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

Pull more KVM updates from Paolo Bonzini:
 "x86:

   - take into account HVA before retrying on MMU notifier race

   - fixes for nested AMD guests without NPT

   - allow INVPCID in guest without PCID

   - disable PML in hardware when not in use

   - MMU code cleanups:

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (28 commits)
  KVM: SVM: Fix nested VM-Exit on #GP interception handling
  KVM: vmx/pmu: Fix dummy check if lbr_desc->event is created
  KVM: x86/mmu: Consider the hva in mmu_notifier retry
  KVM: x86/mmu: Skip mmu_notifier check when handling MMIO page fault
  KVM: Documentation: rectify rst markup in KVM_GET_SUPPORTED_HV_CPUID
  KVM: nSVM: prepare guest save area while is_guest_mode is true
  KVM: x86/mmu: Remove a variety of unnecessary exports
  KVM: x86: Fold "write-protect large" use case into generic write-protect
  KVM: x86/mmu: Don't set dirty bits when disabling dirty logging w/ PML
  KVM: VMX: Dynamically enable/disable PML based on memslot dirty logging
  KVM: x86: Further clarify the logic and comments for toggling log dirty
  KVM: x86: Move MMU's PML logic to common code
  KVM: x86/mmu: Make dirty log size hook (PML) a value, not a function
  KVM: x86/mmu: Expand on the comment in kvm_vcpu_ad_need_write_protect()
  KVM: nVMX: Disable PML in hardware when running L2
  KVM: x86/mmu: Consult max mapping level when zapping collapsible SPTEs
  KVM: x86/mmu: Pass the memslot to the rmap callbacks
  KVM: x86/mmu: Split out max mapping level calculation to helper
  KVM: x86/mmu: Expand collapsible SPTE zap for TDP MMU to ZONE_DEVICE and HugeTLB pages
  KVM: nVMX: no need to undo inject_page_fault change on nested vmexit
  ...

1 files changed, 24 insertions, 1 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index e126ebda36d0..1b65e7204344 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -11,6 +11,7 @@
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/bug.h>
+#include <linux/minmax.h>
 #include <linux/mm.h>
 #include <linux/mmu_notifier.h>
 #include <linux/preempt.h>
@@ -506,6 +507,8 @@ struct kvm {
 	struct mmu_notifier mmu_notifier;
 	unsigned long mmu_notifier_seq;
 	long mmu_notifier_count;
+	unsigned long mmu_notifier_range_start;
+	unsigned long mmu_notifier_range_end;
 #endif
 	long tlbs_dirty;
 	struct list_head devices;
@@ -733,7 +736,7 @@ kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
 kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn);
 kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn,
 			       bool atomic, bool *async, bool write_fault,
-			       bool *writable);
+			       bool *writable, hva_t *hva);
 
 void kvm_release_pfn_clean(kvm_pfn_t pfn);
 void kvm_release_pfn_dirty(kvm_pfn_t pfn);
@@ -1207,6 +1210,26 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
 		return 1;
 	return 0;
 }
+
+static inline int mmu_notifier_retry_hva(struct kvm *kvm,
+					 unsigned long mmu_seq,
+					 unsigned long hva)
+{
+	lockdep_assert_held(&kvm->mmu_lock);
+	/*
+	 * If mmu_notifier_count is non-zero, then the range maintained by
+	 * kvm_mmu_notifier_invalidate_range_start contains all addresses that
+	 * might be being invalidated. Note that it may include some false
+	 * positives, due to shortcuts when handing concurrent invalidations.
+	 */
+	if (unlikely(kvm->mmu_notifier_count) &&
+	    hva >= kvm->mmu_notifier_range_start &&
+	    hva < kvm->mmu_notifier_range_end)
+		return 1;
+	if (kvm->mmu_notifier_seq != mmu_seq)
+		return 1;
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING