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

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - Proper emulation of the OSLock feature of the debug architecture

   - Scalibility improvements for the MMU lock when dirty logging is on

   - New VMID allocator, which will eventually help with SVA in VMs

   - Better support for PMUs in heterogenous systems

   - PSCI 1.1 support, enabling support for SYSTEM_RESET2

   - Implement CONFIG_DEBUG_LIST at EL2

   - Make CONFIG_ARM64_ERRATUM_2077057 default y

   - Reduce the overhead of VM exit when no interrupt is pending

   - Remove traces of 32bit ARM host support from the documentation

   - Updated vgic selftests

   - Various cleanups, doc updates and spelling fixes

  RISC-V:
   - Prevent KVM_COMPAT from being selected

   - Optimize __kvm_riscv_switch_to() implementation

   - RISC-V SBI v0.3 support

  s390:
   - memop selftest

   - fix SCK locking

   - adapter interruptions virtualization for secure guests

   - add Claudio Imbrenda as maintainer

   - first step to do proper storage key checking

  x86:
   - Continue switching kvm_x86_ops to static_call(); introduce
     static_call_cond() and __static_call_ret0 when applicable.

   - Cleanup unused arguments in several functions

   - Synthesize AMD 0x80000021 leaf

   - Fixes and optimization for Hyper-V sparse-bank hypercalls

   - Implement Hyper-V's enlightened MSR bitmap for nested SVM

   - Remove MMU auditing

   - Eager splitting of page tables (new aka "TDP" MMU only) when dirty
     page tracking is enabled

   - Cleanup the implementation of the guest PGD cache

   - Preparation for the implementation of Intel IPI virtualization

   - Fix some segment descriptor checks in the emulator

   - Allow AMD AVIC support on systems with physical APIC ID above 255

   - Better API to disable virtualization quirks

   - Fixes and optimizations for the zapping of page tables:

      - Zap roots in two passes, avoiding RCU read-side critical
        sections that last too long for very large guests backed by 4
        KiB SPTEs.

      - Zap invalid and defunct roots asynchronously via
        concurrency-managed work queue.

      - Allowing yielding when zapping TDP MMU roots in response to the
        root's last reference being put.

      - Batch more TLB flushes with an RCU trick. Whoever frees the
        paging structure now holds RCU as a proxy for all vCPUs running
        in the guest, i.e. to prolongs the grace period on their behalf.
        It then kicks the the vCPUs out of guest mode before doing
        rcu_read_unlock().

  Generic:
   - Introduce __vcalloc and use it for very large allocations that need
     memcg accounting"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (246 commits)
  KVM: use kvcalloc for array allocations
  KVM: x86: Introduce KVM_CAP_DISABLE_QUIRKS2
  kvm: x86: Require const tsc for RT
  KVM: x86: synthesize CPUID leaf 0x80000021h if useful
  KVM: x86: add support for CPUID leaf 0x80000021
  KVM: x86: do not use KVM_X86_OP_OPTIONAL_RET0 for get_mt_mask
  Revert "KVM: x86/mmu: Zap only TDP MMU leafs in kvm_zap_gfn_range()"
  kvm: x86/mmu: Flush TLB before zap_gfn_range releases RCU
  KVM: arm64: fix typos in comments
  KVM: arm64: Generalise VM features into a set of flags
  KVM: s390: selftests: Add error memop tests
  KVM: s390: selftests: Add more copy memop tests
  KVM: s390: selftests: Add named stages for memop test
  KVM: s390: selftests: Add macro as abstraction for MEM_OP
  KVM: s390: selftests: Split memop tests
  KVM: s390x: fix SCK locking
  RISC-V: KVM: Implement SBI HSM suspend call
  RISC-V: KVM: Add common kvm_riscv_vcpu_wfi() function
  RISC-V: Add SBI HSM suspend related defines
  RISC-V: KVM: Implement SBI v0.3 SRST extension
  ...

