Merge tag 'kvm-5.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "This is the first batch of KVM changes.

  ARM:
   - cleanups and corner case fixes.

  PPC:
   - Bugfixes

  x86:
   - Support for mapping DAX areas with large nested page table entries.

   - Cleanups and bugfixes here too. A particularly important one is a
     fix for FPU load when the thread has TIF_NEED_FPU_LOAD. There is
     also a race condition which could be used in guest userspace to
     exploit the guest kernel, for which the embargo expired today.

   - Fast path for IPI delivery vmexits, shaving about 200 clock cycles
     from IPI latency.

   - Protect against "Spectre-v1/L1TF" (bring data in the cache via
     speculative out of bound accesses, use L1TF on the sibling
     hyperthread to read it), which unfortunately is an even bigger
     whack-a-mole game than SpectreV1.

  Sean continues his mission to rewrite KVM. In addition to a sizable
  number of x86 patches, this time he contributed a pretty large
  refactoring of vCPU creation that affects all architectures but should
  not have any visible effect.

  s390 will come next week together with some more x86 patches"

* tag 'kvm-5.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (204 commits)
  x86/KVM: Clean up host's steal time structure
  x86/KVM: Make sure KVM_VCPU_FLUSH_TLB flag is not missed
  x86/kvm: Cache gfn to pfn translation
  x86/kvm: Introduce kvm_(un)map_gfn()
  x86/kvm: Be careful not to clear KVM_VCPU_FLUSH_TLB bit
  KVM: PPC: Book3S PR: Fix -Werror=return-type build failure
  KVM: PPC: Book3S HV: Release lock on page-out failure path
  KVM: arm64: Treat emulated TVAL TimerValue as a signed 32-bit integer
  KVM: arm64: pmu: Only handle supported event counters
  KVM: arm64: pmu: Fix chained SW_INCR counters
  KVM: arm64: pmu: Don't mark a counter as chained if the odd one is disabled
  KVM: arm64: pmu: Don't increment SW_INCR if PMCR.E is unset
  KVM: x86: Use a typedef for fastop functions
  KVM: X86: Add 'else' to unify fastop and execute call path
  KVM: x86: inline memslot_valid_for_gpte
  KVM: x86/mmu: Use huge pages for DAX-backed files
  KVM: x86/mmu: Remove lpage_is_disallowed() check from set_spte()
  KVM: x86/mmu: Fold max_mapping_level() into kvm_mmu_hugepage_adjust()
  KVM: x86/mmu: Zap any compound page when collapsing sptes
  KVM: x86/mmu: Remove obsolete gfn restoration in FNAME(fetch)
  ...

2 files changed, 55 insertions, 64 deletions

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 02f4c21c57f6..11ecc4071a29 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -914,7 +914,6 @@ extern int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc);
 
 static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
-static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 static inline void kvm_arch_free_memslot(struct kvm *kvm,
 		struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index d9e6bf3d54f0..8646c99217f2 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2530,9 +2530,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	if (vcpu->kvm->arch.use_cmma)
 		kvm_s390_vcpu_unsetup_cmma(vcpu);
 	free_page((unsigned long)(vcpu->arch.sie_block));
-
-	kvm_vcpu_uninit(vcpu);
-	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
 static void kvm_free_vcpus(struct kvm *kvm)
@@ -2541,7 +2538,7 @@ static void kvm_free_vcpus(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_arch_vcpu_destroy(vcpu);
+		kvm_vcpu_destroy(vcpu);
 
 	mutex_lock(&kvm->lock);
 	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
@@ -2703,39 +2700,6 @@ static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
 	return rc == 0 && id < KVM_S390_ESCA_CPU_SLOTS;
 }
 
-int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
-	kvm_clear_async_pf_completion_queue(vcpu);
-	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
-				    KVM_SYNC_GPRS |
-				    KVM_SYNC_ACRS |
-				    KVM_SYNC_CRS |
-				    KVM_SYNC_ARCH0 |
-				    KVM_SYNC_PFAULT;
-	kvm_s390_set_prefix(vcpu, 0);
-	if (test_kvm_facility(vcpu->kvm, 64))
-		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
-	if (test_kvm_facility(vcpu->kvm, 82))
-		vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC;
-	if (test_kvm_facility(vcpu->kvm, 133))
-		vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB;
-	if (test_kvm_facility(vcpu->kvm, 156))
-		vcpu->run->kvm_valid_regs |= KVM_SYNC_ETOKEN;
-	/* fprs can be synchronized via vrs, even if the guest has no vx. With
-	 * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format.
-	 */
-	if (MACHINE_HAS_VX)
-		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
-	else
-		vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS;
-
-	if (kvm_is_ucontrol(vcpu->kvm))
-		return __kvm_ucontrol_vcpu_init(vcpu);
-
-	return 0;
-}
-
 /* needs disabled preemption to protect from TOD sync and vcpu_load/put */
 static void __start_cpu_timer_accounting(struct kvm_vcpu *vcpu)
 {
@@ -2962,7 +2926,7 @@ static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->fac = (u32)(u64) model->fac_list;
 }
 
