Add a guest_memfd flag to allow userspace to state that the underlying memory should be configured to be shared by default, and reject user page faults if the guest_memfd instance's memory isn't shared by default. Because KVM doesn't yet support in-place private<=>shared conversions, all guest_memfd memory effectively follows the default state. Alternatively, KVM could deduce the default 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 Cc: Fuad Tabba Signed-off-by: Sean Christopherson --- Documentation/virt/kvm/api.rst | 10 ++++++++-- include/uapi/linux/kvm.h | 3 ++- tools/testing/selftests/kvm/guest_memfd_test.c | 5 +++-- virt/kvm/guest_memfd.c | 6 +++++- 4 files changed, 18 insertions(+), 6 deletions(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index c17a87a0a5ac..4dfe156bbe3c 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6415,8 +6415,14 @@ 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. +supports GUEST_MEMFD_FLAG_MMAP and GUEST_MEMFD_FLAG_DEFAULT_SHARED. Setting +the MMAP flag on guest_memfd creation enables mmap() and faulting of guest_memfd +memory to host userspace (so long as the memory is currently shared). Setting +DEFAULT_SHARED makes all guest_memfd memory shared by default (versus private +by default). Note! Because KVM doesn't yet support in-place private<=>shared +conversions, DEFAULT_SHARED must be specified in order to fault memory into +userspace page tables. This limitation will go away when in-place conversions +are supported. 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..38a2c083b6aa 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_DEFAULT_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 b3ca6737f304..81b11a958c7a 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -274,7 +274,7 @@ static void test_guest_memfd(unsigned long vm_type) vm = vm_create_barebones_type(vm_type); if (vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_MMAP)) - flags |= GUEST_MEMFD_FLAG_MMAP; + flags |= GUEST_MEMFD_FLAG_MMAP | GUEST_MEMFD_FLAG_DEFAULT_SHARED; test_create_guest_memfd_multiple(vm); test_create_guest_memfd_invalid_sizes(vm, flags, page_size); @@ -337,7 +337,8 @@ static void test_guest_memfd_guest(void) "Default VM type should always support guest_memfd mmap()"); 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_DEFAULT_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 08a6bc7d25b6..19f05a45be04 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_DEFAULT_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_DEFAULT_SHARED; if (flags & ~valid_flags) return -EINVAL; -- 2.51.0.536.g15c5d4f767-goog 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. Signed-off-by: Sean Christopherson --- .../testing/selftests/kvm/guest_memfd_test.c | 37 +++++++++---------- 1 file changed, 18 insertions(+), 19 deletions(-) diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 81b11a958c7a..8251d019206a 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"); @@ -241,7 +241,6 @@ 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) { - size_t page_size = getpagesize(); uint64_t flag; int fd; @@ -265,10 +264,8 @@ 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; int fd; - page_size = getpagesize(); total_size = page_size * 4; vm = vm_create_barebones_type(vm_type); @@ -277,22 +274,22 @@ static void test_guest_memfd(unsigned long vm_type) flags |= GUEST_MEMFD_FLAG_MMAP | GUEST_MEMFD_FLAG_DEFAULT_SHARED; 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, flags); @@ -367,6 +364,8 @@ 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. -- 2.51.0.536.g15c5d4f767-goog 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 Signed-off-by: Sean Christopherson --- .../testing/selftests/kvm/guest_memfd_test.c | 31 ++++++++++--------- 1 file changed, 16 insertions(+), 15 deletions(-) diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 8251d019206a..60c6dec63490 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]; @@ -259,14 +259,18 @@ static void test_guest_memfd_flags(struct kvm_vm *vm, uint64_t valid_flags) } } +#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) { uint64_t flags = 0; struct kvm_vm *vm; - size_t total_size; - int fd; - - total_size = page_size * 4; vm = vm_create_barebones_type(vm_type); @@ -276,24 +280,21 @@ 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, flags); - close(fd); kvm_vm_free(vm); } -- 2.51.0.536.g15c5d4f767-goog From: Ackerley Tng 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. test_guest_memfd_flags() tests valid flags, hence it can be run just once per VM type, and valid flag identification can be moved into the test function. Signed-off-by: Ackerley Tng [sean: use double-underscores for the inner helper] Signed-off-by: Sean Christopherson --- .../testing/selftests/kvm/guest_memfd_test.c | 30 ++++++++++++------- 1 file changed, 19 insertions(+), 11 deletions(-) diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 60c6dec63490..5a50a28ce1fa 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -239,11 +239,16 @@ 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 = 0; uint64_t flag; int fd; + if (vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_MMAP)) + valid_flags |= GUEST_MEMFD_FLAG_MMAP | + GUEST_MEMFD_FLAG_DEFAULT_SHARED; + for (flag = BIT(0); flag; flag <<= 1) { fd = __vm_create_guest_memfd(vm, page_size, flag); if (flag & valid_flags) { @@ -267,16 +272,8 @@ 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) { - uint64_t flags = 0; - struct