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

Pull KVM updates from Paolo Bonzini:
 "For x86, there is a new alternative and (in the future) more scalable
  implementation of extended page tables that does not need a reverse
  map from guest physical addresses to host physical addresses.

  For now it is disabled by default because it is still lacking a few of
  the existing MMU's bells and whistles. However it is a very solid
  piece of work and it is already available for people to hammer on it.

  Other updates:

  ARM:
   - New page table code for both hypervisor and guest stage-2
   - Introduction of a new EL2-private host context
   - Allow EL2 to have its own private per-CPU variables
   - Support of PMU event filtering
   - Complete rework of the Spectre mitigation

  PPC:
   - Fix for running nested guests with in-kernel IRQ chip
   - Fix race condition causing occasional host hard lockup
   - Minor cleanups and bugfixes

  x86:
   - allow trapping unknown MSRs to userspace
   - allow userspace to force #GP on specific MSRs
   - INVPCID support on AMD
   - nested AMD cleanup, on demand allocation of nested SVM state
   - hide PV MSRs and hypercalls for features not enabled in CPUID
   - new test for MSR_IA32_TSC writes from host and guest
   - cleanups: MMU, CPUID, shared MSRs
   - LAPIC latency optimizations ad bugfixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (232 commits)
  kvm: x86/mmu: NX largepage recovery for TDP MMU
  kvm: x86/mmu: Don't clear write flooding count for direct roots
  kvm: x86/mmu: Support MMIO in the TDP MMU
  kvm: x86/mmu: Support write protection for nesting in tdp MMU
  kvm: x86/mmu: Support disabling dirty logging for the tdp MMU
  kvm: x86/mmu: Support dirty logging for the TDP MMU
  kvm: x86/mmu: Support changed pte notifier in tdp MMU
  kvm: x86/mmu: Add access tracking for tdp_mmu
  kvm: x86/mmu: Support invalidate range MMU notifier for TDP MMU
  kvm: x86/mmu: Allocate struct kvm_mmu_pages for all pages in TDP MMU
  kvm: x86/mmu: Add TDP MMU PF handler
  kvm: x86/mmu: Remove disallowed_hugepage_adjust shadow_walk_iterator arg
  kvm: x86/mmu: Support zapping SPTEs in the TDP MMU
  KVM: Cache as_id in kvm_memory_slot
  kvm: x86/mmu: Add functions to handle changed TDP SPTEs
  kvm: x86/mmu: Allocate and free TDP MMU roots
  kvm: x86/mmu: Init / Uninit the TDP MMU
  kvm: x86/mmu: Introduce tdp_iter
  KVM: mmu: extract spte.h and spte.c
  KVM: mmu: Separate updating a PTE from kvm_set_pte_rmapp
  ...

1 files changed, 58 insertions, 12 deletions

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index acf9a993dfb6..f56122eedffc 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -46,8 +46,10 @@
 __asm__(".arch_extension	virt");
 #endif
 
-DEFINE_PER_CPU(kvm_host_data_t, kvm_host_data);
+DECLARE_KVM_HYP_PER_CPU(unsigned long, kvm_hyp_vector);
+
 static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
+unsigned long kvm_arm_hyp_percpu_base[NR_CPUS];
 
 /* The VMID used in the VTTBR */
 static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
@@ -145,6 +147,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	int i;
 
+	bitmap_free(kvm->arch.pmu_filter);
+
 	kvm_vgic_destroy(kvm);
 
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
@@ -286,7 +290,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.has_run_once && unlikely(!irqchip_in_kernel(vcpu->kvm)))
 		static_branch_dec(&userspace_irqchip_in_use);
 
-	kvm_mmu_free_memory_caches(vcpu);
+	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_pmu_vcpu_destroy(vcpu);
 
@@ -1259,6 +1263,19 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	}
 }
 
+static unsigned long nvhe_percpu_size(void)
+{
+	return (unsigned long)CHOOSE_NVHE_SYM(__per_cpu_end) -
+		(unsigned long)CHOOSE_NVHE_SYM(__per_cpu_start);
+}
+
+static unsigned long nvhe_percpu_order(void)
+{
+	unsigned long size = nvhe_percpu_size();
+
+	return size ? get_order(size) : 0;
+}
+
 static int kvm_map_vectors(void)
 {
 	/*
@@ -1299,6 +1316,7 @@ static void cpu_init_hyp_mode(void)
 	unsigned long hyp_stack_ptr;
 	unsigned long vector_ptr;
 	unsigned long tpidr_el2;
+	struct arm_smccc_res res;
 
