From 1bcc3f87912779f66cdf1789a066046536ca6ccc Mon Sep 17 00:00:00 2001 From: Yan Zhao Date: Wed, 24 Sep 2025 10:42:55 -0700 Subject: KVM: selftests: Test prefault memory during concurrent memslot removal Expand the prefault memory selftest to add a regression test for a KVM bug where KVM's retry logic would result in (breakable) deadlock due to the memslot deletion waiting on prefaulting to release SRCU, and prefaulting waiting on the memslot to fully disappear (KVM uses a two-step process to delete memslots, and KVM x86 retries page faults if a to-be-deleted, a.k.a. INVALID, memslot is encountered). To exercise concurrent memslot remove, spawn a second thread to initiate memslot removal at roughly the same time as prefaulting. Test memslot removal for all testcases, i.e. don't limit concurrent removal to only the success case. There are essentially three prefault scenarios (so far) that are of interest: 1. Success 2. ENOENT due to no memslot 3. EAGAIN due to INVALID memslot For all intents and purposes, #1 and #2 are mutually exclusive, or rather, easier to test via separate testcases since writing to non-existent memory is trivial. But for #3, making it mutually exclusive with #1 _or_ #2 is actually more complex than testing memslot removal for all scenarios. The only requirement to let memslot removal coexist with other scenarios is a way to guarantee a stable result, e.g. that the "no memslot" test observes ENOENT, not EAGAIN, for the final checks. So, rather than make memslot removal mutually exclusive with the ENOENT scenario, simply restore the memslot and retry prefaulting. For the "no memslot" case, KVM_PRE_FAULT_MEMORY should be idempotent, i.e. should always fail with ENOENT regardless of how many times userspace attempts prefaulting. Pass in both the base GPA and the offset (instead of the "full" GPA) so that the worker can recreate the memslot. Signed-off-by: Yan Zhao Co-developed-by: Sean Christopherson Link: https://lore.kernel.org/r/20250924174255.2141847-1-seanjc@google.com Signed-off-by: Sean Christopherson --- .../testing/selftests/kvm/pre_fault_memory_test.c | 131 ++++++++++++++++++--- 1 file changed, 114 insertions(+), 17 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/kvm/pre_fault_memory_test.c b/tools/testing/selftests/kvm/pre_fault_memory_test.c index 0350a8896a2f..f04768c1d2e4 100644 --- a/tools/testing/selftests/kvm/pre_fault_memory_test.c +++ b/tools/testing/selftests/kvm/pre_fault_memory_test.c @@ -10,6 +10,7 @@ #include #include #include +#include /* Arbitrarily chosen values */ #define TEST_SIZE (SZ_2M + PAGE_SIZE) @@ -30,18 +31,66 @@ static void guest_code(uint64_t base_gpa) GUEST_DONE(); } -static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 gpa, u64 size, - u64 left) +struct slot_worker_data { + struct kvm_vm *vm; + u64 gpa; + uint32_t flags; + bool worker_ready; + bool prefault_ready; + bool recreate_slot; +}; + +static void *delete_slot_worker(void *__data) +{ + struct slot_worker_data *data = __data; + struct kvm_vm *vm = data->vm; + + WRITE_ONCE(data->worker_ready, true); + + while (!READ_ONCE(data->prefault_ready)) + cpu_relax(); + + vm_mem_region_delete(vm, TEST_SLOT); + + while (!READ_ONCE(data->recreate_slot)) + cpu_relax(); + + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, data->gpa, + TEST_SLOT, TEST_NPAGES, data->flags); + + return NULL; +} + +static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 base_gpa, u64 offset, + u64 size, u64 expected_left, bool private) { struct kvm_pre_fault_memory range = { - .gpa = gpa, + .gpa = base_gpa + offset, .size = size, .flags = 0, }; - u64 prev; + struct slot_worker_data data = { + .vm = vcpu->vm, + .gpa = base_gpa, + .flags = private ? KVM_MEM_GUEST_MEMFD : 0, + }; + bool slot_recreated = false; + pthread_t slot_worker; int ret, save_errno; + u64 prev; + + /* + * Concurrently delete (and recreate) the slot to test KVM's handling + * of a racing memslot deletion with prefaulting. + */ + pthread_create(&slot_worker, NULL, delete_slot_worker, &data); - do { + while (!READ_ONCE(data.worker_ready)) + cpu_relax(); + + WRITE_ONCE(data.prefault_ready, true); + + for (;;) { prev = range.size; ret = __vcpu_ioctl(vcpu, KVM_PRE_FAULT_MEMORY, &range); save_errno = errno; @@ -49,18 +98,65 @@ static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 gpa, u64 size, "%sexpecting range.size to change on %s", ret < 0 ? "not " : "", ret < 0 ? "failure" : "success"); - } while (ret >= 0 ? range.size : save_errno == EINTR); - TEST_ASSERT(range.size == left, - "Completed with %lld bytes left, expected %" PRId64, - range.size, left); + /* + * Immediately retry prefaulting if KVM was interrupted by an + * unrelated signal/event. + */ + if (ret < 0 && save_errno == EINTR) + continue; + + /* + * Tell the worker to recreate the slot in order to complete + * prefaulting (if prefault didn't already succeed before the + * slot was deleted) and/or to prepare for the next testcase. + * Wait for the worker to exit so that the next invocation of + * prefaulting is guaranteed to complete (assuming no KVM bugs). + */ + if (!slot_recreated) { + WRITE_ONCE(data.recreate_slot, true); + pthread_join(slot_worker, NULL); + slot_recreated = true; + + /* + * Retry prefaulting to get a stable result, i.e. to + * avoid seeing random EAGAIN failures. Don't retry if + * prefaulting already succeeded, as KVM disallows + * prefaulting with size=0, i.e. blindly retrying would + * result in test failures due to EINVAL. KVM should + * always return success if all bytes are prefaulted, + * i.e. there is no need to guard against EAGAIN being + * returned. + */ + if (range.size) + continue; + } + + /* + * All done if there are no remaining bytes to prefault, or if + * prefaulting failed (EINTR was handled above, and EAGAIN due + * to prefaulting a memslot that's being actively deleted should + * be impossible since the memslot has already been recreated). + */ + if (!range.size || ret < 0) + break; + } - if (left == 0) - __TEST_ASSERT_VM_VCPU_IOCTL(!ret, "KVM_PRE_FAULT_MEMORY", ret, vcpu->vm); + TEST_ASSERT(range.size == expected_left, + "Completed with %llu bytes left, expected %lu", + range.size, expected_left); + + /* + * Assert success if prefaulting the entire range should succeed, i.e. + * complete with no bytes remaining. Otherwise prefaulting should have + * failed due to ENOENT (due to RET_PF_EMULATE for emulated MMIO when + * no memslot exists). + */ + if (!expected_left) + TEST_ASSERT_VM_VCPU_IOCTL(!ret, KVM_PRE_FAULT_MEMORY, ret, vcpu->vm); else - /* No memory slot causes