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

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - Move the arch-specific code into arch/arm64/kvm

   - Start the post-32bit cleanup

   - Cherry-pick a few non-invasive pre-NV patches

  x86:
   - Rework of TLB flushing

   - Rework of event injection, especially with respect to nested
     virtualization

   - Nested AMD event injection facelift, building on the rework of
     generic code and fixing a lot of corner cases

   - Nested AMD live migration support

   - Optimization for TSC deadline MSR writes and IPIs

   - Various cleanups

   - Asynchronous page fault cleanups (from tglx, common topic branch
     with tip tree)

   - Interrupt-based delivery of asynchronous "page ready" events (host
     side)

   - Hyper-V MSRs and hypercalls for guest debugging

   - VMX preemption timer fixes

  s390:
   - Cleanups

  Generic:
   - switch vCPU thread wakeup from swait to rcuwait

  The other architectures, and the guest side of the asynchronous page
  fault work, will come next week"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (256 commits)
  KVM: selftests: fix rdtsc() for vmx_tsc_adjust_test
  KVM: check userspace_addr for all memslots
  KVM: selftests: update hyperv_cpuid with SynDBG tests
  x86/kvm/hyper-v: Add support for synthetic debugger via hypercalls
  x86/kvm/hyper-v: enable hypercalls regardless of hypercall page
  x86/kvm/hyper-v: Add support for synthetic debugger interface
  x86/hyper-v: Add synthetic debugger definitions
  KVM: selftests: VMX preemption timer migration test
  KVM: nVMX: Fix VMX preemption timer migration
  x86/kvm/hyper-v: Explicitly align hcall param for kvm_hyperv_exit
  KVM: x86/pmu: Support full width counting
  KVM: x86/pmu: Tweak kvm_pmu_get_msr to pass 'struct msr_data' in
  KVM: x86: announce KVM_FEATURE_ASYNC_PF_INT
  KVM: x86: acknowledgment mechanism for async pf page ready notifications
  KVM: x86: interrupt based APF 'page ready' event delivery
  KVM: introduce kvm_read_guest_offset_cached()
  KVM: rename kvm_arch_can_inject_async_page_present() to kvm_arch_can_dequeue_async_page_present()
  KVM: x86: extend struct kvm_vcpu_pv_apf_data with token info
  Revert "KVM: async_pf: Fix #DF due to inject "Page not Present" and "Page Ready" exceptions simultaneously"
  KVM: VMX: Replace zero-length array with flexible-array
  ...

3 files changed, 90 insertions, 77 deletions

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 9622431069bc..c9cede5c7d0d 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -161,6 +161,9 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	vm = calloc(1, sizeof(*vm));
 	TEST_ASSERT(vm != NULL, "Insufficient Memory");
 
+	INIT_LIST_HEAD(&vm->vcpus);
+	INIT_LIST_HEAD(&vm->userspace_mem_regions);
+
 	vm->mode = mode;
 	vm->type = 0;
 
@@ -258,8 +261,7 @@ void kvm_vm_restart(struct kvm_vm *vmp, int perm)
 	if (vmp->has_irqchip)
 		vm_create_irqchip(vmp);
 
-	for (region = vmp->userspace_mem_region_head; region;
-		region = region->next) {
+	list_for_each_entry(region, &vmp->userspace_mem_regions, list) {
 		int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
 		TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
 			    "  rc: %i errno: %i\n"
@@ -319,8 +321,7 @@ userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end)
 {
 	struct userspace_mem_region *region;
 
-	for (region = vm->userspace_mem_region_head; region;
-		region = region->next) {
+	list_for_each_entry(region, &vm->userspace_mem_regions, list) {
 		uint64_t existing_start = region->region.guest_phys_addr;
 		uint64_t existing_end = region->region.guest_phys_addr
 			+ region->region.memory_size - 1;
@@ -378,11 +379,11 @@ kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
  */
 struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid)
 {
-	struct vcpu *vcpup;
+	struct vcpu *vcpu;
 
-	for (vcpup = vm->vcpu_head; vcpup; vcpup = vcpup->next) {
-		if (vcpup->id == vcpuid)
-			return vcpup;
+	list_for_each_entry(vcpu, &vm->vcpus, list) {
+		if (vcpu->id == vcpuid)
+			return vcpu;
 	}
 
 	return NULL;
@@ -392,18 +393,16 @@ struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid)
  * VM VCPU Remove
  *
  * Input Args:
- *   vm - Virtual Machine
- *   vcpuid - VCPU ID
+ *   vcpu - VCPU to remove
  *
  * Output Args: None
  *
  * Return: None, TEST_ASSERT failures for all error conditions
  *
- * Within the VM specified by vm, removes the VCPU given by vcpuid.
+ * Removes a vCPU from a VM and frees its resources.
  */
-static void vm_vcpu_rm(struct kvm_vm *vm, uint32_t vcpuid)
+static void vm_vcpu_rm(struct vcpu *vcpu)
 {
-	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
 
 	ret = munmap(vcpu->state, sizeof(*vcpu->state));
@@ -413,21 +412,17 @@ static void vm_vcpu_rm(struct kvm_vm *vm, uint32_t vcpuid)
 	TEST_ASSERT(ret == 0, "Close of VCPU fd failed, rc: %i "
 		"errno: %i", ret, errno);
 
