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
  ...

2 files changed, 32 insertions, 5 deletions

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 917086be5c6b..446f628a9de1 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -666,7 +666,6 @@ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu)
 
 	kvm_vcpu_halt(vcpu);
 	vcpu_clear_flag(vcpu, IN_WFIT);
-	kvm_clear_request(KVM_REQ_UNHALT, vcpu);
 
 	preempt_disable();
 	vgic_v4_load(vcpu);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index c9a13e487187..34c5feed9dc1 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -92,9 +92,13 @@ static bool kvm_is_device_pfn(unsigned long pfn)
 static void *stage2_memcache_zalloc_page(void *arg)
 {
 	struct kvm_mmu_memory_cache *mc = arg;
+	void *virt;
 
 	/* Allocated with __GFP_ZERO, so no need to zero */
-	return kvm_mmu_memory_cache_alloc(mc);
+	virt = kvm_mmu_memory_cache_alloc(mc);
+	if (virt)
+		kvm_account_pgtable_pages(virt, 1);
+	return virt;
 }
 
 static void *kvm_host_zalloc_pages_exact(size_t size)
@@ -102,6 +106,21 @@ static void *kvm_host_zalloc_pages_exact(size_t size)
 	return alloc_pages_exact(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
 }
 
+static void *kvm_s2_zalloc_pages_exact(size_t size)
+{
+	void *virt = kvm_host_zalloc_pages_exact(size);
+
+	if (virt)
+		kvm_account_pgtable_pages(virt, (size >> PAGE_SHIFT));
+	return virt;
+}
+
+static void kvm_s2_free_pages_exact(void *virt, size_t size)
+{
+	kvm_account_pgtable_pages(virt, -(size >> PAGE_SHIFT));
+	free_pages_exact(virt, size);
+}
+
 static void kvm_host_get_page(void *addr)
 {
 	get_page(virt_to_page(addr));
@@ -112,6 +131,15 @@ static void kvm_host_put_page(void *addr)
 	put_page(virt_to_page(addr));
 }
 
+static void kvm_s2_put_page(void *addr)
+{
+	struct page *p = virt_to_page(addr);
+	/* Dropping last refcount, the page will be freed */
+	if (page_count(p) == 1)
+		kvm_account_pgtable_pages(addr, -1);
+	put_page(p);
+}
+
 static int kvm_host_page_count(void *addr)
 {
 	return page_count(virt_to_page(addr));
@@ -625,10 +653,10 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr)
 
 static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
 	.zalloc_page		= stage2_memcache_zalloc_page,
-	.zalloc_pages_exact	= kvm_host_zalloc_pages_exact,
-	.free_pages_exact	= free_pages_exact,
+	.zalloc_pages_exact	= kvm_s2_zalloc_pages_exact,
+	.free_pages_exact	= kvm_s2_free_pages_exact,
 	.get_page		= kvm_host_get_page,
-	.put_page		= kvm_host_put_page,
+	.put_page		= kvm_s2_put_page,
 	.page_count		= kvm_host_page_count,
 	.phys_to_virt		= kvm_host_va,
 	.virt_to_phys		= kvm_host_pa,