RET_PF_EMULATE. it results in -ENOENT. */ - __TEST_ASSERT_VM_VCPU_IOCTL(ret && save_errno == ENOENT, - "KVM_PRE_FAULT_MEMORY", ret, vcpu->vm); + TEST_ASSERT_VM_VCPU_IOCTL(ret && save_errno == ENOENT, + KVM_PRE_FAULT_MEMORY, ret, vcpu->vm); } static void __test_pre_fault_memory(unsigned long vm_type, bool private) @@ -97,9 +193,10 @@ static void __test_pre_fault_memory(unsigned long vm_type, bool private) if (private) vm_mem_set_private(vm, guest_test_phys_mem, TEST_SIZE); - pre_fault_memory(vcpu, guest_test_phys_mem, SZ_2M, 0); - pre_fault_memory(vcpu, guest_test_phys_mem + SZ_2M, PAGE_SIZE * 2, PAGE_SIZE); - pre_fault_memory(vcpu, guest_test_phys_mem + TEST_SIZE, PAGE_SIZE, PAGE_SIZE); + + pre_fault_memory(vcpu, guest_test_phys_mem, 0, SZ_2M, 0, private); + pre_fault_memory(vcpu, guest_test_phys_mem, SZ_2M, PAGE_SIZE * 2, PAGE_SIZE, private); + pre_fault_memory(vcpu, guest_test_phys_mem, TEST_SIZE, PAGE_SIZE, PAGE_SIZE, private); vcpu_args_set(vcpu, 1, guest_test_virt_mem); vcpu_run(vcpu); -- cgit v1.2.3 From d2042d8f96ddefdeee823737f813efe3ab4b4e8d Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 3 Oct 2025 16:25:54 -0700 Subject: KVM: Rework KVM_CAP_GUEST_MEMFD_MMAP into KVM_CAP_GUEST_MEMFD_FLAGS Rework the not-yet-released KVM_CAP_GUEST_MEMFD_MMAP into a more generic KVM_CAP_GUEST_MEMFD_FLAGS capability so that adding new flags doesn't require a new capability, and so that developers aren't tempted to bundle multiple flags into a single capability. Note, kvm_vm_ioctl_check_extension_generic() can only return a 32-bit value, but that limitation can be easily circumvented by adding e.g. KVM_CAP_GUEST_MEMFD_FLAGS2 in the unlikely event guest_memfd supports more than 32 flags. Reviewed-by: Ackerley Tng Tested-by: Ackerley Tng Reviewed-by: David Hildenbrand Link: https://lore.kernel.org/r/20251003232606.4070510-2-seanjc@google.com Signed-off-by: Sean Christopherson --- Documentation/virt/kvm/api.rst | 10 +++++++--- include/uapi/linux/kvm.h | 2 +- tools/testing/selftests/kvm/guest_memfd_test.c | 13 ++++++------- virt/kvm/kvm_main.c | 7 +++++-- 4 files changed, 19 insertions(+), 13 deletions(-) (limited to 'tools/testing') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 6ae24c5ca559..7ba92f2ced38 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6432,9 +6432,13 @@ most one mapping per page, i.e. binding multiple memory regions to a single guest_memfd range is not allowed (any number of memory regions can be bound to a single guest_memfd file, but the bound ranges must not overlap). -When the capability KVM_CAP_GUEST_MEMFD_MMAP is supported, the 'flags' field -supports GUEST_MEMFD_FLAG_MMAP. Setting this flag on guest_memfd creation -enables mmap() and faulting of guest_memfd memory to host userspace. +The capability KVM_CAP_GUEST_MEMFD_FLAGS enumerates the `flags` that can be +specified via KVM_CREATE_GUEST_MEMFD. Currently defined flags: + + ============================ ================================================ + GUEST_MEMFD_FLAG_MMAP Enable using mmap() on the guest_memfd file + descriptor. + ============================ ================================================ When the KVM MMU performs a PFN lookup to service a guest fault and the backing guest_memfd has the GUEST_MEMFD_FLAG_MMAP set, then the fault will always be diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 6efa98a57ec1..b1d52d0c56ec 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -962,7 +962,7 @@ struct kvm_enable_cap { #define KVM_CAP_ARM_EL2_E2H0 241 #define KVM_CAP_RISCV_MP_STATE_RESET 242 #define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243 -#define KVM_CAP_GUEST_MEMFD_MMAP 244 +#define KVM_CAP_GUEST_MEMFD_FLAGS 244 struct kvm_irq_routing_irqchip { __u32 irqchip; diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index b3ca6737f304..3e58bd496104 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -262,19 +262,17 @@ static void test_guest_memfd_flags(struct kvm_vm *vm, uint64_t valid_flags) static void test_guest_memfd(unsigned long vm_type) { - uint64_t flags = 0; struct kvm_vm *vm; size_t total_size; size_t page_size; + uint64_t flags; int fd; page_size = getpagesize(); total_size = page_size * 4; vm = vm_create_barebones_type(vm_type); - - if (vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_MMAP)) - flags |= GUEST_MEMFD_FLAG_MMAP; + flags = vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS); test_create_guest_memfd_multiple(vm); test_create_guest_memfd_invalid_sizes(vm, flags, page_size); @@ -328,13 +326,14 @@ static void test_guest_memfd_guest(void) size_t size; int fd, i; - if (!kvm_has_cap(KVM_CAP_GUEST_MEMFD_MMAP)) + if (!kvm_check_cap(KVM_CAP_GUEST_MEMFD_FLAGS)) return; vm = __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, &vcpu, 1, guest_code); - TEST_ASSERT(vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_MMAP), - "Default VM type should always support guest_memfd mmap()"); + TEST_ASSERT(vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS) & GUEST_MEMFD_FLAG_MMAP, + "Default VM type should support MMAP, supported flags = 0x%x", + vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS)); size = vm->page_size; fd = vm_create_guest_memfd(vm, size, GUEST_MEMFD_FLAG_MMAP); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 226faeaa8e56..e3a268757621 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4928,8 +4928,11 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) #ifdef CONFIG_KVM_GUEST_MEMFD case KVM_CAP_GUEST_MEMFD: return 1; - case KVM_CAP_GUEST_MEMFD_MMAP: - return !kvm || kvm_arch_supports_gmem_mmap(kvm); + case KVM_CAP_GUEST_MEMFD_FLAGS: + if (!kvm || kvm_arch_supports_gmem_mmap(kvm)) + return GUEST_MEMFD_FLAG_MMAP; + + return 0; #endif default: break; -- cgit v1.2.3 From fe2bf6234e947bf5544db6d386af1df2a8db80f3 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 3 Oct 2025 16:25:55 -0700 Subject: KVM: guest_memfd: Add INIT_SHARED flag, reject user page faults if not set Add a guest_memfd flag to allow userspace to state that the underlying memory should be configured to be initialized as shared, and reject user page faults if the guest_memfd instance's memory isn't shared. Because KVM doesn't yet support in-place private<=>shared conversions, all guest_memfd memory effectively follows the initial state. Alternatively, KVM could deduce the initial state based on MMAP, which for all intents and purposes is what KVM currently does. However, implicitly deriving the default state based on MMAP will result in a messy ABI when support for in-place conversions is added. For x86 CoCo VMs, which