-	if (vcpu->next)
-		vcpu->next->prev = vcpu->prev;
-	if (vcpu->prev)
-		vcpu->prev->next = vcpu->next;
-	else
-		vm->vcpu_head = vcpu->next;
+	list_del(&vcpu->list);
 	free(vcpu);
 }
 
 void kvm_vm_release(struct kvm_vm *vmp)
 {
+	struct vcpu *vcpu, *tmp;
 	int ret;
 
-	while (vmp->vcpu_head)
-		vm_vcpu_rm(vmp, vmp->vcpu_head->id);
+	list_for_each_entry_safe(vcpu, tmp, &vmp->vcpus, list)
+		vm_vcpu_rm(vcpu);
 
 	ret = close(vmp->fd);
 	TEST_ASSERT(ret == 0, "Close of vm fd failed,\n"
@@ -438,35 +433,38 @@ void kvm_vm_release(struct kvm_vm *vmp)
 		"  vmp->kvm_fd: %i rc: %i errno: %i", vmp->kvm_fd, ret, errno);
 }
 
+static void __vm_mem_region_delete(struct kvm_vm *vm,
+				   struct userspace_mem_region *region)
+{
+	int ret;
+
+	list_del(&region->list);
+
+	region->region.memory_size = 0;
+	ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
+	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed, "
+		    "rc: %i errno: %i", ret, errno);
+
+	sparsebit_free(&region->unused_phy_pages);
+	ret = munmap(region->mmap_start, region->mmap_size);
+	TEST_ASSERT(ret == 0, "munmap failed, rc: %i errno: %i", ret, errno);
+
+	free(region);
+}
+
 /*
  * Destroys and frees the VM pointed to by vmp.
  */
 void kvm_vm_free(struct kvm_vm *vmp)
 {
-	int ret;
+	struct userspace_mem_region *region, *tmp;
 
 	if (vmp == NULL)
 		return;
 
 	/* Free userspace_mem_regions. */
-	while (vmp->userspace_mem_region_head) {
-		struct userspace_mem_region *region
-			= vmp->userspace_mem_region_head;
-
-		region->region.memory_size = 0;
-		ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION,
-			&region->region);
-		TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed, "
-			"rc: %i errno: %i", ret, errno);
-
-		vmp->userspace_mem_region_head = region->next;
-		sparsebit_free(&region->unused_phy_pages);
-		ret = munmap(region->mmap_start, region->mmap_size);
-		TEST_ASSERT(ret == 0, "munmap failed, rc: %i errno: %i",
-			    ret, errno);
-
-		free(region);
-	}
+	list_for_each_entry_safe(region, tmp, &vmp->userspace_mem_regions, list)
+		__vm_mem_region_delete(vmp, region);
 
 	/* Free sparsebit arrays. */
 	sparsebit_free(&vmp->vpages_valid);
@@ -612,12 +610,10 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 			(uint64_t) region->region.memory_size);
 
 	/* Confirm no region with the requested slot already exists. */
-	for (region = vm->userspace_mem_region_head; region;
-		region = region->next) {
-		if (region->region.slot == slot)
-			break;
-	}
-	if (region != NULL)
+	list_for_each_entry(region, &vm->userspace_mem_regions, list) {
+		if (region->region.slot != slot)
+			continue;
+
 		TEST_FAIL("A mem region with the requested slot "
 			"already exists.\n"
 			"  requested slot: %u paddr: 0x%lx npages: 0x%lx\n"
@@ -626,6 +622,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 			region->region.slot,
 			(uint64_t) region->region.guest_phys_addr,
 			(uint64_t) region->region.memory_size);
+	}
 
 	/* Allocate and initialize new mem region structure. */
 	region = calloc(1, sizeof(*region));
@@ -686,10 +683,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 		guest_paddr, (uint64_t) region->region.memory_size);
 
 	/* Add to linked-list of memory regions. */
-	if (vm->userspace_mem_region_head)
-		vm->userspace_mem_region_head->prev = region;
-	region->next = vm->userspace_mem_region_head;
-	vm->userspace_mem_region_head = region;
+	list_add(&region->list, &vm->userspace_mem_regions);
 }
 
 /*
@@ -712,20 +706,17 @@ memslot2region(struct kvm_vm *vm, uint32_t memslot)
 {
 	struct userspace_mem_region *region;
 
-	for (region = vm->userspace_mem_region_head; region;
-		region = region->next) {
+	list_for_each_entry(region, &vm->userspace_mem_regions, list) {
 		if (region->region.slot == memslot)
-			break;
-	}
-	if (region == NULL) {
-		fprintf(stderr, "No mem region with the requested slot found,\n"
-			"  requested slot: %u\n", memslot);
-		fputs("---- vm dump ----\n", stderr);
-		vm_dump(stderr, vm, 2);
-		TEST_FAIL("Mem region not found");
+			return region;
 	}
 