-int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
+static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	int rc = 0;
 
@@ -3035,26 +2999,22 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	return rc;
 }
 
-struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
-				      unsigned int id)
+int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
 {
-	struct kvm_vcpu *vcpu;
-	struct sie_page *sie_page;
-	int rc = -EINVAL;
-
 	if (!kvm_is_ucontrol(kvm) && !sca_can_add_vcpu(kvm, id))
-		goto out;
-
-	rc = -ENOMEM;
+		return -EINVAL;
+	return 0;
+}
 
-	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
-	if (!vcpu)
-		goto out;
+int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
+{
+	struct sie_page *sie_page;
+	int rc;
 
 	BUILD_BUG_ON(sizeof(struct sie_page) != 4096);
 	sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL);
 	if (!sie_page)
-		goto out_free_cpu;
+		return -ENOMEM;
 
 	vcpu->arch.sie_block = &sie_page->sie_block;
 	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
@@ -3063,27 +3023,59 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	vcpu->arch.sie_block->mso = 0;
 	vcpu->arch.sie_block->msl = sclp.hamax;
 
-	vcpu->arch.sie_block->icpua = id;
+	vcpu->arch.sie_block->icpua = vcpu->vcpu_id;
 	spin_lock_init(&vcpu->arch.local_int.lock);
-	vcpu->arch.sie_block->gd = (u32)(u64)kvm->arch.gisa_int.origin;
+	vcpu->arch.sie_block->gd = (u32)(u64)vcpu->kvm->arch.gisa_int.origin;
 	if (vcpu->arch.sie_block->gd && sclp.has_gisaf)
 		vcpu->arch.sie_block->gd |= GISA_FORMAT1;
 	seqcount_init(&vcpu->arch.cputm_seqcount);
 
-	rc = kvm_vcpu_init(vcpu, kvm, id);
+	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
+	kvm_clear_async_pf_completion_queue(vcpu);
+	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
+				    KVM_SYNC_GPRS |
+				    KVM_SYNC_ACRS |
+				    KVM_SYNC_CRS |
+				    KVM_SYNC_ARCH0 |
+				    KVM_SYNC_PFAULT;
+	kvm_s390_set_prefix(vcpu, 0);
+	if (test_kvm_facility(vcpu->kvm, 64))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
+	if (test_kvm_facility(vcpu->kvm, 82))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC;
+	if (test_kvm_facility(vcpu->kvm, 133))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB;
+	if (test_kvm_facility(vcpu->kvm, 156))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_ETOKEN;
+	/* fprs can be synchronized via vrs, even if the guest has no vx. With
+	 * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format.
+	 */
+	if (MACHINE_HAS_VX)
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
+	else
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS;
+
+	if (kvm_is_ucontrol(vcpu->kvm)) {
+		rc = __kvm_ucontrol_vcpu_init(vcpu);
+		if (rc)
+			goto out_free_sie_block;
+	}
+
+	VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK",
+		 vcpu->vcpu_id, vcpu, vcpu->arch.sie_block);
+	trace_kvm_s390_create_vcpu(vcpu->vcpu_id, vcpu, vcpu->arch.sie_block);
+
+	rc = kvm_s390_vcpu_setup(vcpu);
 	if (rc)
-		goto out_free_sie_block;
-	VM_EVENT(kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", id, vcpu,
-		 vcpu->arch.sie_block);
-	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
+		goto out_ucontrol_uninit;
+	return 0;
 
-	return vcpu;
+out_ucontrol_uninit:
+	if (kvm_is_ucontrol(vcpu->kvm))
+		gmap_remove(vcpu->arch.gmap);
 out_free_sie_block:
 	free_page((unsigned long)(vcpu->arch.sie_block));
-out_free_cpu:
-	kmem_cache_free(kvm_vcpu_cache, vcpu);
-out:
-	return ERR_PTR(rc);
+	return rc;
 }
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)