don't yet support MMAP, memory is currently private by default (otherwise the memory would be unusable). If MMAP implies memory is shared by default, then the default state for CoCo VMs will vary based on MMAP, and from userspace's perspective, will change when in-place conversion support is added. I.e. to maintain guest<=>host ABI, userspace would need to immediately convert all memory from shared=>private, which is both ugly and inefficient. The inefficiency could be avoided by adding a flag to state that memory is _private_ by default, irrespective of MMAP, but that would lead to an equally messy and hard to document ABI. Bite the bullet and immediately add a flag to control the default state so that the effective behavior is explicit and straightforward. Fixes: 3d3a04fad25a ("KVM: Allow and advertise support for host mmap() on guest_memfd files") Cc: David Hildenbrand Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Reviewed-by: Ackerley Tng Tested-by: Ackerley Tng Reviewed-by: David Hildenbrand Link: https://lore.kernel.org/r/20251003232606.4070510-3-seanjc@google.com Signed-off-by: Sean Christopherson --- Documentation/virt/kvm/api.rst | 5 +++++ include/uapi/linux/kvm.h | 3 ++- tools/testing/selftests/kvm/guest_memfd_test.c | 15 ++++++++++++--- virt/kvm/guest_memfd.c | 6 +++++- virt/kvm/kvm_main.c | 3 ++- 5 files changed, 26 insertions(+), 6 deletions(-) (limited to 'tools/testing') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 7ba92f2ced38..754b662a453c 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6438,6 +6438,11 @@ specified via KVM_CREATE_GUEST_MEMFD. Currently defined flags: ============================ ================================================ GUEST_MEMFD_FLAG_MMAP Enable using mmap() on the guest_memfd file descriptor. + GUEST_MEMFD_FLAG_INIT_SHARED Make all memory in the file shared during + KVM_CREATE_GUEST_MEMFD (memory files created + without INIT_SHARED will be marked private). + Shared memory can be faulted into host userspace + page tables. Private memory cannot. ============================ ================================================ When the KVM MMU performs a PFN lookup to service a guest fault and the backing diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index b1d52d0c56ec..52f6000ab020 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1599,7 +1599,8 @@ struct kvm_memory_attributes { #define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) #define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO, 0xd4, struct kvm_create_guest_memfd) -#define GUEST_MEMFD_FLAG_MMAP (1ULL << 0) +#define GUEST_MEMFD_FLAG_MMAP (1ULL << 0) +#define GUEST_MEMFD_FLAG_INIT_SHARED (1ULL << 1) struct kvm_create_guest_memfd { __u64 size; diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 3e58bd496104..0de56ce3c4e2 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -239,8 +239,9 @@ static void test_create_guest_memfd_multiple(struct kvm_vm *vm) close(fd1); } -static void test_guest_memfd_flags(struct kvm_vm *vm, uint64_t valid_flags) +static void test_guest_memfd_flags(struct kvm_vm *vm) { + uint64_t valid_flags = vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS); size_t page_size = getpagesize(); uint64_t flag; int fd; @@ -274,6 +275,10 @@ static void test_guest_memfd(unsigned long vm_type) vm = vm_create_barebones_type(vm_type); flags = vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS); + /* This test doesn't yet support testing mmap() on private memory. */ + if (!(flags & GUEST_MEMFD_FLAG_INIT_SHARED)) + flags &= ~GUEST_MEMFD_FLAG_MMAP; + test_create_guest_memfd_multiple(vm); test_create_guest_memfd_invalid_sizes(vm, flags, page_size); @@ -292,7 +297,7 @@ static void test_guest_memfd(unsigned long vm_type) test_fallocate(fd, page_size, total_size); test_invalid_punch_hole(fd, page_size, total_size); - test_guest_memfd_flags(vm, flags); + test_guest_memfd_flags(vm); close(fd); kvm_vm_free(vm); @@ -334,9 +339,13 @@ static void test_guest_memfd_guest(void) TEST_ASSERT(vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS) & GUEST_MEMFD_FLAG_MMAP, "Default VM type should support MMAP, supported flags = 0x%x", vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS)); + TEST_ASSERT(vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS) & GUEST_MEMFD_FLAG_INIT_SHARED, + "Default VM type should support INIT_SHARED, supported flags = 0x%x", + vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS)); size = vm->page_size; - fd = vm_create_guest_memfd(vm, size, GUEST_MEMFD_FLAG_MMAP); + fd = vm_create_guest_memfd(vm, size, GUEST_MEMFD_FLAG_MMAP | + GUEST_MEMFD_FLAG_INIT_SHARED); vm_set_user_memory_region2(vm, slot, KVM_MEM_GUEST_MEMFD, gpa, size, NULL, fd, 0); mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 94bafd6c558c..cf3afba23a6b 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -328,6 +328,9 @@ static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf) if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode)) return VM_FAULT_SIGBUS; + if (!((u64)inode->i_private & GUEST_MEMFD_FLAG_INIT_SHARED)) + return VM_FAULT_SIGBUS; + folio = kvm_gmem_get_folio(inode, vmf->pgoff); if (IS_ERR(folio)) { int err = PTR_ERR(folio); @@ -525,7 +528,8 @@ int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args) u64 valid_flags = 0; if (kvm_arch_supports_gmem_mmap(kvm)) - valid_flags |= GUEST_MEMFD_FLAG_MMAP; + valid_flags |= GUEST_MEMFD_FLAG_MMAP | + GUEST_MEMFD_FLAG_INIT_SHARED; if (flags & ~valid_flags) return -EINVAL; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index e3a268757621..5f644ca54af3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4930,7 +4930,8 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) return 1; case KVM_CAP_GUEST_MEMFD_FLAGS: if (!kvm || kvm_arch_supports_gmem_mmap(kvm)) - return GUEST_MEMFD_FLAG_MMAP; + return GUEST_MEMFD_FLAG_MMAP | + GUEST_MEMFD_FLAG_INIT_SHARED; return 0; #endif -- cgit v1.2.3 From 3a6c08538c742624c60cb6a53dd61eb025e0d1e1 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 3 Oct 2025 16:25:59 -0700 Subject: KVM: selftests: Stash the host page size in a global in the guest_memfd test Use a global variable to track the host page size in the guest_memfd test so that the information doesn't need to be constantly passed around. The state is purely a reflection of the underlying system, i.e. can't be set by the test and is constant for a given invocation of the test, and thus explicitly passing the host page size to individual testcases adds no value, e.g. doesn't allow testing different combinations. Making page_size a global will simplify an upcoming change to create a new guest_memfd instance per testcase. No functional change intended. Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Reviewed-by: David Hildenbrand Reviewed-by: Ackerley Tng Tested-by: Ackerley Tng Link: https://lore.kernel.org/r/20251003232606.4070510-7-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/guest_memfd_test.c | 37 +++++++++++++------------- 1 file changed, 18 insertions(+), 19 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 0de56ce3c4e2..a7c9601bd31e 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -24,6 +24,8 @@ #include "test_util.h" #include "ucall_common.h" +static size_t page_size; + static void test_file_read_write(int fd) { char buf[64]; @@ -38,7 +40,7 @@ static void test_file_read_write(int fd) "pwrite on a guest_mem fd should fail"); } -static void test_mmap_supported(int fd, size_t page_size, size_t total_size) +static void test_mmap_supported(int fd, size_t total_size) { const char val = 0xaa; char *mem; @@ -78,7 +80,7 @@ void fault_sigbus_handler(int signum) siglongjmp(jmpbuf, 1); } -static void test_fault_overflow(int fd, size_t page_size, size_t total_size) +static void test_fault_overflow(int fd, size_t total_size) { struct sigaction sa_old, sa_new = { .sa_handler = fault_sigbus_handler, @@ -106,7 +108,7 @@ static void test_fault_overflow(int fd, size_t page_size, size_t total_size) TEST_ASSERT(!ret, "munmap() should succeed."); } -static void test_mmap_not_supported(int fd, size_t page_size, size_t total_size) +static void test_mmap_not_supported(int fd, size_t total_size) { char *mem; @@ -117,7 +119,7 @@ static void test_mmap_not_supported(int fd, size_t page_size, size_t total_size) TEST_ASSERT_EQ(mem, MAP_FAILED); } -static void test_file_size(int fd, size_t page_size, size_t total_size) +static void test_file_size(int fd, size_t total_size) { struct stat sb; int ret; @@ -128,7 +130,7 @@ static void test_file_size(int fd, size_t page_size, size_t total_size) TEST_ASSERT_EQ(sb.st_blksize, page_size); } -static void test_fallocate(int fd, size_t page_size, size_t total_size) +static void test_fallocate(int fd, size_t total_size) { int ret; @@ -165,7 +167,7 @@ static void test_fallocate(int fd, size_t page_size, size_t total_size) TEST_ASSERT(!ret, "fallocate to restore punched hole should succeed"); } -static void test_invalid_punch_hole(int fd, size_t page_size, size_t total_size) +static void test_invalid_punch_hole(int fd, size_t total_size) { struct { off_t offset; @@ -196,8 +198,7 @@ static void test_invalid_punch_hole(int fd, size_t page_size, size_t total_size) } static void test_create_guest_memfd_invalid_sizes(struct kvm_vm *vm, - uint64_t guest_memfd_flags, - size_t page_size) + uint64_t guest_memfd_flags) { size_t size; int fd; @@ -214,7 +215,6 @@ static void test_create_guest_memfd_multiple(struct kvm_vm *vm) { int fd1, fd2, ret; struct stat st1, st2; - size_t page_size = getpagesize(); fd1 = __vm_create_guest_memfd(vm, page_size, 0); TEST_ASSERT(fd1 != -1, "memfd creation should succeed"); @@ -242,7 +242,6 @@ static void test_create_guest_memfd_multiple(struct kvm_vm *vm) static void test_guest_memfd_flags(struct kvm_vm *vm) { uint64_t valid_flags = vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS); - size_t page_size = getpagesize(); uint64_t flag; int fd; @@ -265,11 +264,9 @@ static void test_guest_memfd(unsigned long vm_type) { struct kvm_vm *vm; size_t total_size; - size_t page_size; uint64_t flags; int fd; - page_size = getpagesize(); total_size = page_size * 4; vm = vm_create_barebones_type(vm_type); @@ -280,22 +277,22 @@ static void test_guest_memfd(unsigned long vm_type) flags &= ~GUEST_MEMFD_FLAG_MMAP; test_create_guest_memfd_multiple(vm); - test_create_guest_memfd_invalid_sizes(vm, flags, page_size); + test_create_guest_memfd_invalid_sizes(vm, flags); fd = vm_create_guest_memfd(vm, total_size, flags); test_file_read_write(fd); if (flags & GUEST_MEMFD_FLAG_MMAP) { - test_mmap_supported(fd, page_size, total_size); - test_fault_overflow(fd, page_size, total_size); + test_mmap_supported(fd, total_size); + test_fault_overflow(fd, total_size); } else { - test_mmap_not_supported(fd, page_size, total_size); + test_mmap_not_supported(fd, total_size); } - test_file_size(fd, page_size, total_size); - test_fallocate(fd, page_size, total_size); - test_invalid_punch_hole(fd, page_size, total_size); + test_file_size(fd, total_size); + test_fallocate(fd, total_size); + test_invalid_punch_hole(fd, total_size); test_guest_memfd_flags(vm); @@ -374,6 +371,8 @@ int main(int argc, char *argv[]) TEST_REQUIRE(kvm_has_cap(KVM_CAP_GUEST_MEMFD)); + page_size = getpagesize(); + /* * Not all architectures support KVM_CAP_VM_TYPES. However, those that * support guest_memfd have that support for the default VM type. -- cgit v1.2.3 From 21d602ed616aebae4de568be55db65a1f5a3be10 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 3 Oct 2025 16:26:00 -0700 Subject: KVM: selftests: Create a new guest_memfd for each testcase Refactor the guest_memfd selftest to improve test isolation by creating a a new guest_memfd for each testcase. Currently, the test reuses a single guest_memfd instance for all testcases, and thus creates dependencies between tests, e.g. not truncating folios from the guest_memfd instance at the end of a test could lead to unexpected results (see the PUNCH_HOLE purging that needs to done by in-flight the NUMA testcases[1]). Invoke each test via a macro wrapper to create and close a guest_memfd to cut down on the boilerplate copy+paste needed to create a test. Link: https://lore.kernel.org/all/20250827175247.83322-10-shivankg@amd.com Reported-by: Ackerley Tng Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Reviewed-by: David Hildenbrand Reviewed-by: Ackerley Tng Tested-by: Ackerley Tng Link: https://lore.kernel.org/r/20251003232606.4070510-8-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/guest_memfd_test.c | 31 +++++++++++++------------- 1 file changed, 16 insertions(+), 15 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index a7c9601bd31e..afdc4d3a956d 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -26,7 +26,7 @@ static size_t page_size; -static void test_file_read_write(int fd) +static void test_file_read_write(int fd, size_t total_size) { char buf[64]; @@ -260,14 +260,18 @@ static void test_guest_memfd_flags(struct kvm_vm *vm) } } +#define gmem_test(__test, __vm, __flags) \ +do { \ + int fd = vm_create_guest_memfd(__vm, page_size * 4, __flags); \ + \ + test_##__test(fd, page_size * 4); \ + close(fd); \ +} while (0) + static void test_guest_memfd(unsigned long vm_type) { struct kvm_vm *vm; - size_t total_size; uint64_t flags; - int fd; - - total_size = page_size * 4; vm = vm_create_barebones_type(vm_type); flags = vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS); @@ -279,24 +283,21 @@ static void test_guest_memfd(unsigned long vm_type) test_create_guest_memfd_multiple(vm); test_create_guest_memfd_invalid_sizes(vm, flags); - fd = vm_create_guest_memfd(vm, total_size, flags); - - test_file_read_write(fd); + gmem_test(file_read_write, vm, flags); if (flags & GUEST_MEMFD_FLAG_MMAP) { - test_mmap_supported(fd, total_size); - test_fault_overflow(fd, total_size); + gmem_test(mmap_supported, vm, flags); + gmem_test(fault_overflow, vm, flags); } else { - test_mmap_not_supported(fd, total_size); + gmem_test(mmap_not_supported, vm, flags); } - test_file_size(fd, total_size); - test_fallocate(fd, total_size); - test_invalid_punch_hole(fd, total_size); + gmem_test(file_size, vm, flags); + gmem_test(fallocate, vm, flags); + gmem_test(invalid_punch_hole, vm, flags); test_guest_memfd_flags(vm); - close(fd); kvm_vm_free(vm); } -- cgit v1.2.3 From df0d9923f7055169cb01b050236e5a9a2b36db02 Mon Sep 17 00:00:00 2001 From: Ackerley Tng Date: Fri, 3 Oct 2025 16:26:01 -0700 Subject: KVM: selftests: Add test coverage for guest_memfd without GUEST_MEMFD_FLAG_MMAP If a VM type supports KVM_CAP_GUEST_MEMFD_MMAP, the guest_memfd test will run all test cases with GUEST_MEMFD_FLAG_MMAP set. This leaves the code path for creating a non-mmap()-able guest_memfd on a VM that supports mappable guest memfds untested. Refactor the test to run the main test suite with a given set of flags. Then, for VM types that support the mappable capability, invoke the test suite twice: once with no flags, and once with GUEST_MEMFD_FLAG_MMAP set. This ensures both creation paths are properly exercised on capable VMs. Run test_guest_memfd_flags() only once per VM type since it depends only on the set of valid/supported flags, i.e. iterating over an arbitrary set of flags is both unnecessary and wrong. Signed-off-by: Ackerley Tng [sean: use double-underscores for the inner helper] Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Reviewed-by: David Hildenbrand Link: https://lore.kernel.org/r/20251003232606.4070510-9-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/guest_memfd_test.c | 27 +++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index afdc4d3a956d..9f98a067ab51 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -268,18 +268,8 @@ do { \ close(fd); \ } while (0) -static void test_guest_memfd(unsigned long vm_type) +static void __test_guest_memfd(struct kvm_vm *vm, uint64_t flags) { - struct kvm_vm *vm; - uint64_t flags; - - vm = vm_create_barebones_type(vm_type); - flags = vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS); - - /* This test doesn't yet support testing mmap() on private memory. */ - if (!(flags & GUEST_MEMFD_FLAG_INIT_SHARED)) - flags &= ~GUEST_MEMFD_FLAG_MMAP; - test_create_guest_memfd_multiple(vm); test_create_guest_memfd_invalid_sizes(vm, flags); @@ -295,9 +285,24 @@ static void test_guest_memfd(unsigned long vm_type) gmem_test(file_size, vm, flags); gmem_test(fallocate, vm, flags); gmem_test(invalid_punch_hole, vm, flags); +} + +static void test_guest_memfd(unsigned long vm_type) +{ + struct kvm_vm *vm = vm_create_barebones_type(vm_type); + uint64_t flags; test_guest_memfd_flags(vm); + __test_guest_memfd(vm, 0); + + flags = vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS); + + /* MMAP should always be supported if INIT_SHARED is supported. */ + if (flags & GUEST_MEMFD_FLAG_INIT_SHARED) + __test_guest_memfd(vm, GUEST_MEMFD_FLAG_MMAP | + GUEST_MEMFD_FLAG_INIT_SHARED); + kvm_vm_free(vm); } -- cgit v1.2.3 From 61cee97f40180312dcca9580a5be0b0aa2217f6e Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 3 Oct 2025 16:26:02 -0700 Subject: KVM: selftests: Add wrappers for mmap() and munmap() to assert success Add and use wrappers for mmap() and munmap() that assert success to reduce a significant amount of boilerplate code, to ensure all tests assert on failure, and to provide consistent error messages on failure. No functional change intended. Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Reviewed-by: David Hildenbrand Reviewed-by: Ackerley Tng Link: https://lore.kernel.org/r/20251003232606.4070510-10-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/guest_memfd_test.c | 21 ++++------- tools/testing/selftests/kvm/include/kvm_util.h | 25 ++++++++++++ tools/testing/selftests/kvm/lib/kvm_util.c | 44 ++++++++-------------- tools/testing/selftests/kvm/mmu_stress_test.c | 5 +-- tools/testing/selftests/kvm/s390/ucontrol_test.c | 16 ++++---- .../testing/selftests/kvm/set_memory_region_test.c | 17 ++++----- 6 files changed, 64 insertions(+), 64 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 9f98a067ab51..319fda4f5d53 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -50,8 +50,7 @@ static void test_mmap_supported(int fd, size_t total_size) mem = mmap(NULL, total_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); TEST_ASSERT(mem == MAP_FAILED, "Copy-on-write not allowed by guest_memfd."); - mem = mmap(NULL, total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); - TEST_ASSERT(mem != MAP_FAILED, "mmap() for guest_memfd should succeed."); + mem = kvm_mmap(total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd); memset(mem, val, total_size); for (i = 0; i < total_size; i++) @@ -70,8 +69,7 @@ static void test_mmap_supported(int fd, size_t total_size) for (i = 0; i < total_size; i++) TEST_ASSERT_EQ(READ_ONCE(mem[i]), val); - ret = munmap(mem, total_size); - TEST_ASSERT(!ret, "munmap() should succeed."); + kvm_munmap(mem, total_size); } static sigjmp_buf jmpbuf; @@ -89,10 +87,8 @@ static void test_fault_overflow(int fd, size_t total_size) const char val = 0xaa; char *mem; size_t i; - int ret; - mem = mmap(NULL, map_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); - TEST_ASSERT(mem != MAP_FAILED, "mmap() for guest_memfd should succeed."); + mem = kvm_mmap(map_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd); sigaction(SIGBUS, &sa_new, &sa_old); if (sigsetjmp(jmpbuf, 1) == 0) { @@ -104,8 +100,7 @@ static void test_fault_overflow(int fd, size_t total_size) for (i = 0; i < total_size; i++) TEST_ASSERT_EQ(READ_ONCE(mem[i]), val); - ret = munmap(mem, map_size); - TEST_ASSERT(!ret, "munmap() should succeed."); + kvm_munmap(mem, map_size); } static void test_mmap_not_supported(int fd, size_t total_size) @@ -351,10 +346,9 @@ static void test_guest_memfd_guest(void) GUEST_MEMFD_FLAG_INIT_SHARED); vm_set_user_memory_region2(vm, slot, KVM_MEM_GUEST_MEMFD, gpa, size, NULL, fd, 0); - mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); - TEST_ASSERT(mem != MAP_FAILED, "mmap() on guest_memfd failed"); + mem = kvm_mmap(size, PROT_READ | PROT_WRITE, MAP_SHARED, fd); memset(mem, 0xaa, size); - munmap(mem, size); + kvm_munmap(mem, size); virt_pg_map(vm, gpa, gpa); vcpu_args_set(vcpu, 2, gpa, size); @@ -362,8 +356,7 @@ static void test_guest_memfd_guest(void) TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); - mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); - TEST_ASSERT(mem != MAP_FAILED, "mmap() on guest_memfd failed"); + mem = kvm_mmap(size, PROT_READ | PROT_WRITE, MAP_SHARED, fd); for (i = 0; i < size; i++) TEST_ASSERT_EQ(mem[i], 0xff); diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 26cc30290e76..ee60dbf5208a 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -286,6 +286,31 @@ static inline bool kvm_has_cap(long cap) #define __KVM_SYSCALL_ERROR(_name, _ret) \ "%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno) +static inline void *__kvm_mmap(size_t size, int prot, int flags, int fd, + off_t offset) +{ + void *mem; + + mem = mmap(NULL, size, prot, flags, fd, offset); + TEST_ASSERT(mem != MAP_FAILED, __KVM_SYSCALL_ERROR("mmap()", + (int)(unsigned long)MAP_FAILED)); + + return mem; +} + +static inline void *kvm_mmap(size_t size, int prot, int flags, int fd) +{ + return __kvm_mmap(size, prot, flags, fd, 0); +} + +static inline void kvm_munmap(void *mem, size_t size) +{ + int ret; + + ret = munmap(mem, size); + TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret)); +} + /* * Use the "inner", double-underscore macro when reporting errors from within * other macros so that the name of ioctl() and not its literal numeric value diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 6743fbd9bd67..83a721be7ec5 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -741,13 +741,11 @@ static void vm_vcpu_rm(struct kvm_vm *vm, struct kvm_vcpu *vcpu) int ret; if (vcpu->dirty_gfns) { - ret = munmap(vcpu->dirty_gfns, vm->dirty_ring_size); - TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret)); + kvm_munmap(vcpu->dirty_gfns, vm->dirty_ring_size); vcpu->dirty_gfns = NULL; } - ret = munmap(vcpu->run, vcpu_mmap_sz()); - TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret)); + kvm_munmap(vcpu->run, vcpu_mmap_sz()); ret = close(vcpu->fd); TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("close()", ret)); @@ -783,20 +781,16 @@ void kvm_vm_release(struct kvm_vm *vmp) static void __vm_mem_region_delete(struct kvm_vm *vm, struct userspace_mem_region *region) { - int ret; - rb_erase(®ion->gpa_node, &vm->regions.gpa_tree); rb_erase(®ion->hva_node, &vm->regions.hva_tree); hash_del(®ion->slot_node); sparsebit_free(®ion->unused_phy_pages); sparsebit_free(®ion->protected_phy_pages); - ret = munmap(region->mmap_start, region->mmap_size); - TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret)); + kvm_munmap(region->mmap_start, region->mmap_size); if (region->fd >= 0) { /* There's an extra map when using shared memory. */ - ret = munmap(region->mmap_alias, region->mmap_size); - TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret)); + kvm_munmap(region->mmap_alias, region->mmap_size); close(region->fd); } if (region->region.guest_memfd >= 0) @@ -1053,12 +1047,9 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type 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, - vm_mem_backing_src_alias(src_type)->flag, - region->fd, 0); - TEST_ASSERT(region->mmap_start != MAP_FAILED, - __KVM_SYSCALL_ERROR("mmap()", (int)(unsigned long)MAP_FAILED)); + region->mmap_start = kvm_mmap(region->mmap_size, PROT_READ | PROT_WRITE, + vm_mem_backing_src_alias(src_type)->flag, + region->fd); TEST_ASSERT(!is_backing_src_hugetlb(src_type) || region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz), @@ -1129,12 +1120,10 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, /* If shared memory, create an alias. */ if (region->fd >= 0) { - region->mmap_alias = mmap(NULL, region->mmap_size, - PROT_READ | PROT_WRITE, - vm_mem_backing_src_alias(src_type)->flag, - region->fd, 0); - TEST_ASSERT(region->mmap_alias != MAP_FAILED, - __KVM_SYSCALL_ERROR("mmap()", (int)(unsigned long)MAP_FAILED)); + region->mmap_alias = kvm_mmap(region->mmap_size, + PROT_READ | PROT_WRITE, + vm_mem_backing_src_alias(src_type)->flag, + region->fd); /* Align host alias address */ region->host_alias = align_ptr_up(region->mmap_alias, alignment); @@ -1344,10 +1333,8 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) TEST_ASSERT(vcpu_mmap_sz() >= sizeof(*vcpu->run), "vcpu mmap size " "smaller than expected, vcpu_mmap_sz: %zi expected_min: %zi", vcpu_mmap_sz(), sizeof(*vcpu->run)); - vcpu->run = (struct kvm_run *) mmap(NULL, vcpu_mmap_sz(), - PROT_READ | PROT_WRITE, MAP_SHARED, vcpu->fd, 0); - TEST_ASSERT(vcpu->run != MAP_FAILED, - __KVM_SYSCALL_ERROR("mmap()", (int)(unsigned long)MAP_FAILED)); + vcpu->run = kvm_mmap(vcpu_mmap_sz(), PROT_READ | PROT_WRITE, + MAP_SHARED, vcpu->fd); if (kvm_has_cap(KVM_CAP_BINARY_STATS_FD)) vcpu->stats.fd = vcpu_get_stats_fd(vcpu); @@ -1794,9 +1781,8 @@ void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu) page_size * KVM_DIRTY_LOG_PAGE_OFFSET); TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped exec"); - addr = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, vcpu->fd, - page_size * KVM_DIRTY_LOG_PAGE_OFFSET); - TEST_ASSERT(addr != MAP_FAILED, "Dirty ring map failed"); + addr = __kvm_mmap(size, PROT_READ | PROT_WRITE, MAP_SHARED, vcpu->fd, + page_size * KVM_DIRTY_LOG_PAGE_OFFSET); vcpu->dirty_gfns = addr; vcpu->dirty_gfns_count = size / sizeof(struct kvm_dirty_gfn); diff --git a/tools/testing/selftests/kvm/mmu_stress_test.c b/tools/testing/selftests/kvm/mmu_stress_test.c index 6a437d2be9fa..37b7e6524533 100644 --- a/tools/testing/selftests/kvm/mmu_stress_test.c +++ b/tools/testing/selftests/kvm/mmu_stress_test.c @@ -339,8 +339,7 @@ int main(int argc, char *argv[]) TEST_ASSERT(max_gpa > (4 * slot_size), "MAXPHYADDR <4gb "); fd = kvm_memfd_alloc(slot_size, hugepages); - mem = mmap(NULL, slot_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); - TEST_ASSERT(mem != MAP_FAILED, "mmap() failed"); + mem = kvm_mmap(slot_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd); TEST_ASSERT(!madvise(mem, slot_size, MADV_NOHUGEPAGE), "madvise() failed"); @@ -413,7 +412,7 @@ int main(int argc, char *argv[]) for (slot = (slot - 1) & ~1ull; slot >= first_slot; slot -= 2) vm_set_user_memory_region(vm, slot, 0, 0, 0, NULL); - munmap(mem, slot_size / 2); + kvm_munmap(mem, slot_size / 2); /* Sanity check that the vCPUs actually ran. */ for (i = 0; i < nr_vcpus; i++) diff --git a/tools/testing/selftests/kvm/s390/ucontrol_test.c b/tools/testing/selftests/kvm/s390/ucontrol_test.c index d265b34c54be..50bc1c38225a 100644 --- a/tools/testing/selftests/kvm/s390/ucontrol_test.c +++ b/tools/testing/selftests/kvm/s390/ucontrol_test.c @@ -142,19 +142,17 @@ FIXTURE_SETUP(uc_kvm) self->kvm_run_size = ioctl(self->kvm_fd, KVM_GET_VCPU_MMAP_SIZE, NULL); ASSERT_GE(self->kvm_run_size, sizeof(struct kvm_run)) TH_LOG(KVM_IOCTL_ERROR(KVM_GET_VCPU_MMAP_SIZE, self->kvm_run_size)); - self->run = (struct kvm_run *)mmap(NULL, self->kvm_run_size, - PROT_READ | PROT_WRITE, MAP_SHARED, self->vcpu_fd, 0); - ASSERT_NE(self->run, MAP_FAILED); + self->run = kvm_mmap(self->kvm_run_size, PROT_READ | PROT_WRITE, + MAP_SHARED, self->vcpu_fd); /** * For virtual cpus that have been created with S390 user controlled * virtual machines, the resulting vcpu fd can be memory mapped at page * offset KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of * the virtual cpu's hardware control block. */ - self->sie_block = (struct kvm_s390_sie_block *)mmap(NULL, PAGE_SIZE, - PROT_READ | PROT_WRITE, MAP_SHARED, - self->vcpu_fd, KVM_S390_SIE_PAGE_OFFSET << PAGE_SHIFT); - ASSERT_NE(self->sie_block, MAP_FAILED); + self->sie_block = __kvm_mmap(PAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_SHARED, self->vcpu_fd, + KVM_S390_SIE_PAGE_OFFSET << PAGE_SHIFT); TH_LOG("VM created %p %p", self->run, self->sie_block); @@ -186,8 +184,8 @@ FIXTURE_SETUP(uc_kvm) FIXTURE_TEARDOWN(uc_kvm) { - munmap(self->sie_block, PAGE_SIZE); - munmap(self->run, self->kvm_run_size); + kvm_munmap(self->sie_block, PAGE_SIZE); + kvm_munmap(self->run, self->kvm_run_size); close(self->vcpu_fd); close(self->vm_fd); close(self->kvm_fd); diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index ce3ac0fd6dfb..7fe427ff9b38 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -433,10 +433,10 @@ static void test_add_max_memory_regions(void) pr_info("Adding slots 0..%i, each memory region with %dK size\n", (max_mem_slots - 1), MEM_REGION_SIZE >> 10); - mem = mmap(NULL, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment, - PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1, 0); - TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host"); + + mem = kvm_mmap((size_t)max_mem_slots * MEM_REGION_SIZE + alignment, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1); mem_aligned = (void *)(((size_t) mem + alignment - 1) & ~(alignment - 1)); for (slot = 0; slot < max_mem_slots; slot++) @@ -446,9 +446,8 @@ static void test_add_max_memory_regions(void) mem_aligned + (uint64_t)slot * MEM_REGION_SIZE); /* Check it cannot be added memory slots beyond the limit */ - mem_extra = mmap(NULL, MEM_REGION_SIZE, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); - TEST_ASSERT(mem_extra != MAP_FAILED, "Failed to mmap() host"); + mem_extra = kvm_mmap(MEM_REGION_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1); ret = __vm_set_user_memory_region(vm, max_mem_slots, 0, (uint64_t)max_mem_slots * MEM_REGION_SIZE, @@ -456,8 +455,8 @@ static void test_add_max_memory_regions(void) TEST_ASSERT(ret == -1 && errno == EINVAL, "Adding one more memory slot should fail with EINVAL"); - munmap(mem, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment); - munmap(mem_extra, MEM_REGION_SIZE); + kvm_munmap(mem, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment); + kvm_munmap(mem_extra, MEM_REGION_SIZE); kvm_vm_free(vm); } -- cgit v1.2.3 From 505c953009ec8260870d41ef8109bb4c7e208e6f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 3 Oct 2025 16:26:03 -0700 Subject: KVM: selftests: Isolate the guest_memfd Copy-on-Write negative testcase Move the guest_memfd Copy-on-Write (CoW) testcase to its own function to better separate positive testcases from negative testcases. No functional change intended. Suggested-by: Ackerley Tng Reviewed-by: Ackerley Tng Tested-by: Ackerley Tng Link: https://lore.kernel.org/r/20251003232606.4070510-11-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/guest_memfd_test.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 319fda4f5d53..640636c76eb9 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -40,6 +40,14 @@ static void test_file_read_write(int fd, size_t total_size) "pwrite on a guest_mem fd should fail"); } +static void test_mmap_cow(int fd, size_t size) +{ + void *mem; + + mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); + TEST_ASSERT(mem == MAP_FAILED, "Copy-on-write not allowed by guest_memfd."); +} + static void test_mmap_supported(int fd, size_t total_size) { const char val = 0xaa; @@ -47,9 +55,6 @@ static void test_mmap_supported(int fd, size_t total_size) size_t i; int ret; - mem = mmap(NULL, total_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); - TEST_ASSERT(mem == MAP_FAILED, "Copy-on-write not allowed by guest_memfd."); - mem = kvm_mmap(total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd); memset(mem, val, total_size); @@ -272,6 +277,7 @@ static void __test_guest_memfd(struct kvm_vm *vm, uint64_t flags) if (flags & GUEST_MEMFD_FLAG_MMAP) { gmem_test(mmap_supported, vm, flags); + gmem_test(mmap_cow, vm, flags); gmem_test(fault_overflow, vm, flags); } else { gmem_test(mmap_not_supported, vm, flags); -- cgit v1.2.3 From f91187c0ecc6358ccecf533c5fcc6b7dbb4735cb Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 3 Oct 2025 16:26:04 -0700 Subject: KVM: selftests: Add wrapper macro to handle and assert on expected SIGBUS Extract the guest_memfd test's SIGBUS handling functionality into a common TEST_EXPECT_SIGBUS() macro in anticipation of adding more SIGBUS testcases. Eating a SIGBUS isn't terrible difficult, but it requires a non-trivial amount of boilerplate code, and using a macro allows selftests to print out the exact action that failed to generate a SIGBUS without the developer needing to remember to add a useful error message. Explicitly mark the SIGBUS handler as "used", as gcc-14 at least likes to discard the function before linking. Opportunistically use TEST_FAIL(...) instead of TEST_ASSERT(false, ...), and fix the write path of the guest_memfd test to use the local "val" instead of hardcoding the literal value a second time. Suggested-by: Ackerley Tng Reviewed-by: Ackerley Tng Tested-by: Ackerley Tng Reviewed-by: Lisa Wang Tested-by: Lisa Wang Link: