Add support for registering private memory with kvm using KVM_SET_USER_MEMORY_REGION ioctl.
Helper function to query extended userspace mem region is introduced to allow memory conversion.
vm_mem_backing_src types is extended to contain additional guest memory source types to cover the cases where guest memory can be backed by both anonymous memory and restricted memfd.
Signed-off-by: Vishal Annapurve vannapurve@google.com --- .../selftests/kvm/include/kvm_util_base.h | 12 +++- .../testing/selftests/kvm/include/test_util.h | 4 ++ tools/testing/selftests/kvm/lib/kvm_util.c | 58 +++++++++++++++++-- tools/testing/selftests/kvm/lib/test_util.c | 12 ++++ 4 files changed, 79 insertions(+), 7 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index e42a09cd24a0..5e30f5b461bf 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -30,7 +30,10 @@ typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
struct userspace_mem_region { - struct kvm_userspace_memory_region region; + union { + struct kvm_userspace_memory_region region; + struct kvm_userspace_memory_region_ext region_ext; + }; struct sparsebit *unused_phy_pages; int fd; off_t offset; @@ -194,7 +197,7 @@ static inline bool kvm_has_cap(long cap)
#define kvm_do_ioctl(fd, cmd, arg) \ ({ \ - static_assert(!_IOC_SIZE(cmd) || sizeof(*arg) == _IOC_SIZE(cmd), ""); \ + static_assert(!_IOC_SIZE(cmd) || sizeof(*arg) >= _IOC_SIZE(cmd), ""); \ ioctl(fd, cmd, arg); \ })
@@ -382,6 +385,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot); + struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id); vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages); @@ -708,6 +712,10 @@ struct kvm_userspace_memory_region * kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end);
+struct kvm_userspace_memory_region_ext * +kvm_userspace_memory_region_ext_find(struct kvm_vm *vm, uint64_t start, + uint64_t end); + #define sync_global_to_guest(vm, g) ({ \ typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ memcpy(_p, &(g), sizeof(g)); \ diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index befc754ce9b3..140a61f68fe5 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -96,6 +96,8 @@ enum vm_mem_backing_src_type { VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB, VM_MEM_SRC_SHMEM, VM_MEM_SRC_SHARED_HUGETLB, + VM_MEM_SRC_ANONYMOUS_AND_RESTRICTED_MEMFD, + VM_MEM_SRC_ANON_HTLB2M_AND_RESTRICTED_MEMFD, NUM_SRC_TYPES, };
@@ -103,7 +105,9 @@ enum vm_mem_backing_src_type {
struct vm_mem_backing_src_alias { const char *name; + /* Flags applicable for normal host accessible guest memory */ uint32_t flag; + uint32_t need_restricted_memfd; };
#define MIN_RUN_DELAY_NS 200000UL diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index f1cb1627161f..5990250ec40b 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -31,6 +31,11 @@ int open_path_or_exit(const char *path, int flags) return fd; }
+static int memfd_restricted(unsigned int flags) +{ + return syscall(__NR_memfd_restricted, flags); +} + /* * Open KVM_DEV_PATH if available, otherwise exit the entire program. * @@ -519,6 +524,35 @@ __weak void vcpu_arch_free(struct kvm_vcpu *vcpu)
}
+/* + * KVM Userspace Memory Region Ext Find + * + * Input Args: + * vm - Virtual Machine + * start - Starting VM physical address + * end - Ending VM physical address, inclusive. + * + * Output Args: None + * + * Return: + * Pointer to overlapping ext region, NULL if no such region. + * + * Public interface to userspace_mem_region_find. Allows tests to look up + * the memslot datastructure for a given range of guest physical memory. + */ +struct kvm_userspace_memory_region_ext * +kvm_userspace_memory_region_ext_find(struct kvm_vm *vm, uint64_t start, + uint64_t end) +{ + struct userspace_mem_region *region; + + region = userspace_mem_region_find(vm, start, end); + if (!region) + return NULL; + + return ®ion->region_ext; +} + /* * VM VCPU Remove * @@ -818,6 +852,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, struct userspace_mem_region *region; size_t backing_src_pagesz = get_backing_src_pagesz(src_type); size_t alignment; + int restricted_memfd = -1;
TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages, "Number of guest pages is not compatible with the host. " @@ -915,14 +950,24 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
/* As needed perform madvise */ if ((src_type == VM_MEM_SRC_ANONYMOUS || - src_type == VM_MEM_SRC_ANONYMOUS_THP) && thp_configured()) { + src_type == VM_MEM_SRC_ANONYMOUS_THP || + src_type == VM_MEM_SRC_ANONYMOUS_AND_RESTRICTED_MEMFD) && + thp_configured()) { ret = madvise(region->host_mem, npages * vm->page_size, - src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE); + (src_type == VM_MEM_SRC_ANONYMOUS_THP) ? + MADV_HUGEPAGE : MADV_NOHUGEPAGE); TEST_ASSERT(ret == 0, "madvise failed, addr: %p length: 0x%lx src_type: %s", region->host_mem, npages * vm->page_size, vm_mem_backing_src_alias(src_type)->name); }
+ if (vm_mem_backing_src_alias(src_type)->need_restricted_memfd) { + restricted_memfd = memfd_restricted(0); + TEST_ASSERT(restricted_memfd != -1, + "Failed to create restricted memfd"); + flags |= KVM_MEM_PRIVATE; + } + region->unused_phy_pages = sparsebit_alloc(); sparsebit_set_num(region->unused_phy_pages, guest_paddr >> vm->page_shift, npages); @@ -931,13 +976,16 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, region->region.guest_phys_addr = guest_paddr; region->region.memory_size = npages * vm->page_size; region->region.userspace_addr = (uintptr_t) region->host_mem; - ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, ®ion->region); + region->region_ext.restricted_fd = restricted_memfd; + region->region_ext.restricted_offset = 0; + ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region_ext); TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" " rc: %i errno: %i\n" " slot: %u flags: 0x%x\n" - " guest_phys_addr: 0x%lx size: 0x%lx", + " guest_phys_addr: 0x%lx size: 0x%lx restricted fd: %d\n", ret, errno, slot, flags, - guest_paddr, (uint64_t) region->region.memory_size); + guest_paddr, (uint64_t) region->region.memory_size, + restricted_memfd);
/* Add to quick lookup data structures */ vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region); diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 6d23878bbfe1..ebbac8246016 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -254,6 +254,16 @@ const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i) */ .flag = MAP_SHARED, }, + [VM_MEM_SRC_ANONYMOUS_AND_RESTRICTED_MEMFD] = { + .name = "anonymous_and_restricted_memfd", + .flag = ANON_FLAGS, + .need_restricted_memfd = 1, + }, + [VM_MEM_SRC_ANON_HTLB2M_AND_RESTRICTED_MEMFD] = { + .name = "anonymous_hugetlb_2mb_and_restricted_memfd", + .flag = ANON_HUGE_FLAGS | MAP_HUGE_2MB, + .need_restricted_memfd = 1, + }, }; _Static_assert(ARRAY_SIZE(aliases) == NUM_SRC_TYPES, "Missing new backing src types?"); @@ -272,11 +282,13 @@ size_t get_backing_src_pagesz(uint32_t i) switch (i) { case VM_MEM_SRC_ANONYMOUS: case VM_MEM_SRC_SHMEM: + case VM_MEM_SRC_ANONYMOUS_AND_RESTRICTED_MEMFD: return getpagesize(); case VM_MEM_SRC_ANONYMOUS_THP: return get_trans_hugepagesz(); case VM_MEM_SRC_ANONYMOUS_HUGETLB: case VM_MEM_SRC_SHARED_HUGETLB: + case VM_MEM_SRC_ANON_HTLB2M_AND_RESTRICTED_MEMFD: return get_def_hugetlb_pagesz(); default: return MAP_HUGE_PAGE_SIZE(flag);