1 files changed, 63 insertions, 24 deletions

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index d8cf851ab119..1665a220abcb 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -362,6 +362,20 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	return vm;
 }
 
+struct kvm_vm *vm_create_without_vcpus(enum vm_guest_mode mode, uint64_t pages)
+{
+	struct kvm_vm *vm;
+
+	vm = vm_create(mode, pages, O_RDWR);
+
+	kvm_vm_elf_load(vm, program_invocation_name);
+
+#ifdef __x86_64__
+	vm_create_irqchip(vm);
+#endif
+	return vm;
+}
+
 /*
  * VM Create with customized parameters
  *
@@ -412,13 +426,8 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
 		    nr_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS));
 
 	pages = vm_adjust_num_guest_pages(mode, pages);
-	vm = vm_create(mode, pages, O_RDWR);
 
-	kvm_vm_elf_load(vm, program_invocation_name);
-
-#ifdef __x86_64__
-	vm_create_irqchip(vm);
-#endif
+	vm = vm_create_without_vcpus(mode, pages);
 
 	for (i = 0; i < nr_vcpus; ++i) {
 		uint32_t vcpuid = vcpuids ? vcpuids[i] : i;
@@ -709,6 +718,27 @@ void kvm_vm_free(struct kvm_vm *vmp)
 	free(vmp);
 }
 
+int kvm_memfd_alloc(size_t size, bool hugepages)
+{
+	int memfd_flags = MFD_CLOEXEC;
+	int fd, r;
+
+	if (hugepages)
+		memfd_flags |= MFD_HUGETLB;
+
+	fd = memfd_create("kvm_selftest", memfd_flags);
+	TEST_ASSERT(fd != -1, "memfd_create() failed, errno: %i (%s)",
+		    errno, strerror(errno));
+
+	r = ftruncate(fd, size);
+	TEST_ASSERT(!r, "ftruncate() failed, errno: %i (%s)", errno, strerror(errno));
+
+	r = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, size);
+	TEST_ASSERT(!r, "fallocate() failed, errno: %i (%s)", errno, strerror(errno));
+
+	return fd;
+}
+
 /*
  * Memory Compare, host virtual to guest virtual
  *
@@ -830,6 +860,30 @@ static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree,
 	rb_insert_color(&region->hva_node, hva_tree);
 }
 
+
+int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+				uint64_t gpa, uint64_t size, void *hva)
+{
+	struct kvm_userspace_memory_region region = {
+		.slot = slot,
+		.flags = flags,
+		.guest_phys_addr = gpa,
+		.memory_size = size,
+		.userspace_addr = (uintptr_t)hva,
+	};
+
+	return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region);
+}
+
+void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+			       uint64_t gpa, uint64_t size, void *hva)
+{
+	int ret = __vm_set_user_memory_region(vm, slot, flags, gpa, size, hva);
+
+	TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed, errno = %d (%s)",
+		    errno, strerror(errno));
+}
+
 /*
  * VM Userspace Memory Region Add
  *
@@ -937,24 +991,9 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 		region->mmap_size += alignment;
 
 	region->fd = -1;
-	if (backing_src_is_shared(src_type)) {
-		int memfd_flags = MFD_CLOEXEC;
-
-		if (src_type == VM_MEM_SRC_SHARED_HUGETLB)
-			memfd_flags |= MFD_HUGETLB;
-
-		region->fd = memfd_create("kvm_selftest", memfd_flags);
-		TEST_ASSERT(region->fd != -1,
-			    "memfd_create failed, errno: %i", errno);
-
-		ret = ftruncate(region->fd, region->mmap_size);
-		TEST_ASSERT(ret == 0, "ftruncate failed, errno: %i", errno);
-
-		ret = fallocate(region->fd,
-				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0,
-				region->mmap_size);
-		TEST_ASSERT(ret == 0, "fallocate failed, errno: %i", errno);
-	}
+	if (backing_src_is_shared(src_type))
+		region->fd = kvm_memfd_alloc(region->mmap_size,
+					     src_type == VM_MEM_SRC_SHARED_HUGETLB);
 
 	region->mmap_start = mmap(NULL, region->mmap_size,
 				  PROT_READ | PROT_WRITE,