https://lore.kernel.org/r/20251003232606.4070510-12-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/guest_memfd_test.c | 18 +----------------- tools/testing/selftests/kvm/include/test_util.h | 19 +++++++++++++++++++ tools/testing/selftests/kvm/lib/test_util.c | 7 +++++++ 3 files changed, 27 insertions(+), 17 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 640636c76eb9..73c2e54e7297 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -14,8 +14,6 @@ #include #include #include -#include -#include #include #include #include @@ -77,17 +75,8 @@ static void test_mmap_supported(int fd, size_t total_size) kvm_munmap(mem, total_size); } -static sigjmp_buf jmpbuf; -void fault_sigbus_handler(int signum) -{ - siglongjmp(jmpbuf, 1); -} - static void test_fault_overflow(int fd, size_t total_size) { - struct sigaction sa_old, sa_new = { - .sa_handler = fault_sigbus_handler, - }; size_t map_size = total_size * 4; const char val = 0xaa; char *mem; @@ -95,12 +84,7 @@ static void test_fault_overflow(int fd, size_t total_size) mem = kvm_mmap(map_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd); - sigaction(SIGBUS, &sa_new, &sa_old); - if (sigsetjmp(jmpbuf, 1) == 0) { - memset(mem, 0xaa, map_size); - TEST_ASSERT(false, "memset() should have triggered SIGBUS."); - } - sigaction(SIGBUS, &sa_old, NULL); + TEST_EXPECT_SIGBUS(memset(mem, val, map_size)); for (i = 0; i < total_size; i++) TEST_ASSERT_EQ(READ_ONCE(mem[i]), val); diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index c6ef895fbd9a..b4872ba8ed12 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -8,6 +8,8 @@ #ifndef SELFTEST_KVM_TEST_UTIL_H #define SELFTEST_KVM_TEST_UTIL_H +#include +#include #include #include #include @@ -78,6 +80,23 @@ do { \ __builtin_unreachable(); \ } while (0) +extern sigjmp_buf expect_sigbus_jmpbuf; +void expect_sigbus_handler(int signum); + +#define TEST_EXPECT_SIGBUS(action) \ +do { \ + struct sigaction sa_old, sa_new = { \ + .sa_handler = expect_sigbus_handler, \ + }; \ + \ + sigaction(SIGBUS, &sa_new, &sa_old); \ + if (sigsetjmp(expect_sigbus_jmpbuf, 1) == 0) { \ + action; \ + TEST_FAIL("'%s' should have triggered SIGBUS", #action); \ + } \ + sigaction(SIGBUS, &sa_old, NULL); \ +} while (0) + size_t parse_size(const char *size); int64_t timespec_to_ns(struct timespec ts); diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 03eb99af9b8d..8a1848586a85 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -18,6 +18,13 @@ #include "test_util.h" +sigjmp_buf expect_sigbus_jmpbuf; + +void __attribute__((used)) expect_sigbus_handler(int signum) +{ + siglongjmp(expect_sigbus_jmpbuf, 1); +} + /* * Random number generator that is usable from guest code. This is the * Park-Miller LCG using standard constants. -- cgit v1.2.3 From 19942d4fd9cf022b28a9afb432a6338dcf96fc2f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 3 Oct 2025 16:26:05 -0700 Subject: KVM: selftests: Verify that faulting in private guest_memfd memory fails Add a guest_memfd testcase to verify that faulting in private memory gets a SIGBUS. For now, test only the case where memory is private by default since KVM doesn't yet support in-place conversion. Deliberately run the CoW test with and without INIT_SHARED set as KVM should disallow MAP_PRIVATE regardless of whether the memory itself is private from a CoCo perspective. Cc: Ackerley Tng Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Reviewed-by: David Hildenbrand Reviewed-by: Ackerley Tng Tested-by: Ackerley Tng Link: https://lore.kernel.org/r/20251003232606.4070510-13-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/guest_memfd_test.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 73c2e54e7297..f5372fdf096d 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -75,9 +75,8 @@ static void test_mmap_supported(int fd, size_t total_size) kvm_munmap(mem, total_size); } -static void test_fault_overflow(int fd, size_t total_size) +static void test_fault_sigbus(int fd, size_t accessible_size, size_t map_size) { - size_t map_size = total_size * 4; const char val = 0xaa; char *mem; size_t i; @@ -86,12 +85,22 @@ static void test_fault_overflow(int fd, size_t total_size) TEST_EXPECT_SIGBUS(memset(mem, val, map_size)); - for (i = 0; i < total_size; i++) + for (i = 0; i < accessible_size; i++) TEST_ASSERT_EQ(READ_ONCE(mem[i]), val); kvm_munmap(mem, map_size); } +static void test_fault_overflow(int fd, size_t total_size) +{ + test_fault_sigbus(fd, total_size, total_size * 4); +} + +static void test_fault_private(int fd, size_t total_size) +{ + test_fault_sigbus(fd, 0, total_size); +} + static void test_mmap_not_supported(int fd, size_t total_size) { char *mem; @@ -260,9 +269,14 @@ static void __test_guest_memfd(struct kvm_vm *vm, uint64_t flags) gmem_test(file_read_write, vm, flags); if (flags & GUEST_MEMFD_FLAG_MMAP) { - gmem_test(mmap_supported, vm, flags); + if (flags & GUEST_MEMFD_FLAG_INIT_SHARED) { + gmem_test(mmap_supported, vm, flags); + gmem_test(fault_overflow, vm, flags); + } else { + gmem_test(fault_private, vm, flags); + } + gmem_test(mmap_cow, vm, flags); - gmem_test(fault_overflow, vm, flags); } else { gmem_test(mmap_not_supported, vm, flags); } @@ -282,6 +296,8 @@ static void test_guest_memfd(unsigned long vm_type) __test_guest_memfd(vm, 0); flags = vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS); + if (flags & GUEST_MEMFD_FLAG_MMAP) + __test_guest_memfd(vm, GUEST_MEMFD_FLAG_MMAP); /* MMAP should always be supported if INIT_SHARED is supported. */ if (flags & GUEST_MEMFD_FLAG_INIT_SHARED) -- cgit v1.2.3 From 505f5224b197b77169c977e747cbc18b222f85f9 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 3 Oct 2025 16:26:06 -0700 Subject: KVM: selftests: Verify that reads to inaccessible guest_memfd VMAs SIGBUS Expand the guest_memfd negative testcases for overflow and MAP_PRIVATE to verify that reads to inaccessible memory also get a SIGBUS. Reviewed-by: Ackerley Tng Tested-by: Ackerley Tng Reviewed-by: Lisa Wang Tested-by: Lisa Wang Link: https://lore.kernel.org/r/20251003232606.4070510-14-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/guest_memfd_test.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index f5372fdf096d..e7d9aeb418d3 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -84,6 +84,7 @@ static void test_fault_sigbus(int fd, size_t accessible_size, size_t map_size) mem = kvm_mmap(map_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd); TEST_EXPECT_SIGBUS(memset(mem, val, map_size)); + TEST_EXPECT_SIGBUS((void)READ_ONCE(mem[accessible_size])); for (i = 0; i < accessible_size; i++) TEST_ASSERT_EQ(READ_ONCE(mem[i]), val); -- cgit v1.2.3