kvm_vm *vm; - - vm = vm_create_barebones_type(vm_type); - - if (vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_MMAP)) - flags |= GUEST_MEMFD_FLAG_MMAP | GUEST_MEMFD_FLAG_DEFAULT_SHARED; - test_create_guest_memfd_multiple(vm); test_create_guest_memfd_invalid_sizes(vm, flags); @@ -292,8 +289,19 @@ 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); +} - test_guest_memfd_flags(vm, flags); +static void test_guest_memfd(unsigned long vm_type) +{ + struct kvm_vm *vm = vm_create_barebones_type(vm_type); + + test_guest_memfd_flags(vm); + + __test_guest_memfd(vm, 0); + + if (vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_MMAP)) + __test_guest_memfd(vm, GUEST_MEMFD_FLAG_MMAP | + GUEST_MEMFD_FLAG_DEFAULT_SHARED); kvm_vm_free(vm); } -- 2.51.0.536.g15c5d4f767-goog 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. Signed-off-by: Sean Christopherson --- .../testing/selftests/kvm/guest_memfd_test.c | 21 +++------ .../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 +-- .../selftests/kvm/s390/ucontrol_test.c | 16 +++---- .../selftests/kvm/set_memory_region_test.c | 17 ++++--- 6 files changed, 64 insertions(+), 64 deletions(-) diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 5a50a28ce1fa..5dd40b77dc07 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) @@ -347,10 +342,9 @@ static void test_guest_memfd_guest(void) GUEST_MEMFD_FLAG_DEFAULT_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); @@ -358,8 +352,7 @@ 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 23a506d7eca3..1c68ff0fb3fb 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -278,6 +278,31 @@ 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 c3f5142b0a54..da754b152c11 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -770,13 +770,11 @@ 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)); @@ -810,20 +808,16 @@ 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) @@ -1080,12 +1074,9 @@ 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), @@ -1156,12 +1147,10 @@ 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); @@ -1371,10 +1360,8 @@ 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: %i 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); @@ -1821,9 +1808,8 @@ 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); } -- 2.51.0.536.g15c5d4f767-goog 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. Cc: Ackerley Tng Signed-off-by: Sean Christopherson --- .../testing/selftests/kvm/guest_memfd_test.c | 62 ++++++++++++++----- 1 file changed, 46 insertions(+), 16 deletions(-) diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 5dd40b77dc07..b5a631aca933 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -40,17 +40,26 @@ static void test_file_read_write(int fd, size_t total_size) "pwrite on a guest_mem fd should fail"); } -static void test_mmap_supported(int fd, size_t total_size) +static void *test_mmap_common(int fd, size_t size) { - const char val = 0xaa; - char *mem; - size_t i; - int ret; + void *mem; - mem = mmap(NULL, total_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); + 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."); - mem = kvm_mmap(total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd); + mem = kvm_mmap(size, PROT_READ | PROT_WRITE, MAP_SHARED, fd); + + return mem; +} + +static void test_mmap_supported(int fd, size_t total_size) +{ + const char val = 0xaa; + char *mem; + size_t i; + int ret; + + mem = test_mmap_common(fd, total_size); memset(mem, val, total_size); for (i = 0; i < total_size; i++) @@ -78,31 +87,47 @@ void fault_sigbus_handler(int signum) siglongjmp(jmpbuf, 1); } -static void test_fault_overflow(int fd, size_t total_size) +static void *test_fault_sigbus(int fd, size_t 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; - size_t i; + void *mem; - mem = kvm_mmap(map_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd); + mem = test_mmap_common(fd, size); sigaction(SIGBUS, &sa_new, &sa_old); if (sigsetjmp(jmpbuf, 1) == 0) { - memset(mem, 0xaa, map_size); + memset(mem, 0xaa, size); TEST_ASSERT(false, "memset() should have triggered SIGBUS."); } sigaction(SIGBUS, &sa_old, NULL); + return mem; +} + +static void test_fault_overflow(int fd, size_t total_size) +{ + size_t map_size = total_size * 4; + const char val = 0xaa; + char *mem; + size_t i; + + mem = test_fault_sigbus(fd, map_size); + for (i = 0; i < total_size; i++) TEST_ASSERT_EQ(READ_ONCE(mem[i]), val); kvm_munmap(mem, map_size); } +static void test_fault_private(int fd, size_t total_size) +{ + void *mem = test_fault_sigbus(fd, total_size); + + kvm_munmap(mem, total_size); +} + static void test_mmap_not_supported(int fd, size_t total_size) { char *mem; @@ -274,9 +299,12 @@ 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) { + if (flags & GUEST_MEMFD_FLAG_MMAP && + flags & GUEST_MEMFD_FLAG_DEFAULT_SHARED) { gmem_test(mmap_supported, vm, flags); gmem_test(fault_overflow, vm, flags); + } else if (flags & GUEST_MEMFD_FLAG_MMAP) { + gmem_test(fault_private, vm, flags); } else { gmem_test(mmap_not_supported, vm, flags); } @@ -294,9 +322,11 @@ static void test_guest_memfd(unsigned long vm_type) __test_guest_memfd(vm, 0); - if (vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_MMAP)) + if (vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_MMAP)) { + __test_guest_memfd(vm, GUEST_MEMFD_FLAG_MMAP); __test_guest_memfd(vm, GUEST_MEMFD_FLAG_MMAP | GUEST_MEMFD_FLAG_DEFAULT_SHARED); + } kvm_vm_free(vm); } -- 2.51.0.536.g15c5d4f767-goog