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

Pull kvm updates from Paolo Bonzini:
 "The first batch of KVM patches, mostly covering x86.

  ARM:

   - Account stage2 page table allocations in memory stats

  x86:

   - Account EPT/NPT arm64 page table allocations in memory stats

   - Tracepoint cleanups/fixes for nested VM-Enter and emulated MSR
     accesses

   - Drop eVMCS controls filtering for KVM on Hyper-V, all known
     versions of Hyper-V now support eVMCS fields associated with
     features that are enumerated to the guest

   - Use KVM's sanitized VMCS config as the basis for the values of
     nested VMX capabilities MSRs

   - A myriad event/exception fixes and cleanups. Most notably, pending
     exceptions morph into VM-Exits earlier, as soon as the exception is
     queued, instead of waiting until the next vmentry. This fixed a
     longstanding issue where the exceptions would incorrecly become
     double-faults instead of triggering a vmexit; the common case of
     page-fault vmexits had a special workaround, but now it's fixed for
     good

   - A handful of fixes for memory leaks in error paths

   - Cleanups for VMREAD trampoline and VMX's VM-Exit assembly flow

   - Never write to memory from non-sleepable kvm_vcpu_check_block()

   - Selftests refinements and cleanups

   - Misc typo cleanups

  Generic:

   - remove KVM_REQ_UNHALT"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (94 commits)
  KVM: remove KVM_REQ_UNHALT
  KVM: mips, x86: do not rely on KVM_REQ_UNHALT
  KVM: x86: never write to memory from kvm_vcpu_check_block()
  KVM: x86: Don't snapshot pending INIT/SIPI prior to checking nested events
  KVM: nVMX: Make event request on VMXOFF iff INIT/SIPI is pending
  KVM: nVMX: Make an event request if INIT or SIPI is pending on VM-Enter
  KVM: SVM: Make an event request if INIT or SIPI is pending when GIF is set
  KVM: x86: lapic does not have to process INIT if it is blocked
  KVM: x86: Rename kvm_apic_has_events() to make it INIT/SIPI specific
  KVM: x86: Rename and expose helper to detect if INIT/SIPI are allowed
  KVM: nVMX: Make an event request when pending an MTF nested VM-Exit
  KVM: x86: make vendor code check for all nested events
  mailmap: Update Oliver's email address
  KVM: x86: Allow force_emulation_prefix to be written without a reload
  KVM: selftests: Add an x86-only test to verify nested exception queueing
  KVM: selftests: Use uapi header to get VMX and SVM exit reasons/codes
  KVM: x86: Rename inject_pending_events() to kvm_check_and_inject_events()
  KVM: VMX: Update MTF and ICEBP comments to document KVM's subtle behavior
  KVM: x86: Treat pending TRIPLE_FAULT requests as pending exceptions
  KVM: x86: Morph pending exceptions to pending VM-Exits at queue time
  ...

3 files changed, 31 insertions, 5 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 3552e6af3684..6f81539061d6 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1667,6 +1667,18 @@ static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr)
 	percpu_counter_add(&kvm_total_used_mmu_pages, nr);
 }
 
+static void kvm_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	kvm_mod_used_mmu_pages(kvm, +1);
+	kvm_account_pgtable_pages((void *)sp->spt, +1);
+}
+
+static void kvm_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	kvm_mod_used_mmu_pages(kvm, -1);
+	kvm_account_pgtable_pages((void *)sp->spt, -1);
+}
+
 static void kvm_mmu_free_shadow_page(struct kvm_mmu_page *sp)
 {
 	MMU_WARN_ON(!is_empty_shadow_page(sp->spt));
@@ -2124,7 +2136,7 @@ static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm,
 	 */
 	sp->mmu_valid_gen = kvm->arch.mmu_valid_gen;
 	list_add(&sp->link, &kvm->arch.active_mmu_pages);
-	kvm_mod_used_mmu_pages(kvm, +1);
+	kvm_account_mmu_page(kvm, sp);
 
 	sp->gfn = gfn;
 	sp->role = role;
@@ -2458,7 +2470,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
 			list_add(&sp->link, invalid_list);
 		else
 			list_move(&sp->link, invalid_list);
-		kvm_mod_used_mmu_pages(kvm, -1);
+		kvm_unaccount_mmu_page(kvm, sp);
 	} else {
 		/*
 		 * Remove the active root from the active page list, the root
@@ -4292,7 +4304,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 
 	vcpu->arch.l1tf_flush_l1d = true;
 	if (!flags) {
-		trace_kvm_page_fault(fault_address, error_code);
+		trace_kvm_page_fault(vcpu, fault_address, error_code);
 
 		if (kvm_event_needs_reinjection(vcpu))
 			kvm_mmu_unprotect_page_virt(vcpu, fault_address);
@@ -6704,10 +6716,12 @@ int kvm_mmu_vendor_module_init(void)
 
 	ret = register_shrinker(&mmu_shrinker, "x86-mmu");
 	if (ret)
-		goto out;
+		goto out_shrinker;
 
 	return 0;
 
+out_shrinker:
+	percpu_counter_destroy(&kvm_total_used_mmu_pages);
 out:
 	mmu_destroy_caches();
 	return ret;
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 39e0205e7300..5ab5f94dcb6f 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -472,7 +472,7 @@ error:
 
 #if PTTYPE == PTTYPE_EPT
 	/*
-	 * Use PFERR_RSVD_MASK in error_code to to tell if EPT
+	 * Use PFERR_RSVD_MASK in error_code to tell if EPT
 	 * misconfiguration requires to be injected. The detection is
 	 * done by is_rsvd_bits_set() above.
 	 *
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index bf2ccf9debca..672f0432d777 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -372,6 +372,16 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
 	}
 }
 
+static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	kvm_account_pgtable_pages((void *)sp->spt, +1);
+}
+
+static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	kvm_account_pgtable_pages((void *)sp->spt, -1);
+}
+
 /**
  * tdp_mmu_unlink_sp() - Remove a shadow page from the list of used pages
  *
@@ -384,6 +394,7 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
 static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp,
 			      bool shared)
 {
+	tdp_unaccount_mmu_page(kvm, sp);
 	if (shared)
 		spin_lock(&kvm->arch.tdp_mmu_pages_lock);
 	else
@@ -1132,6 +1143,7 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
 	if (account_nx)
 		account_huge_nx_page(kvm, sp);
 	spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+	tdp_account_mmu_page(kvm, sp);
 
 	return 0;
 }