 	/* Switch from the HYP stub to our own HYP init vector */
 	__hyp_set_vectors(kvm_get_idmap_vector());
@@ -1308,12 +1326,13 @@ static void cpu_init_hyp_mode(void)
 	 * kernel's mapping to the linear mapping, and store it in tpidr_el2
 	 * so that we can use adr_l to access per-cpu variables in EL2.
 	 */
-	tpidr_el2 = ((unsigned long)this_cpu_ptr(&kvm_host_data) -
-		     (unsigned long)kvm_ksym_ref(&kvm_host_data));
+	tpidr_el2 = (unsigned long)this_cpu_ptr_nvhe_sym(__per_cpu_start) -
+		    (unsigned long)kvm_ksym_ref(CHOOSE_NVHE_SYM(__per_cpu_start));
 
 	pgd_ptr = kvm_mmu_get_httbr();
 	hyp_stack_ptr = __this_cpu_read(kvm_arm_hyp_stack_page) + PAGE_SIZE;
-	vector_ptr = (unsigned long)kvm_get_hyp_vector();
+	hyp_stack_ptr = kern_hyp_va(hyp_stack_ptr);
+	vector_ptr = (unsigned long)kern_hyp_va(kvm_ksym_ref(__kvm_hyp_host_vector));
 
 	/*
 	 * Call initialization code, and switch to the full blown HYP code.
@@ -1322,7 +1341,9 @@ static void cpu_init_hyp_mode(void)
 	 * cpus_have_const_cap() wrapper.
 	 */
 	BUG_ON(!system_capabilities_finalized());
-	__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr, tpidr_el2);
+	arm_smccc_1_1_hvc(KVM_HOST_SMCCC_FUNC(__kvm_hyp_init),
+			  pgd_ptr, tpidr_el2, hyp_stack_ptr, vector_ptr, &res);
+	WARN_ON(res.a0 != SMCCC_RET_SUCCESS);
 
 	/*
 	 * Disabling SSBD on a non-VHE system requires us to enable SSBS
@@ -1342,10 +1363,12 @@ static void cpu_hyp_reset(void)
 
 static void cpu_hyp_reinit(void)
 {
-	kvm_init_host_cpu_context(&this_cpu_ptr(&kvm_host_data)->host_ctxt);
+	kvm_init_host_cpu_context(&this_cpu_ptr_hyp_sym(kvm_host_data)->host_ctxt);
 
 	cpu_hyp_reset();
 
+	*this_cpu_ptr_hyp_sym(kvm_hyp_vector) = (unsigned long)kvm_get_hyp_vector();
+
 	if (is_kernel_in_hyp_mode())
 		kvm_timer_init_vhe();
 	else
@@ -1496,8 +1519,10 @@ static void teardown_hyp_mode(void)
 	int cpu;
 
 	free_hyp_pgds();
-	for_each_possible_cpu(cpu)
+	for_each_possible_cpu(cpu) {
 		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
+		free_pages(kvm_arm_hyp_percpu_base[cpu], nvhe_percpu_order());
+	}
 }
 
 /**
@@ -1531,6 +1556,24 @@ static int init_hyp_mode(void)
 	}
 
 	/*
+	 * Allocate and initialize pages for Hypervisor-mode percpu regions.
+	 */
+	for_each_possible_cpu(cpu) {
+		struct page *page;
+		void *page_addr;
+
+		page = alloc_pages(GFP_KERNEL, nvhe_percpu_order());
+		if (!page) {
+			err = -ENOMEM;
+			goto out_err;
+		}
+
+		page_addr = page_address(page);
+		memcpy(page_addr, CHOOSE_NVHE_SYM(__per_cpu_start), nvhe_percpu_size());
+		kvm_arm_hyp_percpu_base[cpu] = (unsigned long)page_addr;
+	}
+
+	/*
 	 * Map the Hyp-code called directly from the host
 	 */
 	err = create_hyp_mappings(kvm_ksym_ref(__hyp_text_start),
@@ -1574,14 +1617,17 @@ static int init_hyp_mode(void)
 		}
 	}
 
+	/*
+	 * Map Hyp percpu pages
+	 */
 	for_each_possible_cpu(cpu) {
-		kvm_host_data_t *cpu_data;
+		char *percpu_begin = (char *)kvm_arm_hyp_percpu_base[cpu];
+		char *percpu_end = percpu_begin + nvhe_percpu_size();
 
-		cpu_data = per_cpu_ptr(&kvm_host_data, cpu);
-		err = create_hyp_mappings(cpu_data, cpu_data + 1, PAGE_HYP);
+		err = create_hyp_mappings(percpu_begin, percpu_end, PAGE_HYP);
 
 		if (err) {
-			kvm_err("Cannot map host CPU state: %d\n", err);
+			kvm_err("Cannot map hyp percpu region\n");
 			goto out_err;
 		}
 	}