-	return region;
+	fprintf(stderr, "No mem region with the requested slot found,\n"
+		"  requested slot: %u\n", memslot);
+	fputs("---- vm dump ----\n", stderr);
+	vm_dump(stderr, vm, 2);
+	TEST_FAIL("Mem region not found");
+	return NULL;
 }
 
 /*
@@ -789,6 +780,24 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa)
 }
 
 /*
+ * VM Memory Region Delete
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   slot - Slot of the memory region to delete
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Delete a memory region.
+ */
+void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot)
+{
+	__vm_mem_region_delete(vm, memslot2region(vm, slot));
+}
+
+/*
  * VCPU mmap Size
  *
  * Input Args: None
@@ -863,10 +872,7 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid)
 		"vcpu id: %u errno: %i", vcpuid, errno);
 
 	/* Add to linked-list of VCPUs. */
-	if (vm->vcpu_head)
-		vm->vcpu_head->prev = vcpu;
-	vcpu->next = vm->vcpu_head;
-	vm->vcpu_head = vcpu;
+	list_add(&vcpu->list, &vm->vcpus);
 }
 
 /*
@@ -1059,8 +1065,8 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
 {
 	struct userspace_mem_region *region;
-	for (region = vm->userspace_mem_region_head; region;
-	     region = region->next) {
+
+	list_for_each_entry(region, &vm->userspace_mem_regions, list) {
 		if ((gpa >= region->region.guest_phys_addr)
 			&& (gpa <= (region->region.guest_phys_addr
 				+ region->region.memory_size - 1)))
@@ -1092,8 +1098,8 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
 vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva)
 {
 	struct userspace_mem_region *region;
-	for (region = vm->userspace_mem_region_head; region;
-	     region = region->next) {
+
+	list_for_each_entry(region, &vm->userspace_mem_regions, list) {
 		if ((hva >= region->host_mem)
 			&& (hva <= (region->host_mem
 				+ region->region.memory_size - 1)))
@@ -1529,8 +1535,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 	fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd);
 	fprintf(stream, "%*spage_size: 0x%x\n", indent, "", vm->page_size);
 	fprintf(stream, "%*sMem Regions:\n", indent, "");
-	for (region = vm->userspace_mem_region_head; region;
-		region = region->next) {
+	list_for_each_entry(region, &vm->userspace_mem_regions, list) {
 		fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx "
 			"host_virt: %p\n", indent + 2, "",
 			(uint64_t) region->region.guest_phys_addr,
@@ -1549,7 +1554,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 		virt_dump(stream, vm, indent + 4);
 	}
 	fprintf(stream, "%*sVCPUs:\n", indent, "");
-	for (vcpu = vm->vcpu_head; vcpu; vcpu = vcpu->next)
+	list_for_each_entry(vcpu, &vm->vcpus, list)
 		vcpu_dump(stream, vm, vcpu->id, indent + 2);
 }
 
@@ -1743,6 +1748,11 @@ unsigned int vm_get_max_gfn(struct kvm_vm *vm)
 	return vm->max_gfn;
 }
 
+int vm_get_fd(struct kvm_vm *vm)
+{
+	return vm->fd;
+}
+
 static unsigned int vm_calc_num_pages(unsigned int num_pages,
 				      unsigned int page_shift,
 				      unsigned int new_page_shift,
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index ca56a0133127..2ef446520748 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -13,7 +13,6 @@
 #define KVM_DEV_PATH		"/dev/kvm"
 
 struct userspace_mem_region {
-	struct userspace_mem_region *next, *prev;
 	struct kvm_userspace_memory_region region;
 	struct sparsebit *unused_phy_pages;
 	int fd;
@@ -21,10 +20,11 @@ struct userspace_mem_region {
 	void *host_mem;
 	void *mmap_start;
 	size_t mmap_size;
+	struct list_head list;
 };
 
 struct vcpu {
-	struct vcpu *next, *prev;
+	struct list_head list;
 	uint32_t id;
 	int fd;
 	struct kvm_run *state;
@@ -41,8 +41,8 @@ struct kvm_vm {
 	unsigned int pa_bits;
 	unsigned int va_bits;
 	uint64_t max_gfn;
-	struct vcpu *vcpu_head;
-	struct userspace_mem_region *userspace_mem_region_head;
+	struct list_head vcpus;
+	struct list_head userspace_mem_regions;
 	struct sparsebit *vpages_valid;
 	struct sparsebit *vpages_mapped;
 	bool has_irqchip;
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index 8d94961bd046..a88c5d665725 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -233,7 +233,10 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
 
 void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
 {
-	struct vcpu *vcpu = vm->vcpu_head;
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+
+	if (!vcpu)
+		return;
 
 	fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n",
 		indent, "", vcpu->state->psw_mask, vcpu->state->psw_addr);