  KVM: x86/mmu: Add helper to update paging metadata
  KVM: x86/mmu: Don't update nested guest's paging bitmasks if CR0.PG=0
  KVM: x86/mmu: Consolidate reset_rsvds_bits_mask() calls
  KVM: x86/mmu: Use MMU role_regs to get LA57, and drop vCPU LA57 helper
  KVM: x86/mmu: Get nested MMU's root level from the MMU's role
  ...

1 files changed, 113 insertions, 15 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 8583ed3ff344..ae7735b490b4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -28,6 +28,7 @@
 #include <linux/rcuwait.h>
 #include <linux/refcount.h>
 #include <linux/nospec.h>
+#include <linux/notifier.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -304,7 +305,6 @@ struct kvm_vcpu {
 	struct pid __rcu *pid;
 	int sigset_active;
 	sigset_t sigset;
-	struct kvm_vcpu_stat stat;
 	unsigned int halt_poll_ns;
 	bool valid_wakeup;
 
@@ -341,6 +341,8 @@ struct kvm_vcpu {
 	bool preempted;
 	bool ready;
 	struct kvm_vcpu_arch arch;
+	struct kvm_vcpu_stat stat;
+	char stats_id[KVM_STATS_NAME_SIZE];
 	struct kvm_dirty_ring dirty_ring;
 };
 
@@ -523,6 +525,15 @@ struct kvm {
 #endif /* KVM_HAVE_MMU_RWLOCK */
 
 	struct mutex slots_lock;
+
+	/*
+	 * Protects the arch-specific fields of struct kvm_memory_slots in
+	 * use by the VM. To be used under the slots_lock (above) or in a
+	 * kvm->srcu critical section where acquiring the slots_lock would
+	 * lead to deadlock with the synchronize_srcu in
+	 * install_new_memslots.
+	 */
+	struct mutex slots_arch_lock;
 	struct mm_struct *mm; /* userspace tied to this vm */
 	struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
 	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
@@ -585,6 +596,11 @@ struct kvm {
 	pid_t userspace_pid;
 	unsigned int max_halt_poll_ns;
 	u32 dirty_ring_size;
+
+#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
+	struct notifier_block pm_notifier;
+#endif
+	char stats_id[KVM_STATS_NAME_SIZE];
 };
 
 #define kvm_err(fmt, ...) \
@@ -998,6 +1014,10 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
 
+#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
+int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state);
+#endif
+
 #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS
 void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry);
 #endif
@@ -1244,26 +1264,104 @@ enum kvm_stat_kind {
 
 struct kvm_stat_data {
 	struct kvm *kvm;
-	struct kvm_stats_debugfs_item *dbgfs_item;
-};
-
-struct kvm_stats_debugfs_item {
-	const char *name;
-	int offset;
+	const struct _kvm_stats_desc *desc;
 	enum kvm_stat_kind kind;
-	int mode;
 };
 
-#define KVM_DBGFS_GET_MODE(dbgfs_item)                                         \
-	((dbgfs_item)->mode ? (dbgfs_item)->mode : 0644)
+struct _kvm_stats_desc {
+	struct kvm_stats_desc desc;
+	char name[KVM_STATS_NAME_SIZE];
+};
 
-#define VM_STAT(n, x, ...) 							\
-	{ n, offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ }
-#define VCPU_STAT(n, x, ...)							\
-	{ n, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ }
+#define STATS_DESC_COMMON(type, unit, base, exp)			       \
+	.flags = type | unit | base |					       \
+		 BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) |	       \
+		 BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) |	       \
+		 BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK),	       \
+	.exponent = exp,						       \
+	.size = 1
+
+#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp)		       \
+	{								       \
+		{							       \
+			STATS_DESC_COMMON(type, unit, base, exp),	       \
+			.offset = offsetof(struct kvm_vm_stat, generic.stat)   \
+		},							       \
+		.name = #stat,						       \
+	}
+#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp)		       \
+	{								       \
+		{							       \
+			STATS_DESC_COMMON(type, unit, base, exp),	       \
+			.offset = offsetof(struct kvm_vcpu_stat, generic.stat) \
+		},							       \
+		.name = #stat,						       \
+	}
+#define VM_STATS_DESC(stat, type, unit, base, exp)			       \
+	{								       \
+		{							       \
+			STATS_DESC_COMMON(type, unit, base, exp),	       \
+			.offset = offsetof(struct kvm_vm_stat, stat)	       \
+		},							       \
+		.name = #stat,						       \
+	}
+#define VCPU_STATS_DESC(stat, type, unit, base, exp)			       \
+	{								       \
+		{							       \
+			STATS_DESC_COMMON(type, unit, base, exp),	       \
+			.offset = offsetof(struct kvm_vcpu_stat, stat)	       \
+		},							       \
+		.name = #stat,						       \
+	}
+/* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */
+#define STATS_DESC(SCOPE, stat, type, unit, base, exp)			       \
+	SCOPE##_STATS_DESC(stat, type, unit, base, exp)
+
+#define STATS_DESC_CUMULATIVE(SCOPE, name, unit, base, exponent)	       \
+	STATS_DESC(SCOPE, name, KVM_STATS_TYPE_CUMULATIVE, unit, base, exponent)
+#define STATS_DESC_INSTANT(SCOPE, name, unit, base, exponent)		       \
+	STATS_DESC(SCOPE, name, KVM_STATS_TYPE_INSTANT, unit, base, exponent)
+#define STATS_DESC_PEAK(SCOPE, name, unit, base, exponent)		       \
+	STATS_DESC(SCOPE, name, KVM_STATS_TYPE_PEAK, unit, base, exponent)
+
+/* Cumulative counter, read/write */
+#define STATS_DESC_COUNTER(SCOPE, name)					       \
+	STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_NONE,		       \
+		KVM_STATS_BASE_POW10, 0)
+/* Instantaneous counter, read only */
+#define STATS_DESC_ICOUNTER(SCOPE, name)				       \
+	STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_NONE,		       \
+		KVM_STATS_BASE_POW10, 0)
+/* Peak counter, read/write */
+#define STATS_DESC_PCOUNTER(SCOPE, name)				       \
+	STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE,		       \
+		KVM_STATS_BASE_POW10, 0)
+
+/* Cumulative time in nanosecond */
+#define STATS_DESC_TIME_NSEC(SCOPE, name)				       \
+	STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS,	       \
+		KVM_STATS_BASE_POW10, -9)
+
+#define KVM_GENERIC_VM_STATS()						       \
+	STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush)
+
+#define KVM_GENERIC_VCPU_STATS()					       \
+	STATS_DESC_COUNTER(VCPU_GENERIC, halt_successful_poll),		       \
+	STATS_DESC_COUNTER(VCPU_GENERIC, halt_attempted_poll),		       \
+	STATS_DESC_COUNTER(VCPU_GENERIC, halt_poll_invalid),		       \
+	STATS_DESC_COUNTER(VCPU_GENERIC, halt_wakeup),			       \
+	STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_success_ns),	       \
+	STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns)
 
-extern struct kvm_stats_debugfs_item debugfs_entries[];
 extern struct dentry *kvm_debugfs_dir;
+ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
+		       const struct _kvm_stats_desc *desc,
+		       void *stats, size_t size_stats,
+		       char __user *user_buffer, size_t size, loff_t *offset);
+extern const struct kvm_stats_header kvm_vm_stats_header;
+extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
+extern const struct kvm_stats_header kvm_vcpu_stats_header;
+extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
 
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)